diff --git "a/training_log_2024.02.18_17.17.08.log" "b/training_log_2024.02.18_17.17.08.log"
new file mode 100644--- /dev/null
+++ "b/training_log_2024.02.18_17.17.08.log"
@@ -0,0 +1,67 @@
+wandb: Currently logged in as: laurence_r. Use `wandb login --relogin` to force relogin
+wandb: Tracking run with wandb version 0.16.3
+wandb: Run data is saved locally in /home/ubuntu/torchtune-colorful-llama/colorful/wandb/run-20240218_171717-bm22a3e4
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run lambent-monkey-9
+wandb: ⭐️ View project at https://wandb.ai/laurence_r/colorful-llama
+wandb: 🚀 View run at https://wandb.ai/laurence_r/colorful-llama/runs/bm22a3e4
+Setting manual seed to local seed 42. Local seed is seed + rank = 42 + 0
+Model is initialized. FSDP and Activation Checkpointing are enabled.
+Compiling model using torch.compile. The first batch may take a few minutes while compilation occurs.
+Tokenizer is initialized from file.
+Optimizer is initialized.
+Loss is initialized.
+
Downloading data files:   0%|          | 0/1 [00:00<?, ?it/s]
+
Downloading data:   0%|          | 0.00/186M [00:00<?, ?B/s]
+
Downloading data:   2%|▏         | 4.19M/186M [00:01<00:57, 3.19MB/s]
+
Downloading data:   7%|▋         | 12.6M/186M [00:01<00:21, 8.27MB/s]
+
Downloading data:  11%|█         | 21.0M/186M [00:02<00:13, 12.4MB/s]
+
Downloading data:  16%|█▌        | 29.4M/186M [00:02<00:10, 15.2MB/s]
+
Downloading data:  20%|██        | 37.7M/186M [00:02<00:08, 18.0MB/s]
+
Downloading data:  25%|██▍       | 46.1M/186M [00:03<00:06, 20.3MB/s]
+
Downloading data:  29%|██▉       | 54.5M/186M [00:03<00:06, 21.6MB/s]
+
Downloading data:  34%|███▎      | 62.9M/186M [00:03<00:05, 23.4MB/s]
+
Downloading data:  38%|███▊      | 71.3M/186M [00:04<00:04, 24.8MB/s]
+
Downloading data:  43%|████▎     | 79.7M/186M [00:04<00:03, 28.7MB/s]
+
Downloading data:  47%|████▋     | 88.1M/186M [00:04<00:03, 29.2MB/s]
+
Downloading data:  52%|█████▏    | 96.5M/186M [00:04<00:03, 29.9MB/s]
+
Downloading data:  56%|█████▌    | 105M/186M [00:05<00:02, 30.2MB/s] 
+
Downloading data:  61%|██████    | 113M/186M [00:05<00:02, 30.7MB/s]
+
Downloading data:  65%|██████▌   | 122M/186M [00:05<00:02, 29.9MB/s]
+
Downloading data:  70%|██████▉   | 130M/186M [00:05<00:01, 29.9MB/s]
+
Downloading data:  74%|███████▍  | 138M/186M [00:06<00:01, 29.3MB/s]
+
Downloading data:  79%|███████▊  | 147M/186M [00:06<00:01, 28.3MB/s]
+
Downloading data:  83%|████████▎ | 155M/186M [00:06<00:01, 28.6MB/s]
+
Downloading data:  88%|████████▊ | 164M/186M [00:07<00:00, 25.4MB/s]
+
Downloading data:  92%|█████████▏| 172M/186M [00:07<00:00, 26.3MB/s]
+
Downloading data:  97%|█████████▋| 180M/186M [00:07<00:00, 26.8MB/s]
+
Downloading data: 100%|██████████| 186M/186M [00:08<00:00, 26.2MB/s]
Downloading data: 100%|██████████| 186M/186M [00:08<00:00, 22.7MB/s]
+
Downloading data files: 100%|██████████| 1/1 [00:08<00:00,  8.22s/it]
Downloading data files: 100%|██████████| 1/1 [00:08<00:00,  8.22s/it]
+
Extracting data files:   0%|          | 0/1 [00:00<?, ?it/s]
Extracting data files: 100%|██████████| 1/1 [00:00<00:00, 355.63it/s]
+
Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 13161 examples [00:00, 91590.06 examples/s]
Generating train split: 38462 examples [00:00, 156458.86 examples/s]
Generating train split: 86244 examples [00:00, 217662.63 examples/s]
Generating train split: 121702 examples [00:00, 233392.14 examples/s]
Generating train split: 167642 examples [00:00, 245015.32 examples/s]
Generating train split: 207040 examples [00:00, 242881.85 examples/s]
Generating train split: 207040 examples [00:00, 224897.81 examples/s]
+Dataset and Sampler are initialized.
+
  0%|          | 0/25880 [00:00<?, ?it/s]
1|1|Loss: 1.6189237833023071:   0%|          | 0/25880 [00:44<?, ?it/s]
1|1|Loss: 1.6189237833023071:   0%|          | 1/25880 [01:16<550:29:06, 76.58s/it]
1|2|Loss: 1.4635165929794312:   0%|          | 1/25880 [02:52<550:29:06, 76.58s/it]
1|2|Loss: 1.4635165929794312:   0%|          | 2/25880 [02:53<635:33:19, 88.41s/it]
1|3|Loss: 1.7190390825271606:   0%|          | 2/25880 [02:53<635:33:19, 88.41s/it]
1|3|Loss: 1.7190390825271606:   0%|          | 3/25880 [02:53<347:41:24, 48.37s/it]
1|4|Loss: 7.297624111175537:   0%|          | 3/25880 [02:54<347:41:24, 48.37s/it] 
1|4|Loss: 7.297624111175537:   0%|          | 4/25880 [02:54<212:25:59, 29.55s/it]
1|5|Loss: 8.567079544067383:   0%|          | 4/25880 [02:55<212:25:59, 29.55s/it]
1|5|Loss: 8.567079544067383:   0%|          | 5/25880 [02:55<137:39:47, 19.15s/it]
1|6|Loss: 8.806475639343262:   0%|          | 5/25880 [02:55<137:39:47, 19.15s/it]
1|6|Loss: 8.806475639343262:   0%|          | 6/25880 [02:56<92:25:16, 12.86s/it] 
1|7|Loss: 8.510991096496582:   0%|          | 6/25880 [02:56<92:25:16, 12.86s/it]
1|7|Loss: 8.510991096496582:   0%|          | 7/25880 [02:56<64:03:55,  8.91s/it]
1|8|Loss: 7.993319511413574:   0%|          | 7/25880 [02:57<64:03:55,  8.91s/it]
1|8|Loss: 7.993319511413574:   0%|          | 8/25880 [02:57<44:58:22,  6.26s/it]
1|9|Loss: 8.005261421203613:   0%|          | 8/25880 [02:57<44:58:22,  6.26s/it]
1|9|Loss: 8.005261421203613:   0%|          | 9/25880 [02:58<32:32:28,  4.53s/it]
1|10|Loss: 8.179129600524902:   0%|          | 9/25880 [02:58<32:32:28,  4.53s/it]
1|10|Loss: 8.179129600524902:   0%|          | 10/25880 [02:58<24:13:31,  3.37s/it]
1|11|Loss: 8.131758689880371:   0%|          | 10/25880 [02:59<24:13:31,  3.37s/it]
1|11|Loss: 8.131758689880371:   0%|          | 11/25880 [02:59<18:37:10,  2.59s/it]
1|12|Loss: 7.988627910614014:   0%|          | 11/25880 [03:00<18:37:10,  2.59s/it]
1|12|Loss: 7.988627910614014:   0%|          | 12/25880 [03:00<14:31:53,  2.02s/it]
1|13|Loss: 7.830815315246582:   0%|          | 12/25880 [03:00<14:31:53,  2.02s/it]
1|13|Loss: 7.830815315246582:   0%|          | 13/25880 [03:01<11:36:45,  1.62s/it]
1|14|Loss: 7.8411359786987305:   0%|          | 13/25880 [03:01<11:36:45,  1.62s/it]
1|14|Loss: 7.8411359786987305:   0%|          | 14/25880 [03:01<9:39:26,  1.34s/it] 
1|15|Loss: 7.741610527038574:   0%|          | 14/25880 [03:02<9:39:26,  1.34s/it] 
1|15|Loss: 7.741610527038574:   0%|          | 15/25880 [03:02<8:31:07,  1.19s/it]
1|16|Loss: 7.7096171379089355:   0%|          | 15/25880 [03:03<8:31:07,  1.19s/it]
1|16|Loss: 7.7096171379089355:   0%|          | 16/25880 [03:03<7:34:57,  1.06s/it]
1|17|Loss: 7.825934410095215:   0%|          | 16/25880 [03:03<7:34:57,  1.06s/it] 
1|17|Loss: 7.825934410095215:   0%|          | 17/25880 [03:04<7:15:26,  1.01s/it]
1|18|Loss: 7.804837226867676:   0%|          | 17/25880 [03:04<7:15:26,  1.01s/it]
1|18|Loss: 7.804837226867676:   0%|          | 18/25880 [03:05<6:34:37,  1.09it/s]
1|19|Loss: 7.264381408691406:   0%|          | 18/25880 [03:05<6:34:37,  1.09it/s]
1|19|Loss: 7.264381408691406:   0%|          | 19/25880 [03:05<5:57:58,  1.20it/s]
1|20|Loss: 7.580247402191162:   0%|          | 19/25880 [03:06<5:57:58,  1.20it/s]
1|20|Loss: 7.580247402191162:   0%|          | 20/25880 [03:06<5:42:06,  1.26it/s]
1|21|Loss: 7.665025234222412:   0%|          | 20/25880 [03:06<5:42:06,  1.26it/s]
1|21|Loss: 7.665025234222412:   0%|          | 21/25880 [03:07<6:09:59,  1.16it/s]
1|22|Loss: 7.358685493469238:   0%|          | 21/25880 [03:07<6:09:59,  1.16it/s]
1|22|Loss: 7.358685493469238:   0%|          | 22/25880 [03:08<6:09:00,  1.17it/s]
1|23|Loss: 7.289007186889648:   0%|          | 22/25880 [03:08<6:09:00,  1.17it/s]
1|23|Loss: 7.289007186889648:   0%|          | 23/25880 [03:09<6:02:52,  1.19it/s]
1|24|Loss: 7.477937698364258:   0%|          | 23/25880 [03:09<6:02:52,  1.19it/s]
1|24|Loss: 7.477937698364258:   0%|          | 24/25880 [03:09<5:27:28,  1.32it/s]
1|25|Loss: 7.293649673461914:   0%|          | 24/25880 [03:09<5:27:28,  1.32it/s]
1|25|Loss: 7.293649673461914:   0%|          | 25/25880 [03:10<5:07:27,  1.40it/s]
1|26|Loss: 7.558351516723633:   0%|          | 25/25880 [03:10<5:07:27,  1.40it/s]
1|26|Loss: 7.558351516723633:   0%|          | 26/25880 [03:10<5:07:51,  1.40it/s]
1|27|Loss: 7.403083324432373:   0%|          | 26/25880 [03:11<5:07:51,  1.40it/s]
1|27|Loss: 7.403083324432373:   0%|          | 27/25880 [03:11<5:28:19,  1.31it/s]
1|28|Loss: 7.395740509033203:   0%|          | 27/25880 [03:12<5:28:19,  1.31it/s]
1|28|Loss: 7.395740509033203:   0%|          | 28/25880 [03:12<5:42:00,  1.26it/s]
1|29|Loss: 7.292909145355225:   0%|          | 28/25880 [03:13<5:42:00,  1.26it/s]
1|29|Loss: 7.292909145355225:   0%|          | 29/25880 [03:13<5:37:48,  1.28it/s]
1|30|Loss: 7.48308801651001:   0%|          | 29/25880 [03:13<5:37:48,  1.28it/s] 
1|30|Loss: 7.48308801651001:   0%|          | 30/25880 [03:14<5:35:48,  1.28it/s]
1|31|Loss: 7.233065605163574:   0%|          | 30/25880 [03:14<5:35:48,  1.28it/s]
1|31|Loss: 7.233065605163574:   0%|          | 31/25880 [03:15<5:57:21,  1.21it/s]
1|32|Loss: 7.055250644683838:   0%|          | 31/25880 [03:15<5:57:21,  1.21it/s]
1|32|Loss: 7.055250644683838:   0%|          | 32/25880 [03:15<5:53:02,  1.22it/s]
1|33|Loss: 7.056478023529053:   0%|          | 32/25880 [03:16<5:53:02,  1.22it/s]
1|33|Loss: 7.056478023529053:   0%|          | 33/25880 [03:16<5:37:57,  1.27it/s]
1|34|Loss: 6.900900363922119:   0%|          | 33/25880 [03:17<5:37:57,  1.27it/s]
1|34|Loss: 6.900900363922119:   0%|          | 34/25880 [03:17<5:34:01,  1.29it/s]
1|35|Loss: 7.00109338760376:   0%|          | 34/25880 [03:17<5:34:01,  1.29it/s] 
1|35|Loss: 7.00109338760376:   0%|          | 35/25880 [03:18<5:40:27,  1.27it/s]
1|36|Loss: 7.100080966949463:   0%|          | 35/25880 [03:18<5:40:27,  1.27it/s]
1|36|Loss: 7.100080966949463:   0%|          | 36/25880 [03:19<5:50:03,  1.23it/s]
1|37|Loss: 6.8619279861450195:   0%|          | 36/25880 [03:19<5:50:03,  1.23it/s]
1|37|Loss: 6.8619279861450195:   0%|          | 37/25880 [03:19<5:43:49,  1.25it/s]
1|38|Loss: 6.689570426940918:   0%|          | 37/25880 [03:20<5:43:49,  1.25it/s] 
1|38|Loss: 6.689570426940918:   0%|          | 38/25880 [03:20<5:46:05,  1.24it/s]
1|39|Loss: 6.839043617248535:   0%|          | 38/25880 [03:21<5:46:05,  1.24it/s]
1|39|Loss: 6.839043617248535:   0%|          | 39/25880 [03:21<5:46:25,  1.24it/s]
1|40|Loss: 6.83236026763916:   0%|          | 39/25880 [03:21<5:46:25,  1.24it/s] 
1|40|Loss: 6.83236026763916:   0%|          | 40/25880 [03:22<5:37:17,  1.28it/s]
1|41|Loss: 6.846078395843506:   0%|          | 40/25880 [03:22<5:37:17,  1.28it/s]
1|41|Loss: 6.846078395843506:   0%|          | 41/25880 [03:22<5:29:56,  1.31it/s]
1|42|Loss: 6.644481182098389:   0%|          | 41/25880 [03:23<5:29:56,  1.31it/s]
1|42|Loss: 6.644481182098389:   0%|          | 42/25880 [03:23<5:25:20,  1.32it/s]
1|43|Loss: 6.862645626068115:   0%|          | 42/25880 [03:24<5:25:20,  1.32it/s]
1|43|Loss: 6.862645626068115:   0%|          | 43/25880 [03:24<5:39:16,  1.27it/s]
1|44|Loss: 6.8582892417907715:   0%|          | 43/25880 [03:24<5:39:16,  1.27it/s]
1|44|Loss: 6.8582892417907715:   0%|          | 44/25880 [03:25<5:36:07,  1.28it/s]
1|45|Loss: 6.727705478668213:   0%|          | 44/25880 [03:25<5:36:07,  1.28it/s] 
1|45|Loss: 6.727705478668213:   0%|          | 45/25880 [03:26<5:39:43,  1.27it/s]
1|46|Loss: 6.710517883300781:   0%|          | 45/25880 [03:26<5:39:43,  1.27it/s]
1|46|Loss: 6.710517883300781:   0%|          | 46/25880 [03:26<5:43:46,  1.25it/s]
1|47|Loss: 6.489753246307373:   0%|          | 46/25880 [03:27<5:43:46,  1.25it/s]
1|47|Loss: 6.489753246307373:   0%|          | 47/25880 [03:27<5:38:02,  1.27it/s]
1|48|Loss: 6.976580619812012:   0%|          | 47/25880 [03:28<5:38:02,  1.27it/s]
1|48|Loss: 6.976580619812012:   0%|          | 48/25880 [03:28<5:21:57,  1.34it/s]
1|49|Loss: 6.979588985443115:   0%|          | 48/25880 [03:28<5:21:57,  1.34it/s]
1|49|Loss: 6.979588985443115:   0%|          | 49/25880 [03:29<5:17:12,  1.36it/s]
1|50|Loss: 6.605827331542969:   0%|          | 49/25880 [03:29<5:17:12,  1.36it/s]
1|50|Loss: 6.605827331542969:   0%|          | 50/25880 [03:29<5:17:18,  1.36it/s]
1|51|Loss: 6.51882791519165:   0%|          | 50/25880 [03:30<5:17:18,  1.36it/s] 
1|51|Loss: 6.51882791519165:   0%|          | 51/25880 [03:30<4:57:44,  1.45it/s]
1|52|Loss: 6.507877826690674:   0%|          | 51/25880 [03:30<4:57:44,  1.45it/s]
1|52|Loss: 6.507877826690674:   0%|          | 52/25880 [03:31<4:56:07,  1.45it/s]
1|53|Loss: 6.632955074310303:   0%|          | 52/25880 [03:31<4:56:07,  1.45it/s]
1|53|Loss: 6.632955074310303:   0%|          | 53/25880 [03:31<5:11:01,  1.38it/s]
1|54|Loss: 6.818670272827148:   0%|          | 53/25880 [03:32<5:11:01,  1.38it/s]
1|54|Loss: 6.818670272827148:   0%|          | 54/25880 [03:32<5:16:02,  1.36it/s]
1|55|Loss: 6.473268032073975:   0%|          | 54/25880 [03:32<5:16:02,  1.36it/s]
1|55|Loss: 6.473268032073975:   0%|          | 55/25880 [03:33<4:47:02,  1.50it/s]
1|56|Loss: 6.528707027435303:   0%|          | 55/25880 [03:33<4:47:02,  1.50it/s]
1|56|Loss: 6.528707027435303:   0%|          | 56/25880 [03:33<4:35:16,  1.56it/s]
1|57|Loss: 6.483237266540527:   0%|          | 56/25880 [03:34<4:35:16,  1.56it/s]
1|57|Loss: 6.483237266540527:   0%|          | 57/25880 [03:34<4:31:35,  1.58it/s]
1|58|Loss: 6.322371482849121:   0%|          | 57/25880 [03:34<4:31:35,  1.58it/s]
1|58|Loss: 6.322371482849121:   0%|          | 58/25880 [03:34<4:20:12,  1.65it/s]
1|59|Loss: 6.4945454597473145:   0%|          | 58/25880 [03:35<4:20:12,  1.65it/s]
1|59|Loss: 6.4945454597473145:   0%|          | 59/25880 [03:35<4:21:28,  1.65it/s]
1|60|Loss: 6.099616527557373:   0%|          | 59/25880 [03:35<4:21:28,  1.65it/s] 
1|60|Loss: 6.099616527557373:   0%|          | 60/25880 [03:36<4:31:08,  1.59it/s]
1|61|Loss: 6.398651599884033:   0%|          | 60/25880 [03:36<4:31:08,  1.59it/s]
1|61|Loss: 6.398651599884033:   0%|          | 61/25880 [03:36<4:19:24,  1.66it/s]
1|62|Loss: 6.514331817626953:   0%|          | 61/25880 [03:37<4:19:24,  1.66it/s]
1|62|Loss: 6.514331817626953:   0%|          | 62/25880 [03:37<4:20:13,  1.65it/s]
1|63|Loss: 6.396385669708252:   0%|          | 62/25880 [03:37<4:20:13,  1.65it/s]
1|63|Loss: 6.396385669708252:   0%|          | 63/25880 [03:37<4:23:52,  1.63it/s]
1|64|Loss: 6.636843204498291:   0%|          | 63/25880 [03:38<4:23:52,  1.63it/s]
1|64|Loss: 6.636843204498291:   0%|          | 64/25880 [03:38<4:51:16,  1.48it/s]
1|65|Loss: 6.26609992980957:   0%|          | 64/25880 [03:39<4:51:16,  1.48it/s] 
1|65|Loss: 6.26609992980957:   0%|          | 65/25880 [03:39<4:58:24,  1.44it/s]
1|66|Loss: 6.520472526550293:   0%|          | 65/25880 [03:39<4:58:24,  1.44it/s]
1|66|Loss: 6.520472526550293:   0%|          | 66/25880 [03:40<5:01:48,  1.43it/s]
1|67|Loss: 6.401865005493164:   0%|          | 66/25880 [03:40<5:01:48,  1.43it/s]
1|67|Loss: 6.401865005493164:   0%|          | 67/25880 [03:40<4:55:07,  1.46it/s]
1|68|Loss: 6.5466628074646:   0%|          | 67/25880 [03:41<4:55:07,  1.46it/s]  
1|68|Loss: 6.5466628074646:   0%|          | 68/25880 [03:41<5:12:23,  1.38it/s]
1|69|Loss: 6.390771389007568:   0%|          | 68/25880 [03:42<5:12:23,  1.38it/s]
1|69|Loss: 6.390771389007568:   0%|          | 69/25880 [03:42<5:15:37,  1.36it/s]
1|70|Loss: 6.417642593383789:   0%|          | 69/25880 [03:42<5:15:37,  1.36it/s]
1|70|Loss: 6.417642593383789:   0%|          | 70/25880 [03:43<5:28:32,  1.31it/s]
1|71|Loss: 6.104414463043213:   0%|          | 70/25880 [03:43<5:28:32,  1.31it/s]
1|71|Loss: 6.104414463043213:   0%|          | 71/25880 [03:44<5:24:45,  1.32it/s]
1|72|Loss: 6.178647518157959:   0%|          | 71/25880 [03:44<5:24:45,  1.32it/s]
1|72|Loss: 6.178647518157959:   0%|          | 72/25880 [03:44<5:10:04,  1.39it/s]
1|73|Loss: 6.187547206878662:   0%|          | 72/25880 [03:45<5:10:04,  1.39it/s]
1|73|Loss: 6.187547206878662:   0%|          | 73/25880 [03:45<4:56:38,  1.45it/s]
1|74|Loss: 6.469612121582031:   0%|          | 73/25880 [03:45<4:56:38,  1.45it/s]
1|74|Loss: 6.469612121582031:   0%|          | 74/25880 [03:45<4:56:33,  1.45it/s]
1|75|Loss: 6.54509973526001:   0%|          | 74/25880 [03:46<4:56:33,  1.45it/s] 
1|75|Loss: 6.54509973526001:   0%|          | 75/25880 [03:46<4:48:40,  1.49it/s]
1|76|Loss: 6.217597007751465:   0%|          | 75/25880 [03:46<4:48:40,  1.49it/s]
1|76|Loss: 6.217597007751465:   0%|          | 76/25880 [03:47<4:52:05,  1.47it/s]
1|77|Loss: 6.402005672454834:   0%|          | 76/25880 [03:47<4:52:05,  1.47it/s]
1|77|Loss: 6.402005672454834:   0%|          | 77/25880 [03:47<4:46:50,  1.50it/s]
1|78|Loss: 6.269653797149658:   0%|          | 77/25880 [03:48<4:46:50,  1.50it/s]
1|78|Loss: 6.269653797149658:   0%|          | 78/25880 [03:48<4:53:20,  1.47it/s]
1|79|Loss: 5.996307373046875:   0%|          | 78/25880 [03:49<4:53:20,  1.47it/s]
1|79|Loss: 5.996307373046875:   0%|          | 79/25880 [03:49<4:50:05,  1.48it/s]
1|80|Loss: 6.506973743438721:   0%|          | 79/25880 [03:49<4:50:05,  1.48it/s]
1|80|Loss: 6.506973743438721:   0%|          | 80/25880 [03:50<4:55:35,  1.45it/s]
1|81|Loss: 6.306725025177002:   0%|          | 80/25880 [03:50<4:55:35,  1.45it/s]
1|81|Loss: 6.306725025177002:   0%|          | 81/25880 [03:50<5:01:59,  1.42it/s]
1|82|Loss: 6.076608180999756:   0%|          | 81/25880 [03:51<5:01:59,  1.42it/s]
1|82|Loss: 6.076608180999756:   0%|          | 82/25880 [03:51<5:12:08,  1.38it/s]
1|83|Loss: 6.3785529136657715:   0%|          | 82/25880 [03:51<5:12:08,  1.38it/s]
1|83|Loss: 6.3785529136657715:   0%|          | 83/25880 [03:52<5:02:58,  1.42it/s]
1|84|Loss: 6.299357891082764:   0%|          | 83/25880 [03:52<5:02:58,  1.42it/s] 
1|84|Loss: 6.299357891082764:   0%|          | 84/25880 [03:52<5:10:52,  1.38it/s]
1|85|Loss: 6.128448486328125:   0%|          | 84/25880 [03:53<5:10:52,  1.38it/s]
1|85|Loss: 6.128448486328125:   0%|          | 85/25880 [03:53<5:02:36,  1.42it/s]
1|86|Loss: 6.252144813537598:   0%|          | 85/25880 [03:54<5:02:36,  1.42it/s]
1|86|Loss: 6.252144813537598:   0%|          | 86/25880 [03:54<5:21:31,  1.34it/s]
1|87|Loss: 5.971617698669434:   0%|          | 86/25880 [03:54<5:21:31,  1.34it/s]
1|87|Loss: 5.971617698669434:   0%|          | 87/25880 [03:55<5:11:37,  1.38it/s]
1|88|Loss: 6.167088985443115:   0%|          | 87/25880 [03:55<5:11:37,  1.38it/s]
1|88|Loss: 6.167088985443115:   0%|          | 88/25880 [03:55<4:56:59,  1.45it/s]
1|89|Loss: 6.144532680511475:   0%|          | 88/25880 [03:56<4:56:59,  1.45it/s]
1|89|Loss: 6.144532680511475:   0%|          | 89/25880 [03:56<5:10:11,  1.39it/s]
1|90|Loss: 6.463816165924072:   0%|          | 89/25880 [03:56<5:10:11,  1.39it/s]
1|90|Loss: 6.463816165924072:   0%|          | 90/25880 [03:57<5:15:40,  1.36it/s]
1|91|Loss: 5.976506233215332:   0%|          | 90/25880 [03:57<5:15:40,  1.36it/s]
1|91|Loss: 5.976506233215332:   0%|          | 91/25880 [03:58<5:12:56,  1.37it/s]
1|92|Loss: 6.1742353439331055:   0%|          | 91/25880 [03:58<5:12:56,  1.37it/s]
1|92|Loss: 6.1742353439331055:   0%|          | 92/25880 [03:58<5:24:51,  1.32it/s]
1|93|Loss: 5.7681565284729:   0%|          | 92/25880 [03:59<5:24:51,  1.32it/s]   
1|93|Loss: 5.7681565284729:   0%|          | 93/25880 [03:59<5:12:34,  1.37it/s]
1|94|Loss: 6.035353183746338:   0%|          | 93/25880 [03:59<5:12:34,  1.37it/s]
1|94|Loss: 6.035353183746338:   0%|          | 94/25880 [04:00<5:15:09,  1.36it/s]
1|95|Loss: 6.039645671844482:   0%|          | 94/25880 [04:00<5:15:09,  1.36it/s]
1|95|Loss: 6.039645671844482:   0%|          | 95/25880 [04:01<5:26:15,  1.32it/s]
1|96|Loss: 5.514318466186523:   0%|          | 95/25880 [04:01<5:26:15,  1.32it/s]
1|96|Loss: 5.514318466186523:   0%|          | 96/25880 [04:01<5:42:01,  1.26it/s]
1|97|Loss: 6.302941799163818:   0%|          | 96/25880 [04:02<5:42:01,  1.26it/s]
1|97|Loss: 6.302941799163818:   0%|          | 97/25880 [04:02<5:56:15,  1.21it/s]
1|98|Loss: 5.822192192077637:   0%|          | 97/25880 [04:03<5:56:15,  1.21it/s]
1|98|Loss: 5.822192192077637:   0%|          | 98/25880 [04:03<5:47:16,  1.24it/s]
1|99|Loss: 5.831696510314941:   0%|          | 98/25880 [04:03<5:47:16,  1.24it/s]
1|99|Loss: 5.831696510314941:   0%|          | 99/25880 [04:04<5:24:56,  1.32it/s]
1|100|Loss: 6.006572246551514:   0%|          | 99/25880 [04:04<5:24:56,  1.32it/s]
1|100|Loss: 6.006572246551514:   0%|          | 100/25880 [04:05<5:28:06,  1.31it/s]
1|101|Loss: 6.069943428039551:   0%|          | 100/25880 [04:05<5:28:06,  1.31it/s]
1|101|Loss: 6.069943428039551:   0%|          | 101/25880 [04:05<5:26:09,  1.32it/s]
1|102|Loss: 6.048723220825195:   0%|          | 101/25880 [04:06<5:26:09,  1.32it/s]
1|102|Loss: 6.048723220825195:   0%|          | 102/25880 [04:06<5:22:52,  1.33it/s]
1|103|Loss: 5.960394382476807:   0%|          | 102/25880 [04:06<5:22:52,  1.33it/s]
1|103|Loss: 5.960394382476807:   0%|          | 103/25880 [04:07<5:20:09,  1.34it/s]
1|104|Loss: 5.785750389099121:   0%|          | 103/25880 [04:07<5:20:09,  1.34it/s]
1|104|Loss: 5.785750389099121:   0%|          | 104/25880 [04:07<5:18:01,  1.35it/s]
1|105|Loss: 6.059625148773193:   0%|          | 104/25880 [04:08<5:18:01,  1.35it/s]
1|105|Loss: 6.059625148773193:   0%|          | 105/25880 [04:08<5:05:16,  1.41it/s]
1|106|Loss: 6.014830589294434:   0%|          | 105/25880 [04:08<5:05:16,  1.41it/s]
1|106|Loss: 6.014830589294434:   0%|          | 106/25880 [04:09<5:01:14,  1.43it/s]
1|107|Loss: 5.9515380859375:   0%|          | 106/25880 [04:09<5:01:14,  1.43it/s]  
1|107|Loss: 5.9515380859375:   0%|          | 107/25880 [04:10<5:18:41,  1.35it/s]
1|108|Loss: 5.878164291381836:   0%|          | 107/25880 [04:10<5:18:41,  1.35it/s]
1|108|Loss: 5.878164291381836:   0%|          | 108/25880 [04:10<5:22:16,  1.33it/s]
1|109|Loss: 6.064287185668945:   0%|          | 108/25880 [04:11<5:22:16,  1.33it/s]
1|109|Loss: 6.064287185668945:   0%|          | 109/25880 [04:11<5:32:05,  1.29it/s]
1|110|Loss: 5.7613630294799805:   0%|          | 109/25880 [04:12<5:32:05,  1.29it/s]
1|110|Loss: 5.7613630294799805:   0%|          | 110/25880 [04:12<5:20:48,  1.34it/s]
1|111|Loss: 5.9643096923828125:   0%|          | 110/25880 [04:12<5:20:48,  1.34it/s]
1|111|Loss: 5.9643096923828125:   0%|          | 111/25880 [04:13<5:17:35,  1.35it/s]
1|112|Loss: 5.7486090660095215:   0%|          | 111/25880 [04:13<5:17:35,  1.35it/s]
1|112|Loss: 5.7486090660095215:   0%|          | 112/25880 [04:13<4:53:56,  1.46it/s]
1|113|Loss: 5.831186294555664:   0%|          | 112/25880 [04:14<4:53:56,  1.46it/s] 
1|113|Loss: 5.831186294555664:   0%|          | 113/25880 [04:14<5:05:37,  1.41it/s]
1|114|Loss: 5.779508590698242:   0%|          | 113/25880 [04:14<5:05:37,  1.41it/s]
1|114|Loss: 5.779508590698242:   0%|          | 114/25880 [04:15<5:24:45,  1.32it/s]
1|115|Loss: 5.580003261566162:   0%|          | 114/25880 [04:15<5:24:45,  1.32it/s]
1|115|Loss: 5.580003261566162:   0%|          | 115/25880 [04:16<5:26:12,  1.32it/s]
1|116|Loss: 5.595301151275635:   0%|          | 115/25880 [04:16<5:26:12,  1.32it/s]
1|116|Loss: 5.595301151275635:   0%|          | 116/25880 [04:16<4:57:52,  1.44it/s]
1|117|Loss: 5.628389835357666:   0%|          | 116/25880 [04:16<4:57:52,  1.44it/s]
1|117|Loss: 5.628389835357666:   0%|          | 117/25880 [04:17<4:45:57,  1.50it/s]
1|118|Loss: 5.624180316925049:   0%|          | 117/25880 [04:17<4:45:57,  1.50it/s]
1|118|Loss: 5.624180316925049:   0%|          | 118/25880 [04:17<4:39:13,  1.54it/s]
1|119|Loss: 5.845114231109619:   0%|          | 118/25880 [04:18<4:39:13,  1.54it/s]
1|119|Loss: 5.845114231109619:   0%|          | 119/25880 [04:18<4:36:07,  1.55it/s]
1|120|Loss: 6.147150993347168:   0%|          | 119/25880 [04:18<4:36:07,  1.55it/s]
1|120|Loss: 6.147150993347168:   0%|          | 120/25880 [04:19<4:54:50,  1.46it/s]
1|121|Loss: 5.6989521980285645:   0%|          | 120/25880 [04:19<4:54:50,  1.46it/s]
1|121|Loss: 5.6989521980285645:   0%|          | 121/25880 [04:19<4:33:29,  1.57it/s]
1|122|Loss: 6.3864970207214355:   0%|          | 121/25880 [04:20<4:33:29,  1.57it/s]
1|122|Loss: 6.3864970207214355:   0%|          | 122/25880 [04:20<4:25:36,  1.62it/s]
1|123|Loss: 6.464258193969727:   0%|          | 122/25880 [04:20<4:25:36,  1.62it/s] 
1|123|Loss: 6.464258193969727:   0%|          | 123/25880 [04:21<4:42:44,  1.52it/s]
1|124|Loss: 6.016910076141357:   0%|          | 123/25880 [04:21<4:42:44,  1.52it/s]
1|124|Loss: 6.016910076141357:   0%|          | 124/25880 [04:21<5:09:59,  1.38it/s]
1|125|Loss: 5.783874034881592:   0%|          | 124/25880 [04:22<5:09:59,  1.38it/s]
1|125|Loss: 5.783874034881592:   0%|          | 125/25880 [04:22<5:05:55,  1.40it/s]
1|126|Loss: 5.910680770874023:   0%|          | 125/25880 [04:23<5:05:55,  1.40it/s]
1|126|Loss: 5.910680770874023:   0%|          | 126/25880 [04:23<5:02:05,  1.42it/s]
1|127|Loss: 5.901681900024414:   0%|          | 126/25880 [04:23<5:02:05,  1.42it/s]
1|127|Loss: 5.901681900024414:   0%|          | 127/25880 [04:24<5:13:56,  1.37it/s]
1|128|Loss: 5.7599778175354:   0%|          | 127/25880 [04:24<5:13:56,  1.37it/s]  
1|128|Loss: 5.7599778175354:   0%|          | 128/25880 [04:24<5:03:49,  1.41it/s]
1|129|Loss: 5.688137531280518:   0%|          | 128/25880 [04:25<5:03:49,  1.41it/s]
1|129|Loss: 5.688137531280518:   0%|          | 129/25880 [04:25<5:01:02,  1.43it/s]
1|130|Loss: 5.696972370147705:   0%|          | 129/25880 [04:25<5:01:02,  1.43it/s]
1|130|Loss: 5.696972370147705:   1%|          | 130/25880 [04:25<4:34:50,  1.56it/s]
1|131|Loss: 5.486574172973633:   1%|          | 130/25880 [04:26<4:34:50,  1.56it/s]
1|131|Loss: 5.486574172973633:   1%|          | 131/25880 [04:26<4:22:33,  1.63it/s]
1|132|Loss: 5.6710991859436035:   1%|          | 131/25880 [04:26<4:22:33,  1.63it/s]
1|132|Loss: 5.6710991859436035:   1%|          | 132/25880 [04:27<4:47:48,  1.49it/s]
1|133|Loss: 5.730915069580078:   1%|          | 132/25880 [04:27<4:47:48,  1.49it/s] 
1|133|Loss: 5.730915069580078:   1%|          | 133/25880 [04:28<5:15:25,  1.36it/s]
1|134|Loss: 5.687467575073242:   1%|          | 133/25880 [04:28<5:15:25,  1.36it/s]
1|134|Loss: 5.687467575073242:   1%|          | 134/25880 [04:28<5:10:03,  1.38it/s]
1|135|Loss: 5.870349407196045:   1%|          | 134/25880 [04:29<5:10:03,  1.38it/s]
1|135|Loss: 5.870349407196045:   1%|          | 135/25880 [04:29<5:08:17,  1.39it/s]
1|136|Loss: 5.77703857421875:   1%|          | 135/25880 [04:30<5:08:17,  1.39it/s] 
1|136|Loss: 5.77703857421875:   1%|          | 136/25880 [04:30<5:15:00,  1.36it/s]
1|137|Loss: 6.022048473358154:   1%|          | 136/25880 [04:30<5:15:00,  1.36it/s]
1|137|Loss: 6.022048473358154:   1%|          | 137/25880 [04:31<5:21:54,  1.33it/s]
1|138|Loss: 5.721133232116699:   1%|          | 137/25880 [04:31<5:21:54,  1.33it/s]
1|138|Loss: 5.721133232116699:   1%|          | 138/25880 [04:31<5:19:02,  1.34it/s]
1|139|Loss: 5.600251197814941:   1%|          | 138/25880 [04:32<5:19:02,  1.34it/s]
1|139|Loss: 5.600251197814941:   1%|          | 139/25880 [04:32<5:03:46,  1.41it/s]
1|140|Loss: 5.798006057739258:   1%|          | 139/25880 [04:32<5:03:46,  1.41it/s]
1|140|Loss: 5.798006057739258:   1%|          | 140/25880 [04:33<5:09:18,  1.39it/s]
1|141|Loss: 5.681280136108398:   1%|          | 140/25880 [04:33<5:09:18,  1.39it/s]
1|141|Loss: 5.681280136108398:   1%|          | 141/25880 [04:34<5:09:00,  1.39it/s]
1|142|Loss: 5.6219682693481445:   1%|          | 141/25880 [04:34<5:09:00,  1.39it/s]
1|142|Loss: 5.6219682693481445:   1%|          | 142/25880 [04:34<5:28:23,  1.31it/s]
1|143|Loss: 5.588465213775635:   1%|          | 142/25880 [04:35<5:28:23,  1.31it/s] 
1|143|Loss: 5.588465213775635:   1%|          | 143/25880 [04:35<5:29:59,  1.30it/s]
1|144|Loss: 5.428513050079346:   1%|          | 143/25880 [04:36<5:29:59,  1.30it/s]
1|144|Loss: 5.428513050079346:   1%|          | 144/25880 [04:36<5:14:10,  1.37it/s]
1|145|Loss: 5.567978858947754:   1%|          | 144/25880 [04:36<5:14:10,  1.37it/s]
1|145|Loss: 5.567978858947754:   1%|          | 145/25880 [04:36<5:00:54,  1.43it/s]
1|146|Loss: 5.661673545837402:   1%|          | 145/25880 [04:37<5:00:54,  1.43it/s]
1|146|Loss: 5.661673545837402:   1%|          | 146/25880 [04:37<5:17:33,  1.35it/s]
1|147|Loss: 5.295879364013672:   1%|          | 146/25880 [04:38<5:17:33,  1.35it/s]
1|147|Loss: 5.295879364013672:   1%|          | 147/25880 [04:38<5:21:21,  1.33it/s]
1|148|Loss: 5.410964488983154:   1%|          | 147/25880 [04:38<5:21:21,  1.33it/s]
1|148|Loss: 5.410964488983154:   1%|          | 148/25880 [04:39<5:16:21,  1.36it/s]
1|149|Loss: 5.348210334777832:   1%|          | 148/25880 [04:39<5:16:21,  1.36it/s]
1|149|Loss: 5.348210334777832:   1%|          | 149/25880 [04:39<5:13:21,  1.37it/s]
1|150|Loss: 5.611785888671875:   1%|          | 149/25880 [04:40<5:13:21,  1.37it/s]
1|150|Loss: 5.611785888671875:   1%|          | 150/25880 [04:40<5:03:18,  1.41it/s]
1|151|Loss: 5.098653793334961:   1%|          | 150/25880 [04:40<5:03:18,  1.41it/s]
1|151|Loss: 5.098653793334961:   1%|          | 151/25880 [04:41<5:01:15,  1.42it/s]
1|152|Loss: 5.3052449226379395:   1%|          | 151/25880 [04:41<5:01:15,  1.42it/s]
1|152|Loss: 5.3052449226379395:   1%|          | 152/25880 [04:42<5:15:40,  1.36it/s]
1|153|Loss: 5.107854843139648:   1%|          | 152/25880 [04:42<5:15:40,  1.36it/s] 
1|153|Loss: 5.107854843139648:   1%|          | 153/25880 [04:42<5:18:06,  1.35it/s]
1|154|Loss: 5.38991641998291:   1%|          | 153/25880 [04:43<5:18:06,  1.35it/s] 
1|154|Loss: 5.38991641998291:   1%|          | 154/25880 [04:43<5:34:31,  1.28it/s]
1|155|Loss: 5.010471820831299:   1%|          | 154/25880 [04:44<5:34:31,  1.28it/s]
1|155|Loss: 5.010471820831299:   1%|          | 155/25880 [04:44<5:45:51,  1.24it/s]
1|156|Loss: 5.199807643890381:   1%|          | 155/25880 [04:45<5:45:51,  1.24it/s]
1|156|Loss: 5.199807643890381:   1%|          | 156/25880 [04:45<5:55:37,  1.21it/s]
1|157|Loss: 5.430544376373291:   1%|          | 156/25880 [04:45<5:55:37,  1.21it/s]
1|157|Loss: 5.430544376373291:   1%|          | 157/25880 [04:46<5:29:32,  1.30it/s]
1|158|Loss: 4.831181526184082:   1%|          | 157/25880 [04:46<5:29:32,  1.30it/s]
1|158|Loss: 4.831181526184082:   1%|          | 158/25880 [04:46<5:10:25,  1.38it/s]
1|159|Loss: 4.889047145843506:   1%|          | 158/25880 [04:47<5:10:25,  1.38it/s]
1|159|Loss: 4.889047145843506:   1%|          | 159/25880 [04:47<5:06:17,  1.40it/s]
1|160|Loss: 5.290665626525879:   1%|          | 159/25880 [04:47<5:06:17,  1.40it/s]
1|160|Loss: 5.290665626525879:   1%|          | 160/25880 [04:48<5:06:47,  1.40it/s]
1|161|Loss: 5.426413536071777:   1%|          | 160/25880 [04:48<5:06:47,  1.40it/s]
1|161|Loss: 5.426413536071777:   1%|          | 161/25880 [04:48<5:09:37,  1.38it/s]
1|162|Loss: 5.459920883178711:   1%|          | 161/25880 [04:49<5:09:37,  1.38it/s]
1|162|Loss: 5.459920883178711:   1%|          | 162/25880 [04:49<5:20:58,  1.34it/s]
1|163|Loss: 4.763543605804443:   1%|          | 162/25880 [04:50<5:20:58,  1.34it/s]
1|163|Loss: 4.763543605804443:   1%|          | 163/25880 [04:50<5:09:24,  1.39it/s]
1|164|Loss: 5.038322448730469:   1%|          | 163/25880 [04:50<5:09:24,  1.39it/s]
1|164|Loss: 5.038322448730469:   1%|          | 164/25880 [04:50<4:55:11,  1.45it/s]
1|165|Loss: 5.0199151039123535:   1%|          | 164/25880 [04:51<4:55:11,  1.45it/s]
1|165|Loss: 5.0199151039123535:   1%|          | 165/25880 [04:51<4:39:00,  1.54it/s]
1|166|Loss: 4.777091026306152:   1%|          | 165/25880 [04:51<4:39:00,  1.54it/s] 
1|166|Loss: 4.777091026306152:   1%|          | 166/25880 [04:52<4:44:09,  1.51it/s]
1|167|Loss: 4.953413963317871:   1%|          | 166/25880 [04:52<4:44:09,  1.51it/s]
1|167|Loss: 4.953413963317871:   1%|          | 167/25880 [04:53<5:05:49,  1.40it/s]
1|168|Loss: 4.998429298400879:   1%|          | 167/25880 [04:53<5:05:49,  1.40it/s]
1|168|Loss: 4.998429298400879:   1%|          | 168/25880 [04:53<5:09:01,  1.39it/s]
1|169|Loss: 4.583998680114746:   1%|          | 168/25880 [04:54<5:09:01,  1.39it/s]
1|169|Loss: 4.583998680114746:   1%|          | 169/25880 [04:54<5:05:24,  1.40it/s]
1|170|Loss: 4.296703815460205:   1%|          | 169/25880 [04:54<5:05:24,  1.40it/s]
1|170|Loss: 4.296703815460205:   1%|          | 170/25880 [04:55<5:13:50,  1.37it/s]
1|171|Loss: 4.763709545135498:   1%|          | 170/25880 [04:55<5:13:50,  1.37it/s]
1|171|Loss: 4.763709545135498:   1%|          | 171/25880 [04:55<4:49:41,  1.48it/s]
1|172|Loss: 4.838900566101074:   1%|          | 171/25880 [04:56<4:49:41,  1.48it/s]
1|172|Loss: 4.838900566101074:   1%|          | 172/25880 [04:56<4:51:23,  1.47it/s]
1|173|Loss: 4.281388282775879:   1%|          | 172/25880 [04:56<4:51:23,  1.47it/s]
1|173|Loss: 4.281388282775879:   1%|          | 173/25880 [04:57<4:44:46,  1.50it/s]
1|174|Loss: 4.207300662994385:   1%|          | 173/25880 [04:57<4:44:46,  1.50it/s]
1|174|Loss: 4.207300662994385:   1%|          | 174/25880 [04:57<4:34:08,  1.56it/s]
1|175|Loss: 4.065749645233154:   1%|          | 174/25880 [04:58<4:34:08,  1.56it/s]
1|175|Loss: 4.065749645233154:   1%|          | 175/25880 [04:58<4:40:44,  1.53it/s]
1|176|Loss: 3.789205551147461:   1%|          | 175/25880 [04:58<4:40:44,  1.53it/s]
1|176|Loss: 3.789205551147461:   1%|          | 176/25880 [04:59<4:41:01,  1.52it/s]
1|177|Loss: 4.348928451538086:   1%|          | 176/25880 [04:59<4:41:01,  1.52it/s]
1|177|Loss: 4.348928451538086:   1%|          | 177/25880 [04:59<4:38:33,  1.54it/s]
1|178|Loss: 4.879255294799805:   1%|          | 177/25880 [05:00<4:38:33,  1.54it/s]
1|178|Loss: 4.879255294799805:   1%|          | 178/25880 [05:00<4:24:03,  1.62it/s]
1|179|Loss: 4.978170871734619:   1%|          | 178/25880 [05:00<4:24:03,  1.62it/s]
1|179|Loss: 4.978170871734619:   1%|          | 179/25880 [05:00<4:23:45,  1.62it/s]
1|180|Loss: 4.036380290985107:   1%|          | 179/25880 [05:01<4:23:45,  1.62it/s]
1|180|Loss: 4.036380290985107:   1%|          | 180/25880 [05:01<4:51:36,  1.47it/s]
1|181|Loss: 4.2333197593688965:   1%|          | 180/25880 [05:02<4:51:36,  1.47it/s]
1|181|Loss: 4.2333197593688965:   1%|          | 181/25880 [05:02<4:52:44,  1.46it/s]
1|182|Loss: 3.9433393478393555:   1%|          | 181/25880 [05:02<4:52:44,  1.46it/s]
1|182|Loss: 3.9433393478393555:   1%|          | 182/25880 [05:03<4:56:54,  1.44it/s]
1|183|Loss: 3.586312770843506:   1%|          | 182/25880 [05:03<4:56:54,  1.44it/s] 
1|183|Loss: 3.586312770843506:   1%|          | 183/25880 [05:03<4:50:54,  1.47it/s]
1|184|Loss: 3.80625057220459:   1%|          | 183/25880 [05:04<4:50:54,  1.47it/s] 
1|184|Loss: 3.80625057220459:   1%|          | 184/25880 [05:04<4:44:42,  1.50it/s]
1|185|Loss: 4.033442974090576:   1%|          | 184/25880 [05:04<4:44:42,  1.50it/s]
1|185|Loss: 4.033442974090576:   1%|          | 185/25880 [05:04<4:38:36,  1.54it/s]
1|186|Loss: 3.7942967414855957:   1%|          | 185/25880 [05:05<4:38:36,  1.54it/s]
1|186|Loss: 3.7942967414855957:   1%|          | 186/25880 [05:05<4:30:37,  1.58it/s]
1|187|Loss: 4.033339977264404:   1%|          | 186/25880 [05:05<4:30:37,  1.58it/s] 
1|187|Loss: 4.033339977264404:   1%|          | 187/25880 [05:06<4:29:22,  1.59it/s]
1|188|Loss: 3.7789697647094727:   1%|          | 187/25880 [05:06<4:29:22,  1.59it/s]
1|188|Loss: 3.7789697647094727:   1%|          | 188/25880 [05:06<4:50:09,  1.48it/s]
1|189|Loss: 3.481654644012451:   1%|          | 188/25880 [05:07<4:50:09,  1.48it/s] 
1|189|Loss: 3.481654644012451:   1%|          | 189/25880 [05:07<4:47:46,  1.49it/s]
1|190|Loss: 3.5487060546875:   1%|          | 189/25880 [05:08<4:47:46,  1.49it/s]  
1|190|Loss: 3.5487060546875:   1%|          | 190/25880 [05:08<4:49:37,  1.48it/s]
1|191|Loss: 3.0552361011505127:   1%|          | 190/25880 [05:08<4:49:37,  1.48it/s]
1|191|Loss: 3.0552361011505127:   1%|          | 191/25880 [05:09<5:14:39,  1.36it/s]
1|192|Loss: 3.7074897289276123:   1%|          | 191/25880 [05:09<5:14:39,  1.36it/s]
1|192|Loss: 3.7074897289276123:   1%|          | 192/25880 [05:09<5:09:10,  1.38it/s]
1|193|Loss: 3.0311474800109863:   1%|          | 192/25880 [05:10<5:09:10,  1.38it/s]
1|193|Loss: 3.0311474800109863:   1%|          | 193/25880 [05:10<5:05:54,  1.40it/s]
1|194|Loss: 3.258460283279419:   1%|          | 193/25880 [05:10<5:05:54,  1.40it/s] 
1|194|Loss: 3.258460283279419:   1%|          | 194/25880 [05:11<5:07:49,  1.39it/s]
1|195|Loss: 3.707897901535034:   1%|          | 194/25880 [05:11<5:07:49,  1.39it/s]
1|195|Loss: 3.707897901535034:   1%|          | 195/25880 [05:11<4:58:02,  1.44it/s]
1|196|Loss: 4.573753356933594:   1%|          | 195/25880 [05:12<4:58:02,  1.44it/s]
1|196|Loss: 4.573753356933594:   1%|          | 196/25880 [05:12<5:23:05,  1.32it/s]
1|197|Loss: 4.032899856567383:   1%|          | 196/25880 [05:13<5:23:05,  1.32it/s]
1|197|Loss: 4.032899856567383:   1%|          | 197/25880 [05:13<5:26:02,  1.31it/s]
1|198|Loss: 3.743116855621338:   1%|          | 197/25880 [05:14<5:26:02,  1.31it/s]
1|198|Loss: 3.743116855621338:   1%|          | 198/25880 [05:14<5:23:48,  1.32it/s]
1|199|Loss: 3.520956516265869:   1%|          | 198/25880 [05:14<5:23:48,  1.32it/s]
1|199|Loss: 3.520956516265869:   1%|          | 199/25880 [05:15<5:21:03,  1.33it/s]
1|200|Loss: 3.2036287784576416:   1%|          | 199/25880 [05:15<5:21:03,  1.33it/s]
1|200|Loss: 3.2036287784576416:   1%|          | 200/25880 [05:15<5:27:56,  1.31it/s]
1|201|Loss: 3.314436435699463:   1%|          | 200/25880 [05:16<5:27:56,  1.31it/s] 
1|201|Loss: 3.314436435699463:   1%|          | 201/25880 [05:16<5:16:10,  1.35it/s]
1|202|Loss: 3.747554302215576:   1%|          | 201/25880 [05:16<5:16:10,  1.35it/s]
1|202|Loss: 3.747554302215576:   1%|          | 202/25880 [05:17<4:57:01,  1.44it/s]
1|203|Loss: 3.021747350692749:   1%|          | 202/25880 [05:17<4:57:01,  1.44it/s]
1|203|Loss: 3.021747350692749:   1%|          | 203/25880 [05:17<5:12:57,  1.37it/s]
1|204|Loss: 3.1766066551208496:   1%|          | 203/25880 [05:18<5:12:57,  1.37it/s]
1|204|Loss: 3.1766066551208496:   1%|          | 204/25880 [05:18<5:18:08,  1.35it/s]
1|205|Loss: 3.2713136672973633:   1%|          | 204/25880 [05:19<5:18:08,  1.35it/s]
1|205|Loss: 3.2713136672973633:   1%|          | 205/25880 [05:19<5:18:34,  1.34it/s]
1|206|Loss: 3.027780771255493:   1%|          | 205/25880 [05:19<5:18:34,  1.34it/s] 
1|206|Loss: 3.027780771255493:   1%|          | 206/25880 [05:20<5:16:45,  1.35it/s]
1|207|Loss: 2.6649746894836426:   1%|          | 206/25880 [05:20<5:16:45,  1.35it/s]
1|207|Loss: 2.6649746894836426:   1%|          | 207/25880 [05:21<5:20:59,  1.33it/s]
1|208|Loss: 2.982017755508423:   1%|          | 207/25880 [05:21<5:20:59,  1.33it/s] 
1|208|Loss: 2.982017755508423:   1%|          | 208/25880 [05:21<5:32:16,  1.29it/s]
1|209|Loss: 3.2303881645202637:   1%|          | 208/25880 [05:22<5:32:16,  1.29it/s]
1|209|Loss: 3.2303881645202637:   1%|          | 209/25880 [05:22<5:17:48,  1.35it/s]
1|210|Loss: 3.3442680835723877:   1%|          | 209/25880 [05:22<5:17:48,  1.35it/s]
1|210|Loss: 3.3442680835723877:   1%|          | 210/25880 [05:23<4:44:14,  1.51it/s]
1|211|Loss: 2.950916290283203:   1%|          | 210/25880 [05:23<4:44:14,  1.51it/s] 
1|211|Loss: 2.950916290283203:   1%|          | 211/25880 [05:23<4:45:23,  1.50it/s]
1|212|Loss: 2.557190418243408:   1%|          | 211/25880 [05:24<4:45:23,  1.50it/s]
1|212|Loss: 2.557190418243408:   1%|          | 212/25880 [05:24<5:04:46,  1.40it/s]
1|213|Loss: 2.8174171447753906:   1%|          | 212/25880 [05:24<5:04:46,  1.40it/s]
1|213|Loss: 2.8174171447753906:   1%|          | 213/25880 [05:25<5:09:25,  1.38it/s]
1|214|Loss: 3.6448144912719727:   1%|          | 213/25880 [05:25<5:09:25,  1.38it/s]
1|214|Loss: 3.6448144912719727:   1%|          | 214/25880 [05:25<4:55:56,  1.45it/s]
1|215|Loss: 2.9825828075408936:   1%|          | 214/25880 [05:26<4:55:56,  1.45it/s]
1|215|Loss: 2.9825828075408936:   1%|          | 215/25880 [05:26<4:44:43,  1.50it/s]
1|216|Loss: 2.647979259490967:   1%|          | 215/25880 [05:26<4:44:43,  1.50it/s] 
1|216|Loss: 2.647979259490967:   1%|          | 216/25880 [05:27<4:52:04,  1.46it/s]
1|217|Loss: 3.0182368755340576:   1%|          | 216/25880 [05:27<4:52:04,  1.46it/s]
1|217|Loss: 3.0182368755340576:   1%|          | 217/25880 [05:28<5:14:44,  1.36it/s]
1|218|Loss: 2.785301446914673:   1%|          | 217/25880 [05:28<5:14:44,  1.36it/s] 
1|218|Loss: 2.785301446914673:   1%|          | 218/25880 [05:28<5:19:07,  1.34it/s]
1|219|Loss: 2.620736598968506:   1%|          | 218/25880 [05:29<5:19:07,  1.34it/s]
1|219|Loss: 2.620736598968506:   1%|          | 219/25880 [05:29<5:27:36,  1.31it/s]
1|220|Loss: 3.2617833614349365:   1%|          | 219/25880 [05:30<5:27:36,  1.31it/s]
1|220|Loss: 3.2617833614349365:   1%|          | 220/25880 [05:30<5:48:13,  1.23it/s]
1|221|Loss: 2.9594502449035645:   1%|          | 220/25880 [05:31<5:48:13,  1.23it/s]
1|221|Loss: 2.9594502449035645:   1%|          | 221/25880 [05:31<5:43:53,  1.24it/s]
1|222|Loss: 3.051591396331787:   1%|          | 221/25880 [05:31<5:43:53,  1.24it/s] 
1|222|Loss: 3.051591396331787:   1%|          | 222/25880 [05:31<5:17:24,  1.35it/s]
1|223|Loss: 3.1040236949920654:   1%|          | 222/25880 [05:32<5:17:24,  1.35it/s]
1|223|Loss: 3.1040236949920654:   1%|          | 223/25880 [05:32<4:59:06,  1.43it/s]
1|224|Loss: 3.1220269203186035:   1%|          | 223/25880 [05:32<4:59:06,  1.43it/s]
1|224|Loss: 3.1220269203186035:   1%|          | 224/25880 [05:33<4:47:39,  1.49it/s]
1|225|Loss: 2.5511231422424316:   1%|          | 224/25880 [05:33<4:47:39,  1.49it/s]
1|225|Loss: 2.5511231422424316:   1%|          | 225/25880 [05:33<5:04:34,  1.40it/s]
1|226|Loss: 2.554922342300415:   1%|          | 225/25880 [05:34<5:04:34,  1.40it/s] 
1|226|Loss: 2.554922342300415:   1%|          | 226/25880 [05:34<5:12:32,  1.37it/s]
1|227|Loss: 2.6657497882843018:   1%|          | 226/25880 [05:35<5:12:32,  1.37it/s]
1|227|Loss: 2.6657497882843018:   1%|          | 227/25880 [05:35<5:21:07,  1.33it/s]
1|228|Loss: 2.931626081466675:   1%|          | 227/25880 [05:35<5:21:07,  1.33it/s] 
1|228|Loss: 2.931626081466675:   1%|          | 228/25880 [05:36<5:25:56,  1.31it/s]
1|229|Loss: 2.807239294052124:   1%|          | 228/25880 [05:36<5:25:56,  1.31it/s]
1|229|Loss: 2.807239294052124:   1%|          | 229/25880 [05:36<5:09:35,  1.38it/s]
1|230|Loss: 2.7376961708068848:   1%|          | 229/25880 [05:37<5:09:35,  1.38it/s]
1|230|Loss: 2.7376961708068848:   1%|          | 230/25880 [05:37<5:06:55,  1.39it/s]
1|231|Loss: 3.0746538639068604:   1%|          | 230/25880 [05:37<5:06:55,  1.39it/s]
1|231|Loss: 3.0746538639068604:   1%|          | 231/25880 [05:38<4:43:54,  1.51it/s]
1|232|Loss: 2.3008692264556885:   1%|          | 231/25880 [05:38<4:43:54,  1.51it/s]
1|232|Loss: 2.3008692264556885:   1%|          | 232/25880 [05:38<4:53:06,  1.46it/s]
1|233|Loss: 2.6288414001464844:   1%|          | 232/25880 [05:39<4:53:06,  1.46it/s]
1|233|Loss: 2.6288414001464844:   1%|          | 233/25880 [05:39<5:10:10,  1.38it/s]
1|234|Loss: 2.4693527221679688:   1%|          | 233/25880 [05:40<5:10:10,  1.38it/s]
1|234|Loss: 2.4693527221679688:   1%|          | 234/25880 [05:40<5:14:12,  1.36it/s]
1|235|Loss: 2.532926321029663:   1%|          | 234/25880 [05:40<5:14:12,  1.36it/s] 
1|235|Loss: 2.532926321029663:   1%|          | 235/25880 [05:41<5:27:27,  1.31it/s]
1|236|Loss: 2.449629306793213:   1%|          | 235/25880 [05:41<5:27:27,  1.31it/s]
1|236|Loss: 2.449629306793213:   1%|          | 236/25880 [05:42<5:32:49,  1.28it/s]
1|237|Loss: 2.1033434867858887:   1%|          | 236/25880 [05:42<5:32:49,  1.28it/s]
1|237|Loss: 2.1033434867858887:   1%|          | 237/25880 [05:42<5:39:03,  1.26it/s]
1|238|Loss: 2.597029447555542:   1%|          | 237/25880 [05:43<5:39:03,  1.26it/s] 
1|238|Loss: 2.597029447555542:   1%|          | 238/25880 [05:43<5:17:20,  1.35it/s]
1|239|Loss: 2.202831745147705:   1%|          | 238/25880 [05:43<5:17:20,  1.35it/s]
1|239|Loss: 2.202831745147705:   1%|          | 239/25880 [05:44<5:08:47,  1.38it/s]
1|240|Loss: 2.463696002960205:   1%|          | 239/25880 [05:44<5:08:47,  1.38it/s]
1|240|Loss: 2.463696002960205:   1%|          | 240/25880 [05:44<4:59:23,  1.43it/s]
1|241|Loss: 2.6236374378204346:   1%|          | 240/25880 [05:45<4:59:23,  1.43it/s]
1|241|Loss: 2.6236374378204346:   1%|          | 241/25880 [05:45<5:00:14,  1.42it/s]
1|242|Loss: 2.441925525665283:   1%|          | 241/25880 [05:46<5:00:14,  1.42it/s] 
1|242|Loss: 2.441925525665283:   1%|          | 242/25880 [05:46<5:03:10,  1.41it/s]
1|243|Loss: 2.0759031772613525:   1%|          | 242/25880 [05:46<5:03:10,  1.41it/s]
1|243|Loss: 2.0759031772613525:   1%|          | 243/25880 [05:47<4:55:27,  1.45it/s]
1|244|Loss: 2.124154806137085:   1%|          | 243/25880 [05:47<4:55:27,  1.45it/s] 
1|244|Loss: 2.124154806137085:   1%|          | 244/25880 [05:47<5:25:18,  1.31it/s]
1|245|Loss: 2.5551536083221436:   1%|          | 244/25880 [05:48<5:25:18,  1.31it/s]
1|245|Loss: 2.5551536083221436:   1%|          | 245/25880 [05:48<5:30:51,  1.29it/s]
1|246|Loss: 2.3991096019744873:   1%|          | 245/25880 [05:49<5:30:51,  1.29it/s]
1|246|Loss: 2.3991096019744873:   1%|          | 246/25880 [05:49<5:34:06,  1.28it/s]
1|247|Loss: 2.376810073852539:   1%|          | 246/25880 [05:49<5:34:06,  1.28it/s] 
1|247|Loss: 2.376810073852539:   1%|          | 247/25880 [05:50<5:30:21,  1.29it/s]
1|248|Loss: 2.336543560028076:   1%|          | 247/25880 [05:50<5:30:21,  1.29it/s]
1|248|Loss: 2.336543560028076:   1%|          | 248/25880 [05:50<5:13:34,  1.36it/s]
1|249|Loss: 2.0833253860473633:   1%|          | 248/25880 [05:51<5:13:34,  1.36it/s]
1|249|Loss: 2.0833253860473633:   1%|          | 249/25880 [05:51<4:58:02,  1.43it/s]
1|250|Loss: 2.194902181625366:   1%|          | 249/25880 [05:51<4:58:02,  1.43it/s] 
1|250|Loss: 2.194902181625366:   1%|          | 250/25880 [05:52<4:50:36,  1.47it/s]
1|251|Loss: 2.328552484512329:   1%|          | 250/25880 [05:52<4:50:36,  1.47it/s]
1|251|Loss: 2.328552484512329:   1%|          | 251/25880 [05:52<4:51:57,  1.46it/s]
1|252|Loss: 2.0584235191345215:   1%|          | 251/25880 [05:53<4:51:57,  1.46it/s]
1|252|Loss: 2.0584235191345215:   1%|          | 252/25880 [05:53<4:59:11,  1.43it/s]
1|253|Loss: 2.3716280460357666:   1%|          | 252/25880 [05:53<4:59:11,  1.43it/s]
1|253|Loss: 2.3716280460357666:   1%|          | 253/25880 [05:54<4:52:12,  1.46it/s]
1|254|Loss: 1.9812695980072021:   1%|          | 253/25880 [05:54<4:52:12,  1.46it/s]
1|254|Loss: 1.9812695980072021:   1%|          | 254/25880 [05:55<5:07:10,  1.39it/s]
1|255|Loss: 1.9778282642364502:   1%|          | 254/25880 [05:55<5:07:10,  1.39it/s]
1|255|Loss: 1.9778282642364502:   1%|          | 255/25880 [05:55<5:24:35,  1.32it/s]
1|256|Loss: 2.322286367416382:   1%|          | 255/25880 [05:56<5:24:35,  1.32it/s] 
1|256|Loss: 2.322286367416382:   1%|          | 256/25880 [05:56<5:21:24,  1.33it/s]
1|257|Loss: 2.157109498977661:   1%|          | 256/25880 [05:57<5:21:24,  1.33it/s]
1|257|Loss: 2.157109498977661:   1%|          | 257/25880 [05:57<5:19:24,  1.34it/s]
1|258|Loss: 2.1348068714141846:   1%|          | 257/25880 [05:57<5:19:24,  1.34it/s]
1|258|Loss: 2.1348068714141846:   1%|          | 258/25880 [05:58<5:15:51,  1.35it/s]
1|259|Loss: 2.6789309978485107:   1%|          | 258/25880 [05:58<5:15:51,  1.35it/s]
1|259|Loss: 2.6789309978485107:   1%|          | 259/25880 [05:58<4:57:28,  1.44it/s]
1|260|Loss: 2.2035458087921143:   1%|          | 259/25880 [05:59<4:57:28,  1.44it/s]
1|260|Loss: 2.2035458087921143:   1%|          | 260/25880 [05:59<4:55:20,  1.45it/s]
1|261|Loss: 2.1215410232543945:   1%|          | 260/25880 [05:59<4:55:20,  1.45it/s]
1|261|Loss: 2.1215410232543945:   1%|          | 261/25880 [06:00<5:14:24,  1.36it/s]
1|262|Loss: 2.2618308067321777:   1%|          | 261/25880 [06:00<5:14:24,  1.36it/s]
1|262|Loss: 2.2618308067321777:   1%|          | 262/25880 [06:00<5:08:53,  1.38it/s]
1|263|Loss: 2.2978618144989014:   1%|          | 262/25880 [06:01<5:08:53,  1.38it/s]
1|263|Loss: 2.2978618144989014:   1%|          | 263/25880 [06:01<4:55:14,  1.45it/s]
1|264|Loss: 2.0947585105895996:   1%|          | 263/25880 [06:01<4:55:14,  1.45it/s]
1|264|Loss: 2.0947585105895996:   1%|          | 264/25880 [06:02<4:57:23,  1.44it/s]
1|265|Loss: 1.8106794357299805:   1%|          | 264/25880 [06:02<4:57:23,  1.44it/s]
1|265|Loss: 1.8106794357299805:   1%|          | 265/25880 [06:03<5:13:54,  1.36it/s]
1|266|Loss: 2.1564764976501465:   1%|          | 265/25880 [06:03<5:13:54,  1.36it/s]
1|266|Loss: 2.1564764976501465:   1%|          | 266/25880 [06:03<5:16:54,  1.35it/s]
1|267|Loss: 2.3264145851135254:   1%|          | 266/25880 [06:04<5:16:54,  1.35it/s]
1|267|Loss: 2.3264145851135254:   1%|          | 267/25880 [06:04<5:28:15,  1.30it/s]
1|268|Loss: 2.1635730266571045:   1%|          | 267/25880 [06:05<5:28:15,  1.30it/s]
1|268|Loss: 2.1635730266571045:   1%|          | 268/25880 [06:05<5:27:22,  1.30it/s]
1|269|Loss: 1.8977264165878296:   1%|          | 268/25880 [06:05<5:27:22,  1.30it/s]
1|269|Loss: 1.8977264165878296:   1%|          | 269/25880 [06:06<5:28:46,  1.30it/s]
1|270|Loss: 2.0979561805725098:   1%|          | 269/25880 [06:06<5:28:46,  1.30it/s]
1|270|Loss: 2.0979561805725098:   1%|          | 270/25880 [06:06<5:26:22,  1.31it/s]
1|271|Loss: 2.6308188438415527:   1%|          | 270/25880 [06:07<5:26:22,  1.31it/s]
1|271|Loss: 2.6308188438415527:   1%|          | 271/25880 [06:07<4:52:56,  1.46it/s]
1|272|Loss: 3.230077028274536:   1%|          | 271/25880 [06:07<4:52:56,  1.46it/s] 
1|272|Loss: 3.230077028274536:   1%|          | 272/25880 [06:08<4:50:50,  1.47it/s]
1|273|Loss: 2.337998628616333:   1%|          | 272/25880 [06:08<4:50:50,  1.47it/s]
1|273|Loss: 2.337998628616333:   1%|          | 273/25880 [06:08<4:47:48,  1.48it/s]
1|274|Loss: 2.6399176120758057:   1%|          | 273/25880 [06:09<4:47:48,  1.48it/s]
1|274|Loss: 2.6399176120758057:   1%|          | 274/25880 [06:09<4:30:06,  1.58it/s]
1|275|Loss: 2.0303421020507812:   1%|          | 274/25880 [06:09<4:30:06,  1.58it/s]
1|275|Loss: 2.0303421020507812:   1%|          | 275/25880 [06:10<4:37:03,  1.54it/s]
1|276|Loss: 2.039180040359497:   1%|          | 275/25880 [06:10<4:37:03,  1.54it/s] 
1|276|Loss: 2.039180040359497:   1%|          | 276/25880 [06:10<4:45:26,  1.49it/s]
1|277|Loss: 2.3432114124298096:   1%|          | 276/25880 [06:11<4:45:26,  1.49it/s]
1|277|Loss: 2.3432114124298096:   1%|          | 277/25880 [06:11<4:40:13,  1.52it/s]
1|278|Loss: 2.18548583984375:   1%|          | 277/25880 [06:11<4:40:13,  1.52it/s]  
1|278|Loss: 2.18548583984375:   1%|          | 278/25880 [06:11<4:35:17,  1.55it/s]
1|279|Loss: 1.7425363063812256:   1%|          | 278/25880 [06:12<4:35:17,  1.55it/s]
1|279|Loss: 1.7425363063812256:   1%|          | 279/25880 [06:12<4:48:54,  1.48it/s]
1|280|Loss: 2.037055492401123:   1%|          | 279/25880 [06:13<4:48:54,  1.48it/s] 
1|280|Loss: 2.037055492401123:   1%|          | 280/25880 [06:13<4:39:15,  1.53it/s]
1|281|Loss: 2.264503240585327:   1%|          | 280/25880 [06:13<4:39:15,  1.53it/s]
1|281|Loss: 2.264503240585327:   1%|          | 281/25880 [06:13<4:34:53,  1.55it/s]
1|282|Loss: 2.7150065898895264:   1%|          | 281/25880 [06:14<4:34:53,  1.55it/s]
1|282|Loss: 2.7150065898895264:   1%|          | 282/25880 [06:14<4:34:46,  1.55it/s]
1|283|Loss: 2.3235621452331543:   1%|          | 282/25880 [06:14<4:34:46,  1.55it/s]
1|283|Loss: 2.3235621452331543:   1%|          | 283/25880 [06:15<4:40:08,  1.52it/s]
1|284|Loss: 2.0100619792938232:   1%|          | 283/25880 [06:15<4:40:08,  1.52it/s]
1|284|Loss: 2.0100619792938232:   1%|          | 284/25880 [06:15<4:32:37,  1.56it/s]
1|285|Loss: 2.0365772247314453:   1%|          | 284/25880 [06:16<4:32:37,  1.56it/s]
1|285|Loss: 2.0365772247314453:   1%|          | 285/25880 [06:16<4:31:16,  1.57it/s]
1|286|Loss: 2.0716488361358643:   1%|          | 285/25880 [06:16<4:31:16,  1.57it/s]
1|286|Loss: 2.0716488361358643:   1%|          | 286/25880 [06:17<4:32:19,  1.57it/s]
1|287|Loss: 1.8558019399642944:   1%|          | 286/25880 [06:17<4:32:19,  1.57it/s]
1|287|Loss: 1.8558019399642944:   1%|          | 287/25880 [06:17<4:38:50,  1.53it/s]
1|288|Loss: 1.929784893989563:   1%|          | 287/25880 [06:18<4:38:50,  1.53it/s] 
1|288|Loss: 1.929784893989563:   1%|          | 288/25880 [06:18<4:38:41,  1.53it/s]
1|289|Loss: 2.090196132659912:   1%|          | 288/25880 [06:18<4:38:41,  1.53it/s]
1|289|Loss: 2.090196132659912:   1%|          | 289/25880 [06:19<4:48:05,  1.48it/s]
1|290|Loss: 1.955950379371643:   1%|          | 289/25880 [06:19<4:48:05,  1.48it/s]
1|290|Loss: 1.955950379371643:   1%|          | 290/25880 [06:19<4:53:06,  1.46it/s]
1|291|Loss: 2.0413646697998047:   1%|          | 290/25880 [06:20<4:53:06,  1.46it/s]
1|291|Loss: 2.0413646697998047:   1%|          | 291/25880 [06:20<5:16:32,  1.35it/s]
1|292|Loss: 2.0052459239959717:   1%|          | 291/25880 [06:21<5:16:32,  1.35it/s]
1|292|Loss: 2.0052459239959717:   1%|          | 292/25880 [06:21<5:16:22,  1.35it/s]
1|293|Loss: 1.675282597541809:   1%|          | 292/25880 [06:21<5:16:22,  1.35it/s] 
1|293|Loss: 1.675282597541809:   1%|          | 293/25880 [06:22<5:19:38,  1.33it/s]
1|294|Loss: 1.9377981424331665:   1%|          | 293/25880 [06:22<5:19:38,  1.33it/s]
1|294|Loss: 1.9377981424331665:   1%|          | 294/25880 [06:23<5:15:48,  1.35it/s]
1|295|Loss: 2.0836338996887207:   1%|          | 294/25880 [06:23<5:15:48,  1.35it/s]
1|295|Loss: 2.0836338996887207:   1%|          | 295/25880 [06:23<5:03:49,  1.40it/s]
1|296|Loss: 1.8525956869125366:   1%|          | 295/25880 [06:24<5:03:49,  1.40it/s]
1|296|Loss: 1.8525956869125366:   1%|          | 296/25880 [06:24<5:00:36,  1.42it/s]
1|297|Loss: 1.8804575204849243:   1%|          | 296/25880 [06:24<5:00:36,  1.42it/s]
1|297|Loss: 1.8804575204849243:   1%|          | 297/25880 [06:25<5:02:10,  1.41it/s]
1|298|Loss: 1.7023619413375854:   1%|          | 297/25880 [06:25<5:02:10,  1.41it/s]
1|298|Loss: 1.7023619413375854:   1%|          | 298/25880 [06:25<5:14:35,  1.36it/s]
1|299|Loss: 1.5524108409881592:   1%|          | 298/25880 [06:26<5:14:35,  1.36it/s]
1|299|Loss: 1.5524108409881592:   1%|          | 299/25880 [06:26<5:30:53,  1.29it/s]
1|300|Loss: 1.6696280241012573:   1%|          | 299/25880 [06:27<5:30:53,  1.29it/s]
1|300|Loss: 1.6696280241012573:   1%|          | 300/25880 [06:27<5:43:16,  1.24it/s]
1|301|Loss: 1.8588240146636963:   1%|          | 300/25880 [06:28<5:43:16,  1.24it/s]
1|301|Loss: 1.8588240146636963:   1%|          | 301/25880 [06:28<5:35:04,  1.27it/s]
1|302|Loss: 1.6739587783813477:   1%|          | 301/25880 [06:28<5:35:04,  1.27it/s]
1|302|Loss: 1.6739587783813477:   1%|          | 302/25880 [06:29<5:28:28,  1.30it/s]
1|303|Loss: 1.667906641960144:   1%|          | 302/25880 [06:29<5:28:28,  1.30it/s] 
1|303|Loss: 1.667906641960144:   1%|          | 303/25880 [06:29<5:26:18,  1.31it/s]
1|304|Loss: 2.221621036529541:   1%|          | 303/25880 [06:30<5:26:18,  1.31it/s]
1|304|Loss: 2.221621036529541:   1%|          | 304/25880 [06:30<5:50:15,  1.22it/s]
1|305|Loss: 1.985304594039917:   1%|          | 304/25880 [06:31<5:50:15,  1.22it/s]
1|305|Loss: 1.985304594039917:   1%|          | 305/25880 [06:31<5:42:42,  1.24it/s]
1|306|Loss: 1.5295850038528442:   1%|          | 305/25880 [06:31<5:42:42,  1.24it/s]
1|306|Loss: 1.5295850038528442:   1%|          | 306/25880 [06:32<5:39:59,  1.25it/s]
1|307|Loss: 1.882479190826416:   1%|          | 306/25880 [06:32<5:39:59,  1.25it/s] 
1|307|Loss: 1.882479190826416:   1%|          | 307/25880 [06:33<5:21:21,  1.33it/s]
1|308|Loss: 1.8721630573272705:   1%|          | 307/25880 [06:33<5:21:21,  1.33it/s]
1|308|Loss: 1.8721630573272705:   1%|          | 308/25880 [06:33<5:00:12,  1.42it/s]
1|309|Loss: 1.7360951900482178:   1%|          | 308/25880 [06:33<5:00:12,  1.42it/s]
1|309|Loss: 1.7360951900482178:   1%|          | 309/25880 [06:34<4:59:20,  1.42it/s]
1|310|Loss: 2.1294074058532715:   1%|          | 309/25880 [06:34<4:59:20,  1.42it/s]
1|310|Loss: 2.1294074058532715:   1%|          | 310/25880 [06:34<4:46:31,  1.49it/s]
1|311|Loss: 1.8135877847671509:   1%|          | 310/25880 [06:35<4:46:31,  1.49it/s]
1|311|Loss: 1.8135877847671509:   1%|          | 311/25880 [06:35<4:55:43,  1.44it/s]
1|312|Loss: 1.7592768669128418:   1%|          | 311/25880 [06:36<4:55:43,  1.44it/s]
1|312|Loss: 1.7592768669128418:   1%|          | 312/25880 [06:36<5:29:26,  1.29it/s]
1|313|Loss: 1.6184781789779663:   1%|          | 312/25880 [06:37<5:29:26,  1.29it/s]
1|313|Loss: 1.6184781789779663:   1%|          | 313/25880 [06:37<5:33:14,  1.28it/s]
1|314|Loss: 1.8628698587417603:   1%|          | 313/25880 [06:37<5:33:14,  1.28it/s]
1|314|Loss: 1.8628698587417603:   1%|          | 314/25880 [06:38<5:23:23,  1.32it/s]
1|315|Loss: 2.2388532161712646:   1%|          | 314/25880 [06:38<5:23:23,  1.32it/s]
1|315|Loss: 2.2388532161712646:   1%|          | 315/25880 [06:38<4:49:24,  1.47it/s]
1|316|Loss: 1.8098750114440918:   1%|          | 315/25880 [06:38<4:49:24,  1.47it/s]
1|316|Loss: 1.8098750114440918:   1%|          | 316/25880 [06:39<4:44:46,  1.50it/s]
1|317|Loss: 1.5082577466964722:   1%|          | 316/25880 [06:39<4:44:46,  1.50it/s]
1|317|Loss: 1.5082577466964722:   1%|          | 317/25880 [06:39<4:51:39,  1.46it/s]
1|318|Loss: 1.8981075286865234:   1%|          | 317/25880 [06:40<4:51:39,  1.46it/s]
1|318|Loss: 1.8981075286865234:   1%|          | 318/25880 [06:40<4:35:01,  1.55it/s]
1|319|Loss: 1.765511393547058:   1%|          | 318/25880 [06:40<4:35:01,  1.55it/s] 
1|319|Loss: 1.765511393547058:   1%|          | 319/25880 [06:41<4:26:08,  1.60it/s]
1|320|Loss: 1.757127285003662:   1%|          | 319/25880 [06:41<4:26:08,  1.60it/s]
1|320|Loss: 1.757127285003662:   1%|          | 320/25880 [06:41<4:47:32,  1.48it/s]
1|321|Loss: 1.510898470878601:   1%|          | 320/25880 [06:42<4:47:32,  1.48it/s]
1|321|Loss: 1.510898470878601:   1%|          | 321/25880 [06:42<5:05:29,  1.39it/s]
1|322|Loss: 1.3606458902359009:   1%|          | 321/25880 [06:43<5:05:29,  1.39it/s]
1|322|Loss: 1.3606458902359009:   1%|          | 322/25880 [06:43<5:24:07,  1.31it/s]
1|323|Loss: 1.652726173400879:   1%|          | 322/25880 [06:44<5:24:07,  1.31it/s] 
1|323|Loss: 1.652726173400879:   1%|          | 323/25880 [06:44<5:35:01,  1.27it/s]
1|324|Loss: 1.6560968160629272:   1%|          | 323/25880 [06:44<5:35:01,  1.27it/s]
1|324|Loss: 1.6560968160629272:   1%|▏         | 324/25880 [06:45<5:30:40,  1.29it/s]
1|325|Loss: 1.7714259624481201:   1%|▏         | 324/25880 [06:45<5:30:40,  1.29it/s]
1|325|Loss: 1.7714259624481201:   1%|▏         | 325/25880 [06:45<5:12:42,  1.36it/s]
1|326|Loss: 1.593410611152649:   1%|▏         | 325/25880 [06:46<5:12:42,  1.36it/s] 
1|326|Loss: 1.593410611152649:   1%|▏         | 326/25880 [06:46<5:10:40,  1.37it/s]
1|327|Loss: 1.6797916889190674:   1%|▏         | 326/25880 [06:46<5:10:40,  1.37it/s]
1|327|Loss: 1.6797916889190674:   1%|▏         | 327/25880 [06:47<5:21:46,  1.32it/s]
1|328|Loss: 1.7755894660949707:   1%|▏         | 327/25880 [06:47<5:21:46,  1.32it/s]
1|328|Loss: 1.7755894660949707:   1%|▏         | 328/25880 [06:48<5:20:38,  1.33it/s]
1|329|Loss: 1.5461742877960205:   1%|▏         | 328/25880 [06:48<5:20:38,  1.33it/s]
1|329|Loss: 1.5461742877960205:   1%|▏         | 329/25880 [06:48<5:17:50,  1.34it/s]
1|330|Loss: 1.6652454137802124:   1%|▏         | 329/25880 [06:49<5:17:50,  1.34it/s]
1|330|Loss: 1.6652454137802124:   1%|▏         | 330/25880 [06:49<5:15:39,  1.35it/s]
1|331|Loss: 1.8947653770446777:   1%|▏         | 330/25880 [06:49<5:15:39,  1.35it/s]
1|331|Loss: 1.8947653770446777:   1%|▏         | 331/25880 [06:50<4:58:13,  1.43it/s]
1|332|Loss: 1.622933268547058:   1%|▏         | 331/25880 [06:50<4:58:13,  1.43it/s] 
1|332|Loss: 1.622933268547058:   1%|▏         | 332/25880 [06:50<4:48:04,  1.48it/s]
1|333|Loss: 1.9444043636322021:   1%|▏         | 332/25880 [06:51<4:48:04,  1.48it/s]
1|333|Loss: 1.9444043636322021:   1%|▏         | 333/25880 [06:51<4:29:47,  1.58it/s]
1|334|Loss: 1.536312460899353:   1%|▏         | 333/25880 [06:51<4:29:47,  1.58it/s] 
1|334|Loss: 1.536312460899353:   1%|▏         | 334/25880 [06:51<4:36:07,  1.54it/s]
1|335|Loss: 1.6315269470214844:   1%|▏         | 334/25880 [06:52<4:36:07,  1.54it/s]
1|335|Loss: 1.6315269470214844:   1%|▏         | 335/25880 [06:52<4:37:02,  1.54it/s]
1|336|Loss: 1.7645679712295532:   1%|▏         | 335/25880 [06:52<4:37:02,  1.54it/s]
1|336|Loss: 1.7645679712295532:   1%|▏         | 336/25880 [06:53<4:16:32,  1.66it/s]
1|337|Loss: 1.951244592666626:   1%|▏         | 336/25880 [06:53<4:16:32,  1.66it/s] 
1|337|Loss: 1.951244592666626:   1%|▏         | 337/25880 [06:53<4:10:23,  1.70it/s]
1|338|Loss: 1.6132912635803223:   1%|▏         | 337/25880 [06:54<4:10:23,  1.70it/s]
1|338|Loss: 1.6132912635803223:   1%|▏         | 338/25880 [06:54<4:25:59,  1.60it/s]
1|339|Loss: 1.9033350944519043:   1%|▏         | 338/25880 [06:54<4:25:59,  1.60it/s]
1|339|Loss: 1.9033350944519043:   1%|▏         | 339/25880 [06:55<4:30:57,  1.57it/s]
1|340|Loss: 2.1249115467071533:   1%|▏         | 339/25880 [06:55<4:30:57,  1.57it/s]
1|340|Loss: 2.1249115467071533:   1%|▏         | 340/25880 [06:55<4:28:26,  1.59it/s]
1|341|Loss: 1.7166833877563477:   1%|▏         | 340/25880 [06:56<4:28:26,  1.59it/s]
1|341|Loss: 1.7166833877563477:   1%|▏         | 341/25880 [06:56<4:24:10,  1.61it/s]
1|342|Loss: 1.4916590452194214:   1%|▏         | 341/25880 [06:56<4:24:10,  1.61it/s]
1|342|Loss: 1.4916590452194214:   1%|▏         | 342/25880 [06:57<4:46:00,  1.49it/s]
1|343|Loss: 1.7302192449569702:   1%|▏         | 342/25880 [06:57<4:46:00,  1.49it/s]
1|343|Loss: 1.7302192449569702:   1%|▏         | 343/25880 [06:57<5:04:30,  1.40it/s]
1|344|Loss: 1.558692216873169:   1%|▏         | 343/25880 [06:58<5:04:30,  1.40it/s] 
1|344|Loss: 1.558692216873169:   1%|▏         | 344/25880 [06:58<4:56:54,  1.43it/s]
1|345|Loss: 1.499387502670288:   1%|▏         | 344/25880 [06:58<4:56:54,  1.43it/s]
1|345|Loss: 1.499387502670288:   1%|▏         | 345/25880 [06:59<4:49:02,  1.47it/s]
1|346|Loss: 1.745216965675354:   1%|▏         | 345/25880 [06:59<4:49:02,  1.47it/s]
1|346|Loss: 1.745216965675354:   1%|▏         | 346/25880 [06:59<4:44:14,  1.50it/s]
1|347|Loss: 1.929442048072815:   1%|▏         | 346/25880 [07:00<4:44:14,  1.50it/s]
1|347|Loss: 1.929442048072815:   1%|▏         | 347/25880 [07:00<4:24:31,  1.61it/s]
1|348|Loss: 1.9016404151916504:   1%|▏         | 347/25880 [07:00<4:24:31,  1.61it/s]
1|348|Loss: 1.9016404151916504:   1%|▏         | 348/25880 [07:00<4:13:40,  1.68it/s]
1|349|Loss: 1.8378520011901855:   1%|▏         | 348/25880 [07:01<4:13:40,  1.68it/s]
1|349|Loss: 1.8378520011901855:   1%|▏         | 349/25880 [07:01<4:27:25,  1.59it/s]
1|350|Loss: 1.8092137575149536:   1%|▏         | 349/25880 [07:02<4:27:25,  1.59it/s]
1|350|Loss: 1.8092137575149536:   1%|▏         | 350/25880 [07:02<4:53:30,  1.45it/s]
1|351|Loss: 1.7302926778793335:   1%|▏         | 350/25880 [07:02<4:53:30,  1.45it/s]
1|351|Loss: 1.7302926778793335:   1%|▏         | 351/25880 [07:03<5:07:36,  1.38it/s]
1|352|Loss: 1.7135257720947266:   1%|▏         | 351/25880 [07:03<5:07:36,  1.38it/s]
1|352|Loss: 1.7135257720947266:   1%|▏         | 352/25880 [07:03<4:59:24,  1.42it/s]
1|353|Loss: 1.5776557922363281:   1%|▏         | 352/25880 [07:04<4:59:24,  1.42it/s]
1|353|Loss: 1.5776557922363281:   1%|▏         | 353/25880 [07:04<4:45:37,  1.49it/s]
1|354|Loss: 1.5223000049591064:   1%|▏         | 353/25880 [07:04<4:45:37,  1.49it/s]
1|354|Loss: 1.5223000049591064:   1%|▏         | 354/25880 [07:05<4:47:27,  1.48it/s]
1|355|Loss: 1.8288124799728394:   1%|▏         | 354/25880 [07:05<4:47:27,  1.48it/s]
1|355|Loss: 1.8288124799728394:   1%|▏         | 355/25880 [07:05<4:41:33,  1.51it/s]
1|356|Loss: 1.613053798675537:   1%|▏         | 355/25880 [07:06<4:41:33,  1.51it/s] 
1|356|Loss: 1.613053798675537:   1%|▏         | 356/25880 [07:06<4:58:07,  1.43it/s]
1|357|Loss: 1.797410488128662:   1%|▏         | 356/25880 [07:06<4:58:07,  1.43it/s]
1|357|Loss: 1.797410488128662:   1%|▏         | 357/25880 [07:07<4:42:22,  1.51it/s]
1|358|Loss: 1.6460710763931274:   1%|▏         | 357/25880 [07:07<4:42:22,  1.51it/s]
1|358|Loss: 1.6460710763931274:   1%|▏         | 358/25880 [07:07<4:56:53,  1.43it/s]
1|359|Loss: 1.522337555885315:   1%|▏         | 358/25880 [07:08<4:56:53,  1.43it/s] 
1|359|Loss: 1.522337555885315:   1%|▏         | 359/25880 [07:08<5:23:39,  1.31it/s]
1|360|Loss: 1.625562310218811:   1%|▏         | 359/25880 [07:09<5:23:39,  1.31it/s]
1|360|Loss: 1.625562310218811:   1%|▏         | 360/25880 [07:09<5:25:51,  1.31it/s]
1|361|Loss: 1.787968635559082:   1%|▏         | 360/25880 [07:10<5:25:51,  1.31it/s]
1|361|Loss: 1.787968635559082:   1%|▏         | 361/25880 [07:10<5:22:00,  1.32it/s]
1|362|Loss: 1.5297586917877197:   1%|▏         | 361/25880 [07:10<5:22:00,  1.32it/s]
1|362|Loss: 1.5297586917877197:   1%|▏         | 362/25880 [07:10<5:03:13,  1.40it/s]
1|363|Loss: 1.5627760887145996:   1%|▏         | 362/25880 [07:11<5:03:13,  1.40it/s]
1|363|Loss: 1.5627760887145996:   1%|▏         | 363/25880 [07:11<5:02:36,  1.41it/s]
1|364|Loss: 1.9129105806350708:   1%|▏         | 363/25880 [07:12<5:02:36,  1.41it/s]
1|364|Loss: 1.9129105806350708:   1%|▏         | 364/25880 [07:12<4:56:39,  1.43it/s]
1|365|Loss: 1.744141697883606:   1%|▏         | 364/25880 [07:12<4:56:39,  1.43it/s] 
1|365|Loss: 1.744141697883606:   1%|▏         | 365/25880 [07:13<5:31:00,  1.28it/s]
1|366|Loss: 1.538961410522461:   1%|▏         | 365/25880 [07:13<5:31:00,  1.28it/s]
1|366|Loss: 1.538961410522461:   1%|▏         | 366/25880 [07:14<5:45:04,  1.23it/s]
1|367|Loss: 1.5178561210632324:   1%|▏         | 366/25880 [07:14<5:45:04,  1.23it/s]
1|367|Loss: 1.5178561210632324:   1%|▏         | 367/25880 [07:14<5:29:39,  1.29it/s]
1|368|Loss: 1.515121340751648:   1%|▏         | 367/25880 [07:15<5:29:39,  1.29it/s] 
1|368|Loss: 1.515121340751648:   1%|▏         | 368/25880 [07:15<5:21:58,  1.32it/s]
1|369|Loss: 1.863551378250122:   1%|▏         | 368/25880 [07:15<5:21:58,  1.32it/s]
1|369|Loss: 1.863551378250122:   1%|▏         | 369/25880 [07:16<5:03:46,  1.40it/s]
1|370|Loss: 1.4244943857192993:   1%|▏         | 369/25880 [07:16<5:03:46,  1.40it/s]
1|370|Loss: 1.4244943857192993:   1%|▏         | 370/25880 [07:17<5:17:14,  1.34it/s]
1|371|Loss: 1.500949501991272:   1%|▏         | 370/25880 [07:17<5:17:14,  1.34it/s] 
1|371|Loss: 1.500949501991272:   1%|▏         | 371/25880 [07:17<5:26:59,  1.30it/s]
1|372|Loss: 1.436065435409546:   1%|▏         | 371/25880 [07:18<5:26:59,  1.30it/s]
1|372|Loss: 1.436065435409546:   1%|▏         | 372/25880 [07:18<5:24:30,  1.31it/s]
1|373|Loss: 1.3984414339065552:   1%|▏         | 372/25880 [07:18<5:24:30,  1.31it/s]
1|373|Loss: 1.3984414339065552:   1%|▏         | 373/25880 [07:19<5:18:51,  1.33it/s]
1|374|Loss: 1.5024596452713013:   1%|▏         | 373/25880 [07:19<5:18:51,  1.33it/s]
1|374|Loss: 1.5024596452713013:   1%|▏         | 374/25880 [07:20<5:31:03,  1.28it/s]
1|375|Loss: 1.5421065092086792:   1%|▏         | 374/25880 [07:20<5:31:03,  1.28it/s]
1|375|Loss: 1.5421065092086792:   1%|▏         | 375/25880 [07:20<5:28:37,  1.29it/s]
1|376|Loss: 1.4272857904434204:   1%|▏         | 375/25880 [07:21<5:28:37,  1.29it/s]
1|376|Loss: 1.4272857904434204:   1%|▏         | 376/25880 [07:21<5:22:54,  1.32it/s]
1|377|Loss: 1.439202904701233:   1%|▏         | 376/25880 [07:22<5:22:54,  1.32it/s] 
1|377|Loss: 1.439202904701233:   1%|▏         | 377/25880 [07:22<5:20:53,  1.32it/s]
1|378|Loss: 1.3528168201446533:   1%|▏         | 377/25880 [07:22<5:20:53,  1.32it/s]
1|378|Loss: 1.3528168201446533:   1%|▏         | 378/25880 [07:23<5:28:15,  1.29it/s]
1|379|Loss: 1.2683261632919312:   1%|▏         | 378/25880 [07:23<5:28:15,  1.29it/s]
1|379|Loss: 1.2683261632919312:   1%|▏         | 379/25880 [07:24<5:43:27,  1.24it/s]
1|380|Loss: 1.5723154544830322:   1%|▏         | 379/25880 [07:24<5:43:27,  1.24it/s]
1|380|Loss: 1.5723154544830322:   1%|▏         | 380/25880 [07:24<5:28:38,  1.29it/s]
1|381|Loss: 1.5064424276351929:   1%|▏         | 380/25880 [07:25<5:28:38,  1.29it/s]
1|381|Loss: 1.5064424276351929:   1%|▏         | 381/25880 [07:25<5:11:41,  1.36it/s]
1|382|Loss: 1.4432207345962524:   1%|▏         | 381/25880 [07:25<5:11:41,  1.36it/s]
1|382|Loss: 1.4432207345962524:   1%|▏         | 382/25880 [07:26<5:16:43,  1.34it/s]
1|383|Loss: 1.7227354049682617:   1%|▏         | 382/25880 [07:26<5:16:43,  1.34it/s]
1|383|Loss: 1.7227354049682617:   1%|▏         | 383/25880 [07:26<5:00:42,  1.41it/s]
1|384|Loss: 1.3183608055114746:   1%|▏         | 383/25880 [07:27<5:00:42,  1.41it/s]
1|384|Loss: 1.3183608055114746:   1%|▏         | 384/25880 [07:27<5:12:31,  1.36it/s]
1|385|Loss: 1.307063341140747:   1%|▏         | 384/25880 [07:28<5:12:31,  1.36it/s] 
1|385|Loss: 1.307063341140747:   1%|▏         | 385/25880 [07:28<5:06:55,  1.38it/s]
1|386|Loss: 1.5227113962173462:   1%|▏         | 385/25880 [07:28<5:06:55,  1.38it/s]
1|386|Loss: 1.5227113962173462:   1%|▏         | 386/25880 [07:29<5:15:41,  1.35it/s]
1|387|Loss: 1.6330711841583252:   1%|▏         | 386/25880 [07:29<5:15:41,  1.35it/s]
1|387|Loss: 1.6330711841583252:   1%|▏         | 387/25880 [07:29<5:04:28,  1.40it/s]
1|388|Loss: 1.4347339868545532:   1%|▏         | 387/25880 [07:30<5:04:28,  1.40it/s]
1|388|Loss: 1.4347339868545532:   1%|▏         | 388/25880 [07:30<5:08:01,  1.38it/s]
1|389|Loss: 1.264442801475525:   1%|▏         | 388/25880 [07:30<5:08:01,  1.38it/s] 
1|389|Loss: 1.264442801475525:   2%|▏         | 389/25880 [07:31<5:34:19,  1.27it/s]
1|390|Loss: 1.8615151643753052:   2%|▏         | 389/25880 [07:31<5:34:19,  1.27it/s]
1|390|Loss: 1.8615151643753052:   2%|▏         | 390/25880 [07:31<4:55:48,  1.44it/s]
1|391|Loss: 2.1095778942108154:   2%|▏         | 390/25880 [07:32<4:55:48,  1.44it/s]
1|391|Loss: 2.1095778942108154:   2%|▏         | 391/25880 [07:32<4:36:27,  1.54it/s]
1|392|Loss: 1.6995242834091187:   2%|▏         | 391/25880 [07:32<4:36:27,  1.54it/s]
1|392|Loss: 1.6995242834091187:   2%|▏         | 392/25880 [07:33<4:30:51,  1.57it/s]
1|393|Loss: 1.3566399812698364:   2%|▏         | 392/25880 [07:33<4:30:51,  1.57it/s]
1|393|Loss: 1.3566399812698364:   2%|▏         | 393/25880 [07:33<4:41:08,  1.51it/s]
1|394|Loss: 1.5863300561904907:   2%|▏         | 393/25880 [07:34<4:41:08,  1.51it/s]
1|394|Loss: 1.5863300561904907:   2%|▏         | 394/25880 [07:34<4:52:12,  1.45it/s]
1|395|Loss: 1.570057988166809:   2%|▏         | 394/25880 [07:34<4:52:12,  1.45it/s] 
1|395|Loss: 1.570057988166809:   2%|▏         | 395/25880 [07:35<4:44:39,  1.49it/s]
1|396|Loss: 1.6981697082519531:   2%|▏         | 395/25880 [07:35<4:44:39,  1.49it/s]
1|396|Loss: 1.6981697082519531:   2%|▏         | 396/25880 [07:35<4:36:35,  1.54it/s]
1|397|Loss: 1.3200089931488037:   2%|▏         | 396/25880 [07:36<4:36:35,  1.54it/s]
1|397|Loss: 1.3200089931488037:   2%|▏         | 397/25880 [07:36<4:54:43,  1.44it/s]
1|398|Loss: 1.5071449279785156:   2%|▏         | 397/25880 [07:37<4:54:43,  1.44it/s]
1|398|Loss: 1.5071449279785156:   2%|▏         | 398/25880 [07:37<5:13:52,  1.35it/s]
1|399|Loss: 1.458797574043274:   2%|▏         | 398/25880 [07:37<5:13:52,  1.35it/s] 
1|399|Loss: 1.458797574043274:   2%|▏         | 399/25880 [07:38<5:13:58,  1.35it/s]
1|400|Loss: 1.556219458580017:   2%|▏         | 399/25880 [07:38<5:13:58,  1.35it/s]
1|400|Loss: 1.556219458580017:   2%|▏         | 400/25880 [07:38<5:02:35,  1.40it/s]
1|401|Loss: 1.4780726432800293:   2%|▏         | 400/25880 [07:39<5:02:35,  1.40it/s]
1|401|Loss: 1.4780726432800293:   2%|▏         | 401/25880 [07:39<5:01:54,  1.41it/s]
1|402|Loss: 1.5062084197998047:   2%|▏         | 401/25880 [07:39<5:01:54,  1.41it/s]
1|402|Loss: 1.5062084197998047:   2%|▏         | 402/25880 [07:40<5:11:26,  1.36it/s]
1|403|Loss: 1.6459773778915405:   2%|▏         | 402/25880 [07:40<5:11:26,  1.36it/s]
1|403|Loss: 1.6459773778915405:   2%|▏         | 403/25880 [07:40<4:51:32,  1.46it/s]
1|404|Loss: 1.3659473657608032:   2%|▏         | 403/25880 [07:41<4:51:32,  1.46it/s]
1|404|Loss: 1.3659473657608032:   2%|▏         | 404/25880 [07:41<4:36:14,  1.54it/s]
1|405|Loss: 1.3288235664367676:   2%|▏         | 404/25880 [07:41<4:36:14,  1.54it/s]
1|405|Loss: 1.3288235664367676:   2%|▏         | 405/25880 [07:42<4:33:05,  1.55it/s]
1|406|Loss: 1.4868073463439941:   2%|▏         | 405/25880 [07:42<4:33:05,  1.55it/s]
1|406|Loss: 1.4868073463439941:   2%|▏         | 406/25880 [07:42<4:51:42,  1.46it/s]
1|407|Loss: 1.3710429668426514:   2%|▏         | 406/25880 [07:43<4:51:42,  1.46it/s]
1|407|Loss: 1.3710429668426514:   2%|▏         | 407/25880 [07:43<4:59:28,  1.42it/s]
1|408|Loss: 1.5322566032409668:   2%|▏         | 407/25880 [07:43<4:59:28,  1.42it/s]
1|408|Loss: 1.5322566032409668:   2%|▏         | 408/25880 [07:44<4:58:42,  1.42it/s]
1|409|Loss: 1.3968279361724854:   2%|▏         | 408/25880 [07:44<4:58:42,  1.42it/s]
1|409|Loss: 1.3968279361724854:   2%|▏         | 409/25880 [07:45<5:06:43,  1.38it/s]
1|410|Loss: 1.3963723182678223:   2%|▏         | 409/25880 [07:45<5:06:43,  1.38it/s]
1|410|Loss: 1.3963723182678223:   2%|▏         | 410/25880 [07:45<5:14:24,  1.35it/s]
1|411|Loss: 1.3942335844039917:   2%|▏         | 410/25880 [07:46<5:14:24,  1.35it/s]
1|411|Loss: 1.3942335844039917:   2%|▏         | 411/25880 [07:46<5:16:23,  1.34it/s]
1|412|Loss: 1.304883360862732:   2%|▏         | 411/25880 [07:47<5:16:23,  1.34it/s] 
1|412|Loss: 1.304883360862732:   2%|▏         | 412/25880 [07:47<5:16:31,  1.34it/s]
1|413|Loss: 1.3097851276397705:   2%|▏         | 412/25880 [07:47<5:16:31,  1.34it/s]
1|413|Loss: 1.3097851276397705:   2%|▏         | 413/25880 [07:48<5:06:06,  1.39it/s]
1|414|Loss: 1.371976613998413:   2%|▏         | 413/25880 [07:48<5:06:06,  1.39it/s] 
1|414|Loss: 1.371976613998413:   2%|▏         | 414/25880 [07:48<5:04:43,  1.39it/s]
1|415|Loss: 1.2853010892868042:   2%|▏         | 414/25880 [07:49<5:04:43,  1.39it/s]
1|415|Loss: 1.2853010892868042:   2%|▏         | 415/25880 [07:49<5:03:18,  1.40it/s]
1|416|Loss: 1.4401299953460693:   2%|▏         | 415/25880 [07:49<5:03:18,  1.40it/s]
1|416|Loss: 1.4401299953460693:   2%|▏         | 416/25880 [07:50<5:06:16,  1.39it/s]
1|417|Loss: 1.3085893392562866:   2%|▏         | 416/25880 [07:50<5:06:16,  1.39it/s]
1|417|Loss: 1.3085893392562866:   2%|▏         | 417/25880 [07:50<4:56:00,  1.43it/s]
1|418|Loss: 1.3330247402191162:   2%|▏         | 417/25880 [07:51<4:56:00,  1.43it/s]
1|418|Loss: 1.3330247402191162:   2%|▏         | 418/25880 [07:51<5:10:03,  1.37it/s]
1|419|Loss: 1.5331193208694458:   2%|▏         | 418/25880 [07:52<5:10:03,  1.37it/s]
1|419|Loss: 1.5331193208694458:   2%|▏         | 419/25880 [07:52<5:14:13,  1.35it/s]
1|420|Loss: 1.2873904705047607:   2%|▏         | 419/25880 [07:52<5:14:13,  1.35it/s]
1|420|Loss: 1.2873904705047607:   2%|▏         | 420/25880 [07:53<5:13:39,  1.35it/s]
1|421|Loss: 1.2100958824157715:   2%|▏         | 420/25880 [07:53<5:13:39,  1.35it/s]
1|421|Loss: 1.2100958824157715:   2%|▏         | 421/25880 [07:53<5:18:45,  1.33it/s]
1|422|Loss: 1.5404565334320068:   2%|▏         | 421/25880 [07:54<5:18:45,  1.33it/s]
1|422|Loss: 1.5404565334320068:   2%|▏         | 422/25880 [07:54<5:07:39,  1.38it/s]
1|423|Loss: 1.2253001928329468:   2%|▏         | 422/25880 [07:54<5:07:39,  1.38it/s]
1|423|Loss: 1.2253001928329468:   2%|▏         | 423/25880 [07:55<5:20:57,  1.32it/s]
1|424|Loss: 1.289812684059143:   2%|▏         | 423/25880 [07:55<5:20:57,  1.32it/s] 
1|424|Loss: 1.289812684059143:   2%|▏         | 424/25880 [07:56<5:21:57,  1.32it/s]
1|425|Loss: 1.2729884386062622:   2%|▏         | 424/25880 [07:56<5:21:57,  1.32it/s]
1|425|Loss: 1.2729884386062622:   2%|▏         | 425/25880 [07:56<5:18:43,  1.33it/s]
1|426|Loss: 1.3076351881027222:   2%|▏         | 425/25880 [07:57<5:18:43,  1.33it/s]
1|426|Loss: 1.3076351881027222:   2%|▏         | 426/25880 [07:57<5:22:05,  1.32it/s]
1|427|Loss: 1.2430418729782104:   2%|▏         | 426/25880 [07:58<5:22:05,  1.32it/s]
1|427|Loss: 1.2430418729782104:   2%|▏         | 427/25880 [07:58<5:19:56,  1.33it/s]
1|428|Loss: 1.1836754083633423:   2%|▏         | 427/25880 [07:58<5:19:56,  1.33it/s]
1|428|Loss: 1.1836754083633423:   2%|▏         | 428/25880 [07:59<5:26:17,  1.30it/s]
1|429|Loss: 1.351170301437378:   2%|▏         | 428/25880 [07:59<5:26:17,  1.30it/s] 
1|429|Loss: 1.351170301437378:   2%|▏         | 429/25880 [07:59<5:20:04,  1.33it/s]
1|430|Loss: 1.2066643238067627:   2%|▏         | 429/25880 [08:00<5:20:04,  1.33it/s]
1|430|Loss: 1.2066643238067627:   2%|▏         | 430/25880 [08:00<4:52:53,  1.45it/s]
1|431|Loss: 1.4839524030685425:   2%|▏         | 430/25880 [08:00<4:52:53,  1.45it/s]
1|431|Loss: 1.4839524030685425:   2%|▏         | 431/25880 [08:00<4:23:42,  1.61it/s]
1|432|Loss: 1.3300094604492188:   2%|▏         | 431/25880 [08:01<4:23:42,  1.61it/s]
1|432|Loss: 1.3300094604492188:   2%|▏         | 432/25880 [08:01<4:15:44,  1.66it/s]
1|433|Loss: 1.3881897926330566:   2%|▏         | 432/25880 [08:01<4:15:44,  1.66it/s]
1|433|Loss: 1.3881897926330566:   2%|▏         | 433/25880 [08:02<4:24:57,  1.60it/s]
1|434|Loss: 1.3334237337112427:   2%|▏         | 433/25880 [08:02<4:24:57,  1.60it/s]
1|434|Loss: 1.3334237337112427:   2%|▏         | 434/25880 [08:02<4:43:54,  1.49it/s]
1|435|Loss: 1.4451251029968262:   2%|▏         | 434/25880 [08:03<4:43:54,  1.49it/s]
1|435|Loss: 1.4451251029968262:   2%|▏         | 435/25880 [08:03<5:08:42,  1.37it/s]
1|436|Loss: 1.3778568506240845:   2%|▏         | 435/25880 [08:04<5:08:42,  1.37it/s]
1|436|Loss: 1.3778568506240845:   2%|▏         | 436/25880 [08:04<5:13:58,  1.35it/s]
1|437|Loss: 1.2896872758865356:   2%|▏         | 436/25880 [08:04<5:13:58,  1.35it/s]
1|437|Loss: 1.2896872758865356:   2%|▏         | 437/25880 [08:05<5:09:24,  1.37it/s]
1|438|Loss: 1.4834065437316895:   2%|▏         | 437/25880 [08:05<5:09:24,  1.37it/s]
1|438|Loss: 1.4834065437316895:   2%|▏         | 438/25880 [08:06<5:18:31,  1.33it/s]
1|439|Loss: 1.3384522199630737:   2%|▏         | 438/25880 [08:06<5:18:31,  1.33it/s]
1|439|Loss: 1.3384522199630737:   2%|▏         | 439/25880 [08:06<5:19:56,  1.33it/s]
1|440|Loss: 1.3541405200958252:   2%|▏         | 439/25880 [08:07<5:19:56,  1.33it/s]
1|440|Loss: 1.3541405200958252:   2%|▏         | 440/25880 [08:07<5:19:56,  1.33it/s]
1|441|Loss: 1.2087373733520508:   2%|▏         | 440/25880 [08:08<5:19:56,  1.33it/s]
1|441|Loss: 1.2087373733520508:   2%|▏         | 441/25880 [08:08<5:25:41,  1.30it/s]
1|442|Loss: 1.4075491428375244:   2%|▏         | 441/25880 [08:08<5:25:41,  1.30it/s]
1|442|Loss: 1.4075491428375244:   2%|▏         | 442/25880 [08:09<5:34:04,  1.27it/s]
1|443|Loss: 1.3417690992355347:   2%|▏         | 442/25880 [08:09<5:34:04,  1.27it/s]
1|443|Loss: 1.3417690992355347:   2%|▏         | 443/25880 [08:09<5:18:20,  1.33it/s]
1|444|Loss: 1.5666625499725342:   2%|▏         | 443/25880 [08:10<5:18:20,  1.33it/s]
1|444|Loss: 1.5666625499725342:   2%|▏         | 444/25880 [08:10<5:09:31,  1.37it/s]
1|445|Loss: 1.4529253244400024:   2%|▏         | 444/25880 [08:10<5:09:31,  1.37it/s]
1|445|Loss: 1.4529253244400024:   2%|▏         | 445/25880 [08:11<4:43:24,  1.50it/s]
1|446|Loss: 1.6344317197799683:   2%|▏         | 445/25880 [08:11<4:43:24,  1.50it/s]
1|446|Loss: 1.6344317197799683:   2%|▏         | 446/25880 [08:11<4:54:25,  1.44it/s]
1|447|Loss: 1.2106428146362305:   2%|▏         | 446/25880 [08:12<4:54:25,  1.44it/s]
1|447|Loss: 1.2106428146362305:   2%|▏         | 447/25880 [08:12<5:01:11,  1.41it/s]
1|448|Loss: 1.185274362564087:   2%|▏         | 447/25880 [08:13<5:01:11,  1.41it/s] 
1|448|Loss: 1.185274362564087:   2%|▏         | 448/25880 [08:13<5:17:45,  1.33it/s]
1|449|Loss: 1.1808881759643555:   2%|▏         | 448/25880 [08:13<5:17:45,  1.33it/s]
1|449|Loss: 1.1808881759643555:   2%|▏         | 449/25880 [08:14<5:19:29,  1.33it/s]
1|450|Loss: 1.34249746799469:   2%|▏         | 449/25880 [08:14<5:19:29,  1.33it/s]  
1|450|Loss: 1.34249746799469:   2%|▏         | 450/25880 [08:14<5:16:20,  1.34it/s]
1|451|Loss: 1.3782652616500854:   2%|▏         | 450/25880 [08:15<5:16:20,  1.34it/s]
1|451|Loss: 1.3782652616500854:   2%|▏         | 451/25880 [08:15<5:14:13,  1.35it/s]
1|452|Loss: 1.3629164695739746:   2%|▏         | 451/25880 [08:16<5:14:13,  1.35it/s]
1|452|Loss: 1.3629164695739746:   2%|▏         | 452/25880 [08:16<4:50:18,  1.46it/s]
1|453|Loss: 1.2365005016326904:   2%|▏         | 452/25880 [08:16<4:50:18,  1.46it/s]
1|453|Loss: 1.2365005016326904:   2%|▏         | 453/25880 [08:16<4:39:21,  1.52it/s]
1|454|Loss: 1.0753482580184937:   2%|▏         | 453/25880 [08:17<4:39:21,  1.52it/s]
1|454|Loss: 1.0753482580184937:   2%|▏         | 454/25880 [08:17<4:34:07,  1.55it/s]
1|455|Loss: 1.2030166387557983:   2%|▏         | 454/25880 [08:17<4:34:07,  1.55it/s]
1|455|Loss: 1.2030166387557983:   2%|▏         | 455/25880 [08:18<4:41:50,  1.50it/s]
1|456|Loss: 1.224193811416626:   2%|▏         | 455/25880 [08:18<4:41:50,  1.50it/s] 
1|456|Loss: 1.224193811416626:   2%|▏         | 456/25880 [08:18<4:40:23,  1.51it/s]
1|457|Loss: 1.173903226852417:   2%|▏         | 456/25880 [08:19<4:40:23,  1.51it/s]
1|457|Loss: 1.173903226852417:   2%|▏         | 457/25880 [08:19<5:02:12,  1.40it/s]
1|458|Loss: 1.1098304986953735:   2%|▏         | 457/25880 [08:20<5:02:12,  1.40it/s]
1|458|Loss: 1.1098304986953735:   2%|▏         | 458/25880 [08:20<5:09:27,  1.37it/s]
1|459|Loss: 1.5337650775909424:   2%|▏         | 458/25880 [08:20<5:09:27,  1.37it/s]
1|459|Loss: 1.5337650775909424:   2%|▏         | 459/25880 [08:21<5:00:43,  1.41it/s]
1|460|Loss: 1.2296700477600098:   2%|▏         | 459/25880 [08:21<5:00:43,  1.41it/s]
1|460|Loss: 1.2296700477600098:   2%|▏         | 460/25880 [08:21<5:00:21,  1.41it/s]
1|461|Loss: 1.1883577108383179:   2%|▏         | 460/25880 [08:22<5:00:21,  1.41it/s]
1|461|Loss: 1.1883577108383179:   2%|▏         | 461/25880 [08:22<5:09:52,  1.37it/s]
1|462|Loss: 1.1608632802963257:   2%|▏         | 461/25880 [08:22<5:09:52,  1.37it/s]
1|462|Loss: 1.1608632802963257:   2%|▏         | 462/25880 [08:23<5:13:11,  1.35it/s]
1|463|Loss: 1.1510601043701172:   2%|▏         | 462/25880 [08:23<5:13:11,  1.35it/s]
1|463|Loss: 1.1510601043701172:   2%|▏         | 463/25880 [08:24<5:20:49,  1.32it/s]
1|464|Loss: 1.2505152225494385:   2%|▏         | 463/25880 [08:24<5:20:49,  1.32it/s]
1|464|Loss: 1.2505152225494385:   2%|▏         | 464/25880 [08:24<5:18:53,  1.33it/s]
1|465|Loss: 1.2143499851226807:   2%|▏         | 464/25880 [08:25<5:18:53,  1.33it/s]
1|465|Loss: 1.2143499851226807:   2%|▏         | 465/25880 [08:25<4:57:48,  1.42it/s]
1|466|Loss: 1.2965099811553955:   2%|▏         | 465/25880 [08:25<4:57:48,  1.42it/s]
1|466|Loss: 1.2965099811553955:   2%|▏         | 466/25880 [08:26<4:38:19,  1.52it/s]
1|467|Loss: 1.4693740606307983:   2%|▏         | 466/25880 [08:26<4:38:19,  1.52it/s]
1|467|Loss: 1.4693740606307983:   2%|▏         | 467/25880 [08:26<4:14:12,  1.67it/s]
1|468|Loss: 2.0149993896484375:   2%|▏         | 467/25880 [08:26<4:14:12,  1.67it/s]
1|468|Loss: 2.0149993896484375:   2%|▏         | 468/25880 [08:26<3:58:01,  1.78it/s]
1|469|Loss: 1.3012824058532715:   2%|▏         | 468/25880 [08:27<3:58:01,  1.78it/s]
1|469|Loss: 1.3012824058532715:   2%|▏         | 469/25880 [08:27<4:10:27,  1.69it/s]
1|470|Loss: 1.2131379842758179:   2%|▏         | 469/25880 [08:28<4:10:27,  1.69it/s]
1|470|Loss: 1.2131379842758179:   2%|▏         | 470/25880 [08:28<4:32:37,  1.55it/s]
1|471|Loss: 1.207648515701294:   2%|▏         | 470/25880 [08:28<4:32:37,  1.55it/s] 
1|471|Loss: 1.207648515701294:   2%|▏         | 471/25880 [08:29<4:45:53,  1.48it/s]
1|472|Loss: 1.317145824432373:   2%|▏         | 471/25880 [08:29<4:45:53,  1.48it/s]
1|472|Loss: 1.317145824432373:   2%|▏         | 472/25880 [08:29<4:53:01,  1.45it/s]
1|473|Loss: 1.1639564037322998:   2%|▏         | 472/25880 [08:30<4:53:01,  1.45it/s]
1|473|Loss: 1.1639564037322998:   2%|▏         | 473/25880 [08:30<5:17:12,  1.33it/s]
1|474|Loss: 1.1640011072158813:   2%|▏         | 473/25880 [08:31<5:17:12,  1.33it/s]
1|474|Loss: 1.1640011072158813:   2%|▏         | 474/25880 [08:31<5:30:04,  1.28it/s]
1|475|Loss: 1.2398478984832764:   2%|▏         | 474/25880 [08:32<5:30:04,  1.28it/s]
1|475|Loss: 1.2398478984832764:   2%|▏         | 475/25880 [08:32<5:27:07,  1.29it/s]
1|476|Loss: 1.0528264045715332:   2%|▏         | 475/25880 [08:32<5:27:07,  1.29it/s]
1|476|Loss: 1.0528264045715332:   2%|▏         | 476/25880 [08:33<5:34:04,  1.27it/s]
1|477|Loss: 1.1275346279144287:   2%|▏         | 476/25880 [08:33<5:34:04,  1.27it/s]
1|477|Loss: 1.1275346279144287:   2%|▏         | 477/25880 [08:34<5:42:38,  1.24it/s]
1|478|Loss: 1.1617748737335205:   2%|▏         | 477/25880 [08:34<5:42:38,  1.24it/s]
1|478|Loss: 1.1617748737335205:   2%|▏         | 478/25880 [08:34<5:50:55,  1.21it/s]
1|479|Loss: 1.1410313844680786:   2%|▏         | 478/25880 [08:35<5:50:55,  1.21it/s]
1|479|Loss: 1.1410313844680786:   2%|▏         | 479/25880 [08:35<6:01:50,  1.17it/s]
1|480|Loss: 1.2887591123580933:   2%|▏         | 479/25880 [08:36<6:01:50,  1.17it/s]
1|480|Loss: 1.2887591123580933:   2%|▏         | 480/25880 [08:36<5:50:13,  1.21it/s]
1|481|Loss: 1.196967363357544:   2%|▏         | 480/25880 [08:36<5:50:13,  1.21it/s] 
1|481|Loss: 1.196967363357544:   2%|▏         | 481/25880 [08:37<5:38:02,  1.25it/s]
1|482|Loss: 1.2604846954345703:   2%|▏         | 481/25880 [08:37<5:38:02,  1.25it/s]
1|482|Loss: 1.2604846954345703:   2%|▏         | 482/25880 [08:38<5:25:21,  1.30it/s]
1|483|Loss: 1.1643521785736084:   2%|▏         | 482/25880 [08:38<5:25:21,  1.30it/s]
1|483|Loss: 1.1643521785736084:   2%|▏         | 483/25880 [08:38<5:08:10,  1.37it/s]
1|484|Loss: 1.2214897871017456:   2%|▏         | 483/25880 [08:39<5:08:10,  1.37it/s]
1|484|Loss: 1.2214897871017456:   2%|▏         | 484/25880 [08:39<5:11:24,  1.36it/s]
1|485|Loss: 1.0468491315841675:   2%|▏         | 484/25880 [08:39<5:11:24,  1.36it/s]
1|485|Loss: 1.0468491315841675:   2%|▏         | 485/25880 [08:40<5:25:59,  1.30it/s]
1|486|Loss: 1.112677812576294:   2%|▏         | 485/25880 [08:40<5:25:59,  1.30it/s] 
1|486|Loss: 1.112677812576294:   2%|▏         | 486/25880 [08:40<5:16:16,  1.34it/s]
1|487|Loss: 1.1080739498138428:   2%|▏         | 486/25880 [08:41<5:16:16,  1.34it/s]
1|487|Loss: 1.1080739498138428:   2%|▏         | 487/25880 [08:41<5:00:02,  1.41it/s]
1|488|Loss: 1.2611417770385742:   2%|▏         | 487/25880 [08:41<5:00:02,  1.41it/s]
1|488|Loss: 1.2611417770385742:   2%|▏         | 488/25880 [08:42<5:13:52,  1.35it/s]
1|489|Loss: 1.2407091856002808:   2%|▏         | 488/25880 [08:42<5:13:52,  1.35it/s]
1|489|Loss: 1.2407091856002808:   2%|▏         | 489/25880 [08:43<5:06:33,  1.38it/s]
1|490|Loss: 1.1470485925674438:   2%|▏         | 489/25880 [08:43<5:06:33,  1.38it/s]
1|490|Loss: 1.1470485925674438:   2%|▏         | 490/25880 [08:43<4:42:55,  1.50it/s]
1|491|Loss: 1.1495646238327026:   2%|▏         | 490/25880 [08:43<4:42:55,  1.50it/s]
1|491|Loss: 1.1495646238327026:   2%|▏         | 491/25880 [08:44<4:45:59,  1.48it/s]
1|492|Loss: 1.1525013446807861:   2%|▏         | 491/25880 [08:44<4:45:59,  1.48it/s]
1|492|Loss: 1.1525013446807861:   2%|▏         | 492/25880 [08:45<5:03:40,  1.39it/s]
1|493|Loss: 1.1295429468154907:   2%|▏         | 492/25880 [08:45<5:03:40,  1.39it/s]
1|493|Loss: 1.1295429468154907:   2%|▏         | 493/25880 [08:45<4:52:30,  1.45it/s]
1|494|Loss: 1.1455740928649902:   2%|▏         | 493/25880 [08:46<4:52:30,  1.45it/s]
1|494|Loss: 1.1455740928649902:   2%|▏         | 494/25880 [08:46<4:53:38,  1.44it/s]
1|495|Loss: 1.0620416402816772:   2%|▏         | 494/25880 [08:46<4:53:38,  1.44it/s]
1|495|Loss: 1.0620416402816772:   2%|▏         | 495/25880 [08:47<5:05:45,  1.38it/s]
1|496|Loss: 1.1842889785766602:   2%|▏         | 495/25880 [08:47<5:05:45,  1.38it/s]
1|496|Loss: 1.1842889785766602:   2%|▏         | 496/25880 [08:47<5:05:32,  1.38it/s]
1|497|Loss: 1.2265450954437256:   2%|▏         | 496/25880 [08:48<5:05:32,  1.38it/s]
1|497|Loss: 1.2265450954437256:   2%|▏         | 497/25880 [08:48<5:11:52,  1.36it/s]
1|498|Loss: 1.1405879259109497:   2%|▏         | 497/25880 [08:49<5:11:52,  1.36it/s]
1|498|Loss: 1.1405879259109497:   2%|▏         | 498/25880 [08:49<5:09:43,  1.37it/s]
1|499|Loss: 1.3887947797775269:   2%|▏         | 498/25880 [08:49<5:09:43,  1.37it/s]
1|499|Loss: 1.3887947797775269:   2%|▏         | 499/25880 [08:50<5:05:51,  1.38it/s]
1|500|Loss: 1.138332486152649:   2%|▏         | 499/25880 [08:50<5:05:51,  1.38it/s] 
1|500|Loss: 1.138332486152649:   2%|▏         | 500/25880 [08:50<5:06:03,  1.38it/s]
1|501|Loss: 1.037952184677124:   2%|▏         | 500/25880 [08:51<5:06:03,  1.38it/s]
1|501|Loss: 1.037952184677124:   2%|▏         | 501/25880 [08:51<5:07:25,  1.38it/s]
1|502|Loss: 1.221985101699829:   2%|▏         | 501/25880 [08:51<5:07:25,  1.38it/s]
1|502|Loss: 1.221985101699829:   2%|▏         | 502/25880 [08:52<4:58:47,  1.42it/s]
1|503|Loss: 1.068649411201477:   2%|▏         | 502/25880 [08:52<4:58:47,  1.42it/s]
1|503|Loss: 1.068649411201477:   2%|▏         | 503/25880 [08:52<5:00:51,  1.41it/s]
1|504|Loss: 1.1167510747909546:   2%|▏         | 503/25880 [08:53<5:00:51,  1.41it/s]
1|504|Loss: 1.1167510747909546:   2%|▏         | 504/25880 [08:53<5:05:57,  1.38it/s]
1|505|Loss: 1.2066982984542847:   2%|▏         | 504/25880 [08:54<5:05:57,  1.38it/s]
1|505|Loss: 1.2066982984542847:   2%|▏         | 505/25880 [08:54<5:06:47,  1.38it/s]
1|506|Loss: 1.0724809169769287:   2%|▏         | 505/25880 [08:54<5:06:47,  1.38it/s]
1|506|Loss: 1.0724809169769287:   2%|▏         | 506/25880 [08:55<4:55:38,  1.43it/s]
1|507|Loss: 1.095848560333252:   2%|▏         | 506/25880 [08:55<4:55:38,  1.43it/s] 
1|507|Loss: 1.095848560333252:   2%|▏         | 507/25880 [08:55<4:32:10,  1.55it/s]
1|508|Loss: 1.2559620141983032:   2%|▏         | 507/25880 [08:55<4:32:10,  1.55it/s]
1|508|Loss: 1.2559620141983032:   2%|▏         | 508/25880 [08:56<4:33:36,  1.55it/s]
1|509|Loss: 1.1498050689697266:   2%|▏         | 508/25880 [08:56<4:33:36,  1.55it/s]
1|509|Loss: 1.1498050689697266:   2%|▏         | 509/25880 [08:56<4:28:17,  1.58it/s]
1|510|Loss: 1.077315092086792:   2%|▏         | 509/25880 [08:57<4:28:17,  1.58it/s] 
1|510|Loss: 1.077315092086792:   2%|▏         | 510/25880 [08:57<4:27:25,  1.58it/s]
1|511|Loss: 0.9641885161399841:   2%|▏         | 510/25880 [08:57<4:27:25,  1.58it/s]
1|511|Loss: 0.9641885161399841:   2%|▏         | 511/25880 [08:58<4:50:09,  1.46it/s]
1|512|Loss: 1.1297978162765503:   2%|▏         | 511/25880 [08:58<4:50:09,  1.46it/s]
1|512|Loss: 1.1297978162765503:   2%|▏         | 512/25880 [08:59<5:23:40,  1.31it/s]
1|513|Loss: 0.9183921813964844:   2%|▏         | 512/25880 [08:59<5:23:40,  1.31it/s]
1|513|Loss: 0.9183921813964844:   2%|▏         | 513/25880 [09:00<5:54:02,  1.19it/s]
1|514|Loss: 1.29655122756958:   2%|▏         | 513/25880 [09:00<5:54:02,  1.19it/s]  
1|514|Loss: 1.29655122756958:   2%|▏         | 514/25880 [09:01<5:48:56,  1.21it/s]
1|515|Loss: 1.945358395576477:   2%|▏         | 514/25880 [09:01<5:48:56,  1.21it/s]
1|515|Loss: 1.945358395576477:   2%|▏         | 515/25880 [09:01<5:36:40,  1.26it/s]
1|516|Loss: 2.51654052734375:   2%|▏         | 515/25880 [09:02<5:36:40,  1.26it/s] 
1|516|Loss: 2.51654052734375:   2%|▏         | 516/25880 [09:02<5:28:50,  1.29it/s]
1|517|Loss: 1.455950140953064:   2%|▏         | 516/25880 [09:02<5:28:50,  1.29it/s]
1|517|Loss: 1.455950140953064:   2%|▏         | 517/25880 [09:03<5:20:24,  1.32it/s]
1|518|Loss: 1.0994298458099365:   2%|▏         | 517/25880 [09:03<5:20:24,  1.32it/s]
1|518|Loss: 1.0994298458099365:   2%|▏         | 518/25880 [09:04<5:21:43,  1.31it/s]
1|519|Loss: 1.1845649480819702:   2%|▏         | 518/25880 [09:04<5:21:43,  1.31it/s]
1|519|Loss: 1.1845649480819702:   2%|▏         | 519/25880 [09:04<5:10:33,  1.36it/s]
1|520|Loss: 1.222554326057434:   2%|▏         | 519/25880 [09:04<5:10:33,  1.36it/s] 
1|520|Loss: 1.222554326057434:   2%|▏         | 520/25880 [09:05<4:29:59,  1.57it/s]
1|521|Loss: 1.353136420249939:   2%|▏         | 520/25880 [09:05<4:29:59,  1.57it/s]
1|521|Loss: 1.353136420249939:   2%|▏         | 521/25880 [09:05<4:23:27,  1.60it/s]
1|522|Loss: 1.1661880016326904:   2%|▏         | 521/25880 [09:06<4:23:27,  1.60it/s]
1|522|Loss: 1.1661880016326904:   2%|▏         | 522/25880 [09:06<4:44:31,  1.49it/s]
1|523|Loss: 1.1101844310760498:   2%|▏         | 522/25880 [09:06<4:44:31,  1.49it/s]
1|523|Loss: 1.1101844310760498:   2%|▏         | 523/25880 [09:07<4:55:37,  1.43it/s]
1|524|Loss: 1.0509033203125:   2%|▏         | 523/25880 [09:07<4:55:37,  1.43it/s]   
1|524|Loss: 1.0509033203125:   2%|▏         | 524/25880 [09:08<5:19:25,  1.32it/s]
1|525|Loss: 1.0132391452789307:   2%|▏         | 524/25880 [09:08<5:19:25,  1.32it/s]
1|525|Loss: 1.0132391452789307:   2%|▏         | 525/25880 [09:08<5:11:05,  1.36it/s]
1|526|Loss: 1.2737212181091309:   2%|▏         | 525/25880 [09:09<5:11:05,  1.36it/s]
1|526|Loss: 1.2737212181091309:   2%|▏         | 526/25880 [09:09<4:55:37,  1.43it/s]
1|527|Loss: 1.2317121028900146:   2%|▏         | 526/25880 [09:09<4:55:37,  1.43it/s]
1|527|Loss: 1.2317121028900146:   2%|▏         | 527/25880 [09:10<5:04:17,  1.39it/s]
1|528|Loss: 1.241642951965332:   2%|▏         | 527/25880 [09:10<5:04:17,  1.39it/s] 
1|528|Loss: 1.241642951965332:   2%|▏         | 528/25880 [09:11<5:15:36,  1.34it/s]
1|529|Loss: 1.0853161811828613:   2%|▏         | 528/25880 [09:11<5:15:36,  1.34it/s]
1|529|Loss: 1.0853161811828613:   2%|▏         | 529/25880 [09:11<5:25:41,  1.30it/s]
1|530|Loss: 1.1007732152938843:   2%|▏         | 529/25880 [09:12<5:25:41,  1.30it/s]
1|530|Loss: 1.1007732152938843:   2%|▏         | 530/25880 [09:12<5:41:58,  1.24it/s]
1|531|Loss: 1.0805844068527222:   2%|▏         | 530/25880 [09:13<5:41:58,  1.24it/s]
1|531|Loss: 1.0805844068527222:   2%|▏         | 531/25880 [09:13<5:55:51,  1.19it/s]
1|532|Loss: 1.0318918228149414:   2%|▏         | 531/25880 [09:14<5:55:51,  1.19it/s]
1|532|Loss: 1.0318918228149414:   2%|▏         | 532/25880 [09:14<5:46:24,  1.22it/s]
1|533|Loss: 1.1741994619369507:   2%|▏         | 532/25880 [09:14<5:46:24,  1.22it/s]
1|533|Loss: 1.1741994619369507:   2%|▏         | 533/25880 [09:15<5:36:04,  1.26it/s]
1|534|Loss: 1.1883279085159302:   2%|▏         | 533/25880 [09:15<5:36:04,  1.26it/s]
1|534|Loss: 1.1883279085159302:   2%|▏         | 534/25880 [09:15<5:34:47,  1.26it/s]
1|535|Loss: 1.0210485458374023:   2%|▏         | 534/25880 [09:16<5:34:47,  1.26it/s]
1|535|Loss: 1.0210485458374023:   2%|▏         | 535/25880 [09:16<5:29:42,  1.28it/s]
1|536|Loss: 1.0210669040679932:   2%|▏         | 535/25880 [09:17<5:29:42,  1.28it/s]
1|536|Loss: 1.0210669040679932:   2%|▏         | 536/25880 [09:17<5:25:51,  1.30it/s]
1|537|Loss: 1.1117788553237915:   2%|▏         | 536/25880 [09:17<5:25:51,  1.30it/s]
1|537|Loss: 1.1117788553237915:   2%|▏         | 537/25880 [09:18<5:12:49,  1.35it/s]
1|538|Loss: 1.0533473491668701:   2%|▏         | 537/25880 [09:18<5:12:49,  1.35it/s]
1|538|Loss: 1.0533473491668701:   2%|▏         | 538/25880 [09:18<4:59:31,  1.41it/s]
1|539|Loss: 1.0847015380859375:   2%|▏         | 538/25880 [09:19<4:59:31,  1.41it/s]
1|539|Loss: 1.0847015380859375:   2%|▏         | 539/25880 [09:19<4:59:53,  1.41it/s]
1|540|Loss: 1.0999616384506226:   2%|▏         | 539/25880 [09:19<4:59:53,  1.41it/s]
1|540|Loss: 1.0999616384506226:   2%|▏         | 540/25880 [09:20<5:07:42,  1.37it/s]
1|541|Loss: 1.2056145668029785:   2%|▏         | 540/25880 [09:20<5:07:42,  1.37it/s]
1|541|Loss: 1.2056145668029785:   2%|▏         | 541/25880 [09:20<4:58:42,  1.41it/s]
1|542|Loss: 1.1807665824890137:   2%|▏         | 541/25880 [09:21<4:58:42,  1.41it/s]
1|542|Loss: 1.1807665824890137:   2%|▏         | 542/25880 [09:21<5:00:38,  1.40it/s]
1|543|Loss: 1.1161147356033325:   2%|▏         | 542/25880 [09:22<5:00:38,  1.40it/s]
1|543|Loss: 1.1161147356033325:   2%|▏         | 543/25880 [09:22<5:03:04,  1.39it/s]
1|544|Loss: 1.1385265588760376:   2%|▏         | 543/25880 [09:22<5:03:04,  1.39it/s]
1|544|Loss: 1.1385265588760376:   2%|▏         | 544/25880 [09:23<5:06:37,  1.38it/s]
1|545|Loss: 1.0429739952087402:   2%|▏         | 544/25880 [09:23<5:06:37,  1.38it/s]
1|545|Loss: 1.0429739952087402:   2%|▏         | 545/25880 [09:23<5:05:22,  1.38it/s]
1|546|Loss: 0.9818318486213684:   2%|▏         | 545/25880 [09:24<5:05:22,  1.38it/s]
1|546|Loss: 0.9818318486213684:   2%|▏         | 546/25880 [09:24<5:02:33,  1.40it/s]
1|547|Loss: 1.3175630569458008:   2%|▏         | 546/25880 [09:24<5:02:33,  1.40it/s]
1|547|Loss: 1.3175630569458008:   2%|▏         | 547/25880 [09:25<4:59:27,  1.41it/s]
1|548|Loss: 1.201004147529602:   2%|▏         | 547/25880 [09:25<4:59:27,  1.41it/s] 
1|548|Loss: 1.201004147529602:   2%|▏         | 548/25880 [09:25<4:48:38,  1.46it/s]
1|549|Loss: 1.0817979574203491:   2%|▏         | 548/25880 [09:26<4:48:38,  1.46it/s]
1|549|Loss: 1.0817979574203491:   2%|▏         | 549/25880 [09:26<4:40:08,  1.51it/s]
1|550|Loss: 1.0616872310638428:   2%|▏         | 549/25880 [09:26<4:40:08,  1.51it/s]
1|550|Loss: 1.0616872310638428:   2%|▏         | 550/25880 [09:27<4:56:33,  1.42it/s]
1|551|Loss: 0.9312084913253784:   2%|▏         | 550/25880 [09:27<4:56:33,  1.42it/s]
1|551|Loss: 0.9312084913253784:   2%|▏         | 551/25880 [09:28<5:16:27,  1.33it/s]
1|552|Loss: 1.0390383005142212:   2%|▏         | 551/25880 [09:28<5:16:27,  1.33it/s]
1|552|Loss: 1.0390383005142212:   2%|▏         | 552/25880 [09:28<5:17:25,  1.33it/s]
1|553|Loss: 0.9962058663368225:   2%|▏         | 552/25880 [09:29<5:17:25,  1.33it/s]
1|553|Loss: 0.9962058663368225:   2%|▏         | 553/25880 [09:29<5:10:33,  1.36it/s]
1|554|Loss: 0.9790336489677429:   2%|▏         | 553/25880 [09:29<5:10:33,  1.36it/s]
1|554|Loss: 0.9790336489677429:   2%|▏         | 554/25880 [09:30<5:18:03,  1.33it/s]
1|555|Loss: 1.0662133693695068:   2%|▏         | 554/25880 [09:30<5:18:03,  1.33it/s]
1|555|Loss: 1.0662133693695068:   2%|▏         | 555/25880 [09:30<5:01:58,  1.40it/s]
1|556|Loss: 1.1765917539596558:   2%|▏         | 555/25880 [09:31<5:01:58,  1.40it/s]
1|556|Loss: 1.1765917539596558:   2%|▏         | 556/25880 [09:31<4:48:49,  1.46it/s]
1|557|Loss: 1.1890405416488647:   2%|▏         | 556/25880 [09:31<4:48:49,  1.46it/s]
1|557|Loss: 1.1890405416488647:   2%|▏         | 557/25880 [09:32<4:30:03,  1.56it/s]
1|558|Loss: 1.1123692989349365:   2%|▏         | 557/25880 [09:32<4:30:03,  1.56it/s]
1|558|Loss: 1.1123692989349365:   2%|▏         | 558/25880 [09:32<4:36:51,  1.52it/s]
1|559|Loss: 1.0471820831298828:   2%|▏         | 558/25880 [09:33<4:36:51,  1.52it/s]
1|559|Loss: 1.0471820831298828:   2%|▏         | 559/25880 [09:33<4:48:24,  1.46it/s]
1|560|Loss: 0.8892609477043152:   2%|▏         | 559/25880 [09:33<4:48:24,  1.46it/s]
1|560|Loss: 0.8892609477043152:   2%|▏         | 560/25880 [09:34<4:45:19,  1.48it/s]
1|561|Loss: 1.1067525148391724:   2%|▏         | 560/25880 [09:34<4:45:19,  1.48it/s]
1|561|Loss: 1.1067525148391724:   2%|▏         | 561/25880 [09:35<5:03:05,  1.39it/s]
1|562|Loss: 1.144199252128601:   2%|▏         | 561/25880 [09:35<5:03:05,  1.39it/s] 
1|562|Loss: 1.144199252128601:   2%|▏         | 562/25880 [09:35<4:50:33,  1.45it/s]
1|563|Loss: 1.0181176662445068:   2%|▏         | 562/25880 [09:36<4:50:33,  1.45it/s]
1|563|Loss: 1.0181176662445068:   2%|▏         | 563/25880 [09:36<5:02:02,  1.40it/s]
1|564|Loss: 1.1014925241470337:   2%|▏         | 563/25880 [09:36<5:02:02,  1.40it/s]
1|564|Loss: 1.1014925241470337:   2%|▏         | 564/25880 [09:37<5:21:36,  1.31it/s]
1|565|Loss: 1.1134040355682373:   2%|▏         | 564/25880 [09:37<5:21:36,  1.31it/s]
1|565|Loss: 1.1134040355682373:   2%|▏         | 565/25880 [09:38<5:32:30,  1.27it/s]
1|566|Loss: 1.08319890499115:   2%|▏         | 565/25880 [09:38<5:32:30,  1.27it/s]  
1|566|Loss: 1.08319890499115:   2%|▏         | 566/25880 [09:38<5:12:10,  1.35it/s]
1|567|Loss: 1.1419731378555298:   2%|▏         | 566/25880 [09:39<5:12:10,  1.35it/s]
1|567|Loss: 1.1419731378555298:   2%|▏         | 567/25880 [09:39<4:56:42,  1.42it/s]
1|568|Loss: 1.117103099822998:   2%|▏         | 567/25880 [09:39<4:56:42,  1.42it/s] 
1|568|Loss: 1.117103099822998:   2%|▏         | 568/25880 [09:40<5:10:21,  1.36it/s]
1|569|Loss: 0.9889201521873474:   2%|▏         | 568/25880 [09:40<5:10:21,  1.36it/s]
1|569|Loss: 0.9889201521873474:   2%|▏         | 569/25880 [09:41<5:27:53,  1.29it/s]
1|570|Loss: 0.983420729637146:   2%|▏         | 569/25880 [09:41<5:27:53,  1.29it/s] 
1|570|Loss: 0.983420729637146:   2%|▏         | 570/25880 [09:41<5:31:59,  1.27it/s]
1|571|Loss: 0.9513450860977173:   2%|▏         | 570/25880 [09:42<5:31:59,  1.27it/s]
1|571|Loss: 0.9513450860977173:   2%|▏         | 571/25880 [09:42<5:38:56,  1.24it/s]
1|572|Loss: 0.9543721079826355:   2%|▏         | 571/25880 [09:43<5:38:56,  1.24it/s]
1|572|Loss: 0.9543721079826355:   2%|▏         | 572/25880 [09:43<5:38:38,  1.25it/s]
1|573|Loss: 0.9978671669960022:   2%|▏         | 572/25880 [09:43<5:38:38,  1.25it/s]
1|573|Loss: 0.9978671669960022:   2%|▏         | 573/25880 [09:44<5:16:20,  1.33it/s]
1|574|Loss: 1.0878305435180664:   2%|▏         | 573/25880 [09:44<5:16:20,  1.33it/s]
1|574|Loss: 1.0878305435180664:   2%|▏         | 574/25880 [09:44<4:51:43,  1.45it/s]
1|575|Loss: 1.0845588445663452:   2%|▏         | 574/25880 [09:45<4:51:43,  1.45it/s]
1|575|Loss: 1.0845588445663452:   2%|▏         | 575/25880 [09:45<4:57:37,  1.42it/s]
1|576|Loss: 0.941868007183075:   2%|▏         | 575/25880 [09:45<4:57:37,  1.42it/s] 
1|576|Loss: 0.941868007183075:   2%|▏         | 576/25880 [09:46<5:10:26,  1.36it/s]
1|577|Loss: 1.036310076713562:   2%|▏         | 576/25880 [09:46<5:10:26,  1.36it/s]
1|577|Loss: 1.036310076713562:   2%|▏         | 577/25880 [09:47<5:23:21,  1.30it/s]
1|578|Loss: 1.0176846981048584:   2%|▏         | 577/25880 [09:47<5:23:21,  1.30it/s]
1|578|Loss: 1.0176846981048584:   2%|▏         | 578/25880 [09:47<5:10:42,  1.36it/s]
1|579|Loss: 1.1579265594482422:   2%|▏         | 578/25880 [09:48<5:10:42,  1.36it/s]
1|579|Loss: 1.1579265594482422:   2%|▏         | 579/25880 [09:48<4:55:33,  1.43it/s]
1|580|Loss: 0.9743635058403015:   2%|▏         | 579/25880 [09:48<4:55:33,  1.43it/s]
1|580|Loss: 0.9743635058403015:   2%|▏         | 580/25880 [09:49<5:03:17,  1.39it/s]
1|581|Loss: 0.9603372812271118:   2%|▏         | 580/25880 [09:49<5:03:17,  1.39it/s]
1|581|Loss: 0.9603372812271118:   2%|▏         | 581/25880 [09:49<5:13:08,  1.35it/s]
1|582|Loss: 1.2460556030273438:   2%|▏         | 581/25880 [09:50<5:13:08,  1.35it/s]
1|582|Loss: 1.2460556030273438:   2%|▏         | 582/25880 [09:50<5:26:57,  1.29it/s]
1|583|Loss: 0.9440760016441345:   2%|▏         | 582/25880 [09:51<5:26:57,  1.29it/s]
1|583|Loss: 0.9440760016441345:   2%|▏         | 583/25880 [09:51<5:26:35,  1.29it/s]
1|584|Loss: 1.0869961977005005:   2%|▏         | 583/25880 [09:51<5:26:35,  1.29it/s]
1|584|Loss: 1.0869961977005005:   2%|▏         | 584/25880 [09:52<5:09:46,  1.36it/s]
1|585|Loss: 1.1354342699050903:   2%|▏         | 584/25880 [09:52<5:09:46,  1.36it/s]
1|585|Loss: 1.1354342699050903:   2%|▏         | 585/25880 [09:52<4:47:53,  1.46it/s]
1|586|Loss: 1.086527943611145:   2%|▏         | 585/25880 [09:53<4:47:53,  1.46it/s] 
1|586|Loss: 1.086527943611145:   2%|▏         | 586/25880 [09:53<4:38:58,  1.51it/s]
1|587|Loss: 1.2521085739135742:   2%|▏         | 586/25880 [09:53<4:38:58,  1.51it/s]
1|587|Loss: 1.2521085739135742:   2%|▏         | 587/25880 [09:54<4:45:37,  1.48it/s]
1|588|Loss: 1.536267876625061:   2%|▏         | 587/25880 [09:54<4:45:37,  1.48it/s] 
1|588|Loss: 1.536267876625061:   2%|▏         | 588/25880 [09:54<4:43:02,  1.49it/s]
1|589|Loss: 2.9961671829223633:   2%|▏         | 588/25880 [09:55<4:43:02,  1.49it/s]
1|589|Loss: 2.9961671829223633:   2%|▏         | 589/25880 [09:55<4:58:17,  1.41it/s]
1|590|Loss: 2.5104119777679443:   2%|▏         | 589/25880 [09:55<4:58:17,  1.41it/s]
1|590|Loss: 2.5104119777679443:   2%|▏         | 590/25880 [09:56<5:10:13,  1.36it/s]
1|591|Loss: 2.20234751701355:   2%|▏         | 590/25880 [09:56<5:10:13,  1.36it/s]  
1|591|Loss: 2.20234751701355:   2%|▏         | 591/25880 [09:57<5:01:09,  1.40it/s]
1|592|Loss: 1.821410894393921:   2%|▏         | 591/25880 [09:57<5:01:09,  1.40it/s]
1|592|Loss: 1.821410894393921:   2%|▏         | 592/25880 [09:57<5:00:13,  1.40it/s]
1|593|Loss: 1.4543936252593994:   2%|▏         | 592/25880 [09:58<5:00:13,  1.40it/s]
1|593|Loss: 1.4543936252593994:   2%|▏         | 593/25880 [09:58<5:01:44,  1.40it/s]
1|594|Loss: 1.469466209411621:   2%|▏         | 593/25880 [09:58<5:01:44,  1.40it/s] 
1|594|Loss: 1.469466209411621:   2%|▏         | 594/25880 [09:59<5:04:44,  1.38it/s]
1|595|Loss: 1.327880620956421:   2%|▏         | 594/25880 [09:59<5:04:44,  1.38it/s]
1|595|Loss: 1.327880620956421:   2%|▏         | 595/25880 [09:59<5:06:16,  1.38it/s]
1|596|Loss: 1.2065746784210205:   2%|▏         | 595/25880 [10:00<5:06:16,  1.38it/s]
1|596|Loss: 1.2065746784210205:   2%|▏         | 596/25880 [10:00<5:16:51,  1.33it/s]
1|597|Loss: 1.0780242681503296:   2%|▏         | 596/25880 [10:01<5:16:51,  1.33it/s]
1|597|Loss: 1.0780242681503296:   2%|▏         | 597/25880 [10:01<5:25:27,  1.29it/s]
1|598|Loss: 1.285462498664856:   2%|▏         | 597/25880 [10:02<5:25:27,  1.29it/s] 
1|598|Loss: 1.285462498664856:   2%|▏         | 598/25880 [10:02<5:50:41,  1.20it/s]
1|599|Loss: 1.1102901697158813:   2%|▏         | 598/25880 [10:02<5:50:41,  1.20it/s]
1|599|Loss: 1.1102901697158813:   2%|▏         | 599/25880 [10:03<5:37:41,  1.25it/s]
1|600|Loss: 1.1784125566482544:   2%|▏         | 599/25880 [10:03<5:37:41,  1.25it/s]
1|600|Loss: 1.1784125566482544:   2%|▏         | 600/25880 [10:04<5:36:59,  1.25it/s]
1|601|Loss: 1.2676678895950317:   2%|▏         | 600/25880 [10:04<5:36:59,  1.25it/s]
1|601|Loss: 1.2676678895950317:   2%|▏         | 601/25880 [10:04<5:20:47,  1.31it/s]
1|602|Loss: 1.36106276512146:   2%|▏         | 601/25880 [10:05<5:20:47,  1.31it/s]  
1|602|Loss: 1.36106276512146:   2%|▏         | 602/25880 [10:05<5:02:45,  1.39it/s]
1|603|Loss: 0.9917705655097961:   2%|▏         | 602/25880 [10:05<5:02:45,  1.39it/s]
1|603|Loss: 0.9917705655097961:   2%|▏         | 603/25880 [10:06<4:59:36,  1.41it/s]
1|604|Loss: 1.0836279392242432:   2%|▏         | 603/25880 [10:06<4:59:36,  1.41it/s]
1|604|Loss: 1.0836279392242432:   2%|▏         | 604/25880 [10:06<5:02:00,  1.39it/s]
1|605|Loss: 1.3120497465133667:   2%|▏         | 604/25880 [10:07<5:02:00,  1.39it/s]
1|605|Loss: 1.3120497465133667:   2%|▏         | 605/25880 [10:07<4:50:32,  1.45it/s]
1|606|Loss: 1.0528175830841064:   2%|▏         | 605/25880 [10:07<4:50:32,  1.45it/s]
1|606|Loss: 1.0528175830841064:   2%|▏         | 606/25880 [10:08<5:10:11,  1.36it/s]
1|607|Loss: 1.1625027656555176:   2%|▏         | 606/25880 [10:08<5:10:11,  1.36it/s]
1|607|Loss: 1.1625027656555176:   2%|▏         | 607/25880 [10:08<4:51:31,  1.44it/s]
1|608|Loss: 1.03842031955719:   2%|▏         | 607/25880 [10:09<4:51:31,  1.44it/s]  
1|608|Loss: 1.03842031955719:   2%|▏         | 608/25880 [10:09<4:46:36,  1.47it/s]
1|609|Loss: 1.1200740337371826:   2%|▏         | 608/25880 [10:09<4:46:36,  1.47it/s]
1|609|Loss: 1.1200740337371826:   2%|▏         | 609/25880 [10:10<4:39:42,  1.51it/s]
1|610|Loss: 0.9946357011795044:   2%|▏         | 609/25880 [10:10<4:39:42,  1.51it/s]
1|610|Loss: 0.9946357011795044:   2%|▏         | 610/25880 [10:10<5:04:53,  1.38it/s]
1|611|Loss: 1.150303840637207:   2%|▏         | 610/25880 [10:11<5:04:53,  1.38it/s] 
1|611|Loss: 1.150303840637207:   2%|▏         | 611/25880 [10:11<5:10:32,  1.36it/s]
1|612|Loss: 0.953306257724762:   2%|▏         | 611/25880 [10:12<5:10:32,  1.36it/s]
1|612|Loss: 0.953306257724762:   2%|▏         | 612/25880 [10:12<5:00:36,  1.40it/s]
1|613|Loss: 1.0730189085006714:   2%|▏         | 612/25880 [10:12<5:00:36,  1.40it/s]
1|613|Loss: 1.0730189085006714:   2%|▏         | 613/25880 [10:13<5:06:16,  1.37it/s]
1|614|Loss: 1.0379760265350342:   2%|▏         | 613/25880 [10:13<5:06:16,  1.37it/s]
1|614|Loss: 1.0379760265350342:   2%|▏         | 614/25880 [10:13<5:05:34,  1.38it/s]
1|615|Loss: 1.0258760452270508:   2%|▏         | 614/25880 [10:14<5:05:34,  1.38it/s]
1|615|Loss: 1.0258760452270508:   2%|▏         | 615/25880 [10:14<5:02:36,  1.39it/s]
1|616|Loss: 1.2176445722579956:   2%|▏         | 615/25880 [10:15<5:02:36,  1.39it/s]
1|616|Loss: 1.2176445722579956:   2%|▏         | 616/25880 [10:15<5:14:44,  1.34it/s]
1|617|Loss: 1.130563735961914:   2%|▏         | 616/25880 [10:15<5:14:44,  1.34it/s] 
1|617|Loss: 1.130563735961914:   2%|▏         | 617/25880 [10:16<5:00:08,  1.40it/s]
1|618|Loss: 0.9863291382789612:   2%|▏         | 617/25880 [10:16<5:00:08,  1.40it/s]
1|618|Loss: 0.9863291382789612:   2%|▏         | 618/25880 [10:16<4:48:41,  1.46it/s]
1|619|Loss: 1.2375677824020386:   2%|▏         | 618/25880 [10:17<4:48:41,  1.46it/s]
1|619|Loss: 1.2375677824020386:   2%|▏         | 619/25880 [10:17<4:53:03,  1.44it/s]
1|620|Loss: 1.0182669162750244:   2%|▏         | 619/25880 [10:17<4:53:03,  1.44it/s]
1|620|Loss: 1.0182669162750244:   2%|▏         | 620/25880 [10:18<4:58:21,  1.41it/s]
1|621|Loss: 1.174059271812439:   2%|▏         | 620/25880 [10:18<4:58:21,  1.41it/s] 
1|621|Loss: 1.174059271812439:   2%|▏         | 621/25880 [10:18<4:58:11,  1.41it/s]
1|622|Loss: 1.0501292943954468:   2%|▏         | 621/25880 [10:19<4:58:11,  1.41it/s]
1|622|Loss: 1.0501292943954468:   2%|▏         | 622/25880 [10:19<4:39:17,  1.51it/s]
1|623|Loss: 0.9906651377677917:   2%|▏         | 622/25880 [10:19<4:39:17,  1.51it/s]
1|623|Loss: 0.9906651377677917:   2%|▏         | 623/25880 [10:20<4:44:18,  1.48it/s]
1|624|Loss: 1.0476335287094116:   2%|▏         | 623/25880 [10:20<4:44:18,  1.48it/s]
1|624|Loss: 1.0476335287094116:   2%|▏         | 624/25880 [10:20<4:57:48,  1.41it/s]
1|625|Loss: 1.0036847591400146:   2%|▏         | 624/25880 [10:21<4:57:48,  1.41it/s]
1|625|Loss: 1.0036847591400146:   2%|▏         | 625/25880 [10:21<4:59:37,  1.40it/s]
1|626|Loss: 0.9606533646583557:   2%|▏         | 625/25880 [10:22<4:59:37,  1.40it/s]
1|626|Loss: 0.9606533646583557:   2%|▏         | 626/25880 [10:22<5:11:24,  1.35it/s]
1|627|Loss: 0.9572339653968811:   2%|▏         | 626/25880 [10:22<5:11:24,  1.35it/s]
1|627|Loss: 0.9572339653968811:   2%|▏         | 627/25880 [10:23<5:09:23,  1.36it/s]
1|628|Loss: 1.1290841102600098:   2%|▏         | 627/25880 [10:23<5:09:23,  1.36it/s]
1|628|Loss: 1.1290841102600098:   2%|▏         | 628/25880 [10:23<4:56:40,  1.42it/s]
1|629|Loss: 1.0871204137802124:   2%|▏         | 628/25880 [10:24<4:56:40,  1.42it/s]
1|629|Loss: 1.0871204137802124:   2%|▏         | 629/25880 [10:24<4:54:25,  1.43it/s]
1|630|Loss: 1.1677515506744385:   2%|▏         | 629/25880 [10:24<4:54:25,  1.43it/s]
1|630|Loss: 1.1677515506744385:   2%|▏         | 630/25880 [10:25<4:45:46,  1.47it/s]
1|631|Loss: 0.9715495705604553:   2%|▏         | 630/25880 [10:25<4:45:46,  1.47it/s]
1|631|Loss: 0.9715495705604553:   2%|▏         | 631/25880 [10:25<5:08:17,  1.36it/s]
1|632|Loss: 1.0248758792877197:   2%|▏         | 631/25880 [10:26<5:08:17,  1.36it/s]
1|632|Loss: 1.0248758792877197:   2%|▏         | 632/25880 [10:26<5:03:03,  1.39it/s]
1|633|Loss: 1.0239973068237305:   2%|▏         | 632/25880 [10:27<5:03:03,  1.39it/s]
1|633|Loss: 1.0239973068237305:   2%|▏         | 633/25880 [10:27<5:04:11,  1.38it/s]
1|634|Loss: 0.9921531677246094:   2%|▏         | 633/25880 [10:27<5:04:11,  1.38it/s]
1|634|Loss: 0.9921531677246094:   2%|▏         | 634/25880 [10:28<5:19:32,  1.32it/s]
1|635|Loss: 1.192869782447815:   2%|▏         | 634/25880 [10:28<5:19:32,  1.32it/s] 
1|635|Loss: 1.192869782447815:   2%|▏         | 635/25880 [10:28<5:26:02,  1.29it/s]
1|636|Loss: 0.9543742537498474:   2%|▏         | 635/25880 [10:29<5:26:02,  1.29it/s]
1|636|Loss: 0.9543742537498474:   2%|▏         | 636/25880 [10:29<5:14:13,  1.34it/s]
1|637|Loss: 1.0173150300979614:   2%|▏         | 636/25880 [10:30<5:14:13,  1.34it/s]
1|637|Loss: 1.0173150300979614:   2%|▏         | 637/25880 [10:30<5:23:43,  1.30it/s]
1|638|Loss: 0.9434924125671387:   2%|▏         | 637/25880 [10:30<5:23:43,  1.30it/s]
1|638|Loss: 0.9434924125671387:   2%|▏         | 638/25880 [10:31<5:31:45,  1.27it/s]
1|639|Loss: 0.9779296517372131:   2%|▏         | 638/25880 [10:31<5:31:45,  1.27it/s]
1|639|Loss: 0.9779296517372131:   2%|▏         | 639/25880 [10:32<5:34:03,  1.26it/s]
1|640|Loss: 0.9263690710067749:   2%|▏         | 639/25880 [10:32<5:34:03,  1.26it/s]
1|640|Loss: 0.9263690710067749:   2%|▏         | 640/25880 [10:32<5:24:09,  1.30it/s]
1|641|Loss: 1.199259638786316:   2%|▏         | 640/25880 [10:33<5:24:09,  1.30it/s] 
1|641|Loss: 1.199259638786316:   2%|▏         | 641/25880 [10:33<5:14:53,  1.34it/s]
1|642|Loss: 1.0508837699890137:   2%|▏         | 641/25880 [10:33<5:14:53,  1.34it/s]
1|642|Loss: 1.0508837699890137:   2%|▏         | 642/25880 [10:34<5:08:06,  1.37it/s]
1|643|Loss: 1.1720483303070068:   2%|▏         | 642/25880 [10:34<5:08:06,  1.37it/s]
1|643|Loss: 1.1720483303070068:   2%|▏         | 643/25880 [10:34<4:55:02,  1.43it/s]
1|644|Loss: 0.9611064791679382:   2%|▏         | 643/25880 [10:35<4:55:02,  1.43it/s]
1|644|Loss: 0.9611064791679382:   2%|▏         | 644/25880 [10:35<5:05:40,  1.38it/s]
1|645|Loss: 0.9997978210449219:   2%|▏         | 644/25880 [10:36<5:05:40,  1.38it/s]
1|645|Loss: 0.9997978210449219:   2%|▏         | 645/25880 [10:36<5:09:08,  1.36it/s]
1|646|Loss: 1.0199166536331177:   2%|▏         | 645/25880 [10:36<5:09:08,  1.36it/s]
1|646|Loss: 1.0199166536331177:   2%|▏         | 646/25880 [10:37<5:11:31,  1.35it/s]
1|647|Loss: 0.9619096517562866:   2%|▏         | 646/25880 [10:37<5:11:31,  1.35it/s]
1|647|Loss: 0.9619096517562866:   2%|▎         | 647/25880 [10:37<5:21:14,  1.31it/s]
1|648|Loss: 1.0511895418167114:   2%|▎         | 647/25880 [10:38<5:21:14,  1.31it/s]
1|648|Loss: 1.0511895418167114:   3%|▎         | 648/25880 [10:38<5:30:46,  1.27it/s]
1|649|Loss: 0.974032461643219:   3%|▎         | 648/25880 [10:39<5:30:46,  1.27it/s] 
1|649|Loss: 0.974032461643219:   3%|▎         | 649/25880 [10:39<5:15:35,  1.33it/s]
1|650|Loss: 0.9673607349395752:   3%|▎         | 649/25880 [10:39<5:15:35,  1.33it/s]
1|650|Loss: 0.9673607349395752:   3%|▎         | 650/25880 [10:40<5:06:46,  1.37it/s]
1|651|Loss: 0.9482753276824951:   3%|▎         | 650/25880 [10:40<5:06:46,  1.37it/s]
1|651|Loss: 0.9482753276824951:   3%|▎         | 651/25880 [10:40<5:06:19,  1.37it/s]
1|652|Loss: 1.0773087739944458:   3%|▎         | 651/25880 [10:41<5:06:19,  1.37it/s]
1|652|Loss: 1.0773087739944458:   3%|▎         | 652/25880 [10:41<5:12:10,  1.35it/s]
1|653|Loss: 0.9855918288230896:   3%|▎         | 652/25880 [10:42<5:12:10,  1.35it/s]
1|653|Loss: 0.9855918288230896:   3%|▎         | 653/25880 [10:42<5:03:31,  1.39it/s]
1|654|Loss: 1.1543511152267456:   3%|▎         | 653/25880 [10:42<5:03:31,  1.39it/s]
1|654|Loss: 1.1543511152267456:   3%|▎         | 654/25880 [10:42<4:50:19,  1.45it/s]
1|655|Loss: 0.9579104781150818:   3%|▎         | 654/25880 [10:43<4:50:19,  1.45it/s]
1|655|Loss: 0.9579104781150818:   3%|▎         | 655/25880 [10:43<4:43:20,  1.48it/s]
1|656|Loss: 1.0608521699905396:   3%|▎         | 655/25880 [10:44<4:43:20,  1.48it/s]
1|656|Loss: 1.0608521699905396:   3%|▎         | 656/25880 [10:44<4:55:36,  1.42it/s]
1|657|Loss: 0.8883712291717529:   3%|▎         | 656/25880 [10:44<4:55:36,  1.42it/s]
1|657|Loss: 0.8883712291717529:   3%|▎         | 657/25880 [10:45<5:10:18,  1.35it/s]
1|658|Loss: 1.0878952741622925:   3%|▎         | 657/25880 [10:45<5:10:18,  1.35it/s]
1|658|Loss: 1.0878952741622925:   3%|▎         | 658/25880 [10:46<5:18:48,  1.32it/s]
1|659|Loss: 1.0570213794708252:   3%|▎         | 658/25880 [10:46<5:18:48,  1.32it/s]
1|659|Loss: 1.0570213794708252:   3%|▎         | 659/25880 [10:46<5:13:12,  1.34it/s]
1|660|Loss: 0.9358461499214172:   3%|▎         | 659/25880 [10:47<5:13:12,  1.34it/s]
1|660|Loss: 0.9358461499214172:   3%|▎         | 660/25880 [10:47<5:07:27,  1.37it/s]
1|661|Loss: 1.1134741306304932:   3%|▎         | 660/25880 [10:47<5:07:27,  1.37it/s]
1|661|Loss: 1.1134741306304932:   3%|▎         | 661/25880 [10:48<5:02:30,  1.39it/s]
1|662|Loss: 1.0587146282196045:   3%|▎         | 661/25880 [10:48<5:02:30,  1.39it/s]
1|662|Loss: 1.0587146282196045:   3%|▎         | 662/25880 [10:48<4:46:43,  1.47it/s]
1|663|Loss: 0.9739654660224915:   3%|▎         | 662/25880 [10:49<4:46:43,  1.47it/s]
1|663|Loss: 0.9739654660224915:   3%|▎         | 663/25880 [10:49<4:57:53,  1.41it/s]
1|664|Loss: 1.0166938304901123:   3%|▎         | 663/25880 [10:49<4:57:53,  1.41it/s]
1|664|Loss: 1.0166938304901123:   3%|▎         | 664/25880 [10:50<5:12:37,  1.34it/s]
1|665|Loss: 1.0341778993606567:   3%|▎         | 664/25880 [10:50<5:12:37,  1.34it/s]
1|665|Loss: 1.0341778993606567:   3%|▎         | 665/25880 [10:50<4:57:45,  1.41it/s]
1|666|Loss: 1.1145496368408203:   3%|▎         | 665/25880 [10:51<4:57:45,  1.41it/s]
1|666|Loss: 1.1145496368408203:   3%|▎         | 666/25880 [10:51<5:02:10,  1.39it/s]
1|667|Loss: 0.9894826412200928:   3%|▎         | 666/25880 [10:52<5:02:10,  1.39it/s]
1|667|Loss: 0.9894826412200928:   3%|▎         | 667/25880 [10:52<5:02:12,  1.39it/s]
1|668|Loss: 1.0957856178283691:   3%|▎         | 667/25880 [10:52<5:02:12,  1.39it/s]
1|668|Loss: 1.0957856178283691:   3%|▎         | 668/25880 [10:53<5:21:42,  1.31it/s]
1|669|Loss: 0.9610901474952698:   3%|▎         | 668/25880 [10:53<5:21:42,  1.31it/s]
1|669|Loss: 0.9610901474952698:   3%|▎         | 669/25880 [10:54<5:22:57,  1.30it/s]
1|670|Loss: 1.0915452241897583:   3%|▎         | 669/25880 [10:54<5:22:57,  1.30it/s]
1|670|Loss: 1.0915452241897583:   3%|▎         | 670/25880 [10:54<5:00:30,  1.40it/s]
1|671|Loss: 1.0335770845413208:   3%|▎         | 670/25880 [10:55<5:00:30,  1.40it/s]
1|671|Loss: 1.0335770845413208:   3%|▎         | 671/25880 [10:55<5:09:37,  1.36it/s]
1|672|Loss: 0.982408881187439:   3%|▎         | 671/25880 [10:55<5:09:37,  1.36it/s] 
1|672|Loss: 0.982408881187439:   3%|▎         | 672/25880 [10:56<5:12:59,  1.34it/s]
1|673|Loss: 1.1257553100585938:   3%|▎         | 672/25880 [10:56<5:12:59,  1.34it/s]
1|673|Loss: 1.1257553100585938:   3%|▎         | 673/25880 [10:56<4:48:51,  1.45it/s]
1|674|Loss: 1.0807063579559326:   3%|▎         | 673/25880 [10:57<4:48:51,  1.45it/s]
1|674|Loss: 1.0807063579559326:   3%|▎         | 674/25880 [10:57<4:39:24,  1.50it/s]
1|675|Loss: 1.123313307762146:   3%|▎         | 674/25880 [10:57<4:39:24,  1.50it/s] 
1|675|Loss: 1.123313307762146:   3%|▎         | 675/25880 [10:58<4:56:49,  1.42it/s]
1|676|Loss: 1.0343914031982422:   3%|▎         | 675/25880 [10:58<4:56:49,  1.42it/s]
1|676|Loss: 1.0343914031982422:   3%|▎         | 676/25880 [10:58<5:13:45,  1.34it/s]
1|677|Loss: 1.1276379823684692:   3%|▎         | 676/25880 [10:59<5:13:45,  1.34it/s]
1|677|Loss: 1.1276379823684692:   3%|▎         | 677/25880 [10:59<5:04:26,  1.38it/s]
1|678|Loss: 1.0328775644302368:   3%|▎         | 677/25880 [11:00<5:04:26,  1.38it/s]
1|678|Loss: 1.0328775644302368:   3%|▎         | 678/25880 [11:00<5:02:20,  1.39it/s]
1|679|Loss: 1.1546915769577026:   3%|▎         | 678/25880 [11:00<5:02:20,  1.39it/s]
1|679|Loss: 1.1546915769577026:   3%|▎         | 679/25880 [11:00<4:35:34,  1.52it/s]
1|680|Loss: 1.0842212438583374:   3%|▎         | 679/25880 [11:01<4:35:34,  1.52it/s]
1|680|Loss: 1.0842212438583374:   3%|▎         | 680/25880 [11:01<4:11:58,  1.67it/s]
1|681|Loss: 1.0509843826293945:   3%|▎         | 680/25880 [11:01<4:11:58,  1.67it/s]
1|681|Loss: 1.0509843826293945:   3%|▎         | 681/25880 [11:01<4:18:25,  1.63it/s]
1|682|Loss: 0.9676299691200256:   3%|▎         | 681/25880 [11:02<4:18:25,  1.63it/s]
1|682|Loss: 0.9676299691200256:   3%|▎         | 682/25880 [11:02<4:22:18,  1.60it/s]
1|683|Loss: 0.9038744568824768:   3%|▎         | 682/25880 [11:03<4:22:18,  1.60it/s]
1|683|Loss: 0.9038744568824768:   3%|▎         | 683/25880 [11:03<4:45:20,  1.47it/s]
1|684|Loss: 1.1691967248916626:   3%|▎         | 683/25880 [11:03<4:45:20,  1.47it/s]
1|684|Loss: 1.1691967248916626:   3%|▎         | 684/25880 [11:03<4:20:54,  1.61it/s]
1|685|Loss: 0.9737510681152344:   3%|▎         | 684/25880 [11:04<4:20:54,  1.61it/s]
1|685|Loss: 0.9737510681152344:   3%|▎         | 685/25880 [11:04<4:27:41,  1.57it/s]
1|686|Loss: 0.9687440991401672:   3%|▎         | 685/25880 [11:05<4:27:41,  1.57it/s]
1|686|Loss: 0.9687440991401672:   3%|▎         | 686/25880 [11:05<4:45:19,  1.47it/s]
1|687|Loss: 1.0011870861053467:   3%|▎         | 686/25880 [11:05<4:45:19,  1.47it/s]
1|687|Loss: 1.0011870861053467:   3%|▎         | 687/25880 [11:05<4:28:12,  1.57it/s]
1|688|Loss: 0.8895404934883118:   3%|▎         | 687/25880 [11:06<4:28:12,  1.57it/s]
1|688|Loss: 0.8895404934883118:   3%|▎         | 688/25880 [11:06<4:12:35,  1.66it/s]
1|689|Loss: 0.8899860978126526:   3%|▎         | 688/25880 [11:06<4:12:35,  1.66it/s]
1|689|Loss: 0.8899860978126526:   3%|▎         | 689/25880 [11:07<4:38:13,  1.51it/s]
1|690|Loss: 1.124751091003418:   3%|▎         | 689/25880 [11:07<4:38:13,  1.51it/s] 
1|690|Loss: 1.124751091003418:   3%|▎         | 690/25880 [11:07<4:41:27,  1.49it/s]
1|691|Loss: 1.0363826751708984:   3%|▎         | 690/25880 [11:08<4:41:27,  1.49it/s]
1|691|Loss: 1.0363826751708984:   3%|▎         | 691/25880 [11:08<4:52:24,  1.44it/s]
1|692|Loss: 1.131130337715149:   3%|▎         | 691/25880 [11:09<4:52:24,  1.44it/s] 
1|692|Loss: 1.131130337715149:   3%|▎         | 692/25880 [11:09<4:23:27,  1.59it/s]
1|693|Loss: 1.5638296604156494:   3%|▎         | 692/25880 [11:09<4:23:27,  1.59it/s]
1|693|Loss: 1.5638296604156494:   3%|▎         | 693/25880 [11:09<4:29:11,  1.56it/s]
1|694|Loss: 1.062171459197998:   3%|▎         | 693/25880 [11:10<4:29:11,  1.56it/s] 
1|694|Loss: 1.062171459197998:   3%|▎         | 694/25880 [11:10<4:42:26,  1.49it/s]
1|695|Loss: 1.0845963954925537:   3%|▎         | 694/25880 [11:10<4:42:26,  1.49it/s]
1|695|Loss: 1.0845963954925537:   3%|▎         | 695/25880 [11:11<4:35:48,  1.52it/s]
1|696|Loss: 0.8016397953033447:   3%|▎         | 695/25880 [11:11<4:35:48,  1.52it/s]
1|696|Loss: 0.8016397953033447:   3%|▎         | 696/25880 [11:12<4:53:27,  1.43it/s]
1|697|Loss: 0.9311208724975586:   3%|▎         | 696/25880 [11:12<4:53:27,  1.43it/s]
1|697|Loss: 0.9311208724975586:   3%|▎         | 697/25880 [11:12<4:42:36,  1.49it/s]
1|698|Loss: 1.0094020366668701:   3%|▎         | 697/25880 [11:12<4:42:36,  1.49it/s]
1|698|Loss: 1.0094020366668701:   3%|▎         | 698/25880 [11:13<4:45:29,  1.47it/s]
1|699|Loss: 0.9891465902328491:   3%|▎         | 698/25880 [11:13<4:45:29,  1.47it/s]
1|699|Loss: 0.9891465902328491:   3%|▎         | 699/25880 [11:14<5:09:56,  1.35it/s]
1|700|Loss: 1.017814040184021:   3%|▎         | 699/25880 [11:14<5:09:56,  1.35it/s] 
1|700|Loss: 1.017814040184021:   3%|▎         | 700/25880 [11:14<5:12:52,  1.34it/s]
1|701|Loss: 1.1604735851287842:   3%|▎         | 700/25880 [11:15<5:12:52,  1.34it/s]
1|701|Loss: 1.1604735851287842:   3%|▎         | 701/25880 [11:15<5:07:51,  1.36it/s]
1|702|Loss: 1.193605899810791:   3%|▎         | 701/25880 [11:16<5:07:51,  1.36it/s] 
1|702|Loss: 1.193605899810791:   3%|▎         | 702/25880 [11:16<4:56:07,  1.42it/s]
1|703|Loss: 1.1495691537857056:   3%|▎         | 702/25880 [11:16<4:56:07,  1.42it/s]
1|703|Loss: 1.1495691537857056:   3%|▎         | 703/25880 [11:17<5:03:12,  1.38it/s]
1|704|Loss: 1.0664290189743042:   3%|▎         | 703/25880 [11:17<5:03:12,  1.38it/s]
1|704|Loss: 1.0664290189743042:   3%|▎         | 704/25880 [11:17<4:43:11,  1.48it/s]
1|705|Loss: 0.9894859790802002:   3%|▎         | 704/25880 [11:17<4:43:11,  1.48it/s]
1|705|Loss: 0.9894859790802002:   3%|▎         | 705/25880 [11:18<4:49:53,  1.45it/s]
1|706|Loss: 1.1491364240646362:   3%|▎         | 705/25880 [11:18<4:49:53,  1.45it/s]
1|706|Loss: 1.1491364240646362:   3%|▎         | 706/25880 [11:19<5:02:32,  1.39it/s]
1|707|Loss: 0.9622358083724976:   3%|▎         | 706/25880 [11:19<5:02:32,  1.39it/s]
1|707|Loss: 0.9622358083724976:   3%|▎         | 707/25880 [11:19<5:03:49,  1.38it/s]
1|708|Loss: 1.1557472944259644:   3%|▎         | 707/25880 [11:20<5:03:49,  1.38it/s]
1|708|Loss: 1.1557472944259644:   3%|▎         | 708/25880 [11:20<5:00:31,  1.40it/s]
1|709|Loss: 1.0409157276153564:   3%|▎         | 708/25880 [11:20<5:00:31,  1.40it/s]
1|709|Loss: 1.0409157276153564:   3%|▎         | 709/25880 [11:21<5:01:25,  1.39it/s]
1|710|Loss: 0.9772124886512756:   3%|▎         | 709/25880 [11:21<5:01:25,  1.39it/s]
1|710|Loss: 0.9772124886512756:   3%|▎         | 710/25880 [11:22<5:13:35,  1.34it/s]
1|711|Loss: 0.9592693448066711:   3%|▎         | 710/25880 [11:22<5:13:35,  1.34it/s]
1|711|Loss: 0.9592693448066711:   3%|▎         | 711/25880 [11:22<4:45:34,  1.47it/s]
1|712|Loss: 1.031195044517517:   3%|▎         | 711/25880 [11:22<4:45:34,  1.47it/s] 
1|712|Loss: 1.031195044517517:   3%|▎         | 712/25880 [11:23<4:27:03,  1.57it/s]
1|713|Loss: 1.0385831594467163:   3%|▎         | 712/25880 [11:23<4:27:03,  1.57it/s]
1|713|Loss: 1.0385831594467163:   3%|▎         | 713/25880 [11:23<4:16:28,  1.64it/s]
1|714|Loss: 1.0218983888626099:   3%|▎         | 713/25880 [11:24<4:16:28,  1.64it/s]
1|714|Loss: 1.0218983888626099:   3%|▎         | 714/25880 [11:24<4:33:59,  1.53it/s]
1|715|Loss: 0.9625368714332581:   3%|▎         | 714/25880 [11:24<4:33:59,  1.53it/s]
1|715|Loss: 0.9625368714332581:   3%|▎         | 715/25880 [11:25<5:04:44,  1.38it/s]
1|716|Loss: 1.030884861946106:   3%|▎         | 715/25880 [11:25<5:04:44,  1.38it/s] 
1|716|Loss: 1.030884861946106:   3%|▎         | 716/25880 [11:26<4:54:55,  1.42it/s]
1|717|Loss: 1.065327525138855:   3%|▎         | 716/25880 [11:26<4:54:55,  1.42it/s]
1|717|Loss: 1.065327525138855:   3%|▎         | 717/25880 [11:26<4:50:33,  1.44it/s]
1|718|Loss: 1.0670908689498901:   3%|▎         | 717/25880 [11:27<4:50:33,  1.44it/s]
1|718|Loss: 1.0670908689498901:   3%|▎         | 718/25880 [11:27<5:07:39,  1.36it/s]
1|719|Loss: 1.10028874874115:   3%|▎         | 718/25880 [11:27<5:07:39,  1.36it/s]  
1|719|Loss: 1.10028874874115:   3%|▎         | 719/25880 [11:28<5:16:08,  1.33it/s]
1|720|Loss: 0.9256308674812317:   3%|▎         | 719/25880 [11:28<5:16:08,  1.33it/s]
1|720|Loss: 0.9256308674812317:   3%|▎         | 720/25880 [11:29<5:16:00,  1.33it/s]
1|721|Loss: 0.9375005960464478:   3%|▎         | 720/25880 [11:29<5:16:00,  1.33it/s]
1|721|Loss: 0.9375005960464478:   3%|▎         | 721/25880 [11:29<5:14:05,  1.34it/s]
1|722|Loss: 1.058230996131897:   3%|▎         | 721/25880 [11:30<5:14:05,  1.34it/s] 
1|722|Loss: 1.058230996131897:   3%|▎         | 722/25880 [11:30<4:47:18,  1.46it/s]
1|723|Loss: 0.8984065651893616:   3%|▎         | 722/25880 [11:30<4:47:18,  1.46it/s]
1|723|Loss: 0.8984065651893616:   3%|▎         | 723/25880 [11:30<4:37:07,  1.51it/s]
1|724|Loss: 0.9984320402145386:   3%|▎         | 723/25880 [11:31<4:37:07,  1.51it/s]
1|724|Loss: 0.9984320402145386:   3%|▎         | 724/25880 [11:31<4:45:28,  1.47it/s]
1|725|Loss: 1.0323314666748047:   3%|▎         | 724/25880 [11:32<4:45:28,  1.47it/s]
1|725|Loss: 1.0323314666748047:   3%|▎         | 725/25880 [11:32<4:53:07,  1.43it/s]
1|726|Loss: 0.9763772487640381:   3%|▎         | 725/25880 [11:32<4:53:07,  1.43it/s]
1|726|Loss: 0.9763772487640381:   3%|▎         | 726/25880 [11:33<4:59:54,  1.40it/s]
1|727|Loss: 1.0540186166763306:   3%|▎         | 726/25880 [11:33<4:59:54,  1.40it/s]
1|727|Loss: 1.0540186166763306:   3%|▎         | 727/25880 [11:33<4:59:33,  1.40it/s]
1|728|Loss: 0.8964972496032715:   3%|▎         | 727/25880 [11:34<4:59:33,  1.40it/s]
1|728|Loss: 0.8964972496032715:   3%|▎         | 728/25880 [11:34<5:06:27,  1.37it/s]
1|729|Loss: 0.8633138537406921:   3%|▎         | 728/25880 [11:35<5:06:27,  1.37it/s]
1|729|Loss: 0.8633138537406921:   3%|▎         | 729/25880 [11:35<5:10:07,  1.35it/s]
1|730|Loss: 1.0283174514770508:   3%|▎         | 729/25880 [11:35<5:10:07,  1.35it/s]
1|730|Loss: 1.0283174514770508:   3%|▎         | 730/25880 [11:36<4:54:23,  1.42it/s]
1|731|Loss: 1.0387555360794067:   3%|▎         | 730/25880 [11:36<4:54:23,  1.42it/s]
1|731|Loss: 1.0387555360794067:   3%|▎         | 731/25880 [11:36<4:44:24,  1.47it/s]
1|732|Loss: 0.9202255010604858:   3%|▎         | 731/25880 [11:37<4:44:24,  1.47it/s]
1|732|Loss: 0.9202255010604858:   3%|▎         | 732/25880 [11:37<5:01:05,  1.39it/s]
1|733|Loss: 1.219821810722351:   3%|▎         | 732/25880 [11:37<5:01:05,  1.39it/s] 
1|733|Loss: 1.219821810722351:   3%|▎         | 733/25880 [11:38<5:06:16,  1.37it/s]
1|734|Loss: 1.1132402420043945:   3%|▎         | 733/25880 [11:38<5:06:16,  1.37it/s]
1|734|Loss: 1.1132402420043945:   3%|▎         | 734/25880 [11:38<4:56:57,  1.41it/s]
1|735|Loss: 1.02049720287323:   3%|▎         | 734/25880 [11:39<4:56:57,  1.41it/s]  
1|735|Loss: 1.02049720287323:   3%|▎         | 735/25880 [11:39<4:54:03,  1.43it/s]
1|736|Loss: 1.0372745990753174:   3%|▎         | 735/25880 [11:39<4:54:03,  1.43it/s]
1|736|Loss: 1.0372745990753174:   3%|▎         | 736/25880 [11:40<4:56:06,  1.42it/s]
1|737|Loss: 0.9482160210609436:   3%|▎         | 736/25880 [11:40<4:56:06,  1.42it/s]
1|737|Loss: 0.9482160210609436:   3%|▎         | 737/25880 [11:40<4:55:46,  1.42it/s]
1|738|Loss: 1.0636647939682007:   3%|▎         | 737/25880 [11:41<4:55:46,  1.42it/s]
1|738|Loss: 1.0636647939682007:   3%|▎         | 738/25880 [11:41<4:49:07,  1.45it/s]
1|739|Loss: 0.9592134952545166:   3%|▎         | 738/25880 [11:42<4:49:07,  1.45it/s]
1|739|Loss: 0.9592134952545166:   3%|▎         | 739/25880 [11:42<5:10:28,  1.35it/s]
1|740|Loss: 0.9836676716804504:   3%|▎         | 739/25880 [11:42<5:10:28,  1.35it/s]
1|740|Loss: 0.9836676716804504:   3%|▎         | 740/25880 [11:43<5:13:33,  1.34it/s]
1|741|Loss: 0.9481184482574463:   3%|▎         | 740/25880 [11:44<5:13:33,  1.34it/s]
1|741|Loss: 0.9481184482574463:   3%|▎         | 741/25880 [11:44<5:55:37,  1.18it/s]
1|742|Loss: 1.1130955219268799:   3%|▎         | 741/25880 [11:44<5:55:37,  1.18it/s]
1|742|Loss: 1.1130955219268799:   3%|▎         | 742/25880 [11:44<5:29:46,  1.27it/s]
1|743|Loss: 1.03477942943573:   3%|▎         | 742/25880 [11:45<5:29:46,  1.27it/s]  
1|743|Loss: 1.03477942943573:   3%|▎         | 743/25880 [11:45<5:30:36,  1.27it/s]
1|744|Loss: 1.149004340171814:   3%|▎         | 743/25880 [11:46<5:30:36,  1.27it/s]
1|744|Loss: 1.149004340171814:   3%|▎         | 744/25880 [11:46<5:30:54,  1.27it/s]
1|745|Loss: 0.9186775088310242:   3%|▎         | 744/25880 [11:47<5:30:54,  1.27it/s]
1|745|Loss: 0.9186775088310242:   3%|▎         | 745/25880 [11:47<5:36:45,  1.24it/s]
1|746|Loss: 1.0475949048995972:   3%|▎         | 745/25880 [11:47<5:36:45,  1.24it/s]
1|746|Loss: 1.0475949048995972:   3%|▎         | 746/25880 [11:48<5:31:37,  1.26it/s]
1|747|Loss: 0.9133381843566895:   3%|▎         | 746/25880 [11:48<5:31:37,  1.26it/s]
1|747|Loss: 0.9133381843566895:   3%|▎         | 747/25880 [11:49<5:37:12,  1.24it/s]
1|748|Loss: 0.8083393573760986:   3%|▎         | 747/25880 [11:49<5:37:12,  1.24it/s]
1|748|Loss: 0.8083393573760986:   3%|▎         | 748/25880 [11:49<5:32:33,  1.26it/s]
1|749|Loss: 1.132627248764038:   3%|▎         | 748/25880 [11:50<5:32:33,  1.26it/s] 
1|749|Loss: 1.132627248764038:   3%|▎         | 749/25880 [11:50<5:54:35,  1.18it/s]
1|750|Loss: 1.0289185047149658:   3%|▎         | 749/25880 [11:51<5:54:35,  1.18it/s]
1|750|Loss: 1.0289185047149658:   3%|▎         | 750/25880 [11:51<6:07:18,  1.14it/s]
1|751|Loss: 1.2131497859954834:   3%|▎         | 750/25880 [11:52<6:07:18,  1.14it/s]
1|751|Loss: 1.2131497859954834:   3%|▎         | 751/25880 [11:52<5:52:27,  1.19it/s]
1|752|Loss: 1.0064040422439575:   3%|▎         | 751/25880 [11:52<5:52:27,  1.19it/s]
1|752|Loss: 1.0064040422439575:   3%|▎         | 752/25880 [11:53<5:38:23,  1.24it/s]
1|753|Loss: 1.0236815214157104:   3%|▎         | 752/25880 [11:53<5:38:23,  1.24it/s]
1|753|Loss: 1.0236815214157104:   3%|▎         | 753/25880 [11:53<5:30:15,  1.27it/s]
1|754|Loss: 0.9200698733329773:   3%|▎         | 753/25880 [11:54<5:30:15,  1.27it/s]
1|754|Loss: 0.9200698733329773:   3%|▎         | 754/25880 [11:54<5:24:21,  1.29it/s]
1|755|Loss: 1.0236870050430298:   3%|▎         | 754/25880 [11:55<5:24:21,  1.29it/s]
1|755|Loss: 1.0236870050430298:   3%|▎         | 755/25880 [11:55<5:10:05,  1.35it/s]
1|756|Loss: 0.8873353600502014:   3%|▎         | 755/25880 [11:55<5:10:05,  1.35it/s]
1|756|Loss: 0.8873353600502014:   3%|▎         | 756/25880 [11:55<4:54:40,  1.42it/s]
1|757|Loss: 1.0958586931228638:   3%|▎         | 756/25880 [11:56<4:54:40,  1.42it/s]
1|757|Loss: 1.0958586931228638:   3%|▎         | 757/25880 [11:56<4:56:27,  1.41it/s]
1|758|Loss: 1.0818408727645874:   3%|▎         | 757/25880 [11:57<4:56:27,  1.41it/s]
1|758|Loss: 1.0818408727645874:   3%|▎         | 758/25880 [11:57<4:49:01,  1.45it/s]
1|759|Loss: 1.006015658378601:   3%|▎         | 758/25880 [11:57<4:49:01,  1.45it/s] 
1|759|Loss: 1.006015658378601:   3%|▎         | 759/25880 [11:58<4:48:42,  1.45it/s]
1|760|Loss: 0.8513486981391907:   3%|▎         | 759/25880 [11:58<4:48:42,  1.45it/s]
1|760|Loss: 0.8513486981391907:   3%|▎         | 760/25880 [11:58<4:37:09,  1.51it/s]
1|761|Loss: 0.9854196310043335:   3%|▎         | 760/25880 [11:58<4:37:09,  1.51it/s]
1|761|Loss: 0.9854196310043335:   3%|▎         | 761/25880 [11:59<4:16:31,  1.63it/s]
1|762|Loss: 1.1684337854385376:   3%|▎         | 761/25880 [11:59<4:16:31,  1.63it/s]
1|762|Loss: 1.1684337854385376:   3%|▎         | 762/25880 [11:59<4:06:25,  1.70it/s]
1|763|Loss: 1.0612003803253174:   3%|▎         | 762/25880 [12:00<4:06:25,  1.70it/s]
1|763|Loss: 1.0612003803253174:   3%|▎         | 763/25880 [12:00<4:34:54,  1.52it/s]
1|764|Loss: 0.9693098068237305:   3%|▎         | 763/25880 [12:00<4:34:54,  1.52it/s]
1|764|Loss: 0.9693098068237305:   3%|▎         | 764/25880 [12:01<5:00:42,  1.39it/s]
1|765|Loss: 1.0580463409423828:   3%|▎         | 764/25880 [12:01<5:00:42,  1.39it/s]
1|765|Loss: 1.0580463409423828:   3%|▎         | 765/25880 [12:02<5:11:24,  1.34it/s]
1|766|Loss: 1.0626823902130127:   3%|▎         | 765/25880 [12:02<5:11:24,  1.34it/s]
1|766|Loss: 1.0626823902130127:   3%|▎         | 766/25880 [12:02<5:22:51,  1.30it/s]
1|767|Loss: 0.9433116912841797:   3%|▎         | 766/25880 [12:03<5:22:51,  1.30it/s]
1|767|Loss: 0.9433116912841797:   3%|▎         | 767/25880 [12:03<5:17:51,  1.32it/s]
1|768|Loss: 0.8574423789978027:   3%|▎         | 767/25880 [12:04<5:17:51,  1.32it/s]
1|768|Loss: 0.8574423789978027:   3%|▎         | 768/25880 [12:04<5:09:06,  1.35it/s]
1|769|Loss: 1.0009164810180664:   3%|▎         | 768/25880 [12:04<5:09:06,  1.35it/s]
1|769|Loss: 1.0009164810180664:   3%|▎         | 769/25880 [12:05<5:16:19,  1.32it/s]
1|770|Loss: 0.8597211837768555:   3%|▎         | 769/25880 [12:05<5:16:19,  1.32it/s]
1|770|Loss: 0.8597211837768555:   3%|▎         | 770/25880 [12:06<5:38:09,  1.24it/s]
1|771|Loss: 1.0893616676330566:   3%|▎         | 770/25880 [12:06<5:38:09,  1.24it/s]
1|771|Loss: 1.0893616676330566:   3%|▎         | 771/25880 [12:07<5:53:34,  1.18it/s]
1|772|Loss: 0.9907385110855103:   3%|▎         | 771/25880 [12:07<5:53:34,  1.18it/s]
1|772|Loss: 0.9907385110855103:   3%|▎         | 772/25880 [12:07<5:32:01,  1.26it/s]
1|773|Loss: 0.8919482827186584:   3%|▎         | 772/25880 [12:08<5:32:01,  1.26it/s]
1|773|Loss: 0.8919482827186584:   3%|▎         | 773/25880 [12:08<5:22:08,  1.30it/s]
1|774|Loss: 0.9047350287437439:   3%|▎         | 773/25880 [12:08<5:22:08,  1.30it/s]
1|774|Loss: 0.9047350287437439:   3%|▎         | 774/25880 [12:09<5:17:59,  1.32it/s]
1|775|Loss: 1.0089205503463745:   3%|▎         | 774/25880 [12:09<5:17:59,  1.32it/s]
1|775|Loss: 1.0089205503463745:   3%|▎         | 775/25880 [12:09<5:14:02,  1.33it/s]
1|776|Loss: 0.8164899945259094:   3%|▎         | 775/25880 [12:10<5:14:02,  1.33it/s]
1|776|Loss: 0.8164899945259094:   3%|▎         | 776/25880 [12:10<5:20:37,  1.30it/s]
1|777|Loss: 0.9547771215438843:   3%|▎         | 776/25880 [12:11<5:20:37,  1.30it/s]
1|777|Loss: 0.9547771215438843:   3%|▎         | 777/25880 [12:11<5:30:32,  1.27it/s]
1|778|Loss: 1.0097589492797852:   3%|▎         | 777/25880 [12:11<5:30:32,  1.27it/s]
1|778|Loss: 1.0097589492797852:   3%|▎         | 778/25880 [12:12<5:36:40,  1.24it/s]
1|779|Loss: 0.9500139951705933:   3%|▎         | 778/25880 [12:12<5:36:40,  1.24it/s]
1|779|Loss: 0.9500139951705933:   3%|▎         | 779/25880 [12:13<5:37:08,  1.24it/s]
1|780|Loss: 0.8977728486061096:   3%|▎         | 779/25880 [12:13<5:37:08,  1.24it/s]
1|780|Loss: 0.8977728486061096:   3%|▎         | 780/25880 [12:13<5:27:15,  1.28it/s]
1|781|Loss: 0.8998236656188965:   3%|▎         | 780/25880 [12:14<5:27:15,  1.28it/s]
1|781|Loss: 0.8998236656188965:   3%|▎         | 781/25880 [12:14<5:21:16,  1.30it/s]
1|782|Loss: 0.9669007062911987:   3%|▎         | 781/25880 [12:15<5:21:16,  1.30it/s]
1|782|Loss: 0.9669007062911987:   3%|▎         | 782/25880 [12:15<5:30:32,  1.27it/s]
1|783|Loss: 0.9479638338088989:   3%|▎         | 782/25880 [12:15<5:30:32,  1.27it/s]
1|783|Loss: 0.9479638338088989:   3%|▎         | 783/25880 [12:16<5:36:32,  1.24it/s]
1|784|Loss: 0.9493647813796997:   3%|▎         | 783/25880 [12:16<5:36:32,  1.24it/s]
1|784|Loss: 0.9493647813796997:   3%|▎         | 784/25880 [12:17<5:29:18,  1.27it/s]
1|785|Loss: 1.0084372758865356:   3%|▎         | 784/25880 [12:17<5:29:18,  1.27it/s]
1|785|Loss: 1.0084372758865356:   3%|▎         | 785/25880 [12:17<5:07:50,  1.36it/s]
1|786|Loss: 0.9170528650283813:   3%|▎         | 785/25880 [12:18<5:07:50,  1.36it/s]
1|786|Loss: 0.9170528650283813:   3%|▎         | 786/25880 [12:18<5:08:12,  1.36it/s]
1|787|Loss: 0.921161949634552:   3%|▎         | 786/25880 [12:18<5:08:12,  1.36it/s] 
1|787|Loss: 0.921161949634552:   3%|▎         | 787/25880 [12:19<4:53:12,  1.43it/s]
1|788|Loss: 0.8783969879150391:   3%|▎         | 787/25880 [12:19<4:53:12,  1.43it/s]
1|788|Loss: 0.8783969879150391:   3%|▎         | 788/25880 [12:19<5:03:04,  1.38it/s]
1|789|Loss: 0.9259191751480103:   3%|▎         | 788/25880 [12:20<5:03:04,  1.38it/s]
1|789|Loss: 0.9259191751480103:   3%|▎         | 789/25880 [12:20<5:20:17,  1.31it/s]
1|790|Loss: 0.8983389139175415:   3%|▎         | 789/25880 [12:21<5:20:17,  1.31it/s]
1|790|Loss: 0.8983389139175415:   3%|▎         | 790/25880 [12:21<5:11:22,  1.34it/s]
1|791|Loss: 0.8538445234298706:   3%|▎         | 790/25880 [12:21<5:11:22,  1.34it/s]
1|791|Loss: 0.8538445234298706:   3%|▎         | 791/25880 [12:22<5:33:25,  1.25it/s]
1|792|Loss: 0.8755342960357666:   3%|▎         | 791/25880 [12:22<5:33:25,  1.25it/s]
1|792|Loss: 0.8755342960357666:   3%|▎         | 792/25880 [12:23<5:44:26,  1.21it/s]
1|793|Loss: 0.8360125422477722:   3%|▎         | 792/25880 [12:23<5:44:26,  1.21it/s]
1|793|Loss: 0.8360125422477722:   3%|▎         | 793/25880 [12:23<5:17:47,  1.32it/s]
1|794|Loss: 0.9237987995147705:   3%|▎         | 793/25880 [12:24<5:17:47,  1.32it/s]
1|794|Loss: 0.9237987995147705:   3%|▎         | 794/25880 [12:24<5:09:41,  1.35it/s]
1|795|Loss: 0.9438585042953491:   3%|▎         | 794/25880 [12:24<5:09:41,  1.35it/s]
1|795|Loss: 0.9438585042953491:   3%|▎         | 795/25880 [12:25<5:05:23,  1.37it/s]
1|796|Loss: 0.8251006603240967:   3%|▎         | 795/25880 [12:25<5:05:23,  1.37it/s]
1|796|Loss: 0.8251006603240967:   3%|▎         | 796/25880 [12:25<5:09:26,  1.35it/s]
1|797|Loss: 1.0005664825439453:   3%|▎         | 796/25880 [12:26<5:09:26,  1.35it/s]
1|797|Loss: 1.0005664825439453:   3%|▎         | 797/25880 [12:26<4:41:48,  1.48it/s]
1|798|Loss: 1.035832405090332:   3%|▎         | 797/25880 [12:26<4:41:48,  1.48it/s] 
1|798|Loss: 1.035832405090332:   3%|▎         | 798/25880 [12:27<4:55:24,  1.42it/s]
1|799|Loss: 0.9174322485923767:   3%|▎         | 798/25880 [12:27<4:55:24,  1.42it/s]
1|799|Loss: 0.9174322485923767:   3%|▎         | 799/25880 [12:28<4:59:55,  1.39it/s]
1|800|Loss: 0.935209333896637:   3%|▎         | 799/25880 [12:28<4:59:55,  1.39it/s] 
1|800|Loss: 0.935209333896637:   3%|▎         | 800/25880 [12:28<4:51:09,  1.44it/s]
1|801|Loss: 1.0234462022781372:   3%|▎         | 800/25880 [12:29<4:51:09,  1.44it/s]
1|801|Loss: 1.0234462022781372:   3%|▎         | 801/25880 [12:29<5:05:39,  1.37it/s]
1|802|Loss: 0.8790590763092041:   3%|▎         | 801/25880 [12:29<5:05:39,  1.37it/s]
1|802|Loss: 0.8790590763092041:   3%|▎         | 802/25880 [12:30<5:27:53,  1.27it/s]
1|803|Loss: 0.9306979179382324:   3%|▎         | 802/25880 [12:30<5:27:53,  1.27it/s]
1|803|Loss: 0.9306979179382324:   3%|▎         | 803/25880 [12:31<5:27:11,  1.28it/s]
1|804|Loss: 1.0162999629974365:   3%|▎         | 803/25880 [12:31<5:27:11,  1.28it/s]
1|804|Loss: 1.0162999629974365:   3%|▎         | 804/25880 [12:31<5:10:36,  1.35it/s]
1|805|Loss: 0.987175703048706:   3%|▎         | 804/25880 [12:32<5:10:36,  1.35it/s] 
1|805|Loss: 0.987175703048706:   3%|▎         | 805/25880 [12:32<5:06:03,  1.37it/s]
1|806|Loss: 0.9946043491363525:   3%|▎         | 805/25880 [12:32<5:06:03,  1.37it/s]
1|806|Loss: 0.9946043491363525:   3%|▎         | 806/25880 [12:33<4:42:58,  1.48it/s]
1|807|Loss: 0.9304737448692322:   3%|▎         | 806/25880 [12:33<4:42:58,  1.48it/s]
1|807|Loss: 0.9304737448692322:   3%|▎         | 807/25880 [12:33<4:44:13,  1.47it/s]
1|808|Loss: 0.9450376629829407:   3%|▎         | 807/25880 [12:34<4:44:13,  1.47it/s]
1|808|Loss: 0.9450376629829407:   3%|▎         | 808/25880 [12:34<5:02:41,  1.38it/s]
1|809|Loss: 0.8431492447853088:   3%|▎         | 808/25880 [12:35<5:02:41,  1.38it/s]
1|809|Loss: 0.8431492447853088:   3%|▎         | 809/25880 [12:35<5:12:24,  1.34it/s]
1|810|Loss: 0.8424388766288757:   3%|▎         | 809/25880 [12:35<5:12:24,  1.34it/s]
1|810|Loss: 0.8424388766288757:   3%|▎         | 810/25880 [12:36<5:24:41,  1.29it/s]
1|811|Loss: 0.9004791975021362:   3%|▎         | 810/25880 [12:36<5:24:41,  1.29it/s]
1|811|Loss: 0.9004791975021362:   3%|▎         | 811/25880 [12:36<5:23:25,  1.29it/s]
1|812|Loss: 1.0115277767181396:   3%|▎         | 811/25880 [12:37<5:23:25,  1.29it/s]
1|812|Loss: 1.0115277767181396:   3%|▎         | 812/25880 [12:37<4:58:11,  1.40it/s]
1|813|Loss: 0.9389268755912781:   3%|▎         | 812/25880 [12:37<4:58:11,  1.40it/s]
1|813|Loss: 0.9389268755912781:   3%|▎         | 813/25880 [12:38<4:43:05,  1.48it/s]
1|814|Loss: 0.9355939030647278:   3%|▎         | 813/25880 [12:38<4:43:05,  1.48it/s]
1|814|Loss: 0.9355939030647278:   3%|▎         | 814/25880 [12:38<4:58:43,  1.40it/s]
1|815|Loss: 0.9138544797897339:   3%|▎         | 814/25880 [12:39<4:58:43,  1.40it/s]
1|815|Loss: 0.9138544797897339:   3%|▎         | 815/25880 [12:39<5:05:35,  1.37it/s]
1|816|Loss: 1.1197302341461182:   3%|▎         | 815/25880 [12:40<5:05:35,  1.37it/s]
1|816|Loss: 1.1197302341461182:   3%|▎         | 816/25880 [12:40<4:57:03,  1.41it/s]
1|817|Loss: 0.801418125629425:   3%|▎         | 816/25880 [12:40<4:57:03,  1.41it/s] 
1|817|Loss: 0.801418125629425:   3%|▎         | 817/25880 [12:40<4:41:34,  1.48it/s]
1|818|Loss: 0.8096194863319397:   3%|▎         | 817/25880 [12:41<4:41:34,  1.48it/s]
1|818|Loss: 0.8096194863319397:   3%|▎         | 818/25880 [12:41<4:41:53,  1.48it/s]
1|819|Loss: 0.9694567322731018:   3%|▎         | 818/25880 [12:42<4:41:53,  1.48it/s]
1|819|Loss: 0.9694567322731018:   3%|▎         | 819/25880 [12:42<4:59:48,  1.39it/s]
1|820|Loss: 0.9151885509490967:   3%|▎         | 819/25880 [12:42<4:59:48,  1.39it/s]
1|820|Loss: 0.9151885509490967:   3%|▎         | 820/25880 [12:43<5:02:33,  1.38it/s]
1|821|Loss: 0.8958554863929749:   3%|▎         | 820/25880 [12:43<5:02:33,  1.38it/s]
1|821|Loss: 0.8958554863929749:   3%|▎         | 821/25880 [12:44<5:14:35,  1.33it/s]
1|822|Loss: 0.9776624441146851:   3%|▎         | 821/25880 [12:44<5:14:35,  1.33it/s]
1|822|Loss: 0.9776624441146851:   3%|▎         | 822/25880 [12:44<5:24:49,  1.29it/s]
1|823|Loss: 1.0625638961791992:   3%|▎         | 822/25880 [12:45<5:24:49,  1.29it/s]
1|823|Loss: 1.0625638961791992:   3%|▎         | 823/25880 [12:45<5:20:18,  1.30it/s]
1|824|Loss: 0.9701422452926636:   3%|▎         | 823/25880 [12:46<5:20:18,  1.30it/s]
1|824|Loss: 0.9701422452926636:   3%|▎         | 824/25880 [12:46<5:24:59,  1.28it/s]
1|825|Loss: 0.8876422047615051:   3%|▎         | 824/25880 [12:46<5:24:59,  1.28it/s]
1|825|Loss: 0.8876422047615051:   3%|▎         | 825/25880 [12:47<5:12:19,  1.34it/s]
1|826|Loss: 1.0761469602584839:   3%|▎         | 825/25880 [12:47<5:12:19,  1.34it/s]
1|826|Loss: 1.0761469602584839:   3%|▎         | 826/25880 [12:47<5:23:51,  1.29it/s]
1|827|Loss: 0.8197564482688904:   3%|▎         | 826/25880 [12:48<5:23:51,  1.29it/s]
1|827|Loss: 0.8197564482688904:   3%|▎         | 827/25880 [12:48<4:54:25,  1.42it/s]
1|828|Loss: 0.9654766917228699:   3%|▎         | 827/25880 [12:48<4:54:25,  1.42it/s]
1|828|Loss: 0.9654766917228699:   3%|▎         | 828/25880 [12:49<4:50:51,  1.44it/s]
1|829|Loss: 0.8218287825584412:   3%|▎         | 828/25880 [12:49<4:50:51,  1.44it/s]
1|829|Loss: 0.8218287825584412:   3%|▎         | 829/25880 [12:49<4:56:03,  1.41it/s]
1|830|Loss: 0.9582938551902771:   3%|▎         | 829/25880 [12:50<4:56:03,  1.41it/s]
1|830|Loss: 0.9582938551902771:   3%|▎         | 830/25880 [12:50<4:40:44,  1.49it/s]
1|831|Loss: 1.0113605260849:   3%|▎         | 830/25880 [12:50<4:40:44,  1.49it/s]   
1|831|Loss: 1.0113605260849:   3%|▎         | 831/25880 [12:51<4:48:35,  1.45it/s]
1|832|Loss: 0.8431547284126282:   3%|▎         | 831/25880 [12:51<4:48:35,  1.45it/s]
1|832|Loss: 0.8431547284126282:   3%|▎         | 832/25880 [12:51<4:41:22,  1.48it/s]
1|833|Loss: 0.7215794920921326:   3%|▎         | 832/25880 [12:52<4:41:22,  1.48it/s]
1|833|Loss: 0.7215794920921326:   3%|▎         | 833/25880 [12:52<5:03:47,  1.37it/s]
1|834|Loss: 0.9073747992515564:   3%|▎         | 833/25880 [12:53<5:03:47,  1.37it/s]
1|834|Loss: 0.9073747992515564:   3%|▎         | 834/25880 [12:53<4:57:11,  1.40it/s]
1|835|Loss: 0.905957818031311:   3%|▎         | 834/25880 [12:53<4:57:11,  1.40it/s] 
1|835|Loss: 0.905957818031311:   3%|▎         | 835/25880 [12:54<4:53:48,  1.42it/s]
1|836|Loss: 0.9003305435180664:   3%|▎         | 835/25880 [12:54<4:53:48,  1.42it/s]
1|836|Loss: 0.9003305435180664:   3%|▎         | 836/25880 [12:54<4:46:55,  1.45it/s]
1|837|Loss: 0.9722704887390137:   3%|▎         | 836/25880 [12:55<4:46:55,  1.45it/s]
1|837|Loss: 0.9722704887390137:   3%|▎         | 837/25880 [12:55<4:55:44,  1.41it/s]
1|838|Loss: 1.0398021936416626:   3%|▎         | 837/25880 [12:55<4:55:44,  1.41it/s]
1|838|Loss: 1.0398021936416626:   3%|▎         | 838/25880 [12:56<4:50:59,  1.43it/s]
1|839|Loss: 0.9750987887382507:   3%|▎         | 838/25880 [12:56<4:50:59,  1.43it/s]
1|839|Loss: 0.9750987887382507:   3%|▎         | 839/25880 [12:56<4:50:06,  1.44it/s]
1|840|Loss: 0.9501492977142334:   3%|▎         | 839/25880 [12:57<4:50:06,  1.44it/s]
1|840|Loss: 0.9501492977142334:   3%|▎         | 840/25880 [12:57<4:38:18,  1.50it/s]
1|841|Loss: 1.0018466711044312:   3%|▎         | 840/25880 [12:57<4:38:18,  1.50it/s]
1|841|Loss: 1.0018466711044312:   3%|▎         | 841/25880 [12:58<4:54:03,  1.42it/s]
1|842|Loss: 1.003255844116211:   3%|▎         | 841/25880 [12:58<4:54:03,  1.42it/s] 
1|842|Loss: 1.003255844116211:   3%|▎         | 842/25880 [12:59<5:05:43,  1.36it/s]
1|843|Loss: 1.1284211874008179:   3%|▎         | 842/25880 [12:59<5:05:43,  1.36it/s]
1|843|Loss: 1.1284211874008179:   3%|▎         | 843/25880 [12:59<4:39:09,  1.49it/s]
1|844|Loss: 0.9014019966125488:   3%|▎         | 843/25880 [12:59<4:39:09,  1.49it/s]
1|844|Loss: 0.9014019966125488:   3%|▎         | 844/25880 [13:00<4:46:49,  1.45it/s]
1|845|Loss: 0.9776995778083801:   3%|▎         | 844/25880 [13:00<4:46:49,  1.45it/s]
1|845|Loss: 0.9776995778083801:   3%|▎         | 845/25880 [13:00<4:45:26,  1.46it/s]
1|846|Loss: 0.9053126573562622:   3%|▎         | 845/25880 [13:01<4:45:26,  1.46it/s]
1|846|Loss: 0.9053126573562622:   3%|▎         | 846/25880 [13:01<4:46:55,  1.45it/s]
1|847|Loss: 0.8353146910667419:   3%|▎         | 846/25880 [13:02<4:46:55,  1.45it/s]
1|847|Loss: 0.8353146910667419:   3%|▎         | 847/25880 [13:02<5:14:15,  1.33it/s]
1|848|Loss: 0.9584663510322571:   3%|▎         | 847/25880 [13:02<5:14:15,  1.33it/s]
1|848|Loss: 0.9584663510322571:   3%|▎         | 848/25880 [13:03<5:08:24,  1.35it/s]
1|849|Loss: 0.8767469525337219:   3%|▎         | 848/25880 [13:03<5:08:24,  1.35it/s]
1|849|Loss: 0.8767469525337219:   3%|▎         | 849/25880 [13:03<4:49:24,  1.44it/s]
1|850|Loss: 1.207471251487732:   3%|▎         | 849/25880 [13:04<4:49:24,  1.44it/s] 
1|850|Loss: 1.207471251487732:   3%|▎         | 850/25880 [13:04<4:36:09,  1.51it/s]
1|851|Loss: 0.8378648161888123:   3%|▎         | 850/25880 [13:04<4:36:09,  1.51it/s]
1|851|Loss: 0.8378648161888123:   3%|▎         | 851/25880 [13:05<4:53:45,  1.42it/s]
1|852|Loss: 0.9401432275772095:   3%|▎         | 851/25880 [13:05<4:53:45,  1.42it/s]
1|852|Loss: 0.9401432275772095:   3%|▎         | 852/25880 [13:06<5:10:03,  1.35it/s]
1|853|Loss: 0.9533436894416809:   3%|▎         | 852/25880 [13:06<5:10:03,  1.35it/s]
1|853|Loss: 0.9533436894416809:   3%|▎         | 853/25880 [13:06<5:10:16,  1.34it/s]
1|854|Loss: 0.9151109457015991:   3%|▎         | 853/25880 [13:07<5:10:16,  1.34it/s]
1|854|Loss: 0.9151109457015991:   3%|▎         | 854/25880 [13:07<5:23:12,  1.29it/s]
1|855|Loss: 1.109499454498291:   3%|▎         | 854/25880 [13:08<5:23:12,  1.29it/s] 
1|855|Loss: 1.109499454498291:   3%|▎         | 855/25880 [13:08<5:12:41,  1.33it/s]
1|856|Loss: 0.8971902132034302:   3%|▎         | 855/25880 [13:08<5:12:41,  1.33it/s]
1|856|Loss: 0.8971902132034302:   3%|▎         | 856/25880 [13:09<5:07:48,  1.35it/s]
1|857|Loss: 0.9871997237205505:   3%|▎         | 856/25880 [13:09<5:07:48,  1.35it/s]
1|857|Loss: 0.9871997237205505:   3%|▎         | 857/25880 [13:09<5:14:30,  1.33it/s]
1|858|Loss: 0.9435529708862305:   3%|▎         | 857/25880 [13:10<5:14:30,  1.33it/s]
1|858|Loss: 0.9435529708862305:   3%|▎         | 858/25880 [13:10<5:04:23,  1.37it/s]
1|859|Loss: 0.9000135064125061:   3%|▎         | 858/25880 [13:10<5:04:23,  1.37it/s]
1|859|Loss: 0.9000135064125061:   3%|▎         | 859/25880 [13:11<4:52:45,  1.42it/s]
1|860|Loss: 0.9355219602584839:   3%|▎         | 859/25880 [13:11<4:52:45,  1.42it/s]
1|860|Loss: 0.9355219602584839:   3%|▎         | 860/25880 [13:11<4:44:52,  1.46it/s]
1|861|Loss: 0.8588271737098694:   3%|▎         | 860/25880 [13:12<4:44:52,  1.46it/s]
1|861|Loss: 0.8588271737098694:   3%|▎         | 861/25880 [13:12<4:46:17,  1.46it/s]
1|862|Loss: 0.9782876968383789:   3%|▎         | 861/25880 [13:12<4:46:17,  1.46it/s]
1|862|Loss: 0.9782876968383789:   3%|▎         | 862/25880 [13:13<4:39:18,  1.49it/s]
1|863|Loss: 1.0219312906265259:   3%|▎         | 862/25880 [13:13<4:39:18,  1.49it/s]
1|863|Loss: 1.0219312906265259:   3%|▎         | 863/25880 [13:14<5:06:49,  1.36it/s]
1|864|Loss: 0.9182459115982056:   3%|▎         | 863/25880 [13:14<5:06:49,  1.36it/s]
1|864|Loss: 0.9182459115982056:   3%|▎         | 864/25880 [13:14<5:08:38,  1.35it/s]
1|865|Loss: 0.9961207509040833:   3%|▎         | 864/25880 [13:15<5:08:38,  1.35it/s]
1|865|Loss: 0.9961207509040833:   3%|▎         | 865/25880 [13:15<4:43:27,  1.47it/s]
1|866|Loss: 1.0092648267745972:   3%|▎         | 865/25880 [13:15<4:43:27,  1.47it/s]
1|866|Loss: 1.0092648267745972:   3%|▎         | 866/25880 [13:15<4:40:58,  1.48it/s]
1|867|Loss: 1.1073416471481323:   3%|▎         | 866/25880 [13:16<4:40:58,  1.48it/s]
1|867|Loss: 1.1073416471481323:   3%|▎         | 867/25880 [13:16<4:28:49,  1.55it/s]
1|868|Loss: 0.9923467040061951:   3%|▎         | 867/25880 [13:16<4:28:49,  1.55it/s]
1|868|Loss: 0.9923467040061951:   3%|▎         | 868/25880 [13:17<4:49:52,  1.44it/s]
1|869|Loss: 0.8170403838157654:   3%|▎         | 868/25880 [13:17<4:49:52,  1.44it/s]
1|869|Loss: 0.8170403838157654:   3%|▎         | 869/25880 [13:18<4:48:57,  1.44it/s]
1|870|Loss: 1.039894700050354:   3%|▎         | 869/25880 [13:18<4:48:57,  1.44it/s] 
1|870|Loss: 1.039894700050354:   3%|▎         | 870/25880 [13:18<4:37:22,  1.50it/s]
1|871|Loss: 0.9858796000480652:   3%|▎         | 870/25880 [13:18<4:37:22,  1.50it/s]
1|871|Loss: 0.9858796000480652:   3%|▎         | 871/25880 [13:19<4:29:13,  1.55it/s]
1|872|Loss: 0.9494043588638306:   3%|▎         | 871/25880 [13:19<4:29:13,  1.55it/s]
1|872|Loss: 0.9494043588638306:   3%|▎         | 872/25880 [13:19<4:37:33,  1.50it/s]
1|873|Loss: 0.9091068506240845:   3%|▎         | 872/25880 [13:20<4:37:33,  1.50it/s]
1|873|Loss: 0.9091068506240845:   3%|▎         | 873/25880 [13:20<4:58:04,  1.40it/s]
1|874|Loss: 0.903761625289917:   3%|▎         | 873/25880 [13:21<4:58:04,  1.40it/s] 
1|874|Loss: 0.903761625289917:   3%|▎         | 874/25880 [13:21<4:41:43,  1.48it/s]
1|875|Loss: 0.9336625933647156:   3%|▎         | 874/25880 [13:21<4:41:43,  1.48it/s]
1|875|Loss: 0.9336625933647156:   3%|▎         | 875/25880 [13:22<4:48:06,  1.45it/s]
1|876|Loss: 0.9442099928855896:   3%|▎         | 875/25880 [13:22<4:48:06,  1.45it/s]
1|876|Loss: 0.9442099928855896:   3%|▎         | 876/25880 [13:22<5:05:35,  1.36it/s]
1|877|Loss: 0.9789550304412842:   3%|▎         | 876/25880 [13:23<5:05:35,  1.36it/s]
1|877|Loss: 0.9789550304412842:   3%|▎         | 877/25880 [13:23<5:09:31,  1.35it/s]
1|878|Loss: 0.97982257604599:   3%|▎         | 877/25880 [13:24<5:09:31,  1.35it/s]  
1|878|Loss: 0.97982257604599:   3%|▎         | 878/25880 [13:24<5:09:41,  1.35it/s]
1|879|Loss: 0.8980950117111206:   3%|▎         | 878/25880 [13:24<5:09:41,  1.35it/s]
1|879|Loss: 0.8980950117111206:   3%|▎         | 879/25880 [13:25<4:59:57,  1.39it/s]
1|880|Loss: 1.0305795669555664:   3%|▎         | 879/25880 [13:25<4:59:57,  1.39it/s]
1|880|Loss: 1.0305795669555664:   3%|▎         | 880/25880 [13:25<4:55:39,  1.41it/s]
1|881|Loss: 0.8179324269294739:   3%|▎         | 880/25880 [13:26<4:55:39,  1.41it/s]
1|881|Loss: 0.8179324269294739:   3%|▎         | 881/25880 [13:26<4:47:47,  1.45it/s]
1|882|Loss: 0.8421029448509216:   3%|▎         | 881/25880 [13:26<4:47:47,  1.45it/s]
1|882|Loss: 0.8421029448509216:   3%|▎         | 882/25880 [13:27<4:52:06,  1.43it/s]
1|883|Loss: 0.7495384812355042:   3%|▎         | 882/25880 [13:27<4:52:06,  1.43it/s]
1|883|Loss: 0.7495384812355042:   3%|▎         | 883/25880 [13:27<4:57:48,  1.40it/s]
1|884|Loss: 0.8880332708358765:   3%|▎         | 883/25880 [13:28<4:57:48,  1.40it/s]
1|884|Loss: 0.8880332708358765:   3%|▎         | 884/25880 [13:28<4:23:28,  1.58it/s]
1|885|Loss: 0.9774776697158813:   3%|▎         | 884/25880 [13:28<4:23:28,  1.58it/s]
1|885|Loss: 0.9774776697158813:   3%|▎         | 885/25880 [13:28<4:09:19,  1.67it/s]
1|886|Loss: 0.9350204467773438:   3%|▎         | 885/25880 [13:29<4:09:19,  1.67it/s]
1|886|Loss: 0.9350204467773438:   3%|▎         | 886/25880 [13:29<4:59:09,  1.39it/s]
1|887|Loss: 1.3231102228164673:   3%|▎         | 886/25880 [13:30<4:59:09,  1.39it/s]
1|887|Loss: 1.3231102228164673:   3%|▎         | 887/25880 [13:30<5:35:33,  1.24it/s]
1|888|Loss: 0.9168338179588318:   3%|▎         | 887/25880 [13:31<5:35:33,  1.24it/s]
1|888|Loss: 0.9168338179588318:   3%|▎         | 888/25880 [13:31<5:33:31,  1.25it/s]
1|889|Loss: 1.0412187576293945:   3%|▎         | 888/25880 [13:32<5:33:31,  1.25it/s]
1|889|Loss: 1.0412187576293945:   3%|▎         | 889/25880 [13:32<5:25:14,  1.28it/s]
1|890|Loss: 0.9156469106674194:   3%|▎         | 889/25880 [13:32<5:25:14,  1.28it/s]
1|890|Loss: 0.9156469106674194:   3%|▎         | 890/25880 [13:33<5:36:18,  1.24it/s]
1|891|Loss: 0.9174980521202087:   3%|▎         | 890/25880 [13:33<5:36:18,  1.24it/s]
1|891|Loss: 0.9174980521202087:   3%|▎         | 891/25880 [13:34<5:36:16,  1.24it/s]
1|892|Loss: 0.8987804055213928:   3%|▎         | 891/25880 [13:34<5:36:16,  1.24it/s]
1|892|Loss: 0.8987804055213928:   3%|▎         | 892/25880 [13:34<5:29:46,  1.26it/s]
1|893|Loss: 0.8795822858810425:   3%|▎         | 892/25880 [13:35<5:29:46,  1.26it/s]
1|893|Loss: 0.8795822858810425:   3%|▎         | 893/25880 [13:35<5:22:31,  1.29it/s]
1|894|Loss: 1.0094151496887207:   3%|▎         | 893/25880 [13:35<5:22:31,  1.29it/s]
1|894|Loss: 1.0094151496887207:   3%|▎         | 894/25880 [13:36<5:07:37,  1.35it/s]
1|895|Loss: 0.9586195349693298:   3%|▎         | 894/25880 [13:36<5:07:37,  1.35it/s]
1|895|Loss: 0.9586195349693298:   3%|▎         | 895/25880 [13:36<4:55:27,  1.41it/s]
1|896|Loss: 0.7772217392921448:   3%|▎         | 895/25880 [13:37<4:55:27,  1.41it/s]
1|896|Loss: 0.7772217392921448:   3%|▎         | 896/25880 [13:37<5:07:27,  1.35it/s]
1|897|Loss: 1.004436731338501:   3%|▎         | 896/25880 [13:38<5:07:27,  1.35it/s] 
1|897|Loss: 1.004436731338501:   3%|▎         | 897/25880 [13:38<5:24:48,  1.28it/s]
1|898|Loss: 0.9143998622894287:   3%|▎         | 897/25880 [13:39<5:24:48,  1.28it/s]
1|898|Loss: 0.9143998622894287:   3%|▎         | 898/25880 [13:39<5:35:20,  1.24it/s]
1|899|Loss: 0.8870411515235901:   3%|▎         | 898/25880 [13:39<5:35:20,  1.24it/s]
1|899|Loss: 0.8870411515235901:   3%|▎         | 899/25880 [13:39<5:01:50,  1.38it/s]
1|900|Loss: 0.8416601419448853:   3%|▎         | 899/25880 [13:40<5:01:50,  1.38it/s]
1|900|Loss: 0.8416601419448853:   3%|▎         | 900/25880 [13:40<5:02:33,  1.38it/s]
1|901|Loss: 0.715158224105835:   3%|▎         | 900/25880 [13:41<5:02:33,  1.38it/s] 
1|901|Loss: 0.715158224105835:   3%|▎         | 901/25880 [13:41<4:55:29,  1.41it/s]
1|902|Loss: 0.8472555875778198:   3%|▎         | 901/25880 [13:41<4:55:29,  1.41it/s]
1|902|Loss: 0.8472555875778198:   3%|▎         | 902/25880 [13:42<4:53:02,  1.42it/s]
1|903|Loss: 0.8809016942977905:   3%|▎         | 902/25880 [13:42<4:53:02,  1.42it/s]
1|903|Loss: 0.8809016942977905:   3%|▎         | 903/25880 [13:42<4:40:03,  1.49it/s]
1|904|Loss: 1.0765267610549927:   3%|▎         | 903/25880 [13:43<4:40:03,  1.49it/s]
1|904|Loss: 1.0765267610549927:   3%|▎         | 904/25880 [13:43<4:54:45,  1.41it/s]
1|905|Loss: 0.8871039748191833:   3%|▎         | 904/25880 [13:43<4:54:45,  1.41it/s]
1|905|Loss: 0.8871039748191833:   3%|▎         | 905/25880 [13:44<4:57:14,  1.40it/s]
1|906|Loss: 0.9719682335853577:   3%|▎         | 905/25880 [13:44<4:57:14,  1.40it/s]
1|906|Loss: 0.9719682335853577:   4%|▎         | 906/25880 [13:44<4:58:09,  1.40it/s]
1|907|Loss: 0.9119023680686951:   4%|▎         | 906/25880 [13:45<4:58:09,  1.40it/s]
1|907|Loss: 0.9119023680686951:   4%|▎         | 907/25880 [13:45<5:05:35,  1.36it/s]
1|908|Loss: 0.8736162185668945:   4%|▎         | 907/25880 [13:46<5:05:35,  1.36it/s]
1|908|Loss: 0.8736162185668945:   4%|▎         | 908/25880 [13:46<5:06:26,  1.36it/s]
1|909|Loss: 0.9558180570602417:   4%|▎         | 908/25880 [13:46<5:06:26,  1.36it/s]
1|909|Loss: 0.9558180570602417:   4%|▎         | 909/25880 [13:47<5:20:00,  1.30it/s]
1|910|Loss: 1.0657694339752197:   4%|▎         | 909/25880 [13:47<5:20:00,  1.30it/s]
1|910|Loss: 1.0657694339752197:   4%|▎         | 910/25880 [13:47<4:52:13,  1.42it/s]
1|911|Loss: 0.8995296359062195:   4%|▎         | 910/25880 [13:48<4:52:13,  1.42it/s]
1|911|Loss: 0.8995296359062195:   4%|▎         | 911/25880 [13:48<5:01:20,  1.38it/s]
1|912|Loss: 0.8994900584220886:   4%|▎         | 911/25880 [13:49<5:01:20,  1.38it/s]
1|912|Loss: 0.8994900584220886:   4%|▎         | 912/25880 [13:49<5:16:13,  1.32it/s]
1|913|Loss: 0.9221137762069702:   4%|▎         | 912/25880 [13:49<5:16:13,  1.32it/s]
1|913|Loss: 0.9221137762069702:   4%|▎         | 913/25880 [13:50<5:26:06,  1.28it/s]
1|914|Loss: 0.9004773497581482:   4%|▎         | 913/25880 [13:50<5:26:06,  1.28it/s]
1|914|Loss: 0.9004773497581482:   4%|▎         | 914/25880 [13:50<5:19:32,  1.30it/s]
1|915|Loss: 0.8200632333755493:   4%|▎         | 914/25880 [13:51<5:19:32,  1.30it/s]
1|915|Loss: 0.8200632333755493:   4%|▎         | 915/25880 [13:51<5:13:33,  1.33it/s]
1|916|Loss: 0.8204901218414307:   4%|▎         | 915/25880 [13:52<5:13:33,  1.33it/s]
1|916|Loss: 0.8204901218414307:   4%|▎         | 916/25880 [13:52<5:00:49,  1.38it/s]
1|917|Loss: 0.8696280121803284:   4%|▎         | 916/25880 [13:52<5:00:49,  1.38it/s]
1|917|Loss: 0.8696280121803284:   4%|▎         | 917/25880 [13:53<4:55:44,  1.41it/s]
1|918|Loss: 1.0124664306640625:   4%|▎         | 917/25880 [13:53<4:55:44,  1.41it/s]
1|918|Loss: 1.0124664306640625:   4%|▎         | 918/25880 [13:53<5:06:26,  1.36it/s]
1|919|Loss: 0.8915688991546631:   4%|▎         | 918/25880 [13:54<5:06:26,  1.36it/s]
1|919|Loss: 0.8915688991546631:   4%|▎         | 919/25880 [13:54<5:19:55,  1.30it/s]
1|920|Loss: 0.9775419235229492:   4%|▎         | 919/25880 [13:55<5:19:55,  1.30it/s]
1|920|Loss: 0.9775419235229492:   4%|▎         | 920/25880 [13:55<5:09:25,  1.34it/s]
1|921|Loss: 1.061434030532837:   4%|▎         | 920/25880 [13:55<5:09:25,  1.34it/s] 
1|921|Loss: 1.061434030532837:   4%|▎         | 921/25880 [13:56<4:56:59,  1.40it/s]
1|922|Loss: 0.9461795091629028:   4%|▎         | 921/25880 [13:56<4:56:59,  1.40it/s]
1|922|Loss: 0.9461795091629028:   4%|▎         | 922/25880 [13:56<4:53:08,  1.42it/s]
1|923|Loss: 0.848002016544342:   4%|▎         | 922/25880 [13:57<4:53:08,  1.42it/s] 
1|923|Loss: 0.848002016544342:   4%|▎         | 923/25880 [13:57<4:54:12,  1.41it/s]
1|924|Loss: 0.8849719762802124:   4%|▎         | 923/25880 [13:57<4:54:12,  1.41it/s]
1|924|Loss: 0.8849719762802124:   4%|▎         | 924/25880 [13:58<4:46:57,  1.45it/s]
1|925|Loss: 0.9882059693336487:   4%|▎         | 924/25880 [13:58<4:46:57,  1.45it/s]
1|925|Loss: 0.9882059693336487:   4%|▎         | 925/25880 [13:58<4:40:02,  1.49it/s]
1|926|Loss: 1.0013689994812012:   4%|▎         | 925/25880 [13:59<4:40:02,  1.49it/s]
1|926|Loss: 1.0013689994812012:   4%|▎         | 926/25880 [13:59<4:44:46,  1.46it/s]
1|927|Loss: 0.9991648197174072:   4%|▎         | 926/25880 [13:59<4:44:46,  1.46it/s]
1|927|Loss: 0.9991648197174072:   4%|▎         | 927/25880 [14:00<4:41:14,  1.48it/s]
1|928|Loss: 0.8832259178161621:   4%|▎         | 927/25880 [14:00<4:41:14,  1.48it/s]
1|928|Loss: 0.8832259178161621:   4%|▎         | 928/25880 [14:00<4:55:39,  1.41it/s]
1|929|Loss: 1.1161679029464722:   4%|▎         | 928/25880 [14:01<4:55:39,  1.41it/s]
1|929|Loss: 1.1161679029464722:   4%|▎         | 929/25880 [14:01<4:34:45,  1.51it/s]
1|930|Loss: 0.9435951113700867:   4%|▎         | 929/25880 [14:01<4:34:45,  1.51it/s]
1|930|Loss: 0.9435951113700867:   4%|▎         | 930/25880 [14:02<4:37:25,  1.50it/s]
1|931|Loss: 0.968706488609314:   4%|▎         | 930/25880 [14:02<4:37:25,  1.50it/s] 
1|931|Loss: 0.968706488609314:   4%|▎         | 931/25880 [14:02<5:00:43,  1.38it/s]
1|932|Loss: 0.861632227897644:   4%|▎         | 931/25880 [14:03<5:00:43,  1.38it/s]
1|932|Loss: 0.861632227897644:   4%|▎         | 932/25880 [14:03<5:04:38,  1.36it/s]
1|933|Loss: 0.8634203672409058:   4%|▎         | 932/25880 [14:04<5:04:38,  1.36it/s]
1|933|Loss: 0.8634203672409058:   4%|▎         | 933/25880 [14:04<5:11:30,  1.33it/s]
1|934|Loss: 1.009427547454834:   4%|▎         | 933/25880 [14:04<5:11:30,  1.33it/s] 
1|934|Loss: 1.009427547454834:   4%|▎         | 934/25880 [14:05<5:22:47,  1.29it/s]
1|935|Loss: 0.9334450364112854:   4%|▎         | 934/25880 [14:05<5:22:47,  1.29it/s]
1|935|Loss: 0.9334450364112854:   4%|▎         | 935/25880 [14:06<5:32:44,  1.25it/s]
1|936|Loss: 0.8611193299293518:   4%|▎         | 935/25880 [14:06<5:32:44,  1.25it/s]
1|936|Loss: 0.8611193299293518:   4%|▎         | 936/25880 [14:06<5:28:33,  1.27it/s]
1|937|Loss: 0.9186157584190369:   4%|▎         | 936/25880 [14:07<5:28:33,  1.27it/s]
1|937|Loss: 0.9186157584190369:   4%|▎         | 937/25880 [14:07<5:26:31,  1.27it/s]
1|938|Loss: 0.8992483019828796:   4%|▎         | 937/25880 [14:08<5:26:31,  1.27it/s]
1|938|Loss: 0.8992483019828796:   4%|▎         | 938/25880 [14:08<5:29:31,  1.26it/s]
1|939|Loss: 0.8901407718658447:   4%|▎         | 938/25880 [14:08<5:29:31,  1.26it/s]
1|939|Loss: 0.8901407718658447:   4%|▎         | 939/25880 [14:09<5:07:48,  1.35it/s]
1|940|Loss: 0.9472577571868896:   4%|▎         | 939/25880 [14:09<5:07:48,  1.35it/s]
1|940|Loss: 0.9472577571868896:   4%|▎         | 940/25880 [14:09<5:03:52,  1.37it/s]
1|941|Loss: 0.8709307909011841:   4%|▎         | 940/25880 [14:10<5:03:52,  1.37it/s]
1|941|Loss: 0.8709307909011841:   4%|▎         | 941/25880 [14:10<5:11:59,  1.33it/s]
1|942|Loss: 0.9091961979866028:   4%|▎         | 941/25880 [14:11<5:11:59,  1.33it/s]
1|942|Loss: 0.9091961979866028:   4%|▎         | 942/25880 [14:11<4:59:29,  1.39it/s]
1|943|Loss: 0.8575065732002258:   4%|▎         | 942/25880 [14:11<4:59:29,  1.39it/s]
1|943|Loss: 0.8575065732002258:   4%|▎         | 943/25880 [14:12<4:59:01,  1.39it/s]
1|944|Loss: 1.0148026943206787:   4%|▎         | 943/25880 [14:12<4:59:01,  1.39it/s]
1|944|Loss: 1.0148026943206787:   4%|▎         | 944/25880 [14:12<4:58:17,  1.39it/s]
1|945|Loss: 1.0950473546981812:   4%|▎         | 944/25880 [14:13<4:58:17,  1.39it/s]
1|945|Loss: 1.0950473546981812:   4%|▎         | 945/25880 [14:13<4:36:08,  1.51it/s]
1|946|Loss: 0.971078097820282:   4%|▎         | 945/25880 [14:13<4:36:08,  1.51it/s] 
1|946|Loss: 0.971078097820282:   4%|▎         | 946/25880 [14:13<4:39:46,  1.49it/s]
1|947|Loss: 0.9829787611961365:   4%|▎         | 946/25880 [14:14<4:39:46,  1.49it/s]
1|947|Loss: 0.9829787611961365:   4%|▎         | 947/25880 [14:14<4:37:30,  1.50it/s]
1|948|Loss: 0.8009136915206909:   4%|▎         | 947/25880 [14:15<4:37:30,  1.50it/s]
1|948|Loss: 0.8009136915206909:   4%|▎         | 948/25880 [14:15<4:48:12,  1.44it/s]
1|949|Loss: 0.9327248334884644:   4%|▎         | 948/25880 [14:15<4:48:12,  1.44it/s]
1|949|Loss: 0.9327248334884644:   4%|▎         | 949/25880 [14:16<4:43:07,  1.47it/s]
1|950|Loss: 1.0078109502792358:   4%|▎         | 949/25880 [14:16<4:43:07,  1.47it/s]
1|950|Loss: 1.0078109502792358:   4%|▎         | 950/25880 [14:16<4:46:30,  1.45it/s]
1|951|Loss: 0.9444061517715454:   4%|▎         | 950/25880 [14:17<4:46:30,  1.45it/s]
1|951|Loss: 0.9444061517715454:   4%|▎         | 951/25880 [14:17<4:41:53,  1.47it/s]
1|952|Loss: 0.9786055684089661:   4%|▎         | 951/25880 [14:17<4:41:53,  1.47it/s]
1|952|Loss: 0.9786055684089661:   4%|▎         | 952/25880 [14:18<4:59:27,  1.39it/s]
1|953|Loss: 0.8967410326004028:   4%|▎         | 952/25880 [14:18<4:59:27,  1.39it/s]
1|953|Loss: 0.8967410326004028:   4%|▎         | 953/25880 [14:19<5:19:46,  1.30it/s]
1|954|Loss: 0.9717830419540405:   4%|▎         | 953/25880 [14:19<5:19:46,  1.30it/s]
1|954|Loss: 0.9717830419540405:   4%|▎         | 954/25880 [14:19<4:57:30,  1.40it/s]
1|955|Loss: 0.9661399126052856:   4%|▎         | 954/25880 [14:20<4:57:30,  1.40it/s]
1|955|Loss: 0.9661399126052856:   4%|▎         | 955/25880 [14:20<5:03:16,  1.37it/s]
1|956|Loss: 0.9605260491371155:   4%|▎         | 955/25880 [14:20<5:03:16,  1.37it/s]
1|956|Loss: 0.9605260491371155:   4%|▎         | 956/25880 [14:21<4:47:24,  1.45it/s]
1|957|Loss: 0.8926464319229126:   4%|▎         | 956/25880 [14:21<4:47:24,  1.45it/s]
1|957|Loss: 0.8926464319229126:   4%|▎         | 957/25880 [14:21<4:57:29,  1.40it/s]
1|958|Loss: 0.8212535977363586:   4%|▎         | 957/25880 [14:22<4:57:29,  1.40it/s]
1|958|Loss: 0.8212535977363586:   4%|▎         | 958/25880 [14:22<5:19:54,  1.30it/s]
1|959|Loss: 0.8999689817428589:   4%|▎         | 958/25880 [14:23<5:19:54,  1.30it/s]
1|959|Loss: 0.8999689817428589:   4%|▎         | 959/25880 [14:23<5:29:21,  1.26it/s]
1|960|Loss: 0.8708869218826294:   4%|▎         | 959/25880 [14:23<5:29:21,  1.26it/s]
1|960|Loss: 0.8708869218826294:   4%|▎         | 960/25880 [14:24<5:33:36,  1.24it/s]
1|961|Loss: 0.843665599822998:   4%|▎         | 960/25880 [14:24<5:33:36,  1.24it/s] 
1|961|Loss: 0.843665599822998:   4%|▎         | 961/25880 [14:25<5:17:07,  1.31it/s]
1|962|Loss: 0.9169431924819946:   4%|▎         | 961/25880 [14:25<5:17:07,  1.31it/s]
1|962|Loss: 0.9169431924819946:   4%|▎         | 962/25880 [14:25<5:09:00,  1.34it/s]
1|963|Loss: 0.9382011294364929:   4%|▎         | 962/25880 [14:26<5:09:00,  1.34it/s]
1|963|Loss: 0.9382011294364929:   4%|▎         | 963/25880 [14:26<5:17:18,  1.31it/s]
1|964|Loss: 0.7850143313407898:   4%|▎         | 963/25880 [14:26<5:17:18,  1.31it/s]
1|964|Loss: 0.7850143313407898:   4%|▎         | 964/25880 [14:27<5:15:51,  1.31it/s]
1|965|Loss: 0.9602389335632324:   4%|▎         | 964/25880 [14:27<5:15:51,  1.31it/s]
1|965|Loss: 0.9602389335632324:   4%|▎         | 965/25880 [14:28<5:09:13,  1.34it/s]
1|966|Loss: 0.9584032893180847:   4%|▎         | 965/25880 [14:28<5:09:13,  1.34it/s]
1|966|Loss: 0.9584032893180847:   4%|▎         | 966/25880 [14:28<4:55:09,  1.41it/s]
1|967|Loss: 0.7219310402870178:   4%|▎         | 966/25880 [14:29<4:55:09,  1.41it/s]
1|967|Loss: 0.7219310402870178:   4%|▎         | 967/25880 [14:29<4:51:40,  1.42it/s]
1|968|Loss: 0.8653293251991272:   4%|▎         | 967/25880 [14:29<4:51:40,  1.42it/s]
1|968|Loss: 0.8653293251991272:   4%|▎         | 968/25880 [14:29<4:31:06,  1.53it/s]
1|969|Loss: 0.9716980457305908:   4%|▎         | 968/25880 [14:30<4:31:06,  1.53it/s]
1|969|Loss: 0.9716980457305908:   4%|▎         | 969/25880 [14:30<4:32:28,  1.52it/s]
1|970|Loss: 0.8584945797920227:   4%|▎         | 969/25880 [14:30<4:32:28,  1.52it/s]
1|970|Loss: 0.8584945797920227:   4%|▎         | 970/25880 [14:31<4:38:34,  1.49it/s]
1|971|Loss: 1.088541865348816:   4%|▎         | 970/25880 [14:31<4:38:34,  1.49it/s] 
1|971|Loss: 1.088541865348816:   4%|▍         | 971/25880 [14:32<4:52:04,  1.42it/s]
1|972|Loss: 0.862512469291687:   4%|▍         | 971/25880 [14:32<4:52:04,  1.42it/s]
1|972|Loss: 0.862512469291687:   4%|▍         | 972/25880 [14:32<4:45:53,  1.45it/s]
1|973|Loss: 0.869297444820404:   4%|▍         | 972/25880 [14:32<4:45:53,  1.45it/s]
1|973|Loss: 0.869297444820404:   4%|▍         | 973/25880 [14:33<4:13:50,  1.64it/s]
1|974|Loss: 0.7622671127319336:   4%|▍         | 973/25880 [14:33<4:13:50,  1.64it/s]
1|974|Loss: 0.7622671127319336:   4%|▍         | 974/25880 [14:33<3:59:12,  1.74it/s]
1|975|Loss: 0.9646447896957397:   4%|▍         | 974/25880 [14:33<3:59:12,  1.74it/s]
1|975|Loss: 0.9646447896957397:   4%|▍         | 975/25880 [14:34<4:03:13,  1.71it/s]
1|976|Loss: 0.9627317786216736:   4%|▍         | 975/25880 [14:34<4:03:13,  1.71it/s]
1|976|Loss: 0.9627317786216736:   4%|▍         | 976/25880 [14:34<4:01:02,  1.72it/s]
1|977|Loss: 0.9576392769813538:   4%|▍         | 976/25880 [14:35<4:01:02,  1.72it/s]
1|977|Loss: 0.9576392769813538:   4%|▍         | 977/25880 [14:35<4:26:39,  1.56it/s]
1|978|Loss: 0.9896119236946106:   4%|▍         | 977/25880 [14:35<4:26:39,  1.56it/s]
1|978|Loss: 0.9896119236946106:   4%|▍         | 978/25880 [14:36<4:38:20,  1.49it/s]
1|979|Loss: 0.9258149862289429:   4%|▍         | 978/25880 [14:36<4:38:20,  1.49it/s]
1|979|Loss: 0.9258149862289429:   4%|▍         | 979/25880 [14:36<4:35:47,  1.50it/s]
1|980|Loss: 0.8571731448173523:   4%|▍         | 979/25880 [14:37<4:35:47,  1.50it/s]
1|980|Loss: 0.8571731448173523:   4%|▍         | 980/25880 [14:37<4:26:03,  1.56it/s]
1|981|Loss: 0.8734731078147888:   4%|▍         | 980/25880 [14:37<4:26:03,  1.56it/s]
1|981|Loss: 0.8734731078147888:   4%|▍         | 981/25880 [14:38<4:32:59,  1.52it/s]
1|982|Loss: 0.8619715571403503:   4%|▍         | 981/25880 [14:38<4:32:59,  1.52it/s]
1|982|Loss: 0.8619715571403503:   4%|▍         | 982/25880 [14:39<4:56:44,  1.40it/s]
1|983|Loss: 0.9248859286308289:   4%|▍         | 982/25880 [14:39<4:56:44,  1.40it/s]
1|983|Loss: 0.9248859286308289:   4%|▍         | 983/25880 [14:39<4:51:10,  1.43it/s]
1|984|Loss: 0.9717397689819336:   4%|▍         | 983/25880 [14:40<4:51:10,  1.43it/s]
1|984|Loss: 0.9717397689819336:   4%|▍         | 984/25880 [14:40<4:36:55,  1.50it/s]
1|985|Loss: 0.8874683976173401:   4%|▍         | 984/25880 [14:40<4:36:55,  1.50it/s]
1|985|Loss: 0.8874683976173401:   4%|▍         | 985/25880 [14:41<4:38:41,  1.49it/s]
1|986|Loss: 0.8860136866569519:   4%|▍         | 985/25880 [14:41<4:38:41,  1.49it/s]
1|986|Loss: 0.8860136866569519:   4%|▍         | 986/25880 [14:41<4:45:18,  1.45it/s]
1|987|Loss: 0.9852046370506287:   4%|▍         | 986/25880 [14:42<4:45:18,  1.45it/s]
1|987|Loss: 0.9852046370506287:   4%|▍         | 987/25880 [14:42<4:38:32,  1.49it/s]
1|988|Loss: 0.9597854018211365:   4%|▍         | 987/25880 [14:42<4:38:32,  1.49it/s]
1|988|Loss: 0.9597854018211365:   4%|▍         | 988/25880 [14:43<4:42:06,  1.47it/s]
1|989|Loss: 0.9184086918830872:   4%|▍         | 988/25880 [14:43<4:42:06,  1.47it/s]
1|989|Loss: 0.9184086918830872:   4%|▍         | 989/25880 [14:43<4:19:13,  1.60it/s]
1|990|Loss: 0.9966704845428467:   4%|▍         | 989/25880 [14:43<4:19:13,  1.60it/s]
1|990|Loss: 0.9966704845428467:   4%|▍         | 990/25880 [14:44<4:21:13,  1.59it/s]
1|991|Loss: 1.0656906366348267:   4%|▍         | 990/25880 [14:44<4:21:13,  1.59it/s]
1|991|Loss: 1.0656906366348267:   4%|▍         | 991/25880 [14:44<4:20:22,  1.59it/s]
1|992|Loss: 0.8364261388778687:   4%|▍         | 991/25880 [14:45<4:20:22,  1.59it/s]
1|992|Loss: 0.8364261388778687:   4%|▍         | 992/25880 [14:45<4:35:48,  1.50it/s]
1|993|Loss: 0.9842987656593323:   4%|▍         | 992/25880 [14:46<4:35:48,  1.50it/s]
1|993|Loss: 0.9842987656593323:   4%|▍         | 993/25880 [14:46<4:51:26,  1.42it/s]
1|994|Loss: 0.9481340646743774:   4%|▍         | 993/25880 [14:46<4:51:26,  1.42it/s]
1|994|Loss: 0.9481340646743774:   4%|▍         | 994/25880 [14:47<5:06:30,  1.35it/s]
1|995|Loss: 0.7907130718231201:   4%|▍         | 994/25880 [14:47<5:06:30,  1.35it/s]
1|995|Loss: 0.7907130718231201:   4%|▍         | 995/25880 [14:47<5:06:51,  1.35it/s]
1|996|Loss: 0.8565470576286316:   4%|▍         | 995/25880 [14:48<5:06:51,  1.35it/s]
1|996|Loss: 0.8565470576286316:   4%|▍         | 996/25880 [14:48<5:02:12,  1.37it/s]
1|997|Loss: 1.0369112491607666:   4%|▍         | 996/25880 [14:49<5:02:12,  1.37it/s]
1|997|Loss: 1.0369112491607666:   4%|▍         | 997/25880 [14:49<4:52:06,  1.42it/s]
1|998|Loss: 0.9025200009346008:   4%|▍         | 997/25880 [14:49<4:52:06,  1.42it/s]
1|998|Loss: 0.9025200009346008:   4%|▍         | 998/25880 [14:50<5:16:04,  1.31it/s]
1|999|Loss: 1.0576084852218628:   4%|▍         | 998/25880 [14:50<5:16:04,  1.31it/s]
1|999|Loss: 1.0576084852218628:   4%|▍         | 999/25880 [14:50<5:17:34,  1.31it/s]
1|1000|Loss: 0.8229052424430847:   4%|▍         | 999/25880 [14:51<5:17:34,  1.31it/s]
1|1000|Loss: 0.8229052424430847:   4%|▍         | 1000/25880 [14:51<5:37:00,  1.23it/s]
1|1001|Loss: 0.8678731322288513:   4%|▍         | 1000/25880 [14:52<5:37:00,  1.23it/s]
1|1001|Loss: 0.8678731322288513:   4%|▍         | 1001/25880 [14:52<5:33:18,  1.24it/s]
1|1002|Loss: 0.8607666492462158:   4%|▍         | 1001/25880 [14:53<5:33:18,  1.24it/s]
1|1002|Loss: 0.8607666492462158:   4%|▍         | 1002/25880 [14:53<5:24:41,  1.28it/s]
1|1003|Loss: 0.9369547367095947:   4%|▍         | 1002/25880 [14:53<5:24:41,  1.28it/s]
1|1003|Loss: 0.9369547367095947:   4%|▍         | 1003/25880 [14:54<5:09:07,  1.34it/s]
1|1004|Loss: 0.992042601108551:   4%|▍         | 1003/25880 [14:54<5:09:07,  1.34it/s] 
1|1004|Loss: 0.992042601108551:   4%|▍         | 1004/25880 [14:54<5:06:37,  1.35it/s]
1|1005|Loss: 0.8522279858589172:   4%|▍         | 1004/25880 [14:55<5:06:37,  1.35it/s]
1|1005|Loss: 0.8522279858589172:   4%|▍         | 1005/25880 [14:55<5:07:34,  1.35it/s]
1|1006|Loss: 0.9417310357093811:   4%|▍         | 1005/25880 [14:55<5:07:34,  1.35it/s]
1|1006|Loss: 0.9417310357093811:   4%|▍         | 1006/25880 [14:56<4:56:45,  1.40it/s]
1|1007|Loss: 0.9734816551208496:   4%|▍         | 1006/25880 [14:56<4:56:45,  1.40it/s]
1|1007|Loss: 0.9734816551208496:   4%|▍         | 1007/25880 [14:56<4:40:52,  1.48it/s]
1|1008|Loss: 0.8568747043609619:   4%|▍         | 1007/25880 [14:57<4:40:52,  1.48it/s]
1|1008|Loss: 0.8568747043609619:   4%|▍         | 1008/25880 [14:57<4:43:10,  1.46it/s]
1|1009|Loss: 0.887894332408905:   4%|▍         | 1008/25880 [14:57<4:43:10,  1.46it/s] 
1|1009|Loss: 0.887894332408905:   4%|▍         | 1009/25880 [14:58<4:48:08,  1.44it/s]
1|1010|Loss: 0.8310858011245728:   4%|▍         | 1009/25880 [14:58<4:48:08,  1.44it/s]
1|1010|Loss: 0.8310858011245728:   4%|▍         | 1010/25880 [14:58<4:29:16,  1.54it/s]
1|1011|Loss: 0.9214836955070496:   4%|▍         | 1010/25880 [14:59<4:29:16,  1.54it/s]
1|1011|Loss: 0.9214836955070496:   4%|▍         | 1011/25880 [14:59<4:21:40,  1.58it/s]
1|1012|Loss: 1.036100149154663:   4%|▍         | 1011/25880 [14:59<4:21:40,  1.58it/s] 
1|1012|Loss: 1.036100149154663:   4%|▍         | 1012/25880 [15:00<4:40:46,  1.48it/s]
1|1013|Loss: 0.9520487785339355:   4%|▍         | 1012/25880 [15:00<4:40:46,  1.48it/s]
1|1013|Loss: 0.9520487785339355:   4%|▍         | 1013/25880 [15:00<4:54:20,  1.41it/s]
1|1014|Loss: 0.8618558645248413:   4%|▍         | 1013/25880 [15:01<4:54:20,  1.41it/s]
1|1014|Loss: 0.8618558645248413:   4%|▍         | 1014/25880 [15:01<5:12:13,  1.33it/s]
1|1015|Loss: 0.9826377034187317:   4%|▍         | 1014/25880 [15:02<5:12:13,  1.33it/s]
1|1015|Loss: 0.9826377034187317:   4%|▍         | 1015/25880 [15:02<5:14:52,  1.32it/s]
1|1016|Loss: 0.9832728505134583:   4%|▍         | 1015/25880 [15:02<5:14:52,  1.32it/s]
1|1016|Loss: 0.9832728505134583:   4%|▍         | 1016/25880 [15:03<5:03:05,  1.37it/s]
1|1017|Loss: 0.8477011919021606:   4%|▍         | 1016/25880 [15:03<5:03:05,  1.37it/s]
1|1017|Loss: 0.8477011919021606:   4%|▍         | 1017/25880 [15:04<5:23:31,  1.28it/s]
1|1018|Loss: 0.9526979327201843:   4%|▍         | 1017/25880 [15:04<5:23:31,  1.28it/s]
1|1018|Loss: 0.9526979327201843:   4%|▍         | 1018/25880 [15:04<5:24:09,  1.28it/s]
1|1019|Loss: 0.9033721685409546:   4%|▍         | 1018/25880 [15:05<5:24:09,  1.28it/s]
1|1019|Loss: 0.9033721685409546:   4%|▍         | 1019/25880 [15:05<5:10:25,  1.33it/s]
1|1020|Loss: 0.9123239517211914:   4%|▍         | 1019/25880 [15:06<5:10:25,  1.33it/s]
1|1020|Loss: 0.9123239517211914:   4%|▍         | 1020/25880 [15:06<5:30:48,  1.25it/s]
1|1021|Loss: 0.9781783223152161:   4%|▍         | 1020/25880 [15:06<5:30:48,  1.25it/s]
1|1021|Loss: 0.9781783223152161:   4%|▍         | 1021/25880 [15:07<5:20:10,  1.29it/s]
1|1022|Loss: 0.8618592619895935:   4%|▍         | 1021/25880 [15:07<5:20:10,  1.29it/s]
1|1022|Loss: 0.8618592619895935:   4%|▍         | 1022/25880 [15:07<5:20:29,  1.29it/s]
1|1023|Loss: 0.9406509399414062:   4%|▍         | 1022/25880 [15:08<5:20:29,  1.29it/s]
1|1023|Loss: 0.9406509399414062:   4%|▍         | 1023/25880 [15:08<5:14:52,  1.32it/s]
1|1024|Loss: 0.9363439679145813:   4%|▍         | 1023/25880 [15:09<5:14:52,  1.32it/s]
1|1024|Loss: 0.9363439679145813:   4%|▍         | 1024/25880 [15:09<5:01:19,  1.37it/s]
1|1025|Loss: 0.9744524955749512:   4%|▍         | 1024/25880 [15:09<5:01:19,  1.37it/s]
1|1025|Loss: 0.9744524955749512:   4%|▍         | 1025/25880 [15:10<4:56:01,  1.40it/s]
1|1026|Loss: 0.9742251634597778:   4%|▍         | 1025/25880 [15:10<4:56:01,  1.40it/s]
1|1026|Loss: 0.9742251634597778:   4%|▍         | 1026/25880 [15:10<4:56:06,  1.40it/s]
1|1027|Loss: 0.8892983198165894:   4%|▍         | 1026/25880 [15:11<4:56:06,  1.40it/s]
1|1027|Loss: 0.8892983198165894:   4%|▍         | 1027/25880 [15:11<4:54:28,  1.41it/s]
1|1028|Loss: 1.0891695022583008:   4%|▍         | 1027/25880 [15:11<4:54:28,  1.41it/s]
1|1028|Loss: 1.0891695022583008:   4%|▍         | 1028/25880 [15:12<5:01:10,  1.38it/s]
1|1029|Loss: 1.0748451948165894:   4%|▍         | 1028/25880 [15:12<5:01:10,  1.38it/s]
1|1029|Loss: 1.0748451948165894:   4%|▍         | 1029/25880 [15:12<4:54:10,  1.41it/s]
1|1030|Loss: 0.9266566038131714:   4%|▍         | 1029/25880 [15:13<4:54:10,  1.41it/s]
1|1030|Loss: 0.9266566038131714:   4%|▍         | 1030/25880 [15:13<4:52:09,  1.42it/s]
1|1031|Loss: 0.884285569190979:   4%|▍         | 1030/25880 [15:13<4:52:09,  1.42it/s] 
1|1031|Loss: 0.884285569190979:   4%|▍         | 1031/25880 [15:14<4:40:57,  1.47it/s]
1|1032|Loss: 1.0208237171173096:   4%|▍         | 1031/25880 [15:14<4:40:57,  1.47it/s]
1|1032|Loss: 1.0208237171173096:   4%|▍         | 1032/25880 [15:14<4:23:05,  1.57it/s]
1|1033|Loss: 0.9305364489555359:   4%|▍         | 1032/25880 [15:15<4:23:05,  1.57it/s]
1|1033|Loss: 0.9305364489555359:   4%|▍         | 1033/25880 [15:15<4:31:16,  1.53it/s]
1|1034|Loss: 1.0335453748703003:   4%|▍         | 1033/25880 [15:15<4:31:16,  1.53it/s]
1|1034|Loss: 1.0335453748703003:   4%|▍         | 1034/25880 [15:16<4:51:47,  1.42it/s]
1|1035|Loss: 1.064151644706726:   4%|▍         | 1034/25880 [15:16<4:51:47,  1.42it/s] 
1|1035|Loss: 1.064151644706726:   4%|▍         | 1035/25880 [15:16<4:40:32,  1.48it/s]
1|1036|Loss: 0.8419873118400574:   4%|▍         | 1035/25880 [15:17<4:40:32,  1.48it/s]
1|1036|Loss: 0.8419873118400574:   4%|▍         | 1036/25880 [15:17<4:41:50,  1.47it/s]
1|1037|Loss: 0.9325888752937317:   4%|▍         | 1036/25880 [15:17<4:41:50,  1.47it/s]
1|1037|Loss: 0.9325888752937317:   4%|▍         | 1037/25880 [15:18<4:49:40,  1.43it/s]
1|1038|Loss: 0.9252194166183472:   4%|▍         | 1037/25880 [15:18<4:49:40,  1.43it/s]
1|1038|Loss: 0.9252194166183472:   4%|▍         | 1038/25880 [15:18<4:45:24,  1.45it/s]
1|1039|Loss: 0.9618199467658997:   4%|▍         | 1038/25880 [15:19<4:45:24,  1.45it/s]
1|1039|Loss: 0.9618199467658997:   4%|▍         | 1039/25880 [15:19<4:53:57,  1.41it/s]
1|1040|Loss: 0.9301050305366516:   4%|▍         | 1039/25880 [15:20<4:53:57,  1.41it/s]
1|1040|Loss: 0.9301050305366516:   4%|▍         | 1040/25880 [15:20<5:06:07,  1.35it/s]
1|1041|Loss: 0.833740770816803:   4%|▍         | 1040/25880 [15:20<5:06:07,  1.35it/s] 
1|1041|Loss: 0.833740770816803:   4%|▍         | 1041/25880 [15:21<5:13:22,  1.32it/s]
1|1042|Loss: 0.9230663776397705:   4%|▍         | 1041/25880 [15:21<5:13:22,  1.32it/s]
1|1042|Loss: 0.9230663776397705:   4%|▍         | 1042/25880 [15:21<4:51:06,  1.42it/s]
1|1043|Loss: 0.9409689903259277:   4%|▍         | 1042/25880 [15:22<4:51:06,  1.42it/s]
1|1043|Loss: 0.9409689903259277:   4%|▍         | 1043/25880 [15:22<4:48:51,  1.43it/s]
1|1044|Loss: 0.7673306465148926:   4%|▍         | 1043/25880 [15:22<4:48:51,  1.43it/s]
1|1044|Loss: 0.7673306465148926:   4%|▍         | 1044/25880 [15:23<5:00:20,  1.38it/s]
1|1045|Loss: 0.9695330262184143:   4%|▍         | 1044/25880 [15:23<5:00:20,  1.38it/s]
1|1045|Loss: 0.9695330262184143:   4%|▍         | 1045/25880 [15:23<4:48:51,  1.43it/s]
1|1046|Loss: 0.8934109807014465:   4%|▍         | 1045/25880 [15:24<4:48:51,  1.43it/s]
1|1046|Loss: 0.8934109807014465:   4%|▍         | 1046/25880 [15:24<4:36:45,  1.50it/s]
1|1047|Loss: 0.8150332570075989:   4%|▍         | 1046/25880 [15:24<4:36:45,  1.50it/s]
1|1047|Loss: 0.8150332570075989:   4%|▍         | 1047/25880 [15:25<4:38:58,  1.48it/s]
1|1048|Loss: 0.812366247177124:   4%|▍         | 1047/25880 [15:25<4:38:58,  1.48it/s] 
1|1048|Loss: 0.812366247177124:   4%|▍         | 1048/25880 [15:26<4:50:23,  1.43it/s]
1|1049|Loss: 0.8273158669471741:   4%|▍         | 1048/25880 [15:26<4:50:23,  1.43it/s]
1|1049|Loss: 0.8273158669471741:   4%|▍         | 1049/25880 [15:26<4:58:26,  1.39it/s]
1|1050|Loss: 0.8388773202896118:   4%|▍         | 1049/25880 [15:27<4:58:26,  1.39it/s]
1|1050|Loss: 0.8388773202896118:   4%|▍         | 1050/25880 [15:27<4:49:48,  1.43it/s]
1|1051|Loss: 0.8887283205986023:   4%|▍         | 1050/25880 [15:27<4:49:48,  1.43it/s]
1|1051|Loss: 0.8887283205986023:   4%|▍         | 1051/25880 [15:28<4:41:36,  1.47it/s]
1|1052|Loss: 0.9414829015731812:   4%|▍         | 1051/25880 [15:28<4:41:36,  1.47it/s]
1|1052|Loss: 0.9414829015731812:   4%|▍         | 1052/25880 [15:28<4:44:49,  1.45it/s]
1|1053|Loss: 0.9286534190177917:   4%|▍         | 1052/25880 [15:29<4:44:49,  1.45it/s]
1|1053|Loss: 0.9286534190177917:   4%|▍         | 1053/25880 [15:29<4:58:58,  1.38it/s]
1|1054|Loss: 0.9838211536407471:   4%|▍         | 1053/25880 [15:30<4:58:58,  1.38it/s]
1|1054|Loss: 0.9838211536407471:   4%|▍         | 1054/25880 [15:30<5:09:55,  1.34it/s]
1|1055|Loss: 0.9770718812942505:   4%|▍         | 1054/25880 [15:30<5:09:55,  1.34it/s]
1|1055|Loss: 0.9770718812942505:   4%|▍         | 1055/25880 [15:31<5:09:51,  1.34it/s]
1|1056|Loss: 0.9867784976959229:   4%|▍         | 1055/25880 [15:31<5:09:51,  1.34it/s]
1|1056|Loss: 0.9867784976959229:   4%|▍         | 1056/25880 [15:31<5:07:49,  1.34it/s]
1|1057|Loss: 0.8839704990386963:   4%|▍         | 1056/25880 [15:32<5:07:49,  1.34it/s]
1|1057|Loss: 0.8839704990386963:   4%|▍         | 1057/25880 [15:32<5:06:33,  1.35it/s]
1|1058|Loss: 0.9907457232475281:   4%|▍         | 1057/25880 [15:33<5:06:33,  1.35it/s]
1|1058|Loss: 0.9907457232475281:   4%|▍         | 1058/25880 [15:33<5:07:10,  1.35it/s]
1|1059|Loss: 0.8917219042778015:   4%|▍         | 1058/25880 [15:33<5:07:10,  1.35it/s]
1|1059|Loss: 0.8917219042778015:   4%|▍         | 1059/25880 [15:33<4:46:50,  1.44it/s]
1|1060|Loss: 1.0085591077804565:   4%|▍         | 1059/25880 [15:34<4:46:50,  1.44it/s]
1|1060|Loss: 1.0085591077804565:   4%|▍         | 1060/25880 [15:34<4:53:58,  1.41it/s]
1|1061|Loss: 0.9787033796310425:   4%|▍         | 1060/25880 [15:35<4:53:58,  1.41it/s]
1|1061|Loss: 0.9787033796310425:   4%|▍         | 1061/25880 [15:35<4:46:35,  1.44it/s]
1|1062|Loss: 0.8751806020736694:   4%|▍         | 1061/25880 [15:35<4:46:35,  1.44it/s]
1|1062|Loss: 0.8751806020736694:   4%|▍         | 1062/25880 [15:36<5:00:56,  1.37it/s]
1|1063|Loss: 0.8352415561676025:   4%|▍         | 1062/25880 [15:36<5:00:56,  1.37it/s]
1|1063|Loss: 0.8352415561676025:   4%|▍         | 1063/25880 [15:37<5:16:45,  1.31it/s]
1|1064|Loss: 0.9456930756568909:   4%|▍         | 1063/25880 [15:37<5:16:45,  1.31it/s]
1|1064|Loss: 0.9456930756568909:   4%|▍         | 1064/25880 [15:37<5:16:39,  1.31it/s]
1|1065|Loss: 0.8378985524177551:   4%|▍         | 1064/25880 [15:38<5:16:39,  1.31it/s]
1|1065|Loss: 0.8378985524177551:   4%|▍         | 1065/25880 [15:38<5:22:45,  1.28it/s]
1|1066|Loss: 0.7742872834205627:   4%|▍         | 1065/25880 [15:39<5:22:45,  1.28it/s]
1|1066|Loss: 0.7742872834205627:   4%|▍         | 1066/25880 [15:39<5:18:48,  1.30it/s]
1|1067|Loss: 0.933796763420105:   4%|▍         | 1066/25880 [15:39<5:18:48,  1.30it/s] 
1|1067|Loss: 0.933796763420105:   4%|▍         | 1067/25880 [15:40<5:25:50,  1.27it/s]
1|1068|Loss: 0.9216170907020569:   4%|▍         | 1067/25880 [15:40<5:25:50,  1.27it/s]
1|1068|Loss: 0.9216170907020569:   4%|▍         | 1068/25880 [15:41<5:29:59,  1.25it/s]
1|1069|Loss: 0.8962861895561218:   4%|▍         | 1068/25880 [15:41<5:29:59,  1.25it/s]
1|1069|Loss: 0.8962861895561218:   4%|▍         | 1069/25880 [15:41<5:33:18,  1.24it/s]
1|1070|Loss: 0.8742848038673401:   4%|▍         | 1069/25880 [15:42<5:33:18,  1.24it/s]
1|1070|Loss: 0.8742848038673401:   4%|▍         | 1070/25880 [15:42<5:32:37,  1.24it/s]
1|1071|Loss: 1.0164295434951782:   4%|▍         | 1070/25880 [15:43<5:32:37,  1.24it/s]
1|1071|Loss: 1.0164295434951782:   4%|▍         | 1071/25880 [15:43<5:11:12,  1.33it/s]
1|1072|Loss: 0.9557153582572937:   4%|▍         | 1071/25880 [15:43<5:11:12,  1.33it/s]
1|1072|Loss: 0.9557153582572937:   4%|▍         | 1072/25880 [15:43<5:01:15,  1.37it/s]
1|1073|Loss: 0.9706172347068787:   4%|▍         | 1072/25880 [15:44<5:01:15,  1.37it/s]
1|1073|Loss: 0.9706172347068787:   4%|▍         | 1073/25880 [15:44<5:11:24,  1.33it/s]
1|1074|Loss: 0.8505306243896484:   4%|▍         | 1073/25880 [15:45<5:11:24,  1.33it/s]
1|1074|Loss: 0.8505306243896484:   4%|▍         | 1074/25880 [15:45<4:53:46,  1.41it/s]
1|1075|Loss: 0.9561598300933838:   4%|▍         | 1074/25880 [15:45<4:53:46,  1.41it/s]
1|1075|Loss: 0.9561598300933838:   4%|▍         | 1075/25880 [15:45<4:40:08,  1.48it/s]
1|1076|Loss: 0.9387634992599487:   4%|▍         | 1075/25880 [15:46<4:40:08,  1.48it/s]
1|1076|Loss: 0.9387634992599487:   4%|▍         | 1076/25880 [15:46<5:02:10,  1.37it/s]
1|1077|Loss: 0.8985977172851562:   4%|▍         | 1076/25880 [15:47<5:02:10,  1.37it/s]
1|1077|Loss: 0.8985977172851562:   4%|▍         | 1077/25880 [15:47<5:06:15,  1.35it/s]
1|1078|Loss: 1.0096129179000854:   4%|▍         | 1077/25880 [15:47<5:06:15,  1.35it/s]
1|1078|Loss: 1.0096129179000854:   4%|▍         | 1078/25880 [15:48<4:53:27,  1.41it/s]
1|1079|Loss: 0.840141773223877:   4%|▍         | 1078/25880 [15:48<4:53:27,  1.41it/s] 
1|1079|Loss: 0.840141773223877:   4%|▍         | 1079/25880 [15:48<5:00:37,  1.37it/s]
1|1080|Loss: 0.8441965579986572:   4%|▍         | 1079/25880 [15:49<5:00:37,  1.37it/s]
1|1080|Loss: 0.8441965579986572:   4%|▍         | 1080/25880 [15:49<4:45:45,  1.45it/s]
1|1081|Loss: 0.8222780227661133:   4%|▍         | 1080/25880 [15:49<4:45:45,  1.45it/s]
1|1081|Loss: 0.8222780227661133:   4%|▍         | 1081/25880 [15:50<4:45:43,  1.45it/s]
1|1082|Loss: 0.9988042116165161:   4%|▍         | 1081/25880 [15:50<4:45:43,  1.45it/s]
1|1082|Loss: 0.9988042116165161:   4%|▍         | 1082/25880 [15:50<4:32:29,  1.52it/s]
1|1083|Loss: 0.9156968593597412:   4%|▍         | 1082/25880 [15:51<4:32:29,  1.52it/s]
1|1083|Loss: 0.9156968593597412:   4%|▍         | 1083/25880 [15:51<4:36:45,  1.49it/s]
1|1084|Loss: 0.9233149886131287:   4%|▍         | 1083/25880 [15:51<4:36:45,  1.49it/s]
1|1084|Loss: 0.9233149886131287:   4%|▍         | 1084/25880 [15:52<4:42:16,  1.46it/s]
1|1085|Loss: 0.868147075176239:   4%|▍         | 1084/25880 [15:52<4:42:16,  1.46it/s] 
1|1085|Loss: 0.868147075176239:   4%|▍         | 1085/25880 [15:52<4:35:36,  1.50it/s]
1|1086|Loss: 0.9545527100563049:   4%|▍         | 1085/25880 [15:53<4:35:36,  1.50it/s]
1|1086|Loss: 0.9545527100563049:   4%|▍         | 1086/25880 [15:53<4:25:51,  1.55it/s]
1|1087|Loss: 0.895470142364502:   4%|▍         | 1086/25880 [15:53<4:25:51,  1.55it/s] 
1|1087|Loss: 0.895470142364502:   4%|▍         | 1087/25880 [15:54<4:18:01,  1.60it/s]
1|1088|Loss: 0.9916670322418213:   4%|▍         | 1087/25880 [15:54<4:18:01,  1.60it/s]
1|1088|Loss: 0.9916670322418213:   4%|▍         | 1088/25880 [15:54<4:28:10,  1.54it/s]
1|1089|Loss: 0.9900830984115601:   4%|▍         | 1088/25880 [15:55<4:28:10,  1.54it/s]
1|1089|Loss: 0.9900830984115601:   4%|▍         | 1089/25880 [15:55<4:40:34,  1.47it/s]
1|1090|Loss: 0.7893074154853821:   4%|▍         | 1089/25880 [15:55<4:40:34,  1.47it/s]
1|1090|Loss: 0.7893074154853821:   4%|▍         | 1090/25880 [15:56<4:47:30,  1.44it/s]
1|1091|Loss: 0.9351413249969482:   4%|▍         | 1090/25880 [15:56<4:47:30,  1.44it/s]
1|1091|Loss: 0.9351413249969482:   4%|▍         | 1091/25880 [15:57<4:52:54,  1.41it/s]
1|1092|Loss: 0.9883922338485718:   4%|▍         | 1091/25880 [15:57<4:52:54,  1.41it/s]
1|1092|Loss: 0.9883922338485718:   4%|▍         | 1092/25880 [15:57<4:38:50,  1.48it/s]
1|1093|Loss: 1.0377700328826904:   4%|▍         | 1092/25880 [15:57<4:38:50,  1.48it/s]
1|1093|Loss: 1.0377700328826904:   4%|▍         | 1093/25880 [15:58<4:30:34,  1.53it/s]
1|1094|Loss: 0.940644383430481:   4%|▍         | 1093/25880 [15:58<4:30:34,  1.53it/s] 
1|1094|Loss: 0.940644383430481:   4%|▍         | 1094/25880 [15:58<4:35:05,  1.50it/s]
1|1095|Loss: 1.0214346647262573:   4%|▍         | 1094/25880 [15:59<4:35:05,  1.50it/s]
1|1095|Loss: 1.0214346647262573:   4%|▍         | 1095/25880 [15:59<4:39:07,  1.48it/s]
1|1096|Loss: 0.980574905872345:   4%|▍         | 1095/25880 [15:59<4:39:07,  1.48it/s] 
1|1096|Loss: 0.980574905872345:   4%|▍         | 1096/25880 [16:00<4:35:40,  1.50it/s]
1|1097|Loss: 0.8683973550796509:   4%|▍         | 1096/25880 [16:00<4:35:40,  1.50it/s]
1|1097|Loss: 0.8683973550796509:   4%|▍         | 1097/25880 [16:00<4:41:07,  1.47it/s]
1|1098|Loss: 0.9020904302597046:   4%|▍         | 1097/25880 [16:01<4:41:07,  1.47it/s]
1|1098|Loss: 0.9020904302597046:   4%|▍         | 1098/25880 [16:01<4:48:59,  1.43it/s]
1|1099|Loss: 0.8444005846977234:   4%|▍         | 1098/25880 [16:02<4:48:59,  1.43it/s]
1|1099|Loss: 0.8444005846977234:   4%|▍         | 1099/25880 [16:02<4:55:34,  1.40it/s]
1|1100|Loss: 1.0283750295639038:   4%|▍         | 1099/25880 [16:02<4:55:34,  1.40it/s]
1|1100|Loss: 1.0283750295639038:   4%|▍         | 1100/25880 [16:02<4:31:02,  1.52it/s]
1|1101|Loss: 0.8640511631965637:   4%|▍         | 1100/25880 [16:03<4:31:02,  1.52it/s]
1|1101|Loss: 0.8640511631965637:   4%|▍         | 1101/25880 [16:03<4:39:52,  1.48it/s]
1|1102|Loss: 0.8721246123313904:   4%|▍         | 1101/25880 [16:04<4:39:52,  1.48it/s]
1|1102|Loss: 0.8721246123313904:   4%|▍         | 1102/25880 [16:04<4:28:37,  1.54it/s]
1|1103|Loss: 0.9882102012634277:   4%|▍         | 1102/25880 [16:04<4:28:37,  1.54it/s]
1|1103|Loss: 0.9882102012634277:   4%|▍         | 1103/25880 [16:04<4:30:24,  1.53it/s]
1|1104|Loss: 0.955705463886261:   4%|▍         | 1103/25880 [16:05<4:30:24,  1.53it/s] 
1|1104|Loss: 0.955705463886261:   4%|▍         | 1104/25880 [16:05<4:36:11,  1.50it/s]
1|1105|Loss: 0.959670901298523:   4%|▍         | 1104/25880 [16:06<4:36:11,  1.50it/s]
1|1105|Loss: 0.959670901298523:   4%|▍         | 1105/25880 [16:06<4:33:13,  1.51it/s]
1|1106|Loss: 0.9934606552124023:   4%|▍         | 1105/25880 [16:06<4:33:13,  1.51it/s]
1|1106|Loss: 0.9934606552124023:   4%|▍         | 1106/25880 [16:07<4:52:00,  1.41it/s]
1|1107|Loss: 0.8080253005027771:   4%|▍         | 1106/25880 [16:07<4:52:00,  1.41it/s]
1|1107|Loss: 0.8080253005027771:   4%|▍         | 1107/25880 [16:08<5:17:03,  1.30it/s]
1|1108|Loss: 0.8001697063446045:   4%|▍         | 1107/25880 [16:08<5:17:03,  1.30it/s]
1|1108|Loss: 0.8001697063446045:   4%|▍         | 1108/25880 [16:08<4:43:14,  1.46it/s]
1|1109|Loss: 0.8338809013366699:   4%|▍         | 1108/25880 [16:08<4:43:14,  1.46it/s]
1|1109|Loss: 0.8338809013366699:   4%|▍         | 1109/25880 [16:09<4:31:57,  1.52it/s]
1|1110|Loss: 0.9556728601455688:   4%|▍         | 1109/25880 [16:09<4:31:57,  1.52it/s]
1|1110|Loss: 0.9556728601455688:   4%|▍         | 1110/25880 [16:09<4:29:47,  1.53it/s]
1|1111|Loss: 0.9519923329353333:   4%|▍         | 1110/25880 [16:10<4:29:47,  1.53it/s]
1|1111|Loss: 0.9519923329353333:   4%|▍         | 1111/25880 [16:10<4:34:24,  1.50it/s]
1|1112|Loss: 0.9565202593803406:   4%|▍         | 1111/25880 [16:10<4:34:24,  1.50it/s]
1|1112|Loss: 0.9565202593803406:   4%|▍         | 1112/25880 [16:11<4:30:28,  1.53it/s]
1|1113|Loss: 1.0241798162460327:   4%|▍         | 1112/25880 [16:11<4:30:28,  1.53it/s]
1|1113|Loss: 1.0241798162460327:   4%|▍         | 1113/25880 [16:11<4:37:29,  1.49it/s]
1|1114|Loss: 0.9198802709579468:   4%|▍         | 1113/25880 [16:12<4:37:29,  1.49it/s]
1|1114|Loss: 0.9198802709579468:   4%|▍         | 1114/25880 [16:12<4:33:44,  1.51it/s]
1|1115|Loss: 0.897624135017395:   4%|▍         | 1114/25880 [16:12<4:33:44,  1.51it/s] 
1|1115|Loss: 0.897624135017395:   4%|▍         | 1115/25880 [16:13<4:36:17,  1.49it/s]
1|1116|Loss: 1.025890827178955:   4%|▍         | 1115/25880 [16:13<4:36:17,  1.49it/s]
1|1116|Loss: 1.025890827178955:   4%|▍         | 1116/25880 [16:13<4:34:45,  1.50it/s]
1|1117|Loss: 0.9423998594284058:   4%|▍         | 1116/25880 [16:14<4:34:45,  1.50it/s]
1|1117|Loss: 0.9423998594284058:   4%|▍         | 1117/25880 [16:14<4:38:15,  1.48it/s]
1|1118|Loss: 0.8176281452178955:   4%|▍         | 1117/25880 [16:14<4:38:15,  1.48it/s]
1|1118|Loss: 0.8176281452178955:   4%|▍         | 1118/25880 [16:15<4:46:00,  1.44it/s]
1|1119|Loss: 0.9448502659797668:   4%|▍         | 1118/25880 [16:15<4:46:00,  1.44it/s]
1|1119|Loss: 0.9448502659797668:   4%|▍         | 1119/25880 [16:15<4:43:08,  1.46it/s]
1|1120|Loss: 0.9890082478523254:   4%|▍         | 1119/25880 [16:16<4:43:08,  1.46it/s]
1|1120|Loss: 0.9890082478523254:   4%|▍         | 1120/25880 [16:16<4:37:03,  1.49it/s]
1|1121|Loss: 0.9999829530715942:   4%|▍         | 1120/25880 [16:16<4:37:03,  1.49it/s]
1|1121|Loss: 0.9999829530715942:   4%|▍         | 1121/25880 [16:17<4:32:52,  1.51it/s]
1|1122|Loss: 0.8142818808555603:   4%|▍         | 1121/25880 [16:17<4:32:52,  1.51it/s]
1|1122|Loss: 0.8142818808555603:   4%|▍         | 1122/25880 [16:17<4:27:35,  1.54it/s]
1|1123|Loss: 0.8211474418640137:   4%|▍         | 1122/25880 [16:18<4:27:35,  1.54it/s]
1|1123|Loss: 0.8211474418640137:   4%|▍         | 1123/25880 [16:18<4:57:44,  1.39it/s]
1|1124|Loss: 1.0607112646102905:   4%|▍         | 1123/25880 [16:19<4:57:44,  1.39it/s]
1|1124|Loss: 1.0607112646102905:   4%|▍         | 1124/25880 [16:19<4:54:02,  1.40it/s]
1|1125|Loss: 0.9106721878051758:   4%|▍         | 1124/25880 [16:19<4:54:02,  1.40it/s]
1|1125|Loss: 0.9106721878051758:   4%|▍         | 1125/25880 [16:20<5:10:24,  1.33it/s]
1|1126|Loss: 0.9080246090888977:   4%|▍         | 1125/25880 [16:20<5:10:24,  1.33it/s]
1|1126|Loss: 0.9080246090888977:   4%|▍         | 1126/25880 [16:20<4:51:42,  1.41it/s]
1|1127|Loss: 0.8260325789451599:   4%|▍         | 1126/25880 [16:21<4:51:42,  1.41it/s]
1|1127|Loss: 0.8260325789451599:   4%|▍         | 1127/25880 [16:21<4:52:04,  1.41it/s]
1|1128|Loss: 0.7352240681648254:   4%|▍         | 1127/25880 [16:21<4:52:04,  1.41it/s]
1|1128|Loss: 0.7352240681648254:   4%|▍         | 1128/25880 [16:22<4:31:58,  1.52it/s]
1|1129|Loss: 0.971980631351471:   4%|▍         | 1128/25880 [16:22<4:31:58,  1.52it/s] 
1|1129|Loss: 0.971980631351471:   4%|▍         | 1129/25880 [16:22<4:23:50,  1.56it/s]
1|1130|Loss: 0.91377854347229:   4%|▍         | 1129/25880 [16:22<4:23:50,  1.56it/s] 
1|1130|Loss: 0.91377854347229:   4%|▍         | 1130/25880 [16:23<4:23:30,  1.57it/s]
1|1131|Loss: 0.8722203373908997:   4%|▍         | 1130/25880 [16:23<4:23:30,  1.57it/s]
1|1131|Loss: 0.8722203373908997:   4%|▍         | 1131/25880 [16:23<4:21:07,  1.58it/s]
1|1132|Loss: 0.9745607376098633:   4%|▍         | 1131/25880 [16:24<4:21:07,  1.58it/s]
1|1132|Loss: 0.9745607376098633:   4%|▍         | 1132/25880 [16:24<4:27:33,  1.54it/s]
1|1133|Loss: 1.080041527748108:   4%|▍         | 1132/25880 [16:24<4:27:33,  1.54it/s] 
1|1133|Loss: 1.080041527748108:   4%|▍         | 1133/25880 [16:25<4:33:17,  1.51it/s]
1|1134|Loss: 0.9123186469078064:   4%|▍         | 1133/25880 [16:25<4:33:17,  1.51it/s]
1|1134|Loss: 0.9123186469078064:   4%|▍         | 1134/25880 [16:25<4:28:45,  1.53it/s]
1|1135|Loss: 0.8952772617340088:   4%|▍         | 1134/25880 [16:26<4:28:45,  1.53it/s]
1|1135|Loss: 0.8952772617340088:   4%|▍         | 1135/25880 [16:26<4:20:33,  1.58it/s]
1|1136|Loss: 0.8835107684135437:   4%|▍         | 1135/25880 [16:26<4:20:33,  1.58it/s]
1|1136|Loss: 0.8835107684135437:   4%|▍         | 1136/25880 [16:27<4:11:48,  1.64it/s]
1|1137|Loss: 0.8307209014892578:   4%|▍         | 1136/25880 [16:27<4:11:48,  1.64it/s]
1|1137|Loss: 0.8307209014892578:   4%|▍         | 1137/25880 [16:27<4:28:14,  1.54it/s]
1|1138|Loss: 0.9974895715713501:   4%|▍         | 1137/25880 [16:28<4:28:14,  1.54it/s]
1|1138|Loss: 0.9974895715713501:   4%|▍         | 1138/25880 [16:28<5:35:32,  1.23it/s]
1|1139|Loss: 0.938812255859375:   4%|▍         | 1138/25880 [16:29<5:35:32,  1.23it/s] 
1|1139|Loss: 0.938812255859375:   4%|▍         | 1139/25880 [16:29<5:37:56,  1.22it/s]
1|1140|Loss: 0.9470289945602417:   4%|▍         | 1139/25880 [16:30<5:37:56,  1.22it/s]
1|1140|Loss: 0.9470289945602417:   4%|▍         | 1140/25880 [16:30<5:32:34,  1.24it/s]
1|1141|Loss: 0.9235852956771851:   4%|▍         | 1140/25880 [16:31<5:32:34,  1.24it/s]
1|1141|Loss: 0.9235852956771851:   4%|▍         | 1141/25880 [16:31<5:37:17,  1.22it/s]
1|1142|Loss: 0.9313095211982727:   4%|▍         | 1141/25880 [16:31<5:37:17,  1.22it/s]
1|1142|Loss: 0.9313095211982727:   4%|▍         | 1142/25880 [16:32<5:21:42,  1.28it/s]
1|1143|Loss: 0.9052477478981018:   4%|▍         | 1142/25880 [16:32<5:21:42,  1.28it/s]
1|1143|Loss: 0.9052477478981018:   4%|▍         | 1143/25880 [16:32<5:25:17,  1.27it/s]
1|1144|Loss: 0.9185270667076111:   4%|▍         | 1143/25880 [16:33<5:25:17,  1.27it/s]
1|1144|Loss: 0.9185270667076111:   4%|▍         | 1144/25880 [16:33<5:28:42,  1.25it/s]
1|1145|Loss: 0.7697774767875671:   4%|▍         | 1144/25880 [16:34<5:28:42,  1.25it/s]
1|1145|Loss: 0.7697774767875671:   4%|▍         | 1145/25880 [16:34<5:22:57,  1.28it/s]
1|1146|Loss: 0.9680343270301819:   4%|▍         | 1145/25880 [16:34<5:22:57,  1.28it/s]
1|1146|Loss: 0.9680343270301819:   4%|▍         | 1146/25880 [16:35<5:28:31,  1.25it/s]
1|1147|Loss: 0.7037281394004822:   4%|▍         | 1146/25880 [16:35<5:28:31,  1.25it/s]
1|1147|Loss: 0.7037281394004822:   4%|▍         | 1147/25880 [16:36<5:51:15,  1.17it/s]
1|1148|Loss: 0.7334120273590088:   4%|▍         | 1147/25880 [16:36<5:51:15,  1.17it/s]
1|1148|Loss: 0.7334120273590088:   4%|▍         | 1148/25880 [16:37<5:43:58,  1.20it/s]
1|1149|Loss: 0.9989980459213257:   4%|▍         | 1148/25880 [16:37<5:43:58,  1.20it/s]
1|1149|Loss: 0.9989980459213257:   4%|▍         | 1149/25880 [16:37<5:31:16,  1.24it/s]
1|1150|Loss: 0.8267793655395508:   4%|▍         | 1149/25880 [16:38<5:31:16,  1.24it/s]
1|1150|Loss: 0.8267793655395508:   4%|▍         | 1150/25880 [16:38<5:22:16,  1.28it/s]
1|1151|Loss: 0.8864255547523499:   4%|▍         | 1150/25880 [16:39<5:22:16,  1.28it/s]
1|1151|Loss: 0.8864255547523499:   4%|▍         | 1151/25880 [16:39<5:23:34,  1.27it/s]
1|1152|Loss: 0.791122317314148:   4%|▍         | 1151/25880 [16:39<5:23:34,  1.27it/s] 
1|1152|Loss: 0.791122317314148:   4%|▍         | 1152/25880 [16:40<5:49:42,  1.18it/s]
1|1153|Loss: 1.0209379196166992:   4%|▍         | 1152/25880 [16:40<5:49:42,  1.18it/s]
1|1153|Loss: 1.0209379196166992:   4%|▍         | 1153/25880 [16:41<5:29:14,  1.25it/s]
1|1154|Loss: 1.0546571016311646:   4%|▍         | 1153/25880 [16:41<5:29:14,  1.25it/s]
1|1154|Loss: 1.0546571016311646:   4%|▍         | 1154/25880 [16:41<5:26:10,  1.26it/s]
1|1155|Loss: 0.9463356733322144:   4%|▍         | 1154/25880 [16:42<5:26:10,  1.26it/s]
1|1155|Loss: 0.9463356733322144:   4%|▍         | 1155/25880 [16:42<5:39:39,  1.21it/s]
1|1156|Loss: 1.1155059337615967:   4%|▍         | 1155/25880 [16:43<5:39:39,  1.21it/s]
1|1156|Loss: 1.1155059337615967:   4%|▍         | 1156/25880 [16:43<5:33:25,  1.24it/s]
1|1157|Loss: 0.7991117238998413:   4%|▍         | 1156/25880 [16:43<5:33:25,  1.24it/s]
1|1157|Loss: 0.7991117238998413:   4%|▍         | 1157/25880 [16:44<5:30:39,  1.25it/s]
1|1158|Loss: 0.8997358083724976:   4%|▍         | 1157/25880 [16:44<5:30:39,  1.25it/s]
1|1158|Loss: 0.8997358083724976:   4%|▍         | 1158/25880 [16:45<5:21:25,  1.28it/s]
1|1159|Loss: 0.9290248155593872:   4%|▍         | 1158/25880 [16:45<5:21:25,  1.28it/s]
1|1159|Loss: 0.9290248155593872:   4%|▍         | 1159/25880 [16:45<5:22:18,  1.28it/s]
1|1160|Loss: 0.8839132785797119:   4%|▍         | 1159/25880 [16:46<5:22:18,  1.28it/s]
1|1160|Loss: 0.8839132785797119:   4%|▍         | 1160/25880 [16:46<5:23:31,  1.27it/s]
1|1161|Loss: 0.7972683310508728:   4%|▍         | 1160/25880 [16:47<5:23:31,  1.27it/s]
1|1161|Loss: 0.7972683310508728:   4%|▍         | 1161/25880 [16:47<5:32:14,  1.24it/s]
1|1162|Loss: 0.9354384541511536:   4%|▍         | 1161/25880 [16:47<5:32:14,  1.24it/s]
1|1162|Loss: 0.9354384541511536:   4%|▍         | 1162/25880 [16:48<5:18:25,  1.29it/s]
1|1163|Loss: 0.93637615442276:   4%|▍         | 1162/25880 [16:48<5:18:25,  1.29it/s]  
1|1163|Loss: 0.93637615442276:   4%|▍         | 1163/25880 [16:48<5:24:26,  1.27it/s]
1|1164|Loss: 0.8230203986167908:   4%|▍         | 1163/25880 [16:49<5:24:26,  1.27it/s]
1|1164|Loss: 0.8230203986167908:   4%|▍         | 1164/25880 [16:49<5:19:01,  1.29it/s]
1|1165|Loss: 0.9690197706222534:   4%|▍         | 1164/25880 [16:50<5:19:01,  1.29it/s]
1|1165|Loss: 0.9690197706222534:   5%|▍         | 1165/25880 [16:50<5:26:41,  1.26it/s]
1|1166|Loss: 1.011085867881775:   5%|▍         | 1165/25880 [16:50<5:26:41,  1.26it/s] 
1|1166|Loss: 1.011085867881775:   5%|▍         | 1166/25880 [16:51<5:14:11,  1.31it/s]
1|1167|Loss: 0.7728431224822998:   5%|▍         | 1166/25880 [16:51<5:14:11,  1.31it/s]
1|1167|Loss: 0.7728431224822998:   5%|▍         | 1167/25880 [16:52<5:19:52,  1.29it/s]
1|1168|Loss: 0.6189852952957153:   5%|▍         | 1167/25880 [16:52<5:19:52,  1.29it/s]
1|1168|Loss: 0.6189852952957153:   5%|▍         | 1168/25880 [16:52<5:09:14,  1.33it/s]
1|1169|Loss: 0.8270386457443237:   5%|▍         | 1168/25880 [16:53<5:09:14,  1.33it/s]
1|1169|Loss: 0.8270386457443237:   5%|▍         | 1169/25880 [16:53<5:04:46,  1.35it/s]
1|1170|Loss: 0.9169656038284302:   5%|▍         | 1169/25880 [16:53<5:04:46,  1.35it/s]
1|1170|Loss: 0.9169656038284302:   5%|▍         | 1170/25880 [16:54<4:54:23,  1.40it/s]
1|1171|Loss: 0.9622018933296204:   5%|▍         | 1170/25880 [16:54<4:54:23,  1.40it/s]
1|1171|Loss: 0.9622018933296204:   5%|▍         | 1171/25880 [16:54<4:55:30,  1.39it/s]
1|1172|Loss: 1.0854673385620117:   5%|▍         | 1171/25880 [16:55<4:55:30,  1.39it/s]
1|1172|Loss: 1.0854673385620117:   5%|▍         | 1172/25880 [16:55<4:55:26,  1.39it/s]
1|1173|Loss: 1.0864160060882568:   5%|▍         | 1172/25880 [16:55<4:55:26,  1.39it/s]
1|1173|Loss: 1.0864160060882568:   5%|▍         | 1173/25880 [16:56<4:55:27,  1.39it/s]
1|1174|Loss: 1.0905277729034424:   5%|▍         | 1173/25880 [16:56<4:55:27,  1.39it/s]
1|1174|Loss: 1.0905277729034424:   5%|▍         | 1174/25880 [16:57<5:11:54,  1.32it/s]
1|1175|Loss: 0.9342898726463318:   5%|▍         | 1174/25880 [16:57<5:11:54,  1.32it/s]
1|1175|Loss: 0.9342898726463318:   5%|▍         | 1175/25880 [16:57<5:14:17,  1.31it/s]
1|1176|Loss: 0.9136332273483276:   5%|▍         | 1175/25880 [16:58<5:14:17,  1.31it/s]
1|1176|Loss: 0.9136332273483276:   5%|▍         | 1176/25880 [16:58<5:11:28,  1.32it/s]
1|1177|Loss: 0.8689286112785339:   5%|▍         | 1176/25880 [16:59<5:11:28,  1.32it/s]
1|1177|Loss: 0.8689286112785339:   5%|▍         | 1177/25880 [16:59<5:08:26,  1.33it/s]
1|1178|Loss: 0.9265019297599792:   5%|▍         | 1177/25880 [16:59<5:08:26,  1.33it/s]
1|1178|Loss: 0.9265019297599792:   5%|▍         | 1178/25880 [16:59<4:43:37,  1.45it/s]
1|1179|Loss: 0.9609776735305786:   5%|▍         | 1178/25880 [17:00<4:43:37,  1.45it/s]
1|1179|Loss: 0.9609776735305786:   5%|▍         | 1179/25880 [17:00<4:31:18,  1.52it/s]
1|1180|Loss: 0.8746913075447083:   5%|▍         | 1179/25880 [17:00<4:31:18,  1.52it/s]
1|1180|Loss: 0.8746913075447083:   5%|▍         | 1180/25880 [17:01<4:50:05,  1.42it/s]
1|1181|Loss: 0.8058377504348755:   5%|▍         | 1180/25880 [17:01<4:50:05,  1.42it/s]
1|1181|Loss: 0.8058377504348755:   5%|▍         | 1181/25880 [17:01<4:46:09,  1.44it/s]
1|1182|Loss: 1.0834648609161377:   5%|▍         | 1181/25880 [17:02<4:46:09,  1.44it/s]
1|1182|Loss: 1.0834648609161377:   5%|▍         | 1182/25880 [17:02<4:47:50,  1.43it/s]
1|1183|Loss: 0.9107024073600769:   5%|▍         | 1182/25880 [17:03<4:47:50,  1.43it/s]
1|1183|Loss: 0.9107024073600769:   5%|▍         | 1183/25880 [17:03<4:51:46,  1.41it/s]
1|1184|Loss: 0.8769358396530151:   5%|▍         | 1183/25880 [17:03<4:51:46,  1.41it/s]
1|1184|Loss: 0.8769358396530151:   5%|▍         | 1184/25880 [17:04<4:44:57,  1.44it/s]
1|1185|Loss: 0.9975705742835999:   5%|▍         | 1184/25880 [17:04<4:44:57,  1.44it/s]
1|1185|Loss: 0.9975705742835999:   5%|▍         | 1185/25880 [17:04<4:57:41,  1.38it/s]
1|1186|Loss: 0.874988317489624:   5%|▍         | 1185/25880 [17:05<4:57:41,  1.38it/s] 
1|1186|Loss: 0.874988317489624:   5%|▍         | 1186/25880 [17:05<4:51:48,  1.41it/s]
1|1187|Loss: 1.0134776830673218:   5%|▍         | 1186/25880 [17:05<4:51:48,  1.41it/s]
1|1187|Loss: 1.0134776830673218:   5%|▍         | 1187/25880 [17:06<4:42:38,  1.46it/s]
1|1188|Loss: 0.8447571396827698:   5%|▍         | 1187/25880 [17:06<4:42:38,  1.46it/s]
1|1188|Loss: 0.8447571396827698:   5%|▍         | 1188/25880 [17:06<4:45:25,  1.44it/s]
1|1189|Loss: 0.8831176161766052:   5%|▍         | 1188/25880 [17:07<4:45:25,  1.44it/s]
1|1189|Loss: 0.8831176161766052:   5%|▍         | 1189/25880 [17:07<4:38:09,  1.48it/s]
1|1190|Loss: 0.8346627950668335:   5%|▍         | 1189/25880 [17:07<4:38:09,  1.48it/s]
1|1190|Loss: 0.8346627950668335:   5%|▍         | 1190/25880 [17:08<4:51:33,  1.41it/s]
1|1191|Loss: 0.8931208848953247:   5%|▍         | 1190/25880 [17:08<4:51:33,  1.41it/s]
1|1191|Loss: 0.8931208848953247:   5%|▍         | 1191/25880 [17:09<4:53:50,  1.40it/s]
1|1192|Loss: 0.773147463798523:   5%|▍         | 1191/25880 [17:09<4:53:50,  1.40it/s] 
1|1192|Loss: 0.773147463798523:   5%|▍         | 1192/25880 [17:09<5:04:25,  1.35it/s]
1|1193|Loss: 0.9370070695877075:   5%|▍         | 1192/25880 [17:10<5:04:25,  1.35it/s]
1|1193|Loss: 0.9370070695877075:   5%|▍         | 1193/25880 [17:10<5:10:37,  1.32it/s]
1|1194|Loss: 0.8847934007644653:   5%|▍         | 1193/25880 [17:10<5:10:37,  1.32it/s]
1|1194|Loss: 0.8847934007644653:   5%|▍         | 1194/25880 [17:11<4:33:42,  1.50it/s]
1|1195|Loss: 0.9127596616744995:   5%|▍         | 1194/25880 [17:11<4:33:42,  1.50it/s]
1|1195|Loss: 0.9127596616744995:   5%|▍         | 1195/25880 [17:11<4:45:01,  1.44it/s]
1|1196|Loss: 0.9420749545097351:   5%|▍         | 1195/25880 [17:12<4:45:01,  1.44it/s]
1|1196|Loss: 0.9420749545097351:   5%|▍         | 1196/25880 [17:12<4:53:06,  1.40it/s]
1|1197|Loss: 0.9174559712409973:   5%|▍         | 1196/25880 [17:12<4:53:06,  1.40it/s]
1|1197|Loss: 0.9174559712409973:   5%|▍         | 1197/25880 [17:13<4:53:00,  1.40it/s]
1|1198|Loss: 0.9523019194602966:   5%|▍         | 1197/25880 [17:13<4:53:00,  1.40it/s]
1|1198|Loss: 0.9523019194602966:   5%|▍         | 1198/25880 [17:14<4:54:43,  1.40it/s]
1|1199|Loss: 0.9131326675415039:   5%|▍         | 1198/25880 [17:14<4:54:43,  1.40it/s]
1|1199|Loss: 0.9131326675415039:   5%|▍         | 1199/25880 [17:14<4:45:17,  1.44it/s]
1|1200|Loss: 0.87003493309021:   5%|▍         | 1199/25880 [17:15<4:45:17,  1.44it/s]  
1|1200|Loss: 0.87003493309021:   5%|▍         | 1200/25880 [17:15<4:46:54,  1.43it/s]
1|1201|Loss: 0.876162588596344:   5%|▍         | 1200/25880 [17:15<4:46:54,  1.43it/s]
1|1201|Loss: 0.876162588596344:   5%|▍         | 1201/25880 [17:16<4:48:17,  1.43it/s]
1|1202|Loss: 0.9624610543251038:   5%|▍         | 1201/25880 [17:16<4:48:17,  1.43it/s]
1|1202|Loss: 0.9624610543251038:   5%|▍         | 1202/25880 [17:16<4:34:07,  1.50it/s]
1|1203|Loss: 0.8252156972885132:   5%|▍         | 1202/25880 [17:17<4:34:07,  1.50it/s]
1|1203|Loss: 0.8252156972885132:   5%|▍         | 1203/25880 [17:17<4:37:26,  1.48it/s]
1|1204|Loss: 0.9314789175987244:   5%|▍         | 1203/25880 [17:17<4:37:26,  1.48it/s]
1|1204|Loss: 0.9314789175987244:   5%|▍         | 1204/25880 [17:18<4:35:21,  1.49it/s]
1|1205|Loss: 0.7690649032592773:   5%|▍         | 1204/25880 [17:18<4:35:21,  1.49it/s]
1|1205|Loss: 0.7690649032592773:   5%|▍         | 1205/25880 [17:18<4:47:37,  1.43it/s]
1|1206|Loss: 0.9498505592346191:   5%|▍         | 1205/25880 [17:19<4:47:37,  1.43it/s]
1|1206|Loss: 0.9498505592346191:   5%|▍         | 1206/25880 [17:19<4:59:23,  1.37it/s]
1|1207|Loss: 0.9087847471237183:   5%|▍         | 1206/25880 [17:20<4:59:23,  1.37it/s]
1|1207|Loss: 0.9087847471237183:   5%|▍         | 1207/25880 [17:20<5:02:03,  1.36it/s]
1|1208|Loss: 0.8682031035423279:   5%|▍         | 1207/25880 [17:20<5:02:03,  1.36it/s]
1|1208|Loss: 0.8682031035423279:   5%|▍         | 1208/25880 [17:20<4:39:17,  1.47it/s]
1|1209|Loss: 0.899368405342102:   5%|▍         | 1208/25880 [17:21<4:39:17,  1.47it/s] 
1|1209|Loss: 0.899368405342102:   5%|▍         | 1209/25880 [17:21<4:36:42,  1.49it/s]
1|1210|Loss: 0.8171612024307251:   5%|▍         | 1209/25880 [17:21<4:36:42,  1.49it/s]
1|1210|Loss: 0.8171612024307251:   5%|▍         | 1210/25880 [17:22<4:39:44,  1.47it/s]
1|1211|Loss: 0.836590588092804:   5%|▍         | 1210/25880 [17:22<4:39:44,  1.47it/s] 
1|1211|Loss: 0.836590588092804:   5%|▍         | 1211/25880 [17:23<4:56:45,  1.39it/s]
1|1212|Loss: 0.9654548168182373:   5%|▍         | 1211/25880 [17:23<4:56:45,  1.39it/s]
1|1212|Loss: 0.9654548168182373:   5%|▍         | 1212/25880 [17:23<5:01:11,  1.36it/s]
1|1213|Loss: 0.891814112663269:   5%|▍         | 1212/25880 [17:24<5:01:11,  1.36it/s] 
1|1213|Loss: 0.891814112663269:   5%|▍         | 1213/25880 [17:24<4:51:08,  1.41it/s]
1|1214|Loss: 0.8574719429016113:   5%|▍         | 1213/25880 [17:24<4:51:08,  1.41it/s]
1|1214|Loss: 0.8574719429016113:   5%|▍         | 1214/25880 [17:25<4:42:21,  1.46it/s]
1|1215|Loss: 0.8302862644195557:   5%|▍         | 1214/25880 [17:25<4:42:21,  1.46it/s]
1|1215|Loss: 0.8302862644195557:   5%|▍         | 1215/25880 [17:25<4:45:24,  1.44it/s]
1|1216|Loss: 0.8826474547386169:   5%|▍         | 1215/25880 [17:26<4:45:24,  1.44it/s]
1|1216|Loss: 0.8826474547386169:   5%|▍         | 1216/25880 [17:26<4:59:23,  1.37it/s]
1|1217|Loss: 0.9599581956863403:   5%|▍         | 1216/25880 [17:27<4:59:23,  1.37it/s]
1|1217|Loss: 0.9599581956863403:   5%|▍         | 1217/25880 [17:27<5:03:25,  1.35it/s]
1|1218|Loss: 0.8581708669662476:   5%|▍         | 1217/25880 [17:27<5:03:25,  1.35it/s]
1|1218|Loss: 0.8581708669662476:   5%|▍         | 1218/25880 [17:28<5:13:06,  1.31it/s]
1|1219|Loss: 0.8591443300247192:   5%|▍         | 1218/25880 [17:28<5:13:06,  1.31it/s]
1|1219|Loss: 0.8591443300247192:   5%|▍         | 1219/25880 [17:28<5:03:22,  1.35it/s]
1|1220|Loss: 0.9183761477470398:   5%|▍         | 1219/25880 [17:29<5:03:22,  1.35it/s]
1|1220|Loss: 0.9183761477470398:   5%|▍         | 1220/25880 [17:29<4:57:03,  1.38it/s]
1|1221|Loss: 0.9371283650398254:   5%|▍         | 1220/25880 [17:29<4:57:03,  1.38it/s]
1|1221|Loss: 0.9371283650398254:   5%|▍         | 1221/25880 [17:30<4:53:00,  1.40it/s]
1|1222|Loss: 0.8645073175430298:   5%|▍         | 1221/25880 [17:30<4:53:00,  1.40it/s]
1|1222|Loss: 0.8645073175430298:   5%|▍         | 1222/25880 [17:31<4:54:31,  1.40it/s]
1|1223|Loss: 0.736415684223175:   5%|▍         | 1222/25880 [17:31<4:54:31,  1.40it/s] 
1|1223|Loss: 0.736415684223175:   5%|▍         | 1223/25880 [17:31<4:48:07,  1.43it/s]
1|1224|Loss: 0.845158576965332:   5%|▍         | 1223/25880 [17:32<4:48:07,  1.43it/s]
1|1224|Loss: 0.845158576965332:   5%|▍         | 1224/25880 [17:32<4:32:12,  1.51it/s]
1|1225|Loss: 0.9248802661895752:   5%|▍         | 1224/25880 [17:32<4:32:12,  1.51it/s]
1|1225|Loss: 0.9248802661895752:   5%|▍         | 1225/25880 [17:32<4:36:25,  1.49it/s]
1|1226|Loss: 0.9422130584716797:   5%|▍         | 1225/25880 [17:33<4:36:25,  1.49it/s]
1|1226|Loss: 0.9422130584716797:   5%|▍         | 1226/25880 [17:33<4:40:41,  1.46it/s]
1|1227|Loss: 0.9810699820518494:   5%|▍         | 1226/25880 [17:34<4:40:41,  1.46it/s]
1|1227|Loss: 0.9810699820518494:   5%|▍         | 1227/25880 [17:34<4:35:16,  1.49it/s]
1|1228|Loss: 0.8599498867988586:   5%|▍         | 1227/25880 [17:34<4:35:16,  1.49it/s]
1|1228|Loss: 0.8599498867988586:   5%|▍         | 1228/25880 [17:34<4:38:11,  1.48it/s]
1|1229|Loss: 0.8203154802322388:   5%|▍         | 1228/25880 [17:35<4:38:11,  1.48it/s]
1|1229|Loss: 0.8203154802322388:   5%|▍         | 1229/25880 [17:35<4:44:15,  1.45it/s]
1|1230|Loss: 0.873090922832489:   5%|▍         | 1229/25880 [17:36<4:44:15,  1.45it/s] 
1|1230|Loss: 0.873090922832489:   5%|▍         | 1230/25880 [17:36<4:35:08,  1.49it/s]
1|1231|Loss: 0.7901325225830078:   5%|▍         | 1230/25880 [17:36<4:35:08,  1.49it/s]
1|1231|Loss: 0.7901325225830078:   5%|▍         | 1231/25880 [17:37<5:02:51,  1.36it/s]
1|1232|Loss: 0.8176815509796143:   5%|▍         | 1231/25880 [17:37<5:02:51,  1.36it/s]
1|1232|Loss: 0.8176815509796143:   5%|▍         | 1232/25880 [17:37<4:44:45,  1.44it/s]
1|1233|Loss: 0.9069539308547974:   5%|▍         | 1232/25880 [17:38<4:44:45,  1.44it/s]
1|1233|Loss: 0.9069539308547974:   5%|▍         | 1233/25880 [17:38<4:52:12,  1.41it/s]
1|1234|Loss: 0.9295392036437988:   5%|▍         | 1233/25880 [17:38<4:52:12,  1.41it/s]
1|1234|Loss: 0.9295392036437988:   5%|▍         | 1234/25880 [17:39<4:46:07,  1.44it/s]
1|1235|Loss: 0.8478135466575623:   5%|▍         | 1234/25880 [17:39<4:46:07,  1.44it/s]
1|1235|Loss: 0.8478135466575623:   5%|▍         | 1235/25880 [17:39<4:45:03,  1.44it/s]
1|1236|Loss: 0.9392029047012329:   5%|▍         | 1235/25880 [17:40<4:45:03,  1.44it/s]
1|1236|Loss: 0.9392029047012329:   5%|▍         | 1236/25880 [17:40<4:48:31,  1.42it/s]
1|1237|Loss: 0.9255236983299255:   5%|▍         | 1236/25880 [17:41<4:48:31,  1.42it/s]
1|1237|Loss: 0.9255236983299255:   5%|▍         | 1237/25880 [17:41<4:48:30,  1.42it/s]
1|1238|Loss: 0.8089247941970825:   5%|▍         | 1237/25880 [17:41<4:48:30,  1.42it/s]
1|1238|Loss: 0.8089247941970825:   5%|▍         | 1238/25880 [17:42<4:58:12,  1.38it/s]
1|1239|Loss: 0.785037636756897:   5%|▍         | 1238/25880 [17:42<4:58:12,  1.38it/s] 
1|1239|Loss: 0.785037636756897:   5%|▍         | 1239/25880 [17:42<4:45:44,  1.44it/s]
1|1240|Loss: 0.7861958146095276:   5%|▍         | 1239/25880 [17:43<4:45:44,  1.44it/s]
1|1240|Loss: 0.7861958146095276:   5%|▍         | 1240/25880 [17:43<4:43:00,  1.45it/s]
1|1241|Loss: 0.9366739988327026:   5%|▍         | 1240/25880 [17:43<4:43:00,  1.45it/s]
1|1241|Loss: 0.9366739988327026:   5%|▍         | 1241/25880 [17:44<4:48:26,  1.42it/s]
1|1242|Loss: 0.8895365595817566:   5%|▍         | 1241/25880 [17:44<4:48:26,  1.42it/s]
1|1242|Loss: 0.8895365595817566:   5%|▍         | 1242/25880 [17:44<5:00:58,  1.36it/s]
1|1243|Loss: 0.9215933680534363:   5%|▍         | 1242/25880 [17:45<5:00:58,  1.36it/s]
1|1243|Loss: 0.9215933680534363:   5%|▍         | 1243/25880 [17:45<4:51:09,  1.41it/s]
1|1244|Loss: 0.847983717918396:   5%|▍         | 1243/25880 [17:45<4:51:09,  1.41it/s] 
1|1244|Loss: 0.847983717918396:   5%|▍         | 1244/25880 [17:46<4:52:27,  1.40it/s]
1|1245|Loss: 0.8398571610450745:   5%|▍         | 1244/25880 [17:46<4:52:27,  1.40it/s]
1|1245|Loss: 0.8398571610450745:   5%|▍         | 1245/25880 [17:46<4:44:13,  1.44it/s]
1|1246|Loss: 0.8658085465431213:   5%|▍         | 1245/25880 [17:47<4:44:13,  1.44it/s]
1|1246|Loss: 0.8658085465431213:   5%|▍         | 1246/25880 [17:47<4:46:10,  1.43it/s]
1|1247|Loss: 0.8711158037185669:   5%|▍         | 1246/25880 [17:48<4:46:10,  1.43it/s]
1|1247|Loss: 0.8711158037185669:   5%|▍         | 1247/25880 [17:48<4:41:46,  1.46it/s]
1|1248|Loss: 0.8899914026260376:   5%|▍         | 1247/25880 [17:48<4:41:46,  1.46it/s]
1|1248|Loss: 0.8899914026260376:   5%|▍         | 1248/25880 [17:48<4:34:01,  1.50it/s]
1|1249|Loss: 1.0241588354110718:   5%|▍         | 1248/25880 [17:49<4:34:01,  1.50it/s]
1|1249|Loss: 1.0241588354110718:   5%|▍         | 1249/25880 [17:49<4:51:23,  1.41it/s]
1|1250|Loss: 0.8998942375183105:   5%|▍         | 1249/25880 [17:50<4:51:23,  1.41it/s]
1|1250|Loss: 0.8998942375183105:   5%|▍         | 1250/25880 [17:50<5:25:04,  1.26it/s]
1|1251|Loss: 0.9336777329444885:   5%|▍         | 1250/25880 [17:51<5:25:04,  1.26it/s]
1|1251|Loss: 0.9336777329444885:   5%|▍         | 1251/25880 [17:51<5:25:49,  1.26it/s]
1|1252|Loss: 0.8714534640312195:   5%|▍         | 1251/25880 [17:51<5:25:49,  1.26it/s]
1|1252|Loss: 0.8714534640312195:   5%|▍         | 1252/25880 [17:52<5:09:09,  1.33it/s]
1|1253|Loss: 0.8107448816299438:   5%|▍         | 1252/25880 [17:52<5:09:09,  1.33it/s]
1|1253|Loss: 0.8107448816299438:   5%|▍         | 1253/25880 [17:52<4:55:44,  1.39it/s]
1|1254|Loss: 0.9323006272315979:   5%|▍         | 1253/25880 [17:53<4:55:44,  1.39it/s]
1|1254|Loss: 0.9323006272315979:   5%|▍         | 1254/25880 [17:53<5:00:37,  1.37it/s]
1|1255|Loss: 0.9543931484222412:   5%|▍         | 1254/25880 [17:54<5:00:37,  1.37it/s]
1|1255|Loss: 0.9543931484222412:   5%|▍         | 1255/25880 [17:54<4:53:30,  1.40it/s]
1|1256|Loss: 0.8767864108085632:   5%|▍         | 1255/25880 [17:54<4:53:30,  1.40it/s]
1|1256|Loss: 0.8767864108085632:   5%|▍         | 1256/25880 [17:55<5:00:06,  1.37it/s]
1|1257|Loss: 0.7266126871109009:   5%|▍         | 1256/25880 [17:55<5:00:06,  1.37it/s]
1|1257|Loss: 0.7266126871109009:   5%|▍         | 1257/25880 [17:55<5:01:13,  1.36it/s]
1|1258|Loss: 0.9203858375549316:   5%|▍         | 1257/25880 [17:56<5:01:13,  1.36it/s]
1|1258|Loss: 0.9203858375549316:   5%|▍         | 1258/25880 [17:56<5:12:59,  1.31it/s]
1|1259|Loss: 0.86324542760849:   5%|▍         | 1258/25880 [17:57<5:12:59,  1.31it/s]  
1|1259|Loss: 0.86324542760849:   5%|▍         | 1259/25880 [17:57<5:23:13,  1.27it/s]
1|1260|Loss: 0.9040764570236206:   5%|▍         | 1259/25880 [17:57<5:23:13,  1.27it/s]
1|1260|Loss: 0.9040764570236206:   5%|▍         | 1260/25880 [17:58<5:19:07,  1.29it/s]
1|1261|Loss: 0.9754088521003723:   5%|▍         | 1260/25880 [17:58<5:19:07,  1.29it/s]
1|1261|Loss: 0.9754088521003723:   5%|▍         | 1261/25880 [17:59<5:22:23,  1.27it/s]
1|1262|Loss: 1.0677149295806885:   5%|▍         | 1261/25880 [17:59<5:22:23,  1.27it/s]
1|1262|Loss: 1.0677149295806885:   5%|▍         | 1262/25880 [17:59<5:29:38,  1.24it/s]
1|1263|Loss: 0.9132692217826843:   5%|▍         | 1262/25880 [18:00<5:29:38,  1.24it/s]
1|1263|Loss: 0.9132692217826843:   5%|▍         | 1263/25880 [18:00<5:12:48,  1.31it/s]
1|1264|Loss: 0.8865056037902832:   5%|▍         | 1263/25880 [18:00<5:12:48,  1.31it/s]
1|1264|Loss: 0.8865056037902832:   5%|▍         | 1264/25880 [18:01<4:48:21,  1.42it/s]
1|1265|Loss: 1.0928988456726074:   5%|▍         | 1264/25880 [18:01<4:48:21,  1.42it/s]
1|1265|Loss: 1.0928988456726074:   5%|▍         | 1265/25880 [18:01<4:44:00,  1.44it/s]
1|1266|Loss: 0.8641179800033569:   5%|▍         | 1265/25880 [18:02<4:44:00,  1.44it/s]
1|1266|Loss: 0.8641179800033569:   5%|▍         | 1266/25880 [18:02<4:44:38,  1.44it/s]
1|1267|Loss: 0.8409817218780518:   5%|▍         | 1266/25880 [18:02<4:44:38,  1.44it/s]
1|1267|Loss: 0.8409817218780518:   5%|▍         | 1267/25880 [18:03<4:28:37,  1.53it/s]
1|1268|Loss: 0.8376966118812561:   5%|▍         | 1267/25880 [18:03<4:28:37,  1.53it/s]
1|1268|Loss: 0.8376966118812561:   5%|▍         | 1268/25880 [18:03<4:22:07,  1.56it/s]
1|1269|Loss: 0.9919171929359436:   5%|▍         | 1268/25880 [18:04<4:22:07,  1.56it/s]
1|1269|Loss: 0.9919171929359436:   5%|▍         | 1269/25880 [18:04<4:22:20,  1.56it/s]
1|1270|Loss: 0.8329214453697205:   5%|▍         | 1269/25880 [18:04<4:22:20,  1.56it/s]
1|1270|Loss: 0.8329214453697205:   5%|▍         | 1270/25880 [18:05<4:43:36,  1.45it/s]
1|1271|Loss: 0.8471787571907043:   5%|▍         | 1270/25880 [18:05<4:43:36,  1.45it/s]
1|1271|Loss: 0.8471787571907043:   5%|▍         | 1271/25880 [18:05<4:49:03,  1.42it/s]
1|1272|Loss: 0.9110886454582214:   5%|▍         | 1271/25880 [18:06<4:49:03,  1.42it/s]
1|1272|Loss: 0.9110886454582214:   5%|▍         | 1272/25880 [18:06<4:29:08,  1.52it/s]
1|1273|Loss: 0.980065107345581:   5%|▍         | 1272/25880 [18:06<4:29:08,  1.52it/s] 
1|1273|Loss: 0.980065107345581:   5%|▍         | 1273/25880 [18:07<4:34:09,  1.50it/s]
1|1274|Loss: 0.8456948399543762:   5%|▍         | 1273/25880 [18:07<4:34:09,  1.50it/s]
1|1274|Loss: 0.8456948399543762:   5%|▍         | 1274/25880 [18:07<4:40:58,  1.46it/s]
1|1275|Loss: 0.961352527141571:   5%|▍         | 1274/25880 [18:08<4:40:58,  1.46it/s] 
1|1275|Loss: 0.961352527141571:   5%|▍         | 1275/25880 [18:08<4:57:20,  1.38it/s]
1|1276|Loss: 0.9380010962486267:   5%|▍         | 1275/25880 [18:09<4:57:20,  1.38it/s]
1|1276|Loss: 0.9380010962486267:   5%|▍         | 1276/25880 [18:09<5:01:20,  1.36it/s]
1|1277|Loss: 0.7716579437255859:   5%|▍         | 1276/25880 [18:09<5:01:20,  1.36it/s]
1|1277|Loss: 0.7716579437255859:   5%|▍         | 1277/25880 [18:10<5:09:26,  1.33it/s]
1|1278|Loss: 0.9331958889961243:   5%|▍         | 1277/25880 [18:10<5:09:26,  1.33it/s]
1|1278|Loss: 0.9331958889961243:   5%|▍         | 1278/25880 [18:10<5:14:22,  1.30it/s]
1|1279|Loss: 0.9043216109275818:   5%|▍         | 1278/25880 [18:11<5:14:22,  1.30it/s]
1|1279|Loss: 0.9043216109275818:   5%|▍         | 1279/25880 [18:11<5:22:14,  1.27it/s]
1|1280|Loss: 0.81463623046875:   5%|▍         | 1279/25880 [18:12<5:22:14,  1.27it/s]  
1|1280|Loss: 0.81463623046875:   5%|▍         | 1280/25880 [18:12<5:06:10,  1.34it/s]
1|1281|Loss: 0.9036967158317566:   5%|▍         | 1280/25880 [18:12<5:06:10,  1.34it/s]
1|1281|Loss: 0.9036967158317566:   5%|▍         | 1281/25880 [18:13<4:50:02,  1.41it/s]
1|1282|Loss: 0.8478888273239136:   5%|▍         | 1281/25880 [18:13<4:50:02,  1.41it/s]
1|1282|Loss: 0.8478888273239136:   5%|▍         | 1282/25880 [18:13<4:47:50,  1.42it/s]
1|1283|Loss: 0.9288220405578613:   5%|▍         | 1282/25880 [18:14<4:47:50,  1.42it/s]
1|1283|Loss: 0.9288220405578613:   5%|▍         | 1283/25880 [18:14<4:41:46,  1.45it/s]
1|1284|Loss: 0.9395231604576111:   5%|▍         | 1283/25880 [18:14<4:41:46,  1.45it/s]
1|1284|Loss: 0.9395231604576111:   5%|▍         | 1284/25880 [18:15<4:36:31,  1.48it/s]
1|1285|Loss: 0.9158374071121216:   5%|▍         | 1284/25880 [18:15<4:36:31,  1.48it/s]
1|1285|Loss: 0.9158374071121216:   5%|▍         | 1285/25880 [18:15<4:48:17,  1.42it/s]
1|1286|Loss: 0.7442485690116882:   5%|▍         | 1285/25880 [18:16<4:48:17,  1.42it/s]
1|1286|Loss: 0.7442485690116882:   5%|▍         | 1286/25880 [18:16<4:44:00,  1.44it/s]
1|1287|Loss: 0.8980644941329956:   5%|▍         | 1286/25880 [18:16<4:44:00,  1.44it/s]
1|1287|Loss: 0.8980644941329956:   5%|▍         | 1287/25880 [18:17<4:52:10,  1.40it/s]
1|1288|Loss: 0.9727754592895508:   5%|▍         | 1287/25880 [18:17<4:52:10,  1.40it/s]
1|1288|Loss: 0.9727754592895508:   5%|▍         | 1288/25880 [18:17<4:38:40,  1.47it/s]
1|1289|Loss: 0.9622812867164612:   5%|▍         | 1288/25880 [18:18<4:38:40,  1.47it/s]
1|1289|Loss: 0.9622812867164612:   5%|▍         | 1289/25880 [18:18<4:31:30,  1.51it/s]
1|1290|Loss: 0.7157211899757385:   5%|▍         | 1289/25880 [18:18<4:31:30,  1.51it/s]
1|1290|Loss: 0.7157211899757385:   5%|▍         | 1290/25880 [18:19<4:38:54,  1.47it/s]
1|1291|Loss: 0.9432211518287659:   5%|▍         | 1290/25880 [18:19<4:38:54,  1.47it/s]
1|1291|Loss: 0.9432211518287659:   5%|▍         | 1291/25880 [18:20<5:00:31,  1.36it/s]
1|1292|Loss: 0.9177498817443848:   5%|▍         | 1291/25880 [18:20<5:00:31,  1.36it/s]
1|1292|Loss: 0.9177498817443848:   5%|▍         | 1292/25880 [18:20<4:47:41,  1.42it/s]
1|1293|Loss: 0.8971007466316223:   5%|▍         | 1292/25880 [18:21<4:47:41,  1.42it/s]
1|1293|Loss: 0.8971007466316223:   5%|▍         | 1293/25880 [18:21<4:56:19,  1.38it/s]
1|1294|Loss: 0.9133504629135132:   5%|▍         | 1293/25880 [18:21<4:56:19,  1.38it/s]
1|1294|Loss: 0.9133504629135132:   5%|▌         | 1294/25880 [18:22<4:56:34,  1.38it/s]
1|1295|Loss: 0.925898551940918:   5%|▌         | 1294/25880 [18:22<4:56:34,  1.38it/s] 
1|1295|Loss: 0.925898551940918:   5%|▌         | 1295/25880 [18:22<4:56:13,  1.38it/s]
1|1296|Loss: 0.9749665260314941:   5%|▌         | 1295/25880 [18:23<4:56:13,  1.38it/s]
1|1296|Loss: 0.9749665260314941:   5%|▌         | 1296/25880 [18:23<5:11:55,  1.31it/s]
1|1297|Loss: 0.791883111000061:   5%|▌         | 1296/25880 [18:24<5:11:55,  1.31it/s] 
1|1297|Loss: 0.791883111000061:   5%|▌         | 1297/25880 [18:24<5:08:58,  1.33it/s]
1|1298|Loss: 0.9245578050613403:   5%|▌         | 1297/25880 [18:24<5:08:58,  1.33it/s]
1|1298|Loss: 0.9245578050613403:   5%|▌         | 1298/25880 [18:25<5:05:32,  1.34it/s]
1|1299|Loss: 0.8642652034759521:   5%|▌         | 1298/25880 [18:25<5:05:32,  1.34it/s]
1|1299|Loss: 0.8642652034759521:   5%|▌         | 1299/25880 [18:26<5:19:00,  1.28it/s]
1|1300|Loss: 1.0050630569458008:   5%|▌         | 1299/25880 [18:26<5:19:00,  1.28it/s]
1|1300|Loss: 1.0050630569458008:   5%|▌         | 1300/25880 [18:26<5:27:31,  1.25it/s]
1|1301|Loss: 0.8833180665969849:   5%|▌         | 1300/25880 [18:27<5:27:31,  1.25it/s]
1|1301|Loss: 0.8833180665969849:   5%|▌         | 1301/25880 [18:27<5:40:17,  1.20it/s]
1|1302|Loss: 0.7386803030967712:   5%|▌         | 1301/25880 [18:28<5:40:17,  1.20it/s]
1|1302|Loss: 0.7386803030967712:   5%|▌         | 1302/25880 [18:28<5:15:01,  1.30it/s]
1|1303|Loss: 0.8518028855323792:   5%|▌         | 1302/25880 [18:28<5:15:01,  1.30it/s]
1|1303|Loss: 0.8518028855323792:   5%|▌         | 1303/25880 [18:29<5:28:23,  1.25it/s]
1|1304|Loss: 0.8125027418136597:   5%|▌         | 1303/25880 [18:29<5:28:23,  1.25it/s]
1|1304|Loss: 0.8125027418136597:   5%|▌         | 1304/25880 [18:30<5:43:40,  1.19it/s]
1|1305|Loss: 0.992361843585968:   5%|▌         | 1304/25880 [18:30<5:43:40,  1.19it/s] 
1|1305|Loss: 0.992361843585968:   5%|▌         | 1305/25880 [18:31<5:35:07,  1.22it/s]
1|1306|Loss: 0.9514042735099792:   5%|▌         | 1305/25880 [18:31<5:35:07,  1.22it/s]
1|1306|Loss: 0.9514042735099792:   5%|▌         | 1306/25880 [18:31<5:22:42,  1.27it/s]
1|1307|Loss: 0.9635409712791443:   5%|▌         | 1306/25880 [18:32<5:22:42,  1.27it/s]
1|1307|Loss: 0.9635409712791443:   5%|▌         | 1307/25880 [18:32<5:06:46,  1.34it/s]
1|1308|Loss: 0.9024257659912109:   5%|▌         | 1307/25880 [18:32<5:06:46,  1.34it/s]
1|1308|Loss: 0.9024257659912109:   5%|▌         | 1308/25880 [18:33<5:04:19,  1.35it/s]
1|1309|Loss: 0.775479257106781:   5%|▌         | 1308/25880 [18:33<5:04:19,  1.35it/s] 
1|1309|Loss: 0.775479257106781:   5%|▌         | 1309/25880 [18:33<5:13:14,  1.31it/s]
1|1310|Loss: 0.9540282487869263:   5%|▌         | 1309/25880 [18:34<5:13:14,  1.31it/s]
1|1310|Loss: 0.9540282487869263:   5%|▌         | 1310/25880 [18:34<5:11:16,  1.32it/s]
1|1311|Loss: 0.8825357556343079:   5%|▌         | 1310/25880 [18:35<5:11:16,  1.32it/s]
1|1311|Loss: 0.8825357556343079:   5%|▌         | 1311/25880 [18:35<5:04:33,  1.34it/s]
1|1312|Loss: 1.018964409828186:   5%|▌         | 1311/25880 [18:35<5:04:33,  1.34it/s] 
1|1312|Loss: 1.018964409828186:   5%|▌         | 1312/25880 [18:36<5:17:03,  1.29it/s]
1|1313|Loss: 0.8842217922210693:   5%|▌         | 1312/25880 [18:36<5:17:03,  1.29it/s]
1|1313|Loss: 0.8842217922210693:   5%|▌         | 1313/25880 [18:37<5:30:03,  1.24it/s]
1|1314|Loss: 0.7608764171600342:   5%|▌         | 1313/25880 [18:37<5:30:03,  1.24it/s]
1|1314|Loss: 0.7608764171600342:   5%|▌         | 1314/25880 [18:38<5:47:38,  1.18it/s]
1|1315|Loss: 0.8588107228279114:   5%|▌         | 1314/25880 [18:38<5:47:38,  1.18it/s]
1|1315|Loss: 0.8588107228279114:   5%|▌         | 1315/25880 [18:38<5:29:21,  1.24it/s]
1|1316|Loss: 0.8641065955162048:   5%|▌         | 1315/25880 [18:39<5:29:21,  1.24it/s]
1|1316|Loss: 0.8641065955162048:   5%|▌         | 1316/25880 [18:39<5:19:02,  1.28it/s]
1|1317|Loss: 0.9083324670791626:   5%|▌         | 1316/25880 [18:39<5:19:02,  1.28it/s]
1|1317|Loss: 0.9083324670791626:   5%|▌         | 1317/25880 [18:40<4:58:30,  1.37it/s]
1|1318|Loss: 0.7235925197601318:   5%|▌         | 1317/25880 [18:40<4:58:30,  1.37it/s]
1|1318|Loss: 0.7235925197601318:   5%|▌         | 1318/25880 [18:40<5:07:43,  1.33it/s]
1|1319|Loss: 0.9193440675735474:   5%|▌         | 1318/25880 [18:41<5:07:43,  1.33it/s]
1|1319|Loss: 0.9193440675735474:   5%|▌         | 1319/25880 [18:41<5:18:13,  1.29it/s]
1|1320|Loss: 0.7506898045539856:   5%|▌         | 1319/25880 [18:42<5:18:13,  1.29it/s]
1|1320|Loss: 0.7506898045539856:   5%|▌         | 1320/25880 [18:42<5:03:01,  1.35it/s]
1|1321|Loss: 0.8417694568634033:   5%|▌         | 1320/25880 [18:42<5:03:01,  1.35it/s]
1|1321|Loss: 0.8417694568634033:   5%|▌         | 1321/25880 [18:43<5:00:03,  1.36it/s]
1|1322|Loss: 0.8637160658836365:   5%|▌         | 1321/25880 [18:43<5:00:03,  1.36it/s]
1|1322|Loss: 0.8637160658836365:   5%|▌         | 1322/25880 [18:43<4:49:02,  1.42it/s]
1|1323|Loss: 0.8808100819587708:   5%|▌         | 1322/25880 [18:44<4:49:02,  1.42it/s]
1|1323|Loss: 0.8808100819587708:   5%|▌         | 1323/25880 [18:44<4:46:35,  1.43it/s]
1|1324|Loss: 0.8486070036888123:   5%|▌         | 1323/25880 [18:44<4:46:35,  1.43it/s]
1|1324|Loss: 0.8486070036888123:   5%|▌         | 1324/25880 [18:45<4:40:40,  1.46it/s]
1|1325|Loss: 0.9106911420822144:   5%|▌         | 1324/25880 [18:45<4:40:40,  1.46it/s]
1|1325|Loss: 0.9106911420822144:   5%|▌         | 1325/25880 [18:45<4:46:17,  1.43it/s]
1|1326|Loss: 0.816128134727478:   5%|▌         | 1325/25880 [18:46<4:46:17,  1.43it/s] 
1|1326|Loss: 0.816128134727478:   5%|▌         | 1326/25880 [18:46<4:58:12,  1.37it/s]
1|1327|Loss: 0.9306833148002625:   5%|▌         | 1326/25880 [18:47<4:58:12,  1.37it/s]
1|1327|Loss: 0.9306833148002625:   5%|▌         | 1327/25880 [18:47<4:59:37,  1.37it/s]
1|1328|Loss: 1.065272569656372:   5%|▌         | 1327/25880 [18:47<4:59:37,  1.37it/s] 
1|1328|Loss: 1.065272569656372:   5%|▌         | 1328/25880 [18:48<4:58:34,  1.37it/s]
1|1329|Loss: 0.9340622425079346:   5%|▌         | 1328/25880 [18:48<4:58:34,  1.37it/s]
1|1329|Loss: 0.9340622425079346:   5%|▌         | 1329/25880 [18:48<4:50:13,  1.41it/s]
1|1330|Loss: 0.8335438966751099:   5%|▌         | 1329/25880 [18:49<4:50:13,  1.41it/s]
1|1330|Loss: 0.8335438966751099:   5%|▌         | 1330/25880 [18:49<4:41:16,  1.45it/s]
1|1331|Loss: 0.8749067783355713:   5%|▌         | 1330/25880 [18:49<4:41:16,  1.45it/s]
1|1331|Loss: 0.8749067783355713:   5%|▌         | 1331/25880 [18:50<5:03:05,  1.35it/s]
1|1332|Loss: 1.0448776483535767:   5%|▌         | 1331/25880 [18:50<5:03:05,  1.35it/s]
1|1332|Loss: 1.0448776483535767:   5%|▌         | 1332/25880 [18:50<4:49:11,  1.41it/s]
1|1333|Loss: 0.8239859938621521:   5%|▌         | 1332/25880 [18:51<4:49:11,  1.41it/s]
1|1333|Loss: 0.8239859938621521:   5%|▌         | 1333/25880 [18:51<4:14:17,  1.61it/s]
1|1334|Loss: 0.8917369842529297:   5%|▌         | 1333/25880 [18:51<4:14:17,  1.61it/s]
1|1334|Loss: 0.8917369842529297:   5%|▌         | 1334/25880 [18:51<4:11:37,  1.63it/s]
1|1335|Loss: 0.7886270880699158:   5%|▌         | 1334/25880 [18:52<4:11:37,  1.63it/s]
1|1335|Loss: 0.7886270880699158:   5%|▌         | 1335/25880 [18:52<3:56:19,  1.73it/s]
1|1336|Loss: 1.0197727680206299:   5%|▌         | 1335/25880 [18:52<3:56:19,  1.73it/s]
1|1336|Loss: 1.0197727680206299:   5%|▌         | 1336/25880 [18:52<3:46:10,  1.81it/s]
1|1337|Loss: 0.9340047240257263:   5%|▌         | 1336/25880 [18:53<3:46:10,  1.81it/s]
1|1337|Loss: 0.9340047240257263:   5%|▌         | 1337/25880 [18:53<4:07:36,  1.65it/s]
1|1338|Loss: 0.9239466190338135:   5%|▌         | 1337/25880 [18:54<4:07:36,  1.65it/s]
1|1338|Loss: 0.9239466190338135:   5%|▌         | 1338/25880 [18:54<4:22:10,  1.56it/s]
1|1339|Loss: 0.8721061944961548:   5%|▌         | 1338/25880 [18:54<4:22:10,  1.56it/s]
1|1339|Loss: 0.8721061944961548:   5%|▌         | 1339/25880 [18:55<4:23:16,  1.55it/s]
1|1340|Loss: 0.9244766235351562:   5%|▌         | 1339/25880 [18:55<4:23:16,  1.55it/s]
1|1340|Loss: 0.9244766235351562:   5%|▌         | 1340/25880 [18:55<4:32:50,  1.50it/s]
1|1341|Loss: 0.9857479929924011:   5%|▌         | 1340/25880 [18:56<4:32:50,  1.50it/s]
1|1341|Loss: 0.9857479929924011:   5%|▌         | 1341/25880 [18:56<4:30:57,  1.51it/s]
1|1342|Loss: 0.9833326935768127:   5%|▌         | 1341/25880 [18:56<4:30:57,  1.51it/s]
1|1342|Loss: 0.9833326935768127:   5%|▌         | 1342/25880 [18:56<4:17:28,  1.59it/s]
1|1343|Loss: 0.889240026473999:   5%|▌         | 1342/25880 [18:57<4:17:28,  1.59it/s] 
1|1343|Loss: 0.889240026473999:   5%|▌         | 1343/25880 [18:57<4:24:19,  1.55it/s]
1|1344|Loss: 0.7978143095970154:   5%|▌         | 1343/25880 [18:58<4:24:19,  1.55it/s]
1|1344|Loss: 0.7978143095970154:   5%|▌         | 1344/25880 [18:58<4:31:11,  1.51it/s]
1|1345|Loss: 1.1152640581130981:   5%|▌         | 1344/25880 [18:58<4:31:11,  1.51it/s]
1|1345|Loss: 1.1152640581130981:   5%|▌         | 1345/25880 [18:59<4:35:57,  1.48it/s]
1|1346|Loss: 0.8794601559638977:   5%|▌         | 1345/25880 [18:59<4:35:57,  1.48it/s]
1|1346|Loss: 0.8794601559638977:   5%|▌         | 1346/25880 [18:59<4:41:17,  1.45it/s]
1|1347|Loss: 0.9362787008285522:   5%|▌         | 1346/25880 [19:00<4:41:17,  1.45it/s]
1|1347|Loss: 0.9362787008285522:   5%|▌         | 1347/25880 [19:00<4:45:50,  1.43it/s]
1|1348|Loss: 0.7705097198486328:   5%|▌         | 1347/25880 [19:01<4:45:50,  1.43it/s]
1|1348|Loss: 0.7705097198486328:   5%|▌         | 1348/25880 [19:02<6:52:51,  1.01s/it]
1|1349|Loss: 0.8357783555984497:   5%|▌         | 1348/25880 [19:02<6:52:51,  1.01s/it]
1|1349|Loss: 0.8357783555984497:   5%|▌         | 1349/25880 [19:03<6:30:57,  1.05it/s]
1|1350|Loss: 0.9415479302406311:   5%|▌         | 1349/25880 [19:03<6:30:57,  1.05it/s]
1|1350|Loss: 0.9415479302406311:   5%|▌         | 1350/25880 [19:03<5:55:59,  1.15it/s]
1|1351|Loss: 0.9402651786804199:   5%|▌         | 1350/25880 [19:04<5:55:59,  1.15it/s]
1|1351|Loss: 0.9402651786804199:   5%|▌         | 1351/25880 [19:04<5:26:40,  1.25it/s]
1|1352|Loss: 1.0533851385116577:   5%|▌         | 1351/25880 [19:04<5:26:40,  1.25it/s]
1|1352|Loss: 1.0533851385116577:   5%|▌         | 1352/25880 [19:04<4:53:42,  1.39it/s]
1|1353|Loss: 0.9862514734268188:   5%|▌         | 1352/25880 [19:05<4:53:42,  1.39it/s]
1|1353|Loss: 0.9862514734268188:   5%|▌         | 1353/25880 [19:05<4:51:11,  1.40it/s]
1|1354|Loss: 0.9695726037025452:   5%|▌         | 1353/25880 [19:05<4:51:11,  1.40it/s]
1|1354|Loss: 0.9695726037025452:   5%|▌         | 1354/25880 [19:06<4:54:08,  1.39it/s]
1|1355|Loss: 0.8848164081573486:   5%|▌         | 1354/25880 [19:06<4:54:08,  1.39it/s]
1|1355|Loss: 0.8848164081573486:   5%|▌         | 1355/25880 [19:07<5:14:00,  1.30it/s]
1|1356|Loss: 0.8723494410514832:   5%|▌         | 1355/25880 [19:07<5:14:00,  1.30it/s]
1|1356|Loss: 0.8723494410514832:   5%|▌         | 1356/25880 [19:08<5:33:36,  1.23it/s]
1|1357|Loss: 0.9168217778205872:   5%|▌         | 1356/25880 [19:08<5:33:36,  1.23it/s]
1|1357|Loss: 0.9168217778205872:   5%|▌         | 1357/25880 [19:08<5:14:22,  1.30it/s]
1|1358|Loss: 0.8941324353218079:   5%|▌         | 1357/25880 [19:09<5:14:22,  1.30it/s]
1|1358|Loss: 0.8941324353218079:   5%|▌         | 1358/25880 [19:09<5:19:09,  1.28it/s]
1|1359|Loss: 0.93193119764328:   5%|▌         | 1358/25880 [19:10<5:19:09,  1.28it/s]  
1|1359|Loss: 0.93193119764328:   5%|▌         | 1359/25880 [19:10<5:26:19,  1.25it/s]
1|1360|Loss: 0.9448733925819397:   5%|▌         | 1359/25880 [19:10<5:26:19,  1.25it/s]
1|1360|Loss: 0.9448733925819397:   5%|▌         | 1360/25880 [19:11<5:03:01,  1.35it/s]
1|1361|Loss: 0.9448776841163635:   5%|▌         | 1360/25880 [19:11<5:03:01,  1.35it/s]
1|1361|Loss: 0.9448776841163635:   5%|▌         | 1361/25880 [19:11<4:57:42,  1.37it/s]
1|1362|Loss: 0.8932991623878479:   5%|▌         | 1361/25880 [19:12<4:57:42,  1.37it/s]
1|1362|Loss: 0.8932991623878479:   5%|▌         | 1362/25880 [19:12<5:05:06,  1.34it/s]
1|1363|Loss: 0.8169530034065247:   5%|▌         | 1362/25880 [19:12<5:05:06,  1.34it/s]
1|1363|Loss: 0.8169530034065247:   5%|▌         | 1363/25880 [19:13<5:19:20,  1.28it/s]
1|1364|Loss: 0.9185631275177002:   5%|▌         | 1363/25880 [19:13<5:19:20,  1.28it/s]
1|1364|Loss: 0.9185631275177002:   5%|▌         | 1364/25880 [19:13<4:53:44,  1.39it/s]
1|1365|Loss: 0.8046196103096008:   5%|▌         | 1364/25880 [19:14<4:53:44,  1.39it/s]
1|1365|Loss: 0.8046196103096008:   5%|▌         | 1365/25880 [19:14<5:02:36,  1.35it/s]
1|1366|Loss: 0.9045897126197815:   5%|▌         | 1365/25880 [19:15<5:02:36,  1.35it/s]
1|1366|Loss: 0.9045897126197815:   5%|▌         | 1366/25880 [19:15<5:16:42,  1.29it/s]
1|1367|Loss: 0.7736251354217529:   5%|▌         | 1366/25880 [19:15<5:16:42,  1.29it/s]
1|1367|Loss: 0.7736251354217529:   5%|▌         | 1367/25880 [19:16<5:01:29,  1.36it/s]
1|1368|Loss: 0.9424879550933838:   5%|▌         | 1367/25880 [19:16<5:01:29,  1.36it/s]
1|1368|Loss: 0.9424879550933838:   5%|▌         | 1368/25880 [19:16<4:54:06,  1.39it/s]
1|1369|Loss: 1.0206164121627808:   5%|▌         | 1368/25880 [19:17<4:54:06,  1.39it/s]
1|1369|Loss: 1.0206164121627808:   5%|▌         | 1369/25880 [19:17<5:07:28,  1.33it/s]
1|1370|Loss: 0.7833355665206909:   5%|▌         | 1369/25880 [19:18<5:07:28,  1.33it/s]
1|1370|Loss: 0.7833355665206909:   5%|▌         | 1370/25880 [19:18<5:09:07,  1.32it/s]
1|1371|Loss: 0.983038604259491:   5%|▌         | 1370/25880 [19:18<5:09:07,  1.32it/s] 
1|1371|Loss: 0.983038604259491:   5%|▌         | 1371/25880 [19:19<4:54:01,  1.39it/s]
1|1372|Loss: 0.9241259694099426:   5%|▌         | 1371/25880 [19:19<4:54:01,  1.39it/s]
1|1372|Loss: 0.9241259694099426:   5%|▌         | 1372/25880 [19:19<5:07:18,  1.33it/s]
1|1373|Loss: 0.8809866905212402:   5%|▌         | 1372/25880 [19:20<5:07:18,  1.33it/s]
1|1373|Loss: 0.8809866905212402:   5%|▌         | 1373/25880 [19:20<4:54:29,  1.39it/s]
1|1374|Loss: 0.8308897614479065:   5%|▌         | 1373/25880 [19:21<4:54:29,  1.39it/s]
1|1374|Loss: 0.8308897614479065:   5%|▌         | 1374/25880 [19:21<5:05:02,  1.34it/s]
1|1375|Loss: 0.9331772923469543:   5%|▌         | 1374/25880 [19:21<5:05:02,  1.34it/s]
1|1375|Loss: 0.9331772923469543:   5%|▌         | 1375/25880 [19:22<5:07:19,  1.33it/s]
1|1376|Loss: 0.9275427460670471:   5%|▌         | 1375/25880 [19:22<5:07:19,  1.33it/s]
1|1376|Loss: 0.9275427460670471:   5%|▌         | 1376/25880 [19:22<5:05:47,  1.34it/s]
1|1377|Loss: 0.9334383010864258:   5%|▌         | 1376/25880 [19:23<5:05:47,  1.34it/s]
1|1377|Loss: 0.9334383010864258:   5%|▌         | 1377/25880 [19:23<5:16:07,  1.29it/s]
1|1378|Loss: 0.933817982673645:   5%|▌         | 1377/25880 [19:24<5:16:07,  1.29it/s] 
1|1378|Loss: 0.933817982673645:   5%|▌         | 1378/25880 [19:24<4:55:18,  1.38it/s]
1|1379|Loss: 0.8596223592758179:   5%|▌         | 1378/25880 [19:24<4:55:18,  1.38it/s]
1|1379|Loss: 0.8596223592758179:   5%|▌         | 1379/25880 [19:24<4:39:26,  1.46it/s]
1|1380|Loss: 0.8707494735717773:   5%|▌         | 1379/25880 [19:25<4:39:26,  1.46it/s]
1|1380|Loss: 0.8707494735717773:   5%|▌         | 1380/25880 [19:25<5:06:36,  1.33it/s]
1|1381|Loss: 0.7962992787361145:   5%|▌         | 1380/25880 [19:26<5:06:36,  1.33it/s]
1|1381|Loss: 0.7962992787361145:   5%|▌         | 1381/25880 [19:26<5:10:15,  1.32it/s]
1|1382|Loss: 0.7584788203239441:   5%|▌         | 1381/25880 [19:27<5:10:15,  1.32it/s]
1|1382|Loss: 0.7584788203239441:   5%|▌         | 1382/25880 [19:27<5:04:34,  1.34it/s]
1|1383|Loss: 0.9229514002799988:   5%|▌         | 1382/25880 [19:27<5:04:34,  1.34it/s]
1|1383|Loss: 0.9229514002799988:   5%|▌         | 1383/25880 [19:28<5:21:25,  1.27it/s]
1|1384|Loss: 0.9484671950340271:   5%|▌         | 1383/25880 [19:28<5:21:25,  1.27it/s]
1|1384|Loss: 0.9484671950340271:   5%|▌         | 1384/25880 [19:29<5:37:31,  1.21it/s]
1|1385|Loss: 1.000491976737976:   5%|▌         | 1384/25880 [19:29<5:37:31,  1.21it/s] 
1|1385|Loss: 1.000491976737976:   5%|▌         | 1385/25880 [19:29<5:20:52,  1.27it/s]
1|1386|Loss: 0.7465053796768188:   5%|▌         | 1385/25880 [19:30<5:20:52,  1.27it/s]
1|1386|Loss: 0.7465053796768188:   5%|▌         | 1386/25880 [19:30<5:09:02,  1.32it/s]
1|1387|Loss: 0.812700629234314:   5%|▌         | 1386/25880 [19:30<5:09:02,  1.32it/s] 
1|1387|Loss: 0.812700629234314:   5%|▌         | 1387/25880 [19:31<5:17:42,  1.28it/s]
1|1388|Loss: 0.9702218174934387:   5%|▌         | 1387/25880 [19:31<5:17:42,  1.28it/s]
1|1388|Loss: 0.9702218174934387:   5%|▌         | 1388/25880 [19:32<5:13:15,  1.30it/s]
1|1389|Loss: 0.8287590742111206:   5%|▌         | 1388/25880 [19:32<5:13:15,  1.30it/s]
1|1389|Loss: 0.8287590742111206:   5%|▌         | 1389/25880 [19:32<5:14:17,  1.30it/s]
1|1390|Loss: 0.9400367140769958:   5%|▌         | 1389/25880 [19:33<5:14:17,  1.30it/s]
1|1390|Loss: 0.9400367140769958:   5%|▌         | 1390/25880 [19:33<5:20:29,  1.27it/s]
1|1391|Loss: 0.9126696586608887:   5%|▌         | 1390/25880 [19:34<5:20:29,  1.27it/s]
1|1391|Loss: 0.9126696586608887:   5%|▌         | 1391/25880 [19:34<5:16:36,  1.29it/s]
1|1392|Loss: 0.8630219101905823:   5%|▌         | 1391/25880 [19:34<5:16:36,  1.29it/s]
1|1392|Loss: 0.8630219101905823:   5%|▌         | 1392/25880 [19:35<5:17:12,  1.29it/s]
1|1393|Loss: 0.8485130071640015:   5%|▌         | 1392/25880 [19:35<5:17:12,  1.29it/s]
1|1393|Loss: 0.8485130071640015:   5%|▌         | 1393/25880 [19:35<5:02:20,  1.35it/s]
1|1394|Loss: 0.8801045417785645:   5%|▌         | 1393/25880 [19:36<5:02:20,  1.35it/s]
1|1394|Loss: 0.8801045417785645:   5%|▌         | 1394/25880 [19:36<4:46:55,  1.42it/s]
1|1395|Loss: 0.9533664584159851:   5%|▌         | 1394/25880 [19:36<4:46:55,  1.42it/s]
1|1395|Loss: 0.9533664584159851:   5%|▌         | 1395/25880 [19:37<4:38:25,  1.47it/s]
1|1396|Loss: 0.8456206321716309:   5%|▌         | 1395/25880 [19:37<4:38:25,  1.47it/s]
1|1396|Loss: 0.8456206321716309:   5%|▌         | 1396/25880 [19:37<4:42:48,  1.44it/s]
1|1397|Loss: 0.8923784494400024:   5%|▌         | 1396/25880 [19:38<4:42:48,  1.44it/s]
1|1397|Loss: 0.8923784494400024:   5%|▌         | 1397/25880 [19:38<4:44:27,  1.43it/s]
1|1398|Loss: 0.8427826166152954:   5%|▌         | 1397/25880 [19:38<4:44:27,  1.43it/s]
1|1398|Loss: 0.8427826166152954:   5%|▌         | 1398/25880 [19:39<4:32:48,  1.50it/s]
1|1399|Loss: 0.7569946050643921:   5%|▌         | 1398/25880 [19:39<4:32:48,  1.50it/s]
1|1399|Loss: 0.7569946050643921:   5%|▌         | 1399/25880 [19:40<5:01:44,  1.35it/s]
1|1400|Loss: 0.8758569955825806:   5%|▌         | 1399/25880 [19:40<5:01:44,  1.35it/s]
1|1400|Loss: 0.8758569955825806:   5%|▌         | 1400/25880 [19:40<4:53:15,  1.39it/s]
1|1401|Loss: 0.9368434548377991:   5%|▌         | 1400/25880 [19:41<4:53:15,  1.39it/s]
1|1401|Loss: 0.9368434548377991:   5%|▌         | 1401/25880 [19:41<4:15:30,  1.60it/s]
1|1402|Loss: 0.8413234353065491:   5%|▌         | 1401/25880 [19:41<4:15:30,  1.60it/s]
1|1402|Loss: 0.8413234353065491:   5%|▌         | 1402/25880 [19:41<4:29:46,  1.51it/s]
1|1403|Loss: 0.8338865041732788:   5%|▌         | 1402/25880 [19:42<4:29:46,  1.51it/s]
1|1403|Loss: 0.8338865041732788:   5%|▌         | 1403/25880 [19:42<4:45:37,  1.43it/s]
1|1404|Loss: 0.7955458164215088:   5%|▌         | 1403/25880 [19:43<4:45:37,  1.43it/s]
1|1404|Loss: 0.7955458164215088:   5%|▌         | 1404/25880 [19:43<5:00:35,  1.36it/s]
1|1405|Loss: 0.9170824289321899:   5%|▌         | 1404/25880 [19:43<5:00:35,  1.36it/s]
1|1405|Loss: 0.9170824289321899:   5%|▌         | 1405/25880 [19:44<5:08:59,  1.32it/s]
1|1406|Loss: 0.8885723948478699:   5%|▌         | 1405/25880 [19:44<5:08:59,  1.32it/s]
1|1406|Loss: 0.8885723948478699:   5%|▌         | 1406/25880 [19:45<5:12:45,  1.30it/s]
1|1407|Loss: 0.9552847146987915:   5%|▌         | 1406/25880 [19:45<5:12:45,  1.30it/s]
1|1407|Loss: 0.9552847146987915:   5%|▌         | 1407/25880 [19:45<5:07:22,  1.33it/s]
1|1408|Loss: 0.9638857245445251:   5%|▌         | 1407/25880 [19:46<5:07:22,  1.33it/s]
1|1408|Loss: 0.9638857245445251:   5%|▌         | 1408/25880 [19:46<5:04:55,  1.34it/s]
1|1409|Loss: 0.9014281630516052:   5%|▌         | 1408/25880 [19:46<5:04:55,  1.34it/s]
1|1409|Loss: 0.9014281630516052:   5%|▌         | 1409/25880 [19:47<5:01:04,  1.35it/s]
1|1410|Loss: 0.9126731157302856:   5%|▌         | 1409/25880 [19:47<5:01:04,  1.35it/s]
1|1410|Loss: 0.9126731157302856:   5%|▌         | 1410/25880 [19:48<5:01:10,  1.35it/s]
1|1411|Loss: 0.957946240901947:   5%|▌         | 1410/25880 [19:48<5:01:10,  1.35it/s] 
1|1411|Loss: 0.957946240901947:   5%|▌         | 1411/25880 [19:48<5:01:26,  1.35it/s]
1|1412|Loss: 0.8667107224464417:   5%|▌         | 1411/25880 [19:49<5:01:26,  1.35it/s]
1|1412|Loss: 0.8667107224464417:   5%|▌         | 1412/25880 [19:49<4:45:59,  1.43it/s]
1|1413|Loss: 0.8459522128105164:   5%|▌         | 1412/25880 [19:49<4:45:59,  1.43it/s]
1|1413|Loss: 0.8459522128105164:   5%|▌         | 1413/25880 [19:50<4:46:34,  1.42it/s]
1|1414|Loss: 0.8007397651672363:   5%|▌         | 1413/25880 [19:50<4:46:34,  1.42it/s]
1|1414|Loss: 0.8007397651672363:   5%|▌         | 1414/25880 [19:50<4:56:52,  1.37it/s]
1|1415|Loss: 0.9280204176902771:   5%|▌         | 1414/25880 [19:51<4:56:52,  1.37it/s]
1|1415|Loss: 0.9280204176902771:   5%|▌         | 1415/25880 [19:51<4:48:34,  1.41it/s]
1|1416|Loss: 0.8760178685188293:   5%|▌         | 1415/25880 [19:51<4:48:34,  1.41it/s]
1|1416|Loss: 0.8760178685188293:   5%|▌         | 1416/25880 [19:52<4:45:45,  1.43it/s]
1|1417|Loss: 0.8286041617393494:   5%|▌         | 1416/25880 [19:52<4:45:45,  1.43it/s]
1|1417|Loss: 0.8286041617393494:   5%|▌         | 1417/25880 [19:52<4:45:55,  1.43it/s]
1|1418|Loss: 0.9174425005912781:   5%|▌         | 1417/25880 [19:53<4:45:55,  1.43it/s]
1|1418|Loss: 0.9174425005912781:   5%|▌         | 1418/25880 [19:53<5:06:59,  1.33it/s]
1|1419|Loss: 0.8168567419052124:   5%|▌         | 1418/25880 [19:54<5:06:59,  1.33it/s]
1|1419|Loss: 0.8168567419052124:   5%|▌         | 1419/25880 [19:54<5:20:35,  1.27it/s]
1|1420|Loss: 0.9887343645095825:   5%|▌         | 1419/25880 [19:55<5:20:35,  1.27it/s]
1|1420|Loss: 0.9887343645095825:   5%|▌         | 1420/25880 [19:55<5:07:53,  1.32it/s]
1|1421|Loss: 0.8942094445228577:   5%|▌         | 1420/25880 [19:55<5:07:53,  1.32it/s]
1|1421|Loss: 0.8942094445228577:   5%|▌         | 1421/25880 [19:56<4:59:36,  1.36it/s]
1|1422|Loss: 0.8447287082672119:   5%|▌         | 1421/25880 [19:56<4:59:36,  1.36it/s]
1|1422|Loss: 0.8447287082672119:   5%|▌         | 1422/25880 [19:56<4:58:11,  1.37it/s]
1|1423|Loss: 0.9045791029930115:   5%|▌         | 1422/25880 [19:57<4:58:11,  1.37it/s]
1|1423|Loss: 0.9045791029930115:   5%|▌         | 1423/25880 [19:57<4:59:03,  1.36it/s]
1|1424|Loss: 0.8407143950462341:   5%|▌         | 1423/25880 [19:57<4:59:03,  1.36it/s]
1|1424|Loss: 0.8407143950462341:   6%|▌         | 1424/25880 [19:58<4:56:02,  1.38it/s]
1|1425|Loss: 1.0064448118209839:   6%|▌         | 1424/25880 [19:58<4:56:02,  1.38it/s]
1|1425|Loss: 1.0064448118209839:   6%|▌         | 1425/25880 [19:58<4:28:32,  1.52it/s]
1|1426|Loss: 0.8989339470863342:   6%|▌         | 1425/25880 [19:59<4:28:32,  1.52it/s]
1|1426|Loss: 0.8989339470863342:   6%|▌         | 1426/25880 [19:59<4:20:53,  1.56it/s]
1|1427|Loss: 0.8528618812561035:   6%|▌         | 1426/25880 [19:59<4:20:53,  1.56it/s]
1|1427|Loss: 0.8528618812561035:   6%|▌         | 1427/25880 [20:00<4:30:29,  1.51it/s]
1|1428|Loss: 0.8361174464225769:   6%|▌         | 1427/25880 [20:00<4:30:29,  1.51it/s]
1|1428|Loss: 0.8361174464225769:   6%|▌         | 1428/25880 [20:00<4:30:30,  1.51it/s]
1|1429|Loss: 0.9053767919540405:   6%|▌         | 1428/25880 [20:01<4:30:30,  1.51it/s]
1|1429|Loss: 0.9053767919540405:   6%|▌         | 1429/25880 [20:01<4:42:14,  1.44it/s]
1|1430|Loss: 0.8856250643730164:   6%|▌         | 1429/25880 [20:01<4:42:14,  1.44it/s]
1|1430|Loss: 0.8856250643730164:   6%|▌         | 1430/25880 [20:02<4:50:44,  1.40it/s]
1|1431|Loss: 1.0126838684082031:   6%|▌         | 1430/25880 [20:02<4:50:44,  1.40it/s]
1|1431|Loss: 1.0126838684082031:   6%|▌         | 1431/25880 [20:02<4:59:43,  1.36it/s]
1|1432|Loss: 1.4273532629013062:   6%|▌         | 1431/25880 [20:03<4:59:43,  1.36it/s]
1|1432|Loss: 1.4273532629013062:   6%|▌         | 1432/25880 [20:04<5:41:04,  1.19it/s]
1|1433|Loss: 1.0581856966018677:   6%|▌         | 1432/25880 [20:04<5:41:04,  1.19it/s]
1|1433|Loss: 1.0581856966018677:   6%|▌         | 1433/25880 [20:04<5:30:06,  1.23it/s]
1|1434|Loss: 1.0094244480133057:   6%|▌         | 1433/25880 [20:05<5:30:06,  1.23it/s]
1|1434|Loss: 1.0094244480133057:   6%|▌         | 1434/25880 [20:05<5:19:58,  1.27it/s]
1|1435|Loss: 0.8456778526306152:   6%|▌         | 1434/25880 [20:05<5:19:58,  1.27it/s]
1|1435|Loss: 0.8456778526306152:   6%|▌         | 1435/25880 [20:06<5:20:45,  1.27it/s]
1|1436|Loss: 0.9360323548316956:   6%|▌         | 1435/25880 [20:06<5:20:45,  1.27it/s]
1|1436|Loss: 0.9360323548316956:   6%|▌         | 1436/25880 [20:07<5:33:23,  1.22it/s]
1|1437|Loss: 0.8448207974433899:   6%|▌         | 1436/25880 [20:07<5:33:23,  1.22it/s]
1|1437|Loss: 0.8448207974433899:   6%|▌         | 1437/25880 [20:07<5:15:25,  1.29it/s]
1|1438|Loss: 0.9205691814422607:   6%|▌         | 1437/25880 [20:08<5:15:25,  1.29it/s]
1|1438|Loss: 0.9205691814422607:   6%|▌         | 1438/25880 [20:08<4:56:15,  1.38it/s]
1|1439|Loss: 1.048447847366333:   6%|▌         | 1438/25880 [20:08<4:56:15,  1.38it/s] 
1|1439|Loss: 1.048447847366333:   6%|▌         | 1439/25880 [20:09<4:33:00,  1.49it/s]
1|1440|Loss: 0.8052701354026794:   6%|▌         | 1439/25880 [20:09<4:33:00,  1.49it/s]
1|1440|Loss: 0.8052701354026794:   6%|▌         | 1440/25880 [20:09<4:42:11,  1.44it/s]
1|1441|Loss: 0.7827172875404358:   6%|▌         | 1440/25880 [20:10<4:42:11,  1.44it/s]
1|1441|Loss: 0.7827172875404358:   6%|▌         | 1441/25880 [20:10<4:30:39,  1.50it/s]
1|1442|Loss: 0.969957172870636:   6%|▌         | 1441/25880 [20:10<4:30:39,  1.50it/s] 
1|1442|Loss: 0.969957172870636:   6%|▌         | 1442/25880 [20:11<4:25:04,  1.54it/s]
1|1443|Loss: 0.8923332095146179:   6%|▌         | 1442/25880 [20:11<4:25:04,  1.54it/s]
1|1443|Loss: 0.8923332095146179:   6%|▌         | 1443/25880 [20:11<4:42:45,  1.44it/s]
1|1444|Loss: 0.8273696303367615:   6%|▌         | 1443/25880 [20:12<4:42:45,  1.44it/s]
1|1444|Loss: 0.8273696303367615:   6%|▌         | 1444/25880 [20:12<4:32:14,  1.50it/s]
1|1445|Loss: 0.904545783996582:   6%|▌         | 1444/25880 [20:12<4:32:14,  1.50it/s] 
1|1445|Loss: 0.904545783996582:   6%|▌         | 1445/25880 [20:13<4:26:01,  1.53it/s]
1|1446|Loss: 1.0409966707229614:   6%|▌         | 1445/25880 [20:13<4:26:01,  1.53it/s]
1|1446|Loss: 1.0409966707229614:   6%|▌         | 1446/25880 [20:13<4:11:54,  1.62it/s]
1|1447|Loss: 0.7966676354408264:   6%|▌         | 1446/25880 [20:13<4:11:54,  1.62it/s]
1|1447|Loss: 0.7966676354408264:   6%|▌         | 1447/25880 [20:14<4:16:53,  1.59it/s]
1|1448|Loss: 0.9151202440261841:   6%|▌         | 1447/25880 [20:14<4:16:53,  1.59it/s]
1|1448|Loss: 0.9151202440261841:   6%|▌         | 1448/25880 [20:14<4:12:39,  1.61it/s]
1|1449|Loss: 0.9438058733940125:   6%|▌         | 1448/25880 [20:15<4:12:39,  1.61it/s]
1|1449|Loss: 0.9438058733940125:   6%|▌         | 1449/25880 [20:15<4:34:05,  1.49it/s]
1|1450|Loss: 0.8501383662223816:   6%|▌         | 1449/25880 [20:16<4:34:05,  1.49it/s]
1|1450|Loss: 0.8501383662223816:   6%|▌         | 1450/25880 [20:16<4:33:34,  1.49it/s]
1|1451|Loss: 0.8964343070983887:   6%|▌         | 1450/25880 [20:16<4:33:34,  1.49it/s]
1|1451|Loss: 0.8964343070983887:   6%|▌         | 1451/25880 [20:16<4:28:58,  1.51it/s]
1|1452|Loss: 0.9205774068832397:   6%|▌         | 1451/25880 [20:17<4:28:58,  1.51it/s]
1|1452|Loss: 0.9205774068832397:   6%|▌         | 1452/25880 [20:17<4:45:11,  1.43it/s]
1|1453|Loss: 1.0558675527572632:   6%|▌         | 1452/25880 [20:18<4:45:11,  1.43it/s]
1|1453|Loss: 1.0558675527572632:   6%|▌         | 1453/25880 [20:18<4:50:23,  1.40it/s]
1|1454|Loss: 0.981066107749939:   6%|▌         | 1453/25880 [20:18<4:50:23,  1.40it/s] 
1|1454|Loss: 0.981066107749939:   6%|▌         | 1454/25880 [20:19<4:48:48,  1.41it/s]
1|1455|Loss: 0.8413927555084229:   6%|▌         | 1454/25880 [20:19<4:48:48,  1.41it/s]
1|1455|Loss: 0.8413927555084229:   6%|▌         | 1455/25880 [20:20<5:16:01,  1.29it/s]
1|1456|Loss: 1.014848232269287:   6%|▌         | 1455/25880 [20:20<5:16:01,  1.29it/s] 
1|1456|Loss: 1.014848232269287:   6%|▌         | 1456/25880 [20:20<5:20:07,  1.27it/s]
1|1457|Loss: 0.8481207489967346:   6%|▌         | 1456/25880 [20:21<5:20:07,  1.27it/s]
1|1457|Loss: 0.8481207489967346:   6%|▌         | 1457/25880 [20:21<5:11:19,  1.31it/s]
1|1458|Loss: 0.8924869894981384:   6%|▌         | 1457/25880 [20:22<5:11:19,  1.31it/s]
1|1458|Loss: 0.8924869894981384:   6%|▌         | 1458/25880 [20:22<5:17:48,  1.28it/s]
1|1459|Loss: 0.9783052802085876:   6%|▌         | 1458/25880 [20:22<5:17:48,  1.28it/s]
1|1459|Loss: 0.9783052802085876:   6%|▌         | 1459/25880 [20:23<5:15:25,  1.29it/s]
1|1460|Loss: 0.9380418658256531:   6%|▌         | 1459/25880 [20:23<5:15:25,  1.29it/s]
1|1460|Loss: 0.9380418658256531:   6%|▌         | 1460/25880 [20:23<5:10:28,  1.31it/s]
1|1461|Loss: 0.9512555003166199:   6%|▌         | 1460/25880 [20:24<5:10:28,  1.31it/s]
1|1461|Loss: 0.9512555003166199:   6%|▌         | 1461/25880 [20:24<5:12:17,  1.30it/s]
1|1462|Loss: 0.8932090401649475:   6%|▌         | 1461/25880 [20:25<5:12:17,  1.30it/s]
1|1462|Loss: 0.8932090401649475:   6%|▌         | 1462/25880 [20:25<5:21:17,  1.27it/s]
1|1463|Loss: 0.9288210272789001:   6%|▌         | 1462/25880 [20:25<5:21:17,  1.27it/s]
1|1463|Loss: 0.9288210272789001:   6%|▌         | 1463/25880 [20:26<5:06:49,  1.33it/s]
1|1464|Loss: 0.8347072005271912:   6%|▌         | 1463/25880 [20:26<5:06:49,  1.33it/s]
1|1464|Loss: 0.8347072005271912:   6%|▌         | 1464/25880 [20:26<5:01:03,  1.35it/s]
1|1465|Loss: 0.9350064396858215:   6%|▌         | 1464/25880 [20:27<5:01:03,  1.35it/s]
1|1465|Loss: 0.9350064396858215:   6%|▌         | 1465/25880 [20:27<5:09:28,  1.31it/s]
1|1466|Loss: 0.9525861740112305:   6%|▌         | 1465/25880 [20:28<5:09:28,  1.31it/s]
1|1466|Loss: 0.9525861740112305:   6%|▌         | 1466/25880 [20:28<4:59:59,  1.36it/s]
1|1467|Loss: 0.9764167666435242:   6%|▌         | 1466/25880 [20:28<4:59:59,  1.36it/s]
1|1467|Loss: 0.9764167666435242:   6%|▌         | 1467/25880 [20:29<4:48:14,  1.41it/s]
1|1468|Loss: 0.9261665940284729:   6%|▌         | 1467/25880 [20:29<4:48:14,  1.41it/s]
1|1468|Loss: 0.9261665940284729:   6%|▌         | 1468/25880 [20:29<4:35:19,  1.48it/s]
1|1469|Loss: 0.8538151979446411:   6%|▌         | 1468/25880 [20:30<4:35:19,  1.48it/s]
1|1469|Loss: 0.8538151979446411:   6%|▌         | 1469/25880 [20:30<4:38:48,  1.46it/s]
1|1470|Loss: 0.8926880359649658:   6%|▌         | 1469/25880 [20:30<4:38:48,  1.46it/s]
1|1470|Loss: 0.8926880359649658:   6%|▌         | 1470/25880 [20:31<4:44:37,  1.43it/s]
1|1471|Loss: 0.9163338541984558:   6%|▌         | 1470/25880 [20:31<4:44:37,  1.43it/s]
1|1471|Loss: 0.9163338541984558:   6%|▌         | 1471/25880 [20:31<4:55:01,  1.38it/s]
1|1472|Loss: 0.819622814655304:   6%|▌         | 1471/25880 [20:32<4:55:01,  1.38it/s] 
1|1472|Loss: 0.819622814655304:   6%|▌         | 1472/25880 [20:32<4:48:08,  1.41it/s]
1|1473|Loss: 0.9048357605934143:   6%|▌         | 1472/25880 [20:32<4:48:08,  1.41it/s]
1|1473|Loss: 0.9048357605934143:   6%|▌         | 1473/25880 [20:33<5:03:31,  1.34it/s]
1|1474|Loss: 0.911868155002594:   6%|▌         | 1473/25880 [20:33<5:03:31,  1.34it/s] 
1|1474|Loss: 0.911868155002594:   6%|▌         | 1474/25880 [20:34<5:07:08,  1.32it/s]
1|1475|Loss: 0.8754063248634338:   6%|▌         | 1474/25880 [20:34<5:07:08,  1.32it/s]
1|1475|Loss: 0.8754063248634338:   6%|▌         | 1475/25880 [20:35<5:17:39,  1.28it/s]
1|1476|Loss: 0.8395768404006958:   6%|▌         | 1475/25880 [20:35<5:17:39,  1.28it/s]
1|1476|Loss: 0.8395768404006958:   6%|▌         | 1476/25880 [20:35<5:11:43,  1.30it/s]
1|1477|Loss: 0.9711194634437561:   6%|▌         | 1476/25880 [20:36<5:11:43,  1.30it/s]
1|1477|Loss: 0.9711194634437561:   6%|▌         | 1477/25880 [20:36<5:28:33,  1.24it/s]
1|1478|Loss: 0.9267842173576355:   6%|▌         | 1477/25880 [20:37<5:28:33,  1.24it/s]
1|1478|Loss: 0.9267842173576355:   6%|▌         | 1478/25880 [20:37<5:21:55,  1.26it/s]
1|1479|Loss: 0.9221276640892029:   6%|▌         | 1478/25880 [20:37<5:21:55,  1.26it/s]
1|1479|Loss: 0.9221276640892029:   6%|▌         | 1479/25880 [20:38<5:01:32,  1.35it/s]
1|1480|Loss: 0.7795500159263611:   6%|▌         | 1479/25880 [20:38<5:01:32,  1.35it/s]
1|1480|Loss: 0.7795500159263611:   6%|▌         | 1480/25880 [20:38<5:15:55,  1.29it/s]
1|1481|Loss: 0.9479749202728271:   6%|▌         | 1480/25880 [20:39<5:15:55,  1.29it/s]
1|1481|Loss: 0.9479749202728271:   6%|▌         | 1481/25880 [20:39<5:05:34,  1.33it/s]
1|1482|Loss: 0.9179133176803589:   6%|▌         | 1481/25880 [20:39<5:05:34,  1.33it/s]
1|1482|Loss: 0.9179133176803589:   6%|▌         | 1482/25880 [20:40<5:01:01,  1.35it/s]
1|1483|Loss: 0.8786789774894714:   6%|▌         | 1482/25880 [20:40<5:01:01,  1.35it/s]
1|1483|Loss: 0.8786789774894714:   6%|▌         | 1483/25880 [20:41<5:05:49,  1.33it/s]
1|1484|Loss: 0.8803879022598267:   6%|▌         | 1483/25880 [20:41<5:05:49,  1.33it/s]
1|1484|Loss: 0.8803879022598267:   6%|▌         | 1484/25880 [20:41<5:15:13,  1.29it/s]
1|1485|Loss: 1.0561039447784424:   6%|▌         | 1484/25880 [20:42<5:15:13,  1.29it/s]
1|1485|Loss: 1.0561039447784424:   6%|▌         | 1485/25880 [20:42<5:13:07,  1.30it/s]
1|1486|Loss: 0.983920693397522:   6%|▌         | 1485/25880 [20:43<5:13:07,  1.30it/s] 
1|1486|Loss: 0.983920693397522:   6%|▌         | 1486/25880 [20:43<4:54:39,  1.38it/s]
1|1487|Loss: 0.7818312048912048:   6%|▌         | 1486/25880 [20:43<4:54:39,  1.38it/s]
1|1487|Loss: 0.7818312048912048:   6%|▌         | 1487/25880 [20:43<4:51:09,  1.40it/s]
1|1488|Loss: 0.9249915480613708:   6%|▌         | 1487/25880 [20:44<4:51:09,  1.40it/s]
1|1488|Loss: 0.9249915480613708:   6%|▌         | 1488/25880 [20:44<5:02:17,  1.34it/s]
1|1489|Loss: 0.8766390681266785:   6%|▌         | 1488/25880 [20:45<5:02:17,  1.34it/s]
1|1489|Loss: 0.8766390681266785:   6%|▌         | 1489/25880 [20:45<5:04:04,  1.34it/s]
1|1490|Loss: 1.057754635810852:   6%|▌         | 1489/25880 [20:45<5:04:04,  1.34it/s] 
1|1490|Loss: 1.057754635810852:   6%|▌         | 1490/25880 [20:46<4:53:48,  1.38it/s]
1|1491|Loss: 0.8218140006065369:   6%|▌         | 1490/25880 [20:46<4:53:48,  1.38it/s]
1|1491|Loss: 0.8218140006065369:   6%|▌         | 1491/25880 [20:46<4:44:00,  1.43it/s]
1|1492|Loss: 0.7863970994949341:   6%|▌         | 1491/25880 [20:47<4:44:00,  1.43it/s]
1|1492|Loss: 0.7863970994949341:   6%|▌         | 1492/25880 [20:47<4:48:16,  1.41it/s]
1|1493|Loss: 0.9820914268493652:   6%|▌         | 1492/25880 [20:48<4:48:16,  1.41it/s]
1|1493|Loss: 0.9820914268493652:   6%|▌         | 1493/25880 [20:48<5:02:53,  1.34it/s]
1|1494|Loss: 0.8841037750244141:   6%|▌         | 1493/25880 [20:48<5:02:53,  1.34it/s]
1|1494|Loss: 0.8841037750244141:   6%|▌         | 1494/25880 [20:49<4:56:02,  1.37it/s]
1|1495|Loss: 0.8782479763031006:   6%|▌         | 1494/25880 [20:49<4:56:02,  1.37it/s]
1|1495|Loss: 0.8782479763031006:   6%|▌         | 1495/25880 [20:49<5:04:18,  1.34it/s]
1|1496|Loss: 1.0013400316238403:   6%|▌         | 1495/25880 [20:50<5:04:18,  1.34it/s]
1|1496|Loss: 1.0013400316238403:   6%|▌         | 1496/25880 [20:50<5:04:21,  1.34it/s]
1|1497|Loss: 0.8248642086982727:   6%|▌         | 1496/25880 [20:51<5:04:21,  1.34it/s]
1|1497|Loss: 0.8248642086982727:   6%|▌         | 1497/25880 [20:51<4:59:16,  1.36it/s]
1|1498|Loss: 0.7978609204292297:   6%|▌         | 1497/25880 [20:51<4:59:16,  1.36it/s]
1|1498|Loss: 0.7978609204292297:   6%|▌         | 1498/25880 [20:52<5:10:34,  1.31it/s]
1|1499|Loss: 0.6834606528282166:   6%|▌         | 1498/25880 [20:52<5:10:34,  1.31it/s]
1|1499|Loss: 0.6834606528282166:   6%|▌         | 1499/25880 [20:52<4:43:44,  1.43it/s]
1|1500|Loss: 0.8167489767074585:   6%|▌         | 1499/25880 [20:53<4:43:44,  1.43it/s]
1|1500|Loss: 0.8167489767074585:   6%|▌         | 1500/25880 [20:53<4:37:44,  1.46it/s]
1|1501|Loss: 0.8664286136627197:   6%|▌         | 1500/25880 [20:53<4:37:44,  1.46it/s]
1|1501|Loss: 0.8664286136627197:   6%|▌         | 1501/25880 [20:54<5:01:03,  1.35it/s]
1|1502|Loss: 0.9726648330688477:   6%|▌         | 1501/25880 [20:54<5:01:03,  1.35it/s]
1|1502|Loss: 0.9726648330688477:   6%|▌         | 1502/25880 [20:54<4:55:31,  1.37it/s]
1|1503|Loss: 0.980538010597229:   6%|▌         | 1502/25880 [20:55<4:55:31,  1.37it/s] 
1|1503|Loss: 0.980538010597229:   6%|▌         | 1503/25880 [20:55<4:54:13,  1.38it/s]
1|1504|Loss: 0.8378322720527649:   6%|▌         | 1503/25880 [20:56<4:54:13,  1.38it/s]
1|1504|Loss: 0.8378322720527649:   6%|▌         | 1504/25880 [20:56<5:00:20,  1.35it/s]
1|1505|Loss: 0.9684833884239197:   6%|▌         | 1504/25880 [20:56<5:00:20,  1.35it/s]
1|1505|Loss: 0.9684833884239197:   6%|▌         | 1505/25880 [20:57<5:07:36,  1.32it/s]
1|1506|Loss: 0.8712760806083679:   6%|▌         | 1505/25880 [20:57<5:07:36,  1.32it/s]
1|1506|Loss: 0.8712760806083679:   6%|▌         | 1506/25880 [20:57<5:05:06,  1.33it/s]
1|1507|Loss: 0.8804094791412354:   6%|▌         | 1506/25880 [20:58<5:05:06,  1.33it/s]
1|1507|Loss: 0.8804094791412354:   6%|▌         | 1507/25880 [20:58<5:01:46,  1.35it/s]
1|1508|Loss: 0.7927500009536743:   6%|▌         | 1507/25880 [20:59<5:01:46,  1.35it/s]
1|1508|Loss: 0.7927500009536743:   6%|▌         | 1508/25880 [20:59<5:11:40,  1.30it/s]
1|1509|Loss: 0.8114035129547119:   6%|▌         | 1508/25880 [20:59<5:11:40,  1.30it/s]
1|1509|Loss: 0.8114035129547119:   6%|▌         | 1509/25880 [21:00<5:26:17,  1.24it/s]
1|1510|Loss: 0.8886551856994629:   6%|▌         | 1509/25880 [21:00<5:26:17,  1.24it/s]
1|1510|Loss: 0.8886551856994629:   6%|▌         | 1510/25880 [21:01<5:32:16,  1.22it/s]
1|1511|Loss: 0.8098525404930115:   6%|▌         | 1510/25880 [21:01<5:32:16,  1.22it/s]
1|1511|Loss: 0.8098525404930115:   6%|▌         | 1511/25880 [21:02<5:35:41,  1.21it/s]
1|1512|Loss: 0.9673669934272766:   6%|▌         | 1511/25880 [21:02<5:35:41,  1.21it/s]
1|1512|Loss: 0.9673669934272766:   6%|▌         | 1512/25880 [21:02<5:18:55,  1.27it/s]
1|1513|Loss: 0.7607635855674744:   6%|▌         | 1512/25880 [21:03<5:18:55,  1.27it/s]
1|1513|Loss: 0.7607635855674744:   6%|▌         | 1513/25880 [21:03<5:06:49,  1.32it/s]
1|1514|Loss: 0.868930995464325:   6%|▌         | 1513/25880 [21:03<5:06:49,  1.32it/s] 
1|1514|Loss: 0.868930995464325:   6%|▌         | 1514/25880 [21:04<5:21:43,  1.26it/s]
1|1515|Loss: 0.8973818421363831:   6%|▌         | 1514/25880 [21:04<5:21:43,  1.26it/s]
1|1515|Loss: 0.8973818421363831:   6%|▌         | 1515/25880 [21:05<5:08:06,  1.32it/s]
1|1516|Loss: 0.8642770051956177:   6%|▌         | 1515/25880 [21:05<5:08:06,  1.32it/s]
1|1516|Loss: 0.8642770051956177:   6%|▌         | 1516/25880 [21:05<5:14:02,  1.29it/s]
1|1517|Loss: 0.8616887331008911:   6%|▌         | 1516/25880 [21:06<5:14:02,  1.29it/s]
1|1517|Loss: 0.8616887331008911:   6%|▌         | 1517/25880 [21:06<4:57:40,  1.36it/s]
1|1518|Loss: 0.7882732152938843:   6%|▌         | 1517/25880 [21:06<4:57:40,  1.36it/s]
1|1518|Loss: 0.7882732152938843:   6%|▌         | 1518/25880 [21:07<4:50:31,  1.40it/s]
1|1519|Loss: 0.9705277681350708:   6%|▌         | 1518/25880 [21:07<4:50:31,  1.40it/s]
1|1519|Loss: 0.9705277681350708:   6%|▌         | 1519/25880 [21:08<5:09:50,  1.31it/s]
1|1520|Loss: 0.8306757211685181:   6%|▌         | 1519/25880 [21:08<5:09:50,  1.31it/s]
1|1520|Loss: 0.8306757211685181:   6%|▌         | 1520/25880 [21:08<5:20:07,  1.27it/s]
1|1521|Loss: 0.7991619110107422:   6%|▌         | 1520/25880 [21:09<5:20:07,  1.27it/s]
1|1521|Loss: 0.7991619110107422:   6%|▌         | 1521/25880 [21:09<5:11:53,  1.30it/s]
1|1522|Loss: 0.9130069613456726:   6%|▌         | 1521/25880 [21:09<5:11:53,  1.30it/s]
1|1522|Loss: 0.9130069613456726:   6%|▌         | 1522/25880 [21:10<5:03:43,  1.34it/s]
1|1523|Loss: 0.8637932538986206:   6%|▌         | 1522/25880 [21:10<5:03:43,  1.34it/s]
1|1523|Loss: 0.8637932538986206:   6%|▌         | 1523/25880 [21:10<4:39:06,  1.45it/s]
1|1524|Loss: 0.8081281781196594:   6%|▌         | 1523/25880 [21:11<4:39:06,  1.45it/s]
1|1524|Loss: 0.8081281781196594:   6%|▌         | 1524/25880 [21:11<4:35:58,  1.47it/s]
1|1525|Loss: 0.9115468263626099:   6%|▌         | 1524/25880 [21:11<4:35:58,  1.47it/s]
1|1525|Loss: 0.9115468263626099:   6%|▌         | 1525/25880 [21:12<4:17:05,  1.58it/s]
1|1526|Loss: 0.8934781551361084:   6%|▌         | 1525/25880 [21:12<4:17:05,  1.58it/s]
1|1526|Loss: 0.8934781551361084:   6%|▌         | 1526/25880 [21:12<4:13:57,  1.60it/s]
1|1527|Loss: 0.8893522024154663:   6%|▌         | 1526/25880 [21:13<4:13:57,  1.60it/s]
1|1527|Loss: 0.8893522024154663:   6%|▌         | 1527/25880 [21:13<4:24:41,  1.53it/s]
1|1528|Loss: 0.8831617832183838:   6%|▌         | 1527/25880 [21:13<4:24:41,  1.53it/s]
1|1528|Loss: 0.8831617832183838:   6%|▌         | 1528/25880 [21:14<4:47:26,  1.41it/s]
1|1529|Loss: 0.7690548896789551:   6%|▌         | 1528/25880 [21:14<4:47:26,  1.41it/s]
1|1529|Loss: 0.7690548896789551:   6%|▌         | 1529/25880 [21:15<5:37:18,  1.20it/s]
1|1530|Loss: 0.9348936080932617:   6%|▌         | 1529/25880 [21:15<5:37:18,  1.20it/s]
1|1530|Loss: 0.9348936080932617:   6%|▌         | 1530/25880 [21:16<5:21:43,  1.26it/s]
1|1531|Loss: 0.9479044675827026:   6%|▌         | 1530/25880 [21:16<5:21:43,  1.26it/s]
1|1531|Loss: 0.9479044675827026:   6%|▌         | 1531/25880 [21:16<5:15:39,  1.29it/s]
1|1532|Loss: 0.8638970851898193:   6%|▌         | 1531/25880 [21:17<5:15:39,  1.29it/s]
1|1532|Loss: 0.8638970851898193:   6%|▌         | 1532/25880 [21:17<5:03:37,  1.34it/s]
1|1533|Loss: 0.9876587986946106:   6%|▌         | 1532/25880 [21:17<5:03:37,  1.34it/s]
1|1533|Loss: 0.9876587986946106:   6%|▌         | 1533/25880 [21:18<4:48:50,  1.40it/s]
1|1534|Loss: 0.8354372382164001:   6%|▌         | 1533/25880 [21:18<4:48:50,  1.40it/s]
1|1534|Loss: 0.8354372382164001:   6%|▌         | 1534/25880 [21:18<4:58:02,  1.36it/s]
1|1535|Loss: 0.994055986404419:   6%|▌         | 1534/25880 [21:19<4:58:02,  1.36it/s] 
1|1535|Loss: 0.994055986404419:   6%|▌         | 1535/25880 [21:19<4:42:29,  1.44it/s]
1|1536|Loss: 0.8852141499519348:   6%|▌         | 1535/25880 [21:19<4:42:29,  1.44it/s]
1|1536|Loss: 0.8852141499519348:   6%|▌         | 1536/25880 [21:20<4:30:54,  1.50it/s]
1|1537|Loss: 0.9504990577697754:   6%|▌         | 1536/25880 [21:20<4:30:54,  1.50it/s]
1|1537|Loss: 0.9504990577697754:   6%|▌         | 1537/25880 [21:20<4:47:24,  1.41it/s]
1|1538|Loss: 0.7840315103530884:   6%|▌         | 1537/25880 [21:21<4:47:24,  1.41it/s]
1|1538|Loss: 0.7840315103530884:   6%|▌         | 1538/25880 [21:21<5:23:15,  1.26it/s]
1|1539|Loss: 0.8869490027427673:   6%|▌         | 1538/25880 [21:22<5:23:15,  1.26it/s]
1|1539|Loss: 0.8869490027427673:   6%|▌         | 1539/25880 [21:22<5:15:38,  1.29it/s]
1|1540|Loss: 0.7858606576919556:   6%|▌         | 1539/25880 [21:22<5:15:38,  1.29it/s]
1|1540|Loss: 0.7858606576919556:   6%|▌         | 1540/25880 [21:23<5:04:29,  1.33it/s]
1|1541|Loss: 0.8159616589546204:   6%|▌         | 1540/25880 [21:23<5:04:29,  1.33it/s]
1|1541|Loss: 0.8159616589546204:   6%|▌         | 1541/25880 [21:23<4:44:03,  1.43it/s]
1|1542|Loss: 0.8940750360488892:   6%|▌         | 1541/25880 [21:24<4:44:03,  1.43it/s]
1|1542|Loss: 0.8940750360488892:   6%|▌         | 1542/25880 [21:24<4:53:45,  1.38it/s]
1|1543|Loss: 0.8345547318458557:   6%|▌         | 1542/25880 [21:25<4:53:45,  1.38it/s]
1|1543|Loss: 0.8345547318458557:   6%|▌         | 1543/25880 [21:25<4:56:28,  1.37it/s]
1|1544|Loss: 0.8157174587249756:   6%|▌         | 1543/25880 [21:25<4:56:28,  1.37it/s]
1|1544|Loss: 0.8157174587249756:   6%|▌         | 1544/25880 [21:25<4:32:56,  1.49it/s]
1|1545|Loss: 1.1293821334838867:   6%|▌         | 1544/25880 [21:26<4:32:56,  1.49it/s]
1|1545|Loss: 1.1293821334838867:   6%|▌         | 1545/25880 [21:26<4:35:53,  1.47it/s]
1|1546|Loss: 0.9076155424118042:   6%|▌         | 1545/25880 [21:27<4:35:53,  1.47it/s]
1|1546|Loss: 0.9076155424118042:   6%|▌         | 1546/25880 [21:27<5:00:37,  1.35it/s]
1|1547|Loss: 1.0434507131576538:   6%|▌         | 1546/25880 [21:27<5:00:37,  1.35it/s]
1|1547|Loss: 1.0434507131576538:   6%|▌         | 1547/25880 [21:28<5:01:16,  1.35it/s]
1|1548|Loss: 0.8407968282699585:   6%|▌         | 1547/25880 [21:28<5:01:16,  1.35it/s]
1|1548|Loss: 0.8407968282699585:   6%|▌         | 1548/25880 [21:29<5:10:44,  1.31it/s]
1|1549|Loss: 0.9543201923370361:   6%|▌         | 1548/25880 [21:29<5:10:44,  1.31it/s]
1|1549|Loss: 0.9543201923370361:   6%|▌         | 1549/25880 [21:29<5:10:31,  1.31it/s]
1|1550|Loss: 0.8123995065689087:   6%|▌         | 1549/25880 [21:30<5:10:31,  1.31it/s]
1|1550|Loss: 0.8123995065689087:   6%|▌         | 1550/25880 [21:30<4:52:29,  1.39it/s]
1|1551|Loss: 0.9763150811195374:   6%|▌         | 1550/25880 [21:30<4:52:29,  1.39it/s]
1|1551|Loss: 0.9763150811195374:   6%|▌         | 1551/25880 [21:31<4:47:12,  1.41it/s]
1|1552|Loss: 0.9307674765586853:   6%|▌         | 1551/25880 [21:31<4:47:12,  1.41it/s]
1|1552|Loss: 0.9307674765586853:   6%|▌         | 1552/25880 [21:31<4:58:06,  1.36it/s]
1|1553|Loss: 0.9002774357795715:   6%|▌         | 1552/25880 [21:32<4:58:06,  1.36it/s]
1|1553|Loss: 0.9002774357795715:   6%|▌         | 1553/25880 [21:32<5:00:24,  1.35it/s]
1|1554|Loss: 0.9045907258987427:   6%|▌         | 1553/25880 [21:33<5:00:24,  1.35it/s]
1|1554|Loss: 0.9045907258987427:   6%|▌         | 1554/25880 [21:33<4:40:32,  1.45it/s]
1|1555|Loss: 0.8794950842857361:   6%|▌         | 1554/25880 [21:33<4:40:32,  1.45it/s]
1|1555|Loss: 0.8794950842857361:   6%|▌         | 1555/25880 [21:33<4:40:50,  1.44it/s]
1|1556|Loss: 0.8392117023468018:   6%|▌         | 1555/25880 [21:34<4:40:50,  1.44it/s]
1|1556|Loss: 0.8392117023468018:   6%|▌         | 1556/25880 [21:34<4:19:00,  1.57it/s]
1|1557|Loss: 0.6830366849899292:   6%|▌         | 1556/25880 [21:34<4:19:00,  1.57it/s]
1|1557|Loss: 0.6830366849899292:   6%|▌         | 1557/25880 [21:35<4:22:56,  1.54it/s]
1|1558|Loss: 0.7615254521369934:   6%|▌         | 1557/25880 [21:35<4:22:56,  1.54it/s]
1|1558|Loss: 0.7615254521369934:   6%|▌         | 1558/25880 [21:35<4:21:29,  1.55it/s]
1|1559|Loss: 0.878616213798523:   6%|▌         | 1558/25880 [21:36<4:21:29,  1.55it/s] 
1|1559|Loss: 0.878616213798523:   6%|▌         | 1559/25880 [21:36<4:15:35,  1.59it/s]
1|1560|Loss: 0.8774509429931641:   6%|▌         | 1559/25880 [21:36<4:15:35,  1.59it/s]
1|1560|Loss: 0.8774509429931641:   6%|▌         | 1560/25880 [21:37<4:14:45,  1.59it/s]
1|1561|Loss: 0.9323005676269531:   6%|▌         | 1560/25880 [21:37<4:14:45,  1.59it/s]
1|1561|Loss: 0.9323005676269531:   6%|▌         | 1561/25880 [21:37<4:31:50,  1.49it/s]
1|1562|Loss: 0.9051945209503174:   6%|▌         | 1561/25880 [21:38<4:31:50,  1.49it/s]
1|1562|Loss: 0.9051945209503174:   6%|▌         | 1562/25880 [21:38<4:31:36,  1.49it/s]
1|1563|Loss: 0.9752857685089111:   6%|▌         | 1562/25880 [21:38<4:31:36,  1.49it/s]
1|1563|Loss: 0.9752857685089111:   6%|▌         | 1563/25880 [21:39<4:19:26,  1.56it/s]
1|1564|Loss: 0.78351891040802:   6%|▌         | 1563/25880 [21:39<4:19:26,  1.56it/s]  
1|1564|Loss: 0.78351891040802:   6%|▌         | 1564/25880 [21:39<4:35:49,  1.47it/s]
1|1565|Loss: 0.8418306112289429:   6%|▌         | 1564/25880 [21:40<4:35:49,  1.47it/s]
1|1565|Loss: 0.8418306112289429:   6%|▌         | 1565/25880 [21:40<4:55:22,  1.37it/s]
1|1566|Loss: 0.8067600727081299:   6%|▌         | 1565/25880 [21:41<4:55:22,  1.37it/s]
1|1566|Loss: 0.8067600727081299:   6%|▌         | 1566/25880 [21:41<4:59:06,  1.35it/s]
1|1567|Loss: 0.9358185529708862:   6%|▌         | 1566/25880 [21:41<4:59:06,  1.35it/s]
1|1567|Loss: 0.9358185529708862:   6%|▌         | 1567/25880 [21:41<4:38:13,  1.46it/s]
1|1568|Loss: 1.0857168436050415:   6%|▌         | 1567/25880 [21:42<4:38:13,  1.46it/s]
1|1568|Loss: 1.0857168436050415:   6%|▌         | 1568/25880 [21:42<4:47:38,  1.41it/s]
1|1569|Loss: 0.9053514003753662:   6%|▌         | 1568/25880 [21:43<4:47:38,  1.41it/s]
1|1569|Loss: 0.9053514003753662:   6%|▌         | 1569/25880 [21:43<4:57:51,  1.36it/s]
1|1570|Loss: 0.8892583250999451:   6%|▌         | 1569/25880 [21:43<4:57:51,  1.36it/s]
1|1570|Loss: 0.8892583250999451:   6%|▌         | 1570/25880 [21:44<5:00:25,  1.35it/s]
1|1571|Loss: 0.7885804772377014:   6%|▌         | 1570/25880 [21:44<5:00:25,  1.35it/s]
1|1571|Loss: 0.7885804772377014:   6%|▌         | 1571/25880 [21:44<4:44:40,  1.42it/s]
1|1572|Loss: 0.907050609588623:   6%|▌         | 1571/25880 [21:45<4:44:40,  1.42it/s] 
1|1572|Loss: 0.907050609588623:   6%|▌         | 1572/25880 [21:45<4:33:19,  1.48it/s]
1|1573|Loss: 0.9146115183830261:   6%|▌         | 1572/25880 [21:45<4:33:19,  1.48it/s]
1|1573|Loss: 0.9146115183830261:   6%|▌         | 1573/25880 [21:46<4:25:46,  1.52it/s]
1|1574|Loss: 0.799044668674469:   6%|▌         | 1573/25880 [21:46<4:25:46,  1.52it/s] 
1|1574|Loss: 0.799044668674469:   6%|▌         | 1574/25880 [21:46<4:31:15,  1.49it/s]
1|1575|Loss: 0.8294841051101685:   6%|▌         | 1574/25880 [21:47<4:31:15,  1.49it/s]
1|1575|Loss: 0.8294841051101685:   6%|▌         | 1575/25880 [21:47<4:45:47,  1.42it/s]
1|1576|Loss: 0.7654128670692444:   6%|▌         | 1575/25880 [21:48<4:45:47,  1.42it/s]
1|1576|Loss: 0.7654128670692444:   6%|▌         | 1576/25880 [21:48<4:50:58,  1.39it/s]
1|1577|Loss: 0.8654682636260986:   6%|▌         | 1576/25880 [21:48<4:50:58,  1.39it/s]
1|1577|Loss: 0.8654682636260986:   6%|▌         | 1577/25880 [21:49<5:03:39,  1.33it/s]
1|1578|Loss: 0.8422743082046509:   6%|▌         | 1577/25880 [21:49<5:03:39,  1.33it/s]
1|1578|Loss: 0.8422743082046509:   6%|▌         | 1578/25880 [21:49<5:04:13,  1.33it/s]
1|1579|Loss: 0.8884157538414001:   6%|▌         | 1578/25880 [21:50<5:04:13,  1.33it/s]
1|1579|Loss: 0.8884157538414001:   6%|▌         | 1579/25880 [21:50<4:49:45,  1.40it/s]
1|1580|Loss: 0.9493159651756287:   6%|▌         | 1579/25880 [21:50<4:49:45,  1.40it/s]
1|1580|Loss: 0.9493159651756287:   6%|▌         | 1580/25880 [21:51<4:59:11,  1.35it/s]
1|1581|Loss: 0.7234219908714294:   6%|▌         | 1580/25880 [21:51<4:59:11,  1.35it/s]
1|1581|Loss: 0.7234219908714294:   6%|▌         | 1581/25880 [21:52<5:25:29,  1.24it/s]
1|1582|Loss: 0.8075312376022339:   6%|▌         | 1581/25880 [21:52<5:25:29,  1.24it/s]
1|1582|Loss: 0.8075312376022339:   6%|▌         | 1582/25880 [21:53<5:20:52,  1.26it/s]
1|1583|Loss: 0.8052831888198853:   6%|▌         | 1582/25880 [21:53<5:20:52,  1.26it/s]
1|1583|Loss: 0.8052831888198853:   6%|▌         | 1583/25880 [21:53<5:11:42,  1.30it/s]
1|1584|Loss: 0.9245456457138062:   6%|▌         | 1583/25880 [21:54<5:11:42,  1.30it/s]
1|1584|Loss: 0.9245456457138062:   6%|▌         | 1584/25880 [21:54<4:57:30,  1.36it/s]
1|1585|Loss: 0.8979369401931763:   6%|▌         | 1584/25880 [21:54<4:57:30,  1.36it/s]
1|1585|Loss: 0.8979369401931763:   6%|▌         | 1585/25880 [21:55<4:41:09,  1.44it/s]
1|1586|Loss: 0.78888338804245:   6%|▌         | 1585/25880 [21:55<4:41:09,  1.44it/s]  
1|1586|Loss: 0.78888338804245:   6%|▌         | 1586/25880 [21:55<4:41:57,  1.44it/s]
1|1587|Loss: 0.8917317390441895:   6%|▌         | 1586/25880 [21:56<4:41:57,  1.44it/s]
1|1587|Loss: 0.8917317390441895:   6%|▌         | 1587/25880 [21:56<4:18:58,  1.56it/s]
1|1588|Loss: 0.9923632144927979:   6%|▌         | 1587/25880 [21:56<4:18:58,  1.56it/s]
1|1588|Loss: 0.9923632144927979:   6%|▌         | 1588/25880 [21:56<4:03:25,  1.66it/s]
1|1589|Loss: 0.8793179392814636:   6%|▌         | 1588/25880 [21:57<4:03:25,  1.66it/s]
1|1589|Loss: 0.8793179392814636:   6%|▌         | 1589/25880 [21:57<4:11:29,  1.61it/s]
1|1590|Loss: 0.8730183839797974:   6%|▌         | 1589/25880 [21:57<4:11:29,  1.61it/s]
1|1590|Loss: 0.8730183839797974:   6%|▌         | 1590/25880 [21:58<4:38:07,  1.46it/s]
1|1591|Loss: 0.6650652289390564:   6%|▌         | 1590/25880 [21:58<4:38:07,  1.46it/s]
1|1591|Loss: 0.6650652289390564:   6%|▌         | 1591/25880 [21:59<4:59:19,  1.35it/s]
1|1592|Loss: 0.9416584372520447:   6%|▌         | 1591/25880 [21:59<4:59:19,  1.35it/s]
1|1592|Loss: 0.9416584372520447:   6%|▌         | 1592/25880 [21:59<4:51:14,  1.39it/s]
1|1593|Loss: 0.8780555725097656:   6%|▌         | 1592/25880 [22:00<4:51:14,  1.39it/s]
1|1593|Loss: 0.8780555725097656:   6%|▌         | 1593/25880 [22:00<5:01:35,  1.34it/s]
1|1594|Loss: 0.9993847012519836:   6%|▌         | 1593/25880 [22:01<5:01:35,  1.34it/s]
1|1594|Loss: 0.9993847012519836:   6%|▌         | 1594/25880 [22:01<5:14:38,  1.29it/s]
1|1595|Loss: 1.0050679445266724:   6%|▌         | 1594/25880 [22:01<5:14:38,  1.29it/s]
1|1595|Loss: 1.0050679445266724:   6%|▌         | 1595/25880 [22:02<5:31:09,  1.22it/s]
1|1596|Loss: 0.8571215271949768:   6%|▌         | 1595/25880 [22:02<5:31:09,  1.22it/s]
1|1596|Loss: 0.8571215271949768:   6%|▌         | 1596/25880 [22:03<5:16:35,  1.28it/s]
1|1597|Loss: 0.9336360692977905:   6%|▌         | 1596/25880 [22:03<5:16:35,  1.28it/s]
1|1597|Loss: 0.9336360692977905:   6%|▌         | 1597/25880 [22:03<5:08:38,  1.31it/s]
1|1598|Loss: 0.7087387442588806:   6%|▌         | 1597/25880 [22:04<5:08:38,  1.31it/s]
1|1598|Loss: 0.7087387442588806:   6%|▌         | 1598/25880 [22:04<5:15:54,  1.28it/s]
1|1599|Loss: 1.0081076622009277:   6%|▌         | 1598/25880 [22:05<5:15:54,  1.28it/s]
1|1599|Loss: 1.0081076622009277:   6%|▌         | 1599/25880 [22:05<5:14:21,  1.29it/s]
1|1600|Loss: 0.7549096345901489:   6%|▌         | 1599/25880 [22:05<5:14:21,  1.29it/s]
1|1600|Loss: 0.7549096345901489:   6%|▌         | 1600/25880 [22:06<4:57:46,  1.36it/s]
1|1601|Loss: 1.0109622478485107:   6%|▌         | 1600/25880 [22:06<4:57:46,  1.36it/s]
1|1601|Loss: 1.0109622478485107:   6%|▌         | 1601/25880 [22:06<4:51:46,  1.39it/s]
1|1602|Loss: 0.8147277235984802:   6%|▌         | 1601/25880 [22:07<4:51:46,  1.39it/s]
1|1602|Loss: 0.8147277235984802:   6%|▌         | 1602/25880 [22:07<5:01:54,  1.34it/s]
1|1603|Loss: 0.8584645390510559:   6%|▌         | 1602/25880 [22:07<5:01:54,  1.34it/s]
1|1603|Loss: 0.8584645390510559:   6%|▌         | 1603/25880 [22:08<5:16:04,  1.28it/s]
1|1604|Loss: 0.7860695123672485:   6%|▌         | 1603/25880 [22:08<5:16:04,  1.28it/s]
1|1604|Loss: 0.7860695123672485:   6%|▌         | 1604/25880 [22:09<5:03:21,  1.33it/s]
1|1605|Loss: 0.9920600056648254:   6%|▌         | 1604/25880 [22:09<5:03:21,  1.33it/s]
1|1605|Loss: 0.9920600056648254:   6%|▌         | 1605/25880 [22:09<5:10:16,  1.30it/s]
1|1606|Loss: 0.8555694818496704:   6%|▌         | 1605/25880 [22:10<5:10:16,  1.30it/s]
1|1606|Loss: 0.8555694818496704:   6%|▌         | 1606/25880 [22:10<4:59:36,  1.35it/s]
1|1607|Loss: 1.0165013074874878:   6%|▌         | 1606/25880 [22:10<4:59:36,  1.35it/s]
1|1607|Loss: 1.0165013074874878:   6%|▌         | 1607/25880 [22:11<4:46:49,  1.41it/s]
1|1608|Loss: 0.8182984590530396:   6%|▌         | 1607/25880 [22:11<4:46:49,  1.41it/s]
1|1608|Loss: 0.8182984590530396:   6%|▌         | 1608/25880 [22:11<4:43:41,  1.43it/s]
1|1609|Loss: 0.7699023485183716:   6%|▌         | 1608/25880 [22:12<4:43:41,  1.43it/s]
1|1609|Loss: 0.7699023485183716:   6%|▌         | 1609/25880 [22:12<4:55:33,  1.37it/s]
1|1610|Loss: 0.8241317868232727:   6%|▌         | 1609/25880 [22:13<4:55:33,  1.37it/s]
1|1610|Loss: 0.8241317868232727:   6%|▌         | 1610/25880 [22:13<4:45:58,  1.41it/s]
1|1611|Loss: 0.8410172462463379:   6%|▌         | 1610/25880 [22:13<4:45:58,  1.41it/s]
1|1611|Loss: 0.8410172462463379:   6%|▌         | 1611/25880 [22:14<4:58:02,  1.36it/s]
1|1612|Loss: 0.9551360607147217:   6%|▌         | 1611/25880 [22:14<4:58:02,  1.36it/s]
1|1612|Loss: 0.9551360607147217:   6%|▌         | 1612/25880 [22:14<4:58:35,  1.35it/s]
1|1613|Loss: 0.826913058757782:   6%|▌         | 1612/25880 [22:15<4:58:35,  1.35it/s] 
1|1613|Loss: 0.826913058757782:   6%|▌         | 1613/25880 [22:15<5:14:47,  1.28it/s]
1|1614|Loss: 1.004560947418213:   6%|▌         | 1613/25880 [22:16<5:14:47,  1.28it/s]
1|1614|Loss: 1.004560947418213:   6%|▌         | 1614/25880 [22:16<5:23:25,  1.25it/s]
1|1615|Loss: 0.9010164141654968:   6%|▌         | 1614/25880 [22:16<5:23:25,  1.25it/s]
1|1615|Loss: 0.9010164141654968:   6%|▌         | 1615/25880 [22:17<5:00:14,  1.35it/s]
1|1616|Loss: 0.7990955114364624:   6%|▌         | 1615/25880 [22:17<5:00:14,  1.35it/s]
1|1616|Loss: 0.7990955114364624:   6%|▌         | 1616/25880 [22:18<5:19:33,  1.27it/s]
1|1617|Loss: 0.8253001570701599:   6%|▌         | 1616/25880 [22:18<5:19:33,  1.27it/s]
1|1617|Loss: 0.8253001570701599:   6%|▌         | 1617/25880 [22:18<5:11:01,  1.30it/s]
1|1618|Loss: 1.0374996662139893:   6%|▌         | 1617/25880 [22:19<5:11:01,  1.30it/s]
1|1618|Loss: 1.0374996662139893:   6%|▋         | 1618/25880 [22:19<4:49:51,  1.40it/s]
1|1619|Loss: 0.9663203358650208:   6%|▋         | 1618/25880 [22:19<4:49:51,  1.40it/s]
1|1619|Loss: 0.9663203358650208:   6%|▋         | 1619/25880 [22:20<4:39:12,  1.45it/s]
1|1620|Loss: 0.8305080533027649:   6%|▋         | 1619/25880 [22:20<4:39:12,  1.45it/s]
1|1620|Loss: 0.8305080533027649:   6%|▋         | 1620/25880 [22:20<4:44:40,  1.42it/s]
1|1621|Loss: 0.7314786911010742:   6%|▋         | 1620/25880 [22:21<4:44:40,  1.42it/s]
1|1621|Loss: 0.7314786911010742:   6%|▋         | 1621/25880 [22:21<4:59:43,  1.35it/s]
1|1622|Loss: 0.902520477771759:   6%|▋         | 1621/25880 [22:22<4:59:43,  1.35it/s] 
1|1622|Loss: 0.902520477771759:   6%|▋         | 1622/25880 [22:22<5:19:31,  1.27it/s]
1|1623|Loss: 0.9680770039558411:   6%|▋         | 1622/25880 [22:22<5:19:31,  1.27it/s]
1|1623|Loss: 0.9680770039558411:   6%|▋         | 1623/25880 [22:23<5:16:26,  1.28it/s]
1|1624|Loss: 1.0853198766708374:   6%|▋         | 1623/25880 [22:23<5:16:26,  1.28it/s]
1|1624|Loss: 1.0853198766708374:   6%|▋         | 1624/25880 [22:24<5:15:43,  1.28it/s]
1|1625|Loss: 1.3603256940841675:   6%|▋         | 1624/25880 [22:24<5:15:43,  1.28it/s]
1|1625|Loss: 1.3603256940841675:   6%|▋         | 1625/25880 [22:24<5:11:07,  1.30it/s]
1|1626|Loss: 1.0226627588272095:   6%|▋         | 1625/25880 [22:25<5:11:07,  1.30it/s]
1|1626|Loss: 1.0226627588272095:   6%|▋         | 1626/25880 [22:25<4:39:12,  1.45it/s]
1|1627|Loss: 1.0483771562576294:   6%|▋         | 1626/25880 [22:25<4:39:12,  1.45it/s]
1|1627|Loss: 1.0483771562576294:   6%|▋         | 1627/25880 [22:25<4:38:29,  1.45it/s]
1|1628|Loss: 0.9906942844390869:   6%|▋         | 1627/25880 [22:26<4:38:29,  1.45it/s]
1|1628|Loss: 0.9906942844390869:   6%|▋         | 1628/25880 [22:26<4:42:16,  1.43it/s]
1|1629|Loss: 1.0009459257125854:   6%|▋         | 1628/25880 [22:27<4:42:16,  1.43it/s]
1|1629|Loss: 1.0009459257125854:   6%|▋         | 1629/25880 [22:27<5:04:22,  1.33it/s]
1|1630|Loss: 0.9008427858352661:   6%|▋         | 1629/25880 [22:27<5:04:22,  1.33it/s]
1|1630|Loss: 0.9008427858352661:   6%|▋         | 1630/25880 [22:28<4:31:13,  1.49it/s]
1|1631|Loss: 0.8552601933479309:   6%|▋         | 1630/25880 [22:28<4:31:13,  1.49it/s]
1|1631|Loss: 0.8552601933479309:   6%|▋         | 1631/25880 [22:28<4:13:14,  1.60it/s]
1|1632|Loss: 0.7729103565216064:   6%|▋         | 1631/25880 [22:28<4:13:14,  1.60it/s]
1|1632|Loss: 0.7729103565216064:   6%|▋         | 1632/25880 [22:29<4:34:26,  1.47it/s]
1|1633|Loss: 0.7407714128494263:   6%|▋         | 1632/25880 [22:29<4:34:26,  1.47it/s]
1|1633|Loss: 0.7407714128494263:   6%|▋         | 1633/25880 [22:30<5:03:00,  1.33it/s]
1|1634|Loss: 0.808871865272522:   6%|▋         | 1633/25880 [22:30<5:03:00,  1.33it/s] 
1|1634|Loss: 0.808871865272522:   6%|▋         | 1634/25880 [22:31<5:12:10,  1.29it/s]
1|1635|Loss: 0.9017930030822754:   6%|▋         | 1634/25880 [22:31<5:12:10,  1.29it/s]
1|1635|Loss: 0.9017930030822754:   6%|▋         | 1635/25880 [22:31<5:21:59,  1.25it/s]
1|1636|Loss: 1.11665678024292:   6%|▋         | 1635/25880 [22:32<5:21:59,  1.25it/s]  
1|1636|Loss: 1.11665678024292:   6%|▋         | 1636/25880 [22:32<5:06:38,  1.32it/s]
1|1637|Loss: 0.9467771649360657:   6%|▋         | 1636/25880 [22:33<5:06:38,  1.32it/s]
1|1637|Loss: 0.9467771649360657:   6%|▋         | 1637/25880 [22:33<4:51:22,  1.39it/s]
1|1638|Loss: 0.9363311529159546:   6%|▋         | 1637/25880 [22:33<4:51:22,  1.39it/s]
1|1638|Loss: 0.9363311529159546:   6%|▋         | 1638/25880 [22:34<4:51:29,  1.39it/s]
1|1639|Loss: 0.910307765007019:   6%|▋         | 1638/25880 [22:34<4:51:29,  1.39it/s] 
1|1639|Loss: 0.910307765007019:   6%|▋         | 1639/25880 [22:34<4:51:04,  1.39it/s]
1|1640|Loss: 0.9983421564102173:   6%|▋         | 1639/25880 [22:35<4:51:04,  1.39it/s]
1|1640|Loss: 0.9983421564102173:   6%|▋         | 1640/25880 [22:35<5:02:52,  1.33it/s]
1|1641|Loss: 0.9815530180931091:   6%|▋         | 1640/25880 [22:36<5:02:52,  1.33it/s]
1|1641|Loss: 0.9815530180931091:   6%|▋         | 1641/25880 [22:36<5:13:34,  1.29it/s]
1|1642|Loss: 0.9155095219612122:   6%|▋         | 1641/25880 [22:36<5:13:34,  1.29it/s]
1|1642|Loss: 0.9155095219612122:   6%|▋         | 1642/25880 [22:37<5:28:04,  1.23it/s]
1|1643|Loss: 1.1552772521972656:   6%|▋         | 1642/25880 [22:37<5:28:04,  1.23it/s]
1|1643|Loss: 1.1552772521972656:   6%|▋         | 1643/25880 [22:38<5:23:31,  1.25it/s]
1|1644|Loss: 0.9403573274612427:   6%|▋         | 1643/25880 [22:38<5:23:31,  1.25it/s]
1|1644|Loss: 0.9403573274612427:   6%|▋         | 1644/25880 [22:38<5:27:42,  1.23it/s]
1|1645|Loss: 0.9028154015541077:   6%|▋         | 1644/25880 [22:39<5:27:42,  1.23it/s]
1|1645|Loss: 0.9028154015541077:   6%|▋         | 1645/25880 [22:39<5:39:49,  1.19it/s]
1|1646|Loss: 0.7408891916275024:   6%|▋         | 1645/25880 [22:40<5:39:49,  1.19it/s]
1|1646|Loss: 0.7408891916275024:   6%|▋         | 1646/25880 [22:40<5:27:39,  1.23it/s]
1|1647|Loss: 0.8329381942749023:   6%|▋         | 1646/25880 [22:40<5:27:39,  1.23it/s]
1|1647|Loss: 0.8329381942749023:   6%|▋         | 1647/25880 [22:41<5:13:48,  1.29it/s]
1|1648|Loss: 0.8525842428207397:   6%|▋         | 1647/25880 [22:41<5:13:48,  1.29it/s]
1|1648|Loss: 0.8525842428207397:   6%|▋         | 1648/25880 [22:41<4:48:14,  1.40it/s]
1|1649|Loss: 0.898108720779419:   6%|▋         | 1648/25880 [22:42<4:48:14,  1.40it/s] 
1|1649|Loss: 0.898108720779419:   6%|▋         | 1649/25880 [22:42<4:36:57,  1.46it/s]
1|1650|Loss: 0.8747385144233704:   6%|▋         | 1649/25880 [22:42<4:36:57,  1.46it/s]
1|1650|Loss: 0.8747385144233704:   6%|▋         | 1650/25880 [22:43<4:31:55,  1.49it/s]
1|1651|Loss: 0.8450754880905151:   6%|▋         | 1650/25880 [22:43<4:31:55,  1.49it/s]
1|1651|Loss: 0.8450754880905151:   6%|▋         | 1651/25880 [22:43<4:27:36,  1.51it/s]
1|1652|Loss: 0.9398720264434814:   6%|▋         | 1651/25880 [22:44<4:27:36,  1.51it/s]
1|1652|Loss: 0.9398720264434814:   6%|▋         | 1652/25880 [22:44<4:36:07,  1.46it/s]
1|1653|Loss: 0.8624714016914368:   6%|▋         | 1652/25880 [22:44<4:36:07,  1.46it/s]
1|1653|Loss: 0.8624714016914368:   6%|▋         | 1653/25880 [22:45<4:48:11,  1.40it/s]
1|1654|Loss: 1.0408166646957397:   6%|▋         | 1653/25880 [22:45<4:48:11,  1.40it/s]
1|1654|Loss: 1.0408166646957397:   6%|▋         | 1654/25880 [22:46<5:01:25,  1.34it/s]
1|1655|Loss: 0.9342095255851746:   6%|▋         | 1654/25880 [22:46<5:01:25,  1.34it/s]
1|1655|Loss: 0.9342095255851746:   6%|▋         | 1655/25880 [22:46<4:40:36,  1.44it/s]
1|1656|Loss: 0.951437771320343:   6%|▋         | 1655/25880 [22:46<4:40:36,  1.44it/s] 
1|1656|Loss: 0.951437771320343:   6%|▋         | 1656/25880 [22:47<4:39:21,  1.45it/s]
1|1657|Loss: 0.8421599864959717:   6%|▋         | 1656/25880 [22:47<4:39:21,  1.45it/s]
1|1657|Loss: 0.8421599864959717:   6%|▋         | 1657/25880 [22:48<4:42:26,  1.43it/s]
1|1658|Loss: 0.9895051717758179:   6%|▋         | 1657/25880 [22:48<4:42:26,  1.43it/s]
1|1658|Loss: 0.9895051717758179:   6%|▋         | 1658/25880 [22:48<4:53:04,  1.38it/s]
1|1659|Loss: 0.9110329747200012:   6%|▋         | 1658/25880 [22:49<4:53:04,  1.38it/s]
1|1659|Loss: 0.9110329747200012:   6%|▋         | 1659/25880 [22:49<4:46:41,  1.41it/s]
1|1660|Loss: 1.0042698383331299:   6%|▋         | 1659/25880 [22:49<4:46:41,  1.41it/s]
1|1660|Loss: 1.0042698383331299:   6%|▋         | 1660/25880 [22:50<4:32:40,  1.48it/s]
1|1661|Loss: 0.7075091600418091:   6%|▋         | 1660/25880 [22:50<4:32:40,  1.48it/s]
1|1661|Loss: 0.7075091600418091:   6%|▋         | 1661/25880 [22:50<5:00:44,  1.34it/s]
1|1662|Loss: 0.9493914842605591:   6%|▋         | 1661/25880 [22:51<5:00:44,  1.34it/s]
1|1662|Loss: 0.9493914842605591:   6%|▋         | 1662/25880 [22:51<5:04:04,  1.33it/s]
1|1663|Loss: 0.8601690530776978:   6%|▋         | 1662/25880 [22:52<5:04:04,  1.33it/s]
1|1663|Loss: 0.8601690530776978:   6%|▋         | 1663/25880 [22:52<5:10:38,  1.30it/s]
1|1664|Loss: 0.8862278461456299:   6%|▋         | 1663/25880 [22:52<5:10:38,  1.30it/s]
1|1664|Loss: 0.8862278461456299:   6%|▋         | 1664/25880 [22:53<4:53:03,  1.38it/s]
1|1665|Loss: 0.8576679229736328:   6%|▋         | 1664/25880 [22:53<4:53:03,  1.38it/s]
1|1665|Loss: 0.8576679229736328:   6%|▋         | 1665/25880 [22:54<5:07:26,  1.31it/s]
1|1666|Loss: 1.0133681297302246:   6%|▋         | 1665/25880 [22:54<5:07:26,  1.31it/s]
1|1666|Loss: 1.0133681297302246:   6%|▋         | 1666/25880 [22:54<4:59:08,  1.35it/s]
1|1667|Loss: 0.8807951807975769:   6%|▋         | 1666/25880 [22:55<4:59:08,  1.35it/s]
1|1667|Loss: 0.8807951807975769:   6%|▋         | 1667/25880 [22:55<5:06:03,  1.32it/s]
1|1668|Loss: 0.962605893611908:   6%|▋         | 1667/25880 [22:55<5:06:03,  1.32it/s] 
1|1668|Loss: 0.962605893611908:   6%|▋         | 1668/25880 [22:56<5:04:07,  1.33it/s]
1|1669|Loss: 0.9576882123947144:   6%|▋         | 1668/25880 [22:56<5:04:07,  1.33it/s]
1|1669|Loss: 0.9576882123947144:   6%|▋         | 1669/25880 [22:56<4:49:57,  1.39it/s]
1|1670|Loss: 0.8595443964004517:   6%|▋         | 1669/25880 [22:57<4:49:57,  1.39it/s]
1|1670|Loss: 0.8595443964004517:   6%|▋         | 1670/25880 [22:57<5:07:43,  1.31it/s]
1|1671|Loss: 0.9301041960716248:   6%|▋         | 1670/25880 [22:58<5:07:43,  1.31it/s]
1|1671|Loss: 0.9301041960716248:   6%|▋         | 1671/25880 [22:58<5:23:37,  1.25it/s]
1|1672|Loss: 0.7406831979751587:   6%|▋         | 1671/25880 [22:59<5:23:37,  1.25it/s]
1|1672|Loss: 0.7406831979751587:   6%|▋         | 1672/25880 [22:59<5:26:21,  1.24it/s]
1|1673|Loss: 1.0307323932647705:   6%|▋         | 1672/25880 [22:59<5:26:21,  1.24it/s]
1|1673|Loss: 1.0307323932647705:   6%|▋         | 1673/25880 [23:00<5:28:00,  1.23it/s]
1|1674|Loss: 0.7537355422973633:   6%|▋         | 1673/25880 [23:00<5:28:00,  1.23it/s]
1|1674|Loss: 0.7537355422973633:   6%|▋         | 1674/25880 [23:00<5:08:41,  1.31it/s]
1|1675|Loss: 0.9263482689857483:   6%|▋         | 1674/25880 [23:01<5:08:41,  1.31it/s]
1|1675|Loss: 0.9263482689857483:   6%|▋         | 1675/25880 [23:01<5:13:29,  1.29it/s]
1|1676|Loss: 0.9734707474708557:   6%|▋         | 1675/25880 [23:02<5:13:29,  1.29it/s]
1|1676|Loss: 0.9734707474708557:   6%|▋         | 1676/25880 [23:02<5:03:20,  1.33it/s]
1|1677|Loss: 1.083343267440796:   6%|▋         | 1676/25880 [23:02<5:03:20,  1.33it/s] 
1|1677|Loss: 1.083343267440796:   6%|▋         | 1677/25880 [23:03<4:47:50,  1.40it/s]
1|1678|Loss: 0.7235366106033325:   6%|▋         | 1677/25880 [23:03<4:47:50,  1.40it/s]
1|1678|Loss: 0.7235366106033325:   6%|▋         | 1678/25880 [23:03<4:12:30,  1.60it/s]
1|1679|Loss: 0.894241988658905:   6%|▋         | 1678/25880 [23:03<4:12:30,  1.60it/s] 
1|1679|Loss: 0.894241988658905:   6%|▋         | 1679/25880 [23:04<4:00:32,  1.68it/s]
1|1680|Loss: 0.8832305073738098:   6%|▋         | 1679/25880 [23:04<4:00:32,  1.68it/s]
1|1680|Loss: 0.8832305073738098:   6%|▋         | 1680/25880 [23:04<4:26:38,  1.51it/s]
1|1681|Loss: 0.9339384436607361:   6%|▋         | 1680/25880 [23:05<4:26:38,  1.51it/s]
1|1681|Loss: 0.9339384436607361:   6%|▋         | 1681/25880 [23:05<4:44:47,  1.42it/s]
1|1682|Loss: 1.006951093673706:   6%|▋         | 1681/25880 [23:06<4:44:47,  1.42it/s] 
1|1682|Loss: 1.006951093673706:   6%|▋         | 1682/25880 [23:06<4:39:15,  1.44it/s]
1|1683|Loss: 0.9191034436225891:   6%|▋         | 1682/25880 [23:06<4:39:15,  1.44it/s]
1|1683|Loss: 0.9191034436225891:   7%|▋         | 1683/25880 [23:07<4:41:33,  1.43it/s]
1|1684|Loss: 0.9135164618492126:   7%|▋         | 1683/25880 [23:07<4:41:33,  1.43it/s]
1|1684|Loss: 0.9135164618492126:   7%|▋         | 1684/25880 [23:07<4:25:41,  1.52it/s]
1|1685|Loss: 0.866826593875885:   7%|▋         | 1684/25880 [23:08<4:25:41,  1.52it/s] 
1|1685|Loss: 0.866826593875885:   7%|▋         | 1685/25880 [23:08<4:44:00,  1.42it/s]
1|1686|Loss: 0.9422324299812317:   7%|▋         | 1685/25880 [23:08<4:44:00,  1.42it/s]
1|1686|Loss: 0.9422324299812317:   7%|▋         | 1686/25880 [23:09<5:03:18,  1.33it/s]
1|1687|Loss: 0.9270157814025879:   7%|▋         | 1686/25880 [23:09<5:03:18,  1.33it/s]
1|1687|Loss: 0.9270157814025879:   7%|▋         | 1687/25880 [23:10<5:06:19,  1.32it/s]
1|1688|Loss: 0.8529611229896545:   7%|▋         | 1687/25880 [23:10<5:06:19,  1.32it/s]
1|1688|Loss: 0.8529611229896545:   7%|▋         | 1688/25880 [23:10<5:03:34,  1.33it/s]
1|1689|Loss: 0.812372088432312:   7%|▋         | 1688/25880 [23:11<5:03:34,  1.33it/s] 
1|1689|Loss: 0.812372088432312:   7%|▋         | 1689/25880 [23:11<5:00:00,  1.34it/s]
1|1690|Loss: 0.7906290888786316:   7%|▋         | 1689/25880 [23:11<5:00:00,  1.34it/s]
1|1690|Loss: 0.7906290888786316:   7%|▋         | 1690/25880 [23:12<5:03:45,  1.33it/s]
1|1691|Loss: 0.8109798431396484:   7%|▋         | 1690/25880 [23:12<5:03:45,  1.33it/s]
1|1691|Loss: 0.8109798431396484:   7%|▋         | 1691/25880 [23:13<5:08:33,  1.31it/s]
1|1692|Loss: 0.9144158363342285:   7%|▋         | 1691/25880 [23:13<5:08:33,  1.31it/s]
1|1692|Loss: 0.9144158363342285:   7%|▋         | 1692/25880 [23:14<5:27:28,  1.23it/s]
1|1693|Loss: 0.8809207677841187:   7%|▋         | 1692/25880 [23:14<5:27:28,  1.23it/s]
1|1693|Loss: 0.8809207677841187:   7%|▋         | 1693/25880 [23:14<5:29:16,  1.22it/s]
1|1694|Loss: 0.9342219233512878:   7%|▋         | 1693/25880 [23:15<5:29:16,  1.22it/s]
1|1694|Loss: 0.9342219233512878:   7%|▋         | 1694/25880 [23:15<4:59:30,  1.35it/s]
1|1695|Loss: 0.8671965003013611:   7%|▋         | 1694/25880 [23:15<4:59:30,  1.35it/s]
1|1695|Loss: 0.8671965003013611:   7%|▋         | 1695/25880 [23:16<4:52:08,  1.38it/s]
1|1696|Loss: 0.831278920173645:   7%|▋         | 1695/25880 [23:16<4:52:08,  1.38it/s] 
1|1696|Loss: 0.831278920173645:   7%|▋         | 1696/25880 [23:16<4:39:22,  1.44it/s]
1|1697|Loss: 0.7997744083404541:   7%|▋         | 1696/25880 [23:17<4:39:22,  1.44it/s]
1|1697|Loss: 0.7997744083404541:   7%|▋         | 1697/25880 [23:17<4:41:17,  1.43it/s]
1|1698|Loss: 0.9183290600776672:   7%|▋         | 1697/25880 [23:17<4:41:17,  1.43it/s]
1|1698|Loss: 0.9183290600776672:   7%|▋         | 1698/25880 [23:18<4:37:47,  1.45it/s]
1|1699|Loss: 0.9286316633224487:   7%|▋         | 1698/25880 [23:18<4:37:47,  1.45it/s]
1|1699|Loss: 0.9286316633224487:   7%|▋         | 1699/25880 [23:18<4:29:49,  1.49it/s]
1|1700|Loss: 0.9195696115493774:   7%|▋         | 1699/25880 [23:19<4:29:49,  1.49it/s]
1|1700|Loss: 0.9195696115493774:   7%|▋         | 1700/25880 [23:19<4:44:35,  1.42it/s]
1|1701|Loss: 0.8306816816329956:   7%|▋         | 1700/25880 [23:19<4:44:35,  1.42it/s]
1|1701|Loss: 0.8306816816329956:   7%|▋         | 1701/25880 [23:20<4:47:07,  1.40it/s]
1|1702|Loss: 0.8297750353813171:   7%|▋         | 1701/25880 [23:20<4:47:07,  1.40it/s]
1|1702|Loss: 0.8297750353813171:   7%|▋         | 1702/25880 [23:20<4:37:15,  1.45it/s]
1|1703|Loss: 0.9379045367240906:   7%|▋         | 1702/25880 [23:21<4:37:15,  1.45it/s]
1|1703|Loss: 0.9379045367240906:   7%|▋         | 1703/25880 [23:21<4:40:29,  1.44it/s]
1|1704|Loss: 0.9115672707557678:   7%|▋         | 1703/25880 [23:21<4:40:29,  1.44it/s]
1|1704|Loss: 0.9115672707557678:   7%|▋         | 1704/25880 [23:22<4:36:03,  1.46it/s]
1|1705|Loss: 0.8959013223648071:   7%|▋         | 1704/25880 [23:22<4:36:03,  1.46it/s]
1|1705|Loss: 0.8959013223648071:   7%|▋         | 1705/25880 [23:22<4:39:53,  1.44it/s]
1|1706|Loss: 0.7564226388931274:   7%|▋         | 1705/25880 [23:23<4:39:53,  1.44it/s]
1|1706|Loss: 0.7564226388931274:   7%|▋         | 1706/25880 [23:23<4:41:33,  1.43it/s]
1|1707|Loss: 0.8408206105232239:   7%|▋         | 1706/25880 [23:24<4:41:33,  1.43it/s]
1|1707|Loss: 0.8408206105232239:   7%|▋         | 1707/25880 [23:24<4:44:27,  1.42it/s]
1|1708|Loss: 0.8185390830039978:   7%|▋         | 1707/25880 [23:24<4:44:27,  1.42it/s]
1|1708|Loss: 0.8185390830039978:   7%|▋         | 1708/25880 [23:25<4:56:52,  1.36it/s]
1|1709|Loss: 0.9293944835662842:   7%|▋         | 1708/25880 [23:25<4:56:52,  1.36it/s]
1|1709|Loss: 0.9293944835662842:   7%|▋         | 1709/25880 [23:25<4:59:45,  1.34it/s]
1|1710|Loss: 0.9222538471221924:   7%|▋         | 1709/25880 [23:26<4:59:45,  1.34it/s]
1|1710|Loss: 0.9222538471221924:   7%|▋         | 1710/25880 [23:26<4:37:47,  1.45it/s]
1|1711|Loss: 0.8240697383880615:   7%|▋         | 1710/25880 [23:26<4:37:47,  1.45it/s]
1|1711|Loss: 0.8240697383880615:   7%|▋         | 1711/25880 [23:27<4:37:21,  1.45it/s]
1|1712|Loss: 0.8584977388381958:   7%|▋         | 1711/25880 [23:27<4:37:21,  1.45it/s]
1|1712|Loss: 0.8584977388381958:   7%|▋         | 1712/25880 [23:27<4:20:39,  1.55it/s]
1|1713|Loss: 1.0075770616531372:   7%|▋         | 1712/25880 [23:28<4:20:39,  1.55it/s]
1|1713|Loss: 1.0075770616531372:   7%|▋         | 1713/25880 [23:28<4:31:14,  1.48it/s]
1|1714|Loss: 0.9992068409919739:   7%|▋         | 1713/25880 [23:28<4:31:14,  1.48it/s]
1|1714|Loss: 0.9992068409919739:   7%|▋         | 1714/25880 [23:29<4:37:28,  1.45it/s]
1|1715|Loss: 0.869796633720398:   7%|▋         | 1714/25880 [23:29<4:37:28,  1.45it/s] 
1|1715|Loss: 0.869796633720398:   7%|▋         | 1715/25880 [23:29<4:37:49,  1.45it/s]
1|1716|Loss: 0.7343053817749023:   7%|▋         | 1715/25880 [23:30<4:37:49,  1.45it/s]
1|1716|Loss: 0.7343053817749023:   7%|▋         | 1716/25880 [23:30<4:41:07,  1.43it/s]
1|1717|Loss: 1.0255526304244995:   7%|▋         | 1716/25880 [23:30<4:41:07,  1.43it/s]
1|1717|Loss: 1.0255526304244995:   7%|▋         | 1717/25880 [23:31<4:33:30,  1.47it/s]
1|1718|Loss: 0.8674551844596863:   7%|▋         | 1717/25880 [23:31<4:33:30,  1.47it/s]
1|1718|Loss: 0.8674551844596863:   7%|▋         | 1718/25880 [23:31<4:28:15,  1.50it/s]
1|1719|Loss: 0.9877078533172607:   7%|▋         | 1718/25880 [23:32<4:28:15,  1.50it/s]
1|1719|Loss: 0.9877078533172607:   7%|▋         | 1719/25880 [23:32<4:34:10,  1.47it/s]
1|1720|Loss: 0.7343026399612427:   7%|▋         | 1719/25880 [23:32<4:34:10,  1.47it/s]
1|1720|Loss: 0.7343026399612427:   7%|▋         | 1720/25880 [23:33<4:31:24,  1.48it/s]
1|1721|Loss: 0.9976744651794434:   7%|▋         | 1720/25880 [23:33<4:31:24,  1.48it/s]
1|1721|Loss: 0.9976744651794434:   7%|▋         | 1721/25880 [23:33<4:36:00,  1.46it/s]
1|1722|Loss: 0.7397629022598267:   7%|▋         | 1721/25880 [23:34<4:36:00,  1.46it/s]
1|1722|Loss: 0.7397629022598267:   7%|▋         | 1722/25880 [23:34<4:47:37,  1.40it/s]
1|1723|Loss: 0.7638477683067322:   7%|▋         | 1722/25880 [23:35<4:47:37,  1.40it/s]
1|1723|Loss: 0.7638477683067322:   7%|▋         | 1723/25880 [23:35<4:52:47,  1.38it/s]
1|1724|Loss: 0.994856595993042:   7%|▋         | 1723/25880 [23:35<4:52:47,  1.38it/s] 
1|1724|Loss: 0.994856595993042:   7%|▋         | 1724/25880 [23:36<5:08:01,  1.31it/s]
1|1725|Loss: 0.852496325969696:   7%|▋         | 1724/25880 [23:36<5:08:01,  1.31it/s]
1|1725|Loss: 0.852496325969696:   7%|▋         | 1725/25880 [23:37<5:08:06,  1.31it/s]
1|1726|Loss: 1.0227843523025513:   7%|▋         | 1725/25880 [23:37<5:08:06,  1.31it/s]
1|1726|Loss: 1.0227843523025513:   7%|▋         | 1726/25880 [23:37<5:03:49,  1.33it/s]
1|1727|Loss: 0.8517511487007141:   7%|▋         | 1726/25880 [23:38<5:03:49,  1.33it/s]
1|1727|Loss: 0.8517511487007141:   7%|▋         | 1727/25880 [23:38<5:02:52,  1.33it/s]
1|1728|Loss: 0.9151630401611328:   7%|▋         | 1727/25880 [23:39<5:02:52,  1.33it/s]
1|1728|Loss: 0.9151630401611328:   7%|▋         | 1728/25880 [23:39<5:01:00,  1.34it/s]
1|1729|Loss: 0.8764405250549316:   7%|▋         | 1728/25880 [23:39<5:01:00,  1.34it/s]
1|1729|Loss: 0.8764405250549316:   7%|▋         | 1729/25880 [23:40<4:55:35,  1.36it/s]
1|1730|Loss: 0.9620506763458252:   7%|▋         | 1729/25880 [23:40<4:55:35,  1.36it/s]
1|1730|Loss: 0.9620506763458252:   7%|▋         | 1730/25880 [23:40<4:30:23,  1.49it/s]
1|1731|Loss: 0.949306070804596:   7%|▋         | 1730/25880 [23:40<4:30:23,  1.49it/s] 
1|1731|Loss: 0.949306070804596:   7%|▋         | 1731/25880 [23:41<4:30:59,  1.49it/s]
1|1732|Loss: 1.0343815088272095:   7%|▋         | 1731/25880 [23:41<4:30:59,  1.49it/s]
1|1732|Loss: 1.0343815088272095:   7%|▋         | 1732/25880 [23:42<4:49:47,  1.39it/s]
1|1733|Loss: 0.7853485345840454:   7%|▋         | 1732/25880 [23:42<4:49:47,  1.39it/s]
1|1733|Loss: 0.7853485345840454:   7%|▋         | 1733/25880 [23:42<4:51:40,  1.38it/s]
1|1734|Loss: 0.9385194778442383:   7%|▋         | 1733/25880 [23:43<4:51:40,  1.38it/s]
1|1734|Loss: 0.9385194778442383:   7%|▋         | 1734/25880 [23:43<4:38:01,  1.45it/s]
1|1735|Loss: 0.8531597852706909:   7%|▋         | 1734/25880 [23:43<4:38:01,  1.45it/s]
1|1735|Loss: 0.8531597852706909:   7%|▋         | 1735/25880 [23:44<4:35:43,  1.46it/s]
1|1736|Loss: 0.8560665845870972:   7%|▋         | 1735/25880 [23:44<4:35:43,  1.46it/s]
1|1736|Loss: 0.8560665845870972:   7%|▋         | 1736/25880 [23:44<4:31:42,  1.48it/s]
1|1737|Loss: 1.175804615020752:   7%|▋         | 1736/25880 [23:45<4:31:42,  1.48it/s] 
1|1737|Loss: 1.175804615020752:   7%|▋         | 1737/25880 [23:45<4:55:10,  1.36it/s]
1|1738|Loss: 0.8103970885276794:   7%|▋         | 1737/25880 [23:46<4:55:10,  1.36it/s]
1|1738|Loss: 0.8103970885276794:   7%|▋         | 1738/25880 [23:46<5:17:48,  1.27it/s]
1|1739|Loss: 0.910629153251648:   7%|▋         | 1738/25880 [23:46<5:17:48,  1.27it/s] 
1|1739|Loss: 0.910629153251648:   7%|▋         | 1739/25880 [23:47<5:14:38,  1.28it/s]
1|1740|Loss: 0.873560905456543:   7%|▋         | 1739/25880 [23:47<5:14:38,  1.28it/s]
1|1740|Loss: 0.873560905456543:   7%|▋         | 1740/25880 [23:47<4:50:56,  1.38it/s]
1|1741|Loss: 0.8802574872970581:   7%|▋         | 1740/25880 [23:48<4:50:56,  1.38it/s]
1|1741|Loss: 0.8802574872970581:   7%|▋         | 1741/25880 [23:48<4:54:58,  1.36it/s]
1|1742|Loss: 0.9492213129997253:   7%|▋         | 1741/25880 [23:49<4:54:58,  1.36it/s]
1|1742|Loss: 0.9492213129997253:   7%|▋         | 1742/25880 [23:49<5:07:04,  1.31it/s]
1|1743|Loss: 0.9083814024925232:   7%|▋         | 1742/25880 [23:49<5:07:04,  1.31it/s]
1|1743|Loss: 0.9083814024925232:   7%|▋         | 1743/25880 [23:50<4:48:59,  1.39it/s]
1|1744|Loss: 0.8173335790634155:   7%|▋         | 1743/25880 [23:50<4:48:59,  1.39it/s]
1|1744|Loss: 0.8173335790634155:   7%|▋         | 1744/25880 [23:50<4:36:57,  1.45it/s]
1|1745|Loss: 0.8798068165779114:   7%|▋         | 1744/25880 [23:51<4:36:57,  1.45it/s]
1|1745|Loss: 0.8798068165779114:   7%|▋         | 1745/25880 [23:51<4:38:08,  1.45it/s]
1|1746|Loss: 0.8441633582115173:   7%|▋         | 1745/25880 [23:51<4:38:08,  1.45it/s]
1|1746|Loss: 0.8441633582115173:   7%|▋         | 1746/25880 [23:51<4:18:45,  1.55it/s]
1|1747|Loss: 1.0627716779708862:   7%|▋         | 1746/25880 [23:52<4:18:45,  1.55it/s]
1|1747|Loss: 1.0627716779708862:   7%|▋         | 1747/25880 [23:52<4:12:12,  1.59it/s]
1|1748|Loss: 0.9737792611122131:   7%|▋         | 1747/25880 [23:52<4:12:12,  1.59it/s]
1|1748|Loss: 0.9737792611122131:   7%|▋         | 1748/25880 [23:53<4:10:54,  1.60it/s]
1|1749|Loss: 0.9204273223876953:   7%|▋         | 1748/25880 [23:53<4:10:54,  1.60it/s]
1|1749|Loss: 0.9204273223876953:   7%|▋         | 1749/25880 [23:53<4:32:53,  1.47it/s]
1|1750|Loss: 0.8818349242210388:   7%|▋         | 1749/25880 [23:54<4:32:53,  1.47it/s]
1|1750|Loss: 0.8818349242210388:   7%|▋         | 1750/25880 [23:54<4:29:36,  1.49it/s]
1|1751|Loss: 0.9300657510757446:   7%|▋         | 1750/25880 [23:54<4:29:36,  1.49it/s]
1|1751|Loss: 0.9300657510757446:   7%|▋         | 1751/25880 [23:55<4:32:26,  1.48it/s]
1|1752|Loss: 0.8597284555435181:   7%|▋         | 1751/25880 [23:55<4:32:26,  1.48it/s]
1|1752|Loss: 0.8597284555435181:   7%|▋         | 1752/25880 [23:56<4:46:01,  1.41it/s]
1|1753|Loss: 0.9874036908149719:   7%|▋         | 1752/25880 [23:56<4:46:01,  1.41it/s]
1|1753|Loss: 0.9874036908149719:   7%|▋         | 1753/25880 [23:56<4:39:58,  1.44it/s]
1|1754|Loss: 0.8995174169540405:   7%|▋         | 1753/25880 [23:57<4:39:58,  1.44it/s]
1|1754|Loss: 0.8995174169540405:   7%|▋         | 1754/25880 [23:57<4:51:40,  1.38it/s]
1|1755|Loss: 0.8373149633407593:   7%|▋         | 1754/25880 [23:57<4:51:40,  1.38it/s]
1|1755|Loss: 0.8373149633407593:   7%|▋         | 1755/25880 [23:58<4:55:10,  1.36it/s]
1|1756|Loss: 0.8394766449928284:   7%|▋         | 1755/25880 [23:58<4:55:10,  1.36it/s]
1|1756|Loss: 0.8394766449928284:   7%|▋         | 1756/25880 [23:59<4:57:04,  1.35it/s]
1|1757|Loss: 0.9484727382659912:   7%|▋         | 1756/25880 [23:59<4:57:04,  1.35it/s]
1|1757|Loss: 0.9484727382659912:   7%|▋         | 1757/25880 [23:59<4:40:43,  1.43it/s]
1|1758|Loss: 0.9141066670417786:   7%|▋         | 1757/25880 [24:00<4:40:43,  1.43it/s]
1|1758|Loss: 0.9141066670417786:   7%|▋         | 1758/25880 [24:00<4:41:14,  1.43it/s]
1|1759|Loss: 0.9044300317764282:   7%|▋         | 1758/25880 [24:00<4:41:14,  1.43it/s]
1|1759|Loss: 0.9044300317764282:   7%|▋         | 1759/25880 [24:00<4:22:18,  1.53it/s]
1|1760|Loss: 0.9364019632339478:   7%|▋         | 1759/25880 [24:01<4:22:18,  1.53it/s]
1|1760|Loss: 0.9364019632339478:   7%|▋         | 1760/25880 [24:01<4:22:10,  1.53it/s]
1|1761|Loss: 0.864954948425293:   7%|▋         | 1760/25880 [24:01<4:22:10,  1.53it/s] 
1|1761|Loss: 0.864954948425293:   7%|▋         | 1761/25880 [24:02<4:37:35,  1.45it/s]
1|1762|Loss: 0.9051234722137451:   7%|▋         | 1761/25880 [24:02<4:37:35,  1.45it/s]
1|1762|Loss: 0.9051234722137451:   7%|▋         | 1762/25880 [24:03<4:41:14,  1.43it/s]
1|1763|Loss: 0.8438126444816589:   7%|▋         | 1762/25880 [24:03<4:41:14,  1.43it/s]
1|1763|Loss: 0.8438126444816589:   7%|▋         | 1763/25880 [24:03<4:51:38,  1.38it/s]
1|1764|Loss: 0.8521558046340942:   7%|▋         | 1763/25880 [24:04<4:51:38,  1.38it/s]
1|1764|Loss: 0.8521558046340942:   7%|▋         | 1764/25880 [24:04<4:51:30,  1.38it/s]
1|1765|Loss: 0.9558472633361816:   7%|▋         | 1764/25880 [24:04<4:51:30,  1.38it/s]
1|1765|Loss: 0.9558472633361816:   7%|▋         | 1765/25880 [24:05<4:57:21,  1.35it/s]
1|1766|Loss: 0.8294220566749573:   7%|▋         | 1765/25880 [24:05<4:57:21,  1.35it/s]
1|1766|Loss: 0.8294220566749573:   7%|▋         | 1766/25880 [24:05<4:31:14,  1.48it/s]
1|1767|Loss: 0.8385441303253174:   7%|▋         | 1766/25880 [24:06<4:31:14,  1.48it/s]
1|1767|Loss: 0.8385441303253174:   7%|▋         | 1767/25880 [24:06<4:20:04,  1.55it/s]
1|1768|Loss: 1.018776297569275:   7%|▋         | 1767/25880 [24:06<4:20:04,  1.55it/s] 
1|1768|Loss: 1.018776297569275:   7%|▋         | 1768/25880 [24:07<4:16:57,  1.56it/s]
1|1769|Loss: 0.856571614742279:   7%|▋         | 1768/25880 [24:07<4:16:57,  1.56it/s]
1|1769|Loss: 0.856571614742279:   7%|▋         | 1769/25880 [24:07<4:30:55,  1.48it/s]
1|1770|Loss: 0.754715085029602:   7%|▋         | 1769/25880 [24:08<4:30:55,  1.48it/s]
1|1770|Loss: 0.754715085029602:   7%|▋         | 1770/25880 [24:08<4:39:32,  1.44it/s]
1|1771|Loss: 0.7880834937095642:   7%|▋         | 1770/25880 [24:08<4:39:32,  1.44it/s]
1|1771|Loss: 0.7880834937095642:   7%|▋         | 1771/25880 [24:09<4:45:23,  1.41it/s]
1|1772|Loss: 0.9223344326019287:   7%|▋         | 1771/25880 [24:09<4:45:23,  1.41it/s]
1|1772|Loss: 0.9223344326019287:   7%|▋         | 1772/25880 [24:09<4:34:18,  1.46it/s]
1|1773|Loss: 0.8314079642295837:   7%|▋         | 1772/25880 [24:10<4:34:18,  1.46it/s]
1|1773|Loss: 0.8314079642295837:   7%|▋         | 1773/25880 [24:10<4:44:01,  1.41it/s]
1|1774|Loss: 0.7478259801864624:   7%|▋         | 1773/25880 [24:11<4:44:01,  1.41it/s]
1|1774|Loss: 0.7478259801864624:   7%|▋         | 1774/25880 [24:11<4:46:21,  1.40it/s]
1|1775|Loss: 0.9791368246078491:   7%|▋         | 1774/25880 [24:11<4:46:21,  1.40it/s]
1|1775|Loss: 0.9791368246078491:   7%|▋         | 1775/25880 [24:11<4:30:28,  1.49it/s]
1|1776|Loss: 0.9293222427368164:   7%|▋         | 1775/25880 [24:12<4:30:28,  1.49it/s]
1|1776|Loss: 0.9293222427368164:   7%|▋         | 1776/25880 [24:12<4:43:35,  1.42it/s]
1|1777|Loss: 0.9265874028205872:   7%|▋         | 1776/25880 [24:13<4:43:35,  1.42it/s]
1|1777|Loss: 0.9265874028205872:   7%|▋         | 1777/25880 [24:13<4:47:48,  1.40it/s]
1|1778|Loss: 0.9190539717674255:   7%|▋         | 1777/25880 [24:13<4:47:48,  1.40it/s]
1|1778|Loss: 0.9190539717674255:   7%|▋         | 1778/25880 [24:14<5:02:35,  1.33it/s]
1|1779|Loss: 0.9688828587532043:   7%|▋         | 1778/25880 [24:14<5:02:35,  1.33it/s]
1|1779|Loss: 0.9688828587532043:   7%|▋         | 1779/25880 [24:15<5:17:18,  1.27it/s]
1|1780|Loss: 0.8112974166870117:   7%|▋         | 1779/25880 [24:15<5:17:18,  1.27it/s]
1|1780|Loss: 0.8112974166870117:   7%|▋         | 1780/25880 [24:16<5:18:53,  1.26it/s]
1|1781|Loss: 0.9087561368942261:   7%|▋         | 1780/25880 [24:16<5:18:53,  1.26it/s]
1|1781|Loss: 0.9087561368942261:   7%|▋         | 1781/25880 [24:16<4:56:31,  1.35it/s]
1|1782|Loss: 0.7206647992134094:   7%|▋         | 1781/25880 [24:17<4:56:31,  1.35it/s]
1|1782|Loss: 0.7206647992134094:   7%|▋         | 1782/25880 [24:17<5:02:52,  1.33it/s]
1|1783|Loss: 0.79388427734375:   7%|▋         | 1782/25880 [24:17<5:02:52,  1.33it/s]  
1|1783|Loss: 0.79388427734375:   7%|▋         | 1783/25880 [24:18<4:52:15,  1.37it/s]
1|1784|Loss: 0.8868270516395569:   7%|▋         | 1783/25880 [24:18<4:52:15,  1.37it/s]
1|1784|Loss: 0.8868270516395569:   7%|▋         | 1784/25880 [24:18<4:56:38,  1.35it/s]
1|1785|Loss: 0.8982200026512146:   7%|▋         | 1784/25880 [24:19<4:56:38,  1.35it/s]
1|1785|Loss: 0.8982200026512146:   7%|▋         | 1785/25880 [24:19<4:57:46,  1.35it/s]
1|1786|Loss: 0.8598014116287231:   7%|▋         | 1785/25880 [24:20<4:57:46,  1.35it/s]
1|1786|Loss: 0.8598014116287231:   7%|▋         | 1786/25880 [24:20<5:08:37,  1.30it/s]
1|1787|Loss: 0.8938379883766174:   7%|▋         | 1786/25880 [24:20<5:08:37,  1.30it/s]
1|1787|Loss: 0.8938379883766174:   7%|▋         | 1787/25880 [24:20<4:41:13,  1.43it/s]
1|1788|Loss: 0.8670259714126587:   7%|▋         | 1787/25880 [24:21<4:41:13,  1.43it/s]
1|1788|Loss: 0.8670259714126587:   7%|▋         | 1788/25880 [24:21<4:29:13,  1.49it/s]
1|1789|Loss: 0.8499186635017395:   7%|▋         | 1788/25880 [24:22<4:29:13,  1.49it/s]
1|1789|Loss: 0.8499186635017395:   7%|▋         | 1789/25880 [24:22<4:47:01,  1.40it/s]
1|1790|Loss: 0.8431788086891174:   7%|▋         | 1789/25880 [24:22<4:47:01,  1.40it/s]
1|1790|Loss: 0.8431788086891174:   7%|▋         | 1790/25880 [24:23<4:44:11,  1.41it/s]
1|1791|Loss: 0.9284136891365051:   7%|▋         | 1790/25880 [24:23<4:44:11,  1.41it/s]
1|1791|Loss: 0.9284136891365051:   7%|▋         | 1791/25880 [24:23<4:45:28,  1.41it/s]
1|1792|Loss: 0.9206815958023071:   7%|▋         | 1791/25880 [24:24<4:45:28,  1.41it/s]
1|1792|Loss: 0.9206815958023071:   7%|▋         | 1792/25880 [24:24<4:45:42,  1.41it/s]
1|1793|Loss: 0.846139669418335:   7%|▋         | 1792/25880 [24:24<4:45:42,  1.41it/s] 
1|1793|Loss: 0.846139669418335:   7%|▋         | 1793/25880 [24:25<4:44:19,  1.41it/s]
1|1794|Loss: 0.7765657305717468:   7%|▋         | 1793/25880 [24:25<4:44:19,  1.41it/s]
1|1794|Loss: 0.7765657305717468:   7%|▋         | 1794/25880 [24:25<4:37:59,  1.44it/s]
1|1795|Loss: 0.945514440536499:   7%|▋         | 1794/25880 [24:26<4:37:59,  1.44it/s] 
1|1795|Loss: 0.945514440536499:   7%|▋         | 1795/25880 [24:26<4:59:18,  1.34it/s]
1|1796|Loss: 0.8792217373847961:   7%|▋         | 1795/25880 [24:27<4:59:18,  1.34it/s]
1|1796|Loss: 0.8792217373847961:   7%|▋         | 1796/25880 [24:27<4:59:28,  1.34it/s]
1|1797|Loss: 0.759412407875061:   7%|▋         | 1796/25880 [24:27<4:59:28,  1.34it/s] 
1|1797|Loss: 0.759412407875061:   7%|▋         | 1797/25880 [24:28<4:57:17,  1.35it/s]
1|1798|Loss: 0.9258663058280945:   7%|▋         | 1797/25880 [24:28<4:57:17,  1.35it/s]
1|1798|Loss: 0.9258663058280945:   7%|▋         | 1798/25880 [24:29<5:09:41,  1.30it/s]
1|1799|Loss: 0.96488356590271:   7%|▋         | 1798/25880 [24:29<5:09:41,  1.30it/s]  
1|1799|Loss: 0.96488356590271:   7%|▋         | 1799/25880 [24:29<4:54:49,  1.36it/s]
1|1800|Loss: 0.9720009565353394:   7%|▋         | 1799/25880 [24:30<4:54:49,  1.36it/s]
1|1800|Loss: 0.9720009565353394:   7%|▋         | 1800/25880 [24:30<4:48:07,  1.39it/s]
1|1801|Loss: 0.7873648405075073:   7%|▋         | 1800/25880 [24:30<4:48:07,  1.39it/s]
1|1801|Loss: 0.7873648405075073:   7%|▋         | 1801/25880 [24:30<4:22:23,  1.53it/s]
1|1802|Loss: 0.890455961227417:   7%|▋         | 1801/25880 [24:31<4:22:23,  1.53it/s] 
1|1802|Loss: 0.890455961227417:   7%|▋         | 1802/25880 [24:31<4:29:40,  1.49it/s]
1|1803|Loss: 0.9126954674720764:   7%|▋         | 1802/25880 [24:32<4:29:40,  1.49it/s]
1|1803|Loss: 0.9126954674720764:   7%|▋         | 1803/25880 [24:32<4:45:43,  1.40it/s]
1|1804|Loss: 0.7921786308288574:   7%|▋         | 1803/25880 [24:32<4:45:43,  1.40it/s]
1|1804|Loss: 0.7921786308288574:   7%|▋         | 1804/25880 [24:33<4:38:31,  1.44it/s]
1|1805|Loss: 0.8229749798774719:   7%|▋         | 1804/25880 [24:33<4:38:31,  1.44it/s]
1|1805|Loss: 0.8229749798774719:   7%|▋         | 1805/25880 [24:33<4:54:46,  1.36it/s]
1|1806|Loss: 0.9182118773460388:   7%|▋         | 1805/25880 [24:34<4:54:46,  1.36it/s]
1|1806|Loss: 0.9182118773460388:   7%|▋         | 1806/25880 [24:34<4:44:33,  1.41it/s]
1|1807|Loss: 0.9152183532714844:   7%|▋         | 1806/25880 [24:34<4:44:33,  1.41it/s]
1|1807|Loss: 0.9152183532714844:   7%|▋         | 1807/25880 [24:35<4:48:30,  1.39it/s]
1|1808|Loss: 0.9919429421424866:   7%|▋         | 1807/25880 [24:35<4:48:30,  1.39it/s]
1|1808|Loss: 0.9919429421424866:   7%|▋         | 1808/25880 [24:35<4:37:35,  1.45it/s]
1|1809|Loss: 0.807901918888092:   7%|▋         | 1808/25880 [24:36<4:37:35,  1.45it/s] 
1|1809|Loss: 0.807901918888092:   7%|▋         | 1809/25880 [24:36<4:38:37,  1.44it/s]
1|1810|Loss: 0.9024315476417542:   7%|▋         | 1809/25880 [24:37<4:38:37,  1.44it/s]
1|1810|Loss: 0.9024315476417542:   7%|▋         | 1810/25880 [24:37<4:34:00,  1.46it/s]
1|1811|Loss: 1.012114405632019:   7%|▋         | 1810/25880 [24:37<4:34:00,  1.46it/s] 
1|1811|Loss: 1.012114405632019:   7%|▋         | 1811/25880 [24:37<4:26:19,  1.51it/s]
1|1812|Loss: 0.9403834342956543:   7%|▋         | 1811/25880 [24:38<4:26:19,  1.51it/s]
1|1812|Loss: 0.9403834342956543:   7%|▋         | 1812/25880 [24:38<4:20:53,  1.54it/s]
1|1813|Loss: 0.9034838080406189:   7%|▋         | 1812/25880 [24:38<4:20:53,  1.54it/s]
1|1813|Loss: 0.9034838080406189:   7%|▋         | 1813/25880 [24:39<4:50:21,  1.38it/s]
1|1814|Loss: 0.7446664571762085:   7%|▋         | 1813/25880 [24:39<4:50:21,  1.38it/s]
1|1814|Loss: 0.7446664571762085:   7%|▋         | 1814/25880 [24:40<5:07:23,  1.30it/s]
1|1815|Loss: 0.7724085450172424:   7%|▋         | 1814/25880 [24:40<5:07:23,  1.30it/s]
1|1815|Loss: 0.7724085450172424:   7%|▋         | 1815/25880 [24:41<5:23:30,  1.24it/s]
1|1816|Loss: 0.9622483253479004:   7%|▋         | 1815/25880 [24:41<5:23:30,  1.24it/s]
1|1816|Loss: 0.9622483253479004:   7%|▋         | 1816/25880 [24:41<5:07:32,  1.30it/s]
1|1817|Loss: 0.7386387586593628:   7%|▋         | 1816/25880 [24:42<5:07:32,  1.30it/s]
1|1817|Loss: 0.7386387586593628:   7%|▋         | 1817/25880 [24:42<4:46:55,  1.40it/s]
1|1818|Loss: 0.8910448551177979:   7%|▋         | 1817/25880 [24:42<4:46:55,  1.40it/s]
1|1818|Loss: 0.8910448551177979:   7%|▋         | 1818/25880 [24:43<4:42:22,  1.42it/s]
1|1819|Loss: 0.8450075387954712:   7%|▋         | 1818/25880 [24:43<4:42:22,  1.42it/s]
1|1819|Loss: 0.8450075387954712:   7%|▋         | 1819/25880 [24:43<4:42:34,  1.42it/s]
1|1820|Loss: 0.8564255237579346:   7%|▋         | 1819/25880 [24:44<4:42:34,  1.42it/s]
1|1820|Loss: 0.8564255237579346:   7%|▋         | 1820/25880 [24:44<4:46:42,  1.40it/s]
1|1821|Loss: 0.7780359983444214:   7%|▋         | 1820/25880 [24:44<4:46:42,  1.40it/s]
1|1821|Loss: 0.7780359983444214:   7%|▋         | 1821/25880 [24:45<4:49:53,  1.38it/s]
1|1822|Loss: 0.8742129802703857:   7%|▋         | 1821/25880 [24:45<4:49:53,  1.38it/s]
1|1822|Loss: 0.8742129802703857:   7%|▋         | 1822/25880 [24:46<4:57:33,  1.35it/s]
1|1823|Loss: 0.82325279712677:   7%|▋         | 1822/25880 [24:46<4:57:33,  1.35it/s]  
1|1823|Loss: 0.82325279712677:   7%|▋         | 1823/25880 [24:46<4:57:47,  1.35it/s]
1|1824|Loss: 0.893994927406311:   7%|▋         | 1823/25880 [24:47<4:57:47,  1.35it/s]
1|1824|Loss: 0.893994927406311:   7%|▋         | 1824/25880 [24:47<4:45:50,  1.40it/s]
1|1825|Loss: 0.7426729798316956:   7%|▋         | 1824/25880 [24:47<4:45:50,  1.40it/s]
1|1825|Loss: 0.7426729798316956:   7%|▋         | 1825/25880 [24:48<4:21:40,  1.53it/s]
1|1826|Loss: 0.86055988073349:   7%|▋         | 1825/25880 [24:48<4:21:40,  1.53it/s]  
1|1826|Loss: 0.86055988073349:   7%|▋         | 1826/25880 [24:48<4:05:51,  1.63it/s]
1|1827|Loss: 0.9173657894134521:   7%|▋         | 1826/25880 [24:48<4:05:51,  1.63it/s]
1|1827|Loss: 0.9173657894134521:   7%|▋         | 1827/25880 [24:49<4:17:12,  1.56it/s]
1|1828|Loss: 0.9958573579788208:   7%|▋         | 1827/25880 [24:49<4:17:12,  1.56it/s]
1|1828|Loss: 0.9958573579788208:   7%|▋         | 1828/25880 [24:49<4:20:43,  1.54it/s]
1|1829|Loss: 0.8804016709327698:   7%|▋         | 1828/25880 [24:50<4:20:43,  1.54it/s]
1|1829|Loss: 0.8804016709327698:   7%|▋         | 1829/25880 [24:50<4:17:45,  1.56it/s]
1|1830|Loss: 0.8136934041976929:   7%|▋         | 1829/25880 [24:50<4:17:45,  1.56it/s]
1|1830|Loss: 0.8136934041976929:   7%|▋         | 1830/25880 [24:51<4:35:09,  1.46it/s]
1|1831|Loss: 1.0356814861297607:   7%|▋         | 1830/25880 [24:51<4:35:09,  1.46it/s]
1|1831|Loss: 1.0356814861297607:   7%|▋         | 1831/25880 [24:51<4:31:56,  1.47it/s]
1|1832|Loss: 0.9261301159858704:   7%|▋         | 1831/25880 [24:52<4:31:56,  1.47it/s]
1|1832|Loss: 0.9261301159858704:   7%|▋         | 1832/25880 [24:52<4:49:38,  1.38it/s]
1|1833|Loss: 0.9727784395217896:   7%|▋         | 1832/25880 [24:53<4:49:38,  1.38it/s]
1|1833|Loss: 0.9727784395217896:   7%|▋         | 1833/25880 [24:53<5:03:44,  1.32it/s]
1|1834|Loss: 1.0551546812057495:   7%|▋         | 1833/25880 [24:54<5:03:44,  1.32it/s]
1|1834|Loss: 1.0551546812057495:   7%|▋         | 1834/25880 [24:54<5:03:21,  1.32it/s]
1|1835|Loss: 0.8459258079528809:   7%|▋         | 1834/25880 [24:54<5:03:21,  1.32it/s]
1|1835|Loss: 0.8459258079528809:   7%|▋         | 1835/25880 [24:54<4:25:20,  1.51it/s]
1|1836|Loss: 0.8717199563980103:   7%|▋         | 1835/25880 [24:55<4:25:20,  1.51it/s]
1|1836|Loss: 0.8717199563980103:   7%|▋         | 1836/25880 [24:55<4:25:55,  1.51it/s]
1|1837|Loss: 0.9355879426002502:   7%|▋         | 1836/25880 [24:55<4:25:55,  1.51it/s]
1|1837|Loss: 0.9355879426002502:   7%|▋         | 1837/25880 [24:56<4:40:01,  1.43it/s]
1|1838|Loss: 0.9627153873443604:   7%|▋         | 1837/25880 [24:56<4:40:01,  1.43it/s]
1|1838|Loss: 0.9627153873443604:   7%|▋         | 1838/25880 [24:57<4:52:03,  1.37it/s]
1|1839|Loss: 0.8456707000732422:   7%|▋         | 1838/25880 [24:57<4:52:03,  1.37it/s]
1|1839|Loss: 0.8456707000732422:   7%|▋         | 1839/25880 [24:57<4:43:52,  1.41it/s]
1|1840|Loss: 0.786507248878479:   7%|▋         | 1839/25880 [24:58<4:43:52,  1.41it/s] 
1|1840|Loss: 0.786507248878479:   7%|▋         | 1840/25880 [24:58<4:23:08,  1.52it/s]
1|1841|Loss: 0.7864192128181458:   7%|▋         | 1840/25880 [24:58<4:23:08,  1.52it/s]
1|1841|Loss: 0.7864192128181458:   7%|▋         | 1841/25880 [24:58<4:17:15,  1.56it/s]
1|1842|Loss: 0.8423699736595154:   7%|▋         | 1841/25880 [24:59<4:17:15,  1.56it/s]
1|1842|Loss: 0.8423699736595154:   7%|▋         | 1842/25880 [24:59<4:26:31,  1.50it/s]
1|1843|Loss: 1.0052211284637451:   7%|▋         | 1842/25880 [24:59<4:26:31,  1.50it/s]
1|1843|Loss: 1.0052211284637451:   7%|▋         | 1843/25880 [25:00<4:22:56,  1.52it/s]
1|1844|Loss: 0.8881122469902039:   7%|▋         | 1843/25880 [25:00<4:22:56,  1.52it/s]
1|1844|Loss: 0.8881122469902039:   7%|▋         | 1844/25880 [25:00<4:29:20,  1.49it/s]
1|1845|Loss: 0.8548437356948853:   7%|▋         | 1844/25880 [25:01<4:29:20,  1.49it/s]
1|1845|Loss: 0.8548437356948853:   7%|▋         | 1845/25880 [25:01<4:36:45,  1.45it/s]
1|1846|Loss: 1.0033214092254639:   7%|▋         | 1845/25880 [25:02<4:36:45,  1.45it/s]
1|1846|Loss: 1.0033214092254639:   7%|▋         | 1846/25880 [25:02<4:41:47,  1.42it/s]
1|1847|Loss: 0.9914506673812866:   7%|▋         | 1846/25880 [25:02<4:41:47,  1.42it/s]
1|1847|Loss: 0.9914506673812866:   7%|▋         | 1847/25880 [25:03<4:36:18,  1.45it/s]
1|1848|Loss: 0.9762967228889465:   7%|▋         | 1847/25880 [25:03<4:36:18,  1.45it/s]
1|1848|Loss: 0.9762967228889465:   7%|▋         | 1848/25880 [25:03<4:27:50,  1.50it/s]
1|1849|Loss: 0.7368032336235046:   7%|▋         | 1848/25880 [25:04<4:27:50,  1.50it/s]
1|1849|Loss: 0.7368032336235046:   7%|▋         | 1849/25880 [25:04<4:47:16,  1.39it/s]
1|1850|Loss: 0.8723832368850708:   7%|▋         | 1849/25880 [25:05<4:47:16,  1.39it/s]
1|1850|Loss: 0.8723832368850708:   7%|▋         | 1850/25880 [25:05<5:07:19,  1.30it/s]
1|1851|Loss: 0.9189714789390564:   7%|▋         | 1850/25880 [25:05<5:07:19,  1.30it/s]
1|1851|Loss: 0.9189714789390564:   7%|▋         | 1851/25880 [25:06<4:56:28,  1.35it/s]
1|1852|Loss: 0.7911412119865417:   7%|▋         | 1851/25880 [25:06<4:56:28,  1.35it/s]
1|1852|Loss: 0.7911412119865417:   7%|▋         | 1852/25880 [25:06<4:58:24,  1.34it/s]
1|1853|Loss: 0.9044487476348877:   7%|▋         | 1852/25880 [25:07<4:58:24,  1.34it/s]
1|1853|Loss: 0.9044487476348877:   7%|▋         | 1853/25880 [25:07<5:17:02,  1.26it/s]
1|1854|Loss: 0.8321210741996765:   7%|▋         | 1853/25880 [25:08<5:17:02,  1.26it/s]
1|1854|Loss: 0.8321210741996765:   7%|▋         | 1854/25880 [25:08<5:05:25,  1.31it/s]
1|1855|Loss: 0.7835183143615723:   7%|▋         | 1854/25880 [25:08<5:05:25,  1.31it/s]
1|1855|Loss: 0.7835183143615723:   7%|▋         | 1855/25880 [25:09<5:04:41,  1.31it/s]
1|1856|Loss: 0.6585712432861328:   7%|▋         | 1855/25880 [25:09<5:04:41,  1.31it/s]
1|1856|Loss: 0.6585712432861328:   7%|▋         | 1856/25880 [25:09<5:00:12,  1.33it/s]
1|1857|Loss: 0.8304957151412964:   7%|▋         | 1856/25880 [25:10<5:00:12,  1.33it/s]
1|1857|Loss: 0.8304957151412964:   7%|▋         | 1857/25880 [25:10<5:03:08,  1.32it/s]
1|1858|Loss: 0.9377970099449158:   7%|▋         | 1857/25880 [25:11<5:03:08,  1.32it/s]
1|1858|Loss: 0.9377970099449158:   7%|▋         | 1858/25880 [25:11<4:51:20,  1.37it/s]
1|1859|Loss: 0.9645376801490784:   7%|▋         | 1858/25880 [25:11<4:51:20,  1.37it/s]
1|1859|Loss: 0.9645376801490784:   7%|▋         | 1859/25880 [25:11<4:38:31,  1.44it/s]
1|1860|Loss: 0.9995905756950378:   7%|▋         | 1859/25880 [25:12<4:38:31,  1.44it/s]
1|1860|Loss: 0.9995905756950378:   7%|▋         | 1860/25880 [25:12<4:49:33,  1.38it/s]
1|1861|Loss: 0.9036593437194824:   7%|▋         | 1860/25880 [25:13<4:49:33,  1.38it/s]
1|1861|Loss: 0.9036593437194824:   7%|▋         | 1861/25880 [25:13<4:59:49,  1.34it/s]
1|1862|Loss: 0.961065411567688:   7%|▋         | 1861/25880 [25:13<4:59:49,  1.34it/s] 
1|1862|Loss: 0.961065411567688:   7%|▋         | 1862/25880 [25:14<4:56:24,  1.35it/s]
1|1863|Loss: 0.9566631317138672:   7%|▋         | 1862/25880 [25:14<4:56:24,  1.35it/s]
1|1863|Loss: 0.9566631317138672:   7%|▋         | 1863/25880 [25:15<4:54:44,  1.36it/s]
1|1864|Loss: 0.8290411233901978:   7%|▋         | 1863/25880 [25:15<4:54:44,  1.36it/s]
1|1864|Loss: 0.8290411233901978:   7%|▋         | 1864/25880 [25:15<4:54:36,  1.36it/s]
1|1865|Loss: 0.7031968832015991:   7%|▋         | 1864/25880 [25:16<4:54:36,  1.36it/s]
1|1865|Loss: 0.7031968832015991:   7%|▋         | 1865/25880 [25:16<5:01:45,  1.33it/s]
1|1866|Loss: 0.8479530811309814:   7%|▋         | 1865/25880 [25:16<5:01:45,  1.33it/s]
1|1866|Loss: 0.8479530811309814:   7%|▋         | 1866/25880 [25:17<4:57:00,  1.35it/s]
1|1867|Loss: 0.8029713034629822:   7%|▋         | 1866/25880 [25:17<4:57:00,  1.35it/s]
1|1867|Loss: 0.8029713034629822:   7%|▋         | 1867/25880 [25:17<4:54:44,  1.36it/s]
1|1868|Loss: 0.7717968821525574:   7%|▋         | 1867/25880 [25:18<4:54:44,  1.36it/s]
1|1868|Loss: 0.7717968821525574:   7%|▋         | 1868/25880 [25:18<4:51:32,  1.37it/s]
1|1869|Loss: 0.8410069346427917:   7%|▋         | 1868/25880 [25:19<4:51:32,  1.37it/s]
1|1869|Loss: 0.8410069346427917:   7%|▋         | 1869/25880 [25:19<5:02:43,  1.32it/s]
1|1870|Loss: 0.8966278433799744:   7%|▋         | 1869/25880 [25:19<5:02:43,  1.32it/s]
1|1870|Loss: 0.8966278433799744:   7%|▋         | 1870/25880 [25:20<4:46:20,  1.40it/s]
1|1871|Loss: 0.8270439505577087:   7%|▋         | 1870/25880 [25:20<4:46:20,  1.40it/s]
1|1871|Loss: 0.8270439505577087:   7%|▋         | 1871/25880 [25:20<4:40:44,  1.43it/s]
1|1872|Loss: 0.7687872052192688:   7%|▋         | 1871/25880 [25:21<4:40:44,  1.43it/s]
1|1872|Loss: 0.7687872052192688:   7%|▋         | 1872/25880 [25:21<4:40:24,  1.43it/s]
1|1873|Loss: 1.0038692951202393:   7%|▋         | 1872/25880 [25:21<4:40:24,  1.43it/s]
1|1873|Loss: 1.0038692951202393:   7%|▋         | 1873/25880 [25:22<4:33:47,  1.46it/s]
1|1874|Loss: 0.9341152310371399:   7%|▋         | 1873/25880 [25:22<4:33:47,  1.46it/s]
1|1874|Loss: 0.9341152310371399:   7%|▋         | 1874/25880 [25:22<4:36:53,  1.44it/s]
1|1875|Loss: 0.965275228023529:   7%|▋         | 1874/25880 [25:23<4:36:53,  1.44it/s] 
1|1875|Loss: 0.965275228023529:   7%|▋         | 1875/25880 [25:23<4:50:59,  1.37it/s]
1|1876|Loss: 1.1197693347930908:   7%|▋         | 1875/25880 [25:24<4:50:59,  1.37it/s]
1|1876|Loss: 1.1197693347930908:   7%|▋         | 1876/25880 [25:24<5:00:47,  1.33it/s]
1|1877|Loss: 0.7393854260444641:   7%|▋         | 1876/25880 [25:24<5:00:47,  1.33it/s]
1|1877|Loss: 0.7393854260444641:   7%|▋         | 1877/25880 [25:25<4:49:19,  1.38it/s]
1|1878|Loss: 0.7062352895736694:   7%|▋         | 1877/25880 [25:25<4:49:19,  1.38it/s]
1|1878|Loss: 0.7062352895736694:   7%|▋         | 1878/25880 [25:25<5:04:50,  1.31it/s]
1|1879|Loss: 0.912169873714447:   7%|▋         | 1878/25880 [25:26<5:04:50,  1.31it/s] 
1|1879|Loss: 0.912169873714447:   7%|▋         | 1879/25880 [25:26<4:55:44,  1.35it/s]
1|1880|Loss: 0.8115476965904236:   7%|▋         | 1879/25880 [25:27<4:55:44,  1.35it/s]
1|1880|Loss: 0.8115476965904236:   7%|▋         | 1880/25880 [25:27<4:30:55,  1.48it/s]
1|1881|Loss: 0.8492420315742493:   7%|▋         | 1880/25880 [25:27<4:30:55,  1.48it/s]
1|1881|Loss: 0.8492420315742493:   7%|▋         | 1881/25880 [25:27<4:28:34,  1.49it/s]
1|1882|Loss: 0.7116723656654358:   7%|▋         | 1881/25880 [25:28<4:28:34,  1.49it/s]
1|1882|Loss: 0.7116723656654358:   7%|▋         | 1882/25880 [25:28<4:17:38,  1.55it/s]
1|1883|Loss: 0.8705387711524963:   7%|▋         | 1882/25880 [25:28<4:17:38,  1.55it/s]
1|1883|Loss: 0.8705387711524963:   7%|▋         | 1883/25880 [25:29<4:06:58,  1.62it/s]
1|1884|Loss: 0.789178729057312:   7%|▋         | 1883/25880 [25:29<4:06:58,  1.62it/s] 
1|1884|Loss: 0.789178729057312:   7%|▋         | 1884/25880 [25:29<4:16:35,  1.56it/s]
1|1885|Loss: 0.9871864318847656:   7%|▋         | 1884/25880 [25:30<4:16:35,  1.56it/s]
1|1885|Loss: 0.9871864318847656:   7%|▋         | 1885/25880 [25:30<4:24:23,  1.51it/s]
1|1886|Loss: 0.7747324109077454:   7%|▋         | 1885/25880 [25:30<4:24:23,  1.51it/s]
1|1886|Loss: 0.7747324109077454:   7%|▋         | 1886/25880 [25:31<4:29:14,  1.49it/s]
1|1887|Loss: 0.9160608649253845:   7%|▋         | 1886/25880 [25:31<4:29:14,  1.49it/s]
1|1887|Loss: 0.9160608649253845:   7%|▋         | 1887/25880 [25:31<4:40:24,  1.43it/s]
1|1888|Loss: 0.8150686621665955:   7%|▋         | 1887/25880 [25:32<4:40:24,  1.43it/s]
1|1888|Loss: 0.8150686621665955:   7%|▋         | 1888/25880 [25:32<4:43:45,  1.41it/s]
1|1889|Loss: 0.8974069952964783:   7%|▋         | 1888/25880 [25:33<4:43:45,  1.41it/s]
1|1889|Loss: 0.8974069952964783:   7%|▋         | 1889/25880 [25:33<4:44:55,  1.40it/s]
1|1890|Loss: 0.9753139019012451:   7%|▋         | 1889/25880 [25:33<4:44:55,  1.40it/s]
1|1890|Loss: 0.9753139019012451:   7%|▋         | 1890/25880 [25:33<4:27:47,  1.49it/s]
1|1891|Loss: 0.829940915107727:   7%|▋         | 1890/25880 [25:34<4:27:47,  1.49it/s] 
1|1891|Loss: 0.829940915107727:   7%|��         | 1891/25880 [25:34<4:21:31,  1.53it/s]
1|1892|Loss: 0.8016127347946167:   7%|▋         | 1891/25880 [25:34<4:21:31,  1.53it/s]
1|1892|Loss: 0.8016127347946167:   7%|▋         | 1892/25880 [25:35<4:29:06,  1.49it/s]
1|1893|Loss: 0.8525596261024475:   7%|▋         | 1892/25880 [25:35<4:29:06,  1.49it/s]
1|1893|Loss: 0.8525596261024475:   7%|▋         | 1893/25880 [25:35<4:24:25,  1.51it/s]
1|1894|Loss: 0.8267694711685181:   7%|▋         | 1893/25880 [25:36<4:24:25,  1.51it/s]
1|1894|Loss: 0.8267694711685181:   7%|▋         | 1894/25880 [25:36<4:15:00,  1.57it/s]
1|1895|Loss: 0.8188226819038391:   7%|▋         | 1894/25880 [25:36<4:15:00,  1.57it/s]
1|1895|Loss: 0.8188226819038391:   7%|▋         | 1895/25880 [25:37<4:34:01,  1.46it/s]
1|1896|Loss: 0.7930740714073181:   7%|▋         | 1895/25880 [25:37<4:34:01,  1.46it/s]
1|1896|Loss: 0.7930740714073181:   7%|▋         | 1896/25880 [25:38<4:49:39,  1.38it/s]
1|1897|Loss: 0.8641759753227234:   7%|▋         | 1896/25880 [25:38<4:49:39,  1.38it/s]
1|1897|Loss: 0.8641759753227234:   7%|▋         | 1897/25880 [25:38<5:09:23,  1.29it/s]
1|1898|Loss: 0.9462007284164429:   7%|▋         | 1897/25880 [25:39<5:09:23,  1.29it/s]
1|1898|Loss: 0.9462007284164429:   7%|▋         | 1898/25880 [25:39<4:59:11,  1.34it/s]
1|1899|Loss: 0.949735164642334:   7%|▋         | 1898/25880 [25:40<4:59:11,  1.34it/s] 
1|1899|Loss: 0.949735164642334:   7%|▋         | 1899/25880 [25:40<5:06:20,  1.30it/s]
1|1900|Loss: 1.122544527053833:   7%|▋         | 1899/25880 [25:40<5:06:20,  1.30it/s]
1|1900|Loss: 1.122544527053833:   7%|▋         | 1900/25880 [25:41<5:02:57,  1.32it/s]
1|1901|Loss: 0.9130248427391052:   7%|▋         | 1900/25880 [25:41<5:02:57,  1.32it/s]
1|1901|Loss: 0.9130248427391052:   7%|▋         | 1901/25880 [25:41<4:31:46,  1.47it/s]
1|1902|Loss: 0.8381566405296326:   7%|▋         | 1901/25880 [25:42<4:31:46,  1.47it/s]
1|1902|Loss: 0.8381566405296326:   7%|▋         | 1902/25880 [25:42<4:30:35,  1.48it/s]
1|1903|Loss: 0.8896343111991882:   7%|▋         | 1902/25880 [25:42<4:30:35,  1.48it/s]
1|1903|Loss: 0.8896343111991882:   7%|▋         | 1903/25880 [25:43<4:38:52,  1.43it/s]
1|1904|Loss: 0.8812887668609619:   7%|▋         | 1903/25880 [25:43<4:38:52,  1.43it/s]
1|1904|Loss: 0.8812887668609619:   7%|▋         | 1904/25880 [25:43<4:41:27,  1.42it/s]
1|1905|Loss: 0.8530343770980835:   7%|▋         | 1904/25880 [25:44<4:41:27,  1.42it/s]
1|1905|Loss: 0.8530343770980835:   7%|▋         | 1905/25880 [25:44<4:26:56,  1.50it/s]
1|1906|Loss: 0.7810801863670349:   7%|▋         | 1905/25880 [25:44<4:26:56,  1.50it/s]
1|1906|Loss: 0.7810801863670349:   7%|▋         | 1906/25880 [25:45<4:21:35,  1.53it/s]
1|1907|Loss: 0.9389748573303223:   7%|▋         | 1906/25880 [25:45<4:21:35,  1.53it/s]
1|1907|Loss: 0.9389748573303223:   7%|▋         | 1907/25880 [25:45<4:34:30,  1.46it/s]
1|1908|Loss: 0.7160785794258118:   7%|▋         | 1907/25880 [25:46<4:34:30,  1.46it/s]
1|1908|Loss: 0.7160785794258118:   7%|▋         | 1908/25880 [25:46<5:18:22,  1.25it/s]
1|1909|Loss: 0.7949849367141724:   7%|▋         | 1908/25880 [25:47<5:18:22,  1.25it/s]
1|1909|Loss: 0.7949849367141724:   7%|▋         | 1909/25880 [25:47<5:05:24,  1.31it/s]
1|1910|Loss: 0.8747372627258301:   7%|▋         | 1909/25880 [25:47<5:05:24,  1.31it/s]
1|1910|Loss: 0.8747372627258301:   7%|▋         | 1910/25880 [25:48<5:23:02,  1.24it/s]
1|1911|Loss: 1.0228067636489868:   7%|▋         | 1910/25880 [25:48<5:23:02,  1.24it/s]
1|1911|Loss: 1.0228067636489868:   7%|▋         | 1911/25880 [25:49<5:27:57,  1.22it/s]
1|1912|Loss: 0.7574563026428223:   7%|▋         | 1911/25880 [25:49<5:27:57,  1.22it/s]
1|1912|Loss: 0.7574563026428223:   7%|▋         | 1912/25880 [25:49<4:59:44,  1.33it/s]
1|1913|Loss: 0.8080346584320068:   7%|▋         | 1912/25880 [25:50<4:59:44,  1.33it/s]
1|1913|Loss: 0.8080346584320068:   7%|▋         | 1913/25880 [25:50<4:59:29,  1.33it/s]
1|1914|Loss: 0.9351176023483276:   7%|▋         | 1913/25880 [25:51<4:59:29,  1.33it/s]
1|1914|Loss: 0.9351176023483276:   7%|▋         | 1914/25880 [25:51<4:50:28,  1.38it/s]
1|1915|Loss: 0.9318501949310303:   7%|▋         | 1914/25880 [25:51<4:50:28,  1.38it/s]
1|1915|Loss: 0.9318501949310303:   7%|▋         | 1915/25880 [25:52<4:58:55,  1.34it/s]
1|1916|Loss: 0.8797577619552612:   7%|▋         | 1915/25880 [25:52<4:58:55,  1.34it/s]
1|1916|Loss: 0.8797577619552612:   7%|▋         | 1916/25880 [25:52<4:47:47,  1.39it/s]
1|1917|Loss: 0.9795059561729431:   7%|▋         | 1916/25880 [25:53<4:47:47,  1.39it/s]
1|1917|Loss: 0.9795059561729431:   7%|▋         | 1917/25880 [25:53<4:37:08,  1.44it/s]
1|1918|Loss: 0.8890841007232666:   7%|▋         | 1917/25880 [25:53<4:37:08,  1.44it/s]
1|1918|Loss: 0.8890841007232666:   7%|▋         | 1918/25880 [25:54<4:36:22,  1.45it/s]
1|1919|Loss: 0.7521286606788635:   7%|▋         | 1918/25880 [25:54<4:36:22,  1.45it/s]
1|1919|Loss: 0.7521286606788635:   7%|▋         | 1919/25880 [25:54<4:27:01,  1.50it/s]
1|1920|Loss: 0.8918337225914001:   7%|▋         | 1919/25880 [25:55<4:27:01,  1.50it/s]
1|1920|Loss: 0.8918337225914001:   7%|▋         | 1920/25880 [25:55<4:30:50,  1.47it/s]
1|1921|Loss: 0.9626703858375549:   7%|▋         | 1920/25880 [25:55<4:30:50,  1.47it/s]
1|1921|Loss: 0.9626703858375549:   7%|▋         | 1921/25880 [25:56<4:37:20,  1.44it/s]
1|1922|Loss: 0.780852198600769:   7%|▋         | 1921/25880 [25:56<4:37:20,  1.44it/s] 
1|1922|Loss: 0.780852198600769:   7%|▋         | 1922/25880 [25:56<4:38:51,  1.43it/s]
1|1923|Loss: 0.8355371952056885:   7%|▋         | 1922/25880 [25:57<4:38:51,  1.43it/s]
1|1923|Loss: 0.8355371952056885:   7%|▋         | 1923/25880 [25:57<4:33:00,  1.46it/s]
1|1924|Loss: 0.7566738128662109:   7%|▋         | 1923/25880 [25:57<4:33:00,  1.46it/s]
1|1924|Loss: 0.7566738128662109:   7%|▋         | 1924/25880 [25:58<4:37:07,  1.44it/s]
1|1925|Loss: 0.8340115547180176:   7%|▋         | 1924/25880 [25:58<4:37:07,  1.44it/s]
1|1925|Loss: 0.8340115547180176:   7%|▋         | 1925/25880 [25:58<4:43:23,  1.41it/s]
1|1926|Loss: 1.0844401121139526:   7%|▋         | 1925/25880 [25:59<4:43:23,  1.41it/s]
1|1926|Loss: 1.0844401121139526:   7%|▋         | 1926/25880 [25:59<4:56:04,  1.35it/s]
1|1927|Loss: 0.9316347241401672:   7%|▋         | 1926/25880 [26:00<4:56:04,  1.35it/s]
1|1927|Loss: 0.9316347241401672:   7%|▋         | 1927/25880 [26:00<5:02:12,  1.32it/s]
1|1928|Loss: 1.1643093824386597:   7%|▋         | 1927/25880 [26:00<5:02:12,  1.32it/s]
1|1928|Loss: 1.1643093824386597:   7%|▋         | 1928/25880 [26:01<4:51:44,  1.37it/s]
1|1929|Loss: 0.8496191501617432:   7%|▋         | 1928/25880 [26:01<4:51:44,  1.37it/s]
1|1929|Loss: 0.8496191501617432:   7%|▋         | 1929/25880 [26:02<5:00:27,  1.33it/s]
1|1930|Loss: 0.8282564282417297:   7%|▋         | 1929/25880 [26:02<5:00:27,  1.33it/s]
1|1930|Loss: 0.8282564282417297:   7%|▋         | 1930/25880 [26:02<5:10:49,  1.28it/s]
1|1931|Loss: 0.8827641010284424:   7%|▋         | 1930/25880 [26:03<5:10:49,  1.28it/s]
1|1931|Loss: 0.8827641010284424:   7%|▋         | 1931/25880 [26:03<5:08:59,  1.29it/s]
1|1932|Loss: 0.9602141380310059:   7%|▋         | 1931/25880 [26:04<5:08:59,  1.29it/s]
1|1932|Loss: 0.9602141380310059:   7%|▋         | 1932/25880 [26:04<4:56:27,  1.35it/s]
1|1933|Loss: 0.9092472195625305:   7%|▋         | 1932/25880 [26:04<4:56:27,  1.35it/s]
1|1933|Loss: 0.9092472195625305:   7%|▋         | 1933/25880 [26:04<4:44:32,  1.40it/s]
1|1934|Loss: 0.8630181550979614:   7%|▋         | 1933/25880 [26:05<4:44:32,  1.40it/s]
1|1934|Loss: 0.8630181550979614:   7%|▋         | 1934/25880 [26:05<4:36:29,  1.44it/s]
1|1935|Loss: 0.9317601919174194:   7%|▋         | 1934/25880 [26:06<4:36:29,  1.44it/s]
1|1935|Loss: 0.9317601919174194:   7%|▋         | 1935/25880 [26:06<4:51:13,  1.37it/s]
1|1936|Loss: 0.7717365622520447:   7%|▋         | 1935/25880 [26:06<4:51:13,  1.37it/s]
1|1936|Loss: 0.7717365622520447:   7%|▋         | 1936/25880 [26:07<5:00:22,  1.33it/s]
1|1937|Loss: 0.8510021567344666:   7%|▋         | 1936/25880 [26:07<5:00:22,  1.33it/s]
1|1937|Loss: 0.8510021567344666:   7%|▋         | 1937/25880 [26:07<4:56:47,  1.34it/s]
1|1938|Loss: 0.8425734043121338:   7%|▋         | 1937/25880 [26:08<4:56:47,  1.34it/s]
1|1938|Loss: 0.8425734043121338:   7%|▋         | 1938/25880 [26:08<4:39:44,  1.43it/s]
1|1939|Loss: 0.8227239847183228:   7%|▋         | 1938/25880 [26:08<4:39:44,  1.43it/s]
1|1939|Loss: 0.8227239847183228:   7%|▋         | 1939/25880 [26:09<4:49:33,  1.38it/s]
1|1940|Loss: 0.8587467074394226:   7%|▋         | 1939/25880 [26:09<4:49:33,  1.38it/s]
1|1940|Loss: 0.8587467074394226:   7%|▋         | 1940/25880 [26:10<4:52:16,  1.37it/s]
1|1941|Loss: 0.7694913148880005:   7%|▋         | 1940/25880 [26:10<4:52:16,  1.37it/s]
1|1941|Loss: 0.7694913148880005:   8%|▊         | 1941/25880 [26:10<4:52:45,  1.36it/s]
1|1942|Loss: 0.9698306322097778:   8%|▊         | 1941/25880 [26:11<4:52:45,  1.36it/s]
1|1942|Loss: 0.9698306322097778:   8%|▊         | 1942/25880 [26:11<4:54:17,  1.36it/s]
1|1943|Loss: 0.9654108881950378:   8%|▊         | 1942/25880 [26:11<4:54:17,  1.36it/s]
1|1943|Loss: 0.9654108881950378:   8%|▊         | 1943/25880 [26:12<4:45:46,  1.40it/s]
1|1944|Loss: 0.9802228808403015:   8%|▊         | 1943/25880 [26:12<4:45:46,  1.40it/s]
1|1944|Loss: 0.9802228808403015:   8%|▊         | 1944/25880 [26:13<4:55:06,  1.35it/s]
1|1945|Loss: 0.8659336566925049:   8%|▊         | 1944/25880 [26:13<4:55:06,  1.35it/s]
1|1945|Loss: 0.8659336566925049:   8%|▊         | 1945/25880 [26:13<4:57:44,  1.34it/s]
1|1946|Loss: 0.8791990280151367:   8%|▊         | 1945/25880 [26:14<4:57:44,  1.34it/s]
1|1946|Loss: 0.8791990280151367:   8%|▊         | 1946/25880 [26:14<4:46:15,  1.39it/s]
1|1947|Loss: 0.9200792908668518:   8%|▊         | 1946/25880 [26:14<4:46:15,  1.39it/s]
1|1947|Loss: 0.9200792908668518:   8%|▊         | 1947/25880 [26:15<4:34:34,  1.45it/s]
1|1948|Loss: 1.0317003726959229:   8%|▊         | 1947/25880 [26:15<4:34:34,  1.45it/s]
1|1948|Loss: 1.0317003726959229:   8%|▊         | 1948/25880 [26:15<4:36:54,  1.44it/s]
1|1949|Loss: 0.8203604221343994:   8%|▊         | 1948/25880 [26:16<4:36:54,  1.44it/s]
1|1949|Loss: 0.8203604221343994:   8%|▊         | 1949/25880 [26:16<4:38:39,  1.43it/s]
1|1950|Loss: 0.9305028319358826:   8%|▊         | 1949/25880 [26:16<4:38:39,  1.43it/s]
1|1950|Loss: 0.9305028319358826:   8%|▊         | 1950/25880 [26:17<4:47:03,  1.39it/s]
1|1951|Loss: 0.7420649528503418:   8%|▊         | 1950/25880 [26:17<4:47:03,  1.39it/s]
1|1951|Loss: 0.7420649528503418:   8%|▊         | 1951/25880 [26:18<5:02:39,  1.32it/s]
1|1952|Loss: 0.9129526615142822:   8%|▊         | 1951/25880 [26:18<5:02:39,  1.32it/s]
1|1952|Loss: 0.9129526615142822:   8%|▊         | 1952/25880 [26:18<4:48:37,  1.38it/s]
1|1953|Loss: 0.751027524471283:   8%|▊         | 1952/25880 [26:19<4:48:37,  1.38it/s] 
1|1953|Loss: 0.751027524471283:   8%|▊         | 1953/25880 [26:19<4:55:00,  1.35it/s]
1|1954|Loss: 0.7831611037254333:   8%|▊         | 1953/25880 [26:19<4:55:00,  1.35it/s]
1|1954|Loss: 0.7831611037254333:   8%|▊         | 1954/25880 [26:20<4:45:29,  1.40it/s]
1|1955|Loss: 0.939315140247345:   8%|▊         | 1954/25880 [26:20<4:45:29,  1.40it/s] 
1|1955|Loss: 0.939315140247345:   8%|▊         | 1955/25880 [26:20<4:41:58,  1.41it/s]
1|1956|Loss: 0.900826096534729:   8%|▊         | 1955/25880 [26:21<4:41:58,  1.41it/s]
1|1956|Loss: 0.900826096534729:   8%|▊         | 1956/25880 [26:21<4:35:57,  1.44it/s]
1|1957|Loss: 0.7107390761375427:   8%|▊         | 1956/25880 [26:21<4:35:57,  1.44it/s]
1|1957|Loss: 0.7107390761375427:   8%|▊         | 1957/25880 [26:22<4:45:28,  1.40it/s]
1|1958|Loss: 0.9924368858337402:   8%|▊         | 1957/25880 [26:22<4:45:28,  1.40it/s]
1|1958|Loss: 0.9924368858337402:   8%|▊         | 1958/25880 [26:23<4:46:07,  1.39it/s]
1|1959|Loss: 0.9452735781669617:   8%|▊         | 1958/25880 [26:23<4:46:07,  1.39it/s]
1|1959|Loss: 0.9452735781669617:   8%|▊         | 1959/25880 [26:23<4:46:46,  1.39it/s]
1|1960|Loss: 0.8067241907119751:   8%|▊         | 1959/25880 [26:24<4:46:46,  1.39it/s]
1|1960|Loss: 0.8067241907119751:   8%|▊         | 1960/25880 [26:24<4:33:04,  1.46it/s]
1|1961|Loss: 0.8912142515182495:   8%|▊         | 1960/25880 [26:24<4:33:04,  1.46it/s]
1|1961|Loss: 0.8912142515182495:   8%|▊         | 1961/25880 [26:25<4:49:10,  1.38it/s]
1|1962|Loss: 0.8613559603691101:   8%|▊         | 1961/25880 [26:25<4:49:10,  1.38it/s]
1|1962|Loss: 0.8613559603691101:   8%|▊         | 1962/25880 [26:25<4:40:01,  1.42it/s]
1|1963|Loss: 0.8919049501419067:   8%|▊         | 1962/25880 [26:26<4:40:01,  1.42it/s]
1|1963|Loss: 0.8919049501419067:   8%|▊         | 1963/25880 [26:26<4:36:59,  1.44it/s]
1|1964|Loss: 0.928048849105835:   8%|▊         | 1963/25880 [26:26<4:36:59,  1.44it/s] 
1|1964|Loss: 0.928048849105835:   8%|▊         | 1964/25880 [26:27<4:39:33,  1.43it/s]
1|1965|Loss: 0.896074652671814:   8%|▊         | 1964/25880 [26:27<4:39:33,  1.43it/s]
1|1965|Loss: 0.896074652671814:   8%|▊         | 1965/25880 [26:28<4:52:45,  1.36it/s]
1|1966|Loss: 0.9048970937728882:   8%|▊         | 1965/25880 [26:28<4:52:45,  1.36it/s]
1|1966|Loss: 0.9048970937728882:   8%|▊         | 1966/25880 [26:28<4:41:02,  1.42it/s]
1|1967|Loss: 1.0568042993545532:   8%|▊         | 1966/25880 [26:29<4:41:02,  1.42it/s]
1|1967|Loss: 1.0568042993545532:   8%|▊         | 1967/25880 [26:29<4:41:40,  1.41it/s]
1|1968|Loss: 0.9063449501991272:   8%|▊         | 1967/25880 [26:29<4:41:40,  1.41it/s]
1|1968|Loss: 0.9063449501991272:   8%|▊         | 1968/25880 [26:30<4:55:22,  1.35it/s]
1|1969|Loss: 0.8222008347511292:   8%|▊         | 1968/25880 [26:30<4:55:22,  1.35it/s]
1|1969|Loss: 0.8222008347511292:   8%|▊         | 1969/25880 [26:30<4:56:03,  1.35it/s]
1|1970|Loss: 0.9194784164428711:   8%|▊         | 1969/25880 [26:31<4:56:03,  1.35it/s]
1|1970|Loss: 0.9194784164428711:   8%|▊         | 1970/25880 [26:31<5:05:45,  1.30it/s]
1|1971|Loss: 0.7969092130661011:   8%|▊         | 1970/25880 [26:32<5:05:45,  1.30it/s]
1|1971|Loss: 0.7969092130661011:   8%|▊         | 1971/25880 [26:32<5:14:44,  1.27it/s]
1|1972|Loss: 0.9239910244941711:   8%|▊         | 1971/25880 [26:33<5:14:44,  1.27it/s]
1|1972|Loss: 0.9239910244941711:   8%|▊         | 1972/25880 [26:33<5:10:02,  1.29it/s]
1|1973|Loss: 0.9333072900772095:   8%|▊         | 1972/25880 [26:33<5:10:02,  1.29it/s]
1|1973|Loss: 0.9333072900772095:   8%|▊         | 1973/25880 [26:34<5:11:28,  1.28it/s]
1|1974|Loss: 0.9370822310447693:   8%|▊         | 1973/25880 [26:34<5:11:28,  1.28it/s]
1|1974|Loss: 0.9370822310447693:   8%|▊         | 1974/25880 [26:34<5:04:37,  1.31it/s]
1|1975|Loss: 0.8805047869682312:   8%|▊         | 1974/25880 [26:35<5:04:37,  1.31it/s]
1|1975|Loss: 0.8805047869682312:   8%|▊         | 1975/25880 [26:35<4:33:13,  1.46it/s]
1|1976|Loss: 1.1052825450897217:   8%|▊         | 1975/25880 [26:35<4:33:13,  1.46it/s]
1|1976|Loss: 1.1052825450897217:   8%|▊         | 1976/25880 [26:36<4:40:33,  1.42it/s]
1|1977|Loss: 0.9659276008605957:   8%|▊         | 1976/25880 [26:36<4:40:33,  1.42it/s]
1|1977|Loss: 0.9659276008605957:   8%|▊         | 1977/25880 [26:36<4:43:57,  1.40it/s]
1|1978|Loss: 0.7944340109825134:   8%|▊         | 1977/25880 [26:37<4:43:57,  1.40it/s]
1|1978|Loss: 0.7944340109825134:   8%|▊         | 1978/25880 [26:37<5:21:03,  1.24it/s]
1|1979|Loss: 0.9127511382102966:   8%|▊         | 1978/25880 [26:38<5:21:03,  1.24it/s]
1|1979|Loss: 0.9127511382102966:   8%|▊         | 1979/25880 [26:38<5:13:31,  1.27it/s]
1|1980|Loss: 0.861678421497345:   8%|▊         | 1979/25880 [26:38<5:13:31,  1.27it/s] 
1|1980|Loss: 0.861678421497345:   8%|▊         | 1980/25880 [26:39<4:41:41,  1.41it/s]
1|1981|Loss: 0.8407585620880127:   8%|▊         | 1980/25880 [26:39<4:41:41,  1.41it/s]
1|1981|Loss: 0.8407585620880127:   8%|▊         | 1981/25880 [26:39<4:29:35,  1.48it/s]
1|1982|Loss: 0.86418217420578:   8%|▊         | 1981/25880 [26:40<4:29:35,  1.48it/s]  
1|1982|Loss: 0.86418217420578:   8%|▊         | 1982/25880 [26:40<3:59:14,  1.66it/s]
1|1983|Loss: 1.001290202140808:   8%|▊         | 1982/25880 [26:40<3:59:14,  1.66it/s]
1|1983|Loss: 1.001290202140808:   8%|▊         | 1983/25880 [26:40<3:57:04,  1.68it/s]
1|1984|Loss: 0.9712169170379639:   8%|▊         | 1983/25880 [26:41<3:57:04,  1.68it/s]
1|1984|Loss: 0.9712169170379639:   8%|▊         | 1984/25880 [26:41<4:11:09,  1.59it/s]
1|1985|Loss: 0.9232835173606873:   8%|▊         | 1984/25880 [26:41<4:11:09,  1.59it/s]
1|1985|Loss: 0.9232835173606873:   8%|▊         | 1985/25880 [26:42<4:24:55,  1.50it/s]
1|1986|Loss: 0.886245608329773:   8%|▊         | 1985/25880 [26:42<4:24:55,  1.50it/s] 
1|1986|Loss: 0.886245608329773:   8%|▊         | 1986/25880 [26:42<4:19:06,  1.54it/s]
1|1987|Loss: 0.9118593335151672:   8%|▊         | 1986/25880 [26:43<4:19:06,  1.54it/s]
1|1987|Loss: 0.9118593335151672:   8%|▊         | 1987/25880 [26:43<4:15:43,  1.56it/s]
1|1988|Loss: 0.8960130214691162:   8%|▊         | 1987/25880 [26:43<4:15:43,  1.56it/s]
1|1988|Loss: 0.8960130214691162:   8%|▊         | 1988/25880 [26:44<4:21:23,  1.52it/s]
1|1989|Loss: 0.9171212315559387:   8%|▊         | 1988/25880 [26:44<4:21:23,  1.52it/s]
1|1989|Loss: 0.9171212315559387:   8%|▊         | 1989/25880 [26:44<4:30:21,  1.47it/s]
1|1990|Loss: 0.8644104599952698:   8%|▊         | 1989/25880 [26:45<4:30:21,  1.47it/s]
1|1990|Loss: 0.8644104599952698:   8%|▊         | 1990/25880 [26:45<4:28:27,  1.48it/s]
1|1991|Loss: 0.9173485636711121:   8%|▊         | 1990/25880 [26:45<4:28:27,  1.48it/s]
1|1991|Loss: 0.9173485636711121:   8%|▊         | 1991/25880 [26:46<4:44:57,  1.40it/s]
1|1992|Loss: 0.8831107020378113:   8%|▊         | 1991/25880 [26:46<4:44:57,  1.40it/s]
1|1992|Loss: 0.8831107020378113:   8%|▊         | 1992/25880 [26:47<5:14:46,  1.26it/s]
1|1993|Loss: 0.9712207317352295:   8%|▊         | 1992/25880 [26:47<5:14:46,  1.26it/s]
1|1993|Loss: 0.9712207317352295:   8%|▊         | 1993/25880 [26:48<5:15:48,  1.26it/s]
1|1994|Loss: 0.9063466787338257:   8%|▊         | 1993/25880 [26:48<5:15:48,  1.26it/s]
1|1994|Loss: 0.9063466787338257:   8%|▊         | 1994/25880 [26:48<5:21:02,  1.24it/s]
1|1995|Loss: 0.8939812183380127:   8%|▊         | 1994/25880 [26:49<5:21:02,  1.24it/s]
1|1995|Loss: 0.8939812183380127:   8%|▊         | 1995/25880 [26:49<5:26:38,  1.22it/s]
1|1996|Loss: 0.8907089233398438:   8%|▊         | 1995/25880 [26:50<5:26:38,  1.22it/s]
1|1996|Loss: 0.8907089233398438:   8%|▊         | 1996/25880 [26:50<5:18:57,  1.25it/s]
1|1997|Loss: 1.0828803777694702:   8%|▊         | 1996/25880 [26:50<5:18:57,  1.25it/s]
1|1997|Loss: 1.0828803777694702:   8%|▊         | 1997/25880 [26:51<4:59:47,  1.33it/s]
1|1998|Loss: 0.7797620296478271:   8%|▊         | 1997/25880 [26:51<4:59:47,  1.33it/s]
1|1998|Loss: 0.7797620296478271:   8%|▊         | 1998/25880 [26:52<5:16:21,  1.26it/s]
1|1999|Loss: 0.8633244037628174:   8%|▊         | 1998/25880 [26:52<5:16:21,  1.26it/s]
1|1999|Loss: 0.8633244037628174:   8%|▊         | 1999/25880 [26:52<5:25:57,  1.22it/s]
1|2000|Loss: 0.8665885329246521:   8%|▊         | 1999/25880 [26:53<5:25:57,  1.22it/s]
1|2000|Loss: 0.8665885329246521:   8%|▊         | 2000/25880 [26:53<5:20:11,  1.24it/s]
1|2001|Loss: 0.8891934156417847:   8%|▊         | 2000/25880 [26:54<5:20:11,  1.24it/s]
1|2001|Loss: 0.8891934156417847:   8%|▊         | 2001/25880 [26:54<4:52:42,  1.36it/s]
1|2002|Loss: 0.9395540952682495:   8%|▊         | 2001/25880 [26:54<4:52:42,  1.36it/s]
1|2002|Loss: 0.9395540952682495:   8%|▊         | 2002/25880 [26:54<4:46:13,  1.39it/s]
1|2003|Loss: 0.8224161267280579:   8%|▊         | 2002/25880 [26:55<4:46:13,  1.39it/s]
1|2003|Loss: 0.8224161267280579:   8%|▊         | 2003/25880 [26:55<4:52:10,  1.36it/s]
1|2004|Loss: 0.7759190797805786:   8%|▊         | 2003/25880 [26:56<4:52:10,  1.36it/s]
1|2004|Loss: 0.7759190797805786:   8%|▊         | 2004/25880 [26:56<4:54:31,  1.35it/s]
1|2005|Loss: 0.8655796051025391:   8%|▊         | 2004/25880 [26:56<4:54:31,  1.35it/s]
1|2005|Loss: 0.8655796051025391:   8%|▊         | 2005/25880 [26:57<5:03:05,  1.31it/s]
1|2006|Loss: 0.9248467087745667:   8%|▊         | 2005/25880 [26:57<5:03:05,  1.31it/s]
1|2006|Loss: 0.9248467087745667:   8%|▊         | 2006/25880 [26:58<5:06:48,  1.30it/s]
1|2007|Loss: 0.9409283399581909:   8%|▊         | 2006/25880 [26:58<5:06:48,  1.30it/s]
1|2007|Loss: 0.9409283399581909:   8%|▊         | 2007/25880 [26:58<5:01:48,  1.32it/s]
1|2008|Loss: 0.8741434812545776:   8%|▊         | 2007/25880 [26:59<5:01:48,  1.32it/s]
1|2008|Loss: 0.8741434812545776:   8%|▊         | 2008/25880 [26:59<5:11:36,  1.28it/s]
1|2009|Loss: 0.8180903196334839:   8%|▊         | 2008/25880 [27:00<5:11:36,  1.28it/s]
1|2009|Loss: 0.8180903196334839:   8%|▊         | 2009/25880 [27:00<5:01:09,  1.32it/s]
1|2010|Loss: 0.8506532311439514:   8%|▊         | 2009/25880 [27:00<5:01:09,  1.32it/s]
1|2010|Loss: 0.8506532311439514:   8%|▊         | 2010/25880 [27:00<4:38:55,  1.43it/s]
1|2011|Loss: 0.7655802965164185:   8%|▊         | 2010/25880 [27:01<4:38:55,  1.43it/s]
1|2011|Loss: 0.7655802965164185:   8%|▊         | 2011/25880 [27:01<4:47:27,  1.38it/s]
1|2012|Loss: 1.0433326959609985:   8%|▊         | 2011/25880 [27:02<4:47:27,  1.38it/s]
1|2012|Loss: 1.0433326959609985:   8%|▊         | 2012/25880 [27:02<4:33:37,  1.45it/s]
1|2013|Loss: 0.8204509019851685:   8%|▊         | 2012/25880 [27:02<4:33:37,  1.45it/s]
1|2013|Loss: 0.8204509019851685:   8%|▊         | 2013/25880 [27:03<4:52:21,  1.36it/s]
1|2014|Loss: 0.9364712834358215:   8%|▊         | 2013/25880 [27:03<4:52:21,  1.36it/s]
1|2014|Loss: 0.9364712834358215:   8%|▊         | 2014/25880 [27:03<4:39:19,  1.42it/s]
1|2015|Loss: 0.9230399131774902:   8%|▊         | 2014/25880 [27:04<4:39:19,  1.42it/s]
1|2015|Loss: 0.9230399131774902:   8%|▊         | 2015/25880 [27:04<4:21:45,  1.52it/s]
1|2016|Loss: 0.7583656907081604:   8%|▊         | 2015/25880 [27:04<4:21:45,  1.52it/s]
1|2016|Loss: 0.7583656907081604:   8%|▊         | 2016/25880 [27:05<4:37:14,  1.43it/s]
1|2017|Loss: 0.7844659686088562:   8%|▊         | 2016/25880 [27:05<4:37:14,  1.43it/s]
1|2017|Loss: 0.7844659686088562:   8%|▊         | 2017/25880 [27:05<4:44:34,  1.40it/s]
1|2018|Loss: 0.9231110215187073:   8%|▊         | 2017/25880 [27:06<4:44:34,  1.40it/s]
1|2018|Loss: 0.9231110215187073:   8%|▊         | 2018/25880 [27:06<4:33:01,  1.46it/s]
1|2019|Loss: 0.7454724311828613:   8%|▊         | 2018/25880 [27:06<4:33:01,  1.46it/s]
1|2019|Loss: 0.7454724311828613:   8%|▊         | 2019/25880 [27:07<4:30:43,  1.47it/s]
1|2020|Loss: 0.8974494338035583:   8%|▊         | 2019/25880 [27:07<4:30:43,  1.47it/s]
1|2020|Loss: 0.8974494338035583:   8%|▊         | 2020/25880 [27:07<4:26:41,  1.49it/s]
1|2021|Loss: 0.9733932614326477:   8%|▊         | 2020/25880 [27:08<4:26:41,  1.49it/s]
1|2021|Loss: 0.9733932614326477:   8%|▊         | 2021/25880 [27:08<4:45:52,  1.39it/s]
1|2022|Loss: 0.7822544574737549:   8%|▊         | 2021/25880 [27:09<4:45:52,  1.39it/s]
1|2022|Loss: 0.7822544574737549:   8%|▊         | 2022/25880 [27:09<4:40:34,  1.42it/s]
1|2023|Loss: 0.8248133063316345:   8%|▊         | 2022/25880 [27:09<4:40:34,  1.42it/s]
1|2023|Loss: 0.8248133063316345:   8%|▊         | 2023/25880 [27:10<4:45:50,  1.39it/s]
1|2024|Loss: 0.9361258149147034:   8%|▊         | 2023/25880 [27:10<4:45:50,  1.39it/s]
1|2024|Loss: 0.9361258149147034:   8%|▊         | 2024/25880 [27:10<4:40:18,  1.42it/s]
1|2025|Loss: 0.9595301151275635:   8%|▊         | 2024/25880 [27:11<4:40:18,  1.42it/s]
1|2025|Loss: 0.9595301151275635:   8%|▊         | 2025/25880 [27:11<4:47:26,  1.38it/s]
1|2026|Loss: 0.9293397665023804:   8%|▊         | 2025/25880 [27:11<4:47:26,  1.38it/s]
1|2026|Loss: 0.9293397665023804:   8%|▊         | 2026/25880 [27:12<4:39:40,  1.42it/s]
1|2027|Loss: 0.8879390358924866:   8%|▊         | 2026/25880 [27:12<4:39:40,  1.42it/s]
1|2027|Loss: 0.8879390358924866:   8%|▊         | 2027/25880 [27:12<4:26:11,  1.49it/s]
1|2028|Loss: 0.8756878972053528:   8%|▊         | 2027/25880 [27:13<4:26:11,  1.49it/s]
1|2028|Loss: 0.8756878972053528:   8%|▊         | 2028/25880 [27:13<4:31:11,  1.47it/s]
1|2029|Loss: 0.919259250164032:   8%|▊         | 2028/25880 [27:13<4:31:11,  1.47it/s] 
1|2029|Loss: 0.919259250164032:   8%|▊         | 2029/25880 [27:14<4:19:08,  1.53it/s]
1|2030|Loss: 1.0992375612258911:   8%|▊         | 2029/25880 [27:14<4:19:08,  1.53it/s]
1|2030|Loss: 1.0992375612258911:   8%|▊         | 2030/25880 [27:14<4:30:23,  1.47it/s]
1|2031|Loss: 0.9112398028373718:   8%|▊         | 2030/25880 [27:15<4:30:23,  1.47it/s]
1|2031|Loss: 0.9112398028373718:   8%|▊         | 2031/25880 [27:15<4:38:11,  1.43it/s]
1|2032|Loss: 0.8407264351844788:   8%|▊         | 2031/25880 [27:15<4:38:11,  1.43it/s]
1|2032|Loss: 0.8407264351844788:   8%|▊         | 2032/25880 [27:16<4:53:01,  1.36it/s]
1|2033|Loss: 0.7371342778205872:   8%|▊         | 2032/25880 [27:16<4:53:01,  1.36it/s]
1|2033|Loss: 0.7371342778205872:   8%|▊         | 2033/25880 [27:17<4:56:01,  1.34it/s]
1|2034|Loss: 0.8390342593193054:   8%|▊         | 2033/25880 [27:17<4:56:01,  1.34it/s]
1|2034|Loss: 0.8390342593193054:   8%|▊         | 2034/25880 [27:17<4:45:51,  1.39it/s]
1|2035|Loss: 0.9390867352485657:   8%|▊         | 2034/25880 [27:18<4:45:51,  1.39it/s]
1|2035|Loss: 0.9390867352485657:   8%|▊         | 2035/25880 [27:18<4:36:53,  1.44it/s]
1|2036|Loss: 0.9583082795143127:   8%|▊         | 2035/25880 [27:18<4:36:53,  1.44it/s]
1|2036|Loss: 0.9583082795143127:   8%|▊         | 2036/25880 [27:19<4:50:28,  1.37it/s]
1|2037|Loss: 0.806763768196106:   8%|▊         | 2036/25880 [27:19<4:50:28,  1.37it/s] 
1|2037|Loss: 0.806763768196106:   8%|▊         | 2037/25880 [27:19<4:51:07,  1.36it/s]
1|2038|Loss: 0.9014881253242493:   8%|▊         | 2037/25880 [27:20<4:51:07,  1.36it/s]
1|2038|Loss: 0.9014881253242493:   8%|▊         | 2038/25880 [27:20<4:41:00,  1.41it/s]
1|2039|Loss: 0.8678332567214966:   8%|▊         | 2038/25880 [27:21<4:41:00,  1.41it/s]
1|2039|Loss: 0.8678332567214966:   8%|▊         | 2039/25880 [27:21<4:47:21,  1.38it/s]
1|2040|Loss: 0.9533693790435791:   8%|▊         | 2039/25880 [27:21<4:47:21,  1.38it/s]
1|2040|Loss: 0.9533693790435791:   8%|▊         | 2040/25880 [27:22<4:50:30,  1.37it/s]
1|2041|Loss: 0.881975531578064:   8%|▊         | 2040/25880 [27:22<4:50:30,  1.37it/s] 
1|2041|Loss: 0.881975531578064:   8%|▊         | 2041/25880 [27:22<4:47:31,  1.38it/s]
1|2042|Loss: 0.7988808751106262:   8%|▊         | 2041/25880 [27:23<4:47:31,  1.38it/s]
1|2042|Loss: 0.7988808751106262:   8%|▊         | 2042/25880 [27:23<4:26:07,  1.49it/s]
1|2043|Loss: 0.8483189940452576:   8%|▊         | 2042/25880 [27:23<4:26:07,  1.49it/s]
1|2043|Loss: 0.8483189940452576:   8%|▊         | 2043/25880 [27:24<4:49:59,  1.37it/s]
1|2044|Loss: 0.8252503871917725:   8%|▊         | 2043/25880 [27:24<4:49:59,  1.37it/s]
1|2044|Loss: 0.8252503871917725:   8%|▊         | 2044/25880 [27:25<5:07:50,  1.29it/s]
1|2045|Loss: 1.0721355676651:   8%|▊         | 2044/25880 [27:25<5:07:50,  1.29it/s]   
1|2045|Loss: 1.0721355676651:   8%|▊         | 2045/25880 [27:25<5:11:36,  1.27it/s]
1|2046|Loss: 0.949738621711731:   8%|▊         | 2045/25880 [27:26<5:11:36,  1.27it/s]
1|2046|Loss: 0.949738621711731:   8%|▊         | 2046/25880 [27:26<5:07:24,  1.29it/s]
1|2047|Loss: 0.786956250667572:   8%|▊         | 2046/25880 [27:27<5:07:24,  1.29it/s]
1|2047|Loss: 0.786956250667572:   8%|▊         | 2047/25880 [27:27<5:01:15,  1.32it/s]
1|2048|Loss: 0.9362807869911194:   8%|▊         | 2047/25880 [27:27<5:01:15,  1.32it/s]
1|2048|Loss: 0.9362807869911194:   8%|▊         | 2048/25880 [27:28<4:42:15,  1.41it/s]
1|2049|Loss: 0.9457042217254639:   8%|▊         | 2048/25880 [27:28<4:42:15,  1.41it/s]
1|2049|Loss: 0.9457042217254639:   8%|▊         | 2049/25880 [27:28<4:31:23,  1.46it/s]
1|2050|Loss: 0.8739755749702454:   8%|▊         | 2049/25880 [27:29<4:31:23,  1.46it/s]
1|2050|Loss: 0.8739755749702454:   8%|▊         | 2050/25880 [27:29<4:33:04,  1.45it/s]
1|2051|Loss: 0.6584078669548035:   8%|▊         | 2050/25880 [27:29<4:33:04,  1.45it/s]
1|2051|Loss: 0.6584078669548035:   8%|▊         | 2051/25880 [27:30<4:44:49,  1.39it/s]
1|2052|Loss: 0.9184251427650452:   8%|▊         | 2051/25880 [27:30<4:44:49,  1.39it/s]
1|2052|Loss: 0.9184251427650452:   8%|▊         | 2052/25880 [27:30<4:57:25,  1.34it/s]
1|2053|Loss: 0.8856356739997864:   8%|▊         | 2052/25880 [27:31<4:57:25,  1.34it/s]
1|2053|Loss: 0.8856356739997864:   8%|▊         | 2053/25880 [27:31<4:46:18,  1.39it/s]
1|2054|Loss: 0.8637431859970093:   8%|▊         | 2053/25880 [27:31<4:46:18,  1.39it/s]
1|2054|Loss: 0.8637431859970093:   8%|▊         | 2054/25880 [27:32<4:36:06,  1.44it/s]
1|2055|Loss: 0.9746880531311035:   8%|▊         | 2054/25880 [27:32<4:36:06,  1.44it/s]
1|2055|Loss: 0.9746880531311035:   8%|▊         | 2055/25880 [27:33<4:49:40,  1.37it/s]
1|2056|Loss: 0.887614369392395:   8%|▊         | 2055/25880 [27:33<4:49:40,  1.37it/s] 
1|2056|Loss: 0.887614369392395:   8%|▊         | 2056/25880 [27:33<5:11:02,  1.28it/s]
1|2057|Loss: 0.7598886489868164:   8%|▊         | 2056/25880 [27:34<5:11:02,  1.28it/s]
1|2057|Loss: 0.7598886489868164:   8%|▊         | 2057/25880 [27:34<5:24:05,  1.23it/s]
1|2058|Loss: 0.9553549289703369:   8%|▊         | 2057/25880 [27:35<5:24:05,  1.23it/s]
1|2058|Loss: 0.9553549289703369:   8%|▊         | 2058/25880 [27:35<5:09:29,  1.28it/s]
1|2059|Loss: 0.8896533846855164:   8%|▊         | 2058/25880 [27:35<5:09:29,  1.28it/s]
1|2059|Loss: 0.8896533846855164:   8%|▊         | 2059/25880 [27:36<4:59:16,  1.33it/s]
1|2060|Loss: 0.850639283657074:   8%|▊         | 2059/25880 [27:36<4:59:16,  1.33it/s] 
1|2060|Loss: 0.850639283657074:   8%|▊         | 2060/25880 [27:36<4:46:50,  1.38it/s]
1|2061|Loss: 1.0229835510253906:   8%|▊         | 2060/25880 [27:37<4:46:50,  1.38it/s]
1|2061|Loss: 1.0229835510253906:   8%|▊         | 2061/25880 [27:37<4:34:33,  1.45it/s]
1|2062|Loss: 0.9282301664352417:   8%|▊         | 2061/25880 [27:37<4:34:33,  1.45it/s]
1|2062|Loss: 0.9282301664352417:   8%|▊         | 2062/25880 [27:38<4:46:09,  1.39it/s]
1|2063|Loss: 0.9424443244934082:   8%|▊         | 2062/25880 [27:38<4:46:09,  1.39it/s]
1|2063|Loss: 0.9424443244934082:   8%|▊         | 2063/25880 [27:38<4:38:22,  1.43it/s]
1|2064|Loss: 0.9018839001655579:   8%|▊         | 2063/25880 [27:39<4:38:22,  1.43it/s]
1|2064|Loss: 0.9018839001655579:   8%|▊         | 2064/25880 [27:39<4:30:20,  1.47it/s]
1|2065|Loss: 0.9395269155502319:   8%|▊         | 2064/25880 [27:39<4:30:20,  1.47it/s]
1|2065|Loss: 0.9395269155502319:   8%|▊         | 2065/25880 [27:40<4:43:08,  1.40it/s]
1|2066|Loss: 0.9165393710136414:   8%|▊         | 2065/25880 [27:40<4:43:08,  1.40it/s]
1|2066|Loss: 0.9165393710136414:   8%|▊         | 2066/25880 [27:41<4:44:06,  1.40it/s]
1|2067|Loss: 0.9823250770568848:   8%|▊         | 2066/25880 [27:41<4:44:06,  1.40it/s]
1|2067|Loss: 0.9823250770568848:   8%|▊         | 2067/25880 [27:41<4:42:04,  1.41it/s]
1|2068|Loss: 0.886335551738739:   8%|▊         | 2067/25880 [27:42<4:42:04,  1.41it/s] 
1|2068|Loss: 0.886335551738739:   8%|▊         | 2068/25880 [27:42<4:54:35,  1.35it/s]
1|2069|Loss: 0.704098105430603:   8%|▊         | 2068/25880 [27:43<4:54:35,  1.35it/s]
1|2069|Loss: 0.704098105430603:   8%|▊         | 2069/25880 [27:43<5:21:24,  1.23it/s]
1|2070|Loss: 1.011047124862671:   8%|▊         | 2069/25880 [27:44<5:21:24,  1.23it/s]
1|2070|Loss: 1.011047124862671:   8%|▊         | 2070/25880 [27:44<5:17:02,  1.25it/s]
1|2071|Loss: 0.779116690158844:   8%|▊         | 2070/25880 [27:44<5:17:02,  1.25it/s]
1|2071|Loss: 0.779116690158844:   8%|▊         | 2071/25880 [27:44<4:51:10,  1.36it/s]
1|2072|Loss: 0.8580299615859985:   8%|▊         | 2071/25880 [27:45<4:51:10,  1.36it/s]
1|2072|Loss: 0.8580299615859985:   8%|▊         | 2072/25880 [27:45<5:08:40,  1.29it/s]
1|2073|Loss: 0.733601987361908:   8%|▊         | 2072/25880 [27:46<5:08:40,  1.29it/s] 
1|2073|Loss: 0.733601987361908:   8%|▊         | 2073/25880 [27:46<5:08:54,  1.28it/s]
1|2074|Loss: 0.7805237770080566:   8%|▊         | 2073/25880 [27:46<5:08:54,  1.28it/s]
1|2074|Loss: 0.7805237770080566:   8%|▊         | 2074/25880 [27:47<4:50:33,  1.37it/s]
1|2075|Loss: 0.895010232925415:   8%|▊         | 2074/25880 [27:47<4:50:33,  1.37it/s] 
1|2075|Loss: 0.895010232925415:   8%|▊         | 2075/25880 [27:47<4:37:24,  1.43it/s]
1|2076|Loss: 0.9476448893547058:   8%|▊         | 2075/25880 [27:48<4:37:24,  1.43it/s]
1|2076|Loss: 0.9476448893547058:   8%|▊         | 2076/25880 [27:48<4:48:46,  1.37it/s]
1|2077|Loss: 0.9146932363510132:   8%|▊         | 2076/25880 [27:49<4:48:46,  1.37it/s]
1|2077|Loss: 0.9146932363510132:   8%|▊         | 2077/25880 [27:49<4:49:13,  1.37it/s]
1|2078|Loss: 0.9350839257240295:   8%|▊         | 2077/25880 [27:49<4:49:13,  1.37it/s]
1|2078|Loss: 0.9350839257240295:   8%|▊         | 2078/25880 [27:50<5:00:09,  1.32it/s]
1|2079|Loss: 1.0180275440216064:   8%|▊         | 2078/25880 [27:50<5:00:09,  1.32it/s]
1|2079|Loss: 1.0180275440216064:   8%|▊         | 2079/25880 [27:51<5:07:36,  1.29it/s]
1|2080|Loss: 0.8434984087944031:   8%|▊         | 2079/25880 [27:51<5:07:36,  1.29it/s]
1|2080|Loss: 0.8434984087944031:   8%|▊         | 2080/25880 [27:51<5:03:48,  1.31it/s]
1|2081|Loss: 0.9816367626190186:   8%|▊         | 2080/25880 [27:52<5:03:48,  1.31it/s]
1|2081|Loss: 0.9816367626190186:   8%|▊         | 2081/25880 [27:52<4:50:28,  1.37it/s]
1|2082|Loss: 1.0161482095718384:   8%|▊         | 2081/25880 [27:52<4:50:28,  1.37it/s]
1|2082|Loss: 1.0161482095718384:   8%|▊         | 2082/25880 [27:53<4:49:53,  1.37it/s]
1|2083|Loss: 0.9433314800262451:   8%|▊         | 2082/25880 [27:53<4:49:53,  1.37it/s]
1|2083|Loss: 0.9433314800262451:   8%|▊         | 2083/25880 [27:53<4:52:28,  1.36it/s]
1|2084|Loss: 0.9246090054512024:   8%|▊         | 2083/25880 [27:54<4:52:28,  1.36it/s]
1|2084|Loss: 0.9246090054512024:   8%|▊         | 2084/25880 [27:54<4:45:03,  1.39it/s]
1|2085|Loss: 0.9069226980209351:   8%|▊         | 2084/25880 [27:54<4:45:03,  1.39it/s]
1|2085|Loss: 0.9069226980209351:   8%|▊         | 2085/25880 [27:55<4:58:51,  1.33it/s]
1|2086|Loss: 0.8525716066360474:   8%|▊         | 2085/25880 [27:55<4:58:51,  1.33it/s]
1|2086|Loss: 0.8525716066360474:   8%|▊         | 2086/25880 [27:56<5:11:33,  1.27it/s]
1|2087|Loss: 0.9738429188728333:   8%|▊         | 2086/25880 [27:56<5:11:33,  1.27it/s]
1|2087|Loss: 0.9738429188728333:   8%|▊         | 2087/25880 [27:56<5:06:15,  1.29it/s]
1|2088|Loss: 0.7673521637916565:   8%|▊         | 2087/25880 [27:57<5:06:15,  1.29it/s]
1|2088|Loss: 0.7673521637916565:   8%|▊         | 2088/25880 [27:57<4:51:49,  1.36it/s]
1|2089|Loss: 0.9512028098106384:   8%|▊         | 2088/25880 [27:58<4:51:49,  1.36it/s]
1|2089|Loss: 0.9512028098106384:   8%|▊         | 2089/25880 [27:58<4:59:10,  1.33it/s]
1|2090|Loss: 0.8907099366188049:   8%|▊         | 2089/25880 [27:58<4:59:10,  1.33it/s]
1|2090|Loss: 0.8907099366188049:   8%|▊         | 2090/25880 [27:59<4:58:14,  1.33it/s]
1|2091|Loss: 0.9375573992729187:   8%|▊         | 2090/25880 [27:59<4:58:14,  1.33it/s]
1|2091|Loss: 0.9375573992729187:   8%|▊         | 2091/25880 [27:59<4:34:13,  1.45it/s]
1|2092|Loss: 0.9861595034599304:   8%|▊         | 2091/25880 [28:00<4:34:13,  1.45it/s]
1|2092|Loss: 0.9861595034599304:   8%|▊         | 2092/25880 [28:00<4:10:21,  1.58it/s]
1|2093|Loss: 0.9747428894042969:   8%|▊         | 2092/25880 [28:00<4:10:21,  1.58it/s]
1|2093|Loss: 0.9747428894042969:   8%|▊         | 2093/25880 [28:00<4:22:29,  1.51it/s]
1|2094|Loss: 0.8296351432800293:   8%|▊         | 2093/25880 [28:01<4:22:29,  1.51it/s]
1|2094|Loss: 0.8296351432800293:   8%|▊         | 2094/25880 [28:01<4:32:41,  1.45it/s]
1|2095|Loss: 0.7784674167633057:   8%|▊         | 2094/25880 [28:02<4:32:41,  1.45it/s]
1|2095|Loss: 0.7784674167633057:   8%|▊         | 2095/25880 [28:02<4:51:40,  1.36it/s]
1|2096|Loss: 0.7860633730888367:   8%|▊         | 2095/25880 [28:02<4:51:40,  1.36it/s]
1|2096|Loss: 0.7860633730888367:   8%|▊         | 2096/25880 [28:03<4:46:53,  1.38it/s]
1|2097|Loss: 1.05668044090271:   8%|▊         | 2096/25880 [28:03<4:46:53,  1.38it/s]  
1|2097|Loss: 1.05668044090271:   8%|▊         | 2097/25880 [28:03<4:43:49,  1.40it/s]
1|2098|Loss: 0.9702386856079102:   8%|▊         | 2097/25880 [28:04<4:43:49,  1.40it/s]
1|2098|Loss: 0.9702386856079102:   8%|▊         | 2098/25880 [28:04<5:08:34,  1.28it/s]
1|2099|Loss: 0.7498999834060669:   8%|▊         | 2098/25880 [28:05<5:08:34,  1.28it/s]
1|2099|Loss: 0.7498999834060669:   8%|▊         | 2099/25880 [28:05<4:59:01,  1.33it/s]
1|2100|Loss: 0.7555547952651978:   8%|▊         | 2099/25880 [28:05<4:59:01,  1.33it/s]
1|2100|Loss: 0.7555547952651978:   8%|▊         | 2100/25880 [28:06<5:02:39,  1.31it/s]
1|2101|Loss: 0.9146943688392639:   8%|▊         | 2100/25880 [28:06<5:02:39,  1.31it/s]
1|2101|Loss: 0.9146943688392639:   8%|▊         | 2101/25880 [28:07<5:14:19,  1.26it/s]
1|2102|Loss: 1.0570839643478394:   8%|▊         | 2101/25880 [28:07<5:14:19,  1.26it/s]
1|2102|Loss: 1.0570839643478394:   8%|▊         | 2102/25880 [28:07<5:10:41,  1.28it/s]
1|2103|Loss: 0.8964089155197144:   8%|▊         | 2102/25880 [28:08<5:10:41,  1.28it/s]
1|2103|Loss: 0.8964089155197144:   8%|▊         | 2103/25880 [28:08<4:55:23,  1.34it/s]
1|2104|Loss: 1.0466818809509277:   8%|▊         | 2103/25880 [28:09<4:55:23,  1.34it/s]
1|2104|Loss: 1.0466818809509277:   8%|▊         | 2104/25880 [28:09<5:02:53,  1.31it/s]
1|2105|Loss: 0.8930076956748962:   8%|▊         | 2104/25880 [28:09<5:02:53,  1.31it/s]
1|2105|Loss: 0.8930076956748962:   8%|▊         | 2105/25880 [28:10<5:12:10,  1.27it/s]
1|2106|Loss: 0.8351892828941345:   8%|▊         | 2105/25880 [28:10<5:12:10,  1.27it/s]
1|2106|Loss: 0.8351892828941345:   8%|▊         | 2106/25880 [28:11<5:18:34,  1.24it/s]
1|2107|Loss: 0.8638978600502014:   8%|▊         | 2106/25880 [28:11<5:18:34,  1.24it/s]
1|2107|Loss: 0.8638978600502014:   8%|▊         | 2107/25880 [28:11<5:04:41,  1.30it/s]
1|2108|Loss: 0.8193199038505554:   8%|▊         | 2107/25880 [28:12<5:04:41,  1.30it/s]
1|2108|Loss: 0.8193199038505554:   8%|▊         | 2108/25880 [28:12<4:34:52,  1.44it/s]
1|2109|Loss: 0.8518757224082947:   8%|▊         | 2108/25880 [28:12<4:34:52,  1.44it/s]
1|2109|Loss: 0.8518757224082947:   8%|▊         | 2109/25880 [28:13<4:30:21,  1.47it/s]
1|2110|Loss: 0.805336058139801:   8%|▊         | 2109/25880 [28:13<4:30:21,  1.47it/s] 
1|2110|Loss: 0.805336058139801:   8%|▊         | 2110/25880 [28:13<4:32:45,  1.45it/s]
1|2111|Loss: 0.837074339389801:   8%|▊         | 2110/25880 [28:14<4:32:45,  1.45it/s]
1|2111|Loss: 0.837074339389801:   8%|▊         | 2111/25880 [28:14<4:26:26,  1.49it/s]
1|2112|Loss: 0.9389035105705261:   8%|▊         | 2111/25880 [28:14<4:26:26,  1.49it/s]
1|2112|Loss: 0.9389035105705261:   8%|▊         | 2112/25880 [28:14<4:22:13,  1.51it/s]
1|2113|Loss: 0.8674754500389099:   8%|▊         | 2112/25880 [28:15<4:22:13,  1.51it/s]
1|2113|Loss: 0.8674754500389099:   8%|▊         | 2113/25880 [28:15<4:35:14,  1.44it/s]
1|2114|Loss: 0.8452343344688416:   8%|▊         | 2113/25880 [28:16<4:35:14,  1.44it/s]
1|2114|Loss: 0.8452343344688416:   8%|▊         | 2114/25880 [28:16<4:18:09,  1.53it/s]
1|2115|Loss: 0.8393008708953857:   8%|▊         | 2114/25880 [28:16<4:18:09,  1.53it/s]
1|2115|Loss: 0.8393008708953857:   8%|▊         | 2115/25880 [28:17<4:30:46,  1.46it/s]
1|2116|Loss: 0.8246603608131409:   8%|▊         | 2115/25880 [28:17<4:30:46,  1.46it/s]
1|2116|Loss: 0.8246603608131409:   8%|▊         | 2116/25880 [28:17<4:45:40,  1.39it/s]
1|2117|Loss: 0.9120103120803833:   8%|▊         | 2116/25880 [28:18<4:45:40,  1.39it/s]
1|2117|Loss: 0.9120103120803833:   8%|▊         | 2117/25880 [28:18<4:40:17,  1.41it/s]
1|2118|Loss: 0.8927320241928101:   8%|▊         | 2117/25880 [28:18<4:40:17,  1.41it/s]
1|2118|Loss: 0.8927320241928101:   8%|▊         | 2118/25880 [28:19<4:30:34,  1.46it/s]
1|2119|Loss: 0.8406867980957031:   8%|▊         | 2118/25880 [28:19<4:30:34,  1.46it/s]
1|2119|Loss: 0.8406867980957031:   8%|▊         | 2119/25880 [28:19<4:43:41,  1.40it/s]
1|2120|Loss: 0.9526412487030029:   8%|▊         | 2119/25880 [28:20<4:43:41,  1.40it/s]
1|2120|Loss: 0.9526412487030029:   8%|▊         | 2120/25880 [28:20<4:33:10,  1.45it/s]
1|2121|Loss: 0.9919796586036682:   8%|▊         | 2120/25880 [28:20<4:33:10,  1.45it/s]
1|2121|Loss: 0.9919796586036682:   8%|▊         | 2121/25880 [28:21<4:34:45,  1.44it/s]
1|2122|Loss: 0.9368487000465393:   8%|▊         | 2121/25880 [28:21<4:34:45,  1.44it/s]
1|2122|Loss: 0.9368487000465393:   8%|▊         | 2122/25880 [28:22<4:51:04,  1.36it/s]
1|2123|Loss: 0.8805723190307617:   8%|▊         | 2122/25880 [28:22<4:51:04,  1.36it/s]
1|2123|Loss: 0.8805723190307617:   8%|▊         | 2123/25880 [28:22<4:43:21,  1.40it/s]
1|2124|Loss: 0.7640694379806519:   8%|▊         | 2123/25880 [28:23<4:43:21,  1.40it/s]
1|2124|Loss: 0.7640694379806519:   8%|▊         | 2124/25880 [28:23<4:33:23,  1.45it/s]
1|2125|Loss: 0.818501889705658:   8%|▊         | 2124/25880 [28:23<4:33:23,  1.45it/s] 
1|2125|Loss: 0.818501889705658:   8%|▊         | 2125/25880 [28:24<4:36:08,  1.43it/s]
1|2126|Loss: 0.9303027987480164:   8%|▊         | 2125/25880 [28:24<4:36:08,  1.43it/s]
1|2126|Loss: 0.9303027987480164:   8%|▊         | 2126/25880 [28:24<4:53:27,  1.35it/s]
1|2127|Loss: 0.9331743717193604:   8%|▊         | 2126/25880 [28:25<4:53:27,  1.35it/s]
1|2127|Loss: 0.9331743717193604:   8%|▊         | 2127/25880 [28:25<4:56:32,  1.33it/s]
1|2128|Loss: 0.9294869303703308:   8%|▊         | 2127/25880 [28:26<4:56:32,  1.33it/s]
1|2128|Loss: 0.9294869303703308:   8%|▊         | 2128/25880 [28:26<4:45:32,  1.39it/s]
1|2129|Loss: 0.9062473177909851:   8%|▊         | 2128/25880 [28:26<4:45:32,  1.39it/s]
1|2129|Loss: 0.9062473177909851:   8%|▊         | 2129/25880 [28:27<4:33:20,  1.45it/s]
1|2130|Loss: 0.9335184693336487:   8%|▊         | 2129/25880 [28:27<4:33:20,  1.45it/s]
1|2130|Loss: 0.9335184693336487:   8%|▊         | 2130/25880 [28:27<4:21:50,  1.51it/s]
1|2131|Loss: 0.8585557341575623:   8%|▊         | 2130/25880 [28:28<4:21:50,  1.51it/s]
1|2131|Loss: 0.8585557341575623:   8%|▊         | 2131/25880 [28:28<4:37:35,  1.43it/s]
1|2132|Loss: 1.0001184940338135:   8%|▊         | 2131/25880 [28:28<4:37:35,  1.43it/s]
1|2132|Loss: 1.0001184940338135:   8%|▊         | 2132/25880 [28:29<4:35:35,  1.44it/s]
1|2133|Loss: 0.9705149531364441:   8%|▊         | 2132/25880 [28:29<4:35:35,  1.44it/s]
1|2133|Loss: 0.9705149531364441:   8%|▊         | 2133/25880 [28:29<4:54:58,  1.34it/s]
1|2134|Loss: 0.8442598581314087:   8%|▊         | 2133/25880 [28:30<4:54:58,  1.34it/s]
1|2134|Loss: 0.8442598581314087:   8%|▊         | 2134/25880 [28:30<5:06:39,  1.29it/s]
1|2135|Loss: 1.0378508567810059:   8%|▊         | 2134/25880 [28:31<5:06:39,  1.29it/s]
1|2135|Loss: 1.0378508567810059:   8%|▊         | 2135/25880 [28:31<5:12:18,  1.27it/s]
1|2136|Loss: 0.9417068958282471:   8%|▊         | 2135/25880 [28:32<5:12:18,  1.27it/s]
1|2136|Loss: 0.9417068958282471:   8%|▊         | 2136/25880 [28:32<5:07:11,  1.29it/s]
1|2137|Loss: 0.756230890750885:   8%|▊         | 2136/25880 [28:32<5:07:11,  1.29it/s] 
1|2137|Loss: 0.756230890750885:   8%|▊         | 2137/25880 [28:33<4:52:02,  1.36it/s]
1|2138|Loss: 0.8559049367904663:   8%|▊         | 2137/25880 [28:33<4:52:02,  1.36it/s]
1|2138|Loss: 0.8559049367904663:   8%|▊         | 2138/25880 [28:33<4:49:07,  1.37it/s]
1|2139|Loss: 0.8089301586151123:   8%|▊         | 2138/25880 [28:34<4:49:07,  1.37it/s]
1|2139|Loss: 0.8089301586151123:   8%|▊         | 2139/25880 [28:34<4:40:42,  1.41it/s]
1|2140|Loss: 0.7863641381263733:   8%|▊         | 2139/25880 [28:34<4:40:42,  1.41it/s]
1|2140|Loss: 0.7863641381263733:   8%|▊         | 2140/25880 [28:34<4:24:40,  1.49it/s]
1|2141|Loss: 0.8055086135864258:   8%|▊         | 2140/25880 [28:35<4:24:40,  1.49it/s]
1|2141|Loss: 0.8055086135864258:   8%|▊         | 2141/25880 [28:35<4:28:18,  1.47it/s]
1|2142|Loss: 0.942074716091156:   8%|▊         | 2141/25880 [28:36<4:28:18,  1.47it/s] 
1|2142|Loss: 0.942074716091156:   8%|▊         | 2142/25880 [28:36<4:35:16,  1.44it/s]
1|2143|Loss: 0.8489502668380737:   8%|▊         | 2142/25880 [28:36<4:35:16,  1.44it/s]
1|2143|Loss: 0.8489502668380737:   8%|▊         | 2143/25880 [28:37<4:39:22,  1.42it/s]
1|2144|Loss: 0.9056118726730347:   8%|▊         | 2143/25880 [28:37<4:39:22,  1.42it/s]
1|2144|Loss: 0.9056118726730347:   8%|▊         | 2144/25880 [28:37<4:42:36,  1.40it/s]
1|2145|Loss: 0.8544257283210754:   8%|▊         | 2144/25880 [28:38<4:42:36,  1.40it/s]
1|2145|Loss: 0.8544257283210754:   8%|▊         | 2145/25880 [28:38<4:46:47,  1.38it/s]
1|2146|Loss: 0.8840118050575256:   8%|▊         | 2145/25880 [28:39<4:46:47,  1.38it/s]
1|2146|Loss: 0.8840118050575256:   8%|▊         | 2146/25880 [28:39<4:48:50,  1.37it/s]
1|2147|Loss: 0.9028978943824768:   8%|▊         | 2146/25880 [28:39<4:48:50,  1.37it/s]
1|2147|Loss: 0.9028978943824768:   8%|▊         | 2147/25880 [28:40<5:02:47,  1.31it/s]
1|2148|Loss: 0.8203727006912231:   8%|▊         | 2147/25880 [28:40<5:02:47,  1.31it/s]
1|2148|Loss: 0.8203727006912231:   8%|▊         | 2148/25880 [28:41<5:13:55,  1.26it/s]
1|2149|Loss: 0.9556049704551697:   8%|▊         | 2148/25880 [28:41<5:13:55,  1.26it/s]
1|2149|Loss: 0.9556049704551697:   8%|▊         | 2149/25880 [28:41<5:15:35,  1.25it/s]
1|2150|Loss: 0.8232768774032593:   8%|▊         | 2149/25880 [28:42<5:15:35,  1.25it/s]
1|2150|Loss: 0.8232768774032593:   8%|▊         | 2150/25880 [28:42<5:09:25,  1.28it/s]
1|2151|Loss: 0.8398607969284058:   8%|▊         | 2150/25880 [28:43<5:09:25,  1.28it/s]
1|2151|Loss: 0.8398607969284058:   8%|▊         | 2151/25880 [28:43<5:00:52,  1.31it/s]
1|2152|Loss: 0.906634509563446:   8%|▊         | 2151/25880 [28:43<5:00:52,  1.31it/s] 
1|2152|Loss: 0.906634509563446:   8%|▊         | 2152/25880 [28:44<4:56:18,  1.33it/s]
1|2153|Loss: 0.7583886384963989:   8%|▊         | 2152/25880 [28:44<4:56:18,  1.33it/s]
1|2153|Loss: 0.7583886384963989:   8%|▊         | 2153/25880 [28:44<4:59:13,  1.32it/s]
1|2154|Loss: 0.8270552754402161:   8%|▊         | 2153/25880 [28:45<4:59:13,  1.32it/s]
1|2154|Loss: 0.8270552754402161:   8%|▊         | 2154/25880 [28:45<5:10:02,  1.28it/s]
1|2155|Loss: 0.7639198303222656:   8%|▊         | 2154/25880 [28:46<5:10:02,  1.28it/s]
1|2155|Loss: 0.7639198303222656:   8%|▊         | 2155/25880 [28:46<5:14:27,  1.26it/s]
1|2156|Loss: 0.8470816612243652:   8%|▊         | 2155/25880 [28:46<5:14:27,  1.26it/s]
1|2156|Loss: 0.8470816612243652:   8%|▊         | 2156/25880 [28:47<5:05:58,  1.29it/s]
1|2157|Loss: 1.020447015762329:   8%|▊         | 2156/25880 [28:47<5:05:58,  1.29it/s] 
1|2157|Loss: 1.020447015762329:   8%|▊         | 2157/25880 [28:47<4:57:35,  1.33it/s]
1|2158|Loss: 0.8770244121551514:   8%|▊         | 2157/25880 [28:48<4:57:35,  1.33it/s]
1|2158|Loss: 0.8770244121551514:   8%|▊         | 2158/25880 [28:48<4:27:43,  1.48it/s]
1|2159|Loss: 0.8638542294502258:   8%|▊         | 2158/25880 [28:48<4:27:43,  1.48it/s]
1|2159|Loss: 0.8638542294502258:   8%|▊         | 2159/25880 [28:49<4:26:34,  1.48it/s]
1|2160|Loss: 0.8329394459724426:   8%|▊         | 2159/25880 [28:49<4:26:34,  1.48it/s]
1|2160|Loss: 0.8329394459724426:   8%|▊         | 2160/25880 [28:49<4:34:12,  1.44it/s]
1|2161|Loss: 0.9392792582511902:   8%|▊         | 2160/25880 [28:50<4:34:12,  1.44it/s]
1|2161|Loss: 0.9392792582511902:   8%|▊         | 2161/25880 [28:50<4:30:58,  1.46it/s]
1|2162|Loss: 0.9517256021499634:   8%|▊         | 2161/25880 [28:50<4:30:58,  1.46it/s]
1|2162|Loss: 0.9517256021499634:   8%|▊         | 2162/25880 [28:51<4:45:04,  1.39it/s]
1|2163|Loss: 0.7806611061096191:   8%|▊         | 2162/25880 [28:51<4:45:04,  1.39it/s]
1|2163|Loss: 0.7806611061096191:   8%|▊         | 2163/25880 [28:52<4:50:16,  1.36it/s]
1|2164|Loss: 0.8463473320007324:   8%|▊         | 2163/25880 [28:52<4:50:16,  1.36it/s]
1|2164|Loss: 0.8463473320007324:   8%|▊         | 2164/25880 [28:52<4:56:36,  1.33it/s]
1|2165|Loss: 0.674822986125946:   8%|▊         | 2164/25880 [28:53<4:56:36,  1.33it/s] 
1|2165|Loss: 0.674822986125946:   8%|▊         | 2165/25880 [28:53<4:56:16,  1.33it/s]
1|2166|Loss: 0.8649084568023682:   8%|▊         | 2165/25880 [28:54<4:56:16,  1.33it/s]
1|2166|Loss: 0.8649084568023682:   8%|▊         | 2166/25880 [28:54<5:08:03,  1.28it/s]
1|2167|Loss: 0.9296054244041443:   8%|▊         | 2166/25880 [28:54<5:08:03,  1.28it/s]
1|2167|Loss: 0.9296054244041443:   8%|▊         | 2167/25880 [28:55<4:45:31,  1.38it/s]
1|2168|Loss: 0.910058319568634:   8%|▊         | 2167/25880 [28:55<4:45:31,  1.38it/s] 
1|2168|Loss: 0.910058319568634:   8%|▊         | 2168/25880 [28:55<4:37:59,  1.42it/s]
1|2169|Loss: 1.095492959022522:   8%|▊         | 2168/25880 [28:56<4:37:59,  1.42it/s]
1|2169|Loss: 1.095492959022522:   8%|▊         | 2169/25880 [28:56<4:52:02,  1.35it/s]
1|2170|Loss: 0.8746602535247803:   8%|▊         | 2169/25880 [28:56<4:52:02,  1.35it/s]
1|2170|Loss: 0.8746602535247803:   8%|▊         | 2170/25880 [28:57<4:54:15,  1.34it/s]
1|2171|Loss: 0.7623724341392517:   8%|▊         | 2170/25880 [28:57<4:54:15,  1.34it/s]
1|2171|Loss: 0.7623724341392517:   8%|▊         | 2171/25880 [28:57<4:30:59,  1.46it/s]
1|2172|Loss: 0.8388692736625671:   8%|▊         | 2171/25880 [28:58<4:30:59,  1.46it/s]
1|2172|Loss: 0.8388692736625671:   8%|▊         | 2172/25880 [28:58<4:21:55,  1.51it/s]
1|2173|Loss: 0.6967539191246033:   8%|▊         | 2172/25880 [28:58<4:21:55,  1.51it/s]
1|2173|Loss: 0.6967539191246033:   8%|▊         | 2173/25880 [28:59<4:30:35,  1.46it/s]
1|2174|Loss: 0.8431963324546814:   8%|▊         | 2173/25880 [28:59<4:30:35,  1.46it/s]
1|2174|Loss: 0.8431963324546814:   8%|▊         | 2174/25880 [28:59<4:44:06,  1.39it/s]
1|2175|Loss: 0.8988164663314819:   8%|▊         | 2174/25880 [29:00<4:44:06,  1.39it/s]
1|2175|Loss: 0.8988164663314819:   8%|▊         | 2175/25880 [29:00<4:38:13,  1.42it/s]
1|2176|Loss: 0.8624476194381714:   8%|▊         | 2175/25880 [29:01<4:38:13,  1.42it/s]
1|2176|Loss: 0.8624476194381714:   8%|▊         | 2176/25880 [29:01<4:44:47,  1.39it/s]
1|2177|Loss: 0.9570579528808594:   8%|▊         | 2176/25880 [29:01<4:44:47,  1.39it/s]
1|2177|Loss: 0.9570579528808594:   8%|▊         | 2177/25880 [29:02<4:48:05,  1.37it/s]
1|2178|Loss: 0.8665118217468262:   8%|▊         | 2177/25880 [29:02<4:48:05,  1.37it/s]
1|2178|Loss: 0.8665118217468262:   8%|▊         | 2178/25880 [29:02<4:39:54,  1.41it/s]
1|2179|Loss: 0.8732091188430786:   8%|▊         | 2178/25880 [29:03<4:39:54,  1.41it/s]
1|2179|Loss: 0.8732091188430786:   8%|▊         | 2179/25880 [29:03<4:41:32,  1.40it/s]
1|2180|Loss: 0.9495804309844971:   8%|▊         | 2179/25880 [29:03<4:41:32,  1.40it/s]
1|2180|Loss: 0.9495804309844971:   8%|▊         | 2180/25880 [29:04<4:35:57,  1.43it/s]
1|2181|Loss: 0.8981230854988098:   8%|▊         | 2180/25880 [29:04<4:35:57,  1.43it/s]
1|2181|Loss: 0.8981230854988098:   8%|▊         | 2181/25880 [29:04<4:29:30,  1.47it/s]
1|2182|Loss: 0.795097827911377:   8%|▊         | 2181/25880 [29:05<4:29:30,  1.47it/s] 
1|2182|Loss: 0.795097827911377:   8%|▊         | 2182/25880 [29:05<4:19:59,  1.52it/s]
1|2183|Loss: 0.914214015007019:   8%|▊         | 2182/25880 [29:05<4:19:59,  1.52it/s]
1|2183|Loss: 0.914214015007019:   8%|▊         | 2183/25880 [29:06<4:33:25,  1.44it/s]
1|2184|Loss: 0.8766282200813293:   8%|▊         | 2183/25880 [29:06<4:33:25,  1.44it/s]
1|2184|Loss: 0.8766282200813293:   8%|▊         | 2184/25880 [29:07<4:49:57,  1.36it/s]
1|2185|Loss: 0.9810503125190735:   8%|▊         | 2184/25880 [29:07<4:49:57,  1.36it/s]
1|2185|Loss: 0.9810503125190735:   8%|▊         | 2185/25880 [29:07<4:57:46,  1.33it/s]
1|2186|Loss: 0.7979044914245605:   8%|▊         | 2185/25880 [29:08<4:57:46,  1.33it/s]
1|2186|Loss: 0.7979044914245605:   8%|▊         | 2186/25880 [29:08<5:07:01,  1.29it/s]
1|2187|Loss: 0.8916498422622681:   8%|▊         | 2186/25880 [29:09<5:07:01,  1.29it/s]
1|2187|Loss: 0.8916498422622681:   8%|▊         | 2187/25880 [29:09<4:53:17,  1.35it/s]
1|2188|Loss: 0.8379637002944946:   8%|▊         | 2187/25880 [29:09<4:53:17,  1.35it/s]
1|2188|Loss: 0.8379637002944946:   8%|▊         | 2188/25880 [29:09<4:41:04,  1.40it/s]
1|2189|Loss: 0.8408699631690979:   8%|▊         | 2188/25880 [29:10<4:41:04,  1.40it/s]
1|2189|Loss: 0.8408699631690979:   8%|▊         | 2189/25880 [29:10<4:30:41,  1.46it/s]
1|2190|Loss: 0.8188833594322205:   8%|▊         | 2189/25880 [29:10<4:30:41,  1.46it/s]
1|2190|Loss: 0.8188833594322205:   8%|▊         | 2190/25880 [29:11<4:30:48,  1.46it/s]
1|2191|Loss: 0.8091122508049011:   8%|▊         | 2190/25880 [29:11<4:30:48,  1.46it/s]
1|2191|Loss: 0.8091122508049011:   8%|▊         | 2191/25880 [29:12<4:40:35,  1.41it/s]
1|2192|Loss: 0.8939709663391113:   8%|▊         | 2191/25880 [29:12<4:40:35,  1.41it/s]
1|2192|Loss: 0.8939709663391113:   8%|▊         | 2192/25880 [29:12<4:36:34,  1.43it/s]
1|2193|Loss: 0.8403159379959106:   8%|▊         | 2192/25880 [29:13<4:36:34,  1.43it/s]
1|2193|Loss: 0.8403159379959106:   8%|▊         | 2193/25880 [29:13<4:59:33,  1.32it/s]
1|2194|Loss: 1.0543924570083618:   8%|▊         | 2193/25880 [29:14<4:59:33,  1.32it/s]
1|2194|Loss: 1.0543924570083618:   8%|▊         | 2194/25880 [29:14<5:20:02,  1.23it/s]
1|2195|Loss: 0.9746890664100647:   8%|▊         | 2194/25880 [29:15<5:20:02,  1.23it/s]
1|2195|Loss: 0.9746890664100647:   8%|▊         | 2195/25880 [29:15<5:29:12,  1.20it/s]
1|2196|Loss: 0.8117456436157227:   8%|▊         | 2195/25880 [29:15<5:29:12,  1.20it/s]
1|2196|Loss: 0.8117456436157227:   8%|▊         | 2196/25880 [29:16<5:10:20,  1.27it/s]
1|2197|Loss: 0.8888740539550781:   8%|▊         | 2196/25880 [29:16<5:10:20,  1.27it/s]
1|2197|Loss: 0.8888740539550781:   8%|▊         | 2197/25880 [29:16<4:46:31,  1.38it/s]
1|2198|Loss: 0.8713480234146118:   8%|▊         | 2197/25880 [29:17<4:46:31,  1.38it/s]
1|2198|Loss: 0.8713480234146118:   8%|▊         | 2198/25880 [29:17<4:17:45,  1.53it/s]
1|2199|Loss: 0.960112452507019:   8%|▊         | 2198/25880 [29:17<4:17:45,  1.53it/s] 
1|2199|Loss: 0.960112452507019:   8%|▊         | 2199/25880 [29:17<4:25:40,  1.49it/s]
1|2200|Loss: 0.9984456300735474:   8%|▊         | 2199/25880 [29:18<4:25:40,  1.49it/s]
1|2200|Loss: 0.9984456300735474:   9%|▊         | 2200/25880 [29:18<4:26:40,  1.48it/s]
1|2201|Loss: 0.9423604011535645:   9%|▊         | 2200/25880 [29:19<4:26:40,  1.48it/s]
1|2201|Loss: 0.9423604011535645:   9%|▊         | 2201/25880 [29:19<4:38:38,  1.42it/s]
1|2202|Loss: 0.8248393535614014:   9%|▊         | 2201/25880 [29:19<4:38:38,  1.42it/s]
1|2202|Loss: 0.8248393535614014:   9%|▊         | 2202/25880 [29:20<4:43:13,  1.39it/s]
1|2203|Loss: 0.8854796886444092:   9%|▊         | 2202/25880 [29:20<4:43:13,  1.39it/s]
1|2203|Loss: 0.8854796886444092:   9%|▊         | 2203/25880 [29:20<4:36:17,  1.43it/s]
1|2204|Loss: 0.9584473967552185:   9%|▊         | 2203/25880 [29:21<4:36:17,  1.43it/s]
1|2204|Loss: 0.9584473967552185:   9%|▊         | 2204/25880 [29:21<4:49:14,  1.36it/s]
1|2205|Loss: 0.9963188171386719:   9%|▊         | 2204/25880 [29:21<4:49:14,  1.36it/s]
1|2205|Loss: 0.9963188171386719:   9%|▊         | 2205/25880 [29:22<4:31:12,  1.45it/s]
1|2206|Loss: 0.9275652170181274:   9%|▊         | 2205/25880 [29:22<4:31:12,  1.45it/s]
1|2206|Loss: 0.9275652170181274:   9%|▊         | 2206/25880 [29:22<4:22:03,  1.51it/s]
1|2207|Loss: 0.7931293249130249:   9%|▊         | 2206/25880 [29:23<4:22:03,  1.51it/s]
1|2207|Loss: 0.7931293249130249:   9%|▊         | 2207/25880 [29:23<4:29:08,  1.47it/s]
1|2208|Loss: 0.9391791224479675:   9%|▊         | 2207/25880 [29:23<4:29:08,  1.47it/s]
1|2208|Loss: 0.9391791224479675:   9%|▊         | 2208/25880 [29:24<4:36:17,  1.43it/s]
1|2209|Loss: 0.8462520837783813:   9%|▊         | 2208/25880 [29:24<4:36:17,  1.43it/s]
1|2209|Loss: 0.8462520837783813:   9%|▊         | 2209/25880 [29:24<4:40:00,  1.41it/s]
1|2210|Loss: 0.9956053495407104:   9%|▊         | 2209/25880 [29:25<4:40:00,  1.41it/s]
1|2210|Loss: 0.9956053495407104:   9%|▊         | 2210/25880 [29:25<4:39:07,  1.41it/s]
1|2211|Loss: 0.8028967380523682:   9%|▊         | 2210/25880 [29:26<4:39:07,  1.41it/s]
1|2211|Loss: 0.8028967380523682:   9%|▊         | 2211/25880 [29:26<4:47:32,  1.37it/s]
1|2212|Loss: 0.7604979276657104:   9%|▊         | 2211/25880 [29:26<4:47:32,  1.37it/s]
1|2212|Loss: 0.7604979276657104:   9%|▊         | 2212/25880 [29:27<4:46:29,  1.38it/s]
1|2213|Loss: 0.9453539252281189:   9%|▊         | 2212/25880 [29:27<4:46:29,  1.38it/s]
1|2213|Loss: 0.9453539252281189:   9%|▊         | 2213/25880 [29:27<4:53:03,  1.35it/s]
1|2214|Loss: 0.9061219096183777:   9%|▊         | 2213/25880 [29:28<4:53:03,  1.35it/s]
1|2214|Loss: 0.9061219096183777:   9%|▊         | 2214/25880 [29:28<5:07:16,  1.28it/s]
1|2215|Loss: 0.9770033359527588:   9%|▊         | 2214/25880 [29:29<5:07:16,  1.28it/s]
1|2215|Loss: 0.9770033359527588:   9%|▊         | 2215/25880 [29:29<4:57:15,  1.33it/s]
1|2216|Loss: 0.8946643471717834:   9%|▊         | 2215/25880 [29:29<4:57:15,  1.33it/s]
1|2216|Loss: 0.8946643471717834:   9%|▊         | 2216/25880 [29:30<5:14:58,  1.25it/s]
1|2217|Loss: 0.831766664981842:   9%|▊         | 2216/25880 [29:30<5:14:58,  1.25it/s] 
1|2217|Loss: 0.831766664981842:   9%|▊         | 2217/25880 [29:31<5:03:55,  1.30it/s]
1|2218|Loss: 0.8892278075218201:   9%|▊         | 2217/25880 [29:31<5:03:55,  1.30it/s]
1|2218|Loss: 0.8892278075218201:   9%|▊         | 2218/25880 [29:31<5:06:44,  1.29it/s]
1|2219|Loss: 0.9856908321380615:   9%|▊         | 2218/25880 [29:32<5:06:44,  1.29it/s]
1|2219|Loss: 0.9856908321380615:   9%|▊         | 2219/25880 [29:32<5:05:34,  1.29it/s]
1|2220|Loss: 0.8930096626281738:   9%|▊         | 2219/25880 [29:33<5:05:34,  1.29it/s]
1|2220|Loss: 0.8930096626281738:   9%|▊         | 2220/25880 [29:33<5:01:15,  1.31it/s]
1|2221|Loss: 0.8361395597457886:   9%|▊         | 2220/25880 [29:33<5:01:15,  1.31it/s]
1|2221|Loss: 0.8361395597457886:   9%|▊         | 2221/25880 [29:34<4:53:44,  1.34it/s]
1|2222|Loss: 0.9177204370498657:   9%|▊         | 2221/25880 [29:34<4:53:44,  1.34it/s]
1|2222|Loss: 0.9177204370498657:   9%|▊         | 2222/25880 [29:34<4:42:25,  1.40it/s]
1|2223|Loss: 0.8505367636680603:   9%|▊         | 2222/25880 [29:35<4:42:25,  1.40it/s]
1|2223|Loss: 0.8505367636680603:   9%|▊         | 2223/25880 [29:35<5:03:53,  1.30it/s]
1|2224|Loss: 0.9419499635696411:   9%|▊         | 2223/25880 [29:36<5:03:53,  1.30it/s]
1|2224|Loss: 0.9419499635696411:   9%|▊         | 2224/25880 [29:36<5:05:20,  1.29it/s]
1|2225|Loss: 0.885978102684021:   9%|▊         | 2224/25880 [29:36<5:05:20,  1.29it/s] 
1|2225|Loss: 0.885978102684021:   9%|▊         | 2225/25880 [29:37<5:10:37,  1.27it/s]
1|2226|Loss: 0.8716714382171631:   9%|▊         | 2225/25880 [29:37<5:10:37,  1.27it/s]
1|2226|Loss: 0.8716714382171631:   9%|▊         | 2226/25880 [29:38<5:02:58,  1.30it/s]
1|2227|Loss: 0.879393994808197:   9%|▊         | 2226/25880 [29:38<5:02:58,  1.30it/s] 
1|2227|Loss: 0.879393994808197:   9%|▊         | 2227/25880 [29:38<5:07:44,  1.28it/s]
1|2228|Loss: 0.7229511141777039:   9%|▊         | 2227/25880 [29:39<5:07:44,  1.28it/s]
1|2228|Loss: 0.7229511141777039:   9%|▊         | 2228/25880 [29:39<5:09:23,  1.27it/s]
1|2229|Loss: 0.9960229992866516:   9%|▊         | 2228/25880 [29:40<5:09:23,  1.27it/s]
1|2229|Loss: 0.9960229992866516:   9%|▊         | 2229/25880 [29:40<5:04:49,  1.29it/s]
1|2230|Loss: 0.99635910987854:   9%|▊         | 2229/25880 [29:40<5:04:49,  1.29it/s]  
1|2230|Loss: 0.99635910987854:   9%|▊         | 2230/25880 [29:40<4:47:09,  1.37it/s]
1|2231|Loss: 0.7993332147598267:   9%|▊         | 2230/25880 [29:41<4:47:09,  1.37it/s]
1|2231|Loss: 0.7993332147598267:   9%|▊         | 2231/25880 [29:41<4:40:55,  1.40it/s]
1|2232|Loss: 0.8310571908950806:   9%|▊         | 2231/25880 [29:42<4:40:55,  1.40it/s]
1|2232|Loss: 0.8310571908950806:   9%|▊         | 2232/25880 [29:42<4:39:41,  1.41it/s]
1|2233|Loss: 0.7785529494285583:   9%|▊         | 2232/25880 [29:42<4:39:41,  1.41it/s]
1|2233|Loss: 0.7785529494285583:   9%|▊         | 2233/25880 [29:43<4:32:30,  1.45it/s]
1|2234|Loss: 0.7660360932350159:   9%|▊         | 2233/25880 [29:43<4:32:30,  1.45it/s]
1|2234|Loss: 0.7660360932350159:   9%|▊         | 2234/25880 [29:43<4:33:09,  1.44it/s]
1|2235|Loss: 0.7650290131568909:   9%|▊         | 2234/25880 [29:44<4:33:09,  1.44it/s]
1|2235|Loss: 0.7650290131568909:   9%|▊         | 2235/25880 [29:44<4:46:04,  1.38it/s]
1|2236|Loss: 1.0426288843154907:   9%|▊         | 2235/25880 [29:44<4:46:04,  1.38it/s]
1|2236|Loss: 1.0426288843154907:   9%|▊         | 2236/25880 [29:45<4:30:26,  1.46it/s]
1|2237|Loss: 0.8472785353660583:   9%|▊         | 2236/25880 [29:45<4:30:26,  1.46it/s]
1|2237|Loss: 0.8472785353660583:   9%|▊         | 2237/25880 [29:45<4:40:29,  1.40it/s]
1|2238|Loss: 1.101825475692749:   9%|▊         | 2237/25880 [29:46<4:40:29,  1.40it/s] 
1|2238|Loss: 1.101825475692749:   9%|▊         | 2238/25880 [29:46<4:50:16,  1.36it/s]
1|2239|Loss: 0.9644676446914673:   9%|▊         | 2238/25880 [29:47<4:50:16,  1.36it/s]
1|2239|Loss: 0.9644676446914673:   9%|▊         | 2239/25880 [29:47<4:51:58,  1.35it/s]
1|2240|Loss: 0.886165976524353:   9%|▊         | 2239/25880 [29:47<4:51:58,  1.35it/s] 
1|2240|Loss: 0.886165976524353:   9%|▊         | 2240/25880 [29:48<4:52:03,  1.35it/s]
1|2241|Loss: 0.8765619397163391:   9%|▊         | 2240/25880 [29:48<4:52:03,  1.35it/s]
1|2241|Loss: 0.8765619397163391:   9%|▊         | 2241/25880 [29:48<4:41:03,  1.40it/s]
1|2242|Loss: 0.7877869009971619:   9%|▊         | 2241/25880 [29:49<4:41:03,  1.40it/s]
1|2242|Loss: 0.7877869009971619:   9%|▊         | 2242/25880 [29:49<4:51:42,  1.35it/s]
1|2243|Loss: 0.7739086747169495:   9%|▊         | 2242/25880 [29:50<4:51:42,  1.35it/s]
1|2243|Loss: 0.7739086747169495:   9%|▊         | 2243/25880 [29:50<4:53:47,  1.34it/s]
1|2244|Loss: 0.8645860552787781:   9%|▊         | 2243/25880 [29:50<4:53:47,  1.34it/s]
1|2244|Loss: 0.8645860552787781:   9%|▊         | 2244/25880 [29:51<5:00:43,  1.31it/s]
1|2245|Loss: 0.9156683087348938:   9%|▊         | 2244/25880 [29:51<5:00:43,  1.31it/s]
1|2245|Loss: 0.9156683087348938:   9%|▊         | 2245/25880 [29:51<4:48:01,  1.37it/s]
1|2246|Loss: 0.7049757242202759:   9%|▊         | 2245/25880 [29:52<4:48:01,  1.37it/s]
1|2246|Loss: 0.7049757242202759:   9%|▊         | 2246/25880 [29:52<4:58:23,  1.32it/s]
1|2247|Loss: 0.7537963390350342:   9%|▊         | 2246/25880 [29:53<4:58:23,  1.32it/s]
1|2247|Loss: 0.7537963390350342:   9%|▊         | 2247/25880 [29:53<4:59:18,  1.32it/s]
1|2248|Loss: 0.7858307361602783:   9%|▊         | 2247/25880 [29:53<4:59:18,  1.32it/s]
1|2248|Loss: 0.7858307361602783:   9%|▊         | 2248/25880 [29:54<5:05:39,  1.29it/s]
1|2249|Loss: 0.8021924495697021:   9%|▊         | 2248/25880 [29:54<5:05:39,  1.29it/s]
1|2249|Loss: 0.8021924495697021:   9%|▊         | 2249/25880 [29:54<4:54:15,  1.34it/s]
1|2250|Loss: 0.8893416523933411:   9%|▊         | 2249/25880 [29:55<4:54:15,  1.34it/s]
1|2250|Loss: 0.8893416523933411:   9%|▊         | 2250/25880 [29:55<4:51:32,  1.35it/s]
1|2251|Loss: 0.8611708283424377:   9%|▊         | 2250/25880 [29:55<4:51:32,  1.35it/s]
1|2251|Loss: 0.8611708283424377:   9%|▊         | 2251/25880 [29:56<4:38:17,  1.42it/s]
1|2252|Loss: 0.9064770936965942:   9%|▊         | 2251/25880 [29:56<4:38:17,  1.42it/s]
1|2252|Loss: 0.9064770936965942:   9%|▊         | 2252/25880 [29:56<4:18:53,  1.52it/s]
1|2253|Loss: 0.6895246505737305:   9%|▊         | 2252/25880 [29:57<4:18:53,  1.52it/s]
1|2253|Loss: 0.6895246505737305:   9%|▊         | 2253/25880 [29:57<4:34:09,  1.44it/s]
1|2254|Loss: 0.8646447658538818:   9%|▊         | 2253/25880 [29:57<4:34:09,  1.44it/s]
1|2254|Loss: 0.8646447658538818:   9%|▊         | 2254/25880 [29:58<4:33:48,  1.44it/s]
1|2255|Loss: 0.9157074093818665:   9%|▊         | 2254/25880 [29:58<4:33:48,  1.44it/s]
1|2255|Loss: 0.9157074093818665:   9%|▊         | 2255/25880 [29:58<4:24:54,  1.49it/s]
1|2256|Loss: 0.964296281337738:   9%|▊         | 2255/25880 [29:59<4:24:54,  1.49it/s] 
1|2256|Loss: 0.964296281337738:   9%|▊         | 2256/25880 [29:59<4:41:32,  1.40it/s]
1|2257|Loss: 0.9074246883392334:   9%|▊         | 2256/25880 [30:00<4:41:32,  1.40it/s]
1|2257|Loss: 0.9074246883392334:   9%|▊         | 2257/25880 [30:00<4:58:13,  1.32it/s]
1|2258|Loss: 0.9214761257171631:   9%|▊         | 2257/25880 [30:00<4:58:13,  1.32it/s]
1|2258|Loss: 0.9214761257171631:   9%|▊         | 2258/25880 [30:01<4:58:21,  1.32it/s]
1|2259|Loss: 0.7836170792579651:   9%|▊         | 2258/25880 [30:01<4:58:21,  1.32it/s]
1|2259|Loss: 0.7836170792579651:   9%|▊         | 2259/25880 [30:02<4:51:46,  1.35it/s]
1|2260|Loss: 0.9307422041893005:   9%|▊         | 2259/25880 [30:02<4:51:46,  1.35it/s]
1|2260|Loss: 0.9307422041893005:   9%|▊         | 2260/25880 [30:02<4:17:02,  1.53it/s]
1|2261|Loss: 0.8319840431213379:   9%|▊         | 2260/25880 [30:02<4:17:02,  1.53it/s]
1|2261|Loss: 0.8319840431213379:   9%|▊         | 2261/25880 [30:03<4:15:43,  1.54it/s]
1|2262|Loss: 1.1008110046386719:   9%|▊         | 2261/25880 [30:03<4:15:43,  1.54it/s]
1|2262|Loss: 1.1008110046386719:   9%|▊         | 2262/25880 [30:03<4:01:05,  1.63it/s]
1|2263|Loss: 0.9544343948364258:   9%|▊         | 2262/25880 [30:03<4:01:05,  1.63it/s]
1|2263|Loss: 0.9544343948364258:   9%|▊         | 2263/25880 [30:04<4:09:29,  1.58it/s]
1|2264|Loss: 0.884959876537323:   9%|▊         | 2263/25880 [30:04<4:09:29,  1.58it/s] 
1|2264|Loss: 0.884959876537323:   9%|▊         | 2264/25880 [30:04<4:08:15,  1.59it/s]
1|2265|Loss: 0.8063095808029175:   9%|▊         | 2264/25880 [30:05<4:08:15,  1.59it/s]
1|2265|Loss: 0.8063095808029175:   9%|▉         | 2265/25880 [30:05<4:21:51,  1.50it/s]
1|2266|Loss: 0.9003191590309143:   9%|▉         | 2265/25880 [30:06<4:21:51,  1.50it/s]
1|2266|Loss: 0.9003191590309143:   9%|▉         | 2266/25880 [30:06<4:32:38,  1.44it/s]
1|2267|Loss: 0.7901692390441895:   9%|▉         | 2266/25880 [30:06<4:32:38,  1.44it/s]
1|2267|Loss: 0.7901692390441895:   9%|▉         | 2267/25880 [30:06<4:03:22,  1.62it/s]
1|2268|Loss: 0.833713173866272:   9%|▉         | 2267/25880 [30:07<4:03:22,  1.62it/s] 
1|2268|Loss: 0.833713173866272:   9%|▉         | 2268/25880 [30:07<4:05:36,  1.60it/s]
1|2269|Loss: 0.9925230741500854:   9%|▉         | 2268/25880 [30:07<4:05:36,  1.60it/s]
1|2269|Loss: 0.9925230741500854:   9%|▉         | 2269/25880 [30:08<4:19:08,  1.52it/s]
1|2270|Loss: 0.8808445334434509:   9%|▉         | 2269/25880 [30:08<4:19:08,  1.52it/s]
1|2270|Loss: 0.8808445334434509:   9%|▉         | 2270/25880 [30:09<4:28:21,  1.47it/s]
1|2271|Loss: 0.9331380128860474:   9%|▉         | 2270/25880 [30:09<4:28:21,  1.47it/s]
1|2271|Loss: 0.9331380128860474:   9%|▉         | 2271/25880 [30:09<4:55:47,  1.33it/s]
1|2272|Loss: 0.8363266587257385:   9%|▉         | 2271/25880 [30:10<4:55:47,  1.33it/s]
1|2272|Loss: 0.8363266587257385:   9%|▉         | 2272/25880 [30:10<4:37:46,  1.42it/s]
1|2273|Loss: 0.8127119541168213:   9%|▉         | 2272/25880 [30:10<4:37:46,  1.42it/s]
1|2273|Loss: 0.8127119541168213:   9%|▉         | 2273/25880 [30:11<4:59:57,  1.31it/s]
1|2274|Loss: 0.8006616830825806:   9%|▉         | 2273/25880 [30:11<4:59:57,  1.31it/s]
1|2274|Loss: 0.8006616830825806:   9%|▉         | 2274/25880 [30:12<5:03:07,  1.30it/s]
1|2275|Loss: 0.9570187330245972:   9%|▉         | 2274/25880 [30:12<5:03:07,  1.30it/s]
1|2275|Loss: 0.9570187330245972:   9%|▉         | 2275/25880 [30:12<4:44:14,  1.38it/s]
1|2276|Loss: 1.094939112663269:   9%|▉         | 2275/25880 [30:13<4:44:14,  1.38it/s] 
1|2276|Loss: 1.094939112663269:   9%|▉         | 2276/25880 [30:13<4:32:39,  1.44it/s]
1|2277|Loss: 0.824748694896698:   9%|▉         | 2276/25880 [30:13<4:32:39,  1.44it/s]
1|2277|Loss: 0.824748694896698:   9%|▉         | 2277/25880 [30:14<4:26:37,  1.48it/s]
1|2278|Loss: 0.8354426026344299:   9%|▉         | 2277/25880 [30:14<4:26:37,  1.48it/s]
1|2278|Loss: 0.8354426026344299:   9%|▉         | 2278/25880 [30:14<4:19:45,  1.51it/s]
1|2279|Loss: 1.0405229330062866:   9%|▉         | 2278/25880 [30:15<4:19:45,  1.51it/s]
1|2279|Loss: 1.0405229330062866:   9%|▉         | 2279/25880 [30:15<4:09:00,  1.58it/s]
1|2280|Loss: 0.8398299217224121:   9%|▉         | 2279/25880 [30:15<4:09:00,  1.58it/s]
1|2280|Loss: 0.8398299217224121:   9%|▉         | 2280/25880 [30:15<4:16:45,  1.53it/s]
1|2281|Loss: 0.9347447752952576:   9%|▉         | 2280/25880 [30:16<4:16:45,  1.53it/s]
1|2281|Loss: 0.9347447752952576:   9%|▉         | 2281/25880 [30:16<4:26:36,  1.48it/s]
1|2282|Loss: 0.8862583637237549:   9%|▉         | 2281/25880 [30:17<4:26:36,  1.48it/s]
1|2282|Loss: 0.8862583637237549:   9%|▉         | 2282/25880 [30:17<4:29:40,  1.46it/s]
1|2283|Loss: 0.9926539063453674:   9%|▉         | 2282/25880 [30:17<4:29:40,  1.46it/s]
1|2283|Loss: 0.9926539063453674:   9%|▉         | 2283/25880 [30:18<4:25:58,  1.48it/s]
1|2284|Loss: 0.8660773634910583:   9%|▉         | 2283/25880 [30:18<4:25:58,  1.48it/s]
1|2284|Loss: 0.8660773634910583:   9%|▉         | 2284/25880 [30:18<4:30:44,  1.45it/s]
1|2285|Loss: 0.825352668762207:   9%|▉         | 2284/25880 [30:19<4:30:44,  1.45it/s] 
1|2285|Loss: 0.825352668762207:   9%|▉         | 2285/25880 [30:19<4:36:43,  1.42it/s]
1|2286|Loss: 0.8609490394592285:   9%|▉         | 2285/25880 [30:19<4:36:43,  1.42it/s]
1|2286|Loss: 0.8609490394592285:   9%|▉         | 2286/25880 [30:20<4:26:04,  1.48it/s]
1|2287|Loss: 0.8158360719680786:   9%|▉         | 2286/25880 [30:20<4:26:04,  1.48it/s]
1|2287|Loss: 0.8158360719680786:   9%|▉         | 2287/25880 [30:20<4:17:11,  1.53it/s]
1|2288|Loss: 0.8471632599830627:   9%|▉         | 2287/25880 [30:21<4:17:11,  1.53it/s]
1|2288|Loss: 0.8471632599830627:   9%|▉         | 2288/25880 [30:21<4:24:33,  1.49it/s]
1|2289|Loss: 0.7576910853385925:   9%|▉         | 2288/25880 [30:21<4:24:33,  1.49it/s]
1|2289|Loss: 0.7576910853385925:   9%|▉         | 2289/25880 [30:22<4:38:55,  1.41it/s]
1|2290|Loss: 0.9078323245048523:   9%|▉         | 2289/25880 [30:22<4:38:55,  1.41it/s]
1|2290|Loss: 0.9078323245048523:   9%|▉         | 2290/25880 [30:22<4:16:33,  1.53it/s]
1|2291|Loss: 0.8334282636642456:   9%|▉         | 2290/25880 [30:23<4:16:33,  1.53it/s]
1|2291|Loss: 0.8334282636642456:   9%|▉         | 2291/25880 [30:23<4:20:01,  1.51it/s]
1|2292|Loss: 0.8499109745025635:   9%|▉         | 2291/25880 [30:23<4:20:01,  1.51it/s]
1|2292|Loss: 0.8499109745025635:   9%|▉         | 2292/25880 [30:24<4:47:48,  1.37it/s]
1|2293|Loss: 0.9164309501647949:   9%|▉         | 2292/25880 [30:24<4:47:48,  1.37it/s]
1|2293|Loss: 0.9164309501647949:   9%|▉         | 2293/25880 [30:25<5:10:23,  1.27it/s]
1|2294|Loss: 0.8512423038482666:   9%|▉         | 2293/25880 [30:25<5:10:23,  1.27it/s]
1|2294|Loss: 0.8512423038482666:   9%|▉         | 2294/25880 [30:25<4:51:14,  1.35it/s]
1|2295|Loss: 1.1652100086212158:   9%|▉         | 2294/25880 [30:26<4:51:14,  1.35it/s]
1|2295|Loss: 1.1652100086212158:   9%|▉         | 2295/25880 [30:26<5:27:32,  1.20it/s]
1|2296|Loss: 0.9779103994369507:   9%|▉         | 2295/25880 [30:27<5:27:32,  1.20it/s]
1|2296|Loss: 0.9779103994369507:   9%|▉         | 2296/25880 [30:27<5:36:52,  1.17it/s]
1|2297|Loss: 0.8047491908073425:   9%|▉         | 2296/25880 [30:28<5:36:52,  1.17it/s]
1|2297|Loss: 0.8047491908073425:   9%|▉         | 2297/25880 [30:28<5:42:43,  1.15it/s]
1|2298|Loss: 0.9589204788208008:   9%|▉         | 2297/25880 [30:29<5:42:43,  1.15it/s]
1|2298|Loss: 0.9589204788208008:   9%|▉         | 2298/25880 [30:29<5:35:49,  1.17it/s]
1|2299|Loss: 0.7819575667381287:   9%|▉         | 2298/25880 [30:29<5:35:49,  1.17it/s]
1|2299|Loss: 0.7819575667381287:   9%|▉         | 2299/25880 [30:30<5:12:24,  1.26it/s]
1|2300|Loss: 1.0406893491744995:   9%|▉         | 2299/25880 [30:30<5:12:24,  1.26it/s]
1|2300|Loss: 1.0406893491744995:   9%|▉         | 2300/25880 [30:30<5:02:23,  1.30it/s]
1|2301|Loss: 1.0413050651550293:   9%|▉         | 2300/25880 [30:31<5:02:23,  1.30it/s]
1|2301|Loss: 1.0413050651550293:   9%|▉         | 2301/25880 [30:31<4:37:20,  1.42it/s]
1|2302|Loss: 0.8517116904258728:   9%|▉         | 2301/25880 [30:31<4:37:20,  1.42it/s]
1|2302|Loss: 0.8517116904258728:   9%|▉         | 2302/25880 [30:32<4:33:53,  1.43it/s]
1|2303|Loss: 0.8788714408874512:   9%|▉         | 2302/25880 [30:32<4:33:53,  1.43it/s]
1|2303|Loss: 0.8788714408874512:   9%|▉         | 2303/25880 [30:33<4:51:06,  1.35it/s]
1|2304|Loss: 0.7532952427864075:   9%|▉         | 2303/25880 [30:33<4:51:06,  1.35it/s]
1|2304|Loss: 0.7532952427864075:   9%|▉         | 2304/25880 [30:33<4:39:56,  1.40it/s]
1|2305|Loss: 0.774054765701294:   9%|▉         | 2304/25880 [30:34<4:39:56,  1.40it/s] 
1|2305|Loss: 0.774054765701294:   9%|▉         | 2305/25880 [30:34<4:48:30,  1.36it/s]
1|2306|Loss: 1.0680547952651978:   9%|▉         | 2305/25880 [30:34<4:48:30,  1.36it/s]
1|2306|Loss: 1.0680547952651978:   9%|▉         | 2306/25880 [30:35<4:48:11,  1.36it/s]
1|2307|Loss: 0.8641243577003479:   9%|▉         | 2306/25880 [30:35<4:48:11,  1.36it/s]
1|2307|Loss: 0.8641243577003479:   9%|▉         | 2307/25880 [30:35<4:54:39,  1.33it/s]
1|2308|Loss: 0.8298794031143188:   9%|▉         | 2307/25880 [30:36<4:54:39,  1.33it/s]
1|2308|Loss: 0.8298794031143188:   9%|▉         | 2308/25880 [30:36<4:52:19,  1.34it/s]
1|2309|Loss: 0.8634141683578491:   9%|▉         | 2308/25880 [30:37<4:52:19,  1.34it/s]
1|2309|Loss: 0.8634141683578491:   9%|▉         | 2309/25880 [30:37<4:47:23,  1.37it/s]
1|2310|Loss: 0.8474105000495911:   9%|▉         | 2309/25880 [30:37<4:47:23,  1.37it/s]
1|2310|Loss: 0.8474105000495911:   9%|▉         | 2310/25880 [30:38<4:46:28,  1.37it/s]
1|2311|Loss: 1.0172417163848877:   9%|▉         | 2310/25880 [30:38<4:46:28,  1.37it/s]
1|2311|Loss: 1.0172417163848877:   9%|▉         | 2311/25880 [30:38<5:01:37,  1.30it/s]
1|2312|Loss: 0.9447892904281616:   9%|▉         | 2311/25880 [30:39<5:01:37,  1.30it/s]
1|2312|Loss: 0.9447892904281616:   9%|▉         | 2312/25880 [30:39<5:15:40,  1.24it/s]
1|2313|Loss: 0.8122536540031433:   9%|▉         | 2312/25880 [30:40<5:15:40,  1.24it/s]
1|2313|Loss: 0.8122536540031433:   9%|▉         | 2313/25880 [30:40<5:10:57,  1.26it/s]
1|2314|Loss: 0.7658330202102661:   9%|▉         | 2313/25880 [30:41<5:10:57,  1.26it/s]
1|2314|Loss: 0.7658330202102661:   9%|▉         | 2314/25880 [30:41<5:03:17,  1.30it/s]
1|2315|Loss: 0.8568068146705627:   9%|▉         | 2314/25880 [30:41<5:03:17,  1.30it/s]
1|2315|Loss: 0.8568068146705627:   9%|▉         | 2315/25880 [30:41<4:44:07,  1.38it/s]
1|2316|Loss: 0.8660703301429749:   9%|▉         | 2315/25880 [30:42<4:44:07,  1.38it/s]
1|2316|Loss: 0.8660703301429749:   9%|▉         | 2316/25880 [30:42<4:30:46,  1.45it/s]
1|2317|Loss: 0.9219893217086792:   9%|▉         | 2316/25880 [30:42<4:30:46,  1.45it/s]
1|2317|Loss: 0.9219893217086792:   9%|▉         | 2317/25880 [30:43<3:59:16,  1.64it/s]
1|2318|Loss: 0.8362985253334045:   9%|▉         | 2317/25880 [30:43<3:59:16,  1.64it/s]
1|2318|Loss: 0.8362985253334045:   9%|▉         | 2318/25880 [30:43<3:55:02,  1.67it/s]
1|2319|Loss: 0.9608173966407776:   9%|▉         | 2318/25880 [30:43<3:55:02,  1.67it/s]
1|2319|Loss: 0.9608173966407776:   9%|▉         | 2319/25880 [30:44<4:05:28,  1.60it/s]
1|2320|Loss: 0.7925356030464172:   9%|▉         | 2319/25880 [30:44<4:05:28,  1.60it/s]
1|2320|Loss: 0.7925356030464172:   9%|▉         | 2320/25880 [30:45<4:17:20,  1.53it/s]
1|2321|Loss: 0.8546355962753296:   9%|▉         | 2320/25880 [30:45<4:17:20,  1.53it/s]
1|2321|Loss: 0.8546355962753296:   9%|▉         | 2321/25880 [30:45<4:27:40,  1.47it/s]
1|2322|Loss: 0.8850486874580383:   9%|▉         | 2321/25880 [30:46<4:27:40,  1.47it/s]
1|2322|Loss: 0.8850486874580383:   9%|▉         | 2322/25880 [30:46<4:31:11,  1.45it/s]
1|2323|Loss: 0.7422416806221008:   9%|▉         | 2322/25880 [30:46<4:31:11,  1.45it/s]
1|2323|Loss: 0.7422416806221008:   9%|▉         | 2323/25880 [30:47<4:46:13,  1.37it/s]
1|2324|Loss: 0.9744246006011963:   9%|▉         | 2323/25880 [30:47<4:46:13,  1.37it/s]
1|2324|Loss: 0.9744246006011963:   9%|▉         | 2324/25880 [30:48<4:51:29,  1.35it/s]
1|2325|Loss: 0.8376731872558594:   9%|▉         | 2324/25880 [30:48<4:51:29,  1.35it/s]
1|2325|Loss: 0.8376731872558594:   9%|▉         | 2325/25880 [30:48<4:59:30,  1.31it/s]
1|2326|Loss: 0.8459433317184448:   9%|▉         | 2325/25880 [30:49<4:59:30,  1.31it/s]
1|2326|Loss: 0.8459433317184448:   9%|▉         | 2326/25880 [30:49<4:48:50,  1.36it/s]
1|2327|Loss: 0.8559287786483765:   9%|▉         | 2326/25880 [30:49<4:48:50,  1.36it/s]
1|2327|Loss: 0.8559287786483765:   9%|▉         | 2327/25880 [30:50<4:43:31,  1.38it/s]
1|2328|Loss: 0.8121169209480286:   9%|▉         | 2327/25880 [30:50<4:43:31,  1.38it/s]
1|2328|Loss: 0.8121169209480286:   9%|▉         | 2328/25880 [30:51<5:01:59,  1.30it/s]
1|2329|Loss: 0.9929308295249939:   9%|▉         | 2328/25880 [30:51<5:01:59,  1.30it/s]
1|2329|Loss: 0.9929308295249939:   9%|▉         | 2329/25880 [30:51<5:11:09,  1.26it/s]
1|2330|Loss: 0.9207371473312378:   9%|▉         | 2329/25880 [30:52<5:11:09,  1.26it/s]
1|2330|Loss: 0.9207371473312378:   9%|▉         | 2330/25880 [30:52<4:49:30,  1.36it/s]
1|2331|Loss: 0.9157499074935913:   9%|▉         | 2330/25880 [30:52<4:49:30,  1.36it/s]
1|2331|Loss: 0.9157499074935913:   9%|▉         | 2331/25880 [30:53<4:57:02,  1.32it/s]
1|2332|Loss: 0.8561352491378784:   9%|▉         | 2331/25880 [30:53<4:57:02,  1.32it/s]
1|2332|Loss: 0.8561352491378784:   9%|▉         | 2332/25880 [30:54<4:54:18,  1.33it/s]
1|2333|Loss: 0.8634017705917358:   9%|▉         | 2332/25880 [30:54<4:54:18,  1.33it/s]
1|2333|Loss: 0.8634017705917358:   9%|▉         | 2333/25880 [30:55<5:16:04,  1.24it/s]
1|2334|Loss: 0.859634280204773:   9%|▉         | 2333/25880 [30:55<5:16:04,  1.24it/s] 
1|2334|Loss: 0.859634280204773:   9%|▉         | 2334/25880 [30:55<5:03:55,  1.29it/s]
1|2335|Loss: 0.9221948385238647:   9%|▉         | 2334/25880 [30:56<5:03:55,  1.29it/s]
1|2335|Loss: 0.9221948385238647:   9%|▉         | 2335/25880 [30:56<4:56:22,  1.32it/s]
1|2336|Loss: 0.8005694150924683:   9%|▉         | 2335/25880 [30:56<4:56:22,  1.32it/s]
1|2336|Loss: 0.8005694150924683:   9%|▉         | 2336/25880 [30:56<4:27:46,  1.47it/s]
1|2337|Loss: 0.853583812713623:   9%|▉         | 2336/25880 [30:57<4:27:46,  1.47it/s] 
1|2337|Loss: 0.853583812713623:   9%|▉         | 2337/25880 [30:57<4:25:46,  1.48it/s]
1|2338|Loss: 0.8279115557670593:   9%|▉         | 2337/25880 [30:58<4:25:46,  1.48it/s]
1|2338|Loss: 0.8279115557670593:   9%|▉         | 2338/25880 [30:58<4:41:10,  1.40it/s]
1|2339|Loss: 0.830810546875:   9%|▉         | 2338/25880 [30:58<4:41:10,  1.40it/s]    
1|2339|Loss: 0.830810546875:   9%|▉         | 2339/25880 [30:59<4:46:33,  1.37it/s]
1|2340|Loss: 0.8406019806861877:   9%|▉         | 2339/25880 [30:59<4:46:33,  1.37it/s]
1|2340|Loss: 0.8406019806861877:   9%|▉         | 2340/25880 [30:59<4:44:17,  1.38it/s]
1|2341|Loss: 0.8598118424415588:   9%|▉         | 2340/25880 [31:00<4:44:17,  1.38it/s]
1|2341|Loss: 0.8598118424415588:   9%|▉         | 2341/25880 [31:00<4:41:29,  1.39it/s]
1|2342|Loss: 0.9927293062210083:   9%|▉         | 2341/25880 [31:00<4:41:29,  1.39it/s]
1|2342|Loss: 0.9927293062210083:   9%|▉         | 2342/25880 [31:01<4:33:42,  1.43it/s]
1|2343|Loss: 0.8523209691047668:   9%|▉         | 2342/25880 [31:01<4:33:42,  1.43it/s]
1|2343|Loss: 0.8523209691047668:   9%|▉         | 2343/25880 [31:01<4:13:08,  1.55it/s]
1|2344|Loss: 0.9111072421073914:   9%|▉         | 2343/25880 [31:02<4:13:08,  1.55it/s]
1|2344|Loss: 0.9111072421073914:   9%|▉         | 2344/25880 [31:02<3:54:17,  1.67it/s]
1|2345|Loss: 0.9158274531364441:   9%|▉         | 2344/25880 [31:02<3:54:17,  1.67it/s]
1|2345|Loss: 0.9158274531364441:   9%|▉         | 2345/25880 [31:03<4:13:33,  1.55it/s]
1|2346|Loss: 0.947666347026825:   9%|▉         | 2345/25880 [31:03<4:13:33,  1.55it/s] 
1|2346|Loss: 0.947666347026825:   9%|▉         | 2346/25880 [31:03<4:09:09,  1.57it/s]
1|2347|Loss: 0.9528952836990356:   9%|▉         | 2346/25880 [31:03<4:09:09,  1.57it/s]
1|2347|Loss: 0.9528952836990356:   9%|▉         | 2347/25880 [31:04<3:49:42,  1.71it/s]
1|2348|Loss: 0.9093126058578491:   9%|▉         | 2347/25880 [31:04<3:49:42,  1.71it/s]
1|2348|Loss: 0.9093126058578491:   9%|▉         | 2348/25880 [31:04<4:09:01,  1.57it/s]
1|2349|Loss: 0.8001710772514343:   9%|▉         | 2348/25880 [31:05<4:09:01,  1.57it/s]
1|2349|Loss: 0.8001710772514343:   9%|▉         | 2349/25880 [31:05<4:13:50,  1.55it/s]
1|2350|Loss: 0.7346639633178711:   9%|▉         | 2349/25880 [31:05<4:13:50,  1.55it/s]
1|2350|Loss: 0.7346639633178711:   9%|▉         | 2350/25880 [31:06<4:26:46,  1.47it/s]
1|2351|Loss: 1.0126699209213257:   9%|▉         | 2350/25880 [31:06<4:26:46,  1.47it/s]
1|2351|Loss: 1.0126699209213257:   9%|▉         | 2351/25880 [31:06<4:26:39,  1.47it/s]
1|2352|Loss: 0.9313485026359558:   9%|▉         | 2351/25880 [31:07<4:26:39,  1.47it/s]
1|2352|Loss: 0.9313485026359558:   9%|▉         | 2352/25880 [31:07<4:13:42,  1.55it/s]
1|2353|Loss: 0.9992685317993164:   9%|▉         | 2352/25880 [31:07<4:13:42,  1.55it/s]
1|2353|Loss: 0.9992685317993164:   9%|▉         | 2353/25880 [31:08<4:32:41,  1.44it/s]
1|2354|Loss: 0.8184424638748169:   9%|▉         | 2353/25880 [31:08<4:32:41,  1.44it/s]
1|2354|Loss: 0.8184424638748169:   9%|▉         | 2354/25880 [31:08<4:27:07,  1.47it/s]
1|2355|Loss: 0.7873808145523071:   9%|▉         | 2354/25880 [31:09<4:27:07,  1.47it/s]
1|2355|Loss: 0.7873808145523071:   9%|▉         | 2355/25880 [31:09<4:29:12,  1.46it/s]
1|2356|Loss: 0.8436676263809204:   9%|▉         | 2355/25880 [31:10<4:29:12,  1.46it/s]
1|2356|Loss: 0.8436676263809204:   9%|▉         | 2356/25880 [31:10<4:23:48,  1.49it/s]
1|2357|Loss: 0.7833297252655029:   9%|▉         | 2356/25880 [31:10<4:23:48,  1.49it/s]
1|2357|Loss: 0.7833297252655029:   9%|▉         | 2357/25880 [31:11<4:25:58,  1.47it/s]
1|2358|Loss: 0.900991678237915:   9%|▉         | 2357/25880 [31:11<4:25:58,  1.47it/s] 
1|2358|Loss: 0.900991678237915:   9%|▉         | 2358/25880 [31:11<4:31:19,  1.44it/s]
1|2359|Loss: 0.875317394733429:   9%|▉         | 2358/25880 [31:12<4:31:19,  1.44it/s]
1|2359|Loss: 0.875317394733429:   9%|▉         | 2359/25880 [31:12<4:27:01,  1.47it/s]
1|2360|Loss: 0.8304491639137268:   9%|▉         | 2359/25880 [31:12<4:27:01,  1.47it/s]
1|2360|Loss: 0.8304491639137268:   9%|▉         | 2360/25880 [31:13<4:18:03,  1.52it/s]
1|2361|Loss: 0.8647913932800293:   9%|▉         | 2360/25880 [31:13<4:18:03,  1.52it/s]
1|2361|Loss: 0.8647913932800293:   9%|▉         | 2361/25880 [31:13<4:24:54,  1.48it/s]
1|2362|Loss: 0.876558244228363:   9%|▉         | 2361/25880 [31:14<4:24:54,  1.48it/s] 
1|2362|Loss: 0.876558244228363:   9%|▉         | 2362/25880 [31:14<4:33:16,  1.43it/s]
1|2363|Loss: 0.8617072105407715:   9%|▉         | 2362/25880 [31:14<4:33:16,  1.43it/s]
1|2363|Loss: 0.8617072105407715:   9%|▉         | 2363/25880 [31:15<4:28:43,  1.46it/s]
1|2364|Loss: 0.9643235802650452:   9%|▉         | 2363/25880 [31:15<4:28:43,  1.46it/s]
1|2364|Loss: 0.9643235802650452:   9%|▉         | 2364/25880 [31:15<4:23:18,  1.49it/s]
1|2365|Loss: 0.7785727381706238:   9%|▉         | 2364/25880 [31:16<4:23:18,  1.49it/s]
1|2365|Loss: 0.7785727381706238:   9%|▉         | 2365/25880 [31:16<4:29:43,  1.45it/s]
1|2366|Loss: 0.7575781941413879:   9%|▉         | 2365/25880 [31:16<4:29:43,  1.45it/s]
1|2366|Loss: 0.7575781941413879:   9%|▉         | 2366/25880 [31:17<4:19:10,  1.51it/s]
1|2367|Loss: 1.0802665948867798:   9%|▉         | 2366/25880 [31:17<4:19:10,  1.51it/s]
1|2367|Loss: 1.0802665948867798:   9%|▉         | 2367/25880 [31:17<4:10:04,  1.57it/s]
1|2368|Loss: 0.9583585262298584:   9%|▉         | 2367/25880 [31:18<4:10:04,  1.57it/s]
1|2368|Loss: 0.9583585262298584:   9%|▉         | 2368/25880 [31:18<4:22:26,  1.49it/s]
1|2369|Loss: 0.9001217484474182:   9%|▉         | 2368/25880 [31:18<4:22:26,  1.49it/s]
1|2369|Loss: 0.9001217484474182:   9%|▉         | 2369/25880 [31:19<4:22:50,  1.49it/s]
1|2370|Loss: 0.9382464289665222:   9%|▉         | 2369/25880 [31:19<4:22:50,  1.49it/s]
1|2370|Loss: 0.9382464289665222:   9%|▉         | 2370/25880 [31:19<4:24:33,  1.48it/s]
1|2371|Loss: 0.915102481842041:   9%|▉         | 2370/25880 [31:20<4:24:33,  1.48it/s] 
1|2371|Loss: 0.915102481842041:   9%|▉         | 2371/25880 [31:20<4:29:33,  1.45it/s]
1|2372|Loss: 0.9456186890602112:   9%|▉         | 2371/25880 [31:20<4:29:33,  1.45it/s]
1|2372|Loss: 0.9456186890602112:   9%|▉         | 2372/25880 [31:21<4:31:01,  1.45it/s]
1|2373|Loss: 0.6824461817741394:   9%|▉         | 2372/25880 [31:21<4:31:01,  1.45it/s]
1|2373|Loss: 0.6824461817741394:   9%|▉         | 2373/25880 [31:21<4:33:53,  1.43it/s]
1|2374|Loss: 0.9045604467391968:   9%|▉         | 2373/25880 [31:22<4:33:53,  1.43it/s]
1|2374|Loss: 0.9045604467391968:   9%|▉         | 2374/25880 [31:22<4:39:02,  1.40it/s]
1|2375|Loss: 0.8680627346038818:   9%|▉         | 2374/25880 [31:23<4:39:02,  1.40it/s]
1|2375|Loss: 0.8680627346038818:   9%|▉         | 2375/25880 [31:23<4:33:08,  1.43it/s]
1|2376|Loss: 0.8295511603355408:   9%|▉         | 2375/25880 [31:23<4:33:08,  1.43it/s]
1|2376|Loss: 0.8295511603355408:   9%|▉         | 2376/25880 [31:23<4:26:25,  1.47it/s]
1|2377|Loss: 0.8034570217132568:   9%|▉         | 2376/25880 [31:24<4:26:25,  1.47it/s]
1|2377|Loss: 0.8034570217132568:   9%|▉         | 2377/25880 [31:24<4:21:56,  1.50it/s]
1|2378|Loss: 0.9571316242218018:   9%|▉         | 2377/25880 [31:25<4:21:56,  1.50it/s]
1|2378|Loss: 0.9571316242218018:   9%|▉         | 2378/25880 [31:25<4:32:31,  1.44it/s]
1|2379|Loss: 0.9791707992553711:   9%|▉         | 2378/25880 [31:25<4:32:31,  1.44it/s]
1|2379|Loss: 0.9791707992553711:   9%|▉         | 2379/25880 [31:26<4:47:31,  1.36it/s]
1|2380|Loss: 0.8810123205184937:   9%|▉         | 2379/25880 [31:26<4:47:31,  1.36it/s]
1|2380|Loss: 0.8810123205184937:   9%|▉         | 2380/25880 [31:26<4:38:06,  1.41it/s]
1|2381|Loss: 0.8620470762252808:   9%|▉         | 2380/25880 [31:27<4:38:06,  1.41it/s]
1|2381|Loss: 0.8620470762252808:   9%|▉         | 2381/25880 [31:27<4:38:38,  1.41it/s]
1|2382|Loss: 0.957836389541626:   9%|▉         | 2381/25880 [31:27<4:38:38,  1.41it/s] 
1|2382|Loss: 0.957836389541626:   9%|▉         | 2382/25880 [31:28<4:50:57,  1.35it/s]
1|2383|Loss: 0.8099892735481262:   9%|▉         | 2382/25880 [31:28<4:50:57,  1.35it/s]
1|2383|Loss: 0.8099892735481262:   9%|▉         | 2383/25880 [31:29<5:08:41,  1.27it/s]
1|2384|Loss: 0.8510599136352539:   9%|▉         | 2383/25880 [31:29<5:08:41,  1.27it/s]
1|2384|Loss: 0.8510599136352539:   9%|▉         | 2384/25880 [31:30<5:06:15,  1.28it/s]
1|2385|Loss: 0.7762832641601562:   9%|▉         | 2384/25880 [31:30<5:06:15,  1.28it/s]
1|2385|Loss: 0.7762832641601562:   9%|▉         | 2385/25880 [31:30<4:49:07,  1.35it/s]
1|2386|Loss: 0.8480278849601746:   9%|▉         | 2385/25880 [31:31<4:49:07,  1.35it/s]
1|2386|Loss: 0.8480278849601746:   9%|▉         | 2386/25880 [31:31<4:57:05,  1.32it/s]
1|2387|Loss: 0.8231613636016846:   9%|▉         | 2386/25880 [31:31<4:57:05,  1.32it/s]
1|2387|Loss: 0.8231613636016846:   9%|▉         | 2387/25880 [31:32<4:56:37,  1.32it/s]
1|2388|Loss: 0.7236108779907227:   9%|▉         | 2387/25880 [31:32<4:56:37,  1.32it/s]
1|2388|Loss: 0.7236108779907227:   9%|▉         | 2388/25880 [31:33<5:02:41,  1.29it/s]
1|2389|Loss: 0.7385993003845215:   9%|▉         | 2388/25880 [31:33<5:02:41,  1.29it/s]
1|2389|Loss: 0.7385993003845215:   9%|▉         | 2389/25880 [31:33<5:00:00,  1.31it/s]
1|2390|Loss: 0.9050827026367188:   9%|▉         | 2389/25880 [31:34<5:00:00,  1.31it/s]
1|2390|Loss: 0.9050827026367188:   9%|▉         | 2390/25880 [31:34<4:54:45,  1.33it/s]
1|2391|Loss: 0.9206483364105225:   9%|▉         | 2390/25880 [31:34<4:54:45,  1.33it/s]
1|2391|Loss: 0.9206483364105225:   9%|▉         | 2391/25880 [31:35<4:48:51,  1.36it/s]
1|2392|Loss: 0.7950525879859924:   9%|▉         | 2391/25880 [31:35<4:48:51,  1.36it/s]
1|2392|Loss: 0.7950525879859924:   9%|▉         | 2392/25880 [31:36<4:57:22,  1.32it/s]
1|2393|Loss: 0.7649223208427429:   9%|▉         | 2392/25880 [31:36<4:57:22,  1.32it/s]
1|2393|Loss: 0.7649223208427429:   9%|▉         | 2393/25880 [31:36<5:07:21,  1.27it/s]
1|2394|Loss: 0.9426332116127014:   9%|▉         | 2393/25880 [31:37<5:07:21,  1.27it/s]
1|2394|Loss: 0.9426332116127014:   9%|▉         | 2394/25880 [31:37<4:55:52,  1.32it/s]
1|2395|Loss: 0.9239425659179688:   9%|▉         | 2394/25880 [31:37<4:55:52,  1.32it/s]
1|2395|Loss: 0.9239425659179688:   9%|▉         | 2395/25880 [31:38<4:27:55,  1.46it/s]
1|2396|Loss: 0.7930379509925842:   9%|▉         | 2395/25880 [31:38<4:27:55,  1.46it/s]
1|2396|Loss: 0.7930379509925842:   9%|▉         | 2396/25880 [31:38<4:01:40,  1.62it/s]
1|2397|Loss: 0.900711178779602:   9%|▉         | 2396/25880 [31:38<4:01:40,  1.62it/s] 
1|2397|Loss: 0.900711178779602:   9%|▉         | 2397/25880 [31:39<4:13:08,  1.55it/s]
1|2398|Loss: 0.7246517539024353:   9%|▉         | 2397/25880 [31:39<4:13:08,  1.55it/s]
1|2398|Loss: 0.7246517539024353:   9%|▉         | 2398/25880 [31:40<4:30:56,  1.44it/s]
1|2399|Loss: 1.0082632303237915:   9%|▉         | 2398/25880 [31:40<4:30:56,  1.44it/s]
1|2399|Loss: 1.0082632303237915:   9%|▉         | 2399/25880 [31:40<4:27:04,  1.47it/s]
1|2400|Loss: 0.7978756427764893:   9%|▉         | 2399/25880 [31:41<4:27:04,  1.47it/s]
1|2400|Loss: 0.7978756427764893:   9%|▉         | 2400/25880 [31:41<4:43:47,  1.38it/s]
1|2401|Loss: 0.9369546175003052:   9%|▉         | 2400/25880 [31:41<4:43:47,  1.38it/s]
1|2401|Loss: 0.9369546175003052:   9%|▉         | 2401/25880 [31:42<4:34:34,  1.43it/s]
1|2402|Loss: 0.809100866317749:   9%|▉         | 2401/25880 [31:42<4:34:34,  1.43it/s] 
1|2402|Loss: 0.809100866317749:   9%|▉         | 2402/25880 [31:42<4:31:36,  1.44it/s]
1|2403|Loss: 0.8695200681686401:   9%|▉         | 2402/25880 [31:43<4:31:36,  1.44it/s]
1|2403|Loss: 0.8695200681686401:   9%|▉         | 2403/25880 [31:43<4:32:17,  1.44it/s]
1|2404|Loss: 1.0082446336746216:   9%|▉         | 2403/25880 [31:43<4:32:17,  1.44it/s]
1|2404|Loss: 1.0082446336746216:   9%|▉         | 2404/25880 [31:44<4:24:34,  1.48it/s]
1|2405|Loss: 0.9102219939231873:   9%|▉         | 2404/25880 [31:44<4:24:34,  1.48it/s]
1|2405|Loss: 0.9102219939231873:   9%|▉         | 2405/25880 [31:44<4:29:44,  1.45it/s]
1|2406|Loss: 0.9360664486885071:   9%|▉         | 2405/25880 [31:45<4:29:44,  1.45it/s]
1|2406|Loss: 0.9360664486885071:   9%|▉         | 2406/25880 [31:45<4:37:15,  1.41it/s]
1|2407|Loss: 0.9654697179794312:   9%|▉         | 2406/25880 [31:46<4:37:15,  1.41it/s]
1|2407|Loss: 0.9654697179794312:   9%|▉         | 2407/25880 [31:46<4:31:23,  1.44it/s]
1|2408|Loss: 0.799812912940979:   9%|▉         | 2407/25880 [31:46<4:31:23,  1.44it/s] 
1|2408|Loss: 0.799812912940979:   9%|▉         | 2408/25880 [31:46<4:14:29,  1.54it/s]
1|2409|Loss: 0.8423132300376892:   9%|▉         | 2408/25880 [31:47<4:14:29,  1.54it/s]
1|2409|Loss: 0.8423132300376892:   9%|▉         | 2409/25880 [31:47<4:19:04,  1.51it/s]
1|2410|Loss: 0.8718928098678589:   9%|▉         | 2409/25880 [31:47<4:19:04,  1.51it/s]
1|2410|Loss: 0.8718928098678589:   9%|▉         | 2410/25880 [31:48<4:32:58,  1.43it/s]
1|2411|Loss: 0.8461803793907166:   9%|▉         | 2410/25880 [31:48<4:32:58,  1.43it/s]
1|2411|Loss: 0.8461803793907166:   9%|▉         | 2411/25880 [31:48<4:27:45,  1.46it/s]
1|2412|Loss: 0.8864250779151917:   9%|▉         | 2411/25880 [31:49<4:27:45,  1.46it/s]
1|2412|Loss: 0.8864250779151917:   9%|▉         | 2412/25880 [31:49<4:30:13,  1.45it/s]
1|2413|Loss: 0.8211349844932556:   9%|▉         | 2412/25880 [31:50<4:30:13,  1.45it/s]
1|2413|Loss: 0.8211349844932556:   9%|▉         | 2413/25880 [31:50<4:35:04,  1.42it/s]
1|2414|Loss: 0.8315927982330322:   9%|▉         | 2413/25880 [31:50<4:35:04,  1.42it/s]
1|2414|Loss: 0.8315927982330322:   9%|▉         | 2414/25880 [31:50<4:06:18,  1.59it/s]
1|2415|Loss: 0.7436875700950623:   9%|▉         | 2414/25880 [31:51<4:06:18,  1.59it/s]
1|2415|Loss: 0.7436875700950623:   9%|▉         | 2415/25880 [31:51<4:00:13,  1.63it/s]
1|2416|Loss: 0.7608733177185059:   9%|▉         | 2415/25880 [31:51<4:00:13,  1.63it/s]
1|2416|Loss: 0.7608733177185059:   9%|▉         | 2416/25880 [31:52<4:11:39,  1.55it/s]
1|2417|Loss: 0.9186948537826538:   9%|▉         | 2416/25880 [31:52<4:11:39,  1.55it/s]
1|2417|Loss: 0.9186948537826538:   9%|▉         | 2417/25880 [31:52<4:30:00,  1.45it/s]
1|2418|Loss: 0.8845750689506531:   9%|▉         | 2417/25880 [31:53<4:30:00,  1.45it/s]
1|2418|Loss: 0.8845750689506531:   9%|▉         | 2418/25880 [31:53<4:25:33,  1.47it/s]
1|2419|Loss: 0.8081254959106445:   9%|▉         | 2418/25880 [31:54<4:25:33,  1.47it/s]
1|2419|Loss: 0.8081254959106445:   9%|▉         | 2419/25880 [31:54<4:30:35,  1.45it/s]
1|2420|Loss: 0.9664938449859619:   9%|▉         | 2419/25880 [31:54<4:30:35,  1.45it/s]
1|2420|Loss: 0.9664938449859619:   9%|▉         | 2420/25880 [31:55<4:33:50,  1.43it/s]
1|2421|Loss: 0.890745222568512:   9%|▉         | 2420/25880 [31:55<4:33:50,  1.43it/s] 
1|2421|Loss: 0.890745222568512:   9%|▉         | 2421/25880 [31:55<4:37:09,  1.41it/s]
1|2422|Loss: 0.9923348426818848:   9%|▉         | 2421/25880 [31:56<4:37:09,  1.41it/s]
1|2422|Loss: 0.9923348426818848:   9%|▉         | 2422/25880 [31:56<4:40:05,  1.40it/s]
1|2423|Loss: 0.8923130631446838:   9%|▉         | 2422/25880 [31:56<4:40:05,  1.40it/s]
1|2423|Loss: 0.8923130631446838:   9%|▉         | 2423/25880 [31:57<4:47:16,  1.36it/s]
1|2424|Loss: 0.8562220335006714:   9%|▉         | 2423/25880 [31:57<4:47:16,  1.36it/s]
1|2424|Loss: 0.8562220335006714:   9%|▉         | 2424/25880 [31:58<5:00:02,  1.30it/s]
1|2425|Loss: 0.7484661936759949:   9%|▉         | 2424/25880 [31:58<5:00:02,  1.30it/s]
1|2425|Loss: 0.7484661936759949:   9%|▉         | 2425/25880 [31:59<5:21:37,  1.22it/s]
1|2426|Loss: 0.7941418886184692:   9%|▉         | 2425/25880 [31:59<5:21:37,  1.22it/s]
1|2426|Loss: 0.7941418886184692:   9%|▉         | 2426/25880 [31:59<5:13:01,  1.25it/s]
1|2427|Loss: 0.7870064973831177:   9%|▉         | 2426/25880 [32:00<5:13:01,  1.25it/s]
1|2427|Loss: 0.7870064973831177:   9%|▉         | 2427/25880 [32:00<4:49:56,  1.35it/s]
1|2428|Loss: 0.8523959517478943:   9%|▉         | 2427/25880 [32:00<4:49:56,  1.35it/s]
1|2428|Loss: 0.8523959517478943:   9%|▉         | 2428/25880 [32:01<4:44:36,  1.37it/s]
1|2429|Loss: 0.8715901970863342:   9%|▉         | 2428/25880 [32:01<4:44:36,  1.37it/s]
1|2429|Loss: 0.8715901970863342:   9%|▉         | 2429/25880 [32:01<4:30:38,  1.44it/s]
1|2430|Loss: 0.8727631568908691:   9%|▉         | 2429/25880 [32:02<4:30:38,  1.44it/s]
1|2430|Loss: 0.8727631568908691:   9%|▉         | 2430/25880 [32:02<4:10:24,  1.56it/s]
1|2431|Loss: 0.8552316427230835:   9%|▉         | 2430/25880 [32:02<4:10:24,  1.56it/s]
1|2431|Loss: 0.8552316427230835:   9%|▉         | 2431/25880 [32:03<4:24:08,  1.48it/s]
1|2432|Loss: 0.8838081955909729:   9%|▉         | 2431/25880 [32:03<4:24:08,  1.48it/s]
1|2432|Loss: 0.8838081955909729:   9%|▉         | 2432/25880 [32:03<4:33:38,  1.43it/s]
1|2433|Loss: 0.9615422487258911:   9%|▉         | 2432/25880 [32:04<4:33:38,  1.43it/s]
1|2433|Loss: 0.9615422487258911:   9%|▉         | 2433/25880 [32:04<4:37:51,  1.41it/s]
1|2434|Loss: 0.8917538523674011:   9%|▉         | 2433/25880 [32:04<4:37:51,  1.41it/s]
1|2434|Loss: 0.8917538523674011:   9%|▉         | 2434/25880 [32:05<4:40:49,  1.39it/s]
1|2435|Loss: 0.8451623320579529:   9%|▉         | 2434/25880 [32:05<4:40:49,  1.39it/s]
1|2435|Loss: 0.8451623320579529:   9%|▉         | 2435/25880 [32:06<4:45:22,  1.37it/s]
1|2436|Loss: 1.121747374534607:   9%|▉         | 2435/25880 [32:06<4:45:22,  1.37it/s] 
1|2436|Loss: 1.121747374534607:   9%|▉         | 2436/25880 [32:06<4:58:07,  1.31it/s]
1|2437|Loss: 0.9343807697296143:   9%|▉         | 2436/25880 [32:07<4:58:07,  1.31it/s]
1|2437|Loss: 0.9343807697296143:   9%|▉         | 2437/25880 [32:07<5:16:13,  1.24it/s]
1|2438|Loss: 0.8282790184020996:   9%|▉         | 2437/25880 [32:08<5:16:13,  1.24it/s]
1|2438|Loss: 0.8282790184020996:   9%|▉         | 2438/25880 [32:08<5:09:09,  1.26it/s]
1|2439|Loss: 0.7486094236373901:   9%|▉         | 2438/25880 [32:08<5:09:09,  1.26it/s]
1|2439|Loss: 0.7486094236373901:   9%|▉         | 2439/25880 [32:09<5:00:44,  1.30it/s]
1|2440|Loss: 0.7696340680122375:   9%|▉         | 2439/25880 [32:09<5:00:44,  1.30it/s]
1|2440|Loss: 0.7696340680122375:   9%|▉         | 2440/25880 [32:09<4:52:42,  1.33it/s]
1|2441|Loss: 0.8322363495826721:   9%|▉         | 2440/25880 [32:10<4:52:42,  1.33it/s]
1|2441|Loss: 0.8322363495826721:   9%|▉         | 2441/25880 [32:10<4:50:00,  1.35it/s]
1|2442|Loss: 0.8235926628112793:   9%|▉         | 2441/25880 [32:11<4:50:00,  1.35it/s]
1|2442|Loss: 0.8235926628112793:   9%|▉         | 2442/25880 [32:11<4:50:06,  1.35it/s]
1|2443|Loss: 0.9656230211257935:   9%|▉         | 2442/25880 [32:11<4:50:06,  1.35it/s]
1|2443|Loss: 0.9656230211257935:   9%|▉         | 2443/25880 [32:12<4:56:54,  1.32it/s]
1|2444|Loss: 0.9176424145698547:   9%|▉         | 2443/25880 [32:12<4:56:54,  1.32it/s]
1|2444|Loss: 0.9176424145698547:   9%|▉         | 2444/25880 [32:12<4:34:46,  1.42it/s]
1|2445|Loss: 0.7800924777984619:   9%|▉         | 2444/25880 [32:13<4:34:46,  1.42it/s]
1|2445|Loss: 0.7800924777984619:   9%|▉         | 2445/25880 [32:13<4:32:52,  1.43it/s]
1|2446|Loss: 0.9024288058280945:   9%|▉         | 2445/25880 [32:13<4:32:52,  1.43it/s]
1|2446|Loss: 0.9024288058280945:   9%|▉         | 2446/25880 [32:14<4:54:44,  1.33it/s]
1|2447|Loss: 0.8776633143424988:   9%|▉         | 2446/25880 [32:14<4:54:44,  1.33it/s]
1|2447|Loss: 0.8776633143424988:   9%|▉         | 2447/25880 [32:15<4:42:06,  1.38it/s]
1|2448|Loss: 0.849716067314148:   9%|▉         | 2447/25880 [32:15<4:42:06,  1.38it/s] 
1|2448|Loss: 0.849716067314148:   9%|▉         | 2448/25880 [32:15<4:49:26,  1.35it/s]
1|2449|Loss: 0.8972867131233215:   9%|▉         | 2448/25880 [32:16<4:49:26,  1.35it/s]
1|2449|Loss: 0.8972867131233215:   9%|▉         | 2449/25880 [32:16<4:41:50,  1.39it/s]
1|2450|Loss: 0.8771246075630188:   9%|▉         | 2449/25880 [32:16<4:41:50,  1.39it/s]
1|2450|Loss: 0.8771246075630188:   9%|▉         | 2450/25880 [32:17<4:55:33,  1.32it/s]
1|2451|Loss: 0.8192126750946045:   9%|▉         | 2450/25880 [32:17<4:55:33,  1.32it/s]
1|2451|Loss: 0.8192126750946045:   9%|▉         | 2451/25880 [32:18<4:56:58,  1.31it/s]
1|2452|Loss: 0.9430311918258667:   9%|▉         | 2451/25880 [32:18<4:56:58,  1.31it/s]
1|2452|Loss: 0.9430311918258667:   9%|▉         | 2452/25880 [32:18<4:59:59,  1.30it/s]
1|2453|Loss: 0.9925038814544678:   9%|▉         | 2452/25880 [32:19<4:59:59,  1.30it/s]
1|2453|Loss: 0.9925038814544678:   9%|▉         | 2453/25880 [32:19<4:43:18,  1.38it/s]
1|2454|Loss: 1.0066554546356201:   9%|▉         | 2453/25880 [32:19<4:43:18,  1.38it/s]
1|2454|Loss: 1.0066554546356201:   9%|▉         | 2454/25880 [32:20<4:51:33,  1.34it/s]
1|2455|Loss: 1.045027732849121:   9%|▉         | 2454/25880 [32:20<4:51:33,  1.34it/s] 
1|2455|Loss: 1.045027732849121:   9%|▉         | 2455/25880 [32:21<5:09:37,  1.26it/s]
1|2456|Loss: 0.8050597906112671:   9%|▉         | 2455/25880 [32:21<5:09:37,  1.26it/s]
1|2456|Loss: 0.8050597906112671:   9%|▉         | 2456/25880 [32:22<5:15:26,  1.24it/s]
1|2457|Loss: 0.7123568058013916:   9%|▉         | 2456/25880 [32:22<5:15:26,  1.24it/s]
1|2457|Loss: 0.7123568058013916:   9%|▉         | 2457/25880 [32:22<5:09:32,  1.26it/s]
1|2458|Loss: 1.037551999092102:   9%|▉         | 2457/25880 [32:23<5:09:32,  1.26it/s] 
1|2458|Loss: 1.037551999092102:   9%|▉         | 2458/25880 [32:23<5:16:26,  1.23it/s]
1|2459|Loss: 0.9716713428497314:   9%|▉         | 2458/25880 [32:24<5:16:26,  1.23it/s]
1|2459|Loss: 0.9716713428497314:  10%|▉         | 2459/25880 [32:24<5:11:54,  1.25it/s]
1|2460|Loss: 0.8703295588493347:  10%|▉         | 2459/25880 [32:24<5:11:54,  1.25it/s]
1|2460|Loss: 0.8703295588493347:  10%|▉         | 2460/25880 [32:25<5:04:19,  1.28it/s]
1|2461|Loss: 0.8270339965820312:  10%|▉         | 2460/25880 [32:25<5:04:19,  1.28it/s]
1|2461|Loss: 0.8270339965820312:  10%|▉         | 2461/25880 [32:25<4:50:20,  1.34it/s]
1|2462|Loss: 1.0337244272232056:  10%|▉         | 2461/25880 [32:26<4:50:20,  1.34it/s]
1|2462|Loss: 1.0337244272232056:  10%|▉         | 2462/25880 [32:26<4:26:11,  1.47it/s]
1|2463|Loss: 0.8030048608779907:  10%|▉         | 2462/25880 [32:26<4:26:11,  1.47it/s]
1|2463|Loss: 0.8030048608779907:  10%|▉         | 2463/25880 [32:26<4:18:14,  1.51it/s]
1|2464|Loss: 0.8686344623565674:  10%|▉         | 2463/25880 [32:27<4:18:14,  1.51it/s]
1|2464|Loss: 0.8686344623565674:  10%|▉         | 2464/25880 [32:27<4:46:51,  1.36it/s]
1|2465|Loss: 0.814410388469696:  10%|▉         | 2464/25880 [32:28<4:46:51,  1.36it/s] 
1|2465|Loss: 0.814410388469696:  10%|▉         | 2465/25880 [32:28<4:58:04,  1.31it/s]
1|2466|Loss: 0.7749134302139282:  10%|▉         | 2465/25880 [32:29<4:58:04,  1.31it/s]
1|2466|Loss: 0.7749134302139282:  10%|▉         | 2466/25880 [32:29<4:57:38,  1.31it/s]
1|2467|Loss: 0.8883809447288513:  10%|▉         | 2466/25880 [32:29<4:57:38,  1.31it/s]
1|2467|Loss: 0.8883809447288513:  10%|▉         | 2467/25880 [32:30<4:55:16,  1.32it/s]
1|2468|Loss: 0.8539209365844727:  10%|▉         | 2467/25880 [32:30<4:55:16,  1.32it/s]
1|2468|Loss: 0.8539209365844727:  10%|▉         | 2468/25880 [32:30<4:41:35,  1.39it/s]
1|2469|Loss: 0.8927236199378967:  10%|▉         | 2468/25880 [32:31<4:41:35,  1.39it/s]
1|2469|Loss: 0.8927236199378967:  10%|▉         | 2469/25880 [32:31<4:31:31,  1.44it/s]
1|2470|Loss: 0.871807873249054:  10%|▉         | 2469/25880 [32:31<4:31:31,  1.44it/s] 
1|2470|Loss: 0.871807873249054:  10%|▉         | 2470/25880 [32:32<4:24:56,  1.47it/s]
1|2471|Loss: 0.8060298562049866:  10%|▉         | 2470/25880 [32:32<4:24:56,  1.47it/s]
1|2471|Loss: 0.8060298562049866:  10%|▉         | 2471/25880 [32:32<4:36:23,  1.41it/s]
1|2472|Loss: 0.7499758005142212:  10%|▉         | 2471/25880 [32:33<4:36:23,  1.41it/s]
1|2472|Loss: 0.7499758005142212:  10%|▉         | 2472/25880 [32:33<4:49:32,  1.35it/s]
1|2473|Loss: 0.7560397982597351:  10%|▉         | 2472/25880 [32:34<4:49:32,  1.35it/s]
1|2473|Loss: 0.7560397982597351:  10%|▉         | 2473/25880 [32:34<4:48:02,  1.35it/s]
1|2474|Loss: 0.7787769436836243:  10%|▉         | 2473/25880 [32:34<4:48:02,  1.35it/s]
1|2474|Loss: 0.7787769436836243:  10%|▉         | 2474/25880 [32:35<5:03:06,  1.29it/s]
1|2475|Loss: 0.7679334282875061:  10%|▉         | 2474/25880 [32:35<5:03:06,  1.29it/s]
1|2475|Loss: 0.7679334282875061:  10%|▉         | 2475/25880 [32:36<5:26:32,  1.19it/s]
1|2476|Loss: 0.7718780040740967:  10%|▉         | 2475/25880 [32:36<5:26:32,  1.19it/s]
1|2476|Loss: 0.7718780040740967:  10%|▉         | 2476/25880 [32:37<5:12:07,  1.25it/s]
1|2477|Loss: 0.8842926025390625:  10%|▉         | 2476/25880 [32:37<5:12:07,  1.25it/s]
1|2477|Loss: 0.8842926025390625:  10%|▉         | 2477/25880 [32:37<5:01:44,  1.29it/s]
1|2478|Loss: 0.9092993140220642:  10%|▉         | 2477/25880 [32:38<5:01:44,  1.29it/s]
1|2478|Loss: 0.9092993140220642:  10%|▉         | 2478/25880 [32:38<5:10:47,  1.25it/s]
1|2479|Loss: 0.8205224275588989:  10%|▉         | 2478/25880 [32:38<5:10:47,  1.25it/s]
1|2479|Loss: 0.8205224275588989:  10%|▉         | 2479/25880 [32:39<4:59:10,  1.30it/s]
1|2480|Loss: 0.8559072017669678:  10%|▉         | 2479/25880 [32:39<4:59:10,  1.30it/s]
1|2480|Loss: 0.8559072017669678:  10%|▉         | 2480/25880 [32:39<4:26:47,  1.46it/s]
1|2481|Loss: 0.7437537908554077:  10%|▉         | 2480/25880 [32:40<4:26:47,  1.46it/s]
1|2481|Loss: 0.7437537908554077:  10%|▉         | 2481/25880 [32:40<4:12:49,  1.54it/s]
1|2482|Loss: 0.9046966433525085:  10%|▉         | 2481/25880 [32:40<4:12:49,  1.54it/s]
1|2482|Loss: 0.9046966433525085:  10%|▉         | 2482/25880 [32:40<4:15:07,  1.53it/s]
1|2483|Loss: 1.0140845775604248:  10%|▉         | 2482/25880 [32:41<4:15:07,  1.53it/s]
1|2483|Loss: 1.0140845775604248:  10%|▉         | 2483/25880 [32:41<4:29:39,  1.45it/s]
1|2484|Loss: 0.9003393650054932:  10%|▉         | 2483/25880 [32:42<4:29:39,  1.45it/s]
1|2484|Loss: 0.9003393650054932:  10%|▉         | 2484/25880 [32:42<4:37:45,  1.40it/s]
1|2485|Loss: 0.843926727771759:  10%|▉         | 2484/25880 [32:42<4:37:45,  1.40it/s] 
1|2485|Loss: 0.843926727771759:  10%|▉         | 2485/25880 [32:43<4:37:43,  1.40it/s]
1|2486|Loss: 0.8152924180030823:  10%|▉         | 2485/25880 [32:43<4:37:43,  1.40it/s]
1|2486|Loss: 0.8152924180030823:  10%|▉         | 2486/25880 [32:43<4:40:12,  1.39it/s]
1|2487|Loss: 0.8651251792907715:  10%|▉         | 2486/25880 [32:44<4:40:12,  1.39it/s]
1|2487|Loss: 0.8651251792907715:  10%|▉         | 2487/25880 [32:44<4:40:33,  1.39it/s]
1|2488|Loss: 0.957115650177002:  10%|▉         | 2487/25880 [32:45<4:40:33,  1.39it/s] 
1|2488|Loss: 0.957115650177002:  10%|▉         | 2488/25880 [32:45<4:41:31,  1.38it/s]
1|2489|Loss: 0.7788683772087097:  10%|▉         | 2488/25880 [32:45<4:41:31,  1.38it/s]
1|2489|Loss: 0.7788683772087097:  10%|▉         | 2489/25880 [32:46<4:40:25,  1.39it/s]
1|2490|Loss: 0.9826168417930603:  10%|▉         | 2489/25880 [32:46<4:40:25,  1.39it/s]
1|2490|Loss: 0.9826168417930603:  10%|▉         | 2490/25880 [32:46<4:30:08,  1.44it/s]
1|2491|Loss: 1.0244594812393188:  10%|▉         | 2490/25880 [32:47<4:30:08,  1.44it/s]
1|2491|Loss: 1.0244594812393188:  10%|▉         | 2491/25880 [32:47<4:32:53,  1.43it/s]
1|2492|Loss: 0.8437880873680115:  10%|▉         | 2491/25880 [32:47<4:32:53,  1.43it/s]
1|2492|Loss: 0.8437880873680115:  10%|▉         | 2492/25880 [32:48<4:28:54,  1.45it/s]
1|2493|Loss: 0.7638133764266968:  10%|▉         | 2492/25880 [32:48<4:28:54,  1.45it/s]
1|2493|Loss: 0.7638133764266968:  10%|▉         | 2493/25880 [32:48<4:32:22,  1.43it/s]
1|2494|Loss: 0.8337677121162415:  10%|▉         | 2493/25880 [32:49<4:32:22,  1.43it/s]
1|2494|Loss: 0.8337677121162415:  10%|▉         | 2494/25880 [32:49<4:46:26,  1.36it/s]
1|2495|Loss: 0.9253836870193481:  10%|▉         | 2494/25880 [32:50<4:46:26,  1.36it/s]
1|2495|Loss: 0.9253836870193481:  10%|▉         | 2495/25880 [32:50<4:48:22,  1.35it/s]
1|2496|Loss: 0.8832498788833618:  10%|▉         | 2495/25880 [32:50<4:48:22,  1.35it/s]
1|2496|Loss: 0.8832498788833618:  10%|▉         | 2496/25880 [32:51<4:38:48,  1.40it/s]
1|2497|Loss: 0.9038108587265015:  10%|▉         | 2496/25880 [32:51<4:38:48,  1.40it/s]
1|2497|Loss: 0.9038108587265015:  10%|▉         | 2497/25880 [32:51<4:49:57,  1.34it/s]
1|2498|Loss: 0.7736967206001282:  10%|▉         | 2497/25880 [32:52<4:49:57,  1.34it/s]
1|2498|Loss: 0.7736967206001282:  10%|▉         | 2498/25880 [32:52<4:52:14,  1.33it/s]
1|2499|Loss: 0.8491712808609009:  10%|▉         | 2498/25880 [32:53<4:52:14,  1.33it/s]
1|2499|Loss: 0.8491712808609009:  10%|▉         | 2499/25880 [32:53<4:50:33,  1.34it/s]
1|2500|Loss: 0.8532252907752991:  10%|▉         | 2499/25880 [32:53<4:50:33,  1.34it/s]
1|2500|Loss: 0.8532252907752991:  10%|▉         | 2500/25880 [32:54<4:49:14,  1.35it/s]
1|2501|Loss: 0.8300270438194275:  10%|▉         | 2500/25880 [32:54<4:49:14,  1.35it/s]
1|2501|Loss: 0.8300270438194275:  10%|▉         | 2501/25880 [32:54<4:46:32,  1.36it/s]
1|2502|Loss: 0.971674382686615:  10%|▉         | 2501/25880 [32:55<4:46:32,  1.36it/s] 
1|2502|Loss: 0.971674382686615:  10%|▉         | 2502/25880 [32:55<4:45:16,  1.37it/s]
1|2503|Loss: 0.97562175989151:  10%|▉         | 2502/25880 [32:56<4:45:16,  1.37it/s] 
1|2503|Loss: 0.97562175989151:  10%|▉         | 2503/25880 [32:56<4:52:03,  1.33it/s]
1|2504|Loss: 0.8874228000640869:  10%|▉         | 2503/25880 [32:56<4:52:03,  1.33it/s]
1|2504|Loss: 0.8874228000640869:  10%|▉         | 2504/25880 [32:56<4:30:51,  1.44it/s]
1|2505|Loss: 0.8961407542228699:  10%|▉         | 2504/25880 [32:57<4:30:51,  1.44it/s]
1|2505|Loss: 0.8961407542228699:  10%|▉         | 2505/25880 [32:57<4:15:30,  1.52it/s]
1|2506|Loss: 0.8421957492828369:  10%|▉         | 2505/25880 [32:57<4:15:30,  1.52it/s]
1|2506|Loss: 0.8421957492828369:  10%|▉         | 2506/25880 [32:58<4:20:25,  1.50it/s]
1|2507|Loss: 0.8002338409423828:  10%|▉         | 2506/25880 [32:58<4:20:25,  1.50it/s]
1|2507|Loss: 0.8002338409423828:  10%|▉         | 2507/25880 [32:58<4:25:23,  1.47it/s]
1|2508|Loss: 0.8456876873970032:  10%|▉         | 2507/25880 [32:59<4:25:23,  1.47it/s]
1|2508|Loss: 0.8456876873970032:  10%|▉         | 2508/25880 [32:59<4:35:40,  1.41it/s]
1|2509|Loss: 0.9066020250320435:  10%|▉         | 2508/25880 [33:00<4:35:40,  1.41it/s]
1|2509|Loss: 0.9066020250320435:  10%|▉         | 2509/25880 [33:00<4:50:46,  1.34it/s]
1|2510|Loss: 0.9134118556976318:  10%|▉         | 2509/25880 [33:00<4:50:46,  1.34it/s]
1|2510|Loss: 0.9134118556976318:  10%|▉         | 2510/25880 [33:01<4:39:25,  1.39it/s]
1|2511|Loss: 0.9793692231178284:  10%|▉         | 2510/25880 [33:01<4:39:25,  1.39it/s]
1|2511|Loss: 0.9793692231178284:  10%|▉         | 2511/25880 [33:01<4:38:46,  1.40it/s]
1|2512|Loss: 0.8884180784225464:  10%|▉         | 2511/25880 [33:02<4:38:46,  1.40it/s]
1|2512|Loss: 0.8884180784225464:  10%|▉         | 2512/25880 [33:02<4:39:37,  1.39it/s]
1|2513|Loss: 0.8209474682807922:  10%|▉         | 2512/25880 [33:03<4:39:37,  1.39it/s]
1|2513|Loss: 0.8209474682807922:  10%|▉         | 2513/25880 [33:03<4:38:56,  1.40it/s]
1|2514|Loss: 0.8879654407501221:  10%|▉         | 2513/25880 [33:03<4:38:56,  1.40it/s]
1|2514|Loss: 0.8879654407501221:  10%|▉         | 2514/25880 [33:04<4:42:04,  1.38it/s]
1|2515|Loss: 0.841338574886322:  10%|▉         | 2514/25880 [33:04<4:42:04,  1.38it/s] 
1|2515|Loss: 0.841338574886322:  10%|▉         | 2515/25880 [33:04<4:55:23,  1.32it/s]
1|2516|Loss: 0.8057458400726318:  10%|▉         | 2515/25880 [33:05<4:55:23,  1.32it/s]
1|2516|Loss: 0.8057458400726318:  10%|▉         | 2516/25880 [33:05<5:01:10,  1.29it/s]
1|2517|Loss: 0.757452666759491:  10%|▉         | 2516/25880 [33:06<5:01:10,  1.29it/s] 
1|2517|Loss: 0.757452666759491:  10%|▉         | 2517/25880 [33:06<4:37:36,  1.40it/s]
1|2518|Loss: 0.8116251230239868:  10%|▉         | 2517/25880 [33:06<4:37:36,  1.40it/s]
1|2518|Loss: 0.8116251230239868:  10%|▉         | 2518/25880 [33:06<4:33:48,  1.42it/s]
1|2519|Loss: 0.8198399543762207:  10%|▉         | 2518/25880 [33:07<4:33:48,  1.42it/s]
1|2519|Loss: 0.8198399543762207:  10%|▉         | 2519/25880 [33:07<4:36:54,  1.41it/s]
1|2520|Loss: 0.7977319955825806:  10%|▉         | 2519/25880 [33:08<4:36:54,  1.41it/s]
1|2520|Loss: 0.7977319955825806:  10%|▉         | 2520/25880 [33:08<5:17:22,  1.23it/s]
1|2521|Loss: 0.9549969434738159:  10%|▉         | 2520/25880 [33:09<5:17:22,  1.23it/s]
1|2521|Loss: 0.9549969434738159:  10%|▉         | 2521/25880 [33:09<5:34:51,  1.16it/s]
1|2522|Loss: 0.8415581583976746:  10%|▉         | 2521/25880 [33:10<5:34:51,  1.16it/s]
1|2522|Loss: 0.8415581583976746:  10%|▉         | 2522/25880 [33:10<5:24:01,  1.20it/s]
1|2523|Loss: 0.899458646774292:  10%|▉         | 2522/25880 [33:10<5:24:01,  1.20it/s] 
1|2523|Loss: 0.899458646774292:  10%|▉         | 2523/25880 [33:11<5:11:53,  1.25it/s]
1|2524|Loss: 0.8833113312721252:  10%|▉         | 2523/25880 [33:11<5:11:53,  1.25it/s]
1|2524|Loss: 0.8833113312721252:  10%|▉         | 2524/25880 [33:11<5:00:36,  1.29it/s]
1|2525|Loss: 0.8356006741523743:  10%|▉         | 2524/25880 [33:12<5:00:36,  1.29it/s]
1|2525|Loss: 0.8356006741523743:  10%|▉         | 2525/25880 [33:12<4:31:43,  1.43it/s]
1|2526|Loss: 0.8660423755645752:  10%|▉         | 2525/25880 [33:12<4:31:43,  1.43it/s]
1|2526|Loss: 0.8660423755645752:  10%|▉         | 2526/25880 [33:13<4:30:16,  1.44it/s]
1|2527|Loss: 0.7594861388206482:  10%|▉         | 2526/25880 [33:13<4:30:16,  1.44it/s]
1|2527|Loss: 0.7594861388206482:  10%|▉         | 2527/25880 [33:13<4:46:38,  1.36it/s]
1|2528|Loss: 0.8873510956764221:  10%|▉         | 2527/25880 [33:14<4:46:38,  1.36it/s]
1|2528|Loss: 0.8873510956764221:  10%|▉         | 2528/25880 [33:14<5:01:44,  1.29it/s]
1|2529|Loss: 0.931211531162262:  10%|▉         | 2528/25880 [33:15<5:01:44,  1.29it/s] 
1|2529|Loss: 0.931211531162262:  10%|▉         | 2529/25880 [33:15<5:09:45,  1.26it/s]
1|2530|Loss: 0.9969522356987:  10%|▉         | 2529/25880 [33:16<5:09:45,  1.26it/s]  
1|2530|Loss: 0.9969522356987:  10%|▉         | 2530/25880 [33:16<4:52:51,  1.33it/s]
1|2531|Loss: 0.9759848117828369:  10%|▉         | 2530/25880 [33:16<4:52:51,  1.33it/s]
1|2531|Loss: 0.9759848117828369:  10%|▉         | 2531/25880 [33:16<4:36:58,  1.41it/s]
1|2532|Loss: 0.9204484820365906:  10%|▉         | 2531/25880 [33:17<4:36:58,  1.41it/s]
1|2532|Loss: 0.9204484820365906:  10%|▉         | 2532/25880 [33:17<4:37:47,  1.40it/s]
1|2533|Loss: 0.8661060929298401:  10%|▉         | 2532/25880 [33:18<4:37:47,  1.40it/s]
1|2533|Loss: 0.8661060929298401:  10%|▉         | 2533/25880 [33:18<4:46:32,  1.36it/s]
1|2534|Loss: 0.8359386920928955:  10%|▉         | 2533/25880 [33:18<4:46:32,  1.36it/s]
1|2534|Loss: 0.8359386920928955:  10%|▉         | 2534/25880 [33:19<4:30:35,  1.44it/s]
1|2535|Loss: 0.9045385122299194:  10%|▉         | 2534/25880 [33:19<4:30:35,  1.44it/s]
1|2535|Loss: 0.9045385122299194:  10%|▉         | 2535/25880 [33:19<4:30:46,  1.44it/s]
1|2536|Loss: 0.8115240335464478:  10%|▉         | 2535/25880 [33:20<4:30:46,  1.44it/s]
1|2536|Loss: 0.8115240335464478:  10%|▉         | 2536/25880 [33:20<4:34:27,  1.42it/s]
1|2537|Loss: 0.673253059387207:  10%|▉         | 2536/25880 [33:20<4:34:27,  1.42it/s] 
1|2537|Loss: 0.673253059387207:  10%|▉         | 2537/25880 [33:21<4:42:36,  1.38it/s]
1|2538|Loss: 0.7927718758583069:  10%|▉         | 2537/25880 [33:21<4:42:36,  1.38it/s]
1|2538|Loss: 0.7927718758583069:  10%|▉         | 2538/25880 [33:21<4:28:55,  1.45it/s]
1|2539|Loss: 0.8914749026298523:  10%|▉         | 2538/25880 [33:22<4:28:55,  1.45it/s]
1|2539|Loss: 0.8914749026298523:  10%|▉         | 2539/25880 [33:22<4:19:10,  1.50it/s]
1|2540|Loss: 0.7736120223999023:  10%|▉         | 2539/25880 [33:22<4:19:10,  1.50it/s]
1|2540|Loss: 0.7736120223999023:  10%|▉         | 2540/25880 [33:23<4:35:28,  1.41it/s]
1|2541|Loss: 0.8543744683265686:  10%|▉         | 2540/25880 [33:23<4:35:28,  1.41it/s]
1|2541|Loss: 0.8543744683265686:  10%|▉         | 2541/25880 [33:24<4:43:36,  1.37it/s]
1|2542|Loss: 0.8266300559043884:  10%|▉         | 2541/25880 [33:24<4:43:36,  1.37it/s]
1|2542|Loss: 0.8266300559043884:  10%|▉         | 2542/25880 [33:24<4:34:25,  1.42it/s]
1|2543|Loss: 0.7664715647697449:  10%|▉         | 2542/25880 [33:25<4:34:25,  1.42it/s]
1|2543|Loss: 0.7664715647697449:  10%|▉         | 2543/25880 [33:25<4:21:32,  1.49it/s]
1|2544|Loss: 0.7449769377708435:  10%|▉         | 2543/25880 [33:25<4:21:32,  1.49it/s]
1|2544|Loss: 0.7449769377708435:  10%|▉         | 2544/25880 [33:26<4:25:29,  1.46it/s]
1|2545|Loss: 0.9461602568626404:  10%|▉         | 2544/25880 [33:26<4:25:29,  1.46it/s]
1|2545|Loss: 0.9461602568626404:  10%|▉         | 2545/25880 [33:26<4:20:50,  1.49it/s]
1|2546|Loss: 0.7229223847389221:  10%|▉         | 2545/25880 [33:27<4:20:50,  1.49it/s]
1|2546|Loss: 0.7229223847389221:  10%|▉         | 2546/25880 [33:27<4:17:01,  1.51it/s]
1|2547|Loss: 0.8169935345649719:  10%|▉         | 2546/25880 [33:27<4:17:01,  1.51it/s]
1|2547|Loss: 0.8169935345649719:  10%|▉         | 2547/25880 [33:28<4:23:50,  1.47it/s]
1|2548|Loss: 0.9333035945892334:  10%|▉         | 2547/25880 [33:28<4:23:50,  1.47it/s]
1|2548|Loss: 0.9333035945892334:  10%|▉         | 2548/25880 [33:28<4:31:23,  1.43it/s]
1|2549|Loss: 0.8773466348648071:  10%|▉         | 2548/25880 [33:29<4:31:23,  1.43it/s]
1|2549|Loss: 0.8773466348648071:  10%|▉         | 2549/25880 [33:29<4:33:42,  1.42it/s]
1|2550|Loss: 0.9396119713783264:  10%|▉         | 2549/25880 [33:29<4:33:42,  1.42it/s]
1|2550|Loss: 0.9396119713783264:  10%|▉         | 2550/25880 [33:30<4:19:30,  1.50it/s]
1|2551|Loss: 0.9031956791877747:  10%|▉         | 2550/25880 [33:30<4:19:30,  1.50it/s]
1|2551|Loss: 0.9031956791877747:  10%|▉         | 2551/25880 [33:30<4:36:36,  1.41it/s]
1|2552|Loss: 0.8530637621879578:  10%|▉         | 2551/25880 [33:31<4:36:36,  1.41it/s]
1|2552|Loss: 0.8530637621879578:  10%|▉         | 2552/25880 [33:31<4:42:51,  1.37it/s]
1|2553|Loss: 0.9402118921279907:  10%|▉         | 2552/25880 [33:32<4:42:51,  1.37it/s]
1|2553|Loss: 0.9402118921279907:  10%|▉         | 2553/25880 [33:32<4:41:01,  1.38it/s]
1|2554|Loss: 0.8942908048629761:  10%|▉         | 2553/25880 [33:32<4:41:01,  1.38it/s]
1|2554|Loss: 0.8942908048629761:  10%|▉         | 2554/25880 [33:33<4:40:30,  1.39it/s]
1|2555|Loss: 0.9369004964828491:  10%|▉         | 2554/25880 [33:33<4:40:30,  1.39it/s]
1|2555|Loss: 0.9369004964828491:  10%|▉         | 2555/25880 [33:33<4:32:34,  1.43it/s]
1|2556|Loss: 0.9744207859039307:  10%|▉         | 2555/25880 [33:34<4:32:34,  1.43it/s]
1|2556|Loss: 0.9744207859039307:  10%|▉         | 2556/25880 [33:34<4:45:13,  1.36it/s]
1|2557|Loss: 0.9018080830574036:  10%|▉         | 2556/25880 [33:34<4:45:13,  1.36it/s]
1|2557|Loss: 0.9018080830574036:  10%|▉         | 2557/25880 [33:35<4:55:23,  1.32it/s]
1|2558|Loss: 0.9146385788917542:  10%|▉         | 2557/25880 [33:35<4:55:23,  1.32it/s]
1|2558|Loss: 0.9146385788917542:  10%|▉         | 2558/25880 [33:36<4:45:29,  1.36it/s]
1|2559|Loss: 0.8720450401306152:  10%|▉         | 2558/25880 [33:36<4:45:29,  1.36it/s]
1|2559|Loss: 0.8720450401306152:  10%|▉         | 2559/25880 [33:36<4:17:54,  1.51it/s]
1|2560|Loss: 0.9005069136619568:  10%|▉         | 2559/25880 [33:36<4:17:54,  1.51it/s]
1|2560|Loss: 0.9005069136619568:  10%|▉         | 2560/25880 [33:37<4:07:27,  1.57it/s]
1|2561|Loss: 0.8853070735931396:  10%|▉         | 2560/25880 [33:37<4:07:27,  1.57it/s]
1|2561|Loss: 0.8853070735931396:  10%|▉         | 2561/25880 [33:37<4:05:27,  1.58it/s]
1|2562|Loss: 0.8808000087738037:  10%|▉         | 2561/25880 [33:38<4:05:27,  1.58it/s]
1|2562|Loss: 0.8808000087738037:  10%|▉         | 2562/25880 [33:38<4:05:56,  1.58it/s]
1|2563|Loss: 0.8797621726989746:  10%|▉         | 2562/25880 [33:38<4:05:56,  1.58it/s]
1|2563|Loss: 0.8797621726989746:  10%|▉         | 2563/25880 [33:39<4:41:10,  1.38it/s]
1|2564|Loss: 0.9265825748443604:  10%|▉         | 2563/25880 [33:39<4:41:10,  1.38it/s]
1|2564|Loss: 0.9265825748443604:  10%|▉         | 2564/25880 [33:40<4:47:28,  1.35it/s]
1|2565|Loss: 0.9933614730834961:  10%|▉         | 2564/25880 [33:40<4:47:28,  1.35it/s]
1|2565|Loss: 0.9933614730834961:  10%|▉         | 2565/25880 [33:40<4:47:12,  1.35it/s]
1|2566|Loss: 0.8362306356430054:  10%|▉         | 2565/25880 [33:41<4:47:12,  1.35it/s]
1|2566|Loss: 0.8362306356430054:  10%|▉         | 2566/25880 [33:41<4:56:28,  1.31it/s]
1|2567|Loss: 0.7282235026359558:  10%|▉         | 2566/25880 [33:42<4:56:28,  1.31it/s]
1|2567|Loss: 0.7282235026359558:  10%|▉         | 2567/25880 [33:42<5:05:47,  1.27it/s]
1|2568|Loss: 0.9247390031814575:  10%|▉         | 2567/25880 [33:42<5:05:47,  1.27it/s]
1|2568|Loss: 0.9247390031814575:  10%|▉         | 2568/25880 [33:43<4:44:07,  1.37it/s]
1|2569|Loss: 0.8114284873008728:  10%|▉         | 2568/25880 [33:43<4:44:07,  1.37it/s]
1|2569|Loss: 0.8114284873008728:  10%|▉         | 2569/25880 [33:43<4:44:09,  1.37it/s]
1|2570|Loss: 0.8527466654777527:  10%|▉         | 2569/25880 [33:44<4:44:09,  1.37it/s]
1|2570|Loss: 0.8527466654777527:  10%|▉         | 2570/25880 [33:44<4:27:18,  1.45it/s]
1|2571|Loss: 0.8173414468765259:  10%|▉         | 2570/25880 [33:44<4:27:18,  1.45it/s]
1|2571|Loss: 0.8173414468765259:  10%|▉         | 2571/25880 [33:44<4:13:38,  1.53it/s]
1|2572|Loss: 0.8053035140037537:  10%|▉         | 2571/25880 [33:45<4:13:38,  1.53it/s]
1|2572|Loss: 0.8053035140037537:  10%|▉         | 2572/25880 [33:45<4:10:37,  1.55it/s]
1|2573|Loss: 0.8584597110748291:  10%|▉         | 2572/25880 [33:45<4:10:37,  1.55it/s]
1|2573|Loss: 0.8584597110748291:  10%|▉         | 2573/25880 [33:46<4:19:31,  1.50it/s]
1|2574|Loss: 0.9168938398361206:  10%|▉         | 2573/25880 [33:46<4:19:31,  1.50it/s]
1|2574|Loss: 0.9168938398361206:  10%|▉         | 2574/25880 [33:47<4:25:31,  1.46it/s]
1|2575|Loss: 0.8479027152061462:  10%|▉         | 2574/25880 [33:47<4:25:31,  1.46it/s]
1|2575|Loss: 0.8479027152061462:  10%|▉         | 2575/25880 [33:47<4:30:00,  1.44it/s]
1|2576|Loss: 0.9058663845062256:  10%|▉         | 2575/25880 [33:48<4:30:00,  1.44it/s]
1|2576|Loss: 0.9058663845062256:  10%|▉         | 2576/25880 [33:48<4:40:00,  1.39it/s]
1|2577|Loss: 0.7774979472160339:  10%|▉         | 2576/25880 [33:48<4:40:00,  1.39it/s]
1|2577|Loss: 0.7774979472160339:  10%|▉         | 2577/25880 [33:49<4:29:03,  1.44it/s]
1|2578|Loss: 0.9602117538452148:  10%|▉         | 2577/25880 [33:49<4:29:03,  1.44it/s]
1|2578|Loss: 0.9602117538452148:  10%|▉         | 2578/25880 [33:49<4:30:06,  1.44it/s]
1|2579|Loss: 0.847611665725708:  10%|▉         | 2578/25880 [33:50<4:30:06,  1.44it/s] 
1|2579|Loss: 0.847611665725708:  10%|▉         | 2579/25880 [33:50<4:31:43,  1.43it/s]
1|2580|Loss: 0.8066345453262329:  10%|▉         | 2579/25880 [33:50<4:31:43,  1.43it/s]
1|2580|Loss: 0.8066345453262329:  10%|▉         | 2580/25880 [33:51<4:32:03,  1.43it/s]
1|2581|Loss: 0.9662781357765198:  10%|▉         | 2580/25880 [33:51<4:32:03,  1.43it/s]
1|2581|Loss: 0.9662781357765198:  10%|▉         | 2581/25880 [33:52<4:45:59,  1.36it/s]
1|2582|Loss: 0.8049527406692505:  10%|▉         | 2581/25880 [33:52<4:45:59,  1.36it/s]
1|2582|Loss: 0.8049527406692505:  10%|▉         | 2582/25880 [33:52<4:49:59,  1.34it/s]
1|2583|Loss: 0.6798693537712097:  10%|▉         | 2582/25880 [33:53<4:49:59,  1.34it/s]
1|2583|Loss: 0.6798693537712097:  10%|▉         | 2583/25880 [33:53<4:37:50,  1.40it/s]
1|2584|Loss: 0.7950832843780518:  10%|▉         | 2583/25880 [33:53<4:37:50,  1.40it/s]
1|2584|Loss: 0.7950832843780518:  10%|▉         | 2584/25880 [33:54<4:33:48,  1.42it/s]
1|2585|Loss: 1.0176212787628174:  10%|▉         | 2584/25880 [33:54<4:33:48,  1.42it/s]
1|2585|Loss: 1.0176212787628174:  10%|▉         | 2585/25880 [33:54<4:47:06,  1.35it/s]
1|2586|Loss: 0.965982973575592:  10%|▉         | 2585/25880 [33:55<4:47:06,  1.35it/s] 
1|2586|Loss: 0.965982973575592:  10%|▉         | 2586/25880 [33:55<4:56:22,  1.31it/s]
1|2587|Loss: 0.9423398971557617:  10%|▉         | 2586/25880 [33:56<4:56:22,  1.31it/s]
1|2587|Loss: 0.9423398971557617:  10%|▉         | 2587/25880 [33:56<4:53:43,  1.32it/s]
1|2588|Loss: 0.9721906185150146:  10%|▉         | 2587/25880 [33:56<4:53:43,  1.32it/s]
1|2588|Loss: 0.9721906185150146:  10%|█         | 2588/25880 [33:57<4:50:40,  1.34it/s]
1|2589|Loss: 0.8074830174446106:  10%|█         | 2588/25880 [33:57<4:50:40,  1.34it/s]
1|2589|Loss: 0.8074830174446106:  10%|█         | 2589/25880 [33:57<4:39:50,  1.39it/s]
1|2590|Loss: 0.7884160280227661:  10%|█         | 2589/25880 [33:58<4:39:50,  1.39it/s]
1|2590|Loss: 0.7884160280227661:  10%|█         | 2590/25880 [33:58<4:15:49,  1.52it/s]
1|2591|Loss: 0.9644480347633362:  10%|█         | 2590/25880 [33:58<4:15:49,  1.52it/s]
1|2591|Loss: 0.9644480347633362:  10%|█         | 2591/25880 [33:59<4:18:17,  1.50it/s]
1|2592|Loss: 0.7845040559768677:  10%|█         | 2591/25880 [33:59<4:18:17,  1.50it/s]
1|2592|Loss: 0.7845040559768677:  10%|█         | 2592/25880 [33:59<4:35:51,  1.41it/s]
1|2593|Loss: 0.8934640884399414:  10%|█         | 2592/25880 [34:00<4:35:51,  1.41it/s]
1|2593|Loss: 0.8934640884399414:  10%|█         | 2593/25880 [34:00<4:49:33,  1.34it/s]
1|2594|Loss: 0.9314980506896973:  10%|█         | 2593/25880 [34:01<4:49:33,  1.34it/s]
1|2594|Loss: 0.9314980506896973:  10%|█         | 2594/25880 [34:01<4:35:38,  1.41it/s]
1|2595|Loss: 0.8746967315673828:  10%|█         | 2594/25880 [34:01<4:35:38,  1.41it/s]
1|2595|Loss: 0.8746967315673828:  10%|█         | 2595/25880 [34:02<4:35:31,  1.41it/s]
1|2596|Loss: 0.5629470348358154:  10%|█         | 2595/25880 [34:02<4:35:31,  1.41it/s]
1|2596|Loss: 0.5629470348358154:  10%|█         | 2596/25880 [34:02<4:39:21,  1.39it/s]
1|2597|Loss: 0.8888092637062073:  10%|█         | 2596/25880 [34:03<4:39:21,  1.39it/s]
1|2597|Loss: 0.8888092637062073:  10%|█         | 2597/25880 [34:03<4:27:31,  1.45it/s]
1|2598|Loss: 0.8553345203399658:  10%|█         | 2597/25880 [34:03<4:27:31,  1.45it/s]
1|2598|Loss: 0.8553345203399658:  10%|█         | 2598/25880 [34:04<4:16:19,  1.51it/s]
1|2599|Loss: 0.8615875840187073:  10%|█         | 2598/25880 [34:04<4:16:19,  1.51it/s]
1|2599|Loss: 0.8615875840187073:  10%|█         | 2599/25880 [34:04<4:18:26,  1.50it/s]
1|2600|Loss: 0.8372740745544434:  10%|█         | 2599/25880 [34:05<4:18:26,  1.50it/s]
1|2600|Loss: 0.8372740745544434:  10%|█         | 2600/25880 [34:05<4:31:49,  1.43it/s]
1|2601|Loss: 0.620842695236206:  10%|█         | 2600/25880 [34:06<4:31:49,  1.43it/s] 
1|2601|Loss: 0.620842695236206:  10%|█         | 2601/25880 [34:06<5:01:09,  1.29it/s]
1|2602|Loss: 0.89345383644104:  10%|█         | 2601/25880 [34:06<5:01:09,  1.29it/s] 
1|2602|Loss: 0.89345383644104:  10%|█         | 2602/25880 [34:07<5:04:06,  1.28it/s]
1|2603|Loss: 0.9192345142364502:  10%|█         | 2602/25880 [34:07<5:04:06,  1.28it/s]
1|2603|Loss: 0.9192345142364502:  10%|█         | 2603/25880 [34:08<4:58:11,  1.30it/s]
1|2604|Loss: 0.8796173334121704:  10%|█         | 2603/25880 [34:08<4:58:11,  1.30it/s]
1|2604|Loss: 0.8796173334121704:  10%|█         | 2604/25880 [34:08<4:41:27,  1.38it/s]
1|2605|Loss: 0.8494985103607178:  10%|█         | 2604/25880 [34:09<4:41:27,  1.38it/s]
1|2605|Loss: 0.8494985103607178:  10%|█         | 2605/25880 [34:09<4:46:52,  1.35it/s]
1|2606|Loss: 0.8197091817855835:  10%|█         | 2605/25880 [34:09<4:46:52,  1.35it/s]
1|2606|Loss: 0.8197091817855835:  10%|█         | 2606/25880 [34:10<4:47:34,  1.35it/s]
1|2607|Loss: 0.9107625484466553:  10%|█         | 2606/25880 [34:10<4:47:34,  1.35it/s]
1|2607|Loss: 0.9107625484466553:  10%|█         | 2607/25880 [34:10<4:55:21,  1.31it/s]
1|2608|Loss: 0.8605341911315918:  10%|█         | 2607/25880 [34:11<4:55:21,  1.31it/s]
1|2608|Loss: 0.8605341911315918:  10%|█         | 2608/25880 [34:11<4:53:42,  1.32it/s]
1|2609|Loss: 1.006443977355957:  10%|█         | 2608/25880 [34:12<4:53:42,  1.32it/s] 
1|2609|Loss: 1.006443977355957:  10%|█         | 2609/25880 [34:12<4:52:11,  1.33it/s]
1|2610|Loss: 0.9126588106155396:  10%|█         | 2609/25880 [34:12<4:52:11,  1.33it/s]
1|2610|Loss: 0.9126588106155396:  10%|█         | 2610/25880 [34:13<4:57:30,  1.30it/s]
1|2611|Loss: 0.8258098363876343:  10%|█         | 2610/25880 [34:13<4:57:30,  1.30it/s]
1|2611|Loss: 0.8258098363876343:  10%|█         | 2611/25880 [34:14<5:16:29,  1.23it/s]
1|2612|Loss: 0.9012627005577087:  10%|█         | 2611/25880 [34:14<5:16:29,  1.23it/s]
1|2612|Loss: 0.9012627005577087:  10%|█         | 2612/25880 [34:14<5:12:04,  1.24it/s]
1|2613|Loss: 0.9946007132530212:  10%|█         | 2612/25880 [34:15<5:12:04,  1.24it/s]
1|2613|Loss: 0.9946007132530212:  10%|█         | 2613/25880 [34:15<5:00:13,  1.29it/s]
1|2614|Loss: 0.8244733810424805:  10%|█         | 2613/25880 [34:16<5:00:13,  1.29it/s]
1|2614|Loss: 0.8244733810424805:  10%|█         | 2614/25880 [34:16<5:04:53,  1.27it/s]
1|2615|Loss: 0.8791755437850952:  10%|█         | 2614/25880 [34:16<5:04:53,  1.27it/s]
1|2615|Loss: 0.8791755437850952:  10%|█         | 2615/25880 [34:17<4:59:21,  1.30it/s]
1|2616|Loss: 0.8405917882919312:  10%|█         | 2615/25880 [34:17<4:59:21,  1.30it/s]
1|2616|Loss: 0.8405917882919312:  10%|█         | 2616/25880 [34:17<4:58:38,  1.30it/s]
1|2617|Loss: 0.8864697813987732:  10%|█         | 2616/25880 [34:18<4:58:38,  1.30it/s]
1|2617|Loss: 0.8864697813987732:  10%|█         | 2617/25880 [34:18<5:01:26,  1.29it/s]
1|2618|Loss: 0.8967665433883667:  10%|█         | 2617/25880 [34:19<5:01:26,  1.29it/s]
1|2618|Loss: 0.8967665433883667:  10%|█         | 2618/25880 [34:19<4:49:16,  1.34it/s]
1|2619|Loss: 0.9374378323554993:  10%|█         | 2618/25880 [34:19<4:49:16,  1.34it/s]
1|2619|Loss: 0.9374378323554993:  10%|█         | 2619/25880 [34:20<4:54:22,  1.32it/s]
1|2620|Loss: 0.8538336157798767:  10%|█         | 2619/25880 [34:20<4:54:22,  1.32it/s]
1|2620|Loss: 0.8538336157798767:  10%|█         | 2620/25880 [34:21<4:53:42,  1.32it/s]
1|2621|Loss: 0.9898553490638733:  10%|█         | 2620/25880 [34:21<4:53:42,  1.32it/s]
1|2621|Loss: 0.9898553490638733:  10%|█         | 2621/25880 [34:21<4:48:21,  1.34it/s]
1|2622|Loss: 0.893814742565155:  10%|█         | 2621/25880 [34:22<4:48:21,  1.34it/s] 
1|2622|Loss: 0.893814742565155:  10%|█         | 2622/25880 [34:22<4:46:22,  1.35it/s]
1|2623|Loss: 0.9711647629737854:  10%|█         | 2622/25880 [34:22<4:46:22,  1.35it/s]
1|2623|Loss: 0.9711647629737854:  10%|█         | 2623/25880 [34:23<4:43:12,  1.37it/s]
1|2624|Loss: 0.771203339099884:  10%|█         | 2623/25880 [34:23<4:43:12,  1.37it/s] 
1|2624|Loss: 0.771203339099884:  10%|█         | 2624/25880 [34:24<5:28:41,  1.18it/s]
1|2625|Loss: 0.797851026058197:  10%|█         | 2624/25880 [34:24<5:28:41,  1.18it/s]
1|2625|Loss: 0.797851026058197:  10%|█         | 2625/25880 [34:24<5:06:12,  1.27it/s]
1|2626|Loss: 0.8154357075691223:  10%|█         | 2625/25880 [34:25<5:06:12,  1.27it/s]
1|2626|Loss: 0.8154357075691223:  10%|█         | 2626/25880 [34:25<5:15:20,  1.23it/s]
1|2627|Loss: 0.8385162353515625:  10%|█         | 2626/25880 [34:26<5:15:20,  1.23it/s]
1|2627|Loss: 0.8385162353515625:  10%|█         | 2627/25880 [34:26<5:12:16,  1.24it/s]
1|2628|Loss: 0.9499874114990234:  10%|█         | 2627/25880 [34:27<5:12:16,  1.24it/s]
1|2628|Loss: 0.9499874114990234:  10%|█         | 2628/25880 [34:27<5:11:42,  1.24it/s]
1|2629|Loss: 0.9294536113739014:  10%|█         | 2628/25880 [34:27<5:11:42,  1.24it/s]
1|2629|Loss: 0.9294536113739014:  10%|█         | 2629/25880 [34:28<5:01:37,  1.28it/s]
1|2630|Loss: 1.0543403625488281:  10%|█         | 2629/25880 [34:28<5:01:37,  1.28it/s]
1|2630|Loss: 1.0543403625488281:  10%|█         | 2630/25880 [34:28<4:55:25,  1.31it/s]
1|2631|Loss: 0.7896250486373901:  10%|█         | 2630/25880 [34:29<4:55:25,  1.31it/s]
1|2631|Loss: 0.7896250486373901:  10%|█         | 2631/25880 [34:29<5:08:19,  1.26it/s]
1|2632|Loss: 0.7987635731697083:  10%|█         | 2631/25880 [34:30<5:08:19,  1.26it/s]
1|2632|Loss: 0.7987635731697083:  10%|█         | 2632/25880 [34:30<5:04:16,  1.27it/s]
1|2633|Loss: 0.9471254944801331:  10%|█         | 2632/25880 [34:30<5:04:16,  1.27it/s]
1|2633|Loss: 0.9471254944801331:  10%|█         | 2633/25880 [34:31<4:55:06,  1.31it/s]
1|2634|Loss: 0.8511739373207092:  10%|█         | 2633/25880 [34:31<4:55:06,  1.31it/s]
1|2634|Loss: 0.8511739373207092:  10%|█         | 2634/25880 [34:31<4:50:21,  1.33it/s]
1|2635|Loss: 0.8713637590408325:  10%|█         | 2634/25880 [34:32<4:50:21,  1.33it/s]
1|2635|Loss: 0.8713637590408325:  10%|█         | 2635/25880 [34:32<4:40:02,  1.38it/s]
1|2636|Loss: 0.7685826420783997:  10%|█         | 2635/25880 [34:32<4:40:02,  1.38it/s]
1|2636|Loss: 0.7685826420783997:  10%|█         | 2636/25880 [34:33<4:20:29,  1.49it/s]
1|2637|Loss: 0.7544286847114563:  10%|█         | 2636/25880 [34:33<4:20:29,  1.49it/s]
1|2637|Loss: 0.7544286847114563:  10%|█         | 2637/25880 [34:33<4:22:44,  1.47it/s]
1|2638|Loss: 0.8771803975105286:  10%|█         | 2637/25880 [34:34<4:22:44,  1.47it/s]
1|2638|Loss: 0.8771803975105286:  10%|█         | 2638/25880 [34:34<4:34:37,  1.41it/s]
1|2639|Loss: 0.8119210600852966:  10%|█         | 2638/25880 [34:35<4:34:37,  1.41it/s]
1|2639|Loss: 0.8119210600852966:  10%|█         | 2639/25880 [34:35<4:59:52,  1.29it/s]
1|2640|Loss: 0.7840451002120972:  10%|█         | 2639/25880 [34:35<4:59:52,  1.29it/s]
1|2640|Loss: 0.7840451002120972:  10%|█         | 2640/25880 [34:36<4:52:29,  1.32it/s]
1|2641|Loss: 0.8781530857086182:  10%|█         | 2640/25880 [34:36<4:52:29,  1.32it/s]
1|2641|Loss: 0.8781530857086182:  10%|█         | 2641/25880 [34:36<4:49:54,  1.34it/s]
1|2642|Loss: 0.8433356285095215:  10%|█         | 2641/25880 [34:37<4:49:54,  1.34it/s]
1|2642|Loss: 0.8433356285095215:  10%|█         | 2642/25880 [34:37<4:33:00,  1.42it/s]
1|2643|Loss: 0.8621377944946289:  10%|█         | 2642/25880 [34:37<4:33:00,  1.42it/s]
1|2643|Loss: 0.8621377944946289:  10%|█         | 2643/25880 [34:38<4:31:44,  1.43it/s]
1|2644|Loss: 0.8425304293632507:  10%|█         | 2643/25880 [34:38<4:31:44,  1.43it/s]
1|2644|Loss: 0.8425304293632507:  10%|█         | 2644/25880 [34:38<4:34:40,  1.41it/s]
1|2645|Loss: 0.9087121486663818:  10%|█         | 2644/25880 [34:39<4:34:40,  1.41it/s]
1|2645|Loss: 0.9087121486663818:  10%|█         | 2645/25880 [34:39<4:29:29,  1.44it/s]
1|2646|Loss: 0.820285439491272:  10%|█         | 2645/25880 [34:40<4:29:29,  1.44it/s] 
1|2646|Loss: 0.820285439491272:  10%|█         | 2646/25880 [34:40<4:49:09,  1.34it/s]
1|2647|Loss: 0.8893234729766846:  10%|█         | 2646/25880 [34:40<4:49:09,  1.34it/s]
1|2647|Loss: 0.8893234729766846:  10%|█         | 2647/25880 [34:41<4:35:08,  1.41it/s]
1|2648|Loss: 0.9048510193824768:  10%|█         | 2647/25880 [34:41<4:35:08,  1.41it/s]
1|2648|Loss: 0.9048510193824768:  10%|█         | 2648/25880 [34:41<4:24:56,  1.46it/s]
1|2649|Loss: 0.9820054769515991:  10%|█         | 2648/25880 [34:42<4:24:56,  1.46it/s]
1|2649|Loss: 0.9820054769515991:  10%|█         | 2649/25880 [34:42<4:14:49,  1.52it/s]
1|2650|Loss: 0.8331649303436279:  10%|█         | 2649/25880 [34:42<4:14:49,  1.52it/s]
1|2650|Loss: 0.8331649303436279:  10%|█         | 2650/25880 [34:43<4:32:15,  1.42it/s]
1|2651|Loss: 0.958262026309967:  10%|█         | 2650/25880 [34:43<4:32:15,  1.42it/s] 
1|2651|Loss: 0.958262026309967:  10%|█         | 2651/25880 [34:43<4:29:11,  1.44it/s]
1|2652|Loss: 0.8373801708221436:  10%|█         | 2651/25880 [34:44<4:29:11,  1.44it/s]
1|2652|Loss: 0.8373801708221436:  10%|█         | 2652/25880 [34:44<4:36:24,  1.40it/s]
1|2653|Loss: 0.90541011095047:  10%|█         | 2652/25880 [34:45<4:36:24,  1.40it/s]  
1|2653|Loss: 0.90541011095047:  10%|█         | 2653/25880 [34:45<4:40:59,  1.38it/s]
1|2654|Loss: 0.8114103674888611:  10%|█         | 2653/25880 [34:45<4:40:59,  1.38it/s]
1|2654|Loss: 0.8114103674888611:  10%|█         | 2654/25880 [34:46<4:42:21,  1.37it/s]
1|2655|Loss: 0.7941452264785767:  10%|█         | 2654/25880 [34:46<4:42:21,  1.37it/s]
1|2655|Loss: 0.7941452264785767:  10%|█         | 2655/25880 [34:46<4:25:59,  1.46it/s]
1|2656|Loss: 0.8333608508110046:  10%|█         | 2655/25880 [34:47<4:25:59,  1.46it/s]
1|2656|Loss: 0.8333608508110046:  10%|█         | 2656/25880 [34:47<4:18:35,  1.50it/s]
1|2657|Loss: 0.7945685386657715:  10%|█         | 2656/25880 [34:47<4:18:35,  1.50it/s]
1|2657|Loss: 0.7945685386657715:  10%|█         | 2657/25880 [34:47<3:58:29,  1.62it/s]
1|2658|Loss: 0.8171164989471436:  10%|█         | 2657/25880 [34:48<3:58:29,  1.62it/s]
1|2658|Loss: 0.8171164989471436:  10%|█         | 2658/25880 [34:48<3:56:49,  1.63it/s]
1|2659|Loss: 1.0598191022872925:  10%|█         | 2658/25880 [34:48<3:56:49,  1.63it/s]
1|2659|Loss: 1.0598191022872925:  10%|█         | 2659/25880 [34:49<4:13:41,  1.53it/s]
1|2660|Loss: 0.8999427556991577:  10%|█         | 2659/25880 [34:49<4:13:41,  1.53it/s]
1|2660|Loss: 0.8999427556991577:  10%|█         | 2660/25880 [34:49<4:23:51,  1.47it/s]
1|2661|Loss: 0.9177923202514648:  10%|█         | 2660/25880 [34:50<4:23:51,  1.47it/s]
1|2661|Loss: 0.9177923202514648:  10%|█         | 2661/25880 [34:50<4:18:24,  1.50it/s]
1|2662|Loss: 0.87333083152771:  10%|█         | 2661/25880 [34:50<4:18:24,  1.50it/s]  
1|2662|Loss: 0.87333083152771:  10%|█         | 2662/25880 [34:51<4:28:09,  1.44it/s]
1|2663|Loss: 0.8648199439048767:  10%|█         | 2662/25880 [34:51<4:28:09,  1.44it/s]
1|2663|Loss: 0.8648199439048767:  10%|█         | 2663/25880 [34:52<4:43:37,  1.36it/s]
1|2664|Loss: 0.8224874138832092:  10%|█         | 2663/25880 [34:52<4:43:37,  1.36it/s]
1|2664|Loss: 0.8224874138832092:  10%|█         | 2664/25880 [34:52<4:43:08,  1.37it/s]
1|2665|Loss: 0.8287513852119446:  10%|█         | 2664/25880 [34:53<4:43:08,  1.37it/s]
1|2665|Loss: 0.8287513852119446:  10%|█         | 2665/25880 [34:53<4:33:49,  1.41it/s]
1|2666|Loss: 0.8979108929634094:  10%|█         | 2665/25880 [34:53<4:33:49,  1.41it/s]
1|2666|Loss: 0.8979108929634094:  10%|█         | 2666/25880 [34:54<4:45:47,  1.35it/s]
1|2667|Loss: 0.8472349047660828:  10%|█         | 2666/25880 [34:54<4:45:47,  1.35it/s]
1|2667|Loss: 0.8472349047660828:  10%|█         | 2667/25880 [34:54<4:16:28,  1.51it/s]
1|2668|Loss: 0.7568458318710327:  10%|█         | 2667/25880 [34:55<4:16:28,  1.51it/s]
1|2668|Loss: 0.7568458318710327:  10%|█         | 2668/25880 [34:55<4:06:51,  1.57it/s]
1|2669|Loss: 0.8098611235618591:  10%|█         | 2668/25880 [34:55<4:06:51,  1.57it/s]
1|2669|Loss: 0.8098611235618591:  10%|█         | 2669/25880 [34:56<4:24:12,  1.46it/s]
1|2670|Loss: 0.803424060344696:  10%|█         | 2669/25880 [34:56<4:24:12,  1.46it/s] 
1|2670|Loss: 0.803424060344696:  10%|█         | 2670/25880 [34:56<4:33:43,  1.41it/s]
1|2671|Loss: 0.9325874447822571:  10%|█         | 2670/25880 [34:57<4:33:43,  1.41it/s]
1|2671|Loss: 0.9325874447822571:  10%|█         | 2671/25880 [34:57<4:46:30,  1.35it/s]
1|2672|Loss: 0.8162342309951782:  10%|█         | 2671/25880 [34:58<4:46:30,  1.35it/s]
1|2672|Loss: 0.8162342309951782:  10%|█         | 2672/25880 [34:58<5:13:15,  1.23it/s]
1|2673|Loss: 0.7957364320755005:  10%|█         | 2672/25880 [34:59<5:13:15,  1.23it/s]
1|2673|Loss: 0.7957364320755005:  10%|█         | 2673/25880 [34:59<5:11:43,  1.24it/s]
1|2674|Loss: 0.8796806335449219:  10%|█         | 2673/25880 [34:59<5:11:43,  1.24it/s]
1|2674|Loss: 0.8796806335449219:  10%|█         | 2674/25880 [35:00<5:09:38,  1.25it/s]
1|2675|Loss: 0.7686449885368347:  10%|█         | 2674/25880 [35:00<5:09:38,  1.25it/s]
1|2675|Loss: 0.7686449885368347:  10%|█         | 2675/25880 [35:01<5:33:47,  1.16it/s]
1|2676|Loss: 0.799996554851532:  10%|█         | 2675/25880 [35:01<5:33:47,  1.16it/s] 
1|2676|Loss: 0.799996554851532:  10%|█         | 2676/25880 [35:02<5:17:39,  1.22it/s]
1|2677|Loss: 0.8087844848632812:  10%|█         | 2676/25880 [35:02<5:17:39,  1.22it/s]
1|2677|Loss: 0.8087844848632812:  10%|█         | 2677/25880 [35:02<4:44:35,  1.36it/s]
1|2678|Loss: 0.9171327352523804:  10%|█         | 2677/25880 [35:02<4:44:35,  1.36it/s]
1|2678|Loss: 0.9171327352523804:  10%|█         | 2678/25880 [35:03<4:50:32,  1.33it/s]
1|2679|Loss: 0.7228244543075562:  10%|█         | 2678/25880 [35:03<4:50:32,  1.33it/s]
1|2679|Loss: 0.7228244543075562:  10%|█         | 2679/25880 [35:04<4:48:47,  1.34it/s]
1|2680|Loss: 0.8042036294937134:  10%|█         | 2679/25880 [35:04<4:48:47,  1.34it/s]
1|2680|Loss: 0.8042036294937134:  10%|█         | 2680/25880 [35:04<4:56:23,  1.30it/s]
1|2681|Loss: 0.7939492464065552:  10%|█         | 2680/25880 [35:05<4:56:23,  1.30it/s]
1|2681|Loss: 0.7939492464065552:  10%|█         | 2681/25880 [35:05<4:36:27,  1.40it/s]
1|2682|Loss: 0.9334571361541748:  10%|█         | 2681/25880 [35:05<4:36:27,  1.40it/s]
1|2682|Loss: 0.9334571361541748:  10%|█         | 2682/25880 [35:06<4:19:19,  1.49it/s]
1|2683|Loss: 0.7269729971885681:  10%|█         | 2682/25880 [35:06<4:19:19,  1.49it/s]
1|2683|Loss: 0.7269729971885681:  10%|█         | 2683/25880 [35:06<4:45:55,  1.35it/s]
1|2684|Loss: 0.9200078845024109:  10%|█         | 2683/25880 [35:07<4:45:55,  1.35it/s]
1|2684|Loss: 0.9200078845024109:  10%|█         | 2684/25880 [35:07<4:41:30,  1.37it/s]
1|2685|Loss: 0.8967204689979553:  10%|█         | 2684/25880 [35:08<4:41:30,  1.37it/s]
1|2685|Loss: 0.8967204689979553:  10%|█         | 2685/25880 [35:08<4:37:00,  1.40it/s]
1|2686|Loss: 0.9287119507789612:  10%|█         | 2685/25880 [35:08<4:37:00,  1.40it/s]
1|2686|Loss: 0.9287119507789612:  10%|█         | 2686/25880 [35:08<4:21:45,  1.48it/s]
1|2687|Loss: 1.1414198875427246:  10%|█         | 2686/25880 [35:09<4:21:45,  1.48it/s]
1|2687|Loss: 1.1414198875427246:  10%|█         | 2687/25880 [35:09<4:33:08,  1.42it/s]
1|2688|Loss: 0.8544687628746033:  10%|█         | 2687/25880 [35:10<4:33:08,  1.42it/s]
1|2688|Loss: 0.8544687628746033:  10%|█         | 2688/25880 [35:10<4:49:36,  1.33it/s]
1|2689|Loss: 0.8420852422714233:  10%|█         | 2688/25880 [35:11<4:49:36,  1.33it/s]
1|2689|Loss: 0.8420852422714233:  10%|█         | 2689/25880 [35:11<5:04:00,  1.27it/s]
1|2690|Loss: 0.9293338656425476:  10%|█         | 2689/25880 [35:11<5:04:00,  1.27it/s]
1|2690|Loss: 0.9293338656425476:  10%|█         | 2690/25880 [35:12<5:12:04,  1.24it/s]
1|2691|Loss: 0.8162468671798706:  10%|█         | 2690/25880 [35:12<5:12:04,  1.24it/s]
1|2691|Loss: 0.8162468671798706:  10%|█         | 2691/25880 [35:12<4:56:08,  1.31it/s]
1|2692|Loss: 0.892350435256958:  10%|█         | 2691/25880 [35:13<4:56:08,  1.31it/s] 
1|2692|Loss: 0.892350435256958:  10%|█         | 2692/25880 [35:13<4:28:55,  1.44it/s]
1|2693|Loss: 0.8221288919448853:  10%|█         | 2692/25880 [35:13<4:28:55,  1.44it/s]
1|2693|Loss: 0.8221288919448853:  10%|█         | 2693/25880 [35:14<4:16:27,  1.51it/s]
1|2694|Loss: 0.7874032258987427:  10%|█         | 2693/25880 [35:14<4:16:27,  1.51it/s]
1|2694|Loss: 0.7874032258987427:  10%|█         | 2694/25880 [35:14<4:28:41,  1.44it/s]
1|2695|Loss: 0.8851169943809509:  10%|█         | 2694/25880 [35:15<4:28:41,  1.44it/s]
1|2695|Loss: 0.8851169943809509:  10%|█         | 2695/25880 [35:15<4:43:12,  1.36it/s]
1|2696|Loss: 0.8200336694717407:  10%|█         | 2695/25880 [35:16<4:43:12,  1.36it/s]
1|2696|Loss: 0.8200336694717407:  10%|█         | 2696/25880 [35:16<4:32:36,  1.42it/s]
1|2697|Loss: 0.8463465571403503:  10%|█         | 2696/25880 [35:16<4:32:36,  1.42it/s]
1|2697|Loss: 0.8463465571403503:  10%|█         | 2697/25880 [35:17<4:44:14,  1.36it/s]
1|2698|Loss: 0.8171852231025696:  10%|█         | 2697/25880 [35:17<4:44:14,  1.36it/s]
1|2698|Loss: 0.8171852231025696:  10%|█         | 2698/25880 [35:17<4:36:47,  1.40it/s]
1|2699|Loss: 0.8521121740341187:  10%|█         | 2698/25880 [35:18<4:36:47,  1.40it/s]
1|2699|Loss: 0.8521121740341187:  10%|█         | 2699/25880 [35:18<4:36:37,  1.40it/s]
1|2700|Loss: 0.7720707058906555:  10%|█         | 2699/25880 [35:18<4:36:37,  1.40it/s]
1|2700|Loss: 0.7720707058906555:  10%|█         | 2700/25880 [35:19<4:35:47,  1.40it/s]
1|2701|Loss: 0.7774351835250854:  10%|█         | 2700/25880 [35:19<4:35:47,  1.40it/s]
1|2701|Loss: 0.7774351835250854:  10%|█         | 2701/25880 [35:19<4:34:05,  1.41it/s]
1|2702|Loss: 0.8640249967575073:  10%|█         | 2701/25880 [35:20<4:34:05,  1.41it/s]
1|2702|Loss: 0.8640249967575073:  10%|█         | 2702/25880 [35:20<4:40:07,  1.38it/s]
1|2703|Loss: 0.8556879162788391:  10%|█         | 2702/25880 [35:21<4:40:07,  1.38it/s]
1|2703|Loss: 0.8556879162788391:  10%|█         | 2703/25880 [35:21<4:53:17,  1.32it/s]
1|2704|Loss: 0.7863031625747681:  10%|█         | 2703/25880 [35:21<4:53:17,  1.32it/s]
1|2704|Loss: 0.7863031625747681:  10%|█         | 2704/25880 [35:22<5:02:02,  1.28it/s]
1|2705|Loss: 0.8588108420372009:  10%|█         | 2704/25880 [35:22<5:02:02,  1.28it/s]
1|2705|Loss: 0.8588108420372009:  10%|█         | 2705/25880 [35:23<4:55:03,  1.31it/s]
1|2706|Loss: 0.8835194110870361:  10%|█         | 2705/25880 [35:23<4:55:03,  1.31it/s]
1|2706|Loss: 0.8835194110870361:  10%|█         | 2706/25880 [35:23<5:04:22,  1.27it/s]
1|2707|Loss: 0.828475832939148:  10%|█         | 2706/25880 [35:24<5:04:22,  1.27it/s] 
1|2707|Loss: 0.828475832939148:  10%|█         | 2707/25880 [35:24<5:07:43,  1.26it/s]
1|2708|Loss: 1.0233412981033325:  10%|█         | 2707/25880 [35:25<5:07:43,  1.26it/s]
1|2708|Loss: 1.0233412981033325:  10%|█         | 2708/25880 [35:25<4:59:21,  1.29it/s]
1|2709|Loss: 0.8472224473953247:  10%|█         | 2708/25880 [35:25<4:59:21,  1.29it/s]
1|2709|Loss: 0.8472224473953247:  10%|█         | 2709/25880 [35:26<5:04:32,  1.27it/s]
1|2710|Loss: 0.8794093728065491:  10%|█         | 2709/25880 [35:26<5:04:32,  1.27it/s]
1|2710|Loss: 0.8794093728065491:  10%|█         | 2710/25880 [35:27<4:58:11,  1.30it/s]
1|2711|Loss: 0.6844399571418762:  10%|█         | 2710/25880 [35:27<4:58:11,  1.30it/s]
1|2711|Loss: 0.6844399571418762:  10%|█         | 2711/25880 [35:27<5:06:25,  1.26it/s]
1|2712|Loss: 0.6601385474205017:  10%|█         | 2711/25880 [35:28<5:06:25,  1.26it/s]
1|2712|Loss: 0.6601385474205017:  10%|█         | 2712/25880 [35:28<4:49:56,  1.33it/s]
1|2713|Loss: 0.8973745107650757:  10%|█         | 2712/25880 [35:28<4:49:56,  1.33it/s]
1|2713|Loss: 0.8973745107650757:  10%|█         | 2713/25880 [35:29<4:50:02,  1.33it/s]
1|2714|Loss: 0.7713978886604309:  10%|█         | 2713/25880 [35:29<4:50:02,  1.33it/s]
1|2714|Loss: 0.7713978886604309:  10%|█         | 2714/25880 [35:29<4:29:15,  1.43it/s]
1|2715|Loss: 0.8999675512313843:  10%|█         | 2714/25880 [35:30<4:29:15,  1.43it/s]
1|2715|Loss: 0.8999675512313843:  10%|█         | 2715/25880 [35:30<4:25:39,  1.45it/s]
1|2716|Loss: 0.7772563099861145:  10%|█         | 2715/25880 [35:30<4:25:39,  1.45it/s]
1|2716|Loss: 0.7772563099861145:  10%|█         | 2716/25880 [35:31<4:18:52,  1.49it/s]
1|2717|Loss: 0.9619031548500061:  10%|█         | 2716/25880 [35:31<4:18:52,  1.49it/s]
1|2717|Loss: 0.9619031548500061:  10%|█         | 2717/25880 [35:31<4:29:19,  1.43it/s]
1|2718|Loss: 1.0202454328536987:  10%|█         | 2717/25880 [35:32<4:29:19,  1.43it/s]
1|2718|Loss: 1.0202454328536987:  11%|█         | 2718/25880 [35:32<4:49:01,  1.34it/s]
1|2719|Loss: 0.9096245169639587:  11%|█         | 2718/25880 [35:33<4:49:01,  1.34it/s]
1|2719|Loss: 0.9096245169639587:  11%|█         | 2719/25880 [35:33<4:53:05,  1.32it/s]
1|2720|Loss: 0.8119662404060364:  11%|█         | 2719/25880 [35:33<4:53:05,  1.32it/s]
1|2720|Loss: 0.8119662404060364:  11%|█         | 2720/25880 [35:34<5:00:32,  1.28it/s]
1|2721|Loss: 0.8293529152870178:  11%|█         | 2720/25880 [35:34<5:00:32,  1.28it/s]
1|2721|Loss: 0.8293529152870178:  11%|█         | 2721/25880 [35:34<4:38:29,  1.39it/s]
1|2722|Loss: 0.9748489856719971:  11%|█         | 2721/25880 [35:35<4:38:29,  1.39it/s]
1|2722|Loss: 0.9748489856719971:  11%|█         | 2722/25880 [35:35<4:34:28,  1.41it/s]
1|2723|Loss: 0.8122187852859497:  11%|█         | 2722/25880 [35:36<4:34:28,  1.41it/s]
1|2723|Loss: 0.8122187852859497:  11%|█         | 2723/25880 [35:36<5:01:11,  1.28it/s]
1|2724|Loss: 0.9287537336349487:  11%|█         | 2723/25880 [35:37<5:01:11,  1.28it/s]
1|2724|Loss: 0.9287537336349487:  11%|█         | 2724/25880 [35:37<5:38:48,  1.14it/s]
1|2725|Loss: 0.8918173313140869:  11%|█         | 2724/25880 [35:38<5:38:48,  1.14it/s]
1|2725|Loss: 0.8918173313140869:  11%|█         | 2725/25880 [35:38<5:36:52,  1.15it/s]
1|2726|Loss: 0.8137032985687256:  11%|█         | 2725/25880 [35:38<5:36:52,  1.15it/s]
1|2726|Loss: 0.8137032985687256:  11%|█         | 2726/25880 [35:39<5:14:05,  1.23it/s]
1|2727|Loss: 1.064307689666748:  11%|█         | 2726/25880 [35:39<5:14:05,  1.23it/s] 
1|2727|Loss: 1.064307689666748:  11%|█         | 2727/25880 [35:39<4:49:17,  1.33it/s]
1|2728|Loss: 0.9294372200965881:  11%|█         | 2727/25880 [35:40<4:49:17,  1.33it/s]
1|2728|Loss: 0.9294372200965881:  11%|█         | 2728/25880 [35:40<4:35:38,  1.40it/s]
1|2729|Loss: 0.8718504905700684:  11%|█         | 2728/25880 [35:40<4:35:38,  1.40it/s]
1|2729|Loss: 0.8718504905700684:  11%|█         | 2729/25880 [35:41<4:42:26,  1.37it/s]
1|2730|Loss: 0.8469254374504089:  11%|█         | 2729/25880 [35:41<4:42:26,  1.37it/s]
1|2730|Loss: 0.8469254374504089:  11%|█         | 2730/25880 [35:41<4:43:39,  1.36it/s]
1|2731|Loss: 0.930101215839386:  11%|█         | 2730/25880 [35:42<4:43:39,  1.36it/s] 
1|2731|Loss: 0.930101215839386:  11%|█         | 2731/25880 [35:42<4:31:53,  1.42it/s]
1|2732|Loss: 0.9033361077308655:  11%|█         | 2731/25880 [35:42<4:31:53,  1.42it/s]
1|2732|Loss: 0.9033361077308655:  11%|█         | 2732/25880 [35:43<4:31:26,  1.42it/s]
1|2733|Loss: 0.7285296320915222:  11%|█         | 2732/25880 [35:43<4:31:26,  1.42it/s]
1|2733|Loss: 0.7285296320915222:  11%|█         | 2733/25880 [35:44<4:45:59,  1.35it/s]
1|2734|Loss: 0.881954550743103:  11%|█         | 2733/25880 [35:44<4:45:59,  1.35it/s] 
1|2734|Loss: 0.881954550743103:  11%|█         | 2734/25880 [35:44<4:48:07,  1.34it/s]
1|2735|Loss: 0.8483020663261414:  11%|█         | 2734/25880 [35:45<4:48:07,  1.34it/s]
1|2735|Loss: 0.8483020663261414:  11%|█         | 2735/25880 [35:45<4:35:07,  1.40it/s]
1|2736|Loss: 0.7892749309539795:  11%|█         | 2735/25880 [35:45<4:35:07,  1.40it/s]
1|2736|Loss: 0.7892749309539795:  11%|█         | 2736/25880 [35:46<4:26:06,  1.45it/s]
1|2737|Loss: 0.8990539312362671:  11%|█         | 2736/25880 [35:46<4:26:06,  1.45it/s]
1|2737|Loss: 0.8990539312362671:  11%|█         | 2737/25880 [35:46<4:30:30,  1.43it/s]
1|2738|Loss: 0.9430071711540222:  11%|█         | 2737/25880 [35:47<4:30:30,  1.43it/s]
1|2738|Loss: 0.9430071711540222:  11%|█         | 2738/25880 [35:47<4:36:37,  1.39it/s]
1|2739|Loss: 0.9020999670028687:  11%|█         | 2738/25880 [35:48<4:36:37,  1.39it/s]
1|2739|Loss: 0.9020999670028687:  11%|█         | 2739/25880 [35:48<4:57:05,  1.30it/s]
1|2740|Loss: 1.0780214071273804:  11%|█         | 2739/25880 [35:49<4:57:05,  1.30it/s]
1|2740|Loss: 1.0780214071273804:  11%|█         | 2740/25880 [35:49<5:10:35,  1.24it/s]
1|2741|Loss: 1.0549421310424805:  11%|█         | 2740/25880 [35:49<5:10:35,  1.24it/s]
1|2741|Loss: 1.0549421310424805:  11%|█         | 2741/25880 [35:50<5:15:47,  1.22it/s]
1|2742|Loss: 0.890672504901886:  11%|█         | 2741/25880 [35:50<5:15:47,  1.22it/s] 
1|2742|Loss: 0.890672504901886:  11%|█         | 2742/25880 [35:51<5:20:30,  1.20it/s]
1|2743|Loss: 0.8270280957221985:  11%|█         | 2742/25880 [35:51<5:20:30,  1.20it/s]
1|2743|Loss: 0.8270280957221985:  11%|█         | 2743/25880 [35:51<5:12:40,  1.23it/s]
1|2744|Loss: 0.7723153233528137:  11%|█         | 2743/25880 [35:52<5:12:40,  1.23it/s]
1|2744|Loss: 0.7723153233528137:  11%|█         | 2744/25880 [35:52<5:20:45,  1.20it/s]
1|2745|Loss: 0.9354575872421265:  11%|█         | 2744/25880 [35:53<5:20:45,  1.20it/s]
1|2745|Loss: 0.9354575872421265:  11%|█         | 2745/25880 [35:53<5:02:39,  1.27it/s]
1|2746|Loss: 0.9492942690849304:  11%|█         | 2745/25880 [35:53<5:02:39,  1.27it/s]
1|2746|Loss: 0.9492942690849304:  11%|█         | 2746/25880 [35:54<4:54:24,  1.31it/s]
1|2747|Loss: 0.9507792592048645:  11%|█         | 2746/25880 [35:54<4:54:24,  1.31it/s]
1|2747|Loss: 0.9507792592048645:  11%|█         | 2747/25880 [35:54<4:50:07,  1.33it/s]
1|2748|Loss: 0.8679286241531372:  11%|█         | 2747/25880 [35:55<4:50:07,  1.33it/s]
1|2748|Loss: 0.8679286241531372:  11%|█         | 2748/25880 [35:55<4:48:09,  1.34it/s]
1|2749|Loss: 0.96608567237854:  11%|█         | 2748/25880 [35:56<4:48:09,  1.34it/s]  
1|2749|Loss: 0.96608567237854:  11%|█         | 2749/25880 [35:56<4:44:11,  1.36it/s]
1|2750|Loss: 0.883870005607605:  11%|█         | 2749/25880 [35:56<4:44:11,  1.36it/s]
1|2750|Loss: 0.883870005607605:  11%|█         | 2750/25880 [35:57<5:00:02,  1.28it/s]
1|2751|Loss: 0.9356410503387451:  11%|█         | 2750/25880 [35:57<5:00:02,  1.28it/s]
1|2751|Loss: 0.9356410503387451:  11%|█         | 2751/25880 [35:58<5:04:11,  1.27it/s]
1|2752|Loss: 0.8622904419898987:  11%|█         | 2751/25880 [35:58<5:04:11,  1.27it/s]
1|2752|Loss: 0.8622904419898987:  11%|█         | 2752/25880 [35:58<4:51:13,  1.32it/s]
1|2753|Loss: 0.8130068182945251:  11%|█         | 2752/25880 [35:59<4:51:13,  1.32it/s]
1|2753|Loss: 0.8130068182945251:  11%|█         | 2753/25880 [35:59<4:43:20,  1.36it/s]
1|2754|Loss: 0.7724531292915344:  11%|█         | 2753/25880 [35:59<4:43:20,  1.36it/s]
1|2754|Loss: 0.7724531292915344:  11%|█         | 2754/25880 [36:00<4:28:17,  1.44it/s]
1|2755|Loss: 0.8942692279815674:  11%|█         | 2754/25880 [36:00<4:28:17,  1.44it/s]
1|2755|Loss: 0.8942692279815674:  11%|█         | 2755/25880 [36:00<4:30:29,  1.42it/s]
1|2756|Loss: 0.944932758808136:  11%|█         | 2755/25880 [36:01<4:30:29,  1.42it/s] 
1|2756|Loss: 0.944932758808136:  11%|█         | 2756/25880 [36:01<4:55:39,  1.30it/s]
1|2757|Loss: 0.7389355301856995:  11%|█         | 2756/25880 [36:02<4:55:39,  1.30it/s]
1|2757|Loss: 0.7389355301856995:  11%|█         | 2757/25880 [36:02<5:14:47,  1.22it/s]
1|2758|Loss: 0.7673318982124329:  11%|█         | 2757/25880 [36:02<5:14:47,  1.22it/s]
1|2758|Loss: 0.7673318982124329:  11%|█         | 2758/25880 [36:03<5:06:02,  1.26it/s]
1|2759|Loss: 0.9043036103248596:  11%|█         | 2758/25880 [36:03<5:06:02,  1.26it/s]
1|2759|Loss: 0.9043036103248596:  11%|█         | 2759/25880 [36:04<5:07:27,  1.25it/s]
1|2760|Loss: 0.8470075130462646:  11%|█         | 2759/25880 [36:04<5:07:27,  1.25it/s]
1|2760|Loss: 0.8470075130462646:  11%|█         | 2760/25880 [36:04<4:54:21,  1.31it/s]
1|2761|Loss: 0.7787911891937256:  11%|█         | 2760/25880 [36:05<4:54:21,  1.31it/s]
1|2761|Loss: 0.7787911891937256:  11%|█         | 2761/25880 [36:05<4:49:31,  1.33it/s]
1|2762|Loss: 0.9234938025474548:  11%|█         | 2761/25880 [36:05<4:49:31,  1.33it/s]
1|2762|Loss: 0.9234938025474548:  11%|█         | 2762/25880 [36:06<4:31:37,  1.42it/s]
1|2763|Loss: 0.844567060470581:  11%|█         | 2762/25880 [36:06<4:31:37,  1.42it/s] 
1|2763|Loss: 0.844567060470581:  11%|█         | 2763/25880 [36:06<4:29:56,  1.43it/s]
1|2764|Loss: 0.9150092005729675:  11%|█         | 2763/25880 [36:07<4:29:56,  1.43it/s]
1|2764|Loss: 0.9150092005729675:  11%|█         | 2764/25880 [36:07<4:33:54,  1.41it/s]
1|2765|Loss: 0.8100500106811523:  11%|█         | 2764/25880 [36:07<4:33:54,  1.41it/s]
1|2765|Loss: 0.8100500106811523:  11%|█         | 2765/25880 [36:08<4:05:12,  1.57it/s]
1|2766|Loss: 0.8348706364631653:  11%|█         | 2765/25880 [36:08<4:05:12,  1.57it/s]
1|2766|Loss: 0.8348706364631653:  11%|█         | 2766/25880 [36:08<4:06:05,  1.57it/s]
1|2767|Loss: 0.9649474620819092:  11%|█         | 2766/25880 [36:09<4:06:05,  1.57it/s]
1|2767|Loss: 0.9649474620819092:  11%|█         | 2767/25880 [36:09<4:07:38,  1.56it/s]
1|2768|Loss: 0.9224429726600647:  11%|█         | 2767/25880 [36:09<4:07:38,  1.56it/s]
1|2768|Loss: 0.9224429726600647:  11%|█         | 2768/25880 [36:10<4:16:42,  1.50it/s]
1|2769|Loss: 0.765154242515564:  11%|█         | 2768/25880 [36:10<4:16:42,  1.50it/s] 
1|2769|Loss: 0.765154242515564:  11%|█         | 2769/25880 [36:10<4:24:40,  1.46it/s]
1|2770|Loss: 0.9889925122261047:  11%|█         | 2769/25880 [36:11<4:24:40,  1.46it/s]
1|2770|Loss: 0.9889925122261047:  11%|█         | 2770/25880 [36:11<4:29:09,  1.43it/s]
1|2771|Loss: 0.8764733076095581:  11%|█         | 2770/25880 [36:11<4:29:09,  1.43it/s]
1|2771|Loss: 0.8764733076095581:  11%|█         | 2771/25880 [36:12<4:23:39,  1.46it/s]
1|2772|Loss: 0.7118796706199646:  11%|█         | 2771/25880 [36:12<4:23:39,  1.46it/s]
1|2772|Loss: 0.7118796706199646:  11%|█         | 2772/25880 [36:12<4:31:59,  1.42it/s]
1|2773|Loss: 1.0055643320083618:  11%|█         | 2772/25880 [36:13<4:31:59,  1.42it/s]
1|2773|Loss: 1.0055643320083618:  11%|█         | 2773/25880 [36:13<4:16:50,  1.50it/s]
1|2774|Loss: 0.8643346428871155:  11%|█         | 2773/25880 [36:13<4:16:50,  1.50it/s]
1|2774|Loss: 0.8643346428871155:  11%|█         | 2774/25880 [36:14<4:19:37,  1.48it/s]
1|2775|Loss: 0.8297089338302612:  11%|█         | 2774/25880 [36:14<4:19:37,  1.48it/s]
1|2775|Loss: 0.8297089338302612:  11%|█         | 2775/25880 [36:14<4:32:21,  1.41it/s]
1|2776|Loss: 0.7672062516212463:  11%|█         | 2775/25880 [36:15<4:32:21,  1.41it/s]
1|2776|Loss: 0.7672062516212463:  11%|█         | 2776/25880 [36:15<4:37:28,  1.39it/s]
1|2777|Loss: 0.7545611262321472:  11%|█         | 2776/25880 [36:16<4:37:28,  1.39it/s]
1|2777|Loss: 0.7545611262321472:  11%|█         | 2777/25880 [36:16<4:30:49,  1.42it/s]
1|2778|Loss: 0.8156021237373352:  11%|█         | 2777/25880 [36:16<4:30:49,  1.42it/s]
1|2778|Loss: 0.8156021237373352:  11%|█         | 2778/25880 [36:17<4:33:44,  1.41it/s]
1|2779|Loss: 0.9317287802696228:  11%|█         | 2778/25880 [36:17<4:33:44,  1.41it/s]
1|2779|Loss: 0.9317287802696228:  11%|█         | 2779/25880 [36:17<4:36:20,  1.39it/s]
1|2780|Loss: 0.7730470299720764:  11%|█         | 2779/25880 [36:18<4:36:20,  1.39it/s]
1|2780|Loss: 0.7730470299720764:  11%|█         | 2780/25880 [36:18<4:23:23,  1.46it/s]
1|2781|Loss: 0.8592444062232971:  11%|█         | 2780/25880 [36:18<4:23:23,  1.46it/s]
1|2781|Loss: 0.8592444062232971:  11%|█         | 2781/25880 [36:18<4:05:16,  1.57it/s]
1|2782|Loss: 0.9018489718437195:  11%|█         | 2781/25880 [36:19<4:05:16,  1.57it/s]
1|2782|Loss: 0.9018489718437195:  11%|█         | 2782/25880 [36:19<4:24:49,  1.45it/s]
1|2783|Loss: 0.8627695441246033:  11%|█         | 2782/25880 [36:20<4:24:49,  1.45it/s]
1|2783|Loss: 0.8627695441246033:  11%|█         | 2783/25880 [36:20<4:43:23,  1.36it/s]
1|2784|Loss: 0.8537511825561523:  11%|█         | 2783/25880 [36:21<4:43:23,  1.36it/s]
1|2784|Loss: 0.8537511825561523:  11%|█         | 2784/25880 [36:21<4:45:37,  1.35it/s]
1|2785|Loss: 0.8940759897232056:  11%|█         | 2784/25880 [36:21<4:45:37,  1.35it/s]
1|2785|Loss: 0.8940759897232056:  11%|█         | 2785/25880 [36:22<4:41:20,  1.37it/s]
1|2786|Loss: 0.8379040360450745:  11%|█         | 2785/25880 [36:22<4:41:20,  1.37it/s]
1|2786|Loss: 0.8379040360450745:  11%|█         | 2786/25880 [36:22<4:39:50,  1.38it/s]
1|2787|Loss: 0.9468305110931396:  11%|█         | 2786/25880 [36:23<4:39:50,  1.38it/s]
1|2787|Loss: 0.9468305110931396:  11%|█         | 2787/25880 [36:23<4:40:36,  1.37it/s]
1|2788|Loss: 0.8217053413391113:  11%|█         | 2787/25880 [36:23<4:40:36,  1.37it/s]
1|2788|Loss: 0.8217053413391113:  11%|█         | 2788/25880 [36:24<4:49:48,  1.33it/s]
1|2789|Loss: 1.1544603109359741:  11%|█         | 2788/25880 [36:24<4:49:48,  1.33it/s]
1|2789|Loss: 1.1544603109359741:  11%|█         | 2789/25880 [36:25<4:41:06,  1.37it/s]
1|2790|Loss: 0.8137375712394714:  11%|█         | 2789/25880 [36:25<4:41:06,  1.37it/s]
1|2790|Loss: 0.8137375712394714:  11%|█         | 2790/25880 [36:25<4:39:40,  1.38it/s]
1|2791|Loss: 0.8219977021217346:  11%|█         | 2790/25880 [36:26<4:39:40,  1.38it/s]
1|2791|Loss: 0.8219977021217346:  11%|█         | 2791/25880 [36:26<4:40:25,  1.37it/s]
1|2792|Loss: 0.9109159708023071:  11%|█         | 2791/25880 [36:26<4:40:25,  1.37it/s]
1|2792|Loss: 0.9109159708023071:  11%|█         | 2792/25880 [36:27<4:51:20,  1.32it/s]
1|2793|Loss: 0.8060905933380127:  11%|█         | 2792/25880 [36:27<4:51:20,  1.32it/s]
1|2793|Loss: 0.8060905933380127:  11%|█         | 2793/25880 [36:28<4:51:24,  1.32it/s]
1|2794|Loss: 0.8678418397903442:  11%|█         | 2793/25880 [36:28<4:51:24,  1.32it/s]
1|2794|Loss: 0.8678418397903442:  11%|█         | 2794/25880 [36:28<4:39:22,  1.38it/s]
1|2795|Loss: 0.7655397653579712:  11%|█         | 2794/25880 [36:29<4:39:22,  1.38it/s]
1|2795|Loss: 0.7655397653579712:  11%|█         | 2795/25880 [36:29<4:49:05,  1.33it/s]
1|2796|Loss: 0.8496482968330383:  11%|█         | 2795/25880 [36:29<4:49:05,  1.33it/s]
1|2796|Loss: 0.8496482968330383:  11%|█         | 2796/25880 [36:30<4:54:24,  1.31it/s]
1|2797|Loss: 0.8778285384178162:  11%|█         | 2796/25880 [36:30<4:54:24,  1.31it/s]
1|2797|Loss: 0.8778285384178162:  11%|█         | 2797/25880 [36:31<4:53:40,  1.31it/s]
1|2798|Loss: 0.841590940952301:  11%|█         | 2797/25880 [36:31<4:53:40,  1.31it/s] 
1|2798|Loss: 0.841590940952301:  11%|█         | 2798/25880 [36:31<4:40:09,  1.37it/s]
1|2799|Loss: 0.8279924392700195:  11%|█         | 2798/25880 [36:32<4:40:09,  1.37it/s]
1|2799|Loss: 0.8279924392700195:  11%|█         | 2799/25880 [36:32<4:29:02,  1.43it/s]
1|2800|Loss: 0.8816848397254944:  11%|█         | 2799/25880 [36:32<4:29:02,  1.43it/s]
1|2800|Loss: 0.8816848397254944:  11%|█         | 2800/25880 [36:33<4:30:23,  1.42it/s]
1|2801|Loss: 0.8019191026687622:  11%|█         | 2800/25880 [36:33<4:30:23,  1.42it/s]
1|2801|Loss: 0.8019191026687622:  11%|█         | 2801/25880 [36:33<4:24:38,  1.45it/s]
1|2802|Loss: 0.840155303478241:  11%|█         | 2801/25880 [36:34<4:24:38,  1.45it/s] 
1|2802|Loss: 0.840155303478241:  11%|█         | 2802/25880 [36:34<4:24:36,  1.45it/s]
1|2803|Loss: 0.8935617208480835:  11%|█         | 2802/25880 [36:34<4:24:36,  1.45it/s]
1|2803|Loss: 0.8935617208480835:  11%|█         | 2803/25880 [36:35<4:46:18,  1.34it/s]
1|2804|Loss: 0.9123645424842834:  11%|█         | 2803/25880 [36:35<4:46:18,  1.34it/s]
1|2804|Loss: 0.9123645424842834:  11%|█         | 2804/25880 [36:36<4:50:24,  1.32it/s]
1|2805|Loss: 0.9888582825660706:  11%|█         | 2804/25880 [36:36<4:50:24,  1.32it/s]
1|2805|Loss: 0.9888582825660706:  11%|█         | 2805/25880 [36:36<4:50:53,  1.32it/s]
1|2806|Loss: 0.9925366044044495:  11%|█         | 2805/25880 [36:37<4:50:53,  1.32it/s]
1|2806|Loss: 0.9925366044044495:  11%|█         | 2806/25880 [36:37<4:46:31,  1.34it/s]
1|2807|Loss: 1.0338635444641113:  11%|█         | 2806/25880 [36:37<4:46:31,  1.34it/s]
1|2807|Loss: 1.0338635444641113:  11%|█         | 2807/25880 [36:38<4:44:07,  1.35it/s]
1|2808|Loss: 0.9427103400230408:  11%|█         | 2807/25880 [36:38<4:44:07,  1.35it/s]
1|2808|Loss: 0.9427103400230408:  11%|█         | 2808/25880 [36:39<4:48:21,  1.33it/s]
1|2809|Loss: 0.9799061417579651:  11%|█         | 2808/25880 [36:39<4:48:21,  1.33it/s]
1|2809|Loss: 0.9799061417579651:  11%|█         | 2809/25880 [36:39<4:47:53,  1.34it/s]
1|2810|Loss: 0.7943622469902039:  11%|█         | 2809/25880 [36:40<4:47:53,  1.34it/s]
1|2810|Loss: 0.7943622469902039:  11%|█         | 2810/25880 [36:40<4:46:00,  1.34it/s]
1|2811|Loss: 0.9078953862190247:  11%|█         | 2810/25880 [36:40<4:46:00,  1.34it/s]
1|2811|Loss: 0.9078953862190247:  11%|█         | 2811/25880 [36:41<4:33:09,  1.41it/s]
1|2812|Loss: 1.1071738004684448:  11%|█         | 2811/25880 [36:41<4:33:09,  1.41it/s]
1|2812|Loss: 1.1071738004684448:  11%|█         | 2812/25880 [36:41<4:48:50,  1.33it/s]
1|2813|Loss: 0.9247472286224365:  11%|█         | 2812/25880 [36:42<4:48:50,  1.33it/s]
1|2813|Loss: 0.9247472286224365:  11%|█         | 2813/25880 [36:42<4:40:08,  1.37it/s]
1|2814|Loss: 0.9808573722839355:  11%|█         | 2813/25880 [36:43<4:40:08,  1.37it/s]
1|2814|Loss: 0.9808573722839355:  11%|█         | 2814/25880 [36:43<4:35:28,  1.40it/s]
1|2815|Loss: 0.9173945784568787:  11%|█         | 2814/25880 [36:43<4:35:28,  1.40it/s]
1|2815|Loss: 0.9173945784568787:  11%|█         | 2815/25880 [36:44<4:42:28,  1.36it/s]
1|2816|Loss: 0.7587372660636902:  11%|█         | 2815/25880 [36:44<4:42:28,  1.36it/s]
1|2816|Loss: 0.7587372660636902:  11%|█         | 2816/25880 [36:44<4:54:53,  1.30it/s]
1|2817|Loss: 0.9208441376686096:  11%|█         | 2816/25880 [36:45<4:54:53,  1.30it/s]
1|2817|Loss: 0.9208441376686096:  11%|█         | 2817/25880 [36:45<5:03:20,  1.27it/s]
1|2818|Loss: 0.8857478499412537:  11%|█         | 2817/25880 [36:46<5:03:20,  1.27it/s]
1|2818|Loss: 0.8857478499412537:  11%|█         | 2818/25880 [36:46<4:59:08,  1.28it/s]
1|2819|Loss: 0.7920972108840942:  11%|█         | 2818/25880 [36:46<4:59:08,  1.28it/s]
1|2819|Loss: 0.7920972108840942:  11%|█         | 2819/25880 [36:47<4:59:11,  1.28it/s]
1|2820|Loss: 0.9592630863189697:  11%|█         | 2819/25880 [36:47<4:59:11,  1.28it/s]
1|2820|Loss: 0.9592630863189697:  11%|█         | 2820/25880 [36:48<4:52:23,  1.31it/s]
1|2821|Loss: 0.7781820297241211:  11%|█         | 2820/25880 [36:48<4:52:23,  1.31it/s]
1|2821|Loss: 0.7781820297241211:  11%|█         | 2821/25880 [36:48<4:39:17,  1.38it/s]
1|2822|Loss: 0.9728502631187439:  11%|█         | 2821/25880 [36:49<4:39:17,  1.38it/s]
1|2822|Loss: 0.9728502631187439:  11%|█         | 2822/25880 [36:49<4:55:11,  1.30it/s]
1|2823|Loss: 0.7841541171073914:  11%|█         | 2822/25880 [36:50<4:55:11,  1.30it/s]
1|2823|Loss: 0.7841541171073914:  11%|█         | 2823/25880 [36:50<5:03:47,  1.26it/s]
1|2824|Loss: 0.909069299697876:  11%|█         | 2823/25880 [36:50<5:03:47,  1.26it/s] 
1|2824|Loss: 0.909069299697876:  11%|█         | 2824/25880 [36:51<5:05:39,  1.26it/s]
1|2825|Loss: 0.8740931749343872:  11%|█         | 2824/25880 [36:51<5:05:39,  1.26it/s]
1|2825|Loss: 0.8740931749343872:  11%|█         | 2825/25880 [36:51<5:00:36,  1.28it/s]
1|2826|Loss: 0.8335537910461426:  11%|█         | 2825/25880 [36:52<5:00:36,  1.28it/s]
1|2826|Loss: 0.8335537910461426:  11%|█         | 2826/25880 [36:52<5:05:52,  1.26it/s]
1|2827|Loss: 0.8398371338844299:  11%|█         | 2826/25880 [36:53<5:05:52,  1.26it/s]
1|2827|Loss: 0.8398371338844299:  11%|█         | 2827/25880 [36:53<5:06:21,  1.25it/s]
1|2828|Loss: 0.86850506067276:  11%|█         | 2827/25880 [36:54<5:06:21,  1.25it/s]  
1|2828|Loss: 0.86850506067276:  11%|█         | 2828/25880 [36:54<5:09:49,  1.24it/s]
1|2829|Loss: 0.9743912816047668:  11%|█         | 2828/25880 [36:54<5:09:49,  1.24it/s]
1|2829|Loss: 0.9743912816047668:  11%|█         | 2829/25880 [36:55<5:10:18,  1.24it/s]
1|2830|Loss: 0.8377438187599182:  11%|█         | 2829/25880 [36:55<5:10:18,  1.24it/s]
1|2830|Loss: 0.8377438187599182:  11%|█         | 2830/25880 [36:55<4:59:50,  1.28it/s]
1|2831|Loss: 0.7840962409973145:  11%|█         | 2830/25880 [36:56<4:59:50,  1.28it/s]
1|2831|Loss: 0.7840962409973145:  11%|█         | 2831/25880 [36:56<4:40:18,  1.37it/s]
1|2832|Loss: 0.8690205216407776:  11%|█         | 2831/25880 [36:56<4:40:18,  1.37it/s]
1|2832|Loss: 0.8690205216407776:  11%|█         | 2832/25880 [36:57<4:41:42,  1.36it/s]
1|2833|Loss: 0.6765246391296387:  11%|█         | 2832/25880 [36:57<4:41:42,  1.36it/s]
1|2833|Loss: 0.6765246391296387:  11%|█         | 2833/25880 [36:57<4:34:30,  1.40it/s]
1|2834|Loss: 0.8992809057235718:  11%|█         | 2833/25880 [36:58<4:34:30,  1.40it/s]
1|2834|Loss: 0.8992809057235718:  11%|█         | 2834/25880 [36:58<4:45:53,  1.34it/s]
1|2835|Loss: 0.8996087312698364:  11%|█         | 2834/25880 [36:59<4:45:53,  1.34it/s]
1|2835|Loss: 0.8996087312698364:  11%|█         | 2835/25880 [36:59<4:44:32,  1.35it/s]
1|2836|Loss: 0.9715707898139954:  11%|█         | 2835/25880 [36:59<4:44:32,  1.35it/s]
1|2836|Loss: 0.9715707898139954:  11%|█         | 2836/25880 [37:00<4:40:11,  1.37it/s]
1|2837|Loss: 0.8701977133750916:  11%|█         | 2836/25880 [37:00<4:40:11,  1.37it/s]
1|2837|Loss: 0.8701977133750916:  11%|█         | 2837/25880 [37:00<4:28:52,  1.43it/s]
1|2838|Loss: 0.9359563589096069:  11%|█         | 2837/25880 [37:01<4:28:52,  1.43it/s]
1|2838|Loss: 0.9359563589096069:  11%|█         | 2838/25880 [37:01<4:31:50,  1.41it/s]
1|2839|Loss: 0.7344201803207397:  11%|█         | 2838/25880 [37:02<4:31:50,  1.41it/s]
1|2839|Loss: 0.7344201803207397:  11%|█         | 2839/25880 [37:02<4:57:43,  1.29it/s]
1|2840|Loss: 0.7355427742004395:  11%|█         | 2839/25880 [37:02<4:57:43,  1.29it/s]
1|2840|Loss: 0.7355427742004395:  11%|█         | 2840/25880 [37:03<4:58:27,  1.29it/s]
1|2841|Loss: 0.9159966111183167:  11%|█         | 2840/25880 [37:03<4:58:27,  1.29it/s]
1|2841|Loss: 0.9159966111183167:  11%|█         | 2841/25880 [37:04<4:53:00,  1.31it/s]
1|2842|Loss: 0.9915420413017273:  11%|█         | 2841/25880 [37:04<4:53:00,  1.31it/s]
1|2842|Loss: 0.9915420413017273:  11%|█         | 2842/25880 [37:04<4:41:17,  1.37it/s]
1|2843|Loss: 0.835085391998291:  11%|█         | 2842/25880 [37:05<4:41:17,  1.37it/s] 
1|2843|Loss: 0.835085391998291:  11%|█         | 2843/25880 [37:05<4:28:54,  1.43it/s]
1|2844|Loss: 0.8278388977050781:  11%|█         | 2843/25880 [37:05<4:28:54,  1.43it/s]
1|2844|Loss: 0.8278388977050781:  11%|█         | 2844/25880 [37:06<4:26:45,  1.44it/s]
1|2845|Loss: 0.8793191313743591:  11%|█         | 2844/25880 [37:06<4:26:45,  1.44it/s]
1|2845|Loss: 0.8793191313743591:  11%|█         | 2845/25880 [37:06<3:56:14,  1.63it/s]
1|2846|Loss: 0.7054132223129272:  11%|█         | 2845/25880 [37:06<3:56:14,  1.63it/s]
1|2846|Loss: 0.7054132223129272:  11%|█         | 2846/25880 [37:07<3:58:43,  1.61it/s]
1|2847|Loss: 0.978257417678833:  11%|█         | 2846/25880 [37:07<3:58:43,  1.61it/s] 
1|2847|Loss: 0.978257417678833:  11%|█         | 2847/25880 [37:07<3:49:13,  1.67it/s]
1|2848|Loss: 0.808383047580719:  11%|█         | 2847/25880 [37:07<3:49:13,  1.67it/s]
1|2848|Loss: 0.808383047580719:  11%|█         | 2848/25880 [37:08<3:58:29,  1.61it/s]
1|2849|Loss: 0.8770323395729065:  11%|█         | 2848/25880 [37:08<3:58:29,  1.61it/s]
1|2849|Loss: 0.8770323395729065:  11%|█         | 2849/25880 [37:09<4:20:17,  1.47it/s]
1|2850|Loss: 0.9002609252929688:  11%|█         | 2849/25880 [37:09<4:20:17,  1.47it/s]
1|2850|Loss: 0.9002609252929688:  11%|█         | 2850/25880 [37:09<3:56:57,  1.62it/s]
1|2851|Loss: 0.9728336334228516:  11%|█         | 2850/25880 [37:09<3:56:57,  1.62it/s]
1|2851|Loss: 0.9728336334228516:  11%|█         | 2851/25880 [37:10<4:16:34,  1.50it/s]
1|2852|Loss: 0.8651566505432129:  11%|█         | 2851/25880 [37:10<4:16:34,  1.50it/s]
1|2852|Loss: 0.8651566505432129:  11%|█         | 2852/25880 [37:11<4:38:58,  1.38it/s]
1|2853|Loss: 0.9724401235580444:  11%|█         | 2852/25880 [37:11<4:38:58,  1.38it/s]
1|2853|Loss: 0.9724401235580444:  11%|█         | 2853/25880 [37:11<4:34:53,  1.40it/s]
1|2854|Loss: 1.0552831888198853:  11%|█         | 2853/25880 [37:12<4:34:53,  1.40it/s]
1|2854|Loss: 1.0552831888198853:  11%|█         | 2854/25880 [37:12<4:34:49,  1.40it/s]
1|2855|Loss: 1.070864200592041:  11%|█         | 2854/25880 [37:13<4:34:49,  1.40it/s] 
1|2855|Loss: 1.070864200592041:  11%|█         | 2855/25880 [37:13<4:33:32,  1.40it/s]
1|2856|Loss: 0.9499112367630005:  11%|█         | 2855/25880 [37:13<4:33:32,  1.40it/s]
1|2856|Loss: 0.9499112367630005:  11%|█         | 2856/25880 [37:14<4:34:58,  1.40it/s]
1|2857|Loss: 0.948596715927124:  11%|█         | 2856/25880 [37:14<4:34:58,  1.40it/s] 
1|2857|Loss: 0.948596715927124:  11%|█         | 2857/25880 [37:14<4:34:00,  1.40it/s]
1|2858|Loss: 0.8777275681495667:  11%|█         | 2857/25880 [37:15<4:34:00,  1.40it/s]
1|2858|Loss: 0.8777275681495667:  11%|█         | 2858/25880 [37:15<4:32:21,  1.41it/s]
1|2859|Loss: 0.9545380473136902:  11%|█         | 2858/25880 [37:15<4:32:21,  1.41it/s]
1|2859|Loss: 0.9545380473136902:  11%|█         | 2859/25880 [37:16<4:46:28,  1.34it/s]
1|2860|Loss: 0.7776657938957214:  11%|█         | 2859/25880 [37:16<4:46:28,  1.34it/s]
1|2860|Loss: 0.7776657938957214:  11%|█         | 2860/25880 [37:17<4:46:39,  1.34it/s]
1|2861|Loss: 0.6952893137931824:  11%|█         | 2860/25880 [37:17<4:46:39,  1.34it/s]
1|2861|Loss: 0.6952893137931824:  11%|█         | 2861/25880 [37:17<4:53:09,  1.31it/s]
1|2862|Loss: 0.8176076412200928:  11%|█         | 2861/25880 [37:18<4:53:09,  1.31it/s]
1|2862|Loss: 0.8176076412200928:  11%|█         | 2862/25880 [37:18<4:52:18,  1.31it/s]
1|2863|Loss: 0.8187578320503235:  11%|█         | 2862/25880 [37:18<4:52:18,  1.31it/s]
1|2863|Loss: 0.8187578320503235:  11%|█         | 2863/25880 [37:19<4:39:17,  1.37it/s]
1|2864|Loss: 0.9189619421958923:  11%|█         | 2863/25880 [37:19<4:39:17,  1.37it/s]
1|2864|Loss: 0.9189619421958923:  11%|█         | 2864/25880 [37:19<4:17:03,  1.49it/s]
1|2865|Loss: 0.7993388175964355:  11%|█         | 2864/25880 [37:20<4:17:03,  1.49it/s]
1|2865|Loss: 0.7993388175964355:  11%|█         | 2865/25880 [37:20<4:15:30,  1.50it/s]
1|2866|Loss: 0.8771771788597107:  11%|█         | 2865/25880 [37:20<4:15:30,  1.50it/s]
1|2866|Loss: 0.8771771788597107:  11%|█         | 2866/25880 [37:21<4:05:47,  1.56it/s]
1|2867|Loss: 1.0410025119781494:  11%|█         | 2866/25880 [37:21<4:05:47,  1.56it/s]
1|2867|Loss: 1.0410025119781494:  11%|█         | 2867/25880 [37:21<4:10:26,  1.53it/s]
1|2868|Loss: 0.880866289138794:  11%|█         | 2867/25880 [37:22<4:10:26,  1.53it/s] 
1|2868|Loss: 0.880866289138794:  11%|█         | 2868/25880 [37:22<4:08:17,  1.54it/s]
1|2869|Loss: 0.7782441973686218:  11%|█         | 2868/25880 [37:22<4:08:17,  1.54it/s]
1|2869|Loss: 0.7782441973686218:  11%|█         | 2869/25880 [37:23<4:20:56,  1.47it/s]
1|2870|Loss: 0.7976247668266296:  11%|█         | 2869/25880 [37:23<4:20:56,  1.47it/s]
1|2870|Loss: 0.7976247668266296:  11%|█         | 2870/25880 [37:24<4:45:32,  1.34it/s]
1|2871|Loss: 0.8502769470214844:  11%|█         | 2870/25880 [37:24<4:45:32,  1.34it/s]
1|2871|Loss: 0.8502769470214844:  11%|█         | 2871/25880 [37:24<4:49:01,  1.33it/s]
1|2872|Loss: 0.8122617602348328:  11%|█         | 2871/25880 [37:25<4:49:01,  1.33it/s]
1|2872|Loss: 0.8122617602348328:  11%|█         | 2872/25880 [37:25<4:38:50,  1.38it/s]
1|2873|Loss: 0.7829896211624146:  11%|█         | 2872/25880 [37:25<4:38:50,  1.38it/s]
1|2873|Loss: 0.7829896211624146:  11%|█         | 2873/25880 [37:26<4:29:02,  1.43it/s]
1|2874|Loss: 0.7655782103538513:  11%|█         | 2873/25880 [37:26<4:29:02,  1.43it/s]
1|2874|Loss: 0.7655782103538513:  11%|█         | 2874/25880 [37:26<4:31:10,  1.41it/s]
1|2875|Loss: 0.8123716115951538:  11%|█         | 2874/25880 [37:27<4:31:10,  1.41it/s]
1|2875|Loss: 0.8123716115951538:  11%|█         | 2875/25880 [37:27<4:44:30,  1.35it/s]
1|2876|Loss: 0.9206600189208984:  11%|█         | 2875/25880 [37:28<4:44:30,  1.35it/s]
1|2876|Loss: 0.9206600189208984:  11%|█         | 2876/25880 [37:28<4:26:38,  1.44it/s]
1|2877|Loss: 0.8104820251464844:  11%|█         | 2876/25880 [37:28<4:26:38,  1.44it/s]
1|2877|Loss: 0.8104820251464844:  11%|█         | 2877/25880 [37:28<4:14:45,  1.50it/s]
1|2878|Loss: 0.8608278036117554:  11%|█         | 2877/25880 [37:29<4:14:45,  1.50it/s]
1|2878|Loss: 0.8608278036117554:  11%|█         | 2878/25880 [37:29<4:32:45,  1.41it/s]
1|2879|Loss: 0.8303533792495728:  11%|█         | 2878/25880 [37:30<4:32:45,  1.41it/s]
1|2879|Loss: 0.8303533792495728:  11%|█         | 2879/25880 [37:30<4:36:25,  1.39it/s]
1|2880|Loss: 0.8447770476341248:  11%|█         | 2879/25880 [37:30<4:36:25,  1.39it/s]
1|2880|Loss: 0.8447770476341248:  11%|█         | 2880/25880 [37:31<4:34:19,  1.40it/s]
1|2881|Loss: 0.9336174726486206:  11%|█         | 2880/25880 [37:31<4:34:19,  1.40it/s]
1|2881|Loss: 0.9336174726486206:  11%|█         | 2881/25880 [37:31<4:34:39,  1.40it/s]
1|2882|Loss: 0.8838829398155212:  11%|█         | 2881/25880 [37:32<4:34:39,  1.40it/s]
1|2882|Loss: 0.8838829398155212:  11%|█         | 2882/25880 [37:32<4:10:16,  1.53it/s]
1|2883|Loss: 0.897522509098053:  11%|█         | 2882/25880 [37:32<4:10:16,  1.53it/s] 
1|2883|Loss: 0.897522509098053:  11%|█         | 2883/25880 [37:32<4:02:00,  1.58it/s]
1|2884|Loss: 1.036877989768982:  11%|█         | 2883/25880 [37:33<4:02:00,  1.58it/s]
1|2884|Loss: 1.036877989768982:  11%|█         | 2884/25880 [37:33<3:56:32,  1.62it/s]
1|2885|Loss: 0.9274507164955139:  11%|█         | 2884/25880 [37:33<3:56:32,  1.62it/s]
1|2885|Loss: 0.9274507164955139:  11%|█         | 2885/25880 [37:34<4:15:05,  1.50it/s]
1|2886|Loss: 0.8753806948661804:  11%|█         | 2885/25880 [37:34<4:15:05,  1.50it/s]
1|2886|Loss: 0.8753806948661804:  11%|█         | 2886/25880 [37:34<4:14:55,  1.50it/s]
1|2887|Loss: 0.759223461151123:  11%|█         | 2886/25880 [37:35<4:14:55,  1.50it/s] 
1|2887|Loss: 0.759223461151123:  11%|█         | 2887/25880 [37:35<4:30:57,  1.41it/s]
1|2888|Loss: 0.8629658222198486:  11%|█         | 2887/25880 [37:36<4:30:57,  1.41it/s]
1|2888|Loss: 0.8629658222198486:  11%|█         | 2888/25880 [37:36<4:49:49,  1.32it/s]
1|2889|Loss: 0.8399034142494202:  11%|█         | 2888/25880 [37:37<4:49:49,  1.32it/s]
1|2889|Loss: 0.8399034142494202:  11%|█         | 2889/25880 [37:37<4:52:08,  1.31it/s]
1|2890|Loss: 0.9499974846839905:  11%|█         | 2889/25880 [37:37<4:52:08,  1.31it/s]
1|2890|Loss: 0.9499974846839905:  11%|█         | 2890/25880 [37:38<4:49:18,  1.32it/s]
1|2891|Loss: 0.9177014827728271:  11%|█         | 2890/25880 [37:38<4:49:18,  1.32it/s]
1|2891|Loss: 0.9177014827728271:  11%|█         | 2891/25880 [37:38<4:34:29,  1.40it/s]
1|2892|Loss: 0.920212984085083:  11%|█         | 2891/25880 [37:39<4:34:29,  1.40it/s] 
1|2892|Loss: 0.920212984085083:  11%|█         | 2892/25880 [37:39<4:39:35,  1.37it/s]
1|2893|Loss: 0.8706436157226562:  11%|█         | 2892/25880 [37:39<4:39:35,  1.37it/s]
1|2893|Loss: 0.8706436157226562:  11%|█         | 2893/25880 [37:40<4:38:48,  1.37it/s]
1|2894|Loss: 0.7202839255332947:  11%|█         | 2893/25880 [37:40<4:38:48,  1.37it/s]
1|2894|Loss: 0.7202839255332947:  11%|█         | 2894/25880 [37:40<4:37:59,  1.38it/s]
1|2895|Loss: 0.8221853971481323:  11%|█         | 2894/25880 [37:41<4:37:59,  1.38it/s]
1|2895|Loss: 0.8221853971481323:  11%|█         | 2895/25880 [37:41<4:29:54,  1.42it/s]
1|2896|Loss: 0.8543374538421631:  11%|█         | 2895/25880 [37:42<4:29:54,  1.42it/s]
1|2896|Loss: 0.8543374538421631:  11%|█         | 2896/25880 [37:42<4:42:27,  1.36it/s]
1|2897|Loss: 0.9518990516662598:  11%|█         | 2896/25880 [37:42<4:42:27,  1.36it/s]
1|2897|Loss: 0.9518990516662598:  11%|█         | 2897/25880 [37:43<4:34:33,  1.40it/s]
1|2898|Loss: 0.8904684782028198:  11%|█         | 2897/25880 [37:43<4:34:33,  1.40it/s]
1|2898|Loss: 0.8904684782028198:  11%|█         | 2898/25880 [37:43<4:24:36,  1.45it/s]
1|2899|Loss: 0.8337001800537109:  11%|█         | 2898/25880 [37:44<4:24:36,  1.45it/s]
1|2899|Loss: 0.8337001800537109:  11%|█         | 2899/25880 [37:44<4:39:30,  1.37it/s]
1|2900|Loss: 0.872462809085846:  11%|█         | 2899/25880 [37:44<4:39:30,  1.37it/s] 
1|2900|Loss: 0.872462809085846:  11%|█         | 2900/25880 [37:45<4:43:49,  1.35it/s]
1|2901|Loss: 0.8761542439460754:  11%|█         | 2900/25880 [37:45<4:43:49,  1.35it/s]
1|2901|Loss: 0.8761542439460754:  11%|█         | 2901/25880 [37:45<4:23:51,  1.45it/s]
1|2902|Loss: 0.8374373912811279:  11%|█         | 2901/25880 [37:46<4:23:51,  1.45it/s]
1|2902|Loss: 0.8374373912811279:  11%|█         | 2902/25880 [37:46<4:12:58,  1.51it/s]
1|2903|Loss: 0.6143316626548767:  11%|█         | 2902/25880 [37:46<4:12:58,  1.51it/s]
1|2903|Loss: 0.6143316626548767:  11%|█         | 2903/25880 [37:47<4:19:09,  1.48it/s]
1|2904|Loss: 0.7260173559188843:  11%|█         | 2903/25880 [37:47<4:19:09,  1.48it/s]
1|2904|Loss: 0.7260173559188843:  11%|█         | 2904/25880 [37:47<4:34:42,  1.39it/s]
1|2905|Loss: 0.95211261510849:  11%|█         | 2904/25880 [37:48<4:34:42,  1.39it/s]  
1|2905|Loss: 0.95211261510849:  11%|█         | 2905/25880 [37:48<4:39:30,  1.37it/s]
1|2906|Loss: 0.8858811259269714:  11%|█         | 2905/25880 [37:49<4:39:30,  1.37it/s]
1|2906|Loss: 0.8858811259269714:  11%|█         | 2906/25880 [37:49<4:40:13,  1.37it/s]
1|2907|Loss: 0.884631872177124:  11%|█         | 2906/25880 [37:49<4:40:13,  1.37it/s] 
1|2907|Loss: 0.884631872177124:  11%|█         | 2907/25880 [37:50<4:47:05,  1.33it/s]
1|2908|Loss: 0.8050212264060974:  11%|█         | 2907/25880 [37:50<4:47:05,  1.33it/s]
1|2908|Loss: 0.8050212264060974:  11%|█         | 2908/25880 [37:51<4:46:00,  1.34it/s]
1|2909|Loss: 0.9919977188110352:  11%|█         | 2908/25880 [37:51<4:46:00,  1.34it/s]
1|2909|Loss: 0.9919977188110352:  11%|█         | 2909/25880 [37:51<4:40:56,  1.36it/s]
1|2910|Loss: 0.9348737001419067:  11%|█         | 2909/25880 [37:52<4:40:56,  1.36it/s]
1|2910|Loss: 0.9348737001419067:  11%|█         | 2910/25880 [37:52<4:28:59,  1.42it/s]
1|2911|Loss: 0.9096913933753967:  11%|█         | 2910/25880 [37:52<4:28:59,  1.42it/s]
1|2911|Loss: 0.9096913933753967:  11%|█         | 2911/25880 [37:53<4:31:00,  1.41it/s]
1|2912|Loss: 0.8001489639282227:  11%|█         | 2911/25880 [37:53<4:31:00,  1.41it/s]
1|2912|Loss: 0.8001489639282227:  11%|█▏        | 2912/25880 [37:53<4:17:59,  1.48it/s]
1|2913|Loss: 0.872580349445343:  11%|█▏        | 2912/25880 [37:53<4:17:59,  1.48it/s] 
1|2913|Loss: 0.872580349445343:  11%|█▏        | 2913/25880 [37:54<4:01:37,  1.58it/s]
1|2914|Loss: 0.9187688231468201:  11%|█▏        | 2913/25880 [37:54<4:01:37,  1.58it/s]
1|2914|Loss: 0.9187688231468201:  11%|█▏        | 2914/25880 [37:54<4:10:05,  1.53it/s]
1|2915|Loss: 0.807667076587677:  11%|█▏        | 2914/25880 [37:55<4:10:05,  1.53it/s] 
1|2915|Loss: 0.807667076587677:  11%|█▏        | 2915/25880 [37:55<3:48:37,  1.67it/s]
1|2916|Loss: 0.8265758156776428:  11%|█▏        | 2915/25880 [37:55<3:48:37,  1.67it/s]
1|2916|Loss: 0.8265758156776428:  11%|█▏        | 2916/25880 [37:56<4:05:16,  1.56it/s]
1|2917|Loss: 0.7502855062484741:  11%|█▏        | 2916/25880 [37:56<4:05:16,  1.56it/s]
1|2917|Loss: 0.7502855062484741:  11%|█▏        | 2917/25880 [37:56<4:17:38,  1.49it/s]
1|2918|Loss: 0.9156610369682312:  11%|█▏        | 2917/25880 [37:57<4:17:38,  1.49it/s]
1|2918|Loss: 0.9156610369682312:  11%|█▏        | 2918/25880 [37:57<4:15:15,  1.50it/s]
1|2919|Loss: 0.840091347694397:  11%|█▏        | 2918/25880 [37:57<4:15:15,  1.50it/s] 
1|2919|Loss: 0.840091347694397:  11%|█▏        | 2919/25880 [37:58<4:18:39,  1.48it/s]
1|2920|Loss: 0.8213721513748169:  11%|█▏        | 2919/25880 [37:58<4:18:39,  1.48it/s]
1|2920|Loss: 0.8213721513748169:  11%|█▏        | 2920/25880 [37:58<4:14:01,  1.51it/s]
1|2921|Loss: 0.8181815147399902:  11%|█▏        | 2920/25880 [37:59<4:14:01,  1.51it/s]
1|2921|Loss: 0.8181815147399902:  11%|█▏        | 2921/25880 [37:59<4:07:57,  1.54it/s]
1|2922|Loss: 0.9160295128822327:  11%|█▏        | 2921/25880 [37:59<4:07:57,  1.54it/s]
1|2922|Loss: 0.9160295128822327:  11%|█▏        | 2922/25880 [38:00<4:16:00,  1.49it/s]
1|2923|Loss: 0.8891890048980713:  11%|█▏        | 2922/25880 [38:00<4:16:00,  1.49it/s]
1|2923|Loss: 0.8891890048980713:  11%|█▏        | 2923/25880 [38:00<4:25:18,  1.44it/s]
1|2924|Loss: 0.7399659156799316:  11%|█▏        | 2923/25880 [38:01<4:25:18,  1.44it/s]
1|2924|Loss: 0.7399659156799316:  11%|█▏        | 2924/25880 [38:01<4:31:00,  1.41it/s]
1|2925|Loss: 1.0810283422470093:  11%|█▏        | 2924/25880 [38:02<4:31:00,  1.41it/s]
1|2925|Loss: 1.0810283422470093:  11%|█▏        | 2925/25880 [38:02<4:24:26,  1.45it/s]
1|2926|Loss: 0.778632402420044:  11%|█▏        | 2925/25880 [38:02<4:24:26,  1.45it/s] 
1|2926|Loss: 0.778632402420044:  11%|█▏        | 2926/25880 [38:02<4:24:09,  1.45it/s]
1|2927|Loss: 0.8802356123924255:  11%|█▏        | 2926/25880 [38:03<4:24:09,  1.45it/s]
1|2927|Loss: 0.8802356123924255:  11%|█▏        | 2927/25880 [38:03<4:29:34,  1.42it/s]
1|2928|Loss: 0.8207479119300842:  11%|█▏        | 2927/25880 [38:04<4:29:34,  1.42it/s]
1|2928|Loss: 0.8207479119300842:  11%|█▏        | 2928/25880 [38:04<4:07:37,  1.54it/s]
1|2929|Loss: 0.8813730478286743:  11%|█▏        | 2928/25880 [38:04<4:07:37,  1.54it/s]
1|2929|Loss: 0.8813730478286743:  11%|█▏        | 2929/25880 [38:04<4:01:49,  1.58it/s]
1|2930|Loss: 0.9637640714645386:  11%|█▏        | 2929/25880 [38:05<4:01:49,  1.58it/s]
1|2930|Loss: 0.9637640714645386:  11%|█▏        | 2930/25880 [38:05<4:16:29,  1.49it/s]
1|2931|Loss: 0.7839037775993347:  11%|█▏        | 2930/25880 [38:06<4:16:29,  1.49it/s]
1|2931|Loss: 0.7839037775993347:  11%|█▏        | 2931/25880 [38:06<4:24:21,  1.45it/s]
1|2932|Loss: 0.8693011403083801:  11%|█▏        | 2931/25880 [38:06<4:24:21,  1.45it/s]
1|2932|Loss: 0.8693011403083801:  11%|█▏        | 2932/25880 [38:07<4:34:10,  1.39it/s]
1|2933|Loss: 0.8483161926269531:  11%|█▏        | 2932/25880 [38:07<4:34:10,  1.39it/s]
1|2933|Loss: 0.8483161926269531:  11%|█▏        | 2933/25880 [38:07<4:34:25,  1.39it/s]
1|2934|Loss: 0.8651040196418762:  11%|█▏        | 2933/25880 [38:08<4:34:25,  1.39it/s]
1|2934|Loss: 0.8651040196418762:  11%|█▏        | 2934/25880 [38:08<4:26:33,  1.43it/s]
1|2935|Loss: 0.8322947025299072:  11%|█▏        | 2934/25880 [38:08<4:26:33,  1.43it/s]
1|2935|Loss: 0.8322947025299072:  11%|█▏        | 2935/25880 [38:09<4:26:13,  1.44it/s]
1|2936|Loss: 0.8773431181907654:  11%|█▏        | 2935/25880 [38:09<4:26:13,  1.44it/s]
1|2936|Loss: 0.8773431181907654:  11%|█▏        | 2936/25880 [38:09<4:18:42,  1.48it/s]
1|2937|Loss: 0.8804121017456055:  11%|█▏        | 2936/25880 [38:10<4:18:42,  1.48it/s]
1|2937|Loss: 0.8804121017456055:  11%|█▏        | 2937/25880 [38:10<4:23:35,  1.45it/s]
1|2938|Loss: 0.865174412727356:  11%|█▏        | 2937/25880 [38:10<4:23:35,  1.45it/s] 
1|2938|Loss: 0.865174412727356:  11%|█▏        | 2938/25880 [38:11<4:40:18,  1.36it/s]
1|2939|Loss: 0.932889997959137:  11%|█▏        | 2938/25880 [38:11<4:40:18,  1.36it/s]
1|2939|Loss: 0.932889997959137:  11%|█▏        | 2939/25880 [38:12<4:55:48,  1.29it/s]
1|2940|Loss: 0.9268458485603333:  11%|█▏        | 2939/25880 [38:12<4:55:48,  1.29it/s]
1|2940|Loss: 0.9268458485603333:  11%|█▏        | 2940/25880 [38:12<4:51:58,  1.31it/s]
1|2941|Loss: 0.8265712857246399:  11%|█▏        | 2940/25880 [38:13<4:51:58,  1.31it/s]
1|2941|Loss: 0.8265712857246399:  11%|█▏        | 2941/25880 [38:13<4:38:40,  1.37it/s]
1|2942|Loss: 0.7993976473808289:  11%|█▏        | 2941/25880 [38:14<4:38:40,  1.37it/s]
1|2942|Loss: 0.7993976473808289:  11%|█▏        | 2942/25880 [38:14<4:38:34,  1.37it/s]
1|2943|Loss: 1.0166569948196411:  11%|█▏        | 2942/25880 [38:14<4:38:34,  1.37it/s]
1|2943|Loss: 1.0166569948196411:  11%|█▏        | 2943/25880 [38:15<4:53:50,  1.30it/s]
1|2944|Loss: 0.7273536920547485:  11%|█▏        | 2943/25880 [38:15<4:53:50,  1.30it/s]
1|2944|Loss: 0.7273536920547485:  11%|█▏        | 2944/25880 [38:16<5:04:43,  1.25it/s]
1|2945|Loss: 0.920645534992218:  11%|█▏        | 2944/25880 [38:16<5:04:43,  1.25it/s] 
1|2945|Loss: 0.920645534992218:  11%|█▏        | 2945/25880 [38:16<5:05:06,  1.25it/s]
1|2946|Loss: 0.7921804189682007:  11%|█▏        | 2945/25880 [38:17<5:05:06,  1.25it/s]
1|2946|Loss: 0.7921804189682007:  11%|█▏        | 2946/25880 [38:17<4:56:44,  1.29it/s]
1|2947|Loss: 0.9275409579277039:  11%|█▏        | 2946/25880 [38:17<4:56:44,  1.29it/s]
1|2947|Loss: 0.9275409579277039:  11%|█▏        | 2947/25880 [38:18<4:48:08,  1.33it/s]
1|2948|Loss: 0.8199717998504639:  11%|█▏        | 2947/25880 [38:18<4:48:08,  1.33it/s]
1|2948|Loss: 0.8199717998504639:  11%|█▏        | 2948/25880 [38:18<4:35:57,  1.39it/s]
1|2949|Loss: 0.8479167222976685:  11%|█▏        | 2948/25880 [38:19<4:35:57,  1.39it/s]
1|2949|Loss: 0.8479167222976685:  11%|█▏        | 2949/25880 [38:19<4:02:28,  1.58it/s]
1|2950|Loss: 0.8910118341445923:  11%|█▏        | 2949/25880 [38:19<4:02:28,  1.58it/s]
1|2950|Loss: 0.8910118341445923:  11%|█▏        | 2950/25880 [38:19<3:54:23,  1.63it/s]
1|2951|Loss: 1.0574110746383667:  11%|█▏        | 2950/25880 [38:20<3:54:23,  1.63it/s]
1|2951|Loss: 1.0574110746383667:  11%|█▏        | 2951/25880 [38:20<4:15:57,  1.49it/s]
1|2952|Loss: 0.8456122279167175:  11%|█▏        | 2951/25880 [38:21<4:15:57,  1.49it/s]
1|2952|Loss: 0.8456122279167175:  11%|█▏        | 2952/25880 [38:21<4:22:59,  1.45it/s]
1|2953|Loss: 0.6720930337905884:  11%|█▏        | 2952/25880 [38:21<4:22:59,  1.45it/s]
1|2953|Loss: 0.6720930337905884:  11%|█▏        | 2953/25880 [38:22<4:24:24,  1.45it/s]
1|2954|Loss: 0.7858434319496155:  11%|█▏        | 2953/25880 [38:22<4:24:24,  1.45it/s]
1|2954|Loss: 0.7858434319496155:  11%|█▏        | 2954/25880 [38:23<4:51:46,  1.31it/s]
1|2955|Loss: 0.9516224265098572:  11%|█▏        | 2954/25880 [38:23<4:51:46,  1.31it/s]
1|2955|Loss: 0.9516224265098572:  11%|█▏        | 2955/25880 [38:23<4:38:42,  1.37it/s]
1|2956|Loss: 0.7569831609725952:  11%|█▏        | 2955/25880 [38:24<4:38:42,  1.37it/s]
1|2956|Loss: 0.7569831609725952:  11%|█▏        | 2956/25880 [38:24<4:52:25,  1.31it/s]
1|2957|Loss: 0.952684760093689:  11%|█▏        | 2956/25880 [38:25<4:52:25,  1.31it/s] 
1|2957|Loss: 0.952684760093689:  11%|█▏        | 2957/25880 [38:25<5:05:02,  1.25it/s]
1|2958|Loss: 0.6759620904922485:  11%|█▏        | 2957/25880 [38:25<5:05:02,  1.25it/s]
1|2958|Loss: 0.6759620904922485:  11%|█▏        | 2958/25880 [38:26<4:44:42,  1.34it/s]
1|2959|Loss: 0.9954266548156738:  11%|█▏        | 2958/25880 [38:26<4:44:42,  1.34it/s]
1|2959|Loss: 0.9954266548156738:  11%|█▏        | 2959/25880 [38:26<4:48:03,  1.33it/s]
1|2960|Loss: 0.9984729290008545:  11%|█▏        | 2959/25880 [38:27<4:48:03,  1.33it/s]
1|2960|Loss: 0.9984729290008545:  11%|█▏        | 2960/25880 [38:27<5:00:08,  1.27it/s]
1|2961|Loss: 0.8515378832817078:  11%|█▏        | 2960/25880 [38:28<5:00:08,  1.27it/s]
1|2961|Loss: 0.8515378832817078:  11%|█▏        | 2961/25880 [38:28<4:54:54,  1.30it/s]
1|2962|Loss: 0.854457437992096:  11%|█▏        | 2961/25880 [38:28<4:54:54,  1.30it/s] 
1|2962|Loss: 0.854457437992096:  11%|█▏        | 2962/25880 [38:29<4:38:24,  1.37it/s]
1|2963|Loss: 0.8100407719612122:  11%|█▏        | 2962/25880 [38:29<4:38:24,  1.37it/s]
1|2963|Loss: 0.8100407719612122:  11%|█▏        | 2963/25880 [38:29<4:35:59,  1.38it/s]
1|2964|Loss: 0.8326709866523743:  11%|█▏        | 2963/25880 [38:30<4:35:59,  1.38it/s]
1|2964|Loss: 0.8326709866523743:  11%|█▏        | 2964/25880 [38:30<4:48:04,  1.33it/s]
1|2965|Loss: 0.8712406754493713:  11%|█▏        | 2964/25880 [38:31<4:48:04,  1.33it/s]
1|2965|Loss: 0.8712406754493713:  11%|█▏        | 2965/25880 [38:31<4:38:11,  1.37it/s]
1|2966|Loss: 1.0111407041549683:  11%|█▏        | 2965/25880 [38:31<4:38:11,  1.37it/s]
1|2966|Loss: 1.0111407041549683:  11%|█▏        | 2966/25880 [38:32<4:37:18,  1.38it/s]
1|2967|Loss: 0.8785739541053772:  11%|█▏        | 2966/25880 [38:32<4:37:18,  1.38it/s]
1|2967|Loss: 0.8785739541053772:  11%|█▏        | 2967/25880 [38:32<4:47:39,  1.33it/s]
1|2968|Loss: 0.8226630687713623:  11%|█▏        | 2967/25880 [38:33<4:47:39,  1.33it/s]
1|2968|Loss: 0.8226630687713623:  11%|█▏        | 2968/25880 [38:33<4:36:55,  1.38it/s]
1|2969|Loss: 0.8863293528556824:  11%|█▏        | 2968/25880 [38:33<4:36:55,  1.38it/s]
1|2969|Loss: 0.8863293528556824:  11%|█▏        | 2969/25880 [38:34<4:36:57,  1.38it/s]
1|2970|Loss: 0.9126296639442444:  11%|█▏        | 2969/25880 [38:34<4:36:57,  1.38it/s]
1|2970|Loss: 0.9126296639442444:  11%|█▏        | 2970/25880 [38:34<4:30:33,  1.41it/s]
1|2971|Loss: 0.9094820022583008:  11%|█▏        | 2970/25880 [38:35<4:30:33,  1.41it/s]
1|2971|Loss: 0.9094820022583008:  11%|█▏        | 2971/25880 [38:35<4:22:56,  1.45it/s]
1|2972|Loss: 0.8734307289123535:  11%|█▏        | 2971/25880 [38:35<4:22:56,  1.45it/s]
1|2972|Loss: 0.8734307289123535:  11%|█▏        | 2972/25880 [38:36<4:44:02,  1.34it/s]
1|2973|Loss: 1.1203277111053467:  11%|█▏        | 2972/25880 [38:36<4:44:02,  1.34it/s]
1|2973|Loss: 1.1203277111053467:  11%|█▏        | 2973/25880 [38:37<4:46:22,  1.33it/s]
1|2974|Loss: 0.94536954164505:  11%|█▏        | 2973/25880 [38:37<4:46:22,  1.33it/s]  
1|2974|Loss: 0.94536954164505:  11%|█▏        | 2974/25880 [38:38<4:55:30,  1.29it/s]
1|2975|Loss: 0.8371286392211914:  11%|█▏        | 2974/25880 [38:38<4:55:30,  1.29it/s]
1|2975|Loss: 0.8371286392211914:  11%|█▏        | 2975/25880 [38:38<4:51:03,  1.31it/s]
1|2976|Loss: 0.7913376092910767:  11%|█▏        | 2975/25880 [38:39<4:51:03,  1.31it/s]
1|2976|Loss: 0.7913376092910767:  11%|█▏        | 2976/25880 [38:39<5:10:26,  1.23it/s]
1|2977|Loss: 0.9522089958190918:  11%|█▏        | 2976/25880 [38:40<5:10:26,  1.23it/s]
1|2977|Loss: 0.9522089958190918:  12%|█▏        | 2977/25880 [38:40<5:07:56,  1.24it/s]
1|2978|Loss: 0.9120436906814575:  12%|█▏        | 2977/25880 [38:40<5:07:56,  1.24it/s]
1|2978|Loss: 0.9120436906814575:  12%|█▏        | 2978/25880 [38:41<4:59:46,  1.27it/s]
1|2979|Loss: 0.8604394197463989:  12%|█▏        | 2978/25880 [38:41<4:59:46,  1.27it/s]
1|2979|Loss: 0.8604394197463989:  12%|█▏        | 2979/25880 [38:41<4:54:08,  1.30it/s]
1|2980|Loss: 0.8089801073074341:  12%|█▏        | 2979/25880 [38:42<4:54:08,  1.30it/s]
1|2980|Loss: 0.8089801073074341:  12%|█▏        | 2980/25880 [38:42<4:49:47,  1.32it/s]
1|2981|Loss: 0.7953079342842102:  12%|█▏        | 2980/25880 [38:43<4:49:47,  1.32it/s]
1|2981|Loss: 0.7953079342842102:  12%|█▏        | 2981/25880 [38:43<4:21:35,  1.46it/s]
1|2982|Loss: 0.7340936660766602:  12%|█▏        | 2981/25880 [38:43<4:21:35,  1.46it/s]
1|2982|Loss: 0.7340936660766602:  12%|█▏        | 2982/25880 [38:43<4:11:43,  1.52it/s]
1|2983|Loss: 0.7025694251060486:  12%|█▏        | 2982/25880 [38:44<4:11:43,  1.52it/s]
1|2983|Loss: 0.7025694251060486:  12%|█▏        | 2983/25880 [38:44<4:15:15,  1.50it/s]
1|2984|Loss: 0.9544552564620972:  12%|█▏        | 2983/25880 [38:44<4:15:15,  1.50it/s]
1|2984|Loss: 0.9544552564620972:  12%|█▏        | 2984/25880 [38:45<4:21:28,  1.46it/s]
1|2985|Loss: 0.8141277432441711:  12%|█▏        | 2984/25880 [38:45<4:21:28,  1.46it/s]
1|2985|Loss: 0.8141277432441711:  12%|█▏        | 2985/25880 [38:46<4:35:24,  1.39it/s]
1|2986|Loss: 0.8519057631492615:  12%|█▏        | 2985/25880 [38:46<4:35:24,  1.39it/s]
1|2986|Loss: 0.8519057631492615:  12%|█▏        | 2986/25880 [38:46<4:30:41,  1.41it/s]
1|2987|Loss: 0.8982248902320862:  12%|█▏        | 2986/25880 [38:47<4:30:41,  1.41it/s]
1|2987|Loss: 0.8982248902320862:  12%|█▏        | 2987/25880 [38:47<4:32:36,  1.40it/s]
1|2988|Loss: 0.9613516330718994:  12%|█▏        | 2987/25880 [38:47<4:32:36,  1.40it/s]
1|2988|Loss: 0.9613516330718994:  12%|█▏        | 2988/25880 [38:48<4:37:00,  1.38it/s]
1|2989|Loss: 0.9244502782821655:  12%|█▏        | 2988/25880 [38:48<4:37:00,  1.38it/s]
1|2989|Loss: 0.9244502782821655:  12%|█▏        | 2989/25880 [38:48<4:44:20,  1.34it/s]
1|2990|Loss: 0.8996816873550415:  12%|█▏        | 2989/25880 [38:49<4:44:20,  1.34it/s]
1|2990|Loss: 0.8996816873550415:  12%|█▏        | 2990/25880 [38:49<4:34:14,  1.39it/s]
1|2991|Loss: 0.9662348031997681:  12%|█▏        | 2990/25880 [38:49<4:34:14,  1.39it/s]
1|2991|Loss: 0.9662348031997681:  12%|█▏        | 2991/25880 [38:50<4:21:11,  1.46it/s]
1|2992|Loss: 0.9373964667320251:  12%|█▏        | 2991/25880 [38:50<4:21:11,  1.46it/s]
1|2992|Loss: 0.9373964667320251:  12%|█▏        | 2992/25880 [38:50<4:04:52,  1.56it/s]
1|2993|Loss: 0.962786078453064:  12%|█▏        | 2992/25880 [38:51<4:04:52,  1.56it/s] 
1|2993|Loss: 0.962786078453064:  12%|█▏        | 2993/25880 [38:51<4:02:02,  1.58it/s]
1|2994|Loss: 0.9263103604316711:  12%|█▏        | 2993/25880 [38:51<4:02:02,  1.58it/s]
1|2994|Loss: 0.9263103604316711:  12%|█▏        | 2994/25880 [38:52<4:03:25,  1.57it/s]
1|2995|Loss: 0.7360949516296387:  12%|█▏        | 2994/25880 [38:52<4:03:25,  1.57it/s]
1|2995|Loss: 0.7360949516296387:  12%|█▏        | 2995/25880 [38:52<4:12:01,  1.51it/s]
1|2996|Loss: 1.021862268447876:  12%|█▏        | 2995/25880 [38:53<4:12:01,  1.51it/s] 
1|2996|Loss: 1.021862268447876:  12%|█▏        | 2996/25880 [38:53<4:31:00,  1.41it/s]
1|2997|Loss: 0.9438427090644836:  12%|█▏        | 2996/25880 [38:54<4:31:00,  1.41it/s]
1|2997|Loss: 0.9438427090644836:  12%|█▏        | 2997/25880 [38:54<4:46:32,  1.33it/s]
1|2998|Loss: 0.8398451805114746:  12%|█▏        | 2997/25880 [38:54<4:46:32,  1.33it/s]
1|2998|Loss: 0.8398451805114746:  12%|█▏        | 2998/25880 [38:55<4:46:02,  1.33it/s]
1|2999|Loss: 1.1097217798233032:  12%|█▏        | 2998/25880 [38:55<4:46:02,  1.33it/s]
1|2999|Loss: 1.1097217798233032:  12%|█▏        | 2999/25880 [38:55<4:55:21,  1.29it/s]
1|3000|Loss: 0.8006400465965271:  12%|█▏        | 2999/25880 [38:56<4:55:21,  1.29it/s]
1|3000|Loss: 0.8006400465965271:  12%|█▏        | 3000/25880 [38:56<5:03:26,  1.26it/s]
1|3001|Loss: 0.8770071864128113:  12%|█▏        | 3000/25880 [38:57<5:03:26,  1.26it/s]
1|3001|Loss: 0.8770071864128113:  12%|█▏        | 3001/25880 [38:57<5:21:20,  1.19it/s]
1|3002|Loss: 0.9601955413818359:  12%|█▏        | 3001/25880 [38:58<5:21:20,  1.19it/s]
1|3002|Loss: 0.9601955413818359:  12%|█▏        | 3002/25880 [38:58<5:32:50,  1.15it/s]
1|3003|Loss: 0.9046564698219299:  12%|█▏        | 3002/25880 [38:59<5:32:50,  1.15it/s]
1|3003|Loss: 0.9046564698219299:  12%|█▏        | 3003/25880 [38:59<5:27:31,  1.16it/s]
1|3004|Loss: 0.7924061417579651:  12%|█▏        | 3003/25880 [38:59<5:27:31,  1.16it/s]
1|3004|Loss: 0.7924061417579651:  12%|█▏        | 3004/25880 [39:00<5:20:53,  1.19it/s]
1|3005|Loss: 0.9025030732154846:  12%|█▏        | 3004/25880 [39:00<5:20:53,  1.19it/s]
1|3005|Loss: 0.9025030732154846:  12%|█▏        | 3005/25880 [39:00<4:57:10,  1.28it/s]
1|3006|Loss: 0.8261176347732544:  12%|█▏        | 3005/25880 [39:01<4:57:10,  1.28it/s]
1|3006|Loss: 0.8261176347732544:  12%|█▏        | 3006/25880 [39:01<4:37:06,  1.38it/s]
1|3007|Loss: 0.8270522356033325:  12%|█▏        | 3006/25880 [39:01<4:37:06,  1.38it/s]
1|3007|Loss: 0.8270522356033325:  12%|█▏        | 3007/25880 [39:02<4:34:41,  1.39it/s]
1|3008|Loss: 0.9157220721244812:  12%|█▏        | 3007/25880 [39:02<4:34:41,  1.39it/s]
1|3008|Loss: 0.9157220721244812:  12%|█▏        | 3008/25880 [39:03<4:52:54,  1.30it/s]
1|3009|Loss: 1.119989275932312:  12%|█▏        | 3008/25880 [39:03<4:52:54,  1.30it/s] 
1|3009|Loss: 1.119989275932312:  12%|█▏        | 3009/25880 [39:03<4:44:39,  1.34it/s]
1|3010|Loss: 0.9011226296424866:  12%|█▏        | 3009/25880 [39:04<4:44:39,  1.34it/s]
1|3010|Loss: 0.9011226296424866:  12%|█▏        | 3010/25880 [39:04<4:32:42,  1.40it/s]
1|3011|Loss: 0.9688878655433655:  12%|█▏        | 3010/25880 [39:04<4:32:42,  1.40it/s]
1|3011|Loss: 0.9688878655433655:  12%|█▏        | 3011/25880 [39:05<4:38:20,  1.37it/s]
1|3012|Loss: 0.8946241140365601:  12%|█▏        | 3011/25880 [39:05<4:38:20,  1.37it/s]
1|3012|Loss: 0.8946241140365601:  12%|█▏        | 3012/25880 [39:06<4:45:58,  1.33it/s]
1|3013|Loss: 0.861369252204895:  12%|█▏        | 3012/25880 [39:06<4:45:58,  1.33it/s] 
1|3013|Loss: 0.861369252204895:  12%|█▏        | 3013/25880 [39:06<4:54:57,  1.29it/s]
1|3014|Loss: 0.9413425922393799:  12%|█▏        | 3013/25880 [39:07<4:54:57,  1.29it/s]
1|3014|Loss: 0.9413425922393799:  12%|█▏        | 3014/25880 [39:07<4:43:41,  1.34it/s]
1|3015|Loss: 0.7921697497367859:  12%|█▏        | 3014/25880 [39:08<4:43:41,  1.34it/s]
1|3015|Loss: 0.7921697497367859:  12%|█▏        | 3015/25880 [39:08<4:48:53,  1.32it/s]
1|3016|Loss: 0.9077402353286743:  12%|█▏        | 3015/25880 [39:08<4:48:53,  1.32it/s]
1|3016|Loss: 0.9077402353286743:  12%|█▏        | 3016/25880 [39:09<4:48:46,  1.32it/s]
1|3017|Loss: 0.9096280336380005:  12%|█▏        | 3016/25880 [39:09<4:48:46,  1.32it/s]
1|3017|Loss: 0.9096280336380005:  12%|█▏        | 3017/25880 [39:09<4:48:12,  1.32it/s]
1|3018|Loss: 0.8240596055984497:  12%|█▏        | 3017/25880 [39:10<4:48:12,  1.32it/s]
1|3018|Loss: 0.8240596055984497:  12%|█▏        | 3018/25880 [39:10<4:53:27,  1.30it/s]
1|3019|Loss: 0.8174610733985901:  12%|█▏        | 3018/25880 [39:11<4:53:27,  1.30it/s]
1|3019|Loss: 0.8174610733985901:  12%|█▏        | 3019/25880 [39:11<4:51:15,  1.31it/s]
1|3020|Loss: 0.9169201850891113:  12%|█▏        | 3019/25880 [39:11<4:51:15,  1.31it/s]
1|3020|Loss: 0.9169201850891113:  12%|█▏        | 3020/25880 [39:12<4:48:15,  1.32it/s]
1|3021|Loss: 0.8461387157440186:  12%|█▏        | 3020/25880 [39:12<4:48:15,  1.32it/s]
1|3021|Loss: 0.8461387157440186:  12%|█▏        | 3021/25880 [39:12<4:37:15,  1.37it/s]
1|3022|Loss: 0.8793622851371765:  12%|█▏        | 3021/25880 [39:13<4:37:15,  1.37it/s]
1|3022|Loss: 0.8793622851371765:  12%|█▏        | 3022/25880 [39:13<4:27:10,  1.43it/s]
1|3023|Loss: 0.8423520922660828:  12%|█▏        | 3022/25880 [39:13<4:27:10,  1.43it/s]
1|3023|Loss: 0.8423520922660828:  12%|█▏        | 3023/25880 [39:14<4:37:43,  1.37it/s]
1|3024|Loss: 0.880262017250061:  12%|█▏        | 3023/25880 [39:14<4:37:43,  1.37it/s] 
1|3024|Loss: 0.880262017250061:  12%|█▏        | 3024/25880 [39:14<4:31:31,  1.40it/s]
1|3025|Loss: 0.6829825639724731:  12%|█▏        | 3024/25880 [39:15<4:31:31,  1.40it/s]
1|3025|Loss: 0.6829825639724731:  12%|█▏        | 3025/25880 [39:15<4:40:55,  1.36it/s]
1|3026|Loss: 0.9786985516548157:  12%|█▏        | 3025/25880 [39:16<4:40:55,  1.36it/s]
1|3026|Loss: 0.9786985516548157:  12%|█▏        | 3026/25880 [39:16<4:28:56,  1.42it/s]
1|3027|Loss: 0.8251430988311768:  12%|█▏        | 3026/25880 [39:16<4:28:56,  1.42it/s]
1|3027|Loss: 0.8251430988311768:  12%|█▏        | 3027/25880 [39:17<4:41:05,  1.36it/s]
1|3028|Loss: 0.9210370182991028:  12%|█▏        | 3027/25880 [39:17<4:41:05,  1.36it/s]
1|3028|Loss: 0.9210370182991028:  12%|█▏        | 3028/25880 [39:18<4:50:45,  1.31it/s]
1|3029|Loss: 0.8701356649398804:  12%|█▏        | 3028/25880 [39:18<4:50:45,  1.31it/s]
1|3029|Loss: 0.8701356649398804:  12%|█▏        | 3029/25880 [39:18<4:38:53,  1.37it/s]
1|3030|Loss: 0.8836236000061035:  12%|█▏        | 3029/25880 [39:18<4:38:53,  1.37it/s]
1|3030|Loss: 0.8836236000061035:  12%|█▏        | 3030/25880 [39:19<4:16:15,  1.49it/s]
1|3031|Loss: 0.8103534579277039:  12%|█▏        | 3030/25880 [39:19<4:16:15,  1.49it/s]
1|3031|Loss: 0.8103534579277039:  12%|█▏        | 3031/25880 [39:19<4:14:39,  1.50it/s]
1|3032|Loss: 0.790919840335846:  12%|█▏        | 3031/25880 [39:20<4:14:39,  1.50it/s] 
1|3032|Loss: 0.790919840335846:  12%|█▏        | 3032/25880 [39:20<3:59:56,  1.59it/s]
1|3033|Loss: 0.7997795343399048:  12%|█▏        | 3032/25880 [39:20<3:59:56,  1.59it/s]
1|3033|Loss: 0.7997795343399048:  12%|█▏        | 3033/25880 [39:20<3:40:51,  1.72it/s]
1|3034|Loss: 0.8452742099761963:  12%|█▏        | 3033/25880 [39:21<3:40:51,  1.72it/s]
1|3034|Loss: 0.8452742099761963:  12%|█▏        | 3034/25880 [39:21<3:51:16,  1.65it/s]
1|3035|Loss: 0.9444755911827087:  12%|█▏        | 3034/25880 [39:21<3:51:16,  1.65it/s]
1|3035|Loss: 0.9444755911827087:  12%|█▏        | 3035/25880 [39:22<3:58:07,  1.60it/s]
1|3036|Loss: 0.9466623663902283:  12%|█▏        | 3035/25880 [39:22<3:58:07,  1.60it/s]
1|3036|Loss: 0.9466623663902283:  12%|█▏        | 3036/25880 [39:22<3:47:43,  1.67it/s]
1|3037|Loss: 0.8681383728981018:  12%|█▏        | 3036/25880 [39:23<3:47:43,  1.67it/s]
1|3037|Loss: 0.8681383728981018:  12%|█▏        | 3037/25880 [39:23<3:54:41,  1.62it/s]
1|3038|Loss: 0.7776095867156982:  12%|█▏        | 3037/25880 [39:23<3:54:41,  1.62it/s]
1|3038|Loss: 0.7776095867156982:  12%|█▏        | 3038/25880 [39:24<3:58:47,  1.59it/s]
1|3039|Loss: 0.8104381561279297:  12%|█▏        | 3038/25880 [39:24<3:58:47,  1.59it/s]
1|3039|Loss: 0.8104381561279297:  12%|█▏        | 3039/25880 [39:24<4:06:14,  1.55it/s]
1|3040|Loss: 0.7916859984397888:  12%|█▏        | 3039/25880 [39:25<4:06:14,  1.55it/s]
1|3040|Loss: 0.7916859984397888:  12%|█▏        | 3040/25880 [39:25<4:21:46,  1.45it/s]
1|3041|Loss: 0.8728014230728149:  12%|█▏        | 3040/25880 [39:25<4:21:46,  1.45it/s]
1|3041|Loss: 0.8728014230728149:  12%|█▏        | 3041/25880 [39:26<4:26:30,  1.43it/s]
1|3042|Loss: 0.722479522228241:  12%|█▏        | 3041/25880 [39:26<4:26:30,  1.43it/s] 
1|3042|Loss: 0.722479522228241:  12%|█▏        | 3042/25880 [39:26<3:56:13,  1.61it/s]
1|3043|Loss: 0.8491644859313965:  12%|█▏        | 3042/25880 [39:27<3:56:13,  1.61it/s]
1|3043|Loss: 0.8491644859313965:  12%|█▏        | 3043/25880 [39:27<4:12:09,  1.51it/s]
1|3044|Loss: 0.7972732186317444:  12%|█▏        | 3043/25880 [39:27<4:12:09,  1.51it/s]
1|3044|Loss: 0.7972732186317444:  12%|█▏        | 3044/25880 [39:28<4:15:14,  1.49it/s]
1|3045|Loss: 0.8208372592926025:  12%|█▏        | 3044/25880 [39:28<4:15:14,  1.49it/s]
1|3045|Loss: 0.8208372592926025:  12%|█▏        | 3045/25880 [39:28<4:06:59,  1.54it/s]
1|3046|Loss: 0.8953875303268433:  12%|█▏        | 3045/25880 [39:29<4:06:59,  1.54it/s]
1|3046|Loss: 0.8953875303268433:  12%|█▏        | 3046/25880 [39:29<3:54:58,  1.62it/s]
1|3047|Loss: 0.9113184809684753:  12%|█▏        | 3046/25880 [39:29<3:54:58,  1.62it/s]
1|3047|Loss: 0.9113184809684753:  12%|█▏        | 3047/25880 [39:30<4:14:02,  1.50it/s]
1|3048|Loss: 0.8900847434997559:  12%|█▏        | 3047/25880 [39:30<4:14:02,  1.50it/s]
1|3048|Loss: 0.8900847434997559:  12%|█▏        | 3048/25880 [39:31<4:51:26,  1.31it/s]
1|3049|Loss: 0.8529499173164368:  12%|█▏        | 3048/25880 [39:31<4:51:26,  1.31it/s]
1|3049|Loss: 0.8529499173164368:  12%|█▏        | 3049/25880 [39:31<5:06:15,  1.24it/s]
1|3050|Loss: 0.9722897410392761:  12%|█▏        | 3049/25880 [39:32<5:06:15,  1.24it/s]
1|3050|Loss: 0.9722897410392761:  12%|█▏        | 3050/25880 [39:32<4:34:36,  1.39it/s]
1|3051|Loss: 0.8702815771102905:  12%|█▏        | 3050/25880 [39:32<4:34:36,  1.39it/s]
1|3051|Loss: 0.8702815771102905:  12%|█▏        | 3051/25880 [39:33<4:15:38,  1.49it/s]
1|3052|Loss: 0.9116514921188354:  12%|█▏        | 3051/25880 [39:33<4:15:38,  1.49it/s]
1|3052|Loss: 0.9116514921188354:  12%|█▏        | 3052/25880 [39:33<4:05:36,  1.55it/s]
1|3053|Loss: 0.9820337891578674:  12%|█▏        | 3052/25880 [39:34<4:05:36,  1.55it/s]
1|3053|Loss: 0.9820337891578674:  12%|█▏        | 3053/25880 [39:34<4:28:05,  1.42it/s]
1|3054|Loss: 0.866511344909668:  12%|█▏        | 3053/25880 [39:34<4:28:05,  1.42it/s] 
1|3054|Loss: 0.866511344909668:  12%|█▏        | 3054/25880 [39:35<4:40:07,  1.36it/s]
1|3055|Loss: 0.8811230063438416:  12%|█▏        | 3054/25880 [39:35<4:40:07,  1.36it/s]
1|3055|Loss: 0.8811230063438416:  12%|█▏        | 3055/25880 [39:35<4:33:07,  1.39it/s]
1|3056|Loss: 0.8972471356391907:  12%|█▏        | 3055/25880 [39:36<4:33:07,  1.39it/s]
1|3056|Loss: 0.8972471356391907:  12%|█▏        | 3056/25880 [39:36<4:24:03,  1.44it/s]
1|3057|Loss: 0.8781535029411316:  12%|█▏        | 3056/25880 [39:36<4:24:03,  1.44it/s]
1|3057|Loss: 0.8781535029411316:  12%|█▏        | 3057/25880 [39:37<4:31:21,  1.40it/s]
1|3058|Loss: 0.9167625904083252:  12%|█▏        | 3057/25880 [39:37<4:31:21,  1.40it/s]
1|3058|Loss: 0.9167625904083252:  12%|█▏        | 3058/25880 [39:38<4:25:10,  1.43it/s]
1|3059|Loss: 0.8674201369285583:  12%|█▏        | 3058/25880 [39:38<4:25:10,  1.43it/s]
1|3059|Loss: 0.8674201369285583:  12%|█▏        | 3059/25880 [39:38<4:27:16,  1.42it/s]
1|3060|Loss: 0.798339307308197:  12%|█▏        | 3059/25880 [39:39<4:27:16,  1.42it/s] 
1|3060|Loss: 0.798339307308197:  12%|█▏        | 3060/25880 [39:39<4:52:44,  1.30it/s]
1|3061|Loss: 0.7815204858779907:  12%|█▏        | 3060/25880 [39:40<4:52:44,  1.30it/s]
1|3061|Loss: 0.7815204858779907:  12%|█▏        | 3061/25880 [39:40<4:54:35,  1.29it/s]
1|3062|Loss: 0.8306559324264526:  12%|█▏        | 3061/25880 [39:40<4:54:35,  1.29it/s]
1|3062|Loss: 0.8306559324264526:  12%|█▏        | 3062/25880 [39:41<4:47:30,  1.32it/s]
1|3063|Loss: 0.9145660996437073:  12%|█▏        | 3062/25880 [39:41<4:47:30,  1.32it/s]
1|3063|Loss: 0.9145660996437073:  12%|█▏        | 3063/25880 [39:41<4:42:51,  1.34it/s]
1|3064|Loss: 0.9331129789352417:  12%|█▏        | 3063/25880 [39:42<4:42:51,  1.34it/s]
1|3064|Loss: 0.9331129789352417:  12%|█▏        | 3064/25880 [39:42<4:32:23,  1.40it/s]
1|3065|Loss: 0.8837674856185913:  12%|█▏        | 3064/25880 [39:42<4:32:23,  1.40it/s]
1|3065|Loss: 0.8837674856185913:  12%|█▏        | 3065/25880 [39:43<4:31:42,  1.40it/s]
1|3066|Loss: 0.9443157315254211:  12%|█▏        | 3065/25880 [39:43<4:31:42,  1.40it/s]
1|3066|Loss: 0.9443157315254211:  12%|█▏        | 3066/25880 [39:43<4:22:44,  1.45it/s]
1|3067|Loss: 0.7908015847206116:  12%|█▏        | 3066/25880 [39:44<4:22:44,  1.45it/s]
1|3067|Loss: 0.7908015847206116:  12%|█▏        | 3067/25880 [39:44<4:22:38,  1.45it/s]
1|3068|Loss: 0.8437738418579102:  12%|█▏        | 3067/25880 [39:44<4:22:38,  1.45it/s]
1|3068|Loss: 0.8437738418579102:  12%|█▏        | 3068/25880 [39:45<4:23:15,  1.44it/s]
1|3069|Loss: 0.6915068030357361:  12%|█▏        | 3068/25880 [39:45<4:23:15,  1.44it/s]
1|3069|Loss: 0.6915068030357361:  12%|█▏        | 3069/25880 [39:46<4:35:30,  1.38it/s]
1|3070|Loss: 0.7719879150390625:  12%|█▏        | 3069/25880 [39:46<4:35:30,  1.38it/s]
1|3070|Loss: 0.7719879150390625:  12%|█▏        | 3070/25880 [39:46<4:29:53,  1.41it/s]
1|3071|Loss: 0.8607442378997803:  12%|█▏        | 3070/25880 [39:47<4:29:53,  1.41it/s]
1|3071|Loss: 0.8607442378997803:  12%|█▏        | 3071/25880 [39:47<4:27:11,  1.42it/s]
1|3072|Loss: 0.7948265671730042:  12%|█▏        | 3071/25880 [39:47<4:27:11,  1.42it/s]
1|3072|Loss: 0.7948265671730042:  12%|█▏        | 3072/25880 [39:48<4:35:09,  1.38it/s]
1|3073|Loss: 0.7251845598220825:  12%|█▏        | 3072/25880 [39:48<4:35:09,  1.38it/s]
1|3073|Loss: 0.7251845598220825:  12%|█▏        | 3073/25880 [39:48<4:25:00,  1.43it/s]
1|3074|Loss: 1.0022177696228027:  12%|█▏        | 3073/25880 [39:49<4:25:00,  1.43it/s]
1|3074|Loss: 1.0022177696228027:  12%|█▏        | 3074/25880 [39:49<4:16:23,  1.48it/s]
1|3075|Loss: 1.0177913904190063:  12%|█▏        | 3074/25880 [39:49<4:16:23,  1.48it/s]
1|3075|Loss: 1.0177913904190063:  12%|█▏        | 3075/25880 [39:50<4:29:41,  1.41it/s]
1|3076|Loss: 0.9474055171012878:  12%|█▏        | 3075/25880 [39:50<4:29:41,  1.41it/s]
1|3076|Loss: 0.9474055171012878:  12%|█▏        | 3076/25880 [39:50<4:23:35,  1.44it/s]
1|3077|Loss: 1.0062196254730225:  12%|█▏        | 3076/25880 [39:51<4:23:35,  1.44it/s]
1|3077|Loss: 1.0062196254730225:  12%|█▏        | 3077/25880 [39:51<4:11:14,  1.51it/s]
1|3078|Loss: 0.908178985118866:  12%|█▏        | 3077/25880 [39:51<4:11:14,  1.51it/s] 
1|3078|Loss: 0.908178985118866:  12%|█▏        | 3078/25880 [39:52<4:13:43,  1.50it/s]
1|3079|Loss: 0.7971240282058716:  12%|█▏        | 3078/25880 [39:52<4:13:43,  1.50it/s]
1|3079|Loss: 0.7971240282058716:  12%|█▏        | 3079/25880 [39:52<4:12:11,  1.51it/s]
1|3080|Loss: 0.9169833064079285:  12%|█▏        | 3079/25880 [39:53<4:12:11,  1.51it/s]
1|3080|Loss: 0.9169833064079285:  12%|█▏        | 3080/25880 [39:53<4:09:49,  1.52it/s]
1|3081|Loss: 0.8384639620780945:  12%|█▏        | 3080/25880 [39:53<4:09:49,  1.52it/s]
1|3081|Loss: 0.8384639620780945:  12%|█▏        | 3081/25880 [39:54<4:08:08,  1.53it/s]
1|3082|Loss: 0.9705029129981995:  12%|█▏        | 3081/25880 [39:54<4:08:08,  1.53it/s]
1|3082|Loss: 0.9705029129981995:  12%|█▏        | 3082/25880 [39:54<4:22:05,  1.45it/s]
1|3083|Loss: 0.8379822969436646:  12%|█▏        | 3082/25880 [39:55<4:22:05,  1.45it/s]
1|3083|Loss: 0.8379822969436646:  12%|█▏        | 3083/25880 [39:55<4:14:37,  1.49it/s]
1|3084|Loss: 0.8669195175170898:  12%|█▏        | 3083/25880 [39:55<4:14:37,  1.49it/s]
1|3084|Loss: 0.8669195175170898:  12%|█▏        | 3084/25880 [39:56<4:17:24,  1.48it/s]
1|3085|Loss: 0.7931758761405945:  12%|█▏        | 3084/25880 [39:56<4:17:24,  1.48it/s]
1|3085|Loss: 0.7931758761405945:  12%|█▏        | 3085/25880 [39:56<4:28:38,  1.41it/s]
1|3086|Loss: 0.8690593242645264:  12%|█▏        | 3085/25880 [39:57<4:28:38,  1.41it/s]
1|3086|Loss: 0.8690593242645264:  12%|█▏        | 3086/25880 [39:57<4:33:14,  1.39it/s]
1|3087|Loss: 0.8468993902206421:  12%|█▏        | 3086/25880 [39:58<4:33:14,  1.39it/s]
1|3087|Loss: 0.8468993902206421:  12%|█▏        | 3087/25880 [39:58<4:08:20,  1.53it/s]
1|3088|Loss: 0.8383774757385254:  12%|█▏        | 3087/25880 [39:58<4:08:20,  1.53it/s]
1|3088|Loss: 0.8383774757385254:  12%|█▏        | 3088/25880 [39:58<4:01:46,  1.57it/s]
1|3089|Loss: 0.8879618644714355:  12%|█▏        | 3088/25880 [39:59<4:01:46,  1.57it/s]
1|3089|Loss: 0.8879618644714355:  12%|█▏        | 3089/25880 [39:59<4:22:26,  1.45it/s]
1|3090|Loss: 0.9676513075828552:  12%|█▏        | 3089/25880 [40:00<4:22:26,  1.45it/s]
1|3090|Loss: 0.9676513075828552:  12%|█▏        | 3090/25880 [40:00<4:39:44,  1.36it/s]
1|3091|Loss: 0.8560561537742615:  12%|█▏        | 3090/25880 [40:00<4:39:44,  1.36it/s]
1|3091|Loss: 0.8560561537742615:  12%|█▏        | 3091/25880 [40:01<4:47:51,  1.32it/s]
1|3092|Loss: 0.9235469102859497:  12%|█▏        | 3091/25880 [40:01<4:47:51,  1.32it/s]
1|3092|Loss: 0.9235469102859497:  12%|█▏        | 3092/25880 [40:01<4:30:05,  1.41it/s]
1|3093|Loss: 0.8382872939109802:  12%|█▏        | 3092/25880 [40:02<4:30:05,  1.41it/s]
1|3093|Loss: 0.8382872939109802:  12%|█▏        | 3093/25880 [40:02<4:42:42,  1.34it/s]
1|3094|Loss: 0.9242388606071472:  12%|█▏        | 3093/25880 [40:03<4:42:42,  1.34it/s]
1|3094|Loss: 0.9242388606071472:  12%|█▏        | 3094/25880 [40:03<4:32:34,  1.39it/s]
1|3095|Loss: 0.8000036478042603:  12%|█▏        | 3094/25880 [40:03<4:32:34,  1.39it/s]
1|3095|Loss: 0.8000036478042603:  12%|█▏        | 3095/25880 [40:04<4:27:53,  1.42it/s]
1|3096|Loss: 0.8960744142532349:  12%|█▏        | 3095/25880 [40:04<4:27:53,  1.42it/s]
1|3096|Loss: 0.8960744142532349:  12%|█▏        | 3096/25880 [40:04<4:04:33,  1.55it/s]
1|3097|Loss: 0.8779194355010986:  12%|█▏        | 3096/25880 [40:04<4:04:33,  1.55it/s]
1|3097|Loss: 0.8779194355010986:  12%|█▏        | 3097/25880 [40:05<4:05:07,  1.55it/s]
1|3098|Loss: 0.8809975981712341:  12%|█▏        | 3097/25880 [40:05<4:05:07,  1.55it/s]
1|3098|Loss: 0.8809975981712341:  12%|█▏        | 3098/25880 [40:05<4:21:48,  1.45it/s]
1|3099|Loss: 0.8264052867889404:  12%|█▏        | 3098/25880 [40:06<4:21:48,  1.45it/s]
1|3099|Loss: 0.8264052867889404:  12%|█▏        | 3099/25880 [40:06<4:20:32,  1.46it/s]
1|3100|Loss: 0.9336407780647278:  12%|█▏        | 3099/25880 [40:07<4:20:32,  1.46it/s]
1|3100|Loss: 0.9336407780647278:  12%|█▏        | 3100/25880 [40:07<4:11:17,  1.51it/s]
1|3101|Loss: 0.854170024394989:  12%|█▏        | 3100/25880 [40:07<4:11:17,  1.51it/s] 
1|3101|Loss: 0.854170024394989:  12%|█▏        | 3101/25880 [40:07<4:04:52,  1.55it/s]
1|3102|Loss: 0.8897377252578735:  12%|█▏        | 3101/25880 [40:08<4:04:52,  1.55it/s]
1|3102|Loss: 0.8897377252578735:  12%|█▏        | 3102/25880 [40:08<4:21:04,  1.45it/s]
1|3103|Loss: 0.8536981344223022:  12%|█▏        | 3102/25880 [40:09<4:21:04,  1.45it/s]
1|3103|Loss: 0.8536981344223022:  12%|█▏        | 3103/25880 [40:09<4:36:53,  1.37it/s]
1|3104|Loss: 0.8262844085693359:  12%|█▏        | 3103/25880 [40:09<4:36:53,  1.37it/s]
1|3104|Loss: 0.8262844085693359:  12%|█▏        | 3104/25880 [40:10<4:35:59,  1.38it/s]
1|3105|Loss: 0.7537729144096375:  12%|█▏        | 3104/25880 [40:10<4:35:59,  1.38it/s]
1|3105|Loss: 0.7537729144096375:  12%|█▏        | 3105/25880 [40:10<4:40:47,  1.35it/s]
1|3106|Loss: 0.7510654330253601:  12%|█▏        | 3105/25880 [40:11<4:40:47,  1.35it/s]
1|3106|Loss: 0.7510654330253601:  12%|█▏        | 3106/25880 [40:11<4:39:25,  1.36it/s]
1|3107|Loss: 0.9915189146995544:  12%|█▏        | 3106/25880 [40:12<4:39:25,  1.36it/s]
1|3107|Loss: 0.9915189146995544:  12%|█▏        | 3107/25880 [40:12<4:38:27,  1.36it/s]
1|3108|Loss: 0.810300350189209:  12%|█▏        | 3107/25880 [40:12<4:38:27,  1.36it/s] 
1|3108|Loss: 0.810300350189209:  12%|█▏        | 3108/25880 [40:13<4:38:33,  1.36it/s]
1|3109|Loss: 0.9299424886703491:  12%|█▏        | 3108/25880 [40:13<4:38:33,  1.36it/s]
1|3109|Loss: 0.9299424886703491:  12%|█▏        | 3109/25880 [40:13<4:39:38,  1.36it/s]
1|3110|Loss: 0.8442355990409851:  12%|█▏        | 3109/25880 [40:14<4:39:38,  1.36it/s]
1|3110|Loss: 0.8442355990409851:  12%|█▏        | 3110/25880 [40:14<4:39:38,  1.36it/s]
1|3111|Loss: 0.6834238171577454:  12%|█▏        | 3110/25880 [40:14<4:39:38,  1.36it/s]
1|3111|Loss: 0.6834238171577454:  12%|█▏        | 3111/25880 [40:15<4:20:10,  1.46it/s]
1|3112|Loss: 0.8888719081878662:  12%|█▏        | 3111/25880 [40:15<4:20:10,  1.46it/s]
1|3112|Loss: 0.8888719081878662:  12%|█▏        | 3112/25880 [40:15<4:28:44,  1.41it/s]
1|3113|Loss: 0.7643808126449585:  12%|█▏        | 3112/25880 [40:16<4:28:44,  1.41it/s]
1|3113|Loss: 0.7643808126449585:  12%|█▏        | 3113/25880 [40:16<4:33:02,  1.39it/s]
1|3114|Loss: 0.8882359266281128:  12%|█▏        | 3113/25880 [40:17<4:33:02,  1.39it/s]
1|3114|Loss: 0.8882359266281128:  12%|█▏        | 3114/25880 [40:17<4:33:52,  1.39it/s]
1|3115|Loss: 0.824995756149292:  12%|█▏        | 3114/25880 [40:17<4:33:52,  1.39it/s] 
1|3115|Loss: 0.824995756149292:  12%|█▏        | 3115/25880 [40:18<4:32:41,  1.39it/s]
1|3116|Loss: 0.9221863150596619:  12%|█▏        | 3115/25880 [40:18<4:32:41,  1.39it/s]
1|3116|Loss: 0.9221863150596619:  12%|█▏        | 3116/25880 [40:18<4:21:14,  1.45it/s]
1|3117|Loss: 0.9421266913414001:  12%|█▏        | 3116/25880 [40:19<4:21:14,  1.45it/s]
1|3117|Loss: 0.9421266913414001:  12%|█▏        | 3117/25880 [40:19<4:14:22,  1.49it/s]
1|3118|Loss: 0.961580753326416:  12%|█▏        | 3117/25880 [40:19<4:14:22,  1.49it/s] 
1|3118|Loss: 0.961580753326416:  12%|█▏        | 3118/25880 [40:20<4:09:11,  1.52it/s]
1|3119|Loss: 1.0021620988845825:  12%|█▏        | 3118/25880 [40:20<4:09:11,  1.52it/s]
1|3119|Loss: 1.0021620988845825:  12%|█▏        | 3119/25880 [40:20<4:04:27,  1.55it/s]
1|3120|Loss: 0.8429174423217773:  12%|█▏        | 3119/25880 [40:21<4:04:27,  1.55it/s]
1|3120|Loss: 0.8429174423217773:  12%|█▏        | 3120/25880 [40:21<4:03:42,  1.56it/s]
1|3121|Loss: 0.8964331746101379:  12%|█▏        | 3120/25880 [40:21<4:03:42,  1.56it/s]
1|3121|Loss: 0.8964331746101379:  12%|█▏        | 3121/25880 [40:21<4:09:11,  1.52it/s]
1|3122|Loss: 0.8197522163391113:  12%|█▏        | 3121/25880 [40:22<4:09:11,  1.52it/s]
1|3122|Loss: 0.8197522163391113:  12%|█▏        | 3122/25880 [40:22<3:51:38,  1.64it/s]
1|3123|Loss: 0.8796024322509766:  12%|█▏        | 3122/25880 [40:22<3:51:38,  1.64it/s]
1|3123|Loss: 0.8796024322509766:  12%|█▏        | 3123/25880 [40:23<3:55:32,  1.61it/s]
1|3124|Loss: 0.8825047016143799:  12%|█▏        | 3123/25880 [40:23<3:55:32,  1.61it/s]
1|3124|Loss: 0.8825047016143799:  12%|█▏        | 3124/25880 [40:23<3:48:36,  1.66it/s]
1|3125|Loss: 0.7895915508270264:  12%|█▏        | 3124/25880 [40:24<3:48:36,  1.66it/s]
1|3125|Loss: 0.7895915508270264:  12%|█▏        | 3125/25880 [40:24<3:47:57,  1.66it/s]
1|3126|Loss: 0.8653365969657898:  12%|█▏        | 3125/25880 [40:24<3:47:57,  1.66it/s]
1|3126|Loss: 0.8653365969657898:  12%|█▏        | 3126/25880 [40:25<4:05:10,  1.55it/s]
1|3127|Loss: 0.8755762577056885:  12%|█▏        | 3126/25880 [40:25<4:05:10,  1.55it/s]
1|3127|Loss: 0.8755762577056885:  12%|█▏        | 3127/25880 [40:25<3:51:01,  1.64it/s]
1|3128|Loss: 0.9184436798095703:  12%|█▏        | 3127/25880 [40:25<3:51:01,  1.64it/s]
1|3128|Loss: 0.9184436798095703:  12%|█▏        | 3128/25880 [40:26<3:40:10,  1.72it/s]
1|3129|Loss: 1.0991569757461548:  12%|█▏        | 3128/25880 [40:26<3:40:10,  1.72it/s]
1|3129|Loss: 1.0991569757461548:  12%|█▏        | 3129/25880 [40:26<3:49:43,  1.65it/s]
1|3130|Loss: 0.8525432348251343:  12%|█▏        | 3129/25880 [40:27<3:49:43,  1.65it/s]
1|3130|Loss: 0.8525432348251343:  12%|█▏        | 3130/25880 [40:27<3:53:10,  1.63it/s]
1|3131|Loss: 0.8755093216896057:  12%|█▏        | 3130/25880 [40:27<3:53:10,  1.63it/s]
1|3131|Loss: 0.8755093216896057:  12%|█▏        | 3131/25880 [40:27<3:53:04,  1.63it/s]
1|3132|Loss: 0.8433690667152405:  12%|█▏        | 3131/25880 [40:28<3:53:04,  1.63it/s]
1|3132|Loss: 0.8433690667152405:  12%|█▏        | 3132/25880 [40:28<3:47:58,  1.66it/s]
1|3133|Loss: 0.9366084933280945:  12%|█▏        | 3132/25880 [40:28<3:47:58,  1.66it/s]
1|3133|Loss: 0.9366084933280945:  12%|█▏        | 3133/25880 [40:29<3:44:48,  1.69it/s]
1|3134|Loss: 0.8544474244117737:  12%|█▏        | 3133/25880 [40:29<3:44:48,  1.69it/s]
1|3134|Loss: 0.8544474244117737:  12%|█▏        | 3134/25880 [40:29<4:07:55,  1.53it/s]
1|3135|Loss: 0.9079568386077881:  12%|█▏        | 3134/25880 [40:30<4:07:55,  1.53it/s]
1|3135|Loss: 0.9079568386077881:  12%|█▏        | 3135/25880 [40:30<3:54:25,  1.62it/s]
1|3136|Loss: 0.931522786617279:  12%|█▏        | 3135/25880 [40:30<3:54:25,  1.62it/s] 
1|3136|Loss: 0.931522786617279:  12%|█▏        | 3136/25880 [40:31<4:01:26,  1.57it/s]
1|3137|Loss: 0.9777006506919861:  12%|█▏        | 3136/25880 [40:31<4:01:26,  1.57it/s]
1|3137|Loss: 0.9777006506919861:  12%|█▏        | 3137/25880 [40:31<4:04:26,  1.55it/s]
1|3138|Loss: 0.8592079281806946:  12%|█▏        | 3137/25880 [40:32<4:04:26,  1.55it/s]
1|3138|Loss: 0.8592079281806946:  12%|█▏        | 3138/25880 [40:32<4:09:29,  1.52it/s]
1|3139|Loss: 0.8854273557662964:  12%|█▏        | 3138/25880 [40:32<4:09:29,  1.52it/s]
1|3139|Loss: 0.8854273557662964:  12%|█▏        | 3139/25880 [40:33<4:16:39,  1.48it/s]
1|3140|Loss: 0.8581548929214478:  12%|█▏        | 3139/25880 [40:33<4:16:39,  1.48it/s]
1|3140|Loss: 0.8581548929214478:  12%|█▏        | 3140/25880 [40:34<4:31:07,  1.40it/s]
1|3141|Loss: 0.9628000855445862:  12%|█▏        | 3140/25880 [40:34<4:31:07,  1.40it/s]
1|3141|Loss: 0.9628000855445862:  12%|█▏        | 3141/25880 [40:34<4:34:46,  1.38it/s]
1|3142|Loss: 0.8256062269210815:  12%|█▏        | 3141/25880 [40:35<4:34:46,  1.38it/s]
1|3142|Loss: 0.8256062269210815:  12%|█▏        | 3142/25880 [40:35<4:18:59,  1.46it/s]
1|3143|Loss: 1.0471655130386353:  12%|█▏        | 3142/25880 [40:35<4:18:59,  1.46it/s]
1|3143|Loss: 1.0471655130386353:  12%|█▏        | 3143/25880 [40:35<4:06:55,  1.53it/s]
1|3144|Loss: 0.8513842225074768:  12%|█▏        | 3143/25880 [40:36<4:06:55,  1.53it/s]
1|3144|Loss: 0.8513842225074768:  12%|█▏        | 3144/25880 [40:36<4:21:40,  1.45it/s]
1|3145|Loss: 0.8590537309646606:  12%|█▏        | 3144/25880 [40:37<4:21:40,  1.45it/s]
1|3145|Loss: 0.8590537309646606:  12%|█▏        | 3145/25880 [40:37<4:19:40,  1.46it/s]
1|3146|Loss: 0.8982861638069153:  12%|█▏        | 3145/25880 [40:37<4:19:40,  1.46it/s]
1|3146|Loss: 0.8982861638069153:  12%|█▏        | 3146/25880 [40:37<4:09:32,  1.52it/s]
1|3147|Loss: 0.8670174479484558:  12%|█▏        | 3146/25880 [40:38<4:09:32,  1.52it/s]
1|3147|Loss: 0.8670174479484558:  12%|█▏        | 3147/25880 [40:38<4:06:15,  1.54it/s]
1|3148|Loss: 0.8742057085037231:  12%|█▏        | 3147/25880 [40:39<4:06:15,  1.54it/s]
1|3148|Loss: 0.8742057085037231:  12%|█▏        | 3148/25880 [40:39<4:18:48,  1.46it/s]
1|3149|Loss: 0.785336434841156:  12%|█▏        | 3148/25880 [40:39<4:18:48,  1.46it/s] 
1|3149|Loss: 0.785336434841156:  12%|█▏        | 3149/25880 [40:40<4:25:53,  1.42it/s]
1|3150|Loss: 0.84306800365448:  12%|█▏        | 3149/25880 [40:40<4:25:53,  1.42it/s] 
1|3150|Loss: 0.84306800365448:  12%|█▏        | 3150/25880 [40:40<4:25:52,  1.42it/s]
1|3151|Loss: 0.8560243844985962:  12%|█▏        | 3150/25880 [40:41<4:25:52,  1.42it/s]
1|3151|Loss: 0.8560243844985962:  12%|█▏        | 3151/25880 [40:41<4:27:32,  1.42it/s]
1|3152|Loss: 0.8605386018753052:  12%|█▏        | 3151/25880 [40:41<4:27:32,  1.42it/s]
1|3152|Loss: 0.8605386018753052:  12%|█▏        | 3152/25880 [40:42<4:29:57,  1.40it/s]
1|3153|Loss: 0.8495535254478455:  12%|█▏        | 3152/25880 [40:42<4:29:57,  1.40it/s]
1|3153|Loss: 0.8495535254478455:  12%|█▏        | 3153/25880 [40:42<4:31:40,  1.39it/s]
1|3154|Loss: 0.9692033529281616:  12%|█▏        | 3153/25880 [40:43<4:31:40,  1.39it/s]
1|3154|Loss: 0.9692033529281616:  12%|█▏        | 3154/25880 [40:43<4:32:24,  1.39it/s]
1|3155|Loss: 0.8292843699455261:  12%|█▏        | 3154/25880 [40:44<4:32:24,  1.39it/s]
1|3155|Loss: 0.8292843699455261:  12%|█▏        | 3155/25880 [40:44<4:00:21,  1.58it/s]
1|3156|Loss: 0.8826761841773987:  12%|█▏        | 3155/25880 [40:44<4:00:21,  1.58it/s]
1|3156|Loss: 0.8826761841773987:  12%|█▏        | 3156/25880 [40:44<4:08:59,  1.52it/s]
1|3157|Loss: 0.8590672612190247:  12%|█▏        | 3156/25880 [40:45<4:08:59,  1.52it/s]
1|3157|Loss: 0.8590672612190247:  12%|█▏        | 3157/25880 [40:45<4:18:51,  1.46it/s]
1|3158|Loss: 0.9113664031028748:  12%|█▏        | 3157/25880 [40:45<4:18:51,  1.46it/s]
1|3158|Loss: 0.9113664031028748:  12%|█▏        | 3158/25880 [40:46<4:15:24,  1.48it/s]
1|3159|Loss: 0.8256866335868835:  12%|█▏        | 3158/25880 [40:46<4:15:24,  1.48it/s]
1|3159|Loss: 0.8256866335868835:  12%|█▏        | 3159/25880 [40:47<4:29:11,  1.41it/s]
1|3160|Loss: 0.8869438767433167:  12%|█▏        | 3159/25880 [40:47<4:29:11,  1.41it/s]
1|3160|Loss: 0.8869438767433167:  12%|█▏        | 3160/25880 [40:47<4:20:30,  1.45it/s]
1|3161|Loss: 0.8460657000541687:  12%|█▏        | 3160/25880 [40:48<4:20:30,  1.45it/s]
1|3161|Loss: 0.8460657000541687:  12%|█▏        | 3161/25880 [40:48<4:26:45,  1.42it/s]
1|3162|Loss: 0.8644195199012756:  12%|█▏        | 3161/25880 [40:48<4:26:45,  1.42it/s]
1|3162|Loss: 0.8644195199012756:  12%|█▏        | 3162/25880 [40:49<4:21:25,  1.45it/s]
1|3163|Loss: 0.9419834613800049:  12%|█▏        | 3162/25880 [40:49<4:21:25,  1.45it/s]
1|3163|Loss: 0.9419834613800049:  12%|█▏        | 3163/25880 [40:49<4:24:34,  1.43it/s]
1|3164|Loss: 0.8617757558822632:  12%|█▏        | 3163/25880 [40:50<4:24:34,  1.43it/s]
1|3164|Loss: 0.8617757558822632:  12%|█▏        | 3164/25880 [40:50<4:35:26,  1.37it/s]
1|3165|Loss: 0.8395333886146545:  12%|█▏        | 3164/25880 [40:51<4:35:26,  1.37it/s]
1|3165|Loss: 0.8395333886146545:  12%|█▏        | 3165/25880 [40:51<4:48:45,  1.31it/s]
1|3166|Loss: 0.9853910803794861:  12%|█▏        | 3165/25880 [40:51<4:48:45,  1.31it/s]
1|3166|Loss: 0.9853910803794861:  12%|█▏        | 3166/25880 [40:52<4:46:05,  1.32it/s]
1|3167|Loss: 0.837181568145752:  12%|█▏        | 3166/25880 [40:52<4:46:05,  1.32it/s] 
1|3167|Loss: 0.837181568145752:  12%|█▏        | 3167/25880 [40:52<4:39:40,  1.35it/s]
1|3168|Loss: 0.8306578397750854:  12%|█▏        | 3167/25880 [40:53<4:39:40,  1.35it/s]
1|3168|Loss: 0.8306578397750854:  12%|█▏        | 3168/25880 [40:53<4:50:16,  1.30it/s]
1|3169|Loss: 0.959141194820404:  12%|█▏        | 3168/25880 [40:54<4:50:16,  1.30it/s] 
1|3169|Loss: 0.959141194820404:  12%|█▏        | 3169/25880 [40:54<5:07:37,  1.23it/s]
1|3170|Loss: 0.8552943468093872:  12%|█▏        | 3169/25880 [40:55<5:07:37,  1.23it/s]
1|3170|Loss: 0.8552943468093872:  12%|█▏        | 3170/25880 [40:55<4:49:17,  1.31it/s]
1|3171|Loss: 0.8630321025848389:  12%|█▏        | 3170/25880 [40:55<4:49:17,  1.31it/s]
1|3171|Loss: 0.8630321025848389:  12%|█▏        | 3171/25880 [40:55<4:33:13,  1.39it/s]
1|3172|Loss: 0.8691374659538269:  12%|█▏        | 3171/25880 [40:56<4:33:13,  1.39it/s]
1|3172|Loss: 0.8691374659538269:  12%|█▏        | 3172/25880 [40:56<4:33:53,  1.38it/s]
1|3173|Loss: 0.829042911529541:  12%|█▏        | 3172/25880 [40:57<4:33:53,  1.38it/s] 
1|3173|Loss: 0.829042911529541:  12%|█▏        | 3173/25880 [40:57<4:40:58,  1.35it/s]
1|3174|Loss: 0.8919891715049744:  12%|█▏        | 3173/25880 [40:57<4:40:58,  1.35it/s]
1|3174|Loss: 0.8919891715049744:  12%|█▏        | 3174/25880 [40:58<4:52:36,  1.29it/s]
1|3175|Loss: 0.9009943604469299:  12%|█▏        | 3174/25880 [40:58<4:52:36,  1.29it/s]
1|3175|Loss: 0.9009943604469299:  12%|█▏        | 3175/25880 [40:58<4:43:08,  1.34it/s]
1|3176|Loss: 0.8158806562423706:  12%|█▏        | 3175/25880 [40:59<4:43:08,  1.34it/s]
1|3176|Loss: 0.8158806562423706:  12%|█▏        | 3176/25880 [40:59<4:40:06,  1.35it/s]
1|3177|Loss: 0.949842095375061:  12%|█▏        | 3176/25880 [41:00<4:40:06,  1.35it/s] 
1|3177|Loss: 0.949842095375061:  12%|█▏        | 3177/25880 [41:00<4:41:01,  1.35it/s]
1|3178|Loss: 0.9048524498939514:  12%|█▏        | 3177/25880 [41:00<4:41:01,  1.35it/s]
1|3178|Loss: 0.9048524498939514:  12%|█▏        | 3178/25880 [41:01<4:27:19,  1.42it/s]
1|3179|Loss: 0.7773081064224243:  12%|█▏        | 3178/25880 [41:01<4:27:19,  1.42it/s]
1|3179|Loss: 0.7773081064224243:  12%|█▏        | 3179/25880 [41:01<4:35:09,  1.38it/s]
1|3180|Loss: 0.8577297925949097:  12%|█▏        | 3179/25880 [41:02<4:35:09,  1.38it/s]
1|3180|Loss: 0.8577297925949097:  12%|█▏        | 3180/25880 [41:02<4:34:29,  1.38it/s]
1|3181|Loss: 0.9812235236167908:  12%|█▏        | 3180/25880 [41:02<4:34:29,  1.38it/s]
1|3181|Loss: 0.9812235236167908:  12%|█▏        | 3181/25880 [41:03<4:47:28,  1.32it/s]
1|3182|Loss: 0.9006220698356628:  12%|█▏        | 3181/25880 [41:03<4:47:28,  1.32it/s]
1|3182|Loss: 0.9006220698356628:  12%|█▏        | 3182/25880 [41:04<4:40:02,  1.35it/s]
1|3183|Loss: 1.0441527366638184:  12%|█▏        | 3182/25880 [41:04<4:40:02,  1.35it/s]
1|3183|Loss: 1.0441527366638184:  12%|█▏        | 3183/25880 [41:04<4:28:25,  1.41it/s]
1|3184|Loss: 0.8514278531074524:  12%|█▏        | 3183/25880 [41:05<4:28:25,  1.41it/s]
1|3184|Loss: 0.8514278531074524:  12%|█▏        | 3184/25880 [41:05<4:14:44,  1.48it/s]
1|3185|Loss: 0.8131443858146667:  12%|█▏        | 3184/25880 [41:05<4:14:44,  1.48it/s]
1|3185|Loss: 0.8131443858146667:  12%|█▏        | 3185/25880 [41:06<4:18:35,  1.46it/s]
1|3186|Loss: 0.58404141664505:  12%|█▏        | 3185/25880 [41:06<4:18:35,  1.46it/s]  
1|3186|Loss: 0.58404141664505:  12%|█▏        | 3186/25880 [41:06<4:29:18,  1.40it/s]
1|3187|Loss: 0.8956164717674255:  12%|█▏        | 3186/25880 [41:07<4:29:18,  1.40it/s]
1|3187|Loss: 0.8956164717674255:  12%|█▏        | 3187/25880 [41:07<4:38:44,  1.36it/s]
1|3188|Loss: 0.8735268115997314:  12%|█▏        | 3187/25880 [41:08<4:38:44,  1.36it/s]
1|3188|Loss: 0.8735268115997314:  12%|█▏        | 3188/25880 [41:08<4:37:16,  1.36it/s]
1|3189|Loss: 0.7656281590461731:  12%|█▏        | 3188/25880 [41:08<4:37:16,  1.36it/s]
1|3189|Loss: 0.7656281590461731:  12%|█▏        | 3189/25880 [41:09<4:33:21,  1.38it/s]
1|3190|Loss: 0.8862354755401611:  12%|█▏        | 3189/25880 [41:09<4:33:21,  1.38it/s]
1|3190|Loss: 0.8862354755401611:  12%|█▏        | 3190/25880 [41:09<4:33:35,  1.38it/s]
1|3191|Loss: 0.8387140035629272:  12%|█▏        | 3190/25880 [41:10<4:33:35,  1.38it/s]
1|3191|Loss: 0.8387140035629272:  12%|█▏        | 3191/25880 [41:10<4:43:52,  1.33it/s]
1|3192|Loss: 0.8871532678604126:  12%|█▏        | 3191/25880 [41:11<4:43:52,  1.33it/s]
1|3192|Loss: 0.8871532678604126:  12%|█▏        | 3192/25880 [41:11<4:53:10,  1.29it/s]
1|3193|Loss: 1.01185941696167:  12%|█▏        | 3192/25880 [41:11<4:53:10,  1.29it/s]  
1|3193|Loss: 1.01185941696167:  12%|█▏        | 3193/25880 [41:12<4:41:46,  1.34it/s]
1|3194|Loss: 1.1693235635757446:  12%|█▏        | 3193/25880 [41:12<4:41:46,  1.34it/s]
1|3194|Loss: 1.1693235635757446:  12%|█▏        | 3194/25880 [41:12<4:59:23,  1.26it/s]
1|3195|Loss: 0.8748731017112732:  12%|█▏        | 3194/25880 [41:13<4:59:23,  1.26it/s]
1|3195|Loss: 0.8748731017112732:  12%|█▏        | 3195/25880 [41:13<4:57:47,  1.27it/s]
1|3196|Loss: 0.8950712084770203:  12%|█▏        | 3195/25880 [41:14<4:57:47,  1.27it/s]
1|3196|Loss: 0.8950712084770203:  12%|█▏        | 3196/25880 [41:14<4:51:21,  1.30it/s]
1|3197|Loss: 0.8801517486572266:  12%|█▏        | 3196/25880 [41:14<4:51:21,  1.30it/s]
1|3197|Loss: 0.8801517486572266:  12%|█▏        | 3197/25880 [41:15<4:53:00,  1.29it/s]
1|3198|Loss: 0.8979673981666565:  12%|█▏        | 3197/25880 [41:15<4:53:00,  1.29it/s]
1|3198|Loss: 0.8979673981666565:  12%|█▏        | 3198/25880 [41:15<4:41:38,  1.34it/s]
1|3199|Loss: 0.6656947731971741:  12%|█▏        | 3198/25880 [41:16<4:41:38,  1.34it/s]
1|3199|Loss: 0.6656947731971741:  12%|█▏        | 3199/25880 [41:16<4:49:12,  1.31it/s]
1|3200|Loss: 0.850937008857727:  12%|█▏        | 3199/25880 [41:17<4:49:12,  1.31it/s] 
1|3200|Loss: 0.850937008857727:  12%|█▏        | 3200/25880 [41:17<4:46:16,  1.32it/s]
1|3201|Loss: 0.7870036363601685:  12%|█▏        | 3200/25880 [41:17<4:46:16,  1.32it/s]
1|3201|Loss: 0.7870036363601685:  12%|█▏        | 3201/25880 [41:18<4:35:10,  1.37it/s]
1|3202|Loss: 0.945772647857666:  12%|█▏        | 3201/25880 [41:18<4:35:10,  1.37it/s] 
1|3202|Loss: 0.945772647857666:  12%|█▏        | 3202/25880 [41:18<4:23:22,  1.44it/s]
1|3203|Loss: 1.043023943901062:  12%|█▏        | 3202/25880 [41:19<4:23:22,  1.44it/s]
1|3203|Loss: 1.043023943901062:  12%|█▏        | 3203/25880 [41:19<4:08:57,  1.52it/s]
1|3204|Loss: 1.0212044715881348:  12%|█▏        | 3203/25880 [41:19<4:08:57,  1.52it/s]
1|3204|Loss: 1.0212044715881348:  12%|█▏        | 3204/25880 [41:20<4:27:02,  1.42it/s]
1|3205|Loss: 0.9788414835929871:  12%|█▏        | 3204/25880 [41:20<4:27:02,  1.42it/s]
1|3205|Loss: 0.9788414835929871:  12%|█▏        | 3205/25880 [41:20<4:35:55,  1.37it/s]
1|3206|Loss: 0.8332804441452026:  12%|█▏        | 3205/25880 [41:21<4:35:55,  1.37it/s]
1|3206|Loss: 0.8332804441452026:  12%|█▏        | 3206/25880 [41:21<4:21:20,  1.45it/s]
1|3207|Loss: 0.882449209690094:  12%|█▏        | 3206/25880 [41:21<4:21:20,  1.45it/s] 
1|3207|Loss: 0.882449209690094:  12%|█▏        | 3207/25880 [41:22<4:32:09,  1.39it/s]
1|3208|Loss: 0.8801757097244263:  12%|█▏        | 3207/25880 [41:22<4:32:09,  1.39it/s]
1|3208|Loss: 0.8801757097244263:  12%|█▏        | 3208/25880 [41:23<4:37:03,  1.36it/s]
1|3209|Loss: 0.9631343483924866:  12%|█▏        | 3208/25880 [41:23<4:37:03,  1.36it/s]
1|3209|Loss: 0.9631343483924866:  12%|█▏        | 3209/25880 [41:23<4:34:40,  1.38it/s]
1|3210|Loss: 0.8167818188667297:  12%|█▏        | 3209/25880 [41:24<4:34:40,  1.38it/s]
1|3210|Loss: 0.8167818188667297:  12%|█▏        | 3210/25880 [41:24<4:31:06,  1.39it/s]
1|3211|Loss: 0.7560901641845703:  12%|█▏        | 3210/25880 [41:24<4:31:06,  1.39it/s]
1|3211|Loss: 0.7560901641845703:  12%|█▏        | 3211/25880 [41:25<4:32:12,  1.39it/s]
1|3212|Loss: 0.8940011858940125:  12%|█▏        | 3211/25880 [41:25<4:32:12,  1.39it/s]
1|3212|Loss: 0.8940011858940125:  12%|█▏        | 3212/25880 [41:26<4:38:04,  1.36it/s]
1|3213|Loss: 0.7410683035850525:  12%|█▏        | 3212/25880 [41:26<4:38:04,  1.36it/s]
1|3213|Loss: 0.7410683035850525:  12%|█▏        | 3213/25880 [41:26<4:56:57,  1.27it/s]
1|3214|Loss: 0.9243733882904053:  12%|█▏        | 3213/25880 [41:27<4:56:57,  1.27it/s]
1|3214|Loss: 0.9243733882904053:  12%|█▏        | 3214/25880 [41:27<4:39:16,  1.35it/s]
1|3215|Loss: 0.8921307325363159:  12%|█▏        | 3214/25880 [41:27<4:39:16,  1.35it/s]
1|3215|Loss: 0.8921307325363159:  12%|█▏        | 3215/25880 [41:28<4:26:14,  1.42it/s]
1|3216|Loss: 0.8108676671981812:  12%|█▏        | 3215/25880 [41:28<4:26:14,  1.42it/s]
1|3216|Loss: 0.8108676671981812:  12%|█▏        | 3216/25880 [41:28<4:27:02,  1.41it/s]
1|3217|Loss: 0.8320114612579346:  12%|█▏        | 3216/25880 [41:29<4:27:02,  1.41it/s]
1|3217|Loss: 0.8320114612579346:  12%|█▏        | 3217/25880 [41:29<4:29:45,  1.40it/s]
1|3218|Loss: 0.765606701374054:  12%|█▏        | 3217/25880 [41:30<4:29:45,  1.40it/s] 
1|3218|Loss: 0.765606701374054:  12%|█▏        | 3218/25880 [41:30<4:31:27,  1.39it/s]
1|3219|Loss: 0.9989831447601318:  12%|█▏        | 3218/25880 [41:30<4:31:27,  1.39it/s]
1|3219|Loss: 0.9989831447601318:  12%|█▏        | 3219/25880 [41:31<4:30:21,  1.40it/s]
1|3220|Loss: 1.0281492471694946:  12%|█▏        | 3219/25880 [41:31<4:30:21,  1.40it/s]
1|3220|Loss: 1.0281492471694946:  12%|█▏        | 3220/25880 [41:31<4:28:38,  1.41it/s]
1|3221|Loss: 0.9261682629585266:  12%|█▏        | 3220/25880 [41:32<4:28:38,  1.41it/s]
1|3221|Loss: 0.9261682629585266:  12%|█▏        | 3221/25880 [41:32<4:16:29,  1.47it/s]
1|3222|Loss: 0.9364202618598938:  12%|█▏        | 3221/25880 [41:32<4:16:29,  1.47it/s]
1|3222|Loss: 0.9364202618598938:  12%|█▏        | 3222/25880 [41:32<4:06:23,  1.53it/s]
1|3223|Loss: 0.9315778613090515:  12%|█▏        | 3222/25880 [41:33<4:06:23,  1.53it/s]
1|3223|Loss: 0.9315778613090515:  12%|█▏        | 3223/25880 [41:33<3:51:49,  1.63it/s]
1|3224|Loss: 0.9665067791938782:  12%|█▏        | 3223/25880 [41:33<3:51:49,  1.63it/s]
1|3224|Loss: 0.9665067791938782:  12%|█▏        | 3224/25880 [41:34<3:45:41,  1.67it/s]
1|3225|Loss: 0.9612396359443665:  12%|█▏        | 3224/25880 [41:34<3:45:41,  1.67it/s]
1|3225|Loss: 0.9612396359443665:  12%|█▏        | 3225/25880 [41:34<3:49:22,  1.65it/s]
1|3226|Loss: 0.8815433382987976:  12%|█▏        | 3225/25880 [41:35<3:49:22,  1.65it/s]
1|3226|Loss: 0.8815433382987976:  12%|█▏        | 3226/25880 [41:35<4:12:32,  1.50it/s]
1|3227|Loss: 0.9029222726821899:  12%|█▏        | 3226/25880 [41:35<4:12:32,  1.50it/s]
1|3227|Loss: 0.9029222726821899:  12%|█▏        | 3227/25880 [41:35<3:57:18,  1.59it/s]
1|3228|Loss: 0.970723032951355:  12%|█▏        | 3227/25880 [41:36<3:57:18,  1.59it/s] 
1|3228|Loss: 0.970723032951355:  12%|█▏        | 3228/25880 [41:36<3:46:09,  1.67it/s]
1|3229|Loss: 0.8708478808403015:  12%|█▏        | 3228/25880 [41:36<3:46:09,  1.67it/s]
1|3229|Loss: 0.8708478808403015:  12%|█▏        | 3229/25880 [41:37<4:08:10,  1.52it/s]
1|3230|Loss: 0.8020843267440796:  12%|█▏        | 3229/25880 [41:37<4:08:10,  1.52it/s]
1|3230|Loss: 0.8020843267440796:  12%|█▏        | 3230/25880 [41:38<4:16:57,  1.47it/s]
1|3231|Loss: 0.9566396474838257:  12%|█▏        | 3230/25880 [41:38<4:16:57,  1.47it/s]
1|3231|Loss: 0.9566396474838257:  12%|█▏        | 3231/25880 [41:38<4:11:25,  1.50it/s]
1|3232|Loss: 0.7152365446090698:  12%|█▏        | 3231/25880 [41:39<4:11:25,  1.50it/s]
1|3232|Loss: 0.7152365446090698:  12%|█▏        | 3232/25880 [41:39<4:05:41,  1.54it/s]
1|3233|Loss: 0.7830864787101746:  12%|█▏        | 3232/25880 [41:39<4:05:41,  1.54it/s]
1|3233|Loss: 0.7830864787101746:  12%|█▏        | 3233/25880 [41:40<4:12:54,  1.49it/s]
1|3234|Loss: 1.0637855529785156:  12%|█▏        | 3233/25880 [41:40<4:12:54,  1.49it/s]
1|3234|Loss: 1.0637855529785156:  12%|█▏        | 3234/25880 [41:40<4:21:58,  1.44it/s]
1|3235|Loss: 1.1206368207931519:  12%|█▏        | 3234/25880 [41:41<4:21:58,  1.44it/s]
1|3235|Loss: 1.1206368207931519:  12%|█▎        | 3235/25880 [41:41<4:26:43,  1.41it/s]
1|3236|Loss: 0.8001103401184082:  12%|█▎        | 3235/25880 [41:41<4:26:43,  1.41it/s]
1|3236|Loss: 0.8001103401184082:  13%|█▎        | 3236/25880 [41:42<4:26:11,  1.42it/s]
1|3237|Loss: 0.8122038245201111:  13%|█▎        | 3236/25880 [41:42<4:26:11,  1.42it/s]
1|3237|Loss: 0.8122038245201111:  13%|█▎        | 3237/25880 [41:42<4:29:15,  1.40it/s]
1|3238|Loss: 0.8624428510665894:  13%|█▎        | 3237/25880 [41:43<4:29:15,  1.40it/s]
1|3238|Loss: 0.8624428510665894:  13%|█▎        | 3238/25880 [41:43<4:40:41,  1.34it/s]
1|3239|Loss: 0.8822468519210815:  13%|█▎        | 3238/25880 [41:44<4:40:41,  1.34it/s]
1|3239|Loss: 0.8822468519210815:  13%|█▎        | 3239/25880 [41:44<4:30:40,  1.39it/s]
1|3240|Loss: 0.92796391248703:  13%|█▎        | 3239/25880 [41:44<4:30:40,  1.39it/s]  
1|3240|Loss: 0.92796391248703:  13%|█▎        | 3240/25880 [41:45<4:38:23,  1.36it/s]
1|3241|Loss: 0.865037739276886:  13%|█▎        | 3240/25880 [41:45<4:38:23,  1.36it/s]
1|3241|Loss: 0.865037739276886:  13%|█▎        | 3241/25880 [41:45<4:36:38,  1.36it/s]
1|3242|Loss: 0.8557952046394348:  13%|█▎        | 3241/25880 [41:46<4:36:38,  1.36it/s]
1|3242|Loss: 0.8557952046394348:  13%|█▎        | 3242/25880 [41:46<4:44:31,  1.33it/s]
1|3243|Loss: 0.9390136003494263:  13%|█▎        | 3242/25880 [41:47<4:44:31,  1.33it/s]
1|3243|Loss: 0.9390136003494263:  13%|█▎        | 3243/25880 [41:47<4:41:10,  1.34it/s]
1|3244|Loss: 0.8765403628349304:  13%|█▎        | 3243/25880 [41:47<4:41:10,  1.34it/s]
1|3244|Loss: 0.8765403628349304:  13%|█▎        | 3244/25880 [41:48<4:30:55,  1.39it/s]
1|3245|Loss: 0.8158425688743591:  13%|█▎        | 3244/25880 [41:48<4:30:55,  1.39it/s]
1|3245|Loss: 0.8158425688743591:  13%|█▎        | 3245/25880 [41:48<4:20:08,  1.45it/s]
1|3246|Loss: 0.9219001531600952:  13%|█▎        | 3245/25880 [41:49<4:20:08,  1.45it/s]
1|3246|Loss: 0.9219001531600952:  13%|█▎        | 3246/25880 [41:49<4:11:27,  1.50it/s]
1|3247|Loss: 0.8496913909912109:  13%|█▎        | 3246/25880 [41:49<4:11:27,  1.50it/s]
1|3247|Loss: 0.8496913909912109:  13%|█▎        | 3247/25880 [41:50<4:15:50,  1.47it/s]
1|3248|Loss: 0.8075591325759888:  13%|█▎        | 3247/25880 [41:50<4:15:50,  1.47it/s]
1|3248|Loss: 0.8075591325759888:  13%|█▎        | 3248/25880 [41:50<4:28:10,  1.41it/s]
1|3249|Loss: 0.9641243815422058:  13%|█▎        | 3248/25880 [41:51<4:28:10,  1.41it/s]
1|3249|Loss: 0.9641243815422058:  13%|█▎        | 3249/25880 [41:51<4:31:35,  1.39it/s]
1|3250|Loss: 0.8148393630981445:  13%|█▎        | 3249/25880 [41:51<4:31:35,  1.39it/s]
1|3250|Loss: 0.8148393630981445:  13%|��▎        | 3250/25880 [41:52<4:36:52,  1.36it/s]
1|3251|Loss: 0.8349811434745789:  13%|█▎        | 3250/25880 [41:52<4:36:52,  1.36it/s]
1|3251|Loss: 0.8349811434745789:  13%|█▎        | 3251/25880 [41:53<4:35:13,  1.37it/s]
1|3252|Loss: 0.8945529460906982:  13%|█▎        | 3251/25880 [41:53<4:35:13,  1.37it/s]
1|3252|Loss: 0.8945529460906982:  13%|█▎        | 3252/25880 [41:53<4:34:00,  1.38it/s]
1|3253|Loss: 0.852533221244812:  13%|█▎        | 3252/25880 [41:54<4:34:00,  1.38it/s] 
1|3253|Loss: 0.852533221244812:  13%|█▎        | 3253/25880 [41:54<4:32:02,  1.39it/s]
1|3254|Loss: 0.7935978174209595:  13%|█▎        | 3253/25880 [41:54<4:32:02,  1.39it/s]
1|3254|Loss: 0.7935978174209595:  13%|█▎        | 3254/25880 [41:55<4:21:31,  1.44it/s]
1|3255|Loss: 0.8977875709533691:  13%|█▎        | 3254/25880 [41:55<4:21:31,  1.44it/s]
1|3255|Loss: 0.8977875709533691:  13%|█▎        | 3255/25880 [41:55<4:23:19,  1.43it/s]
1|3256|Loss: 1.0806100368499756:  13%|█▎        | 3255/25880 [41:56<4:23:19,  1.43it/s]
1|3256|Loss: 1.0806100368499756:  13%|█▎        | 3256/25880 [41:56<4:18:43,  1.46it/s]
1|3257|Loss: 0.9846317172050476:  13%|█▎        | 3256/25880 [41:56<4:18:43,  1.46it/s]
1|3257|Loss: 0.9846317172050476:  13%|█▎        | 3257/25880 [41:57<4:01:25,  1.56it/s]
1|3258|Loss: 0.9369757771492004:  13%|█▎        | 3257/25880 [41:57<4:01:25,  1.56it/s]
1|3258|Loss: 0.9369757771492004:  13%|█▎        | 3258/25880 [41:57<4:07:14,  1.52it/s]
1|3259|Loss: 0.9851540923118591:  13%|█▎        | 3258/25880 [41:58<4:07:14,  1.52it/s]
1|3259|Loss: 0.9851540923118591:  13%|█▎        | 3259/25880 [41:58<4:08:56,  1.51it/s]
1|3260|Loss: 0.97650545835495:  13%|█▎        | 3259/25880 [41:58<4:08:56,  1.51it/s]  
1|3260|Loss: 0.97650545835495:  13%|█▎        | 3260/25880 [41:59<4:23:55,  1.43it/s]
1|3261|Loss: 0.7709826827049255:  13%|█▎        | 3260/25880 [41:59<4:23:55,  1.43it/s]
1|3261|Loss: 0.7709826827049255:  13%|█▎        | 3261/25880 [41:59<4:15:31,  1.48it/s]
1|3262|Loss: 0.7753656506538391:  13%|█▎        | 3261/25880 [42:00<4:15:31,  1.48it/s]
1|3262|Loss: 0.7753656506538391:  13%|█▎        | 3262/25880 [42:00<4:07:41,  1.52it/s]
1|3263|Loss: 0.881034255027771:  13%|█▎        | 3262/25880 [42:00<4:07:41,  1.52it/s] 
1|3263|Loss: 0.881034255027771:  13%|█▎        | 3263/25880 [42:01<4:14:19,  1.48it/s]
1|3264|Loss: 0.7460020780563354:  13%|█▎        | 3263/25880 [42:01<4:14:19,  1.48it/s]
1|3264|Loss: 0.7460020780563354:  13%|█▎        | 3264/25880 [42:01<4:00:57,  1.56it/s]
1|3265|Loss: 0.9023450613021851:  13%|█▎        | 3264/25880 [42:01<4:00:57,  1.56it/s]
1|3265|Loss: 0.9023450613021851:  13%|█▎        | 3265/25880 [42:02<3:52:26,  1.62it/s]
1|3266|Loss: 0.8839859366416931:  13%|█▎        | 3265/25880 [42:02<3:52:26,  1.62it/s]
1|3266|Loss: 0.8839859366416931:  13%|█▎        | 3266/25880 [42:02<4:03:24,  1.55it/s]
1|3267|Loss: 0.9296443462371826:  13%|█▎        | 3266/25880 [42:03<4:03:24,  1.55it/s]
1|3267|Loss: 0.9296443462371826:  13%|█▎        | 3267/25880 [42:03<4:30:46,  1.39it/s]
1|3268|Loss: 0.7004590630531311:  13%|█▎        | 3267/25880 [42:04<4:30:46,  1.39it/s]
1|3268|Loss: 0.7004590630531311:  13%|█▎        | 3268/25880 [42:04<4:44:40,  1.32it/s]
1|3269|Loss: 0.8250084519386292:  13%|█▎        | 3268/25880 [42:05<4:44:40,  1.32it/s]
1|3269|Loss: 0.8250084519386292:  13%|█▎        | 3269/25880 [42:05<5:04:34,  1.24it/s]
1|3270|Loss: 0.8800910711288452:  13%|█▎        | 3269/25880 [42:06<5:04:34,  1.24it/s]
1|3270|Loss: 0.8800910711288452:  13%|█▎        | 3270/25880 [42:06<5:00:48,  1.25it/s]
1|3271|Loss: 0.8402122259140015:  13%|█▎        | 3270/25880 [42:06<5:00:48,  1.25it/s]
1|3271|Loss: 0.8402122259140015:  13%|█▎        | 3271/25880 [42:07<4:54:27,  1.28it/s]
1|3272|Loss: 0.7632010579109192:  13%|█▎        | 3271/25880 [42:07<4:54:27,  1.28it/s]
1|3272|Loss: 0.7632010579109192:  13%|█▎        | 3272/25880 [42:07<4:55:53,  1.27it/s]
1|3273|Loss: 0.8338905572891235:  13%|█▎        | 3272/25880 [42:08<4:55:53,  1.27it/s]
1|3273|Loss: 0.8338905572891235:  13%|█▎        | 3273/25880 [42:08<5:04:14,  1.24it/s]
1|3274|Loss: 0.6470146179199219:  13%|█▎        | 3273/25880 [42:09<5:04:14,  1.24it/s]
1|3274|Loss: 0.6470146179199219:  13%|█▎        | 3274/25880 [42:09<4:57:01,  1.27it/s]
1|3275|Loss: 0.9727216958999634:  13%|█▎        | 3274/25880 [42:09<4:57:01,  1.27it/s]
1|3275|Loss: 0.9727216958999634:  13%|█▎        | 3275/25880 [42:10<4:37:22,  1.36it/s]
1|3276|Loss: 0.8796687722206116:  13%|█▎        | 3275/25880 [42:10<4:37:22,  1.36it/s]
1|3276|Loss: 0.8796687722206116:  13%|█▎        | 3276/25880 [42:10<4:32:46,  1.38it/s]
1|3277|Loss: 0.9847559928894043:  13%|█▎        | 3276/25880 [42:11<4:32:46,  1.38it/s]
1|3277|Loss: 0.9847559928894043:  13%|█▎        | 3277/25880 [42:11<4:43:39,  1.33it/s]
1|3278|Loss: 0.9092787504196167:  13%|█▎        | 3277/25880 [42:12<4:43:39,  1.33it/s]
1|3278|Loss: 0.9092787504196167:  13%|█▎        | 3278/25880 [42:12<4:44:09,  1.33it/s]
1|3279|Loss: 0.7094757556915283:  13%|█▎        | 3278/25880 [42:12<4:44:09,  1.33it/s]
1|3279|Loss: 0.7094757556915283:  13%|█▎        | 3279/25880 [42:13<4:50:15,  1.30it/s]
1|3280|Loss: 0.8396865129470825:  13%|█▎        | 3279/25880 [42:13<4:50:15,  1.30it/s]
1|3280|Loss: 0.8396865129470825:  13%|█▎        | 3280/25880 [42:13<4:45:36,  1.32it/s]
1|3281|Loss: 1.0624126195907593:  13%|█▎        | 3280/25880 [42:14<4:45:36,  1.32it/s]
1|3281|Loss: 1.0624126195907593:  13%|█▎        | 3281/25880 [42:14<4:51:12,  1.29it/s]
1|3282|Loss: 0.8669059872627258:  13%|█▎        | 3281/25880 [42:15<4:51:12,  1.29it/s]
1|3282|Loss: 0.8669059872627258:  13%|█▎        | 3282/25880 [42:15<4:53:46,  1.28it/s]
1|3283|Loss: 0.7857778072357178:  13%|█▎        | 3282/25880 [42:15<4:53:46,  1.28it/s]
1|3283|Loss: 0.7857778072357178:  13%|█▎        | 3283/25880 [42:16<4:49:54,  1.30it/s]
1|3284|Loss: 0.8202165961265564:  13%|█▎        | 3283/25880 [42:16<4:49:54,  1.30it/s]
1|3284|Loss: 0.8202165961265564:  13%|█▎        | 3284/25880 [42:17<4:55:07,  1.28it/s]
1|3285|Loss: 0.7962369918823242:  13%|█▎        | 3284/25880 [42:17<4:55:07,  1.28it/s]
1|3285|Loss: 0.7962369918823242:  13%|█▎        | 3285/25880 [42:17<5:00:02,  1.26it/s]
1|3286|Loss: 0.8328149318695068:  13%|█▎        | 3285/25880 [42:18<5:00:02,  1.26it/s]
1|3286|Loss: 0.8328149318695068:  13%|█▎        | 3286/25880 [42:18<4:46:27,  1.31it/s]
1|3287|Loss: 0.8765485286712646:  13%|█▎        | 3286/25880 [42:19<4:46:27,  1.31it/s]
1|3287|Loss: 0.8765485286712646:  13%|█▎        | 3287/25880 [42:19<4:50:13,  1.30it/s]
1|3288|Loss: 0.8299888372421265:  13%|█▎        | 3287/25880 [42:19<4:50:13,  1.30it/s]
1|3288|Loss: 0.8299888372421265:  13%|█▎        | 3288/25880 [42:20<4:53:12,  1.28it/s]
1|3289|Loss: 0.889590322971344:  13%|█▎        | 3288/25880 [42:20<4:53:12,  1.28it/s] 
1|3289|Loss: 0.889590322971344:  13%|█▎        | 3289/25880 [42:20<4:47:34,  1.31it/s]
1|3290|Loss: 0.8361730575561523:  13%|█▎        | 3289/25880 [42:21<4:47:34,  1.31it/s]
1|3290|Loss: 0.8361730575561523:  13%|█▎        | 3290/25880 [42:21<4:54:29,  1.28it/s]
1|3291|Loss: 0.7672120332717896:  13%|█▎        | 3290/25880 [42:22<4:54:29,  1.28it/s]
1|3291|Loss: 0.7672120332717896:  13%|█▎        | 3291/25880 [42:22<5:04:32,  1.24it/s]
1|3292|Loss: 0.9048008918762207:  13%|█▎        | 3291/25880 [42:23<5:04:32,  1.24it/s]
1|3292|Loss: 0.9048008918762207:  13%|█▎        | 3292/25880 [42:23<4:51:24,  1.29it/s]
1|3293|Loss: 0.8459634184837341:  13%|█▎        | 3292/25880 [42:23<4:51:24,  1.29it/s]
1|3293|Loss: 0.8459634184837341:  13%|█▎        | 3293/25880 [42:24<4:46:12,  1.32it/s]
1|3294|Loss: 0.7226729989051819:  13%|█▎        | 3293/25880 [42:24<4:46:12,  1.32it/s]
1|3294|Loss: 0.7226729989051819:  13%|█▎        | 3294/25880 [42:24<4:08:42,  1.51it/s]
1|3295|Loss: 0.8661369681358337:  13%|█▎        | 3294/25880 [42:24<4:08:42,  1.51it/s]
1|3295|Loss: 0.8661369681358337:  13%|█▎        | 3295/25880 [42:25<4:19:47,  1.45it/s]
1|3296|Loss: 0.8866744041442871:  13%|█▎        | 3295/25880 [42:25<4:19:47,  1.45it/s]
1|3296|Loss: 0.8866744041442871:  13%|█▎        | 3296/25880 [42:26<4:38:51,  1.35it/s]
1|3297|Loss: 0.8865464329719543:  13%|█▎        | 3296/25880 [42:26<4:38:51,  1.35it/s]
1|3297|Loss: 0.8865464329719543:  13%|█▎        | 3297/25880 [42:26<4:41:40,  1.34it/s]
1|3298|Loss: 0.7163980603218079:  13%|█▎        | 3297/25880 [42:27<4:41:40,  1.34it/s]
1|3298|Loss: 0.7163980603218079:  13%|█▎        | 3298/25880 [42:27<4:29:10,  1.40it/s]
1|3299|Loss: 0.8299708366394043:  13%|█▎        | 3298/25880 [42:27<4:29:10,  1.40it/s]
1|3299|Loss: 0.8299708366394043:  13%|█▎        | 3299/25880 [42:28<4:29:11,  1.40it/s]
1|3300|Loss: 0.9910258054733276:  13%|█▎        | 3299/25880 [42:28<4:29:11,  1.40it/s]
1|3300|Loss: 0.9910258054733276:  13%|█▎        | 3300/25880 [42:29<4:42:06,  1.33it/s]
1|3301|Loss: 0.9752298593521118:  13%|█▎        | 3300/25880 [42:29<4:42:06,  1.33it/s]
1|3301|Loss: 0.9752298593521118:  13%|█▎        | 3301/25880 [42:29<4:52:04,  1.29it/s]
1|3302|Loss: 0.8969207406044006:  13%|█▎        | 3301/25880 [42:30<4:52:04,  1.29it/s]
1|3302|Loss: 0.8969207406044006:  13%|█▎        | 3302/25880 [42:30<4:57:19,  1.27it/s]
1|3303|Loss: 0.9567515254020691:  13%|█▎        | 3302/25880 [42:31<4:57:19,  1.27it/s]
1|3303|Loss: 0.9567515254020691:  13%|█▎        | 3303/25880 [42:31<4:58:21,  1.26it/s]
1|3304|Loss: 0.8690674901008606:  13%|█▎        | 3303/25880 [42:31<4:58:21,  1.26it/s]
1|3304|Loss: 0.8690674901008606:  13%|█▎        | 3304/25880 [42:32<4:50:30,  1.30it/s]
1|3305|Loss: 0.7923464775085449:  13%|█▎        | 3304/25880 [42:32<4:50:30,  1.30it/s]
1|3305|Loss: 0.7923464775085449:  13%|█▎        | 3305/25880 [42:33<5:01:40,  1.25it/s]
1|3306|Loss: 0.8141441345214844:  13%|█▎        | 3305/25880 [42:33<5:01:40,  1.25it/s]
1|3306|Loss: 0.8141441345214844:  13%|█▎        | 3306/25880 [42:33<5:07:20,  1.22it/s]
1|3307|Loss: 0.8817206025123596:  13%|█▎        | 3306/25880 [42:34<5:07:20,  1.22it/s]
1|3307|Loss: 0.8817206025123596:  13%|█▎        | 3307/25880 [42:34<5:01:42,  1.25it/s]
1|3308|Loss: 0.7329561710357666:  13%|█▎        | 3307/25880 [42:35<5:01:42,  1.25it/s]
1|3308|Loss: 0.7329561710357666:  13%|█▎        | 3308/25880 [42:35<4:46:17,  1.31it/s]
1|3309|Loss: 0.8602094054222107:  13%|█▎        | 3308/25880 [42:35<4:46:17,  1.31it/s]
1|3309|Loss: 0.8602094054222107:  13%|█▎        | 3309/25880 [42:36<4:53:17,  1.28it/s]
1|3310|Loss: 0.8150302171707153:  13%|█▎        | 3309/25880 [42:36<4:53:17,  1.28it/s]
1|3310|Loss: 0.8150302171707153:  13%|█▎        | 3310/25880 [42:36<4:51:39,  1.29it/s]
1|3311|Loss: 0.7671552300453186:  13%|█▎        | 3310/25880 [42:37<4:51:39,  1.29it/s]
1|3311|Loss: 0.7671552300453186:  13%|█▎        | 3311/25880 [42:37<4:38:47,  1.35it/s]
1|3312|Loss: 0.830371081829071:  13%|█▎        | 3311/25880 [42:38<4:38:47,  1.35it/s] 
1|3312|Loss: 0.830371081829071:  13%|█▎        | 3312/25880 [42:38<4:25:39,  1.42it/s]
1|3313|Loss: 0.8848211765289307:  13%|█▎        | 3312/25880 [42:38<4:25:39,  1.42it/s]
1|3313|Loss: 0.8848211765289307:  13%|█▎        | 3313/25880 [42:38<4:10:25,  1.50it/s]
1|3314|Loss: 0.9957230091094971:  13%|█▎        | 3313/25880 [42:39<4:10:25,  1.50it/s]
1|3314|Loss: 0.9957230091094971:  13%|█▎        | 3314/25880 [42:39<4:10:44,  1.50it/s]
1|3315|Loss: 1.6303317546844482:  13%|█▎        | 3314/25880 [42:39<4:10:44,  1.50it/s]
1|3315|Loss: 1.6303317546844482:  13%|█▎        | 3315/25880 [42:40<4:29:50,  1.39it/s]
1|3316|Loss: 1.3145132064819336:  13%|█▎        | 3315/25880 [42:40<4:29:50,  1.39it/s]
1|3316|Loss: 1.3145132064819336:  13%|█▎        | 3316/25880 [42:41<4:44:09,  1.32it/s]
1|3317|Loss: 1.0856140851974487:  13%|█▎        | 3316/25880 [42:41<4:44:09,  1.32it/s]
1|3317|Loss: 1.0856140851974487:  13%|█▎        | 3317/25880 [42:41<4:34:57,  1.37it/s]
1|3318|Loss: 1.3117190599441528:  13%|█▎        | 3317/25880 [42:42<4:34:57,  1.37it/s]
1|3318|Loss: 1.3117190599441528:  13%|█▎        | 3318/25880 [42:42<4:22:18,  1.43it/s]
1|3319|Loss: 0.8308899402618408:  13%|█▎        | 3318/25880 [42:42<4:22:18,  1.43it/s]
1|3319|Loss: 0.8308899402618408:  13%|█▎        | 3319/25880 [42:43<4:28:29,  1.40it/s]
1|3320|Loss: 0.8525500297546387:  13%|█▎        | 3319/25880 [42:43<4:28:29,  1.40it/s]
1|3320|Loss: 0.8525500297546387:  13%|█▎        | 3320/25880 [42:43<4:24:20,  1.42it/s]
1|3321|Loss: 0.7566325664520264:  13%|█▎        | 3320/25880 [42:44<4:24:20,  1.42it/s]
1|3321|Loss: 0.7566325664520264:  13%|█▎        | 3321/25880 [42:44<4:08:00,  1.52it/s]
1|3322|Loss: 0.7661359906196594:  13%|█▎        | 3321/25880 [42:44<4:08:00,  1.52it/s]
1|3322|Loss: 0.7661359906196594:  13%|█▎        | 3322/25880 [42:45<4:11:06,  1.50it/s]
1|3323|Loss: 0.9454442858695984:  13%|█▎        | 3322/25880 [42:45<4:11:06,  1.50it/s]
1|3323|Loss: 0.9454442858695984:  13%|█▎        | 3323/25880 [42:45<4:10:38,  1.50it/s]
1|3324|Loss: 0.9052824974060059:  13%|█▎        | 3323/25880 [42:46<4:10:38,  1.50it/s]
1|3324|Loss: 0.9052824974060059:  13%|█▎        | 3324/25880 [42:46<4:00:31,  1.56it/s]
1|3325|Loss: 0.8527141809463501:  13%|█▎        | 3324/25880 [42:46<4:00:31,  1.56it/s]
1|3325|Loss: 0.8527141809463501:  13%|█▎        | 3325/25880 [42:47<3:56:26,  1.59it/s]
1|3326|Loss: 0.9252672791481018:  13%|█▎        | 3325/25880 [42:47<3:56:26,  1.59it/s]
1|3326|Loss: 0.9252672791481018:  13%|█▎        | 3326/25880 [42:47<3:55:45,  1.59it/s]
1|3327|Loss: 0.8833678960800171:  13%|█▎        | 3326/25880 [42:48<3:55:45,  1.59it/s]
1|3327|Loss: 0.8833678960800171:  13%|█▎        | 3327/25880 [42:48<4:14:10,  1.48it/s]
1|3328|Loss: 0.8764504194259644:  13%|█▎        | 3327/25880 [42:48<4:14:10,  1.48it/s]
1|3328|Loss: 0.8764504194259644:  13%|█▎        | 3328/25880 [42:48<4:02:16,  1.55it/s]
1|3329|Loss: 0.9354700446128845:  13%|█▎        | 3328/25880 [42:49<4:02:16,  1.55it/s]
1|3329|Loss: 0.9354700446128845:  13%|█▎        | 3329/25880 [42:49<4:11:49,  1.49it/s]
1|3330|Loss: 0.8474135994911194:  13%|█▎        | 3329/25880 [42:50<4:11:49,  1.49it/s]
1|3330|Loss: 0.8474135994911194:  13%|█▎        | 3330/25880 [42:50<4:00:42,  1.56it/s]
1|3331|Loss: 0.9643917679786682:  13%|█▎        | 3330/25880 [42:50<4:00:42,  1.56it/s]
1|3331|Loss: 0.9643917679786682:  13%|█▎        | 3331/25880 [42:50<3:45:32,  1.67it/s]
1|3332|Loss: 1.1207754611968994:  13%|█▎        | 3331/25880 [42:51<3:45:32,  1.67it/s]
1|3332|Loss: 1.1207754611968994:  13%|█▎        | 3332/25880 [42:51<3:52:16,  1.62it/s]
1|3333|Loss: 0.8622962236404419:  13%|█▎        | 3332/25880 [42:51<3:52:16,  1.62it/s]
1|3333|Loss: 0.8622962236404419:  13%|█▎        | 3333/25880 [42:52<4:03:39,  1.54it/s]
1|3334|Loss: 0.8853890299797058:  13%|█���        | 3333/25880 [42:52<4:03:39,  1.54it/s]
1|3334|Loss: 0.8853890299797058:  13%|█▎        | 3334/25880 [42:52<4:04:17,  1.54it/s]
1|3335|Loss: 0.9987143278121948:  13%|█▎        | 3334/25880 [42:53<4:04:17,  1.54it/s]
1|3335|Loss: 0.9987143278121948:  13%|█▎        | 3335/25880 [42:53<4:09:08,  1.51it/s]
1|3336|Loss: 0.8903113007545471:  13%|█▎        | 3335/25880 [42:53<4:09:08,  1.51it/s]
1|3336|Loss: 0.8903113007545471:  13%|█▎        | 3336/25880 [42:54<4:13:25,  1.48it/s]
1|3337|Loss: 0.8998734354972839:  13%|█▎        | 3336/25880 [42:54<4:13:25,  1.48it/s]
1|3337|Loss: 0.8998734354972839:  13%|█▎        | 3337/25880 [42:55<4:32:37,  1.38it/s]
1|3338|Loss: 0.6965352296829224:  13%|█▎        | 3337/25880 [42:55<4:32:37,  1.38it/s]
1|3338|Loss: 0.6965352296829224:  13%|█▎        | 3338/25880 [42:55<4:29:22,  1.39it/s]
1|3339|Loss: 0.9688613414764404:  13%|█▎        | 3338/25880 [42:56<4:29:22,  1.39it/s]
1|3339|Loss: 0.9688613414764404:  13%|█▎        | 3339/25880 [42:56<4:10:54,  1.50it/s]
1|3340|Loss: 0.9323781728744507:  13%|█▎        | 3339/25880 [42:56<4:10:54,  1.50it/s]
1|3340|Loss: 0.9323781728744507:  13%|█▎        | 3340/25880 [42:56<4:04:59,  1.53it/s]
1|3341|Loss: 0.8527522683143616:  13%|█▎        | 3340/25880 [42:57<4:04:59,  1.53it/s]
1|3341|Loss: 0.8527522683143616:  13%|█▎        | 3341/25880 [42:57<3:56:08,  1.59it/s]
1|3342|Loss: 0.9268226623535156:  13%|█▎        | 3341/25880 [42:57<3:56:08,  1.59it/s]
1|3342|Loss: 0.9268226623535156:  13%|█▎        | 3342/25880 [42:58<4:19:41,  1.45it/s]
1|3343|Loss: 0.908251941204071:  13%|█▎        | 3342/25880 [42:58<4:19:41,  1.45it/s] 
1|3343|Loss: 0.908251941204071:  13%|█▎        | 3343/25880 [42:59<4:25:32,  1.41it/s]
1|3344|Loss: 1.0001755952835083:  13%|█▎        | 3343/25880 [42:59<4:25:32,  1.41it/s]
1|3344|Loss: 1.0001755952835083:  13%|█▎        | 3344/25880 [42:59<4:24:50,  1.42it/s]
1|3345|Loss: 0.8332419395446777:  13%|█▎        | 3344/25880 [43:00<4:24:50,  1.42it/s]
1|3345|Loss: 0.8332419395446777:  13%|█▎        | 3345/25880 [43:00<4:35:39,  1.36it/s]
1|3346|Loss: 0.8175119161605835:  13%|█▎        | 3345/25880 [43:01<4:35:39,  1.36it/s]
1|3346|Loss: 0.8175119161605835:  13%|█▎        | 3346/25880 [43:01<4:36:37,  1.36it/s]
1|3347|Loss: 0.7432792782783508:  13%|█▎        | 3346/25880 [43:01<4:36:37,  1.36it/s]
1|3347|Loss: 0.7432792782783508:  13%|█▎        | 3347/25880 [43:02<4:33:13,  1.37it/s]
1|3348|Loss: 0.8838208317756653:  13%|█▎        | 3347/25880 [43:02<4:33:13,  1.37it/s]
1|3348|Loss: 0.8838208317756653:  13%|█▎        | 3348/25880 [43:02<4:33:00,  1.38it/s]
1|3349|Loss: 0.8756970167160034:  13%|█▎        | 3348/25880 [43:03<4:33:00,  1.38it/s]
1|3349|Loss: 0.8756970167160034:  13%|█▎        | 3349/25880 [43:03<4:33:42,  1.37it/s]
1|3350|Loss: 0.869123637676239:  13%|█▎        | 3349/25880 [43:03<4:33:42,  1.37it/s] 
1|3350|Loss: 0.869123637676239:  13%|█▎        | 3350/25880 [43:04<4:34:28,  1.37it/s]
1|3351|Loss: 0.9199133515357971:  13%|█▎        | 3350/25880 [43:04<4:34:28,  1.37it/s]
1|3351|Loss: 0.9199133515357971:  13%|█▎        | 3351/25880 [43:05<4:39:27,  1.34it/s]
1|3352|Loss: 0.8836847543716431:  13%|█▎        | 3351/25880 [43:05<4:39:27,  1.34it/s]
1|3352|Loss: 0.8836847543716431:  13%|█▎        | 3352/25880 [43:05<4:39:04,  1.35it/s]
1|3353|Loss: 0.8415215015411377:  13%|█▎        | 3352/25880 [43:06<4:39:04,  1.35it/s]
1|3353|Loss: 0.8415215015411377:  13%|█▎        | 3353/25880 [43:06<4:20:59,  1.44it/s]
1|3354|Loss: 0.8968238830566406:  13%|█▎        | 3353/25880 [43:06<4:20:59,  1.44it/s]
1|3354|Loss: 0.8968238830566406:  13%|█▎        | 3354/25880 [43:06<4:10:44,  1.50it/s]
1|3355|Loss: 0.938054621219635:  13%|█▎        | 3354/25880 [43:07<4:10:44,  1.50it/s] 
1|3355|Loss: 0.938054621219635:  13%|█▎        | 3355/25880 [43:07<4:07:12,  1.52it/s]
1|3356|Loss: 0.9118753671646118:  13%|█▎        | 3355/25880 [43:07<4:07:12,  1.52it/s]
1|3356|Loss: 0.9118753671646118:  13%|█▎        | 3356/25880 [43:08<4:10:33,  1.50it/s]
1|3357|Loss: 0.8518555164337158:  13%|█▎        | 3356/25880 [43:08<4:10:33,  1.50it/s]
1|3357|Loss: 0.8518555164337158:  13%|█▎        | 3357/25880 [43:09<4:25:13,  1.42it/s]
1|3358|Loss: 0.9414541125297546:  13%|█▎        | 3357/25880 [43:09<4:25:13,  1.42it/s]
1|3358|Loss: 0.9414541125297546:  13%|█▎        | 3358/25880 [43:09<4:17:10,  1.46it/s]
1|3359|Loss: 0.8892590403556824:  13%|█▎        | 3358/25880 [43:10<4:17:10,  1.46it/s]
1|3359|Loss: 0.8892590403556824:  13%|█▎        | 3359/25880 [43:10<4:19:22,  1.45it/s]
1|3360|Loss: 0.9068700075149536:  13%|█▎        | 3359/25880 [43:10<4:19:22,  1.45it/s]
1|3360|Loss: 0.9068700075149536:  13%|█▎        | 3360/25880 [43:11<4:32:56,  1.38it/s]
1|3361|Loss: 0.8443514108657837:  13%|█▎        | 3360/25880 [43:11<4:32:56,  1.38it/s]
1|3361|Loss: 0.8443514108657837:  13%|█▎        | 3361/25880 [43:11<4:34:58,  1.36it/s]
1|3362|Loss: 0.8631790280342102:  13%|█▎        | 3361/25880 [43:12<4:34:58,  1.36it/s]
1|3362|Loss: 0.8631790280342102:  13%|█▎        | 3362/25880 [43:12<4:34:22,  1.37it/s]
1|3363|Loss: 0.8764911890029907:  13%|█▎        | 3362/25880 [43:13<4:34:22,  1.37it/s]
1|3363|Loss: 0.8764911890029907:  13%|█▎        | 3363/25880 [43:13<4:33:54,  1.37it/s]
1|3364|Loss: 0.7852224111557007:  13%|█▎        | 3363/25880 [43:13<4:33:54,  1.37it/s]
1|3364|Loss: 0.7852224111557007:  13%|█▎        | 3364/25880 [43:14<4:42:46,  1.33it/s]
1|3365|Loss: 0.9775651693344116:  13%|█▎        | 3364/25880 [43:14<4:42:46,  1.33it/s]
1|3365|Loss: 0.9775651693344116:  13%|█▎        | 3365/25880 [43:14<4:42:04,  1.33it/s]
1|3366|Loss: 0.8477327823638916:  13%|█▎        | 3365/25880 [43:15<4:42:04,  1.33it/s]
1|3366|Loss: 0.8477327823638916:  13%|█▎        | 3366/25880 [43:15<4:45:26,  1.31it/s]
1|3367|Loss: 0.9936171770095825:  13%|█▎        | 3366/25880 [43:16<4:45:26,  1.31it/s]
1|3367|Loss: 0.9936171770095825:  13%|█▎        | 3367/25880 [43:16<4:33:18,  1.37it/s]
1|3368|Loss: 0.8190439939498901:  13%|█▎        | 3367/25880 [43:16<4:33:18,  1.37it/s]
1|3368|Loss: 0.8190439939498901:  13%|█▎        | 3368/25880 [43:17<4:48:15,  1.30it/s]
1|3369|Loss: 0.8687934875488281:  13%|█▎        | 3368/25880 [43:17<4:48:15,  1.30it/s]
1|3369|Loss: 0.8687934875488281:  13%|█▎        | 3369/25880 [43:18<4:45:16,  1.32it/s]
1|3370|Loss: 0.9176495671272278:  13%|█▎        | 3369/25880 [43:18<4:45:16,  1.32it/s]
1|3370|Loss: 0.9176495671272278:  13%|█▎        | 3370/25880 [43:18<4:38:34,  1.35it/s]
1|3371|Loss: 0.8610780239105225:  13%|█▎        | 3370/25880 [43:19<4:38:34,  1.35it/s]
1|3371|Loss: 0.8610780239105225:  13%|█▎        | 3371/25880 [43:19<4:43:11,  1.32it/s]
1|3372|Loss: 0.9253243207931519:  13%|█▎        | 3371/25880 [43:19<4:43:11,  1.32it/s]
1|3372|Loss: 0.9253243207931519:  13%|█▎        | 3372/25880 [43:20<4:47:15,  1.31it/s]
1|3373|Loss: 0.9323713183403015:  13%|█▎        | 3372/25880 [43:20<4:47:15,  1.31it/s]
1|3373|Loss: 0.9323713183403015:  13%|█▎        | 3373/25880 [43:21<4:46:38,  1.31it/s]
1|3374|Loss: 0.9016101956367493:  13%|█▎        | 3373/25880 [43:21<4:46:38,  1.31it/s]
1|3374|Loss: 0.9016101956367493:  13%|█▎        | 3374/25880 [43:21<4:41:44,  1.33it/s]
1|3375|Loss: 0.9457798004150391:  13%|█▎        | 3374/25880 [43:22<4:41:44,  1.33it/s]
1|3375|Loss: 0.9457798004150391:  13%|█▎        | 3375/25880 [43:22<4:44:56,  1.32it/s]
1|3376|Loss: 0.856142520904541:  13%|█▎        | 3375/25880 [43:22<4:44:56,  1.32it/s] 
1|3376|Loss: 0.856142520904541:  13%|█▎        | 3376/25880 [43:23<4:33:00,  1.37it/s]
1|3377|Loss: 0.8488619923591614:  13%|█▎        | 3376/25880 [43:23<4:33:00,  1.37it/s]
1|3377|Loss: 0.8488619923591614:  13%|█▎        | 3377/25880 [43:24<4:51:41,  1.29it/s]
1|3378|Loss: 0.8526535630226135:  13%|█▎        | 3377/25880 [43:24<4:51:41,  1.29it/s]
1|3378|Loss: 0.8526535630226135:  13%|█▎        | 3378/25880 [43:24<4:39:21,  1.34it/s]
1|3379|Loss: 0.9249690175056458:  13%|█▎        | 3378/25880 [43:25<4:39:21,  1.34it/s]
1|3379|Loss: 0.9249690175056458:  13%|█▎        | 3379/25880 [43:25<4:31:06,  1.38it/s]
1|3380|Loss: 0.9218093752861023:  13%|█▎        | 3379/25880 [43:25<4:31:06,  1.38it/s]
1|3380|Loss: 0.9218093752861023:  13%|█▎        | 3380/25880 [43:26<4:44:16,  1.32it/s]
1|3381|Loss: 0.9576531052589417:  13%|█▎        | 3380/25880 [43:26<4:44:16,  1.32it/s]
1|3381|Loss: 0.9576531052589417:  13%|█▎        | 3381/25880 [43:26<4:34:53,  1.36it/s]
1|3382|Loss: 0.8934329152107239:  13%|█▎        | 3381/25880 [43:27<4:34:53,  1.36it/s]
1|3382|Loss: 0.8934329152107239:  13%|█▎        | 3382/25880 [43:27<4:33:06,  1.37it/s]
1|3383|Loss: 0.8069100975990295:  13%|█▎        | 3382/25880 [43:28<4:33:06,  1.37it/s]
1|3383|Loss: 0.8069100975990295:  13%|█▎        | 3383/25880 [43:28<4:34:29,  1.37it/s]
1|3384|Loss: 0.7994755506515503:  13%|█▎        | 3383/25880 [43:28<4:34:29,  1.37it/s]
1|3384|Loss: 0.7994755506515503:  13%|█▎        | 3384/25880 [43:29<4:24:22,  1.42it/s]
1|3385|Loss: 0.9120246767997742:  13%|█▎        | 3384/25880 [43:29<4:24:22,  1.42it/s]
1|3385|Loss: 0.9120246767997742:  13%|█▎        | 3385/25880 [43:29<4:14:37,  1.47it/s]
1|3386|Loss: 0.9834553003311157:  13%|█▎        | 3385/25880 [43:30<4:14:37,  1.47it/s]
1|3386|Loss: 0.9834553003311157:  13%|█▎        | 3386/25880 [43:30<4:19:29,  1.44it/s]
1|3387|Loss: 0.8662852048873901:  13%|█▎        | 3386/25880 [43:30<4:19:29,  1.44it/s]
1|3387|Loss: 0.8662852048873901:  13%|█▎        | 3387/25880 [43:31<4:31:15,  1.38it/s]
1|3388|Loss: 0.8576581478118896:  13%|█▎        | 3387/25880 [43:31<4:31:15,  1.38it/s]
1|3388|Loss: 0.8576581478118896:  13%|█▎        | 3388/25880 [43:31<4:33:39,  1.37it/s]
1|3389|Loss: 1.0417505502700806:  13%|█▎        | 3388/25880 [43:32<4:33:39,  1.37it/s]
1|3389|Loss: 1.0417505502700806:  13%|█▎        | 3389/25880 [43:32<4:15:15,  1.47it/s]
1|3390|Loss: 0.9581670165061951:  13%|█▎        | 3389/25880 [43:32<4:15:15,  1.47it/s]
1|3390|Loss: 0.9581670165061951:  13%|█▎        | 3390/25880 [43:33<4:07:42,  1.51it/s]
1|3391|Loss: 0.8412117958068848:  13%|█▎        | 3390/25880 [43:33<4:07:42,  1.51it/s]
1|3391|Loss: 0.8412117958068848:  13%|█▎        | 3391/25880 [43:33<4:15:56,  1.46it/s]
1|3392|Loss: 0.8120669722557068:  13%|█▎        | 3391/25880 [43:34<4:15:56,  1.46it/s]
1|3392|Loss: 0.8120669722557068:  13%|█▎        | 3392/25880 [43:34<4:21:44,  1.43it/s]
1|3393|Loss: 1.0147162675857544:  13%|█▎        | 3392/25880 [43:34<4:21:44,  1.43it/s]
1|3393|Loss: 1.0147162675857544:  13%|█▎        | 3393/25880 [43:35<4:16:56,  1.46it/s]
1|3394|Loss: 0.8443676233291626:  13%|█▎        | 3393/25880 [43:35<4:16:56,  1.46it/s]
1|3394|Loss: 0.8443676233291626:  13%|█▎        | 3394/25880 [43:35<4:17:43,  1.45it/s]
1|3395|Loss: 0.8387590646743774:  13%|█▎        | 3394/25880 [43:36<4:17:43,  1.45it/s]
1|3395|Loss: 0.8387590646743774:  13%|█▎        | 3395/25880 [43:36<4:10:47,  1.49it/s]
1|3396|Loss: 0.8552650809288025:  13%|█▎        | 3395/25880 [43:36<4:10:47,  1.49it/s]
1|3396|Loss: 0.8552650809288025:  13%|█▎        | 3396/25880 [43:37<4:12:29,  1.48it/s]
1|3397|Loss: 0.8038876056671143:  13%|█▎        | 3396/25880 [43:37<4:12:29,  1.48it/s]
1|3397|Loss: 0.8038876056671143:  13%|█▎        | 3397/25880 [43:38<4:31:32,  1.38it/s]
1|3398|Loss: 0.8981471061706543:  13%|█▎        | 3397/25880 [43:38<4:31:32,  1.38it/s]
1|3398|Loss: 0.8981471061706543:  13%|█▎        | 3398/25880 [43:38<4:24:04,  1.42it/s]
1|3399|Loss: 1.1072813272476196:  13%|█▎        | 3398/25880 [43:39<4:24:04,  1.42it/s]
1|3399|Loss: 1.1072813272476196:  13%|█▎        | 3399/25880 [43:39<4:35:28,  1.36it/s]
1|3400|Loss: 0.8962887525558472:  13%|█▎        | 3399/25880 [43:40<4:35:28,  1.36it/s]
1|3400|Loss: 0.8962887525558472:  13%|█▎        | 3400/25880 [43:40<4:49:52,  1.29it/s]
1|3401|Loss: 0.8520186543464661:  13%|█▎        | 3400/25880 [43:40<4:49:52,  1.29it/s]
1|3401|Loss: 0.8520186543464661:  13%|█▎        | 3401/25880 [43:41<4:49:15,  1.30it/s]
1|3402|Loss: 0.7882552742958069:  13%|█▎        | 3401/25880 [43:41<4:49:15,  1.30it/s]
1|3402|Loss: 0.7882552742958069:  13%|█▎        | 3402/25880 [43:41<4:44:51,  1.32it/s]
1|3403|Loss: 0.8630695939064026:  13%|█▎        | 3402/25880 [43:42<4:44:51,  1.32it/s]
1|3403|Loss: 0.8630695939064026:  13%|█▎        | 3403/25880 [43:42<4:47:41,  1.30it/s]
1|3404|Loss: 0.8639501929283142:  13%|█▎        | 3403/25880 [43:43<4:47:41,  1.30it/s]
1|3404|Loss: 0.8639501929283142:  13%|█▎        | 3404/25880 [43:43<4:24:55,  1.41it/s]
1|3405|Loss: 0.7384994029998779:  13%|█▎        | 3404/25880 [43:43<4:24:55,  1.41it/s]
1|3405|Loss: 0.7384994029998779:  13%|█▎        | 3405/25880 [43:43<4:06:42,  1.52it/s]
1|3406|Loss: 0.8369126319885254:  13%|█▎        | 3405/25880 [43:44<4:06:42,  1.52it/s]
1|3406|Loss: 0.8369126319885254:  13%|█▎        | 3406/25880 [43:44<4:08:00,  1.51it/s]
1|3407|Loss: 0.8728699088096619:  13%|█▎        | 3406/25880 [43:44<4:08:00,  1.51it/s]
1|3407|Loss: 0.8728699088096619:  13%|█▎        | 3407/25880 [43:45<4:15:58,  1.46it/s]
1|3408|Loss: 0.8609357476234436:  13%|█▎        | 3407/25880 [43:45<4:15:58,  1.46it/s]
1|3408|Loss: 0.8609357476234436:  13%|█▎        | 3408/25880 [43:45<4:22:34,  1.43it/s]
1|3409|Loss: 0.898607075214386:  13%|█▎        | 3408/25880 [43:46<4:22:34,  1.43it/s] 
1|3409|Loss: 0.898607075214386:  13%|█▎        | 3409/25880 [43:46<4:18:35,  1.45it/s]
1|3410|Loss: 0.811080813407898:  13%|█▎        | 3409/25880 [43:47<4:18:35,  1.45it/s]
1|3410|Loss: 0.811080813407898:  13%|█▎        | 3410/25880 [43:47<4:30:15,  1.39it/s]
1|3411|Loss: 0.8226068615913391:  13%|█▎        | 3410/25880 [43:47<4:30:15,  1.39it/s]
1|3411|Loss: 0.8226068615913391:  13%|█▎        | 3411/25880 [43:48<4:34:32,  1.36it/s]
1|3412|Loss: 0.7373986840248108:  13%|█▎        | 3411/25880 [43:48<4:34:32,  1.36it/s]
1|3412|Loss: 0.7373986840248108:  13%|█▎        | 3412/25880 [43:48<4:32:09,  1.38it/s]
1|3413|Loss: 0.9385232925415039:  13%|█▎        | 3412/25880 [43:49<4:32:09,  1.38it/s]
1|3413|Loss: 0.9385232925415039:  13%|█▎        | 3413/25880 [43:49<4:19:10,  1.44it/s]
1|3414|Loss: 0.8616519570350647:  13%|█▎        | 3413/25880 [43:49<4:19:10,  1.44it/s]
1|3414|Loss: 0.8616519570350647:  13%|█▎        | 3414/25880 [43:50<4:20:02,  1.44it/s]
1|3415|Loss: 0.7890366315841675:  13%|█▎        | 3414/25880 [43:50<4:20:02,  1.44it/s]
1|3415|Loss: 0.7890366315841675:  13%|█▎        | 3415/25880 [43:50<4:28:51,  1.39it/s]
1|3416|Loss: 0.9651826024055481:  13%|█▎        | 3415/25880 [43:51<4:28:51,  1.39it/s]
1|3416|Loss: 0.9651826024055481:  13%|█▎        | 3416/25880 [43:51<4:21:59,  1.43it/s]
1|3417|Loss: 0.8748681545257568:  13%|█▎        | 3416/25880 [43:51<4:21:59,  1.43it/s]
1|3417|Loss: 0.8748681545257568:  13%|█▎        | 3417/25880 [43:52<4:12:18,  1.48it/s]
1|3418|Loss: 0.9570211172103882:  13%|█▎        | 3417/25880 [43:52<4:12:18,  1.48it/s]
1|3418|Loss: 0.9570211172103882:  13%|█▎        | 3418/25880 [43:52<4:05:39,  1.52it/s]
1|3419|Loss: 0.9371099472045898:  13%|█▎        | 3418/25880 [43:53<4:05:39,  1.52it/s]
1|3419|Loss: 0.9371099472045898:  13%|█▎        | 3419/25880 [43:53<4:03:41,  1.54it/s]
1|3420|Loss: 0.7856574058532715:  13%|█▎        | 3419/25880 [43:53<4:03:41,  1.54it/s]
1|3420|Loss: 0.7856574058532715:  13%|█▎        | 3420/25880 [43:54<4:07:41,  1.51it/s]
1|3421|Loss: 0.8660844564437866:  13%|█▎        | 3420/25880 [43:54<4:07:41,  1.51it/s]
1|3421|Loss: 0.8660844564437866:  13%|█▎        | 3421/25880 [43:54<4:11:14,  1.49it/s]
1|3422|Loss: 0.8081185817718506:  13%|█▎        | 3421/25880 [43:55<4:11:14,  1.49it/s]
1|3422|Loss: 0.8081185817718506:  13%|█▎        | 3422/25880 [43:55<3:56:17,  1.58it/s]
1|3423|Loss: 0.8958911299705505:  13%|█▎        | 3422/25880 [43:55<3:56:17,  1.58it/s]
1|3423|Loss: 0.8958911299705505:  13%|█▎        | 3423/25880 [43:56<3:59:30,  1.56it/s]
1|3424|Loss: 0.9622607827186584:  13%|█▎        | 3423/25880 [43:56<3:59:30,  1.56it/s]
1|3424|Loss: 0.9622607827186584:  13%|█▎        | 3424/25880 [43:56<4:08:30,  1.51it/s]
1|3425|Loss: 1.0640455484390259:  13%|█▎        | 3424/25880 [43:57<4:08:30,  1.51it/s]
1|3425|Loss: 1.0640455484390259:  13%|█▎        | 3425/25880 [43:57<4:36:19,  1.35it/s]
1|3426|Loss: 0.8116810321807861:  13%|█▎        | 3425/25880 [43:58<4:36:19,  1.35it/s]
1|3426|Loss: 0.8116810321807861:  13%|█▎        | 3426/25880 [43:58<4:32:23,  1.37it/s]
1|3427|Loss: 0.9678810238838196:  13%|█▎        | 3426/25880 [43:58<4:32:23,  1.37it/s]
1|3427|Loss: 0.9678810238838196:  13%|█▎        | 3427/25880 [43:59<4:23:01,  1.42it/s]
1|3428|Loss: 0.7441218495368958:  13%|█▎        | 3427/25880 [43:59<4:23:01,  1.42it/s]
1|3428|Loss: 0.7441218495368958:  13%|█▎        | 3428/25880 [43:59<4:24:46,  1.41it/s]
1|3429|Loss: 0.6557111740112305:  13%|█▎        | 3428/25880 [44:00<4:24:46,  1.41it/s]
1|3429|Loss: 0.6557111740112305:  13%|█▎        | 3429/25880 [44:00<4:37:43,  1.35it/s]
1|3430|Loss: 0.9132289886474609:  13%|█▎        | 3429/25880 [44:00<4:37:43,  1.35it/s]
1|3430|Loss: 0.9132289886474609:  13%|█▎        | 3430/25880 [44:01<4:29:38,  1.39it/s]
1|3431|Loss: 0.9027093648910522:  13%|█▎        | 3430/25880 [44:01<4:29:38,  1.39it/s]
1|3431|Loss: 0.9027093648910522:  13%|█▎        | 3431/25880 [44:01<4:03:26,  1.54it/s]
1|3432|Loss: 0.8100801110267639:  13%|█▎        | 3431/25880 [44:02<4:03:26,  1.54it/s]
1|3432|Loss: 0.8100801110267639:  13%|█▎        | 3432/25880 [44:02<4:02:33,  1.54it/s]
1|3433|Loss: 0.724071204662323:  13%|█▎        | 3432/25880 [44:02<4:02:33,  1.54it/s] 
1|3433|Loss: 0.724071204662323:  13%|█▎        | 3433/25880 [44:03<4:10:56,  1.49it/s]
1|3434|Loss: 0.8790538907051086:  13%|█▎        | 3433/25880 [44:03<4:10:56,  1.49it/s]
1|3434|Loss: 0.8790538907051086:  13%|█▎        | 3434/25880 [44:03<4:23:55,  1.42it/s]
1|3435|Loss: 0.9251973032951355:  13%|█▎        | 3434/25880 [44:04<4:23:55,  1.42it/s]
1|3435|Loss: 0.9251973032951355:  13%|█▎        | 3435/25880 [44:04<4:29:26,  1.39it/s]
1|3436|Loss: 0.9106406569480896:  13%|█▎        | 3435/25880 [44:05<4:29:26,  1.39it/s]
1|3436|Loss: 0.9106406569480896:  13%|█▎        | 3436/25880 [44:05<4:28:40,  1.39it/s]
1|3437|Loss: 0.8293361663818359:  13%|█▎        | 3436/25880 [44:05<4:28:40,  1.39it/s]
1|3437|Loss: 0.8293361663818359:  13%|█▎        | 3437/25880 [44:06<4:34:13,  1.36it/s]
1|3438|Loss: 0.75197833776474:  13%|█▎        | 3437/25880 [44:06<4:34:13,  1.36it/s]  
1|3438|Loss: 0.75197833776474:  13%|█▎        | 3438/25880 [44:07<4:58:11,  1.25it/s]
1|3439|Loss: 0.8279520273208618:  13%|█▎        | 3438/25880 [44:07<4:58:11,  1.25it/s]
1|3439|Loss: 0.8279520273208618:  13%|█▎        | 3439/25880 [44:07<4:55:14,  1.27it/s]
1|3440|Loss: 0.8927544951438904:  13%|█▎        | 3439/25880 [44:08<4:55:14,  1.27it/s]
1|3440|Loss: 0.8927544951438904:  13%|█▎        | 3440/25880 [44:08<4:48:13,  1.30it/s]
1|3441|Loss: 0.7629175186157227:  13%|█▎        | 3440/25880 [44:08<4:48:13,  1.30it/s]
1|3441|Loss: 0.7629175186157227:  13%|█▎        | 3441/25880 [44:09<4:29:52,  1.39it/s]
1|3442|Loss: 0.8360475897789001:  13%|█▎        | 3441/25880 [44:09<4:29:52,  1.39it/s]
1|3442|Loss: 0.8360475897789001:  13%|█▎        | 3442/25880 [44:09<4:24:39,  1.41it/s]
1|3443|Loss: 0.782454252243042:  13%|█▎        | 3442/25880 [44:10<4:24:39,  1.41it/s] 
1|3443|Loss: 0.782454252243042:  13%|█▎        | 3443/25880 [44:10<4:23:15,  1.42it/s]
1|3444|Loss: 0.9545331001281738:  13%|█▎        | 3443/25880 [44:10<4:23:15,  1.42it/s]
1|3444|Loss: 0.9545331001281738:  13%|█▎        | 3444/25880 [44:11<4:25:23,  1.41it/s]
1|3445|Loss: 0.8517459034919739:  13%|█▎        | 3444/25880 [44:11<4:25:23,  1.41it/s]
1|3445|Loss: 0.8517459034919739:  13%|█▎        | 3445/25880 [44:11<4:25:19,  1.41it/s]
1|3446|Loss: 0.9296510219573975:  13%|█▎        | 3445/25880 [44:12<4:25:19,  1.41it/s]
1|3446|Loss: 0.9296510219573975:  13%|█▎        | 3446/25880 [44:12<4:27:44,  1.40it/s]
1|3447|Loss: 0.8398978114128113:  13%|█▎        | 3446/25880 [44:13<4:27:44,  1.40it/s]
1|3447|Loss: 0.8398978114128113:  13%|█▎        | 3447/25880 [44:13<4:18:03,  1.45it/s]
1|3448|Loss: 0.8607771396636963:  13%|█▎        | 3447/25880 [44:13<4:18:03,  1.45it/s]
1|3448|Loss: 0.8607771396636963:  13%|█▎        | 3448/25880 [44:13<4:06:35,  1.52it/s]
1|3449|Loss: 0.9165345430374146:  13%|█▎        | 3448/25880 [44:14<4:06:35,  1.52it/s]
1|3449|Loss: 0.9165345430374146:  13%|█▎        | 3449/25880 [44:14<4:09:23,  1.50it/s]
1|3450|Loss: 0.8652918338775635:  13%|█▎        | 3449/25880 [44:15<4:09:23,  1.50it/s]
1|3450|Loss: 0.8652918338775635:  13%|█▎        | 3450/25880 [44:15<4:15:54,  1.46it/s]
1|3451|Loss: 0.8788804411888123:  13%|█▎        | 3450/25880 [44:15<4:15:54,  1.46it/s]
1|3451|Loss: 0.8788804411888123:  13%|█▎        | 3451/25880 [44:16<4:35:10,  1.36it/s]
1|3452|Loss: 1.0462039709091187:  13%|█▎        | 3451/25880 [44:16<4:35:10,  1.36it/s]
1|3452|Loss: 1.0462039709091187:  13%|█▎        | 3452/25880 [44:16<4:36:10,  1.35it/s]
1|3453|Loss: 0.8343902826309204:  13%|█▎        | 3452/25880 [44:17<4:36:10,  1.35it/s]
1|3453|Loss: 0.8343902826309204:  13%|█▎        | 3453/25880 [44:17<4:43:18,  1.32it/s]
1|3454|Loss: 0.8225147724151611:  13%|█▎        | 3453/25880 [44:18<4:43:18,  1.32it/s]
1|3454|Loss: 0.8225147724151611:  13%|█▎        | 3454/25880 [44:18<4:42:32,  1.32it/s]
1|3455|Loss: 0.988854706287384:  13%|█▎        | 3454/25880 [44:18<4:42:32,  1.32it/s] 
1|3455|Loss: 0.988854706287384:  13%|█▎        | 3455/25880 [44:19<4:29:30,  1.39it/s]
1|3456|Loss: 0.9642648100852966:  13%|█▎        | 3455/25880 [44:19<4:29:30,  1.39it/s]
1|3456|Loss: 0.9642648100852966:  13%|█▎        | 3456/25880 [44:19<4:12:35,  1.48it/s]
1|3457|Loss: 0.8839818835258484:  13%|█▎        | 3456/25880 [44:20<4:12:35,  1.48it/s]
1|3457|Loss: 0.8839818835258484:  13%|█▎        | 3457/25880 [44:20<4:21:19,  1.43it/s]
1|3458|Loss: 0.925557017326355:  13%|█▎        | 3457/25880 [44:20<4:21:19,  1.43it/s] 
1|3458|Loss: 0.925557017326355:  13%|█▎        | 3458/25880 [44:21<4:39:49,  1.34it/s]
1|3459|Loss: 0.9118373394012451:  13%|█▎        | 3458/25880 [44:21<4:39:49,  1.34it/s]
1|3459|Loss: 0.9118373394012451:  13%|█▎        | 3459/25880 [44:22<4:47:43,  1.30it/s]
1|3460|Loss: 0.8601487874984741:  13%|█▎        | 3459/25880 [44:22<4:47:43,  1.30it/s]
1|3460|Loss: 0.8601487874984741:  13%|█▎        | 3460/25880 [44:22<4:45:23,  1.31it/s]
1|3461|Loss: 0.7980982065200806:  13%|█▎        | 3460/25880 [44:23<4:45:23,  1.31it/s]
1|3461|Loss: 0.7980982065200806:  13%|█▎        | 3461/25880 [44:23<4:39:13,  1.34it/s]
1|3462|Loss: 0.8111902475357056:  13%|█▎        | 3461/25880 [44:24<4:39:13,  1.34it/s]
1|3462|Loss: 0.8111902475357056:  13%|█▎        | 3462/25880 [44:24<4:41:28,  1.33it/s]
1|3463|Loss: 0.8915935754776001:  13%|█▎        | 3462/25880 [44:24<4:41:28,  1.33it/s]
1|3463|Loss: 0.8915935754776001:  13%|█▎        | 3463/25880 [44:25<4:46:22,  1.30it/s]
1|3464|Loss: 0.8176965117454529:  13%|█▎        | 3463/25880 [44:25<4:46:22,  1.30it/s]
1|3464|Loss: 0.8176965117454529:  13%|█▎        | 3464/25880 [44:25<4:33:35,  1.37it/s]
1|3465|Loss: 0.8221718072891235:  13%|█▎        | 3464/25880 [44:26<4:33:35,  1.37it/s]
1|3465|Loss: 0.8221718072891235:  13%|█▎        | 3465/25880 [44:26<4:27:54,  1.39it/s]
1|3466|Loss: 0.9312913417816162:  13%|█▎        | 3465/25880 [44:26<4:27:54,  1.39it/s]
1|3466|Loss: 0.9312913417816162:  13%|█▎        | 3466/25880 [44:27<4:28:53,  1.39it/s]
1|3467|Loss: 0.8790745139122009:  13%|█▎        | 3466/25880 [44:27<4:28:53,  1.39it/s]
1|3467|Loss: 0.8790745139122009:  13%|█▎        | 3467/25880 [44:27<4:22:30,  1.42it/s]
1|3468|Loss: 0.906531572341919:  13%|█▎        | 3467/25880 [44:28<4:22:30,  1.42it/s] 
1|3468|Loss: 0.906531572341919:  13%|█▎        | 3468/25880 [44:28<4:22:55,  1.42it/s]
1|3469|Loss: 0.9474027156829834:  13%|█▎        | 3468/25880 [44:29<4:22:55,  1.42it/s]
1|3469|Loss: 0.9474027156829834:  13%|█▎        | 3469/25880 [44:29<4:35:56,  1.35it/s]
1|3470|Loss: 0.8225719928741455:  13%|█▎        | 3469/25880 [44:29<4:35:56,  1.35it/s]
1|3470|Loss: 0.8225719928741455:  13%|█▎        | 3470/25880 [44:30<4:35:51,  1.35it/s]
1|3471|Loss: 0.9394897222518921:  13%|█▎        | 3470/25880 [44:30<4:35:51,  1.35it/s]
1|3471|Loss: 0.9394897222518921:  13%|█▎        | 3471/25880 [44:30<4:18:43,  1.44it/s]
1|3472|Loss: 0.9461451768875122:  13%|█▎        | 3471/25880 [44:31<4:18:43,  1.44it/s]
1|3472|Loss: 0.9461451768875122:  13%|█▎        | 3472/25880 [44:31<4:10:34,  1.49it/s]
1|3473|Loss: 0.8607426881790161:  13%|█▎        | 3472/25880 [44:31<4:10:34,  1.49it/s]
1|3473|Loss: 0.8607426881790161:  13%|█▎        | 3473/25880 [44:31<4:04:38,  1.53it/s]
1|3474|Loss: 0.8613916039466858:  13%|█▎        | 3473/25880 [44:32<4:04:38,  1.53it/s]
1|3474|Loss: 0.8613916039466858:  13%|█▎        | 3474/25880 [44:32<4:10:13,  1.49it/s]
1|3475|Loss: 0.8468278646469116:  13%|█▎        | 3474/25880 [44:33<4:10:13,  1.49it/s]
1|3475|Loss: 0.8468278646469116:  13%|█▎        | 3475/25880 [44:33<4:04:51,  1.53it/s]
1|3476|Loss: 0.9185017347335815:  13%|█▎        | 3475/25880 [44:33<4:04:51,  1.53it/s]
1|3476|Loss: 0.9185017347335815:  13%|█▎        | 3476/25880 [44:33<3:53:33,  1.60it/s]
1|3477|Loss: 0.9756276607513428:  13%|█▎        | 3476/25880 [44:34<3:53:33,  1.60it/s]
1|3477|Loss: 0.9756276607513428:  13%|█▎        | 3477/25880 [44:34<3:52:54,  1.60it/s]
1|3478|Loss: 0.9014139175415039:  13%|█▎        | 3477/25880 [44:34<3:52:54,  1.60it/s]
1|3478|Loss: 0.9014139175415039:  13%|█▎        | 3478/25880 [44:35<4:14:01,  1.47it/s]
1|3479|Loss: 0.9132559299468994:  13%|█▎        | 3478/25880 [44:35<4:14:01,  1.47it/s]
1|3479|Loss: 0.9132559299468994:  13%|█▎        | 3479/25880 [44:35<4:10:41,  1.49it/s]
1|3480|Loss: 0.8427487015724182:  13%|█▎        | 3479/25880 [44:36<4:10:41,  1.49it/s]
1|3480|Loss: 0.8427487015724182:  13%|█▎        | 3480/25880 [44:36<4:34:41,  1.36it/s]
1|3481|Loss: 0.9161112308502197:  13%|█▎        | 3480/25880 [44:37<4:34:41,  1.36it/s]
1|3481|Loss: 0.9161112308502197:  13%|█▎        | 3481/25880 [44:37<4:37:45,  1.34it/s]
1|3482|Loss: 1.1086602210998535:  13%|█▎        | 3481/25880 [44:38<4:37:45,  1.34it/s]
1|3482|Loss: 1.1086602210998535:  13%|█▎        | 3482/25880 [44:38<4:52:09,  1.28it/s]
1|3483|Loss: 0.7455857396125793:  13%|█▎        | 3482/25880 [44:38<4:52:09,  1.28it/s]
1|3483|Loss: 0.7455857396125793:  13%|█▎        | 3483/25880 [44:39<4:32:08,  1.37it/s]
1|3484|Loss: 0.9450921416282654:  13%|█▎        | 3483/25880 [44:39<4:32:08,  1.37it/s]
1|3484|Loss: 0.9450921416282654:  13%|█▎        | 3484/25880 [44:39<4:26:55,  1.40it/s]
1|3485|Loss: 0.9515954256057739:  13%|█▎        | 3484/25880 [44:40<4:26:55,  1.40it/s]
1|3485|Loss: 0.9515954256057739:  13%|█▎        | 3485/25880 [44:40<4:25:33,  1.41it/s]
1|3486|Loss: 0.7541894316673279:  13%|█▎        | 3485/25880 [44:40<4:25:33,  1.41it/s]
1|3486|Loss: 0.7541894316673279:  13%|█▎        | 3486/25880 [44:41<4:26:23,  1.40it/s]
1|3487|Loss: 0.9378540515899658:  13%|█▎        | 3486/25880 [44:41<4:26:23,  1.40it/s]
1|3487|Loss: 0.9378540515899658:  13%|█▎        | 3487/25880 [44:41<4:28:11,  1.39it/s]
1|3488|Loss: 0.7861957550048828:  13%|█▎        | 3487/25880 [44:42<4:28:11,  1.39it/s]
1|3488|Loss: 0.7861957550048828:  13%|█▎        | 3488/25880 [44:42<4:42:12,  1.32it/s]
1|3489|Loss: 0.8909814953804016:  13%|█▎        | 3488/25880 [44:43<4:42:12,  1.32it/s]
1|3489|Loss: 0.8909814953804016:  13%|█▎        | 3489/25880 [44:43<4:55:17,  1.26it/s]
1|3490|Loss: 0.9233824014663696:  13%|█▎        | 3489/25880 [44:44<4:55:17,  1.26it/s]
1|3490|Loss: 0.9233824014663696:  13%|█▎        | 3490/25880 [44:44<5:02:37,  1.23it/s]
1|3491|Loss: 0.8050971627235413:  13%|█▎        | 3490/25880 [44:44<5:02:37,  1.23it/s]
1|3491|Loss: 0.8050971627235413:  13%|█▎        | 3491/25880 [44:45<5:06:43,  1.22it/s]
1|3492|Loss: 0.7921062111854553:  13%|█▎        | 3491/25880 [44:45<5:06:43,  1.22it/s]
1|3492|Loss: 0.7921062111854553:  13%|█▎        | 3492/25880 [44:45<4:45:48,  1.31it/s]
1|3493|Loss: 0.8983587622642517:  13%|█▎        | 3492/25880 [44:46<4:45:48,  1.31it/s]
1|3493|Loss: 0.8983587622642517:  13%|█▎        | 3493/25880 [44:46<4:50:58,  1.28it/s]
1|3494|Loss: 0.8787115216255188:  13%|█▎        | 3493/25880 [44:47<4:50:58,  1.28it/s]
1|3494|Loss: 0.8787115216255188:  14%|█▎        | 3494/25880 [44:47<4:50:29,  1.28it/s]
1|3495|Loss: 0.9662349820137024:  14%|█▎        | 3494/25880 [44:47<4:50:29,  1.28it/s]
1|3495|Loss: 0.9662349820137024:  14%|█▎        | 3495/25880 [44:48<4:37:52,  1.34it/s]
1|3496|Loss: 0.8984375:  14%|█▎        | 3495/25880 [44:48<4:37:52,  1.34it/s]         
1|3496|Loss: 0.8984375:  14%|█▎        | 3496/25880 [44:48<4:33:49,  1.36it/s]
1|3497|Loss: 0.8649137020111084:  14%|█▎        | 3496/25880 [44:49<4:33:49,  1.36it/s]
1|3497|Loss: 0.8649137020111084:  14%|█▎        | 3497/25880 [44:49<4:33:17,  1.37it/s]
1|3498|Loss: 0.7835608124732971:  14%|█▎        | 3497/25880 [44:50<4:33:17,  1.37it/s]
1|3498|Loss: 0.7835608124732971:  14%|█▎        | 3498/25880 [44:50<4:33:55,  1.36it/s]
1|3499|Loss: 0.801369845867157:  14%|█▎        | 3498/25880 [44:50<4:33:55,  1.36it/s] 
1|3499|Loss: 0.801369845867157:  14%|█▎        | 3499/25880 [44:50<4:09:03,  1.50it/s]
1|3500|Loss: 0.865748405456543:  14%|█▎        | 3499/25880 [44:51<4:09:03,  1.50it/s]
1|3500|Loss: 0.865748405456543:  14%|█▎        | 3500/25880 [44:51<4:17:42,  1.45it/s]
1|3501|Loss: 0.6812250018119812:  14%|█▎        | 3500/25880 [44:52<4:17:42,  1.45it/s]
1|3501|Loss: 0.6812250018119812:  14%|█▎        | 3501/25880 [44:52<4:28:31,  1.39it/s]
1|3502|Loss: 0.8833288550376892:  14%|█▎        | 3501/25880 [44:52<4:28:31,  1.39it/s]
1|3502|Loss: 0.8833288550376892:  14%|█▎        | 3502/25880 [44:53<4:32:27,  1.37it/s]
1|3503|Loss: 0.9827753901481628:  14%|█▎        | 3502/25880 [44:53<4:32:27,  1.37it/s]
1|3503|Loss: 0.9827753901481628:  14%|█▎        | 3503/25880 [44:54<4:43:38,  1.31it/s]
1|3504|Loss: 0.9263406991958618:  14%|█▎        | 3503/25880 [44:54<4:43:38,  1.31it/s]
1|3504|Loss: 0.9263406991958618:  14%|█▎        | 3504/25880 [44:54<4:41:12,  1.33it/s]
1|3505|Loss: 0.9055337905883789:  14%|█▎        | 3504/25880 [44:55<4:41:12,  1.33it/s]
1|3505|Loss: 0.9055337905883789:  14%|█▎        | 3505/25880 [44:55<4:37:56,  1.34it/s]
1|3506|Loss: 0.6395264863967896:  14%|█▎        | 3505/25880 [44:55<4:37:56,  1.34it/s]
1|3506|Loss: 0.6395264863967896:  14%|█▎        | 3506/25880 [44:56<4:59:35,  1.24it/s]
1|3507|Loss: 0.8389096260070801:  14%|█▎        | 3506/25880 [44:56<4:59:35,  1.24it/s]
1|3507|Loss: 0.8389096260070801:  14%|█▎        | 3507/25880 [44:57<4:58:24,  1.25it/s]
1|3508|Loss: 0.899622917175293:  14%|█▎        | 3507/25880 [44:57<4:58:24,  1.25it/s] 
1|3508|Loss: 0.899622917175293:  14%|█▎        | 3508/25880 [44:57<4:41:46,  1.32it/s]
1|3509|Loss: 0.8541861772537231:  14%|█▎        | 3508/25880 [44:58<4:41:46,  1.32it/s]
1|3509|Loss: 0.8541861772537231:  14%|█▎        | 3509/25880 [44:58<5:12:42,  1.19it/s]
1|3510|Loss: 0.8380681276321411:  14%|█▎        | 3509/25880 [44:59<5:12:42,  1.19it/s]
1|3510|Loss: 0.8380681276321411:  14%|█▎        | 3510/25880 [44:59<5:11:27,  1.20it/s]
1|3511|Loss: 0.7807683348655701:  14%|█▎        | 3510/25880 [45:00<5:11:27,  1.20it/s]
1|3511|Loss: 0.7807683348655701:  14%|█▎        | 3511/25880 [45:00<4:46:05,  1.30it/s]
1|3512|Loss: 0.8659040331840515:  14%|█▎        | 3511/25880 [45:00<4:46:05,  1.30it/s]
1|3512|Loss: 0.8659040331840515:  14%|█▎        | 3512/25880 [45:01<4:38:14,  1.34it/s]
1|3513|Loss: 0.9021680355072021:  14%|█▎        | 3512/25880 [45:01<4:38:14,  1.34it/s]
1|3513|Loss: 0.9021680355072021:  14%|█▎        | 3513/25880 [45:01<4:20:10,  1.43it/s]
1|3514|Loss: 0.7943850755691528:  14%|█▎        | 3513/25880 [45:01<4:20:10,  1.43it/s]
1|3514|Loss: 0.7943850755691528:  14%|█▎        | 3514/25880 [45:02<4:03:12,  1.53it/s]
1|3515|Loss: 0.8834187984466553:  14%|█▎        | 3514/25880 [45:02<4:03:12,  1.53it/s]
1|3515|Loss: 0.8834187984466553:  14%|█▎        | 3515/25880 [45:02<4:16:14,  1.45it/s]
1|3516|Loss: 0.91646808385849:  14%|█▎        | 3515/25880 [45:03<4:16:14,  1.45it/s]  
1|3516|Loss: 0.91646808385849:  14%|█▎        | 3516/25880 [45:03<4:36:26,  1.35it/s]
1|3517|Loss: 0.905218780040741:  14%|█▎        | 3516/25880 [45:04<4:36:26,  1.35it/s]
1|3517|Loss: 0.905218780040741:  14%|█▎        | 3517/25880 [45:04<4:44:06,  1.31it/s]
1|3518|Loss: 0.8914265632629395:  14%|█▎        | 3517/25880 [45:05<4:44:06,  1.31it/s]
1|3518|Loss: 0.8914265632629395:  14%|█▎        | 3518/25880 [45:05<4:43:36,  1.31it/s]
1|3519|Loss: 0.9163394570350647:  14%|█▎        | 3518/25880 [45:05<4:43:36,  1.31it/s]
1|3519|Loss: 0.9163394570350647:  14%|█▎        | 3519/25880 [45:05<4:20:28,  1.43it/s]
1|3520|Loss: 0.8355667591094971:  14%|█▎        | 3519/25880 [45:06<4:20:28,  1.43it/s]
1|3520|Loss: 0.8355667591094971:  14%|█▎        | 3520/25880 [45:06<4:31:47,  1.37it/s]
1|3521|Loss: 0.8349319100379944:  14%|█▎        | 3520/25880 [45:07<4:31:47,  1.37it/s]
1|3521|Loss: 0.8349319100379944:  14%|█▎        | 3521/25880 [45:07<4:44:09,  1.31it/s]
1|3522|Loss: 0.9128578305244446:  14%|█▎        | 3521/25880 [45:08<4:44:09,  1.31it/s]
1|3522|Loss: 0.9128578305244446:  14%|█▎        | 3522/25880 [45:08<5:03:25,  1.23it/s]
1|3523|Loss: 0.9265139102935791:  14%|█▎        | 3522/25880 [45:08<5:03:25,  1.23it/s]
1|3523|Loss: 0.9265139102935791:  14%|█▎        | 3523/25880 [45:09<4:51:11,  1.28it/s]
1|3524|Loss: 1.0170176029205322:  14%|█▎        | 3523/25880 [45:09<4:51:11,  1.28it/s]
1|3524|Loss: 1.0170176029205322:  14%|█▎        | 3524/25880 [45:09<4:44:30,  1.31it/s]
1|3525|Loss: 0.9251250624656677:  14%|█▎        | 3524/25880 [45:10<4:44:30,  1.31it/s]
1|3525|Loss: 0.9251250624656677:  14%|█▎        | 3525/25880 [45:10<4:33:36,  1.36it/s]
1|3526|Loss: 0.8396432995796204:  14%|█▎        | 3525/25880 [45:11<4:33:36,  1.36it/s]
1|3526|Loss: 0.8396432995796204:  14%|█▎        | 3526/25880 [45:11<4:54:51,  1.26it/s]
1|3527|Loss: 0.8977648019790649:  14%|█▎        | 3526/25880 [45:11<4:54:51,  1.26it/s]
1|3527|Loss: 0.8977648019790649:  14%|█▎        | 3527/25880 [45:12<4:44:36,  1.31it/s]
1|3528|Loss: 0.9774971604347229:  14%|█▎        | 3527/25880 [45:12<4:44:36,  1.31it/s]
1|3528|Loss: 0.9774971604347229:  14%|█▎        | 3528/25880 [45:12<4:30:04,  1.38it/s]
1|3529|Loss: 0.8193944692611694:  14%|█▎        | 3528/25880 [45:13<4:30:04,  1.38it/s]
1|3529|Loss: 0.8193944692611694:  14%|█▎        | 3529/25880 [45:13<4:26:28,  1.40it/s]
1|3530|Loss: 0.8840450048446655:  14%|█▎        | 3529/25880 [45:13<4:26:28,  1.40it/s]
1|3530|Loss: 0.8840450048446655:  14%|█▎        | 3530/25880 [45:14<4:17:03,  1.45it/s]
1|3531|Loss: 1.0189741849899292:  14%|█▎        | 3530/25880 [45:14<4:17:03,  1.45it/s]
1|3531|Loss: 1.0189741849899292:  14%|█▎        | 3531/25880 [45:14<4:28:42,  1.39it/s]
1|3532|Loss: 0.9119922518730164:  14%|█▎        | 3531/25880 [45:15<4:28:42,  1.39it/s]
1|3532|Loss: 0.9119922518730164:  14%|█▎        | 3532/25880 [45:15<4:42:05,  1.32it/s]
1|3533|Loss: 0.9799536466598511:  14%|█▎        | 3532/25880 [45:16<4:42:05,  1.32it/s]
1|3533|Loss: 0.9799536466598511:  14%|█▎        | 3533/25880 [45:16<4:30:58,  1.37it/s]
1|3534|Loss: 0.7932842373847961:  14%|█▎        | 3533/25880 [45:16<4:30:58,  1.37it/s]
1|3534|Loss: 0.7932842373847961:  14%|█▎        | 3534/25880 [45:17<4:34:01,  1.36it/s]
1|3535|Loss: 0.9282363653182983:  14%|█▎        | 3534/25880 [45:17<4:34:01,  1.36it/s]
1|3535|Loss: 0.9282363653182983:  14%|█▎        | 3535/25880 [45:17<4:32:40,  1.37it/s]
1|3536|Loss: 0.8589449524879456:  14%|█▎        | 3535/25880 [45:18<4:32:40,  1.37it/s]
1|3536|Loss: 0.8589449524879456:  14%|█▎        | 3536/25880 [45:18<4:41:07,  1.32it/s]
1|3537|Loss: 0.7745168805122375:  14%|█▎        | 3536/25880 [45:19<4:41:07,  1.32it/s]
1|3537|Loss: 0.7745168805122375:  14%|█▎        | 3537/25880 [45:19<4:41:20,  1.32it/s]
1|3538|Loss: 0.8467931151390076:  14%|█▎        | 3537/25880 [45:19<4:41:20,  1.32it/s]
1|3538|Loss: 0.8467931151390076:  14%|█▎        | 3538/25880 [45:20<4:30:35,  1.38it/s]
1|3539|Loss: 0.8525100946426392:  14%|█▎        | 3538/25880 [45:20<4:30:35,  1.38it/s]
1|3539|Loss: 0.8525100946426392:  14%|█▎        | 3539/25880 [45:20<4:28:45,  1.39it/s]
1|3540|Loss: 1.0105499029159546:  14%|█▎        | 3539/25880 [45:21<4:28:45,  1.39it/s]
1|3540|Loss: 1.0105499029159546:  14%|█▎        | 3540/25880 [45:21<4:34:07,  1.36it/s]
1|3541|Loss: 0.8653990030288696:  14%|█▎        | 3540/25880 [45:22<4:34:07,  1.36it/s]
1|3541|Loss: 0.8653990030288696:  14%|█▎        | 3541/25880 [45:22<4:35:26,  1.35it/s]
1|3542|Loss: 0.8931378722190857:  14%|█▎        | 3541/25880 [45:22<4:35:26,  1.35it/s]
1|3542|Loss: 0.8931378722190857:  14%|█▎        | 3542/25880 [45:23<4:46:11,  1.30it/s]
1|3543|Loss: 0.7210338711738586:  14%|█▎        | 3542/25880 [45:23<4:46:11,  1.30it/s]
1|3543|Loss: 0.7210338711738586:  14%|█▎        | 3543/25880 [45:24<4:58:28,  1.25it/s]
1|3544|Loss: 0.9242860078811646:  14%|█▎        | 3543/25880 [45:24<4:58:28,  1.25it/s]
1|3544|Loss: 0.9242860078811646:  14%|█▎        | 3544/25880 [45:24<4:53:54,  1.27it/s]
1|3545|Loss: 0.8114420175552368:  14%|█▎        | 3544/25880 [45:25<4:53:54,  1.27it/s]
1|3545|Loss: 0.8114420175552368:  14%|█▎        | 3545/25880 [45:25<4:26:19,  1.40it/s]
1|3546|Loss: 0.8910371661186218:  14%|█▎        | 3545/25880 [45:25<4:26:19,  1.40it/s]
1|3546|Loss: 0.8910371661186218:  14%|█▎        | 3546/25880 [45:26<4:12:55,  1.47it/s]
1|3547|Loss: 0.8907943964004517:  14%|█▎        | 3546/25880 [45:26<4:12:55,  1.47it/s]
1|3547|Loss: 0.8907943964004517:  14%|█▎        | 3547/25880 [45:26<4:00:38,  1.55it/s]
1|3548|Loss: 0.7118030190467834:  14%|█▎        | 3547/25880 [45:26<4:00:38,  1.55it/s]
1|3548|Loss: 0.7118030190467834:  14%|█▎        | 3548/25880 [45:27<4:14:55,  1.46it/s]
1|3549|Loss: 0.8963037133216858:  14%|█▎        | 3548/25880 [45:27<4:14:55,  1.46it/s]
1|3549|Loss: 0.8963037133216858:  14%|█▎        | 3549/25880 [45:28<4:13:43,  1.47it/s]
1|3550|Loss: 0.9167640209197998:  14%|█▎        | 3549/25880 [45:28<4:13:43,  1.47it/s]
1|3550|Loss: 0.9167640209197998:  14%|█▎        | 3550/25880 [45:28<4:15:07,  1.46it/s]
1|3551|Loss: 0.7560994625091553:  14%|█▎        | 3550/25880 [45:29<4:15:07,  1.46it/s]
1|3551|Loss: 0.7560994625091553:  14%|█▎        | 3551/25880 [45:29<3:57:03,  1.57it/s]
1|3552|Loss: 0.8243743777275085:  14%|█▎        | 3551/25880 [45:29<3:57:03,  1.57it/s]
1|3552|Loss: 0.8243743777275085:  14%|█▎        | 3552/25880 [45:30<4:18:25,  1.44it/s]
1|3553|Loss: 0.8918927311897278:  14%|█▎        | 3552/25880 [45:30<4:18:25,  1.44it/s]
1|3553|Loss: 0.8918927311897278:  14%|█▎        | 3553/25880 [45:30<4:33:41,  1.36it/s]
1|3554|Loss: 1.001979947090149:  14%|█▎        | 3553/25880 [45:31<4:33:41,  1.36it/s] 
1|3554|Loss: 1.001979947090149:  14%|█▎        | 3554/25880 [45:31<4:50:44,  1.28it/s]
1|3555|Loss: 0.8763726949691772:  14%|█▎        | 3554/25880 [45:32<4:50:44,  1.28it/s]
1|3555|Loss: 0.8763726949691772:  14%|█▎        | 3555/25880 [45:32<4:35:16,  1.35it/s]
1|3556|Loss: 0.8250834345817566:  14%|█▎        | 3555/25880 [45:32<4:35:16,  1.35it/s]
1|3556|Loss: 0.8250834345817566:  14%|█▎        | 3556/25880 [45:32<3:59:43,  1.55it/s]
1|3557|Loss: 0.7969566583633423:  14%|█▎        | 3556/25880 [45:33<3:59:43,  1.55it/s]
1|3557|Loss: 0.7969566583633423:  14%|█▎        | 3557/25880 [45:33<3:53:32,  1.59it/s]
1|3558|Loss: 0.9214640259742737:  14%|█▎        | 3557/25880 [45:33<3:53:32,  1.59it/s]
1|3558|Loss: 0.9214640259742737:  14%|█▎        | 3558/25880 [45:34<3:45:16,  1.65it/s]
1|3559|Loss: 0.7968414425849915:  14%|█▎        | 3558/25880 [45:34<3:45:16,  1.65it/s]
1|3559|Loss: 0.7968414425849915:  14%|█▍        | 3559/25880 [45:34<4:00:44,  1.55it/s]
1|3560|Loss: 0.8914891481399536:  14%|█▍        | 3559/25880 [45:35<4:00:44,  1.55it/s]
1|3560|Loss: 0.8914891481399536:  14%|█▍        | 3560/25880 [45:35<4:03:04,  1.53it/s]
1|3561|Loss: 0.8851778507232666:  14%|█▍        | 3560/25880 [45:35<4:03:04,  1.53it/s]
1|3561|Loss: 0.8851778507232666:  14%|█▍        | 3561/25880 [45:36<4:09:04,  1.49it/s]
1|3562|Loss: 0.8698978424072266:  14%|█▍        | 3561/25880 [45:36<4:09:04,  1.49it/s]
1|3562|Loss: 0.8698978424072266:  14%|█▍        | 3562/25880 [45:36<4:07:25,  1.50it/s]
1|3563|Loss: 0.8704133033752441:  14%|█▍        | 3562/25880 [45:37<4:07:25,  1.50it/s]
1|3563|Loss: 0.8704133033752441:  14%|█▍        | 3563/25880 [45:37<4:12:58,  1.47it/s]
1|3564|Loss: 0.5361800193786621:  14%|█▍        | 3563/25880 [45:38<4:12:58,  1.47it/s]
1|3564|Loss: 0.5361800193786621:  14%|█▍        | 3564/25880 [45:38<4:52:22,  1.27it/s]
1|3565|Loss: 0.7324923872947693:  14%|█▍        | 3564/25880 [45:39<4:52:22,  1.27it/s]
1|3565|Loss: 0.7324923872947693:  14%|█▍        | 3565/25880 [45:39<5:01:38,  1.23it/s]
1|3566|Loss: 0.7478383183479309:  14%|█▍        | 3565/25880 [45:39<5:01:38,  1.23it/s]
1|3566|Loss: 0.7478383183479309:  14%|█▍        | 3566/25880 [45:39<4:34:16,  1.36it/s]
1|3567|Loss: 0.6987836956977844:  14%|█▍        | 3566/25880 [45:40<4:34:16,  1.36it/s]
1|3567|Loss: 0.6987836956977844:  14%|█▍        | 3567/25880 [45:40<4:26:30,  1.40it/s]
1|3568|Loss: 0.7815783619880676:  14%|█▍        | 3567/25880 [45:41<4:26:30,  1.40it/s]
1|3568|Loss: 0.7815783619880676:  14%|█▍        | 3568/25880 [45:41<4:51:22,  1.28it/s]
1|3569|Loss: 0.8776993155479431:  14%|█▍        | 3568/25880 [45:42<4:51:22,  1.28it/s]
1|3569|Loss: 0.8776993155479431:  14%|█▍        | 3569/25880 [45:42<4:43:40,  1.31it/s]
1|3570|Loss: 0.858072817325592:  14%|█▍        | 3569/25880 [45:42<4:43:40,  1.31it/s] 
1|3570|Loss: 0.858072817325592:  14%|█▍        | 3570/25880 [45:42<4:30:21,  1.38it/s]
1|3571|Loss: 0.8130826354026794:  14%|█▍        | 3570/25880 [45:43<4:30:21,  1.38it/s]
1|3571|Loss: 0.8130826354026794:  14%|█▍        | 3571/25880 [45:43<4:39:43,  1.33it/s]
1|3572|Loss: 0.8766199946403503:  14%|█▍        | 3571/25880 [45:44<4:39:43,  1.33it/s]
1|3572|Loss: 0.8766199946403503:  14%|█▍        | 3572/25880 [45:44<4:24:48,  1.40it/s]
1|3573|Loss: 0.9471608996391296:  14%|█▍        | 3572/25880 [45:44<4:24:48,  1.40it/s]
1|3573|Loss: 0.9471608996391296:  14%|█▍        | 3573/25880 [45:45<4:22:51,  1.41it/s]
1|3574|Loss: 0.8864442706108093:  14%|█▍        | 3573/25880 [45:45<4:22:51,  1.41it/s]
1|3574|Loss: 0.8864442706108093:  14%|█▍        | 3574/25880 [45:45<4:22:53,  1.41it/s]
1|3575|Loss: 0.9189416170120239:  14%|█▍        | 3574/25880 [45:46<4:22:53,  1.41it/s]
1|3575|Loss: 0.9189416170120239:  14%|█▍        | 3575/25880 [45:46<4:46:06,  1.30it/s]
1|3576|Loss: 0.9680727124214172:  14%|█▍        | 3575/25880 [45:47<4:46:06,  1.30it/s]
1|3576|Loss: 0.9680727124214172:  14%|█▍        | 3576/25880 [45:47<4:39:19,  1.33it/s]
1|3577|Loss: 0.8200419545173645:  14%|█▍        | 3576/25880 [45:47<4:39:19,  1.33it/s]
1|3577|Loss: 0.8200419545173645:  14%|█▍        | 3577/25880 [45:48<4:48:37,  1.29it/s]
1|3578|Loss: 0.888565182685852:  14%|█▍        | 3577/25880 [45:48<4:48:37,  1.29it/s] 
1|3578|Loss: 0.888565182685852:  14%|█▍        | 3578/25880 [45:48<4:44:25,  1.31it/s]
1|3579|Loss: 0.7011752724647522:  14%|█▍        | 3578/25880 [45:49<4:44:25,  1.31it/s]
1|3579|Loss: 0.7011752724647522:  14%|█▍        | 3579/25880 [45:49<4:29:01,  1.38it/s]
1|3580|Loss: 0.6979168057441711:  14%|█▍        | 3579/25880 [45:49<4:29:01,  1.38it/s]
1|3580|Loss: 0.6979168057441711:  14%|█▍        | 3580/25880 [45:50<4:16:41,  1.45it/s]
1|3581|Loss: 0.8102480173110962:  14%|█▍        | 3580/25880 [45:50<4:16:41,  1.45it/s]
1|3581|Loss: 0.8102480173110962:  14%|█▍        | 3581/25880 [45:50<3:54:43,  1.58it/s]
1|3582|Loss: 0.9026226997375488:  14%|█▍        | 3581/25880 [45:51<3:54:43,  1.58it/s]
1|3582|Loss: 0.9026226997375488:  14%|█▍        | 3582/25880 [45:51<3:58:45,  1.56it/s]
1|3583|Loss: 0.812382161617279:  14%|█▍        | 3582/25880 [45:51<3:58:45,  1.56it/s] 
1|3583|Loss: 0.812382161617279:  14%|█▍        | 3583/25880 [45:51<3:52:30,  1.60it/s]
1|3584|Loss: 0.9733086228370667:  14%|█▍        | 3583/25880 [45:52<3:52:30,  1.60it/s]
1|3584|Loss: 0.9733086228370667:  14%|█▍        | 3584/25880 [45:52<4:10:25,  1.48it/s]
1|3585|Loss: 0.7299471497535706:  14%|█▍        | 3584/25880 [45:53<4:10:25,  1.48it/s]
1|3585|Loss: 0.7299471497535706:  14%|█▍        | 3585/25880 [45:53<4:57:46,  1.25it/s]
1|3586|Loss: 0.8135744333267212:  14%|█▍        | 3585/25880 [45:54<4:57:46,  1.25it/s]
1|3586|Loss: 0.8135744333267212:  14%|█▍        | 3586/25880 [45:54<5:06:13,  1.21it/s]
1|3587|Loss: 0.9453925490379333:  14%|█▍        | 3586/25880 [45:55<5:06:13,  1.21it/s]
1|3587|Loss: 0.9453925490379333:  14%|█▍        | 3587/25880 [45:55<5:02:11,  1.23it/s]
1|3588|Loss: 0.9046012759208679:  14%|█▍        | 3587/25880 [45:55<5:02:11,  1.23it/s]
1|3588|Loss: 0.9046012759208679:  14%|█▍        | 3588/25880 [45:56<4:58:54,  1.24it/s]
1|3589|Loss: 0.9579158425331116:  14%|█▍        | 3588/25880 [45:56<4:58:54,  1.24it/s]
1|3589|Loss: 0.9579158425331116:  14%|█▍        | 3589/25880 [45:56<4:44:05,  1.31it/s]
1|3590|Loss: 0.8686721324920654:  14%|█▍        | 3589/25880 [45:57<4:44:05,  1.31it/s]
1|3590|Loss: 0.8686721324920654:  14%|█▍        | 3590/25880 [45:57<4:30:27,  1.37it/s]
1|3591|Loss: 0.8736609816551208:  14%|█▍        | 3590/25880 [45:58<4:30:27,  1.37it/s]
1|3591|Loss: 0.8736609816551208:  14%|█▍        | 3591/25880 [45:58<4:30:28,  1.37it/s]
1|3592|Loss: 0.9292667508125305:  14%|█▍        | 3591/25880 [45:58<4:30:28,  1.37it/s]
1|3592|Loss: 0.9292667508125305:  14%|█▍        | 3592/25880 [45:58<4:12:00,  1.47it/s]
1|3593|Loss: 0.9513267278671265:  14%|█▍        | 3592/25880 [45:59<4:12:00,  1.47it/s]
1|3593|Loss: 0.9513267278671265:  14%|█▍        | 3593/25880 [45:59<4:33:03,  1.36it/s]
1|3594|Loss: 0.8150047659873962:  14%|█▍        | 3593/25880 [46:00<4:33:03,  1.36it/s]
1|3594|Loss: 0.8150047659873962:  14%|█▍        | 3594/25880 [46:00<4:48:33,  1.29it/s]
1|3595|Loss: 0.7226805090904236:  14%|█▍        | 3594/25880 [46:01<4:48:33,  1.29it/s]
1|3595|Loss: 0.7226805090904236:  14%|█▍        | 3595/25880 [46:01<4:55:37,  1.26it/s]
1|3596|Loss: 0.7652113437652588:  14%|█▍        | 3595/25880 [46:01<4:55:37,  1.26it/s]
1|3596|Loss: 0.7652113437652588:  14%|█▍        | 3596/25880 [46:02<5:01:27,  1.23it/s]
1|3597|Loss: 0.9503782391548157:  14%|█▍        | 3596/25880 [46:02<5:01:27,  1.23it/s]
1|3597|Loss: 0.9503782391548157:  14%|█▍        | 3597/25880 [46:02<4:41:58,  1.32it/s]
1|3598|Loss: 0.8136311769485474:  14%|█▍        | 3597/25880 [46:03<4:41:58,  1.32it/s]
1|3598|Loss: 0.8136311769485474:  14%|█▍        | 3598/25880 [46:03<4:40:31,  1.32it/s]
1|3599|Loss: 0.8530638217926025:  14%|█▍        | 3598/25880 [46:04<4:40:31,  1.32it/s]
1|3599|Loss: 0.8530638217926025:  14%|█▍        | 3599/25880 [46:04<4:44:09,  1.31it/s]
1|3600|Loss: 1.0003310441970825:  14%|█▍        | 3599/25880 [46:04<4:44:09,  1.31it/s]
1|3600|Loss: 1.0003310441970825:  14%|█▍        | 3600/25880 [46:05<4:52:34,  1.27it/s]
1|3601|Loss: 0.9192482233047485:  14%|█▍        | 3600/25880 [46:05<4:52:34,  1.27it/s]
1|3601|Loss: 0.9192482233047485:  14%|█▍        | 3601/25880 [46:06<4:56:05,  1.25it/s]
1|3602|Loss: 0.8653058409690857:  14%|█▍        | 3601/25880 [46:06<4:56:05,  1.25it/s]
1|3602|Loss: 0.8653058409690857:  14%|█▍        | 3602/25880 [46:07<5:00:59,  1.23it/s]
1|3603|Loss: 0.796846330165863:  14%|█▍        | 3602/25880 [46:07<5:00:59,  1.23it/s] 
1|3603|Loss: 0.796846330165863:  14%|█▍        | 3603/25880 [46:07<4:52:05,  1.27it/s]
1|3604|Loss: 0.8788818717002869:  14%|█▍        | 3603/25880 [46:08<4:52:05,  1.27it/s]
1|3604|Loss: 0.8788818717002869:  14%|█▍        | 3604/25880 [46:08<4:25:23,  1.40it/s]
1|3605|Loss: 0.8411139249801636:  14%|█▍        | 3604/25880 [46:08<4:25:23,  1.40it/s]
1|3605|Loss: 0.8411139249801636:  14%|█▍        | 3605/25880 [46:09<4:28:33,  1.38it/s]
1|3606|Loss: 1.0155925750732422:  14%|█▍        | 3605/25880 [46:09<4:28:33,  1.38it/s]
1|3606|Loss: 1.0155925750732422:  14%|█▍        | 3606/25880 [46:09<4:31:42,  1.37it/s]
1|3607|Loss: 0.897364616394043:  14%|█▍        | 3606/25880 [46:10<4:31:42,  1.37it/s] 
1|3607|Loss: 0.897364616394043:  14%|█▍        | 3607/25880 [46:10<4:32:16,  1.36it/s]
1|3608|Loss: 0.7666833400726318:  14%|█▍        | 3607/25880 [46:10<4:32:16,  1.36it/s]
1|3608|Loss: 0.7666833400726318:  14%|█▍        | 3608/25880 [46:11<4:20:56,  1.42it/s]
1|3609|Loss: 0.7746359705924988:  14%|█▍        | 3608/25880 [46:11<4:20:56,  1.42it/s]
1|3609|Loss: 0.7746359705924988:  14%|█▍        | 3609/25880 [46:11<4:21:28,  1.42it/s]
1|3610|Loss: 0.8922393918037415:  14%|█▍        | 3609/25880 [46:12<4:21:28,  1.42it/s]
1|3610|Loss: 0.8922393918037415:  14%|█▍        | 3610/25880 [46:12<4:16:35,  1.45it/s]
1|3611|Loss: 0.9208629727363586:  14%|█▍        | 3610/25880 [46:12<4:16:35,  1.45it/s]
1|3611|Loss: 0.9208629727363586:  14%|█▍        | 3611/25880 [46:13<4:09:27,  1.49it/s]
1|3612|Loss: 0.7609139084815979:  14%|█▍        | 3611/25880 [46:13<4:09:27,  1.49it/s]
1|3612|Loss: 0.7609139084815979:  14%|█▍        | 3612/25880 [46:13<4:20:02,  1.43it/s]
1|3613|Loss: 0.7759150862693787:  14%|█▍        | 3612/25880 [46:14<4:20:02,  1.43it/s]
1|3613|Loss: 0.7759150862693787:  14%|█▍        | 3613/25880 [46:14<4:48:05,  1.29it/s]
1|3614|Loss: 0.8945925831794739:  14%|█▍        | 3613/25880 [46:15<4:48:05,  1.29it/s]
1|3614|Loss: 0.8945925831794739:  14%|█▍        | 3614/25880 [46:15<4:39:06,  1.33it/s]
1|3615|Loss: 0.824491560459137:  14%|█▍        | 3614/25880 [46:15<4:39:06,  1.33it/s] 
1|3615|Loss: 0.824491560459137:  14%|█▍        | 3615/25880 [46:16<4:20:44,  1.42it/s]
1|3616|Loss: 0.7865610122680664:  14%|█▍        | 3615/25880 [46:16<4:20:44,  1.42it/s]
1|3616|Loss: 0.7865610122680664:  14%|█▍        | 3616/25880 [46:16<4:33:17,  1.36it/s]
1|3617|Loss: 0.9375296235084534:  14%|█▍        | 3616/25880 [46:17<4:33:17,  1.36it/s]
1|3617|Loss: 0.9375296235084534:  14%|█▍        | 3617/25880 [46:17<4:43:00,  1.31it/s]
1|3618|Loss: 1.0014818906784058:  14%|█▍        | 3617/25880 [46:18<4:43:00,  1.31it/s]
1|3618|Loss: 1.0014818906784058:  14%|█▍        | 3618/25880 [46:18<4:45:49,  1.30it/s]
1|3619|Loss: 0.8574057221412659:  14%|█▍        | 3618/25880 [46:19<4:45:49,  1.30it/s]
1|3619|Loss: 0.8574057221412659:  14%|█▍        | 3619/25880 [46:19<4:45:04,  1.30it/s]
1|3620|Loss: 0.8813437223434448:  14%|█▍        | 3619/25880 [46:19<4:45:04,  1.30it/s]
1|3620|Loss: 0.8813437223434448:  14%|█▍        | 3620/25880 [46:20<4:41:53,  1.32it/s]
1|3621|Loss: 0.8538676500320435:  14%|█▍        | 3620/25880 [46:20<4:41:53,  1.32it/s]
1|3621|Loss: 0.8538676500320435:  14%|█▍        | 3621/25880 [46:20<4:44:02,  1.31it/s]
1|3622|Loss: 0.7781311869621277:  14%|█▍        | 3621/25880 [46:21<4:44:02,  1.31it/s]
1|3622|Loss: 0.7781311869621277:  14%|█▍        | 3622/25880 [46:21<4:41:03,  1.32it/s]
1|3623|Loss: 0.9774864912033081:  14%|█▍        | 3622/25880 [46:21<4:41:03,  1.32it/s]
1|3623|Loss: 0.9774864912033081:  14%|█▍        | 3623/25880 [46:22<4:37:45,  1.34it/s]
1|3624|Loss: 0.8577467799186707:  14%|█▍        | 3623/25880 [46:22<4:37:45,  1.34it/s]
1|3624|Loss: 0.8577467799186707:  14%|█▍        | 3624/25880 [46:23<4:51:37,  1.27it/s]
1|3625|Loss: 1.01324462890625:  14%|█▍        | 3624/25880 [46:23<4:51:37,  1.27it/s]  
1|3625|Loss: 1.01324462890625:  14%|█▍        | 3625/25880 [46:24<4:54:23,  1.26it/s]
1|3626|Loss: 0.8992655873298645:  14%|█▍        | 3625/25880 [46:24<4:54:23,  1.26it/s]
1|3626|Loss: 0.8992655873298645:  14%|█▍        | 3626/25880 [46:24<4:46:49,  1.29it/s]
1|3627|Loss: 0.9834441542625427:  14%|█▍        | 3626/25880 [46:25<4:46:49,  1.29it/s]
1|3627|Loss: 0.9834441542625427:  14%|█▍        | 3627/25880 [46:25<4:33:04,  1.36it/s]
1|3628|Loss: 0.8238548040390015:  14%|█▍        | 3627/25880 [46:25<4:33:04,  1.36it/s]
1|3628|Loss: 0.8238548040390015:  14%|█▍        | 3628/25880 [46:26<4:39:40,  1.33it/s]
1|3629|Loss: 0.90189129114151:  14%|█▍        | 3628/25880 [46:26<4:39:40,  1.33it/s]  
1|3629|Loss: 0.90189129114151:  14%|█▍        | 3629/25880 [46:26<4:29:05,  1.38it/s]
1|3630|Loss: 0.7898648381233215:  14%|█▍        | 3629/25880 [46:27<4:29:05,  1.38it/s]
1|3630|Loss: 0.7898648381233215:  14%|█▍        | 3630/25880 [46:27<4:24:35,  1.40it/s]
1|3631|Loss: 0.8449848890304565:  14%|█▍        | 3630/25880 [46:27<4:24:35,  1.40it/s]
1|3631|Loss: 0.8449848890304565:  14%|█▍        | 3631/25880 [46:28<4:25:20,  1.40it/s]
1|3632|Loss: 0.9432412981987:  14%|█▍        | 3631/25880 [46:28<4:25:20,  1.40it/s]   
1|3632|Loss: 0.9432412981987:  14%|█▍        | 3632/25880 [46:28<4:26:36,  1.39it/s]
1|3633|Loss: 0.7551761269569397:  14%|█▍        | 3632/25880 [46:29<4:26:36,  1.39it/s]
1|3633|Loss: 0.7551761269569397:  14%|█▍        | 3633/25880 [46:29<4:02:57,  1.53it/s]
1|3634|Loss: 0.8554196953773499:  14%|█▍        | 3633/25880 [46:29<4:02:57,  1.53it/s]
1|3634|Loss: 0.8554196953773499:  14%|█▍        | 3634/25880 [46:30<4:09:25,  1.49it/s]
1|3635|Loss: 0.7269633412361145:  14%|█▍        | 3634/25880 [46:30<4:09:25,  1.49it/s]
1|3635|Loss: 0.7269633412361145:  14%|█▍        | 3635/25880 [46:31<4:33:49,  1.35it/s]
1|3636|Loss: 0.8856915235519409:  14%|█▍        | 3635/25880 [46:31<4:33:49,  1.35it/s]
1|3636|Loss: 0.8856915235519409:  14%|█▍        | 3636/25880 [46:31<4:49:35,  1.28it/s]
1|3637|Loss: 0.9368336200714111:  14%|█▍        | 3636/25880 [46:32<4:49:35,  1.28it/s]
1|3637|Loss: 0.9368336200714111:  14%|█▍        | 3637/25880 [46:32<4:36:59,  1.34it/s]
1|3638|Loss: 0.9198089241981506:  14%|█▍        | 3637/25880 [46:32<4:36:59,  1.34it/s]
1|3638|Loss: 0.9198089241981506:  14%|█▍        | 3638/25880 [46:33<4:19:06,  1.43it/s]
1|3639|Loss: 0.9567463397979736:  14%|█▍        | 3638/25880 [46:33<4:19:06,  1.43it/s]
1|3639|Loss: 0.9567463397979736:  14%|█▍        | 3639/25880 [46:33<4:25:45,  1.39it/s]
1|3640|Loss: 0.7904866933822632:  14%|█▍        | 3639/25880 [46:34<4:25:45,  1.39it/s]
1|3640|Loss: 0.7904866933822632:  14%|█▍        | 3640/25880 [46:34<4:41:55,  1.31it/s]
1|3641|Loss: 0.960260808467865:  14%|█▍        | 3640/25880 [46:35<4:41:55,  1.31it/s] 
1|3641|Loss: 0.960260808467865:  14%|█▍        | 3641/25880 [46:35<4:43:02,  1.31it/s]
1|3642|Loss: 0.7260797023773193:  14%|█▍        | 3641/25880 [46:35<4:43:02,  1.31it/s]
1|3642|Loss: 0.7260797023773193:  14%|█▍        | 3642/25880 [46:36<4:29:29,  1.38it/s]
1|3643|Loss: 0.8708349466323853:  14%|█▍        | 3642/25880 [46:36<4:29:29,  1.38it/s]
1|3643|Loss: 0.8708349466323853:  14%|█▍        | 3643/25880 [46:36<4:24:48,  1.40it/s]
1|3644|Loss: 0.8240683674812317:  14%|█▍        | 3643/25880 [46:37<4:24:48,  1.40it/s]
1|3644|Loss: 0.8240683674812317:  14%|█▍        | 3644/25880 [46:37<4:23:23,  1.41it/s]
1|3645|Loss: 0.8172921538352966:  14%|█▍        | 3644/25880 [46:38<4:23:23,  1.41it/s]
1|3645|Loss: 0.8172921538352966:  14%|█▍        | 3645/25880 [46:38<4:47:35,  1.29it/s]
1|3646|Loss: 0.9396733045578003:  14%|█▍        | 3645/25880 [46:39<4:47:35,  1.29it/s]
1|3646|Loss: 0.9396733045578003:  14%|█▍        | 3646/25880 [46:39<4:56:23,  1.25it/s]
1|3647|Loss: 0.8545659780502319:  14%|█▍        | 3646/25880 [46:39<4:56:23,  1.25it/s]
1|3647|Loss: 0.8545659780502319:  14%|█▍        | 3647/25880 [46:39<4:30:42,  1.37it/s]
1|3648|Loss: 0.9989569783210754:  14%|█▍        | 3647/25880 [46:40<4:30:42,  1.37it/s]
1|3648|Loss: 0.9989569783210754:  14%|█▍        | 3648/25880 [46:40<4:15:39,  1.45it/s]
1|3649|Loss: 0.9101892709732056:  14%|█▍        | 3648/25880 [46:40<4:15:39,  1.45it/s]
1|3649|Loss: 0.9101892709732056:  14%|█▍        | 3649/25880 [46:41<4:15:08,  1.45it/s]
1|3650|Loss: 1.0270274877548218:  14%|█▍        | 3649/25880 [46:41<4:15:08,  1.45it/s]
1|3650|Loss: 1.0270274877548218:  14%|█▍        | 3650/25880 [46:41<4:08:33,  1.49it/s]
1|3651|Loss: 0.8156051635742188:  14%|█▍        | 3650/25880 [46:42<4:08:33,  1.49it/s]
1|3651|Loss: 0.8156051635742188:  14%|█▍        | 3651/25880 [46:42<4:20:03,  1.42it/s]
1|3652|Loss: 0.8597468137741089:  14%|█▍        | 3651/25880 [46:43<4:20:03,  1.42it/s]
1|3652|Loss: 0.8597468137741089:  14%|█▍        | 3652/25880 [46:43<4:38:44,  1.33it/s]
1|3653|Loss: 0.9482436776161194:  14%|█▍        | 3652/25880 [46:43<4:38:44,  1.33it/s]
1|3653|Loss: 0.9482436776161194:  14%|█▍        | 3653/25880 [46:44<4:38:14,  1.33it/s]
1|3654|Loss: 0.8708042502403259:  14%|█▍        | 3653/25880 [46:44<4:38:14,  1.33it/s]
1|3654|Loss: 0.8708042502403259:  14%|█▍        | 3654/25880 [46:44<4:19:26,  1.43it/s]
1|3655|Loss: 0.8971991539001465:  14%|█▍        | 3654/25880 [46:45<4:19:26,  1.43it/s]
1|3655|Loss: 0.8971991539001465:  14%|█▍        | 3655/25880 [46:45<4:10:18,  1.48it/s]
1|3656|Loss: 0.7929173707962036:  14%|█▍        | 3655/25880 [46:45<4:10:18,  1.48it/s]
1|3656|Loss: 0.7929173707962036:  14%|█▍        | 3656/25880 [46:46<4:16:04,  1.45it/s]
1|3657|Loss: 0.9386821985244751:  14%|█▍        | 3656/25880 [46:46<4:16:04,  1.45it/s]
1|3657|Loss: 0.9386821985244751:  14%|█▍        | 3657/25880 [46:47<4:31:34,  1.36it/s]
1|3658|Loss: 0.8276286721229553:  14%|█▍        | 3657/25880 [46:47<4:31:34,  1.36it/s]
1|3658|Loss: 0.8276286721229553:  14%|█▍        | 3658/25880 [46:47<4:39:52,  1.32it/s]
1|3659|Loss: 0.9111972451210022:  14%|█▍        | 3658/25880 [46:48<4:39:52,  1.32it/s]
1|3659|Loss: 0.9111972451210022:  14%|█▍        | 3659/25880 [46:48<4:28:31,  1.38it/s]
1|3660|Loss: 0.7373723387718201:  14%|█▍        | 3659/25880 [46:48<4:28:31,  1.38it/s]
1|3660|Loss: 0.7373723387718201:  14%|█▍        | 3660/25880 [46:49<4:10:52,  1.48it/s]
1|3661|Loss: 0.8793920874595642:  14%|█▍        | 3660/25880 [46:49<4:10:52,  1.48it/s]
1|3661|Loss: 0.8793920874595642:  14%|█▍        | 3661/25880 [46:49<3:49:07,  1.62it/s]
1|3662|Loss: 0.7590819001197815:  14%|█▍        | 3661/25880 [46:49<3:49:07,  1.62it/s]
1|3662|Loss: 0.7590819001197815:  14%|█▍        | 3662/25880 [46:50<4:05:24,  1.51it/s]
1|3663|Loss: 0.8808698058128357:  14%|█▍        | 3662/25880 [46:50<4:05:24,  1.51it/s]
1|3663|Loss: 0.8808698058128357:  14%|█▍        | 3663/25880 [46:51<4:24:38,  1.40it/s]
1|3664|Loss: 0.7485296726226807:  14%|█▍        | 3663/25880 [46:51<4:24:38,  1.40it/s]
1|3664|Loss: 0.7485296726226807:  14%|█▍        | 3664/25880 [46:51<4:18:23,  1.43it/s]
1|3665|Loss: 0.9525442123413086:  14%|█▍        | 3664/25880 [46:52<4:18:23,  1.43it/s]
1|3665|Loss: 0.9525442123413086:  14%|█▍        | 3665/25880 [46:52<4:09:39,  1.48it/s]
1|3666|Loss: 0.7717122435569763:  14%|█▍        | 3665/25880 [46:52<4:09:39,  1.48it/s]
1|3666|Loss: 0.7717122435569763:  14%|█▍        | 3666/25880 [46:53<4:03:10,  1.52it/s]
1|3667|Loss: 0.7434617280960083:  14%|█▍        | 3666/25880 [46:53<4:03:10,  1.52it/s]
1|3667|Loss: 0.7434617280960083:  14%|█▍        | 3667/25880 [46:53<4:15:13,  1.45it/s]
1|3668|Loss: 0.7649978399276733:  14%|█▍        | 3667/25880 [46:54<4:15:13,  1.45it/s]
1|3668|Loss: 0.7649978399276733:  14%|█▍        | 3668/25880 [46:54<4:30:02,  1.37it/s]
1|3669|Loss: 0.9122374057769775:  14%|█▍        | 3668/25880 [46:55<4:30:02,  1.37it/s]
1|3669|Loss: 0.9122374057769775:  14%|█▍        | 3669/25880 [46:55<4:22:25,  1.41it/s]
1|3670|Loss: 0.8164748549461365:  14%|█▍        | 3669/25880 [46:55<4:22:25,  1.41it/s]
1|3670|Loss: 0.8164748549461365:  14%|█▍        | 3670/25880 [46:56<4:23:21,  1.41it/s]
1|3671|Loss: 0.7337178587913513:  14%|█▍        | 3670/25880 [46:56<4:23:21,  1.41it/s]
1|3671|Loss: 0.7337178587913513:  14%|█▍        | 3671/25880 [46:56<4:46:04,  1.29it/s]
1|3672|Loss: 0.858171284198761:  14%|█▍        | 3671/25880 [46:57<4:46:04,  1.29it/s] 
1|3672|Loss: 0.858171284198761:  14%|█▍        | 3672/25880 [46:57<4:37:51,  1.33it/s]
1|3673|Loss: 0.8116559982299805:  14%|█▍        | 3672/25880 [46:58<4:37:51,  1.33it/s]
1|3673|Loss: 0.8116559982299805:  14%|█▍        | 3673/25880 [46:58<4:40:20,  1.32it/s]
1|3674|Loss: 0.9247543811798096:  14%|█▍        | 3673/25880 [46:58<4:40:20,  1.32it/s]
1|3674|Loss: 0.9247543811798096:  14%|█▍        | 3674/25880 [46:59<4:47:10,  1.29it/s]
1|3675|Loss: 0.8514589667320251:  14%|█▍        | 3674/25880 [46:59<4:47:10,  1.29it/s]
1|3675|Loss: 0.8514589667320251:  14%|█▍        | 3675/25880 [46:59<4:44:32,  1.30it/s]
1|3676|Loss: 0.8858110904693604:  14%|█▍        | 3675/25880 [47:00<4:44:32,  1.30it/s]
1|3676|Loss: 0.8858110904693604:  14%|█▍        | 3676/25880 [47:00<4:40:42,  1.32it/s]
1|3677|Loss: 0.9454788565635681:  14%|█▍        | 3676/25880 [47:01<4:40:42,  1.32it/s]
1|3677|Loss: 0.9454788565635681:  14%|█▍        | 3677/25880 [47:01<4:38:14,  1.33it/s]
1|3678|Loss: 0.9271767735481262:  14%|█▍        | 3677/25880 [47:01<4:38:14,  1.33it/s]
1|3678|Loss: 0.9271767735481262:  14%|█▍        | 3678/25880 [47:02<4:34:43,  1.35it/s]
1|3679|Loss: 0.7553406357765198:  14%|█▍        | 3678/25880 [47:02<4:34:43,  1.35it/s]
1|3679|Loss: 0.7553406357765198:  14%|█▍        | 3679/25880 [47:02<4:37:52,  1.33it/s]
1|3680|Loss: 0.8730389475822449:  14%|█▍        | 3679/25880 [47:03<4:37:52,  1.33it/s]
1|3680|Loss: 0.8730389475822449:  14%|█▍        | 3680/25880 [47:03<4:38:21,  1.33it/s]
1|3681|Loss: 0.8582329750061035:  14%|█▍        | 3680/25880 [47:04<4:38:21,  1.33it/s]
1|3681|Loss: 0.8582329750061035:  14%|█▍        | 3681/25880 [47:04<4:23:21,  1.40it/s]
1|3682|Loss: 0.9564576148986816:  14%|█▍        | 3681/25880 [47:04<4:23:21,  1.40it/s]
1|3682|Loss: 0.9564576148986816:  14%|█▍        | 3682/25880 [47:05<4:21:56,  1.41it/s]
1|3683|Loss: 0.8525969982147217:  14%|█▍        | 3682/25880 [47:05<4:21:56,  1.41it/s]
1|3683|Loss: 0.8525969982147217:  14%|█▍        | 3683/25880 [47:05<4:24:23,  1.40it/s]
1|3684|Loss: 0.801685631275177:  14%|█▍        | 3683/25880 [47:06<4:24:23,  1.40it/s] 
1|3684|Loss: 0.801685631275177:  14%|█▍        | 3684/25880 [47:06<4:26:00,  1.39it/s]
1|3685|Loss: 0.9351202249526978:  14%|█▍        | 3684/25880 [47:06<4:26:00,  1.39it/s]
1|3685|Loss: 0.9351202249526978:  14%|█▍        | 3685/25880 [47:07<4:28:29,  1.38it/s]
1|3686|Loss: 0.7855160236358643:  14%|█▍        | 3685/25880 [47:07<4:28:29,  1.38it/s]
1|3686|Loss: 0.7855160236358643:  14%|█▍        | 3686/25880 [47:07<4:21:14,  1.42it/s]
1|3687|Loss: 0.9692797660827637:  14%|█▍        | 3686/25880 [47:08<4:21:14,  1.42it/s]
1|3687|Loss: 0.9692797660827637:  14%|█▍        | 3687/25880 [47:08<4:22:25,  1.41it/s]
1|3688|Loss: 0.9439224004745483:  14%|█▍        | 3687/25880 [47:08<4:22:25,  1.41it/s]
1|3688|Loss: 0.9439224004745483:  14%|█▍        | 3688/25880 [47:09<4:15:10,  1.45it/s]
1|3689|Loss: 0.8518128395080566:  14%|█▍        | 3688/25880 [47:09<4:15:10,  1.45it/s]
1|3689|Loss: 0.8518128395080566:  14%|█▍        | 3689/25880 [47:09<3:57:43,  1.56it/s]
1|3690|Loss: 0.9059221744537354:  14%|█▍        | 3689/25880 [47:10<3:57:43,  1.56it/s]
1|3690|Loss: 0.9059221744537354:  14%|█▍        | 3690/25880 [47:10<3:42:45,  1.66it/s]
1|3691|Loss: 0.9532309770584106:  14%|█▍        | 3690/25880 [47:10<3:42:45,  1.66it/s]
1|3691|Loss: 0.9532309770584106:  14%|█▍        | 3691/25880 [47:10<3:50:10,  1.61it/s]
1|3692|Loss: 0.7300285696983337:  14%|█▍        | 3691/25880 [47:11<3:50:10,  1.61it/s]
1|3692|Loss: 0.7300285696983337:  14%|█▍        | 3692/25880 [47:11<4:15:56,  1.44it/s]
1|3693|Loss: 0.8740664124488831:  14%|█▍        | 3692/25880 [47:12<4:15:56,  1.44it/s]
1|3693|Loss: 0.8740664124488831:  14%|█▍        | 3693/25880 [47:12<4:29:03,  1.37it/s]
1|3694|Loss: 0.9428248405456543:  14%|█▍        | 3693/25880 [47:13<4:29:03,  1.37it/s]
1|3694|Loss: 0.9428248405456543:  14%|█▍        | 3694/25880 [47:13<4:27:52,  1.38it/s]
1|3695|Loss: 0.7917133569717407:  14%|█▍        | 3694/25880 [47:13<4:27:52,  1.38it/s]
1|3695|Loss: 0.7917133569717407:  14%|█▍        | 3695/25880 [47:13<4:19:30,  1.42it/s]
1|3696|Loss: 0.7969850301742554:  14%|█���        | 3695/25880 [47:14<4:19:30,  1.42it/s]
1|3696|Loss: 0.7969850301742554:  14%|█▍        | 3696/25880 [47:14<4:10:07,  1.48it/s]
1|3697|Loss: 0.9585433006286621:  14%|█▍        | 3696/25880 [47:14<4:10:07,  1.48it/s]
1|3697|Loss: 0.9585433006286621:  14%|█▍        | 3697/25880 [47:15<4:13:21,  1.46it/s]
1|3698|Loss: 0.810751736164093:  14%|█▍        | 3697/25880 [47:15<4:13:21,  1.46it/s] 
1|3698|Loss: 0.810751736164093:  14%|█▍        | 3698/25880 [47:15<3:53:56,  1.58it/s]
1|3699|Loss: 0.935329258441925:  14%|█▍        | 3698/25880 [47:16<3:53:56,  1.58it/s]
1|3699|Loss: 0.935329258441925:  14%|█▍        | 3699/25880 [47:16<3:55:08,  1.57it/s]
1|3700|Loss: 0.7571300268173218:  14%|█▍        | 3699/25880 [47:16<3:55:08,  1.57it/s]
1|3700|Loss: 0.7571300268173218:  14%|█▍        | 3700/25880 [47:17<4:27:19,  1.38it/s]
1|3701|Loss: 0.9607648849487305:  14%|█▍        | 3700/25880 [47:17<4:27:19,  1.38it/s]
1|3701|Loss: 0.9607648849487305:  14%|█▍        | 3701/25880 [47:18<4:35:20,  1.34it/s]
1|3702|Loss: 0.8367343544960022:  14%|█▍        | 3701/25880 [47:18<4:35:20,  1.34it/s]
1|3702|Loss: 0.8367343544960022:  14%|█▍        | 3702/25880 [47:18<4:34:59,  1.34it/s]
1|3703|Loss: 0.8362496495246887:  14%|█▍        | 3702/25880 [47:19<4:34:59,  1.34it/s]
1|3703|Loss: 0.8362496495246887:  14%|█▍        | 3703/25880 [47:19<4:47:12,  1.29it/s]
1|3704|Loss: 0.6735065579414368:  14%|█▍        | 3703/25880 [47:20<4:47:12,  1.29it/s]
1|3704|Loss: 0.6735065579414368:  14%|█▍        | 3704/25880 [47:20<4:38:15,  1.33it/s]
1|3705|Loss: 0.6890023350715637:  14%|█▍        | 3704/25880 [47:20<4:38:15,  1.33it/s]
1|3705|Loss: 0.6890023350715637:  14%|█▍        | 3705/25880 [47:21<4:34:04,  1.35it/s]
1|3706|Loss: 0.9820160269737244:  14%|█▍        | 3705/25880 [47:21<4:34:04,  1.35it/s]
1|3706|Loss: 0.9820160269737244:  14%|█▍        | 3706/25880 [47:21<4:32:57,  1.35it/s]
1|3707|Loss: 0.9182315468788147:  14%|█▍        | 3706/25880 [47:22<4:32:57,  1.35it/s]
1|3707|Loss: 0.9182315468788147:  14%|█▍        | 3707/25880 [47:22<4:38:17,  1.33it/s]
1|3708|Loss: 0.830352246761322:  14%|█▍        | 3707/25880 [47:23<4:38:17,  1.33it/s] 
1|3708|Loss: 0.830352246761322:  14%|█▍        | 3708/25880 [47:23<4:38:27,  1.33it/s]
1|3709|Loss: 0.8534124493598938:  14%|█▍        | 3708/25880 [47:23<4:38:27,  1.33it/s]
1|3709|Loss: 0.8534124493598938:  14%|█▍        | 3709/25880 [47:24<4:20:56,  1.42it/s]
1|3710|Loss: 0.8422062397003174:  14%|█▍        | 3709/25880 [47:24<4:20:56,  1.42it/s]
1|3710|Loss: 0.8422062397003174:  14%|█▍        | 3710/25880 [47:24<4:20:31,  1.42it/s]
1|3711|Loss: 0.8727200627326965:  14%|█▍        | 3710/25880 [47:25<4:20:31,  1.42it/s]
1|3711|Loss: 0.8727200627326965:  14%|█▍        | 3711/25880 [47:25<4:25:28,  1.39it/s]
1|3712|Loss: 0.9153271317481995:  14%|█▍        | 3711/25880 [47:25<4:25:28,  1.39it/s]
1|3712|Loss: 0.9153271317481995:  14%|█▍        | 3712/25880 [47:26<4:36:27,  1.34it/s]
1|3713|Loss: 0.8746630549430847:  14%|█▍        | 3712/25880 [47:26<4:36:27,  1.34it/s]
1|3713|Loss: 0.8746630549430847:  14%|█▍        | 3713/25880 [47:27<4:42:52,  1.31it/s]
1|3714|Loss: 0.9980249404907227:  14%|█▍        | 3713/25880 [47:27<4:42:52,  1.31it/s]
1|3714|Loss: 0.9980249404907227:  14%|█▍        | 3714/25880 [47:27<4:50:57,  1.27it/s]
1|3715|Loss: 0.9067897200584412:  14%|█▍        | 3714/25880 [47:28<4:50:57,  1.27it/s]
1|3715|Loss: 0.9067897200584412:  14%|█▍        | 3715/25880 [47:28<4:40:00,  1.32it/s]
1|3716|Loss: 1.0052227973937988:  14%|█▍        | 3715/25880 [47:29<4:40:00,  1.32it/s]
1|3716|Loss: 1.0052227973937988:  14%|█▍        | 3716/25880 [47:29<4:52:26,  1.26it/s]
1|3717|Loss: 0.8576149344444275:  14%|█▍        | 3716/25880 [47:29<4:52:26,  1.26it/s]
1|3717|Loss: 0.8576149344444275:  14%|█▍        | 3717/25880 [47:30<4:49:33,  1.28it/s]
1|3718|Loss: 0.8783923387527466:  14%|█▍        | 3717/25880 [47:30<4:49:33,  1.28it/s]
1|3718|Loss: 0.8783923387527466:  14%|█▍        | 3718/25880 [47:31<5:03:24,  1.22it/s]
1|3719|Loss: 0.9650020003318787:  14%|█▍        | 3718/25880 [47:31<5:03:24,  1.22it/s]
1|3719|Loss: 0.9650020003318787:  14%|█▍        | 3719/25880 [47:32<5:11:49,  1.18it/s]
1|3720|Loss: 0.8317450284957886:  14%|█▍        | 3719/25880 [47:32<5:11:49,  1.18it/s]
1|3720|Loss: 0.8317450284957886:  14%|█▍        | 3720/25880 [47:32<4:54:39,  1.25it/s]
1|3721|Loss: 0.8602471947669983:  14%|█▍        | 3720/25880 [47:33<4:54:39,  1.25it/s]
1|3721|Loss: 0.8602471947669983:  14%|█▍        | 3721/25880 [47:33<4:45:47,  1.29it/s]
1|3722|Loss: 0.8092371821403503:  14%|█▍        | 3721/25880 [47:33<4:45:47,  1.29it/s]
1|3722|Loss: 0.8092371821403503:  14%|█▍        | 3722/25880 [47:34<4:42:40,  1.31it/s]
1|3723|Loss: 0.8999777436256409:  14%|█▍        | 3722/25880 [47:34<4:42:40,  1.31it/s]
1|3723|Loss: 0.8999777436256409:  14%|█▍        | 3723/25880 [47:35<4:48:16,  1.28it/s]
1|3724|Loss: 0.8136498928070068:  14%|█▍        | 3723/25880 [47:35<4:48:16,  1.28it/s]
1|3724|Loss: 0.8136498928070068:  14%|█▍        | 3724/25880 [47:35<4:25:05,  1.39it/s]
1|3725|Loss: 1.1487444639205933:  14%|█▍        | 3724/25880 [47:35<4:25:05,  1.39it/s]
1|3725|Loss: 1.1487444639205933:  14%|█▍        | 3725/25880 [47:36<4:02:05,  1.53it/s]
1|3726|Loss: 0.9455670118331909:  14%|█▍        | 3725/25880 [47:36<4:02:05,  1.53it/s]
1|3726|Loss: 0.9455670118331909:  14%|█▍        | 3726/25880 [47:36<4:06:56,  1.50it/s]
1|3727|Loss: 0.8265326619148254:  14%|█▍        | 3726/25880 [47:37<4:06:56,  1.50it/s]
1|3727|Loss: 0.8265326619148254:  14%|█▍        | 3727/25880 [47:37<4:28:39,  1.37it/s]
1|3728|Loss: 0.7384651899337769:  14%|█▍        | 3727/25880 [47:38<4:28:39,  1.37it/s]
1|3728|Loss: 0.7384651899337769:  14%|█▍        | 3728/25880 [47:38<4:24:43,  1.39it/s]
1|3729|Loss: 0.9974960088729858:  14%|█▍        | 3728/25880 [47:38<4:24:43,  1.39it/s]
1|3729|Loss: 0.9974960088729858:  14%|█▍        | 3729/25880 [47:38<4:04:12,  1.51it/s]
1|3730|Loss: 0.9229689240455627:  14%|█▍        | 3729/25880 [47:39<4:04:12,  1.51it/s]
1|3730|Loss: 0.9229689240455627:  14%|█▍        | 3730/25880 [47:39<4:04:05,  1.51it/s]
1|3731|Loss: 0.9603754281997681:  14%|█▍        | 3730/25880 [47:39<4:04:05,  1.51it/s]
1|3731|Loss: 0.9603754281997681:  14%|█▍        | 3731/25880 [47:40<3:58:05,  1.55it/s]
1|3732|Loss: 0.7671096920967102:  14%|█▍        | 3731/25880 [47:40<3:58:05,  1.55it/s]
1|3732|Loss: 0.7671096920967102:  14%|█▍        | 3732/25880 [47:40<4:03:53,  1.51it/s]
1|3733|Loss: 0.8037899732589722:  14%|█▍        | 3732/25880 [47:41<4:03:53,  1.51it/s]
1|3733|Loss: 0.8037899732589722:  14%|█▍        | 3733/25880 [47:41<4:12:11,  1.46it/s]
1|3734|Loss: 0.8815047740936279:  14%|█▍        | 3733/25880 [47:42<4:12:11,  1.46it/s]
1|3734|Loss: 0.8815047740936279:  14%|█▍        | 3734/25880 [47:42<4:08:00,  1.49it/s]
1|3735|Loss: 0.992649257183075:  14%|█▍        | 3734/25880 [47:42<4:08:00,  1.49it/s] 
1|3735|Loss: 0.992649257183075:  14%|█▍        | 3735/25880 [47:43<4:13:32,  1.46it/s]
1|3736|Loss: 0.9332329034805298:  14%|█▍        | 3735/25880 [47:43<4:13:32,  1.46it/s]
1|3736|Loss: 0.9332329034805298:  14%|█▍        | 3736/25880 [47:43<4:19:42,  1.42it/s]
1|3737|Loss: 0.9461117386817932:  14%|█▍        | 3736/25880 [47:44<4:19:42,  1.42it/s]
1|3737|Loss: 0.9461117386817932:  14%|█▍        | 3737/25880 [47:44<4:23:06,  1.40it/s]
1|3738|Loss: 0.7443382740020752:  14%|█▍        | 3737/25880 [47:44<4:23:06,  1.40it/s]
1|3738|Loss: 0.7443382740020752:  14%|█▍        | 3738/25880 [47:45<4:33:11,  1.35it/s]
1|3739|Loss: 0.9322798252105713:  14%|█▍        | 3738/25880 [47:45<4:33:11,  1.35it/s]
1|3739|Loss: 0.9322798252105713:  14%|█▍        | 3739/25880 [47:45<4:26:13,  1.39it/s]
1|3740|Loss: 1.0178288221359253:  14%|█▍        | 3739/25880 [47:46<4:26:13,  1.39it/s]
1|3740|Loss: 1.0178288221359253:  14%|█▍        | 3740/25880 [47:46<4:37:52,  1.33it/s]
1|3741|Loss: 0.9285174608230591:  14%|█▍        | 3740/25880 [47:47<4:37:52,  1.33it/s]
1|3741|Loss: 0.9285174608230591:  14%|█▍        | 3741/25880 [47:47<4:48:08,  1.28it/s]
1|3742|Loss: 0.9286137223243713:  14%|█▍        | 3741/25880 [47:48<4:48:08,  1.28it/s]
1|3742|Loss: 0.9286137223243713:  14%|█▍        | 3742/25880 [47:48<4:42:36,  1.31it/s]
1|3743|Loss: 0.8041118383407593:  14%|█▍        | 3742/25880 [47:48<4:42:36,  1.31it/s]
1|3743|Loss: 0.8041118383407593:  14%|█▍        | 3743/25880 [47:49<4:35:44,  1.34it/s]
1|3744|Loss: 0.8337352275848389:  14%|█▍        | 3743/25880 [47:49<4:35:44,  1.34it/s]
1|3744|Loss: 0.8337352275848389:  14%|█▍        | 3744/25880 [47:49<4:34:45,  1.34it/s]
1|3745|Loss: 0.8396416306495667:  14%|█▍        | 3744/25880 [47:50<4:34:45,  1.34it/s]
1|3745|Loss: 0.8396416306495667:  14%|█▍        | 3745/25880 [47:50<4:45:22,  1.29it/s]
1|3746|Loss: 0.844407320022583:  14%|█▍        | 3745/25880 [47:51<4:45:22,  1.29it/s] 
1|3746|Loss: 0.844407320022583:  14%|█▍        | 3746/25880 [47:51<4:45:32,  1.29it/s]
1|3747|Loss: 0.8722508549690247:  14%|█▍        | 3746/25880 [47:51<4:45:32,  1.29it/s]
1|3747|Loss: 0.8722508549690247:  14%|█▍        | 3747/25880 [47:52<4:21:41,  1.41it/s]
1|3748|Loss: 0.8803957104682922:  14%|█▍        | 3747/25880 [47:52<4:21:41,  1.41it/s]
1|3748|Loss: 0.8803957104682922:  14%|█▍        | 3748/25880 [47:52<4:03:33,  1.51it/s]
1|3749|Loss: 0.9377619028091431:  14%|█▍        | 3748/25880 [47:52<4:03:33,  1.51it/s]
1|3749|Loss: 0.9377619028091431:  14%|█▍        | 3749/25880 [47:53<4:09:15,  1.48it/s]
1|3750|Loss: 0.8471629023551941:  14%|█▍        | 3749/25880 [47:53<4:09:15,  1.48it/s]
1|3750|Loss: 0.8471629023551941:  14%|█▍        | 3750/25880 [47:53<4:06:01,  1.50it/s]
1|3751|Loss: 0.8675470948219299:  14%|█▍        | 3750/25880 [47:54<4:06:01,  1.50it/s]
1|3751|Loss: 0.8675470948219299:  14%|█▍        | 3751/25880 [47:54<4:00:03,  1.54it/s]
1|3752|Loss: 0.8433341979980469:  14%|█▍        | 3751/25880 [47:54<4:00:03,  1.54it/s]
1|3752|Loss: 0.8433341979980469:  14%|█▍        | 3752/25880 [47:55<4:04:09,  1.51it/s]
1|3753|Loss: 0.9329544901847839:  14%|█▍        | 3752/25880 [47:55<4:04:09,  1.51it/s]
1|3753|Loss: 0.9329544901847839:  15%|█▍        | 3753/25880 [47:56<4:24:08,  1.40it/s]
1|3754|Loss: 0.9548348784446716:  15%|█▍        | 3753/25880 [47:56<4:24:08,  1.40it/s]
1|3754|Loss: 0.9548348784446716:  15%|█▍        | 3754/25880 [47:56<4:21:57,  1.41it/s]
1|3755|Loss: 0.8266135454177856:  15%|█▍        | 3754/25880 [47:57<4:21:57,  1.41it/s]
1|3755|Loss: 0.8266135454177856:  15%|█▍        | 3755/25880 [47:57<4:35:22,  1.34it/s]
1|3756|Loss: 0.9221526980400085:  15%|█▍        | 3755/25880 [47:57<4:35:22,  1.34it/s]
1|3756|Loss: 0.9221526980400085:  15%|█▍        | 3756/25880 [47:58<4:18:20,  1.43it/s]
1|3757|Loss: 0.9212915301322937:  15%|█▍        | 3756/25880 [47:58<4:18:20,  1.43it/s]
1|3757|Loss: 0.9212915301322937:  15%|█▍        | 3757/25880 [47:58<4:13:31,  1.45it/s]
1|3758|Loss: 0.9730325937271118:  15%|█▍        | 3757/25880 [47:59<4:13:31,  1.45it/s]
1|3758|Loss: 0.9730325937271118:  15%|█▍        | 3758/25880 [47:59<4:26:37,  1.38it/s]
1|3759|Loss: 0.9088011980056763:  15%|█▍        | 3758/25880 [48:00<4:26:37,  1.38it/s]
1|3759|Loss: 0.9088011980056763:  15%|█▍        | 3759/25880 [48:00<4:21:43,  1.41it/s]
1|3760|Loss: 0.9667731523513794:  15%|█▍        | 3759/25880 [48:00<4:21:43,  1.41it/s]
1|3760|Loss: 0.9667731523513794:  15%|█▍        | 3760/25880 [48:01<4:23:54,  1.40it/s]
1|3761|Loss: 0.9038373827934265:  15%|█▍        | 3760/25880 [48:01<4:23:54,  1.40it/s]
1|3761|Loss: 0.9038373827934265:  15%|█▍        | 3761/25880 [48:01<4:18:07,  1.43it/s]
1|3762|Loss: 0.846203625202179:  15%|█▍        | 3761/25880 [48:02<4:18:07,  1.43it/s] 
1|3762|Loss: 0.846203625202179:  15%|█▍        | 3762/25880 [48:02<3:58:00,  1.55it/s]
1|3763|Loss: 0.7722275853157043:  15%|█▍        | 3762/25880 [48:02<3:58:00,  1.55it/s]
1|3763|Loss: 0.7722275853157043:  15%|█▍        | 3763/25880 [48:02<4:10:20,  1.47it/s]
1|3764|Loss: 0.9311435222625732:  15%|█▍        | 3763/25880 [48:03<4:10:20,  1.47it/s]
1|3764|Loss: 0.9311435222625732:  15%|█▍        | 3764/25880 [48:03<4:30:27,  1.36it/s]
1|3765|Loss: 0.79319828748703:  15%|█▍        | 3764/25880 [48:04<4:30:27,  1.36it/s]  
1|3765|Loss: 0.79319828748703:  15%|█▍        | 3765/25880 [48:04<4:14:45,  1.45it/s]
1|3766|Loss: 0.7155653238296509:  15%|█▍        | 3765/25880 [48:04<4:14:45,  1.45it/s]
1|3766|Loss: 0.7155653238296509:  15%|█▍        | 3766/25880 [48:05<4:24:08,  1.40it/s]
1|3767|Loss: 0.8855218887329102:  15%|█▍        | 3766/25880 [48:05<4:24:08,  1.40it/s]
1|3767|Loss: 0.8855218887329102:  15%|█▍        | 3767/25880 [48:05<4:26:17,  1.38it/s]
1|3768|Loss: 0.9204884171485901:  15%|█▍        | 3767/25880 [48:06<4:26:17,  1.38it/s]
1|3768|Loss: 0.9204884171485901:  15%|█▍        | 3768/25880 [48:06<4:24:12,  1.39it/s]
1|3769|Loss: 0.8068779110908508:  15%|█▍        | 3768/25880 [48:07<4:24:12,  1.39it/s]
1|3769|Loss: 0.8068779110908508:  15%|█▍        | 3769/25880 [48:07<4:22:38,  1.40it/s]
1|3770|Loss: 0.8881115913391113:  15%|█▍        | 3769/25880 [48:07<4:22:38,  1.40it/s]
1|3770|Loss: 0.8881115913391113:  15%|█▍        | 3770/25880 [48:07<4:13:14,  1.46it/s]
1|3771|Loss: 1.040774941444397:  15%|█▍        | 3770/25880 [48:08<4:13:14,  1.46it/s] 
1|3771|Loss: 1.040774941444397:  15%|█▍        | 3771/25880 [48:08<4:07:07,  1.49it/s]
1|3772|Loss: 0.8430459499359131:  15%|█▍        | 3771/25880 [48:08<4:07:07,  1.49it/s]
1|3772|Loss: 0.8430459499359131:  15%|█▍        | 3772/25880 [48:09<4:12:27,  1.46it/s]
1|3773|Loss: 0.8788660168647766:  15%|█▍        | 3772/25880 [48:09<4:12:27,  1.46it/s]
1|3773|Loss: 0.8788660168647766:  15%|█▍        | 3773/25880 [48:10<4:18:22,  1.43it/s]
1|3774|Loss: 0.9485262632369995:  15%|█▍        | 3773/25880 [48:10<4:18:22,  1.43it/s]
1|3774|Loss: 0.9485262632369995:  15%|█▍        | 3774/25880 [48:10<4:19:45,  1.42it/s]
1|3775|Loss: 0.8758771419525146:  15%|█▍        | 3774/25880 [48:11<4:19:45,  1.42it/s]
1|3775|Loss: 0.8758771419525146:  15%|█▍        | 3775/25880 [48:11<4:08:34,  1.48it/s]
1|3776|Loss: 0.8391525745391846:  15%|█▍        | 3775/25880 [48:11<4:08:34,  1.48it/s]
1|3776|Loss: 0.8391525745391846:  15%|█▍        | 3776/25880 [48:12<4:26:48,  1.38it/s]
1|3777|Loss: 0.8779064416885376:  15%|█▍        | 3776/25880 [48:12<4:26:48,  1.38it/s]
1|3777|Loss: 0.8779064416885376:  15%|█▍        | 3777/25880 [48:12<4:20:52,  1.41it/s]
1|3778|Loss: 0.7026335000991821:  15%|█▍        | 3777/25880 [48:13<4:20:52,  1.41it/s]
1|3778|Loss: 0.7026335000991821:  15%|█▍        | 3778/25880 [48:13<4:23:24,  1.40it/s]
1|3779|Loss: 0.840124249458313:  15%|█▍        | 3778/25880 [48:14<4:23:24,  1.40it/s] 
1|3779|Loss: 0.840124249458313:  15%|█▍        | 3779/25880 [48:14<4:38:55,  1.32it/s]
1|3780|Loss: 0.9397749304771423:  15%|█▍        | 3779/25880 [48:14<4:38:55,  1.32it/s]
1|3780|Loss: 0.9397749304771423:  15%|█▍        | 3780/25880 [48:15<4:36:39,  1.33it/s]
1|3781|Loss: 0.7428768277168274:  15%|█▍        | 3780/25880 [48:15<4:36:39,  1.33it/s]
1|3781|Loss: 0.7428768277168274:  15%|█▍        | 3781/25880 [48:15<4:30:54,  1.36it/s]
1|3782|Loss: 0.9928562641143799:  15%|█▍        | 3781/25880 [48:16<4:30:54,  1.36it/s]
1|3782|Loss: 0.9928562641143799:  15%|█▍        | 3782/25880 [48:16<4:30:37,  1.36it/s]
1|3783|Loss: 0.8916002511978149:  15%|█▍        | 3782/25880 [48:17<4:30:37,  1.36it/s]
1|3783|Loss: 0.8916002511978149:  15%|█▍        | 3783/25880 [48:17<4:47:27,  1.28it/s]
1|3784|Loss: 0.7964428067207336:  15%|█▍        | 3783/25880 [48:17<4:47:27,  1.28it/s]
1|3784|Loss: 0.7964428067207336:  15%|█▍        | 3784/25880 [48:18<4:37:37,  1.33it/s]
1|3785|Loss: 0.9061199426651001:  15%|█▍        | 3784/25880 [48:18<4:37:37,  1.33it/s]
1|3785|Loss: 0.9061199426651001:  15%|█▍        | 3785/25880 [48:18<4:32:43,  1.35it/s]
1|3786|Loss: 0.8726207613945007:  15%|█▍        | 3785/25880 [48:19<4:32:43,  1.35it/s]
1|3786|Loss: 0.8726207613945007:  15%|█▍        | 3786/25880 [48:19<4:47:59,  1.28it/s]
1|3787|Loss: 0.7087450623512268:  15%|█▍        | 3786/25880 [48:20<4:47:59,  1.28it/s]
1|3787|Loss: 0.7087450623512268:  15%|█▍        | 3787/25880 [48:20<4:57:08,  1.24it/s]
1|3788|Loss: 0.9644657969474792:  15%|█▍        | 3787/25880 [48:21<4:57:08,  1.24it/s]
1|3788|Loss: 0.9644657969474792:  15%|█▍        | 3788/25880 [48:21<4:49:15,  1.27it/s]
1|3789|Loss: 0.940625786781311:  15%|█▍        | 3788/25880 [48:21<4:49:15,  1.27it/s] 
1|3789|Loss: 0.940625786781311:  15%|█▍        | 3789/25880 [48:22<4:52:44,  1.26it/s]
1|3790|Loss: 0.7202558517456055:  15%|█▍        | 3789/25880 [48:22<4:52:44,  1.26it/s]
1|3790|Loss: 0.7202558517456055:  15%|█▍        | 3790/25880 [48:22<4:29:04,  1.37it/s]
1|3791|Loss: 0.8964985013008118:  15%|█▍        | 3790/25880 [48:23<4:29:04,  1.37it/s]
1|3791|Loss: 0.8964985013008118:  15%|█▍        | 3791/25880 [48:23<4:20:50,  1.41it/s]
1|3792|Loss: 0.8469313979148865:  15%|█▍        | 3791/25880 [48:23<4:20:50,  1.41it/s]
1|3792|Loss: 0.8469313979148865:  15%|█▍        | 3792/25880 [48:24<4:10:26,  1.47it/s]
1|3793|Loss: 0.9295728206634521:  15%|█▍        | 3792/25880 [48:24<4:10:26,  1.47it/s]
1|3793|Loss: 0.9295728206634521:  15%|█▍        | 3793/25880 [48:25<4:38:17,  1.32it/s]
1|3794|Loss: 0.8836610913276672:  15%|█▍        | 3793/25880 [48:25<4:38:17,  1.32it/s]
1|3794|Loss: 0.8836610913276672:  15%|█▍        | 3794/25880 [48:25<4:59:11,  1.23it/s]
1|3795|Loss: 0.8207736611366272:  15%|█▍        | 3794/25880 [48:26<4:59:11,  1.23it/s]
1|3795|Loss: 0.8207736611366272:  15%|█▍        | 3795/25880 [48:26<4:34:17,  1.34it/s]
1|3796|Loss: 0.9439082145690918:  15%|█▍        | 3795/25880 [48:26<4:34:17,  1.34it/s]
1|3796|Loss: 0.9439082145690918:  15%|█▍        | 3796/25880 [48:27<4:11:53,  1.46it/s]
1|3797|Loss: 0.8216753602027893:  15%|█▍        | 3796/25880 [48:27<4:11:53,  1.46it/s]
1|3797|Loss: 0.8216753602027893:  15%|█▍        | 3797/25880 [48:27<3:59:38,  1.54it/s]
1|3798|Loss: 0.7732767462730408:  15%|█▍        | 3797/25880 [48:28<3:59:38,  1.54it/s]
1|3798|Loss: 0.7732767462730408:  15%|█▍        | 3798/25880 [48:28<4:13:21,  1.45it/s]
1|3799|Loss: 0.807583749294281:  15%|█▍        | 3798/25880 [48:28<4:13:21,  1.45it/s] 
1|3799|Loss: 0.807583749294281:  15%|█▍        | 3799/25880 [48:28<3:49:30,  1.60it/s]
1|3800|Loss: 0.7403662204742432:  15%|█▍        | 3799/25880 [48:29<3:49:30,  1.60it/s]
1|3800|Loss: 0.7403662204742432:  15%|█▍        | 3800/25880 [48:29<3:42:37,  1.65it/s]
1|3801|Loss: 0.8707452416419983:  15%|█▍        | 3800/25880 [48:29<3:42:37,  1.65it/s]
1|3801|Loss: 0.8707452416419983:  15%|█▍        | 3801/25880 [48:30<3:53:52,  1.57it/s]
1|3802|Loss: 0.8661648035049438:  15%|█▍        | 3801/25880 [48:30<3:53:52,  1.57it/s]
1|3802|Loss: 0.8661648035049438:  15%|█▍        | 3802/25880 [48:30<3:57:41,  1.55it/s]
1|3803|Loss: 0.997132420539856:  15%|█▍        | 3802/25880 [48:31<3:57:41,  1.55it/s] 
1|3803|Loss: 0.997132420539856:  15%|█▍        | 3803/25880 [48:31<4:02:36,  1.52it/s]
1|3804|Loss: 0.9773917198181152:  15%|█▍        | 3803/25880 [48:31<4:02:36,  1.52it/s]
1|3804|Loss: 0.9773917198181152:  15%|█▍        | 3804/25880 [48:32<3:56:25,  1.56it/s]
1|3805|Loss: 0.9668604731559753:  15%|█▍        | 3804/25880 [48:32<3:56:25,  1.56it/s]
1|3805|Loss: 0.9668604731559753:  15%|█▍        | 3805/25880 [48:32<3:54:40,  1.57it/s]
1|3806|Loss: 0.8742586970329285:  15%|█▍        | 3805/25880 [48:33<3:54:40,  1.57it/s]
1|3806|Loss: 0.8742586970329285:  15%|█▍        | 3806/25880 [48:33<3:52:34,  1.58it/s]
1|3807|Loss: 0.9605216383934021:  15%|█▍        | 3806/25880 [48:33<3:52:34,  1.58it/s]
1|3807|Loss: 0.9605216383934021:  15%|█▍        | 3807/25880 [48:34<4:00:12,  1.53it/s]
1|3808|Loss: 0.8531419038772583:  15%|█▍        | 3807/25880 [48:34<4:00:12,  1.53it/s]
1|3808|Loss: 0.8531419038772583:  15%|█▍        | 3808/25880 [48:34<4:07:53,  1.48it/s]
1|3809|Loss: 0.775078535079956:  15%|█▍        | 3808/25880 [48:35<4:07:53,  1.48it/s] 
1|3809|Loss: 0.775078535079956:  15%|█▍        | 3809/25880 [48:35<4:13:47,  1.45it/s]
1|3810|Loss: 0.9688682556152344:  15%|█▍        | 3809/25880 [48:35<4:13:47,  1.45it/s]
1|3810|Loss: 0.9688682556152344:  15%|█▍        | 3810/25880 [48:36<4:19:22,  1.42it/s]
1|3811|Loss: 0.8159353733062744:  15%|█▍        | 3810/25880 [48:36<4:19:22,  1.42it/s]
1|3811|Loss: 0.8159353733062744:  15%|█▍        | 3811/25880 [48:36<4:04:08,  1.51it/s]
1|3812|Loss: 0.7914540767669678:  15%|█▍        | 3811/25880 [48:37<4:04:08,  1.51it/s]
1|3812|Loss: 0.7914540767669678:  15%|█▍        | 3812/25880 [48:37<3:58:45,  1.54it/s]
1|3813|Loss: 0.8221476674079895:  15%|█▍        | 3812/25880 [48:37<3:58:45,  1.54it/s]
1|3813|Loss: 0.8221476674079895:  15%|█▍        | 3813/25880 [48:38<4:12:28,  1.46it/s]
1|3814|Loss: 0.9552276134490967:  15%|█▍        | 3813/25880 [48:38<4:12:28,  1.46it/s]
1|3814|Loss: 0.9552276134490967:  15%|█▍        | 3814/25880 [48:38<4:15:25,  1.44it/s]
1|3815|Loss: 0.8483607769012451:  15%|█▍        | 3814/25880 [48:39<4:15:25,  1.44it/s]
1|3815|Loss: 0.8483607769012451:  15%|█▍        | 3815/25880 [48:39<4:02:44,  1.51it/s]
1|3816|Loss: 0.8366242051124573:  15%|█▍        | 3815/25880 [48:39<4:02:44,  1.51it/s]
1|3816|Loss: 0.8366242051124573:  15%|█▍        | 3816/25880 [48:40<4:15:04,  1.44it/s]
1|3817|Loss: 0.803305447101593:  15%|█▍        | 3816/25880 [48:40<4:15:04,  1.44it/s] 
1|3817|Loss: 0.803305447101593:  15%|█▍        | 3817/25880 [48:41<4:21:16,  1.41it/s]
1|3818|Loss: 0.8047807216644287:  15%|█▍        | 3817/25880 [48:41<4:21:16,  1.41it/s]
1|3818|Loss: 0.8047807216644287:  15%|█▍        | 3818/25880 [48:41<4:37:07,  1.33it/s]
1|3819|Loss: 0.8028214573860168:  15%|█▍        | 3818/25880 [48:42<4:37:07,  1.33it/s]
1|3819|Loss: 0.8028214573860168:  15%|█▍        | 3819/25880 [48:42<4:54:49,  1.25it/s]
1|3820|Loss: 0.7791281938552856:  15%|█▍        | 3819/25880 [48:43<4:54:49,  1.25it/s]
1|3820|Loss: 0.7791281938552856:  15%|█▍        | 3820/25880 [48:43<4:43:00,  1.30it/s]
1|3821|Loss: 0.8332204222679138:  15%|█▍        | 3820/25880 [48:43<4:43:00,  1.30it/s]
1|3821|Loss: 0.8332204222679138:  15%|█▍        | 3821/25880 [48:44<4:38:16,  1.32it/s]
1|3822|Loss: 0.7755864262580872:  15%|█▍        | 3821/25880 [48:44<4:38:16,  1.32it/s]
1|3822|Loss: 0.7755864262580872:  15%|█▍        | 3822/25880 [48:44<4:36:46,  1.33it/s]
1|3823|Loss: 0.92049241065979:  15%|█▍        | 3822/25880 [48:45<4:36:46,  1.33it/s]  
1|3823|Loss: 0.92049241065979:  15%|█▍        | 3823/25880 [48:45<4:33:10,  1.35it/s]
1|3824|Loss: 0.8391196727752686:  15%|█▍        | 3823/25880 [48:46<4:33:10,  1.35it/s]
1|3824|Loss: 0.8391196727752686:  15%|█▍        | 3824/25880 [48:46<4:30:37,  1.36it/s]
1|3825|Loss: 0.9150209426879883:  15%|█▍        | 3824/25880 [48:46<4:30:37,  1.36it/s]
1|3825|Loss: 0.9150209426879883:  15%|█▍        | 3825/25880 [48:47<4:37:57,  1.32it/s]
1|3826|Loss: 0.9808279275894165:  15%|█▍        | 3825/25880 [48:47<4:37:57,  1.32it/s]
1|3826|Loss: 0.9808279275894165:  15%|█▍        | 3826/25880 [48:48<4:43:07,  1.30it/s]
1|3827|Loss: 0.9172834753990173:  15%|█▍        | 3826/25880 [48:48<4:43:07,  1.30it/s]
1|3827|Loss: 0.9172834753990173:  15%|█▍        | 3827/25880 [48:48<4:40:07,  1.31it/s]
1|3828|Loss: 0.8446409106254578:  15%|█▍        | 3827/25880 [48:49<4:40:07,  1.31it/s]
1|3828|Loss: 0.8446409106254578:  15%|█▍        | 3828/25880 [48:49<4:42:54,  1.30it/s]
1|3829|Loss: 0.8291469216346741:  15%|█▍        | 3828/25880 [48:49<4:42:54,  1.30it/s]
1|3829|Loss: 0.8291469216346741:  15%|█▍        | 3829/25880 [48:50<4:32:30,  1.35it/s]
1|3830|Loss: 0.7966928482055664:  15%|█▍        | 3829/25880 [48:50<4:32:30,  1.35it/s]
1|3830|Loss: 0.7966928482055664:  15%|█▍        | 3830/25880 [48:51<4:49:53,  1.27it/s]
1|3831|Loss: 0.9041128158569336:  15%|█▍        | 3830/25880 [48:51<4:49:53,  1.27it/s]
1|3831|Loss: 0.9041128158569336:  15%|█▍        | 3831/25880 [48:51<4:50:45,  1.26it/s]
1|3832|Loss: 0.9039232730865479:  15%|█▍        | 3831/25880 [48:52<4:50:45,  1.26it/s]
1|3832|Loss: 0.9039232730865479:  15%|█▍        | 3832/25880 [48:52<4:44:30,  1.29it/s]
1|3833|Loss: 0.8061540126800537:  15%|█▍        | 3832/25880 [48:53<4:44:30,  1.29it/s]
1|3833|Loss: 0.8061540126800537:  15%|█▍        | 3833/25880 [48:53<4:31:03,  1.36it/s]
1|3834|Loss: 0.7925757765769958:  15%|█▍        | 3833/25880 [48:53<4:31:03,  1.36it/s]
1|3834|Loss: 0.7925757765769958:  15%|█▍        | 3834/25880 [48:54<4:27:56,  1.37it/s]
1|3835|Loss: 0.853134036064148:  15%|█▍        | 3834/25880 [48:54<4:27:56,  1.37it/s] 
1|3835|Loss: 0.853134036064148:  15%|█▍        | 3835/25880 [48:54<4:27:48,  1.37it/s]
1|3836|Loss: 0.7178382277488708:  15%|█▍        | 3835/25880 [48:55<4:27:48,  1.37it/s]
1|3836|Loss: 0.7178382277488708:  15%|█▍        | 3836/25880 [48:55<4:25:44,  1.38it/s]
1|3837|Loss: 1.0174660682678223:  15%|█▍        | 3836/25880 [48:55<4:25:44,  1.38it/s]
1|3837|Loss: 1.0174660682678223:  15%|█▍        | 3837/25880 [48:56<4:26:26,  1.38it/s]
1|3838|Loss: 0.9397481679916382:  15%|█▍        | 3837/25880 [48:56<4:26:26,  1.38it/s]
1|3838|Loss: 0.9397481679916382:  15%|█▍        | 3838/25880 [48:56<4:27:46,  1.37it/s]
1|3839|Loss: 0.9554451704025269:  15%|█▍        | 3838/25880 [48:57<4:27:46,  1.37it/s]
1|3839|Loss: 0.9554451704025269:  15%|█▍        | 3839/25880 [48:57<4:28:25,  1.37it/s]
1|3840|Loss: 0.845232367515564:  15%|█▍        | 3839/25880 [48:58<4:28:25,  1.37it/s] 
1|3840|Loss: 0.845232367515564:  15%|█▍        | 3840/25880 [48:58<4:18:34,  1.42it/s]
1|3841|Loss: 0.8807134032249451:  15%|█▍        | 3840/25880 [48:58<4:18:34,  1.42it/s]
1|3841|Loss: 0.8807134032249451:  15%|█▍        | 3841/25880 [48:58<4:10:45,  1.46it/s]
1|3842|Loss: 0.8182202577590942:  15%|█▍        | 3841/25880 [48:59<4:10:45,  1.46it/s]
1|3842|Loss: 0.8182202577590942:  15%|█▍        | 3842/25880 [48:59<4:19:26,  1.42it/s]
1|3843|Loss: 0.8478305339813232:  15%|█▍        | 3842/25880 [49:00<4:19:26,  1.42it/s]
1|3843|Loss: 0.8478305339813232:  15%|█▍        | 3843/25880 [49:00<4:32:13,  1.35it/s]
1|3844|Loss: 0.9184973835945129:  15%|█▍        | 3843/25880 [49:00<4:32:13,  1.35it/s]
1|3844|Loss: 0.9184973835945129:  15%|█▍        | 3844/25880 [49:01<4:30:27,  1.36it/s]
1|3845|Loss: 0.9001180529594421:  15%|█▍        | 3844/25880 [49:01<4:30:27,  1.36it/s]
1|3845|Loss: 0.9001180529594421:  15%|█▍        | 3845/25880 [49:01<4:10:54,  1.46it/s]
1|3846|Loss: 0.9039636850357056:  15%|█▍        | 3845/25880 [49:02<4:10:54,  1.46it/s]
1|3846|Loss: 0.9039636850357056:  15%|█▍        | 3846/25880 [49:02<4:20:20,  1.41it/s]
1|3847|Loss: 0.7544320821762085:  15%|█▍        | 3846/25880 [49:03<4:20:20,  1.41it/s]
1|3847|Loss: 0.7544320821762085:  15%|█▍        | 3847/25880 [49:03<4:24:58,  1.39it/s]
1|3848|Loss: 0.7769256830215454:  15%|█▍        | 3847/25880 [49:03<4:24:58,  1.39it/s]
1|3848|Loss: 0.7769256830215454:  15%|█▍        | 3848/25880 [49:04<4:18:34,  1.42it/s]
1|3849|Loss: 1.0636695623397827:  15%|█▍        | 3848/25880 [49:04<4:18:34,  1.42it/s]
1|3849|Loss: 1.0636695623397827:  15%|█▍        | 3849/25880 [49:04<4:12:16,  1.46it/s]
1|3850|Loss: 0.8045573234558105:  15%|█▍        | 3849/25880 [49:05<4:12:16,  1.46it/s]
1|3850|Loss: 0.8045573234558105:  15%|█▍        | 3850/25880 [49:05<4:20:58,  1.41it/s]
1|3851|Loss: 0.7363927960395813:  15%|█▍        | 3850/25880 [49:05<4:20:58,  1.41it/s]
1|3851|Loss: 0.7363927960395813:  15%|█▍        | 3851/25880 [49:05<4:00:13,  1.53it/s]
1|3852|Loss: 0.7715814709663391:  15%|█▍        | 3851/25880 [49:06<4:00:13,  1.53it/s]
1|3852|Loss: 0.7715814709663391:  15%|█▍        | 3852/25880 [49:06<4:10:50,  1.46it/s]
1|3853|Loss: 0.8984622955322266:  15%|█▍        | 3852/25880 [49:07<4:10:50,  1.46it/s]
1|3853|Loss: 0.8984622955322266:  15%|█▍        | 3853/25880 [49:07<4:09:57,  1.47it/s]
1|3854|Loss: 0.8145310878753662:  15%|█▍        | 3853/25880 [49:07<4:09:57,  1.47it/s]
1|3854|Loss: 0.8145310878753662:  15%|█▍        | 3854/25880 [49:07<4:01:33,  1.52it/s]
1|3855|Loss: 0.8216450214385986:  15%|█▍        | 3854/25880 [49:08<4:01:33,  1.52it/s]
1|3855|Loss: 0.8216450214385986:  15%|█▍        | 3855/25880 [49:08<4:06:57,  1.49it/s]
1|3856|Loss: 0.8780025243759155:  15%|█▍        | 3855/25880 [49:09<4:06:57,  1.49it/s]
1|3856|Loss: 0.8780025243759155:  15%|█▍        | 3856/25880 [49:09<4:14:31,  1.44it/s]
1|3857|Loss: 0.9186842441558838:  15%|█▍        | 3856/25880 [49:09<4:14:31,  1.44it/s]
1|3857|Loss: 0.9186842441558838:  15%|█▍        | 3857/25880 [49:10<4:09:41,  1.47it/s]
1|3858|Loss: 0.6470751762390137:  15%|█▍        | 3857/25880 [49:10<4:09:41,  1.47it/s]
1|3858|Loss: 0.6470751762390137:  15%|█▍        | 3858/25880 [49:10<4:22:19,  1.40it/s]
1|3859|Loss: 0.9165148138999939:  15%|█▍        | 3858/25880 [49:11<4:22:19,  1.40it/s]
1|3859|Loss: 0.9165148138999939:  15%|█▍        | 3859/25880 [49:11<4:25:23,  1.38it/s]
1|3860|Loss: 0.8733228445053101:  15%|█▍        | 3859/25880 [49:11<4:25:23,  1.38it/s]
1|3860|Loss: 0.8733228445053101:  15%|█▍        | 3860/25880 [49:12<4:12:15,  1.45it/s]
1|3861|Loss: 0.7693653106689453:  15%|█▍        | 3860/25880 [49:12<4:12:15,  1.45it/s]
1|3861|Loss: 0.7693653106689453:  15%|█▍        | 3861/25880 [49:12<3:49:16,  1.60it/s]
1|3862|Loss: 0.8726257085800171:  15%|█▍        | 3861/25880 [49:13<3:49:16,  1.60it/s]
1|3862|Loss: 0.8726257085800171:  15%|█▍        | 3862/25880 [49:13<4:19:40,  1.41it/s]
1|3863|Loss: 0.8518746495246887:  15%|█▍        | 3862/25880 [49:13<4:19:40,  1.41it/s]
1|3863|Loss: 0.8518746495246887:  15%|█▍        | 3863/25880 [49:14<4:05:37,  1.49it/s]
1|3864|Loss: 0.8283700346946716:  15%|█▍        | 3863/25880 [49:14<4:05:37,  1.49it/s]
1|3864|Loss: 0.8283700346946716:  15%|█▍        | 3864/25880 [49:14<4:05:34,  1.49it/s]
1|3865|Loss: 0.8789426684379578:  15%|█▍        | 3864/25880 [49:15<4:05:34,  1.49it/s]
1|3865|Loss: 0.8789426684379578:  15%|█▍        | 3865/25880 [49:15<4:17:05,  1.43it/s]
1|3866|Loss: 0.6727176904678345:  15%|█▍        | 3865/25880 [49:16<4:17:05,  1.43it/s]
1|3866|Loss: 0.6727176904678345:  15%|█▍        | 3866/25880 [49:16<4:14:01,  1.44it/s]
1|3867|Loss: 1.066602110862732:  15%|█▍        | 3866/25880 [49:16<4:14:01,  1.44it/s] 
1|3867|Loss: 1.066602110862732:  15%|█▍        | 3867/25880 [49:16<4:04:07,  1.50it/s]
1|3868|Loss: 1.0091677904129028:  15%|█▍        | 3867/25880 [49:17<4:04:07,  1.50it/s]
1|3868|Loss: 1.0091677904129028:  15%|█▍        | 3868/25880 [49:17<3:52:01,  1.58it/s]
1|3869|Loss: 0.7772493362426758:  15%|█▍        | 3868/25880 [49:17<3:52:01,  1.58it/s]
1|3869|Loss: 0.7772493362426758:  15%|█▍        | 3869/25880 [49:18<4:19:23,  1.41it/s]
1|3870|Loss: 0.9379338026046753:  15%|█▍        | 3869/25880 [49:18<4:19:23,  1.41it/s]
1|3870|Loss: 0.9379338026046753:  15%|█▍        | 3870/25880 [49:19<4:25:00,  1.38it/s]
1|3871|Loss: 0.8027441501617432:  15%|█▍        | 3870/25880 [49:19<4:25:00,  1.38it/s]
1|3871|Loss: 0.8027441501617432:  15%|█▍        | 3871/25880 [49:19<4:31:06,  1.35it/s]
1|3872|Loss: 0.7991227507591248:  15%|█▍        | 3871/25880 [49:20<4:31:06,  1.35it/s]
1|3872|Loss: 0.7991227507591248:  15%|█▍        | 3872/25880 [49:20<4:23:08,  1.39it/s]
1|3873|Loss: 0.837684154510498:  15%|█▍        | 3872/25880 [49:20<4:23:08,  1.39it/s] 
1|3873|Loss: 0.837684154510498:  15%|█▍        | 3873/25880 [49:21<4:20:19,  1.41it/s]
1|3874|Loss: 0.9693582057952881:  15%|█▍        | 3873/25880 [49:21<4:20:19,  1.41it/s]
1|3874|Loss: 0.9693582057952881:  15%|█▍        | 3874/25880 [49:21<4:13:30,  1.45it/s]
1|3875|Loss: 0.9382153749465942:  15%|█▍        | 3874/25880 [49:22<4:13:30,  1.45it/s]
1|3875|Loss: 0.9382153749465942:  15%|█▍        | 3875/25880 [49:22<4:06:13,  1.49it/s]
1|3876|Loss: 0.9883554577827454:  15%|█▍        | 3875/25880 [49:22<4:06:13,  1.49it/s]
1|3876|Loss: 0.9883554577827454:  15%|█▍        | 3876/25880 [49:23<4:02:29,  1.51it/s]
1|3877|Loss: 0.8642752170562744:  15%|█▍        | 3876/25880 [49:23<4:02:29,  1.51it/s]
1|3877|Loss: 0.8642752170562744:  15%|█▍        | 3877/25880 [49:23<4:05:47,  1.49it/s]
1|3878|Loss: 0.7382146716117859:  15%|█▍        | 3877/25880 [49:24<4:05:47,  1.49it/s]
1|3878|Loss: 0.7382146716117859:  15%|█▍        | 3878/25880 [49:24<4:21:38,  1.40it/s]
1|3879|Loss: 0.8621549606323242:  15%|█▍        | 3878/25880 [49:25<4:21:38,  1.40it/s]
1|3879|Loss: 0.8621549606323242:  15%|█▍        | 3879/25880 [49:25<4:28:31,  1.37it/s]
1|3880|Loss: 0.7725036144256592:  15%|█▍        | 3879/25880 [49:25<4:28:31,  1.37it/s]
1|3880|Loss: 0.7725036144256592:  15%|█▍        | 3880/25880 [49:26<4:30:02,  1.36it/s]
1|3881|Loss: 0.8658552765846252:  15%|█▍        | 3880/25880 [49:26<4:30:02,  1.36it/s]
1|3881|Loss: 0.8658552765846252:  15%|█▍        | 3881/25880 [49:26<4:32:23,  1.35it/s]
1|3882|Loss: 0.80829256772995:  15%|█▍        | 3881/25880 [49:27<4:32:23,  1.35it/s]  
1|3882|Loss: 0.80829256772995:  15%|█▌        | 3882/25880 [49:27<4:47:50,  1.27it/s]
1|3883|Loss: 0.8003978133201599:  15%|█▌        | 3882/25880 [49:28<4:47:50,  1.27it/s]
1|3883|Loss: 0.8003978133201599:  15%|█▌        | 3883/25880 [49:28<5:01:20,  1.22it/s]
1|3884|Loss: 0.8966231346130371:  15%|█▌        | 3883/25880 [49:29<5:01:20,  1.22it/s]
1|3884|Loss: 0.8966231346130371:  15%|█▌        | 3884/25880 [49:29<4:47:05,  1.28it/s]
1|3885|Loss: 0.7723523378372192:  15%|█▌        | 3884/25880 [49:29<4:47:05,  1.28it/s]
1|3885|Loss: 0.7723523378372192:  15%|█▌        | 3885/25880 [49:30<4:39:06,  1.31it/s]
1|3886|Loss: 0.7704278826713562:  15%|█▌        | 3885/25880 [49:30<4:39:06,  1.31it/s]
1|3886|Loss: 0.7704278826713562:  15%|█▌        | 3886/25880 [49:30<4:25:24,  1.38it/s]
1|3887|Loss: 0.888543963432312:  15%|█▌        | 3886/25880 [49:31<4:25:24,  1.38it/s] 
1|3887|Loss: 0.888543963432312:  15%|█▌        | 3887/25880 [49:31<4:15:18,  1.44it/s]
1|3888|Loss: 0.7662784457206726:  15%|█▌        | 3887/25880 [49:31<4:15:18,  1.44it/s]
1|3888|Loss: 0.7662784457206726:  15%|█▌        | 3888/25880 [49:32<4:09:01,  1.47it/s]
1|3889|Loss: 0.928779661655426:  15%|█▌        | 3888/25880 [49:32<4:09:01,  1.47it/s] 
1|3889|Loss: 0.928779661655426:  15%|█▌        | 3889/25880 [49:32<4:24:00,  1.39it/s]
1|3890|Loss: 0.838275671005249:  15%|█▌        | 3889/25880 [49:33<4:24:00,  1.39it/s]
1|3890|Loss: 0.838275671005249:  15%|█▌        | 3890/25880 [49:33<4:37:00,  1.32it/s]
1|3891|Loss: 0.8706786036491394:  15%|█▌        | 3890/25880 [49:34<4:37:00,  1.32it/s]
1|3891|Loss: 0.8706786036491394:  15%|█▌        | 3891/25880 [49:34<4:32:55,  1.34it/s]
1|3892|Loss: 0.7902153134346008:  15%|█▌        | 3891/25880 [49:34<4:32:55,  1.34it/s]
1|3892|Loss: 0.7902153134346008:  15%|█▌        | 3892/25880 [49:35<4:31:03,  1.35it/s]
1|3893|Loss: 0.7888147234916687:  15%|█▌        | 3892/25880 [49:35<4:31:03,  1.35it/s]
1|3893|Loss: 0.7888147234916687:  15%|█▌        | 3893/25880 [49:36<4:50:21,  1.26it/s]
1|3894|Loss: 0.903017520904541:  15%|█▌        | 3893/25880 [49:36<4:50:21,  1.26it/s] 
1|3894|Loss: 0.903017520904541:  15%|█▌        | 3894/25880 [49:36<4:40:34,  1.31it/s]
1|3895|Loss: 0.9719480276107788:  15%|█▌        | 3894/25880 [49:37<4:40:34,  1.31it/s]
1|3895|Loss: 0.9719480276107788:  15%|█▌        | 3895/25880 [49:37<4:34:57,  1.33it/s]
1|3896|Loss: 0.8364732265472412:  15%|█▌        | 3895/25880 [49:37<4:34:57,  1.33it/s]
1|3896|Loss: 0.8364732265472412:  15%|█▌        | 3896/25880 [49:38<4:23:40,  1.39it/s]
1|3897|Loss: 0.8627076148986816:  15%|█▌        | 3896/25880 [49:38<4:23:40,  1.39it/s]
1|3897|Loss: 0.8627076148986816:  15%|█▌        | 3897/25880 [49:38<4:20:09,  1.41it/s]
1|3898|Loss: 1.1073659658432007:  15%|█▌        | 3897/25880 [49:39<4:20:09,  1.41it/s]
1|3898|Loss: 1.1073659658432007:  15%|█▌        | 3898/25880 [49:39<4:09:34,  1.47it/s]
1|3899|Loss: 0.8958104848861694:  15%|█▌        | 3898/25880 [49:39<4:09:34,  1.47it/s]
1|3899|Loss: 0.8958104848861694:  15%|█▌        | 3899/25880 [49:40<4:00:52,  1.52it/s]
1|3900|Loss: 0.9953005909919739:  15%|█▌        | 3899/25880 [49:40<4:00:52,  1.52it/s]
1|3900|Loss: 0.9953005909919739:  15%|█▌        | 3900/25880 [49:40<4:08:02,  1.48it/s]
1|3901|Loss: 0.961353600025177:  15%|█▌        | 3900/25880 [49:41<4:08:02,  1.48it/s] 
1|3901|Loss: 0.961353600025177:  15%|█▌        | 3901/25880 [49:41<4:21:15,  1.40it/s]
1|3902|Loss: 0.8508341908454895:  15%|█▌        | 3901/25880 [49:41<4:21:15,  1.40it/s]
1|3902|Loss: 0.8508341908454895:  15%|█▌        | 3902/25880 [49:42<4:32:46,  1.34it/s]
1|3903|Loss: 0.8847181797027588:  15%|█▌        | 3902/25880 [49:42<4:32:46,  1.34it/s]
1|3903|Loss: 0.8847181797027588:  15%|█▌        | 3903/25880 [49:43<4:34:13,  1.34it/s]
1|3904|Loss: 1.0876832008361816:  15%|█▌        | 3903/25880 [49:43<4:34:13,  1.34it/s]
1|3904|Loss: 1.0876832008361816:  15%|█▌        | 3904/25880 [49:43<4:30:26,  1.35it/s]
1|3905|Loss: 0.8083993196487427:  15%|█▌        | 3904/25880 [49:44<4:30:26,  1.35it/s]
1|3905|Loss: 0.8083993196487427:  15%|█▌        | 3905/25880 [49:44<4:21:16,  1.40it/s]
1|3906|Loss: 0.8607333302497864:  15%|█▌        | 3905/25880 [49:44<4:21:16,  1.40it/s]
1|3906|Loss: 0.8607333302497864:  15%|█▌        | 3906/25880 [49:45<4:32:12,  1.35it/s]
1|3907|Loss: 0.9216734170913696:  15%|█▌        | 3906/25880 [49:45<4:32:12,  1.35it/s]
1|3907|Loss: 0.9216734170913696:  15%|█▌        | 3907/25880 [49:45<4:14:21,  1.44it/s]
1|3908|Loss: 0.7080332040786743:  15%|█▌        | 3907/25880 [49:46<4:14:21,  1.44it/s]
1|3908|Loss: 0.7080332040786743:  15%|█▌        | 3908/25880 [49:46<4:56:57,  1.23it/s]
1|3909|Loss: 0.8330649733543396:  15%|█▌        | 3908/25880 [49:47<4:56:57,  1.23it/s]
1|3909|Loss: 0.8330649733543396:  15%|█▌        | 3909/25880 [49:47<5:08:36,  1.19it/s]
1|3910|Loss: 0.9984700679779053:  15%|█▌        | 3909/25880 [49:48<5:08:36,  1.19it/s]
1|3910|Loss: 0.9984700679779053:  15%|█▌        | 3910/25880 [49:48<5:18:35,  1.15it/s]
1|3911|Loss: 0.7013381123542786:  15%|█▌        | 3910/25880 [49:49<5:18:35,  1.15it/s]
1|3911|Loss: 0.7013381123542786:  15%|█▌        | 3911/25880 [49:49<5:00:24,  1.22it/s]
1|3912|Loss: 0.8956034183502197:  15%|█▌        | 3911/25880 [49:49<5:00:24,  1.22it/s]
1|3912|Loss: 0.8956034183502197:  15%|█▌        | 3912/25880 [49:50<4:39:03,  1.31it/s]
1|3913|Loss: 0.8407762050628662:  15%|█▌        | 3912/25880 [49:50<4:39:03,  1.31it/s]
1|3913|Loss: 0.8407762050628662:  15%|█▌        | 3913/25880 [49:50<4:32:53,  1.34it/s]
1|3914|Loss: 0.6844248175621033:  15%|█▌        | 3913/25880 [49:51<4:32:53,  1.34it/s]
1|3914|Loss: 0.6844248175621033:  15%|█▌        | 3914/25880 [49:51<4:14:47,  1.44it/s]
1|3915|Loss: 0.9045425057411194:  15%|█▌        | 3914/25880 [49:51<4:14:47,  1.44it/s]
1|3915|Loss: 0.9045425057411194:  15%|█▌        | 3915/25880 [49:52<4:11:10,  1.46it/s]
1|3916|Loss: 0.9306548833847046:  15%|█▌        | 3915/25880 [49:52<4:11:10,  1.46it/s]
1|3916|Loss: 0.9306548833847046:  15%|█▌        | 3916/25880 [49:52<4:20:49,  1.40it/s]
1|3917|Loss: 0.8457891345024109:  15%|█▌        | 3916/25880 [49:53<4:20:49,  1.40it/s]
1|3917|Loss: 0.8457891345024109:  15%|█▌        | 3917/25880 [49:53<4:24:07,  1.39it/s]
1|3918|Loss: 0.8313466906547546:  15%|█▌        | 3917/25880 [49:53<4:24:07,  1.39it/s]
1|3918|Loss: 0.8313466906547546:  15%|█▌        | 3918/25880 [49:54<4:25:06,  1.38it/s]
1|3919|Loss: 0.7822767496109009:  15%|█▌        | 3918/25880 [49:54<4:25:06,  1.38it/s]
1|3919|Loss: 0.7822767496109009:  15%|█▌        | 3919/25880 [49:55<4:22:59,  1.39it/s]
1|3920|Loss: 0.8014774322509766:  15%|█▌        | 3919/25880 [49:55<4:22:59,  1.39it/s]
1|3920|Loss: 0.8014774322509766:  15%|█▌        | 3920/25880 [49:55<4:43:17,  1.29it/s]
1|3921|Loss: 0.8908181190490723:  15%|█▌        | 3920/25880 [49:56<4:43:17,  1.29it/s]
1|3921|Loss: 0.8908181190490723:  15%|█▌        | 3921/25880 [49:56<4:32:52,  1.34it/s]
1|3922|Loss: 0.914189875125885:  15%|█▌        | 3921/25880 [49:57<4:32:52,  1.34it/s] 
1|3922|Loss: 0.914189875125885:  15%|█▌        | 3922/25880 [49:57<4:49:11,  1.27it/s]
1|3923|Loss: 0.9671552777290344:  15%|█▌        | 3922/25880 [49:57<4:49:11,  1.27it/s]
1|3923|Loss: 0.9671552777290344:  15%|█▌        | 3923/25880 [49:58<4:45:46,  1.28it/s]
1|3924|Loss: 0.7877538800239563:  15%|█▌        | 3923/25880 [49:58<4:45:46,  1.28it/s]
1|3924|Loss: 0.7877538800239563:  15%|█▌        | 3924/25880 [49:58<4:39:32,  1.31it/s]
1|3925|Loss: 0.8502179384231567:  15%|█▌        | 3924/25880 [49:59<4:39:32,  1.31it/s]
1|3925|Loss: 0.8502179384231567:  15%|█▌        | 3925/25880 [49:59<4:40:18,  1.31it/s]
1|3926|Loss: 0.9765682816505432:  15%|█▌        | 3925/25880 [50:00<4:40:18,  1.31it/s]
1|3926|Loss: 0.9765682816505432:  15%|█▌        | 3926/25880 [50:00<4:37:34,  1.32it/s]
1|3927|Loss: 0.7774139642715454:  15%|█▌        | 3926/25880 [50:00<4:37:34,  1.32it/s]
1|3927|Loss: 0.7774139642715454:  15%|█▌        | 3927/25880 [50:01<4:44:44,  1.28it/s]
1|3928|Loss: 0.8468431234359741:  15%|█▌        | 3927/25880 [50:01<4:44:44,  1.28it/s]
1|3928|Loss: 0.8468431234359741:  15%|█▌        | 3928/25880 [50:02<4:51:23,  1.26it/s]
1|3929|Loss: 1.036287784576416:  15%|█▌        | 3928/25880 [50:02<4:51:23,  1.26it/s] 
1|3929|Loss: 1.036287784576416:  15%|█▌        | 3929/25880 [50:02<4:30:51,  1.35it/s]
1|3930|Loss: 0.8604535460472107:  15%|█▌        | 3929/25880 [50:03<4:30:51,  1.35it/s]
1|3930|Loss: 0.8604535460472107:  15%|█▌        | 3930/25880 [50:03<4:23:03,  1.39it/s]
1|3931|Loss: 0.9528887867927551:  15%|█▌        | 3930/25880 [50:03<4:23:03,  1.39it/s]
1|3931|Loss: 0.9528887867927551:  15%|█▌        | 3931/25880 [50:04<4:39:45,  1.31it/s]
1|3932|Loss: 0.8996067047119141:  15%|█▌        | 3931/25880 [50:04<4:39:45,  1.31it/s]
1|3932|Loss: 0.8996067047119141:  15%|█▌        | 3932/25880 [50:04<4:22:32,  1.39it/s]
1|3933|Loss: 0.8504447937011719:  15%|█▌        | 3932/25880 [50:05<4:22:32,  1.39it/s]
1|3933|Loss: 0.8504447937011719:  15%|█▌        | 3933/25880 [50:05<4:25:59,  1.38it/s]
1|3934|Loss: 0.7626108527183533:  15%|█▌        | 3933/25880 [50:06<4:25:59,  1.38it/s]
1|3934|Loss: 0.7626108527183533:  15%|█▌        | 3934/25880 [50:06<4:25:38,  1.38it/s]
1|3935|Loss: 0.7800627946853638:  15%|█▌        | 3934/25880 [50:06<4:25:38,  1.38it/s]
1|3935|Loss: 0.7800627946853638:  15%|█▌        | 3935/25880 [50:07<4:24:46,  1.38it/s]
1|3936|Loss: 0.8562241196632385:  15%|█▌        | 3935/25880 [50:07<4:24:46,  1.38it/s]
1|3936|Loss: 0.8562241196632385:  15%|█▌        | 3936/25880 [50:07<4:33:53,  1.34it/s]
1|3937|Loss: 0.8295397162437439:  15%|█▌        | 3936/25880 [50:08<4:33:53,  1.34it/s]
1|3937|Loss: 0.8295397162437439:  15%|█▌        | 3937/25880 [50:08<4:31:21,  1.35it/s]
1|3938|Loss: 0.7870454788208008:  15%|█▌        | 3937/25880 [50:09<4:31:21,  1.35it/s]
1|3938|Loss: 0.7870454788208008:  15%|█▌        | 3938/25880 [50:09<4:15:26,  1.43it/s]
1|3939|Loss: 0.8131254315376282:  15%|█▌        | 3938/25880 [50:09<4:15:26,  1.43it/s]
1|3939|Loss: 0.8131254315376282:  15%|█▌        | 3939/25880 [50:09<4:14:51,  1.43it/s]
1|3940|Loss: 0.7648005485534668:  15%|█▌        | 3939/25880 [50:10<4:14:51,  1.43it/s]
1|3940|Loss: 0.7648005485534668:  15%|█▌        | 3940/25880 [50:10<3:45:24,  1.62it/s]
1|3941|Loss: 0.8170375823974609:  15%|█▌        | 3940/25880 [50:10<3:45:24,  1.62it/s]
1|3941|Loss: 0.8170375823974609:  15%|█▌        | 3941/25880 [50:11<3:50:52,  1.58it/s]
1|3942|Loss: 0.6911172270774841:  15%|█▌        | 3941/25880 [50:11<3:50:52,  1.58it/s]
1|3942|Loss: 0.6911172270774841:  15%|█▌        | 3942/25880 [50:11<4:13:57,  1.44it/s]
1|3943|Loss: 0.7350144982337952:  15%|█▌        | 3942/25880 [50:12<4:13:57,  1.44it/s]
1|3943|Loss: 0.7350144982337952:  15%|█▌        | 3943/25880 [50:12<4:21:54,  1.40it/s]
1|3944|Loss: 0.9825404286384583:  15%|█▌        | 3943/25880 [50:13<4:21:54,  1.40it/s]
1|3944|Loss: 0.9825404286384583:  15%|█▌        | 3944/25880 [50:13<4:21:22,  1.40it/s]
1|3945|Loss: 0.8059744834899902:  15%|█▌        | 3944/25880 [50:13<4:21:22,  1.40it/s]
1|3945|Loss: 0.8059744834899902:  15%|█▌        | 3945/25880 [50:13<4:08:35,  1.47it/s]
1|3946|Loss: 0.8172953128814697:  15%|█▌        | 3945/25880 [50:14<4:08:35,  1.47it/s]
1|3946|Loss: 0.8172953128814697:  15%|█▌        | 3946/25880 [50:14<4:33:27,  1.34it/s]
1|3947|Loss: 0.8569818735122681:  15%|█▌        | 3946/25880 [50:15<4:33:27,  1.34it/s]
1|3947|Loss: 0.8569818735122681:  15%|█▌        | 3947/25880 [50:15<4:51:45,  1.25it/s]
1|3948|Loss: 0.837982177734375:  15%|█▌        | 3947/25880 [50:16<4:51:45,  1.25it/s] 
1|3948|Loss: 0.837982177734375:  15%|█▌        | 3948/25880 [50:16<4:45:46,  1.28it/s]
1|3949|Loss: 0.905315101146698:  15%|█▌        | 3948/25880 [50:16<4:45:46,  1.28it/s]
1|3949|Loss: 0.905315101146698:  15%|█▌        | 3949/25880 [50:17<4:26:21,  1.37it/s]
1|3950|Loss: 0.9635303616523743:  15%|█▌        | 3949/25880 [50:17<4:26:21,  1.37it/s]
1|3950|Loss: 0.9635303616523743:  15%|█▌        | 3950/25880 [50:17<4:20:26,  1.40it/s]
1|3951|Loss: 0.7888653874397278:  15%|█▌        | 3950/25880 [50:18<4:20:26,  1.40it/s]
1|3951|Loss: 0.7888653874397278:  15%|█▌        | 3951/25880 [50:18<4:13:21,  1.44it/s]
1|3952|Loss: 0.7118350267410278:  15%|█▌        | 3951/25880 [50:18<4:13:21,  1.44it/s]
1|3952|Loss: 0.7118350267410278:  15%|█▌        | 3952/25880 [50:18<3:55:29,  1.55it/s]
1|3953|Loss: 0.8932051062583923:  15%|█▌        | 3952/25880 [50:19<3:55:29,  1.55it/s]
1|3953|Loss: 0.8932051062583923:  15%|█▌        | 3953/25880 [50:19<3:59:30,  1.53it/s]
1|3954|Loss: 0.736330509185791:  15%|█▌        | 3953/25880 [50:20<3:59:30,  1.53it/s] 
1|3954|Loss: 0.736330509185791:  15%|█▌        | 3954/25880 [50:20<4:28:06,  1.36it/s]
1|3955|Loss: 0.8246284127235413:  15%|█▌        | 3954/25880 [50:20<4:28:06,  1.36it/s]
1|3955|Loss: 0.8246284127235413:  15%|█▌        | 3955/25880 [50:21<4:08:19,  1.47it/s]
1|3956|Loss: 0.9276326894760132:  15%|█▌        | 3955/25880 [50:21<4:08:19,  1.47it/s]
1|3956|Loss: 0.9276326894760132:  15%|█▌        | 3956/25880 [50:21<4:08:40,  1.47it/s]
1|3957|Loss: 0.8620625138282776:  15%|█▌        | 3956/25880 [50:22<4:08:40,  1.47it/s]
1|3957|Loss: 0.8620625138282776:  15%|█▌        | 3957/25880 [50:22<4:19:44,  1.41it/s]
1|3958|Loss: 0.6877913475036621:  15%|█▌        | 3957/25880 [50:23<4:19:44,  1.41it/s]
1|3958|Loss: 0.6877913475036621:  15%|█▌        | 3958/25880 [50:23<4:38:35,  1.31it/s]
1|3959|Loss: 0.8760749697685242:  15%|█▌        | 3958/25880 [50:23<4:38:35,  1.31it/s]
1|3959|Loss: 0.8760749697685242:  15%|█▌        | 3959/25880 [50:24<4:29:11,  1.36it/s]
1|3960|Loss: 0.7662108540534973:  15%|█▌        | 3959/25880 [50:24<4:29:11,  1.36it/s]
1|3960|Loss: 0.7662108540534973:  15%|█▌        | 3960/25880 [50:24<4:26:44,  1.37it/s]
1|3961|Loss: 0.7979016900062561:  15%|█▌        | 3960/25880 [50:25<4:26:44,  1.37it/s]
1|3961|Loss: 0.7979016900062561:  15%|█▌        | 3961/25880 [50:25<4:29:23,  1.36it/s]
1|3962|Loss: 0.6992120146751404:  15%|█▌        | 3961/25880 [50:26<4:29:23,  1.36it/s]
1|3962|Loss: 0.6992120146751404:  15%|█▌        | 3962/25880 [50:26<4:21:12,  1.40it/s]
1|3963|Loss: 0.8219984769821167:  15%|█▌        | 3962/25880 [50:26<4:21:12,  1.40it/s]
1|3963|Loss: 0.8219984769821167:  15%|█▌        | 3963/25880 [50:27<4:25:47,  1.37it/s]
1|3964|Loss: 0.7639591693878174:  15%|█▌        | 3963/25880 [50:27<4:25:47,  1.37it/s]
1|3964|Loss: 0.7639591693878174:  15%|█▌        | 3964/25880 [50:27<4:27:20,  1.37it/s]
1|3965|Loss: 0.8716537356376648:  15%|█▌        | 3964/25880 [50:28<4:27:20,  1.37it/s]
1|3965|Loss: 0.8716537356376648:  15%|█▌        | 3965/25880 [50:28<4:31:21,  1.35it/s]
1|3966|Loss: 0.9923990964889526:  15%|█▌        | 3965/25880 [50:29<4:31:21,  1.35it/s]
1|3966|Loss: 0.9923990964889526:  15%|█▌        | 3966/25880 [50:29<4:40:09,  1.30it/s]
1|3967|Loss: 0.7824181318283081:  15%|█▌        | 3966/25880 [50:29<4:40:09,  1.30it/s]
1|3967|Loss: 0.7824181318283081:  15%|█▌        | 3967/25880 [50:30<4:46:27,  1.27it/s]
1|3968|Loss: 0.8777505159378052:  15%|█▌        | 3967/25880 [50:30<4:46:27,  1.27it/s]
1|3968|Loss: 0.8777505159378052:  15%|█▌        | 3968/25880 [50:30<4:35:26,  1.33it/s]
1|3969|Loss: 0.8472211360931396:  15%|█▌        | 3968/25880 [50:31<4:35:26,  1.33it/s]
1|3969|Loss: 0.8472211360931396:  15%|█▌        | 3969/25880 [50:31<4:11:33,  1.45it/s]
1|3970|Loss: 0.8036808967590332:  15%|█▌        | 3969/25880 [50:31<4:11:33,  1.45it/s]
1|3970|Loss: 0.8036808967590332:  15%|█▌        | 3970/25880 [50:32<4:15:07,  1.43it/s]
1|3971|Loss: 0.9725050330162048:  15%|█▌        | 3970/25880 [50:32<4:15:07,  1.43it/s]
1|3971|Loss: 0.9725050330162048:  15%|█▌        | 3971/25880 [50:32<4:31:06,  1.35it/s]
1|3972|Loss: 1.012226939201355:  15%|█▌        | 3971/25880 [50:33<4:31:06,  1.35it/s] 
1|3972|Loss: 1.012226939201355:  15%|█▌        | 3972/25880 [50:33<4:25:38,  1.37it/s]
1|3973|Loss: 0.8690997958183289:  15%|█▌        | 3972/25880 [50:33<4:25:38,  1.37it/s]
1|3973|Loss: 0.8690997958183289:  15%|█▌        | 3973/25880 [50:34<3:52:17,  1.57it/s]
1|3974|Loss: 0.8188555240631104:  15%|█▌        | 3973/25880 [50:34<3:52:17,  1.57it/s]
1|3974|Loss: 0.8188555240631104:  15%|█▌        | 3974/25880 [50:34<3:37:05,  1.68it/s]
1|3975|Loss: 0.9629490971565247:  15%|█▌        | 3974/25880 [50:34<3:37:05,  1.68it/s]
1|3975|Loss: 0.9629490971565247:  15%|█▌        | 3975/25880 [50:35<3:36:56,  1.68it/s]
1|3976|Loss: 0.8180978894233704:  15%|█▌        | 3975/25880 [50:35<3:36:56,  1.68it/s]
1|3976|Loss: 0.8180978894233704:  15%|█▌        | 3976/25880 [50:35<3:46:36,  1.61it/s]
1|3977|Loss: 0.7842657566070557:  15%|█▌        | 3976/25880 [50:36<3:46:36,  1.61it/s]
1|3977|Loss: 0.7842657566070557:  15%|█▌        | 3977/25880 [50:36<3:49:42,  1.59it/s]
1|3978|Loss: 0.982281506061554:  15%|█▌        | 3977/25880 [50:36<3:49:42,  1.59it/s] 
1|3978|Loss: 0.982281506061554:  15%|█▌        | 3978/25880 [50:37<3:55:58,  1.55it/s]
1|3979|Loss: 0.8638748526573181:  15%|█▌        | 3978/25880 [50:37<3:55:58,  1.55it/s]
1|3979|Loss: 0.8638748526573181:  15%|█▌        | 3979/25880 [50:37<4:05:02,  1.49it/s]
1|3980|Loss: 0.9494079351425171:  15%|█▌        | 3979/25880 [50:38<4:05:02,  1.49it/s]
1|3980|Loss: 0.9494079351425171:  15%|█▌        | 3980/25880 [50:38<4:09:29,  1.46it/s]
1|3981|Loss: 0.9475952386856079:  15%|█▌        | 3980/25880 [50:39<4:09:29,  1.46it/s]
1|3981|Loss: 0.9475952386856079:  15%|█▌        | 3981/25880 [50:39<4:14:15,  1.44it/s]
1|3982|Loss: 0.8191516995429993:  15%|█▌        | 3981/25880 [50:39<4:14:15,  1.44it/s]
1|3982|Loss: 0.8191516995429993:  15%|█▌        | 3982/25880 [50:40<4:18:01,  1.41it/s]
1|3983|Loss: 0.9226700067520142:  15%|█▌        | 3982/25880 [50:40<4:18:01,  1.41it/s]
1|3983|Loss: 0.9226700067520142:  15%|█▌        | 3983/25880 [50:40<4:12:02,  1.45it/s]
1|3984|Loss: 0.8326729536056519:  15%|█▌        | 3983/25880 [50:41<4:12:02,  1.45it/s]
1|3984|Loss: 0.8326729536056519:  15%|█▌        | 3984/25880 [50:41<3:57:03,  1.54it/s]
1|3985|Loss: 0.8649925589561462:  15%|█▌        | 3984/25880 [50:41<3:57:03,  1.54it/s]
1|3985|Loss: 0.8649925589561462:  15%|█▌        | 3985/25880 [50:42<4:12:27,  1.45it/s]
1|3986|Loss: 0.8811448216438293:  15%|█▌        | 3985/25880 [50:42<4:12:27,  1.45it/s]
1|3986|Loss: 0.8811448216438293:  15%|█▌        | 3986/25880 [50:42<4:19:59,  1.40it/s]
1|3987|Loss: 0.8311405181884766:  15%|█▌        | 3986/25880 [50:43<4:19:59,  1.40it/s]
1|3987|Loss: 0.8311405181884766:  15%|█▌        | 3987/25880 [50:43<4:14:07,  1.44it/s]
1|3988|Loss: 0.875313937664032:  15%|█▌        | 3987/25880 [50:43<4:14:07,  1.44it/s] 
1|3988|Loss: 0.875313937664032:  15%|█▌        | 3988/25880 [50:44<4:25:09,  1.38it/s]
1|3989|Loss: 0.9209898114204407:  15%|█▌        | 3988/25880 [50:44<4:25:09,  1.38it/s]
1|3989|Loss: 0.9209898114204407:  15%|█▌        | 3989/25880 [50:45<4:33:41,  1.33it/s]
1|3990|Loss: 0.9974917769432068:  15%|█▌        | 3989/25880 [50:45<4:33:41,  1.33it/s]
1|3990|Loss: 0.9974917769432068:  15%|█▌        | 3990/25880 [50:45<4:45:07,  1.28it/s]
1|3991|Loss: 0.9235153198242188:  15%|█▌        | 3990/25880 [50:46<4:45:07,  1.28it/s]
1|3991|Loss: 0.9235153198242188:  15%|█▌        | 3991/25880 [50:46<4:24:11,  1.38it/s]
1|3992|Loss: 0.8457181453704834:  15%|█▌        | 3991/25880 [50:46<4:24:11,  1.38it/s]
1|3992|Loss: 0.8457181453704834:  15%|█▌        | 3992/25880 [50:47<4:08:01,  1.47it/s]
1|3993|Loss: 0.9245746731758118:  15%|█▌        | 3992/25880 [50:47<4:08:01,  1.47it/s]
1|3993|Loss: 0.9245746731758118:  15%|█▌        | 3993/25880 [50:47<4:12:09,  1.45it/s]
1|3994|Loss: 0.9406288266181946:  15%|█▌        | 3993/25880 [50:48<4:12:09,  1.45it/s]
1|3994|Loss: 0.9406288266181946:  15%|█▌        | 3994/25880 [50:48<4:14:49,  1.43it/s]
1|3995|Loss: 0.7877276539802551:  15%|█▌        | 3994/25880 [50:48<4:14:49,  1.43it/s]
1|3995|Loss: 0.7877276539802551:  15%|█▌        | 3995/25880 [50:49<4:16:05,  1.42it/s]
1|3996|Loss: 0.7582266926765442:  15%|█▌        | 3995/25880 [50:49<4:16:05,  1.42it/s]
1|3996|Loss: 0.7582266926765442:  15%|█▌        | 3996/25880 [50:50<4:28:37,  1.36it/s]
1|3997|Loss: 0.965844988822937:  15%|█▌        | 3996/25880 [50:50<4:28:37,  1.36it/s] 
1|3997|Loss: 0.965844988822937:  15%|█▌        | 3997/25880 [50:50<4:30:32,  1.35it/s]
1|3998|Loss: 0.7523196935653687:  15%|█▌        | 3997/25880 [50:51<4:30:32,  1.35it/s]
1|3998|Loss: 0.7523196935653687:  15%|█▌        | 3998/25880 [50:51<4:28:52,  1.36it/s]
1|3999|Loss: 0.9841300845146179:  15%|█▌        | 3998/25880 [50:52<4:28:52,  1.36it/s]
1|3999|Loss: 0.9841300845146179:  15%|█▌        | 3999/25880 [50:52<4:34:43,  1.33it/s]
1|4000|Loss: 0.882494330406189:  15%|█▌        | 3999/25880 [50:52<4:34:43,  1.33it/s] 
1|4000|Loss: 0.882494330406189:  15%|█▌        | 4000/25880 [50:53<4:31:24,  1.34it/s]
1|4001|Loss: 0.8296750783920288:  15%|█▌        | 4000/25880 [50:53<4:31:24,  1.34it/s]
1|4001|Loss: 0.8296750783920288:  15%|█▌        | 4001/25880 [50:53<4:20:53,  1.40it/s]
1|4002|Loss: 0.8425896763801575:  15%|█▌        | 4001/25880 [50:54<4:20:53,  1.40it/s]
1|4002|Loss: 0.8425896763801575:  15%|█▌        | 4002/25880 [50:54<4:21:25,  1.39it/s]
1|4003|Loss: 1.0507078170776367:  15%|█▌        | 4002/25880 [50:54<4:21:25,  1.39it/s]
1|4003|Loss: 1.0507078170776367:  15%|█▌        | 4003/25880 [50:55<4:34:10,  1.33it/s]
1|4004|Loss: 0.8425987958908081:  15%|█▌        | 4003/25880 [50:55<4:34:10,  1.33it/s]
1|4004|Loss: 0.8425987958908081:  15%|█▌        | 4004/25880 [50:55<4:24:54,  1.38it/s]
1|4005|Loss: 0.8010794520378113:  15%|█▌        | 4004/25880 [50:56<4:24:54,  1.38it/s]
1|4005|Loss: 0.8010794520378113:  15%|█▌        | 4005/25880 [50:56<4:12:31,  1.44it/s]
1|4006|Loss: 0.8121006488800049:  15%|█▌        | 4005/25880 [50:56<4:12:31,  1.44it/s]
1|4006|Loss: 0.8121006488800049:  15%|█▌        | 4006/25880 [50:57<4:15:06,  1.43it/s]
1|4007|Loss: 1.0077887773513794:  15%|█▌        | 4006/25880 [50:57<4:15:06,  1.43it/s]
1|4007|Loss: 1.0077887773513794:  15%|█▌        | 4007/25880 [50:57<3:59:33,  1.52it/s]
1|4008|Loss: 0.8677431344985962:  15%|█▌        | 4007/25880 [50:58<3:59:33,  1.52it/s]
1|4008|Loss: 0.8677431344985962:  15%|█▌        | 4008/25880 [50:58<4:09:11,  1.46it/s]
1|4009|Loss: 0.939881443977356:  15%|█▌        | 4008/25880 [50:58<4:09:11,  1.46it/s] 
1|4009|Loss: 0.939881443977356:  15%|█▌        | 4009/25880 [50:59<4:02:13,  1.50it/s]
1|4010|Loss: 0.8872867226600647:  15%|█▌        | 4009/25880 [50:59<4:02:13,  1.50it/s]
1|4010|Loss: 0.8872867226600647:  15%|█▌        | 4010/25880 [50:59<3:57:47,  1.53it/s]
1|4011|Loss: 0.8077046871185303:  15%|█▌        | 4010/25880 [51:00<3:57:47,  1.53it/s]
1|4011|Loss: 0.8077046871185303:  15%|█▌        | 4011/25880 [51:00<4:12:51,  1.44it/s]
1|4012|Loss: 0.8162625432014465:  15%|█▌        | 4011/25880 [51:01<4:12:51,  1.44it/s]
1|4012|Loss: 0.8162625432014465:  16%|█▌        | 4012/25880 [51:01<4:19:15,  1.41it/s]
1|4013|Loss: 0.8799434900283813:  16%|█▌        | 4012/25880 [51:01<4:19:15,  1.41it/s]
1|4013|Loss: 0.8799434900283813:  16%|█▌        | 4013/25880 [51:02<4:28:33,  1.36it/s]
1|4014|Loss: 0.8406102657318115:  16%|█▌        | 4013/25880 [51:02<4:28:33,  1.36it/s]
1|4014|Loss: 0.8406102657318115:  16%|█▌        | 4014/25880 [51:02<4:29:26,  1.35it/s]
1|4015|Loss: 0.9280861616134644:  16%|█▌        | 4014/25880 [51:03<4:29:26,  1.35it/s]
1|4015|Loss: 0.9280861616134644:  16%|█▌        | 4015/25880 [51:03<4:18:01,  1.41it/s]
1|4016|Loss: 0.7892976403236389:  16%|█▌        | 4015/25880 [51:03<4:18:01,  1.41it/s]
1|4016|Loss: 0.7892976403236389:  16%|█▌        | 4016/25880 [51:04<4:18:36,  1.41it/s]
1|4017|Loss: 0.8573441505432129:  16%|█▌        | 4016/25880 [51:04<4:18:36,  1.41it/s]
1|4017|Loss: 0.8573441505432129:  16%|█▌        | 4017/25880 [51:05<4:21:10,  1.40it/s]
1|4018|Loss: 0.8026909828186035:  16%|█▌        | 4017/25880 [51:05<4:21:10,  1.40it/s]
1|4018|Loss: 0.8026909828186035:  16%|█▌        | 4018/25880 [51:05<4:38:26,  1.31it/s]
1|4019|Loss: 0.8833566904067993:  16%|█▌        | 4018/25880 [51:06<4:38:26,  1.31it/s]
1|4019|Loss: 0.8833566904067993:  16%|█▌        | 4019/25880 [51:06<4:21:20,  1.39it/s]
1|4020|Loss: 0.8376641869544983:  16%|█▌        | 4019/25880 [51:06<4:21:20,  1.39it/s]
1|4020|Loss: 0.8376641869544983:  16%|█▌        | 4020/25880 [51:07<4:09:36,  1.46it/s]
1|4021|Loss: 0.8382026553153992:  16%|█▌        | 4020/25880 [51:07<4:09:36,  1.46it/s]
1|4021|Loss: 0.8382026553153992:  16%|█▌        | 4021/25880 [51:07<4:12:47,  1.44it/s]
1|4022|Loss: 0.8713263273239136:  16%|█▌        | 4021/25880 [51:08<4:12:47,  1.44it/s]
1|4022|Loss: 0.8713263273239136:  16%|█▌        | 4022/25880 [51:08<4:08:31,  1.47it/s]
1|4023|Loss: 0.8253509998321533:  16%|█▌        | 4022/25880 [51:08<4:08:31,  1.47it/s]
1|4023|Loss: 0.8253509998321533:  16%|█▌        | 4023/25880 [51:09<4:02:04,  1.50it/s]
1|4024|Loss: 0.8420119881629944:  16%|█▌        | 4023/25880 [51:09<4:02:04,  1.50it/s]
1|4024|Loss: 0.8420119881629944:  16%|█▌        | 4024/25880 [51:09<4:15:57,  1.42it/s]
1|4025|Loss: 0.9901093244552612:  16%|█▌        | 4024/25880 [51:10<4:15:57,  1.42it/s]
1|4025|Loss: 0.9901093244552612:  16%|█▌        | 4025/25880 [51:10<4:29:24,  1.35it/s]
1|4026|Loss: 0.8874413371086121:  16%|█▌        | 4025/25880 [51:11<4:29:24,  1.35it/s]
1|4026|Loss: 0.8874413371086121:  16%|█▌        | 4026/25880 [51:11<4:20:12,  1.40it/s]
1|4027|Loss: 0.8754648566246033:  16%|█▌        | 4026/25880 [51:11<4:20:12,  1.40it/s]
1|4027|Loss: 0.8754648566246033:  16%|█▌        | 4027/25880 [51:12<4:33:08,  1.33it/s]
1|4028|Loss: 0.8827990293502808:  16%|█▌        | 4027/25880 [51:12<4:33:08,  1.33it/s]
1|4028|Loss: 0.8827990293502808:  16%|█▌        | 4028/25880 [51:13<4:43:39,  1.28it/s]
1|4029|Loss: 0.801689088344574:  16%|█▌        | 4028/25880 [51:13<4:43:39,  1.28it/s] 
1|4029|Loss: 0.801689088344574:  16%|█▌        | 4029/25880 [51:13<4:30:55,  1.34it/s]
1|4030|Loss: 0.7692206501960754:  16%|█▌        | 4029/25880 [51:14<4:30:55,  1.34it/s]
1|4030|Loss: 0.7692206501960754:  16%|█▌        | 4030/25880 [51:14<4:27:51,  1.36it/s]
1|4031|Loss: 0.889639139175415:  16%|█▌        | 4030/25880 [51:14<4:27:51,  1.36it/s] 
1|4031|Loss: 0.889639139175415:  16%|█▌        | 4031/25880 [51:15<4:38:32,  1.31it/s]
1|4032|Loss: 1.0533658266067505:  16%|█▌        | 4031/25880 [51:15<4:38:32,  1.31it/s]
1|4032|Loss: 1.0533658266067505:  16%|█▌        | 4032/25880 [51:16<4:50:04,  1.26it/s]
1|4033|Loss: 0.7746355533599854:  16%|█▌        | 4032/25880 [51:16<4:50:04,  1.26it/s]
1|4033|Loss: 0.7746355533599854:  16%|█▌        | 4033/25880 [51:16<4:46:01,  1.27it/s]
1|4034|Loss: 0.803063690662384:  16%|█▌        | 4033/25880 [51:17<4:46:01,  1.27it/s] 
1|4034|Loss: 0.803063690662384:  16%|█▌        | 4034/25880 [51:17<4:40:35,  1.30it/s]
1|4035|Loss: 0.8320909738540649:  16%|█▌        | 4034/25880 [51:18<4:40:35,  1.30it/s]
1|4035|Loss: 0.8320909738540649:  16%|█▌        | 4035/25880 [51:18<4:28:28,  1.36it/s]
1|4036|Loss: 0.9915894865989685:  16%|█▌        | 4035/25880 [51:18<4:28:28,  1.36it/s]
1|4036|Loss: 0.9915894865989685:  16%|█▌        | 4036/25880 [51:18<4:01:51,  1.51it/s]
1|4037|Loss: 0.9162651300430298:  16%|█▌        | 4036/25880 [51:19<4:01:51,  1.51it/s]
1|4037|Loss: 0.9162651300430298:  16%|█▌        | 4037/25880 [51:19<4:00:02,  1.52it/s]
1|4038|Loss: 0.8964105248451233:  16%|█▌        | 4037/25880 [51:19<4:00:02,  1.52it/s]
1|4038|Loss: 0.8964105248451233:  16%|█▌        | 4038/25880 [51:19<3:43:03,  1.63it/s]
1|4039|Loss: 0.9799182415008545:  16%|█▌        | 4038/25880 [51:20<3:43:03,  1.63it/s]
1|4039|Loss: 0.9799182415008545:  16%|█▌        | 4039/25880 [51:20<3:57:22,  1.53it/s]
1|4040|Loss: 0.8706347346305847:  16%|█▌        | 4039/25880 [51:21<3:57:22,  1.53it/s]
1|4040|Loss: 0.8706347346305847:  16%|█▌        | 4040/25880 [51:21<4:07:46,  1.47it/s]
1|4041|Loss: 0.8014772534370422:  16%|█▌        | 4040/25880 [51:21<4:07:46,  1.47it/s]
1|4041|Loss: 0.8014772534370422:  16%|█▌        | 4041/25880 [51:22<4:30:07,  1.35it/s]
1|4042|Loss: 0.9721853137016296:  16%|█▌        | 4041/25880 [51:22<4:30:07,  1.35it/s]
1|4042|Loss: 0.9721853137016296:  16%|█▌        | 4042/25880 [51:23<4:43:35,  1.28it/s]
1|4043|Loss: 0.7926284074783325:  16%|█▌        | 4042/25880 [51:23<4:43:35,  1.28it/s]
1|4043|Loss: 0.7926284074783325:  16%|█▌        | 4043/25880 [51:23<4:42:19,  1.29it/s]
1|4044|Loss: 0.879083514213562:  16%|█▌        | 4043/25880 [51:24<4:42:19,  1.29it/s] 
1|4044|Loss: 0.879083514213562:  16%|█▌        | 4044/25880 [51:24<4:26:03,  1.37it/s]
1|4045|Loss: 0.8691961765289307:  16%|█▌        | 4044/25880 [51:24<4:26:03,  1.37it/s]
1|4045|Loss: 0.8691961765289307:  16%|█▌        | 4045/25880 [51:25<4:22:08,  1.39it/s]
1|4046|Loss: 0.8630027174949646:  16%|█▌        | 4045/25880 [51:25<4:22:08,  1.39it/s]
1|4046|Loss: 0.8630027174949646:  16%|█▌        | 4046/25880 [51:26<4:33:02,  1.33it/s]
1|4047|Loss: 0.8694409728050232:  16%|█▌        | 4046/25880 [51:26<4:33:02,  1.33it/s]
1|4047|Loss: 0.8694409728050232:  16%|█▌        | 4047/25880 [51:26<4:34:08,  1.33it/s]
1|4048|Loss: 0.9460933804512024:  16%|█▌        | 4047/25880 [51:27<4:34:08,  1.33it/s]
1|4048|Loss: 0.9460933804512024:  16%|█▌        | 4048/25880 [51:27<4:40:15,  1.30it/s]
1|4049|Loss: 0.868857741355896:  16%|█▌        | 4048/25880 [51:28<4:40:15,  1.30it/s] 
1|4049|Loss: 0.868857741355896:  16%|█▌        | 4049/25880 [51:28<4:35:09,  1.32it/s]
1|4050|Loss: 0.7040485739707947:  16%|█▌        | 4049/25880 [51:28<4:35:09,  1.32it/s]
1|4050|Loss: 0.7040485739707947:  16%|█▌        | 4050/25880 [51:29<4:40:36,  1.30it/s]
1|4051|Loss: 0.8021673560142517:  16%|█▌        | 4050/25880 [51:29<4:40:36,  1.30it/s]
1|4051|Loss: 0.8021673560142517:  16%|█▌        | 4051/25880 [51:29<4:43:37,  1.28it/s]
1|4052|Loss: 0.772367537021637:  16%|█▌        | 4051/25880 [51:30<4:43:37,  1.28it/s] 
1|4052|Loss: 0.772367537021637:  16%|█▌        | 4052/25880 [51:30<4:30:27,  1.35it/s]
1|4053|Loss: 0.9529637694358826:  16%|█▌        | 4052/25880 [51:31<4:30:27,  1.35it/s]
1|4053|Loss: 0.9529637694358826:  16%|█▌        | 4053/25880 [51:31<4:16:26,  1.42it/s]
1|4054|Loss: 0.857222318649292:  16%|█▌        | 4053/25880 [51:31<4:16:26,  1.42it/s] 
1|4054|Loss: 0.857222318649292:  16%|█▌        | 4054/25880 [51:31<4:17:21,  1.41it/s]
1|4055|Loss: 0.828485906124115:  16%|█▌        | 4054/25880 [51:32<4:17:21,  1.41it/s]
1|4055|Loss: 0.828485906124115:  16%|█▌        | 4055/25880 [51:32<4:32:41,  1.33it/s]
1|4056|Loss: 0.8463087677955627:  16%|█▌        | 4055/25880 [51:33<4:32:41,  1.33it/s]
1|4056|Loss: 0.8463087677955627:  16%|█▌        | 4056/25880 [51:33<4:45:43,  1.27it/s]
1|4057|Loss: 0.8670092225074768:  16%|█▌        | 4056/25880 [51:34<4:45:43,  1.27it/s]
1|4057|Loss: 0.8670092225074768:  16%|█▌        | 4057/25880 [51:34<4:43:04,  1.28it/s]
1|4058|Loss: 0.871511697769165:  16%|█▌        | 4057/25880 [51:34<4:43:04,  1.28it/s] 
1|4058|Loss: 0.871511697769165:  16%|█▌        | 4058/25880 [51:35<4:30:06,  1.35it/s]
1|4059|Loss: 0.9142755270004272:  16%|█▌        | 4058/25880 [51:35<4:30:06,  1.35it/s]
1|4059|Loss: 0.9142755270004272:  16%|█▌        | 4059/25880 [51:35<4:14:58,  1.43it/s]
1|4060|Loss: 1.0371719598770142:  16%|█▌        | 4059/25880 [51:36<4:14:58,  1.43it/s]
1|4060|Loss: 1.0371719598770142:  16%|█▌        | 4060/25880 [51:36<3:55:45,  1.54it/s]
1|4061|Loss: 0.8143985271453857:  16%|█▌        | 4060/25880 [51:36<3:55:45,  1.54it/s]
1|4061|Loss: 0.8143985271453857:  16%|█▌        | 4061/25880 [51:36<3:51:30,  1.57it/s]
1|4062|Loss: 0.9430893659591675:  16%|█▌        | 4061/25880 [51:37<3:51:30,  1.57it/s]
1|4062|Loss: 0.9430893659591675:  16%|█▌        | 4062/25880 [51:37<4:00:13,  1.51it/s]
1|4063|Loss: 0.7946480512619019:  16%|█▌        | 4062/25880 [51:38<4:00:13,  1.51it/s]
1|4063|Loss: 0.7946480512619019:  16%|█▌        | 4063/25880 [51:38<4:18:20,  1.41it/s]
1|4064|Loss: 0.9154375195503235:  16%|█▌        | 4063/25880 [51:38<4:18:20,  1.41it/s]
1|4064|Loss: 0.9154375195503235:  16%|█▌        | 4064/25880 [51:39<4:28:15,  1.36it/s]
1|4065|Loss: 0.8911434412002563:  16%|█▌        | 4064/25880 [51:39<4:28:15,  1.36it/s]
1|4065|Loss: 0.8911434412002563:  16%|█▌        | 4065/25880 [51:39<4:31:00,  1.34it/s]
1|4066|Loss: 0.8449286818504333:  16%|█▌        | 4065/25880 [51:40<4:31:00,  1.34it/s]
1|4066|Loss: 0.8449286818504333:  16%|█▌        | 4066/25880 [51:40<4:27:16,  1.36it/s]
1|4067|Loss: 1.001257061958313:  16%|█▌        | 4066/25880 [51:41<4:27:16,  1.36it/s] 
1|4067|Loss: 1.001257061958313:  16%|█▌        | 4067/25880 [51:41<4:26:43,  1.36it/s]
1|4068|Loss: 0.9449293613433838:  16%|█▌        | 4067/25880 [51:41<4:26:43,  1.36it/s]
1|4068|Loss: 0.9449293613433838:  16%|█▌        | 4068/25880 [51:42<4:32:49,  1.33it/s]
1|4069|Loss: 0.8337796926498413:  16%|█▌        | 4068/25880 [51:42<4:32:49,  1.33it/s]
1|4069|Loss: 0.8337796926498413:  16%|█▌        | 4069/25880 [51:42<4:33:56,  1.33it/s]
1|4070|Loss: 0.7537182569503784:  16%|█▌        | 4069/25880 [51:43<4:33:56,  1.33it/s]
1|4070|Loss: 0.7537182569503784:  16%|█▌        | 4070/25880 [51:43<4:43:53,  1.28it/s]
1|4071|Loss: 0.8996942639350891:  16%|█▌        | 4070/25880 [51:44<4:43:53,  1.28it/s]
1|4071|Loss: 0.8996942639350891:  16%|█▌        | 4071/25880 [51:44<4:33:42,  1.33it/s]
1|4072|Loss: 0.67160964012146:  16%|█▌        | 4071/25880 [51:44<4:33:42,  1.33it/s]  
1|4072|Loss: 0.67160964012146:  16%|█▌        | 4072/25880 [51:45<4:34:18,  1.33it/s]
1|4073|Loss: 0.9045588970184326:  16%|█▌        | 4072/25880 [51:45<4:34:18,  1.33it/s]
1|4073|Loss: 0.9045588970184326:  16%|█▌        | 4073/25880 [51:45<4:33:02,  1.33it/s]
1|4074|Loss: 0.7362494468688965:  16%|█▌        | 4073/25880 [51:46<4:33:02,  1.33it/s]
1|4074|Loss: 0.7362494468688965:  16%|█▌        | 4074/25880 [51:46<4:22:48,  1.38it/s]
1|4075|Loss: 0.8969150185585022:  16%|█▌        | 4074/25880 [51:47<4:22:48,  1.38it/s]
1|4075|Loss: 0.8969150185585022:  16%|█▌        | 4075/25880 [51:47<4:26:42,  1.36it/s]
1|4076|Loss: 0.7586155533790588:  16%|█▌        | 4075/25880 [51:47<4:26:42,  1.36it/s]
1|4076|Loss: 0.7586155533790588:  16%|█▌        | 4076/25880 [51:48<4:34:04,  1.33it/s]
1|4077|Loss: 0.9013814926147461:  16%|█▌        | 4076/25880 [51:48<4:34:04,  1.33it/s]
1|4077|Loss: 0.9013814926147461:  16%|█▌        | 4077/25880 [51:48<4:15:20,  1.42it/s]
1|4078|Loss: 0.7722960710525513:  16%|█▌        | 4077/25880 [51:49<4:15:20,  1.42it/s]
1|4078|Loss: 0.7722960710525513:  16%|█▌        | 4078/25880 [51:49<4:11:03,  1.45it/s]
1|4079|Loss: 0.7036502361297607:  16%|█▌        | 4078/25880 [51:49<4:11:03,  1.45it/s]
1|4079|Loss: 0.7036502361297607:  16%|█▌        | 4079/25880 [51:50<4:21:00,  1.39it/s]
1|4080|Loss: 0.8750898838043213:  16%|█▌        | 4079/25880 [51:50<4:21:00,  1.39it/s]
1|4080|Loss: 0.8750898838043213:  16%|█▌        | 4080/25880 [51:50<4:13:28,  1.43it/s]
1|4081|Loss: 0.8876346945762634:  16%|█▌        | 4080/25880 [51:51<4:13:28,  1.43it/s]
1|4081|Loss: 0.8876346945762634:  16%|█▌        | 4081/25880 [51:51<4:20:41,  1.39it/s]
1|4082|Loss: 0.945508599281311:  16%|█▌        | 4081/25880 [51:52<4:20:41,  1.39it/s] 
1|4082|Loss: 0.945508599281311:  16%|█▌        | 4082/25880 [51:52<4:13:46,  1.43it/s]
1|4083|Loss: 0.832275390625:  16%|█▌        | 4082/25880 [51:52<4:13:46,  1.43it/s]   
1|4083|Loss: 0.832275390625:  16%|█▌        | 4083/25880 [51:52<4:02:12,  1.50it/s]
1|4084|Loss: 0.8719989061355591:  16%|█▌        | 4083/25880 [51:53<4:02:12,  1.50it/s]
1|4084|Loss: 0.8719989061355591:  16%|█▌        | 4084/25880 [51:53<4:05:09,  1.48it/s]
1|4085|Loss: 0.8114371299743652:  16%|█▌        | 4084/25880 [51:54<4:05:09,  1.48it/s]
1|4085|Loss: 0.8114371299743652:  16%|█▌        | 4085/25880 [51:54<4:15:55,  1.42it/s]
1|4086|Loss: 0.9357609748840332:  16%|█▌        | 4085/25880 [51:54<4:15:55,  1.42it/s]
1|4086|Loss: 0.9357609748840332:  16%|█▌        | 4086/25880 [51:55<4:29:10,  1.35it/s]
1|4087|Loss: 0.8180650472640991:  16%|█▌        | 4086/25880 [51:55<4:29:10,  1.35it/s]
1|4087|Loss: 0.8180650472640991:  16%|█▌        | 4087/25880 [51:55<4:35:35,  1.32it/s]
1|4088|Loss: 0.9394954442977905:  16%|█▌        | 4087/25880 [51:56<4:35:35,  1.32it/s]
1|4088|Loss: 0.9394954442977905:  16%|█▌        | 4088/25880 [51:56<4:35:12,  1.32it/s]
1|4089|Loss: 0.7975454926490784:  16%|█▌        | 4088/25880 [51:57<4:35:12,  1.32it/s]
1|4089|Loss: 0.7975454926490784:  16%|█▌        | 4089/25880 [51:57<4:34:13,  1.32it/s]
1|4090|Loss: 0.6700162291526794:  16%|█▌        | 4089/25880 [51:57<4:34:13,  1.32it/s]
1|4090|Loss: 0.6700162291526794:  16%|█▌        | 4090/25880 [51:58<4:24:38,  1.37it/s]
1|4091|Loss: 1.004680871963501:  16%|█▌        | 4090/25880 [51:58<4:24:38,  1.37it/s] 
1|4091|Loss: 1.004680871963501:  16%|█▌        | 4091/25880 [51:58<4:27:44,  1.36it/s]
1|4092|Loss: 1.3457567691802979:  16%|█▌        | 4091/25880 [51:59<4:27:44,  1.36it/s]
1|4092|Loss: 1.3457567691802979:  16%|█▌        | 4092/25880 [52:00<5:20:45,  1.13it/s]
1|4093|Loss: 0.9529668092727661:  16%|█▌        | 4092/25880 [52:00<5:20:45,  1.13it/s]
1|4093|Loss: 0.9529668092727661:  16%|█▌        | 4093/25880 [52:00<5:14:33,  1.15it/s]
1|4094|Loss: 0.806370198726654:  16%|█▌        | 4093/25880 [52:01<5:14:33,  1.15it/s] 
1|4094|Loss: 0.806370198726654:  16%|█▌        | 4094/25880 [52:01<5:04:02,  1.19it/s]
1|4095|Loss: 0.7605098485946655:  16%|█▌        | 4094/25880 [52:02<5:04:02,  1.19it/s]
1|4095|Loss: 0.7605098485946655:  16%|█▌        | 4095/25880 [52:02<4:55:07,  1.23it/s]
1|4096|Loss: 0.7427645325660706:  16%|█▌        | 4095/25880 [52:02<4:55:07,  1.23it/s]
1|4096|Loss: 0.7427645325660706:  16%|█▌        | 4096/25880 [52:03<4:53:14,  1.24it/s]
1|4097|Loss: 0.8646384477615356:  16%|█▌        | 4096/25880 [52:03<4:53:14,  1.24it/s]
1|4097|Loss: 0.8646384477615356:  16%|█▌        | 4097/25880 [52:03<4:37:49,  1.31it/s]
1|4098|Loss: 0.8004787564277649:  16%|█▌        | 4097/25880 [52:04<4:37:49,  1.31it/s]
1|4098|Loss: 0.8004787564277649:  16%|█▌        | 4098/25880 [52:04<4:16:32,  1.42it/s]
1|4099|Loss: 0.9962702989578247:  16%|█▌        | 4098/25880 [52:04<4:16:32,  1.42it/s]
1|4099|Loss: 0.9962702989578247:  16%|█▌        | 4099/25880 [52:05<4:15:51,  1.42it/s]
1|4100|Loss: 0.8537190556526184:  16%|█▌        | 4099/25880 [52:05<4:15:51,  1.42it/s]
1|4100|Loss: 0.8537190556526184:  16%|█▌        | 4100/25880 [52:05<4:09:42,  1.45it/s]
1|4101|Loss: 0.7587457895278931:  16%|█▌        | 4100/25880 [52:06<4:09:42,  1.45it/s]
1|4101|Loss: 0.7587457895278931:  16%|█▌        | 4101/25880 [52:06<4:13:23,  1.43it/s]
1|4102|Loss: 0.7752373218536377:  16%|█▌        | 4101/25880 [52:07<4:13:23,  1.43it/s]
1|4102|Loss: 0.7752373218536377:  16%|█▌        | 4102/25880 [52:07<4:26:57,  1.36it/s]
1|4103|Loss: 0.9515308737754822:  16%|█▌        | 4102/25880 [52:07<4:26:57,  1.36it/s]
1|4103|Loss: 0.9515308737754822:  16%|█▌        | 4103/25880 [52:08<4:33:44,  1.33it/s]
1|4104|Loss: 0.6028744578361511:  16%|█▌        | 4103/25880 [52:08<4:33:44,  1.33it/s]
1|4104|Loss: 0.6028744578361511:  16%|█▌        | 4104/25880 [52:09<4:52:28,  1.24it/s]
1|4105|Loss: 0.7294531464576721:  16%|█▌        | 4104/25880 [52:09<4:52:28,  1.24it/s]
1|4105|Loss: 0.7294531464576721:  16%|█▌        | 4105/25880 [52:09<4:39:30,  1.30it/s]
1|4106|Loss: 0.7860201597213745:  16%|█▌        | 4105/25880 [52:10<4:39:30,  1.30it/s]
1|4106|Loss: 0.7860201597213745:  16%|█▌        | 4106/25880 [52:10<4:45:27,  1.27it/s]
1|4107|Loss: 0.803862452507019:  16%|█▌        | 4106/25880 [52:11<4:45:27,  1.27it/s] 
1|4107|Loss: 0.803862452507019:  16%|█▌        | 4107/25880 [52:11<4:33:07,  1.33it/s]
1|4108|Loss: 0.956529438495636:  16%|█▌        | 4107/25880 [52:11<4:33:07,  1.33it/s]
1|4108|Loss: 0.956529438495636:  16%|█▌        | 4108/25880 [52:12<4:34:14,  1.32it/s]
1|4109|Loss: 0.9962290525436401:  16%|█▌        | 4108/25880 [52:12<4:34:14,  1.32it/s]
1|4109|Loss: 0.9962290525436401:  16%|█▌        | 4109/25880 [52:12<4:21:17,  1.39it/s]
1|4110|Loss: 0.9387789368629456:  16%|█▌        | 4109/25880 [52:13<4:21:17,  1.39it/s]
1|4110|Loss: 0.9387789368629456:  16%|█▌        | 4110/25880 [52:13<4:31:13,  1.34it/s]
1|4111|Loss: 0.7594853639602661:  16%|█▌        | 4110/25880 [52:13<4:31:13,  1.34it/s]
1|4111|Loss: 0.7594853639602661:  16%|█▌        | 4111/25880 [52:14<4:33:35,  1.33it/s]
1|4112|Loss: 0.9654789566993713:  16%|█▌        | 4111/25880 [52:14<4:33:35,  1.33it/s]
1|4112|Loss: 0.9654789566993713:  16%|█▌        | 4112/25880 [52:15<4:37:07,  1.31it/s]
1|4113|Loss: 0.9089899063110352:  16%|█▌        | 4112/25880 [52:15<4:37:07,  1.31it/s]
1|4113|Loss: 0.9089899063110352:  16%|█▌        | 4113/25880 [52:15<4:34:55,  1.32it/s]
1|4114|Loss: 0.747538149356842:  16%|█▌        | 4113/25880 [52:16<4:34:55,  1.32it/s] 
1|4114|Loss: 0.747538149356842:  16%|█▌        | 4114/25880 [52:16<4:23:42,  1.38it/s]
1|4115|Loss: 0.7226503491401672:  16%|█▌        | 4114/25880 [52:16<4:23:42,  1.38it/s]
1|4115|Loss: 0.7226503491401672:  16%|█▌        | 4115/25880 [52:17<4:27:11,  1.36it/s]
1|4116|Loss: 0.7548302412033081:  16%|█▌        | 4115/25880 [52:17<4:27:11,  1.36it/s]
1|4116|Loss: 0.7548302412033081:  16%|█▌        | 4116/25880 [52:18<4:44:39,  1.27it/s]
1|4117|Loss: 0.840761125087738:  16%|█▌        | 4116/25880 [52:18<4:44:39,  1.27it/s] 
1|4117|Loss: 0.840761125087738:  16%|█▌        | 4117/25880 [52:18<4:32:43,  1.33it/s]
1|4118|Loss: 0.937849223613739:  16%|█▌        | 4117/25880 [52:19<4:32:43,  1.33it/s]
1|4118|Loss: 0.937849223613739:  16%|█▌        | 4118/25880 [52:19<4:33:14,  1.33it/s]
1|4119|Loss: 0.967214822769165:  16%|█▌        | 4118/25880 [52:20<4:33:14,  1.33it/s]
1|4119|Loss: 0.967214822769165:  16%|█▌        | 4119/25880 [52:20<4:32:21,  1.33it/s]
1|4120|Loss: 0.9130184650421143:  16%|█▌        | 4119/25880 [52:20<4:32:21,  1.33it/s]
1|4120|Loss: 0.9130184650421143:  16%|█▌        | 4120/25880 [52:21<4:31:21,  1.34it/s]
1|4121|Loss: 0.8321442604064941:  16%|█▌        | 4120/25880 [52:21<4:31:21,  1.34it/s]
1|4121|Loss: 0.8321442604064941:  16%|█▌        | 4121/25880 [52:21<4:40:59,  1.29it/s]
1|4122|Loss: 0.7996734380722046:  16%|█▌        | 4121/25880 [52:22<4:40:59,  1.29it/s]
1|4122|Loss: 0.7996734380722046:  16%|█▌        | 4122/25880 [52:22<4:31:17,  1.34it/s]
1|4123|Loss: 0.9406694173812866:  16%|█▌        | 4122/25880 [52:22<4:31:17,  1.34it/s]
1|4123|Loss: 0.9406694173812866:  16%|█▌        | 4123/25880 [52:23<4:28:55,  1.35it/s]
1|4124|Loss: 0.8837183117866516:  16%|█▌        | 4123/25880 [52:23<4:28:55,  1.35it/s]
1|4124|Loss: 0.8837183117866516:  16%|█▌        | 4124/25880 [52:23<3:57:49,  1.52it/s]
1|4125|Loss: 0.9450003504753113:  16%|█▌        | 4124/25880 [52:24<3:57:49,  1.52it/s]
1|4125|Loss: 0.9450003504753113:  16%|█▌        | 4125/25880 [52:24<4:06:05,  1.47it/s]
1|4126|Loss: 0.9215711951255798:  16%|█▌        | 4125/25880 [52:24<4:06:05,  1.47it/s]
1|4126|Loss: 0.9215711951255798:  16%|█▌        | 4126/25880 [52:25<4:05:47,  1.48it/s]
1|4127|Loss: 0.7619035840034485:  16%|█▌        | 4126/25880 [52:25<4:05:47,  1.48it/s]
1|4127|Loss: 0.7619035840034485:  16%|█▌        | 4127/25880 [52:25<4:01:22,  1.50it/s]
1|4128|Loss: 1.080924391746521:  16%|█▌        | 4127/25880 [52:26<4:01:22,  1.50it/s] 
1|4128|Loss: 1.080924391746521:  16%|█▌        | 4128/25880 [52:26<3:56:59,  1.53it/s]
1|4129|Loss: 0.9902843832969666:  16%|█▌        | 4128/25880 [52:26<3:56:59,  1.53it/s]
1|4129|Loss: 0.9902843832969666:  16%|█▌        | 4129/25880 [52:27<4:03:19,  1.49it/s]
1|4130|Loss: 0.8513849377632141:  16%|█▌        | 4129/25880 [52:27<4:03:19,  1.49it/s]
1|4130|Loss: 0.8513849377632141:  16%|█▌        | 4130/25880 [52:27<4:09:47,  1.45it/s]
1|4131|Loss: 0.807863712310791:  16%|█▌        | 4130/25880 [52:28<4:09:47,  1.45it/s] 
1|4131|Loss: 0.807863712310791:  16%|█▌        | 4131/25880 [52:28<4:01:19,  1.50it/s]
1|4132|Loss: 0.8140854239463806:  16%|█▌        | 4131/25880 [52:28<4:01:19,  1.50it/s]
1|4132|Loss: 0.8140854239463806:  16%|█▌        | 4132/25880 [52:29<4:04:43,  1.48it/s]
1|4133|Loss: 0.8432058095932007:  16%|█▌        | 4132/25880 [52:29<4:04:43,  1.48it/s]
1|4133|Loss: 0.8432058095932007:  16%|█▌        | 4133/25880 [52:29<4:00:11,  1.51it/s]
1|4134|Loss: 1.0213342905044556:  16%|█▌        | 4133/25880 [52:30<4:00:11,  1.51it/s]
1|4134|Loss: 1.0213342905044556:  16%|█▌        | 4134/25880 [52:30<4:06:20,  1.47it/s]
1|4135|Loss: 0.7933145761489868:  16%|█▌        | 4134/25880 [52:30<4:06:20,  1.47it/s]
1|4135|Loss: 0.7933145761489868:  16%|█▌        | 4135/25880 [52:31<4:03:04,  1.49it/s]
1|4136|Loss: 0.8109517097473145:  16%|█▌        | 4135/25880 [52:31<4:03:04,  1.49it/s]
1|4136|Loss: 0.8109517097473145:  16%|█▌        | 4136/25880 [52:32<4:19:01,  1.40it/s]
1|4137|Loss: 0.9770931601524353:  16%|█▌        | 4136/25880 [52:32<4:19:01,  1.40it/s]
1|4137|Loss: 0.9770931601524353:  16%|█▌        | 4137/25880 [52:32<4:24:45,  1.37it/s]
1|4138|Loss: 0.7781878709793091:  16%|█▌        | 4137/25880 [52:33<4:24:45,  1.37it/s]
1|4138|Loss: 0.7781878709793091:  16%|█▌        | 4138/25880 [52:33<4:26:45,  1.36it/s]
1|4139|Loss: 0.9622954726219177:  16%|█▌        | 4138/25880 [52:33<4:26:45,  1.36it/s]
1|4139|Loss: 0.9622954726219177:  16%|█▌        | 4139/25880 [52:34<4:27:46,  1.35it/s]
1|4140|Loss: 0.8330244421958923:  16%|█▌        | 4139/25880 [52:34<4:27:46,  1.35it/s]
1|4140|Loss: 0.8330244421958923:  16%|█▌        | 4140/25880 [52:35<4:25:31,  1.36it/s]
1|4141|Loss: 0.8042726516723633:  16%|█▌        | 4140/25880 [52:35<4:25:31,  1.36it/s]
1|4141|Loss: 0.8042726516723633:  16%|█▌        | 4141/25880 [52:35<4:22:13,  1.38it/s]
1|4142|Loss: 0.7346880435943604:  16%|█▌        | 4141/25880 [52:36<4:22:13,  1.38it/s]
1|4142|Loss: 0.7346880435943604:  16%|█▌        | 4142/25880 [52:36<4:23:43,  1.37it/s]
1|4143|Loss: 0.9013058543205261:  16%|█▌        | 4142/25880 [52:36<4:23:43,  1.37it/s]
1|4143|Loss: 0.9013058543205261:  16%|█▌        | 4143/25880 [52:37<4:11:41,  1.44it/s]
1|4144|Loss: 0.8104549050331116:  16%|█▌        | 4143/25880 [52:37<4:11:41,  1.44it/s]
1|4144|Loss: 0.8104549050331116:  16%|█▌        | 4144/25880 [52:37<4:04:38,  1.48it/s]
1|4145|Loss: 0.8576637506484985:  16%|█▌        | 4144/25880 [52:38<4:04:38,  1.48it/s]
1|4145|Loss: 0.8576637506484985:  16%|█▌        | 4145/25880 [52:38<4:17:33,  1.41it/s]
1|4146|Loss: 0.889839231967926:  16%|█▌        | 4145/25880 [52:38<4:17:33,  1.41it/s] 
1|4146|Loss: 0.889839231967926:  16%|█▌        | 4146/25880 [52:39<4:18:55,  1.40it/s]
1|4147|Loss: 0.8117133378982544:  16%|█▌        | 4146/25880 [52:39<4:18:55,  1.40it/s]
1|4147|Loss: 0.8117133378982544:  16%|█▌        | 4147/25880 [52:39<4:20:19,  1.39it/s]
1|4148|Loss: 0.6775200366973877:  16%|█▌        | 4147/25880 [52:40<4:20:19,  1.39it/s]
1|4148|Loss: 0.6775200366973877:  16%|█▌        | 4148/25880 [52:40<4:08:56,  1.45it/s]
1|4149|Loss: 0.8920249938964844:  16%|█▌        | 4148/25880 [52:40<4:08:56,  1.45it/s]
1|4149|Loss: 0.8920249938964844:  16%|█▌        | 4149/25880 [52:41<4:10:51,  1.44it/s]
1|4150|Loss: 0.8121618628501892:  16%|█▌        | 4149/25880 [52:41<4:10:51,  1.44it/s]
1|4150|Loss: 0.8121618628501892:  16%|█▌        | 4150/25880 [52:41<4:15:17,  1.42it/s]
1|4151|Loss: 0.9203256368637085:  16%|█▌        | 4150/25880 [52:42<4:15:17,  1.42it/s]
1|4151|Loss: 0.9203256368637085:  16%|█▌        | 4151/25880 [52:42<4:20:06,  1.39it/s]
1|4152|Loss: 0.7483109831809998:  16%|█▌        | 4151/25880 [52:43<4:20:06,  1.39it/s]
1|4152|Loss: 0.7483109831809998:  16%|█▌        | 4152/25880 [52:43<4:08:49,  1.46it/s]
1|4153|Loss: 0.884662389755249:  16%|█▌        | 4152/25880 [52:43<4:08:49,  1.46it/s] 
1|4153|Loss: 0.884662389755249:  16%|█▌        | 4153/25880 [52:44<4:09:49,  1.45it/s]
1|4154|Loss: 0.8780437707901001:  16%|█▌        | 4153/25880 [52:44<4:09:49,  1.45it/s]
1|4154|Loss: 0.8780437707901001:  16%|█▌        | 4154/25880 [52:44<4:18:38,  1.40it/s]
1|4155|Loss: 0.9197998046875:  16%|█▌        | 4154/25880 [52:45<4:18:38,  1.40it/s]   
1|4155|Loss: 0.9197998046875:  16%|█▌        | 4155/25880 [52:45<4:32:08,  1.33it/s]
1|4156|Loss: 0.7470781207084656:  16%|█▌        | 4155/25880 [52:46<4:32:08,  1.33it/s]
1|4156|Loss: 0.7470781207084656:  16%|█▌        | 4156/25880 [52:46<4:37:52,  1.30it/s]
1|4157|Loss: 0.7289904952049255:  16%|█▌        | 4156/25880 [52:46<4:37:52,  1.30it/s]
1|4157|Loss: 0.7289904952049255:  16%|█▌        | 4157/25880 [52:47<4:22:39,  1.38it/s]
1|4158|Loss: 0.853078305721283:  16%|█▌        | 4157/25880 [52:47<4:22:39,  1.38it/s] 
1|4158|Loss: 0.853078305721283:  16%|█▌        | 4158/25880 [52:47<4:00:23,  1.51it/s]
1|4159|Loss: 0.837602436542511:  16%|█▌        | 4158/25880 [52:47<4:00:23,  1.51it/s]
1|4159|Loss: 0.837602436542511:  16%|█▌        | 4159/25880 [52:48<3:43:39,  1.62it/s]
1|4160|Loss: 0.8688364624977112:  16%|█▌        | 4159/25880 [52:48<3:43:39,  1.62it/s]
1|4160|Loss: 0.8688364624977112:  16%|█▌        | 4160/25880 [52:48<3:58:53,  1.52it/s]
1|4161|Loss: 0.9562560319900513:  16%|█▌        | 4160/25880 [52:49<3:58:53,  1.52it/s]
1|4161|Loss: 0.9562560319900513:  16%|█▌        | 4161/25880 [52:49<4:06:09,  1.47it/s]
1|4162|Loss: 0.793254554271698:  16%|█▌        | 4161/25880 [52:50<4:06:09,  1.47it/s] 
1|4162|Loss: 0.793254554271698:  16%|█▌        | 4162/25880 [52:50<4:17:23,  1.41it/s]
1|4163|Loss: 0.7691571116447449:  16%|█▌        | 4162/25880 [52:50<4:17:23,  1.41it/s]
1|4163|Loss: 0.7691571116447449:  16%|█▌        | 4163/25880 [52:51<4:40:47,  1.29it/s]
1|4164|Loss: 0.9073077440261841:  16%|█▌        | 4163/25880 [52:51<4:40:47,  1.29it/s]
1|4164|Loss: 0.9073077440261841:  16%|█▌        | 4164/25880 [52:52<4:40:54,  1.29it/s]
1|4165|Loss: 0.8636484146118164:  16%|█▌        | 4164/25880 [52:52<4:40:54,  1.29it/s]
1|4165|Loss: 0.8636484146118164:  16%|█▌        | 4165/25880 [52:52<4:36:34,  1.31it/s]
1|4166|Loss: 0.8916834592819214:  16%|█▌        | 4165/25880 [52:53<4:36:34,  1.31it/s]
1|4166|Loss: 0.8916834592819214:  16%|█▌        | 4166/25880 [52:53<4:34:23,  1.32it/s]
1|4167|Loss: 0.825268030166626:  16%|█▌        | 4166/25880 [52:53<4:34:23,  1.32it/s] 
1|4167|Loss: 0.825268030166626:  16%|█▌        | 4167/25880 [52:54<4:25:10,  1.36it/s]
1|4168|Loss: 0.795060932636261:  16%|█▌        | 4167/25880 [52:54<4:25:10,  1.36it/s]
1|4168|Loss: 0.795060932636261:  16%|█▌        | 4168/25880 [52:55<4:32:19,  1.33it/s]
1|4169|Loss: 0.8674786686897278:  16%|█▌        | 4168/25880 [52:55<4:32:19,  1.33it/s]
1|4169|Loss: 0.8674786686897278:  16%|█▌        | 4169/25880 [52:55<4:42:12,  1.28it/s]
1|4170|Loss: 0.8262507915496826:  16%|█▌        | 4169/25880 [52:56<4:42:12,  1.28it/s]
1|4170|Loss: 0.8262507915496826:  16%|█▌        | 4170/25880 [52:56<4:32:35,  1.33it/s]
1|4171|Loss: 0.9599711298942566:  16%|█▌        | 4170/25880 [52:56<4:32:35,  1.33it/s]
1|4171|Loss: 0.9599711298942566:  16%|█▌        | 4171/25880 [52:57<4:36:37,  1.31it/s]
1|4172|Loss: 0.9555503129959106:  16%|█▌        | 4171/25880 [52:57<4:36:37,  1.31it/s]
1|4172|Loss: 0.9555503129959106:  16%|█▌        | 4172/25880 [52:58<4:32:57,  1.33it/s]
1|4173|Loss: 0.7146748900413513:  16%|█▌        | 4172/25880 [52:58<4:32:57,  1.33it/s]
1|4173|Loss: 0.7146748900413513:  16%|█▌        | 4173/25880 [52:58<4:26:37,  1.36it/s]
1|4174|Loss: 0.8499758243560791:  16%|█▌        | 4173/25880 [52:59<4:26:37,  1.36it/s]
1|4174|Loss: 0.8499758243560791:  16%|█▌        | 4174/25880 [52:59<4:33:15,  1.32it/s]
1|4175|Loss: 0.9635202288627625:  16%|█▌        | 4174/25880 [53:00<4:33:15,  1.32it/s]
1|4175|Loss: 0.9635202288627625:  16%|█▌        | 4175/25880 [53:00<4:45:22,  1.27it/s]
1|4176|Loss: 0.8165216445922852:  16%|█▌        | 4175/25880 [53:00<4:45:22,  1.27it/s]
1|4176|Loss: 0.8165216445922852:  16%|█▌        | 4176/25880 [53:01<4:30:04,  1.34it/s]
1|4177|Loss: 0.8217282891273499:  16%|█▌        | 4176/25880 [53:01<4:30:04,  1.34it/s]
1|4177|Loss: 0.8217282891273499:  16%|█▌        | 4177/25880 [53:01<4:29:38,  1.34it/s]
1|4178|Loss: 0.8675970435142517:  16%|█▌        | 4177/25880 [53:02<4:29:38,  1.34it/s]
1|4178|Loss: 0.8675970435142517:  16%|█▌        | 4178/25880 [53:02<4:39:45,  1.29it/s]
1|4179|Loss: 0.9385091066360474:  16%|█▌        | 4178/25880 [53:03<4:39:45,  1.29it/s]
1|4179|Loss: 0.9385091066360474:  16%|█▌        | 4179/25880 [53:03<4:49:45,  1.25it/s]
1|4180|Loss: 0.9957748055458069:  16%|█▌        | 4179/25880 [53:03<4:49:45,  1.25it/s]
1|4180|Loss: 0.9957748055458069:  16%|█▌        | 4180/25880 [53:04<4:26:15,  1.36it/s]
1|4181|Loss: 0.9158028960227966:  16%|█▌        | 4180/25880 [53:04<4:26:15,  1.36it/s]
1|4181|Loss: 0.9158028960227966:  16%|█▌        | 4181/25880 [53:04<4:05:56,  1.47it/s]
1|4182|Loss: 0.8489224314689636:  16%|█▌        | 4181/25880 [53:05<4:05:56,  1.47it/s]
1|4182|Loss: 0.8489224314689636:  16%|█▌        | 4182/25880 [53:05<3:54:37,  1.54it/s]
1|4183|Loss: 0.7725787162780762:  16%|█▌        | 4182/25880 [53:05<3:54:37,  1.54it/s]
1|4183|Loss: 0.7725787162780762:  16%|█▌        | 4183/25880 [53:05<3:47:18,  1.59it/s]
1|4184|Loss: 0.9343085885047913:  16%|█▌        | 4183/25880 [53:06<3:47:18,  1.59it/s]
1|4184|Loss: 0.9343085885047913:  16%|█▌        | 4184/25880 [53:06<3:41:55,  1.63it/s]
1|4185|Loss: 0.7052720189094543:  16%|█▌        | 4184/25880 [53:06<3:41:55,  1.63it/s]
1|4185|Loss: 0.7052720189094543:  16%|█▌        | 4185/25880 [53:07<3:59:06,  1.51it/s]
1|4186|Loss: 0.906729519367218:  16%|█▌        | 4185/25880 [53:07<3:59:06,  1.51it/s] 
1|4186|Loss: 0.906729519367218:  16%|█▌        | 4186/25880 [53:07<4:00:25,  1.50it/s]
1|4187|Loss: 0.8224218487739563:  16%|█▌        | 4186/25880 [53:08<4:00:25,  1.50it/s]
1|4187|Loss: 0.8224218487739563:  16%|█▌        | 4187/25880 [53:08<4:06:58,  1.46it/s]
1|4188|Loss: 0.8346778154373169:  16%|█▌        | 4187/25880 [53:09<4:06:58,  1.46it/s]
1|4188|Loss: 0.8346778154373169:  16%|█▌        | 4188/25880 [53:09<4:10:10,  1.45it/s]
1|4189|Loss: 0.8240509629249573:  16%|█▌        | 4188/25880 [53:09<4:10:10,  1.45it/s]
1|4189|Loss: 0.8240509629249573:  16%|█▌        | 4189/25880 [53:10<4:14:30,  1.42it/s]
1|4190|Loss: 0.9742275476455688:  16%|█▌        | 4189/25880 [53:10<4:14:30,  1.42it/s]
1|4190|Loss: 0.9742275476455688:  16%|█▌        | 4190/25880 [53:10<4:00:52,  1.50it/s]
1|4191|Loss: 0.9935322403907776:  16%|█▌        | 4190/25880 [53:10<4:00:52,  1.50it/s]
1|4191|Loss: 0.9935322403907776:  16%|█▌        | 4191/25880 [53:11<3:50:00,  1.57it/s]
1|4192|Loss: 0.7835066318511963:  16%|█▌        | 4191/25880 [53:11<3:50:00,  1.57it/s]
1|4192|Loss: 0.7835066318511963:  16%|█▌        | 4192/25880 [53:11<4:07:25,  1.46it/s]
1|4193|Loss: 0.869881272315979:  16%|█▌        | 4192/25880 [53:12<4:07:25,  1.46it/s] 
1|4193|Loss: 0.869881272315979:  16%|█▌        | 4193/25880 [53:12<3:57:05,  1.52it/s]
1|4194|Loss: 0.8725546002388:  16%|█▌        | 4193/25880 [53:12<3:57:05,  1.52it/s]  
1|4194|Loss: 0.8725546002388:  16%|█▌        | 4194/25880 [53:13<3:59:57,  1.51it/s]
1|4195|Loss: 0.8331269025802612:  16%|█▌        | 4194/25880 [53:13<3:59:57,  1.51it/s]
1|4195|Loss: 0.8331269025802612:  16%|█▌        | 4195/25880 [53:13<3:47:33,  1.59it/s]
1|4196|Loss: 0.9507790803909302:  16%|█▌        | 4195/25880 [53:14<3:47:33,  1.59it/s]
1|4196|Loss: 0.9507790803909302:  16%|█▌        | 4196/25880 [53:14<4:04:03,  1.48it/s]
1|4197|Loss: 0.7792001962661743:  16%|█▌        | 4196/25880 [53:14<4:04:03,  1.48it/s]
1|4197|Loss: 0.7792001962661743:  16%|█▌        | 4197/25880 [53:15<4:03:23,  1.48it/s]
1|4198|Loss: 0.8729504942893982:  16%|█▌        | 4197/25880 [53:15<4:03:23,  1.48it/s]
1|4198|Loss: 0.8729504942893982:  16%|█▌        | 4198/25880 [53:15<3:55:09,  1.54it/s]
1|4199|Loss: 0.7485647797584534:  16%|█▌        | 4198/25880 [53:16<3:55:09,  1.54it/s]
1|4199|Loss: 0.7485647797584534:  16%|█▌        | 4199/25880 [53:16<4:00:04,  1.51it/s]
1|4200|Loss: 0.8461394309997559:  16%|█▌        | 4199/25880 [53:16<4:00:04,  1.51it/s]
1|4200|Loss: 0.8461394309997559:  16%|█▌        | 4200/25880 [53:17<3:59:01,  1.51it/s]
1|4201|Loss: 0.8849011659622192:  16%|█▌        | 4200/25880 [53:17<3:59:01,  1.51it/s]
1|4201|Loss: 0.8849011659622192:  16%|█▌        | 4201/25880 [53:18<4:25:20,  1.36it/s]
1|4202|Loss: 1.0190527439117432:  16%|█▌        | 4201/25880 [53:18<4:25:20,  1.36it/s]
1|4202|Loss: 1.0190527439117432:  16%|█▌        | 4202/25880 [53:18<4:30:27,  1.34it/s]
1|4203|Loss: 0.7867582440376282:  16%|█▌        | 4202/25880 [53:19<4:30:27,  1.34it/s]
1|4203|Loss: 0.7867582440376282:  16%|█▌        | 4203/25880 [53:19<4:33:31,  1.32it/s]
1|4204|Loss: 0.8708658814430237:  16%|█▌        | 4203/25880 [53:20<4:33:31,  1.32it/s]
1|4204|Loss: 0.8708658814430237:  16%|█▌        | 4204/25880 [53:20<4:54:54,  1.23it/s]
1|4205|Loss: 0.8987715244293213:  16%|█▌        | 4204/25880 [53:21<4:54:54,  1.23it/s]
1|4205|Loss: 0.8987715244293213:  16%|█▌        | 4205/25880 [53:21<4:45:09,  1.27it/s]
1|4206|Loss: 0.9336739182472229:  16%|█▌        | 4205/25880 [53:21<4:45:09,  1.27it/s]
1|4206|Loss: 0.9336739182472229:  16%|█▋        | 4206/25880 [53:22<4:42:52,  1.28it/s]
1|4207|Loss: 0.8653042316436768:  16%|█▋        | 4206/25880 [53:22<4:42:52,  1.28it/s]
1|4207|Loss: 0.8653042316436768:  16%|█▋        | 4207/25880 [53:22<4:39:37,  1.29it/s]
1|4208|Loss: 0.8730809688568115:  16%|█▋        | 4207/25880 [53:23<4:39:37,  1.29it/s]
1|4208|Loss: 0.8730809688568115:  16%|█▋        | 4208/25880 [53:23<4:35:35,  1.31it/s]
1|4209|Loss: 0.843504786491394:  16%|█▋        | 4208/25880 [53:24<4:35:35,  1.31it/s] 
1|4209|Loss: 0.843504786491394:  16%|█▋        | 4209/25880 [53:24<4:31:20,  1.33it/s]
1|4210|Loss: 0.8387936949729919:  16%|█▋        | 4209/25880 [53:24<4:31:20,  1.33it/s]
1|4210|Loss: 0.8387936949729919:  16%|█▋        | 4210/25880 [53:24<4:09:16,  1.45it/s]
1|4211|Loss: 0.8502655029296875:  16%|█▋        | 4210/25880 [53:25<4:09:16,  1.45it/s]
1|4211|Loss: 0.8502655029296875:  16%|█▋        | 4211/25880 [53:25<4:14:59,  1.42it/s]
1|4212|Loss: 0.8818783760070801:  16%|█▋        | 4211/25880 [53:26<4:14:59,  1.42it/s]
1|4212|Loss: 0.8818783760070801:  16%|█▋        | 4212/25880 [53:26<4:19:52,  1.39it/s]
1|4213|Loss: 0.8308041095733643:  16%|█▋        | 4212/25880 [53:26<4:19:52,  1.39it/s]
1|4213|Loss: 0.8308041095733643:  16%|█▋        | 4213/25880 [53:27<4:29:52,  1.34it/s]
1|4214|Loss: 0.7805968523025513:  16%|█▋        | 4213/25880 [53:27<4:29:52,  1.34it/s]
1|4214|Loss: 0.7805968523025513:  16%|█▋        | 4214/25880 [53:27<4:21:58,  1.38it/s]
1|4215|Loss: 0.8558773398399353:  16%|█▋        | 4214/25880 [53:28<4:21:58,  1.38it/s]
1|4215|Loss: 0.8558773398399353:  16%|█▋        | 4215/25880 [53:28<4:29:11,  1.34it/s]
1|4216|Loss: 0.8681783080101013:  16%|█▋        | 4215/25880 [53:29<4:29:11,  1.34it/s]
1|4216|Loss: 0.8681783080101013:  16%|█▋        | 4216/25880 [53:29<4:20:19,  1.39it/s]
1|4217|Loss: 0.8641421794891357:  16%|█▋        | 4216/25880 [53:29<4:20:19,  1.39it/s]
1|4217|Loss: 0.8641421794891357:  16%|█▋        | 4217/25880 [53:30<4:32:15,  1.33it/s]
1|4218|Loss: 0.7669360041618347:  16%|█▋        | 4217/25880 [53:30<4:32:15,  1.33it/s]
1|4218|Loss: 0.7669360041618347:  16%|█▋        | 4218/25880 [53:30<4:37:30,  1.30it/s]
1|4219|Loss: 0.7849034667015076:  16%|█▋        | 4218/25880 [53:31<4:37:30,  1.30it/s]
1|4219|Loss: 0.7849034667015076:  16%|█▋        | 4219/25880 [53:31<4:34:38,  1.31it/s]
1|4220|Loss: 0.8997223973274231:  16%|█▋        | 4219/25880 [53:32<4:34:38,  1.31it/s]
1|4220|Loss: 0.8997223973274231:  16%|█▋        | 4220/25880 [53:32<4:06:51,  1.46it/s]
1|4221|Loss: 0.8121454119682312:  16%|█▋        | 4220/25880 [53:32<4:06:51,  1.46it/s]
1|4221|Loss: 0.8121454119682312:  16%|█▋        | 4221/25880 [53:32<4:02:33,  1.49it/s]
1|4222|Loss: 0.8758732080459595:  16%|█▋        | 4221/25880 [53:33<4:02:33,  1.49it/s]
1|4222|Loss: 0.8758732080459595:  16%|█▋        | 4222/25880 [53:33<4:29:26,  1.34it/s]
1|4223|Loss: 0.7816770672798157:  16%|█▋        | 4222/25880 [53:34<4:29:26,  1.34it/s]
1|4223|Loss: 0.7816770672798157:  16%|█▋        | 4223/25880 [53:34<4:50:55,  1.24it/s]
1|4224|Loss: 0.8829189538955688:  16%|█▋        | 4223/25880 [53:35<4:50:55,  1.24it/s]
1|4224|Loss: 0.8829189538955688:  16%|█▋        | 4224/25880 [53:35<4:38:58,  1.29it/s]
1|4225|Loss: 0.8767819404602051:  16%|█▋        | 4224/25880 [53:35<4:38:58,  1.29it/s]
1|4225|Loss: 0.8767819404602051:  16%|█▋        | 4225/25880 [53:36<4:24:45,  1.36it/s]
1|4226|Loss: 0.7702372670173645:  16%|█▋        | 4225/25880 [53:36<4:24:45,  1.36it/s]
1|4226|Loss: 0.7702372670173645:  16%|█▋        | 4226/25880 [53:36<4:33:27,  1.32it/s]
1|4227|Loss: 0.8180909156799316:  16%|█▋        | 4226/25880 [53:37<4:33:27,  1.32it/s]
1|4227|Loss: 0.8180909156799316:  16%|█▋        | 4227/25880 [53:37<4:23:56,  1.37it/s]
1|4228|Loss: 0.8834143877029419:  16%|█▋        | 4227/25880 [53:37<4:23:56,  1.37it/s]
1|4228|Loss: 0.8834143877029419:  16%|█▋        | 4228/25880 [53:38<4:22:24,  1.38it/s]
1|4229|Loss: 0.9092566967010498:  16%|█▋        | 4228/25880 [53:38<4:22:24,  1.38it/s]
1|4229|Loss: 0.9092566967010498:  16%|█▋        | 4229/25880 [53:39<4:43:40,  1.27it/s]
1|4230|Loss: 0.8555096983909607:  16%|█▋        | 4229/25880 [53:39<4:43:40,  1.27it/s]
1|4230|Loss: 0.8555096983909607:  16%|█▋        | 4230/25880 [53:39<4:30:37,  1.33it/s]
1|4231|Loss: 0.8833298683166504:  16%|█▋        | 4230/25880 [53:40<4:30:37,  1.33it/s]
1|4231|Loss: 0.8833298683166504:  16%|█▋        | 4231/25880 [53:40<4:35:29,  1.31it/s]
1|4232|Loss: 0.9943997859954834:  16%|█▋        | 4231/25880 [53:41<4:35:29,  1.31it/s]
1|4232|Loss: 0.9943997859954834:  16%|█▋        | 4232/25880 [53:41<4:16:28,  1.41it/s]
1|4233|Loss: 0.8211054801940918:  16%|█▋        | 4232/25880 [53:41<4:16:28,  1.41it/s]
1|4233|Loss: 0.8211054801940918:  16%|█▋        | 4233/25880 [53:41<4:15:35,  1.41it/s]
1|4234|Loss: 0.7829347848892212:  16%|█▋        | 4233/25880 [53:42<4:15:35,  1.41it/s]
1|4234|Loss: 0.7829347848892212:  16%|█▋        | 4234/25880 [53:42<4:23:58,  1.37it/s]
1|4235|Loss: 0.9000897407531738:  16%|█▋        | 4234/25880 [53:43<4:23:58,  1.37it/s]
1|4235|Loss: 0.9000897407531738:  16%|█▋        | 4235/25880 [53:43<4:34:10,  1.32it/s]
1|4236|Loss: 1.213548183441162:  16%|█▋        | 4235/25880 [53:44<4:34:10,  1.32it/s] 
1|4236|Loss: 1.213548183441162:  16%|█▋        | 4236/25880 [53:44<4:49:21,  1.25it/s]
1|4237|Loss: 0.8271276950836182:  16%|█▋        | 4236/25880 [53:44<4:49:21,  1.25it/s]
1|4237|Loss: 0.8271276950836182:  16%|█▋        | 4237/25880 [53:45<4:43:18,  1.27it/s]
1|4238|Loss: 0.8155209422111511:  16%|█▋        | 4237/25880 [53:45<4:43:18,  1.27it/s]
1|4238|Loss: 0.8155209422111511:  16%|█▋        | 4238/25880 [53:46<5:16:46,  1.14it/s]
1|4239|Loss: 0.9013468027114868:  16%|█▋        | 4238/25880 [53:46<5:16:46,  1.14it/s]
1|4239|Loss: 0.9013468027114868:  16%|█▋        | 4239/25880 [53:47<5:12:00,  1.16it/s]
1|4240|Loss: 0.8298699259757996:  16%|█▋        | 4239/25880 [53:47<5:12:00,  1.16it/s]
1|4240|Loss: 0.8298699259757996:  16%|█▋        | 4240/25880 [53:47<4:55:11,  1.22it/s]
1|4241|Loss: 0.9319421648979187:  16%|█▋        | 4240/25880 [53:48<4:55:11,  1.22it/s]
1|4241|Loss: 0.9319421648979187:  16%|█▋        | 4241/25880 [53:48<4:36:48,  1.30it/s]
1|4242|Loss: 1.147326111793518:  16%|█▋        | 4241/25880 [53:48<4:36:48,  1.30it/s] 
1|4242|Loss: 1.147326111793518:  16%|█▋        | 4242/25880 [53:49<4:42:36,  1.28it/s]
1|4243|Loss: 0.9089637994766235:  16%|█▋        | 4242/25880 [53:49<4:42:36,  1.28it/s]
1|4243|Loss: 0.9089637994766235:  16%|█▋        | 4243/25880 [53:50<4:41:30,  1.28it/s]
1|4244|Loss: 0.9469945430755615:  16%|█▋        | 4243/25880 [53:50<4:41:30,  1.28it/s]
1|4244|Loss: 0.9469945430755615:  16%|█▋        | 4244/25880 [53:50<4:23:08,  1.37it/s]
1|4245|Loss: 0.8719573020935059:  16%|█▋        | 4244/25880 [53:51<4:23:08,  1.37it/s]
1|4245|Loss: 0.8719573020935059:  16%|█▋        | 4245/25880 [53:51<4:28:26,  1.34it/s]
1|4246|Loss: 0.8189886808395386:  16%|█▋        | 4245/25880 [53:51<4:28:26,  1.34it/s]
1|4246|Loss: 0.8189886808395386:  16%|█▋        | 4246/25880 [53:52<4:37:49,  1.30it/s]
1|4247|Loss: 0.9094488024711609:  16%|█▋        | 4246/25880 [53:52<4:37:49,  1.30it/s]
1|4247|Loss: 0.9094488024711609:  16%|█▋        | 4247/25880 [53:53<4:46:27,  1.26it/s]
1|4248|Loss: 0.8339160680770874:  16%|█▋        | 4247/25880 [53:53<4:46:27,  1.26it/s]
1|4248|Loss: 0.8339160680770874:  16%|█▋        | 4248/25880 [53:53<4:52:47,  1.23it/s]
1|4249|Loss: 0.9487538933753967:  16%|█▋        | 4248/25880 [53:54<4:52:47,  1.23it/s]
1|4249|Loss: 0.9487538933753967:  16%|█▋        | 4249/25880 [53:54<4:45:27,  1.26it/s]
1|4250|Loss: 0.8797248005867004:  16%|█▋        | 4249/25880 [53:55<4:45:27,  1.26it/s]
1|4250|Loss: 0.8797248005867004:  16%|█▋        | 4250/25880 [53:55<4:36:22,  1.30it/s]
1|4251|Loss: 0.7460011839866638:  16%|█▋        | 4250/25880 [53:55<4:36:22,  1.30it/s]
1|4251|Loss: 0.7460011839866638:  16%|█▋        | 4251/25880 [53:55<4:02:10,  1.49it/s]
1|4252|Loss: 0.7706702947616577:  16%|█▋        | 4251/25880 [53:56<4:02:10,  1.49it/s]
1|4252|Loss: 0.7706702947616577:  16%|█▋        | 4252/25880 [53:56<3:54:24,  1.54it/s]
1|4253|Loss: 0.8913635015487671:  16%|█▋        | 4252/25880 [53:56<3:54:24,  1.54it/s]
1|4253|Loss: 0.8913635015487671:  16%|█▋        | 4253/25880 [53:57<3:59:05,  1.51it/s]
1|4254|Loss: 0.9631218314170837:  16%|█▋        | 4253/25880 [53:57<3:59:05,  1.51it/s]
1|4254|Loss: 0.9631218314170837:  16%|█▋        | 4254/25880 [53:57<3:52:13,  1.55it/s]
1|4255|Loss: 0.9080824255943298:  16%|█▋        | 4254/25880 [53:58<3:52:13,  1.55it/s]
1|4255|Loss: 0.9080824255943298:  16%|█▋        | 4255/25880 [53:58<4:14:27,  1.42it/s]
1|4256|Loss: 0.8758347034454346:  16%|█▋        | 4255/25880 [53:59<4:14:27,  1.42it/s]
1|4256|Loss: 0.8758347034454346:  16%|█▋        | 4256/25880 [53:59<4:30:09,  1.33it/s]
1|4257|Loss: 1.031470537185669:  16%|█▋        | 4256/25880 [53:59<4:30:09,  1.33it/s] 
1|4257|Loss: 1.031470537185669:  16%|█▋        | 4257/25880 [54:00<4:21:47,  1.38it/s]
1|4258|Loss: 0.8304914236068726:  16%|█▋        | 4257/25880 [54:00<4:21:47,  1.38it/s]
1|4258|Loss: 0.8304914236068726:  16%|█▋        | 4258/25880 [54:00<4:17:58,  1.40it/s]
1|4259|Loss: 0.8831350803375244:  16%|█▋        | 4258/25880 [54:01<4:17:58,  1.40it/s]
1|4259|Loss: 0.8831350803375244:  16%|█▋        | 4259/25880 [54:01<4:30:55,  1.33it/s]
1|4260|Loss: 0.996712327003479:  16%|█▋        | 4259/25880 [54:02<4:30:55,  1.33it/s] 
1|4260|Loss: 0.996712327003479:  16%|█▋        | 4260/25880 [54:02<4:33:05,  1.32it/s]
1|4261|Loss: 0.8164470791816711:  16%|█▋        | 4260/25880 [54:02<4:33:05,  1.32it/s]
1|4261|Loss: 0.8164470791816711:  16%|█▋        | 4261/25880 [54:03<4:27:19,  1.35it/s]
1|4262|Loss: 0.9169356226921082:  16%|█▋        | 4261/25880 [54:03<4:27:19,  1.35it/s]
1|4262|Loss: 0.9169356226921082:  16%|█▋        | 4262/25880 [54:03<4:25:26,  1.36it/s]
1|4263|Loss: 0.8641718029975891:  16%|█▋        | 4262/25880 [54:04<4:25:26,  1.36it/s]
1|4263|Loss: 0.8641718029975891:  16%|█▋        | 4263/25880 [54:04<4:36:33,  1.30it/s]
1|4264|Loss: 0.8945672512054443:  16%|█▋        | 4263/25880 [54:05<4:36:33,  1.30it/s]
1|4264|Loss: 0.8945672512054443:  16%|█▋        | 4264/25880 [54:05<4:26:28,  1.35it/s]
1|4265|Loss: 0.8953070044517517:  16%|█▋        | 4264/25880 [54:05<4:26:28,  1.35it/s]
1|4265|Loss: 0.8953070044517517:  16%|█▋        | 4265/25880 [54:06<4:29:20,  1.34it/s]
1|4266|Loss: 0.8707192540168762:  16%|█▋        | 4265/25880 [54:06<4:29:20,  1.34it/s]
1|4266|Loss: 0.8707192540168762:  16%|█▋        | 4266/25880 [54:06<4:13:35,  1.42it/s]
1|4267|Loss: 0.8025656938552856:  16%|█▋        | 4266/25880 [54:07<4:13:35,  1.42it/s]
1|4267|Loss: 0.8025656938552856:  16%|█▋        | 4267/25880 [54:07<3:51:44,  1.55it/s]
1|4268|Loss: 0.8728927969932556:  16%|█▋        | 4267/25880 [54:07<3:51:44,  1.55it/s]
1|4268|Loss: 0.8728927969932556:  16%|█▋        | 4268/25880 [54:07<3:31:53,  1.70it/s]
1|4269|Loss: 0.8330718278884888:  16%|█▋        | 4268/25880 [54:08<3:31:53,  1.70it/s]
1|4269|Loss: 0.8330718278884888:  16%|█▋        | 4269/25880 [54:08<3:41:45,  1.62it/s]
1|4270|Loss: 0.7777588367462158:  16%|█▋        | 4269/25880 [54:08<3:41:45,  1.62it/s]
1|4270|Loss: 0.7777588367462158:  16%|█▋        | 4270/25880 [54:09<3:52:45,  1.55it/s]
1|4271|Loss: 0.8693236708641052:  16%|█▋        | 4270/25880 [54:09<3:52:45,  1.55it/s]
1|4271|Loss: 0.8693236708641052:  17%|█▋        | 4271/25880 [54:09<4:06:08,  1.46it/s]
1|4272|Loss: 0.8076991438865662:  17%|█▋        | 4271/25880 [54:10<4:06:08,  1.46it/s]
1|4272|Loss: 0.8076991438865662:  17%|█▋        | 4272/25880 [54:10<3:55:03,  1.53it/s]
1|4273|Loss: 0.9493348598480225:  17%|█▋        | 4272/25880 [54:10<3:55:03,  1.53it/s]
1|4273|Loss: 0.9493348598480225:  17%|█▋        | 4273/25880 [54:11<4:11:19,  1.43it/s]
1|4274|Loss: 0.8287085890769958:  17%|█▋        | 4273/25880 [54:11<4:11:19,  1.43it/s]
1|4274|Loss: 0.8287085890769958:  17%|█▋        | 4274/25880 [54:12<4:27:29,  1.35it/s]
1|4275|Loss: 0.9866775870323181:  17%|█▋        | 4274/25880 [54:12<4:27:29,  1.35it/s]
1|4275|Loss: 0.9866775870323181:  17%|█▋        | 4275/25880 [54:12<4:15:34,  1.41it/s]
1|4276|Loss: 0.8274542689323425:  17%|█▋        | 4275/25880 [54:13<4:15:34,  1.41it/s]
1|4276|Loss: 0.8274542689323425:  17%|█▋        | 4276/25880 [54:13<4:06:46,  1.46it/s]
1|4277|Loss: 1.0265594720840454:  17%|█▋        | 4276/25880 [54:13<4:06:46,  1.46it/s]
1|4277|Loss: 1.0265594720840454:  17%|█▋        | 4277/25880 [54:14<4:00:04,  1.50it/s]
1|4278|Loss: 0.8034293055534363:  17%|█▋        | 4277/25880 [54:14<4:00:04,  1.50it/s]
1|4278|Loss: 0.8034293055534363:  17%|█▋        | 4278/25880 [54:14<3:56:16,  1.52it/s]
1|4279|Loss: 1.0606354475021362:  17%|█▋        | 4278/25880 [54:15<3:56:16,  1.52it/s]
1|4279|Loss: 1.0606354475021362:  17%|█▋        | 4279/25880 [54:15<3:54:58,  1.53it/s]
1|4280|Loss: 0.9358078837394714:  17%|█▋        | 4279/25880 [54:15<3:54:58,  1.53it/s]
1|4280|Loss: 0.9358078837394714:  17%|█▋        | 4280/25880 [54:16<4:02:20,  1.49it/s]
1|4281|Loss: 0.9027990698814392:  17%|█▋        | 4280/25880 [54:16<4:02:20,  1.49it/s]
1|4281|Loss: 0.9027990698814392:  17%|█▋        | 4281/25880 [54:16<4:19:41,  1.39it/s]
1|4282|Loss: 0.7821304798126221:  17%|█▋        | 4281/25880 [54:17<4:19:41,  1.39it/s]
1|4282|Loss: 0.7821304798126221:  17%|█▋        | 4282/25880 [54:17<3:52:06,  1.55it/s]
1|4283|Loss: 0.8660429120063782:  17%|█▋        | 4282/25880 [54:17<3:52:06,  1.55it/s]
1|4283|Loss: 0.8660429120063782:  17%|█▋        | 4283/25880 [54:18<4:07:24,  1.45it/s]
1|4284|Loss: 0.7723789215087891:  17%|█▋        | 4283/25880 [54:18<4:07:24,  1.45it/s]
1|4284|Loss: 0.7723789215087891:  17%|█▋        | 4284/25880 [54:18<4:16:43,  1.40it/s]
1|4285|Loss: 0.8371660709381104:  17%|█▋        | 4284/25880 [54:19<4:16:43,  1.40it/s]
1|4285|Loss: 0.8371660709381104:  17%|█▋        | 4285/25880 [54:19<4:19:39,  1.39it/s]
1|4286|Loss: 0.8451535701751709:  17%|█▋        | 4285/25880 [54:20<4:19:39,  1.39it/s]
1|4286|Loss: 0.8451535701751709:  17%|█▋        | 4286/25880 [54:20<4:21:30,  1.38it/s]
1|4287|Loss: 0.783527135848999:  17%|█▋        | 4286/25880 [54:20<4:21:30,  1.38it/s] 
1|4287|Loss: 0.783527135848999:  17%|█▋        | 4287/25880 [54:20<3:58:09,  1.51it/s]
1|4288|Loss: 0.8808326125144958:  17%|█▋        | 4287/25880 [54:21<3:58:09,  1.51it/s]
1|4288|Loss: 0.8808326125144958:  17%|█▋        | 4288/25880 [54:21<3:56:10,  1.52it/s]
1|4289|Loss: 0.8678447604179382:  17%|█▋        | 4288/25880 [54:21<3:56:10,  1.52it/s]
1|4289|Loss: 0.8678447604179382:  17%|█▋        | 4289/25880 [54:22<4:01:10,  1.49it/s]
1|4290|Loss: 0.8313086628913879:  17%|█▋        | 4289/25880 [54:22<4:01:10,  1.49it/s]
1|4290|Loss: 0.8313086628913879:  17%|█▋        | 4290/25880 [54:22<3:54:50,  1.53it/s]
1|4291|Loss: 0.7851917147636414:  17%|█▋        | 4290/25880 [54:23<3:54:50,  1.53it/s]
1|4291|Loss: 0.7851917147636414:  17%|█▋        | 4291/25880 [54:23<4:00:27,  1.50it/s]
1|4292|Loss: 0.7789804935455322:  17%|█▋        | 4291/25880 [54:24<4:00:27,  1.50it/s]
1|4292|Loss: 0.7789804935455322:  17%|█▋        | 4292/25880 [54:24<4:27:29,  1.35it/s]
1|4293|Loss: 0.8079282641410828:  17%|█▋        | 4292/25880 [54:24<4:27:29,  1.35it/s]
1|4293|Loss: 0.8079282641410828:  17%|█▋        | 4293/25880 [54:25<4:30:40,  1.33it/s]
1|4294|Loss: 0.9230501055717468:  17%|█▋        | 4293/25880 [54:25<4:30:40,  1.33it/s]
1|4294|Loss: 0.9230501055717468:  17%|█▋        | 4294/25880 [54:25<4:14:54,  1.41it/s]
1|4295|Loss: 0.7752789855003357:  17%|█▋        | 4294/25880 [54:26<4:14:54,  1.41it/s]
1|4295|Loss: 0.7752789855003357:  17%|█▋        | 4295/25880 [54:26<4:05:53,  1.46it/s]
1|4296|Loss: 0.836553692817688:  17%|█▋        | 4295/25880 [54:26<4:05:53,  1.46it/s] 
1|4296|Loss: 0.836553692817688:  17%|█▋        | 4296/25880 [54:27<4:17:10,  1.40it/s]
1|4297|Loss: 0.9545534253120422:  17%|█▋        | 4296/25880 [54:27<4:17:10,  1.40it/s]
1|4297|Loss: 0.9545534253120422:  17%|█▋        | 4297/25880 [54:28<4:26:45,  1.35it/s]
1|4298|Loss: 0.8527889251708984:  17%|█▋        | 4297/25880 [54:28<4:26:45,  1.35it/s]
1|4298|Loss: 0.8527889251708984:  17%|█▋        | 4298/25880 [54:28<4:26:38,  1.35it/s]
1|4299|Loss: 0.9423702359199524:  17%|█▋        | 4298/25880 [54:29<4:26:38,  1.35it/s]
1|4299|Loss: 0.9423702359199524:  17%|█▋        | 4299/25880 [54:29<4:41:20,  1.28it/s]
1|4300|Loss: 0.6763573288917542:  17%|█▋        | 4299/25880 [54:30<4:41:20,  1.28it/s]
1|4300|Loss: 0.6763573288917542:  17%|█▋        | 4300/25880 [54:30<4:40:53,  1.28it/s]
1|4301|Loss: 0.9775007367134094:  17%|█▋        | 4300/25880 [54:30<4:40:53,  1.28it/s]
1|4301|Loss: 0.9775007367134094:  17%|█▋        | 4301/25880 [54:31<4:26:25,  1.35it/s]
1|4302|Loss: 0.8294930458068848:  17%|█▋        | 4301/25880 [54:31<4:26:25,  1.35it/s]
1|4302|Loss: 0.8294930458068848:  17%|█▋        | 4302/25880 [54:31<4:09:40,  1.44it/s]
1|4303|Loss: 0.8947975039482117:  17%|█▋        | 4302/25880 [54:32<4:09:40,  1.44it/s]
1|4303|Loss: 0.8947975039482117:  17%|█▋        | 4303/25880 [54:32<4:02:15,  1.48it/s]
1|4304|Loss: 0.8046683669090271:  17%|█▋        | 4303/25880 [54:32<4:02:15,  1.48it/s]
1|4304|Loss: 0.8046683669090271:  17%|█▋        | 4304/25880 [54:33<4:16:53,  1.40it/s]
1|4305|Loss: 0.8625322580337524:  17%|█▋        | 4304/25880 [54:33<4:16:53,  1.40it/s]
1|4305|Loss: 0.8625322580337524:  17%|█▋        | 4305/25880 [54:33<4:21:01,  1.38it/s]
1|4306|Loss: 0.8485679030418396:  17%|█▋        | 4305/25880 [54:34<4:21:01,  1.38it/s]
1|4306|Loss: 0.8485679030418396:  17%|█▋        | 4306/25880 [54:34<4:25:56,  1.35it/s]
1|4307|Loss: 0.7877424955368042:  17%|█▋        | 4306/25880 [54:35<4:25:56,  1.35it/s]
1|4307|Loss: 0.7877424955368042:  17%|█▋        | 4307/25880 [54:35<4:14:38,  1.41it/s]
1|4308|Loss: 1.0070546865463257:  17%|█▋        | 4307/25880 [54:35<4:14:38,  1.41it/s]
1|4308|Loss: 1.0070546865463257:  17%|█▋        | 4308/25880 [54:35<3:54:27,  1.53it/s]
1|4309|Loss: 0.8297368288040161:  17%|█▋        | 4308/25880 [54:36<3:54:27,  1.53it/s]
1|4309|Loss: 0.8297368288040161:  17%|█▋        | 4309/25880 [54:36<3:55:08,  1.53it/s]
1|4310|Loss: 0.8981355428695679:  17%|█▋        | 4309/25880 [54:36<3:55:08,  1.53it/s]
1|4310|Loss: 0.8981355428695679:  17%|█▋        | 4310/25880 [54:37<3:50:28,  1.56it/s]
1|4311|Loss: 0.814140260219574:  17%|█▋        | 4310/25880 [54:37<3:50:28,  1.56it/s] 
1|4311|Loss: 0.814140260219574:  17%|█▋        | 4311/25880 [54:37<4:01:39,  1.49it/s]
1|4312|Loss: 0.8692581653594971:  17%|█▋        | 4311/25880 [54:38<4:01:39,  1.49it/s]
1|4312|Loss: 0.8692581653594971:  17%|█▋        | 4312/25880 [54:38<4:10:23,  1.44it/s]
1|4313|Loss: 0.9959220290184021:  17%|█▋        | 4312/25880 [54:39<4:10:23,  1.44it/s]
1|4313|Loss: 0.9959220290184021:  17%|█▋        | 4313/25880 [54:39<4:26:54,  1.35it/s]
1|4314|Loss: 0.6756178140640259:  17%|█▋        | 4313/25880 [54:39<4:26:54,  1.35it/s]
1|4314|Loss: 0.6756178140640259:  17%|█▋        | 4314/25880 [54:40<4:26:19,  1.35it/s]
1|4315|Loss: 0.8081769347190857:  17%|█▋        | 4314/25880 [54:40<4:26:19,  1.35it/s]
1|4315|Loss: 0.8081769347190857:  17%|█▋        | 4315/25880 [54:40<4:28:59,  1.34it/s]
1|4316|Loss: 0.8058023452758789:  17%|█▋        | 4315/25880 [54:41<4:28:59,  1.34it/s]
1|4316|Loss: 0.8058023452758789:  17%|█▋        | 4316/25880 [54:41<4:34:05,  1.31it/s]
1|4317|Loss: 0.838067889213562:  17%|█▋        | 4316/25880 [54:42<4:34:05,  1.31it/s] 
1|4317|Loss: 0.838067889213562:  17%|█▋        | 4317/25880 [54:42<4:42:53,  1.27it/s]
1|4318|Loss: 0.7912877202033997:  17%|█▋        | 4317/25880 [54:42<4:42:53,  1.27it/s]
1|4318|Loss: 0.7912877202033997:  17%|█▋        | 4318/25880 [54:43<4:32:27,  1.32it/s]
1|4319|Loss: 0.8560320734977722:  17%|█▋        | 4318/25880 [54:43<4:32:27,  1.32it/s]
1|4319|Loss: 0.8560320734977722:  17%|█▋        | 4319/25880 [54:43<4:16:02,  1.40it/s]
1|4320|Loss: 0.8100526332855225:  17%|█▋        | 4319/25880 [54:44<4:16:02,  1.40it/s]
1|4320|Loss: 0.8100526332855225:  17%|█▋        | 4320/25880 [54:44<4:16:22,  1.40it/s]
1|4321|Loss: 0.777554452419281:  17%|█▋        | 4320/25880 [54:44<4:16:22,  1.40it/s] 
1|4321|Loss: 0.777554452419281:  17%|█▋        | 4321/25880 [54:45<4:06:12,  1.46it/s]
1|4322|Loss: 0.8827679753303528:  17%|█▋        | 4321/25880 [54:45<4:06:12,  1.46it/s]
1|4322|Loss: 0.8827679753303528:  17%|█▋        | 4322/25880 [54:45<4:04:56,  1.47it/s]
1|4323|Loss: 0.7275504469871521:  17%|█▋        | 4322/25880 [54:46<4:04:56,  1.47it/s]
1|4323|Loss: 0.7275504469871521:  17%|█▋        | 4323/25880 [54:46<4:20:11,  1.38it/s]
1|4324|Loss: 0.8186495900154114:  17%|█▋        | 4323/25880 [54:47<4:20:11,  1.38it/s]
1|4324|Loss: 0.8186495900154114:  17%|█▋        | 4324/25880 [54:47<4:24:18,  1.36it/s]
1|4325|Loss: 0.8159081339836121:  17%|█▋        | 4324/25880 [54:47<4:24:18,  1.36it/s]
1|4325|Loss: 0.8159081339836121:  17%|█▋        | 4325/25880 [54:48<4:10:37,  1.43it/s]
1|4326|Loss: 1.0101964473724365:  17%|█▋        | 4325/25880 [54:48<4:10:37,  1.43it/s]
1|4326|Loss: 1.0101964473724365:  17%|█▋        | 4326/25880 [54:48<4:23:38,  1.36it/s]
1|4327|Loss: 0.8973358869552612:  17%|█▋        | 4326/25880 [54:49<4:23:38,  1.36it/s]
1|4327|Loss: 0.8973358869552612:  17%|█▋        | 4327/25880 [54:49<4:05:55,  1.46it/s]
1|4328|Loss: 0.875462532043457:  17%|█▋        | 4327/25880 [54:49<4:05:55,  1.46it/s] 
1|4328|Loss: 0.875462532043457:  17%|█▋        | 4328/25880 [54:50<3:55:08,  1.53it/s]
1|4329|Loss: 0.8319496512413025:  17%|█▋        | 4328/25880 [54:50<3:55:08,  1.53it/s]
1|4329|Loss: 0.8319496512413025:  17%|█▋        | 4329/25880 [54:50<3:47:48,  1.58it/s]
1|4330|Loss: 0.8089112043380737:  17%|█▋        | 4329/25880 [54:51<3:47:48,  1.58it/s]
1|4330|Loss: 0.8089112043380737:  17%|█▋        | 4330/25880 [54:51<4:03:49,  1.47it/s]
1|4331|Loss: 0.9021210074424744:  17%|█▋        | 4330/25880 [54:51<4:03:49,  1.47it/s]
1|4331|Loss: 0.9021210074424744:  17%|█▋        | 4331/25880 [54:52<4:19:26,  1.38it/s]
1|4332|Loss: 0.818929135799408:  17%|█▋        | 4331/25880 [54:52<4:19:26,  1.38it/s] 
1|4332|Loss: 0.818929135799408:  17%|█▋        | 4332/25880 [54:53<4:28:12,  1.34it/s]
1|4333|Loss: 0.9678569436073303:  17%|█▋        | 4332/25880 [54:53<4:28:12,  1.34it/s]
1|4333|Loss: 0.9678569436073303:  17%|█▋        | 4333/25880 [54:53<4:40:59,  1.28it/s]
1|4334|Loss: 0.8548762798309326:  17%|█▋        | 4333/25880 [54:54<4:40:59,  1.28it/s]
1|4334|Loss: 0.8548762798309326:  17%|█▋        | 4334/25880 [54:54<4:38:55,  1.29it/s]
1|4335|Loss: 0.9649834036827087:  17%|█▋        | 4334/25880 [54:55<4:38:55,  1.29it/s]
1|4335|Loss: 0.9649834036827087:  17%|█▋        | 4335/25880 [54:55<4:25:35,  1.35it/s]
1|4336|Loss: 0.8281905651092529:  17%|█▋        | 4335/25880 [54:55<4:25:35,  1.35it/s]
1|4336|Loss: 0.8281905651092529:  17%|█▋        | 4336/25880 [54:55<4:20:19,  1.38it/s]
1|4337|Loss: 0.8130118250846863:  17%|█▋        | 4336/25880 [54:56<4:20:19,  1.38it/s]
1|4337|Loss: 0.8130118250846863:  17%|█▋        | 4337/25880 [54:56<4:30:56,  1.33it/s]
1|4338|Loss: 0.7729045152664185:  17%|█▋        | 4337/25880 [54:57<4:30:56,  1.33it/s]
1|4338|Loss: 0.7729045152664185:  17%|█▋        | 4338/25880 [54:57<4:24:17,  1.36it/s]
1|4339|Loss: 0.9172698259353638:  17%|█▋        | 4338/25880 [54:57<4:24:17,  1.36it/s]
1|4339|Loss: 0.9172698259353638:  17%|█▋        | 4339/25880 [54:58<4:23:35,  1.36it/s]
1|4340|Loss: 0.797183096408844:  17%|█▋        | 4339/25880 [54:58<4:23:35,  1.36it/s] 
1|4340|Loss: 0.797183096408844:  17%|█▋        | 4340/25880 [54:58<4:08:27,  1.44it/s]
1|4341|Loss: 0.8546133041381836:  17%|█▋        | 4340/25880 [54:59<4:08:27,  1.44it/s]
1|4341|Loss: 0.8546133041381836:  17%|█▋        | 4341/25880 [54:59<4:13:46,  1.41it/s]
1|4342|Loss: 0.8031337261199951:  17%|█▋        | 4341/25880 [55:00<4:13:46,  1.41it/s]
1|4342|Loss: 0.8031337261199951:  17%|█▋        | 4342/25880 [55:00<4:24:02,  1.36it/s]
1|4343|Loss: 0.8136152625083923:  17%|█▋        | 4342/25880 [55:00<4:24:02,  1.36it/s]
1|4343|Loss: 0.8136152625083923:  17%|█▋        | 4343/25880 [55:01<4:14:31,  1.41it/s]
1|4344|Loss: 0.830405592918396:  17%|█▋        | 4343/25880 [55:01<4:14:31,  1.41it/s] 
1|4344|Loss: 0.830405592918396:  17%|█▋        | 4344/25880 [55:01<3:55:43,  1.52it/s]
1|4345|Loss: 0.8642008900642395:  17%|█▋        | 4344/25880 [55:01<3:55:43,  1.52it/s]
1|4345|Loss: 0.8642008900642395:  17%|█▋        | 4345/25880 [55:02<4:00:42,  1.49it/s]
1|4346|Loss: 0.7578395009040833:  17%|█▋        | 4345/25880 [55:02<4:00:42,  1.49it/s]
1|4346|Loss: 0.7578395009040833:  17%|█▋        | 4346/25880 [55:03<4:08:21,  1.45it/s]
1|4347|Loss: 0.9239338040351868:  17%|█▋        | 4346/25880 [55:03<4:08:21,  1.45it/s]
1|4347|Loss: 0.9239338040351868:  17%|█▋        | 4347/25880 [55:03<4:13:46,  1.41it/s]
1|4348|Loss: 0.760636568069458:  17%|█▋        | 4347/25880 [55:04<4:13:46,  1.41it/s] 
1|4348|Loss: 0.760636568069458:  17%|█▋        | 4348/25880 [55:04<4:07:00,  1.45it/s]
1|4349|Loss: 0.9718860983848572:  17%|█▋        | 4348/25880 [55:04<4:07:00,  1.45it/s]
1|4349|Loss: 0.9718860983848572:  17%|█▋        | 4349/25880 [55:05<4:25:01,  1.35it/s]
1|4350|Loss: 0.8858492970466614:  17%|█▋        | 4349/25880 [55:05<4:25:01,  1.35it/s]
1|4350|Loss: 0.8858492970466614:  17%|█▋        | 4350/25880 [55:05<4:16:20,  1.40it/s]
1|4351|Loss: 0.8775016665458679:  17%|█▋        | 4350/25880 [55:06<4:16:20,  1.40it/s]
1|4351|Loss: 0.8775016665458679:  17%|█▋        | 4351/25880 [55:06<4:14:30,  1.41it/s]
1|4352|Loss: 0.9011261463165283:  17%|█▋        | 4351/25880 [55:06<4:14:30,  1.41it/s]
1|4352|Loss: 0.9011261463165283:  17%|█▋        | 4352/25880 [55:07<4:08:30,  1.44it/s]
1|4353|Loss: 1.0011461973190308:  17%|█▋        | 4352/25880 [55:07<4:08:30,  1.44it/s]
1|4353|Loss: 1.0011461973190308:  17%|█▋        | 4353/25880 [55:07<4:11:26,  1.43it/s]
1|4354|Loss: 0.9075379967689514:  17%|█▋        | 4353/25880 [55:08<4:11:26,  1.43it/s]
1|4354|Loss: 0.9075379967689514:  17%|█▋        | 4354/25880 [55:08<4:26:54,  1.34it/s]
1|4355|Loss: 0.870786190032959:  17%|█▋        | 4354/25880 [55:09<4:26:54,  1.34it/s] 
1|4355|Loss: 0.870786190032959:  17%|█▋        | 4355/25880 [55:09<4:33:36,  1.31it/s]
1|4356|Loss: 0.8756946325302124:  17%|█▋        | 4355/25880 [55:10<4:33:36,  1.31it/s]
1|4356|Loss: 0.8756946325302124:  17%|█▋        | 4356/25880 [55:10<4:23:32,  1.36it/s]
1|4357|Loss: 0.7702386975288391:  17%|█▋        | 4356/25880 [55:10<4:23:32,  1.36it/s]
1|4357|Loss: 0.7702386975288391:  17%|█▋        | 4357/25880 [55:10<4:13:05,  1.42it/s]
1|4358|Loss: 0.7959746718406677:  17%|█▋        | 4357/25880 [55:11<4:13:05,  1.42it/s]
1|4358|Loss: 0.7959746718406677:  17%|█▋        | 4358/25880 [55:11<4:11:21,  1.43it/s]
1|4359|Loss: 1.0177404880523682:  17%|█▋        | 4358/25880 [55:12<4:11:21,  1.43it/s]
1|4359|Loss: 1.0177404880523682:  17%|█▋        | 4359/25880 [55:12<4:19:54,  1.38it/s]
1|4360|Loss: 0.765053927898407:  17%|█▋        | 4359/25880 [55:12<4:19:54,  1.38it/s] 
1|4360|Loss: 0.765053927898407:  17%|█▋        | 4360/25880 [55:13<4:14:15,  1.41it/s]
1|4361|Loss: 0.9212297201156616:  17%|█▋        | 4360/25880 [55:13<4:14:15,  1.41it/s]
1|4361|Loss: 0.9212297201156616:  17%|█▋        | 4361/25880 [55:13<4:19:21,  1.38it/s]
1|4362|Loss: 0.8853885531425476:  17%|█▋        | 4361/25880 [55:14<4:19:21,  1.38it/s]
1|4362|Loss: 0.8853885531425476:  17%|█▋        | 4362/25880 [55:14<4:26:44,  1.34it/s]
1|4363|Loss: 0.9105672240257263:  17%|█▋        | 4362/25880 [55:15<4:26:44,  1.34it/s]
1|4363|Loss: 0.9105672240257263:  17%|█▋        | 4363/25880 [55:15<4:19:07,  1.38it/s]
1|4364|Loss: 0.7992985248565674:  17%|█▋        | 4363/25880 [55:15<4:19:07,  1.38it/s]
1|4364|Loss: 0.7992985248565674:  17%|█▋        | 4364/25880 [55:15<4:04:42,  1.47it/s]
1|4365|Loss: 0.8593249917030334:  17%|█▋        | 4364/25880 [55:16<4:04:42,  1.47it/s]
1|4365|Loss: 0.8593249917030334:  17%|█▋        | 4365/25880 [55:16<4:04:29,  1.47it/s]
1|4366|Loss: 0.8631346225738525:  17%|█▋        | 4365/25880 [55:16<4:04:29,  1.47it/s]
1|4366|Loss: 0.8631346225738525:  17%|█▋        | 4366/25880 [55:17<4:10:06,  1.43it/s]
1|4367|Loss: 1.0850030183792114:  17%|█▋        | 4366/25880 [55:17<4:10:06,  1.43it/s]
1|4367|Loss: 1.0850030183792114:  17%|█▋        | 4367/25880 [55:17<4:04:20,  1.47it/s]
1|4368|Loss: 0.9188293814659119:  17%|█▋        | 4367/25880 [55:18<4:04:20,  1.47it/s]
1|4368|Loss: 0.9188293814659119:  17%|█▋        | 4368/25880 [55:18<4:08:35,  1.44it/s]
1|4369|Loss: 1.043604850769043:  17%|█▋        | 4368/25880 [55:19<4:08:35,  1.44it/s] 
1|4369|Loss: 1.043604850769043:  17%|█▋        | 4369/25880 [55:19<4:02:47,  1.48it/s]
1|4370|Loss: 0.8958442211151123:  17%|█▋        | 4369/25880 [55:19<4:02:47,  1.48it/s]
1|4370|Loss: 0.8958442211151123:  17%|█▋        | 4370/25880 [55:20<4:13:51,  1.41it/s]
1|4371|Loss: 0.9354761838912964:  17%|█▋        | 4370/25880 [55:20<4:13:51,  1.41it/s]
1|4371|Loss: 0.9354761838912964:  17%|█▋        | 4371/25880 [55:20<4:19:28,  1.38it/s]
1|4372|Loss: 0.8221422433853149:  17%|█▋        | 4371/25880 [55:21<4:19:28,  1.38it/s]
1|4372|Loss: 0.8221422433853149:  17%|█▋        | 4372/25880 [55:21<4:41:22,  1.27it/s]
1|4373|Loss: 0.9025136828422546:  17%|█▋        | 4372/25880 [55:22<4:41:22,  1.27it/s]
1|4373|Loss: 0.9025136828422546:  17%|█▋        | 4373/25880 [55:22<4:32:48,  1.31it/s]
1|4374|Loss: 0.9087404608726501:  17%|█▋        | 4373/25880 [55:22<4:32:48,  1.31it/s]
1|4374|Loss: 0.9087404608726501:  17%|█▋        | 4374/25880 [55:23<4:16:26,  1.40it/s]
1|4375|Loss: 0.7620809674263:  17%|█▋        | 4374/25880 [55:23<4:16:26,  1.40it/s]   
1|4375|Loss: 0.7620809674263:  17%|█▋        | 4375/25880 [55:23<4:06:52,  1.45it/s]
1|4376|Loss: 0.7846207022666931:  17%|█▋        | 4375/25880 [55:24<4:06:52,  1.45it/s]
1|4376|Loss: 0.7846207022666931:  17%|█▋        | 4376/25880 [55:24<4:29:59,  1.33it/s]
1|4377|Loss: 0.8993083238601685:  17%|█▋        | 4376/25880 [55:25<4:29:59,  1.33it/s]
1|4377|Loss: 0.8993083238601685:  17%|█▋        | 4377/25880 [55:25<4:29:22,  1.33it/s]
1|4378|Loss: 0.8666107058525085:  17%|█▋        | 4377/25880 [55:25<4:29:22,  1.33it/s]
1|4378|Loss: 0.8666107058525085:  17%|█▋        | 4378/25880 [55:26<4:26:41,  1.34it/s]
1|4379|Loss: 0.9097862839698792:  17%|█▋        | 4378/25880 [55:26<4:26:41,  1.34it/s]
1|4379|Loss: 0.9097862839698792:  17%|█▋        | 4379/25880 [55:26<4:36:52,  1.29it/s]
1|4380|Loss: 0.8347959518432617:  17%|█▋        | 4379/25880 [55:27<4:36:52,  1.29it/s]
1|4380|Loss: 0.8347959518432617:  17%|█▋        | 4380/25880 [55:27<4:37:20,  1.29it/s]
1|4381|Loss: 0.7946672439575195:  17%|█▋        | 4380/25880 [55:28<4:37:20,  1.29it/s]
1|4381|Loss: 0.7946672439575195:  17%|█▋        | 4381/25880 [55:28<4:34:55,  1.30it/s]
1|4382|Loss: 0.9481809735298157:  17%|█▋        | 4381/25880 [55:28<4:34:55,  1.30it/s]
1|4382|Loss: 0.9481809735298157:  17%|█▋        | 4382/25880 [55:29<4:31:33,  1.32it/s]
1|4383|Loss: 0.8244616985321045:  17%|█▋        | 4382/25880 [55:29<4:31:33,  1.32it/s]
1|4383|Loss: 0.8244616985321045:  17%|█▋        | 4383/25880 [55:29<4:28:46,  1.33it/s]
1|4384|Loss: 0.7928938269615173:  17%|█▋        | 4383/25880 [55:30<4:28:46,  1.33it/s]
1|4384|Loss: 0.7928938269615173:  17%|█▋        | 4384/25880 [55:30<4:19:07,  1.38it/s]
1|4385|Loss: 0.8169125318527222:  17%|█▋        | 4384/25880 [55:30<4:19:07,  1.38it/s]
1|4385|Loss: 0.8169125318527222:  17%|█▋        | 4385/25880 [55:31<4:07:41,  1.45it/s]
1|4386|Loss: 0.8351154923439026:  17%|█▋        | 4385/25880 [55:31<4:07:41,  1.45it/s]
1|4386|Loss: 0.8351154923439026:  17%|█▋        | 4386/25880 [55:31<4:10:47,  1.43it/s]
1|4387|Loss: 0.7437207698822021:  17%|█▋        | 4386/25880 [55:32<4:10:47,  1.43it/s]
1|4387|Loss: 0.7437207698822021:  17%|█▋        | 4387/25880 [55:32<4:34:11,  1.31it/s]
1|4388|Loss: 0.8407633304595947:  17%|█▋        | 4387/25880 [55:33<4:34:11,  1.31it/s]
1|4388|Loss: 0.8407633304595947:  17%|█▋        | 4388/25880 [55:33<4:41:39,  1.27it/s]
1|4389|Loss: 1.0682975053787231:  17%|█▋        | 4388/25880 [55:34<4:41:39,  1.27it/s]
1|4389|Loss: 1.0682975053787231:  17%|█▋        | 4389/25880 [55:34<4:43:04,  1.27it/s]
1|4390|Loss: 0.8800672888755798:  17%|█▋        | 4389/25880 [55:34<4:43:04,  1.27it/s]
1|4390|Loss: 0.8800672888755798:  17%|█▋        | 4390/25880 [55:35<4:29:53,  1.33it/s]
1|4391|Loss: 0.9730120897293091:  17%|█▋        | 4390/25880 [55:35<4:29:53,  1.33it/s]
1|4391|Loss: 0.9730120897293091:  17%|█▋        | 4391/25880 [55:35<4:22:54,  1.36it/s]
1|4392|Loss: 0.993605375289917:  17%|█▋        | 4391/25880 [55:36<4:22:54,  1.36it/s] 
1|4392|Loss: 0.993605375289917:  17%|█▋        | 4392/25880 [55:36<4:22:56,  1.36it/s]
1|4393|Loss: 0.8849111795425415:  17%|█▋        | 4392/25880 [55:36<4:22:56,  1.36it/s]
1|4393|Loss: 0.8849111795425415:  17%|█▋        | 4393/25880 [55:37<4:20:32,  1.37it/s]
1|4394|Loss: 0.9245909452438354:  17%|█▋        | 4393/25880 [55:37<4:20:32,  1.37it/s]
1|4394|Loss: 0.9245909452438354:  17%|█▋        | 4394/25880 [55:37<4:12:09,  1.42it/s]
1|4395|Loss: 1.0168322324752808:  17%|█▋        | 4394/25880 [55:38<4:12:09,  1.42it/s]
1|4395|Loss: 1.0168322324752808:  17%|█▋        | 4395/25880 [55:38<4:05:47,  1.46it/s]
1|4396|Loss: 0.8742623925209045:  17%|█▋        | 4395/25880 [55:38<4:05:47,  1.46it/s]
1|4396|Loss: 0.8742623925209045:  17%|█▋        | 4396/25880 [55:39<4:06:00,  1.46it/s]
1|4397|Loss: 0.7036749720573425:  17%|█▋        | 4396/25880 [55:39<4:06:00,  1.46it/s]
1|4397|Loss: 0.7036749720573425:  17%|█▋        | 4397/25880 [55:39<4:00:21,  1.49it/s]
1|4398|Loss: 0.8698723912239075:  17%|█▋        | 4397/25880 [55:40<4:00:21,  1.49it/s]
1|4398|Loss: 0.8698723912239075:  17%|█▋        | 4398/25880 [55:40<3:56:08,  1.52it/s]
1|4399|Loss: 0.9418089389801025:  17%|█▋        | 4398/25880 [55:40<3:56:08,  1.52it/s]
1|4399|Loss: 0.9418089389801025:  17%|█▋        | 4399/25880 [55:41<4:02:31,  1.48it/s]
1|4400|Loss: 0.9630531668663025:  17%|█▋        | 4399/25880 [55:41<4:02:31,  1.48it/s]
1|4400|Loss: 0.9630531668663025:  17%|█▋        | 4400/25880 [55:41<4:01:01,  1.49it/s]
1|4401|Loss: 0.8474669456481934:  17%|█▋        | 4400/25880 [55:42<4:01:01,  1.49it/s]
1|4401|Loss: 0.8474669456481934:  17%|█▋        | 4401/25880 [55:42<3:41:04,  1.62it/s]
1|4402|Loss: 0.9679269790649414:  17%|█▋        | 4401/25880 [55:42<3:41:04,  1.62it/s]
1|4402|Loss: 0.9679269790649414:  17%|█▋        | 4402/25880 [55:42<3:35:23,  1.66it/s]
1|4403|Loss: 0.8798746466636658:  17%|█▋        | 4402/25880 [55:43<3:35:23,  1.66it/s]
1|4403|Loss: 0.8798746466636658:  17%|█▋        | 4403/25880 [55:43<3:30:56,  1.70it/s]
1|4404|Loss: 0.5377025008201599:  17%|█▋        | 4403/25880 [55:43<3:30:56,  1.70it/s]
1|4404|Loss: 0.5377025008201599:  17%|█▋        | 4404/25880 [55:44<3:23:21,  1.76it/s]
1|4405|Loss: 0.7722682356834412:  17%|█▋        | 4404/25880 [55:44<3:23:21,  1.76it/s]
1|4405|Loss: 0.7722682356834412:  17%|█▋        | 4405/25880 [55:44<3:35:50,  1.66it/s]
1|4406|Loss: 0.8946842551231384:  17%|█▋        | 4405/25880 [55:45<3:35:50,  1.66it/s]
1|4406|Loss: 0.8946842551231384:  17%|█▋        | 4406/25880 [55:45<3:47:14,  1.57it/s]
1|4407|Loss: 0.7396087050437927:  17%|█▋        | 4406/25880 [55:45<3:47:14,  1.57it/s]
1|4407|Loss: 0.7396087050437927:  17%|█▋        | 4407/25880 [55:46<3:56:30,  1.51it/s]
1|4408|Loss: 0.7154576778411865:  17%|█▋        | 4407/25880 [55:46<3:56:30,  1.51it/s]
1|4408|Loss: 0.7154576778411865:  17%|█▋        | 4408/25880 [55:46<4:04:24,  1.46it/s]
1|4409|Loss: 0.878674328327179:  17%|█▋        | 4408/25880 [55:47<4:04:24,  1.46it/s] 
1|4409|Loss: 0.878674328327179:  17%|█▋        | 4409/25880 [55:47<4:18:22,  1.39it/s]
1|4410|Loss: 0.7906176447868347:  17%|█▋        | 4409/25880 [55:48<4:18:22,  1.39it/s]
1|4410|Loss: 0.7906176447868347:  17%|█▋        | 4410/25880 [55:48<4:00:24,  1.49it/s]
1|4411|Loss: 0.8505664467811584:  17%|█▋        | 4410/25880 [55:48<4:00:24,  1.49it/s]
1|4411|Loss: 0.8505664467811584:  17%|█▋        | 4411/25880 [55:48<3:48:10,  1.57it/s]
1|4412|Loss: 0.7621632218360901:  17%|█▋        | 4411/25880 [55:49<3:48:10,  1.57it/s]
1|4412|Loss: 0.7621632218360901:  17%|█▋        | 4412/25880 [55:49<4:03:40,  1.47it/s]
1|4413|Loss: 0.8001248240470886:  17%|█▋        | 4412/25880 [55:49<4:03:40,  1.47it/s]
1|4413|Loss: 0.8001248240470886:  17%|█▋        | 4413/25880 [55:50<4:01:01,  1.48it/s]
1|4414|Loss: 0.9630857706069946:  17%|█▋        | 4413/25880 [55:50<4:01:01,  1.48it/s]
1|4414|Loss: 0.9630857706069946:  17%|█▋        | 4414/25880 [55:50<3:54:56,  1.52it/s]
1|4415|Loss: 0.7869535088539124:  17%|█▋        | 4414/25880 [55:51<3:54:56,  1.52it/s]
1|4415|Loss: 0.7869535088539124:  17%|█▋        | 4415/25880 [55:51<3:58:20,  1.50it/s]
1|4416|Loss: 0.7879956364631653:  17%|█▋        | 4415/25880 [55:51<3:58:20,  1.50it/s]
1|4416|Loss: 0.7879956364631653:  17%|█▋        | 4416/25880 [55:52<4:10:00,  1.43it/s]
1|4417|Loss: 0.9074510335922241:  17%|█▋        | 4416/25880 [55:52<4:10:00,  1.43it/s]
1|4417|Loss: 0.9074510335922241:  17%|█▋        | 4417/25880 [55:53<4:16:15,  1.40it/s]
1|4418|Loss: 0.8027320504188538:  17%|█▋        | 4417/25880 [55:53<4:16:15,  1.40it/s]
1|4418|Loss: 0.8027320504188538:  17%|█▋        | 4418/25880 [55:53<4:23:20,  1.36it/s]
1|4419|Loss: 0.872144341468811:  17%|█▋        | 4418/25880 [55:54<4:23:20,  1.36it/s] 
1|4419|Loss: 0.872144341468811:  17%|█▋        | 4419/25880 [55:54<4:37:22,  1.29it/s]
1|4420|Loss: 0.8147717714309692:  17%|█▋        | 4419/25880 [55:55<4:37:22,  1.29it/s]
1|4420|Loss: 0.8147717714309692:  17%|█▋        | 4420/25880 [55:55<4:37:17,  1.29it/s]
1|4421|Loss: 0.7862834334373474:  17%|█▋        | 4420/25880 [55:55<4:37:17,  1.29it/s]
1|4421|Loss: 0.7862834334373474:  17%|█▋        | 4421/25880 [55:56<4:30:07,  1.32it/s]
1|4422|Loss: 1.0367218255996704:  17%|█▋        | 4421/25880 [55:56<4:30:07,  1.32it/s]
1|4422|Loss: 1.0367218255996704:  17%|█▋        | 4422/25880 [55:57<4:35:02,  1.30it/s]
1|4423|Loss: 1.0120186805725098:  17%|█▋        | 4422/25880 [55:57<4:35:02,  1.30it/s]
1|4423|Loss: 1.0120186805725098:  17%|█▋        | 4423/25880 [55:57<4:33:20,  1.31it/s]
1|4424|Loss: 0.7609703540802002:  17%|█▋        | 4423/25880 [55:58<4:33:20,  1.31it/s]
1|4424|Loss: 0.7609703540802002:  17%|█▋        | 4424/25880 [55:58<4:11:49,  1.42it/s]
1|4425|Loss: 0.8484504818916321:  17%|█▋        | 4424/25880 [55:58<4:11:49,  1.42it/s]
1|4425|Loss: 0.8484504818916321:  17%|█▋        | 4425/25880 [55:58<4:00:20,  1.49it/s]
1|4426|Loss: 0.758625328540802:  17%|█▋        | 4425/25880 [55:59<4:00:20,  1.49it/s] 
1|4426|Loss: 0.758625328540802:  17%|█▋        | 4426/25880 [55:59<4:03:56,  1.47it/s]
1|4427|Loss: 0.9047625064849854:  17%|█▋        | 4426/25880 [56:00<4:03:56,  1.47it/s]
1|4427|Loss: 0.9047625064849854:  17%|█▋        | 4427/25880 [56:00<4:24:48,  1.35it/s]
1|4428|Loss: 0.8687461018562317:  17%|█▋        | 4427/25880 [56:00<4:24:48,  1.35it/s]
1|4428|Loss: 0.8687461018562317:  17%|█▋        | 4428/25880 [56:01<4:32:08,  1.31it/s]
1|4429|Loss: 0.634419322013855:  17%|█▋        | 4428/25880 [56:01<4:32:08,  1.31it/s] 
1|4429|Loss: 0.634419322013855:  17%|█▋        | 4429/25880 [56:02<4:34:58,  1.30it/s]
1|4430|Loss: 0.6596235036849976:  17%|█▋        | 4429/25880 [56:02<4:34:58,  1.30it/s]
1|4430|Loss: 0.6596235036849976:  17%|█▋        | 4430/25880 [56:03<4:47:45,  1.24it/s]
1|4431|Loss: 0.8786845207214355:  17%|█▋        | 4430/25880 [56:03<4:47:45,  1.24it/s]
1|4431|Loss: 0.8786845207214355:  17%|█▋        | 4431/25880 [56:03<4:19:31,  1.38it/s]
1|4432|Loss: 0.9029459953308105:  17%|█▋        | 4431/25880 [56:03<4:19:31,  1.38it/s]
1|4432|Loss: 0.9029459953308105:  17%|█▋        | 4432/25880 [56:04<4:13:17,  1.41it/s]
1|4433|Loss: 0.8471047878265381:  17%|█▋        | 4432/25880 [56:04<4:13:17,  1.41it/s]
1|4433|Loss: 0.8471047878265381:  17%|█▋        | 4433/25880 [56:04<4:15:43,  1.40it/s]
1|4434|Loss: 0.9383427500724792:  17%|█▋        | 4433/25880 [56:05<4:15:43,  1.40it/s]
1|4434|Loss: 0.9383427500724792:  17%|█▋        | 4434/25880 [56:05<4:22:25,  1.36it/s]
1|4435|Loss: 0.9287415742874146:  17%|█▋        | 4434/25880 [56:06<4:22:25,  1.36it/s]
1|4435|Loss: 0.9287415742874146:  17%|█▋        | 4435/25880 [56:06<4:15:59,  1.40it/s]
1|4436|Loss: 0.8960797786712646:  17%|█▋        | 4435/25880 [56:06<4:15:59,  1.40it/s]
1|4436|Loss: 0.8960797786712646:  17%|█▋        | 4436/25880 [56:07<4:22:25,  1.36it/s]
1|4437|Loss: 0.7759991884231567:  17%|█▋        | 4436/25880 [56:07<4:22:25,  1.36it/s]
1|4437|Loss: 0.7759991884231567:  17%|█▋        | 4437/25880 [56:07<3:59:39,  1.49it/s]
1|4438|Loss: 0.8454412221908569:  17%|█▋        | 4437/25880 [56:08<3:59:39,  1.49it/s]
1|4438|Loss: 0.8454412221908569:  17%|█▋        | 4438/25880 [56:08<3:57:05,  1.51it/s]
1|4439|Loss: 0.7966746091842651:  17%|█▋        | 4438/25880 [56:08<3:57:05,  1.51it/s]
1|4439|Loss: 0.7966746091842651:  17%|█▋        | 4439/25880 [56:09<4:00:33,  1.49it/s]
1|4440|Loss: 0.7482790350914001:  17%|█▋        | 4439/25880 [56:09<4:00:33,  1.49it/s]
1|4440|Loss: 0.7482790350914001:  17%|█▋        | 4440/25880 [56:09<4:05:12,  1.46it/s]
1|4441|Loss: 0.8681787848472595:  17%|█▋        | 4440/25880 [56:10<4:05:12,  1.46it/s]
1|4441|Loss: 0.8681787848472595:  17%|█▋        | 4441/25880 [56:10<4:17:44,  1.39it/s]
1|4442|Loss: 0.9235615730285645:  17%|█▋        | 4441/25880 [56:10<4:17:44,  1.39it/s]
1|4442|Loss: 0.9235615730285645:  17%|█▋        | 4442/25880 [56:11<4:17:17,  1.39it/s]
1|4443|Loss: 0.8588639497756958:  17%|█▋        | 4442/25880 [56:11<4:17:17,  1.39it/s]
1|4443|Loss: 0.8588639497756958:  17%|█▋        | 4443/25880 [56:11<4:09:21,  1.43it/s]
1|4444|Loss: 0.9467863440513611:  17%|█▋        | 4443/25880 [56:12<4:09:21,  1.43it/s]
1|4444|Loss: 0.9467863440513611:  17%|█▋        | 4444/25880 [56:12<4:02:42,  1.47it/s]
1|4445|Loss: 0.9267661571502686:  17%|█▋        | 4444/25880 [56:12<4:02:42,  1.47it/s]
1|4445|Loss: 0.9267661571502686:  17%|█▋        | 4445/25880 [56:13<3:56:23,  1.51it/s]
1|4446|Loss: 0.8616359233856201:  17%|█▋        | 4445/25880 [56:13<3:56:23,  1.51it/s]
1|4446|Loss: 0.8616359233856201:  17%|█▋        | 4446/25880 [56:13<3:44:45,  1.59it/s]
1|4447|Loss: 0.8371974229812622:  17%|█▋        | 4446/25880 [56:14<3:44:45,  1.59it/s]
1|4447|Loss: 0.8371974229812622:  17%|█▋        | 4447/25880 [56:14<3:48:34,  1.56it/s]
1|4448|Loss: 0.9253495931625366:  17%|█▋        | 4447/25880 [56:14<3:48:34,  1.56it/s]
1|4448|Loss: 0.9253495931625366:  17%|█▋        | 4448/25880 [56:15<4:04:25,  1.46it/s]
1|4449|Loss: 0.8160049915313721:  17%|█▋        | 4448/25880 [56:15<4:04:25,  1.46it/s]
1|4449|Loss: 0.8160049915313721:  17%|█▋        | 4449/25880 [56:15<4:09:20,  1.43it/s]
1|4450|Loss: 0.9141547083854675:  17%|█▋        | 4449/25880 [56:16<4:09:20,  1.43it/s]
1|4450|Loss: 0.9141547083854675:  17%|█▋        | 4450/25880 [56:16<4:11:58,  1.42it/s]
1|4451|Loss: 0.8223742842674255:  17%|█▋        | 4450/25880 [56:17<4:11:58,  1.42it/s]
1|4451|Loss: 0.8223742842674255:  17%|█▋        | 4451/25880 [56:17<4:13:49,  1.41it/s]
1|4452|Loss: 0.910982608795166:  17%|█▋        | 4451/25880 [56:17<4:13:49,  1.41it/s] 
1|4452|Loss: 0.910982608795166:  17%|█▋        | 4452/25880 [56:18<4:16:54,  1.39it/s]
1|4453|Loss: 0.9461879134178162:  17%|█▋        | 4452/25880 [56:18<4:16:54,  1.39it/s]
1|4453|Loss: 0.9461879134178162:  17%|█▋        | 4453/25880 [56:18<4:18:56,  1.38it/s]
1|4454|Loss: 0.8991332650184631:  17%|█▋        | 4453/25880 [56:19<4:18:56,  1.38it/s]
1|4454|Loss: 0.8991332650184631:  17%|█▋        | 4454/25880 [56:19<4:17:49,  1.39it/s]
1|4455|Loss: 0.8310673832893372:  17%|█▋        | 4454/25880 [56:19<4:17:49,  1.39it/s]
1|4455|Loss: 0.8310673832893372:  17%|█▋        | 4455/25880 [56:20<4:02:58,  1.47it/s]
1|4456|Loss: 0.7703912258148193:  17%|█▋        | 4455/25880 [56:20<4:02:58,  1.47it/s]
1|4456|Loss: 0.7703912258148193:  17%|█▋        | 4456/25880 [56:20<3:57:02,  1.51it/s]
1|4457|Loss: 0.787835955619812:  17%|█▋        | 4456/25880 [56:21<3:57:02,  1.51it/s] 
1|4457|Loss: 0.787835955619812:  17%|█▋        | 4457/25880 [56:21<4:02:42,  1.47it/s]
1|4458|Loss: 0.8831416964530945:  17%|█▋        | 4457/25880 [56:21<4:02:42,  1.47it/s]
1|4458|Loss: 0.8831416964530945:  17%|█▋        | 4458/25880 [56:22<4:07:49,  1.44it/s]
1|4459|Loss: 0.8401870131492615:  17%|█▋        | 4458/25880 [56:22<4:07:49,  1.44it/s]
1|4459|Loss: 0.8401870131492615:  17%|█▋        | 4459/25880 [56:22<4:09:06,  1.43it/s]
1|4460|Loss: 0.7213355302810669:  17%|█▋        | 4459/25880 [56:23<4:09:06,  1.43it/s]
1|4460|Loss: 0.7213355302810669:  17%|█▋        | 4460/25880 [56:23<4:16:00,  1.39it/s]
1|4461|Loss: 0.7714715600013733:  17%|█▋        | 4460/25880 [56:24<4:16:00,  1.39it/s]
1|4461|Loss: 0.7714715600013733:  17%|█▋        | 4461/25880 [56:24<4:28:07,  1.33it/s]
1|4462|Loss: 0.7954971194267273:  17%|█▋        | 4461/25880 [56:24<4:28:07,  1.33it/s]
1|4462|Loss: 0.7954971194267273:  17%|█▋        | 4462/25880 [56:25<4:44:09,  1.26it/s]
1|4463|Loss: 0.8952640295028687:  17%|█▋        | 4462/25880 [56:25<4:44:09,  1.26it/s]
1|4463|Loss: 0.8952640295028687:  17%|█▋        | 4463/25880 [56:26<4:22:13,  1.36it/s]
1|4464|Loss: 0.7478916645050049:  17%|█▋        | 4463/25880 [56:26<4:22:13,  1.36it/s]
1|4464|Loss: 0.7478916645050049:  17%|█▋        | 4464/25880 [56:26<4:17:33,  1.39it/s]
1|4465|Loss: 0.8483851552009583:  17%|█▋        | 4464/25880 [56:27<4:17:33,  1.39it/s]
1|4465|Loss: 0.8483851552009583:  17%|█▋        | 4465/25880 [56:27<4:19:40,  1.37it/s]
1|4466|Loss: 0.8754035830497742:  17%|█▋        | 4465/25880 [56:27<4:19:40,  1.37it/s]
1|4466|Loss: 0.8754035830497742:  17%|█▋        | 4466/25880 [56:28<4:28:08,  1.33it/s]
1|4467|Loss: 0.9293333292007446:  17%|█▋        | 4466/25880 [56:28<4:28:08,  1.33it/s]
1|4467|Loss: 0.9293333292007446:  17%|█▋        | 4467/25880 [56:28<4:20:01,  1.37it/s]
1|4468|Loss: 0.9420081377029419:  17%|█▋        | 4467/25880 [56:29<4:20:01,  1.37it/s]
1|4468|Loss: 0.9420081377029419:  17%|█▋        | 4468/25880 [56:29<4:10:17,  1.43it/s]
1|4469|Loss: 0.856412947177887:  17%|█▋        | 4468/25880 [56:29<4:10:17,  1.43it/s] 
1|4469|Loss: 0.856412947177887:  17%|█▋        | 4469/25880 [56:30<4:15:56,  1.39it/s]
1|4470|Loss: 0.8687155842781067:  17%|█▋        | 4469/25880 [56:30<4:15:56,  1.39it/s]
1|4470|Loss: 0.8687155842781067:  17%|█▋        | 4470/25880 [56:31<4:29:11,  1.33it/s]
1|4471|Loss: 1.0273245573043823:  17%|█▋        | 4470/25880 [56:31<4:29:11,  1.33it/s]
1|4471|Loss: 1.0273245573043823:  17%|█▋        | 4471/25880 [56:32<4:42:44,  1.26it/s]
1|4472|Loss: 0.8360602259635925:  17%|█▋        | 4471/25880 [56:32<4:42:44,  1.26it/s]
1|4472|Loss: 0.8360602259635925:  17%|█▋        | 4472/25880 [56:32<4:37:11,  1.29it/s]
1|4473|Loss: 0.8961207866668701:  17%|█▋        | 4472/25880 [56:33<4:37:11,  1.29it/s]
1|4473|Loss: 0.8961207866668701:  17%|█▋        | 4473/25880 [56:33<4:53:28,  1.22it/s]
1|4474|Loss: 0.8421556949615479:  17%|█▋        | 4473/25880 [56:34<4:53:28,  1.22it/s]
1|4474|Loss: 0.8421556949615479:  17%|█▋        | 4474/25880 [56:34<4:42:48,  1.26it/s]
1|4475|Loss: 0.7801275849342346:  17%|█▋        | 4474/25880 [56:34<4:42:48,  1.26it/s]
1|4475|Loss: 0.7801275849342346:  17%|█▋        | 4475/25880 [56:35<4:32:04,  1.31it/s]
1|4476|Loss: 0.8669882416725159:  17%|█▋        | 4475/25880 [56:35<4:32:04,  1.31it/s]
1|4476|Loss: 0.8669882416725159:  17%|█▋        | 4476/25880 [56:35<4:28:28,  1.33it/s]
1|4477|Loss: 0.6954346299171448:  17%|█▋        | 4476/25880 [56:36<4:28:28,  1.33it/s]
1|4477|Loss: 0.6954346299171448:  17%|█▋        | 4477/25880 [56:36<4:24:32,  1.35it/s]
1|4478|Loss: 0.8440805077552795:  17%|█▋        | 4477/25880 [56:36<4:24:32,  1.35it/s]
1|4478|Loss: 0.8440805077552795:  17%|█▋        | 4478/25880 [56:37<4:12:54,  1.41it/s]
1|4479|Loss: 0.9279516935348511:  17%|█▋        | 4478/25880 [56:37<4:12:54,  1.41it/s]
1|4479|Loss: 0.9279516935348511:  17%|█▋        | 4479/25880 [56:37<4:05:14,  1.45it/s]
1|4480|Loss: 0.8547502160072327:  17%|█▋        | 4479/25880 [56:38<4:05:14,  1.45it/s]
1|4480|Loss: 0.8547502160072327:  17%|█▋        | 4480/25880 [56:38<3:58:14,  1.50it/s]
1|4481|Loss: 0.8969786763191223:  17%|█▋        | 4480/25880 [56:38<3:58:14,  1.50it/s]
1|4481|Loss: 0.8969786763191223:  17%|█▋        | 4481/25880 [56:39<4:00:35,  1.48it/s]
1|4482|Loss: 0.8806146383285522:  17%|█▋        | 4481/25880 [56:39<4:00:35,  1.48it/s]
1|4482|Loss: 0.8806146383285522:  17%|█▋        | 4482/25880 [56:39<4:07:14,  1.44it/s]
1|4483|Loss: 0.9933103919029236:  17%|█▋        | 4482/25880 [56:40<4:07:14,  1.44it/s]
1|4483|Loss: 0.9933103919029236:  17%|█▋        | 4483/25880 [56:40<4:05:09,  1.45it/s]
1|4484|Loss: 0.8990687727928162:  17%|█▋        | 4483/25880 [56:40<4:05:09,  1.45it/s]
1|4484|Loss: 0.8990687727928162:  17%|█▋        | 4484/25880 [56:41<4:07:30,  1.44it/s]
1|4485|Loss: 0.9164524674415588:  17%|█▋        | 4484/25880 [56:41<4:07:30,  1.44it/s]
1|4485|Loss: 0.9164524674415588:  17%|█▋        | 4485/25880 [56:42<4:12:01,  1.41it/s]
1|4486|Loss: 0.8530222773551941:  17%|█▋        | 4485/25880 [56:42<4:12:01,  1.41it/s]
1|4486|Loss: 0.8530222773551941:  17%|█▋        | 4486/25880 [56:42<4:02:09,  1.47it/s]
1|4487|Loss: 0.8970427513122559:  17%|█▋        | 4486/25880 [56:42<4:02:09,  1.47it/s]
1|4487|Loss: 0.8970427513122559:  17%|█▋        | 4487/25880 [56:43<4:05:05,  1.45it/s]
1|4488|Loss: 0.9618905186653137:  17%|█▋        | 4487/25880 [56:43<4:05:05,  1.45it/s]
1|4488|Loss: 0.9618905186653137:  17%|█▋        | 4488/25880 [56:43<3:51:18,  1.54it/s]
1|4489|Loss: 0.8686315417289734:  17%|█▋        | 4488/25880 [56:44<3:51:18,  1.54it/s]
1|4489|Loss: 0.8686315417289734:  17%|█▋        | 4489/25880 [56:44<3:36:21,  1.65it/s]
1|4490|Loss: 0.8900410532951355:  17%|█▋        | 4489/25880 [56:44<3:36:21,  1.65it/s]
1|4490|Loss: 0.8900410532951355:  17%|█▋        | 4490/25880 [56:45<3:36:58,  1.64it/s]
1|4491|Loss: 0.8763887882232666:  17%|█▋        | 4490/25880 [56:45<3:36:58,  1.64it/s]
1|4491|Loss: 0.8763887882232666:  17%|█▋        | 4491/25880 [56:45<3:29:30,  1.70it/s]
1|4492|Loss: 0.8905892372131348:  17%|█▋        | 4491/25880 [56:45<3:29:30,  1.70it/s]
1|4492|Loss: 0.8905892372131348:  17%|█▋        | 4492/25880 [56:46<3:28:24,  1.71it/s]
1|4493|Loss: 0.7057371735572815:  17%|█▋        | 4492/25880 [56:46<3:28:24,  1.71it/s]
1|4493|Loss: 0.7057371735572815:  17%|█▋        | 4493/25880 [56:46<3:40:39,  1.62it/s]
1|4494|Loss: 0.9517573714256287:  17%|█▋        | 4493/25880 [56:47<3:40:39,  1.62it/s]
1|4494|Loss: 0.9517573714256287:  17%|█▋        | 4494/25880 [56:47<4:00:32,  1.48it/s]
1|4495|Loss: 0.7615296244621277:  17%|█▋        | 4494/25880 [56:48<4:00:32,  1.48it/s]
1|4495|Loss: 0.7615296244621277:  17%|█▋        | 4495/25880 [56:48<4:09:37,  1.43it/s]
1|4496|Loss: 0.8435491919517517:  17%|█▋        | 4495/25880 [56:48<4:09:37,  1.43it/s]
1|4496|Loss: 0.8435491919517517:  17%|█▋        | 4496/25880 [56:49<4:10:51,  1.42it/s]
1|4497|Loss: 0.8677863478660583:  17%|█▋        | 4496/25880 [56:49<4:10:51,  1.42it/s]
1|4497|Loss: 0.8677863478660583:  17%|█▋        | 4497/25880 [56:50<4:32:51,  1.31it/s]
1|4498|Loss: 0.8199504613876343:  17%|█▋        | 4497/25880 [56:50<4:32:51,  1.31it/s]
1|4498|Loss: 0.8199504613876343:  17%|█▋        | 4498/25880 [56:50<4:44:38,  1.25it/s]
1|4499|Loss: 0.854848325252533:  17%|█▋        | 4498/25880 [56:51<4:44:38,  1.25it/s] 
1|4499|Loss: 0.854848325252533:  17%|█▋        | 4499/25880 [56:51<4:53:32,  1.21it/s]
1|4500|Loss: 0.8969361782073975:  17%|█▋        | 4499/25880 [56:52<4:53:32,  1.21it/s]
1|4500|Loss: 0.8969361782073975:  17%|█▋        | 4500/25880 [56:52<4:39:33,  1.27it/s]
1|4501|Loss: 0.8754705190658569:  17%|█▋        | 4500/25880 [56:52<4:39:33,  1.27it/s]
1|4501|Loss: 0.8754705190658569:  17%|█▋        | 4501/25880 [56:52<4:12:53,  1.41it/s]
1|4502|Loss: 0.7221152186393738:  17%|█▋        | 4501/25880 [56:53<4:12:53,  1.41it/s]
1|4502|Loss: 0.7221152186393738:  17%|█▋        | 4502/25880 [56:53<4:10:08,  1.42it/s]
1|4503|Loss: 0.9415379762649536:  17%|█▋        | 4502/25880 [56:54<4:10:08,  1.42it/s]
1|4503|Loss: 0.9415379762649536:  17%|█▋        | 4503/25880 [56:54<4:05:29,  1.45it/s]
1|4504|Loss: 0.9585407972335815:  17%|█▋        | 4503/25880 [56:54<4:05:29,  1.45it/s]
1|4504|Loss: 0.9585407972335815:  17%|█▋        | 4504/25880 [56:54<3:43:47,  1.59it/s]
1|4505|Loss: 0.8503991365432739:  17%|█▋        | 4504/25880 [56:55<3:43:47,  1.59it/s]
1|4505|Loss: 0.8503991365432739:  17%|█▋        | 4505/25880 [56:55<3:35:34,  1.65it/s]
1|4506|Loss: 0.8047775626182556:  17%|█▋        | 4505/25880 [56:55<3:35:34,  1.65it/s]
1|4506|Loss: 0.8047775626182556:  17%|█▋        | 4506/25880 [56:56<3:52:17,  1.53it/s]
1|4507|Loss: 0.9247685670852661:  17%|█▋        | 4506/25880 [56:56<3:52:17,  1.53it/s]
1|4507|Loss: 0.9247685670852661:  17%|█▋        | 4507/25880 [56:56<3:31:15,  1.69it/s]
1|4508|Loss: 0.8830095529556274:  17%|█▋        | 4507/25880 [56:56<3:31:15,  1.69it/s]
1|4508|Loss: 0.8830095529556274:  17%|█▋        | 4508/25880 [56:57<3:31:21,  1.69it/s]
1|4509|Loss: 0.7248607277870178:  17%|█▋        | 4508/25880 [56:57<3:31:21,  1.69it/s]
1|4509|Loss: 0.7248607277870178:  17%|█▋        | 4509/25880 [56:58<4:07:34,  1.44it/s]
1|4510|Loss: 0.9693253040313721:  17%|█▋        | 4509/25880 [56:59<4:07:34,  1.44it/s]
1|4510|Loss: 0.9693253040313721:  17%|█▋        | 4510/25880 [56:59<4:58:22,  1.19it/s]
1|4511|Loss: 0.849429726600647:  17%|█▋        | 4510/25880 [56:59<4:58:22,  1.19it/s] 
1|4511|Loss: 0.849429726600647:  17%|█▋        | 4511/25880 [57:00<4:57:19,  1.20it/s]
1|4512|Loss: 0.8888719081878662:  17%|█▋        | 4511/25880 [57:00<4:57:19,  1.20it/s]
1|4512|Loss: 0.8888719081878662:  17%|█▋        | 4512/25880 [57:00<4:59:54,  1.19it/s]
1|4513|Loss: 0.7500514388084412:  17%|█▋        | 4512/25880 [57:01<4:59:54,  1.19it/s]
1|4513|Loss: 0.7500514388084412:  17%|█▋        | 4513/25880 [57:01<4:52:14,  1.22it/s]
1|4514|Loss: 0.9163556694984436:  17%|█▋        | 4513/25880 [57:02<4:52:14,  1.22it/s]
1|4514|Loss: 0.9163556694984436:  17%|█▋        | 4514/25880 [57:02<4:35:10,  1.29it/s]
1|4515|Loss: 0.8918565511703491:  17%|█▋        | 4514/25880 [57:02<4:35:10,  1.29it/s]
1|4515|Loss: 0.8918565511703491:  17%|█▋        | 4515/25880 [57:03<4:40:33,  1.27it/s]
1|4516|Loss: 0.7687220573425293:  17%|█▋        | 4515/25880 [57:03<4:40:33,  1.27it/s]
1|4516|Loss: 0.7687220573425293:  17%|█▋        | 4516/25880 [57:03<4:35:36,  1.29it/s]
1|4517|Loss: 0.7967516779899597:  17%|█▋        | 4516/25880 [57:04<4:35:36,  1.29it/s]
1|4517|Loss: 0.7967516779899597:  17%|█▋        | 4517/25880 [57:04<4:14:51,  1.40it/s]
1|4518|Loss: 0.7976202964782715:  17%|█▋        | 4517/25880 [57:04<4:14:51,  1.40it/s]
1|4518|Loss: 0.7976202964782715:  17%|█▋        | 4518/25880 [57:05<4:05:08,  1.45it/s]
1|4519|Loss: 0.8408433198928833:  17%|█▋        | 4518/25880 [57:05<4:05:08,  1.45it/s]
1|4519|Loss: 0.8408433198928833:  17%|█▋        | 4519/25880 [57:05<3:49:14,  1.55it/s]
1|4520|Loss: 0.8966495394706726:  17%|█▋        | 4519/25880 [57:06<3:49:14,  1.55it/s]
1|4520|Loss: 0.8966495394706726:  17%|█▋        | 4520/25880 [57:06<3:51:19,  1.54it/s]
1|4521|Loss: 0.8506963849067688:  17%|█▋        | 4520/25880 [57:06<3:51:19,  1.54it/s]
1|4521|Loss: 0.8506963849067688:  17%|█▋        | 4521/25880 [57:07<4:00:24,  1.48it/s]
1|4522|Loss: 0.8771460652351379:  17%|█▋        | 4521/25880 [57:07<4:00:24,  1.48it/s]
1|4522|Loss: 0.8771460652351379:  17%|█▋        | 4522/25880 [57:07<4:13:42,  1.40it/s]
1|4523|Loss: 0.8300558924674988:  17%|█▋        | 4522/25880 [57:08<4:13:42,  1.40it/s]
1|4523|Loss: 0.8300558924674988:  17%|█▋        | 4523/25880 [57:08<4:30:09,  1.32it/s]
1|4524|Loss: 0.8570659756660461:  17%|█▋        | 4523/25880 [57:09<4:30:09,  1.32it/s]
1|4524|Loss: 0.8570659756660461:  17%|█▋        | 4524/25880 [57:09<4:31:48,  1.31it/s]
1|4525|Loss: 0.9383130669593811:  17%|█▋        | 4524/25880 [57:10<4:31:48,  1.31it/s]
1|4525|Loss: 0.9383130669593811:  17%|█▋        | 4525/25880 [57:10<4:39:37,  1.27it/s]
1|4526|Loss: 0.798525869846344:  17%|█▋        | 4525/25880 [57:10<4:39:37,  1.27it/s] 
1|4526|Loss: 0.798525869846344:  17%|█▋        | 4526/25880 [57:11<4:34:14,  1.30it/s]
1|4527|Loss: 0.788702666759491:  17%|█▋        | 4526/25880 [57:11<4:34:14,  1.30it/s]
1|4527|Loss: 0.788702666759491:  17%|█▋        | 4527/25880 [57:11<4:37:27,  1.28it/s]
1|4528|Loss: 0.8037779927253723:  17%|█▋        | 4527/25880 [57:12<4:37:27,  1.28it/s]
1|4528|Loss: 0.8037779927253723:  17%|█▋        | 4528/25880 [57:12<4:31:28,  1.31it/s]
1|4529|Loss: 0.7790597677230835:  17%|█▋        | 4528/25880 [57:13<4:31:28,  1.31it/s]
1|4529|Loss: 0.7790597677230835:  18%|█▊        | 4529/25880 [57:13<4:24:49,  1.34it/s]
1|4530|Loss: 0.8238956332206726:  18%|█▊        | 4529/25880 [57:13<4:24:49,  1.34it/s]
1|4530|Loss: 0.8238956332206726:  18%|█▊        | 4530/25880 [57:13<4:09:42,  1.42it/s]
1|4531|Loss: 0.96075439453125:  18%|█▊        | 4530/25880 [57:14<4:09:42,  1.42it/s]  
1|4531|Loss: 0.96075439453125:  18%|█▊        | 4531/25880 [57:14<4:23:03,  1.35it/s]
1|4532|Loss: 1.0031198263168335:  18%|█▊        | 4531/25880 [57:15<4:23:03,  1.35it/s]
1|4532|Loss: 1.0031198263168335:  18%|█▊        | 4532/25880 [57:15<4:23:47,  1.35it/s]
1|4533|Loss: 0.9063421487808228:  18%|█▊        | 4532/25880 [57:15<4:23:47,  1.35it/s]
1|4533|Loss: 0.9063421487808228:  18%|█▊        | 4533/25880 [57:16<4:21:43,  1.36it/s]
1|4534|Loss: 0.7620049715042114:  18%|█▊        | 4533/25880 [57:16<4:21:43,  1.36it/s]
1|4534|Loss: 0.7620049715042114:  18%|█▊        | 4534/25880 [57:17<4:32:43,  1.30it/s]
1|4535|Loss: 0.7725899815559387:  18%|█▊        | 4534/25880 [57:17<4:32:43,  1.30it/s]
1|4535|Loss: 0.7725899815559387:  18%|█▊        | 4535/25880 [57:17<4:22:12,  1.36it/s]
1|4536|Loss: 0.7526772022247314:  18%|█▊        | 4535/25880 [57:18<4:22:12,  1.36it/s]
1|4536|Loss: 0.7526772022247314:  18%|█▊        | 4536/25880 [57:18<4:11:30,  1.41it/s]
1|4537|Loss: 0.7588951587677002:  18%|█▊        | 4536/25880 [57:18<4:11:30,  1.41it/s]
1|4537|Loss: 0.7588951587677002:  18%|█▊        | 4537/25880 [57:19<4:09:49,  1.42it/s]
1|4538|Loss: 0.9063774347305298:  18%|█▊        | 4537/25880 [57:19<4:09:49,  1.42it/s]
1|4538|Loss: 0.9063774347305298:  18%|█▊        | 4538/25880 [57:19<4:12:11,  1.41it/s]
1|4539|Loss: 0.7236892580986023:  18%|█▊        | 4538/25880 [57:20<4:12:11,  1.41it/s]
1|4539|Loss: 0.7236892580986023:  18%|█▊        | 4539/25880 [57:20<4:04:32,  1.45it/s]
1|4540|Loss: 0.8500151634216309:  18%|█▊        | 4539/25880 [57:20<4:04:32,  1.45it/s]
1|4540|Loss: 0.8500151634216309:  18%|█▊        | 4540/25880 [57:21<4:14:58,  1.39it/s]
1|4541|Loss: 0.8196013569831848:  18%|█▊        | 4540/25880 [57:21<4:14:58,  1.39it/s]
1|4541|Loss: 0.8196013569831848:  18%|█▊        | 4541/25880 [57:21<4:08:44,  1.43it/s]
1|4542|Loss: 0.844041109085083:  18%|█▊        | 4541/25880 [57:22<4:08:44,  1.43it/s] 
1|4542|Loss: 0.844041109085083:  18%|█▊        | 4542/25880 [57:22<4:09:48,  1.42it/s]
1|4543|Loss: 0.8655693531036377:  18%|█▊        | 4542/25880 [57:22<4:09:48,  1.42it/s]
1|4543|Loss: 0.8655693531036377:  18%|█▊        | 4543/25880 [57:23<4:02:57,  1.46it/s]
1|4544|Loss: 0.942393958568573:  18%|█▊        | 4543/25880 [57:23<4:02:57,  1.46it/s] 
1|4544|Loss: 0.942393958568573:  18%|█▊        | 4544/25880 [57:23<4:06:38,  1.44it/s]
1|4545|Loss: 0.8976274728775024:  18%|█▊        | 4544/25880 [57:24<4:06:38,  1.44it/s]
1|4545|Loss: 0.8976274728775024:  18%|█▊        | 4545/25880 [57:24<4:19:28,  1.37it/s]
1|4546|Loss: 0.9634115099906921:  18%|█▊        | 4545/25880 [57:25<4:19:28,  1.37it/s]
1|4546|Loss: 0.9634115099906921:  18%|█▊        | 4546/25880 [57:25<4:33:13,  1.30it/s]
1|4547|Loss: 0.8791993856430054:  18%|█▊        | 4546/25880 [57:26<4:33:13,  1.30it/s]
1|4547|Loss: 0.8791993856430054:  18%|█▊        | 4547/25880 [57:26<4:37:03,  1.28it/s]
1|4548|Loss: 0.9099761247634888:  18%|█▊        | 4547/25880 [57:26<4:37:03,  1.28it/s]
1|4548|Loss: 0.9099761247634888:  18%|█▊        | 4548/25880 [57:27<4:14:59,  1.39it/s]
1|4549|Loss: 0.7902117371559143:  18%|█▊        | 4548/25880 [57:27<4:14:59,  1.39it/s]
1|4549|Loss: 0.7902117371559143:  18%|█▊        | 4549/25880 [57:27<4:21:43,  1.36it/s]
1|4550|Loss: 0.8886602520942688:  18%|█▊        | 4549/25880 [57:28<4:21:43,  1.36it/s]
1|4550|Loss: 0.8886602520942688:  18%|█▊        | 4550/25880 [57:28<4:32:37,  1.30it/s]
1|4551|Loss: 0.9287868738174438:  18%|█▊        | 4550/25880 [57:29<4:32:37,  1.30it/s]
1|4551|Loss: 0.9287868738174438:  18%|█▊        | 4551/25880 [57:29<4:23:11,  1.35it/s]
1|4552|Loss: 0.8165110349655151:  18%|█▊        | 4551/25880 [57:29<4:23:11,  1.35it/s]
1|4552|Loss: 0.8165110349655151:  18%|█▊        | 4552/25880 [57:30<4:20:06,  1.37it/s]
1|4553|Loss: 0.7977192401885986:  18%|█▊        | 4552/25880 [57:30<4:20:06,  1.37it/s]
1|4553|Loss: 0.7977192401885986:  18%|█▊        | 4553/25880 [57:30<4:29:13,  1.32it/s]
1|4554|Loss: 0.8185428380966187:  18%|█▊        | 4553/25880 [57:31<4:29:13,  1.32it/s]
1|4554|Loss: 0.8185428380966187:  18%|█▊        | 4554/25880 [57:31<4:29:13,  1.32it/s]
1|4555|Loss: 1.0028318166732788:  18%|█▊        | 4554/25880 [57:32<4:29:13,  1.32it/s]
1|4555|Loss: 1.0028318166732788:  18%|█▊        | 4555/25880 [57:32<4:38:37,  1.28it/s]
1|4556|Loss: 0.9579415321350098:  18%|█▊        | 4555/25880 [57:32<4:38:37,  1.28it/s]
1|4556|Loss: 0.9579415321350098:  18%|█▊        | 4556/25880 [57:33<4:18:07,  1.38it/s]
1|4557|Loss: 0.8259734511375427:  18%|█▊        | 4556/25880 [57:33<4:18:07,  1.38it/s]
1|4557|Loss: 0.8259734511375427:  18%|█▊        | 4557/25880 [57:33<4:26:53,  1.33it/s]
1|4558|Loss: 0.9142380356788635:  18%|█▊        | 4557/25880 [57:34<4:26:53,  1.33it/s]
1|4558|Loss: 0.9142380356788635:  18%|█▊        | 4558/25880 [57:34<4:44:02,  1.25it/s]
1|4559|Loss: 0.9341709017753601:  18%|█▊        | 4558/25880 [57:35<4:44:02,  1.25it/s]
1|4559|Loss: 0.9341709017753601:  18%|█▊        | 4559/25880 [57:35<4:39:28,  1.27it/s]
1|4560|Loss: 0.8077763915061951:  18%|█▊        | 4559/25880 [57:35<4:39:28,  1.27it/s]
1|4560|Loss: 0.8077763915061951:  18%|█▊        | 4560/25880 [57:36<4:30:44,  1.31it/s]
1|4561|Loss: 0.9370335936546326:  18%|█▊        | 4560/25880 [57:36<4:30:44,  1.31it/s]
1|4561|Loss: 0.9370335936546326:  18%|█▊        | 4561/25880 [57:36<4:26:59,  1.33it/s]
1|4562|Loss: 0.8448044061660767:  18%|█▊        | 4561/25880 [57:37<4:26:59,  1.33it/s]
1|4562|Loss: 0.8448044061660767:  18%|█▊        | 4562/25880 [57:37<4:35:23,  1.29it/s]
1|4563|Loss: 0.9564175605773926:  18%|█▊        | 4562/25880 [57:38<4:35:23,  1.29it/s]
1|4563|Loss: 0.9564175605773926:  18%|█▊        | 4563/25880 [57:38<4:45:05,  1.25it/s]
1|4564|Loss: 0.8733531832695007:  18%|█▊        | 4563/25880 [57:39<4:45:05,  1.25it/s]
1|4564|Loss: 0.8733531832695007:  18%|█▊        | 4564/25880 [57:39<4:49:15,  1.23it/s]
1|4565|Loss: 0.7732540369033813:  18%|█▊        | 4564/25880 [57:39<4:49:15,  1.23it/s]
1|4565|Loss: 0.7732540369033813:  18%|█▊        | 4565/25880 [57:40<4:54:19,  1.21it/s]
1|4566|Loss: 0.9213735461235046:  18%|█▊        | 4565/25880 [57:40<4:54:19,  1.21it/s]
1|4566|Loss: 0.9213735461235046:  18%|█▊        | 4566/25880 [57:41<4:56:01,  1.20it/s]
1|4567|Loss: 0.8967256546020508:  18%|█▊        | 4566/25880 [57:41<4:56:01,  1.20it/s]
1|4567|Loss: 0.8967256546020508:  18%|█▊        | 4567/25880 [57:41<4:44:37,  1.25it/s]
1|4568|Loss: 0.8227465748786926:  18%|█▊        | 4567/25880 [57:42<4:44:37,  1.25it/s]
1|4568|Loss: 0.8227465748786926:  18%|█▊        | 4568/25880 [57:42<4:15:31,  1.39it/s]
1|4569|Loss: 1.0299161672592163:  18%|█▊        | 4568/25880 [57:42<4:15:31,  1.39it/s]
1|4569|Loss: 1.0299161672592163:  18%|█▊        | 4569/25880 [57:43<4:08:58,  1.43it/s]
1|4570|Loss: 0.8309218883514404:  18%|█▊        | 4569/25880 [57:43<4:08:58,  1.43it/s]
1|4570|Loss: 0.8309218883514404:  18%|█▊        | 4570/25880 [57:43<3:58:56,  1.49it/s]
1|4571|Loss: 0.9134384393692017:  18%|█▊        | 4570/25880 [57:44<3:58:56,  1.49it/s]
1|4571|Loss: 0.9134384393692017:  18%|█▊        | 4571/25880 [57:44<4:02:08,  1.47it/s]
1|4572|Loss: 0.7270454168319702:  18%|█▊        | 4571/25880 [57:44<4:02:08,  1.47it/s]
1|4572|Loss: 0.7270454168319702:  18%|█▊        | 4572/25880 [57:44<3:46:24,  1.57it/s]
1|4573|Loss: 0.8763834834098816:  18%|█▊        | 4572/25880 [57:45<3:46:24,  1.57it/s]
1|4573|Loss: 0.8763834834098816:  18%|█▊        | 4573/25880 [57:45<3:55:15,  1.51it/s]
1|4574|Loss: 0.7522159814834595:  18%|█▊        | 4573/25880 [57:46<3:55:15,  1.51it/s]
1|4574|Loss: 0.7522159814834595:  18%|█▊        | 4574/25880 [57:46<4:14:30,  1.40it/s]
1|4575|Loss: 0.865450382232666:  18%|█▊        | 4574/25880 [57:46<4:14:30,  1.40it/s] 
1|4575|Loss: 0.865450382232666:  18%|█▊        | 4575/25880 [57:47<4:16:26,  1.38it/s]
1|4576|Loss: 0.8485420346260071:  18%|█▊        | 4575/25880 [57:47<4:16:26,  1.38it/s]
1|4576|Loss: 0.8485420346260071:  18%|█▊        | 4576/25880 [57:48<4:22:54,  1.35it/s]
1|4577|Loss: 0.7358973026275635:  18%|█▊        | 4576/25880 [57:48<4:22:54,  1.35it/s]
1|4577|Loss: 0.7358973026275635:  18%|█▊        | 4577/25880 [57:48<4:08:12,  1.43it/s]
1|4578|Loss: 0.8395121097564697:  18%|█▊        | 4577/25880 [57:48<4:08:12,  1.43it/s]
1|4578|Loss: 0.8395121097564697:  18%|█▊        | 4578/25880 [57:49<4:08:20,  1.43it/s]
1|4579|Loss: 1.0041574239730835:  18%|█▊        | 4578/25880 [57:49<4:08:20,  1.43it/s]
1|4579|Loss: 1.0041574239730835:  18%|█▊        | 4579/25880 [57:50<4:05:07,  1.45it/s]
1|4580|Loss: 0.9045704007148743:  18%|█▊        | 4579/25880 [57:50<4:05:07,  1.45it/s]
1|4580|Loss: 0.9045704007148743:  18%|█▊        | 4580/25880 [57:50<4:13:31,  1.40it/s]
1|4581|Loss: 0.8231966495513916:  18%|█▊        | 4580/25880 [57:51<4:13:31,  1.40it/s]
1|4581|Loss: 0.8231966495513916:  18%|█▊        | 4581/25880 [57:51<4:17:13,  1.38it/s]
1|4582|Loss: 0.9619737863540649:  18%|█▊        | 4581/25880 [57:51<4:17:13,  1.38it/s]
1|4582|Loss: 0.9619737863540649:  18%|█▊        | 4582/25880 [57:52<4:10:43,  1.42it/s]
1|4583|Loss: 0.9011519551277161:  18%|█▊        | 4582/25880 [57:52<4:10:43,  1.42it/s]
1|4583|Loss: 0.9011519551277161:  18%|█▊        | 4583/25880 [57:52<4:16:21,  1.38it/s]
1|4584|Loss: 0.8466939926147461:  18%|█▊        | 4583/25880 [57:53<4:16:21,  1.38it/s]
1|4584|Loss: 0.8466939926147461:  18%|█▊        | 4584/25880 [57:53<4:17:01,  1.38it/s]
1|4585|Loss: 0.8864197134971619:  18%|█▊        | 4584/25880 [57:54<4:17:01,  1.38it/s]
1|4585|Loss: 0.8864197134971619:  18%|█▊        | 4585/25880 [57:54<4:18:06,  1.38it/s]
1|4586|Loss: 0.756012499332428:  18%|█▊        | 4585/25880 [57:54<4:18:06,  1.38it/s] 
1|4586|Loss: 0.756012499332428:  18%|█▊        | 4586/25880 [57:55<4:24:27,  1.34it/s]
1|4587|Loss: 0.8960191011428833:  18%|█▊        | 4586/25880 [57:55<4:24:27,  1.34it/s]
1|4587|Loss: 0.8960191011428833:  18%|█▊        | 4587/25880 [57:55<4:17:00,  1.38it/s]
1|4588|Loss: 0.8858208060264587:  18%|█▊        | 4587/25880 [57:56<4:17:00,  1.38it/s]
1|4588|Loss: 0.8858208060264587:  18%|█▊        | 4588/25880 [57:56<4:15:43,  1.39it/s]
1|4589|Loss: 0.9401794075965881:  18%|█▊        | 4588/25880 [57:56<4:15:43,  1.39it/s]
1|4589|Loss: 0.9401794075965881:  18%|█▊        | 4589/25880 [57:57<4:14:09,  1.40it/s]
1|4590|Loss: 1.0402640104293823:  18%|█▊        | 4589/25880 [57:57<4:14:09,  1.40it/s]
1|4590|Loss: 1.0402640104293823:  18%|█▊        | 4590/25880 [57:57<4:12:48,  1.40it/s]
1|4591|Loss: 0.9752320051193237:  18%|█▊        | 4590/25880 [57:58<4:12:48,  1.40it/s]
1|4591|Loss: 0.9752320051193237:  18%|█▊        | 4591/25880 [57:58<4:11:11,  1.41it/s]
1|4592|Loss: 0.8820309042930603:  18%|█▊        | 4591/25880 [57:59<4:11:11,  1.41it/s]
1|4592|Loss: 0.8820309042930603:  18%|█▊        | 4592/25880 [57:59<4:23:28,  1.35it/s]
1|4593|Loss: 0.9686342477798462:  18%|█▊        | 4592/25880 [58:00<4:23:28,  1.35it/s]
1|4593|Loss: 0.9686342477798462:  18%|█▊        | 4593/25880 [58:00<4:44:59,  1.24it/s]
1|4594|Loss: 0.7056023478507996:  18%|█▊        | 4593/25880 [58:00<4:44:59,  1.24it/s]
1|4594|Loss: 0.7056023478507996:  18%|█▊        | 4594/25880 [58:01<5:02:16,  1.17it/s]
1|4595|Loss: 0.966438353061676:  18%|█▊        | 4594/25880 [58:01<5:02:16,  1.17it/s] 
1|4595|Loss: 0.966438353061676:  18%|█▊        | 4595/25880 [58:02<5:02:41,  1.17it/s]
1|4596|Loss: 0.8229252099990845:  18%|█▊        | 4595/25880 [58:02<5:02:41,  1.17it/s]
1|4596|Loss: 0.8229252099990845:  18%|█▊        | 4596/25880 [58:03<4:48:59,  1.23it/s]
1|4597|Loss: 0.7964861392974854:  18%|█▊        | 4596/25880 [58:03<4:48:59,  1.23it/s]
1|4597|Loss: 0.7964861392974854:  18%|█▊        | 4597/25880 [58:03<4:51:12,  1.22it/s]
1|4598|Loss: 0.7801411151885986:  18%|█▊        | 4597/25880 [58:04<4:51:12,  1.22it/s]
1|4598|Loss: 0.7801411151885986:  18%|█▊        | 4598/25880 [58:04<4:35:19,  1.29it/s]
1|4599|Loss: 0.9837082028388977:  18%|█▊        | 4598/25880 [58:04<4:35:19,  1.29it/s]
1|4599|Loss: 0.9837082028388977:  18%|█▊        | 4599/25880 [58:05<4:12:54,  1.40it/s]
1|4600|Loss: 0.930945873260498:  18%|█▊        | 4599/25880 [58:05<4:12:54,  1.40it/s] 
1|4600|Loss: 0.930945873260498:  18%|█▊        | 4600/25880 [58:05<4:22:35,  1.35it/s]
1|4601|Loss: 0.7505871057510376:  18%|█▊        | 4600/25880 [58:06<4:22:35,  1.35it/s]
1|4601|Loss: 0.7505871057510376:  18%|█▊        | 4601/25880 [58:06<4:01:41,  1.47it/s]
1|4602|Loss: 0.9215765595436096:  18%|█▊        | 4601/25880 [58:06<4:01:41,  1.47it/s]
1|4602|Loss: 0.9215765595436096:  18%|█▊        | 4602/25880 [58:07<4:00:17,  1.48it/s]
1|4603|Loss: 0.7982478737831116:  18%|█▊        | 4602/25880 [58:07<4:00:17,  1.48it/s]
1|4603|Loss: 0.7982478737831116:  18%|█▊        | 4603/25880 [58:07<3:36:38,  1.64it/s]
1|4604|Loss: 0.8028658628463745:  18%|█▊        | 4603/25880 [58:07<3:36:38,  1.64it/s]
1|4604|Loss: 0.8028658628463745:  18%|█▊        | 4604/25880 [58:08<3:43:18,  1.59it/s]
1|4605|Loss: 0.8021105527877808:  18%|█▊        | 4604/25880 [58:08<3:43:18,  1.59it/s]
1|4605|Loss: 0.8021105527877808:  18%|█▊        | 4605/25880 [58:08<3:54:27,  1.51it/s]
1|4606|Loss: 0.8253487348556519:  18%|█▊        | 4605/25880 [58:09<3:54:27,  1.51it/s]
1|4606|Loss: 0.8253487348556519:  18%|█▊        | 4606/25880 [58:09<3:59:59,  1.48it/s]
1|4607|Loss: 0.8909156918525696:  18%|█▊        | 4606/25880 [58:10<3:59:59,  1.48it/s]
1|4607|Loss: 0.8909156918525696:  18%|█▊        | 4607/25880 [58:10<3:57:46,  1.49it/s]
1|4608|Loss: 0.8890343308448792:  18%|█▊        | 4607/25880 [58:10<3:57:46,  1.49it/s]
1|4608|Loss: 0.8890343308448792:  18%|█▊        | 4608/25880 [58:11<4:08:06,  1.43it/s]
1|4609|Loss: 0.8255061507225037:  18%|█▊        | 4608/25880 [58:11<4:08:06,  1.43it/s]
1|4609|Loss: 0.8255061507225037:  18%|█▊        | 4609/25880 [58:12<4:34:00,  1.29it/s]
1|4610|Loss: 0.8287732601165771:  18%|█▊        | 4609/25880 [58:12<4:34:00,  1.29it/s]
1|4610|Loss: 0.8287732601165771:  18%|█▊        | 4610/25880 [58:12<4:17:40,  1.38it/s]
1|4611|Loss: 0.9723037481307983:  18%|█▊        | 4610/25880 [58:13<4:17:40,  1.38it/s]
1|4611|Loss: 0.9723037481307983:  18%|█▊        | 4611/25880 [58:13<4:28:49,  1.32it/s]
1|4612|Loss: 0.8792051672935486:  18%|█▊        | 4611/25880 [58:13<4:28:49,  1.32it/s]
1|4612|Loss: 0.8792051672935486:  18%|█▊        | 4612/25880 [58:14<4:27:29,  1.33it/s]
1|4613|Loss: 0.9444325566291809:  18%|█▊        | 4612/25880 [58:14<4:27:29,  1.33it/s]
1|4613|Loss: 0.9444325566291809:  18%|█▊        | 4613/25880 [58:14<4:16:55,  1.38it/s]
1|4614|Loss: 0.9843535423278809:  18%|█▊        | 4613/25880 [58:15<4:16:55,  1.38it/s]
1|4614|Loss: 0.9843535423278809:  18%|█▊        | 4614/25880 [58:15<4:00:43,  1.47it/s]
1|4615|Loss: 0.9065651893615723:  18%|��▊        | 4614/25880 [58:15<4:00:43,  1.47it/s]
1|4615|Loss: 0.9065651893615723:  18%|█▊        | 4615/25880 [58:16<4:00:08,  1.48it/s]
1|4616|Loss: 0.9410940408706665:  18%|█▊        | 4615/25880 [58:16<4:00:08,  1.48it/s]
1|4616|Loss: 0.9410940408706665:  18%|█▊        | 4616/25880 [58:16<4:13:30,  1.40it/s]
1|4617|Loss: 0.8499128222465515:  18%|█▊        | 4616/25880 [58:17<4:13:30,  1.40it/s]
1|4617|Loss: 0.8499128222465515:  18%|█▊        | 4617/25880 [58:17<3:58:42,  1.48it/s]
1|4618|Loss: 0.8674456477165222:  18%|█▊        | 4617/25880 [58:17<3:58:42,  1.48it/s]
1|4618|Loss: 0.8674456477165222:  18%|█▊        | 4618/25880 [58:18<3:57:04,  1.49it/s]
1|4619|Loss: 0.9049699306488037:  18%|█▊        | 4618/25880 [58:18<3:57:04,  1.49it/s]
1|4619|Loss: 0.9049699306488037:  18%|█▊        | 4619/25880 [58:18<4:00:42,  1.47it/s]
1|4620|Loss: 0.9244965314865112:  18%|█▊        | 4619/25880 [58:19<4:00:42,  1.47it/s]
1|4620|Loss: 0.9244965314865112:  18%|█▊        | 4620/25880 [58:19<4:05:31,  1.44it/s]
1|4621|Loss: 0.8696091771125793:  18%|█▊        | 4620/25880 [58:20<4:05:31,  1.44it/s]
1|4621|Loss: 0.8696091771125793:  18%|█▊        | 4621/25880 [58:20<4:14:29,  1.39it/s]
1|4622|Loss: 1.025100588798523:  18%|█▊        | 4621/25880 [58:20<4:14:29,  1.39it/s] 
1|4622|Loss: 1.025100588798523:  18%|█▊        | 4622/25880 [58:21<4:17:30,  1.38it/s]
1|4623|Loss: 0.8105654120445251:  18%|█▊        | 4622/25880 [58:21<4:17:30,  1.38it/s]
1|4623|Loss: 0.8105654120445251:  18%|█▊        | 4623/25880 [58:21<4:15:39,  1.39it/s]
1|4624|Loss: 0.8604537844657898:  18%|█▊        | 4623/25880 [58:22<4:15:39,  1.39it/s]
1|4624|Loss: 0.8604537844657898:  18%|█▊        | 4624/25880 [58:22<4:22:29,  1.35it/s]
1|4625|Loss: 0.8510264754295349:  18%|█▊        | 4624/25880 [58:22<4:22:29,  1.35it/s]
1|4625|Loss: 0.8510264754295349:  18%|█▊        | 4625/25880 [58:23<4:02:45,  1.46it/s]
1|4626|Loss: 0.7840055227279663:  18%|█▊        | 4625/25880 [58:23<4:02:45,  1.46it/s]
1|4626|Loss: 0.7840055227279663:  18%|█▊        | 4626/25880 [58:23<3:54:05,  1.51it/s]
1|4627|Loss: 0.8558935523033142:  18%|█▊        | 4626/25880 [58:24<3:54:05,  1.51it/s]
1|4627|Loss: 0.8558935523033142:  18%|█▊        | 4627/25880 [58:24<4:04:31,  1.45it/s]
1|4628|Loss: 0.9440183043479919:  18%|█▊        | 4627/25880 [58:24<4:04:31,  1.45it/s]
1|4628|Loss: 0.9440183043479919:  18%|█▊        | 4628/25880 [58:25<4:15:04,  1.39it/s]
1|4629|Loss: 0.8750001192092896:  18%|█▊        | 4628/25880 [58:25<4:15:04,  1.39it/s]
1|4629|Loss: 0.8750001192092896:  18%|█▊        | 4629/25880 [58:26<4:28:08,  1.32it/s]
1|4630|Loss: 0.847135066986084:  18%|█▊        | 4629/25880 [58:26<4:28:08,  1.32it/s] 
1|4630|Loss: 0.847135066986084:  18%|█▊        | 4630/25880 [58:26<4:30:03,  1.31it/s]
1|4631|Loss: 0.7846765518188477:  18%|█▊        | 4630/25880 [58:27<4:30:03,  1.31it/s]
1|4631|Loss: 0.7846765518188477:  18%|█▊        | 4631/25880 [58:27<4:25:03,  1.34it/s]
1|4632|Loss: 0.9493687748908997:  18%|█▊        | 4631/25880 [58:28<4:25:03,  1.34it/s]
1|4632|Loss: 0.9493687748908997:  18%|█▊        | 4632/25880 [58:28<4:20:14,  1.36it/s]
1|4633|Loss: 0.8017676472663879:  18%|█▊        | 4632/25880 [58:28<4:20:14,  1.36it/s]
1|4633|Loss: 0.8017676472663879:  18%|█▊        | 4633/25880 [58:29<4:19:05,  1.37it/s]
1|4634|Loss: 0.8952712416648865:  18%|█▊        | 4633/25880 [58:29<4:19:05,  1.37it/s]
1|4634|Loss: 0.8952712416648865:  18%|█▊        | 4634/25880 [58:29<4:00:09,  1.47it/s]
1|4635|Loss: 0.7041972875595093:  18%|█▊        | 4634/25880 [58:29<4:00:09,  1.47it/s]
1|4635|Loss: 0.7041972875595093:  18%|█▊        | 4635/25880 [58:30<3:50:40,  1.53it/s]
1|4636|Loss: 0.8385947942733765:  18%|█▊        | 4635/25880 [58:30<3:50:40,  1.53it/s]
1|4636|Loss: 0.8385947942733765:  18%|█▊        | 4636/25880 [58:31<4:07:02,  1.43it/s]
1|4637|Loss: 0.9328538775444031:  18%|█▊        | 4636/25880 [58:31<4:07:02,  1.43it/s]
1|4637|Loss: 0.9328538775444031:  18%|█▊        | 4637/25880 [58:31<4:25:38,  1.33it/s]
1|4638|Loss: 1.0370984077453613:  18%|█▊        | 4637/25880 [58:32<4:25:38,  1.33it/s]
1|4638|Loss: 1.0370984077453613:  18%|█▊        | 4638/25880 [58:32<4:36:30,  1.28it/s]
1|4639|Loss: 0.7990885376930237:  18%|█▊        | 4638/25880 [58:33<4:36:30,  1.28it/s]
1|4639|Loss: 0.7990885376930237:  18%|█▊        | 4639/25880 [58:33<4:33:51,  1.29it/s]
1|4640|Loss: 0.8774684071540833:  18%|█▊        | 4639/25880 [58:33<4:33:51,  1.29it/s]
1|4640|Loss: 0.8774684071540833:  18%|█▊        | 4640/25880 [58:34<4:41:23,  1.26it/s]
1|4641|Loss: 0.8357511758804321:  18%|█▊        | 4640/25880 [58:34<4:41:23,  1.26it/s]
1|4641|Loss: 0.8357511758804321:  18%|█▊        | 4641/25880 [58:35<4:38:20,  1.27it/s]
1|4642|Loss: 0.8754993081092834:  18%|█▊        | 4641/25880 [58:35<4:38:20,  1.27it/s]
1|4642|Loss: 0.8754993081092834:  18%|█▊        | 4642/25880 [58:35<4:30:17,  1.31it/s]
1|4643|Loss: 1.0236178636550903:  18%|█▊        | 4642/25880 [58:36<4:30:17,  1.31it/s]
1|4643|Loss: 1.0236178636550903:  18%|█▊        | 4643/25880 [58:36<4:23:49,  1.34it/s]
1|4644|Loss: 0.6954053044319153:  18%|█▊        | 4643/25880 [58:36<4:23:49,  1.34it/s]
1|4644|Loss: 0.6954053044319153:  18%|█▊        | 4644/25880 [58:37<3:57:51,  1.49it/s]
1|4645|Loss: 0.9076048135757446:  18%|█▊        | 4644/25880 [58:37<3:57:51,  1.49it/s]
1|4645|Loss: 0.9076048135757446:  18%|█▊        | 4645/25880 [58:37<3:58:48,  1.48it/s]
1|4646|Loss: 0.8653353452682495:  18%|█▊        | 4645/25880 [58:38<3:58:48,  1.48it/s]
1|4646|Loss: 0.8653353452682495:  18%|█▊        | 4646/25880 [58:38<4:14:15,  1.39it/s]
1|4647|Loss: 0.7503340244293213:  18%|█▊        | 4646/25880 [58:38<4:14:15,  1.39it/s]
1|4647|Loss: 0.7503340244293213:  18%|█▊        | 4647/25880 [58:39<4:16:46,  1.38it/s]
1|4648|Loss: 0.8593586087226868:  18%|█▊        | 4647/25880 [58:39<4:16:46,  1.38it/s]
1|4648|Loss: 0.8593586087226868:  18%|█▊        | 4648/25880 [58:39<4:14:26,  1.39it/s]
1|4649|Loss: 0.823433518409729:  18%|█▊        | 4648/25880 [58:40<4:14:26,  1.39it/s] 
1|4649|Loss: 0.823433518409729:  18%|█▊        | 4649/25880 [58:40<4:23:31,  1.34it/s]
1|4650|Loss: 0.8701197504997253:  18%|█▊        | 4649/25880 [58:41<4:23:31,  1.34it/s]
1|4650|Loss: 0.8701197504997253:  18%|█▊        | 4650/25880 [58:41<4:32:28,  1.30it/s]
1|4651|Loss: 0.7045978903770447:  18%|█▊        | 4650/25880 [58:42<4:32:28,  1.30it/s]
1|4651|Loss: 0.7045978903770447:  18%|█▊        | 4651/25880 [58:42<4:30:38,  1.31it/s]
1|4652|Loss: 0.8543444871902466:  18%|█▊        | 4651/25880 [58:42<4:30:38,  1.31it/s]
1|4652|Loss: 0.8543444871902466:  18%|█▊        | 4652/25880 [58:43<4:38:55,  1.27it/s]
1|4653|Loss: 0.8610183596611023:  18%|█▊        | 4652/25880 [58:43<4:38:55,  1.27it/s]
1|4653|Loss: 0.8610183596611023:  18%|█▊        | 4653/25880 [58:44<4:56:22,  1.19it/s]
1|4654|Loss: 0.8092204332351685:  18%|█▊        | 4653/25880 [58:44<4:56:22,  1.19it/s]
1|4654|Loss: 0.8092204332351685:  18%|█▊        | 4654/25880 [58:44<4:37:18,  1.28it/s]
1|4655|Loss: 0.7973669767379761:  18%|█▊        | 4654/25880 [58:45<4:37:18,  1.28it/s]
1|4655|Loss: 0.7973669767379761:  18%|█▊        | 4655/25880 [58:45<4:40:26,  1.26it/s]
1|4656|Loss: 0.9262701869010925:  18%|█▊        | 4655/25880 [58:46<4:40:26,  1.26it/s]
1|4656|Loss: 0.9262701869010925:  18%|█▊        | 4656/25880 [58:46<4:42:07,  1.25it/s]
1|4657|Loss: 0.9046216011047363:  18%|█▊        | 4656/25880 [58:46<4:42:07,  1.25it/s]
1|4657|Loss: 0.9046216011047363:  18%|█▊        | 4657/25880 [58:47<4:45:30,  1.24it/s]
1|4658|Loss: 0.9115446209907532:  18%|█▊        | 4657/25880 [58:47<4:45:30,  1.24it/s]
1|4658|Loss: 0.9115446209907532:  18%|█▊        | 4658/25880 [58:48<4:48:49,  1.22it/s]
1|4659|Loss: 0.812690019607544:  18%|█▊        | 4658/25880 [58:48<4:48:49,  1.22it/s] 
1|4659|Loss: 0.812690019607544:  18%|█▊        | 4659/25880 [58:48<4:32:27,  1.30it/s]
1|4660|Loss: 0.8108546137809753:  18%|█▊        | 4659/25880 [58:49<4:32:27,  1.30it/s]
1|4660|Loss: 0.8108546137809753:  18%|█▊        | 4660/25880 [58:49<4:48:36,  1.23it/s]
1|4661|Loss: 0.8979259133338928:  18%|█▊        | 4660/25880 [58:50<4:48:36,  1.23it/s]
1|4661|Loss: 0.8979259133338928:  18%|█▊        | 4661/25880 [58:50<4:27:52,  1.32it/s]
1|4662|Loss: 0.9086901545524597:  18%|█▊        | 4661/25880 [58:50<4:27:52,  1.32it/s]
1|4662|Loss: 0.9086901545524597:  18%|█▊        | 4662/25880 [58:51<4:20:02,  1.36it/s]
1|4663|Loss: 0.7224472165107727:  18%|█▊        | 4662/25880 [58:51<4:20:02,  1.36it/s]
1|4663|Loss: 0.7224472165107727:  18%|█▊        | 4663/25880 [58:51<4:39:30,  1.27it/s]
1|4664|Loss: 0.8253419399261475:  18%|█▊        | 4663/25880 [58:52<4:39:30,  1.27it/s]
1|4664|Loss: 0.8253419399261475:  18%|█▊        | 4664/25880 [58:52<4:29:17,  1.31it/s]
1|4665|Loss: 0.7456567883491516:  18%|█▊        | 4664/25880 [58:53<4:29:17,  1.31it/s]
1|4665|Loss: 0.7456567883491516:  18%|█▊        | 4665/25880 [58:53<4:24:07,  1.34it/s]
1|4666|Loss: 0.7667710781097412:  18%|█▊        | 4665/25880 [58:53<4:24:07,  1.34it/s]
1|4666|Loss: 0.7667710781097412:  18%|█▊        | 4666/25880 [58:54<4:38:55,  1.27it/s]
1|4667|Loss: 0.9557632803916931:  18%|█▊        | 4666/25880 [58:54<4:38:55,  1.27it/s]
1|4667|Loss: 0.9557632803916931:  18%|█▊        | 4667/25880 [58:54<4:34:03,  1.29it/s]
1|4668|Loss: 1.0252196788787842:  18%|█▊        | 4667/25880 [58:55<4:34:03,  1.29it/s]
1|4668|Loss: 1.0252196788787842:  18%|█▊        | 4668/25880 [58:55<4:19:27,  1.36it/s]
1|4669|Loss: 0.7618377804756165:  18%|█▊        | 4668/25880 [58:55<4:19:27,  1.36it/s]
1|4669|Loss: 0.7618377804756165:  18%|█▊        | 4669/25880 [58:56<4:02:05,  1.46it/s]
1|4670|Loss: 0.8805422186851501:  18%|█▊        | 4669/25880 [58:56<4:02:05,  1.46it/s]
1|4670|Loss: 0.8805422186851501:  18%|█▊        | 4670/25880 [58:56<3:55:12,  1.50it/s]
1|4671|Loss: 0.8146326541900635:  18%|█▊        | 4670/25880 [58:57<3:55:12,  1.50it/s]
1|4671|Loss: 0.8146326541900635:  18%|█▊        | 4671/25880 [58:57<3:43:08,  1.58it/s]
1|4672|Loss: 0.7959055304527283:  18%|█▊        | 4671/25880 [58:57<3:43:08,  1.58it/s]
1|4672|Loss: 0.7959055304527283:  18%|█▊        | 4672/25880 [58:58<3:46:29,  1.56it/s]
1|4673|Loss: 0.8340969085693359:  18%|█▊        | 4672/25880 [58:58<3:46:29,  1.56it/s]
1|4673|Loss: 0.8340969085693359:  18%|█▊        | 4673/25880 [58:58<3:56:59,  1.49it/s]
1|4674|Loss: 0.9706557393074036:  18%|█▊        | 4673/25880 [58:59<3:56:59,  1.49it/s]
1|4674|Loss: 0.9706557393074036:  18%|█▊        | 4674/25880 [58:59<4:14:30,  1.39it/s]
1|4675|Loss: 0.8087551593780518:  18%|█▊        | 4674/25880 [59:00<4:14:30,  1.39it/s]
1|4675|Loss: 0.8087551593780518:  18%|█▊        | 4675/25880 [59:00<4:19:02,  1.36it/s]
1|4676|Loss: 0.8526976108551025:  18%|█▊        | 4675/25880 [59:00<4:19:02,  1.36it/s]
1|4676|Loss: 0.8526976108551025:  18%|█▊        | 4676/25880 [59:00<3:57:42,  1.49it/s]
1|4677|Loss: 0.8085557222366333:  18%|█▊        | 4676/25880 [59:01<3:57:42,  1.49it/s]
1|4677|Loss: 0.8085557222366333:  18%|█▊        | 4677/25880 [59:01<4:08:33,  1.42it/s]
1|4678|Loss: 0.8311943411827087:  18%|█▊        | 4677/25880 [59:02<4:08:33,  1.42it/s]
1|4678|Loss: 0.8311943411827087:  18%|█▊        | 4678/25880 [59:02<4:15:52,  1.38it/s]
1|4679|Loss: 0.9555731415748596:  18%|█▊        | 4678/25880 [59:02<4:15:52,  1.38it/s]
1|4679|Loss: 0.9555731415748596:  18%|█▊        | 4679/25880 [59:03<4:08:01,  1.42it/s]
1|4680|Loss: 0.6876890659332275:  18%|█▊        | 4679/25880 [59:03<4:08:01,  1.42it/s]
1|4680|Loss: 0.6876890659332275:  18%|█▊        | 4680/25880 [59:03<4:18:43,  1.37it/s]
1|4681|Loss: 0.5732612013816833:  18%|█▊        | 4680/25880 [59:04<4:18:43,  1.37it/s]
1|4681|Loss: 0.5732612013816833:  18%|█▊        | 4681/25880 [59:04<4:36:30,  1.28it/s]
1|4682|Loss: 1.0611560344696045:  18%|█▊        | 4681/25880 [59:05<4:36:30,  1.28it/s]
1|4682|Loss: 1.0611560344696045:  18%|█▊        | 4682/25880 [59:05<4:42:58,  1.25it/s]
1|4683|Loss: 0.7849571108818054:  18%|█▊        | 4682/25880 [59:06<4:42:58,  1.25it/s]
1|4683|Loss: 0.7849571108818054:  18%|█▊        | 4683/25880 [59:06<4:29:42,  1.31it/s]
1|4684|Loss: 0.8756204843521118:  18%|█▊        | 4683/25880 [59:06<4:29:42,  1.31it/s]
1|4684|Loss: 0.8756204843521118:  18%|█▊        | 4684/25880 [59:07<4:30:50,  1.30it/s]
1|4685|Loss: 0.8803810477256775:  18%|█▊        | 4684/25880 [59:07<4:30:50,  1.30it/s]
1|4685|Loss: 0.8803810477256775:  18%|█▊        | 4685/25880 [59:07<4:10:29,  1.41it/s]
1|4686|Loss: 0.8780778646469116:  18%|█▊        | 4685/25880 [59:08<4:10:29,  1.41it/s]
1|4686|Loss: 0.8780778646469116:  18%|█▊        | 4686/25880 [59:08<4:17:19,  1.37it/s]
1|4687|Loss: 0.8222352266311646:  18%|█▊        | 4686/25880 [59:08<4:17:19,  1.37it/s]
1|4687|Loss: 0.8222352266311646:  18%|█▊        | 4687/25880 [59:09<4:16:59,  1.37it/s]
1|4688|Loss: 1.0319191217422485:  18%|█▊        | 4687/25880 [59:09<4:16:59,  1.37it/s]
1|4688|Loss: 1.0319191217422485:  18%|█▊        | 4688/25880 [59:09<4:13:57,  1.39it/s]
1|4689|Loss: 0.9004809260368347:  18%|█▊        | 4688/25880 [59:10<4:13:57,  1.39it/s]
1|4689|Loss: 0.9004809260368347:  18%|█▊        | 4689/25880 [59:10<4:11:51,  1.40it/s]
1|4690|Loss: 0.9692940711975098:  18%|█▊        | 4689/25880 [59:10<4:11:51,  1.40it/s]
1|4690|Loss: 0.9692940711975098:  18%|█▊        | 4690/25880 [59:11<4:18:11,  1.37it/s]
1|4691|Loss: 0.9125866889953613:  18%|█▊        | 4690/25880 [59:11<4:18:11,  1.37it/s]
1|4691|Loss: 0.9125866889953613:  18%|█▊        | 4691/25880 [59:11<4:09:53,  1.41it/s]
1|4692|Loss: 0.8742808699607849:  18%|█▊        | 4691/25880 [59:12<4:09:53,  1.41it/s]
1|4692|Loss: 0.8742808699607849:  18%|█▊        | 4692/25880 [59:12<4:20:04,  1.36it/s]
1|4693|Loss: 0.9290893077850342:  18%|█▊        | 4692/25880 [59:13<4:20:04,  1.36it/s]
1|4693|Loss: 0.9290893077850342:  18%|█▊        | 4693/25880 [59:13<4:07:35,  1.43it/s]
1|4694|Loss: 0.825296938419342:  18%|█▊        | 4693/25880 [59:13<4:07:35,  1.43it/s] 
1|4694|Loss: 0.825296938419342:  18%|█▊        | 4694/25880 [59:14<4:07:15,  1.43it/s]
1|4695|Loss: 0.78628009557724:  18%|█▊        | 4694/25880 [59:14<4:07:15,  1.43it/s] 
1|4695|Loss: 0.78628009557724:  18%|█▊        | 4695/25880 [59:14<4:01:49,  1.46it/s]
1|4696|Loss: 0.8798453211784363:  18%|█▊        | 4695/25880 [59:15<4:01:49,  1.46it/s]
1|4696|Loss: 0.8798453211784363:  18%|█▊        | 4696/25880 [59:15<4:06:43,  1.43it/s]
1|4697|Loss: 0.8859401345252991:  18%|█▊        | 4696/25880 [59:15<4:06:43,  1.43it/s]
1|4697|Loss: 0.8859401345252991:  18%|█▊        | 4697/25880 [59:16<4:03:55,  1.45it/s]
1|4698|Loss: 0.8350623846054077:  18%|█▊        | 4697/25880 [59:16<4:03:55,  1.45it/s]
1|4698|Loss: 0.8350623846054077:  18%|█▊        | 4698/25880 [59:16<4:06:17,  1.43it/s]
1|4699|Loss: 0.7544986009597778:  18%|█▊        | 4698/25880 [59:17<4:06:17,  1.43it/s]
1|4699|Loss: 0.7544986009597778:  18%|█▊        | 4699/25880 [59:17<4:06:41,  1.43it/s]
1|4700|Loss: 0.8571606278419495:  18%|█▊        | 4699/25880 [59:17<4:06:41,  1.43it/s]
1|4700|Loss: 0.8571606278419495:  18%|█▊        | 4700/25880 [59:18<3:56:12,  1.49it/s]
1|4701|Loss: 0.842764139175415:  18%|█▊        | 4700/25880 [59:18<3:56:12,  1.49it/s] 
1|4701|Loss: 0.842764139175415:  18%|█▊        | 4701/25880 [59:18<4:06:13,  1.43it/s]
1|4702|Loss: 0.7917341589927673:  18%|█▊        | 4701/25880 [59:19<4:06:13,  1.43it/s]
1|4702|Loss: 0.7917341589927673:  18%|█▊        | 4702/25880 [59:19<4:09:34,  1.41it/s]
1|4703|Loss: 0.8712108731269836:  18%|█▊        | 4702/25880 [59:20<4:09:34,  1.41it/s]
1|4703|Loss: 0.8712108731269836:  18%|█▊        | 4703/25880 [59:20<4:01:41,  1.46it/s]
1|4704|Loss: 0.8934966325759888:  18%|█▊        | 4703/25880 [59:20<4:01:41,  1.46it/s]
1|4704|Loss: 0.8934966325759888:  18%|█▊        | 4704/25880 [59:20<4:03:40,  1.45it/s]
1|4705|Loss: 0.6946985721588135:  18%|█▊        | 4704/25880 [59:21<4:03:40,  1.45it/s]
1|4705|Loss: 0.6946985721588135:  18%|█▊        | 4705/25880 [59:21<4:16:15,  1.38it/s]
1|4706|Loss: 0.9153410196304321:  18%|█▊        | 4705/25880 [59:22<4:16:15,  1.38it/s]
1|4706|Loss: 0.9153410196304321:  18%|█▊        | 4706/25880 [59:22<4:23:37,  1.34it/s]
1|4707|Loss: 0.9656105637550354:  18%|█▊        | 4706/25880 [59:23<4:23:37,  1.34it/s]
1|4707|Loss: 0.9656105637550354:  18%|█▊        | 4707/25880 [59:23<4:29:15,  1.31it/s]
1|4708|Loss: 0.7780256867408752:  18%|█▊        | 4707/25880 [59:23<4:29:15,  1.31it/s]
1|4708|Loss: 0.7780256867408752:  18%|█▊        | 4708/25880 [59:24<4:35:48,  1.28it/s]
1|4709|Loss: 0.8248831629753113:  18%|█▊        | 4708/25880 [59:24<4:35:48,  1.28it/s]
1|4709|Loss: 0.8248831629753113:  18%|█▊        | 4709/25880 [59:24<4:24:28,  1.33it/s]
1|4710|Loss: 0.8973645567893982:  18%|█▊        | 4709/25880 [59:25<4:24:28,  1.33it/s]
1|4710|Loss: 0.8973645567893982:  18%|█▊        | 4710/25880 [59:25<4:12:40,  1.40it/s]
1|4711|Loss: 0.7224246859550476:  18%|█▊        | 4710/25880 [59:25<4:12:40,  1.40it/s]
1|4711|Loss: 0.7224246859550476:  18%|█▊        | 4711/25880 [59:26<3:57:20,  1.49it/s]
1|4712|Loss: 0.8699154257774353:  18%|█▊        | 4711/25880 [59:26<3:57:20,  1.49it/s]
1|4712|Loss: 0.8699154257774353:  18%|█▊        | 4712/25880 [59:26<3:59:01,  1.48it/s]
1|4713|Loss: 0.6966615915298462:  18%|█▊        | 4712/25880 [59:27<3:59:01,  1.48it/s]
1|4713|Loss: 0.6966615915298462:  18%|█▊        | 4713/25880 [59:27<4:04:57,  1.44it/s]
1|4714|Loss: 0.8489277958869934:  18%|█▊        | 4713/25880 [59:27<4:04:57,  1.44it/s]
1|4714|Loss: 0.8489277958869934:  18%|█▊        | 4714/25880 [59:28<4:10:47,  1.41it/s]
1|4715|Loss: 0.8860529065132141:  18%|█▊        | 4714/25880 [59:28<4:10:47,  1.41it/s]
1|4715|Loss: 0.8860529065132141:  18%|█▊        | 4715/25880 [59:28<4:06:14,  1.43it/s]
1|4716|Loss: 0.9514756798744202:  18%|█▊        | 4715/25880 [59:29<4:06:14,  1.43it/s]
1|4716|Loss: 0.9514756798744202:  18%|█▊        | 4716/25880 [59:29<4:00:16,  1.47it/s]
1|4717|Loss: 0.7823725938796997:  18%|█▊        | 4716/25880 [59:29<4:00:16,  1.47it/s]
1|4717|Loss: 0.7823725938796997:  18%|█▊        | 4717/25880 [59:30<4:04:25,  1.44it/s]
1|4718|Loss: 0.9114792346954346:  18%|█▊        | 4717/25880 [59:30<4:04:25,  1.44it/s]
1|4718|Loss: 0.9114792346954346:  18%|█▊        | 4718/25880 [59:30<3:51:52,  1.52it/s]
1|4719|Loss: 0.9044607877731323:  18%|█▊        | 4718/25880 [59:31<3:51:52,  1.52it/s]
1|4719|Loss: 0.9044607877731323:  18%|█▊        | 4719/25880 [59:31<3:56:48,  1.49it/s]
1|4720|Loss: 0.8394535779953003:  18%|█▊        | 4719/25880 [59:31<3:56:48,  1.49it/s]
1|4720|Loss: 0.8394535779953003:  18%|█▊        | 4720/25880 [59:32<4:03:53,  1.45it/s]
1|4721|Loss: 0.8573430180549622:  18%|█▊        | 4720/25880 [59:32<4:03:53,  1.45it/s]
1|4721|Loss: 0.8573430180549622:  18%|█▊        | 4721/25880 [59:33<4:05:11,  1.44it/s]
1|4722|Loss: 0.8975105881690979:  18%|█▊        | 4721/25880 [59:33<4:05:11,  1.44it/s]
1|4722|Loss: 0.8975105881690979:  18%|█▊        | 4722/25880 [59:33<4:14:39,  1.38it/s]
1|4723|Loss: 0.7324668169021606:  18%|█▊        | 4722/25880 [59:34<4:14:39,  1.38it/s]
1|4723|Loss: 0.7324668169021606:  18%|█▊        | 4723/25880 [59:34<4:14:34,  1.39it/s]
1|4724|Loss: 0.8420721292495728:  18%|█▊        | 4723/25880 [59:34<4:14:34,  1.39it/s]
1|4724|Loss: 0.8420721292495728:  18%|█▊        | 4724/25880 [59:35<4:19:14,  1.36it/s]
1|4725|Loss: 0.9225021004676819:  18%|█▊        | 4724/25880 [59:35<4:19:14,  1.36it/s]
1|4725|Loss: 0.9225021004676819:  18%|█▊        | 4725/25880 [59:36<4:27:23,  1.32it/s]
1|4726|Loss: 0.8526941537857056:  18%|█▊        | 4725/25880 [59:36<4:27:23,  1.32it/s]
1|4726|Loss: 0.8526941537857056:  18%|█▊        | 4726/25880 [59:36<4:31:19,  1.30it/s]
1|4727|Loss: 0.8617435097694397:  18%|█▊        | 4726/25880 [59:37<4:31:19,  1.30it/s]
1|4727|Loss: 0.8617435097694397:  18%|█▊        | 4727/25880 [59:37<4:44:37,  1.24it/s]
1|4728|Loss: 0.7863273024559021:  18%|█▊        | 4727/25880 [59:38<4:44:37,  1.24it/s]
1|4728|Loss: 0.7863273024559021:  18%|█▊        | 4728/25880 [59:38<4:32:46,  1.29it/s]
1|4729|Loss: 0.9539226293563843:  18%|█▊        | 4728/25880 [59:38<4:32:46,  1.29it/s]
1|4729|Loss: 0.9539226293563843:  18%|█▊        | 4729/25880 [59:39<4:18:59,  1.36it/s]
1|4730|Loss: 0.888773500919342:  18%|█▊        | 4729/25880 [59:39<4:18:59,  1.36it/s] 
1|4730|Loss: 0.888773500919342:  18%|█▊        | 4730/25880 [59:39<4:14:41,  1.38it/s]
1|4731|Loss: 0.7595307230949402:  18%|█▊        | 4730/25880 [59:40<4:14:41,  1.38it/s]
1|4731|Loss: 0.7595307230949402:  18%|█▊        | 4731/25880 [59:40<3:57:50,  1.48it/s]
1|4732|Loss: 0.9139224886894226:  18%|█▊        | 4731/25880 [59:40<3:57:50,  1.48it/s]
1|4732|Loss: 0.9139224886894226:  18%|█▊        | 4732/25880 [59:41<3:56:37,  1.49it/s]
1|4733|Loss: 0.8197134137153625:  18%|█▊        | 4732/25880 [59:41<3:56:37,  1.49it/s]
1|4733|Loss: 0.8197134137153625:  18%|█▊        | 4733/25880 [59:41<4:02:24,  1.45it/s]
1|4734|Loss: 0.8935511708259583:  18%|█▊        | 4733/25880 [59:42<4:02:24,  1.45it/s]
1|4734|Loss: 0.8935511708259583:  18%|█▊        | 4734/25880 [59:42<4:07:54,  1.42it/s]
1|4735|Loss: 0.8476160764694214:  18%|█▊        | 4734/25880 [59:42<4:07:54,  1.42it/s]
1|4735|Loss: 0.8476160764694214:  18%|█▊        | 4735/25880 [59:43<3:50:28,  1.53it/s]
1|4736|Loss: 0.8449642062187195:  18%|█▊        | 4735/25880 [59:43<3:50:28,  1.53it/s]
1|4736|Loss: 0.8449642062187195:  18%|█▊        | 4736/25880 [59:43<3:50:58,  1.53it/s]
1|4737|Loss: 0.7590807676315308:  18%|█▊        | 4736/25880 [59:44<3:50:58,  1.53it/s]
1|4737|Loss: 0.7590807676315308:  18%|█▊        | 4737/25880 [59:44<3:51:14,  1.52it/s]
1|4738|Loss: 0.9007863998413086:  18%|█▊        | 4737/25880 [59:44<3:51:14,  1.52it/s]
1|4738|Loss: 0.9007863998413086:  18%|█▊        | 4738/25880 [59:45<3:54:16,  1.50it/s]
1|4739|Loss: 0.8401343822479248:  18%|█▊        | 4738/25880 [59:45<3:54:16,  1.50it/s]
1|4739|Loss: 0.8401343822479248:  18%|█▊        | 4739/25880 [59:45<4:02:10,  1.45it/s]
1|4740|Loss: 0.7771274447441101:  18%|█▊        | 4739/25880 [59:46<4:02:10,  1.45it/s]
1|4740|Loss: 0.7771274447441101:  18%|█▊        | 4740/25880 [59:46<4:23:48,  1.34it/s]
1|4741|Loss: 0.7277636528015137:  18%|█▊        | 4740/25880 [59:47<4:23:48,  1.34it/s]
1|4741|Loss: 0.7277636528015137:  18%|█▊        | 4741/25880 [59:47<4:13:09,  1.39it/s]
1|4742|Loss: 0.7341926097869873:  18%|█▊        | 4741/25880 [59:47<4:13:09,  1.39it/s]
1|4742|Loss: 0.7341926097869873:  18%|█▊        | 4742/25880 [59:48<4:30:32,  1.30it/s]
1|4743|Loss: 0.8308221697807312:  18%|█▊        | 4742/25880 [59:48<4:30:32,  1.30it/s]
1|4743|Loss: 0.8308221697807312:  18%|█▊        | 4743/25880 [59:49<4:40:31,  1.26it/s]
1|4744|Loss: 0.7990352511405945:  18%|█▊        | 4743/25880 [59:49<4:40:31,  1.26it/s]
1|4744|Loss: 0.7990352511405945:  18%|█▊        | 4744/25880 [59:49<4:27:55,  1.31it/s]
1|4745|Loss: 0.960696816444397:  18%|█▊        | 4744/25880 [59:50<4:27:55,  1.31it/s] 
1|4745|Loss: 0.960696816444397:  18%|█▊        | 4745/25880 [59:50<4:35:57,  1.28it/s]
1|4746|Loss: 0.8378558158874512:  18%|█▊        | 4745/25880 [59:51<4:35:57,  1.28it/s]
1|4746|Loss: 0.8378558158874512:  18%|█▊        | 4746/25880 [59:51<4:35:24,  1.28it/s]
1|4747|Loss: 0.8828078508377075:  18%|█▊        | 4746/25880 [59:51<4:35:24,  1.28it/s]
1|4747|Loss: 0.8828078508377075:  18%|█▊        | 4747/25880 [59:52<4:30:49,  1.30it/s]
1|4748|Loss: 0.8125625252723694:  18%|█▊        | 4747/25880 [59:52<4:30:49,  1.30it/s]
1|4748|Loss: 0.8125625252723694:  18%|█▊        | 4748/25880 [59:52<4:26:07,  1.32it/s]
1|4749|Loss: 0.8590103387832642:  18%|█▊        | 4748/25880 [59:53<4:26:07,  1.32it/s]
1|4749|Loss: 0.8590103387832642:  18%|█▊        | 4749/25880 [59:53<4:31:56,  1.30it/s]
1|4750|Loss: 0.8253204822540283:  18%|█▊        | 4749/25880 [59:54<4:31:56,  1.30it/s]
1|4750|Loss: 0.8253204822540283:  18%|█▊        | 4750/25880 [59:54<4:22:06,  1.34it/s]
1|4751|Loss: 1.0478535890579224:  18%|█▊        | 4750/25880 [59:54<4:22:06,  1.34it/s]
1|4751|Loss: 1.0478535890579224:  18%|█▊        | 4751/25880 [59:55<4:30:29,  1.30it/s]
1|4752|Loss: 0.8037729263305664:  18%|█▊        | 4751/25880 [59:55<4:30:29,  1.30it/s]
1|4752|Loss: 0.8037729263305664:  18%|█▊        | 4752/25880 [59:55<4:17:49,  1.37it/s]
1|4753|Loss: 0.9614721536636353:  18%|█▊        | 4752/25880 [59:56<4:17:49,  1.37it/s]
1|4753|Loss: 0.9614721536636353:  18%|█▊        | 4753/25880 [59:56<4:22:45,  1.34it/s]
1|4754|Loss: 0.7557117342948914:  18%|█▊        | 4753/25880 [59:57<4:22:45,  1.34it/s]
1|4754|Loss: 0.7557117342948914:  18%|█▊        | 4754/25880 [59:57<4:33:56,  1.29it/s]
1|4755|Loss: 0.8555638194084167:  18%|█▊        | 4754/25880 [59:57<4:33:56,  1.29it/s]
1|4755|Loss: 0.8555638194084167:  18%|█▊        | 4755/25880 [59:58<4:17:24,  1.37it/s]
1|4756|Loss: 0.8802390098571777:  18%|█▊        | 4755/25880 [59:58<4:17:24,  1.37it/s]
1|4756|Loss: 0.8802390098571777:  18%|█▊        | 4756/25880 [59:58<4:10:33,  1.41it/s]
1|4757|Loss: 0.9115849733352661:  18%|█▊        | 4756/25880 [59:59<4:10:33,  1.41it/s]
1|4757|Loss: 0.9115849733352661:  18%|█▊        | 4757/25880 [59:59<4:30:38,  1.30it/s]
1|4758|Loss: 0.9261289834976196:  18%|█▊        | 4757/25880 [1:00:00<4:30:38,  1.30it/s]
1|4758|Loss: 0.9261289834976196:  18%|█▊        | 4758/25880 [1:00:00<4:16:29,  1.37it/s]
1|4759|Loss: 0.8772698640823364:  18%|█▊        | 4758/25880 [1:00:00<4:16:29,  1.37it/s]
1|4759|Loss: 0.8772698640823364:  18%|█▊        | 4759/25880 [1:00:00<4:12:38,  1.39it/s]
1|4760|Loss: 1.0039676427841187:  18%|█▊        | 4759/25880 [1:00:01<4:12:38,  1.39it/s]
1|4760|Loss: 1.0039676427841187:  18%|█▊        | 4760/25880 [1:00:01<4:11:47,  1.40it/s]
1|4761|Loss: 0.8867462873458862:  18%|█▊        | 4760/25880 [1:00:02<4:11:47,  1.40it/s]
1|4761|Loss: 0.8867462873458862:  18%|█▊        | 4761/25880 [1:00:02<3:58:19,  1.48it/s]
1|4762|Loss: 0.8563405275344849:  18%|█▊        | 4761/25880 [1:00:02<3:58:19,  1.48it/s]
1|4762|Loss: 0.8563405275344849:  18%|█▊        | 4762/25880 [1:00:03<4:11:56,  1.40it/s]
1|4763|Loss: 0.797248125076294:  18%|█▊        | 4762/25880 [1:00:03<4:11:56,  1.40it/s] 
1|4763|Loss: 0.797248125076294:  18%|█▊        | 4763/25880 [1:00:03<4:33:22,  1.29it/s]
1|4764|Loss: 0.8599445223808289:  18%|█▊        | 4763/25880 [1:00:04<4:33:22,  1.29it/s]
1|4764|Loss: 0.8599445223808289:  18%|█▊        | 4764/25880 [1:00:04<4:23:07,  1.34it/s]
1|4765|Loss: 0.8620521426200867:  18%|█▊        | 4764/25880 [1:00:05<4:23:07,  1.34it/s]
1|4765|Loss: 0.8620521426200867:  18%|█▊        | 4765/25880 [1:00:05<4:12:05,  1.40it/s]
1|4766|Loss: 0.8435190320014954:  18%|█▊        | 4765/25880 [1:00:05<4:12:05,  1.40it/s]
1|4766|Loss: 0.8435190320014954:  18%|█▊        | 4766/25880 [1:00:05<4:04:40,  1.44it/s]
1|4767|Loss: 0.8843970894813538:  18%|█▊        | 4766/25880 [1:00:06<4:04:40,  1.44it/s]
1|4767|Loss: 0.8843970894813538:  18%|█▊        | 4767/25880 [1:00:06<4:03:50,  1.44it/s]
1|4768|Loss: 0.8495258092880249:  18%|█▊        | 4767/25880 [1:00:07<4:03:50,  1.44it/s]
1|4768|Loss: 0.8495258092880249:  18%|█▊        | 4768/25880 [1:00:07<4:13:04,  1.39it/s]
1|4769|Loss: 0.9983221888542175:  18%|█▊        | 4768/25880 [1:00:07<4:13:04,  1.39it/s]
1|4769|Loss: 0.9983221888542175:  18%|█▊        | 4769/25880 [1:00:08<4:25:43,  1.32it/s]
1|4770|Loss: 0.960917592048645:  18%|█▊        | 4769/25880 [1:00:08<4:25:43,  1.32it/s] 
1|4770|Loss: 0.960917592048645:  18%|█▊        | 4770/25880 [1:00:09<4:31:10,  1.30it/s]
1|4771|Loss: 1.009873867034912:  18%|█▊        | 4770/25880 [1:00:09<4:31:10,  1.30it/s]
1|4771|Loss: 1.009873867034912:  18%|█▊        | 4771/25880 [1:00:09<4:25:38,  1.32it/s]
1|4772|Loss: 0.6911853551864624:  18%|█▊        | 4771/25880 [1:00:10<4:25:38,  1.32it/s]
1|4772|Loss: 0.6911853551864624:  18%|█▊        | 4772/25880 [1:00:10<4:09:06,  1.41it/s]
1|4773|Loss: 0.8475397825241089:  18%|█▊        | 4772/25880 [1:00:10<4:09:06,  1.41it/s]
1|4773|Loss: 0.8475397825241089:  18%|█▊        | 4773/25880 [1:00:11<4:13:45,  1.39it/s]
1|4774|Loss: 0.9424055814743042:  18%|█▊        | 4773/25880 [1:00:11<4:13:45,  1.39it/s]
1|4774|Loss: 0.9424055814743042:  18%|█▊        | 4774/25880 [1:00:11<4:15:48,  1.38it/s]
1|4775|Loss: 0.9616134166717529:  18%|█▊        | 4774/25880 [1:00:12<4:15:48,  1.38it/s]
1|4775|Loss: 0.9616134166717529:  18%|█▊        | 4775/25880 [1:00:12<4:08:54,  1.41it/s]
1|4776|Loss: 0.8884593844413757:  18%|█▊        | 4775/25880 [1:00:12<4:08:54,  1.41it/s]
1|4776|Loss: 0.8884593844413757:  18%|█▊        | 4776/25880 [1:00:13<4:10:00,  1.41it/s]
1|4777|Loss: 0.8017579317092896:  18%|█▊        | 4776/25880 [1:00:13<4:10:00,  1.41it/s]
1|4777|Loss: 0.8017579317092896:  18%|█▊        | 4777/25880 [1:00:13<4:11:59,  1.40it/s]
1|4778|Loss: 0.8114594221115112:  18%|█▊        | 4777/25880 [1:00:14<4:11:59,  1.40it/s]
1|4778|Loss: 0.8114594221115112:  18%|█▊        | 4778/25880 [1:00:14<4:33:21,  1.29it/s]
1|4779|Loss: 0.8705015778541565:  18%|█▊        | 4778/25880 [1:00:15<4:33:21,  1.29it/s]
1|4779|Loss: 0.8705015778541565:  18%|█▊        | 4779/25880 [1:00:15<4:30:31,  1.30it/s]
1|4780|Loss: 0.8709498643875122:  18%|█▊        | 4779/25880 [1:00:16<4:30:31,  1.30it/s]
1|4780|Loss: 0.8709498643875122:  18%|█▊        | 4780/25880 [1:00:16<4:26:04,  1.32it/s]
1|4781|Loss: 0.8884946703910828:  18%|█▊        | 4780/25880 [1:00:16<4:26:04,  1.32it/s]
1|4781|Loss: 0.8884946703910828:  18%|█▊        | 4781/25880 [1:00:16<3:59:47,  1.47it/s]
1|4782|Loss: 0.8574488759040833:  18%|█▊        | 4781/25880 [1:00:17<3:59:47,  1.47it/s]
1|4782|Loss: 0.8574488759040833:  18%|█▊        | 4782/25880 [1:00:17<3:48:39,  1.54it/s]
1|4783|Loss: 0.8227661848068237:  18%|█▊        | 4782/25880 [1:00:17<3:48:39,  1.54it/s]
1|4783|Loss: 0.8227661848068237:  18%|█▊        | 4783/25880 [1:00:18<3:41:51,  1.58it/s]
1|4784|Loss: 0.7287001609802246:  18%|█▊        | 4783/25880 [1:00:18<3:41:51,  1.58it/s]
1|4784|Loss: 0.7287001609802246:  18%|█▊        | 4784/25880 [1:00:18<4:10:20,  1.40it/s]
1|4785|Loss: 0.8639156222343445:  18%|█▊        | 4784/25880 [1:00:19<4:10:20,  1.40it/s]
1|4785|Loss: 0.8639156222343445:  18%|█▊        | 4785/25880 [1:00:19<4:16:15,  1.37it/s]
1|4786|Loss: 0.9540589451789856:  18%|█▊        | 4785/25880 [1:00:20<4:16:15,  1.37it/s]
1|4786|Loss: 0.9540589451789856:  18%|█▊        | 4786/25880 [1:00:20<4:27:49,  1.31it/s]
1|4787|Loss: 0.868912398815155:  18%|█▊        | 4786/25880 [1:00:20<4:27:49,  1.31it/s] 
1|4787|Loss: 0.868912398815155:  18%|█▊        | 4787/25880 [1:00:21<4:18:05,  1.36it/s]
1|4788|Loss: 0.9067369699478149:  18%|█▊        | 4787/25880 [1:00:21<4:18:05,  1.36it/s]
1|4788|Loss: 0.9067369699478149:  19%|█▊        | 4788/25880 [1:00:21<4:16:51,  1.37it/s]
1|4789|Loss: 0.9356644153594971:  19%|█▊        | 4788/25880 [1:00:22<4:16:51,  1.37it/s]
1|4789|Loss: 0.9356644153594971:  19%|█▊        | 4789/25880 [1:00:22<4:29:37,  1.30it/s]
1|4790|Loss: 0.8476611971855164:  19%|█▊        | 4789/25880 [1:00:23<4:29:37,  1.30it/s]
1|4790|Loss: 0.8476611971855164:  19%|█▊        | 4790/25880 [1:00:23<4:27:40,  1.31it/s]
1|4791|Loss: 0.8496290445327759:  19%|█▊        | 4790/25880 [1:00:23<4:27:40,  1.31it/s]
1|4791|Loss: 0.8496290445327759:  19%|█▊        | 4791/25880 [1:00:24<4:21:44,  1.34it/s]
1|4792|Loss: 0.7091267108917236:  19%|█▊        | 4791/25880 [1:00:24<4:21:44,  1.34it/s]
1|4792|Loss: 0.7091267108917236:  19%|█▊        | 4792/25880 [1:00:24<4:19:09,  1.36it/s]
1|4793|Loss: 0.9029849171638489:  19%|█▊        | 4792/25880 [1:00:25<4:19:09,  1.36it/s]
1|4793|Loss: 0.9029849171638489:  19%|█▊        | 4793/25880 [1:00:25<4:18:11,  1.36it/s]
1|4794|Loss: 0.8643877506256104:  19%|█▊        | 4793/25880 [1:00:26<4:18:11,  1.36it/s]
1|4794|Loss: 0.8643877506256104:  19%|█▊        | 4794/25880 [1:00:26<4:17:57,  1.36it/s]
1|4795|Loss: 0.9543259143829346:  19%|█▊        | 4794/25880 [1:00:26<4:17:57,  1.36it/s]
1|4795|Loss: 0.9543259143829346:  19%|█▊        | 4795/25880 [1:00:27<4:25:22,  1.32it/s]
1|4796|Loss: 0.8098605275154114:  19%|█▊        | 4795/25880 [1:00:27<4:25:22,  1.32it/s]
1|4796|Loss: 0.8098605275154114:  19%|█▊        | 4796/25880 [1:00:28<4:37:00,  1.27it/s]
1|4797|Loss: 0.8767647743225098:  19%|█▊        | 4796/25880 [1:00:28<4:37:00,  1.27it/s]
1|4797|Loss: 0.8767647743225098:  19%|█▊        | 4797/25880 [1:00:28<4:27:15,  1.31it/s]
1|4798|Loss: 0.8023800253868103:  19%|█▊        | 4797/25880 [1:00:29<4:27:15,  1.31it/s]
1|4798|Loss: 0.8023800253868103:  19%|█▊        | 4798/25880 [1:00:29<4:12:45,  1.39it/s]
1|4799|Loss: 0.8887622952461243:  19%|█▊        | 4798/25880 [1:00:29<4:12:45,  1.39it/s]
1|4799|Loss: 0.8887622952461243:  19%|█▊        | 4799/25880 [1:00:30<4:21:36,  1.34it/s]
1|4800|Loss: 0.9554596543312073:  19%|█▊        | 4799/25880 [1:00:30<4:21:36,  1.34it/s]
1|4800|Loss: 0.9554596543312073:  19%|█▊        | 4800/25880 [1:00:30<4:10:14,  1.40it/s]
1|4801|Loss: 0.7652417421340942:  19%|█▊        | 4800/25880 [1:00:31<4:10:14,  1.40it/s]
1|4801|Loss: 0.7652417421340942:  19%|█▊        | 4801/25880 [1:00:31<4:10:20,  1.40it/s]
1|4802|Loss: 0.8831833600997925:  19%|█▊        | 4801/25880 [1:00:31<4:10:20,  1.40it/s]
1|4802|Loss: 0.8831833600997925:  19%|█▊        | 4802/25880 [1:00:32<4:03:50,  1.44it/s]
1|4803|Loss: 0.8239629864692688:  19%|█▊        | 4802/25880 [1:00:32<4:03:50,  1.44it/s]
1|4803|Loss: 0.8239629864692688:  19%|█▊        | 4803/25880 [1:00:32<4:07:05,  1.42it/s]
1|4804|Loss: 0.8687646985054016:  19%|█▊        | 4803/25880 [1:00:33<4:07:05,  1.42it/s]
1|4804|Loss: 0.8687646985054016:  19%|█▊        | 4804/25880 [1:00:33<4:01:54,  1.45it/s]
1|4805|Loss: 0.8603848218917847:  19%|█▊        | 4804/25880 [1:00:34<4:01:54,  1.45it/s]
1|4805|Loss: 0.8603848218917847:  19%|█▊        | 4805/25880 [1:00:34<4:13:46,  1.38it/s]
1|4806|Loss: 0.8857833743095398:  19%|█▊        | 4805/25880 [1:00:34<4:13:46,  1.38it/s]
1|4806|Loss: 0.8857833743095398:  19%|█▊        | 4806/25880 [1:00:35<4:15:55,  1.37it/s]
1|4807|Loss: 0.8595065474510193:  19%|█▊        | 4806/25880 [1:00:35<4:15:55,  1.37it/s]
1|4807|Loss: 0.8595065474510193:  19%|█▊        | 4807/25880 [1:00:35<4:00:57,  1.46it/s]
1|4808|Loss: 0.8680440783500671:  19%|█▊        | 4807/25880 [1:00:36<4:00:57,  1.46it/s]
1|4808|Loss: 0.8680440783500671:  19%|█▊        | 4808/25880 [1:00:36<4:03:20,  1.44it/s]
1|4809|Loss: 0.7802872061729431:  19%|█▊        | 4808/25880 [1:00:36<4:03:20,  1.44it/s]
1|4809|Loss: 0.7802872061729431:  19%|█▊        | 4809/25880 [1:00:37<3:58:54,  1.47it/s]
1|4810|Loss: 0.7191557288169861:  19%|█▊        | 4809/25880 [1:00:37<3:58:54,  1.47it/s]
1|4810|Loss: 0.7191557288169861:  19%|█▊        | 4810/25880 [1:00:37<4:10:11,  1.40it/s]
1|4811|Loss: 0.8270753622055054:  19%|█▊        | 4810/25880 [1:00:38<4:10:11,  1.40it/s]
1|4811|Loss: 0.8270753622055054:  19%|█▊        | 4811/25880 [1:00:38<4:24:53,  1.33it/s]
1|4812|Loss: 0.858726441860199:  19%|█▊        | 4811/25880 [1:00:39<4:24:53,  1.33it/s] 
1|4812|Loss: 0.858726441860199:  19%|█▊        | 4812/25880 [1:00:39<4:29:56,  1.30it/s]
1|4813|Loss: 0.7800408005714417:  19%|█▊        | 4812/25880 [1:00:39<4:29:56,  1.30it/s]
1|4813|Loss: 0.7800408005714417:  19%|█▊        | 4813/25880 [1:00:40<4:27:37,  1.31it/s]
1|4814|Loss: 0.9065272808074951:  19%|█▊        | 4813/25880 [1:00:40<4:27:37,  1.31it/s]
1|4814|Loss: 0.9065272808074951:  19%|█▊        | 4814/25880 [1:00:41<4:21:34,  1.34it/s]
1|4815|Loss: 0.7324985265731812:  19%|█▊        | 4814/25880 [1:00:41<4:21:34,  1.34it/s]
1|4815|Loss: 0.7324985265731812:  19%|█▊        | 4815/25880 [1:00:41<4:21:24,  1.34it/s]
1|4816|Loss: 0.8574498891830444:  19%|█▊        | 4815/25880 [1:00:42<4:21:24,  1.34it/s]
1|4816|Loss: 0.8574498891830444:  19%|█▊        | 4816/25880 [1:00:42<4:20:40,  1.35it/s]
1|4817|Loss: 0.7379197478294373:  19%|█▊        | 4816/25880 [1:00:42<4:20:40,  1.35it/s]
1|4817|Loss: 0.7379197478294373:  19%|█▊        | 4817/25880 [1:00:43<4:31:40,  1.29it/s]
1|4818|Loss: 0.9591225981712341:  19%|█▊        | 4817/25880 [1:00:43<4:31:40,  1.29it/s]
1|4818|Loss: 0.9591225981712341:  19%|█▊        | 4818/25880 [1:00:43<4:07:59,  1.42it/s]
1|4819|Loss: 0.7491946220397949:  19%|█▊        | 4818/25880 [1:00:44<4:07:59,  1.42it/s]
1|4819|Loss: 0.7491946220397949:  19%|█▊        | 4819/25880 [1:00:44<4:00:59,  1.46it/s]
1|4820|Loss: 0.7487174868583679:  19%|█▊        | 4819/25880 [1:00:44<4:00:59,  1.46it/s]
1|4820|Loss: 0.7487174868583679:  19%|█▊        | 4820/25880 [1:00:45<4:11:20,  1.40it/s]
1|4821|Loss: 0.8272965550422668:  19%|█▊        | 4820/25880 [1:00:45<4:11:20,  1.40it/s]
1|4821|Loss: 0.8272965550422668:  19%|█▊        | 4821/25880 [1:00:46<4:19:16,  1.35it/s]
1|4822|Loss: 0.7878948450088501:  19%|█▊        | 4821/25880 [1:00:46<4:19:16,  1.35it/s]
1|4822|Loss: 0.7878948450088501:  19%|█▊        | 4822/25880 [1:00:46<4:19:48,  1.35it/s]
1|4823|Loss: 0.7815434336662292:  19%|█▊        | 4822/25880 [1:00:47<4:19:48,  1.35it/s]
1|4823|Loss: 0.7815434336662292:  19%|█▊        | 4823/25880 [1:00:47<3:54:42,  1.50it/s]
1|4824|Loss: 0.9317102432250977:  19%|█▊        | 4823/25880 [1:00:47<3:54:42,  1.50it/s]
1|4824|Loss: 0.9317102432250977:  19%|█▊        | 4824/25880 [1:00:48<3:55:13,  1.49it/s]
1|4825|Loss: 0.92319256067276:  19%|█▊        | 4824/25880 [1:00:48<3:55:13,  1.49it/s]  
1|4825|Loss: 0.92319256067276:  19%|█▊        | 4825/25880 [1:00:48<4:11:31,  1.40it/s]
1|4826|Loss: 0.957200288772583:  19%|█▊        | 4825/25880 [1:00:49<4:11:31,  1.40it/s]
1|4826|Loss: 0.957200288772583:  19%|█▊        | 4826/25880 [1:00:49<4:13:16,  1.39it/s]
1|4827|Loss: 0.9147486090660095:  19%|█▊        | 4826/25880 [1:00:50<4:13:16,  1.39it/s]
1|4827|Loss: 0.9147486090660095:  19%|█▊        | 4827/25880 [1:00:50<4:24:13,  1.33it/s]
1|4828|Loss: 0.7656790018081665:  19%|█▊        | 4827/25880 [1:00:50<4:24:13,  1.33it/s]
1|4828|Loss: 0.7656790018081665:  19%|█▊        | 4828/25880 [1:00:51<4:08:41,  1.41it/s]
1|4829|Loss: 0.8222243189811707:  19%|█▊        | 4828/25880 [1:00:51<4:08:41,  1.41it/s]
1|4829|Loss: 0.8222243189811707:  19%|█▊        | 4829/25880 [1:00:51<3:43:30,  1.57it/s]
1|4830|Loss: 0.8161026239395142:  19%|█▊        | 4829/25880 [1:00:51<3:43:30,  1.57it/s]
1|4830|Loss: 0.8161026239395142:  19%|█▊        | 4830/25880 [1:00:52<3:36:10,  1.62it/s]
1|4831|Loss: 0.7786086797714233:  19%|█▊        | 4830/25880 [1:00:52<3:36:10,  1.62it/s]
1|4831|Loss: 0.7786086797714233:  19%|█▊        | 4831/25880 [1:00:52<3:49:56,  1.53it/s]
1|4832|Loss: 0.9781266450881958:  19%|█▊        | 4831/25880 [1:00:53<3:49:56,  1.53it/s]
1|4832|Loss: 0.9781266450881958:  19%|█▊        | 4832/25880 [1:00:53<4:12:52,  1.39it/s]
1|4833|Loss: 0.7480066418647766:  19%|█▊        | 4832/25880 [1:00:54<4:12:52,  1.39it/s]
1|4833|Loss: 0.7480066418647766:  19%|█▊        | 4833/25880 [1:00:54<4:18:10,  1.36it/s]
1|4834|Loss: 0.8977090120315552:  19%|█▊        | 4833/25880 [1:00:54<4:18:10,  1.36it/s]
1|4834|Loss: 0.8977090120315552:  19%|█▊        | 4834/25880 [1:00:55<4:17:32,  1.36it/s]
1|4835|Loss: 0.9383245706558228:  19%|█▊        | 4834/25880 [1:00:55<4:17:32,  1.36it/s]
1|4835|Loss: 0.9383245706558228:  19%|█▊        | 4835/25880 [1:00:55<4:18:17,  1.36it/s]
1|4836|Loss: 0.7886765599250793:  19%|█▊        | 4835/25880 [1:00:56<4:18:17,  1.36it/s]
1|4836|Loss: 0.7886765599250793:  19%|█▊        | 4836/25880 [1:00:56<4:18:01,  1.36it/s]
1|4837|Loss: 0.9031452536582947:  19%|█▊        | 4836/25880 [1:00:57<4:18:01,  1.36it/s]
1|4837|Loss: 0.9031452536582947:  19%|█▊        | 4837/25880 [1:00:57<4:37:07,  1.27it/s]
1|4838|Loss: 0.8601362705230713:  19%|█▊        | 4837/25880 [1:00:58<4:37:07,  1.27it/s]
1|4838|Loss: 0.8601362705230713:  19%|█▊        | 4838/25880 [1:00:58<4:45:12,  1.23it/s]
1|4839|Loss: 0.957244873046875:  19%|█▊        | 4838/25880 [1:00:58<4:45:12,  1.23it/s] 
1|4839|Loss: 0.957244873046875:  19%|█▊        | 4839/25880 [1:00:59<4:43:30,  1.24it/s]
1|4840|Loss: 0.9190101623535156:  19%|█▊        | 4839/25880 [1:00:59<4:43:30,  1.24it/s]
1|4840|Loss: 0.9190101623535156:  19%|█▊        | 4840/25880 [1:01:00<4:45:34,  1.23it/s]
1|4841|Loss: 0.8569311499595642:  19%|█▊        | 4840/25880 [1:01:00<4:45:34,  1.23it/s]
1|4841|Loss: 0.8569311499595642:  19%|█▊        | 4841/25880 [1:01:00<4:43:32,  1.24it/s]
1|4842|Loss: 0.7980767488479614:  19%|█▊        | 4841/25880 [1:01:01<4:43:32,  1.24it/s]
1|4842|Loss: 0.7980767488479614:  19%|█▊        | 4842/25880 [1:01:01<4:48:54,  1.21it/s]
1|4843|Loss: 0.6567891836166382:  19%|█▊        | 4842/25880 [1:01:02<4:48:54,  1.21it/s]
1|4843|Loss: 0.6567891836166382:  19%|█▊        | 4843/25880 [1:01:02<4:29:44,  1.30it/s]
1|4844|Loss: 0.8587514758110046:  19%|█▊        | 4843/25880 [1:01:02<4:29:44,  1.30it/s]
1|4844|Loss: 0.8587514758110046:  19%|█▊        | 4844/25880 [1:01:03<4:30:19,  1.30it/s]
1|4845|Loss: 0.7332597970962524:  19%|█▊        | 4844/25880 [1:01:03<4:30:19,  1.30it/s]
1|4845|Loss: 0.7332597970962524:  19%|█▊        | 4845/25880 [1:01:03<4:20:19,  1.35it/s]
1|4846|Loss: 0.9308812618255615:  19%|█▊        | 4845/25880 [1:01:04<4:20:19,  1.35it/s]
1|4846|Loss: 0.9308812618255615:  19%|█▊        | 4846/25880 [1:01:04<4:14:42,  1.38it/s]
1|4847|Loss: 0.7600216269493103:  19%|█▊        | 4846/25880 [1:01:04<4:14:42,  1.38it/s]
1|4847|Loss: 0.7600216269493103:  19%|█▊        | 4847/25880 [1:01:05<4:24:31,  1.33it/s]
1|4848|Loss: 0.8171555995941162:  19%|█▊        | 4847/25880 [1:01:05<4:24:31,  1.33it/s]
1|4848|Loss: 0.8171555995941162:  19%|█▊        | 4848/25880 [1:01:06<4:24:51,  1.32it/s]
1|4849|Loss: 0.795647382736206:  19%|█▊        | 4848/25880 [1:01:06<4:24:51,  1.32it/s] 
1|4849|Loss: 0.795647382736206:  19%|█▊        | 4849/25880 [1:01:07<4:43:29,  1.24it/s]
1|4850|Loss: 0.789943516254425:  19%|█▊        | 4849/25880 [1:01:07<4:43:29,  1.24it/s]
1|4850|Loss: 0.789943516254425:  19%|█▊        | 4850/25880 [1:01:07<4:42:31,  1.24it/s]
1|4851|Loss: 0.9692203402519226:  19%|█▊        | 4850/25880 [1:01:08<4:42:31,  1.24it/s]
1|4851|Loss: 0.9692203402519226:  19%|█▊        | 4851/25880 [1:01:08<4:35:06,  1.27it/s]
1|4852|Loss: 0.883518397808075:  19%|█▊        | 4851/25880 [1:01:08<4:35:06,  1.27it/s] 
1|4852|Loss: 0.883518397808075:  19%|█▊        | 4852/25880 [1:01:09<4:33:32,  1.28it/s]
1|4853|Loss: 0.8011499643325806:  19%|█▊        | 4852/25880 [1:01:09<4:33:32,  1.28it/s]
1|4853|Loss: 0.8011499643325806:  19%|█▉        | 4853/25880 [1:01:09<4:01:03,  1.45it/s]
1|4854|Loss: 0.9142338633537292:  19%|█▉        | 4853/25880 [1:01:10<4:01:03,  1.45it/s]
1|4854|Loss: 0.9142338633537292:  19%|█▉        | 4854/25880 [1:01:10<3:57:28,  1.48it/s]
1|4855|Loss: 0.8110845685005188:  19%|█▉        | 4854/25880 [1:01:10<3:57:28,  1.48it/s]
1|4855|Loss: 0.8110845685005188:  19%|█▉        | 4855/25880 [1:01:11<3:53:28,  1.50it/s]
1|4856|Loss: 0.9394344091415405:  19%|█▉        | 4855/25880 [1:01:11<3:53:28,  1.50it/s]
1|4856|Loss: 0.9394344091415405:  19%|█▉        | 4856/25880 [1:01:11<3:48:13,  1.54it/s]
1|4857|Loss: 0.8124428391456604:  19%|█▉        | 4856/25880 [1:01:12<3:48:13,  1.54it/s]
1|4857|Loss: 0.8124428391456604:  19%|█▉        | 4857/25880 [1:01:12<3:55:09,  1.49it/s]
1|4858|Loss: 0.8282331228256226:  19%|█▉        | 4857/25880 [1:01:12<3:55:09,  1.49it/s]
1|4858|Loss: 0.8282331228256226:  19%|█▉        | 4858/25880 [1:01:13<4:13:45,  1.38it/s]
1|4859|Loss: 0.7129679918289185:  19%|█▉        | 4858/25880 [1:01:13<4:13:45,  1.38it/s]
1|4859|Loss: 0.7129679918289185:  19%|█▉        | 4859/25880 [1:01:13<4:10:30,  1.40it/s]
1|4860|Loss: 0.7708824276924133:  19%|█▉        | 4859/25880 [1:01:14<4:10:30,  1.40it/s]
1|4860|Loss: 0.7708824276924133:  19%|█▉        | 4860/25880 [1:01:14<3:58:38,  1.47it/s]
1|4861|Loss: 0.9720467925071716:  19%|█▉        | 4860/25880 [1:01:14<3:58:38,  1.47it/s]
1|4861|Loss: 0.9720467925071716:  19%|█▉        | 4861/25880 [1:01:15<4:11:19,  1.39it/s]
1|4862|Loss: 0.8130815625190735:  19%|█▉        | 4861/25880 [1:01:15<4:11:19,  1.39it/s]
1|4862|Loss: 0.8130815625190735:  19%|█▉        | 4862/25880 [1:01:16<4:08:01,  1.41it/s]
1|4863|Loss: 0.937444269657135:  19%|█▉        | 4862/25880 [1:01:16<4:08:01,  1.41it/s] 
1|4863|Loss: 0.937444269657135:  19%|█▉        | 4863/25880 [1:01:16<4:08:25,  1.41it/s]
1|4864|Loss: 0.9385144710540771:  19%|█▉        | 4863/25880 [1:01:17<4:08:25,  1.41it/s]
1|4864|Loss: 0.9385144710540771:  19%|█▉        | 4864/25880 [1:01:17<4:08:44,  1.41it/s]
1|4865|Loss: 0.8229742646217346:  19%|█▉        | 4864/25880 [1:01:17<4:08:44,  1.41it/s]
1|4865|Loss: 0.8229742646217346:  19%|█▉        | 4865/25880 [1:01:18<4:09:34,  1.40it/s]
1|4866|Loss: 0.8139829039573669:  19%|█▉        | 4865/25880 [1:01:18<4:09:34,  1.40it/s]
1|4866|Loss: 0.8139829039573669:  19%|█▉        | 4866/25880 [1:01:18<4:12:09,  1.39it/s]
1|4867|Loss: 0.8005139827728271:  19%|█▉        | 4866/25880 [1:01:19<4:12:09,  1.39it/s]
1|4867|Loss: 0.8005139827728271:  19%|█▉        | 4867/25880 [1:01:19<4:01:51,  1.45it/s]
1|4868|Loss: 0.9072750210762024:  19%|█▉        | 4867/25880 [1:01:19<4:01:51,  1.45it/s]
1|4868|Loss: 0.9072750210762024:  19%|█▉        | 4868/25880 [1:01:20<4:04:24,  1.43it/s]
1|4869|Loss: 0.8250428438186646:  19%|█▉        | 4868/25880 [1:01:20<4:04:24,  1.43it/s]
1|4869|Loss: 0.8250428438186646:  19%|█▉        | 4869/25880 [1:01:20<4:09:16,  1.40it/s]
1|4870|Loss: 0.9047385454177856:  19%|█▉        | 4869/25880 [1:01:21<4:09:16,  1.40it/s]
1|4870|Loss: 0.9047385454177856:  19%|█▉        | 4870/25880 [1:01:21<3:51:07,  1.52it/s]
1|4871|Loss: 0.7910355925559998:  19%|█▉        | 4870/25880 [1:01:21<3:51:07,  1.52it/s]
1|4871|Loss: 0.7910355925559998:  19%|█▉        | 4871/25880 [1:01:22<3:58:21,  1.47it/s]
1|4872|Loss: 0.8880782723426819:  19%|█▉        | 4871/25880 [1:01:22<3:58:21,  1.47it/s]
1|4872|Loss: 0.8880782723426819:  19%|█▉        | 4872/25880 [1:01:22<3:50:42,  1.52it/s]
1|4873|Loss: 0.8536983132362366:  19%|█▉        | 4872/25880 [1:01:23<3:50:42,  1.52it/s]
1|4873|Loss: 0.8536983132362366:  19%|█▉        | 4873/25880 [1:01:23<3:44:06,  1.56it/s]
1|4874|Loss: 0.7494419813156128:  19%|█▉        | 4873/25880 [1:01:23<3:44:06,  1.56it/s]
1|4874|Loss: 0.7494419813156128:  19%|█▉        | 4874/25880 [1:01:24<4:01:34,  1.45it/s]
1|4875|Loss: 0.880949079990387:  19%|█▉        | 4874/25880 [1:01:24<4:01:34,  1.45it/s] 
1|4875|Loss: 0.880949079990387:  19%|█▉        | 4875/25880 [1:01:25<4:09:55,  1.40it/s]
1|4876|Loss: 0.9630389213562012:  19%|█▉        | 4875/25880 [1:01:25<4:09:55,  1.40it/s]
1|4876|Loss: 0.9630389213562012:  19%|█▉        | 4876/25880 [1:01:25<4:12:22,  1.39it/s]
1|4877|Loss: 0.8389919400215149:  19%|█▉        | 4876/25880 [1:01:26<4:12:22,  1.39it/s]
1|4877|Loss: 0.8389919400215149:  19%|█▉        | 4877/25880 [1:01:26<4:14:42,  1.37it/s]
1|4878|Loss: 0.791064977645874:  19%|█▉        | 4877/25880 [1:01:27<4:14:42,  1.37it/s] 
1|4878|Loss: 0.791064977645874:  19%|█▉        | 4878/25880 [1:01:27<5:18:14,  1.10it/s]
1|4879|Loss: 0.8829078078269958:  19%|█▉        | 4878/25880 [1:01:28<5:18:14,  1.10it/s]
1|4879|Loss: 0.8829078078269958:  19%|█▉        | 4879/25880 [1:01:28<5:26:02,  1.07it/s]
1|4880|Loss: 0.8246655464172363:  19%|█▉        | 4879/25880 [1:01:29<5:26:02,  1.07it/s]
1|4880|Loss: 0.8246655464172363:  19%|█▉        | 4880/25880 [1:01:29<4:47:00,  1.22it/s]
1|4881|Loss: 0.9437110424041748:  19%|█▉        | 4880/25880 [1:01:29<4:47:00,  1.22it/s]
1|4881|Loss: 0.9437110424041748:  19%|█▉        | 4881/25880 [1:01:30<4:34:12,  1.28it/s]
1|4882|Loss: 0.8903967142105103:  19%|█▉        | 4881/25880 [1:01:30<4:34:12,  1.28it/s]
1|4882|Loss: 0.8903967142105103:  19%|█▉        | 4882/25880 [1:01:30<4:30:54,  1.29it/s]
1|4883|Loss: 1.007594108581543:  19%|█▉        | 4882/25880 [1:01:31<4:30:54,  1.29it/s] 
1|4883|Loss: 1.007594108581543:  19%|█▉        | 4883/25880 [1:01:31<4:27:24,  1.31it/s]
1|4884|Loss: 0.7952988147735596:  19%|█▉        | 4883/25880 [1:01:32<4:27:24,  1.31it/s]
1|4884|Loss: 0.7952988147735596:  19%|█▉        | 4884/25880 [1:01:32<4:30:31,  1.29it/s]
1|4885|Loss: 0.846515953540802:  19%|█▉        | 4884/25880 [1:01:32<4:30:31,  1.29it/s] 
1|4885|Loss: 0.846515953540802:  19%|█▉        | 4885/25880 [1:01:33<4:32:40,  1.28it/s]
1|4886|Loss: 0.7625415325164795:  19%|█▉        | 4885/25880 [1:01:33<4:32:40,  1.28it/s]
1|4886|Loss: 0.7625415325164795:  19%|█▉        | 4886/25880 [1:01:33<4:21:05,  1.34it/s]
1|4887|Loss: 0.947143018245697:  19%|█▉        | 4886/25880 [1:01:34<4:21:05,  1.34it/s] 
1|4887|Loss: 0.947143018245697:  19%|█▉        | 4887/25880 [1:01:34<4:08:04,  1.41it/s]
1|4888|Loss: 0.8636601567268372:  19%|█▉        | 4887/25880 [1:01:34<4:08:04,  1.41it/s]
1|4888|Loss: 0.8636601567268372:  19%|█▉        | 4888/25880 [1:01:35<4:06:09,  1.42it/s]
1|4889|Loss: 0.9351613521575928:  19%|█▉        | 4888/25880 [1:01:35<4:06:09,  1.42it/s]
1|4889|Loss: 0.9351613521575928:  19%|█▉        | 4889/25880 [1:01:35<3:58:37,  1.47it/s]
1|4890|Loss: 0.8801299333572388:  19%|█▉        | 4889/25880 [1:01:36<3:58:37,  1.47it/s]
1|4890|Loss: 0.8801299333572388:  19%|█▉        | 4890/25880 [1:01:36<4:09:08,  1.40it/s]
1|4891|Loss: 0.9630773663520813:  19%|█▉        | 4890/25880 [1:01:36<4:09:08,  1.40it/s]
1|4891|Loss: 0.9630773663520813:  19%|█▉        | 4891/25880 [1:01:37<4:03:39,  1.44it/s]
1|4892|Loss: 0.778509259223938:  19%|█▉        | 4891/25880 [1:01:37<4:03:39,  1.44it/s] 
1|4892|Loss: 0.778509259223938:  19%|█▉        | 4892/25880 [1:01:38<4:13:27,  1.38it/s]
1|4893|Loss: 0.9548396468162537:  19%|█▉        | 4892/25880 [1:01:38<4:13:27,  1.38it/s]
1|4893|Loss: 0.9548396468162537:  19%|█▉        | 4893/25880 [1:01:38<4:21:34,  1.34it/s]
1|4894|Loss: 0.8080660700798035:  19%|█▉        | 4893/25880 [1:01:39<4:21:34,  1.34it/s]
1|4894|Loss: 0.8080660700798035:  19%|█▉        | 4894/25880 [1:01:39<4:18:46,  1.35it/s]
1|4895|Loss: 0.7632570266723633:  19%|█▉        | 4894/25880 [1:01:39<4:18:46,  1.35it/s]
1|4895|Loss: 0.7632570266723633:  19%|█▉        | 4895/25880 [1:01:40<4:29:33,  1.30it/s]
1|4896|Loss: 0.908126950263977:  19%|█▉        | 4895/25880 [1:01:40<4:29:33,  1.30it/s] 
1|4896|Loss: 0.908126950263977:  19%|█▉        | 4896/25880 [1:01:41<4:27:10,  1.31it/s]
1|4897|Loss: 0.857623279094696:  19%|█▉        | 4896/25880 [1:01:41<4:27:10,  1.31it/s]
1|4897|Loss: 0.857623279094696:  19%|█▉        | 4897/25880 [1:01:41<4:15:17,  1.37it/s]
1|4898|Loss: 0.9603256583213806:  19%|█▉        | 4897/25880 [1:01:42<4:15:17,  1.37it/s]
1|4898|Loss: 0.9603256583213806:  19%|█▉        | 4898/25880 [1:01:42<4:17:36,  1.36it/s]
1|4899|Loss: 0.827361524105072:  19%|█▉        | 4898/25880 [1:01:43<4:17:36,  1.36it/s] 
1|4899|Loss: 0.827361524105072:  19%|█▉        | 4899/25880 [1:01:43<4:30:00,  1.30it/s]
1|4900|Loss: 0.9014012813568115:  19%|█▉        | 4899/25880 [1:01:43<4:30:00,  1.30it/s]
1|4900|Loss: 0.9014012813568115:  19%|█▉        | 4900/25880 [1:01:44<4:41:51,  1.24it/s]
1|4901|Loss: 0.8747917413711548:  19%|█▉        | 4900/25880 [1:01:44<4:41:51,  1.24it/s]
1|4901|Loss: 0.8747917413711548:  19%|█▉        | 4901/25880 [1:01:44<4:25:41,  1.32it/s]
1|4902|Loss: 0.8953279256820679:  19%|█▉        | 4901/25880 [1:01:45<4:25:41,  1.32it/s]
1|4902|Loss: 0.8953279256820679:  19%|█▉        | 4902/25880 [1:01:45<4:28:09,  1.30it/s]
1|4903|Loss: 0.8214168548583984:  19%|█▉        | 4902/25880 [1:01:46<4:28:09,  1.30it/s]
1|4903|Loss: 0.8214168548583984:  19%|█▉        | 4903/25880 [1:01:46<4:34:14,  1.27it/s]
1|4904|Loss: 0.8867865204811096:  19%|█▉        | 4903/25880 [1:01:46<4:34:14,  1.27it/s]
1|4904|Loss: 0.8867865204811096:  19%|█▉        | 4904/25880 [1:01:47<4:36:32,  1.26it/s]
1|4905|Loss: 0.8940199017524719:  19%|█▉        | 4904/25880 [1:01:47<4:36:32,  1.26it/s]
1|4905|Loss: 0.8940199017524719:  19%|█▉        | 4905/25880 [1:01:48<4:31:56,  1.29it/s]
1|4906|Loss: 0.7852427959442139:  19%|█▉        | 4905/25880 [1:01:48<4:31:56,  1.29it/s]
1|4906|Loss: 0.7852427959442139:  19%|█▉        | 4906/25880 [1:01:48<4:28:36,  1.30it/s]
1|4907|Loss: 0.8302972316741943:  19%|█▉        | 4906/25880 [1:01:49<4:28:36,  1.30it/s]
1|4907|Loss: 0.8302972316741943:  19%|█▉        | 4907/25880 [1:01:49<4:23:06,  1.33it/s]
1|4908|Loss: 0.7946165204048157:  19%|█▉        | 4907/25880 [1:01:49<4:23:06,  1.33it/s]
1|4908|Loss: 0.7946165204048157:  19%|█▉        | 4908/25880 [1:01:50<4:17:38,  1.36it/s]
1|4909|Loss: 0.845396101474762:  19%|█▉        | 4908/25880 [1:01:50<4:17:38,  1.36it/s] 
1|4909|Loss: 0.845396101474762:  19%|█▉        | 4909/25880 [1:01:51<4:21:39,  1.34it/s]
1|4910|Loss: 0.7934014201164246:  19%|█▉        | 4909/25880 [1:01:51<4:21:39,  1.34it/s]
1|4910|Loss: 0.7934014201164246:  19%|█▉        | 4910/25880 [1:01:51<4:26:59,  1.31it/s]
1|4911|Loss: 1.0181288719177246:  19%|█▉        | 4910/25880 [1:01:52<4:26:59,  1.31it/s]
1|4911|Loss: 1.0181288719177246:  19%|█▉        | 4911/25880 [1:01:52<4:35:28,  1.27it/s]
1|4912|Loss: 0.8758435249328613:  19%|█▉        | 4911/25880 [1:01:53<4:35:28,  1.27it/s]
1|4912|Loss: 0.8758435249328613:  19%|█▉        | 4912/25880 [1:01:53<4:44:00,  1.23it/s]
1|4913|Loss: 0.8647692203521729:  19%|█▉        | 4912/25880 [1:01:53<4:44:00,  1.23it/s]
1|4913|Loss: 0.8647692203521729:  19%|█▉        | 4913/25880 [1:01:54<4:26:16,  1.31it/s]
1|4914|Loss: 0.9442965984344482:  19%|█▉        | 4913/25880 [1:01:54<4:26:16,  1.31it/s]
1|4914|Loss: 0.9442965984344482:  19%|█▉        | 4914/25880 [1:01:54<4:12:01,  1.39it/s]
1|4915|Loss: 0.9251809120178223:  19%|█▉        | 4914/25880 [1:01:55<4:12:01,  1.39it/s]
1|4915|Loss: 0.9251809120178223:  19%|█▉        | 4915/25880 [1:01:55<4:08:31,  1.41it/s]
1|4916|Loss: 0.889227569103241:  19%|█▉        | 4915/25880 [1:01:55<4:08:31,  1.41it/s] 
1|4916|Loss: 0.889227569103241:  19%|█▉        | 4916/25880 [1:01:56<4:07:16,  1.41it/s]
1|4917|Loss: 0.8673549890518188:  19%|█▉        | 4916/25880 [1:01:56<4:07:16,  1.41it/s]
1|4917|Loss: 0.8673549890518188:  19%|█▉        | 4917/25880 [1:01:57<4:21:56,  1.33it/s]
1|4918|Loss: 0.8725317120552063:  19%|█▉        | 4917/25880 [1:01:57<4:21:56,  1.33it/s]
1|4918|Loss: 0.8725317120552063:  19%|█▉        | 4918/25880 [1:01:57<4:21:14,  1.34it/s]
1|4919|Loss: 0.840949296951294:  19%|█▉        | 4918/25880 [1:01:58<4:21:14,  1.34it/s] 
1|4919|Loss: 0.840949296951294:  19%|█▉        | 4919/25880 [1:01:58<4:31:35,  1.29it/s]
1|4920|Loss: 0.9896819591522217:  19%|█▉        | 4919/25880 [1:01:59<4:31:35,  1.29it/s]
1|4920|Loss: 0.9896819591522217:  19%|█▉        | 4920/25880 [1:01:59<4:28:16,  1.30it/s]
1|4921|Loss: 0.9257938265800476:  19%|█▉        | 4920/25880 [1:01:59<4:28:16,  1.30it/s]
1|4921|Loss: 0.9257938265800476:  19%|█▉        | 4921/25880 [1:02:00<4:11:49,  1.39it/s]
1|4922|Loss: 0.7660405039787292:  19%|█▉        | 4921/25880 [1:02:00<4:11:49,  1.39it/s]
1|4922|Loss: 0.7660405039787292:  19%|█▉        | 4922/25880 [1:02:00<4:21:55,  1.33it/s]
1|4923|Loss: 0.8241786956787109:  19%|█▉        | 4922/25880 [1:02:01<4:21:55,  1.33it/s]
1|4923|Loss: 0.8241786956787109:  19%|█▉        | 4923/25880 [1:02:01<4:16:02,  1.36it/s]
1|4924|Loss: 0.9189009070396423:  19%|█▉        | 4923/25880 [1:02:01<4:16:02,  1.36it/s]
1|4924|Loss: 0.9189009070396423:  19%|█▉        | 4924/25880 [1:02:02<4:22:24,  1.33it/s]
1|4925|Loss: 0.7924596667289734:  19%|█▉        | 4924/25880 [1:02:02<4:22:24,  1.33it/s]
1|4925|Loss: 0.7924596667289734:  19%|█▉        | 4925/25880 [1:02:02<3:53:23,  1.50it/s]
1|4926|Loss: 0.8344756960868835:  19%|█▉        | 4925/25880 [1:02:03<3:53:23,  1.50it/s]
1|4926|Loss: 0.8344756960868835:  19%|█▉        | 4926/25880 [1:02:03<3:38:17,  1.60it/s]
1|4927|Loss: 0.7854300141334534:  19%|█▉        | 4926/25880 [1:02:03<3:38:17,  1.60it/s]
1|4927|Loss: 0.7854300141334534:  19%|█▉        | 4927/25880 [1:02:04<3:53:50,  1.49it/s]
1|4928|Loss: 0.7882834076881409:  19%|█▉        | 4927/25880 [1:02:04<3:53:50,  1.49it/s]
1|4928|Loss: 0.7882834076881409:  19%|█▉        | 4928/25880 [1:02:04<4:02:36,  1.44it/s]
1|4929|Loss: 0.8898196220397949:  19%|█▉        | 4928/25880 [1:02:05<4:02:36,  1.44it/s]
1|4929|Loss: 0.8898196220397949:  19%|█▉        | 4929/25880 [1:02:05<3:58:46,  1.46it/s]
1|4930|Loss: 0.6942786574363708:  19%|█▉        | 4929/25880 [1:02:05<3:58:46,  1.46it/s]
1|4930|Loss: 0.6942786574363708:  19%|█▉        | 4930/25880 [1:02:06<4:02:15,  1.44it/s]
1|4931|Loss: 0.8729915618896484:  19%|█▉        | 4930/25880 [1:02:06<4:02:15,  1.44it/s]
1|4931|Loss: 0.8729915618896484:  19%|█▉        | 4931/25880 [1:02:06<4:10:31,  1.39it/s]
1|4932|Loss: 0.7005200982093811:  19%|█▉        | 4931/25880 [1:02:07<4:10:31,  1.39it/s]
1|4932|Loss: 0.7005200982093811:  19%|█▉        | 4932/25880 [1:02:07<3:49:06,  1.52it/s]
1|4933|Loss: 0.8741415143013:  19%|█▉        | 4932/25880 [1:02:07<3:49:06,  1.52it/s]   
1|4933|Loss: 0.8741415143013:  19%|█▉        | 4933/25880 [1:02:08<3:48:30,  1.53it/s]
1|4934|Loss: 0.798485279083252:  19%|█▉        | 4933/25880 [1:02:08<3:48:30,  1.53it/s]
1|4934|Loss: 0.798485279083252:  19%|█▉        | 4934/25880 [1:02:08<3:45:44,  1.55it/s]
1|4935|Loss: 0.8366642594337463:  19%|█▉        | 4934/25880 [1:02:09<3:45:44,  1.55it/s]
1|4935|Loss: 0.8366642594337463:  19%|█▉        | 4935/25880 [1:02:09<3:43:59,  1.56it/s]
1|4936|Loss: 0.8678963780403137:  19%|█▉        | 4935/25880 [1:02:09<3:43:59,  1.56it/s]
1|4936|Loss: 0.8678963780403137:  19%|█▉        | 4936/25880 [1:02:10<3:49:20,  1.52it/s]
1|4937|Loss: 0.7470411062240601:  19%|█▉        | 4936/25880 [1:02:10<3:49:20,  1.52it/s]
1|4937|Loss: 0.7470411062240601:  19%|█▉        | 4937/25880 [1:02:10<4:06:38,  1.42it/s]
1|4938|Loss: 0.7716812491416931:  19%|█▉        | 4937/25880 [1:02:11<4:06:38,  1.42it/s]
1|4938|Loss: 0.7716812491416931:  19%|█▉        | 4938/25880 [1:02:11<4:20:44,  1.34it/s]
1|4939|Loss: 1.0011142492294312:  19%|█▉        | 4938/25880 [1:02:12<4:20:44,  1.34it/s]
1|4939|Loss: 1.0011142492294312:  19%|█▉        | 4939/25880 [1:02:12<4:21:17,  1.34it/s]
1|4940|Loss: 0.7940889000892639:  19%|█▉        | 4939/25880 [1:02:12<4:21:17,  1.34it/s]
1|4940|Loss: 0.7940889000892639:  19%|█▉        | 4940/25880 [1:02:13<4:32:15,  1.28it/s]
1|4941|Loss: 0.8448065519332886:  19%|█▉        | 4940/25880 [1:02:13<4:32:15,  1.28it/s]
1|4941|Loss: 0.8448065519332886:  19%|█▉        | 4941/25880 [1:02:14<4:21:06,  1.34it/s]
1|4942|Loss: 0.9232844114303589:  19%|█▉        | 4941/25880 [1:02:14<4:21:06,  1.34it/s]
1|4942|Loss: 0.9232844114303589:  19%|█▉        | 4942/25880 [1:02:14<4:32:56,  1.28it/s]
1|4943|Loss: 0.8593487739562988:  19%|█▉        | 4942/25880 [1:02:15<4:32:56,  1.28it/s]
1|4943|Loss: 0.8593487739562988:  19%|█▉        | 4943/25880 [1:02:15<4:37:18,  1.26it/s]
1|4944|Loss: 0.8836836218833923:  19%|█▉        | 4943/25880 [1:02:16<4:37:18,  1.26it/s]
1|4944|Loss: 0.8836836218833923:  19%|█▉        | 4944/25880 [1:02:16<4:38:07,  1.25it/s]
1|4945|Loss: 0.7539618015289307:  19%|█▉        | 4944/25880 [1:02:16<4:38:07,  1.25it/s]
1|4945|Loss: 0.7539618015289307:  19%|█▉        | 4945/25880 [1:02:17<4:24:20,  1.32it/s]
1|4946|Loss: 0.7178212404251099:  19%|█▉        | 4945/25880 [1:02:17<4:24:20,  1.32it/s]
1|4946|Loss: 0.7178212404251099:  19%|█▉        | 4946/25880 [1:02:17<4:24:58,  1.32it/s]
1|4947|Loss: 0.9085463285446167:  19%|█▉        | 4946/25880 [1:02:18<4:24:58,  1.32it/s]
1|4947|Loss: 0.9085463285446167:  19%|█▉        | 4947/25880 [1:02:18<4:20:58,  1.34it/s]
1|4948|Loss: 0.7466036677360535:  19%|█▉        | 4947/25880 [1:02:19<4:20:58,  1.34it/s]
1|4948|Loss: 0.7466036677360535:  19%|█▉        | 4948/25880 [1:02:19<4:17:25,  1.36it/s]
1|4949|Loss: 0.8043819665908813:  19%|█▉        | 4948/25880 [1:02:19<4:17:25,  1.36it/s]
1|4949|Loss: 0.8043819665908813:  19%|█▉        | 4949/25880 [1:02:20<4:06:21,  1.42it/s]
1|4950|Loss: 0.8141398429870605:  19%|█▉        | 4949/25880 [1:02:20<4:06:21,  1.42it/s]
1|4950|Loss: 0.8141398429870605:  19%|█▉        | 4950/25880 [1:02:20<3:58:10,  1.46it/s]
1|4951|Loss: 0.836198091506958:  19%|█▉        | 4950/25880 [1:02:21<3:58:10,  1.46it/s] 
1|4951|Loss: 0.836198091506958:  19%|█▉        | 4951/25880 [1:02:21<4:01:30,  1.44it/s]
1|4952|Loss: 0.8477873206138611:  19%|█▉        | 4951/25880 [1:02:21<4:01:30,  1.44it/s]
1|4952|Loss: 0.8477873206138611:  19%|█▉        | 4952/25880 [1:02:21<3:54:23,  1.49it/s]
1|4953|Loss: 0.924054741859436:  19%|█▉        | 4952/25880 [1:02:22<3:54:23,  1.49it/s] 
1|4953|Loss: 0.924054741859436:  19%|█▉        | 4953/25880 [1:02:22<3:49:02,  1.52it/s]
1|4954|Loss: 0.7685936689376831:  19%|█▉        | 4953/25880 [1:02:22<3:49:02,  1.52it/s]
1|4954|Loss: 0.7685936689376831:  19%|█▉        | 4954/25880 [1:02:23<3:25:51,  1.69it/s]
1|4955|Loss: 0.9430803060531616:  19%|█▉        | 4954/25880 [1:02:23<3:25:51,  1.69it/s]
1|4955|Loss: 0.9430803060531616:  19%|█▉        | 4955/25880 [1:02:23<3:44:16,  1.55it/s]
1|4956|Loss: 0.90247642993927:  19%|█▉        | 4955/25880 [1:02:24<3:44:16,  1.55it/s]  
1|4956|Loss: 0.90247642993927:  19%|█▉        | 4956/25880 [1:02:24<4:11:46,  1.39it/s]
1|4957|Loss: 0.9658086895942688:  19%|█▉        | 4956/25880 [1:02:25<4:11:46,  1.39it/s]
1|4957|Loss: 0.9658086895942688:  19%|█▉        | 4957/25880 [1:02:25<4:24:34,  1.32it/s]
1|4958|Loss: 0.8694605827331543:  19%|█▉        | 4957/25880 [1:02:26<4:24:34,  1.32it/s]
1|4958|Loss: 0.8694605827331543:  19%|█▉        | 4958/25880 [1:02:26<4:31:39,  1.28it/s]
1|4959|Loss: 0.8916707634925842:  19%|█▉        | 4958/25880 [1:02:26<4:31:39,  1.28it/s]
1|4959|Loss: 0.8916707634925842:  19%|█▉        | 4959/25880 [1:02:27<4:48:24,  1.21it/s]
1|4960|Loss: 0.8175431489944458:  19%|█▉        | 4959/25880 [1:02:27<4:48:24,  1.21it/s]
1|4960|Loss: 0.8175431489944458:  19%|█▉        | 4960/25880 [1:02:28<4:40:50,  1.24it/s]
1|4961|Loss: 0.9349948167800903:  19%|█▉        | 4960/25880 [1:02:28<4:40:50,  1.24it/s]
1|4961|Loss: 0.9349948167800903:  19%|█▉        | 4961/25880 [1:02:28<4:08:32,  1.40it/s]
1|4962|Loss: 0.8733989596366882:  19%|█▉        | 4961/25880 [1:02:28<4:08:32,  1.40it/s]
1|4962|Loss: 0.8733989596366882:  19%|█▉        | 4962/25880 [1:02:29<4:15:59,  1.36it/s]
1|4963|Loss: 0.8086855411529541:  19%|█▉        | 4962/25880 [1:02:29<4:15:59,  1.36it/s]
1|4963|Loss: 0.8086855411529541:  19%|█▉        | 4963/25880 [1:02:30<4:29:16,  1.29it/s]
1|4964|Loss: 0.7631397247314453:  19%|█▉        | 4963/25880 [1:02:30<4:29:16,  1.29it/s]
1|4964|Loss: 0.7631397247314453:  19%|█▉        | 4964/25880 [1:02:30<4:16:35,  1.36it/s]
1|4965|Loss: 0.9608464241027832:  19%|█▉        | 4964/25880 [1:02:31<4:16:35,  1.36it/s]
1|4965|Loss: 0.9608464241027832:  19%|█▉        | 4965/25880 [1:02:31<4:12:46,  1.38it/s]
1|4966|Loss: 0.8197744488716125:  19%|█▉        | 4965/25880 [1:02:31<4:12:46,  1.38it/s]
1|4966|Loss: 0.8197744488716125:  19%|█▉        | 4966/25880 [1:02:32<4:15:14,  1.37it/s]
1|4967|Loss: 0.9674504399299622:  19%|█▉        | 4966/25880 [1:02:32<4:15:14,  1.37it/s]
1|4967|Loss: 0.9674504399299622:  19%|█▉        | 4967/25880 [1:02:33<4:15:31,  1.36it/s]
1|4968|Loss: 0.8338150978088379:  19%|█▉        | 4967/25880 [1:02:33<4:15:31,  1.36it/s]
1|4968|Loss: 0.8338150978088379:  19%|█▉        | 4968/25880 [1:02:33<4:15:00,  1.37it/s]
1|4969|Loss: 0.8904025554656982:  19%|█▉        | 4968/25880 [1:02:34<4:15:00,  1.37it/s]
1|4969|Loss: 0.8904025554656982:  19%|█▉        | 4969/25880 [1:02:34<4:12:31,  1.38it/s]
1|4970|Loss: 0.8389539122581482:  19%|█▉        | 4969/25880 [1:02:34<4:12:31,  1.38it/s]
1|4970|Loss: 0.8389539122581482:  19%|█▉        | 4970/25880 [1:02:35<4:14:06,  1.37it/s]
1|4971|Loss: 0.8765427470207214:  19%|█▉        | 4970/25880 [1:02:35<4:14:06,  1.37it/s]
1|4971|Loss: 0.8765427470207214:  19%|█▉        | 4971/25880 [1:02:36<4:22:56,  1.33it/s]
1|4972|Loss: 0.8052608966827393:  19%|█▉        | 4971/25880 [1:02:36<4:22:56,  1.33it/s]
1|4972|Loss: 0.8052608966827393:  19%|█▉        | 4972/25880 [1:02:36<4:31:07,  1.29it/s]
1|4973|Loss: 0.7878967523574829:  19%|█▉        | 4972/25880 [1:02:37<4:31:07,  1.29it/s]
1|4973|Loss: 0.7878967523574829:  19%|█▉        | 4973/25880 [1:02:37<4:13:28,  1.37it/s]
1|4974|Loss: 0.854957103729248:  19%|█▉        | 4973/25880 [1:02:37<4:13:28,  1.37it/s] 
1|4974|Loss: 0.854957103729248:  19%|█▉        | 4974/25880 [1:02:38<4:02:01,  1.44it/s]
1|4975|Loss: 0.8026589751243591:  19%|█▉        | 4974/25880 [1:02:38<4:02:01,  1.44it/s]
1|4975|Loss: 0.8026589751243591:  19%|█▉        | 4975/25880 [1:02:38<3:53:51,  1.49it/s]
1|4976|Loss: 0.9482606649398804:  19%|█▉        | 4975/25880 [1:02:39<3:53:51,  1.49it/s]
1|4976|Loss: 0.9482606649398804:  19%|█▉        | 4976/25880 [1:02:39<4:08:12,  1.40it/s]
1|4977|Loss: 0.8640889525413513:  19%|█▉        | 4976/25880 [1:02:39<4:08:12,  1.40it/s]
1|4977|Loss: 0.8640889525413513:  19%|█▉        | 4977/25880 [1:02:40<4:05:53,  1.42it/s]
1|4978|Loss: 0.7188449501991272:  19%|█▉        | 4977/25880 [1:02:40<4:05:53,  1.42it/s]
1|4978|Loss: 0.7188449501991272:  19%|█▉        | 4978/25880 [1:02:40<4:04:12,  1.43it/s]
1|4979|Loss: 0.8843307495117188:  19%|█▉        | 4978/25880 [1:02:41<4:04:12,  1.43it/s]
1|4979|Loss: 0.8843307495117188:  19%|█▉        | 4979/25880 [1:02:41<3:58:45,  1.46it/s]
1|4980|Loss: 0.9198769927024841:  19%|█▉        | 4979/25880 [1:02:41<3:58:45,  1.46it/s]
1|4980|Loss: 0.9198769927024841:  19%|█▉        | 4980/25880 [1:02:42<4:03:18,  1.43it/s]
1|4981|Loss: 0.8485300540924072:  19%|█▉        | 4980/25880 [1:02:42<4:03:18,  1.43it/s]
1|4981|Loss: 0.8485300540924072:  19%|█▉        | 4981/25880 [1:02:42<3:44:25,  1.55it/s]
1|4982|Loss: 0.7886288166046143:  19%|█▉        | 4981/25880 [1:02:43<3:44:25,  1.55it/s]
1|4982|Loss: 0.7886288166046143:  19%|█▉        | 4982/25880 [1:02:43<3:52:44,  1.50it/s]
1|4983|Loss: 0.7924213409423828:  19%|█▉        | 4982/25880 [1:02:43<3:52:44,  1.50it/s]
1|4983|Loss: 0.7924213409423828:  19%|█▉        | 4983/25880 [1:02:44<4:09:12,  1.40it/s]
1|4984|Loss: 0.9658268094062805:  19%|█▉        | 4983/25880 [1:02:44<4:09:12,  1.40it/s]
1|4984|Loss: 0.9658268094062805:  19%|█▉        | 4984/25880 [1:02:45<4:13:19,  1.37it/s]
1|4985|Loss: 0.9173255562782288:  19%|█▉        | 4984/25880 [1:02:45<4:13:19,  1.37it/s]
1|4985|Loss: 0.9173255562782288:  19%|█▉        | 4985/25880 [1:02:45<4:13:23,  1.37it/s]
1|4986|Loss: 0.9218233227729797:  19%|█▉        | 4985/25880 [1:02:46<4:13:23,  1.37it/s]
1|4986|Loss: 0.9218233227729797:  19%|█▉        | 4986/25880 [1:02:46<4:02:05,  1.44it/s]
1|4987|Loss: 0.8942599892616272:  19%|█▉        | 4986/25880 [1:02:46<4:02:05,  1.44it/s]
1|4987|Loss: 0.8942599892616272:  19%|█▉        | 4987/25880 [1:02:47<4:00:02,  1.45it/s]
1|4988|Loss: 0.9306846857070923:  19%|█▉        | 4987/25880 [1:02:47<4:00:02,  1.45it/s]
1|4988|Loss: 0.9306846857070923:  19%|█▉        | 4988/25880 [1:02:47<4:05:20,  1.42it/s]
1|4989|Loss: 0.9290084838867188:  19%|█▉        | 4988/25880 [1:02:48<4:05:20,  1.42it/s]
1|4989|Loss: 0.9290084838867188:  19%|█▉        | 4989/25880 [1:02:48<4:06:41,  1.41it/s]
1|4990|Loss: 0.804926872253418:  19%|█▉        | 4989/25880 [1:02:49<4:06:41,  1.41it/s] 
1|4990|Loss: 0.804926872253418:  19%|█▉        | 4990/25880 [1:02:49<4:17:06,  1.35it/s]
1|4991|Loss: 0.9264626502990723:  19%|█▉        | 4990/25880 [1:02:49<4:17:06,  1.35it/s]
1|4991|Loss: 0.9264626502990723:  19%|█▉        | 4991/25880 [1:02:50<4:10:52,  1.39it/s]
1|4992|Loss: 0.7429894208908081:  19%|█▉        | 4991/25880 [1:02:50<4:10:52,  1.39it/s]
1|4992|Loss: 0.7429894208908081:  19%|█▉        | 4992/25880 [1:02:51<4:32:44,  1.28it/s]
1|4993|Loss: 1.0561262369155884:  19%|█▉        | 4992/25880 [1:02:51<4:32:44,  1.28it/s]
1|4993|Loss: 1.0561262369155884:  19%|█▉        | 4993/25880 [1:02:51<4:44:57,  1.22it/s]
1|4994|Loss: 0.8963125944137573:  19%|█▉        | 4993/25880 [1:02:52<4:44:57,  1.22it/s]
1|4994|Loss: 0.8963125944137573:  19%|█▉        | 4994/25880 [1:02:52<4:20:14,  1.34it/s]
1|4995|Loss: 0.8845366835594177:  19%|█▉        | 4994/25880 [1:02:52<4:20:14,  1.34it/s]
1|4995|Loss: 0.8845366835594177:  19%|█▉        | 4995/25880 [1:02:53<3:55:23,  1.48it/s]
1|4996|Loss: 0.8401861190795898:  19%|█▉        | 4995/25880 [1:02:53<3:55:23,  1.48it/s]
1|4996|Loss: 0.8401861190795898:  19%|█▉        | 4996/25880 [1:02:53<3:53:51,  1.49it/s]
1|4997|Loss: 0.7273129224777222:  19%|█▉        | 4996/25880 [1:02:54<3:53:51,  1.49it/s]
1|4997|Loss: 0.7273129224777222:  19%|█▉        | 4997/25880 [1:02:54<3:59:04,  1.46it/s]
1|4998|Loss: 0.7334977984428406:  19%|█▉        | 4997/25880 [1:02:54<3:59:04,  1.46it/s]
1|4998|Loss: 0.7334977984428406:  19%|█▉        | 4998/25880 [1:02:55<4:22:46,  1.32it/s]
1|4999|Loss: 0.7117075324058533:  19%|█▉        | 4998/25880 [1:02:55<4:22:46,  1.32it/s]
1|4999|Loss: 0.7117075324058533:  19%|█▉        | 4999/25880 [1:02:56<4:37:39,  1.25it/s]
1|5000|Loss: 0.8977050185203552:  19%|█▉        | 4999/25880 [1:02:56<4:37:39,  1.25it/s]
1|5000|Loss: 0.8977050185203552:  19%|█▉        | 5000/25880 [1:02:56<4:26:45,  1.30it/s]
1|5001|Loss: 0.922265350818634:  19%|█▉        | 5000/25880 [1:02:57<4:26:45,  1.30it/s] 
1|5001|Loss: 0.922265350818634:  19%|█▉        | 5001/25880 [1:02:57<4:29:22,  1.29it/s]
1|5002|Loss: 0.8596416711807251:  19%|█▉        | 5001/25880 [1:02:58<4:29:22,  1.29it/s]
1|5002|Loss: 0.8596416711807251:  19%|█▉        | 5002/25880 [1:02:58<4:35:23,  1.26it/s]
1|5003|Loss: 1.0115957260131836:  19%|█▉        | 5002/25880 [1:02:58<4:35:23,  1.26it/s]
1|5003|Loss: 1.0115957260131836:  19%|█▉        | 5003/25880 [1:02:59<4:38:27,  1.25it/s]
1|5004|Loss: 0.8110364675521851:  19%|█▉        | 5003/25880 [1:02:59<4:38:27,  1.25it/s]
1|5004|Loss: 0.8110364675521851:  19%|█▉        | 5004/25880 [1:03:00<4:45:18,  1.22it/s]
1|5005|Loss: 0.8019338846206665:  19%|█▉        | 5004/25880 [1:03:00<4:45:18,  1.22it/s]
1|5005|Loss: 0.8019338846206665:  19%|█▉        | 5005/25880 [1:03:00<4:40:02,  1.24it/s]
1|5006|Loss: 0.8645105361938477:  19%|█▉        | 5005/25880 [1:03:01<4:40:02,  1.24it/s]
1|5006|Loss: 0.8645105361938477:  19%|█▉        | 5006/25880 [1:03:01<4:54:25,  1.18it/s]
1|5007|Loss: 0.8086435198783875:  19%|█▉        | 5006/25880 [1:03:02<4:54:25,  1.18it/s]
1|5007|Loss: 0.8086435198783875:  19%|█▉        | 5007/25880 [1:03:02<4:39:08,  1.25it/s]
1|5008|Loss: 0.8570225834846497:  19%|█▉        | 5007/25880 [1:03:02<4:39:08,  1.25it/s]
1|5008|Loss: 0.8570225834846497:  19%|█▉        | 5008/25880 [1:03:03<4:21:44,  1.33it/s]
1|5009|Loss: 0.8275014758110046:  19%|█▉        | 5008/25880 [1:03:03<4:21:44,  1.33it/s]
1|5009|Loss: 0.8275014758110046:  19%|█▉        | 5009/25880 [1:03:03<4:18:16,  1.35it/s]
1|5010|Loss: 0.8714897036552429:  19%|█▉        | 5009/25880 [1:03:04<4:18:16,  1.35it/s]
1|5010|Loss: 0.8714897036552429:  19%|█▉        | 5010/25880 [1:03:04<4:21:30,  1.33it/s]
1|5011|Loss: 0.8360028862953186:  19%|█▉        | 5010/25880 [1:03:05<4:21:30,  1.33it/s]
1|5011|Loss: 0.8360028862953186:  19%|█▉        | 5011/25880 [1:03:05<4:40:19,  1.24it/s]
1|5012|Loss: 0.9417414665222168:  19%|█▉        | 5011/25880 [1:03:06<4:40:19,  1.24it/s]
1|5012|Loss: 0.9417414665222168:  19%|█▉        | 5012/25880 [1:03:06<4:45:51,  1.22it/s]
1|5013|Loss: 0.8325780630111694:  19%|█▉        | 5012/25880 [1:03:06<4:45:51,  1.22it/s]
1|5013|Loss: 0.8325780630111694:  19%|█▉        | 5013/25880 [1:03:07<4:44:22,  1.22it/s]
1|5014|Loss: 0.6991127133369446:  19%|█▉        | 5013/25880 [1:03:07<4:44:22,  1.22it/s]
1|5014|Loss: 0.6991127133369446:  19%|█▉        | 5014/25880 [1:03:07<4:21:54,  1.33it/s]
1|5015|Loss: 0.8691571354866028:  19%|█▉        | 5014/25880 [1:03:08<4:21:54,  1.33it/s]
1|5015|Loss: 0.8691571354866028:  19%|█▉        | 5015/25880 [1:03:08<4:24:20,  1.32it/s]
1|5016|Loss: 0.8135700225830078:  19%|█▉        | 5015/25880 [1:03:09<4:24:20,  1.32it/s]
1|5016|Loss: 0.8135700225830078:  19%|█▉        | 5016/25880 [1:03:09<4:20:28,  1.34it/s]
1|5017|Loss: 0.7881554365158081:  19%|█▉        | 5016/25880 [1:03:09<4:20:28,  1.34it/s]
1|5017|Loss: 0.7881554365158081:  19%|█▉        | 5017/25880 [1:03:10<4:18:55,  1.34it/s]
1|5018|Loss: 0.9102170467376709:  19%|█▉        | 5017/25880 [1:03:10<4:18:55,  1.34it/s]
1|5018|Loss: 0.9102170467376709:  19%|█▉        | 5018/25880 [1:03:11<4:27:10,  1.30it/s]
1|5019|Loss: 0.8191503882408142:  19%|█▉        | 5018/25880 [1:03:11<4:27:10,  1.30it/s]
1|5019|Loss: 0.8191503882408142:  19%|█▉        | 5019/25880 [1:03:11<4:15:24,  1.36it/s]
1|5020|Loss: 0.923758327960968:  19%|█▉        | 5019/25880 [1:03:12<4:15:24,  1.36it/s] 
1|5020|Loss: 0.923758327960968:  19%|█▉        | 5020/25880 [1:03:12<4:13:06,  1.37it/s]
1|5021|Loss: 0.8122499585151672:  19%|█▉        | 5020/25880 [1:03:12<4:13:06,  1.37it/s]
1|5021|Loss: 0.8122499585151672:  19%|█▉        | 5021/25880 [1:03:13<4:03:52,  1.43it/s]
1|5022|Loss: 0.7152332663536072:  19%|█▉        | 5021/25880 [1:03:13<4:03:52,  1.43it/s]
1|5022|Loss: 0.7152332663536072:  19%|█▉        | 5022/25880 [1:03:13<4:01:39,  1.44it/s]
1|5023|Loss: 0.8554647564888:  19%|█▉        | 5022/25880 [1:03:14<4:01:39,  1.44it/s]   
1|5023|Loss: 0.8554647564888:  19%|█▉        | 5023/25880 [1:03:14<3:57:11,  1.47it/s]
1|5024|Loss: 0.7837389707565308:  19%|█▉        | 5023/25880 [1:03:14<3:57:11,  1.47it/s]
1|5024|Loss: 0.7837389707565308:  19%|█▉        | 5024/25880 [1:03:15<3:58:28,  1.46it/s]
1|5025|Loss: 0.8188424110412598:  19%|█▉        | 5024/25880 [1:03:15<3:58:28,  1.46it/s]
1|5025|Loss: 0.8188424110412598:  19%|█▉        | 5025/25880 [1:03:15<3:59:53,  1.45it/s]
1|5026|Loss: 0.9729629158973694:  19%|█▉        | 5025/25880 [1:03:16<3:59:53,  1.45it/s]
1|5026|Loss: 0.9729629158973694:  19%|█▉        | 5026/25880 [1:03:16<3:44:19,  1.55it/s]
1|5027|Loss: 0.8906435966491699:  19%|█▉        | 5026/25880 [1:03:16<3:44:19,  1.55it/s]
1|5027|Loss: 0.8906435966491699:  19%|█▉        | 5027/25880 [1:03:17<4:01:08,  1.44it/s]
1|5028|Loss: 0.7335683703422546:  19%|█▉        | 5027/25880 [1:03:17<4:01:08,  1.44it/s]
1|5028|Loss: 0.7335683703422546:  19%|█▉        | 5028/25880 [1:03:17<3:55:56,  1.47it/s]
1|5029|Loss: 0.8427908420562744:  19%|█▉        | 5028/25880 [1:03:18<3:55:56,  1.47it/s]
1|5029|Loss: 0.8427908420562744:  19%|█▉        | 5029/25880 [1:03:18<3:57:55,  1.46it/s]
1|5030|Loss: 0.7503936290740967:  19%|█▉        | 5029/25880 [1:03:18<3:57:55,  1.46it/s]
1|5030|Loss: 0.7503936290740967:  19%|█▉        | 5030/25880 [1:03:19<3:59:25,  1.45it/s]
1|5031|Loss: 0.7894924879074097:  19%|█▉        | 5030/25880 [1:03:19<3:59:25,  1.45it/s]
1|5031|Loss: 0.7894924879074097:  19%|█▉        | 5031/25880 [1:03:19<4:12:37,  1.38it/s]
1|5032|Loss: 0.9137626886367798:  19%|█▉        | 5031/25880 [1:03:20<4:12:37,  1.38it/s]
1|5032|Loss: 0.9137626886367798:  19%|█▉        | 5032/25880 [1:03:20<4:25:57,  1.31it/s]
1|5033|Loss: 0.882818877696991:  19%|█▉        | 5032/25880 [1:03:21<4:25:57,  1.31it/s] 
1|5033|Loss: 0.882818877696991:  19%|█▉        | 5033/25880 [1:03:21<4:25:24,  1.31it/s]
1|5034|Loss: 0.8503908514976501:  19%|█▉        | 5033/25880 [1:03:21<4:25:24,  1.31it/s]
1|5034|Loss: 0.8503908514976501:  19%|█▉        | 5034/25880 [1:03:22<4:21:36,  1.33it/s]
1|5035|Loss: 0.9274505376815796:  19%|█▉        | 5034/25880 [1:03:22<4:21:36,  1.33it/s]
1|5035|Loss: 0.9274505376815796:  19%|█▉        | 5035/25880 [1:03:23<4:18:23,  1.34it/s]
1|5036|Loss: 0.984498143196106:  19%|█▉        | 5035/25880 [1:03:23<4:18:23,  1.34it/s] 
1|5036|Loss: 0.984498143196106:  19%|█▉        | 5036/25880 [1:03:23<3:58:14,  1.46it/s]
1|5037|Loss: 0.7563027143478394:  19%|█▉        | 5036/25880 [1:03:23<3:58:14,  1.46it/s]
1|5037|Loss: 0.7563027143478394:  19%|█▉        | 5037/25880 [1:03:24<3:48:24,  1.52it/s]
1|5038|Loss: 0.8411501049995422:  19%|█▉        | 5037/25880 [1:03:24<3:48:24,  1.52it/s]
1|5038|Loss: 0.8411501049995422:  19%|█▉        | 5038/25880 [1:03:24<3:52:01,  1.50it/s]
1|5039|Loss: 0.8515896201133728:  19%|█▉        | 5038/25880 [1:03:25<3:52:01,  1.50it/s]
1|5039|Loss: 0.8515896201133728:  19%|█▉        | 5039/25880 [1:03:25<3:57:35,  1.46it/s]
1|5040|Loss: 0.9414231777191162:  19%|█▉        | 5039/25880 [1:03:25<3:57:35,  1.46it/s]
1|5040|Loss: 0.9414231777191162:  19%|█▉        | 5040/25880 [1:03:26<3:54:40,  1.48it/s]
1|5041|Loss: 0.8074071407318115:  19%|█▉        | 5040/25880 [1:03:26<3:54:40,  1.48it/s]
1|5041|Loss: 0.8074071407318115:  19%|█▉        | 5041/25880 [1:03:26<3:49:33,  1.51it/s]
1|5042|Loss: 0.876843273639679:  19%|█▉        | 5041/25880 [1:03:27<3:49:33,  1.51it/s] 
1|5042|Loss: 0.876843273639679:  19%|█▉        | 5042/25880 [1:03:27<4:04:20,  1.42it/s]
1|5043|Loss: 0.6535570025444031:  19%|█▉        | 5042/25880 [1:03:28<4:04:20,  1.42it/s]
1|5043|Loss: 0.6535570025444031:  19%|█▉        | 5043/25880 [1:03:28<4:07:19,  1.40it/s]
1|5044|Loss: 1.0024034976959229:  19%|█▉        | 5043/25880 [1:03:28<4:07:19,  1.40it/s]
1|5044|Loss: 1.0024034976959229:  19%|█▉        | 5044/25880 [1:03:29<4:06:00,  1.41it/s]
1|5045|Loss: 0.7417232990264893:  19%|█▉        | 5044/25880 [1:03:29<4:06:00,  1.41it/s]
1|5045|Loss: 0.7417232990264893:  19%|█▉        | 5045/25880 [1:03:29<3:49:13,  1.51it/s]
1|5046|Loss: 0.9635027647018433:  19%|█▉        | 5045/25880 [1:03:29<3:49:13,  1.51it/s]
1|5046|Loss: 0.9635027647018433:  19%|█▉        | 5046/25880 [1:03:30<3:29:41,  1.66it/s]
1|5047|Loss: 0.7441983222961426:  19%|█▉        | 5046/25880 [1:03:30<3:29:41,  1.66it/s]
1|5047|Loss: 0.7441983222961426:  20%|█▉        | 5047/25880 [1:03:30<3:46:12,  1.53it/s]
1|5048|Loss: 0.9519795179367065:  20%|█▉        | 5047/25880 [1:03:31<3:46:12,  1.53it/s]
1|5048|Loss: 0.9519795179367065:  20%|█▉        | 5048/25880 [1:03:31<4:21:07,  1.33it/s]
1|5049|Loss: 0.843026340007782:  20%|█▉        | 5048/25880 [1:03:32<4:21:07,  1.33it/s] 
1|5049|Loss: 0.843026340007782:  20%|█▉        | 5049/25880 [1:03:32<4:35:05,  1.26it/s]
1|5050|Loss: 0.7659283876419067:  20%|█▉        | 5049/25880 [1:03:33<4:35:05,  1.26it/s]
1|5050|Loss: 0.7659283876419067:  20%|█▉        | 5050/25880 [1:03:33<4:36:57,  1.25it/s]
1|5051|Loss: 0.8677822947502136:  20%|█▉        | 5050/25880 [1:03:33<4:36:57,  1.25it/s]
1|5051|Loss: 0.8677822947502136:  20%|█▉        | 5051/25880 [1:03:34<4:32:28,  1.27it/s]
1|5052|Loss: 0.772904098033905:  20%|█▉        | 5051/25880 [1:03:34<4:32:28,  1.27it/s] 
1|5052|Loss: 0.772904098033905:  20%|█▉        | 5052/25880 [1:03:35<4:37:28,  1.25it/s]
1|5053|Loss: 0.8875163793563843:  20%|█▉        | 5052/25880 [1:03:35<4:37:28,  1.25it/s]
1|5053|Loss: 0.8875163793563843:  20%|█▉        | 5053/25880 [1:03:35<4:26:02,  1.30it/s]
1|5054|Loss: 0.8388713002204895:  20%|█▉        | 5053/25880 [1:03:36<4:26:02,  1.30it/s]
1|5054|Loss: 0.8388713002204895:  20%|█▉        | 5054/25880 [1:03:36<4:30:33,  1.28it/s]
1|5055|Loss: 0.8055108785629272:  20%|█▉        | 5054/25880 [1:03:37<4:30:33,  1.28it/s]
1|5055|Loss: 0.8055108785629272:  20%|█▉        | 5055/25880 [1:03:37<4:28:10,  1.29it/s]
1|5056|Loss: 0.8672025799751282:  20%|█▉        | 5055/25880 [1:03:37<4:28:10,  1.29it/s]
1|5056|Loss: 0.8672025799751282:  20%|█▉        | 5056/25880 [1:03:38<4:20:50,  1.33it/s]
1|5057|Loss: 0.7986577749252319:  20%|█▉        | 5056/25880 [1:03:38<4:20:50,  1.33it/s]
1|5057|Loss: 0.7986577749252319:  20%|█▉        | 5057/25880 [1:03:38<4:18:25,  1.34it/s]
1|5058|Loss: 0.7499209046363831:  20%|█▉        | 5057/25880 [1:03:39<4:18:25,  1.34it/s]
1|5058|Loss: 0.7499209046363831:  20%|█▉        | 5058/25880 [1:03:39<4:26:54,  1.30it/s]
1|5059|Loss: 0.7656772136688232:  20%|█▉        | 5058/25880 [1:03:40<4:26:54,  1.30it/s]
1|5059|Loss: 0.7656772136688232:  20%|█▉        | 5059/25880 [1:03:40<4:13:47,  1.37it/s]
1|5060|Loss: 0.8683426976203918:  20%|█▉        | 5059/25880 [1:03:40<4:13:47,  1.37it/s]
1|5060|Loss: 0.8683426976203918:  20%|█▉        | 5060/25880 [1:03:40<4:03:04,  1.43it/s]
1|5061|Loss: 0.7197831273078918:  20%|█▉        | 5060/25880 [1:03:41<4:03:04,  1.43it/s]
1|5061|Loss: 0.7197831273078918:  20%|█▉        | 5061/25880 [1:03:41<4:01:42,  1.44it/s]
1|5062|Loss: 0.8486617207527161:  20%|█▉        | 5061/25880 [1:03:41<4:01:42,  1.44it/s]
1|5062|Loss: 0.8486617207527161:  20%|█▉        | 5062/25880 [1:03:42<4:01:33,  1.44it/s]
1|5063|Loss: 0.7951942682266235:  20%|█▉        | 5062/25880 [1:03:42<4:01:33,  1.44it/s]
1|5063|Loss: 0.7951942682266235:  20%|█▉        | 5063/25880 [1:03:42<3:56:19,  1.47it/s]
1|5064|Loss: 0.9251035451889038:  20%|█▉        | 5063/25880 [1:03:43<3:56:19,  1.47it/s]
1|5064|Loss: 0.9251035451889038:  20%|█▉        | 5064/25880 [1:03:43<4:07:55,  1.40it/s]
1|5065|Loss: 0.8931874632835388:  20%|█▉        | 5064/25880 [1:03:44<4:07:55,  1.40it/s]
1|5065|Loss: 0.8931874632835388:  20%|█▉        | 5065/25880 [1:03:44<3:58:57,  1.45it/s]
1|5066|Loss: 0.8138428330421448:  20%|█▉        | 5065/25880 [1:03:44<3:58:57,  1.45it/s]
1|5066|Loss: 0.8138428330421448:  20%|█▉        | 5066/25880 [1:03:45<5:08:45,  1.12it/s]
1|5067|Loss: 0.8849225044250488:  20%|█▉        | 5066/25880 [1:03:46<5:08:45,  1.12it/s]
1|5067|Loss: 0.8849225044250488:  20%|█▉        | 5067/25880 [1:03:46<5:00:15,  1.16it/s]
1|5068|Loss: 0.8551639318466187:  20%|█▉        | 5067/25880 [1:03:46<5:00:15,  1.16it/s]
1|5068|Loss: 0.8551639318466187:  20%|█▉        | 5068/25880 [1:03:47<4:43:18,  1.22it/s]
1|5069|Loss: 0.7982305288314819:  20%|█▉        | 5068/25880 [1:03:47<4:43:18,  1.22it/s]
1|5069|Loss: 0.7982305288314819:  20%|█▉        | 5069/25880 [1:03:47<4:17:19,  1.35it/s]
1|5070|Loss: 0.8131757378578186:  20%|█▉        | 5069/25880 [1:03:48<4:17:19,  1.35it/s]
1|5070|Loss: 0.8131757378578186:  20%|█▉        | 5070/25880 [1:03:48<4:12:13,  1.38it/s]
1|5071|Loss: 0.9638105630874634:  20%|█▉        | 5070/25880 [1:03:48<4:12:13,  1.38it/s]
1|5071|Loss: 0.9638105630874634:  20%|█▉        | 5071/25880 [1:03:49<4:13:44,  1.37it/s]
1|5072|Loss: 0.780107319355011:  20%|█▉        | 5071/25880 [1:03:49<4:13:44,  1.37it/s] 
1|5072|Loss: 0.780107319355011:  20%|█▉        | 5072/25880 [1:03:49<4:14:10,  1.36it/s]
1|5073|Loss: 0.9956886768341064:  20%|█▉        | 5072/25880 [1:03:50<4:14:10,  1.36it/s]
1|5073|Loss: 0.9956886768341064:  20%|█▉        | 5073/25880 [1:03:50<4:32:41,  1.27it/s]
1|5074|Loss: 0.7251290082931519:  20%|█▉        | 5073/25880 [1:03:51<4:32:41,  1.27it/s]
1|5074|Loss: 0.7251290082931519:  20%|█▉        | 5074/25880 [1:03:51<4:39:24,  1.24it/s]
1|5075|Loss: 0.9188046455383301:  20%|█▉        | 5074/25880 [1:03:52<4:39:24,  1.24it/s]
1|5075|Loss: 0.9188046455383301:  20%|█▉        | 5075/25880 [1:03:52<4:52:34,  1.19it/s]
1|5076|Loss: 0.9457978010177612:  20%|█▉        | 5075/25880 [1:03:53<4:52:34,  1.19it/s]
1|5076|Loss: 0.9457978010177612:  20%|█▉        | 5076/25880 [1:03:53<4:46:16,  1.21it/s]
1|5077|Loss: 0.8764391541481018:  20%|█▉        | 5076/25880 [1:03:53<4:46:16,  1.21it/s]
1|5077|Loss: 0.8764391541481018:  20%|█▉        | 5077/25880 [1:03:54<4:30:11,  1.28it/s]
1|5078|Loss: 0.7940127849578857:  20%|█▉        | 5077/25880 [1:03:54<4:30:11,  1.28it/s]
1|5078|Loss: 0.7940127849578857:  20%|█▉        | 5078/25880 [1:03:54<4:24:29,  1.31it/s]
1|5079|Loss: 0.9501561522483826:  20%|█▉        | 5078/25880 [1:03:55<4:24:29,  1.31it/s]
1|5079|Loss: 0.9501561522483826:  20%|█▉        | 5079/25880 [1:03:55<4:09:26,  1.39it/s]
1|5080|Loss: 0.8428193926811218:  20%|█▉        | 5079/25880 [1:03:55<4:09:26,  1.39it/s]
1|5080|Loss: 0.8428193926811218:  20%|█▉        | 5080/25880 [1:03:56<4:29:41,  1.29it/s]
1|5081|Loss: 0.6766689419746399:  20%|█▉        | 5080/25880 [1:03:56<4:29:41,  1.29it/s]
1|5081|Loss: 0.6766689419746399:  20%|█▉        | 5081/25880 [1:03:57<4:21:26,  1.33it/s]
1|5082|Loss: 0.8340312242507935:  20%|█▉        | 5081/25880 [1:03:57<4:21:26,  1.33it/s]
1|5082|Loss: 0.8340312242507935:  20%|█▉        | 5082/25880 [1:03:57<3:59:53,  1.44it/s]
1|5083|Loss: 0.9283964037895203:  20%|█▉        | 5082/25880 [1:03:57<3:59:53,  1.44it/s]
1|5083|Loss: 0.9283964037895203:  20%|█▉        | 5083/25880 [1:03:58<3:56:51,  1.46it/s]
1|5084|Loss: 0.9425672888755798:  20%|█▉        | 5083/25880 [1:03:58<3:56:51,  1.46it/s]
1|5084|Loss: 0.9425672888755798:  20%|█▉        | 5084/25880 [1:03:58<3:48:17,  1.52it/s]
1|5085|Loss: 1.0831291675567627:  20%|█▉        | 5084/25880 [1:03:59<3:48:17,  1.52it/s]
1|5085|Loss: 1.0831291675567627:  20%|█▉        | 5085/25880 [1:03:59<3:43:00,  1.55it/s]
1|5086|Loss: 0.8768267631530762:  20%|█▉        | 5085/25880 [1:03:59<3:43:00,  1.55it/s]
1|5086|Loss: 0.8768267631530762:  20%|█▉        | 5086/25880 [1:04:00<3:55:55,  1.47it/s]
1|5087|Loss: 0.7668514251708984:  20%|█▉        | 5086/25880 [1:04:00<3:55:55,  1.47it/s]
1|5087|Loss: 0.7668514251708984:  20%|█▉        | 5087/25880 [1:04:00<3:44:01,  1.55it/s]
1|5088|Loss: 0.8171884417533875:  20%|█▉        | 5087/25880 [1:04:01<3:44:01,  1.55it/s]
1|5088|Loss: 0.8171884417533875:  20%|█▉        | 5088/25880 [1:04:01<4:09:40,  1.39it/s]
1|5089|Loss: 0.8717250227928162:  20%|█▉        | 5088/25880 [1:04:02<4:09:40,  1.39it/s]
1|5089|Loss: 0.8717250227928162:  20%|█▉        | 5089/25880 [1:04:02<4:27:58,  1.29it/s]
1|5090|Loss: 1.0485875606536865:  20%|█▉        | 5089/25880 [1:04:03<4:27:58,  1.29it/s]
1|5090|Loss: 1.0485875606536865:  20%|█▉        | 5090/25880 [1:04:03<4:34:25,  1.26it/s]
1|5091|Loss: 0.8999261856079102:  20%|█▉        | 5090/25880 [1:04:03<4:34:25,  1.26it/s]
1|5091|Loss: 0.8999261856079102:  20%|█▉        | 5091/25880 [1:04:04<4:31:01,  1.28it/s]
1|5092|Loss: 0.8647469282150269:  20%|█▉        | 5091/25880 [1:04:04<4:31:01,  1.28it/s]
1|5092|Loss: 0.8647469282150269:  20%|█▉        | 5092/25880 [1:04:04<4:24:23,  1.31it/s]
1|5093|Loss: 0.9497002959251404:  20%|█▉        | 5092/25880 [1:04:05<4:24:23,  1.31it/s]
1|5093|Loss: 0.9497002959251404:  20%|█▉        | 5093/25880 [1:04:05<4:36:24,  1.25it/s]
1|5094|Loss: 0.8031983971595764:  20%|█▉        | 5093/25880 [1:04:06<4:36:24,  1.25it/s]
1|5094|Loss: 0.8031983971595764:  20%|█▉        | 5094/25880 [1:04:06<4:25:36,  1.30it/s]
1|5095|Loss: 0.8327263593673706:  20%|█▉        | 5094/25880 [1:04:06<4:25:36,  1.30it/s]
1|5095|Loss: 0.8327263593673706:  20%|█▉        | 5095/25880 [1:04:07<4:28:17,  1.29it/s]
1|5096|Loss: 0.749616265296936:  20%|█▉        | 5095/25880 [1:04:07<4:28:17,  1.29it/s] 
1|5096|Loss: 0.749616265296936:  20%|█▉        | 5096/25880 [1:04:08<4:47:04,  1.21it/s]
1|5097|Loss: 0.79053795337677:  20%|█▉        | 5096/25880 [1:04:08<4:47:04,  1.21it/s] 
1|5097|Loss: 0.79053795337677:  20%|█▉        | 5097/25880 [1:04:09<5:11:30,  1.11it/s]
1|5098|Loss: 0.8169159293174744:  20%|█▉        | 5097/25880 [1:04:09<5:11:30,  1.11it/s]
1|5098|Loss: 0.8169159293174744:  20%|█▉        | 5098/25880 [1:04:10<5:10:49,  1.11it/s]
1|5099|Loss: 0.8159021139144897:  20%|█▉        | 5098/25880 [1:04:10<5:10:49,  1.11it/s]
1|5099|Loss: 0.8159021139144897:  20%|█▉        | 5099/25880 [1:04:10<4:45:15,  1.21it/s]
1|5100|Loss: 0.7703118920326233:  20%|█▉        | 5099/25880 [1:04:11<4:45:15,  1.21it/s]
1|5100|Loss: 0.7703118920326233:  20%|█▉        | 5100/25880 [1:04:11<4:40:16,  1.24it/s]
1|5101|Loss: 0.9503075480461121:  20%|█▉        | 5100/25880 [1:04:12<4:40:16,  1.24it/s]
1|5101|Loss: 0.9503075480461121:  20%|█▉        | 5101/25880 [1:04:12<4:43:25,  1.22it/s]
1|5102|Loss: 0.8473051190376282:  20%|█▉        | 5101/25880 [1:04:12<4:43:25,  1.22it/s]
1|5102|Loss: 0.8473051190376282:  20%|█▉        | 5102/25880 [1:04:13<4:37:01,  1.25it/s]
1|5103|Loss: 1.0075997114181519:  20%|█▉        | 5102/25880 [1:04:13<4:37:01,  1.25it/s]
1|5103|Loss: 1.0075997114181519:  20%|█▉        | 5103/25880 [1:04:13<4:27:38,  1.29it/s]
1|5104|Loss: 0.8692415356636047:  20%|█▉        | 5103/25880 [1:04:14<4:27:38,  1.29it/s]
1|5104|Loss: 0.8692415356636047:  20%|█▉        | 5104/25880 [1:04:14<4:15:06,  1.36it/s]
1|5105|Loss: 0.8636388182640076:  20%|█▉        | 5104/25880 [1:04:14<4:15:06,  1.36it/s]
1|5105|Loss: 0.8636388182640076:  20%|█▉        | 5105/25880 [1:04:15<4:12:22,  1.37it/s]
1|5106|Loss: 0.8006561398506165:  20%|█▉        | 5105/25880 [1:04:15<4:12:22,  1.37it/s]
1|5106|Loss: 0.8006561398506165:  20%|█▉        | 5106/25880 [1:04:16<4:20:19,  1.33it/s]
1|5107|Loss: 0.7928081154823303:  20%|█▉        | 5106/25880 [1:04:16<4:20:19,  1.33it/s]
1|5107|Loss: 0.7928081154823303:  20%|█▉        | 5107/25880 [1:04:16<4:17:48,  1.34it/s]
1|5108|Loss: 0.7740327715873718:  20%|█▉        | 5107/25880 [1:04:17<4:17:48,  1.34it/s]
1|5108|Loss: 0.7740327715873718:  20%|█▉        | 5108/25880 [1:04:17<3:57:39,  1.46it/s]
1|5109|Loss: 0.8301635980606079:  20%|█▉        | 5108/25880 [1:04:17<3:57:39,  1.46it/s]
1|5109|Loss: 0.8301635980606079:  20%|█▉        | 5109/25880 [1:04:18<4:05:21,  1.41it/s]
1|5110|Loss: 0.8870000839233398:  20%|█▉        | 5109/25880 [1:04:18<4:05:21,  1.41it/s]
1|5110|Loss: 0.8870000839233398:  20%|█▉        | 5110/25880 [1:04:18<4:06:45,  1.40it/s]
1|5111|Loss: 0.8973336815834045:  20%|█▉        | 5110/25880 [1:04:19<4:06:45,  1.40it/s]
1|5111|Loss: 0.8973336815834045:  20%|█▉        | 5111/25880 [1:04:19<4:14:38,  1.36it/s]
1|5112|Loss: 0.7775341868400574:  20%|█▉        | 5111/25880 [1:04:20<4:14:38,  1.36it/s]
1|5112|Loss: 0.7775341868400574:  20%|█▉        | 5112/25880 [1:04:20<4:08:09,  1.39it/s]
1|5113|Loss: 0.7802239656448364:  20%|█▉        | 5112/25880 [1:04:20<4:08:09,  1.39it/s]
1|5113|Loss: 0.7802239656448364:  20%|█▉        | 5113/25880 [1:04:21<4:19:48,  1.33it/s]
1|5114|Loss: 0.7000834345817566:  20%|█▉        | 5113/25880 [1:04:21<4:19:48,  1.33it/s]
1|5114|Loss: 0.7000834345817566:  20%|█▉        | 5114/25880 [1:04:21<4:13:17,  1.37it/s]
1|5115|Loss: 0.8897898197174072:  20%|█▉        | 5114/25880 [1:04:22<4:13:17,  1.37it/s]
1|5115|Loss: 0.8897898197174072:  20%|█▉        | 5115/25880 [1:04:22<4:01:39,  1.43it/s]
1|5116|Loss: 0.8366860747337341:  20%|█▉        | 5115/25880 [1:04:22<4:01:39,  1.43it/s]
1|5116|Loss: 0.8366860747337341:  20%|█▉        | 5116/25880 [1:04:23<4:10:55,  1.38it/s]
1|5117|Loss: 0.7474437355995178:  20%|█▉        | 5116/25880 [1:04:23<4:10:55,  1.38it/s]
1|5117|Loss: 0.7474437355995178:  20%|█▉        | 5117/25880 [1:04:24<4:20:46,  1.33it/s]
1|5118|Loss: 0.608253538608551:  20%|█▉        | 5117/25880 [1:04:24<4:20:46,  1.33it/s] 
1|5118|Loss: 0.608253538608551:  20%|█▉        | 5118/25880 [1:04:24<4:19:45,  1.33it/s]
1|5119|Loss: 0.8808243274688721:  20%|█▉        | 5118/25880 [1:04:25<4:19:45,  1.33it/s]
1|5119|Loss: 0.8808243274688721:  20%|█▉        | 5119/25880 [1:04:25<4:33:27,  1.27it/s]
1|5120|Loss: 0.9791266918182373:  20%|█▉        | 5119/25880 [1:04:26<4:33:27,  1.27it/s]
1|5120|Loss: 0.9791266918182373:  20%|█▉        | 5120/25880 [1:04:26<4:41:55,  1.23it/s]
1|5121|Loss: 0.82328200340271:  20%|█▉        | 5120/25880 [1:04:27<4:41:55,  1.23it/s]  
1|5121|Loss: 0.82328200340271:  20%|█▉        | 5121/25880 [1:04:27<4:33:50,  1.26it/s]
1|5122|Loss: 0.8916245698928833:  20%|█▉        | 5121/25880 [1:04:27<4:33:50,  1.26it/s]
1|5122|Loss: 0.8916245698928833:  20%|█▉        | 5122/25880 [1:04:28<4:26:30,  1.30it/s]
1|5123|Loss: 0.7191998362541199:  20%|█▉        | 5122/25880 [1:04:28<4:26:30,  1.30it/s]
1|5123|Loss: 0.7191998362541199:  20%|█▉        | 5123/25880 [1:04:28<3:59:06,  1.45it/s]
1|5124|Loss: 0.8874213099479675:  20%|█▉        | 5123/25880 [1:04:28<3:59:06,  1.45it/s]
1|5124|Loss: 0.8874213099479675:  20%|█▉        | 5124/25880 [1:04:29<4:12:05,  1.37it/s]
1|5125|Loss: 0.7678930759429932:  20%|█▉        | 5124/25880 [1:04:29<4:12:05,  1.37it/s]
1|5125|Loss: 0.7678930759429932:  20%|█▉        | 5125/25880 [1:04:30<4:20:37,  1.33it/s]
1|5126|Loss: 0.804368793964386:  20%|█▉        | 5125/25880 [1:04:30<4:20:37,  1.33it/s] 
1|5126|Loss: 0.804368793964386:  20%|█▉        | 5126/25880 [1:04:31<4:30:30,  1.28it/s]
1|5127|Loss: 1.0913649797439575:  20%|█▉        | 5126/25880 [1:04:31<4:30:30,  1.28it/s]
1|5127|Loss: 1.0913649797439575:  20%|█▉        | 5127/25880 [1:04:31<4:13:22,  1.37it/s]
1|5128|Loss: 0.8342679738998413:  20%|█▉        | 5127/25880 [1:04:32<4:13:22,  1.37it/s]
1|5128|Loss: 0.8342679738998413:  20%|█▉        | 5128/25880 [1:04:32<4:07:56,  1.39it/s]
1|5129|Loss: 0.833489716053009:  20%|█▉        | 5128/25880 [1:04:32<4:07:56,  1.39it/s] 
1|5129|Loss: 0.833489716053009:  20%|█▉        | 5129/25880 [1:04:33<4:10:31,  1.38it/s]
1|5130|Loss: 0.8295521140098572:  20%|█▉        | 5129/25880 [1:04:33<4:10:31,  1.38it/s]
1|5130|Loss: 0.8295521140098572:  20%|█▉        | 5130/25880 [1:04:33<4:12:23,  1.37it/s]
1|5131|Loss: 0.814263105392456:  20%|█▉        | 5130/25880 [1:04:34<4:12:23,  1.37it/s] 
1|5131|Loss: 0.814263105392456:  20%|█▉        | 5131/25880 [1:04:34<4:12:02,  1.37it/s]
1|5132|Loss: 0.686571478843689:  20%|█▉        | 5131/25880 [1:04:34<4:12:02,  1.37it/s]
1|5132|Loss: 0.686571478843689:  20%|█▉        | 5132/25880 [1:04:35<4:16:39,  1.35it/s]
1|5133|Loss: 0.8183994293212891:  20%|█▉        | 5132/25880 [1:04:35<4:16:39,  1.35it/s]
1|5133|Loss: 0.8183994293212891:  20%|█▉        | 5133/25880 [1:04:36<4:17:26,  1.34it/s]
1|5134|Loss: 0.8756837844848633:  20%|█▉        | 5133/25880 [1:04:36<4:17:26,  1.34it/s]
1|5134|Loss: 0.8756837844848633:  20%|█▉        | 5134/25880 [1:04:36<4:17:07,  1.34it/s]
1|5135|Loss: 0.8081273436546326:  20%|█▉        | 5134/25880 [1:04:37<4:17:07,  1.34it/s]
1|5135|Loss: 0.8081273436546326:  20%|█▉        | 5135/25880 [1:04:37<4:08:38,  1.39it/s]
1|5136|Loss: 0.9494094252586365:  20%|█▉        | 5135/25880 [1:04:37<4:08:38,  1.39it/s]
1|5136|Loss: 0.9494094252586365:  20%|█▉        | 5136/25880 [1:04:38<4:10:05,  1.38it/s]
1|5137|Loss: 0.9155185222625732:  20%|█▉        | 5136/25880 [1:04:38<4:10:05,  1.38it/s]
1|5137|Loss: 0.9155185222625732:  20%|█▉        | 5137/25880 [1:04:38<4:09:23,  1.39it/s]
1|5138|Loss: 0.9108492732048035:  20%|█▉        | 5137/25880 [1:04:39<4:09:23,  1.39it/s]
1|5138|Loss: 0.9108492732048035:  20%|█▉        | 5138/25880 [1:04:39<4:09:06,  1.39it/s]
1|5139|Loss: 0.9517008066177368:  20%|█▉        | 5138/25880 [1:04:40<4:09:06,  1.39it/s]
1|5139|Loss: 0.9517008066177368:  20%|█▉        | 5139/25880 [1:04:40<4:09:02,  1.39it/s]
1|5140|Loss: 0.7041809558868408:  20%|█▉        | 5139/25880 [1:04:40<4:09:02,  1.39it/s]
1|5140|Loss: 0.7041809558868408:  20%|█▉        | 5140/25880 [1:04:41<4:02:12,  1.43it/s]
1|5141|Loss: 0.8735235929489136:  20%|█▉        | 5140/25880 [1:04:41<4:02:12,  1.43it/s]
1|5141|Loss: 0.8735235929489136:  20%|█▉        | 5141/25880 [1:04:41<3:48:45,  1.51it/s]
1|5142|Loss: 0.9950482845306396:  20%|█▉        | 5141/25880 [1:04:41<3:48:45,  1.51it/s]
1|5142|Loss: 0.9950482845306396:  20%|█▉        | 5142/25880 [1:04:42<3:53:40,  1.48it/s]
1|5143|Loss: 1.0194146633148193:  20%|█▉        | 5142/25880 [1:04:42<3:53:40,  1.48it/s]
1|5143|Loss: 1.0194146633148193:  20%|█▉        | 5143/25880 [1:04:42<3:52:24,  1.49it/s]
1|5144|Loss: 0.9984352588653564:  20%|█▉        | 5143/25880 [1:04:43<3:52:24,  1.49it/s]
1|5144|Loss: 0.9984352588653564:  20%|█▉        | 5144/25880 [1:04:43<3:47:22,  1.52it/s]
1|5145|Loss: 0.8782376050949097:  20%|█▉        | 5144/25880 [1:04:43<3:47:22,  1.52it/s]
1|5145|Loss: 0.8782376050949097:  20%|█▉        | 5145/25880 [1:04:44<3:42:59,  1.55it/s]
1|5146|Loss: 0.8364619612693787:  20%|█▉        | 5145/25880 [1:04:44<3:42:59,  1.55it/s]
1|5146|Loss: 0.8364619612693787:  20%|█▉        | 5146/25880 [1:04:44<3:42:00,  1.56it/s]
1|5147|Loss: 0.9473506808280945:  20%|█▉        | 5146/25880 [1:04:45<3:42:00,  1.56it/s]
1|5147|Loss: 0.9473506808280945:  20%|█▉        | 5147/25880 [1:04:45<3:51:25,  1.49it/s]
1|5148|Loss: 0.8098076581954956:  20%|█▉        | 5147/25880 [1:04:45<3:51:25,  1.49it/s]
1|5148|Loss: 0.8098076581954956:  20%|█▉        | 5148/25880 [1:04:46<3:55:54,  1.46it/s]
1|5149|Loss: 1.0000990629196167:  20%|█▉        | 5148/25880 [1:04:46<3:55:54,  1.46it/s]
1|5149|Loss: 1.0000990629196167:  20%|█▉        | 5149/25880 [1:04:46<3:57:27,  1.46it/s]
1|5150|Loss: 0.7987955808639526:  20%|█▉        | 5149/25880 [1:04:47<3:57:27,  1.46it/s]
1|5150|Loss: 0.7987955808639526:  20%|█▉        | 5150/25880 [1:04:47<4:05:26,  1.41it/s]
1|5151|Loss: 0.8274566531181335:  20%|█▉        | 5150/25880 [1:04:48<4:05:26,  1.41it/s]
1|5151|Loss: 0.8274566531181335:  20%|█▉        | 5151/25880 [1:04:48<3:56:24,  1.46it/s]
1|5152|Loss: 0.9026209712028503:  20%|█▉        | 5151/25880 [1:04:48<3:56:24,  1.46it/s]
1|5152|Loss: 0.9026209712028503:  20%|█▉        | 5152/25880 [1:04:48<3:45:21,  1.53it/s]
1|5153|Loss: 0.9431679248809814:  20%|█▉        | 5152/25880 [1:04:49<3:45:21,  1.53it/s]
1|5153|Loss: 0.9431679248809814:  20%|█▉        | 5153/25880 [1:04:49<3:51:39,  1.49it/s]
1|5154|Loss: 1.0340381860733032:  20%|█▉        | 5153/25880 [1:04:50<3:51:39,  1.49it/s]
1|5154|Loss: 1.0340381860733032:  20%|█▉        | 5154/25880 [1:04:50<3:59:33,  1.44it/s]
1|5155|Loss: 0.9198976159095764:  20%|█▉        | 5154/25880 [1:04:50<3:59:33,  1.44it/s]
1|5155|Loss: 0.9198976159095764:  20%|█▉        | 5155/25880 [1:04:51<4:08:54,  1.39it/s]
1|5156|Loss: 0.7625417113304138:  20%|█▉        | 5155/25880 [1:04:51<4:08:54,  1.39it/s]
1|5156|Loss: 0.7625417113304138:  20%|█▉        | 5156/25880 [1:04:51<4:11:51,  1.37it/s]
1|5157|Loss: 0.9059597849845886:  20%|█▉        | 5156/25880 [1:04:52<4:11:51,  1.37it/s]
1|5157|Loss: 0.9059597849845886:  20%|█▉        | 5157/25880 [1:04:52<3:51:49,  1.49it/s]
1|5158|Loss: 0.8323163390159607:  20%|█▉        | 5157/25880 [1:04:52<3:51:49,  1.49it/s]
1|5158|Loss: 0.8323163390159607:  20%|█▉        | 5158/25880 [1:04:53<3:53:49,  1.48it/s]
1|5159|Loss: 0.9085412621498108:  20%|█▉        | 5158/25880 [1:04:53<3:53:49,  1.48it/s]
1|5159|Loss: 0.9085412621498108:  20%|█▉        | 5159/25880 [1:04:53<3:47:43,  1.52it/s]
1|5160|Loss: 0.8689725995063782:  20%|█▉        | 5159/25880 [1:04:54<3:47:43,  1.52it/s]
1|5160|Loss: 0.8689725995063782:  20%|█▉        | 5160/25880 [1:04:54<3:44:45,  1.54it/s]
1|5161|Loss: 0.9644206762313843:  20%|█▉        | 5160/25880 [1:04:54<3:44:45,  1.54it/s]
1|5161|Loss: 0.9644206762313843:  20%|█▉        | 5161/25880 [1:04:55<3:41:56,  1.56it/s]
1|5162|Loss: 0.7914515137672424:  20%|█▉        | 5161/25880 [1:04:55<3:41:56,  1.56it/s]
1|5162|Loss: 0.7914515137672424:  20%|█▉        | 5162/25880 [1:04:55<3:54:51,  1.47it/s]
1|5163|Loss: 1.012676477432251:  20%|█▉        | 5162/25880 [1:04:56<3:54:51,  1.47it/s] 
1|5163|Loss: 1.012676477432251:  20%|█▉        | 5163/25880 [1:04:56<3:58:42,  1.45it/s]
1|5164|Loss: 0.8433159589767456:  20%|█▉        | 5163/25880 [1:04:56<3:58:42,  1.45it/s]
1|5164|Loss: 0.8433159589767456:  20%|█▉        | 5164/25880 [1:04:57<4:01:16,  1.43it/s]
1|5165|Loss: 0.8494532108306885:  20%|█▉        | 5164/25880 [1:04:57<4:01:16,  1.43it/s]
1|5165|Loss: 0.8494532108306885:  20%|█▉        | 5165/25880 [1:04:58<4:15:26,  1.35it/s]
1|5166|Loss: 0.8819092512130737:  20%|█▉        | 5165/25880 [1:04:58<4:15:26,  1.35it/s]
1|5166|Loss: 0.8819092512130737:  20%|█▉        | 5166/25880 [1:04:58<4:03:16,  1.42it/s]
1|5167|Loss: 0.8654215335845947:  20%|█▉        | 5166/25880 [1:04:59<4:03:16,  1.42it/s]
1|5167|Loss: 0.8654215335845947:  20%|█▉        | 5167/25880 [1:04:59<4:01:54,  1.43it/s]
1|5168|Loss: 0.9259913563728333:  20%|█▉        | 5167/25880 [1:04:59<4:01:54,  1.43it/s]
1|5168|Loss: 0.9259913563728333:  20%|█▉        | 5168/25880 [1:05:00<4:05:44,  1.40it/s]
1|5169|Loss: 0.8709051012992859:  20%|█▉        | 5168/25880 [1:05:00<4:05:44,  1.40it/s]
1|5169|Loss: 0.8709051012992859:  20%|█▉        | 5169/25880 [1:05:00<4:09:30,  1.38it/s]
1|5170|Loss: 0.8286389112472534:  20%|█▉        | 5169/25880 [1:05:01<4:09:30,  1.38it/s]
1|5170|Loss: 0.8286389112472534:  20%|█▉        | 5170/25880 [1:05:01<4:11:39,  1.37it/s]
1|5171|Loss: 0.845496416091919:  20%|█▉        | 5170/25880 [1:05:02<4:11:39,  1.37it/s] 
1|5171|Loss: 0.845496416091919:  20%|█▉        | 5171/25880 [1:05:02<4:13:20,  1.36it/s]
1|5172|Loss: 0.7624551653862:  20%|█▉        | 5171/25880 [1:05:02<4:13:20,  1.36it/s]  
1|5172|Loss: 0.7624551653862:  20%|█▉        | 5172/25880 [1:05:03<4:23:30,  1.31it/s]
1|5173|Loss: 0.9562503099441528:  20%|█▉        | 5172/25880 [1:05:03<4:23:30,  1.31it/s]
1|5173|Loss: 0.9562503099441528:  20%|█▉        | 5173/25880 [1:05:03<4:23:03,  1.31it/s]
1|5174|Loss: 0.9446114897727966:  20%|█▉        | 5173/25880 [1:05:04<4:23:03,  1.31it/s]
1|5174|Loss: 0.9446114897727966:  20%|█▉        | 5174/25880 [1:05:04<4:08:33,  1.39it/s]
1|5175|Loss: 0.8068687319755554:  20%|█▉        | 5174/25880 [1:05:04<4:08:33,  1.39it/s]
1|5175|Loss: 0.8068687319755554:  20%|█▉        | 5175/25880 [1:05:05<4:06:48,  1.40it/s]
1|5176|Loss: 0.9074608683586121:  20%|█▉        | 5175/25880 [1:05:05<4:06:48,  1.40it/s]
1|5176|Loss: 0.9074608683586121:  20%|██        | 5176/25880 [1:05:06<4:09:19,  1.38it/s]
1|5177|Loss: 0.833639919757843:  20%|██        | 5176/25880 [1:05:06<4:09:19,  1.38it/s] 
1|5177|Loss: 0.833639919757843:  20%|██        | 5177/25880 [1:05:06<4:12:37,  1.37it/s]
1|5178|Loss: 0.8624178171157837:  20%|██        | 5177/25880 [1:05:07<4:12:37,  1.37it/s]
1|5178|Loss: 0.8624178171157837:  20%|██        | 5178/25880 [1:05:07<4:23:05,  1.31it/s]
1|5179|Loss: 0.8516852855682373:  20%|██        | 5178/25880 [1:05:08<4:23:05,  1.31it/s]
1|5179|Loss: 0.8516852855682373:  20%|██        | 5179/25880 [1:05:08<4:38:17,  1.24it/s]
1|5180|Loss: 0.8506669402122498:  20%|██        | 5179/25880 [1:05:08<4:38:17,  1.24it/s]
1|5180|Loss: 0.8506669402122498:  20%|██        | 5180/25880 [1:05:09<4:38:45,  1.24it/s]
1|5181|Loss: 0.8893469572067261:  20%|██        | 5180/25880 [1:05:09<4:38:45,  1.24it/s]
1|5181|Loss: 0.8893469572067261:  20%|██        | 5181/25880 [1:05:10<4:37:17,  1.24it/s]
1|5182|Loss: 0.9970807433128357:  20%|██        | 5181/25880 [1:05:10<4:37:17,  1.24it/s]
1|5182|Loss: 0.9970807433128357:  20%|██        | 5182/25880 [1:05:10<4:35:50,  1.25it/s]
1|5183|Loss: 0.9684780836105347:  20%|██        | 5182/25880 [1:05:11<4:35:50,  1.25it/s]
1|5183|Loss: 0.9684780836105347:  20%|██        | 5183/25880 [1:05:11<4:22:04,  1.32it/s]
1|5184|Loss: 0.8440461754798889:  20%|██        | 5183/25880 [1:05:11<4:22:04,  1.32it/s]
1|5184|Loss: 0.8440461754798889:  20%|██        | 5184/25880 [1:05:12<4:07:37,  1.39it/s]
1|5185|Loss: 0.8773158192634583:  20%|██        | 5184/25880 [1:05:12<4:07:37,  1.39it/s]
1|5185|Loss: 0.8773158192634583:  20%|██        | 5185/25880 [1:05:13<4:22:30,  1.31it/s]
1|5186|Loss: 0.9247245788574219:  20%|██        | 5185/25880 [1:05:13<4:22:30,  1.31it/s]
1|5186|Loss: 0.9247245788574219:  20%|██        | 5186/25880 [1:05:13<4:15:48,  1.35it/s]
1|5187|Loss: 0.8328356742858887:  20%|██        | 5186/25880 [1:05:14<4:15:48,  1.35it/s]
1|5187|Loss: 0.8328356742858887:  20%|██        | 5187/25880 [1:05:14<4:02:57,  1.42it/s]
1|5188|Loss: 0.7229057550430298:  20%|██        | 5187/25880 [1:05:14<4:02:57,  1.42it/s]
1|5188|Loss: 0.7229057550430298:  20%|██        | 5188/25880 [1:05:15<3:54:16,  1.47it/s]
1|5189|Loss: 0.7793070673942566:  20%|██        | 5188/25880 [1:05:15<3:54:16,  1.47it/s]
1|5189|Loss: 0.7793070673942566:  20%|██        | 5189/25880 [1:05:15<4:13:57,  1.36it/s]
1|5190|Loss: 0.8501778244972229:  20%|██        | 5189/25880 [1:05:16<4:13:57,  1.36it/s]
1|5190|Loss: 0.8501778244972229:  20%|██        | 5190/25880 [1:05:16<4:08:16,  1.39it/s]
1|5191|Loss: 0.7486559152603149:  20%|██        | 5190/25880 [1:05:16<4:08:16,  1.39it/s]
1|5191|Loss: 0.7486559152603149:  20%|██        | 5191/25880 [1:05:17<4:08:19,  1.39it/s]
1|5192|Loss: 0.9737990498542786:  20%|██        | 5191/25880 [1:05:17<4:08:19,  1.39it/s]
1|5192|Loss: 0.9737990498542786:  20%|██        | 5192/25880 [1:05:18<4:09:46,  1.38it/s]
1|5193|Loss: 0.8221262693405151:  20%|██        | 5192/25880 [1:05:18<4:09:46,  1.38it/s]
1|5193|Loss: 0.8221262693405151:  20%|██        | 5193/25880 [1:05:18<4:10:44,  1.38it/s]
1|5194|Loss: 0.8637610077857971:  20%|██        | 5193/25880 [1:05:19<4:10:44,  1.38it/s]
1|5194|Loss: 0.8637610077857971:  20%|██        | 5194/25880 [1:05:19<4:21:16,  1.32it/s]
1|5195|Loss: 0.7573923468589783:  20%|██        | 5194/25880 [1:05:19<4:21:16,  1.32it/s]
1|5195|Loss: 0.7573923468589783:  20%|██        | 5195/25880 [1:05:20<4:20:57,  1.32it/s]
1|5196|Loss: 0.8174102306365967:  20%|██        | 5195/25880 [1:05:20<4:20:57,  1.32it/s]
1|5196|Loss: 0.8174102306365967:  20%|██        | 5196/25880 [1:05:20<4:10:12,  1.38it/s]
1|5197|Loss: 0.8136643767356873:  20%|██        | 5196/25880 [1:05:21<4:10:12,  1.38it/s]
1|5197|Loss: 0.8136643767356873:  20%|██        | 5197/25880 [1:05:21<4:15:14,  1.35it/s]
1|5198|Loss: 0.8336251974105835:  20%|██        | 5197/25880 [1:05:22<4:15:14,  1.35it/s]
1|5198|Loss: 0.8336251974105835:  20%|██        | 5198/25880 [1:05:22<4:20:14,  1.32it/s]
1|5199|Loss: 0.8605605959892273:  20%|██        | 5198/25880 [1:05:23<4:20:14,  1.32it/s]
1|5199|Loss: 0.8605605959892273:  20%|██        | 5199/25880 [1:05:23<4:39:10,  1.23it/s]
1|5200|Loss: 0.9027652144432068:  20%|██        | 5199/25880 [1:05:23<4:39:10,  1.23it/s]
1|5200|Loss: 0.9027652144432068:  20%|██        | 5200/25880 [1:05:24<4:51:54,  1.18it/s]
1|5201|Loss: 0.8125003576278687:  20%|██        | 5200/25880 [1:05:24<4:51:54,  1.18it/s]
1|5201|Loss: 0.8125003576278687:  20%|██        | 5201/25880 [1:05:25<4:53:26,  1.17it/s]
1|5202|Loss: 0.7981135845184326:  20%|██        | 5201/25880 [1:05:25<4:53:26,  1.17it/s]
1|5202|Loss: 0.7981135845184326:  20%|██        | 5202/25880 [1:05:26<4:43:53,  1.21it/s]
1|5203|Loss: 0.8640393018722534:  20%|██        | 5202/25880 [1:05:26<4:43:53,  1.21it/s]
1|5203|Loss: 0.8640393018722534:  20%|██        | 5203/25880 [1:05:26<4:33:42,  1.26it/s]
1|5204|Loss: 0.9084509611129761:  20%|██        | 5203/25880 [1:05:27<4:33:42,  1.26it/s]
1|5204|Loss: 0.9084509611129761:  20%|██        | 5204/25880 [1:05:27<4:19:21,  1.33it/s]
1|5205|Loss: 0.9511242508888245:  20%|██        | 5204/25880 [1:05:27<4:19:21,  1.33it/s]
1|5205|Loss: 0.9511242508888245:  20%|██        | 5205/25880 [1:05:28<4:33:58,  1.26it/s]
1|5206|Loss: 0.8479932546615601:  20%|██        | 5205/25880 [1:05:28<4:33:58,  1.26it/s]
1|5206|Loss: 0.8479932546615601:  20%|██        | 5206/25880 [1:05:29<4:29:39,  1.28it/s]
1|5207|Loss: 0.9250756502151489:  20%|██        | 5206/25880 [1:05:29<4:29:39,  1.28it/s]
1|5207|Loss: 0.9250756502151489:  20%|██        | 5207/25880 [1:05:29<4:33:38,  1.26it/s]
1|5208|Loss: 0.8859464526176453:  20%|██        | 5207/25880 [1:05:30<4:33:38,  1.26it/s]
1|5208|Loss: 0.8859464526176453:  20%|██        | 5208/25880 [1:05:30<4:41:28,  1.22it/s]
1|5209|Loss: 0.9057210087776184:  20%|██        | 5208/25880 [1:05:31<4:41:28,  1.22it/s]
1|5209|Loss: 0.9057210087776184:  20%|██        | 5209/25880 [1:05:31<4:33:14,  1.26it/s]
1|5210|Loss: 0.8407576084136963:  20%|██        | 5209/25880 [1:05:31<4:33:14,  1.26it/s]
1|5210|Loss: 0.8407576084136963:  20%|██        | 5210/25880 [1:05:32<4:46:34,  1.20it/s]
1|5211|Loss: 0.7118738293647766:  20%|██        | 5210/25880 [1:05:32<4:46:34,  1.20it/s]
1|5211|Loss: 0.7118738293647766:  20%|██        | 5211/25880 [1:05:33<4:46:35,  1.20it/s]
1|5212|Loss: 0.94035404920578:  20%|██        | 5211/25880 [1:05:33<4:46:35,  1.20it/s]  
1|5212|Loss: 0.94035404920578:  20%|██        | 5212/25880 [1:05:34<4:45:33,  1.21it/s]
1|5213|Loss: 0.9107626676559448:  20%|██        | 5212/25880 [1:05:34<4:45:33,  1.21it/s]
1|5213|Loss: 0.9107626676559448:  20%|██        | 5213/25880 [1:05:34<4:38:36,  1.24it/s]
1|5214|Loss: 0.8420284986495972:  20%|██        | 5213/25880 [1:05:35<4:38:36,  1.24it/s]
1|5214|Loss: 0.8420284986495972:  20%|██        | 5214/25880 [1:05:35<4:37:40,  1.24it/s]
1|5215|Loss: 0.8425919413566589:  20%|██        | 5214/25880 [1:05:36<4:37:40,  1.24it/s]
1|5215|Loss: 0.8425919413566589:  20%|██        | 5215/25880 [1:05:36<4:32:19,  1.26it/s]
1|5216|Loss: 0.8576378226280212:  20%|██        | 5215/25880 [1:05:36<4:32:19,  1.26it/s]
1|5216|Loss: 0.8576378226280212:  20%|██        | 5216/25880 [1:05:37<4:38:17,  1.24it/s]
1|5217|Loss: 0.8942064642906189:  20%|██        | 5216/25880 [1:05:37<4:38:17,  1.24it/s]
1|5217|Loss: 0.8942064642906189:  20%|██        | 5217/25880 [1:05:38<4:41:38,  1.22it/s]
1|5218|Loss: 0.8551121950149536:  20%|██        | 5217/25880 [1:05:38<4:41:38,  1.22it/s]
1|5218|Loss: 0.8551121950149536:  20%|██        | 5218/25880 [1:05:38<4:27:20,  1.29it/s]
1|5219|Loss: 0.8099421858787537:  20%|██        | 5218/25880 [1:05:39<4:27:20,  1.29it/s]
1|5219|Loss: 0.8099421858787537:  20%|██        | 5219/25880 [1:05:39<4:13:45,  1.36it/s]
1|5220|Loss: 0.9873513579368591:  20%|██        | 5219/25880 [1:05:39<4:13:45,  1.36it/s]
1|5220|Loss: 0.9873513579368591:  20%|██        | 5220/25880 [1:05:40<4:12:12,  1.37it/s]
1|5221|Loss: 0.8024008870124817:  20%|██        | 5220/25880 [1:05:40<4:12:12,  1.37it/s]
1|5221|Loss: 0.8024008870124817:  20%|██        | 5221/25880 [1:05:40<4:20:58,  1.32it/s]
1|5222|Loss: 0.9001481533050537:  20%|██        | 5221/25880 [1:05:41<4:20:58,  1.32it/s]
1|5222|Loss: 0.9001481533050537:  20%|██        | 5222/25880 [1:05:41<4:31:37,  1.27it/s]
1|5223|Loss: 0.8016007542610168:  20%|██        | 5222/25880 [1:05:42<4:31:37,  1.27it/s]
1|5223|Loss: 0.8016007542610168:  20%|██        | 5223/25880 [1:05:42<4:27:18,  1.29it/s]
1|5224|Loss: 0.7882092595100403:  20%|██        | 5223/25880 [1:05:42<4:27:18,  1.29it/s]
1|5224|Loss: 0.7882092595100403:  20%|██        | 5224/25880 [1:05:43<4:29:42,  1.28it/s]
1|5225|Loss: 0.8860920667648315:  20%|██        | 5224/25880 [1:05:43<4:29:42,  1.28it/s]
1|5225|Loss: 0.8860920667648315:  20%|██        | 5225/25880 [1:05:44<4:18:11,  1.33it/s]
1|5226|Loss: 0.8860223293304443:  20%|██        | 5225/25880 [1:05:44<4:18:11,  1.33it/s]
1|5226|Loss: 0.8860223293304443:  20%|██        | 5226/25880 [1:05:44<4:16:07,  1.34it/s]
1|5227|Loss: 0.8232941627502441:  20%|██        | 5226/25880 [1:05:45<4:16:07,  1.34it/s]
1|5227|Loss: 0.8232941627502441:  20%|██        | 5227/25880 [1:05:45<4:20:13,  1.32it/s]
1|5228|Loss: 0.9357245564460754:  20%|██        | 5227/25880 [1:05:45<4:20:13,  1.32it/s]
1|5228|Loss: 0.9357245564460754:  20%|██        | 5228/25880 [1:05:46<4:12:23,  1.36it/s]
1|5229|Loss: 0.8624932765960693:  20%|██        | 5228/25880 [1:05:46<4:12:23,  1.36it/s]
1|5229|Loss: 0.8624932765960693:  20%|██        | 5229/25880 [1:05:46<4:00:30,  1.43it/s]
1|5230|Loss: 0.9633783102035522:  20%|██        | 5229/25880 [1:05:47<4:00:30,  1.43it/s]
1|5230|Loss: 0.9633783102035522:  20%|██        | 5230/25880 [1:05:47<4:11:26,  1.37it/s]
1|5231|Loss: 0.9130926728248596:  20%|██        | 5230/25880 [1:05:48<4:11:26,  1.37it/s]
1|5231|Loss: 0.9130926728248596:  20%|██        | 5231/25880 [1:05:48<4:18:54,  1.33it/s]
1|5232|Loss: 0.9020631313323975:  20%|██        | 5231/25880 [1:05:48<4:18:54,  1.33it/s]
1|5232|Loss: 0.9020631313323975:  20%|██        | 5232/25880 [1:05:49<4:11:02,  1.37it/s]
1|5233|Loss: 0.8195925951004028:  20%|██        | 5232/25880 [1:05:49<4:11:02,  1.37it/s]
1|5233|Loss: 0.8195925951004028:  20%|██        | 5233/25880 [1:05:49<3:46:18,  1.52it/s]
1|5234|Loss: 0.7430764436721802:  20%|██        | 5233/25880 [1:05:49<3:46:18,  1.52it/s]
1|5234|Loss: 0.7430764436721802:  20%|██        | 5234/25880 [1:05:50<3:39:42,  1.57it/s]
1|5235|Loss: 0.922022819519043:  20%|██        | 5234/25880 [1:05:50<3:39:42,  1.57it/s] 
1|5235|Loss: 0.922022819519043:  20%|██        | 5235/25880 [1:05:51<4:02:16,  1.42it/s]
1|5236|Loss: 0.809013843536377:  20%|██        | 5235/25880 [1:05:51<4:02:16,  1.42it/s]
1|5236|Loss: 0.809013843536377:  20%|██        | 5236/25880 [1:05:51<4:20:28,  1.32it/s]
1|5237|Loss: 0.7848522067070007:  20%|██        | 5236/25880 [1:05:52<4:20:28,  1.32it/s]
1|5237|Loss: 0.7848522067070007:  20%|██        | 5237/25880 [1:05:52<4:28:00,  1.28it/s]
1|5238|Loss: 1.0076324939727783:  20%|██        | 5237/25880 [1:05:53<4:28:00,  1.28it/s]
1|5238|Loss: 1.0076324939727783:  20%|██        | 5238/25880 [1:05:53<4:22:33,  1.31it/s]
1|5239|Loss: 0.8057844638824463:  20%|██        | 5238/25880 [1:05:53<4:22:33,  1.31it/s]
1|5239|Loss: 0.8057844638824463:  20%|██        | 5239/25880 [1:05:54<4:10:58,  1.37it/s]
1|5240|Loss: 0.8143927454948425:  20%|██        | 5239/25880 [1:05:54<4:10:58,  1.37it/s]
1|5240|Loss: 0.8143927454948425:  20%|██        | 5240/25880 [1:05:55<4:24:59,  1.30it/s]
1|5241|Loss: 0.9625207781791687:  20%|██        | 5240/25880 [1:05:55<4:24:59,  1.30it/s]
1|5241|Loss: 0.9625207781791687:  20%|██        | 5241/25880 [1:05:55<4:44:27,  1.21it/s]
1|5242|Loss: 0.9157785177230835:  20%|██        | 5241/25880 [1:05:56<4:44:27,  1.21it/s]
1|5242|Loss: 0.9157785177230835:  20%|██        | 5242/25880 [1:05:56<4:38:55,  1.23it/s]
1|5243|Loss: 1.013350009918213:  20%|██        | 5242/25880 [1:05:57<4:38:55,  1.23it/s] 
1|5243|Loss: 1.013350009918213:  20%|██        | 5243/25880 [1:05:57<4:17:36,  1.34it/s]
1|5244|Loss: 0.8259263038635254:  20%|██        | 5243/25880 [1:05:57<4:17:36,  1.34it/s]
1|5244|Loss: 0.8259263038635254:  20%|██        | 5244/25880 [1:05:58<4:09:16,  1.38it/s]
1|5245|Loss: 0.8224403262138367:  20%|██        | 5244/25880 [1:05:58<4:09:16,  1.38it/s]
1|5245|Loss: 0.8224403262138367:  20%|██        | 5245/25880 [1:05:58<4:20:35,  1.32it/s]
1|5246|Loss: 0.797258198261261:  20%|██        | 5245/25880 [1:05:59<4:20:35,  1.32it/s] 
1|5246|Loss: 0.797258198261261:  20%|██        | 5246/25880 [1:05:59<3:54:35,  1.47it/s]
1|5247|Loss: 0.7699121832847595:  20%|██        | 5246/25880 [1:05:59<3:54:35,  1.47it/s]
1|5247|Loss: 0.7699121832847595:  20%|██        | 5247/25880 [1:05:59<3:49:24,  1.50it/s]
1|5248|Loss: 0.9203429222106934:  20%|██        | 5247/25880 [1:06:00<3:49:24,  1.50it/s]
1|5248|Loss: 0.9203429222106934:  20%|██        | 5248/25880 [1:06:00<4:05:03,  1.40it/s]
1|5249|Loss: 0.8876684308052063:  20%|██        | 5248/25880 [1:06:01<4:05:03,  1.40it/s]
1|5249|Loss: 0.8876684308052063:  20%|██        | 5249/25880 [1:06:01<3:51:01,  1.49it/s]
1|5250|Loss: 0.9510142207145691:  20%|██        | 5249/25880 [1:06:01<3:51:01,  1.49it/s]
1|5250|Loss: 0.9510142207145691:  20%|██        | 5250/25880 [1:06:01<3:43:07,  1.54it/s]
1|5251|Loss: 0.8403337001800537:  20%|██        | 5250/25880 [1:06:02<3:43:07,  1.54it/s]
1|5251|Loss: 0.8403337001800537:  20%|██        | 5251/25880 [1:06:02<3:26:15,  1.67it/s]
1|5252|Loss: 0.9017339944839478:  20%|██        | 5251/25880 [1:06:02<3:26:15,  1.67it/s]
1|5252|Loss: 0.9017339944839478:  20%|██        | 5252/25880 [1:06:03<3:41:57,  1.55it/s]
1|5253|Loss: 0.744182288646698:  20%|██        | 5252/25880 [1:06:03<3:41:57,  1.55it/s] 
1|5253|Loss: 0.744182288646698:  20%|██        | 5253/25880 [1:06:04<4:01:00,  1.43it/s]
1|5254|Loss: 0.8329178094863892:  20%|██        | 5253/25880 [1:06:04<4:01:00,  1.43it/s]
1|5254|Loss: 0.8329178094863892:  20%|██        | 5254/25880 [1:06:04<4:18:19,  1.33it/s]
1|5255|Loss: 1.0016670227050781:  20%|██        | 5254/25880 [1:06:05<4:18:19,  1.33it/s]
1|5255|Loss: 1.0016670227050781:  20%|██        | 5255/25880 [1:06:05<4:12:51,  1.36it/s]
1|5256|Loss: 0.8324828147888184:  20%|██        | 5255/25880 [1:06:06<4:12:51,  1.36it/s]
1|5256|Loss: 0.8324828147888184:  20%|██        | 5256/25880 [1:06:06<4:11:22,  1.37it/s]
1|5257|Loss: 0.9395520091056824:  20%|██        | 5256/25880 [1:06:06<4:11:22,  1.37it/s]
1|5257|Loss: 0.9395520091056824:  20%|██        | 5257/25880 [1:06:07<4:09:59,  1.37it/s]
1|5258|Loss: 0.8409606218338013:  20%|██        | 5257/25880 [1:06:07<4:09:59,  1.37it/s]
1|5258|Loss: 0.8409606218338013:  20%|██        | 5258/25880 [1:06:07<4:20:58,  1.32it/s]
1|5259|Loss: 0.8887388706207275:  20%|██        | 5258/25880 [1:06:08<4:20:58,  1.32it/s]
1|5259|Loss: 0.8887388706207275:  20%|██        | 5259/25880 [1:06:08<4:33:00,  1.26it/s]
1|5260|Loss: 0.9044126868247986:  20%|██        | 5259/25880 [1:06:09<4:33:00,  1.26it/s]
1|5260|Loss: 0.9044126868247986:  20%|██        | 5260/25880 [1:06:09<4:29:53,  1.27it/s]
1|5261|Loss: 0.9180532097816467:  20%|██        | 5260/25880 [1:06:09<4:29:53,  1.27it/s]
1|5261|Loss: 0.9180532097816467:  20%|██        | 5261/25880 [1:06:10<4:32:12,  1.26it/s]
1|5262|Loss: 0.8388859033584595:  20%|██        | 5261/25880 [1:06:10<4:32:12,  1.26it/s]
1|5262|Loss: 0.8388859033584595:  20%|██        | 5262/25880 [1:06:11<4:25:13,  1.30it/s]
1|5263|Loss: 0.845411479473114:  20%|██        | 5262/25880 [1:06:11<4:25:13,  1.30it/s] 
1|5263|Loss: 0.845411479473114:  20%|██        | 5263/25880 [1:06:11<4:07:36,  1.39it/s]
1|5264|Loss: 0.8437690734863281:  20%|██        | 5263/25880 [1:06:11<4:07:36,  1.39it/s]
1|5264|Loss: 0.8437690734863281:  20%|██        | 5264/25880 [1:06:12<3:47:07,  1.51it/s]
1|5265|Loss: 0.8226345777511597:  20%|██        | 5264/25880 [1:06:12<3:47:07,  1.51it/s]
1|5265|Loss: 0.8226345777511597:  20%|██        | 5265/25880 [1:06:12<3:46:28,  1.52it/s]
1|5266|Loss: 0.8099115490913391:  20%|██        | 5265/25880 [1:06:13<3:46:28,  1.52it/s]
1|5266|Loss: 0.8099115490913391:  20%|██        | 5266/25880 [1:06:13<4:00:53,  1.43it/s]
1|5267|Loss: 0.8195554614067078:  20%|██        | 5266/25880 [1:06:14<4:00:53,  1.43it/s]
1|5267|Loss: 0.8195554614067078:  20%|██        | 5267/25880 [1:06:14<4:07:01,  1.39it/s]
1|5268|Loss: 0.8260634541511536:  20%|██        | 5267/25880 [1:06:14<4:07:01,  1.39it/s]
1|5268|Loss: 0.8260634541511536:  20%|██        | 5268/25880 [1:06:14<3:39:14,  1.57it/s]
1|5269|Loss: 0.7570685744285583:  20%|██        | 5268/25880 [1:06:15<3:39:14,  1.57it/s]
1|5269|Loss: 0.7570685744285583:  20%|██        | 5269/25880 [1:06:15<3:41:45,  1.55it/s]
1|5270|Loss: 0.8879342079162598:  20%|██        | 5269/25880 [1:06:15<3:41:45,  1.55it/s]
1|5270|Loss: 0.8879342079162598:  20%|██        | 5270/25880 [1:06:16<3:40:47,  1.56it/s]
1|5271|Loss: 0.8400306105613708:  20%|██        | 5270/25880 [1:06:16<3:40:47,  1.56it/s]
1|5271|Loss: 0.8400306105613708:  20%|██        | 5271/25880 [1:06:16<3:39:59,  1.56it/s]
1|5272|Loss: 0.8422669768333435:  20%|██        | 5271/25880 [1:06:17<3:39:59,  1.56it/s]
1|5272|Loss: 0.8422669768333435:  20%|██        | 5272/25880 [1:06:17<3:44:52,  1.53it/s]
1|5273|Loss: 0.8367761373519897:  20%|██        | 5272/25880 [1:06:17<3:44:52,  1.53it/s]
1|5273|Loss: 0.8367761373519897:  20%|██        | 5273/25880 [1:06:18<3:51:14,  1.49it/s]
1|5274|Loss: 0.8104167580604553:  20%|██        | 5273/25880 [1:06:18<3:51:14,  1.49it/s]
1|5274|Loss: 0.8104167580604553:  20%|██        | 5274/25880 [1:06:18<4:03:04,  1.41it/s]
1|5275|Loss: 0.7708089351654053:  20%|██        | 5274/25880 [1:06:19<4:03:04,  1.41it/s]
1|5275|Loss: 0.7708089351654053:  20%|██        | 5275/25880 [1:06:19<4:14:37,  1.35it/s]
1|5276|Loss: 0.7667278051376343:  20%|██        | 5275/25880 [1:06:20<4:14:37,  1.35it/s]
1|5276|Loss: 0.7667278051376343:  20%|██        | 5276/25880 [1:06:20<4:04:00,  1.41it/s]
1|5277|Loss: 0.8331220746040344:  20%|██        | 5276/25880 [1:06:20<4:04:00,  1.41it/s]
1|5277|Loss: 0.8331220746040344:  20%|██        | 5277/25880 [1:06:21<4:21:33,  1.31it/s]
1|5278|Loss: 0.8864423036575317:  20%|██        | 5277/25880 [1:06:21<4:21:33,  1.31it/s]
1|5278|Loss: 0.8864423036575317:  20%|██        | 5278/25880 [1:06:22<4:20:40,  1.32it/s]
1|5279|Loss: 1.0199257135391235:  20%|██        | 5278/25880 [1:06:22<4:20:40,  1.32it/s]
1|5279|Loss: 1.0199257135391235:  20%|██        | 5279/25880 [1:06:22<4:22:08,  1.31it/s]
1|5280|Loss: 0.9223477840423584:  20%|██        | 5279/25880 [1:06:23<4:22:08,  1.31it/s]
1|5280|Loss: 0.9223477840423584:  20%|██        | 5280/25880 [1:06:23<4:17:55,  1.33it/s]
1|5281|Loss: 0.8623815178871155:  20%|██        | 5280/25880 [1:06:23<4:17:55,  1.33it/s]
1|5281|Loss: 0.8623815178871155:  20%|██        | 5281/25880 [1:06:24<4:24:58,  1.30it/s]
1|5282|Loss: 0.6483356356620789:  20%|██        | 5281/25880 [1:06:24<4:24:58,  1.30it/s]
1|5282|Loss: 0.6483356356620789:  20%|██        | 5282/25880 [1:06:24<4:07:00,  1.39it/s]
1|5283|Loss: 0.8473814129829407:  20%|██        | 5282/25880 [1:06:25<4:07:00,  1.39it/s]
1|5283|Loss: 0.8473814129829407:  20%|██        | 5283/25880 [1:06:25<4:08:25,  1.38it/s]
1|5284|Loss: 0.6932645440101624:  20%|██        | 5283/25880 [1:06:26<4:08:25,  1.38it/s]
1|5284|Loss: 0.6932645440101624:  20%|██        | 5284/25880 [1:06:26<4:10:30,  1.37it/s]
1|5285|Loss: 0.9378305077552795:  20%|██        | 5284/25880 [1:06:26<4:10:30,  1.37it/s]
1|5285|Loss: 0.9378305077552795:  20%|██        | 5285/25880 [1:06:27<4:07:52,  1.38it/s]
1|5286|Loss: 0.792514443397522:  20%|██        | 5285/25880 [1:06:27<4:07:52,  1.38it/s] 
1|5286|Loss: 0.792514443397522:  20%|██        | 5286/25880 [1:06:27<4:08:46,  1.38it/s]
1|5287|Loss: 0.9236909747123718:  20%|██        | 5286/25880 [1:06:28<4:08:46,  1.38it/s]
1|5287|Loss: 0.9236909747123718:  20%|██        | 5287/25880 [1:06:28<4:03:14,  1.41it/s]
1|5288|Loss: 0.9946255087852478:  20%|██        | 5287/25880 [1:06:28<4:03:14,  1.41it/s]
1|5288|Loss: 0.9946255087852478:  20%|██        | 5288/25880 [1:06:29<4:01:42,  1.42it/s]
1|5289|Loss: 0.8249949812889099:  20%|██        | 5288/25880 [1:06:29<4:01:42,  1.42it/s]
1|5289|Loss: 0.8249949812889099:  20%|██        | 5289/25880 [1:06:29<3:56:11,  1.45it/s]
1|5290|Loss: 0.8642885684967041:  20%|██        | 5289/25880 [1:06:30<3:56:11,  1.45it/s]
1|5290|Loss: 0.8642885684967041:  20%|██        | 5290/25880 [1:06:30<4:04:28,  1.40it/s]
1|5291|Loss: 1.0003738403320312:  20%|██        | 5290/25880 [1:06:31<4:04:28,  1.40it/s]
1|5291|Loss: 1.0003738403320312:  20%|██        | 5291/25880 [1:06:31<4:12:02,  1.36it/s]
1|5292|Loss: 0.8041254281997681:  20%|██        | 5291/25880 [1:06:31<4:12:02,  1.36it/s]
1|5292|Loss: 0.8041254281997681:  20%|██        | 5292/25880 [1:06:32<4:02:09,  1.42it/s]
1|5293|Loss: 0.9079629182815552:  20%|██        | 5292/25880 [1:06:32<4:02:09,  1.42it/s]
1|5293|Loss: 0.9079629182815552:  20%|██        | 5293/25880 [1:06:32<4:00:42,  1.43it/s]
1|5294|Loss: 0.8704081177711487:  20%|██        | 5293/25880 [1:06:33<4:00:42,  1.43it/s]
1|5294|Loss: 0.8704081177711487:  20%|██        | 5294/25880 [1:06:33<3:51:32,  1.48it/s]
1|5295|Loss: 0.8736133575439453:  20%|██        | 5294/25880 [1:06:33<3:51:32,  1.48it/s]
1|5295|Loss: 0.8736133575439453:  20%|██        | 5295/25880 [1:06:34<3:54:54,  1.46it/s]
1|5296|Loss: 0.8850945234298706:  20%|██        | 5295/25880 [1:06:34<3:54:54,  1.46it/s]
1|5296|Loss: 0.8850945234298706:  20%|██        | 5296/25880 [1:06:34<3:52:43,  1.47it/s]
1|5297|Loss: 0.9977917671203613:  20%|██        | 5296/25880 [1:06:35<3:52:43,  1.47it/s]
1|5297|Loss: 0.9977917671203613:  20%|██        | 5297/25880 [1:06:35<3:46:54,  1.51it/s]
1|5298|Loss: 1.0222870111465454:  20%|██        | 5297/25880 [1:06:35<3:46:54,  1.51it/s]
1|5298|Loss: 1.0222870111465454:  20%|██        | 5298/25880 [1:06:36<3:42:18,  1.54it/s]
1|5299|Loss: 0.8007479906082153:  20%|██        | 5298/25880 [1:06:36<3:42:18,  1.54it/s]
1|5299|Loss: 0.8007479906082153:  20%|██        | 5299/25880 [1:06:36<3:45:47,  1.52it/s]
1|5300|Loss: 0.8131647706031799:  20%|██        | 5299/25880 [1:06:37<3:45:47,  1.52it/s]
1|5300|Loss: 0.8131647706031799:  20%|██        | 5300/25880 [1:06:37<3:39:49,  1.56it/s]
1|5301|Loss: 0.8906156420707703:  20%|██        | 5300/25880 [1:06:37<3:39:49,  1.56it/s]
1|5301|Loss: 0.8906156420707703:  20%|██        | 5301/25880 [1:06:38<3:55:30,  1.46it/s]
1|5302|Loss: 1.0002835988998413:  20%|██        | 5301/25880 [1:06:38<3:55:30,  1.46it/s]
1|5302|Loss: 1.0002835988998413:  20%|██        | 5302/25880 [1:06:38<4:07:28,  1.39it/s]
1|5303|Loss: 0.8343462347984314:  20%|██        | 5302/25880 [1:06:39<4:07:28,  1.39it/s]
1|5303|Loss: 0.8343462347984314:  20%|██        | 5303/25880 [1:06:39<4:00:49,  1.42it/s]
1|5304|Loss: 0.7635313868522644:  20%|██        | 5303/25880 [1:06:39<4:00:49,  1.42it/s]
1|5304|Loss: 0.7635313868522644:  20%|██        | 5304/25880 [1:06:40<4:00:29,  1.43it/s]
1|5305|Loss: 0.8770740628242493:  20%|██        | 5304/25880 [1:06:40<4:00:29,  1.43it/s]
1|5305|Loss: 0.8770740628242493:  20%|██        | 5305/25880 [1:06:40<3:50:32,  1.49it/s]
1|5306|Loss: 0.8994772434234619:  20%|██        | 5305/25880 [1:06:41<3:50:32,  1.49it/s]
1|5306|Loss: 0.8994772434234619:  21%|██        | 5306/25880 [1:06:41<4:02:51,  1.41it/s]
1|5307|Loss: 0.828496515750885:  21%|██        | 5306/25880 [1:06:42<4:02:51,  1.41it/s] 
1|5307|Loss: 0.828496515750885:  21%|██        | 5307/25880 [1:06:42<4:08:06,  1.38it/s]
1|5308|Loss: 0.5688536763191223:  21%|██        | 5307/25880 [1:06:42<4:08:06,  1.38it/s]
1|5308|Loss: 0.5688536763191223:  21%|██        | 5308/25880 [1:06:43<4:23:46,  1.30it/s]
1|5309|Loss: 0.9153813123703003:  21%|██        | 5308/25880 [1:06:43<4:23:46,  1.30it/s]
1|5309|Loss: 0.9153813123703003:  21%|██        | 5309/25880 [1:06:44<4:43:28,  1.21it/s]
1|5310|Loss: 0.7926665544509888:  21%|██        | 5309/25880 [1:06:44<4:43:28,  1.21it/s]
1|5310|Loss: 0.7926665544509888:  21%|██        | 5310/25880 [1:06:44<4:31:03,  1.26it/s]
1|5311|Loss: 0.7505409717559814:  21%|██        | 5310/25880 [1:06:45<4:31:03,  1.26it/s]
1|5311|Loss: 0.7505409717559814:  21%|██        | 5311/25880 [1:06:45<4:33:07,  1.26it/s]
1|5312|Loss: 0.8776455521583557:  21%|██        | 5311/25880 [1:06:46<4:33:07,  1.26it/s]
1|5312|Loss: 0.8776455521583557:  21%|██        | 5312/25880 [1:06:46<4:29:46,  1.27it/s]
1|5313|Loss: 0.7161316871643066:  21%|██        | 5312/25880 [1:06:46<4:29:46,  1.27it/s]
1|5313|Loss: 0.7161316871643066:  21%|██        | 5313/25880 [1:06:47<4:25:33,  1.29it/s]
1|5314|Loss: 0.8539589047431946:  21%|██        | 5313/25880 [1:06:47<4:25:33,  1.29it/s]
1|5314|Loss: 0.8539589047431946:  21%|██        | 5314/25880 [1:06:47<4:14:10,  1.35it/s]
1|5315|Loss: 0.7851498126983643:  21%|██        | 5314/25880 [1:06:48<4:14:10,  1.35it/s]
1|5315|Loss: 0.7851498126983643:  21%|██        | 5315/25880 [1:06:48<4:09:12,  1.38it/s]
1|5316|Loss: 0.8356964588165283:  21%|██        | 5315/25880 [1:06:48<4:09:12,  1.38it/s]
1|5316|Loss: 0.8356964588165283:  21%|██        | 5316/25880 [1:06:49<3:56:43,  1.45it/s]
1|5317|Loss: 0.8451715111732483:  21%|██        | 5316/25880 [1:06:49<3:56:43,  1.45it/s]
1|5317|Loss: 0.8451715111732483:  21%|██        | 5317/25880 [1:06:49<3:35:16,  1.59it/s]
1|5318|Loss: 0.8270205855369568:  21%|██        | 5317/25880 [1:06:50<3:35:16,  1.59it/s]
1|5318|Loss: 0.8270205855369568:  21%|██        | 5318/25880 [1:06:50<3:40:58,  1.55it/s]
1|5319|Loss: 0.6385749578475952:  21%|██        | 5318/25880 [1:06:50<3:40:58,  1.55it/s]
1|5319|Loss: 0.6385749578475952:  21%|██        | 5319/25880 [1:06:51<3:43:01,  1.54it/s]
1|5320|Loss: 0.9224211573600769:  21%|██        | 5319/25880 [1:06:51<3:43:01,  1.54it/s]
1|5320|Loss: 0.9224211573600769:  21%|██        | 5320/25880 [1:06:51<3:46:44,  1.51it/s]
1|5321|Loss: 0.7638243436813354:  21%|██        | 5320/25880 [1:06:52<3:46:44,  1.51it/s]
1|5321|Loss: 0.7638243436813354:  21%|██        | 5321/25880 [1:06:52<3:43:20,  1.53it/s]
1|5322|Loss: 0.7598466277122498:  21%|██        | 5321/25880 [1:06:52<3:43:20,  1.53it/s]
1|5322|Loss: 0.7598466277122498:  21%|██        | 5322/25880 [1:06:52<3:28:51,  1.64it/s]
1|5323|Loss: 0.8783944845199585:  21%|██        | 5322/25880 [1:06:53<3:28:51,  1.64it/s]
1|5323|Loss: 0.8783944845199585:  21%|██        | 5323/25880 [1:06:53<3:26:56,  1.66it/s]
1|5324|Loss: 0.6815821528434753:  21%|██        | 5323/25880 [1:06:53<3:26:56,  1.66it/s]
1|5324|Loss: 0.6815821528434753:  21%|██        | 5324/25880 [1:06:54<3:26:08,  1.66it/s]
1|5325|Loss: 1.0223435163497925:  21%|██        | 5324/25880 [1:06:54<3:26:08,  1.66it/s]
1|5325|Loss: 1.0223435163497925:  21%|██        | 5325/25880 [1:06:54<3:26:52,  1.66it/s]
1|5326|Loss: 0.802993655204773:  21%|██        | 5325/25880 [1:06:55<3:26:52,  1.66it/s] 
1|5326|Loss: 0.802993655204773:  21%|██        | 5326/25880 [1:06:55<3:27:52,  1.65it/s]
1|5327|Loss: 0.804338276386261:  21%|██        | 5326/25880 [1:06:55<3:27:52,  1.65it/s]
1|5327|Loss: 0.804338276386261:  21%|██        | 5327/25880 [1:06:55<3:26:08,  1.66it/s]
1|5328|Loss: 0.8100429177284241:  21%|██        | 5327/25880 [1:06:56<3:26:08,  1.66it/s]
1|5328|Loss: 0.8100429177284241:  21%|██        | 5328/25880 [1:06:56<3:56:07,  1.45it/s]
1|5329|Loss: 0.7233683466911316:  21%|██        | 5328/25880 [1:06:57<3:56:07,  1.45it/s]
1|5329|Loss: 0.7233683466911316:  21%|██        | 5329/25880 [1:06:57<4:06:48,  1.39it/s]
1|5330|Loss: 0.9764028787612915:  21%|██        | 5329/25880 [1:06:58<4:06:48,  1.39it/s]
1|5330|Loss: 0.9764028787612915:  21%|██        | 5330/25880 [1:06:58<4:24:46,  1.29it/s]
1|5331|Loss: 0.9083007574081421:  21%|██        | 5330/25880 [1:06:58<4:24:46,  1.29it/s]
1|5331|Loss: 0.9083007574081421:  21%|██        | 5331/25880 [1:06:59<4:32:42,  1.26it/s]
1|5332|Loss: 0.7760909199714661:  21%|██        | 5331/25880 [1:06:59<4:32:42,  1.26it/s]
1|5332|Loss: 0.7760909199714661:  21%|██        | 5332/25880 [1:07:00<4:27:36,  1.28it/s]
1|5333|Loss: 0.9188117384910583:  21%|██        | 5332/25880 [1:07:00<4:27:36,  1.28it/s]
1|5333|Loss: 0.9188117384910583:  21%|██        | 5333/25880 [1:07:00<4:22:56,  1.30it/s]
1|5334|Loss: 0.8903557658195496:  21%|██        | 5333/25880 [1:07:01<4:22:56,  1.30it/s]
1|5334|Loss: 0.8903557658195496:  21%|██        | 5334/25880 [1:07:01<4:34:31,  1.25it/s]
1|5335|Loss: 0.8899610638618469:  21%|██        | 5334/25880 [1:07:02<4:34:31,  1.25it/s]
1|5335|Loss: 0.8899610638618469:  21%|██        | 5335/25880 [1:07:02<4:47:01,  1.19it/s]
1|5336|Loss: 0.7581871151924133:  21%|██        | 5335/25880 [1:07:03<4:47:01,  1.19it/s]
1|5336|Loss: 0.7581871151924133:  21%|██        | 5336/25880 [1:07:03<4:37:52,  1.23it/s]
1|5337|Loss: 0.8660128116607666:  21%|██        | 5336/25880 [1:07:03<4:37:52,  1.23it/s]
1|5337|Loss: 0.8660128116607666:  21%|██        | 5337/25880 [1:07:04<4:28:49,  1.27it/s]
1|5338|Loss: 0.9080413579940796:  21%|██        | 5337/25880 [1:07:04<4:28:49,  1.27it/s]
1|5338|Loss: 0.9080413579940796:  21%|██        | 5338/25880 [1:07:04<4:31:16,  1.26it/s]
1|5339|Loss: 0.7370976805686951:  21%|██        | 5338/25880 [1:07:05<4:31:16,  1.26it/s]
1|5339|Loss: 0.7370976805686951:  21%|██        | 5339/25880 [1:07:05<4:26:26,  1.28it/s]
1|5340|Loss: 0.7823600769042969:  21%|██        | 5339/25880 [1:07:06<4:26:26,  1.28it/s]
1|5340|Loss: 0.7823600769042969:  21%|██        | 5340/25880 [1:07:06<4:18:51,  1.32it/s]
1|5341|Loss: 0.8964875936508179:  21%|██        | 5340/25880 [1:07:06<4:18:51,  1.32it/s]
1|5341|Loss: 0.8964875936508179:  21%|██        | 5341/25880 [1:07:07<4:20:16,  1.32it/s]
1|5342|Loss: 0.8831285834312439:  21%|██        | 5341/25880 [1:07:07<4:20:16,  1.32it/s]
1|5342|Loss: 0.8831285834312439:  21%|██        | 5342/25880 [1:07:07<4:06:22,  1.39it/s]
1|5343|Loss: 1.0175087451934814:  21%|██        | 5342/25880 [1:07:08<4:06:22,  1.39it/s]
1|5343|Loss: 1.0175087451934814:  21%|██        | 5343/25880 [1:07:08<4:11:52,  1.36it/s]
1|5344|Loss: 0.8581163287162781:  21%|██        | 5343/25880 [1:07:08<4:11:52,  1.36it/s]
1|5344|Loss: 0.8581163287162781:  21%|██        | 5344/25880 [1:07:09<4:21:05,  1.31it/s]
1|5345|Loss: 0.8030973672866821:  21%|██        | 5344/25880 [1:07:09<4:21:05,  1.31it/s]
1|5345|Loss: 0.8030973672866821:  21%|██        | 5345/25880 [1:07:09<4:10:13,  1.37it/s]
1|5346|Loss: 0.8252094984054565:  21%|██        | 5345/25880 [1:07:10<4:10:13,  1.37it/s]
1|5346|Loss: 0.8252094984054565:  21%|██        | 5346/25880 [1:07:10<4:08:06,  1.38it/s]
1|5347|Loss: 0.8649742007255554:  21%|██        | 5346/25880 [1:07:11<4:08:06,  1.38it/s]
1|5347|Loss: 0.8649742007255554:  21%|██        | 5347/25880 [1:07:11<4:12:55,  1.35it/s]
1|5348|Loss: 0.8687061071395874:  21%|██        | 5347/25880 [1:07:11<4:12:55,  1.35it/s]
1|5348|Loss: 0.8687061071395874:  21%|██        | 5348/25880 [1:07:12<4:13:34,  1.35it/s]
1|5349|Loss: 0.8389378190040588:  21%|██        | 5348/25880 [1:07:12<4:13:34,  1.35it/s]
1|5349|Loss: 0.8389378190040588:  21%|██        | 5349/25880 [1:07:12<3:55:22,  1.45it/s]
1|5350|Loss: 0.8317972421646118:  21%|██        | 5349/25880 [1:07:13<3:55:22,  1.45it/s]
1|5350|Loss: 0.8317972421646118:  21%|██        | 5350/25880 [1:07:13<3:57:03,  1.44it/s]
1|5351|Loss: 0.8682345747947693:  21%|██        | 5350/25880 [1:07:13<3:57:03,  1.44it/s]
1|5351|Loss: 0.8682345747947693:  21%|██        | 5351/25880 [1:07:14<4:02:04,  1.41it/s]
1|5352|Loss: 0.787625253200531:  21%|██        | 5351/25880 [1:07:14<4:02:04,  1.41it/s] 
1|5352|Loss: 0.787625253200531:  21%|██        | 5352/25880 [1:07:14<3:52:08,  1.47it/s]
1|5353|Loss: 0.8925966024398804:  21%|██        | 5352/25880 [1:07:15<3:52:08,  1.47it/s]
1|5353|Loss: 0.8925966024398804:  21%|██        | 5353/25880 [1:07:15<3:59:12,  1.43it/s]
1|5354|Loss: 0.8329524397850037:  21%|██        | 5353/25880 [1:07:15<3:59:12,  1.43it/s]
1|5354|Loss: 0.8329524397850037:  21%|██        | 5354/25880 [1:07:16<3:54:24,  1.46it/s]
1|5355|Loss: 0.9281765818595886:  21%|██        | 5354/25880 [1:07:16<3:54:24,  1.46it/s]
1|5355|Loss: 0.9281765818595886:  21%|██        | 5355/25880 [1:07:17<4:02:17,  1.41it/s]
1|5356|Loss: 0.9759944081306458:  21%|██        | 5355/25880 [1:07:17<4:02:17,  1.41it/s]
1|5356|Loss: 0.9759944081306458:  21%|██        | 5356/25880 [1:07:17<3:56:32,  1.45it/s]
1|5357|Loss: 0.7613137364387512:  21%|██        | 5356/25880 [1:07:18<3:56:32,  1.45it/s]
1|5357|Loss: 0.7613137364387512:  21%|██        | 5357/25880 [1:07:18<3:58:41,  1.43it/s]
1|5358|Loss: 0.7930180430412292:  21%|██        | 5357/25880 [1:07:18<3:58:41,  1.43it/s]
1|5358|Loss: 0.7930180430412292:  21%|██        | 5358/25880 [1:07:18<3:50:12,  1.49it/s]
1|5359|Loss: 0.8630331754684448:  21%|██        | 5358/25880 [1:07:19<3:50:12,  1.49it/s]
1|5359|Loss: 0.8630331754684448:  21%|██        | 5359/25880 [1:07:19<3:45:38,  1.52it/s]
1|5360|Loss: 0.8756164312362671:  21%|██        | 5359/25880 [1:07:19<3:45:38,  1.52it/s]
1|5360|Loss: 0.8756164312362671:  21%|██        | 5360/25880 [1:07:20<3:38:40,  1.56it/s]
1|5361|Loss: 0.8721399307250977:  21%|██        | 5360/25880 [1:07:20<3:38:40,  1.56it/s]
1|5361|Loss: 0.8721399307250977:  21%|██        | 5361/25880 [1:07:20<3:44:14,  1.53it/s]
1|5362|Loss: 0.852799117565155:  21%|██        | 5361/25880 [1:07:21<3:44:14,  1.53it/s] 
1|5362|Loss: 0.852799117565155:  21%|██        | 5362/25880 [1:07:21<3:40:18,  1.55it/s]
1|5363|Loss: 0.7978304624557495:  21%|██        | 5362/25880 [1:07:21<3:40:18,  1.55it/s]
1|5363|Loss: 0.7978304624557495:  21%|██        | 5363/25880 [1:07:22<3:45:42,  1.52it/s]
1|5364|Loss: 0.7853119373321533:  21%|██        | 5363/25880 [1:07:22<3:45:42,  1.52it/s]
1|5364|Loss: 0.7853119373321533:  21%|██        | 5364/25880 [1:07:22<3:50:22,  1.48it/s]
1|5365|Loss: 0.8036379814147949:  21%|██        | 5364/25880 [1:07:23<3:50:22,  1.48it/s]
1|5365|Loss: 0.8036379814147949:  21%|██        | 5365/25880 [1:07:23<3:42:47,  1.53it/s]
1|5366|Loss: 0.9021543264389038:  21%|██        | 5365/25880 [1:07:23<3:42:47,  1.53it/s]
1|5366|Loss: 0.9021543264389038:  21%|██        | 5366/25880 [1:07:24<3:30:57,  1.62it/s]
1|5367|Loss: 0.8145002126693726:  21%|██        | 5366/25880 [1:07:24<3:30:57,  1.62it/s]
1|5367|Loss: 0.8145002126693726:  21%|██        | 5367/25880 [1:07:24<3:39:35,  1.56it/s]
1|5368|Loss: 0.8874691724777222:  21%|██        | 5367/25880 [1:07:25<3:39:35,  1.56it/s]
1|5368|Loss: 0.8874691724777222:  21%|██        | 5368/25880 [1:07:25<3:37:54,  1.57it/s]
1|5369|Loss: 0.8299578428268433:  21%|██        | 5368/25880 [1:07:25<3:37:54,  1.57it/s]
1|5369|Loss: 0.8299578428268433:  21%|██        | 5369/25880 [1:07:26<3:54:11,  1.46it/s]
1|5370|Loss: 0.8501642942428589:  21%|██        | 5369/25880 [1:07:26<3:54:11,  1.46it/s]
1|5370|Loss: 0.8501642942428589:  21%|██        | 5370/25880 [1:07:26<4:02:39,  1.41it/s]
1|5371|Loss: 0.7850173115730286:  21%|██        | 5370/25880 [1:07:27<4:02:39,  1.41it/s]
1|5371|Loss: 0.7850173115730286:  21%|██        | 5371/25880 [1:07:27<4:15:02,  1.34it/s]
1|5372|Loss: 0.8123399019241333:  21%|██        | 5371/25880 [1:07:28<4:15:02,  1.34it/s]
1|5372|Loss: 0.8123399019241333:  21%|██        | 5372/25880 [1:07:28<4:04:10,  1.40it/s]
1|5373|Loss: 0.8342678546905518:  21%|██        | 5372/25880 [1:07:28<4:04:10,  1.40it/s]
1|5373|Loss: 0.8342678546905518:  21%|██        | 5373/25880 [1:07:29<4:09:02,  1.37it/s]
1|5374|Loss: 0.8398928642272949:  21%|██        | 5373/25880 [1:07:29<4:09:02,  1.37it/s]
1|5374|Loss: 0.8398928642272949:  21%|██        | 5374/25880 [1:07:29<4:01:27,  1.42it/s]
1|5375|Loss: 0.8800079226493835:  21%|██        | 5374/25880 [1:07:30<4:01:27,  1.42it/s]
1|5375|Loss: 0.8800079226493835:  21%|██        | 5375/25880 [1:07:30<4:14:12,  1.34it/s]
1|5376|Loss: 0.8584592342376709:  21%|██        | 5375/25880 [1:07:31<4:14:12,  1.34it/s]
1|5376|Loss: 0.8584592342376709:  21%|██        | 5376/25880 [1:07:31<4:38:10,  1.23it/s]
1|5377|Loss: 0.9617547988891602:  21%|██        | 5376/25880 [1:07:32<4:38:10,  1.23it/s]
1|5377|Loss: 0.9617547988891602:  21%|██        | 5377/25880 [1:07:32<4:44:28,  1.20it/s]
1|5378|Loss: 0.7842682600021362:  21%|██        | 5377/25880 [1:07:32<4:44:28,  1.20it/s]
1|5378|Loss: 0.7842682600021362:  21%|██        | 5378/25880 [1:07:33<4:36:27,  1.24it/s]
1|5379|Loss: 0.707053542137146:  21%|██        | 5378/25880 [1:07:33<4:36:27,  1.24it/s] 
1|5379|Loss: 0.707053542137146:  21%|██        | 5379/25880 [1:07:34<4:43:22,  1.21it/s]
1|5380|Loss: 0.7999091148376465:  21%|██        | 5379/25880 [1:07:34<4:43:22,  1.21it/s]
1|5380|Loss: 0.7999091148376465:  21%|██        | 5380/25880 [1:07:34<4:42:40,  1.21it/s]
1|5381|Loss: 0.6879832148551941:  21%|██        | 5380/25880 [1:07:35<4:42:40,  1.21it/s]
1|5381|Loss: 0.6879832148551941:  21%|██        | 5381/25880 [1:07:35<4:54:50,  1.16it/s]
1|5382|Loss: 0.7918307781219482:  21%|██        | 5381/25880 [1:07:36<4:54:50,  1.16it/s]
1|5382|Loss: 0.7918307781219482:  21%|██        | 5382/25880 [1:07:36<4:47:44,  1.19it/s]
1|5383|Loss: 0.7286694049835205:  21%|██        | 5382/25880 [1:07:37<4:47:44,  1.19it/s]
1|5383|Loss: 0.7286694049835205:  21%|██        | 5383/25880 [1:07:37<4:46:05,  1.19it/s]
1|5384|Loss: 0.9574112296104431:  21%|██        | 5383/25880 [1:07:37<4:46:05,  1.19it/s]
1|5384|Loss: 0.9574112296104431:  21%|██        | 5384/25880 [1:07:38<4:26:06,  1.28it/s]
1|5385|Loss: 0.8170444965362549:  21%|██        | 5384/25880 [1:07:38<4:26:06,  1.28it/s]
1|5385|Loss: 0.8170444965362549:  21%|██        | 5385/25880 [1:07:38<4:23:56,  1.29it/s]
1|5386|Loss: 0.9344622492790222:  21%|██        | 5385/25880 [1:07:39<4:23:56,  1.29it/s]
1|5386|Loss: 0.9344622492790222:  21%|██        | 5386/25880 [1:07:39<4:13:18,  1.35it/s]
1|5387|Loss: 0.8086850047111511:  21%|██        | 5386/25880 [1:07:39<4:13:18,  1.35it/s]
1|5387|Loss: 0.8086850047111511:  21%|██        | 5387/25880 [1:07:40<3:52:42,  1.47it/s]
1|5388|Loss: 0.738004207611084:  21%|██        | 5387/25880 [1:07:40<3:52:42,  1.47it/s] 
1|5388|Loss: 0.738004207611084:  21%|██        | 5388/25880 [1:07:40<3:50:29,  1.48it/s]
1|5389|Loss: 0.8700687885284424:  21%|██        | 5388/25880 [1:07:41<3:50:29,  1.48it/s]
1|5389|Loss: 0.8700687885284424:  21%|██        | 5389/25880 [1:07:41<3:46:36,  1.51it/s]
1|5390|Loss: 0.833398163318634:  21%|██        | 5389/25880 [1:07:41<3:46:36,  1.51it/s] 
1|5390|Loss: 0.833398163318634:  21%|██        | 5390/25880 [1:07:42<3:41:48,  1.54it/s]
1|5391|Loss: 0.6288607716560364:  21%|██        | 5390/25880 [1:07:42<3:41:48,  1.54it/s]
1|5391|Loss: 0.6288607716560364:  21%|██        | 5391/25880 [1:07:43<4:13:32,  1.35it/s]
1|5392|Loss: 0.8059807419776917:  21%|██        | 5391/25880 [1:07:43<4:13:32,  1.35it/s]
1|5392|Loss: 0.8059807419776917:  21%|██        | 5392/25880 [1:07:43<4:23:37,  1.30it/s]
1|5393|Loss: 0.7063328623771667:  21%|██        | 5392/25880 [1:07:44<4:23:37,  1.30it/s]
1|5393|Loss: 0.7063328623771667:  21%|██        | 5393/25880 [1:07:44<4:40:38,  1.22it/s]
1|5394|Loss: 0.8505160212516785:  21%|██        | 5393/25880 [1:07:45<4:40:38,  1.22it/s]
1|5394|Loss: 0.8505160212516785:  21%|██        | 5394/25880 [1:07:45<4:36:30,  1.23it/s]
1|5395|Loss: 0.8864340782165527:  21%|██        | 5394/25880 [1:07:45<4:36:30,  1.23it/s]
1|5395|Loss: 0.8864340782165527:  21%|██        | 5395/25880 [1:07:46<4:26:06,  1.28it/s]
1|5396|Loss: 0.9604422450065613:  21%|██        | 5395/25880 [1:07:46<4:26:06,  1.28it/s]
1|5396|Loss: 0.9604422450065613:  21%|██        | 5396/25880 [1:07:47<4:30:39,  1.26it/s]
1|5397|Loss: 0.8353624939918518:  21%|██        | 5396/25880 [1:07:47<4:30:39,  1.26it/s]
1|5397|Loss: 0.8353624939918518:  21%|██        | 5397/25880 [1:07:48<4:49:39,  1.18it/s]
1|5398|Loss: 1.0127754211425781:  21%|██        | 5397/25880 [1:07:48<4:49:39,  1.18it/s]
1|5398|Loss: 1.0127754211425781:  21%|██        | 5398/25880 [1:07:48<4:41:13,  1.21it/s]
1|5399|Loss: 0.9402672052383423:  21%|██        | 5398/25880 [1:07:49<4:41:13,  1.21it/s]
1|5399|Loss: 0.9402672052383423:  21%|██        | 5399/25880 [1:07:49<4:28:24,  1.27it/s]
1|5400|Loss: 0.8861567378044128:  21%|██        | 5399/25880 [1:07:49<4:28:24,  1.27it/s]
1|5400|Loss: 0.8861567378044128:  21%|██        | 5400/25880 [1:07:50<4:12:29,  1.35it/s]
1|5401|Loss: 1.1170413494110107:  21%|██        | 5400/25880 [1:07:50<4:12:29,  1.35it/s]
1|5401|Loss: 1.1170413494110107:  21%|██        | 5401/25880 [1:07:50<3:46:35,  1.51it/s]
1|5402|Loss: 0.9189022779464722:  21%|██        | 5401/25880 [1:07:51<3:46:35,  1.51it/s]
1|5402|Loss: 0.9189022779464722:  21%|██        | 5402/25880 [1:07:51<3:46:44,  1.51it/s]
1|5403|Loss: 0.9381396174430847:  21%|██        | 5402/25880 [1:07:51<3:46:44,  1.51it/s]
1|5403|Loss: 0.9381396174430847:  21%|██        | 5403/25880 [1:07:52<4:01:47,  1.41it/s]
1|5404|Loss: 0.8579109311103821:  21%|██        | 5403/25880 [1:07:52<4:01:47,  1.41it/s]
1|5404|Loss: 0.8579109311103821:  21%|██        | 5404/25880 [1:07:53<4:24:50,  1.29it/s]
1|5405|Loss: 0.8412299156188965:  21%|██        | 5404/25880 [1:07:53<4:24:50,  1.29it/s]
1|5405|Loss: 0.8412299156188965:  21%|██        | 5405/25880 [1:07:53<4:23:18,  1.30it/s]
1|5406|Loss: 1.0266529321670532:  21%|██        | 5405/25880 [1:07:54<4:23:18,  1.30it/s]
1|5406|Loss: 1.0266529321670532:  21%|██        | 5406/25880 [1:07:54<4:16:00,  1.33it/s]
1|5407|Loss: 0.9075258374214172:  21%|██        | 5406/25880 [1:07:54<4:16:00,  1.33it/s]
1|5407|Loss: 0.9075258374214172:  21%|██        | 5407/25880 [1:07:55<4:10:48,  1.36it/s]
1|5408|Loss: 0.8352667093276978:  21%|██        | 5407/25880 [1:07:55<4:10:48,  1.36it/s]
1|5408|Loss: 0.8352667093276978:  21%|██        | 5408/25880 [1:07:56<4:17:43,  1.32it/s]
1|5409|Loss: 0.8964502811431885:  21%|██        | 5408/25880 [1:07:56<4:17:43,  1.32it/s]
1|5409|Loss: 0.8964502811431885:  21%|██        | 5409/25880 [1:07:56<4:32:25,  1.25it/s]
1|5410|Loss: 0.9035307765007019:  21%|██        | 5409/25880 [1:07:57<4:32:25,  1.25it/s]
1|5410|Loss: 0.9035307765007019:  21%|██        | 5410/25880 [1:07:57<4:26:11,  1.28it/s]
1|5411|Loss: 0.8224610686302185:  21%|██        | 5410/25880 [1:07:58<4:26:11,  1.28it/s]
1|5411|Loss: 0.8224610686302185:  21%|██        | 5411/25880 [1:07:58<4:12:50,  1.35it/s]
1|5412|Loss: 0.878082811832428:  21%|██        | 5411/25880 [1:07:58<4:12:50,  1.35it/s] 
1|5412|Loss: 0.878082811832428:  21%|██        | 5412/25880 [1:07:58<3:59:59,  1.42it/s]
1|5413|Loss: 0.7858809232711792:  21%|██        | 5412/25880 [1:07:59<3:59:59,  1.42it/s]
1|5413|Loss: 0.7858809232711792:  21%|██        | 5413/25880 [1:07:59<4:01:09,  1.41it/s]
1|5414|Loss: 0.8310598731040955:  21%|██        | 5413/25880 [1:08:00<4:01:09,  1.41it/s]
1|5414|Loss: 0.8310598731040955:  21%|██        | 5414/25880 [1:08:00<4:04:18,  1.40it/s]
1|5415|Loss: 0.8090773820877075:  21%|██        | 5414/25880 [1:08:00<4:04:18,  1.40it/s]
1|5415|Loss: 0.8090773820877075:  21%|██        | 5415/25880 [1:08:01<4:26:54,  1.28it/s]
1|5416|Loss: 0.9170345664024353:  21%|██        | 5415/25880 [1:08:01<4:26:54,  1.28it/s]
1|5416|Loss: 0.9170345664024353:  21%|██        | 5416/25880 [1:08:02<4:32:55,  1.25it/s]
1|5417|Loss: 0.7721051573753357:  21%|██        | 5416/25880 [1:08:02<4:32:55,  1.25it/s]
1|5417|Loss: 0.7721051573753357:  21%|██        | 5417/25880 [1:08:02<4:25:24,  1.28it/s]
1|5418|Loss: 0.7988991737365723:  21%|██        | 5417/25880 [1:08:03<4:25:24,  1.28it/s]
1|5418|Loss: 0.7988991737365723:  21%|██        | 5418/25880 [1:08:03<4:20:13,  1.31it/s]
1|5419|Loss: 0.8446871042251587:  21%|██        | 5418/25880 [1:08:04<4:20:13,  1.31it/s]
1|5419|Loss: 0.8446871042251587:  21%|██        | 5419/25880 [1:08:04<4:28:51,  1.27it/s]
1|5420|Loss: 0.9219360947608948:  21%|██        | 5419/25880 [1:08:04<4:28:51,  1.27it/s]
1|5420|Loss: 0.9219360947608948:  21%|██        | 5420/25880 [1:08:05<4:26:25,  1.28it/s]
1|5421|Loss: 0.8079987168312073:  21%|██        | 5420/25880 [1:08:05<4:26:25,  1.28it/s]
1|5421|Loss: 0.8079987168312073:  21%|██        | 5421/25880 [1:08:06<4:33:42,  1.25it/s]
1|5422|Loss: 0.734980583190918:  21%|██        | 5421/25880 [1:08:06<4:33:42,  1.25it/s] 
1|5422|Loss: 0.734980583190918:  21%|██        | 5422/25880 [1:08:06<4:27:34,  1.27it/s]
1|5423|Loss: 0.9395591616630554:  21%|██        | 5422/25880 [1:08:07<4:27:34,  1.27it/s]
1|5423|Loss: 0.9395591616630554:  21%|██        | 5423/25880 [1:08:07<4:30:37,  1.26it/s]
1|5424|Loss: 0.9692001938819885:  21%|██        | 5423/25880 [1:08:08<4:30:37,  1.26it/s]
1|5424|Loss: 0.9692001938819885:  21%|██        | 5424/25880 [1:08:08<4:35:08,  1.24it/s]
1|5425|Loss: 0.8505868911743164:  21%|██        | 5424/25880 [1:08:08<4:35:08,  1.24it/s]
1|5425|Loss: 0.8505868911743164:  21%|██        | 5425/25880 [1:08:09<4:16:22,  1.33it/s]
1|5426|Loss: 0.7453665137290955:  21%|██        | 5425/25880 [1:08:09<4:16:22,  1.33it/s]
1|5426|Loss: 0.7453665137290955:  21%|██        | 5426/25880 [1:08:09<4:04:10,  1.40it/s]
1|5427|Loss: 0.8975610733032227:  21%|██        | 5426/25880 [1:08:10<4:04:10,  1.40it/s]
1|5427|Loss: 0.8975610733032227:  21%|██        | 5427/25880 [1:08:10<4:05:04,  1.39it/s]
1|5428|Loss: 0.8747603297233582:  21%|██        | 5427/25880 [1:08:10<4:05:04,  1.39it/s]
1|5428|Loss: 0.8747603297233582:  21%|██        | 5428/25880 [1:08:11<4:05:50,  1.39it/s]
1|5429|Loss: 0.8354049921035767:  21%|██        | 5428/25880 [1:08:11<4:05:50,  1.39it/s]
1|5429|Loss: 0.8354049921035767:  21%|██        | 5429/25880 [1:08:11<4:11:22,  1.36it/s]
1|5430|Loss: 0.8720694184303284:  21%|██        | 5429/25880 [1:08:12<4:11:22,  1.36it/s]
1|5430|Loss: 0.8720694184303284:  21%|██        | 5430/25880 [1:08:12<4:05:11,  1.39it/s]
1|5431|Loss: 0.641607940196991:  21%|██        | 5430/25880 [1:08:13<4:05:11,  1.39it/s] 
1|5431|Loss: 0.641607940196991:  21%|██        | 5431/25880 [1:08:13<4:09:10,  1.37it/s]
1|5432|Loss: 0.9053322672843933:  21%|██        | 5431/25880 [1:08:13<4:09:10,  1.37it/s]
1|5432|Loss: 0.9053322672843933:  21%|██        | 5432/25880 [1:08:14<4:08:49,  1.37it/s]
1|5433|Loss: 0.8172404766082764:  21%|██        | 5432/25880 [1:08:14<4:08:49,  1.37it/s]
1|5433|Loss: 0.8172404766082764:  21%|██        | 5433/25880 [1:08:14<3:58:58,  1.43it/s]
1|5434|Loss: 0.9549724459648132:  21%|██        | 5433/25880 [1:08:15<3:58:58,  1.43it/s]
1|5434|Loss: 0.9549724459648132:  21%|██        | 5434/25880 [1:08:15<3:39:17,  1.55it/s]
1|5435|Loss: 0.8379135727882385:  21%|██        | 5434/25880 [1:08:15<3:39:17,  1.55it/s]
1|5435|Loss: 0.8379135727882385:  21%|██        | 5435/25880 [1:08:16<3:51:22,  1.47it/s]
1|5436|Loss: 0.962198793888092:  21%|██        | 5435/25880 [1:08:16<3:51:22,  1.47it/s] 
1|5436|Loss: 0.962198793888092:  21%|██        | 5436/25880 [1:08:16<3:59:21,  1.42it/s]
1|5437|Loss: 0.7532191872596741:  21%|██        | 5436/25880 [1:08:17<3:59:21,  1.42it/s]
1|5437|Loss: 0.7532191872596741:  21%|██        | 5437/25880 [1:08:17<3:55:36,  1.45it/s]
1|5438|Loss: 0.8179888129234314:  21%|██        | 5437/25880 [1:08:17<3:55:36,  1.45it/s]
1|5438|Loss: 0.8179888129234314:  21%|██        | 5438/25880 [1:08:18<3:48:14,  1.49it/s]
1|5439|Loss: 0.8675801753997803:  21%|██        | 5438/25880 [1:08:18<3:48:14,  1.49it/s]
1|5439|Loss: 0.8675801753997803:  21%|██        | 5439/25880 [1:08:18<3:49:15,  1.49it/s]
1|5440|Loss: 0.8676201701164246:  21%|██        | 5439/25880 [1:08:19<3:49:15,  1.49it/s]
1|5440|Loss: 0.8676201701164246:  21%|██        | 5440/25880 [1:08:19<3:46:23,  1.50it/s]
1|5441|Loss: 1.0351390838623047:  21%|██        | 5440/25880 [1:08:19<3:46:23,  1.50it/s]
1|5441|Loss: 1.0351390838623047:  21%|██        | 5441/25880 [1:08:20<3:59:19,  1.42it/s]
1|5442|Loss: 0.7492207884788513:  21%|██        | 5441/25880 [1:08:20<3:59:19,  1.42it/s]
1|5442|Loss: 0.7492207884788513:  21%|██        | 5442/25880 [1:08:21<4:16:33,  1.33it/s]
1|5443|Loss: 0.7663596272468567:  21%|██        | 5442/25880 [1:08:21<4:16:33,  1.33it/s]
1|5443|Loss: 0.7663596272468567:  21%|██        | 5443/25880 [1:08:21<4:09:06,  1.37it/s]
1|5444|Loss: 0.9588530659675598:  21%|██        | 5443/25880 [1:08:22<4:09:06,  1.37it/s]
1|5444|Loss: 0.9588530659675598:  21%|██        | 5444/25880 [1:08:22<3:59:05,  1.42it/s]
1|5445|Loss: 0.84537273645401:  21%|██        | 5444/25880 [1:08:22<3:59:05,  1.42it/s]  
1|5445|Loss: 0.84537273645401:  21%|██        | 5445/25880 [1:08:22<3:44:18,  1.52it/s]
1|5446|Loss: 0.8331372737884521:  21%|██        | 5445/25880 [1:08:23<3:44:18,  1.52it/s]
1|5446|Loss: 0.8331372737884521:  21%|██        | 5446/25880 [1:08:23<3:39:10,  1.55it/s]
1|5447|Loss: 0.8250095844268799:  21%|██        | 5446/25880 [1:08:23<3:39:10,  1.55it/s]
1|5447|Loss: 0.8250095844268799:  21%|██        | 5447/25880 [1:08:24<3:54:12,  1.45it/s]
1|5448|Loss: 0.794344961643219:  21%|██        | 5447/25880 [1:08:24<3:54:12,  1.45it/s] 
1|5448|Loss: 0.794344961643219:  21%|██        | 5448/25880 [1:08:25<4:05:32,  1.39it/s]
1|5449|Loss: 0.9273622632026672:  21%|██        | 5448/25880 [1:08:25<4:05:32,  1.39it/s]
1|5449|Loss: 0.9273622632026672:  21%|██        | 5449/25880 [1:08:25<4:07:57,  1.37it/s]
1|5450|Loss: 0.7969973087310791:  21%|██        | 5449/25880 [1:08:26<4:07:57,  1.37it/s]
1|5450|Loss: 0.7969973087310791:  21%|██        | 5450/25880 [1:08:26<4:12:15,  1.35it/s]
1|5451|Loss: 0.7961694002151489:  21%|██        | 5450/25880 [1:08:27<4:12:15,  1.35it/s]
1|5451|Loss: 0.7961694002151489:  21%|██        | 5451/25880 [1:08:27<4:20:29,  1.31it/s]
1|5452|Loss: 0.8674409985542297:  21%|██        | 5451/25880 [1:08:27<4:20:29,  1.31it/s]
1|5452|Loss: 0.8674409985542297:  21%|██        | 5452/25880 [1:08:28<4:00:25,  1.42it/s]
1|5453|Loss: 0.9111117720603943:  21%|██        | 5452/25880 [1:08:28<4:00:25,  1.42it/s]
1|5453|Loss: 0.9111117720603943:  21%|██        | 5453/25880 [1:08:28<3:50:44,  1.48it/s]
1|5454|Loss: 0.8641163110733032:  21%|██        | 5453/25880 [1:08:29<3:50:44,  1.48it/s]
1|5454|Loss: 0.8641163110733032:  21%|██        | 5454/25880 [1:08:29<3:55:16,  1.45it/s]
1|5455|Loss: 0.8788031339645386:  21%|██        | 5454/25880 [1:08:29<3:55:16,  1.45it/s]
1|5455|Loss: 0.8788031339645386:  21%|██        | 5455/25880 [1:08:29<3:37:09,  1.57it/s]
1|5456|Loss: 0.8365051746368408:  21%|██        | 5455/25880 [1:08:30<3:37:09,  1.57it/s]
1|5456|Loss: 0.8365051746368408:  21%|██        | 5456/25880 [1:08:30<3:56:20,  1.44it/s]
1|5457|Loss: 0.7882428765296936:  21%|██        | 5456/25880 [1:08:31<3:56:20,  1.44it/s]
1|5457|Loss: 0.7882428765296936:  21%|██        | 5457/25880 [1:08:31<4:04:13,  1.39it/s]
1|5458|Loss: 0.8408505320549011:  21%|██        | 5457/25880 [1:08:31<4:04:13,  1.39it/s]
1|5458|Loss: 0.8408505320549011:  21%|██        | 5458/25880 [1:08:32<4:17:37,  1.32it/s]
1|5459|Loss: 0.8085654377937317:  21%|██        | 5458/25880 [1:08:32<4:17:37,  1.32it/s]
1|5459|Loss: 0.8085654377937317:  21%|██        | 5459/25880 [1:08:33<4:15:30,  1.33it/s]
1|5460|Loss: 0.8250972628593445:  21%|██        | 5459/25880 [1:08:33<4:15:30,  1.33it/s]
1|5460|Loss: 0.8250972628593445:  21%|██        | 5460/25880 [1:08:33<4:11:03,  1.36it/s]
1|5461|Loss: 0.8320329189300537:  21%|██        | 5460/25880 [1:08:34<4:11:03,  1.36it/s]
1|5461|Loss: 0.8320329189300537:  21%|██        | 5461/25880 [1:08:34<4:06:43,  1.38it/s]
1|5462|Loss: 0.8645727634429932:  21%|██        | 5461/25880 [1:08:34<4:06:43,  1.38it/s]
1|5462|Loss: 0.8645727634429932:  21%|██        | 5462/25880 [1:08:35<4:07:37,  1.37it/s]
1|5463|Loss: 0.8347287774085999:  21%|██        | 5462/25880 [1:08:35<4:07:37,  1.37it/s]
1|5463|Loss: 0.8347287774085999:  21%|██        | 5463/25880 [1:08:36<4:19:58,  1.31it/s]
1|5464|Loss: 0.925464928150177:  21%|██        | 5463/25880 [1:08:36<4:19:58,  1.31it/s] 
1|5464|Loss: 0.925464928150177:  21%|██        | 5464/25880 [1:08:36<4:12:46,  1.35it/s]
1|5465|Loss: 0.7972467541694641:  21%|██        | 5464/25880 [1:08:37<4:12:46,  1.35it/s]
1|5465|Loss: 0.7972467541694641:  21%|██        | 5465/25880 [1:08:37<4:07:23,  1.38it/s]
1|5466|Loss: 0.7599316835403442:  21%|██        | 5465/25880 [1:08:37<4:07:23,  1.38it/s]
1|5466|Loss: 0.7599316835403442:  21%|██        | 5466/25880 [1:08:38<4:04:47,  1.39it/s]
1|5467|Loss: 0.9002748727798462:  21%|██        | 5466/25880 [1:08:38<4:04:47,  1.39it/s]
1|5467|Loss: 0.9002748727798462:  21%|██        | 5467/25880 [1:08:38<4:06:24,  1.38it/s]
1|5468|Loss: 0.9333550930023193:  21%|██        | 5467/25880 [1:08:39<4:06:24,  1.38it/s]
1|5468|Loss: 0.9333550930023193:  21%|██        | 5468/25880 [1:08:39<4:05:44,  1.38it/s]
1|5469|Loss: 0.8806520700454712:  21%|██        | 5468/25880 [1:08:39<4:05:44,  1.38it/s]
1|5469|Loss: 0.8806520700454712:  21%|██        | 5469/25880 [1:08:40<4:03:43,  1.40it/s]
1|5470|Loss: 0.9422032237052917:  21%|██        | 5469/25880 [1:08:40<4:03:43,  1.40it/s]
1|5470|Loss: 0.9422032237052917:  21%|██        | 5470/25880 [1:08:40<3:56:46,  1.44it/s]
1|5471|Loss: 1.0453517436981201:  21%|██        | 5470/25880 [1:08:41<3:56:46,  1.44it/s]
1|5471|Loss: 1.0453517436981201:  21%|██        | 5471/25880 [1:08:41<3:56:21,  1.44it/s]
1|5472|Loss: 0.8016257286071777:  21%|██        | 5471/25880 [1:08:42<3:56:21,  1.44it/s]
1|5472|Loss: 0.8016257286071777:  21%|██        | 5472/25880 [1:08:42<4:03:17,  1.40it/s]
1|5473|Loss: 0.7811951637268066:  21%|██        | 5472/25880 [1:08:42<4:03:17,  1.40it/s]
1|5473|Loss: 0.7811951637268066:  21%|██        | 5473/25880 [1:08:43<4:06:03,  1.38it/s]
1|5474|Loss: 0.8060843348503113:  21%|██        | 5473/25880 [1:08:43<4:06:03,  1.38it/s]
1|5474|Loss: 0.8060843348503113:  21%|██        | 5474/25880 [1:08:43<3:52:09,  1.46it/s]
1|5475|Loss: 0.9181849360466003:  21%|██        | 5474/25880 [1:08:44<3:52:09,  1.46it/s]
1|5475|Loss: 0.9181849360466003:  21%|██        | 5475/25880 [1:08:44<3:39:08,  1.55it/s]
1|5476|Loss: 0.7973731756210327:  21%|██        | 5475/25880 [1:08:44<3:39:08,  1.55it/s]
1|5476|Loss: 0.7973731756210327:  21%|██        | 5476/25880 [1:08:44<3:42:17,  1.53it/s]
1|5477|Loss: 0.8252525329589844:  21%|██        | 5476/25880 [1:08:45<3:42:17,  1.53it/s]
1|5477|Loss: 0.8252525329589844:  21%|██        | 5477/25880 [1:08:45<3:57:30,  1.43it/s]
1|5478|Loss: 0.9819144606590271:  21%|██        | 5477/25880 [1:08:46<3:57:30,  1.43it/s]
1|5478|Loss: 0.9819144606590271:  21%|██        | 5478/25880 [1:08:46<4:02:47,  1.40it/s]
1|5479|Loss: 0.8279284238815308:  21%|██        | 5478/25880 [1:08:46<4:02:47,  1.40it/s]
1|5479|Loss: 0.8279284238815308:  21%|██        | 5479/25880 [1:08:47<4:04:18,  1.39it/s]
1|5480|Loss: 0.8501741290092468:  21%|██        | 5479/25880 [1:08:47<4:04:18,  1.39it/s]
1|5480|Loss: 0.8501741290092468:  21%|██        | 5480/25880 [1:08:47<3:55:59,  1.44it/s]
1|5481|Loss: 0.7816144824028015:  21%|██        | 5480/25880 [1:08:48<3:55:59,  1.44it/s]
1|5481|Loss: 0.7816144824028015:  21%|██        | 5481/25880 [1:08:48<4:12:14,  1.35it/s]
1|5482|Loss: 0.7417551875114441:  21%|██        | 5481/25880 [1:08:49<4:12:14,  1.35it/s]
1|5482|Loss: 0.7417551875114441:  21%|██        | 5482/25880 [1:08:49<3:57:43,  1.43it/s]
1|5483|Loss: 0.8585476279258728:  21%|██        | 5482/25880 [1:08:49<3:57:43,  1.43it/s]
1|5483|Loss: 0.8585476279258728:  21%|██        | 5483/25880 [1:08:50<3:55:58,  1.44it/s]
1|5484|Loss: 0.7697173953056335:  21%|██        | 5483/25880 [1:08:50<3:55:58,  1.44it/s]
1|5484|Loss: 0.7697173953056335:  21%|██        | 5484/25880 [1:08:50<4:12:08,  1.35it/s]
1|5485|Loss: 0.7664911150932312:  21%|██        | 5484/25880 [1:08:51<4:12:08,  1.35it/s]
1|5485|Loss: 0.7664911150932312:  21%|██        | 5485/25880 [1:08:51<4:05:46,  1.38it/s]
1|5486|Loss: 0.8705422878265381:  21%|██        | 5485/25880 [1:08:51<4:05:46,  1.38it/s]
1|5486|Loss: 0.8705422878265381:  21%|██        | 5486/25880 [1:08:52<4:03:33,  1.40it/s]
1|5487|Loss: 1.019331693649292:  21%|██        | 5486/25880 [1:08:52<4:03:33,  1.40it/s] 
1|5487|Loss: 1.019331693649292:  21%|██        | 5487/25880 [1:08:53<4:04:57,  1.39it/s]
1|5488|Loss: 0.9013620615005493:  21%|██        | 5487/25880 [1:08:53<4:04:57,  1.39it/s]
1|5488|Loss: 0.9013620615005493:  21%|██        | 5488/25880 [1:08:53<4:07:14,  1.37it/s]
1|5489|Loss: 0.8510265946388245:  21%|██        | 5488/25880 [1:08:54<4:07:14,  1.37it/s]
1|5489|Loss: 0.8510265946388245:  21%|██        | 5489/25880 [1:08:54<4:33:56,  1.24it/s]
1|5490|Loss: 0.9343064427375793:  21%|██        | 5489/25880 [1:08:55<4:33:56,  1.24it/s]
1|5490|Loss: 0.9343064427375793:  21%|██        | 5490/25880 [1:08:55<4:38:54,  1.22it/s]
1|5491|Loss: 0.7712175846099854:  21%|██        | 5490/25880 [1:08:56<4:38:54,  1.22it/s]
1|5491|Loss: 0.7712175846099854:  21%|██        | 5491/25880 [1:08:56<4:35:58,  1.23it/s]
1|5492|Loss: 0.9521201252937317:  21%|██        | 5491/25880 [1:08:56<4:35:58,  1.23it/s]
1|5492|Loss: 0.9521201252937317:  21%|██        | 5492/25880 [1:08:57<4:30:11,  1.26it/s]
1|5493|Loss: 0.8941245675086975:  21%|██        | 5492/25880 [1:08:57<4:30:11,  1.26it/s]
1|5493|Loss: 0.8941245675086975:  21%|██        | 5493/25880 [1:08:57<4:15:47,  1.33it/s]
1|5494|Loss: 0.6802835464477539:  21%|██        | 5493/25880 [1:08:58<4:15:47,  1.33it/s]
1|5494|Loss: 0.6802835464477539:  21%|██        | 5494/25880 [1:08:58<4:38:32,  1.22it/s]
1|5495|Loss: 0.8076370358467102:  21%|██        | 5494/25880 [1:08:59<4:38:32,  1.22it/s]
1|5495|Loss: 0.8076370358467102:  21%|██        | 5495/25880 [1:08:59<4:23:39,  1.29it/s]
1|5496|Loss: 0.7473602890968323:  21%|██        | 5495/25880 [1:08:59<4:23:39,  1.29it/s]
1|5496|Loss: 0.7473602890968323:  21%|██        | 5496/25880 [1:09:00<4:25:20,  1.28it/s]
1|5497|Loss: 0.8387236595153809:  21%|██        | 5496/25880 [1:09:00<4:25:20,  1.28it/s]
1|5497|Loss: 0.8387236595153809:  21%|██        | 5497/25880 [1:09:01<4:23:50,  1.29it/s]
1|5498|Loss: 0.9561896324157715:  21%|██        | 5497/25880 [1:09:01<4:23:50,  1.29it/s]
1|5498|Loss: 0.9561896324157715:  21%|██        | 5498/25880 [1:09:01<4:29:51,  1.26it/s]
1|5499|Loss: 0.7539710402488708:  21%|██        | 5498/25880 [1:09:02<4:29:51,  1.26it/s]
1|5499|Loss: 0.7539710402488708:  21%|██        | 5499/25880 [1:09:02<4:35:21,  1.23it/s]
1|5500|Loss: 0.7011498808860779:  21%|██        | 5499/25880 [1:09:03<4:35:21,  1.23it/s]
1|5500|Loss: 0.7011498808860779:  21%|██▏       | 5500/25880 [1:09:03<4:45:27,  1.19it/s]
1|5501|Loss: 1.0020465850830078:  21%|██▏       | 5500/25880 [1:09:04<4:45:27,  1.19it/s]
1|5501|Loss: 1.0020465850830078:  21%|██▏       | 5501/25880 [1:09:04<4:50:22,  1.17it/s]
1|5502|Loss: 0.9361892938613892:  21%|██▏       | 5501/25880 [1:09:04<4:50:22,  1.17it/s]
1|5502|Loss: 0.9361892938613892:  21%|██▏       | 5502/25880 [1:09:05<4:32:23,  1.25it/s]
1|5503|Loss: 0.778491735458374:  21%|██▏       | 5502/25880 [1:09:05<4:32:23,  1.25it/s] 
1|5503|Loss: 0.778491735458374:  21%|██▏       | 5503/25880 [1:09:05<4:11:25,  1.35it/s]
1|5504|Loss: 0.8827226758003235:  21%|██▏       | 5503/25880 [1:09:06<4:11:25,  1.35it/s]
1|5504|Loss: 0.8827226758003235:  21%|██▏       | 5504/25880 [1:09:06<4:06:44,  1.38it/s]
1|5505|Loss: 0.7569313049316406:  21%|██▏       | 5504/25880 [1:09:06<4:06:44,  1.38it/s]
1|5505|Loss: 0.7569313049316406:  21%|██▏       | 5505/25880 [1:09:07<3:57:29,  1.43it/s]
1|5506|Loss: 0.6600211262702942:  21%|██▏       | 5505/25880 [1:09:07<3:57:29,  1.43it/s]
1|5506|Loss: 0.6600211262702942:  21%|██▏       | 5506/25880 [1:09:07<4:08:02,  1.37it/s]
1|5507|Loss: 0.8469015955924988:  21%|██▏       | 5506/25880 [1:09:08<4:08:02,  1.37it/s]
1|5507|Loss: 0.8469015955924988:  21%|██▏       | 5507/25880 [1:09:08<4:26:18,  1.28it/s]
1|5508|Loss: 0.8418089151382446:  21%|██▏       | 5507/25880 [1:09:09<4:26:18,  1.28it/s]
1|5508|Loss: 0.8418089151382446:  21%|██▏       | 5508/25880 [1:09:09<4:21:51,  1.30it/s]
1|5509|Loss: 0.8524609208106995:  21%|██▏       | 5508/25880 [1:09:09<4:21:51,  1.30it/s]
1|5509|Loss: 0.8524609208106995:  21%|██▏       | 5509/25880 [1:09:10<4:14:05,  1.34it/s]
1|5510|Loss: 0.8749752640724182:  21%|██▏       | 5509/25880 [1:09:10<4:14:05,  1.34it/s]
1|5510|Loss: 0.8749752640724182:  21%|██▏       | 5510/25880 [1:09:10<4:12:24,  1.35it/s]
1|5511|Loss: 0.8276276588439941:  21%|██▏       | 5510/25880 [1:09:11<4:12:24,  1.35it/s]
1|5511|Loss: 0.8276276588439941:  21%|██▏       | 5511/25880 [1:09:11<4:02:32,  1.40it/s]
1|5512|Loss: 0.8329078555107117:  21%|██▏       | 5511/25880 [1:09:11<4:02:32,  1.40it/s]
1|5512|Loss: 0.8329078555107117:  21%|██▏       | 5512/25880 [1:09:12<4:02:19,  1.40it/s]
1|5513|Loss: 0.9290508031845093:  21%|██▏       | 5512/25880 [1:09:12<4:02:19,  1.40it/s]
1|5513|Loss: 0.9290508031845093:  21%|██▏       | 5513/25880 [1:09:13<4:16:37,  1.32it/s]
1|5514|Loss: 0.9353194832801819:  21%|██▏       | 5513/25880 [1:09:13<4:16:37,  1.32it/s]
1|5514|Loss: 0.9353194832801819:  21%|██▏       | 5514/25880 [1:09:14<4:27:54,  1.27it/s]
1|5515|Loss: 0.9313865900039673:  21%|██▏       | 5514/25880 [1:09:14<4:27:54,  1.27it/s]
1|5515|Loss: 0.9313865900039673:  21%|██▏       | 5515/25880 [1:09:14<4:24:40,  1.28it/s]
1|5516|Loss: 0.8512710928916931:  21%|██▏       | 5515/25880 [1:09:15<4:24:40,  1.28it/s]
1|5516|Loss: 0.8512710928916931:  21%|██▏       | 5516/25880 [1:09:15<4:12:11,  1.35it/s]
1|5517|Loss: 0.8509548902511597:  21%|��█▏       | 5516/25880 [1:09:15<4:12:11,  1.35it/s]
1|5517|Loss: 0.8509548902511597:  21%|██▏       | 5517/25880 [1:09:16<4:19:43,  1.31it/s]
1|5518|Loss: 0.901382327079773:  21%|██▏       | 5517/25880 [1:09:16<4:19:43,  1.31it/s] 
1|5518|Loss: 0.901382327079773:  21%|██▏       | 5518/25880 [1:09:17<4:20:24,  1.30it/s]
1|5519|Loss: 0.8386164307594299:  21%|██▏       | 5518/25880 [1:09:17<4:20:24,  1.30it/s]
1|5519|Loss: 0.8386164307594299:  21%|██▏       | 5519/25880 [1:09:17<4:09:26,  1.36it/s]
1|5520|Loss: 0.7130712866783142:  21%|██▏       | 5519/25880 [1:09:18<4:09:26,  1.36it/s]
1|5520|Loss: 0.7130712866783142:  21%|██▏       | 5520/25880 [1:09:18<4:15:37,  1.33it/s]
1|5521|Loss: 0.7660874128341675:  21%|██▏       | 5520/25880 [1:09:18<4:15:37,  1.33it/s]
1|5521|Loss: 0.7660874128341675:  21%|██▏       | 5521/25880 [1:09:19<4:34:29,  1.24it/s]
1|5522|Loss: 0.8382130265235901:  21%|██▏       | 5521/25880 [1:09:19<4:34:29,  1.24it/s]
1|5522|Loss: 0.8382130265235901:  21%|██▏       | 5522/25880 [1:09:20<4:23:59,  1.29it/s]
1|5523|Loss: 0.817786455154419:  21%|██▏       | 5522/25880 [1:09:20<4:23:59,  1.29it/s] 
1|5523|Loss: 0.817786455154419:  21%|██▏       | 5523/25880 [1:09:20<4:15:20,  1.33it/s]
1|5524|Loss: 0.9346277117729187:  21%|██▏       | 5523/25880 [1:09:21<4:15:20,  1.33it/s]
1|5524|Loss: 0.9346277117729187:  21%|██▏       | 5524/25880 [1:09:21<4:12:36,  1.34it/s]
1|5525|Loss: 0.8680782318115234:  21%|██▏       | 5524/25880 [1:09:21<4:12:36,  1.34it/s]
1|5525|Loss: 0.8680782318115234:  21%|██▏       | 5525/25880 [1:09:22<4:11:21,  1.35it/s]
1|5526|Loss: 0.9073023200035095:  21%|██▏       | 5525/25880 [1:09:22<4:11:21,  1.35it/s]
1|5526|Loss: 0.9073023200035095:  21%|██▏       | 5526/25880 [1:09:23<4:14:54,  1.33it/s]
1|5527|Loss: 0.7545095682144165:  21%|██▏       | 5526/25880 [1:09:23<4:14:54,  1.33it/s]
1|5527|Loss: 0.7545095682144165:  21%|██▏       | 5527/25880 [1:09:23<4:07:21,  1.37it/s]
1|5528|Loss: 0.8295025825500488:  21%|██▏       | 5527/25880 [1:09:24<4:07:21,  1.37it/s]
1|5528|Loss: 0.8295025825500488:  21%|██▏       | 5528/25880 [1:09:24<3:54:36,  1.45it/s]
1|5529|Loss: 0.8422662019729614:  21%|██▏       | 5528/25880 [1:09:24<3:54:36,  1.45it/s]
1|5529|Loss: 0.8422662019729614:  21%|██▏       | 5529/25880 [1:09:25<3:54:50,  1.44it/s]
1|5530|Loss: 0.8102437257766724:  21%|██▏       | 5529/25880 [1:09:25<3:54:50,  1.44it/s]
1|5530|Loss: 0.8102437257766724:  21%|██▏       | 5530/25880 [1:09:25<3:43:48,  1.52it/s]
1|5531|Loss: 0.8247938752174377:  21%|██▏       | 5530/25880 [1:09:26<3:43:48,  1.52it/s]
1|5531|Loss: 0.8247938752174377:  21%|██▏       | 5531/25880 [1:09:26<3:57:03,  1.43it/s]
1|5532|Loss: 0.9088485836982727:  21%|██▏       | 5531/25880 [1:09:26<3:57:03,  1.43it/s]
1|5532|Loss: 0.9088485836982727:  21%|██▏       | 5532/25880 [1:09:27<4:03:48,  1.39it/s]
1|5533|Loss: 0.8015722036361694:  21%|██▏       | 5532/25880 [1:09:27<4:03:48,  1.39it/s]
1|5533|Loss: 0.8015722036361694:  21%|██▏       | 5533/25880 [1:09:27<3:47:48,  1.49it/s]
1|5534|Loss: 0.8595123887062073:  21%|██▏       | 5533/25880 [1:09:28<3:47:48,  1.49it/s]
1|5534|Loss: 0.8595123887062073:  21%|██▏       | 5534/25880 [1:09:28<3:57:21,  1.43it/s]
1|5535|Loss: 0.7574170827865601:  21%|██▏       | 5534/25880 [1:09:28<3:57:21,  1.43it/s]
1|5535|Loss: 0.7574170827865601:  21%|██▏       | 5535/25880 [1:09:29<4:03:03,  1.40it/s]
1|5536|Loss: 0.9161959886550903:  21%|██▏       | 5535/25880 [1:09:29<4:03:03,  1.40it/s]
1|5536|Loss: 0.9161959886550903:  21%|██▏       | 5536/25880 [1:09:30<4:05:30,  1.38it/s]
1|5537|Loss: 0.9200322031974792:  21%|██▏       | 5536/25880 [1:09:30<4:05:30,  1.38it/s]
1|5537|Loss: 0.9200322031974792:  21%|██▏       | 5537/25880 [1:09:30<4:07:55,  1.37it/s]
1|5538|Loss: 0.7684445381164551:  21%|██▏       | 5537/25880 [1:09:31<4:07:55,  1.37it/s]
1|5538|Loss: 0.7684445381164551:  21%|██▏       | 5538/25880 [1:09:31<3:59:47,  1.41it/s]
1|5539|Loss: 0.83744215965271:  21%|██▏       | 5538/25880 [1:09:31<3:59:47,  1.41it/s]  
1|5539|Loss: 0.83744215965271:  21%|██▏       | 5539/25880 [1:09:32<3:59:56,  1.41it/s]
1|5540|Loss: 0.7472339272499084:  21%|██▏       | 5539/25880 [1:09:32<3:59:56,  1.41it/s]
1|5540|Loss: 0.7472339272499084:  21%|██▏       | 5540/25880 [1:09:32<4:02:18,  1.40it/s]
1|5541|Loss: 0.7178822755813599:  21%|██▏       | 5540/25880 [1:09:33<4:02:18,  1.40it/s]
1|5541|Loss: 0.7178822755813599:  21%|██▏       | 5541/25880 [1:09:33<3:41:06,  1.53it/s]
1|5542|Loss: 0.8153146505355835:  21%|██▏       | 5541/25880 [1:09:33<3:41:06,  1.53it/s]
1|5542|Loss: 0.8153146505355835:  21%|██▏       | 5542/25880 [1:09:33<3:20:26,  1.69it/s]
1|5543|Loss: 0.792920708656311:  21%|██▏       | 5542/25880 [1:09:34<3:20:26,  1.69it/s] 
1|5543|Loss: 0.792920708656311:  21%|██▏       | 5543/25880 [1:09:34<3:06:28,  1.82it/s]
1|5544|Loss: 0.6969847083091736:  21%|██▏       | 5543/25880 [1:09:34<3:06:28,  1.82it/s]
1|5544|Loss: 0.6969847083091736:  21%|██▏       | 5544/25880 [1:09:34<3:19:24,  1.70it/s]
1|5545|Loss: 0.7941622138023376:  21%|██▏       | 5544/25880 [1:09:35<3:19:24,  1.70it/s]
1|5545|Loss: 0.7941622138023376:  21%|██▏       | 5545/25880 [1:09:35<3:27:29,  1.63it/s]
1|5546|Loss: 0.8495669960975647:  21%|██▏       | 5545/25880 [1:09:35<3:27:29,  1.63it/s]
1|5546|Loss: 0.8495669960975647:  21%|██▏       | 5546/25880 [1:09:36<3:38:13,  1.55it/s]
1|5547|Loss: 0.8800380825996399:  21%|██▏       | 5546/25880 [1:09:36<3:38:13,  1.55it/s]
1|5547|Loss: 0.8800380825996399:  21%|██▏       | 5547/25880 [1:09:36<3:35:32,  1.57it/s]
1|5548|Loss: 0.9634098410606384:  21%|██▏       | 5547/25880 [1:09:37<3:35:32,  1.57it/s]
1|5548|Loss: 0.9634098410606384:  21%|██▏       | 5548/25880 [1:09:37<3:39:36,  1.54it/s]
1|5549|Loss: 0.928840160369873:  21%|██▏       | 5548/25880 [1:09:38<3:39:36,  1.54it/s] 
1|5549|Loss: 0.928840160369873:  21%|██▏       | 5549/25880 [1:09:38<3:46:46,  1.49it/s]
1|5550|Loss: 0.8862518668174744:  21%|██▏       | 5549/25880 [1:09:38<3:46:46,  1.49it/s]
1|5550|Loss: 0.8862518668174744:  21%|██▏       | 5550/25880 [1:09:39<3:57:23,  1.43it/s]
1|5551|Loss: 0.9755471348762512:  21%|██▏       | 5550/25880 [1:09:39<3:57:23,  1.43it/s]
1|5551|Loss: 0.9755471348762512:  21%|██▏       | 5551/25880 [1:09:39<3:43:35,  1.52it/s]
1|5552|Loss: 0.9555304646492004:  21%|██▏       | 5551/25880 [1:09:40<3:43:35,  1.52it/s]
1|5552|Loss: 0.9555304646492004:  21%|██▏       | 5552/25880 [1:09:40<3:45:40,  1.50it/s]
1|5553|Loss: 0.9260504245758057:  21%|██▏       | 5552/25880 [1:09:40<3:45:40,  1.50it/s]
1|5553|Loss: 0.9260504245758057:  21%|██▏       | 5553/25880 [1:09:41<3:52:31,  1.46it/s]
1|5554|Loss: 0.9191105365753174:  21%|██▏       | 5553/25880 [1:09:41<3:52:31,  1.46it/s]
1|5554|Loss: 0.9191105365753174:  21%|██▏       | 5554/25880 [1:09:41<4:05:44,  1.38it/s]
1|5555|Loss: 0.7966001629829407:  21%|██▏       | 5554/25880 [1:09:42<4:05:44,  1.38it/s]
1|5555|Loss: 0.7966001629829407:  21%|██▏       | 5555/25880 [1:09:42<4:09:35,  1.36it/s]
1|5556|Loss: 0.8095027208328247:  21%|██▏       | 5555/25880 [1:09:43<4:09:35,  1.36it/s]
1|5556|Loss: 0.8095027208328247:  21%|██▏       | 5556/25880 [1:09:43<4:07:59,  1.37it/s]
1|5557|Loss: 0.9131825566291809:  21%|██▏       | 5556/25880 [1:09:43<4:07:59,  1.37it/s]
1|5557|Loss: 0.9131825566291809:  21%|██▏       | 5557/25880 [1:09:44<4:04:30,  1.39it/s]
1|5558|Loss: 0.7579339146614075:  21%|██▏       | 5557/25880 [1:09:44<4:04:30,  1.39it/s]
1|5558|Loss: 0.7579339146614075:  21%|██▏       | 5558/25880 [1:09:44<3:50:07,  1.47it/s]
1|5559|Loss: 0.8565859794616699:  21%|██▏       | 5558/25880 [1:09:44<3:50:07,  1.47it/s]
1|5559|Loss: 0.8565859794616699:  21%|██▏       | 5559/25880 [1:09:45<3:35:30,  1.57it/s]
1|5560|Loss: 0.7594115734100342:  21%|██▏       | 5559/25880 [1:09:45<3:35:30,  1.57it/s]
1|5560|Loss: 0.7594115734100342:  21%|██▏       | 5560/25880 [1:09:45<3:31:31,  1.60it/s]
1|5561|Loss: 0.7619664072990417:  21%|██▏       | 5560/25880 [1:09:46<3:31:31,  1.60it/s]
1|5561|Loss: 0.7619664072990417:  21%|██▏       | 5561/25880 [1:09:46<3:44:43,  1.51it/s]
1|5562|Loss: 0.7357433438301086:  21%|██▏       | 5561/25880 [1:09:46<3:44:43,  1.51it/s]
1|5562|Loss: 0.7357433438301086:  21%|██▏       | 5562/25880 [1:09:47<3:54:02,  1.45it/s]
1|5563|Loss: 0.7886060476303101:  21%|██▏       | 5562/25880 [1:09:47<3:54:02,  1.45it/s]
1|5563|Loss: 0.7886060476303101:  21%|██▏       | 5563/25880 [1:09:47<3:42:24,  1.52it/s]
1|5564|Loss: 0.7208210229873657:  21%|██▏       | 5563/25880 [1:09:48<3:42:24,  1.52it/s]
1|5564|Loss: 0.7208210229873657:  21%|██▏       | 5564/25880 [1:09:48<3:36:36,  1.56it/s]
1|5565|Loss: 0.8697848916053772:  21%|██▏       | 5564/25880 [1:09:48<3:36:36,  1.56it/s]
1|5565|Loss: 0.8697848916053772:  22%|██▏       | 5565/25880 [1:09:49<3:40:56,  1.53it/s]
1|5566|Loss: 0.8221415281295776:  22%|██▏       | 5565/25880 [1:09:49<3:40:56,  1.53it/s]
1|5566|Loss: 0.8221415281295776:  22%|██▏       | 5566/25880 [1:09:49<3:40:58,  1.53it/s]
1|5567|Loss: 0.8543559312820435:  22%|██▏       | 5566/25880 [1:09:50<3:40:58,  1.53it/s]
1|5567|Loss: 0.8543559312820435:  22%|██▏       | 5567/25880 [1:09:50<3:47:58,  1.49it/s]
1|5568|Loss: 0.8500786423683167:  22%|██▏       | 5567/25880 [1:09:50<3:47:58,  1.49it/s]
1|5568|Loss: 0.8500786423683167:  22%|██▏       | 5568/25880 [1:09:51<4:02:42,  1.39it/s]
1|5569|Loss: 0.8553643822669983:  22%|██▏       | 5568/25880 [1:09:51<4:02:42,  1.39it/s]
1|5569|Loss: 0.8553643822669983:  22%|██▏       | 5569/25880 [1:09:52<4:07:28,  1.37it/s]
1|5570|Loss: 0.9801986217498779:  22%|██▏       | 5569/25880 [1:09:52<4:07:28,  1.37it/s]
1|5570|Loss: 0.9801986217498779:  22%|██▏       | 5570/25880 [1:09:52<4:06:09,  1.38it/s]
1|5571|Loss: 0.8358067870140076:  22%|██▏       | 5570/25880 [1:09:53<4:06:09,  1.38it/s]
1|5571|Loss: 0.8358067870140076:  22%|██▏       | 5571/25880 [1:09:53<3:47:27,  1.49it/s]
1|5572|Loss: 0.6998500227928162:  22%|██▏       | 5571/25880 [1:09:53<3:47:27,  1.49it/s]
1|5572|Loss: 0.6998500227928162:  22%|██▏       | 5572/25880 [1:09:54<3:58:03,  1.42it/s]
1|5573|Loss: 0.8050898313522339:  22%|██▏       | 5572/25880 [1:09:54<3:58:03,  1.42it/s]
1|5573|Loss: 0.8050898313522339:  22%|██▏       | 5573/25880 [1:09:55<4:22:47,  1.29it/s]
1|5574|Loss: 0.949009895324707:  22%|██▏       | 5573/25880 [1:09:55<4:22:47,  1.29it/s] 
1|5574|Loss: 0.949009895324707:  22%|██▏       | 5574/25880 [1:09:55<4:15:24,  1.33it/s]
1|5575|Loss: 0.823018491268158:  22%|██▏       | 5574/25880 [1:09:56<4:15:24,  1.33it/s]
1|5575|Loss: 0.823018491268158:  22%|██▏       | 5575/25880 [1:09:56<4:15:10,  1.33it/s]
1|5576|Loss: 0.9252761602401733:  22%|██▏       | 5575/25880 [1:09:56<4:15:10,  1.33it/s]
1|5576|Loss: 0.9252761602401733:  22%|██▏       | 5576/25880 [1:09:57<4:14:44,  1.33it/s]
1|5577|Loss: 0.9116961359977722:  22%|██▏       | 5576/25880 [1:09:57<4:14:44,  1.33it/s]
1|5577|Loss: 0.9116961359977722:  22%|██▏       | 5577/25880 [1:09:57<4:02:47,  1.39it/s]
1|5578|Loss: 0.8226147294044495:  22%|██▏       | 5577/25880 [1:09:58<4:02:47,  1.39it/s]
1|5578|Loss: 0.8226147294044495:  22%|██▏       | 5578/25880 [1:09:58<3:49:24,  1.47it/s]
1|5579|Loss: 0.9787606596946716:  22%|██▏       | 5578/25880 [1:09:58<3:49:24,  1.47it/s]
1|5579|Loss: 0.9787606596946716:  22%|██▏       | 5579/25880 [1:09:59<3:37:40,  1.55it/s]
1|5580|Loss: 1.0285966396331787:  22%|██▏       | 5579/25880 [1:09:59<3:37:40,  1.55it/s]
1|5580|Loss: 1.0285966396331787:  22%|██▏       | 5580/25880 [1:09:59<3:35:14,  1.57it/s]
1|5581|Loss: 0.922187864780426:  22%|██▏       | 5580/25880 [1:10:00<3:35:14,  1.57it/s] 
1|5581|Loss: 0.922187864780426:  22%|██▏       | 5581/25880 [1:10:00<3:29:01,  1.62it/s]
1|5582|Loss: 0.8690657019615173:  22%|██▏       | 5581/25880 [1:10:00<3:29:01,  1.62it/s]
1|5582|Loss: 0.8690657019615173:  22%|██▏       | 5582/25880 [1:10:00<3:29:40,  1.61it/s]
1|5583|Loss: 0.8355880975723267:  22%|██▏       | 5582/25880 [1:10:01<3:29:40,  1.61it/s]
1|5583|Loss: 0.8355880975723267:  22%|██▏       | 5583/25880 [1:10:01<3:58:17,  1.42it/s]
1|5584|Loss: 0.7855120301246643:  22%|██▏       | 5583/25880 [1:10:02<3:58:17,  1.42it/s]
1|5584|Loss: 0.7855120301246643:  22%|██▏       | 5584/25880 [1:10:02<3:57:51,  1.42it/s]
1|5585|Loss: 0.9990472793579102:  22%|██▏       | 5584/25880 [1:10:02<3:57:51,  1.42it/s]
1|5585|Loss: 0.9990472793579102:  22%|██▏       | 5585/25880 [1:10:03<4:17:44,  1.31it/s]
1|5586|Loss: 0.8815975189208984:  22%|██▏       | 5585/25880 [1:10:03<4:17:44,  1.31it/s]
1|5586|Loss: 0.8815975189208984:  22%|██▏       | 5586/25880 [1:10:04<4:27:09,  1.27it/s]
1|5587|Loss: 0.7863605618476868:  22%|██▏       | 5586/25880 [1:10:04<4:27:09,  1.27it/s]
1|5587|Loss: 0.7863605618476868:  22%|██▏       | 5587/25880 [1:10:05<4:31:06,  1.25it/s]
1|5588|Loss: 0.7817385792732239:  22%|██▏       | 5587/25880 [1:10:05<4:31:06,  1.25it/s]
1|5588|Loss: 0.7817385792732239:  22%|██▏       | 5588/25880 [1:10:05<4:38:04,  1.22it/s]
1|5589|Loss: 0.9866589903831482:  22%|██▏       | 5588/25880 [1:10:06<4:38:04,  1.22it/s]
1|5589|Loss: 0.9866589903831482:  22%|██▏       | 5589/25880 [1:10:06<4:25:31,  1.27it/s]
1|5590|Loss: 0.7420602440834045:  22%|██▏       | 5589/25880 [1:10:07<4:25:31,  1.27it/s]
1|5590|Loss: 0.7420602440834045:  22%|██▏       | 5590/25880 [1:10:07<4:22:54,  1.29it/s]
1|5591|Loss: 0.9054316282272339:  22%|██▏       | 5590/25880 [1:10:07<4:22:54,  1.29it/s]
1|5591|Loss: 0.9054316282272339:  22%|██▏       | 5591/25880 [1:10:08<4:34:34,  1.23it/s]
1|5592|Loss: 0.8392704129219055:  22%|██▏       | 5591/25880 [1:10:08<4:34:34,  1.23it/s]
1|5592|Loss: 0.8392704129219055:  22%|██▏       | 5592/25880 [1:10:09<4:22:07,  1.29it/s]
1|5593|Loss: 0.770736575126648:  22%|██▏       | 5592/25880 [1:10:09<4:22:07,  1.29it/s] 
1|5593|Loss: 0.770736575126648:  22%|██▏       | 5593/25880 [1:10:09<4:07:55,  1.36it/s]
1|5594|Loss: 0.8295881152153015:  22%|██▏       | 5593/25880 [1:10:10<4:07:55,  1.36it/s]
1|5594|Loss: 0.8295881152153015:  22%|██▏       | 5594/25880 [1:10:10<3:58:37,  1.42it/s]
1|5595|Loss: 0.8795575499534607:  22%|██▏       | 5594/25880 [1:10:10<3:58:37,  1.42it/s]
1|5595|Loss: 0.8795575499534607:  22%|██▏       | 5595/25880 [1:10:10<3:52:02,  1.46it/s]
1|5596|Loss: 0.9203590154647827:  22%|██▏       | 5595/25880 [1:10:11<3:52:02,  1.46it/s]
1|5596|Loss: 0.9203590154647827:  22%|██▏       | 5596/25880 [1:10:11<3:52:10,  1.46it/s]
1|5597|Loss: 0.7592357993125916:  22%|██▏       | 5596/25880 [1:10:12<3:52:10,  1.46it/s]
1|5597|Loss: 0.7592357993125916:  22%|██▏       | 5597/25880 [1:10:12<4:00:16,  1.41it/s]
1|5598|Loss: 0.8531826734542847:  22%|██▏       | 5597/25880 [1:10:12<4:00:16,  1.41it/s]
1|5598|Loss: 0.8531826734542847:  22%|██▏       | 5598/25880 [1:10:13<4:03:40,  1.39it/s]
1|5599|Loss: 0.8555119037628174:  22%|██▏       | 5598/25880 [1:10:13<4:03:40,  1.39it/s]
1|5599|Loss: 0.8555119037628174:  22%|██▏       | 5599/25880 [1:10:13<3:57:28,  1.42it/s]
1|5600|Loss: 0.8660190105438232:  22%|██▏       | 5599/25880 [1:10:14<3:57:28,  1.42it/s]
1|5600|Loss: 0.8660190105438232:  22%|██▏       | 5600/25880 [1:10:14<3:44:23,  1.51it/s]
1|5601|Loss: 0.72220379114151:  22%|██▏       | 5600/25880 [1:10:14<3:44:23,  1.51it/s]  
1|5601|Loss: 0.72220379114151:  22%|██▏       | 5601/25880 [1:10:15<4:08:47,  1.36it/s]
1|5602|Loss: 0.809287965297699:  22%|██▏       | 5601/25880 [1:10:15<4:08:47,  1.36it/s]
1|5602|Loss: 0.809287965297699:  22%|██▏       | 5602/25880 [1:10:16<4:25:58,  1.27it/s]
1|5603|Loss: 0.7028789520263672:  22%|██▏       | 5602/25880 [1:10:16<4:25:58,  1.27it/s]
1|5603|Loss: 0.7028789520263672:  22%|██▏       | 5603/25880 [1:10:16<4:16:45,  1.32it/s]
1|5604|Loss: 1.0196256637573242:  22%|██▏       | 5603/25880 [1:10:17<4:16:45,  1.32it/s]
1|5604|Loss: 1.0196256637573242:  22%|██▏       | 5604/25880 [1:10:17<4:04:50,  1.38it/s]
1|5605|Loss: 1.0124250650405884:  22%|██▏       | 5604/25880 [1:10:17<4:04:50,  1.38it/s]
1|5605|Loss: 1.0124250650405884:  22%|██▏       | 5605/25880 [1:10:18<4:15:05,  1.32it/s]
1|5606|Loss: 0.8288990259170532:  22%|██▏       | 5605/25880 [1:10:18<4:15:05,  1.32it/s]
1|5606|Loss: 0.8288990259170532:  22%|██▏       | 5606/25880 [1:10:19<4:13:17,  1.33it/s]
1|5607|Loss: 0.8906437754631042:  22%|██▏       | 5606/25880 [1:10:19<4:13:17,  1.33it/s]
1|5607|Loss: 0.8906437754631042:  22%|██▏       | 5607/25880 [1:10:19<4:21:01,  1.29it/s]
1|5608|Loss: 0.8013360500335693:  22%|██▏       | 5607/25880 [1:10:20<4:21:01,  1.29it/s]
1|5608|Loss: 0.8013360500335693:  22%|██▏       | 5608/25880 [1:10:20<4:28:21,  1.26it/s]
1|5609|Loss: 0.8718084692955017:  22%|██▏       | 5608/25880 [1:10:21<4:28:21,  1.26it/s]
1|5609|Loss: 0.8718084692955017:  22%|██▏       | 5609/25880 [1:10:21<4:21:41,  1.29it/s]
1|5610|Loss: 0.6965715885162354:  22%|██▏       | 5609/25880 [1:10:21<4:21:41,  1.29it/s]
1|5610|Loss: 0.6965715885162354:  22%|██▏       | 5610/25880 [1:10:22<4:16:15,  1.32it/s]
1|5611|Loss: 0.9771031737327576:  22%|██▏       | 5610/25880 [1:10:22<4:16:15,  1.32it/s]
1|5611|Loss: 0.9771031737327576:  22%|██▏       | 5611/25880 [1:10:22<4:13:49,  1.33it/s]
1|5612|Loss: 0.8295314908027649:  22%|██▏       | 5611/25880 [1:10:23<4:13:49,  1.33it/s]
1|5612|Loss: 0.8295314908027649:  22%|██▏       | 5612/25880 [1:10:23<4:10:01,  1.35it/s]
1|5613|Loss: 0.9282433390617371:  22%|██▏       | 5612/25880 [1:10:24<4:10:01,  1.35it/s]
1|5613|Loss: 0.9282433390617371:  22%|██▏       | 5613/25880 [1:10:24<4:08:01,  1.36it/s]
1|5614|Loss: 0.918296217918396:  22%|██▏       | 5613/25880 [1:10:24<4:08:01,  1.36it/s] 
1|5614|Loss: 0.918296217918396:  22%|██▏       | 5614/25880 [1:10:25<4:05:26,  1.38it/s]
1|5615|Loss: 0.8805683255195618:  22%|██▏       | 5614/25880 [1:10:25<4:05:26,  1.38it/s]
1|5615|Loss: 0.8805683255195618:  22%|██▏       | 5615/25880 [1:10:25<3:57:41,  1.42it/s]
1|5616|Loss: 1.2044812440872192:  22%|██▏       | 5615/25880 [1:10:26<3:57:41,  1.42it/s]
1|5616|Loss: 1.2044812440872192:  22%|██▏       | 5616/25880 [1:10:26<4:20:52,  1.29it/s]
1|5617|Loss: 0.740265429019928:  22%|██▏       | 5616/25880 [1:10:27<4:20:52,  1.29it/s] 
1|5617|Loss: 0.740265429019928:  22%|██▏       | 5617/25880 [1:10:27<4:22:24,  1.29it/s]
1|5618|Loss: 0.8931913375854492:  22%|██▏       | 5617/25880 [1:10:27<4:22:24,  1.29it/s]
1|5618|Loss: 0.8931913375854492:  22%|██▏       | 5618/25880 [1:10:28<4:07:27,  1.36it/s]
1|5619|Loss: 0.8060017824172974:  22%|██▏       | 5618/25880 [1:10:28<4:07:27,  1.36it/s]
1|5619|Loss: 0.8060017824172974:  22%|██▏       | 5619/25880 [1:10:28<4:02:28,  1.39it/s]
1|5620|Loss: 1.0234609842300415:  22%|██▏       | 5619/25880 [1:10:29<4:02:28,  1.39it/s]
1|5620|Loss: 1.0234609842300415:  22%|██▏       | 5620/25880 [1:10:29<4:00:40,  1.40it/s]
1|5621|Loss: 0.7208148241043091:  22%|██▏       | 5620/25880 [1:10:29<4:00:40,  1.40it/s]
1|5621|Loss: 0.7208148241043091:  22%|██▏       | 5621/25880 [1:10:29<3:32:12,  1.59it/s]
1|5622|Loss: 0.7883977890014648:  22%|██▏       | 5621/25880 [1:10:30<3:32:12,  1.59it/s]
1|5622|Loss: 0.7883977890014648:  22%|██▏       | 5622/25880 [1:10:30<3:40:02,  1.53it/s]
1|5623|Loss: 0.8662987947463989:  22%|██▏       | 5622/25880 [1:10:30<3:40:02,  1.53it/s]
1|5623|Loss: 0.8662987947463989:  22%|██▏       | 5623/25880 [1:10:31<3:40:21,  1.53it/s]
1|5624|Loss: 0.6898709535598755:  22%|██▏       | 5623/25880 [1:10:31<3:40:21,  1.53it/s]
1|5624|Loss: 0.6898709535598755:  22%|██▏       | 5624/25880 [1:10:31<3:46:46,  1.49it/s]
1|5625|Loss: 0.6842348575592041:  22%|██▏       | 5624/25880 [1:10:32<3:46:46,  1.49it/s]
1|5625|Loss: 0.6842348575592041:  22%|██▏       | 5625/25880 [1:10:32<3:51:02,  1.46it/s]
1|5626|Loss: 0.7647671103477478:  22%|██▏       | 5625/25880 [1:10:33<3:51:02,  1.46it/s]
1|5626|Loss: 0.7647671103477478:  22%|██▏       | 5626/25880 [1:10:33<3:52:21,  1.45it/s]
1|5627|Loss: 0.7800003886222839:  22%|██▏       | 5626/25880 [1:10:33<3:52:21,  1.45it/s]
1|5627|Loss: 0.7800003886222839:  22%|██▏       | 5627/25880 [1:10:34<3:55:44,  1.43it/s]
1|5628|Loss: 0.8494887351989746:  22%|██▏       | 5627/25880 [1:10:34<3:55:44,  1.43it/s]
1|5628|Loss: 0.8494887351989746:  22%|██▏       | 5628/25880 [1:10:34<3:56:54,  1.42it/s]
1|5629|Loss: 0.7882472276687622:  22%|██▏       | 5628/25880 [1:10:35<3:56:54,  1.42it/s]
1|5629|Loss: 0.7882472276687622:  22%|██▏       | 5629/25880 [1:10:35<4:07:25,  1.36it/s]
1|5630|Loss: 0.8557338118553162:  22%|██▏       | 5629/25880 [1:10:35<4:07:25,  1.36it/s]
1|5630|Loss: 0.8557338118553162:  22%|██▏       | 5630/25880 [1:10:36<3:53:12,  1.45it/s]
1|5631|Loss: 0.8268221616744995:  22%|██▏       | 5630/25880 [1:10:36<3:53:12,  1.45it/s]
1|5631|Loss: 0.8268221616744995:  22%|██▏       | 5631/25880 [1:10:36<3:58:33,  1.41it/s]
1|5632|Loss: 0.8859730362892151:  22%|██▏       | 5631/25880 [1:10:37<3:58:33,  1.41it/s]
1|5632|Loss: 0.8859730362892151:  22%|██▏       | 5632/25880 [1:10:37<3:49:59,  1.47it/s]
1|5633|Loss: 0.9723700284957886:  22%|██▏       | 5632/25880 [1:10:37<3:49:59,  1.47it/s]
1|5633|Loss: 0.9723700284957886:  22%|██▏       | 5633/25880 [1:10:38<3:49:22,  1.47it/s]
1|5634|Loss: 0.7347776889801025:  22%|██▏       | 5633/25880 [1:10:38<3:49:22,  1.47it/s]
1|5634|Loss: 0.7347776889801025:  22%|██▏       | 5634/25880 [1:10:38<3:54:19,  1.44it/s]
1|5635|Loss: 0.8219601511955261:  22%|██▏       | 5634/25880 [1:10:39<3:54:19,  1.44it/s]
1|5635|Loss: 0.8219601511955261:  22%|██▏       | 5635/25880 [1:10:39<4:07:21,  1.36it/s]
1|5636|Loss: 0.7777559757232666:  22%|██▏       | 5635/25880 [1:10:40<4:07:21,  1.36it/s]
1|5636|Loss: 0.7777559757232666:  22%|██▏       | 5636/25880 [1:10:40<4:10:04,  1.35it/s]
1|5637|Loss: 1.006811261177063:  22%|██▏       | 5636/25880 [1:10:40<4:10:04,  1.35it/s] 
1|5637|Loss: 1.006811261177063:  22%|██▏       | 5637/25880 [1:10:41<3:49:03,  1.47it/s]
1|5638|Loss: 0.8761436939239502:  22%|██▏       | 5637/25880 [1:10:41<3:49:03,  1.47it/s]
1|5638|Loss: 0.8761436939239502:  22%|██▏       | 5638/25880 [1:10:41<3:42:00,  1.52it/s]
1|5639|Loss: 1.0354235172271729:  22%|██▏       | 5638/25880 [1:10:42<3:42:00,  1.52it/s]
1|5639|Loss: 1.0354235172271729:  22%|██▏       | 5639/25880 [1:10:42<3:52:02,  1.45it/s]
1|5640|Loss: 0.7940263748168945:  22%|██▏       | 5639/25880 [1:10:42<3:52:02,  1.45it/s]
1|5640|Loss: 0.7940263748168945:  22%|██▏       | 5640/25880 [1:10:43<3:49:00,  1.47it/s]
1|5641|Loss: 0.7368846535682678:  22%|██▏       | 5640/25880 [1:10:43<3:49:00,  1.47it/s]
1|5641|Loss: 0.7368846535682678:  22%|██▏       | 5641/25880 [1:10:43<3:56:33,  1.43it/s]
1|5642|Loss: 0.8020055294036865:  22%|██▏       | 5641/25880 [1:10:44<3:56:33,  1.43it/s]
1|5642|Loss: 0.8020055294036865:  22%|██▏       | 5642/25880 [1:10:44<3:43:06,  1.51it/s]
1|5643|Loss: 0.9276270866394043:  22%|██▏       | 5642/25880 [1:10:44<3:43:06,  1.51it/s]
1|5643|Loss: 0.9276270866394043:  22%|██▏       | 5643/25880 [1:10:45<3:45:44,  1.49it/s]
1|5644|Loss: 0.8604610562324524:  22%|██▏       | 5643/25880 [1:10:45<3:45:44,  1.49it/s]
1|5644|Loss: 0.8604610562324524:  22%|██▏       | 5644/25880 [1:10:45<4:02:44,  1.39it/s]
1|5645|Loss: 1.0053999423980713:  22%|██▏       | 5644/25880 [1:10:46<4:02:44,  1.39it/s]
1|5645|Loss: 1.0053999423980713:  22%|██▏       | 5645/25880 [1:10:46<4:14:46,  1.32it/s]
1|5646|Loss: 0.8856407999992371:  22%|██▏       | 5645/25880 [1:10:47<4:14:46,  1.32it/s]
1|5646|Loss: 0.8856407999992371:  22%|██▏       | 5646/25880 [1:10:47<4:21:51,  1.29it/s]
1|5647|Loss: 0.9055992364883423:  22%|██▏       | 5646/25880 [1:10:48<4:21:51,  1.29it/s]
1|5647|Loss: 0.9055992364883423:  22%|██▏       | 5647/25880 [1:10:48<4:19:34,  1.30it/s]
1|5648|Loss: 0.8326544165611267:  22%|██▏       | 5647/25880 [1:10:48<4:19:34,  1.30it/s]
1|5648|Loss: 0.8326544165611267:  22%|██▏       | 5648/25880 [1:10:49<4:13:38,  1.33it/s]
1|5649|Loss: 0.8448076844215393:  22%|██▏       | 5648/25880 [1:10:49<4:13:38,  1.33it/s]
1|5649|Loss: 0.8448076844215393:  22%|██▏       | 5649/25880 [1:10:49<4:08:07,  1.36it/s]
1|5650|Loss: 0.8995375633239746:  22%|██▏       | 5649/25880 [1:10:50<4:08:07,  1.36it/s]
1|5650|Loss: 0.8995375633239746:  22%|██▏       | 5650/25880 [1:10:50<3:57:37,  1.42it/s]
1|5651|Loss: 0.9035824537277222:  22%|██▏       | 5650/25880 [1:10:50<3:57:37,  1.42it/s]
1|5651|Loss: 0.9035824537277222:  22%|██▏       | 5651/25880 [1:10:51<3:59:30,  1.41it/s]
1|5652|Loss: 0.8177196979522705:  22%|██▏       | 5651/25880 [1:10:51<3:59:30,  1.41it/s]
1|5652|Loss: 0.8177196979522705:  22%|██▏       | 5652/25880 [1:10:51<3:52:54,  1.45it/s]
1|5653|Loss: 0.8875036835670471:  22%|██▏       | 5652/25880 [1:10:52<3:52:54,  1.45it/s]
1|5653|Loss: 0.8875036835670471:  22%|██▏       | 5653/25880 [1:10:52<3:54:42,  1.44it/s]
1|5654|Loss: 0.7884095311164856:  22%|██▏       | 5653/25880 [1:10:52<3:54:42,  1.44it/s]
1|5654|Loss: 0.7884095311164856:  22%|██▏       | 5654/25880 [1:10:53<3:57:46,  1.42it/s]
1|5655|Loss: 0.8677943348884583:  22%|██▏       | 5654/25880 [1:10:53<3:57:46,  1.42it/s]
1|5655|Loss: 0.8677943348884583:  22%|██▏       | 5655/25880 [1:10:53<3:53:15,  1.45it/s]
1|5656|Loss: 0.9190677404403687:  22%|██▏       | 5655/25880 [1:10:54<3:53:15,  1.45it/s]
1|5656|Loss: 0.9190677404403687:  22%|██▏       | 5656/25880 [1:10:54<4:04:13,  1.38it/s]
1|5657|Loss: 0.8113896250724792:  22%|██▏       | 5656/25880 [1:10:55<4:04:13,  1.38it/s]
1|5657|Loss: 0.8113896250724792:  22%|██▏       | 5657/25880 [1:10:55<3:58:07,  1.42it/s]
1|5658|Loss: 0.9508023858070374:  22%|██▏       | 5657/25880 [1:10:55<3:58:07,  1.42it/s]
1|5658|Loss: 0.9508023858070374:  22%|██▏       | 5658/25880 [1:10:56<3:58:21,  1.41it/s]
1|5659|Loss: 0.870241105556488:  22%|██▏       | 5658/25880 [1:10:56<3:58:21,  1.41it/s] 
1|5659|Loss: 0.870241105556488:  22%|██▏       | 5659/25880 [1:10:56<4:00:49,  1.40it/s]
1|5660|Loss: 0.8366793394088745:  22%|██▏       | 5659/25880 [1:10:57<4:00:49,  1.40it/s]
1|5660|Loss: 0.8366793394088745:  22%|██▏       | 5660/25880 [1:10:57<4:02:30,  1.39it/s]
1|5661|Loss: 0.8711800575256348:  22%|██▏       | 5660/25880 [1:10:57<4:02:30,  1.39it/s]
1|5661|Loss: 0.8711800575256348:  22%|██▏       | 5661/25880 [1:10:58<4:03:25,  1.38it/s]
1|5662|Loss: 0.7447133660316467:  22%|██▏       | 5661/25880 [1:10:58<4:03:25,  1.38it/s]
1|5662|Loss: 0.7447133660316467:  22%|██▏       | 5662/25880 [1:10:58<4:03:32,  1.38it/s]
1|5663|Loss: 0.8645442724227905:  22%|██▏       | 5662/25880 [1:10:59<4:03:32,  1.38it/s]
1|5663|Loss: 0.8645442724227905:  22%|██▏       | 5663/25880 [1:10:59<4:04:16,  1.38it/s]
1|5664|Loss: 0.8747047781944275:  22%|██▏       | 5663/25880 [1:11:00<4:04:16,  1.38it/s]
1|5664|Loss: 0.8747047781944275:  22%|██▏       | 5664/25880 [1:11:00<4:04:31,  1.38it/s]
1|5665|Loss: 0.7855350971221924:  22%|██▏       | 5664/25880 [1:11:00<4:04:31,  1.38it/s]
1|5665|Loss: 0.7855350971221924:  22%|██▏       | 5665/25880 [1:11:01<4:12:27,  1.33it/s]
1|5666|Loss: 0.9600138664245605:  22%|██▏       | 5665/25880 [1:11:01<4:12:27,  1.33it/s]
1|5666|Loss: 0.9600138664245605:  22%|██▏       | 5666/25880 [1:11:02<4:21:43,  1.29it/s]
1|5667|Loss: 0.7570632696151733:  22%|██▏       | 5666/25880 [1:11:02<4:21:43,  1.29it/s]
1|5667|Loss: 0.7570632696151733:  22%|██▏       | 5667/25880 [1:11:02<4:26:21,  1.26it/s]
1|5668|Loss: 0.7247994542121887:  22%|██▏       | 5667/25880 [1:11:03<4:26:21,  1.26it/s]
1|5668|Loss: 0.7247994542121887:  22%|██▏       | 5668/25880 [1:11:03<4:29:37,  1.25it/s]
1|5669|Loss: 0.7546346187591553:  22%|██▏       | 5668/25880 [1:11:04<4:29:37,  1.25it/s]
1|5669|Loss: 0.7546346187591553:  22%|██▏       | 5669/25880 [1:11:04<4:36:09,  1.22it/s]
1|5670|Loss: 0.6951088905334473:  22%|██▏       | 5669/25880 [1:11:05<4:36:09,  1.22it/s]
1|5670|Loss: 0.6951088905334473:  22%|██▏       | 5670/25880 [1:11:05<4:23:53,  1.28it/s]
1|5671|Loss: 0.7427858114242554:  22%|██▏       | 5670/25880 [1:11:05<4:23:53,  1.28it/s]
1|5671|Loss: 0.7427858114242554:  22%|██▏       | 5671/25880 [1:11:06<4:36:30,  1.22it/s]
1|5672|Loss: 0.6462277173995972:  22%|██▏       | 5671/25880 [1:11:06<4:36:30,  1.22it/s]
1|5672|Loss: 0.6462277173995972:  22%|██▏       | 5672/25880 [1:11:07<4:40:46,  1.20it/s]
1|5673|Loss: 0.8458153009414673:  22%|██▏       | 5672/25880 [1:11:07<4:40:46,  1.20it/s]
1|5673|Loss: 0.8458153009414673:  22%|██▏       | 5673/25880 [1:11:07<4:39:17,  1.21it/s]
1|5674|Loss: 0.7913500666618347:  22%|██▏       | 5673/25880 [1:11:08<4:39:17,  1.21it/s]
1|5674|Loss: 0.7913500666618347:  22%|██▏       | 5674/25880 [1:11:08<4:30:52,  1.24it/s]
1|5675|Loss: 0.8865214586257935:  22%|██▏       | 5674/25880 [1:11:09<4:30:52,  1.24it/s]
1|5675|Loss: 0.8865214586257935:  22%|██▏       | 5675/25880 [1:11:09<4:23:59,  1.28it/s]
1|5676|Loss: 0.809108555316925:  22%|██▏       | 5675/25880 [1:11:09<4:23:59,  1.28it/s] 
1|5676|Loss: 0.809108555316925:  22%|██▏       | 5676/25880 [1:11:10<4:18:46,  1.30it/s]
1|5677|Loss: 0.7459350824356079:  22%|██▏       | 5676/25880 [1:11:10<4:18:46,  1.30it/s]
1|5677|Loss: 0.7459350824356079:  22%|██▏       | 5677/25880 [1:11:10<4:02:24,  1.39it/s]
1|5678|Loss: 0.8333263993263245:  22%|██▏       | 5677/25880 [1:11:11<4:02:24,  1.39it/s]
1|5678|Loss: 0.8333263993263245:  22%|██▏       | 5678/25880 [1:11:11<3:58:15,  1.41it/s]
1|5679|Loss: 0.9689627885818481:  22%|██▏       | 5678/25880 [1:11:11<3:58:15,  1.41it/s]
1|5679|Loss: 0.9689627885818481:  22%|██▏       | 5679/25880 [1:11:11<3:42:39,  1.51it/s]
1|5680|Loss: 0.8336628079414368:  22%|██▏       | 5679/25880 [1:11:12<3:42:39,  1.51it/s]
1|5680|Loss: 0.8336628079414368:  22%|██▏       | 5680/25880 [1:11:12<3:54:53,  1.43it/s]
1|5681|Loss: 0.8833022713661194:  22%|██▏       | 5680/25880 [1:11:13<3:54:53,  1.43it/s]
1|5681|Loss: 0.8833022713661194:  22%|██▏       | 5681/25880 [1:11:13<3:38:40,  1.54it/s]
1|5682|Loss: 0.8292577266693115:  22%|██▏       | 5681/25880 [1:11:13<3:38:40,  1.54it/s]
1|5682|Loss: 0.8292577266693115:  22%|██▏       | 5682/25880 [1:11:13<3:41:11,  1.52it/s]
1|5683|Loss: 0.7989016771316528:  22%|██▏       | 5682/25880 [1:11:14<3:41:11,  1.52it/s]
1|5683|Loss: 0.7989016771316528:  22%|██▏       | 5683/25880 [1:11:14<3:49:29,  1.47it/s]
1|5684|Loss: 0.8099208474159241:  22%|██▏       | 5683/25880 [1:11:15<3:49:29,  1.47it/s]
1|5684|Loss: 0.8099208474159241:  22%|██▏       | 5684/25880 [1:11:15<3:59:24,  1.41it/s]
1|5685|Loss: 0.9887113571166992:  22%|██▏       | 5684/25880 [1:11:15<3:59:24,  1.41it/s]
1|5685|Loss: 0.9887113571166992:  22%|██▏       | 5685/25880 [1:11:16<4:06:41,  1.36it/s]
1|5686|Loss: 0.8771460652351379:  22%|██▏       | 5685/25880 [1:11:16<4:06:41,  1.36it/s]
1|5686|Loss: 0.8771460652351379:  22%|██▏       | 5686/25880 [1:11:17<4:17:21,  1.31it/s]
1|5687|Loss: 0.8952053189277649:  22%|██▏       | 5686/25880 [1:11:17<4:17:21,  1.31it/s]
1|5687|Loss: 0.8952053189277649:  22%|██▏       | 5687/25880 [1:11:17<4:14:46,  1.32it/s]
1|5688|Loss: 0.7871546149253845:  22%|██▏       | 5687/25880 [1:11:18<4:14:46,  1.32it/s]
1|5688|Loss: 0.7871546149253845:  22%|██▏       | 5688/25880 [1:11:18<3:53:09,  1.44it/s]
1|5689|Loss: 0.7311719655990601:  22%|██▏       | 5688/25880 [1:11:18<3:53:09,  1.44it/s]
1|5689|Loss: 0.7311719655990601:  22%|██▏       | 5689/25880 [1:11:19<3:57:56,  1.41it/s]
1|5690|Loss: 0.7971085906028748:  22%|██▏       | 5689/25880 [1:11:19<3:57:56,  1.41it/s]
1|5690|Loss: 0.7971085906028748:  22%|██▏       | 5690/25880 [1:11:19<4:07:43,  1.36it/s]
1|5691|Loss: 0.7187075614929199:  22%|██▏       | 5690/25880 [1:11:20<4:07:43,  1.36it/s]
1|5691|Loss: 0.7187075614929199:  22%|██▏       | 5691/25880 [1:11:20<3:57:43,  1.42it/s]
1|5692|Loss: 0.7882205843925476:  22%|██▏       | 5691/25880 [1:11:20<3:57:43,  1.42it/s]
1|5692|Loss: 0.7882205843925476:  22%|██▏       | 5692/25880 [1:11:21<4:01:37,  1.39it/s]
1|5693|Loss: 0.8475807905197144:  22%|██▏       | 5692/25880 [1:11:21<4:01:37,  1.39it/s]
1|5693|Loss: 0.8475807905197144:  22%|██▏       | 5693/25880 [1:11:21<3:44:41,  1.50it/s]
1|5694|Loss: 0.7890681028366089:  22%|██▏       | 5693/25880 [1:11:22<3:44:41,  1.50it/s]
1|5694|Loss: 0.7890681028366089:  22%|██▏       | 5694/25880 [1:11:22<3:26:27,  1.63it/s]
1|5695|Loss: 0.864372968673706:  22%|██▏       | 5694/25880 [1:11:22<3:26:27,  1.63it/s] 
1|5695|Loss: 0.864372968673706:  22%|██▏       | 5695/25880 [1:11:22<3:25:43,  1.64it/s]
1|5696|Loss: 0.8104662299156189:  22%|██▏       | 5695/25880 [1:11:23<3:25:43,  1.64it/s]
1|5696|Loss: 0.8104662299156189:  22%|██▏       | 5696/25880 [1:11:23<3:23:45,  1.65it/s]
1|5697|Loss: 0.872574508190155:  22%|██▏       | 5696/25880 [1:11:23<3:23:45,  1.65it/s] 
1|5697|Loss: 0.872574508190155:  22%|██▏       | 5697/25880 [1:11:23<3:05:21,  1.81it/s]
1|5698|Loss: 0.6680001020431519:  22%|██▏       | 5697/25880 [1:11:24<3:05:21,  1.81it/s]
1|5698|Loss: 0.6680001020431519:  22%|██▏       | 5698/25880 [1:11:24<2:57:52,  1.89it/s]
1|5699|Loss: 0.8753775954246521:  22%|██▏       | 5698/25880 [1:11:24<2:57:52,  1.89it/s]
1|5699|Loss: 0.8753775954246521:  22%|██▏       | 5699/25880 [1:11:25<3:06:02,  1.81it/s]
1|5700|Loss: 0.8755545616149902:  22%|██▏       | 5699/25880 [1:11:25<3:06:02,  1.81it/s]
1|5700|Loss: 0.8755545616149902:  22%|██▏       | 5700/25880 [1:11:25<3:20:27,  1.68it/s]
1|5701|Loss: 0.8537574410438538:  22%|██▏       | 5700/25880 [1:11:26<3:20:27,  1.68it/s]
1|5701|Loss: 0.8537574410438538:  22%|██▏       | 5701/25880 [1:11:26<3:39:17,  1.53it/s]
1|5702|Loss: 0.96930330991745:  22%|██▏       | 5701/25880 [1:11:26<3:39:17,  1.53it/s]  
1|5702|Loss: 0.96930330991745:  22%|██▏       | 5702/25880 [1:11:27<3:49:50,  1.46it/s]
1|5703|Loss: 0.9186575412750244:  22%|██▏       | 5702/25880 [1:11:27<3:49:50,  1.46it/s]
1|5703|Loss: 0.9186575412750244:  22%|██▏       | 5703/25880 [1:11:27<3:52:54,  1.44it/s]
1|5704|Loss: 0.8766327500343323:  22%|██▏       | 5703/25880 [1:11:28<3:52:54,  1.44it/s]
1|5704|Loss: 0.8766327500343323:  22%|██▏       | 5704/25880 [1:11:28<3:56:29,  1.42it/s]
1|5705|Loss: 0.7789283394813538:  22%|██▏       | 5704/25880 [1:11:29<3:56:29,  1.42it/s]
1|5705|Loss: 0.7789283394813538:  22%|██▏       | 5705/25880 [1:11:29<3:57:32,  1.42it/s]
1|5706|Loss: 0.8324165940284729:  22%|██▏       | 5705/25880 [1:11:29<3:57:32,  1.42it/s]
1|5706|Loss: 0.8324165940284729:  22%|██▏       | 5706/25880 [1:11:30<3:51:24,  1.45it/s]
1|5707|Loss: 0.8280777335166931:  22%|██▏       | 5706/25880 [1:11:30<3:51:24,  1.45it/s]
1|5707|Loss: 0.8280777335166931:  22%|██▏       | 5707/25880 [1:11:30<3:51:26,  1.45it/s]
1|5708|Loss: 0.8025440573692322:  22%|██▏       | 5707/25880 [1:11:31<3:51:26,  1.45it/s]
1|5708|Loss: 0.8025440573692322:  22%|██▏       | 5708/25880 [1:11:31<4:05:03,  1.37it/s]
1|5709|Loss: 0.7872920632362366:  22%|██▏       | 5708/25880 [1:11:31<4:05:03,  1.37it/s]
1|5709|Loss: 0.7872920632362366:  22%|██▏       | 5709/25880 [1:11:32<3:55:44,  1.43it/s]
1|5710|Loss: 0.9910265207290649:  22%|██▏       | 5709/25880 [1:11:32<3:55:44,  1.43it/s]
1|5710|Loss: 0.9910265207290649:  22%|██▏       | 5710/25880 [1:11:32<3:55:04,  1.43it/s]
1|5711|Loss: 0.9286395311355591:  22%|██▏       | 5710/25880 [1:11:33<3:55:04,  1.43it/s]
1|5711|Loss: 0.9286395311355591:  22%|██▏       | 5711/25880 [1:11:33<3:44:02,  1.50it/s]
1|5712|Loss: 0.8467622995376587:  22%|██▏       | 5711/25880 [1:11:33<3:44:02,  1.50it/s]
1|5712|Loss: 0.8467622995376587:  22%|██▏       | 5712/25880 [1:11:34<3:37:40,  1.54it/s]
1|5713|Loss: 1.0083389282226562:  22%|██▏       | 5712/25880 [1:11:34<3:37:40,  1.54it/s]
1|5713|Loss: 1.0083389282226562:  22%|██▏       | 5713/25880 [1:11:34<3:36:25,  1.55it/s]
1|5714|Loss: 0.7632812261581421:  22%|██▏       | 5713/25880 [1:11:35<3:36:25,  1.55it/s]
1|5714|Loss: 0.7632812261581421:  22%|██▏       | 5714/25880 [1:11:35<3:41:11,  1.52it/s]
1|5715|Loss: 0.8246874809265137:  22%|██▏       | 5714/25880 [1:11:35<3:41:11,  1.52it/s]
1|5715|Loss: 0.8246874809265137:  22%|██▏       | 5715/25880 [1:11:36<3:48:20,  1.47it/s]
1|5716|Loss: 0.8687513470649719:  22%|██▏       | 5715/25880 [1:11:36<3:48:20,  1.47it/s]
1|5716|Loss: 0.8687513470649719:  22%|██▏       | 5716/25880 [1:11:36<3:53:52,  1.44it/s]
1|5717|Loss: 0.8403022289276123:  22%|██▏       | 5716/25880 [1:11:37<3:53:52,  1.44it/s]
1|5717|Loss: 0.8403022289276123:  22%|██▏       | 5717/25880 [1:11:37<3:58:17,  1.41it/s]
1|5718|Loss: 0.9809636473655701:  22%|██▏       | 5717/25880 [1:11:38<3:58:17,  1.41it/s]
1|5718|Loss: 0.9809636473655701:  22%|██▏       | 5718/25880 [1:11:38<4:02:33,  1.39it/s]
1|5719|Loss: 0.7102460861206055:  22%|██▏       | 5718/25880 [1:11:38<4:02:33,  1.39it/s]
1|5719|Loss: 0.7102460861206055:  22%|██▏       | 5719/25880 [1:11:39<4:15:47,  1.31it/s]
1|5720|Loss: 0.8991291522979736:  22%|██▏       | 5719/25880 [1:11:39<4:15:47,  1.31it/s]
1|5720|Loss: 0.8991291522979736:  22%|██▏       | 5720/25880 [1:11:39<4:08:18,  1.35it/s]
1|5721|Loss: 0.8795957565307617:  22%|██▏       | 5720/25880 [1:11:40<4:08:18,  1.35it/s]
1|5721|Loss: 0.8795957565307617:  22%|██▏       | 5721/25880 [1:11:40<4:02:51,  1.38it/s]
1|5722|Loss: 0.8791388869285583:  22%|██▏       | 5721/25880 [1:11:41<4:02:51,  1.38it/s]
1|5722|Loss: 0.8791388869285583:  22%|██▏       | 5722/25880 [1:11:41<4:02:52,  1.38it/s]
1|5723|Loss: 0.9506650567054749:  22%|██▏       | 5722/25880 [1:11:41<4:02:52,  1.38it/s]
1|5723|Loss: 0.9506650567054749:  22%|██▏       | 5723/25880 [1:11:42<3:56:14,  1.42it/s]
1|5724|Loss: 0.8839259147644043:  22%|██▏       | 5723/25880 [1:11:42<3:56:14,  1.42it/s]
1|5724|Loss: 0.8839259147644043:  22%|██▏       | 5724/25880 [1:11:42<3:56:52,  1.42it/s]
1|5725|Loss: 0.869397759437561:  22%|██▏       | 5724/25880 [1:11:43<3:56:52,  1.42it/s] 
1|5725|Loss: 0.869397759437561:  22%|██▏       | 5725/25880 [1:11:43<3:52:18,  1.45it/s]
1|5726|Loss: 0.7808738946914673:  22%|██▏       | 5725/25880 [1:11:43<3:52:18,  1.45it/s]
1|5726|Loss: 0.7808738946914673:  22%|██▏       | 5726/25880 [1:11:44<3:59:09,  1.40it/s]
1|5727|Loss: 0.8591722846031189:  22%|██▏       | 5726/25880 [1:11:44<3:59:09,  1.40it/s]
1|5727|Loss: 0.8591722846031189:  22%|██▏       | 5727/25880 [1:11:44<3:52:56,  1.44it/s]
1|5728|Loss: 0.9224188923835754:  22%|██▏       | 5727/25880 [1:11:45<3:52:56,  1.44it/s]
1|5728|Loss: 0.9224188923835754:  22%|██▏       | 5728/25880 [1:11:45<3:51:45,  1.45it/s]
1|5729|Loss: 0.9132353067398071:  22%|██▏       | 5728/25880 [1:11:45<3:51:45,  1.45it/s]
1|5729|Loss: 0.9132353067398071:  22%|██▏       | 5729/25880 [1:11:46<3:48:17,  1.47it/s]
1|5730|Loss: 0.8301537036895752:  22%|██▏       | 5729/25880 [1:11:46<3:48:17,  1.47it/s]
1|5730|Loss: 0.8301537036895752:  22%|██▏       | 5730/25880 [1:11:46<3:49:02,  1.47it/s]
1|5731|Loss: 0.9022432565689087:  22%|██▏       | 5730/25880 [1:11:47<3:49:02,  1.47it/s]
1|5731|Loss: 0.9022432565689087:  22%|██▏       | 5731/25880 [1:11:47<3:46:06,  1.49it/s]
1|5732|Loss: 0.8598067760467529:  22%|██▏       | 5731/25880 [1:11:47<3:46:06,  1.49it/s]
1|5732|Loss: 0.8598067760467529:  22%|██▏       | 5732/25880 [1:11:48<3:40:54,  1.52it/s]
1|5733|Loss: 0.9628110527992249:  22%|██▏       | 5732/25880 [1:11:48<3:40:54,  1.52it/s]
1|5733|Loss: 0.9628110527992249:  22%|██▏       | 5733/25880 [1:11:48<3:58:19,  1.41it/s]
1|5734|Loss: 0.7589304447174072:  22%|██▏       | 5733/25880 [1:11:49<3:58:19,  1.41it/s]
1|5734|Loss: 0.7589304447174072:  22%|██▏       | 5734/25880 [1:11:49<4:01:44,  1.39it/s]
1|5735|Loss: 0.760254442691803:  22%|██▏       | 5734/25880 [1:11:50<4:01:44,  1.39it/s] 
1|5735|Loss: 0.760254442691803:  22%|██▏       | 5735/25880 [1:11:50<4:16:32,  1.31it/s]
1|5736|Loss: 0.8295395374298096:  22%|██▏       | 5735/25880 [1:11:50<4:16:32,  1.31it/s]
1|5736|Loss: 0.8295395374298096:  22%|██▏       | 5736/25880 [1:11:51<4:16:42,  1.31it/s]
1|5737|Loss: 0.8570622801780701:  22%|██▏       | 5736/25880 [1:11:51<4:16:42,  1.31it/s]
1|5737|Loss: 0.8570622801780701:  22%|██▏       | 5737/25880 [1:11:51<4:01:17,  1.39it/s]
1|5738|Loss: 0.8179497718811035:  22%|██▏       | 5737/25880 [1:11:52<4:01:17,  1.39it/s]
1|5738|Loss: 0.8179497718811035:  22%|██▏       | 5738/25880 [1:11:52<4:00:38,  1.39it/s]
1|5739|Loss: 0.9164318442344666:  22%|██▏       | 5738/25880 [1:11:53<4:00:38,  1.39it/s]
1|5739|Loss: 0.9164318442344666:  22%|██▏       | 5739/25880 [1:11:53<4:00:28,  1.40it/s]
1|5740|Loss: 0.8017931580543518:  22%|██▏       | 5739/25880 [1:11:53<4:00:28,  1.40it/s]
1|5740|Loss: 0.8017931580543518:  22%|██▏       | 5740/25880 [1:11:54<4:12:33,  1.33it/s]
1|5741|Loss: 0.9091952443122864:  22%|██▏       | 5740/25880 [1:11:54<4:12:33,  1.33it/s]
1|5741|Loss: 0.9091952443122864:  22%|██▏       | 5741/25880 [1:11:54<4:05:21,  1.37it/s]
1|5742|Loss: 0.7636575102806091:  22%|██▏       | 5741/25880 [1:11:55<4:05:21,  1.37it/s]
1|5742|Loss: 0.7636575102806091:  22%|██▏       | 5742/25880 [1:11:55<4:04:23,  1.37it/s]
1|5743|Loss: 0.9241815209388733:  22%|██▏       | 5742/25880 [1:11:55<4:04:23,  1.37it/s]
1|5743|Loss: 0.9241815209388733:  22%|██▏       | 5743/25880 [1:11:56<4:03:09,  1.38it/s]
1|5744|Loss: 0.6902558207511902:  22%|██▏       | 5743/25880 [1:11:56<4:03:09,  1.38it/s]
1|5744|Loss: 0.6902558207511902:  22%|██▏       | 5744/25880 [1:11:57<5:19:03,  1.05it/s]
1|5745|Loss: 0.827082633972168:  22%|██▏       | 5744/25880 [1:11:58<5:19:03,  1.05it/s] 
1|5745|Loss: 0.827082633972168:  22%|██▏       | 5745/25880 [1:11:58<5:34:54,  1.00it/s]
1|5746|Loss: 0.9063704609870911:  22%|██▏       | 5745/25880 [1:11:59<5:34:54,  1.00it/s]
1|5746|Loss: 0.9063704609870911:  22%|██▏       | 5746/25880 [1:11:59<5:03:02,  1.11it/s]
1|5747|Loss: 0.8695469498634338:  22%|██▏       | 5746/25880 [1:11:59<5:03:02,  1.11it/s]
1|5747|Loss: 0.8695469498634338:  22%|██▏       | 5747/25880 [1:12:00<4:45:03,  1.18it/s]
1|5748|Loss: 0.8904353976249695:  22%|██▏       | 5747/25880 [1:12:00<4:45:03,  1.18it/s]
1|5748|Loss: 0.8904353976249695:  22%|██▏       | 5748/25880 [1:12:01<4:33:51,  1.23it/s]
1|5749|Loss: 0.8997018337249756:  22%|██▏       | 5748/25880 [1:12:01<4:33:51,  1.23it/s]
1|5749|Loss: 0.8997018337249756:  22%|██▏       | 5749/25880 [1:12:01<4:29:59,  1.24it/s]
1|5750|Loss: 0.9222264885902405:  22%|██▏       | 5749/25880 [1:12:02<4:29:59,  1.24it/s]
1|5750|Loss: 0.9222264885902405:  22%|██▏       | 5750/25880 [1:12:02<4:25:06,  1.27it/s]
1|5751|Loss: 0.7904154062271118:  22%|██▏       | 5750/25880 [1:12:02<4:25:06,  1.27it/s]
1|5751|Loss: 0.7904154062271118:  22%|██▏       | 5751/25880 [1:12:03<4:12:41,  1.33it/s]
1|5752|Loss: 0.8830476999282837:  22%|██▏       | 5751/25880 [1:12:03<4:12:41,  1.33it/s]
1|5752|Loss: 0.8830476999282837:  22%|██▏       | 5752/25880 [1:12:04<4:16:17,  1.31it/s]
1|5753|Loss: 0.690977931022644:  22%|██▏       | 5752/25880 [1:12:04<4:16:17,  1.31it/s] 
1|5753|Loss: 0.690977931022644:  22%|██▏       | 5753/25880 [1:12:04<4:05:33,  1.37it/s]
1|5754|Loss: 0.7579759359359741:  22%|██▏       | 5753/25880 [1:12:04<4:05:33,  1.37it/s]
1|5754|Loss: 0.7579759359359741:  22%|██▏       | 5754/25880 [1:12:05<3:48:58,  1.46it/s]
1|5755|Loss: 0.9099732637405396:  22%|██▏       | 5754/25880 [1:12:05<3:48:58,  1.46it/s]
1|5755|Loss: 0.9099732637405396:  22%|██▏       | 5755/25880 [1:12:05<3:33:48,  1.57it/s]
1|5756|Loss: 1.0092062950134277:  22%|██▏       | 5755/25880 [1:12:06<3:33:48,  1.57it/s]
1|5756|Loss: 1.0092062950134277:  22%|██▏       | 5756/25880 [1:12:06<3:38:28,  1.54it/s]
1|5757|Loss: 0.8494512438774109:  22%|██▏       | 5756/25880 [1:12:06<3:38:28,  1.54it/s]
1|5757|Loss: 0.8494512438774109:  22%|██▏       | 5757/25880 [1:12:07<3:38:52,  1.53it/s]
1|5758|Loss: 0.871787965297699:  22%|██▏       | 5757/25880 [1:12:07<3:38:52,  1.53it/s] 
1|5758|Loss: 0.871787965297699:  22%|██▏       | 5758/25880 [1:12:07<3:37:36,  1.54it/s]
1|5759|Loss: 1.0012552738189697:  22%|██▏       | 5758/25880 [1:12:08<3:37:36,  1.54it/s]
1|5759|Loss: 1.0012552738189697:  22%|██▏       | 5759/25880 [1:12:08<3:29:38,  1.60it/s]
1|5760|Loss: 0.8728016018867493:  22%|██▏       | 5759/25880 [1:12:08<3:29:38,  1.60it/s]
1|5760|Loss: 0.8728016018867493:  22%|██▏       | 5760/25880 [1:12:08<3:26:59,  1.62it/s]
1|5761|Loss: 0.8339454531669617:  22%|██▏       | 5760/25880 [1:12:09<3:26:59,  1.62it/s]
1|5761|Loss: 0.8339454531669617:  22%|██▏       | 5761/25880 [1:12:09<3:33:25,  1.57it/s]
1|5762|Loss: 0.9923450350761414:  22%|██▏       | 5761/25880 [1:12:09<3:33:25,  1.57it/s]
1|5762|Loss: 0.9923450350761414:  22%|██▏       | 5762/25880 [1:12:10<3:39:40,  1.53it/s]
1|5763|Loss: 0.7790080308914185:  22%|██▏       | 5762/25880 [1:12:10<3:39:40,  1.53it/s]
1|5763|Loss: 0.7790080308914185:  22%|██▏       | 5763/25880 [1:12:11<3:45:39,  1.49it/s]
1|5764|Loss: 0.8410796523094177:  22%|██▏       | 5763/25880 [1:12:11<3:45:39,  1.49it/s]
1|5764|Loss: 0.8410796523094177:  22%|██▏       | 5764/25880 [1:12:11<3:28:32,  1.61it/s]
1|5765|Loss: 0.8378943204879761:  22%|██▏       | 5764/25880 [1:12:11<3:28:32,  1.61it/s]
1|5765|Loss: 0.8378943204879761:  22%|██▏       | 5765/25880 [1:12:12<3:34:29,  1.56it/s]
1|5766|Loss: 0.8042652010917664:  22%|██▏       | 5765/25880 [1:12:12<3:34:29,  1.56it/s]
1|5766|Loss: 0.8042652010917664:  22%|██▏       | 5766/25880 [1:12:12<3:43:19,  1.50it/s]
1|5767|Loss: 0.7903263568878174:  22%|██▏       | 5766/25880 [1:12:13<3:43:19,  1.50it/s]
1|5767|Loss: 0.7903263568878174:  22%|██▏       | 5767/25880 [1:12:13<3:37:04,  1.54it/s]
1|5768|Loss: 0.7988209128379822:  22%|██▏       | 5767/25880 [1:12:13<3:37:04,  1.54it/s]
1|5768|Loss: 0.7988209128379822:  22%|██▏       | 5768/25880 [1:12:14<3:48:12,  1.47it/s]
1|5769|Loss: 0.8072568774223328:  22%|██▏       | 5768/25880 [1:12:14<3:48:12,  1.47it/s]
1|5769|Loss: 0.8072568774223328:  22%|██▏       | 5769/25880 [1:12:15<4:02:25,  1.38it/s]
1|5770|Loss: 0.7856151461601257:  22%|██▏       | 5769/25880 [1:12:15<4:02:25,  1.38it/s]
1|5770|Loss: 0.7856151461601257:  22%|██▏       | 5770/25880 [1:12:15<3:52:50,  1.44it/s]
1|5771|Loss: 0.7834283113479614:  22%|██▏       | 5770/25880 [1:12:16<3:52:50,  1.44it/s]
1|5771|Loss: 0.7834283113479614:  22%|██▏       | 5771/25880 [1:12:16<3:52:59,  1.44it/s]
1|5772|Loss: 0.9554166197776794:  22%|██▏       | 5771/25880 [1:12:16<3:52:59,  1.44it/s]
1|5772|Loss: 0.9554166197776794:  22%|██▏       | 5772/25880 [1:12:17<4:11:03,  1.33it/s]
1|5773|Loss: 0.9515408873558044:  22%|██▏       | 5772/25880 [1:12:17<4:11:03,  1.33it/s]
1|5773|Loss: 0.9515408873558044:  22%|██▏       | 5773/25880 [1:12:18<4:18:38,  1.30it/s]
1|5774|Loss: 0.8154301047325134:  22%|██▏       | 5773/25880 [1:12:18<4:18:38,  1.30it/s]
1|5774|Loss: 0.8154301047325134:  22%|██▏       | 5774/25880 [1:12:18<3:55:48,  1.42it/s]
1|5775|Loss: 0.8530682921409607:  22%|██▏       | 5774/25880 [1:12:19<3:55:48,  1.42it/s]
1|5775|Loss: 0.8530682921409607:  22%|██▏       | 5775/25880 [1:12:19<3:53:19,  1.44it/s]
1|5776|Loss: 0.8649086356163025:  22%|██▏       | 5775/25880 [1:12:19<3:53:19,  1.44it/s]
1|5776|Loss: 0.8649086356163025:  22%|██▏       | 5776/25880 [1:12:20<4:09:09,  1.34it/s]
1|5777|Loss: 0.7872949242591858:  22%|██▏       | 5776/25880 [1:12:20<4:09:09,  1.34it/s]
1|5777|Loss: 0.7872949242591858:  22%|██▏       | 5777/25880 [1:12:20<3:48:55,  1.46it/s]
1|5778|Loss: 1.0042202472686768:  22%|██▏       | 5777/25880 [1:12:21<3:48:55,  1.46it/s]
1|5778|Loss: 1.0042202472686768:  22%|██▏       | 5778/25880 [1:12:21<3:44:50,  1.49it/s]
1|5779|Loss: 0.7696911692619324:  22%|██▏       | 5778/25880 [1:12:21<3:44:50,  1.49it/s]
1|5779|Loss: 0.7696911692619324:  22%|██▏       | 5779/25880 [1:12:22<3:55:58,  1.42it/s]
1|5780|Loss: 0.7978684306144714:  22%|██▏       | 5779/25880 [1:12:22<3:55:58,  1.42it/s]
1|5780|Loss: 0.7978684306144714:  22%|██▏       | 5780/25880 [1:12:22<3:37:23,  1.54it/s]
1|5781|Loss: 0.7587464451789856:  22%|██▏       | 5780/25880 [1:12:23<3:37:23,  1.54it/s]
1|5781|Loss: 0.7587464451789856:  22%|██▏       | 5781/25880 [1:12:23<3:49:52,  1.46it/s]
1|5782|Loss: 0.8517669439315796:  22%|██▏       | 5781/25880 [1:12:23<3:49:52,  1.46it/s]
1|5782|Loss: 0.8517669439315796:  22%|██▏       | 5782/25880 [1:12:24<4:07:43,  1.35it/s]
1|5783|Loss: 0.8504971861839294:  22%|██▏       | 5782/25880 [1:12:24<4:07:43,  1.35it/s]
1|5783|Loss: 0.8504971861839294:  22%|██▏       | 5783/25880 [1:12:25<4:03:27,  1.38it/s]
1|5784|Loss: 0.9259345531463623:  22%|██▏       | 5783/25880 [1:12:25<4:03:27,  1.38it/s]
1|5784|Loss: 0.9259345531463623:  22%|██▏       | 5784/25880 [1:12:25<4:10:13,  1.34it/s]
1|5785|Loss: 0.8260159492492676:  22%|██▏       | 5784/25880 [1:12:26<4:10:13,  1.34it/s]
1|5785|Loss: 0.8260159492492676:  22%|██▏       | 5785/25880 [1:12:26<4:08:13,  1.35it/s]
1|5786|Loss: 0.786282479763031:  22%|██▏       | 5785/25880 [1:12:27<4:08:13,  1.35it/s] 
1|5786|Loss: 0.786282479763031:  22%|██▏       | 5786/25880 [1:12:27<4:26:24,  1.26it/s]
1|5787|Loss: 0.9277298450469971:  22%|██▏       | 5786/25880 [1:12:27<4:26:24,  1.26it/s]
1|5787|Loss: 0.9277298450469971:  22%|██▏       | 5787/25880 [1:12:28<4:16:28,  1.31it/s]
1|5788|Loss: 0.948596715927124:  22%|██▏       | 5787/25880 [1:12:28<4:16:28,  1.31it/s] 
1|5788|Loss: 0.948596715927124:  22%|██▏       | 5788/25880 [1:12:28<3:58:41,  1.40it/s]
1|5789|Loss: 0.6297419667243958:  22%|██▏       | 5788/25880 [1:12:29<3:58:41,  1.40it/s]
1|5789|Loss: 0.6297419667243958:  22%|██▏       | 5789/25880 [1:12:29<3:59:14,  1.40it/s]
1|5790|Loss: 0.8795878291130066:  22%|██▏       | 5789/25880 [1:12:29<3:59:14,  1.40it/s]
1|5790|Loss: 0.8795878291130066:  22%|██▏       | 5790/25880 [1:12:30<3:49:49,  1.46it/s]
1|5791|Loss: 0.9432939887046814:  22%|██▏       | 5790/25880 [1:12:30<3:49:49,  1.46it/s]
1|5791|Loss: 0.9432939887046814:  22%|██▏       | 5791/25880 [1:12:30<3:56:52,  1.41it/s]
1|5792|Loss: 0.8918225765228271:  22%|██▏       | 5791/25880 [1:12:31<3:56:52,  1.41it/s]
1|5792|Loss: 0.8918225765228271:  22%|██▏       | 5792/25880 [1:12:31<4:05:59,  1.36it/s]
1|5793|Loss: 1.0019036531448364:  22%|██▏       | 5792/25880 [1:12:32<4:05:59,  1.36it/s]
1|5793|Loss: 1.0019036531448364:  22%|██▏       | 5793/25880 [1:12:32<4:07:08,  1.35it/s]
1|5794|Loss: 0.9525996446609497:  22%|██▏       | 5793/25880 [1:12:32<4:07:08,  1.35it/s]
1|5794|Loss: 0.9525996446609497:  22%|██▏       | 5794/25880 [1:12:33<4:06:13,  1.36it/s]
1|5795|Loss: 0.9544390439987183:  22%|██▏       | 5794/25880 [1:12:33<4:06:13,  1.36it/s]
1|5795|Loss: 0.9544390439987183:  22%|██▏       | 5795/25880 [1:12:33<3:58:35,  1.40it/s]
1|5796|Loss: 0.9093577861785889:  22%|██▏       | 5795/25880 [1:12:34<3:58:35,  1.40it/s]
1|5796|Loss: 0.9093577861785889:  22%|██▏       | 5796/25880 [1:12:34<3:36:56,  1.54it/s]
1|5797|Loss: 0.883353054523468:  22%|██▏       | 5796/25880 [1:12:34<3:36:56,  1.54it/s] 
1|5797|Loss: 0.883353054523468:  22%|██▏       | 5797/25880 [1:12:35<3:55:01,  1.42it/s]
1|5798|Loss: 0.9042364954948425:  22%|██▏       | 5797/25880 [1:12:35<3:55:01,  1.42it/s]
1|5798|Loss: 0.9042364954948425:  22%|██▏       | 5798/25880 [1:12:35<4:01:58,  1.38it/s]
1|5799|Loss: 0.7633811235427856:  22%|██▏       | 5798/25880 [1:12:36<4:01:58,  1.38it/s]
1|5799|Loss: 0.7633811235427856:  22%|██▏       | 5799/25880 [1:12:36<3:40:15,  1.52it/s]
1|5800|Loss: 0.8940990567207336:  22%|██▏       | 5799/25880 [1:12:36<3:40:15,  1.52it/s]
1|5800|Loss: 0.8940990567207336:  22%|██▏       | 5800/25880 [1:12:36<3:19:42,  1.68it/s]
1|5801|Loss: 0.7893519997596741:  22%|██▏       | 5800/25880 [1:12:37<3:19:42,  1.68it/s]
1|5801|Loss: 0.7893519997596741:  22%|██▏       | 5801/25880 [1:12:37<3:34:57,  1.56it/s]
1|5802|Loss: 0.9561399817466736:  22%|██▏       | 5801/25880 [1:12:38<3:34:57,  1.56it/s]
1|5802|Loss: 0.9561399817466736:  22%|██▏       | 5802/25880 [1:12:38<3:50:28,  1.45it/s]
1|5803|Loss: 0.6937333941459656:  22%|██▏       | 5802/25880 [1:12:38<3:50:28,  1.45it/s]
1|5803|Loss: 0.6937333941459656:  22%|██▏       | 5803/25880 [1:12:39<4:10:53,  1.33it/s]
1|5804|Loss: 0.6593700647354126:  22%|██▏       | 5803/25880 [1:12:39<4:10:53,  1.33it/s]
1|5804|Loss: 0.6593700647354126:  22%|██▏       | 5804/25880 [1:12:40<4:10:42,  1.33it/s]
1|5805|Loss: 0.9238396883010864:  22%|██▏       | 5804/25880 [1:12:40<4:10:42,  1.33it/s]
1|5805|Loss: 0.9238396883010864:  22%|██▏       | 5805/25880 [1:12:40<4:17:02,  1.30it/s]
1|5806|Loss: 0.8358545303344727:  22%|██▏       | 5805/25880 [1:12:41<4:17:02,  1.30it/s]
1|5806|Loss: 0.8358545303344727:  22%|██▏       | 5806/25880 [1:12:41<3:48:02,  1.47it/s]
1|5807|Loss: 0.8616994619369507:  22%|██▏       | 5806/25880 [1:12:41<3:48:02,  1.47it/s]
1|5807|Loss: 0.8616994619369507:  22%|██▏       | 5807/25880 [1:12:42<3:55:16,  1.42it/s]
1|5808|Loss: 0.9371806979179382:  22%|██▏       | 5807/25880 [1:12:42<3:55:16,  1.42it/s]
1|5808|Loss: 0.9371806979179382:  22%|██▏       | 5808/25880 [1:12:42<3:58:18,  1.40it/s]
1|5809|Loss: 0.8979573845863342:  22%|██▏       | 5808/25880 [1:12:43<3:58:18,  1.40it/s]
1|5809|Loss: 0.8979573845863342:  22%|██▏       | 5809/25880 [1:12:43<3:52:03,  1.44it/s]
1|5810|Loss: 0.726999044418335:  22%|██▏       | 5809/25880 [1:12:43<3:52:03,  1.44it/s] 
1|5810|Loss: 0.726999044418335:  22%|██▏       | 5810/25880 [1:12:44<4:13:39,  1.32it/s]
1|5811|Loss: 1.0287920236587524:  22%|██▏       | 5810/25880 [1:12:44<4:13:39,  1.32it/s]
1|5811|Loss: 1.0287920236587524:  22%|██▏       | 5811/25880 [1:12:45<4:28:58,  1.24it/s]
1|5812|Loss: 0.7632128596305847:  22%|██▏       | 5811/25880 [1:12:45<4:28:58,  1.24it/s]
1|5812|Loss: 0.7632128596305847:  22%|██▏       | 5812/25880 [1:12:46<4:23:50,  1.27it/s]
1|5813|Loss: 0.887141227722168:  22%|██▏       | 5812/25880 [1:12:46<4:23:50,  1.27it/s] 
1|5813|Loss: 0.887141227722168:  22%|██▏       | 5813/25880 [1:12:46<4:17:51,  1.30it/s]
1|5814|Loss: 0.721575915813446:  22%|██▏       | 5813/25880 [1:12:47<4:17:51,  1.30it/s]
1|5814|Loss: 0.721575915813446:  22%|██▏       | 5814/25880 [1:12:47<4:13:10,  1.32it/s]
1|5815|Loss: 0.9294917583465576:  22%|██▏       | 5814/25880 [1:12:47<4:13:10,  1.32it/s]
1|5815|Loss: 0.9294917583465576:  22%|██▏       | 5815/25880 [1:12:48<4:10:25,  1.34it/s]
1|5816|Loss: 0.8570499420166016:  22%|██▏       | 5815/25880 [1:12:48<4:10:25,  1.34it/s]
1|5816|Loss: 0.8570499420166016:  22%|██▏       | 5816/25880 [1:12:48<4:06:33,  1.36it/s]
1|5817|Loss: 0.8948277235031128:  22%|██▏       | 5816/25880 [1:12:49<4:06:33,  1.36it/s]
1|5817|Loss: 0.8948277235031128:  22%|██▏       | 5817/25880 [1:12:49<3:55:59,  1.42it/s]
1|5818|Loss: 1.0064929723739624:  22%|██▏       | 5817/25880 [1:12:49<3:55:59,  1.42it/s]
1|5818|Loss: 1.0064929723739624:  22%|██▏       | 5818/25880 [1:12:50<3:38:49,  1.53it/s]
1|5819|Loss: 0.8933945894241333:  22%|██▏       | 5818/25880 [1:12:50<3:38:49,  1.53it/s]
1|5819|Loss: 0.8933945894241333:  22%|██▏       | 5819/25880 [1:12:50<3:42:14,  1.50it/s]
1|5820|Loss: 0.8984780311584473:  22%|██▏       | 5819/25880 [1:12:51<3:42:14,  1.50it/s]
1|5820|Loss: 0.8984780311584473:  22%|██▏       | 5820/25880 [1:12:51<3:48:43,  1.46it/s]
1|5821|Loss: 0.8631640076637268:  22%|██▏       | 5820/25880 [1:12:51<3:48:43,  1.46it/s]
1|5821|Loss: 0.8631640076637268:  22%|██▏       | 5821/25880 [1:12:52<3:50:40,  1.45it/s]
1|5822|Loss: 0.8646212816238403:  22%|██▏       | 5821/25880 [1:12:52<3:50:40,  1.45it/s]
1|5822|Loss: 0.8646212816238403:  22%|██▏       | 5822/25880 [1:12:52<3:51:40,  1.44it/s]
1|5823|Loss: 0.7414074540138245:  22%|██▏       | 5822/25880 [1:12:53<3:51:40,  1.44it/s]
1|5823|Loss: 0.7414074540138245:  22%|██▎       | 5823/25880 [1:12:53<3:56:00,  1.42it/s]
1|5824|Loss: 0.8849722146987915:  22%|██▎       | 5823/25880 [1:12:54<3:56:00,  1.42it/s]
1|5824|Loss: 0.8849722146987915:  23%|██▎       | 5824/25880 [1:12:54<3:44:58,  1.49it/s]
1|5825|Loss: 0.8892378807067871:  23%|██▎       | 5824/25880 [1:12:54<3:44:58,  1.49it/s]
1|5825|Loss: 0.8892378807067871:  23%|██▎       | 5825/25880 [1:12:54<3:47:31,  1.47it/s]
1|5826|Loss: 0.826302170753479:  23%|██▎       | 5825/25880 [1:12:55<3:47:31,  1.47it/s] 
1|5826|Loss: 0.826302170753479:  23%|██▎       | 5826/25880 [1:12:55<3:51:15,  1.45it/s]
1|5827|Loss: 0.8951985836029053:  23%|██▎       | 5826/25880 [1:12:56<3:51:15,  1.45it/s]
1|5827|Loss: 0.8951985836029053:  23%|██▎       | 5827/25880 [1:12:56<3:53:04,  1.43it/s]
1|5828|Loss: 0.8773055076599121:  23%|██▎       | 5827/25880 [1:12:56<3:53:04,  1.43it/s]
1|5828|Loss: 0.8773055076599121:  23%|██▎       | 5828/25880 [1:12:57<4:10:24,  1.33it/s]
1|5829|Loss: 0.8327622413635254:  23%|██▎       | 5828/25880 [1:12:57<4:10:24,  1.33it/s]
1|5829|Loss: 0.8327622413635254:  23%|██▎       | 5829/25880 [1:12:58<4:20:08,  1.28it/s]
1|5830|Loss: 0.7223815321922302:  23%|██▎       | 5829/25880 [1:12:58<4:20:08,  1.28it/s]
1|5830|Loss: 0.7223815321922302:  23%|██▎       | 5830/25880 [1:12:58<4:31:39,  1.23it/s]
1|5831|Loss: 0.6978875994682312:  23%|██▎       | 5830/25880 [1:12:59<4:31:39,  1.23it/s]
1|5831|Loss: 0.6978875994682312:  23%|██▎       | 5831/25880 [1:12:59<4:38:08,  1.20it/s]
1|5832|Loss: 0.8733698725700378:  23%|██▎       | 5831/25880 [1:13:00<4:38:08,  1.20it/s]
1|5832|Loss: 0.8733698725700378:  23%|██▎       | 5832/25880 [1:13:00<4:31:09,  1.23it/s]
1|5833|Loss: 0.9800225496292114:  23%|██▎       | 5832/25880 [1:13:00<4:31:09,  1.23it/s]
1|5833|Loss: 0.9800225496292114:  23%|██▎       | 5833/25880 [1:13:01<4:08:34,  1.34it/s]
1|5834|Loss: 0.7982283234596252:  23%|██▎       | 5833/25880 [1:13:01<4:08:34,  1.34it/s]
1|5834|Loss: 0.7982283234596252:  23%|██▎       | 5834/25880 [1:13:01<4:01:25,  1.38it/s]
1|5835|Loss: 0.9218779802322388:  23%|██▎       | 5834/25880 [1:13:02<4:01:25,  1.38it/s]
1|5835|Loss: 0.9218779802322388:  23%|██▎       | 5835/25880 [1:13:02<3:47:19,  1.47it/s]
1|5836|Loss: 1.0056520700454712:  23%|██▎       | 5835/25880 [1:13:02<3:47:19,  1.47it/s]
1|5836|Loss: 1.0056520700454712:  23%|██▎       | 5836/25880 [1:13:03<3:46:35,  1.47it/s]
1|5837|Loss: 0.9706286787986755:  23%|██▎       | 5836/25880 [1:13:03<3:46:35,  1.47it/s]
1|5837|Loss: 0.9706286787986755:  23%|██▎       | 5837/25880 [1:13:03<4:03:20,  1.37it/s]
1|5838|Loss: 0.8531954288482666:  23%|██▎       | 5837/25880 [1:13:04<4:03:20,  1.37it/s]
1|5838|Loss: 0.8531954288482666:  23%|██▎       | 5838/25880 [1:13:04<4:07:51,  1.35it/s]
1|5839|Loss: 0.8860780596733093:  23%|██▎       | 5838/25880 [1:13:05<4:07:51,  1.35it/s]
1|5839|Loss: 0.8860780596733093:  23%|██▎       | 5839/25880 [1:13:05<4:07:18,  1.35it/s]
1|5840|Loss: 0.8152527213096619:  23%|██▎       | 5839/25880 [1:13:05<4:07:18,  1.35it/s]
1|5840|Loss: 0.8152527213096619:  23%|██▎       | 5840/25880 [1:13:06<4:17:51,  1.30it/s]
1|5841|Loss: 0.7377867102622986:  23%|██▎       | 5840/25880 [1:13:06<4:17:51,  1.30it/s]
1|5841|Loss: 0.7377867102622986:  23%|██▎       | 5841/25880 [1:13:07<4:09:23,  1.34it/s]
1|5842|Loss: 0.981458306312561:  23%|██▎       | 5841/25880 [1:13:07<4:09:23,  1.34it/s] 
1|5842|Loss: 0.981458306312561:  23%|██▎       | 5842/25880 [1:13:07<4:18:36,  1.29it/s]
1|5843|Loss: 0.997761070728302:  23%|██▎       | 5842/25880 [1:13:08<4:18:36,  1.29it/s]
1|5843|Loss: 0.997761070728302:  23%|██▎       | 5843/25880 [1:13:08<3:55:38,  1.42it/s]
1|5844|Loss: 0.6879129409790039:  23%|██▎       | 5843/25880 [1:13:08<3:55:38,  1.42it/s]
1|5844|Loss: 0.6879129409790039:  23%|██▎       | 5844/25880 [1:13:09<3:52:19,  1.44it/s]
1|5845|Loss: 0.901963472366333:  23%|██▎       | 5844/25880 [1:13:09<3:52:19,  1.44it/s] 
1|5845|Loss: 0.901963472366333:  23%|██▎       | 5845/25880 [1:13:09<3:44:15,  1.49it/s]
1|5846|Loss: 0.7431896328926086:  23%|██▎       | 5845/25880 [1:13:10<3:44:15,  1.49it/s]
1|5846|Loss: 0.7431896328926086:  23%|██▎       | 5846/25880 [1:13:10<3:48:03,  1.46it/s]
1|5847|Loss: 0.7739190459251404:  23%|██▎       | 5846/25880 [1:13:10<3:48:03,  1.46it/s]
1|5847|Loss: 0.7739190459251404:  23%|██▎       | 5847/25880 [1:13:11<3:58:01,  1.40it/s]
1|5848|Loss: 0.8338719010353088:  23%|██▎       | 5847/25880 [1:13:11<3:58:01,  1.40it/s]
1|5848|Loss: 0.8338719010353088:  23%|██▎       | 5848/25880 [1:13:11<3:59:08,  1.40it/s]
1|5849|Loss: 0.873009979724884:  23%|██▎       | 5848/25880 [1:13:12<3:59:08,  1.40it/s] 
1|5849|Loss: 0.873009979724884:  23%|██▎       | 5849/25880 [1:13:12<3:51:59,  1.44it/s]
1|5850|Loss: 0.7215048670768738:  23%|██▎       | 5849/25880 [1:13:12<3:51:59,  1.44it/s]
1|5850|Loss: 0.7215048670768738:  23%|██▎       | 5850/25880 [1:13:13<3:52:00,  1.44it/s]
1|5851|Loss: 0.9153479933738708:  23%|██▎       | 5850/25880 [1:13:13<3:52:00,  1.44it/s]
1|5851|Loss: 0.9153479933738708:  23%|██▎       | 5851/25880 [1:13:13<3:54:59,  1.42it/s]
1|5852|Loss: 0.880422830581665:  23%|██▎       | 5851/25880 [1:13:14<3:54:59,  1.42it/s] 
1|5852|Loss: 0.880422830581665:  23%|██▎       | 5852/25880 [1:13:14<3:58:31,  1.40it/s]
1|5853|Loss: 1.0261130332946777:  23%|██▎       | 5852/25880 [1:13:15<3:58:31,  1.40it/s]
1|5853|Loss: 1.0261130332946777:  23%|██▎       | 5853/25880 [1:13:15<4:05:15,  1.36it/s]
1|5854|Loss: 0.7715513706207275:  23%|██▎       | 5853/25880 [1:13:15<4:05:15,  1.36it/s]
1|5854|Loss: 0.7715513706207275:  23%|██▎       | 5854/25880 [1:13:16<4:03:54,  1.37it/s]
1|5855|Loss: 0.8535038232803345:  23%|██▎       | 5854/25880 [1:13:16<4:03:54,  1.37it/s]
1|5855|Loss: 0.8535038232803345:  23%|██▎       | 5855/25880 [1:13:17<4:10:34,  1.33it/s]
1|5856|Loss: 1.0227329730987549:  23%|██▎       | 5855/25880 [1:13:17<4:10:34,  1.33it/s]
1|5856|Loss: 1.0227329730987549:  23%|██▎       | 5856/25880 [1:13:17<4:02:42,  1.38it/s]
1|5857|Loss: 0.8419284224510193:  23%|██▎       | 5856/25880 [1:13:18<4:02:42,  1.38it/s]
1|5857|Loss: 0.8419284224510193:  23%|██▎       | 5857/25880 [1:13:18<3:50:15,  1.45it/s]
1|5858|Loss: 0.9383967518806458:  23%|██▎       | 5857/25880 [1:13:18<3:50:15,  1.45it/s]
1|5858|Loss: 0.9383967518806458:  23%|██▎       | 5858/25880 [1:13:18<3:34:53,  1.55it/s]
1|5859|Loss: 0.7793470025062561:  23%|██▎       | 5858/25880 [1:13:19<3:34:53,  1.55it/s]
1|5859|Loss: 0.7793470025062561:  23%|██▎       | 5859/25880 [1:13:19<3:47:45,  1.47it/s]
1|5860|Loss: 0.9372023940086365:  23%|██▎       | 5859/25880 [1:13:20<3:47:45,  1.47it/s]
1|5860|Loss: 0.9372023940086365:  23%|██▎       | 5860/25880 [1:13:20<4:00:16,  1.39it/s]
1|5861|Loss: 0.7797842025756836:  23%|██▎       | 5860/25880 [1:13:20<4:00:16,  1.39it/s]
1|5861|Loss: 0.7797842025756836:  23%|██▎       | 5861/25880 [1:13:21<4:03:58,  1.37it/s]
1|5862|Loss: 0.8516178131103516:  23%|██▎       | 5861/25880 [1:13:21<4:03:58,  1.37it/s]
1|5862|Loss: 0.8516178131103516:  23%|██▎       | 5862/25880 [1:13:21<4:04:18,  1.37it/s]
1|5863|Loss: 0.8367433547973633:  23%|██▎       | 5862/25880 [1:13:22<4:04:18,  1.37it/s]
1|5863|Loss: 0.8367433547973633:  23%|██▎       | 5863/25880 [1:13:22<4:09:38,  1.34it/s]
1|5864|Loss: 0.7655386328697205:  23%|██▎       | 5863/25880 [1:13:23<4:09:38,  1.34it/s]
1|5864|Loss: 0.7655386328697205:  23%|██▎       | 5864/25880 [1:13:23<3:53:02,  1.43it/s]
1|5865|Loss: 0.9799119830131531:  23%|██▎       | 5864/25880 [1:13:23<3:53:02,  1.43it/s]
1|5865|Loss: 0.9799119830131531:  23%|██▎       | 5865/25880 [1:13:23<3:42:44,  1.50it/s]
1|5866|Loss: 0.8568792939186096:  23%|██▎       | 5865/25880 [1:13:24<3:42:44,  1.50it/s]
1|5866|Loss: 0.8568792939186096:  23%|██▎       | 5866/25880 [1:13:24<3:46:22,  1.47it/s]
1|5867|Loss: 0.9800787568092346:  23%|██▎       | 5866/25880 [1:13:24<3:46:22,  1.47it/s]
1|5867|Loss: 0.9800787568092346:  23%|██▎       | 5867/25880 [1:13:25<3:42:03,  1.50it/s]
1|5868|Loss: 0.8777429461479187:  23%|██▎       | 5867/25880 [1:13:25<3:42:03,  1.50it/s]
1|5868|Loss: 0.8777429461479187:  23%|██▎       | 5868/25880 [1:13:25<3:46:45,  1.47it/s]
1|5869|Loss: 0.9164376258850098:  23%|██▎       | 5868/25880 [1:13:26<3:46:45,  1.47it/s]
1|5869|Loss: 0.9164376258850098:  23%|██▎       | 5869/25880 [1:13:26<3:49:47,  1.45it/s]
1|5870|Loss: 0.7877761125564575:  23%|██▎       | 5869/25880 [1:13:27<3:49:47,  1.45it/s]
1|5870|Loss: 0.7877761125564575:  23%|██▎       | 5870/25880 [1:13:27<3:53:07,  1.43it/s]
1|5871|Loss: 1.007864236831665:  23%|██▎       | 5870/25880 [1:13:27<3:53:07,  1.43it/s] 
1|5871|Loss: 1.007864236831665:  23%|██▎       | 5871/25880 [1:13:28<3:47:30,  1.47it/s]
1|5872|Loss: 0.8366326093673706:  23%|██▎       | 5871/25880 [1:13:28<3:47:30,  1.47it/s]
1|5872|Loss: 0.8366326093673706:  23%|██▎       | 5872/25880 [1:13:28<3:50:48,  1.44it/s]
1|5873|Loss: 0.8342455625534058:  23%|██▎       | 5872/25880 [1:13:29<3:50:48,  1.44it/s]
1|5873|Loss: 0.8342455625534058:  23%|██▎       | 5873/25880 [1:13:29<3:46:16,  1.47it/s]
1|5874|Loss: 0.8403237462043762:  23%|██▎       | 5873/25880 [1:13:29<3:46:16,  1.47it/s]
1|5874|Loss: 0.8403237462043762:  23%|██▎       | 5874/25880 [1:13:30<3:56:55,  1.41it/s]
1|5875|Loss: 0.9095296263694763:  23%|██▎       | 5874/25880 [1:13:30<3:56:55,  1.41it/s]
1|5875|Loss: 0.9095296263694763:  23%|██▎       | 5875/25880 [1:13:30<3:48:20,  1.46it/s]
1|5876|Loss: 0.8073670864105225:  23%|██▎       | 5875/25880 [1:13:31<3:48:20,  1.46it/s]
1|5876|Loss: 0.8073670864105225:  23%|██▎       | 5876/25880 [1:13:31<4:10:39,  1.33it/s]
1|5877|Loss: 0.913670539855957:  23%|██▎       | 5876/25880 [1:13:32<4:10:39,  1.33it/s] 
1|5877|Loss: 0.913670539855957:  23%|██▎       | 5877/25880 [1:13:32<3:55:09,  1.42it/s]
1|5878|Loss: 0.7828248143196106:  23%|██▎       | 5877/25880 [1:13:32<3:55:09,  1.42it/s]
1|5878|Loss: 0.7828248143196106:  23%|██▎       | 5878/25880 [1:13:32<3:52:28,  1.43it/s]
1|5879|Loss: 0.8275179862976074:  23%|██▎       | 5878/25880 [1:13:33<3:52:28,  1.43it/s]
1|5879|Loss: 0.8275179862976074:  23%|██▎       | 5879/25880 [1:13:33<3:48:35,  1.46it/s]
1|5880|Loss: 0.8982533812522888:  23%|██▎       | 5879/25880 [1:13:33<3:48:35,  1.46it/s]
1|5880|Loss: 0.8982533812522888:  23%|██▎       | 5880/25880 [1:13:34<3:51:08,  1.44it/s]
1|5881|Loss: 0.8107208609580994:  23%|██▎       | 5880/25880 [1:13:34<3:51:08,  1.44it/s]
1|5881|Loss: 0.8107208609580994:  23%|██▎       | 5881/25880 [1:13:35<4:05:21,  1.36it/s]
1|5882|Loss: 0.8384878039360046:  23%|██▎       | 5881/25880 [1:13:35<4:05:21,  1.36it/s]
1|5882|Loss: 0.8384878039360046:  23%|██▎       | 5882/25880 [1:13:35<3:59:19,  1.39it/s]
1|5883|Loss: 0.9430725574493408:  23%|██▎       | 5882/25880 [1:13:36<3:59:19,  1.39it/s]
1|5883|Loss: 0.9430725574493408:  23%|██▎       | 5883/25880 [1:13:36<3:55:32,  1.41it/s]
1|5884|Loss: 0.9454278945922852:  23%|██▎       | 5883/25880 [1:13:36<3:55:32,  1.41it/s]
1|5884|Loss: 0.9454278945922852:  23%|██▎       | 5884/25880 [1:13:37<3:56:57,  1.41it/s]
1|5885|Loss: 0.8299451470375061:  23%|██▎       | 5884/25880 [1:13:37<3:56:57,  1.41it/s]
1|5885|Loss: 0.8299451470375061:  23%|██▎       | 5885/25880 [1:13:38<4:04:49,  1.36it/s]
1|5886|Loss: 0.9481357932090759:  23%|██▎       | 5885/25880 [1:13:38<4:04:49,  1.36it/s]
1|5886|Loss: 0.9481357932090759:  23%|██▎       | 5886/25880 [1:13:38<3:58:53,  1.39it/s]
1|5887|Loss: 0.9872289299964905:  23%|██▎       | 5886/25880 [1:13:39<3:58:53,  1.39it/s]
1|5887|Loss: 0.9872289299964905:  23%|██▎       | 5887/25880 [1:13:39<3:49:14,  1.45it/s]
1|5888|Loss: 0.7224411368370056:  23%|██▎       | 5887/25880 [1:13:39<3:49:14,  1.45it/s]
1|5888|Loss: 0.7224411368370056:  23%|██▎       | 5888/25880 [1:13:40<3:49:27,  1.45it/s]
1|5889|Loss: 0.8660919070243835:  23%|██▎       | 5888/25880 [1:13:40<3:49:27,  1.45it/s]
1|5889|Loss: 0.8660919070243835:  23%|██▎       | 5889/25880 [1:13:40<4:07:20,  1.35it/s]
1|5890|Loss: 0.6574460864067078:  23%|██▎       | 5889/25880 [1:13:41<4:07:20,  1.35it/s]
1|5890|Loss: 0.6574460864067078:  23%|██▎       | 5890/25880 [1:13:41<3:52:07,  1.44it/s]
1|5891|Loss: 0.8887242674827576:  23%|██▎       | 5890/25880 [1:13:41<3:52:07,  1.44it/s]
1|5891|Loss: 0.8887242674827576:  23%|██▎       | 5891/25880 [1:13:42<4:08:59,  1.34it/s]
1|5892|Loss: 0.7901631593704224:  23%|██▎       | 5891/25880 [1:13:42<4:08:59,  1.34it/s]
1|5892|Loss: 0.7901631593704224:  23%|██▎       | 5892/25880 [1:13:43<4:15:59,  1.30it/s]
1|5893|Loss: 0.7973905801773071:  23%|██▎       | 5892/25880 [1:13:43<4:15:59,  1.30it/s]
1|5893|Loss: 0.7973905801773071:  23%|██▎       | 5893/25880 [1:13:43<3:57:31,  1.40it/s]
1|5894|Loss: 1.0088757276535034:  23%|██▎       | 5893/25880 [1:13:44<3:57:31,  1.40it/s]
1|5894|Loss: 1.0088757276535034:  23%|██▎       | 5894/25880 [1:13:44<3:55:04,  1.42it/s]
1|5895|Loss: 0.8135204911231995:  23%|██▎       | 5894/25880 [1:13:44<3:55:04,  1.42it/s]
1|5895|Loss: 0.8135204911231995:  23%|██▎       | 5895/25880 [1:13:45<3:58:19,  1.40it/s]
1|5896|Loss: 0.8867685794830322:  23%|██▎       | 5895/25880 [1:13:45<3:58:19,  1.40it/s]
1|5896|Loss: 0.8867685794830322:  23%|██▎       | 5896/25880 [1:13:46<4:10:26,  1.33it/s]
1|5897|Loss: 0.8309494853019714:  23%|██▎       | 5896/25880 [1:13:46<4:10:26,  1.33it/s]
1|5897|Loss: 0.8309494853019714:  23%|██▎       | 5897/25880 [1:13:46<4:08:55,  1.34it/s]
1|5898|Loss: 0.7879480719566345:  23%|██▎       | 5897/25880 [1:13:47<4:08:55,  1.34it/s]
1|5898|Loss: 0.7879480719566345:  23%|██▎       | 5898/25880 [1:13:47<4:21:23,  1.27it/s]
1|5899|Loss: 0.8912867307662964:  23%|██▎       | 5898/25880 [1:13:48<4:21:23,  1.27it/s]
1|5899|Loss: 0.8912867307662964:  23%|██▎       | 5899/25880 [1:13:48<4:19:41,  1.28it/s]
1|5900|Loss: 0.8244494795799255:  23%|██▎       | 5899/25880 [1:13:48<4:19:41,  1.28it/s]
1|5900|Loss: 0.8244494795799255:  23%|██▎       | 5900/25880 [1:13:49<4:25:04,  1.26it/s]
1|5901|Loss: 0.7705860733985901:  23%|██▎       | 5900/25880 [1:13:49<4:25:04,  1.26it/s]
1|5901|Loss: 0.7705860733985901:  23%|██▎       | 5901/25880 [1:13:49<4:22:06,  1.27it/s]
1|5902|Loss: 0.8869673013687134:  23%|██▎       | 5901/25880 [1:13:50<4:22:06,  1.27it/s]
1|5902|Loss: 0.8869673013687134:  23%|██▎       | 5902/25880 [1:13:50<4:35:56,  1.21it/s]
1|5903|Loss: 0.7825982570648193:  23%|██▎       | 5902/25880 [1:13:51<4:35:56,  1.21it/s]
1|5903|Loss: 0.7825982570648193:  23%|██▎       | 5903/25880 [1:13:51<4:32:34,  1.22it/s]
1|5904|Loss: 0.7335997819900513:  23%|██▎       | 5903/25880 [1:13:52<4:32:34,  1.22it/s]
1|5904|Loss: 0.7335997819900513:  23%|██▎       | 5904/25880 [1:13:52<4:24:09,  1.26it/s]
1|5905|Loss: 0.90247642993927:  23%|██▎       | 5904/25880 [1:13:52<4:24:09,  1.26it/s]  
1|5905|Loss: 0.90247642993927:  23%|██▎       | 5905/25880 [1:13:53<4:14:41,  1.31it/s]
1|5906|Loss: 0.8948439359664917:  23%|██▎       | 5905/25880 [1:13:53<4:14:41,  1.31it/s]
1|5906|Loss: 0.8948439359664917:  23%|██▎       | 5906/25880 [1:13:53<4:22:24,  1.27it/s]
1|5907|Loss: 0.8230942487716675:  23%|██▎       | 5906/25880 [1:13:54<4:22:24,  1.27it/s]
1|5907|Loss: 0.8230942487716675:  23%|██▎       | 5907/25880 [1:13:54<4:21:15,  1.27it/s]
1|5908|Loss: 0.7307595610618591:  23%|██▎       | 5907/25880 [1:13:55<4:21:15,  1.27it/s]
1|5908|Loss: 0.7307595610618591:  23%|██▎       | 5908/25880 [1:13:55<4:16:31,  1.30it/s]
1|5909|Loss: 0.8654270768165588:  23%|██▎       | 5908/25880 [1:13:55<4:16:31,  1.30it/s]
1|5909|Loss: 0.8654270768165588:  23%|██▎       | 5909/25880 [1:13:56<4:23:11,  1.26it/s]
1|5910|Loss: 0.9731569886207581:  23%|██▎       | 5909/25880 [1:13:56<4:23:11,  1.26it/s]
1|5910|Loss: 0.9731569886207581:  23%|██▎       | 5910/25880 [1:13:57<4:21:48,  1.27it/s]
1|5911|Loss: 0.9268199801445007:  23%|██▎       | 5910/25880 [1:13:57<4:21:48,  1.27it/s]
1|5911|Loss: 0.9268199801445007:  23%|██▎       | 5911/25880 [1:13:58<4:36:06,  1.21it/s]
1|5912|Loss: 0.8468984961509705:  23%|██▎       | 5911/25880 [1:13:58<4:36:06,  1.21it/s]
1|5912|Loss: 0.8468984961509705:  23%|██▎       | 5912/25880 [1:13:58<4:28:22,  1.24it/s]
1|5913|Loss: 0.8217690587043762:  23%|██▎       | 5912/25880 [1:13:59<4:28:22,  1.24it/s]
1|5913|Loss: 0.8217690587043762:  23%|██▎       | 5913/25880 [1:13:59<4:17:27,  1.29it/s]
1|5914|Loss: 0.8879069685935974:  23%|██▎       | 5913/25880 [1:13:59<4:17:27,  1.29it/s]
1|5914|Loss: 0.8879069685935974:  23%|██▎       | 5914/25880 [1:14:00<3:54:36,  1.42it/s]
1|5915|Loss: 0.89389568567276:  23%|██▎       | 5914/25880 [1:14:00<3:54:36,  1.42it/s]  
1|5915|Loss: 0.89389568567276:  23%|██▎       | 5915/25880 [1:14:00<4:00:18,  1.38it/s]
1|5916|Loss: 0.8665193319320679:  23%|██▎       | 5915/25880 [1:14:01<4:00:18,  1.38it/s]
1|5916|Loss: 0.8665193319320679:  23%|██▎       | 5916/25880 [1:14:01<4:08:32,  1.34it/s]
1|5917|Loss: 0.8652976751327515:  23%|██▎       | 5916/25880 [1:14:02<4:08:32,  1.34it/s]
1|5917|Loss: 0.8652976751327515:  23%|██▎       | 5917/25880 [1:14:02<4:14:17,  1.31it/s]
1|5918|Loss: 0.941361665725708:  23%|██▎       | 5917/25880 [1:14:02<4:14:17,  1.31it/s] 
1|5918|Loss: 0.941361665725708:  23%|██▎       | 5918/25880 [1:14:03<4:23:22,  1.26it/s]
1|5919|Loss: 0.8127297163009644:  23%|██▎       | 5918/25880 [1:14:03<4:23:22,  1.26it/s]
1|5919|Loss: 0.8127297163009644:  23%|██▎       | 5919/25880 [1:14:03<4:12:03,  1.32it/s]
1|5920|Loss: 0.8373533487319946:  23%|██▎       | 5919/25880 [1:14:04<4:12:03,  1.32it/s]
1|5920|Loss: 0.8373533487319946:  23%|██▎       | 5920/25880 [1:14:04<4:08:47,  1.34it/s]
1|5921|Loss: 0.8288031220436096:  23%|██▎       | 5920/25880 [1:14:05<4:08:47,  1.34it/s]
1|5921|Loss: 0.8288031220436096:  23%|██▎       | 5921/25880 [1:14:05<4:05:59,  1.35it/s]
1|5922|Loss: 0.8459339737892151:  23%|██▎       | 5921/25880 [1:14:05<4:05:59,  1.35it/s]
1|5922|Loss: 0.8459339737892151:  23%|██▎       | 5922/25880 [1:14:06<3:57:28,  1.40it/s]
1|5923|Loss: 0.8055542707443237:  23%|██▎       | 5922/25880 [1:14:06<3:57:28,  1.40it/s]
1|5923|Loss: 0.8055542707443237:  23%|██▎       | 5923/25880 [1:14:06<4:05:09,  1.36it/s]
1|5924|Loss: 0.7176893949508667:  23%|██▎       | 5923/25880 [1:14:07<4:05:09,  1.36it/s]
1|5924|Loss: 0.7176893949508667:  23%|██▎       | 5924/25880 [1:14:07<3:44:34,  1.48it/s]
1|5925|Loss: 0.874104380607605:  23%|██▎       | 5924/25880 [1:14:07<3:44:34,  1.48it/s] 
1|5925|Loss: 0.874104380607605:  23%|██▎       | 5925/25880 [1:14:08<3:52:53,  1.43it/s]
1|5926|Loss: 0.8178266882896423:  23%|██▎       | 5925/25880 [1:14:08<3:52:53,  1.43it/s]
1|5926|Loss: 0.8178266882896423:  23%|██▎       | 5926/25880 [1:14:08<3:58:25,  1.39it/s]
1|5927|Loss: 0.8232443332672119:  23%|██▎       | 5926/25880 [1:14:09<3:58:25,  1.39it/s]
1|5927|Loss: 0.8232443332672119:  23%|██▎       | 5927/25880 [1:14:09<3:47:19,  1.46it/s]
1|5928|Loss: 0.8185070753097534:  23%|██▎       | 5927/25880 [1:14:09<3:47:19,  1.46it/s]
1|5928|Loss: 0.8185070753097534:  23%|██▎       | 5928/25880 [1:14:10<3:58:05,  1.40it/s]
1|5929|Loss: 0.9064034223556519:  23%|██▎       | 5928/25880 [1:14:10<3:58:05,  1.40it/s]
1|5929|Loss: 0.9064034223556519:  23%|██▎       | 5929/25880 [1:14:11<4:09:34,  1.33it/s]
1|5930|Loss: 0.8029250502586365:  23%|██▎       | 5929/25880 [1:14:11<4:09:34,  1.33it/s]
1|5930|Loss: 0.8029250502586365:  23%|██▎       | 5930/25880 [1:14:11<4:07:01,  1.35it/s]
1|5931|Loss: 0.7665879130363464:  23%|██▎       | 5930/25880 [1:14:12<4:07:01,  1.35it/s]
1|5931|Loss: 0.7665879130363464:  23%|██▎       | 5931/25880 [1:14:12<4:19:36,  1.28it/s]
1|5932|Loss: 0.7987545728683472:  23%|██▎       | 5931/25880 [1:14:13<4:19:36,  1.28it/s]
1|5932|Loss: 0.7987545728683472:  23%|██▎       | 5932/25880 [1:14:13<4:17:50,  1.29it/s]
1|5933|Loss: 0.893292248249054:  23%|██▎       | 5932/25880 [1:14:13<4:17:50,  1.29it/s] 
1|5933|Loss: 0.893292248249054:  23%|██▎       | 5933/25880 [1:14:14<4:11:24,  1.32it/s]
1|5934|Loss: 0.8696170449256897:  23%|██▎       | 5933/25880 [1:14:14<4:11:24,  1.32it/s]
1|5934|Loss: 0.8696170449256897:  23%|██▎       | 5934/25880 [1:14:14<4:08:30,  1.34it/s]
1|5935|Loss: 0.9027753472328186:  23%|██▎       | 5934/25880 [1:14:15<4:08:30,  1.34it/s]
1|5935|Loss: 0.9027753472328186:  23%|██▎       | 5935/25880 [1:14:15<3:52:55,  1.43it/s]
1|5936|Loss: 0.8612817525863647:  23%|██▎       | 5935/25880 [1:14:15<3:52:55,  1.43it/s]
1|5936|Loss: 0.8612817525863647:  23%|██▎       | 5936/25880 [1:14:16<4:07:23,  1.34it/s]
1|5937|Loss: 0.911794900894165:  23%|██▎       | 5936/25880 [1:14:16<4:07:23,  1.34it/s] 
1|5937|Loss: 0.911794900894165:  23%|██▎       | 5937/25880 [1:14:17<4:02:23,  1.37it/s]
1|5938|Loss: 0.7990204095840454:  23%|██▎       | 5937/25880 [1:14:17<4:02:23,  1.37it/s]
1|5938|Loss: 0.7990204095840454:  23%|██▎       | 5938/25880 [1:14:17<4:12:55,  1.31it/s]
1|5939|Loss: 0.8523434996604919:  23%|██▎       | 5938/25880 [1:14:18<4:12:55,  1.31it/s]
1|5939|Loss: 0.8523434996604919:  23%|██▎       | 5939/25880 [1:14:18<4:21:04,  1.27it/s]
1|5940|Loss: 0.8436249494552612:  23%|██▎       | 5939/25880 [1:14:19<4:21:04,  1.27it/s]
1|5940|Loss: 0.8436249494552612:  23%|██▎       | 5940/25880 [1:14:19<4:17:20,  1.29it/s]
1|5941|Loss: 0.8229014873504639:  23%|██▎       | 5940/25880 [1:14:19<4:17:20,  1.29it/s]
1|5941|Loss: 0.8229014873504639:  23%|██▎       | 5941/25880 [1:14:20<3:56:45,  1.40it/s]
1|5942|Loss: 0.8599095940589905:  23%|██▎       | 5941/25880 [1:14:20<3:56:45,  1.40it/s]
1|5942|Loss: 0.8599095940589905:  23%|██▎       | 5942/25880 [1:14:20<3:54:33,  1.42it/s]
1|5943|Loss: 1.0039910078048706:  23%|██▎       | 5942/25880 [1:14:21<3:54:33,  1.42it/s]
1|5943|Loss: 1.0039910078048706:  23%|██▎       | 5943/25880 [1:14:21<4:01:57,  1.37it/s]
1|5944|Loss: 0.9051478505134583:  23%|██▎       | 5943/25880 [1:14:21<4:01:57,  1.37it/s]
1|5944|Loss: 0.9051478505134583:  23%|██▎       | 5944/25880 [1:14:22<4:01:18,  1.38it/s]
1|5945|Loss: 0.8673086762428284:  23%|██▎       | 5944/25880 [1:14:22<4:01:18,  1.38it/s]
1|5945|Loss: 0.8673086762428284:  23%|██▎       | 5945/25880 [1:14:22<4:01:33,  1.38it/s]
1|5946|Loss: 0.8670234084129333:  23%|██▎       | 5945/25880 [1:14:23<4:01:33,  1.38it/s]
1|5946|Loss: 0.8670234084129333:  23%|██▎       | 5946/25880 [1:14:23<4:12:06,  1.32it/s]
1|5947|Loss: 0.8673948645591736:  23%|██▎       | 5946/25880 [1:14:24<4:12:06,  1.32it/s]
1|5947|Loss: 0.8673948645591736:  23%|██▎       | 5947/25880 [1:14:24<4:16:57,  1.29it/s]
1|5948|Loss: 0.8478491902351379:  23%|██▎       | 5947/25880 [1:14:24<4:16:57,  1.29it/s]
1|5948|Loss: 0.8478491902351379:  23%|██▎       | 5948/25880 [1:14:25<3:58:42,  1.39it/s]
1|5949|Loss: 0.7610000371932983:  23%|██▎       | 5948/25880 [1:14:25<3:58:42,  1.39it/s]
1|5949|Loss: 0.7610000371932983:  23%|██▎       | 5949/25880 [1:14:25<3:48:35,  1.45it/s]
1|5950|Loss: 0.7969473004341125:  23%|██▎       | 5949/25880 [1:14:26<3:48:35,  1.45it/s]
1|5950|Loss: 0.7969473004341125:  23%|██▎       | 5950/25880 [1:14:26<3:51:30,  1.43it/s]
1|5951|Loss: 0.9027867913246155:  23%|██▎       | 5950/25880 [1:14:26<3:51:30,  1.43it/s]
1|5951|Loss: 0.9027867913246155:  23%|██▎       | 5951/25880 [1:14:27<3:53:11,  1.42it/s]
1|5952|Loss: 0.7932674884796143:  23%|██▎       | 5951/25880 [1:14:27<3:53:11,  1.42it/s]
1|5952|Loss: 0.7932674884796143:  23%|██▎       | 5952/25880 [1:14:27<3:55:45,  1.41it/s]
1|5953|Loss: 0.9487216472625732:  23%|██▎       | 5952/25880 [1:14:28<3:55:45,  1.41it/s]
1|5953|Loss: 0.9487216472625732:  23%|██▎       | 5953/25880 [1:14:28<3:58:14,  1.39it/s]
1|5954|Loss: 0.8451413512229919:  23%|██▎       | 5953/25880 [1:14:29<3:58:14,  1.39it/s]
1|5954|Loss: 0.8451413512229919:  23%|██▎       | 5954/25880 [1:14:29<4:03:52,  1.36it/s]
1|5955|Loss: 0.8801373243331909:  23%|██▎       | 5954/25880 [1:14:29<4:03:52,  1.36it/s]
1|5955|Loss: 0.8801373243331909:  23%|██▎       | 5955/25880 [1:14:30<4:04:27,  1.36it/s]
1|5956|Loss: 0.6858469247817993:  23%|██▎       | 5955/25880 [1:14:30<4:04:27,  1.36it/s]
1|5956|Loss: 0.6858469247817993:  23%|██▎       | 5956/25880 [1:14:30<4:09:20,  1.33it/s]
1|5957|Loss: 0.9207614064216614:  23%|██▎       | 5956/25880 [1:14:31<4:09:20,  1.33it/s]
1|5957|Loss: 0.9207614064216614:  23%|██▎       | 5957/25880 [1:14:31<4:09:29,  1.33it/s]
1|5958|Loss: 0.8466483950614929:  23%|██▎       | 5957/25880 [1:14:32<4:09:29,  1.33it/s]
1|5958|Loss: 0.8466483950614929:  23%|██▎       | 5958/25880 [1:14:32<3:55:52,  1.41it/s]
1|5959|Loss: 0.8549314737319946:  23%|██▎       | 5958/25880 [1:14:32<3:55:52,  1.41it/s]
1|5959|Loss: 0.8549314737319946:  23%|██▎       | 5959/25880 [1:14:32<3:45:25,  1.47it/s]
1|5960|Loss: 0.7958906888961792:  23%|██▎       | 5959/25880 [1:14:33<3:45:25,  1.47it/s]
1|5960|Loss: 0.7958906888961792:  23%|██▎       | 5960/25880 [1:14:33<3:48:30,  1.45it/s]
1|5961|Loss: 0.9176161885261536:  23%|██▎       | 5960/25880 [1:14:34<3:48:30,  1.45it/s]
1|5961|Loss: 0.9176161885261536:  23%|██▎       | 5961/25880 [1:14:34<4:02:21,  1.37it/s]
1|5962|Loss: 0.925246000289917:  23%|██▎       | 5961/25880 [1:14:34<4:02:21,  1.37it/s] 
1|5962|Loss: 0.925246000289917:  23%|██▎       | 5962/25880 [1:14:35<4:15:04,  1.30it/s]
1|5963|Loss: 0.8851358890533447:  23%|██▎       | 5962/25880 [1:14:35<4:15:04,  1.30it/s]
1|5963|Loss: 0.8851358890533447:  23%|██▎       | 5963/25880 [1:14:36<4:24:11,  1.26it/s]
1|5964|Loss: 0.9670597910881042:  23%|██▎       | 5963/25880 [1:14:36<4:24:11,  1.26it/s]
1|5964|Loss: 0.9670597910881042:  23%|██▎       | 5964/25880 [1:14:36<4:20:38,  1.27it/s]
1|5965|Loss: 0.83547443151474:  23%|██▎       | 5964/25880 [1:14:37<4:20:38,  1.27it/s]  
1|5965|Loss: 0.83547443151474:  23%|██▎       | 5965/25880 [1:14:37<4:15:40,  1.30it/s]
1|5966|Loss: 0.8956477046012878:  23%|██▎       | 5965/25880 [1:14:38<4:15:40,  1.30it/s]
1|5966|Loss: 0.8956477046012878:  23%|██▎       | 5966/25880 [1:14:38<4:16:46,  1.29it/s]
1|5967|Loss: 0.7987117171287537:  23%|██▎       | 5966/25880 [1:14:38<4:16:46,  1.29it/s]
1|5967|Loss: 0.7987117171287537:  23%|██▎       | 5967/25880 [1:14:39<4:06:59,  1.34it/s]
1|5968|Loss: 0.8930253386497498:  23%|██▎       | 5967/25880 [1:14:39<4:06:59,  1.34it/s]
1|5968|Loss: 0.8930253386497498:  23%|██▎       | 5968/25880 [1:14:39<3:56:33,  1.40it/s]
1|5969|Loss: 0.8944637179374695:  23%|██▎       | 5968/25880 [1:14:40<3:56:33,  1.40it/s]
1|5969|Loss: 0.8944637179374695:  23%|██▎       | 5969/25880 [1:14:40<3:57:40,  1.40it/s]
1|5970|Loss: 0.9625691771507263:  23%|██▎       | 5969/25880 [1:14:40<3:57:40,  1.40it/s]
1|5970|Loss: 0.9625691771507263:  23%|██▎       | 5970/25880 [1:14:41<3:49:05,  1.45it/s]
1|5971|Loss: 0.8331210613250732:  23%|██▎       | 5970/25880 [1:14:41<3:49:05,  1.45it/s]
1|5971|Loss: 0.8331210613250732:  23%|██▎       | 5971/25880 [1:14:41<3:58:17,  1.39it/s]
1|5972|Loss: 0.7817672491073608:  23%|██▎       | 5971/25880 [1:14:42<3:58:17,  1.39it/s]
1|5972|Loss: 0.7817672491073608:  23%|██▎       | 5972/25880 [1:14:42<4:09:49,  1.33it/s]
1|5973|Loss: 0.8838437795639038:  23%|██▎       | 5972/25880 [1:14:43<4:09:49,  1.33it/s]
1|5973|Loss: 0.8838437795639038:  23%|██▎       | 5973/25880 [1:14:43<3:52:19,  1.43it/s]
1|5974|Loss: 0.8475140333175659:  23%|██▎       | 5973/25880 [1:14:43<3:52:19,  1.43it/s]
1|5974|Loss: 0.8475140333175659:  23%|██▎       | 5974/25880 [1:14:44<3:51:17,  1.43it/s]
1|5975|Loss: 0.8122264742851257:  23%|██▎       | 5974/25880 [1:14:44<3:51:17,  1.43it/s]
1|5975|Loss: 0.8122264742851257:  23%|██▎       | 5975/25880 [1:14:44<3:48:30,  1.45it/s]
1|5976|Loss: 0.8975963592529297:  23%|██▎       | 5975/25880 [1:14:45<3:48:30,  1.45it/s]
1|5976|Loss: 0.8975963592529297:  23%|██▎       | 5976/25880 [1:14:45<3:31:15,  1.57it/s]
1|5977|Loss: 1.131971001625061:  23%|██▎       | 5976/25880 [1:14:45<3:31:15,  1.57it/s] 
1|5977|Loss: 1.131971001625061:  23%|██▎       | 5977/25880 [1:14:45<3:32:41,  1.56it/s]
1|5978|Loss: 0.8169208765029907:  23%|██▎       | 5977/25880 [1:14:46<3:32:41,  1.56it/s]
1|5978|Loss: 0.8169208765029907:  23%|██▎       | 5978/25880 [1:14:46<3:38:52,  1.52it/s]
1|5979|Loss: 0.8872552514076233:  23%|██▎       | 5978/25880 [1:14:46<3:38:52,  1.52it/s]
1|5979|Loss: 0.8872552514076233:  23%|██▎       | 5979/25880 [1:14:47<3:33:12,  1.56it/s]
1|5980|Loss: 0.9069899916648865:  23%|██▎       | 5979/25880 [1:14:47<3:33:12,  1.56it/s]
1|5980|Loss: 0.9069899916648865:  23%|██▎       | 5980/25880 [1:14:47<3:39:07,  1.51it/s]
1|5981|Loss: 0.7839500308036804:  23%|██▎       | 5980/25880 [1:14:48<3:39:07,  1.51it/s]
1|5981|Loss: 0.7839500308036804:  23%|██▎       | 5981/25880 [1:14:48<3:45:58,  1.47it/s]
1|5982|Loss: 0.7836496829986572:  23%|██▎       | 5981/25880 [1:14:49<3:45:58,  1.47it/s]
1|5982|Loss: 0.7836496829986572:  23%|██▎       | 5982/25880 [1:14:49<3:55:16,  1.41it/s]
1|5983|Loss: 0.8713181614875793:  23%|██▎       | 5982/25880 [1:14:49<3:55:16,  1.41it/s]
1|5983|Loss: 0.8713181614875793:  23%|██▎       | 5983/25880 [1:14:50<3:49:51,  1.44it/s]
1|5984|Loss: 0.8640826940536499:  23%|██▎       | 5983/25880 [1:14:50<3:49:51,  1.44it/s]
1|5984|Loss: 0.8640826940536499:  23%|██▎       | 5984/25880 [1:14:50<4:02:18,  1.37it/s]
1|5985|Loss: 0.7669655084609985:  23%|██▎       | 5984/25880 [1:14:51<4:02:18,  1.37it/s]
1|5985|Loss: 0.7669655084609985:  23%|██▎       | 5985/25880 [1:14:51<4:12:29,  1.31it/s]
1|5986|Loss: 0.8711400032043457:  23%|██▎       | 5985/25880 [1:14:52<4:12:29,  1.31it/s]
1|5986|Loss: 0.8711400032043457:  23%|██▎       | 5986/25880 [1:14:52<4:12:22,  1.31it/s]
1|5987|Loss: 0.9275006055831909:  23%|██▎       | 5986/25880 [1:14:52<4:12:22,  1.31it/s]
1|5987|Loss: 0.9275006055831909:  23%|██▎       | 5987/25880 [1:14:53<3:52:49,  1.42it/s]
1|5988|Loss: 0.7710437178611755:  23%|██▎       | 5987/25880 [1:14:53<3:52:49,  1.42it/s]
1|5988|Loss: 0.7710437178611755:  23%|██▎       | 5988/25880 [1:14:53<3:50:57,  1.44it/s]
1|5989|Loss: 0.8456135392189026:  23%|██▎       | 5988/25880 [1:14:54<3:50:57,  1.44it/s]
1|5989|Loss: 0.8456135392189026:  23%|██▎       | 5989/25880 [1:14:54<3:55:05,  1.41it/s]
1|5990|Loss: 0.8291392922401428:  23%|██▎       | 5989/25880 [1:14:54<3:55:05,  1.41it/s]
1|5990|Loss: 0.8291392922401428:  23%|██▎       | 5990/25880 [1:14:55<3:55:52,  1.41it/s]
1|5991|Loss: 0.8365228176116943:  23%|██▎       | 5990/25880 [1:14:55<3:55:52,  1.41it/s]
1|5991|Loss: 0.8365228176116943:  23%|██▎       | 5991/25880 [1:14:55<3:46:10,  1.47it/s]
1|5992|Loss: 0.8958622813224792:  23%|██▎       | 5991/25880 [1:14:56<3:46:10,  1.47it/s]
1|5992|Loss: 0.8958622813224792:  23%|██▎       | 5992/25880 [1:14:56<3:48:32,  1.45it/s]
1|5993|Loss: 0.8960933685302734:  23%|██▎       | 5992/25880 [1:14:56<3:48:32,  1.45it/s]
1|5993|Loss: 0.8960933685302734:  23%|██▎       | 5993/25880 [1:14:57<3:41:26,  1.50it/s]
1|5994|Loss: 0.8199262619018555:  23%|██▎       | 5993/25880 [1:14:57<3:41:26,  1.50it/s]
1|5994|Loss: 0.8199262619018555:  23%|██▎       | 5994/25880 [1:14:57<3:44:30,  1.48it/s]
1|5995|Loss: 0.8765649199485779:  23%|██▎       | 5994/25880 [1:14:58<3:44:30,  1.48it/s]
1|5995|Loss: 0.8765649199485779:  23%|██▎       | 5995/25880 [1:14:58<3:49:22,  1.44it/s]
1|5996|Loss: 0.9336302280426025:  23%|██▎       | 5995/25880 [1:14:58<3:49:22,  1.44it/s]
1|5996|Loss: 0.9336302280426025:  23%|██▎       | 5996/25880 [1:14:59<3:35:34,  1.54it/s]
1|5997|Loss: 0.8763453364372253:  23%|██▎       | 5996/25880 [1:14:59<3:35:34,  1.54it/s]
1|5997|Loss: 0.8763453364372253:  23%|██▎       | 5997/25880 [1:14:59<3:32:04,  1.56it/s]
1|5998|Loss: 0.8056889176368713:  23%|██▎       | 5997/25880 [1:15:00<3:32:04,  1.56it/s]
1|5998|Loss: 0.8056889176368713:  23%|██▎       | 5998/25880 [1:15:00<3:49:26,  1.44it/s]
1|5999|Loss: 0.8655146360397339:  23%|██▎       | 5998/25880 [1:15:00<3:49:26,  1.44it/s]
1|5999|Loss: 0.8655146360397339:  23%|██▎       | 5999/25880 [1:15:01<3:56:51,  1.40it/s]
1|6000|Loss: 0.7206514477729797:  23%|██▎       | 5999/25880 [1:15:01<3:56:51,  1.40it/s]
1|6000|Loss: 0.7206514477729797:  23%|██▎       | 6000/25880 [1:15:01<3:47:36,  1.46it/s]
1|6001|Loss: 0.7357102632522583:  23%|██▎       | 6000/25880 [1:15:02<3:47:36,  1.46it/s]
1|6001|Loss: 0.7357102632522583:  23%|██▎       | 6001/25880 [1:15:02<3:32:43,  1.56it/s]
1|6002|Loss: 0.7885870337486267:  23%|██▎       | 6001/25880 [1:15:02<3:32:43,  1.56it/s]
1|6002|Loss: 0.7885870337486267:  23%|██▎       | 6002/25880 [1:15:03<3:26:04,  1.61it/s]
1|6003|Loss: 0.8160930871963501:  23%|██▎       | 6002/25880 [1:15:03<3:26:04,  1.61it/s]
1|6003|Loss: 0.8160930871963501:  23%|██▎       | 6003/25880 [1:15:03<3:15:50,  1.69it/s]
1|6004|Loss: 0.954608142375946:  23%|██▎       | 6003/25880 [1:15:03<3:15:50,  1.69it/s] 
1|6004|Loss: 0.954608142375946:  23%|██▎       | 6004/25880 [1:15:04<3:25:02,  1.62it/s]
1|6005|Loss: 0.8990415334701538:  23%|██▎       | 6004/25880 [1:15:04<3:25:02,  1.62it/s]
1|6005|Loss: 0.8990415334701538:  23%|██▎       | 6005/25880 [1:15:04<3:27:09,  1.60it/s]
1|6006|Loss: 0.8610620498657227:  23%|██▎       | 6005/25880 [1:15:05<3:27:09,  1.60it/s]
1|6006|Loss: 0.8610620498657227:  23%|██▎       | 6006/25880 [1:15:05<3:45:02,  1.47it/s]
1|6007|Loss: 0.9511609673500061:  23%|██▎       | 6006/25880 [1:15:06<3:45:02,  1.47it/s]
1|6007|Loss: 0.9511609673500061:  23%|██▎       | 6007/25880 [1:15:06<4:02:59,  1.36it/s]
1|6008|Loss: 0.8678615689277649:  23%|██▎       | 6007/25880 [1:15:06<4:02:59,  1.36it/s]
1|6008|Loss: 0.8678615689277649:  23%|██▎       | 6008/25880 [1:15:07<3:58:34,  1.39it/s]
1|6009|Loss: 0.8896432518959045:  23%|██▎       | 6008/25880 [1:15:07<3:58:34,  1.39it/s]
1|6009|Loss: 0.8896432518959045:  23%|██▎       | 6009/25880 [1:15:07<3:56:51,  1.40it/s]
1|6010|Loss: 0.836685299873352:  23%|██▎       | 6009/25880 [1:15:08<3:56:51,  1.40it/s] 
1|6010|Loss: 0.836685299873352:  23%|██▎       | 6010/25880 [1:15:08<4:03:43,  1.36it/s]
1|6011|Loss: 0.8767178654670715:  23%|██▎       | 6010/25880 [1:15:09<4:03:43,  1.36it/s]
1|6011|Loss: 0.8767178654670715:  23%|██▎       | 6011/25880 [1:15:09<4:24:21,  1.25it/s]
1|6012|Loss: 0.8192957043647766:  23%|██▎       | 6011/25880 [1:15:10<4:24:21,  1.25it/s]
1|6012|Loss: 0.8192957043647766:  23%|██▎       | 6012/25880 [1:15:10<4:16:37,  1.29it/s]
1|6013|Loss: 0.9017254114151001:  23%|██▎       | 6012/25880 [1:15:10<4:16:37,  1.29it/s]
1|6013|Loss: 0.9017254114151001:  23%|██▎       | 6013/25880 [1:15:11<4:08:41,  1.33it/s]
1|6014|Loss: 0.7725589275360107:  23%|██▎       | 6013/25880 [1:15:11<4:08:41,  1.33it/s]
1|6014|Loss: 0.7725589275360107:  23%|██▎       | 6014/25880 [1:15:11<3:55:27,  1.41it/s]
1|6015|Loss: 0.9117358922958374:  23%|██▎       | 6014/25880 [1:15:12<3:55:27,  1.41it/s]
1|6015|Loss: 0.9117358922958374:  23%|██▎       | 6015/25880 [1:15:12<3:55:01,  1.41it/s]
1|6016|Loss: 0.8260619044303894:  23%|██▎       | 6015/25880 [1:15:12<3:55:01,  1.41it/s]
1|6016|Loss: 0.8260619044303894:  23%|██▎       | 6016/25880 [1:15:13<3:57:56,  1.39it/s]
1|6017|Loss: 0.6869857311248779:  23%|██▎       | 6016/25880 [1:15:13<3:57:56,  1.39it/s]
1|6017|Loss: 0.6869857311248779:  23%|██▎       | 6017/25880 [1:15:13<3:31:54,  1.56it/s]
1|6018|Loss: 0.877184271812439:  23%|██▎       | 6017/25880 [1:15:13<3:31:54,  1.56it/s] 
1|6018|Loss: 0.877184271812439:  23%|██▎       | 6018/25880 [1:15:14<3:42:35,  1.49it/s]
1|6019|Loss: 0.843899667263031:  23%|██▎       | 6018/25880 [1:15:14<3:42:35,  1.49it/s]
1|6019|Loss: 0.843899667263031:  23%|██▎       | 6019/25880 [1:15:15<3:48:07,  1.45it/s]
1|6020|Loss: 0.7952713966369629:  23%|██▎       | 6019/25880 [1:15:15<3:48:07,  1.45it/s]
1|6020|Loss: 0.7952713966369629:  23%|██▎       | 6020/25880 [1:15:15<3:59:22,  1.38it/s]
1|6021|Loss: 0.8341396450996399:  23%|██▎       | 6020/25880 [1:15:16<3:59:22,  1.38it/s]
1|6021|Loss: 0.8341396450996399:  23%|██▎       | 6021/25880 [1:15:16<3:53:12,  1.42it/s]
1|6022|Loss: 0.8071821331977844:  23%|██▎       | 6021/25880 [1:15:16<3:53:12,  1.42it/s]
1|6022|Loss: 0.8071821331977844:  23%|██▎       | 6022/25880 [1:15:17<3:53:20,  1.42it/s]
1|6023|Loss: 0.8394443988800049:  23%|██▎       | 6022/25880 [1:15:17<3:53:20,  1.42it/s]
1|6023|Loss: 0.8394443988800049:  23%|██▎       | 6023/25880 [1:15:17<3:55:20,  1.41it/s]
1|6024|Loss: 0.833950400352478:  23%|���█▎       | 6023/25880 [1:15:18<3:55:20,  1.41it/s] 
1|6024|Loss: 0.833950400352478:  23%|██▎       | 6024/25880 [1:15:18<3:49:58,  1.44it/s]
1|6025|Loss: 0.9402697086334229:  23%|██▎       | 6024/25880 [1:15:19<3:49:58,  1.44it/s]
1|6025|Loss: 0.9402697086334229:  23%|██▎       | 6025/25880 [1:15:19<4:06:33,  1.34it/s]
1|6026|Loss: 1.002601146697998:  23%|██▎       | 6025/25880 [1:15:19<4:06:33,  1.34it/s] 
1|6026|Loss: 1.002601146697998:  23%|██▎       | 6026/25880 [1:15:20<3:57:29,  1.39it/s]
1|6027|Loss: 0.9328396320343018:  23%|██▎       | 6026/25880 [1:15:20<3:57:29,  1.39it/s]
1|6027|Loss: 0.9328396320343018:  23%|██▎       | 6027/25880 [1:15:20<3:49:19,  1.44it/s]
1|6028|Loss: 0.7419506311416626:  23%|██▎       | 6027/25880 [1:15:21<3:49:19,  1.44it/s]
1|6028|Loss: 0.7419506311416626:  23%|██▎       | 6028/25880 [1:15:21<3:49:28,  1.44it/s]
1|6029|Loss: 0.7796841263771057:  23%|██▎       | 6028/25880 [1:15:21<3:49:28,  1.44it/s]
1|6029|Loss: 0.7796841263771057:  23%|██▎       | 6029/25880 [1:15:22<3:52:07,  1.43it/s]
1|6030|Loss: 0.9057741165161133:  23%|██▎       | 6029/25880 [1:15:22<3:52:07,  1.43it/s]
1|6030|Loss: 0.9057741165161133:  23%|██▎       | 6030/25880 [1:15:22<3:43:08,  1.48it/s]
1|6031|Loss: 0.7338405847549438:  23%|██▎       | 6030/25880 [1:15:23<3:43:08,  1.48it/s]
1|6031|Loss: 0.7338405847549438:  23%|██▎       | 6031/25880 [1:15:23<3:45:51,  1.46it/s]
1|6032|Loss: 0.9089964628219604:  23%|██▎       | 6031/25880 [1:15:23<3:45:51,  1.46it/s]
1|6032|Loss: 0.9089964628219604:  23%|██▎       | 6032/25880 [1:15:24<3:59:11,  1.38it/s]
1|6033|Loss: 0.8735425472259521:  23%|██▎       | 6032/25880 [1:15:24<3:59:11,  1.38it/s]
1|6033|Loss: 0.8735425472259521:  23%|██▎       | 6033/25880 [1:15:25<4:02:46,  1.36it/s]
1|6034|Loss: 0.8709779381752014:  23%|██▎       | 6033/25880 [1:15:25<4:02:46,  1.36it/s]
1|6034|Loss: 0.8709779381752014:  23%|██▎       | 6034/25880 [1:15:25<4:08:31,  1.33it/s]
1|6035|Loss: 0.6781519651412964:  23%|██▎       | 6034/25880 [1:15:26<4:08:31,  1.33it/s]
1|6035|Loss: 0.6781519651412964:  23%|██▎       | 6035/25880 [1:15:26<4:26:25,  1.24it/s]
1|6036|Loss: 0.9377351403236389:  23%|██▎       | 6035/25880 [1:15:27<4:26:25,  1.24it/s]
1|6036|Loss: 0.9377351403236389:  23%|██▎       | 6036/25880 [1:15:27<4:43:07,  1.17it/s]
1|6037|Loss: 0.913216233253479:  23%|██▎       | 6036/25880 [1:15:28<4:43:07,  1.17it/s] 
1|6037|Loss: 0.913216233253479:  23%|██▎       | 6037/25880 [1:15:28<4:36:07,  1.20it/s]
1|6038|Loss: 0.8873935341835022:  23%|██▎       | 6037/25880 [1:15:28<4:36:07,  1.20it/s]
1|6038|Loss: 0.8873935341835022:  23%|██▎       | 6038/25880 [1:15:29<4:26:45,  1.24it/s]
1|6039|Loss: 0.8814021348953247:  23%|██▎       | 6038/25880 [1:15:29<4:26:45,  1.24it/s]
1|6039|Loss: 0.8814021348953247:  23%|██▎       | 6039/25880 [1:15:29<4:11:34,  1.31it/s]
1|6040|Loss: 0.9667034149169922:  23%|██▎       | 6039/25880 [1:15:30<4:11:34,  1.31it/s]
1|6040|Loss: 0.9667034149169922:  23%|██▎       | 6040/25880 [1:15:30<4:11:34,  1.31it/s]
1|6041|Loss: 0.9265716671943665:  23%|██▎       | 6040/25880 [1:15:31<4:11:34,  1.31it/s]
1|6041|Loss: 0.9265716671943665:  23%|██▎       | 6041/25880 [1:15:31<4:10:47,  1.32it/s]
1|6042|Loss: 0.7825554013252258:  23%|██▎       | 6041/25880 [1:15:31<4:10:47,  1.32it/s]
1|6042|Loss: 0.7825554013252258:  23%|██▎       | 6042/25880 [1:15:32<4:01:18,  1.37it/s]
1|6043|Loss: 0.8729544878005981:  23%|██▎       | 6042/25880 [1:15:32<4:01:18,  1.37it/s]
1|6043|Loss: 0.8729544878005981:  23%|██▎       | 6043/25880 [1:15:32<3:52:36,  1.42it/s]
1|6044|Loss: 0.7433304786682129:  23%|██▎       | 6043/25880 [1:15:33<3:52:36,  1.42it/s]
1|6044|Loss: 0.7433304786682129:  23%|██▎       | 6044/25880 [1:15:33<3:59:55,  1.38it/s]
1|6045|Loss: 0.9149614572525024:  23%|██▎       | 6044/25880 [1:15:33<3:59:55,  1.38it/s]
1|6045|Loss: 0.9149614572525024:  23%|██▎       | 6045/25880 [1:15:34<4:07:51,  1.33it/s]
1|6046|Loss: 0.8094453811645508:  23%|██▎       | 6045/25880 [1:15:34<4:07:51,  1.33it/s]
1|6046|Loss: 0.8094453811645508:  23%|██▎       | 6046/25880 [1:15:35<4:00:05,  1.38it/s]
1|6047|Loss: 0.8159589767456055:  23%|██▎       | 6046/25880 [1:15:35<4:00:05,  1.38it/s]
1|6047|Loss: 0.8159589767456055:  23%|██▎       | 6047/25880 [1:15:35<4:17:33,  1.28it/s]
1|6048|Loss: 0.8032506108283997:  23%|██▎       | 6047/25880 [1:15:36<4:17:33,  1.28it/s]
1|6048|Loss: 0.8032506108283997:  23%|██▎       | 6048/25880 [1:15:36<4:01:21,  1.37it/s]
1|6049|Loss: 0.8119162321090698:  23%|██▎       | 6048/25880 [1:15:36<4:01:21,  1.37it/s]
1|6049|Loss: 0.8119162321090698:  23%|██▎       | 6049/25880 [1:15:37<3:56:45,  1.40it/s]
1|6050|Loss: 0.9199895262718201:  23%|██▎       | 6049/25880 [1:15:37<3:56:45,  1.40it/s]
1|6050|Loss: 0.9199895262718201:  23%|██▎       | 6050/25880 [1:15:37<3:56:01,  1.40it/s]
1|6051|Loss: 0.9343279600143433:  23%|██▎       | 6050/25880 [1:15:38<3:56:01,  1.40it/s]
1|6051|Loss: 0.9343279600143433:  23%|██▎       | 6051/25880 [1:15:38<4:15:32,  1.29it/s]
1|6052|Loss: 0.9154115915298462:  23%|██▎       | 6051/25880 [1:15:39<4:15:32,  1.29it/s]
1|6052|Loss: 0.9154115915298462:  23%|██▎       | 6052/25880 [1:15:39<4:14:05,  1.30it/s]
1|6053|Loss: 0.8635940551757812:  23%|██▎       | 6052/25880 [1:15:39<4:14:05,  1.30it/s]
1|6053|Loss: 0.8635940551757812:  23%|██▎       | 6053/25880 [1:15:40<4:07:28,  1.34it/s]
1|6054|Loss: 0.7724004983901978:  23%|██▎       | 6053/25880 [1:15:40<4:07:28,  1.34it/s]
1|6054|Loss: 0.7724004983901978:  23%|██▎       | 6054/25880 [1:15:40<3:57:30,  1.39it/s]
1|6055|Loss: 0.8618445992469788:  23%|██▎       | 6054/25880 [1:15:41<3:57:30,  1.39it/s]
1|6055|Loss: 0.8618445992469788:  23%|██▎       | 6055/25880 [1:15:41<3:42:33,  1.48it/s]
1|6056|Loss: 0.9342687129974365:  23%|██▎       | 6055/25880 [1:15:41<3:42:33,  1.48it/s]
1|6056|Loss: 0.9342687129974365:  23%|██▎       | 6056/25880 [1:15:42<3:45:09,  1.47it/s]
1|6057|Loss: 0.9284619092941284:  23%|██▎       | 6056/25880 [1:15:42<3:45:09,  1.47it/s]
1|6057|Loss: 0.9284619092941284:  23%|██▎       | 6057/25880 [1:15:42<3:21:56,  1.64it/s]
1|6058|Loss: 0.8457892537117004:  23%|██▎       | 6057/25880 [1:15:42<3:21:56,  1.64it/s]
1|6058|Loss: 0.8457892537117004:  23%|██▎       | 6058/25880 [1:15:43<3:24:40,  1.61it/s]
1|6059|Loss: 0.8661213517189026:  23%|██▎       | 6058/25880 [1:15:43<3:24:40,  1.61it/s]
1|6059|Loss: 0.8661213517189026:  23%|██▎       | 6059/25880 [1:15:43<3:25:45,  1.61it/s]
1|6060|Loss: 0.8610631823539734:  23%|██▎       | 6059/25880 [1:15:44<3:25:45,  1.61it/s]
1|6060|Loss: 0.8610631823539734:  23%|██▎       | 6060/25880 [1:15:44<3:25:28,  1.61it/s]
1|6061|Loss: 0.8009037971496582:  23%|██▎       | 6060/25880 [1:15:45<3:25:28,  1.61it/s]
1|6061|Loss: 0.8009037971496582:  23%|██▎       | 6061/25880 [1:15:45<3:54:14,  1.41it/s]
1|6062|Loss: 0.7193798422813416:  23%|██▎       | 6061/25880 [1:15:45<3:54:14,  1.41it/s]
1|6062|Loss: 0.7193798422813416:  23%|██▎       | 6062/25880 [1:15:46<4:12:38,  1.31it/s]
1|6063|Loss: 0.9220276474952698:  23%|██▎       | 6062/25880 [1:15:46<4:12:38,  1.31it/s]
1|6063|Loss: 0.9220276474952698:  23%|██▎       | 6063/25880 [1:15:47<4:20:08,  1.27it/s]
1|6064|Loss: 0.8528535962104797:  23%|██▎       | 6063/25880 [1:15:47<4:20:08,  1.27it/s]
1|6064|Loss: 0.8528535962104797:  23%|██▎       | 6064/25880 [1:15:47<4:16:33,  1.29it/s]
1|6065|Loss: 0.8663918972015381:  23%|██▎       | 6064/25880 [1:15:48<4:16:33,  1.29it/s]
1|6065|Loss: 0.8663918972015381:  23%|██▎       | 6065/25880 [1:15:48<4:17:25,  1.28it/s]
1|6066|Loss: 0.8888406157493591:  23%|██▎       | 6065/25880 [1:15:49<4:17:25,  1.28it/s]
1|6066|Loss: 0.8888406157493591:  23%|██▎       | 6066/25880 [1:15:49<4:23:27,  1.25it/s]
1|6067|Loss: 0.9416107535362244:  23%|██▎       | 6066/25880 [1:15:49<4:23:27,  1.25it/s]
1|6067|Loss: 0.9416107535362244:  23%|██▎       | 6067/25880 [1:15:50<4:05:37,  1.34it/s]
1|6068|Loss: 0.8610026240348816:  23%|██▎       | 6067/25880 [1:15:50<4:05:37,  1.34it/s]
1|6068|Loss: 0.8610026240348816:  23%|██▎       | 6068/25880 [1:15:50<3:49:01,  1.44it/s]
1|6069|Loss: 0.8649597764015198:  23%|██▎       | 6068/25880 [1:15:51<3:49:01,  1.44it/s]
1|6069|Loss: 0.8649597764015198:  23%|██▎       | 6069/25880 [1:15:51<3:47:41,  1.45it/s]
1|6070|Loss: 0.7038277387619019:  23%|██▎       | 6069/25880 [1:15:51<3:47:41,  1.45it/s]
1|6070|Loss: 0.7038277387619019:  23%|██▎       | 6070/25880 [1:15:52<3:59:04,  1.38it/s]
1|6071|Loss: 0.8998088836669922:  23%|██▎       | 6070/25880 [1:15:52<3:59:04,  1.38it/s]
1|6071|Loss: 0.8998088836669922:  23%|██▎       | 6071/25880 [1:15:52<3:52:25,  1.42it/s]
1|6072|Loss: 0.7592090964317322:  23%|██▎       | 6071/25880 [1:15:53<3:52:25,  1.42it/s]
1|6072|Loss: 0.7592090964317322:  23%|██▎       | 6072/25880 [1:15:53<3:50:44,  1.43it/s]
1|6073|Loss: 0.9062208533287048:  23%|██▎       | 6072/25880 [1:15:54<3:50:44,  1.43it/s]
1|6073|Loss: 0.9062208533287048:  23%|██▎       | 6073/25880 [1:15:54<3:59:23,  1.38it/s]
1|6074|Loss: 0.9297061562538147:  23%|██▎       | 6073/25880 [1:15:54<3:59:23,  1.38it/s]
1|6074|Loss: 0.9297061562538147:  23%|██▎       | 6074/25880 [1:15:55<3:59:47,  1.38it/s]
1|6075|Loss: 0.7320147156715393:  23%|██▎       | 6074/25880 [1:15:55<3:59:47,  1.38it/s]
1|6075|Loss: 0.7320147156715393:  23%|██▎       | 6075/25880 [1:15:55<3:41:33,  1.49it/s]
1|6076|Loss: 0.9443000555038452:  23%|██▎       | 6075/25880 [1:15:55<3:41:33,  1.49it/s]
1|6076|Loss: 0.9443000555038452:  23%|██▎       | 6076/25880 [1:15:56<3:35:42,  1.53it/s]
1|6077|Loss: 0.6987308859825134:  23%|██▎       | 6076/25880 [1:15:56<3:35:42,  1.53it/s]
1|6077|Loss: 0.6987308859825134:  23%|██▎       | 6077/25880 [1:15:56<3:39:33,  1.50it/s]
1|6078|Loss: 0.8111624121665955:  23%|██▎       | 6077/25880 [1:15:57<3:39:33,  1.50it/s]
1|6078|Loss: 0.8111624121665955:  23%|██▎       | 6078/25880 [1:15:57<3:52:49,  1.42it/s]
1|6079|Loss: 0.8428985476493835:  23%|██▎       | 6078/25880 [1:15:58<3:52:49,  1.42it/s]
1|6079|Loss: 0.8428985476493835:  23%|██▎       | 6079/25880 [1:15:58<3:47:58,  1.45it/s]
1|6080|Loss: 0.709644079208374:  23%|██▎       | 6079/25880 [1:15:58<3:47:58,  1.45it/s] 
1|6080|Loss: 0.709644079208374:  23%|██▎       | 6080/25880 [1:15:58<3:32:21,  1.55it/s]
1|6081|Loss: 0.8374949097633362:  23%|██▎       | 6080/25880 [1:15:59<3:32:21,  1.55it/s]
1|6081|Loss: 0.8374949097633362:  23%|██▎       | 6081/25880 [1:15:59<3:44:26,  1.47it/s]
1|6082|Loss: 0.8455616235733032:  23%|██▎       | 6081/25880 [1:16:00<3:44:26,  1.47it/s]
1|6082|Loss: 0.8455616235733032:  24%|██▎       | 6082/25880 [1:16:00<3:44:20,  1.47it/s]
1|6083|Loss: 0.8537353277206421:  24%|██▎       | 6082/25880 [1:16:00<3:44:20,  1.47it/s]
1|6083|Loss: 0.8537353277206421:  24%|██▎       | 6083/25880 [1:16:01<4:06:03,  1.34it/s]
1|6084|Loss: 0.7948228716850281:  24%|██▎       | 6083/25880 [1:16:01<4:06:03,  1.34it/s]
1|6084|Loss: 0.7948228716850281:  24%|██▎       | 6084/25880 [1:16:02<4:09:17,  1.32it/s]
1|6085|Loss: 0.9151589870452881:  24%|██▎       | 6084/25880 [1:16:02<4:09:17,  1.32it/s]
1|6085|Loss: 0.9151589870452881:  24%|██▎       | 6085/25880 [1:16:02<4:14:39,  1.30it/s]
1|6086|Loss: 0.9216498732566833:  24%|██▎       | 6085/25880 [1:16:03<4:14:39,  1.30it/s]
1|6086|Loss: 0.9216498732566833:  24%|██▎       | 6086/25880 [1:16:03<4:17:01,  1.28it/s]
1|6087|Loss: 0.9354761242866516:  24%|██▎       | 6086/25880 [1:16:04<4:17:01,  1.28it/s]
1|6087|Loss: 0.9354761242866516:  24%|██▎       | 6087/25880 [1:16:04<4:20:36,  1.27it/s]
1|6088|Loss: 0.8517504930496216:  24%|██▎       | 6087/25880 [1:16:04<4:20:36,  1.27it/s]
1|6088|Loss: 0.8517504930496216:  24%|██▎       | 6088/25880 [1:16:05<4:16:29,  1.29it/s]
1|6089|Loss: 0.752162754535675:  24%|██▎       | 6088/25880 [1:16:05<4:16:29,  1.29it/s] 
1|6089|Loss: 0.752162754535675:  24%|██▎       | 6089/25880 [1:16:06<4:16:27,  1.29it/s]
1|6090|Loss: 0.8129255771636963:  24%|██▎       | 6089/25880 [1:16:06<4:16:27,  1.29it/s]
1|6090|Loss: 0.8129255771636963:  24%|██▎       | 6090/25880 [1:16:06<4:13:36,  1.30it/s]
1|6091|Loss: 0.8502886891365051:  24%|██▎       | 6090/25880 [1:16:07<4:13:36,  1.30it/s]
1|6091|Loss: 0.8502886891365051:  24%|██▎       | 6091/25880 [1:16:07<4:17:17,  1.28it/s]
1|6092|Loss: 0.8115015625953674:  24%|██▎       | 6091/25880 [1:16:08<4:17:17,  1.28it/s]
1|6092|Loss: 0.8115015625953674:  24%|██▎       | 6092/25880 [1:16:08<4:14:37,  1.30it/s]
1|6093|Loss: 0.9371340274810791:  24%|██▎       | 6092/25880 [1:16:08<4:14:37,  1.30it/s]
1|6093|Loss: 0.9371340274810791:  24%|██▎       | 6093/25880 [1:16:09<4:25:09,  1.24it/s]
1|6094|Loss: 0.9189708232879639:  24%|██▎       | 6093/25880 [1:16:09<4:25:09,  1.24it/s]
1|6094|Loss: 0.9189708232879639:  24%|██▎       | 6094/25880 [1:16:09<4:22:50,  1.25it/s]
1|6095|Loss: 0.7767521142959595:  24%|██▎       | 6094/25880 [1:16:10<4:22:50,  1.25it/s]
1|6095|Loss: 0.7767521142959595:  24%|██▎       | 6095/25880 [1:16:10<4:18:38,  1.27it/s]
1|6096|Loss: 0.9903636574745178:  24%|██▎       | 6095/25880 [1:16:11<4:18:38,  1.27it/s]
1|6096|Loss: 0.9903636574745178:  24%|██▎       | 6096/25880 [1:16:11<4:20:26,  1.27it/s]
1|6097|Loss: 0.9174032211303711:  24%|██▎       | 6096/25880 [1:16:11<4:20:26,  1.27it/s]
1|6097|Loss: 0.9174032211303711:  24%|██▎       | 6097/25880 [1:16:12<4:24:02,  1.25it/s]
1|6098|Loss: 0.9212642908096313:  24%|██▎       | 6097/25880 [1:16:12<4:24:02,  1.25it/s]
1|6098|Loss: 0.9212642908096313:  24%|██▎       | 6098/25880 [1:16:13<4:25:00,  1.24it/s]
1|6099|Loss: 1.1297580003738403:  24%|██▎       | 6098/25880 [1:16:13<4:25:00,  1.24it/s]
1|6099|Loss: 1.1297580003738403:  24%|██▎       | 6099/25880 [1:16:13<4:19:37,  1.27it/s]
1|6100|Loss: 0.8958680033683777:  24%|██▎       | 6099/25880 [1:16:14<4:19:37,  1.27it/s]
1|6100|Loss: 0.8958680033683777:  24%|██▎       | 6100/25880 [1:16:14<4:11:14,  1.31it/s]
1|6101|Loss: 1.0301120281219482:  24%|██▎       | 6100/25880 [1:16:15<4:11:14,  1.31it/s]
1|6101|Loss: 1.0301120281219482:  24%|██▎       | 6101/25880 [1:16:15<4:08:37,  1.33it/s]
1|6102|Loss: 0.7301291227340698:  24%|██▎       | 6101/25880 [1:16:15<4:08:37,  1.33it/s]
1|6102|Loss: 0.7301291227340698:  24%|██▎       | 6102/25880 [1:16:16<4:21:40,  1.26it/s]
1|6103|Loss: 0.8926039338111877:  24%|██▎       | 6102/25880 [1:16:16<4:21:40,  1.26it/s]
1|6103|Loss: 0.8926039338111877:  24%|██▎       | 6103/25880 [1:16:17<4:29:05,  1.22it/s]
1|6104|Loss: 0.6573771238327026:  24%|█��▎       | 6103/25880 [1:16:17<4:29:05,  1.22it/s]
1|6104|Loss: 0.6573771238327026:  24%|██▎       | 6104/25880 [1:16:17<4:21:54,  1.26it/s]
1|6105|Loss: 0.7627798318862915:  24%|██▎       | 6104/25880 [1:16:18<4:21:54,  1.26it/s]
1|6105|Loss: 0.7627798318862915:  24%|██▎       | 6105/25880 [1:16:18<4:26:16,  1.24it/s]
1|6106|Loss: 0.8577260971069336:  24%|██▎       | 6105/25880 [1:16:19<4:26:16,  1.24it/s]
1|6106|Loss: 0.8577260971069336:  24%|██▎       | 6106/25880 [1:16:19<4:22:26,  1.26it/s]
1|6107|Loss: 0.8070878982543945:  24%|██▎       | 6106/25880 [1:16:19<4:22:26,  1.26it/s]
1|6107|Loss: 0.8070878982543945:  24%|██▎       | 6107/25880 [1:16:20<4:18:07,  1.28it/s]
1|6108|Loss: 0.765774130821228:  24%|██▎       | 6107/25880 [1:16:20<4:18:07,  1.28it/s] 
1|6108|Loss: 0.765774130821228:  24%|██▎       | 6108/25880 [1:16:21<4:31:37,  1.21it/s]
1|6109|Loss: 0.8296411037445068:  24%|██▎       | 6108/25880 [1:16:21<4:31:37,  1.21it/s]
1|6109|Loss: 0.8296411037445068:  24%|██▎       | 6109/25880 [1:16:21<4:27:19,  1.23it/s]
1|6110|Loss: 0.8192760348320007:  24%|██▎       | 6109/25880 [1:16:22<4:27:19,  1.23it/s]
1|6110|Loss: 0.8192760348320007:  24%|██▎       | 6110/25880 [1:16:22<4:13:02,  1.30it/s]
1|6111|Loss: 0.8021409511566162:  24%|██▎       | 6110/25880 [1:16:22<4:13:02,  1.30it/s]
1|6111|Loss: 0.8021409511566162:  24%|██▎       | 6111/25880 [1:16:23<3:50:32,  1.43it/s]
1|6112|Loss: 1.0148111581802368:  24%|██▎       | 6111/25880 [1:16:23<3:50:32,  1.43it/s]
1|6112|Loss: 1.0148111581802368:  24%|██▎       | 6112/25880 [1:16:23<3:48:48,  1.44it/s]
1|6113|Loss: 0.957564115524292:  24%|██▎       | 6112/25880 [1:16:24<3:48:48,  1.44it/s] 
1|6113|Loss: 0.957564115524292:  24%|██▎       | 6113/25880 [1:16:24<3:53:34,  1.41it/s]
1|6114|Loss: 0.8811861872673035:  24%|██▎       | 6113/25880 [1:16:24<3:53:34,  1.41it/s]
1|6114|Loss: 0.8811861872673035:  24%|██▎       | 6114/25880 [1:16:25<3:56:17,  1.39it/s]
1|6115|Loss: 0.8707150220870972:  24%|██▎       | 6114/25880 [1:16:25<3:56:17,  1.39it/s]
1|6115|Loss: 0.8707150220870972:  24%|██▎       | 6115/25880 [1:16:25<3:37:53,  1.51it/s]
1|6116|Loss: 0.8686962127685547:  24%|██▎       | 6115/25880 [1:16:26<3:37:53,  1.51it/s]
1|6116|Loss: 0.8686962127685547:  24%|██▎       | 6116/25880 [1:16:26<3:31:03,  1.56it/s]
1|6117|Loss: 0.9552526473999023:  24%|██▎       | 6116/25880 [1:16:26<3:31:03,  1.56it/s]
1|6117|Loss: 0.9552526473999023:  24%|██▎       | 6117/25880 [1:16:27<3:30:50,  1.56it/s]
1|6118|Loss: 0.8512908220291138:  24%|██▎       | 6117/25880 [1:16:27<3:30:50,  1.56it/s]
1|6118|Loss: 0.8512908220291138:  24%|██▎       | 6118/25880 [1:16:27<3:46:00,  1.46it/s]
1|6119|Loss: 1.0449730157852173:  24%|██▎       | 6118/25880 [1:16:28<3:46:00,  1.46it/s]
1|6119|Loss: 1.0449730157852173:  24%|██▎       | 6119/25880 [1:16:28<3:53:02,  1.41it/s]
1|6120|Loss: 0.959743857383728:  24%|██▎       | 6119/25880 [1:16:29<3:53:02,  1.41it/s] 
1|6120|Loss: 0.959743857383728:  24%|██▎       | 6120/25880 [1:16:29<3:53:49,  1.41it/s]
1|6121|Loss: 0.891109824180603:  24%|██▎       | 6120/25880 [1:16:29<3:53:49,  1.41it/s]
1|6121|Loss: 0.891109824180603:  24%|██▎       | 6121/25880 [1:16:30<3:55:04,  1.40it/s]
1|6122|Loss: 0.8574841022491455:  24%|██▎       | 6121/25880 [1:16:30<3:55:04,  1.40it/s]
1|6122|Loss: 0.8574841022491455:  24%|██▎       | 6122/25880 [1:16:30<3:42:09,  1.48it/s]
1|6123|Loss: 1.0297365188598633:  24%|██▎       | 6122/25880 [1:16:31<3:42:09,  1.48it/s]
1|6123|Loss: 1.0297365188598633:  24%|██▎       | 6123/25880 [1:16:31<3:44:15,  1.47it/s]
1|6124|Loss: 0.8667630553245544:  24%|██▎       | 6123/25880 [1:16:31<3:44:15,  1.47it/s]
1|6124|Loss: 0.8667630553245544:  24%|██▎       | 6124/25880 [1:16:31<3:37:52,  1.51it/s]
1|6125|Loss: 0.7576100826263428:  24%|██▎       | 6124/25880 [1:16:32<3:37:52,  1.51it/s]
1|6125|Loss: 0.7576100826263428:  24%|██▎       | 6125/25880 [1:16:32<3:24:19,  1.61it/s]
1|6126|Loss: 0.741873025894165:  24%|██▎       | 6125/25880 [1:16:32<3:24:19,  1.61it/s] 
1|6126|Loss: 0.741873025894165:  24%|██▎       | 6126/25880 [1:16:33<3:30:22,  1.56it/s]
1|6127|Loss: 0.7837052345275879:  24%|██▎       | 6126/25880 [1:16:33<3:30:22,  1.56it/s]
1|6127|Loss: 0.7837052345275879:  24%|██▎       | 6127/25880 [1:16:33<3:25:26,  1.60it/s]
1|6128|Loss: 0.8247965574264526:  24%|██▎       | 6127/25880 [1:16:34<3:25:26,  1.60it/s]
1|6128|Loss: 0.8247965574264526:  24%|██▎       | 6128/25880 [1:16:34<3:40:30,  1.49it/s]
1|6129|Loss: 0.7586265206336975:  24%|██▎       | 6128/25880 [1:16:34<3:40:30,  1.49it/s]
1|6129|Loss: 0.7586265206336975:  24%|██▎       | 6129/25880 [1:16:35<3:41:32,  1.49it/s]
1|6130|Loss: 0.783385694026947:  24%|██▎       | 6129/25880 [1:16:35<3:41:32,  1.49it/s] 
1|6130|Loss: 0.783385694026947:  24%|██▎       | 6130/25880 [1:16:35<3:29:38,  1.57it/s]
1|6131|Loss: 0.7889032363891602:  24%|██▎       | 6130/25880 [1:16:36<3:29:38,  1.57it/s]
1|6131|Loss: 0.7889032363891602:  24%|██▎       | 6131/25880 [1:16:36<3:32:17,  1.55it/s]
1|6132|Loss: 0.8039999008178711:  24%|██▎       | 6131/25880 [1:16:36<3:32:17,  1.55it/s]
1|6132|Loss: 0.8039999008178711:  24%|██▎       | 6132/25880 [1:16:37<3:38:44,  1.50it/s]
1|6133|Loss: 1.0708255767822266:  24%|██▎       | 6132/25880 [1:16:37<3:38:44,  1.50it/s]
1|6133|Loss: 1.0708255767822266:  24%|██▎       | 6133/25880 [1:16:37<3:44:24,  1.47it/s]
1|6134|Loss: 0.8388692140579224:  24%|██▎       | 6133/25880 [1:16:38<3:44:24,  1.47it/s]
1|6134|Loss: 0.8388692140579224:  24%|██▎       | 6134/25880 [1:16:38<3:50:13,  1.43it/s]
1|6135|Loss: 0.7300873398780823:  24%|██▎       | 6134/25880 [1:16:39<3:50:13,  1.43it/s]
1|6135|Loss: 0.7300873398780823:  24%|██▎       | 6135/25880 [1:16:39<3:55:26,  1.40it/s]
1|6136|Loss: 0.7590541243553162:  24%|██▎       | 6135/25880 [1:16:39<3:55:26,  1.40it/s]
1|6136|Loss: 0.7590541243553162:  24%|██▎       | 6136/25880 [1:16:40<3:50:48,  1.43it/s]
1|6137|Loss: 0.9255190491676331:  24%|██▎       | 6136/25880 [1:16:40<3:50:48,  1.43it/s]
1|6137|Loss: 0.9255190491676331:  24%|██▎       | 6137/25880 [1:16:40<3:35:49,  1.52it/s]
1|6138|Loss: 0.7917343974113464:  24%|██▎       | 6137/25880 [1:16:40<3:35:49,  1.52it/s]
1|6138|Loss: 0.7917343974113464:  24%|██▎       | 6138/25880 [1:16:41<3:39:54,  1.50it/s]
1|6139|Loss: 0.9016953706741333:  24%|██▎       | 6138/25880 [1:16:41<3:39:54,  1.50it/s]
1|6139|Loss: 0.9016953706741333:  24%|██▎       | 6139/25880 [1:16:41<3:39:54,  1.50it/s]
1|6140|Loss: 0.8470749855041504:  24%|██▎       | 6139/25880 [1:16:42<3:39:54,  1.50it/s]
1|6140|Loss: 0.8470749855041504:  24%|██▎       | 6140/25880 [1:16:42<3:42:25,  1.48it/s]
1|6141|Loss: 0.7683421969413757:  24%|██▎       | 6140/25880 [1:16:43<3:42:25,  1.48it/s]
1|6141|Loss: 0.7683421969413757:  24%|██▎       | 6141/25880 [1:16:43<3:48:50,  1.44it/s]
1|6142|Loss: 0.9097039103507996:  24%|██▎       | 6141/25880 [1:16:43<3:48:50,  1.44it/s]
1|6142|Loss: 0.9097039103507996:  24%|██▎       | 6142/25880 [1:16:44<4:01:25,  1.36it/s]
1|6143|Loss: 0.7946650981903076:  24%|██▎       | 6142/25880 [1:16:44<4:01:25,  1.36it/s]
1|6143|Loss: 0.7946650981903076:  24%|██▎       | 6143/25880 [1:16:45<4:10:41,  1.31it/s]
1|6144|Loss: 0.8863340020179749:  24%|██▎       | 6143/25880 [1:16:45<4:10:41,  1.31it/s]
1|6144|Loss: 0.8863340020179749:  24%|██▎       | 6144/25880 [1:16:45<3:42:12,  1.48it/s]
1|6145|Loss: 0.882280707359314:  24%|██▎       | 6144/25880 [1:16:45<3:42:12,  1.48it/s] 
1|6145|Loss: 0.882280707359314:  24%|██▎       | 6145/25880 [1:16:46<3:32:59,  1.54it/s]
1|6146|Loss: 0.7542161345481873:  24%|██▎       | 6145/25880 [1:16:46<3:32:59,  1.54it/s]
1|6146|Loss: 0.7542161345481873:  24%|██▎       | 6146/25880 [1:16:46<3:17:25,  1.67it/s]
1|6147|Loss: 0.7837112545967102:  24%|██▎       | 6146/25880 [1:16:46<3:17:25,  1.67it/s]
1|6147|Loss: 0.7837112545967102:  24%|██▍       | 6147/25880 [1:16:47<3:14:45,  1.69it/s]
1|6148|Loss: 0.9628702402114868:  24%|██▍       | 6147/25880 [1:16:47<3:14:45,  1.69it/s]
1|6148|Loss: 0.9628702402114868:  24%|██▍       | 6148/25880 [1:16:47<3:10:27,  1.73it/s]
1|6149|Loss: 0.8190158009529114:  24%|██▍       | 6148/25880 [1:16:48<3:10:27,  1.73it/s]
1|6149|Loss: 0.8190158009529114:  24%|██▍       | 6149/25880 [1:16:48<3:26:58,  1.59it/s]
1|6150|Loss: 0.7974363565444946:  24%|██▍       | 6149/25880 [1:16:48<3:26:58,  1.59it/s]
1|6150|Loss: 0.7974363565444946:  24%|██▍       | 6150/25880 [1:16:49<3:42:54,  1.48it/s]
1|6151|Loss: 0.8035123348236084:  24%|██▍       | 6150/25880 [1:16:49<3:42:54,  1.48it/s]
1|6151|Loss: 0.8035123348236084:  24%|██▍       | 6151/25880 [1:16:49<3:42:17,  1.48it/s]
1|6152|Loss: 0.8506457805633545:  24%|██▍       | 6151/25880 [1:16:50<3:42:17,  1.48it/s]
1|6152|Loss: 0.8506457805633545:  24%|██▍       | 6152/25880 [1:16:50<3:43:07,  1.47it/s]
1|6153|Loss: 0.8025794625282288:  24%|██▍       | 6152/25880 [1:16:50<3:43:07,  1.47it/s]
1|6153|Loss: 0.8025794625282288:  24%|██▍       | 6153/25880 [1:16:51<3:45:13,  1.46it/s]
1|6154|Loss: 0.9455799460411072:  24%|██▍       | 6153/25880 [1:16:51<3:45:13,  1.46it/s]
1|6154|Loss: 0.9455799460411072:  24%|██▍       | 6154/25880 [1:16:51<3:41:11,  1.49it/s]
1|6155|Loss: 0.901033878326416:  24%|██▍       | 6154/25880 [1:16:52<3:41:11,  1.49it/s] 
1|6155|Loss: 0.901033878326416:  24%|██▍       | 6155/25880 [1:16:52<3:27:52,  1.58it/s]
1|6156|Loss: 0.7893975973129272:  24%|██▍       | 6155/25880 [1:16:52<3:27:52,  1.58it/s]
1|6156|Loss: 0.7893975973129272:  24%|██▍       | 6156/25880 [1:16:53<4:03:02,  1.35it/s]
1|6157|Loss: 0.8375806212425232:  24%|██▍       | 6156/25880 [1:16:53<4:03:02,  1.35it/s]
1|6157|Loss: 0.8375806212425232:  24%|██▍       | 6157/25880 [1:16:54<3:52:19,  1.41it/s]
1|6158|Loss: 0.8212094902992249:  24%|██▍       | 6157/25880 [1:16:54<3:52:19,  1.41it/s]
1|6158|Loss: 0.8212094902992249:  24%|██▍       | 6158/25880 [1:16:54<3:39:15,  1.50it/s]
1|6159|Loss: 0.9814108610153198:  24%|██▍       | 6158/25880 [1:16:55<3:39:15,  1.50it/s]
1|6159|Loss: 0.9814108610153198:  24%|██▍       | 6159/25880 [1:16:55<3:39:59,  1.49it/s]
1|6160|Loss: 0.7980512976646423:  24%|██▍       | 6159/25880 [1:16:55<3:39:59,  1.49it/s]
1|6160|Loss: 0.7980512976646423:  24%|██▍       | 6160/25880 [1:16:56<3:55:02,  1.40it/s]
1|6161|Loss: 0.7912519574165344:  24%|██▍       | 6160/25880 [1:16:56<3:55:02,  1.40it/s]
1|6161|Loss: 0.7912519574165344:  24%|██▍       | 6161/25880 [1:16:56<3:59:04,  1.37it/s]
1|6162|Loss: 0.8823060989379883:  24%|██▍       | 6161/25880 [1:16:57<3:59:04,  1.37it/s]
1|6162|Loss: 0.8823060989379883:  24%|██▍       | 6162/25880 [1:16:57<3:36:43,  1.52it/s]
1|6163|Loss: 0.8209152817726135:  24%|██▍       | 6162/25880 [1:16:57<3:36:43,  1.52it/s]
1|6163|Loss: 0.8209152817726135:  24%|██▍       | 6163/25880 [1:16:57<3:24:05,  1.61it/s]
1|6164|Loss: 0.7374987602233887:  24%|██▍       | 6163/25880 [1:16:58<3:24:05,  1.61it/s]
1|6164|Loss: 0.7374987602233887:  24%|██▍       | 6164/25880 [1:16:58<3:24:00,  1.61it/s]
1|6165|Loss: 0.7572748064994812:  24%|██▍       | 6164/25880 [1:16:58<3:24:00,  1.61it/s]
1|6165|Loss: 0.7572748064994812:  24%|██▍       | 6165/25880 [1:16:59<3:24:06,  1.61it/s]
1|6166|Loss: 0.7568814754486084:  24%|██▍       | 6165/25880 [1:16:59<3:24:06,  1.61it/s]
1|6166|Loss: 0.7568814754486084:  24%|██▍       | 6166/25880 [1:16:59<3:33:09,  1.54it/s]
1|6167|Loss: 0.7794610261917114:  24%|██▍       | 6166/25880 [1:17:00<3:33:09,  1.54it/s]
1|6167|Loss: 0.7794610261917114:  24%|██▍       | 6167/25880 [1:17:00<3:41:38,  1.48it/s]
1|6168|Loss: 0.7349271774291992:  24%|██▍       | 6167/25880 [1:17:01<3:41:38,  1.48it/s]
1|6168|Loss: 0.7349271774291992:  24%|██▍       | 6168/25880 [1:17:01<3:46:49,  1.45it/s]
1|6169|Loss: 0.7802584171295166:  24%|██▍       | 6168/25880 [1:17:01<3:46:49,  1.45it/s]
1|6169|Loss: 0.7802584171295166:  24%|██▍       | 6169/25880 [1:17:02<3:51:22,  1.42it/s]
1|6170|Loss: 0.9300211668014526:  24%|██▍       | 6169/25880 [1:17:02<3:51:22,  1.42it/s]
1|6170|Loss: 0.9300211668014526:  24%|██▍       | 6170/25880 [1:17:02<3:55:43,  1.39it/s]
1|6171|Loss: 0.8093562126159668:  24%|██▍       | 6170/25880 [1:17:03<3:55:43,  1.39it/s]
1|6171|Loss: 0.8093562126159668:  24%|██▍       | 6171/25880 [1:17:03<4:03:45,  1.35it/s]
1|6172|Loss: 0.7893333435058594:  24%|██▍       | 6171/25880 [1:17:04<4:03:45,  1.35it/s]
1|6172|Loss: 0.7893333435058594:  24%|██▍       | 6172/25880 [1:17:04<4:24:16,  1.24it/s]
1|6173|Loss: 0.8548699617385864:  24%|██▍       | 6172/25880 [1:17:05<4:24:16,  1.24it/s]
1|6173|Loss: 0.8548699617385864:  24%|██▍       | 6173/25880 [1:17:05<4:23:16,  1.25it/s]
1|6174|Loss: 0.8267616033554077:  24%|██▍       | 6173/25880 [1:17:05<4:23:16,  1.25it/s]
1|6174|Loss: 0.8267616033554077:  24%|██▍       | 6174/25880 [1:17:06<4:16:47,  1.28it/s]
1|6175|Loss: 0.7968146800994873:  24%|██▍       | 6174/25880 [1:17:06<4:16:47,  1.28it/s]
1|6175|Loss: 0.7968146800994873:  24%|██▍       | 6175/25880 [1:17:06<4:12:03,  1.30it/s]
1|6176|Loss: 0.9633152484893799:  24%|██▍       | 6175/25880 [1:17:07<4:12:03,  1.30it/s]
1|6176|Loss: 0.9633152484893799:  24%|██▍       | 6176/25880 [1:17:07<4:05:30,  1.34it/s]
1|6177|Loss: 0.8385236263275146:  24%|██▍       | 6176/25880 [1:17:07<4:05:30,  1.34it/s]
1|6177|Loss: 0.8385236263275146:  24%|██▍       | 6177/25880 [1:17:08<3:54:17,  1.40it/s]
1|6178|Loss: 0.9909162521362305:  24%|██▍       | 6177/25880 [1:17:08<3:54:17,  1.40it/s]
1|6178|Loss: 0.9909162521362305:  24%|██▍       | 6178/25880 [1:17:09<4:07:24,  1.33it/s]
1|6179|Loss: 0.7234408855438232:  24%|██▍       | 6178/25880 [1:17:09<4:07:24,  1.33it/s]
1|6179|Loss: 0.7234408855438232:  24%|██▍       | 6179/25880 [1:17:09<3:59:26,  1.37it/s]
1|6180|Loss: 0.906647801399231:  24%|██▍       | 6179/25880 [1:17:10<3:59:26,  1.37it/s] 
1|6180|Loss: 0.906647801399231:  24%|██▍       | 6180/25880 [1:17:10<3:45:41,  1.45it/s]
1|6181|Loss: 0.857161283493042:  24%|██▍       | 6180/25880 [1:17:10<3:45:41,  1.45it/s]
1|6181|Loss: 0.857161283493042:  24%|██▍       | 6181/25880 [1:17:11<3:56:55,  1.39it/s]
1|6182|Loss: 0.8171828389167786:  24%|██▍       | 6181/25880 [1:17:11<3:56:55,  1.39it/s]
1|6182|Loss: 0.8171828389167786:  24%|██▍       | 6182/25880 [1:17:11<3:53:04,  1.41it/s]
1|6183|Loss: 0.8342761397361755:  24%|██▍       | 6182/25880 [1:17:12<3:53:04,  1.41it/s]
1|6183|Loss: 0.8342761397361755:  24%|██▍       | 6183/25880 [1:17:12<3:54:10,  1.40it/s]
1|6184|Loss: 0.8578087687492371:  24%|██▍       | 6183/25880 [1:17:12<3:54:10,  1.40it/s]
1|6184|Loss: 0.8578087687492371:  24%|██▍       | 6184/25880 [1:17:13<3:40:51,  1.49it/s]
1|6185|Loss: 0.9124925136566162:  24%|██▍       | 6184/25880 [1:17:13<3:40:51,  1.49it/s]
1|6185|Loss: 0.9124925136566162:  24%|██▍       | 6185/25880 [1:17:13<3:42:26,  1.48it/s]
1|6186|Loss: 0.8763360381126404:  24%|██▍       | 6185/25880 [1:17:14<3:42:26,  1.48it/s]
1|6186|Loss: 0.8763360381126404:  24%|██▍       | 6186/25880 [1:17:14<3:45:08,  1.46it/s]
1|6187|Loss: 1.0139480829238892:  24%|██▍       | 6186/25880 [1:17:14<3:45:08,  1.46it/s]
1|6187|Loss: 1.0139480829238892:  24%|██▍       | 6187/25880 [1:17:15<4:00:43,  1.36it/s]
1|6188|Loss: 0.9495280981063843:  24%|██▍       | 6187/25880 [1:17:15<4:00:43,  1.36it/s]
1|6188|Loss: 0.9495280981063843:  24%|██▍       | 6188/25880 [1:17:16<4:11:54,  1.30it/s]
1|6189|Loss: 0.7859724760055542:  24%|██▍       | 6188/25880 [1:17:16<4:11:54,  1.30it/s]
1|6189|Loss: 0.7859724760055542:  24%|██▍       | 6189/25880 [1:17:17<4:19:15,  1.27it/s]
1|6190|Loss: 0.8225550651550293:  24%|██▍       | 6189/25880 [1:17:17<4:19:15,  1.27it/s]
1|6190|Loss: 0.8225550651550293:  24%|██▍       | 6190/25880 [1:17:17<4:26:13,  1.23it/s]
1|6191|Loss: 0.8038159012794495:  24%|██▍       | 6190/25880 [1:17:18<4:26:13,  1.23it/s]
1|6191|Loss: 0.8038159012794495:  24%|██▍       | 6191/25880 [1:17:18<4:21:53,  1.25it/s]
1|6192|Loss: 0.7030987739562988:  24%|██▍       | 6191/25880 [1:17:19<4:21:53,  1.25it/s]
1|6192|Loss: 0.7030987739562988:  24%|██▍       | 6192/25880 [1:17:19<4:08:31,  1.32it/s]
1|6193|Loss: 0.7211283445358276:  24%|██▍       | 6192/25880 [1:17:19<4:08:31,  1.32it/s]
1|6193|Loss: 0.7211283445358276:  24%|██▍       | 6193/25880 [1:17:20<4:09:52,  1.31it/s]
1|6194|Loss: 0.8249428868293762:  24%|██▍       | 6193/25880 [1:17:20<4:09:52,  1.31it/s]
1|6194|Loss: 0.8249428868293762:  24%|██▍       | 6194/25880 [1:17:20<4:13:45,  1.29it/s]
1|6195|Loss: 0.7225983142852783:  24%|██▍       | 6194/25880 [1:17:21<4:13:45,  1.29it/s]
1|6195|Loss: 0.7225983142852783:  24%|██▍       | 6195/25880 [1:17:21<4:16:19,  1.28it/s]
1|6196|Loss: 0.8723569512367249:  24%|██▍       | 6195/25880 [1:17:22<4:16:19,  1.28it/s]
1|6196|Loss: 0.8723569512367249:  24%|██▍       | 6196/25880 [1:17:22<4:05:44,  1.34it/s]
1|6197|Loss: 0.7391002774238586:  24%|██▍       | 6196/25880 [1:17:22<4:05:44,  1.34it/s]
1|6197|Loss: 0.7391002774238586:  24%|██▍       | 6197/25880 [1:17:23<4:02:21,  1.35it/s]
1|6198|Loss: 0.7438275218009949:  24%|██▍       | 6197/25880 [1:17:23<4:02:21,  1.35it/s]
1|6198|Loss: 0.7438275218009949:  24%|██▍       | 6198/25880 [1:17:23<3:39:41,  1.49it/s]
1|6199|Loss: 0.7764282822608948:  24%|██▍       | 6198/25880 [1:17:23<3:39:41,  1.49it/s]
1|6199|Loss: 0.7764282822608948:  24%|██▍       | 6199/25880 [1:17:24<3:44:07,  1.46it/s]
1|6200|Loss: 0.8041958212852478:  24%|██▍       | 6199/25880 [1:17:24<3:44:07,  1.46it/s]
1|6200|Loss: 0.8041958212852478:  24%|██▍       | 6200/25880 [1:17:24<3:43:23,  1.47it/s]
1|6201|Loss: 0.9505356550216675:  24%|██▍       | 6200/25880 [1:17:25<3:43:23,  1.47it/s]
1|6201|Loss: 0.9505356550216675:  24%|██▍       | 6201/25880 [1:17:25<3:35:37,  1.52it/s]
1|6202|Loss: 0.9127922058105469:  24%|██▍       | 6201/25880 [1:17:25<3:35:37,  1.52it/s]
1|6202|Loss: 0.9127922058105469:  24%|██▍       | 6202/25880 [1:17:26<3:51:27,  1.42it/s]
1|6203|Loss: 0.8405717611312866:  24%|██▍       | 6202/25880 [1:17:26<3:51:27,  1.42it/s]
1|6203|Loss: 0.8405717611312866:  24%|██▍       | 6203/25880 [1:17:27<4:09:49,  1.31it/s]
1|6204|Loss: 0.9873940944671631:  24%|██▍       | 6203/25880 [1:17:27<4:09:49,  1.31it/s]
1|6204|Loss: 0.9873940944671631:  24%|██▍       | 6204/25880 [1:17:28<4:08:26,  1.32it/s]
1|6205|Loss: 0.7856293320655823:  24%|██▍       | 6204/25880 [1:17:28<4:08:26,  1.32it/s]
1|6205|Loss: 0.7856293320655823:  24%|██▍       | 6205/25880 [1:17:28<4:11:37,  1.30it/s]
1|6206|Loss: 0.8431393504142761:  24%|██▍       | 6205/25880 [1:17:29<4:11:37,  1.30it/s]
1|6206|Loss: 0.8431393504142761:  24%|██▍       | 6206/25880 [1:17:29<4:11:01,  1.31it/s]
1|6207|Loss: 0.8061071038246155:  24%|██▍       | 6206/25880 [1:17:29<4:11:01,  1.31it/s]
1|6207|Loss: 0.8061071038246155:  24%|██▍       | 6207/25880 [1:17:30<4:01:25,  1.36it/s]
1|6208|Loss: 0.896118700504303:  24%|██▍       | 6207/25880 [1:17:30<4:01:25,  1.36it/s] 
1|6208|Loss: 0.896118700504303:  24%|██▍       | 6208/25880 [1:17:30<3:59:06,  1.37it/s]
1|6209|Loss: 0.7824447154998779:  24%|██▍       | 6208/25880 [1:17:31<3:59:06,  1.37it/s]
1|6209|Loss: 0.7824447154998779:  24%|██▍       | 6209/25880 [1:17:31<4:00:05,  1.37it/s]
1|6210|Loss: 0.8937629461288452:  24%|██▍       | 6209/25880 [1:17:32<4:00:05,  1.37it/s]
1|6210|Loss: 0.8937629461288452:  24%|██▍       | 6210/25880 [1:17:32<4:01:49,  1.36it/s]
1|6211|Loss: 0.9441765546798706:  24%|██▍       | 6210/25880 [1:17:32<4:01:49,  1.36it/s]
1|6211|Loss: 0.9441765546798706:  24%|██▍       | 6211/25880 [1:17:33<3:59:29,  1.37it/s]
1|6212|Loss: 0.7453658580780029:  24%|██▍       | 6211/25880 [1:17:33<3:59:29,  1.37it/s]
1|6212|Loss: 0.7453658580780029:  24%|██▍       | 6212/25880 [1:17:33<3:40:51,  1.48it/s]
1|6213|Loss: 0.8990508913993835:  24%|██▍       | 6212/25880 [1:17:34<3:40:51,  1.48it/s]
1|6213|Loss: 0.8990508913993835:  24%|██▍       | 6213/25880 [1:17:34<3:47:51,  1.44it/s]
1|6214|Loss: 1.009813666343689:  24%|██▍       | 6213/25880 [1:17:34<3:47:51,  1.44it/s] 
1|6214|Loss: 1.009813666343689:  24%|██▍       | 6214/25880 [1:17:35<4:02:08,  1.35it/s]
1|6215|Loss: 0.8274574875831604:  24%|██▍       | 6214/25880 [1:17:35<4:02:08,  1.35it/s]
1|6215|Loss: 0.8274574875831604:  24%|██▍       | 6215/25880 [1:17:36<4:04:27,  1.34it/s]
1|6216|Loss: 0.7672308087348938:  24%|██▍       | 6215/25880 [1:17:36<4:04:27,  1.34it/s]
1|6216|Loss: 0.7672308087348938:  24%|██▍       | 6216/25880 [1:17:36<4:07:09,  1.33it/s]
1|6217|Loss: 0.9972231388092041:  24%|██▍       | 6216/25880 [1:17:37<4:07:09,  1.33it/s]
1|6217|Loss: 0.9972231388092041:  24%|██▍       | 6217/25880 [1:17:37<4:03:44,  1.34it/s]
1|6218|Loss: 0.8570263385772705:  24%|██▍       | 6217/25880 [1:17:37<4:03:44,  1.34it/s]
1|6218|Loss: 0.8570263385772705:  24%|██▍       | 6218/25880 [1:17:38<4:02:24,  1.35it/s]
1|6219|Loss: 0.9645755290985107:  24%|██▍       | 6218/25880 [1:17:38<4:02:24,  1.35it/s]
1|6219|Loss: 0.9645755290985107:  24%|██▍       | 6219/25880 [1:17:38<3:59:50,  1.37it/s]
1|6220|Loss: 0.8599177002906799:  24%|██▍       | 6219/25880 [1:17:39<3:59:50,  1.37it/s]
1|6220|Loss: 0.8599177002906799:  24%|██▍       | 6220/25880 [1:17:39<4:04:16,  1.34it/s]
1|6221|Loss: 0.838476300239563:  24%|██▍       | 6220/25880 [1:17:40<4:04:16,  1.34it/s] 
1|6221|Loss: 0.838476300239563:  24%|██▍       | 6221/25880 [1:17:40<4:08:08,  1.32it/s]
1|6222|Loss: 0.9247612953186035:  24%|██▍       | 6221/25880 [1:17:40<4:08:08,  1.32it/s]
1|6222|Loss: 0.9247612953186035:  24%|██▍       | 6222/25880 [1:17:41<4:12:02,  1.30it/s]
1|6223|Loss: 0.8415538668632507:  24%|██▍       | 6222/25880 [1:17:41<4:12:02,  1.30it/s]
1|6223|Loss: 0.8415538668632507:  24%|██▍       | 6223/25880 [1:17:42<4:10:58,  1.31it/s]
1|6224|Loss: 0.9661005735397339:  24%|██▍       | 6223/25880 [1:17:42<4:10:58,  1.31it/s]
1|6224|Loss: 0.9661005735397339:  24%|██▍       | 6224/25880 [1:17:42<4:07:52,  1.32it/s]
1|6225|Loss: 0.703794538974762:  24%|██▍       | 6224/25880 [1:17:43<4:07:52,  1.32it/s] 
1|6225|Loss: 0.703794538974762:  24%|██▍       | 6225/25880 [1:17:43<4:19:42,  1.26it/s]
1|6226|Loss: 0.7209053039550781:  24%|██▍       | 6225/25880 [1:17:44<4:19:42,  1.26it/s]
1|6226|Loss: 0.7209053039550781:  24%|██▍       | 6226/25880 [1:17:44<4:14:50,  1.29it/s]
1|6227|Loss: 0.8740739822387695:  24%|██▍       | 6226/25880 [1:17:44<4:14:50,  1.29it/s]
1|6227|Loss: 0.8740739822387695:  24%|██▍       | 6227/25880 [1:17:45<4:10:41,  1.31it/s]
1|6228|Loss: 0.8736566305160522:  24%|██▍       | 6227/25880 [1:17:45<4:10:41,  1.31it/s]
1|6228|Loss: 0.8736566305160522:  24%|██▍       | 6228/25880 [1:17:45<3:58:35,  1.37it/s]
1|6229|Loss: 0.8074341416358948:  24%|██▍       | 6228/25880 [1:17:46<3:58:35,  1.37it/s]
1|6229|Loss: 0.8074341416358948:  24%|██▍       | 6229/25880 [1:17:46<3:49:03,  1.43it/s]
1|6230|Loss: 0.7739386558532715:  24%|██▍       | 6229/25880 [1:17:46<3:49:03,  1.43it/s]
1|6230|Loss: 0.7739386558532715:  24%|██▍       | 6230/25880 [1:17:47<3:58:15,  1.37it/s]
1|6231|Loss: 0.8095480799674988:  24%|██▍       | 6230/25880 [1:17:47<3:58:15,  1.37it/s]
1|6231|Loss: 0.8095480799674988:  24%|██▍       | 6231/25880 [1:17:47<3:57:25,  1.38it/s]
1|6232|Loss: 0.8026851415634155:  24%|██▍       | 6231/25880 [1:17:48<3:57:25,  1.38it/s]
1|6232|Loss: 0.8026851415634155:  24%|██▍       | 6232/25880 [1:17:48<3:48:10,  1.44it/s]
1|6233|Loss: 0.8363499045372009:  24%|██▍       | 6232/25880 [1:17:49<3:48:10,  1.44it/s]
1|6233|Loss: 0.8363499045372009:  24%|██▍       | 6233/25880 [1:17:49<3:49:53,  1.42it/s]
1|6234|Loss: 0.779619574546814:  24%|██▍       | 6233/25880 [1:17:49<3:49:53,  1.42it/s] 
1|6234|Loss: 0.779619574546814:  24%|██▍       | 6234/25880 [1:17:49<3:44:37,  1.46it/s]
1|6235|Loss: 0.8905278444290161:  24%|██▍       | 6234/25880 [1:17:50<3:44:37,  1.46it/s]
1|6235|Loss: 0.8905278444290161:  24%|██▍       | 6235/25880 [1:17:50<3:55:47,  1.39it/s]
1|6236|Loss: 0.7657169699668884:  24%|██▍       | 6235/25880 [1:17:51<3:55:47,  1.39it/s]
1|6236|Loss: 0.7657169699668884:  24%|██▍       | 6236/25880 [1:17:51<4:07:38,  1.32it/s]
1|6237|Loss: 0.8159509897232056:  24%|██▍       | 6236/25880 [1:17:52<4:07:38,  1.32it/s]
1|6237|Loss: 0.8159509897232056:  24%|██▍       | 6237/25880 [1:17:52<4:04:39,  1.34it/s]
1|6238|Loss: 0.8339565992355347:  24%|██▍       | 6237/25880 [1:17:52<4:04:39,  1.34it/s]
1|6238|Loss: 0.8339565992355347:  24%|██▍       | 6238/25880 [1:17:53<3:59:31,  1.37it/s]
1|6239|Loss: 0.8269855976104736:  24%|██▍       | 6238/25880 [1:17:53<3:59:31,  1.37it/s]
1|6239|Loss: 0.8269855976104736:  24%|██▍       | 6239/25880 [1:17:53<3:58:38,  1.37it/s]
1|6240|Loss: 0.8337692618370056:  24%|██▍       | 6239/25880 [1:17:54<3:58:38,  1.37it/s]
1|6240|Loss: 0.8337692618370056:  24%|██▍       | 6240/25880 [1:17:54<4:09:23,  1.31it/s]
1|6241|Loss: 0.8326238989830017:  24%|██▍       | 6240/25880 [1:17:55<4:09:23,  1.31it/s]
1|6241|Loss: 0.8326238989830017:  24%|██▍       | 6241/25880 [1:17:55<4:07:01,  1.33it/s]
1|6242|Loss: 0.9373326301574707:  24%|██▍       | 6241/25880 [1:17:55<4:07:01,  1.33it/s]
1|6242|Loss: 0.9373326301574707:  24%|██▍       | 6242/25880 [1:17:55<3:52:18,  1.41it/s]
1|6243|Loss: 0.8225987553596497:  24%|██▍       | 6242/25880 [1:17:56<3:52:18,  1.41it/s]
1|6243|Loss: 0.8225987553596497:  24%|██▍       | 6243/25880 [1:17:56<3:44:04,  1.46it/s]
1|6244|Loss: 0.9814777374267578:  24%|██▍       | 6243/25880 [1:17:56<3:44:04,  1.46it/s]
1|6244|Loss: 0.9814777374267578:  24%|██▍       | 6244/25880 [1:17:57<3:39:50,  1.49it/s]
1|6245|Loss: 0.9752198457717896:  24%|██▍       | 6244/25880 [1:17:57<3:39:50,  1.49it/s]
1|6245|Loss: 0.9752198457717896:  24%|██▍       | 6245/25880 [1:17:57<3:37:10,  1.51it/s]
1|6246|Loss: 0.9556536078453064:  24%|██▍       | 6245/25880 [1:17:58<3:37:10,  1.51it/s]
1|6246|Loss: 0.9556536078453064:  24%|██▍       | 6246/25880 [1:17:58<3:26:06,  1.59it/s]
1|6247|Loss: 0.7255968451499939:  24%|██▍       | 6246/25880 [1:17:58<3:26:06,  1.59it/s]
1|6247|Loss: 0.7255968451499939:  24%|██▍       | 6247/25880 [1:17:58<3:14:19,  1.68it/s]
1|6248|Loss: 0.8538918495178223:  24%|██▍       | 6247/25880 [1:17:59<3:14:19,  1.68it/s]
1|6248|Loss: 0.8538918495178223:  24%|██▍       | 6248/25880 [1:17:59<3:24:38,  1.60it/s]
1|6249|Loss: 0.823854386806488:  24%|██▍       | 6248/25880 [1:18:00<3:24:38,  1.60it/s] 
1|6249|Loss: 0.823854386806488:  24%|██▍       | 6249/25880 [1:18:00<3:50:35,  1.42it/s]
1|6250|Loss: 0.9476826190948486:  24%|██▍       | 6249/25880 [1:18:00<3:50:35,  1.42it/s]
1|6250|Loss: 0.9476826190948486:  24%|██▍       | 6250/25880 [1:18:01<4:01:22,  1.36it/s]
1|6251|Loss: 0.8424152731895447:  24%|██▍       | 6250/25880 [1:18:01<4:01:22,  1.36it/s]
1|6251|Loss: 0.8424152731895447:  24%|██▍       | 6251/25880 [1:18:02<4:12:09,  1.30it/s]
1|6252|Loss: 0.8738386631011963:  24%|██▍       | 6251/25880 [1:18:02<4:12:09,  1.30it/s]
1|6252|Loss: 0.8738386631011963:  24%|██▍       | 6252/25880 [1:18:02<4:11:03,  1.30it/s]
1|6253|Loss: 0.8857125043869019:  24%|██▍       | 6252/25880 [1:18:03<4:11:03,  1.30it/s]
1|6253|Loss: 0.8857125043869019:  24%|██▍       | 6253/25880 [1:18:03<4:15:09,  1.28it/s]
1|6254|Loss: 0.8739171028137207:  24%|██▍       | 6253/25880 [1:18:04<4:15:09,  1.28it/s]
1|6254|Loss: 0.8739171028137207:  24%|██▍       | 6254/25880 [1:18:04<4:09:46,  1.31it/s]
1|6255|Loss: 0.9630297422409058:  24%|██▍       | 6254/25880 [1:18:04<4:09:46,  1.31it/s]
1|6255|Loss: 0.9630297422409058:  24%|██▍       | 6255/25880 [1:18:05<4:03:21,  1.34it/s]
1|6256|Loss: 0.9330876469612122:  24%|██▍       | 6255/25880 [1:18:05<4:03:21,  1.34it/s]
1|6256|Loss: 0.9330876469612122:  24%|██▍       | 6256/25880 [1:18:05<3:49:23,  1.43it/s]
1|6257|Loss: 0.8847935199737549:  24%|██▍       | 6256/25880 [1:18:06<3:49:23,  1.43it/s]
1|6257|Loss: 0.8847935199737549:  24%|██▍       | 6257/25880 [1:18:06<3:59:56,  1.36it/s]
1|6258|Loss: 1.0265703201293945:  24%|██▍       | 6257/25880 [1:18:07<3:59:56,  1.36it/s]
1|6258|Loss: 1.0265703201293945:  24%|██▍       | 6258/25880 [1:18:07<4:11:20,  1.30it/s]
1|6259|Loss: 0.6275126338005066:  24%|██▍       | 6258/25880 [1:18:07<4:11:20,  1.30it/s]
1|6259|Loss: 0.6275126338005066:  24%|██▍       | 6259/25880 [1:18:07<3:47:32,  1.44it/s]
1|6260|Loss: 0.8004340529441833:  24%|██▍       | 6259/25880 [1:18:08<3:47:32,  1.44it/s]
1|6260|Loss: 0.8004340529441833:  24%|██▍       | 6260/25880 [1:18:08<3:50:53,  1.42it/s]
1|6261|Loss: 0.8844298124313354:  24%|██▍       | 6260/25880 [1:18:09<3:50:53,  1.42it/s]
1|6261|Loss: 0.8844298124313354:  24%|██▍       | 6261/25880 [1:18:09<3:45:35,  1.45it/s]
1|6262|Loss: 0.8456855416297913:  24%|██▍       | 6261/25880 [1:18:09<3:45:35,  1.45it/s]
1|6262|Loss: 0.8456855416297913:  24%|██▍       | 6262/25880 [1:18:10<3:51:49,  1.41it/s]
1|6263|Loss: 0.7961998581886292:  24%|██▍       | 6262/25880 [1:18:10<3:51:49,  1.41it/s]
1|6263|Loss: 0.7961998581886292:  24%|██▍       | 6263/25880 [1:18:10<3:59:18,  1.37it/s]
1|6264|Loss: 0.8637971878051758:  24%|██▍       | 6263/25880 [1:18:11<3:59:18,  1.37it/s]
1|6264|Loss: 0.8637971878051758:  24%|██▍       | 6264/25880 [1:18:11<4:06:03,  1.33it/s]
1|6265|Loss: 0.7558202147483826:  24%|██▍       | 6264/25880 [1:18:12<4:06:03,  1.33it/s]
1|6265|Loss: 0.7558202147483826:  24%|██▍       | 6265/25880 [1:18:12<4:12:47,  1.29it/s]
1|6266|Loss: 0.8032654523849487:  24%|██▍       | 6265/25880 [1:18:12<4:12:47,  1.29it/s]
1|6266|Loss: 0.8032654523849487:  24%|██▍       | 6266/25880 [1:18:13<4:01:41,  1.35it/s]
1|6267|Loss: 0.8569228053092957:  24%|██▍       | 6266/25880 [1:18:13<4:01:41,  1.35it/s]
1|6267|Loss: 0.8569228053092957:  24%|██▍       | 6267/25880 [1:18:13<3:51:43,  1.41it/s]
1|6268|Loss: 0.7389037013053894:  24%|██▍       | 6267/25880 [1:18:14<3:51:43,  1.41it/s]
1|6268|Loss: 0.7389037013053894:  24%|██▍       | 6268/25880 [1:18:14<4:10:39,  1.30it/s]
1|6269|Loss: 0.8925045132637024:  24%|██▍       | 6268/25880 [1:18:15<4:10:39,  1.30it/s]
1|6269|Loss: 0.8925045132637024:  24%|██▍       | 6269/25880 [1:18:15<3:59:58,  1.36it/s]
1|6270|Loss: 0.918952465057373:  24%|██▍       | 6269/25880 [1:18:15<3:59:58,  1.36it/s] 
1|6270|Loss: 0.918952465057373:  24%|██▍       | 6270/25880 [1:18:16<4:07:58,  1.32it/s]
1|6271|Loss: 0.8354024887084961:  24%|██▍       | 6270/25880 [1:18:16<4:07:58,  1.32it/s]
1|6271|Loss: 0.8354024887084961:  24%|██▍       | 6271/25880 [1:18:16<4:06:25,  1.33it/s]
1|6272|Loss: 0.7319938540458679:  24%|██▍       | 6271/25880 [1:18:17<4:06:25,  1.33it/s]
1|6272|Loss: 0.7319938540458679:  24%|██▍       | 6272/25880 [1:18:17<4:01:24,  1.35it/s]
1|6273|Loss: 0.8297359347343445:  24%|██▍       | 6272/25880 [1:18:18<4:01:24,  1.35it/s]
1|6273|Loss: 0.8297359347343445:  24%|██▍       | 6273/25880 [1:18:18<4:14:28,  1.28it/s]
1|6274|Loss: 0.8335941433906555:  24%|██▍       | 6273/25880 [1:18:18<4:14:28,  1.28it/s]
1|6274|Loss: 0.8335941433906555:  24%|██▍       | 6274/25880 [1:18:19<4:13:25,  1.29it/s]
1|6275|Loss: 0.8853414058685303:  24%|██▍       | 6274/25880 [1:18:19<4:13:25,  1.29it/s]
1|6275|Loss: 0.8853414058685303:  24%|██▍       | 6275/25880 [1:18:19<4:01:54,  1.35it/s]
1|6276|Loss: 0.7716812491416931:  24%|██▍       | 6275/25880 [1:18:20<4:01:54,  1.35it/s]
1|6276|Loss: 0.7716812491416931:  24%|██▍       | 6276/25880 [1:18:20<4:19:42,  1.26it/s]
1|6277|Loss: 0.9960719347000122:  24%|██▍       | 6276/25880 [1:18:21<4:19:42,  1.26it/s]
1|6277|Loss: 0.9960719347000122:  24%|██▍       | 6277/25880 [1:18:21<4:07:46,  1.32it/s]
1|6278|Loss: 0.7957515716552734:  24%|██▍       | 6277/25880 [1:18:21<4:07:46,  1.32it/s]
1|6278|Loss: 0.7957515716552734:  24%|██▍       | 6278/25880 [1:18:22<4:03:25,  1.34it/s]
1|6279|Loss: 0.8344772458076477:  24%|██▍       | 6278/25880 [1:18:22<4:03:25,  1.34it/s]
1|6279|Loss: 0.8344772458076477:  24%|██▍       | 6279/25880 [1:18:23<4:08:45,  1.31it/s]
1|6280|Loss: 0.8523642420768738:  24%|██▍       | 6279/25880 [1:18:23<4:08:45,  1.31it/s]
1|6280|Loss: 0.8523642420768738:  24%|██▍       | 6280/25880 [1:18:23<4:16:36,  1.27it/s]
1|6281|Loss: 0.8296154141426086:  24%|██▍       | 6280/25880 [1:18:24<4:16:36,  1.27it/s]
1|6281|Loss: 0.8296154141426086:  24%|██▍       | 6281/25880 [1:18:24<4:14:24,  1.28it/s]
1|6282|Loss: 0.8401562571525574:  24%|██▍       | 6281/25880 [1:18:25<4:14:24,  1.28it/s]
1|6282|Loss: 0.8401562571525574:  24%|██▍       | 6282/25880 [1:18:25<4:14:26,  1.28it/s]
1|6283|Loss: 0.8090676665306091:  24%|██▍       | 6282/25880 [1:18:25<4:14:26,  1.28it/s]
1|6283|Loss: 0.8090676665306091:  24%|██▍       | 6283/25880 [1:18:26<4:02:24,  1.35it/s]
1|6284|Loss: 0.7772596478462219:  24%|██▍       | 6283/25880 [1:18:26<4:02:24,  1.35it/s]
1|6284|Loss: 0.7772596478462219:  24%|██▍       | 6284/25880 [1:18:26<3:58:52,  1.37it/s]
1|6285|Loss: 0.9541943073272705:  24%|██▍       | 6284/25880 [1:18:27<3:58:52,  1.37it/s]
1|6285|Loss: 0.9541943073272705:  24%|██▍       | 6285/25880 [1:18:27<4:05:54,  1.33it/s]
1|6286|Loss: 0.789223849773407:  24%|██▍       | 6285/25880 [1:18:27<4:05:54,  1.33it/s] 
1|6286|Loss: 0.789223849773407:  24%|██▍       | 6286/25880 [1:18:28<3:56:59,  1.38it/s]
1|6287|Loss: 0.6799842715263367:  24%|██▍       | 6286/25880 [1:18:28<3:56:59,  1.38it/s]
1|6287|Loss: 0.6799842715263367:  24%|██▍       | 6287/25880 [1:18:29<4:09:10,  1.31it/s]
1|6288|Loss: 0.7841088175773621:  24%|██▍       | 6287/25880 [1:18:29<4:09:10,  1.31it/s]
1|6288|Loss: 0.7841088175773621:  24%|██▍       | 6288/25880 [1:18:29<4:06:57,  1.32it/s]
1|6289|Loss: 0.8792768120765686:  24%|██▍       | 6288/25880 [1:18:30<4:06:57,  1.32it/s]
1|6289|Loss: 0.8792768120765686:  24%|██▍       | 6289/25880 [1:18:30<4:04:57,  1.33it/s]
1|6290|Loss: 0.8240863680839539:  24%|██▍       | 6289/25880 [1:18:30<4:04:57,  1.33it/s]
1|6290|Loss: 0.8240863680839539:  24%|██▍       | 6290/25880 [1:18:31<4:04:06,  1.34it/s]
1|6291|Loss: 0.8412544131278992:  24%|██▍       | 6290/25880 [1:18:31<4:04:06,  1.34it/s]
1|6291|Loss: 0.8412544131278992:  24%|██▍       | 6291/25880 [1:18:31<3:46:44,  1.44it/s]
1|6292|Loss: 0.9065524339675903:  24%|██▍       | 6291/25880 [1:18:32<3:46:44,  1.44it/s]
1|6292|Loss: 0.9065524339675903:  24%|██▍       | 6292/25880 [1:18:32<3:37:46,  1.50it/s]
1|6293|Loss: 0.824373722076416:  24%|██▍       | 6292/25880 [1:18:32<3:37:46,  1.50it/s] 
1|6293|Loss: 0.824373722076416:  24%|██▍       | 6293/25880 [1:18:33<3:33:23,  1.53it/s]
1|6294|Loss: 0.758430540561676:  24%|██▍       | 6293/25880 [1:18:33<3:33:23,  1.53it/s]
1|6294|Loss: 0.758430540561676:  24%|██▍       | 6294/25880 [1:18:33<3:51:21,  1.41it/s]
1|6295|Loss: 0.889529287815094:  24%|██▍       | 6294/25880 [1:18:34<3:51:21,  1.41it/s]
1|6295|Loss: 0.889529287815094:  24%|██▍       | 6295/25880 [1:18:34<3:57:34,  1.37it/s]
1|6296|Loss: 1.0449198484420776:  24%|██▍       | 6295/25880 [1:18:35<3:57:34,  1.37it/s]
1|6296|Loss: 1.0449198484420776:  24%|██▍       | 6296/25880 [1:18:35<3:59:32,  1.36it/s]
1|6297|Loss: 0.810661256313324:  24%|██▍       | 6296/25880 [1:18:35<3:59:32,  1.36it/s] 
1|6297|Loss: 0.810661256313324:  24%|██▍       | 6297/25880 [1:18:36<3:51:01,  1.41it/s]
1|6298|Loss: 0.8910636901855469:  24%|██▍       | 6297/25880 [1:18:36<3:51:01,  1.41it/s]
1|6298|Loss: 0.8910636901855469:  24%|██▍       | 6298/25880 [1:18:36<3:50:50,  1.41it/s]
1|6299|Loss: 0.7868140935897827:  24%|██▍       | 6298/25880 [1:18:37<3:50:50,  1.41it/s]
1|6299|Loss: 0.7868140935897827:  24%|██▍       | 6299/25880 [1:18:37<4:11:06,  1.30it/s]
1|6300|Loss: 0.8888809680938721:  24%|██▍       | 6299/25880 [1:18:38<4:11:06,  1.30it/s]
1|6300|Loss: 0.8888809680938721:  24%|██▍       | 6300/25880 [1:18:38<4:09:20,  1.31it/s]
1|6301|Loss: 0.9366660714149475:  24%|██▍       | 6300/25880 [1:18:38<4:09:20,  1.31it/s]
1|6301|Loss: 0.9366660714149475:  24%|██▍       | 6301/25880 [1:18:39<3:58:10,  1.37it/s]
1|6302|Loss: 0.7673539519309998:  24%|██▍       | 6301/25880 [1:18:39<3:58:10,  1.37it/s]
1|6302|Loss: 0.7673539519309998:  24%|██▍       | 6302/25880 [1:18:39<3:57:46,  1.37it/s]
1|6303|Loss: 0.8280784487724304:  24%|██▍       | 6302/25880 [1:18:40<3:57:46,  1.37it/s]
1|6303|Loss: 0.8280784487724304:  24%|██▍       | 6303/25880 [1:18:40<3:56:12,  1.38it/s]
1|6304|Loss: 0.8209217190742493:  24%|██▍       | 6303/25880 [1:18:40<3:56:12,  1.38it/s]
1|6304|Loss: 0.8209217190742493:  24%|██▍       | 6304/25880 [1:18:41<4:03:37,  1.34it/s]
1|6305|Loss: 0.9791914820671082:  24%|██▍       | 6304/25880 [1:18:41<4:03:37,  1.34it/s]
1|6305|Loss: 0.9791914820671082:  24%|██▍       | 6305/25880 [1:18:42<3:56:38,  1.38it/s]
1|6306|Loss: 0.9756824374198914:  24%|██▍       | 6305/25880 [1:18:42<3:56:38,  1.38it/s]
1|6306|Loss: 0.9756824374198914:  24%|██▍       | 6306/25880 [1:18:42<3:47:41,  1.43it/s]
1|6307|Loss: 0.7792938947677612:  24%|██▍       | 6306/25880 [1:18:43<3:47:41,  1.43it/s]
1|6307|Loss: 0.7792938947677612:  24%|██▍       | 6307/25880 [1:18:43<3:42:10,  1.47it/s]
1|6308|Loss: 0.9777234196662903:  24%|██▍       | 6307/25880 [1:18:43<3:42:10,  1.47it/s]
1|6308|Loss: 0.9777234196662903:  24%|██▍       | 6308/25880 [1:18:44<3:59:46,  1.36it/s]
1|6309|Loss: 0.9215371608734131:  24%|██▍       | 6308/25880 [1:18:44<3:59:46,  1.36it/s]
1|6309|Loss: 0.9215371608734131:  24%|██▍       | 6309/25880 [1:18:44<3:49:05,  1.42it/s]
1|6310|Loss: 0.6913737058639526:  24%|██▍       | 6309/25880 [1:18:45<3:49:05,  1.42it/s]
1|6310|Loss: 0.6913737058639526:  24%|██▍       | 6310/25880 [1:18:45<3:33:58,  1.52it/s]
1|6311|Loss: 0.9446293711662292:  24%|██▍       | 6310/25880 [1:18:45<3:33:58,  1.52it/s]
1|6311|Loss: 0.9446293711662292:  24%|██▍       | 6311/25880 [1:18:45<3:29:57,  1.55it/s]
1|6312|Loss: 0.8536821007728577:  24%|██▍       | 6311/25880 [1:18:46<3:29:57,  1.55it/s]
1|6312|Loss: 0.8536821007728577:  24%|██▍       | 6312/25880 [1:18:46<3:26:12,  1.58it/s]
1|6313|Loss: 0.8562394380569458:  24%|██▍       | 6312/25880 [1:18:46<3:26:12,  1.58it/s]
1|6313|Loss: 0.8562394380569458:  24%|██▍       | 6313/25880 [1:18:47<3:34:17,  1.52it/s]
1|6314|Loss: 0.8450648188591003:  24%|██▍       | 6313/25880 [1:18:47<3:34:17,  1.52it/s]
1|6314|Loss: 0.8450648188591003:  24%|██▍       | 6314/25880 [1:18:48<3:51:45,  1.41it/s]
1|6315|Loss: 0.9449589252471924:  24%|██▍       | 6314/25880 [1:18:48<3:51:45,  1.41it/s]
1|6315|Loss: 0.9449589252471924:  24%|██▍       | 6315/25880 [1:18:49<4:08:26,  1.31it/s]
1|6316|Loss: 0.8301880955696106:  24%|██▍       | 6315/25880 [1:18:49<4:08:26,  1.31it/s]
1|6316|Loss: 0.8301880955696106:  24%|██▍       | 6316/25880 [1:18:49<4:09:58,  1.30it/s]
1|6317|Loss: 0.8069024085998535:  24%|██▍       | 6316/25880 [1:18:50<4:09:58,  1.30it/s]
1|6317|Loss: 0.8069024085998535:  24%|██▍       | 6317/25880 [1:18:50<4:27:11,  1.22it/s]
1|6318|Loss: 0.8576487302780151:  24%|██▍       | 6317/25880 [1:18:51<4:27:11,  1.22it/s]
1|6318|Loss: 0.8576487302780151:  24%|██▍       | 6318/25880 [1:18:51<4:37:11,  1.18it/s]
1|6319|Loss: 0.9091746211051941:  24%|██▍       | 6318/25880 [1:18:52<4:37:11,  1.18it/s]
1|6319|Loss: 0.9091746211051941:  24%|██▍       | 6319/25880 [1:18:52<4:18:45,  1.26it/s]
1|6320|Loss: 0.8761740326881409:  24%|██▍       | 6319/25880 [1:18:52<4:18:45,  1.26it/s]
1|6320|Loss: 0.8761740326881409:  24%|██▍       | 6320/25880 [1:18:53<4:09:09,  1.31it/s]
1|6321|Loss: 0.9055343866348267:  24%|██▍       | 6320/25880 [1:18:53<4:09:09,  1.31it/s]
1|6321|Loss: 0.9055343866348267:  24%|██▍       | 6321/25880 [1:18:53<4:03:06,  1.34it/s]
1|6322|Loss: 0.8400543332099915:  24%|██▍       | 6321/25880 [1:18:54<4:03:06,  1.34it/s]
1|6322|Loss: 0.8400543332099915:  24%|██▍       | 6322/25880 [1:18:54<4:07:46,  1.32it/s]
1|6323|Loss: 0.9448830485343933:  24%|██▍       | 6322/25880 [1:18:54<4:07:46,  1.32it/s]
1|6323|Loss: 0.9448830485343933:  24%|██▍       | 6323/25880 [1:18:55<4:06:34,  1.32it/s]
1|6324|Loss: 0.7899022698402405:  24%|██▍       | 6323/25880 [1:18:55<4:06:34,  1.32it/s]
1|6324|Loss: 0.7899022698402405:  24%|██▍       | 6324/25880 [1:18:55<4:04:05,  1.34it/s]
1|6325|Loss: 0.712721586227417:  24%|██▍       | 6324/25880 [1:18:56<4:04:05,  1.34it/s] 
1|6325|Loss: 0.712721586227417:  24%|██▍       | 6325/25880 [1:18:56<4:11:12,  1.30it/s]
1|6326|Loss: 0.8530274629592896:  24%|██▍       | 6325/25880 [1:18:57<4:11:12,  1.30it/s]
1|6326|Loss: 0.8530274629592896:  24%|██▍       | 6326/25880 [1:18:57<4:07:56,  1.31it/s]
1|6327|Loss: 0.8000640869140625:  24%|██▍       | 6326/25880 [1:18:57<4:07:56,  1.31it/s]
1|6327|Loss: 0.8000640869140625:  24%|██▍       | 6327/25880 [1:18:58<3:57:16,  1.37it/s]
1|6328|Loss: 0.8796620965003967:  24%|██▍       | 6327/25880 [1:18:58<3:57:16,  1.37it/s]
1|6328|Loss: 0.8796620965003967:  24%|██▍       | 6328/25880 [1:18:58<3:55:16,  1.39it/s]
1|6329|Loss: 0.9304028153419495:  24%|██▍       | 6328/25880 [1:18:59<3:55:16,  1.39it/s]
1|6329|Loss: 0.9304028153419495:  24%|██▍       | 6329/25880 [1:18:59<3:48:42,  1.42it/s]
1|6330|Loss: 0.9460756778717041:  24%|██▍       | 6329/25880 [1:18:59<3:48:42,  1.42it/s]
1|6330|Loss: 0.9460756778717041:  24%|██▍       | 6330/25880 [1:19:00<3:57:35,  1.37it/s]
1|6331|Loss: 0.8245316743850708:  24%|██▍       | 6330/25880 [1:19:00<3:57:35,  1.37it/s]
1|6331|Loss: 0.8245316743850708:  24%|██▍       | 6331/25880 [1:19:01<4:04:23,  1.33it/s]
1|6332|Loss: 0.9033874273300171:  24%|██▍       | 6331/25880 [1:19:01<4:04:23,  1.33it/s]
1|6332|Loss: 0.9033874273300171:  24%|██▍       | 6332/25880 [1:19:01<4:04:12,  1.33it/s]
1|6333|Loss: 0.8522273898124695:  24%|██▍       | 6332/25880 [1:19:02<4:04:12,  1.33it/s]
1|6333|Loss: 0.8522273898124695:  24%|██▍       | 6333/25880 [1:19:02<3:59:50,  1.36it/s]
1|6334|Loss: 0.9037112593650818:  24%|██▍       | 6333/25880 [1:19:02<3:59:50,  1.36it/s]
1|6334|Loss: 0.9037112593650818:  24%|██▍       | 6334/25880 [1:19:03<3:49:27,  1.42it/s]
1|6335|Loss: 0.7590490579605103:  24%|██▍       | 6334/25880 [1:19:03<3:49:27,  1.42it/s]
1|6335|Loss: 0.7590490579605103:  24%|██▍       | 6335/25880 [1:19:03<3:40:34,  1.48it/s]
1|6336|Loss: 0.8667106032371521:  24%|██▍       | 6335/25880 [1:19:04<3:40:34,  1.48it/s]
1|6336|Loss: 0.8667106032371521:  24%|██▍       | 6336/25880 [1:19:04<3:58:04,  1.37it/s]
1|6337|Loss: 0.8945429921150208:  24%|██▍       | 6336/25880 [1:19:05<3:58:04,  1.37it/s]
1|6337|Loss: 0.8945429921150208:  24%|██▍       | 6337/25880 [1:19:05<3:54:35,  1.39it/s]
1|6338|Loss: 0.8004642724990845:  24%|██▍       | 6337/25880 [1:19:05<3:54:35,  1.39it/s]
1|6338|Loss: 0.8004642724990845:  24%|██▍       | 6338/25880 [1:19:06<4:01:37,  1.35it/s]
1|6339|Loss: 0.860941469669342:  24%|██▍       | 6338/25880 [1:19:06<4:01:37,  1.35it/s] 
1|6339|Loss: 0.860941469669342:  24%|██▍       | 6339/25880 [1:19:06<4:00:07,  1.36it/s]
1|6340|Loss: 0.9045668244361877:  24%|██▍       | 6339/25880 [1:19:07<4:00:07,  1.36it/s]
1|6340|Loss: 0.9045668244361877:  24%|██▍       | 6340/25880 [1:19:07<3:47:58,  1.43it/s]
1|6341|Loss: 0.8825392127037048:  24%|██▍       | 6340/25880 [1:19:07<3:47:58,  1.43it/s]
1|6341|Loss: 0.8825392127037048:  25%|██▍       | 6341/25880 [1:19:08<3:47:03,  1.43it/s]
1|6342|Loss: 0.8001757264137268:  25%|██▍       | 6341/25880 [1:19:08<3:47:03,  1.43it/s]
1|6342|Loss: 0.8001757264137268:  25%|██▍       | 6342/25880 [1:19:09<4:01:12,  1.35it/s]
1|6343|Loss: 0.8465607166290283:  25%|██▍       | 6342/25880 [1:19:09<4:01:12,  1.35it/s]
1|6343|Loss: 0.8465607166290283:  25%|██▍       | 6343/25880 [1:19:09<4:01:04,  1.35it/s]
1|6344|Loss: 0.8090205788612366:  25%|██▍       | 6343/25880 [1:19:10<4:01:04,  1.35it/s]
1|6344|Loss: 0.8090205788612366:  25%|██▍       | 6344/25880 [1:19:10<4:06:37,  1.32it/s]
1|6345|Loss: 0.9325515627861023:  25%|██▍       | 6344/25880 [1:19:11<4:06:37,  1.32it/s]
1|6345|Loss: 0.9325515627861023:  25%|██▍       | 6345/25880 [1:19:11<4:07:22,  1.32it/s]
1|6346|Loss: 0.7394139170646667:  25%|██▍       | 6345/25880 [1:19:11<4:07:22,  1.32it/s]
1|6346|Loss: 0.7394139170646667:  25%|██▍       | 6346/25880 [1:19:11<3:43:05,  1.46it/s]
1|6347|Loss: 0.9180935621261597:  25%|██▍       | 6346/25880 [1:19:12<3:43:05,  1.46it/s]
1|6347|Loss: 0.9180935621261597:  25%|██▍       | 6347/25880 [1:19:12<3:39:04,  1.49it/s]
1|6348|Loss: 0.8523223996162415:  25%|██▍       | 6347/25880 [1:19:12<3:39:04,  1.49it/s]
1|6348|Loss: 0.8523223996162415:  25%|██▍       | 6348/25880 [1:19:13<3:44:40,  1.45it/s]
1|6349|Loss: 0.8736752867698669:  25%|██▍       | 6348/25880 [1:19:13<3:44:40,  1.45it/s]
1|6349|Loss: 0.8736752867698669:  25%|██▍       | 6349/25880 [1:19:14<3:58:42,  1.36it/s]
1|6350|Loss: 0.9345701932907104:  25%|██▍       | 6349/25880 [1:19:14<3:58:42,  1.36it/s]
1|6350|Loss: 0.9345701932907104:  25%|██▍       | 6350/25880 [1:19:14<4:01:16,  1.35it/s]
1|6351|Loss: 0.933768093585968:  25%|██▍       | 6350/25880 [1:19:15<4:01:16,  1.35it/s] 
1|6351|Loss: 0.933768093585968:  25%|██▍       | 6351/25880 [1:19:15<4:11:52,  1.29it/s]
1|6352|Loss: 0.9167003035545349:  25%|██▍       | 6351/25880 [1:19:16<4:11:52,  1.29it/s]
1|6352|Loss: 0.9167003035545349:  25%|██▍       | 6352/25880 [1:19:16<3:49:33,  1.42it/s]
1|6353|Loss: 0.8066989183425903:  25%|██▍       | 6352/25880 [1:19:16<3:49:33,  1.42it/s]
1|6353|Loss: 0.8066989183425903:  25%|██▍       | 6353/25880 [1:19:16<3:37:02,  1.50it/s]
1|6354|Loss: 0.7623022794723511:  25%|██▍       | 6353/25880 [1:19:17<3:37:02,  1.50it/s]
1|6354|Loss: 0.7623022794723511:  25%|██▍       | 6354/25880 [1:19:17<3:47:25,  1.43it/s]
1|6355|Loss: 0.8662787079811096:  25%|██▍       | 6354/25880 [1:19:17<3:47:25,  1.43it/s]
1|6355|Loss: 0.8662787079811096:  25%|██▍       | 6355/25880 [1:19:18<3:38:32,  1.49it/s]
1|6356|Loss: 0.7279108166694641:  25%|██▍       | 6355/25880 [1:19:18<3:38:32,  1.49it/s]
1|6356|Loss: 0.7279108166694641:  25%|██▍       | 6356/25880 [1:19:18<3:29:07,  1.56it/s]
1|6357|Loss: 0.8752115368843079:  25%|██▍       | 6356/25880 [1:19:19<3:29:07,  1.56it/s]
1|6357|Loss: 0.8752115368843079:  25%|██▍       | 6357/25880 [1:19:19<3:56:03,  1.38it/s]
1|6358|Loss: 0.8098982572555542:  25%|██▍       | 6357/25880 [1:19:20<3:56:03,  1.38it/s]
1|6358|Loss: 0.8098982572555542:  25%|██▍       | 6358/25880 [1:19:20<4:08:43,  1.31it/s]
1|6359|Loss: 0.8768511414527893:  25%|██▍       | 6358/25880 [1:19:20<4:08:43,  1.31it/s]
1|6359|Loss: 0.8768511414527893:  25%|██▍       | 6359/25880 [1:19:21<3:57:54,  1.37it/s]
1|6360|Loss: 0.8779774308204651:  25%|██▍       | 6359/25880 [1:19:21<3:57:54,  1.37it/s]
1|6360|Loss: 0.8779774308204651:  25%|██▍       | 6360/25880 [1:19:21<3:55:24,  1.38it/s]
1|6361|Loss: 0.8153747320175171:  25%|██▍       | 6360/25880 [1:19:22<3:55:24,  1.38it/s]
1|6361|Loss: 0.8153747320175171:  25%|██▍       | 6361/25880 [1:19:22<3:56:18,  1.38it/s]
1|6362|Loss: 1.0488735437393188:  25%|██▍       | 6361/25880 [1:19:23<3:56:18,  1.38it/s]
1|6362|Loss: 1.0488735437393188:  25%|██▍       | 6362/25880 [1:19:23<3:49:45,  1.42it/s]
1|6363|Loss: 0.8782501220703125:  25%|██▍       | 6362/25880 [1:19:23<3:49:45,  1.42it/s]
1|6363|Loss: 0.8782501220703125:  25%|██▍       | 6363/25880 [1:19:23<3:48:46,  1.42it/s]
1|6364|Loss: 0.7865526080131531:  25%|██▍       | 6363/25880 [1:19:24<3:48:46,  1.42it/s]
1|6364|Loss: 0.7865526080131531:  25%|██▍       | 6364/25880 [1:19:24<3:48:51,  1.42it/s]
1|6365|Loss: 0.8643402457237244:  25%|██▍       | 6364/25880 [1:19:25<3:48:51,  1.42it/s]
1|6365|Loss: 0.8643402457237244:  25%|██▍       | 6365/25880 [1:19:25<3:49:02,  1.42it/s]
1|6366|Loss: 0.774813175201416:  25%|██▍       | 6365/25880 [1:19:25<3:49:02,  1.42it/s] 
1|6366|Loss: 0.774813175201416:  25%|██▍       | 6366/25880 [1:19:26<3:43:57,  1.45it/s]
1|6367|Loss: 0.8875971436500549:  25%|██▍       | 6366/25880 [1:19:26<3:43:57,  1.45it/s]
1|6367|Loss: 0.8875971436500549:  25%|██▍       | 6367/25880 [1:19:26<3:26:53,  1.57it/s]
1|6368|Loss: 0.9738800525665283:  25%|██▍       | 6367/25880 [1:19:26<3:26:53,  1.57it/s]
1|6368|Loss: 0.9738800525665283:  25%|██▍       | 6368/25880 [1:19:27<3:30:21,  1.55it/s]
1|6369|Loss: 0.8416304588317871:  25%|██▍       | 6368/25880 [1:19:27<3:30:21,  1.55it/s]
1|6369|Loss: 0.8416304588317871:  25%|██▍       | 6369/25880 [1:19:27<3:31:20,  1.54it/s]
1|6370|Loss: 0.8066751956939697:  25%|██▍       | 6369/25880 [1:19:28<3:31:20,  1.54it/s]
1|6370|Loss: 0.8066751956939697:  25%|██▍       | 6370/25880 [1:19:28<3:42:43,  1.46it/s]
1|6371|Loss: 0.833392322063446:  25%|██▍       | 6370/25880 [1:19:29<3:42:43,  1.46it/s] 
1|6371|Loss: 0.833392322063446:  25%|██▍       | 6371/25880 [1:19:29<3:49:55,  1.41it/s]
1|6372|Loss: 0.9626284837722778:  25%|██▍       | 6371/25880 [1:19:29<3:49:55,  1.41it/s]
1|6372|Loss: 0.9626284837722778:  25%|██▍       | 6372/25880 [1:19:30<3:51:25,  1.40it/s]
1|6373|Loss: 0.8082519769668579:  25%|██▍       | 6372/25880 [1:19:30<3:51:25,  1.40it/s]
1|6373|Loss: 0.8082519769668579:  25%|██▍       | 6373/25880 [1:19:30<3:33:27,  1.52it/s]
1|6374|Loss: 1.0694166421890259:  25%|██▍       | 6373/25880 [1:19:31<3:33:27,  1.52it/s]
1|6374|Loss: 1.0694166421890259:  25%|██▍       | 6374/25880 [1:19:31<3:33:49,  1.52it/s]
1|6375|Loss: 0.8161482810974121:  25%|██▍       | 6374/25880 [1:19:31<3:33:49,  1.52it/s]
1|6375|Loss: 0.8161482810974121:  25%|██▍       | 6375/25880 [1:19:32<3:38:34,  1.49it/s]
1|6376|Loss: 0.7836952805519104:  25%|██▍       | 6375/25880 [1:19:32<3:38:34,  1.49it/s]
1|6376|Loss: 0.7836952805519104:  25%|██▍       | 6376/25880 [1:19:32<3:41:28,  1.47it/s]
1|6377|Loss: 0.8171142339706421:  25%|██▍       | 6376/25880 [1:19:33<3:41:28,  1.47it/s]
1|6377|Loss: 0.8171142339706421:  25%|██▍       | 6377/25880 [1:19:33<3:43:07,  1.46it/s]
1|6378|Loss: 0.8095618486404419:  25%|██▍       | 6377/25880 [1:19:33<3:43:07,  1.46it/s]
1|6378|Loss: 0.8095618486404419:  25%|██▍       | 6378/25880 [1:19:34<3:39:14,  1.48it/s]
1|6379|Loss: 0.8743314743041992:  25%|██▍       | 6378/25880 [1:19:34<3:39:14,  1.48it/s]
1|6379|Loss: 0.8743314743041992:  25%|██▍       | 6379/25880 [1:19:34<3:21:10,  1.62it/s]
1|6380|Loss: 0.8994455337524414:  25%|██▍       | 6379/25880 [1:19:34<3:21:10,  1.62it/s]
1|6380|Loss: 0.8994455337524414:  25%|██▍       | 6380/25880 [1:19:35<3:24:04,  1.59it/s]
1|6381|Loss: 0.8479329943656921:  25%|██▍       | 6380/25880 [1:19:35<3:24:04,  1.59it/s]
1|6381|Loss: 0.8479329943656921:  25%|██▍       | 6381/25880 [1:19:36<3:48:03,  1.42it/s]
1|6382|Loss: 0.8978970050811768:  25%|██▍       | 6381/25880 [1:19:36<3:48:03,  1.42it/s]
1|6382|Loss: 0.8978970050811768:  25%|██▍       | 6382/25880 [1:19:36<3:43:43,  1.45it/s]
1|6383|Loss: 0.9541653394699097:  25%|██▍       | 6382/25880 [1:19:37<3:43:43,  1.45it/s]
1|6383|Loss: 0.9541653394699097:  25%|██▍       | 6383/25880 [1:19:37<3:27:09,  1.57it/s]
1|6384|Loss: 0.7489397525787354:  25%|██▍       | 6383/25880 [1:19:37<3:27:09,  1.57it/s]
1|6384|Loss: 0.7489397525787354:  25%|██▍       | 6384/25880 [1:19:38<3:40:11,  1.48it/s]
1|6385|Loss: 0.8478408455848694:  25%|██▍       | 6384/25880 [1:19:38<3:40:11,  1.48it/s]
1|6385|Loss: 0.8478408455848694:  25%|██▍       | 6385/25880 [1:19:38<3:58:21,  1.36it/s]
1|6386|Loss: 0.8849467039108276:  25%|██▍       | 6385/25880 [1:19:39<3:58:21,  1.36it/s]
1|6386|Loss: 0.8849467039108276:  25%|██▍       | 6386/25880 [1:19:39<3:55:18,  1.38it/s]
1|6387|Loss: 0.8519136309623718:  25%|██▍       | 6386/25880 [1:19:39<3:55:18,  1.38it/s]
1|6387|Loss: 0.8519136309623718:  25%|██▍       | 6387/25880 [1:19:40<3:37:34,  1.49it/s]
1|6388|Loss: 0.8112906813621521:  25%|██▍       | 6387/25880 [1:19:40<3:37:34,  1.49it/s]
1|6388|Loss: 0.8112906813621521:  25%|██▍       | 6388/25880 [1:19:40<3:31:37,  1.54it/s]
1|6389|Loss: 0.8128573894500732:  25%|██▍       | 6388/25880 [1:19:41<3:31:37,  1.54it/s]
1|6389|Loss: 0.8128573894500732:  25%|██▍       | 6389/25880 [1:19:41<3:25:37,  1.58it/s]
1|6390|Loss: 0.806100606918335:  25%|██▍       | 6389/25880 [1:19:41<3:25:37,  1.58it/s] 
1|6390|Loss: 0.806100606918335:  25%|██▍       | 6390/25880 [1:19:41<3:24:37,  1.59it/s]
1|6391|Loss: 1.0348082780838013:  25%|██▍       | 6390/25880 [1:19:42<3:24:37,  1.59it/s]
1|6391|Loss: 1.0348082780838013:  25%|██▍       | 6391/25880 [1:19:42<3:25:45,  1.58it/s]
1|6392|Loss: 0.783242404460907:  25%|██▍       | 6391/25880 [1:19:42<3:25:45,  1.58it/s] 
1|6392|Loss: 0.783242404460907:  25%|██▍       | 6392/25880 [1:19:43<3:31:12,  1.54it/s]
1|6393|Loss: 0.9795066118240356:  25%|██▍       | 6392/25880 [1:19:43<3:31:12,  1.54it/s]
1|6393|Loss: 0.9795066118240356:  25%|██▍       | 6393/25880 [1:19:44<3:43:39,  1.45it/s]
1|6394|Loss: 0.8985008001327515:  25%|██▍       | 6393/25880 [1:19:44<3:43:39,  1.45it/s]
1|6394|Loss: 0.8985008001327515:  25%|██▍       | 6394/25880 [1:19:44<3:50:53,  1.41it/s]
1|6395|Loss: 0.817859947681427:  25%|██▍       | 6394/25880 [1:19:45<3:50:53,  1.41it/s] 
1|6395|Loss: 0.817859947681427:  25%|██▍       | 6395/25880 [1:19:45<3:46:15,  1.44it/s]
1|6396|Loss: 0.8524550795555115:  25%|██▍       | 6395/25880 [1:19:45<3:46:15,  1.44it/s]
1|6396|Loss: 0.8524550795555115:  25%|██▍       | 6396/25880 [1:19:46<3:45:38,  1.44it/s]
1|6397|Loss: 0.823620617389679:  25%|██▍       | 6396/25880 [1:19:46<3:45:38,  1.44it/s] 
1|6397|Loss: 0.823620617389679:  25%|██��       | 6397/25880 [1:19:46<3:52:35,  1.40it/s]
1|6398|Loss: 0.8302953839302063:  25%|██▍       | 6397/25880 [1:19:47<3:52:35,  1.40it/s]
1|6398|Loss: 0.8302953839302063:  25%|██▍       | 6398/25880 [1:19:47<3:55:56,  1.38it/s]
1|6399|Loss: 0.8129214644432068:  25%|██▍       | 6398/25880 [1:19:48<3:55:56,  1.38it/s]
1|6399|Loss: 0.8129214644432068:  25%|██▍       | 6399/25880 [1:19:48<3:38:47,  1.48it/s]
1|6400|Loss: 0.8338476419448853:  25%|██▍       | 6399/25880 [1:19:48<3:38:47,  1.48it/s]
1|6400|Loss: 0.8338476419448853:  25%|██▍       | 6400/25880 [1:19:49<3:45:42,  1.44it/s]
1|6401|Loss: 0.6749011278152466:  25%|██▍       | 6400/25880 [1:19:49<3:45:42,  1.44it/s]
1|6401|Loss: 0.6749011278152466:  25%|██▍       | 6401/25880 [1:19:49<3:33:17,  1.52it/s]
1|6402|Loss: 0.9152346253395081:  25%|██▍       | 6401/25880 [1:19:49<3:33:17,  1.52it/s]
1|6402|Loss: 0.9152346253395081:  25%|██▍       | 6402/25880 [1:19:50<3:37:39,  1.49it/s]
1|6403|Loss: 0.7373159527778625:  25%|██▍       | 6402/25880 [1:19:50<3:37:39,  1.49it/s]
1|6403|Loss: 0.7373159527778625:  25%|██▍       | 6403/25880 [1:19:51<3:44:10,  1.45it/s]
1|6404|Loss: 0.8312860727310181:  25%|██▍       | 6403/25880 [1:19:51<3:44:10,  1.45it/s]
1|6404|Loss: 0.8312860727310181:  25%|██▍       | 6404/25880 [1:19:51<3:49:18,  1.42it/s]
1|6405|Loss: 0.974984347820282:  25%|██▍       | 6404/25880 [1:19:52<3:49:18,  1.42it/s] 
1|6405|Loss: 0.974984347820282:  25%|██▍       | 6405/25880 [1:19:52<3:53:49,  1.39it/s]
1|6406|Loss: 0.9413955807685852:  25%|██▍       | 6405/25880 [1:19:52<3:53:49,  1.39it/s]
1|6406|Loss: 0.9413955807685852:  25%|██▍       | 6406/25880 [1:19:53<3:55:49,  1.38it/s]
1|6407|Loss: 0.8971850872039795:  25%|██▍       | 6406/25880 [1:19:53<3:55:49,  1.38it/s]
1|6407|Loss: 0.8971850872039795:  25%|██▍       | 6407/25880 [1:19:54<4:00:11,  1.35it/s]
1|6408|Loss: 0.8183467984199524:  25%|██▍       | 6407/25880 [1:19:54<4:00:11,  1.35it/s]
1|6408|Loss: 0.8183467984199524:  25%|██▍       | 6408/25880 [1:19:54<3:46:52,  1.43it/s]
1|6409|Loss: 0.8295333385467529:  25%|██▍       | 6408/25880 [1:19:54<3:46:52,  1.43it/s]
1|6409|Loss: 0.8295333385467529:  25%|██▍       | 6409/25880 [1:19:55<3:38:32,  1.48it/s]
1|6410|Loss: 0.8027368783950806:  25%|██▍       | 6409/25880 [1:19:55<3:38:32,  1.48it/s]
1|6410|Loss: 0.8027368783950806:  25%|██▍       | 6410/25880 [1:19:56<3:46:37,  1.43it/s]
1|6411|Loss: 0.898094892501831:  25%|██▍       | 6410/25880 [1:19:56<3:46:37,  1.43it/s] 
1|6411|Loss: 0.898094892501831:  25%|██▍       | 6411/25880 [1:19:56<3:51:59,  1.40it/s]
1|6412|Loss: 0.8004534244537354:  25%|██▍       | 6411/25880 [1:19:57<3:51:59,  1.40it/s]
1|6412|Loss: 0.8004534244537354:  25%|██▍       | 6412/25880 [1:19:57<3:35:23,  1.51it/s]
1|6413|Loss: 0.7183694243431091:  25%|██▍       | 6412/25880 [1:19:57<3:35:23,  1.51it/s]
1|6413|Loss: 0.7183694243431091:  25%|██▍       | 6413/25880 [1:19:58<3:42:42,  1.46it/s]
1|6414|Loss: 0.8779524564743042:  25%|██▍       | 6413/25880 [1:19:58<3:42:42,  1.46it/s]
1|6414|Loss: 0.8779524564743042:  25%|██▍       | 6414/25880 [1:19:58<3:41:24,  1.47it/s]
1|6415|Loss: 0.9682098031044006:  25%|██▍       | 6414/25880 [1:19:59<3:41:24,  1.47it/s]
1|6415|Loss: 0.9682098031044006:  25%|██▍       | 6415/25880 [1:19:59<3:44:45,  1.44it/s]
1|6416|Loss: 0.8035811185836792:  25%|██▍       | 6415/25880 [1:19:59<3:44:45,  1.44it/s]
1|6416|Loss: 0.8035811185836792:  25%|██▍       | 6416/25880 [1:20:00<3:46:39,  1.43it/s]
1|6417|Loss: 0.6532202959060669:  25%|██▍       | 6416/25880 [1:20:00<3:46:39,  1.43it/s]
1|6417|Loss: 0.6532202959060669:  25%|██▍       | 6417/25880 [1:20:00<3:27:17,  1.56it/s]
1|6418|Loss: 0.7986411452293396:  25%|██▍       | 6417/25880 [1:20:01<3:27:17,  1.56it/s]
1|6418|Loss: 0.7986411452293396:  25%|██▍       | 6418/25880 [1:20:01<3:36:08,  1.50it/s]
1|6419|Loss: 0.8563422560691833:  25%|██▍       | 6418/25880 [1:20:01<3:36:08,  1.50it/s]
1|6419|Loss: 0.8563422560691833:  25%|██▍       | 6419/25880 [1:20:02<3:50:45,  1.41it/s]
1|6420|Loss: 0.7091000080108643:  25%|██▍       | 6419/25880 [1:20:02<3:50:45,  1.41it/s]
1|6420|Loss: 0.7091000080108643:  25%|██▍       | 6420/25880 [1:20:02<3:58:34,  1.36it/s]
1|6421|Loss: 0.8014594912528992:  25%|██▍       | 6420/25880 [1:20:03<3:58:34,  1.36it/s]
1|6421|Loss: 0.8014594912528992:  25%|██▍       | 6421/25880 [1:20:03<3:59:31,  1.35it/s]
1|6422|Loss: 0.7504296898841858:  25%|██▍       | 6421/25880 [1:20:04<3:59:31,  1.35it/s]
1|6422|Loss: 0.7504296898841858:  25%|██▍       | 6422/25880 [1:20:04<3:56:02,  1.37it/s]
1|6423|Loss: 0.9134844541549683:  25%|██▍       | 6422/25880 [1:20:04<3:56:02,  1.37it/s]
1|6423|Loss: 0.9134844541549683:  25%|██▍       | 6423/25880 [1:20:04<3:39:24,  1.48it/s]
1|6424|Loss: 0.8706057071685791:  25%|██▍       | 6423/25880 [1:20:05<3:39:24,  1.48it/s]
1|6424|Loss: 0.8706057071685791:  25%|██▍       | 6424/25880 [1:20:05<3:32:23,  1.53it/s]
1|6425|Loss: 0.9262146949768066:  25%|██▍       | 6424/25880 [1:20:05<3:32:23,  1.53it/s]
1|6425|Loss: 0.9262146949768066:  25%|██▍       | 6425/25880 [1:20:06<3:30:16,  1.54it/s]
1|6426|Loss: 0.8195275068283081:  25%|██▍       | 6425/25880 [1:20:06<3:30:16,  1.54it/s]
1|6426|Loss: 0.8195275068283081:  25%|██▍       | 6426/25880 [1:20:07<3:48:09,  1.42it/s]
1|6427|Loss: 0.9633897542953491:  25%|██▍       | 6426/25880 [1:20:07<3:48:09,  1.42it/s]
1|6427|Loss: 0.9633897542953491:  25%|██▍       | 6427/25880 [1:20:07<3:45:33,  1.44it/s]
1|6428|Loss: 0.7370966076850891:  25%|██▍       | 6427/25880 [1:20:08<3:45:33,  1.44it/s]
1|6428|Loss: 0.7370966076850891:  25%|██▍       | 6428/25880 [1:20:08<3:25:36,  1.58it/s]
1|6429|Loss: 0.8286042213439941:  25%|██▍       | 6428/25880 [1:20:08<3:25:36,  1.58it/s]
1|6429|Loss: 0.8286042213439941:  25%|██▍       | 6429/25880 [1:20:08<3:37:00,  1.49it/s]
1|6430|Loss: 0.8218778371810913:  25%|██▍       | 6429/25880 [1:20:09<3:37:00,  1.49it/s]
1|6430|Loss: 0.8218778371810913:  25%|██▍       | 6430/25880 [1:20:09<3:36:13,  1.50it/s]
1|6431|Loss: 0.795290470123291:  25%|██▍       | 6430/25880 [1:20:09<3:36:13,  1.50it/s] 
1|6431|Loss: 0.795290470123291:  25%|██▍       | 6431/25880 [1:20:10<3:33:08,  1.52it/s]
1|6432|Loss: 0.9732919931411743:  25%|██▍       | 6431/25880 [1:20:10<3:33:08,  1.52it/s]
1|6432|Loss: 0.9732919931411743:  25%|██▍       | 6432/25880 [1:20:11<3:39:52,  1.47it/s]
1|6433|Loss: 0.8312451839447021:  25%|██▍       | 6432/25880 [1:20:11<3:39:52,  1.47it/s]
1|6433|Loss: 0.8312451839447021:  25%|██▍       | 6433/25880 [1:20:11<3:46:08,  1.43it/s]
1|6434|Loss: 0.9058891534805298:  25%|██▍       | 6433/25880 [1:20:12<3:46:08,  1.43it/s]
1|6434|Loss: 0.9058891534805298:  25%|██▍       | 6434/25880 [1:20:12<3:33:44,  1.52it/s]
1|6435|Loss: 0.7417105436325073:  25%|██▍       | 6434/25880 [1:20:12<3:33:44,  1.52it/s]
1|6435|Loss: 0.7417105436325073:  25%|██▍       | 6435/25880 [1:20:13<3:37:50,  1.49it/s]
1|6436|Loss: 0.7197352051734924:  25%|██▍       | 6435/25880 [1:20:13<3:37:50,  1.49it/s]
1|6436|Loss: 0.7197352051734924:  25%|██▍       | 6436/25880 [1:20:13<3:50:26,  1.41it/s]
1|6437|Loss: 0.9815213680267334:  25%|██▍       | 6436/25880 [1:20:14<3:50:26,  1.41it/s]
1|6437|Loss: 0.9815213680267334:  25%|██▍       | 6437/25880 [1:20:14<3:32:29,  1.52it/s]
1|6438|Loss: 0.9252973794937134:  25%|██▍       | 6437/25880 [1:20:14<3:32:29,  1.52it/s]
1|6438|Loss: 0.9252973794937134:  25%|██▍       | 6438/25880 [1:20:15<3:34:28,  1.51it/s]
1|6439|Loss: 0.8666163682937622:  25%|██▍       | 6438/25880 [1:20:15<3:34:28,  1.51it/s]
1|6439|Loss: 0.8666163682937622:  25%|██▍       | 6439/25880 [1:20:15<3:29:49,  1.54it/s]
1|6440|Loss: 0.7288710474967957:  25%|██▍       | 6439/25880 [1:20:16<3:29:49,  1.54it/s]
1|6440|Loss: 0.7288710474967957:  25%|██▍       | 6440/25880 [1:20:16<3:40:55,  1.47it/s]
1|6441|Loss: 0.9828229546546936:  25%|██▍       | 6440/25880 [1:20:16<3:40:55,  1.47it/s]
1|6441|Loss: 0.9828229546546936:  25%|██▍       | 6441/25880 [1:20:17<3:40:10,  1.47it/s]
1|6442|Loss: 0.8386820554733276:  25%|██▍       | 6441/25880 [1:20:17<3:40:10,  1.47it/s]
1|6442|Loss: 0.8386820554733276:  25%|██▍       | 6442/25880 [1:20:17<3:53:11,  1.39it/s]
1|6443|Loss: 0.8878247737884521:  25%|██▍       | 6442/25880 [1:20:18<3:53:11,  1.39it/s]
1|6443|Loss: 0.8878247737884521:  25%|██▍       | 6443/25880 [1:20:18<3:56:49,  1.37it/s]
1|6444|Loss: 0.9790430665016174:  25%|██▍       | 6443/25880 [1:20:19<3:56:49,  1.37it/s]
1|6444|Loss: 0.9790430665016174:  25%|██▍       | 6444/25880 [1:20:19<3:54:09,  1.38it/s]
1|6445|Loss: 0.8947697281837463:  25%|██▍       | 6444/25880 [1:20:19<3:54:09,  1.38it/s]
1|6445|Loss: 0.8947697281837463:  25%|██▍       | 6445/25880 [1:20:20<3:51:55,  1.40it/s]
1|6446|Loss: 0.8871257305145264:  25%|██▍       | 6445/25880 [1:20:20<3:51:55,  1.40it/s]
1|6446|Loss: 0.8871257305145264:  25%|██▍       | 6446/25880 [1:20:20<4:04:42,  1.32it/s]
1|6447|Loss: 0.8685129284858704:  25%|██▍       | 6446/25880 [1:20:21<4:04:42,  1.32it/s]
1|6447|Loss: 0.8685129284858704:  25%|██▍       | 6447/25880 [1:20:21<3:58:52,  1.36it/s]
1|6448|Loss: 0.8133700489997864:  25%|██▍       | 6447/25880 [1:20:22<3:58:52,  1.36it/s]
1|6448|Loss: 0.8133700489997864:  25%|██▍       | 6448/25880 [1:20:22<4:06:14,  1.32it/s]
1|6449|Loss: 0.8782646656036377:  25%|██▍       | 6448/25880 [1:20:22<4:06:14,  1.32it/s]
1|6449|Loss: 0.8782646656036377:  25%|██▍       | 6449/25880 [1:20:23<4:09:56,  1.30it/s]
1|6450|Loss: 0.9041887521743774:  25%|██▍       | 6449/25880 [1:20:23<4:09:56,  1.30it/s]
1|6450|Loss: 0.9041887521743774:  25%|██▍       | 6450/25880 [1:20:24<4:12:10,  1.28it/s]
1|6451|Loss: 0.8159462213516235:  25%|██▍       | 6450/25880 [1:20:24<4:12:10,  1.28it/s]
1|6451|Loss: 0.8159462213516235:  25%|██▍       | 6451/25880 [1:20:24<4:06:45,  1.31it/s]
1|6452|Loss: 0.9117113947868347:  25%|██▍       | 6451/25880 [1:20:25<4:06:45,  1.31it/s]
1|6452|Loss: 0.9117113947868347:  25%|██▍       | 6452/25880 [1:20:25<4:14:09,  1.27it/s]
1|6453|Loss: 0.9561351537704468:  25%|██▍       | 6452/25880 [1:20:25<4:14:09,  1.27it/s]
1|6453|Loss: 0.9561351537704468:  25%|██▍       | 6453/25880 [1:20:26<4:12:00,  1.28it/s]
1|6454|Loss: 0.8620891571044922:  25%|██▍       | 6453/25880 [1:20:26<4:12:00,  1.28it/s]
1|6454|Loss: 0.8620891571044922:  25%|██▍       | 6454/25880 [1:20:27<4:07:46,  1.31it/s]
1|6455|Loss: 0.7990577816963196:  25%|██▍       | 6454/25880 [1:20:27<4:07:46,  1.31it/s]
1|6455|Loss: 0.7990577816963196:  25%|██▍       | 6455/25880 [1:20:27<4:02:42,  1.33it/s]
1|6456|Loss: 0.895516037940979:  25%|██▍       | 6455/25880 [1:20:28<4:02:42,  1.33it/s] 
1|6456|Loss: 0.895516037940979:  25%|██▍       | 6456/25880 [1:20:28<3:57:36,  1.36it/s]
1|6457|Loss: 0.8091883659362793:  25%|██▍       | 6456/25880 [1:20:28<3:57:36,  1.36it/s]
1|6457|Loss: 0.8091883659362793:  25%|██▍       | 6457/25880 [1:20:29<3:57:09,  1.36it/s]
1|6458|Loss: 0.8044315576553345:  25%|██▍       | 6457/25880 [1:20:29<3:57:09,  1.36it/s]
1|6458|Loss: 0.8044315576553345:  25%|██▍       | 6458/25880 [1:20:29<3:50:44,  1.40it/s]
1|6459|Loss: 0.9425061941146851:  25%|██▍       | 6458/25880 [1:20:30<3:50:44,  1.40it/s]
1|6459|Loss: 0.9425061941146851:  25%|██▍       | 6459/25880 [1:20:30<4:01:33,  1.34it/s]
1|6460|Loss: 0.6581793427467346:  25%|██▍       | 6459/25880 [1:20:31<4:01:33,  1.34it/s]
1|6460|Loss: 0.6581793427467346:  25%|██▍       | 6460/25880 [1:20:31<3:54:17,  1.38it/s]
1|6461|Loss: 0.8451299667358398:  25%|██▍       | 6460/25880 [1:20:31<3:54:17,  1.38it/s]
1|6461|Loss: 0.8451299667358398:  25%|██▍       | 6461/25880 [1:20:32<3:50:34,  1.40it/s]
1|6462|Loss: 0.80165696144104:  25%|██▍       | 6461/25880 [1:20:32<3:50:34,  1.40it/s]  
1|6462|Loss: 0.80165696144104:  25%|██▍       | 6462/25880 [1:20:32<4:06:00,  1.32it/s]
1|6463|Loss: 0.7761585116386414:  25%|██▍       | 6462/25880 [1:20:33<4:06:00,  1.32it/s]
1|6463|Loss: 0.7761585116386414:  25%|██▍       | 6463/25880 [1:20:33<4:06:27,  1.31it/s]
1|6464|Loss: 0.8329622149467468:  25%|██▍       | 6463/25880 [1:20:34<4:06:27,  1.31it/s]
1|6464|Loss: 0.8329622149467468:  25%|██▍       | 6464/25880 [1:20:34<3:43:51,  1.45it/s]
1|6465|Loss: 0.8714554309844971:  25%|██▍       | 6464/25880 [1:20:34<3:43:51,  1.45it/s]
1|6465|Loss: 0.8714554309844971:  25%|██▍       | 6465/25880 [1:20:34<3:40:07,  1.47it/s]
1|6466|Loss: 1.0096845626831055:  25%|██▍       | 6465/25880 [1:20:35<3:40:07,  1.47it/s]
1|6466|Loss: 1.0096845626831055:  25%|██▍       | 6466/25880 [1:20:35<3:51:53,  1.40it/s]
1|6467|Loss: 0.8665646314620972:  25%|██▍       | 6466/25880 [1:20:36<3:51:53,  1.40it/s]
1|6467|Loss: 0.8665646314620972:  25%|██▍       | 6467/25880 [1:20:36<3:37:57,  1.48it/s]
1|6468|Loss: 0.8200837969779968:  25%|██▍       | 6467/25880 [1:20:36<3:37:57,  1.48it/s]
1|6468|Loss: 0.8200837969779968:  25%|██▍       | 6468/25880 [1:20:36<3:29:46,  1.54it/s]
1|6469|Loss: 0.7816189527511597:  25%|██▍       | 6468/25880 [1:20:37<3:29:46,  1.54it/s]
1|6469|Loss: 0.7816189527511597:  25%|██▍       | 6469/25880 [1:20:37<3:55:02,  1.38it/s]
1|6470|Loss: 0.9418430328369141:  25%|██▍       | 6469/25880 [1:20:38<3:55:02,  1.38it/s]
1|6470|Loss: 0.9418430328369141:  25%|██▌       | 6470/25880 [1:20:38<3:58:29,  1.36it/s]
1|6471|Loss: 0.6706849932670593:  25%|██▌       | 6470/25880 [1:20:38<3:58:29,  1.36it/s]
1|6471|Loss: 0.6706849932670593:  25%|██▌       | 6471/25880 [1:20:39<3:55:27,  1.37it/s]
1|6472|Loss: 0.903763473033905:  25%|██▌       | 6471/25880 [1:20:39<3:55:27,  1.37it/s] 
1|6472|Loss: 0.903763473033905:  25%|██▌       | 6472/25880 [1:20:40<4:02:27,  1.33it/s]
1|6473|Loss: 0.8156970739364624:  25%|██▌       | 6472/25880 [1:20:40<4:02:27,  1.33it/s]
1|6473|Loss: 0.8156970739364624:  25%|██▌       | 6473/25880 [1:20:40<3:51:27,  1.40it/s]
1|6474|Loss: 0.8400108218193054:  25%|██▌       | 6473/25880 [1:20:41<3:51:27,  1.40it/s]
1|6474|Loss: 0.8400108218193054:  25%|██▌       | 6474/25880 [1:20:41<3:55:40,  1.37it/s]
1|6475|Loss: 0.7848148345947266:  25%|██▌       | 6474/25880 [1:20:41<3:55:40,  1.37it/s]
1|6475|Loss: 0.7848148345947266:  25%|██▌       | 6475/25880 [1:20:42<4:06:54,  1.31it/s]
1|6476|Loss: 0.8054350018501282:  25%|██▌       | 6475/25880 [1:20:42<4:06:54,  1.31it/s]
1|6476|Loss: 0.8054350018501282:  25%|██▌       | 6476/25880 [1:20:43<4:21:00,  1.24it/s]
1|6477|Loss: 0.852333128452301:  25%|██▌       | 6476/25880 [1:20:43<4:21:00,  1.24it/s] 
1|6477|Loss: 0.852333128452301:  25%|██▌       | 6477/25880 [1:20:44<4:27:44,  1.21it/s]
1|6478|Loss: 0.887786865234375:  25%|██▌       | 6477/25880 [1:20:44<4:27:44,  1.21it/s]
1|6478|Loss: 0.887786865234375:  25%|██▌       | 6478/25880 [1:20:44<4:35:29,  1.17it/s]
1|6479|Loss: 0.8101328015327454:  25%|██▌       | 6478/25880 [1:20:45<4:35:29,  1.17it/s]
1|6479|Loss: 0.8101328015327454:  25%|██▌       | 6479/25880 [1:20:45<4:34:21,  1.18it/s]
1|6480|Loss: 0.8344768285751343:  25%|██▌       | 6479/25880 [1:20:46<4:34:21,  1.18it/s]
1|6480|Loss: 0.8344768285751343:  25%|██▌       | 6480/25880 [1:20:46<4:43:39,  1.14it/s]
1|6481|Loss: 0.7857334017753601:  25%|██▌       | 6480/25880 [1:20:47<4:43:39,  1.14it/s]
1|6481|Loss: 0.7857334017753601:  25%|██▌       | 6481/25880 [1:20:47<4:13:28,  1.28it/s]
1|6482|Loss: 0.818658173084259:  25%|██▌       | 6481/25880 [1:20:47<4:13:28,  1.28it/s] 
1|6482|Loss: 0.818658173084259:  25%|██▌       | 6482/25880 [1:20:47<3:52:02,  1.39it/s]
1|6483|Loss: 0.8332918882369995:  25%|██▌       | 6482/25880 [1:20:48<3:52:02,  1.39it/s]
1|6483|Loss: 0.8332918882369995:  25%|██▌       | 6483/25880 [1:20:48<3:47:39,  1.42it/s]
1|6484|Loss: 0.8070942759513855:  25%|██▌       | 6483/25880 [1:20:48<3:47:39,  1.42it/s]
1|6484|Loss: 0.8070942759513855:  25%|██▌       | 6484/25880 [1:20:49<3:42:31,  1.45it/s]
1|6485|Loss: 0.8988291025161743:  25%|██▌       | 6484/25880 [1:20:49<3:42:31,  1.45it/s]
1|6485|Loss: 0.8988291025161743:  25%|██▌       | 6485/25880 [1:20:49<3:38:07,  1.48it/s]
1|6486|Loss: 0.8852592706680298:  25%|██▌       | 6485/25880 [1:20:50<3:38:07,  1.48it/s]
1|6486|Loss: 0.8852592706680298:  25%|██▌       | 6486/25880 [1:20:50<3:49:28,  1.41it/s]
1|6487|Loss: 0.8274458646774292:  25%|██▌       | 6486/25880 [1:20:51<3:49:28,  1.41it/s]
1|6487|Loss: 0.8274458646774292:  25%|██▌       | 6487/25880 [1:20:51<3:44:07,  1.44it/s]
1|6488|Loss: 0.8533793091773987:  25%|██▌       | 6487/25880 [1:20:51<3:44:07,  1.44it/s]
1|6488|Loss: 0.8533793091773987:  25%|██▌       | 6488/25880 [1:20:51<3:38:32,  1.48it/s]
1|6489|Loss: 0.941821813583374:  25%|██▌       | 6488/25880 [1:20:52<3:38:32,  1.48it/s] 
1|6489|Loss: 0.941821813583374:  25%|██▌       | 6489/25880 [1:20:52<3:39:50,  1.47it/s]
1|6490|Loss: 0.9244945049285889:  25%|██▌       | 6489/25880 [1:20:53<3:39:50,  1.47it/s]
1|6490|Loss: 0.9244945049285889:  25%|██▌       | 6490/25880 [1:20:53<3:54:26,  1.38it/s]
1|6491|Loss: 0.8636030554771423:  25%|██▌       | 6490/25880 [1:20:53<3:54:26,  1.38it/s]
1|6491|Loss: 0.8636030554771423:  25%|██▌       | 6491/25880 [1:20:54<3:55:11,  1.37it/s]
1|6492|Loss: 0.7790558934211731:  25%|██▌       | 6491/25880 [1:20:54<3:55:11,  1.37it/s]
1|6492|Loss: 0.7790558934211731:  25%|██▌       | 6492/25880 [1:20:54<3:54:10,  1.38it/s]
1|6493|Loss: 0.9441945552825928:  25%|██▌       | 6492/25880 [1:20:55<3:54:10,  1.38it/s]
1|6493|Loss: 0.9441945552825928:  25%|██▌       | 6493/25880 [1:20:55<4:09:06,  1.30it/s]
1|6494|Loss: 0.7130321860313416:  25%|██▌       | 6493/25880 [1:20:56<4:09:06,  1.30it/s]
1|6494|Loss: 0.7130321860313416:  25%|██▌       | 6494/25880 [1:20:56<4:26:59,  1.21it/s]
1|6495|Loss: 0.7947730422019958:  25%|██▌       | 6494/25880 [1:20:57<4:26:59,  1.21it/s]
1|6495|Loss: 0.7947730422019958:  25%|██▌       | 6495/25880 [1:20:57<4:21:13,  1.24it/s]
1|6496|Loss: 0.7767801284790039:  25%|██▌       | 6495/25880 [1:20:57<4:21:13,  1.24it/s]
1|6496|Loss: 0.7767801284790039:  25%|██▌       | 6496/25880 [1:20:58<4:13:25,  1.27it/s]
1|6497|Loss: 0.8780286908149719:  25%|██▌       | 6496/25880 [1:20:58<4:13:25,  1.27it/s]
1|6497|Loss: 0.8780286908149719:  25%|██▌       | 6497/25880 [1:20:58<4:13:26,  1.27it/s]
1|6498|Loss: 0.8728382587432861:  25%|██▌       | 6497/25880 [1:20:59<4:13:26,  1.27it/s]
1|6498|Loss: 0.8728382587432861:  25%|██▌       | 6498/25880 [1:20:59<4:11:12,  1.29it/s]
1|6499|Loss: 0.8634654879570007:  25%|██▌       | 6498/25880 [1:21:00<4:11:12,  1.29it/s]
1|6499|Loss: 0.8634654879570007:  25%|██▌       | 6499/25880 [1:21:00<4:08:56,  1.30it/s]
1|6500|Loss: 0.8926903009414673:  25%|██▌       | 6499/25880 [1:21:00<4:08:56,  1.30it/s]Model checkpoint of size 25961 MB saved to output/alpaca-colorful-llama2-finetune/model_0_6500.ckpt
+Skipping uploading to HuggingFace Hub (no repo id specified)
+
1|6500|Loss: 0.8926903009414673:  25%|██▌       | 6500/25880 [1:21:47<79:04:05, 14.69s/it]
1|6501|Loss: 1.0245416164398193:  25%|██▌       | 6500/25880 [1:21:47<79:04:05, 14.69s/it]
1|6501|Loss: 1.0245416164398193:  25%|██▌       | 6501/25880 [1:21:48<56:20:19, 10.47s/it]
1|6502|Loss: 0.8936096429824829:  25%|██▌       | 6501/25880 [1:21:48<56:20:19, 10.47s/it]
1|6502|Loss: 0.8936096429824829:  25%|██▌       | 6502/25880 [1:21:49<40:37:29,  7.55s/it]
1|6503|Loss: 0.8773505687713623:  25%|██▌       | 6502/25880 [1:21:49<40:37:29,  7.55s/it]
1|6503|Loss: 0.8773505687713623:  25%|██▌       | 6503/25880 [1:21:49<29:24:44,  5.46s/it]
1|6504|Loss: 0.7343732714653015:  25%|██▌       | 6503/25880 [1:21:50<29:24:44,  5.46s/it]
1|6504|Loss: 0.7343732714653015:  25%|██▌       | 6504/25880 [1:21:50<21:57:07,  4.08s/it]
1|6505|Loss: 0.8597156405448914:  25%|██▌       | 6504/25880 [1:21:50<21:57:07,  4.08s/it]
1|6505|Loss: 0.8597156405448914:  25%|██▌       | 6505/25880 [1:21:51<16:28:27,  3.06s/it]
1|6506|Loss: 0.8985366225242615:  25%|██▌       | 6505/25880 [1:21:51<16:28:27,  3.06s/it]
1|6506|Loss: 0.8985366225242615:  25%|██▌       | 6506/25880 [1:21:51<12:48:04,  2.38s/it]
1|6507|Loss: 0.8358655571937561:  25%|██▌       | 6506/25880 [1:21:52<12:48:04,  2.38s/it]
1|6507|Loss: 0.8358655571937561:  25%|██▌       | 6507/25880 [1:21:52<10:30:29,  1.95s/it]
1|6508|Loss: 0.9385076761245728:  25%|██▌       | 6507/25880 [1:21:53<10:30:29,  1.95s/it]
1|6508|Loss: 0.9385076761245728:  25%|██▌       | 6508/25880 [1:21:53<8:45:58,  1.63s/it] 
1|6509|Loss: 0.866382360458374:  25%|██▌       | 6508/25880 [1:21:54<8:45:58,  1.63s/it] 
1|6509|Loss: 0.866382360458374:  25%|██▌       | 6509/25880 [1:21:54<7:20:11,  1.36s/it]
1|6510|Loss: 0.8987348079681396:  25%|██▌       | 6509/25880 [1:21:54<7:20:11,  1.36s/it]
1|6510|Loss: 0.8987348079681396:  25%|██▌       | 6510/25880 [1:21:55<6:18:20,  1.17s/it]
1|6511|Loss: 0.7692699432373047:  25%|██▌       | 6510/25880 [1:21:55<6:18:20,  1.17s/it]
1|6511|Loss: 0.7692699432373047:  25%|██▌       | 6511/25880 [1:21:56<5:43:00,  1.06s/it]
1|6512|Loss: 0.9426987171173096:  25%|██▌       | 6511/25880 [1:21:56<5:43:00,  1.06s/it]
1|6512|Loss: 0.9426987171173096:  25%|██▌       | 6512/25880 [1:21:56<4:58:34,  1.08it/s]
1|6513|Loss: 0.8983498811721802:  25%|██▌       | 6512/25880 [1:21:56<4:58:34,  1.08it/s]
1|6513|Loss: 0.8983498811721802:  25%|██▌       | 6513/25880 [1:21:57<4:24:06,  1.22it/s]
1|6514|Loss: 0.8201776742935181:  25%|██▌       | 6513/25880 [1:21:57<4:24:06,  1.22it/s]
1|6514|Loss: 0.8201776742935181:  25%|██▌       | 6514/25880 [1:21:57<4:17:20,  1.25it/s]
1|6515|Loss: 0.708955705165863:  25%|██▌       | 6514/25880 [1:21:58<4:17:20,  1.25it/s] 
1|6515|Loss: 0.708955705165863:  25%|██▌       | 6515/25880 [1:21:58<3:57:54,  1.36it/s]
1|6516|Loss: 0.8206918239593506:  25%|██▌       | 6515/25880 [1:21:58<3:57:54,  1.36it/s]
1|6516|Loss: 0.8206918239593506:  25%|██▌       | 6516/25880 [1:21:59<3:50:57,  1.40it/s]
1|6517|Loss: 0.8855257630348206:  25%|██▌       | 6516/25880 [1:21:59<3:50:57,  1.40it/s]
1|6517|Loss: 0.8855257630348206:  25%|██▌       | 6517/25880 [1:21:59<3:43:49,  1.44it/s]
1|6518|Loss: 0.8285773992538452:  25%|██▌       | 6517/25880 [1:22:00<3:43:49,  1.44it/s]
1|6518|Loss: 0.8285773992538452:  25%|██▌       | 6518/25880 [1:22:00<3:31:27,  1.53it/s]
1|6519|Loss: 0.7469403743743896:  25%|██▌       | 6518/25880 [1:22:00<3:31:27,  1.53it/s]
1|6519|Loss: 0.7469403743743896:  25%|██▌       | 6519/25880 [1:22:00<3:19:08,  1.62it/s]
1|6520|Loss: 0.8591446876525879:  25%|██▌       | 6519/25880 [1:22:01<3:19:08,  1.62it/s]
1|6520|Loss: 0.8591446876525879:  25%|██▌       | 6520/25880 [1:22:01<3:26:46,  1.56it/s]
1|6521|Loss: 0.8005762100219727:  25%|██▌       | 6520/25880 [1:22:02<3:26:46,  1.56it/s]
1|6521|Loss: 0.8005762100219727:  25%|██▌       | 6521/25880 [1:22:02<3:43:05,  1.45it/s]
1|6522|Loss: 0.7348192930221558:  25%|██▌       | 6521/25880 [1:22:02<3:43:05,  1.45it/s]
1|6522|Loss: 0.7348192930221558:  25%|██▌       | 6522/25880 [1:22:03<3:45:33,  1.43it/s]
1|6523|Loss: 0.8340805172920227:  25%|██▌       | 6522/25880 [1:22:03<3:45:33,  1.43it/s]
1|6523|Loss: 0.8340805172920227:  25%|██▌       | 6523/25880 [1:22:03<3:44:56,  1.43it/s]
1|6524|Loss: 0.9469980597496033:  25%|██▌       | 6523/25880 [1:22:04<3:44:56,  1.43it/s]
1|6524|Loss: 0.9469980597496033:  25%|██▌       | 6524/25880 [1:22:04<3:52:24,  1.39it/s]
1|6525|Loss: 0.7874542474746704:  25%|██▌       | 6524/25880 [1:22:05<3:52:24,  1.39it/s]
1|6525|Loss: 0.7874542474746704:  25%|██▌       | 6525/25880 [1:22:05<3:40:49,  1.46it/s]
1|6526|Loss: 0.8136796951293945:  25%|██▌       | 6525/25880 [1:22:05<3:40:49,  1.46it/s]
1|6526|Loss: 0.8136796951293945:  25%|██▌       | 6526/25880 [1:22:05<3:26:03,  1.57it/s]
1|6527|Loss: 0.9023729562759399:  25%|██▌       | 6526/25880 [1:22:06<3:26:03,  1.57it/s]
1|6527|Loss: 0.9023729562759399:  25%|██▌       | 6527/25880 [1:22:06<3:34:30,  1.50it/s]
1|6528|Loss: 0.8586741089820862:  25%|██▌       | 6527/25880 [1:22:06<3:34:30,  1.50it/s]
1|6528|Loss: 0.8586741089820862:  25%|██▌       | 6528/25880 [1:22:07<3:45:52,  1.43it/s]
1|6529|Loss: 0.8353742361068726:  25%|██▌       | 6528/25880 [1:22:07<3:45:52,  1.43it/s]
1|6529|Loss: 0.8353742361068726:  25%|██▌       | 6529/25880 [1:22:08<3:47:11,  1.42it/s]
1|6530|Loss: 0.8284489512443542:  25%|��█▌       | 6529/25880 [1:22:08<3:47:11,  1.42it/s]
1|6530|Loss: 0.8284489512443542:  25%|██▌       | 6530/25880 [1:22:08<3:57:39,  1.36it/s]
1|6531|Loss: 0.8385546207427979:  25%|██▌       | 6530/25880 [1:22:09<3:57:39,  1.36it/s]
1|6531|Loss: 0.8385546207427979:  25%|██▌       | 6531/25880 [1:22:09<3:57:30,  1.36it/s]
1|6532|Loss: 0.8131864070892334:  25%|██▌       | 6531/25880 [1:22:09<3:57:30,  1.36it/s]
1|6532|Loss: 0.8131864070892334:  25%|██▌       | 6532/25880 [1:22:10<3:38:20,  1.48it/s]
1|6533|Loss: 0.8845915794372559:  25%|██▌       | 6532/25880 [1:22:10<3:38:20,  1.48it/s]
1|6533|Loss: 0.8845915794372559:  25%|██▌       | 6533/25880 [1:22:10<3:43:42,  1.44it/s]
1|6534|Loss: 0.8791754245758057:  25%|██▌       | 6533/25880 [1:22:11<3:43:42,  1.44it/s]
1|6534|Loss: 0.8791754245758057:  25%|██▌       | 6534/25880 [1:22:11<3:39:01,  1.47it/s]
1|6535|Loss: 0.9277815222740173:  25%|██▌       | 6534/25880 [1:22:11<3:39:01,  1.47it/s]
1|6535|Loss: 0.9277815222740173:  25%|██▌       | 6535/25880 [1:22:12<3:41:41,  1.45it/s]
1|6536|Loss: 0.808236300945282:  25%|██▌       | 6535/25880 [1:22:12<3:41:41,  1.45it/s] 
1|6536|Loss: 0.808236300945282:  25%|██▌       | 6536/25880 [1:22:12<3:37:13,  1.48it/s]
1|6537|Loss: 0.8888972401618958:  25%|██▌       | 6536/25880 [1:22:13<3:37:13,  1.48it/s]
1|6537|Loss: 0.8888972401618958:  25%|██▌       | 6537/25880 [1:22:13<3:40:19,  1.46it/s]
1|6538|Loss: 0.8796430230140686:  25%|██▌       | 6537/25880 [1:22:13<3:40:19,  1.46it/s]
1|6538|Loss: 0.8796430230140686:  25%|██▌       | 6538/25880 [1:22:14<3:33:31,  1.51it/s]
1|6539|Loss: 1.0272109508514404:  25%|██▌       | 6538/25880 [1:22:14<3:33:31,  1.51it/s]
1|6539|Loss: 1.0272109508514404:  25%|██▌       | 6539/25880 [1:22:14<3:27:35,  1.55it/s]
1|6540|Loss: 0.7429033517837524:  25%|██▌       | 6539/25880 [1:22:15<3:27:35,  1.55it/s]
1|6540|Loss: 0.7429033517837524:  25%|██▌       | 6540/25880 [1:22:15<3:41:15,  1.46it/s]
1|6541|Loss: 0.8023909330368042:  25%|██▌       | 6540/25880 [1:22:15<3:41:15,  1.46it/s]
1|6541|Loss: 0.8023909330368042:  25%|██▌       | 6541/25880 [1:22:16<3:52:14,  1.39it/s]
1|6542|Loss: 0.7383711934089661:  25%|██▌       | 6541/25880 [1:22:16<3:52:14,  1.39it/s]
1|6542|Loss: 0.7383711934089661:  25%|██▌       | 6542/25880 [1:22:17<3:55:08,  1.37it/s]
1|6543|Loss: 0.8883561491966248:  25%|██▌       | 6542/25880 [1:22:17<3:55:08,  1.37it/s]
1|6543|Loss: 0.8883561491966248:  25%|██▌       | 6543/25880 [1:22:17<4:04:59,  1.32it/s]
1|6544|Loss: 0.817641019821167:  25%|██▌       | 6543/25880 [1:22:18<4:04:59,  1.32it/s] 
1|6544|Loss: 0.817641019821167:  25%|██▌       | 6544/25880 [1:22:18<4:02:01,  1.33it/s]
1|6545|Loss: 0.8595395088195801:  25%|██▌       | 6544/25880 [1:22:19<4:02:01,  1.33it/s]
1|6545|Loss: 0.8595395088195801:  25%|██▌       | 6545/25880 [1:22:19<3:52:13,  1.39it/s]
1|6546|Loss: 0.7940743565559387:  25%|██▌       | 6545/25880 [1:22:19<3:52:13,  1.39it/s]
1|6546|Loss: 0.7940743565559387:  25%|██▌       | 6546/25880 [1:22:19<3:37:40,  1.48it/s]
1|6547|Loss: 0.8924784660339355:  25%|██▌       | 6546/25880 [1:22:20<3:37:40,  1.48it/s]
1|6547|Loss: 0.8924784660339355:  25%|██▌       | 6547/25880 [1:22:20<3:48:45,  1.41it/s]
1|6548|Loss: 0.8568525910377502:  25%|██▌       | 6547/25880 [1:22:21<3:48:45,  1.41it/s]
1|6548|Loss: 0.8568525910377502:  25%|██▌       | 6548/25880 [1:22:21<4:02:57,  1.33it/s]
1|6549|Loss: 0.8539144992828369:  25%|██▌       | 6548/25880 [1:22:21<4:02:57,  1.33it/s]
1|6549|Loss: 0.8539144992828369:  25%|██▌       | 6549/25880 [1:22:22<3:54:48,  1.37it/s]
1|6550|Loss: 0.8867011666297913:  25%|██▌       | 6549/25880 [1:22:22<3:54:48,  1.37it/s]
1|6550|Loss: 0.8867011666297913:  25%|██▌       | 6550/25880 [1:22:22<3:57:49,  1.35it/s]
1|6551|Loss: 1.0047613382339478:  25%|██▌       | 6550/25880 [1:22:23<3:57:49,  1.35it/s]
1|6551|Loss: 1.0047613382339478:  25%|██▌       | 6551/25880 [1:22:23<3:58:37,  1.35it/s]
1|6552|Loss: 0.9151245355606079:  25%|██▌       | 6551/25880 [1:22:24<3:58:37,  1.35it/s]
1|6552|Loss: 0.9151245355606079:  25%|██▌       | 6552/25880 [1:22:24<3:58:49,  1.35it/s]
1|6553|Loss: 0.8842482566833496:  25%|██▌       | 6552/25880 [1:22:24<3:58:49,  1.35it/s]
1|6553|Loss: 0.8842482566833496:  25%|██▌       | 6553/25880 [1:22:25<3:58:47,  1.35it/s]
1|6554|Loss: 0.8772693872451782:  25%|██▌       | 6553/25880 [1:22:25<3:58:47,  1.35it/s]
1|6554|Loss: 0.8772693872451782:  25%|██▌       | 6554/25880 [1:22:25<3:51:13,  1.39it/s]
1|6555|Loss: 1.0545272827148438:  25%|██▌       | 6554/25880 [1:22:26<3:51:13,  1.39it/s]
1|6555|Loss: 1.0545272827148438:  25%|██▌       | 6555/25880 [1:22:26<4:09:41,  1.29it/s]
1|6556|Loss: 0.9021212458610535:  25%|██▌       | 6555/25880 [1:22:27<4:09:41,  1.29it/s]
1|6556|Loss: 0.9021212458610535:  25%|██▌       | 6556/25880 [1:22:27<4:01:55,  1.33it/s]
1|6557|Loss: 0.8558964729309082:  25%|██▌       | 6556/25880 [1:22:27<4:01:55,  1.33it/s]
1|6557|Loss: 0.8558964729309082:  25%|██▌       | 6557/25880 [1:22:28<4:05:49,  1.31it/s]
1|6558|Loss: 0.8030501008033752:  25%|██▌       | 6557/25880 [1:22:28<4:05:49,  1.31it/s]
1|6558|Loss: 0.8030501008033752:  25%|██▌       | 6558/25880 [1:22:28<3:47:19,  1.42it/s]
1|6559|Loss: 0.8597932457923889:  25%|██▌       | 6558/25880 [1:22:29<3:47:19,  1.42it/s]
1|6559|Loss: 0.8597932457923889:  25%|██▌       | 6559/25880 [1:22:29<3:44:33,  1.43it/s]
1|6560|Loss: 0.8291424512863159:  25%|██▌       | 6559/25880 [1:22:29<3:44:33,  1.43it/s]
1|6560|Loss: 0.8291424512863159:  25%|██▌       | 6560/25880 [1:22:30<3:36:47,  1.49it/s]
1|6561|Loss: 0.8139998912811279:  25%|██▌       | 6560/25880 [1:22:30<3:36:47,  1.49it/s]
1|6561|Loss: 0.8139998912811279:  25%|██▌       | 6561/25880 [1:22:30<3:17:39,  1.63it/s]
1|6562|Loss: 0.770492434501648:  25%|██▌       | 6561/25880 [1:22:30<3:17:39,  1.63it/s] 
1|6562|Loss: 0.770492434501648:  25%|██▌       | 6562/25880 [1:22:31<3:29:27,  1.54it/s]
1|6563|Loss: 0.8231935501098633:  25%|██▌       | 6562/25880 [1:22:31<3:29:27,  1.54it/s]
1|6563|Loss: 0.8231935501098633:  25%|██▌       | 6563/25880 [1:22:31<3:29:33,  1.54it/s]
1|6564|Loss: 0.8328003883361816:  25%|██▌       | 6563/25880 [1:22:32<3:29:33,  1.54it/s]
1|6564|Loss: 0.8328003883361816:  25%|██▌       | 6564/25880 [1:22:32<3:32:42,  1.51it/s]
1|6565|Loss: 0.9287300705909729:  25%|██▌       | 6564/25880 [1:22:33<3:32:42,  1.51it/s]
1|6565|Loss: 0.9287300705909729:  25%|██▌       | 6565/25880 [1:22:33<3:35:46,  1.49it/s]
1|6566|Loss: 0.879121720790863:  25%|██▌       | 6565/25880 [1:22:33<3:35:46,  1.49it/s] 
1|6566|Loss: 0.879121720790863:  25%|██▌       | 6566/25880 [1:22:34<3:50:00,  1.40it/s]
1|6567|Loss: 0.8824334740638733:  25%|██▌       | 6566/25880 [1:22:34<3:50:00,  1.40it/s]
1|6567|Loss: 0.8824334740638733:  25%|██▌       | 6567/25880 [1:22:34<3:45:19,  1.43it/s]
1|6568|Loss: 0.9017861485481262:  25%|██▌       | 6567/25880 [1:22:35<3:45:19,  1.43it/s]
1|6568|Loss: 0.9017861485481262:  25%|██▌       | 6568/25880 [1:22:35<3:46:00,  1.42it/s]
1|6569|Loss: 0.8404046297073364:  25%|██▌       | 6568/25880 [1:22:35<3:46:00,  1.42it/s]
1|6569|Loss: 0.8404046297073364:  25%|██▌       | 6569/25880 [1:22:36<3:41:22,  1.45it/s]
1|6570|Loss: 0.7370776534080505:  25%|██▌       | 6569/25880 [1:22:36<3:41:22,  1.45it/s]
1|6570|Loss: 0.7370776534080505:  25%|██▌       | 6570/25880 [1:22:36<3:47:56,  1.41it/s]
1|6571|Loss: 0.7695437669754028:  25%|██▌       | 6570/25880 [1:22:37<3:47:56,  1.41it/s]
1|6571|Loss: 0.7695437669754028:  25%|██▌       | 6571/25880 [1:22:37<3:49:20,  1.40it/s]
1|6572|Loss: 0.9018054008483887:  25%|██▌       | 6571/25880 [1:22:38<3:49:20,  1.40it/s]
1|6572|Loss: 0.9018054008483887:  25%|██▌       | 6572/25880 [1:22:38<3:50:42,  1.39it/s]
1|6573|Loss: 0.9408276081085205:  25%|██▌       | 6572/25880 [1:22:38<3:50:42,  1.39it/s]
1|6573|Loss: 0.9408276081085205:  25%|██▌       | 6573/25880 [1:22:39<3:57:16,  1.36it/s]
1|6574|Loss: 0.689547061920166:  25%|██▌       | 6573/25880 [1:22:39<3:57:16,  1.36it/s] 
1|6574|Loss: 0.689547061920166:  25%|██▌       | 6574/25880 [1:22:39<3:41:57,  1.45it/s]
1|6575|Loss: 0.764494001865387:  25%|██▌       | 6574/25880 [1:22:40<3:41:57,  1.45it/s]
1|6575|Loss: 0.764494001865387:  25%|██▌       | 6575/25880 [1:22:40<3:39:05,  1.47it/s]
1|6576|Loss: 0.8308088779449463:  25%|██▌       | 6575/25880 [1:22:40<3:39:05,  1.47it/s]
1|6576|Loss: 0.8308088779449463:  25%|██▌       | 6576/25880 [1:22:41<3:57:03,  1.36it/s]
1|6577|Loss: 0.8220311999320984:  25%|██▌       | 6576/25880 [1:22:41<3:57:03,  1.36it/s]
1|6577|Loss: 0.8220311999320984:  25%|██▌       | 6577/25880 [1:22:42<4:08:39,  1.29it/s]
1|6578|Loss: 1.0043293237686157:  25%|██▌       | 6577/25880 [1:22:42<4:08:39,  1.29it/s]
1|6578|Loss: 1.0043293237686157:  25%|██▌       | 6578/25880 [1:22:42<4:04:22,  1.32it/s]
1|6579|Loss: 0.9958564043045044:  25%|██▌       | 6578/25880 [1:22:43<4:04:22,  1.32it/s]
1|6579|Loss: 0.9958564043045044:  25%|██▌       | 6579/25880 [1:22:43<4:08:59,  1.29it/s]
1|6580|Loss: 0.8276404738426208:  25%|██▌       | 6579/25880 [1:22:44<4:08:59,  1.29it/s]
1|6580|Loss: 0.8276404738426208:  25%|██▌       | 6580/25880 [1:22:44<3:59:35,  1.34it/s]
1|6581|Loss: 0.7200596332550049:  25%|██▌       | 6580/25880 [1:22:44<3:59:35,  1.34it/s]
1|6581|Loss: 0.7200596332550049:  25%|██▌       | 6581/25880 [1:22:45<3:55:57,  1.36it/s]
1|6582|Loss: 0.8122143149375916:  25%|██▌       | 6581/25880 [1:22:45<3:55:57,  1.36it/s]
1|6582|Loss: 0.8122143149375916:  25%|██▌       | 6582/25880 [1:22:45<4:02:52,  1.32it/s]
1|6583|Loss: 0.754482090473175:  25%|██▌       | 6582/25880 [1:22:46<4:02:52,  1.32it/s] 
1|6583|Loss: 0.754482090473175:  25%|██▌       | 6583/25880 [1:22:46<4:09:39,  1.29it/s]
1|6584|Loss: 0.8719199299812317:  25%|██▌       | 6583/25880 [1:22:47<4:09:39,  1.29it/s]
1|6584|Loss: 0.8719199299812317:  25%|██▌       | 6584/25880 [1:22:47<4:05:09,  1.31it/s]
1|6585|Loss: 0.9476045966148376:  25%|██▌       | 6584/25880 [1:22:47<4:05:09,  1.31it/s]
1|6585|Loss: 0.9476045966148376:  25%|██▌       | 6585/25880 [1:22:48<4:10:27,  1.28it/s]
1|6586|Loss: 0.9507688879966736:  25%|██▌       | 6585/25880 [1:22:48<4:10:27,  1.28it/s]
1|6586|Loss: 0.9507688879966736:  25%|██▌       | 6586/25880 [1:22:49<4:09:18,  1.29it/s]
1|6587|Loss: 0.977981448173523:  25%|██▌       | 6586/25880 [1:22:49<4:09:18,  1.29it/s] 
1|6587|Loss: 0.977981448173523:  25%|██▌       | 6587/25880 [1:22:49<3:54:14,  1.37it/s]
1|6588|Loss: 0.8996777534484863:  25%|██▌       | 6587/25880 [1:22:50<3:54:14,  1.37it/s]
1|6588|Loss: 0.8996777534484863:  25%|██▌       | 6588/25880 [1:22:50<4:09:13,  1.29it/s]
1|6589|Loss: 0.872402548789978:  25%|██▌       | 6588/25880 [1:22:50<4:09:13,  1.29it/s] 
1|6589|Loss: 0.872402548789978:  25%|██▌       | 6589/25880 [1:22:51<4:02:30,  1.33it/s]
1|6590|Loss: 0.7854928970336914:  25%|██▌       | 6589/25880 [1:22:51<4:02:30,  1.33it/s]
1|6590|Loss: 0.7854928970336914:  25%|██▌       | 6590/25880 [1:22:51<3:36:58,  1.48it/s]
1|6591|Loss: 0.9605628252029419:  25%|██▌       | 6590/25880 [1:22:52<3:36:58,  1.48it/s]
1|6591|Loss: 0.9605628252029419:  25%|██▌       | 6591/25880 [1:22:52<3:55:06,  1.37it/s]
1|6592|Loss: 0.8705820441246033:  25%|██▌       | 6591/25880 [1:22:53<3:55:06,  1.37it/s]
1|6592|Loss: 0.8705820441246033:  25%|██▌       | 6592/25880 [1:22:53<4:07:17,  1.30it/s]
1|6593|Loss: 0.8463382720947266:  25%|██▌       | 6592/25880 [1:22:53<4:07:17,  1.30it/s]
1|6593|Loss: 0.8463382720947266:  25%|██▌       | 6593/25880 [1:22:54<4:05:32,  1.31it/s]
1|6594|Loss: 0.9426106214523315:  25%|██▌       | 6593/25880 [1:22:54<4:05:32,  1.31it/s]
1|6594|Loss: 0.9426106214523315:  25%|██▌       | 6594/25880 [1:22:54<3:47:08,  1.42it/s]
1|6595|Loss: 0.8168379068374634:  25%|██▌       | 6594/25880 [1:22:55<3:47:08,  1.42it/s]
1|6595|Loss: 0.8168379068374634:  25%|██▌       | 6595/25880 [1:22:55<3:36:40,  1.48it/s]
1|6596|Loss: 0.7651033401489258:  25%|██▌       | 6595/25880 [1:22:55<3:36:40,  1.48it/s]
1|6596|Loss: 0.7651033401489258:  25%|██▌       | 6596/25880 [1:22:56<3:40:16,  1.46it/s]
1|6597|Loss: 0.7923921346664429:  25%|██▌       | 6596/25880 [1:22:56<3:40:16,  1.46it/s]
1|6597|Loss: 0.7923921346664429:  25%|██▌       | 6597/25880 [1:22:56<3:53:39,  1.38it/s]
1|6598|Loss: 0.8316180109977722:  25%|██▌       | 6597/25880 [1:22:57<3:53:39,  1.38it/s]
1|6598|Loss: 0.8316180109977722:  25%|██▌       | 6598/25880 [1:22:57<3:54:09,  1.37it/s]
1|6599|Loss: 0.8347035646438599:  25%|██▌       | 6598/25880 [1:22:57<3:54:09,  1.37it/s]
1|6599|Loss: 0.8347035646438599:  25%|██▌       | 6599/25880 [1:22:58<3:44:41,  1.43it/s]
1|6600|Loss: 0.792248010635376:  25%|██▌       | 6599/25880 [1:22:58<3:44:41,  1.43it/s] 
1|6600|Loss: 0.792248010635376:  26%|██▌       | 6600/25880 [1:22:58<3:36:49,  1.48it/s]
1|6601|Loss: 0.7944244742393494:  26%|██▌       | 6600/25880 [1:22:59<3:36:49,  1.48it/s]
1|6601|Loss: 0.7944244742393494:  26%|██▌       | 6601/25880 [1:22:59<3:24:41,  1.57it/s]
1|6602|Loss: 0.7032868266105652:  26%|██▌       | 6601/25880 [1:22:59<3:24:41,  1.57it/s]
1|6602|Loss: 0.7032868266105652:  26%|██▌       | 6602/25880 [1:23:00<3:22:43,  1.58it/s]
1|6603|Loss: 0.7873930335044861:  26%|██▌       | 6602/25880 [1:23:00<3:22:43,  1.58it/s]
1|6603|Loss: 0.7873930335044861:  26%|██▌       | 6603/25880 [1:23:00<3:15:27,  1.64it/s]
1|6604|Loss: 0.8998865485191345:  26%|██▌       | 6603/25880 [1:23:00<3:15:27,  1.64it/s]
1|6604|Loss: 0.8998865485191345:  26%|██▌       | 6604/25880 [1:23:01<3:31:00,  1.52it/s]
1|6605|Loss: 0.8429433703422546:  26%|██▌       | 6604/25880 [1:23:01<3:31:00,  1.52it/s]
1|6605|Loss: 0.8429433703422546:  26%|██▌       | 6605/25880 [1:23:02<3:39:52,  1.46it/s]
1|6606|Loss: 0.9905986189842224:  26%|██▌       | 6605/25880 [1:23:02<3:39:52,  1.46it/s]
1|6606|Loss: 0.9905986189842224:  26%|██▌       | 6606/25880 [1:23:02<3:49:30,  1.40it/s]
1|6607|Loss: 1.1267638206481934:  26%|██▌       | 6606/25880 [1:23:03<3:49:30,  1.40it/s]
1|6607|Loss: 1.1267638206481934:  26%|██▌       | 6607/25880 [1:23:03<3:53:58,  1.37it/s]
1|6608|Loss: 0.849940299987793:  26%|██▌       | 6607/25880 [1:23:04<3:53:58,  1.37it/s] 
1|6608|Loss: 0.849940299987793:  26%|██▌       | 6608/25880 [1:23:04<3:47:46,  1.41it/s]
1|6609|Loss: 0.6869024634361267:  26%|██▌       | 6608/25880 [1:23:04<3:47:46,  1.41it/s]
1|6609|Loss: 0.6869024634361267:  26%|██▌       | 6609/25880 [1:23:05<3:57:04,  1.35it/s]
1|6610|Loss: 1.034414291381836:  26%|██▌       | 6609/25880 [1:23:05<3:57:04,  1.35it/s] 
1|6610|Loss: 1.034414291381836:  26%|██▌       | 6610/25880 [1:23:05<3:43:30,  1.44it/s]
1|6611|Loss: 0.7992917895317078:  26%|██▌       | 6610/25880 [1:23:06<3:43:30,  1.44it/s]
1|6611|Loss: 0.7992917895317078:  26%|██▌       | 6611/25880 [1:23:06<3:42:47,  1.44it/s]
1|6612|Loss: 0.7708732485771179:  26%|██▌       | 6611/25880 [1:23:06<3:42:47,  1.44it/s]
1|6612|Loss: 0.7708732485771179:  26%|██▌       | 6612/25880 [1:23:07<3:45:48,  1.42it/s]
1|6613|Loss: 0.6767881512641907:  26%|██▌       | 6612/25880 [1:23:07<3:45:48,  1.42it/s]
1|6613|Loss: 0.6767881512641907:  26%|██▌       | 6613/25880 [1:23:07<3:57:27,  1.35it/s]
1|6614|Loss: 0.8120492696762085:  26%|██▌       | 6613/25880 [1:23:08<3:57:27,  1.35it/s]
1|6614|Loss: 0.8120492696762085:  26%|██▌       | 6614/25880 [1:23:08<3:59:24,  1.34it/s]
1|6615|Loss: 0.7077484130859375:  26%|██▌       | 6614/25880 [1:23:09<3:59:24,  1.34it/s]
1|6615|Loss: 0.7077484130859375:  26%|██▌       | 6615/25880 [1:23:09<3:36:48,  1.48it/s]
1|6616|Loss: 0.8480521440505981:  26%|██▌       | 6615/25880 [1:23:09<3:36:48,  1.48it/s]
1|6616|Loss: 0.8480521440505981:  26%|██▌       | 6616/25880 [1:23:09<3:33:57,  1.50it/s]
1|6617|Loss: 0.8537241816520691:  26%|██▌       | 6616/25880 [1:23:10<3:33:57,  1.50it/s]
1|6617|Loss: 0.8537241816520691:  26%|██▌       | 6617/25880 [1:23:10<3:36:47,  1.48it/s]
1|6618|Loss: 0.9460752010345459:  26%|██▌       | 6617/25880 [1:23:10<3:36:47,  1.48it/s]
1|6618|Loss: 0.9460752010345459:  26%|██▌       | 6618/25880 [1:23:11<3:41:01,  1.45it/s]
1|6619|Loss: 0.9608603119850159:  26%|██▌       | 6618/25880 [1:23:11<3:41:01,  1.45it/s]
1|6619|Loss: 0.9608603119850159:  26%|██▌       | 6619/25880 [1:23:11<3:23:02,  1.58it/s]
1|6620|Loss: 0.7407161593437195:  26%|██▌       | 6619/25880 [1:23:12<3:23:02,  1.58it/s]
1|6620|Loss: 0.7407161593437195:  26%|██▌       | 6620/25880 [1:23:12<3:24:09,  1.57it/s]
1|6621|Loss: 0.9044579267501831:  26%|██▌       | 6620/25880 [1:23:12<3:24:09,  1.57it/s]
1|6621|Loss: 0.9044579267501831:  26%|██▌       | 6621/25880 [1:23:13<3:32:21,  1.51it/s]
1|6622|Loss: 0.7930312752723694:  26%|██▌       | 6621/25880 [1:23:13<3:32:21,  1.51it/s]
1|6622|Loss: 0.7930312752723694:  26%|██▌       | 6622/25880 [1:23:13<3:32:27,  1.51it/s]
1|6623|Loss: 0.8778824806213379:  26%|██▌       | 6622/25880 [1:23:14<3:32:27,  1.51it/s]
1|6623|Loss: 0.8778824806213379:  26%|██▌       | 6623/25880 [1:23:14<3:28:56,  1.54it/s]
1|6624|Loss: 0.9555897116661072:  26%|██▌       | 6623/25880 [1:23:14<3:28:56,  1.54it/s]
1|6624|Loss: 0.9555897116661072:  26%|██▌       | 6624/25880 [1:23:15<3:27:32,  1.55it/s]
1|6625|Loss: 0.7566812038421631:  26%|██▌       | 6624/25880 [1:23:15<3:27:32,  1.55it/s]
1|6625|Loss: 0.7566812038421631:  26%|██▌       | 6625/25880 [1:23:15<3:51:50,  1.38it/s]
1|6626|Loss: 0.8066872954368591:  26%|██▌       | 6625/25880 [1:23:16<3:51:50,  1.38it/s]
1|6626|Loss: 0.8066872954368591:  26%|██▌       | 6626/25880 [1:23:16<4:05:02,  1.31it/s]
1|6627|Loss: 0.8605054616928101:  26%|██▌       | 6626/25880 [1:23:17<4:05:02,  1.31it/s]
1|6627|Loss: 0.8605054616928101:  26%|██▌       | 6627/25880 [1:23:17<4:03:17,  1.32it/s]
1|6628|Loss: 0.9302979111671448:  26%|██▌       | 6627/25880 [1:23:17<4:03:17,  1.32it/s]
1|6628|Loss: 0.9302979111671448:  26%|██▌       | 6628/25880 [1:23:18<3:51:08,  1.39it/s]
1|6629|Loss: 0.8267567753791809:  26%|██▌       | 6628/25880 [1:23:18<3:51:08,  1.39it/s]
1|6629|Loss: 0.8267567753791809:  26%|██▌       | 6629/25880 [1:23:18<3:40:42,  1.45it/s]
1|6630|Loss: 0.9154953360557556:  26%|██▌       | 6629/25880 [1:23:19<3:40:42,  1.45it/s]
1|6630|Loss: 0.9154953360557556:  26%|██▌       | 6630/25880 [1:23:19<3:35:38,  1.49it/s]
1|6631|Loss: 0.9200130701065063:  26%|██▌       | 6630/25880 [1:23:19<3:35:38,  1.49it/s]
1|6631|Loss: 0.9200130701065063:  26%|██▌       | 6631/25880 [1:23:20<3:40:37,  1.45it/s]
1|6632|Loss: 0.80765700340271:  26%|██▌       | 6631/25880 [1:23:20<3:40:37,  1.45it/s]  
1|6632|Loss: 0.80765700340271:  26%|██▌       | 6632/25880 [1:23:20<3:29:56,  1.53it/s]
1|6633|Loss: 1.098151683807373:  26%|██▌       | 6632/25880 [1:23:21<3:29:56,  1.53it/s]
1|6633|Loss: 1.098151683807373:  26%|██▌       | 6633/25880 [1:23:21<3:34:08,  1.50it/s]
1|6634|Loss: 1.001933217048645:  26%|██▌       | 6633/25880 [1:23:21<3:34:08,  1.50it/s]
1|6634|Loss: 1.001933217048645:  26%|██▌       | 6634/25880 [1:23:22<3:32:43,  1.51it/s]
1|6635|Loss: 0.9672693014144897:  26%|██▌       | 6634/25880 [1:23:22<3:32:43,  1.51it/s]
1|6635|Loss: 0.9672693014144897:  26%|██▌       | 6635/25880 [1:23:22<3:37:41,  1.47it/s]
1|6636|Loss: 0.9176666736602783:  26%|██▌       | 6635/25880 [1:23:23<3:37:41,  1.47it/s]
1|6636|Loss: 0.9176666736602783:  26%|██▌       | 6636/25880 [1:23:23<3:41:27,  1.45it/s]
1|6637|Loss: 0.87738037109375:  26%|██▌       | 6636/25880 [1:23:23<3:41:27,  1.45it/s]  
1|6637|Loss: 0.87738037109375:  26%|██▌       | 6637/25880 [1:23:24<3:42:34,  1.44it/s]
1|6638|Loss: 0.768720805644989:  26%|██▌       | 6637/25880 [1:23:24<3:42:34,  1.44it/s]
1|6638|Loss: 0.768720805644989:  26%|██▌       | 6638/25880 [1:23:24<3:46:35,  1.42it/s]
1|6639|Loss: 0.9264177083969116:  26%|██▌       | 6638/25880 [1:23:25<3:46:35,  1.42it/s]
1|6639|Loss: 0.9264177083969116:  26%|██▌       | 6639/25880 [1:23:25<3:54:25,  1.37it/s]
1|6640|Loss: 0.7527406811714172:  26%|██▌       | 6639/25880 [1:23:26<3:54:25,  1.37it/s]
1|6640|Loss: 0.7527406811714172:  26%|██▌       | 6640/25880 [1:23:26<4:05:45,  1.30it/s]
1|6641|Loss: 0.8426635265350342:  26%|██▌       | 6640/25880 [1:23:26<4:05:45,  1.30it/s]
1|6641|Loss: 0.8426635265350342:  26%|██▌       | 6641/25880 [1:23:27<3:46:35,  1.42it/s]
1|6642|Loss: 0.8308087587356567:  26%|██▌       | 6641/25880 [1:23:27<3:46:35,  1.42it/s]
1|6642|Loss: 0.8308087587356567:  26%|██▌       | 6642/25880 [1:23:27<3:43:29,  1.43it/s]
1|6643|Loss: 0.8494561314582825:  26%|██▌       | 6642/25880 [1:23:28<3:43:29,  1.43it/s]
1|6643|Loss: 0.8494561314582825:  26%|██▌       | 6643/25880 [1:23:28<3:25:29,  1.56it/s]
1|6644|Loss: 0.767439603805542:  26%|██▌       | 6643/25880 [1:23:28<3:25:29,  1.56it/s] 
1|6644|Loss: 0.767439603805542:  26%|██▌       | 6644/25880 [1:23:28<3:17:30,  1.62it/s]
1|6645|Loss: 0.7342042922973633:  26%|██▌       | 6644/25880 [1:23:29<3:17:30,  1.62it/s]
1|6645|Loss: 0.7342042922973633:  26%|██▌       | 6645/25880 [1:23:29<3:25:13,  1.56it/s]
1|6646|Loss: 0.9056965708732605:  26%|██▌       | 6645/25880 [1:23:30<3:25:13,  1.56it/s]
1|6646|Loss: 0.9056965708732605:  26%|██▌       | 6646/25880 [1:23:30<3:31:33,  1.52it/s]
1|6647|Loss: 0.6652939319610596:  26%|██▌       | 6646/25880 [1:23:30<3:31:33,  1.52it/s]
1|6647|Loss: 0.6652939319610596:  26%|██▌       | 6647/25880 [1:23:30<3:28:23,  1.54it/s]
1|6648|Loss: 0.8393981456756592:  26%|██▌       | 6647/25880 [1:23:31<3:28:23,  1.54it/s]
1|6648|Loss: 0.8393981456756592:  26%|██▌       | 6648/25880 [1:23:31<3:31:20,  1.52it/s]
1|6649|Loss: 0.7907230257987976:  26%|██▌       | 6648/25880 [1:23:32<3:31:20,  1.52it/s]
1|6649|Loss: 0.7907230257987976:  26%|██▌       | 6649/25880 [1:23:32<3:55:25,  1.36it/s]
1|6650|Loss: 0.8764274716377258:  26%|██▌       | 6649/25880 [1:23:32<3:55:25,  1.36it/s]
1|6650|Loss: 0.8764274716377258:  26%|██▌       | 6650/25880 [1:23:33<3:42:31,  1.44it/s]
1|6651|Loss: 0.8783855438232422:  26%|██▌       | 6650/25880 [1:23:33<3:42:31,  1.44it/s]
1|6651|Loss: 0.8783855438232422:  26%|██▌       | 6651/25880 [1:23:33<3:42:02,  1.44it/s]
1|6652|Loss: 0.7469044923782349:  26%|██▌       | 6651/25880 [1:23:34<3:42:02,  1.44it/s]
1|6652|Loss: 0.7469044923782349:  26%|██▌       | 6652/25880 [1:23:34<3:46:46,  1.41it/s]
1|6653|Loss: 0.8348826766014099:  26%|██▌       | 6652/25880 [1:23:35<3:46:46,  1.41it/s]
1|6653|Loss: 0.8348826766014099:  26%|██▌       | 6653/25880 [1:23:35<3:52:59,  1.38it/s]
1|6654|Loss: 0.9040011763572693:  26%|██▌       | 6653/25880 [1:23:35<3:52:59,  1.38it/s]
1|6654|Loss: 0.9040011763572693:  26%|██▌       | 6654/25880 [1:23:36<4:02:06,  1.32it/s]
1|6655|Loss: 1.066818118095398:  26%|██▌       | 6654/25880 [1:23:36<4:02:06,  1.32it/s] 
1|6655|Loss: 1.066818118095398:  26%|██▌       | 6655/25880 [1:23:36<4:01:59,  1.32it/s]
1|6656|Loss: 0.8326035737991333:  26%|██▌       | 6655/25880 [1:23:37<4:01:59,  1.32it/s]
1|6656|Loss: 0.8326035737991333:  26%|██▌       | 6656/25880 [1:23:37<4:01:28,  1.33it/s]
1|6657|Loss: 1.0010470151901245:  26%|██▌       | 6656/25880 [1:23:38<4:01:28,  1.33it/s]
1|6657|Loss: 1.0010470151901245:  26%|██▌       | 6657/25880 [1:23:38<4:07:40,  1.29it/s]
1|6658|Loss: 0.8754585385322571:  26%|██▌       | 6657/25880 [1:23:38<4:07:40,  1.29it/s]
1|6658|Loss: 0.8754585385322571:  26%|██▌       | 6658/25880 [1:23:39<4:03:18,  1.32it/s]
1|6659|Loss: 0.8456699848175049:  26%|██▌       | 6658/25880 [1:23:39<4:03:18,  1.32it/s]
1|6659|Loss: 0.8456699848175049:  26%|██▌       | 6659/25880 [1:23:39<3:45:48,  1.42it/s]
1|6660|Loss: 0.8624879121780396:  26%|██▌       | 6659/25880 [1:23:40<3:45:48,  1.42it/s]
1|6660|Loss: 0.8624879121780396:  26%|██▌       | 6660/25880 [1:23:40<3:33:31,  1.50it/s]
1|6661|Loss: 0.8861719369888306:  26%|██▌       | 6660/25880 [1:23:40<3:33:31,  1.50it/s]
1|6661|Loss: 0.8861719369888306:  26%|██▌       | 6661/25880 [1:23:41<3:36:30,  1.48it/s]
1|6662|Loss: 0.8519443869590759:  26%|██▌       | 6661/25880 [1:23:41<3:36:30,  1.48it/s]
1|6662|Loss: 0.8519443869590759:  26%|██▌       | 6662/25880 [1:23:41<3:51:06,  1.39it/s]
1|6663|Loss: 0.9407748579978943:  26%|██▌       | 6662/25880 [1:23:42<3:51:06,  1.39it/s]
1|6663|Loss: 0.9407748579978943:  26%|██▌       | 6663/25880 [1:23:42<3:55:52,  1.36it/s]
1|6664|Loss: 0.9454017281532288:  26%|██▌       | 6663/25880 [1:23:43<3:55:52,  1.36it/s]
1|6664|Loss: 0.9454017281532288:  26%|██▌       | 6664/25880 [1:23:43<3:55:57,  1.36it/s]
1|6665|Loss: 0.946389377117157:  26%|██▌       | 6664/25880 [1:23:43<3:55:57,  1.36it/s] 
1|6665|Loss: 0.946389377117157:  26%|██▌       | 6665/25880 [1:23:44<3:53:28,  1.37it/s]
1|6666|Loss: 0.8151707649230957:  26%|██▌       | 6665/25880 [1:23:44<3:53:28,  1.37it/s]
1|6666|Loss: 0.8151707649230957:  26%|██▌       | 6666/25880 [1:23:44<3:58:36,  1.34it/s]
1|6667|Loss: 0.8651716709136963:  26%|██▌       | 6666/25880 [1:23:45<3:58:36,  1.34it/s]
1|6667|Loss: 0.8651716709136963:  26%|██▌       | 6667/25880 [1:23:45<4:16:48,  1.25it/s]
1|6668|Loss: 0.9218221306800842:  26%|██▌       | 6667/25880 [1:23:46<4:16:48,  1.25it/s]
1|6668|Loss: 0.9218221306800842:  26%|██▌       | 6668/25880 [1:23:46<4:22:11,  1.22it/s]
1|6669|Loss: 0.8400837182998657:  26%|██▌       | 6668/25880 [1:23:47<4:22:11,  1.22it/s]
1|6669|Loss: 0.8400837182998657:  26%|██▌       | 6669/25880 [1:23:47<4:16:33,  1.25it/s]
1|6670|Loss: 1.0258311033248901:  26%|██▌       | 6669/25880 [1:23:47<4:16:33,  1.25it/s]
1|6670|Loss: 1.0258311033248901:  26%|██▌       | 6670/25880 [1:23:48<4:19:50,  1.23it/s]
1|6671|Loss: 0.9585404992103577:  26%|██▌       | 6670/25880 [1:23:48<4:19:50,  1.23it/s]
1|6671|Loss: 0.9585404992103577:  26%|██▌       | 6671/25880 [1:23:48<3:58:06,  1.34it/s]
1|6672|Loss: 0.8114300966262817:  26%|██▌       | 6671/25880 [1:23:49<3:58:06,  1.34it/s]
1|6672|Loss: 0.8114300966262817:  26%|██▌       | 6672/25880 [1:23:49<4:03:26,  1.32it/s]
1|6673|Loss: 0.8124533891677856:  26%|██▌       | 6672/25880 [1:23:50<4:03:26,  1.32it/s]
1|6673|Loss: 0.8124533891677856:  26%|██▌       | 6673/25880 [1:23:50<3:42:45,  1.44it/s]
1|6674|Loss: 0.7483518719673157:  26%|██▌       | 6673/25880 [1:23:50<3:42:45,  1.44it/s]
1|6674|Loss: 0.7483518719673157:  26%|██▌       | 6674/25880 [1:23:50<3:41:06,  1.45it/s]
1|6675|Loss: 0.8447975516319275:  26%|██▌       | 6674/25880 [1:23:51<3:41:06,  1.45it/s]
1|6675|Loss: 0.8447975516319275:  26%|██▌       | 6675/25880 [1:23:51<3:51:39,  1.38it/s]
1|6676|Loss: 0.7890473008155823:  26%|██▌       | 6675/25880 [1:23:52<3:51:39,  1.38it/s]
1|6676|Loss: 0.7890473008155823:  26%|██▌       | 6676/25880 [1:23:52<3:36:44,  1.48it/s]
1|6677|Loss: 0.8256940841674805:  26%|██▌       | 6676/25880 [1:23:52<3:36:44,  1.48it/s]
1|6677|Loss: 0.8256940841674805:  26%|██▌       | 6677/25880 [1:23:52<3:35:46,  1.48it/s]
1|6678|Loss: 0.8702038526535034:  26%|██▌       | 6677/25880 [1:23:53<3:35:46,  1.48it/s]
1|6678|Loss: 0.8702038526535034:  26%|██▌       | 6678/25880 [1:23:53<3:27:21,  1.54it/s]
1|6679|Loss: 0.8606315851211548:  26%|██▌       | 6678/25880 [1:23:53<3:27:21,  1.54it/s]
1|6679|Loss: 0.8606315851211548:  26%|██▌       | 6679/25880 [1:23:54<3:24:55,  1.56it/s]
1|6680|Loss: 0.9190199375152588:  26%|██▌       | 6679/25880 [1:23:54<3:24:55,  1.56it/s]
1|6680|Loss: 0.9190199375152588:  26%|██▌       | 6680/25880 [1:23:54<3:18:28,  1.61it/s]
1|6681|Loss: 0.834189772605896:  26%|██▌       | 6680/25880 [1:23:55<3:18:28,  1.61it/s] 
1|6681|Loss: 0.834189772605896:  26%|██▌       | 6681/25880 [1:23:55<3:16:39,  1.63it/s]
1|6682|Loss: 0.8418489098548889:  26%|██▌       | 6681/25880 [1:23:55<3:16:39,  1.63it/s]
1|6682|Loss: 0.8418489098548889:  26%|██▌       | 6682/25880 [1:23:56<3:23:21,  1.57it/s]
1|6683|Loss: 0.9340859055519104:  26%|██▌       | 6682/25880 [1:23:56<3:23:21,  1.57it/s]
1|6683|Loss: 0.9340859055519104:  26%|██▌       | 6683/25880 [1:23:56<3:39:53,  1.46it/s]
1|6684|Loss: 0.9581509828567505:  26%|██▌       | 6683/25880 [1:23:57<3:39:53,  1.46it/s]
1|6684|Loss: 0.9581509828567505:  26%|██▌       | 6684/25880 [1:23:57<3:37:46,  1.47it/s]
1|6685|Loss: 0.8122488856315613:  26%|██▌       | 6684/25880 [1:23:57<3:37:46,  1.47it/s]
1|6685|Loss: 0.8122488856315613:  26%|██▌       | 6685/25880 [1:23:58<3:51:07,  1.38it/s]
1|6686|Loss: 0.8724306225776672:  26%|██▌       | 6685/25880 [1:23:58<3:51:07,  1.38it/s]
1|6686|Loss: 0.8724306225776672:  26%|██▌       | 6686/25880 [1:23:58<3:43:46,  1.43it/s]
1|6687|Loss: 0.7993438839912415:  26%|██▌       | 6686/25880 [1:23:59<3:43:46,  1.43it/s]
1|6687|Loss: 0.7993438839912415:  26%|██▌       | 6687/25880 [1:23:59<3:52:40,  1.37it/s]
1|6688|Loss: 0.8798061013221741:  26%|██▌       | 6687/25880 [1:24:00<3:52:40,  1.37it/s]
1|6688|Loss: 0.8798061013221741:  26%|██▌       | 6688/25880 [1:24:00<3:53:42,  1.37it/s]
1|6689|Loss: 1.0259839296340942:  26%|██▌       | 6688/25880 [1:24:00<3:53:42,  1.37it/s]
1|6689|Loss: 1.0259839296340942:  26%|██▌       | 6689/25880 [1:24:01<4:03:37,  1.31it/s]
1|6690|Loss: 0.846067488193512:  26%|██▌       | 6689/25880 [1:24:01<4:03:37,  1.31it/s] 
1|6690|Loss: 0.846067488193512:  26%|██▌       | 6690/25880 [1:24:02<4:11:43,  1.27it/s]
1|6691|Loss: 0.8179407715797424:  26%|██▌       | 6690/25880 [1:24:02<4:11:43,  1.27it/s]
1|6691|Loss: 0.8179407715797424:  26%|██▌       | 6691/25880 [1:24:02<3:59:10,  1.34it/s]
1|6692|Loss: 0.7861669659614563:  26%|██▌       | 6691/25880 [1:24:03<3:59:10,  1.34it/s]
1|6692|Loss: 0.7861669659614563:  26%|██▌       | 6692/25880 [1:24:03<3:54:47,  1.36it/s]
1|6693|Loss: 0.9269232749938965:  26%|██▌       | 6692/25880 [1:24:03<3:54:47,  1.36it/s]
1|6693|Loss: 0.9269232749938965:  26%|██▌       | 6693/25880 [1:24:04<3:45:08,  1.42it/s]
1|6694|Loss: 0.9274454712867737:  26%|██▌       | 6693/25880 [1:24:04<3:45:08,  1.42it/s]
1|6694|Loss: 0.9274454712867737:  26%|██▌       | 6694/25880 [1:24:04<3:33:20,  1.50it/s]
1|6695|Loss: 0.8062410950660706:  26%|██▌       | 6694/25880 [1:24:05<3:33:20,  1.50it/s]
1|6695|Loss: 0.8062410950660706:  26%|██▌       | 6695/25880 [1:24:05<3:34:55,  1.49it/s]
1|6696|Loss: 0.8267786502838135:  26%|██▌       | 6695/25880 [1:24:05<3:34:55,  1.49it/s]
1|6696|Loss: 0.8267786502838135:  26%|██▌       | 6696/25880 [1:24:06<3:33:06,  1.50it/s]
1|6697|Loss: 0.8422738313674927:  26%|██▌       | 6696/25880 [1:24:06<3:33:06,  1.50it/s]
1|6697|Loss: 0.8422738313674927:  26%|██▌       | 6697/25880 [1:24:06<3:52:03,  1.38it/s]
1|6698|Loss: 0.8107350468635559:  26%|██▌       | 6697/25880 [1:24:07<3:52:03,  1.38it/s]
1|6698|Loss: 0.8107350468635559:  26%|██▌       | 6698/25880 [1:24:07<3:57:20,  1.35it/s]
1|6699|Loss: 0.811147928237915:  26%|██▌       | 6698/25880 [1:24:08<3:57:20,  1.35it/s] 
1|6699|Loss: 0.811147928237915:  26%|██▌       | 6699/25880 [1:24:08<3:41:42,  1.44it/s]
1|6700|Loss: 0.7523130774497986:  26%|██▌       | 6699/25880 [1:24:08<3:41:42,  1.44it/s]
1|6700|Loss: 0.7523130774497986:  26%|██▌       | 6700/25880 [1:24:08<3:34:22,  1.49it/s]
1|6701|Loss: 0.8741769790649414:  26%|██▌       | 6700/25880 [1:24:09<3:34:22,  1.49it/s]
1|6701|Loss: 0.8741769790649414:  26%|██▌       | 6701/25880 [1:24:09<3:38:45,  1.46it/s]
1|6702|Loss: 0.9374613165855408:  26%|██▌       | 6701/25880 [1:24:10<3:38:45,  1.46it/s]
1|6702|Loss: 0.9374613165855408:  26%|██▌       | 6702/25880 [1:24:10<3:43:53,  1.43it/s]
1|6703|Loss: 0.8922220468521118:  26%|██▌       | 6702/25880 [1:24:10<3:43:53,  1.43it/s]
1|6703|Loss: 0.8922220468521118:  26%|██▌       | 6703/25880 [1:24:11<3:44:40,  1.42it/s]
1|6704|Loss: 0.9196121096611023:  26%|██▌       | 6703/25880 [1:24:11<3:44:40,  1.42it/s]
1|6704|Loss: 0.9196121096611023:  26%|██▌       | 6704/25880 [1:24:11<4:01:10,  1.33it/s]
1|6705|Loss: 0.7831263542175293:  26%|██▌       | 6704/25880 [1:24:12<4:01:10,  1.33it/s]
1|6705|Loss: 0.7831263542175293:  26%|██▌       | 6705/25880 [1:24:12<4:02:35,  1.32it/s]
1|6706|Loss: 0.7039908766746521:  26%|██▌       | 6705/25880 [1:24:13<4:02:35,  1.32it/s]
1|6706|Loss: 0.7039908766746521:  26%|██▌       | 6706/25880 [1:24:13<4:05:10,  1.30it/s]
1|6707|Loss: 0.9145997762680054:  26%|██▌       | 6706/25880 [1:24:13<4:05:10,  1.30it/s]
1|6707|Loss: 0.9145997762680054:  26%|██▌       | 6707/25880 [1:24:14<3:54:26,  1.36it/s]
1|6708|Loss: 0.9204378128051758:  26%|██▌       | 6707/25880 [1:24:14<3:54:26,  1.36it/s]
1|6708|Loss: 0.9204378128051758:  26%|██▌       | 6708/25880 [1:24:14<3:44:47,  1.42it/s]
1|6709|Loss: 0.7027103304862976:  26%|██▌       | 6708/25880 [1:24:15<3:44:47,  1.42it/s]
1|6709|Loss: 0.7027103304862976:  26%|██▌       | 6709/25880 [1:24:15<3:43:42,  1.43it/s]
1|6710|Loss: 0.8150492310523987:  26%|██▌       | 6709/25880 [1:24:15<3:43:42,  1.43it/s]
1|6710|Loss: 0.8150492310523987:  26%|██▌       | 6710/25880 [1:24:16<3:53:42,  1.37it/s]
1|6711|Loss: 0.7518684267997742:  26%|██▌       | 6710/25880 [1:24:16<3:53:42,  1.37it/s]
1|6711|Loss: 0.7518684267997742:  26%|██▌       | 6711/25880 [1:24:16<3:48:16,  1.40it/s]
1|6712|Loss: 0.8767500519752502:  26%|██▌       | 6711/25880 [1:24:17<3:48:16,  1.40it/s]
1|6712|Loss: 0.8767500519752502:  26%|██▌       | 6712/25880 [1:24:17<3:39:46,  1.45it/s]
1|6713|Loss: 0.7203603386878967:  26%|██▌       | 6712/25880 [1:24:17<3:39:46,  1.45it/s]
1|6713|Loss: 0.7203603386878967:  26%|██▌       | 6713/25880 [1:24:18<3:34:53,  1.49it/s]
1|6714|Loss: 0.8980178236961365:  26%|██▌       | 6713/25880 [1:24:18<3:34:53,  1.49it/s]
1|6714|Loss: 0.8980178236961365:  26%|██▌       | 6714/25880 [1:24:18<3:31:54,  1.51it/s]
1|6715|Loss: 0.7793527245521545:  26%|██▌       | 6714/25880 [1:24:19<3:31:54,  1.51it/s]
1|6715|Loss: 0.7793527245521545:  26%|██▌       | 6715/25880 [1:24:19<3:36:11,  1.48it/s]
1|6716|Loss: 0.749061107635498:  26%|██▌       | 6715/25880 [1:24:20<3:36:11,  1.48it/s] 
1|6716|Loss: 0.749061107635498:  26%|██▌       | 6716/25880 [1:24:20<3:45:13,  1.42it/s]
1|6717|Loss: 0.7705743908882141:  26%|██▌       | 6716/25880 [1:24:20<3:45:13,  1.42it/s]
1|6717|Loss: 0.7705743908882141:  26%|██▌       | 6717/25880 [1:24:21<3:49:01,  1.39it/s]
1|6718|Loss: 0.7344164848327637:  26%|██▌       | 6717/25880 [1:24:21<3:49:01,  1.39it/s]
1|6718|Loss: 0.7344164848327637:  26%|██▌       | 6718/25880 [1:24:21<3:41:32,  1.44it/s]
1|6719|Loss: 0.8956827521324158:  26%|██▌       | 6718/25880 [1:24:22<3:41:32,  1.44it/s]
1|6719|Loss: 0.8956827521324158:  26%|██▌       | 6719/25880 [1:24:22<3:36:06,  1.48it/s]
1|6720|Loss: 0.9734074473381042:  26%|██▌       | 6719/25880 [1:24:22<3:36:06,  1.48it/s]
1|6720|Loss: 0.9734074473381042:  26%|██▌       | 6720/25880 [1:24:22<3:21:04,  1.59it/s]
1|6721|Loss: 0.9317576289176941:  26%|██▌       | 6720/25880 [1:24:23<3:21:04,  1.59it/s]
1|6721|Loss: 0.9317576289176941:  26%|██▌       | 6721/25880 [1:24:23<3:17:29,  1.62it/s]
1|6722|Loss: 0.8959182500839233:  26%|██▌       | 6721/25880 [1:24:23<3:17:29,  1.62it/s]
1|6722|Loss: 0.8959182500839233:  26%|██▌       | 6722/25880 [1:24:24<3:19:16,  1.60it/s]
1|6723|Loss: 1.0282373428344727:  26%|██▌       | 6722/25880 [1:24:24<3:19:16,  1.60it/s]
1|6723|Loss: 1.0282373428344727:  26%|██▌       | 6723/25880 [1:24:24<3:37:40,  1.47it/s]
1|6724|Loss: 0.7706236839294434:  26%|██▌       | 6723/25880 [1:24:25<3:37:40,  1.47it/s]
1|6724|Loss: 0.7706236839294434:  26%|██▌       | 6724/25880 [1:24:25<3:45:18,  1.42it/s]
1|6725|Loss: 0.8288924098014832:  26%|██▌       | 6724/25880 [1:24:26<3:45:18,  1.42it/s]
1|6725|Loss: 0.8288924098014832:  26%|██▌       | 6725/25880 [1:24:26<3:58:49,  1.34it/s]
1|6726|Loss: 0.7557589411735535:  26%|██▌       | 6725/25880 [1:24:26<3:58:49,  1.34it/s]
1|6726|Loss: 0.7557589411735535:  26%|██▌       | 6726/25880 [1:24:27<3:51:58,  1.38it/s]
1|6727|Loss: 0.9106194376945496:  26%|██▌       | 6726/25880 [1:24:27<3:51:58,  1.38it/s]
1|6727|Loss: 0.9106194376945496:  26%|██▌       | 6727/25880 [1:24:27<3:47:53,  1.40it/s]
1|6728|Loss: 1.0132421255111694:  26%|██▌       | 6727/25880 [1:24:28<3:47:53,  1.40it/s]
1|6728|Loss: 1.0132421255111694:  26%|██▌       | 6728/25880 [1:24:28<3:49:43,  1.39it/s]
1|6729|Loss: 0.8098480701446533:  26%|██▌       | 6728/25880 [1:24:29<3:49:43,  1.39it/s]
1|6729|Loss: 0.8098480701446533:  26%|██▌       | 6729/25880 [1:24:29<3:52:13,  1.37it/s]
1|6730|Loss: 0.7524386644363403:  26%|██▌       | 6729/25880 [1:24:29<3:52:13,  1.37it/s]
1|6730|Loss: 0.7524386644363403:  26%|██▌       | 6730/25880 [1:24:30<3:52:28,  1.37it/s]
1|6731|Loss: 0.8234145641326904:  26%|██▌       | 6730/25880 [1:24:30<3:52:28,  1.37it/s]
1|6731|Loss: 0.8234145641326904:  26%|██▌       | 6731/25880 [1:24:30<3:53:05,  1.37it/s]
1|6732|Loss: 0.9044919013977051:  26%|██▌       | 6731/25880 [1:24:31<3:53:05,  1.37it/s]
1|6732|Loss: 0.9044919013977051:  26%|██▌       | 6732/25880 [1:24:31<3:59:39,  1.33it/s]
1|6733|Loss: 0.8701974153518677:  26%|██▌       | 6732/25880 [1:24:32<3:59:39,  1.33it/s]
1|6733|Loss: 0.8701974153518677:  26%|██▌       | 6733/25880 [1:24:32<3:48:44,  1.40it/s]
1|6734|Loss: 0.8568963408470154:  26%|██▌       | 6733/25880 [1:24:32<3:48:44,  1.40it/s]
1|6734|Loss: 0.8568963408470154:  26%|██▌       | 6734/25880 [1:24:32<3:38:16,  1.46it/s]
1|6735|Loss: 0.8340966105461121:  26%|██▌       | 6734/25880 [1:24:33<3:38:16,  1.46it/s]
1|6735|Loss: 0.8340966105461121:  26%|██▌       | 6735/25880 [1:24:33<3:31:52,  1.51it/s]
1|6736|Loss: 0.8552125096321106:  26%|██▌       | 6735/25880 [1:24:33<3:31:52,  1.51it/s]
1|6736|Loss: 0.8552125096321106:  26%|██▌       | 6736/25880 [1:24:34<3:27:54,  1.53it/s]
1|6737|Loss: 0.7890864014625549:  26%|██▌       | 6736/25880 [1:24:34<3:27:54,  1.53it/s]
1|6737|Loss: 0.7890864014625549:  26%|██▌       | 6737/25880 [1:24:34<3:31:57,  1.51it/s]
1|6738|Loss: 0.9335306286811829:  26%|██▌       | 6737/25880 [1:24:35<3:31:57,  1.51it/s]
1|6738|Loss: 0.9335306286811829:  26%|██▌       | 6738/25880 [1:24:35<3:37:58,  1.46it/s]
1|6739|Loss: 0.7564836740493774:  26%|██▌       | 6738/25880 [1:24:35<3:37:58,  1.46it/s]
1|6739|Loss: 0.7564836740493774:  26%|██▌       | 6739/25880 [1:24:36<3:48:11,  1.40it/s]
1|6740|Loss: 0.8756229877471924:  26%|██▌       | 6739/25880 [1:24:36<3:48:11,  1.40it/s]
1|6740|Loss: 0.8756229877471924:  26%|██▌       | 6740/25880 [1:24:37<3:50:33,  1.38it/s]
1|6741|Loss: 0.8636456727981567:  26%|██▌       | 6740/25880 [1:24:37<3:50:33,  1.38it/s]
1|6741|Loss: 0.8636456727981567:  26%|██▌       | 6741/25880 [1:24:37<4:00:11,  1.33it/s]
1|6742|Loss: 0.797301709651947:  26%|██▌       | 6741/25880 [1:24:38<4:00:11,  1.33it/s] 
1|6742|Loss: 0.797301709651947:  26%|██▌       | 6742/25880 [1:24:38<3:47:21,  1.40it/s]
1|6743|Loss: 0.8264036774635315:  26%|██▌       | 6742/25880 [1:24:38<3:47:21,  1.40it/s]
1|6743|Loss: 0.8264036774635315:  26%|���█▌       | 6743/25880 [1:24:39<3:36:18,  1.47it/s]
1|6744|Loss: 0.6838809847831726:  26%|██▌       | 6743/25880 [1:24:39<3:36:18,  1.47it/s]
1|6744|Loss: 0.6838809847831726:  26%|██▌       | 6744/25880 [1:24:39<3:46:21,  1.41it/s]
1|6745|Loss: 0.9163762927055359:  26%|██▌       | 6744/25880 [1:24:40<3:46:21,  1.41it/s]
1|6745|Loss: 0.9163762927055359:  26%|██▌       | 6745/25880 [1:24:40<3:43:23,  1.43it/s]
1|6746|Loss: 0.7881792783737183:  26%|██▌       | 6745/25880 [1:24:40<3:43:23,  1.43it/s]
1|6746|Loss: 0.7881792783737183:  26%|██▌       | 6746/25880 [1:24:41<3:42:06,  1.44it/s]
1|6747|Loss: 0.7863236665725708:  26%|██▌       | 6746/25880 [1:24:41<3:42:06,  1.44it/s]
1|6747|Loss: 0.7863236665725708:  26%|██▌       | 6747/25880 [1:24:41<3:38:14,  1.46it/s]
1|6748|Loss: 0.7482893466949463:  26%|██▌       | 6747/25880 [1:24:42<3:38:14,  1.46it/s]
1|6748|Loss: 0.7482893466949463:  26%|██▌       | 6748/25880 [1:24:42<3:41:02,  1.44it/s]
1|6749|Loss: 0.8422046303749084:  26%|██▌       | 6748/25880 [1:24:43<3:41:02,  1.44it/s]
1|6749|Loss: 0.8422046303749084:  26%|██▌       | 6749/25880 [1:24:43<3:37:22,  1.47it/s]
1|6750|Loss: 0.8955188989639282:  26%|██▌       | 6749/25880 [1:24:43<3:37:22,  1.47it/s]
1|6750|Loss: 0.8955188989639282:  26%|██▌       | 6750/25880 [1:24:44<3:46:03,  1.41it/s]
1|6751|Loss: 0.8307927250862122:  26%|██▌       | 6750/25880 [1:24:44<3:46:03,  1.41it/s]
1|6751|Loss: 0.8307927250862122:  26%|██▌       | 6751/25880 [1:24:44<3:42:59,  1.43it/s]
1|6752|Loss: 0.9298984408378601:  26%|██▌       | 6751/25880 [1:24:45<3:42:59,  1.43it/s]
1|6752|Loss: 0.9298984408378601:  26%|██▌       | 6752/25880 [1:24:45<3:45:05,  1.42it/s]
1|6753|Loss: 0.8080212473869324:  26%|██▌       | 6752/25880 [1:24:45<3:45:05,  1.42it/s]
1|6753|Loss: 0.8080212473869324:  26%|██▌       | 6753/25880 [1:24:46<3:45:30,  1.41it/s]
1|6754|Loss: 0.8259279131889343:  26%|██▌       | 6753/25880 [1:24:46<3:45:30,  1.41it/s]
1|6754|Loss: 0.8259279131889343:  26%|██▌       | 6754/25880 [1:24:47<4:09:29,  1.28it/s]
1|6755|Loss: 0.7687633037567139:  26%|██▌       | 6754/25880 [1:24:47<4:09:29,  1.28it/s]
1|6755|Loss: 0.7687633037567139:  26%|██▌       | 6755/25880 [1:24:48<4:19:00,  1.23it/s]
1|6756|Loss: 0.8617787957191467:  26%|██▌       | 6755/25880 [1:24:48<4:19:00,  1.23it/s]
1|6756|Loss: 0.8617787957191467:  26%|██▌       | 6756/25880 [1:24:48<4:10:41,  1.27it/s]
1|6757|Loss: 0.7925683856010437:  26%|██▌       | 6756/25880 [1:24:49<4:10:41,  1.27it/s]
1|6757|Loss: 0.7925683856010437:  26%|██▌       | 6757/25880 [1:24:49<4:08:22,  1.28it/s]
1|6758|Loss: 0.8447830080986023:  26%|██▌       | 6757/25880 [1:24:49<4:08:22,  1.28it/s]
1|6758|Loss: 0.8447830080986023:  26%|██▌       | 6758/25880 [1:24:50<3:58:57,  1.33it/s]
1|6759|Loss: 0.9170023798942566:  26%|██▌       | 6758/25880 [1:24:50<3:58:57,  1.33it/s]
1|6759|Loss: 0.9170023798942566:  26%|██▌       | 6759/25880 [1:24:50<4:02:54,  1.31it/s]
1|6760|Loss: 0.7999322414398193:  26%|██▌       | 6759/25880 [1:24:51<4:02:54,  1.31it/s]
1|6760|Loss: 0.7999322414398193:  26%|██▌       | 6760/25880 [1:24:51<3:59:57,  1.33it/s]
1|6761|Loss: 0.9262164235115051:  26%|██▌       | 6760/25880 [1:24:52<3:59:57,  1.33it/s]
1|6761|Loss: 0.9262164235115051:  26%|██▌       | 6761/25880 [1:24:52<3:50:43,  1.38it/s]
1|6762|Loss: 0.9753864407539368:  26%|██▌       | 6761/25880 [1:24:52<3:50:43,  1.38it/s]
1|6762|Loss: 0.9753864407539368:  26%|██▌       | 6762/25880 [1:24:53<3:53:54,  1.36it/s]
1|6763|Loss: 0.8341726660728455:  26%|██▌       | 6762/25880 [1:24:53<3:53:54,  1.36it/s]
1|6763|Loss: 0.8341726660728455:  26%|██▌       | 6763/25880 [1:24:53<3:56:00,  1.35it/s]
1|6764|Loss: 0.8330168128013611:  26%|██▌       | 6763/25880 [1:24:54<3:56:00,  1.35it/s]
1|6764|Loss: 0.8330168128013611:  26%|██▌       | 6764/25880 [1:24:54<4:05:59,  1.30it/s]
1|6765|Loss: 1.0496141910552979:  26%|██▌       | 6764/25880 [1:24:55<4:05:59,  1.30it/s]
1|6765|Loss: 1.0496141910552979:  26%|██▌       | 6765/25880 [1:24:55<4:05:42,  1.30it/s]
1|6766|Loss: 0.8098642230033875:  26%|██▌       | 6765/25880 [1:24:55<4:05:42,  1.30it/s]
1|6766|Loss: 0.8098642230033875:  26%|██▌       | 6766/25880 [1:24:56<4:12:05,  1.26it/s]
1|6767|Loss: 0.7958004474639893:  26%|██▌       | 6766/25880 [1:24:56<4:12:05,  1.26it/s]
1|6767|Loss: 0.7958004474639893:  26%|██▌       | 6767/25880 [1:24:57<4:09:02,  1.28it/s]
1|6768|Loss: 0.8588898777961731:  26%|██▌       | 6767/25880 [1:24:57<4:09:02,  1.28it/s]
1|6768|Loss: 0.8588898777961731:  26%|██▌       | 6768/25880 [1:24:57<3:56:44,  1.35it/s]
1|6769|Loss: 0.8803616166114807:  26%|██▌       | 6768/25880 [1:24:58<3:56:44,  1.35it/s]
1|6769|Loss: 0.8803616166114807:  26%|██▌       | 6769/25880 [1:24:58<3:58:19,  1.34it/s]
1|6770|Loss: 1.090599536895752:  26%|██▌       | 6769/25880 [1:24:58<3:58:19,  1.34it/s] 
1|6770|Loss: 1.090599536895752:  26%|██▌       | 6770/25880 [1:24:59<3:58:31,  1.34it/s]
1|6771|Loss: 0.7406309843063354:  26%|██▌       | 6770/25880 [1:24:59<3:58:31,  1.34it/s]
1|6771|Loss: 0.7406309843063354:  26%|██▌       | 6771/25880 [1:24:59<3:48:29,  1.39it/s]
1|6772|Loss: 0.7811062335968018:  26%|██▌       | 6771/25880 [1:25:00<3:48:29,  1.39it/s]
1|6772|Loss: 0.7811062335968018:  26%|██▌       | 6772/25880 [1:25:00<3:52:14,  1.37it/s]
1|6773|Loss: 0.8832594752311707:  26%|██▌       | 6772/25880 [1:25:01<3:52:14,  1.37it/s]
1|6773|Loss: 0.8832594752311707:  26%|██▌       | 6773/25880 [1:25:01<4:03:00,  1.31it/s]
1|6774|Loss: 0.8654148578643799:  26%|██▌       | 6773/25880 [1:25:01<4:03:00,  1.31it/s]
1|6774|Loss: 0.8654148578643799:  26%|██▌       | 6774/25880 [1:25:02<4:10:23,  1.27it/s]
1|6775|Loss: 0.8914796710014343:  26%|██▌       | 6774/25880 [1:25:02<4:10:23,  1.27it/s]
1|6775|Loss: 0.8914796710014343:  26%|██▌       | 6775/25880 [1:25:03<3:59:59,  1.33it/s]
1|6776|Loss: 0.9412321448326111:  26%|██▌       | 6775/25880 [1:25:03<3:59:59,  1.33it/s]
1|6776|Loss: 0.9412321448326111:  26%|██▌       | 6776/25880 [1:25:03<3:49:40,  1.39it/s]
1|6777|Loss: 0.8805801272392273:  26%|██▌       | 6776/25880 [1:25:04<3:49:40,  1.39it/s]
1|6777|Loss: 0.8805801272392273:  26%|██▌       | 6777/25880 [1:25:04<3:40:58,  1.44it/s]
1|6778|Loss: 0.7054909467697144:  26%|██▌       | 6777/25880 [1:25:04<3:40:58,  1.44it/s]
1|6778|Loss: 0.7054909467697144:  26%|██▌       | 6778/25880 [1:25:05<3:57:20,  1.34it/s]
1|6779|Loss: 0.7938555479049683:  26%|██▌       | 6778/25880 [1:25:05<3:57:20,  1.34it/s]
1|6779|Loss: 0.7938555479049683:  26%|██▌       | 6779/25880 [1:25:05<3:41:22,  1.44it/s]
1|6780|Loss: 0.8971182703971863:  26%|██▌       | 6779/25880 [1:25:06<3:41:22,  1.44it/s]
1|6780|Loss: 0.8971182703971863:  26%|██▌       | 6780/25880 [1:25:06<3:39:10,  1.45it/s]
1|6781|Loss: 0.8674613237380981:  26%|██▌       | 6780/25880 [1:25:06<3:39:10,  1.45it/s]
1|6781|Loss: 0.8674613237380981:  26%|██▌       | 6781/25880 [1:25:07<3:42:42,  1.43it/s]
1|6782|Loss: 0.8043837547302246:  26%|██▌       | 6781/25880 [1:25:07<3:42:42,  1.43it/s]
1|6782|Loss: 0.8043837547302246:  26%|██▌       | 6782/25880 [1:25:07<3:42:59,  1.43it/s]
1|6783|Loss: 0.8824698328971863:  26%|██▌       | 6782/25880 [1:25:08<3:42:59,  1.43it/s]
1|6783|Loss: 0.8824698328971863:  26%|██▌       | 6783/25880 [1:25:08<3:37:34,  1.46it/s]
1|6784|Loss: 0.8170185685157776:  26%|██▌       | 6783/25880 [1:25:08<3:37:34,  1.46it/s]
1|6784|Loss: 0.8170185685157776:  26%|██▌       | 6784/25880 [1:25:09<3:48:14,  1.39it/s]
1|6785|Loss: 1.022780418395996:  26%|██▌       | 6784/25880 [1:25:09<3:48:14,  1.39it/s] 
1|6785|Loss: 1.022780418395996:  26%|██▌       | 6785/25880 [1:25:10<3:52:35,  1.37it/s]
1|6786|Loss: 0.9515296220779419:  26%|██▌       | 6785/25880 [1:25:10<3:52:35,  1.37it/s]
1|6786|Loss: 0.9515296220779419:  26%|██▌       | 6786/25880 [1:25:10<4:03:02,  1.31it/s]
1|6787|Loss: 0.8994418382644653:  26%|██▌       | 6786/25880 [1:25:11<4:03:02,  1.31it/s]
1|6787|Loss: 0.8994418382644653:  26%|██▌       | 6787/25880 [1:25:11<3:46:02,  1.41it/s]
1|6788|Loss: 0.8764584064483643:  26%|██▌       | 6787/25880 [1:25:11<3:46:02,  1.41it/s]
1|6788|Loss: 0.8764584064483643:  26%|██▌       | 6788/25880 [1:25:12<3:35:19,  1.48it/s]
1|6789|Loss: 0.7223767042160034:  26%|██▌       | 6788/25880 [1:25:12<3:35:19,  1.48it/s]
1|6789|Loss: 0.7223767042160034:  26%|██▌       | 6789/25880 [1:25:12<3:29:57,  1.52it/s]
1|6790|Loss: 0.8676065802574158:  26%|██▌       | 6789/25880 [1:25:13<3:29:57,  1.52it/s]
1|6790|Loss: 0.8676065802574158:  26%|██▌       | 6790/25880 [1:25:13<3:42:21,  1.43it/s]
1|6791|Loss: 0.8012621998786926:  26%|██▌       | 6790/25880 [1:25:13<3:42:21,  1.43it/s]
1|6791|Loss: 0.8012621998786926:  26%|██▌       | 6791/25880 [1:25:14<3:47:48,  1.40it/s]
1|6792|Loss: 0.8701472282409668:  26%|██▌       | 6791/25880 [1:25:14<3:47:48,  1.40it/s]
1|6792|Loss: 0.8701472282409668:  26%|██▌       | 6792/25880 [1:25:14<3:41:56,  1.43it/s]
1|6793|Loss: 0.7536994218826294:  26%|██▌       | 6792/25880 [1:25:15<3:41:56,  1.43it/s]
1|6793|Loss: 0.7536994218826294:  26%|██▌       | 6793/25880 [1:25:15<3:36:05,  1.47it/s]
1|6794|Loss: 0.9405632019042969:  26%|██▌       | 6793/25880 [1:25:15<3:36:05,  1.47it/s]
1|6794|Loss: 0.9405632019042969:  26%|██▋       | 6794/25880 [1:25:16<3:43:58,  1.42it/s]
1|6795|Loss: 0.6954423189163208:  26%|██▋       | 6794/25880 [1:25:16<3:43:58,  1.42it/s]
1|6795|Loss: 0.6954423189163208:  26%|██▋       | 6795/25880 [1:25:17<3:54:53,  1.35it/s]
1|6796|Loss: 0.8868439793586731:  26%|██▋       | 6795/25880 [1:25:17<3:54:53,  1.35it/s]
1|6796|Loss: 0.8868439793586731:  26%|██▋       | 6796/25880 [1:25:17<3:45:07,  1.41it/s]
1|6797|Loss: 0.9339297413825989:  26%|██▋       | 6796/25880 [1:25:18<3:45:07,  1.41it/s]
1|6797|Loss: 0.9339297413825989:  26%|██▋       | 6797/25880 [1:25:18<3:51:33,  1.37it/s]
1|6798|Loss: 0.7482286095619202:  26%|██▋       | 6797/25880 [1:25:18<3:51:33,  1.37it/s]
1|6798|Loss: 0.7482286095619202:  26%|██▋       | 6798/25880 [1:25:19<3:42:02,  1.43it/s]
1|6799|Loss: 0.8638678789138794:  26%|██▋       | 6798/25880 [1:25:19<3:42:02,  1.43it/s]
1|6799|Loss: 0.8638678789138794:  26%|██▋       | 6799/25880 [1:25:19<3:42:11,  1.43it/s]
1|6800|Loss: 0.732920229434967:  26%|██▋       | 6799/25880 [1:25:20<3:42:11,  1.43it/s] 
1|6800|Loss: 0.732920229434967:  26%|██▋       | 6800/25880 [1:25:20<3:28:02,  1.53it/s]
1|6801|Loss: 0.8043979406356812:  26%|██▋       | 6800/25880 [1:25:20<3:28:02,  1.53it/s]
1|6801|Loss: 0.8043979406356812:  26%|██▋       | 6801/25880 [1:25:21<3:39:47,  1.45it/s]
1|6802|Loss: 0.8818511366844177:  26%|██▋       | 6801/25880 [1:25:21<3:39:47,  1.45it/s]
1|6802|Loss: 0.8818511366844177:  26%|██▋       | 6802/25880 [1:25:21<3:44:45,  1.41it/s]
1|6803|Loss: 0.7968267798423767:  26%|██▋       | 6802/25880 [1:25:22<3:44:45,  1.41it/s]
1|6803|Loss: 0.7968267798423767:  26%|██▋       | 6803/25880 [1:25:22<3:39:33,  1.45it/s]
1|6804|Loss: 0.8711957335472107:  26%|██▋       | 6803/25880 [1:25:22<3:39:33,  1.45it/s]
1|6804|Loss: 0.8711957335472107:  26%|██▋       | 6804/25880 [1:25:23<3:39:44,  1.45it/s]
1|6805|Loss: 0.8849200010299683:  26%|██▋       | 6804/25880 [1:25:23<3:39:44,  1.45it/s]
1|6805|Loss: 0.8849200010299683:  26%|██▋       | 6805/25880 [1:25:23<3:36:01,  1.47it/s]
1|6806|Loss: 0.8751813173294067:  26%|██▋       | 6805/25880 [1:25:24<3:36:01,  1.47it/s]
1|6806|Loss: 0.8751813173294067:  26%|██▋       | 6806/25880 [1:25:24<3:39:02,  1.45it/s]
1|6807|Loss: 0.8981216549873352:  26%|██▋       | 6806/25880 [1:25:25<3:39:02,  1.45it/s]
1|6807|Loss: 0.8981216549873352:  26%|██▋       | 6807/25880 [1:25:25<3:57:22,  1.34it/s]
1|6808|Loss: 0.7790274620056152:  26%|██▋       | 6807/25880 [1:25:25<3:57:22,  1.34it/s]
1|6808|Loss: 0.7790274620056152:  26%|██▋       | 6808/25880 [1:25:26<3:52:13,  1.37it/s]
1|6809|Loss: 0.7877047061920166:  26%|██▋       | 6808/25880 [1:25:26<3:52:13,  1.37it/s]
1|6809|Loss: 0.7877047061920166:  26%|██▋       | 6809/25880 [1:25:27<4:02:42,  1.31it/s]
1|6810|Loss: 0.82662433385849:  26%|██▋       | 6809/25880 [1:25:27<4:02:42,  1.31it/s]  
1|6810|Loss: 0.82662433385849:  26%|██▋       | 6810/25880 [1:25:27<3:49:34,  1.38it/s]
1|6811|Loss: 0.826245903968811:  26%|██▋       | 6810/25880 [1:25:28<3:49:34,  1.38it/s]
1|6811|Loss: 0.826245903968811:  26%|██▋       | 6811/25880 [1:25:28<3:45:02,  1.41it/s]
1|6812|Loss: 0.925584614276886:  26%|██▋       | 6811/25880 [1:25:28<3:45:02,  1.41it/s]
1|6812|Loss: 0.925584614276886:  26%|██▋       | 6812/25880 [1:25:29<3:47:37,  1.40it/s]
1|6813|Loss: 0.7674014568328857:  26%|██▋       | 6812/25880 [1:25:29<3:47:37,  1.40it/s]
1|6813|Loss: 0.7674014568328857:  26%|██▋       | 6813/25880 [1:25:29<3:34:03,  1.48it/s]
1|6814|Loss: 0.8523954749107361:  26%|██▋       | 6813/25880 [1:25:30<3:34:03,  1.48it/s]
1|6814|Loss: 0.8523954749107361:  26%|██▋       | 6814/25880 [1:25:30<3:34:49,  1.48it/s]
1|6815|Loss: 0.9088778495788574:  26%|██▋       | 6814/25880 [1:25:30<3:34:49,  1.48it/s]
1|6815|Loss: 0.9088778495788574:  26%|██▋       | 6815/25880 [1:25:31<3:41:30,  1.43it/s]
1|6816|Loss: 0.7718359231948853:  26%|██▋       | 6815/25880 [1:25:31<3:41:30,  1.43it/s]
1|6816|Loss: 0.7718359231948853:  26%|██▋       | 6816/25880 [1:25:31<3:36:32,  1.47it/s]
1|6817|Loss: 0.8645389676094055:  26%|██▋       | 6816/25880 [1:25:32<3:36:32,  1.47it/s]
1|6817|Loss: 0.8645389676094055:  26%|██▋       | 6817/25880 [1:25:32<3:30:18,  1.51it/s]
1|6818|Loss: 0.8582736849784851:  26%|██▋       | 6817/25880 [1:25:32<3:30:18,  1.51it/s]
1|6818|Loss: 0.8582736849784851:  26%|██▋       | 6818/25880 [1:25:33<3:39:21,  1.45it/s]
1|6819|Loss: 0.8304321765899658:  26%|██▋       | 6818/25880 [1:25:33<3:39:21,  1.45it/s]
1|6819|Loss: 0.8304321765899658:  26%|██▋       | 6819/25880 [1:25:33<3:42:47,  1.43it/s]
1|6820|Loss: 0.8831521272659302:  26%|██▋       | 6819/25880 [1:25:34<3:42:47,  1.43it/s]
1|6820|Loss: 0.8831521272659302:  26%|██▋       | 6820/25880 [1:25:34<3:42:22,  1.43it/s]
1|6821|Loss: 0.7782564163208008:  26%|██▋       | 6820/25880 [1:25:34<3:42:22,  1.43it/s]
1|6821|Loss: 0.7782564163208008:  26%|██▋       | 6821/25880 [1:25:35<3:59:26,  1.33it/s]
1|6822|Loss: 0.9773770570755005:  26%|██▋       | 6821/25880 [1:25:35<3:59:26,  1.33it/s]
1|6822|Loss: 0.9773770570755005:  26%|██▋       | 6822/25880 [1:25:36<3:47:32,  1.40it/s]
1|6823|Loss: 0.9500068426132202:  26%|██▋       | 6822/25880 [1:25:36<3:47:32,  1.40it/s]
1|6823|Loss: 0.9500068426132202:  26%|██▋       | 6823/25880 [1:25:36<3:36:23,  1.47it/s]
1|6824|Loss: 0.747073769569397:  26%|██▋       | 6823/25880 [1:25:36<3:36:23,  1.47it/s] 
1|6824|Loss: 0.747073769569397:  26%|██▋       | 6824/25880 [1:25:37<3:27:24,  1.53it/s]
1|6825|Loss: 0.7653616666793823:  26%|██▋       | 6824/25880 [1:25:37<3:27:24,  1.53it/s]
1|6825|Loss: 0.7653616666793823:  26%|██▋       | 6825/25880 [1:25:37<3:32:14,  1.50it/s]
1|6826|Loss: 0.771645724773407:  26%|██▋       | 6825/25880 [1:25:38<3:32:14,  1.50it/s] 
1|6826|Loss: 0.771645724773407:  26%|██▋       | 6826/25880 [1:25:38<3:19:11,  1.59it/s]
1|6827|Loss: 0.9315683841705322:  26%|██▋       | 6826/25880 [1:25:38<3:19:11,  1.59it/s]
1|6827|Loss: 0.9315683841705322:  26%|██▋       | 6827/25880 [1:25:39<3:28:43,  1.52it/s]
1|6828|Loss: 0.8934820294380188:  26%|██▋       | 6827/25880 [1:25:39<3:28:43,  1.52it/s]
1|6828|Loss: 0.8934820294380188:  26%|██▋       | 6828/25880 [1:25:39<3:38:54,  1.45it/s]
1|6829|Loss: 0.8532615303993225:  26%|██▋       | 6828/25880 [1:25:40<3:38:54,  1.45it/s]
1|6829|Loss: 0.8532615303993225:  26%|██▋       | 6829/25880 [1:25:40<3:52:49,  1.36it/s]
1|6830|Loss: 0.9282751679420471:  26%|██▋       | 6829/25880 [1:25:41<3:52:49,  1.36it/s]
1|6830|Loss: 0.9282751679420471:  26%|██▋       | 6830/25880 [1:25:41<3:53:00,  1.36it/s]
1|6831|Loss: 0.8479046821594238:  26%|██▋       | 6830/25880 [1:25:41<3:53:00,  1.36it/s]
1|6831|Loss: 0.8479046821594238:  26%|██▋       | 6831/25880 [1:25:42<3:49:54,  1.38it/s]
1|6832|Loss: 1.0149176120758057:  26%|██▋       | 6831/25880 [1:25:42<3:49:54,  1.38it/s]
1|6832|Loss: 1.0149176120758057:  26%|██▋       | 6832/25880 [1:25:42<3:50:09,  1.38it/s]
1|6833|Loss: 0.8011019825935364:  26%|██▋       | 6832/25880 [1:25:43<3:50:09,  1.38it/s]
1|6833|Loss: 0.8011019825935364:  26%|██▋       | 6833/25880 [1:25:43<3:59:00,  1.33it/s]
1|6834|Loss: 0.787773072719574:  26%|██▋       | 6833/25880 [1:25:44<3:59:00,  1.33it/s] 
1|6834|Loss: 0.787773072719574:  26%|██▋       | 6834/25880 [1:25:44<3:51:04,  1.37it/s]
1|6835|Loss: 0.8425678610801697:  26%|██▋       | 6834/25880 [1:25:44<3:51:04,  1.37it/s]
1|6835|Loss: 0.8425678610801697:  26%|██▋       | 6835/25880 [1:25:45<3:49:26,  1.38it/s]
1|6836|Loss: 0.9146767854690552:  26%|██▋       | 6835/25880 [1:25:45<3:49:26,  1.38it/s]
1|6836|Loss: 0.9146767854690552:  26%|██▋       | 6836/25880 [1:25:45<3:57:57,  1.33it/s]
1|6837|Loss: 0.8912792801856995:  26%|██▋       | 6836/25880 [1:25:46<3:57:57,  1.33it/s]
1|6837|Loss: 0.8912792801856995:  26%|██▋       | 6837/25880 [1:25:46<3:51:18,  1.37it/s]
1|6838|Loss: 0.8183149695396423:  26%|██▋       | 6837/25880 [1:25:47<3:51:18,  1.37it/s]
1|6838|Loss: 0.8183149695396423:  26%|██▋       | 6838/25880 [1:25:47<4:01:14,  1.32it/s]
1|6839|Loss: 0.8706696033477783:  26%|██▋       | 6838/25880 [1:25:47<4:01:14,  1.32it/s]
1|6839|Loss: 0.8706696033477783:  26%|██▋       | 6839/25880 [1:25:48<3:53:21,  1.36it/s]
1|6840|Loss: 0.9037275314331055:  26%|██▋       | 6839/25880 [1:25:48<3:53:21,  1.36it/s]
1|6840|Loss: 0.9037275314331055:  26%|██▋       | 6840/25880 [1:25:48<3:50:54,  1.37it/s]
1|6841|Loss: 0.8356287479400635:  26%|██▋       | 6840/25880 [1:25:49<3:50:54,  1.37it/s]
1|6841|Loss: 0.8356287479400635:  26%|██▋       | 6841/25880 [1:25:49<3:51:09,  1.37it/s]
1|6842|Loss: 0.9372948408126831:  26%|██▋       | 6841/25880 [1:25:50<3:51:09,  1.37it/s]
1|6842|Loss: 0.9372948408126831:  26%|██▋       | 6842/25880 [1:25:50<4:02:42,  1.31it/s]
1|6843|Loss: 0.8105496168136597:  26%|██▋       | 6842/25880 [1:25:50<4:02:42,  1.31it/s]
1|6843|Loss: 0.8105496168136597:  26%|██▋       | 6843/25880 [1:25:51<4:02:43,  1.31it/s]
1|6844|Loss: 0.8086010813713074:  26%|██▋       | 6843/25880 [1:25:51<4:02:43,  1.31it/s]
1|6844|Loss: 0.8086010813713074:  26%|██▋       | 6844/25880 [1:25:51<4:03:33,  1.30it/s]
1|6845|Loss: 0.853491485118866:  26%|██▋       | 6844/25880 [1:25:52<4:03:33,  1.30it/s] 
1|6845|Loss: 0.853491485118866:  26%|██▋       | 6845/25880 [1:25:52<4:01:36,  1.31it/s]
1|6846|Loss: 0.7339928150177002:  26%|██▋       | 6845/25880 [1:25:53<4:01:36,  1.31it/s]
1|6846|Loss: 0.7339928150177002:  26%|██▋       | 6846/25880 [1:25:53<4:08:22,  1.28it/s]
1|6847|Loss: 0.7329000234603882:  26%|██▋       | 6846/25880 [1:25:53<4:08:22,  1.28it/s]
1|6847|Loss: 0.7329000234603882:  26%|██▋       | 6847/25880 [1:25:54<3:45:22,  1.41it/s]
1|6848|Loss: 0.8317468166351318:  26%|██▋       | 6847/25880 [1:25:54<3:45:22,  1.41it/s]
1|6848|Loss: 0.8317468166351318:  26%|██▋       | 6848/25880 [1:25:54<3:34:58,  1.48it/s]
1|6849|Loss: 0.8700043559074402:  26%|██▋       | 6848/25880 [1:25:55<3:34:58,  1.48it/s]
1|6849|Loss: 0.8700043559074402:  26%|██▋       | 6849/25880 [1:25:55<3:31:58,  1.50it/s]
1|6850|Loss: 0.8780001401901245:  26%|██▋       | 6849/25880 [1:25:55<3:31:58,  1.50it/s]
1|6850|Loss: 0.8780001401901245:  26%|██▋       | 6850/25880 [1:25:56<3:48:19,  1.39it/s]
1|6851|Loss: 0.7794234156608582:  26%|██▋       | 6850/25880 [1:25:56<3:48:19,  1.39it/s]
1|6851|Loss: 0.7794234156608582:  26%|██▋       | 6851/25880 [1:25:56<3:50:22,  1.38it/s]
1|6852|Loss: 0.8347950577735901:  26%|██▋       | 6851/25880 [1:25:57<3:50:22,  1.38it/s]
1|6852|Loss: 0.8347950577735901:  26%|██▋       | 6852/25880 [1:25:57<4:01:32,  1.31it/s]
1|6853|Loss: 0.8144439458847046:  26%|██▋       | 6852/25880 [1:25:58<4:01:32,  1.31it/s]
1|6853|Loss: 0.8144439458847046:  26%|██▋       | 6853/25880 [1:25:58<3:59:52,  1.32it/s]
1|6854|Loss: 0.7712688446044922:  26%|██▋       | 6853/25880 [1:25:58<3:59:52,  1.32it/s]
1|6854|Loss: 0.7712688446044922:  26%|██▋       | 6854/25880 [1:25:59<3:57:45,  1.33it/s]
1|6855|Loss: 0.8392896056175232:  26%|██▋       | 6854/25880 [1:25:59<3:57:45,  1.33it/s]
1|6855|Loss: 0.8392896056175232:  26%|██▋       | 6855/25880 [1:26:00<4:00:31,  1.32it/s]
1|6856|Loss: 1.1118038892745972:  26%|██▋       | 6855/25880 [1:26:00<4:00:31,  1.32it/s]
1|6856|Loss: 1.1118038892745972:  26%|██▋       | 6856/25880 [1:26:00<4:03:46,  1.30it/s]
1|6857|Loss: 0.6697115898132324:  26%|██▋       | 6856/25880 [1:26:01<4:03:46,  1.30it/s]
1|6857|Loss: 0.6697115898132324:  26%|██▋       | 6857/25880 [1:26:01<3:54:33,  1.35it/s]
1|6858|Loss: 0.8346506953239441:  26%|██▋       | 6857/25880 [1:26:01<3:54:33,  1.35it/s]
1|6858|Loss: 0.8346506953239441:  26%|██▋       | 6858/25880 [1:26:02<3:45:22,  1.41it/s]
1|6859|Loss: 0.8413257598876953:  26%|██▋       | 6858/25880 [1:26:02<3:45:22,  1.41it/s]
1|6859|Loss: 0.8413257598876953:  27%|██▋       | 6859/25880 [1:26:02<3:46:21,  1.40it/s]
1|6860|Loss: 0.6806606650352478:  27%|██▋       | 6859/25880 [1:26:03<3:46:21,  1.40it/s]
1|6860|Loss: 0.6806606650352478:  27%|██▋       | 6860/25880 [1:26:03<4:09:50,  1.27it/s]
1|6861|Loss: 0.897931694984436:  27%|██▋       | 6860/25880 [1:26:04<4:09:50,  1.27it/s] 
1|6861|Loss: 0.897931694984436:  27%|██▋       | 6861/25880 [1:26:04<4:12:37,  1.25it/s]
1|6862|Loss: 0.7823119163513184:  27%|██▋       | 6861/25880 [1:26:05<4:12:37,  1.25it/s]
1|6862|Loss: 0.7823119163513184:  27%|██▋       | 6862/25880 [1:26:05<4:04:49,  1.29it/s]
1|6863|Loss: 0.8096199035644531:  27%|██▋       | 6862/25880 [1:26:05<4:04:49,  1.29it/s]
1|6863|Loss: 0.8096199035644531:  27%|██▋       | 6863/25880 [1:26:06<3:52:55,  1.36it/s]
1|6864|Loss: 0.8335899114608765:  27%|██▋       | 6863/25880 [1:26:06<3:52:55,  1.36it/s]
1|6864|Loss: 0.8335899114608765:  27%|██▋       | 6864/25880 [1:26:06<3:48:54,  1.38it/s]
1|6865|Loss: 0.7942686080932617:  27%|██▋       | 6864/25880 [1:26:07<3:48:54,  1.38it/s]
1|6865|Loss: 0.7942686080932617:  27%|██▋       | 6865/25880 [1:26:07<3:41:48,  1.43it/s]
1|6866|Loss: 0.8499801754951477:  27%|██▋       | 6865/25880 [1:26:07<3:41:48,  1.43it/s]
1|6866|Loss: 0.8499801754951477:  27%|██▋       | 6866/25880 [1:26:08<3:43:32,  1.42it/s]
1|6867|Loss: 0.8889405131340027:  27%|██▋       | 6866/25880 [1:26:08<3:43:32,  1.42it/s]
1|6867|Loss: 0.8889405131340027:  27%|██▋       | 6867/25880 [1:26:08<4:00:37,  1.32it/s]
1|6868|Loss: 0.7621721029281616:  27%|██▋       | 6867/25880 [1:26:09<4:00:37,  1.32it/s]
1|6868|Loss: 0.7621721029281616:  27%|██▋       | 6868/25880 [1:26:09<4:13:06,  1.25it/s]
1|6869|Loss: 0.9087045192718506:  27%|██▋       | 6868/25880 [1:26:10<4:13:06,  1.25it/s]
1|6869|Loss: 0.9087045192718506:  27%|██▋       | 6869/25880 [1:26:10<3:49:14,  1.38it/s]
1|6870|Loss: 0.7829602956771851:  27%|██▋       | 6869/25880 [1:26:10<3:49:14,  1.38it/s]
1|6870|Loss: 0.7829602956771851:  27%|██▋       | 6870/25880 [1:26:11<3:41:42,  1.43it/s]
1|6871|Loss: 0.7462124228477478:  27%|██▋       | 6870/25880 [1:26:11<3:41:42,  1.43it/s]
1|6871|Loss: 0.7462124228477478:  27%|██▋       | 6871/25880 [1:26:11<3:43:36,  1.42it/s]
1|6872|Loss: 0.7556878328323364:  27%|██▋       | 6871/25880 [1:26:12<3:43:36,  1.42it/s]
1|6872|Loss: 0.7556878328323364:  27%|██▋       | 6872/25880 [1:26:12<3:39:10,  1.45it/s]
1|6873|Loss: 0.9789625406265259:  27%|██▋       | 6872/25880 [1:26:12<3:39:10,  1.45it/s]
1|6873|Loss: 0.9789625406265259:  27%|██▋       | 6873/25880 [1:26:13<3:48:50,  1.38it/s]
1|6874|Loss: 0.9952574968338013:  27%|██▋       | 6873/25880 [1:26:13<3:48:50,  1.38it/s]
1|6874|Loss: 0.9952574968338013:  27%|██▋       | 6874/25880 [1:26:13<3:40:06,  1.44it/s]
1|6875|Loss: 0.8492626547813416:  27%|██▋       | 6874/25880 [1:26:14<3:40:06,  1.44it/s]
1|6875|Loss: 0.8492626547813416:  27%|██▋       | 6875/25880 [1:26:14<3:31:55,  1.49it/s]
1|6876|Loss: 0.816545844078064:  27%|██▋       | 6875/25880 [1:26:14<3:31:55,  1.49it/s] 
1|6876|Loss: 0.816545844078064:  27%|██▋       | 6876/25880 [1:26:15<3:40:23,  1.44it/s]
1|6877|Loss: 0.9407387971878052:  27%|██▋       | 6876/25880 [1:26:15<3:40:23,  1.44it/s]
1|6877|Loss: 0.9407387971878052:  27%|██▋       | 6877/25880 [1:26:15<3:44:57,  1.41it/s]
1|6878|Loss: 0.9228965640068054:  27%|██▋       | 6877/25880 [1:26:16<3:44:57,  1.41it/s]
1|6878|Loss: 0.9228965640068054:  27%|██▋       | 6878/25880 [1:26:16<3:46:42,  1.40it/s]
1|6879|Loss: 0.8158899545669556:  27%|██▋       | 6878/25880 [1:26:17<3:46:42,  1.40it/s]
1|6879|Loss: 0.8158899545669556:  27%|██▋       | 6879/25880 [1:26:17<3:36:41,  1.46it/s]
1|6880|Loss: 0.7539935111999512:  27%|██▋       | 6879/25880 [1:26:17<3:36:41,  1.46it/s]
1|6880|Loss: 0.7539935111999512:  27%|██▋       | 6880/25880 [1:26:18<3:49:02,  1.38it/s]
1|6881|Loss: 0.886178195476532:  27%|██▋       | 6880/25880 [1:26:18<3:49:02,  1.38it/s] 
1|6881|Loss: 0.886178195476532:  27%|██▋       | 6881/25880 [1:26:18<3:41:30,  1.43it/s]
1|6882|Loss: 0.7758035063743591:  27%|██▋       | 6881/25880 [1:26:19<3:41:30,  1.43it/s]
1|6882|Loss: 0.7758035063743591:  27%|██▋       | 6882/25880 [1:26:19<3:45:30,  1.40it/s]
1|6883|Loss: 0.9722980856895447:  27%|██▋       | 6882/25880 [1:26:19<3:45:30,  1.40it/s]
1|6883|Loss: 0.9722980856895447:  27%|██▋       | 6883/25880 [1:26:20<3:31:55,  1.49it/s]
1|6884|Loss: 0.9265149831771851:  27%|██▋       | 6883/25880 [1:26:20<3:31:55,  1.49it/s]
1|6884|Loss: 0.9265149831771851:  27%|██▋       | 6884/25880 [1:26:20<3:30:59,  1.50it/s]
1|6885|Loss: 0.7531757354736328:  27%|██▋       | 6884/25880 [1:26:21<3:30:59,  1.50it/s]
1|6885|Loss: 0.7531757354736328:  27%|██▋       | 6885/25880 [1:26:21<3:27:23,  1.53it/s]
1|6886|Loss: 0.8843767046928406:  27%|██▋       | 6885/25880 [1:26:21<3:27:23,  1.53it/s]
1|6886|Loss: 0.8843767046928406:  27%|██▋       | 6886/25880 [1:26:22<3:33:30,  1.48it/s]
1|6887|Loss: 0.9160541296005249:  27%|██▋       | 6886/25880 [1:26:22<3:33:30,  1.48it/s]
1|6887|Loss: 0.9160541296005249:  27%|██▋       | 6887/25880 [1:26:22<3:26:26,  1.53it/s]
1|6888|Loss: 0.75779128074646:  27%|██▋       | 6887/25880 [1:26:23<3:26:26,  1.53it/s]  
1|6888|Loss: 0.75779128074646:  27%|██▋       | 6888/25880 [1:26:23<3:35:10,  1.47it/s]
1|6889|Loss: 0.7619636654853821:  27%|██▋       | 6888/25880 [1:26:23<3:35:10,  1.47it/s]
1|6889|Loss: 0.7619636654853821:  27%|██▋       | 6889/25880 [1:26:24<3:43:04,  1.42it/s]
1|6890|Loss: 0.8567364811897278:  27%|██▋       | 6889/25880 [1:26:24<3:43:04,  1.42it/s]
1|6890|Loss: 0.8567364811897278:  27%|██▋       | 6890/25880 [1:26:24<3:38:10,  1.45it/s]
1|6891|Loss: 0.9184896349906921:  27%|██▋       | 6890/25880 [1:26:25<3:38:10,  1.45it/s]
1|6891|Loss: 0.9184896349906921:  27%|██▋       | 6891/25880 [1:26:25<3:28:53,  1.52it/s]
1|6892|Loss: 0.9129817485809326:  27%|██▋       | 6891/25880 [1:26:25<3:28:53,  1.52it/s]
1|6892|Loss: 0.9129817485809326:  27%|██▋       | 6892/25880 [1:26:25<3:16:12,  1.61it/s]
1|6893|Loss: 0.972091019153595:  27%|██▋       | 6892/25880 [1:26:26<3:16:12,  1.61it/s] 
1|6893|Loss: 0.972091019153595:  27%|██▋       | 6893/25880 [1:26:26<3:31:36,  1.50it/s]
1|6894|Loss: 0.8826051950454712:  27%|██▋       | 6893/25880 [1:26:27<3:31:36,  1.50it/s]
1|6894|Loss: 0.8826051950454712:  27%|██▋       | 6894/25880 [1:26:27<3:38:03,  1.45it/s]
1|6895|Loss: 0.788861870765686:  27%|██▋       | 6894/25880 [1:26:27<3:38:03,  1.45it/s] 
1|6895|Loss: 0.788861870765686:  27%|██▋       | 6895/25880 [1:26:28<3:32:12,  1.49it/s]
1|6896|Loss: 0.7749809622764587:  27%|██▋       | 6895/25880 [1:26:28<3:32:12,  1.49it/s]
1|6896|Loss: 0.7749809622764587:  27%|██▋       | 6896/25880 [1:26:28<3:36:36,  1.46it/s]
1|6897|Loss: 0.8097439408302307:  27%|██▋       | 6896/25880 [1:26:29<3:36:36,  1.46it/s]
1|6897|Loss: 0.8097439408302307:  27%|██▋       | 6897/25880 [1:26:29<3:48:26,  1.38it/s]
1|6898|Loss: 0.8078205585479736:  27%|██▋       | 6897/25880 [1:26:30<3:48:26,  1.38it/s]
1|6898|Loss: 0.8078205585479736:  27%|██▋       | 6898/25880 [1:26:30<3:48:51,  1.38it/s]
1|6899|Loss: 0.9118233323097229:  27%|██▋       | 6898/25880 [1:26:30<3:48:51,  1.38it/s]
1|6899|Loss: 0.9118233323097229:  27%|██▋       | 6899/25880 [1:26:31<3:42:22,  1.42it/s]
1|6900|Loss: 0.8158752918243408:  27%|██▋       | 6899/25880 [1:26:31<3:42:22,  1.42it/s]
1|6900|Loss: 0.8158752918243408:  27%|██▋       | 6900/25880 [1:26:31<3:41:38,  1.43it/s]
1|6901|Loss: 0.8097662925720215:  27%|██▋       | 6900/25880 [1:26:32<3:41:38,  1.43it/s]
1|6901|Loss: 0.8097662925720215:  27%|██▋       | 6901/25880 [1:26:32<3:34:52,  1.47it/s]
1|6902|Loss: 0.7671501040458679:  27%|██▋       | 6901/25880 [1:26:32<3:34:52,  1.47it/s]
1|6902|Loss: 0.7671501040458679:  27%|██▋       | 6902/25880 [1:26:32<3:25:48,  1.54it/s]
1|6903|Loss: 0.8167237043380737:  27%|██▋       | 6902/25880 [1:26:33<3:25:48,  1.54it/s]
1|6903|Loss: 0.8167237043380737:  27%|██▋       | 6903/25880 [1:26:33<3:11:43,  1.65it/s]
1|6904|Loss: 0.7528226971626282:  27%|██▋       | 6903/25880 [1:26:33<3:11:43,  1.65it/s]
1|6904|Loss: 0.7528226971626282:  27%|██▋       | 6904/25880 [1:26:34<3:22:55,  1.56it/s]
1|6905|Loss: 0.7744340300559998:  27%|██▋       | 6904/25880 [1:26:34<3:22:55,  1.56it/s]
1|6905|Loss: 0.7744340300559998:  27%|██▋       | 6905/25880 [1:26:34<3:33:12,  1.48it/s]
1|6906|Loss: 0.7901273369789124:  27%|██▋       | 6905/25880 [1:26:35<3:33:12,  1.48it/s]
1|6906|Loss: 0.7901273369789124:  27%|██▋       | 6906/25880 [1:26:35<3:17:24,  1.60it/s]
1|6907|Loss: 0.9457663297653198:  27%|██▋       | 6906/25880 [1:26:35<3:17:24,  1.60it/s]
1|6907|Loss: 0.9457663297653198:  27%|██▋       | 6907/25880 [1:26:35<3:14:57,  1.62it/s]
1|6908|Loss: 0.9136826992034912:  27%|██▋       | 6907/25880 [1:26:36<3:14:57,  1.62it/s]
1|6908|Loss: 0.9136826992034912:  27%|██▋       | 6908/25880 [1:26:36<3:25:01,  1.54it/s]
1|6909|Loss: 0.8308871984481812:  27%|██▋       | 6908/25880 [1:26:37<3:25:01,  1.54it/s]
1|6909|Loss: 0.8308871984481812:  27%|██▋       | 6909/25880 [1:26:37<3:32:56,  1.48it/s]
1|6910|Loss: 0.9804291725158691:  27%|██▋       | 6909/25880 [1:26:37<3:32:56,  1.48it/s]
1|6910|Loss: 0.9804291725158691:  27%|██▋       | 6910/25880 [1:26:38<3:36:15,  1.46it/s]
1|6911|Loss: 0.8214256763458252:  27%|██▋       | 6910/25880 [1:26:38<3:36:15,  1.46it/s]
1|6911|Loss: 0.8214256763458252:  27%|██▋       | 6911/25880 [1:26:38<3:41:19,  1.43it/s]
1|6912|Loss: 0.872714102268219:  27%|██▋       | 6911/25880 [1:26:39<3:41:19,  1.43it/s] 
1|6912|Loss: 0.872714102268219:  27%|██▋       | 6912/25880 [1:26:39<3:53:53,  1.35it/s]
1|6913|Loss: 0.8485936522483826:  27%|██▋       | 6912/25880 [1:26:40<3:53:53,  1.35it/s]
1|6913|Loss: 0.8485936522483826:  27%|██▋       | 6913/25880 [1:26:40<3:56:30,  1.34it/s]
1|6914|Loss: 0.852735698223114:  27%|██▋       | 6913/25880 [1:26:40<3:56:30,  1.34it/s] 
1|6914|Loss: 0.852735698223114:  27%|██▋       | 6914/25880 [1:26:41<3:52:39,  1.36it/s]
1|6915|Loss: 0.8757303357124329:  27%|██▋       | 6914/25880 [1:26:41<3:52:39,  1.36it/s]
1|6915|Loss: 0.8757303357124329:  27%|██▋       | 6915/25880 [1:26:41<3:43:20,  1.42it/s]
1|6916|Loss: 0.9481672644615173:  27%|██▋       | 6915/25880 [1:26:42<3:43:20,  1.42it/s]
1|6916|Loss: 0.9481672644615173:  27%|██▋       | 6916/25880 [1:26:42<3:36:51,  1.46it/s]
1|6917|Loss: 0.8913522362709045:  27%|██▋       | 6916/25880 [1:26:42<3:36:51,  1.46it/s]
1|6917|Loss: 0.8913522362709045:  27%|██▋       | 6917/25880 [1:26:43<3:45:48,  1.40it/s]
1|6918|Loss: 0.7607132792472839:  27%|██▋       | 6917/25880 [1:26:43<3:45:48,  1.40it/s]
1|6918|Loss: 0.7607132792472839:  27%|██▋       | 6918/25880 [1:26:44<3:56:05,  1.34it/s]
1|6919|Loss: 0.8746510148048401:  27%|██▋       | 6918/25880 [1:26:44<3:56:05,  1.34it/s]
1|6919|Loss: 0.8746510148048401:  27%|██▋       | 6919/25880 [1:26:44<3:56:23,  1.34it/s]
1|6920|Loss: 0.7063430547714233:  27%|██▋       | 6919/25880 [1:26:45<3:56:23,  1.34it/s]
1|6920|Loss: 0.7063430547714233:  27%|██▋       | 6920/25880 [1:26:45<3:54:50,  1.35it/s]
1|6921|Loss: 0.7615938782691956:  27%|██▋       | 6920/25880 [1:26:46<3:54:50,  1.35it/s]
1|6921|Loss: 0.7615938782691956:  27%|██▋       | 6921/25880 [1:26:46<4:08:08,  1.27it/s]
1|6922|Loss: 0.8324313163757324:  27%|██▋       | 6921/25880 [1:26:46<4:08:08,  1.27it/s]
1|6922|Loss: 0.8324313163757324:  27%|██▋       | 6922/25880 [1:26:47<3:59:53,  1.32it/s]
1|6923|Loss: 0.868453860282898:  27%|██▋       | 6922/25880 [1:26:47<3:59:53,  1.32it/s] 
1|6923|Loss: 0.868453860282898:  27%|██▋       | 6923/25880 [1:26:48<4:09:40,  1.27it/s]
1|6924|Loss: 0.877295196056366:  27%|██▋       | 6923/25880 [1:26:48<4:09:40,  1.27it/s]
1|6924|Loss: 0.877295196056366:  27%|██▋       | 6924/25880 [1:26:48<4:08:09,  1.27it/s]
1|6925|Loss: 0.9660933613777161:  27%|██▋       | 6924/25880 [1:26:49<4:08:09,  1.27it/s]
1|6925|Loss: 0.9660933613777161:  27%|██▋       | 6925/25880 [1:26:49<4:09:30,  1.27it/s]
1|6926|Loss: 0.8747889995574951:  27%|██▋       | 6925/25880 [1:26:49<4:09:30,  1.27it/s]
1|6926|Loss: 0.8747889995574951:  27%|██▋       | 6926/25880 [1:26:50<3:58:54,  1.32it/s]
1|6927|Loss: 0.8560876250267029:  27%|██▋       | 6926/25880 [1:26:50<3:58:54,  1.32it/s]
1|6927|Loss: 0.8560876250267029:  27%|██▋       | 6927/25880 [1:26:50<3:48:18,  1.38it/s]
1|6928|Loss: 0.9353460073471069:  27%|██▋       | 6927/25880 [1:26:51<3:48:18,  1.38it/s]
1|6928|Loss: 0.9353460073471069:  27%|██▋       | 6928/25880 [1:26:51<3:33:58,  1.48it/s]
1|6929|Loss: 0.772831916809082:  27%|██▋       | 6928/25880 [1:26:51<3:33:58,  1.48it/s] 
1|6929|Loss: 0.772831916809082:  27%|██▋       | 6929/25880 [1:26:51<3:18:47,  1.59it/s]
1|6930|Loss: 0.8059055805206299:  27%|██▋       | 6929/25880 [1:26:52<3:18:47,  1.59it/s]
1|6930|Loss: 0.8059055805206299:  27%|██▋       | 6930/25880 [1:26:52<3:17:24,  1.60it/s]
1|6931|Loss: 0.8783493041992188:  27%|██▋       | 6930/25880 [1:26:52<3:17:24,  1.60it/s]
1|6931|Loss: 0.8783493041992188:  27%|██▋       | 6931/25880 [1:26:53<3:14:37,  1.62it/s]
1|6932|Loss: 0.8777365684509277:  27%|██▋       | 6931/25880 [1:26:53<3:14:37,  1.62it/s]
1|6932|Loss: 0.8777365684509277:  27%|██▋       | 6932/25880 [1:26:53<3:27:26,  1.52it/s]
1|6933|Loss: 0.7623518109321594:  27%|██▋       | 6932/25880 [1:26:54<3:27:26,  1.52it/s]
1|6933|Loss: 0.7623518109321594:  27%|██▋       | 6933/25880 [1:26:54<3:24:31,  1.54it/s]
1|6934|Loss: 0.8280609250068665:  27%|██▋       | 6933/25880 [1:26:54<3:24:31,  1.54it/s]
1|6934|Loss: 0.8280609250068665:  27%|██▋       | 6934/25880 [1:26:55<3:30:30,  1.50it/s]
1|6935|Loss: 0.8327494263648987:  27%|██▋       | 6934/25880 [1:26:55<3:30:30,  1.50it/s]
1|6935|Loss: 0.8327494263648987:  27%|██▋       | 6935/25880 [1:26:56<3:52:33,  1.36it/s]
1|6936|Loss: 0.918685793876648:  27%|██▋       | 6935/25880 [1:26:56<3:52:33,  1.36it/s] 
1|6936|Loss: 0.918685793876648:  27%|██▋       | 6936/25880 [1:26:56<3:47:20,  1.39it/s]
1|6937|Loss: 0.9636956453323364:  27%|██▋       | 6936/25880 [1:26:57<3:47:20,  1.39it/s]
1|6937|Loss: 0.9636956453323364:  27%|██▋       | 6937/25880 [1:26:57<3:37:43,  1.45it/s]
1|6938|Loss: 0.8690615892410278:  27%|██▋       | 6937/25880 [1:26:57<3:37:43,  1.45it/s]
1|6938|Loss: 0.8690615892410278:  27%|██▋       | 6938/25880 [1:26:58<3:32:06,  1.49it/s]
1|6939|Loss: 0.9222596883773804:  27%|██▋       | 6938/25880 [1:26:58<3:32:06,  1.49it/s]
1|6939|Loss: 0.9222596883773804:  27%|██▋       | 6939/25880 [1:26:58<3:45:17,  1.40it/s]
1|6940|Loss: 0.9101249575614929:  27%|██▋       | 6939/25880 [1:26:59<3:45:17,  1.40it/s]
1|6940|Loss: 0.9101249575614929:  27%|██▋       | 6940/25880 [1:26:59<3:47:55,  1.38it/s]
1|6941|Loss: 0.8483783602714539:  27%|██▋       | 6940/25880 [1:27:00<3:47:55,  1.38it/s]
1|6941|Loss: 0.8483783602714539:  27%|██▋       | 6941/25880 [1:27:00<3:47:33,  1.39it/s]
1|6942|Loss: 0.7539426684379578:  27%|██▋       | 6941/25880 [1:27:00<3:47:33,  1.39it/s]
1|6942|Loss: 0.7539426684379578:  27%|██▋       | 6942/25880 [1:27:01<3:48:44,  1.38it/s]
1|6943|Loss: 0.6895486116409302:  27%|██▋       | 6942/25880 [1:27:01<3:48:44,  1.38it/s]
1|6943|Loss: 0.6895486116409302:  27%|██▋       | 6943/25880 [1:27:02<4:11:13,  1.26it/s]
1|6944|Loss: 0.8602427840232849:  27%|██▋       | 6943/25880 [1:27:02<4:11:13,  1.26it/s]
1|6944|Loss: 0.8602427840232849:  27%|██▋       | 6944/25880 [1:27:02<4:12:20,  1.25it/s]
1|6945|Loss: 0.7880332469940186:  27%|██▋       | 6944/25880 [1:27:03<4:12:20,  1.25it/s]
1|6945|Loss: 0.7880332469940186:  27%|██▋       | 6945/25880 [1:27:03<4:05:05,  1.29it/s]
1|6946|Loss: 0.8695453405380249:  27%|██▋       | 6945/25880 [1:27:04<4:05:05,  1.29it/s]
1|6946|Loss: 0.8695453405380249:  27%|██▋       | 6946/25880 [1:27:04<4:00:38,  1.31it/s]
1|6947|Loss: 0.8628029227256775:  27%|██▋       | 6946/25880 [1:27:04<4:00:38,  1.31it/s]
1|6947|Loss: 0.8628029227256775:  27%|██▋       | 6947/25880 [1:27:05<3:57:41,  1.33it/s]
1|6948|Loss: 0.9253450036048889:  27%|██▋       | 6947/25880 [1:27:05<3:57:41,  1.33it/s]
1|6948|Loss: 0.9253450036048889:  27%|██▋       | 6948/25880 [1:27:05<3:53:24,  1.35it/s]
1|6949|Loss: 0.8062294721603394:  27%|██▋       | 6948/25880 [1:27:06<3:53:24,  1.35it/s]
1|6949|Loss: 0.8062294721603394:  27%|██▋       | 6949/25880 [1:27:06<3:32:36,  1.48it/s]
1|6950|Loss: 0.8841214179992676:  27%|██▋       | 6949/25880 [1:27:06<3:32:36,  1.48it/s]
1|6950|Loss: 0.8841214179992676:  27%|██▋       | 6950/25880 [1:27:06<3:30:33,  1.50it/s]
1|6951|Loss: 0.8278903365135193:  27%|██▋       | 6950/25880 [1:27:07<3:30:33,  1.50it/s]
1|6951|Loss: 0.8278903365135193:  27%|██▋       | 6951/25880 [1:27:07<3:27:11,  1.52it/s]
1|6952|Loss: 0.9153076410293579:  27%|██▋       | 6951/25880 [1:27:08<3:27:11,  1.52it/s]
1|6952|Loss: 0.9153076410293579:  27%|██▋       | 6952/25880 [1:27:08<3:42:31,  1.42it/s]
1|6953|Loss: 0.7885494232177734:  27%|██▋       | 6952/25880 [1:27:08<3:42:31,  1.42it/s]
1|6953|Loss: 0.7885494232177734:  27%|██▋       | 6953/25880 [1:27:09<3:45:46,  1.40it/s]
1|6954|Loss: 0.6966864466667175:  27%|██▋       | 6953/25880 [1:27:09<3:45:46,  1.40it/s]
1|6954|Loss: 0.6966864466667175:  27%|██▋       | 6954/25880 [1:27:09<3:39:26,  1.44it/s]
1|6955|Loss: 0.908598005771637:  27%|██▋       | 6954/25880 [1:27:10<3:39:26,  1.44it/s] 
1|6955|Loss: 0.908598005771637:  27%|██▋       | 6955/25880 [1:27:10<3:39:15,  1.44it/s]
1|6956|Loss: 0.7945923805236816:  27%|██▋       | 6955/25880 [1:27:10<3:39:15,  1.44it/s]
1|6956|Loss: 0.7945923805236816:  27%|██▋       | 6956/25880 [1:27:11<3:42:59,  1.41it/s]
1|6957|Loss: 0.8333256244659424:  27%|██▋       | 6956/25880 [1:27:11<3:42:59,  1.41it/s]
1|6957|Loss: 0.8333256244659424:  27%|██▋       | 6957/25880 [1:27:11<3:38:49,  1.44it/s]
1|6958|Loss: 0.8109942674636841:  27%|██▋       | 6957/25880 [1:27:12<3:38:49,  1.44it/s]
1|6958|Loss: 0.8109942674636841:  27%|██▋       | 6958/25880 [1:27:12<3:48:28,  1.38it/s]
1|6959|Loss: 0.8974212408065796:  27%|██▋       | 6958/25880 [1:27:13<3:48:28,  1.38it/s]
1|6959|Loss: 0.8974212408065796:  27%|██▋       | 6959/25880 [1:27:13<3:42:50,  1.42it/s]
1|6960|Loss: 0.8404510617256165:  27%|██▋       | 6959/25880 [1:27:13<3:42:50,  1.42it/s]
1|6960|Loss: 0.8404510617256165:  27%|██▋       | 6960/25880 [1:27:14<3:51:47,  1.36it/s]
1|6961|Loss: 0.7132479548454285:  27%|██▋       | 6960/25880 [1:27:14<3:51:47,  1.36it/s]
1|6961|Loss: 0.7132479548454285:  27%|██▋       | 6961/25880 [1:27:14<3:57:48,  1.33it/s]
1|6962|Loss: 0.837610125541687:  27%|██▋       | 6961/25880 [1:27:15<3:57:48,  1.33it/s] 
1|6962|Loss: 0.837610125541687:  27%|██▋       | 6962/25880 [1:27:15<4:08:43,  1.27it/s]
1|6963|Loss: 0.9427326321601868:  27%|██▋       | 6962/25880 [1:27:16<4:08:43,  1.27it/s]
1|6963|Loss: 0.9427326321601868:  27%|██▋       | 6963/25880 [1:27:16<4:04:39,  1.29it/s]
1|6964|Loss: 0.7438325881958008:  27%|██▋       | 6963/25880 [1:27:16<4:04:39,  1.29it/s]
1|6964|Loss: 0.7438325881958008:  27%|██▋       | 6964/25880 [1:27:17<4:01:03,  1.31it/s]
1|6965|Loss: 0.8342974781990051:  27%|██▋       | 6964/25880 [1:27:17<4:01:03,  1.31it/s]
1|6965|Loss: 0.8342974781990051:  27%|██▋       | 6965/25880 [1:27:18<4:02:53,  1.30it/s]
1|6966|Loss: 0.8254895806312561:  27%|██▋       | 6965/25880 [1:27:18<4:02:53,  1.30it/s]
1|6966|Loss: 0.8254895806312561:  27%|██▋       | 6966/25880 [1:27:18<4:09:38,  1.26it/s]
1|6967|Loss: 0.8259532451629639:  27%|██▋       | 6966/25880 [1:27:19<4:09:38,  1.26it/s]
1|6967|Loss: 0.8259532451629639:  27%|██▋       | 6967/25880 [1:27:19<4:00:07,  1.31it/s]
1|6968|Loss: 0.8656908869743347:  27%|██▋       | 6967/25880 [1:27:20<4:00:07,  1.31it/s]
1|6968|Loss: 0.8656908869743347:  27%|██▋       | 6968/25880 [1:27:20<3:55:31,  1.34it/s]
1|6969|Loss: 0.8915423154830933:  27%|██▋       | 6968/25880 [1:27:20<3:55:31,  1.34it/s]
1|6969|Loss: 0.8915423154830933:  27%|██▋       | 6969/25880 [1:27:21<3:54:43,  1.34it/s]
1|6970|Loss: 0.717580258846283:  27%|██▋       | 6969/25880 [1:27:21<3:54:43,  1.34it/s] 
1|6970|Loss: 0.717580258846283:  27%|██▋       | 6970/25880 [1:27:22<4:50:16,  1.09it/s]
1|6971|Loss: 0.8368052244186401:  27%|██▋       | 6970/25880 [1:27:23<4:50:16,  1.09it/s]
1|6971|Loss: 0.8368052244186401:  27%|██▋       | 6971/25880 [1:27:23<5:09:01,  1.02it/s]
1|6972|Loss: 0.840691864490509:  27%|██▋       | 6971/25880 [1:27:24<5:09:01,  1.02it/s] 
1|6972|Loss: 0.840691864490509:  27%|██▋       | 6972/25880 [1:27:24<4:53:19,  1.07it/s]
1|6973|Loss: 0.706977367401123:  27%|██▋       | 6972/25880 [1:27:24<4:53:19,  1.07it/s]
1|6973|Loss: 0.706977367401123:  27%|██▋       | 6973/25880 [1:27:25<4:53:01,  1.08it/s]
1|6974|Loss: 0.7967063784599304:  27%|██▋       | 6973/25880 [1:27:25<4:53:01,  1.08it/s]
1|6974|Loss: 0.7967063784599304:  27%|██▋       | 6974/25880 [1:27:25<4:30:03,  1.17it/s]
1|6975|Loss: 0.8983017206192017:  27%|██▋       | 6974/25880 [1:27:26<4:30:03,  1.17it/s]
1|6975|Loss: 0.8983017206192017:  27%|██▋       | 6975/25880 [1:27:26<4:20:48,  1.21it/s]
1|6976|Loss: 0.7706693410873413:  27%|██▋       | 6975/25880 [1:27:27<4:20:48,  1.21it/s]
1|6976|Loss: 0.7706693410873413:  27%|██▋       | 6976/25880 [1:27:27<4:02:53,  1.30it/s]
1|6977|Loss: 0.7892206311225891:  27%|██▋       | 6976/25880 [1:27:27<4:02:53,  1.30it/s]
1|6977|Loss: 0.7892206311225891:  27%|██▋       | 6977/25880 [1:27:27<3:47:10,  1.39it/s]
1|6978|Loss: 0.9507722854614258:  27%|██▋       | 6977/25880 [1:27:28<3:47:10,  1.39it/s]
1|6978|Loss: 0.9507722854614258:  27%|██▋       | 6978/25880 [1:27:28<3:51:55,  1.36it/s]
1|6979|Loss: 0.8573486804962158:  27%|██▋       | 6978/25880 [1:27:29<3:51:55,  1.36it/s]
1|6979|Loss: 0.8573486804962158:  27%|██▋       | 6979/25880 [1:27:29<3:58:17,  1.32it/s]
1|6980|Loss: 0.7988417148590088:  27%|██▋       | 6979/25880 [1:27:29<3:58:17,  1.32it/s]
1|6980|Loss: 0.7988417148590088:  27%|██▋       | 6980/25880 [1:27:30<3:57:43,  1.33it/s]
1|6981|Loss: 0.8631353974342346:  27%|██▋       | 6980/25880 [1:27:30<3:57:43,  1.33it/s]
1|6981|Loss: 0.8631353974342346:  27%|██▋       | 6981/25880 [1:27:31<3:56:32,  1.33it/s]
1|6982|Loss: 0.7615625262260437:  27%|██▋       | 6981/25880 [1:27:31<3:56:32,  1.33it/s]
1|6982|Loss: 0.7615625262260437:  27%|██▋       | 6982/25880 [1:27:31<3:59:58,  1.31it/s]
1|6983|Loss: 0.8083974719047546:  27%|██▋       | 6982/25880 [1:27:32<3:59:58,  1.31it/s]
1|6983|Loss: 0.8083974719047546:  27%|██▋       | 6983/25880 [1:27:32<3:55:52,  1.34it/s]
1|6984|Loss: 0.8308313488960266:  27%|██▋       | 6983/25880 [1:27:32<3:55:52,  1.34it/s]
1|6984|Loss: 0.8308313488960266:  27%|██▋       | 6984/25880 [1:27:33<3:46:37,  1.39it/s]
1|6985|Loss: 0.6092300415039062:  27%|██▋       | 6984/25880 [1:27:33<3:46:37,  1.39it/s]
1|6985|Loss: 0.6092300415039062:  27%|██▋       | 6985/25880 [1:27:33<3:25:23,  1.53it/s]
1|6986|Loss: 0.8026356101036072:  27%|██▋       | 6985/25880 [1:27:34<3:25:23,  1.53it/s]
1|6986|Loss: 0.8026356101036072:  27%|██▋       | 6986/25880 [1:27:34<3:27:32,  1.52it/s]
1|6987|Loss: 0.8159646391868591:  27%|██▋       | 6986/25880 [1:27:34<3:27:32,  1.52it/s]
1|6987|Loss: 0.8159646391868591:  27%|██▋       | 6987/25880 [1:27:35<3:26:51,  1.52it/s]
1|6988|Loss: 0.8416564464569092:  27%|██▋       | 6987/25880 [1:27:35<3:26:51,  1.52it/s]
1|6988|Loss: 0.8416564464569092:  27%|██▋       | 6988/25880 [1:27:35<3:22:53,  1.55it/s]
1|6989|Loss: 0.8051908612251282:  27%|██▋       | 6988/25880 [1:27:36<3:22:53,  1.55it/s]
1|6989|Loss: 0.8051908612251282:  27%|██▋       | 6989/25880 [1:27:36<3:28:35,  1.51it/s]
1|6990|Loss: 0.7424615621566772:  27%|██▋       | 6989/25880 [1:27:36<3:28:35,  1.51it/s]
1|6990|Loss: 0.7424615621566772:  27%|██▋       | 6990/25880 [1:27:36<3:23:32,  1.55it/s]
1|6991|Loss: 0.7830162644386292:  27%|██▋       | 6990/25880 [1:27:37<3:23:32,  1.55it/s]
1|6991|Loss: 0.7830162644386292:  27%|██▋       | 6991/25880 [1:27:37<3:13:42,  1.63it/s]
1|6992|Loss: 0.9384979605674744:  27%|██▋       | 6991/25880 [1:27:37<3:13:42,  1.63it/s]
1|6992|Loss: 0.9384979605674744:  27%|██▋       | 6992/25880 [1:27:38<3:34:31,  1.47it/s]
1|6993|Loss: 0.8736440539360046:  27%|██▋       | 6992/25880 [1:27:38<3:34:31,  1.47it/s]
1|6993|Loss: 0.8736440539360046:  27%|██▋       | 6993/25880 [1:27:39<3:52:13,  1.36it/s]
1|6994|Loss: 0.9349223971366882:  27%|██▋       | 6993/25880 [1:27:39<3:52:13,  1.36it/s]
1|6994|Loss: 0.9349223971366882:  27%|██▋       | 6994/25880 [1:27:39<3:41:04,  1.42it/s]
1|6995|Loss: 0.7438960671424866:  27%|██▋       | 6994/25880 [1:27:40<3:41:04,  1.42it/s]
1|6995|Loss: 0.7438960671424866:  27%|██▋       | 6995/25880 [1:27:40<3:40:44,  1.43it/s]
1|6996|Loss: 0.8660001754760742:  27%|██▋       | 6995/25880 [1:27:40<3:40:44,  1.43it/s]
1|6996|Loss: 0.8660001754760742:  27%|██▋       | 6996/25880 [1:27:41<3:37:19,  1.45it/s]
1|6997|Loss: 0.7271146178245544:  27%|██▋       | 6996/25880 [1:27:41<3:37:19,  1.45it/s]
1|6997|Loss: 0.7271146178245544:  27%|██▋       | 6997/25880 [1:27:41<3:40:21,  1.43it/s]
1|6998|Loss: 0.8408098816871643:  27%|██▋       | 6997/25880 [1:27:42<3:40:21,  1.43it/s]
1|6998|Loss: 0.8408098816871643:  27%|██▋       | 6998/25880 [1:27:42<3:44:42,  1.40it/s]
1|6999|Loss: 0.8228379487991333:  27%|██▋       | 6998/25880 [1:27:43<3:44:42,  1.40it/s]
1|6999|Loss: 0.8228379487991333:  27%|██▋       | 6999/25880 [1:27:43<4:04:48,  1.29it/s]
1|7000|Loss: 0.955327033996582:  27%|██▋       | 6999/25880 [1:27:44<4:04:48,  1.29it/s] 
1|7000|Loss: 0.955327033996582:  27%|██▋       | 7000/25880 [1:27:44<4:09:55,  1.26it/s]
1|7001|Loss: 0.8155456781387329:  27%|██▋       | 7000/25880 [1:27:44<4:09:55,  1.26it/s]
1|7001|Loss: 0.8155456781387329:  27%|██▋       | 7001/25880 [1:27:45<3:56:29,  1.33it/s]
1|7002|Loss: 0.8609912395477295:  27%|██▋       | 7001/25880 [1:27:45<3:56:29,  1.33it/s]
1|7002|Loss: 0.8609912395477295:  27%|██▋       | 7002/25880 [1:27:45<3:38:48,  1.44it/s]
1|7003|Loss: 0.8496708869934082:  27%|██▋       | 7002/25880 [1:27:46<3:38:48,  1.44it/s]
1|7003|Loss: 0.8496708869934082:  27%|██▋       | 7003/25880 [1:27:46<3:53:34,  1.35it/s]
1|7004|Loss: 0.9573927521705627:  27%|██▋       | 7003/25880 [1:27:46<3:53:34,  1.35it/s]
1|7004|Loss: 0.9573927521705627:  27%|██▋       | 7004/25880 [1:27:47<3:53:57,  1.34it/s]
1|7005|Loss: 0.8564357757568359:  27%|██▋       | 7004/25880 [1:27:47<3:53:57,  1.34it/s]
1|7005|Loss: 0.8564357757568359:  27%|██▋       | 7005/25880 [1:27:47<3:45:36,  1.39it/s]
1|7006|Loss: 0.9409686923027039:  27%|██▋       | 7005/25880 [1:27:48<3:45:36,  1.39it/s]
1|7006|Loss: 0.9409686923027039:  27%|██▋       | 7006/25880 [1:27:48<3:53:20,  1.35it/s]
1|7007|Loss: 0.7766963243484497:  27%|██▋       | 7006/25880 [1:27:49<3:53:20,  1.35it/s]
1|7007|Loss: 0.7766963243484497:  27%|██▋       | 7007/25880 [1:27:49<4:07:34,  1.27it/s]
1|7008|Loss: 0.8006072044372559:  27%|██▋       | 7007/25880 [1:27:50<4:07:34,  1.27it/s]
1|7008|Loss: 0.8006072044372559:  27%|██▋       | 7008/25880 [1:27:50<4:14:22,  1.24it/s]
1|7009|Loss: 0.8713330626487732:  27%|██▋       | 7008/25880 [1:27:50<4:14:22,  1.24it/s]
1|7009|Loss: 0.8713330626487732:  27%|██▋       | 7009/25880 [1:27:51<4:00:55,  1.31it/s]
1|7010|Loss: 0.7781668901443481:  27%|██▋       | 7009/25880 [1:27:51<4:00:55,  1.31it/s]
1|7010|Loss: 0.7781668901443481:  27%|██▋       | 7010/25880 [1:27:51<4:04:50,  1.28it/s]
1|7011|Loss: 0.934906005859375:  27%|██▋       | 7010/25880 [1:27:52<4:04:50,  1.28it/s] 
1|7011|Loss: 0.934906005859375:  27%|██▋       | 7011/25880 [1:27:52<4:01:09,  1.30it/s]
1|7012|Loss: 0.7603859305381775:  27%|██▋       | 7011/25880 [1:27:53<4:01:09,  1.30it/s]
1|7012|Loss: 0.7603859305381775:  27%|██▋       | 7012/25880 [1:27:53<3:57:59,  1.32it/s]
1|7013|Loss: 0.7770185470581055:  27%|██▋       | 7012/25880 [1:27:53<3:57:59,  1.32it/s]
1|7013|Loss: 0.7770185470581055:  27%|██▋       | 7013/25880 [1:27:54<3:55:53,  1.33it/s]
1|7014|Loss: 0.7656509876251221:  27%|██▋       | 7013/25880 [1:27:54<3:55:53,  1.33it/s]
1|7014|Loss: 0.7656509876251221:  27%|██▋       | 7014/25880 [1:27:54<3:40:39,  1.43it/s]
1|7015|Loss: 0.8760645389556885:  27%|██▋       | 7014/25880 [1:27:55<3:40:39,  1.43it/s]
1|7015|Loss: 0.8760645389556885:  27%|██▋       | 7015/25880 [1:27:55<3:28:55,  1.50it/s]
1|7016|Loss: 0.9512754082679749:  27%|██▋       | 7015/25880 [1:27:55<3:28:55,  1.50it/s]
1|7016|Loss: 0.9512754082679749:  27%|██▋       | 7016/25880 [1:27:56<3:39:45,  1.43it/s]
1|7017|Loss: 0.8500751852989197:  27%|██▋       | 7016/25880 [1:27:56<3:39:45,  1.43it/s]
1|7017|Loss: 0.8500751852989197:  27%|██▋       | 7017/25880 [1:27:56<3:49:55,  1.37it/s]
1|7018|Loss: 0.9470809698104858:  27%|██▋       | 7017/25880 [1:27:57<3:49:55,  1.37it/s]
1|7018|Loss: 0.9470809698104858:  27%|██▋       | 7018/25880 [1:27:57<3:49:37,  1.37it/s]
1|7019|Loss: 0.861472487449646:  27%|██▋       | 7018/25880 [1:27:57<3:49:37,  1.37it/s] 
1|7019|Loss: 0.861472487449646:  27%|██▋       | 7019/25880 [1:27:58<3:49:52,  1.37it/s]
1|7020|Loss: 0.7231740951538086:  27%|██▋       | 7019/25880 [1:27:58<3:49:52,  1.37it/s]
1|7020|Loss: 0.7231740951538086:  27%|██▋       | 7020/25880 [1:27:59<3:59:45,  1.31it/s]
1|7021|Loss: 0.8305479884147644:  27%|██▋       | 7020/25880 [1:27:59<3:59:45,  1.31it/s]
1|7021|Loss: 0.8305479884147644:  27%|██▋       | 7021/25880 [1:27:59<3:52:44,  1.35it/s]
1|7022|Loss: 0.8432648777961731:  27%|██▋       | 7021/25880 [1:28:00<3:52:44,  1.35it/s]
1|7022|Loss: 0.8432648777961731:  27%|██▋       | 7022/25880 [1:28:00<4:03:50,  1.29it/s]
1|7023|Loss: 0.9088178277015686:  27%|██▋       | 7022/25880 [1:28:01<4:03:50,  1.29it/s]
1|7023|Loss: 0.9088178277015686:  27%|██▋       | 7023/25880 [1:28:01<3:56:00,  1.33it/s]
1|7024|Loss: 0.8559197783470154:  27%|██▋       | 7023/25880 [1:28:01<3:56:00,  1.33it/s]
1|7024|Loss: 0.8559197783470154:  27%|██▋       | 7024/25880 [1:28:02<3:57:10,  1.33it/s]
1|7025|Loss: 0.7054224610328674:  27%|██▋       | 7024/25880 [1:28:02<3:57:10,  1.33it/s]
1|7025|Loss: 0.7054224610328674:  27%|██▋       | 7025/25880 [1:28:02<3:56:25,  1.33it/s]
1|7026|Loss: 0.8887102007865906:  27%|██▋       | 7025/25880 [1:28:03<3:56:25,  1.33it/s]
1|7026|Loss: 0.8887102007865906:  27%|██▋       | 7026/25880 [1:28:03<3:45:13,  1.40it/s]
1|7027|Loss: 0.8311195969581604:  27%|██▋       | 7026/25880 [1:28:03<3:45:13,  1.40it/s]
1|7027|Loss: 0.8311195969581604:  27%|██▋       | 7027/25880 [1:28:04<3:44:59,  1.40it/s]
1|7028|Loss: 0.8657488226890564:  27%|██▋       | 7027/25880 [1:28:04<3:44:59,  1.40it/s]
1|7028|Loss: 0.8657488226890564:  27%|██▋       | 7028/25880 [1:28:05<3:54:01,  1.34it/s]
1|7029|Loss: 0.8667685985565186:  27%|██▋       | 7028/25880 [1:28:05<3:54:01,  1.34it/s]
1|7029|Loss: 0.8667685985565186:  27%|██▋       | 7029/25880 [1:28:05<3:42:55,  1.41it/s]
1|7030|Loss: 0.8552165627479553:  27%|██▋       | 7029/25880 [1:28:06<3:42:55,  1.41it/s]
1|7030|Loss: 0.8552165627479553:  27%|██▋       | 7030/25880 [1:28:06<3:42:31,  1.41it/s]
1|7031|Loss: 0.800286591053009:  27%|██▋       | 7030/25880 [1:28:06<3:42:31,  1.41it/s] 
1|7031|Loss: 0.800286591053009:  27%|██▋       | 7031/25880 [1:28:07<3:36:12,  1.45it/s]
1|7032|Loss: 0.7729281783103943:  27%|██▋       | 7031/25880 [1:28:07<3:36:12,  1.45it/s]
1|7032|Loss: 0.7729281783103943:  27%|██▋       | 7032/25880 [1:28:07<3:27:36,  1.51it/s]
1|7033|Loss: 0.8029984831809998:  27%|██▋       | 7032/25880 [1:28:07<3:27:36,  1.51it/s]
1|7033|Loss: 0.8029984831809998:  27%|██▋       | 7033/25880 [1:28:08<3:22:03,  1.55it/s]
1|7034|Loss: 0.8912028670310974:  27%|██▋       | 7033/25880 [1:28:08<3:22:03,  1.55it/s]
1|7034|Loss: 0.8912028670310974:  27%|██▋       | 7034/25880 [1:28:08<3:26:04,  1.52it/s]
1|7035|Loss: 0.791657030582428:  27%|██▋       | 7034/25880 [1:28:09<3:26:04,  1.52it/s] 
1|7035|Loss: 0.791657030582428:  27%|██▋       | 7035/25880 [1:28:09<3:22:13,  1.55it/s]
1|7036|Loss: 0.86299729347229:  27%|██▋       | 7035/25880 [1:28:09<3:22:13,  1.55it/s] 
1|7036|Loss: 0.86299729347229:  27%|██▋       | 7036/25880 [1:28:10<3:18:27,  1.58it/s]
1|7037|Loss: 0.7706515192985535:  27%|██▋       | 7036/25880 [1:28:10<3:18:27,  1.58it/s]
1|7037|Loss: 0.7706515192985535:  27%|██▋       | 7037/25880 [1:28:10<3:14:06,  1.62it/s]
1|7038|Loss: 0.9636136293411255:  27%|██▋       | 7037/25880 [1:28:11<3:14:06,  1.62it/s]
1|7038|Loss: 0.9636136293411255:  27%|██▋       | 7038/25880 [1:28:11<3:09:53,  1.65it/s]
1|7039|Loss: 0.8086663484573364:  27%|██▋       | 7038/25880 [1:28:11<3:09:53,  1.65it/s]
1|7039|Loss: 0.8086663484573364:  27%|██▋       | 7039/25880 [1:28:12<3:19:03,  1.58it/s]
1|7040|Loss: 0.8988850116729736:  27%|██▋       | 7039/25880 [1:28:12<3:19:03,  1.58it/s]
1|7040|Loss: 0.8988850116729736:  27%|██▋       | 7040/25880 [1:28:12<3:29:14,  1.50it/s]
1|7041|Loss: 0.8704231977462769:  27%|██▋       | 7040/25880 [1:28:13<3:29:14,  1.50it/s]
1|7041|Loss: 0.8704231977462769:  27%|██▋       | 7041/25880 [1:28:13<3:27:10,  1.52it/s]
1|7042|Loss: 0.9196821451187134:  27%|██▋       | 7041/25880 [1:28:13<3:27:10,  1.52it/s]
1|7042|Loss: 0.9196821451187134:  27%|██▋       | 7042/25880 [1:28:14<3:35:51,  1.45it/s]
1|7043|Loss: 0.8520352244377136:  27%|██▋       | 7042/25880 [1:28:14<3:35:51,  1.45it/s]
1|7043|Loss: 0.8520352244377136:  27%|██▋       | 7043/25880 [1:28:15<3:58:22,  1.32it/s]
1|7044|Loss: 0.8719354867935181:  27%|██▋       | 7043/25880 [1:28:15<3:58:22,  1.32it/s]
1|7044|Loss: 0.8719354867935181:  27%|██▋       | 7044/25880 [1:28:15<4:00:57,  1.30it/s]
1|7045|Loss: 0.8418776392936707:  27%|██▋       | 7044/25880 [1:28:16<4:00:57,  1.30it/s]
1|7045|Loss: 0.8418776392936707:  27%|██▋       | 7045/25880 [1:28:16<3:51:32,  1.36it/s]
1|7046|Loss: 0.8376269936561584:  27%|██▋       | 7045/25880 [1:28:16<3:51:32,  1.36it/s]
1|7046|Loss: 0.8376269936561584:  27%|██▋       | 7046/25880 [1:28:17<3:47:25,  1.38it/s]
1|7047|Loss: 0.8651188611984253:  27%|██▋       | 7046/25880 [1:28:17<3:47:25,  1.38it/s]
1|7047|Loss: 0.8651188611984253:  27%|██▋       | 7047/25880 [1:28:17<3:51:36,  1.36it/s]
1|7048|Loss: 0.7939419746398926:  27%|██▋       | 7047/25880 [1:28:18<3:51:36,  1.36it/s]
1|7048|Loss: 0.7939419746398926:  27%|██▋       | 7048/25880 [1:28:18<4:00:05,  1.31it/s]
1|7049|Loss: 0.7181776762008667:  27%|██▋       | 7048/25880 [1:28:19<4:00:05,  1.31it/s]
1|7049|Loss: 0.7181776762008667:  27%|██▋       | 7049/25880 [1:28:19<3:56:11,  1.33it/s]
1|7050|Loss: 0.8341807126998901:  27%|██▋       | 7049/25880 [1:28:19<3:56:11,  1.33it/s]
1|7050|Loss: 0.8341807126998901:  27%|██▋       | 7050/25880 [1:28:20<3:44:01,  1.40it/s]
1|7051|Loss: 0.8578609824180603:  27%|██▋       | 7050/25880 [1:28:20<3:44:01,  1.40it/s]
1|7051|Loss: 0.8578609824180603:  27%|██▋       | 7051/25880 [1:28:20<3:36:22,  1.45it/s]
1|7052|Loss: 0.8247413039207458:  27%|██▋       | 7051/25880 [1:28:21<3:36:22,  1.45it/s]
1|7052|Loss: 0.8247413039207458:  27%|██▋       | 7052/25880 [1:28:21<3:31:42,  1.48it/s]
1|7053|Loss: 0.86109858751297:  27%|██▋       | 7052/25880 [1:28:21<3:31:42,  1.48it/s]  
1|7053|Loss: 0.86109858751297:  27%|██▋       | 7053/25880 [1:28:22<3:32:19,  1.48it/s]
1|7054|Loss: 0.9524103999137878:  27%|██▋       | 7053/25880 [1:28:22<3:32:19,  1.48it/s]
1|7054|Loss: 0.9524103999137878:  27%|██▋       | 7054/25880 [1:28:22<3:22:33,  1.55it/s]
1|7055|Loss: 0.7405986785888672:  27%|██▋       | 7054/25880 [1:28:23<3:22:33,  1.55it/s]
1|7055|Loss: 0.7405986785888672:  27%|██▋       | 7055/25880 [1:28:23<3:44:13,  1.40it/s]
1|7056|Loss: 0.8197944164276123:  27%|██▋       | 7055/25880 [1:28:24<3:44:13,  1.40it/s]
1|7056|Loss: 0.8197944164276123:  27%|██▋       | 7056/25880 [1:28:24<4:04:07,  1.29it/s]
1|7057|Loss: 0.7934169769287109:  27%|██▋       | 7056/25880 [1:28:24<4:04:07,  1.29it/s]
1|7057|Loss: 0.7934169769287109:  27%|██▋       | 7057/25880 [1:28:25<4:17:12,  1.22it/s]
1|7058|Loss: 0.8349817395210266:  27%|██▋       | 7057/25880 [1:28:25<4:17:12,  1.22it/s]
1|7058|Loss: 0.8349817395210266:  27%|██▋       | 7058/25880 [1:28:26<4:21:16,  1.20it/s]
1|7059|Loss: 0.8006947636604309:  27%|██▋       | 7058/25880 [1:28:26<4:21:16,  1.20it/s]
1|7059|Loss: 0.8006947636604309:  27%|██▋       | 7059/25880 [1:28:27<4:28:55,  1.17it/s]
1|7060|Loss: 0.8184115290641785:  27%|██▋       | 7059/25880 [1:28:27<4:28:55,  1.17it/s]
1|7060|Loss: 0.8184115290641785:  27%|██▋       | 7060/25880 [1:28:27<4:20:28,  1.20it/s]
1|7061|Loss: 0.72479248046875:  27%|██▋       | 7060/25880 [1:28:28<4:20:28,  1.20it/s]  
1|7061|Loss: 0.72479248046875:  27%|██▋       | 7061/25880 [1:28:28<4:19:52,  1.21it/s]
1|7062|Loss: 0.9421856999397278:  27%|██▋       | 7061/25880 [1:28:29<4:19:52,  1.21it/s]
1|7062|Loss: 0.9421856999397278:  27%|██▋       | 7062/25880 [1:28:29<4:22:12,  1.20it/s]
1|7063|Loss: 0.8527406454086304:  27%|██▋       | 7062/25880 [1:28:30<4:22:12,  1.20it/s]
1|7063|Loss: 0.8527406454086304:  27%|██▋       | 7063/25880 [1:28:30<3:58:25,  1.32it/s]
1|7064|Loss: 0.7089822888374329:  27%|██▋       | 7063/25880 [1:28:30<3:58:25,  1.32it/s]
1|7064|Loss: 0.7089822888374329:  27%|██▋       | 7064/25880 [1:28:30<3:34:24,  1.46it/s]
1|7065|Loss: 0.8139247298240662:  27%|██▋       | 7064/25880 [1:28:31<3:34:24,  1.46it/s]
1|7065|Loss: 0.8139247298240662:  27%|██▋       | 7065/25880 [1:28:31<3:31:44,  1.48it/s]
1|7066|Loss: 0.9366874694824219:  27%|██▋       | 7065/25880 [1:28:31<3:31:44,  1.48it/s]
1|7066|Loss: 0.9366874694824219:  27%|██▋       | 7066/25880 [1:28:32<3:29:09,  1.50it/s]
1|7067|Loss: 0.9182000160217285:  27%|██▋       | 7066/25880 [1:28:32<3:29:09,  1.50it/s]
1|7067|Loss: 0.9182000160217285:  27%|██▋       | 7067/25880 [1:28:32<3:24:22,  1.53it/s]
1|7068|Loss: 0.9685637950897217:  27%|██▋       | 7067/25880 [1:28:33<3:24:22,  1.53it/s]
1|7068|Loss: 0.9685637950897217:  27%|██▋       | 7068/25880 [1:28:33<3:26:56,  1.52it/s]
1|7069|Loss: 0.9709844589233398:  27%|██▋       | 7068/25880 [1:28:33<3:26:56,  1.52it/s]
1|7069|Loss: 0.9709844589233398:  27%|██▋       | 7069/25880 [1:28:34<3:40:08,  1.42it/s]
1|7070|Loss: 0.7385569214820862:  27%|██▋       | 7069/25880 [1:28:34<3:40:08,  1.42it/s]
1|7070|Loss: 0.7385569214820862:  27%|██▋       | 7070/25880 [1:28:34<3:44:01,  1.40it/s]
1|7071|Loss: 0.8839179277420044:  27%|██▋       | 7070/25880 [1:28:35<3:44:01,  1.40it/s]
1|7071|Loss: 0.8839179277420044:  27%|██▋       | 7071/25880 [1:28:35<3:45:23,  1.39it/s]
1|7072|Loss: 0.8692078590393066:  27%|██▋       | 7071/25880 [1:28:35<3:45:23,  1.39it/s]
1|7072|Loss: 0.8692078590393066:  27%|██▋       | 7072/25880 [1:28:36<3:47:17,  1.38it/s]
1|7073|Loss: 0.7869680523872375:  27%|██▋       | 7072/25880 [1:28:36<3:47:17,  1.38it/s]
1|7073|Loss: 0.7869680523872375:  27%|██▋       | 7073/25880 [1:28:37<3:49:46,  1.36it/s]
1|7074|Loss: 0.8565263152122498:  27%|██▋       | 7073/25880 [1:28:37<3:49:46,  1.36it/s]
1|7074|Loss: 0.8565263152122498:  27%|██▋       | 7074/25880 [1:28:37<3:58:45,  1.31it/s]
1|7075|Loss: 0.8286744952201843:  27%|██▋       | 7074/25880 [1:28:38<3:58:45,  1.31it/s]
1|7075|Loss: 0.8286744952201843:  27%|██▋       | 7075/25880 [1:28:38<4:02:55,  1.29it/s]
1|7076|Loss: 0.9381718039512634:  27%|██▋       | 7075/25880 [1:28:39<4:02:55,  1.29it/s]
1|7076|Loss: 0.9381718039512634:  27%|██▋       | 7076/25880 [1:28:39<3:39:07,  1.43it/s]
1|7077|Loss: 0.8804401755332947:  27%|██▋       | 7076/25880 [1:28:39<3:39:07,  1.43it/s]
1|7077|Loss: 0.8804401755332947:  27%|██▋       | 7077/25880 [1:28:39<3:40:52,  1.42it/s]
1|7078|Loss: 0.8829953074455261:  27%|██▋       | 7077/25880 [1:28:40<3:40:52,  1.42it/s]
1|7078|Loss: 0.8829953074455261:  27%|██▋       | 7078/25880 [1:28:40<3:58:53,  1.31it/s]
1|7079|Loss: 0.8362058401107788:  27%|██▋       | 7078/25880 [1:28:41<3:58:53,  1.31it/s]
1|7079|Loss: 0.8362058401107788:  27%|██▋       | 7079/25880 [1:28:41<3:45:54,  1.39it/s]
1|7080|Loss: 0.784460186958313:  27%|██▋       | 7079/25880 [1:28:41<3:45:54,  1.39it/s] 
1|7080|Loss: 0.784460186958313:  27%|██▋       | 7080/25880 [1:28:42<3:41:00,  1.42it/s]
1|7081|Loss: 0.8354926109313965:  27%|██▋       | 7080/25880 [1:28:42<3:41:00,  1.42it/s]
1|7081|Loss: 0.8354926109313965:  27%|██▋       | 7081/25880 [1:28:42<3:46:51,  1.38it/s]
1|7082|Loss: 0.8839496374130249:  27%|██▋       | 7081/25880 [1:28:43<3:46:51,  1.38it/s]
1|7082|Loss: 0.8839496374130249:  27%|██▋       | 7082/25880 [1:28:43<3:47:03,  1.38it/s]
1|7083|Loss: 0.7593747973442078:  27%|██▋       | 7082/25880 [1:28:44<3:47:03,  1.38it/s]
1|7083|Loss: 0.7593747973442078:  27%|██▋       | 7083/25880 [1:28:44<3:46:52,  1.38it/s]
1|7084|Loss: 0.9115572571754456:  27%|██▋       | 7083/25880 [1:28:44<3:46:52,  1.38it/s]
1|7084|Loss: 0.9115572571754456:  27%|██▋       | 7084/25880 [1:28:45<3:57:11,  1.32it/s]
1|7085|Loss: 0.8458613157272339:  27%|██▋       | 7084/25880 [1:28:45<3:57:11,  1.32it/s]
1|7085|Loss: 0.8458613157272339:  27%|██▋       | 7085/25880 [1:28:45<3:57:56,  1.32it/s]
1|7086|Loss: 0.7754484415054321:  27%|██▋       | 7085/25880 [1:28:46<3:57:56,  1.32it/s]
1|7086|Loss: 0.7754484415054321:  27%|██▋       | 7086/25880 [1:28:46<3:45:10,  1.39it/s]
1|7087|Loss: 0.8810036778450012:  27%|██▋       | 7086/25880 [1:28:46<3:45:10,  1.39it/s]
1|7087|Loss: 0.8810036778450012:  27%|██▋       | 7087/25880 [1:28:47<3:48:27,  1.37it/s]
1|7088|Loss: 0.8431030511856079:  27%|██▋       | 7087/25880 [1:28:47<3:48:27,  1.37it/s]
1|7088|Loss: 0.8431030511856079:  27%|██▋       | 7088/25880 [1:28:48<3:43:01,  1.40it/s]
1|7089|Loss: 0.8231119513511658:  27%|██▋       | 7088/25880 [1:28:48<3:43:01,  1.40it/s]
1|7089|Loss: 0.8231119513511658:  27%|██▋       | 7089/25880 [1:28:48<3:35:39,  1.45it/s]
1|7090|Loss: 0.9376242160797119:  27%|██▋       | 7089/25880 [1:28:48<3:35:39,  1.45it/s]
1|7090|Loss: 0.9376242160797119:  27%|██▋       | 7090/25880 [1:28:49<3:29:14,  1.50it/s]
1|7091|Loss: 0.9560772180557251:  27%|██▋       | 7090/25880 [1:28:49<3:29:14,  1.50it/s]
1|7091|Loss: 0.9560772180557251:  27%|██▋       | 7091/25880 [1:28:49<3:16:55,  1.59it/s]
1|7092|Loss: 0.8592560291290283:  27%|██▋       | 7091/25880 [1:28:50<3:16:55,  1.59it/s]
1|7092|Loss: 0.8592560291290283:  27%|██▋       | 7092/25880 [1:28:50<3:29:47,  1.49it/s]
1|7093|Loss: 0.819819986820221:  27%|██▋       | 7092/25880 [1:28:50<3:29:47,  1.49it/s] 
1|7093|Loss: 0.819819986820221:  27%|██▋       | 7093/25880 [1:28:51<3:37:25,  1.44it/s]
1|7094|Loss: 0.8594895005226135:  27%|██▋       | 7093/25880 [1:28:51<3:37:25,  1.44it/s]
1|7094|Loss: 0.8594895005226135:  27%|██▋       | 7094/25880 [1:28:52<3:49:37,  1.36it/s]
1|7095|Loss: 0.8331694006919861:  27%|██▋       | 7094/25880 [1:28:52<3:49:37,  1.36it/s]
1|7095|Loss: 0.8331694006919861:  27%|██▋       | 7095/25880 [1:28:53<4:08:40,  1.26it/s]
1|7096|Loss: 0.8041008114814758:  27%|██▋       | 7095/25880 [1:28:53<4:08:40,  1.26it/s]
1|7096|Loss: 0.8041008114814758:  27%|██▋       | 7096/25880 [1:28:53<4:00:07,  1.30it/s]
1|7097|Loss: 0.7694337368011475:  27%|██▋       | 7096/25880 [1:28:54<4:00:07,  1.30it/s]
1|7097|Loss: 0.7694337368011475:  27%|██▋       | 7097/25880 [1:28:54<4:00:28,  1.30it/s]
1|7098|Loss: 0.9079248309135437:  27%|██▋       | 7097/25880 [1:28:54<4:00:28,  1.30it/s]
1|7098|Loss: 0.9079248309135437:  27%|██▋       | 7098/25880 [1:28:55<3:57:35,  1.32it/s]
1|7099|Loss: 1.004318356513977:  27%|██▋       | 7098/25880 [1:28:55<3:57:35,  1.32it/s] 
1|7099|Loss: 1.004318356513977:  27%|██▋       | 7099/25880 [1:28:55<3:33:34,  1.47it/s]
1|7100|Loss: 0.8632071018218994:  27%|██▋       | 7099/25880 [1:28:56<3:33:34,  1.47it/s]
1|7100|Loss: 0.8632071018218994:  27%|██▋       | 7100/25880 [1:28:56<4:00:42,  1.30it/s]
1|7101|Loss: 0.8099876642227173:  27%|██▋       | 7100/25880 [1:28:57<4:00:42,  1.30it/s]
1|7101|Loss: 0.8099876642227173:  27%|██▋       | 7101/25880 [1:28:57<3:48:27,  1.37it/s]
1|7102|Loss: 0.6897552609443665:  27%|██▋       | 7101/25880 [1:28:57<3:48:27,  1.37it/s]
1|7102|Loss: 0.6897552609443665:  27%|██▋       | 7102/25880 [1:28:58<3:45:01,  1.39it/s]
1|7103|Loss: 0.8390936255455017:  27%|██▋       | 7102/25880 [1:28:58<3:45:01,  1.39it/s]
1|7103|Loss: 0.8390936255455017:  27%|██▋       | 7103/25880 [1:28:58<3:38:20,  1.43it/s]
1|7104|Loss: 0.8979828953742981:  27%|██▋       | 7103/25880 [1:28:59<3:38:20,  1.43it/s]
1|7104|Loss: 0.8979828953742981:  27%|██▋       | 7104/25880 [1:28:59<3:32:15,  1.47it/s]
1|7105|Loss: 0.8329561352729797:  27%|██▋       | 7104/25880 [1:28:59<3:32:15,  1.47it/s]
1|7105|Loss: 0.8329561352729797:  27%|██▋       | 7105/25880 [1:29:00<3:46:41,  1.38it/s]
1|7106|Loss: 0.892857015132904:  27%|██▋       | 7105/25880 [1:29:00<3:46:41,  1.38it/s] 
1|7106|Loss: 0.892857015132904:  27%|██▋       | 7106/25880 [1:29:01<3:54:09,  1.34it/s]
1|7107|Loss: 1.0261791944503784:  27%|██▋       | 7106/25880 [1:29:01<3:54:09,  1.34it/s]
1|7107|Loss: 1.0261791944503784:  27%|██▋       | 7107/25880 [1:29:01<3:43:01,  1.40it/s]
1|7108|Loss: 0.906792938709259:  27%|██▋       | 7107/25880 [1:29:01<3:43:01,  1.40it/s] 
1|7108|Loss: 0.906792938709259:  27%|██▋       | 7108/25880 [1:29:02<3:34:44,  1.46it/s]
1|7109|Loss: 0.8890244364738464:  27%|██▋       | 7108/25880 [1:29:02<3:34:44,  1.46it/s]
1|7109|Loss: 0.8890244364738464:  27%|██▋       | 7109/25880 [1:29:02<3:38:19,  1.43it/s]
1|7110|Loss: 1.0608006715774536:  27%|██▋       | 7109/25880 [1:29:03<3:38:19,  1.43it/s]
1|7110|Loss: 1.0608006715774536:  27%|██▋       | 7110/25880 [1:29:03<3:29:23,  1.49it/s]
1|7111|Loss: 0.7711653709411621:  27%|██▋       | 7110/25880 [1:29:03<3:29:23,  1.49it/s]
1|7111|Loss: 0.7711653709411621:  27%|██▋       | 7111/25880 [1:29:04<3:31:42,  1.48it/s]
1|7112|Loss: 0.7647241950035095:  27%|██▋       | 7111/25880 [1:29:04<3:31:42,  1.48it/s]
1|7112|Loss: 0.7647241950035095:  27%|██▋       | 7112/25880 [1:29:05<3:38:07,  1.43it/s]
1|7113|Loss: 0.8900941014289856:  27%|██▋       | 7112/25880 [1:29:05<3:38:07,  1.43it/s]
1|7113|Loss: 0.8900941014289856:  27%|██▋       | 7113/25880 [1:29:05<3:30:21,  1.49it/s]
1|7114|Loss: 0.8940223455429077:  27%|██▋       | 7113/25880 [1:29:06<3:30:21,  1.49it/s]
1|7114|Loss: 0.8940223455429077:  27%|██▋       | 7114/25880 [1:29:06<3:39:45,  1.42it/s]
1|7115|Loss: 0.8068999648094177:  27%|██▋       | 7114/25880 [1:29:06<3:39:45,  1.42it/s]
1|7115|Loss: 0.8068999648094177:  27%|██▋       | 7115/25880 [1:29:07<4:01:53,  1.29it/s]
1|7116|Loss: 0.7806289792060852:  27%|██▋       | 7115/25880 [1:29:07<4:01:53,  1.29it/s]
1|7116|Loss: 0.7806289792060852:  27%|██▋       | 7116/25880 [1:29:08<4:07:16,  1.26it/s]
1|7117|Loss: 0.9303803443908691:  27%|██▋       | 7116/25880 [1:29:08<4:07:16,  1.26it/s]
1|7117|Loss: 0.9303803443908691:  28%|██▊       | 7117/25880 [1:29:08<4:01:24,  1.30it/s]
1|7118|Loss: 0.843566358089447:  28%|██▊       | 7117/25880 [1:29:09<4:01:24,  1.30it/s] 
1|7118|Loss: 0.843566358089447:  28%|██▊       | 7118/25880 [1:29:09<3:48:47,  1.37it/s]
1|7119|Loss: 0.8540574312210083:  28%|██▊       | 7118/25880 [1:29:09<3:48:47,  1.37it/s]
1|7119|Loss: 0.8540574312210083:  28%|██▊       | 7119/25880 [1:29:10<3:52:09,  1.35it/s]
1|7120|Loss: 0.8622403740882874:  28%|██▊       | 7119/25880 [1:29:10<3:52:09,  1.35it/s]
1|7120|Loss: 0.8622403740882874:  28%|██▊       | 7120/25880 [1:29:11<3:53:17,  1.34it/s]
1|7121|Loss: 0.7956908941268921:  28%|██▊       | 7120/25880 [1:29:11<3:53:17,  1.34it/s]
1|7121|Loss: 0.7956908941268921:  28%|██▊       | 7121/25880 [1:29:11<3:41:06,  1.41it/s]
1|7122|Loss: 0.7852789759635925:  28%|██▊       | 7121/25880 [1:29:12<3:41:06,  1.41it/s]
1|7122|Loss: 0.7852789759635925:  28%|██▊       | 7122/25880 [1:29:12<3:47:48,  1.37it/s]
1|7123|Loss: 0.8918179273605347:  28%|██▊       | 7122/25880 [1:29:12<3:47:48,  1.37it/s]
1|7123|Loss: 0.8918179273605347:  28%|██▊       | 7123/25880 [1:29:13<3:54:44,  1.33it/s]
1|7124|Loss: 0.8456196188926697:  28%|██▊       | 7123/25880 [1:29:13<3:54:44,  1.33it/s]
1|7124|Loss: 0.8456196188926697:  28%|██▊       | 7124/25880 [1:29:13<3:45:02,  1.39it/s]
1|7125|Loss: 0.795838475227356:  28%|██▊       | 7124/25880 [1:29:14<3:45:02,  1.39it/s] 
1|7125|Loss: 0.795838475227356:  28%|██▊       | 7125/25880 [1:29:14<3:52:49,  1.34it/s]
1|7126|Loss: 0.8148478269577026:  28%|██▊       | 7125/25880 [1:29:15<3:52:49,  1.34it/s]
1|7126|Loss: 0.8148478269577026:  28%|██▊       | 7126/25880 [1:29:15<3:37:26,  1.44it/s]
1|7127|Loss: 0.8468894958496094:  28%|██▊       | 7126/25880 [1:29:15<3:37:26,  1.44it/s]
1|7127|Loss: 0.8468894958496094:  28%|██▊       | 7127/25880 [1:29:15<3:08:44,  1.66it/s]
1|7128|Loss: 0.9008560180664062:  28%|██▊       | 7127/25880 [1:29:16<3:08:44,  1.66it/s]
1|7128|Loss: 0.9008560180664062:  28%|██▊       | 7128/25880 [1:29:16<3:05:36,  1.68it/s]
1|7129|Loss: 0.7711231112480164:  28%|██▊       | 7128/25880 [1:29:16<3:05:36,  1.68it/s]
1|7129|Loss: 0.7711231112480164:  28%|██▊       | 7129/25880 [1:29:16<3:08:49,  1.66it/s]
1|7130|Loss: 0.9092701077461243:  28%|██▊       | 7129/25880 [1:29:17<3:08:49,  1.66it/s]
1|7130|Loss: 0.9092701077461243:  28%|██▊       | 7130/25880 [1:29:17<3:18:37,  1.57it/s]
1|7131|Loss: 0.8367477655410767:  28%|██▊       | 7130/25880 [1:29:18<3:18:37,  1.57it/s]
1|7131|Loss: 0.8367477655410767:  28%|██▊       | 7131/25880 [1:29:18<3:34:05,  1.46it/s]
1|7132|Loss: 0.8247068524360657:  28%|██▊       | 7131/25880 [1:29:18<3:34:05,  1.46it/s]
1|7132|Loss: 0.8247068524360657:  28%|██▊       | 7132/25880 [1:29:19<3:39:55,  1.42it/s]
1|7133|Loss: 0.7934666275978088:  28%|██▊       | 7132/25880 [1:29:19<3:39:55,  1.42it/s]
1|7133|Loss: 0.7934666275978088:  28%|██▊       | 7133/25880 [1:29:19<3:50:14,  1.36it/s]
1|7134|Loss: 0.7629290223121643:  28%|██▊       | 7133/25880 [1:29:20<3:50:14,  1.36it/s]
1|7134|Loss: 0.7629290223121643:  28%|██▊       | 7134/25880 [1:29:20<4:00:03,  1.30it/s]
1|7135|Loss: 0.8518422842025757:  28%|██▊       | 7134/25880 [1:29:21<4:00:03,  1.30it/s]
1|7135|Loss: 0.8518422842025757:  28%|██▊       | 7135/25880 [1:29:21<3:58:56,  1.31it/s]
1|7136|Loss: 0.8793925642967224:  28%|██▊       | 7135/25880 [1:29:22<3:58:56,  1.31it/s]
1|7136|Loss: 0.8793925642967224:  28%|██▊       | 7136/25880 [1:29:22<4:08:57,  1.25it/s]
1|7137|Loss: 0.6930230855941772:  28%|██▊       | 7136/25880 [1:29:22<4:08:57,  1.25it/s]
1|7137|Loss: 0.6930230855941772:  28%|██▊       | 7137/25880 [1:29:23<4:10:14,  1.25it/s]
1|7138|Loss: 0.7834866642951965:  28%|██▊       | 7137/25880 [1:29:23<4:10:14,  1.25it/s]
1|7138|Loss: 0.7834866642951965:  28%|██▊       | 7138/25880 [1:29:24<4:12:25,  1.24it/s]
1|7139|Loss: 0.9988313913345337:  28%|██▊       | 7138/25880 [1:29:24<4:12:25,  1.24it/s]
1|7139|Loss: 0.9988313913345337:  28%|██▊       | 7139/25880 [1:29:24<3:47:51,  1.37it/s]
1|7140|Loss: 0.9180898070335388:  28%|██▊       | 7139/25880 [1:29:24<3:47:51,  1.37it/s]
1|7140|Loss: 0.9180898070335388:  28%|██▊       | 7140/25880 [1:29:25<3:50:05,  1.36it/s]
1|7141|Loss: 0.957464337348938:  28%|██▊       | 7140/25880 [1:29:25<3:50:05,  1.36it/s] 
1|7141|Loss: 0.957464337348938:  28%|██▊       | 7141/25880 [1:29:26<3:58:16,  1.31it/s]
1|7142|Loss: 0.8201661109924316:  28%|██▊       | 7141/25880 [1:29:26<3:58:16,  1.31it/s]
1|7142|Loss: 0.8201661109924316:  28%|██▊       | 7142/25880 [1:29:26<3:57:07,  1.32it/s]
1|7143|Loss: 0.621488630771637:  28%|██▊       | 7142/25880 [1:29:27<3:57:07,  1.32it/s] 
1|7143|Loss: 0.621488630771637:  28%|██▊       | 7143/25880 [1:29:27<4:07:38,  1.26it/s]
1|7144|Loss: 0.956342875957489:  28%|██▊       | 7143/25880 [1:29:28<4:07:38,  1.26it/s]
1|7144|Loss: 0.956342875957489:  28%|██▊       | 7144/25880 [1:29:28<4:13:40,  1.23it/s]
1|7145|Loss: 0.8469350337982178:  28%|██▊       | 7144/25880 [1:29:29<4:13:40,  1.23it/s]
1|7145|Loss: 0.8469350337982178:  28%|██▊       | 7145/25880 [1:29:29<4:06:20,  1.27it/s]
1|7146|Loss: 0.6659311056137085:  28%|██▊       | 7145/25880 [1:29:29<4:06:20,  1.27it/s]
1|7146|Loss: 0.6659311056137085:  28%|██▊       | 7146/25880 [1:29:30<3:57:35,  1.31it/s]
1|7147|Loss: 0.7992851138114929:  28%|██▊       | 7146/25880 [1:29:30<3:57:35,  1.31it/s]
1|7147|Loss: 0.7992851138114929:  28%|██▊       | 7147/25880 [1:29:30<3:53:20,  1.34it/s]
1|7148|Loss: 0.8200904130935669:  28%|██▊       | 7147/25880 [1:29:31<3:53:20,  1.34it/s]
1|7148|Loss: 0.8200904130935669:  28%|██▊       | 7148/25880 [1:29:31<3:48:41,  1.37it/s]
1|7149|Loss: 0.7962853908538818:  28%|██▊       | 7148/25880 [1:29:31<3:48:41,  1.37it/s]
1|7149|Loss: 0.7962853908538818:  28%|██▊       | 7149/25880 [1:29:32<3:40:34,  1.42it/s]
1|7150|Loss: 0.8237320184707642:  28%|██▊       | 7149/25880 [1:29:32<3:40:34,  1.42it/s]
1|7150|Loss: 0.8237320184707642:  28%|██▊       | 7150/25880 [1:29:32<3:42:02,  1.41it/s]
1|7151|Loss: 0.7602890729904175:  28%|██▊       | 7150/25880 [1:29:33<3:42:02,  1.41it/s]
1|7151|Loss: 0.7602890729904175:  28%|██▊       | 7151/25880 [1:29:33<3:51:15,  1.35it/s]
1|7152|Loss: 0.8155885934829712:  28%|██▊       | 7151/25880 [1:29:34<3:51:15,  1.35it/s]
1|7152|Loss: 0.8155885934829712:  28%|██▊       | 7152/25880 [1:29:34<3:26:01,  1.52it/s]
1|7153|Loss: 0.8814758658409119:  28%|██▊       | 7152/25880 [1:29:34<3:26:01,  1.52it/s]
1|7153|Loss: 0.8814758658409119:  28%|██▊       | 7153/25880 [1:29:34<3:24:49,  1.52it/s]
1|7154|Loss: 0.8107578754425049:  28%|██▊       | 7153/25880 [1:29:35<3:24:49,  1.52it/s]
1|7154|Loss: 0.8107578754425049:  28%|██▊       | 7154/25880 [1:29:35<3:38:45,  1.43it/s]
1|7155|Loss: 0.7860047817230225:  28%|██▊       | 7154/25880 [1:29:36<3:38:45,  1.43it/s]
1|7155|Loss: 0.7860047817230225:  28%|██▊       | 7155/25880 [1:29:36<3:44:07,  1.39it/s]
1|7156|Loss: 0.8738419413566589:  28%|██▊       | 7155/25880 [1:29:36<3:44:07,  1.39it/s]
1|7156|Loss: 0.8738419413566589:  28%|██▊       | 7156/25880 [1:29:37<3:47:11,  1.37it/s]
1|7157|Loss: 0.8941594362258911:  28%|██▊       | 7156/25880 [1:29:37<3:47:11,  1.37it/s]
1|7157|Loss: 0.8941594362258911:  28%|██▊       | 7157/25880 [1:29:37<3:49:53,  1.36it/s]
1|7158|Loss: 0.8348613977432251:  28%|██▊       | 7157/25880 [1:29:38<3:49:53,  1.36it/s]
1|7158|Loss: 0.8348613977432251:  28%|██▊       | 7158/25880 [1:29:38<3:43:25,  1.40it/s]
1|7159|Loss: 0.856732964515686:  28%|██▊       | 7158/25880 [1:29:38<3:43:25,  1.40it/s] 
1|7159|Loss: 0.856732964515686:  28%|██▊       | 7159/25880 [1:29:39<3:51:18,  1.35it/s]
1|7160|Loss: 0.7487787008285522:  28%|██▊       | 7159/25880 [1:29:39<3:51:18,  1.35it/s]
1|7160|Loss: 0.7487787008285522:  28%|██▊       | 7160/25880 [1:29:40<3:49:44,  1.36it/s]
1|7161|Loss: 0.9342808723449707:  28%|██▊       | 7160/25880 [1:29:40<3:49:44,  1.36it/s]
1|7161|Loss: 0.9342808723449707:  28%|██▊       | 7161/25880 [1:29:40<3:48:43,  1.36it/s]
1|7162|Loss: 0.9242033958435059:  28%|██▊       | 7161/25880 [1:29:41<3:48:43,  1.36it/s]
1|7162|Loss: 0.9242033958435059:  28%|██▊       | 7162/25880 [1:29:41<3:57:35,  1.31it/s]
1|7163|Loss: 0.8383597731590271:  28%|██▊       | 7162/25880 [1:29:42<3:57:35,  1.31it/s]
1|7163|Loss: 0.8383597731590271:  28%|██▊       | 7163/25880 [1:29:42<4:01:39,  1.29it/s]
1|7164|Loss: 0.8047484755516052:  28%|██▊       | 7163/25880 [1:29:42<4:01:39,  1.29it/s]
1|7164|Loss: 0.8047484755516052:  28%|██▊       | 7164/25880 [1:29:43<4:10:41,  1.24it/s]
1|7165|Loss: 0.8134806156158447:  28%|██▊       | 7164/25880 [1:29:43<4:10:41,  1.24it/s]
1|7165|Loss: 0.8134806156158447:  28%|██▊       | 7165/25880 [1:29:44<4:06:54,  1.26it/s]
1|7166|Loss: 0.7809600830078125:  28%|██▊       | 7165/25880 [1:29:44<4:06:54,  1.26it/s]
1|7166|Loss: 0.7809600830078125:  28%|██▊       | 7166/25880 [1:29:44<4:02:12,  1.29it/s]
1|7167|Loss: 0.905228316783905:  28%|██▊       | 7166/25880 [1:29:45<4:02:12,  1.29it/s] 
1|7167|Loss: 0.905228316783905:  28%|██▊       | 7167/25880 [1:29:45<3:49:44,  1.36it/s]
1|7168|Loss: 0.8036714792251587:  28%|██▊       | 7167/25880 [1:29:45<3:49:44,  1.36it/s]
1|7168|Loss: 0.8036714792251587:  28%|██▊       | 7168/25880 [1:29:46<3:40:03,  1.42it/s]
1|7169|Loss: 0.8787918090820312:  28%|██▊       | 7168/25880 [1:29:46<3:40:03,  1.42it/s]
1|7169|Loss: 0.8787918090820312:  28%|██▊       | 7169/25880 [1:29:46<3:27:28,  1.50it/s]
1|7170|Loss: 0.7198274731636047:  28%|██▊       | 7169/25880 [1:29:46<3:27:28,  1.50it/s]
1|7170|Loss: 0.7198274731636047:  28%|██▊       | 7170/25880 [1:29:47<3:17:01,  1.58it/s]
1|7171|Loss: 0.9122552275657654:  28%|██▊       | 7170/25880 [1:29:47<3:17:01,  1.58it/s]
1|7171|Loss: 0.9122552275657654:  28%|██▊       | 7171/25880 [1:29:47<3:22:59,  1.54it/s]
1|7172|Loss: 0.8610415458679199:  28%|██▊       | 7171/25880 [1:29:48<3:22:59,  1.54it/s]
1|7172|Loss: 0.8610415458679199:  28%|██▊       | 7172/25880 [1:29:48<3:11:50,  1.63it/s]
1|7173|Loss: 0.8623669743537903:  28%|██▊       | 7172/25880 [1:29:48<3:11:50,  1.63it/s]
1|7173|Loss: 0.8623669743537903:  28%|██▊       | 7173/25880 [1:29:49<3:31:12,  1.48it/s]
1|7174|Loss: 0.8828528523445129:  28%|██▊       | 7173/25880 [1:29:49<3:31:12,  1.48it/s]
1|7174|Loss: 0.8828528523445129:  28%|██▊       | 7174/25880 [1:29:50<3:47:48,  1.37it/s]
1|7175|Loss: 0.8033198714256287:  28%|██▊       | 7174/25880 [1:29:50<3:47:48,  1.37it/s]
1|7175|Loss: 0.8033198714256287:  28%|██▊       | 7175/25880 [1:29:50<3:54:40,  1.33it/s]
1|7176|Loss: 0.7507479786872864:  28%|██▊       | 7175/25880 [1:29:51<3:54:40,  1.33it/s]
1|7176|Loss: 0.7507479786872864:  28%|██▊       | 7176/25880 [1:29:51<3:53:50,  1.33it/s]
1|7177|Loss: 0.8719725608825684:  28%|██▊       | 7176/25880 [1:29:52<3:53:50,  1.33it/s]
1|7177|Loss: 0.8719725608825684:  28%|██▊       | 7177/25880 [1:29:52<3:55:39,  1.32it/s]
1|7178|Loss: 0.9548283815383911:  28%|██▊       | 7177/25880 [1:29:52<3:55:39,  1.32it/s]
1|7178|Loss: 0.9548283815383911:  28%|██▊       | 7178/25880 [1:29:53<4:07:55,  1.26it/s]
1|7179|Loss: 0.8846849799156189:  28%|██▊       | 7178/25880 [1:29:53<4:07:55,  1.26it/s]
1|7179|Loss: 0.8846849799156189:  28%|██▊       | 7179/25880 [1:29:54<4:22:41,  1.19it/s]
1|7180|Loss: 0.775252103805542:  28%|██▊       | 7179/25880 [1:29:54<4:22:41,  1.19it/s] 
1|7180|Loss: 0.775252103805542:  28%|██▊       | 7180/25880 [1:29:55<4:18:01,  1.21it/s]
1|7181|Loss: 0.8238705396652222:  28%|██▊       | 7180/25880 [1:29:55<4:18:01,  1.21it/s]
1|7181|Loss: 0.8238705396652222:  28%|██▊       | 7181/25880 [1:29:55<4:03:06,  1.28it/s]
1|7182|Loss: 0.8625085949897766:  28%|██▊       | 7181/25880 [1:29:56<4:03:06,  1.28it/s]
1|7182|Loss: 0.8625085949897766:  28%|██▊       | 7182/25880 [1:29:56<3:56:53,  1.32it/s]
1|7183|Loss: 1.1114174127578735:  28%|██▊       | 7182/25880 [1:29:56<3:56:53,  1.32it/s]
1|7183|Loss: 1.1114174127578735:  28%|██▊       | 7183/25880 [1:29:57<4:04:35,  1.27it/s]
1|7184|Loss: 0.7506992816925049:  28%|██▊       | 7183/25880 [1:29:57<4:04:35,  1.27it/s]
1|7184|Loss: 0.7506992816925049:  28%|██▊       | 7184/25880 [1:29:58<4:03:53,  1.28it/s]
1|7185|Loss: 0.9000607132911682:  28%|██▊       | 7184/25880 [1:29:58<4:03:53,  1.28it/s]
1|7185|Loss: 0.9000607132911682:  28%|██▊       | 7185/25880 [1:29:58<3:57:33,  1.31it/s]
1|7186|Loss: 0.8174014687538147:  28%|██▊       | 7185/25880 [1:29:59<3:57:33,  1.31it/s]
1|7186|Loss: 0.8174014687538147:  28%|██▊       | 7186/25880 [1:29:59<3:53:21,  1.34it/s]
1|7187|Loss: 1.0205020904541016:  28%|██▊       | 7186/25880 [1:29:59<3:53:21,  1.34it/s]
1|7187|Loss: 1.0205020904541016:  28%|██▊       | 7187/25880 [1:30:00<3:42:42,  1.40it/s]
1|7188|Loss: 0.8814143538475037:  28%|██▊       | 7187/25880 [1:30:00<3:42:42,  1.40it/s]
1|7188|Loss: 0.8814143538475037:  28%|██▊       | 7188/25880 [1:30:00<3:47:19,  1.37it/s]
1|7189|Loss: 0.8264713883399963:  28%|██▊       | 7188/25880 [1:30:01<3:47:19,  1.37it/s]
1|7189|Loss: 0.8264713883399963:  28%|██▊       | 7189/25880 [1:30:01<3:56:07,  1.32it/s]
1|7190|Loss: 0.921816885471344:  28%|██▊       | 7189/25880 [1:30:02<3:56:07,  1.32it/s] 
1|7190|Loss: 0.921816885471344:  28%|██▊       | 7190/25880 [1:30:02<3:29:27,  1.49it/s]
1|7191|Loss: 0.7994760274887085:  28%|██▊       | 7190/25880 [1:30:02<3:29:27,  1.49it/s]
1|7191|Loss: 0.7994760274887085:  28%|██▊       | 7191/25880 [1:30:02<3:12:45,  1.62it/s]
1|7192|Loss: 0.6249198913574219:  28%|██▊       | 7191/25880 [1:30:03<3:12:45,  1.62it/s]
1|7192|Loss: 0.6249198913574219:  28%|██▊       | 7192/25880 [1:30:03<3:41:35,  1.41it/s]
1|7193|Loss: 0.9035720229148865:  28%|██▊       | 7192/25880 [1:30:04<3:41:35,  1.41it/s]
1|7193|Loss: 0.9035720229148865:  28%|██▊       | 7193/25880 [1:30:04<4:00:43,  1.29it/s]
1|7194|Loss: 0.7359957695007324:  28%|██▊       | 7193/25880 [1:30:05<4:00:43,  1.29it/s]
1|7194|Loss: 0.7359957695007324:  28%|██▊       | 7194/25880 [1:30:05<4:09:59,  1.25it/s]
1|7195|Loss: 0.8909782767295837:  28%|██▊       | 7194/25880 [1:30:05<4:09:59,  1.25it/s]
1|7195|Loss: 0.8909782767295837:  28%|██▊       | 7195/25880 [1:30:06<4:19:31,  1.20it/s]
1|7196|Loss: 0.8928902745246887:  28%|██▊       | 7195/25880 [1:30:06<4:19:31,  1.20it/s]
1|7196|Loss: 0.8928902745246887:  28%|██▊       | 7196/25880 [1:30:06<4:04:25,  1.27it/s]
1|7197|Loss: 0.8062245845794678:  28%|██▊       | 7196/25880 [1:30:07<4:04:25,  1.27it/s]
1|7197|Loss: 0.8062245845794678:  28%|██▊       | 7197/25880 [1:30:07<4:05:45,  1.27it/s]
1|7198|Loss: 0.8407418131828308:  28%|██▊       | 7197/25880 [1:30:08<4:05:45,  1.27it/s]
1|7198|Loss: 0.8407418131828308:  28%|██▊       | 7198/25880 [1:30:08<3:51:51,  1.34it/s]
1|7199|Loss: 0.8322564959526062:  28%|██▊       | 7198/25880 [1:30:08<3:51:51,  1.34it/s]
1|7199|Loss: 0.8322564959526062:  28%|██▊       | 7199/25880 [1:30:09<3:39:07,  1.42it/s]
1|7200|Loss: 1.0118848085403442:  28%|██▊       | 7199/25880 [1:30:09<3:39:07,  1.42it/s]
1|7200|Loss: 1.0118848085403442:  28%|██▊       | 7200/25880 [1:30:09<3:32:35,  1.46it/s]
1|7201|Loss: 0.9078773260116577:  28%|██▊       | 7200/25880 [1:30:10<3:32:35,  1.46it/s]
1|7201|Loss: 0.9078773260116577:  28%|██▊       | 7201/25880 [1:30:10<3:52:32,  1.34it/s]
1|7202|Loss: 0.9421310424804688:  28%|██▊       | 7201/25880 [1:30:10<3:52:32,  1.34it/s]
1|7202|Loss: 0.9421310424804688:  28%|██▊       | 7202/25880 [1:30:11<3:34:49,  1.45it/s]
1|7203|Loss: 0.8340412974357605:  28%|██▊       | 7202/25880 [1:30:11<3:34:49,  1.45it/s]
1|7203|Loss: 0.8340412974357605:  28%|██▊       | 7203/25880 [1:30:11<3:38:17,  1.43it/s]
1|7204|Loss: 0.8847252130508423:  28%|██▊       | 7203/25880 [1:30:12<3:38:17,  1.43it/s]
1|7204|Loss: 0.8847252130508423:  28%|██▊       | 7204/25880 [1:30:12<3:40:12,  1.41it/s]
1|7205|Loss: 0.8324894309043884:  28%|██▊       | 7204/25880 [1:30:13<3:40:12,  1.41it/s]
1|7205|Loss: 0.8324894309043884:  28%|██▊       | 7205/25880 [1:30:13<3:49:17,  1.36it/s]
1|7206|Loss: 1.0791363716125488:  28%|██▊       | 7205/25880 [1:30:13<3:49:17,  1.36it/s]
1|7206|Loss: 1.0791363716125488:  28%|██▊       | 7206/25880 [1:30:14<3:50:54,  1.35it/s]
1|7207|Loss: 0.7726529836654663:  28%|██▊       | 7206/25880 [1:30:14<3:50:54,  1.35it/s]
1|7207|Loss: 0.7726529836654663:  28%|██▊       | 7207/25880 [1:30:14<3:29:07,  1.49it/s]
1|7208|Loss: 0.8492862582206726:  28%|██▊       | 7207/25880 [1:30:14<3:29:07,  1.49it/s]
1|7208|Loss: 0.8492862582206726:  28%|██▊       | 7208/25880 [1:30:15<3:12:32,  1.62it/s]
1|7209|Loss: 0.869470477104187:  28%|██▊       | 7208/25880 [1:30:15<3:12:32,  1.62it/s] 
1|7209|Loss: 0.869470477104187:  28%|██▊       | 7209/25880 [1:30:15<3:27:54,  1.50it/s]
1|7210|Loss: 0.9750272631645203:  28%|██▊       | 7209/25880 [1:30:16<3:27:54,  1.50it/s]
1|7210|Loss: 0.9750272631645203:  28%|██▊       | 7210/25880 [1:30:16<3:40:32,  1.41it/s]
1|7211|Loss: 0.803216814994812:  28%|██▊       | 7210/25880 [1:30:17<3:40:32,  1.41it/s] 
1|7211|Loss: 0.803216814994812:  28%|██▊       | 7211/25880 [1:30:17<3:30:37,  1.48it/s]
1|7212|Loss: 0.7392180562019348:  28%|██▊       | 7211/25880 [1:30:17<3:30:37,  1.48it/s]
1|7212|Loss: 0.7392180562019348:  28%|██▊       | 7212/25880 [1:30:18<3:41:03,  1.41it/s]
1|7213|Loss: 0.893846333026886:  28%|██▊       | 7212/25880 [1:30:18<3:41:03,  1.41it/s] 
1|7213|Loss: 0.893846333026886:  28%|██▊       | 7213/25880 [1:30:18<3:43:21,  1.39it/s]
1|7214|Loss: 0.7817781567573547:  28%|██▊       | 7213/25880 [1:30:19<3:43:21,  1.39it/s]
1|7214|Loss: 0.7817781567573547:  28%|██▊       | 7214/25880 [1:30:19<3:28:21,  1.49it/s]
1|7215|Loss: 0.8241233825683594:  28%|██▊       | 7214/25880 [1:30:19<3:28:21,  1.49it/s]
1|7215|Loss: 0.8241233825683594:  28%|██▊       | 7215/25880 [1:30:20<3:21:16,  1.55it/s]
1|7216|Loss: 0.8189102411270142:  28%|██▊       | 7215/25880 [1:30:20<3:21:16,  1.55it/s]
1|7216|Loss: 0.8189102411270142:  28%|██▊       | 7216/25880 [1:30:20<3:15:06,  1.59it/s]
1|7217|Loss: 1.0335476398468018:  28%|██▊       | 7216/25880 [1:30:20<3:15:06,  1.59it/s]
1|7217|Loss: 1.0335476398468018:  28%|██▊       | 7217/25880 [1:30:21<3:19:22,  1.56it/s]
1|7218|Loss: 0.9003270268440247:  28%|██▊       | 7217/25880 [1:30:21<3:19:22,  1.56it/s]
1|7218|Loss: 0.9003270268440247:  28%|██▊       | 7218/25880 [1:30:21<3:06:04,  1.67it/s]
1|7219|Loss: 0.7547876238822937:  28%|██▊       | 7218/25880 [1:30:22<3:06:04,  1.67it/s]
1|7219|Loss: 0.7547876238822937:  28%|██▊       | 7219/25880 [1:30:22<3:06:16,  1.67it/s]
1|7220|Loss: 0.8751794099807739:  28%|██▊       | 7219/25880 [1:30:22<3:06:16,  1.67it/s]
1|7220|Loss: 0.8751794099807739:  28%|██▊       | 7220/25880 [1:30:23<3:27:11,  1.50it/s]
1|7221|Loss: 0.9364230036735535:  28%|██▊       | 7220/25880 [1:30:23<3:27:11,  1.50it/s]
1|7221|Loss: 0.9364230036735535:  28%|██▊       | 7221/25880 [1:30:23<3:19:14,  1.56it/s]
1|7222|Loss: 0.8208456039428711:  28%|██▊       | 7221/25880 [1:30:24<3:19:14,  1.56it/s]
1|7222|Loss: 0.8208456039428711:  28%|██▊       | 7222/25880 [1:30:24<3:12:25,  1.62it/s]
1|7223|Loss: 0.8133288025856018:  28%|██▊       | 7222/25880 [1:30:24<3:12:25,  1.62it/s]
1|7223|Loss: 0.8133288025856018:  28%|██▊       | 7223/25880 [1:30:25<3:27:25,  1.50it/s]
1|7224|Loss: 0.8831002116203308:  28%|██▊       | 7223/25880 [1:30:25<3:27:25,  1.50it/s]
1|7224|Loss: 0.8831002116203308:  28%|██▊       | 7224/25880 [1:30:25<3:32:23,  1.46it/s]
1|7225|Loss: 1.072477102279663:  28%|██▊       | 7224/25880 [1:30:26<3:32:23,  1.46it/s] 
1|7225|Loss: 1.072477102279663:  28%|██▊       | 7225/25880 [1:30:26<3:26:54,  1.50it/s]
1|7226|Loss: 0.8471091389656067:  28%|██▊       | 7225/25880 [1:30:26<3:26:54,  1.50it/s]
1|7226|Loss: 0.8471091389656067:  28%|██▊       | 7226/25880 [1:30:27<3:23:38,  1.53it/s]
1|7227|Loss: 0.8620743155479431:  28%|██▊       | 7226/25880 [1:30:27<3:23:38,  1.53it/s]
1|7227|Loss: 0.8620743155479431:  28%|██▊       | 7227/25880 [1:30:27<3:29:54,  1.48it/s]
1|7228|Loss: 0.8130735754966736:  28%|██▊       | 7227/25880 [1:30:28<3:29:54,  1.48it/s]
1|7228|Loss: 0.8130735754966736:  28%|██▊       | 7228/25880 [1:30:28<3:53:17,  1.33it/s]
1|7229|Loss: 0.8840028643608093:  28%|██▊       | 7228/25880 [1:30:29<3:53:17,  1.33it/s]
1|7229|Loss: 0.8840028643608093:  28%|██▊       | 7229/25880 [1:30:29<4:01:45,  1.29it/s]
1|7230|Loss: 0.8317570686340332:  28%|██▊       | 7229/25880 [1:30:30<4:01:45,  1.29it/s]
1|7230|Loss: 0.8317570686340332:  28%|██▊       | 7230/25880 [1:30:30<4:05:30,  1.27it/s]
1|7231|Loss: 1.06378173828125:  28%|██▊       | 7230/25880 [1:30:30<4:05:30,  1.27it/s]  
1|7231|Loss: 1.06378173828125:  28%|██▊       | 7231/25880 [1:30:31<3:59:31,  1.30it/s]
1|7232|Loss: 0.8380651473999023:  28%|██▊       | 7231/25880 [1:30:31<3:59:31,  1.30it/s]
1|7232|Loss: 0.8380651473999023:  28%|██▊       | 7232/25880 [1:30:31<4:00:28,  1.29it/s]
1|7233|Loss: 0.8369988799095154:  28%|██▊       | 7232/25880 [1:30:32<4:00:28,  1.29it/s]
1|7233|Loss: 0.8369988799095154:  28%|██▊       | 7233/25880 [1:30:32<4:11:17,  1.24it/s]
1|7234|Loss: 0.5960205793380737:  28%|██▊       | 7233/25880 [1:30:33<4:11:17,  1.24it/s]
1|7234|Loss: 0.5960205793380737:  28%|██▊       | 7234/25880 [1:30:33<3:58:40,  1.30it/s]
1|7235|Loss: 0.9292420744895935:  28%|██▊       | 7234/25880 [1:30:33<3:58:40,  1.30it/s]
1|7235|Loss: 0.9292420744895935:  28%|██▊       | 7235/25880 [1:30:34<3:41:09,  1.41it/s]
1|7236|Loss: 0.7839751839637756:  28%|██▊       | 7235/25880 [1:30:34<3:41:09,  1.41it/s]
1|7236|Loss: 0.7839751839637756:  28%|██▊       | 7236/25880 [1:30:34<3:40:03,  1.41it/s]
1|7237|Loss: 0.7755808234214783:  28%|██▊       | 7236/25880 [1:30:35<3:40:03,  1.41it/s]
1|7237|Loss: 0.7755808234214783:  28%|██▊       | 7237/25880 [1:30:35<3:33:17,  1.46it/s]
1|7238|Loss: 0.7792197465896606:  28%|██▊       | 7237/25880 [1:30:35<3:33:17,  1.46it/s]
1|7238|Loss: 0.7792197465896606:  28%|██▊       | 7238/25880 [1:30:36<3:28:23,  1.49it/s]
1|7239|Loss: 0.7867109775543213:  28%|██▊       | 7238/25880 [1:30:36<3:28:23,  1.49it/s]
1|7239|Loss: 0.7867109775543213:  28%|██▊       | 7239/25880 [1:30:36<3:20:52,  1.55it/s]
1|7240|Loss: 0.8667775392532349:  28%|██▊       | 7239/25880 [1:30:36<3:20:52,  1.55it/s]
1|7240|Loss: 0.8667775392532349:  28%|██▊       | 7240/25880 [1:30:37<3:24:14,  1.52it/s]
1|7241|Loss: 0.8254686594009399:  28%|██▊       | 7240/25880 [1:30:37<3:24:14,  1.52it/s]
1|7241|Loss: 0.8254686594009399:  28%|██▊       | 7241/25880 [1:30:37<3:04:50,  1.68it/s]
1|7242|Loss: 0.8638718724250793:  28%|██▊       | 7241/25880 [1:30:38<3:04:50,  1.68it/s]
1|7242|Loss: 0.8638718724250793:  28%|██▊       | 7242/25880 [1:30:38<3:11:19,  1.62it/s]
1|7243|Loss: 0.7088906168937683:  28%|██▊       | 7242/25880 [1:30:38<3:11:19,  1.62it/s]
1|7243|Loss: 0.7088906168937683:  28%|██▊       | 7243/25880 [1:30:39<3:21:50,  1.54it/s]
1|7244|Loss: 0.8194749355316162:  28%|██▊       | 7243/25880 [1:30:39<3:21:50,  1.54it/s]
1|7244|Loss: 0.8194749355316162:  28%|██▊       | 7244/25880 [1:30:39<3:02:03,  1.71it/s]
1|7245|Loss: 0.9083467125892639:  28%|██▊       | 7244/25880 [1:30:39<3:02:03,  1.71it/s]
1|7245|Loss: 0.9083467125892639:  28%|██▊       | 7245/25880 [1:30:40<3:13:37,  1.60it/s]
1|7246|Loss: 0.9051554799079895:  28%|██▊       | 7245/25880 [1:30:40<3:13:37,  1.60it/s]
1|7246|Loss: 0.9051554799079895:  28%|██▊       | 7246/25880 [1:30:41<3:23:17,  1.53it/s]
1|7247|Loss: 0.9086163640022278:  28%|██▊       | 7246/25880 [1:30:41<3:23:17,  1.53it/s]
1|7247|Loss: 0.9086163640022278:  28%|██▊       | 7247/25880 [1:30:41<3:37:42,  1.43it/s]
1|7248|Loss: 0.7188090085983276:  28%|██▊       | 7247/25880 [1:30:42<3:37:42,  1.43it/s]
1|7248|Loss: 0.7188090085983276:  28%|██▊       | 7248/25880 [1:30:42<3:49:39,  1.35it/s]
1|7249|Loss: 0.8213114142417908:  28%|██▊       | 7248/25880 [1:30:43<3:49:39,  1.35it/s]
1|7249|Loss: 0.8213114142417908:  28%|██▊       | 7249/25880 [1:30:43<3:50:08,  1.35it/s]
1|7250|Loss: 1.0183273553848267:  28%|██▊       | 7249/25880 [1:30:43<3:50:08,  1.35it/s]
1|7250|Loss: 1.0183273553848267:  28%|██▊       | 7250/25880 [1:30:44<3:52:58,  1.33it/s]
1|7251|Loss: 0.8335995078086853:  28%|██▊       | 7250/25880 [1:30:44<3:52:58,  1.33it/s]
1|7251|Loss: 0.8335995078086853:  28%|██▊       | 7251/25880 [1:30:44<3:45:53,  1.37it/s]
1|7252|Loss: 0.8381786942481995:  28%|██▊       | 7251/25880 [1:30:45<3:45:53,  1.37it/s]
1|7252|Loss: 0.8381786942481995:  28%|██▊       | 7252/25880 [1:30:45<3:41:31,  1.40it/s]
1|7253|Loss: 0.8163595199584961:  28%|██▊       | 7252/25880 [1:30:45<3:41:31,  1.40it/s]
1|7253|Loss: 0.8163595199584961:  28%|██▊       | 7253/25880 [1:30:46<3:40:22,  1.41it/s]
1|7254|Loss: 0.8452502489089966:  28%|██▊       | 7253/25880 [1:30:46<3:40:22,  1.41it/s]
1|7254|Loss: 0.8452502489089966:  28%|██▊       | 7254/25880 [1:30:46<3:39:20,  1.42it/s]
1|7255|Loss: 0.8369254469871521:  28%|██▊       | 7254/25880 [1:30:47<3:39:20,  1.42it/s]
1|7255|Loss: 0.8369254469871521:  28%|██▊       | 7255/25880 [1:30:47<3:33:52,  1.45it/s]
1|7256|Loss: 0.8780908584594727:  28%|██▊       | 7255/25880 [1:30:47<3:33:52,  1.45it/s]
1|7256|Loss: 0.8780908584594727:  28%|██▊       | 7256/25880 [1:30:48<3:29:19,  1.48it/s]
1|7257|Loss: 0.8752641677856445:  28%|██▊       | 7256/25880 [1:30:48<3:29:19,  1.48it/s]
1|7257|Loss: 0.8752641677856445:  28%|██▊       | 7257/25880 [1:30:49<3:44:56,  1.38it/s]
1|7258|Loss: 0.6747618913650513:  28%|██▊       | 7257/25880 [1:30:49<3:44:56,  1.38it/s]
1|7258|Loss: 0.6747618913650513:  28%|██▊       | 7258/25880 [1:30:49<3:59:37,  1.30it/s]
1|7259|Loss: 0.7002652883529663:  28%|██▊       | 7258/25880 [1:30:50<3:59:37,  1.30it/s]
1|7259|Loss: 0.7002652883529663:  28%|██▊       | 7259/25880 [1:30:50<3:42:17,  1.40it/s]
1|7260|Loss: 0.8339313268661499:  28%|██▊       | 7259/25880 [1:30:50<3:42:17,  1.40it/s]
1|7260|Loss: 0.8339313268661499:  28%|██▊       | 7260/25880 [1:30:51<3:48:04,  1.36it/s]
1|7261|Loss: 0.7922447919845581:  28%|██▊       | 7260/25880 [1:30:51<3:48:04,  1.36it/s]
1|7261|Loss: 0.7922447919845581:  28%|██▊       | 7261/25880 [1:30:51<3:35:21,  1.44it/s]
1|7262|Loss: 0.8467929363250732:  28%|██▊       | 7261/25880 [1:30:52<3:35:21,  1.44it/s]
1|7262|Loss: 0.8467929363250732:  28%|██▊       | 7262/25880 [1:30:52<3:19:22,  1.56it/s]
1|7263|Loss: 0.8940079212188721:  28%|██▊       | 7262/25880 [1:30:52<3:19:22,  1.56it/s]
1|7263|Loss: 0.8940079212188721:  28%|██▊       | 7263/25880 [1:30:53<3:16:47,  1.58it/s]
1|7264|Loss: 0.8229979276657104:  28%|██▊       | 7263/25880 [1:30:53<3:16:47,  1.58it/s]
1|7264|Loss: 0.8229979276657104:  28%|██▊       | 7264/25880 [1:30:53<3:08:48,  1.64it/s]
1|7265|Loss: 0.8936965465545654:  28%|██▊       | 7264/25880 [1:30:53<3:08:48,  1.64it/s]
1|7265|Loss: 0.8936965465545654:  28%|██▊       | 7265/25880 [1:30:54<3:07:14,  1.66it/s]
1|7266|Loss: 0.8905707597732544:  28%|██▊       | 7265/25880 [1:30:54<3:07:14,  1.66it/s]
1|7266|Loss: 0.8905707597732544:  28%|██▊       | 7266/25880 [1:30:54<3:06:14,  1.67it/s]
1|7267|Loss: 0.8921298980712891:  28%|██▊       | 7266/25880 [1:30:55<3:06:14,  1.67it/s]
1|7267|Loss: 0.8921298980712891:  28%|██▊       | 7267/25880 [1:30:55<3:06:42,  1.66it/s]
1|7268|Loss: 0.8550428748130798:  28%|██▊       | 7267/25880 [1:30:55<3:06:42,  1.66it/s]
1|7268|Loss: 0.8550428748130798:  28%|██▊       | 7268/25880 [1:30:56<3:30:40,  1.47it/s]
1|7269|Loss: 0.8572434782981873:  28%|██▊       | 7268/25880 [1:30:56<3:30:40,  1.47it/s]
1|7269|Loss: 0.8572434782981873:  28%|██▊       | 7269/25880 [1:30:57<3:52:46,  1.33it/s]
1|7270|Loss: 0.8836093544960022:  28%|██▊       | 7269/25880 [1:30:57<3:52:46,  1.33it/s]
1|7270|Loss: 0.8836093544960022:  28%|██▊       | 7270/25880 [1:30:58<4:08:33,  1.25it/s]
1|7271|Loss: 0.8412363529205322:  28%|██▊       | 7270/25880 [1:30:58<4:08:33,  1.25it/s]
1|7271|Loss: 0.8412363529205322:  28%|██▊       | 7271/25880 [1:30:58<4:12:28,  1.23it/s]
1|7272|Loss: 0.7421568632125854:  28%|██▊       | 7271/25880 [1:30:59<4:12:28,  1.23it/s]
1|7272|Loss: 0.7421568632125854:  28%|██▊       | 7272/25880 [1:30:59<4:04:19,  1.27it/s]
1|7273|Loss: 0.6425435543060303:  28%|██▊       | 7272/25880 [1:31:00<4:04:19,  1.27it/s]
1|7273|Loss: 0.6425435543060303:  28%|██▊       | 7273/25880 [1:31:00<4:26:06,  1.17it/s]
1|7274|Loss: 0.8938099145889282:  28%|██▊       | 7273/25880 [1:31:01<4:26:06,  1.17it/s]
1|7274|Loss: 0.8938099145889282:  28%|██▊       | 7274/25880 [1:31:01<4:19:55,  1.19it/s]
1|7275|Loss: 0.951007068157196:  28%|██▊       | 7274/25880 [1:31:01<4:19:55,  1.19it/s] 
1|7275|Loss: 0.951007068157196:  28%|██▊       | 7275/25880 [1:31:02<4:08:48,  1.25it/s]
1|7276|Loss: 0.7564376592636108:  28%|██▊       | 7275/25880 [1:31:02<4:08:48,  1.25it/s]
1|7276|Loss: 0.7564376592636108:  28%|██▊       | 7276/25880 [1:31:02<3:59:42,  1.29it/s]
1|7277|Loss: 0.790294349193573:  28%|██▊       | 7276/25880 [1:31:03<3:59:42,  1.29it/s] 
1|7277|Loss: 0.790294349193573:  28%|██▊       | 7277/25880 [1:31:03<3:59:03,  1.30it/s]
1|7278|Loss: 0.8908445239067078:  28%|██▊       | 7277/25880 [1:31:04<3:59:03,  1.30it/s]
1|7278|Loss: 0.8908445239067078:  28%|██▊       | 7278/25880 [1:31:04<3:48:23,  1.36it/s]
1|7279|Loss: 0.9428316354751587:  28%|██▊       | 7278/25880 [1:31:04<3:48:23,  1.36it/s]
1|7279|Loss: 0.9428316354751587:  28%|██▊       | 7279/25880 [1:31:04<3:39:49,  1.41it/s]
1|7280|Loss: 0.9049196243286133:  28%|██▊       | 7279/25880 [1:31:05<3:39:49,  1.41it/s]
1|7280|Loss: 0.9049196243286133:  28%|██▊       | 7280/25880 [1:31:05<3:40:30,  1.41it/s]
1|7281|Loss: 0.8328672647476196:  28%|██▊       | 7280/25880 [1:31:06<3:40:30,  1.41it/s]
1|7281|Loss: 0.8328672647476196:  28%|██▊       | 7281/25880 [1:31:06<3:40:05,  1.41it/s]
1|7282|Loss: 1.0600289106369019:  28%|██▊       | 7281/25880 [1:31:06<3:40:05,  1.41it/s]
1|7282|Loss: 1.0600289106369019:  28%|██▊       | 7282/25880 [1:31:07<4:26:14,  1.16it/s]
1|7283|Loss: 0.6152421236038208:  28%|██▊       | 7282/25880 [1:31:08<4:26:14,  1.16it/s]
1|7283|Loss: 0.6152421236038208:  28%|██▊       | 7283/25880 [1:31:08<4:25:30,  1.17it/s]
1|7284|Loss: 0.9193081259727478:  28%|██▊       | 7283/25880 [1:31:08<4:25:30,  1.17it/s]
1|7284|Loss: 0.9193081259727478:  28%|██▊       | 7284/25880 [1:31:09<4:13:01,  1.22it/s]
1|7285|Loss: 0.909267783164978:  28%|██▊       | 7284/25880 [1:31:09<4:13:01,  1.22it/s] 
1|7285|Loss: 0.909267783164978:  28%|██▊       | 7285/25880 [1:31:09<3:54:15,  1.32it/s]
1|7286|Loss: 0.8360273838043213:  28%|██▊       | 7285/25880 [1:31:10<3:54:15,  1.32it/s]
1|7286|Loss: 0.8360273838043213:  28%|██▊       | 7286/25880 [1:31:10<3:48:33,  1.36it/s]
1|7287|Loss: 0.8625450730323792:  28%|██▊       | 7286/25880 [1:31:10<3:48:33,  1.36it/s]
1|7287|Loss: 0.8625450730323792:  28%|██▊       | 7287/25880 [1:31:11<3:53:07,  1.33it/s]
1|7288|Loss: 0.9298520088195801:  28%|██▊       | 7287/25880 [1:31:11<3:53:07,  1.33it/s]
1|7288|Loss: 0.9298520088195801:  28%|██▊       | 7288/25880 [1:31:11<3:45:36,  1.37it/s]
1|7289|Loss: 0.7732665538787842:  28%|██▊       | 7288/25880 [1:31:12<3:45:36,  1.37it/s]
1|7289|Loss: 0.7732665538787842:  28%|██▊       | 7289/25880 [1:31:12<3:42:13,  1.39it/s]
1|7290|Loss: 0.8976945281028748:  28%|██▊       | 7289/25880 [1:31:12<3:42:13,  1.39it/s]
1|7290|Loss: 0.8976945281028748:  28%|██▊       | 7290/25880 [1:31:13<3:36:05,  1.43it/s]
1|7291|Loss: 0.7931685447692871:  28%|██▊       | 7290/25880 [1:31:13<3:36:05,  1.43it/s]
1|7291|Loss: 0.7931685447692871:  28%|██▊       | 7291/25880 [1:31:14<3:45:41,  1.37it/s]
1|7292|Loss: 0.9481394290924072:  28%|██▊       | 7291/25880 [1:31:14<3:45:41,  1.37it/s]
1|7292|Loss: 0.9481394290924072:  28%|██▊       | 7292/25880 [1:31:14<3:40:59,  1.40it/s]
1|7293|Loss: 0.8056549429893494:  28%|██▊       | 7292/25880 [1:31:15<3:40:59,  1.40it/s]
1|7293|Loss: 0.8056549429893494:  28%|██▊       | 7293/25880 [1:31:15<3:41:10,  1.40it/s]
1|7294|Loss: 0.8188011646270752:  28%|██▊       | 7293/25880 [1:31:15<3:41:10,  1.40it/s]
1|7294|Loss: 0.8188011646270752:  28%|██▊       | 7294/25880 [1:31:16<3:39:58,  1.41it/s]
1|7295|Loss: 0.8313316702842712:  28%|██▊       | 7294/25880 [1:31:16<3:39:58,  1.41it/s]
1|7295|Loss: 0.8313316702842712:  28%|██▊       | 7295/25880 [1:31:16<3:19:38,  1.55it/s]
1|7296|Loss: 0.8071392178535461:  28%|██▊       | 7295/25880 [1:31:16<3:19:38,  1.55it/s]
1|7296|Loss: 0.8071392178535461:  28%|██▊       | 7296/25880 [1:31:17<3:13:32,  1.60it/s]
1|7297|Loss: 0.7962979674339294:  28%|██▊       | 7296/25880 [1:31:17<3:13:32,  1.60it/s]
1|7297|Loss: 0.7962979674339294:  28%|██▊       | 7297/25880 [1:31:17<3:21:57,  1.53it/s]
1|7298|Loss: 1.0514165163040161:  28%|██▊       | 7297/25880 [1:31:18<3:21:57,  1.53it/s]
1|7298|Loss: 1.0514165163040161:  28%|██▊       | 7298/25880 [1:31:18<3:12:52,  1.61it/s]
1|7299|Loss: 0.9156980514526367:  28%|██▊       | 7298/25880 [1:31:18<3:12:52,  1.61it/s]
1|7299|Loss: 0.9156980514526367:  28%|██▊       | 7299/25880 [1:31:19<3:24:05,  1.52it/s]
1|7300|Loss: 0.7622693181037903:  28%|██▊       | 7299/25880 [1:31:19<3:24:05,  1.52it/s]
1|7300|Loss: 0.7622693181037903:  28%|██▊       | 7300/25880 [1:31:20<3:39:04,  1.41it/s]
1|7301|Loss: 0.6643573641777039:  28%|██▊       | 7300/25880 [1:31:20<3:39:04,  1.41it/s]
1|7301|Loss: 0.6643573641777039:  28%|██▊       | 7301/25880 [1:31:20<3:47:10,  1.36it/s]
1|7302|Loss: 0.9801952242851257:  28%|██▊       | 7301/25880 [1:31:21<3:47:10,  1.36it/s]
1|7302|Loss: 0.9801952242851257:  28%|██▊       | 7302/25880 [1:31:21<3:46:02,  1.37it/s]
1|7303|Loss: 0.8088567852973938:  28%|██▊       | 7302/25880 [1:31:21<3:46:02,  1.37it/s]
1|7303|Loss: 0.8088567852973938:  28%|██▊       | 7303/25880 [1:31:22<3:38:44,  1.42it/s]
1|7304|Loss: 0.8457261323928833:  28%|██▊       | 7303/25880 [1:31:22<3:38:44,  1.42it/s]
1|7304|Loss: 0.8457261323928833:  28%|██▊       | 7304/25880 [1:31:23<3:49:35,  1.35it/s]
1|7305|Loss: 0.831144392490387:  28%|██▊       | 7304/25880 [1:31:23<3:49:35,  1.35it/s] 
1|7305|Loss: 0.831144392490387:  28%|██▊       | 7305/25880 [1:31:24<4:11:28,  1.23it/s]
1|7306|Loss: 0.8188364505767822:  28%|██▊       | 7305/25880 [1:31:24<4:11:28,  1.23it/s]
1|7306|Loss: 0.8188364505767822:  28%|██▊       | 7306/25880 [1:31:24<4:07:05,  1.25it/s]
1|7307|Loss: 0.848694384098053:  28%|██▊       | 7306/25880 [1:31:25<4:07:05,  1.25it/s] 
1|7307|Loss: 0.848694384098053:  28%|██▊       | 7307/25880 [1:31:25<4:01:44,  1.28it/s]
1|7308|Loss: 0.8604803085327148:  28%|██▊       | 7307/25880 [1:31:25<4:01:44,  1.28it/s]
1|7308|Loss: 0.8604803085327148:  28%|██▊       | 7308/25880 [1:31:26<3:58:16,  1.30it/s]
1|7309|Loss: 0.898932158946991:  28%|██▊       | 7308/25880 [1:31:26<3:58:16,  1.30it/s] 
1|7309|Loss: 0.898932158946991:  28%|██▊       | 7309/25880 [1:31:26<3:48:06,  1.36it/s]
1|7310|Loss: 0.7919347882270813:  28%|██▊       | 7309/25880 [1:31:27<3:48:06,  1.36it/s]
1|7310|Loss: 0.7919347882270813:  28%|██▊       | 7310/25880 [1:31:27<3:50:03,  1.35it/s]
1|7311|Loss: 0.9326827526092529:  28%|██▊       | 7310/25880 [1:31:28<3:50:03,  1.35it/s]
1|7311|Loss: 0.9326827526092529:  28%|██▊       | 7311/25880 [1:31:28<3:48:06,  1.36it/s]
1|7312|Loss: 0.8606563806533813:  28%|██▊       | 7311/25880 [1:31:28<3:48:06,  1.36it/s]
1|7312|Loss: 0.8606563806533813:  28%|██▊       | 7312/25880 [1:31:29<3:40:04,  1.41it/s]
1|7313|Loss: 0.8347715735435486:  28%|██▊       | 7312/25880 [1:31:29<3:40:04,  1.41it/s]
1|7313|Loss: 0.8347715735435486:  28%|██▊       | 7313/25880 [1:31:29<3:50:44,  1.34it/s]
1|7314|Loss: 0.8643331527709961:  28%|██▊       | 7313/25880 [1:31:30<3:50:44,  1.34it/s]
1|7314|Loss: 0.8643331527709961:  28%|██▊       | 7314/25880 [1:31:30<3:59:33,  1.29it/s]
1|7315|Loss: 0.8084926605224609:  28%|██▊       | 7314/25880 [1:31:31<3:59:33,  1.29it/s]
1|7315|Loss: 0.8084926605224609:  28%|██▊       | 7315/25880 [1:31:31<4:07:23,  1.25it/s]
1|7316|Loss: 0.8512306809425354:  28%|██▊       | 7315/25880 [1:31:32<4:07:23,  1.25it/s]
1|7316|Loss: 0.8512306809425354:  28%|██▊       | 7316/25880 [1:31:32<3:55:56,  1.31it/s]
1|7317|Loss: 0.8709014058113098:  28%|██▊       | 7316/25880 [1:31:32<3:55:56,  1.31it/s]
1|7317|Loss: 0.8709014058113098:  28%|██▊       | 7317/25880 [1:31:33<3:59:36,  1.29it/s]
1|7318|Loss: 0.9597342014312744:  28%|██▊       | 7317/25880 [1:31:33<3:59:36,  1.29it/s]
1|7318|Loss: 0.9597342014312744:  28%|██▊       | 7318/25880 [1:31:33<3:58:24,  1.30it/s]
1|7319|Loss: 0.940339982509613:  28%|██▊       | 7318/25880 [1:31:34<3:58:24,  1.30it/s] 
1|7319|Loss: 0.940339982509613:  28%|██▊       | 7319/25880 [1:31:34<3:46:14,  1.37it/s]
1|7320|Loss: 0.8913485407829285:  28%|██▊       | 7319/25880 [1:31:34<3:46:14,  1.37it/s]
1|7320|Loss: 0.8913485407829285:  28%|██▊       | 7320/25880 [1:31:35<3:41:40,  1.40it/s]
1|7321|Loss: 0.776734471321106:  28%|██▊       | 7320/25880 [1:31:35<3:41:40,  1.40it/s] 
1|7321|Loss: 0.776734471321106:  28%|██▊       | 7321/25880 [1:31:35<3:34:48,  1.44it/s]
1|7322|Loss: 0.867597222328186:  28%|██▊       | 7321/25880 [1:31:36<3:34:48,  1.44it/s]
1|7322|Loss: 0.867597222328186:  28%|██▊       | 7322/25880 [1:31:36<3:34:38,  1.44it/s]
1|7323|Loss: 0.9766871929168701:  28%|██▊       | 7322/25880 [1:31:36<3:34:38,  1.44it/s]
1|7323|Loss: 0.9766871929168701:  28%|██▊       | 7323/25880 [1:31:37<3:38:31,  1.42it/s]
1|7324|Loss: 0.766444206237793:  28%|██▊       | 7323/25880 [1:31:37<3:38:31,  1.42it/s] 
1|7324|Loss: 0.766444206237793:  28%|██▊       | 7324/25880 [1:31:38<3:49:08,  1.35it/s]
1|7325|Loss: 0.9413403868675232:  28%|██▊       | 7324/25880 [1:31:38<3:49:08,  1.35it/s]
1|7325|Loss: 0.9413403868675232:  28%|██▊       | 7325/25880 [1:31:38<3:50:47,  1.34it/s]
1|7326|Loss: 0.7958104014396667:  28%|██▊       | 7325/25880 [1:31:39<3:50:47,  1.34it/s]
1|7326|Loss: 0.7958104014396667:  28%|██▊       | 7326/25880 [1:31:39<3:53:25,  1.32it/s]
1|7327|Loss: 0.8421438932418823:  28%|██▊       | 7326/25880 [1:31:39<3:53:25,  1.32it/s]
1|7327|Loss: 0.8421438932418823:  28%|██▊       | 7327/25880 [1:31:40<3:53:07,  1.33it/s]
1|7328|Loss: 1.0278979539871216:  28%|██▊       | 7327/25880 [1:31:40<3:53:07,  1.33it/s]
1|7328|Loss: 1.0278979539871216:  28%|██▊       | 7328/25880 [1:31:40<3:37:23,  1.42it/s]
1|7329|Loss: 0.7862058877944946:  28%|██▊       | 7328/25880 [1:31:41<3:37:23,  1.42it/s]
1|7329|Loss: 0.7862058877944946:  28%|██▊       | 7329/25880 [1:31:41<3:34:22,  1.44it/s]
1|7330|Loss: 0.8923547863960266:  28%|██▊       | 7329/25880 [1:31:42<3:34:22,  1.44it/s]
1|7330|Loss: 0.8923547863960266:  28%|██▊       | 7330/25880 [1:31:42<3:44:43,  1.38it/s]
1|7331|Loss: 0.778788685798645:  28%|██▊       | 7330/25880 [1:31:42<3:44:43,  1.38it/s] 
1|7331|Loss: 0.778788685798645:  28%|██▊       | 7331/25880 [1:31:42<3:25:43,  1.50it/s]
1|7332|Loss: 0.6704586744308472:  28%|██▊       | 7331/25880 [1:31:43<3:25:43,  1.50it/s]
1|7332|Loss: 0.6704586744308472:  28%|██▊       | 7332/25880 [1:31:43<3:47:08,  1.36it/s]
1|7333|Loss: 0.7172342538833618:  28%|██▊       | 7332/25880 [1:31:44<3:47:08,  1.36it/s]
1|7333|Loss: 0.7172342538833618:  28%|██▊       | 7333/25880 [1:31:44<3:39:32,  1.41it/s]
1|7334|Loss: 0.8259364366531372:  28%|██▊       | 7333/25880 [1:31:44<3:39:32,  1.41it/s]
1|7334|Loss: 0.8259364366531372:  28%|██▊       | 7334/25880 [1:31:45<3:52:08,  1.33it/s]
1|7335|Loss: 0.8689894080162048:  28%|██▊       | 7334/25880 [1:31:45<3:52:08,  1.33it/s]
1|7335|Loss: 0.8689894080162048:  28%|██▊       | 7335/25880 [1:31:46<4:01:36,  1.28it/s]
1|7336|Loss: 0.8517122268676758:  28%|██▊       | 7335/25880 [1:31:46<4:01:36,  1.28it/s]
1|7336|Loss: 0.8517122268676758:  28%|██▊       | 7336/25880 [1:31:46<4:03:57,  1.27it/s]
1|7337|Loss: 0.8416165709495544:  28%|██▊       | 7336/25880 [1:31:47<4:03:57,  1.27it/s]
1|7337|Loss: 0.8416165709495544:  28%|██▊       | 7337/25880 [1:31:47<4:00:26,  1.29it/s]
1|7338|Loss: 0.7750585079193115:  28%|██▊       | 7337/25880 [1:31:48<4:00:26,  1.29it/s]
1|7338|Loss: 0.7750585079193115:  28%|██▊       | 7338/25880 [1:31:48<3:55:52,  1.31it/s]
1|7339|Loss: 0.8397715091705322:  28%|██▊       | 7338/25880 [1:31:48<3:55:52,  1.31it/s]
1|7339|Loss: 0.8397715091705322:  28%|██▊       | 7339/25880 [1:31:49<3:43:53,  1.38it/s]
1|7340|Loss: 0.8689610362052917:  28%|██▊       | 7339/25880 [1:31:49<3:43:53,  1.38it/s]
1|7340|Loss: 0.8689610362052917:  28%|██▊       | 7340/25880 [1:31:49<3:49:17,  1.35it/s]
1|7341|Loss: 0.7369889616966248:  28%|██▊       | 7340/25880 [1:31:50<3:49:17,  1.35it/s]
1|7341|Loss: 0.7369889616966248:  28%|██▊       | 7341/25880 [1:31:50<3:56:31,  1.31it/s]
1|7342|Loss: 0.9861556887626648:  28%|██▊       | 7341/25880 [1:31:51<3:56:31,  1.31it/s]
1|7342|Loss: 0.9861556887626648:  28%|██▊       | 7342/25880 [1:31:51<3:41:33,  1.39it/s]
1|7343|Loss: 0.8498945236206055:  28%|██▊       | 7342/25880 [1:31:51<3:41:33,  1.39it/s]
1|7343|Loss: 0.8498945236206055:  28%|██▊       | 7343/25880 [1:31:52<3:56:48,  1.30it/s]
1|7344|Loss: 0.8659438490867615:  28%|██▊       | 7343/25880 [1:31:52<3:56:48,  1.30it/s]
1|7344|Loss: 0.8659438490867615:  28%|██▊       | 7344/25880 [1:31:52<3:51:04,  1.34it/s]
1|7345|Loss: 0.7630366683006287:  28%|██▊       | 7344/25880 [1:31:53<3:51:04,  1.34it/s]
1|7345|Loss: 0.7630366683006287:  28%|██▊       | 7345/25880 [1:31:53<3:55:31,  1.31it/s]
1|7346|Loss: 0.8428314328193665:  28%|██▊       | 7345/25880 [1:31:54<3:55:31,  1.31it/s]
1|7346|Loss: 0.8428314328193665:  28%|██▊       | 7346/25880 [1:31:54<3:45:44,  1.37it/s]
1|7347|Loss: 0.828033447265625:  28%|██▊       | 7346/25880 [1:31:54<3:45:44,  1.37it/s] 
1|7347|Loss: 0.828033447265625:  28%|██▊       | 7347/25880 [1:31:55<3:44:33,  1.38it/s]
1|7348|Loss: 0.9011238217353821:  28%|██▊       | 7347/25880 [1:31:55<3:44:33,  1.38it/s]
1|7348|Loss: 0.9011238217353821:  28%|██▊       | 7348/25880 [1:31:55<3:37:08,  1.42it/s]
1|7349|Loss: 0.7552295327186584:  28%|██▊       | 7348/25880 [1:31:56<3:37:08,  1.42it/s]
1|7349|Loss: 0.7552295327186584:  28%|██▊       | 7349/25880 [1:31:56<3:47:55,  1.36it/s]
1|7350|Loss: 1.0388622283935547:  28%|██▊       | 7349/25880 [1:31:57<3:47:55,  1.36it/s]
1|7350|Loss: 1.0388622283935547:  28%|██▊       | 7350/25880 [1:31:57<4:03:45,  1.27it/s]
1|7351|Loss: 0.7187857031822205:  28%|██▊       | 7350/25880 [1:31:57<4:03:45,  1.27it/s]
1|7351|Loss: 0.7187857031822205:  28%|██▊       | 7351/25880 [1:31:58<3:53:03,  1.33it/s]
1|7352|Loss: 0.7595582008361816:  28%|██▊       | 7351/25880 [1:31:58<3:53:03,  1.33it/s]
1|7352|Loss: 0.7595582008361816:  28%|██▊       | 7352/25880 [1:31:58<3:48:42,  1.35it/s]
1|7353|Loss: 0.7831301689147949:  28%|██▊       | 7352/25880 [1:31:59<3:48:42,  1.35it/s]
1|7353|Loss: 0.7831301689147949:  28%|██▊       | 7353/25880 [1:31:59<3:54:38,  1.32it/s]
1|7354|Loss: 0.8653324246406555:  28%|██▊       | 7353/25880 [1:32:00<3:54:38,  1.32it/s]
1|7354|Loss: 0.8653324246406555:  28%|██▊       | 7354/25880 [1:32:00<3:54:18,  1.32it/s]
1|7355|Loss: 0.864722728729248:  28%|██▊       | 7354/25880 [1:32:00<3:54:18,  1.32it/s] 
1|7355|Loss: 0.864722728729248:  28%|██▊       | 7355/25880 [1:32:00<3:39:10,  1.41it/s]
1|7356|Loss: 0.7462531328201294:  28%|██▊       | 7355/25880 [1:32:01<3:39:10,  1.41it/s]
1|7356|Loss: 0.7462531328201294:  28%|██▊       | 7356/25880 [1:32:01<3:43:00,  1.38it/s]
1|7357|Loss: 0.7956262230873108:  28%|██▊       | 7356/25880 [1:32:02<3:43:00,  1.38it/s]
1|7357|Loss: 0.7956262230873108:  28%|██▊       | 7357/25880 [1:32:02<3:55:41,  1.31it/s]
1|7358|Loss: 0.8091755509376526:  28%|██▊       | 7357/25880 [1:32:02<3:55:41,  1.31it/s]
1|7358|Loss: 0.8091755509376526:  28%|██▊       | 7358/25880 [1:32:03<3:35:35,  1.43it/s]
1|7359|Loss: 0.8204742074012756:  28%|██▊       | 7358/25880 [1:32:03<3:35:35,  1.43it/s]
1|7359|Loss: 0.8204742074012756:  28%|██▊       | 7359/25880 [1:32:03<3:40:03,  1.40it/s]
1|7360|Loss: 0.8649208545684814:  28%|██▊       | 7359/25880 [1:32:04<3:40:03,  1.40it/s]
1|7360|Loss: 0.8649208545684814:  28%|██▊       | 7360/25880 [1:32:04<3:43:49,  1.38it/s]
1|7361|Loss: 0.8024587631225586:  28%|██▊       | 7360/25880 [1:32:05<3:43:49,  1.38it/s]
1|7361|Loss: 0.8024587631225586:  28%|██▊       | 7361/25880 [1:32:05<3:51:38,  1.33it/s]
1|7362|Loss: 0.7915509939193726:  28%|██▊       | 7361/25880 [1:32:05<3:51:38,  1.33it/s]
1|7362|Loss: 0.7915509939193726:  28%|██▊       | 7362/25880 [1:32:06<3:42:23,  1.39it/s]
1|7363|Loss: 0.9262290000915527:  28%|██▊       | 7362/25880 [1:32:06<3:42:23,  1.39it/s]
1|7363|Loss: 0.9262290000915527:  28%|██▊       | 7363/25880 [1:32:06<3:41:11,  1.40it/s]
1|7364|Loss: 0.867341160774231:  28%|██▊       | 7363/25880 [1:32:07<3:41:11,  1.40it/s] 
1|7364|Loss: 0.867341160774231:  28%|██▊       | 7364/25880 [1:32:07<3:42:25,  1.39it/s]
1|7365|Loss: 0.8332029581069946:  28%|██▊       | 7364/25880 [1:32:07<3:42:25,  1.39it/s]
1|7365|Loss: 0.8332029581069946:  28%|██▊       | 7365/25880 [1:32:08<3:43:22,  1.38it/s]
1|7366|Loss: 0.8564456105232239:  28%|██▊       | 7365/25880 [1:32:08<3:43:22,  1.38it/s]
1|7366|Loss: 0.8564456105232239:  28%|██▊       | 7366/25880 [1:32:09<3:54:13,  1.32it/s]
1|7367|Loss: 0.8200085163116455:  28%|██▊       | 7366/25880 [1:32:09<3:54:13,  1.32it/s]
1|7367|Loss: 0.8200085163116455:  28%|██▊       | 7367/25880 [1:32:09<4:04:38,  1.26it/s]
1|7368|Loss: 0.8506775498390198:  28%|██▊       | 7367/25880 [1:32:10<4:04:38,  1.26it/s]
1|7368|Loss: 0.8506775498390198:  28%|██▊       | 7368/25880 [1:32:10<4:01:42,  1.28it/s]
1|7369|Loss: 0.8317958116531372:  28%|██▊       | 7368/25880 [1:32:11<4:01:42,  1.28it/s]
1|7369|Loss: 0.8317958116531372:  28%|██▊       | 7369/25880 [1:32:11<3:57:15,  1.30it/s]
1|7370|Loss: 0.8616198301315308:  28%|██▊       | 7369/25880 [1:32:11<3:57:15,  1.30it/s]
1|7370|Loss: 0.8616198301315308:  28%|██▊       | 7370/25880 [1:32:12<3:59:06,  1.29it/s]
1|7371|Loss: 0.9326128959655762:  28%|██▊       | 7370/25880 [1:32:12<3:59:06,  1.29it/s]
1|7371|Loss: 0.9326128959655762:  28%|██▊       | 7371/25880 [1:32:13<3:57:01,  1.30it/s]
1|7372|Loss: 0.8692336678504944:  28%|██▊       | 7371/25880 [1:32:13<3:57:01,  1.30it/s]
1|7372|Loss: 0.8692336678504944:  28%|██▊       | 7372/25880 [1:32:13<3:51:14,  1.33it/s]
1|7373|Loss: 0.8390652537345886:  28%|██▊       | 7372/25880 [1:32:14<3:51:14,  1.33it/s]
1|7373|Loss: 0.8390652537345886:  28%|██▊       | 7373/25880 [1:32:14<3:38:03,  1.41it/s]
1|7374|Loss: 0.9005929827690125:  28%|██▊       | 7373/25880 [1:32:14<3:38:03,  1.41it/s]
1|7374|Loss: 0.9005929827690125:  28%|██▊       | 7374/25880 [1:32:14<3:29:01,  1.48it/s]
1|7375|Loss: 0.7124356627464294:  28%|██▊       | 7374/25880 [1:32:15<3:29:01,  1.48it/s]
1|7375|Loss: 0.7124356627464294:  28%|██▊       | 7375/25880 [1:32:15<3:23:30,  1.52it/s]
1|7376|Loss: 0.9297211170196533:  28%|██▊       | 7375/25880 [1:32:15<3:23:30,  1.52it/s]
1|7376|Loss: 0.9297211170196533:  29%|██▊       | 7376/25880 [1:32:16<3:32:13,  1.45it/s]
1|7377|Loss: 0.7937406897544861:  29%|██▊       | 7376/25880 [1:32:16<3:32:13,  1.45it/s]
1|7377|Loss: 0.7937406897544861:  29%|██▊       | 7377/25880 [1:32:17<3:35:10,  1.43it/s]
1|7378|Loss: 0.9095566272735596:  29%|██▊       | 7377/25880 [1:32:17<3:35:10,  1.43it/s]
1|7378|Loss: 0.9095566272735596:  29%|██▊       | 7378/25880 [1:32:17<3:37:28,  1.42it/s]
1|7379|Loss: 0.9768564105033875:  29%|██▊       | 7378/25880 [1:32:18<3:37:28,  1.42it/s]
1|7379|Loss: 0.9768564105033875:  29%|██▊       | 7379/25880 [1:32:18<3:31:27,  1.46it/s]
1|7380|Loss: 0.8751617670059204:  29%|██▊       | 7379/25880 [1:32:18<3:31:27,  1.46it/s]
1|7380|Loss: 0.8751617670059204:  29%|██▊       | 7380/25880 [1:32:19<3:31:35,  1.46it/s]
1|7381|Loss: 0.7745497822761536:  29%|██▊       | 7380/25880 [1:32:19<3:31:35,  1.46it/s]
1|7381|Loss: 0.7745497822761536:  29%|██▊       | 7381/25880 [1:32:19<3:24:27,  1.51it/s]
1|7382|Loss: 0.7158293128013611:  29%|██▊       | 7381/25880 [1:32:19<3:24:27,  1.51it/s]
1|7382|Loss: 0.7158293128013611:  29%|██▊       | 7382/25880 [1:32:20<3:12:31,  1.60it/s]
1|7383|Loss: 0.7566818594932556:  29%|██▊       | 7382/25880 [1:32:20<3:12:31,  1.60it/s]
1|7383|Loss: 0.7566818594932556:  29%|██▊       | 7383/25880 [1:32:20<3:03:23,  1.68it/s]
1|7384|Loss: 0.7802070379257202:  29%|██▊       | 7383/25880 [1:32:21<3:03:23,  1.68it/s]
1|7384|Loss: 0.7802070379257202:  29%|██▊       | 7384/25880 [1:32:21<3:15:50,  1.57it/s]
1|7385|Loss: 0.7263264656066895:  29%|██▊       | 7384/25880 [1:32:21<3:15:50,  1.57it/s]
1|7385|Loss: 0.7263264656066895:  29%|██▊       | 7385/25880 [1:32:22<3:39:49,  1.40it/s]
1|7386|Loss: 0.7666832804679871:  29%|██▊       | 7385/25880 [1:32:22<3:39:49,  1.40it/s]
1|7386|Loss: 0.7666832804679871:  29%|██▊       | 7386/25880 [1:32:23<3:33:35,  1.44it/s]
1|7387|Loss: 0.813962459564209:  29%|██▊       | 7386/25880 [1:32:23<3:33:35,  1.44it/s] 
1|7387|Loss: 0.813962459564209:  29%|██▊       | 7387/25880 [1:32:23<3:25:11,  1.50it/s]
1|7388|Loss: 0.8784468770027161:  29%|██▊       | 7387/25880 [1:32:23<3:25:11,  1.50it/s]
1|7388|Loss: 0.8784468770027161:  29%|██▊       | 7388/25880 [1:32:24<3:27:10,  1.49it/s]
1|7389|Loss: 0.9644389152526855:  29%|██▊       | 7388/25880 [1:32:24<3:27:10,  1.49it/s]
1|7389|Loss: 0.9644389152526855:  29%|██▊       | 7389/25880 [1:32:25<3:39:19,  1.41it/s]
1|7390|Loss: 0.6589486598968506:  29%|██▊       | 7389/25880 [1:32:25<3:39:19,  1.41it/s]
1|7390|Loss: 0.6589486598968506:  29%|██▊       | 7390/25880 [1:32:26<3:56:30,  1.30it/s]
1|7391|Loss: 0.8644364476203918:  29%|██▊       | 7390/25880 [1:32:26<3:56:30,  1.30it/s]
1|7391|Loss: 0.8644364476203918:  29%|██▊       | 7391/25880 [1:32:26<3:55:27,  1.31it/s]
1|7392|Loss: 0.9459521174430847:  29%|██▊       | 7391/25880 [1:32:27<3:55:27,  1.31it/s]
1|7392|Loss: 0.9459521174430847:  29%|██▊       | 7392/25880 [1:32:27<3:43:23,  1.38it/s]
1|7393|Loss: 1.0329381227493286:  29%|██▊       | 7392/25880 [1:32:27<3:43:23,  1.38it/s]
1|7393|Loss: 1.0329381227493286:  29%|██▊       | 7393/25880 [1:32:28<3:42:42,  1.38it/s]
1|7394|Loss: 0.8842602968215942:  29%|██▊       | 7393/25880 [1:32:28<3:42:42,  1.38it/s]
1|7394|Loss: 0.8842602968215942:  29%|██▊       | 7394/25880 [1:32:28<3:43:32,  1.38it/s]
1|7395|Loss: 0.819874107837677:  29%|██▊       | 7394/25880 [1:32:29<3:43:32,  1.38it/s] 
1|7395|Loss: 0.819874107837677:  29%|██▊       | 7395/25880 [1:32:29<3:43:32,  1.38it/s]
1|7396|Loss: 0.9185469150543213:  29%|██▊       | 7395/25880 [1:32:29<3:43:32,  1.38it/s]
1|7396|Loss: 0.9185469150543213:  29%|██▊       | 7396/25880 [1:32:30<3:35:38,  1.43it/s]
1|7397|Loss: 0.8694156408309937:  29%|██▊       | 7396/25880 [1:32:30<3:35:38,  1.43it/s]
1|7397|Loss: 0.8694156408309937:  29%|██▊       | 7397/25880 [1:32:30<3:36:14,  1.42it/s]
1|7398|Loss: 0.8778720498085022:  29%|██▊       | 7397/25880 [1:32:31<3:36:14,  1.42it/s]
1|7398|Loss: 0.8778720498085022:  29%|██▊       | 7398/25880 [1:32:31<3:36:31,  1.42it/s]
1|7399|Loss: 0.8364700078964233:  29%|██▊       | 7398/25880 [1:32:31<3:36:31,  1.42it/s]
1|7399|Loss: 0.8364700078964233:  29%|██▊       | 7399/25880 [1:32:32<3:31:28,  1.46it/s]
1|7400|Loss: 0.8233354687690735:  29%|██▊       | 7399/25880 [1:32:32<3:31:28,  1.46it/s]
1|7400|Loss: 0.8233354687690735:  29%|██▊       | 7400/25880 [1:32:33<3:38:08,  1.41it/s]
1|7401|Loss: 0.8929196000099182:  29%|██▊       | 7400/25880 [1:32:33<3:38:08,  1.41it/s]
1|7401|Loss: 0.8929196000099182:  29%|██▊       | 7401/25880 [1:32:33<3:52:27,  1.32it/s]
1|7402|Loss: 0.8424015641212463:  29%|██▊       | 7401/25880 [1:32:34<3:52:27,  1.32it/s]
1|7402|Loss: 0.8424015641212463:  29%|██▊       | 7402/25880 [1:32:34<4:00:22,  1.28it/s]
1|7403|Loss: 0.8780922293663025:  29%|██▊       | 7402/25880 [1:32:35<4:00:22,  1.28it/s]
1|7403|Loss: 0.8780922293663025:  29%|██▊       | 7403/25880 [1:32:35<3:48:48,  1.35it/s]
1|7404|Loss: 0.88897305727005:  29%|██▊       | 7403/25880 [1:32:35<3:48:48,  1.35it/s]  
1|7404|Loss: 0.88897305727005:  29%|██▊       | 7404/25880 [1:32:36<3:53:28,  1.32it/s]
1|7405|Loss: 0.8643138408660889:  29%|██▊       | 7404/25880 [1:32:36<3:53:28,  1.32it/s]
1|7405|Loss: 0.8643138408660889:  29%|██▊       | 7405/25880 [1:32:36<3:36:22,  1.42it/s]
1|7406|Loss: 0.7515603303909302:  29%|██▊       | 7405/25880 [1:32:37<3:36:22,  1.42it/s]
1|7406|Loss: 0.7515603303909302:  29%|██▊       | 7406/25880 [1:32:37<3:33:41,  1.44it/s]
1|7407|Loss: 0.7883582711219788:  29%|██▊       | 7406/25880 [1:32:37<3:33:41,  1.44it/s]
1|7407|Loss: 0.7883582711219788:  29%|██▊       | 7407/25880 [1:32:38<3:43:46,  1.38it/s]
1|7408|Loss: 0.7779858708381653:  29%|██▊       | 7407/25880 [1:32:38<3:43:46,  1.38it/s]
1|7408|Loss: 0.7779858708381653:  29%|██▊       | 7408/25880 [1:32:39<3:54:26,  1.31it/s]
1|7409|Loss: 0.7476813793182373:  29%|██▊       | 7408/25880 [1:32:39<3:54:26,  1.31it/s]
1|7409|Loss: 0.7476813793182373:  29%|██▊       | 7409/25880 [1:32:39<3:35:20,  1.43it/s]
1|7410|Loss: 0.864295244216919:  29%|██▊       | 7409/25880 [1:32:39<3:35:20,  1.43it/s] 
1|7410|Loss: 0.864295244216919:  29%|██▊       | 7410/25880 [1:32:40<3:22:26,  1.52it/s]
1|7411|Loss: 0.9048718214035034:  29%|██▊       | 7410/25880 [1:32:40<3:22:26,  1.52it/s]
1|7411|Loss: 0.9048718214035034:  29%|██▊       | 7411/25880 [1:32:40<3:15:26,  1.58it/s]
1|7412|Loss: 0.799458920955658:  29%|██▊       | 7411/25880 [1:32:41<3:15:26,  1.58it/s] 
1|7412|Loss: 0.799458920955658:  29%|██▊       | 7412/25880 [1:32:41<3:19:06,  1.55it/s]
1|7413|Loss: 0.9621995687484741:  29%|██▊       | 7412/25880 [1:32:41<3:19:06,  1.55it/s]
1|7413|Loss: 0.9621995687484741:  29%|██▊       | 7413/25880 [1:32:42<3:19:13,  1.54it/s]
1|7414|Loss: 0.9045289754867554:  29%|██▊       | 7413/25880 [1:32:42<3:19:13,  1.54it/s]
1|7414|Loss: 0.9045289754867554:  29%|██▊       | 7414/25880 [1:32:42<3:38:44,  1.41it/s]
1|7415|Loss: 0.8130463361740112:  29%|██▊       | 7414/25880 [1:32:43<3:38:44,  1.41it/s]
1|7415|Loss: 0.8130463361740112:  29%|██▊       | 7415/25880 [1:32:43<3:49:04,  1.34it/s]
1|7416|Loss: 0.7200270891189575:  29%|██▊       | 7415/25880 [1:32:44<3:49:04,  1.34it/s]
1|7416|Loss: 0.7200270891189575:  29%|██▊       | 7416/25880 [1:32:44<3:58:55,  1.29it/s]
1|7417|Loss: 0.8286944627761841:  29%|██▊       | 7416/25880 [1:32:44<3:58:55,  1.29it/s]
1|7417|Loss: 0.8286944627761841:  29%|██▊       | 7417/25880 [1:32:45<3:39:11,  1.40it/s]
1|7418|Loss: 0.9706057906150818:  29%|██▊       | 7417/25880 [1:32:45<3:39:11,  1.40it/s]
1|7418|Loss: 0.9706057906150818:  29%|██▊       | 7418/25880 [1:32:45<3:36:00,  1.42it/s]
1|7419|Loss: 0.7351593971252441:  29%|██▊       | 7418/25880 [1:32:46<3:36:00,  1.42it/s]
1|7419|Loss: 0.7351593971252441:  29%|██▊       | 7419/25880 [1:32:46<3:38:54,  1.41it/s]
1|7420|Loss: 0.9275451898574829:  29%|██▊       | 7419/25880 [1:32:46<3:38:54,  1.41it/s]
1|7420|Loss: 0.9275451898574829:  29%|██▊       | 7420/25880 [1:32:47<3:33:15,  1.44it/s]
1|7421|Loss: 0.9981253743171692:  29%|██▊       | 7420/25880 [1:32:47<3:33:15,  1.44it/s]
1|7421|Loss: 0.9981253743171692:  29%|██▊       | 7421/25880 [1:32:47<3:19:46,  1.54it/s]
1|7422|Loss: 0.7929289937019348:  29%|██▊       | 7421/25880 [1:32:48<3:19:46,  1.54it/s]
1|7422|Loss: 0.7929289937019348:  29%|██▊       | 7422/25880 [1:32:48<3:20:11,  1.54it/s]
1|7423|Loss: 0.836764931678772:  29%|██▊       | 7422/25880 [1:32:48<3:20:11,  1.54it/s] 
1|7423|Loss: 0.836764931678772:  29%|██▊       | 7423/25880 [1:32:49<3:24:12,  1.51it/s]
1|7424|Loss: 0.782008707523346:  29%|██▊       | 7423/25880 [1:32:49<3:24:12,  1.51it/s]
1|7424|Loss: 0.782008707523346:  29%|██▊       | 7424/25880 [1:32:49<3:30:30,  1.46it/s]
1|7425|Loss: 0.9024251103401184:  29%|██▊       | 7424/25880 [1:32:50<3:30:30,  1.46it/s]
1|7425|Loss: 0.9024251103401184:  29%|██▊       | 7425/25880 [1:32:50<3:24:04,  1.51it/s]
1|7426|Loss: 0.852811872959137:  29%|██▊       | 7425/25880 [1:32:50<3:24:04,  1.51it/s] 
1|7426|Loss: 0.852811872959137:  29%|██▊       | 7426/25880 [1:32:51<3:27:25,  1.48it/s]
1|7427|Loss: 0.8406685590744019:  29%|██▊       | 7426/25880 [1:32:51<3:27:25,  1.48it/s]
1|7427|Loss: 0.8406685590744019:  29%|██▊       | 7427/25880 [1:32:51<3:31:56,  1.45it/s]
1|7428|Loss: 0.7453041672706604:  29%|██▊       | 7427/25880 [1:32:52<3:31:56,  1.45it/s]
1|7428|Loss: 0.7453041672706604:  29%|██▊       | 7428/25880 [1:32:52<3:16:51,  1.56it/s]
1|7429|Loss: 0.8302817344665527:  29%|██▊       | 7428/25880 [1:32:52<3:16:51,  1.56it/s]
1|7429|Loss: 0.8302817344665527:  29%|██▊       | 7429/25880 [1:32:53<3:21:07,  1.53it/s]
1|7430|Loss: 0.757737398147583:  29%|██▊       | 7429/25880 [1:32:53<3:21:07,  1.53it/s] 
1|7430|Loss: 0.757737398147583:  29%|██▊       | 7430/25880 [1:32:53<3:29:09,  1.47it/s]
1|7431|Loss: 0.9617505669593811:  29%|██▊       | 7430/25880 [1:32:54<3:29:09,  1.47it/s]
1|7431|Loss: 0.9617505669593811:  29%|██▊       | 7431/25880 [1:32:54<3:27:09,  1.48it/s]
1|7432|Loss: 1.0088908672332764:  29%|██▊       | 7431/25880 [1:32:54<3:27:09,  1.48it/s]
1|7432|Loss: 1.0088908672332764:  29%|██▊       | 7432/25880 [1:32:55<3:28:40,  1.47it/s]
1|7433|Loss: 0.7817541360855103:  29%|██▊       | 7432/25880 [1:32:55<3:28:40,  1.47it/s]
1|7433|Loss: 0.7817541360855103:  29%|██▊       | 7433/25880 [1:32:55<3:37:54,  1.41it/s]
1|7434|Loss: 0.8151023387908936:  29%|██▊       | 7433/25880 [1:32:56<3:37:54,  1.41it/s]
1|7434|Loss: 0.8151023387908936:  29%|██▊       | 7434/25880 [1:32:56<3:40:35,  1.39it/s]
1|7435|Loss: 0.7025343775749207:  29%|██▊       | 7434/25880 [1:32:57<3:40:35,  1.39it/s]
1|7435|Loss: 0.7025343775749207:  29%|██▊       | 7435/25880 [1:32:57<3:41:56,  1.39it/s]
1|7436|Loss: 0.861189603805542:  29%|██▊       | 7435/25880 [1:32:57<3:41:56,  1.39it/s] 
1|7436|Loss: 0.861189603805542:  29%|██▊       | 7436/25880 [1:32:58<3:41:39,  1.39it/s]
1|7437|Loss: 1.0068018436431885:  29%|██▊       | 7436/25880 [1:32:58<3:41:39,  1.39it/s]
1|7437|Loss: 1.0068018436431885:  29%|██▊       | 7437/25880 [1:32:58<3:42:23,  1.38it/s]
1|7438|Loss: 0.8786678910255432:  29%|██▊       | 7437/25880 [1:32:59<3:42:23,  1.38it/s]
1|7438|Loss: 0.8786678910255432:  29%|██▊       | 7438/25880 [1:32:59<3:32:16,  1.45it/s]
1|7439|Loss: 0.9069205522537231:  29%|██▊       | 7438/25880 [1:32:59<3:32:16,  1.45it/s]
1|7439|Loss: 0.9069205522537231:  29%|██▊       | 7439/25880 [1:33:00<3:17:48,  1.55it/s]
1|7440|Loss: 0.8447755575180054:  29%|██▊       | 7439/25880 [1:33:00<3:17:48,  1.55it/s]
1|7440|Loss: 0.8447755575180054:  29%|██▊       | 7440/25880 [1:33:00<3:28:28,  1.47it/s]
1|7441|Loss: 0.9330919981002808:  29%|██▊       | 7440/25880 [1:33:01<3:28:28,  1.47it/s]
1|7441|Loss: 0.9330919981002808:  29%|██▉       | 7441/25880 [1:33:01<3:18:12,  1.55it/s]
1|7442|Loss: 0.8065522313117981:  29%|██▉       | 7441/25880 [1:33:01<3:18:12,  1.55it/s]
1|7442|Loss: 0.8065522313117981:  29%|██▉       | 7442/25880 [1:33:02<3:21:50,  1.52it/s]
1|7443|Loss: 0.7592025399208069:  29%|██▉       | 7442/25880 [1:33:02<3:21:50,  1.52it/s]
1|7443|Loss: 0.7592025399208069:  29%|██▉       | 7443/25880 [1:33:02<3:38:28,  1.41it/s]
1|7444|Loss: 0.7345676422119141:  29%|██▉       | 7443/25880 [1:33:03<3:38:28,  1.41it/s]
1|7444|Loss: 0.7345676422119141:  29%|██▉       | 7444/25880 [1:33:03<3:28:11,  1.48it/s]
1|7445|Loss: 0.8701448440551758:  29%|██▉       | 7444/25880 [1:33:03<3:28:11,  1.48it/s]
1|7445|Loss: 0.8701448440551758:  29%|██▉       | 7445/25880 [1:33:04<3:28:51,  1.47it/s]
1|7446|Loss: 0.8731393814086914:  29%|██▉       | 7445/25880 [1:33:04<3:28:51,  1.47it/s]
1|7446|Loss: 0.8731393814086914:  29%|██▉       | 7446/25880 [1:33:04<3:26:00,  1.49it/s]
1|7447|Loss: 0.6905200481414795:  29%|██▉       | 7446/25880 [1:33:05<3:26:00,  1.49it/s]
1|7447|Loss: 0.6905200481414795:  29%|██▉       | 7447/25880 [1:33:05<3:21:05,  1.53it/s]
1|7448|Loss: 0.7654908895492554:  29%|██▉       | 7447/25880 [1:33:05<3:21:05,  1.53it/s]
1|7448|Loss: 0.7654908895492554:  29%|██▉       | 7448/25880 [1:33:06<3:17:13,  1.56it/s]
1|7449|Loss: 0.7480518221855164:  29%|██▉       | 7448/25880 [1:33:06<3:17:13,  1.56it/s]
1|7449|Loss: 0.7480518221855164:  29%|██▉       | 7449/25880 [1:33:06<3:14:24,  1.58it/s]
1|7450|Loss: 0.7406160235404968:  29%|██▉       | 7449/25880 [1:33:07<3:14:24,  1.58it/s]
1|7450|Loss: 0.7406160235404968:  29%|██▉       | 7450/25880 [1:33:07<3:28:34,  1.47it/s]
1|7451|Loss: 0.8619128465652466:  29%|██▉       | 7450/25880 [1:33:07<3:28:34,  1.47it/s]
1|7451|Loss: 0.8619128465652466:  29%|██▉       | 7451/25880 [1:33:08<3:35:32,  1.42it/s]
1|7452|Loss: 0.7458042502403259:  29%|██▉       | 7451/25880 [1:33:08<3:35:32,  1.42it/s]
1|7452|Loss: 0.7458042502403259:  29%|██▉       | 7452/25880 [1:33:08<3:39:15,  1.40it/s]
1|7453|Loss: 0.8162750601768494:  29%|██▉       | 7452/25880 [1:33:09<3:39:15,  1.40it/s]
1|7453|Loss: 0.8162750601768494:  29%|██▉       | 7453/25880 [1:33:09<3:46:39,  1.35it/s]
1|7454|Loss: 0.9144310355186462:  29%|██▉       | 7453/25880 [1:33:10<3:46:39,  1.35it/s]
1|7454|Loss: 0.9144310355186462:  29%|██▉       | 7454/25880 [1:33:10<3:51:06,  1.33it/s]
1|7455|Loss: 0.8527861833572388:  29%|██▉       | 7454/25880 [1:33:10<3:51:06,  1.33it/s]
1|7455|Loss: 0.8527861833572388:  29%|██▉       | 7455/25880 [1:33:11<3:43:08,  1.38it/s]
1|7456|Loss: 0.7881081104278564:  29%|██▉       | 7455/25880 [1:33:11<3:43:08,  1.38it/s]
1|7456|Loss: 0.7881081104278564:  29%|██▉       | 7456/25880 [1:33:11<3:25:24,  1.49it/s]
1|7457|Loss: 0.942495584487915:  29%|██▉       | 7456/25880 [1:33:12<3:25:24,  1.49it/s] 
1|7457|Loss: 0.942495584487915:  29%|██▉       | 7457/25880 [1:33:12<3:34:39,  1.43it/s]
1|7458|Loss: 0.885949969291687:  29%|██▉       | 7457/25880 [1:33:12<3:34:39,  1.43it/s]
1|7458|Loss: 0.885949969291687:  29%|██▉       | 7458/25880 [1:33:13<3:38:43,  1.40it/s]
1|7459|Loss: 0.9590678215026855:  29%|██▉       | 7458/25880 [1:33:13<3:38:43,  1.40it/s]
1|7459|Loss: 0.9590678215026855:  29%|██▉       | 7459/25880 [1:33:13<3:39:46,  1.40it/s]
1|7460|Loss: 0.9687316417694092:  29%|██▉       | 7459/25880 [1:33:14<3:39:46,  1.40it/s]
1|7460|Loss: 0.9687316417694092:  29%|██▉       | 7460/25880 [1:33:14<3:45:47,  1.36it/s]
1|7461|Loss: 0.9008930921554565:  29%|██▉       | 7460/25880 [1:33:15<3:45:47,  1.36it/s]
1|7461|Loss: 0.9008930921554565:  29%|██▉       | 7461/25880 [1:33:15<3:46:54,  1.35it/s]
1|7462|Loss: 0.8319957852363586:  29%|██▉       | 7461/25880 [1:33:15<3:46:54,  1.35it/s]
1|7462|Loss: 0.8319957852363586:  29%|██▉       | 7462/25880 [1:33:16<3:43:59,  1.37it/s]
1|7463|Loss: 0.832550585269928:  29%|██▉       | 7462/25880 [1:33:16<3:43:59,  1.37it/s] 
1|7463|Loss: 0.832550585269928:  29%|██▉       | 7463/25880 [1:33:16<3:42:52,  1.38it/s]
1|7464|Loss: 0.9498814344406128:  29%|��█▉       | 7463/25880 [1:33:17<3:42:52,  1.38it/s]
1|7464|Loss: 0.9498814344406128:  29%|██▉       | 7464/25880 [1:33:17<4:00:28,  1.28it/s]
1|7465|Loss: 1.050701379776001:  29%|██▉       | 7464/25880 [1:33:18<4:00:28,  1.28it/s] 
1|7465|Loss: 1.050701379776001:  29%|██▉       | 7465/25880 [1:33:18<4:19:31,  1.18it/s]
1|7466|Loss: 1.0303691625595093:  29%|██▉       | 7465/25880 [1:33:19<4:19:31,  1.18it/s]
1|7466|Loss: 1.0303691625595093:  29%|██▉       | 7466/25880 [1:33:19<4:20:10,  1.18it/s]
1|7467|Loss: 0.6830875277519226:  29%|██▉       | 7466/25880 [1:33:20<4:20:10,  1.18it/s]
1|7467|Loss: 0.6830875277519226:  29%|██▉       | 7467/25880 [1:33:20<4:27:06,  1.15it/s]
1|7468|Loss: 0.8522475361824036:  29%|██▉       | 7467/25880 [1:33:21<4:27:06,  1.15it/s]
1|7468|Loss: 0.8522475361824036:  29%|██▉       | 7468/25880 [1:33:21<4:11:21,  1.22it/s]
1|7469|Loss: 0.7544441819190979:  29%|██▉       | 7468/25880 [1:33:21<4:11:21,  1.22it/s]
1|7469|Loss: 0.7544441819190979:  29%|██▉       | 7469/25880 [1:33:22<3:59:02,  1.28it/s]
1|7470|Loss: 0.7226933836936951:  29%|██▉       | 7469/25880 [1:33:22<3:59:02,  1.28it/s]
1|7470|Loss: 0.7226933836936951:  29%|██▉       | 7470/25880 [1:33:22<3:57:54,  1.29it/s]
1|7471|Loss: 0.7859282493591309:  29%|██▉       | 7470/25880 [1:33:23<3:57:54,  1.29it/s]
1|7471|Loss: 0.7859282493591309:  29%|██▉       | 7471/25880 [1:33:23<3:52:52,  1.32it/s]
1|7472|Loss: 0.7658615708351135:  29%|██▉       | 7471/25880 [1:33:23<3:52:52,  1.32it/s]
1|7472|Loss: 0.7658615708351135:  29%|██▉       | 7472/25880 [1:33:24<3:57:35,  1.29it/s]
1|7473|Loss: 0.7973378896713257:  29%|██▉       | 7472/25880 [1:33:24<3:57:35,  1.29it/s]
1|7473|Loss: 0.7973378896713257:  29%|██▉       | 7473/25880 [1:33:25<3:54:33,  1.31it/s]
1|7474|Loss: 0.9547905325889587:  29%|██▉       | 7473/25880 [1:33:25<3:54:33,  1.31it/s]
1|7474|Loss: 0.9547905325889587:  29%|██▉       | 7474/25880 [1:33:25<3:49:15,  1.34it/s]
1|7475|Loss: 0.70802903175354:  29%|██▉       | 7474/25880 [1:33:26<3:49:15,  1.34it/s]  
1|7475|Loss: 0.70802903175354:  29%|██▉       | 7475/25880 [1:33:26<3:44:17,  1.37it/s]
1|7476|Loss: 1.0116257667541504:  29%|██▉       | 7475/25880 [1:33:26<3:44:17,  1.37it/s]
1|7476|Loss: 1.0116257667541504:  29%|██▉       | 7476/25880 [1:33:27<3:29:51,  1.46it/s]
1|7477|Loss: 0.8386369347572327:  29%|██▉       | 7476/25880 [1:33:27<3:29:51,  1.46it/s]
1|7477|Loss: 0.8386369347572327:  29%|██▉       | 7477/25880 [1:33:27<3:21:59,  1.52it/s]
1|7478|Loss: 0.8830299377441406:  29%|██▉       | 7477/25880 [1:33:27<3:21:59,  1.52it/s]
1|7478|Loss: 0.8830299377441406:  29%|██▉       | 7478/25880 [1:33:28<3:20:02,  1.53it/s]
1|7479|Loss: 0.6142616868019104:  29%|██▉       | 7478/25880 [1:33:28<3:20:02,  1.53it/s]
1|7479|Loss: 0.6142616868019104:  29%|██▉       | 7479/25880 [1:33:28<3:25:39,  1.49it/s]
1|7480|Loss: 0.9194926619529724:  29%|██▉       | 7479/25880 [1:33:29<3:25:39,  1.49it/s]
1|7480|Loss: 0.9194926619529724:  29%|██▉       | 7480/25880 [1:33:29<3:28:32,  1.47it/s]
1|7481|Loss: 0.8535640835762024:  29%|██▉       | 7480/25880 [1:33:30<3:28:32,  1.47it/s]
1|7481|Loss: 0.8535640835762024:  29%|██▉       | 7481/25880 [1:33:30<3:25:41,  1.49it/s]
1|7482|Loss: 0.8980460166931152:  29%|██▉       | 7481/25880 [1:33:30<3:25:41,  1.49it/s]
1|7482|Loss: 0.8980460166931152:  29%|██▉       | 7482/25880 [1:33:30<3:09:13,  1.62it/s]
1|7483|Loss: 0.7994961142539978:  29%|██▉       | 7482/25880 [1:33:31<3:09:13,  1.62it/s]
1|7483|Loss: 0.7994961142539978:  29%|██▉       | 7483/25880 [1:33:31<3:22:14,  1.52it/s]
1|7484|Loss: 0.8461658358573914:  29%|██▉       | 7483/25880 [1:33:31<3:22:14,  1.52it/s]
1|7484|Loss: 0.8461658358573914:  29%|██▉       | 7484/25880 [1:33:32<3:10:56,  1.61it/s]
1|7485|Loss: 0.744595468044281:  29%|██▉       | 7484/25880 [1:33:32<3:10:56,  1.61it/s] 
1|7485|Loss: 0.744595468044281:  29%|██▉       | 7485/25880 [1:33:32<3:21:43,  1.52it/s]
1|7486|Loss: 0.8147589564323425:  29%|██▉       | 7485/25880 [1:33:33<3:21:43,  1.52it/s]
1|7486|Loss: 0.8147589564323425:  29%|██▉       | 7486/25880 [1:33:33<3:36:39,  1.41it/s]
1|7487|Loss: 0.8208853602409363:  29%|██▉       | 7486/25880 [1:33:34<3:36:39,  1.41it/s]
1|7487|Loss: 0.8208853602409363:  29%|██▉       | 7487/25880 [1:33:34<3:32:59,  1.44it/s]
1|7488|Loss: 0.7971997261047363:  29%|██▉       | 7487/25880 [1:33:34<3:32:59,  1.44it/s]
1|7488|Loss: 0.7971997261047363:  29%|██▉       | 7488/25880 [1:33:35<3:32:12,  1.44it/s]
1|7489|Loss: 0.845277726650238:  29%|██▉       | 7488/25880 [1:33:35<3:32:12,  1.44it/s] 
1|7489|Loss: 0.845277726650238:  29%|██▉       | 7489/25880 [1:33:35<3:19:54,  1.53it/s]
1|7490|Loss: 0.9541276097297668:  29%|██▉       | 7489/25880 [1:33:35<3:19:54,  1.53it/s]
1|7490|Loss: 0.9541276097297668:  29%|██▉       | 7490/25880 [1:33:36<3:28:14,  1.47it/s]
1|7491|Loss: 0.8142070770263672:  29%|██▉       | 7490/25880 [1:33:36<3:28:14,  1.47it/s]
1|7491|Loss: 0.8142070770263672:  29%|██▉       | 7491/25880 [1:33:37<3:27:23,  1.48it/s]
1|7492|Loss: 0.8932388424873352:  29%|██▉       | 7491/25880 [1:33:37<3:27:23,  1.48it/s]
1|7492|Loss: 0.8932388424873352:  29%|██▉       | 7492/25880 [1:33:37<3:34:47,  1.43it/s]
1|7493|Loss: 0.9432315230369568:  29%|██▉       | 7492/25880 [1:33:38<3:34:47,  1.43it/s]
1|7493|Loss: 0.9432315230369568:  29%|██▉       | 7493/25880 [1:33:38<3:40:01,  1.39it/s]
1|7494|Loss: 0.8885276913642883:  29%|██▉       | 7493/25880 [1:33:38<3:40:01,  1.39it/s]
1|7494|Loss: 0.8885276913642883:  29%|██▉       | 7494/25880 [1:33:39<3:35:52,  1.42it/s]
1|7495|Loss: 0.7747584581375122:  29%|██▉       | 7494/25880 [1:33:39<3:35:52,  1.42it/s]
1|7495|Loss: 0.7747584581375122:  29%|██▉       | 7495/25880 [1:33:39<3:27:40,  1.48it/s]
1|7496|Loss: 0.9379720091819763:  29%|██▉       | 7495/25880 [1:33:40<3:27:40,  1.48it/s]
1|7496|Loss: 0.9379720091819763:  29%|██▉       | 7496/25880 [1:33:40<3:39:05,  1.40it/s]
1|7497|Loss: 0.846686065196991:  29%|██▉       | 7496/25880 [1:33:40<3:39:05,  1.40it/s] 
1|7497|Loss: 0.846686065196991:  29%|██▉       | 7497/25880 [1:33:41<3:26:21,  1.48it/s]
1|7498|Loss: 0.8309295773506165:  29%|██▉       | 7497/25880 [1:33:41<3:26:21,  1.48it/s]
1|7498|Loss: 0.8309295773506165:  29%|██▉       | 7498/25880 [1:33:41<3:28:36,  1.47it/s]
1|7499|Loss: 0.7578749060630798:  29%|██▉       | 7498/25880 [1:33:42<3:28:36,  1.47it/s]
1|7499|Loss: 0.7578749060630798:  29%|██▉       | 7499/25880 [1:33:42<3:34:42,  1.43it/s]
1|7500|Loss: 0.8066983819007874:  29%|██▉       | 7499/25880 [1:33:43<3:34:42,  1.43it/s]
1|7500|Loss: 0.8066983819007874:  29%|██▉       | 7500/25880 [1:33:43<3:44:39,  1.36it/s]
1|7501|Loss: 0.7513698935508728:  29%|██▉       | 7500/25880 [1:33:43<3:44:39,  1.36it/s]
1|7501|Loss: 0.7513698935508728:  29%|██▉       | 7501/25880 [1:33:44<3:53:43,  1.31it/s]
1|7502|Loss: 0.9683681130409241:  29%|██▉       | 7501/25880 [1:33:44<3:53:43,  1.31it/s]
1|7502|Loss: 0.9683681130409241:  29%|██▉       | 7502/25880 [1:33:45<4:05:38,  1.25it/s]
1|7503|Loss: 0.9767256379127502:  29%|██▉       | 7502/25880 [1:33:45<4:05:38,  1.25it/s]
1|7503|Loss: 0.9767256379127502:  29%|██▉       | 7503/25880 [1:33:45<4:03:04,  1.26it/s]
1|7504|Loss: 0.9105436205863953:  29%|██▉       | 7503/25880 [1:33:46<4:03:04,  1.26it/s]
1|7504|Loss: 0.9105436205863953:  29%|██▉       | 7504/25880 [1:33:46<3:49:18,  1.34it/s]
1|7505|Loss: 0.8753227591514587:  29%|██▉       | 7504/25880 [1:33:47<3:49:18,  1.34it/s]
1|7505|Loss: 0.8753227591514587:  29%|██▉       | 7505/25880 [1:33:47<3:58:39,  1.28it/s]
1|7506|Loss: 0.9857330322265625:  29%|██▉       | 7505/25880 [1:33:47<3:58:39,  1.28it/s]
1|7506|Loss: 0.9857330322265625:  29%|██▉       | 7506/25880 [1:33:48<4:05:05,  1.25it/s]
1|7507|Loss: 0.8370359539985657:  29%|██▉       | 7506/25880 [1:33:48<4:05:05,  1.25it/s]
1|7507|Loss: 0.8370359539985657:  29%|██▉       | 7507/25880 [1:33:49<4:00:47,  1.27it/s]
1|7508|Loss: 0.9351251125335693:  29%|██▉       | 7507/25880 [1:33:49<4:00:47,  1.27it/s]
1|7508|Loss: 0.9351251125335693:  29%|██▉       | 7508/25880 [1:33:49<3:57:10,  1.29it/s]
1|7509|Loss: 0.8617483973503113:  29%|██▉       | 7508/25880 [1:33:50<3:57:10,  1.29it/s]
1|7509|Loss: 0.8617483973503113:  29%|██▉       | 7509/25880 [1:33:50<4:11:12,  1.22it/s]
1|7510|Loss: 0.979802131652832:  29%|██▉       | 7509/25880 [1:33:51<4:11:12,  1.22it/s] 
1|7510|Loss: 0.979802131652832:  29%|██▉       | 7510/25880 [1:33:51<3:58:52,  1.28it/s]
1|7511|Loss: 0.7630115151405334:  29%|██▉       | 7510/25880 [1:33:51<3:58:52,  1.28it/s]
1|7511|Loss: 0.7630115151405334:  29%|██▉       | 7511/25880 [1:33:52<4:04:52,  1.25it/s]
1|7512|Loss: 0.8253840804100037:  29%|██▉       | 7511/25880 [1:33:52<4:04:52,  1.25it/s]
1|7512|Loss: 0.8253840804100037:  29%|██▉       | 7512/25880 [1:33:53<4:08:22,  1.23it/s]
1|7513|Loss: 0.8756073713302612:  29%|██▉       | 7512/25880 [1:33:53<4:08:22,  1.23it/s]
1|7513|Loss: 0.8756073713302612:  29%|██▉       | 7513/25880 [1:33:53<3:53:31,  1.31it/s]
1|7514|Loss: 0.849794328212738:  29%|██▉       | 7513/25880 [1:33:54<3:53:31,  1.31it/s] 
1|7514|Loss: 0.849794328212738:  29%|██▉       | 7514/25880 [1:33:54<3:46:14,  1.35it/s]
1|7515|Loss: 0.7091777324676514:  29%|██▉       | 7514/25880 [1:33:54<3:46:14,  1.35it/s]
1|7515|Loss: 0.7091777324676514:  29%|██▉       | 7515/25880 [1:33:55<3:35:59,  1.42it/s]
1|7516|Loss: 0.7723550200462341:  29%|██▉       | 7515/25880 [1:33:55<3:35:59,  1.42it/s]
1|7516|Loss: 0.7723550200462341:  29%|██▉       | 7516/25880 [1:33:55<3:49:46,  1.33it/s]
1|7517|Loss: 0.906367838382721:  29%|██▉       | 7516/25880 [1:33:56<3:49:46,  1.33it/s] 
1|7517|Loss: 0.906367838382721:  29%|██▉       | 7517/25880 [1:33:56<3:49:28,  1.33it/s]
1|7518|Loss: 0.8160898685455322:  29%|██▉       | 7517/25880 [1:33:57<3:49:28,  1.33it/s]
1|7518|Loss: 0.8160898685455322:  29%|██▉       | 7518/25880 [1:33:57<3:53:49,  1.31it/s]
1|7519|Loss: 0.8143943548202515:  29%|██▉       | 7518/25880 [1:33:57<3:53:49,  1.31it/s]
1|7519|Loss: 0.8143943548202515:  29%|██▉       | 7519/25880 [1:33:58<3:49:39,  1.33it/s]
1|7520|Loss: 0.7916920781135559:  29%|██▉       | 7519/25880 [1:33:58<3:49:39,  1.33it/s]
1|7520|Loss: 0.7916920781135559:  29%|██▉       | 7520/25880 [1:33:59<4:05:23,  1.25it/s]
1|7521|Loss: 0.8626133799552917:  29%|██▉       | 7520/25880 [1:33:59<4:05:23,  1.25it/s]
1|7521|Loss: 0.8626133799552917:  29%|██▉       | 7521/25880 [1:33:59<4:08:22,  1.23it/s]
1|7522|Loss: 0.7986563444137573:  29%|██▉       | 7521/25880 [1:34:00<4:08:22,  1.23it/s]
1|7522|Loss: 0.7986563444137573:  29%|██▉       | 7522/25880 [1:34:00<4:12:42,  1.21it/s]
1|7523|Loss: 0.9026941061019897:  29%|██▉       | 7522/25880 [1:34:01<4:12:42,  1.21it/s]
1|7523|Loss: 0.9026941061019897:  29%|██▉       | 7523/25880 [1:34:01<4:08:32,  1.23it/s]
1|7524|Loss: 0.7768988013267517:  29%|██▉       | 7523/25880 [1:34:01<4:08:32,  1.23it/s]
1|7524|Loss: 0.7768988013267517:  29%|██▉       | 7524/25880 [1:34:02<4:08:34,  1.23it/s]
1|7525|Loss: 0.6538658738136292:  29%|██▉       | 7524/25880 [1:34:02<4:08:34,  1.23it/s]
1|7525|Loss: 0.6538658738136292:  29%|██▉       | 7525/25880 [1:34:02<3:46:19,  1.35it/s]
1|7526|Loss: 0.8702370524406433:  29%|██▉       | 7525/25880 [1:34:03<3:46:19,  1.35it/s]
1|7526|Loss: 0.8702370524406433:  29%|██▉       | 7526/25880 [1:34:03<3:32:31,  1.44it/s]
1|7527|Loss: 0.8394536375999451:  29%|██▉       | 7526/25880 [1:34:03<3:32:31,  1.44it/s]
1|7527|Loss: 0.8394536375999451:  29%|██▉       | 7527/25880 [1:34:04<3:31:11,  1.45it/s]
1|7528|Loss: 0.7475608587265015:  29%|██▉       | 7527/25880 [1:34:04<3:31:11,  1.45it/s]
1|7528|Loss: 0.7475608587265015:  29%|██▉       | 7528/25880 [1:34:05<3:44:25,  1.36it/s]
1|7529|Loss: 0.7789880037307739:  29%|██▉       | 7528/25880 [1:34:05<3:44:25,  1.36it/s]
1|7529|Loss: 0.7789880037307739:  29%|██▉       | 7529/25880 [1:34:05<3:44:55,  1.36it/s]
1|7530|Loss: 0.7655095458030701:  29%|██▉       | 7529/25880 [1:34:06<3:44:55,  1.36it/s]
1|7530|Loss: 0.7655095458030701:  29%|██▉       | 7530/25880 [1:34:06<3:41:07,  1.38it/s]
1|7531|Loss: 0.9106440544128418:  29%|██▉       | 7530/25880 [1:34:06<3:41:07,  1.38it/s]
1|7531|Loss: 0.9106440544128418:  29%|██▉       | 7531/25880 [1:34:07<3:38:50,  1.40it/s]
1|7532|Loss: 0.8307021856307983:  29%|██▉       | 7531/25880 [1:34:07<3:38:50,  1.40it/s]
1|7532|Loss: 0.8307021856307983:  29%|██▉       | 7532/25880 [1:34:07<3:31:12,  1.45it/s]
1|7533|Loss: 0.927903413772583:  29%|██▉       | 7532/25880 [1:34:08<3:31:12,  1.45it/s] 
1|7533|Loss: 0.927903413772583:  29%|██▉       | 7533/25880 [1:34:08<3:30:41,  1.45it/s]
1|7534|Loss: 0.7909401655197144:  29%|██▉       | 7533/25880 [1:34:08<3:30:41,  1.45it/s]
1|7534|Loss: 0.7909401655197144:  29%|██▉       | 7534/25880 [1:34:09<3:34:09,  1.43it/s]
1|7535|Loss: 0.7830596566200256:  29%|██▉       | 7534/25880 [1:34:09<3:34:09,  1.43it/s]
1|7535|Loss: 0.7830596566200256:  29%|██▉       | 7535/25880 [1:34:10<3:45:14,  1.36it/s]
1|7536|Loss: 0.9415015578269958:  29%|██▉       | 7535/25880 [1:34:10<3:45:14,  1.36it/s]
1|7536|Loss: 0.9415015578269958:  29%|██▉       | 7536/25880 [1:34:10<3:35:04,  1.42it/s]
1|7537|Loss: 0.7568373680114746:  29%|██▉       | 7536/25880 [1:34:11<3:35:04,  1.42it/s]
1|7537|Loss: 0.7568373680114746:  29%|██▉       | 7537/25880 [1:34:11<3:45:26,  1.36it/s]
1|7538|Loss: 0.9671857357025146:  29%|██▉       | 7537/25880 [1:34:11<3:45:26,  1.36it/s]
1|7538|Loss: 0.9671857357025146:  29%|██▉       | 7538/25880 [1:34:12<3:53:03,  1.31it/s]
1|7539|Loss: 0.7411202788352966:  29%|██▉       | 7538/25880 [1:34:12<3:53:03,  1.31it/s]
1|7539|Loss: 0.7411202788352966:  29%|██▉       | 7539/25880 [1:34:13<3:52:02,  1.32it/s]
1|7540|Loss: 0.7527709007263184:  29%|██▉       | 7539/25880 [1:34:13<3:52:02,  1.32it/s]
1|7540|Loss: 0.7527709007263184:  29%|██▉       | 7540/25880 [1:34:13<3:58:32,  1.28it/s]
1|7541|Loss: 0.7666445374488831:  29%|██▉       | 7540/25880 [1:34:14<3:58:32,  1.28it/s]
1|7541|Loss: 0.7666445374488831:  29%|██▉       | 7541/25880 [1:34:14<3:46:28,  1.35it/s]
1|7542|Loss: 0.800627589225769:  29%|██▉       | 7541/25880 [1:34:14<3:46:28,  1.35it/s] 
1|7542|Loss: 0.800627589225769:  29%|██▉       | 7542/25880 [1:34:15<3:24:10,  1.50it/s]
1|7543|Loss: 0.9482914209365845:  29%|██▉       | 7542/25880 [1:34:15<3:24:10,  1.50it/s]
1|7543|Loss: 0.9482914209365845:  29%|██▉       | 7543/25880 [1:34:15<3:31:53,  1.44it/s]
1|7544|Loss: 0.8476362228393555:  29%|██▉       | 7543/25880 [1:34:16<3:31:53,  1.44it/s]
1|7544|Loss: 0.8476362228393555:  29%|██▉       | 7544/25880 [1:34:16<3:42:04,  1.38it/s]
1|7545|Loss: 0.8761174082756042:  29%|██▉       | 7544/25880 [1:34:17<3:42:04,  1.38it/s]
1|7545|Loss: 0.8761174082756042:  29%|██▉       | 7545/25880 [1:34:17<3:50:20,  1.33it/s]
1|7546|Loss: 0.8283901810646057:  29%|██▉       | 7545/25880 [1:34:17<3:50:20,  1.33it/s]
1|7546|Loss: 0.8283901810646057:  29%|██▉       | 7546/25880 [1:34:18<4:02:52,  1.26it/s]
1|7547|Loss: 1.0336610078811646:  29%|██▉       | 7546/25880 [1:34:18<4:02:52,  1.26it/s]
1|7547|Loss: 1.0336610078811646:  29%|██▉       | 7547/25880 [1:34:19<3:58:00,  1.28it/s]
1|7548|Loss: 0.7777262330055237:  29%|██▉       | 7547/25880 [1:34:19<3:58:00,  1.28it/s]
1|7548|Loss: 0.7777262330055237:  29%|██▉       | 7548/25880 [1:34:19<3:27:38,  1.47it/s]
1|7549|Loss: 0.8171161413192749:  29%|██▉       | 7548/25880 [1:34:19<3:27:38,  1.47it/s]
1|7549|Loss: 0.8171161413192749:  29%|██▉       | 7549/25880 [1:34:20<3:30:26,  1.45it/s]
1|7550|Loss: 0.836756706237793:  29%|██▉       | 7549/25880 [1:34:20<3:30:26,  1.45it/s] 
1|7550|Loss: 0.836756706237793:  29%|██▉       | 7550/25880 [1:34:20<3:33:27,  1.43it/s]
1|7551|Loss: 0.5975057482719421:  29%|██▉       | 7550/25880 [1:34:21<3:33:27,  1.43it/s]
1|7551|Loss: 0.5975057482719421:  29%|██▉       | 7551/25880 [1:34:21<3:52:13,  1.32it/s]
1|7552|Loss: 0.8738399147987366:  29%|██▉       | 7551/25880 [1:34:22<3:52:13,  1.32it/s]
1|7552|Loss: 0.8738399147987366:  29%|██▉       | 7552/25880 [1:34:22<3:45:06,  1.36it/s]
1|7553|Loss: 0.9495782852172852:  29%|██▉       | 7552/25880 [1:34:22<3:45:06,  1.36it/s]
1|7553|Loss: 0.9495782852172852:  29%|██▉       | 7553/25880 [1:34:23<3:36:01,  1.41it/s]
1|7554|Loss: 0.8305715918540955:  29%|██▉       | 7553/25880 [1:34:23<3:36:01,  1.41it/s]
1|7554|Loss: 0.8305715918540955:  29%|██▉       | 7554/25880 [1:34:23<3:36:06,  1.41it/s]
1|7555|Loss: 0.8125594854354858:  29%|██▉       | 7554/25880 [1:34:24<3:36:06,  1.41it/s]
1|7555|Loss: 0.8125594854354858:  29%|██▉       | 7555/25880 [1:34:24<3:35:04,  1.42it/s]
1|7556|Loss: 0.6993860006332397:  29%|██▉       | 7555/25880 [1:34:24<3:35:04,  1.42it/s]
1|7556|Loss: 0.6993860006332397:  29%|██▉       | 7556/25880 [1:34:25<3:41:16,  1.38it/s]
1|7557|Loss: 0.9250763058662415:  29%|██▉       | 7556/25880 [1:34:25<3:41:16,  1.38it/s]
1|7557|Loss: 0.9250763058662415:  29%|██▉       | 7557/25880 [1:34:26<3:37:09,  1.41it/s]
1|7558|Loss: 0.8690337538719177:  29%|██▉       | 7557/25880 [1:34:26<3:37:09,  1.41it/s]
1|7558|Loss: 0.8690337538719177:  29%|██▉       | 7558/25880 [1:34:26<3:37:52,  1.40it/s]
1|7559|Loss: 0.7497190237045288:  29%|██▉       | 7558/25880 [1:34:27<3:37:52,  1.40it/s]
1|7559|Loss: 0.7497190237045288:  29%|██▉       | 7559/25880 [1:34:27<3:30:42,  1.45it/s]
1|7560|Loss: 1.0798088312149048:  29%|██▉       | 7559/25880 [1:34:27<3:30:42,  1.45it/s]
1|7560|Loss: 1.0798088312149048:  29%|██▉       | 7560/25880 [1:34:28<3:32:28,  1.44it/s]
1|7561|Loss: 0.9393527507781982:  29%|██▉       | 7560/25880 [1:34:28<3:32:28,  1.44it/s]
1|7561|Loss: 0.9393527507781982:  29%|██▉       | 7561/25880 [1:34:28<3:27:43,  1.47it/s]
1|7562|Loss: 0.8234784007072449:  29%|██▉       | 7561/25880 [1:34:29<3:27:43,  1.47it/s]
1|7562|Loss: 0.8234784007072449:  29%|██▉       | 7562/25880 [1:34:29<3:38:54,  1.39it/s]
1|7563|Loss: 0.8365185856819153:  29%|██▉       | 7562/25880 [1:34:29<3:38:54,  1.39it/s]
1|7563|Loss: 0.8365185856819153:  29%|██▉       | 7563/25880 [1:34:30<3:50:09,  1.33it/s]
1|7564|Loss: 0.8475509285926819:  29%|██▉       | 7563/25880 [1:34:30<3:50:09,  1.33it/s]
1|7564|Loss: 0.8475509285926819:  29%|██▉       | 7564/25880 [1:34:31<3:57:30,  1.29it/s]
1|7565|Loss: 0.6974509954452515:  29%|██▉       | 7564/25880 [1:34:31<3:57:30,  1.29it/s]
1|7565|Loss: 0.6974509954452515:  29%|██▉       | 7565/25880 [1:34:31<3:55:38,  1.30it/s]
1|7566|Loss: 0.8733577132225037:  29%|██▉       | 7565/25880 [1:34:32<3:55:38,  1.30it/s]
1|7566|Loss: 0.8733577132225037:  29%|██▉       | 7566/25880 [1:34:32<3:44:20,  1.36it/s]
1|7567|Loss: 0.8861464262008667:  29%|██▉       | 7566/25880 [1:34:32<3:44:20,  1.36it/s]
1|7567|Loss: 0.8861464262008667:  29%|██▉       | 7567/25880 [1:34:33<3:31:55,  1.44it/s]
1|7568|Loss: 0.886669397354126:  29%|██▉       | 7567/25880 [1:34:33<3:31:55,  1.44it/s] 
1|7568|Loss: 0.886669397354126:  29%|██▉       | 7568/25880 [1:34:33<3:33:49,  1.43it/s]
1|7569|Loss: 0.7680944204330444:  29%|██▉       | 7568/25880 [1:34:34<3:33:49,  1.43it/s]
1|7569|Loss: 0.7680944204330444:  29%|██▉       | 7569/25880 [1:34:34<3:31:03,  1.45it/s]
1|7570|Loss: 0.7916686534881592:  29%|██▉       | 7569/25880 [1:34:34<3:31:03,  1.45it/s]
1|7570|Loss: 0.7916686534881592:  29%|██▉       | 7570/25880 [1:34:35<3:34:31,  1.42it/s]
1|7571|Loss: 0.8221594095230103:  29%|██▉       | 7570/25880 [1:34:35<3:34:31,  1.42it/s]
1|7571|Loss: 0.8221594095230103:  29%|██▉       | 7571/25880 [1:34:35<3:31:21,  1.44it/s]
1|7572|Loss: 0.9115699529647827:  29%|██▉       | 7571/25880 [1:34:36<3:31:21,  1.44it/s]
1|7572|Loss: 0.9115699529647827:  29%|██▉       | 7572/25880 [1:34:36<3:39:50,  1.39it/s]
1|7573|Loss: 0.9002732038497925:  29%|██▉       | 7572/25880 [1:34:37<3:39:50,  1.39it/s]
1|7573|Loss: 0.9002732038497925:  29%|██▉       | 7573/25880 [1:34:37<3:39:32,  1.39it/s]
1|7574|Loss: 0.868965744972229:  29%|██▉       | 7573/25880 [1:34:37<3:39:32,  1.39it/s] 
1|7574|Loss: 0.868965744972229:  29%|██▉       | 7574/25880 [1:34:38<3:44:53,  1.36it/s]
1|7575|Loss: 0.7442114353179932:  29%|██▉       | 7574/25880 [1:34:38<3:44:53,  1.36it/s]
1|7575|Loss: 0.7442114353179932:  29%|██▉       | 7575/25880 [1:34:39<3:55:30,  1.30it/s]
1|7576|Loss: 0.8743940591812134:  29%|██▉       | 7575/25880 [1:34:39<3:55:30,  1.30it/s]
1|7576|Loss: 0.8743940591812134:  29%|██▉       | 7576/25880 [1:34:39<4:05:53,  1.24it/s]
1|7577|Loss: 0.7798634767532349:  29%|██▉       | 7576/25880 [1:34:40<4:05:53,  1.24it/s]
1|7577|Loss: 0.7798634767532349:  29%|██▉       | 7577/25880 [1:34:40<3:49:29,  1.33it/s]
1|7578|Loss: 0.8028527498245239:  29%|██▉       | 7577/25880 [1:34:40<3:49:29,  1.33it/s]
1|7578|Loss: 0.8028527498245239:  29%|██▉       | 7578/25880 [1:34:41<3:43:30,  1.36it/s]
1|7579|Loss: 0.8513644933700562:  29%|██▉       | 7578/25880 [1:34:41<3:43:30,  1.36it/s]
1|7579|Loss: 0.8513644933700562:  29%|██▉       | 7579/25880 [1:34:41<3:34:14,  1.42it/s]
1|7580|Loss: 0.8475916981697083:  29%|██▉       | 7579/25880 [1:34:42<3:34:14,  1.42it/s]
1|7580|Loss: 0.8475916981697083:  29%|██▉       | 7580/25880 [1:34:42<3:32:17,  1.44it/s]
1|7581|Loss: 0.8699800372123718:  29%|██▉       | 7580/25880 [1:34:43<3:32:17,  1.44it/s]
1|7581|Loss: 0.8699800372123718:  29%|██▉       | 7581/25880 [1:34:43<3:32:35,  1.43it/s]
1|7582|Loss: 0.8341019153594971:  29%|██▉       | 7581/25880 [1:34:43<3:32:35,  1.43it/s]
1|7582|Loss: 0.8341019153594971:  29%|██▉       | 7582/25880 [1:34:43<3:23:17,  1.50it/s]
1|7583|Loss: 0.8071438074111938:  29%|██▉       | 7582/25880 [1:34:44<3:23:17,  1.50it/s]
1|7583|Loss: 0.8071438074111938:  29%|██▉       | 7583/25880 [1:34:44<3:26:17,  1.48it/s]
1|7584|Loss: 0.7544177770614624:  29%|██▉       | 7583/25880 [1:34:44<3:26:17,  1.48it/s]
1|7584|Loss: 0.7544177770614624:  29%|██▉       | 7584/25880 [1:34:45<3:14:45,  1.57it/s]
1|7585|Loss: 0.8048427104949951:  29%|██▉       | 7584/25880 [1:34:45<3:14:45,  1.57it/s]
1|7585|Loss: 0.8048427104949951:  29%|██▉       | 7585/25880 [1:34:46<3:32:32,  1.43it/s]
1|7586|Loss: 0.8641881346702576:  29%|██▉       | 7585/25880 [1:34:46<3:32:32,  1.43it/s]
1|7586|Loss: 0.8641881346702576:  29%|██▉       | 7586/25880 [1:34:46<3:47:56,  1.34it/s]
1|7587|Loss: 0.7683145999908447:  29%|██▉       | 7586/25880 [1:34:47<3:47:56,  1.34it/s]
1|7587|Loss: 0.7683145999908447:  29%|██▉       | 7587/25880 [1:34:47<3:56:51,  1.29it/s]
1|7588|Loss: 0.8150442242622375:  29%|██▉       | 7587/25880 [1:34:48<3:56:51,  1.29it/s]
1|7588|Loss: 0.8150442242622375:  29%|██▉       | 7588/25880 [1:34:48<3:45:53,  1.35it/s]
1|7589|Loss: 0.8561080098152161:  29%|██▉       | 7588/25880 [1:34:48<3:45:53,  1.35it/s]
1|7589|Loss: 0.8561080098152161:  29%|██▉       | 7589/25880 [1:34:49<3:43:54,  1.36it/s]
1|7590|Loss: 0.9385631084442139:  29%|██▉       | 7589/25880 [1:34:49<3:43:54,  1.36it/s]
1|7590|Loss: 0.9385631084442139:  29%|██▉       | 7590/25880 [1:34:49<3:36:08,  1.41it/s]
1|7591|Loss: 1.0129185914993286:  29%|██▉       | 7590/25880 [1:34:50<3:36:08,  1.41it/s]
1|7591|Loss: 1.0129185914993286:  29%|██▉       | 7591/25880 [1:34:50<3:29:20,  1.46it/s]
1|7592|Loss: 0.8151806592941284:  29%|██▉       | 7591/25880 [1:34:50<3:29:20,  1.46it/s]
1|7592|Loss: 0.8151806592941284:  29%|██▉       | 7592/25880 [1:34:51<3:31:49,  1.44it/s]
1|7593|Loss: 0.9293841123580933:  29%|██▉       | 7592/25880 [1:34:51<3:31:49,  1.44it/s]
1|7593|Loss: 0.9293841123580933:  29%|██▉       | 7593/25880 [1:34:51<3:41:38,  1.38it/s]
1|7594|Loss: 0.9100534915924072:  29%|██▉       | 7593/25880 [1:34:52<3:41:38,  1.38it/s]
1|7594|Loss: 0.9100534915924072:  29%|██▉       | 7594/25880 [1:34:52<3:52:16,  1.31it/s]
1|7595|Loss: 0.7968044877052307:  29%|██▉       | 7594/25880 [1:34:53<3:52:16,  1.31it/s]
1|7595|Loss: 0.7968044877052307:  29%|██▉       | 7595/25880 [1:34:53<3:56:34,  1.29it/s]
1|7596|Loss: 0.9658722281455994:  29%|██▉       | 7595/25880 [1:34:53<3:56:34,  1.29it/s]
1|7596|Loss: 0.9658722281455994:  29%|██▉       | 7596/25880 [1:34:54<3:45:24,  1.35it/s]
1|7597|Loss: 0.841788113117218:  29%|██▉       | 7596/25880 [1:34:54<3:45:24,  1.35it/s] 
1|7597|Loss: 0.841788113117218:  29%|██▉       | 7597/25880 [1:34:54<3:42:12,  1.37it/s]
1|7598|Loss: 0.6895426511764526:  29%|██▉       | 7597/25880 [1:34:55<3:42:12,  1.37it/s]
1|7598|Loss: 0.6895426511764526:  29%|██▉       | 7598/25880 [1:34:55<3:35:14,  1.42it/s]
1|7599|Loss: 0.9621527791023254:  29%|██▉       | 7598/25880 [1:34:55<3:35:14,  1.42it/s]
1|7599|Loss: 0.9621527791023254:  29%|██▉       | 7599/25880 [1:34:56<3:29:03,  1.46it/s]
1|7600|Loss: 0.8652881383895874:  29%|██▉       | 7599/25880 [1:34:56<3:29:03,  1.46it/s]
1|7600|Loss: 0.8652881383895874:  29%|██▉       | 7600/25880 [1:34:57<3:40:22,  1.38it/s]
1|7601|Loss: 0.757037878036499:  29%|██▉       | 7600/25880 [1:34:57<3:40:22,  1.38it/s] 
1|7601|Loss: 0.757037878036499:  29%|██▉       | 7601/25880 [1:34:57<3:35:35,  1.41it/s]
1|7602|Loss: 0.6800609230995178:  29%|██▉       | 7601/25880 [1:34:58<3:35:35,  1.41it/s]
1|7602|Loss: 0.6800609230995178:  29%|██▉       | 7602/25880 [1:34:58<3:22:51,  1.50it/s]
1|7603|Loss: 0.9778751730918884:  29%|██▉       | 7602/25880 [1:34:58<3:22:51,  1.50it/s]
1|7603|Loss: 0.9778751730918884:  29%|██▉       | 7603/25880 [1:34:58<3:25:56,  1.48it/s]
1|7604|Loss: 0.8492169976234436:  29%|██▉       | 7603/25880 [1:34:59<3:25:56,  1.48it/s]
1|7604|Loss: 0.8492169976234436:  29%|██▉       | 7604/25880 [1:34:59<3:38:36,  1.39it/s]
1|7605|Loss: 0.8888882994651794:  29%|██▉       | 7604/25880 [1:35:00<3:38:36,  1.39it/s]
1|7605|Loss: 0.8888882994651794:  29%|██▉       | 7605/25880 [1:35:00<3:30:48,  1.44it/s]
1|7606|Loss: 0.8656527996063232:  29%|██▉       | 7605/25880 [1:35:00<3:30:48,  1.44it/s]
1|7606|Loss: 0.8656527996063232:  29%|██▉       | 7606/25880 [1:35:01<3:28:50,  1.46it/s]
1|7607|Loss: 0.8829421997070312:  29%|██▉       | 7606/25880 [1:35:01<3:28:50,  1.46it/s]
1|7607|Loss: 0.8829421997070312:  29%|██▉       | 7607/25880 [1:35:01<3:51:21,  1.32it/s]
1|7608|Loss: 0.8113413453102112:  29%|██▉       | 7607/25880 [1:35:02<3:51:21,  1.32it/s]
1|7608|Loss: 0.8113413453102112:  29%|██▉       | 7608/25880 [1:35:02<3:36:24,  1.41it/s]
1|7609|Loss: 0.6395949721336365:  29%|██▉       | 7608/25880 [1:35:02<3:36:24,  1.41it/s]
1|7609|Loss: 0.6395949721336365:  29%|██▉       | 7609/25880 [1:35:03<3:46:53,  1.34it/s]
1|7610|Loss: 0.7974547147750854:  29%|██▉       | 7609/25880 [1:35:03<3:46:53,  1.34it/s]
1|7610|Loss: 0.7974547147750854:  29%|██▉       | 7610/25880 [1:35:04<3:48:20,  1.33it/s]
1|7611|Loss: 0.9321213364601135:  29%|██▉       | 7610/25880 [1:35:04<3:48:20,  1.33it/s]
1|7611|Loss: 0.9321213364601135:  29%|██▉       | 7611/25880 [1:35:04<3:46:37,  1.34it/s]
1|7612|Loss: 0.816167414188385:  29%|██▉       | 7611/25880 [1:35:05<3:46:37,  1.34it/s] 
1|7612|Loss: 0.816167414188385:  29%|██▉       | 7612/25880 [1:35:05<3:43:51,  1.36it/s]
1|7613|Loss: 0.8022893667221069:  29%|██▉       | 7612/25880 [1:35:06<3:43:51,  1.36it/s]
1|7613|Loss: 0.8022893667221069:  29%|██▉       | 7613/25880 [1:35:06<3:49:48,  1.32it/s]
1|7614|Loss: 0.8060194253921509:  29%|██▉       | 7613/25880 [1:35:06<3:49:48,  1.32it/s]
1|7614|Loss: 0.8060194253921509:  29%|██▉       | 7614/25880 [1:35:07<3:49:24,  1.33it/s]
1|7615|Loss: 0.9356210231781006:  29%|██▉       | 7614/25880 [1:35:07<3:49:24,  1.33it/s]
1|7615|Loss: 0.9356210231781006:  29%|██▉       | 7615/25880 [1:35:07<3:35:51,  1.41it/s]
1|7616|Loss: 0.7640291452407837:  29%|██▉       | 7615/25880 [1:35:08<3:35:51,  1.41it/s]
1|7616|Loss: 0.7640291452407837:  29%|██▉       | 7616/25880 [1:35:08<3:27:51,  1.46it/s]
1|7617|Loss: 0.880246639251709:  29%|██▉       | 7616/25880 [1:35:08<3:27:51,  1.46it/s] 
1|7617|Loss: 0.880246639251709:  29%|██▉       | 7617/25880 [1:35:09<3:20:59,  1.51it/s]
1|7618|Loss: 0.9227880835533142:  29%|██▉       | 7617/25880 [1:35:09<3:20:59,  1.51it/s]
1|7618|Loss: 0.9227880835533142:  29%|██▉       | 7618/25880 [1:35:09<3:16:04,  1.55it/s]
1|7619|Loss: 0.9394364953041077:  29%|██▉       | 7618/25880 [1:35:09<3:16:04,  1.55it/s]
1|7619|Loss: 0.9394364953041077:  29%|██▉       | 7619/25880 [1:35:10<3:22:23,  1.50it/s]
1|7620|Loss: 0.6715783476829529:  29%|██▉       | 7619/25880 [1:35:10<3:22:23,  1.50it/s]
1|7620|Loss: 0.6715783476829529:  29%|██▉       | 7620/25880 [1:35:11<3:47:31,  1.34it/s]
1|7621|Loss: 0.8101144433021545:  29%|██▉       | 7620/25880 [1:35:11<3:47:31,  1.34it/s]
1|7621|Loss: 0.8101144433021545:  29%|██▉       | 7621/25880 [1:35:11<3:43:13,  1.36it/s]
1|7622|Loss: 0.7637870907783508:  29%|██▉       | 7621/25880 [1:35:12<3:43:13,  1.36it/s]
1|7622|Loss: 0.7637870907783508:  29%|██▉       | 7622/25880 [1:35:12<3:31:02,  1.44it/s]
1|7623|Loss: 1.0510367155075073:  29%|██▉       | 7622/25880 [1:35:12<3:31:02,  1.44it/s]
1|7623|Loss: 1.0510367155075073:  29%|██▉       | 7623/25880 [1:35:13<3:24:48,  1.49it/s]
1|7624|Loss: 0.8338055610656738:  29%|██▉       | 7623/25880 [1:35:13<3:24:48,  1.49it/s]
1|7624|Loss: 0.8338055610656738:  29%|██▉       | 7624/25880 [1:35:13<3:08:12,  1.62it/s]
1|7625|Loss: 0.9142931699752808:  29%|██▉       | 7624/25880 [1:35:14<3:08:12,  1.62it/s]
1|7625|Loss: 0.9142931699752808:  29%|██▉       | 7625/25880 [1:35:14<3:22:04,  1.51it/s]
1|7626|Loss: 0.775590181350708:  29%|██▉       | 7625/25880 [1:35:14<3:22:04,  1.51it/s] 
1|7626|Loss: 0.775590181350708:  29%|██▉       | 7626/25880 [1:35:15<3:20:54,  1.51it/s]
1|7627|Loss: 0.8470627069473267:  29%|██▉       | 7626/25880 [1:35:15<3:20:54,  1.51it/s]
1|7627|Loss: 0.8470627069473267:  29%|██▉       | 7627/25880 [1:35:15<3:33:03,  1.43it/s]
1|7628|Loss: 0.8393155336380005:  29%|██▉       | 7627/25880 [1:35:16<3:33:03,  1.43it/s]
1|7628|Loss: 0.8393155336380005:  29%|██▉       | 7628/25880 [1:35:16<3:38:21,  1.39it/s]
1|7629|Loss: 0.7407656311988831:  29%|██▉       | 7628/25880 [1:35:16<3:38:21,  1.39it/s]
1|7629|Loss: 0.7407656311988831:  29%|██▉       | 7629/25880 [1:35:17<3:14:25,  1.56it/s]
1|7630|Loss: 0.7539385557174683:  29%|██▉       | 7629/25880 [1:35:17<3:14:25,  1.56it/s]
1|7630|Loss: 0.7539385557174683:  29%|██▉       | 7630/25880 [1:35:17<3:01:12,  1.68it/s]
1|7631|Loss: 0.8573961853981018:  29%|██▉       | 7630/25880 [1:35:18<3:01:12,  1.68it/s]
1|7631|Loss: 0.8573961853981018:  29%|██▉       | 7631/25880 [1:35:18<3:19:28,  1.52it/s]
1|7632|Loss: 0.8100526332855225:  29%|██▉       | 7631/25880 [1:35:18<3:19:28,  1.52it/s]
1|7632|Loss: 0.8100526332855225:  29%|██▉       | 7632/25880 [1:35:19<3:30:20,  1.45it/s]
1|7633|Loss: 0.7937071919441223:  29%|██▉       | 7632/25880 [1:35:19<3:30:20,  1.45it/s]
1|7633|Loss: 0.7937071919441223:  29%|██▉       | 7633/25880 [1:35:19<3:24:24,  1.49it/s]
1|7634|Loss: 0.8419177532196045:  29%|██▉       | 7633/25880 [1:35:20<3:24:24,  1.49it/s]
1|7634|Loss: 0.8419177532196045:  29%|██▉       | 7634/25880 [1:35:20<3:13:43,  1.57it/s]
1|7635|Loss: 0.877114474773407:  29%|██▉       | 7634/25880 [1:35:20<3:13:43,  1.57it/s] 
1|7635|Loss: 0.877114474773407:  30%|██▉       | 7635/25880 [1:35:21<3:19:02,  1.53it/s]
1|7636|Loss: 0.9055271744728088:  30%|██▉       | 7635/25880 [1:35:21<3:19:02,  1.53it/s]
1|7636|Loss: 0.9055271744728088:  30%|██▉       | 7636/25880 [1:35:21<3:39:10,  1.39it/s]
1|7637|Loss: 0.8914209008216858:  30%|██▉       | 7636/25880 [1:35:22<3:39:10,  1.39it/s]
1|7637|Loss: 0.8914209008216858:  30%|██▉       | 7637/25880 [1:35:22<3:43:35,  1.36it/s]
1|7638|Loss: 0.749820351600647:  30%|██▉       | 7637/25880 [1:35:23<3:43:35,  1.36it/s] 
1|7638|Loss: 0.749820351600647:  30%|██▉       | 7638/25880 [1:35:23<3:22:45,  1.50it/s]
1|7639|Loss: 0.8358321189880371:  30%|██▉       | 7638/25880 [1:35:23<3:22:45,  1.50it/s]
1|7639|Loss: 0.8358321189880371:  30%|██▉       | 7639/25880 [1:35:23<3:22:47,  1.50it/s]
1|7640|Loss: 0.9231694340705872:  30%|██▉       | 7639/25880 [1:35:24<3:22:47,  1.50it/s]
1|7640|Loss: 0.9231694340705872:  30%|██▉       | 7640/25880 [1:35:24<3:15:50,  1.55it/s]
1|7641|Loss: 0.9246231317520142:  30%|██▉       | 7640/25880 [1:35:24<3:15:50,  1.55it/s]
1|7641|Loss: 0.9246231317520142:  30%|██▉       | 7641/25880 [1:35:25<3:19:56,  1.52it/s]
1|7642|Loss: 0.8592026233673096:  30%|██▉       | 7641/25880 [1:35:25<3:19:56,  1.52it/s]
1|7642|Loss: 0.8592026233673096:  30%|██▉       | 7642/25880 [1:35:25<3:33:23,  1.42it/s]
1|7643|Loss: 0.7556825876235962:  30%|██▉       | 7642/25880 [1:35:26<3:33:23,  1.42it/s]
1|7643|Loss: 0.7556825876235962:  30%|██▉       | 7643/25880 [1:35:26<3:44:33,  1.35it/s]
1|7644|Loss: 0.8101065754890442:  30%|██▉       | 7643/25880 [1:35:27<3:44:33,  1.35it/s]
1|7644|Loss: 0.8101065754890442:  30%|██▉       | 7644/25880 [1:35:27<3:37:37,  1.40it/s]
1|7645|Loss: 0.9035903215408325:  30%|██▉       | 7644/25880 [1:35:27<3:37:37,  1.40it/s]
1|7645|Loss: 0.9035903215408325:  30%|██▉       | 7645/25880 [1:35:28<3:36:57,  1.40it/s]
1|7646|Loss: 0.6847116947174072:  30%|██▉       | 7645/25880 [1:35:28<3:36:57,  1.40it/s]
1|7646|Loss: 0.6847116947174072:  30%|██▉       | 7646/25880 [1:35:28<3:30:14,  1.45it/s]
1|7647|Loss: 0.8608834147453308:  30%|██▉       | 7646/25880 [1:35:29<3:30:14,  1.45it/s]
1|7647|Loss: 0.8608834147453308:  30%|██▉       | 7647/25880 [1:35:29<3:21:58,  1.50it/s]
1|7648|Loss: 0.8867879509925842:  30%|██▉       | 7647/25880 [1:35:29<3:21:58,  1.50it/s]
1|7648|Loss: 0.8867879509925842:  30%|██▉       | 7648/25880 [1:35:30<3:30:26,  1.44it/s]
1|7649|Loss: 0.866989016532898:  30%|██▉       | 7648/25880 [1:35:30<3:30:26,  1.44it/s] 
1|7649|Loss: 0.866989016532898:  30%|██▉       | 7649/25880 [1:35:30<3:35:15,  1.41it/s]
1|7650|Loss: 0.768515944480896:  30%|██▉       | 7649/25880 [1:35:31<3:35:15,  1.41it/s]
1|7650|Loss: 0.768515944480896:  30%|██▉       | 7650/25880 [1:35:31<3:45:38,  1.35it/s]
1|7651|Loss: 0.828585684299469:  30%|██▉       | 7650/25880 [1:35:32<3:45:38,  1.35it/s]
1|7651|Loss: 0.828585684299469:  30%|██▉       | 7651/25880 [1:35:32<3:40:16,  1.38it/s]
1|7652|Loss: 0.9423379898071289:  30%|██▉       | 7651/25880 [1:35:32<3:40:16,  1.38it/s]
1|7652|Loss: 0.9423379898071289:  30%|██▉       | 7652/25880 [1:35:33<3:39:35,  1.38it/s]
1|7653|Loss: 0.9088042378425598:  30%|██▉       | 7652/25880 [1:35:33<3:39:35,  1.38it/s]
1|7653|Loss: 0.9088042378425598:  30%|██▉       | 7653/25880 [1:35:33<3:31:32,  1.44it/s]
1|7654|Loss: 0.8161190152168274:  30%|██▉       | 7653/25880 [1:35:34<3:31:32,  1.44it/s]
1|7654|Loss: 0.8161190152168274:  30%|██▉       | 7654/25880 [1:35:34<3:35:58,  1.41it/s]
1|7655|Loss: 0.7029907703399658:  30%|██▉       | 7654/25880 [1:35:34<3:35:58,  1.41it/s]
1|7655|Loss: 0.7029907703399658:  30%|██▉       | 7655/25880 [1:35:35<3:37:12,  1.40it/s]
1|7656|Loss: 0.8788802027702332:  30%|██▉       | 7655/25880 [1:35:35<3:37:12,  1.40it/s]
1|7656|Loss: 0.8788802027702332:  30%|██▉       | 7656/25880 [1:35:36<3:51:15,  1.31it/s]
1|7657|Loss: 0.8308563828468323:  30%|██▉       | 7656/25880 [1:35:36<3:51:15,  1.31it/s]
1|7657|Loss: 0.8308563828468323:  30%|██▉       | 7657/25880 [1:35:36<3:41:31,  1.37it/s]
1|7658|Loss: 0.8711977005004883:  30%|██▉       | 7657/25880 [1:35:37<3:41:31,  1.37it/s]
1|7658|Loss: 0.8711977005004883:  30%|██▉       | 7658/25880 [1:35:37<3:47:33,  1.33it/s]
1|7659|Loss: 0.9415650367736816:  30%|██▉       | 7658/25880 [1:35:37<3:47:33,  1.33it/s]
1|7659|Loss: 0.9415650367736816:  30%|██▉       | 7659/25880 [1:35:38<3:46:15,  1.34it/s]
1|7660|Loss: 0.8298078179359436:  30%|██▉       | 7659/25880 [1:35:38<3:46:15,  1.34it/s]
1|7660|Loss: 0.8298078179359436:  30%|██▉       | 7660/25880 [1:35:38<3:31:39,  1.43it/s]
1|7661|Loss: 0.8583967685699463:  30%|██▉       | 7660/25880 [1:35:39<3:31:39,  1.43it/s]
1|7661|Loss: 0.8583967685699463:  30%|██▉       | 7661/25880 [1:35:39<3:24:59,  1.48it/s]
1|7662|Loss: 0.8645060062408447:  30%|██▉       | 7661/25880 [1:35:39<3:24:59,  1.48it/s]
1|7662|Loss: 0.8645060062408447:  30%|██▉       | 7662/25880 [1:35:40<3:22:11,  1.50it/s]
1|7663|Loss: 0.8121304512023926:  30%|██▉       | 7662/25880 [1:35:40<3:22:11,  1.50it/s]
1|7663|Loss: 0.8121304512023926:  30%|██▉       | 7663/25880 [1:35:40<3:18:06,  1.53it/s]
1|7664|Loss: 0.7595706582069397:  30%|██▉       | 7663/25880 [1:35:41<3:18:06,  1.53it/s]
1|7664|Loss: 0.7595706582069397:  30%|██▉       | 7664/25880 [1:35:41<3:10:01,  1.60it/s]
1|7665|Loss: 0.8035833239555359:  30%|██▉       | 7664/25880 [1:35:41<3:10:01,  1.60it/s]
1|7665|Loss: 0.8035833239555359:  30%|██▉       | 7665/25880 [1:35:42<3:23:27,  1.49it/s]
1|7666|Loss: 0.7149617075920105:  30%|██▉       | 7665/25880 [1:35:42<3:23:27,  1.49it/s]
1|7666|Loss: 0.7149617075920105:  30%|██▉       | 7666/25880 [1:35:42<3:31:32,  1.44it/s]
1|7667|Loss: 0.8346033692359924:  30%|██▉       | 7666/25880 [1:35:43<3:31:32,  1.44it/s]
1|7667|Loss: 0.8346033692359924:  30%|██▉       | 7667/25880 [1:35:43<3:35:22,  1.41it/s]
1|7668|Loss: 0.8791459202766418:  30%|██▉       | 7667/25880 [1:35:43<3:35:22,  1.41it/s]
1|7668|Loss: 0.8791459202766418:  30%|██▉       | 7668/25880 [1:35:44<3:28:25,  1.46it/s]
1|7669|Loss: 1.0223349332809448:  30%|██▉       | 7668/25880 [1:35:44<3:28:25,  1.46it/s]
1|7669|Loss: 1.0223349332809448:  30%|██▉       | 7669/25880 [1:35:44<3:28:22,  1.46it/s]
1|7670|Loss: 0.8715245127677917:  30%|██▉       | 7669/25880 [1:35:45<3:28:22,  1.46it/s]
1|7670|Loss: 0.8715245127677917:  30%|██▉       | 7670/25880 [1:35:45<3:20:09,  1.52it/s]
1|7671|Loss: 0.7657333016395569:  30%|██▉       | 7670/25880 [1:35:45<3:20:09,  1.52it/s]
1|7671|Loss: 0.7657333016395569:  30%|██▉       | 7671/25880 [1:35:46<3:32:08,  1.43it/s]
1|7672|Loss: 0.8779321312904358:  30%|██▉       | 7671/25880 [1:35:46<3:32:08,  1.43it/s]
1|7672|Loss: 0.8779321312904358:  30%|██▉       | 7672/25880 [1:35:46<3:28:55,  1.45it/s]
1|7673|Loss: 0.8394245505332947:  30%|██▉       | 7672/25880 [1:35:47<3:28:55,  1.45it/s]
1|7673|Loss: 0.8394245505332947:  30%|██▉       | 7673/25880 [1:35:47<3:30:58,  1.44it/s]
1|7674|Loss: 0.8646368384361267:  30%|██▉       | 7673/25880 [1:35:48<3:30:58,  1.44it/s]
1|7674|Loss: 0.8646368384361267:  30%|██▉       | 7674/25880 [1:35:48<3:44:11,  1.35it/s]
1|7675|Loss: 0.9126750230789185:  30%|██▉       | 7674/25880 [1:35:48<3:44:11,  1.35it/s]
1|7675|Loss: 0.9126750230789185:  30%|██▉       | 7675/25880 [1:35:49<3:54:01,  1.30it/s]
1|7676|Loss: 0.8835852742195129:  30%|██▉       | 7675/25880 [1:35:49<3:54:01,  1.30it/s]
1|7676|Loss: 0.8835852742195129:  30%|██▉       | 7676/25880 [1:35:50<3:52:22,  1.31it/s]
1|7677|Loss: 0.8010676503181458:  30%|██▉       | 7676/25880 [1:35:50<3:52:22,  1.31it/s]
1|7677|Loss: 0.8010676503181458:  30%|██▉       | 7677/25880 [1:35:50<3:34:23,  1.42it/s]
1|7678|Loss: 0.9093686938285828:  30%|██▉       | 7677/25880 [1:35:51<3:34:23,  1.42it/s]
1|7678|Loss: 0.9093686938285828:  30%|██▉       | 7678/25880 [1:35:51<3:32:29,  1.43it/s]
1|7679|Loss: 0.8941386342048645:  30%|██▉       | 7678/25880 [1:35:51<3:32:29,  1.43it/s]
1|7679|Loss: 0.8941386342048645:  30%|██▉       | 7679/25880 [1:35:52<3:45:10,  1.35it/s]
1|7680|Loss: 0.8148232102394104:  30%|██▉       | 7679/25880 [1:35:52<3:45:10,  1.35it/s]
1|7680|Loss: 0.8148232102394104:  30%|██▉       | 7680/25880 [1:35:52<3:45:22,  1.35it/s]
1|7681|Loss: 0.7619912028312683:  30%|██▉       | 7680/25880 [1:35:53<3:45:22,  1.35it/s]
1|7681|Loss: 0.7619912028312683:  30%|██▉       | 7681/25880 [1:35:53<3:48:42,  1.33it/s]
1|7682|Loss: 0.8754065632820129:  30%|██▉       | 7681/25880 [1:35:54<3:48:42,  1.33it/s]
1|7682|Loss: 0.8754065632820129:  30%|██▉       | 7682/25880 [1:35:54<3:56:12,  1.28it/s]
1|7683|Loss: 0.8622360229492188:  30%|██▉       | 7682/25880 [1:35:54<3:56:12,  1.28it/s]
1|7683|Loss: 0.8622360229492188:  30%|██▉       | 7683/25880 [1:35:55<3:48:33,  1.33it/s]
1|7684|Loss: 0.9033104181289673:  30%|██▉       | 7683/25880 [1:35:55<3:48:33,  1.33it/s]
1|7684|Loss: 0.9033104181289673:  30%|██▉       | 7684/25880 [1:35:56<4:01:52,  1.25it/s]
1|7685|Loss: 0.8772802948951721:  30%|██▉       | 7684/25880 [1:35:56<4:01:52,  1.25it/s]
1|7685|Loss: 0.8772802948951721:  30%|██▉       | 7685/25880 [1:35:56<3:59:46,  1.26it/s]
1|7686|Loss: 0.8024780750274658:  30%|██▉       | 7685/25880 [1:35:57<3:59:46,  1.26it/s]
1|7686|Loss: 0.8024780750274658:  30%|██▉       | 7686/25880 [1:35:57<3:54:23,  1.29it/s]
1|7687|Loss: 0.8655722141265869:  30%|██▉       | 7686/25880 [1:35:58<3:54:23,  1.29it/s]
1|7687|Loss: 0.8655722141265869:  30%|██▉       | 7687/25880 [1:35:58<3:58:00,  1.27it/s]
1|7688|Loss: 0.866267204284668:  30%|██▉       | 7687/25880 [1:35:58<3:58:00,  1.27it/s] 
1|7688|Loss: 0.866267204284668:  30%|██▉       | 7688/25880 [1:35:59<3:43:24,  1.36it/s]
1|7689|Loss: 0.8122376799583435:  30%|██▉       | 7688/25880 [1:35:59<3:43:24,  1.36it/s]
1|7689|Loss: 0.8122376799583435:  30%|██▉       | 7689/25880 [1:35:59<3:25:08,  1.48it/s]
1|7690|Loss: 0.8262832164764404:  30%|██▉       | 7689/25880 [1:36:00<3:25:08,  1.48it/s]
1|7690|Loss: 0.8262832164764404:  30%|██▉       | 7690/25880 [1:36:00<3:39:02,  1.38it/s]
1|7691|Loss: 0.7469645738601685:  30%|██▉       | 7690/25880 [1:36:00<3:39:02,  1.38it/s]
1|7691|Loss: 0.7469645738601685:  30%|██▉       | 7691/25880 [1:36:01<3:43:38,  1.36it/s]
1|7692|Loss: 0.8146204948425293:  30%|██▉       | 7691/25880 [1:36:01<3:43:38,  1.36it/s]
1|7692|Loss: 0.8146204948425293:  30%|██▉       | 7692/25880 [1:36:02<3:51:00,  1.31it/s]
1|7693|Loss: 0.8913441300392151:  30%|██▉       | 7692/25880 [1:36:02<3:51:00,  1.31it/s]
1|7693|Loss: 0.8913441300392151:  30%|██▉       | 7693/25880 [1:36:02<3:49:43,  1.32it/s]
1|7694|Loss: 0.9006465673446655:  30%|██▉       | 7693/25880 [1:36:03<3:49:43,  1.32it/s]
1|7694|Loss: 0.9006465673446655:  30%|██▉       | 7694/25880 [1:36:03<3:50:50,  1.31it/s]
1|7695|Loss: 0.8364361524581909:  30%|██▉       | 7694/25880 [1:36:03<3:50:50,  1.31it/s]
1|7695|Loss: 0.8364361524581909:  30%|██▉       | 7695/25880 [1:36:04<3:47:02,  1.33it/s]
1|7696|Loss: 0.8315465450286865:  30%|██▉       | 7695/25880 [1:36:04<3:47:02,  1.33it/s]
1|7696|Loss: 0.8315465450286865:  30%|██▉       | 7696/25880 [1:36:04<3:36:13,  1.40it/s]
1|7697|Loss: 0.9542130827903748:  30%|██▉       | 7696/25880 [1:36:05<3:36:13,  1.40it/s]
1|7697|Loss: 0.9542130827903748:  30%|██▉       | 7697/25880 [1:36:05<3:33:44,  1.42it/s]
1|7698|Loss: 0.810130774974823:  30%|██▉       | 7697/25880 [1:36:06<3:33:44,  1.42it/s] 
1|7698|Loss: 0.810130774974823:  30%|██▉       | 7698/25880 [1:36:06<3:35:42,  1.40it/s]
1|7699|Loss: 0.8470785617828369:  30%|██▉       | 7698/25880 [1:36:06<3:35:42,  1.40it/s]
1|7699|Loss: 0.8470785617828369:  30%|██▉       | 7699/25880 [1:36:07<3:42:55,  1.36it/s]
1|7700|Loss: 0.8252968788146973:  30%|██▉       | 7699/25880 [1:36:07<3:42:55,  1.36it/s]
1|7700|Loss: 0.8252968788146973:  30%|██▉       | 7700/25880 [1:36:07<3:27:30,  1.46it/s]
1|7701|Loss: 0.9049515128135681:  30%|██▉       | 7700/25880 [1:36:08<3:27:30,  1.46it/s]
1|7701|Loss: 0.9049515128135681:  30%|██▉       | 7701/25880 [1:36:08<3:25:25,  1.47it/s]
1|7702|Loss: 0.8451634049415588:  30%|██▉       | 7701/25880 [1:36:08<3:25:25,  1.47it/s]
1|7702|Loss: 0.8451634049415588:  30%|██▉       | 7702/25880 [1:36:09<3:40:20,  1.38it/s]
1|7703|Loss: 0.8010965585708618:  30%|██▉       | 7702/25880 [1:36:09<3:40:20,  1.38it/s]
1|7703|Loss: 0.8010965585708618:  30%|██▉       | 7703/25880 [1:36:10<3:50:57,  1.31it/s]
1|7704|Loss: 0.7339485883712769:  30%|██▉       | 7703/25880 [1:36:10<3:50:57,  1.31it/s]
1|7704|Loss: 0.7339485883712769:  30%|██▉       | 7704/25880 [1:36:10<3:50:53,  1.31it/s]
1|7705|Loss: 0.8269603848457336:  30%|██▉       | 7704/25880 [1:36:11<3:50:53,  1.31it/s]
1|7705|Loss: 0.8269603848457336:  30%|██▉       | 7705/25880 [1:36:11<3:46:26,  1.34it/s]
1|7706|Loss: 0.856454610824585:  30%|██▉       | 7705/25880 [1:36:11<3:46:26,  1.34it/s] 
1|7706|Loss: 0.856454610824585:  30%|██▉       | 7706/25880 [1:36:12<3:48:42,  1.32it/s]
1|7707|Loss: 0.9134185910224915:  30%|██▉       | 7706/25880 [1:36:12<3:48:42,  1.32it/s]
1|7707|Loss: 0.9134185910224915:  30%|██▉       | 7707/25880 [1:36:13<3:48:17,  1.33it/s]
1|7708|Loss: 0.8173748254776001:  30%|██▉       | 7707/25880 [1:36:13<3:48:17,  1.33it/s]
1|7708|Loss: 0.8173748254776001:  30%|██▉       | 7708/25880 [1:36:13<3:54:13,  1.29it/s]
1|7709|Loss: 0.8071281313896179:  30%|██▉       | 7708/25880 [1:36:14<3:54:13,  1.29it/s]
1|7709|Loss: 0.8071281313896179:  30%|██▉       | 7709/25880 [1:36:14<3:49:32,  1.32it/s]
1|7710|Loss: 1.093568205833435:  30%|██▉       | 7709/25880 [1:36:14<3:49:32,  1.32it/s] 
1|7710|Loss: 1.093568205833435:  30%|██▉       | 7710/25880 [1:36:15<3:39:47,  1.38it/s]
1|7711|Loss: 0.9649553894996643:  30%|██▉       | 7710/25880 [1:36:15<3:39:47,  1.38it/s]
1|7711|Loss: 0.9649553894996643:  30%|██▉       | 7711/25880 [1:36:15<3:38:53,  1.38it/s]
1|7712|Loss: 0.8703836798667908:  30%|██▉       | 7711/25880 [1:36:16<3:38:53,  1.38it/s]
1|7712|Loss: 0.8703836798667908:  30%|██▉       | 7712/25880 [1:36:16<3:23:06,  1.49it/s]
1|7713|Loss: 0.8161023259162903:  30%|██▉       | 7712/25880 [1:36:16<3:23:06,  1.49it/s]
1|7713|Loss: 0.8161023259162903:  30%|██▉       | 7713/25880 [1:36:17<3:29:52,  1.44it/s]
1|7714|Loss: 0.974962055683136:  30%|██▉       | 7713/25880 [1:36:17<3:29:52,  1.44it/s] 
1|7714|Loss: 0.974962055683136:  30%|██▉       | 7714/25880 [1:36:17<3:32:20,  1.43it/s]
1|7715|Loss: 0.9452147483825684:  30%|██▉       | 7714/25880 [1:36:18<3:32:20,  1.43it/s]
1|7715|Loss: 0.9452147483825684:  30%|██▉       | 7715/25880 [1:36:18<3:41:01,  1.37it/s]
1|7716|Loss: 0.8110320568084717:  30%|██▉       | 7715/25880 [1:36:19<3:41:01,  1.37it/s]
1|7716|Loss: 0.8110320568084717:  30%|██▉       | 7716/25880 [1:36:19<3:42:47,  1.36it/s]
1|7717|Loss: 0.862248420715332:  30%|██▉       | 7716/25880 [1:36:19<3:42:47,  1.36it/s] 
1|7717|Loss: 0.862248420715332:  30%|██▉       | 7717/25880 [1:36:20<3:43:19,  1.36it/s]
1|7718|Loss: 0.778742790222168:  30%|██▉       | 7717/25880 [1:36:20<3:43:19,  1.36it/s]
1|7718|Loss: 0.778742790222168:  30%|██▉       | 7718/25880 [1:36:21<3:51:26,  1.31it/s]
1|7719|Loss: 0.7685062885284424:  30%|██▉       | 7718/25880 [1:36:21<3:51:26,  1.31it/s]
1|7719|Loss: 0.7685062885284424:  30%|██▉       | 7719/25880 [1:36:21<3:44:11,  1.35it/s]
1|7720|Loss: 0.825452446937561:  30%|██▉       | 7719/25880 [1:36:22<3:44:11,  1.35it/s] 
1|7720|Loss: 0.825452446937561:  30%|██▉       | 7720/25880 [1:36:22<3:41:50,  1.36it/s]
1|7721|Loss: 0.7648812532424927:  30%|██▉       | 7720/25880 [1:36:22<3:41:50,  1.36it/s]
1|7721|Loss: 0.7648812532424927:  30%|██▉       | 7721/25880 [1:36:23<3:39:23,  1.38it/s]
1|7722|Loss: 0.8394520282745361:  30%|██▉       | 7721/25880 [1:36:23<3:39:23,  1.38it/s]
1|7722|Loss: 0.8394520282745361:  30%|██▉       | 7722/25880 [1:36:24<3:56:19,  1.28it/s]
1|7723|Loss: 0.8352009057998657:  30%|██▉       | 7722/25880 [1:36:24<3:56:19,  1.28it/s]
1|7723|Loss: 0.8352009057998657:  30%|██▉       | 7723/25880 [1:36:24<3:53:55,  1.29it/s]
1|7724|Loss: 0.7422081232070923:  30%|██▉       | 7723/25880 [1:36:25<3:53:55,  1.29it/s]
1|7724|Loss: 0.7422081232070923:  30%|██▉       | 7724/25880 [1:36:25<3:49:19,  1.32it/s]
1|7725|Loss: 0.8083094358444214:  30%|██▉       | 7724/25880 [1:36:25<3:49:19,  1.32it/s]
1|7725|Loss: 0.8083094358444214:  30%|██▉       | 7725/25880 [1:36:26<3:39:59,  1.38it/s]
1|7726|Loss: 0.816428542137146:  30%|██▉       | 7725/25880 [1:36:26<3:39:59,  1.38it/s] 
1|7726|Loss: 0.816428542137146:  30%|██▉       | 7726/25880 [1:36:27<3:45:54,  1.34it/s]
1|7727|Loss: 0.8649414777755737:  30%|██▉       | 7726/25880 [1:36:27<3:45:54,  1.34it/s]
1|7727|Loss: 0.8649414777755737:  30%|██▉       | 7727/25880 [1:36:27<3:46:58,  1.33it/s]
1|7728|Loss: 0.9462901949882507:  30%|██▉       | 7727/25880 [1:36:28<3:46:58,  1.33it/s]
1|7728|Loss: 0.9462901949882507:  30%|██▉       | 7728/25880 [1:36:28<3:52:38,  1.30it/s]
1|7729|Loss: 0.8348944187164307:  30%|██▉       | 7728/25880 [1:36:29<3:52:38,  1.30it/s]
1|7729|Loss: 0.8348944187164307:  30%|██▉       | 7729/25880 [1:36:29<3:51:48,  1.31it/s]
1|7730|Loss: 0.8724352717399597:  30%|██▉       | 7729/25880 [1:36:29<3:51:48,  1.31it/s]
1|7730|Loss: 0.8724352717399597:  30%|██▉       | 7730/25880 [1:36:30<3:54:23,  1.29it/s]
1|7731|Loss: 0.9111899137496948:  30%|██▉       | 7730/25880 [1:36:30<3:54:23,  1.29it/s]
1|7731|Loss: 0.9111899137496948:  30%|██▉       | 7731/25880 [1:36:30<3:56:55,  1.28it/s]
1|7732|Loss: 0.8201870918273926:  30%|██▉       | 7731/25880 [1:36:31<3:56:55,  1.28it/s]
1|7732|Loss: 0.8201870918273926:  30%|██▉       | 7732/25880 [1:36:31<3:51:11,  1.31it/s]
1|7733|Loss: 0.7754403352737427:  30%|██▉       | 7732/25880 [1:36:32<3:51:11,  1.31it/s]
1|7733|Loss: 0.7754403352737427:  30%|██▉       | 7733/25880 [1:36:32<3:47:42,  1.33it/s]
1|7734|Loss: 0.7943951487541199:  30%|██▉       | 7733/25880 [1:36:32<3:47:42,  1.33it/s]
1|7734|Loss: 0.7943951487541199:  30%|██▉       | 7734/25880 [1:36:33<3:37:46,  1.39it/s]
1|7735|Loss: 1.0236269235610962:  30%|██▉       | 7734/25880 [1:36:33<3:37:46,  1.39it/s]
1|7735|Loss: 1.0236269235610962:  30%|██▉       | 7735/25880 [1:36:33<3:49:45,  1.32it/s]
1|7736|Loss: 0.8645369410514832:  30%|██▉       | 7735/25880 [1:36:34<3:49:45,  1.32it/s]
1|7736|Loss: 0.8645369410514832:  30%|██▉       | 7736/25880 [1:36:34<3:37:26,  1.39it/s]
1|7737|Loss: 1.0455691814422607:  30%|██▉       | 7736/25880 [1:36:34<3:37:26,  1.39it/s]
1|7737|Loss: 1.0455691814422607:  30%|██▉       | 7737/25880 [1:36:35<3:48:45,  1.32it/s]
1|7738|Loss: 0.8954277038574219:  30%|██▉       | 7737/25880 [1:36:35<3:48:45,  1.32it/s]
1|7738|Loss: 0.8954277038574219:  30%|██▉       | 7738/25880 [1:36:36<3:56:50,  1.28it/s]
1|7739|Loss: 0.900915801525116:  30%|██▉       | 7738/25880 [1:36:36<3:56:50,  1.28it/s] 
1|7739|Loss: 0.900915801525116:  30%|██▉       | 7739/25880 [1:36:36<3:54:52,  1.29it/s]
1|7740|Loss: 0.8887972831726074:  30%|██▉       | 7739/25880 [1:36:37<3:54:52,  1.29it/s]
1|7740|Loss: 0.8887972831726074:  30%|██▉       | 7740/25880 [1:36:37<4:03:58,  1.24it/s]
1|7741|Loss: 0.8841402530670166:  30%|██▉       | 7740/25880 [1:36:38<4:03:58,  1.24it/s]
1|7741|Loss: 0.8841402530670166:  30%|██▉       | 7741/25880 [1:36:38<3:53:24,  1.30it/s]
1|7742|Loss: 0.7948933243751526:  30%|██▉       | 7741/25880 [1:36:38<3:53:24,  1.30it/s]
1|7742|Loss: 0.7948933243751526:  30%|██▉       | 7742/25880 [1:36:39<3:55:08,  1.29it/s]
1|7743|Loss: 1.0216984748840332:  30%|██▉       | 7742/25880 [1:36:39<3:55:08,  1.29it/s]
1|7743|Loss: 1.0216984748840332:  30%|██▉       | 7743/25880 [1:36:40<3:45:44,  1.34it/s]
1|7744|Loss: 0.9054380655288696:  30%|██▉       | 7743/25880 [1:36:40<3:45:44,  1.34it/s]
1|7744|Loss: 0.9054380655288696:  30%|██▉       | 7744/25880 [1:36:40<3:42:44,  1.36it/s]
1|7745|Loss: 0.860548734664917:  30%|██▉       | 7744/25880 [1:36:41<3:42:44,  1.36it/s] 
1|7745|Loss: 0.860548734664917:  30%|██▉       | 7745/25880 [1:36:41<3:17:00,  1.53it/s]
1|7746|Loss: 0.905613362789154:  30%|██▉       | 7745/25880 [1:36:41<3:17:00,  1.53it/s]
1|7746|Loss: 0.905613362789154:  30%|██▉       | 7746/25880 [1:36:41<3:29:20,  1.44it/s]
1|7747|Loss: 0.843411386013031:  30%|██▉       | 7746/25880 [1:36:42<3:29:20,  1.44it/s]
1|7747|Loss: 0.843411386013031:  30%|██▉       | 7747/25880 [1:36:42<3:53:28,  1.29it/s]
1|7748|Loss: 0.8184113502502441:  30%|██▉       | 7747/25880 [1:36:43<3:53:28,  1.29it/s]
1|7748|Loss: 0.8184113502502441:  30%|██▉       | 7748/25880 [1:36:43<4:01:29,  1.25it/s]
1|7749|Loss: 0.7948554158210754:  30%|██▉       | 7748/25880 [1:36:44<4:01:29,  1.25it/s]
1|7749|Loss: 0.7948554158210754:  30%|██▉       | 7749/25880 [1:36:44<3:54:40,  1.29it/s]
1|7750|Loss: 0.8467100858688354:  30%|██▉       | 7749/25880 [1:36:44<3:54:40,  1.29it/s]
1|7750|Loss: 0.8467100858688354:  30%|██▉       | 7750/25880 [1:36:45<3:47:54,  1.33it/s]
1|7751|Loss: 0.9309192895889282:  30%|██▉       | 7750/25880 [1:36:45<3:47:54,  1.33it/s]
1|7751|Loss: 0.9309192895889282:  30%|██▉       | 7751/25880 [1:36:46<3:54:58,  1.29it/s]
1|7752|Loss: 0.8526287078857422:  30%|██▉       | 7751/25880 [1:36:46<3:54:58,  1.29it/s]
1|7752|Loss: 0.8526287078857422:  30%|██▉       | 7752/25880 [1:36:46<3:47:20,  1.33it/s]
1|7753|Loss: 0.9384997487068176:  30%|██▉       | 7752/25880 [1:36:47<3:47:20,  1.33it/s]
1|7753|Loss: 0.9384997487068176:  30%|██▉       | 7753/25880 [1:36:47<3:41:54,  1.36it/s]
1|7754|Loss: 0.6949793100357056:  30%|██▉       | 7753/25880 [1:36:47<3:41:54,  1.36it/s]
1|7754|Loss: 0.6949793100357056:  30%|██▉       | 7754/25880 [1:36:48<3:33:26,  1.42it/s]
1|7755|Loss: 1.0074063539505005:  30%|██▉       | 7754/25880 [1:36:48<3:33:26,  1.42it/s]
1|7755|Loss: 1.0074063539505005:  30%|██▉       | 7755/25880 [1:36:48<3:41:34,  1.36it/s]
1|7756|Loss: 0.9529780745506287:  30%|██▉       | 7755/25880 [1:36:49<3:41:34,  1.36it/s]
1|7756|Loss: 0.9529780745506287:  30%|██▉       | 7756/25880 [1:36:49<3:30:03,  1.44it/s]
1|7757|Loss: 0.8602911233901978:  30%|██▉       | 7756/25880 [1:36:49<3:30:03,  1.44it/s]
1|7757|Loss: 0.8602911233901978:  30%|██▉       | 7757/25880 [1:36:50<3:30:16,  1.44it/s]
1|7758|Loss: 0.9334020614624023:  30%|██▉       | 7757/25880 [1:36:50<3:30:16,  1.44it/s]
1|7758|Loss: 0.9334020614624023:  30%|██▉       | 7758/25880 [1:36:50<3:31:33,  1.43it/s]
1|7759|Loss: 0.8675711154937744:  30%|██▉       | 7758/25880 [1:36:51<3:31:33,  1.43it/s]
1|7759|Loss: 0.8675711154937744:  30%|██▉       | 7759/25880 [1:36:51<3:27:00,  1.46it/s]
1|7760|Loss: 0.7614784836769104:  30%|██▉       | 7759/25880 [1:36:51<3:27:00,  1.46it/s]
1|7760|Loss: 0.7614784836769104:  30%|██▉       | 7760/25880 [1:36:52<3:34:59,  1.40it/s]
1|7761|Loss: 1.016618251800537:  30%|██▉       | 7760/25880 [1:36:52<3:34:59,  1.40it/s] 
1|7761|Loss: 1.016618251800537:  30%|██▉       | 7761/25880 [1:36:53<3:39:16,  1.38it/s]
1|7762|Loss: 0.8767170310020447:  30%|██▉       | 7761/25880 [1:36:53<3:39:16,  1.38it/s]
1|7762|Loss: 0.8767170310020447:  30%|██▉       | 7762/25880 [1:36:53<3:40:57,  1.37it/s]
1|7763|Loss: 0.7841877341270447:  30%|██▉       | 7762/25880 [1:36:54<3:40:57,  1.37it/s]
1|7763|Loss: 0.7841877341270447:  30%|██▉       | 7763/25880 [1:36:54<3:55:23,  1.28it/s]
1|7764|Loss: 0.8610845804214478:  30%|██▉       | 7763/25880 [1:36:55<3:55:23,  1.28it/s]
1|7764|Loss: 0.8610845804214478:  30%|███       | 7764/25880 [1:36:55<3:53:59,  1.29it/s]
1|7765|Loss: 0.8376797437667847:  30%|███       | 7764/25880 [1:36:55<3:53:59,  1.29it/s]
1|7765|Loss: 0.8376797437667847:  30%|███       | 7765/25880 [1:36:56<3:43:29,  1.35it/s]
1|7766|Loss: 0.8883479237556458:  30%|███       | 7765/25880 [1:36:56<3:43:29,  1.35it/s]
1|7766|Loss: 0.8883479237556458:  30%|███       | 7766/25880 [1:36:56<3:42:31,  1.36it/s]
1|7767|Loss: 0.8599724173545837:  30%|███       | 7766/25880 [1:36:57<3:42:31,  1.36it/s]
1|7767|Loss: 0.8599724173545837:  30%|███       | 7767/25880 [1:36:57<3:56:19,  1.28it/s]
1|7768|Loss: 0.8098070025444031:  30%|███       | 7767/25880 [1:36:58<3:56:19,  1.28it/s]
1|7768|Loss: 0.8098070025444031:  30%|███       | 7768/25880 [1:36:58<3:54:38,  1.29it/s]
1|7769|Loss: 0.8380681872367859:  30%|███       | 7768/25880 [1:36:58<3:54:38,  1.29it/s]
1|7769|Loss: 0.8380681872367859:  30%|███       | 7769/25880 [1:36:59<3:43:47,  1.35it/s]
1|7770|Loss: 0.9501550793647766:  30%|███       | 7769/25880 [1:36:59<3:43:47,  1.35it/s]
1|7770|Loss: 0.9501550793647766:  30%|███       | 7770/25880 [1:36:59<3:26:29,  1.46it/s]
1|7771|Loss: 0.8111630082130432:  30%|███       | 7770/25880 [1:37:00<3:26:29,  1.46it/s]
1|7771|Loss: 0.8111630082130432:  30%|███       | 7771/25880 [1:37:00<3:34:25,  1.41it/s]
1|7772|Loss: 0.7166261672973633:  30%|███       | 7771/25880 [1:37:00<3:34:25,  1.41it/s]
1|7772|Loss: 0.7166261672973633:  30%|███       | 7772/25880 [1:37:01<3:38:15,  1.38it/s]
1|7773|Loss: 0.8595126271247864:  30%|███       | 7772/25880 [1:37:01<3:38:15,  1.38it/s]
1|7773|Loss: 0.8595126271247864:  30%|███       | 7773/25880 [1:37:02<3:48:02,  1.32it/s]
1|7774|Loss: 0.8852839469909668:  30%|███       | 7773/25880 [1:37:02<3:48:02,  1.32it/s]
1|7774|Loss: 0.8852839469909668:  30%|███       | 7774/25880 [1:37:02<3:42:12,  1.36it/s]
1|7775|Loss: 0.8789856433868408:  30%|███       | 7774/25880 [1:37:03<3:42:12,  1.36it/s]
1|7775|Loss: 0.8789856433868408:  30%|███       | 7775/25880 [1:37:03<3:37:37,  1.39it/s]
1|7776|Loss: 0.8935937881469727:  30%|███       | 7775/25880 [1:37:03<3:37:37,  1.39it/s]
1|7776|Loss: 0.8935937881469727:  30%|███       | 7776/25880 [1:37:04<3:37:10,  1.39it/s]
1|7777|Loss: 0.8084860444068909:  30%|███       | 7776/25880 [1:37:04<3:37:10,  1.39it/s]
1|7777|Loss: 0.8084860444068909:  30%|███       | 7777/25880 [1:37:04<3:38:54,  1.38it/s]
1|7778|Loss: 0.9380927085876465:  30%|███       | 7777/25880 [1:37:05<3:38:54,  1.38it/s]
1|7778|Loss: 0.9380927085876465:  30%|███       | 7778/25880 [1:37:05<3:31:31,  1.43it/s]
1|7779|Loss: 0.8131775259971619:  30%|███       | 7778/25880 [1:37:05<3:31:31,  1.43it/s]
1|7779|Loss: 0.8131775259971619:  30%|███       | 7779/25880 [1:37:06<3:42:17,  1.36it/s]
1|7780|Loss: 0.8558481931686401:  30%|███       | 7779/25880 [1:37:06<3:42:17,  1.36it/s]
1|7780|Loss: 0.8558481931686401:  30%|███       | 7780/25880 [1:37:07<3:44:21,  1.34it/s]
1|7781|Loss: 0.7512125968933105:  30%|███       | 7780/25880 [1:37:07<3:44:21,  1.34it/s]
1|7781|Loss: 0.7512125968933105:  30%|███       | 7781/25880 [1:37:07<3:40:51,  1.37it/s]
1|7782|Loss: 0.9025511145591736:  30%|███       | 7781/25880 [1:37:08<3:40:51,  1.37it/s]
1|7782|Loss: 0.9025511145591736:  30%|███       | 7782/25880 [1:37:08<3:32:03,  1.42it/s]
1|7783|Loss: 0.79068523645401:  30%|███       | 7782/25880 [1:37:08<3:32:03,  1.42it/s]  
1|7783|Loss: 0.79068523645401:  30%|███       | 7783/25880 [1:37:09<3:33:53,  1.41it/s]
1|7784|Loss: 0.9179222583770752:  30%|███       | 7783/25880 [1:37:09<3:33:53,  1.41it/s]
1|7784|Loss: 0.9179222583770752:  30%|███       | 7784/25880 [1:37:10<3:43:06,  1.35it/s]
1|7785|Loss: 0.9517038464546204:  30%|███       | 7784/25880 [1:37:10<3:43:06,  1.35it/s]
1|7785|Loss: 0.9517038464546204:  30%|███       | 7785/25880 [1:37:10<3:42:10,  1.36it/s]
1|7786|Loss: 0.9198733568191528:  30%|███       | 7785/25880 [1:37:11<3:42:10,  1.36it/s]
1|7786|Loss: 0.9198733568191528:  30%|███       | 7786/25880 [1:37:11<3:34:13,  1.41it/s]
1|7787|Loss: 0.9334234595298767:  30%|███       | 7786/25880 [1:37:11<3:34:13,  1.41it/s]
1|7787|Loss: 0.9334234595298767:  30%|███       | 7787/25880 [1:37:12<3:28:15,  1.45it/s]
1|7788|Loss: 0.8448707461357117:  30%|███       | 7787/25880 [1:37:12<3:28:15,  1.45it/s]
1|7788|Loss: 0.8448707461357117:  30%|███       | 7788/25880 [1:37:12<3:16:13,  1.54it/s]
1|7789|Loss: 0.9459896087646484:  30%|███       | 7788/25880 [1:37:12<3:16:13,  1.54it/s]
1|7789|Loss: 0.9459896087646484:  30%|███       | 7789/25880 [1:37:13<3:13:18,  1.56it/s]
1|7790|Loss: 1.0161789655685425:  30%|███       | 7789/25880 [1:37:13<3:13:18,  1.56it/s]
1|7790|Loss: 1.0161789655685425:  30%|███       | 7790/25880 [1:37:14<3:28:29,  1.45it/s]
1|7791|Loss: 0.8444786071777344:  30%|███       | 7790/25880 [1:37:14<3:28:29,  1.45it/s]
1|7791|Loss: 0.8444786071777344:  30%|███       | 7791/25880 [1:37:14<3:48:16,  1.32it/s]
1|7792|Loss: 0.7990012168884277:  30%|███       | 7791/25880 [1:37:15<3:48:16,  1.32it/s]
1|7792|Loss: 0.7990012168884277:  30%|███       | 7792/25880 [1:37:15<3:56:23,  1.28it/s]
1|7793|Loss: 0.8881078362464905:  30%|███       | 7792/25880 [1:37:16<3:56:23,  1.28it/s]
1|7793|Loss: 0.8881078362464905:  30%|███       | 7793/25880 [1:37:16<3:54:35,  1.29it/s]
1|7794|Loss: 0.836510956287384:  30%|███       | 7793/25880 [1:37:16<3:54:35,  1.29it/s] 
1|7794|Loss: 0.836510956287384:  30%|███       | 7794/25880 [1:37:17<4:01:43,  1.25it/s]
1|7795|Loss: 0.8543698191642761:  30%|███       | 7794/25880 [1:37:17<4:01:43,  1.25it/s]
1|7795|Loss: 0.8543698191642761:  30%|███       | 7795/25880 [1:37:18<4:11:46,  1.20it/s]
1|7796|Loss: 0.8987164497375488:  30%|███       | 7795/25880 [1:37:18<4:11:46,  1.20it/s]
1|7796|Loss: 0.8987164497375488:  30%|███       | 7796/25880 [1:37:18<3:57:40,  1.27it/s]
1|7797|Loss: 0.79165118932724:  30%|███       | 7796/25880 [1:37:19<3:57:40,  1.27it/s]  
1|7797|Loss: 0.79165118932724:  30%|███       | 7797/25880 [1:37:19<3:39:40,  1.37it/s]
1|7798|Loss: 0.8088139891624451:  30%|███       | 7797/25880 [1:37:19<3:39:40,  1.37it/s]
1|7798|Loss: 0.8088139891624451:  30%|███       | 7798/25880 [1:37:20<3:35:19,  1.40it/s]
1|7799|Loss: 0.9081794023513794:  30%|███       | 7798/25880 [1:37:20<3:35:19,  1.40it/s]
1|7799|Loss: 0.9081794023513794:  30%|███       | 7799/25880 [1:37:21<3:40:13,  1.37it/s]
1|7800|Loss: 0.7992718815803528:  30%|███       | 7799/25880 [1:37:21<3:40:13,  1.37it/s]
1|7800|Loss: 0.7992718815803528:  30%|███       | 7800/25880 [1:37:21<3:39:49,  1.37it/s]
1|7801|Loss: 0.888790488243103:  30%|███       | 7800/25880 [1:37:22<3:39:49,  1.37it/s] 
1|7801|Loss: 0.888790488243103:  30%|███       | 7801/25880 [1:37:22<3:39:48,  1.37it/s]
1|7802|Loss: 0.8896098136901855:  30%|███       | 7801/25880 [1:37:22<3:39:48,  1.37it/s]
1|7802|Loss: 0.8896098136901855:  30%|███       | 7802/25880 [1:37:23<3:41:23,  1.36it/s]
1|7803|Loss: 0.9391665458679199:  30%|███       | 7802/25880 [1:37:23<3:41:23,  1.36it/s]
1|7803|Loss: 0.9391665458679199:  30%|███       | 7803/25880 [1:37:24<3:52:45,  1.29it/s]
1|7804|Loss: 1.0328315496444702:  30%|███       | 7803/25880 [1:37:24<3:52:45,  1.29it/s]
1|7804|Loss: 1.0328315496444702:  30%|███       | 7804/25880 [1:37:24<3:57:27,  1.27it/s]
1|7805|Loss: 0.8091581463813782:  30%|███       | 7804/25880 [1:37:25<3:57:27,  1.27it/s]
1|7805|Loss: 0.8091581463813782:  30%|███       | 7805/25880 [1:37:25<3:51:30,  1.30it/s]
1|7806|Loss: 0.797031581401825:  30%|███       | 7805/25880 [1:37:26<3:51:30,  1.30it/s] 
1|7806|Loss: 0.797031581401825:  30%|███       | 7806/25880 [1:37:26<3:46:06,  1.33it/s]
1|7807|Loss: 0.9777887463569641:  30%|███       | 7806/25880 [1:37:26<3:46:06,  1.33it/s]
1|7807|Loss: 0.9777887463569641:  30%|███       | 7807/25880 [1:37:27<3:37:20,  1.39it/s]
1|7808|Loss: 0.7547046542167664:  30%|███       | 7807/25880 [1:37:27<3:37:20,  1.39it/s]
1|7808|Loss: 0.7547046542167664:  30%|███       | 7808/25880 [1:37:27<3:36:06,  1.39it/s]
1|7809|Loss: 0.910962700843811:  30%|███       | 7808/25880 [1:37:28<3:36:06,  1.39it/s] 
1|7809|Loss: 0.910962700843811:  30%|███       | 7809/25880 [1:37:28<3:30:35,  1.43it/s]
1|7810|Loss: 0.9309822916984558:  30%|███       | 7809/25880 [1:37:28<3:30:35,  1.43it/s]
1|7810|Loss: 0.9309822916984558:  30%|███       | 7810/25880 [1:37:29<3:31:48,  1.42it/s]
1|7811|Loss: 0.7758402824401855:  30%|███       | 7810/25880 [1:37:29<3:31:48,  1.42it/s]
1|7811|Loss: 0.7758402824401855:  30%|███       | 7811/25880 [1:37:29<3:27:59,  1.45it/s]
1|7812|Loss: 0.9016230702400208:  30%|███       | 7811/25880 [1:37:30<3:27:59,  1.45it/s]
1|7812|Loss: 0.9016230702400208:  30%|███       | 7812/25880 [1:37:30<3:37:28,  1.38it/s]
1|7813|Loss: 0.8556864261627197:  30%|███       | 7812/25880 [1:37:31<3:37:28,  1.38it/s]
1|7813|Loss: 0.8556864261627197:  30%|███       | 7813/25880 [1:37:31<3:49:52,  1.31it/s]
1|7814|Loss: 0.8190376162528992:  30%|███       | 7813/25880 [1:37:31<3:49:52,  1.31it/s]
1|7814|Loss: 0.8190376162528992:  30%|███       | 7814/25880 [1:37:32<3:49:54,  1.31it/s]
1|7815|Loss: 0.7872520089149475:  30%|███       | 7814/25880 [1:37:32<3:49:54,  1.31it/s]
1|7815|Loss: 0.7872520089149475:  30%|███       | 7815/25880 [1:37:32<3:54:01,  1.29it/s]
1|7816|Loss: 0.7970325946807861:  30%|███       | 7815/25880 [1:37:33<3:54:01,  1.29it/s]
1|7816|Loss: 0.7970325946807861:  30%|███       | 7816/25880 [1:37:33<3:51:36,  1.30it/s]
1|7817|Loss: 0.8135872483253479:  30%|███       | 7816/25880 [1:37:34<3:51:36,  1.30it/s]
1|7817|Loss: 0.8135872483253479:  30%|███       | 7817/25880 [1:37:34<3:57:14,  1.27it/s]
1|7818|Loss: 0.7626596093177795:  30%|███       | 7817/25880 [1:37:34<3:57:14,  1.27it/s]
1|7818|Loss: 0.7626596093177795:  30%|███       | 7818/25880 [1:37:35<3:39:07,  1.37it/s]
1|7819|Loss: 0.8749843239784241:  30%|███       | 7818/25880 [1:37:35<3:39:07,  1.37it/s]
1|7819|Loss: 0.8749843239784241:  30%|███       | 7819/25880 [1:37:35<3:22:39,  1.49it/s]
1|7820|Loss: 0.9356318116188049:  30%|███       | 7819/25880 [1:37:36<3:22:39,  1.49it/s]
1|7820|Loss: 0.9356318116188049:  30%|███       | 7820/25880 [1:37:36<3:34:09,  1.41it/s]
1|7821|Loss: 0.8901404738426208:  30%|███       | 7820/25880 [1:37:36<3:34:09,  1.41it/s]
1|7821|Loss: 0.8901404738426208:  30%|███       | 7821/25880 [1:37:37<3:43:56,  1.34it/s]
1|7822|Loss: 0.9937812089920044:  30%|███       | 7821/25880 [1:37:37<3:43:56,  1.34it/s]
1|7822|Loss: 0.9937812089920044:  30%|███       | 7822/25880 [1:37:37<3:28:16,  1.45it/s]
1|7823|Loss: 0.8220155835151672:  30%|███       | 7822/25880 [1:37:38<3:28:16,  1.45it/s]
1|7823|Loss: 0.8220155835151672:  30%|███       | 7823/25880 [1:37:38<3:15:03,  1.54it/s]
1|7824|Loss: 0.8767962455749512:  30%|███       | 7823/25880 [1:37:38<3:15:03,  1.54it/s]
1|7824|Loss: 0.8767962455749512:  30%|███       | 7824/25880 [1:37:39<3:12:54,  1.56it/s]
1|7825|Loss: 0.8251582384109497:  30%|███       | 7824/25880 [1:37:39<3:12:54,  1.56it/s]
1|7825|Loss: 0.8251582384109497:  30%|███       | 7825/25880 [1:37:39<3:17:39,  1.52it/s]
1|7826|Loss: 0.7733864784240723:  30%|███       | 7825/25880 [1:37:40<3:17:39,  1.52it/s]
1|7826|Loss: 0.7733864784240723:  30%|███       | 7826/25880 [1:37:40<3:40:54,  1.36it/s]
1|7827|Loss: 0.8362094163894653:  30%|███       | 7826/25880 [1:37:41<3:40:54,  1.36it/s]
1|7827|Loss: 0.8362094163894653:  30%|███       | 7827/25880 [1:37:41<3:38:45,  1.38it/s]
1|7828|Loss: 0.9569782614707947:  30%|███       | 7827/25880 [1:37:41<3:38:45,  1.38it/s]
1|7828|Loss: 0.9569782614707947:  30%|███       | 7828/25880 [1:37:42<3:31:10,  1.42it/s]
1|7829|Loss: 0.8105136156082153:  30%|███       | 7828/25880 [1:37:42<3:31:10,  1.42it/s]
1|7829|Loss: 0.8105136156082153:  30%|███       | 7829/25880 [1:37:42<3:32:13,  1.42it/s]
1|7830|Loss: 0.7973018288612366:  30%|███       | 7829/25880 [1:37:43<3:32:13,  1.42it/s]
1|7830|Loss: 0.7973018288612366:  30%|███       | 7830/25880 [1:37:43<3:38:12,  1.38it/s]
1|7831|Loss: 0.7563507556915283:  30%|███       | 7830/25880 [1:37:43<3:38:12,  1.38it/s]
1|7831|Loss: 0.7563507556915283:  30%|███       | 7831/25880 [1:37:44<3:29:36,  1.44it/s]
1|7832|Loss: 0.8612560033798218:  30%|███       | 7831/25880 [1:37:44<3:29:36,  1.44it/s]
1|7832|Loss: 0.8612560033798218:  30%|███       | 7832/25880 [1:37:44<3:23:20,  1.48it/s]
1|7833|Loss: 0.8428462743759155:  30%|███       | 7832/25880 [1:37:45<3:23:20,  1.48it/s]
1|7833|Loss: 0.8428462743759155:  30%|███       | 7833/25880 [1:37:45<3:26:57,  1.45it/s]
1|7834|Loss: 0.8848879337310791:  30%|███       | 7833/25880 [1:37:45<3:26:57,  1.45it/s]
1|7834|Loss: 0.8848879337310791:  30%|███       | 7834/25880 [1:37:46<3:30:27,  1.43it/s]
1|7835|Loss: 0.9680284261703491:  30%|███       | 7834/25880 [1:37:46<3:30:27,  1.43it/s]
1|7835|Loss: 0.9680284261703491:  30%|███       | 7835/25880 [1:37:46<3:18:26,  1.52it/s]
1|7836|Loss: 0.8771220445632935:  30%|███       | 7835/25880 [1:37:47<3:18:26,  1.52it/s]
1|7836|Loss: 0.8771220445632935:  30%|███       | 7836/25880 [1:37:47<3:21:29,  1.49it/s]
1|7837|Loss: 0.8767949342727661:  30%|███       | 7836/25880 [1:37:47<3:21:29,  1.49it/s]
1|7837|Loss: 0.8767949342727661:  30%|███       | 7837/25880 [1:37:48<3:21:33,  1.49it/s]
1|7838|Loss: 0.9279497265815735:  30%|███       | 7837/25880 [1:37:48<3:21:33,  1.49it/s]
1|7838|Loss: 0.9279497265815735:  30%|███       | 7838/25880 [1:37:48<3:15:20,  1.54it/s]
1|7839|Loss: 0.9421677589416504:  30%|███       | 7838/25880 [1:37:49<3:15:20,  1.54it/s]
1|7839|Loss: 0.9421677589416504:  30%|███       | 7839/25880 [1:37:49<3:17:32,  1.52it/s]
1|7840|Loss: 0.8879526853561401:  30%|███       | 7839/25880 [1:37:49<3:17:32,  1.52it/s]
1|7840|Loss: 0.8879526853561401:  30%|███       | 7840/25880 [1:37:50<3:28:39,  1.44it/s]
1|7841|Loss: 0.9177144765853882:  30%|███       | 7840/25880 [1:37:50<3:28:39,  1.44it/s]
1|7841|Loss: 0.9177144765853882:  30%|███       | 7841/25880 [1:37:50<3:34:00,  1.40it/s]
1|7842|Loss: 0.7866296172142029:  30%|███       | 7841/25880 [1:37:51<3:34:00,  1.40it/s]
1|7842|Loss: 0.7866296172142029:  30%|███       | 7842/25880 [1:37:51<3:30:01,  1.43it/s]
1|7843|Loss: 0.8408143520355225:  30%|███       | 7842/25880 [1:37:51<3:30:01,  1.43it/s]
1|7843|Loss: 0.8408143520355225:  30%|███       | 7843/25880 [1:37:52<3:32:42,  1.41it/s]
1|7844|Loss: 0.8897883892059326:  30%|███       | 7843/25880 [1:37:52<3:32:42,  1.41it/s]
1|7844|Loss: 0.8897883892059326:  30%|███       | 7844/25880 [1:37:53<3:35:32,  1.39it/s]
1|7845|Loss: 0.7760874032974243:  30%|███       | 7844/25880 [1:37:53<3:35:32,  1.39it/s]
1|7845|Loss: 0.7760874032974243:  30%|███       | 7845/25880 [1:37:53<3:16:26,  1.53it/s]
1|7846|Loss: 0.7571635842323303:  30%|███       | 7845/25880 [1:37:53<3:16:26,  1.53it/s]
1|7846|Loss: 0.7571635842323303:  30%|███       | 7846/25880 [1:37:54<3:26:35,  1.45it/s]
1|7847|Loss: 0.8259695172309875:  30%|███       | 7846/25880 [1:37:54<3:26:35,  1.45it/s]
1|7847|Loss: 0.8259695172309875:  30%|███       | 7847/25880 [1:37:55<3:32:48,  1.41it/s]
1|7848|Loss: 0.816989541053772:  30%|███       | 7847/25880 [1:37:55<3:32:48,  1.41it/s] 
1|7848|Loss: 0.816989541053772:  30%|███       | 7848/25880 [1:37:55<3:40:08,  1.37it/s]
1|7849|Loss: 0.9265425205230713:  30%|███       | 7848/25880 [1:37:56<3:40:08,  1.37it/s]
1|7849|Loss: 0.9265425205230713:  30%|███       | 7849/25880 [1:37:56<3:33:10,  1.41it/s]
1|7850|Loss: 0.7921217083930969:  30%|███       | 7849/25880 [1:37:56<3:33:10,  1.41it/s]
1|7850|Loss: 0.7921217083930969:  30%|███       | 7850/25880 [1:37:57<3:39:44,  1.37it/s]
1|7851|Loss: 0.904653012752533:  30%|███       | 7850/25880 [1:37:57<3:39:44,  1.37it/s] 
1|7851|Loss: 0.904653012752533:  30%|███       | 7851/25880 [1:37:57<3:30:14,  1.43it/s]
1|7852|Loss: 0.8619846105575562:  30%|███       | 7851/25880 [1:37:58<3:30:14,  1.43it/s]
1|7852|Loss: 0.8619846105575562:  30%|███       | 7852/25880 [1:37:58<3:23:55,  1.47it/s]
1|7853|Loss: 0.8438335657119751:  30%|███       | 7852/25880 [1:37:58<3:23:55,  1.47it/s]
1|7853|Loss: 0.8438335657119751:  30%|███       | 7853/25880 [1:37:59<3:25:23,  1.46it/s]
1|7854|Loss: 1.003315806388855:  30%|███       | 7853/25880 [1:37:59<3:25:23,  1.46it/s] 
1|7854|Loss: 1.003315806388855:  30%|███       | 7854/25880 [1:37:59<3:22:26,  1.48it/s]
1|7855|Loss: 0.8475566506385803:  30%|███       | 7854/25880 [1:38:00<3:22:26,  1.48it/s]
1|7855|Loss: 0.8475566506385803:  30%|███       | 7855/25880 [1:38:00<3:24:32,  1.47it/s]
1|7856|Loss: 0.9011755585670471:  30%|███       | 7855/25880 [1:38:01<3:24:32,  1.47it/s]
1|7856|Loss: 0.9011755585670471:  30%|███       | 7856/25880 [1:38:01<3:35:24,  1.39it/s]
1|7857|Loss: 0.8888514637947083:  30%|███       | 7856/25880 [1:38:01<3:35:24,  1.39it/s]
1|7857|Loss: 0.8888514637947083:  30%|███       | 7857/25880 [1:38:02<3:47:48,  1.32it/s]
1|7858|Loss: 0.9282246828079224:  30%|███       | 7857/25880 [1:38:02<3:47:48,  1.32it/s]
1|7858|Loss: 0.9282246828079224:  30%|███       | 7858/25880 [1:38:03<3:56:24,  1.27it/s]
1|7859|Loss: 0.702293872833252:  30%|███       | 7858/25880 [1:38:03<3:56:24,  1.27it/s] 
1|7859|Loss: 0.702293872833252:  30%|███       | 7859/25880 [1:38:03<3:45:20,  1.33it/s]
1|7860|Loss: 0.8968270421028137:  30%|███       | 7859/25880 [1:38:04<3:45:20,  1.33it/s]
1|7860|Loss: 0.8968270421028137:  30%|███       | 7860/25880 [1:38:04<3:34:46,  1.40it/s]
1|7861|Loss: 1.0561648607254028:  30%|███       | 7860/25880 [1:38:04<3:34:46,  1.40it/s]
1|7861|Loss: 1.0561648607254028:  30%|███       | 7861/25880 [1:38:05<3:36:07,  1.39it/s]
1|7862|Loss: 0.8869643807411194:  30%|███       | 7861/25880 [1:38:05<3:36:07,  1.39it/s]
1|7862|Loss: 0.8869643807411194:  30%|███       | 7862/25880 [1:38:06<3:54:57,  1.28it/s]
1|7863|Loss: 0.705708384513855:  30%|███       | 7862/25880 [1:38:06<3:54:57,  1.28it/s] 
1|7863|Loss: 0.705708384513855:  30%|███       | 7863/25880 [1:38:06<3:38:21,  1.38it/s]
1|7864|Loss: 0.7672011256217957:  30%|███       | 7863/25880 [1:38:07<3:38:21,  1.38it/s]
1|7864|Loss: 0.7672011256217957:  30%|███       | 7864/25880 [1:38:07<3:38:29,  1.37it/s]
1|7865|Loss: 0.8482806086540222:  30%|███       | 7864/25880 [1:38:07<3:38:29,  1.37it/s]
1|7865|Loss: 0.8482806086540222:  30%|███       | 7865/25880 [1:38:08<3:48:37,  1.31it/s]
1|7866|Loss: 0.8781681656837463:  30%|███       | 7865/25880 [1:38:08<3:48:37,  1.31it/s]
1|7866|Loss: 0.8781681656837463:  30%|███       | 7866/25880 [1:38:09<3:56:47,  1.27it/s]
1|7867|Loss: 0.8818516731262207:  30%|███       | 7866/25880 [1:38:09<3:56:47,  1.27it/s]
1|7867|Loss: 0.8818516731262207:  30%|███       | 7867/25880 [1:38:09<3:46:38,  1.32it/s]
1|7868|Loss: 0.766431450843811:  30%|███       | 7867/25880 [1:38:10<3:46:38,  1.32it/s] 
1|7868|Loss: 0.766431450843811:  30%|███       | 7868/25880 [1:38:10<3:35:41,  1.39it/s]
1|7869|Loss: 0.9143274426460266:  30%|███       | 7868/25880 [1:38:10<3:35:41,  1.39it/s]
1|7869|Loss: 0.9143274426460266:  30%|███       | 7869/25880 [1:38:11<3:40:37,  1.36it/s]
1|7870|Loss: 0.9179208278656006:  30%|███       | 7869/25880 [1:38:11<3:40:37,  1.36it/s]
1|7870|Loss: 0.9179208278656006:  30%|███       | 7870/25880 [1:38:11<3:34:55,  1.40it/s]
1|7871|Loss: 0.9431663155555725:  30%|███       | 7870/25880 [1:38:12<3:34:55,  1.40it/s]
1|7871|Loss: 0.9431663155555725:  30%|███       | 7871/25880 [1:38:12<3:35:26,  1.39it/s]
1|7872|Loss: 0.9564376473426819:  30%|███       | 7871/25880 [1:38:13<3:35:26,  1.39it/s]
1|7872|Loss: 0.9564376473426819:  30%|███       | 7872/25880 [1:38:13<3:47:07,  1.32it/s]
1|7873|Loss: 0.6764150261878967:  30%|███       | 7872/25880 [1:38:13<3:47:07,  1.32it/s]
1|7873|Loss: 0.6764150261878967:  30%|███       | 7873/25880 [1:38:14<4:00:54,  1.25it/s]
1|7874|Loss: 0.7783915400505066:  30%|███       | 7873/25880 [1:38:14<4:00:54,  1.25it/s]
1|7874|Loss: 0.7783915400505066:  30%|███       | 7874/25880 [1:38:15<4:08:07,  1.21it/s]
1|7875|Loss: 0.8882601857185364:  30%|███       | 7874/25880 [1:38:15<4:08:07,  1.21it/s]
1|7875|Loss: 0.8882601857185364:  30%|███       | 7875/25880 [1:38:15<4:02:18,  1.24it/s]
1|7876|Loss: 0.778390645980835:  30%|███       | 7875/25880 [1:38:16<4:02:18,  1.24it/s] 
1|7876|Loss: 0.778390645980835:  30%|███       | 7876/25880 [1:38:16<3:59:04,  1.26it/s]
1|7877|Loss: 0.8406403064727783:  30%|███       | 7876/25880 [1:38:17<3:59:04,  1.26it/s]
1|7877|Loss: 0.8406403064727783:  30%|███       | 7877/25880 [1:38:17<3:55:17,  1.28it/s]
1|7878|Loss: 0.8244633674621582:  30%|███       | 7877/25880 [1:38:17<3:55:17,  1.28it/s]
1|7878|Loss: 0.8244633674621582:  30%|███       | 7878/25880 [1:38:18<3:50:59,  1.30it/s]
1|7879|Loss: 0.6395689249038696:  30%|███       | 7878/25880 [1:38:18<3:50:59,  1.30it/s]
1|7879|Loss: 0.6395689249038696:  30%|███       | 7879/25880 [1:38:18<3:38:52,  1.37it/s]
1|7880|Loss: 0.8592602014541626:  30%|███       | 7879/25880 [1:38:19<3:38:52,  1.37it/s]
1|7880|Loss: 0.8592602014541626:  30%|███       | 7880/25880 [1:38:19<3:37:00,  1.38it/s]
1|7881|Loss: 0.8737503290176392:  30%|███       | 7880/25880 [1:38:20<3:37:00,  1.38it/s]
1|7881|Loss: 0.8737503290176392:  30%|███       | 7881/25880 [1:38:20<3:46:21,  1.33it/s]
1|7882|Loss: 0.8529654741287231:  30%|███       | 7881/25880 [1:38:20<3:46:21,  1.33it/s]
1|7882|Loss: 0.8529654741287231:  30%|███       | 7882/25880 [1:38:21<3:36:37,  1.38it/s]
1|7883|Loss: 0.7996286153793335:  30%|███       | 7882/25880 [1:38:21<3:36:37,  1.38it/s]
1|7883|Loss: 0.7996286153793335:  30%|███       | 7883/25880 [1:38:21<3:27:50,  1.44it/s]
1|7884|Loss: 0.9068549871444702:  30%|███       | 7883/25880 [1:38:22<3:27:50,  1.44it/s]
1|7884|Loss: 0.9068549871444702:  30%|███       | 7884/25880 [1:38:22<3:29:40,  1.43it/s]
1|7885|Loss: 0.7891823649406433:  30%|███       | 7884/25880 [1:38:22<3:29:40,  1.43it/s]
1|7885|Loss: 0.7891823649406433:  30%|███       | 7885/25880 [1:38:23<3:32:20,  1.41it/s]
1|7886|Loss: 0.8474264740943909:  30%|███       | 7885/25880 [1:38:23<3:32:20,  1.41it/s]
1|7886|Loss: 0.8474264740943909:  30%|███       | 7886/25880 [1:38:23<3:39:36,  1.37it/s]
1|7887|Loss: 0.8684396147727966:  30%|███       | 7886/25880 [1:38:24<3:39:36,  1.37it/s]
1|7887|Loss: 0.8684396147727966:  30%|███       | 7887/25880 [1:38:24<3:38:21,  1.37it/s]
1|7888|Loss: 0.8485921621322632:  30%|███       | 7887/25880 [1:38:25<3:38:21,  1.37it/s]
1|7888|Loss: 0.8485921621322632:  30%|███       | 7888/25880 [1:38:25<3:35:59,  1.39it/s]
1|7889|Loss: 0.7601807117462158:  30%|███       | 7888/25880 [1:38:25<3:35:59,  1.39it/s]
1|7889|Loss: 0.7601807117462158:  30%|███       | 7889/25880 [1:38:26<3:29:54,  1.43it/s]
1|7890|Loss: 0.8625481128692627:  30%|███       | 7889/25880 [1:38:26<3:29:54,  1.43it/s]
1|7890|Loss: 0.8625481128692627:  30%|███       | 7890/25880 [1:38:26<3:37:44,  1.38it/s]
1|7891|Loss: 0.8000954985618591:  30%|███       | 7890/25880 [1:38:27<3:37:44,  1.38it/s]
1|7891|Loss: 0.8000954985618591:  30%|███       | 7891/25880 [1:38:27<3:47:01,  1.32it/s]
1|7892|Loss: 0.7960811853408813:  30%|███       | 7891/25880 [1:38:28<3:47:01,  1.32it/s]
1|7892|Loss: 0.7960811853408813:  30%|███       | 7892/25880 [1:38:28<3:52:06,  1.29it/s]
1|7893|Loss: 0.8471465706825256:  30%|███       | 7892/25880 [1:38:28<3:52:06,  1.29it/s]
1|7893|Loss: 0.8471465706825256:  30%|███       | 7893/25880 [1:38:29<3:38:37,  1.37it/s]
1|7894|Loss: 0.9222652912139893:  30%|███       | 7893/25880 [1:38:29<3:38:37,  1.37it/s]
1|7894|Loss: 0.9222652912139893:  31%|███       | 7894/25880 [1:38:29<3:43:16,  1.34it/s]
1|7895|Loss: 0.7204411625862122:  31%|███       | 7894/25880 [1:38:30<3:43:16,  1.34it/s]
1|7895|Loss: 0.7204411625862122:  31%|███       | 7895/25880 [1:38:30<3:35:10,  1.39it/s]
1|7896|Loss: 0.9186199307441711:  31%|███       | 7895/25880 [1:38:30<3:35:10,  1.39it/s]
1|7896|Loss: 0.9186199307441711:  31%|███       | 7896/25880 [1:38:31<3:25:49,  1.46it/s]
1|7897|Loss: 0.9933027625083923:  31%|███       | 7896/25880 [1:38:31<3:25:49,  1.46it/s]
1|7897|Loss: 0.9933027625083923:  31%|███       | 7897/25880 [1:38:31<3:31:53,  1.41it/s]
1|7898|Loss: 0.8780643343925476:  31%|███       | 7897/25880 [1:38:32<3:31:53,  1.41it/s]
1|7898|Loss: 0.8780643343925476:  31%|███       | 7898/25880 [1:38:32<3:29:12,  1.43it/s]
1|7899|Loss: 0.8820871114730835:  31%|███       | 7898/25880 [1:38:32<3:29:12,  1.43it/s]
1|7899|Loss: 0.8820871114730835:  31%|███       | 7899/25880 [1:38:33<3:14:44,  1.54it/s]
1|7900|Loss: 0.8901488780975342:  31%|███       | 7899/25880 [1:38:33<3:14:44,  1.54it/s]
1|7900|Loss: 0.8901488780975342:  31%|███       | 7900/25880 [1:38:33<3:07:19,  1.60it/s]
1|7901|Loss: 0.8472970128059387:  31%|███       | 7900/25880 [1:38:33<3:07:19,  1.60it/s]
1|7901|Loss: 0.8472970128059387:  31%|███       | 7901/25880 [1:38:34<3:05:38,  1.61it/s]
1|7902|Loss: 0.8079904913902283:  31%|███       | 7901/25880 [1:38:34<3:05:38,  1.61it/s]
1|7902|Loss: 0.8079904913902283:  31%|███       | 7902/25880 [1:38:34<3:13:33,  1.55it/s]
1|7903|Loss: 0.9229968190193176:  31%|███       | 7902/25880 [1:38:35<3:13:33,  1.55it/s]
1|7903|Loss: 0.9229968190193176:  31%|███       | 7903/25880 [1:38:35<3:21:51,  1.48it/s]
1|7904|Loss: 0.8460142612457275:  31%|███       | 7903/25880 [1:38:36<3:21:51,  1.48it/s]
1|7904|Loss: 0.8460142612457275:  31%|███       | 7904/25880 [1:38:36<3:34:04,  1.40it/s]
1|7905|Loss: 0.879421591758728:  31%|███       | 7904/25880 [1:38:36<3:34:04,  1.40it/s] 
1|7905|Loss: 0.879421591758728:  31%|███       | 7905/25880 [1:38:37<3:35:14,  1.39it/s]
1|7906|Loss: 0.880291759967804:  31%|███       | 7905/25880 [1:38:37<3:35:14,  1.39it/s]
1|7906|Loss: 0.880291759967804:  31%|███       | 7906/25880 [1:38:37<3:25:59,  1.45it/s]
1|7907|Loss: 1.0041064023971558:  31%|███       | 7906/25880 [1:38:38<3:25:59,  1.45it/s]
1|7907|Loss: 1.0041064023971558:  31%|███       | 7907/25880 [1:38:38<3:37:29,  1.38it/s]
1|7908|Loss: 1.0182111263275146:  31%|███       | 7907/25880 [1:38:39<3:37:29,  1.38it/s]
1|7908|Loss: 1.0182111263275146:  31%|███       | 7908/25880 [1:38:39<3:30:32,  1.42it/s]
1|7909|Loss: 0.7079073190689087:  31%|███       | 7908/25880 [1:38:39<3:30:32,  1.42it/s]
1|7909|Loss: 0.7079073190689087:  31%|███       | 7909/25880 [1:38:40<3:34:24,  1.40it/s]
1|7910|Loss: 0.801878809928894:  31%|███       | 7909/25880 [1:38:40<3:34:24,  1.40it/s] 
1|7910|Loss: 0.801878809928894:  31%|███       | 7910/25880 [1:38:40<3:28:46,  1.43it/s]
1|7911|Loss: 0.9327561259269714:  31%|███       | 7910/25880 [1:38:41<3:28:46,  1.43it/s]
1|7911|Loss: 0.9327561259269714:  31%|███       | 7911/25880 [1:38:41<3:40:44,  1.36it/s]
1|7912|Loss: 0.8056766390800476:  31%|███       | 7911/25880 [1:38:41<3:40:44,  1.36it/s]
1|7912|Loss: 0.8056766390800476:  31%|███       | 7912/25880 [1:38:42<3:18:58,  1.51it/s]
1|7913|Loss: 0.8664705157279968:  31%|███       | 7912/25880 [1:38:42<3:18:58,  1.51it/s]
1|7913|Loss: 0.8664705157279968:  31%|███       | 7913/25880 [1:38:42<3:24:22,  1.47it/s]
1|7914|Loss: 0.8568732738494873:  31%|███       | 7913/25880 [1:38:43<3:24:22,  1.47it/s]
1|7914|Loss: 0.8568732738494873:  31%|███       | 7914/25880 [1:38:43<3:27:48,  1.44it/s]
1|7915|Loss: 0.7827792167663574:  31%|███       | 7914/25880 [1:38:43<3:27:48,  1.44it/s]
1|7915|Loss: 0.7827792167663574:  31%|███       | 7915/25880 [1:38:44<3:35:37,  1.39it/s]
1|7916|Loss: 0.6784201264381409:  31%|███       | 7915/25880 [1:38:44<3:35:37,  1.39it/s]
1|7916|Loss: 0.6784201264381409:  31%|███       | 7916/25880 [1:38:45<3:50:56,  1.30it/s]
1|7917|Loss: 0.8513645529747009:  31%|███       | 7916/25880 [1:38:45<3:50:56,  1.30it/s]
1|7917|Loss: 0.8513645529747009:  31%|███       | 7917/25880 [1:38:45<3:48:54,  1.31it/s]
1|7918|Loss: 0.8394924998283386:  31%|███       | 7917/25880 [1:38:46<3:48:54,  1.31it/s]
1|7918|Loss: 0.8394924998283386:  31%|███       | 7918/25880 [1:38:46<3:30:16,  1.42it/s]
1|7919|Loss: 0.8215180039405823:  31%|███       | 7918/25880 [1:38:46<3:30:16,  1.42it/s]
1|7919|Loss: 0.8215180039405823:  31%|███       | 7919/25880 [1:38:47<3:22:11,  1.48it/s]
1|7920|Loss: 0.764761209487915:  31%|███       | 7919/25880 [1:38:47<3:22:11,  1.48it/s] 
1|7920|Loss: 0.764761209487915:  31%|███       | 7920/25880 [1:38:47<3:26:38,  1.45it/s]
1|7921|Loss: 0.6397405862808228:  31%|███       | 7920/25880 [1:38:48<3:26:38,  1.45it/s]
1|7921|Loss: 0.6397405862808228:  31%|███       | 7921/25880 [1:38:48<3:47:36,  1.32it/s]
1|7922|Loss: 0.6414462327957153:  31%|███       | 7921/25880 [1:38:49<3:47:36,  1.32it/s]
1|7922|Loss: 0.6414462327957153:  31%|███       | 7922/25880 [1:38:49<3:46:48,  1.32it/s]
1|7923|Loss: 0.848009467124939:  31%|███       | 7922/25880 [1:38:49<3:46:48,  1.32it/s] 
1|7923|Loss: 0.848009467124939:  31%|███       | 7923/25880 [1:38:50<3:33:42,  1.40it/s]
1|7924|Loss: 0.7907510995864868:  31%|███       | 7923/25880 [1:38:50<3:33:42,  1.40it/s]
1|7924|Loss: 0.7907510995864868:  31%|███       | 7924/25880 [1:38:50<3:25:15,  1.46it/s]
1|7925|Loss: 0.6969361305236816:  31%|███       | 7924/25880 [1:38:51<3:25:15,  1.46it/s]
1|7925|Loss: 0.6969361305236816:  31%|███       | 7925/25880 [1:38:51<3:08:07,  1.59it/s]
1|7926|Loss: 0.8262105584144592:  31%|███       | 7925/25880 [1:38:51<3:08:07,  1.59it/s]
1|7926|Loss: 0.8262105584144592:  31%|███       | 7926/25880 [1:38:51<3:09:52,  1.58it/s]
1|7927|Loss: 0.9225451946258545:  31%|███       | 7926/25880 [1:38:52<3:09:52,  1.58it/s]
1|7927|Loss: 0.9225451946258545:  31%|███       | 7927/25880 [1:38:52<3:17:42,  1.51it/s]
1|7928|Loss: 0.7679065465927124:  31%|███       | 7927/25880 [1:38:52<3:17:42,  1.51it/s]
1|7928|Loss: 0.7679065465927124:  31%|███       | 7928/25880 [1:38:53<3:15:22,  1.53it/s]
1|7929|Loss: 0.9434735774993896:  31%|███       | 7928/25880 [1:38:53<3:15:22,  1.53it/s]
1|7929|Loss: 0.9434735774993896:  31%|███       | 7929/25880 [1:38:53<3:12:22,  1.56it/s]
1|7930|Loss: 0.8741952180862427:  31%|███       | 7929/25880 [1:38:54<3:12:22,  1.56it/s]
1|7930|Loss: 0.8741952180862427:  31%|███       | 7930/25880 [1:38:54<3:12:00,  1.56it/s]
1|7931|Loss: 0.7890545725822449:  31%|███       | 7930/25880 [1:38:54<3:12:00,  1.56it/s]
1|7931|Loss: 0.7890545725822449:  31%|███       | 7931/25880 [1:38:55<3:19:27,  1.50it/s]
1|7932|Loss: 0.875950038433075:  31%|███       | 7931/25880 [1:38:55<3:19:27,  1.50it/s] 
1|7932|Loss: 0.875950038433075:  31%|███       | 7932/25880 [1:38:55<3:24:09,  1.47it/s]
1|7933|Loss: 0.8197447657585144:  31%|███       | 7932/25880 [1:38:56<3:24:09,  1.47it/s]
1|7933|Loss: 0.8197447657585144:  31%|███       | 7933/25880 [1:38:56<3:44:05,  1.33it/s]
1|7934|Loss: 0.8780947923660278:  31%|███       | 7933/25880 [1:38:57<3:44:05,  1.33it/s]
1|7934|Loss: 0.8780947923660278:  31%|███       | 7934/25880 [1:38:57<3:50:41,  1.30it/s]
1|7935|Loss: 0.7714859843254089:  31%|███       | 7934/25880 [1:38:58<3:50:41,  1.30it/s]
1|7935|Loss: 0.7714859843254089:  31%|███       | 7935/25880 [1:38:58<4:05:05,  1.22it/s]
1|7936|Loss: 0.8797014355659485:  31%|███       | 7935/25880 [1:38:59<4:05:05,  1.22it/s]
1|7936|Loss: 0.8797014355659485:  31%|███       | 7936/25880 [1:38:59<4:06:48,  1.21it/s]
1|7937|Loss: 0.7723180651664734:  31%|███       | 7936/25880 [1:38:59<4:06:48,  1.21it/s]
1|7937|Loss: 0.7723180651664734:  31%|███       | 7937/25880 [1:39:00<3:59:40,  1.25it/s]
1|7938|Loss: 0.747447669506073:  31%|███       | 7937/25880 [1:39:00<3:59:40,  1.25it/s] 
1|7938|Loss: 0.747447669506073:  31%|███       | 7938/25880 [1:39:00<3:50:45,  1.30it/s]
1|7939|Loss: 0.7445937991142273:  31%|███       | 7938/25880 [1:39:01<3:50:45,  1.30it/s]
1|7939|Loss: 0.7445937991142273:  31%|███       | 7939/25880 [1:39:01<3:46:14,  1.32it/s]
1|7940|Loss: 0.8892976641654968:  31%|███       | 7939/25880 [1:39:02<3:46:14,  1.32it/s]
1|7940|Loss: 0.8892976641654968:  31%|███       | 7940/25880 [1:39:02<3:51:46,  1.29it/s]
1|7941|Loss: 0.7952612638473511:  31%|███       | 7940/25880 [1:39:02<3:51:46,  1.29it/s]
1|7941|Loss: 0.7952612638473511:  31%|███       | 7941/25880 [1:39:03<3:51:27,  1.29it/s]
1|7942|Loss: 0.7847833037376404:  31%|███       | 7941/25880 [1:39:03<3:51:27,  1.29it/s]
1|7942|Loss: 0.7847833037376404:  31%|███       | 7942/25880 [1:39:04<4:05:16,  1.22it/s]
1|7943|Loss: 0.9367690682411194:  31%|███       | 7942/25880 [1:39:04<4:05:16,  1.22it/s]
1|7943|Loss: 0.9367690682411194:  31%|███       | 7943/25880 [1:39:04<3:47:26,  1.31it/s]
1|7944|Loss: 0.9796311855316162:  31%|███       | 7943/25880 [1:39:05<3:47:26,  1.31it/s]
1|7944|Loss: 0.9796311855316162:  31%|███       | 7944/25880 [1:39:05<3:29:49,  1.42it/s]
1|7945|Loss: 0.8266267776489258:  31%|███       | 7944/25880 [1:39:05<3:29:49,  1.42it/s]
1|7945|Loss: 0.8266267776489258:  31%|███       | 7945/25880 [1:39:05<3:27:02,  1.44it/s]
1|7946|Loss: 0.837011456489563:  31%|███       | 7945/25880 [1:39:06<3:27:02,  1.44it/s] 
1|7946|Loss: 0.837011456489563:  31%|███       | 7946/25880 [1:39:06<3:37:18,  1.38it/s]
1|7947|Loss: 0.7968049049377441:  31%|███       | 7946/25880 [1:39:07<3:37:18,  1.38it/s]
1|7947|Loss: 0.7968049049377441:  31%|███       | 7947/25880 [1:39:07<3:30:54,  1.42it/s]
1|7948|Loss: 0.9883323311805725:  31%|███       | 7947/25880 [1:39:07<3:30:54,  1.42it/s]
1|7948|Loss: 0.9883323311805725:  31%|███       | 7948/25880 [1:39:08<3:22:39,  1.47it/s]
1|7949|Loss: 0.845070481300354:  31%|███       | 7948/25880 [1:39:08<3:22:39,  1.47it/s] 
1|7949|Loss: 0.845070481300354:  31%|███       | 7949/25880 [1:39:08<3:25:29,  1.45it/s]
1|7950|Loss: 0.7539952397346497:  31%|███       | 7949/25880 [1:39:09<3:25:29,  1.45it/s]
1|7950|Loss: 0.7539952397346497:  31%|███       | 7950/25880 [1:39:09<3:29:16,  1.43it/s]
1|7951|Loss: 0.8666197061538696:  31%|███       | 7950/25880 [1:39:09<3:29:16,  1.43it/s]
1|7951|Loss: 0.8666197061538696:  31%|███       | 7951/25880 [1:39:10<3:16:00,  1.52it/s]
1|7952|Loss: 0.8060771226882935:  31%|███       | 7951/25880 [1:39:10<3:16:00,  1.52it/s]
1|7952|Loss: 0.8060771226882935:  31%|███       | 7952/25880 [1:39:10<3:16:21,  1.52it/s]
1|7953|Loss: 0.8118882179260254:  31%|███       | 7952/25880 [1:39:11<3:16:21,  1.52it/s]
1|7953|Loss: 0.8118882179260254:  31%|███       | 7953/25880 [1:39:11<3:22:55,  1.47it/s]
1|7954|Loss: 0.7924259305000305:  31%|███       | 7953/25880 [1:39:11<3:22:55,  1.47it/s]
1|7954|Loss: 0.7924259305000305:  31%|███       | 7954/25880 [1:39:12<3:33:10,  1.40it/s]
1|7955|Loss: 0.9109857678413391:  31%|███       | 7954/25880 [1:39:12<3:33:10,  1.40it/s]
1|7955|Loss: 0.9109857678413391:  31%|███       | 7955/25880 [1:39:12<3:27:39,  1.44it/s]
1|7956|Loss: 0.892331600189209:  31%|███       | 7955/25880 [1:39:13<3:27:39,  1.44it/s] 
1|7956|Loss: 0.892331600189209:  31%|███       | 7956/25880 [1:39:13<3:28:50,  1.43it/s]
1|7957|Loss: 0.838930070400238:  31%|███       | 7956/25880 [1:39:14<3:28:50,  1.43it/s]
1|7957|Loss: 0.838930070400238:  31%|███       | 7957/25880 [1:39:14<3:39:25,  1.36it/s]
1|7958|Loss: 0.8391930460929871:  31%|███       | 7957/25880 [1:39:14<3:39:25,  1.36it/s]
1|7958|Loss: 0.8391930460929871:  31%|███       | 7958/25880 [1:39:15<3:32:38,  1.40it/s]
1|7959|Loss: 1.0079095363616943:  31%|███       | 7958/25880 [1:39:15<3:32:38,  1.40it/s]
1|7959|Loss: 1.0079095363616943:  31%|███       | 7959/25880 [1:39:15<3:30:08,  1.42it/s]
1|7960|Loss: 0.9219614863395691:  31%|███       | 7959/25880 [1:39:16<3:30:08,  1.42it/s]
1|7960|Loss: 0.9219614863395691:  31%|███       | 7960/25880 [1:39:16<3:25:50,  1.45it/s]
1|7961|Loss: 0.8142338395118713:  31%|███       | 7960/25880 [1:39:16<3:25:50,  1.45it/s]
1|7961|Loss: 0.8142338395118713:  31%|███       | 7961/25880 [1:39:16<3:17:44,  1.51it/s]
1|7962|Loss: 0.9490185379981995:  31%|███       | 7961/25880 [1:39:17<3:17:44,  1.51it/s]
1|7962|Loss: 0.9490185379981995:  31%|███       | 7962/25880 [1:39:17<3:15:06,  1.53it/s]
1|7963|Loss: 0.7741498947143555:  31%|███       | 7962/25880 [1:39:17<3:15:06,  1.53it/s]
1|7963|Loss: 0.7741498947143555:  31%|███       | 7963/25880 [1:39:18<3:14:20,  1.54it/s]
1|7964|Loss: 0.8718125820159912:  31%|███       | 7963/25880 [1:39:18<3:14:20,  1.54it/s]
1|7964|Loss: 0.8718125820159912:  31%|███       | 7964/25880 [1:39:18<3:19:28,  1.50it/s]
1|7965|Loss: 0.819420576095581:  31%|███       | 7964/25880 [1:39:19<3:19:28,  1.50it/s] 
1|7965|Loss: 0.819420576095581:  31%|███       | 7965/25880 [1:39:19<3:24:56,  1.46it/s]
1|7966|Loss: 0.744278609752655:  31%|███       | 7965/25880 [1:39:20<3:24:56,  1.46it/s]
1|7966|Loss: 0.744278609752655:  31%|███       | 7966/25880 [1:39:20<3:27:00,  1.44it/s]
1|7967|Loss: 0.8515501022338867:  31%|███       | 7966/25880 [1:39:20<3:27:00,  1.44it/s]
1|7967|Loss: 0.8515501022338867:  31%|███       | 7967/25880 [1:39:21<3:29:34,  1.42it/s]
1|7968|Loss: 0.8454073071479797:  31%|███       | 7967/25880 [1:39:21<3:29:34,  1.42it/s]
1|7968|Loss: 0.8454073071479797:  31%|███       | 7968/25880 [1:39:21<3:25:32,  1.45it/s]
1|7969|Loss: 0.7772024273872375:  31%|███       | 7968/25880 [1:39:22<3:25:32,  1.45it/s]
1|7969|Loss: 0.7772024273872375:  31%|███       | 7969/25880 [1:39:22<3:10:28,  1.57it/s]
1|7970|Loss: 0.7725101709365845:  31%|███       | 7969/25880 [1:39:22<3:10:28,  1.57it/s]
1|7970|Loss: 0.7725101709365845:  31%|███       | 7970/25880 [1:39:22<3:14:00,  1.54it/s]
1|7971|Loss: 0.9445744752883911:  31%|███       | 7970/25880 [1:39:23<3:14:00,  1.54it/s]
1|7971|Loss: 0.9445744752883911:  31%|███       | 7971/25880 [1:39:23<3:26:48,  1.44it/s]
1|7972|Loss: 0.7219598889350891:  31%|███       | 7971/25880 [1:39:24<3:26:48,  1.44it/s]
1|7972|Loss: 0.7219598889350891:  31%|███       | 7972/25880 [1:39:24<3:29:31,  1.42it/s]
1|7973|Loss: 0.806125283241272:  31%|███       | 7972/25880 [1:39:24<3:29:31,  1.42it/s] 
1|7973|Loss: 0.806125283241272:  31%|███       | 7973/25880 [1:39:25<3:32:29,  1.40it/s]
1|7974|Loss: 0.9572378396987915:  31%|███       | 7973/25880 [1:39:25<3:32:29,  1.40it/s]
1|7974|Loss: 0.9572378396987915:  31%|███       | 7974/25880 [1:39:26<3:42:05,  1.34it/s]
1|7975|Loss: 0.6980915665626526:  31%|███       | 7974/25880 [1:39:26<3:42:05,  1.34it/s]
1|7975|Loss: 0.6980915665626526:  31%|███       | 7975/25880 [1:39:26<3:16:35,  1.52it/s]
1|7976|Loss: 0.8041127324104309:  31%|███       | 7975/25880 [1:39:26<3:16:35,  1.52it/s]
1|7976|Loss: 0.8041127324104309:  31%|███       | 7976/25880 [1:39:27<3:16:54,  1.52it/s]
1|7977|Loss: 1.0144292116165161:  31%|███       | 7976/25880 [1:39:27<3:16:54,  1.52it/s]
1|7977|Loss: 1.0144292116165161:  31%|███       | 7977/25880 [1:39:27<3:16:52,  1.52it/s]
1|7978|Loss: 0.8171294331550598:  31%|███       | 7977/25880 [1:39:28<3:16:52,  1.52it/s]
1|7978|Loss: 0.8171294331550598:  31%|███       | 7978/25880 [1:39:28<3:10:58,  1.56it/s]
1|7979|Loss: 0.7961474061012268:  31%|███       | 7978/25880 [1:39:28<3:10:58,  1.56it/s]
1|7979|Loss: 0.7961474061012268:  31%|███       | 7979/25880 [1:39:28<3:01:40,  1.64it/s]
1|7980|Loss: 0.7577266693115234:  31%|███       | 7979/25880 [1:39:29<3:01:40,  1.64it/s]
1|7980|Loss: 0.7577266693115234:  31%|███       | 7980/25880 [1:39:29<3:09:16,  1.58it/s]
1|7981|Loss: 0.7707023620605469:  31%|███       | 7980/25880 [1:39:30<3:09:16,  1.58it/s]
1|7981|Loss: 0.7707023620605469:  31%|███       | 7981/25880 [1:39:30<3:04:40,  1.62it/s]
1|7982|Loss: 0.7256171703338623:  31%|███       | 7981/25880 [1:39:30<3:04:40,  1.62it/s]
1|7982|Loss: 0.7256171703338623:  31%|███       | 7982/25880 [1:39:30<3:03:06,  1.63it/s]
1|7983|Loss: 0.6890273094177246:  31%|███       | 7982/25880 [1:39:31<3:03:06,  1.63it/s]
1|7983|Loss: 0.6890273094177246:  31%|███       | 7983/25880 [1:39:31<3:19:10,  1.50it/s]
1|7984|Loss: 0.940324604511261:  31%|███       | 7983/25880 [1:39:32<3:19:10,  1.50it/s] 
1|7984|Loss: 0.940324604511261:  31%|███       | 7984/25880 [1:39:32<3:27:03,  1.44it/s]
1|7985|Loss: 0.9122371673583984:  31%|███       | 7984/25880 [1:39:32<3:27:03,  1.44it/s]
1|7985|Loss: 0.9122371673583984:  31%|███       | 7985/25880 [1:39:33<3:40:54,  1.35it/s]
1|7986|Loss: 0.8113349080085754:  31%|███       | 7985/25880 [1:39:33<3:40:54,  1.35it/s]
1|7986|Loss: 0.8113349080085754:  31%|███       | 7986/25880 [1:39:34<3:49:22,  1.30it/s]
1|7987|Loss: 0.8515336513519287:  31%|███       | 7986/25880 [1:39:34<3:49:22,  1.30it/s]
1|7987|Loss: 0.8515336513519287:  31%|███       | 7987/25880 [1:39:34<3:54:00,  1.27it/s]
1|7988|Loss: 0.8482291102409363:  31%|███       | 7987/25880 [1:39:35<3:54:00,  1.27it/s]
1|7988|Loss: 0.8482291102409363:  31%|███       | 7988/25880 [1:39:35<3:48:54,  1.30it/s]
1|7989|Loss: 0.8093456029891968:  31%|███       | 7988/25880 [1:39:36<3:48:54,  1.30it/s]
1|7989|Loss: 0.8093456029891968:  31%|███       | 7989/25880 [1:39:36<3:38:39,  1.36it/s]
1|7990|Loss: 0.7563596963882446:  31%|███       | 7989/25880 [1:39:36<3:38:39,  1.36it/s]
1|7990|Loss: 0.7563596963882446:  31%|███       | 7990/25880 [1:39:36<3:30:44,  1.41it/s]
1|7991|Loss: 0.8349327445030212:  31%|███       | 7990/25880 [1:39:37<3:30:44,  1.41it/s]
1|7991|Loss: 0.8349327445030212:  31%|███       | 7991/25880 [1:39:37<3:30:49,  1.41it/s]
1|7992|Loss: 0.8141117691993713:  31%|███       | 7991/25880 [1:39:38<3:30:49,  1.41it/s]
1|7992|Loss: 0.8141117691993713:  31%|███       | 7992/25880 [1:39:38<3:36:34,  1.38it/s]
1|7993|Loss: 0.8989229202270508:  31%|███       | 7992/25880 [1:39:38<3:36:34,  1.38it/s]
1|7993|Loss: 0.8989229202270508:  31%|███       | 7993/25880 [1:39:39<3:32:03,  1.41it/s]
1|7994|Loss: 0.8571162819862366:  31%|███       | 7993/25880 [1:39:39<3:32:03,  1.41it/s]
1|7994|Loss: 0.8571162819862366:  31%|███       | 7994/25880 [1:39:39<3:30:42,  1.41it/s]
1|7995|Loss: 0.8127937316894531:  31%|███       | 7994/25880 [1:39:40<3:30:42,  1.41it/s]
1|7995|Loss: 0.8127937316894531:  31%|███       | 7995/25880 [1:39:40<3:17:37,  1.51it/s]
1|7996|Loss: 0.976631760597229:  31%|███       | 7995/25880 [1:39:40<3:17:37,  1.51it/s] 
1|7996|Loss: 0.976631760597229:  31%|███       | 7996/25880 [1:39:41<3:20:40,  1.49it/s]
1|7997|Loss: 0.9447590708732605:  31%|███       | 7996/25880 [1:39:41<3:20:40,  1.49it/s]
1|7997|Loss: 0.9447590708732605:  31%|███       | 7997/25880 [1:39:41<3:06:58,  1.59it/s]
1|7998|Loss: 0.9435091614723206:  31%|███       | 7997/25880 [1:39:41<3:06:58,  1.59it/s]
1|7998|Loss: 0.9435091614723206:  31%|███       | 7998/25880 [1:39:42<3:16:00,  1.52it/s]
1|7999|Loss: 0.8845946192741394:  31%|███       | 7998/25880 [1:39:42<3:16:00,  1.52it/s]
1|7999|Loss: 0.8845946192741394:  31%|███       | 7999/25880 [1:39:43<3:28:06,  1.43it/s]
1|8000|Loss: 0.9025675654411316:  31%|███       | 7999/25880 [1:39:43<3:28:06,  1.43it/s]
1|8000|Loss: 0.9025675654411316:  31%|███       | 8000/25880 [1:39:43<3:25:56,  1.45it/s]
1|8001|Loss: 0.8378636240959167:  31%|███       | 8000/25880 [1:39:44<3:25:56,  1.45it/s]
1|8001|Loss: 0.8378636240959167:  31%|███       | 8001/25880 [1:39:44<3:34:58,  1.39it/s]
1|8002|Loss: 0.8236063122749329:  31%|███       | 8001/25880 [1:39:45<3:34:58,  1.39it/s]
1|8002|Loss: 0.8236063122749329:  31%|███       | 8002/25880 [1:39:45<3:46:59,  1.31it/s]
1|8003|Loss: 0.8182162642478943:  31%|███       | 8002/25880 [1:39:45<3:46:59,  1.31it/s]
1|8003|Loss: 0.8182162642478943:  31%|███       | 8003/25880 [1:39:46<3:47:04,  1.31it/s]
1|8004|Loss: 0.8451895713806152:  31%|███       | 8003/25880 [1:39:46<3:47:04,  1.31it/s]
1|8004|Loss: 0.8451895713806152:  31%|███       | 8004/25880 [1:39:46<3:44:09,  1.33it/s]
1|8005|Loss: 0.7534170150756836:  31%|███       | 8004/25880 [1:39:47<3:44:09,  1.33it/s]
1|8005|Loss: 0.7534170150756836:  31%|███       | 8005/25880 [1:39:47<3:47:22,  1.31it/s]
1|8006|Loss: 0.848520815372467:  31%|███       | 8005/25880 [1:39:48<3:47:22,  1.31it/s] 
1|8006|Loss: 0.848520815372467:  31%|███       | 8006/25880 [1:39:48<3:55:12,  1.27it/s]
1|8007|Loss: 0.7799302935600281:  31%|███       | 8006/25880 [1:39:49<3:55:12,  1.27it/s]
1|8007|Loss: 0.7799302935600281:  31%|███       | 8007/25880 [1:39:49<3:59:58,  1.24it/s]
1|8008|Loss: 0.9797860383987427:  31%|███       | 8007/25880 [1:39:49<3:59:58,  1.24it/s]
1|8008|Loss: 0.9797860383987427:  31%|███       | 8008/25880 [1:39:49<3:41:52,  1.34it/s]
1|8009|Loss: 0.7994862794876099:  31%|███       | 8008/25880 [1:39:50<3:41:52,  1.34it/s]
1|8009|Loss: 0.7994862794876099:  31%|███       | 8009/25880 [1:39:50<3:54:39,  1.27it/s]
1|8010|Loss: 0.7882734537124634:  31%|███       | 8009/25880 [1:39:51<3:54:39,  1.27it/s]
1|8010|Loss: 0.7882734537124634:  31%|███       | 8010/25880 [1:39:51<3:52:04,  1.28it/s]
1|8011|Loss: 0.765380322933197:  31%|███       | 8010/25880 [1:39:52<3:52:04,  1.28it/s] 
1|8011|Loss: 0.765380322933197:  31%|███       | 8011/25880 [1:39:52<3:57:39,  1.25it/s]
1|8012|Loss: 0.8734138011932373:  31%|███       | 8011/25880 [1:39:52<3:57:39,  1.25it/s]
1|8012|Loss: 0.8734138011932373:  31%|███       | 8012/25880 [1:39:53<3:43:53,  1.33it/s]
1|8013|Loss: 0.9148340225219727:  31%|███       | 8012/25880 [1:39:53<3:43:53,  1.33it/s]
1|8013|Loss: 0.9148340225219727:  31%|███       | 8013/25880 [1:39:53<3:39:09,  1.36it/s]
1|8014|Loss: 0.8503161072731018:  31%|███       | 8013/25880 [1:39:54<3:39:09,  1.36it/s]
1|8014|Loss: 0.8503161072731018:  31%|███       | 8014/25880 [1:39:54<3:28:31,  1.43it/s]
1|8015|Loss: 0.918153703212738:  31%|███       | 8014/25880 [1:39:54<3:28:31,  1.43it/s] 
1|8015|Loss: 0.918153703212738:  31%|███       | 8015/25880 [1:39:55<3:28:28,  1.43it/s]
1|8016|Loss: 0.9500728249549866:  31%|███       | 8015/25880 [1:39:55<3:28:28,  1.43it/s]
1|8016|Loss: 0.9500728249549866:  31%|███       | 8016/25880 [1:39:56<3:44:27,  1.33it/s]
1|8017|Loss: 0.8559823632240295:  31%|███       | 8016/25880 [1:39:56<3:44:27,  1.33it/s]
1|8017|Loss: 0.8559823632240295:  31%|███       | 8017/25880 [1:39:56<3:54:20,  1.27it/s]
1|8018|Loss: 0.7433789968490601:  31%|███       | 8017/25880 [1:39:57<3:54:20,  1.27it/s]
1|8018|Loss: 0.7433789968490601:  31%|███       | 8018/25880 [1:39:57<3:50:32,  1.29it/s]
1|8019|Loss: 0.939697265625:  31%|███       | 8018/25880 [1:39:58<3:50:32,  1.29it/s]    
1|8019|Loss: 0.939697265625:  31%|███       | 8019/25880 [1:39:58<3:44:09,  1.33it/s]
1|8020|Loss: 0.930072009563446:  31%|███       | 8019/25880 [1:39:58<3:44:09,  1.33it/s]
1|8020|Loss: 0.930072009563446:  31%|███       | 8020/25880 [1:39:59<3:48:20,  1.30it/s]
1|8021|Loss: 0.8715341091156006:  31%|███       | 8020/25880 [1:39:59<3:48:20,  1.30it/s]
1|8021|Loss: 0.8715341091156006:  31%|███       | 8021/25880 [1:39:59<3:47:40,  1.31it/s]
1|8022|Loss: 0.9165104627609253:  31%|███       | 8021/25880 [1:40:00<3:47:40,  1.31it/s]
1|8022|Loss: 0.9165104627609253:  31%|███       | 8022/25880 [1:40:00<3:28:59,  1.42it/s]
1|8023|Loss: 0.9080142974853516:  31%|███       | 8022/25880 [1:40:00<3:28:59,  1.42it/s]
1|8023|Loss: 0.9080142974853516:  31%|███       | 8023/25880 [1:40:01<3:20:30,  1.48it/s]
1|8024|Loss: 1.0133600234985352:  31%|███       | 8023/25880 [1:40:01<3:20:30,  1.48it/s]
1|8024|Loss: 1.0133600234985352:  31%|███       | 8024/25880 [1:40:01<3:17:28,  1.51it/s]
1|8025|Loss: 0.8627179861068726:  31%|███       | 8024/25880 [1:40:02<3:17:28,  1.51it/s]
1|8025|Loss: 0.8627179861068726:  31%|███       | 8025/25880 [1:40:02<3:15:17,  1.52it/s]
1|8026|Loss: 0.7772254943847656:  31%|███       | 8025/25880 [1:40:02<3:15:17,  1.52it/s]
1|8026|Loss: 0.7772254943847656:  31%|███       | 8026/25880 [1:40:03<4:13:35,  1.17it/s]
1|8027|Loss: 0.8430289030075073:  31%|███       | 8026/25880 [1:40:04<4:13:35,  1.17it/s]
1|8027|Loss: 0.8430289030075073:  31%|███       | 8027/25880 [1:40:04<4:20:34,  1.14it/s]
1|8028|Loss: 1.0071032047271729:  31%|███       | 8027/25880 [1:40:05<4:20:34,  1.14it/s]
1|8028|Loss: 1.0071032047271729:  31%|███       | 8028/25880 [1:40:05<4:16:02,  1.16it/s]
1|8029|Loss: 0.907302975654602:  31%|███       | 8028/25880 [1:40:05<4:16:02,  1.16it/s] 
1|8029|Loss: 0.907302975654602:  31%|███       | 8029/25880 [1:40:06<4:03:54,  1.22it/s]
1|8030|Loss: 0.9054669737815857:  31%|███       | 8029/25880 [1:40:06<4:03:54,  1.22it/s]
1|8030|Loss: 0.9054669737815857:  31%|███       | 8030/25880 [1:40:06<3:40:31,  1.35it/s]
1|8031|Loss: 0.8052484393119812:  31%|███       | 8030/25880 [1:40:07<3:40:31,  1.35it/s]
1|8031|Loss: 0.8052484393119812:  31%|███       | 8031/25880 [1:40:07<3:44:35,  1.32it/s]
1|8032|Loss: 0.9068764448165894:  31%|███       | 8031/25880 [1:40:07<3:44:35,  1.32it/s]
1|8032|Loss: 0.9068764448165894:  31%|███       | 8032/25880 [1:40:08<3:36:56,  1.37it/s]
1|8033|Loss: 0.8592986464500427:  31%|███       | 8032/25880 [1:40:08<3:36:56,  1.37it/s]
1|8033|Loss: 0.8592986464500427:  31%|███       | 8033/25880 [1:40:08<3:26:59,  1.44it/s]
1|8034|Loss: 0.8466866612434387:  31%|███       | 8033/25880 [1:40:09<3:26:59,  1.44it/s]
1|8034|Loss: 0.8466866612434387:  31%|███       | 8034/25880 [1:40:09<3:26:32,  1.44it/s]
1|8035|Loss: 1.0826343297958374:  31%|███       | 8034/25880 [1:40:09<3:26:32,  1.44it/s]
1|8035|Loss: 1.0826343297958374:  31%|███       | 8035/25880 [1:40:10<3:30:36,  1.41it/s]
1|8036|Loss: 0.8356356024742126:  31%|███       | 8035/25880 [1:40:10<3:30:36,  1.41it/s]
1|8036|Loss: 0.8356356024742126:  31%|███       | 8036/25880 [1:40:10<3:13:45,  1.53it/s]
1|8037|Loss: 0.7673162221908569:  31%|███       | 8036/25880 [1:40:11<3:13:45,  1.53it/s]
1|8037|Loss: 0.7673162221908569:  31%|███       | 8037/25880 [1:40:11<3:22:43,  1.47it/s]
1|8038|Loss: 0.884528398513794:  31%|███       | 8037/25880 [1:40:11<3:22:43,  1.47it/s] 
1|8038|Loss: 0.884528398513794:  31%|███       | 8038/25880 [1:40:12<3:20:50,  1.48it/s]
1|8039|Loss: 0.8357794880867004:  31%|███       | 8038/25880 [1:40:12<3:20:50,  1.48it/s]
1|8039|Loss: 0.8357794880867004:  31%|███       | 8039/25880 [1:40:12<3:17:36,  1.50it/s]
1|8040|Loss: 0.887958824634552:  31%|███       | 8039/25880 [1:40:13<3:17:36,  1.50it/s] 
1|8040|Loss: 0.887958824634552:  31%|███       | 8040/25880 [1:40:13<3:20:21,  1.48it/s]
1|8041|Loss: 0.8247391581535339:  31%|███       | 8040/25880 [1:40:13<3:20:21,  1.48it/s]
1|8041|Loss: 0.8247391581535339:  31%|███       | 8041/25880 [1:40:14<3:22:27,  1.47it/s]
1|8042|Loss: 0.7881692051887512:  31%|███       | 8041/25880 [1:40:14<3:22:27,  1.47it/s]
1|8042|Loss: 0.7881692051887512:  31%|███       | 8042/25880 [1:40:14<3:19:23,  1.49it/s]
1|8043|Loss: 0.8269147872924805:  31%|███       | 8042/25880 [1:40:15<3:19:23,  1.49it/s]
1|8043|Loss: 0.8269147872924805:  31%|███       | 8043/25880 [1:40:15<3:27:59,  1.43it/s]
1|8044|Loss: 0.8262961506843567:  31%|███       | 8043/25880 [1:40:15<3:27:59,  1.43it/s]
1|8044|Loss: 0.8262961506843567:  31%|███       | 8044/25880 [1:40:16<3:25:32,  1.45it/s]
1|8045|Loss: 0.8261154294013977:  31%|███       | 8044/25880 [1:40:16<3:25:32,  1.45it/s]
1|8045|Loss: 0.8261154294013977:  31%|███       | 8045/25880 [1:40:17<3:32:22,  1.40it/s]
1|8046|Loss: 0.9015416502952576:  31%|███       | 8045/25880 [1:40:17<3:32:22,  1.40it/s]
1|8046|Loss: 0.9015416502952576:  31%|███       | 8046/25880 [1:40:17<3:22:45,  1.47it/s]
1|8047|Loss: 0.7711762189865112:  31%|███       | 8046/25880 [1:40:18<3:22:45,  1.47it/s]
1|8047|Loss: 0.7711762189865112:  31%|███       | 8047/25880 [1:40:18<3:46:27,  1.31it/s]
1|8048|Loss: 0.8488654494285583:  31%|███       | 8047/25880 [1:40:19<3:46:27,  1.31it/s]
1|8048|Loss: 0.8488654494285583:  31%|███       | 8048/25880 [1:40:19<3:49:14,  1.30it/s]
1|8049|Loss: 0.9104196429252625:  31%|███       | 8048/25880 [1:40:19<3:49:14,  1.30it/s]
1|8049|Loss: 0.9104196429252625:  31%|███       | 8049/25880 [1:40:19<3:34:37,  1.38it/s]
1|8050|Loss: 0.7823095321655273:  31%|███       | 8049/25880 [1:40:20<3:34:37,  1.38it/s]
1|8050|Loss: 0.7823095321655273:  31%|███       | 8050/25880 [1:40:20<3:24:17,  1.45it/s]
1|8051|Loss: 0.8890357613563538:  31%|███       | 8050/25880 [1:40:20<3:24:17,  1.45it/s]
1|8051|Loss: 0.8890357613563538:  31%|███       | 8051/25880 [1:40:21<3:24:23,  1.45it/s]
1|8052|Loss: 0.7849562764167786:  31%|███       | 8051/25880 [1:40:21<3:24:23,  1.45it/s]
1|8052|Loss: 0.7849562764167786:  31%|███       | 8052/25880 [1:40:21<3:25:15,  1.45it/s]
1|8053|Loss: 0.8226317167282104:  31%|███       | 8052/25880 [1:40:22<3:25:15,  1.45it/s]
1|8053|Loss: 0.8226317167282104:  31%|███       | 8053/25880 [1:40:22<3:28:17,  1.43it/s]
1|8054|Loss: 0.9301581382751465:  31%|███       | 8053/25880 [1:40:23<3:28:17,  1.43it/s]
1|8054|Loss: 0.9301581382751465:  31%|███       | 8054/25880 [1:40:23<3:25:19,  1.45it/s]
1|8055|Loss: 0.8168562054634094:  31%|███       | 8054/25880 [1:40:23<3:25:19,  1.45it/s]
1|8055|Loss: 0.8168562054634094:  31%|███       | 8055/25880 [1:40:23<3:19:10,  1.49it/s]
1|8056|Loss: 0.9453939199447632:  31%|███       | 8055/25880 [1:40:24<3:19:10,  1.49it/s]
1|8056|Loss: 0.9453939199447632:  31%|███       | 8056/25880 [1:40:24<3:23:53,  1.46it/s]
1|8057|Loss: 0.914930522441864:  31%|███       | 8056/25880 [1:40:25<3:23:53,  1.46it/s] 
1|8057|Loss: 0.914930522441864:  31%|███       | 8057/25880 [1:40:25<3:44:40,  1.32it/s]
1|8058|Loss: 0.8050589561462402:  31%|███       | 8057/25880 [1:40:25<3:44:40,  1.32it/s]
1|8058|Loss: 0.8050589561462402:  31%|███       | 8058/25880 [1:40:26<3:29:29,  1.42it/s]
1|8059|Loss: 0.7818416953086853:  31%|███       | 8058/25880 [1:40:26<3:29:29,  1.42it/s]
1|8059|Loss: 0.7818416953086853:  31%|███       | 8059/25880 [1:40:26<3:24:36,  1.45it/s]
1|8060|Loss: 0.9154683351516724:  31%|███       | 8059/25880 [1:40:27<3:24:36,  1.45it/s]
1|8060|Loss: 0.9154683351516724:  31%|███       | 8060/25880 [1:40:27<3:32:31,  1.40it/s]
1|8061|Loss: 0.7791618704795837:  31%|███       | 8060/25880 [1:40:28<3:32:31,  1.40it/s]
1|8061|Loss: 0.7791618704795837:  31%|███       | 8061/25880 [1:40:28<3:35:13,  1.38it/s]
1|8062|Loss: 0.7174103260040283:  31%|███       | 8061/25880 [1:40:28<3:35:13,  1.38it/s]
1|8062|Loss: 0.7174103260040283:  31%|███       | 8062/25880 [1:40:29<3:29:45,  1.42it/s]
1|8063|Loss: 0.7883902788162231:  31%|███       | 8062/25880 [1:40:29<3:29:45,  1.42it/s]
1|8063|Loss: 0.7883902788162231:  31%|███       | 8063/25880 [1:40:29<3:13:01,  1.54it/s]
1|8064|Loss: 0.9955042600631714:  31%|███       | 8063/25880 [1:40:29<3:13:01,  1.54it/s]
1|8064|Loss: 0.9955042600631714:  31%|███       | 8064/25880 [1:40:30<3:15:14,  1.52it/s]
1|8065|Loss: 0.7713617086410522:  31%|███       | 8064/25880 [1:40:30<3:15:14,  1.52it/s]
1|8065|Loss: 0.7713617086410522:  31%|███       | 8065/25880 [1:40:30<3:21:59,  1.47it/s]
1|8066|Loss: 0.880333423614502:  31%|███       | 8065/25880 [1:40:31<3:21:59,  1.47it/s] 
1|8066|Loss: 0.880333423614502:  31%|███       | 8066/25880 [1:40:31<3:31:45,  1.40it/s]
1|8067|Loss: 0.8966448307037354:  31%|███       | 8066/25880 [1:40:32<3:31:45,  1.40it/s]
1|8067|Loss: 0.8966448307037354:  31%|███       | 8067/25880 [1:40:32<3:43:15,  1.33it/s]
1|8068|Loss: 0.6478541493415833:  31%|███       | 8067/25880 [1:40:33<3:43:15,  1.33it/s]
1|8068|Loss: 0.6478541493415833:  31%|███       | 8068/25880 [1:40:33<4:01:10,  1.23it/s]
1|8069|Loss: 0.8220574855804443:  31%|███       | 8068/25880 [1:40:33<4:01:10,  1.23it/s]
1|8069|Loss: 0.8220574855804443:  31%|███       | 8069/25880 [1:40:34<3:49:52,  1.29it/s]
1|8070|Loss: 0.7813138365745544:  31%|███       | 8069/25880 [1:40:34<3:49:52,  1.29it/s]
1|8070|Loss: 0.7813138365745544:  31%|███       | 8070/25880 [1:40:34<3:33:23,  1.39it/s]
1|8071|Loss: 0.9131110310554504:  31%|███       | 8070/25880 [1:40:35<3:33:23,  1.39it/s]
1|8071|Loss: 0.9131110310554504:  31%|███       | 8071/25880 [1:40:35<3:32:11,  1.40it/s]
1|8072|Loss: 0.86717689037323:  31%|███       | 8071/25880 [1:40:35<3:32:11,  1.40it/s]  
1|8072|Loss: 0.86717689037323:  31%|███       | 8072/25880 [1:40:36<3:23:22,  1.46it/s]
1|8073|Loss: 0.8045796751976013:  31%|███       | 8072/25880 [1:40:36<3:23:22,  1.46it/s]
1|8073|Loss: 0.8045796751976013:  31%|███       | 8073/25880 [1:40:36<3:14:34,  1.53it/s]
1|8074|Loss: 0.8198114037513733:  31%|███       | 8073/25880 [1:40:37<3:14:34,  1.53it/s]
1|8074|Loss: 0.8198114037513733:  31%|███       | 8074/25880 [1:40:37<3:08:28,  1.57it/s]
1|8075|Loss: 0.9303557872772217:  31%|███       | 8074/25880 [1:40:37<3:08:28,  1.57it/s]
1|8075|Loss: 0.9303557872772217:  31%|███       | 8075/25880 [1:40:38<3:14:08,  1.53it/s]
1|8076|Loss: 0.9622174501419067:  31%|███       | 8075/25880 [1:40:38<3:14:08,  1.53it/s]
1|8076|Loss: 0.9622174501419067:  31%|███       | 8076/25880 [1:40:38<3:24:53,  1.45it/s]
1|8077|Loss: 0.9088888168334961:  31%|███       | 8076/25880 [1:40:39<3:24:53,  1.45it/s]
1|8077|Loss: 0.9088888168334961:  31%|███       | 8077/25880 [1:40:39<3:20:23,  1.48it/s]
1|8078|Loss: 0.8634663820266724:  31%|███       | 8077/25880 [1:40:39<3:20:23,  1.48it/s]
1|8078|Loss: 0.8634663820266724:  31%|███       | 8078/25880 [1:40:40<3:31:14,  1.40it/s]
1|8079|Loss: 0.8992598056793213:  31%|███       | 8078/25880 [1:40:40<3:31:14,  1.40it/s]
1|8079|Loss: 0.8992598056793213:  31%|███       | 8079/25880 [1:40:40<3:23:02,  1.46it/s]
1|8080|Loss: 0.9723420143127441:  31%|███       | 8079/25880 [1:40:41<3:23:02,  1.46it/s]
1|8080|Loss: 0.9723420143127441:  31%|███       | 8080/25880 [1:40:41<3:22:02,  1.47it/s]
1|8081|Loss: 0.8403580784797668:  31%|███       | 8080/25880 [1:40:41<3:22:02,  1.47it/s]
1|8081|Loss: 0.8403580784797668:  31%|███       | 8081/25880 [1:40:42<3:33:26,  1.39it/s]
1|8082|Loss: 0.9914864897727966:  31%|███       | 8081/25880 [1:40:42<3:33:26,  1.39it/s]
1|8082|Loss: 0.9914864897727966:  31%|███       | 8082/25880 [1:40:43<3:37:29,  1.36it/s]
1|8083|Loss: 0.8521349430084229:  31%|███       | 8082/25880 [1:40:43<3:37:29,  1.36it/s]
1|8083|Loss: 0.8521349430084229:  31%|███       | 8083/25880 [1:40:43<3:43:08,  1.33it/s]
1|8084|Loss: 0.9545958638191223:  31%|███       | 8083/25880 [1:40:44<3:43:08,  1.33it/s]
1|8084|Loss: 0.9545958638191223:  31%|███       | 8084/25880 [1:40:44<3:35:34,  1.38it/s]
1|8085|Loss: 0.8261534571647644:  31%|███       | 8084/25880 [1:40:44<3:35:34,  1.38it/s]
1|8085|Loss: 0.8261534571647644:  31%|███       | 8085/25880 [1:40:45<3:26:09,  1.44it/s]
1|8086|Loss: 0.8873307704925537:  31%|███       | 8085/25880 [1:40:45<3:26:09,  1.44it/s]
1|8086|Loss: 0.8873307704925537:  31%|███       | 8086/25880 [1:40:45<3:21:14,  1.47it/s]
1|8087|Loss: 0.9510975480079651:  31%|███       | 8086/25880 [1:40:46<3:21:14,  1.47it/s]
1|8087|Loss: 0.9510975480079651:  31%|███       | 8087/25880 [1:40:46<3:31:09,  1.40it/s]
1|8088|Loss: 0.8014304637908936:  31%|███       | 8087/25880 [1:40:47<3:31:09,  1.40it/s]
1|8088|Loss: 0.8014304637908936:  31%|███▏      | 8088/25880 [1:40:47<3:38:20,  1.36it/s]
1|8089|Loss: 0.9021456837654114:  31%|███▏      | 8088/25880 [1:40:47<3:38:20,  1.36it/s]
1|8089|Loss: 0.9021456837654114:  31%|███▏      | 8089/25880 [1:40:48<3:45:25,  1.32it/s]
1|8090|Loss: 0.8291765451431274:  31%|███▏      | 8089/25880 [1:40:48<3:45:25,  1.32it/s]
1|8090|Loss: 0.8291765451431274:  31%|███▏      | 8090/25880 [1:40:49<4:02:10,  1.22it/s]
1|8091|Loss: 0.7315214276313782:  31%|███▏      | 8090/25880 [1:40:49<4:02:10,  1.22it/s]
1|8091|Loss: 0.7315214276313782:  31%|███▏      | 8091/25880 [1:40:49<4:01:01,  1.23it/s]
1|8092|Loss: 1.0341883897781372:  31%|███▏      | 8091/25880 [1:40:50<4:01:01,  1.23it/s]
1|8092|Loss: 1.0341883897781372:  31%|███▏      | 8092/25880 [1:40:50<4:01:53,  1.23it/s]
1|8093|Loss: 0.853234052658081:  31%|███▏      | 8092/25880 [1:40:51<4:01:53,  1.23it/s] 
1|8093|Loss: 0.853234052658081:  31%|███▏      | 8093/25880 [1:40:51<4:05:45,  1.21it/s]
1|8094|Loss: 0.8790732622146606:  31%|███▏      | 8093/25880 [1:40:52<4:05:45,  1.21it/s]
1|8094|Loss: 0.8790732622146606:  31%|███▏      | 8094/25880 [1:40:52<3:53:43,  1.27it/s]
1|8095|Loss: 0.8472652435302734:  31%|███▏      | 8094/25880 [1:40:52<3:53:43,  1.27it/s]
1|8095|Loss: 0.8472652435302734:  31%|███▏      | 8095/25880 [1:40:52<3:32:29,  1.39it/s]
1|8096|Loss: 0.8700461387634277:  31%|███▏      | 8095/25880 [1:40:53<3:32:29,  1.39it/s]
1|8096|Loss: 0.8700461387634277:  31%|███▏      | 8096/25880 [1:40:53<3:31:08,  1.40it/s]
1|8097|Loss: 0.7486717104911804:  31%|███▏      | 8096/25880 [1:40:54<3:31:08,  1.40it/s]
1|8097|Loss: 0.7486717104911804:  31%|███▏      | 8097/25880 [1:40:54<3:31:39,  1.40it/s]
1|8098|Loss: 0.9084405303001404:  31%|███▏      | 8097/25880 [1:40:54<3:31:39,  1.40it/s]
1|8098|Loss: 0.9084405303001404:  31%|███▏      | 8098/25880 [1:40:55<3:30:41,  1.41it/s]
1|8099|Loss: 0.8557818531990051:  31%|███▏      | 8098/25880 [1:40:55<3:30:41,  1.41it/s]
1|8099|Loss: 0.8557818531990051:  31%|███▏      | 8099/25880 [1:40:55<3:32:05,  1.40it/s]
1|8100|Loss: 0.7997607588768005:  31%|███▏      | 8099/25880 [1:40:56<3:32:05,  1.40it/s]
1|8100|Loss: 0.7997607588768005:  31%|███▏      | 8100/25880 [1:40:56<3:50:41,  1.28it/s]
1|8101|Loss: 0.9663331508636475:  31%|███▏      | 8100/25880 [1:40:57<3:50:41,  1.28it/s]
1|8101|Loss: 0.9663331508636475:  31%|███▏      | 8101/25880 [1:40:57<4:02:00,  1.22it/s]
1|8102|Loss: 0.7650696635246277:  31%|███▏      | 8101/25880 [1:40:58<4:02:00,  1.22it/s]
1|8102|Loss: 0.7650696635246277:  31%|███▏      | 8102/25880 [1:40:58<3:57:50,  1.25it/s]
1|8103|Loss: 0.9221059083938599:  31%|███▏      | 8102/25880 [1:40:58<3:57:50,  1.25it/s]
1|8103|Loss: 0.9221059083938599:  31%|███▏      | 8103/25880 [1:40:59<3:59:57,  1.23it/s]
1|8104|Loss: 0.8130326271057129:  31%|███▏      | 8103/25880 [1:40:59<3:59:57,  1.23it/s]
1|8104|Loss: 0.8130326271057129:  31%|███▏      | 8104/25880 [1:40:59<3:53:14,  1.27it/s]
1|8105|Loss: 0.7236960530281067:  31%|███▏      | 8104/25880 [1:41:00<3:53:14,  1.27it/s]
1|8105|Loss: 0.7236960530281067:  31%|███▏      | 8105/25880 [1:41:00<3:47:16,  1.30it/s]
1|8106|Loss: 0.7737830281257629:  31%|███▏      | 8105/25880 [1:41:01<3:47:16,  1.30it/s]
1|8106|Loss: 0.7737830281257629:  31%|███▏      | 8106/25880 [1:41:01<3:37:29,  1.36it/s]
1|8107|Loss: 0.7868168354034424:  31%|███▏      | 8106/25880 [1:41:01<3:37:29,  1.36it/s]
1|8107|Loss: 0.7868168354034424:  31%|███▏      | 8107/25880 [1:41:02<3:39:28,  1.35it/s]
1|8108|Loss: 0.8833682537078857:  31%|███▏      | 8107/25880 [1:41:02<3:39:28,  1.35it/s]
1|8108|Loss: 0.8833682537078857:  31%|███▏      | 8108/25880 [1:41:02<3:50:07,  1.29it/s]
1|8109|Loss: 0.8677303791046143:  31%|███▏      | 8108/25880 [1:41:03<3:50:07,  1.29it/s]
1|8109|Loss: 0.8677303791046143:  31%|███▏      | 8109/25880 [1:41:03<3:29:57,  1.41it/s]
1|8110|Loss: 0.8444335460662842:  31%|███▏      | 8109/25880 [1:41:03<3:29:57,  1.41it/s]
1|8110|Loss: 0.8444335460662842:  31%|███▏      | 8110/25880 [1:41:04<3:19:52,  1.48it/s]
1|8111|Loss: 0.6884265542030334:  31%|███▏      | 8110/25880 [1:41:04<3:19:52,  1.48it/s]
1|8111|Loss: 0.6884265542030334:  31%|███▏      | 8111/25880 [1:41:04<3:23:12,  1.46it/s]
1|8112|Loss: 0.9718752503395081:  31%|███▏      | 8111/25880 [1:41:05<3:23:12,  1.46it/s]
1|8112|Loss: 0.9718752503395081:  31%|███▏      | 8112/25880 [1:41:05<3:25:28,  1.44it/s]
1|8113|Loss: 0.8602845668792725:  31%|███▏      | 8112/25880 [1:41:05<3:25:28,  1.44it/s]
1|8113|Loss: 0.8602845668792725:  31%|███▏      | 8113/25880 [1:41:06<3:26:16,  1.44it/s]
1|8114|Loss: 0.931606113910675:  31%|███▏      | 8113/25880 [1:41:06<3:26:16,  1.44it/s] 
1|8114|Loss: 0.931606113910675:  31%|███▏      | 8114/25880 [1:41:06<3:14:46,  1.52it/s]
1|8115|Loss: 0.8758379817008972:  31%|███▏      | 8114/25880 [1:41:07<3:14:46,  1.52it/s]
1|8115|Loss: 0.8758379817008972:  31%|███▏      | 8115/25880 [1:41:07<3:24:44,  1.45it/s]
1|8116|Loss: 0.9164844155311584:  31%|███▏      | 8115/25880 [1:41:07<3:24:44,  1.45it/s]
1|8116|Loss: 0.9164844155311584:  31%|███▏      | 8116/25880 [1:41:08<3:29:36,  1.41it/s]
1|8117|Loss: 0.920647144317627:  31%|███▏      | 8116/25880 [1:41:08<3:29:36,  1.41it/s] 
1|8117|Loss: 0.920647144317627:  31%|███▏      | 8117/25880 [1:41:09<3:38:56,  1.35it/s]
1|8118|Loss: 0.7996870279312134:  31%|███▏      | 8117/25880 [1:41:09<3:38:56,  1.35it/s]
1|8118|Loss: 0.7996870279312134:  31%|███▏      | 8118/25880 [1:41:09<3:32:00,  1.40it/s]
1|8119|Loss: 0.8116272687911987:  31%|███▏      | 8118/25880 [1:41:10<3:32:00,  1.40it/s]
1|8119|Loss: 0.8116272687911987:  31%|███▏      | 8119/25880 [1:41:10<3:31:12,  1.40it/s]
1|8120|Loss: 0.9043880701065063:  31%|███▏      | 8119/25880 [1:41:10<3:31:12,  1.40it/s]
1|8120|Loss: 0.9043880701065063:  31%|███▏      | 8120/25880 [1:41:11<3:24:20,  1.45it/s]
1|8121|Loss: 0.9986627697944641:  31%|███▏      | 8120/25880 [1:41:11<3:24:20,  1.45it/s]
1|8121|Loss: 0.9986627697944641:  31%|███▏      | 8121/25880 [1:41:11<3:25:47,  1.44it/s]
1|8122|Loss: 0.8664573431015015:  31%|███▏      | 8121/25880 [1:41:12<3:25:47,  1.44it/s]
1|8122|Loss: 0.8664573431015015:  31%|███▏      | 8122/25880 [1:41:12<3:09:13,  1.56it/s]
1|8123|Loss: 0.7823286652565002:  31%|███▏      | 8122/25880 [1:41:12<3:09:13,  1.56it/s]
1|8123|Loss: 0.7823286652565002:  31%|███▏      | 8123/25880 [1:41:12<2:52:23,  1.72it/s]
1|8124|Loss: 0.8607236742973328:  31%|███▏      | 8123/25880 [1:41:13<2:52:23,  1.72it/s]
1|8124|Loss: 0.8607236742973328:  31%|███▏      | 8124/25880 [1:41:13<2:49:59,  1.74it/s]
1|8125|Loss: 0.8345714211463928:  31%|███▏      | 8124/25880 [1:41:13<2:49:59,  1.74it/s]
1|8125|Loss: 0.8345714211463928:  31%|███▏      | 8125/25880 [1:41:13<2:45:22,  1.79it/s]
1|8126|Loss: 0.7048554420471191:  31%|███▏      | 8125/25880 [1:41:14<2:45:22,  1.79it/s]
1|8126|Loss: 0.7048554420471191:  31%|███▏      | 8126/25880 [1:41:14<3:03:26,  1.61it/s]
1|8127|Loss: 0.8526138663291931:  31%|███▏      | 8126/25880 [1:41:15<3:03:26,  1.61it/s]
1|8127|Loss: 0.8526138663291931:  31%|███▏      | 8127/25880 [1:41:15<3:24:04,  1.45it/s]
1|8128|Loss: 0.76320880651474:  31%|███▏      | 8127/25880 [1:41:15<3:24:04,  1.45it/s]  
1|8128|Loss: 0.76320880651474:  31%|███▏      | 8128/25880 [1:41:15<3:11:03,  1.55it/s]
1|8129|Loss: 0.965843141078949:  31%|███▏      | 8128/25880 [1:41:16<3:11:03,  1.55it/s]
1|8129|Loss: 0.965843141078949:  31%|███▏      | 8129/25880 [1:41:16<3:14:16,  1.52it/s]
1|8130|Loss: 0.7343072891235352:  31%|███▏      | 8129/25880 [1:41:17<3:14:16,  1.52it/s]
1|8130|Loss: 0.7343072891235352:  31%|███▏      | 8130/25880 [1:41:17<3:30:17,  1.41it/s]
1|8131|Loss: 0.8562924265861511:  31%|███▏      | 8130/25880 [1:41:17<3:30:17,  1.41it/s]
1|8131|Loss: 0.8562924265861511:  31%|███▏      | 8131/25880 [1:41:18<3:34:54,  1.38it/s]
1|8132|Loss: 0.8261380195617676:  31%|███▏      | 8131/25880 [1:41:18<3:34:54,  1.38it/s]
1|8132|Loss: 0.8261380195617676:  31%|███▏      | 8132/25880 [1:41:18<3:26:53,  1.43it/s]
1|8133|Loss: 0.6608610153198242:  31%|███▏      | 8132/25880 [1:41:19<3:26:53,  1.43it/s]
1|8133|Loss: 0.6608610153198242:  31%|███▏      | 8133/25880 [1:41:19<3:35:57,  1.37it/s]
1|8134|Loss: 0.7416295409202576:  31%|███▏      | 8133/25880 [1:41:20<3:35:57,  1.37it/s]
1|8134|Loss: 0.7416295409202576:  31%|███▏      | 8134/25880 [1:41:20<3:39:19,  1.35it/s]
1|8135|Loss: 0.7913324236869812:  31%|███▏      | 8134/25880 [1:41:20<3:39:19,  1.35it/s]
1|8135|Loss: 0.7913324236869812:  31%|███▏      | 8135/25880 [1:41:21<3:32:19,  1.39it/s]
1|8136|Loss: 0.7874636054039001:  31%|███▏      | 8135/25880 [1:41:21<3:32:19,  1.39it/s]
1|8136|Loss: 0.7874636054039001:  31%|███▏      | 8136/25880 [1:41:21<3:23:51,  1.45it/s]
1|8137|Loss: 0.7930204272270203:  31%|███▏      | 8136/25880 [1:41:22<3:23:51,  1.45it/s]
1|8137|Loss: 0.7930204272270203:  31%|███▏      | 8137/25880 [1:41:22<3:19:12,  1.48it/s]
1|8138|Loss: 0.9197635650634766:  31%|███▏      | 8137/25880 [1:41:22<3:19:12,  1.48it/s]
1|8138|Loss: 0.9197635650634766:  31%|███▏      | 8138/25880 [1:41:22<3:12:11,  1.54it/s]
1|8139|Loss: 0.8055806159973145:  31%|███▏      | 8138/25880 [1:41:23<3:12:11,  1.54it/s]
1|8139|Loss: 0.8055806159973145:  31%|███▏      | 8139/25880 [1:41:23<3:09:27,  1.56it/s]
1|8140|Loss: 0.7040939331054688:  31%|███▏      | 8139/25880 [1:41:24<3:09:27,  1.56it/s]
1|8140|Loss: 0.7040939331054688:  31%|███▏      | 8140/25880 [1:41:24<3:32:16,  1.39it/s]
1|8141|Loss: 0.8046844005584717:  31%|███▏      | 8140/25880 [1:41:24<3:32:16,  1.39it/s]
1|8141|Loss: 0.8046844005584717:  31%|███▏      | 8141/25880 [1:41:25<3:41:28,  1.33it/s]
1|8142|Loss: 0.9819360375404358:  31%|███▏      | 8141/25880 [1:41:25<3:41:28,  1.33it/s]
1|8142|Loss: 0.9819360375404358:  31%|███▏      | 8142/25880 [1:41:26<3:40:59,  1.34it/s]
1|8143|Loss: 0.8938159346580505:  31%|███▏      | 8142/25880 [1:41:26<3:40:59,  1.34it/s]
1|8143|Loss: 0.8938159346580505:  31%|███▏      | 8143/25880 [1:41:26<3:30:58,  1.40it/s]
1|8144|Loss: 0.7956367135047913:  31%|███▏      | 8143/25880 [1:41:27<3:30:58,  1.40it/s]
1|8144|Loss: 0.7956367135047913:  31%|███▏      | 8144/25880 [1:41:27<3:30:54,  1.40it/s]
1|8145|Loss: 0.7343858480453491:  31%|███▏      | 8144/25880 [1:41:27<3:30:54,  1.40it/s]
1|8145|Loss: 0.7343858480453491:  31%|███▏      | 8145/25880 [1:41:28<3:49:05,  1.29it/s]
1|8146|Loss: 0.8358743190765381:  31%|███▏      | 8145/25880 [1:41:28<3:49:05,  1.29it/s]
1|8146|Loss: 0.8358743190765381:  31%|███▏      | 8146/25880 [1:41:29<3:41:22,  1.34it/s]
1|8147|Loss: 0.8790554404258728:  31%|███▏      | 8146/25880 [1:41:29<3:41:22,  1.34it/s]
1|8147|Loss: 0.8790554404258728:  31%|███▏      | 8147/25880 [1:41:29<3:39:06,  1.35it/s]
1|8148|Loss: 0.8504610657691956:  31%|███▏      | 8147/25880 [1:41:30<3:39:06,  1.35it/s]
1|8148|Loss: 0.8504610657691956:  31%|███▏      | 8148/25880 [1:41:30<3:47:28,  1.30it/s]
1|8149|Loss: 0.8298057913780212:  31%|███▏      | 8148/25880 [1:41:31<3:47:28,  1.30it/s]
1|8149|Loss: 0.8298057913780212:  31%|███▏      | 8149/25880 [1:41:31<3:45:32,  1.31it/s]
1|8150|Loss: 0.8021554350852966:  31%|███▏      | 8149/25880 [1:41:31<3:45:32,  1.31it/s]
1|8150|Loss: 0.8021554350852966:  31%|███▏      | 8150/25880 [1:41:32<3:42:36,  1.33it/s]
1|8151|Loss: 1.027544379234314:  31%|███▏      | 8150/25880 [1:41:32<3:42:36,  1.33it/s] 
1|8151|Loss: 1.027544379234314:  31%|███▏      | 8151/25880 [1:41:32<3:52:10,  1.27it/s]
1|8152|Loss: 0.7483007907867432:  31%|███▏      | 8151/25880 [1:41:33<3:52:10,  1.27it/s]
1|8152|Loss: 0.7483007907867432:  31%|███▏      | 8152/25880 [1:41:33<3:33:18,  1.39it/s]
1|8153|Loss: 1.0315316915512085:  31%|███▏      | 8152/25880 [1:41:33<3:33:18,  1.39it/s]
1|8153|Loss: 1.0315316915512085:  32%|███▏      | 8153/25880 [1:41:34<3:22:39,  1.46it/s]
1|8154|Loss: 0.8403156399726868:  32%|███▏      | 8153/25880 [1:41:34<3:22:39,  1.46it/s]
1|8154|Loss: 0.8403156399726868:  32%|███▏      | 8154/25880 [1:41:34<3:24:45,  1.44it/s]
1|8155|Loss: 0.9838275909423828:  32%|███▏      | 8154/25880 [1:41:35<3:24:45,  1.44it/s]
1|8155|Loss: 0.9838275909423828:  32%|███▏      | 8155/25880 [1:41:35<3:29:00,  1.41it/s]
1|8156|Loss: 0.8997947573661804:  32%|███▏      | 8155/25880 [1:41:35<3:29:00,  1.41it/s]
1|8156|Loss: 0.8997947573661804:  32%|███▏      | 8156/25880 [1:41:36<3:07:11,  1.58it/s]
1|8157|Loss: 0.8506157398223877:  32%|███▏      | 8156/25880 [1:41:36<3:07:11,  1.58it/s]
1|8157|Loss: 0.8506157398223877:  32%|███▏      | 8157/25880 [1:41:36<3:10:53,  1.55it/s]
1|8158|Loss: 1.0035874843597412:  32%|███▏      | 8157/25880 [1:41:37<3:10:53,  1.55it/s]
1|8158|Loss: 1.0035874843597412:  32%|███▏      | 8158/25880 [1:41:37<3:19:34,  1.48it/s]
1|8159|Loss: 0.8499264121055603:  32%|███▏      | 8158/25880 [1:41:37<3:19:34,  1.48it/s]
1|8159|Loss: 0.8499264121055603:  32%|███▏      | 8159/25880 [1:41:38<3:34:09,  1.38it/s]
1|8160|Loss: 0.9078489542007446:  32%|███▏      | 8159/25880 [1:41:38<3:34:09,  1.38it/s]
1|8160|Loss: 0.9078489542007446:  32%|███▏      | 8160/25880 [1:41:39<3:38:02,  1.35it/s]
1|8161|Loss: 0.8294286131858826:  32%|███▏      | 8160/25880 [1:41:39<3:38:02,  1.35it/s]
1|8161|Loss: 0.8294286131858826:  32%|███▏      | 8161/25880 [1:41:39<3:37:40,  1.36it/s]
1|8162|Loss: 0.8321237564086914:  32%|███▏      | 8161/25880 [1:41:40<3:37:40,  1.36it/s]
1|8162|Loss: 0.8321237564086914:  32%|███▏      | 8162/25880 [1:41:40<3:54:04,  1.26it/s]
1|8163|Loss: 0.9899094104766846:  32%|███▏      | 8162/25880 [1:41:41<3:54:04,  1.26it/s]
1|8163|Loss: 0.9899094104766846:  32%|███▏      | 8163/25880 [1:41:41<3:57:05,  1.25it/s]
1|8164|Loss: 0.9620774984359741:  32%|███▏      | 8163/25880 [1:41:41<3:57:05,  1.25it/s]
1|8164|Loss: 0.9620774984359741:  32%|███▏      | 8164/25880 [1:41:42<3:52:43,  1.27it/s]
1|8165|Loss: 0.8815221786499023:  32%|███▏      | 8164/25880 [1:41:42<3:52:43,  1.27it/s]
1|8165|Loss: 0.8815221786499023:  32%|███▏      | 8165/25880 [1:41:42<3:39:45,  1.34it/s]
1|8166|Loss: 0.8713779449462891:  32%|███▏      | 8165/25880 [1:41:43<3:39:45,  1.34it/s]
1|8166|Loss: 0.8713779449462891:  32%|███▏      | 8166/25880 [1:41:43<3:36:25,  1.36it/s]
1|8167|Loss: 0.729377031326294:  32%|███▏      | 8166/25880 [1:41:44<3:36:25,  1.36it/s] 
1|8167|Loss: 0.729377031326294:  32%|███▏      | 8167/25880 [1:41:44<3:36:47,  1.36it/s]
1|8168|Loss: 0.8241289258003235:  32%|███▏      | 8167/25880 [1:41:44<3:36:47,  1.36it/s]
1|8168|Loss: 0.8241289258003235:  32%|███▏      | 8168/25880 [1:41:45<3:46:33,  1.30it/s]
1|8169|Loss: 0.8499000668525696:  32%|███▏      | 8168/25880 [1:41:45<3:46:33,  1.30it/s]
1|8169|Loss: 0.8499000668525696:  32%|███▏      | 8169/25880 [1:41:45<3:44:08,  1.32it/s]
1|8170|Loss: 0.8262786269187927:  32%|███▏      | 8169/25880 [1:41:46<3:44:08,  1.32it/s]
1|8170|Loss: 0.8262786269187927:  32%|███▏      | 8170/25880 [1:41:46<3:41:57,  1.33it/s]
1|8171|Loss: 0.6515628099441528:  32%|███▏      | 8170/25880 [1:41:47<3:41:57,  1.33it/s]
1|8171|Loss: 0.6515628099441528:  32%|███▏      | 8171/25880 [1:41:47<3:41:17,  1.33it/s]
1|8172|Loss: 0.8269425630569458:  32%|███▏      | 8171/25880 [1:41:47<3:41:17,  1.33it/s]
1|8172|Loss: 0.8269425630569458:  32%|███▏      | 8172/25880 [1:41:48<3:47:05,  1.30it/s]
1|8173|Loss: 0.7500713467597961:  32%|███▏      | 8172/25880 [1:41:48<3:47:05,  1.30it/s]
1|8173|Loss: 0.7500713467597961:  32%|███▏      | 8173/25880 [1:41:49<3:52:06,  1.27it/s]
1|8174|Loss: 0.7753669023513794:  32%|███▏      | 8173/25880 [1:41:49<3:52:06,  1.27it/s]
1|8174|Loss: 0.7753669023513794:  32%|███▏      | 8174/25880 [1:41:49<3:52:28,  1.27it/s]
1|8175|Loss: 1.0383728742599487:  32%|███▏      | 8174/25880 [1:41:50<3:52:28,  1.27it/s]
1|8175|Loss: 1.0383728742599487:  32%|███▏      | 8175/25880 [1:41:50<3:42:07,  1.33it/s]
1|8176|Loss: 0.8485084176063538:  32%|███▏      | 8175/25880 [1:41:50<3:42:07,  1.33it/s]
1|8176|Loss: 0.8485084176063538:  32%|███▏      | 8176/25880 [1:41:51<3:30:40,  1.40it/s]
1|8177|Loss: 0.950238049030304:  32%|███▏      | 8176/25880 [1:41:51<3:30:40,  1.40it/s] 
1|8177|Loss: 0.950238049030304:  32%|███▏      | 8177/25880 [1:41:51<3:21:58,  1.46it/s]
1|8178|Loss: 0.6083245277404785:  32%|███▏      | 8177/25880 [1:41:52<3:21:58,  1.46it/s]
1|8178|Loss: 0.6083245277404785:  32%|███▏      | 8178/25880 [1:41:52<3:41:10,  1.33it/s]
1|8179|Loss: 0.7377349734306335:  32%|███▏      | 8178/25880 [1:41:53<3:41:10,  1.33it/s]
1|8179|Loss: 0.7377349734306335:  32%|███▏      | 8179/25880 [1:41:53<3:37:05,  1.36it/s]
1|8180|Loss: 0.932631254196167:  32%|███▏      | 8179/25880 [1:41:53<3:37:05,  1.36it/s] 
1|8180|Loss: 0.932631254196167:  32%|███▏      | 8180/25880 [1:41:54<3:35:24,  1.37it/s]
1|8181|Loss: 0.8080083727836609:  32%|███▏      | 8180/25880 [1:41:54<3:35:24,  1.37it/s]
1|8181|Loss: 0.8080083727836609:  32%|███▏      | 8181/25880 [1:41:54<3:36:20,  1.36it/s]
1|8182|Loss: 0.8416441082954407:  32%|███▏      | 8181/25880 [1:41:55<3:36:20,  1.36it/s]
1|8182|Loss: 0.8416441082954407:  32%|███▏      | 8182/25880 [1:41:55<3:44:39,  1.31it/s]
1|8183|Loss: 0.9006079435348511:  32%|███▏      | 8182/25880 [1:41:56<3:44:39,  1.31it/s]
1|8183|Loss: 0.9006079435348511:  32%|███▏      | 8183/25880 [1:41:56<3:33:32,  1.38it/s]
1|8184|Loss: 0.9294637441635132:  32%|███▏      | 8183/25880 [1:41:56<3:33:32,  1.38it/s]
1|8184|Loss: 0.9294637441635132:  32%|███▏      | 8184/25880 [1:41:57<3:32:16,  1.39it/s]
1|8185|Loss: 0.8565830588340759:  32%|███▏      | 8184/25880 [1:41:57<3:32:16,  1.39it/s]
1|8185|Loss: 0.8565830588340759:  32%|███▏      | 8185/25880 [1:41:57<3:46:36,  1.30it/s]
1|8186|Loss: 0.8208082914352417:  32%|███▏      | 8185/25880 [1:41:58<3:46:36,  1.30it/s]
1|8186|Loss: 0.8208082914352417:  32%|███▏      | 8186/25880 [1:41:58<3:38:04,  1.35it/s]
1|8187|Loss: 0.8352159857749939:  32%|███▏      | 8186/25880 [1:41:58<3:38:04,  1.35it/s]
1|8187|Loss: 0.8352159857749939:  32%|███▏      | 8187/25880 [1:41:59<3:28:34,  1.41it/s]
1|8188|Loss: 1.050479531288147:  32%|███▏      | 8187/25880 [1:41:59<3:28:34,  1.41it/s] 
1|8188|Loss: 1.050479531288147:  32%|███▏      | 8188/25880 [1:41:59<3:33:55,  1.38it/s]
1|8189|Loss: 0.7836434245109558:  32%|███▏      | 8188/25880 [1:42:00<3:33:55,  1.38it/s]
1|8189|Loss: 0.7836434245109558:  32%|███▏      | 8189/25880 [1:42:00<3:35:33,  1.37it/s]
1|8190|Loss: 0.8448551297187805:  32%|███▏      | 8189/25880 [1:42:01<3:35:33,  1.37it/s]
1|8190|Loss: 0.8448551297187805:  32%|███▏      | 8190/25880 [1:42:01<3:35:16,  1.37it/s]
1|8191|Loss: 0.9364346861839294:  32%|███▏      | 8190/25880 [1:42:01<3:35:16,  1.37it/s]
1|8191|Loss: 0.9364346861839294:  32%|███▏      | 8191/25880 [1:42:02<3:35:42,  1.37it/s]
1|8192|Loss: 0.9302524328231812:  32%|███▏      | 8191/25880 [1:42:02<3:35:42,  1.37it/s]
1|8192|Loss: 0.9302524328231812:  32%|███▏      | 8192/25880 [1:42:02<3:41:32,  1.33it/s]
1|8193|Loss: 0.8460983037948608:  32%|███▏      | 8192/25880 [1:42:03<3:41:32,  1.33it/s]
1|8193|Loss: 0.8460983037948608:  32%|███▏      | 8193/25880 [1:42:03<3:41:17,  1.33it/s]
1|8194|Loss: 0.75348961353302:  32%|███▏      | 8193/25880 [1:42:04<3:41:17,  1.33it/s]  
1|8194|Loss: 0.75348961353302:  32%|███▏      | 8194/25880 [1:42:04<3:40:01,  1.34it/s]
1|8195|Loss: 0.7999286651611328:  32%|███▏      | 8194/25880 [1:42:04<3:40:01,  1.34it/s]
1|8195|Loss: 0.7999286651611328:  32%|███▏      | 8195/25880 [1:42:05<3:33:00,  1.38it/s]
1|8196|Loss: 0.8063860535621643:  32%|███▏      | 8195/25880 [1:42:05<3:33:00,  1.38it/s]
1|8196|Loss: 0.8063860535621643:  32%|███▏      | 8196/25880 [1:42:05<3:12:22,  1.53it/s]
1|8197|Loss: 0.7368538975715637:  32%|███▏      | 8196/25880 [1:42:05<3:12:22,  1.53it/s]
1|8197|Loss: 0.7368538975715637:  32%|███▏      | 8197/25880 [1:42:06<3:04:23,  1.60it/s]
1|8198|Loss: 0.718112587928772:  32%|███▏      | 8197/25880 [1:42:06<3:04:23,  1.60it/s] 
1|8198|Loss: 0.718112587928772:  32%|███▏      | 8198/25880 [1:42:06<3:11:49,  1.54it/s]
1|8199|Loss: 0.7761315107345581:  32%|███▏      | 8198/25880 [1:42:07<3:11:49,  1.54it/s]
1|8199|Loss: 0.7761315107345581:  32%|███▏      | 8199/25880 [1:42:07<3:29:08,  1.41it/s]
1|8200|Loss: 0.758813202381134:  32%|███▏      | 8199/25880 [1:42:08<3:29:08,  1.41it/s] 
1|8200|Loss: 0.758813202381134:  32%|███▏      | 8200/25880 [1:42:08<3:38:45,  1.35it/s]
1|8201|Loss: 0.9347490072250366:  32%|███▏      | 8200/25880 [1:42:08<3:38:45,  1.35it/s]
1|8201|Loss: 0.9347490072250366:  32%|███▏      | 8201/25880 [1:42:09<3:23:17,  1.45it/s]
1|8202|Loss: 0.8947080969810486:  32%|███▏      | 8201/25880 [1:42:09<3:23:17,  1.45it/s]
1|8202|Loss: 0.8947080969810486:  32%|███▏      | 8202/25880 [1:42:09<3:26:44,  1.43it/s]
1|8203|Loss: 0.7843496203422546:  32%|███▏      | 8202/25880 [1:42:10<3:26:44,  1.43it/s]
1|8203|Loss: 0.7843496203422546:  32%|███▏      | 8203/25880 [1:42:10<3:31:57,  1.39it/s]
1|8204|Loss: 0.8578078150749207:  32%|███▏      | 8203/25880 [1:42:10<3:31:57,  1.39it/s]
1|8204|Loss: 0.8578078150749207:  32%|███▏      | 8204/25880 [1:42:11<3:27:59,  1.42it/s]
1|8205|Loss: 0.8408836126327515:  32%|███▏      | 8204/25880 [1:42:11<3:27:59,  1.42it/s]
1|8205|Loss: 0.8408836126327515:  32%|███▏      | 8205/25880 [1:42:12<3:29:22,  1.41it/s]
1|8206|Loss: 0.6737689971923828:  32%|███▏      | 8205/25880 [1:42:12<3:29:22,  1.41it/s]
1|8206|Loss: 0.6737689971923828:  32%|███▏      | 8206/25880 [1:42:12<3:38:16,  1.35it/s]
1|8207|Loss: 0.7761756777763367:  32%|███▏      | 8206/25880 [1:42:13<3:38:16,  1.35it/s]
1|8207|Loss: 0.7761756777763367:  32%|███▏      | 8207/25880 [1:42:13<3:44:36,  1.31it/s]
1|8208|Loss: 0.8773688673973083:  32%|███▏      | 8207/25880 [1:42:14<3:44:36,  1.31it/s]
1|8208|Loss: 0.8773688673973083:  32%|███▏      | 8208/25880 [1:42:14<3:36:51,  1.36it/s]
1|8209|Loss: 0.8727219104766846:  32%|███▏      | 8208/25880 [1:42:14<3:36:51,  1.36it/s]
1|8209|Loss: 0.8727219104766846:  32%|███▏      | 8209/25880 [1:42:14<3:24:22,  1.44it/s]
1|8210|Loss: 0.833869993686676:  32%|███▏      | 8209/25880 [1:42:15<3:24:22,  1.44it/s] 
1|8210|Loss: 0.833869993686676:  32%|███▏      | 8210/25880 [1:42:15<3:33:23,  1.38it/s]
1|8211|Loss: 0.7754920125007629:  32%|███▏      | 8210/25880 [1:42:16<3:33:23,  1.38it/s]
1|8211|Loss: 0.7754920125007629:  32%|███▏      | 8211/25880 [1:42:16<3:43:19,  1.32it/s]
1|8212|Loss: 0.8569894433021545:  32%|███▏      | 8211/25880 [1:42:16<3:43:19,  1.32it/s]
1|8212|Loss: 0.8569894433021545:  32%|███▏      | 8212/25880 [1:42:17<3:34:38,  1.37it/s]
1|8213|Loss: 0.9711492657661438:  32%|███▏      | 8212/25880 [1:42:17<3:34:38,  1.37it/s]
1|8213|Loss: 0.9711492657661438:  32%|███▏      | 8213/25880 [1:42:17<3:40:18,  1.34it/s]
1|8214|Loss: 0.743005633354187:  32%|███▏      | 8213/25880 [1:42:18<3:40:18,  1.34it/s] 
1|8214|Loss: 0.743005633354187:  32%|███▏      | 8214/25880 [1:42:18<3:42:17,  1.32it/s]
1|8215|Loss: 0.7131211757659912:  32%|███▏      | 8214/25880 [1:42:19<3:42:17,  1.32it/s]
1|8215|Loss: 0.7131211757659912:  32%|███▏      | 8215/25880 [1:42:19<3:28:28,  1.41it/s]
1|8216|Loss: 0.8323785662651062:  32%|███▏      | 8215/25880 [1:42:19<3:28:28,  1.41it/s]
1|8216|Loss: 0.8323785662651062:  32%|███▏      | 8216/25880 [1:42:20<3:26:50,  1.42it/s]
1|8217|Loss: 0.788455605506897:  32%|███▏      | 8216/25880 [1:42:20<3:26:50,  1.42it/s] 
1|8217|Loss: 0.788455605506897:  32%|███▏      | 8217/25880 [1:42:20<3:14:55,  1.51it/s]
1|8218|Loss: 0.9349856972694397:  32%|███▏      | 8217/25880 [1:42:20<3:14:55,  1.51it/s]
1|8218|Loss: 0.9349856972694397:  32%|███▏      | 8218/25880 [1:42:21<3:21:16,  1.46it/s]
1|8219|Loss: 0.8633609414100647:  32%|███▏      | 8218/25880 [1:42:21<3:21:16,  1.46it/s]
1|8219|Loss: 0.8633609414100647:  32%|███▏      | 8219/25880 [1:42:22<3:24:29,  1.44it/s]
1|8220|Loss: 0.8446828126907349:  32%|███▏      | 8219/25880 [1:42:22<3:24:29,  1.44it/s]
1|8220|Loss: 0.8446828126907349:  32%|███▏      | 8220/25880 [1:42:22<3:44:35,  1.31it/s]
1|8221|Loss: 1.1548172235488892:  32%|███▏      | 8220/25880 [1:42:23<3:44:35,  1.31it/s]
1|8221|Loss: 1.1548172235488892:  32%|███▏      | 8221/25880 [1:42:23<3:54:18,  1.26it/s]
1|8222|Loss: 0.8095018267631531:  32%|███▏      | 8221/25880 [1:42:24<3:54:18,  1.26it/s]
1|8222|Loss: 0.8095018267631531:  32%|███▏      | 8222/25880 [1:42:24<3:58:26,  1.23it/s]
1|8223|Loss: 0.8363963961601257:  32%|███▏      | 8222/25880 [1:42:25<3:58:26,  1.23it/s]
1|8223|Loss: 0.8363963961601257:  32%|███▏      | 8223/25880 [1:42:25<3:45:52,  1.30it/s]
1|8224|Loss: 0.8338617086410522:  32%|███▏      | 8223/25880 [1:42:25<3:45:52,  1.30it/s]
1|8224|Loss: 0.8338617086410522:  32%|███▏      | 8224/25880 [1:42:26<3:39:06,  1.34it/s]
1|8225|Loss: 0.9113350510597229:  32%|███▏      | 8224/25880 [1:42:26<3:39:06,  1.34it/s]
1|8225|Loss: 0.9113350510597229:  32%|███▏      | 8225/25880 [1:42:26<3:29:42,  1.40it/s]
1|8226|Loss: 0.856013834476471:  32%|███▏      | 8225/25880 [1:42:27<3:29:42,  1.40it/s] 
1|8226|Loss: 0.856013834476471:  32%|███▏      | 8226/25880 [1:42:27<3:29:20,  1.41it/s]
1|8227|Loss: 0.8159664869308472:  32%|███▏      | 8226/25880 [1:42:27<3:29:20,  1.41it/s]
1|8227|Loss: 0.8159664869308472:  32%|███▏      | 8227/25880 [1:42:28<3:37:10,  1.35it/s]
1|8228|Loss: 0.8639867305755615:  32%|███▏      | 8227/25880 [1:42:28<3:37:10,  1.35it/s]
1|8228|Loss: 0.8639867305755615:  32%|███▏      | 8228/25880 [1:42:29<3:45:02,  1.31it/s]
1|8229|Loss: 0.8734819293022156:  32%|███▏      | 8228/25880 [1:42:29<3:45:02,  1.31it/s]
1|8229|Loss: 0.8734819293022156:  32%|███▏      | 8229/25880 [1:42:29<3:37:49,  1.35it/s]
1|8230|Loss: 0.8915425539016724:  32%|███▏      | 8229/25880 [1:42:30<3:37:49,  1.35it/s]
1|8230|Loss: 0.8915425539016724:  32%|███▏      | 8230/25880 [1:42:30<3:35:50,  1.36it/s]
1|8231|Loss: 0.8152640461921692:  32%|███▏      | 8230/25880 [1:42:30<3:35:50,  1.36it/s]
1|8231|Loss: 0.8152640461921692:  32%|███▏      | 8231/25880 [1:42:31<3:36:27,  1.36it/s]
1|8232|Loss: 0.798194944858551:  32%|███▏      | 8231/25880 [1:42:31<3:36:27,  1.36it/s] 
1|8232|Loss: 0.798194944858551:  32%|███▏      | 8232/25880 [1:42:31<3:34:01,  1.37it/s]
1|8233|Loss: 0.8067910671234131:  32%|███▏      | 8232/25880 [1:42:32<3:34:01,  1.37it/s]
1|8233|Loss: 0.8067910671234131:  32%|███▏      | 8233/25880 [1:42:32<3:33:02,  1.38it/s]
1|8234|Loss: 0.8972411751747131:  32%|███▏      | 8233/25880 [1:42:32<3:33:02,  1.38it/s]
1|8234|Loss: 0.8972411751747131:  32%|███▏      | 8234/25880 [1:42:33<3:19:00,  1.48it/s]
1|8235|Loss: 0.8936029672622681:  32%|███▏      | 8234/25880 [1:42:33<3:19:00,  1.48it/s]
1|8235|Loss: 0.8936029672622681:  32%|███▏      | 8235/25880 [1:42:33<3:17:29,  1.49it/s]
1|8236|Loss: 0.7469217777252197:  32%|███▏      | 8235/25880 [1:42:34<3:17:29,  1.49it/s]
1|8236|Loss: 0.7469217777252197:  32%|███▏      | 8236/25880 [1:42:34<3:28:44,  1.41it/s]
1|8237|Loss: 0.9905851483345032:  32%|███▏      | 8236/25880 [1:42:35<3:28:44,  1.41it/s]
1|8237|Loss: 0.9905851483345032:  32%|███▏      | 8237/25880 [1:42:35<3:33:29,  1.38it/s]
1|8238|Loss: 0.86928391456604:  32%|███▏      | 8237/25880 [1:42:35<3:33:29,  1.38it/s]  
1|8238|Loss: 0.86928391456604:  32%|███▏      | 8238/25880 [1:42:36<3:34:32,  1.37it/s]
1|8239|Loss: 0.7493526339530945:  32%|███▏      | 8238/25880 [1:42:36<3:34:32,  1.37it/s]
1|8239|Loss: 0.7493526339530945:  32%|███▏      | 8239/25880 [1:42:36<3:23:58,  1.44it/s]
1|8240|Loss: 0.88582843542099:  32%|███▏      | 8239/25880 [1:42:37<3:23:58,  1.44it/s]  
1|8240|Loss: 0.88582843542099:  32%|███▏      | 8240/25880 [1:42:37<3:17:55,  1.49it/s]
1|8241|Loss: 0.8934645056724548:  32%|███▏      | 8240/25880 [1:42:37<3:17:55,  1.49it/s]
1|8241|Loss: 0.8934645056724548:  32%|███▏      | 8241/25880 [1:42:38<3:28:12,  1.41it/s]
1|8242|Loss: 0.7812592387199402:  32%|███▏      | 8241/25880 [1:42:38<3:28:12,  1.41it/s]
1|8242|Loss: 0.7812592387199402:  32%|███▏      | 8242/25880 [1:42:38<3:35:39,  1.36it/s]
1|8243|Loss: 0.8953756093978882:  32%|███▏      | 8242/25880 [1:42:39<3:35:39,  1.36it/s]
1|8243|Loss: 0.8953756093978882:  32%|███▏      | 8243/25880 [1:42:39<3:47:30,  1.29it/s]
1|8244|Loss: 0.8693472146987915:  32%|███▏      | 8243/25880 [1:42:40<3:47:30,  1.29it/s]
1|8244|Loss: 0.8693472146987915:  32%|███▏      | 8244/25880 [1:42:40<3:37:27,  1.35it/s]
1|8245|Loss: 0.8607505559921265:  32%|███▏      | 8244/25880 [1:42:40<3:37:27,  1.35it/s]
1|8245|Loss: 0.8607505559921265:  32%|███▏      | 8245/25880 [1:42:41<3:41:04,  1.33it/s]
1|8246|Loss: 0.7295498847961426:  32%|███▏      | 8245/25880 [1:42:41<3:41:04,  1.33it/s]
1|8246|Loss: 0.7295498847961426:  32%|███▏      | 8246/25880 [1:42:41<3:33:01,  1.38it/s]
1|8247|Loss: 0.7177990078926086:  32%|███▏      | 8246/25880 [1:42:42<3:33:01,  1.38it/s]
1|8247|Loss: 0.7177990078926086:  32%|███▏      | 8247/25880 [1:42:42<3:32:55,  1.38it/s]
1|8248|Loss: 0.8179548382759094:  32%|███▏      | 8247/25880 [1:42:43<3:32:55,  1.38it/s]
1|8248|Loss: 0.8179548382759094:  32%|███▏      | 8248/25880 [1:42:43<3:39:01,  1.34it/s]
1|8249|Loss: 0.8053303360939026:  32%|███▏      | 8248/25880 [1:42:43<3:39:01,  1.34it/s]
1|8249|Loss: 0.8053303360939026:  32%|███▏      | 8249/25880 [1:42:44<3:36:10,  1.36it/s]
1|8250|Loss: 0.7689225077629089:  32%|███▏      | 8249/25880 [1:42:44<3:36:10,  1.36it/s]
1|8250|Loss: 0.7689225077629089:  32%|███▏      | 8250/25880 [1:42:44<3:38:53,  1.34it/s]
1|8251|Loss: 0.7829434275627136:  32%|███▏      | 8250/25880 [1:42:45<3:38:53,  1.34it/s]
1|8251|Loss: 0.7829434275627136:  32%|███▏      | 8251/25880 [1:42:45<3:44:05,  1.31it/s]
1|8252|Loss: 0.6824109554290771:  32%|███▏      | 8251/25880 [1:42:46<3:44:05,  1.31it/s]
1|8252|Loss: 0.6824109554290771:  32%|███▏      | 8252/25880 [1:42:46<3:47:14,  1.29it/s]
1|8253|Loss: 0.8586020469665527:  32%|███▏      | 8252/25880 [1:42:46<3:47:14,  1.29it/s]
1|8253|Loss: 0.8586020469665527:  32%|███▏      | 8253/25880 [1:42:47<3:44:55,  1.31it/s]
1|8254|Loss: 0.8192552328109741:  32%|███▏      | 8253/25880 [1:42:47<3:44:55,  1.31it/s]
1|8254|Loss: 0.8192552328109741:  32%|███▏      | 8254/25880 [1:42:47<3:32:21,  1.38it/s]
1|8255|Loss: 0.7646315693855286:  32%|███▏      | 8254/25880 [1:42:48<3:32:21,  1.38it/s]
1|8255|Loss: 0.7646315693855286:  32%|███▏      | 8255/25880 [1:42:48<3:27:41,  1.41it/s]
1|8256|Loss: 0.8086835741996765:  32%|███▏      | 8255/25880 [1:42:48<3:27:41,  1.41it/s]
1|8256|Loss: 0.8086835741996765:  32%|███▏      | 8256/25880 [1:42:49<3:29:09,  1.40it/s]
1|8257|Loss: 0.9222633838653564:  32%|███▏      | 8256/25880 [1:42:49<3:29:09,  1.40it/s]
1|8257|Loss: 0.9222633838653564:  32%|███▏      | 8257/25880 [1:42:50<3:31:25,  1.39it/s]
1|8258|Loss: 0.8102851510047913:  32%|███▏      | 8257/25880 [1:42:50<3:31:25,  1.39it/s]
1|8258|Loss: 0.8102851510047913:  32%|███▏      | 8258/25880 [1:42:50<3:40:11,  1.33it/s]
1|8259|Loss: 0.8712324500083923:  32%|███▏      | 8258/25880 [1:42:51<3:40:11,  1.33it/s]
1|8259|Loss: 0.8712324500083923:  32%|███▏      | 8259/25880 [1:42:51<3:40:45,  1.33it/s]
1|8260|Loss: 0.8947582244873047:  32%|███▏      | 8259/25880 [1:42:52<3:40:45,  1.33it/s]
1|8260|Loss: 0.8947582244873047:  32%|███▏      | 8260/25880 [1:42:52<3:39:09,  1.34it/s]
1|8261|Loss: 0.8751236796379089:  32%|███▏      | 8260/25880 [1:42:52<3:39:09,  1.34it/s]
1|8261|Loss: 0.8751236796379089:  32%|███▏      | 8261/25880 [1:42:53<3:41:33,  1.33it/s]
1|8262|Loss: 0.7830250859260559:  32%|███▏      | 8261/25880 [1:42:53<3:41:33,  1.33it/s]
1|8262|Loss: 0.7830250859260559:  32%|███▏      | 8262/25880 [1:42:53<3:40:28,  1.33it/s]
1|8263|Loss: 0.8958227038383484:  32%|███▏      | 8262/25880 [1:42:54<3:40:28,  1.33it/s]
1|8263|Loss: 0.8958227038383484:  32%|███▏      | 8263/25880 [1:42:54<4:12:51,  1.16it/s]
1|8264|Loss: 0.9314652681350708:  32%|███▏      | 8263/25880 [1:42:55<4:12:51,  1.16it/s]
1|8264|Loss: 0.9314652681350708:  32%|███▏      | 8264/25880 [1:42:55<3:44:30,  1.31it/s]
1|8265|Loss: 0.8978554606437683:  32%|███▏      | 8264/25880 [1:42:55<3:44:30,  1.31it/s]
1|8265|Loss: 0.8978554606437683:  32%|███▏      | 8265/25880 [1:42:56<3:29:19,  1.40it/s]
1|8266|Loss: 0.869193434715271:  32%|███▏      | 8265/25880 [1:42:56<3:29:19,  1.40it/s] 
1|8266|Loss: 0.869193434715271:  32%|███▏      | 8266/25880 [1:42:56<3:28:11,  1.41it/s]
1|8267|Loss: 0.6429457664489746:  32%|███▏      | 8266/25880 [1:42:57<3:28:11,  1.41it/s]
1|8267|Loss: 0.6429457664489746:  32%|███▏      | 8267/25880 [1:42:57<3:28:05,  1.41it/s]
1|8268|Loss: 0.9184649586677551:  32%|███▏      | 8267/25880 [1:42:57<3:28:05,  1.41it/s]
1|8268|Loss: 0.9184649586677551:  32%|███▏      | 8268/25880 [1:42:58<3:29:46,  1.40it/s]
1|8269|Loss: 0.8528565764427185:  32%|███▏      | 8268/25880 [1:42:58<3:29:46,  1.40it/s]
1|8269|Loss: 0.8528565764427185:  32%|███▏      | 8269/25880 [1:42:58<3:23:20,  1.44it/s]
1|8270|Loss: 0.9239445924758911:  32%|███▏      | 8269/25880 [1:42:59<3:23:20,  1.44it/s]
1|8270|Loss: 0.9239445924758911:  32%|███▏      | 8270/25880 [1:42:59<3:29:48,  1.40it/s]
1|8271|Loss: 0.8981066346168518:  32%|███▏      | 8270/25880 [1:43:00<3:29:48,  1.40it/s]
1|8271|Loss: 0.8981066346168518:  32%|███▏      | 8271/25880 [1:43:00<3:25:48,  1.43it/s]
1|8272|Loss: 0.891839861869812:  32%|███▏      | 8271/25880 [1:43:00<3:25:48,  1.43it/s] 
1|8272|Loss: 0.891839861869812:  32%|███▏      | 8272/25880 [1:43:00<3:20:54,  1.46it/s]
1|8273|Loss: 0.8360997438430786:  32%|███▏      | 8272/25880 [1:43:01<3:20:54,  1.46it/s]
1|8273|Loss: 0.8360997438430786:  32%|███▏      | 8273/25880 [1:43:01<3:16:57,  1.49it/s]
1|8274|Loss: 0.8428831696510315:  32%|███▏      | 8273/25880 [1:43:01<3:16:57,  1.49it/s]
1|8274|Loss: 0.8428831696510315:  32%|███▏      | 8274/25880 [1:43:02<3:18:27,  1.48it/s]
1|8275|Loss: 0.7931234836578369:  32%|███▏      | 8274/25880 [1:43:02<3:18:27,  1.48it/s]
1|8275|Loss: 0.7931234836578369:  32%|███▏      | 8275/25880 [1:43:03<3:22:11,  1.45it/s]
1|8276|Loss: 0.8639867305755615:  32%|███▏      | 8275/25880 [1:43:03<3:22:11,  1.45it/s]
1|8276|Loss: 0.8639867305755615:  32%|███▏      | 8276/25880 [1:43:03<3:17:20,  1.49it/s]
1|8277|Loss: 0.8396619558334351:  32%|███▏      | 8276/25880 [1:43:04<3:17:20,  1.49it/s]
1|8277|Loss: 0.8396619558334351:  32%|███▏      | 8277/25880 [1:43:04<3:19:56,  1.47it/s]
1|8278|Loss: 0.8908692598342896:  32%|███▏      | 8277/25880 [1:43:04<3:19:56,  1.47it/s]
1|8278|Loss: 0.8908692598342896:  32%|███▏      | 8278/25880 [1:43:05<3:24:07,  1.44it/s]
1|8279|Loss: 0.9150096774101257:  32%|███▏      | 8278/25880 [1:43:05<3:24:07,  1.44it/s]
1|8279|Loss: 0.9150096774101257:  32%|███▏      | 8279/25880 [1:43:05<3:20:50,  1.46it/s]
1|8280|Loss: 0.9381672143936157:  32%|███▏      | 8279/25880 [1:43:06<3:20:50,  1.46it/s]
1|8280|Loss: 0.9381672143936157:  32%|███▏      | 8280/25880 [1:43:06<3:28:35,  1.41it/s]
1|8281|Loss: 0.8559638857841492:  32%|███▏      | 8280/25880 [1:43:06<3:28:35,  1.41it/s]
1|8281|Loss: 0.8559638857841492:  32%|███▏      | 8281/25880 [1:43:07<3:32:12,  1.38it/s]
1|8282|Loss: 0.885539710521698:  32%|███▏      | 8281/25880 [1:43:07<3:32:12,  1.38it/s] 
1|8282|Loss: 0.885539710521698:  32%|███▏      | 8282/25880 [1:43:07<3:31:07,  1.39it/s]
1|8283|Loss: 0.808505117893219:  32%|███▏      | 8282/25880 [1:43:08<3:31:07,  1.39it/s]
1|8283|Loss: 0.808505117893219:  32%|███▏      | 8283/25880 [1:43:08<3:36:08,  1.36it/s]
1|8284|Loss: 0.8796945214271545:  32%|███▏      | 8283/25880 [1:43:09<3:36:08,  1.36it/s]
1|8284|Loss: 0.8796945214271545:  32%|███▏      | 8284/25880 [1:43:09<3:24:10,  1.44it/s]
1|8285|Loss: 0.8569731116294861:  32%|███▏      | 8284/25880 [1:43:09<3:24:10,  1.44it/s]
1|8285|Loss: 0.8569731116294861:  32%|███▏      | 8285/25880 [1:43:09<3:15:42,  1.50it/s]
1|8286|Loss: 0.7551742792129517:  32%|███▏      | 8285/25880 [1:43:10<3:15:42,  1.50it/s]
1|8286|Loss: 0.7551742792129517:  32%|███▏      | 8286/25880 [1:43:10<3:00:12,  1.63it/s]
1|8287|Loss: 0.9833923578262329:  32%|███▏      | 8286/25880 [1:43:10<3:00:12,  1.63it/s]
1|8287|Loss: 0.9833923578262329:  32%|███▏      | 8287/25880 [1:43:11<3:03:55,  1.59it/s]
1|8288|Loss: 0.8067866563796997:  32%|███▏      | 8287/25880 [1:43:11<3:03:55,  1.59it/s]
1|8288|Loss: 0.8067866563796997:  32%|███▏      | 8288/25880 [1:43:11<3:12:58,  1.52it/s]
1|8289|Loss: 0.8687717914581299:  32%|███▏      | 8288/25880 [1:43:12<3:12:58,  1.52it/s]
1|8289|Loss: 0.8687717914581299:  32%|███▏      | 8289/25880 [1:43:12<3:19:35,  1.47it/s]
1|8290|Loss: 0.8119188547134399:  32%|███▏      | 8289/25880 [1:43:12<3:19:35,  1.47it/s]
1|8290|Loss: 0.8119188547134399:  32%|███▏      | 8290/25880 [1:43:13<3:30:34,  1.39it/s]
1|8291|Loss: 0.7226241827011108:  32%|███▏      | 8290/25880 [1:43:13<3:30:34,  1.39it/s]
1|8291|Loss: 0.7226241827011108:  32%|███▏      | 8291/25880 [1:43:14<3:26:33,  1.42it/s]
1|8292|Loss: 0.7791078686714172:  32%|███▏      | 8291/25880 [1:43:14<3:26:33,  1.42it/s]
1|8292|Loss: 0.7791078686714172:  32%|███▏      | 8292/25880 [1:43:14<3:34:10,  1.37it/s]
1|8293|Loss: 0.8135978579521179:  32%|███▏      | 8292/25880 [1:43:15<3:34:10,  1.37it/s]
1|8293|Loss: 0.8135978579521179:  32%|███▏      | 8293/25880 [1:43:15<3:29:46,  1.40it/s]
1|8294|Loss: 0.8378468155860901:  32%|███▏      | 8293/25880 [1:43:15<3:29:46,  1.40it/s]
1|8294|Loss: 0.8378468155860901:  32%|███▏      | 8294/25880 [1:43:16<3:29:22,  1.40it/s]
1|8295|Loss: 0.8177046179771423:  32%|███▏      | 8294/25880 [1:43:16<3:29:22,  1.40it/s]
1|8295|Loss: 0.8177046179771423:  32%|███▏      | 8295/25880 [1:43:16<3:31:16,  1.39it/s]
1|8296|Loss: 0.6998075842857361:  32%|███▏      | 8295/25880 [1:43:17<3:31:16,  1.39it/s]
1|8296|Loss: 0.6998075842857361:  32%|███▏      | 8296/25880 [1:43:17<3:41:37,  1.32it/s]
1|8297|Loss: 0.7924788594245911:  32%|███▏      | 8296/25880 [1:43:18<3:41:37,  1.32it/s]
1|8297|Loss: 0.7924788594245911:  32%|███▏      | 8297/25880 [1:43:18<3:55:06,  1.25it/s]
1|8298|Loss: 0.9048519134521484:  32%|███▏      | 8297/25880 [1:43:19<3:55:06,  1.25it/s]
1|8298|Loss: 0.9048519134521484:  32%|███▏      | 8298/25880 [1:43:19<4:00:14,  1.22it/s]
1|8299|Loss: 0.9877339005470276:  32%|███▏      | 8298/25880 [1:43:19<4:00:14,  1.22it/s]
1|8299|Loss: 0.9877339005470276:  32%|███▏      | 8299/25880 [1:43:20<3:55:27,  1.24it/s]
1|8300|Loss: 0.868320107460022:  32%|███▏      | 8299/25880 [1:43:20<3:55:27,  1.24it/s] 
1|8300|Loss: 0.868320107460022:  32%|███▏      | 8300/25880 [1:43:21<3:58:01,  1.23it/s]
1|8301|Loss: 0.7855871915817261:  32%|███▏      | 8300/25880 [1:43:21<3:58:01,  1.23it/s]
1|8301|Loss: 0.7855871915817261:  32%|███▏      | 8301/25880 [1:43:21<3:46:59,  1.29it/s]
1|8302|Loss: 0.7602922320365906:  32%|███▏      | 8301/25880 [1:43:22<3:46:59,  1.29it/s]
1|8302|Loss: 0.7602922320365906:  32%|███▏      | 8302/25880 [1:43:22<3:40:06,  1.33it/s]
1|8303|Loss: 0.7648521065711975:  32%|███▏      | 8302/25880 [1:43:22<3:40:06,  1.33it/s]
1|8303|Loss: 0.7648521065711975:  32%|███▏      | 8303/25880 [1:43:23<3:29:29,  1.40it/s]
1|8304|Loss: 0.8887041211128235:  32%|███▏      | 8303/25880 [1:43:23<3:29:29,  1.40it/s]
1|8304|Loss: 0.8887041211128235:  32%|███▏      | 8304/25880 [1:43:23<3:23:07,  1.44it/s]
1|8305|Loss: 0.9803519248962402:  32%|███▏      | 8304/25880 [1:43:24<3:23:07,  1.44it/s]
1|8305|Loss: 0.9803519248962402:  32%|███▏      | 8305/25880 [1:43:24<3:18:23,  1.48it/s]
1|8306|Loss: 1.0075174570083618:  32%|███▏      | 8305/25880 [1:43:24<3:18:23,  1.48it/s]
1|8306|Loss: 1.0075174570083618:  32%|███▏      | 8306/25880 [1:43:25<3:15:01,  1.50it/s]
1|8307|Loss: 0.8564764857292175:  32%|███▏      | 8306/25880 [1:43:25<3:15:01,  1.50it/s]
1|8307|Loss: 0.8564764857292175:  32%|███▏      | 8307/25880 [1:43:25<3:19:04,  1.47it/s]
1|8308|Loss: 0.8737694621086121:  32%|███▏      | 8307/25880 [1:43:26<3:19:04,  1.47it/s]
1|8308|Loss: 0.8737694621086121:  32%|███▏      | 8308/25880 [1:43:26<3:15:29,  1.50it/s]
1|8309|Loss: 0.8246859312057495:  32%|███▏      | 8308/25880 [1:43:26<3:15:29,  1.50it/s]
1|8309|Loss: 0.8246859312057495:  32%|███▏      | 8309/25880 [1:43:27<3:09:47,  1.54it/s]
1|8310|Loss: 0.8245357275009155:  32%|███▏      | 8309/25880 [1:43:27<3:09:47,  1.54it/s]
1|8310|Loss: 0.8245357275009155:  32%|███▏      | 8310/25880 [1:43:27<3:06:08,  1.57it/s]
1|8311|Loss: 0.8795995712280273:  32%|███▏      | 8310/25880 [1:43:28<3:06:08,  1.57it/s]
1|8311|Loss: 0.8795995712280273:  32%|███▏      | 8311/25880 [1:43:28<3:31:10,  1.39it/s]
1|8312|Loss: 0.7609553933143616:  32%|███▏      | 8311/25880 [1:43:29<3:31:10,  1.39it/s]
1|8312|Loss: 0.7609553933143616:  32%|███▏      | 8312/25880 [1:43:29<3:47:31,  1.29it/s]
1|8313|Loss: 0.8155698776245117:  32%|███▏      | 8312/25880 [1:43:29<3:47:31,  1.29it/s]
1|8313|Loss: 0.8155698776245117:  32%|███▏      | 8313/25880 [1:43:30<3:34:01,  1.37it/s]
1|8314|Loss: 0.8657606244087219:  32%|███▏      | 8313/25880 [1:43:30<3:34:01,  1.37it/s]
1|8314|Loss: 0.8657606244087219:  32%|███▏      | 8314/25880 [1:43:30<3:24:25,  1.43it/s]
1|8315|Loss: 0.7400130033493042:  32%|███▏      | 8314/25880 [1:43:31<3:24:25,  1.43it/s]
1|8315|Loss: 0.7400130033493042:  32%|███▏      | 8315/25880 [1:43:31<3:30:30,  1.39it/s]
1|8316|Loss: 0.8447732329368591:  32%|███▏      | 8315/25880 [1:43:31<3:30:30,  1.39it/s]
1|8316|Loss: 0.8447732329368591:  32%|███▏      | 8316/25880 [1:43:32<3:41:05,  1.32it/s]
1|8317|Loss: 0.8694764375686646:  32%|███▏      | 8316/25880 [1:43:32<3:41:05,  1.32it/s]
1|8317|Loss: 0.8694764375686646:  32%|███▏      | 8317/25880 [1:43:33<3:45:26,  1.30it/s]
1|8318|Loss: 0.9672755599021912:  32%|███▏      | 8317/25880 [1:43:33<3:45:26,  1.30it/s]
1|8318|Loss: 0.9672755599021912:  32%|███▏      | 8318/25880 [1:43:33<3:32:16,  1.38it/s]
1|8319|Loss: 0.7964339852333069:  32%|███▏      | 8318/25880 [1:43:34<3:32:16,  1.38it/s]
1|8319|Loss: 0.7964339852333069:  32%|███▏      | 8319/25880 [1:43:34<3:23:05,  1.44it/s]
1|8320|Loss: 0.8828393816947937:  32%|███▏      | 8319/25880 [1:43:34<3:23:05,  1.44it/s]
1|8320|Loss: 0.8828393816947937:  32%|███▏      | 8320/25880 [1:43:35<3:23:16,  1.44it/s]
1|8321|Loss: 0.8595501184463501:  32%|███▏      | 8320/25880 [1:43:35<3:23:16,  1.44it/s]
1|8321|Loss: 0.8595501184463501:  32%|███▏      | 8321/25880 [1:43:35<3:24:19,  1.43it/s]
1|8322|Loss: 0.8603504300117493:  32%|███▏      | 8321/25880 [1:43:36<3:24:19,  1.43it/s]
1|8322|Loss: 0.8603504300117493:  32%|███▏      | 8322/25880 [1:43:36<3:20:16,  1.46it/s]
1|8323|Loss: 0.8723610043525696:  32%|███▏      | 8322/25880 [1:43:36<3:20:16,  1.46it/s]
1|8323|Loss: 0.8723610043525696:  32%|███▏      | 8323/25880 [1:43:36<2:57:38,  1.65it/s]
1|8324|Loss: 0.8486005067825317:  32%|███▏      | 8323/25880 [1:43:37<2:57:38,  1.65it/s]
1|8324|Loss: 0.8486005067825317:  32%|███▏      | 8324/25880 [1:43:37<3:09:23,  1.54it/s]
1|8325|Loss: 0.7407246232032776:  32%|███▏      | 8324/25880 [1:43:38<3:09:23,  1.54it/s]
1|8325|Loss: 0.7407246232032776:  32%|███▏      | 8325/25880 [1:43:38<3:23:11,  1.44it/s]
1|8326|Loss: 0.8271036148071289:  32%|███▏      | 8325/25880 [1:43:38<3:23:11,  1.44it/s]
1|8326|Loss: 0.8271036148071289:  32%|███▏      | 8326/25880 [1:43:39<3:31:28,  1.38it/s]
1|8327|Loss: 0.7822302579879761:  32%|███▏      | 8326/25880 [1:43:39<3:31:28,  1.38it/s]
1|8327|Loss: 0.7822302579879761:  32%|███▏      | 8327/25880 [1:43:39<3:31:27,  1.38it/s]
1|8328|Loss: 0.9658292531967163:  32%|███▏      | 8327/25880 [1:43:40<3:31:27,  1.38it/s]
1|8328|Loss: 0.9658292531967163:  32%|███▏      | 8328/25880 [1:43:40<3:23:07,  1.44it/s]
1|8329|Loss: 0.6178308129310608:  32%|███▏      | 8328/25880 [1:43:40<3:23:07,  1.44it/s]
1|8329|Loss: 0.6178308129310608:  32%|███▏      | 8329/25880 [1:43:41<3:40:18,  1.33it/s]
1|8330|Loss: 0.9122865200042725:  32%|███▏      | 8329/25880 [1:43:41<3:40:18,  1.33it/s]
1|8330|Loss: 0.9122865200042725:  32%|███▏      | 8330/25880 [1:43:42<3:36:14,  1.35it/s]
1|8331|Loss: 0.9620296359062195:  32%|███▏      | 8330/25880 [1:43:42<3:36:14,  1.35it/s]
1|8331|Loss: 0.9620296359062195:  32%|███▏      | 8331/25880 [1:43:42<3:25:49,  1.42it/s]
1|8332|Loss: 0.7844681143760681:  32%|███▏      | 8331/25880 [1:43:43<3:25:49,  1.42it/s]
1|8332|Loss: 0.7844681143760681:  32%|███▏      | 8332/25880 [1:43:43<3:34:49,  1.36it/s]
1|8333|Loss: 0.7132717370986938:  32%|███▏      | 8332/25880 [1:43:44<3:34:49,  1.36it/s]
1|8333|Loss: 0.7132717370986938:  32%|███▏      | 8333/25880 [1:43:44<3:59:54,  1.22it/s]
1|8334|Loss: 0.7722907066345215:  32%|███▏      | 8333/25880 [1:43:45<3:59:54,  1.22it/s]
1|8334|Loss: 0.7722907066345215:  32%|███▏      | 8334/25880 [1:43:45<4:08:45,  1.18it/s]
1|8335|Loss: 0.8199531435966492:  32%|███▏      | 8334/25880 [1:43:45<4:08:45,  1.18it/s]
1|8335|Loss: 0.8199531435966492:  32%|███▏      | 8335/25880 [1:43:46<4:03:03,  1.20it/s]
1|8336|Loss: 0.7750008702278137:  32%|███▏      | 8335/25880 [1:43:46<4:03:03,  1.20it/s]
1|8336|Loss: 0.7750008702278137:  32%|███▏      | 8336/25880 [1:43:47<3:54:30,  1.25it/s]
1|8337|Loss: 0.9679597616195679:  32%|███▏      | 8336/25880 [1:43:47<3:54:30,  1.25it/s]
1|8337|Loss: 0.9679597616195679:  32%|███▏      | 8337/25880 [1:43:47<3:54:31,  1.25it/s]
1|8338|Loss: 0.918921172618866:  32%|███▏      | 8337/25880 [1:43:48<3:54:31,  1.25it/s] 
1|8338|Loss: 0.918921172618866:  32%|███▏      | 8338/25880 [1:43:48<3:53:34,  1.25it/s]
1|8339|Loss: 0.780828595161438:  32%|███▏      | 8338/25880 [1:43:49<3:53:34,  1.25it/s]
1|8339|Loss: 0.780828595161438:  32%|███▏      | 8339/25880 [1:43:49<3:42:28,  1.31it/s]
1|8340|Loss: 0.9634894132614136:  32%|███▏      | 8339/25880 [1:43:49<3:42:28,  1.31it/s]
1|8340|Loss: 0.9634894132614136:  32%|███▏      | 8340/25880 [1:43:50<3:42:59,  1.31it/s]
1|8341|Loss: 0.9500454664230347:  32%|███▏      | 8340/25880 [1:43:50<3:42:59,  1.31it/s]
1|8341|Loss: 0.9500454664230347:  32%|███▏      | 8341/25880 [1:43:50<3:41:21,  1.32it/s]
1|8342|Loss: 0.873043417930603:  32%|███▏      | 8341/25880 [1:43:51<3:41:21,  1.32it/s] 
1|8342|Loss: 0.873043417930603:  32%|███▏      | 8342/25880 [1:43:51<3:37:43,  1.34it/s]
1|8343|Loss: 0.8931341767311096:  32%|███▏      | 8342/25880 [1:43:51<3:37:43,  1.34it/s]
1|8343|Loss: 0.8931341767311096:  32%|███▏      | 8343/25880 [1:43:52<3:37:14,  1.35it/s]
1|8344|Loss: 0.872076690196991:  32%|███▏      | 8343/25880 [1:43:52<3:37:14,  1.35it/s] 
1|8344|Loss: 0.872076690196991:  32%|███▏      | 8344/25880 [1:43:53<3:36:37,  1.35it/s]
1|8345|Loss: 0.944121241569519:  32%|███▏      | 8344/25880 [1:43:53<3:36:37,  1.35it/s]
1|8345|Loss: 0.944121241569519:  32%|███▏      | 8345/25880 [1:43:53<3:43:41,  1.31it/s]
1|8346|Loss: 0.834165096282959:  32%|███▏      | 8345/25880 [1:43:54<3:43:41,  1.31it/s]
1|8346|Loss: 0.834165096282959:  32%|███▏      | 8346/25880 [1:43:54<3:29:12,  1.40it/s]
1|8347|Loss: 0.8439106941223145:  32%|███▏      | 8346/25880 [1:43:54<3:29:12,  1.40it/s]
1|8347|Loss: 0.8439106941223145:  32%|███▏      | 8347/25880 [1:43:55<3:27:20,  1.41it/s]
1|8348|Loss: 0.9067875742912292:  32%|███▏      | 8347/25880 [1:43:55<3:27:20,  1.41it/s]
1|8348|Loss: 0.9067875742912292:  32%|███▏      | 8348/25880 [1:43:55<3:29:09,  1.40it/s]
1|8349|Loss: 0.8897674083709717:  32%|███▏      | 8348/25880 [1:43:56<3:29:09,  1.40it/s]
1|8349|Loss: 0.8897674083709717:  32%|███▏      | 8349/25880 [1:43:56<3:21:54,  1.45it/s]
1|8350|Loss: 0.9720742106437683:  32%|███▏      | 8349/25880 [1:43:56<3:21:54,  1.45it/s]
1|8350|Loss: 0.9720742106437683:  32%|███▏      | 8350/25880 [1:43:57<3:21:41,  1.45it/s]
1|8351|Loss: 0.8700044751167297:  32%|███▏      | 8350/25880 [1:43:57<3:21:41,  1.45it/s]
1|8351|Loss: 0.8700044751167297:  32%|███▏      | 8351/25880 [1:43:57<3:24:31,  1.43it/s]
1|8352|Loss: 0.9238733053207397:  32%|███▏      | 8351/25880 [1:43:58<3:24:31,  1.43it/s]
1|8352|Loss: 0.9238733053207397:  32%|███▏      | 8352/25880 [1:43:58<3:26:52,  1.41it/s]
1|8353|Loss: 0.7845369577407837:  32%|███▏      | 8352/25880 [1:43:58<3:26:52,  1.41it/s]
1|8353|Loss: 0.7845369577407837:  32%|███▏      | 8353/25880 [1:43:59<3:03:10,  1.59it/s]
1|8354|Loss: 0.9727756381034851:  32%|███▏      | 8353/25880 [1:43:59<3:03:10,  1.59it/s]
1|8354|Loss: 0.9727756381034851:  32%|███▏      | 8354/25880 [1:43:59<3:13:27,  1.51it/s]
1|8355|Loss: 0.8732744455337524:  32%|███▏      | 8354/25880 [1:44:00<3:13:27,  1.51it/s]
1|8355|Loss: 0.8732744455337524:  32%|███▏      | 8355/25880 [1:44:00<3:26:08,  1.42it/s]
1|8356|Loss: 0.9934977889060974:  32%|███▏      | 8355/25880 [1:44:01<3:26:08,  1.42it/s]
1|8356|Loss: 0.9934977889060974:  32%|███▏      | 8356/25880 [1:44:01<3:33:44,  1.37it/s]
1|8357|Loss: 0.8428053855895996:  32%|███▏      | 8356/25880 [1:44:01<3:33:44,  1.37it/s]
1|8357|Loss: 0.8428053855895996:  32%|███▏      | 8357/25880 [1:44:02<3:32:46,  1.37it/s]
1|8358|Loss: 0.9069995284080505:  32%|███▏      | 8357/25880 [1:44:02<3:32:46,  1.37it/s]
1|8358|Loss: 0.9069995284080505:  32%|███▏      | 8358/25880 [1:44:02<3:31:24,  1.38it/s]
1|8359|Loss: 0.7954389452934265:  32%|███▏      | 8358/25880 [1:44:03<3:31:24,  1.38it/s]
1|8359|Loss: 0.7954389452934265:  32%|███▏      | 8359/25880 [1:44:03<3:25:05,  1.42it/s]
1|8360|Loss: 0.9131947159767151:  32%|███▏      | 8359/25880 [1:44:03<3:25:05,  1.42it/s]
1|8360|Loss: 0.9131947159767151:  32%|███▏      | 8360/25880 [1:44:04<3:17:59,  1.47it/s]
1|8361|Loss: 0.7398406267166138:  32%|███▏      | 8360/25880 [1:44:04<3:17:59,  1.47it/s]
1|8361|Loss: 0.7398406267166138:  32%|███▏      | 8361/25880 [1:44:04<3:20:38,  1.46it/s]
1|8362|Loss: 0.8069908022880554:  32%|███▏      | 8361/25880 [1:44:05<3:20:38,  1.46it/s]
1|8362|Loss: 0.8069908022880554:  32%|███▏      | 8362/25880 [1:44:05<3:11:39,  1.52it/s]
1|8363|Loss: 0.8034490346908569:  32%|███▏      | 8362/25880 [1:44:05<3:11:39,  1.52it/s]
1|8363|Loss: 0.8034490346908569:  32%|███▏      | 8363/25880 [1:44:06<3:15:05,  1.50it/s]
1|8364|Loss: 0.7761916518211365:  32%|███▏      | 8363/25880 [1:44:06<3:15:05,  1.50it/s]
1|8364|Loss: 0.7761916518211365:  32%|███▏      | 8364/25880 [1:44:06<3:21:11,  1.45it/s]
1|8365|Loss: 0.9178356528282166:  32%|███▏      | 8364/25880 [1:44:07<3:21:11,  1.45it/s]
1|8365|Loss: 0.9178356528282166:  32%|███▏      | 8365/25880 [1:44:07<3:18:51,  1.47it/s]
1|8366|Loss: 0.8584280014038086:  32%|███▏      | 8365/25880 [1:44:07<3:18:51,  1.47it/s]
1|8366|Loss: 0.8584280014038086:  32%|███▏      | 8366/25880 [1:44:07<3:01:49,  1.61it/s]
1|8367|Loss: 0.8835605978965759:  32%|███▏      | 8366/25880 [1:44:08<3:01:49,  1.61it/s]
1|8367|Loss: 0.8835605978965759:  32%|███▏      | 8367/25880 [1:44:08<3:09:51,  1.54it/s]
1|8368|Loss: 0.9215641021728516:  32%|███▏      | 8367/25880 [1:44:09<3:09:51,  1.54it/s]
1|8368|Loss: 0.9215641021728516:  32%|███▏      | 8368/25880 [1:44:09<3:11:57,  1.52it/s]
1|8369|Loss: 0.8102912306785583:  32%|███▏      | 8368/25880 [1:44:09<3:11:57,  1.52it/s]
1|8369|Loss: 0.8102912306785583:  32%|███▏      | 8369/25880 [1:44:10<3:16:41,  1.48it/s]
1|8370|Loss: 0.8901046514511108:  32%|███▏      | 8369/25880 [1:44:10<3:16:41,  1.48it/s]
1|8370|Loss: 0.8901046514511108:  32%|███▏      | 8370/25880 [1:44:10<3:28:57,  1.40it/s]
1|8371|Loss: 0.8309063911437988:  32%|███▏      | 8370/25880 [1:44:11<3:28:57,  1.40it/s]
1|8371|Loss: 0.8309063911437988:  32%|███▏      | 8371/25880 [1:44:11<3:44:44,  1.30it/s]
1|8372|Loss: 0.8394522666931152:  32%|███▏      | 8371/25880 [1:44:12<3:44:44,  1.30it/s]
1|8372|Loss: 0.8394522666931152:  32%|███▏      | 8372/25880 [1:44:12<3:49:04,  1.27it/s]
1|8373|Loss: 0.9341623187065125:  32%|███▏      | 8372/25880 [1:44:13<3:49:04,  1.27it/s]
1|8373|Loss: 0.9341623187065125:  32%|███▏      | 8373/25880 [1:44:13<3:46:42,  1.29it/s]
1|8374|Loss: 0.8408873677253723:  32%|███▏      | 8373/25880 [1:44:13<3:46:42,  1.29it/s]
1|8374|Loss: 0.8408873677253723:  32%|███▏      | 8374/25880 [1:44:14<3:54:08,  1.25it/s]
1|8375|Loss: 0.8443566560745239:  32%|███▏      | 8374/25880 [1:44:14<3:54:08,  1.25it/s]
1|8375|Loss: 0.8443566560745239:  32%|███▏      | 8375/25880 [1:44:15<3:50:51,  1.26it/s]
1|8376|Loss: 0.900455117225647:  32%|███▏      | 8375/25880 [1:44:15<3:50:51,  1.26it/s] 
1|8376|Loss: 0.900455117225647:  32%|███▏      | 8376/25880 [1:44:15<3:37:39,  1.34it/s]
1|8377|Loss: 0.7846647500991821:  32%|███▏      | 8376/25880 [1:44:16<3:37:39,  1.34it/s]
1|8377|Loss: 0.7846647500991821:  32%|███▏      | 8377/25880 [1:44:16<3:42:39,  1.31it/s]
1|8378|Loss: 0.9483360052108765:  32%|███▏      | 8377/25880 [1:44:16<3:42:39,  1.31it/s]
1|8378|Loss: 0.9483360052108765:  32%|███▏      | 8378/25880 [1:44:17<3:49:02,  1.27it/s]
1|8379|Loss: 0.7602161169052124:  32%|███▏      | 8378/25880 [1:44:17<3:49:02,  1.27it/s]
1|8379|Loss: 0.7602161169052124:  32%|███▏      | 8379/25880 [1:44:18<3:51:19,  1.26it/s]
1|8380|Loss: 0.6776841878890991:  32%|███▏      | 8379/25880 [1:44:18<3:51:19,  1.26it/s]
1|8380|Loss: 0.6776841878890991:  32%|███▏      | 8380/25880 [1:44:18<3:47:15,  1.28it/s]
1|8381|Loss: 0.7239373326301575:  32%|███▏      | 8380/25880 [1:44:19<3:47:15,  1.28it/s]
1|8381|Loss: 0.7239373326301575:  32%|███▏      | 8381/25880 [1:44:19<3:28:59,  1.40it/s]
1|8382|Loss: 0.8187172412872314:  32%|███▏      | 8381/25880 [1:44:19<3:28:59,  1.40it/s]
1|8382|Loss: 0.8187172412872314:  32%|███▏      | 8382/25880 [1:44:20<3:27:43,  1.40it/s]
1|8383|Loss: 0.8331767320632935:  32%|███▏      | 8382/25880 [1:44:20<3:27:43,  1.40it/s]
1|8383|Loss: 0.8331767320632935:  32%|███▏      | 8383/25880 [1:44:20<3:27:45,  1.40it/s]
1|8384|Loss: 0.7823772430419922:  32%|███▏      | 8383/25880 [1:44:21<3:27:45,  1.40it/s]
1|8384|Loss: 0.7823772430419922:  32%|███▏      | 8384/25880 [1:44:21<3:28:13,  1.40it/s]
1|8385|Loss: 0.8128002285957336:  32%|███▏      | 8384/25880 [1:44:21<3:28:13,  1.40it/s]
1|8385|Loss: 0.8128002285957336:  32%|███▏      | 8385/25880 [1:44:22<3:29:08,  1.39it/s]
1|8386|Loss: 0.9558776617050171:  32%|███▏      | 8385/25880 [1:44:22<3:29:08,  1.39it/s]
1|8386|Loss: 0.9558776617050171:  32%|███▏      | 8386/25880 [1:44:23<3:44:16,  1.30it/s]
1|8387|Loss: 0.8540133237838745:  32%|███▏      | 8386/25880 [1:44:23<3:44:16,  1.30it/s]
1|8387|Loss: 0.8540133237838745:  32%|███▏      | 8387/25880 [1:44:23<3:44:34,  1.30it/s]
1|8388|Loss: 0.843967616558075:  32%|███▏      | 8387/25880 [1:44:24<3:44:34,  1.30it/s] 
1|8388|Loss: 0.843967616558075:  32%|███▏      | 8388/25880 [1:44:24<3:46:38,  1.29it/s]
1|8389|Loss: 0.7761349678039551:  32%|███▏      | 8388/25880 [1:44:25<3:46:38,  1.29it/s]
1|8389|Loss: 0.7761349678039551:  32%|███▏      | 8389/25880 [1:44:25<3:43:33,  1.30it/s]
1|8390|Loss: 0.7573622465133667:  32%|███▏      | 8389/25880 [1:44:25<3:43:33,  1.30it/s]
1|8390|Loss: 0.7573622465133667:  32%|███▏      | 8390/25880 [1:44:26<3:40:05,  1.32it/s]
1|8391|Loss: 1.0073586702346802:  32%|███▏      | 8390/25880 [1:44:26<3:40:05,  1.32it/s]
1|8391|Loss: 1.0073586702346802:  32%|███▏      | 8391/25880 [1:44:26<3:25:14,  1.42it/s]
1|8392|Loss: 0.7559365034103394:  32%|███▏      | 8391/25880 [1:44:27<3:25:14,  1.42it/s]
1|8392|Loss: 0.7559365034103394:  32%|███▏      | 8392/25880 [1:44:27<3:28:24,  1.40it/s]
1|8393|Loss: 0.8684277534484863:  32%|███▏      | 8392/25880 [1:44:27<3:28:24,  1.40it/s]
1|8393|Loss: 0.8684277534484863:  32%|███▏      | 8393/25880 [1:44:28<3:28:49,  1.40it/s]
1|8394|Loss: 0.7952446341514587:  32%|███▏      | 8393/25880 [1:44:28<3:28:49,  1.40it/s]
1|8394|Loss: 0.7952446341514587:  32%|███▏      | 8394/25880 [1:44:29<3:42:23,  1.31it/s]
1|8395|Loss: 0.9214445948600769:  32%|███▏      | 8394/25880 [1:44:29<3:42:23,  1.31it/s]
1|8395|Loss: 0.9214445948600769:  32%|███▏      | 8395/25880 [1:44:29<3:32:07,  1.37it/s]
1|8396|Loss: 0.7179589867591858:  32%|███▏      | 8395/25880 [1:44:30<3:32:07,  1.37it/s]
1|8396|Loss: 0.7179589867591858:  32%|███▏      | 8396/25880 [1:44:30<3:40:36,  1.32it/s]
1|8397|Loss: 0.8882404565811157:  32%|███▏      | 8396/25880 [1:44:31<3:40:36,  1.32it/s]
1|8397|Loss: 0.8882404565811157:  32%|███▏      | 8397/25880 [1:44:31<3:45:12,  1.29it/s]
1|8398|Loss: 0.8886236548423767:  32%|███▏      | 8397/25880 [1:44:31<3:45:12,  1.29it/s]
1|8398|Loss: 0.8886236548423767:  32%|███▏      | 8398/25880 [1:44:32<3:59:06,  1.22it/s]
1|8399|Loss: 0.8915348649024963:  32%|███▏      | 8398/25880 [1:44:32<3:59:06,  1.22it/s]
1|8399|Loss: 0.8915348649024963:  32%|███▏      | 8399/25880 [1:44:33<3:45:30,  1.29it/s]
1|8400|Loss: 0.8961871862411499:  32%|███▏      | 8399/25880 [1:44:33<3:45:30,  1.29it/s]
1|8400|Loss: 0.8961871862411499:  32%|███▏      | 8400/25880 [1:44:33<3:45:03,  1.29it/s]
1|8401|Loss: 0.8343177437782288:  32%|███▏      | 8400/25880 [1:44:34<3:45:03,  1.29it/s]
1|8401|Loss: 0.8343177437782288:  32%|███▏      | 8401/25880 [1:44:34<3:42:33,  1.31it/s]
1|8402|Loss: 0.8494102358818054:  32%|███▏      | 8401/25880 [1:44:34<3:42:33,  1.31it/s]
1|8402|Loss: 0.8494102358818054:  32%|███▏      | 8402/25880 [1:44:35<3:55:33,  1.24it/s]
1|8403|Loss: 0.8027796745300293:  32%|███▏      | 8402/25880 [1:44:35<3:55:33,  1.24it/s]
1|8403|Loss: 0.8027796745300293:  32%|███▏      | 8403/25880 [1:44:36<3:41:59,  1.31it/s]
1|8404|Loss: 0.8758485913276672:  32%|███▏      | 8403/25880 [1:44:36<3:41:59,  1.31it/s]
1|8404|Loss: 0.8758485913276672:  32%|███▏      | 8404/25880 [1:44:36<3:36:13,  1.35it/s]
1|8405|Loss: 0.7742761969566345:  32%|███▏      | 8404/25880 [1:44:37<3:36:13,  1.35it/s]
1|8405|Loss: 0.7742761969566345:  32%|███▏      | 8405/25880 [1:44:37<3:41:25,  1.32it/s]
1|8406|Loss: 0.800763726234436:  32%|███▏      | 8405/25880 [1:44:37<3:41:25,  1.32it/s] 
1|8406|Loss: 0.800763726234436:  32%|███▏      | 8406/25880 [1:44:38<3:40:54,  1.32it/s]
1|8407|Loss: 0.769830048084259:  32%|███▏      | 8406/25880 [1:44:38<3:40:54,  1.32it/s]
1|8407|Loss: 0.769830048084259:  32%|███▏      | 8407/25880 [1:44:38<3:23:09,  1.43it/s]
1|8408|Loss: 0.9687538743019104:  32%|███▏      | 8407/25880 [1:44:39<3:23:09,  1.43it/s]
1|8408|Loss: 0.9687538743019104:  32%|███▏      | 8408/25880 [1:44:39<3:22:47,  1.44it/s]
1|8409|Loss: 0.8128525018692017:  32%|███▏      | 8408/25880 [1:44:39<3:22:47,  1.44it/s]
1|8409|Loss: 0.8128525018692017:  32%|███▏      | 8409/25880 [1:44:40<3:12:26,  1.51it/s]
1|8410|Loss: 0.7547765970230103:  32%|███▏      | 8409/25880 [1:44:40<3:12:26,  1.51it/s]
1|8410|Loss: 0.7547765970230103:  32%|███▏      | 8410/25880 [1:44:41<3:28:15,  1.40it/s]
1|8411|Loss: 0.8055477738380432:  32%|███▏      | 8410/25880 [1:44:41<3:28:15,  1.40it/s]
1|8411|Loss: 0.8055477738380432:  32%|███▎      | 8411/25880 [1:44:41<3:37:24,  1.34it/s]
1|8412|Loss: 0.9194902181625366:  32%|███▎      | 8411/25880 [1:44:42<3:37:24,  1.34it/s]
1|8412|Loss: 0.9194902181625366:  33%|███▎      | 8412/25880 [1:44:42<3:31:08,  1.38it/s]
1|8413|Loss: 0.8947357535362244:  33%|███▎      | 8412/25880 [1:44:42<3:31:08,  1.38it/s]
1|8413|Loss: 0.8947357535362244:  33%|███▎      | 8413/25880 [1:44:43<3:37:10,  1.34it/s]
1|8414|Loss: 0.7404082417488098:  33%|███▎      | 8413/25880 [1:44:43<3:37:10,  1.34it/s]
1|8414|Loss: 0.7404082417488098:  33%|███▎      | 8414/25880 [1:44:44<3:53:18,  1.25it/s]
1|8415|Loss: 0.9306135177612305:  33%|███▎      | 8414/25880 [1:44:44<3:53:18,  1.25it/s]
1|8415|Loss: 0.9306135177612305:  33%|███▎      | 8415/25880 [1:44:45<3:58:10,  1.22it/s]
1|8416|Loss: 0.784761369228363:  33%|███▎      | 8415/25880 [1:44:45<3:58:10,  1.22it/s] 
1|8416|Loss: 0.784761369228363:  33%|███▎      | 8416/25880 [1:44:45<3:44:22,  1.30it/s]
1|8417|Loss: 0.7580721974372864:  33%|███▎      | 8416/25880 [1:44:46<3:44:22,  1.30it/s]
1|8417|Loss: 0.7580721974372864:  33%|███▎      | 8417/25880 [1:44:46<3:38:29,  1.33it/s]
1|8418|Loss: 0.7178544998168945:  33%|███▎      | 8417/25880 [1:44:46<3:38:29,  1.33it/s]
1|8418|Loss: 0.7178544998168945:  33%|███▎      | 8418/25880 [1:44:47<3:53:34,  1.25it/s]
1|8419|Loss: 0.908427357673645:  33%|███▎      | 8418/25880 [1:44:47<3:53:34,  1.25it/s] 
1|8419|Loss: 0.908427357673645:  33%|███▎      | 8419/25880 [1:44:48<3:52:27,  1.25it/s]
1|8420|Loss: 0.9387195110321045:  33%|███▎      | 8419/25880 [1:44:48<3:52:27,  1.25it/s]
1|8420|Loss: 0.9387195110321045:  33%|███▎      | 8420/25880 [1:44:48<3:35:51,  1.35it/s]
1|8421|Loss: 0.7531296610832214:  33%|███▎      | 8420/25880 [1:44:49<3:35:51,  1.35it/s]
1|8421|Loss: 0.7531296610832214:  33%|███▎      | 8421/25880 [1:44:49<3:12:37,  1.51it/s]
1|8422|Loss: 0.9120461940765381:  33%|███▎      | 8421/25880 [1:44:49<3:12:37,  1.51it/s]
1|8422|Loss: 0.9120461940765381:  33%|███▎      | 8422/25880 [1:44:49<3:13:26,  1.50it/s]
1|8423|Loss: 0.7354915142059326:  33%|███▎      | 8422/25880 [1:44:50<3:13:26,  1.50it/s]
1|8423|Loss: 0.7354915142059326:  33%|███▎      | 8423/25880 [1:44:50<3:29:28,  1.39it/s]
1|8424|Loss: 0.9554135799407959:  33%|███▎      | 8423/25880 [1:44:51<3:29:28,  1.39it/s]
1|8424|Loss: 0.9554135799407959:  33%|███▎      | 8424/25880 [1:44:51<3:22:54,  1.43it/s]
1|8425|Loss: 0.9017760753631592:  33%|███▎      | 8424/25880 [1:44:51<3:22:54,  1.43it/s]
1|8425|Loss: 0.9017760753631592:  33%|███▎      | 8425/25880 [1:44:52<3:29:55,  1.39it/s]
1|8426|Loss: 0.9352291226387024:  33%|███▎      | 8425/25880 [1:44:52<3:29:55,  1.39it/s]
1|8426|Loss: 0.9352291226387024:  33%|███▎      | 8426/25880 [1:44:53<3:40:42,  1.32it/s]
1|8427|Loss: 0.7719351053237915:  33%|███▎      | 8426/25880 [1:44:53<3:40:42,  1.32it/s]
1|8427|Loss: 0.7719351053237915:  33%|███▎      | 8427/25880 [1:44:53<3:41:55,  1.31it/s]
1|8428|Loss: 0.9484087228775024:  33%|███▎      | 8427/25880 [1:44:54<3:41:55,  1.31it/s]
1|8428|Loss: 0.9484087228775024:  33%|███▎      | 8428/25880 [1:44:54<3:40:59,  1.32it/s]
1|8429|Loss: 0.8807669281959534:  33%|███▎      | 8428/25880 [1:44:54<3:40:59,  1.32it/s]
1|8429|Loss: 0.8807669281959534:  33%|███▎      | 8429/25880 [1:44:55<3:37:17,  1.34it/s]
1|8430|Loss: 0.7425526976585388:  33%|███▎      | 8429/25880 [1:44:55<3:37:17,  1.34it/s]
1|8430|Loss: 0.7425526976585388:  33%|███▎      | 8430/25880 [1:44:56<3:43:37,  1.30it/s]
1|8431|Loss: 1.0372343063354492:  33%|███▎      | 8430/25880 [1:44:56<3:43:37,  1.30it/s]
1|8431|Loss: 1.0372343063354492:  33%|███▎      | 8431/25880 [1:44:56<3:35:05,  1.35it/s]
1|8432|Loss: 0.7878398299217224:  33%|███▎      | 8431/25880 [1:44:57<3:35:05,  1.35it/s]
1|8432|Loss: 0.7878398299217224:  33%|███▎      | 8432/25880 [1:44:57<3:32:01,  1.37it/s]
1|8433|Loss: 0.898552417755127:  33%|███▎      | 8432/25880 [1:44:57<3:32:01,  1.37it/s] 
1|8433|Loss: 0.898552417755127:  33%|███▎      | 8433/25880 [1:44:58<3:24:06,  1.42it/s]
1|8434|Loss: 0.75269615650177:  33%|███▎      | 8433/25880 [1:44:58<3:24:06,  1.42it/s] 
1|8434|Loss: 0.75269615650177:  33%|███▎      | 8434/25880 [1:44:58<3:31:48,  1.37it/s]
1|8435|Loss: 0.7897971868515015:  33%|███▎      | 8434/25880 [1:44:59<3:31:48,  1.37it/s]
1|8435|Loss: 0.7897971868515015:  33%|███▎      | 8435/25880 [1:44:59<3:44:02,  1.30it/s]
1|8436|Loss: 0.8657162189483643:  33%|███▎      | 8435/25880 [1:45:00<3:44:02,  1.30it/s]
1|8436|Loss: 0.8657162189483643:  33%|███▎      | 8436/25880 [1:45:00<3:34:00,  1.36it/s]
1|8437|Loss: 0.947329580783844:  33%|███▎      | 8436/25880 [1:45:00<3:34:00,  1.36it/s] 
1|8437|Loss: 0.947329580783844:  33%|███▎      | 8437/25880 [1:45:01<3:31:03,  1.38it/s]
1|8438|Loss: 0.9598990082740784:  33%|███▎      | 8437/25880 [1:45:01<3:31:03,  1.38it/s]
1|8438|Loss: 0.9598990082740784:  33%|███▎      | 8438/25880 [1:45:01<3:31:58,  1.37it/s]
1|8439|Loss: 1.0147299766540527:  33%|███▎      | 8438/25880 [1:45:02<3:31:58,  1.37it/s]
1|8439|Loss: 1.0147299766540527:  33%|███▎      | 8439/25880 [1:45:02<3:39:07,  1.33it/s]
1|8440|Loss: 0.9015895128250122:  33%|███▎      | 8439/25880 [1:45:03<3:39:07,  1.33it/s]
1|8440|Loss: 0.9015895128250122:  33%|███▎      | 8440/25880 [1:45:03<3:32:36,  1.37it/s]
1|8441|Loss: 0.8011479377746582:  33%|███▎      | 8440/25880 [1:45:03<3:32:36,  1.37it/s]
1|8441|Loss: 0.8011479377746582:  33%|███▎      | 8441/25880 [1:45:04<3:28:49,  1.39it/s]
1|8442|Loss: 0.838631808757782:  33%|███▎      | 8441/25880 [1:45:04<3:28:49,  1.39it/s] 
1|8442|Loss: 0.838631808757782:  33%|███▎      | 8442/25880 [1:45:04<3:15:04,  1.49it/s]
1|8443|Loss: 0.9194992184638977:  33%|███▎      | 8442/25880 [1:45:04<3:15:04,  1.49it/s]
1|8443|Loss: 0.9194992184638977:  33%|███▎      | 8443/25880 [1:45:05<3:16:37,  1.48it/s]
1|8444|Loss: 0.6970274448394775:  33%|███▎      | 8443/25880 [1:45:05<3:16:37,  1.48it/s]
1|8444|Loss: 0.6970274448394775:  33%|███▎      | 8444/25880 [1:45:05<3:01:52,  1.60it/s]
1|8445|Loss: 0.8017609119415283:  33%|███▎      | 8444/25880 [1:45:06<3:01:52,  1.60it/s]
1|8445|Loss: 0.8017609119415283:  33%|███▎      | 8445/25880 [1:45:06<3:12:35,  1.51it/s]
1|8446|Loss: 0.9692452549934387:  33%|███▎      | 8445/25880 [1:45:07<3:12:35,  1.51it/s]
1|8446|Loss: 0.9692452549934387:  33%|███▎      | 8446/25880 [1:45:07<3:32:40,  1.37it/s]
1|8447|Loss: 0.9451552033424377:  33%|███▎      | 8446/25880 [1:45:07<3:32:40,  1.37it/s]
1|8447|Loss: 0.9451552033424377:  33%|███▎      | 8447/25880 [1:45:08<3:46:12,  1.28it/s]
1|8448|Loss: 0.9076415300369263:  33%|███▎      | 8447/25880 [1:45:08<3:46:12,  1.28it/s]
1|8448|Loss: 0.9076415300369263:  33%|███▎      | 8448/25880 [1:45:09<3:53:26,  1.24it/s]
1|8449|Loss: 0.8601107597351074:  33%|███▎      | 8448/25880 [1:45:09<3:53:26,  1.24it/s]
1|8449|Loss: 0.8601107597351074:  33%|███▎      | 8449/25880 [1:45:09<3:34:09,  1.36it/s]
1|8450|Loss: 0.9159555435180664:  33%|███▎      | 8449/25880 [1:45:10<3:34:09,  1.36it/s]
1|8450|Loss: 0.9159555435180664:  33%|███▎      | 8450/25880 [1:45:10<3:46:17,  1.28it/s]
1|8451|Loss: 0.7850613594055176:  33%|███▎      | 8450/25880 [1:45:11<3:46:17,  1.28it/s]
1|8451|Loss: 0.7850613594055176:  33%|███▎      | 8451/25880 [1:45:11<3:46:17,  1.28it/s]
1|8452|Loss: 0.8591469526290894:  33%|███▎      | 8451/25880 [1:45:11<3:46:17,  1.28it/s]
1|8452|Loss: 0.8591469526290894:  33%|███▎      | 8452/25880 [1:45:12<3:42:57,  1.30it/s]
1|8453|Loss: 0.8906205296516418:  33%|███▎      | 8452/25880 [1:45:12<3:42:57,  1.30it/s]
1|8453|Loss: 0.8906205296516418:  33%|███▎      | 8453/25880 [1:45:12<3:45:22,  1.29it/s]
1|8454|Loss: 0.8212171196937561:  33%|███▎      | 8453/25880 [1:45:13<3:45:22,  1.29it/s]
1|8454|Loss: 0.8212171196937561:  33%|███▎      | 8454/25880 [1:45:14<4:43:34,  1.02it/s]
1|8455|Loss: 0.8407079577445984:  33%|███▎      | 8454/25880 [1:45:14<4:43:34,  1.02it/s]
1|8455|Loss: 0.8407079577445984:  33%|███▎      | 8455/25880 [1:45:15<4:35:49,  1.05it/s]
1|8456|Loss: 0.7958351373672485:  33%|███▎      | 8455/25880 [1:45:15<4:35:49,  1.05it/s]
1|8456|Loss: 0.7958351373672485:  33%|███▎      | 8456/25880 [1:45:16<4:21:58,  1.11it/s]
1|8457|Loss: 0.8798049092292786:  33%|███▎      | 8456/25880 [1:45:16<4:21:58,  1.11it/s]
1|8457|Loss: 0.8798049092292786:  33%|███▎      | 8457/25880 [1:45:16<4:06:26,  1.18it/s]
1|8458|Loss: 0.8210986852645874:  33%|███▎      | 8457/25880 [1:45:17<4:06:26,  1.18it/s]
1|8458|Loss: 0.8210986852645874:  33%|███▎      | 8458/25880 [1:45:17<3:40:21,  1.32it/s]
1|8459|Loss: 0.8767756223678589:  33%|███▎      | 8458/25880 [1:45:17<3:40:21,  1.32it/s]
1|8459|Loss: 0.8767756223678589:  33%|███▎      | 8459/25880 [1:45:18<3:34:46,  1.35it/s]
1|8460|Loss: 0.9249307513237:  33%|███▎      | 8459/25880 [1:45:18<3:34:46,  1.35it/s]   
1|8460|Loss: 0.9249307513237:  33%|███▎      | 8460/25880 [1:45:18<3:28:40,  1.39it/s]
1|8461|Loss: 1.0129390954971313:  33%|███▎      | 8460/25880 [1:45:19<3:28:40,  1.39it/s]
1|8461|Loss: 1.0129390954971313:  33%|███▎      | 8461/25880 [1:45:19<3:28:39,  1.39it/s]
1|8462|Loss: 0.8280125260353088:  33%|███▎      | 8461/25880 [1:45:19<3:28:39,  1.39it/s]
1|8462|Loss: 0.8280125260353088:  33%|███▎      | 8462/25880 [1:45:20<3:21:12,  1.44it/s]
1|8463|Loss: 0.9025717377662659:  33%|███▎      | 8462/25880 [1:45:20<3:21:12,  1.44it/s]
1|8463|Loss: 0.9025717377662659:  33%|███▎      | 8463/25880 [1:45:20<3:07:07,  1.55it/s]
1|8464|Loss: 0.8201420903205872:  33%|███▎      | 8463/25880 [1:45:20<3:07:07,  1.55it/s]
1|8464|Loss: 0.8201420903205872:  33%|███▎      | 8464/25880 [1:45:21<3:10:11,  1.53it/s]
1|8465|Loss: 0.8891826868057251:  33%|███▎      | 8464/25880 [1:45:21<3:10:11,  1.53it/s]
1|8465|Loss: 0.8891826868057251:  33%|███▎      | 8465/25880 [1:45:21<3:14:51,  1.49it/s]
1|8466|Loss: 0.8805882930755615:  33%|███▎      | 8465/25880 [1:45:22<3:14:51,  1.49it/s]
1|8466|Loss: 0.8805882930755615:  33%|███▎      | 8466/25880 [1:45:22<3:11:38,  1.51it/s]
1|8467|Loss: 0.7319110631942749:  33%|███▎      | 8466/25880 [1:45:23<3:11:38,  1.51it/s]
1|8467|Loss: 0.7319110631942749:  33%|███▎      | 8467/25880 [1:45:23<3:28:38,  1.39it/s]
1|8468|Loss: 0.7710320949554443:  33%|███▎      | 8467/25880 [1:45:23<3:28:38,  1.39it/s]
1|8468|Loss: 0.7710320949554443:  33%|███▎      | 8468/25880 [1:45:24<3:32:24,  1.37it/s]
1|8469|Loss: 0.7495173811912537:  33%|███▎      | 8468/25880 [1:45:24<3:32:24,  1.37it/s]
1|8469|Loss: 0.7495173811912537:  33%|███▎      | 8469/25880 [1:45:24<3:21:40,  1.44it/s]
1|8470|Loss: 0.7607830166816711:  33%|███▎      | 8469/25880 [1:45:25<3:21:40,  1.44it/s]
1|8470|Loss: 0.7607830166816711:  33%|███▎      | 8470/25880 [1:45:25<3:19:49,  1.45it/s]
1|8471|Loss: 0.8095194101333618:  33%|███▎      | 8470/25880 [1:45:25<3:19:49,  1.45it/s]
1|8471|Loss: 0.8095194101333618:  33%|███▎      | 8471/25880 [1:45:26<3:23:19,  1.43it/s]
1|8472|Loss: 0.8038673400878906:  33%|███▎      | 8471/25880 [1:45:26<3:23:19,  1.43it/s]
1|8472|Loss: 0.8038673400878906:  33%|███▎      | 8472/25880 [1:45:27<3:26:51,  1.40it/s]
1|8473|Loss: 0.8911953568458557:  33%|███▎      | 8472/25880 [1:45:27<3:26:51,  1.40it/s]
1|8473|Loss: 0.8911953568458557:  33%|███▎      | 8473/25880 [1:45:27<3:29:28,  1.38it/s]
1|8474|Loss: 0.8365956544876099:  33%|███▎      | 8473/25880 [1:45:28<3:29:28,  1.38it/s]
1|8474|Loss: 0.8365956544876099:  33%|███▎      | 8474/25880 [1:45:28<3:22:44,  1.43it/s]
1|8475|Loss: 0.7509031295776367:  33%|███▎      | 8474/25880 [1:45:28<3:22:44,  1.43it/s]
1|8475|Loss: 0.7509031295776367:  33%|███▎      | 8475/25880 [1:45:29<3:21:38,  1.44it/s]
1|8476|Loss: 0.9470439553260803:  33%|███▎      | 8475/25880 [1:45:29<3:21:38,  1.44it/s]
1|8476|Loss: 0.9470439553260803:  33%|███▎      | 8476/25880 [1:45:29<3:37:42,  1.33it/s]
1|8477|Loss: 0.8010773658752441:  33%|███▎      | 8476/25880 [1:45:30<3:37:42,  1.33it/s]
1|8477|Loss: 0.8010773658752441:  33%|███▎      | 8477/25880 [1:45:30<3:14:25,  1.49it/s]
1|8478|Loss: 0.9101080894470215:  33%|███▎      | 8477/25880 [1:45:30<3:14:25,  1.49it/s]
1|8478|Loss: 0.9101080894470215:  33%|███▎      | 8478/25880 [1:45:31<3:22:22,  1.43it/s]
1|8479|Loss: 0.8527064323425293:  33%|███▎      | 8478/25880 [1:45:31<3:22:22,  1.43it/s]
1|8479|Loss: 0.8527064323425293:  33%|███▎      | 8479/25880 [1:45:31<3:28:22,  1.39it/s]
1|8480|Loss: 0.7341020703315735:  33%|███▎      | 8479/25880 [1:45:32<3:28:22,  1.39it/s]
1|8480|Loss: 0.7341020703315735:  33%|███▎      | 8480/25880 [1:45:32<3:29:46,  1.38it/s]
1|8481|Loss: 0.8171321749687195:  33%|███▎      | 8480/25880 [1:45:33<3:29:46,  1.38it/s]
1|8481|Loss: 0.8171321749687195:  33%|███▎      | 8481/25880 [1:45:33<3:32:04,  1.37it/s]
1|8482|Loss: 0.6990740299224854:  33%|███▎      | 8481/25880 [1:45:33<3:32:04,  1.37it/s]
1|8482|Loss: 0.6990740299224854:  33%|███▎      | 8482/25880 [1:45:34<3:31:23,  1.37it/s]
1|8483|Loss: 0.8449326157569885:  33%|███▎      | 8482/25880 [1:45:34<3:31:23,  1.37it/s]
1|8483|Loss: 0.8449326157569885:  33%|███▎      | 8483/25880 [1:45:34<3:32:25,  1.36it/s]
1|8484|Loss: 0.7876679301261902:  33%|███▎      | 8483/25880 [1:45:35<3:32:25,  1.36it/s]
1|8484|Loss: 0.7876679301261902:  33%|███▎      | 8484/25880 [1:45:35<3:30:56,  1.37it/s]
1|8485|Loss: 0.8191941380500793:  33%|███▎      | 8484/25880 [1:45:36<3:30:56,  1.37it/s]
1|8485|Loss: 0.8191941380500793:  33%|███▎      | 8485/25880 [1:45:36<3:37:11,  1.33it/s]
1|8486|Loss: 0.8796394467353821:  33%|███▎      | 8485/25880 [1:45:36<3:37:11,  1.33it/s]
1|8486|Loss: 0.8796394467353821:  33%|███▎      | 8486/25880 [1:45:37<3:37:11,  1.33it/s]
1|8487|Loss: 0.7887680530548096:  33%|███▎      | 8486/25880 [1:45:37<3:37:11,  1.33it/s]
1|8487|Loss: 0.7887680530548096:  33%|███▎      | 8487/25880 [1:45:38<3:43:52,  1.29it/s]
1|8488|Loss: 0.9430803060531616:  33%|███▎      | 8487/25880 [1:45:38<3:43:52,  1.29it/s]
1|8488|Loss: 0.9430803060531616:  33%|███▎      | 8488/25880 [1:45:38<3:31:04,  1.37it/s]
1|8489|Loss: 0.9304547309875488:  33%|███▎      | 8488/25880 [1:45:38<3:31:04,  1.37it/s]
1|8489|Loss: 0.9304547309875488:  33%|███▎      | 8489/25880 [1:45:39<3:25:42,  1.41it/s]
1|8490|Loss: 0.8682995438575745:  33%|███▎      | 8489/25880 [1:45:39<3:25:42,  1.41it/s]
1|8490|Loss: 0.8682995438575745:  33%|███▎      | 8490/25880 [1:45:40<3:25:25,  1.41it/s]
1|8491|Loss: 0.7933838963508606:  33%|███▎      | 8490/25880 [1:45:40<3:25:25,  1.41it/s]
1|8491|Loss: 0.7933838963508606:  33%|███▎      | 8491/25880 [1:45:40<3:20:45,  1.44it/s]
1|8492|Loss: 1.004791021347046:  33%|███▎      | 8491/25880 [1:45:41<3:20:45,  1.44it/s] 
1|8492|Loss: 1.004791021347046:  33%|███▎      | 8492/25880 [1:45:41<3:14:17,  1.49it/s]
1|8493|Loss: 0.9666948914527893:  33%|███▎      | 8492/25880 [1:45:41<3:14:17,  1.49it/s]
1|8493|Loss: 0.9666948914527893:  33%|███▎      | 8493/25880 [1:45:42<3:31:15,  1.37it/s]
1|8494|Loss: 0.7653666734695435:  33%|███▎      | 8493/25880 [1:45:42<3:31:15,  1.37it/s]
1|8494|Loss: 0.7653666734695435:  33%|███▎      | 8494/25880 [1:45:42<3:20:44,  1.44it/s]
1|8495|Loss: 0.8565526604652405:  33%|███▎      | 8494/25880 [1:45:43<3:20:44,  1.44it/s]
1|8495|Loss: 0.8565526604652405:  33%|███▎      | 8495/25880 [1:45:43<3:18:40,  1.46it/s]
1|8496|Loss: 0.7418463826179504:  33%|███▎      | 8495/25880 [1:45:43<3:18:40,  1.46it/s]
1|8496|Loss: 0.7418463826179504:  33%|███▎      | 8496/25880 [1:45:44<3:31:54,  1.37it/s]
1|8497|Loss: 0.9208123087882996:  33%|███▎      | 8496/25880 [1:45:44<3:31:54,  1.37it/s]
1|8497|Loss: 0.9208123087882996:  33%|███▎      | 8497/25880 [1:45:45<3:41:39,  1.31it/s]
1|8498|Loss: 0.9385195374488831:  33%|███▎      | 8497/25880 [1:45:45<3:41:39,  1.31it/s]
1|8498|Loss: 0.9385195374488831:  33%|███▎      | 8498/25880 [1:45:45<3:41:07,  1.31it/s]
1|8499|Loss: 0.9519753456115723:  33%|███▎      | 8498/25880 [1:45:46<3:41:07,  1.31it/s]
1|8499|Loss: 0.9519753456115723:  33%|███▎      | 8499/25880 [1:45:46<3:36:36,  1.34it/s]
1|8500|Loss: 0.7801671624183655:  33%|███▎      | 8499/25880 [1:45:46<3:36:36,  1.34it/s]
1|8500|Loss: 0.7801671624183655:  33%|███▎      | 8500/25880 [1:45:47<3:38:25,  1.33it/s]
1|8501|Loss: 0.9981234073638916:  33%|███▎      | 8500/25880 [1:45:47<3:38:25,  1.33it/s]
1|8501|Loss: 0.9981234073638916:  33%|███▎      | 8501/25880 [1:45:47<3:24:19,  1.42it/s]
1|8502|Loss: 0.864923894405365:  33%|███▎      | 8501/25880 [1:45:48<3:24:19,  1.42it/s] 
1|8502|Loss: 0.864923894405365:  33%|███▎      | 8502/25880 [1:45:48<3:27:10,  1.40it/s]
1|8503|Loss: 0.8699764013290405:  33%|███▎      | 8502/25880 [1:45:49<3:27:10,  1.40it/s]
1|8503|Loss: 0.8699764013290405:  33%|███▎      | 8503/25880 [1:45:49<3:23:40,  1.42it/s]
1|8504|Loss: 0.8789235949516296:  33%|███▎      | 8503/25880 [1:45:49<3:23:40,  1.42it/s]
1|8504|Loss: 0.8789235949516296:  33%|███▎      | 8504/25880 [1:45:50<3:31:15,  1.37it/s]
1|8505|Loss: 0.7137618660926819:  33%|███▎      | 8504/25880 [1:45:50<3:31:15,  1.37it/s]
1|8505|Loss: 0.7137618660926819:  33%|███▎      | 8505/25880 [1:45:50<3:41:12,  1.31it/s]
1|8506|Loss: 0.8788670897483826:  33%|███▎      | 8505/25880 [1:45:51<3:41:12,  1.31it/s]
1|8506|Loss: 0.8788670897483826:  33%|███▎      | 8506/25880 [1:45:51<3:32:53,  1.36it/s]
1|8507|Loss: 0.8701732754707336:  33%|███▎      | 8506/25880 [1:45:52<3:32:53,  1.36it/s]
1|8507|Loss: 0.8701732754707336:  33%|███▎      | 8507/25880 [1:45:52<3:30:03,  1.38it/s]
1|8508|Loss: 0.8934505581855774:  33%|███▎      | 8507/25880 [1:45:52<3:30:03,  1.38it/s]
1|8508|Loss: 0.8934505581855774:  33%|███▎      | 8508/25880 [1:45:52<3:22:28,  1.43it/s]
1|8509|Loss: 0.942078173160553:  33%|███▎      | 8508/25880 [1:45:53<3:22:28,  1.43it/s] 
1|8509|Loss: 0.942078173160553:  33%|███▎      | 8509/25880 [1:45:53<3:23:40,  1.42it/s]
1|8510|Loss: 0.7167596817016602:  33%|███▎      | 8509/25880 [1:45:54<3:23:40,  1.42it/s]
1|8510|Loss: 0.7167596817016602:  33%|███▎      | 8510/25880 [1:45:54<3:17:38,  1.46it/s]
1|8511|Loss: 0.7903233170509338:  33%|███▎      | 8510/25880 [1:45:54<3:17:38,  1.46it/s]
1|8511|Loss: 0.7903233170509338:  33%|███▎      | 8511/25880 [1:45:54<3:13:29,  1.50it/s]
1|8512|Loss: 0.8688504099845886:  33%|███▎      | 8511/25880 [1:45:55<3:13:29,  1.50it/s]
1|8512|Loss: 0.8688504099845886:  33%|███▎      | 8512/25880 [1:45:55<3:17:40,  1.46it/s]
1|8513|Loss: 0.8224145174026489:  33%|███▎      | 8512/25880 [1:45:56<3:17:40,  1.46it/s]
1|8513|Loss: 0.8224145174026489:  33%|███▎      | 8513/25880 [1:45:56<3:19:33,  1.45it/s]
1|8514|Loss: 0.7485825419425964:  33%|███▎      | 8513/25880 [1:45:56<3:19:33,  1.45it/s]
1|8514|Loss: 0.7485825419425964:  33%|███▎      | 8514/25880 [1:45:57<3:14:35,  1.49it/s]
1|8515|Loss: 0.8820506930351257:  33%|███▎      | 8514/25880 [1:45:57<3:14:35,  1.49it/s]
1|8515|Loss: 0.8820506930351257:  33%|███▎      | 8515/25880 [1:45:57<3:19:00,  1.45it/s]
1|8516|Loss: 0.8348331451416016:  33%|███▎      | 8515/25880 [1:45:58<3:19:00,  1.45it/s]
1|8516|Loss: 0.8348331451416016:  33%|███▎      | 8516/25880 [1:45:58<3:29:10,  1.38it/s]
1|8517|Loss: 0.8177285194396973:  33%|███▎      | 8516/25880 [1:45:59<3:29:10,  1.38it/s]
1|8517|Loss: 0.8177285194396973:  33%|███▎      | 8517/25880 [1:45:59<3:40:16,  1.31it/s]
1|8518|Loss: 0.7885552048683167:  33%|███▎      | 8517/25880 [1:45:59<3:40:16,  1.31it/s]
1|8518|Loss: 0.7885552048683167:  33%|███▎      | 8518/25880 [1:46:00<3:40:02,  1.32it/s]
1|8519|Loss: 0.9409481287002563:  33%|███▎      | 8518/25880 [1:46:00<3:40:02,  1.32it/s]
1|8519|Loss: 0.9409481287002563:  33%|███▎      | 8519/25880 [1:46:00<3:22:07,  1.43it/s]
1|8520|Loss: 0.8605020046234131:  33%|███▎      | 8519/25880 [1:46:01<3:22:07,  1.43it/s]
1|8520|Loss: 0.8605020046234131:  33%|███▎      | 8520/25880 [1:46:01<3:21:10,  1.44it/s]
1|8521|Loss: 0.906522810459137:  33%|███▎      | 8520/25880 [1:46:01<3:21:10,  1.44it/s] 
1|8521|Loss: 0.906522810459137:  33%|███▎      | 8521/25880 [1:46:02<3:13:43,  1.49it/s]
1|8522|Loss: 0.839515745639801:  33%|███▎      | 8521/25880 [1:46:02<3:13:43,  1.49it/s]
1|8522|Loss: 0.839515745639801:  33%|███▎      | 8522/25880 [1:46:02<3:21:46,  1.43it/s]
1|8523|Loss: 0.695293128490448:  33%|███▎      | 8522/25880 [1:46:03<3:21:46,  1.43it/s]
1|8523|Loss: 0.695293128490448:  33%|███▎      | 8523/25880 [1:46:03<3:41:33,  1.31it/s]
1|8524|Loss: 0.989556610584259:  33%|███▎      | 8523/25880 [1:46:04<3:41:33,  1.31it/s]
1|8524|Loss: 0.989556610584259:  33%|███▎      | 8524/25880 [1:46:04<3:42:24,  1.30it/s]
1|8525|Loss: 0.7754760384559631:  33%|███▎      | 8524/25880 [1:46:04<3:42:24,  1.30it/s]
1|8525|Loss: 0.7754760384559631:  33%|███▎      | 8525/25880 [1:46:05<3:52:04,  1.25it/s]
1|8526|Loss: 0.7491377592086792:  33%|███▎      | 8525/25880 [1:46:05<3:52:04,  1.25it/s]
1|8526|Loss: 0.7491377592086792:  33%|███▎      | 8526/25880 [1:46:06<3:59:51,  1.21it/s]
1|8527|Loss: 0.7536177635192871:  33%|███▎      | 8526/25880 [1:46:06<3:59:51,  1.21it/s]
1|8527|Loss: 0.7536177635192871:  33%|███▎      | 8527/25880 [1:46:06<3:45:04,  1.29it/s]
1|8528|Loss: 0.7808401584625244:  33%|███▎      | 8527/25880 [1:46:07<3:45:04,  1.29it/s]
1|8528|Loss: 0.7808401584625244:  33%|███▎      | 8528/25880 [1:46:07<3:41:53,  1.30it/s]
1|8529|Loss: 0.7653681635856628:  33%|███▎      | 8528/25880 [1:46:08<3:41:53,  1.30it/s]
1|8529|Loss: 0.7653681635856628:  33%|███▎      | 8529/25880 [1:46:08<3:52:59,  1.24it/s]
1|8530|Loss: 0.7143251299858093:  33%|███▎      | 8529/25880 [1:46:09<3:52:59,  1.24it/s]
1|8530|Loss: 0.7143251299858093:  33%|███▎      | 8530/25880 [1:46:09<3:58:14,  1.21it/s]
1|8531|Loss: 0.6878158450126648:  33%|███▎      | 8530/25880 [1:46:09<3:58:14,  1.21it/s]
1|8531|Loss: 0.6878158450126648:  33%|███▎      | 8531/25880 [1:46:10<3:59:30,  1.21it/s]
1|8532|Loss: 0.8905802369117737:  33%|███▎      | 8531/25880 [1:46:10<3:59:30,  1.21it/s]
1|8532|Loss: 0.8905802369117737:  33%|███▎      | 8532/25880 [1:46:11<3:53:16,  1.24it/s]
1|8533|Loss: 0.8208499550819397:  33%|███▎      | 8532/25880 [1:46:11<3:53:16,  1.24it/s]
1|8533|Loss: 0.8208499550819397:  33%|███▎      | 8533/25880 [1:46:11<3:52:13,  1.24it/s]
1|8534|Loss: 0.7909654974937439:  33%|███▎      | 8533/25880 [1:46:12<3:52:13,  1.24it/s]
1|8534|Loss: 0.7909654974937439:  33%|███▎      | 8534/25880 [1:46:12<3:27:56,  1.39it/s]
1|8535|Loss: 0.9903298020362854:  33%|███▎      | 8534/25880 [1:46:12<3:27:56,  1.39it/s]
1|8535|Loss: 0.9903298020362854:  33%|███▎      | 8535/25880 [1:46:13<3:24:39,  1.41it/s]
1|8536|Loss: 0.9384984970092773:  33%|███▎      | 8535/25880 [1:46:13<3:24:39,  1.41it/s]
1|8536|Loss: 0.9384984970092773:  33%|███▎      | 8536/25880 [1:46:13<3:18:02,  1.46it/s]
1|8537|Loss: 0.8612828254699707:  33%|███▎      | 8536/25880 [1:46:14<3:18:02,  1.46it/s]
1|8537|Loss: 0.8612828254699707:  33%|███▎      | 8537/25880 [1:46:14<3:16:58,  1.47it/s]
1|8538|Loss: 0.9831055998802185:  33%|███▎      | 8537/25880 [1:46:14<3:16:58,  1.47it/s]
1|8538|Loss: 0.9831055998802185:  33%|███▎      | 8538/25880 [1:46:14<3:05:20,  1.56it/s]
1|8539|Loss: 0.8949357867240906:  33%|███▎      | 8538/25880 [1:46:15<3:05:20,  1.56it/s]
1|8539|Loss: 0.8949357867240906:  33%|███▎      | 8539/25880 [1:46:15<2:54:46,  1.65it/s]
1|8540|Loss: 0.7971166372299194:  33%|███▎      | 8539/25880 [1:46:15<2:54:46,  1.65it/s]
1|8540|Loss: 0.7971166372299194:  33%|███▎      | 8540/25880 [1:46:15<2:51:52,  1.68it/s]
1|8541|Loss: 0.8387901186943054:  33%|███▎      | 8540/25880 [1:46:16<2:51:52,  1.68it/s]
1|8541|Loss: 0.8387901186943054:  33%|███▎      | 8541/25880 [1:46:16<3:08:03,  1.54it/s]
1|8542|Loss: 0.7722716927528381:  33%|███▎      | 8541/25880 [1:46:17<3:08:03,  1.54it/s]
1|8542|Loss: 0.7722716927528381:  33%|███▎      | 8542/25880 [1:46:17<3:16:26,  1.47it/s]
1|8543|Loss: 0.9071892499923706:  33%|███▎      | 8542/25880 [1:46:17<3:16:26,  1.47it/s]
1|8543|Loss: 0.9071892499923706:  33%|███▎      | 8543/25880 [1:46:18<3:04:50,  1.56it/s]
1|8544|Loss: 0.9122224450111389:  33%|███▎      | 8543/25880 [1:46:18<3:04:50,  1.56it/s]
1|8544|Loss: 0.9122224450111389:  33%|███▎      | 8544/25880 [1:46:18<3:06:53,  1.55it/s]
1|8545|Loss: 0.7637712359428406:  33%|███▎      | 8544/25880 [1:46:19<3:06:53,  1.55it/s]
1|8545|Loss: 0.7637712359428406:  33%|███▎      | 8545/25880 [1:46:19<3:13:28,  1.49it/s]
1|8546|Loss: 0.8828040361404419:  33%|███▎      | 8545/25880 [1:46:19<3:13:28,  1.49it/s]
1|8546|Loss: 0.8828040361404419:  33%|███▎      | 8546/25880 [1:46:20<3:18:09,  1.46it/s]
1|8547|Loss: 0.835321843624115:  33%|███▎      | 8546/25880 [1:46:20<3:18:09,  1.46it/s] 
1|8547|Loss: 0.835321843624115:  33%|███▎      | 8547/25880 [1:46:20<3:28:46,  1.38it/s]
1|8548|Loss: 0.897401750087738:  33%|███▎      | 8547/25880 [1:46:21<3:28:46,  1.38it/s]
1|8548|Loss: 0.897401750087738:  33%|███▎      | 8548/25880 [1:46:21<3:31:46,  1.36it/s]
1|8549|Loss: 0.9127704501152039:  33%|███▎      | 8548/25880 [1:46:22<3:31:46,  1.36it/s]
1|8549|Loss: 0.9127704501152039:  33%|███▎      | 8549/25880 [1:46:22<3:37:31,  1.33it/s]
1|8550|Loss: 0.8733816742897034:  33%|███▎      | 8549/25880 [1:46:22<3:37:31,  1.33it/s]
1|8550|Loss: 0.8733816742897034:  33%|███▎      | 8550/25880 [1:46:23<3:37:03,  1.33it/s]
1|8551|Loss: 0.8801771402359009:  33%|███▎      | 8550/25880 [1:46:23<3:37:03,  1.33it/s]
1|8551|Loss: 0.8801771402359009:  33%|███▎      | 8551/25880 [1:46:23<3:25:10,  1.41it/s]
1|8552|Loss: 0.856412410736084:  33%|███▎      | 8551/25880 [1:46:24<3:25:10,  1.41it/s] 
1|8552|Loss: 0.856412410736084:  33%|███▎      | 8552/25880 [1:46:24<3:37:08,  1.33it/s]
1|8553|Loss: 0.914526104927063:  33%|███▎      | 8552/25880 [1:46:25<3:37:08,  1.33it/s]
1|8553|Loss: 0.914526104927063:  33%|███▎      | 8553/25880 [1:46:25<3:32:05,  1.36it/s]
1|8554|Loss: 0.9106242060661316:  33%|███▎      | 8553/25880 [1:46:25<3:32:05,  1.36it/s]
1|8554|Loss: 0.9106242060661316:  33%|███▎      | 8554/25880 [1:46:26<3:22:26,  1.43it/s]
1|8555|Loss: 0.7750264406204224:  33%|███▎      | 8554/25880 [1:46:26<3:22:26,  1.43it/s]
1|8555|Loss: 0.7750264406204224:  33%|███▎      | 8555/25880 [1:46:26<3:07:36,  1.54it/s]
1|8556|Loss: 0.9056355357170105:  33%|███▎      | 8555/25880 [1:46:26<3:07:36,  1.54it/s]
1|8556|Loss: 0.9056355357170105:  33%|███▎      | 8556/25880 [1:46:27<3:08:44,  1.53it/s]
1|8557|Loss: 1.0836938619613647:  33%|███▎      | 8556/25880 [1:46:27<3:08:44,  1.53it/s]
1|8557|Loss: 1.0836938619613647:  33%|███▎      | 8557/25880 [1:46:27<3:14:44,  1.48it/s]
1|8558|Loss: 0.9088546633720398:  33%|███▎      | 8557/25880 [1:46:28<3:14:44,  1.48it/s]
1|8558|Loss: 0.9088546633720398:  33%|███▎      | 8558/25880 [1:46:28<3:05:23,  1.56it/s]
1|8559|Loss: 0.7963460087776184:  33%|███▎      | 8558/25880 [1:46:28<3:05:23,  1.56it/s]
1|8559|Loss: 0.7963460087776184:  33%|███▎      | 8559/25880 [1:46:29<3:03:06,  1.58it/s]
1|8560|Loss: 0.8611906170845032:  33%|███▎      | 8559/25880 [1:46:29<3:03:06,  1.58it/s]
1|8560|Loss: 0.8611906170845032:  33%|███▎      | 8560/25880 [1:46:29<3:18:01,  1.46it/s]
1|8561|Loss: 0.891704797744751:  33%|███▎      | 8560/25880 [1:46:30<3:18:01,  1.46it/s] 
1|8561|Loss: 0.891704797744751:  33%|███▎      | 8561/25880 [1:46:30<3:16:33,  1.47it/s]
1|8562|Loss: 0.8205600380897522:  33%|███▎      | 8561/25880 [1:46:30<3:16:33,  1.47it/s]
1|8562|Loss: 0.8205600380897522:  33%|███▎      | 8562/25880 [1:46:31<3:19:56,  1.44it/s]
1|8563|Loss: 0.9719244241714478:  33%|███▎      | 8562/25880 [1:46:31<3:19:56,  1.44it/s]
1|8563|Loss: 0.9719244241714478:  33%|███▎      | 8563/25880 [1:46:31<3:15:56,  1.47it/s]
1|8564|Loss: 0.7912503480911255:  33%|███▎      | 8563/25880 [1:46:32<3:15:56,  1.47it/s]
1|8564|Loss: 0.7912503480911255:  33%|███▎      | 8564/25880 [1:46:32<3:29:17,  1.38it/s]
1|8565|Loss: 0.8597078323364258:  33%|███▎      | 8564/25880 [1:46:33<3:29:17,  1.38it/s]
1|8565|Loss: 0.8597078323364258:  33%|███▎      | 8565/25880 [1:46:33<3:32:30,  1.36it/s]
1|8566|Loss: 0.7907251715660095:  33%|███▎      | 8565/25880 [1:46:34<3:32:30,  1.36it/s]
1|8566|Loss: 0.7907251715660095:  33%|███▎      | 8566/25880 [1:46:34<3:50:41,  1.25it/s]
1|8567|Loss: 0.7737810611724854:  33%|███▎      | 8566/25880 [1:46:34<3:50:41,  1.25it/s]
1|8567|Loss: 0.7737810611724854:  33%|███▎      | 8567/25880 [1:46:35<3:50:18,  1.25it/s]
1|8568|Loss: 0.7647784352302551:  33%|███▎      | 8567/25880 [1:46:35<3:50:18,  1.25it/s]
1|8568|Loss: 0.7647784352302551:  33%|███▎      | 8568/25880 [1:46:35<3:38:08,  1.32it/s]
1|8569|Loss: 0.6850795745849609:  33%|███▎      | 8568/25880 [1:46:36<3:38:08,  1.32it/s]
1|8569|Loss: 0.6850795745849609:  33%|███▎      | 8569/25880 [1:46:36<3:47:39,  1.27it/s]
1|8570|Loss: 0.9586274027824402:  33%|███▎      | 8569/25880 [1:46:37<3:47:39,  1.27it/s]
1|8570|Loss: 0.9586274027824402:  33%|███▎      | 8570/25880 [1:46:37<3:38:13,  1.32it/s]
1|8571|Loss: 0.8501079082489014:  33%|███▎      | 8570/25880 [1:46:37<3:38:13,  1.32it/s]
1|8571|Loss: 0.8501079082489014:  33%|███▎      | 8571/25880 [1:46:38<3:31:26,  1.36it/s]
1|8572|Loss: 0.9452183842658997:  33%|███▎      | 8571/25880 [1:46:38<3:31:26,  1.36it/s]
1|8572|Loss: 0.9452183842658997:  33%|███▎      | 8572/25880 [1:46:38<3:20:09,  1.44it/s]
1|8573|Loss: 0.8079537153244019:  33%|███▎      | 8572/25880 [1:46:39<3:20:09,  1.44it/s]
1|8573|Loss: 0.8079537153244019:  33%|███▎      | 8573/25880 [1:46:39<3:08:40,  1.53it/s]
1|8574|Loss: 0.8488829135894775:  33%|███▎      | 8573/25880 [1:46:39<3:08:40,  1.53it/s]
1|8574|Loss: 0.8488829135894775:  33%|███▎      | 8574/25880 [1:46:40<3:17:13,  1.46it/s]
1|8575|Loss: 0.7139528393745422:  33%|███▎      | 8574/25880 [1:46:40<3:17:13,  1.46it/s]
1|8575|Loss: 0.7139528393745422:  33%|███▎      | 8575/25880 [1:46:40<3:22:13,  1.43it/s]
1|8576|Loss: 0.7246712446212769:  33%|███▎      | 8575/25880 [1:46:41<3:22:13,  1.43it/s]
1|8576|Loss: 0.7246712446212769:  33%|███▎      | 8576/25880 [1:46:41<3:28:20,  1.38it/s]
1|8577|Loss: 0.8898517489433289:  33%|███▎      | 8576/25880 [1:46:42<3:28:20,  1.38it/s]
1|8577|Loss: 0.8898517489433289:  33%|███▎      | 8577/25880 [1:46:42<3:27:57,  1.39it/s]
1|8578|Loss: 1.0774041414260864:  33%|███▎      | 8577/25880 [1:46:42<3:27:57,  1.39it/s]
1|8578|Loss: 1.0774041414260864:  33%|███▎      | 8578/25880 [1:46:42<3:20:11,  1.44it/s]
1|8579|Loss: 0.9493305683135986:  33%|███▎      | 8578/25880 [1:46:43<3:20:11,  1.44it/s]
1|8579|Loss: 0.9493305683135986:  33%|███▎      | 8579/25880 [1:46:43<3:32:00,  1.36it/s]
1|8580|Loss: 0.9819367527961731:  33%|███▎      | 8579/25880 [1:46:44<3:32:00,  1.36it/s]
1|8580|Loss: 0.9819367527961731:  33%|███▎      | 8580/25880 [1:46:44<3:41:26,  1.30it/s]
1|8581|Loss: 0.8927504420280457:  33%|███▎      | 8580/25880 [1:46:45<3:41:26,  1.30it/s]
1|8581|Loss: 0.8927504420280457:  33%|███▎      | 8581/25880 [1:46:45<3:44:50,  1.28it/s]
1|8582|Loss: 0.8747479915618896:  33%|███▎      | 8581/25880 [1:46:45<3:44:50,  1.28it/s]
1|8582|Loss: 0.8747479915618896:  33%|███▎      | 8582/25880 [1:46:46<3:42:01,  1.30it/s]
1|8583|Loss: 0.8742085695266724:  33%|███▎      | 8582/25880 [1:46:46<3:42:01,  1.30it/s]
1|8583|Loss: 0.8742085695266724:  33%|███▎      | 8583/25880 [1:46:47<3:45:05,  1.28it/s]
1|8584|Loss: 0.9331327080726624:  33%|███▎      | 8583/25880 [1:46:47<3:45:05,  1.28it/s]
1|8584|Loss: 0.9331327080726624:  33%|███▎      | 8584/25880 [1:46:47<3:36:07,  1.33it/s]
1|8585|Loss: 0.8496763706207275:  33%|███▎      | 8584/25880 [1:46:48<3:36:07,  1.33it/s]
1|8585|Loss: 0.8496763706207275:  33%|███▎      | 8585/25880 [1:46:48<3:30:57,  1.37it/s]
1|8586|Loss: 0.8315646648406982:  33%|███▎      | 8585/25880 [1:46:48<3:30:57,  1.37it/s]
1|8586|Loss: 0.8315646648406982:  33%|███▎      | 8586/25880 [1:46:48<3:17:57,  1.46it/s]
1|8587|Loss: 0.7273924946784973:  33%|███▎      | 8586/25880 [1:46:49<3:17:57,  1.46it/s]
1|8587|Loss: 0.7273924946784973:  33%|███▎      | 8587/25880 [1:46:49<3:26:53,  1.39it/s]
1|8588|Loss: 0.8002881407737732:  33%|███▎      | 8587/25880 [1:46:50<3:26:53,  1.39it/s]
1|8588|Loss: 0.8002881407737732:  33%|███▎      | 8588/25880 [1:46:50<3:43:12,  1.29it/s]
1|8589|Loss: 0.898591160774231:  33%|███▎      | 8588/25880 [1:46:51<3:43:12,  1.29it/s] 
1|8589|Loss: 0.898591160774231:  33%|███▎      | 8589/25880 [1:46:51<3:40:15,  1.31it/s]
1|8590|Loss: 0.9597578048706055:  33%|███▎      | 8589/25880 [1:46:51<3:40:15,  1.31it/s]
1|8590|Loss: 0.9597578048706055:  33%|███▎      | 8590/25880 [1:46:51<3:17:22,  1.46it/s]
1|8591|Loss: 0.7504745721817017:  33%|███▎      | 8590/25880 [1:46:52<3:17:22,  1.46it/s]
1|8591|Loss: 0.7504745721817017:  33%|███▎      | 8591/25880 [1:46:52<3:05:51,  1.55it/s]
1|8592|Loss: 0.8717147707939148:  33%|███▎      | 8591/25880 [1:46:52<3:05:51,  1.55it/s]
1|8592|Loss: 0.8717147707939148:  33%|███▎      | 8592/25880 [1:46:53<3:02:57,  1.57it/s]
1|8593|Loss: 0.6848118305206299:  33%|███▎      | 8592/25880 [1:46:53<3:02:57,  1.57it/s]
1|8593|Loss: 0.6848118305206299:  33%|███▎      | 8593/25880 [1:46:53<3:27:41,  1.39it/s]
1|8594|Loss: 0.8813856840133667:  33%|███▎      | 8593/25880 [1:46:54<3:27:41,  1.39it/s]
1|8594|Loss: 0.8813856840133667:  33%|███▎      | 8594/25880 [1:46:54<3:27:43,  1.39it/s]
1|8595|Loss: 0.8661612868309021:  33%|███▎      | 8594/25880 [1:46:55<3:27:43,  1.39it/s]
1|8595|Loss: 0.8661612868309021:  33%|███▎      | 8595/25880 [1:46:55<3:13:18,  1.49it/s]
1|8596|Loss: 0.8683724999427795:  33%|███▎      | 8595/25880 [1:46:55<3:13:18,  1.49it/s]
1|8596|Loss: 0.8683724999427795:  33%|███▎      | 8596/25880 [1:46:56<3:23:58,  1.41it/s]
1|8597|Loss: 0.9318162202835083:  33%|███▎      | 8596/25880 [1:46:56<3:23:58,  1.41it/s]
1|8597|Loss: 0.9318162202835083:  33%|███▎      | 8597/25880 [1:46:56<3:28:09,  1.38it/s]
1|8598|Loss: 0.8691211938858032:  33%|███▎      | 8597/25880 [1:46:57<3:28:09,  1.38it/s]
1|8598|Loss: 0.8691211938858032:  33%|███▎      | 8598/25880 [1:46:57<3:33:28,  1.35it/s]
1|8599|Loss: 0.8630852103233337:  33%|███▎      | 8598/25880 [1:46:58<3:33:28,  1.35it/s]
1|8599|Loss: 0.8630852103233337:  33%|███▎      | 8599/25880 [1:46:58<3:40:35,  1.31it/s]
1|8600|Loss: 0.8534173369407654:  33%|███▎      | 8599/25880 [1:46:58<3:40:35,  1.31it/s]
1|8600|Loss: 0.8534173369407654:  33%|███▎      | 8600/25880 [1:46:59<3:49:36,  1.25it/s]
1|8601|Loss: 0.834304690361023:  33%|███▎      | 8600/25880 [1:46:59<3:49:36,  1.25it/s] 
1|8601|Loss: 0.834304690361023:  33%|███▎      | 8601/25880 [1:47:00<3:54:17,  1.23it/s]
1|8602|Loss: 0.9767166972160339:  33%|███▎      | 8601/25880 [1:47:00<3:54:17,  1.23it/s]
1|8602|Loss: 0.9767166972160339:  33%|███▎      | 8602/25880 [1:47:00<3:46:55,  1.27it/s]
1|8603|Loss: 0.6884257793426514:  33%|███▎      | 8602/25880 [1:47:01<3:46:55,  1.27it/s]
1|8603|Loss: 0.6884257793426514:  33%|███▎      | 8603/25880 [1:47:01<3:42:34,  1.29it/s]
1|8604|Loss: 0.7881622314453125:  33%|███▎      | 8603/25880 [1:47:02<3:42:34,  1.29it/s]
1|8604|Loss: 0.7881622314453125:  33%|███▎      | 8604/25880 [1:47:02<3:40:46,  1.30it/s]
1|8605|Loss: 0.912937343120575:  33%|███▎      | 8604/25880 [1:47:02<3:40:46,  1.30it/s] 
1|8605|Loss: 0.912937343120575:  33%|███▎      | 8605/25880 [1:47:03<3:38:08,  1.32it/s]
1|8606|Loss: 0.914033830165863:  33%|███▎      | 8605/25880 [1:47:03<3:38:08,  1.32it/s]
1|8606|Loss: 0.914033830165863:  33%|███▎      | 8606/25880 [1:47:03<3:28:51,  1.38it/s]
1|8607|Loss: 0.8685792088508606:  33%|███▎      | 8606/25880 [1:47:04<3:28:51,  1.38it/s]
1|8607|Loss: 0.8685792088508606:  33%|███▎      | 8607/25880 [1:47:04<3:35:26,  1.34it/s]
1|8608|Loss: 0.934969961643219:  33%|███▎      | 8607/25880 [1:47:04<3:35:26,  1.34it/s] 
1|8608|Loss: 0.934969961643219:  33%|███▎      | 8608/25880 [1:47:05<3:40:34,  1.31it/s]
1|8609|Loss: 0.7917054295539856:  33%|███▎      | 8608/25880 [1:47:05<3:40:34,  1.31it/s]
1|8609|Loss: 0.7917054295539856:  33%|███▎      | 8609/25880 [1:47:06<3:32:25,  1.36it/s]
1|8610|Loss: 0.8340321183204651:  33%|███▎      | 8609/25880 [1:47:06<3:32:25,  1.36it/s]
1|8610|Loss: 0.8340321183204651:  33%|███▎      | 8610/25880 [1:47:06<3:24:24,  1.41it/s]
1|8611|Loss: 0.8920281529426575:  33%|███▎      | 8610/25880 [1:47:07<3:24:24,  1.41it/s]
1|8611|Loss: 0.8920281529426575:  33%|███▎      | 8611/25880 [1:47:07<3:18:14,  1.45it/s]
1|8612|Loss: 0.7880846858024597:  33%|███▎      | 8611/25880 [1:47:07<3:18:14,  1.45it/s]
1|8612|Loss: 0.7880846858024597:  33%|███▎      | 8612/25880 [1:47:07<3:11:55,  1.50it/s]
1|8613|Loss: 0.709327757358551:  33%|███▎      | 8612/25880 [1:47:08<3:11:55,  1.50it/s] 
1|8613|Loss: 0.709327757358551:  33%|███▎      | 8613/25880 [1:47:08<3:08:25,  1.53it/s]
1|8614|Loss: 0.8113160133361816:  33%|███▎      | 8613/25880 [1:47:08<3:08:25,  1.53it/s]
1|8614|Loss: 0.8113160133361816:  33%|███▎      | 8614/25880 [1:47:09<2:54:33,  1.65it/s]
1|8615|Loss: 0.6611147522926331:  33%|███▎      | 8614/25880 [1:47:09<2:54:33,  1.65it/s]
1|8615|Loss: 0.6611147522926331:  33%|███▎      | 8615/25880 [1:47:09<3:09:21,  1.52it/s]
1|8616|Loss: 0.8265736103057861:  33%|███▎      | 8615/25880 [1:47:10<3:09:21,  1.52it/s]
1|8616|Loss: 0.8265736103057861:  33%|███▎      | 8616/25880 [1:47:10<3:03:18,  1.57it/s]
1|8617|Loss: 0.9519131183624268:  33%|███▎      | 8616/25880 [1:47:10<3:03:18,  1.57it/s]
1|8617|Loss: 0.9519131183624268:  33%|███▎      | 8617/25880 [1:47:11<3:05:39,  1.55it/s]
1|8618|Loss: 0.6722629070281982:  33%|███▎      | 8617/25880 [1:47:11<3:05:39,  1.55it/s]
1|8618|Loss: 0.6722629070281982:  33%|███▎      | 8618/25880 [1:47:11<3:10:21,  1.51it/s]
1|8619|Loss: 0.8735740184783936:  33%|███▎      | 8618/25880 [1:47:12<3:10:21,  1.51it/s]
1|8619|Loss: 0.8735740184783936:  33%|███▎      | 8619/25880 [1:47:12<3:15:06,  1.47it/s]
1|8620|Loss: 0.8852433562278748:  33%|███▎      | 8619/25880 [1:47:12<3:15:06,  1.47it/s]
1|8620|Loss: 0.8852433562278748:  33%|███▎      | 8620/25880 [1:47:13<3:19:49,  1.44it/s]
1|8621|Loss: 0.8158624768257141:  33%|███▎      | 8620/25880 [1:47:13<3:19:49,  1.44it/s]
1|8621|Loss: 0.8158624768257141:  33%|███▎      | 8621/25880 [1:47:13<3:07:21,  1.54it/s]
1|8622|Loss: 0.7791597247123718:  33%|███▎      | 8621/25880 [1:47:14<3:07:21,  1.54it/s]
1|8622|Loss: 0.7791597247123718:  33%|███▎      | 8622/25880 [1:47:14<3:15:22,  1.47it/s]
1|8623|Loss: 0.9026572704315186:  33%|███▎      | 8622/25880 [1:47:14<3:15:22,  1.47it/s]
1|8623|Loss: 0.9026572704315186:  33%|███▎      | 8623/25880 [1:47:15<3:29:19,  1.37it/s]
1|8624|Loss: 0.9952287673950195:  33%|███▎      | 8623/25880 [1:47:15<3:29:19,  1.37it/s]
1|8624|Loss: 0.9952287673950195:  33%|███▎      | 8624/25880 [1:47:15<3:17:05,  1.46it/s]
1|8625|Loss: 0.866229772567749:  33%|███▎      | 8624/25880 [1:47:16<3:17:05,  1.46it/s] 
1|8625|Loss: 0.866229772567749:  33%|███▎      | 8625/25880 [1:47:16<3:14:49,  1.48it/s]
1|8626|Loss: 0.7585453391075134:  33%|███▎      | 8625/25880 [1:47:17<3:14:49,  1.48it/s]
1|8626|Loss: 0.7585453391075134:  33%|███▎      | 8626/25880 [1:47:17<3:28:38,  1.38it/s]
1|8627|Loss: 0.8318676352500916:  33%|███▎      | 8626/25880 [1:47:17<3:28:38,  1.38it/s]
1|8627|Loss: 0.8318676352500916:  33%|███▎      | 8627/25880 [1:47:18<3:24:22,  1.41it/s]
1|8628|Loss: 0.9150745868682861:  33%|███▎      | 8627/25880 [1:47:18<3:24:22,  1.41it/s]
1|8628|Loss: 0.9150745868682861:  33%|███▎      | 8628/25880 [1:47:18<3:32:36,  1.35it/s]
1|8629|Loss: 0.9830846786499023:  33%|███▎      | 8628/25880 [1:47:19<3:32:36,  1.35it/s]
1|8629|Loss: 0.9830846786499023:  33%|███▎      | 8629/25880 [1:47:19<3:20:23,  1.43it/s]
1|8630|Loss: 0.7788881659507751:  33%|███▎      | 8629/25880 [1:47:19<3:20:23,  1.43it/s]
1|8630|Loss: 0.7788881659507751:  33%|███▎      | 8630/25880 [1:47:20<3:25:53,  1.40it/s]
1|8631|Loss: 0.826984703540802:  33%|███▎      | 8630/25880 [1:47:20<3:25:53,  1.40it/s] 
1|8631|Loss: 0.826984703540802:  33%|███▎      | 8631/25880 [1:47:21<3:26:33,  1.39it/s]
1|8632|Loss: 0.9197081327438354:  33%|███▎      | 8631/25880 [1:47:21<3:26:33,  1.39it/s]
1|8632|Loss: 0.9197081327438354:  33%|███▎      | 8632/25880 [1:47:21<3:19:10,  1.44it/s]
1|8633|Loss: 0.7429400682449341:  33%|███▎      | 8632/25880 [1:47:22<3:19:10,  1.44it/s]
1|8633|Loss: 0.7429400682449341:  33%|███▎      | 8633/25880 [1:47:22<3:33:22,  1.35it/s]
1|8634|Loss: 0.8063688278198242:  33%|███▎      | 8633/25880 [1:47:22<3:33:22,  1.35it/s]
1|8634|Loss: 0.8063688278198242:  33%|███▎      | 8634/25880 [1:47:23<3:33:22,  1.35it/s]
1|8635|Loss: 0.8146554827690125:  33%|███▎      | 8634/25880 [1:47:23<3:33:22,  1.35it/s]
1|8635|Loss: 0.8146554827690125:  33%|███▎      | 8635/25880 [1:47:23<3:32:36,  1.35it/s]
1|8636|Loss: 0.7711473703384399:  33%|███▎      | 8635/25880 [1:47:24<3:32:36,  1.35it/s]
1|8636|Loss: 0.7711473703384399:  33%|███▎      | 8636/25880 [1:47:24<3:40:34,  1.30it/s]
1|8637|Loss: 0.9245532155036926:  33%|███▎      | 8636/25880 [1:47:25<3:40:34,  1.30it/s]
1|8637|Loss: 0.9245532155036926:  33%|███▎      | 8637/25880 [1:47:25<3:26:39,  1.39it/s]
1|8638|Loss: 0.8743770718574524:  33%|███▎      | 8637/25880 [1:47:25<3:26:39,  1.39it/s]
1|8638|Loss: 0.8743770718574524:  33%|███▎      | 8638/25880 [1:47:25<3:08:59,  1.52it/s]
1|8639|Loss: 0.8316549062728882:  33%|███▎      | 8638/25880 [1:47:26<3:08:59,  1.52it/s]
1|8639|Loss: 0.8316549062728882:  33%|███▎      | 8639/25880 [1:47:26<3:01:09,  1.59it/s]
1|8640|Loss: 0.7717276811599731:  33%|███▎      | 8639/25880 [1:47:26<3:01:09,  1.59it/s]
1|8640|Loss: 0.7717276811599731:  33%|███▎      | 8640/25880 [1:47:27<3:13:44,  1.48it/s]
1|8641|Loss: 0.9332371354103088:  33%|███▎      | 8640/25880 [1:47:27<3:13:44,  1.48it/s]
1|8641|Loss: 0.9332371354103088:  33%|███▎      | 8641/25880 [1:47:27<3:11:57,  1.50it/s]
1|8642|Loss: 0.9141702055931091:  33%|███▎      | 8641/25880 [1:47:28<3:11:57,  1.50it/s]
1|8642|Loss: 0.9141702055931091:  33%|███▎      | 8642/25880 [1:47:28<3:21:56,  1.42it/s]
1|8643|Loss: 0.9575123190879822:  33%|███▎      | 8642/25880 [1:47:29<3:21:56,  1.42it/s]
1|8643|Loss: 0.9575123190879822:  33%|███▎      | 8643/25880 [1:47:29<3:11:55,  1.50it/s]
1|8644|Loss: 0.881077229976654:  33%|███▎      | 8643/25880 [1:47:29<3:11:55,  1.50it/s] 
1|8644|Loss: 0.881077229976654:  33%|███▎      | 8644/25880 [1:47:29<3:13:54,  1.48it/s]
1|8645|Loss: 0.944258451461792:  33%|███▎      | 8644/25880 [1:47:30<3:13:54,  1.48it/s]
1|8645|Loss: 0.944258451461792:  33%|███▎      | 8645/25880 [1:47:30<3:11:10,  1.50it/s]
1|8646|Loss: 0.957356333732605:  33%|███▎      | 8645/25880 [1:47:30<3:11:10,  1.50it/s]
1|8646|Loss: 0.957356333732605:  33%|███▎      | 8646/25880 [1:47:31<3:04:44,  1.55it/s]
1|8647|Loss: 0.7672382593154907:  33%|███▎      | 8646/25880 [1:47:31<3:04:44,  1.55it/s]
1|8647|Loss: 0.7672382593154907:  33%|███▎      | 8647/25880 [1:47:31<3:01:38,  1.58it/s]
1|8648|Loss: 0.830810546875:  33%|███▎      | 8647/25880 [1:47:32<3:01:38,  1.58it/s]    
1|8648|Loss: 0.830810546875:  33%|███▎      | 8648/25880 [1:47:32<3:02:01,  1.58it/s]
1|8649|Loss: 0.7668589353561401:  33%|███▎      | 8648/25880 [1:47:32<3:02:01,  1.58it/s]
1|8649|Loss: 0.7668589353561401:  33%|███▎      | 8649/25880 [1:47:33<3:13:43,  1.48it/s]
1|8650|Loss: 0.7806907892227173:  33%|███▎      | 8649/25880 [1:47:33<3:13:43,  1.48it/s]
1|8650|Loss: 0.7806907892227173:  33%|███▎      | 8650/25880 [1:47:34<3:27:46,  1.38it/s]
1|8651|Loss: 0.8787103295326233:  33%|███▎      | 8650/25880 [1:47:34<3:27:46,  1.38it/s]
1|8651|Loss: 0.8787103295326233:  33%|███▎      | 8651/25880 [1:47:34<3:24:56,  1.40it/s]
1|8652|Loss: 0.7815647721290588:  33%|███▎      | 8651/25880 [1:47:35<3:24:56,  1.40it/s]
1|8652|Loss: 0.7815647721290588:  33%|███▎      | 8652/25880 [1:47:35<3:05:39,  1.55it/s]
1|8653|Loss: 0.7083752155303955:  33%|███▎      | 8652/25880 [1:47:35<3:05:39,  1.55it/s]
1|8653|Loss: 0.7083752155303955:  33%|███▎      | 8653/25880 [1:47:36<3:15:20,  1.47it/s]
1|8654|Loss: 0.9105281233787537:  33%|███▎      | 8653/25880 [1:47:36<3:15:20,  1.47it/s]
1|8654|Loss: 0.9105281233787537:  33%|███▎      | 8654/25880 [1:47:36<3:22:55,  1.41it/s]
1|8655|Loss: 0.7710990905761719:  33%|███▎      | 8654/25880 [1:47:37<3:22:55,  1.41it/s]
1|8655|Loss: 0.7710990905761719:  33%|███▎      | 8655/25880 [1:47:37<3:26:30,  1.39it/s]
1|8656|Loss: 0.8921092748641968:  33%|███▎      | 8655/25880 [1:47:37<3:26:30,  1.39it/s]
1|8656|Loss: 0.8921092748641968:  33%|███▎      | 8656/25880 [1:47:38<3:17:23,  1.45it/s]
1|8657|Loss: 0.7635234594345093:  33%|███▎      | 8656/25880 [1:47:38<3:17:23,  1.45it/s]
1|8657|Loss: 0.7635234594345093:  33%|███▎      | 8657/25880 [1:47:38<3:16:49,  1.46it/s]
1|8658|Loss: 0.8756409883499146:  33%|███▎      | 8657/25880 [1:47:39<3:16:49,  1.46it/s]
1|8658|Loss: 0.8756409883499146:  33%|███▎      | 8658/25880 [1:47:39<3:19:57,  1.44it/s]
1|8659|Loss: 0.7750059962272644:  33%|███▎      | 8658/25880 [1:47:39<3:19:57,  1.44it/s]
1|8659|Loss: 0.7750059962272644:  33%|███▎      | 8659/25880 [1:47:40<3:32:12,  1.35it/s]
1|8660|Loss: 0.9171686172485352:  33%|███▎      | 8659/25880 [1:47:40<3:32:12,  1.35it/s]
1|8660|Loss: 0.9171686172485352:  33%|███▎      | 8660/25880 [1:47:41<3:28:25,  1.38it/s]
1|8661|Loss: 0.7867960333824158:  33%|███▎      | 8660/25880 [1:47:41<3:28:25,  1.38it/s]
1|8661|Loss: 0.7867960333824158:  33%|███▎      | 8661/25880 [1:47:41<3:20:49,  1.43it/s]
1|8662|Loss: 0.8636087775230408:  33%|███▎      | 8661/25880 [1:47:42<3:20:49,  1.43it/s]
1|8662|Loss: 0.8636087775230408:  33%|███▎      | 8662/25880 [1:47:42<3:15:55,  1.46it/s]
1|8663|Loss: 0.7732484340667725:  33%|███▎      | 8662/25880 [1:47:42<3:15:55,  1.46it/s]
1|8663|Loss: 0.7732484340667725:  33%|███▎      | 8663/25880 [1:47:43<3:25:43,  1.39it/s]
1|8664|Loss: 0.853666365146637:  33%|███▎      | 8663/25880 [1:47:43<3:25:43,  1.39it/s] 
1|8664|Loss: 0.853666365146637:  33%|███▎      | 8664/25880 [1:47:43<3:28:29,  1.38it/s]
1|8665|Loss: 0.96333909034729:  33%|███▎      | 8664/25880 [1:47:44<3:28:29,  1.38it/s] 
1|8665|Loss: 0.96333909034729:  33%|███▎      | 8665/25880 [1:47:44<3:35:25,  1.33it/s]
1|8666|Loss: 0.8110716342926025:  33%|███▎      | 8665/25880 [1:47:45<3:35:25,  1.33it/s]
1|8666|Loss: 0.8110716342926025:  33%|███▎      | 8666/25880 [1:47:45<3:27:09,  1.38it/s]
1|8667|Loss: 0.8138971924781799:  33%|███▎      | 8666/25880 [1:47:45<3:27:09,  1.38it/s]
1|8667|Loss: 0.8138971924781799:  33%|███▎      | 8667/25880 [1:47:45<3:17:48,  1.45it/s]
1|8668|Loss: 0.9462020993232727:  33%|███▎      | 8667/25880 [1:47:46<3:17:48,  1.45it/s]
1|8668|Loss: 0.9462020993232727:  33%|███▎      | 8668/25880 [1:47:46<3:17:48,  1.45it/s]
1|8669|Loss: 0.7749962210655212:  33%|███▎      | 8668/25880 [1:47:47<3:17:48,  1.45it/s]
1|8669|Loss: 0.7749962210655212:  33%|███▎      | 8669/25880 [1:47:47<3:25:10,  1.40it/s]
1|8670|Loss: 0.8647493124008179:  33%|███▎      | 8669/25880 [1:47:47<3:25:10,  1.40it/s]
1|8670|Loss: 0.8647493124008179:  34%|███▎      | 8670/25880 [1:47:48<3:18:33,  1.44it/s]
1|8671|Loss: 0.8402983546257019:  34%|███▎      | 8670/25880 [1:47:48<3:18:33,  1.44it/s]
1|8671|Loss: 0.8402983546257019:  34%|███▎      | 8671/25880 [1:47:48<3:27:37,  1.38it/s]
1|8672|Loss: 0.9332520365715027:  34%|███▎      | 8671/25880 [1:47:49<3:27:37,  1.38it/s]
1|8672|Loss: 0.9332520365715027:  34%|███▎      | 8672/25880 [1:47:49<3:20:15,  1.43it/s]
1|8673|Loss: 0.8671446442604065:  34%|███▎      | 8672/25880 [1:47:49<3:20:15,  1.43it/s]
1|8673|Loss: 0.8671446442604065:  34%|███▎      | 8673/25880 [1:47:50<3:28:40,  1.37it/s]
1|8674|Loss: 0.6759901642799377:  34%|███▎      | 8673/25880 [1:47:50<3:28:40,  1.37it/s]
1|8674|Loss: 0.6759901642799377:  34%|███▎      | 8674/25880 [1:47:51<3:32:10,  1.35it/s]
1|8675|Loss: 0.8469734191894531:  34%|███▎      | 8674/25880 [1:47:51<3:32:10,  1.35it/s]
1|8675|Loss: 0.8469734191894531:  34%|███▎      | 8675/25880 [1:47:51<3:30:05,  1.36it/s]
1|8676|Loss: 0.7452378273010254:  34%|███▎      | 8675/25880 [1:47:52<3:30:05,  1.36it/s]
1|8676|Loss: 0.7452378273010254:  34%|███▎      | 8676/25880 [1:47:52<3:29:04,  1.37it/s]
1|8677|Loss: 0.734961986541748:  34%|███▎      | 8676/25880 [1:47:52<3:29:04,  1.37it/s] 
1|8677|Loss: 0.734961986541748:  34%|███▎      | 8677/25880 [1:47:53<3:26:37,  1.39it/s]
1|8678|Loss: 0.9587944149971008:  34%|███▎      | 8677/25880 [1:47:53<3:26:37,  1.39it/s]
1|8678|Loss: 0.9587944149971008:  34%|███▎      | 8678/25880 [1:47:53<3:26:42,  1.39it/s]
1|8679|Loss: 0.8142597079277039:  34%|███▎      | 8678/25880 [1:47:54<3:26:42,  1.39it/s]
1|8679|Loss: 0.8142597079277039:  34%|███▎      | 8679/25880 [1:47:54<3:13:25,  1.48it/s]
1|8680|Loss: 0.9488201141357422:  34%|███▎      | 8679/25880 [1:47:54<3:13:25,  1.48it/s]
1|8680|Loss: 0.9488201141357422:  34%|███▎      | 8680/25880 [1:47:55<3:12:23,  1.49it/s]
1|8681|Loss: 0.6814715266227722:  34%|███▎      | 8680/25880 [1:47:55<3:12:23,  1.49it/s]
1|8681|Loss: 0.6814715266227722:  34%|███▎      | 8681/25880 [1:47:55<3:08:38,  1.52it/s]
1|8682|Loss: 0.8296303153038025:  34%|███▎      | 8681/25880 [1:47:56<3:08:38,  1.52it/s]
1|8682|Loss: 0.8296303153038025:  34%|███▎      | 8682/25880 [1:47:56<3:01:22,  1.58it/s]
1|8683|Loss: 0.8488243222236633:  34%|███▎      | 8682/25880 [1:47:56<3:01:22,  1.58it/s]
1|8683|Loss: 0.8488243222236633:  34%|███▎      | 8683/25880 [1:47:57<3:07:38,  1.53it/s]
1|8684|Loss: 0.8345943093299866:  34%|███▎      | 8683/25880 [1:47:57<3:07:38,  1.53it/s]
1|8684|Loss: 0.8345943093299866:  34%|███▎      | 8684/25880 [1:47:57<2:56:02,  1.63it/s]
1|8685|Loss: 0.8573703169822693:  34%|███▎      | 8684/25880 [1:47:57<2:56:02,  1.63it/s]
1|8685|Loss: 0.8573703169822693:  34%|███▎      | 8685/25880 [1:47:58<2:45:59,  1.73it/s]
1|8686|Loss: 0.956708550453186:  34%|███▎      | 8685/25880 [1:47:58<2:45:59,  1.73it/s] 
1|8686|Loss: 0.956708550453186:  34%|███▎      | 8686/25880 [1:47:58<2:54:16,  1.64it/s]
1|8687|Loss: 0.8538103103637695:  34%|███▎      | 8686/25880 [1:47:59<2:54:16,  1.64it/s]
1|8687|Loss: 0.8538103103637695:  34%|███▎      | 8687/25880 [1:47:59<2:57:45,  1.61it/s]
1|8688|Loss: 0.8881869316101074:  34%|███▎      | 8687/25880 [1:47:59<2:57:45,  1.61it/s]
1|8688|Loss: 0.8881869316101074:  34%|███▎      | 8688/25880 [1:48:00<2:59:49,  1.59it/s]
1|8689|Loss: 1.0500558614730835:  34%|███▎      | 8688/25880 [1:48:00<2:59:49,  1.59it/s]
1|8689|Loss: 1.0500558614730835:  34%|███▎      | 8689/25880 [1:48:00<3:05:31,  1.54it/s]
1|8690|Loss: 0.8158042430877686:  34%|███▎      | 8689/25880 [1:48:01<3:05:31,  1.54it/s]
1|8690|Loss: 0.8158042430877686:  34%|███▎      | 8690/25880 [1:48:01<3:04:28,  1.55it/s]
1|8691|Loss: 0.6735088229179382:  34%|███▎      | 8690/25880 [1:48:01<3:04:28,  1.55it/s]
1|8691|Loss: 0.6735088229179382:  34%|███▎      | 8691/25880 [1:48:02<3:19:58,  1.43it/s]
1|8692|Loss: 0.7502532005310059:  34%|███▎      | 8691/25880 [1:48:02<3:19:58,  1.43it/s]
1|8692|Loss: 0.7502532005310059:  34%|███▎      | 8692/25880 [1:48:02<3:15:12,  1.47it/s]
1|8693|Loss: 0.9035360217094421:  34%|███▎      | 8692/25880 [1:48:03<3:15:12,  1.47it/s]
1|8693|Loss: 0.9035360217094421:  34%|███▎      | 8693/25880 [1:48:03<3:27:01,  1.38it/s]
1|8694|Loss: 0.7018085718154907:  34%|███▎      | 8693/25880 [1:48:04<3:27:01,  1.38it/s]
1|8694|Loss: 0.7018085718154907:  34%|███▎      | 8694/25880 [1:48:04<3:40:18,  1.30it/s]
1|8695|Loss: 0.7914498448371887:  34%|███▎      | 8694/25880 [1:48:04<3:40:18,  1.30it/s]
1|8695|Loss: 0.7914498448371887:  34%|███▎      | 8695/25880 [1:48:05<3:33:49,  1.34it/s]
1|8696|Loss: 0.8335031867027283:  34%|███▎      | 8695/25880 [1:48:05<3:33:49,  1.34it/s]
1|8696|Loss: 0.8335031867027283:  34%|███▎      | 8696/25880 [1:48:05<3:31:43,  1.35it/s]
1|8697|Loss: 0.9080875515937805:  34%|███▎      | 8696/25880 [1:48:06<3:31:43,  1.35it/s]
1|8697|Loss: 0.9080875515937805:  34%|███▎      | 8697/25880 [1:48:06<3:35:00,  1.33it/s]
1|8698|Loss: 0.7648888826370239:  34%|███▎      | 8697/25880 [1:48:07<3:35:00,  1.33it/s]
1|8698|Loss: 0.7648888826370239:  34%|███▎      | 8698/25880 [1:48:07<3:35:04,  1.33it/s]
1|8699|Loss: 0.761052668094635:  34%|███▎      | 8698/25880 [1:48:07<3:35:04,  1.33it/s] 
1|8699|Loss: 0.761052668094635:  34%|███▎      | 8699/25880 [1:48:08<3:22:34,  1.41it/s]
1|8700|Loss: 0.8204544186592102:  34%|███▎      | 8699/25880 [1:48:08<3:22:34,  1.41it/s]
1|8700|Loss: 0.8204544186592102:  34%|███▎      | 8700/25880 [1:48:08<3:11:43,  1.49it/s]
1|8701|Loss: 0.830152153968811:  34%|███▎      | 8700/25880 [1:48:09<3:11:43,  1.49it/s] 
1|8701|Loss: 0.830152153968811:  34%|███▎      | 8701/25880 [1:48:09<3:15:15,  1.47it/s]
1|8702|Loss: 0.775586724281311:  34%|███▎      | 8701/25880 [1:48:09<3:15:15,  1.47it/s]
1|8702|Loss: 0.775586724281311:  34%|███▎      | 8702/25880 [1:48:10<3:19:47,  1.43it/s]
1|8703|Loss: 0.7738102674484253:  34%|███▎      | 8702/25880 [1:48:10<3:19:47,  1.43it/s]
1|8703|Loss: 0.7738102674484253:  34%|███▎      | 8703/25880 [1:48:11<3:34:58,  1.33it/s]
1|8704|Loss: 0.8418013453483582:  34%|███▎      | 8703/25880 [1:48:11<3:34:58,  1.33it/s]
1|8704|Loss: 0.8418013453483582:  34%|███▎      | 8704/25880 [1:48:11<3:36:08,  1.32it/s]
1|8705|Loss: 0.7216507792472839:  34%|███▎      | 8704/25880 [1:48:12<3:36:08,  1.32it/s]
1|8705|Loss: 0.7216507792472839:  34%|███▎      | 8705/25880 [1:48:12<3:34:05,  1.34it/s]
1|8706|Loss: 0.9293491244316101:  34%|███▎      | 8705/25880 [1:48:12<3:34:05,  1.34it/s]
1|8706|Loss: 0.9293491244316101:  34%|███▎      | 8706/25880 [1:48:13<3:33:58,  1.34it/s]
1|8707|Loss: 0.7777766585350037:  34%|███▎      | 8706/25880 [1:48:13<3:33:58,  1.34it/s]
1|8707|Loss: 0.7777766585350037:  34%|███▎      | 8707/25880 [1:48:14<3:49:18,  1.25it/s]
1|8708|Loss: 0.7944044470787048:  34%|███▎      | 8707/25880 [1:48:14<3:49:18,  1.25it/s]
1|8708|Loss: 0.7944044470787048:  34%|███▎      | 8708/25880 [1:48:14<3:41:21,  1.29it/s]
1|8709|Loss: 0.7510298490524292:  34%|███▎      | 8708/25880 [1:48:15<3:41:21,  1.29it/s]
1|8709|Loss: 0.7510298490524292:  34%|███▎      | 8709/25880 [1:48:15<3:26:17,  1.39it/s]
1|8710|Loss: 0.7914583683013916:  34%|███▎      | 8709/25880 [1:48:15<3:26:17,  1.39it/s]
1|8710|Loss: 0.7914583683013916:  34%|███▎      | 8710/25880 [1:48:15<3:05:42,  1.54it/s]
1|8711|Loss: 0.9278348088264465:  34%|███▎      | 8710/25880 [1:48:16<3:05:42,  1.54it/s]
1|8711|Loss: 0.9278348088264465:  34%|███▎      | 8711/25880 [1:48:16<3:00:02,  1.59it/s]
1|8712|Loss: 0.8367427587509155:  34%|███▎      | 8711/25880 [1:48:16<3:00:02,  1.59it/s]
1|8712|Loss: 0.8367427587509155:  34%|███▎      | 8712/25880 [1:48:17<3:16:31,  1.46it/s]
1|8713|Loss: 0.9100777506828308:  34%|███▎      | 8712/25880 [1:48:17<3:16:31,  1.46it/s]
1|8713|Loss: 0.9100777506828308:  34%|███▎      | 8713/25880 [1:48:18<3:15:35,  1.46it/s]
1|8714|Loss: 0.8515451550483704:  34%|███▎      | 8713/25880 [1:48:18<3:15:35,  1.46it/s]
1|8714|Loss: 0.8515451550483704:  34%|███▎      | 8714/25880 [1:48:18<3:18:21,  1.44it/s]
1|8715|Loss: 0.8038226366043091:  34%|███▎      | 8714/25880 [1:48:19<3:18:21,  1.44it/s]
1|8715|Loss: 0.8038226366043091:  34%|███▎      | 8715/25880 [1:48:19<3:22:05,  1.42it/s]
1|8716|Loss: 0.816361129283905:  34%|███▎      | 8715/25880 [1:48:19<3:22:05,  1.42it/s] 
1|8716|Loss: 0.816361129283905:  34%|███▎      | 8716/25880 [1:48:20<3:22:39,  1.41it/s]
1|8717|Loss: 0.8584437370300293:  34%|███▎      | 8716/25880 [1:48:20<3:22:39,  1.41it/s]
1|8717|Loss: 0.8584437370300293:  34%|███▎      | 8717/25880 [1:48:20<3:22:31,  1.41it/s]
1|8718|Loss: 0.7924061417579651:  34%|███▎      | 8717/25880 [1:48:21<3:22:31,  1.41it/s]
1|8718|Loss: 0.7924061417579651:  34%|███▎      | 8718/25880 [1:48:21<3:21:27,  1.42it/s]
1|8719|Loss: 0.8309798240661621:  34%|███▎      | 8718/25880 [1:48:21<3:21:27,  1.42it/s]
1|8719|Loss: 0.8309798240661621:  34%|███▎      | 8719/25880 [1:48:22<3:08:48,  1.51it/s]
1|8720|Loss: 0.8750279545783997:  34%|███▎      | 8719/25880 [1:48:22<3:08:48,  1.51it/s]
1|8720|Loss: 0.8750279545783997:  34%|███▎      | 8720/25880 [1:48:22<3:09:12,  1.51it/s]
1|8721|Loss: 0.8759793043136597:  34%|███▎      | 8720/25880 [1:48:23<3:09:12,  1.51it/s]
1|8721|Loss: 0.8759793043136597:  34%|███▎      | 8721/25880 [1:48:23<3:07:07,  1.53it/s]
1|8722|Loss: 0.8961478471755981:  34%|███▎      | 8721/25880 [1:48:23<3:07:07,  1.53it/s]
1|8722|Loss: 0.8961478471755981:  34%|███▎      | 8722/25880 [1:48:24<3:24:12,  1.40it/s]
1|8723|Loss: 0.901911199092865:  34%|███▎      | 8722/25880 [1:48:24<3:24:12,  1.40it/s] 
1|8723|Loss: 0.901911199092865:  34%|███▎      | 8723/25880 [1:48:25<3:28:43,  1.37it/s]
1|8724|Loss: 0.9807013869285583:  34%|███▎      | 8723/25880 [1:48:25<3:28:43,  1.37it/s]
1|8724|Loss: 0.9807013869285583:  34%|███▎      | 8724/25880 [1:48:25<3:37:26,  1.31it/s]
1|8725|Loss: 0.7106485366821289:  34%|███▎      | 8724/25880 [1:48:26<3:37:26,  1.31it/s]
1|8725|Loss: 0.7106485366821289:  34%|███▎      | 8725/25880 [1:48:26<3:18:11,  1.44it/s]
1|8726|Loss: 0.7263367772102356:  34%|███▎      | 8725/25880 [1:48:26<3:18:11,  1.44it/s]
1|8726|Loss: 0.7263367772102356:  34%|███▎      | 8726/25880 [1:48:27<3:16:03,  1.46it/s]
1|8727|Loss: 0.8275401592254639:  34%|███▎      | 8726/25880 [1:48:27<3:16:03,  1.46it/s]
1|8727|Loss: 0.8275401592254639:  34%|███▎      | 8727/25880 [1:48:27<3:19:34,  1.43it/s]
1|8728|Loss: 0.843091607093811:  34%|███▎      | 8727/25880 [1:48:28<3:19:34,  1.43it/s] 
1|8728|Loss: 0.843091607093811:  34%|███▎      | 8728/25880 [1:48:28<3:21:26,  1.42it/s]
1|8729|Loss: 0.8197521567344666:  34%|███▎      | 8728/25880 [1:48:28<3:21:26,  1.42it/s]
1|8729|Loss: 0.8197521567344666:  34%|███▎      | 8729/25880 [1:48:29<3:13:51,  1.47it/s]
1|8730|Loss: 0.8236820101737976:  34%|███▎      | 8729/25880 [1:48:29<3:13:51,  1.47it/s]
1|8730|Loss: 0.8236820101737976:  34%|███▎      | 8730/25880 [1:48:30<3:31:11,  1.35it/s]
1|8731|Loss: 0.7695258259773254:  34%|███▎      | 8730/25880 [1:48:30<3:31:11,  1.35it/s]
1|8731|Loss: 0.7695258259773254:  34%|███▎      | 8731/25880 [1:48:30<3:27:54,  1.37it/s]
1|8732|Loss: 0.9820801019668579:  34%|███▎      | 8731/25880 [1:48:31<3:27:54,  1.37it/s]
1|8732|Loss: 0.9820801019668579:  34%|███▎      | 8732/25880 [1:48:31<3:27:40,  1.38it/s]
1|8733|Loss: 0.9145306944847107:  34%|███▎      | 8732/25880 [1:48:31<3:27:40,  1.38it/s]
1|8733|Loss: 0.9145306944847107:  34%|███▎      | 8733/25880 [1:48:32<3:28:08,  1.37it/s]
1|8734|Loss: 0.8391913175582886:  34%|███▎      | 8733/25880 [1:48:32<3:28:08,  1.37it/s]
1|8734|Loss: 0.8391913175582886:  34%|███▎      | 8734/25880 [1:48:33<3:36:31,  1.32it/s]
1|8735|Loss: 0.8147948980331421:  34%|███▎      | 8734/25880 [1:48:33<3:36:31,  1.32it/s]
1|8735|Loss: 0.8147948980331421:  34%|███▍      | 8735/25880 [1:48:33<3:28:42,  1.37it/s]
1|8736|Loss: 0.7381654977798462:  34%|███▍      | 8735/25880 [1:48:34<3:28:42,  1.37it/s]
1|8736|Loss: 0.7381654977798462:  34%|███▍      | 8736/25880 [1:48:34<3:17:11,  1.45it/s]
1|8737|Loss: 0.7498487830162048:  34%|███▍      | 8736/25880 [1:48:34<3:17:11,  1.45it/s]
1|8737|Loss: 0.7498487830162048:  34%|███▍      | 8737/25880 [1:48:34<3:10:11,  1.50it/s]
1|8738|Loss: 0.8372399210929871:  34%|███▍      | 8737/25880 [1:48:35<3:10:11,  1.50it/s]
1|8738|Loss: 0.8372399210929871:  34%|███▍      | 8738/25880 [1:48:35<3:12:16,  1.49it/s]
1|8739|Loss: 0.9129525423049927:  34%|███▍      | 8738/25880 [1:48:35<3:12:16,  1.49it/s]
1|8739|Loss: 0.9129525423049927:  34%|███▍      | 8739/25880 [1:48:36<3:06:28,  1.53it/s]
1|8740|Loss: 0.8720527291297913:  34%|███▍      | 8739/25880 [1:48:36<3:06:28,  1.53it/s]
1|8740|Loss: 0.8720527291297913:  34%|███▍      | 8740/25880 [1:48:36<3:11:23,  1.49it/s]
1|8741|Loss: 1.0187265872955322:  34%|███▍      | 8740/25880 [1:48:37<3:11:23,  1.49it/s]
1|8741|Loss: 1.0187265872955322:  34%|███▍      | 8741/25880 [1:48:37<3:15:41,  1.46it/s]
1|8742|Loss: 0.9295101165771484:  34%|███▍      | 8741/25880 [1:48:38<3:15:41,  1.46it/s]
1|8742|Loss: 0.9295101165771484:  34%|███▍      | 8742/25880 [1:48:38<3:16:42,  1.45it/s]
1|8743|Loss: 0.9641724824905396:  34%|███▍      | 8742/25880 [1:48:38<3:16:42,  1.45it/s]
1|8743|Loss: 0.9641724824905396:  34%|███▍      | 8743/25880 [1:48:39<3:24:33,  1.40it/s]
1|8744|Loss: 1.0007332563400269:  34%|███▍      | 8743/25880 [1:48:39<3:24:33,  1.40it/s]
1|8744|Loss: 1.0007332563400269:  34%|███▍      | 8744/25880 [1:48:39<3:36:04,  1.32it/s]
1|8745|Loss: 0.7963841557502747:  34%|███▍      | 8744/25880 [1:48:40<3:36:04,  1.32it/s]
1|8745|Loss: 0.7963841557502747:  34%|███▍      | 8745/25880 [1:48:40<3:37:59,  1.31it/s]
1|8746|Loss: 0.8701603412628174:  34%|███▍      | 8745/25880 [1:48:41<3:37:59,  1.31it/s]
1|8746|Loss: 0.8701603412628174:  34%|███▍      | 8746/25880 [1:48:41<3:36:36,  1.32it/s]
1|8747|Loss: 0.7305156588554382:  34%|███▍      | 8746/25880 [1:48:41<3:36:36,  1.32it/s]
1|8747|Loss: 0.7305156588554382:  34%|███▍      | 8747/25880 [1:48:42<3:38:46,  1.31it/s]
1|8748|Loss: 1.0953772068023682:  34%|███▍      | 8747/25880 [1:48:42<3:38:46,  1.31it/s]
1|8748|Loss: 1.0953772068023682:  34%|███▍      | 8748/25880 [1:48:42<3:31:07,  1.35it/s]
1|8749|Loss: 0.931910514831543:  34%|███▍      | 8748/25880 [1:48:43<3:31:07,  1.35it/s] 
1|8749|Loss: 0.931910514831543:  34%|███▍      | 8749/25880 [1:48:43<3:30:26,  1.36it/s]
1|8750|Loss: 0.7924164533615112:  34%|███▍      | 8749/25880 [1:48:44<3:30:26,  1.36it/s]
1|8750|Loss: 0.7924164533615112:  34%|███▍      | 8750/25880 [1:48:44<3:24:41,  1.39it/s]
1|8751|Loss: 0.883342444896698:  34%|███▍      | 8750/25880 [1:48:44<3:24:41,  1.39it/s] 
1|8751|Loss: 0.883342444896698:  34%|███▍      | 8751/25880 [1:48:45<3:17:01,  1.45it/s]
1|8752|Loss: 0.8003547191619873:  34%|███▍      | 8751/25880 [1:48:45<3:17:01,  1.45it/s]
1|8752|Loss: 0.8003547191619873:  34%|███▍      | 8752/25880 [1:48:45<3:08:01,  1.52it/s]
1|8753|Loss: 0.9011456966400146:  34%|███▍      | 8752/25880 [1:48:45<3:08:01,  1.52it/s]
1|8753|Loss: 0.9011456966400146:  34%|███▍      | 8753/25880 [1:48:46<3:03:23,  1.56it/s]
1|8754|Loss: 0.8612156510353088:  34%|███▍      | 8753/25880 [1:48:46<3:03:23,  1.56it/s]
1|8754|Loss: 0.8612156510353088:  34%|███▍      | 8754/25880 [1:48:46<3:03:12,  1.56it/s]
1|8755|Loss: 0.935173749923706:  34%|███▍      | 8754/25880 [1:48:47<3:03:12,  1.56it/s] 
1|8755|Loss: 0.935173749923706:  34%|███▍      | 8755/25880 [1:48:47<3:19:06,  1.43it/s]
1|8756|Loss: 0.7909879684448242:  34%|███▍      | 8755/25880 [1:48:48<3:19:06,  1.43it/s]
1|8756|Loss: 0.7909879684448242:  34%|███▍      | 8756/25880 [1:48:48<3:42:48,  1.28it/s]
1|8757|Loss: 0.7502963542938232:  34%|███▍      | 8756/25880 [1:48:49<3:42:48,  1.28it/s]
1|8757|Loss: 0.7502963542938232:  34%|███▍      | 8757/25880 [1:48:49<3:49:07,  1.25it/s]
1|8758|Loss: 0.7292373776435852:  34%|███▍      | 8757/25880 [1:48:49<3:49:07,  1.25it/s]
1|8758|Loss: 0.7292373776435852:  34%|███▍      | 8758/25880 [1:48:50<3:50:01,  1.24it/s]
1|8759|Loss: 0.8932706713676453:  34%|███▍      | 8758/25880 [1:48:50<3:50:01,  1.24it/s]
1|8759|Loss: 0.8932706713676453:  34%|███▍      | 8759/25880 [1:48:51<3:48:28,  1.25it/s]
1|8760|Loss: 1.028140902519226:  34%|███▍      | 8759/25880 [1:48:51<3:48:28,  1.25it/s] 
1|8760|Loss: 1.028140902519226:  34%|███▍      | 8760/25880 [1:48:51<3:53:34,  1.22it/s]
1|8761|Loss: 0.8863288164138794:  34%|███▍      | 8760/25880 [1:48:52<3:53:34,  1.22it/s]
1|8761|Loss: 0.8863288164138794:  34%|███▍      | 8761/25880 [1:48:52<3:49:28,  1.24it/s]
1|8762|Loss: 0.967628002166748:  34%|███▍      | 8761/25880 [1:48:53<3:49:28,  1.24it/s] 
1|8762|Loss: 0.967628002166748:  34%|███▍      | 8762/25880 [1:48:53<3:29:51,  1.36it/s]
1|8763|Loss: 0.81732577085495:  34%|███▍      | 8762/25880 [1:48:53<3:29:51,  1.36it/s] 
1|8763|Loss: 0.81732577085495:  34%|███▍      | 8763/25880 [1:48:54<3:30:52,  1.35it/s]
1|8764|Loss: 0.8146925568580627:  34%|███▍      | 8763/25880 [1:48:54<3:30:52,  1.35it/s]
1|8764|Loss: 0.8146925568580627:  34%|███▍      | 8764/25880 [1:48:54<3:25:13,  1.39it/s]
1|8765|Loss: 0.9088352918624878:  34%|███▍      | 8764/25880 [1:48:55<3:25:13,  1.39it/s]
1|8765|Loss: 0.9088352918624878:  34%|███▍      | 8765/25880 [1:48:55<3:34:54,  1.33it/s]
1|8766|Loss: 0.7179834842681885:  34%|███▍      | 8765/25880 [1:48:55<3:34:54,  1.33it/s]
1|8766|Loss: 0.7179834842681885:  34%|███▍      | 8766/25880 [1:48:56<3:22:27,  1.41it/s]
1|8767|Loss: 0.8315358757972717:  34%|███▍      | 8766/25880 [1:48:56<3:22:27,  1.41it/s]
1|8767|Loss: 0.8315358757972717:  34%|███▍      | 8767/25880 [1:48:56<3:18:26,  1.44it/s]
1|8768|Loss: 0.820415735244751:  34%|███▍      | 8767/25880 [1:48:57<3:18:26,  1.44it/s] 
1|8768|Loss: 0.820415735244751:  34%|███▍      | 8768/25880 [1:48:57<3:12:49,  1.48it/s]
1|8769|Loss: 0.9128416776657104:  34%|███▍      | 8768/25880 [1:48:57<3:12:49,  1.48it/s]
1|8769|Loss: 0.9128416776657104:  34%|███▍      | 8769/25880 [1:48:58<3:05:36,  1.54it/s]
1|8770|Loss: 0.8231450319290161:  34%|███▍      | 8769/25880 [1:48:58<3:05:36,  1.54it/s]
1|8770|Loss: 0.8231450319290161:  34%|███▍      | 8770/25880 [1:48:58<2:54:41,  1.63it/s]
1|8771|Loss: 0.9419246315956116:  34%|███▍      | 8770/25880 [1:48:58<2:54:41,  1.63it/s]
1|8771|Loss: 0.9419246315956116:  34%|███▍      | 8771/25880 [1:48:59<3:00:32,  1.58it/s]
1|8772|Loss: 0.8445698022842407:  34%|███▍      | 8771/25880 [1:48:59<3:00:32,  1.58it/s]
1|8772|Loss: 0.8445698022842407:  34%|███▍      | 8772/25880 [1:48:59<3:08:54,  1.51it/s]
1|8773|Loss: 0.8597157001495361:  34%|███▍      | 8772/25880 [1:49:00<3:08:54,  1.51it/s]
1|8773|Loss: 0.8597157001495361:  34%|███▍      | 8773/25880 [1:49:00<3:22:38,  1.41it/s]
1|8774|Loss: 0.8543994426727295:  34%|███▍      | 8773/25880 [1:49:01<3:22:38,  1.41it/s]
1|8774|Loss: 0.8543994426727295:  34%|███▍      | 8774/25880 [1:49:01<3:27:51,  1.37it/s]
1|8775|Loss: 1.0648283958435059:  34%|███▍      | 8774/25880 [1:49:02<3:27:51,  1.37it/s]
1|8775|Loss: 1.0648283958435059:  34%|███▍      | 8775/25880 [1:49:02<3:37:27,  1.31it/s]
1|8776|Loss: 0.7965732216835022:  34%|███▍      | 8775/25880 [1:49:02<3:37:27,  1.31it/s]
1|8776|Loss: 0.7965732216835022:  34%|███▍      | 8776/25880 [1:49:03<3:50:29,  1.24it/s]
1|8777|Loss: 1.0617713928222656:  34%|███▍      | 8776/25880 [1:49:03<3:50:29,  1.24it/s]
1|8777|Loss: 1.0617713928222656:  34%|███▍      | 8777/25880 [1:49:04<4:13:42,  1.12it/s]
1|8778|Loss: 0.8332737684249878:  34%|███▍      | 8777/25880 [1:49:04<4:13:42,  1.12it/s]
1|8778|Loss: 0.8332737684249878:  34%|███▍      | 8778/25880 [1:49:05<4:00:44,  1.18it/s]
1|8779|Loss: 0.7878380417823792:  34%|███▍      | 8778/25880 [1:49:05<4:00:44,  1.18it/s]
1|8779|Loss: 0.7878380417823792:  34%|███▍      | 8779/25880 [1:49:05<3:35:36,  1.32it/s]
1|8780|Loss: 0.8955448269844055:  34%|███▍      | 8779/25880 [1:49:06<3:35:36,  1.32it/s]
1|8780|Loss: 0.8955448269844055:  34%|███▍      | 8780/25880 [1:49:06<3:29:21,  1.36it/s]
1|8781|Loss: 0.9691811800003052:  34%|███▍      | 8780/25880 [1:49:06<3:29:21,  1.36it/s]
1|8781|Loss: 0.9691811800003052:  34%|███▍      | 8781/25880 [1:49:07<3:35:41,  1.32it/s]
1|8782|Loss: 0.9370676875114441:  34%|███▍      | 8781/25880 [1:49:07<3:35:41,  1.32it/s]
1|8782|Loss: 0.9370676875114441:  34%|███▍      | 8782/25880 [1:49:07<3:27:20,  1.37it/s]
1|8783|Loss: 0.7060715556144714:  34%|███▍      | 8782/25880 [1:49:08<3:27:20,  1.37it/s]
1|8783|Loss: 0.7060715556144714:  34%|███▍      | 8783/25880 [1:49:08<3:33:24,  1.34it/s]
1|8784|Loss: 0.7368710041046143:  34%|███▍      | 8783/25880 [1:49:09<3:33:24,  1.34it/s]
1|8784|Loss: 0.7368710041046143:  34%|███▍      | 8784/25880 [1:49:09<3:22:21,  1.41it/s]
1|8785|Loss: 0.8075950741767883:  34%|███▍      | 8784/25880 [1:49:09<3:22:21,  1.41it/s]
1|8785|Loss: 0.8075950741767883:  34%|███▍      | 8785/25880 [1:49:09<3:04:23,  1.55it/s]
1|8786|Loss: 0.8586515188217163:  34%|███▍      | 8785/25880 [1:49:10<3:04:23,  1.55it/s]
1|8786|Loss: 0.8586515188217163:  34%|███▍      | 8786/25880 [1:49:10<2:56:58,  1.61it/s]
1|8787|Loss: 0.7354167103767395:  34%|███▍      | 8786/25880 [1:49:10<2:56:58,  1.61it/s]
1|8787|Loss: 0.7354167103767395:  34%|███▍      | 8787/25880 [1:49:11<3:13:15,  1.47it/s]
1|8788|Loss: 0.947525680065155:  34%|███▍      | 8787/25880 [1:49:11<3:13:15,  1.47it/s] 
1|8788|Loss: 0.947525680065155:  34%|███▍      | 8788/25880 [1:49:11<3:20:11,  1.42it/s]
1|8789|Loss: 0.7856305837631226:  34%|███▍      | 8788/25880 [1:49:12<3:20:11,  1.42it/s]
1|8789|Loss: 0.7856305837631226:  34%|███▍      | 8789/25880 [1:49:12<3:16:38,  1.45it/s]
1|8790|Loss: 0.9155838489532471:  34%|███▍      | 8789/25880 [1:49:12<3:16:38,  1.45it/s]
1|8790|Loss: 0.9155838489532471:  34%|███▍      | 8790/25880 [1:49:13<3:26:10,  1.38it/s]
1|8791|Loss: 0.7129898071289062:  34%|███▍      | 8790/25880 [1:49:13<3:26:10,  1.38it/s]
1|8791|Loss: 0.7129898071289062:  34%|███▍      | 8791/25880 [1:49:14<3:26:13,  1.38it/s]
1|8792|Loss: 0.9903205633163452:  34%|███▍      | 8791/25880 [1:49:14<3:26:13,  1.38it/s]
1|8792|Loss: 0.9903205633163452:  34%|███▍      | 8792/25880 [1:49:14<3:19:55,  1.42it/s]
1|8793|Loss: 0.792298436164856:  34%|███▍      | 8792/25880 [1:49:15<3:19:55,  1.42it/s] 
1|8793|Loss: 0.792298436164856:  34%|███▍      | 8793/25880 [1:49:15<3:27:53,  1.37it/s]
1|8794|Loss: 0.873232364654541:  34%|███▍      | 8793/25880 [1:49:15<3:27:53,  1.37it/s]
1|8794|Loss: 0.873232364654541:  34%|███▍      | 8794/25880 [1:49:16<3:22:49,  1.40it/s]
1|8795|Loss: 0.7162562012672424:  34%|███▍      | 8794/25880 [1:49:16<3:22:49,  1.40it/s]
1|8795|Loss: 0.7162562012672424:  34%|███▍      | 8795/25880 [1:49:16<3:20:55,  1.42it/s]
1|8796|Loss: 0.7804564833641052:  34%|███▍      | 8795/25880 [1:49:17<3:20:55,  1.42it/s]
1|8796|Loss: 0.7804564833641052:  34%|███▍      | 8796/25880 [1:49:17<3:21:10,  1.42it/s]
1|8797|Loss: 0.8233528137207031:  34%|███▍      | 8796/25880 [1:49:18<3:21:10,  1.42it/s]
1|8797|Loss: 0.8233528137207031:  34%|███▍      | 8797/25880 [1:49:18<3:28:01,  1.37it/s]
1|8798|Loss: 0.8283315896987915:  34%|███▍      | 8797/25880 [1:49:18<3:28:01,  1.37it/s]
1|8798|Loss: 0.8283315896987915:  34%|███▍      | 8798/25880 [1:49:19<3:29:12,  1.36it/s]
1|8799|Loss: 0.9327104687690735:  34%|███▍      | 8798/25880 [1:49:19<3:29:12,  1.36it/s]
1|8799|Loss: 0.9327104687690735:  34%|███▍      | 8799/25880 [1:49:19<3:29:19,  1.36it/s]
1|8800|Loss: 0.80353182554245:  34%|███▍      | 8799/25880 [1:49:20<3:29:19,  1.36it/s]  
1|8800|Loss: 0.80353182554245:  34%|███▍      | 8800/25880 [1:49:20<3:27:34,  1.37it/s]
1|8801|Loss: 0.9516221284866333:  34%|███▍      | 8800/25880 [1:49:20<3:27:34,  1.37it/s]
1|8801|Loss: 0.9516221284866333:  34%|███▍      | 8801/25880 [1:49:21<3:24:31,  1.39it/s]
1|8802|Loss: 0.9989888072013855:  34%|███▍      | 8801/25880 [1:49:21<3:24:31,  1.39it/s]
1|8802|Loss: 0.9989888072013855:  34%|███▍      | 8802/25880 [1:49:21<3:22:50,  1.40it/s]
1|8803|Loss: 0.8270697593688965:  34%|███▍      | 8802/25880 [1:49:22<3:22:50,  1.40it/s]
1|8803|Loss: 0.8270697593688965:  34%|███▍      | 8803/25880 [1:49:22<3:23:36,  1.40it/s]
1|8804|Loss: 0.7419016361236572:  34%|███▍      | 8803/25880 [1:49:23<3:23:36,  1.40it/s]
1|8804|Loss: 0.7419016361236572:  34%|███▍      | 8804/25880 [1:49:23<3:05:34,  1.53it/s]
1|8805|Loss: 0.7926284670829773:  34%|███▍      | 8804/25880 [1:49:23<3:05:34,  1.53it/s]
1|8805|Loss: 0.7926284670829773:  34%|███▍      | 8805/25880 [1:49:23<2:41:33,  1.76it/s]
1|8806|Loss: 0.8196570873260498:  34%|███▍      | 8805/25880 [1:49:23<2:41:33,  1.76it/s]
1|8806|Loss: 0.8196570873260498:  34%|███▍      | 8806/25880 [1:49:24<2:35:57,  1.82it/s]
1|8807|Loss: 0.8384451866149902:  34%|███▍      | 8806/25880 [1:49:24<2:35:57,  1.82it/s]
1|8807|Loss: 0.8384451866149902:  34%|███▍      | 8807/25880 [1:49:24<2:37:45,  1.80it/s]
1|8808|Loss: 0.8652710318565369:  34%|███▍      | 8807/25880 [1:49:25<2:37:45,  1.80it/s]
1|8808|Loss: 0.8652710318565369:  34%|███▍      | 8808/25880 [1:49:25<2:53:52,  1.64it/s]
1|8809|Loss: 0.7325069904327393:  34%|███▍      | 8808/25880 [1:49:25<2:53:52,  1.64it/s]
1|8809|Loss: 0.7325069904327393:  34%|███▍      | 8809/25880 [1:49:26<3:17:57,  1.44it/s]
1|8810|Loss: 0.7140147686004639:  34%|███▍      | 8809/25880 [1:49:26<3:17:57,  1.44it/s]
1|8810|Loss: 0.7140147686004639:  34%|███▍      | 8810/25880 [1:49:27<3:27:53,  1.37it/s]
1|8811|Loss: 0.905298113822937:  34%|███▍      | 8810/25880 [1:49:27<3:27:53,  1.37it/s] 
1|8811|Loss: 0.905298113822937:  34%|███▍      | 8811/25880 [1:49:27<3:17:18,  1.44it/s]
1|8812|Loss: 0.885866105556488:  34%|███▍      | 8811/25880 [1:49:28<3:17:18,  1.44it/s]
1|8812|Loss: 0.885866105556488:  34%|███▍      | 8812/25880 [1:49:28<3:22:32,  1.40it/s]
1|8813|Loss: 0.7769848704338074:  34%|███▍      | 8812/25880 [1:49:28<3:22:32,  1.40it/s]
1|8813|Loss: 0.7769848704338074:  34%|███▍      | 8813/25880 [1:49:29<3:10:44,  1.49it/s]
1|8814|Loss: 0.9863544702529907:  34%|███▍      | 8813/25880 [1:49:29<3:10:44,  1.49it/s]
1|8814|Loss: 0.9863544702529907:  34%|███▍      | 8814/25880 [1:49:29<3:20:33,  1.42it/s]
1|8815|Loss: 0.8647987246513367:  34%|███▍      | 8814/25880 [1:49:30<3:20:33,  1.42it/s]
1|8815|Loss: 0.8647987246513367:  34%|███▍      | 8815/25880 [1:49:30<3:10:38,  1.49it/s]
1|8816|Loss: 0.8553462028503418:  34%|███▍      | 8815/25880 [1:49:30<3:10:38,  1.49it/s]
1|8816|Loss: 0.8553462028503418:  34%|███▍      | 8816/25880 [1:49:31<3:13:05,  1.47it/s]
1|8817|Loss: 0.7330594062805176:  34%|███▍      | 8816/25880 [1:49:31<3:13:05,  1.47it/s]
1|8817|Loss: 0.7330594062805176:  34%|███▍      | 8817/25880 [1:49:31<3:11:42,  1.48it/s]
1|8818|Loss: 0.9258044362068176:  34%|███▍      | 8817/25880 [1:49:32<3:11:42,  1.48it/s]
1|8818|Loss: 0.9258044362068176:  34%|███▍      | 8818/25880 [1:49:32<3:32:46,  1.34it/s]
1|8819|Loss: 0.9039039015769958:  34%|███▍      | 8818/25880 [1:49:33<3:32:46,  1.34it/s]
1|8819|Loss: 0.9039039015769958:  34%|███▍      | 8819/25880 [1:49:33<3:30:20,  1.35it/s]
1|8820|Loss: 0.8704685568809509:  34%|███▍      | 8819/25880 [1:49:33<3:30:20,  1.35it/s]
1|8820|Loss: 0.8704685568809509:  34%|███▍      | 8820/25880 [1:49:34<3:28:14,  1.37it/s]
1|8821|Loss: 0.7857158184051514:  34%|███▍      | 8820/25880 [1:49:34<3:28:14,  1.37it/s]
1|8821|Loss: 0.7857158184051514:  34%|███▍      | 8821/25880 [1:49:34<3:25:51,  1.38it/s]
1|8822|Loss: 0.7861042618751526:  34%|███▍      | 8821/25880 [1:49:35<3:25:51,  1.38it/s]
1|8822|Loss: 0.7861042618751526:  34%|███▍      | 8822/25880 [1:49:35<3:16:26,  1.45it/s]
1|8823|Loss: 0.7182408571243286:  34%|███▍      | 8822/25880 [1:49:35<3:16:26,  1.45it/s]
1|8823|Loss: 0.7182408571243286:  34%|███▍      | 8823/25880 [1:49:36<3:10:32,  1.49it/s]
1|8824|Loss: 0.7258219122886658:  34%|███▍      | 8823/25880 [1:49:36<3:10:32,  1.49it/s]
1|8824|Loss: 0.7258219122886658:  34%|███▍      | 8824/25880 [1:49:36<3:07:48,  1.51it/s]
1|8825|Loss: 1.0238862037658691:  34%|███▍      | 8824/25880 [1:49:37<3:07:48,  1.51it/s]
1|8825|Loss: 1.0238862037658691:  34%|███▍      | 8825/25880 [1:49:37<3:20:18,  1.42it/s]
1|8826|Loss: 0.8647801280021667:  34%|███▍      | 8825/25880 [1:49:37<3:20:18,  1.42it/s]
1|8826|Loss: 0.8647801280021667:  34%|███▍      | 8826/25880 [1:49:38<3:22:29,  1.40it/s]
1|8827|Loss: 0.8473671078681946:  34%|███▍      | 8826/25880 [1:49:38<3:22:29,  1.40it/s]
1|8827|Loss: 0.8473671078681946:  34%|███▍      | 8827/25880 [1:49:38<2:58:16,  1.59it/s]
1|8828|Loss: 1.0039048194885254:  34%|███▍      | 8827/25880 [1:49:38<2:58:16,  1.59it/s]
1|8828|Loss: 1.0039048194885254:  34%|███▍      | 8828/25880 [1:49:39<2:44:57,  1.72it/s]
1|8829|Loss: 0.725710391998291:  34%|███▍      | 8828/25880 [1:49:39<2:44:57,  1.72it/s] 
1|8829|Loss: 0.725710391998291:  34%|███▍      | 8829/25880 [1:49:39<2:58:27,  1.59it/s]
1|8830|Loss: 0.8410377502441406:  34%|███▍      | 8829/25880 [1:49:40<2:58:27,  1.59it/s]
1|8830|Loss: 0.8410377502441406:  34%|███▍      | 8830/25880 [1:49:40<3:09:02,  1.50it/s]
1|8831|Loss: 0.8501285314559937:  34%|███▍      | 8830/25880 [1:49:41<3:09:02,  1.50it/s]
1|8831|Loss: 0.8501285314559937:  34%|███▍      | 8831/25880 [1:49:41<3:13:19,  1.47it/s]
1|8832|Loss: 0.7872920632362366:  34%|███▍      | 8831/25880 [1:49:41<3:13:19,  1.47it/s]
1|8832|Loss: 0.7872920632362366:  34%|███▍      | 8832/25880 [1:49:42<3:16:54,  1.44it/s]
1|8833|Loss: 0.7760676145553589:  34%|███▍      | 8832/25880 [1:49:42<3:16:54,  1.44it/s]
1|8833|Loss: 0.7760676145553589:  34%|███▍      | 8833/25880 [1:49:43<3:37:52,  1.30it/s]
1|8834|Loss: 0.790198564529419:  34%|███▍      | 8833/25880 [1:49:43<3:37:52,  1.30it/s] 
1|8834|Loss: 0.790198564529419:  34%|███▍      | 8834/25880 [1:49:44<3:56:12,  1.20it/s]
1|8835|Loss: 0.9226680397987366:  34%|███▍      | 8834/25880 [1:49:44<3:56:12,  1.20it/s]
1|8835|Loss: 0.9226680397987366:  34%|███▍      | 8835/25880 [1:49:44<3:51:16,  1.23it/s]
1|8836|Loss: 0.8336340188980103:  34%|███▍      | 8835/25880 [1:49:45<3:51:16,  1.23it/s]
1|8836|Loss: 0.8336340188980103:  34%|███▍      | 8836/25880 [1:49:45<3:56:14,  1.20it/s]
1|8837|Loss: 0.8029807806015015:  34%|███▍      | 8836/25880 [1:49:46<3:56:14,  1.20it/s]
1|8837|Loss: 0.8029807806015015:  34%|███▍      | 8837/25880 [1:49:46<3:42:19,  1.28it/s]
1|8838|Loss: 0.7233886122703552:  34%|███▍      | 8837/25880 [1:49:46<3:42:19,  1.28it/s]
1|8838|Loss: 0.7233886122703552:  34%|███▍      | 8838/25880 [1:49:47<3:36:13,  1.31it/s]
1|8839|Loss: 0.8601624965667725:  34%|███▍      | 8838/25880 [1:49:47<3:36:13,  1.31it/s]
1|8839|Loss: 0.8601624965667725:  34%|███▍      | 8839/25880 [1:49:47<3:40:41,  1.29it/s]
1|8840|Loss: 0.7976078987121582:  34%|███▍      | 8839/25880 [1:49:48<3:40:41,  1.29it/s]
1|8840|Loss: 0.7976078987121582:  34%|███▍      | 8840/25880 [1:49:48<3:39:23,  1.29it/s]
1|8841|Loss: 0.9027857780456543:  34%|███▍      | 8840/25880 [1:49:49<3:39:23,  1.29it/s]
1|8841|Loss: 0.9027857780456543:  34%|███▍      | 8841/25880 [1:49:49<3:46:47,  1.25it/s]
1|8842|Loss: 0.8502944111824036:  34%|███▍      | 8841/25880 [1:49:49<3:46:47,  1.25it/s]
1|8842|Loss: 0.8502944111824036:  34%|███▍      | 8842/25880 [1:49:50<3:36:14,  1.31it/s]
1|8843|Loss: 0.904575526714325:  34%|███▍      | 8842/25880 [1:49:50<3:36:14,  1.31it/s] 
1|8843|Loss: 0.904575526714325:  34%|███▍      | 8843/25880 [1:49:50<3:23:34,  1.39it/s]
1|8844|Loss: 0.8996506929397583:  34%|███▍      | 8843/25880 [1:49:51<3:23:34,  1.39it/s]
1|8844|Loss: 0.8996506929397583:  34%|███▍      | 8844/25880 [1:49:51<3:30:49,  1.35it/s]
1|8845|Loss: 0.7117024064064026:  34%|███▍      | 8844/25880 [1:49:52<3:30:49,  1.35it/s]
1|8845|Loss: 0.7117024064064026:  34%|███▍      | 8845/25880 [1:49:52<3:38:48,  1.30it/s]
1|8846|Loss: 0.9283682703971863:  34%|███▍      | 8845/25880 [1:49:52<3:38:48,  1.30it/s]
1|8846|Loss: 0.9283682703971863:  34%|███▍      | 8846/25880 [1:49:53<3:37:48,  1.30it/s]
1|8847|Loss: 0.7477532029151917:  34%|███▍      | 8846/25880 [1:49:53<3:37:48,  1.30it/s]
1|8847|Loss: 0.7477532029151917:  34%|███▍      | 8847/25880 [1:49:54<3:52:22,  1.22it/s]
1|8848|Loss: 0.875344455242157:  34%|███▍      | 8847/25880 [1:49:54<3:52:22,  1.22it/s] 
1|8848|Loss: 0.875344455242157:  34%|███▍      | 8848/25880 [1:49:54<3:51:21,  1.23it/s]
1|8849|Loss: 0.7567104697227478:  34%|███▍      | 8848/25880 [1:49:55<3:51:21,  1.23it/s]
1|8849|Loss: 0.7567104697227478:  34%|███▍      | 8849/25880 [1:49:55<3:48:33,  1.24it/s]
1|8850|Loss: 0.7966625690460205:  34%|███▍      | 8849/25880 [1:49:56<3:48:33,  1.24it/s]
1|8850|Loss: 0.7966625690460205:  34%|███▍      | 8850/25880 [1:49:56<3:35:30,  1.32it/s]
1|8851|Loss: 0.9951003789901733:  34%|███▍      | 8850/25880 [1:49:56<3:35:30,  1.32it/s]
1|8851|Loss: 0.9951003789901733:  34%|███▍      | 8851/25880 [1:49:57<3:47:02,  1.25it/s]
1|8852|Loss: 0.7105332016944885:  34%|███▍      | 8851/25880 [1:49:57<3:47:02,  1.25it/s]
1|8852|Loss: 0.7105332016944885:  34%|███▍      | 8852/25880 [1:49:57<3:42:58,  1.27it/s]
1|8853|Loss: 0.7857068777084351:  34%|███▍      | 8852/25880 [1:49:58<3:42:58,  1.27it/s]
1|8853|Loss: 0.7857068777084351:  34%|███▍      | 8853/25880 [1:49:58<3:31:29,  1.34it/s]
1|8854|Loss: 0.8333376049995422:  34%|███▍      | 8853/25880 [1:49:59<3:31:29,  1.34it/s]
1|8854|Loss: 0.8333376049995422:  34%|███▍      | 8854/25880 [1:49:59<3:34:27,  1.32it/s]
1|8855|Loss: 0.917506992816925:  34%|███▍      | 8854/25880 [1:49:59<3:34:27,  1.32it/s] 
1|8855|Loss: 0.917506992816925:  34%|███▍      | 8855/25880 [1:49:59<3:10:38,  1.49it/s]
1|8856|Loss: 0.8651263117790222:  34%|███▍      | 8855/25880 [1:50:00<3:10:38,  1.49it/s]
1|8856|Loss: 0.8651263117790222:  34%|███▍      | 8856/25880 [1:50:00<3:17:28,  1.44it/s]
1|8857|Loss: 0.8797839283943176:  34%|███▍      | 8856/25880 [1:50:01<3:17:28,  1.44it/s]
1|8857|Loss: 0.8797839283943176:  34%|███▍      | 8857/25880 [1:50:01<3:14:29,  1.46it/s]
1|8858|Loss: 0.9088854789733887:  34%|███▍      | 8857/25880 [1:50:01<3:14:29,  1.46it/s]
1|8858|Loss: 0.9088854789733887:  34%|███▍      | 8858/25880 [1:50:01<3:10:27,  1.49it/s]
1|8859|Loss: 0.8535397052764893:  34%|███▍      | 8858/25880 [1:50:02<3:10:27,  1.49it/s]
1|8859|Loss: 0.8535397052764893:  34%|███▍      | 8859/25880 [1:50:02<3:14:00,  1.46it/s]
1|8860|Loss: 0.6548895239830017:  34%|███▍      | 8859/25880 [1:50:03<3:14:00,  1.46it/s]
1|8860|Loss: 0.6548895239830017:  34%|███▍      | 8860/25880 [1:50:03<3:16:03,  1.45it/s]
1|8861|Loss: 0.8320239186286926:  34%|███▍      | 8860/25880 [1:50:03<3:16:03,  1.45it/s]
1|8861|Loss: 0.8320239186286926:  34%|███▍      | 8861/25880 [1:50:03<3:03:40,  1.54it/s]
1|8862|Loss: 0.8094131946563721:  34%|███▍      | 8861/25880 [1:50:04<3:03:40,  1.54it/s]
1|8862|Loss: 0.8094131946563721:  34%|███▍      | 8862/25880 [1:50:04<3:06:38,  1.52it/s]
1|8863|Loss: 0.9208099246025085:  34%|███▍      | 8862/25880 [1:50:04<3:06:38,  1.52it/s]
1|8863|Loss: 0.9208099246025085:  34%|███▍      | 8863/25880 [1:50:05<3:14:29,  1.46it/s]
1|8864|Loss: 0.8885037302970886:  34%|███▍      | 8863/25880 [1:50:05<3:14:29,  1.46it/s]
1|8864|Loss: 0.8885037302970886:  34%|███▍      | 8864/25880 [1:50:06<3:24:15,  1.39it/s]
1|8865|Loss: 0.9025009274482727:  34%|███▍      | 8864/25880 [1:50:06<3:24:15,  1.39it/s]
1|8865|Loss: 0.9025009274482727:  34%|███▍      | 8865/25880 [1:50:06<3:34:31,  1.32it/s]
1|8866|Loss: 0.8452722430229187:  34%|███▍      | 8865/25880 [1:50:07<3:34:31,  1.32it/s]
1|8866|Loss: 0.8452722430229187:  34%|███▍      | 8866/25880 [1:50:07<3:41:07,  1.28it/s]
1|8867|Loss: 0.8297672867774963:  34%|███▍      | 8866/25880 [1:50:08<3:41:07,  1.28it/s]
1|8867|Loss: 0.8297672867774963:  34%|███▍      | 8867/25880 [1:50:08<3:42:24,  1.27it/s]
1|8868|Loss: 0.9356645345687866:  34%|███▍      | 8867/25880 [1:50:09<3:42:24,  1.27it/s]
1|8868|Loss: 0.9356645345687866:  34%|███▍      | 8868/25880 [1:50:09<3:37:27,  1.30it/s]
1|8869|Loss: 0.7407360076904297:  34%|███▍      | 8868/25880 [1:50:09<3:37:27,  1.30it/s]
1|8869|Loss: 0.7407360076904297:  34%|███▍      | 8869/25880 [1:50:09<3:14:51,  1.45it/s]
1|8870|Loss: 0.5879954695701599:  34%|███▍      | 8869/25880 [1:50:10<3:14:51,  1.45it/s]
1|8870|Loss: 0.5879954695701599:  34%|███▍      | 8870/25880 [1:50:10<3:31:09,  1.34it/s]
1|8871|Loss: 0.8374008536338806:  34%|███▍      | 8870/25880 [1:50:11<3:31:09,  1.34it/s]
1|8871|Loss: 0.8374008536338806:  34%|███▍      | 8871/25880 [1:50:11<3:26:01,  1.38it/s]
1|8872|Loss: 0.744697093963623:  34%|███▍      | 8871/25880 [1:50:11<3:26:01,  1.38it/s] 
1|8872|Loss: 0.744697093963623:  34%|███▍      | 8872/25880 [1:50:12<3:23:34,  1.39it/s]
1|8873|Loss: 0.9915605187416077:  34%|███▍      | 8872/25880 [1:50:12<3:23:34,  1.39it/s]
1|8873|Loss: 0.9915605187416077:  34%|███▍      | 8873/25880 [1:50:12<3:33:12,  1.33it/s]
1|8874|Loss: 0.7045782208442688:  34%|███▍      | 8873/25880 [1:50:13<3:33:12,  1.33it/s]
1|8874|Loss: 0.7045782208442688:  34%|███▍      | 8874/25880 [1:50:13<3:26:47,  1.37it/s]
1|8875|Loss: 0.9085462689399719:  34%|███▍      | 8874/25880 [1:50:14<3:26:47,  1.37it/s]
1|8875|Loss: 0.9085462689399719:  34%|███▍      | 8875/25880 [1:50:14<3:29:19,  1.35it/s]
1|8876|Loss: 0.9605647325515747:  34%|███▍      | 8875/25880 [1:50:14<3:29:19,  1.35it/s]
1|8876|Loss: 0.9605647325515747:  34%|███▍      | 8876/25880 [1:50:15<3:29:45,  1.35it/s]
1|8877|Loss: 0.7959209084510803:  34%|███▍      | 8876/25880 [1:50:15<3:29:45,  1.35it/s]
1|8877|Loss: 0.7959209084510803:  34%|███▍      | 8877/25880 [1:50:15<3:36:31,  1.31it/s]
1|8878|Loss: 0.8155941963195801:  34%|███▍      | 8877/25880 [1:50:16<3:36:31,  1.31it/s]
1|8878|Loss: 0.8155941963195801:  34%|███▍      | 8878/25880 [1:50:16<3:35:58,  1.31it/s]
1|8879|Loss: 0.8406791687011719:  34%|███▍      | 8878/25880 [1:50:17<3:35:58,  1.31it/s]
1|8879|Loss: 0.8406791687011719:  34%|███▍      | 8879/25880 [1:50:17<3:30:55,  1.34it/s]
1|8880|Loss: 0.7944183945655823:  34%|███▍      | 8879/25880 [1:50:17<3:30:55,  1.34it/s]
1|8880|Loss: 0.7944183945655823:  34%|███▍      | 8880/25880 [1:50:18<3:22:49,  1.40it/s]
1|8881|Loss: 0.9117928743362427:  34%|███▍      | 8880/25880 [1:50:18<3:22:49,  1.40it/s]
1|8881|Loss: 0.9117928743362427:  34%|███▍      | 8881/25880 [1:50:18<3:14:50,  1.45it/s]
1|8882|Loss: 0.8295251131057739:  34%|███▍      | 8881/25880 [1:50:19<3:14:50,  1.45it/s]
1|8882|Loss: 0.8295251131057739:  34%|███▍      | 8882/25880 [1:50:19<3:14:08,  1.46it/s]
1|8883|Loss: 1.033664584159851:  34%|███▍      | 8882/25880 [1:50:19<3:14:08,  1.46it/s] 
1|8883|Loss: 1.033664584159851:  34%|███▍      | 8883/25880 [1:50:19<3:09:25,  1.50it/s]
1|8884|Loss: 0.8658896088600159:  34%|███▍      | 8883/25880 [1:50:20<3:09:25,  1.50it/s]
1|8884|Loss: 0.8658896088600159:  34%|███▍      | 8884/25880 [1:50:20<3:04:57,  1.53it/s]
1|8885|Loss: 0.9184432029724121:  34%|███▍      | 8884/25880 [1:50:20<3:04:57,  1.53it/s]
1|8885|Loss: 0.9184432029724121:  34%|███▍      | 8885/25880 [1:50:21<3:07:48,  1.51it/s]
1|8886|Loss: 0.8902640342712402:  34%|███▍      | 8885/25880 [1:50:21<3:07:48,  1.51it/s]
1|8886|Loss: 0.8902640342712402:  34%|███▍      | 8886/25880 [1:50:21<3:11:31,  1.48it/s]
1|8887|Loss: 0.9037480354309082:  34%|███▍      | 8886/25880 [1:50:22<3:11:31,  1.48it/s]
1|8887|Loss: 0.9037480354309082:  34%|███▍      | 8887/25880 [1:50:22<3:09:57,  1.49it/s]
1|8888|Loss: 0.8484928607940674:  34%|███▍      | 8887/25880 [1:50:23<3:09:57,  1.49it/s]
1|8888|Loss: 0.8484928607940674:  34%|███▍      | 8888/25880 [1:50:23<3:13:26,  1.46it/s]
1|8889|Loss: 0.7992846369743347:  34%|███▍      | 8888/25880 [1:50:23<3:13:26,  1.46it/s]
1|8889|Loss: 0.7992846369743347:  34%|███▍      | 8889/25880 [1:50:24<3:22:33,  1.40it/s]
1|8890|Loss: 0.816274881362915:  34%|███▍      | 8889/25880 [1:50:24<3:22:33,  1.40it/s] 
1|8890|Loss: 0.816274881362915:  34%|███▍      | 8890/25880 [1:50:24<3:26:09,  1.37it/s]
1|8891|Loss: 0.8002201914787292:  34%|███▍      | 8890/25880 [1:50:25<3:26:09,  1.37it/s]
1|8891|Loss: 0.8002201914787292:  34%|███▍      | 8891/25880 [1:50:25<3:39:52,  1.29it/s]
1|8892|Loss: 0.7775654792785645:  34%|███▍      | 8891/25880 [1:50:26<3:39:52,  1.29it/s]
1|8892|Loss: 0.7775654792785645:  34%|███▍      | 8892/25880 [1:50:26<3:32:57,  1.33it/s]
1|8893|Loss: 0.8529970645904541:  34%|███▍      | 8892/25880 [1:50:26<3:32:57,  1.33it/s]
1|8893|Loss: 0.8529970645904541:  34%|███▍      | 8893/25880 [1:50:27<3:29:38,  1.35it/s]
1|8894|Loss: 0.7498691082000732:  34%|███▍      | 8893/25880 [1:50:27<3:29:38,  1.35it/s]
1|8894|Loss: 0.7498691082000732:  34%|███▍      | 8894/25880 [1:50:27<3:26:11,  1.37it/s]
1|8895|Loss: 0.7056000828742981:  34%|███▍      | 8894/25880 [1:50:28<3:26:11,  1.37it/s]
1|8895|Loss: 0.7056000828742981:  34%|███▍      | 8895/25880 [1:50:28<3:35:59,  1.31it/s]
1|8896|Loss: 0.7988909482955933:  34%|███▍      | 8895/25880 [1:50:29<3:35:59,  1.31it/s]
1|8896|Loss: 0.7988909482955933:  34%|███▍      | 8896/25880 [1:50:29<3:30:16,  1.35it/s]
1|8897|Loss: 0.8492023348808289:  34%|███▍      | 8896/25880 [1:50:29<3:30:16,  1.35it/s]
1|8897|Loss: 0.8492023348808289:  34%|███▍      | 8897/25880 [1:50:30<3:22:10,  1.40it/s]
1|8898|Loss: 0.9210776686668396:  34%|███▍      | 8897/25880 [1:50:30<3:22:10,  1.40it/s]
1|8898|Loss: 0.9210776686668396:  34%|███▍      | 8898/25880 [1:50:30<3:25:57,  1.37it/s]
1|8899|Loss: 0.729709804058075:  34%|███▍      | 8898/25880 [1:50:31<3:25:57,  1.37it/s] 
1|8899|Loss: 0.729709804058075:  34%|███▍      | 8899/25880 [1:50:31<3:44:47,  1.26it/s]
1|8900|Loss: 0.8261668682098389:  34%|███▍      | 8899/25880 [1:50:32<3:44:47,  1.26it/s]
1|8900|Loss: 0.8261668682098389:  34%|███▍      | 8900/25880 [1:50:32<3:34:30,  1.32it/s]
1|8901|Loss: 0.8099548816680908:  34%|███▍      | 8900/25880 [1:50:32<3:34:30,  1.32it/s]
1|8901|Loss: 0.8099548816680908:  34%|███▍      | 8901/25880 [1:50:33<3:23:30,  1.39it/s]
1|8902|Loss: 0.9194160103797913:  34%|███▍      | 8901/25880 [1:50:33<3:23:30,  1.39it/s]
1|8902|Loss: 0.9194160103797913:  34%|███▍      | 8902/25880 [1:50:33<3:33:09,  1.33it/s]
1|8903|Loss: 0.927123486995697:  34%|███▍      | 8902/25880 [1:50:34<3:33:09,  1.33it/s] 
1|8903|Loss: 0.927123486995697:  34%|███▍      | 8903/25880 [1:50:34<3:43:49,  1.26it/s]
1|8904|Loss: 0.844515860080719:  34%|███▍      | 8903/25880 [1:50:35<3:43:49,  1.26it/s]
1|8904|Loss: 0.844515860080719:  34%|███▍      | 8904/25880 [1:50:35<3:39:22,  1.29it/s]
1|8905|Loss: 0.8874024152755737:  34%|███▍      | 8904/25880 [1:50:35<3:39:22,  1.29it/s]
1|8905|Loss: 0.8874024152755737:  34%|███▍      | 8905/25880 [1:50:36<3:41:20,  1.28it/s]
1|8906|Loss: 0.950019359588623:  34%|███▍      | 8905/25880 [1:50:36<3:41:20,  1.28it/s] 
1|8906|Loss: 0.950019359588623:  34%|███▍      | 8906/25880 [1:50:37<3:32:39,  1.33it/s]
1|8907|Loss: 0.874047040939331:  34%|███▍      | 8906/25880 [1:50:37<3:32:39,  1.33it/s]
1|8907|Loss: 0.874047040939331:  34%|███▍      | 8907/25880 [1:50:37<3:15:59,  1.44it/s]
1|8908|Loss: 0.8824853301048279:  34%|███▍      | 8907/25880 [1:50:37<3:15:59,  1.44it/s]
1|8908|Loss: 0.8824853301048279:  34%|███▍      | 8908/25880 [1:50:38<2:56:58,  1.60it/s]
1|8909|Loss: 0.8027366399765015:  34%|███▍      | 8908/25880 [1:50:38<2:56:58,  1.60it/s]
1|8909|Loss: 0.8027366399765015:  34%|███▍      | 8909/25880 [1:50:38<2:58:27,  1.58it/s]
1|8910|Loss: 0.8141661286354065:  34%|███▍      | 8909/25880 [1:50:39<2:58:27,  1.58it/s]
1|8910|Loss: 0.8141661286354065:  34%|███▍      | 8910/25880 [1:50:39<2:59:04,  1.58it/s]
1|8911|Loss: 0.8930084109306335:  34%|███▍      | 8910/25880 [1:50:39<2:59:04,  1.58it/s]
1|8911|Loss: 0.8930084109306335:  34%|███▍      | 8911/25880 [1:50:40<3:06:16,  1.52it/s]
1|8912|Loss: 0.6883829832077026:  34%|███▍      | 8911/25880 [1:50:40<3:06:16,  1.52it/s]
1|8912|Loss: 0.6883829832077026:  34%|███▍      | 8912/25880 [1:50:40<3:19:35,  1.42it/s]
1|8913|Loss: 0.9018003940582275:  34%|███▍      | 8912/25880 [1:50:41<3:19:35,  1.42it/s]
1|8913|Loss: 0.9018003940582275:  34%|███▍      | 8913/25880 [1:50:41<3:17:31,  1.43it/s]
1|8914|Loss: 0.9027237892150879:  34%|███▍      | 8913/25880 [1:50:41<3:17:31,  1.43it/s]
1|8914|Loss: 0.9027237892150879:  34%|███▍      | 8914/25880 [1:50:42<3:17:14,  1.43it/s]
1|8915|Loss: 0.9120083451271057:  34%|███▍      | 8914/25880 [1:50:42<3:17:14,  1.43it/s]
1|8915|Loss: 0.9120083451271057:  34%|███▍      | 8915/25880 [1:50:43<3:24:38,  1.38it/s]
1|8916|Loss: 0.8101100325584412:  34%|███▍      | 8915/25880 [1:50:43<3:24:38,  1.38it/s]
1|8916|Loss: 0.8101100325584412:  34%|███▍      | 8916/25880 [1:50:43<3:26:06,  1.37it/s]
1|8917|Loss: 0.7143732309341431:  34%|███▍      | 8916/25880 [1:50:44<3:26:06,  1.37it/s]
1|8917|Loss: 0.7143732309341431:  34%|███▍      | 8917/25880 [1:50:44<3:25:50,  1.37it/s]
1|8918|Loss: 0.820932149887085:  34%|███▍      | 8917/25880 [1:50:44<3:25:50,  1.37it/s] 
1|8918|Loss: 0.820932149887085:  34%|███▍      | 8918/25880 [1:50:45<3:23:25,  1.39it/s]
1|8919|Loss: 0.8035149574279785:  34%|███▍      | 8918/25880 [1:50:45<3:23:25,  1.39it/s]
1|8919|Loss: 0.8035149574279785:  34%|███▍      | 8919/25880 [1:50:45<3:17:03,  1.43it/s]
1|8920|Loss: 0.7832955121994019:  34%|███▍      | 8919/25880 [1:50:46<3:17:03,  1.43it/s]
1|8920|Loss: 0.7832955121994019:  34%|███▍      | 8920/25880 [1:50:46<3:26:24,  1.37it/s]
1|8921|Loss: 0.8859091401100159:  34%|███▍      | 8920/25880 [1:50:47<3:26:24,  1.37it/s]
1|8921|Loss: 0.8859091401100159:  34%|███▍      | 8921/25880 [1:50:47<3:22:37,  1.39it/s]
1|8922|Loss: 0.8040757179260254:  34%|███▍      | 8921/25880 [1:50:47<3:22:37,  1.39it/s]
1|8922|Loss: 0.8040757179260254:  34%|███▍      | 8922/25880 [1:50:47<3:11:52,  1.47it/s]
1|8923|Loss: 0.837655782699585:  34%|███▍      | 8922/25880 [1:50:48<3:11:52,  1.47it/s] 
1|8923|Loss: 0.837655782699585:  34%|███▍      | 8923/25880 [1:50:48<3:23:26,  1.39it/s]
1|8924|Loss: 0.7440636157989502:  34%|███▍      | 8923/25880 [1:50:49<3:23:26,  1.39it/s]
1|8924|Loss: 0.7440636157989502:  34%|███▍      | 8924/25880 [1:50:49<3:18:16,  1.43it/s]
1|8925|Loss: 0.869766116142273:  34%|███▍      | 8924/25880 [1:50:49<3:18:16,  1.43it/s] 
1|8925|Loss: 0.869766116142273:  34%|███▍      | 8925/25880 [1:50:50<3:10:15,  1.49it/s]
1|8926|Loss: 0.908793032169342:  34%|███▍      | 8925/25880 [1:50:50<3:10:15,  1.49it/s]
1|8926|Loss: 0.908793032169342:  34%|███▍      | 8926/25880 [1:50:50<3:11:31,  1.48it/s]
1|8927|Loss: 0.9208095669746399:  34%|███▍      | 8926/25880 [1:50:51<3:11:31,  1.48it/s]
1|8927|Loss: 0.9208095669746399:  34%|███▍      | 8927/25880 [1:50:51<3:31:18,  1.34it/s]
1|8928|Loss: 0.8417819738388062:  34%|███▍      | 8927/25880 [1:50:52<3:31:18,  1.34it/s]
1|8928|Loss: 0.8417819738388062:  34%|███▍      | 8928/25880 [1:50:52<3:35:31,  1.31it/s]
1|8929|Loss: 0.7917830944061279:  34%|███▍      | 8928/25880 [1:50:52<3:35:31,  1.31it/s]
1|8929|Loss: 0.7917830944061279:  35%|███▍      | 8929/25880 [1:50:53<3:33:43,  1.32it/s]
1|8930|Loss: 0.9226260185241699:  35%|███▍      | 8929/25880 [1:50:53<3:33:43,  1.32it/s]
1|8930|Loss: 0.9226260185241699:  35%|███▍      | 8930/25880 [1:50:53<3:40:03,  1.28it/s]
1|8931|Loss: 0.8264129161834717:  35%|███▍      | 8930/25880 [1:50:54<3:40:03,  1.28it/s]
1|8931|Loss: 0.8264129161834717:  35%|███▍      | 8931/25880 [1:50:54<3:37:57,  1.30it/s]
1|8932|Loss: 0.8630605936050415:  35%|███▍      | 8931/25880 [1:50:55<3:37:57,  1.30it/s]
1|8932|Loss: 0.8630605936050415:  35%|███▍      | 8932/25880 [1:50:55<3:34:10,  1.32it/s]
1|8933|Loss: 0.9806170463562012:  35%|███▍      | 8932/25880 [1:50:55<3:34:10,  1.32it/s]
1|8933|Loss: 0.9806170463562012:  35%|███▍      | 8933/25880 [1:50:56<3:39:40,  1.29it/s]
1|8934|Loss: 0.9094389081001282:  35%|███▍      | 8933/25880 [1:50:56<3:39:40,  1.29it/s]
1|8934|Loss: 0.9094389081001282:  35%|███▍      | 8934/25880 [1:50:57<3:41:59,  1.27it/s]
1|8935|Loss: 0.8859361410140991:  35%|███▍      | 8934/25880 [1:50:57<3:41:59,  1.27it/s]
1|8935|Loss: 0.8859361410140991:  35%|███▍      | 8935/25880 [1:50:57<3:37:29,  1.30it/s]
1|8936|Loss: 0.9133579730987549:  35%|███▍      | 8935/25880 [1:50:58<3:37:29,  1.30it/s]
1|8936|Loss: 0.9133579730987549:  35%|███▍      | 8936/25880 [1:50:58<3:40:17,  1.28it/s]
1|8937|Loss: 0.768794059753418:  35%|███▍      | 8936/25880 [1:50:59<3:40:17,  1.28it/s] 
1|8937|Loss: 0.768794059753418:  35%|███▍      | 8937/25880 [1:50:59<3:42:53,  1.27it/s]
1|8938|Loss: 0.7762860059738159:  35%|███▍      | 8937/25880 [1:50:59<3:42:53,  1.27it/s]
1|8938|Loss: 0.7762860059738159:  35%|███▍      | 8938/25880 [1:50:59<3:20:22,  1.41it/s]
1|8939|Loss: 0.7572479248046875:  35%|███▍      | 8938/25880 [1:51:00<3:20:22,  1.41it/s]
1|8939|Loss: 0.7572479248046875:  35%|███▍      | 8939/25880 [1:51:00<3:25:26,  1.37it/s]
1|8940|Loss: 0.8331042528152466:  35%|███▍      | 8939/25880 [1:51:01<3:25:26,  1.37it/s]
1|8940|Loss: 0.8331042528152466:  35%|███▍      | 8940/25880 [1:51:01<3:23:06,  1.39it/s]
1|8941|Loss: 0.8653982877731323:  35%|███▍      | 8940/25880 [1:51:01<3:23:06,  1.39it/s]
1|8941|Loss: 0.8653982877731323:  35%|███▍      | 8941/25880 [1:51:02<3:16:39,  1.44it/s]
1|8942|Loss: 0.711820662021637:  35%|███▍      | 8941/25880 [1:51:02<3:16:39,  1.44it/s] 
1|8942|Loss: 0.711820662021637:  35%|███▍      | 8942/25880 [1:51:02<3:18:16,  1.42it/s]
1|8943|Loss: 0.8643835186958313:  35%|███▍      | 8942/25880 [1:51:03<3:18:16,  1.42it/s]
1|8943|Loss: 0.8643835186958313:  35%|███▍      | 8943/25880 [1:51:03<3:14:28,  1.45it/s]
1|8944|Loss: 0.7716925740242004:  35%|███▍      | 8943/25880 [1:51:03<3:14:28,  1.45it/s]
1|8944|Loss: 0.7716925740242004:  35%|███▍      | 8944/25880 [1:51:03<2:57:55,  1.59it/s]
1|8945|Loss: 0.8564563393592834:  35%|███▍      | 8944/25880 [1:51:04<2:57:55,  1.59it/s]
1|8945|Loss: 0.8564563393592834:  35%|███▍      | 8945/25880 [1:51:04<3:07:54,  1.50it/s]
1|8946|Loss: 0.9188419580459595:  35%|███▍      | 8945/25880 [1:51:05<3:07:54,  1.50it/s]
1|8946|Loss: 0.9188419580459595:  35%|███▍      | 8946/25880 [1:51:05<3:18:54,  1.42it/s]
1|8947|Loss: 0.9594592452049255:  35%|███▍      | 8946/25880 [1:51:05<3:18:54,  1.42it/s]
1|8947|Loss: 0.9594592452049255:  35%|███▍      | 8947/25880 [1:51:06<3:15:18,  1.45it/s]
1|8948|Loss: 0.7635221481323242:  35%|███▍      | 8947/25880 [1:51:06<3:15:18,  1.45it/s]
1|8948|Loss: 0.7635221481323242:  35%|███▍      | 8948/25880 [1:51:06<3:07:39,  1.50it/s]
1|8949|Loss: 0.8412261009216309:  35%|███▍      | 8948/25880 [1:51:07<3:07:39,  1.50it/s]
1|8949|Loss: 0.8412261009216309:  35%|███▍      | 8949/25880 [1:51:07<3:03:02,  1.54it/s]
1|8950|Loss: 0.8632174730300903:  35%|███▍      | 8949/25880 [1:51:07<3:03:02,  1.54it/s]
1|8950|Loss: 0.8632174730300903:  35%|███▍      | 8950/25880 [1:51:07<3:00:26,  1.56it/s]
1|8951|Loss: 0.8846972584724426:  35%|███▍      | 8950/25880 [1:51:08<3:00:26,  1.56it/s]
1|8951|Loss: 0.8846972584724426:  35%|███▍      | 8951/25880 [1:51:08<3:06:59,  1.51it/s]
1|8952|Loss: 0.9163170456886292:  35%|███▍      | 8951/25880 [1:51:09<3:06:59,  1.51it/s]
1|8952|Loss: 0.9163170456886292:  35%|███▍      | 8952/25880 [1:51:09<2:59:40,  1.57it/s]
1|8953|Loss: 1.034704327583313:  35%|███▍      | 8952/25880 [1:51:09<2:59:40,  1.57it/s] 
1|8953|Loss: 1.034704327583313:  35%|███▍      | 8953/25880 [1:51:09<3:05:15,  1.52it/s]
1|8954|Loss: 0.9523436427116394:  35%|███▍      | 8953/25880 [1:51:10<3:05:15,  1.52it/s]
1|8954|Loss: 0.9523436427116394:  35%|███▍      | 8954/25880 [1:51:10<3:20:36,  1.41it/s]
1|8955|Loss: 0.9266209006309509:  35%|███▍      | 8954/25880 [1:51:11<3:20:36,  1.41it/s]
1|8955|Loss: 0.9266209006309509:  35%|███▍      | 8955/25880 [1:51:11<3:17:13,  1.43it/s]
1|8956|Loss: 0.8435338735580444:  35%|███▍      | 8955/25880 [1:51:11<3:17:13,  1.43it/s]
1|8956|Loss: 0.8435338735580444:  35%|███▍      | 8956/25880 [1:51:12<3:22:00,  1.40it/s]
1|8957|Loss: 0.8419156074523926:  35%|███▍      | 8956/25880 [1:51:12<3:22:00,  1.40it/s]
1|8957|Loss: 0.8419156074523926:  35%|███▍      | 8957/25880 [1:51:13<3:29:05,  1.35it/s]
1|8958|Loss: 0.855642557144165:  35%|███▍      | 8957/25880 [1:51:13<3:29:05,  1.35it/s] 
1|8958|Loss: 0.855642557144165:  35%|███▍      | 8958/25880 [1:51:13<3:20:18,  1.41it/s]
1|8959|Loss: 0.8265940546989441:  35%|███▍      | 8958/25880 [1:51:13<3:20:18,  1.41it/s]
1|8959|Loss: 0.8265940546989441:  35%|███▍      | 8959/25880 [1:51:14<3:07:50,  1.50it/s]
1|8960|Loss: 0.9750142693519592:  35%|███▍      | 8959/25880 [1:51:14<3:07:50,  1.50it/s]
1|8960|Loss: 0.9750142693519592:  35%|███▍      | 8960/25880 [1:51:15<3:18:29,  1.42it/s]
1|8961|Loss: 0.9544086456298828:  35%|███▍      | 8960/25880 [1:51:15<3:18:29,  1.42it/s]
1|8961|Loss: 0.9544086456298828:  35%|███▍      | 8961/25880 [1:51:15<3:23:25,  1.39it/s]
1|8962|Loss: 0.7518687844276428:  35%|███▍      | 8961/25880 [1:51:16<3:23:25,  1.39it/s]
1|8962|Loss: 0.7518687844276428:  35%|███▍      | 8962/25880 [1:51:16<3:22:27,  1.39it/s]
1|8963|Loss: 0.8451313376426697:  35%|███▍      | 8962/25880 [1:51:16<3:22:27,  1.39it/s]
1|8963|Loss: 0.8451313376426697:  35%|███▍      | 8963/25880 [1:51:17<3:26:52,  1.36it/s]
1|8964|Loss: 1.0085649490356445:  35%|███▍      | 8963/25880 [1:51:17<3:26:52,  1.36it/s]
1|8964|Loss: 1.0085649490356445:  35%|███▍      | 8964/25880 [1:51:18<3:36:29,  1.30it/s]
1|8965|Loss: 0.8273252248764038:  35%|███▍      | 8964/25880 [1:51:18<3:36:29,  1.30it/s]
1|8965|Loss: 0.8273252248764038:  35%|███▍      | 8965/25880 [1:51:18<3:40:32,  1.28it/s]
1|8966|Loss: 0.8147164583206177:  35%|███▍      | 8965/25880 [1:51:19<3:40:32,  1.28it/s]
1|8966|Loss: 0.8147164583206177:  35%|███▍      | 8966/25880 [1:51:19<3:29:18,  1.35it/s]
1|8967|Loss: 1.0295395851135254:  35%|███▍      | 8966/25880 [1:51:19<3:29:18,  1.35it/s]
1|8967|Loss: 1.0295395851135254:  35%|███▍      | 8967/25880 [1:51:20<3:23:58,  1.38it/s]
1|8968|Loss: 0.855613112449646:  35%|███▍      | 8967/25880 [1:51:20<3:23:58,  1.38it/s] 
1|8968|Loss: 0.855613112449646:  35%|███▍      | 8968/25880 [1:51:20<3:22:07,  1.39it/s]
1|8969|Loss: 0.7814911603927612:  35%|███▍      | 8968/25880 [1:51:21<3:22:07,  1.39it/s]
1|8969|Loss: 0.7814911603927612:  35%|███▍      | 8969/25880 [1:51:21<3:16:21,  1.44it/s]
1|8970|Loss: 0.7974373698234558:  35%|███▍      | 8969/25880 [1:51:22<3:16:21,  1.44it/s]
1|8970|Loss: 0.7974373698234558:  35%|███▍      | 8970/25880 [1:51:22<3:25:45,  1.37it/s]
1|8971|Loss: 0.8753957152366638:  35%|███▍      | 8970/25880 [1:51:22<3:25:45,  1.37it/s]
1|8971|Loss: 0.8753957152366638:  35%|███▍      | 8971/25880 [1:51:23<3:21:32,  1.40it/s]
1|8972|Loss: 0.8127402663230896:  35%|███▍      | 8971/25880 [1:51:23<3:21:32,  1.40it/s]
1|8972|Loss: 0.8127402663230896:  35%|███▍      | 8972/25880 [1:51:23<3:21:22,  1.40it/s]
1|8973|Loss: 0.796897828578949:  35%|███▍      | 8972/25880 [1:51:24<3:21:22,  1.40it/s] 
1|8973|Loss: 0.796897828578949:  35%|███▍      | 8973/25880 [1:51:24<3:22:58,  1.39it/s]
1|8974|Loss: 0.8740803599357605:  35%|███▍      | 8973/25880 [1:51:24<3:22:58,  1.39it/s]
1|8974|Loss: 0.8740803599357605:  35%|███▍      | 8974/25880 [1:51:25<3:17:58,  1.42it/s]
1|8975|Loss: 0.8461645245552063:  35%|███▍      | 8974/25880 [1:51:25<3:17:58,  1.42it/s]
1|8975|Loss: 0.8461645245552063:  35%|███▍      | 8975/25880 [1:51:26<3:31:57,  1.33it/s]
1|8976|Loss: 0.8532008528709412:  35%|███▍      | 8975/25880 [1:51:26<3:31:57,  1.33it/s]
1|8976|Loss: 0.8532008528709412:  35%|███▍      | 8976/25880 [1:51:26<3:21:39,  1.40it/s]
1|8977|Loss: 0.8836283087730408:  35%|███▍      | 8976/25880 [1:51:27<3:21:39,  1.40it/s]
1|8977|Loss: 0.8836283087730408:  35%|███▍      | 8977/25880 [1:51:27<3:08:22,  1.50it/s]
1|8978|Loss: 0.7903888821601868:  35%|███▍      | 8977/25880 [1:51:27<3:08:22,  1.50it/s]
1|8978|Loss: 0.7903888821601868:  35%|███▍      | 8978/25880 [1:51:27<3:03:01,  1.54it/s]
1|8979|Loss: 0.8061363101005554:  35%|███▍      | 8978/25880 [1:51:28<3:03:01,  1.54it/s]
1|8979|Loss: 0.8061363101005554:  35%|███▍      | 8979/25880 [1:51:28<3:16:43,  1.43it/s]
1|8980|Loss: 0.8995822072029114:  35%|███▍      | 8979/25880 [1:51:29<3:16:43,  1.43it/s]
1|8980|Loss: 0.8995822072029114:  35%|███▍      | 8980/25880 [1:51:29<3:10:22,  1.48it/s]
1|8981|Loss: 0.7365321516990662:  35%|███▍      | 8980/25880 [1:51:29<3:10:22,  1.48it/s]
1|8981|Loss: 0.7365321516990662:  35%|███▍      | 8981/25880 [1:51:30<3:16:30,  1.43it/s]
1|8982|Loss: 1.0032448768615723:  35%|███▍      | 8981/25880 [1:51:30<3:16:30,  1.43it/s]
1|8982|Loss: 1.0032448768615723:  35%|███▍      | 8982/25880 [1:51:30<3:21:22,  1.40it/s]
1|8983|Loss: 0.8122397661209106:  35%|███▍      | 8982/25880 [1:51:31<3:21:22,  1.40it/s]
1|8983|Loss: 0.8122397661209106:  35%|███▍      | 8983/25880 [1:51:31<3:15:35,  1.44it/s]
1|8984|Loss: 0.6741284728050232:  35%|███▍      | 8983/25880 [1:51:31<3:15:35,  1.44it/s]
1|8984|Loss: 0.6741284728050232:  35%|███▍      | 8984/25880 [1:51:32<3:17:13,  1.43it/s]
1|8985|Loss: 0.7961171865463257:  35%|███▍      | 8984/25880 [1:51:32<3:17:13,  1.43it/s]
1|8985|Loss: 0.7961171865463257:  35%|███▍      | 8985/25880 [1:51:32<3:09:46,  1.48it/s]
1|8986|Loss: 0.8736879229545593:  35%|███▍      | 8985/25880 [1:51:33<3:09:46,  1.48it/s]
1|8986|Loss: 0.8736879229545593:  35%|███▍      | 8986/25880 [1:51:33<3:09:44,  1.48it/s]
1|8987|Loss: 0.7897164225578308:  35%|███▍      | 8986/25880 [1:51:33<3:09:44,  1.48it/s]
1|8987|Loss: 0.7897164225578308:  35%|███▍      | 8987/25880 [1:51:34<3:07:36,  1.50it/s]
1|8988|Loss: 0.797761857509613:  35%|███▍      | 8987/25880 [1:51:34<3:07:36,  1.50it/s] 
1|8988|Loss: 0.797761857509613:  35%|███▍      | 8988/25880 [1:51:34<3:12:18,  1.46it/s]
1|8989|Loss: 0.9079291820526123:  35%|███▍      | 8988/25880 [1:51:35<3:12:18,  1.46it/s]
1|8989|Loss: 0.9079291820526123:  35%|███▍      | 8989/25880 [1:51:35<3:23:46,  1.38it/s]
1|8990|Loss: 0.8031282424926758:  35%|███▍      | 8989/25880 [1:51:36<3:23:46,  1.38it/s]
1|8990|Loss: 0.8031282424926758:  35%|███▍      | 8990/25880 [1:51:36<3:24:03,  1.38it/s]
1|8991|Loss: 0.8137320876121521:  35%|███▍      | 8990/25880 [1:51:36<3:24:03,  1.38it/s]
1|8991|Loss: 0.8137320876121521:  35%|███▍      | 8991/25880 [1:51:37<3:30:56,  1.33it/s]
1|8992|Loss: 0.7411499619483948:  35%|███▍      | 8991/25880 [1:51:37<3:30:56,  1.33it/s]
1|8992|Loss: 0.7411499619483948:  35%|███▍      | 8992/25880 [1:51:37<3:29:22,  1.34it/s]
1|8993|Loss: 0.8305313587188721:  35%|███▍      | 8992/25880 [1:51:38<3:29:22,  1.34it/s]
1|8993|Loss: 0.8305313587188721:  35%|███▍      | 8993/25880 [1:51:38<3:37:42,  1.29it/s]
1|8994|Loss: 0.8729193210601807:  35%|███▍      | 8993/25880 [1:51:39<3:37:42,  1.29it/s]
1|8994|Loss: 0.8729193210601807:  35%|███▍      | 8994/25880 [1:51:39<3:35:30,  1.31it/s]
1|8995|Loss: 0.7945208549499512:  35%|███▍      | 8994/25880 [1:51:39<3:35:30,  1.31it/s]
1|8995|Loss: 0.7945208549499512:  35%|███▍      | 8995/25880 [1:51:40<3:36:59,  1.30it/s]
1|8996|Loss: 0.821245014667511:  35%|███▍      | 8995/25880 [1:51:40<3:36:59,  1.30it/s] 
1|8996|Loss: 0.821245014667511:  35%|███▍      | 8996/25880 [1:51:41<3:34:38,  1.31it/s]
1|8997|Loss: 0.7924029231071472:  35%|███▍      | 8996/25880 [1:51:41<3:34:38,  1.31it/s]
1|8997|Loss: 0.7924029231071472:  35%|███▍      | 8997/25880 [1:51:41<3:32:57,  1.32it/s]
1|8998|Loss: 0.9173845052719116:  35%|███▍      | 8997/25880 [1:51:42<3:32:57,  1.32it/s]
1|8998|Loss: 0.9173845052719116:  35%|███▍      | 8998/25880 [1:51:42<3:32:07,  1.33it/s]
1|8999|Loss: 0.8776128888130188:  35%|███▍      | 8998/25880 [1:51:42<3:32:07,  1.33it/s]
1|8999|Loss: 0.8776128888130188:  35%|███▍      | 8999/25880 [1:51:43<3:24:43,  1.37it/s]
1|9000|Loss: 0.8373078107833862:  35%|███▍      | 8999/25880 [1:51:43<3:24:43,  1.37it/s]
1|9000|Loss: 0.8373078107833862:  35%|███▍      | 9000/25880 [1:51:43<3:30:39,  1.34it/s]
1|9001|Loss: 0.7121950387954712:  35%|███▍      | 9000/25880 [1:51:44<3:30:39,  1.34it/s]
1|9001|Loss: 0.7121950387954712:  35%|███▍      | 9001/25880 [1:51:44<3:49:07,  1.23it/s]
1|9002|Loss: 0.8915854096412659:  35%|███▍      | 9001/25880 [1:51:45<3:49:07,  1.23it/s]
1|9002|Loss: 0.8915854096412659:  35%|███▍      | 9002/25880 [1:51:45<3:32:34,  1.32it/s]
1|9003|Loss: 0.9494094252586365:  35%|███▍      | 9002/25880 [1:51:45<3:32:34,  1.32it/s]
1|9003|Loss: 0.9494094252586365:  35%|███▍      | 9003/25880 [1:51:46<3:20:17,  1.40it/s]
1|9004|Loss: 0.8513457775115967:  35%|███▍      | 9003/25880 [1:51:46<3:20:17,  1.40it/s]
1|9004|Loss: 0.8513457775115967:  35%|███▍      | 9004/25880 [1:51:46<3:14:41,  1.44it/s]
1|9005|Loss: 0.7885302901268005:  35%|███▍      | 9004/25880 [1:51:47<3:14:41,  1.44it/s]
1|9005|Loss: 0.7885302901268005:  35%|███▍      | 9005/25880 [1:51:47<2:54:00,  1.62it/s]
1|9006|Loss: 0.8772732019424438:  35%|███▍      | 9005/25880 [1:51:47<2:54:00,  1.62it/s]
1|9006|Loss: 0.8772732019424438:  35%|███▍      | 9006/25880 [1:51:47<2:58:17,  1.58it/s]
1|9007|Loss: 0.8907592296600342:  35%|███▍      | 9006/25880 [1:51:48<2:58:17,  1.58it/s]
1|9007|Loss: 0.8907592296600342:  35%|███▍      | 9007/25880 [1:51:48<3:06:17,  1.51it/s]
1|9008|Loss: 0.7145307064056396:  35%|███▍      | 9007/25880 [1:51:49<3:06:17,  1.51it/s]
1|9008|Loss: 0.7145307064056396:  35%|███▍      | 9008/25880 [1:51:49<3:11:43,  1.47it/s]
1|9009|Loss: 0.770998477935791:  35%|███▍      | 9008/25880 [1:51:49<3:11:43,  1.47it/s] 
1|9009|Loss: 0.770998477935791:  35%|███▍      | 9009/25880 [1:51:50<3:16:21,  1.43it/s]
1|9010|Loss: 0.8787186741828918:  35%|███▍      | 9009/25880 [1:51:50<3:16:21,  1.43it/s]
1|9010|Loss: 0.8787186741828918:  35%|███▍      | 9010/25880 [1:51:50<3:20:27,  1.40it/s]
1|9011|Loss: 0.8199356198310852:  35%|███▍      | 9010/25880 [1:51:51<3:20:27,  1.40it/s]
1|9011|Loss: 0.8199356198310852:  35%|███▍      | 9011/25880 [1:51:51<3:28:54,  1.35it/s]
1|9012|Loss: 1.0567141771316528:  35%|███▍      | 9011/25880 [1:51:52<3:28:54,  1.35it/s]
1|9012|Loss: 1.0567141771316528:  35%|███▍      | 9012/25880 [1:51:52<3:29:39,  1.34it/s]
1|9013|Loss: 0.5619359612464905:  35%|███▍      | 9012/25880 [1:51:53<3:29:39,  1.34it/s]
1|9013|Loss: 0.5619359612464905:  35%|███▍      | 9013/25880 [1:51:53<4:29:07,  1.04it/s]
1|9014|Loss: 0.7753905057907104:  35%|███▍      | 9013/25880 [1:51:54<4:29:07,  1.04it/s]
1|9014|Loss: 0.7753905057907104:  35%|███▍      | 9014/25880 [1:51:54<4:26:47,  1.05it/s]
1|9015|Loss: 0.8337075710296631:  35%|███▍      | 9014/25880 [1:51:55<4:26:47,  1.05it/s]
1|9015|Loss: 0.8337075710296631:  35%|███▍      | 9015/25880 [1:51:55<3:57:18,  1.18it/s]
1|9016|Loss: 0.8974993824958801:  35%|███▍      | 9015/25880 [1:51:55<3:57:18,  1.18it/s]
1|9016|Loss: 0.8974993824958801:  35%|███▍      | 9016/25880 [1:51:56<3:37:08,  1.29it/s]
1|9017|Loss: 0.8490743041038513:  35%|███▍      | 9016/25880 [1:51:56<3:37:08,  1.29it/s]
1|9017|Loss: 0.8490743041038513:  35%|███▍      | 9017/25880 [1:51:56<3:25:44,  1.37it/s]
1|9018|Loss: 0.753620982170105:  35%|███▍      | 9017/25880 [1:51:56<3:25:44,  1.37it/s] 
1|9018|Loss: 0.753620982170105:  35%|███▍      | 9018/25880 [1:51:57<3:08:00,  1.49it/s]
1|9019|Loss: 0.8889914155006409:  35%|███▍      | 9018/25880 [1:51:57<3:08:00,  1.49it/s]
1|9019|Loss: 0.8889914155006409:  35%|███▍      | 9019/25880 [1:51:57<3:02:48,  1.54it/s]
1|9020|Loss: 1.0128520727157593:  35%|███▍      | 9019/25880 [1:51:58<3:02:48,  1.54it/s]
1|9020|Loss: 1.0128520727157593:  35%|███▍      | 9020/25880 [1:51:58<3:06:29,  1.51it/s]
1|9021|Loss: 0.8325842022895813:  35%|███▍      | 9020/25880 [1:51:58<3:06:29,  1.51it/s]
1|9021|Loss: 0.8325842022895813:  35%|███▍      | 9021/25880 [1:51:59<3:11:13,  1.47it/s]
1|9022|Loss: 0.8323221802711487:  35%|███▍      | 9021/25880 [1:51:59<3:11:13,  1.47it/s]
1|9022|Loss: 0.8323221802711487:  35%|███▍      | 9022/25880 [1:51:59<3:16:12,  1.43it/s]
1|9023|Loss: 0.8494001626968384:  35%|███▍      | 9022/25880 [1:52:00<3:16:12,  1.43it/s]
1|9023|Loss: 0.8494001626968384:  35%|███▍      | 9023/25880 [1:52:00<3:17:41,  1.42it/s]
1|9024|Loss: 0.7811557054519653:  35%|███▍      | 9023/25880 [1:52:01<3:17:41,  1.42it/s]
1|9024|Loss: 0.7811557054519653:  35%|███▍      | 9024/25880 [1:52:01<3:22:56,  1.38it/s]
1|9025|Loss: 0.8214128613471985:  35%|███▍      | 9024/25880 [1:52:01<3:22:56,  1.38it/s]
1|9025|Loss: 0.8214128613471985:  35%|███▍      | 9025/25880 [1:52:02<3:15:46,  1.43it/s]
1|9026|Loss: 1.0288901329040527:  35%|███▍      | 9025/25880 [1:52:02<3:15:46,  1.43it/s]
1|9026|Loss: 1.0288901329040527:  35%|███▍      | 9026/25880 [1:52:02<3:13:38,  1.45it/s]
1|9027|Loss: 0.791558563709259:  35%|███▍      | 9026/25880 [1:52:03<3:13:38,  1.45it/s] 
1|9027|Loss: 0.791558563709259:  35%|███▍      | 9027/25880 [1:52:03<3:10:35,  1.47it/s]
1|9028|Loss: 0.8407098054885864:  35%|███▍      | 9027/25880 [1:52:03<3:10:35,  1.47it/s]
1|9028|Loss: 0.8407098054885864:  35%|███▍      | 9028/25880 [1:52:04<3:29:18,  1.34it/s]
1|9029|Loss: 0.8845581412315369:  35%|███▍      | 9028/25880 [1:52:04<3:29:18,  1.34it/s]
1|9029|Loss: 0.8845581412315369:  35%|███▍      | 9029/25880 [1:52:05<3:48:49,  1.23it/s]
1|9030|Loss: 0.8187393546104431:  35%|███▍      | 9029/25880 [1:52:05<3:48:49,  1.23it/s]
1|9030|Loss: 0.8187393546104431:  35%|███▍      | 9030/25880 [1:52:06<3:54:25,  1.20it/s]
1|9031|Loss: 0.9510779976844788:  35%|███▍      | 9030/25880 [1:52:06<3:54:25,  1.20it/s]
1|9031|Loss: 0.9510779976844788:  35%|███▍      | 9031/25880 [1:52:06<3:42:32,  1.26it/s]
1|9032|Loss: 0.9113907814025879:  35%|███▍      | 9031/25880 [1:52:07<3:42:32,  1.26it/s]
1|9032|Loss: 0.9113907814025879:  35%|███▍      | 9032/25880 [1:52:07<3:45:53,  1.24it/s]
1|9033|Loss: 0.9200796484947205:  35%|███▍      | 9032/25880 [1:52:08<3:45:53,  1.24it/s]
1|9033|Loss: 0.9200796484947205:  35%|███▍      | 9033/25880 [1:52:08<3:36:55,  1.29it/s]
1|9034|Loss: 0.9600827693939209:  35%|███▍      | 9033/25880 [1:52:08<3:36:55,  1.29it/s]
1|9034|Loss: 0.9600827693939209:  35%|███▍      | 9034/25880 [1:52:08<3:20:02,  1.40it/s]
1|9035|Loss: 0.8748440742492676:  35%|███▍      | 9034/25880 [1:52:09<3:20:02,  1.40it/s]
1|9035|Loss: 0.8748440742492676:  35%|███▍      | 9035/25880 [1:52:09<3:11:18,  1.47it/s]
1|9036|Loss: 0.8882002234458923:  35%|███▍      | 9035/25880 [1:52:09<3:11:18,  1.47it/s]
1|9036|Loss: 0.8882002234458923:  35%|███▍      | 9036/25880 [1:52:10<3:21:57,  1.39it/s]
1|9037|Loss: 0.7747578620910645:  35%|███▍      | 9036/25880 [1:52:10<3:21:57,  1.39it/s]
1|9037|Loss: 0.7747578620910645:  35%|███▍      | 9037/25880 [1:52:11<3:25:48,  1.36it/s]
1|9038|Loss: 0.9040294289588928:  35%|███▍      | 9037/25880 [1:52:11<3:25:48,  1.36it/s]
1|9038|Loss: 0.9040294289588928:  35%|███▍      | 9038/25880 [1:52:11<3:24:09,  1.37it/s]
1|9039|Loss: 0.838681697845459:  35%|███▍      | 9038/25880 [1:52:12<3:24:09,  1.37it/s] 
1|9039|Loss: 0.838681697845459:  35%|███▍      | 9039/25880 [1:52:12<3:22:09,  1.39it/s]
1|9040|Loss: 0.9952425360679626:  35%|███▍      | 9039/25880 [1:52:12<3:22:09,  1.39it/s]
1|9040|Loss: 0.9952425360679626:  35%|███▍      | 9040/25880 [1:52:13<3:20:51,  1.40it/s]
1|9041|Loss: 0.8559966087341309:  35%|███▍      | 9040/25880 [1:52:13<3:20:51,  1.40it/s]
1|9041|Loss: 0.8559966087341309:  35%|███▍      | 9041/25880 [1:52:14<3:22:44,  1.38it/s]
1|9042|Loss: 0.8851321339607239:  35%|███▍      | 9041/25880 [1:52:14<3:22:44,  1.38it/s]
1|9042|Loss: 0.8851321339607239:  35%|███▍      | 9042/25880 [1:52:14<3:25:02,  1.37it/s]
1|9043|Loss: 0.928785502910614:  35%|███▍      | 9042/25880 [1:52:15<3:25:02,  1.37it/s] 
1|9043|Loss: 0.928785502910614:  35%|███▍      | 9043/25880 [1:52:15<3:29:56,  1.34it/s]
1|9044|Loss: 0.8510466814041138:  35%|███▍      | 9043/25880 [1:52:15<3:29:56,  1.34it/s]
1|9044|Loss: 0.8510466814041138:  35%|███▍      | 9044/25880 [1:52:16<3:39:30,  1.28it/s]
1|9045|Loss: 0.8063905835151672:  35%|███▍      | 9044/25880 [1:52:16<3:39:30,  1.28it/s]
1|9045|Loss: 0.8063905835151672:  35%|███▍      | 9045/25880 [1:52:17<3:39:33,  1.28it/s]
1|9046|Loss: 1.0016186237335205:  35%|███▍      | 9045/25880 [1:52:17<3:39:33,  1.28it/s]
1|9046|Loss: 1.0016186237335205:  35%|███▍      | 9046/25880 [1:52:17<3:33:55,  1.31it/s]
1|9047|Loss: 0.810524582862854:  35%|███▍      | 9046/25880 [1:52:18<3:33:55,  1.31it/s] 
1|9047|Loss: 0.810524582862854:  35%|███▍      | 9047/25880 [1:52:18<3:31:06,  1.33it/s]
1|9048|Loss: 0.7747895121574402:  35%|███▍      | 9047/25880 [1:52:19<3:31:06,  1.33it/s]
1|9048|Loss: 0.7747895121574402:  35%|███▍      | 9048/25880 [1:52:19<3:29:40,  1.34it/s]
1|9049|Loss: 1.0464098453521729:  35%|███▍      | 9048/25880 [1:52:19<3:29:40,  1.34it/s]
1|9049|Loss: 1.0464098453521729:  35%|███▍      | 9049/25880 [1:52:20<3:44:18,  1.25it/s]
1|9050|Loss: 0.8336976766586304:  35%|███▍      | 9049/25880 [1:52:20<3:44:18,  1.25it/s]
1|9050|Loss: 0.8336976766586304:  35%|███▍      | 9050/25880 [1:52:21<3:49:45,  1.22it/s]
1|9051|Loss: 0.9328823089599609:  35%|███▍      | 9050/25880 [1:52:21<3:49:45,  1.22it/s]
1|9051|Loss: 0.9328823089599609:  35%|███▍      | 9051/25880 [1:52:21<3:51:52,  1.21it/s]
1|9052|Loss: 0.8395258784294128:  35%|███▍      | 9051/25880 [1:52:22<3:51:52,  1.21it/s]
1|9052|Loss: 0.8395258784294128:  35%|███▍      | 9052/25880 [1:52:22<3:55:41,  1.19it/s]
1|9053|Loss: 0.6713021397590637:  35%|███▍      | 9052/25880 [1:52:23<3:55:41,  1.19it/s]
1|9053|Loss: 0.6713021397590637:  35%|███▍      | 9053/25880 [1:52:23<4:02:11,  1.16it/s]
1|9054|Loss: 0.810009777545929:  35%|███▍      | 9053/25880 [1:52:24<4:02:11,  1.16it/s] 
1|9054|Loss: 0.810009777545929:  35%|███▍      | 9054/25880 [1:52:24<3:40:15,  1.27it/s]
1|9055|Loss: 0.8380699157714844:  35%|███▍      | 9054/25880 [1:52:24<3:40:15,  1.27it/s]
1|9055|Loss: 0.8380699157714844:  35%|███▍      | 9055/25880 [1:52:24<3:17:26,  1.42it/s]
1|9056|Loss: 0.8522250652313232:  35%|███▍      | 9055/25880 [1:52:25<3:17:26,  1.42it/s]
1|9056|Loss: 0.8522250652313232:  35%|███▍      | 9056/25880 [1:52:25<3:33:13,  1.32it/s]
1|9057|Loss: 0.7808613181114197:  35%|███▍      | 9056/25880 [1:52:26<3:33:13,  1.32it/s]
1|9057|Loss: 0.7808613181114197:  35%|███▍      | 9057/25880 [1:52:26<3:37:09,  1.29it/s]
1|9058|Loss: 1.0271623134613037:  35%|███▍      | 9057/25880 [1:52:27<3:37:09,  1.29it/s]
1|9058|Loss: 1.0271623134613037:  35%|███▌      | 9058/25880 [1:52:27<3:33:31,  1.31it/s]
1|9059|Loss: 0.8025317788124084:  35%|███▌      | 9058/25880 [1:52:27<3:33:31,  1.31it/s]
1|9059|Loss: 0.8025317788124084:  35%|███▌      | 9059/25880 [1:52:28<3:37:12,  1.29it/s]
1|9060|Loss: 0.9133666753768921:  35%|███▌      | 9059/25880 [1:52:28<3:37:12,  1.29it/s]
1|9060|Loss: 0.9133666753768921:  35%|███▌      | 9060/25880 [1:52:28<3:20:25,  1.40it/s]
1|9061|Loss: 0.8109135031700134:  35%|███▌      | 9060/25880 [1:52:29<3:20:25,  1.40it/s]
1|9061|Loss: 0.8109135031700134:  35%|███▌      | 9061/25880 [1:52:29<3:24:44,  1.37it/s]
1|9062|Loss: 0.7223113179206848:  35%|███▌      | 9061/25880 [1:52:29<3:24:44,  1.37it/s]
1|9062|Loss: 0.7223113179206848:  35%|███▌      | 9062/25880 [1:52:30<3:41:47,  1.26it/s]
1|9063|Loss: 0.9028351902961731:  35%|███▌      | 9062/25880 [1:52:30<3:41:47,  1.26it/s]
1|9063|Loss: 0.9028351902961731:  35%|███▌      | 9063/25880 [1:52:31<3:40:24,  1.27it/s]
1|9064|Loss: 0.9426239132881165:  35%|███▌      | 9063/25880 [1:52:31<3:40:24,  1.27it/s]
1|9064|Loss: 0.9426239132881165:  35%|███▌      | 9064/25880 [1:52:31<3:29:41,  1.34it/s]
1|9065|Loss: 0.9041895270347595:  35%|███▌      | 9064/25880 [1:52:32<3:29:41,  1.34it/s]
1|9065|Loss: 0.9041895270347595:  35%|███▌      | 9065/25880 [1:52:32<3:26:37,  1.36it/s]
1|9066|Loss: 0.8404493927955627:  35%|███▌      | 9065/25880 [1:52:32<3:26:37,  1.36it/s]
1|9066|Loss: 0.8404493927955627:  35%|███▌      | 9066/25880 [1:52:33<3:26:04,  1.36it/s]
1|9067|Loss: 0.8047701120376587:  35%|███▌      | 9066/25880 [1:52:33<3:26:04,  1.36it/s]
1|9067|Loss: 0.8047701120376587:  35%|███▌      | 9067/25880 [1:52:33<3:23:29,  1.38it/s]
1|9068|Loss: 0.8812424540519714:  35%|███▌      | 9067/25880 [1:52:34<3:23:29,  1.38it/s]
1|9068|Loss: 0.8812424540519714:  35%|███▌      | 9068/25880 [1:52:34<3:30:28,  1.33it/s]
1|9069|Loss: 0.8259589672088623:  35%|███▌      | 9068/25880 [1:52:35<3:30:28,  1.33it/s]
1|9069|Loss: 0.8259589672088623:  35%|███▌      | 9069/25880 [1:52:35<3:20:11,  1.40it/s]
1|9070|Loss: 0.8935737609863281:  35%|███▌      | 9069/25880 [1:52:35<3:20:11,  1.40it/s]
1|9070|Loss: 0.8935737609863281:  35%|███▌      | 9070/25880 [1:52:36<3:09:06,  1.48it/s]
1|9071|Loss: 0.9064201712608337:  35%|███▌      | 9070/25880 [1:52:36<3:09:06,  1.48it/s]
1|9071|Loss: 0.9064201712608337:  35%|███▌      | 9071/25880 [1:52:36<3:09:06,  1.48it/s]
1|9072|Loss: 0.7388840317726135:  35%|███▌      | 9071/25880 [1:52:37<3:09:06,  1.48it/s]
1|9072|Loss: 0.7388840317726135:  35%|███▌      | 9072/25880 [1:52:37<2:54:23,  1.61it/s]
1|9073|Loss: 0.9159747958183289:  35%|███▌      | 9072/25880 [1:52:37<2:54:23,  1.61it/s]
1|9073|Loss: 0.9159747958183289:  35%|███▌      | 9073/25880 [1:52:37<2:56:35,  1.59it/s]
1|9074|Loss: 0.7650769948959351:  35%|███▌      | 9073/25880 [1:52:38<2:56:35,  1.59it/s]
1|9074|Loss: 0.7650769948959351:  35%|███▌      | 9074/25880 [1:52:38<3:11:34,  1.46it/s]
1|9075|Loss: 0.7596376538276672:  35%|███▌      | 9074/25880 [1:52:39<3:11:34,  1.46it/s]
1|9075|Loss: 0.7596376538276672:  35%|███▌      | 9075/25880 [1:52:39<3:16:49,  1.42it/s]
1|9076|Loss: 0.7078887224197388:  35%|███▌      | 9075/25880 [1:52:39<3:16:49,  1.42it/s]
1|9076|Loss: 0.7078887224197388:  35%|███▌      | 9076/25880 [1:52:40<3:18:42,  1.41it/s]
1|9077|Loss: 0.7792831659317017:  35%|███▌      | 9076/25880 [1:52:40<3:18:42,  1.41it/s]
1|9077|Loss: 0.7792831659317017:  35%|███▌      | 9077/25880 [1:52:40<3:21:06,  1.39it/s]
1|9078|Loss: 0.819155216217041:  35%|███▌      | 9077/25880 [1:52:41<3:21:06,  1.39it/s] 
1|9078|Loss: 0.819155216217041:  35%|███▌      | 9078/25880 [1:52:41<3:16:50,  1.42it/s]
1|9079|Loss: 0.771055281162262:  35%|███▌      | 9078/25880 [1:52:41<3:16:50,  1.42it/s]
1|9079|Loss: 0.771055281162262:  35%|███▌      | 9079/25880 [1:52:42<3:11:21,  1.46it/s]
1|9080|Loss: 0.8683476448059082:  35%|███▌      | 9079/25880 [1:52:42<3:11:21,  1.46it/s]
1|9080|Loss: 0.8683476448059082:  35%|███▌      | 9080/25880 [1:52:42<3:02:10,  1.54it/s]
1|9081|Loss: 0.9486731290817261:  35%|███▌      | 9080/25880 [1:52:43<3:02:10,  1.54it/s]
1|9081|Loss: 0.9486731290817261:  35%|███▌      | 9081/25880 [1:52:43<3:07:16,  1.49it/s]
1|9082|Loss: 0.7492091655731201:  35%|███▌      | 9081/25880 [1:52:43<3:07:16,  1.49it/s]
1|9082|Loss: 0.7492091655731201:  35%|███▌      | 9082/25880 [1:52:44<2:58:48,  1.57it/s]
1|9083|Loss: 0.9030998945236206:  35%|███▌      | 9082/25880 [1:52:44<2:58:48,  1.57it/s]
1|9083|Loss: 0.9030998945236206:  35%|███▌      | 9083/25880 [1:52:44<2:56:33,  1.59it/s]
1|9084|Loss: 0.6559527516365051:  35%|███▌      | 9083/25880 [1:52:45<2:56:33,  1.59it/s]
1|9084|Loss: 0.6559527516365051:  35%|███▌      | 9084/25880 [1:52:45<3:12:01,  1.46it/s]
1|9085|Loss: 0.9106214642524719:  35%|███▌      | 9084/25880 [1:52:45<3:12:01,  1.46it/s]
1|9085|Loss: 0.9106214642524719:  35%|███▌      | 9085/25880 [1:52:46<3:12:31,  1.45it/s]
1|9086|Loss: 0.9424238204956055:  35%|███▌      | 9085/25880 [1:52:46<3:12:31,  1.45it/s]
1|9086|Loss: 0.9424238204956055:  35%|███▌      | 9086/25880 [1:52:46<3:22:52,  1.38it/s]
1|9087|Loss: 0.807628870010376:  35%|███▌      | 9086/25880 [1:52:47<3:22:52,  1.38it/s] 
1|9087|Loss: 0.807628870010376:  35%|███▌      | 9087/25880 [1:52:47<3:33:44,  1.31it/s]
1|9088|Loss: 0.8521754145622253:  35%|███▌      | 9087/25880 [1:52:48<3:33:44,  1.31it/s]
1|9088|Loss: 0.8521754145622253:  35%|███▌      | 9088/25880 [1:52:48<3:41:32,  1.26it/s]
1|9089|Loss: 0.9471291899681091:  35%|███▌      | 9088/25880 [1:52:49<3:41:32,  1.26it/s]
1|9089|Loss: 0.9471291899681091:  35%|███▌      | 9089/25880 [1:52:49<3:39:21,  1.28it/s]
1|9090|Loss: 0.6927145719528198:  35%|███▌      | 9089/25880 [1:52:49<3:39:21,  1.28it/s]
1|9090|Loss: 0.6927145719528198:  35%|███▌      | 9090/25880 [1:52:50<3:35:40,  1.30it/s]
1|9091|Loss: 0.9750638008117676:  35%|███▌      | 9090/25880 [1:52:50<3:35:40,  1.30it/s]
1|9091|Loss: 0.9750638008117676:  35%|███▌      | 9091/25880 [1:52:50<3:40:38,  1.27it/s]
1|9092|Loss: 1.1109743118286133:  35%|███▌      | 9091/25880 [1:52:51<3:40:38,  1.27it/s]
1|9092|Loss: 1.1109743118286133:  35%|███▌      | 9092/25880 [1:52:51<3:44:59,  1.24it/s]
1|9093|Loss: 0.9448567628860474:  35%|███▌      | 9092/25880 [1:52:52<3:44:59,  1.24it/s]
1|9093|Loss: 0.9448567628860474:  35%|███▌      | 9093/25880 [1:52:52<3:50:01,  1.22it/s]
1|9094|Loss: 0.9466684460639954:  35%|███▌      | 9093/25880 [1:52:53<3:50:01,  1.22it/s]
1|9094|Loss: 0.9466684460639954:  35%|███▌      | 9094/25880 [1:52:53<3:38:12,  1.28it/s]
1|9095|Loss: 0.8374667167663574:  35%|███▌      | 9094/25880 [1:52:53<3:38:12,  1.28it/s]
1|9095|Loss: 0.8374667167663574:  35%|███▌      | 9095/25880 [1:52:54<3:26:32,  1.35it/s]
1|9096|Loss: 0.8065914511680603:  35%|███▌      | 9095/25880 [1:52:54<3:26:32,  1.35it/s]
1|9096|Loss: 0.8065914511680603:  35%|███▌      | 9096/25880 [1:52:54<3:31:02,  1.33it/s]
1|9097|Loss: 0.7976514101028442:  35%|███▌      | 9096/25880 [1:52:55<3:31:02,  1.33it/s]
1|9097|Loss: 0.7976514101028442:  35%|███▌      | 9097/25880 [1:52:55<3:23:02,  1.38it/s]
1|9098|Loss: 0.855228841304779:  35%|███▌      | 9097/25880 [1:52:55<3:23:02,  1.38it/s] 
1|9098|Loss: 0.855228841304779:  35%|███▌      | 9098/25880 [1:52:56<3:29:28,  1.34it/s]
1|9099|Loss: 0.9533424377441406:  35%|███▌      | 9098/25880 [1:52:56<3:29:28,  1.34it/s]
1|9099|Loss: 0.9533424377441406:  35%|███▌      | 9099/25880 [1:52:56<3:18:50,  1.41it/s]
1|9100|Loss: 0.8369513750076294:  35%|███▌      | 9099/25880 [1:52:57<3:18:50,  1.41it/s]
1|9100|Loss: 0.8369513750076294:  35%|███▌      | 9100/25880 [1:52:57<3:17:35,  1.42it/s]
1|9101|Loss: 0.9044367671012878:  35%|███▌      | 9100/25880 [1:52:57<3:17:35,  1.42it/s]
1|9101|Loss: 0.9044367671012878:  35%|███▌      | 9101/25880 [1:52:58<3:19:32,  1.40it/s]
1|9102|Loss: 0.9637345671653748:  35%|███▌      | 9101/25880 [1:52:58<3:19:32,  1.40it/s]
1|9102|Loss: 0.9637345671653748:  35%|███▌      | 9102/25880 [1:52:58<3:15:09,  1.43it/s]
1|9103|Loss: 0.9230530261993408:  35%|███▌      | 9102/25880 [1:52:59<3:15:09,  1.43it/s]
1|9103|Loss: 0.9230530261993408:  35%|███▌      | 9103/25880 [1:52:59<3:21:21,  1.39it/s]
1|9104|Loss: 0.8761590123176575:  35%|███▌      | 9103/25880 [1:53:00<3:21:21,  1.39it/s]
1|9104|Loss: 0.8761590123176575:  35%|███▌      | 9104/25880 [1:53:00<3:13:19,  1.45it/s]
1|9105|Loss: 0.7737189531326294:  35%|███▌      | 9104/25880 [1:53:00<3:13:19,  1.45it/s]
1|9105|Loss: 0.7737189531326294:  35%|███▌      | 9105/25880 [1:53:01<3:13:33,  1.44it/s]
1|9106|Loss: 0.9061939120292664:  35%|███▌      | 9105/25880 [1:53:01<3:13:33,  1.44it/s]
1|9106|Loss: 0.9061939120292664:  35%|███▌      | 9106/25880 [1:53:01<3:16:23,  1.42it/s]
1|9107|Loss: 0.9021202921867371:  35%|███▌      | 9106/25880 [1:53:02<3:16:23,  1.42it/s]
1|9107|Loss: 0.9021202921867371:  35%|███▌      | 9107/25880 [1:53:02<3:27:46,  1.35it/s]
1|9108|Loss: 0.8675137162208557:  35%|███▌      | 9107/25880 [1:53:03<3:27:46,  1.35it/s]
1|9108|Loss: 0.8675137162208557:  35%|███▌      | 9108/25880 [1:53:03<3:23:41,  1.37it/s]
1|9109|Loss: 0.8663449287414551:  35%|███▌      | 9108/25880 [1:53:03<3:23:41,  1.37it/s]
1|9109|Loss: 0.8663449287414551:  35%|███▌      | 9109/25880 [1:53:04<3:20:49,  1.39it/s]
1|9110|Loss: 0.7424619793891907:  35%|███▌      | 9109/25880 [1:53:04<3:20:49,  1.39it/s]
1|9110|Loss: 0.7424619793891907:  35%|███▌      | 9110/25880 [1:53:04<3:22:30,  1.38it/s]
1|9111|Loss: 0.8693078756332397:  35%|███▌      | 9110/25880 [1:53:05<3:22:30,  1.38it/s]
1|9111|Loss: 0.8693078756332397:  35%|███▌      | 9111/25880 [1:53:05<3:21:08,  1.39it/s]
1|9112|Loss: 0.9005863666534424:  35%|███▌      | 9111/25880 [1:53:05<3:21:08,  1.39it/s]
1|9112|Loss: 0.9005863666534424:  35%|███▌      | 9112/25880 [1:53:06<3:29:19,  1.34it/s]
1|9113|Loss: 0.8513191938400269:  35%|███▌      | 9112/25880 [1:53:06<3:29:19,  1.34it/s]
1|9113|Loss: 0.8513191938400269:  35%|███▌      | 9113/25880 [1:53:06<3:15:18,  1.43it/s]
1|9114|Loss: 0.8673732876777649:  35%|███▌      | 9113/25880 [1:53:07<3:15:18,  1.43it/s]
1|9114|Loss: 0.8673732876777649:  35%|███▌      | 9114/25880 [1:53:07<3:19:27,  1.40it/s]
1|9115|Loss: 0.9008562564849854:  35%|███▌      | 9114/25880 [1:53:07<3:19:27,  1.40it/s]
1|9115|Loss: 0.9008562564849854:  35%|███▌      | 9115/25880 [1:53:08<3:10:23,  1.47it/s]
1|9116|Loss: 0.7541243433952332:  35%|███▌      | 9115/25880 [1:53:08<3:10:23,  1.47it/s]
1|9116|Loss: 0.7541243433952332:  35%|███▌      | 9116/25880 [1:53:08<2:57:45,  1.57it/s]
1|9117|Loss: 0.9423670768737793:  35%|███▌      | 9116/25880 [1:53:09<2:57:45,  1.57it/s]
1|9117|Loss: 0.9423670768737793:  35%|███▌      | 9117/25880 [1:53:09<3:10:19,  1.47it/s]
1|9118|Loss: 0.6927619576454163:  35%|███▌      | 9117/25880 [1:53:10<3:10:19,  1.47it/s]
1|9118|Loss: 0.6927619576454163:  35%|███▌      | 9118/25880 [1:53:10<3:23:08,  1.38it/s]
1|9119|Loss: 0.8139715194702148:  35%|███▌      | 9118/25880 [1:53:10<3:23:08,  1.38it/s]
1|9119|Loss: 0.8139715194702148:  35%|███▌      | 9119/25880 [1:53:11<3:24:47,  1.36it/s]
1|9120|Loss: 0.7340662479400635:  35%|███▌      | 9119/25880 [1:53:11<3:24:47,  1.36it/s]
1|9120|Loss: 0.7340662479400635:  35%|███▌      | 9120/25880 [1:53:11<3:07:38,  1.49it/s]
1|9121|Loss: 0.9658933281898499:  35%|███▌      | 9120/25880 [1:53:12<3:07:38,  1.49it/s]
1|9121|Loss: 0.9658933281898499:  35%|███▌      | 9121/25880 [1:53:12<3:17:16,  1.42it/s]
1|9122|Loss: 0.7488009333610535:  35%|███▌      | 9121/25880 [1:53:12<3:17:16,  1.42it/s]
1|9122|Loss: 0.7488009333610535:  35%|███▌      | 9122/25880 [1:53:13<3:28:38,  1.34it/s]
1|9123|Loss: 0.7415781021118164:  35%|███▌      | 9122/25880 [1:53:13<3:28:38,  1.34it/s]
1|9123|Loss: 0.7415781021118164:  35%|███▌      | 9123/25880 [1:53:14<3:29:07,  1.34it/s]
1|9124|Loss: 0.7545785903930664:  35%|███▌      | 9123/25880 [1:53:14<3:29:07,  1.34it/s]
1|9124|Loss: 0.7545785903930664:  35%|███▌      | 9124/25880 [1:53:14<3:21:52,  1.38it/s]
1|9125|Loss: 0.7959171533584595:  35%|███▌      | 9124/25880 [1:53:15<3:21:52,  1.38it/s]
1|9125|Loss: 0.7959171533584595:  35%|███▌      | 9125/25880 [1:53:15<3:18:42,  1.41it/s]
1|9126|Loss: 0.9034866690635681:  35%|███▌      | 9125/25880 [1:53:15<3:18:42,  1.41it/s]
1|9126|Loss: 0.9034866690635681:  35%|███▌      | 9126/25880 [1:53:16<3:29:01,  1.34it/s]
1|9127|Loss: 0.7924526333808899:  35%|███▌      | 9126/25880 [1:53:16<3:29:01,  1.34it/s]
1|9127|Loss: 0.7924526333808899:  35%|███▌      | 9127/25880 [1:53:17<3:46:43,  1.23it/s]
1|9128|Loss: 0.9245314598083496:  35%|███▌      | 9127/25880 [1:53:17<3:46:43,  1.23it/s]
1|9128|Loss: 0.9245314598083496:  35%|███▌      | 9128/25880 [1:53:18<3:51:15,  1.21it/s]
1|9129|Loss: 0.8351660966873169:  35%|███▌      | 9128/25880 [1:53:18<3:51:15,  1.21it/s]
1|9129|Loss: 0.8351660966873169:  35%|███▌      | 9129/25880 [1:53:18<3:51:37,  1.21it/s]
1|9130|Loss: 0.8589662313461304:  35%|███▌      | 9129/25880 [1:53:19<3:51:37,  1.21it/s]
1|9130|Loss: 0.8589662313461304:  35%|███▌      | 9130/25880 [1:53:19<3:45:37,  1.24it/s]
1|9131|Loss: 0.9720930457115173:  35%|███▌      | 9130/25880 [1:53:20<3:45:37,  1.24it/s]
1|9131|Loss: 0.9720930457115173:  35%|███▌      | 9131/25880 [1:53:20<3:41:35,  1.26it/s]
1|9132|Loss: 0.9387499094009399:  35%|███▌      | 9131/25880 [1:53:20<3:41:35,  1.26it/s]
1|9132|Loss: 0.9387499094009399:  35%|███▌      | 9132/25880 [1:53:21<3:41:44,  1.26it/s]
1|9133|Loss: 0.8957579731941223:  35%|███▌      | 9132/25880 [1:53:21<3:41:44,  1.26it/s]
1|9133|Loss: 0.8957579731941223:  35%|███▌      | 9133/25880 [1:53:22<3:53:11,  1.20it/s]
1|9134|Loss: 1.027550220489502:  35%|███▌      | 9133/25880 [1:53:22<3:53:11,  1.20it/s] 
1|9134|Loss: 1.027550220489502:  35%|███▌      | 9134/25880 [1:53:22<3:33:40,  1.31it/s]
1|9135|Loss: 0.7781856060028076:  35%|███▌      | 9134/25880 [1:53:23<3:33:40,  1.31it/s]
1|9135|Loss: 0.7781856060028076:  35%|███▌      | 9135/25880 [1:53:23<3:25:13,  1.36it/s]
1|9136|Loss: 0.833364725112915:  35%|███▌      | 9135/25880 [1:53:23<3:25:13,  1.36it/s] 
1|9136|Loss: 0.833364725112915:  35%|███▌      | 9136/25880 [1:53:24<3:24:48,  1.36it/s]
1|9137|Loss: 0.8828864097595215:  35%|███▌      | 9136/25880 [1:53:24<3:24:48,  1.36it/s]
1|9137|Loss: 0.8828864097595215:  35%|███▌      | 9137/25880 [1:53:24<3:35:24,  1.30it/s]
1|9138|Loss: 0.9969267845153809:  35%|███▌      | 9137/25880 [1:53:25<3:35:24,  1.30it/s]
1|9138|Loss: 0.9969267845153809:  35%|███▌      | 9138/25880 [1:53:25<3:29:35,  1.33it/s]
1|9139|Loss: 0.8292878270149231:  35%|███▌      | 9138/25880 [1:53:26<3:29:35,  1.33it/s]
1|9139|Loss: 0.8292878270149231:  35%|███▌      | 9139/25880 [1:53:26<3:27:16,  1.35it/s]
1|9140|Loss: 0.8433201909065247:  35%|███▌      | 9139/25880 [1:53:26<3:27:16,  1.35it/s]
1|9140|Loss: 0.8433201909065247:  35%|███▌      | 9140/25880 [1:53:27<3:27:04,  1.35it/s]
1|9141|Loss: 0.9937994480133057:  35%|███▌      | 9140/25880 [1:53:27<3:27:04,  1.35it/s]
1|9141|Loss: 0.9937994480133057:  35%|███▌      | 9141/25880 [1:53:27<3:24:29,  1.36it/s]
1|9142|Loss: 0.9047371745109558:  35%|███▌      | 9141/25880 [1:53:28<3:24:29,  1.36it/s]
1|9142|Loss: 0.9047371745109558:  35%|███▌      | 9142/25880 [1:53:28<3:27:33,  1.34it/s]
1|9143|Loss: 0.964467465877533:  35%|███▌      | 9142/25880 [1:53:29<3:27:33,  1.34it/s] 
1|9143|Loss: 0.964467465877533:  35%|███▌      | 9143/25880 [1:53:29<3:27:26,  1.34it/s]
1|9144|Loss: 0.8122388124465942:  35%|███▌      | 9143/25880 [1:53:29<3:27:26,  1.34it/s]
1|9144|Loss: 0.8122388124465942:  35%|███▌      | 9144/25880 [1:53:30<3:30:21,  1.33it/s]
1|9145|Loss: 0.8479065299034119:  35%|███▌      | 9144/25880 [1:53:30<3:30:21,  1.33it/s]
1|9145|Loss: 0.8479065299034119:  35%|███▌      | 9145/25880 [1:53:31<3:39:19,  1.27it/s]
1|9146|Loss: 0.7006278038024902:  35%|███▌      | 9145/25880 [1:53:31<3:39:19,  1.27it/s]
1|9146|Loss: 0.7006278038024902:  35%|███▌      | 9146/25880 [1:53:31<3:48:05,  1.22it/s]
1|9147|Loss: 0.8626219630241394:  35%|███▌      | 9146/25880 [1:53:32<3:48:05,  1.22it/s]
1|9147|Loss: 0.8626219630241394:  35%|███▌      | 9147/25880 [1:53:32<3:44:41,  1.24it/s]
1|9148|Loss: 0.9036909937858582:  35%|███▌      | 9147/25880 [1:53:33<3:44:41,  1.24it/s]
1|9148|Loss: 0.9036909937858582:  35%|███▌      | 9148/25880 [1:53:33<3:40:34,  1.26it/s]
1|9149|Loss: 0.8738554120063782:  35%|███▌      | 9148/25880 [1:53:33<3:40:34,  1.26it/s]
1|9149|Loss: 0.8738554120063782:  35%|███▌      | 9149/25880 [1:53:34<3:36:42,  1.29it/s]
1|9150|Loss: 0.7610617280006409:  35%|███▌      | 9149/25880 [1:53:34<3:36:42,  1.29it/s]
1|9150|Loss: 0.7610617280006409:  35%|███▌      | 9150/25880 [1:53:34<3:19:40,  1.40it/s]
1|9151|Loss: 0.8436387777328491:  35%|███▌      | 9150/25880 [1:53:35<3:19:40,  1.40it/s]
1|9151|Loss: 0.8436387777328491:  35%|███▌      | 9151/25880 [1:53:35<3:03:47,  1.52it/s]
1|9152|Loss: 0.9185023903846741:  35%|███▌      | 9151/25880 [1:53:35<3:03:47,  1.52it/s]
1|9152|Loss: 0.9185023903846741:  35%|███▌      | 9152/25880 [1:53:35<3:06:44,  1.49it/s]
1|9153|Loss: 0.7959704399108887:  35%|███▌      | 9152/25880 [1:53:36<3:06:44,  1.49it/s]
1|9153|Loss: 0.7959704399108887:  35%|███▌      | 9153/25880 [1:53:36<2:58:59,  1.56it/s]
1|9154|Loss: 0.7878057956695557:  35%|███▌      | 9153/25880 [1:53:36<2:58:59,  1.56it/s]
1|9154|Loss: 0.7878057956695557:  35%|███▌      | 9154/25880 [1:53:37<3:00:50,  1.54it/s]
1|9155|Loss: 0.8993930220603943:  35%|███▌      | 9154/25880 [1:53:37<3:00:50,  1.54it/s]
1|9155|Loss: 0.8993930220603943:  35%|███▌      | 9155/25880 [1:53:37<3:05:13,  1.50it/s]
1|9156|Loss: 0.8695532083511353:  35%|███▌      | 9155/25880 [1:53:38<3:05:13,  1.50it/s]
1|9156|Loss: 0.8695532083511353:  35%|███▌      | 9156/25880 [1:53:38<3:04:22,  1.51it/s]
1|9157|Loss: 0.8210446834564209:  35%|███▌      | 9156/25880 [1:53:38<3:04:22,  1.51it/s]
1|9157|Loss: 0.8210446834564209:  35%|███▌      | 9157/25880 [1:53:39<3:08:34,  1.48it/s]
1|9158|Loss: 0.8311722278594971:  35%|███▌      | 9157/25880 [1:53:39<3:08:34,  1.48it/s]
1|9158|Loss: 0.8311722278594971:  35%|███▌      | 9158/25880 [1:53:40<3:23:10,  1.37it/s]
1|9159|Loss: 0.8486369252204895:  35%|███▌      | 9158/25880 [1:53:40<3:23:10,  1.37it/s]
1|9159|Loss: 0.8486369252204895:  35%|███▌      | 9159/25880 [1:53:40<3:26:50,  1.35it/s]
1|9160|Loss: 0.8614936470985413:  35%|███▌      | 9159/25880 [1:53:41<3:26:50,  1.35it/s]
1|9160|Loss: 0.8614936470985413:  35%|███▌      | 9160/25880 [1:53:41<3:32:42,  1.31it/s]
1|9161|Loss: 0.8854368925094604:  35%|███▌      | 9160/25880 [1:53:42<3:32:42,  1.31it/s]
1|9161|Loss: 0.8854368925094604:  35%|███▌      | 9161/25880 [1:53:42<3:32:12,  1.31it/s]
1|9162|Loss: 0.9104784727096558:  35%|███▌      | 9161/25880 [1:53:42<3:32:12,  1.31it/s]
1|9162|Loss: 0.9104784727096558:  35%|███▌      | 9162/25880 [1:53:43<3:22:39,  1.37it/s]
1|9163|Loss: 0.7236999273300171:  35%|███▌      | 9162/25880 [1:53:43<3:22:39,  1.37it/s]
1|9163|Loss: 0.7236999273300171:  35%|███▌      | 9163/25880 [1:53:44<3:38:28,  1.28it/s]
1|9164|Loss: 0.8780417442321777:  35%|███▌      | 9163/25880 [1:53:44<3:38:28,  1.28it/s]
1|9164|Loss: 0.8780417442321777:  35%|███▌      | 9164/25880 [1:53:44<3:46:07,  1.23it/s]
1|9165|Loss: 0.7940470576286316:  35%|███▌      | 9164/25880 [1:53:45<3:46:07,  1.23it/s]
1|9165|Loss: 0.7940470576286316:  35%|███▌      | 9165/25880 [1:53:45<3:24:41,  1.36it/s]
1|9166|Loss: 1.0251785516738892:  35%|███▌      | 9165/25880 [1:53:45<3:24:41,  1.36it/s]
1|9166|Loss: 1.0251785516738892:  35%|███▌      | 9166/25880 [1:53:46<3:12:47,  1.44it/s]
1|9167|Loss: 0.7458780407905579:  35%|███▌      | 9166/25880 [1:53:46<3:12:47,  1.44it/s]
1|9167|Loss: 0.7458780407905579:  35%|███▌      | 9167/25880 [1:53:46<3:13:56,  1.44it/s]
1|9168|Loss: 0.860289454460144:  35%|███▌      | 9167/25880 [1:53:47<3:13:56,  1.44it/s] 
1|9168|Loss: 0.860289454460144:  35%|███▌      | 9168/25880 [1:53:47<3:14:01,  1.44it/s]
1|9169|Loss: 0.8333841562271118:  35%|███▌      | 9168/25880 [1:53:47<3:14:01,  1.44it/s]
1|9169|Loss: 0.8333841562271118:  35%|███▌      | 9169/25880 [1:53:48<3:10:05,  1.47it/s]
1|9170|Loss: 0.8837308883666992:  35%|███▌      | 9169/25880 [1:53:48<3:10:05,  1.47it/s]
1|9170|Loss: 0.8837308883666992:  35%|███▌      | 9170/25880 [1:53:48<3:04:48,  1.51it/s]
1|9171|Loss: 0.8571287393569946:  35%|███▌      | 9170/25880 [1:53:49<3:04:48,  1.51it/s]
1|9171|Loss: 0.8571287393569946:  35%|███▌      | 9171/25880 [1:53:49<3:02:33,  1.53it/s]
1|9172|Loss: 0.8230684995651245:  35%|███▌      | 9171/25880 [1:53:49<3:02:33,  1.53it/s]
1|9172|Loss: 0.8230684995651245:  35%|███▌      | 9172/25880 [1:53:50<3:01:09,  1.54it/s]
1|9173|Loss: 0.8257260322570801:  35%|███▌      | 9172/25880 [1:53:50<3:01:09,  1.54it/s]
1|9173|Loss: 0.8257260322570801:  35%|███▌      | 9173/25880 [1:53:50<2:56:25,  1.58it/s]
1|9174|Loss: 0.7857229709625244:  35%|███▌      | 9173/25880 [1:53:50<2:56:25,  1.58it/s]
1|9174|Loss: 0.7857229709625244:  35%|███▌      | 9174/25880 [1:53:51<2:53:03,  1.61it/s]
1|9175|Loss: 0.8976684808731079:  35%|███▌      | 9174/25880 [1:53:51<2:53:03,  1.61it/s]
1|9175|Loss: 0.8976684808731079:  35%|███▌      | 9175/25880 [1:53:51<3:04:25,  1.51it/s]
1|9176|Loss: 0.8293418288230896:  35%|██���▌      | 9175/25880 [1:53:52<3:04:25,  1.51it/s]
1|9176|Loss: 0.8293418288230896:  35%|███▌      | 9176/25880 [1:53:52<3:16:00,  1.42it/s]
1|9177|Loss: 0.8697982430458069:  35%|███▌      | 9176/25880 [1:53:53<3:16:00,  1.42it/s]
1|9177|Loss: 0.8697982430458069:  35%|███▌      | 9177/25880 [1:53:53<3:04:51,  1.51it/s]
1|9178|Loss: 0.7800578474998474:  35%|███▌      | 9177/25880 [1:53:53<3:04:51,  1.51it/s]
1|9178|Loss: 0.7800578474998474:  35%|███▌      | 9178/25880 [1:53:54<3:04:59,  1.50it/s]
1|9179|Loss: 0.7979264855384827:  35%|███▌      | 9178/25880 [1:53:54<3:04:59,  1.50it/s]
1|9179|Loss: 0.7979264855384827:  35%|███▌      | 9179/25880 [1:53:54<2:57:07,  1.57it/s]
1|9180|Loss: 0.8611041903495789:  35%|███▌      | 9179/25880 [1:53:54<2:57:07,  1.57it/s]
1|9180|Loss: 0.8611041903495789:  35%|███▌      | 9180/25880 [1:53:55<2:59:48,  1.55it/s]
1|9181|Loss: 1.0591574907302856:  35%|███▌      | 9180/25880 [1:53:55<2:59:48,  1.55it/s]
1|9181|Loss: 1.0591574907302856:  35%|███▌      | 9181/25880 [1:53:55<3:06:31,  1.49it/s]
1|9182|Loss: 0.8482679128646851:  35%|███▌      | 9181/25880 [1:53:56<3:06:31,  1.49it/s]
1|9182|Loss: 0.8482679128646851:  35%|███▌      | 9182/25880 [1:53:56<3:15:05,  1.43it/s]
1|9183|Loss: 0.9488731026649475:  35%|███▌      | 9182/25880 [1:53:57<3:15:05,  1.43it/s]
1|9183|Loss: 0.9488731026649475:  35%|███▌      | 9183/25880 [1:53:57<3:16:52,  1.41it/s]
1|9184|Loss: 0.836353063583374:  35%|███▌      | 9183/25880 [1:53:57<3:16:52,  1.41it/s] 
1|9184|Loss: 0.836353063583374:  35%|███▌      | 9184/25880 [1:53:58<3:26:38,  1.35it/s]
1|9185|Loss: 0.9170805811882019:  35%|███▌      | 9184/25880 [1:53:58<3:26:38,  1.35it/s]
1|9185|Loss: 0.9170805811882019:  35%|███▌      | 9185/25880 [1:53:58<3:05:31,  1.50it/s]
1|9186|Loss: 0.8798164129257202:  35%|███▌      | 9185/25880 [1:53:59<3:05:31,  1.50it/s]
1|9186|Loss: 0.8798164129257202:  35%|███▌      | 9186/25880 [1:53:59<3:13:48,  1.44it/s]
1|9187|Loss: 0.8898910880088806:  35%|███▌      | 9186/25880 [1:54:00<3:13:48,  1.44it/s]
1|9187|Loss: 0.8898910880088806:  35%|███▌      | 9187/25880 [1:54:00<3:23:07,  1.37it/s]
1|9188|Loss: 0.8317947387695312:  35%|███▌      | 9187/25880 [1:54:00<3:23:07,  1.37it/s]
1|9188|Loss: 0.8317947387695312:  36%|███▌      | 9188/25880 [1:54:01<3:16:57,  1.41it/s]
1|9189|Loss: 0.765964925289154:  36%|███▌      | 9188/25880 [1:54:01<3:16:57,  1.41it/s] 
1|9189|Loss: 0.765964925289154:  36%|███▌      | 9189/25880 [1:54:01<3:31:51,  1.31it/s]
1|9190|Loss: 0.7969061136245728:  36%|███▌      | 9189/25880 [1:54:02<3:31:51,  1.31it/s]
1|9190|Loss: 0.7969061136245728:  36%|███▌      | 9190/25880 [1:54:02<3:26:55,  1.34it/s]
1|9191|Loss: 0.7718197107315063:  36%|███▌      | 9190/25880 [1:54:02<3:26:55,  1.34it/s]
1|9191|Loss: 0.7718197107315063:  36%|███▌      | 9191/25880 [1:54:03<3:17:46,  1.41it/s]
1|9192|Loss: 0.8508493900299072:  36%|███▌      | 9191/25880 [1:54:03<3:17:46,  1.41it/s]
1|9192|Loss: 0.8508493900299072:  36%|███▌      | 9192/25880 [1:54:03<3:21:31,  1.38it/s]
1|9193|Loss: 0.9259570240974426:  36%|███▌      | 9192/25880 [1:54:04<3:21:31,  1.38it/s]
1|9193|Loss: 0.9259570240974426:  36%|███▌      | 9193/25880 [1:54:04<3:17:41,  1.41it/s]
1|9194|Loss: 0.9157623648643494:  36%|███▌      | 9193/25880 [1:54:05<3:17:41,  1.41it/s]
1|9194|Loss: 0.9157623648643494:  36%|███▌      | 9194/25880 [1:54:05<3:10:20,  1.46it/s]
1|9195|Loss: 0.8974555134773254:  36%|███▌      | 9194/25880 [1:54:05<3:10:20,  1.46it/s]
1|9195|Loss: 0.8974555134773254:  36%|███▌      | 9195/25880 [1:54:05<2:49:55,  1.64it/s]
1|9196|Loss: 0.8438511490821838:  36%|███▌      | 9195/25880 [1:54:06<2:49:55,  1.64it/s]
1|9196|Loss: 0.8438511490821838:  36%|███▌      | 9196/25880 [1:54:06<2:53:03,  1.61it/s]
1|9197|Loss: 0.8647112250328064:  36%|███▌      | 9196/25880 [1:54:06<2:53:03,  1.61it/s]
1|9197|Loss: 0.8647112250328064:  36%|███▌      | 9197/25880 [1:54:07<2:55:38,  1.58it/s]
1|9198|Loss: 0.770647406578064:  36%|███▌      | 9197/25880 [1:54:07<2:55:38,  1.58it/s] 
1|9198|Loss: 0.770647406578064:  36%|███▌      | 9198/25880 [1:54:07<3:10:03,  1.46it/s]
1|9199|Loss: 0.8492953777313232:  36%|███▌      | 9198/25880 [1:54:08<3:10:03,  1.46it/s]
1|9199|Loss: 0.8492953777313232:  36%|███▌      | 9199/25880 [1:54:08<3:10:14,  1.46it/s]
1|9200|Loss: 0.7505776286125183:  36%|███▌      | 9199/25880 [1:54:08<3:10:14,  1.46it/s]
1|9200|Loss: 0.7505776286125183:  36%|███▌      | 9200/25880 [1:54:09<3:18:54,  1.40it/s]
1|9201|Loss: 0.8903225064277649:  36%|███▌      | 9200/25880 [1:54:09<3:18:54,  1.40it/s]
1|9201|Loss: 0.8903225064277649:  36%|███▌      | 9201/25880 [1:54:10<3:26:30,  1.35it/s]
1|9202|Loss: 0.8181347846984863:  36%|███▌      | 9201/25880 [1:54:10<3:26:30,  1.35it/s]
1|9202|Loss: 0.8181347846984863:  36%|███▌      | 9202/25880 [1:54:10<3:28:02,  1.34it/s]
1|9203|Loss: 0.7382971048355103:  36%|███▌      | 9202/25880 [1:54:11<3:28:02,  1.34it/s]
1|9203|Loss: 0.7382971048355103:  36%|███▌      | 9203/25880 [1:54:11<3:19:38,  1.39it/s]
1|9204|Loss: 0.9724386930465698:  36%|███▌      | 9203/25880 [1:54:11<3:19:38,  1.39it/s]
1|9204|Loss: 0.9724386930465698:  36%|███▌      | 9204/25880 [1:54:12<3:20:04,  1.39it/s]
1|9205|Loss: 0.8569343090057373:  36%|███▌      | 9204/25880 [1:54:12<3:20:04,  1.39it/s]
1|9205|Loss: 0.8569343090057373:  36%|███▌      | 9205/25880 [1:54:13<3:37:08,  1.28it/s]
1|9206|Loss: 0.6938926577568054:  36%|███▌      | 9205/25880 [1:54:13<3:37:08,  1.28it/s]
1|9206|Loss: 0.6938926577568054:  36%|███▌      | 9206/25880 [1:54:13<3:26:34,  1.35it/s]
1|9207|Loss: 0.7909588813781738:  36%|███▌      | 9206/25880 [1:54:14<3:26:34,  1.35it/s]
1|9207|Loss: 0.7909588813781738:  36%|███▌      | 9207/25880 [1:54:14<3:23:02,  1.37it/s]
1|9208|Loss: 1.015080451965332:  36%|███▌      | 9207/25880 [1:54:14<3:23:02,  1.37it/s] 
1|9208|Loss: 1.015080451965332:  36%|███▌      | 9208/25880 [1:54:15<3:23:26,  1.37it/s]
1|9209|Loss: 0.8295198082923889:  36%|███▌      | 9208/25880 [1:54:15<3:23:26,  1.37it/s]
1|9209|Loss: 0.8295198082923889:  36%|███▌      | 9209/25880 [1:54:16<3:35:46,  1.29it/s]
1|9210|Loss: 0.8636412024497986:  36%|███▌      | 9209/25880 [1:54:16<3:35:46,  1.29it/s]
1|9210|Loss: 0.8636412024497986:  36%|███▌      | 9210/25880 [1:54:16<3:18:30,  1.40it/s]
1|9211|Loss: 0.8335624933242798:  36%|███▌      | 9210/25880 [1:54:16<3:18:30,  1.40it/s]
1|9211|Loss: 0.8335624933242798:  36%|███▌      | 9211/25880 [1:54:17<2:52:57,  1.61it/s]
1|9212|Loss: 0.8779495358467102:  36%|███▌      | 9211/25880 [1:54:17<2:52:57,  1.61it/s]
1|9212|Loss: 0.8779495358467102:  36%|███▌      | 9212/25880 [1:54:17<2:49:01,  1.64it/s]
1|9213|Loss: 0.818432629108429:  36%|███▌      | 9212/25880 [1:54:18<2:49:01,  1.64it/s] 
1|9213|Loss: 0.818432629108429:  36%|███▌      | 9213/25880 [1:54:18<2:58:11,  1.56it/s]
1|9214|Loss: 0.8167823553085327:  36%|███▌      | 9213/25880 [1:54:18<2:58:11,  1.56it/s]
1|9214|Loss: 0.8167823553085327:  36%|███▌      | 9214/25880 [1:54:19<2:52:44,  1.61it/s]
1|9215|Loss: 0.8816871643066406:  36%|███▌      | 9214/25880 [1:54:19<2:52:44,  1.61it/s]
1|9215|Loss: 0.8816871643066406:  36%|███▌      | 9215/25880 [1:54:19<3:04:34,  1.50it/s]
1|9216|Loss: 0.8368147611618042:  36%|███▌      | 9215/25880 [1:54:20<3:04:34,  1.50it/s]
1|9216|Loss: 0.8368147611618042:  36%|███▌      | 9216/25880 [1:54:20<3:12:11,  1.45it/s]
1|9217|Loss: 0.8807461857795715:  36%|███▌      | 9216/25880 [1:54:20<3:12:11,  1.45it/s]
1|9217|Loss: 0.8807461857795715:  36%|███▌      | 9217/25880 [1:54:21<3:14:02,  1.43it/s]
1|9218|Loss: 0.7313882112503052:  36%|███▌      | 9217/25880 [1:54:21<3:14:02,  1.43it/s]
1|9218|Loss: 0.7313882112503052:  36%|███▌      | 9218/25880 [1:54:21<3:08:24,  1.47it/s]
1|9219|Loss: 0.7636380791664124:  36%|███▌      | 9218/25880 [1:54:22<3:08:24,  1.47it/s]
1|9219|Loss: 0.7636380791664124:  36%|███▌      | 9219/25880 [1:54:22<3:19:50,  1.39it/s]
1|9220|Loss: 0.8249654769897461:  36%|███▌      | 9219/25880 [1:54:23<3:19:50,  1.39it/s]
1|9220|Loss: 0.8249654769897461:  36%|███▌      | 9220/25880 [1:54:23<3:17:27,  1.41it/s]
1|9221|Loss: 0.8497886061668396:  36%|███▌      | 9220/25880 [1:54:23<3:17:27,  1.41it/s]
1|9221|Loss: 0.8497886061668396:  36%|███▌      | 9221/25880 [1:54:24<3:10:52,  1.45it/s]
1|9222|Loss: 0.8321212530136108:  36%|███▌      | 9221/25880 [1:54:24<3:10:52,  1.45it/s]
1|9222|Loss: 0.8321212530136108:  36%|███▌      | 9222/25880 [1:54:24<3:13:34,  1.43it/s]
1|9223|Loss: 0.9092316627502441:  36%|███▌      | 9222/25880 [1:54:25<3:13:34,  1.43it/s]
1|9223|Loss: 0.9092316627502441:  36%|███▌      | 9223/25880 [1:54:25<3:21:47,  1.38it/s]
1|9224|Loss: 1.0312453508377075:  36%|███▌      | 9223/25880 [1:54:25<3:21:47,  1.38it/s]
1|9224|Loss: 1.0312453508377075:  36%|███▌      | 9224/25880 [1:54:26<3:27:16,  1.34it/s]
1|9225|Loss: 0.7481652498245239:  36%|███▌      | 9224/25880 [1:54:26<3:27:16,  1.34it/s]
1|9225|Loss: 0.7481652498245239:  36%|███▌      | 9225/25880 [1:54:26<3:19:41,  1.39it/s]
1|9226|Loss: 0.7934527397155762:  36%|███▌      | 9225/25880 [1:54:27<3:19:41,  1.39it/s]
1|9226|Loss: 0.7934527397155762:  36%|███▌      | 9226/25880 [1:54:27<3:04:07,  1.51it/s]
1|9227|Loss: 0.805062472820282:  36%|███▌      | 9226/25880 [1:54:27<3:04:07,  1.51it/s] 
1|9227|Loss: 0.805062472820282:  36%|███▌      | 9227/25880 [1:54:28<3:10:31,  1.46it/s]
1|9228|Loss: 0.7652416229248047:  36%|███▌      | 9227/25880 [1:54:28<3:10:31,  1.46it/s]
1|9228|Loss: 0.7652416229248047:  36%|███▌      | 9228/25880 [1:54:28<3:15:48,  1.42it/s]
1|9229|Loss: 0.8309797644615173:  36%|███▌      | 9228/25880 [1:54:29<3:15:48,  1.42it/s]
1|9229|Loss: 0.8309797644615173:  36%|███▌      | 9229/25880 [1:54:29<3:02:56,  1.52it/s]
1|9230|Loss: 0.8833175301551819:  36%|███▌      | 9229/25880 [1:54:29<3:02:56,  1.52it/s]
1|9230|Loss: 0.8833175301551819:  36%|███▌      | 9230/25880 [1:54:30<3:11:27,  1.45it/s]
1|9231|Loss: 0.7812422513961792:  36%|███▌      | 9230/25880 [1:54:30<3:11:27,  1.45it/s]
1|9231|Loss: 0.7812422513961792:  36%|███▌      | 9231/25880 [1:54:30<3:03:01,  1.52it/s]
1|9232|Loss: 0.5971403121948242:  36%|███▌      | 9231/25880 [1:54:31<3:03:01,  1.52it/s]
1|9232|Loss: 0.5971403121948242:  36%|███▌      | 9232/25880 [1:54:31<3:22:22,  1.37it/s]
1|9233|Loss: 0.7486947774887085:  36%|███▌      | 9232/25880 [1:54:32<3:22:22,  1.37it/s]
1|9233|Loss: 0.7486947774887085:  36%|███▌      | 9233/25880 [1:54:32<3:21:29,  1.38it/s]
1|9234|Loss: 0.7770397663116455:  36%|███▌      | 9233/25880 [1:54:32<3:21:29,  1.38it/s]
1|9234|Loss: 0.7770397663116455:  36%|███▌      | 9234/25880 [1:54:33<3:18:52,  1.39it/s]
1|9235|Loss: 0.7854818105697632:  36%|███▌      | 9234/25880 [1:54:33<3:18:52,  1.39it/s]
1|9235|Loss: 0.7854818105697632:  36%|███▌      | 9235/25880 [1:54:34<3:32:15,  1.31it/s]
1|9236|Loss: 0.8291574120521545:  36%|███▌      | 9235/25880 [1:54:34<3:32:15,  1.31it/s]
1|9236|Loss: 0.8291574120521545:  36%|███▌      | 9236/25880 [1:54:34<3:26:43,  1.34it/s]
1|9237|Loss: 0.8254327774047852:  36%|███▌      | 9236/25880 [1:54:35<3:26:43,  1.34it/s]
1|9237|Loss: 0.8254327774047852:  36%|███▌      | 9237/25880 [1:54:35<3:32:32,  1.31it/s]
1|9238|Loss: 0.9492432475090027:  36%|███▌      | 9237/25880 [1:54:36<3:32:32,  1.31it/s]
1|9238|Loss: 0.9492432475090027:  36%|███▌      | 9238/25880 [1:54:36<3:31:53,  1.31it/s]
1|9239|Loss: 0.8391143083572388:  36%|███▌      | 9238/25880 [1:54:36<3:31:53,  1.31it/s]
1|9239|Loss: 0.8391143083572388:  36%|███▌      | 9239/25880 [1:54:37<3:33:09,  1.30it/s]
1|9240|Loss: 0.8276526927947998:  36%|███▌      | 9239/25880 [1:54:37<3:33:09,  1.30it/s]
1|9240|Loss: 0.8276526927947998:  36%|███▌      | 9240/25880 [1:54:37<3:25:14,  1.35it/s]
1|9241|Loss: 0.871018648147583:  36%|███▌      | 9240/25880 [1:54:38<3:25:14,  1.35it/s] 
1|9241|Loss: 0.871018648147583:  36%|███▌      | 9241/25880 [1:54:38<3:22:52,  1.37it/s]
1|9242|Loss: 0.7487844824790955:  36%|███▌      | 9241/25880 [1:54:38<3:22:52,  1.37it/s]
1|9242|Loss: 0.7487844824790955:  36%|███▌      | 9242/25880 [1:54:39<3:37:48,  1.27it/s]
1|9243|Loss: 0.7961308360099792:  36%|███▌      | 9242/25880 [1:54:39<3:37:48,  1.27it/s]
1|9243|Loss: 0.7961308360099792:  36%|███▌      | 9243/25880 [1:54:40<3:29:31,  1.32it/s]
1|9244|Loss: 0.9777296781539917:  36%|███▌      | 9243/25880 [1:54:40<3:29:31,  1.32it/s]
1|9244|Loss: 0.9777296781539917:  36%|███▌      | 9244/25880 [1:54:40<3:25:42,  1.35it/s]
1|9245|Loss: 0.9228693842887878:  36%|███▌      | 9244/25880 [1:54:41<3:25:42,  1.35it/s]
1|9245|Loss: 0.9228693842887878:  36%|███▌      | 9245/25880 [1:54:41<3:31:49,  1.31it/s]
1|9246|Loss: 0.7744649052619934:  36%|███▌      | 9245/25880 [1:54:42<3:31:49,  1.31it/s]
1|9246|Loss: 0.7744649052619934:  36%|███▌      | 9246/25880 [1:54:42<3:29:01,  1.33it/s]
1|9247|Loss: 0.9335895776748657:  36%|███▌      | 9246/25880 [1:54:42<3:29:01,  1.33it/s]
1|9247|Loss: 0.9335895776748657:  36%|███▌      | 9247/25880 [1:54:43<3:34:45,  1.29it/s]
1|9248|Loss: 0.9228178262710571:  36%|███▌      | 9247/25880 [1:54:43<3:34:45,  1.29it/s]
1|9248|Loss: 0.9228178262710571:  36%|███▌      | 9248/25880 [1:54:43<3:31:44,  1.31it/s]
1|9249|Loss: 0.8058988451957703:  36%|███▌      | 9248/25880 [1:54:44<3:31:44,  1.31it/s]
1|9249|Loss: 0.8058988451957703:  36%|███▌      | 9249/25880 [1:54:44<3:32:46,  1.30it/s]
1|9250|Loss: 0.7806861996650696:  36%|███▌      | 9249/25880 [1:54:45<3:32:46,  1.30it/s]
1|9250|Loss: 0.7806861996650696:  36%|███▌      | 9250/25880 [1:54:45<3:52:35,  1.19it/s]
1|9251|Loss: 0.8173892498016357:  36%|███▌      | 9250/25880 [1:54:46<3:52:35,  1.19it/s]
1|9251|Loss: 0.8173892498016357:  36%|███▌      | 9251/25880 [1:54:46<3:41:30,  1.25it/s]
1|9252|Loss: 0.9192909002304077:  36%|███▌      | 9251/25880 [1:54:46<3:41:30,  1.25it/s]
1|9252|Loss: 0.9192909002304077:  36%|███▌      | 9252/25880 [1:54:47<3:42:19,  1.25it/s]
1|9253|Loss: 0.901546061038971:  36%|███▌      | 9252/25880 [1:54:47<3:42:19,  1.25it/s] 
1|9253|Loss: 0.901546061038971:  36%|███▌      | 9253/25880 [1:54:47<3:37:08,  1.28it/s]
1|9254|Loss: 0.8816685080528259:  36%|███▌      | 9253/25880 [1:54:48<3:37:08,  1.28it/s]
1|9254|Loss: 0.8816685080528259:  36%|███▌      | 9254/25880 [1:54:48<3:36:42,  1.28it/s]
1|9255|Loss: 0.8846325278282166:  36%|███▌      | 9254/25880 [1:54:49<3:36:42,  1.28it/s]
1|9255|Loss: 0.8846325278282166:  36%|███▌      | 9255/25880 [1:54:49<3:34:42,  1.29it/s]
1|9256|Loss: 0.9039286971092224:  36%|███▌      | 9255/25880 [1:54:49<3:34:42,  1.29it/s]
1|9256|Loss: 0.9039286971092224:  36%|███▌      | 9256/25880 [1:54:50<3:33:18,  1.30it/s]
1|9257|Loss: 0.8084860444068909:  36%|███▌      | 9256/25880 [1:54:50<3:33:18,  1.30it/s]
1|9257|Loss: 0.8084860444068909:  36%|███▌      | 9257/25880 [1:54:51<3:35:39,  1.28it/s]
1|9258|Loss: 0.7415204048156738:  36%|███▌      | 9257/25880 [1:54:51<3:35:39,  1.28it/s]
1|9258|Loss: 0.7415204048156738:  36%|███▌      | 9258/25880 [1:54:51<3:33:56,  1.29it/s]
1|9259|Loss: 0.9272352457046509:  36%|███▌      | 9258/25880 [1:54:52<3:33:56,  1.29it/s]
1|9259|Loss: 0.9272352457046509:  36%|███▌      | 9259/25880 [1:54:52<3:31:43,  1.31it/s]
1|9260|Loss: 0.8198475241661072:  36%|███▌      | 9259/25880 [1:54:53<3:31:43,  1.31it/s]
1|9260|Loss: 0.8198475241661072:  36%|███▌      | 9260/25880 [1:54:53<3:38:59,  1.26it/s]
1|9261|Loss: 0.9007879495620728:  36%|███▌      | 9260/25880 [1:54:53<3:38:59,  1.26it/s]
1|9261|Loss: 0.9007879495620728:  36%|███▌      | 9261/25880 [1:54:54<3:27:07,  1.34it/s]
1|9262|Loss: 0.9884274005889893:  36%|███▌      | 9261/25880 [1:54:54<3:27:07,  1.34it/s]
1|9262|Loss: 0.9884274005889893:  36%|███▌      | 9262/25880 [1:54:54<3:15:38,  1.42it/s]
1|9263|Loss: 0.9809165000915527:  36%|███▌      | 9262/25880 [1:54:55<3:15:38,  1.42it/s]
1|9263|Loss: 0.9809165000915527:  36%|███▌      | 9263/25880 [1:54:55<3:08:32,  1.47it/s]
1|9264|Loss: 0.7219341397285461:  36%|███▌      | 9263/25880 [1:54:55<3:08:32,  1.47it/s]
1|9264|Loss: 0.7219341397285461:  36%|███▌      | 9264/25880 [1:54:56<3:27:49,  1.33it/s]
1|9265|Loss: 0.8822508454322815:  36%|███▌      | 9264/25880 [1:54:56<3:27:49,  1.33it/s]
1|9265|Loss: 0.8822508454322815:  36%|███▌      | 9265/25880 [1:54:56<3:23:49,  1.36it/s]
1|9266|Loss: 0.8364989161491394:  36%|███▌      | 9265/25880 [1:54:57<3:23:49,  1.36it/s]
1|9266|Loss: 0.8364989161491394:  36%|███▌      | 9266/25880 [1:54:57<3:19:55,  1.39it/s]
1|9267|Loss: 0.8498630523681641:  36%|███▌      | 9266/25880 [1:54:57<3:19:55,  1.39it/s]
1|9267|Loss: 0.8498630523681641:  36%|███▌      | 9267/25880 [1:54:58<3:14:01,  1.43it/s]
1|9268|Loss: 0.7798362374305725:  36%|███▌      | 9267/25880 [1:54:58<3:14:01,  1.43it/s]
1|9268|Loss: 0.7798362374305725:  36%|███▌      | 9268/25880 [1:54:59<3:22:06,  1.37it/s]
1|9269|Loss: 0.858862042427063:  36%|███▌      | 9268/25880 [1:54:59<3:22:06,  1.37it/s] 
1|9269|Loss: 0.858862042427063:  36%|███▌      | 9269/25880 [1:54:59<3:18:01,  1.40it/s]
1|9270|Loss: 0.7411547303199768:  36%|███▌      | 9269/25880 [1:55:00<3:18:01,  1.40it/s]
1|9270|Loss: 0.7411547303199768:  36%|███▌      | 9270/25880 [1:55:00<3:18:29,  1.39it/s]
1|9271|Loss: 0.7778325080871582:  36%|███▌      | 9270/25880 [1:55:00<3:18:29,  1.39it/s]
1|9271|Loss: 0.7778325080871582:  36%|███▌      | 9271/25880 [1:55:01<3:17:36,  1.40it/s]
1|9272|Loss: 0.8022985458374023:  36%|███▌      | 9271/25880 [1:55:01<3:17:36,  1.40it/s]
1|9272|Loss: 0.8022985458374023:  36%|███▌      | 9272/25880 [1:55:01<3:22:59,  1.36it/s]
1|9273|Loss: 1.000128984451294:  36%|███▌      | 9272/25880 [1:55:02<3:22:59,  1.36it/s] 
1|9273|Loss: 1.000128984451294:  36%|███▌      | 9273/25880 [1:55:02<3:24:19,  1.35it/s]
1|9274|Loss: 0.8045793771743774:  36%|███▌      | 9273/25880 [1:55:03<3:24:19,  1.35it/s]
1|9274|Loss: 0.8045793771743774:  36%|███▌      | 9274/25880 [1:55:03<3:22:05,  1.37it/s]
1|9275|Loss: 0.8913485407829285:  36%|███▌      | 9274/25880 [1:55:03<3:22:05,  1.37it/s]
1|9275|Loss: 0.8913485407829285:  36%|███▌      | 9275/25880 [1:55:04<3:15:47,  1.41it/s]
1|9276|Loss: 0.7654820680618286:  36%|███▌      | 9275/25880 [1:55:04<3:15:47,  1.41it/s]
1|9276|Loss: 0.7654820680618286:  36%|███▌      | 9276/25880 [1:55:04<3:24:30,  1.35it/s]
1|9277|Loss: 0.8618122339248657:  36%|███▌      | 9276/25880 [1:55:05<3:24:30,  1.35it/s]
1|9277|Loss: 0.8618122339248657:  36%|███▌      | 9277/25880 [1:55:05<3:09:52,  1.46it/s]
1|9278|Loss: 0.9051491618156433:  36%|███▌      | 9277/25880 [1:55:05<3:09:52,  1.46it/s]
1|9278|Loss: 0.9051491618156433:  36%|███▌      | 9278/25880 [1:55:06<3:03:00,  1.51it/s]
1|9279|Loss: 0.8425083756446838:  36%|███▌      | 9278/25880 [1:55:06<3:03:00,  1.51it/s]
1|9279|Loss: 0.8425083756446838:  36%|███▌      | 9279/25880 [1:55:06<3:08:53,  1.46it/s]
1|9280|Loss: 0.8283544778823853:  36%|███▌      | 9279/25880 [1:55:07<3:08:53,  1.46it/s]
1|9280|Loss: 0.8283544778823853:  36%|███▌      | 9280/25880 [1:55:07<3:07:53,  1.47it/s]
1|9281|Loss: 0.9398847222328186:  36%|███▌      | 9280/25880 [1:55:07<3:07:53,  1.47it/s]
1|9281|Loss: 0.9398847222328186:  36%|███▌      | 9281/25880 [1:55:08<3:14:28,  1.42it/s]
1|9282|Loss: 0.8092293739318848:  36%|███▌      | 9281/25880 [1:55:08<3:14:28,  1.42it/s]
1|9282|Loss: 0.8092293739318848:  36%|███▌      | 9282/25880 [1:55:08<3:12:18,  1.44it/s]
1|9283|Loss: 0.8636188507080078:  36%|███▌      | 9282/25880 [1:55:09<3:12:18,  1.44it/s]
1|9283|Loss: 0.8636188507080078:  36%|███▌      | 9283/25880 [1:55:09<3:11:58,  1.44it/s]
1|9284|Loss: 0.7388404011726379:  36%|███▌      | 9283/25880 [1:55:09<3:11:58,  1.44it/s]
1|9284|Loss: 0.7388404011726379:  36%|███▌      | 9284/25880 [1:55:10<3:15:08,  1.42it/s]
1|9285|Loss: 0.8755744695663452:  36%|███▌      | 9284/25880 [1:55:10<3:15:08,  1.42it/s]
1|9285|Loss: 0.8755744695663452:  36%|███▌      | 9285/25880 [1:55:11<3:15:41,  1.41it/s]
1|9286|Loss: 0.9246663451194763:  36%|███▌      | 9285/25880 [1:55:11<3:15:41,  1.41it/s]
1|9286|Loss: 0.9246663451194763:  36%|███▌      | 9286/25880 [1:55:11<3:17:04,  1.40it/s]
1|9287|Loss: 0.7625068426132202:  36%|███▌      | 9286/25880 [1:55:12<3:17:04,  1.40it/s]
1|9287|Loss: 0.7625068426132202:  36%|███▌      | 9287/25880 [1:55:12<3:18:43,  1.39it/s]
1|9288|Loss: 0.9519586563110352:  36%|███▌      | 9287/25880 [1:55:12<3:18:43,  1.39it/s]
1|9288|Loss: 0.9519586563110352:  36%|███▌      | 9288/25880 [1:55:13<3:18:35,  1.39it/s]
1|9289|Loss: 0.8192116618156433:  36%|███▌      | 9288/25880 [1:55:13<3:18:35,  1.39it/s]
1|9289|Loss: 0.8192116618156433:  36%|███▌      | 9289/25880 [1:55:13<3:16:52,  1.40it/s]
1|9290|Loss: 1.0426325798034668:  36%|███▌      | 9289/25880 [1:55:14<3:16:52,  1.40it/s]
1|9290|Loss: 1.0426325798034668:  36%|███▌      | 9290/25880 [1:55:14<3:11:51,  1.44it/s]
1|9291|Loss: 0.8813727498054504:  36%|███▌      | 9290/25880 [1:55:14<3:11:51,  1.44it/s]
1|9291|Loss: 0.8813727498054504:  36%|███▌      | 9291/25880 [1:55:15<3:14:34,  1.42it/s]
1|9292|Loss: 0.7325277924537659:  36%|███▌      | 9291/25880 [1:55:15<3:14:34,  1.42it/s]
1|9292|Loss: 0.7325277924537659:  36%|███▌      | 9292/25880 [1:55:16<3:24:01,  1.36it/s]
1|9293|Loss: 0.8918789029121399:  36%|███▌      | 9292/25880 [1:55:16<3:24:01,  1.36it/s]
1|9293|Loss: 0.8918789029121399:  36%|███▌      | 9293/25880 [1:55:16<3:10:27,  1.45it/s]
1|9294|Loss: 0.8687853217124939:  36%|███▌      | 9293/25880 [1:55:17<3:10:27,  1.45it/s]
1|9294|Loss: 0.8687853217124939:  36%|███▌      | 9294/25880 [1:55:17<3:19:29,  1.39it/s]
1|9295|Loss: 0.7808092832565308:  36%|███▌      | 9294/25880 [1:55:17<3:19:29,  1.39it/s]
1|9295|Loss: 0.7808092832565308:  36%|███▌      | 9295/25880 [1:55:18<3:35:51,  1.28it/s]
1|9296|Loss: 0.8146190047264099:  36%|███▌      | 9295/25880 [1:55:18<3:35:51,  1.28it/s]
1|9296|Loss: 0.8146190047264099:  36%|███▌      | 9296/25880 [1:55:19<3:51:09,  1.20it/s]
1|9297|Loss: 0.8069491982460022:  36%|███▌      | 9296/25880 [1:55:19<3:51:09,  1.20it/s]
1|9297|Loss: 0.8069491982460022:  36%|███▌      | 9297/25880 [1:55:19<3:33:02,  1.30it/s]
1|9298|Loss: 0.8384066224098206:  36%|███▌      | 9297/25880 [1:55:20<3:33:02,  1.30it/s]
1|9298|Loss: 0.8384066224098206:  36%|███▌      | 9298/25880 [1:55:20<3:32:27,  1.30it/s]
1|9299|Loss: 0.8699397444725037:  36%|███▌      | 9298/25880 [1:55:21<3:32:27,  1.30it/s]
1|9299|Loss: 0.8699397444725037:  36%|███▌      | 9299/25880 [1:55:21<3:31:08,  1.31it/s]
1|9300|Loss: 0.7652677297592163:  36%|███▌      | 9299/25880 [1:55:21<3:31:08,  1.31it/s]
1|9300|Loss: 0.7652677297592163:  36%|███▌      | 9300/25880 [1:55:22<3:23:07,  1.36it/s]
1|9301|Loss: 0.7752410173416138:  36%|███▌      | 9300/25880 [1:55:22<3:23:07,  1.36it/s]
1|9301|Loss: 0.7752410173416138:  36%|███▌      | 9301/25880 [1:55:22<3:14:08,  1.42it/s]
1|9302|Loss: 0.9395692944526672:  36%|███▌      | 9301/25880 [1:55:23<3:14:08,  1.42it/s]
1|9302|Loss: 0.9395692944526672:  36%|███▌      | 9302/25880 [1:55:23<3:15:07,  1.42it/s]
1|9303|Loss: 0.8033313751220703:  36%|███▌      | 9302/25880 [1:55:23<3:15:07,  1.42it/s]
1|9303|Loss: 0.8033313751220703:  36%|███▌      | 9303/25880 [1:55:24<3:05:47,  1.49it/s]
1|9304|Loss: 0.7327919006347656:  36%|███▌      | 9303/25880 [1:55:24<3:05:47,  1.49it/s]
1|9304|Loss: 0.7327919006347656:  36%|███▌      | 9304/25880 [1:55:24<3:23:24,  1.36it/s]
1|9305|Loss: 0.7637960910797119:  36%|███▌      | 9304/25880 [1:55:25<3:23:24,  1.36it/s]
1|9305|Loss: 0.7637960910797119:  36%|███▌      | 9305/25880 [1:55:25<3:40:04,  1.26it/s]
1|9306|Loss: 0.7250103950500488:  36%|███▌      | 9305/25880 [1:55:26<3:40:04,  1.26it/s]
1|9306|Loss: 0.7250103950500488:  36%|███▌      | 9306/25880 [1:55:26<3:24:07,  1.35it/s]
1|9307|Loss: 0.8719173073768616:  36%|███▌      | 9306/25880 [1:55:26<3:24:07,  1.35it/s]
1|9307|Loss: 0.8719173073768616:  36%|███▌      | 9307/25880 [1:55:27<3:33:04,  1.30it/s]
1|9308|Loss: 0.8659648299217224:  36%|███▌      | 9307/25880 [1:55:27<3:33:04,  1.30it/s]
1|9308|Loss: 0.8659648299217224:  36%|███▌      | 9308/25880 [1:55:28<3:37:14,  1.27it/s]
1|9309|Loss: 0.8999435901641846:  36%|███▌      | 9308/25880 [1:55:28<3:37:14,  1.27it/s]
1|9309|Loss: 0.8999435901641846:  36%|███▌      | 9309/25880 [1:55:28<3:28:18,  1.33it/s]
1|9310|Loss: 0.7311668395996094:  36%|███▌      | 9309/25880 [1:55:29<3:28:18,  1.33it/s]
1|9310|Loss: 0.7311668395996094:  36%|███▌      | 9310/25880 [1:55:29<3:15:14,  1.41it/s]
1|9311|Loss: 0.8877424001693726:  36%|███▌      | 9310/25880 [1:55:29<3:15:14,  1.41it/s]
1|9311|Loss: 0.8877424001693726:  36%|███▌      | 9311/25880 [1:55:30<3:12:59,  1.43it/s]
1|9312|Loss: 0.8340827822685242:  36%|███▌      | 9311/25880 [1:55:30<3:12:59,  1.43it/s]
1|9312|Loss: 0.8340827822685242:  36%|███▌      | 9312/25880 [1:55:30<3:15:01,  1.42it/s]
1|9313|Loss: 0.9099806547164917:  36%|███▌      | 9312/25880 [1:55:31<3:15:01,  1.42it/s]
1|9313|Loss: 0.9099806547164917:  36%|███▌      | 9313/25880 [1:55:31<3:17:31,  1.40it/s]
1|9314|Loss: 0.8367024064064026:  36%|███▌      | 9313/25880 [1:55:31<3:17:31,  1.40it/s]
1|9314|Loss: 0.8367024064064026:  36%|███▌      | 9314/25880 [1:55:32<3:00:55,  1.53it/s]
1|9315|Loss: 0.8645333647727966:  36%|███▌      | 9314/25880 [1:55:32<3:00:55,  1.53it/s]
1|9315|Loss: 0.8645333647727966:  36%|███▌      | 9315/25880 [1:55:32<3:02:11,  1.52it/s]
1|9316|Loss: 0.6133280396461487:  36%|███▌      | 9315/25880 [1:55:33<3:02:11,  1.52it/s]
1|9316|Loss: 0.6133280396461487:  36%|███▌      | 9316/25880 [1:55:33<3:25:05,  1.35it/s]
1|9317|Loss: 0.9179328083992004:  36%|███▌      | 9316/25880 [1:55:34<3:25:05,  1.35it/s]
1|9317|Loss: 0.9179328083992004:  36%|███▌      | 9317/25880 [1:55:34<3:42:23,  1.24it/s]
1|9318|Loss: 0.9375587105751038:  36%|███▌      | 9317/25880 [1:55:35<3:42:23,  1.24it/s]
1|9318|Loss: 0.9375587105751038:  36%|███▌      | 9318/25880 [1:55:35<3:37:34,  1.27it/s]
1|9319|Loss: 0.851789653301239:  36%|███▌      | 9318/25880 [1:55:35<3:37:34,  1.27it/s] 
1|9319|Loss: 0.851789653301239:  36%|███▌      | 9319/25880 [1:55:36<3:30:14,  1.31it/s]
1|9320|Loss: 0.9471689462661743:  36%|███▌      | 9319/25880 [1:55:36<3:30:14,  1.31it/s]
1|9320|Loss: 0.9471689462661743:  36%|███▌      | 9320/25880 [1:55:36<3:34:23,  1.29it/s]
1|9321|Loss: 0.8433142900466919:  36%|███▌      | 9320/25880 [1:55:37<3:34:23,  1.29it/s]
1|9321|Loss: 0.8433142900466919:  36%|███▌      | 9321/25880 [1:55:37<3:32:27,  1.30it/s]
1|9322|Loss: 0.9711264371871948:  36%|███▌      | 9321/25880 [1:55:38<3:32:27,  1.30it/s]
1|9322|Loss: 0.9711264371871948:  36%|███▌      | 9322/25880 [1:55:38<3:17:15,  1.40it/s]
1|9323|Loss: 0.8920308947563171:  36%|███▌      | 9322/25880 [1:55:38<3:17:15,  1.40it/s]
1|9323|Loss: 0.8920308947563171:  36%|███▌      | 9323/25880 [1:55:38<3:16:14,  1.41it/s]
1|9324|Loss: 0.8937475681304932:  36%|███▌      | 9323/25880 [1:55:39<3:16:14,  1.41it/s]
1|9324|Loss: 0.8937475681304932:  36%|███▌      | 9324/25880 [1:55:39<3:03:42,  1.50it/s]
1|9325|Loss: 0.8573880195617676:  36%|███▌      | 9324/25880 [1:55:39<3:03:42,  1.50it/s]
1|9325|Loss: 0.8573880195617676:  36%|███▌      | 9325/25880 [1:55:40<3:09:25,  1.46it/s]
1|9326|Loss: 0.9449389576911926:  36%|███▌      | 9325/25880 [1:55:40<3:09:25,  1.46it/s]
1|9326|Loss: 0.9449389576911926:  36%|███▌      | 9326/25880 [1:55:40<3:14:27,  1.42it/s]
1|9327|Loss: 0.8336870670318604:  36%|███▌      | 9326/25880 [1:55:41<3:14:27,  1.42it/s]
1|9327|Loss: 0.8336870670318604:  36%|███▌      | 9327/25880 [1:55:41<3:25:04,  1.35it/s]
1|9328|Loss: 0.7274942398071289:  36%|███▌      | 9327/25880 [1:55:42<3:25:04,  1.35it/s]
1|9328|Loss: 0.7274942398071289:  36%|███▌      | 9328/25880 [1:55:42<3:19:41,  1.38it/s]
1|9329|Loss: 0.9935394525527954:  36%|███▌      | 9328/25880 [1:55:42<3:19:41,  1.38it/s]
1|9329|Loss: 0.9935394525527954:  36%|███▌      | 9329/25880 [1:55:43<3:05:40,  1.49it/s]
1|9330|Loss: 1.026183843612671:  36%|███▌      | 9329/25880 [1:55:43<3:05:40,  1.49it/s] 
1|9330|Loss: 1.026183843612671:  36%|███▌      | 9330/25880 [1:55:43<3:16:02,  1.41it/s]
1|9331|Loss: 0.7831858992576599:  36%|███▌      | 9330/25880 [1:55:44<3:16:02,  1.41it/s]
1|9331|Loss: 0.7831858992576599:  36%|███▌      | 9331/25880 [1:55:44<3:18:41,  1.39it/s]
1|9332|Loss: 0.9101506471633911:  36%|███▌      | 9331/25880 [1:55:44<3:18:41,  1.39it/s]
1|9332|Loss: 0.9101506471633911:  36%|███▌      | 9332/25880 [1:55:45<3:17:02,  1.40it/s]
1|9333|Loss: 0.7305959463119507:  36%|███▌      | 9332/25880 [1:55:45<3:17:02,  1.40it/s]
1|9333|Loss: 0.7305959463119507:  36%|███▌      | 9333/25880 [1:55:46<3:30:05,  1.31it/s]
1|9334|Loss: 0.9552660584449768:  36%|███▌      | 9333/25880 [1:55:46<3:30:05,  1.31it/s]
1|9334|Loss: 0.9552660584449768:  36%|███▌      | 9334/25880 [1:55:46<3:23:25,  1.36it/s]
1|9335|Loss: 0.8195502161979675:  36%|███▌      | 9334/25880 [1:55:47<3:23:25,  1.36it/s]
1|9335|Loss: 0.8195502161979675:  36%|███▌      | 9335/25880 [1:55:47<3:20:47,  1.37it/s]
1|9336|Loss: 0.7451503276824951:  36%|███▌      | 9335/25880 [1:55:47<3:20:47,  1.37it/s]
1|9336|Loss: 0.7451503276824951:  36%|███▌      | 9336/25880 [1:55:48<3:27:49,  1.33it/s]
1|9337|Loss: 0.8774821162223816:  36%|███▌      | 9336/25880 [1:55:48<3:27:49,  1.33it/s]
1|9337|Loss: 0.8774821162223816:  36%|███▌      | 9337/25880 [1:55:49<3:39:26,  1.26it/s]
1|9338|Loss: 0.897068440914154:  36%|███▌      | 9337/25880 [1:55:49<3:39:26,  1.26it/s] 
1|9338|Loss: 0.897068440914154:  36%|███▌      | 9338/25880 [1:55:49<3:26:38,  1.33it/s]
1|9339|Loss: 0.9068708419799805:  36%|███▌      | 9338/25880 [1:55:50<3:26:38,  1.33it/s]
1|9339|Loss: 0.9068708419799805:  36%|███▌      | 9339/25880 [1:55:50<3:26:25,  1.34it/s]
1|9340|Loss: 0.8010685443878174:  36%|███▌      | 9339/25880 [1:55:51<3:26:25,  1.34it/s]
1|9340|Loss: 0.8010685443878174:  36%|███▌      | 9340/25880 [1:55:51<3:24:02,  1.35it/s]
1|9341|Loss: 0.7972745895385742:  36%|███▌      | 9340/25880 [1:55:51<3:24:02,  1.35it/s]
1|9341|Loss: 0.7972745895385742:  36%|███▌      | 9341/25880 [1:55:52<3:30:27,  1.31it/s]
1|9342|Loss: 0.859589695930481:  36%|███▌      | 9341/25880 [1:55:52<3:30:27,  1.31it/s] 
1|9342|Loss: 0.859589695930481:  36%|███▌      | 9342/25880 [1:55:53<3:33:55,  1.29it/s]
1|9343|Loss: 0.9136240482330322:  36%|███▌      | 9342/25880 [1:55:53<3:33:55,  1.29it/s]
1|9343|Loss: 0.9136240482330322:  36%|███▌      | 9343/25880 [1:55:53<3:37:47,  1.27it/s]
1|9344|Loss: 0.8830116391181946:  36%|███▌      | 9343/25880 [1:55:54<3:37:47,  1.27it/s]
1|9344|Loss: 0.8830116391181946:  36%|███▌      | 9344/25880 [1:55:54<3:28:44,  1.32it/s]
1|9345|Loss: 0.8823028206825256:  36%|███▌      | 9344/25880 [1:55:54<3:28:44,  1.32it/s]
1|9345|Loss: 0.8823028206825256:  36%|███▌      | 9345/25880 [1:55:55<3:19:06,  1.38it/s]
1|9346|Loss: 0.8352850675582886:  36%|███▌      | 9345/25880 [1:55:55<3:19:06,  1.38it/s]
1|9346|Loss: 0.8352850675582886:  36%|███▌      | 9346/25880 [1:55:55<3:17:45,  1.39it/s]
1|9347|Loss: 0.7945240139961243:  36%|███▌      | 9346/25880 [1:55:56<3:17:45,  1.39it/s]
1|9347|Loss: 0.7945240139961243:  36%|███▌      | 9347/25880 [1:55:56<3:24:54,  1.34it/s]
1|9348|Loss: 0.8857582211494446:  36%|███▌      | 9347/25880 [1:55:57<3:24:54,  1.34it/s]
1|9348|Loss: 0.8857582211494446:  36%|███▌      | 9348/25880 [1:55:57<3:25:57,  1.34it/s]
1|9349|Loss: 0.8043898344039917:  36%|███▌      | 9348/25880 [1:55:57<3:25:57,  1.34it/s]
1|9349|Loss: 0.8043898344039917:  36%|███▌      | 9349/25880 [1:55:58<3:15:00,  1.41it/s]
1|9350|Loss: 0.8064733743667603:  36%|███▌      | 9349/25880 [1:55:58<3:15:00,  1.41it/s]
1|9350|Loss: 0.8064733743667603:  36%|███▌      | 9350/25880 [1:55:58<3:23:33,  1.35it/s]
1|9351|Loss: 0.884470522403717:  36%|███▌      | 9350/25880 [1:55:59<3:23:33,  1.35it/s] 
1|9351|Loss: 0.884470522403717:  36%|███▌      | 9351/25880 [1:55:59<3:19:29,  1.38it/s]
1|9352|Loss: 0.8600552082061768:  36%|███▌      | 9351/25880 [1:55:59<3:19:29,  1.38it/s]
1|9352|Loss: 0.8600552082061768:  36%|███▌      | 9352/25880 [1:56:00<3:23:27,  1.35it/s]
1|9353|Loss: 0.849808394908905:  36%|███▌      | 9352/25880 [1:56:00<3:23:27,  1.35it/s] 
1|9353|Loss: 0.849808394908905:  36%|███▌      | 9353/25880 [1:56:01<3:23:39,  1.35it/s]
1|9354|Loss: 0.7521795034408569:  36%|███▌      | 9353/25880 [1:56:01<3:23:39,  1.35it/s]
1|9354|Loss: 0.7521795034408569:  36%|███▌      | 9354/25880 [1:56:01<3:16:32,  1.40it/s]
1|9355|Loss: 1.114117980003357:  36%|███▌      | 9354/25880 [1:56:02<3:16:32,  1.40it/s] 
1|9355|Loss: 1.114117980003357:  36%|███▌      | 9355/25880 [1:56:02<3:07:23,  1.47it/s]
1|9356|Loss: 0.8204193711280823:  36%|███▌      | 9355/25880 [1:56:02<3:07:23,  1.47it/s]
1|9356|Loss: 0.8204193711280823:  36%|███▌      | 9356/25880 [1:56:03<3:13:45,  1.42it/s]
1|9357|Loss: 0.819238543510437:  36%|███▌      | 9356/25880 [1:56:03<3:13:45,  1.42it/s] 
1|9357|Loss: 0.819238543510437:  36%|███▌      | 9357/25880 [1:56:03<3:24:39,  1.35it/s]
1|9358|Loss: 0.7109394669532776:  36%|███▌      | 9357/25880 [1:56:04<3:24:39,  1.35it/s]
1|9358|Loss: 0.7109394669532776:  36%|███▌      | 9358/25880 [1:56:04<3:26:04,  1.34it/s]
1|9359|Loss: 0.8078528046607971:  36%|███▌      | 9358/25880 [1:56:05<3:26:04,  1.34it/s]
1|9359|Loss: 0.8078528046607971:  36%|███▌      | 9359/25880 [1:56:05<3:18:17,  1.39it/s]
1|9360|Loss: 0.8342862725257874:  36%|███▌      | 9359/25880 [1:56:05<3:18:17,  1.39it/s]
1|9360|Loss: 0.8342862725257874:  36%|███▌      | 9360/25880 [1:56:06<3:16:14,  1.40it/s]
1|9361|Loss: 0.8577665090560913:  36%|███▌      | 9360/25880 [1:56:06<3:16:14,  1.40it/s]
1|9361|Loss: 0.8577665090560913:  36%|███▌      | 9361/25880 [1:56:06<3:09:49,  1.45it/s]
1|9362|Loss: 0.9495574831962585:  36%|███▌      | 9361/25880 [1:56:07<3:09:49,  1.45it/s]
1|9362|Loss: 0.9495574831962585:  36%|███▌      | 9362/25880 [1:56:07<3:24:02,  1.35it/s]
1|9363|Loss: 0.8697633147239685:  36%|███▌      | 9362/25880 [1:56:07<3:24:02,  1.35it/s]
1|9363|Loss: 0.8697633147239685:  36%|███▌      | 9363/25880 [1:56:08<3:19:04,  1.38it/s]
1|9364|Loss: 0.8916257619857788:  36%|███▌      | 9363/25880 [1:56:08<3:19:04,  1.38it/s]
1|9364|Loss: 0.8916257619857788:  36%|███▌      | 9364/25880 [1:56:08<3:04:48,  1.49it/s]
1|9365|Loss: 0.9535863399505615:  36%|███▌      | 9364/25880 [1:56:09<3:04:48,  1.49it/s]
1|9365|Loss: 0.9535863399505615:  36%|███▌      | 9365/25880 [1:56:09<3:12:35,  1.43it/s]
1|9366|Loss: 0.8308340907096863:  36%|███▌      | 9365/25880 [1:56:09<3:12:35,  1.43it/s]
1|9366|Loss: 0.8308340907096863:  36%|███▌      | 9366/25880 [1:56:10<3:11:03,  1.44it/s]
1|9367|Loss: 0.8133569955825806:  36%|███▌      | 9366/25880 [1:56:10<3:11:03,  1.44it/s]
1|9367|Loss: 0.8133569955825806:  36%|███▌      | 9367/25880 [1:56:10<3:20:50,  1.37it/s]
1|9368|Loss: 0.8903125524520874:  36%|███▌      | 9367/25880 [1:56:11<3:20:50,  1.37it/s]
1|9368|Loss: 0.8903125524520874:  36%|███▌      | 9368/25880 [1:56:11<3:31:16,  1.30it/s]
1|9369|Loss: 0.7800936698913574:  36%|███▌      | 9368/25880 [1:56:12<3:31:16,  1.30it/s]
1|9369|Loss: 0.7800936698913574:  36%|███▌      | 9369/25880 [1:56:12<3:31:07,  1.30it/s]
1|9370|Loss: 0.8383985161781311:  36%|███▌      | 9369/25880 [1:56:12<3:31:07,  1.30it/s]
1|9370|Loss: 0.8383985161781311:  36%|███▌      | 9370/25880 [1:56:13<3:20:20,  1.37it/s]
1|9371|Loss: 0.9534103274345398:  36%|███▌      | 9370/25880 [1:56:13<3:20:20,  1.37it/s]
1|9371|Loss: 0.9534103274345398:  36%|███▌      | 9371/25880 [1:56:13<3:03:46,  1.50it/s]
1|9372|Loss: 0.9146366715431213:  36%|███▌      | 9371/25880 [1:56:14<3:03:46,  1.50it/s]
1|9372|Loss: 0.9146366715431213:  36%|███▌      | 9372/25880 [1:56:14<3:06:08,  1.48it/s]
1|9373|Loss: 0.775814414024353:  36%|███▌      | 9372/25880 [1:56:14<3:06:08,  1.48it/s] 
1|9373|Loss: 0.775814414024353:  36%|███▌      | 9373/25880 [1:56:15<3:19:20,  1.38it/s]
1|9374|Loss: 0.7978994846343994:  36%|███▌      | 9373/25880 [1:56:15<3:19:20,  1.38it/s]
1|9374|Loss: 0.7978994846343994:  36%|███▌      | 9374/25880 [1:56:15<2:59:28,  1.53it/s]
1|9375|Loss: 0.8726115226745605:  36%|███▌      | 9374/25880 [1:56:16<2:59:28,  1.53it/s]
1|9375|Loss: 0.8726115226745605:  36%|███▌      | 9375/25880 [1:56:16<3:13:36,  1.42it/s]
1|9376|Loss: 0.9165414571762085:  36%|███▌      | 9375/25880 [1:56:17<3:13:36,  1.42it/s]
1|9376|Loss: 0.9165414571762085:  36%|███▌      | 9376/25880 [1:56:17<3:05:41,  1.48it/s]
1|9377|Loss: 0.7596997022628784:  36%|███▌      | 9376/25880 [1:56:17<3:05:41,  1.48it/s]
1|9377|Loss: 0.7596997022628784:  36%|███▌      | 9377/25880 [1:56:17<3:07:24,  1.47it/s]
1|9378|Loss: 0.8341085314750671:  36%|███▌      | 9377/25880 [1:56:18<3:07:24,  1.47it/s]
1|9378|Loss: 0.8341085314750671:  36%|███▌      | 9378/25880 [1:56:18<3:05:46,  1.48it/s]
1|9379|Loss: 0.8196266293525696:  36%|███▌      | 9378/25880 [1:56:18<3:05:46,  1.48it/s]
1|9379|Loss: 0.8196266293525696:  36%|███▌      | 9379/25880 [1:56:19<3:02:30,  1.51it/s]
1|9380|Loss: 0.8107644319534302:  36%|███▌      | 9379/25880 [1:56:19<3:02:30,  1.51it/s]
1|9380|Loss: 0.8107644319534302:  36%|███▌      | 9380/25880 [1:56:19<3:00:40,  1.52it/s]
1|9381|Loss: 0.9569966197013855:  36%|███▌      | 9380/25880 [1:56:20<3:00:40,  1.52it/s]
1|9381|Loss: 0.9569966197013855:  36%|███▌      | 9381/25880 [1:56:20<3:17:25,  1.39it/s]
1|9382|Loss: 0.8880110383033752:  36%|███▌      | 9381/25880 [1:56:21<3:17:25,  1.39it/s]
1|9382|Loss: 0.8880110383033752:  36%|███▋      | 9382/25880 [1:56:21<3:12:04,  1.43it/s]
1|9383|Loss: 0.8593814969062805:  36%|███▋      | 9382/25880 [1:56:21<3:12:04,  1.43it/s]
1|9383|Loss: 0.8593814969062805:  36%|███▋      | 9383/25880 [1:56:22<3:10:11,  1.45it/s]
1|9384|Loss: 0.8142720460891724:  36%|███▋      | 9383/25880 [1:56:22<3:10:11,  1.45it/s]
1|9384|Loss: 0.8142720460891724:  36%|███▋      | 9384/25880 [1:56:22<3:03:23,  1.50it/s]
1|9385|Loss: 0.8544689416885376:  36%|███▋      | 9384/25880 [1:56:23<3:03:23,  1.50it/s]
1|9385|Loss: 0.8544689416885376:  36%|███▋      | 9385/25880 [1:56:23<3:12:55,  1.43it/s]
1|9386|Loss: 0.7380700707435608:  36%|███▋      | 9385/25880 [1:56:23<3:12:55,  1.43it/s]
1|9386|Loss: 0.7380700707435608:  36%|███▋      | 9386/25880 [1:56:24<3:10:46,  1.44it/s]
1|9387|Loss: 0.8429638743400574:  36%|███▋      | 9386/25880 [1:56:24<3:10:46,  1.44it/s]
1|9387|Loss: 0.8429638743400574:  36%|███▋      | 9387/25880 [1:56:24<3:12:44,  1.43it/s]
1|9388|Loss: 1.0652931928634644:  36%|███▋      | 9387/25880 [1:56:25<3:12:44,  1.43it/s]
1|9388|Loss: 1.0652931928634644:  36%|███▋      | 9388/25880 [1:56:25<3:21:33,  1.36it/s]
1|9389|Loss: 0.996479868888855:  36%|███▋      | 9388/25880 [1:56:26<3:21:33,  1.36it/s] 
1|9389|Loss: 0.996479868888855:  36%|███▋      | 9389/25880 [1:56:26<3:27:34,  1.32it/s]
1|9390|Loss: 0.7915101647377014:  36%|███▋      | 9389/25880 [1:56:26<3:27:34,  1.32it/s]
1|9390|Loss: 0.7915101647377014:  36%|███▋      | 9390/25880 [1:56:27<3:33:12,  1.29it/s]
1|9391|Loss: 0.7109091877937317:  36%|███▋      | 9390/25880 [1:56:27<3:33:12,  1.29it/s]
1|9391|Loss: 0.7109091877937317:  36%|███▋      | 9391/25880 [1:56:27<3:25:12,  1.34it/s]
1|9392|Loss: 0.9246025681495667:  36%|███▋      | 9391/25880 [1:56:28<3:25:12,  1.34it/s]
1|9392|Loss: 0.9246025681495667:  36%|███▋      | 9392/25880 [1:56:28<3:16:04,  1.40it/s]
1|9393|Loss: 0.7783752679824829:  36%|███▋      | 9392/25880 [1:56:29<3:16:04,  1.40it/s]
1|9393|Loss: 0.7783752679824829:  36%|███▋      | 9393/25880 [1:56:29<3:22:53,  1.35it/s]
1|9394|Loss: 0.7923706769943237:  36%|███▋      | 9393/25880 [1:56:29<3:22:53,  1.35it/s]
1|9394|Loss: 0.7923706769943237:  36%|███▋      | 9394/25880 [1:56:30<3:30:17,  1.31it/s]
1|9395|Loss: 0.9110925197601318:  36%|███▋      | 9394/25880 [1:56:30<3:30:17,  1.31it/s]
1|9395|Loss: 0.9110925197601318:  36%|███▋      | 9395/25880 [1:56:30<3:23:12,  1.35it/s]
1|9396|Loss: 0.7730467319488525:  36%|███▋      | 9395/25880 [1:56:31<3:23:12,  1.35it/s]
1|9396|Loss: 0.7730467319488525:  36%|███▋      | 9396/25880 [1:56:31<3:02:52,  1.50it/s]
1|9397|Loss: 0.8810741305351257:  36%|███▋      | 9396/25880 [1:56:31<3:02:52,  1.50it/s]
1|9397|Loss: 0.8810741305351257:  36%|███▋      | 9397/25880 [1:56:31<2:47:26,  1.64it/s]
1|9398|Loss: 0.8227559328079224:  36%|███▋      | 9397/25880 [1:56:32<2:47:26,  1.64it/s]
1|9398|Loss: 0.8227559328079224:  36%|███▋      | 9398/25880 [1:56:32<2:53:42,  1.58it/s]
1|9399|Loss: 0.7907299399375916:  36%|███▋      | 9398/25880 [1:56:32<2:53:42,  1.58it/s]
1|9399|Loss: 0.7907299399375916:  36%|███▋      | 9399/25880 [1:56:33<2:55:13,  1.57it/s]
1|9400|Loss: 0.7391613721847534:  36%|███▋      | 9399/25880 [1:56:33<2:55:13,  1.57it/s]
1|9400|Loss: 0.7391613721847534:  36%|███▋      | 9400/25880 [1:56:33<3:01:20,  1.51it/s]
1|9401|Loss: 0.8300365209579468:  36%|███▋      | 9400/25880 [1:56:34<3:01:20,  1.51it/s]
1|9401|Loss: 0.8300365209579468:  36%|███▋      | 9401/25880 [1:56:34<3:08:13,  1.46it/s]
1|9402|Loss: 0.935879111289978:  36%|███▋      | 9401/25880 [1:56:35<3:08:13,  1.46it/s] 
1|9402|Loss: 0.935879111289978:  36%|███▋      | 9402/25880 [1:56:35<3:05:11,  1.48it/s]
1|9403|Loss: 0.804024338722229:  36%|███▋      | 9402/25880 [1:56:35<3:05:11,  1.48it/s]
1|9403|Loss: 0.804024338722229:  36%|███▋      | 9403/25880 [1:56:36<3:08:42,  1.46it/s]
1|9404|Loss: 0.7817386984825134:  36%|███▋      | 9403/25880 [1:56:36<3:08:42,  1.46it/s]
1|9404|Loss: 0.7817386984825134:  36%|███▋      | 9404/25880 [1:56:36<3:10:20,  1.44it/s]
1|9405|Loss: 0.8270087242126465:  36%|███▋      | 9404/25880 [1:56:37<3:10:20,  1.44it/s]
1|9405|Loss: 0.8270087242126465:  36%|███▋      | 9405/25880 [1:56:37<3:21:41,  1.36it/s]
1|9406|Loss: 0.8199858665466309:  36%|███▋      | 9405/25880 [1:56:38<3:21:41,  1.36it/s]
1|9406|Loss: 0.8199858665466309:  36%|███▋      | 9406/25880 [1:56:38<3:30:38,  1.30it/s]
1|9407|Loss: 0.8761370778083801:  36%|███▋      | 9406/25880 [1:56:38<3:30:38,  1.30it/s]
1|9407|Loss: 0.8761370778083801:  36%|███▋      | 9407/25880 [1:56:39<3:29:06,  1.31it/s]
1|9408|Loss: 0.9563082456588745:  36%|███▋      | 9407/25880 [1:56:39<3:29:06,  1.31it/s]
1|9408|Loss: 0.9563082456588745:  36%|███▋      | 9408/25880 [1:56:39<3:24:09,  1.34it/s]
1|9409|Loss: 0.9588306546211243:  36%|███▋      | 9408/25880 [1:56:40<3:24:09,  1.34it/s]
1|9409|Loss: 0.9588306546211243:  36%|███▋      | 9409/25880 [1:56:40<3:21:56,  1.36it/s]
1|9410|Loss: 0.8683350086212158:  36%|███▋      | 9409/25880 [1:56:41<3:21:56,  1.36it/s]
1|9410|Loss: 0.8683350086212158:  36%|███▋      | 9410/25880 [1:56:41<3:30:42,  1.30it/s]
1|9411|Loss: 0.8278069496154785:  36%|███▋      | 9410/25880 [1:56:41<3:30:42,  1.30it/s]
1|9411|Loss: 0.8278069496154785:  36%|███▋      | 9411/25880 [1:56:42<3:33:47,  1.28it/s]
1|9412|Loss: 0.7427529096603394:  36%|███▋      | 9411/25880 [1:56:42<3:33:47,  1.28it/s]
1|9412|Loss: 0.7427529096603394:  36%|███▋      | 9412/25880 [1:56:42<3:21:18,  1.36it/s]
1|9413|Loss: 0.8174517750740051:  36%|███▋      | 9412/25880 [1:56:43<3:21:18,  1.36it/s]
1|9413|Loss: 0.8174517750740051:  36%|███▋      | 9413/25880 [1:56:43<3:24:55,  1.34it/s]
1|9414|Loss: 0.7791439890861511:  36%|███▋      | 9413/25880 [1:56:44<3:24:55,  1.34it/s]
1|9414|Loss: 0.7791439890861511:  36%|███▋      | 9414/25880 [1:56:44<3:15:23,  1.40it/s]
1|9415|Loss: 0.7623195052146912:  36%|███▋      | 9414/25880 [1:56:44<3:15:23,  1.40it/s]
1|9415|Loss: 0.7623195052146912:  36%|███▋      | 9415/25880 [1:56:44<3:00:01,  1.52it/s]
1|9416|Loss: 0.9059160947799683:  36%|███▋      | 9415/25880 [1:56:45<3:00:01,  1.52it/s]
1|9416|Loss: 0.9059160947799683:  36%|███▋      | 9416/25880 [1:56:45<3:12:30,  1.43it/s]
1|9417|Loss: 0.7764174342155457:  36%|███▋      | 9416/25880 [1:56:46<3:12:30,  1.43it/s]
1|9417|Loss: 0.7764174342155457:  36%|███▋      | 9417/25880 [1:56:46<3:16:05,  1.40it/s]
1|9418|Loss: 0.9080166816711426:  36%|███▋      | 9417/25880 [1:56:46<3:16:05,  1.40it/s]
1|9418|Loss: 0.9080166816711426:  36%|███▋      | 9418/25880 [1:56:47<3:20:35,  1.37it/s]
1|9419|Loss: 0.8508310317993164:  36%|███▋      | 9418/25880 [1:56:47<3:20:35,  1.37it/s]
1|9419|Loss: 0.8508310317993164:  36%|███▋      | 9419/25880 [1:56:47<3:21:33,  1.36it/s]
1|9420|Loss: 0.9034574627876282:  36%|███▋      | 9419/25880 [1:56:48<3:21:33,  1.36it/s]
1|9420|Loss: 0.9034574627876282:  36%|███▋      | 9420/25880 [1:56:48<3:13:31,  1.42it/s]
1|9421|Loss: 0.8685044646263123:  36%|███▋      | 9420/25880 [1:56:48<3:13:31,  1.42it/s]
1|9421|Loss: 0.8685044646263123:  36%|███▋      | 9421/25880 [1:56:49<3:05:49,  1.48it/s]
1|9422|Loss: 0.8165225386619568:  36%|███▋      | 9421/25880 [1:56:49<3:05:49,  1.48it/s]
1|9422|Loss: 0.8165225386619568:  36%|███▋      | 9422/25880 [1:56:49<3:16:22,  1.40it/s]
1|9423|Loss: 0.7598248720169067:  36%|███▋      | 9422/25880 [1:56:50<3:16:22,  1.40it/s]
1|9423|Loss: 0.7598248720169067:  36%|███▋      | 9423/25880 [1:56:50<3:19:44,  1.37it/s]
1|9424|Loss: 0.7537400126457214:  36%|███▋      | 9423/25880 [1:56:51<3:19:44,  1.37it/s]
1|9424|Loss: 0.7537400126457214:  36%|███▋      | 9424/25880 [1:56:51<3:11:41,  1.43it/s]
1|9425|Loss: 0.7610143423080444:  36%|███▋      | 9424/25880 [1:56:51<3:11:41,  1.43it/s]
1|9425|Loss: 0.7610143423080444:  36%|███▋      | 9425/25880 [1:56:52<3:24:15,  1.34it/s]
1|9426|Loss: 0.8423820734024048:  36%|███▋      | 9425/25880 [1:56:52<3:24:15,  1.34it/s]
1|9426|Loss: 0.8423820734024048:  36%|███▋      | 9426/25880 [1:56:52<3:30:51,  1.30it/s]
1|9427|Loss: 0.7645667195320129:  36%|███▋      | 9426/25880 [1:56:53<3:30:51,  1.30it/s]
1|9427|Loss: 0.7645667195320129:  36%|███▋      | 9427/25880 [1:56:53<3:28:51,  1.31it/s]
1|9428|Loss: 0.8722994327545166:  36%|███▋      | 9427/25880 [1:56:54<3:28:51,  1.31it/s]
1|9428|Loss: 0.8722994327545166:  36%|███▋      | 9428/25880 [1:56:54<3:24:20,  1.34it/s]
1|9429|Loss: 0.9420325756072998:  36%|███▋      | 9428/25880 [1:56:54<3:24:20,  1.34it/s]
1|9429|Loss: 0.9420325756072998:  36%|███▋      | 9429/25880 [1:56:55<3:30:32,  1.30it/s]
1|9430|Loss: 0.7448456883430481:  36%|███▋      | 9429/25880 [1:56:55<3:30:32,  1.30it/s]
1|9430|Loss: 0.7448456883430481:  36%|███▋      | 9430/25880 [1:56:55<3:22:14,  1.36it/s]
1|9431|Loss: 0.7863780856132507:  36%|███▋      | 9430/25880 [1:56:56<3:22:14,  1.36it/s]
1|9431|Loss: 0.7863780856132507:  36%|███▋      | 9431/25880 [1:56:56<3:08:18,  1.46it/s]
1|9432|Loss: 0.88866126537323:  36%|███▋      | 9431/25880 [1:56:56<3:08:18,  1.46it/s]  
1|9432|Loss: 0.88866126537323:  36%|███▋      | 9432/25880 [1:56:57<3:15:17,  1.40it/s]
1|9433|Loss: 0.8679876327514648:  36%|███▋      | 9432/25880 [1:56:57<3:15:17,  1.40it/s]
1|9433|Loss: 0.8679876327514648:  36%|███▋      | 9433/25880 [1:56:58<3:18:59,  1.38it/s]
1|9434|Loss: 0.9430948495864868:  36%|███▋      | 9433/25880 [1:56:58<3:18:59,  1.38it/s]
1|9434|Loss: 0.9430948495864868:  36%|███▋      | 9434/25880 [1:56:58<3:18:23,  1.38it/s]
1|9435|Loss: 0.875823974609375:  36%|███▋      | 9434/25880 [1:56:59<3:18:23,  1.38it/s] 
1|9435|Loss: 0.875823974609375:  36%|███▋      | 9435/25880 [1:56:59<3:23:39,  1.35it/s]
1|9436|Loss: 0.8316596150398254:  36%|███▋      | 9435/25880 [1:56:59<3:23:39,  1.35it/s]
1|9436|Loss: 0.8316596150398254:  36%|███▋      | 9436/25880 [1:57:00<3:21:34,  1.36it/s]
1|9437|Loss: 0.769101619720459:  36%|███▋      | 9436/25880 [1:57:00<3:21:34,  1.36it/s] 
1|9437|Loss: 0.769101619720459:  36%|███▋      | 9437/25880 [1:57:01<3:32:44,  1.29it/s]
1|9438|Loss: 0.8215999603271484:  36%|███▋      | 9437/25880 [1:57:01<3:32:44,  1.29it/s]
1|9438|Loss: 0.8215999603271484:  36%|███▋      | 9438/25880 [1:57:01<3:26:17,  1.33it/s]
1|9439|Loss: 0.7823687195777893:  36%|███▋      | 9438/25880 [1:57:02<3:26:17,  1.33it/s]
1|9439|Loss: 0.7823687195777893:  36%|███▋      | 9439/25880 [1:57:02<3:21:04,  1.36it/s]
1|9440|Loss: 0.8597180247306824:  36%|███▋      | 9439/25880 [1:57:02<3:21:04,  1.36it/s]
1|9440|Loss: 0.8597180247306824:  36%|███▋      | 9440/25880 [1:57:03<3:20:54,  1.36it/s]
1|9441|Loss: 0.7816962599754333:  36%|███▋      | 9440/25880 [1:57:03<3:20:54,  1.36it/s]
1|9441|Loss: 0.7816962599754333:  36%|███▋      | 9441/25880 [1:57:03<3:19:38,  1.37it/s]
1|9442|Loss: 0.7603057026863098:  36%|███▋      | 9441/25880 [1:57:04<3:19:38,  1.37it/s]
1|9442|Loss: 0.7603057026863098:  36%|███▋      | 9442/25880 [1:57:04<3:38:14,  1.26it/s]
1|9443|Loss: 0.845367431640625:  36%|███▋      | 9442/25880 [1:57:05<3:38:14,  1.26it/s] 
1|9443|Loss: 0.845367431640625:  36%|███▋      | 9443/25880 [1:57:05<3:36:26,  1.27it/s]
1|9444|Loss: 0.9223670363426208:  36%|███▋      | 9443/25880 [1:57:06<3:36:26,  1.27it/s]
1|9444|Loss: 0.9223670363426208:  36%|███▋      | 9444/25880 [1:57:06<3:31:17,  1.30it/s]
1|9445|Loss: 0.7807169556617737:  36%|███▋      | 9444/25880 [1:57:06<3:31:17,  1.30it/s]
1|9445|Loss: 0.7807169556617737:  36%|███▋      | 9445/25880 [1:57:07<3:25:37,  1.33it/s]
1|9446|Loss: 0.7797324061393738:  36%|███▋      | 9445/25880 [1:57:07<3:25:37,  1.33it/s]
1|9446|Loss: 0.7797324061393738:  36%|███▋      | 9446/25880 [1:57:07<3:31:57,  1.29it/s]
1|9447|Loss: 0.8752490282058716:  36%|███▋      | 9446/25880 [1:57:08<3:31:57,  1.29it/s]
1|9447|Loss: 0.8752490282058716:  37%|███▋      | 9447/25880 [1:57:08<3:31:16,  1.30it/s]
1|9448|Loss: 0.833801805973053:  37%|███▋      | 9447/25880 [1:57:09<3:31:16,  1.30it/s] 
1|9448|Loss: 0.833801805973053:  37%|███▋      | 9448/25880 [1:57:09<3:32:32,  1.29it/s]
1|9449|Loss: 0.7365044355392456:  37%|███▋      | 9448/25880 [1:57:09<3:32:32,  1.29it/s]
1|9449|Loss: 0.7365044355392456:  37%|███▋      | 9449/25880 [1:57:10<3:22:47,  1.35it/s]
1|9450|Loss: 0.8908102512359619:  37%|███▋      | 9449/25880 [1:57:10<3:22:47,  1.35it/s]
1|9450|Loss: 0.8908102512359619:  37%|███▋      | 9450/25880 [1:57:10<3:18:01,  1.38it/s]
1|9451|Loss: 0.9025672078132629:  37%|███▋      | 9450/25880 [1:57:11<3:18:01,  1.38it/s]
1|9451|Loss: 0.9025672078132629:  37%|███▋      | 9451/25880 [1:57:11<3:25:44,  1.33it/s]
1|9452|Loss: 0.8824737071990967:  37%|███▋      | 9451/25880 [1:57:11<3:25:44,  1.33it/s]
1|9452|Loss: 0.8824737071990967:  37%|███▋      | 9452/25880 [1:57:12<3:08:21,  1.45it/s]
1|9453|Loss: 0.878404438495636:  37%|███▋      | 9452/25880 [1:57:12<3:08:21,  1.45it/s] 
1|9453|Loss: 0.878404438495636:  37%|███▋      | 9453/25880 [1:57:12<2:59:23,  1.53it/s]
1|9454|Loss: 0.8911347985267639:  37%|███▋      | 9453/25880 [1:57:13<2:59:23,  1.53it/s]
1|9454|Loss: 0.8911347985267639:  37%|███▋      | 9454/25880 [1:57:13<3:11:16,  1.43it/s]
1|9455|Loss: 1.0067189931869507:  37%|███▋      | 9454/25880 [1:57:13<3:11:16,  1.43it/s]
1|9455|Loss: 1.0067189931869507:  37%|███▋      | 9455/25880 [1:57:14<3:08:57,  1.45it/s]
1|9456|Loss: 0.8870885372161865:  37%|███▋      | 9455/25880 [1:57:14<3:08:57,  1.45it/s]
1|9456|Loss: 0.8870885372161865:  37%|███▋      | 9456/25880 [1:57:15<3:17:19,  1.39it/s]
1|9457|Loss: 0.8398376107215881:  37%|███▋      | 9456/25880 [1:57:15<3:17:19,  1.39it/s]
1|9457|Loss: 0.8398376107215881:  37%|███▋      | 9457/25880 [1:57:15<3:17:16,  1.39it/s]
1|9458|Loss: 0.8120357394218445:  37%|███▋      | 9457/25880 [1:57:16<3:17:16,  1.39it/s]
1|9458|Loss: 0.8120357394218445:  37%|███▋      | 9458/25880 [1:57:16<3:15:34,  1.40it/s]
1|9459|Loss: 0.7945119738578796:  37%|███▋      | 9458/25880 [1:57:16<3:15:34,  1.40it/s]
1|9459|Loss: 0.7945119738578796:  37%|███▋      | 9459/25880 [1:57:17<3:20:54,  1.36it/s]
1|9460|Loss: 0.8697594404220581:  37%|███▋      | 9459/25880 [1:57:17<3:20:54,  1.36it/s]
1|9460|Loss: 0.8697594404220581:  37%|███▋      | 9460/25880 [1:57:17<3:21:47,  1.36it/s]
1|9461|Loss: 0.8559067249298096:  37%|███▋      | 9460/25880 [1:57:18<3:21:47,  1.36it/s]
1|9461|Loss: 0.8559067249298096:  37%|███▋      | 9461/25880 [1:57:18<3:27:36,  1.32it/s]
1|9462|Loss: 0.7767331600189209:  37%|███▋      | 9461/25880 [1:57:19<3:27:36,  1.32it/s]
1|9462|Loss: 0.7767331600189209:  37%|███▋      | 9462/25880 [1:57:19<3:08:43,  1.45it/s]
1|9463|Loss: 0.8314346075057983:  37%|███▋      | 9462/25880 [1:57:19<3:08:43,  1.45it/s]
1|9463|Loss: 0.8314346075057983:  37%|██���▋      | 9463/25880 [1:57:19<3:07:28,  1.46it/s]
1|9464|Loss: 0.7800881862640381:  37%|███▋      | 9463/25880 [1:57:20<3:07:28,  1.46it/s]
1|9464|Loss: 0.7800881862640381:  37%|███▋      | 9464/25880 [1:57:20<3:04:46,  1.48it/s]
1|9465|Loss: 0.7616521716117859:  37%|███▋      | 9464/25880 [1:57:20<3:04:46,  1.48it/s]
1|9465|Loss: 0.7616521716117859:  37%|███▋      | 9465/25880 [1:57:21<2:52:38,  1.58it/s]
1|9466|Loss: 0.7387648820877075:  37%|███▋      | 9465/25880 [1:57:21<2:52:38,  1.58it/s]
1|9466|Loss: 0.7387648820877075:  37%|███▋      | 9466/25880 [1:57:21<2:51:00,  1.60it/s]
1|9467|Loss: 1.0273462533950806:  37%|███▋      | 9466/25880 [1:57:22<2:51:00,  1.60it/s]
1|9467|Loss: 1.0273462533950806:  37%|███▋      | 9467/25880 [1:57:22<2:43:58,  1.67it/s]
1|9468|Loss: 0.7554628849029541:  37%|███▋      | 9467/25880 [1:57:22<2:43:58,  1.67it/s]
1|9468|Loss: 0.7554628849029541:  37%|███▋      | 9468/25880 [1:57:22<2:41:17,  1.70it/s]
1|9469|Loss: 0.8518708944320679:  37%|███▋      | 9468/25880 [1:57:23<2:41:17,  1.70it/s]
1|9469|Loss: 0.8518708944320679:  37%|███▋      | 9469/25880 [1:57:23<2:55:13,  1.56it/s]
1|9470|Loss: 0.769605278968811:  37%|███▋      | 9469/25880 [1:57:24<2:55:13,  1.56it/s] 
1|9470|Loss: 0.769605278968811:  37%|███▋      | 9470/25880 [1:57:24<3:07:21,  1.46it/s]
1|9471|Loss: 0.8252732753753662:  37%|███▋      | 9470/25880 [1:57:24<3:07:21,  1.46it/s]
1|9471|Loss: 0.8252732753753662:  37%|███▋      | 9471/25880 [1:57:25<3:06:35,  1.47it/s]
1|9472|Loss: 0.7491635680198669:  37%|███▋      | 9471/25880 [1:57:25<3:06:35,  1.47it/s]
1|9472|Loss: 0.7491635680198669:  37%|███▋      | 9472/25880 [1:57:26<3:26:19,  1.33it/s]
1|9473|Loss: 0.8272077441215515:  37%|███▋      | 9472/25880 [1:57:26<3:26:19,  1.33it/s]
1|9473|Loss: 0.8272077441215515:  37%|███▋      | 9473/25880 [1:57:26<3:23:11,  1.35it/s]
1|9474|Loss: 0.9344370365142822:  37%|███▋      | 9473/25880 [1:57:27<3:23:11,  1.35it/s]
1|9474|Loss: 0.9344370365142822:  37%|███▋      | 9474/25880 [1:57:27<3:12:59,  1.42it/s]
1|9475|Loss: 0.9740155339241028:  37%|███▋      | 9474/25880 [1:57:27<3:12:59,  1.42it/s]
1|9475|Loss: 0.9740155339241028:  37%|███▋      | 9475/25880 [1:57:28<3:14:22,  1.41it/s]
1|9476|Loss: 0.8596844673156738:  37%|███▋      | 9475/25880 [1:57:28<3:14:22,  1.41it/s]
1|9476|Loss: 0.8596844673156738:  37%|███▋      | 9476/25880 [1:57:28<3:17:42,  1.38it/s]
1|9477|Loss: 1.093861699104309:  37%|███▋      | 9476/25880 [1:57:29<3:17:42,  1.38it/s] 
1|9477|Loss: 1.093861699104309:  37%|███▋      | 9477/25880 [1:57:29<3:10:17,  1.44it/s]
1|9478|Loss: 0.8326960206031799:  37%|███▋      | 9477/25880 [1:57:29<3:10:17,  1.44it/s]
1|9478|Loss: 0.8326960206031799:  37%|███▋      | 9478/25880 [1:57:30<3:10:24,  1.44it/s]
1|9479|Loss: 0.851097583770752:  37%|███▋      | 9478/25880 [1:57:30<3:10:24,  1.44it/s] 
1|9479|Loss: 0.851097583770752:  37%|███▋      | 9479/25880 [1:57:30<2:56:32,  1.55it/s]
1|9480|Loss: 0.9058165550231934:  37%|███▋      | 9479/25880 [1:57:31<2:56:32,  1.55it/s]
1|9480|Loss: 0.9058165550231934:  37%|███▋      | 9480/25880 [1:57:31<3:03:49,  1.49it/s]
1|9481|Loss: 0.9172946810722351:  37%|███▋      | 9480/25880 [1:57:31<3:03:49,  1.49it/s]
1|9481|Loss: 0.9172946810722351:  37%|███▋      | 9481/25880 [1:57:32<3:14:37,  1.40it/s]
1|9482|Loss: 0.8879715204238892:  37%|███▋      | 9481/25880 [1:57:32<3:14:37,  1.40it/s]
1|9482|Loss: 0.8879715204238892:  37%|███▋      | 9482/25880 [1:57:32<3:10:07,  1.44it/s]
1|9483|Loss: 0.874225914478302:  37%|███▋      | 9482/25880 [1:57:33<3:10:07,  1.44it/s] 
1|9483|Loss: 0.874225914478302:  37%|███▋      | 9483/25880 [1:57:33<3:17:42,  1.38it/s]
1|9484|Loss: 0.7739747762680054:  37%|███▋      | 9483/25880 [1:57:34<3:17:42,  1.38it/s]
1|9484|Loss: 0.7739747762680054:  37%|███▋      | 9484/25880 [1:57:34<3:27:12,  1.32it/s]
1|9485|Loss: 0.6942379474639893:  37%|███▋      | 9484/25880 [1:57:34<3:27:12,  1.32it/s]
1|9485|Loss: 0.6942379474639893:  37%|███▋      | 9485/25880 [1:57:35<3:25:48,  1.33it/s]
1|9486|Loss: 0.8297820091247559:  37%|███▋      | 9485/25880 [1:57:35<3:25:48,  1.33it/s]
1|9486|Loss: 0.8297820091247559:  37%|███▋      | 9486/25880 [1:57:35<3:17:06,  1.39it/s]
1|9487|Loss: 0.8232316374778748:  37%|███▋      | 9486/25880 [1:57:36<3:17:06,  1.39it/s]
1|9487|Loss: 0.8232316374778748:  37%|███▋      | 9487/25880 [1:57:36<3:04:53,  1.48it/s]
1|9488|Loss: 0.6835778951644897:  37%|███▋      | 9487/25880 [1:57:36<3:04:53,  1.48it/s]
1|9488|Loss: 0.6835778951644897:  37%|███▋      | 9488/25880 [1:57:37<3:23:04,  1.35it/s]
1|9489|Loss: 0.9031016230583191:  37%|███▋      | 9488/25880 [1:57:37<3:23:04,  1.35it/s]
1|9489|Loss: 0.9031016230583191:  37%|███▋      | 9489/25880 [1:57:38<3:28:43,  1.31it/s]
1|9490|Loss: 0.7862070202827454:  37%|███▋      | 9489/25880 [1:57:38<3:28:43,  1.31it/s]
1|9490|Loss: 0.7862070202827454:  37%|███▋      | 9490/25880 [1:57:38<3:13:25,  1.41it/s]
1|9491|Loss: 0.837512195110321:  37%|███▋      | 9490/25880 [1:57:39<3:13:25,  1.41it/s] 
1|9491|Loss: 0.837512195110321:  37%|███▋      | 9491/25880 [1:57:39<3:09:38,  1.44it/s]
1|9492|Loss: 0.9001774787902832:  37%|███▋      | 9491/25880 [1:57:39<3:09:38,  1.44it/s]
1|9492|Loss: 0.9001774787902832:  37%|███▋      | 9492/25880 [1:57:40<3:02:56,  1.49it/s]
1|9493|Loss: 0.7953190207481384:  37%|███▋      | 9492/25880 [1:57:40<3:02:56,  1.49it/s]
1|9493|Loss: 0.7953190207481384:  37%|███▋      | 9493/25880 [1:57:40<2:55:38,  1.55it/s]
1|9494|Loss: 0.8288381099700928:  37%|███▋      | 9493/25880 [1:57:40<2:55:38,  1.55it/s]
1|9494|Loss: 0.8288381099700928:  37%|███▋      | 9494/25880 [1:57:41<2:53:07,  1.58it/s]
1|9495|Loss: 0.7852596640586853:  37%|███▋      | 9494/25880 [1:57:41<2:53:07,  1.58it/s]
1|9495|Loss: 0.7852596640586853:  37%|███▋      | 9495/25880 [1:57:41<3:00:12,  1.52it/s]
1|9496|Loss: 0.9093732833862305:  37%|███▋      | 9495/25880 [1:57:42<3:00:12,  1.52it/s]
1|9496|Loss: 0.9093732833862305:  37%|███▋      | 9496/25880 [1:57:42<3:04:50,  1.48it/s]
1|9497|Loss: 0.8210715055465698:  37%|███▋      | 9496/25880 [1:57:43<3:04:50,  1.48it/s]
1|9497|Loss: 0.8210715055465698:  37%|███▋      | 9497/25880 [1:57:43<3:07:10,  1.46it/s]
1|9498|Loss: 0.9940628409385681:  37%|███▋      | 9497/25880 [1:57:43<3:07:10,  1.46it/s]
1|9498|Loss: 0.9940628409385681:  37%|███▋      | 9498/25880 [1:57:44<3:08:47,  1.45it/s]
1|9499|Loss: 0.7714849710464478:  37%|███▋      | 9498/25880 [1:57:44<3:08:47,  1.45it/s]
1|9499|Loss: 0.7714849710464478:  37%|███▋      | 9499/25880 [1:57:44<3:12:05,  1.42it/s]
1|9500|Loss: 0.8196998834609985:  37%|███▋      | 9499/25880 [1:57:45<3:12:05,  1.42it/s]
1|9500|Loss: 0.8196998834609985:  37%|███▋      | 9500/25880 [1:57:45<3:24:39,  1.33it/s]
1|9501|Loss: 0.91631680727005:  37%|███▋      | 9500/25880 [1:57:46<3:24:39,  1.33it/s]  
1|9501|Loss: 0.91631680727005:  37%|███▋      | 9501/25880 [1:57:46<3:38:05,  1.25it/s]
1|9502|Loss: 0.8088213205337524:  37%|███▋      | 9501/25880 [1:57:47<3:38:05,  1.25it/s]
1|9502|Loss: 0.8088213205337524:  37%|███▋      | 9502/25880 [1:57:47<3:35:07,  1.27it/s]
1|9503|Loss: 0.8392523527145386:  37%|███▋      | 9502/25880 [1:57:47<3:35:07,  1.27it/s]
1|9503|Loss: 0.8392523527145386:  37%|███▋      | 9503/25880 [1:57:48<3:31:20,  1.29it/s]
1|9504|Loss: 0.8698180317878723:  37%|███▋      | 9503/25880 [1:57:48<3:31:20,  1.29it/s]
1|9504|Loss: 0.8698180317878723:  37%|███▋      | 9504/25880 [1:57:48<3:22:42,  1.35it/s]
1|9505|Loss: 0.9886829853057861:  37%|███▋      | 9504/25880 [1:57:49<3:22:42,  1.35it/s]
1|9505|Loss: 0.9886829853057861:  37%|███▋      | 9505/25880 [1:57:49<3:12:47,  1.42it/s]
1|9506|Loss: 0.8457775712013245:  37%|███▋      | 9505/25880 [1:57:49<3:12:47,  1.42it/s]
1|9506|Loss: 0.8457775712013245:  37%|███▋      | 9506/25880 [1:57:50<3:12:50,  1.42it/s]
1|9507|Loss: 0.9523609280586243:  37%|███▋      | 9506/25880 [1:57:50<3:12:50,  1.42it/s]
1|9507|Loss: 0.9523609280586243:  37%|███▋      | 9507/25880 [1:57:50<3:14:40,  1.40it/s]
1|9508|Loss: 1.0267913341522217:  37%|███▋      | 9507/25880 [1:57:51<3:14:40,  1.40it/s]
1|9508|Loss: 1.0267913341522217:  37%|███▋      | 9508/25880 [1:57:51<3:13:43,  1.41it/s]
1|9509|Loss: 0.8657485842704773:  37%|███▋      | 9508/25880 [1:57:51<3:13:43,  1.41it/s]
1|9509|Loss: 0.8657485842704773:  37%|███▋      | 9509/25880 [1:57:52<3:14:58,  1.40it/s]
1|9510|Loss: 0.8327322006225586:  37%|███▋      | 9509/25880 [1:57:52<3:14:58,  1.40it/s]
1|9510|Loss: 0.8327322006225586:  37%|███▋      | 9510/25880 [1:57:53<3:26:34,  1.32it/s]
1|9511|Loss: 1.0122321844100952:  37%|███▋      | 9510/25880 [1:57:53<3:26:34,  1.32it/s]
1|9511|Loss: 1.0122321844100952:  37%|███▋      | 9511/25880 [1:57:53<3:34:15,  1.27it/s]
1|9512|Loss: 0.8542385101318359:  37%|███▋      | 9511/25880 [1:57:54<3:34:15,  1.27it/s]
1|9512|Loss: 0.8542385101318359:  37%|███▋      | 9512/25880 [1:57:54<3:21:07,  1.36it/s]
1|9513|Loss: 0.843170166015625:  37%|███▋      | 9512/25880 [1:57:54<3:21:07,  1.36it/s] 
1|9513|Loss: 0.843170166015625:  37%|███▋      | 9513/25880 [1:57:55<3:24:43,  1.33it/s]
1|9514|Loss: 0.8907870054244995:  37%|███▋      | 9513/25880 [1:57:55<3:24:43,  1.33it/s]
1|9514|Loss: 0.8907870054244995:  37%|███▋      | 9514/25880 [1:57:56<3:36:17,  1.26it/s]
1|9515|Loss: 0.6982483267784119:  37%|███▋      | 9514/25880 [1:57:56<3:36:17,  1.26it/s]
1|9515|Loss: 0.6982483267784119:  37%|███▋      | 9515/25880 [1:57:57<3:34:22,  1.27it/s]
1|9516|Loss: 1.0167169570922852:  37%|███▋      | 9515/25880 [1:57:57<3:34:22,  1.27it/s]
1|9516|Loss: 1.0167169570922852:  37%|███▋      | 9516/25880 [1:57:57<3:39:16,  1.24it/s]
1|9517|Loss: 0.9387703537940979:  37%|███▋      | 9516/25880 [1:57:58<3:39:16,  1.24it/s]
1|9517|Loss: 0.9387703537940979:  37%|███▋      | 9517/25880 [1:57:58<3:29:45,  1.30it/s]
1|9518|Loss: 0.8241486549377441:  37%|███▋      | 9517/25880 [1:57:58<3:29:45,  1.30it/s]
1|9518|Loss: 0.8241486549377441:  37%|███▋      | 9518/25880 [1:57:59<3:19:18,  1.37it/s]
1|9519|Loss: 0.8351922035217285:  37%|███▋      | 9518/25880 [1:57:59<3:19:18,  1.37it/s]
1|9519|Loss: 0.8351922035217285:  37%|███▋      | 9519/25880 [1:57:59<3:18:23,  1.37it/s]
1|9520|Loss: 0.8253041505813599:  37%|███▋      | 9519/25880 [1:58:00<3:18:23,  1.37it/s]
1|9520|Loss: 0.8253041505813599:  37%|███▋      | 9520/25880 [1:58:00<3:23:30,  1.34it/s]
1|9521|Loss: 0.9401299953460693:  37%|███▋      | 9520/25880 [1:58:01<3:23:30,  1.34it/s]
1|9521|Loss: 0.9401299953460693:  37%|███▋      | 9521/25880 [1:58:01<3:23:53,  1.34it/s]
1|9522|Loss: 0.8058092594146729:  37%|███▋      | 9521/25880 [1:58:01<3:23:53,  1.34it/s]
1|9522|Loss: 0.8058092594146729:  37%|███▋      | 9522/25880 [1:58:02<3:34:45,  1.27it/s]
1|9523|Loss: 0.8274879455566406:  37%|███▋      | 9522/25880 [1:58:02<3:34:45,  1.27it/s]
1|9523|Loss: 0.8274879455566406:  37%|███▋      | 9523/25880 [1:58:03<3:37:16,  1.25it/s]
1|9524|Loss: 0.8140825033187866:  37%|███▋      | 9523/25880 [1:58:03<3:37:16,  1.25it/s]
1|9524|Loss: 0.8140825033187866:  37%|███▋      | 9524/25880 [1:58:03<3:25:46,  1.32it/s]
1|9525|Loss: 0.8555988073348999:  37%|███▋      | 9524/25880 [1:58:04<3:25:46,  1.32it/s]
1|9525|Loss: 0.8555988073348999:  37%|███▋      | 9525/25880 [1:58:04<3:28:56,  1.30it/s]
1|9526|Loss: 0.9373271465301514:  37%|███▋      | 9525/25880 [1:58:04<3:28:56,  1.30it/s]
1|9526|Loss: 0.9373271465301514:  37%|███▋      | 9526/25880 [1:58:05<3:09:12,  1.44it/s]
1|9527|Loss: 0.9218733310699463:  37%|███▋      | 9526/25880 [1:58:05<3:09:12,  1.44it/s]
1|9527|Loss: 0.9218733310699463:  37%|███▋      | 9527/25880 [1:58:05<3:08:12,  1.45it/s]
1|9528|Loss: 0.854577898979187:  37%|███▋      | 9527/25880 [1:58:06<3:08:12,  1.45it/s] 
1|9528|Loss: 0.854577898979187:  37%|███▋      | 9528/25880 [1:58:06<3:06:04,  1.46it/s]
1|9529|Loss: 0.8641767501831055:  37%|███▋      | 9528/25880 [1:58:06<3:06:04,  1.46it/s]
1|9529|Loss: 0.8641767501831055:  37%|███▋      | 9529/25880 [1:58:07<3:00:29,  1.51it/s]
1|9530|Loss: 0.7700022459030151:  37%|███▋      | 9529/25880 [1:58:07<3:00:29,  1.51it/s]
1|9530|Loss: 0.7700022459030151:  37%|███▋      | 9530/25880 [1:58:07<2:49:59,  1.60it/s]
1|9531|Loss: 1.0729258060455322:  37%|███▋      | 9530/25880 [1:58:07<2:49:59,  1.60it/s]
1|9531|Loss: 1.0729258060455322:  37%|███▋      | 9531/25880 [1:58:08<2:49:11,  1.61it/s]
1|9532|Loss: 0.8369393944740295:  37%|███▋      | 9531/25880 [1:58:08<2:49:11,  1.61it/s]
1|9532|Loss: 0.8369393944740295:  37%|███▋      | 9532/25880 [1:58:08<2:54:46,  1.56it/s]
1|9533|Loss: 0.9487647414207458:  37%|███▋      | 9532/25880 [1:58:09<2:54:46,  1.56it/s]
1|9533|Loss: 0.9487647414207458:  37%|███▋      | 9533/25880 [1:58:09<2:55:25,  1.55it/s]
1|9534|Loss: 1.0612753629684448:  37%|███▋      | 9533/25880 [1:58:09<2:55:25,  1.55it/s]
1|9534|Loss: 1.0612753629684448:  37%|███▋      | 9534/25880 [1:58:10<3:07:37,  1.45it/s]
1|9535|Loss: 0.8804436326026917:  37%|███▋      | 9534/25880 [1:58:10<3:07:37,  1.45it/s]
1|9535|Loss: 0.8804436326026917:  37%|███▋      | 9535/25880 [1:58:11<3:10:59,  1.43it/s]
1|9536|Loss: 0.800416111946106:  37%|███▋      | 9535/25880 [1:58:11<3:10:59,  1.43it/s] 
1|9536|Loss: 0.800416111946106:  37%|███▋      | 9536/25880 [1:58:11<3:10:18,  1.43it/s]
1|9537|Loss: 0.9334666132926941:  37%|███▋      | 9536/25880 [1:58:12<3:10:18,  1.43it/s]
1|9537|Loss: 0.9334666132926941:  37%|███▋      | 9537/25880 [1:58:12<3:12:58,  1.41it/s]
1|9538|Loss: 0.7350424528121948:  37%|███▋      | 9537/25880 [1:58:12<3:12:58,  1.41it/s]
1|9538|Loss: 0.7350424528121948:  37%|███▋      | 9538/25880 [1:58:12<2:53:17,  1.57it/s]
1|9539|Loss: 0.9334169030189514:  37%|███▋      | 9538/25880 [1:58:13<2:53:17,  1.57it/s]
1|9539|Loss: 0.9334169030189514:  37%|███▋      | 9539/25880 [1:58:13<2:41:36,  1.69it/s]
1|9540|Loss: 0.721572756767273:  37%|███▋      | 9539/25880 [1:58:13<2:41:36,  1.69it/s] 
1|9540|Loss: 0.721572756767273:  37%|███▋      | 9540/25880 [1:58:14<2:48:41,  1.61it/s]
1|9541|Loss: 0.8318438529968262:  37%|███▋      | 9540/25880 [1:58:14<2:48:41,  1.61it/s]
1|9541|Loss: 0.8318438529968262:  37%|███▋      | 9541/25880 [1:58:14<2:51:50,  1.58it/s]
1|9542|Loss: 0.8717482686042786:  37%|███▋      | 9541/25880 [1:58:15<2:51:50,  1.58it/s]
1|9542|Loss: 0.8717482686042786:  37%|███▋      | 9542/25880 [1:58:15<2:58:37,  1.52it/s]
1|9543|Loss: 0.897178053855896:  37%|███▋      | 9542/25880 [1:58:15<2:58:37,  1.52it/s] 
1|9543|Loss: 0.897178053855896:  37%|███▋      | 9543/25880 [1:58:16<3:03:32,  1.48it/s]
1|9544|Loss: 0.8298152089118958:  37%|███▋      | 9543/25880 [1:58:16<3:03:32,  1.48it/s]
1|9544|Loss: 0.8298152089118958:  37%|███▋      | 9544/25880 [1:58:16<3:05:57,  1.46it/s]
1|9545|Loss: 0.6418471336364746:  37%|███▋      | 9544/25880 [1:58:17<3:05:57,  1.46it/s]
1|9545|Loss: 0.6418471336364746:  37%|███▋      | 9545/25880 [1:58:17<3:21:12,  1.35it/s]
1|9546|Loss: 0.8767961859703064:  37%|███▋      | 9545/25880 [1:58:18<3:21:12,  1.35it/s]
1|9546|Loss: 0.8767961859703064:  37%|███▋      | 9546/25880 [1:58:18<3:13:17,  1.41it/s]
1|9547|Loss: 0.9133066534996033:  37%|███▋      | 9546/25880 [1:58:18<3:13:17,  1.41it/s]
1|9547|Loss: 0.9133066534996033:  37%|███▋      | 9547/25880 [1:58:19<3:28:06,  1.31it/s]
1|9548|Loss: 0.856478214263916:  37%|███▋      | 9547/25880 [1:58:19<3:28:06,  1.31it/s] 
1|9548|Loss: 0.856478214263916:  37%|███▋      | 9548/25880 [1:58:20<3:40:06,  1.24it/s]
1|9549|Loss: 0.9043392539024353:  37%|███▋      | 9548/25880 [1:58:20<3:40:06,  1.24it/s]
1|9549|Loss: 0.9043392539024353:  37%|███▋      | 9549/25880 [1:58:21<3:45:34,  1.21it/s]
1|9550|Loss: 0.8066907525062561:  37%|███▋      | 9549/25880 [1:58:21<3:45:34,  1.21it/s]
1|9550|Loss: 0.8066907525062561:  37%|███▋      | 9550/25880 [1:58:22<3:52:10,  1.17it/s]
1|9551|Loss: 0.8330788016319275:  37%|███▋      | 9550/25880 [1:58:22<3:52:10,  1.17it/s]
1|9551|Loss: 0.8330788016319275:  37%|███▋      | 9551/25880 [1:58:22<3:30:39,  1.29it/s]
1|9552|Loss: 0.8246984481811523:  37%|███▋      | 9551/25880 [1:58:22<3:30:39,  1.29it/s]
1|9552|Loss: 0.8246984481811523:  37%|███▋      | 9552/25880 [1:58:23<3:12:01,  1.42it/s]
1|9553|Loss: 0.8474031686782837:  37%|███▋      | 9552/25880 [1:58:23<3:12:01,  1.42it/s]
1|9553|Loss: 0.8474031686782837:  37%|███▋      | 9553/25880 [1:58:23<3:09:21,  1.44it/s]
1|9554|Loss: 0.7592835426330566:  37%|███▋      | 9553/25880 [1:58:24<3:09:21,  1.44it/s]
1|9554|Loss: 0.7592835426330566:  37%|███▋      | 9554/25880 [1:58:24<3:11:45,  1.42it/s]
1|9555|Loss: 0.8308061957359314:  37%|███▋      | 9554/25880 [1:58:25<3:11:45,  1.42it/s]
1|9555|Loss: 0.8308061957359314:  37%|███▋      | 9555/25880 [1:58:25<3:21:25,  1.35it/s]
1|9556|Loss: 0.7794838547706604:  37%|███▋      | 9555/25880 [1:58:25<3:21:25,  1.35it/s]
1|9556|Loss: 0.7794838547706604:  37%|███▋      | 9556/25880 [1:58:26<3:17:45,  1.38it/s]
1|9557|Loss: 0.8457773923873901:  37%|███▋      | 9556/25880 [1:58:26<3:17:45,  1.38it/s]
1|9557|Loss: 0.8457773923873901:  37%|███▋      | 9557/25880 [1:58:26<3:16:59,  1.38it/s]
1|9558|Loss: 0.7946228384971619:  37%|███▋      | 9557/25880 [1:58:27<3:16:59,  1.38it/s]
1|9558|Loss: 0.7946228384971619:  37%|███▋      | 9558/25880 [1:58:27<3:23:53,  1.33it/s]
1|9559|Loss: 0.7051348090171814:  37%|███▋      | 9558/25880 [1:58:28<3:23:53,  1.33it/s]
1|9559|Loss: 0.7051348090171814:  37%|███▋      | 9559/25880 [1:58:28<3:27:04,  1.31it/s]
1|9560|Loss: 0.8036078214645386:  37%|███▋      | 9559/25880 [1:58:28<3:27:04,  1.31it/s]
1|9560|Loss: 0.8036078214645386:  37%|███▋      | 9560/25880 [1:58:29<3:18:18,  1.37it/s]
1|9561|Loss: 0.7878987193107605:  37%|███▋      | 9560/25880 [1:58:29<3:18:18,  1.37it/s]
1|9561|Loss: 0.7878987193107605:  37%|███▋      | 9561/25880 [1:58:29<3:16:10,  1.39it/s]
1|9562|Loss: 0.9042388796806335:  37%|███▋      | 9561/25880 [1:58:30<3:16:10,  1.39it/s]
1|9562|Loss: 0.9042388796806335:  37%|███▋      | 9562/25880 [1:58:30<3:16:29,  1.38it/s]
1|9563|Loss: 0.7341546416282654:  37%|███▋      | 9562/25880 [1:58:30<3:16:29,  1.38it/s]
1|9563|Loss: 0.7341546416282654:  37%|███▋      | 9563/25880 [1:58:31<3:03:54,  1.48it/s]
1|9564|Loss: 0.7681480646133423:  37%|███▋      | 9563/25880 [1:58:31<3:03:54,  1.48it/s]
1|9564|Loss: 0.7681480646133423:  37%|███▋      | 9564/25880 [1:58:31<3:05:00,  1.47it/s]
1|9565|Loss: 1.0151232481002808:  37%|███▋      | 9564/25880 [1:58:32<3:05:00,  1.47it/s]
1|9565|Loss: 1.0151232481002808:  37%|███▋      | 9565/25880 [1:58:32<3:08:50,  1.44it/s]
1|9566|Loss: 0.7797704935073853:  37%|███▋      | 9565/25880 [1:58:32<3:08:50,  1.44it/s]
1|9566|Loss: 0.7797704935073853:  37%|███▋      | 9566/25880 [1:58:33<3:02:17,  1.49it/s]
1|9567|Loss: 0.7695318460464478:  37%|███▋      | 9566/25880 [1:58:33<3:02:17,  1.49it/s]
1|9567|Loss: 0.7695318460464478:  37%|███▋      | 9567/25880 [1:58:33<3:05:02,  1.47it/s]
1|9568|Loss: 0.9731373190879822:  37%|███▋      | 9567/25880 [1:58:34<3:05:02,  1.47it/s]
1|9568|Loss: 0.9731373190879822:  37%|███▋      | 9568/25880 [1:58:34<2:51:27,  1.59it/s]
1|9569|Loss: 0.9380849599838257:  37%|███▋      | 9568/25880 [1:58:34<2:51:27,  1.59it/s]
1|9569|Loss: 0.9380849599838257:  37%|███▋      | 9569/25880 [1:58:34<2:52:35,  1.58it/s]
1|9570|Loss: 0.8440960049629211:  37%|███▋      | 9569/25880 [1:58:35<2:52:35,  1.58it/s]
1|9570|Loss: 0.8440960049629211:  37%|███▋      | 9570/25880 [1:58:35<3:00:41,  1.50it/s]
1|9571|Loss: 0.8157077431678772:  37%|███▋      | 9570/25880 [1:58:36<3:00:41,  1.50it/s]
1|9571|Loss: 0.8157077431678772:  37%|███▋      | 9571/25880 [1:58:36<2:56:30,  1.54it/s]
1|9572|Loss: 0.9083913564682007:  37%|███▋      | 9571/25880 [1:58:36<2:56:30,  1.54it/s]
1|9572|Loss: 0.9083913564682007:  37%|███▋      | 9572/25880 [1:58:36<2:55:01,  1.55it/s]
1|9573|Loss: 0.8034975528717041:  37%|███▋      | 9572/25880 [1:58:37<2:55:01,  1.55it/s]
1|9573|Loss: 0.8034975528717041:  37%|███▋      | 9573/25880 [1:58:37<3:09:08,  1.44it/s]
1|9574|Loss: 0.745793879032135:  37%|███▋      | 9573/25880 [1:58:38<3:09:08,  1.44it/s] 
1|9574|Loss: 0.745793879032135:  37%|███▋      | 9574/25880 [1:58:38<3:22:39,  1.34it/s]
1|9575|Loss: 0.8719830513000488:  37%|███▋      | 9574/25880 [1:58:39<3:22:39,  1.34it/s]
1|9575|Loss: 0.8719830513000488:  37%|███▋      | 9575/25880 [1:58:39<3:24:35,  1.33it/s]
1|9576|Loss: 0.8486068248748779:  37%|███▋      | 9575/25880 [1:58:39<3:24:35,  1.33it/s]
1|9576|Loss: 0.8486068248748779:  37%|███▋      | 9576/25880 [1:58:40<3:26:44,  1.31it/s]
1|9577|Loss: 0.865367591381073:  37%|███▋      | 9576/25880 [1:58:40<3:26:44,  1.31it/s] 
1|9577|Loss: 0.865367591381073:  37%|███▋      | 9577/25880 [1:58:41<3:33:31,  1.27it/s]
1|9578|Loss: 1.0126795768737793:  37%|███▋      | 9577/25880 [1:58:41<3:33:31,  1.27it/s]
1|9578|Loss: 1.0126795768737793:  37%|███▋      | 9578/25880 [1:58:41<3:47:09,  1.20it/s]
1|9579|Loss: 0.8441376090049744:  37%|███▋      | 9578/25880 [1:58:42<3:47:09,  1.20it/s]
1|9579|Loss: 0.8441376090049744:  37%|███▋      | 9579/25880 [1:58:42<3:28:54,  1.30it/s]
1|9580|Loss: 0.7985944151878357:  37%|███▋      | 9579/25880 [1:58:42<3:28:54,  1.30it/s]
1|9580|Loss: 0.7985944151878357:  37%|███▋      | 9580/25880 [1:58:43<3:22:07,  1.34it/s]
1|9581|Loss: 0.7876832485198975:  37%|███▋      | 9580/25880 [1:58:43<3:22:07,  1.34it/s]
1|9581|Loss: 0.7876832485198975:  37%|███▋      | 9581/25880 [1:58:43<3:11:00,  1.42it/s]
1|9582|Loss: 0.8467670679092407:  37%|███▋      | 9581/25880 [1:58:44<3:11:00,  1.42it/s]
1|9582|Loss: 0.8467670679092407:  37%|███▋      | 9582/25880 [1:58:44<3:22:19,  1.34it/s]
1|9583|Loss: 0.8700656294822693:  37%|███▋      | 9582/25880 [1:58:45<3:22:19,  1.34it/s]
1|9583|Loss: 0.8700656294822693:  37%|███▋      | 9583/25880 [1:58:45<3:01:31,  1.50it/s]
1|9584|Loss: 0.8535864949226379:  37%|███▋      | 9583/25880 [1:58:45<3:01:31,  1.50it/s]
1|9584|Loss: 0.8535864949226379:  37%|███▋      | 9584/25880 [1:58:45<2:55:49,  1.54it/s]
1|9585|Loss: 0.9311383366584778:  37%|███▋      | 9584/25880 [1:58:46<2:55:49,  1.54it/s]
1|9585|Loss: 0.9311383366584778:  37%|███▋      | 9585/25880 [1:58:46<2:54:13,  1.56it/s]
1|9586|Loss: 0.8808527588844299:  37%|███▋      | 9585/25880 [1:58:46<2:54:13,  1.56it/s]
1|9586|Loss: 0.8808527588844299:  37%|███▋      | 9586/25880 [1:58:47<3:01:27,  1.50it/s]
1|9587|Loss: 0.8339017629623413:  37%|███▋      | 9586/25880 [1:58:47<3:01:27,  1.50it/s]
1|9587|Loss: 0.8339017629623413:  37%|███▋      | 9587/25880 [1:58:48<3:14:05,  1.40it/s]
1|9588|Loss: 0.8885947465896606:  37%|███▋      | 9587/25880 [1:58:48<3:14:05,  1.40it/s]
1|9588|Loss: 0.8885947465896606:  37%|███▋      | 9588/25880 [1:58:48<3:10:45,  1.42it/s]
1|9589|Loss: 0.7131608724594116:  37%|███▋      | 9588/25880 [1:58:49<3:10:45,  1.42it/s]
1|9589|Loss: 0.7131608724594116:  37%|███▋      | 9589/25880 [1:58:49<3:03:44,  1.48it/s]
1|9590|Loss: 0.8044236302375793:  37%|███▋      | 9589/25880 [1:58:49<3:03:44,  1.48it/s]
1|9590|Loss: 0.8044236302375793:  37%|███▋      | 9590/25880 [1:58:49<3:00:41,  1.50it/s]
1|9591|Loss: 0.9445214867591858:  37%|███▋      | 9590/25880 [1:58:50<3:00:41,  1.50it/s]
1|9591|Loss: 0.9445214867591858:  37%|███▋      | 9591/25880 [1:58:50<3:08:28,  1.44it/s]
1|9592|Loss: 1.0649815797805786:  37%|███▋      | 9591/25880 [1:58:51<3:08:28,  1.44it/s]
1|9592|Loss: 1.0649815797805786:  37%|███▋      | 9592/25880 [1:58:51<3:12:47,  1.41it/s]
1|9593|Loss: 0.8152597546577454:  37%|███▋      | 9592/25880 [1:58:51<3:12:47,  1.41it/s]
1|9593|Loss: 0.8152597546577454:  37%|███▋      | 9593/25880 [1:58:52<3:21:43,  1.35it/s]
1|9594|Loss: 0.9308483004570007:  37%|███▋      | 9593/25880 [1:58:52<3:21:43,  1.35it/s]
1|9594|Loss: 0.9308483004570007:  37%|███▋      | 9594/25880 [1:58:53<3:26:44,  1.31it/s]
1|9595|Loss: 0.8579262495040894:  37%|███▋      | 9594/25880 [1:58:53<3:26:44,  1.31it/s]
1|9595|Loss: 0.8579262495040894:  37%|███▋      | 9595/25880 [1:58:53<3:23:19,  1.33it/s]
1|9596|Loss: 0.7199329137802124:  37%|███▋      | 9595/25880 [1:58:54<3:23:19,  1.33it/s]
1|9596|Loss: 0.7199329137802124:  37%|███▋      | 9596/25880 [1:58:54<3:19:10,  1.36it/s]
1|9597|Loss: 0.6605966091156006:  37%|███▋      | 9596/25880 [1:58:54<3:19:10,  1.36it/s]
1|9597|Loss: 0.6605966091156006:  37%|███▋      | 9597/25880 [1:58:55<3:24:35,  1.33it/s]
1|9598|Loss: 0.6097690463066101:  37%|███▋      | 9597/25880 [1:58:55<3:24:35,  1.33it/s]
1|9598|Loss: 0.6097690463066101:  37%|███▋      | 9598/25880 [1:58:56<3:36:27,  1.25it/s]
1|9599|Loss: 0.8391613364219666:  37%|███▋      | 9598/25880 [1:58:56<3:36:27,  1.25it/s]
1|9599|Loss: 0.8391613364219666:  37%|███▋      | 9599/25880 [1:58:56<3:28:04,  1.30it/s]
1|9600|Loss: 0.8540211319923401:  37%|███▋      | 9599/25880 [1:58:57<3:28:04,  1.30it/s]
1|9600|Loss: 0.8540211319923401:  37%|███▋      | 9600/25880 [1:58:57<3:21:54,  1.34it/s]
1|9601|Loss: 0.8650826215744019:  37%|███▋      | 9600/25880 [1:58:57<3:21:54,  1.34it/s]
1|9601|Loss: 0.8650826215744019:  37%|███▋      | 9601/25880 [1:58:58<3:26:04,  1.32it/s]
1|9602|Loss: 0.9646567702293396:  37%|███▋      | 9601/25880 [1:58:58<3:26:04,  1.32it/s]
1|9602|Loss: 0.9646567702293396:  37%|███▋      | 9602/25880 [1:58:59<3:23:27,  1.33it/s]
1|9603|Loss: 1.0202664136886597:  37%|███▋      | 9602/25880 [1:58:59<3:23:27,  1.33it/s]
1|9603|Loss: 1.0202664136886597:  37%|███▋      | 9603/25880 [1:58:59<3:25:37,  1.32it/s]
1|9604|Loss: 0.8965054750442505:  37%|███▋      | 9603/25880 [1:59:00<3:25:37,  1.32it/s]
1|9604|Loss: 0.8965054750442505:  37%|███▋      | 9604/25880 [1:59:00<3:26:08,  1.32it/s]
1|9605|Loss: 0.8291916251182556:  37%|███▋      | 9604/25880 [1:59:01<3:26:08,  1.32it/s]
1|9605|Loss: 0.8291916251182556:  37%|███▋      | 9605/25880 [1:59:01<3:25:23,  1.32it/s]
1|9606|Loss: 0.8269615769386292:  37%|███▋      | 9605/25880 [1:59:01<3:25:23,  1.32it/s]
1|9606|Loss: 0.8269615769386292:  37%|███▋      | 9606/25880 [1:59:02<3:22:36,  1.34it/s]
1|9607|Loss: 0.8864084482192993:  37%|███▋      | 9606/25880 [1:59:02<3:22:36,  1.34it/s]
1|9607|Loss: 0.8864084482192993:  37%|███▋      | 9607/25880 [1:59:02<3:06:35,  1.45it/s]
1|9608|Loss: 0.7379657626152039:  37%|███▋      | 9607/25880 [1:59:03<3:06:35,  1.45it/s]
1|9608|Loss: 0.7379657626152039:  37%|███▋      | 9608/25880 [1:59:03<3:22:01,  1.34it/s]
1|9609|Loss: 0.9064306616783142:  37%|███▋      | 9608/25880 [1:59:03<3:22:01,  1.34it/s]
1|9609|Loss: 0.9064306616783142:  37%|███▋      | 9609/25880 [1:59:04<3:23:06,  1.34it/s]
1|9610|Loss: 0.8170246481895447:  37%|███▋      | 9609/25880 [1:59:04<3:23:06,  1.34it/s]
1|9610|Loss: 0.8170246481895447:  37%|███▋      | 9610/25880 [1:59:05<3:26:40,  1.31it/s]
1|9611|Loss: 0.7373517155647278:  37%|███▋      | 9610/25880 [1:59:05<3:26:40,  1.31it/s]
1|9611|Loss: 0.7373517155647278:  37%|███▋      | 9611/25880 [1:59:05<3:19:13,  1.36it/s]
1|9612|Loss: 0.9447301626205444:  37%|███▋      | 9611/25880 [1:59:06<3:19:13,  1.36it/s]
1|9612|Loss: 0.9447301626205444:  37%|███▋      | 9612/25880 [1:59:06<3:15:29,  1.39it/s]
1|9613|Loss: 0.882068395614624:  37%|███▋      | 9612/25880 [1:59:06<3:15:29,  1.39it/s] 
1|9613|Loss: 0.882068395614624:  37%|███▋      | 9613/25880 [1:59:07<3:20:01,  1.36it/s]
1|9614|Loss: 0.7770241498947144:  37%|███▋      | 9613/25880 [1:59:07<3:20:01,  1.36it/s]
1|9614|Loss: 0.7770241498947144:  37%|███▋      | 9614/25880 [1:59:07<3:18:43,  1.36it/s]
1|9615|Loss: 0.9099081754684448:  37%|███▋      | 9614/25880 [1:59:08<3:18:43,  1.36it/s]
1|9615|Loss: 0.9099081754684448:  37%|███▋      | 9615/25880 [1:59:08<3:08:08,  1.44it/s]
1|9616|Loss: 0.7543466687202454:  37%|███▋      | 9615/25880 [1:59:08<3:08:08,  1.44it/s]
1|9616|Loss: 0.7543466687202454:  37%|███▋      | 9616/25880 [1:59:09<3:16:22,  1.38it/s]
1|9617|Loss: 1.0270963907241821:  37%|███▋      | 9616/25880 [1:59:09<3:16:22,  1.38it/s]
1|9617|Loss: 1.0270963907241821:  37%|███▋      | 9617/25880 [1:59:10<3:13:31,  1.40it/s]
1|9618|Loss: 0.8895729780197144:  37%|███▋      | 9617/25880 [1:59:10<3:13:31,  1.40it/s]
1|9618|Loss: 0.8895729780197144:  37%|███▋      | 9618/25880 [1:59:10<3:28:42,  1.30it/s]
1|9619|Loss: 0.848613440990448:  37%|███▋      | 9618/25880 [1:59:11<3:28:42,  1.30it/s] 
1|9619|Loss: 0.848613440990448:  37%|███▋      | 9619/25880 [1:59:11<3:34:22,  1.26it/s]
1|9620|Loss: 0.7376073002815247:  37%|███▋      | 9619/25880 [1:59:12<3:34:22,  1.26it/s]
1|9620|Loss: 0.7376073002815247:  37%|███▋      | 9620/25880 [1:59:12<3:39:56,  1.23it/s]
1|9621|Loss: 0.7833207249641418:  37%|███▋      | 9620/25880 [1:59:13<3:39:56,  1.23it/s]
1|9621|Loss: 0.7833207249641418:  37%|███▋      | 9621/25880 [1:59:13<3:20:16,  1.35it/s]
1|9622|Loss: 0.9374973177909851:  37%|███▋      | 9621/25880 [1:59:13<3:20:16,  1.35it/s]
1|9622|Loss: 0.9374973177909851:  37%|███▋      | 9622/25880 [1:59:13<3:13:36,  1.40it/s]
1|9623|Loss: 0.8132412433624268:  37%|███▋      | 9622/25880 [1:59:14<3:13:36,  1.40it/s]
1|9623|Loss: 0.8132412433624268:  37%|███▋      | 9623/25880 [1:59:14<3:05:19,  1.46it/s]
1|9624|Loss: 0.9272293448448181:  37%|███▋      | 9623/25880 [1:59:14<3:05:19,  1.46it/s]
1|9624|Loss: 0.9272293448448181:  37%|███▋      | 9624/25880 [1:59:15<3:06:50,  1.45it/s]
1|9625|Loss: 0.7632110714912415:  37%|███▋      | 9624/25880 [1:59:15<3:06:50,  1.45it/s]
1|9625|Loss: 0.7632110714912415:  37%|███▋      | 9625/25880 [1:59:15<3:10:53,  1.42it/s]
1|9626|Loss: 0.8660898804664612:  37%|███▋      | 9625/25880 [1:59:16<3:10:53,  1.42it/s]
1|9626|Loss: 0.8660898804664612:  37%|███▋      | 9626/25880 [1:59:16<2:54:40,  1.55it/s]
1|9627|Loss: 0.74588942527771:  37%|███▋      | 9626/25880 [1:59:16<2:54:40,  1.55it/s]  
1|9627|Loss: 0.74588942527771:  37%|███▋      | 9627/25880 [1:59:17<2:57:17,  1.53it/s]
1|9628|Loss: 0.9416200518608093:  37%|███▋      | 9627/25880 [1:59:17<2:57:17,  1.53it/s]
1|9628|Loss: 0.9416200518608093:  37%|███▋      | 9628/25880 [1:59:17<2:53:03,  1.57it/s]
1|9629|Loss: 0.6971385478973389:  37%|███▋      | 9628/25880 [1:59:18<2:53:03,  1.57it/s]
1|9629|Loss: 0.6971385478973389:  37%|███▋      | 9629/25880 [1:59:18<2:56:08,  1.54it/s]
1|9630|Loss: 0.786907434463501:  37%|███▋      | 9629/25880 [1:59:18<2:56:08,  1.54it/s] 
1|9630|Loss: 0.786907434463501:  37%|███▋      | 9630/25880 [1:59:19<3:02:23,  1.48it/s]
1|9631|Loss: 0.8621050119400024:  37%|███▋      | 9630/25880 [1:59:19<3:02:23,  1.48it/s]
1|9631|Loss: 0.8621050119400024:  37%|███▋      | 9631/25880 [1:59:19<3:15:14,  1.39it/s]
1|9632|Loss: 0.9206209778785706:  37%|███▋      | 9631/25880 [1:59:20<3:15:14,  1.39it/s]
1|9632|Loss: 0.9206209778785706:  37%|███▋      | 9632/25880 [1:59:20<3:23:13,  1.33it/s]
1|9633|Loss: 0.8474433422088623:  37%|███▋      | 9632/25880 [1:59:21<3:23:13,  1.33it/s]
1|9633|Loss: 0.8474433422088623:  37%|███▋      | 9633/25880 [1:59:21<3:23:00,  1.33it/s]
1|9634|Loss: 0.7728575468063354:  37%|███▋      | 9633/25880 [1:59:21<3:23:00,  1.33it/s]
1|9634|Loss: 0.7728575468063354:  37%|███▋      | 9634/25880 [1:59:22<3:20:11,  1.35it/s]
1|9635|Loss: 0.7914199829101562:  37%|███▋      | 9634/25880 [1:59:22<3:20:11,  1.35it/s]
1|9635|Loss: 0.7914199829101562:  37%|███▋      | 9635/25880 [1:59:22<3:18:44,  1.36it/s]
1|9636|Loss: 0.8658029437065125:  37%|███▋      | 9635/25880 [1:59:23<3:18:44,  1.36it/s]
1|9636|Loss: 0.8658029437065125:  37%|███▋      | 9636/25880 [1:59:23<3:16:31,  1.38it/s]
1|9637|Loss: 0.7535483837127686:  37%|███▋      | 9636/25880 [1:59:24<3:16:31,  1.38it/s]
1|9637|Loss: 0.7535483837127686:  37%|███▋      | 9637/25880 [1:59:24<3:33:07,  1.27it/s]
1|9638|Loss: 0.929756760597229:  37%|███▋      | 9637/25880 [1:59:25<3:33:07,  1.27it/s] 
1|9638|Loss: 0.929756760597229:  37%|███▋      | 9638/25880 [1:59:25<3:40:38,  1.23it/s]
1|9639|Loss: 0.9067903757095337:  37%|███▋      | 9638/25880 [1:59:25<3:40:38,  1.23it/s]
1|9639|Loss: 0.9067903757095337:  37%|███▋      | 9639/25880 [1:59:26<3:39:11,  1.23it/s]
1|9640|Loss: 0.889389157295227:  37%|███▋      | 9639/25880 [1:59:26<3:39:11,  1.23it/s] 
1|9640|Loss: 0.889389157295227:  37%|███▋      | 9640/25880 [1:59:26<3:24:09,  1.33it/s]
1|9641|Loss: 0.9089769721031189:  37%|███▋      | 9640/25880 [1:59:27<3:24:09,  1.33it/s]
1|9641|Loss: 0.9089769721031189:  37%|███▋      | 9641/25880 [1:59:27<3:24:34,  1.32it/s]
1|9642|Loss: 0.8759410977363586:  37%|███▋      | 9641/25880 [1:59:28<3:24:34,  1.32it/s]
1|9642|Loss: 0.8759410977363586:  37%|███▋      | 9642/25880 [1:59:28<3:27:12,  1.31it/s]
1|9643|Loss: 0.5849087238311768:  37%|███▋      | 9642/25880 [1:59:29<3:27:12,  1.31it/s]
1|9643|Loss: 0.5849087238311768:  37%|███▋      | 9643/25880 [1:59:30<4:48:30,  1.07s/it]
1|9644|Loss: 0.7190701365470886:  37%|███▋      | 9643/25880 [1:59:30<4:48:30,  1.07s/it]
1|9644|Loss: 0.7190701365470886:  37%|███▋      | 9644/25880 [1:59:31<4:53:26,  1.08s/it]
1|9645|Loss: 0.8797852396965027:  37%|███▋      | 9644/25880 [1:59:31<4:53:26,  1.08s/it]
1|9645|Loss: 0.8797852396965027:  37%|███▋      | 9645/25880 [1:59:32<4:37:32,  1.03s/it]
1|9646|Loss: 0.888587474822998:  37%|███▋      | 9645/25880 [1:59:32<4:37:32,  1.03s/it] 
1|9646|Loss: 0.888587474822998:  37%|��██▋      | 9646/25880 [1:59:32<4:14:30,  1.06it/s]
1|9647|Loss: 0.8699226379394531:  37%|███▋      | 9646/25880 [1:59:33<4:14:30,  1.06it/s]
1|9647|Loss: 0.8699226379394531:  37%|███▋      | 9647/25880 [1:59:33<3:54:52,  1.15it/s]
1|9648|Loss: 0.781600832939148:  37%|███▋      | 9647/25880 [1:59:34<3:54:52,  1.15it/s] 
1|9648|Loss: 0.781600832939148:  37%|███▋      | 9648/25880 [1:59:34<3:40:56,  1.22it/s]
1|9649|Loss: 0.8012843132019043:  37%|███▋      | 9648/25880 [1:59:34<3:40:56,  1.22it/s]
1|9649|Loss: 0.8012843132019043:  37%|███▋      | 9649/25880 [1:59:35<3:32:58,  1.27it/s]
1|9650|Loss: 0.8595299124717712:  37%|███▋      | 9649/25880 [1:59:35<3:32:58,  1.27it/s]
1|9650|Loss: 0.8595299124717712:  37%|███▋      | 9650/25880 [1:59:35<3:26:20,  1.31it/s]
1|9651|Loss: 0.8624182343482971:  37%|███▋      | 9650/25880 [1:59:36<3:26:20,  1.31it/s]
1|9651|Loss: 0.8624182343482971:  37%|███▋      | 9651/25880 [1:59:36<3:15:22,  1.38it/s]
1|9652|Loss: 0.8972910046577454:  37%|███▋      | 9651/25880 [1:59:36<3:15:22,  1.38it/s]
1|9652|Loss: 0.8972910046577454:  37%|███▋      | 9652/25880 [1:59:37<3:18:43,  1.36it/s]
1|9653|Loss: 0.8152965903282166:  37%|███▋      | 9652/25880 [1:59:37<3:18:43,  1.36it/s]
1|9653|Loss: 0.8152965903282166:  37%|███▋      | 9653/25880 [1:59:37<3:13:25,  1.40it/s]
1|9654|Loss: 0.9071078300476074:  37%|███▋      | 9653/25880 [1:59:38<3:13:25,  1.40it/s]
1|9654|Loss: 0.9071078300476074:  37%|███▋      | 9654/25880 [1:59:38<3:22:56,  1.33it/s]
1|9655|Loss: 0.833281934261322:  37%|███▋      | 9654/25880 [1:59:39<3:22:56,  1.33it/s] 
1|9655|Loss: 0.833281934261322:  37%|███▋      | 9655/25880 [1:59:39<3:30:52,  1.28it/s]
1|9656|Loss: 0.6674951314926147:  37%|███▋      | 9655/25880 [1:59:40<3:30:52,  1.28it/s]
1|9656|Loss: 0.6674951314926147:  37%|███▋      | 9656/25880 [1:59:40<3:43:45,  1.21it/s]
1|9657|Loss: 0.6994574069976807:  37%|███▋      | 9656/25880 [1:59:40<3:43:45,  1.21it/s]
1|9657|Loss: 0.6994574069976807:  37%|███▋      | 9657/25880 [1:59:41<3:41:20,  1.22it/s]
1|9658|Loss: 1.001876711845398:  37%|███▋      | 9657/25880 [1:59:41<3:41:20,  1.22it/s] 
1|9658|Loss: 1.001876711845398:  37%|███▋      | 9658/25880 [1:59:42<3:35:35,  1.25it/s]
1|9659|Loss: 0.8787431120872498:  37%|███▋      | 9658/25880 [1:59:42<3:35:35,  1.25it/s]
1|9659|Loss: 0.8787431120872498:  37%|███▋      | 9659/25880 [1:59:42<3:30:58,  1.28it/s]
1|9660|Loss: 0.8756435513496399:  37%|███▋      | 9659/25880 [1:59:43<3:30:58,  1.28it/s]
1|9660|Loss: 0.8756435513496399:  37%|███▋      | 9660/25880 [1:59:43<3:38:52,  1.24it/s]
1|9661|Loss: 0.8630523085594177:  37%|███▋      | 9660/25880 [1:59:44<3:38:52,  1.24it/s]
1|9661|Loss: 0.8630523085594177:  37%|███▋      | 9661/25880 [1:59:44<3:38:48,  1.24it/s]
1|9662|Loss: 0.7196193337440491:  37%|███▋      | 9661/25880 [1:59:44<3:38:48,  1.24it/s]
1|9662|Loss: 0.7196193337440491:  37%|███▋      | 9662/25880 [1:59:45<3:48:40,  1.18it/s]
1|9663|Loss: 0.8210540413856506:  37%|███▋      | 9662/25880 [1:59:45<3:48:40,  1.18it/s]
1|9663|Loss: 0.8210540413856506:  37%|███▋      | 9663/25880 [1:59:46<3:43:26,  1.21it/s]
1|9664|Loss: 0.8212839365005493:  37%|███▋      | 9663/25880 [1:59:46<3:43:26,  1.21it/s]
1|9664|Loss: 0.8212839365005493:  37%|███▋      | 9664/25880 [1:59:46<3:44:44,  1.20it/s]
1|9665|Loss: 1.0444505214691162:  37%|███▋      | 9664/25880 [1:59:47<3:44:44,  1.20it/s]
1|9665|Loss: 1.0444505214691162:  37%|███▋      | 9665/25880 [1:59:47<3:45:53,  1.20it/s]
1|9666|Loss: 0.834433376789093:  37%|███▋      | 9665/25880 [1:59:48<3:45:53,  1.20it/s] 
1|9666|Loss: 0.834433376789093:  37%|███▋      | 9666/25880 [1:59:48<3:39:00,  1.23it/s]
1|9667|Loss: 0.82607501745224:  37%|███▋      | 9666/25880 [1:59:48<3:39:00,  1.23it/s] 
1|9667|Loss: 0.82607501745224:  37%|███▋      | 9667/25880 [1:59:49<3:24:40,  1.32it/s]
1|9668|Loss: 0.9716485142707825:  37%|███▋      | 9667/25880 [1:59:49<3:24:40,  1.32it/s]
1|9668|Loss: 0.9716485142707825:  37%|███▋      | 9668/25880 [1:59:49<3:11:04,  1.41it/s]
1|9669|Loss: 0.7723262310028076:  37%|███▋      | 9668/25880 [1:59:50<3:11:04,  1.41it/s]
1|9669|Loss: 0.7723262310028076:  37%|███▋      | 9669/25880 [1:59:50<3:04:35,  1.46it/s]
1|9670|Loss: 0.847446084022522:  37%|███▋      | 9669/25880 [1:59:50<3:04:35,  1.46it/s] 
1|9670|Loss: 0.847446084022522:  37%|███▋      | 9670/25880 [1:59:51<3:15:23,  1.38it/s]
1|9671|Loss: 0.9148393273353577:  37%|███▋      | 9670/25880 [1:59:51<3:15:23,  1.38it/s]
1|9671|Loss: 0.9148393273353577:  37%|███▋      | 9671/25880 [1:59:51<3:16:27,  1.38it/s]
1|9672|Loss: 0.989051342010498:  37%|███▋      | 9671/25880 [1:59:52<3:16:27,  1.38it/s] 
1|9672|Loss: 0.989051342010498:  37%|███▋      | 9672/25880 [1:59:52<3:28:49,  1.29it/s]
1|9673|Loss: 0.8187265992164612:  37%|███▋      | 9672/25880 [1:59:53<3:28:49,  1.29it/s]
1|9673|Loss: 0.8187265992164612:  37%|███▋      | 9673/25880 [1:59:53<3:28:39,  1.29it/s]
1|9674|Loss: 0.7959204316139221:  37%|███▋      | 9673/25880 [1:59:53<3:28:39,  1.29it/s]
1|9674|Loss: 0.7959204316139221:  37%|███▋      | 9674/25880 [1:59:54<3:07:10,  1.44it/s]
1|9675|Loss: 0.6738952398300171:  37%|███▋      | 9674/25880 [1:59:54<3:07:10,  1.44it/s]
1|9675|Loss: 0.6738952398300171:  37%|███▋      | 9675/25880 [1:59:54<3:17:11,  1.37it/s]
1|9676|Loss: 0.7832984328269958:  37%|███▋      | 9675/25880 [1:59:55<3:17:11,  1.37it/s]
1|9676|Loss: 0.7832984328269958:  37%|███▋      | 9676/25880 [1:59:55<3:19:41,  1.35it/s]
1|9677|Loss: 0.7781546711921692:  37%|███▋      | 9676/25880 [1:59:56<3:19:41,  1.35it/s]
1|9677|Loss: 0.7781546711921692:  37%|███▋      | 9677/25880 [1:59:56<3:17:00,  1.37it/s]
1|9678|Loss: 0.8727902173995972:  37%|███▋      | 9677/25880 [1:59:56<3:17:00,  1.37it/s]
1|9678|Loss: 0.8727902173995972:  37%|███▋      | 9678/25880 [1:59:57<3:10:37,  1.42it/s]
1|9679|Loss: 0.7690791487693787:  37%|███▋      | 9678/25880 [1:59:57<3:10:37,  1.42it/s]
1|9679|Loss: 0.7690791487693787:  37%|███▋      | 9679/25880 [1:59:57<3:20:30,  1.35it/s]
1|9680|Loss: 0.9059392213821411:  37%|███▋      | 9679/25880 [1:59:58<3:20:30,  1.35it/s]
1|9680|Loss: 0.9059392213821411:  37%|███▋      | 9680/25880 [1:59:58<3:14:42,  1.39it/s]
1|9681|Loss: 0.8043705224990845:  37%|███▋      | 9680/25880 [1:59:58<3:14:42,  1.39it/s]
1|9681|Loss: 0.8043705224990845:  37%|███▋      | 9681/25880 [1:59:59<3:03:59,  1.47it/s]
1|9682|Loss: 0.7340133190155029:  37%|███▋      | 9681/25880 [1:59:59<3:03:59,  1.47it/s]
1|9682|Loss: 0.7340133190155029:  37%|███▋      | 9682/25880 [1:59:59<3:05:13,  1.46it/s]
1|9683|Loss: 0.8469330668449402:  37%|███▋      | 9682/25880 [2:00:00<3:05:13,  1.46it/s]
1|9683|Loss: 0.8469330668449402:  37%|███▋      | 9683/25880 [2:00:00<3:01:23,  1.49it/s]
1|9684|Loss: 0.9020051956176758:  37%|███▋      | 9683/25880 [2:00:00<3:01:23,  1.49it/s]
1|9684|Loss: 0.9020051956176758:  37%|███▋      | 9684/25880 [2:00:01<2:55:50,  1.54it/s]
1|9685|Loss: 0.8413694500923157:  37%|███▋      | 9684/25880 [2:00:01<2:55:50,  1.54it/s]
1|9685|Loss: 0.8413694500923157:  37%|███▋      | 9685/25880 [2:00:01<3:05:53,  1.45it/s]
1|9686|Loss: 1.0212602615356445:  37%|███▋      | 9685/25880 [2:00:02<3:05:53,  1.45it/s]
1|9686|Loss: 1.0212602615356445:  37%|███▋      | 9686/25880 [2:00:02<3:05:02,  1.46it/s]
1|9687|Loss: 0.810427188873291:  37%|███▋      | 9686/25880 [2:00:02<3:05:02,  1.46it/s] 
1|9687|Loss: 0.810427188873291:  37%|███▋      | 9687/25880 [2:00:03<3:13:45,  1.39it/s]
1|9688|Loss: 0.6832061409950256:  37%|███▋      | 9687/25880 [2:00:03<3:13:45,  1.39it/s]
1|9688|Loss: 0.6832061409950256:  37%|███▋      | 9688/25880 [2:00:03<3:01:52,  1.48it/s]
1|9689|Loss: 0.7920168042182922:  37%|███▋      | 9688/25880 [2:00:04<3:01:52,  1.48it/s]
1|9689|Loss: 0.7920168042182922:  37%|███▋      | 9689/25880 [2:00:04<3:07:23,  1.44it/s]
1|9690|Loss: 0.9009504318237305:  37%|███▋      | 9689/25880 [2:00:05<3:07:23,  1.44it/s]
1|9690|Loss: 0.9009504318237305:  37%|███▋      | 9690/25880 [2:00:05<3:16:20,  1.37it/s]
1|9691|Loss: 0.7693848013877869:  37%|███▋      | 9690/25880 [2:00:05<3:16:20,  1.37it/s]
1|9691|Loss: 0.7693848013877869:  37%|███▋      | 9691/25880 [2:00:06<3:18:23,  1.36it/s]
1|9692|Loss: 0.7952536344528198:  37%|███▋      | 9691/25880 [2:00:06<3:18:23,  1.36it/s]
1|9692|Loss: 0.7952536344528198:  37%|███▋      | 9692/25880 [2:00:06<3:18:25,  1.36it/s]
1|9693|Loss: 0.9966389536857605:  37%|███▋      | 9692/25880 [2:00:07<3:18:25,  1.36it/s]
1|9693|Loss: 0.9966389536857605:  37%|███▋      | 9693/25880 [2:00:07<3:06:33,  1.45it/s]
1|9694|Loss: 0.8831868171691895:  37%|███▋      | 9693/25880 [2:00:07<3:06:33,  1.45it/s]
1|9694|Loss: 0.8831868171691895:  37%|███▋      | 9694/25880 [2:00:08<2:57:54,  1.52it/s]
1|9695|Loss: 0.9457309246063232:  37%|███▋      | 9694/25880 [2:00:08<2:57:54,  1.52it/s]
1|9695|Loss: 0.9457309246063232:  37%|███▋      | 9695/25880 [2:00:08<2:53:20,  1.56it/s]
1|9696|Loss: 0.8344661593437195:  37%|███▋      | 9695/25880 [2:00:09<2:53:20,  1.56it/s]
1|9696|Loss: 0.8344661593437195:  37%|███▋      | 9696/25880 [2:00:09<2:52:50,  1.56it/s]
1|9697|Loss: 0.8150604367256165:  37%|███▋      | 9696/25880 [2:00:09<2:52:50,  1.56it/s]
1|9697|Loss: 0.8150604367256165:  37%|███▋      | 9697/25880 [2:00:09<2:49:08,  1.59it/s]
1|9698|Loss: 0.949863851070404:  37%|███▋      | 9697/25880 [2:00:10<2:49:08,  1.59it/s] 
1|9698|Loss: 0.949863851070404:  37%|███▋      | 9698/25880 [2:00:10<2:49:04,  1.60it/s]
1|9699|Loss: 0.9659304618835449:  37%|███▋      | 9698/25880 [2:00:10<2:49:04,  1.60it/s]
1|9699|Loss: 0.9659304618835449:  37%|███▋      | 9699/25880 [2:00:11<2:48:51,  1.60it/s]
1|9700|Loss: 0.8719850182533264:  37%|███▋      | 9699/25880 [2:00:11<2:48:51,  1.60it/s]
1|9700|Loss: 0.8719850182533264:  37%|███▋      | 9700/25880 [2:00:11<2:45:50,  1.63it/s]
1|9701|Loss: 0.8321481943130493:  37%|███▋      | 9700/25880 [2:00:12<2:45:50,  1.63it/s]
1|9701|Loss: 0.8321481943130493:  37%|███▋      | 9701/25880 [2:00:12<2:46:47,  1.62it/s]
1|9702|Loss: 0.9693523645401001:  37%|███▋      | 9701/25880 [2:00:12<2:46:47,  1.62it/s]
1|9702|Loss: 0.9693523645401001:  37%|███▋      | 9702/25880 [2:00:13<2:54:14,  1.55it/s]
1|9703|Loss: 0.6566024422645569:  37%|███▋      | 9702/25880 [2:00:13<2:54:14,  1.55it/s]
1|9703|Loss: 0.6566024422645569:  37%|███▋      | 9703/25880 [2:00:13<2:47:41,  1.61it/s]
1|9704|Loss: 0.8223692178726196:  37%|███▋      | 9703/25880 [2:00:14<2:47:41,  1.61it/s]
1|9704|Loss: 0.8223692178726196:  37%|███▋      | 9704/25880 [2:00:14<2:45:45,  1.63it/s]
1|9705|Loss: 0.8576437830924988:  37%|███▋      | 9704/25880 [2:00:14<2:45:45,  1.63it/s]
1|9705|Loss: 0.8576437830924988:  38%|███▊      | 9705/25880 [2:00:14<2:43:29,  1.65it/s]
1|9706|Loss: 0.8294723033905029:  38%|███▊      | 9705/25880 [2:00:15<2:43:29,  1.65it/s]
1|9706|Loss: 0.8294723033905029:  38%|███▊      | 9706/25880 [2:00:15<2:49:56,  1.59it/s]
1|9707|Loss: 0.796894907951355:  38%|███▊      | 9706/25880 [2:00:16<2:49:56,  1.59it/s] 
1|9707|Loss: 0.796894907951355:  38%|███▊      | 9707/25880 [2:00:16<3:02:15,  1.48it/s]
1|9708|Loss: 0.7927576303482056:  38%|███▊      | 9707/25880 [2:00:16<3:02:15,  1.48it/s]
1|9708|Loss: 0.7927576303482056:  38%|███▊      | 9708/25880 [2:00:17<3:16:51,  1.37it/s]
1|9709|Loss: 0.8518733382225037:  38%|███▊      | 9708/25880 [2:00:17<3:16:51,  1.37it/s]
1|9709|Loss: 0.8518733382225037:  38%|███▊      | 9709/25880 [2:00:17<3:17:47,  1.36it/s]
1|9710|Loss: 0.8147432208061218:  38%|███▊      | 9709/25880 [2:00:18<3:17:47,  1.36it/s]
1|9710|Loss: 0.8147432208061218:  38%|███▊      | 9710/25880 [2:00:18<3:21:03,  1.34it/s]
1|9711|Loss: 0.8084850907325745:  38%|███▊      | 9710/25880 [2:00:19<3:21:03,  1.34it/s]
1|9711|Loss: 0.8084850907325745:  38%|███▊      | 9711/25880 [2:00:19<3:21:30,  1.34it/s]
1|9712|Loss: 0.7563512921333313:  38%|███▊      | 9711/25880 [2:00:19<3:21:30,  1.34it/s]
1|9712|Loss: 0.7563512921333313:  38%|███▊      | 9712/25880 [2:00:20<3:28:06,  1.29it/s]
1|9713|Loss: 0.8729294538497925:  38%|███▊      | 9712/25880 [2:00:20<3:28:06,  1.29it/s]
1|9713|Loss: 0.8729294538497925:  38%|███▊      | 9713/25880 [2:00:20<3:13:01,  1.40it/s]
1|9714|Loss: 0.7408179044723511:  38%|███▊      | 9713/25880 [2:00:21<3:13:01,  1.40it/s]
1|9714|Loss: 0.7408179044723511:  38%|███▊      | 9714/25880 [2:00:21<3:11:00,  1.41it/s]
1|9715|Loss: 0.8381780385971069:  38%|███▊      | 9714/25880 [2:00:21<3:11:00,  1.41it/s]
1|9715|Loss: 0.8381780385971069:  38%|███▊      | 9715/25880 [2:00:22<3:04:14,  1.46it/s]
1|9716|Loss: 0.8428660035133362:  38%|███▊      | 9715/25880 [2:00:22<3:04:14,  1.46it/s]
1|9716|Loss: 0.8428660035133362:  38%|███▊      | 9716/25880 [2:00:23<3:11:42,  1.41it/s]
1|9717|Loss: 0.913151741027832:  38%|███▊      | 9716/25880 [2:00:23<3:11:42,  1.41it/s] 
1|9717|Loss: 0.913151741027832:  38%|███▊      | 9717/25880 [2:00:23<3:24:28,  1.32it/s]
1|9718|Loss: 0.7805662751197815:  38%|███▊      | 9717/25880 [2:00:24<3:24:28,  1.32it/s]
1|9718|Loss: 0.7805662751197815:  38%|███▊      | 9718/25880 [2:00:24<3:18:17,  1.36it/s]
1|9719|Loss: 0.9491785168647766:  38%|███▊      | 9718/25880 [2:00:24<3:18:17,  1.36it/s]
1|9719|Loss: 0.9491785168647766:  38%|███▊      | 9719/25880 [2:00:25<3:10:06,  1.42it/s]
1|9720|Loss: 0.7738916277885437:  38%|███▊      | 9719/25880 [2:00:25<3:10:06,  1.42it/s]
1|9720|Loss: 0.7738916277885437:  38%|███▊      | 9720/25880 [2:00:25<3:08:49,  1.43it/s]
1|9721|Loss: 0.8685962557792664:  38%|███▊      | 9720/25880 [2:00:26<3:08:49,  1.43it/s]
1|9721|Loss: 0.8685962557792664:  38%|███▊      | 9721/25880 [2:00:26<3:08:29,  1.43it/s]
1|9722|Loss: 0.8971649408340454:  38%|███▊      | 9721/25880 [2:00:26<3:08:29,  1.43it/s]
1|9722|Loss: 0.8971649408340454:  38%|███▊      | 9722/25880 [2:00:27<3:15:07,  1.38it/s]
1|9723|Loss: 0.8450994491577148:  38%|███▊      | 9722/25880 [2:00:27<3:15:07,  1.38it/s]
1|9723|Loss: 0.8450994491577148:  38%|███▊      | 9723/25880 [2:00:28<3:16:41,  1.37it/s]
1|9724|Loss: 0.8046907782554626:  38%|███▊      | 9723/25880 [2:00:28<3:16:41,  1.37it/s]
1|9724|Loss: 0.8046907782554626:  38%|███▊      | 9724/25880 [2:00:28<3:06:39,  1.44it/s]
1|9725|Loss: 0.8957194685935974:  38%|███▊      | 9724/25880 [2:00:29<3:06:39,  1.44it/s]
1|9725|Loss: 0.8957194685935974:  38%|███▊      | 9725/25880 [2:00:29<3:18:57,  1.35it/s]
1|9726|Loss: 0.9925327897071838:  38%|███▊      | 9725/25880 [2:00:30<3:18:57,  1.35it/s]
1|9726|Loss: 0.9925327897071838:  38%|███▊      | 9726/25880 [2:00:30<3:27:01,  1.30it/s]
1|9727|Loss: 0.8130203485488892:  38%|███▊      | 9726/25880 [2:00:30<3:27:01,  1.30it/s]
1|9727|Loss: 0.8130203485488892:  38%|███▊      | 9727/25880 [2:00:31<3:31:29,  1.27it/s]
1|9728|Loss: 0.7980141639709473:  38%|███▊      | 9727/25880 [2:00:31<3:31:29,  1.27it/s]
1|9728|Loss: 0.7980141639709473:  38%|███▊      | 9728/25880 [2:00:31<3:14:01,  1.39it/s]
1|9729|Loss: 0.9311675429344177:  38%|███▊      | 9728/25880 [2:00:32<3:14:01,  1.39it/s]
1|9729|Loss: 0.9311675429344177:  38%|███▊      | 9729/25880 [2:00:32<3:17:42,  1.36it/s]
1|9730|Loss: 0.7540642023086548:  38%|███▊      | 9729/25880 [2:00:32<3:17:42,  1.36it/s]
1|9730|Loss: 0.7540642023086548:  38%|███▊      | 9730/25880 [2:00:33<3:20:04,  1.35it/s]
1|9731|Loss: 0.8042379021644592:  38%|███▊      | 9730/25880 [2:00:33<3:20:04,  1.35it/s]
1|9731|Loss: 0.8042379021644592:  38%|███▊      | 9731/25880 [2:00:33<3:05:23,  1.45it/s]
1|9732|Loss: 0.739674985408783:  38%|███▊      | 9731/25880 [2:00:34<3:05:23,  1.45it/s] 
1|9732|Loss: 0.739674985408783:  38%|███▊      | 9732/25880 [2:00:34<3:08:48,  1.43it/s]
1|9733|Loss: 0.8612063527107239:  38%|███▊      | 9732/25880 [2:00:35<3:08:48,  1.43it/s]
1|9733|Loss: 0.8612063527107239:  38%|███▊      | 9733/25880 [2:00:35<3:10:52,  1.41it/s]
1|9734|Loss: 0.7633158564567566:  38%|███▊      | 9733/25880 [2:00:35<3:10:52,  1.41it/s]
1|9734|Loss: 0.7633158564567566:  38%|███▊      | 9734/25880 [2:00:36<3:24:40,  1.31it/s]
1|9735|Loss: 0.8540840744972229:  38%|███▊      | 9734/25880 [2:00:36<3:24:40,  1.31it/s]
1|9735|Loss: 0.8540840744972229:  38%|███▊      | 9735/25880 [2:00:36<3:18:00,  1.36it/s]
1|9736|Loss: 0.8589797616004944:  38%|███▊      | 9735/25880 [2:00:37<3:18:00,  1.36it/s]
1|9736|Loss: 0.8589797616004944:  38%|███▊      | 9736/25880 [2:00:37<3:08:30,  1.43it/s]
1|9737|Loss: 0.6365411877632141:  38%|███▊      | 9736/25880 [2:00:37<3:08:30,  1.43it/s]
1|9737|Loss: 0.6365411877632141:  38%|███▊      | 9737/25880 [2:00:38<3:26:00,  1.31it/s]
1|9738|Loss: 0.7383413910865784:  38%|███▊      | 9737/25880 [2:00:38<3:26:00,  1.31it/s]
1|9738|Loss: 0.7383413910865784:  38%|███▊      | 9738/25880 [2:00:39<3:10:01,  1.42it/s]
1|9739|Loss: 0.7454729080200195:  38%|███▊      | 9738/25880 [2:00:39<3:10:01,  1.42it/s]
1|9739|Loss: 0.7454729080200195:  38%|███▊      | 9739/25880 [2:00:39<3:16:45,  1.37it/s]
1|9740|Loss: 0.7664696574211121:  38%|███▊      | 9739/25880 [2:00:40<3:16:45,  1.37it/s]
1|9740|Loss: 0.7664696574211121:  38%|███▊      | 9740/25880 [2:00:40<3:25:37,  1.31it/s]
1|9741|Loss: 0.8025712966918945:  38%|███▊      | 9740/25880 [2:00:40<3:25:37,  1.31it/s]
1|9741|Loss: 0.8025712966918945:  38%|███▊      | 9741/25880 [2:00:41<3:11:43,  1.40it/s]
1|9742|Loss: 0.8490524291992188:  38%|███▊      | 9741/25880 [2:00:41<3:11:43,  1.40it/s]
1|9742|Loss: 0.8490524291992188:  38%|███▊      | 9742/25880 [2:00:42<3:20:10,  1.34it/s]
1|9743|Loss: 0.8953564763069153:  38%|███▊      | 9742/25880 [2:00:42<3:20:10,  1.34it/s]
1|9743|Loss: 0.8953564763069153:  38%|███▊      | 9743/25880 [2:00:42<3:22:34,  1.33it/s]
1|9744|Loss: 0.7697532773017883:  38%|███▊      | 9743/25880 [2:00:43<3:22:34,  1.33it/s]
1|9744|Loss: 0.7697532773017883:  38%|███▊      | 9744/25880 [2:00:43<3:10:51,  1.41it/s]
1|9745|Loss: 0.7969627380371094:  38%|███▊      | 9744/25880 [2:00:43<3:10:51,  1.41it/s]
1|9745|Loss: 0.7969627380371094:  38%|███▊      | 9745/25880 [2:00:44<3:08:22,  1.43it/s]
1|9746|Loss: 0.816616952419281:  38%|███▊      | 9745/25880 [2:00:44<3:08:22,  1.43it/s] 
1|9746|Loss: 0.816616952419281:  38%|███▊      | 9746/25880 [2:00:44<3:22:20,  1.33it/s]
1|9747|Loss: 0.8335202932357788:  38%|███▊      | 9746/25880 [2:00:45<3:22:20,  1.33it/s]
1|9747|Loss: 0.8335202932357788:  38%|███▊      | 9747/25880 [2:00:45<3:29:54,  1.28it/s]
1|9748|Loss: 0.7997649908065796:  38%|███▊      | 9747/25880 [2:00:46<3:29:54,  1.28it/s]
1|9748|Loss: 0.7997649908065796:  38%|███▊      | 9748/25880 [2:00:46<3:34:54,  1.25it/s]
1|9749|Loss: 0.8722714185714722:  38%|███▊      | 9748/25880 [2:00:47<3:34:54,  1.25it/s]
1|9749|Loss: 0.8722714185714722:  38%|███▊      | 9749/25880 [2:00:47<3:32:12,  1.27it/s]
1|9750|Loss: 0.870043158531189:  38%|███▊      | 9749/25880 [2:00:47<3:32:12,  1.27it/s] 
1|9750|Loss: 0.870043158531189:  38%|███▊      | 9750/25880 [2:00:48<3:27:16,  1.30it/s]
1|9751|Loss: 0.6322727799415588:  38%|███▊      | 9750/25880 [2:00:48<3:27:16,  1.30it/s]
1|9751|Loss: 0.6322727799415588:  38%|███▊      | 9751/25880 [2:00:48<3:23:19,  1.32it/s]
1|9752|Loss: 0.8072830438613892:  38%|███▊      | 9751/25880 [2:00:49<3:23:19,  1.32it/s]
1|9752|Loss: 0.8072830438613892:  38%|███▊      | 9752/25880 [2:00:49<3:15:19,  1.38it/s]
1|9753|Loss: 0.7884314060211182:  38%|███▊      | 9752/25880 [2:00:49<3:15:19,  1.38it/s]
1|9753|Loss: 0.7884314060211182:  38%|███▊      | 9753/25880 [2:00:50<3:15:23,  1.38it/s]
1|9754|Loss: 0.926845371723175:  38%|███▊      | 9753/25880 [2:00:50<3:15:23,  1.38it/s] 
1|9754|Loss: 0.926845371723175:  38%|███▊      | 9754/25880 [2:00:50<3:10:30,  1.41it/s]
1|9755|Loss: 1.2686513662338257:  38%|███▊      | 9754/25880 [2:00:51<3:10:30,  1.41it/s]
1|9755|Loss: 1.2686513662338257:  38%|███▊      | 9755/25880 [2:00:51<3:10:29,  1.41it/s]
1|9756|Loss: 0.8985171318054199:  38%|███▊      | 9755/25880 [2:00:52<3:10:29,  1.41it/s]
1|9756|Loss: 0.8985171318054199:  38%|███▊      | 9756/25880 [2:00:52<3:11:56,  1.40it/s]
1|9757|Loss: 0.6848250031471252:  38%|███▊      | 9756/25880 [2:00:52<3:11:56,  1.40it/s]
1|9757|Loss: 0.6848250031471252:  38%|███▊      | 9757/25880 [2:00:53<3:30:06,  1.28it/s]
1|9758|Loss: 0.8839954733848572:  38%|███▊      | 9757/25880 [2:00:53<3:30:06,  1.28it/s]
1|9758|Loss: 0.8839954733848572:  38%|███▊      | 9758/25880 [2:00:54<3:23:58,  1.32it/s]
1|9759|Loss: 0.7050233483314514:  38%|███▊      | 9758/25880 [2:00:54<3:23:58,  1.32it/s]
1|9759|Loss: 0.7050233483314514:  38%|███▊      | 9759/25880 [2:00:54<3:40:12,  1.22it/s]
1|9760|Loss: 0.9436901807785034:  38%|███▊      | 9759/25880 [2:00:55<3:40:12,  1.22it/s]
1|9760|Loss: 0.9436901807785034:  38%|███▊      | 9760/25880 [2:00:55<3:32:09,  1.27it/s]
1|9761|Loss: 0.8441802263259888:  38%|███▊      | 9760/25880 [2:00:56<3:32:09,  1.27it/s]
1|9761|Loss: 0.8441802263259888:  38%|███▊      | 9761/25880 [2:00:56<3:24:39,  1.31it/s]
1|9762|Loss: 0.9396718144416809:  38%|███▊      | 9761/25880 [2:00:56<3:24:39,  1.31it/s]
1|9762|Loss: 0.9396718144416809:  38%|███▊      | 9762/25880 [2:00:57<3:27:49,  1.29it/s]
1|9763|Loss: 0.8700553774833679:  38%|███▊      | 9762/25880 [2:00:57<3:27:49,  1.29it/s]
1|9763|Loss: 0.8700553774833679:  38%|███▊      | 9763/25880 [2:00:57<3:23:54,  1.32it/s]
1|9764|Loss: 0.9405828714370728:  38%|███▊      | 9763/25880 [2:00:58<3:23:54,  1.32it/s]
1|9764|Loss: 0.9405828714370728:  38%|███▊      | 9764/25880 [2:00:58<3:27:45,  1.29it/s]
1|9765|Loss: 1.0186197757720947:  38%|███▊      | 9764/25880 [2:00:59<3:27:45,  1.29it/s]
1|9765|Loss: 1.0186197757720947:  38%|███▊      | 9765/25880 [2:00:59<3:20:13,  1.34it/s]
1|9766|Loss: 0.8445075750350952:  38%|███▊      | 9765/25880 [2:00:59<3:20:13,  1.34it/s]
1|9766|Loss: 0.8445075750350952:  38%|███▊      | 9766/25880 [2:01:00<3:27:11,  1.30it/s]
1|9767|Loss: 0.8802298903465271:  38%|███▊      | 9766/25880 [2:01:00<3:27:11,  1.30it/s]
1|9767|Loss: 0.8802298903465271:  38%|███▊      | 9767/25880 [2:01:00<3:21:29,  1.33it/s]
1|9768|Loss: 0.8180840611457825:  38%|███▊      | 9767/25880 [2:01:01<3:21:29,  1.33it/s]
1|9768|Loss: 0.8180840611457825:  38%|███▊      | 9768/25880 [2:01:01<3:11:19,  1.40it/s]
1|9769|Loss: 1.1120338439941406:  38%|███▊      | 9768/25880 [2:01:01<3:11:19,  1.40it/s]
1|9769|Loss: 1.1120338439941406:  38%|███▊      | 9769/25880 [2:01:02<3:05:08,  1.45it/s]
1|9770|Loss: 0.9577658176422119:  38%|███▊      | 9769/25880 [2:01:02<3:05:08,  1.45it/s]
1|9770|Loss: 0.9577658176422119:  38%|███▊      | 9770/25880 [2:01:03<3:21:44,  1.33it/s]
1|9771|Loss: 0.964717447757721:  38%|███▊      | 9770/25880 [2:01:03<3:21:44,  1.33it/s] 
1|9771|Loss: 0.964717447757721:  38%|███▊      | 9771/25880 [2:01:03<3:24:40,  1.31it/s]
1|9772|Loss: 0.6004953384399414:  38%|███▊      | 9771/25880 [2:01:04<3:24:40,  1.31it/s]
1|9772|Loss: 0.6004953384399414:  38%|███▊      | 9772/25880 [2:01:04<3:13:49,  1.39it/s]
1|9773|Loss: 0.8099350333213806:  38%|███▊      | 9772/25880 [2:01:04<3:13:49,  1.39it/s]
1|9773|Loss: 0.8099350333213806:  38%|███▊      | 9773/25880 [2:01:05<3:04:21,  1.46it/s]
1|9774|Loss: 0.8186058402061462:  38%|███▊      | 9773/25880 [2:01:05<3:04:21,  1.46it/s]
1|9774|Loss: 0.8186058402061462:  38%|███▊      | 9774/25880 [2:01:05<3:04:43,  1.45it/s]
1|9775|Loss: 0.8691995739936829:  38%|███▊      | 9774/25880 [2:01:06<3:04:43,  1.45it/s]
1|9775|Loss: 0.8691995739936829:  38%|███▊      | 9775/25880 [2:01:06<3:11:06,  1.40it/s]
1|9776|Loss: 0.8997682929039001:  38%|███▊      | 9775/25880 [2:01:06<3:11:06,  1.40it/s]
1|9776|Loss: 0.8997682929039001:  38%|███▊      | 9776/25880 [2:01:07<2:59:52,  1.49it/s]
1|9777|Loss: 0.7871338725090027:  38%|███▊      | 9776/25880 [2:01:07<2:59:52,  1.49it/s]
1|9777|Loss: 0.7871338725090027:  38%|███▊      | 9777/25880 [2:01:07<3:01:55,  1.48it/s]
1|9778|Loss: 1.06251859664917:  38%|███▊      | 9777/25880 [2:01:08<3:01:55,  1.48it/s]  
1|9778|Loss: 1.06251859664917:  38%|███▊      | 9778/25880 [2:01:08<3:09:55,  1.41it/s]
1|9779|Loss: 0.8118331432342529:  38%|███▊      | 9778/25880 [2:01:09<3:09:55,  1.41it/s]
1|9779|Loss: 0.8118331432342529:  38%|███▊      | 9779/25880 [2:01:09<3:07:36,  1.43it/s]
1|9780|Loss: 0.8948670029640198:  38%|███▊      | 9779/25880 [2:01:09<3:07:36,  1.43it/s]
1|9780|Loss: 0.8948670029640198:  38%|███▊      | 9780/25880 [2:01:09<3:06:42,  1.44it/s]
1|9781|Loss: 0.7538518309593201:  38%|███▊      | 9780/25880 [2:01:10<3:06:42,  1.44it/s]
1|9781|Loss: 0.7538518309593201:  38%|███▊      | 9781/25880 [2:01:10<3:07:42,  1.43it/s]
1|9782|Loss: 0.8610501289367676:  38%|███▊      | 9781/25880 [2:01:11<3:07:42,  1.43it/s]
1|9782|Loss: 0.8610501289367676:  38%|███▊      | 9782/25880 [2:01:11<3:04:11,  1.46it/s]
1|9783|Loss: 0.7808047533035278:  38%|███▊      | 9782/25880 [2:01:11<3:04:11,  1.46it/s]
1|9783|Loss: 0.7808047533035278:  38%|███▊      | 9783/25880 [2:01:12<3:06:22,  1.44it/s]
1|9784|Loss: 0.8331413865089417:  38%|███▊      | 9783/25880 [2:01:12<3:06:22,  1.44it/s]
1|9784|Loss: 0.8331413865089417:  38%|███▊      | 9784/25880 [2:01:12<3:08:59,  1.42it/s]
1|9785|Loss: 0.7929463982582092:  38%|███▊      | 9784/25880 [2:01:13<3:08:59,  1.42it/s]
1|9785|Loss: 0.7929463982582092:  38%|███▊      | 9785/25880 [2:01:13<3:08:59,  1.42it/s]
1|9786|Loss: 0.8103039860725403:  38%|███▊      | 9785/25880 [2:01:13<3:08:59,  1.42it/s]
1|9786|Loss: 0.8103039860725403:  38%|███▊      | 9786/25880 [2:01:14<3:16:27,  1.37it/s]
1|9787|Loss: 0.7726004123687744:  38%|███▊      | 9786/25880 [2:01:14<3:16:27,  1.37it/s]
1|9787|Loss: 0.7726004123687744:  38%|███▊      | 9787/25880 [2:01:15<3:15:57,  1.37it/s]
1|9788|Loss: 0.8194741010665894:  38%|███▊      | 9787/25880 [2:01:15<3:15:57,  1.37it/s]
1|9788|Loss: 0.8194741010665894:  38%|███▊      | 9788/25880 [2:01:15<3:09:29,  1.42it/s]
1|9789|Loss: 0.8677785992622375:  38%|███▊      | 9788/25880 [2:01:16<3:09:29,  1.42it/s]
1|9789|Loss: 0.8677785992622375:  38%|███▊      | 9789/25880 [2:01:16<3:07:56,  1.43it/s]
1|9790|Loss: 0.8787088394165039:  38%|███▊      | 9789/25880 [2:01:16<3:07:56,  1.43it/s]
1|9790|Loss: 0.8787088394165039:  38%|███▊      | 9790/25880 [2:01:17<3:04:07,  1.46it/s]
1|9791|Loss: 0.9464019536972046:  38%|███▊      | 9790/25880 [2:01:17<3:04:07,  1.46it/s]
1|9791|Loss: 0.9464019536972046:  38%|███▊      | 9791/25880 [2:01:17<3:10:51,  1.40it/s]
1|9792|Loss: 0.7799936532974243:  38%|███▊      | 9791/25880 [2:01:18<3:10:51,  1.40it/s]
1|9792|Loss: 0.7799936532974243:  38%|███▊      | 9792/25880 [2:01:18<3:14:39,  1.38it/s]
1|9793|Loss: 0.8966706991195679:  38%|███▊      | 9792/25880 [2:01:18<3:14:39,  1.38it/s]
1|9793|Loss: 0.8966706991195679:  38%|███▊      | 9793/25880 [2:01:19<3:20:18,  1.34it/s]
1|9794|Loss: 0.9279256463050842:  38%|███▊      | 9793/25880 [2:01:19<3:20:18,  1.34it/s]
1|9794|Loss: 0.9279256463050842:  38%|███▊      | 9794/25880 [2:01:20<3:17:59,  1.35it/s]
1|9795|Loss: 0.8001265525817871:  38%|███▊      | 9794/25880 [2:01:20<3:17:59,  1.35it/s]
1|9795|Loss: 0.8001265525817871:  38%|███▊      | 9795/25880 [2:01:20<3:26:33,  1.30it/s]
1|9796|Loss: 0.8113646507263184:  38%|███▊      | 9795/25880 [2:01:21<3:26:33,  1.30it/s]
1|9796|Loss: 0.8113646507263184:  38%|███▊      | 9796/25880 [2:01:21<3:30:33,  1.27it/s]
1|9797|Loss: 0.8270881175994873:  38%|███▊      | 9796/25880 [2:01:22<3:30:33,  1.27it/s]
1|9797|Loss: 0.8270881175994873:  38%|███▊      | 9797/25880 [2:01:22<3:17:22,  1.36it/s]
1|9798|Loss: 0.8347619771957397:  38%|███▊      | 9797/25880 [2:01:22<3:17:22,  1.36it/s]
1|9798|Loss: 0.8347619771957397:  38%|███▊      | 9798/25880 [2:01:23<3:20:25,  1.34it/s]
1|9799|Loss: 0.7288893461227417:  38%|███▊      | 9798/25880 [2:01:23<3:20:25,  1.34it/s]
1|9799|Loss: 0.7288893461227417:  38%|███▊      | 9799/25880 [2:01:23<3:21:14,  1.33it/s]
1|9800|Loss: 0.8157892823219299:  38%|███▊      | 9799/25880 [2:01:24<3:21:14,  1.33it/s]
1|9800|Loss: 0.8157892823219299:  38%|███▊      | 9800/25880 [2:01:24<3:12:36,  1.39it/s]
1|9801|Loss: 0.9463314414024353:  38%|███▊      | 9800/25880 [2:01:24<3:12:36,  1.39it/s]
1|9801|Loss: 0.9463314414024353:  38%|███▊      | 9801/25880 [2:01:25<3:06:03,  1.44it/s]
1|9802|Loss: 0.8334619998931885:  38%|███▊      | 9801/25880 [2:01:25<3:06:03,  1.44it/s]
1|9802|Loss: 0.8334619998931885:  38%|███▊      | 9802/25880 [2:01:25<3:06:13,  1.44it/s]
1|9803|Loss: 0.919938325881958:  38%|███▊      | 9802/25880 [2:01:26<3:06:13,  1.44it/s] 
1|9803|Loss: 0.919938325881958:  38%|███▊      | 9803/25880 [2:01:26<2:55:13,  1.53it/s]
1|9804|Loss: 0.8968258500099182:  38%|███▊      | 9803/25880 [2:01:26<2:55:13,  1.53it/s]
1|9804|Loss: 0.8968258500099182:  38%|███▊      | 9804/25880 [2:01:26<2:39:54,  1.68it/s]
1|9805|Loss: 0.890713632106781:  38%|███▊      | 9804/25880 [2:01:27<2:39:54,  1.68it/s] 
1|9805|Loss: 0.890713632106781:  38%|███▊      | 9805/25880 [2:01:27<2:47:15,  1.60it/s]
1|9806|Loss: 0.7784833312034607:  38%|███▊      | 9805/25880 [2:01:27<2:47:15,  1.60it/s]
1|9806|Loss: 0.7784833312034607:  38%|███▊      | 9806/25880 [2:01:28<2:56:34,  1.52it/s]
1|9807|Loss: 0.8424699902534485:  38%|███▊      | 9806/25880 [2:01:28<2:56:34,  1.52it/s]
1|9807|Loss: 0.8424699902534485:  38%|███▊      | 9807/25880 [2:01:28<2:50:56,  1.57it/s]
1|9808|Loss: 0.8009200096130371:  38%|███▊      | 9807/25880 [2:01:29<2:50:56,  1.57it/s]
1|9808|Loss: 0.8009200096130371:  38%|███▊      | 9808/25880 [2:01:29<2:55:57,  1.52it/s]
1|9809|Loss: 0.7607400417327881:  38%|███▊      | 9808/25880 [2:01:29<2:55:57,  1.52it/s]
1|9809|Loss: 0.7607400417327881:  38%|███▊      | 9809/25880 [2:01:30<3:02:08,  1.47it/s]
1|9810|Loss: 0.8651541471481323:  38%|███▊      | 9809/25880 [2:01:30<3:02:08,  1.47it/s]
1|9810|Loss: 0.8651541471481323:  38%|███▊      | 9810/25880 [2:01:31<3:09:36,  1.41it/s]
1|9811|Loss: 0.9951605796813965:  38%|███▊      | 9810/25880 [2:01:31<3:09:36,  1.41it/s]
1|9811|Loss: 0.9951605796813965:  38%|███▊      | 9811/25880 [2:01:31<3:19:35,  1.34it/s]
1|9812|Loss: 0.8177099823951721:  38%|███▊      | 9811/25880 [2:01:32<3:19:35,  1.34it/s]
1|9812|Loss: 0.8177099823951721:  38%|███▊      | 9812/25880 [2:01:32<3:20:05,  1.34it/s]
1|9813|Loss: 0.7717427611351013:  38%|███▊      | 9812/25880 [2:01:33<3:20:05,  1.34it/s]
1|9813|Loss: 0.7717427611351013:  38%|███▊      | 9813/25880 [2:01:33<3:08:50,  1.42it/s]
1|9814|Loss: 0.843971848487854:  38%|███▊      | 9813/25880 [2:01:33<3:08:50,  1.42it/s] 
1|9814|Loss: 0.843971848487854:  38%|███▊      | 9814/25880 [2:01:33<3:02:22,  1.47it/s]
1|9815|Loss: 0.7367774844169617:  38%|███▊      | 9814/25880 [2:01:34<3:02:22,  1.47it/s]
1|9815|Loss: 0.7367774844169617:  38%|███▊      | 9815/25880 [2:01:34<3:06:04,  1.44it/s]
1|9816|Loss: 0.8756102323532104:  38%|███▊      | 9815/25880 [2:01:35<3:06:04,  1.44it/s]
1|9816|Loss: 0.8756102323532104:  38%|███▊      | 9816/25880 [2:01:35<2:59:55,  1.49it/s]
1|9817|Loss: 0.9178484082221985:  38%|███▊      | 9816/25880 [2:01:35<2:59:55,  1.49it/s]
1|9817|Loss: 0.9178484082221985:  38%|███▊      | 9817/25880 [2:01:36<3:08:21,  1.42it/s]
1|9818|Loss: 0.8286107778549194:  38%|███▊      | 9817/25880 [2:01:36<3:08:21,  1.42it/s]
1|9818|Loss: 0.8286107778549194:  38%|███▊      | 9818/25880 [2:01:36<3:04:31,  1.45it/s]
1|9819|Loss: 0.7437173128128052:  38%|███▊      | 9818/25880 [2:01:37<3:04:31,  1.45it/s]
1|9819|Loss: 0.7437173128128052:  38%|███▊      | 9819/25880 [2:01:37<3:07:06,  1.43it/s]
1|9820|Loss: 0.7515050768852234:  38%|███▊      | 9819/25880 [2:01:37<3:07:06,  1.43it/s]
1|9820|Loss: 0.7515050768852234:  38%|███▊      | 9820/25880 [2:01:38<3:10:53,  1.40it/s]
1|9821|Loss: 0.7841511964797974:  38%|███▊      | 9820/25880 [2:01:38<3:10:53,  1.40it/s]
1|9821|Loss: 0.7841511964797974:  38%|███▊      | 9821/25880 [2:01:38<3:13:09,  1.39it/s]
1|9822|Loss: 0.8363879323005676:  38%|███▊      | 9821/25880 [2:01:39<3:13:09,  1.39it/s]
1|9822|Loss: 0.8363879323005676:  38%|███▊      | 9822/25880 [2:01:39<3:17:36,  1.35it/s]
1|9823|Loss: 0.7210119366645813:  38%|███▊      | 9822/25880 [2:01:40<3:17:36,  1.35it/s]
1|9823|Loss: 0.7210119366645813:  38%|███▊      | 9823/25880 [2:01:40<3:05:26,  1.44it/s]
1|9824|Loss: 0.7607113718986511:  38%|███▊      | 9823/25880 [2:01:40<3:05:26,  1.44it/s]
1|9824|Loss: 0.7607113718986511:  38%|███▊      | 9824/25880 [2:01:40<2:59:21,  1.49it/s]
1|9825|Loss: 0.8545085787773132:  38%|███▊      | 9824/25880 [2:01:41<2:59:21,  1.49it/s]
1|9825|Loss: 0.8545085787773132:  38%|███▊      | 9825/25880 [2:01:41<3:04:03,  1.45it/s]
1|9826|Loss: 0.7843216061592102:  38%|███▊      | 9825/25880 [2:01:42<3:04:03,  1.45it/s]
1|9826|Loss: 0.7843216061592102:  38%|███▊      | 9826/25880 [2:01:42<3:15:43,  1.37it/s]
1|9827|Loss: 0.8492245674133301:  38%|███▊      | 9826/25880 [2:01:42<3:15:43,  1.37it/s]
1|9827|Loss: 0.8492245674133301:  38%|███▊      | 9827/25880 [2:01:43<3:22:13,  1.32it/s]
1|9828|Loss: 0.8284640312194824:  38%|███▊      | 9827/25880 [2:01:43<3:22:13,  1.32it/s]
1|9828|Loss: 0.8284640312194824:  38%|███▊      | 9828/25880 [2:01:44<3:29:00,  1.28it/s]
1|9829|Loss: 0.855126678943634:  38%|███▊      | 9828/25880 [2:01:44<3:29:00,  1.28it/s] 
1|9829|Loss: 0.855126678943634:  38%|███▊      | 9829/25880 [2:01:44<3:27:40,  1.29it/s]
1|9830|Loss: 0.8280766606330872:  38%|███▊      | 9829/25880 [2:01:45<3:27:40,  1.29it/s]
1|9830|Loss: 0.8280766606330872:  38%|███▊      | 9830/25880 [2:01:45<3:29:53,  1.27it/s]
1|9831|Loss: 0.8410465717315674:  38%|███▊      | 9830/25880 [2:01:46<3:29:53,  1.27it/s]
1|9831|Loss: 0.8410465717315674:  38%|███▊      | 9831/25880 [2:01:46<3:19:55,  1.34it/s]
1|9832|Loss: 0.7794150114059448:  38%|███▊      | 9831/25880 [2:01:46<3:19:55,  1.34it/s]
1|9832|Loss: 0.7794150114059448:  38%|███▊      | 9832/25880 [2:01:47<3:28:24,  1.28it/s]
1|9833|Loss: 0.8600080609321594:  38%|███▊      | 9832/25880 [2:01:47<3:28:24,  1.28it/s]
1|9833|Loss: 0.8600080609321594:  38%|███▊      | 9833/25880 [2:01:47<3:27:04,  1.29it/s]
1|9834|Loss: 0.9317466020584106:  38%|███▊      | 9833/25880 [2:01:48<3:27:04,  1.29it/s]
1|9834|Loss: 0.9317466020584106:  38%|███▊      | 9834/25880 [2:01:48<3:17:41,  1.35it/s]
1|9835|Loss: 0.8229984641075134:  38%|███▊      | 9834/25880 [2:01:48<3:17:41,  1.35it/s]
1|9835|Loss: 0.8229984641075134:  38%|███▊      | 9835/25880 [2:01:49<3:08:30,  1.42it/s]
1|9836|Loss: 0.8264224529266357:  38%|███▊      | 9835/25880 [2:01:49<3:08:30,  1.42it/s]
1|9836|Loss: 0.8264224529266357:  38%|███▊      | 9836/25880 [2:01:49<3:09:29,  1.41it/s]
1|9837|Loss: 0.8573654294013977:  38%|███▊      | 9836/25880 [2:01:50<3:09:29,  1.41it/s]
1|9837|Loss: 0.8573654294013977:  38%|███▊      | 9837/25880 [2:01:50<3:05:50,  1.44it/s]
1|9838|Loss: 0.7973549962043762:  38%|███▊      | 9837/25880 [2:01:50<3:05:50,  1.44it/s]
1|9838|Loss: 0.7973549962043762:  38%|███▊      | 9838/25880 [2:01:51<3:05:43,  1.44it/s]
1|9839|Loss: 0.9995365738868713:  38%|███▊      | 9838/25880 [2:01:51<3:05:43,  1.44it/s]
1|9839|Loss: 0.9995365738868713:  38%|███▊      | 9839/25880 [2:01:51<2:56:34,  1.51it/s]
1|9840|Loss: 0.711387574672699:  38%|███▊      | 9839/25880 [2:01:52<2:56:34,  1.51it/s] 
1|9840|Loss: 0.711387574672699:  38%|███▊      | 9840/25880 [2:01:52<2:51:43,  1.56it/s]
1|9841|Loss: 0.8902103900909424:  38%|███▊      | 9840/25880 [2:01:52<2:51:43,  1.56it/s]
1|9841|Loss: 0.8902103900909424:  38%|███▊      | 9841/25880 [2:01:53<2:58:30,  1.50it/s]
1|9842|Loss: 0.8686200380325317:  38%|███▊      | 9841/25880 [2:01:53<2:58:30,  1.50it/s]
1|9842|Loss: 0.8686200380325317:  38%|███▊      | 9842/25880 [2:01:54<3:11:30,  1.40it/s]
1|9843|Loss: 0.8616874814033508:  38%|███▊      | 9842/25880 [2:01:54<3:11:30,  1.40it/s]
1|9843|Loss: 0.8616874814033508:  38%|███▊      | 9843/25880 [2:01:54<3:12:42,  1.39it/s]
1|9844|Loss: 0.7331090569496155:  38%|███▊      | 9843/25880 [2:01:55<3:12:42,  1.39it/s]
1|9844|Loss: 0.7331090569496155:  38%|███▊      | 9844/25880 [2:01:55<3:13:25,  1.38it/s]
1|9845|Loss: 0.9332860708236694:  38%|███▊      | 9844/25880 [2:01:55<3:13:25,  1.38it/s]
1|9845|Loss: 0.9332860708236694:  38%|███▊      | 9845/25880 [2:01:56<3:17:47,  1.35it/s]
1|9846|Loss: 0.8978154063224792:  38%|███▊      | 9845/25880 [2:01:56<3:17:47,  1.35it/s]
1|9846|Loss: 0.8978154063224792:  38%|███▊      | 9846/25880 [2:01:57<3:29:57,  1.27it/s]
1|9847|Loss: 0.8833414912223816:  38%|███▊      | 9846/25880 [2:01:57<3:29:57,  1.27it/s]
1|9847|Loss: 0.8833414912223816:  38%|███▊      | 9847/25880 [2:01:57<3:22:38,  1.32it/s]
1|9848|Loss: 0.7957282662391663:  38%|███▊      | 9847/25880 [2:01:58<3:22:38,  1.32it/s]
1|9848|Loss: 0.7957282662391663:  38%|███▊      | 9848/25880 [2:01:58<3:12:39,  1.39it/s]
1|9849|Loss: 0.8165216445922852:  38%|███▊      | 9848/25880 [2:01:58<3:12:39,  1.39it/s]
1|9849|Loss: 0.8165216445922852:  38%|███▊      | 9849/25880 [2:01:59<3:12:59,  1.38it/s]
1|9850|Loss: 0.8533625602722168:  38%|███▊      | 9849/25880 [2:01:59<3:12:59,  1.38it/s]
1|9850|Loss: 0.8533625602722168:  38%|███▊      | 9850/25880 [2:01:59<3:08:28,  1.42it/s]
1|9851|Loss: 0.8761513829231262:  38%|███▊      | 9850/25880 [2:02:00<3:08:28,  1.42it/s]
1|9851|Loss: 0.8761513829231262:  38%|███▊      | 9851/25880 [2:02:00<2:59:07,  1.49it/s]
1|9852|Loss: 0.8786515593528748:  38%|███▊      | 9851/25880 [2:02:00<2:59:07,  1.49it/s]
1|9852|Loss: 0.8786515593528748:  38%|███▊      | 9852/25880 [2:02:01<2:59:22,  1.49it/s]
1|9853|Loss: 0.9102434515953064:  38%|███▊      | 9852/25880 [2:02:01<2:59:22,  1.49it/s]
1|9853|Loss: 0.9102434515953064:  38%|███▊      | 9853/25880 [2:02:02<3:13:13,  1.38it/s]
1|9854|Loss: 0.921725869178772:  38%|███▊      | 9853/25880 [2:02:02<3:13:13,  1.38it/s] 
1|9854|Loss: 0.921725869178772:  38%|███▊      | 9854/25880 [2:02:02<3:05:28,  1.44it/s]
1|9855|Loss: 0.9087050557136536:  38%|███▊      | 9854/25880 [2:02:02<3:05:28,  1.44it/s]
1|9855|Loss: 0.9087050557136536:  38%|███▊      | 9855/25880 [2:02:03<2:59:53,  1.48it/s]
1|9856|Loss: 0.885947585105896:  38%|███▊      | 9855/25880 [2:02:03<2:59:53,  1.48it/s] 
1|9856|Loss: 0.885947585105896:  38%|███▊      | 9856/25880 [2:02:04<3:11:45,  1.39it/s]
1|9857|Loss: 1.0002156496047974:  38%|███▊      | 9856/25880 [2:02:04<3:11:45,  1.39it/s]
1|9857|Loss: 1.0002156496047974:  38%|███▊      | 9857/25880 [2:02:04<3:07:52,  1.42it/s]
1|9858|Loss: 0.8028318881988525:  38%|███▊      | 9857/25880 [2:02:05<3:07:52,  1.42it/s]
1|9858|Loss: 0.8028318881988525:  38%|███▊      | 9858/25880 [2:02:05<2:57:22,  1.51it/s]
1|9859|Loss: 0.8933536410331726:  38%|███▊      | 9858/25880 [2:02:05<2:57:22,  1.51it/s]
1|9859|Loss: 0.8933536410331726:  38%|███▊      | 9859/25880 [2:02:05<2:51:31,  1.56it/s]
1|9860|Loss: 0.7953294515609741:  38%|███▊      | 9859/25880 [2:02:06<2:51:31,  1.56it/s]
1|9860|Loss: 0.7953294515609741:  38%|███▊      | 9860/25880 [2:02:06<2:55:55,  1.52it/s]
1|9861|Loss: 0.8867018222808838:  38%|███▊      | 9860/25880 [2:02:06<2:55:55,  1.52it/s]
1|9861|Loss: 0.8867018222808838:  38%|███▊      | 9861/25880 [2:02:07<2:55:47,  1.52it/s]
1|9862|Loss: 0.8253021240234375:  38%|███▊      | 9861/25880 [2:02:07<2:55:47,  1.52it/s]
1|9862|Loss: 0.8253021240234375:  38%|███▊      | 9862/25880 [2:02:07<2:54:27,  1.53it/s]
1|9863|Loss: 0.937279224395752:  38%|███▊      | 9862/25880 [2:02:08<2:54:27,  1.53it/s] 
1|9863|Loss: 0.937279224395752:  38%|███▊      | 9863/25880 [2:02:08<2:53:38,  1.54it/s]
1|9864|Loss: 0.8069179654121399:  38%|███▊      | 9863/25880 [2:02:09<2:53:38,  1.54it/s]
1|9864|Loss: 0.8069179654121399:  38%|███▊      | 9864/25880 [2:02:09<3:19:10,  1.34it/s]
1|9865|Loss: 0.8066784143447876:  38%|███▊      | 9864/25880 [2:02:09<3:19:10,  1.34it/s]
1|9865|Loss: 0.8066784143447876:  38%|███▊      | 9865/25880 [2:02:10<3:24:13,  1.31it/s]
1|9866|Loss: 0.7035404443740845:  38%|███▊      | 9865/25880 [2:02:10<3:24:13,  1.31it/s]
1|9866|Loss: 0.7035404443740845:  38%|███▊      | 9866/25880 [2:02:11<3:37:26,  1.23it/s]
1|9867|Loss: 0.8568435907363892:  38%|███▊      | 9866/25880 [2:02:11<3:37:26,  1.23it/s]
1|9867|Loss: 0.8568435907363892:  38%|███▊      | 9867/25880 [2:02:12<3:32:55,  1.25it/s]
1|9868|Loss: 0.8994566202163696:  38%|███▊      | 9867/25880 [2:02:12<3:32:55,  1.25it/s]
1|9868|Loss: 0.8994566202163696:  38%|███▊      | 9868/25880 [2:02:12<3:27:40,  1.29it/s]
1|9869|Loss: 0.8054850697517395:  38%|███▊      | 9868/25880 [2:02:13<3:27:40,  1.29it/s]
1|9869|Loss: 0.8054850697517395:  38%|███▊      | 9869/25880 [2:02:13<3:25:16,  1.30it/s]
1|9870|Loss: 0.7682898044586182:  38%|███▊      | 9869/25880 [2:02:13<3:25:16,  1.30it/s]
1|9870|Loss: 0.7682898044586182:  38%|███▊      | 9870/25880 [2:02:14<3:23:15,  1.31it/s]
1|9871|Loss: 0.7462480068206787:  38%|███▊      | 9870/25880 [2:02:14<3:23:15,  1.31it/s]
1|9871|Loss: 0.7462480068206787:  38%|███▊      | 9871/25880 [2:02:14<3:03:31,  1.45it/s]
1|9872|Loss: 0.786135196685791:  38%|███▊      | 9871/25880 [2:02:15<3:03:31,  1.45it/s] 
1|9872|Loss: 0.786135196685791:  38%|███▊      | 9872/25880 [2:02:15<3:02:48,  1.46it/s]
1|9873|Loss: 0.7428160905838013:  38%|███▊      | 9872/25880 [2:02:15<3:02:48,  1.46it/s]
1|9873|Loss: 0.7428160905838013:  38%|███▊      | 9873/25880 [2:02:16<3:06:46,  1.43it/s]
1|9874|Loss: 0.874579906463623:  38%|███▊      | 9873/25880 [2:02:16<3:06:46,  1.43it/s] 
1|9874|Loss: 0.874579906463623:  38%|███▊      | 9874/25880 [2:02:16<3:08:45,  1.41it/s]
1|9875|Loss: 0.9207075834274292:  38%|███▊      | 9874/25880 [2:02:17<3:08:45,  1.41it/s]
1|9875|Loss: 0.9207075834274292:  38%|███▊      | 9875/25880 [2:02:17<3:17:40,  1.35it/s]
1|9876|Loss: 0.7165145874023438:  38%|███▊      | 9875/25880 [2:02:18<3:17:40,  1.35it/s]
1|9876|Loss: 0.7165145874023438:  38%|███▊      | 9876/25880 [2:02:18<3:43:41,  1.19it/s]
1|9877|Loss: 0.8398198485374451:  38%|███▊      | 9876/25880 [2:02:19<3:43:41,  1.19it/s]
1|9877|Loss: 0.8398198485374451:  38%|███▊      | 9877/25880 [2:02:19<3:41:01,  1.21it/s]
1|9878|Loss: 0.7402600646018982:  38%|███▊      | 9877/25880 [2:02:19<3:41:01,  1.21it/s]
1|9878|Loss: 0.7402600646018982:  38%|███▊      | 9878/25880 [2:02:20<3:25:17,  1.30it/s]
1|9879|Loss: 0.8651813268661499:  38%|███▊      | 9878/25880 [2:02:20<3:25:17,  1.30it/s]
1|9879|Loss: 0.8651813268661499:  38%|███▊      | 9879/25880 [2:02:20<3:18:55,  1.34it/s]
1|9880|Loss: 0.8567677140235901:  38%|███▊      | 9879/25880 [2:02:21<3:18:55,  1.34it/s]
1|9880|Loss: 0.8567677140235901:  38%|███▊      | 9880/25880 [2:02:21<3:17:39,  1.35it/s]
1|9881|Loss: 0.8142163157463074:  38%|███▊      | 9880/25880 [2:02:22<3:17:39,  1.35it/s]
1|9881|Loss: 0.8142163157463074:  38%|███▊      | 9881/25880 [2:02:22<3:17:10,  1.35it/s]
1|9882|Loss: 0.8098463416099548:  38%|███▊      | 9881/25880 [2:02:22<3:17:10,  1.35it/s]
1|9882|Loss: 0.8098463416099548:  38%|███▊      | 9882/25880 [2:02:23<3:17:02,  1.35it/s]
1|9883|Loss: 0.8173195719718933:  38%|███▊      | 9882/25880 [2:02:23<3:17:02,  1.35it/s]
1|9883|Loss: 0.8173195719718933:  38%|███▊      | 9883/25880 [2:02:23<3:10:38,  1.40it/s]
1|9884|Loss: 0.9214848279953003:  38%|███▊      | 9883/25880 [2:02:24<3:10:38,  1.40it/s]
1|9884|Loss: 0.9214848279953003:  38%|███▊      | 9884/25880 [2:02:24<3:10:32,  1.40it/s]
1|9885|Loss: 0.8180373907089233:  38%|███▊      | 9884/25880 [2:02:24<3:10:32,  1.40it/s]
1|9885|Loss: 0.8180373907089233:  38%|███▊      | 9885/25880 [2:02:25<3:12:29,  1.38it/s]
1|9886|Loss: 0.7717903256416321:  38%|███▊      | 9885/25880 [2:02:25<3:12:29,  1.38it/s]
1|9886|Loss: 0.7717903256416321:  38%|███▊      | 9886/25880 [2:02:25<3:05:06,  1.44it/s]
1|9887|Loss: 0.7290672063827515:  38%|███▊      | 9886/25880 [2:02:26<3:05:06,  1.44it/s]
1|9887|Loss: 0.7290672063827515:  38%|███▊      | 9887/25880 [2:02:26<3:17:15,  1.35it/s]
1|9888|Loss: 0.8194912075996399:  38%|███▊      | 9887/25880 [2:02:27<3:17:15,  1.35it/s]
1|9888|Loss: 0.8194912075996399:  38%|███▊      | 9888/25880 [2:02:27<3:28:54,  1.28it/s]
1|9889|Loss: 0.775992751121521:  38%|███▊      | 9888/25880 [2:02:27<3:28:54,  1.28it/s] 
1|9889|Loss: 0.775992751121521:  38%|███▊      | 9889/25880 [2:02:28<3:15:59,  1.36it/s]
1|9890|Loss: 0.830726146697998:  38%|███▊      | 9889/25880 [2:02:28<3:15:59,  1.36it/s]
1|9890|Loss: 0.830726146697998:  38%|███▊      | 9890/25880 [2:02:29<3:22:09,  1.32it/s]
1|9891|Loss: 0.7609618902206421:  38%|███▊      | 9890/25880 [2:02:29<3:22:09,  1.32it/s]
1|9891|Loss: 0.7609618902206421:  38%|███▊      | 9891/25880 [2:02:29<3:29:07,  1.27it/s]
1|9892|Loss: 0.9269630908966064:  38%|███▊      | 9891/25880 [2:02:30<3:29:07,  1.27it/s]
1|9892|Loss: 0.9269630908966064:  38%|███▊      | 9892/25880 [2:02:30<3:24:22,  1.30it/s]
1|9893|Loss: 0.8222787976264954:  38%|███▊      | 9892/25880 [2:02:30<3:24:22,  1.30it/s]
1|9893|Loss: 0.8222787976264954:  38%|███▊      | 9893/25880 [2:02:31<3:11:06,  1.39it/s]
1|9894|Loss: 0.8298546671867371:  38%|███▊      | 9893/25880 [2:02:31<3:11:06,  1.39it/s]
1|9894|Loss: 0.8298546671867371:  38%|███▊      | 9894/25880 [2:02:31<3:13:19,  1.38it/s]
1|9895|Loss: 0.9548802971839905:  38%|███▊      | 9894/25880 [2:02:32<3:13:19,  1.38it/s]
1|9895|Loss: 0.9548802971839905:  38%|███▊      | 9895/25880 [2:02:32<3:15:22,  1.36it/s]
1|9896|Loss: 0.8217824101448059:  38%|███▊      | 9895/25880 [2:02:33<3:15:22,  1.36it/s]
1|9896|Loss: 0.8217824101448059:  38%|███▊      | 9896/25880 [2:02:33<3:22:18,  1.32it/s]
1|9897|Loss: 0.730759859085083:  38%|███▊      | 9896/25880 [2:02:33<3:22:18,  1.32it/s] 
1|9897|Loss: 0.730759859085083:  38%|███▊      | 9897/25880 [2:02:34<3:27:23,  1.28it/s]
1|9898|Loss: 0.7985302209854126:  38%|███▊      | 9897/25880 [2:02:34<3:27:23,  1.28it/s]
1|9898|Loss: 0.7985302209854126:  38%|███▊      | 9898/25880 [2:02:35<3:29:32,  1.27it/s]
1|9899|Loss: 0.8105682730674744:  38%|███▊      | 9898/25880 [2:02:35<3:29:32,  1.27it/s]
1|9899|Loss: 0.8105682730674744:  38%|███▊      | 9899/25880 [2:02:35<3:26:24,  1.29it/s]
1|9900|Loss: 0.9967426061630249:  38%|███▊      | 9899/25880 [2:02:36<3:26:24,  1.29it/s]
1|9900|Loss: 0.9967426061630249:  38%|███▊      | 9900/25880 [2:02:36<3:27:45,  1.28it/s]
1|9901|Loss: 0.8762266635894775:  38%|███▊      | 9900/25880 [2:02:37<3:27:45,  1.28it/s]
1|9901|Loss: 0.8762266635894775:  38%|███▊      | 9901/25880 [2:02:37<3:32:33,  1.25it/s]
1|9902|Loss: 0.9898066520690918:  38%|███▊      | 9901/25880 [2:02:38<3:32:33,  1.25it/s]
1|9902|Loss: 0.9898066520690918:  38%|███▊      | 9902/25880 [2:02:38<3:41:11,  1.20it/s]
1|9903|Loss: 0.7621678709983826:  38%|███▊      | 9902/25880 [2:02:38<3:41:11,  1.20it/s]
1|9903|Loss: 0.7621678709983826:  38%|███▊      | 9903/25880 [2:02:39<3:39:43,  1.21it/s]
1|9904|Loss: 0.9678112268447876:  38%|███▊      | 9903/25880 [2:02:39<3:39:43,  1.21it/s]
1|9904|Loss: 0.9678112268447876:  38%|███▊      | 9904/25880 [2:02:40<3:34:37,  1.24it/s]
1|9905|Loss: 0.9091712236404419:  38%|███▊      | 9904/25880 [2:02:40<3:34:37,  1.24it/s]
1|9905|Loss: 0.9091712236404419:  38%|███▊      | 9905/25880 [2:02:40<3:41:19,  1.20it/s]
1|9906|Loss: 0.771051824092865:  38%|███▊      | 9905/25880 [2:02:41<3:41:19,  1.20it/s] 
1|9906|Loss: 0.771051824092865:  38%|███▊      | 9906/25880 [2:02:41<3:28:34,  1.28it/s]
1|9907|Loss: 0.8604782819747925:  38%|███▊      | 9906/25880 [2:02:41<3:28:34,  1.28it/s]
1|9907|Loss: 0.8604782819747925:  38%|███▊      | 9907/25880 [2:02:42<3:28:43,  1.28it/s]
1|9908|Loss: 0.97049480676651:  38%|███▊      | 9907/25880 [2:02:42<3:28:43,  1.28it/s]  
1|9908|Loss: 0.97049480676651:  38%|███▊      | 9908/25880 [2:02:42<3:08:14,  1.41it/s]
1|9909|Loss: 0.8942493796348572:  38%|███▊      | 9908/25880 [2:02:43<3:08:14,  1.41it/s]
1|9909|Loss: 0.8942493796348572:  38%|███▊      | 9909/25880 [2:02:43<2:58:45,  1.49it/s]
1|9910|Loss: 0.777168869972229:  38%|███▊      | 9909/25880 [2:02:43<2:58:45,  1.49it/s] 
1|9910|Loss: 0.777168869972229:  38%|███▊      | 9910/25880 [2:02:44<3:02:28,  1.46it/s]
1|9911|Loss: 0.9858267307281494:  38%|███▊      | 9910/25880 [2:02:44<3:02:28,  1.46it/s]
1|9911|Loss: 0.9858267307281494:  38%|███▊      | 9911/25880 [2:02:45<3:15:46,  1.36it/s]
1|9912|Loss: 0.779180109500885:  38%|███▊      | 9911/25880 [2:02:45<3:15:46,  1.36it/s] 
1|9912|Loss: 0.779180109500885:  38%|███▊      | 9912/25880 [2:02:45<3:25:52,  1.29it/s]
1|9913|Loss: 0.8524543642997742:  38%|███▊      | 9912/25880 [2:02:46<3:25:52,  1.29it/s]
1|9913|Loss: 0.8524543642997742:  38%|███▊      | 9913/25880 [2:02:46<3:31:37,  1.26it/s]
1|9914|Loss: 0.916994035243988:  38%|███▊      | 9913/25880 [2:02:47<3:31:37,  1.26it/s] 
1|9914|Loss: 0.916994035243988:  38%|███▊      | 9914/25880 [2:02:47<3:37:54,  1.22it/s]
1|9915|Loss: 0.8370859622955322:  38%|███▊      | 9914/25880 [2:02:47<3:37:54,  1.22it/s]
1|9915|Loss: 0.8370859622955322:  38%|███▊      | 9915/25880 [2:02:48<3:16:12,  1.36it/s]
1|9916|Loss: 0.8356216549873352:  38%|███▊      | 9915/25880 [2:02:48<3:16:12,  1.36it/s]
1|9916|Loss: 0.8356216549873352:  38%|███▊      | 9916/25880 [2:02:48<3:09:21,  1.41it/s]
1|9917|Loss: 0.9746987819671631:  38%|███▊      | 9916/25880 [2:02:49<3:09:21,  1.41it/s]
1|9917|Loss: 0.9746987819671631:  38%|███▊      | 9917/25880 [2:02:49<2:56:17,  1.51it/s]
1|9918|Loss: 0.9498112797737122:  38%|███▊      | 9917/25880 [2:02:49<2:56:17,  1.51it/s]
1|9918|Loss: 0.9498112797737122:  38%|███▊      | 9918/25880 [2:02:50<3:02:43,  1.46it/s]
1|9919|Loss: 1.0099537372589111:  38%|███▊      | 9918/25880 [2:02:50<3:02:43,  1.46it/s]
1|9919|Loss: 1.0099537372589111:  38%|███▊      | 9919/25880 [2:02:50<3:14:52,  1.37it/s]
1|9920|Loss: 0.8713895678520203:  38%|███▊      | 9919/25880 [2:02:51<3:14:52,  1.37it/s]
1|9920|Loss: 0.8713895678520203:  38%|███▊      | 9920/25880 [2:02:51<3:14:59,  1.36it/s]
1|9921|Loss: 0.9243158102035522:  38%|███▊      | 9920/25880 [2:02:52<3:14:59,  1.36it/s]
1|9921|Loss: 0.9243158102035522:  38%|███▊      | 9921/25880 [2:02:52<3:08:27,  1.41it/s]
1|9922|Loss: 0.8942248225212097:  38%|███▊      | 9921/25880 [2:02:52<3:08:27,  1.41it/s]
1|9922|Loss: 0.8942248225212097:  38%|███▊      | 9922/25880 [2:02:52<2:53:46,  1.53it/s]
1|9923|Loss: 0.8302053809165955:  38%|███▊      | 9922/25880 [2:02:53<2:53:46,  1.53it/s]
1|9923|Loss: 0.8302053809165955:  38%|███▊      | 9923/25880 [2:02:53<2:50:17,  1.56it/s]
1|9924|Loss: 0.7485777735710144:  38%|███▊      | 9923/25880 [2:02:53<2:50:17,  1.56it/s]
1|9924|Loss: 0.7485777735710144:  38%|███▊      | 9924/25880 [2:02:54<3:11:33,  1.39it/s]
1|9925|Loss: 0.9353777766227722:  38%|███▊      | 9924/25880 [2:02:54<3:11:33,  1.39it/s]
1|9925|Loss: 0.9353777766227722:  38%|███▊      | 9925/25880 [2:02:55<3:14:04,  1.37it/s]
1|9926|Loss: 0.8191231489181519:  38%|███▊      | 9925/25880 [2:02:55<3:14:04,  1.37it/s]
1|9926|Loss: 0.8191231489181519:  38%|███▊      | 9926/25880 [2:02:55<3:06:17,  1.43it/s]
1|9927|Loss: 0.9042255282402039:  38%|███▊      | 9926/25880 [2:02:56<3:06:17,  1.43it/s]
1|9927|Loss: 0.9042255282402039:  38%|███▊      | 9927/25880 [2:02:56<3:11:21,  1.39it/s]
1|9928|Loss: 0.8386212587356567:  38%|███▊      | 9927/25880 [2:02:56<3:11:21,  1.39it/s]
1|9928|Loss: 0.8386212587356567:  38%|███▊      | 9928/25880 [2:02:57<3:03:51,  1.45it/s]
1|9929|Loss: 0.7826192378997803:  38%|███▊      | 9928/25880 [2:02:57<3:03:51,  1.45it/s]
1|9929|Loss: 0.7826192378997803:  38%|███▊      | 9929/25880 [2:02:57<2:58:54,  1.49it/s]
1|9930|Loss: 0.8968164920806885:  38%|███▊      | 9929/25880 [2:02:58<2:58:54,  1.49it/s]
1|9930|Loss: 0.8968164920806885:  38%|███▊      | 9930/25880 [2:02:58<3:16:59,  1.35it/s]
1|9931|Loss: 0.7552378177642822:  38%|███▊      | 9930/25880 [2:02:59<3:16:59,  1.35it/s]
1|9931|Loss: 0.7552378177642822:  38%|███▊      | 9931/25880 [2:02:59<3:19:54,  1.33it/s]
1|9932|Loss: 0.8572102189064026:  38%|███▊      | 9931/25880 [2:02:59<3:19:54,  1.33it/s]
1|9932|Loss: 0.8572102189064026:  38%|███▊      | 9932/25880 [2:03:00<3:18:28,  1.34it/s]
1|9933|Loss: 0.8980956673622131:  38%|███▊      | 9932/25880 [2:03:00<3:18:28,  1.34it/s]
1|9933|Loss: 0.8980956673622131:  38%|███▊      | 9933/25880 [2:03:00<3:09:42,  1.40it/s]
1|9934|Loss: 0.8229572772979736:  38%|███▊      | 9933/25880 [2:03:01<3:09:42,  1.40it/s]
1|9934|Loss: 0.8229572772979736:  38%|███▊      | 9934/25880 [2:03:01<3:01:50,  1.46it/s]
1|9935|Loss: 0.9409888982772827:  38%|███▊      | 9934/25880 [2:03:01<3:01:50,  1.46it/s]
1|9935|Loss: 0.9409888982772827:  38%|███▊      | 9935/25880 [2:03:02<3:04:26,  1.44it/s]
1|9936|Loss: 0.9330492615699768:  38%|███▊      | 9935/25880 [2:03:02<3:04:26,  1.44it/s]
1|9936|Loss: 0.9330492615699768:  38%|███▊      | 9936/25880 [2:03:02<3:06:07,  1.43it/s]
1|9937|Loss: 0.8791942596435547:  38%|███▊      | 9936/25880 [2:03:03<3:06:07,  1.43it/s]
1|9937|Loss: 0.8791942596435547:  38%|███▊      | 9937/25880 [2:03:03<3:01:14,  1.47it/s]
1|9938|Loss: 0.8410740494728088:  38%|███▊      | 9937/25880 [2:03:03<3:01:14,  1.47it/s]
1|9938|Loss: 0.8410740494728088:  38%|███▊      | 9938/25880 [2:03:04<2:56:00,  1.51it/s]
1|9939|Loss: 0.8074694871902466:  38%|███▊      | 9938/25880 [2:03:04<2:56:00,  1.51it/s]
1|9939|Loss: 0.8074694871902466:  38%|███▊      | 9939/25880 [2:03:04<2:59:52,  1.48it/s]
1|9940|Loss: 0.8972679972648621:  38%|███▊      | 9939/25880 [2:03:05<2:59:52,  1.48it/s]
1|9940|Loss: 0.8972679972648621:  38%|███▊      | 9940/25880 [2:03:05<3:10:12,  1.40it/s]
1|9941|Loss: 0.7893978357315063:  38%|███▊      | 9940/25880 [2:03:06<3:10:12,  1.40it/s]
1|9941|Loss: 0.7893978357315063:  38%|███▊      | 9941/25880 [2:03:06<2:57:14,  1.50it/s]
1|9942|Loss: 0.7575848698616028:  38%|███▊      | 9941/25880 [2:03:06<2:57:14,  1.50it/s]
1|9942|Loss: 0.7575848698616028:  38%|███▊      | 9942/25880 [2:03:06<2:52:04,  1.54it/s]
1|9943|Loss: 0.9213511347770691:  38%|███▊      | 9942/25880 [2:03:07<2:52:04,  1.54it/s]
1|9943|Loss: 0.9213511347770691:  38%|███▊      | 9943/25880 [2:03:07<3:00:40,  1.47it/s]
1|9944|Loss: 0.8116682767868042:  38%|███▊      | 9943/25880 [2:03:07<3:00:40,  1.47it/s]
1|9944|Loss: 0.8116682767868042:  38%|███▊      | 9944/25880 [2:03:08<3:06:28,  1.42it/s]
1|9945|Loss: 0.8997460603713989:  38%|███▊      | 9944/25880 [2:03:08<3:06:28,  1.42it/s]
1|9945|Loss: 0.8997460603713989:  38%|███▊      | 9945/25880 [2:03:09<3:10:29,  1.39it/s]
1|9946|Loss: 0.885936975479126:  38%|███▊      | 9945/25880 [2:03:09<3:10:29,  1.39it/s] 
1|9946|Loss: 0.885936975479126:  38%|███▊      | 9946/25880 [2:03:09<3:05:16,  1.43it/s]
1|9947|Loss: 0.9032863974571228:  38%|███▊      | 9946/25880 [2:03:10<3:05:16,  1.43it/s]
1|9947|Loss: 0.9032863974571228:  38%|███▊      | 9947/25880 [2:03:10<2:58:44,  1.49it/s]
1|9948|Loss: 0.7840986847877502:  38%|███▊      | 9947/25880 [2:03:10<2:58:44,  1.49it/s]
1|9948|Loss: 0.7840986847877502:  38%|███▊      | 9948/25880 [2:03:11<3:17:44,  1.34it/s]
1|9949|Loss: 0.7430283427238464:  38%|███▊      | 9948/25880 [2:03:11<3:17:44,  1.34it/s]
1|9949|Loss: 0.7430283427238464:  38%|███▊      | 9949/25880 [2:03:12<3:20:00,  1.33it/s]
1|9950|Loss: 0.8858782052993774:  38%|███▊      | 9949/25880 [2:03:12<3:20:00,  1.33it/s]
1|9950|Loss: 0.8858782052993774:  38%|███▊      | 9950/25880 [2:03:12<3:18:07,  1.34it/s]
1|9951|Loss: 0.7333647012710571:  38%|███▊      | 9950/25880 [2:03:13<3:18:07,  1.34it/s]
1|9951|Loss: 0.7333647012710571:  38%|███▊      | 9951/25880 [2:03:13<3:33:40,  1.24it/s]
1|9952|Loss: 0.9985812902450562:  38%|███▊      | 9951/25880 [2:03:14<3:33:40,  1.24it/s]
1|9952|Loss: 0.9985812902450562:  38%|███▊      | 9952/25880 [2:03:14<3:23:10,  1.31it/s]
1|9953|Loss: 0.8905817270278931:  38%|███▊      | 9952/25880 [2:03:14<3:23:10,  1.31it/s]
1|9953|Loss: 0.8905817270278931:  38%|███▊      | 9953/25880 [2:03:14<3:00:10,  1.47it/s]
1|9954|Loss: 0.8070188760757446:  38%|███▊      | 9953/25880 [2:03:15<3:00:10,  1.47it/s]
1|9954|Loss: 0.8070188760757446:  38%|███▊      | 9954/25880 [2:03:15<3:04:07,  1.44it/s]
1|9955|Loss: 0.8780245780944824:  38%|███▊      | 9954/25880 [2:03:15<3:04:07,  1.44it/s]
1|9955|Loss: 0.8780245780944824:  38%|███▊      | 9955/25880 [2:03:16<3:07:54,  1.41it/s]
1|9956|Loss: 0.8549841642379761:  38%|███▊      | 9955/25880 [2:03:16<3:07:54,  1.41it/s]
1|9956|Loss: 0.8549841642379761:  38%|███▊      | 9956/25880 [2:03:17<3:09:42,  1.40it/s]
1|9957|Loss: 0.8565335273742676:  38%|███▊      | 9956/25880 [2:03:17<3:09:42,  1.40it/s]
1|9957|Loss: 0.8565335273742676:  38%|███▊      | 9957/25880 [2:03:17<3:14:17,  1.37it/s]
1|9958|Loss: 0.8383259773254395:  38%|███▊      | 9957/25880 [2:03:18<3:14:17,  1.37it/s]
1|9958|Loss: 0.8383259773254395:  38%|███▊      | 9958/25880 [2:03:18<3:06:32,  1.42it/s]
1|9959|Loss: 0.846549391746521:  38%|███▊      | 9958/25880 [2:03:18<3:06:32,  1.42it/s] 
1|9959|Loss: 0.846549391746521:  38%|███▊      | 9959/25880 [2:03:19<3:12:08,  1.38it/s]
1|9960|Loss: 0.7439775466918945:  38%|███▊      | 9959/25880 [2:03:19<3:12:08,  1.38it/s]
1|9960|Loss: 0.7439775466918945:  38%|███▊      | 9960/25880 [2:03:19<3:13:46,  1.37it/s]
1|9961|Loss: 0.9340186715126038:  38%|███▊      | 9960/25880 [2:03:20<3:13:46,  1.37it/s]
1|9961|Loss: 0.9340186715126038:  38%|███▊      | 9961/25880 [2:03:20<3:04:08,  1.44it/s]
1|9962|Loss: 1.0358221530914307:  38%|███▊      | 9961/25880 [2:03:20<3:04:08,  1.44it/s]
1|9962|Loss: 1.0358221530914307:  38%|███▊      | 9962/25880 [2:03:21<3:06:12,  1.42it/s]
1|9963|Loss: 0.716519296169281:  38%|███▊      | 9962/25880 [2:03:21<3:06:12,  1.42it/s] 
1|9963|Loss: 0.716519296169281:  38%|███▊      | 9963/25880 [2:03:22<3:09:59,  1.40it/s]
1|9964|Loss: 0.8895528316497803:  38%|███▊      | 9963/25880 [2:03:22<3:09:59,  1.40it/s]
1|9964|Loss: 0.8895528316497803:  39%|███▊      | 9964/25880 [2:03:22<3:04:24,  1.44it/s]
1|9965|Loss: 0.7686237096786499:  39%|███▊      | 9964/25880 [2:03:23<3:04:24,  1.44it/s]
1|9965|Loss: 0.7686237096786499:  39%|███▊      | 9965/25880 [2:03:23<3:06:47,  1.42it/s]
1|9966|Loss: 0.8644317388534546:  39%|███▊      | 9965/25880 [2:03:23<3:06:47,  1.42it/s]
1|9966|Loss: 0.8644317388534546:  39%|███▊      | 9966/25880 [2:03:24<3:02:22,  1.45it/s]
1|9967|Loss: 0.7924292087554932:  39%|███▊      | 9966/25880 [2:03:24<3:02:22,  1.45it/s]
1|9967|Loss: 0.7924292087554932:  39%|███▊      | 9967/25880 [2:03:24<3:03:57,  1.44it/s]
1|9968|Loss: 0.8810038566589355:  39%|███▊      | 9967/25880 [2:03:25<3:03:57,  1.44it/s]
1|9968|Loss: 0.8810038566589355:  39%|███▊      | 9968/25880 [2:03:25<3:11:33,  1.38it/s]
1|9969|Loss: 0.8978639841079712:  39%|███▊      | 9968/25880 [2:03:25<3:11:33,  1.38it/s]
1|9969|Loss: 0.8978639841079712:  39%|███▊      | 9969/25880 [2:03:26<3:06:21,  1.42it/s]
1|9970|Loss: 0.9327649474143982:  39%|███▊      | 9969/25880 [2:03:26<3:06:21,  1.42it/s]
1|9970|Loss: 0.9327649474143982:  39%|███▊      | 9970/25880 [2:03:26<3:06:31,  1.42it/s]
1|9971|Loss: 0.7852258086204529:  39%|███▊      | 9970/25880 [2:03:27<3:06:31,  1.42it/s]
1|9971|Loss: 0.7852258086204529:  39%|███▊      | 9971/25880 [2:03:27<3:15:59,  1.35it/s]
1|9972|Loss: 0.7528307437896729:  39%|███▊      | 9971/25880 [2:03:28<3:15:59,  1.35it/s]
1|9972|Loss: 0.7528307437896729:  39%|███▊      | 9972/25880 [2:03:28<3:08:36,  1.41it/s]
1|9973|Loss: 0.9369354844093323:  39%|███▊      | 9972/25880 [2:03:28<3:08:36,  1.41it/s]
1|9973|Loss: 0.9369354844093323:  39%|███▊      | 9973/25880 [2:03:29<3:07:43,  1.41it/s]
1|9974|Loss: 0.9118991494178772:  39%|███▊      | 9973/25880 [2:03:29<3:07:43,  1.41it/s]
1|9974|Loss: 0.9118991494178772:  39%|███▊      | 9974/25880 [2:03:29<3:01:53,  1.46it/s]
1|9975|Loss: 0.845324695110321:  39%|███▊      | 9974/25880 [2:03:30<3:01:53,  1.46it/s] 
1|9975|Loss: 0.845324695110321:  39%|███▊      | 9975/25880 [2:03:30<2:48:03,  1.58it/s]
1|9976|Loss: 0.7772590517997742:  39%|███▊      | 9975/25880 [2:03:30<2:48:03,  1.58it/s]
1|9976|Loss: 0.7772590517997742:  39%|███▊      | 9976/25880 [2:03:30<2:56:49,  1.50it/s]
1|9977|Loss: 0.7693780660629272:  39%|███▊      | 9976/25880 [2:03:31<2:56:49,  1.50it/s]
1|9977|Loss: 0.7693780660629272:  39%|███▊      | 9977/25880 [2:03:31<2:51:51,  1.54it/s]
1|9978|Loss: 0.8311726450920105:  39%|███▊      | 9977/25880 [2:03:31<2:51:51,  1.54it/s]
1|9978|Loss: 0.8311726450920105:  39%|███▊      | 9978/25880 [2:03:32<2:42:33,  1.63it/s]
1|9979|Loss: 0.8674333691596985:  39%|███▊      | 9978/25880 [2:03:32<2:42:33,  1.63it/s]
1|9979|Loss: 0.8674333691596985:  39%|███▊      | 9979/25880 [2:03:32<2:32:47,  1.73it/s]
1|9980|Loss: 0.8248194456100464:  39%|███▊      | 9979/25880 [2:03:32<2:32:47,  1.73it/s]
1|9980|Loss: 0.8248194456100464:  39%|███▊      | 9980/25880 [2:03:33<2:40:49,  1.65it/s]
1|9981|Loss: 0.8516327142715454:  39%|███▊      | 9980/25880 [2:03:33<2:40:49,  1.65it/s]
1|9981|Loss: 0.8516327142715454:  39%|███▊      | 9981/25880 [2:03:34<2:55:41,  1.51it/s]
1|9982|Loss: 0.875717043876648:  39%|███▊      | 9981/25880 [2:03:34<2:55:41,  1.51it/s] 
1|9982|Loss: 0.875717043876648:  39%|███▊      | 9982/25880 [2:03:34<2:52:55,  1.53it/s]
1|9983|Loss: 0.5967164635658264:  39%|███▊      | 9982/25880 [2:03:35<2:52:55,  1.53it/s]
1|9983|Loss: 0.5967164635658264:  39%|███▊      | 9983/25880 [2:03:35<3:13:45,  1.37it/s]
1|9984|Loss: 0.810481071472168:  39%|███▊      | 9983/25880 [2:03:36<3:13:45,  1.37it/s] 
1|9984|Loss: 0.810481071472168:  39%|███▊      | 9984/25880 [2:03:36<3:01:31,  1.46it/s]
1|9985|Loss: 0.8031339049339294:  39%|███▊      | 9984/25880 [2:03:36<3:01:31,  1.46it/s]
1|9985|Loss: 0.8031339049339294:  39%|███▊      | 9985/25880 [2:03:36<2:54:50,  1.52it/s]
1|9986|Loss: 0.8267956972122192:  39%|███▊      | 9985/25880 [2:03:37<2:54:50,  1.52it/s]
1|9986|Loss: 0.8267956972122192:  39%|███▊      | 9986/25880 [2:03:37<2:53:46,  1.52it/s]
1|9987|Loss: 0.7195490002632141:  39%|███▊      | 9986/25880 [2:03:37<2:53:46,  1.52it/s]
1|9987|Loss: 0.7195490002632141:  39%|███▊      | 9987/25880 [2:03:38<3:02:52,  1.45it/s]
1|9988|Loss: 0.7815865278244019:  39%|███▊      | 9987/25880 [2:03:38<3:02:52,  1.45it/s]
1|9988|Loss: 0.7815865278244019:  39%|███▊      | 9988/25880 [2:03:38<3:05:00,  1.43it/s]
1|9989|Loss: 0.7709720730781555:  39%|███▊      | 9988/25880 [2:03:39<3:05:00,  1.43it/s]
1|9989|Loss: 0.7709720730781555:  39%|███▊      | 9989/25880 [2:03:39<3:04:37,  1.43it/s]
1|9990|Loss: 1.0323771238327026:  39%|███▊      | 9989/25880 [2:03:40<3:04:37,  1.43it/s]
1|9990|Loss: 1.0323771238327026:  39%|███▊      | 9990/25880 [2:03:40<3:04:49,  1.43it/s]
1|9991|Loss: 0.8341432809829712:  39%|███▊      | 9990/25880 [2:03:40<3:04:49,  1.43it/s]
1|9991|Loss: 0.8341432809829712:  39%|███▊      | 9991/25880 [2:03:40<2:59:37,  1.47it/s]
1|9992|Loss: 0.9001239538192749:  39%|███▊      | 9991/25880 [2:03:41<2:59:37,  1.47it/s]
1|9992|Loss: 0.9001239538192749:  39%|███▊      | 9992/25880 [2:03:41<3:02:11,  1.45it/s]
1|9993|Loss: 0.7942156195640564:  39%|███▊      | 9992/25880 [2:03:42<3:02:11,  1.45it/s]
1|9993|Loss: 0.7942156195640564:  39%|███▊      | 9993/25880 [2:03:42<3:13:16,  1.37it/s]
1|9994|Loss: 0.8206319212913513:  39%|███▊      | 9993/25880 [2:03:42<3:13:16,  1.37it/s]
1|9994|Loss: 0.8206319212913513:  39%|███▊      | 9994/25880 [2:03:43<3:23:15,  1.30it/s]
1|9995|Loss: 0.8951629400253296:  39%|███▊      | 9994/25880 [2:03:43<3:23:15,  1.30it/s]
1|9995|Loss: 0.8951629400253296:  39%|███▊      | 9995/25880 [2:03:44<3:22:27,  1.31it/s]
1|9996|Loss: 0.7289646863937378:  39%|███▊      | 9995/25880 [2:03:44<3:22:27,  1.31it/s]
1|9996|Loss: 0.7289646863937378:  39%|███▊      | 9996/25880 [2:03:44<3:19:58,  1.32it/s]
1|9997|Loss: 0.841257631778717:  39%|███▊      | 9996/25880 [2:03:45<3:19:58,  1.32it/s] 
1|9997|Loss: 0.841257631778717:  39%|███▊      | 9997/25880 [2:03:45<3:12:59,  1.37it/s]
1|9998|Loss: 0.7580890655517578:  39%|███▊      | 9997/25880 [2:03:45<3:12:59,  1.37it/s]
1|9998|Loss: 0.7580890655517578:  39%|███▊      | 9998/25880 [2:03:46<3:04:42,  1.43it/s]
1|9999|Loss: 0.8830154538154602:  39%|███▊      | 9998/25880 [2:03:46<3:04:42,  1.43it/s]
1|9999|Loss: 0.8830154538154602:  39%|███▊      | 9999/25880 [2:03:46<3:09:58,  1.39it/s]
1|10000|Loss: 0.9391780495643616:  39%|███▊      | 9999/25880 [2:03:47<3:09:58,  1.39it/s]
1|10000|Loss: 0.9391780495643616:  39%|███▊      | 10000/25880 [2:03:47<3:12:15,  1.38it/s]
1|10001|Loss: 1.112973690032959:  39%|███▊      | 10000/25880 [2:03:48<3:12:15,  1.38it/s] 
1|10001|Loss: 1.112973690032959:  39%|███▊      | 10001/25880 [2:03:48<3:13:17,  1.37it/s]
1|10002|Loss: 0.8358180522918701:  39%|███▊      | 10001/25880 [2:03:48<3:13:17,  1.37it/s]
1|10002|Loss: 0.8358180522918701:  39%|███▊      | 10002/25880 [2:03:49<3:13:41,  1.37it/s]
1|10003|Loss: 0.8324723243713379:  39%|███▊      | 10002/25880 [2:03:49<3:13:41,  1.37it/s]
1|10003|Loss: 0.8324723243713379:  39%|███▊      | 10003/25880 [2:03:49<3:13:47,  1.37it/s]
1|10004|Loss: 0.8193178176879883:  39%|███▊      | 10003/25880 [2:03:50<3:13:47,  1.37it/s]
1|10004|Loss: 0.8193178176879883:  39%|███▊      | 10004/25880 [2:03:50<3:03:49,  1.44it/s]
1|10005|Loss: 0.8450919389724731:  39%|███▊      | 10004/25880 [2:03:50<3:03:49,  1.44it/s]
1|10005|Loss: 0.8450919389724731:  39%|███▊      | 10005/25880 [2:03:51<3:13:31,  1.37it/s]
1|10006|Loss: 0.8960445523262024:  39%|███▊      | 10005/25880 [2:03:51<3:13:31,  1.37it/s]
1|10006|Loss: 0.8960445523262024:  39%|███▊      | 10006/25880 [2:03:51<3:06:50,  1.42it/s]
1|10007|Loss: 0.8768527507781982:  39%|███▊      | 10006/25880 [2:03:52<3:06:50,  1.42it/s]
1|10007|Loss: 0.8768527507781982:  39%|███▊      | 10007/25880 [2:03:52<2:53:33,  1.52it/s]
1|10008|Loss: 0.8144075274467468:  39%|███▊      | 10007/25880 [2:03:52<2:53:33,  1.52it/s]
1|10008|Loss: 0.8144075274467468:  39%|███▊      | 10008/25880 [2:03:53<3:01:07,  1.46it/s]
1|10009|Loss: 0.7955757975578308:  39%|███▊      | 10008/25880 [2:03:53<3:01:07,  1.46it/s]
1|10009|Loss: 0.7955757975578308:  39%|███▊      | 10009/25880 [2:03:53<3:00:19,  1.47it/s]
1|10010|Loss: 0.8536522388458252:  39%|███▊      | 10009/25880 [2:03:54<3:00:19,  1.47it/s]
1|10010|Loss: 0.8536522388458252:  39%|███▊      | 10010/25880 [2:03:54<2:56:57,  1.49it/s]
1|10011|Loss: 0.9462222456932068:  39%|███▊      | 10010/25880 [2:03:54<2:56:57,  1.49it/s]
1|10011|Loss: 0.9462222456932068:  39%|███▊      | 10011/25880 [2:03:55<2:49:17,  1.56it/s]
1|10012|Loss: 0.8853821754455566:  39%|███▊      | 10011/25880 [2:03:55<2:49:17,  1.56it/s]
1|10012|Loss: 0.8853821754455566:  39%|███▊      | 10012/25880 [2:03:55<2:53:32,  1.52it/s]
1|10013|Loss: 0.8246849775314331:  39%|███▊      | 10012/25880 [2:03:56<2:53:32,  1.52it/s]
1|10013|Loss: 0.8246849775314331:  39%|███▊      | 10013/25880 [2:03:56<3:00:32,  1.46it/s]
1|10014|Loss: 0.7898730039596558:  39%|███▊      | 10013/25880 [2:03:56<3:00:32,  1.46it/s]
1|10014|Loss: 0.7898730039596558:  39%|███▊      | 10014/25880 [2:03:57<3:05:43,  1.42it/s]
1|10015|Loss: 0.781610369682312:  39%|███▊      | 10014/25880 [2:03:57<3:05:43,  1.42it/s] 
1|10015|Loss: 0.781610369682312:  39%|███▊      | 10015/25880 [2:03:57<2:57:03,  1.49it/s]
1|10016|Loss: 0.8316182494163513:  39%|███▊      | 10015/25880 [2:03:58<2:57:03,  1.49it/s]
1|10016|Loss: 0.8316182494163513:  39%|███▊      | 10016/25880 [2:03:58<2:52:57,  1.53it/s]
1|10017|Loss: 0.8159071803092957:  39%|███▊      | 10016/25880 [2:03:58<2:52:57,  1.53it/s]
1|10017|Loss: 0.8159071803092957:  39%|███▊      | 10017/25880 [2:03:59<2:55:56,  1.50it/s]
1|10018|Loss: 0.7556354999542236:  39%|███▊      | 10017/25880 [2:03:59<2:55:56,  1.50it/s]
1|10018|Loss: 0.7556354999542236:  39%|███▊      | 10018/25880 [2:03:59<2:48:54,  1.57it/s]
1|10019|Loss: 0.7967562675476074:  39%|███▊      | 10018/25880 [2:04:00<2:48:54,  1.57it/s]
1|10019|Loss: 0.7967562675476074:  39%|███▊      | 10019/25880 [2:04:00<2:51:51,  1.54it/s]
1|10020|Loss: 0.7823861837387085:  39%|███▊      | 10019/25880 [2:04:00<2:51:51,  1.54it/s]
1|10020|Loss: 0.7823861837387085:  39%|███▊      | 10020/25880 [2:04:01<3:01:38,  1.46it/s]
1|10021|Loss: 0.7075203061103821:  39%|███▊      | 10020/25880 [2:04:01<3:01:38,  1.46it/s]
1|10021|Loss: 0.7075203061103821:  39%|███▊      | 10021/25880 [2:04:02<3:09:41,  1.39it/s]
1|10022|Loss: 0.9406853914260864:  39%|███▊      | 10021/25880 [2:04:02<3:09:41,  1.39it/s]
1|10022|Loss: 0.9406853914260864:  39%|███▊      | 10022/25880 [2:04:02<3:11:41,  1.38it/s]
1|10023|Loss: 0.9339790344238281:  39%|███▊      | 10022/25880 [2:04:03<3:11:41,  1.38it/s]
1|10023|Loss: 0.9339790344238281:  39%|███▊      | 10023/25880 [2:04:03<3:09:53,  1.39it/s]
1|10024|Loss: 0.9216439723968506:  39%|███▊      | 10023/25880 [2:04:03<3:09:53,  1.39it/s]
1|10024|Loss: 0.9216439723968506:  39%|███▊      | 10024/25880 [2:04:04<3:02:45,  1.45it/s]
1|10025|Loss: 0.7736523747444153:  39%|███▊      | 10024/25880 [2:04:04<3:02:45,  1.45it/s]
1|10025|Loss: 0.7736523747444153:  39%|███▊      | 10025/25880 [2:04:04<3:13:58,  1.36it/s]
1|10026|Loss: 0.6835078001022339:  39%|███▊      | 10025/25880 [2:04:05<3:13:58,  1.36it/s]
1|10026|Loss: 0.6835078001022339:  39%|███▊      | 10026/25880 [2:04:05<3:25:24,  1.29it/s]
1|10027|Loss: 0.9668851494789124:  39%|███▊      | 10026/25880 [2:04:06<3:25:24,  1.29it/s]
1|10027|Loss: 0.9668851494789124:  39%|███▊      | 10027/25880 [2:04:06<3:24:09,  1.29it/s]
1|10028|Loss: 0.7762936353683472:  39%|███▊      | 10027/25880 [2:04:06<3:24:09,  1.29it/s]
1|10028|Loss: 0.7762936353683472:  39%|███▊      | 10028/25880 [2:04:07<3:07:01,  1.41it/s]
1|10029|Loss: 0.905446469783783:  39%|███▊      | 10028/25880 [2:04:07<3:07:01,  1.41it/s] 
1|10029|Loss: 0.905446469783783:  39%|███▉      | 10029/25880 [2:04:07<2:59:36,  1.47it/s]
1|10030|Loss: 0.8149509429931641:  39%|███▉      | 10029/25880 [2:04:08<2:59:36,  1.47it/s]
1|10030|Loss: 0.8149509429931641:  39%|███▉      | 10030/25880 [2:04:08<3:03:13,  1.44it/s]
1|10031|Loss: 0.7885813117027283:  39%|███▉      | 10030/25880 [2:04:08<3:03:13,  1.44it/s]
1|10031|Loss: 0.7885813117027283:  39%|███▉      | 10031/25880 [2:04:09<2:59:06,  1.47it/s]
1|10032|Loss: 0.9020317196846008:  39%|███▉      | 10031/25880 [2:04:09<2:59:06,  1.47it/s]
1|10032|Loss: 0.9020317196846008:  39%|███▉      | 10032/25880 [2:04:09<3:07:45,  1.41it/s]
1|10033|Loss: 0.8799853920936584:  39%|███▉      | 10032/25880 [2:04:10<3:07:45,  1.41it/s]
1|10033|Loss: 0.8799853920936584:  39%|███▉      | 10033/25880 [2:04:10<2:53:01,  1.53it/s]
1|10034|Loss: 0.8485710024833679:  39%|███▉      | 10033/25880 [2:04:10<2:53:01,  1.53it/s]
1|10034|Loss: 0.8485710024833679:  39%|███▉      | 10034/25880 [2:04:11<2:52:31,  1.53it/s]
1|10035|Loss: 0.8642188906669617:  39%|███▉      | 10034/25880 [2:04:11<2:52:31,  1.53it/s]
1|10035|Loss: 0.8642188906669617:  39%|███▉      | 10035/25880 [2:04:11<2:55:56,  1.50it/s]
1|10036|Loss: 0.8832955360412598:  39%|███▉      | 10035/25880 [2:04:12<2:55:56,  1.50it/s]
1|10036|Loss: 0.8832955360412598:  39%|███▉      | 10036/25880 [2:04:12<2:52:45,  1.53it/s]
1|10037|Loss: 0.7642189264297485:  39%|███▉      | 10036/25880 [2:04:12<2:52:45,  1.53it/s]
1|10037|Loss: 0.7642189264297485:  39%|███▉      | 10037/25880 [2:04:13<2:54:59,  1.51it/s]
1|10038|Loss: 0.8331184983253479:  39%|███▉      | 10037/25880 [2:04:13<2:54:59,  1.51it/s]
1|10038|Loss: 0.8331184983253479:  39%|███▉      | 10038/25880 [2:04:13<2:58:21,  1.48it/s]
1|10039|Loss: 0.8156089782714844:  39%|███▉      | 10038/25880 [2:04:14<2:58:21,  1.48it/s]
1|10039|Loss: 0.8156089782714844:  39%|███▉      | 10039/25880 [2:04:14<3:02:58,  1.44it/s]
1|10040|Loss: 0.8551575541496277:  39%|███▉      | 10039/25880 [2:04:14<3:02:58,  1.44it/s]
1|10040|Loss: 0.8551575541496277:  39%|███▉      | 10040/25880 [2:04:15<3:07:18,  1.41it/s]
1|10041|Loss: 0.7673697471618652:  39%|███▉      | 10040/25880 [2:04:15<3:07:18,  1.41it/s]
1|10041|Loss: 0.7673697471618652:  39%|███▉      | 10041/25880 [2:04:15<2:58:23,  1.48it/s]
1|10042|Loss: 0.8160871267318726:  39%|███▉      | 10041/25880 [2:04:16<2:58:23,  1.48it/s]
1|10042|Loss: 0.8160871267318726:  39%|███▉      | 10042/25880 [2:04:16<3:00:55,  1.46it/s]
1|10043|Loss: 0.8614854216575623:  39%|███▉      | 10042/25880 [2:04:16<3:00:55,  1.46it/s]
1|10043|Loss: 0.8614854216575623:  39%|███▉      | 10043/25880 [2:04:17<2:59:24,  1.47it/s]
1|10044|Loss: 0.7643742561340332:  39%|███▉      | 10043/25880 [2:04:17<2:59:24,  1.47it/s]
1|10044|Loss: 0.7643742561340332:  39%|███▉      | 10044/25880 [2:04:17<2:54:59,  1.51it/s]
1|10045|Loss: 0.8038604855537415:  39%|███▉      | 10044/25880 [2:04:18<2:54:59,  1.51it/s]
1|10045|Loss: 0.8038604855537415:  39%|███▉      | 10045/25880 [2:04:18<2:57:21,  1.49it/s]
1|10046|Loss: 0.7174830436706543:  39%|███▉      | 10045/25880 [2:04:18<2:57:21,  1.49it/s]
1|10046|Loss: 0.7174830436706543:  39%|███▉      | 10046/25880 [2:04:19<3:00:55,  1.46it/s]
1|10047|Loss: 0.9391071796417236:  39%|███▉      | 10046/25880 [2:04:19<3:00:55,  1.46it/s]
1|10047|Loss: 0.9391071796417236:  39%|███▉      | 10047/25880 [2:04:20<3:08:18,  1.40it/s]
1|10048|Loss: 0.8164815902709961:  39%|███▉      | 10047/25880 [2:04:20<3:08:18,  1.40it/s]
1|10048|Loss: 0.8164815902709961:  39%|███▉      | 10048/25880 [2:04:20<3:04:40,  1.43it/s]
1|10049|Loss: 0.881883442401886:  39%|███▉      | 10048/25880 [2:04:21<3:04:40,  1.43it/s] 
1|10049|Loss: 0.881883442401886:  39%|███▉      | 10049/25880 [2:04:21<2:52:50,  1.53it/s]
1|10050|Loss: 0.9554162621498108:  39%|███▉      | 10049/25880 [2:04:21<2:52:50,  1.53it/s]
1|10050|Loss: 0.9554162621498108:  39%|███▉      | 10050/25880 [2:04:22<3:07:45,  1.41it/s]
1|10051|Loss: 0.9268540143966675:  39%|███▉      | 10050/25880 [2:04:22<3:07:45,  1.41it/s]
1|10051|Loss: 0.9268540143966675:  39%|███▉      | 10051/25880 [2:04:22<3:10:42,  1.38it/s]
1|10052|Loss: 0.7358607649803162:  39%|███▉      | 10051/25880 [2:04:23<3:10:42,  1.38it/s]
1|10052|Loss: 0.7358607649803162:  39%|███▉      | 10052/25880 [2:04:23<2:52:53,  1.53it/s]
1|10053|Loss: 0.6615625619888306:  39%|███▉      | 10052/25880 [2:04:23<2:52:53,  1.53it/s]
1|10053|Loss: 0.6615625619888306:  39%|███▉      | 10053/25880 [2:04:24<3:01:41,  1.45it/s]
1|10054|Loss: 0.8494512438774109:  39%|███▉      | 10053/25880 [2:04:24<3:01:41,  1.45it/s]
1|10054|Loss: 0.8494512438774109:  39%|███▉      | 10054/25880 [2:04:24<3:11:17,  1.38it/s]
1|10055|Loss: 0.823371946811676:  39%|███▉      | 10054/25880 [2:04:25<3:11:17,  1.38it/s] 
1|10055|Loss: 0.823371946811676:  39%|███▉      | 10055/25880 [2:04:25<2:55:38,  1.50it/s]
1|10056|Loss: 0.8105470538139343:  39%|███▉      | 10055/25880 [2:04:25<2:55:38,  1.50it/s]
1|10056|Loss: 0.8105470538139343:  39%|███▉      | 10056/25880 [2:04:26<2:56:18,  1.50it/s]
1|10057|Loss: 0.7771751284599304:  39%|███▉      | 10056/25880 [2:04:26<2:56:18,  1.50it/s]
1|10057|Loss: 0.7771751284599304:  39%|███▉      | 10057/25880 [2:04:26<3:01:26,  1.45it/s]
1|10058|Loss: 0.7282990217208862:  39%|███▉      | 10057/25880 [2:04:27<3:01:26,  1.45it/s]
1|10058|Loss: 0.7282990217208862:  39%|███▉      | 10058/25880 [2:04:27<3:02:55,  1.44it/s]
1|10059|Loss: 1.0567023754119873:  39%|███▉      | 10058/25880 [2:04:27<3:02:55,  1.44it/s]
1|10059|Loss: 1.0567023754119873:  39%|███▉      | 10059/25880 [2:04:28<3:11:21,  1.38it/s]
1|10060|Loss: 0.7980138659477234:  39%|███▉      | 10059/25880 [2:04:28<3:11:21,  1.38it/s]
1|10060|Loss: 0.7980138659477234:  39%|███▉      | 10060/25880 [2:04:29<3:28:02,  1.27it/s]
1|10061|Loss: 0.714885413646698:  39%|███▉      | 10060/25880 [2:04:29<3:28:02,  1.27it/s] 
1|10061|Loss: 0.714885413646698:  39%|███▉      | 10061/25880 [2:04:30<3:28:03,  1.27it/s]
1|10062|Loss: 0.8828098773956299:  39%|███▉      | 10061/25880 [2:04:30<3:28:03,  1.27it/s]
1|10062|Loss: 0.8828098773956299:  39%|███▉      | 10062/25880 [2:04:30<3:10:09,  1.39it/s]
1|10063|Loss: 0.8195817470550537:  39%|███▉      | 10062/25880 [2:04:31<3:10:09,  1.39it/s]
1|10063|Loss: 0.8195817470550537:  39%|███▉      | 10063/25880 [2:04:31<3:05:42,  1.42it/s]
1|10064|Loss: 0.749082624912262:  39%|███▉      | 10063/25880 [2:04:31<3:05:42,  1.42it/s] 
1|10064|Loss: 0.749082624912262:  39%|███▉      | 10064/25880 [2:04:32<3:07:18,  1.41it/s]
1|10065|Loss: 0.8037055730819702:  39%|███▉      | 10064/25880 [2:04:32<3:07:18,  1.41it/s]
1|10065|Loss: 0.8037055730819702:  39%|███▉      | 10065/25880 [2:04:32<3:08:29,  1.40it/s]
1|10066|Loss: 0.8253874778747559:  39%|███▉      | 10065/25880 [2:04:33<3:08:29,  1.40it/s]
1|10066|Loss: 0.8253874778747559:  39%|███▉      | 10066/25880 [2:04:33<2:55:31,  1.50it/s]
1|10067|Loss: 0.7604093551635742:  39%|███▉      | 10066/25880 [2:04:33<2:55:31,  1.50it/s]
1|10067|Loss: 0.7604093551635742:  39%|███▉      | 10067/25880 [2:04:34<3:03:09,  1.44it/s]
1|10068|Loss: 0.8890626430511475:  39%|███▉      | 10067/25880 [2:04:34<3:03:09,  1.44it/s]
1|10068|Loss: 0.8890626430511475:  39%|███▉      | 10068/25880 [2:04:34<3:08:26,  1.40it/s]
1|10069|Loss: 0.959623396396637:  39%|███▉      | 10068/25880 [2:04:35<3:08:26,  1.40it/s] 
1|10069|Loss: 0.959623396396637:  39%|███▉      | 10069/25880 [2:04:35<3:13:59,  1.36it/s]
1|10070|Loss: 0.9544087052345276:  39%|███▉      | 10069/25880 [2:04:36<3:13:59,  1.36it/s]
1|10070|Loss: 0.9544087052345276:  39%|███▉      | 10070/25880 [2:04:36<3:14:56,  1.35it/s]
1|10071|Loss: 0.7684828639030457:  39%|███▉      | 10070/25880 [2:04:36<3:14:56,  1.35it/s]
1|10071|Loss: 0.7684828639030457:  39%|███▉      | 10071/25880 [2:04:37<3:11:39,  1.37it/s]
1|10072|Loss: 0.9514495730400085:  39%|███▉      | 10071/25880 [2:04:37<3:11:39,  1.37it/s]
1|10072|Loss: 0.9514495730400085:  39%|███▉      | 10072/25880 [2:04:37<3:18:41,  1.33it/s]
1|10073|Loss: 0.8115983605384827:  39%|███▉      | 10072/25880 [2:04:38<3:18:41,  1.33it/s]
1|10073|Loss: 0.8115983605384827:  39%|███▉      | 10073/25880 [2:04:38<3:17:23,  1.33it/s]
1|10074|Loss: 0.914344310760498:  39%|███▉      | 10073/25880 [2:04:39<3:17:23,  1.33it/s] 
1|10074|Loss: 0.914344310760498:  39%|███▉      | 10074/25880 [2:04:39<3:15:20,  1.35it/s]
1|10075|Loss: 0.9665030837059021:  39%|███▉      | 10074/25880 [2:04:39<3:15:20,  1.35it/s]
1|10075|Loss: 0.9665030837059021:  39%|███▉      | 10075/25880 [2:04:40<3:23:51,  1.29it/s]
1|10076|Loss: 0.9223344922065735:  39%|███▉      | 10075/25880 [2:04:40<3:23:51,  1.29it/s]
1|10076|Loss: 0.9223344922065735:  39%|███▉      | 10076/25880 [2:04:40<3:17:26,  1.33it/s]
1|10077|Loss: 0.9512546062469482:  39%|███▉      | 10076/25880 [2:04:41<3:17:26,  1.33it/s]
1|10077|Loss: 0.9512546062469482:  39%|███▉      | 10077/25880 [2:04:41<3:05:23,  1.42it/s]
1|10078|Loss: 0.8281911611557007:  39%|███▉      | 10077/25880 [2:04:41<3:05:23,  1.42it/s]
1|10078|Loss: 0.8281911611557007:  39%|███▉      | 10078/25880 [2:04:42<3:06:10,  1.41it/s]
1|10079|Loss: 0.7835701107978821:  39%|███▉      | 10078/25880 [2:04:42<3:06:10,  1.41it/s]
1|10079|Loss: 0.7835701107978821:  39%|███▉      | 10079/25880 [2:04:42<3:10:06,  1.39it/s]
1|10080|Loss: 0.7816562056541443:  39%|███▉      | 10079/25880 [2:04:43<3:10:06,  1.39it/s]
1|10080|Loss: 0.7816562056541443:  39%|███▉      | 10080/25880 [2:04:43<3:12:13,  1.37it/s]
1|10081|Loss: 0.7432976961135864:  39%|███▉      | 10080/25880 [2:04:44<3:12:13,  1.37it/s]
1|10081|Loss: 0.7432976961135864:  39%|███▉      | 10081/25880 [2:04:44<3:27:11,  1.27it/s]
1|10082|Loss: 0.8654071688652039:  39%|███▉      | 10081/25880 [2:04:45<3:27:11,  1.27it/s]
1|10082|Loss: 0.8654071688652039:  39%|███▉      | 10082/25880 [2:04:45<3:21:09,  1.31it/s]
1|10083|Loss: 0.8134479522705078:  39%|███▉      | 10082/25880 [2:04:45<3:21:09,  1.31it/s]
1|10083|Loss: 0.8134479522705078:  39%|███▉      | 10083/25880 [2:04:46<3:18:31,  1.33it/s]
1|10084|Loss: 0.830505907535553:  39%|███▉      | 10083/25880 [2:04:46<3:18:31,  1.33it/s] 
1|10084|Loss: 0.830505907535553:  39%|███▉      | 10084/25880 [2:04:46<3:23:27,  1.29it/s]
1|10085|Loss: 0.8214725255966187:  39%|███▉      | 10084/25880 [2:04:47<3:23:27,  1.29it/s]
1|10085|Loss: 0.8214725255966187:  39%|███▉      | 10085/25880 [2:04:47<3:12:04,  1.37it/s]
1|10086|Loss: 0.9512133002281189:  39%|███▉      | 10085/25880 [2:04:47<3:12:04,  1.37it/s]
1|10086|Loss: 0.9512133002281189:  39%|███▉      | 10086/25880 [2:04:48<3:21:37,  1.31it/s]
1|10087|Loss: 0.9863823056221008:  39%|███▉      | 10086/25880 [2:04:48<3:21:37,  1.31it/s]
1|10087|Loss: 0.9863823056221008:  39%|███▉      | 10087/25880 [2:04:49<3:16:16,  1.34it/s]
1|10088|Loss: 0.7655095458030701:  39%|███▉      | 10087/25880 [2:04:49<3:16:16,  1.34it/s]
1|10088|Loss: 0.7655095458030701:  39%|███▉      | 10088/25880 [2:04:49<3:08:25,  1.40it/s]
1|10089|Loss: 0.7369718551635742:  39%|███▉      | 10088/25880 [2:04:50<3:08:25,  1.40it/s]
1|10089|Loss: 0.7369718551635742:  39%|███▉      | 10089/25880 [2:04:50<2:54:54,  1.50it/s]
1|10090|Loss: 0.8225962519645691:  39%|███▉      | 10089/25880 [2:04:50<2:54:54,  1.50it/s]
1|10090|Loss: 0.8225962519645691:  39%|███▉      | 10090/25880 [2:04:51<3:02:59,  1.44it/s]
1|10091|Loss: 0.8574551939964294:  39%|███▉      | 10090/25880 [2:04:51<3:02:59,  1.44it/s]
1|10091|Loss: 0.8574551939964294:  39%|███▉      | 10091/25880 [2:04:51<3:07:17,  1.41it/s]
1|10092|Loss: 0.7025262713432312:  39%|███▉      | 10091/25880 [2:04:52<3:07:17,  1.41it/s]
1|10092|Loss: 0.7025262713432312:  39%|███▉      | 10092/25880 [2:04:52<3:13:16,  1.36it/s]
1|10093|Loss: 0.8147353529930115:  39%|███▉      | 10092/25880 [2:04:52<3:13:16,  1.36it/s]
1|10093|Loss: 0.8147353529930115:  39%|███▉      | 10093/25880 [2:04:53<3:04:32,  1.43it/s]
1|10094|Loss: 0.8186697363853455:  39%|███▉      | 10093/25880 [2:04:53<3:04:32,  1.43it/s]
1|10094|Loss: 0.8186697363853455:  39%|███▉      | 10094/25880 [2:04:53<2:54:59,  1.50it/s]
1|10095|Loss: 0.970689594745636:  39%|███▉      | 10094/25880 [2:04:54<2:54:59,  1.50it/s] 
1|10095|Loss: 0.970689594745636:  39%|███▉      | 10095/25880 [2:04:54<2:57:54,  1.48it/s]
1|10096|Loss: 0.8662201166152954:  39%|███▉      | 10095/25880 [2:04:54<2:57:54,  1.48it/s]
1|10096|Loss: 0.8662201166152954:  39%|███▉      | 10096/25880 [2:04:55<3:18:16,  1.33it/s]
1|10097|Loss: 0.8235920667648315:  39%|███▉      | 10096/25880 [2:04:55<3:18:16,  1.33it/s]
1|10097|Loss: 0.8235920667648315:  39%|███▉      | 10097/25880 [2:04:56<3:20:29,  1.31it/s]
1|10098|Loss: 0.9393929243087769:  39%|███▉      | 10097/25880 [2:04:56<3:20:29,  1.31it/s]
1|10098|Loss: 0.9393929243087769:  39%|███▉      | 10098/25880 [2:04:56<3:03:19,  1.43it/s]
1|10099|Loss: 0.8942849040031433:  39%|███▉      | 10098/25880 [2:04:57<3:03:19,  1.43it/s]
1|10099|Loss: 0.8942849040031433:  39%|███▉      | 10099/25880 [2:04:57<3:10:24,  1.38it/s]
1|10100|Loss: 0.942852258682251:  39%|███▉      | 10099/25880 [2:04:57<3:10:24,  1.38it/s] 
1|10100|Loss: 0.942852258682251:  39%|███▉      | 10100/25880 [2:04:58<2:59:46,  1.46it/s]
1|10101|Loss: 0.8219711184501648:  39%|███▉      | 10100/25880 [2:04:58<2:59:46,  1.46it/s]
1|10101|Loss: 0.8219711184501648:  39%|███▉      | 10101/25880 [2:04:58<2:59:43,  1.46it/s]
1|10102|Loss: 0.7737593650817871:  39%|███▉      | 10101/25880 [2:04:59<2:59:43,  1.46it/s]
1|10102|Loss: 0.7737593650817871:  39%|███▉      | 10102/25880 [2:04:59<3:07:10,  1.40it/s]
1|10103|Loss: 0.7831966280937195:  39%|███▉      | 10102/25880 [2:05:00<3:07:10,  1.40it/s]
1|10103|Loss: 0.7831966280937195:  39%|███▉      | 10103/25880 [2:05:00<3:17:38,  1.33it/s]
1|10104|Loss: 0.9210066199302673:  39%|███▉      | 10103/25880 [2:05:00<3:17:38,  1.33it/s]
1|10104|Loss: 0.9210066199302673:  39%|███▉      | 10104/25880 [2:05:01<3:16:36,  1.34it/s]
1|10105|Loss: 0.8481967449188232:  39%|███▉      | 10104/25880 [2:05:01<3:16:36,  1.34it/s]
1|10105|Loss: 0.8481967449188232:  39%|███▉      | 10105/25880 [2:05:01<2:52:56,  1.52it/s]
1|10106|Loss: 0.7912976741790771:  39%|███▉      | 10105/25880 [2:05:01<2:52:56,  1.52it/s]
1|10106|Loss: 0.7912976741790771:  39%|███▉      | 10106/25880 [2:05:02<2:54:15,  1.51it/s]
1|10107|Loss: 0.9815625548362732:  39%|███▉      | 10106/25880 [2:05:02<2:54:15,  1.51it/s]
1|10107|Loss: 0.9815625548362732:  39%|███▉      | 10107/25880 [2:05:03<3:04:26,  1.43it/s]
1|10108|Loss: 0.8296612501144409:  39%|███▉      | 10107/25880 [2:05:03<3:04:26,  1.43it/s]
1|10108|Loss: 0.8296612501144409:  39%|███▉      | 10108/25880 [2:05:03<3:07:27,  1.40it/s]
1|10109|Loss: 0.8844783306121826:  39%|███▉      | 10108/25880 [2:05:04<3:07:27,  1.40it/s]
1|10109|Loss: 0.8844783306121826:  39%|███▉      | 10109/25880 [2:05:04<3:09:06,  1.39it/s]
1|10110|Loss: 0.8190377950668335:  39%|███▉      | 10109/25880 [2:05:04<3:09:06,  1.39it/s]
1|10110|Loss: 0.8190377950668335:  39%|███▉      | 10110/25880 [2:05:05<3:14:40,  1.35it/s]
1|10111|Loss: 0.8442153930664062:  39%|███▉      | 10110/25880 [2:05:05<3:14:40,  1.35it/s]
1|10111|Loss: 0.8442153930664062:  39%|███▉      | 10111/25880 [2:05:06<3:15:28,  1.34it/s]
1|10112|Loss: 0.8506394028663635:  39%|███▉      | 10111/25880 [2:05:06<3:15:28,  1.34it/s]
1|10112|Loss: 0.8506394028663635:  39%|███▉      | 10112/25880 [2:05:06<3:09:16,  1.39it/s]
1|10113|Loss: 0.9184079766273499:  39%|███▉      | 10112/25880 [2:05:07<3:09:16,  1.39it/s]
1|10113|Loss: 0.9184079766273499:  39%|███▉      | 10113/25880 [2:05:07<3:13:34,  1.36it/s]
1|10114|Loss: 0.9895021319389343:  39%|███▉      | 10113/25880 [2:05:07<3:13:34,  1.36it/s]
1|10114|Loss: 0.9895021319389343:  39%|███▉      | 10114/25880 [2:05:08<3:06:52,  1.41it/s]
1|10115|Loss: 0.9122393727302551:  39%|███▉      | 10114/25880 [2:05:08<3:06:52,  1.41it/s]
1|10115|Loss: 0.9122393727302551:  39%|███▉      | 10115/25880 [2:05:08<2:55:43,  1.50it/s]
1|10116|Loss: 0.7858116030693054:  39%|███▉      | 10115/25880 [2:05:09<2:55:43,  1.50it/s]
1|10116|Loss: 0.7858116030693054:  39%|███▉      | 10116/25880 [2:05:09<2:48:23,  1.56it/s]
1|10117|Loss: 0.8342777490615845:  39%|███▉      | 10116/25880 [2:05:09<2:48:23,  1.56it/s]
1|10117|Loss: 0.8342777490615845:  39%|███▉      | 10117/25880 [2:05:09<2:47:42,  1.57it/s]
1|10118|Loss: 0.7804842591285706:  39%|███▉      | 10117/25880 [2:05:10<2:47:42,  1.57it/s]
1|10118|Loss: 0.7804842591285706:  39%|███▉      | 10118/25880 [2:05:10<3:05:57,  1.41it/s]
1|10119|Loss: 0.7346195578575134:  39%|███▉      | 10118/25880 [2:05:11<3:05:57,  1.41it/s]
1|10119|Loss: 0.7346195578575134:  39%|███▉      | 10119/25880 [2:05:11<3:18:24,  1.32it/s]
1|10120|Loss: 0.81974858045578:  39%|███▉      | 10119/25880 [2:05:12<3:18:24,  1.32it/s]  
1|10120|Loss: 0.81974858045578:  39%|███▉      | 10120/25880 [2:05:12<3:16:59,  1.33it/s]
1|10121|Loss: 0.7914326786994934:  39%|███▉      | 10120/25880 [2:05:12<3:16:59,  1.33it/s]
1|10121|Loss: 0.7914326786994934:  39%|███▉      | 10121/25880 [2:05:13<3:12:49,  1.36it/s]
1|10122|Loss: 0.9008879661560059:  39%|███▉      | 10121/25880 [2:05:13<3:12:49,  1.36it/s]
1|10122|Loss: 0.9008879661560059:  39%|███▉      | 10122/25880 [2:05:13<3:05:54,  1.41it/s]
1|10123|Loss: 0.8288560509681702:  39%|███▉      | 10122/25880 [2:05:14<3:05:54,  1.41it/s]
1|10123|Loss: 0.8288560509681702:  39%|███▉      | 10123/25880 [2:05:14<3:07:12,  1.40it/s]
1|10124|Loss: 0.8020825386047363:  39%|███▉      | 10123/25880 [2:05:14<3:07:12,  1.40it/s]
1|10124|Loss: 0.8020825386047363:  39%|███▉      | 10124/25880 [2:05:15<3:14:11,  1.35it/s]
1|10125|Loss: 0.9930521845817566:  39%|███▉      | 10124/25880 [2:05:15<3:14:11,  1.35it/s]
1|10125|Loss: 0.9930521845817566:  39%|███▉      | 10125/25880 [2:05:15<3:04:43,  1.42it/s]
1|10126|Loss: 0.7339447736740112:  39%|███▉      | 10125/25880 [2:05:16<3:04:43,  1.42it/s]
1|10126|Loss: 0.7339447736740112:  39%|███▉      | 10126/25880 [2:05:16<2:55:54,  1.49it/s]
1|10127|Loss: 0.8714225888252258:  39%|███▉      | 10126/25880 [2:05:16<2:55:54,  1.49it/s]
1|10127|Loss: 0.8714225888252258:  39%|███▉      | 10127/25880 [2:05:17<2:52:06,  1.53it/s]
1|10128|Loss: 0.7625438570976257:  39%|███▉      | 10127/25880 [2:05:17<2:52:06,  1.53it/s]
1|10128|Loss: 0.7625438570976257:  39%|███▉      | 10128/25880 [2:05:17<2:47:14,  1.57it/s]
1|10129|Loss: 0.861983060836792:  39%|███▉      | 10128/25880 [2:05:18<2:47:14,  1.57it/s] 
1|10129|Loss: 0.861983060836792:  39%|███▉      | 10129/25880 [2:05:18<2:52:43,  1.52it/s]
1|10130|Loss: 0.7706152200698853:  39%|███▉      | 10129/25880 [2:05:18<2:52:43,  1.52it/s]
1|10130|Loss: 0.7706152200698853:  39%|███▉      | 10130/25880 [2:05:19<2:51:41,  1.53it/s]
1|10131|Loss: 0.7850318551063538:  39%|███▉      | 10130/25880 [2:05:19<2:51:41,  1.53it/s]
1|10131|Loss: 0.7850318551063538:  39%|███▉      | 10131/25880 [2:05:19<3:03:48,  1.43it/s]
1|10132|Loss: 0.7929555177688599:  39%|███▉      | 10131/25880 [2:05:20<3:03:48,  1.43it/s]
1|10132|Loss: 0.7929555177688599:  39%|███▉      | 10132/25880 [2:05:20<3:17:11,  1.33it/s]
1|10133|Loss: 0.9141166806221008:  39%|███▉      | 10132/25880 [2:05:21<3:17:11,  1.33it/s]
1|10133|Loss: 0.9141166806221008:  39%|███▉      | 10133/25880 [2:05:21<3:16:20,  1.34it/s]
1|10134|Loss: 0.8282198905944824:  39%|███▉      | 10133/25880 [2:05:21<3:16:20,  1.34it/s]
1|10134|Loss: 0.8282198905944824:  39%|███▉      | 10134/25880 [2:05:22<3:12:01,  1.37it/s]
1|10135|Loss: 0.7608931064605713:  39%|███▉      | 10134/25880 [2:05:22<3:12:01,  1.37it/s]
1|10135|Loss: 0.7608931064605713:  39%|███▉      | 10135/25880 [2:05:22<2:57:22,  1.48it/s]
1|10136|Loss: 0.9122751355171204:  39%|███▉      | 10135/25880 [2:05:23<2:57:22,  1.48it/s]
1|10136|Loss: 0.9122751355171204:  39%|███▉      | 10136/25880 [2:05:23<3:01:46,  1.44it/s]
1|10137|Loss: 0.8439096808433533:  39%|███▉      | 10136/25880 [2:05:23<3:01:46,  1.44it/s]
1|10137|Loss: 0.8439096808433533:  39%|███▉      | 10137/25880 [2:05:24<3:04:10,  1.42it/s]
1|10138|Loss: 0.8155186176300049:  39%|███▉      | 10137/25880 [2:05:24<3:04:10,  1.42it/s]
1|10138|Loss: 0.8155186176300049:  39%|███▉      | 10138/25880 [2:05:24<3:05:31,  1.41it/s]
1|10139|Loss: 0.8158534169197083:  39%|███▉      | 10138/25880 [2:05:25<3:05:31,  1.41it/s]
1|10139|Loss: 0.8158534169197083:  39%|███▉      | 10139/25880 [2:05:25<3:05:59,  1.41it/s]
1|10140|Loss: 0.7820606231689453:  39%|███▉      | 10139/25880 [2:05:26<3:05:59,  1.41it/s]
1|10140|Loss: 0.7820606231689453:  39%|███▉      | 10140/25880 [2:05:26<3:11:05,  1.37it/s]
1|10141|Loss: 0.7807575464248657:  39%|███▉      | 10140/25880 [2:05:26<3:11:05,  1.37it/s]
1|10141|Loss: 0.7807575464248657:  39%|███▉      | 10141/25880 [2:05:27<3:07:07,  1.40it/s]
1|10142|Loss: 0.9178584814071655:  39%|███▉      | 10141/25880 [2:05:27<3:07:07,  1.40it/s]
1|10142|Loss: 0.9178584814071655:  39%|███▉      | 10142/25880 [2:05:27<2:50:01,  1.54it/s]
1|10143|Loss: 0.8025997877120972:  39%|███▉      | 10142/25880 [2:05:27<2:50:01,  1.54it/s]
1|10143|Loss: 0.8025997877120972:  39%|███▉      | 10143/25880 [2:05:28<2:56:10,  1.49it/s]
1|10144|Loss: 0.805769145488739:  39%|███▉      | 10143/25880 [2:05:28<2:56:10,  1.49it/s] 
1|10144|Loss: 0.805769145488739:  39%|███▉      | 10144/25880 [2:05:28<2:54:39,  1.50it/s]
1|10145|Loss: 0.9077093601226807:  39%|███▉      | 10144/25880 [2:05:29<2:54:39,  1.50it/s]
1|10145|Loss: 0.9077093601226807:  39%|███▉      | 10145/25880 [2:05:29<2:55:43,  1.49it/s]
1|10146|Loss: 0.8742846250534058:  39%|███▉      | 10145/25880 [2:05:30<2:55:43,  1.49it/s]
1|10146|Loss: 0.8742846250534058:  39%|███▉      | 10146/25880 [2:05:30<2:54:11,  1.51it/s]
1|10147|Loss: 0.737259030342102:  39%|███▉      | 10146/25880 [2:05:30<2:54:11,  1.51it/s] 
1|10147|Loss: 0.737259030342102:  39%|███▉      | 10147/25880 [2:05:30<2:50:40,  1.54it/s]
1|10148|Loss: 0.8046196699142456:  39%|███▉      | 10147/25880 [2:05:31<2:50:40,  1.54it/s]
1|10148|Loss: 0.8046196699142456:  39%|███▉      | 10148/25880 [2:05:31<2:45:47,  1.58it/s]
1|10149|Loss: 0.9120951890945435:  39%|███▉      | 10148/25880 [2:05:31<2:45:47,  1.58it/s]
1|10149|Loss: 0.9120951890945435:  39%|███▉      | 10149/25880 [2:05:32<2:51:42,  1.53it/s]
1|10150|Loss: 0.9176807403564453:  39%|███▉      | 10149/25880 [2:05:32<2:51:42,  1.53it/s]
1|10150|Loss: 0.9176807403564453:  39%|███▉      | 10150/25880 [2:05:32<2:58:35,  1.47it/s]
1|10151|Loss: 1.0065913200378418:  39%|███▉      | 10150/25880 [2:05:33<2:58:35,  1.47it/s]
1|10151|Loss: 1.0065913200378418:  39%|███▉      | 10151/25880 [2:05:33<3:09:04,  1.39it/s]
1|10152|Loss: 0.6986585855484009:  39%|███▉      | 10151/25880 [2:05:34<3:09:04,  1.39it/s]
1|10152|Loss: 0.6986585855484009:  39%|███▉      | 10152/25880 [2:05:34<3:05:36,  1.41it/s]
1|10153|Loss: 0.8194739818572998:  39%|███▉      | 10152/25880 [2:05:34<3:05:36,  1.41it/s]
1|10153|Loss: 0.8194739818572998:  39%|███▉      | 10153/25880 [2:05:35<3:04:19,  1.42it/s]
1|10154|Loss: 0.9034982323646545:  39%|███▉      | 10153/25880 [2:05:35<3:04:19,  1.42it/s]
1|10154|Loss: 0.9034982323646545:  39%|███▉      | 10154/25880 [2:05:35<2:56:26,  1.49it/s]
1|10155|Loss: 0.8737359046936035:  39%|███▉      | 10154/25880 [2:05:36<2:56:26,  1.49it/s]
1|10155|Loss: 0.8737359046936035:  39%|███▉      | 10155/25880 [2:05:36<2:51:45,  1.53it/s]
1|10156|Loss: 0.8135892152786255:  39%|███▉      | 10155/25880 [2:05:36<2:51:45,  1.53it/s]
1|10156|Loss: 0.8135892152786255:  39%|███▉      | 10156/25880 [2:05:37<2:57:23,  1.48it/s]
1|10157|Loss: 0.8579632639884949:  39%|███▉      | 10156/25880 [2:05:37<2:57:23,  1.48it/s]
1|10157|Loss: 0.8579632639884949:  39%|███▉      | 10157/25880 [2:05:37<3:02:56,  1.43it/s]
1|10158|Loss: 0.8467245697975159:  39%|███▉      | 10157/25880 [2:05:38<3:02:56,  1.43it/s]
1|10158|Loss: 0.8467245697975159:  39%|███▉      | 10158/25880 [2:05:38<3:12:42,  1.36it/s]
1|10159|Loss: 0.7324276566505432:  39%|███▉      | 10158/25880 [2:05:38<3:12:42,  1.36it/s]
1|10159|Loss: 0.7324276566505432:  39%|███▉      | 10159/25880 [2:05:39<2:57:16,  1.48it/s]
1|10160|Loss: 0.8164082765579224:  39%|███▉      | 10159/25880 [2:05:39<2:57:16,  1.48it/s]
1|10160|Loss: 0.8164082765579224:  39%|███▉      | 10160/25880 [2:05:39<3:04:39,  1.42it/s]
1|10161|Loss: 0.8756833672523499:  39%|███▉      | 10160/25880 [2:05:40<3:04:39,  1.42it/s]
1|10161|Loss: 0.8756833672523499:  39%|███▉      | 10161/25880 [2:05:40<3:09:29,  1.38it/s]
1|10162|Loss: 0.9297564029693604:  39%|███▉      | 10161/25880 [2:05:41<3:09:29,  1.38it/s]
1|10162|Loss: 0.9297564029693604:  39%|███▉      | 10162/25880 [2:05:41<3:11:16,  1.37it/s]
1|10163|Loss: 0.8299720287322998:  39%|███▉      | 10162/25880 [2:05:41<3:11:16,  1.37it/s]
1|10163|Loss: 0.8299720287322998:  39%|███▉      | 10163/25880 [2:05:42<3:06:18,  1.41it/s]
1|10164|Loss: 0.9054440259933472:  39%|███▉      | 10163/25880 [2:05:42<3:06:18,  1.41it/s]
1|10164|Loss: 0.9054440259933472:  39%|███▉      | 10164/25880 [2:05:42<3:09:57,  1.38it/s]
1|10165|Loss: 0.8768329620361328:  39%|███▉      | 10164/25880 [2:05:43<3:09:57,  1.38it/s]
1|10165|Loss: 0.8768329620361328:  39%|███▉      | 10165/25880 [2:05:43<3:09:38,  1.38it/s]
1|10166|Loss: 0.7274293899536133:  39%|███▉      | 10165/25880 [2:05:43<3:09:38,  1.38it/s]
1|10166|Loss: 0.7274293899536133:  39%|███▉      | 10166/25880 [2:05:44<3:07:56,  1.39it/s]
1|10167|Loss: 1.0397316217422485:  39%|███▉      | 10166/25880 [2:05:44<3:07:56,  1.39it/s]
1|10167|Loss: 1.0397316217422485:  39%|███▉      | 10167/25880 [2:05:44<3:01:13,  1.45it/s]
1|10168|Loss: 0.8010401129722595:  39%|███▉      | 10167/25880 [2:05:45<3:01:13,  1.45it/s]
1|10168|Loss: 0.8010401129722595:  39%|███▉      | 10168/25880 [2:05:45<3:09:13,  1.38it/s]
1|10169|Loss: 0.8514712452888489:  39%|███▉      | 10168/25880 [2:05:46<3:09:13,  1.38it/s]
1|10169|Loss: 0.8514712452888489:  39%|███▉      | 10169/25880 [2:05:46<2:57:46,  1.47it/s]
1|10170|Loss: 0.8815038204193115:  39%|███▉      | 10169/25880 [2:05:46<2:57:46,  1.47it/s]
1|10170|Loss: 0.8815038204193115:  39%|███▉      | 10170/25880 [2:05:47<2:59:15,  1.46it/s]
1|10171|Loss: 0.8833011984825134:  39%|███▉      | 10170/25880 [2:05:47<2:59:15,  1.46it/s]
1|10171|Loss: 0.8833011984825134:  39%|███▉      | 10171/25880 [2:05:47<3:09:34,  1.38it/s]
1|10172|Loss: 0.752360999584198:  39%|███▉      | 10171/25880 [2:05:48<3:09:34,  1.38it/s] 
1|10172|Loss: 0.752360999584198:  39%|███▉      | 10172/25880 [2:05:48<3:23:17,  1.29it/s]
1|10173|Loss: 0.8858054280281067:  39%|███▉      | 10172/25880 [2:05:49<3:23:17,  1.29it/s]
1|10173|Loss: 0.8858054280281067:  39%|███▉      | 10173/25880 [2:05:49<3:16:22,  1.33it/s]
1|10174|Loss: 0.8666535019874573:  39%|███▉      | 10173/25880 [2:05:49<3:16:22,  1.33it/s]
1|10174|Loss: 0.8666535019874573:  39%|███▉      | 10174/25880 [2:05:50<3:24:14,  1.28it/s]
1|10175|Loss: 0.9897254705429077:  39%|███▉      | 10174/25880 [2:05:50<3:24:14,  1.28it/s]
1|10175|Loss: 0.9897254705429077:  39%|███▉      | 10175/25880 [2:05:50<3:16:12,  1.33it/s]
1|10176|Loss: 0.9087507128715515:  39%|███▉      | 10175/25880 [2:05:51<3:16:12,  1.33it/s]
1|10176|Loss: 0.9087507128715515:  39%|███▉      | 10176/25880 [2:05:51<3:00:40,  1.45it/s]
1|10177|Loss: 0.916847288608551:  39%|███▉      | 10176/25880 [2:05:51<3:00:40,  1.45it/s] 
1|10177|Loss: 0.916847288608551:  39%|███▉      | 10177/25880 [2:05:52<2:54:20,  1.50it/s]
1|10178|Loss: 0.8817183375358582:  39%|███▉      | 10177/25880 [2:05:52<2:54:20,  1.50it/s]
1|10178|Loss: 0.8817183375358582:  39%|███▉      | 10178/25880 [2:05:52<2:49:33,  1.54it/s]
1|10179|Loss: 0.9346458315849304:  39%|███▉      | 10178/25880 [2:05:53<2:49:33,  1.54it/s]
1|10179|Loss: 0.9346458315849304:  39%|███▉      | 10179/25880 [2:05:53<2:52:07,  1.52it/s]
1|10180|Loss: 0.8481898903846741:  39%|███▉      | 10179/25880 [2:05:53<2:52:07,  1.52it/s]
1|10180|Loss: 0.8481898903846741:  39%|███▉      | 10180/25880 [2:05:54<2:55:51,  1.49it/s]
1|10181|Loss: 0.7316761612892151:  39%|███▉      | 10180/25880 [2:05:54<2:55:51,  1.49it/s]
1|10181|Loss: 0.7316761612892151:  39%|███▉      | 10181/25880 [2:05:55<3:13:56,  1.35it/s]
1|10182|Loss: 0.8566628098487854:  39%|███▉      | 10181/25880 [2:05:55<3:13:56,  1.35it/s]
1|10182|Loss: 0.8566628098487854:  39%|███▉      | 10182/25880 [2:05:55<3:16:09,  1.33it/s]
1|10183|Loss: 0.8269374966621399:  39%|███▉      | 10182/25880 [2:05:56<3:16:09,  1.33it/s]
1|10183|Loss: 0.8269374966621399:  39%|███▉      | 10183/25880 [2:05:56<3:18:19,  1.32it/s]
1|10184|Loss: 0.8818346261978149:  39%|███▉      | 10183/25880 [2:05:56<3:18:19,  1.32it/s]
1|10184|Loss: 0.8818346261978149:  39%|███▉      | 10184/25880 [2:05:57<3:15:32,  1.34it/s]
1|10185|Loss: 0.9678118228912354:  39%|███▉      | 10184/25880 [2:05:57<3:15:32,  1.34it/s]
1|10185|Loss: 0.9678118228912354:  39%|███▉      | 10185/25880 [2:05:57<2:59:59,  1.45it/s]
1|10186|Loss: 0.7666047811508179:  39%|███▉      | 10185/25880 [2:05:58<2:59:59,  1.45it/s]
1|10186|Loss: 0.7666047811508179:  39%|███▉      | 10186/25880 [2:05:58<3:00:49,  1.45it/s]
1|10187|Loss: 0.8513078093528748:  39%|███▉      | 10186/25880 [2:05:58<3:00:49,  1.45it/s]
1|10187|Loss: 0.8513078093528748:  39%|███▉      | 10187/25880 [2:05:59<3:08:29,  1.39it/s]
1|10188|Loss: 0.7573930025100708:  39%|███▉      | 10187/25880 [2:05:59<3:08:29,  1.39it/s]
1|10188|Loss: 0.7573930025100708:  39%|███▉      | 10188/25880 [2:06:00<3:14:39,  1.34it/s]
1|10189|Loss: 0.9153552055358887:  39%|███▉      | 10188/25880 [2:06:00<3:14:39,  1.34it/s]
1|10189|Loss: 0.9153552055358887:  39%|███▉      | 10189/25880 [2:06:01<3:26:26,  1.27it/s]
1|10190|Loss: 0.9529905319213867:  39%|███▉      | 10189/25880 [2:06:01<3:26:26,  1.27it/s]
1|10190|Loss: 0.9529905319213867:  39%|███▉      | 10190/25880 [2:06:01<3:25:30,  1.27it/s]
1|10191|Loss: 0.8159921169281006:  39%|███▉      | 10190/25880 [2:06:02<3:25:30,  1.27it/s]
1|10191|Loss: 0.8159921169281006:  39%|��██▉      | 10191/25880 [2:06:02<3:20:44,  1.30it/s]
1|10192|Loss: 0.924274742603302:  39%|███▉      | 10191/25880 [2:06:02<3:20:44,  1.30it/s] 
1|10192|Loss: 0.924274742603302:  39%|███▉      | 10192/25880 [2:06:03<3:03:08,  1.43it/s]
1|10193|Loss: 0.7366718053817749:  39%|███▉      | 10192/25880 [2:06:03<3:03:08,  1.43it/s]
1|10193|Loss: 0.7366718053817749:  39%|███▉      | 10193/25880 [2:06:03<3:08:23,  1.39it/s]
1|10194|Loss: 0.85394686460495:  39%|███▉      | 10193/25880 [2:06:04<3:08:23,  1.39it/s]  
1|10194|Loss: 0.85394686460495:  39%|███▉      | 10194/25880 [2:06:04<3:22:06,  1.29it/s]
1|10195|Loss: 0.8856648206710815:  39%|███▉      | 10194/25880 [2:06:05<3:22:06,  1.29it/s]
1|10195|Loss: 0.8856648206710815:  39%|███▉      | 10195/25880 [2:06:05<3:28:11,  1.26it/s]
1|10196|Loss: 0.962425947189331:  39%|███▉      | 10195/25880 [2:06:05<3:28:11,  1.26it/s] 
1|10196|Loss: 0.962425947189331:  39%|███▉      | 10196/25880 [2:06:06<3:24:46,  1.28it/s]
1|10197|Loss: 0.9310740828514099:  39%|███▉      | 10196/25880 [2:06:06<3:24:46,  1.28it/s]
1|10197|Loss: 0.9310740828514099:  39%|███▉      | 10197/25880 [2:06:07<3:25:19,  1.27it/s]
1|10198|Loss: 0.8040662407875061:  39%|███▉      | 10197/25880 [2:06:07<3:25:19,  1.27it/s]
1|10198|Loss: 0.8040662407875061:  39%|███▉      | 10198/25880 [2:06:08<3:36:09,  1.21it/s]
1|10199|Loss: 0.6639398336410522:  39%|███▉      | 10198/25880 [2:06:08<3:36:09,  1.21it/s]
1|10199|Loss: 0.6639398336410522:  39%|███▉      | 10199/25880 [2:06:08<3:37:07,  1.20it/s]
1|10200|Loss: 0.9749833941459656:  39%|███▉      | 10199/25880 [2:06:09<3:37:07,  1.20it/s]
1|10200|Loss: 0.9749833941459656:  39%|███▉      | 10200/25880 [2:06:09<3:31:09,  1.24it/s]
1|10201|Loss: 0.702617347240448:  39%|███▉      | 10200/25880 [2:06:10<3:31:09,  1.24it/s] 
1|10201|Loss: 0.702617347240448:  39%|███▉      | 10201/25880 [2:06:10<3:19:35,  1.31it/s]
1|10202|Loss: 0.9288967847824097:  39%|███▉      | 10201/25880 [2:06:10<3:19:35,  1.31it/s]
1|10202|Loss: 0.9288967847824097:  39%|███▉      | 10202/25880 [2:06:11<3:15:12,  1.34it/s]
1|10203|Loss: 0.9335991144180298:  39%|███▉      | 10202/25880 [2:06:11<3:15:12,  1.34it/s]
1|10203|Loss: 0.9335991144180298:  39%|███▉      | 10203/25880 [2:06:11<3:19:49,  1.31it/s]
1|10204|Loss: 0.841145932674408:  39%|███▉      | 10203/25880 [2:06:12<3:19:49,  1.31it/s] 
1|10204|Loss: 0.841145932674408:  39%|███▉      | 10204/25880 [2:06:12<3:09:57,  1.38it/s]
1|10205|Loss: 0.7776188850402832:  39%|███▉      | 10204/25880 [2:06:12<3:09:57,  1.38it/s]
1|10205|Loss: 0.7776188850402832:  39%|███▉      | 10205/25880 [2:06:13<3:14:26,  1.34it/s]
1|10206|Loss: 0.9771194458007812:  39%|███▉      | 10205/25880 [2:06:13<3:14:26,  1.34it/s]
1|10206|Loss: 0.9771194458007812:  39%|███▉      | 10206/25880 [2:06:14<3:24:19,  1.28it/s]
1|10207|Loss: 0.9236013293266296:  39%|███▉      | 10206/25880 [2:06:14<3:24:19,  1.28it/s]
1|10207|Loss: 0.9236013293266296:  39%|███▉      | 10207/25880 [2:06:14<3:23:29,  1.28it/s]
1|10208|Loss: 0.7682907581329346:  39%|███▉      | 10207/25880 [2:06:15<3:23:29,  1.28it/s]
1|10208|Loss: 0.7682907581329346:  39%|███▉      | 10208/25880 [2:06:15<3:20:41,  1.30it/s]
1|10209|Loss: 0.8553168177604675:  39%|███▉      | 10208/25880 [2:06:15<3:20:41,  1.30it/s]
1|10209|Loss: 0.8553168177604675:  39%|███▉      | 10209/25880 [2:06:16<3:11:00,  1.37it/s]
1|10210|Loss: 0.8894922733306885:  39%|███▉      | 10209/25880 [2:06:16<3:11:00,  1.37it/s]
1|10210|Loss: 0.8894922733306885:  39%|███▉      | 10210/25880 [2:06:16<3:03:05,  1.43it/s]
1|10211|Loss: 0.8402503728866577:  39%|███▉      | 10210/25880 [2:06:17<3:03:05,  1.43it/s]
1|10211|Loss: 0.8402503728866577:  39%|███▉      | 10211/25880 [2:06:17<3:04:32,  1.42it/s]
1|10212|Loss: 0.8363984823226929:  39%|███▉      | 10211/25880 [2:06:18<3:04:32,  1.42it/s]
1|10212|Loss: 0.8363984823226929:  39%|███▉      | 10212/25880 [2:06:18<3:07:26,  1.39it/s]
1|10213|Loss: 0.698096752166748:  39%|███▉      | 10212/25880 [2:06:18<3:07:26,  1.39it/s] 
1|10213|Loss: 0.698096752166748:  39%|███▉      | 10213/25880 [2:06:19<3:14:59,  1.34it/s]
1|10214|Loss: 0.8717533946037292:  39%|███▉      | 10213/25880 [2:06:19<3:14:59,  1.34it/s]
1|10214|Loss: 0.8717533946037292:  39%|███▉      | 10214/25880 [2:06:19<2:59:48,  1.45it/s]
1|10215|Loss: 0.8296793103218079:  39%|███▉      | 10214/25880 [2:06:20<2:59:48,  1.45it/s]
1|10215|Loss: 0.8296793103218079:  39%|███▉      | 10215/25880 [2:06:20<2:59:55,  1.45it/s]
1|10216|Loss: 0.6047137379646301:  39%|███▉      | 10215/25880 [2:06:20<2:59:55,  1.45it/s]
1|10216|Loss: 0.6047137379646301:  39%|███▉      | 10216/25880 [2:06:20<2:49:30,  1.54it/s]
1|10217|Loss: 0.7975755929946899:  39%|███▉      | 10216/25880 [2:06:21<2:49:30,  1.54it/s]
1|10217|Loss: 0.7975755929946899:  39%|███▉      | 10217/25880 [2:06:21<3:02:11,  1.43it/s]
1|10218|Loss: 0.974555253982544:  39%|███▉      | 10217/25880 [2:06:22<3:02:11,  1.43it/s] 
1|10218|Loss: 0.974555253982544:  39%|███▉      | 10218/25880 [2:06:22<3:12:17,  1.36it/s]
1|10219|Loss: 0.8774035573005676:  39%|███▉      | 10218/25880 [2:06:23<3:12:17,  1.36it/s]
1|10219|Loss: 0.8774035573005676:  39%|███▉      | 10219/25880 [2:06:23<3:16:33,  1.33it/s]
1|10220|Loss: 0.8577139377593994:  39%|███▉      | 10219/25880 [2:06:23<3:16:33,  1.33it/s]
1|10220|Loss: 0.8577139377593994:  39%|███▉      | 10220/25880 [2:06:24<3:21:50,  1.29it/s]
1|10221|Loss: 0.7960116267204285:  39%|███▉      | 10220/25880 [2:06:24<3:21:50,  1.29it/s]
1|10221|Loss: 0.7960116267204285:  39%|███▉      | 10221/25880 [2:06:24<3:20:37,  1.30it/s]
1|10222|Loss: 0.9177391529083252:  39%|███▉      | 10221/25880 [2:06:25<3:20:37,  1.30it/s]
1|10222|Loss: 0.9177391529083252:  39%|███▉      | 10222/25880 [2:06:25<3:18:47,  1.31it/s]
1|10223|Loss: 0.873905599117279:  39%|███▉      | 10222/25880 [2:06:26<3:18:47,  1.31it/s] 
1|10223|Loss: 0.873905599117279:  40%|███▉      | 10223/25880 [2:06:26<3:22:39,  1.29it/s]
1|10224|Loss: 0.9472042918205261:  40%|███▉      | 10223/25880 [2:06:26<3:22:39,  1.29it/s]
1|10224|Loss: 0.9472042918205261:  40%|███▉      | 10224/25880 [2:06:27<3:14:45,  1.34it/s]
1|10225|Loss: 0.7109026312828064:  40%|███▉      | 10224/25880 [2:06:27<3:14:45,  1.34it/s]
1|10225|Loss: 0.7109026312828064:  40%|███▉      | 10225/25880 [2:06:27<3:16:16,  1.33it/s]
1|10226|Loss: 0.7109180092811584:  40%|███▉      | 10225/25880 [2:06:28<3:16:16,  1.33it/s]
1|10226|Loss: 0.7109180092811584:  40%|███▉      | 10226/25880 [2:06:28<3:13:43,  1.35it/s]
1|10227|Loss: 0.9033433198928833:  40%|███▉      | 10226/25880 [2:06:29<3:13:43,  1.35it/s]
1|10227|Loss: 0.9033433198928833:  40%|███▉      | 10227/25880 [2:06:29<3:06:30,  1.40it/s]
1|10228|Loss: 0.7565533518791199:  40%|███▉      | 10227/25880 [2:06:29<3:06:30,  1.40it/s]
1|10228|Loss: 0.7565533518791199:  40%|███▉      | 10228/25880 [2:06:29<2:59:22,  1.45it/s]
1|10229|Loss: 0.8203043341636658:  40%|███▉      | 10228/25880 [2:06:30<2:59:22,  1.45it/s]
1|10229|Loss: 0.8203043341636658:  40%|███▉      | 10229/25880 [2:06:30<3:07:36,  1.39it/s]
1|10230|Loss: 0.7457212805747986:  40%|███▉      | 10229/25880 [2:06:31<3:07:36,  1.39it/s]
1|10230|Loss: 0.7457212805747986:  40%|███▉      | 10230/25880 [2:06:31<3:04:24,  1.41it/s]
1|10231|Loss: 0.8501589894294739:  40%|███▉      | 10230/25880 [2:06:31<3:04:24,  1.41it/s]
1|10231|Loss: 0.8501589894294739:  40%|███▉      | 10231/25880 [2:06:32<2:59:19,  1.45it/s]
1|10232|Loss: 0.9033278226852417:  40%|███▉      | 10231/25880 [2:06:32<2:59:19,  1.45it/s]
1|10232|Loss: 0.9033278226852417:  40%|███▉      | 10232/25880 [2:06:32<3:01:56,  1.43it/s]
1|10233|Loss: 0.9353587031364441:  40%|███▉      | 10232/25880 [2:06:33<3:01:56,  1.43it/s]
1|10233|Loss: 0.9353587031364441:  40%|███▉      | 10233/25880 [2:06:33<3:05:53,  1.40it/s]
1|10234|Loss: 0.7601074576377869:  40%|███▉      | 10233/25880 [2:06:33<3:05:53,  1.40it/s]
1|10234|Loss: 0.7601074576377869:  40%|███▉      | 10234/25880 [2:06:34<3:08:39,  1.38it/s]
1|10235|Loss: 0.7907505035400391:  40%|███▉      | 10234/25880 [2:06:34<3:08:39,  1.38it/s]
1|10235|Loss: 0.7907505035400391:  40%|███▉      | 10235/25880 [2:06:35<3:09:59,  1.37it/s]
1|10236|Loss: 0.9423655867576599:  40%|███▉      | 10235/25880 [2:06:35<3:09:59,  1.37it/s]
1|10236|Loss: 0.9423655867576599:  40%|███▉      | 10236/25880 [2:06:35<3:03:12,  1.42it/s]
1|10237|Loss: 0.8323644995689392:  40%|███▉      | 10236/25880 [2:06:36<3:03:12,  1.42it/s]
1|10237|Loss: 0.8323644995689392:  40%|███▉      | 10237/25880 [2:06:36<3:03:29,  1.42it/s]
1|10238|Loss: 0.7675098776817322:  40%|███▉      | 10237/25880 [2:06:36<3:03:29,  1.42it/s]
1|10238|Loss: 0.7675098776817322:  40%|███▉      | 10238/25880 [2:06:37<2:58:02,  1.46it/s]
1|10239|Loss: 0.9189497828483582:  40%|███▉      | 10238/25880 [2:06:37<2:58:02,  1.46it/s]
1|10239|Loss: 0.9189497828483582:  40%|███▉      | 10239/25880 [2:06:37<3:00:07,  1.45it/s]
1|10240|Loss: 0.9502192139625549:  40%|███▉      | 10239/25880 [2:06:38<3:00:07,  1.45it/s]
1|10240|Loss: 0.9502192139625549:  40%|███▉      | 10240/25880 [2:06:38<2:57:34,  1.47it/s]
1|10241|Loss: 0.7568334937095642:  40%|███▉      | 10240/25880 [2:06:38<2:57:34,  1.47it/s]
1|10241|Loss: 0.7568334937095642:  40%|███▉      | 10241/25880 [2:06:38<2:50:53,  1.53it/s]
1|10242|Loss: 0.846921980381012:  40%|███▉      | 10241/25880 [2:06:39<2:50:53,  1.53it/s] 
1|10242|Loss: 0.846921980381012:  40%|███▉      | 10242/25880 [2:06:39<2:55:34,  1.48it/s]
1|10243|Loss: 0.8345404267311096:  40%|███▉      | 10242/25880 [2:06:40<2:55:34,  1.48it/s]
1|10243|Loss: 0.8345404267311096:  40%|███▉      | 10243/25880 [2:06:40<3:10:15,  1.37it/s]
1|10244|Loss: 0.7727279663085938:  40%|███▉      | 10243/25880 [2:06:41<3:10:15,  1.37it/s]
1|10244|Loss: 0.7727279663085938:  40%|███▉      | 10244/25880 [2:06:41<3:28:03,  1.25it/s]
1|10245|Loss: 0.8191143274307251:  40%|███▉      | 10244/25880 [2:06:41<3:28:03,  1.25it/s]
1|10245|Loss: 0.8191143274307251:  40%|███▉      | 10245/25880 [2:06:42<3:24:22,  1.28it/s]
1|10246|Loss: 0.8900319337844849:  40%|███▉      | 10245/25880 [2:06:42<3:24:22,  1.28it/s]
1|10246|Loss: 0.8900319337844849:  40%|███▉      | 10246/25880 [2:06:42<3:19:21,  1.31it/s]
1|10247|Loss: 0.8151251673698425:  40%|███▉      | 10246/25880 [2:06:43<3:19:21,  1.31it/s]
1|10247|Loss: 0.8151251673698425:  40%|███▉      | 10247/25880 [2:06:43<3:09:29,  1.38it/s]
1|10248|Loss: 0.9365654587745667:  40%|███▉      | 10247/25880 [2:06:43<3:09:29,  1.38it/s]
1|10248|Loss: 0.9365654587745667:  40%|███▉      | 10248/25880 [2:06:44<3:00:49,  1.44it/s]
1|10249|Loss: 0.8720577955245972:  40%|███▉      | 10248/25880 [2:06:44<3:00:49,  1.44it/s]
1|10249|Loss: 0.8720577955245972:  40%|███▉      | 10249/25880 [2:06:44<2:55:53,  1.48it/s]
1|10250|Loss: 0.8820304274559021:  40%|███▉      | 10249/25880 [2:06:45<2:55:53,  1.48it/s]
1|10250|Loss: 0.8820304274559021:  40%|███▉      | 10250/25880 [2:06:45<2:57:09,  1.47it/s]
1|10251|Loss: 0.8508822321891785:  40%|███▉      | 10250/25880 [2:06:45<2:57:09,  1.47it/s]
1|10251|Loss: 0.8508822321891785:  40%|███▉      | 10251/25880 [2:06:46<3:00:21,  1.44it/s]
1|10252|Loss: 0.8311470150947571:  40%|███▉      | 10251/25880 [2:06:46<3:00:21,  1.44it/s]
1|10252|Loss: 0.8311470150947571:  40%|███▉      | 10252/25880 [2:06:47<3:03:02,  1.42it/s]
1|10253|Loss: 0.9118707776069641:  40%|███▉      | 10252/25880 [2:06:47<3:03:02,  1.42it/s]
1|10253|Loss: 0.9118707776069641:  40%|███▉      | 10253/25880 [2:06:47<2:58:10,  1.46it/s]
1|10254|Loss: 0.8819698095321655:  40%|███▉      | 10253/25880 [2:06:48<2:58:10,  1.46it/s]
1|10254|Loss: 0.8819698095321655:  40%|███▉      | 10254/25880 [2:06:48<3:00:14,  1.44it/s]
1|10255|Loss: 0.9408349990844727:  40%|███▉      | 10254/25880 [2:06:48<3:00:14,  1.44it/s]
1|10255|Loss: 0.9408349990844727:  40%|███▉      | 10255/25880 [2:06:49<3:13:13,  1.35it/s]
1|10256|Loss: 0.8981653451919556:  40%|███▉      | 10255/25880 [2:06:49<3:13:13,  1.35it/s]
1|10256|Loss: 0.8981653451919556:  40%|███▉      | 10256/25880 [2:06:49<3:13:12,  1.35it/s]
1|10257|Loss: 0.8128675222396851:  40%|███▉      | 10256/25880 [2:06:50<3:13:12,  1.35it/s]
1|10257|Loss: 0.8128675222396851:  40%|███▉      | 10257/25880 [2:06:50<3:11:33,  1.36it/s]
1|10258|Loss: 0.7191720008850098:  40%|███▉      | 10257/25880 [2:06:51<3:11:33,  1.36it/s]
1|10258|Loss: 0.7191720008850098:  40%|███▉      | 10258/25880 [2:06:51<3:16:47,  1.32it/s]
1|10259|Loss: 0.866102397441864:  40%|███▉      | 10258/25880 [2:06:51<3:16:47,  1.32it/s] 
1|10259|Loss: 0.866102397441864:  40%|███▉      | 10259/25880 [2:06:52<3:19:45,  1.30it/s]
1|10260|Loss: 0.8619173169136047:  40%|███▉      | 10259/25880 [2:06:52<3:19:45,  1.30it/s]
1|10260|Loss: 0.8619173169136047:  40%|███▉      | 10260/25880 [2:06:53<3:25:37,  1.27it/s]
1|10261|Loss: 0.8936285972595215:  40%|███▉      | 10260/25880 [2:06:53<3:25:37,  1.27it/s]
1|10261|Loss: 0.8936285972595215:  40%|███▉      | 10261/25880 [2:06:53<3:31:06,  1.23it/s]
1|10262|Loss: 0.9437257647514343:  40%|███▉      | 10261/25880 [2:06:54<3:31:06,  1.23it/s]
1|10262|Loss: 0.9437257647514343:  40%|███▉      | 10262/25880 [2:06:54<3:39:34,  1.19it/s]
1|10263|Loss: 0.7676696181297302:  40%|███▉      | 10262/25880 [2:06:55<3:39:34,  1.19it/s]
1|10263|Loss: 0.7676696181297302:  40%|███▉      | 10263/25880 [2:06:55<3:33:40,  1.22it/s]
1|10264|Loss: 1.019234538078308:  40%|███▉      | 10263/25880 [2:06:56<3:33:40,  1.22it/s] 
1|10264|Loss: 1.019234538078308:  40%|███▉      | 10264/25880 [2:06:56<3:26:35,  1.26it/s]
1|10265|Loss: 0.8445408940315247:  40%|███▉      | 10264/25880 [2:06:56<3:26:35,  1.26it/s]
1|10265|Loss: 0.8445408940315247:  40%|███▉      | 10265/25880 [2:06:57<3:19:05,  1.31it/s]
1|10266|Loss: 0.8810884952545166:  40%|███▉      | 10265/25880 [2:06:57<3:19:05,  1.31it/s]
1|10266|Loss: 0.8810884952545166:  40%|███▉      | 10266/25880 [2:06:57<3:19:23,  1.31it/s]
1|10267|Loss: 0.7383860349655151:  40%|███▉      | 10266/25880 [2:06:58<3:19:23,  1.31it/s]
1|10267|Loss: 0.7383860349655151:  40%|███▉      | 10267/25880 [2:06:58<3:12:21,  1.35it/s]
1|10268|Loss: 0.8402894139289856:  40%|███▉      | 10267/25880 [2:06:58<3:12:21,  1.35it/s]
1|10268|Loss: 0.8402894139289856:  40%|███▉      | 10268/25880 [2:06:59<3:22:18,  1.29it/s]
1|10269|Loss: 0.8987915515899658:  40%|███▉      | 10268/25880 [2:06:59<3:22:18,  1.29it/s]
1|10269|Loss: 0.8987915515899658:  40%|███▉      | 10269/25880 [2:07:00<3:16:25,  1.32it/s]
1|10270|Loss: 0.9691004753112793:  40%|███▉      | 10269/25880 [2:07:00<3:16:25,  1.32it/s]
1|10270|Loss: 0.9691004753112793:  40%|███▉      | 10270/25880 [2:07:00<3:03:49,  1.42it/s]
1|10271|Loss: 0.8597167730331421:  40%|███▉      | 10270/25880 [2:07:01<3:03:49,  1.42it/s]
1|10271|Loss: 0.8597167730331421:  40%|███▉      | 10271/25880 [2:07:01<2:57:46,  1.46it/s]
1|10272|Loss: 0.8845568895339966:  40%|███▉      | 10271/25880 [2:07:01<2:57:46,  1.46it/s]
1|10272|Loss: 0.8845568895339966:  40%|███▉      | 10272/25880 [2:07:02<3:03:56,  1.41it/s]
1|10273|Loss: 0.8405539393424988:  40%|███▉      | 10272/25880 [2:07:02<3:03:56,  1.41it/s]
1|10273|Loss: 0.8405539393424988:  40%|███▉      | 10273/25880 [2:07:02<3:07:45,  1.39it/s]
1|10274|Loss: 0.8495449423789978:  40%|███▉      | 10273/25880 [2:07:03<3:07:45,  1.39it/s]
1|10274|Loss: 0.8495449423789978:  40%|███▉      | 10274/25880 [2:07:03<3:09:00,  1.38it/s]
1|10275|Loss: 0.709855318069458:  40%|███▉      | 10274/25880 [2:07:03<3:09:00,  1.38it/s] 
1|10275|Loss: 0.709855318069458:  40%|███▉      | 10275/25880 [2:07:04<2:46:44,  1.56it/s]
1|10276|Loss: 1.0653026103973389:  40%|███▉      | 10275/25880 [2:07:04<2:46:44,  1.56it/s]
1|10276|Loss: 1.0653026103973389:  40%|███▉      | 10276/25880 [2:07:04<2:48:43,  1.54it/s]
1|10277|Loss: 0.7753509283065796:  40%|███▉      | 10276/25880 [2:07:05<2:48:43,  1.54it/s]
1|10277|Loss: 0.7753509283065796:  40%|███▉      | 10277/25880 [2:07:05<3:06:59,  1.39it/s]
1|10278|Loss: 0.8068237900733948:  40%|███▉      | 10277/25880 [2:07:06<3:06:59,  1.39it/s]
1|10278|Loss: 0.8068237900733948:  40%|███▉      | 10278/25880 [2:07:06<3:10:45,  1.36it/s]
1|10279|Loss: 0.852800726890564:  40%|███▉      | 10278/25880 [2:07:06<3:10:45,  1.36it/s] 
1|10279|Loss: 0.852800726890564:  40%|███▉      | 10279/25880 [2:07:07<3:11:16,  1.36it/s]
1|10280|Loss: 1.0484819412231445:  40%|███▉      | 10279/25880 [2:07:07<3:11:16,  1.36it/s]
1|10280|Loss: 1.0484819412231445:  40%|███▉      | 10280/25880 [2:07:07<3:15:39,  1.33it/s]
1|10281|Loss: 0.8391000628471375:  40%|███▉      | 10280/25880 [2:07:08<3:15:39,  1.33it/s]
1|10281|Loss: 0.8391000628471375:  40%|███▉      | 10281/25880 [2:07:08<3:05:49,  1.40it/s]
1|10282|Loss: 0.968544065952301:  40%|███▉      | 10281/25880 [2:07:08<3:05:49,  1.40it/s] 
1|10282|Loss: 0.968544065952301:  40%|███▉      | 10282/25880 [2:07:09<3:02:44,  1.42it/s]
1|10283|Loss: 0.8182010650634766:  40%|███▉      | 10282/25880 [2:07:09<3:02:44,  1.42it/s]
1|10283|Loss: 0.8182010650634766:  40%|███▉      | 10283/25880 [2:07:09<2:56:41,  1.47it/s]
1|10284|Loss: 0.8320242166519165:  40%|███▉      | 10283/25880 [2:07:10<2:56:41,  1.47it/s]
1|10284|Loss: 0.8320242166519165:  40%|███▉      | 10284/25880 [2:07:10<2:52:02,  1.51it/s]
1|10285|Loss: 0.837337851524353:  40%|███▉      | 10284/25880 [2:07:10<2:52:02,  1.51it/s] 
1|10285|Loss: 0.837337851524353:  40%|███▉      | 10285/25880 [2:07:11<3:09:55,  1.37it/s]
1|10286|Loss: 0.689116895198822:  40%|███▉      | 10285/25880 [2:07:11<3:09:55,  1.37it/s]
1|10286|Loss: 0.689116895198822:  40%|███▉      | 10286/25880 [2:07:12<3:11:09,  1.36it/s]
1|10287|Loss: 0.8451111912727356:  40%|███▉      | 10286/25880 [2:07:12<3:11:09,  1.36it/s]
1|10287|Loss: 0.8451111912727356:  40%|███▉      | 10287/25880 [2:07:12<3:09:56,  1.37it/s]
1|10288|Loss: 0.8235631585121155:  40%|███▉      | 10287/25880 [2:07:13<3:09:56,  1.37it/s]
1|10288|Loss: 0.8235631585121155:  40%|███▉      | 10288/25880 [2:07:13<3:10:38,  1.36it/s]
1|10289|Loss: 0.8679100275039673:  40%|███▉      | 10288/25880 [2:07:13<3:10:38,  1.36it/s]
1|10289|Loss: 0.8679100275039673:  40%|███▉      | 10289/25880 [2:07:14<3:04:11,  1.41it/s]
1|10290|Loss: 0.822590708732605:  40%|███▉      | 10289/25880 [2:07:14<3:04:11,  1.41it/s] 
1|10290|Loss: 0.822590708732605:  40%|███▉      | 10290/25880 [2:07:15<3:15:45,  1.33it/s]
1|10291|Loss: 0.9518864154815674:  40%|███▉      | 10290/25880 [2:07:15<3:15:45,  1.33it/s]
1|10291|Loss: 0.9518864154815674:  40%|███▉      | 10291/25880 [2:07:15<3:24:09,  1.27it/s]
1|10292|Loss: 0.8773317933082581:  40%|███▉      | 10291/25880 [2:07:16<3:24:09,  1.27it/s]
1|10292|Loss: 0.8773317933082581:  40%|███▉      | 10292/25880 [2:07:16<3:28:38,  1.25it/s]
1|10293|Loss: 0.8967962265014648:  40%|███▉      | 10292/25880 [2:07:17<3:28:38,  1.25it/s]
1|10293|Loss: 0.8967962265014648:  40%|███▉      | 10293/25880 [2:07:17<3:23:10,  1.28it/s]
1|10294|Loss: 0.9139763116836548:  40%|���██▉      | 10293/25880 [2:07:17<3:23:10,  1.28it/s]
1|10294|Loss: 0.9139763116836548:  40%|███▉      | 10294/25880 [2:07:18<3:27:10,  1.25it/s]
1|10295|Loss: 0.8167004585266113:  40%|███▉      | 10294/25880 [2:07:18<3:27:10,  1.25it/s]
1|10295|Loss: 0.8167004585266113:  40%|███▉      | 10295/25880 [2:07:19<3:25:24,  1.26it/s]
1|10296|Loss: 0.8400797247886658:  40%|███▉      | 10295/25880 [2:07:19<3:25:24,  1.26it/s]
1|10296|Loss: 0.8400797247886658:  40%|███▉      | 10296/25880 [2:07:19<3:29:34,  1.24it/s]
1|10297|Loss: 0.7133346796035767:  40%|███▉      | 10296/25880 [2:07:20<3:29:34,  1.24it/s]
1|10297|Loss: 0.7133346796035767:  40%|███▉      | 10297/25880 [2:07:20<3:30:29,  1.23it/s]
1|10298|Loss: 0.7517893314361572:  40%|███▉      | 10297/25880 [2:07:21<3:30:29,  1.23it/s]
1|10298|Loss: 0.7517893314361572:  40%|███▉      | 10298/25880 [2:07:21<3:07:38,  1.38it/s]
1|10299|Loss: 0.7783530354499817:  40%|███▉      | 10298/25880 [2:07:21<3:07:38,  1.38it/s]
1|10299|Loss: 0.7783530354499817:  40%|███▉      | 10299/25880 [2:07:21<3:03:47,  1.41it/s]
1|10300|Loss: 0.9370713233947754:  40%|███▉      | 10299/25880 [2:07:22<3:03:47,  1.41it/s]
1|10300|Loss: 0.9370713233947754:  40%|███▉      | 10300/25880 [2:07:22<3:09:07,  1.37it/s]
1|10301|Loss: 0.7053219676017761:  40%|███▉      | 10300/25880 [2:07:23<3:09:07,  1.37it/s]
1|10301|Loss: 0.7053219676017761:  40%|███▉      | 10301/25880 [2:07:23<3:15:16,  1.33it/s]
1|10302|Loss: 0.8178074359893799:  40%|███▉      | 10301/25880 [2:07:23<3:15:16,  1.33it/s]
1|10302|Loss: 0.8178074359893799:  40%|███▉      | 10302/25880 [2:07:24<3:22:36,  1.28it/s]
1|10303|Loss: 0.8076661229133606:  40%|███▉      | 10302/25880 [2:07:24<3:22:36,  1.28it/s]
1|10303|Loss: 0.8076661229133606:  40%|███▉      | 10303/25880 [2:07:25<3:28:40,  1.24it/s]
1|10304|Loss: 0.9723012447357178:  40%|███▉      | 10303/25880 [2:07:25<3:28:40,  1.24it/s]
1|10304|Loss: 0.9723012447357178:  40%|███▉      | 10304/25880 [2:07:25<3:24:44,  1.27it/s]
1|10305|Loss: 0.9987488985061646:  40%|███▉      | 10304/25880 [2:07:26<3:24:44,  1.27it/s]
1|10305|Loss: 0.9987488985061646:  40%|███▉      | 10305/25880 [2:07:26<3:19:45,  1.30it/s]
1|10306|Loss: 0.7391132712364197:  40%|███▉      | 10305/25880 [2:07:27<3:19:45,  1.30it/s]
1|10306|Loss: 0.7391132712364197:  40%|███▉      | 10306/25880 [2:07:27<3:28:39,  1.24it/s]
1|10307|Loss: 0.871455192565918:  40%|███▉      | 10306/25880 [2:07:28<3:28:39,  1.24it/s] 
1|10307|Loss: 0.871455192565918:  40%|███▉      | 10307/25880 [2:07:28<3:25:33,  1.26it/s]
1|10308|Loss: 0.9004745483398438:  40%|███▉      | 10307/25880 [2:07:28<3:25:33,  1.26it/s]
1|10308|Loss: 0.9004745483398438:  40%|███▉      | 10308/25880 [2:07:29<3:25:09,  1.27it/s]
1|10309|Loss: 0.9617986083030701:  40%|███▉      | 10308/25880 [2:07:29<3:25:09,  1.27it/s]
1|10309|Loss: 0.9617986083030701:  40%|███▉      | 10309/25880 [2:07:29<3:21:18,  1.29it/s]
1|10310|Loss: 0.7710604071617126:  40%|███▉      | 10309/25880 [2:07:30<3:21:18,  1.29it/s]
1|10310|Loss: 0.7710604071617126:  40%|███▉      | 10310/25880 [2:07:30<3:16:02,  1.32it/s]
1|10311|Loss: 0.8124435544013977:  40%|███▉      | 10310/25880 [2:07:31<3:16:02,  1.32it/s]
1|10311|Loss: 0.8124435544013977:  40%|███▉      | 10311/25880 [2:07:31<3:21:23,  1.29it/s]
1|10312|Loss: 0.8229720592498779:  40%|███▉      | 10311/25880 [2:07:31<3:21:23,  1.29it/s]
1|10312|Loss: 0.8229720592498779:  40%|███▉      | 10312/25880 [2:07:32<3:23:29,  1.28it/s]
1|10313|Loss: 0.8400835990905762:  40%|███▉      | 10312/25880 [2:07:32<3:23:29,  1.28it/s]
1|10313|Loss: 0.8400835990905762:  40%|███▉      | 10313/25880 [2:07:32<3:13:01,  1.34it/s]
1|10314|Loss: 0.8812939524650574:  40%|███▉      | 10313/25880 [2:07:33<3:13:01,  1.34it/s]
1|10314|Loss: 0.8812939524650574:  40%|███▉      | 10314/25880 [2:07:33<3:07:53,  1.38it/s]
1|10315|Loss: 0.8297793865203857:  40%|███▉      | 10314/25880 [2:07:34<3:07:53,  1.38it/s]
1|10315|Loss: 0.8297793865203857:  40%|███▉      | 10315/25880 [2:07:34<3:20:12,  1.30it/s]
1|10316|Loss: 0.9568015933036804:  40%|███▉      | 10315/25880 [2:07:34<3:20:12,  1.30it/s]
1|10316|Loss: 0.9568015933036804:  40%|███▉      | 10316/25880 [2:07:35<3:10:43,  1.36it/s]
1|10317|Loss: 0.8956845998764038:  40%|███▉      | 10316/25880 [2:07:35<3:10:43,  1.36it/s]
1|10317|Loss: 0.8956845998764038:  40%|███▉      | 10317/25880 [2:07:35<3:16:29,  1.32it/s]
1|10318|Loss: 0.7116650342941284:  40%|███▉      | 10317/25880 [2:07:36<3:16:29,  1.32it/s]
1|10318|Loss: 0.7116650342941284:  40%|███▉      | 10318/25880 [2:07:36<3:28:23,  1.24it/s]
1|10319|Loss: 0.7362408638000488:  40%|███▉      | 10318/25880 [2:07:37<3:28:23,  1.24it/s]
1|10319|Loss: 0.7362408638000488:  40%|███▉      | 10319/25880 [2:07:37<3:30:13,  1.23it/s]
1|10320|Loss: 0.7198376059532166:  40%|███▉      | 10319/25880 [2:07:38<3:30:13,  1.23it/s]
1|10320|Loss: 0.7198376059532166:  40%|███▉      | 10320/25880 [2:07:38<3:32:58,  1.22it/s]
1|10321|Loss: 0.7576054334640503:  40%|███▉      | 10320/25880 [2:07:38<3:32:58,  1.22it/s]
1|10321|Loss: 0.7576054334640503:  40%|███▉      | 10321/25880 [2:07:39<3:39:44,  1.18it/s]
1|10322|Loss: 0.9507309198379517:  40%|███▉      | 10321/25880 [2:07:39<3:39:44,  1.18it/s]
1|10322|Loss: 0.9507309198379517:  40%|███▉      | 10322/25880 [2:07:40<3:40:58,  1.17it/s]
1|10323|Loss: 0.848440945148468:  40%|███▉      | 10322/25880 [2:07:40<3:40:58,  1.17it/s] 
1|10323|Loss: 0.848440945148468:  40%|███▉      | 10323/25880 [2:07:41<3:37:45,  1.19it/s]
1|10324|Loss: 0.8840122222900391:  40%|███▉      | 10323/25880 [2:07:41<3:37:45,  1.19it/s]
1|10324|Loss: 0.8840122222900391:  40%|███▉      | 10324/25880 [2:07:41<3:37:33,  1.19it/s]
1|10325|Loss: 0.8566925525665283:  40%|███▉      | 10324/25880 [2:07:42<3:37:33,  1.19it/s]
1|10325|Loss: 0.8566925525665283:  40%|███▉      | 10325/25880 [2:07:42<3:32:15,  1.22it/s]
1|10326|Loss: 1.013071060180664:  40%|███▉      | 10325/25880 [2:07:43<3:32:15,  1.22it/s] 
1|10326|Loss: 1.013071060180664:  40%|███▉      | 10326/25880 [2:07:43<3:26:10,  1.26it/s]
1|10327|Loss: 0.9249544143676758:  40%|███▉      | 10326/25880 [2:07:43<3:26:10,  1.26it/s]
1|10327|Loss: 0.9249544143676758:  40%|███▉      | 10327/25880 [2:07:44<3:21:57,  1.28it/s]
1|10328|Loss: 0.8147034049034119:  40%|███▉      | 10327/25880 [2:07:44<3:21:57,  1.28it/s]
1|10328|Loss: 0.8147034049034119:  40%|███▉      | 10328/25880 [2:07:44<3:19:43,  1.30it/s]
1|10329|Loss: 0.7443974614143372:  40%|███▉      | 10328/25880 [2:07:45<3:19:43,  1.30it/s]
1|10329|Loss: 0.7443974614143372:  40%|███▉      | 10329/25880 [2:07:45<3:18:08,  1.31it/s]
1|10330|Loss: 0.8267355561256409:  40%|███▉      | 10329/25880 [2:07:46<3:18:08,  1.31it/s]
1|10330|Loss: 0.8267355561256409:  40%|███▉      | 10330/25880 [2:07:46<3:15:32,  1.33it/s]
1|10331|Loss: 0.815679669380188:  40%|███▉      | 10330/25880 [2:07:46<3:15:32,  1.33it/s] 
1|10331|Loss: 0.815679669380188:  40%|███▉      | 10331/25880 [2:07:47<3:14:10,  1.33it/s]
1|10332|Loss: 0.8187270760536194:  40%|███▉      | 10331/25880 [2:07:47<3:14:10,  1.33it/s]
1|10332|Loss: 0.8187270760536194:  40%|███▉      | 10332/25880 [2:07:47<3:11:38,  1.35it/s]
1|10333|Loss: 0.8391966223716736:  40%|███▉      | 10332/25880 [2:07:48<3:11:38,  1.35it/s]
1|10333|Loss: 0.8391966223716736:  40%|███▉      | 10333/25880 [2:07:48<3:04:51,  1.40it/s]
1|10334|Loss: 0.980035662651062:  40%|███▉      | 10333/25880 [2:07:48<3:04:51,  1.40it/s] 
1|10334|Loss: 0.980035662651062:  40%|███▉      | 10334/25880 [2:07:49<2:57:57,  1.46it/s]
1|10335|Loss: 0.9321838617324829:  40%|███▉      | 10334/25880 [2:07:49<2:57:57,  1.46it/s]
1|10335|Loss: 0.9321838617324829:  40%|███▉      | 10335/25880 [2:07:49<2:58:09,  1.45it/s]
1|10336|Loss: 0.970720648765564:  40%|███▉      | 10335/25880 [2:07:50<2:58:09,  1.45it/s] 
1|10336|Loss: 0.970720648765564:  40%|███▉      | 10336/25880 [2:07:50<2:54:00,  1.49it/s]
1|10337|Loss: 0.7346009016036987:  40%|███▉      | 10336/25880 [2:07:50<2:54:00,  1.49it/s]
1|10337|Loss: 0.7346009016036987:  40%|███▉      | 10337/25880 [2:07:51<3:03:06,  1.41it/s]
1|10338|Loss: 0.7761312127113342:  40%|███▉      | 10337/25880 [2:07:51<3:03:06,  1.41it/s]
1|10338|Loss: 0.7761312127113342:  40%|███▉      | 10338/25880 [2:07:51<3:04:11,  1.41it/s]
1|10339|Loss: 0.9744546413421631:  40%|███▉      | 10338/25880 [2:07:52<3:04:11,  1.41it/s]
1|10339|Loss: 0.9744546413421631:  40%|███▉      | 10339/25880 [2:07:52<3:10:48,  1.36it/s]
1|10340|Loss: 0.9184779524803162:  40%|███▉      | 10339/25880 [2:07:53<3:10:48,  1.36it/s]
1|10340|Loss: 0.9184779524803162:  40%|███▉      | 10340/25880 [2:07:53<3:22:54,  1.28it/s]
1|10341|Loss: 0.9577021598815918:  40%|███▉      | 10340/25880 [2:07:54<3:22:54,  1.28it/s]
1|10341|Loss: 0.9577021598815918:  40%|███▉      | 10341/25880 [2:07:54<3:21:32,  1.28it/s]
1|10342|Loss: 0.8458265662193298:  40%|███▉      | 10341/25880 [2:07:54<3:21:32,  1.28it/s]
1|10342|Loss: 0.8458265662193298:  40%|███▉      | 10342/25880 [2:07:55<3:16:15,  1.32it/s]
1|10343|Loss: 0.797278881072998:  40%|███▉      | 10342/25880 [2:07:55<3:16:15,  1.32it/s] 
1|10343|Loss: 0.797278881072998:  40%|███▉      | 10343/25880 [2:07:55<3:14:12,  1.33it/s]
1|10344|Loss: 0.8460758328437805:  40%|███▉      | 10343/25880 [2:07:56<3:14:12,  1.33it/s]
1|10344|Loss: 0.8460758328437805:  40%|███▉      | 10344/25880 [2:07:56<3:19:32,  1.30it/s]
1|10345|Loss: 0.7932127118110657:  40%|███▉      | 10344/25880 [2:07:57<3:19:32,  1.30it/s]
1|10345|Loss: 0.7932127118110657:  40%|███▉      | 10345/25880 [2:07:57<3:18:17,  1.31it/s]
1|10346|Loss: 0.7966153025627136:  40%|███▉      | 10345/25880 [2:07:57<3:18:17,  1.31it/s]
1|10346|Loss: 0.7966153025627136:  40%|███▉      | 10346/25880 [2:07:58<3:16:22,  1.32it/s]
1|10347|Loss: 0.7701944708824158:  40%|███▉      | 10346/25880 [2:07:58<3:16:22,  1.32it/s]
1|10347|Loss: 0.7701944708824158:  40%|███▉      | 10347/25880 [2:07:58<3:15:08,  1.33it/s]
1|10348|Loss: 0.8599000573158264:  40%|███▉      | 10347/25880 [2:07:59<3:15:08,  1.33it/s]
1|10348|Loss: 0.8599000573158264:  40%|███▉      | 10348/25880 [2:07:59<3:13:32,  1.34it/s]
1|10349|Loss: 0.8054917454719543:  40%|███▉      | 10348/25880 [2:08:00<3:13:32,  1.34it/s]
1|10349|Loss: 0.8054917454719543:  40%|███▉      | 10349/25880 [2:08:00<3:06:07,  1.39it/s]
1|10350|Loss: 0.7169688940048218:  40%|███▉      | 10349/25880 [2:08:00<3:06:07,  1.39it/s]
1|10350|Loss: 0.7169688940048218:  40%|███▉      | 10350/25880 [2:08:00<2:56:18,  1.47it/s]
1|10351|Loss: 0.8083593845367432:  40%|███▉      | 10350/25880 [2:08:01<2:56:18,  1.47it/s]
1|10351|Loss: 0.8083593845367432:  40%|███▉      | 10351/25880 [2:08:01<2:58:39,  1.45it/s]
1|10352|Loss: 0.9375929236412048:  40%|███▉      | 10351/25880 [2:08:02<2:58:39,  1.45it/s]
1|10352|Loss: 0.9375929236412048:  40%|████      | 10352/25880 [2:08:02<3:08:36,  1.37it/s]
1|10353|Loss: 0.8535630106925964:  40%|████      | 10352/25880 [2:08:02<3:08:36,  1.37it/s]
1|10353|Loss: 0.8535630106925964:  40%|████      | 10353/25880 [2:08:03<3:21:43,  1.28it/s]
1|10354|Loss: 0.8351579308509827:  40%|████      | 10353/25880 [2:08:03<3:21:43,  1.28it/s]
1|10354|Loss: 0.8351579308509827:  40%|████      | 10354/25880 [2:08:04<3:18:45,  1.30it/s]
1|10355|Loss: 0.8898177742958069:  40%|████      | 10354/25880 [2:08:04<3:18:45,  1.30it/s]
1|10355|Loss: 0.8898177742958069:  40%|████      | 10355/25880 [2:08:04<3:09:17,  1.37it/s]
1|10356|Loss: 0.8304696679115295:  40%|████      | 10355/25880 [2:08:05<3:09:17,  1.37it/s]
1|10356|Loss: 0.8304696679115295:  40%|████      | 10356/25880 [2:08:05<3:08:26,  1.37it/s]
1|10357|Loss: 0.8602533936500549:  40%|████      | 10356/25880 [2:08:05<3:08:26,  1.37it/s]
1|10357|Loss: 0.8602533936500549:  40%|████      | 10357/25880 [2:08:06<3:13:50,  1.33it/s]
1|10358|Loss: 0.8321101665496826:  40%|████      | 10357/25880 [2:08:06<3:13:50,  1.33it/s]
1|10358|Loss: 0.8321101665496826:  40%|████      | 10358/25880 [2:08:06<3:14:23,  1.33it/s]
1|10359|Loss: 0.9016687273979187:  40%|████      | 10358/25880 [2:08:07<3:14:23,  1.33it/s]
1|10359|Loss: 0.9016687273979187:  40%|████      | 10359/25880 [2:08:07<2:59:36,  1.44it/s]
1|10360|Loss: 0.7499039173126221:  40%|████      | 10359/25880 [2:08:07<2:59:36,  1.44it/s]
1|10360|Loss: 0.7499039173126221:  40%|████      | 10360/25880 [2:08:08<2:53:19,  1.49it/s]
1|10361|Loss: 0.80891352891922:  40%|████      | 10360/25880 [2:08:08<2:53:19,  1.49it/s]  
1|10361|Loss: 0.80891352891922:  40%|████      | 10361/25880 [2:08:08<2:51:09,  1.51it/s]
1|10362|Loss: 0.7785918116569519:  40%|████      | 10361/25880 [2:08:09<2:51:09,  1.51it/s]
1|10362|Loss: 0.7785918116569519:  40%|████      | 10362/25880 [2:08:09<2:54:47,  1.48it/s]
1|10363|Loss: 0.8351507186889648:  40%|████      | 10362/25880 [2:08:09<2:54:47,  1.48it/s]
1|10363|Loss: 0.8351507186889648:  40%|████      | 10363/25880 [2:08:10<3:05:17,  1.40it/s]
1|10364|Loss: 0.8132352828979492:  40%|████      | 10363/25880 [2:08:10<3:05:17,  1.40it/s]
1|10364|Loss: 0.8132352828979492:  40%|████      | 10364/25880 [2:08:11<3:16:41,  1.31it/s]
1|10365|Loss: 0.8864526748657227:  40%|████      | 10364/25880 [2:08:11<3:16:41,  1.31it/s]
1|10365|Loss: 0.8864526748657227:  40%|████      | 10365/25880 [2:08:11<3:17:53,  1.31it/s]
1|10366|Loss: 0.878869891166687:  40%|████      | 10365/25880 [2:08:12<3:17:53,  1.31it/s] 
1|10366|Loss: 0.878869891166687:  40%|████      | 10366/25880 [2:08:12<3:15:43,  1.32it/s]
1|10367|Loss: 0.8684390783309937:  40%|████      | 10366/25880 [2:08:13<3:15:43,  1.32it/s]
1|10367|Loss: 0.8684390783309937:  40%|████      | 10367/25880 [2:08:13<3:06:32,  1.39it/s]
1|10368|Loss: 0.9552300572395325:  40%|████      | 10367/25880 [2:08:13<3:06:32,  1.39it/s]
1|10368|Loss: 0.9552300572395325:  40%|████      | 10368/25880 [2:08:14<3:06:31,  1.39it/s]
1|10369|Loss: 0.8814281821250916:  40%|████      | 10368/25880 [2:08:14<3:06:31,  1.39it/s]
1|10369|Loss: 0.8814281821250916:  40%|████      | 10369/25880 [2:08:14<3:07:29,  1.38it/s]
1|10370|Loss: 0.8597850203514099:  40%|████      | 10369/25880 [2:08:15<3:07:29,  1.38it/s]
1|10370|Loss: 0.8597850203514099:  40%|████      | 10370/25880 [2:08:15<3:02:01,  1.42it/s]
1|10371|Loss: 1.0403796434402466:  40%|████      | 10370/25880 [2:08:15<3:02:01,  1.42it/s]
1|10371|Loss: 1.0403796434402466:  40%|████      | 10371/25880 [2:08:16<2:56:52,  1.46it/s]
1|10372|Loss: 0.7964662313461304:  40%|████      | 10371/25880 [2:08:16<2:56:52,  1.46it/s]
1|10372|Loss: 0.7964662313461304:  40%|████      | 10372/25880 [2:08:16<2:50:00,  1.52it/s]
1|10373|Loss: 0.843502938747406:  40%|████      | 10372/25880 [2:08:17<2:50:00,  1.52it/s] 
1|10373|Loss: 0.843502938747406:  40%|████      | 10373/25880 [2:08:17<2:45:05,  1.57it/s]
1|10374|Loss: 0.8924385905265808:  40%|████      | 10373/25880 [2:08:17<2:45:05,  1.57it/s]
1|10374|Loss: 0.8924385905265808:  40%|████      | 10374/25880 [2:08:17<2:44:03,  1.58it/s]
1|10375|Loss: 0.8254491686820984:  40%|████      | 10374/25880 [2:08:18<2:44:03,  1.58it/s]
1|10375|Loss: 0.8254491686820984:  40%|████      | 10375/25880 [2:08:18<2:53:30,  1.49it/s]
1|10376|Loss: 0.892627477645874:  40%|████      | 10375/25880 [2:08:19<2:53:30,  1.49it/s] 
1|10376|Loss: 0.892627477645874:  40%|████      | 10376/25880 [2:08:19<2:50:22,  1.52it/s]
1|10377|Loss: 0.7514875531196594:  40%|████      | 10376/25880 [2:08:19<2:50:22,  1.52it/s]
1|10377|Loss: 0.7514875531196594:  40%|████      | 10377/25880 [2:08:19<2:39:41,  1.62it/s]
1|10378|Loss: 0.9594584107398987:  40%|████      | 10377/25880 [2:08:20<2:39:41,  1.62it/s]
1|10378|Loss: 0.9594584107398987:  40%|████      | 10378/25880 [2:08:20<2:37:45,  1.64it/s]
1|10379|Loss: 0.9019429683685303:  40%|████      | 10378/25880 [2:08:20<2:37:45,  1.64it/s]
1|10379|Loss: 0.9019429683685303:  40%|████      | 10379/25880 [2:08:21<2:39:34,  1.62it/s]
1|10380|Loss: 0.8867413997650146:  40%|████      | 10379/25880 [2:08:21<2:39:34,  1.62it/s]
1|10380|Loss: 0.8867413997650146:  40%|████      | 10380/25880 [2:08:21<2:46:45,  1.55it/s]
1|10381|Loss: 0.9289079308509827:  40%|████      | 10380/25880 [2:08:22<2:46:45,  1.55it/s]
1|10381|Loss: 0.9289079308509827:  40%|████      | 10381/25880 [2:08:22<3:01:54,  1.42it/s]
1|10382|Loss: 0.8684177398681641:  40%|████      | 10381/25880 [2:08:23<3:01:54,  1.42it/s]
1|10382|Loss: 0.8684177398681641:  40%|████      | 10382/25880 [2:08:23<3:21:05,  1.28it/s]
1|10383|Loss: 0.8821401596069336:  40%|████      | 10382/25880 [2:08:23<3:21:05,  1.28it/s]
1|10383|Loss: 0.8821401596069336:  40%|████      | 10383/25880 [2:08:24<3:09:52,  1.36it/s]
1|10384|Loss: 0.7841629981994629:  40%|████      | 10383/25880 [2:08:24<3:09:52,  1.36it/s]
1|10384|Loss: 0.7841629981994629:  40%|████      | 10384/25880 [2:08:24<3:10:10,  1.36it/s]
1|10385|Loss: 0.8682847023010254:  40%|████      | 10384/25880 [2:08:25<3:10:10,  1.36it/s]
1|10385|Loss: 0.8682847023010254:  40%|████      | 10385/25880 [2:08:25<3:25:29,  1.26it/s]
1|10386|Loss: 0.846408486366272:  40%|████      | 10385/25880 [2:08:26<3:25:29,  1.26it/s] 
1|10386|Loss: 0.846408486366272:  40%|████      | 10386/25880 [2:08:26<3:18:51,  1.30it/s]
1|10387|Loss: 0.8363637924194336:  40%|████      | 10386/25880 [2:08:26<3:18:51,  1.30it/s]
1|10387|Loss: 0.8363637924194336:  40%|████      | 10387/25880 [2:08:27<3:12:33,  1.34it/s]
1|10388|Loss: 0.7981563210487366:  40%|████      | 10387/25880 [2:08:27<3:12:33,  1.34it/s]
1|10388|Loss: 0.7981563210487366:  40%|████      | 10388/25880 [2:08:27<3:10:30,  1.36it/s]
1|10389|Loss: 0.898292601108551:  40%|████      | 10388/25880 [2:08:28<3:10:30,  1.36it/s] 
1|10389|Loss: 0.898292601108551:  40%|████      | 10389/25880 [2:08:28<2:52:21,  1.50it/s]
1|10390|Loss: 0.9438185691833496:  40%|████      | 10389/25880 [2:08:28<2:52:21,  1.50it/s]
1|10390|Loss: 0.9438185691833496:  40%|████      | 10390/25880 [2:08:29<3:00:23,  1.43it/s]
1|10391|Loss: 0.8995605707168579:  40%|████      | 10390/25880 [2:08:29<3:00:23,  1.43it/s]
1|10391|Loss: 0.8995605707168579:  40%|████      | 10391/25880 [2:08:29<2:55:54,  1.47it/s]
1|10392|Loss: 0.9378176331520081:  40%|████      | 10391/25880 [2:08:30<2:55:54,  1.47it/s]
1|10392|Loss: 0.9378176331520081:  40%|████      | 10392/25880 [2:08:30<2:55:25,  1.47it/s]
1|10393|Loss: 0.8395161032676697:  40%|████      | 10392/25880 [2:08:30<2:55:25,  1.47it/s]
1|10393|Loss: 0.8395161032676697:  40%|████      | 10393/25880 [2:08:31<2:53:01,  1.49it/s]
1|10394|Loss: 0.7507719397544861:  40%|████      | 10393/25880 [2:08:31<2:53:01,  1.49it/s]
1|10394|Loss: 0.7507719397544861:  40%|████      | 10394/25880 [2:08:31<2:43:58,  1.57it/s]
1|10395|Loss: 0.8056078553199768:  40%|████      | 10394/25880 [2:08:32<2:43:58,  1.57it/s]
1|10395|Loss: 0.8056078553199768:  40%|████      | 10395/25880 [2:08:32<2:47:50,  1.54it/s]
1|10396|Loss: 0.7675676941871643:  40%|████      | 10395/25880 [2:08:32<2:47:50,  1.54it/s]
1|10396|Loss: 0.7675676941871643:  40%|████      | 10396/25880 [2:08:33<2:48:13,  1.53it/s]
1|10397|Loss: 0.7044029831886292:  40%|████      | 10396/25880 [2:08:33<2:48:13,  1.53it/s]
1|10397|Loss: 0.7044029831886292:  40%|████      | 10397/25880 [2:08:33<2:43:12,  1.58it/s]
1|10398|Loss: 0.8611115217208862:  40%|████      | 10397/25880 [2:08:33<2:43:12,  1.58it/s]
1|10398|Loss: 0.8611115217208862:  40%|████      | 10398/25880 [2:08:34<2:36:07,  1.65it/s]
1|10399|Loss: 0.7345782518386841:  40%|████      | 10398/25880 [2:08:34<2:36:07,  1.65it/s]
1|10399|Loss: 0.7345782518386841:  40%|████      | 10399/25880 [2:08:34<2:31:47,  1.70it/s]
1|10400|Loss: 0.9452913403511047:  40%|████      | 10399/25880 [2:08:35<2:31:47,  1.70it/s]
1|10400|Loss: 0.9452913403511047:  40%|████      | 10400/25880 [2:08:35<2:41:23,  1.60it/s]
1|10401|Loss: 0.7865736484527588:  40%|████      | 10400/25880 [2:08:35<2:41:23,  1.60it/s]
1|10401|Loss: 0.7865736484527588:  40%|████      | 10401/25880 [2:08:36<3:02:20,  1.41it/s]
1|10402|Loss: 0.7726986408233643:  40%|████      | 10401/25880 [2:08:36<3:02:20,  1.41it/s]
1|10402|Loss: 0.7726986408233643:  40%|████      | 10402/25880 [2:08:37<3:25:12,  1.26it/s]
1|10403|Loss: 0.709560751914978:  40%|████      | 10402/25880 [2:08:37<3:25:12,  1.26it/s] 
1|10403|Loss: 0.709560751914978:  40%|████      | 10403/25880 [2:08:38<3:32:41,  1.21it/s]
1|10404|Loss: 0.7863606214523315:  40%|████      | 10403/25880 [2:08:38<3:32:41,  1.21it/s]
1|10404|Loss: 0.7863606214523315:  40%|████      | 10404/25880 [2:08:39<3:25:43,  1.25it/s]
1|10405|Loss: 0.8635463714599609:  40%|████      | 10404/25880 [2:08:39<3:25:43,  1.25it/s]
1|10405|Loss: 0.8635463714599609:  40%|████      | 10405/25880 [2:08:39<3:10:29,  1.35it/s]
1|10406|Loss: 0.9063184261322021:  40%|████      | 10405/25880 [2:08:39<3:10:29,  1.35it/s]
1|10406|Loss: 0.9063184261322021:  40%|████      | 10406/25880 [2:08:40<3:00:07,  1.43it/s]
1|10407|Loss: 0.822597324848175:  40%|████      | 10406/25880 [2:08:40<3:00:07,  1.43it/s] 
1|10407|Loss: 0.822597324848175:  40%|████      | 10407/25880 [2:08:40<3:00:55,  1.43it/s]
1|10408|Loss: 0.8430782556533813:  40%|████      | 10407/25880 [2:08:41<3:00:55,  1.43it/s]
1|10408|Loss: 0.8430782556533813:  40%|████      | 10408/25880 [2:08:41<3:03:11,  1.41it/s]
1|10409|Loss: 0.9040300846099854:  40%|████      | 10408/25880 [2:08:42<3:03:11,  1.41it/s]
1|10409|Loss: 0.9040300846099854:  40%|████      | 10409/25880 [2:08:42<3:05:21,  1.39it/s]
1|10410|Loss: 0.8915054798126221:  40%|████      | 10409/25880 [2:08:42<3:05:21,  1.39it/s]
1|10410|Loss: 0.8915054798126221:  40%|████      | 10410/25880 [2:08:43<3:18:21,  1.30it/s]
1|10411|Loss: 0.783049464225769:  40%|████      | 10410/25880 [2:08:43<3:18:21,  1.30it/s] 
1|10411|Loss: 0.783049464225769:  40%|████      | 10411/25880 [2:08:44<3:19:14,  1.29it/s]
1|10412|Loss: 0.8019054532051086:  40%|████      | 10411/25880 [2:08:44<3:19:14,  1.29it/s]
1|10412|Loss: 0.8019054532051086:  40%|████      | 10412/25880 [2:08:44<3:22:47,  1.27it/s]
1|10413|Loss: 0.8094488978385925:  40%|████      | 10412/25880 [2:08:45<3:22:47,  1.27it/s]
1|10413|Loss: 0.8094488978385925:  40%|████      | 10413/25880 [2:08:45<3:27:11,  1.24it/s]
1|10414|Loss: 0.8493136167526245:  40%|████      | 10413/25880 [2:08:46<3:27:11,  1.24it/s]
1|10414|Loss: 0.8493136167526245:  40%|████      | 10414/25880 [2:08:46<3:28:06,  1.24it/s]
1|10415|Loss: 1.0142189264297485:  40%|████      | 10414/25880 [2:08:46<3:28:06,  1.24it/s]
1|10415|Loss: 1.0142189264297485:  40%|████      | 10415/25880 [2:08:47<3:26:41,  1.25it/s]
1|10416|Loss: 0.8290631175041199:  40%|████      | 10415/25880 [2:08:47<3:26:41,  1.25it/s]
1|10416|Loss: 0.8290631175041199:  40%|████      | 10416/25880 [2:08:47<3:15:00,  1.32it/s]
1|10417|Loss: 0.8070656061172485:  40%|████      | 10416/25880 [2:08:48<3:15:00,  1.32it/s]
1|10417|Loss: 0.8070656061172485:  40%|████      | 10417/25880 [2:08:48<3:02:05,  1.42it/s]
1|10418|Loss: 0.7660996913909912:  40%|████      | 10417/25880 [2:08:49<3:02:05,  1.42it/s]
1|10418|Loss: 0.7660996913909912:  40%|████      | 10418/25880 [2:08:49<3:15:30,  1.32it/s]
1|10419|Loss: 0.7639100551605225:  40%|████      | 10418/25880 [2:08:49<3:15:30,  1.32it/s]
1|10419|Loss: 0.7639100551605225:  40%|████      | 10419/25880 [2:08:50<3:09:54,  1.36it/s]
1|10420|Loss: 0.8925907611846924:  40%|████      | 10419/25880 [2:08:50<3:09:54,  1.36it/s]
1|10420|Loss: 0.8925907611846924:  40%|████      | 10420/25880 [2:08:50<3:00:54,  1.42it/s]
1|10421|Loss: 0.9060420393943787:  40%|████      | 10420/25880 [2:08:51<3:00:54,  1.42it/s]
1|10421|Loss: 0.9060420393943787:  40%|████      | 10421/25880 [2:08:51<3:05:11,  1.39it/s]
1|10422|Loss: 0.9252684712409973:  40%|████      | 10421/25880 [2:08:51<3:05:11,  1.39it/s]
1|10422|Loss: 0.9252684712409973:  40%|████      | 10422/25880 [2:08:52<3:10:52,  1.35it/s]
1|10423|Loss: 0.40535643696784973:  40%|████      | 10422/25880 [2:08:52<3:10:52,  1.35it/s]
1|10423|Loss: 0.40535643696784973:  40%|████      | 10423/25880 [2:08:53<3:33:38,  1.21it/s]
1|10424|Loss: 0.7517001032829285:  40%|████      | 10423/25880 [2:08:53<3:33:38,  1.21it/s] 
1|10424|Loss: 0.7517001032829285:  40%|████      | 10424/25880 [2:08:54<3:35:51,  1.19it/s]
1|10425|Loss: 0.8770255446434021:  40%|████      | 10424/25880 [2:08:54<3:35:51,  1.19it/s]
1|10425|Loss: 0.8770255446434021:  40%|████      | 10425/25880 [2:08:55<3:33:05,  1.21it/s]
1|10426|Loss: 0.8200145363807678:  40%|████      | 10425/25880 [2:08:55<3:33:05,  1.21it/s]
1|10426|Loss: 0.8200145363807678:  40%|████      | 10426/25880 [2:08:55<3:31:13,  1.22it/s]
1|10427|Loss: 0.746334433555603:  40%|████      | 10426/25880 [2:08:56<3:31:13,  1.22it/s] 
1|10427|Loss: 0.746334433555603:  40%|████      | 10427/25880 [2:08:56<3:11:47,  1.34it/s]
1|10428|Loss: 0.9057236909866333:  40%|████      | 10427/25880 [2:08:56<3:11:47,  1.34it/s]
1|10428|Loss: 0.9057236909866333:  40%|████      | 10428/25880 [2:08:57<3:13:09,  1.33it/s]
1|10429|Loss: 0.8784361481666565:  40%|████      | 10428/25880 [2:08:57<3:13:09,  1.33it/s]
1|10429|Loss: 0.8784361481666565:  40%|████      | 10429/25880 [2:08:58<3:46:46,  1.14it/s]
1|10430|Loss: 0.7367981672286987:  40%|████      | 10429/25880 [2:08:58<3:46:46,  1.14it/s]
1|10430|Loss: 0.7367981672286987:  40%|████      | 10430/25880 [2:08:59<3:56:10,  1.09it/s]
1|10431|Loss: 0.7146251201629639:  40%|████      | 10430/25880 [2:08:59<3:56:10,  1.09it/s]
1|10431|Loss: 0.7146251201629639:  40%|████      | 10431/25880 [2:09:00<3:52:19,  1.11it/s]
1|10432|Loss: 0.9492605328559875:  40%|████      | 10431/25880 [2:09:00<3:52:19,  1.11it/s]
1|10432|Loss: 0.9492605328559875:  40%|████      | 10432/25880 [2:09:00<3:40:01,  1.17it/s]
1|10433|Loss: 1.0150291919708252:  40%|████      | 10432/25880 [2:09:01<3:40:01,  1.17it/s]
1|10433|Loss: 1.0150291919708252:  40%|████      | 10433/25880 [2:09:01<3:24:45,  1.26it/s]
1|10434|Loss: 0.9017689228057861:  40%|████      | 10433/25880 [2:09:02<3:24:45,  1.26it/s]
1|10434|Loss: 0.9017689228057861:  40%|████      | 10434/25880 [2:09:02<3:25:28,  1.25it/s]
1|10435|Loss: 0.986312985420227:  40%|████      | 10434/25880 [2:09:02<3:25:28,  1.25it/s] 
1|10435|Loss: 0.986312985420227:  40%|████      | 10435/25880 [2:09:03<3:27:04,  1.24it/s]
1|10436|Loss: 0.8698233962059021:  40%|████      | 10435/25880 [2:09:03<3:27:04,  1.24it/s]
1|10436|Loss: 0.8698233962059021:  40%|████      | 10436/25880 [2:09:03<3:22:02,  1.27it/s]
1|10437|Loss: 0.8619950413703918:  40%|████      | 10436/25880 [2:09:04<3:22:02,  1.27it/s]
1|10437|Loss: 0.8619950413703918:  40%|████      | 10437/25880 [2:09:04<3:17:13,  1.30it/s]
1|10438|Loss: 0.8972393870353699:  40%|████      | 10437/25880 [2:09:05<3:17:13,  1.30it/s]
1|10438|Loss: 0.8972393870353699:  40%|████      | 10438/25880 [2:09:05<3:06:51,  1.38it/s]
1|10439|Loss: 0.7922801375389099:  40%|████      | 10438/25880 [2:09:05<3:06:51,  1.38it/s]
1|10439|Loss: 0.7922801375389099:  40%|████      | 10439/25880 [2:09:05<2:59:36,  1.43it/s]
1|10440|Loss: 0.8358069658279419:  40%|████      | 10439/25880 [2:09:06<2:59:36,  1.43it/s]
1|10440|Loss: 0.8358069658279419:  40%|████      | 10440/25880 [2:09:06<3:07:07,  1.38it/s]
1|10441|Loss: 0.7174661755561829:  40%|████      | 10440/25880 [2:09:07<3:07:07,  1.38it/s]
1|10441|Loss: 0.7174661755561829:  40%|████      | 10441/25880 [2:09:07<3:09:20,  1.36it/s]
1|10442|Loss: 0.8864290118217468:  40%|████      | 10441/25880 [2:09:07<3:09:20,  1.36it/s]
1|10442|Loss: 0.8864290118217468:  40%|████      | 10442/25880 [2:09:08<3:02:41,  1.41it/s]
1|10443|Loss: 0.790062665939331:  40%|████      | 10442/25880 [2:09:08<3:02:41,  1.41it/s] 
1|10443|Loss: 0.790062665939331:  40%|████      | 10443/25880 [2:09:08<3:02:49,  1.41it/s]
1|10444|Loss: 0.8448015451431274:  40%|████      | 10443/25880 [2:09:09<3:02:49,  1.41it/s]
1|10444|Loss: 0.8448015451431274:  40%|████      | 10444/25880 [2:09:09<3:10:55,  1.35it/s]
1|10445|Loss: 0.7864181995391846:  40%|████      | 10444/25880 [2:09:10<3:10:55,  1.35it/s]
1|10445|Loss: 0.7864181995391846:  40%|████      | 10445/25880 [2:09:10<3:20:02,  1.29it/s]
1|10446|Loss: 0.7979898452758789:  40%|████      | 10445/25880 [2:09:11<3:20:02,  1.29it/s]
1|10446|Loss: 0.7979898452758789:  40%|████      | 10446/25880 [2:09:11<3:27:44,  1.24it/s]
1|10447|Loss: 0.8157191872596741:  40%|████      | 10446/25880 [2:09:11<3:27:44,  1.24it/s]
1|10447|Loss: 0.8157191872596741:  40%|████      | 10447/25880 [2:09:12<3:17:22,  1.30it/s]
1|10448|Loss: 0.7572891116142273:  40%|████      | 10447/25880 [2:09:12<3:17:22,  1.30it/s]
1|10448|Loss: 0.7572891116142273:  40%|████      | 10448/25880 [2:09:12<3:13:12,  1.33it/s]
1|10449|Loss: 0.7834063172340393:  40%|████      | 10448/25880 [2:09:13<3:13:12,  1.33it/s]
1|10449|Loss: 0.7834063172340393:  40%|████      | 10449/25880 [2:09:13<3:13:00,  1.33it/s]
1|10450|Loss: 0.9027811884880066:  40%|████      | 10449/25880 [2:09:14<3:13:00,  1.33it/s]
1|10450|Loss: 0.9027811884880066:  40%|████      | 10450/25880 [2:09:14<3:24:30,  1.26it/s]
1|10451|Loss: 0.8275696039199829:  40%|████      | 10450/25880 [2:09:14<3:24:30,  1.26it/s]
1|10451|Loss: 0.8275696039199829:  40%|████      | 10451/25880 [2:09:15<3:22:43,  1.27it/s]
1|10452|Loss: 0.9098838567733765:  40%|████      | 10451/25880 [2:09:15<3:22:43,  1.27it/s]
1|10452|Loss: 0.9098838567733765:  40%|████      | 10452/25880 [2:09:15<3:16:33,  1.31it/s]
1|10453|Loss: 0.7342629432678223:  40%|████      | 10452/25880 [2:09:16<3:16:33,  1.31it/s]
1|10453|Loss: 0.7342629432678223:  40%|████      | 10453/25880 [2:09:16<3:13:30,  1.33it/s]
1|10454|Loss: 0.7952855229377747:  40%|████      | 10453/25880 [2:09:16<3:13:30,  1.33it/s]
1|10454|Loss: 0.7952855229377747:  40%|████      | 10454/25880 [2:09:17<2:54:02,  1.48it/s]
1|10455|Loss: 0.9361050128936768:  40%|████      | 10454/25880 [2:09:17<2:54:02,  1.48it/s]
1|10455|Loss: 0.9361050128936768:  40%|████      | 10455/25880 [2:09:17<2:52:12,  1.49it/s]
1|10456|Loss: 0.8624412417411804:  40%|████      | 10455/25880 [2:09:18<2:52:12,  1.49it/s]
1|10456|Loss: 0.8624412417411804:  40%|████      | 10456/25880 [2:09:18<3:04:21,  1.39it/s]
1|10457|Loss: 0.7266185283660889:  40%|████      | 10456/25880 [2:09:19<3:04:21,  1.39it/s]
1|10457|Loss: 0.7266185283660889:  40%|████      | 10457/25880 [2:09:19<3:14:58,  1.32it/s]
1|10458|Loss: 0.6293669939041138:  40%|████      | 10457/25880 [2:09:19<3:14:58,  1.32it/s]
1|10458|Loss: 0.6293669939041138:  40%|████      | 10458/25880 [2:09:20<3:18:10,  1.30it/s]
1|10459|Loss: 0.8651193976402283:  40%|████      | 10458/25880 [2:09:20<3:18:10,  1.30it/s]
1|10459|Loss: 0.8651193976402283:  40%|████      | 10459/25880 [2:09:20<3:10:12,  1.35it/s]
1|10460|Loss: 0.8460851311683655:  40%|████      | 10459/25880 [2:09:21<3:10:12,  1.35it/s]
1|10460|Loss: 0.8460851311683655:  40%|████      | 10460/25880 [2:09:21<3:00:56,  1.42it/s]
1|10461|Loss: 0.9045047760009766:  40%|████      | 10460/25880 [2:09:21<3:00:56,  1.42it/s]
1|10461|Loss: 0.9045047760009766:  40%|████      | 10461/25880 [2:09:22<3:01:05,  1.42it/s]
1|10462|Loss: 0.7315645813941956:  40%|████      | 10461/25880 [2:09:22<3:01:05,  1.42it/s]
1|10462|Loss: 0.7315645813941956:  40%|████      | 10462/25880 [2:09:23<3:19:02,  1.29it/s]
1|10463|Loss: 0.9741002321243286:  40%|████      | 10462/25880 [2:09:23<3:19:02,  1.29it/s]
1|10463|Loss: 0.9741002321243286:  40%|████      | 10463/25880 [2:09:24<3:22:05,  1.27it/s]
1|10464|Loss: 0.8398337364196777:  40%|████      | 10463/25880 [2:09:24<3:22:05,  1.27it/s]
1|10464|Loss: 0.8398337364196777:  40%|████      | 10464/25880 [2:09:24<3:09:07,  1.36it/s]
1|10465|Loss: 0.713384211063385:  40%|████      | 10464/25880 [2:09:25<3:09:07,  1.36it/s] 
1|10465|Loss: 0.713384211063385:  40%|████      | 10465/25880 [2:09:25<3:10:38,  1.35it/s]
1|10466|Loss: 0.7978627681732178:  40%|████      | 10465/25880 [2:09:25<3:10:38,  1.35it/s]
1|10466|Loss: 0.7978627681732178:  40%|████      | 10466/25880 [2:09:26<3:10:56,  1.35it/s]
1|10467|Loss: 0.7401050925254822:  40%|████      | 10466/25880 [2:09:26<3:10:56,  1.35it/s]
1|10467|Loss: 0.7401050925254822:  40%|████      | 10467/25880 [2:09:26<3:17:47,  1.30it/s]
1|10468|Loss: 0.9292753338813782:  40%|████      | 10467/25880 [2:09:27<3:17:47,  1.30it/s]
1|10468|Loss: 0.9292753338813782:  40%|████      | 10468/25880 [2:09:27<3:07:59,  1.37it/s]
1|10469|Loss: 0.8198883533477783:  40%|████      | 10468/25880 [2:09:27<3:07:59,  1.37it/s]
1|10469|Loss: 0.8198883533477783:  40%|████      | 10469/25880 [2:09:28<3:03:55,  1.40it/s]
1|10470|Loss: 0.9762055277824402:  40%|████      | 10469/25880 [2:09:28<3:03:55,  1.40it/s]
1|10470|Loss: 0.9762055277824402:  40%|████      | 10470/25880 [2:09:28<2:57:26,  1.45it/s]
1|10471|Loss: 0.8392155766487122:  40%|████      | 10470/25880 [2:09:29<2:57:26,  1.45it/s]
1|10471|Loss: 0.8392155766487122:  40%|████      | 10471/25880 [2:09:29<2:58:18,  1.44it/s]
1|10472|Loss: 0.8828614354133606:  40%|████      | 10471/25880 [2:09:30<2:58:18,  1.44it/s]
1|10472|Loss: 0.8828614354133606:  40%|████      | 10472/25880 [2:09:30<3:05:23,  1.39it/s]
1|10473|Loss: 0.9715045690536499:  40%|████      | 10472/25880 [2:09:30<3:05:23,  1.39it/s]
1|10473|Loss: 0.9715045690536499:  40%|████      | 10473/25880 [2:09:30<2:52:22,  1.49it/s]
1|10474|Loss: 0.7636241912841797:  40%|████      | 10473/25880 [2:09:31<2:52:22,  1.49it/s]
1|10474|Loss: 0.7636241912841797:  40%|████      | 10474/25880 [2:09:31<2:53:11,  1.48it/s]
1|10475|Loss: 0.9070276021957397:  40%|████      | 10474/25880 [2:09:32<2:53:11,  1.48it/s]
1|10475|Loss: 0.9070276021957397:  40%|████      | 10475/25880 [2:09:32<3:01:28,  1.41it/s]
1|10476|Loss: 0.7203571796417236:  40%|████      | 10475/25880 [2:09:32<3:01:28,  1.41it/s]
1|10476|Loss: 0.7203571796417236:  40%|████      | 10476/25880 [2:09:33<2:58:31,  1.44it/s]
1|10477|Loss: 0.8607008457183838:  40%|████      | 10476/25880 [2:09:33<2:58:31,  1.44it/s]
1|10477|Loss: 0.8607008457183838:  40%|████      | 10477/25880 [2:09:33<2:59:31,  1.43it/s]
1|10478|Loss: 0.7998486757278442:  40%|████      | 10477/25880 [2:09:34<2:59:31,  1.43it/s]
1|10478|Loss: 0.7998486757278442:  40%|████      | 10478/25880 [2:09:34<2:56:10,  1.46it/s]
1|10479|Loss: 0.9010565876960754:  40%|████      | 10478/25880 [2:09:34<2:56:10,  1.46it/s]
1|10479|Loss: 0.9010565876960754:  40%|████      | 10479/25880 [2:09:35<2:44:30,  1.56it/s]
1|10480|Loss: 0.9177373647689819:  40%|████      | 10479/25880 [2:09:35<2:44:30,  1.56it/s]
1|10480|Loss: 0.9177373647689819:  40%|████      | 10480/25880 [2:09:35<2:37:12,  1.63it/s]
1|10481|Loss: 0.9281200170516968:  40%|████      | 10480/25880 [2:09:35<2:37:12,  1.63it/s]
1|10481|Loss: 0.9281200170516968:  40%|████      | 10481/25880 [2:09:35<2:21:30,  1.81it/s]
1|10482|Loss: 0.9023568630218506:  40%|████      | 10481/25880 [2:09:36<2:21:30,  1.81it/s]
1|10482|Loss: 0.9023568630218506:  41%|████      | 10482/25880 [2:09:36<2:22:51,  1.80it/s]
1|10483|Loss: 0.8589070439338684:  41%|████      | 10482/25880 [2:09:36<2:22:51,  1.80it/s]
1|10483|Loss: 0.8589070439338684:  41%|████      | 10483/25880 [2:09:37<2:41:50,  1.59it/s]
1|10484|Loss: 0.7477045655250549:  41%|████      | 10483/25880 [2:09:37<2:41:50,  1.59it/s]
1|10484|Loss: 0.7477045655250549:  41%|████      | 10484/25880 [2:09:38<2:55:19,  1.46it/s]
1|10485|Loss: 0.7363177537918091:  41%|████      | 10484/25880 [2:09:38<2:55:19,  1.46it/s]
1|10485|Loss: 0.7363177537918091:  41%|████      | 10485/25880 [2:09:38<3:04:16,  1.39it/s]
1|10486|Loss: 0.8876807689666748:  41%|████      | 10485/25880 [2:09:39<3:04:16,  1.39it/s]
1|10486|Loss: 0.8876807689666748:  41%|████      | 10486/25880 [2:09:39<3:04:43,  1.39it/s]
1|10487|Loss: 0.8821358680725098:  41%|████      | 10486/25880 [2:09:40<3:04:43,  1.39it/s]
1|10487|Loss: 0.8821358680725098:  41%|████      | 10487/25880 [2:09:40<3:06:21,  1.38it/s]
1|10488|Loss: 0.8028845191001892:  41%|████      | 10487/25880 [2:09:40<3:06:21,  1.38it/s]
1|10488|Loss: 0.8028845191001892:  41%|████      | 10488/25880 [2:09:41<3:01:18,  1.41it/s]
1|10489|Loss: 0.8208673596382141:  41%|████      | 10488/25880 [2:09:41<3:01:18,  1.41it/s]
1|10489|Loss: 0.8208673596382141:  41%|████      | 10489/25880 [2:09:41<3:02:56,  1.40it/s]
1|10490|Loss: 0.7919223308563232:  41%|████      | 10489/25880 [2:09:42<3:02:56,  1.40it/s]
1|10490|Loss: 0.7919223308563232:  41%|████      | 10490/25880 [2:09:42<2:57:33,  1.44it/s]
1|10491|Loss: 0.9248421788215637:  41%|████      | 10490/25880 [2:09:42<2:57:33,  1.44it/s]
1|10491|Loss: 0.9248421788215637:  41%|████      | 10491/25880 [2:09:43<3:04:42,  1.39it/s]
1|10492|Loss: 1.0046253204345703:  41%|████      | 10491/25880 [2:09:43<3:04:42,  1.39it/s]
1|10492|Loss: 1.0046253204345703:  41%|████      | 10492/25880 [2:09:44<3:15:14,  1.31it/s]
1|10493|Loss: 0.8553638458251953:  41%|████      | 10492/25880 [2:09:44<3:15:14,  1.31it/s]
1|10493|Loss: 0.8553638458251953:  41%|████      | 10493/25880 [2:09:44<3:13:26,  1.33it/s]
1|10494|Loss: 0.8141196370124817:  41%|████      | 10493/25880 [2:09:45<3:13:26,  1.33it/s]
1|10494|Loss: 0.8141196370124817:  41%|████      | 10494/25880 [2:09:45<3:10:15,  1.35it/s]
1|10495|Loss: 0.9837158918380737:  41%|████      | 10494/25880 [2:09:45<3:10:15,  1.35it/s]
1|10495|Loss: 0.9837158918380737:  41%|████      | 10495/25880 [2:09:46<3:16:07,  1.31it/s]
1|10496|Loss: 0.8763219118118286:  41%|████      | 10495/25880 [2:09:46<3:16:07,  1.31it/s]
1|10496|Loss: 0.8763219118118286:  41%|████      | 10496/25880 [2:09:47<3:08:39,  1.36it/s]
1|10497|Loss: 0.7086593508720398:  41%|████      | 10496/25880 [2:09:47<3:08:39,  1.36it/s]
1|10497|Loss: 0.7086593508720398:  41%|████      | 10497/25880 [2:09:47<3:07:16,  1.37it/s]
1|10498|Loss: 0.8985608220100403:  41%|████      | 10497/25880 [2:09:48<3:07:16,  1.37it/s]
1|10498|Loss: 0.8985608220100403:  41%|████      | 10498/25880 [2:09:48<3:07:49,  1.36it/s]
1|10499|Loss: 0.8565476536750793:  41%|████      | 10498/25880 [2:09:48<3:07:49,  1.36it/s]
1|10499|Loss: 0.8565476536750793:  41%|████      | 10499/25880 [2:09:49<2:57:55,  1.44it/s]
1|10500|Loss: 0.8864688873291016:  41%|████      | 10499/25880 [2:09:49<2:57:55,  1.44it/s]
1|10500|Loss: 0.8864688873291016:  41%|████      | 10500/25880 [2:09:49<2:58:02,  1.44it/s]
1|10501|Loss: 0.8382390737533569:  41%|████      | 10500/25880 [2:09:50<2:58:02,  1.44it/s]
1|10501|Loss: 0.8382390737533569:  41%|████      | 10501/25880 [2:09:50<2:52:02,  1.49it/s]
1|10502|Loss: 0.9113250374794006:  41%|████      | 10501/25880 [2:09:50<2:52:02,  1.49it/s]
1|10502|Loss: 0.9113250374794006:  41%|████      | 10502/25880 [2:09:51<2:47:10,  1.53it/s]
1|10503|Loss: 0.8521813154220581:  41%|████      | 10502/25880 [2:09:51<2:47:10,  1.53it/s]
1|10503|Loss: 0.8521813154220581:  41%|████      | 10503/25880 [2:09:51<2:52:50,  1.48it/s]
1|10504|Loss: 0.9090554118156433:  41%|████      | 10503/25880 [2:09:52<2:52:50,  1.48it/s]
1|10504|Loss: 0.9090554118156433:  41%|████      | 10504/25880 [2:09:52<2:57:18,  1.45it/s]
1|10505|Loss: 0.7675061821937561:  41%|████      | 10504/25880 [2:09:52<2:57:18,  1.45it/s]
1|10505|Loss: 0.7675061821937561:  41%|████      | 10505/25880 [2:09:53<2:54:28,  1.47it/s]
1|10506|Loss: 0.9205923080444336:  41%|████      | 10505/25880 [2:09:53<2:54:28,  1.47it/s]
1|10506|Loss: 0.9205923080444336:  41%|████      | 10506/25880 [2:09:53<2:49:42,  1.51it/s]
1|10507|Loss: 0.9616374969482422:  41%|████      | 10506/25880 [2:09:54<2:49:42,  1.51it/s]
1|10507|Loss: 0.9616374969482422:  41%|████      | 10507/25880 [2:09:54<2:56:54,  1.45it/s]
1|10508|Loss: 0.9171019196510315:  41%|████      | 10507/25880 [2:09:54<2:56:54,  1.45it/s]
1|10508|Loss: 0.9171019196510315:  41%|████      | 10508/25880 [2:09:55<3:10:05,  1.35it/s]
1|10509|Loss: 1.0115325450897217:  41%|████      | 10508/25880 [2:09:55<3:10:05,  1.35it/s]
1|10509|Loss: 1.0115325450897217:  41%|████      | 10509/25880 [2:09:56<3:33:05,  1.20it/s]
1|10510|Loss: 0.7977152466773987:  41%|████      | 10509/25880 [2:09:56<3:33:05,  1.20it/s]
1|10510|Loss: 0.7977152466773987:  41%|████      | 10510/25880 [2:09:57<3:16:54,  1.30it/s]
1|10511|Loss: 0.822379469871521:  41%|████      | 10510/25880 [2:09:57<3:16:54,  1.30it/s] 
1|10511|Loss: 0.822379469871521:  41%|████      | 10511/25880 [2:09:57<3:03:30,  1.40it/s]
1|10512|Loss: 0.8916420936584473:  41%|████      | 10511/25880 [2:09:57<3:03:30,  1.40it/s]
1|10512|Loss: 0.8916420936584473:  41%|████      | 10512/25880 [2:09:58<3:03:17,  1.40it/s]
1|10513|Loss: 0.8790090680122375:  41%|████      | 10512/25880 [2:09:58<3:03:17,  1.40it/s]
1|10513|Loss: 0.8790090680122375:  41%|████      | 10513/25880 [2:09:58<2:49:29,  1.51it/s]
1|10514|Loss: 0.6390050649642944:  41%|████      | 10513/25880 [2:09:59<2:49:29,  1.51it/s]
1|10514|Loss: 0.6390050649642944:  41%|████      | 10514/25880 [2:09:59<2:54:24,  1.47it/s]
1|10515|Loss: 0.760331392288208:  41%|████      | 10514/25880 [2:09:59<2:54:24,  1.47it/s] 
1|10515|Loss: 0.760331392288208:  41%|████      | 10515/25880 [2:10:00<2:44:37,  1.56it/s]
1|10516|Loss: 0.7599086165428162:  41%|████      | 10515/25880 [2:10:00<2:44:37,  1.56it/s]
1|10516|Loss: 0.7599086165428162:  41%|████      | 10516/25880 [2:10:00<2:46:52,  1.53it/s]
1|10517|Loss: 0.7546597719192505:  41%|████      | 10516/25880 [2:10:01<2:46:52,  1.53it/s]
1|10517|Loss: 0.7546597719192505:  41%|████      | 10517/25880 [2:10:01<2:31:07,  1.69it/s]
1|10518|Loss: 0.8773001432418823:  41%|████      | 10517/25880 [2:10:01<2:31:07,  1.69it/s]
1|10518|Loss: 0.8773001432418823:  41%|████      | 10518/25880 [2:10:01<2:29:17,  1.71it/s]
1|10519|Loss: 0.7317570447921753:  41%|████      | 10518/25880 [2:10:02<2:29:17,  1.71it/s]
1|10519|Loss: 0.7317570447921753:  41%|████      | 10519/25880 [2:10:02<2:33:29,  1.67it/s]
1|10520|Loss: 0.785841703414917:  41%|████      | 10519/25880 [2:10:02<2:33:29,  1.67it/s] 
1|10520|Loss: 0.785841703414917:  41%|████      | 10520/25880 [2:10:03<2:42:38,  1.57it/s]
1|10521|Loss: 0.8288263082504272:  41%|████      | 10520/25880 [2:10:03<2:42:38,  1.57it/s]
1|10521|Loss: 0.8288263082504272:  41%|████      | 10521/25880 [2:10:03<2:27:51,  1.73it/s]
1|10522|Loss: 0.8754255175590515:  41%|████      | 10521/25880 [2:10:03<2:27:51,  1.73it/s]
1|10522|Loss: 0.8754255175590515:  41%|████      | 10522/25880 [2:10:04<2:40:46,  1.59it/s]
1|10523|Loss: 0.7314375042915344:  41%|████      | 10522/25880 [2:10:04<2:40:46,  1.59it/s]
1|10523|Loss: 0.7314375042915344:  41%|████      | 10523/25880 [2:10:05<2:53:56,  1.47it/s]
1|10524|Loss: 0.8999462723731995:  41%|████      | 10523/25880 [2:10:05<2:53:56,  1.47it/s]
1|10524|Loss: 0.8999462723731995:  41%|��███      | 10524/25880 [2:10:05<2:49:57,  1.51it/s]
1|10525|Loss: 0.595535933971405:  41%|████      | 10524/25880 [2:10:06<2:49:57,  1.51it/s] 
1|10525|Loss: 0.595535933971405:  41%|████      | 10525/25880 [2:10:06<2:44:12,  1.56it/s]
1|10526|Loss: 0.9334302544593811:  41%|████      | 10525/25880 [2:10:06<2:44:12,  1.56it/s]
1|10526|Loss: 0.9334302544593811:  41%|████      | 10526/25880 [2:10:07<2:49:03,  1.51it/s]
1|10527|Loss: 0.7264333963394165:  41%|████      | 10526/25880 [2:10:07<2:49:03,  1.51it/s]
1|10527|Loss: 0.7264333963394165:  41%|████      | 10527/25880 [2:10:07<3:02:14,  1.40it/s]
1|10528|Loss: 0.8187937140464783:  41%|████      | 10527/25880 [2:10:08<3:02:14,  1.40it/s]
1|10528|Loss: 0.8187937140464783:  41%|████      | 10528/25880 [2:10:08<3:10:12,  1.35it/s]
1|10529|Loss: 0.9277223944664001:  41%|████      | 10528/25880 [2:10:09<3:10:12,  1.35it/s]
1|10529|Loss: 0.9277223944664001:  41%|████      | 10529/25880 [2:10:09<3:10:09,  1.35it/s]
1|10530|Loss: 0.9792189598083496:  41%|████      | 10529/25880 [2:10:10<3:10:09,  1.35it/s]
1|10530|Loss: 0.9792189598083496:  41%|████      | 10530/25880 [2:10:10<3:43:15,  1.15it/s]
1|10531|Loss: 0.9601926803588867:  41%|████      | 10530/25880 [2:10:11<3:43:15,  1.15it/s]
1|10531|Loss: 0.9601926803588867:  41%|████      | 10531/25880 [2:10:11<3:34:07,  1.19it/s]
1|10532|Loss: 0.9561538696289062:  41%|████      | 10531/25880 [2:10:11<3:34:07,  1.19it/s]
1|10532|Loss: 0.9561538696289062:  41%|████      | 10532/25880 [2:10:12<3:23:48,  1.26it/s]
1|10533|Loss: 0.8195197582244873:  41%|████      | 10532/25880 [2:10:12<3:23:48,  1.26it/s]
1|10533|Loss: 0.8195197582244873:  41%|████      | 10533/25880 [2:10:12<3:01:23,  1.41it/s]
1|10534|Loss: 0.8066162467002869:  41%|████      | 10533/25880 [2:10:12<3:01:23,  1.41it/s]
1|10534|Loss: 0.8066162467002869:  41%|████      | 10534/25880 [2:10:13<2:44:56,  1.55it/s]
1|10535|Loss: 0.9047175645828247:  41%|████      | 10534/25880 [2:10:13<2:44:56,  1.55it/s]
1|10535|Loss: 0.9047175645828247:  41%|████      | 10535/25880 [2:10:13<2:41:14,  1.59it/s]
1|10536|Loss: 0.8210102319717407:  41%|████      | 10535/25880 [2:10:14<2:41:14,  1.59it/s]
1|10536|Loss: 0.8210102319717407:  41%|████      | 10536/25880 [2:10:14<2:51:18,  1.49it/s]
1|10537|Loss: 0.8678902387619019:  41%|████      | 10536/25880 [2:10:14<2:51:18,  1.49it/s]
1|10537|Loss: 0.8678902387619019:  41%|████      | 10537/25880 [2:10:15<2:52:05,  1.49it/s]
1|10538|Loss: 0.6799646019935608:  41%|████      | 10537/25880 [2:10:15<2:52:05,  1.49it/s]
1|10538|Loss: 0.6799646019935608:  41%|████      | 10538/25880 [2:10:15<2:49:17,  1.51it/s]
1|10539|Loss: 0.8193371891975403:  41%|████      | 10538/25880 [2:10:16<2:49:17,  1.51it/s]
1|10539|Loss: 0.8193371891975403:  41%|████      | 10539/25880 [2:10:16<2:53:23,  1.47it/s]
1|10540|Loss: 0.8525905609130859:  41%|████      | 10539/25880 [2:10:16<2:53:23,  1.47it/s]
1|10540|Loss: 0.8525905609130859:  41%|████      | 10540/25880 [2:10:17<3:05:56,  1.37it/s]
1|10541|Loss: 0.8513165712356567:  41%|████      | 10540/25880 [2:10:17<3:05:56,  1.37it/s]
1|10541|Loss: 0.8513165712356567:  41%|████      | 10541/25880 [2:10:18<3:08:24,  1.36it/s]
1|10542|Loss: 0.9221561551094055:  41%|████      | 10541/25880 [2:10:18<3:08:24,  1.36it/s]
1|10542|Loss: 0.9221561551094055:  41%|████      | 10542/25880 [2:10:18<3:17:02,  1.30it/s]
1|10543|Loss: 0.6915681958198547:  41%|████      | 10542/25880 [2:10:19<3:17:02,  1.30it/s]
1|10543|Loss: 0.6915681958198547:  41%|████      | 10543/25880 [2:10:19<3:16:48,  1.30it/s]
1|10544|Loss: 0.8292720317840576:  41%|████      | 10543/25880 [2:10:20<3:16:48,  1.30it/s]
1|10544|Loss: 0.8292720317840576:  41%|████      | 10544/25880 [2:10:20<3:16:59,  1.30it/s]
1|10545|Loss: 0.9320040941238403:  41%|████      | 10544/25880 [2:10:20<3:16:59,  1.30it/s]
1|10545|Loss: 0.9320040941238403:  41%|████      | 10545/25880 [2:10:21<3:12:46,  1.33it/s]
1|10546|Loss: 0.9783835411071777:  41%|████      | 10545/25880 [2:10:21<3:12:46,  1.33it/s]
1|10546|Loss: 0.9783835411071777:  41%|████      | 10546/25880 [2:10:21<3:04:27,  1.39it/s]
1|10547|Loss: 0.7273480892181396:  41%|████      | 10546/25880 [2:10:22<3:04:27,  1.39it/s]
1|10547|Loss: 0.7273480892181396:  41%|████      | 10547/25880 [2:10:22<3:09:33,  1.35it/s]
1|10548|Loss: 0.804639995098114:  41%|████      | 10547/25880 [2:10:23<3:09:33,  1.35it/s] 
1|10548|Loss: 0.804639995098114:  41%|████      | 10548/25880 [2:10:23<3:01:06,  1.41it/s]
1|10549|Loss: 0.8917301297187805:  41%|████      | 10548/25880 [2:10:23<3:01:06,  1.41it/s]
1|10549|Loss: 0.8917301297187805:  41%|████      | 10549/25880 [2:10:23<2:58:27,  1.43it/s]
1|10550|Loss: 0.7320693135261536:  41%|████      | 10549/25880 [2:10:24<2:58:27,  1.43it/s]
1|10550|Loss: 0.7320693135261536:  41%|████      | 10550/25880 [2:10:24<2:47:41,  1.52it/s]
1|10551|Loss: 0.8787273168563843:  41%|████      | 10550/25880 [2:10:24<2:47:41,  1.52it/s]
1|10551|Loss: 0.8787273168563843:  41%|████      | 10551/25880 [2:10:25<2:50:44,  1.50it/s]
1|10552|Loss: 0.8787200450897217:  41%|████      | 10551/25880 [2:10:25<2:50:44,  1.50it/s]
1|10552|Loss: 0.8787200450897217:  41%|████      | 10552/25880 [2:10:25<2:56:06,  1.45it/s]
1|10553|Loss: 0.809212327003479:  41%|████      | 10552/25880 [2:10:26<2:56:06,  1.45it/s] 
1|10553|Loss: 0.809212327003479:  41%|████      | 10553/25880 [2:10:26<3:05:53,  1.37it/s]
1|10554|Loss: 0.7166067361831665:  41%|████      | 10553/25880 [2:10:27<3:05:53,  1.37it/s]
1|10554|Loss: 0.7166067361831665:  41%|████      | 10554/25880 [2:10:27<3:13:34,  1.32it/s]
1|10555|Loss: 0.9231973886489868:  41%|████      | 10554/25880 [2:10:28<3:13:34,  1.32it/s]
1|10555|Loss: 0.9231973886489868:  41%|████      | 10555/25880 [2:10:28<3:17:42,  1.29it/s]
1|10556|Loss: 0.7673606276512146:  41%|████      | 10555/25880 [2:10:28<3:17:42,  1.29it/s]
1|10556|Loss: 0.7673606276512146:  41%|████      | 10556/25880 [2:10:29<3:19:43,  1.28it/s]
1|10557|Loss: 0.7439141869544983:  41%|████      | 10556/25880 [2:10:29<3:19:43,  1.28it/s]
1|10557|Loss: 0.7439141869544983:  41%|████      | 10557/25880 [2:10:29<3:11:14,  1.34it/s]
1|10558|Loss: 0.8029783368110657:  41%|████      | 10557/25880 [2:10:30<3:11:14,  1.34it/s]
1|10558|Loss: 0.8029783368110657:  41%|████      | 10558/25880 [2:10:30<2:59:36,  1.42it/s]
1|10559|Loss: 0.9214918613433838:  41%|████      | 10558/25880 [2:10:30<2:59:36,  1.42it/s]
1|10559|Loss: 0.9214918613433838:  41%|████      | 10559/25880 [2:10:31<2:57:16,  1.44it/s]
1|10560|Loss: 0.7273849844932556:  41%|████      | 10559/25880 [2:10:31<2:57:16,  1.44it/s]
1|10560|Loss: 0.7273849844932556:  41%|████      | 10560/25880 [2:10:31<2:52:21,  1.48it/s]
1|10561|Loss: 0.8789795637130737:  41%|████      | 10560/25880 [2:10:32<2:52:21,  1.48it/s]
1|10561|Loss: 0.8789795637130737:  41%|████      | 10561/25880 [2:10:32<2:58:12,  1.43it/s]
1|10562|Loss: 0.8711140155792236:  41%|████      | 10561/25880 [2:10:32<2:58:12,  1.43it/s]
1|10562|Loss: 0.8711140155792236:  41%|████      | 10562/25880 [2:10:33<3:02:10,  1.40it/s]
1|10563|Loss: 0.8251726627349854:  41%|████      | 10562/25880 [2:10:33<3:02:10,  1.40it/s]
1|10563|Loss: 0.8251726627349854:  41%|████      | 10563/25880 [2:10:34<3:03:20,  1.39it/s]
1|10564|Loss: 0.8149694800376892:  41%|████      | 10563/25880 [2:10:34<3:03:20,  1.39it/s]
1|10564|Loss: 0.8149694800376892:  41%|████      | 10564/25880 [2:10:34<3:09:05,  1.35it/s]
1|10565|Loss: 0.7246150374412537:  41%|████      | 10564/25880 [2:10:35<3:09:05,  1.35it/s]
1|10565|Loss: 0.7246150374412537:  41%|████      | 10565/25880 [2:10:35<3:24:49,  1.25it/s]
1|10566|Loss: 0.9050218462944031:  41%|████      | 10565/25880 [2:10:36<3:24:49,  1.25it/s]
1|10566|Loss: 0.9050218462944031:  41%|████      | 10566/25880 [2:10:36<3:08:52,  1.35it/s]
1|10567|Loss: 0.7957639694213867:  41%|████      | 10566/25880 [2:10:36<3:08:52,  1.35it/s]
1|10567|Loss: 0.7957639694213867:  41%|████      | 10567/25880 [2:10:37<3:04:33,  1.38it/s]
1|10568|Loss: 0.9562585949897766:  41%|████      | 10567/25880 [2:10:37<3:04:33,  1.38it/s]
1|10568|Loss: 0.9562585949897766:  41%|████      | 10568/25880 [2:10:37<2:53:28,  1.47it/s]
1|10569|Loss: 0.984295129776001:  41%|████      | 10568/25880 [2:10:37<2:53:28,  1.47it/s] 
1|10569|Loss: 0.984295129776001:  41%|████      | 10569/25880 [2:10:38<2:43:14,  1.56it/s]
1|10570|Loss: 0.7796087861061096:  41%|████      | 10569/25880 [2:10:38<2:43:14,  1.56it/s]
1|10570|Loss: 0.7796087861061096:  41%|████      | 10570/25880 [2:10:38<2:45:59,  1.54it/s]
1|10571|Loss: 0.8218574523925781:  41%|████      | 10570/25880 [2:10:39<2:45:59,  1.54it/s]
1|10571|Loss: 0.8218574523925781:  41%|████      | 10571/25880 [2:10:39<2:52:49,  1.48it/s]
1|10572|Loss: 0.9255995750427246:  41%|████      | 10571/25880 [2:10:40<2:52:49,  1.48it/s]
1|10572|Loss: 0.9255995750427246:  41%|████      | 10572/25880 [2:10:40<3:01:19,  1.41it/s]
1|10573|Loss: 0.7943320870399475:  41%|████      | 10572/25880 [2:10:40<3:01:19,  1.41it/s]
1|10573|Loss: 0.7943320870399475:  41%|████      | 10573/25880 [2:10:41<3:02:14,  1.40it/s]
1|10574|Loss: 0.9334026575088501:  41%|████      | 10573/25880 [2:10:41<3:02:14,  1.40it/s]
1|10574|Loss: 0.9334026575088501:  41%|████      | 10574/25880 [2:10:41<3:03:38,  1.39it/s]
1|10575|Loss: 0.8758237361907959:  41%|████      | 10574/25880 [2:10:42<3:03:38,  1.39it/s]
1|10575|Loss: 0.8758237361907959:  41%|████      | 10575/25880 [2:10:42<3:05:15,  1.38it/s]
1|10576|Loss: 0.879371702671051:  41%|████      | 10575/25880 [2:10:42<3:05:15,  1.38it/s] 
1|10576|Loss: 0.879371702671051:  41%|████      | 10576/25880 [2:10:43<2:58:57,  1.43it/s]
1|10577|Loss: 0.9226577281951904:  41%|████      | 10576/25880 [2:10:43<2:58:57,  1.43it/s]
1|10577|Loss: 0.9226577281951904:  41%|████      | 10577/25880 [2:10:43<3:00:33,  1.41it/s]
1|10578|Loss: 0.8523396849632263:  41%|████      | 10577/25880 [2:10:44<3:00:33,  1.41it/s]
1|10578|Loss: 0.8523396849632263:  41%|████      | 10578/25880 [2:10:44<3:02:35,  1.40it/s]
1|10579|Loss: 0.8046348690986633:  41%|████      | 10578/25880 [2:10:45<3:02:35,  1.40it/s]
1|10579|Loss: 0.8046348690986633:  41%|████      | 10579/25880 [2:10:45<3:03:43,  1.39it/s]
1|10580|Loss: 0.9599761366844177:  41%|████      | 10579/25880 [2:10:45<3:03:43,  1.39it/s]
1|10580|Loss: 0.9599761366844177:  41%|████      | 10580/25880 [2:10:46<3:11:29,  1.33it/s]
1|10581|Loss: 0.8063069581985474:  41%|████      | 10580/25880 [2:10:46<3:11:29,  1.33it/s]
1|10581|Loss: 0.8063069581985474:  41%|████      | 10581/25880 [2:10:46<3:06:29,  1.37it/s]
1|10582|Loss: 0.7872439622879028:  41%|████      | 10581/25880 [2:10:47<3:06:29,  1.37it/s]
1|10582|Loss: 0.7872439622879028:  41%|████      | 10582/25880 [2:10:47<3:08:17,  1.35it/s]
1|10583|Loss: 0.8908827900886536:  41%|████      | 10582/25880 [2:10:48<3:08:17,  1.35it/s]
1|10583|Loss: 0.8908827900886536:  41%|████      | 10583/25880 [2:10:48<3:03:27,  1.39it/s]
1|10584|Loss: 0.913941502571106:  41%|████      | 10583/25880 [2:10:48<3:03:27,  1.39it/s] 
1|10584|Loss: 0.913941502571106:  41%|████      | 10584/25880 [2:10:49<3:02:04,  1.40it/s]
1|10585|Loss: 0.9035006165504456:  41%|████      | 10584/25880 [2:10:49<3:02:04,  1.40it/s]
1|10585|Loss: 0.9035006165504456:  41%|████      | 10585/25880 [2:10:49<3:08:30,  1.35it/s]
1|10586|Loss: 0.8718421459197998:  41%|████      | 10585/25880 [2:10:50<3:08:30,  1.35it/s]
1|10586|Loss: 0.8718421459197998:  41%|████      | 10586/25880 [2:10:50<2:59:54,  1.42it/s]
1|10587|Loss: 0.9000566601753235:  41%|████      | 10586/25880 [2:10:50<2:59:54,  1.42it/s]
1|10587|Loss: 0.9000566601753235:  41%|████      | 10587/25880 [2:10:51<3:07:18,  1.36it/s]
1|10588|Loss: 0.910322904586792:  41%|████      | 10587/25880 [2:10:51<3:07:18,  1.36it/s] 
1|10588|Loss: 0.910322904586792:  41%|████      | 10588/25880 [2:10:52<3:18:00,  1.29it/s]
1|10589|Loss: 0.8500506281852722:  41%|████      | 10588/25880 [2:10:52<3:18:00,  1.29it/s]
1|10589|Loss: 0.8500506281852722:  41%|████      | 10589/25880 [2:10:52<3:17:38,  1.29it/s]
1|10590|Loss: 0.8144115209579468:  41%|████      | 10589/25880 [2:10:53<3:17:38,  1.29it/s]
1|10590|Loss: 0.8144115209579468:  41%|████      | 10590/25880 [2:10:53<3:07:17,  1.36it/s]
1|10591|Loss: 0.8325148820877075:  41%|████      | 10590/25880 [2:10:53<3:07:17,  1.36it/s]
1|10591|Loss: 0.8325148820877075:  41%|████      | 10591/25880 [2:10:54<3:09:34,  1.34it/s]
1|10592|Loss: 0.8400576710700989:  41%|████      | 10591/25880 [2:10:54<3:09:34,  1.34it/s]
1|10592|Loss: 0.8400576710700989:  41%|████      | 10592/25880 [2:10:55<3:13:51,  1.31it/s]
1|10593|Loss: 0.9012852311134338:  41%|████      | 10592/25880 [2:10:55<3:13:51,  1.31it/s]
1|10593|Loss: 0.9012852311134338:  41%|████      | 10593/25880 [2:10:55<3:16:32,  1.30it/s]
1|10594|Loss: 0.7969391942024231:  41%|████      | 10593/25880 [2:10:56<3:16:32,  1.30it/s]
1|10594|Loss: 0.7969391942024231:  41%|████      | 10594/25880 [2:10:56<3:14:55,  1.31it/s]
1|10595|Loss: 0.8199855089187622:  41%|████      | 10594/25880 [2:10:57<3:14:55,  1.31it/s]
1|10595|Loss: 0.8199855089187622:  41%|████      | 10595/25880 [2:10:57<3:19:00,  1.28it/s]
1|10596|Loss: 0.8062089681625366:  41%|████      | 10595/25880 [2:10:57<3:19:00,  1.28it/s]
1|10596|Loss: 0.8062089681625366:  41%|████      | 10596/25880 [2:10:58<3:08:01,  1.35it/s]
1|10597|Loss: 0.9795087575912476:  41%|████      | 10596/25880 [2:10:58<3:08:01,  1.35it/s]
1|10597|Loss: 0.9795087575912476:  41%|████      | 10597/25880 [2:10:58<2:51:35,  1.48it/s]
1|10598|Loss: 0.8554083704948425:  41%|████      | 10597/25880 [2:10:58<2:51:35,  1.48it/s]
1|10598|Loss: 0.8554083704948425:  41%|████      | 10598/25880 [2:10:59<2:50:19,  1.50it/s]
1|10599|Loss: 0.8534277081489563:  41%|████      | 10598/25880 [2:10:59<2:50:19,  1.50it/s]
1|10599|Loss: 0.8534277081489563:  41%|████      | 10599/25880 [2:11:00<2:54:51,  1.46it/s]
1|10600|Loss: 0.801846981048584:  41%|████      | 10599/25880 [2:11:00<2:54:51,  1.46it/s] 
1|10600|Loss: 0.801846981048584:  41%|████      | 10600/25880 [2:11:00<3:04:02,  1.38it/s]
1|10601|Loss: 0.9127036333084106:  41%|████      | 10600/25880 [2:11:01<3:04:02,  1.38it/s]
1|10601|Loss: 0.9127036333084106:  41%|████      | 10601/25880 [2:11:01<3:04:46,  1.38it/s]
1|10602|Loss: 0.8143354654312134:  41%|████      | 10601/25880 [2:11:01<3:04:46,  1.38it/s]
1|10602|Loss: 0.8143354654312134:  41%|████      | 10602/25880 [2:11:02<3:08:21,  1.35it/s]
1|10603|Loss: 0.7493965029716492:  41%|████      | 10602/25880 [2:11:02<3:08:21,  1.35it/s]
1|10603|Loss: 0.7493965029716492:  41%|████      | 10603/25880 [2:11:03<3:13:45,  1.31it/s]
1|10604|Loss: 0.7705013155937195:  41%|████      | 10603/25880 [2:11:03<3:13:45,  1.31it/s]
1|10604|Loss: 0.7705013155937195:  41%|████      | 10604/25880 [2:11:03<2:55:59,  1.45it/s]
1|10605|Loss: 0.8634700179100037:  41%|████      | 10604/25880 [2:11:03<2:55:59,  1.45it/s]
1|10605|Loss: 0.8634700179100037:  41%|████      | 10605/25880 [2:11:04<2:40:46,  1.58it/s]
1|10606|Loss: 0.858332097530365:  41%|████      | 10605/25880 [2:11:04<2:40:46,  1.58it/s] 
1|10606|Loss: 0.858332097530365:  41%|████      | 10606/25880 [2:11:04<2:42:38,  1.57it/s]
1|10607|Loss: 0.8488543629646301:  41%|████      | 10606/25880 [2:11:05<2:42:38,  1.57it/s]
1|10607|Loss: 0.8488543629646301:  41%|████      | 10607/25880 [2:11:05<2:40:01,  1.59it/s]
1|10608|Loss: 0.884310781955719:  41%|████      | 10607/25880 [2:11:05<2:40:01,  1.59it/s] 
1|10608|Loss: 0.884310781955719:  41%|████      | 10608/25880 [2:11:06<2:45:38,  1.54it/s]
1|10609|Loss: 0.8974645733833313:  41%|████      | 10608/25880 [2:11:06<2:45:38,  1.54it/s]
1|10609|Loss: 0.8974645733833313:  41%|████      | 10609/25880 [2:11:06<2:51:33,  1.48it/s]
1|10610|Loss: 0.6693944334983826:  41%|████      | 10609/25880 [2:11:07<2:51:33,  1.48it/s]
1|10610|Loss: 0.6693944334983826:  41%|████      | 10610/25880 [2:11:07<2:46:36,  1.53it/s]
1|10611|Loss: 1.0329362154006958:  41%|████      | 10610/25880 [2:11:07<2:46:36,  1.53it/s]
1|10611|Loss: 1.0329362154006958:  41%|████      | 10611/25880 [2:11:08<2:39:32,  1.60it/s]
1|10612|Loss: 0.8653655052185059:  41%|████      | 10611/25880 [2:11:08<2:39:32,  1.60it/s]
1|10612|Loss: 0.8653655052185059:  41%|████      | 10612/25880 [2:11:08<2:27:32,  1.72it/s]
1|10613|Loss: 0.8398233652114868:  41%|████      | 10612/25880 [2:11:08<2:27:32,  1.72it/s]
1|10613|Loss: 0.8398233652114868:  41%|████      | 10613/25880 [2:11:09<2:34:13,  1.65it/s]
1|10614|Loss: 0.8109433650970459:  41%|████      | 10613/25880 [2:11:09<2:34:13,  1.65it/s]
1|10614|Loss: 0.8109433650970459:  41%|████      | 10614/25880 [2:11:09<2:41:54,  1.57it/s]
1|10615|Loss: 0.859856128692627:  41%|████      | 10614/25880 [2:11:10<2:41:54,  1.57it/s] 
1|10615|Loss: 0.859856128692627:  41%|████      | 10615/25880 [2:11:10<2:55:22,  1.45it/s]
1|10616|Loss: 0.8609248995780945:  41%|████      | 10615/25880 [2:11:11<2:55:22,  1.45it/s]
1|10616|Loss: 0.8609248995780945:  41%|████      | 10616/25880 [2:11:11<3:01:33,  1.40it/s]
1|10617|Loss: 0.8410175442695618:  41%|████      | 10616/25880 [2:11:11<3:01:33,  1.40it/s]
1|10617|Loss: 0.8410175442695618:  41%|████      | 10617/25880 [2:11:12<2:51:19,  1.48it/s]
1|10618|Loss: 0.8592555522918701:  41%|████      | 10617/25880 [2:11:12<2:51:19,  1.48it/s]
1|10618|Loss: 0.8592555522918701:  41%|████      | 10618/25880 [2:11:12<2:59:59,  1.41it/s]
1|10619|Loss: 0.8387814164161682:  41%|████      | 10618/25880 [2:11:13<2:59:59,  1.41it/s]
1|10619|Loss: 0.8387814164161682:  41%|████      | 10619/25880 [2:11:13<2:58:16,  1.43it/s]
1|10620|Loss: 0.7975470423698425:  41%|████      | 10619/25880 [2:11:13<2:58:16,  1.43it/s]
1|10620|Loss: 0.7975470423698425:  41%|████      | 10620/25880 [2:11:14<3:06:20,  1.36it/s]
1|10621|Loss: 0.8816244006156921:  41%|████      | 10620/25880 [2:11:14<3:06:20,  1.36it/s]
1|10621|Loss: 0.8816244006156921:  41%|████      | 10621/25880 [2:11:15<3:09:10,  1.34it/s]
1|10622|Loss: 0.8465772271156311:  41%|████      | 10621/25880 [2:11:15<3:09:10,  1.34it/s]
1|10622|Loss: 0.8465772271156311:  41%|████      | 10622/25880 [2:11:15<3:02:00,  1.40it/s]
1|10623|Loss: 0.7847875356674194:  41%|████      | 10622/25880 [2:11:16<3:02:00,  1.40it/s]
1|10623|Loss: 0.7847875356674194:  41%|████      | 10623/25880 [2:11:16<3:01:21,  1.40it/s]
1|10624|Loss: 0.7648842930793762:  41%|████      | 10623/25880 [2:11:16<3:01:21,  1.40it/s]
1|10624|Loss: 0.7648842930793762:  41%|████      | 10624/25880 [2:11:17<3:03:24,  1.39it/s]
1|10625|Loss: 0.7239594459533691:  41%|████      | 10624/25880 [2:11:17<3:03:24,  1.39it/s]
1|10625|Loss: 0.7239594459533691:  41%|████      | 10625/25880 [2:11:18<3:10:38,  1.33it/s]
1|10626|Loss: 0.7773465514183044:  41%|████      | 10625/25880 [2:11:18<3:10:38,  1.33it/s]
1|10626|Loss: 0.7773465514183044:  41%|████      | 10626/25880 [2:11:18<3:15:02,  1.30it/s]
1|10627|Loss: 0.9318529367446899:  41%|████      | 10626/25880 [2:11:19<3:15:02,  1.30it/s]
1|10627|Loss: 0.9318529367446899:  41%|████      | 10627/25880 [2:11:19<3:07:38,  1.35it/s]
1|10628|Loss: 0.8252278566360474:  41%|████      | 10627/25880 [2:11:19<3:07:38,  1.35it/s]
1|10628|Loss: 0.8252278566360474:  41%|████      | 10628/25880 [2:11:20<3:05:54,  1.37it/s]
1|10629|Loss: 0.8226931095123291:  41%|████      | 10628/25880 [2:11:20<3:05:54,  1.37it/s]
1|10629|Loss: 0.8226931095123291:  41%|████      | 10629/25880 [2:11:20<3:06:05,  1.37it/s]
1|10630|Loss: 0.7534874677658081:  41%|████      | 10629/25880 [2:11:21<3:06:05,  1.37it/s]
1|10630|Loss: 0.7534874677658081:  41%|████      | 10630/25880 [2:11:21<3:07:33,  1.36it/s]
1|10631|Loss: 0.8731812238693237:  41%|████      | 10630/25880 [2:11:22<3:07:33,  1.36it/s]
1|10631|Loss: 0.8731812238693237:  41%|████      | 10631/25880 [2:11:22<3:13:58,  1.31it/s]
1|10632|Loss: 0.7890138030052185:  41%|████      | 10631/25880 [2:11:22<3:13:58,  1.31it/s]
1|10632|Loss: 0.7890138030052185:  41%|████      | 10632/25880 [2:11:23<3:14:34,  1.31it/s]
1|10633|Loss: 0.9296123385429382:  41%|████      | 10632/25880 [2:11:23<3:14:34,  1.31it/s]
1|10633|Loss: 0.9296123385429382:  41%|████      | 10633/25880 [2:11:23<3:10:39,  1.33it/s]
1|10634|Loss: 0.7832613587379456:  41%|████      | 10633/25880 [2:11:24<3:10:39,  1.33it/s]
1|10634|Loss: 0.7832613587379456:  41%|████      | 10634/25880 [2:11:24<3:13:03,  1.32it/s]
1|10635|Loss: 0.8858237862586975:  41%|████      | 10634/25880 [2:11:25<3:13:03,  1.32it/s]
1|10635|Loss: 0.8858237862586975:  41%|████      | 10635/25880 [2:11:25<3:16:16,  1.29it/s]
1|10636|Loss: 0.9769408702850342:  41%|████      | 10635/25880 [2:11:25<3:16:16,  1.29it/s]
1|10636|Loss: 0.9769408702850342:  41%|████      | 10636/25880 [2:11:26<3:12:41,  1.32it/s]
1|10637|Loss: 0.8631957769393921:  41%|████      | 10636/25880 [2:11:26<3:12:41,  1.32it/s]
1|10637|Loss: 0.8631957769393921:  41%|████      | 10637/25880 [2:11:27<3:10:14,  1.34it/s]
1|10638|Loss: 0.9221066832542419:  41%|████      | 10637/25880 [2:11:27<3:10:14,  1.34it/s]
1|10638|Loss: 0.9221066832542419:  41%|████      | 10638/25880 [2:11:27<3:15:30,  1.30it/s]
1|10639|Loss: 0.9365097880363464:  41%|████      | 10638/25880 [2:11:28<3:15:30,  1.30it/s]
1|10639|Loss: 0.9365097880363464:  41%|████      | 10639/25880 [2:11:28<3:12:35,  1.32it/s]
1|10640|Loss: 0.9568526148796082:  41%|████      | 10639/25880 [2:11:28<3:12:35,  1.32it/s]
1|10640|Loss: 0.9568526148796082:  41%|████      | 10640/25880 [2:11:29<3:14:22,  1.31it/s]
1|10641|Loss: 0.8066145181655884:  41%|████      | 10640/25880 [2:11:29<3:14:22,  1.31it/s]
1|10641|Loss: 0.8066145181655884:  41%|████      | 10641/25880 [2:11:30<3:17:12,  1.29it/s]
1|10642|Loss: 0.9339392781257629:  41%|████      | 10641/25880 [2:11:30<3:17:12,  1.29it/s]
1|10642|Loss: 0.9339392781257629:  41%|████      | 10642/25880 [2:11:30<3:09:19,  1.34it/s]
1|10643|Loss: 0.7971416711807251:  41%|████      | 10642/25880 [2:11:31<3:09:19,  1.34it/s]
1|10643|Loss: 0.7971416711807251:  41%|████      | 10643/25880 [2:11:31<3:07:04,  1.36it/s]
1|10644|Loss: 0.7418134808540344:  41%|████      | 10643/25880 [2:11:31<3:07:04,  1.36it/s]
1|10644|Loss: 0.7418134808540344:  41%|████      | 10644/25880 [2:11:32<3:07:16,  1.36it/s]
1|10645|Loss: 0.9093219637870789:  41%|████      | 10644/25880 [2:11:32<3:07:16,  1.36it/s]
1|10645|Loss: 0.9093219637870789:  41%|████      | 10645/25880 [2:11:33<3:14:54,  1.30it/s]
1|10646|Loss: 0.8921825289726257:  41%|████      | 10645/25880 [2:11:33<3:14:54,  1.30it/s]
1|10646|Loss: 0.8921825289726257:  41%|████      | 10646/25880 [2:11:33<3:14:10,  1.31it/s]
1|10647|Loss: 0.8850492835044861:  41%|████      | 10646/25880 [2:11:34<3:14:10,  1.31it/s]
1|10647|Loss: 0.8850492835044861:  41%|████      | 10647/25880 [2:11:34<3:20:17,  1.27it/s]
1|10648|Loss: 0.7964180707931519:  41%|████      | 10647/25880 [2:11:35<3:20:17,  1.27it/s]
1|10648|Loss: 0.7964180707931519:  41%|████      | 10648/25880 [2:11:35<3:24:37,  1.24it/s]
1|10649|Loss: 0.8828710913658142:  41%|████      | 10648/25880 [2:11:35<3:24:37,  1.24it/s]
1|10649|Loss: 0.8828710913658142:  41%|████      | 10649/25880 [2:11:36<3:20:38,  1.27it/s]
1|10650|Loss: 0.8817499279975891:  41%|████      | 10649/25880 [2:11:36<3:20:38,  1.27it/s]
1|10650|Loss: 0.8817499279975891:  41%|████      | 10650/25880 [2:11:37<3:15:59,  1.30it/s]
1|10651|Loss: 0.9584599137306213:  41%|████      | 10650/25880 [2:11:37<3:15:59,  1.30it/s]
1|10651|Loss: 0.9584599137306213:  41%|████      | 10651/25880 [2:11:37<3:03:56,  1.38it/s]
1|10652|Loss: 0.8511548638343811:  41%|████      | 10651/25880 [2:11:38<3:03:56,  1.38it/s]
1|10652|Loss: 0.8511548638343811:  41%|████      | 10652/25880 [2:11:38<3:00:16,  1.41it/s]
1|10653|Loss: 1.0815181732177734:  41%|████      | 10652/25880 [2:11:38<3:00:16,  1.41it/s]
1|10653|Loss: 1.0815181732177734:  41%|████      | 10653/25880 [2:11:38<2:44:02,  1.55it/s]
1|10654|Loss: 0.9241302609443665:  41%|████      | 10653/25880 [2:11:39<2:44:02,  1.55it/s]
1|10654|Loss: 0.9241302609443665:  41%|████      | 10654/25880 [2:11:39<2:32:25,  1.66it/s]
1|10655|Loss: 1.2042038440704346:  41%|████      | 10654/25880 [2:11:39<2:32:25,  1.66it/s]
1|10655|Loss: 1.2042038440704346:  41%|████      | 10655/25880 [2:11:40<2:39:24,  1.59it/s]
1|10656|Loss: 0.844309389591217:  41%|████      | 10655/25880 [2:11:40<2:39:24,  1.59it/s] 
1|10656|Loss: 0.844309389591217:  41%|████      | 10656/25880 [2:11:40<2:46:08,  1.53it/s]
1|10657|Loss: 0.7985010743141174:  41%|████      | 10656/25880 [2:11:41<2:46:08,  1.53it/s]
1|10657|Loss: 0.7985010743141174:  41%|████      | 10657/25880 [2:11:41<2:51:13,  1.48it/s]
1|10658|Loss: 0.987423837184906:  41%|████      | 10657/25880 [2:11:41<2:51:13,  1.48it/s] 
1|10658|Loss: 0.987423837184906:  41%|████      | 10658/25880 [2:11:42<2:48:11,  1.51it/s]
1|10659|Loss: 0.9642993807792664:  41%|████      | 10658/25880 [2:11:42<2:48:11,  1.51it/s]
1|10659|Loss: 0.9642993807792664:  41%|████      | 10659/25880 [2:11:42<2:40:43,  1.58it/s]
1|10660|Loss: 0.8085023164749146:  41%|████      | 10659/25880 [2:11:43<2:40:43,  1.58it/s]
1|10660|Loss: 0.8085023164749146:  41%|████      | 10660/25880 [2:11:43<2:49:38,  1.50it/s]
1|10661|Loss: 0.8435976505279541:  41%|████      | 10660/25880 [2:11:43<2:49:38,  1.50it/s]
1|10661|Loss: 0.8435976505279541:  41%|████      | 10661/25880 [2:11:44<2:55:47,  1.44it/s]
1|10662|Loss: 0.6783347725868225:  41%|████      | 10661/25880 [2:11:44<2:55:47,  1.44it/s]
1|10662|Loss: 0.6783347725868225:  41%|████      | 10662/25880 [2:11:44<3:03:20,  1.38it/s]
1|10663|Loss: 0.94841068983078:  41%|████      | 10662/25880 [2:11:45<3:03:20,  1.38it/s]  
1|10663|Loss: 0.94841068983078:  41%|████      | 10663/25880 [2:11:45<2:58:04,  1.42it/s]
1|10664|Loss: 0.7590821385383606:  41%|████      | 10663/25880 [2:11:46<2:58:04,  1.42it/s]
1|10664|Loss: 0.7590821385383606:  41%|████      | 10664/25880 [2:11:46<3:06:06,  1.36it/s]
1|10665|Loss: 0.9123890995979309:  41%|████      | 10664/25880 [2:11:46<3:06:06,  1.36it/s]
1|10665|Loss: 0.9123890995979309:  41%|████      | 10665/25880 [2:11:47<2:55:02,  1.45it/s]
1|10666|Loss: 0.7839720249176025:  41%|████      | 10665/25880 [2:11:47<2:55:02,  1.45it/s]
1|10666|Loss: 0.7839720249176025:  41%|████      | 10666/25880 [2:11:47<2:54:39,  1.45it/s]
1|10667|Loss: 0.7007919549942017:  41%|████      | 10666/25880 [2:11:48<2:54:39,  1.45it/s]
1|10667|Loss: 0.7007919549942017:  41%|████      | 10667/25880 [2:11:48<2:56:30,  1.44it/s]
1|10668|Loss: 0.9601762890815735:  41%|████      | 10667/25880 [2:11:48<2:56:30,  1.44it/s]
1|10668|Loss: 0.9601762890815735:  41%|████      | 10668/25880 [2:11:49<2:49:48,  1.49it/s]
1|10669|Loss: 0.8680080771446228:  41%|████      | 10668/25880 [2:11:49<2:49:48,  1.49it/s]
1|10669|Loss: 0.8680080771446228:  41%|████      | 10669/25880 [2:11:49<2:51:48,  1.48it/s]
1|10670|Loss: 0.7934973239898682:  41%|████      | 10669/25880 [2:11:50<2:51:48,  1.48it/s]
1|10670|Loss: 0.7934973239898682:  41%|████      | 10670/25880 [2:11:50<2:49:57,  1.49it/s]
1|10671|Loss: 1.0434393882751465:  41%|████      | 10670/25880 [2:11:50<2:49:57,  1.49it/s]
1|10671|Loss: 1.0434393882751465:  41%|████      | 10671/25880 [2:11:50<2:46:15,  1.52it/s]
1|10672|Loss: 0.8277760148048401:  41%|████      | 10671/25880 [2:11:51<2:46:15,  1.52it/s]
1|10672|Loss: 0.8277760148048401:  41%|████      | 10672/25880 [2:11:51<2:54:18,  1.45it/s]
1|10673|Loss: 1.049475908279419:  41%|████      | 10672/25880 [2:11:52<2:54:18,  1.45it/s] 
1|10673|Loss: 1.049475908279419:  41%|████      | 10673/25880 [2:11:52<3:04:19,  1.38it/s]
1|10674|Loss: 0.8864296078681946:  41%|████      | 10673/25880 [2:11:53<3:04:19,  1.38it/s]
1|10674|Loss: 0.8864296078681946:  41%|████      | 10674/25880 [2:11:53<3:09:06,  1.34it/s]
1|10675|Loss: 0.8069978952407837:  41%|████      | 10674/25880 [2:11:53<3:09:06,  1.34it/s]
1|10675|Loss: 0.8069978952407837:  41%|████      | 10675/25880 [2:11:54<3:12:39,  1.32it/s]
1|10676|Loss: 0.6228086352348328:  41%|████      | 10675/25880 [2:11:54<3:12:39,  1.32it/s]
1|10676|Loss: 0.6228086352348328:  41%|████▏     | 10676/25880 [2:11:54<3:11:25,  1.32it/s]
1|10677|Loss: 0.8523441553115845:  41%|████▏     | 10676/25880 [2:11:55<3:11:25,  1.32it/s]
1|10677|Loss: 0.8523441553115845:  41%|████▏     | 10677/25880 [2:11:55<2:57:20,  1.43it/s]
1|10678|Loss: 0.9163480401039124:  41%|████▏     | 10677/25880 [2:11:55<2:57:20,  1.43it/s]
1|10678|Loss: 0.9163480401039124:  41%|████▏     | 10678/25880 [2:11:56<2:50:35,  1.49it/s]
1|10679|Loss: 0.924944281578064:  41%|████▏     | 10678/25880 [2:11:56<2:50:35,  1.49it/s] 
1|10679|Loss: 0.924944281578064:  41%|████▏     | 10679/25880 [2:11:56<2:53:28,  1.46it/s]
1|10680|Loss: 0.8175080418586731:  41%|████▏     | 10679/25880 [2:11:57<2:53:28,  1.46it/s]
1|10680|Loss: 0.8175080418586731:  41%|████▏     | 10680/25880 [2:11:57<2:51:20,  1.48it/s]
1|10681|Loss: 0.8087185621261597:  41%|████▏     | 10680/25880 [2:11:57<2:51:20,  1.48it/s]
1|10681|Loss: 0.8087185621261597:  41%|████▏     | 10681/25880 [2:11:58<2:54:21,  1.45it/s]
1|10682|Loss: 0.9157059192657471:  41%|████▏     | 10681/25880 [2:11:58<2:54:21,  1.45it/s]
1|10682|Loss: 0.9157059192657471:  41%|████▏     | 10682/25880 [2:11:58<2:55:39,  1.44it/s]
1|10683|Loss: 0.7631179094314575:  41%|████▏     | 10682/25880 [2:11:59<2:55:39,  1.44it/s]
1|10683|Loss: 0.7631179094314575:  41%|████▏     | 10683/25880 [2:11:59<3:01:20,  1.40it/s]
1|10684|Loss: 0.7277095317840576:  41%|████▏     | 10683/25880 [2:12:00<3:01:20,  1.40it/s]
1|10684|Loss: 0.7277095317840576:  41%|████▏     | 10684/25880 [2:12:00<2:56:47,  1.43it/s]
1|10685|Loss: 0.8465237617492676:  41%|████▏     | 10684/25880 [2:12:00<2:56:47,  1.43it/s]
1|10685|Loss: 0.8465237617492676:  41%|████▏     | 10685/25880 [2:12:01<2:58:15,  1.42it/s]
1|10686|Loss: 0.8274772763252258:  41%|████▏     | 10685/25880 [2:12:01<2:58:15,  1.42it/s]
1|10686|Loss: 0.8274772763252258:  41%|████▏     | 10686/25880 [2:12:01<2:55:27,  1.44it/s]
1|10687|Loss: 0.8622350096702576:  41%|████▏     | 10686/25880 [2:12:02<2:55:27,  1.44it/s]
1|10687|Loss: 0.8622350096702576:  41%|████▏     | 10687/25880 [2:12:02<2:55:43,  1.44it/s]
1|10688|Loss: 1.0009684562683105:  41%|████▏     | 10687/25880 [2:12:02<2:55:43,  1.44it/s]
1|10688|Loss: 1.0009684562683105:  41%|████▏     | 10688/25880 [2:12:03<2:57:44,  1.42it/s]
1|10689|Loss: 0.8393414616584778:  41%|████▏     | 10688/25880 [2:12:03<2:57:44,  1.42it/s]
1|10689|Loss: 0.8393414616584778:  41%|████▏     | 10689/25880 [2:12:03<2:59:16,  1.41it/s]
1|10690|Loss: 0.8562522530555725:  41%|████▏     | 10689/25880 [2:12:04<2:59:16,  1.41it/s]
1|10690|Loss: 0.8562522530555725:  41%|████▏     | 10690/25880 [2:12:04<3:06:54,  1.35it/s]
1|10691|Loss: 1.0417969226837158:  41%|████▏     | 10690/25880 [2:12:05<3:06:54,  1.35it/s]
1|10691|Loss: 1.0417969226837158:  41%|████▏     | 10691/25880 [2:12:05<3:26:41,  1.22it/s]
1|10692|Loss: 0.9111959338188171:  41%|████▏     | 10691/25880 [2:12:06<3:26:41,  1.22it/s]
1|10692|Loss: 0.9111959338188171:  41%|████▏     | 10692/25880 [2:12:06<3:35:48,  1.17it/s]
1|10693|Loss: 0.8176516890525818:  41%|████▏     | 10692/25880 [2:12:07<3:35:48,  1.17it/s]
1|10693|Loss: 0.8176516890525818:  41%|████▏     | 10693/25880 [2:12:07<3:33:49,  1.18it/s]
1|10694|Loss: 0.8804936408996582:  41%|████▏     | 10693/25880 [2:12:07<3:33:49,  1.18it/s]
1|10694|Loss: 0.8804936408996582:  41%|████▏     | 10694/25880 [2:12:08<3:19:33,  1.27it/s]
1|10695|Loss: 0.820797324180603:  41%|████▏     | 10694/25880 [2:12:08<3:19:33,  1.27it/s] 
1|10695|Loss: 0.820797324180603:  41%|████▏     | 10695/25880 [2:12:08<3:00:06,  1.41it/s]
1|10696|Loss: 0.8107390403747559:  41%|████▏     | 10695/25880 [2:12:08<3:00:06,  1.41it/s]
1|10696|Loss: 0.8107390403747559:  41%|████▏     | 10696/25880 [2:12:09<2:56:44,  1.43it/s]
1|10697|Loss: 0.7767088413238525:  41%|████▏     | 10696/25880 [2:12:09<2:56:44,  1.43it/s]
1|10697|Loss: 0.7767088413238525:  41%|████▏     | 10697/25880 [2:12:10<3:02:00,  1.39it/s]
1|10698|Loss: 0.7797954678535461:  41%|████▏     | 10697/25880 [2:12:10<3:02:00,  1.39it/s]
1|10698|Loss: 0.7797954678535461:  41%|████▏     | 10698/25880 [2:12:10<2:55:22,  1.44it/s]
1|10699|Loss: 0.9042415618896484:  41%|████▏     | 10698/25880 [2:12:11<2:55:22,  1.44it/s]
1|10699|Loss: 0.9042415618896484:  41%|████▏     | 10699/25880 [2:12:11<2:54:38,  1.45it/s]
1|10700|Loss: 0.7412096261978149:  41%|████▏     | 10699/25880 [2:12:11<2:54:38,  1.45it/s]
1|10700|Loss: 0.7412096261978149:  41%|████▏     | 10700/25880 [2:12:11<2:51:09,  1.48it/s]
1|10701|Loss: 0.9098358154296875:  41%|████▏     | 10700/25880 [2:12:12<2:51:09,  1.48it/s]
1|10701|Loss: 0.9098358154296875:  41%|████▏     | 10701/25880 [2:12:12<2:55:03,  1.45it/s]
1|10702|Loss: 0.9029164910316467:  41%|████▏     | 10701/25880 [2:12:13<2:55:03,  1.45it/s]
1|10702|Loss: 0.9029164910316467:  41%|████▏     | 10702/25880 [2:12:13<2:58:46,  1.42it/s]
1|10703|Loss: 0.9785640239715576:  41%|████▏     | 10702/25880 [2:12:13<2:58:46,  1.42it/s]
1|10703|Loss: 0.9785640239715576:  41%|████▏     | 10703/25880 [2:12:14<3:00:44,  1.40it/s]
1|10704|Loss: 0.7638061046600342:  41%|████▏     | 10703/25880 [2:12:14<3:00:44,  1.40it/s]
1|10704|Loss: 0.7638061046600342:  41%|████▏     | 10704/25880 [2:12:14<2:57:10,  1.43it/s]
1|10705|Loss: 0.8259873390197754:  41%|████▏     | 10704/25880 [2:12:15<2:57:10,  1.43it/s]
1|10705|Loss: 0.8259873390197754:  41%|████▏     | 10705/25880 [2:12:15<2:58:13,  1.42it/s]
1|10706|Loss: 0.763071596622467:  41%|████▏     | 10705/25880 [2:12:15<2:58:13,  1.42it/s] 
1|10706|Loss: 0.763071596622467:  41%|████▏     | 10706/25880 [2:12:16<3:07:37,  1.35it/s]
1|10707|Loss: 0.7364208102226257:  41%|████▏     | 10706/25880 [2:12:16<3:07:37,  1.35it/s]
1|10707|Loss: 0.7364208102226257:  41%|████▏     | 10707/25880 [2:12:17<3:02:13,  1.39it/s]
1|10708|Loss: 0.7371721863746643:  41%|████▏     | 10707/25880 [2:12:17<3:02:13,  1.39it/s]
1|10708|Loss: 0.7371721863746643:  41%|████▏     | 10708/25880 [2:12:17<3:05:24,  1.36it/s]
1|10709|Loss: 0.878861129283905:  41%|████▏     | 10708/25880 [2:12:18<3:05:24,  1.36it/s] 
1|10709|Loss: 0.878861129283905:  41%|████▏     | 10709/25880 [2:12:18<3:13:03,  1.31it/s]
1|10710|Loss: 0.7430583238601685:  41%|████▏     | 10709/25880 [2:12:19<3:13:03,  1.31it/s]
1|10710|Loss: 0.7430583238601685:  41%|████▏     | 10710/25880 [2:12:19<3:27:21,  1.22it/s]
1|10711|Loss: 0.8849559426307678:  41%|████▏     | 10710/25880 [2:12:20<3:27:21,  1.22it/s]
1|10711|Loss: 0.8849559426307678:  41%|████▏     | 10711/25880 [2:12:20<3:13:35,  1.31it/s]
1|10712|Loss: 0.8331078886985779:  41%|████▏     | 10711/25880 [2:12:20<3:13:35,  1.31it/s]
1|10712|Loss: 0.8331078886985779:  41%|████▏     | 10712/25880 [2:12:20<3:08:29,  1.34it/s]
1|10713|Loss: 1.2170599699020386:  41%|████▏     | 10712/25880 [2:12:21<3:08:29,  1.34it/s]
1|10713|Loss: 1.2170599699020386:  41%|████▏     | 10713/25880 [2:12:22<3:42:04,  1.14it/s]
1|10714|Loss: 0.97670578956604:  41%|████▏     | 10713/25880 [2:12:22<3:42:04,  1.14it/s]  
1|10714|Loss: 0.97670578956604:  41%|████▏     | 10714/25880 [2:12:23<3:51:19,  1.09it/s]
1|10715|Loss: 0.8865302205085754:  41%|████▏     | 10714/25880 [2:12:23<3:51:19,  1.09it/s]
1|10715|Loss: 0.8865302205085754:  41%|████▏     | 10715/25880 [2:12:23<3:33:09,  1.19it/s]
1|10716|Loss: 0.7643341422080994:  41%|████▏     | 10715/25880 [2:12:24<3:33:09,  1.19it/s]
1|10716|Loss: 0.7643341422080994:  41%|████▏     | 10716/25880 [2:12:24<3:21:06,  1.26it/s]
1|10717|Loss: 0.9883163571357727:  41%|████▏     | 10716/25880 [2:12:24<3:21:06,  1.26it/s]
1|10717|Loss: 0.9883163571357727:  41%|████▏     | 10717/25880 [2:12:25<3:22:52,  1.25it/s]
1|10718|Loss: 0.7681995034217834:  41%|████▏     | 10717/25880 [2:12:25<3:22:52,  1.25it/s]
1|10718|Loss: 0.7681995034217834:  41%|████▏     | 10718/25880 [2:12:26<3:14:17,  1.30it/s]
1|10719|Loss: 0.8463014960289001:  41%|████▏     | 10718/25880 [2:12:26<3:14:17,  1.30it/s]
1|10719|Loss: 0.8463014960289001:  41%|████▏     | 10719/25880 [2:12:26<3:09:46,  1.33it/s]
1|10720|Loss: 0.8076915144920349:  41%|████▏     | 10719/25880 [2:12:27<3:09:46,  1.33it/s]
1|10720|Loss: 0.8076915144920349:  41%|████▏     | 10720/25880 [2:12:27<3:19:09,  1.27it/s]
1|10721|Loss: 0.8287942409515381:  41%|████▏     | 10720/25880 [2:12:27<3:19:09,  1.27it/s]
1|10721|Loss: 0.8287942409515381:  41%|████▏     | 10721/25880 [2:12:28<3:05:05,  1.37it/s]
1|10722|Loss: 0.854192852973938:  41%|████▏     | 10721/25880 [2:12:28<3:05:05,  1.37it/s] 
1|10722|Loss: 0.854192852973938:  41%|████▏     | 10722/25880 [2:12:28<2:59:49,  1.40it/s]
1|10723|Loss: 0.811510443687439:  41%|████▏     | 10722/25880 [2:12:29<2:59:49,  1.40it/s]
1|10723|Loss: 0.811510443687439:  41%|████▏     | 10723/25880 [2:12:29<2:48:19,  1.50it/s]
1|10724|Loss: 0.9233576655387878:  41%|████▏     | 10723/25880 [2:12:29<2:48:19,  1.50it/s]
1|10724|Loss: 0.9233576655387878:  41%|████▏     | 10724/25880 [2:12:30<2:48:21,  1.50it/s]
1|10725|Loss: 0.9040369987487793:  41%|████▏     | 10724/25880 [2:12:30<2:48:21,  1.50it/s]
1|10725|Loss: 0.9040369987487793:  41%|████▏     | 10725/25880 [2:12:30<2:47:27,  1.51it/s]
1|10726|Loss: 0.7741367816925049:  41%|████▏     | 10725/25880 [2:12:31<2:47:27,  1.51it/s]
1|10726|Loss: 0.7741367816925049:  41%|████▏     | 10726/25880 [2:12:31<2:49:37,  1.49it/s]
1|10727|Loss: 0.8036925196647644:  41%|████▏     | 10726/25880 [2:12:31<2:49:37,  1.49it/s]
1|10727|Loss: 0.8036925196647644:  41%|████▏     | 10727/25880 [2:12:32<2:54:02,  1.45it/s]
1|10728|Loss: 0.7986929416656494:  41%|████▏     | 10727/25880 [2:12:32<2:54:02,  1.45it/s]
1|10728|Loss: 0.7986929416656494:  41%|████▏     | 10728/25880 [2:12:32<2:52:09,  1.47it/s]
1|10729|Loss: 0.7135381698608398:  41%|████▏     | 10728/25880 [2:12:33<2:52:09,  1.47it/s]
1|10729|Loss: 0.7135381698608398:  41%|████▏     | 10729/25880 [2:12:33<2:53:16,  1.46it/s]
1|10730|Loss: 0.8426856994628906:  41%|████▏     | 10729/25880 [2:12:33<2:53:16,  1.46it/s]
1|10730|Loss: 0.8426856994628906:  41%|████▏     | 10730/25880 [2:12:34<2:46:37,  1.52it/s]
1|10731|Loss: 0.8291431069374084:  41%|████▏     | 10730/25880 [2:12:34<2:46:37,  1.52it/s]
1|10731|Loss: 0.8291431069374084:  41%|████▏     | 10731/25880 [2:12:34<2:43:47,  1.54it/s]
1|10732|Loss: 0.7753041386604309:  41%|████▏     | 10731/25880 [2:12:35<2:43:47,  1.54it/s]
1|10732|Loss: 0.7753041386604309:  41%|████▏     | 10732/25880 [2:12:35<2:43:12,  1.55it/s]
1|10733|Loss: 0.9073916673660278:  41%|████▏     | 10732/25880 [2:12:35<2:43:12,  1.55it/s]
1|10733|Loss: 0.9073916673660278:  41%|████▏     | 10733/25880 [2:12:36<2:51:29,  1.47it/s]
1|10734|Loss: 0.9114258289337158:  41%|████▏     | 10733/25880 [2:12:36<2:51:29,  1.47it/s]
1|10734|Loss: 0.9114258289337158:  41%|████▏     | 10734/25880 [2:12:36<3:00:49,  1.40it/s]
1|10735|Loss: 0.8258338570594788:  41%|████▏     | 10734/25880 [2:12:37<3:00:49,  1.40it/s]
1|10735|Loss: 0.8258338570594788:  41%|████▏     | 10735/25880 [2:12:37<2:57:49,  1.42it/s]
1|10736|Loss: 0.6672285795211792:  41%|████▏     | 10735/25880 [2:12:37<2:57:49,  1.42it/s]
1|10736|Loss: 0.6672285795211792:  41%|████▏     | 10736/25880 [2:12:38<2:53:16,  1.46it/s]
1|10737|Loss: 0.7428048849105835:  41%|████▏     | 10736/25880 [2:12:38<2:53:16,  1.46it/s]
1|10737|Loss: 0.7428048849105835:  41%|████▏     | 10737/25880 [2:12:38<2:49:49,  1.49it/s]
1|10738|Loss: 0.922317385673523:  41%|████▏     | 10737/25880 [2:12:39<2:49:49,  1.49it/s] 
1|10738|Loss: 0.922317385673523:  41%|████▏     | 10738/25880 [2:12:39<2:45:42,  1.52it/s]
1|10739|Loss: 0.7484551668167114:  41%|████▏     | 10738/25880 [2:12:39<2:45:42,  1.52it/s]
1|10739|Loss: 0.7484551668167114:  41%|████▏     | 10739/25880 [2:12:40<2:41:28,  1.56it/s]
1|10740|Loss: 0.8595396280288696:  41%|████▏     | 10739/25880 [2:12:40<2:41:28,  1.56it/s]
1|10740|Loss: 0.8595396280288696:  41%|████▏     | 10740/25880 [2:12:40<2:49:09,  1.49it/s]
1|10741|Loss: 0.9472992420196533:  41%|████▏     | 10740/25880 [2:12:41<2:49:09,  1.49it/s]
1|10741|Loss: 0.9472992420196533:  42%|████▏     | 10741/25880 [2:12:41<3:03:12,  1.38it/s]
1|10742|Loss: 0.8668478727340698:  42%|████▏     | 10741/25880 [2:12:42<3:03:12,  1.38it/s]
1|10742|Loss: 0.8668478727340698:  42%|████▏     | 10742/25880 [2:12:42<3:10:35,  1.32it/s]
1|10743|Loss: 0.8348732590675354:  42%|████▏     | 10742/25880 [2:12:42<3:10:35,  1.32it/s]
1|10743|Loss: 0.8348732590675354:  42%|████▏     | 10743/25880 [2:12:43<3:07:49,  1.34it/s]
1|10744|Loss: 0.8496582508087158:  42%|████▏     | 10743/25880 [2:12:43<3:07:49,  1.34it/s]
1|10744|Loss: 0.8496582508087158:  42%|████▏     | 10744/25880 [2:12:43<3:06:44,  1.35it/s]
1|10745|Loss: 0.7381354570388794:  42%|████▏     | 10744/25880 [2:12:44<3:06:44,  1.35it/s]
1|10745|Loss: 0.7381354570388794:  42%|████▏     | 10745/25880 [2:12:44<2:53:10,  1.46it/s]
1|10746|Loss: 0.7919394373893738:  42%|████▏     | 10745/25880 [2:12:44<2:53:10,  1.46it/s]
1|10746|Loss: 0.7919394373893738:  42%|████▏     | 10746/25880 [2:12:45<3:00:35,  1.40it/s]
1|10747|Loss: 0.6593176126480103:  42%|████▏     | 10746/25880 [2:12:45<3:00:35,  1.40it/s]
1|10747|Loss: 0.6593176126480103:  42%|████▏     | 10747/25880 [2:12:46<2:58:41,  1.41it/s]
1|10748|Loss: 0.9369370937347412:  42%|████▏     | 10747/25880 [2:12:46<2:58:41,  1.41it/s]
1|10748|Loss: 0.9369370937347412:  42%|████▏     | 10748/25880 [2:12:46<3:08:37,  1.34it/s]
1|10749|Loss: 0.7752540111541748:  42%|████▏     | 10748/25880 [2:12:47<3:08:37,  1.34it/s]
1|10749|Loss: 0.7752540111541748:  42%|████▏     | 10749/25880 [2:12:47<3:10:06,  1.33it/s]
1|10750|Loss: 0.830737292766571:  42%|████▏     | 10749/25880 [2:12:48<3:10:06,  1.33it/s] 
1|10750|Loss: 0.830737292766571:  42%|████▏     | 10750/25880 [2:12:48<3:15:52,  1.29it/s]
1|10751|Loss: 0.7594976425170898:  42%|████▏     | 10750/25880 [2:12:48<3:15:52,  1.29it/s]
1|10751|Loss: 0.7594976425170898:  42%|████▏     | 10751/25880 [2:12:49<3:18:07,  1.27it/s]
1|10752|Loss: 0.8457085490226746:  42%|████▏     | 10751/25880 [2:12:49<3:18:07,  1.27it/s]
1|10752|Loss: 0.8457085490226746:  42%|████▏     | 10752/25880 [2:12:50<3:15:52,  1.29it/s]
1|10753|Loss: 0.8918605446815491:  42%|████▏     | 10752/25880 [2:12:50<3:15:52,  1.29it/s]
1|10753|Loss: 0.8918605446815491:  42%|���███▏     | 10753/25880 [2:12:50<3:13:11,  1.31it/s]
1|10754|Loss: 0.9247340559959412:  42%|████▏     | 10753/25880 [2:12:51<3:13:11,  1.31it/s]
1|10754|Loss: 0.9247340559959412:  42%|████▏     | 10754/25880 [2:12:51<3:11:30,  1.32it/s]
1|10755|Loss: 0.7965480089187622:  42%|████▏     | 10754/25880 [2:12:51<3:11:30,  1.32it/s]
1|10755|Loss: 0.7965480089187622:  42%|████▏     | 10755/25880 [2:12:52<3:17:07,  1.28it/s]
1|10756|Loss: 0.8301482200622559:  42%|████▏     | 10755/25880 [2:12:52<3:17:07,  1.28it/s]
1|10756|Loss: 0.8301482200622559:  42%|████▏     | 10756/25880 [2:12:53<3:18:51,  1.27it/s]
1|10757|Loss: 0.8682823181152344:  42%|████▏     | 10756/25880 [2:12:53<3:18:51,  1.27it/s]
1|10757|Loss: 0.8682823181152344:  42%|████▏     | 10757/25880 [2:12:53<3:10:03,  1.33it/s]
1|10758|Loss: 0.9082140922546387:  42%|████▏     | 10757/25880 [2:12:54<3:10:03,  1.33it/s]
1|10758|Loss: 0.9082140922546387:  42%|████▏     | 10758/25880 [2:12:54<3:08:05,  1.34it/s]
1|10759|Loss: 0.88719642162323:  42%|████▏     | 10758/25880 [2:12:55<3:08:05,  1.34it/s]  
1|10759|Loss: 0.88719642162323:  42%|████▏     | 10759/25880 [2:12:55<3:15:07,  1.29it/s]
1|10760|Loss: 0.9834376573562622:  42%|████▏     | 10759/25880 [2:12:55<3:15:07,  1.29it/s]
1|10760|Loss: 0.9834376573562622:  42%|████▏     | 10760/25880 [2:12:56<3:12:31,  1.31it/s]
1|10761|Loss: 0.8006466031074524:  42%|████▏     | 10760/25880 [2:12:56<3:12:31,  1.31it/s]
1|10761|Loss: 0.8006466031074524:  42%|████▏     | 10761/25880 [2:12:56<3:09:23,  1.33it/s]
1|10762|Loss: 0.7825778722763062:  42%|████▏     | 10761/25880 [2:12:57<3:09:23,  1.33it/s]
1|10762|Loss: 0.7825778722763062:  42%|████▏     | 10762/25880 [2:12:57<3:01:01,  1.39it/s]
1|10763|Loss: 0.8598719835281372:  42%|████▏     | 10762/25880 [2:12:57<3:01:01,  1.39it/s]
1|10763|Loss: 0.8598719835281372:  42%|████▏     | 10763/25880 [2:12:58<3:00:26,  1.40it/s]
1|10764|Loss: 0.9558193683624268:  42%|████▏     | 10763/25880 [2:12:58<3:00:26,  1.40it/s]
1|10764|Loss: 0.9558193683624268:  42%|████▏     | 10764/25880 [2:12:58<2:59:44,  1.40it/s]
1|10765|Loss: 0.7858509421348572:  42%|████▏     | 10764/25880 [2:12:59<2:59:44,  1.40it/s]
1|10765|Loss: 0.7858509421348572:  42%|████▏     | 10765/25880 [2:12:59<3:05:15,  1.36it/s]
1|10766|Loss: 0.8109979629516602:  42%|████▏     | 10765/25880 [2:13:00<3:05:15,  1.36it/s]
1|10766|Loss: 0.8109979629516602:  42%|████▏     | 10766/25880 [2:13:00<2:56:48,  1.42it/s]
1|10767|Loss: 0.7172339558601379:  42%|████▏     | 10766/25880 [2:13:00<2:56:48,  1.42it/s]
1|10767|Loss: 0.7172339558601379:  42%|████▏     | 10767/25880 [2:13:01<2:56:20,  1.43it/s]
1|10768|Loss: 0.9059469103813171:  42%|████▏     | 10767/25880 [2:13:01<2:56:20,  1.43it/s]
1|10768|Loss: 0.9059469103813171:  42%|████▏     | 10768/25880 [2:13:01<2:59:16,  1.40it/s]
1|10769|Loss: 0.9410673379898071:  42%|████▏     | 10768/25880 [2:13:02<2:59:16,  1.40it/s]
1|10769|Loss: 0.9410673379898071:  42%|████▏     | 10769/25880 [2:13:02<2:55:46,  1.43it/s]
1|10770|Loss: 0.754990816116333:  42%|████▏     | 10769/25880 [2:13:02<2:55:46,  1.43it/s] 
1|10770|Loss: 0.754990816116333:  42%|████▏     | 10770/25880 [2:13:03<2:51:31,  1.47it/s]
1|10771|Loss: 0.8572760224342346:  42%|████▏     | 10770/25880 [2:13:03<2:51:31,  1.47it/s]
1|10771|Loss: 0.8572760224342346:  42%|████▏     | 10771/25880 [2:13:03<2:47:10,  1.51it/s]
1|10772|Loss: 0.6559095978736877:  42%|████▏     | 10771/25880 [2:13:04<2:47:10,  1.51it/s]
1|10772|Loss: 0.6559095978736877:  42%|████▏     | 10772/25880 [2:13:04<2:49:14,  1.49it/s]
1|10773|Loss: 0.8428416848182678:  42%|████▏     | 10772/25880 [2:13:04<2:49:14,  1.49it/s]
1|10773|Loss: 0.8428416848182678:  42%|████▏     | 10773/25880 [2:13:05<2:54:23,  1.44it/s]
1|10774|Loss: 0.7491841316223145:  42%|████▏     | 10773/25880 [2:13:05<2:54:23,  1.44it/s]
1|10774|Loss: 0.7491841316223145:  42%|████▏     | 10774/25880 [2:13:05<3:02:13,  1.38it/s]
1|10775|Loss: 0.7770130634307861:  42%|████▏     | 10774/25880 [2:13:06<3:02:13,  1.38it/s]
1|10775|Loss: 0.7770130634307861:  42%|████▏     | 10775/25880 [2:13:06<2:50:34,  1.48it/s]
1|10776|Loss: 0.8849263787269592:  42%|████▏     | 10775/25880 [2:13:06<2:50:34,  1.48it/s]
1|10776|Loss: 0.8849263787269592:  42%|████▏     | 10776/25880 [2:13:07<2:49:32,  1.48it/s]
1|10777|Loss: 0.9670916795730591:  42%|████▏     | 10776/25880 [2:13:07<2:49:32,  1.48it/s]
1|10777|Loss: 0.9670916795730591:  42%|████▏     | 10777/25880 [2:13:07<2:54:31,  1.44it/s]
1|10778|Loss: 0.8027409315109253:  42%|████▏     | 10777/25880 [2:13:08<2:54:31,  1.44it/s]
1|10778|Loss: 0.8027409315109253:  42%|████▏     | 10778/25880 [2:13:08<2:51:38,  1.47it/s]
1|10779|Loss: 0.7057048678398132:  42%|████▏     | 10778/25880 [2:13:08<2:51:38,  1.47it/s]
1|10779|Loss: 0.7057048678398132:  42%|████▏     | 10779/25880 [2:13:09<2:53:51,  1.45it/s]
1|10780|Loss: 0.829874575138092:  42%|████▏     | 10779/25880 [2:13:09<2:53:51,  1.45it/s] 
1|10780|Loss: 0.829874575138092:  42%|████▏     | 10780/25880 [2:13:10<3:06:32,  1.35it/s]
1|10781|Loss: 0.827134907245636:  42%|████▏     | 10780/25880 [2:13:10<3:06:32,  1.35it/s]
1|10781|Loss: 0.827134907245636:  42%|████▏     | 10781/25880 [2:13:10<2:59:20,  1.40it/s]
1|10782|Loss: 0.7756822109222412:  42%|████▏     | 10781/25880 [2:13:11<2:59:20,  1.40it/s]
1|10782|Loss: 0.7756822109222412:  42%|████▏     | 10782/25880 [2:13:11<2:46:05,  1.51it/s]
1|10783|Loss: 0.9348558783531189:  42%|████▏     | 10782/25880 [2:13:11<2:46:05,  1.51it/s]
1|10783|Loss: 0.9348558783531189:  42%|████▏     | 10783/25880 [2:13:11<2:41:37,  1.56it/s]
1|10784|Loss: 0.8982614278793335:  42%|████▏     | 10783/25880 [2:13:12<2:41:37,  1.56it/s]
1|10784|Loss: 0.8982614278793335:  42%|████▏     | 10784/25880 [2:13:12<2:46:52,  1.51it/s]
1|10785|Loss: 0.8423075675964355:  42%|████▏     | 10784/25880 [2:13:12<2:46:52,  1.51it/s]
1|10785|Loss: 0.8423075675964355:  42%|████▏     | 10785/25880 [2:13:13<2:46:43,  1.51it/s]
1|10786|Loss: 0.7781246304512024:  42%|████▏     | 10785/25880 [2:13:13<2:46:43,  1.51it/s]
1|10786|Loss: 0.7781246304512024:  42%|████▏     | 10786/25880 [2:13:13<2:41:56,  1.55it/s]
1|10787|Loss: 0.9634619951248169:  42%|████▏     | 10786/25880 [2:13:14<2:41:56,  1.55it/s]
1|10787|Loss: 0.9634619951248169:  42%|████▏     | 10787/25880 [2:13:14<2:46:50,  1.51it/s]
1|10788|Loss: 0.7114300727844238:  42%|████▏     | 10787/25880 [2:13:14<2:46:50,  1.51it/s]
1|10788|Loss: 0.7114300727844238:  42%|████▏     | 10788/25880 [2:13:15<2:44:06,  1.53it/s]
1|10789|Loss: 1.0898780822753906:  42%|████▏     | 10788/25880 [2:13:15<2:44:06,  1.53it/s]
1|10789|Loss: 1.0898780822753906:  42%|████▏     | 10789/25880 [2:13:15<2:39:32,  1.58it/s]
1|10790|Loss: 0.8191086053848267:  42%|████▏     | 10789/25880 [2:13:16<2:39:32,  1.58it/s]
1|10790|Loss: 0.8191086053848267:  42%|████▏     | 10790/25880 [2:13:16<2:37:09,  1.60it/s]
1|10791|Loss: 0.8377165794372559:  42%|████▏     | 10790/25880 [2:13:16<2:37:09,  1.60it/s]
1|10791|Loss: 0.8377165794372559:  42%|████▏     | 10791/25880 [2:13:17<2:49:38,  1.48it/s]
1|10792|Loss: 0.8607250452041626:  42%|████▏     | 10791/25880 [2:13:17<2:49:38,  1.48it/s]
1|10792|Loss: 0.8607250452041626:  42%|████▏     | 10792/25880 [2:13:17<2:55:32,  1.43it/s]
1|10793|Loss: 0.7230343818664551:  42%|████▏     | 10792/25880 [2:13:18<2:55:32,  1.43it/s]
1|10793|Loss: 0.7230343818664551:  42%|████▏     | 10793/25880 [2:13:18<2:56:53,  1.42it/s]
1|10794|Loss: 1.0019432306289673:  42%|████▏     | 10793/25880 [2:13:19<2:56:53,  1.42it/s]
1|10794|Loss: 1.0019432306289673:  42%|████▏     | 10794/25880 [2:13:19<3:04:23,  1.36it/s]
1|10795|Loss: 0.7837527990341187:  42%|████▏     | 10794/25880 [2:13:19<3:04:23,  1.36it/s]
1|10795|Loss: 0.7837527990341187:  42%|████▏     | 10795/25880 [2:13:20<3:06:00,  1.35it/s]
1|10796|Loss: 0.8232298493385315:  42%|████▏     | 10795/25880 [2:13:20<3:06:00,  1.35it/s]
1|10796|Loss: 0.8232298493385315:  42%|████▏     | 10796/25880 [2:13:21<3:13:04,  1.30it/s]
1|10797|Loss: 1.0593205690383911:  42%|████▏     | 10796/25880 [2:13:21<3:13:04,  1.30it/s]
1|10797|Loss: 1.0593205690383911:  42%|████▏     | 10797/25880 [2:13:21<3:10:54,  1.32it/s]
1|10798|Loss: 0.8800421953201294:  42%|████▏     | 10797/25880 [2:13:22<3:10:54,  1.32it/s]
1|10798|Loss: 0.8800421953201294:  42%|████▏     | 10798/25880 [2:13:22<3:14:47,  1.29it/s]
1|10799|Loss: 0.7944549322128296:  42%|████▏     | 10798/25880 [2:13:23<3:14:47,  1.29it/s]
1|10799|Loss: 0.7944549322128296:  42%|████▏     | 10799/25880 [2:13:23<3:13:31,  1.30it/s]
1|10800|Loss: 0.6712517142295837:  42%|████▏     | 10799/25880 [2:13:23<3:13:31,  1.30it/s]
1|10800|Loss: 0.6712517142295837:  42%|████▏     | 10800/25880 [2:13:23<2:57:19,  1.42it/s]
1|10801|Loss: 0.8222532272338867:  42%|████▏     | 10800/25880 [2:13:24<2:57:19,  1.42it/s]
1|10801|Loss: 0.8222532272338867:  42%|████▏     | 10801/25880 [2:13:24<3:03:04,  1.37it/s]
1|10802|Loss: 0.8496405482292175:  42%|████▏     | 10801/25880 [2:13:25<3:03:04,  1.37it/s]
1|10802|Loss: 0.8496405482292175:  42%|████▏     | 10802/25880 [2:13:25<3:12:47,  1.30it/s]
1|10803|Loss: 0.8900424838066101:  42%|████▏     | 10802/25880 [2:13:26<3:12:47,  1.30it/s]
1|10803|Loss: 0.8900424838066101:  42%|████▏     | 10803/25880 [2:13:26<3:12:52,  1.30it/s]
1|10804|Loss: 0.8408763408660889:  42%|████▏     | 10803/25880 [2:13:26<3:12:52,  1.30it/s]
1|10804|Loss: 0.8408763408660889:  42%|████▏     | 10804/25880 [2:13:26<2:55:47,  1.43it/s]
1|10805|Loss: 0.8114668130874634:  42%|████▏     | 10804/25880 [2:13:27<2:55:47,  1.43it/s]
1|10805|Loss: 0.8114668130874634:  42%|████▏     | 10805/25880 [2:13:27<2:53:41,  1.45it/s]
1|10806|Loss: 0.9963169693946838:  42%|████▏     | 10805/25880 [2:13:27<2:53:41,  1.45it/s]
1|10806|Loss: 0.9963169693946838:  42%|████▏     | 10806/25880 [2:13:28<2:51:05,  1.47it/s]
1|10807|Loss: 0.8310078978538513:  42%|████▏     | 10806/25880 [2:13:28<2:51:05,  1.47it/s]
1|10807|Loss: 0.8310078978538513:  42%|████▏     | 10807/25880 [2:13:28<2:40:00,  1.57it/s]
1|10808|Loss: 0.8682878017425537:  42%|████▏     | 10807/25880 [2:13:29<2:40:00,  1.57it/s]
1|10808|Loss: 0.8682878017425537:  42%|████▏     | 10808/25880 [2:13:29<2:41:28,  1.56it/s]
1|10809|Loss: 0.6881086230278015:  42%|████▏     | 10808/25880 [2:13:29<2:41:28,  1.56it/s]
1|10809|Loss: 0.6881086230278015:  42%|████▏     | 10809/25880 [2:13:30<2:42:05,  1.55it/s]
1|10810|Loss: 0.8388344049453735:  42%|████▏     | 10809/25880 [2:13:30<2:42:05,  1.55it/s]
1|10810|Loss: 0.8388344049453735:  42%|████▏     | 10810/25880 [2:13:30<2:45:22,  1.52it/s]
1|10811|Loss: 0.8305844068527222:  42%|████▏     | 10810/25880 [2:13:31<2:45:22,  1.52it/s]
1|10811|Loss: 0.8305844068527222:  42%|████▏     | 10811/25880 [2:13:31<2:54:34,  1.44it/s]
1|10812|Loss: 0.9979864954948425:  42%|████▏     | 10811/25880 [2:13:31<2:54:34,  1.44it/s]
1|10812|Loss: 0.9979864954948425:  42%|████▏     | 10812/25880 [2:13:32<2:56:16,  1.42it/s]
1|10813|Loss: 0.9138362407684326:  42%|████▏     | 10812/25880 [2:13:32<2:56:16,  1.42it/s]
1|10813|Loss: 0.9138362407684326:  42%|████▏     | 10813/25880 [2:13:32<2:55:43,  1.43it/s]
1|10814|Loss: 0.8639175295829773:  42%|████▏     | 10813/25880 [2:13:33<2:55:43,  1.43it/s]
1|10814|Loss: 0.8639175295829773:  42%|████▏     | 10814/25880 [2:13:33<2:55:21,  1.43it/s]
1|10815|Loss: 0.8628436326980591:  42%|████▏     | 10814/25880 [2:13:34<2:55:21,  1.43it/s]
1|10815|Loss: 0.8628436326980591:  42%|████▏     | 10815/25880 [2:13:34<3:01:39,  1.38it/s]
1|10816|Loss: 0.7598050236701965:  42%|████▏     | 10815/25880 [2:13:34<3:01:39,  1.38it/s]
1|10816|Loss: 0.7598050236701965:  42%|████▏     | 10816/25880 [2:13:35<3:16:47,  1.28it/s]
1|10817|Loss: 0.9038885831832886:  42%|████▏     | 10816/25880 [2:13:35<3:16:47,  1.28it/s]
1|10817|Loss: 0.9038885831832886:  42%|████▏     | 10817/25880 [2:13:36<3:24:08,  1.23it/s]
1|10818|Loss: 0.9241914749145508:  42%|████▏     | 10817/25880 [2:13:36<3:24:08,  1.23it/s]
1|10818|Loss: 0.9241914749145508:  42%|████▏     | 10818/25880 [2:13:36<3:14:54,  1.29it/s]
1|10819|Loss: 0.9943597316741943:  42%|████▏     | 10818/25880 [2:13:37<3:14:54,  1.29it/s]
1|10819|Loss: 0.9943597316741943:  42%|████▏     | 10819/25880 [2:13:37<2:58:03,  1.41it/s]
1|10820|Loss: 0.8538575768470764:  42%|████▏     | 10819/25880 [2:13:37<2:58:03,  1.41it/s]
1|10820|Loss: 0.8538575768470764:  42%|████▏     | 10820/25880 [2:13:38<2:56:51,  1.42it/s]
1|10821|Loss: 0.8861045837402344:  42%|████▏     | 10820/25880 [2:13:38<2:56:51,  1.42it/s]
1|10821|Loss: 0.8861045837402344:  42%|████▏     | 10821/25880 [2:13:39<3:08:24,  1.33it/s]
1|10822|Loss: 0.8112932443618774:  42%|████▏     | 10821/25880 [2:13:39<3:08:24,  1.33it/s]
1|10822|Loss: 0.8112932443618774:  42%|████▏     | 10822/25880 [2:13:39<3:13:03,  1.30it/s]
1|10823|Loss: 0.7496220469474792:  42%|████▏     | 10822/25880 [2:13:40<3:13:03,  1.30it/s]
1|10823|Loss: 0.7496220469474792:  42%|████▏     | 10823/25880 [2:13:40<3:19:49,  1.26it/s]
1|10824|Loss: 0.7122842669487:  42%|████▏     | 10823/25880 [2:13:41<3:19:49,  1.26it/s]   
1|10824|Loss: 0.7122842669487:  42%|████▏     | 10824/25880 [2:13:41<3:17:53,  1.27it/s]
1|10825|Loss: 0.9017693996429443:  42%|████▏     | 10824/25880 [2:13:41<3:17:53,  1.27it/s]
1|10825|Loss: 0.9017693996429443:  42%|████▏     | 10825/25880 [2:13:42<3:14:17,  1.29it/s]
1|10826|Loss: 0.8477537631988525:  42%|████▏     | 10825/25880 [2:13:42<3:14:17,  1.29it/s]
1|10826|Loss: 0.8477537631988525:  42%|████▏     | 10826/25880 [2:13:42<3:09:13,  1.33it/s]
1|10827|Loss: 0.8497812747955322:  42%|████▏     | 10826/25880 [2:13:43<3:09:13,  1.33it/s]
1|10827|Loss: 0.8497812747955322:  42%|████▏     | 10827/25880 [2:13:43<3:05:02,  1.36it/s]
1|10828|Loss: 0.7970690727233887:  42%|████▏     | 10827/25880 [2:13:43<3:05:02,  1.36it/s]
1|10828|Loss: 0.7970690727233887:  42%|████▏     | 10828/25880 [2:13:44<3:04:51,  1.36it/s]
1|10829|Loss: 0.8922131061553955:  42%|████▏     | 10828/25880 [2:13:44<3:04:51,  1.36it/s]
1|10829|Loss: 0.8922131061553955:  42%|████▏     | 10829/25880 [2:13:45<3:05:00,  1.36it/s]
1|10830|Loss: 0.9118041396141052:  42%|████▏     | 10829/25880 [2:13:45<3:05:00,  1.36it/s]
1|10830|Loss: 0.9118041396141052:  42%|████▏     | 10830/25880 [2:13:45<3:04:21,  1.36it/s]
1|10831|Loss: 0.7620413899421692:  42%|████▏     | 10830/25880 [2:13:46<3:04:21,  1.36it/s]
1|10831|Loss: 0.7620413899421692:  42%|████▏     | 10831/25880 [2:13:46<3:04:01,  1.36it/s]
1|10832|Loss: 0.7981230020523071:  42%|████▏     | 10831/25880 [2:13:46<3:04:01,  1.36it/s]
1|10832|Loss: 0.7981230020523071:  42%|████▏     | 10832/25880 [2:13:47<2:57:59,  1.41it/s]
1|10833|Loss: 0.7178854942321777:  42%|████▏     | 10832/25880 [2:13:47<2:57:59,  1.41it/s]
1|10833|Loss: 0.7178854942321777:  42%|████▏     | 10833/25880 [2:13:47<2:43:50,  1.53it/s]
1|10834|Loss: 0.5949934720993042:  42%|████▏     | 10833/25880 [2:13:48<2:43:50,  1.53it/s]
1|10834|Loss: 0.5949934720993042:  42%|████▏     | 10834/25880 [2:13:48<2:45:55,  1.51it/s]
1|10835|Loss: 0.7327930331230164:  42%|████▏     | 10834/25880 [2:13:48<2:45:55,  1.51it/s]
1|10835|Loss: 0.7327930331230164:  42%|████▏     | 10835/25880 [2:13:49<2:44:46,  1.52it/s]
1|10836|Loss: 0.8224671483039856:  42%|████▏     | 10835/25880 [2:13:49<2:44:46,  1.52it/s]
1|10836|Loss: 0.8224671483039856:  42%|████▏     | 10836/25880 [2:13:49<2:54:54,  1.43it/s]
1|10837|Loss: 0.9098877310752869:  42%|████▏     | 10836/25880 [2:13:50<2:54:54,  1.43it/s]
1|10837|Loss: 0.9098877310752869:  42%|████▏     | 10837/25880 [2:13:50<3:05:51,  1.35it/s]
1|10838|Loss: 0.8118323087692261:  42%|████▏     | 10837/25880 [2:13:51<3:05:51,  1.35it/s]
1|10838|Loss: 0.8118323087692261:  42%|████▏     | 10838/25880 [2:13:51<3:05:29,  1.35it/s]
1|10839|Loss: 0.8860564231872559:  42%|████▏     | 10838/25880 [2:13:51<3:05:29,  1.35it/s]
1|10839|Loss: 0.8860564231872559:  42%|████▏     | 10839/25880 [2:13:52<3:05:38,  1.35it/s]
1|10840|Loss: 0.7596500515937805:  42%|████▏     | 10839/25880 [2:13:52<3:05:38,  1.35it/s]
1|10840|Loss: 0.7596500515937805:  42%|████▏     | 10840/25880 [2:13:52<2:50:34,  1.47it/s]
1|10841|Loss: 0.8763217926025391:  42%|████▏     | 10840/25880 [2:13:53<2:50:34,  1.47it/s]
1|10841|Loss: 0.8763217926025391:  42%|████▏     | 10841/25880 [2:13:53<2:50:57,  1.47it/s]
1|10842|Loss: 0.7467610836029053:  42%|████▏     | 10841/25880 [2:13:53<2:50:57,  1.47it/s]
1|10842|Loss: 0.7467610836029053:  42%|████▏     | 10842/25880 [2:13:53<2:42:05,  1.55it/s]
1|10843|Loss: 1.1071157455444336:  42%|████▏     | 10842/25880 [2:13:54<2:42:05,  1.55it/s]
1|10843|Loss: 1.1071157455444336:  42%|████▏     | 10843/25880 [2:13:54<2:44:45,  1.52it/s]
1|10844|Loss: 0.747620165348053:  42%|████▏     | 10843/25880 [2:13:55<2:44:45,  1.52it/s] 
1|10844|Loss: 0.747620165348053:  42%|████▏     | 10844/25880 [2:13:55<2:57:18,  1.41it/s]
1|10845|Loss: 0.8877156376838684:  42%|████▏     | 10844/25880 [2:13:55<2:57:18,  1.41it/s]
1|10845|Loss: 0.8877156376838684:  42%|████▏     | 10845/25880 [2:13:56<2:59:41,  1.39it/s]
1|10846|Loss: 1.0204609632492065:  42%|████▏     | 10845/25880 [2:13:56<2:59:41,  1.39it/s]
1|10846|Loss: 1.0204609632492065:  42%|████▏     | 10846/25880 [2:13:56<2:59:49,  1.39it/s]
1|10847|Loss: 0.9015781283378601:  42%|████▏     | 10846/25880 [2:13:57<2:59:49,  1.39it/s]
1|10847|Loss: 0.9015781283378601:  42%|████▏     | 10847/25880 [2:13:57<3:00:44,  1.39it/s]
1|10848|Loss: 0.8998281359672546:  42%|████▏     | 10847/25880 [2:13:58<3:00:44,  1.39it/s]
1|10848|Loss: 0.8998281359672546:  42%|████▏     | 10848/25880 [2:13:58<3:02:32,  1.37it/s]
1|10849|Loss: 0.8745948672294617:  42%|████▏     | 10848/25880 [2:13:58<3:02:32,  1.37it/s]
1|10849|Loss: 0.8745948672294617:  42%|████▏     | 10849/25880 [2:13:59<3:10:06,  1.32it/s]
1|10850|Loss: 0.787032961845398:  42%|████▏     | 10849/25880 [2:13:59<3:10:06,  1.32it/s] 
1|10850|Loss: 0.787032961845398:  42%|████▏     | 10850/25880 [2:13:59<3:07:48,  1.33it/s]
1|10851|Loss: 0.7868471145629883:  42%|████▏     | 10850/25880 [2:14:00<3:07:48,  1.33it/s]
1|10851|Loss: 0.7868471145629883:  42%|████▏     | 10851/25880 [2:14:00<3:11:43,  1.31it/s]
1|10852|Loss: 0.9840433597564697:  42%|████▏     | 10851/25880 [2:14:01<3:11:43,  1.31it/s]
1|10852|Loss: 0.9840433597564697:  42%|████▏     | 10852/25880 [2:14:01<3:16:13,  1.28it/s]
1|10853|Loss: 0.9864316582679749:  42%|████▏     | 10852/25880 [2:14:01<3:16:13,  1.28it/s]
1|10853|Loss: 0.9864316582679749:  42%|████▏     | 10853/25880 [2:14:02<3:01:33,  1.38it/s]
1|10854|Loss: 0.9255266189575195:  42%|████▏     | 10853/25880 [2:14:02<3:01:33,  1.38it/s]
1|10854|Loss: 0.9255266189575195:  42%|████▏     | 10854/25880 [2:14:02<3:00:01,  1.39it/s]
1|10855|Loss: 0.9388048648834229:  42%|████▏     | 10854/25880 [2:14:03<3:00:01,  1.39it/s]
1|10855|Loss: 0.9388048648834229:  42%|████▏     | 10855/25880 [2:14:03<2:52:44,  1.45it/s]
1|10856|Loss: 0.9816501140594482:  42%|████▏     | 10855/25880 [2:14:03<2:52:44,  1.45it/s]
1|10856|Loss: 0.9816501140594482:  42%|████▏     | 10856/25880 [2:14:03<2:38:50,  1.58it/s]
1|10857|Loss: 0.8017256259918213:  42%|████▏     | 10856/25880 [2:14:04<2:38:50,  1.58it/s]
1|10857|Loss: 0.8017256259918213:  42%|████▏     | 10857/25880 [2:14:04<2:41:50,  1.55it/s]
1|10858|Loss: 0.7657068371772766:  42%|████▏     | 10857/25880 [2:14:04<2:41:50,  1.55it/s]
1|10858|Loss: 0.7657068371772766:  42%|████▏     | 10858/25880 [2:14:05<2:33:11,  1.63it/s]
1|10859|Loss: 0.9536200761795044:  42%|████▏     | 10858/25880 [2:14:05<2:33:11,  1.63it/s]
1|10859|Loss: 0.9536200761795044:  42%|████▏     | 10859/25880 [2:14:05<2:25:12,  1.72it/s]
1|10860|Loss: 0.8371928334236145:  42%|████▏     | 10859/25880 [2:14:06<2:25:12,  1.72it/s]
1|10860|Loss: 0.8371928334236145:  42%|████▏     | 10860/25880 [2:14:06<2:26:20,  1.71it/s]
1|10861|Loss: 0.7198392748832703:  42%|████▏     | 10860/25880 [2:14:06<2:26:20,  1.71it/s]
1|10861|Loss: 0.7198392748832703:  42%|████▏     | 10861/25880 [2:14:06<2:30:36,  1.66it/s]
1|10862|Loss: 0.8790541887283325:  42%|████▏     | 10861/25880 [2:14:07<2:30:36,  1.66it/s]
1|10862|Loss: 0.8790541887283325:  42%|████▏     | 10862/25880 [2:14:07<2:39:48,  1.57it/s]
1|10863|Loss: 0.7746639847755432:  42%|████▏     | 10862/25880 [2:14:08<2:39:48,  1.57it/s]
1|10863|Loss: 0.7746639847755432:  42%|████▏     | 10863/25880 [2:14:08<2:45:41,  1.51it/s]
1|10864|Loss: 0.9032383561134338:  42%|████▏     | 10863/25880 [2:14:08<2:45:41,  1.51it/s]
1|10864|Loss: 0.9032383561134338:  42%|████▏     | 10864/25880 [2:14:08<2:39:36,  1.57it/s]
1|10865|Loss: 0.770382285118103:  42%|████▏     | 10864/25880 [2:14:09<2:39:36,  1.57it/s] 
1|10865|Loss: 0.770382285118103:  42%|████▏     | 10865/25880 [2:14:09<2:55:07,  1.43it/s]
1|10866|Loss: 0.8687819838523865:  42%|████▏     | 10865/25880 [2:14:10<2:55:07,  1.43it/s]
1|10866|Loss: 0.8687819838523865:  42%|████▏     | 10866/25880 [2:14:10<2:53:16,  1.44it/s]
1|10867|Loss: 0.7285031676292419:  42%|████▏     | 10866/25880 [2:14:10<2:53:16,  1.44it/s]
1|10867|Loss: 0.7285031676292419:  42%|████▏     | 10867/25880 [2:14:11<2:52:45,  1.45it/s]
1|10868|Loss: 0.8349321484565735:  42%|████▏     | 10867/25880 [2:14:11<2:52:45,  1.45it/s]
1|10868|Loss: 0.8349321484565735:  42%|████▏     | 10868/25880 [2:14:11<3:01:17,  1.38it/s]
1|10869|Loss: 0.7624273896217346:  42%|████▏     | 10868/25880 [2:14:12<3:01:17,  1.38it/s]
1|10869|Loss: 0.7624273896217346:  42%|████▏     | 10869/25880 [2:14:12<3:01:06,  1.38it/s]
1|10870|Loss: 0.8693422079086304:  42%|████▏     | 10869/25880 [2:14:13<3:01:06,  1.38it/s]
1|10870|Loss: 0.8693422079086304:  42%|████▏     | 10870/25880 [2:14:13<3:06:47,  1.34it/s]
1|10871|Loss: 0.8456081748008728:  42%|████▏     | 10870/25880 [2:14:13<3:06:47,  1.34it/s]
1|10871|Loss: 0.8456081748008728:  42%|████▏     | 10871/25880 [2:14:14<3:01:18,  1.38it/s]
1|10872|Loss: 0.6845036149024963:  42%|████▏     | 10871/25880 [2:14:14<3:01:18,  1.38it/s]
1|10872|Loss: 0.6845036149024963:  42%|████▏     | 10872/25880 [2:14:14<3:00:54,  1.38it/s]
1|10873|Loss: 0.9465963244438171:  42%|████▏     | 10872/25880 [2:14:15<3:00:54,  1.38it/s]
1|10873|Loss: 0.9465963244438171:  42%|████▏     | 10873/25880 [2:14:15<2:55:09,  1.43it/s]
1|10874|Loss: 0.8777396082878113:  42%|████▏     | 10873/25880 [2:14:15<2:55:09,  1.43it/s]
1|10874|Loss: 0.8777396082878113:  42%|████▏     | 10874/25880 [2:14:16<2:56:08,  1.42it/s]
1|10875|Loss: 0.8077568411827087:  42%|████▏     | 10874/25880 [2:14:16<2:56:08,  1.42it/s]
1|10875|Loss: 0.8077568411827087:  42%|████▏     | 10875/25880 [2:14:17<3:13:52,  1.29it/s]
1|10876|Loss: 0.8329669833183289:  42%|████▏     | 10875/25880 [2:14:17<3:13:52,  1.29it/s]
1|10876|Loss: 0.8329669833183289:  42%|████▏     | 10876/25880 [2:14:18<3:26:36,  1.21it/s]
1|10877|Loss: 0.8536368608474731:  42%|████▏     | 10876/25880 [2:14:18<3:26:36,  1.21it/s]
1|10877|Loss: 0.8536368608474731:  42%|████▏     | 10877/25880 [2:14:18<3:13:51,  1.29it/s]
1|10878|Loss: 0.7915982604026794:  42%|████▏     | 10877/25880 [2:14:19<3:13:51,  1.29it/s]
1|10878|Loss: 0.7915982604026794:  42%|████▏     | 10878/25880 [2:14:19<3:09:28,  1.32it/s]
1|10879|Loss: 0.8099988698959351:  42%|███��▏     | 10878/25880 [2:14:19<3:09:28,  1.32it/s]
1|10879|Loss: 0.8099988698959351:  42%|████▏     | 10879/25880 [2:14:20<3:06:38,  1.34it/s]
1|10880|Loss: 0.9388766288757324:  42%|████▏     | 10879/25880 [2:14:20<3:06:38,  1.34it/s]
1|10880|Loss: 0.9388766288757324:  42%|████▏     | 10880/25880 [2:14:21<3:09:21,  1.32it/s]
1|10881|Loss: 0.9079104661941528:  42%|████▏     | 10880/25880 [2:14:21<3:09:21,  1.32it/s]
1|10881|Loss: 0.9079104661941528:  42%|████▏     | 10881/25880 [2:14:21<3:08:34,  1.33it/s]
1|10882|Loss: 0.902338445186615:  42%|████▏     | 10881/25880 [2:14:22<3:08:34,  1.33it/s] 
1|10882|Loss: 0.902338445186615:  42%|████▏     | 10882/25880 [2:14:22<3:13:23,  1.29it/s]
1|10883|Loss: 1.046032428741455:  42%|████▏     | 10882/25880 [2:14:22<3:13:23,  1.29it/s]
1|10883|Loss: 1.046032428741455:  42%|████▏     | 10883/25880 [2:14:23<3:04:39,  1.35it/s]
1|10884|Loss: 0.826796293258667:  42%|████▏     | 10883/25880 [2:14:23<3:04:39,  1.35it/s]
1|10884|Loss: 0.826796293258667:  42%|████▏     | 10884/25880 [2:14:23<2:53:08,  1.44it/s]
1|10885|Loss: 0.8633924722671509:  42%|████▏     | 10884/25880 [2:14:24<2:53:08,  1.44it/s]
1|10885|Loss: 0.8633924722671509:  42%|████▏     | 10885/25880 [2:14:24<2:57:57,  1.40it/s]
1|10886|Loss: 0.7641741037368774:  42%|████▏     | 10885/25880 [2:14:24<2:57:57,  1.40it/s]
1|10886|Loss: 0.7641741037368774:  42%|████▏     | 10886/25880 [2:14:25<2:51:28,  1.46it/s]
1|10887|Loss: 0.8081876039505005:  42%|████▏     | 10886/25880 [2:14:25<2:51:28,  1.46it/s]
1|10887|Loss: 0.8081876039505005:  42%|████▏     | 10887/25880 [2:14:25<2:50:28,  1.47it/s]
1|10888|Loss: 0.8573405742645264:  42%|████▏     | 10887/25880 [2:14:26<2:50:28,  1.47it/s]
1|10888|Loss: 0.8573405742645264:  42%|████▏     | 10888/25880 [2:14:26<2:53:14,  1.44it/s]
1|10889|Loss: 0.8254184126853943:  42%|████▏     | 10888/25880 [2:14:26<2:53:14,  1.44it/s]
1|10889|Loss: 0.8254184126853943:  42%|████▏     | 10889/25880 [2:14:27<2:56:40,  1.41it/s]
1|10890|Loss: 0.8689664006233215:  42%|████▏     | 10889/25880 [2:14:27<2:56:40,  1.41it/s]
1|10890|Loss: 0.8689664006233215:  42%|████▏     | 10890/25880 [2:14:28<3:02:00,  1.37it/s]
1|10891|Loss: 0.8629610538482666:  42%|████▏     | 10890/25880 [2:14:28<3:02:00,  1.37it/s]
1|10891|Loss: 0.8629610538482666:  42%|████▏     | 10891/25880 [2:14:28<3:07:39,  1.33it/s]
1|10892|Loss: 0.8659682869911194:  42%|████▏     | 10891/25880 [2:14:29<3:07:39,  1.33it/s]
1|10892|Loss: 0.8659682869911194:  42%|████▏     | 10892/25880 [2:14:29<3:01:42,  1.37it/s]
1|10893|Loss: 1.0004135370254517:  42%|████▏     | 10892/25880 [2:14:29<3:01:42,  1.37it/s]
1|10893|Loss: 1.0004135370254517:  42%|████▏     | 10893/25880 [2:14:30<3:01:08,  1.38it/s]
1|10894|Loss: 0.9942587018013:  42%|████▏     | 10893/25880 [2:14:30<3:01:08,  1.38it/s]   
1|10894|Loss: 0.9942587018013:  42%|████▏     | 10894/25880 [2:14:31<3:16:13,  1.27it/s]
1|10895|Loss: 0.8277096152305603:  42%|████▏     | 10894/25880 [2:14:31<3:16:13,  1.27it/s]
1|10895|Loss: 0.8277096152305603:  42%|████▏     | 10895/25880 [2:14:32<3:16:38,  1.27it/s]
1|10896|Loss: 0.9348232746124268:  42%|████▏     | 10895/25880 [2:14:32<3:16:38,  1.27it/s]
1|10896|Loss: 0.9348232746124268:  42%|████▏     | 10896/25880 [2:14:32<3:06:13,  1.34it/s]
1|10897|Loss: 0.8858089447021484:  42%|████▏     | 10896/25880 [2:14:33<3:06:13,  1.34it/s]
1|10897|Loss: 0.8858089447021484:  42%|████▏     | 10897/25880 [2:14:33<2:57:46,  1.40it/s]
1|10898|Loss: 0.8883414268493652:  42%|████▏     | 10897/25880 [2:14:33<2:57:46,  1.40it/s]
1|10898|Loss: 0.8883414268493652:  42%|████▏     | 10898/25880 [2:14:33<2:45:01,  1.51it/s]
1|10899|Loss: 0.7735148668289185:  42%|████▏     | 10898/25880 [2:14:34<2:45:01,  1.51it/s]
1|10899|Loss: 0.7735148668289185:  42%|████▏     | 10899/25880 [2:14:34<2:47:42,  1.49it/s]
1|10900|Loss: 0.9391480088233948:  42%|████▏     | 10899/25880 [2:14:34<2:47:42,  1.49it/s]
1|10900|Loss: 0.9391480088233948:  42%|████▏     | 10900/25880 [2:14:35<2:47:03,  1.49it/s]
1|10901|Loss: 0.8175884485244751:  42%|████▏     | 10900/25880 [2:14:35<2:47:03,  1.49it/s]
1|10901|Loss: 0.8175884485244751:  42%|████▏     | 10901/25880 [2:14:35<2:53:42,  1.44it/s]
1|10902|Loss: 0.7863398194313049:  42%|████▏     | 10901/25880 [2:14:36<2:53:42,  1.44it/s]
1|10902|Loss: 0.7863398194313049:  42%|████▏     | 10902/25880 [2:14:36<3:06:43,  1.34it/s]
1|10903|Loss: 0.9032222032546997:  42%|████▏     | 10902/25880 [2:14:37<3:06:43,  1.34it/s]
1|10903|Loss: 0.9032222032546997:  42%|████▏     | 10903/25880 [2:14:37<3:08:50,  1.32it/s]
1|10904|Loss: 0.9381325840950012:  42%|████▏     | 10903/25880 [2:14:38<3:08:50,  1.32it/s]
1|10904|Loss: 0.9381325840950012:  42%|████▏     | 10904/25880 [2:14:38<3:07:39,  1.33it/s]
1|10905|Loss: 0.8138692378997803:  42%|████▏     | 10904/25880 [2:14:38<3:07:39,  1.33it/s]
1|10905|Loss: 0.8138692378997803:  42%|████▏     | 10905/25880 [2:14:39<3:19:59,  1.25it/s]
1|10906|Loss: 0.9267295598983765:  42%|████▏     | 10905/25880 [2:14:39<3:19:59,  1.25it/s]
1|10906|Loss: 0.9267295598983765:  42%|████▏     | 10906/25880 [2:14:40<3:16:38,  1.27it/s]
1|10907|Loss: 0.8288059830665588:  42%|████▏     | 10906/25880 [2:14:40<3:16:38,  1.27it/s]
1|10907|Loss: 0.8288059830665588:  42%|████▏     | 10907/25880 [2:14:40<3:20:26,  1.24it/s]
1|10908|Loss: 0.8809263110160828:  42%|████▏     | 10907/25880 [2:14:41<3:20:26,  1.24it/s]
1|10908|Loss: 0.8809263110160828:  42%|████▏     | 10908/25880 [2:14:41<3:12:15,  1.30it/s]
1|10909|Loss: 0.9676265716552734:  42%|████▏     | 10908/25880 [2:14:41<3:12:15,  1.30it/s]
1|10909|Loss: 0.9676265716552734:  42%|████▏     | 10909/25880 [2:14:42<3:14:00,  1.29it/s]
1|10910|Loss: 0.8524132370948792:  42%|████▏     | 10909/25880 [2:14:42<3:14:00,  1.29it/s]
1|10910|Loss: 0.8524132370948792:  42%|████▏     | 10910/25880 [2:14:43<3:12:15,  1.30it/s]
1|10911|Loss: 0.9877897500991821:  42%|████▏     | 10910/25880 [2:14:43<3:12:15,  1.30it/s]
1|10911|Loss: 0.9877897500991821:  42%|████▏     | 10911/25880 [2:14:43<3:04:38,  1.35it/s]
1|10912|Loss: 0.7909331917762756:  42%|████▏     | 10911/25880 [2:14:44<3:04:38,  1.35it/s]
1|10912|Loss: 0.7909331917762756:  42%|████▏     | 10912/25880 [2:14:44<2:57:06,  1.41it/s]
1|10913|Loss: 0.6325829029083252:  42%|████▏     | 10912/25880 [2:14:44<2:57:06,  1.41it/s]
1|10913|Loss: 0.6325829029083252:  42%|████▏     | 10913/25880 [2:14:45<2:51:29,  1.45it/s]
1|10914|Loss: 0.8308912515640259:  42%|████▏     | 10913/25880 [2:14:45<2:51:29,  1.45it/s]
1|10914|Loss: 0.8308912515640259:  42%|████▏     | 10914/25880 [2:14:45<2:59:35,  1.39it/s]
1|10915|Loss: 0.8169092535972595:  42%|████▏     | 10914/25880 [2:14:46<2:59:35,  1.39it/s]
1|10915|Loss: 0.8169092535972595:  42%|████▏     | 10915/25880 [2:14:46<3:07:27,  1.33it/s]
1|10916|Loss: 0.7897192239761353:  42%|████▏     | 10915/25880 [2:14:47<3:07:27,  1.33it/s]
1|10916|Loss: 0.7897192239761353:  42%|████▏     | 10916/25880 [2:14:47<3:07:47,  1.33it/s]
1|10917|Loss: 0.7381330132484436:  42%|████▏     | 10916/25880 [2:14:47<3:07:47,  1.33it/s]
1|10917|Loss: 0.7381330132484436:  42%|████▏     | 10917/25880 [2:14:48<3:11:28,  1.30it/s]
1|10918|Loss: 0.8409838080406189:  42%|████▏     | 10917/25880 [2:14:48<3:11:28,  1.30it/s]
1|10918|Loss: 0.8409838080406189:  42%|████▏     | 10918/25880 [2:14:49<3:15:51,  1.27it/s]
1|10919|Loss: 0.830365777015686:  42%|████▏     | 10918/25880 [2:14:49<3:15:51,  1.27it/s] 
1|10919|Loss: 0.830365777015686:  42%|████▏     | 10919/25880 [2:14:49<3:20:13,  1.25it/s]
1|10920|Loss: 0.5519362092018127:  42%|████▏     | 10919/25880 [2:14:50<3:20:13,  1.25it/s]
1|10920|Loss: 0.5519362092018127:  42%|████▏     | 10920/25880 [2:14:50<3:00:31,  1.38it/s]
1|10921|Loss: 0.8127641677856445:  42%|████▏     | 10920/25880 [2:14:50<3:00:31,  1.38it/s]
1|10921|Loss: 0.8127641677856445:  42%|████▏     | 10921/25880 [2:14:50<2:47:21,  1.49it/s]
1|10922|Loss: 0.8624234199523926:  42%|████▏     | 10921/25880 [2:14:51<2:47:21,  1.49it/s]
1|10922|Loss: 0.8624234199523926:  42%|████▏     | 10922/25880 [2:14:51<2:49:51,  1.47it/s]
1|10923|Loss: 0.8842864036560059:  42%|████▏     | 10922/25880 [2:14:52<2:49:51,  1.47it/s]
1|10923|Loss: 0.8842864036560059:  42%|████▏     | 10923/25880 [2:14:52<2:54:54,  1.43it/s]
1|10924|Loss: 0.7969441413879395:  42%|████▏     | 10923/25880 [2:14:52<2:54:54,  1.43it/s]
1|10924|Loss: 0.7969441413879395:  42%|████▏     | 10924/25880 [2:14:53<2:48:04,  1.48it/s]
1|10925|Loss: 0.7207008600234985:  42%|████▏     | 10924/25880 [2:14:53<2:48:04,  1.48it/s]
1|10925|Loss: 0.7207008600234985:  42%|████▏     | 10925/25880 [2:14:53<2:49:42,  1.47it/s]
1|10926|Loss: 0.9031233191490173:  42%|████▏     | 10925/25880 [2:14:54<2:49:42,  1.47it/s]
1|10926|Loss: 0.9031233191490173:  42%|████▏     | 10926/25880 [2:14:54<2:53:37,  1.44it/s]
1|10927|Loss: 0.8264527916908264:  42%|████▏     | 10926/25880 [2:14:54<2:53:37,  1.44it/s]
1|10927|Loss: 0.8264527916908264:  42%|████▏     | 10927/25880 [2:14:55<2:46:06,  1.50it/s]
1|10928|Loss: 0.8773489594459534:  42%|████▏     | 10927/25880 [2:14:55<2:46:06,  1.50it/s]
1|10928|Loss: 0.8773489594459534:  42%|████▏     | 10928/25880 [2:14:55<2:51:38,  1.45it/s]
1|10929|Loss: 0.7494533061981201:  42%|████▏     | 10928/25880 [2:14:56<2:51:38,  1.45it/s]
1|10929|Loss: 0.7494533061981201:  42%|████▏     | 10929/25880 [2:14:56<2:54:27,  1.43it/s]
1|10930|Loss: 0.7585484385490417:  42%|████▏     | 10929/25880 [2:14:56<2:54:27,  1.43it/s]
1|10930|Loss: 0.7585484385490417:  42%|████▏     | 10930/25880 [2:14:57<3:07:03,  1.33it/s]
1|10931|Loss: 0.837591290473938:  42%|████▏     | 10930/25880 [2:14:57<3:07:03,  1.33it/s] 
1|10931|Loss: 0.837591290473938:  42%|████▏     | 10931/25880 [2:14:58<3:06:17,  1.34it/s]
1|10932|Loss: 0.8016859292984009:  42%|████▏     | 10931/25880 [2:14:58<3:06:17,  1.34it/s]
1|10932|Loss: 0.8016859292984009:  42%|████▏     | 10932/25880 [2:14:58<2:58:59,  1.39it/s]
1|10933|Loss: 0.6983245611190796:  42%|████▏     | 10932/25880 [2:14:59<2:58:59,  1.39it/s]
1|10933|Loss: 0.6983245611190796:  42%|████▏     | 10933/25880 [2:14:59<2:57:16,  1.41it/s]
1|10934|Loss: 0.9133211374282837:  42%|████▏     | 10933/25880 [2:14:59<2:57:16,  1.41it/s]
1|10934|Loss: 0.9133211374282837:  42%|████▏     | 10934/25880 [2:15:00<3:01:21,  1.37it/s]
1|10935|Loss: 0.9397004842758179:  42%|████▏     | 10934/25880 [2:15:00<3:01:21,  1.37it/s]
1|10935|Loss: 0.9397004842758179:  42%|████▏     | 10935/25880 [2:15:01<3:06:44,  1.33it/s]
1|10936|Loss: 0.7281338572502136:  42%|████▏     | 10935/25880 [2:15:01<3:06:44,  1.33it/s]
1|10936|Loss: 0.7281338572502136:  42%|████▏     | 10936/25880 [2:15:01<3:10:43,  1.31it/s]
1|10937|Loss: 0.9013638496398926:  42%|████▏     | 10936/25880 [2:15:02<3:10:43,  1.31it/s]
1|10937|Loss: 0.9013638496398926:  42%|████▏     | 10937/25880 [2:15:02<3:03:26,  1.36it/s]
1|10938|Loss: 1.077081561088562:  42%|████▏     | 10937/25880 [2:15:02<3:03:26,  1.36it/s] 
1|10938|Loss: 1.077081561088562:  42%|████▏     | 10938/25880 [2:15:03<3:10:10,  1.31it/s]
1|10939|Loss: 0.8524488806724548:  42%|████▏     | 10938/25880 [2:15:03<3:10:10,  1.31it/s]
1|10939|Loss: 0.8524488806724548:  42%|████▏     | 10939/25880 [2:15:04<3:16:15,  1.27it/s]
1|10940|Loss: 0.8891621232032776:  42%|████▏     | 10939/25880 [2:15:04<3:16:15,  1.27it/s]
1|10940|Loss: 0.8891621232032776:  42%|████▏     | 10940/25880 [2:15:05<3:22:24,  1.23it/s]
1|10941|Loss: 0.8445562124252319:  42%|████▏     | 10940/25880 [2:15:05<3:22:24,  1.23it/s]
1|10941|Loss: 0.8445562124252319:  42%|████▏     | 10941/25880 [2:15:05<3:29:59,  1.19it/s]
1|10942|Loss: 0.8908336162567139:  42%|████▏     | 10941/25880 [2:15:06<3:29:59,  1.19it/s]
1|10942|Loss: 0.8908336162567139:  42%|████▏     | 10942/25880 [2:15:06<3:30:24,  1.18it/s]
1|10943|Loss: 0.8741625547409058:  42%|████▏     | 10942/25880 [2:15:07<3:30:24,  1.18it/s]
1|10943|Loss: 0.8741625547409058:  42%|████▏     | 10943/25880 [2:15:07<3:10:10,  1.31it/s]
1|10944|Loss: 0.806523859500885:  42%|████▏     | 10943/25880 [2:15:07<3:10:10,  1.31it/s] 
1|10944|Loss: 0.806523859500885:  42%|████▏     | 10944/25880 [2:15:08<2:57:17,  1.40it/s]
1|10945|Loss: 0.7702091336250305:  42%|████▏     | 10944/25880 [2:15:08<2:57:17,  1.40it/s]
1|10945|Loss: 0.7702091336250305:  42%|████▏     | 10945/25880 [2:15:08<3:04:23,  1.35it/s]
1|10946|Loss: 0.8719278573989868:  42%|████▏     | 10945/25880 [2:15:09<3:04:23,  1.35it/s]
1|10946|Loss: 0.8719278573989868:  42%|████▏     | 10946/25880 [2:15:09<3:04:39,  1.35it/s]
1|10947|Loss: 0.7480581402778625:  42%|████▏     | 10946/25880 [2:15:09<3:04:39,  1.35it/s]
1|10947|Loss: 0.7480581402778625:  42%|████▏     | 10947/25880 [2:15:10<3:11:10,  1.30it/s]
1|10948|Loss: 1.0323785543441772:  42%|████▏     | 10947/25880 [2:15:10<3:11:10,  1.30it/s]
1|10948|Loss: 1.0323785543441772:  42%|████▏     | 10948/25880 [2:15:11<3:04:00,  1.35it/s]
1|10949|Loss: 0.8942877054214478:  42%|████▏     | 10948/25880 [2:15:11<3:04:00,  1.35it/s]
1|10949|Loss: 0.8942877054214478:  42%|████▏     | 10949/25880 [2:15:11<2:56:10,  1.41it/s]
1|10950|Loss: 0.77470862865448:  42%|████▏     | 10949/25880 [2:15:12<2:56:10,  1.41it/s]  
1|10950|Loss: 0.77470862865448:  42%|████▏     | 10950/25880 [2:15:12<2:56:24,  1.41it/s]
1|10951|Loss: 0.7410926222801208:  42%|████▏     | 10950/25880 [2:15:12<2:56:24,  1.41it/s]
1|10951|Loss: 0.7410926222801208:  42%|████▏     | 10951/25880 [2:15:13<3:09:11,  1.32it/s]
1|10952|Loss: 0.9757861495018005:  42%|████▏     | 10951/25880 [2:15:13<3:09:11,  1.32it/s]
1|10952|Loss: 0.9757861495018005:  42%|████▏     | 10952/25880 [2:15:13<3:04:39,  1.35it/s]
1|10953|Loss: 0.7909418344497681:  42%|████▏     | 10952/25880 [2:15:14<3:04:39,  1.35it/s]
1|10953|Loss: 0.7909418344497681:  42%|████▏     | 10953/25880 [2:15:14<2:47:53,  1.48it/s]
1|10954|Loss: 0.9035505652427673:  42%|████▏     | 10953/25880 [2:15:14<2:47:53,  1.48it/s]
1|10954|Loss: 0.9035505652427673:  42%|████▏     | 10954/25880 [2:15:15<2:48:24,  1.48it/s]
1|10955|Loss: 0.8928396701812744:  42%|████▏     | 10954/25880 [2:15:15<2:48:24,  1.48it/s]
1|10955|Loss: 0.8928396701812744:  42%|████▏     | 10955/25880 [2:15:15<2:52:08,  1.45it/s]
1|10956|Loss: 0.8963949680328369:  42%|████▏     | 10955/25880 [2:15:16<2:52:08,  1.45it/s]
1|10956|Loss: 0.8963949680328369:  42%|████▏     | 10956/25880 [2:15:16<3:01:15,  1.37it/s]
1|10957|Loss: 0.7635452151298523:  42%|████▏     | 10956/25880 [2:15:17<3:01:15,  1.37it/s]
1|10957|Loss: 0.7635452151298523:  42%|████▏     | 10957/25880 [2:15:17<3:03:11,  1.36it/s]
1|10958|Loss: 0.7459023594856262:  42%|████▏     | 10957/25880 [2:15:17<3:03:11,  1.36it/s]
1|10958|Loss: 0.7459023594856262:  42%|████▏     | 10958/25880 [2:15:18<2:48:12,  1.48it/s]
1|10959|Loss: 0.8289768695831299:  42%|████▏     | 10958/25880 [2:15:18<2:48:12,  1.48it/s]
1|10959|Loss: 0.8289768695831299:  42%|████▏     | 10959/25880 [2:15:18<2:48:27,  1.48it/s]
1|10960|Loss: 0.664222240447998:  42%|████▏     | 10959/25880 [2:15:19<2:48:27,  1.48it/s] 
1|10960|Loss: 0.664222240447998:  42%|████▏     | 10960/25880 [2:15:19<2:57:56,  1.40it/s]
1|10961|Loss: 0.8952919244766235:  42%|████▏     | 10960/25880 [2:15:19<2:57:56,  1.40it/s]
1|10961|Loss: 0.8952919244766235:  42%|████▏     | 10961/25880 [2:15:20<3:08:55,  1.32it/s]
1|10962|Loss: 0.8283621072769165:  42%|████▏     | 10961/25880 [2:15:20<3:08:55,  1.32it/s]
1|10962|Loss: 0.8283621072769165:  42%|████▏     | 10962/25880 [2:15:21<3:09:21,  1.31it/s]
1|10963|Loss: 0.8812680840492249:  42%|████▏     | 10962/25880 [2:15:21<3:09:21,  1.31it/s]
1|10963|Loss: 0.8812680840492249:  42%|████▏     | 10963/25880 [2:15:21<3:00:13,  1.38it/s]
1|10964|Loss: 0.9404138922691345:  42%|████▏     | 10963/25880 [2:15:22<3:00:13,  1.38it/s]
1|10964|Loss: 0.9404138922691345:  42%|████▏     | 10964/25880 [2:15:22<2:59:55,  1.38it/s]
1|10965|Loss: 0.7203261852264404:  42%|████▏     | 10964/25880 [2:15:22<2:59:55,  1.38it/s]
1|10965|Loss: 0.7203261852264404:  42%|████▏     | 10965/25880 [2:15:23<3:14:34,  1.28it/s]
1|10966|Loss: 0.7865124940872192:  42%|████▏     | 10965/25880 [2:15:23<3:14:34,  1.28it/s]
1|10966|Loss: 0.7865124940872192:  42%|████▏     | 10966/25880 [2:15:24<3:14:10,  1.28it/s]
1|10967|Loss: 0.8570533990859985:  42%|████▏     | 10966/25880 [2:15:24<3:14:10,  1.28it/s]
1|10967|Loss: 0.8570533990859985:  42%|████▏     | 10967/25880 [2:15:24<3:08:24,  1.32it/s]
1|10968|Loss: 0.938721776008606:  42%|████▏     | 10967/25880 [2:15:25<3:08:24,  1.32it/s] 
1|10968|Loss: 0.938721776008606:  42%|████▏     | 10968/25880 [2:15:25<2:58:30,  1.39it/s]
1|10969|Loss: 0.8363823890686035:  42%|████▏     | 10968/25880 [2:15:25<2:58:30,  1.39it/s]
1|10969|Loss: 0.8363823890686035:  42%|████▏     | 10969/25880 [2:15:26<3:06:51,  1.33it/s]
1|10970|Loss: 0.9907368421554565:  42%|████▏     | 10969/25880 [2:15:26<3:06:51,  1.33it/s]
1|10970|Loss: 0.9907368421554565:  42%|████▏     | 10970/25880 [2:15:27<3:11:11,  1.30it/s]
1|10971|Loss: 0.9255074262619019:  42%|████▏     | 10970/25880 [2:15:27<3:11:11,  1.30it/s]
1|10971|Loss: 0.9255074262619019:  42%|████▏     | 10971/25880 [2:15:27<2:56:32,  1.41it/s]
1|10972|Loss: 0.8628091216087341:  42%|████▏     | 10971/25880 [2:15:28<2:56:32,  1.41it/s]
1|10972|Loss: 0.8628091216087341:  42%|████▏     | 10972/25880 [2:15:28<2:52:50,  1.44it/s]
1|10973|Loss: 0.8106010556221008:  42%|████▏     | 10972/25880 [2:15:28<2:52:50,  1.44it/s]
1|10973|Loss: 0.8106010556221008:  42%|████▏     | 10973/25880 [2:15:28<2:42:04,  1.53it/s]
1|10974|Loss: 0.7688251733779907:  42%|████▏     | 10973/25880 [2:15:29<2:42:04,  1.53it/s]
1|10974|Loss: 0.7688251733779907:  42%|████▏     | 10974/25880 [2:15:29<2:52:41,  1.44it/s]
1|10975|Loss: 0.8237908482551575:  42%|████▏     | 10974/25880 [2:15:30<2:52:41,  1.44it/s]
1|10975|Loss: 0.8237908482551575:  42%|████▏     | 10975/25880 [2:15:30<2:56:10,  1.41it/s]
1|10976|Loss: 0.8042023777961731:  42%|████▏     | 10975/25880 [2:15:30<2:56:10,  1.41it/s]
1|10976|Loss: 0.8042023777961731:  42%|████▏     | 10976/25880 [2:15:31<2:52:03,  1.44it/s]
1|10977|Loss: 0.8127429485321045:  42%|████▏     | 10976/25880 [2:15:31<2:52:03,  1.44it/s]
1|10977|Loss: 0.8127429485321045:  42%|████▏     | 10977/25880 [2:15:31<2:48:23,  1.47it/s]
1|10978|Loss: 0.9285261631011963:  42%|████▏     | 10977/25880 [2:15:32<2:48:23,  1.47it/s]
1|10978|Loss: 0.9285261631011963:  42%|████▏     | 10978/25880 [2:15:32<2:38:08,  1.57it/s]
1|10979|Loss: 0.6806976795196533:  42%|████▏     | 10978/25880 [2:15:32<2:38:08,  1.57it/s]
1|10979|Loss: 0.6806976795196533:  42%|█��██▏     | 10979/25880 [2:15:33<2:55:48,  1.41it/s]
1|10980|Loss: 0.9055708646774292:  42%|████▏     | 10979/25880 [2:15:33<2:55:48,  1.41it/s]
1|10980|Loss: 0.9055708646774292:  42%|████▏     | 10980/25880 [2:15:33<3:01:05,  1.37it/s]
1|10981|Loss: 0.6985657811164856:  42%|████▏     | 10980/25880 [2:15:34<3:01:05,  1.37it/s]
1|10981|Loss: 0.6985657811164856:  42%|████▏     | 10981/25880 [2:15:34<3:17:22,  1.26it/s]
1|10982|Loss: 0.8557347059249878:  42%|████▏     | 10981/25880 [2:15:35<3:17:22,  1.26it/s]
1|10982|Loss: 0.8557347059249878:  42%|████▏     | 10982/25880 [2:15:35<3:23:13,  1.22it/s]
1|10983|Loss: 0.9093467593193054:  42%|████▏     | 10982/25880 [2:15:36<3:23:13,  1.22it/s]
1|10983|Loss: 0.9093467593193054:  42%|████▏     | 10983/25880 [2:15:36<3:16:08,  1.27it/s]
1|10984|Loss: 0.8025202751159668:  42%|████▏     | 10983/25880 [2:15:36<3:16:08,  1.27it/s]
1|10984|Loss: 0.8025202751159668:  42%|████▏     | 10984/25880 [2:15:37<3:16:48,  1.26it/s]
1|10985|Loss: 0.7118533253669739:  42%|████▏     | 10984/25880 [2:15:37<3:16:48,  1.26it/s]
1|10985|Loss: 0.7118533253669739:  42%|████▏     | 10985/25880 [2:15:38<3:19:07,  1.25it/s]
1|10986|Loss: 0.773690402507782:  42%|████▏     | 10985/25880 [2:15:38<3:19:07,  1.25it/s] 
1|10986|Loss: 0.773690402507782:  42%|████▏     | 10986/25880 [2:15:38<2:58:15,  1.39it/s]
1|10987|Loss: 0.838588535785675:  42%|████▏     | 10986/25880 [2:15:39<2:58:15,  1.39it/s]
1|10987|Loss: 0.838588535785675:  42%|████▏     | 10987/25880 [2:15:39<2:57:42,  1.40it/s]
1|10988|Loss: 0.7764725089073181:  42%|████▏     | 10987/25880 [2:15:39<2:57:42,  1.40it/s]
1|10988|Loss: 0.7764725089073181:  42%|████▏     | 10988/25880 [2:15:40<3:06:40,  1.33it/s]
1|10989|Loss: 0.8037193417549133:  42%|████▏     | 10988/25880 [2:15:40<3:06:40,  1.33it/s]
1|10989|Loss: 0.8037193417549133:  42%|████▏     | 10989/25880 [2:15:40<3:05:14,  1.34it/s]
1|10990|Loss: 0.9041981101036072:  42%|████▏     | 10989/25880 [2:15:41<3:05:14,  1.34it/s]
1|10990|Loss: 0.9041981101036072:  42%|████▏     | 10990/25880 [2:15:41<3:06:58,  1.33it/s]
1|10991|Loss: 0.8573288917541504:  42%|████▏     | 10990/25880 [2:15:42<3:06:58,  1.33it/s]
1|10991|Loss: 0.8573288917541504:  42%|████▏     | 10991/25880 [2:15:42<3:12:34,  1.29it/s]
1|10992|Loss: 0.748670220375061:  42%|████▏     | 10991/25880 [2:15:42<3:12:34,  1.29it/s] 
1|10992|Loss: 0.748670220375061:  42%|████▏     | 10992/25880 [2:15:43<3:05:33,  1.34it/s]
1|10993|Loss: 0.8563675880432129:  42%|████▏     | 10992/25880 [2:15:43<3:05:33,  1.34it/s]
1|10993|Loss: 0.8563675880432129:  42%|████▏     | 10993/25880 [2:15:43<2:57:49,  1.40it/s]
1|10994|Loss: 1.0189265012741089:  42%|████▏     | 10993/25880 [2:15:44<2:57:49,  1.40it/s]
1|10994|Loss: 1.0189265012741089:  42%|████▏     | 10994/25880 [2:15:44<3:04:49,  1.34it/s]
1|10995|Loss: 0.7665590643882751:  42%|████▏     | 10994/25880 [2:15:45<3:04:49,  1.34it/s]
1|10995|Loss: 0.7665590643882751:  42%|████▏     | 10995/25880 [2:15:45<3:14:56,  1.27it/s]
1|10996|Loss: 0.9976658225059509:  42%|████▏     | 10995/25880 [2:15:46<3:14:56,  1.27it/s]
1|10996|Loss: 0.9976658225059509:  42%|████▏     | 10996/25880 [2:15:46<3:16:57,  1.26it/s]
1|10997|Loss: 0.9532645344734192:  42%|████▏     | 10996/25880 [2:15:46<3:16:57,  1.26it/s]
1|10997|Loss: 0.9532645344734192:  42%|████▏     | 10997/25880 [2:15:47<3:19:39,  1.24it/s]
1|10998|Loss: 0.9891948699951172:  42%|████▏     | 10997/25880 [2:15:47<3:19:39,  1.24it/s]
1|10998|Loss: 0.9891948699951172:  42%|████▏     | 10998/25880 [2:15:48<3:26:45,  1.20it/s]
1|10999|Loss: 0.782311201095581:  42%|████▏     | 10998/25880 [2:15:48<3:26:45,  1.20it/s] 
1|10999|Loss: 0.782311201095581:  42%|████▎     | 10999/25880 [2:15:48<3:11:15,  1.30it/s]
1|11000|Loss: 0.7346644401550293:  42%|████▎     | 10999/25880 [2:15:49<3:11:15,  1.30it/s]
1|11000|Loss: 0.7346644401550293:  43%|████▎     | 11000/25880 [2:15:49<3:12:50,  1.29it/s]
1|11001|Loss: 0.7560829520225525:  43%|████▎     | 11000/25880 [2:15:49<3:12:50,  1.29it/s]
1|11001|Loss: 0.7560829520225525:  43%|████▎     | 11001/25880 [2:15:50<2:55:11,  1.42it/s]
1|11002|Loss: 0.8512272238731384:  43%|████▎     | 11001/25880 [2:15:50<2:55:11,  1.42it/s]
1|11002|Loss: 0.8512272238731384:  43%|████▎     | 11002/25880 [2:15:50<2:45:12,  1.50it/s]
1|11003|Loss: 0.7955999970436096:  43%|████▎     | 11002/25880 [2:15:51<2:45:12,  1.50it/s]
1|11003|Loss: 0.7955999970436096:  43%|████▎     | 11003/25880 [2:15:51<2:52:53,  1.43it/s]
1|11004|Loss: 0.901326060295105:  43%|████▎     | 11003/25880 [2:15:51<2:52:53,  1.43it/s] 
1|11004|Loss: 0.901326060295105:  43%|████▎     | 11004/25880 [2:15:52<2:47:29,  1.48it/s]
1|11005|Loss: 0.8681224584579468:  43%|████▎     | 11004/25880 [2:15:52<2:47:29,  1.48it/s]
1|11005|Loss: 0.8681224584579468:  43%|████▎     | 11005/25880 [2:15:52<2:47:47,  1.48it/s]
1|11006|Loss: 0.7734912633895874:  43%|████▎     | 11005/25880 [2:15:53<2:47:47,  1.48it/s]
1|11006|Loss: 0.7734912633895874:  43%|████▎     | 11006/25880 [2:15:53<2:58:45,  1.39it/s]
1|11007|Loss: 0.7743463516235352:  43%|████▎     | 11006/25880 [2:15:54<2:58:45,  1.39it/s]
1|11007|Loss: 0.7743463516235352:  43%|████▎     | 11007/25880 [2:15:54<3:10:04,  1.30it/s]
1|11008|Loss: 0.9983338117599487:  43%|████▎     | 11007/25880 [2:15:54<3:10:04,  1.30it/s]
1|11008|Loss: 0.9983338117599487:  43%|████▎     | 11008/25880 [2:15:55<2:59:25,  1.38it/s]
1|11009|Loss: 0.8128868341445923:  43%|████▎     | 11008/25880 [2:15:55<2:59:25,  1.38it/s]
1|11009|Loss: 0.8128868341445923:  43%|████▎     | 11009/25880 [2:15:55<2:51:48,  1.44it/s]
1|11010|Loss: 0.9689537286758423:  43%|████▎     | 11009/25880 [2:15:56<2:51:48,  1.44it/s]
1|11010|Loss: 0.9689537286758423:  43%|████▎     | 11010/25880 [2:15:56<2:51:27,  1.45it/s]
1|11011|Loss: 0.8651842474937439:  43%|████▎     | 11010/25880 [2:15:56<2:51:27,  1.45it/s]
1|11011|Loss: 0.8651842474937439:  43%|████▎     | 11011/25880 [2:15:57<3:00:35,  1.37it/s]
1|11012|Loss: 1.0285041332244873:  43%|████▎     | 11011/25880 [2:15:57<3:00:35,  1.37it/s]
1|11012|Loss: 1.0285041332244873:  43%|████▎     | 11012/25880 [2:15:57<3:02:53,  1.35it/s]
1|11013|Loss: 0.7559118270874023:  43%|████▎     | 11012/25880 [2:15:58<3:02:53,  1.35it/s]
1|11013|Loss: 0.7559118270874023:  43%|████▎     | 11013/25880 [2:15:58<3:05:52,  1.33it/s]
1|11014|Loss: 0.8551169037818909:  43%|████▎     | 11013/25880 [2:15:59<3:05:52,  1.33it/s]
1|11014|Loss: 0.8551169037818909:  43%|████▎     | 11014/25880 [2:15:59<2:58:46,  1.39it/s]
1|11015|Loss: 0.8966854810714722:  43%|████▎     | 11014/25880 [2:15:59<2:58:46,  1.39it/s]
1|11015|Loss: 0.8966854810714722:  43%|████▎     | 11015/25880 [2:16:00<3:01:10,  1.37it/s]
1|11016|Loss: 0.7271950840950012:  43%|████▎     | 11015/25880 [2:16:00<3:01:10,  1.37it/s]
1|11016|Loss: 0.7271950840950012:  43%|████▎     | 11016/25880 [2:16:00<3:01:05,  1.37it/s]
1|11017|Loss: 0.768648624420166:  43%|████▎     | 11016/25880 [2:16:01<3:01:05,  1.37it/s] 
1|11017|Loss: 0.768648624420166:  43%|████▎     | 11017/25880 [2:16:01<2:58:51,  1.38it/s]
1|11018|Loss: 0.7934617400169373:  43%|████▎     | 11017/25880 [2:16:01<2:58:51,  1.38it/s]
1|11018|Loss: 0.7934617400169373:  43%|████▎     | 11018/25880 [2:16:02<2:59:38,  1.38it/s]
1|11019|Loss: 0.8411925435066223:  43%|████▎     | 11018/25880 [2:16:02<2:59:38,  1.38it/s]
1|11019|Loss: 0.8411925435066223:  43%|████▎     | 11019/25880 [2:16:02<2:53:54,  1.42it/s]
1|11020|Loss: 0.8996714949607849:  43%|████▎     | 11019/25880 [2:16:03<2:53:54,  1.42it/s]
1|11020|Loss: 0.8996714949607849:  43%|████▎     | 11020/25880 [2:16:03<3:00:38,  1.37it/s]
1|11021|Loss: 0.7843836545944214:  43%|████▎     | 11020/25880 [2:16:04<3:00:38,  1.37it/s]
1|11021|Loss: 0.7843836545944214:  43%|████▎     | 11021/25880 [2:16:04<2:56:45,  1.40it/s]
1|11022|Loss: 0.8500447869300842:  43%|████▎     | 11021/25880 [2:16:04<2:56:45,  1.40it/s]
1|11022|Loss: 0.8500447869300842:  43%|████▎     | 11022/25880 [2:16:05<2:57:07,  1.40it/s]
1|11023|Loss: 0.7449101209640503:  43%|████▎     | 11022/25880 [2:16:05<2:57:07,  1.40it/s]
1|11023|Loss: 0.7449101209640503:  43%|████▎     | 11023/25880 [2:16:05<2:52:00,  1.44it/s]
1|11024|Loss: 0.8153480291366577:  43%|████▎     | 11023/25880 [2:16:06<2:52:00,  1.44it/s]
1|11024|Loss: 0.8153480291366577:  43%|████▎     | 11024/25880 [2:16:06<3:00:06,  1.37it/s]
1|11025|Loss: 0.865001380443573:  43%|████▎     | 11024/25880 [2:16:06<3:00:06,  1.37it/s] 
1|11025|Loss: 0.865001380443573:  43%|████▎     | 11025/25880 [2:16:07<3:00:58,  1.37it/s]
1|11026|Loss: 0.8051363229751587:  43%|████▎     | 11025/25880 [2:16:07<3:00:58,  1.37it/s]
1|11026|Loss: 0.8051363229751587:  43%|████▎     | 11026/25880 [2:16:07<2:50:17,  1.45it/s]
1|11027|Loss: 0.8988192081451416:  43%|████▎     | 11026/25880 [2:16:08<2:50:17,  1.45it/s]
1|11027|Loss: 0.8988192081451416:  43%|████▎     | 11027/25880 [2:16:08<2:42:16,  1.53it/s]
1|11028|Loss: 0.987903892993927:  43%|████▎     | 11027/25880 [2:16:08<2:42:16,  1.53it/s] 
1|11028|Loss: 0.987903892993927:  43%|████▎     | 11028/25880 [2:16:09<2:44:19,  1.51it/s]
1|11029|Loss: 0.8659072518348694:  43%|████▎     | 11028/25880 [2:16:09<2:44:19,  1.51it/s]
1|11029|Loss: 0.8659072518348694:  43%|████▎     | 11029/25880 [2:16:09<2:41:46,  1.53it/s]
1|11030|Loss: 0.9293854832649231:  43%|████▎     | 11029/25880 [2:16:10<2:41:46,  1.53it/s]
1|11030|Loss: 0.9293854832649231:  43%|████▎     | 11030/25880 [2:16:10<2:33:49,  1.61it/s]
1|11031|Loss: 0.73934006690979:  43%|████▎     | 11030/25880 [2:16:10<2:33:49,  1.61it/s]  
1|11031|Loss: 0.73934006690979:  43%|████▎     | 11031/25880 [2:16:11<2:41:58,  1.53it/s]
1|11032|Loss: 0.8804625272750854:  43%|████▎     | 11031/25880 [2:16:11<2:41:58,  1.53it/s]
1|11032|Loss: 0.8804625272750854:  43%|████▎     | 11032/25880 [2:16:11<2:42:05,  1.53it/s]
1|11033|Loss: 0.7081382870674133:  43%|████▎     | 11032/25880 [2:16:12<2:42:05,  1.53it/s]
1|11033|Loss: 0.7081382870674133:  43%|████▎     | 11033/25880 [2:16:12<2:46:25,  1.49it/s]
1|11034|Loss: 0.8107568025588989:  43%|████▎     | 11033/25880 [2:16:12<2:46:25,  1.49it/s]
1|11034|Loss: 0.8107568025588989:  43%|████▎     | 11034/25880 [2:16:13<2:44:36,  1.50it/s]
1|11035|Loss: 0.9859730005264282:  43%|████▎     | 11034/25880 [2:16:13<2:44:36,  1.50it/s]
1|11035|Loss: 0.9859730005264282:  43%|████▎     | 11035/25880 [2:16:13<2:39:28,  1.55it/s]
1|11036|Loss: 0.7894253730773926:  43%|████▎     | 11035/25880 [2:16:14<2:39:28,  1.55it/s]
1|11036|Loss: 0.7894253730773926:  43%|████▎     | 11036/25880 [2:16:14<2:44:35,  1.50it/s]
1|11037|Loss: 0.9207054376602173:  43%|████▎     | 11036/25880 [2:16:14<2:44:35,  1.50it/s]
1|11037|Loss: 0.9207054376602173:  43%|████▎     | 11037/25880 [2:16:15<2:42:05,  1.53it/s]
1|11038|Loss: 0.8795835971832275:  43%|████▎     | 11037/25880 [2:16:15<2:42:05,  1.53it/s]
1|11038|Loss: 0.8795835971832275:  43%|████▎     | 11038/25880 [2:16:15<2:40:05,  1.55it/s]
1|11039|Loss: 0.7626416683197021:  43%|████▎     | 11038/25880 [2:16:15<2:40:05,  1.55it/s]
1|11039|Loss: 0.7626416683197021:  43%|████▎     | 11039/25880 [2:16:16<2:34:52,  1.60it/s]
1|11040|Loss: 0.7000929117202759:  43%|████▎     | 11039/25880 [2:16:16<2:34:52,  1.60it/s]
1|11040|Loss: 0.7000929117202759:  43%|████▎     | 11040/25880 [2:16:16<2:34:21,  1.60it/s]
1|11041|Loss: 0.829972505569458:  43%|████▎     | 11040/25880 [2:16:17<2:34:21,  1.60it/s] 
1|11041|Loss: 0.829972505569458:  43%|████▎     | 11041/25880 [2:16:17<2:48:32,  1.47it/s]
1|11042|Loss: 0.8215093612670898:  43%|████▎     | 11041/25880 [2:16:18<2:48:32,  1.47it/s]
1|11042|Loss: 0.8215093612670898:  43%|████▎     | 11042/25880 [2:16:18<2:54:25,  1.42it/s]
1|11043|Loss: 0.8267722725868225:  43%|████▎     | 11042/25880 [2:16:18<2:54:25,  1.42it/s]
1|11043|Loss: 0.8267722725868225:  43%|████▎     | 11043/25880 [2:16:19<2:57:39,  1.39it/s]
1|11044|Loss: 0.8855295181274414:  43%|████▎     | 11043/25880 [2:16:19<2:57:39,  1.39it/s]
1|11044|Loss: 0.8855295181274414:  43%|████▎     | 11044/25880 [2:16:19<2:52:23,  1.43it/s]
1|11045|Loss: 0.9752512574195862:  43%|████▎     | 11044/25880 [2:16:20<2:52:23,  1.43it/s]
1|11045|Loss: 0.9752512574195862:  43%|████▎     | 11045/25880 [2:16:20<2:46:20,  1.49it/s]
1|11046|Loss: 0.9478090405464172:  43%|████▎     | 11045/25880 [2:16:20<2:46:20,  1.49it/s]
1|11046|Loss: 0.9478090405464172:  43%|████▎     | 11046/25880 [2:16:21<2:47:33,  1.48it/s]
1|11047|Loss: 0.9064804911613464:  43%|████▎     | 11046/25880 [2:16:21<2:47:33,  1.48it/s]
1|11047|Loss: 0.9064804911613464:  43%|████▎     | 11047/25880 [2:16:21<2:50:38,  1.45it/s]
1|11048|Loss: 0.9226597547531128:  43%|████▎     | 11047/25880 [2:16:22<2:50:38,  1.45it/s]
1|11048|Loss: 0.9226597547531128:  43%|████▎     | 11048/25880 [2:16:22<2:46:35,  1.48it/s]
1|11049|Loss: 1.0046823024749756:  43%|████▎     | 11048/25880 [2:16:22<2:46:35,  1.48it/s]
1|11049|Loss: 1.0046823024749756:  43%|████▎     | 11049/25880 [2:16:23<2:36:17,  1.58it/s]
1|11050|Loss: 0.8796595335006714:  43%|████▎     | 11049/25880 [2:16:23<2:36:17,  1.58it/s]
1|11050|Loss: 0.8796595335006714:  43%|████▎     | 11050/25880 [2:16:23<2:38:35,  1.56it/s]
1|11051|Loss: 0.888908326625824:  43%|████▎     | 11050/25880 [2:16:24<2:38:35,  1.56it/s] 
1|11051|Loss: 0.888908326625824:  43%|████▎     | 11051/25880 [2:16:24<2:44:49,  1.50it/s]
1|11052|Loss: 0.8420924544334412:  43%|████▎     | 11051/25880 [2:16:24<2:44:49,  1.50it/s]
1|11052|Loss: 0.8420924544334412:  43%|████▎     | 11052/25880 [2:16:25<2:55:20,  1.41it/s]
1|11053|Loss: 0.8546497225761414:  43%|████▎     | 11052/25880 [2:16:25<2:55:20,  1.41it/s]
1|11053|Loss: 0.8546497225761414:  43%|████▎     | 11053/25880 [2:16:26<3:03:52,  1.34it/s]
1|11054|Loss: 0.7962191700935364:  43%|████▎     | 11053/25880 [2:16:26<3:03:52,  1.34it/s]
1|11054|Loss: 0.7962191700935364:  43%|████▎     | 11054/25880 [2:16:26<3:18:15,  1.25it/s]
1|11055|Loss: 0.7548090815544128:  43%|████▎     | 11054/25880 [2:16:27<3:18:15,  1.25it/s]
1|11055|Loss: 0.7548090815544128:  43%|████▎     | 11055/25880 [2:16:27<3:21:14,  1.23it/s]
1|11056|Loss: 0.864529550075531:  43%|████▎     | 11055/25880 [2:16:28<3:21:14,  1.23it/s] 
1|11056|Loss: 0.864529550075531:  43%|████▎     | 11056/25880 [2:16:28<3:17:29,  1.25it/s]
1|11057|Loss: 0.7513644099235535:  43%|████▎     | 11056/25880 [2:16:29<3:17:29,  1.25it/s]
1|11057|Loss: 0.7513644099235535:  43%|████▎     | 11057/25880 [2:16:29<3:23:44,  1.21it/s]
1|11058|Loss: 0.7600060701370239:  43%|████▎     | 11057/25880 [2:16:29<3:23:44,  1.21it/s]
1|11058|Loss: 0.7600060701370239:  43%|████▎     | 11058/25880 [2:16:30<3:18:50,  1.24it/s]
1|11059|Loss: 0.7982364892959595:  43%|████▎     | 11058/25880 [2:16:30<3:18:50,  1.24it/s]
1|11059|Loss: 0.7982364892959595:  43%|████▎     | 11059/25880 [2:16:30<3:14:16,  1.27it/s]
1|11060|Loss: 0.8479817509651184:  43%|████▎     | 11059/25880 [2:16:31<3:14:16,  1.27it/s]
1|11060|Loss: 0.8479817509651184:  43%|████▎     | 11060/25880 [2:16:31<3:18:44,  1.24it/s]
1|11061|Loss: 0.9438722133636475:  43%|████▎     | 11060/25880 [2:16:32<3:18:44,  1.24it/s]
1|11061|Loss: 0.9438722133636475:  43%|████▎     | 11061/25880 [2:16:32<3:09:54,  1.30it/s]
1|11062|Loss: 0.797991931438446:  43%|████▎     | 11061/25880 [2:16:32<3:09:54,  1.30it/s] 
1|11062|Loss: 0.797991931438446:  43%|████▎     | 11062/25880 [2:16:33<3:13:52,  1.27it/s]
1|11063|Loss: 1.227902889251709:  43%|████▎     | 11062/25880 [2:16:33<3:13:52,  1.27it/s]
1|11063|Loss: 1.227902889251709:  43%|████▎     | 11063/25880 [2:16:34<3:20:18,  1.23it/s]
1|11064|Loss: 0.8565712571144104:  43%|████▎     | 11063/25880 [2:16:34<3:20:18,  1.23it/s]
1|11064|Loss: 0.8565712571144104:  43%|████▎     | 11064/25880 [2:16:34<3:06:38,  1.32it/s]
1|11065|Loss: 0.8320813775062561:  43%|████▎     | 11064/25880 [2:16:35<3:06:38,  1.32it/s]
1|11065|Loss: 0.8320813775062561:  43%|████▎     | 11065/25880 [2:16:35<3:09:26,  1.30it/s]
1|11066|Loss: 0.7495363354682922:  43%|████▎     | 11065/25880 [2:16:36<3:09:26,  1.30it/s]
1|11066|Loss: 0.7495363354682922:  43%|████▎     | 11066/25880 [2:16:36<3:08:55,  1.31it/s]
1|11067|Loss: 0.9666527509689331:  43%|████▎     | 11066/25880 [2:16:36<3:08:55,  1.31it/s]
1|11067|Loss: 0.9666527509689331:  43%|████▎     | 11067/25880 [2:16:36<2:57:02,  1.39it/s]
1|11068|Loss: 0.9560135006904602:  43%|████▎     | 11067/25880 [2:16:37<2:57:02,  1.39it/s]
1|11068|Loss: 0.9560135006904602:  43%|████▎     | 11068/25880 [2:16:37<2:55:57,  1.40it/s]
1|11069|Loss: 0.9788609147071838:  43%|████▎     | 11068/25880 [2:16:38<2:55:57,  1.40it/s]
1|11069|Loss: 0.9788609147071838:  43%|████▎     | 11069/25880 [2:16:38<2:55:32,  1.41it/s]
1|11070|Loss: 0.7499555349349976:  43%|████▎     | 11069/25880 [2:16:38<2:55:32,  1.41it/s]
1|11070|Loss: 0.7499555349349976:  43%|████▎     | 11070/25880 [2:16:39<2:54:27,  1.41it/s]
1|11071|Loss: 0.8484129309654236:  43%|████▎     | 11070/25880 [2:16:39<2:54:27,  1.41it/s]
1|11071|Loss: 0.8484129309654236:  43%|████▎     | 11071/25880 [2:16:39<2:55:06,  1.41it/s]
1|11072|Loss: 0.9939673542976379:  43%|████▎     | 11071/25880 [2:16:40<2:55:06,  1.41it/s]
1|11072|Loss: 0.9939673542976379:  43%|████▎     | 11072/25880 [2:16:40<3:02:11,  1.35it/s]
1|11073|Loss: 0.933970034122467:  43%|████▎     | 11072/25880 [2:16:41<3:02:11,  1.35it/s] 
1|11073|Loss: 0.933970034122467:  43%|████▎     | 11073/25880 [2:16:41<3:14:08,  1.27it/s]
1|11074|Loss: 0.8060603737831116:  43%|████▎     | 11073/25880 [2:16:41<3:14:08,  1.27it/s]
1|11074|Loss: 0.8060603737831116:  43%|████▎     | 11074/25880 [2:16:42<2:56:13,  1.40it/s]
1|11075|Loss: 0.985349714756012:  43%|████▎     | 11074/25880 [2:16:42<2:56:13,  1.40it/s] 
1|11075|Loss: 0.985349714756012:  43%|████▎     | 11075/25880 [2:16:42<2:47:38,  1.47it/s]
1|11076|Loss: 0.9669328331947327:  43%|████▎     | 11075/25880 [2:16:43<2:47:38,  1.47it/s]
1|11076|Loss: 0.9669328331947327:  43%|████▎     | 11076/25880 [2:16:43<2:43:31,  1.51it/s]
1|11077|Loss: 0.9121416807174683:  43%|████▎     | 11076/25880 [2:16:43<2:43:31,  1.51it/s]
1|11077|Loss: 0.9121416807174683:  43%|████▎     | 11077/25880 [2:16:44<2:55:09,  1.41it/s]
1|11078|Loss: 0.7789880037307739:  43%|████▎     | 11077/25880 [2:16:44<2:55:09,  1.41it/s]
1|11078|Loss: 0.7789880037307739:  43%|████▎     | 11078/25880 [2:16:44<3:05:01,  1.33it/s]
1|11079|Loss: 0.842780351638794:  43%|████▎     | 11078/25880 [2:16:45<3:05:01,  1.33it/s] 
1|11079|Loss: 0.842780351638794:  43%|████▎     | 11079/25880 [2:16:45<3:06:00,  1.33it/s]
1|11080|Loss: 0.7630933523178101:  43%|████▎     | 11079/25880 [2:16:46<3:06:00,  1.33it/s]
1|11080|Loss: 0.7630933523178101:  43%|████▎     | 11080/25880 [2:16:46<3:02:58,  1.35it/s]
1|11081|Loss: 0.8389899134635925:  43%|████▎     | 11080/25880 [2:16:46<3:02:58,  1.35it/s]
1|11081|Loss: 0.8389899134635925:  43%|████▎     | 11081/25880 [2:16:47<3:07:37,  1.31it/s]
1|11082|Loss: 0.7954594492912292:  43%|████▎     | 11081/25880 [2:16:47<3:07:37,  1.31it/s]
1|11082|Loss: 0.7954594492912292:  43%|████▎     | 11082/25880 [2:16:47<3:06:33,  1.32it/s]
1|11083|Loss: 0.8154529333114624:  43%|████▎     | 11082/25880 [2:16:48<3:06:33,  1.32it/s]
1|11083|Loss: 0.8154529333114624:  43%|████▎     | 11083/25880 [2:16:48<3:11:34,  1.29it/s]
1|11084|Loss: 0.8271043300628662:  43%|████▎     | 11083/25880 [2:16:49<3:11:34,  1.29it/s]
1|11084|Loss: 0.8271043300628662:  43%|████▎     | 11084/25880 [2:16:49<3:13:28,  1.27it/s]
1|11085|Loss: 0.7911701798439026:  43%|████▎     | 11084/25880 [2:16:50<3:13:28,  1.27it/s]
1|11085|Loss: 0.7911701798439026:  43%|████▎     | 11085/25880 [2:16:50<3:19:51,  1.23it/s]
1|11086|Loss: 0.8392919301986694:  43%|████▎     | 11085/25880 [2:16:50<3:19:51,  1.23it/s]
1|11086|Loss: 0.8392919301986694:  43%|████▎     | 11086/25880 [2:16:51<3:04:07,  1.34it/s]
1|11087|Loss: 0.838964581489563:  43%|████▎     | 11086/25880 [2:16:51<3:04:07,  1.34it/s] 
1|11087|Loss: 0.838964581489563:  43%|████▎     | 11087/25880 [2:16:51<2:54:14,  1.41it/s]
1|11088|Loss: 1.1597797870635986:  43%|████▎     | 11087/25880 [2:16:52<2:54:14,  1.41it/s]
1|11088|Loss: 1.1597797870635986:  43%|████▎     | 11088/25880 [2:16:52<2:43:04,  1.51it/s]
1|11089|Loss: 0.8386979699134827:  43%|████▎     | 11088/25880 [2:16:52<2:43:04,  1.51it/s]
1|11089|Loss: 0.8386979699134827:  43%|████▎     | 11089/25880 [2:16:52<2:28:49,  1.66it/s]
1|11090|Loss: 0.6716901659965515:  43%|████▎     | 11089/25880 [2:16:53<2:28:49,  1.66it/s]
1|11090|Loss: 0.6716901659965515:  43%|████▎     | 11090/25880 [2:16:53<2:42:07,  1.52it/s]
1|11091|Loss: 0.7925745844841003:  43%|████▎     | 11090/25880 [2:16:53<2:42:07,  1.52it/s]
1|11091|Loss: 0.7925745844841003:  43%|████▎     | 11091/25880 [2:16:54<2:50:32,  1.45it/s]
1|11092|Loss: 0.9268988370895386:  43%|████▎     | 11091/25880 [2:16:54<2:50:32,  1.45it/s]
1|11092|Loss: 0.9268988370895386:  43%|████▎     | 11092/25880 [2:16:55<2:57:09,  1.39it/s]
1|11093|Loss: 0.9430642127990723:  43%|████▎     | 11092/25880 [2:16:55<2:57:09,  1.39it/s]
1|11093|Loss: 0.9430642127990723:  43%|████▎     | 11093/25880 [2:16:55<2:59:34,  1.37it/s]
1|11094|Loss: 0.8428351283073425:  43%|████▎     | 11093/25880 [2:16:56<2:59:34,  1.37it/s]
1|11094|Loss: 0.8428351283073425:  43%|████▎     | 11094/25880 [2:16:56<2:57:46,  1.39it/s]
1|11095|Loss: 0.7364770770072937:  43%|████▎     | 11094/25880 [2:16:56<2:57:46,  1.39it/s]
1|11095|Loss: 0.7364770770072937:  43%|████▎     | 11095/25880 [2:16:57<2:55:50,  1.40it/s]
1|11096|Loss: 0.9240615963935852:  43%|████▎     | 11095/25880 [2:16:57<2:55:50,  1.40it/s]
1|11096|Loss: 0.9240615963935852:  43%|████▎     | 11096/25880 [2:16:57<2:56:18,  1.40it/s]
1|11097|Loss: 0.7492624521255493:  43%|████▎     | 11096/25880 [2:16:58<2:56:18,  1.40it/s]
1|11097|Loss: 0.7492624521255493:  43%|████▎     | 11097/25880 [2:16:58<3:10:58,  1.29it/s]
1|11098|Loss: 0.928298830986023:  43%|████▎     | 11097/25880 [2:16:59<3:10:58,  1.29it/s] 
1|11098|Loss: 0.928298830986023:  43%|████▎     | 11098/25880 [2:16:59<3:11:27,  1.29it/s]
1|11099|Loss: 0.7382746934890747:  43%|████▎     | 11098/25880 [2:17:00<3:11:27,  1.29it/s]
1|11099|Loss: 0.7382746934890747:  43%|████▎     | 11099/25880 [2:17:00<3:09:49,  1.30it/s]
1|11100|Loss: 0.8889610171318054:  43%|████▎     | 11099/25880 [2:17:00<3:09:49,  1.30it/s]
1|11100|Loss: 0.8889610171318054:  43%|████▎     | 11100/25880 [2:17:01<3:01:59,  1.35it/s]
1|11101|Loss: 0.7538757920265198:  43%|████▎     | 11100/25880 [2:17:01<3:01:59,  1.35it/s]
1|11101|Loss: 0.7538757920265198:  43%|████▎     | 11101/25880 [2:17:01<2:54:51,  1.41it/s]
1|11102|Loss: 0.8154500126838684:  43%|████▎     | 11101/25880 [2:17:02<2:54:51,  1.41it/s]
1|11102|Loss: 0.8154500126838684:  43%|████▎     | 11102/25880 [2:17:02<2:55:19,  1.40it/s]
1|11103|Loss: 0.9376722574234009:  43%|████▎     | 11102/25880 [2:17:02<2:55:19,  1.40it/s]
1|11103|Loss: 0.9376722574234009:  43%|████▎     | 11103/25880 [2:17:03<2:55:48,  1.40it/s]
1|11104|Loss: 0.8203593492507935:  43%|████▎     | 11103/25880 [2:17:03<2:55:48,  1.40it/s]
1|11104|Loss: 0.8203593492507935:  43%|████▎     | 11104/25880 [2:17:03<2:47:26,  1.47it/s]
1|11105|Loss: 0.8220699429512024:  43%|████▎     | 11104/25880 [2:17:04<2:47:26,  1.47it/s]
1|11105|Loss: 0.8220699429512024:  43%|████▎     | 11105/25880 [2:17:04<2:49:47,  1.45it/s]
1|11106|Loss: 0.8814268708229065:  43%|████▎     | 11105/25880 [2:17:04<2:49:47,  1.45it/s]
1|11106|Loss: 0.8814268708229065:  43%|████▎     | 11106/25880 [2:17:05<2:53:54,  1.42it/s]
1|11107|Loss: 0.8684098720550537:  43%|████▎     | 11106/25880 [2:17:05<2:53:54,  1.42it/s]
1|11107|Loss: 0.8684098720550537:  43%|████▎     | 11107/25880 [2:17:05<2:45:43,  1.49it/s]
1|11108|Loss: 0.8908265233039856:  43%|████▎     | 11107/25880 [2:17:06<2:45:43,  1.49it/s]
1|11108|Loss: 0.8908265233039856:  43%|████▎     | 11108/25880 [2:17:06<2:45:25,  1.49it/s]
1|11109|Loss: 0.8206496238708496:  43%|████▎     | 11108/25880 [2:17:06<2:45:25,  1.49it/s]
1|11109|Loss: 0.8206496238708496:  43%|████▎     | 11109/25880 [2:17:07<2:50:10,  1.45it/s]
1|11110|Loss: 0.9349387288093567:  43%|████▎     | 11109/25880 [2:17:07<2:50:10,  1.45it/s]
1|11110|Loss: 0.9349387288093567:  43%|████▎     | 11110/25880 [2:17:07<2:46:39,  1.48it/s]
1|11111|Loss: 0.7773801684379578:  43%|████▎     | 11110/25880 [2:17:08<2:46:39,  1.48it/s]
1|11111|Loss: 0.7773801684379578:  43%|████▎     | 11111/25880 [2:17:08<3:02:56,  1.35it/s]
1|11112|Loss: 0.7202242612838745:  43%|████▎     | 11111/25880 [2:17:09<3:02:56,  1.35it/s]
1|11112|Loss: 0.7202242612838745:  43%|████▎     | 11112/25880 [2:17:09<2:49:24,  1.45it/s]
1|11113|Loss: 0.8644284009933472:  43%|████▎     | 11112/25880 [2:17:09<2:49:24,  1.45it/s]
1|11113|Loss: 0.8644284009933472:  43%|████▎     | 11113/25880 [2:17:09<2:49:05,  1.46it/s]
1|11114|Loss: 0.9382839798927307:  43%|████▎     | 11113/25880 [2:17:10<2:49:05,  1.46it/s]
1|11114|Loss: 0.9382839798927307:  43%|████▎     | 11114/25880 [2:17:10<3:00:57,  1.36it/s]
1|11115|Loss: 0.8711052536964417:  43%|████▎     | 11114/25880 [2:17:11<3:00:57,  1.36it/s]
1|11115|Loss: 0.8711052536964417:  43%|████▎     | 11115/25880 [2:17:11<2:54:57,  1.41it/s]
1|11116|Loss: 0.8355098962783813:  43%|████▎     | 11115/25880 [2:17:11<2:54:57,  1.41it/s]
1|11116|Loss: 0.8355098962783813:  43%|████▎     | 11116/25880 [2:17:12<2:58:36,  1.38it/s]
1|11117|Loss: 0.800753653049469:  43%|████▎     | 11116/25880 [2:17:12<2:58:36,  1.38it/s] 
1|11117|Loss: 0.800753653049469:  43%|████▎     | 11117/25880 [2:17:13<3:07:02,  1.32it/s]
1|11118|Loss: 0.826354444026947:  43%|████▎     | 11117/25880 [2:17:13<3:07:02,  1.32it/s]
1|11118|Loss: 0.826354444026947:  43%|████▎     | 11118/25880 [2:17:13<3:14:10,  1.27it/s]
1|11119|Loss: 0.8479717969894409:  43%|████▎     | 11118/25880 [2:17:14<3:14:10,  1.27it/s]
1|11119|Loss: 0.8479717969894409:  43%|████▎     | 11119/25880 [2:17:14<3:11:56,  1.28it/s]
1|11120|Loss: 0.9688875079154968:  43%|████▎     | 11119/25880 [2:17:15<3:11:56,  1.28it/s]
1|11120|Loss: 0.9688875079154968:  43%|████▎     | 11120/25880 [2:17:15<3:14:05,  1.27it/s]
1|11121|Loss: 0.9158519506454468:  43%|████▎     | 11120/25880 [2:17:15<3:14:05,  1.27it/s]
1|11121|Loss: 0.9158519506454468:  43%|████▎     | 11121/25880 [2:17:16<3:20:14,  1.23it/s]
1|11122|Loss: 0.8766852617263794:  43%|████▎     | 11121/25880 [2:17:16<3:20:14,  1.23it/s]
1|11122|Loss: 0.8766852617263794:  43%|████▎     | 11122/25880 [2:17:17<3:11:44,  1.28it/s]
1|11123|Loss: 0.941489577293396:  43%|████▎     | 11122/25880 [2:17:17<3:11:44,  1.28it/s] 
1|11123|Loss: 0.941489577293396:  43%|████▎     | 11123/25880 [2:17:17<3:01:36,  1.35it/s]
1|11124|Loss: 0.807673990726471:  43%|████▎     | 11123/25880 [2:17:18<3:01:36,  1.35it/s]
1|11124|Loss: 0.807673990726471:  43%|████▎     | 11124/25880 [2:17:18<3:05:47,  1.32it/s]
1|11125|Loss: 0.8786976933479309:  43%|████▎     | 11124/25880 [2:17:18<3:05:47,  1.32it/s]
1|11125|Loss: 0.8786976933479309:  43%|████▎     | 11125/25880 [2:17:19<3:04:48,  1.33it/s]
1|11126|Loss: 0.900851309299469:  43%|████▎     | 11125/25880 [2:17:19<3:04:48,  1.33it/s] 
1|11126|Loss: 0.900851309299469:  43%|████▎     | 11126/25880 [2:17:19<2:48:29,  1.46it/s]
1|11127|Loss: 0.8331059813499451:  43%|████▎     | 11126/25880 [2:17:20<2:48:29,  1.46it/s]
1|11127|Loss: 0.8331059813499451:  43%|████▎     | 11127/25880 [2:17:20<2:53:38,  1.42it/s]
1|11128|Loss: 0.9268794059753418:  43%|████▎     | 11127/25880 [2:17:20<2:53:38,  1.42it/s]
1|11128|Loss: 0.9268794059753418:  43%|████▎     | 11128/25880 [2:17:21<3:00:15,  1.36it/s]
1|11129|Loss: 0.8790158033370972:  43%|████▎     | 11128/25880 [2:17:21<3:00:15,  1.36it/s]
1|11129|Loss: 0.8790158033370972:  43%|████▎     | 11129/25880 [2:17:21<2:49:28,  1.45it/s]
1|11130|Loss: 0.7325736880302429:  43%|████▎     | 11129/25880 [2:17:22<2:49:28,  1.45it/s]
1|11130|Loss: 0.7325736880302429:  43%|████▎     | 11130/25880 [2:17:22<2:49:04,  1.45it/s]
1|11131|Loss: 0.8954715132713318:  43%|████▎     | 11130/25880 [2:17:22<2:49:04,  1.45it/s]
1|11131|Loss: 0.8954715132713318:  43%|████▎     | 11131/25880 [2:17:23<2:44:04,  1.50it/s]
1|11132|Loss: 0.7149584889411926:  43%|████▎     | 11131/25880 [2:17:23<2:44:04,  1.50it/s]
1|11132|Loss: 0.7149584889411926:  43%|████▎     | 11132/25880 [2:17:23<2:50:05,  1.45it/s]
1|11133|Loss: 0.8637921810150146:  43%|████▎     | 11132/25880 [2:17:24<2:50:05,  1.45it/s]
1|11133|Loss: 0.8637921810150146:  43%|████▎     | 11133/25880 [2:17:24<2:52:30,  1.42it/s]
1|11134|Loss: 1.0263679027557373:  43%|████▎     | 11133/25880 [2:17:25<2:52:30,  1.42it/s]
1|11134|Loss: 1.0263679027557373:  43%|████▎     | 11134/25880 [2:17:25<2:54:20,  1.41it/s]
1|11135|Loss: 0.8100911974906921:  43%|████▎     | 11134/25880 [2:17:25<2:54:20,  1.41it/s]
1|11135|Loss: 0.8100911974906921:  43%|████▎     | 11135/25880 [2:17:26<2:56:13,  1.39it/s]
1|11136|Loss: 0.8289203643798828:  43%|████▎     | 11135/25880 [2:17:26<2:56:13,  1.39it/s]
1|11136|Loss: 0.8289203643798828:  43%|████▎     | 11136/25880 [2:17:26<3:05:28,  1.32it/s]
1|11137|Loss: 0.7929001450538635:  43%|████▎     | 11136/25880 [2:17:27<3:05:28,  1.32it/s]
1|11137|Loss: 0.7929001450538635:  43%|████▎     | 11137/25880 [2:17:27<3:00:25,  1.36it/s]
1|11138|Loss: 0.7366837859153748:  43%|████▎     | 11137/25880 [2:17:28<3:00:25,  1.36it/s]
1|11138|Loss: 0.7366837859153748:  43%|████▎     | 11138/25880 [2:17:28<3:10:39,  1.29it/s]
1|11139|Loss: 0.9043408036231995:  43%|████▎     | 11138/25880 [2:17:28<3:10:39,  1.29it/s]
1|11139|Loss: 0.9043408036231995:  43%|████▎     | 11139/25880 [2:17:29<3:03:43,  1.34it/s]
1|11140|Loss: 0.8670853972434998:  43%|████▎     | 11139/25880 [2:17:29<3:03:43,  1.34it/s]
1|11140|Loss: 0.8670853972434998:  43%|████▎     | 11140/25880 [2:17:29<3:00:22,  1.36it/s]
1|11141|Loss: 0.9116960763931274:  43%|████▎     | 11140/25880 [2:17:30<3:00:22,  1.36it/s]
1|11141|Loss: 0.9116960763931274:  43%|████▎     | 11141/25880 [2:17:30<2:50:36,  1.44it/s]
1|11142|Loss: 0.7452596426010132:  43%|████▎     | 11141/25880 [2:17:30<2:50:36,  1.44it/s]
1|11142|Loss: 0.7452596426010132:  43%|████▎     | 11142/25880 [2:17:31<2:51:03,  1.44it/s]
1|11143|Loss: 0.9410374760627747:  43%|████▎     | 11142/25880 [2:17:31<2:51:03,  1.44it/s]
1|11143|Loss: 0.9410374760627747:  43%|████▎     | 11143/25880 [2:17:31<2:48:15,  1.46it/s]
1|11144|Loss: 0.7828112244606018:  43%|████▎     | 11143/25880 [2:17:32<2:48:15,  1.46it/s]
1|11144|Loss: 0.7828112244606018:  43%|████▎     | 11144/25880 [2:17:32<2:45:28,  1.48it/s]
1|11145|Loss: 0.8331177234649658:  43%|████▎     | 11144/25880 [2:17:32<2:45:28,  1.48it/s]
1|11145|Loss: 0.8331177234649658:  43%|████▎     | 11145/25880 [2:17:33<2:46:51,  1.47it/s]
1|11146|Loss: 0.8735618591308594:  43%|████▎     | 11145/25880 [2:17:33<2:46:51,  1.47it/s]
1|11146|Loss: 0.8735618591308594:  43%|████▎     | 11146/25880 [2:17:33<2:45:01,  1.49it/s]
1|11147|Loss: 0.8328936696052551:  43%|████▎     | 11146/25880 [2:17:34<2:45:01,  1.49it/s]
1|11147|Loss: 0.8328936696052551:  43%|████▎     | 11147/25880 [2:17:34<2:48:33,  1.46it/s]
1|11148|Loss: 0.816743016242981:  43%|████▎     | 11147/25880 [2:17:35<2:48:33,  1.46it/s] 
1|11148|Loss: 0.816743016242981:  43%|████▎     | 11148/25880 [2:17:35<2:54:41,  1.41it/s]
1|11149|Loss: 0.8305903077125549:  43%|████▎     | 11148/25880 [2:17:35<2:54:41,  1.41it/s]
1|11149|Loss: 0.8305903077125549:  43%|████▎     | 11149/25880 [2:17:36<2:54:55,  1.40it/s]
1|11150|Loss: 0.7792705297470093:  43%|████▎     | 11149/25880 [2:17:36<2:54:55,  1.40it/s]
1|11150|Loss: 0.7792705297470093:  43%|████▎     | 11150/25880 [2:17:36<2:50:26,  1.44it/s]
1|11151|Loss: 0.7865227460861206:  43%|████▎     | 11150/25880 [2:17:37<2:50:26,  1.44it/s]
1|11151|Loss: 0.7865227460861206:  43%|████▎     | 11151/25880 [2:17:37<2:56:11,  1.39it/s]
1|11152|Loss: 0.9335094690322876:  43%|████▎     | 11151/25880 [2:17:37<2:56:11,  1.39it/s]
1|11152|Loss: 0.9335094690322876:  43%|████▎     | 11152/25880 [2:17:38<3:05:51,  1.32it/s]
1|11153|Loss: 0.9676362872123718:  43%|████▎     | 11152/25880 [2:17:38<3:05:51,  1.32it/s]
1|11153|Loss: 0.9676362872123718:  43%|████▎     | 11153/25880 [2:17:39<3:04:50,  1.33it/s]
1|11154|Loss: 0.8445059061050415:  43%|████▎     | 11153/25880 [2:17:39<3:04:50,  1.33it/s]
1|11154|Loss: 0.8445059061050415:  43%|████▎     | 11154/25880 [2:17:39<3:08:56,  1.30it/s]
1|11155|Loss: 0.9868857860565186:  43%|████▎     | 11154/25880 [2:17:40<3:08:56,  1.30it/s]
1|11155|Loss: 0.9868857860565186:  43%|████▎     | 11155/25880 [2:17:40<3:14:32,  1.26it/s]
1|11156|Loss: 0.9506794214248657:  43%|████▎     | 11155/25880 [2:17:41<3:14:32,  1.26it/s]
1|11156|Loss: 0.9506794214248657:  43%|████▎     | 11156/25880 [2:17:41<2:59:11,  1.37it/s]
1|11157|Loss: 0.7493467926979065:  43%|████▎     | 11156/25880 [2:17:41<2:59:11,  1.37it/s]
1|11157|Loss: 0.7493467926979065:  43%|████▎     | 11157/25880 [2:17:42<3:07:12,  1.31it/s]
1|11158|Loss: 0.7871825695037842:  43%|████▎     | 11157/25880 [2:17:42<3:07:12,  1.31it/s]
1|11158|Loss: 0.7871825695037842:  43%|████▎     | 11158/25880 [2:17:42<3:07:45,  1.31it/s]
1|11159|Loss: 0.8730477690696716:  43%|████▎     | 11158/25880 [2:17:43<3:07:45,  1.31it/s]
1|11159|Loss: 0.8730477690696716:  43%|████▎     | 11159/25880 [2:17:43<3:00:02,  1.36it/s]
1|11160|Loss: 0.8684870600700378:  43%|████▎     | 11159/25880 [2:17:43<3:00:02,  1.36it/s]
1|11160|Loss: 0.8684870600700378:  43%|████▎     | 11160/25880 [2:17:44<2:58:49,  1.37it/s]
1|11161|Loss: 0.8922215104103088:  43%|████▎     | 11160/25880 [2:17:44<2:58:49,  1.37it/s]
1|11161|Loss: 0.8922215104103088:  43%|████▎     | 11161/25880 [2:17:44<2:54:29,  1.41it/s]
1|11162|Loss: 0.9641689658164978:  43%|████▎     | 11161/25880 [2:17:45<2:54:29,  1.41it/s]
1|11162|Loss: 0.9641689658164978:  43%|████▎     | 11162/25880 [2:17:45<2:49:07,  1.45it/s]
1|11163|Loss: 0.8512784242630005:  43%|████▎     | 11162/25880 [2:17:46<2:49:07,  1.45it/s]
1|11163|Loss: 0.8512784242630005:  43%|████▎     | 11163/25880 [2:17:46<2:51:38,  1.43it/s]
1|11164|Loss: 0.8485133051872253:  43%|████▎     | 11163/25880 [2:17:46<2:51:38,  1.43it/s]
1|11164|Loss: 0.8485133051872253:  43%|████▎     | 11164/25880 [2:17:47<2:54:49,  1.40it/s]
1|11165|Loss: 0.8326180577278137:  43%|████▎     | 11164/25880 [2:17:47<2:54:49,  1.40it/s]
1|11165|Loss: 0.8326180577278137:  43%|████▎     | 11165/25880 [2:17:47<2:44:28,  1.49it/s]
1|11166|Loss: 0.8605204224586487:  43%|████▎     | 11165/25880 [2:17:47<2:44:28,  1.49it/s]
1|11166|Loss: 0.8605204224586487:  43%|████▎     | 11166/25880 [2:17:48<2:37:37,  1.56it/s]
1|11167|Loss: 0.8138580918312073:  43%|████▎     | 11166/25880 [2:17:48<2:37:37,  1.56it/s]
1|11167|Loss: 0.8138580918312073:  43%|████▎     | 11167/25880 [2:17:48<2:41:52,  1.51it/s]
1|11168|Loss: 0.7664216160774231:  43%|████▎     | 11167/25880 [2:17:49<2:41:52,  1.51it/s]
1|11168|Loss: 0.7664216160774231:  43%|████▎     | 11168/25880 [2:17:49<2:53:20,  1.41it/s]
1|11169|Loss: 0.8113111853599548:  43%|████▎     | 11168/25880 [2:17:50<2:53:20,  1.41it/s]
1|11169|Loss: 0.8113111853599548:  43%|████▎     | 11169/25880 [2:17:50<3:07:38,  1.31it/s]
1|11170|Loss: 0.789888322353363:  43%|████▎     | 11169/25880 [2:17:51<3:07:38,  1.31it/s] 
1|11170|Loss: 0.789888322353363:  43%|████▎     | 11170/25880 [2:17:51<3:12:17,  1.28it/s]
1|11171|Loss: 0.7772043943405151:  43%|████▎     | 11170/25880 [2:17:51<3:12:17,  1.28it/s]
1|11171|Loss: 0.7772043943405151:  43%|████▎     | 11171/25880 [2:17:52<3:09:35,  1.29it/s]
1|11172|Loss: 0.7926427125930786:  43%|████▎     | 11171/25880 [2:17:52<3:09:35,  1.29it/s]
1|11172|Loss: 0.7926427125930786:  43%|████▎     | 11172/25880 [2:17:52<3:07:03,  1.31it/s]
1|11173|Loss: 0.8678377866744995:  43%|████▎     | 11172/25880 [2:17:53<3:07:03,  1.31it/s]
1|11173|Loss: 0.8678377866744995:  43%|████▎     | 11173/25880 [2:17:53<2:53:07,  1.42it/s]
1|11174|Loss: 0.8856175541877747:  43%|████▎     | 11173/25880 [2:17:53<2:53:07,  1.42it/s]
1|11174|Loss: 0.8856175541877747:  43%|████▎     | 11174/25880 [2:17:54<2:53:08,  1.42it/s]
1|11175|Loss: 0.759046733379364:  43%|████▎     | 11174/25880 [2:17:54<2:53:08,  1.42it/s] 
1|11175|Loss: 0.759046733379364:  43%|████▎     | 11175/25880 [2:17:55<2:56:13,  1.39it/s]
1|11176|Loss: 0.861038088798523:  43%|████▎     | 11175/25880 [2:17:55<2:56:13,  1.39it/s]
1|11176|Loss: 0.861038088798523:  43%|████▎     | 11176/25880 [2:17:55<2:50:56,  1.43it/s]
1|11177|Loss: 0.7923205494880676:  43%|████▎     | 11176/25880 [2:17:56<2:50:56,  1.43it/s]
1|11177|Loss: 0.7923205494880676:  43%|████▎     | 11177/25880 [2:17:56<2:55:10,  1.40it/s]
1|11178|Loss: 0.8611294627189636:  43%|████▎     | 11177/25880 [2:17:56<2:55:10,  1.40it/s]
1|11178|Loss: 0.8611294627189636:  43%|████▎     | 11178/25880 [2:17:57<3:04:31,  1.33it/s]
1|11179|Loss: 0.9085575938224792:  43%|████▎     | 11178/25880 [2:17:57<3:04:31,  1.33it/s]
1|11179|Loss: 0.9085575938224792:  43%|████▎     | 11179/25880 [2:17:57<3:03:23,  1.34it/s]
1|11180|Loss: 0.8789356350898743:  43%|████▎     | 11179/25880 [2:17:58<3:03:23,  1.34it/s]
1|11180|Loss: 0.8789356350898743:  43%|████▎     | 11180/25880 [2:17:58<3:07:02,  1.31it/s]
1|11181|Loss: 1.0128580331802368:  43%|████▎     | 11180/25880 [2:17:59<3:07:02,  1.31it/s]
1|11181|Loss: 1.0128580331802368:  43%|████▎     | 11181/25880 [2:17:59<3:09:14,  1.29it/s]
1|11182|Loss: 0.862758994102478:  43%|████▎     | 11181/25880 [2:18:00<3:09:14,  1.29it/s] 
1|11182|Loss: 0.862758994102478:  43%|████▎     | 11182/25880 [2:18:00<3:13:07,  1.27it/s]
1|11183|Loss: 0.852534830570221:  43%|████▎     | 11182/25880 [2:18:00<3:13:07,  1.27it/s]
1|11183|Loss: 0.852534830570221:  43%|████▎     | 11183/25880 [2:18:01<3:09:44,  1.29it/s]
1|11184|Loss: 0.8121774196624756:  43%|████▎     | 11183/25880 [2:18:01<3:09:44,  1.29it/s]
1|11184|Loss: 0.8121774196624756:  43%|████▎     | 11184/25880 [2:18:01<3:13:57,  1.26it/s]
1|11185|Loss: 0.7379547953605652:  43%|████▎     | 11184/25880 [2:18:02<3:13:57,  1.26it/s]
1|11185|Loss: 0.7379547953605652:  43%|████▎     | 11185/25880 [2:18:02<3:17:35,  1.24it/s]
1|11186|Loss: 0.8610458970069885:  43%|████▎     | 11185/25880 [2:18:03<3:17:35,  1.24it/s]
1|11186|Loss: 0.8610458970069885:  43%|████▎     | 11186/25880 [2:18:03<3:02:43,  1.34it/s]
1|11187|Loss: 0.8549282550811768:  43%|████▎     | 11186/25880 [2:18:03<3:02:43,  1.34it/s]
1|11187|Loss: 0.8549282550811768:  43%|████▎     | 11187/25880 [2:18:04<3:03:06,  1.34it/s]
1|11188|Loss: 0.8730452060699463:  43%|████▎     | 11187/25880 [2:18:04<3:03:06,  1.34it/s]
1|11188|Loss: 0.8730452060699463:  43%|████▎     | 11188/25880 [2:18:05<3:11:18,  1.28it/s]
1|11189|Loss: 0.7307593822479248:  43%|████▎     | 11188/25880 [2:18:05<3:11:18,  1.28it/s]
1|11189|Loss: 0.7307593822479248:  43%|████▎     | 11189/25880 [2:18:05<3:02:37,  1.34it/s]
1|11190|Loss: 0.8102171421051025:  43%|████▎     | 11189/25880 [2:18:06<3:02:37,  1.34it/s]
1|11190|Loss: 0.8102171421051025:  43%|████▎     | 11190/25880 [2:18:06<3:09:15,  1.29it/s]
1|11191|Loss: 0.7442167401313782:  43%|████▎     | 11190/25880 [2:18:06<3:09:15,  1.29it/s]
1|11191|Loss: 0.7442167401313782:  43%|████▎     | 11191/25880 [2:18:07<3:01:58,  1.35it/s]
1|11192|Loss: 0.6589764952659607:  43%|████▎     | 11191/25880 [2:18:07<3:01:58,  1.35it/s]
1|11192|Loss: 0.6589764952659607:  43%|████▎     | 11192/25880 [2:18:08<3:18:07,  1.24it/s]
1|11193|Loss: 0.8213022947311401:  43%|████▎     | 11192/25880 [2:18:08<3:18:07,  1.24it/s]
1|11193|Loss: 0.8213022947311401:  43%|████▎     | 11193/25880 [2:18:08<3:10:34,  1.28it/s]
1|11194|Loss: 0.7866473197937012:  43%|████▎     | 11193/25880 [2:18:09<3:10:34,  1.28it/s]
1|11194|Loss: 0.7866473197937012:  43%|████▎     | 11194/25880 [2:18:09<2:56:29,  1.39it/s]
1|11195|Loss: 0.8864902257919312:  43%|████▎     | 11194/25880 [2:18:09<2:56:29,  1.39it/s]
1|11195|Loss: 0.8864902257919312:  43%|████▎     | 11195/25880 [2:18:10<2:49:43,  1.44it/s]
1|11196|Loss: 0.9344583749771118:  43%|████▎     | 11195/25880 [2:18:10<2:49:43,  1.44it/s]
1|11196|Loss: 0.9344583749771118:  43%|████▎     | 11196/25880 [2:18:10<2:55:58,  1.39it/s]
1|11197|Loss: 0.9319905638694763:  43%|████▎     | 11196/25880 [2:18:11<2:55:58,  1.39it/s]
1|11197|Loss: 0.9319905638694763:  43%|████▎     | 11197/25880 [2:18:11<2:58:22,  1.37it/s]
1|11198|Loss: 0.8489015102386475:  43%|████▎     | 11197/25880 [2:18:12<2:58:22,  1.37it/s]
1|11198|Loss: 0.8489015102386475:  43%|████▎     | 11198/25880 [2:18:12<2:56:58,  1.38it/s]
1|11199|Loss: 0.7708833813667297:  43%|████▎     | 11198/25880 [2:18:12<2:56:58,  1.38it/s]
1|11199|Loss: 0.7708833813667297:  43%|████▎     | 11199/25880 [2:18:13<2:55:17,  1.40it/s]
1|11200|Loss: 0.8550103902816772:  43%|████▎     | 11199/25880 [2:18:13<2:55:17,  1.40it/s]
1|11200|Loss: 0.8550103902816772:  43%|████▎     | 11200/25880 [2:18:13<2:42:42,  1.50it/s]
1|11201|Loss: 0.8168485164642334:  43%|████▎     | 11200/25880 [2:18:13<2:42:42,  1.50it/s]
1|11201|Loss: 0.8168485164642334:  43%|████▎     | 11201/25880 [2:18:14<2:51:08,  1.43it/s]
1|11202|Loss: 0.923446774482727:  43%|████▎     | 11201/25880 [2:18:14<2:51:08,  1.43it/s] 
1|11202|Loss: 0.923446774482727:  43%|████▎     | 11202/25880 [2:18:15<2:49:12,  1.45it/s]
1|11203|Loss: 0.8616387844085693:  43%|████▎     | 11202/25880 [2:18:15<2:49:12,  1.45it/s]
1|11203|Loss: 0.8616387844085693:  43%|████▎     | 11203/25880 [2:18:15<2:40:28,  1.52it/s]
1|11204|Loss: 0.8483657836914062:  43%|████▎     | 11203/25880 [2:18:16<2:40:28,  1.52it/s]
1|11204|Loss: 0.8483657836914062:  43%|████▎     | 11204/25880 [2:18:16<2:46:50,  1.47it/s]
1|11205|Loss: 0.9234233498573303:  43%|████▎     | 11204/25880 [2:18:16<2:46:50,  1.47it/s]
1|11205|Loss: 0.9234233498573303:  43%|████▎     | 11205/25880 [2:18:17<2:49:58,  1.44it/s]
1|11206|Loss: 0.7203651666641235:  43%|████▎     | 11205/25880 [2:18:17<2:49:58,  1.44it/s]
1|11206|Loss: 0.7203651666641235:  43%|████▎     | 11206/25880 [2:18:17<2:58:14,  1.37it/s]
1|11207|Loss: 0.8761701583862305:  43%|████▎     | 11206/25880 [2:18:18<2:58:14,  1.37it/s]
1|11207|Loss: 0.8761701583862305:  43%|████▎     | 11207/25880 [2:18:18<2:54:15,  1.40it/s]
1|11208|Loss: 0.98465895652771:  43%|████▎     | 11207/25880 [2:18:18<2:54:15,  1.40it/s]  
1|11208|Loss: 0.98465895652771:  43%|████▎     | 11208/25880 [2:18:19<2:40:00,  1.53it/s]
1|11209|Loss: 0.9595431089401245:  43%|████▎     | 11208/25880 [2:18:19<2:40:00,  1.53it/s]
1|11209|Loss: 0.9595431089401245:  43%|████▎     | 11209/25880 [2:18:19<2:40:36,  1.52it/s]
1|11210|Loss: 0.7694954872131348:  43%|████▎     | 11209/25880 [2:18:20<2:40:36,  1.52it/s]
1|11210|Loss: 0.7694954872131348:  43%|████▎     | 11210/25880 [2:18:20<2:44:16,  1.49it/s]
1|11211|Loss: 0.9478768110275269:  43%|████▎     | 11210/25880 [2:18:20<2:44:16,  1.49it/s]
1|11211|Loss: 0.9478768110275269:  43%|████▎     | 11211/25880 [2:18:20<2:33:45,  1.59it/s]
1|11212|Loss: 0.8650975227355957:  43%|████▎     | 11211/25880 [2:18:21<2:33:45,  1.59it/s]
1|11212|Loss: 0.8650975227355957:  43%|████▎     | 11212/25880 [2:18:21<2:36:13,  1.56it/s]
1|11213|Loss: 0.8413203358650208:  43%|████▎     | 11212/25880 [2:18:22<2:36:13,  1.56it/s]
1|11213|Loss: 0.8413203358650208:  43%|████▎     | 11213/25880 [2:18:22<2:36:43,  1.56it/s]
1|11214|Loss: 0.7455629706382751:  43%|████▎     | 11213/25880 [2:18:22<2:36:43,  1.56it/s]
1|11214|Loss: 0.7455629706382751:  43%|████▎     | 11214/25880 [2:18:22<2:40:44,  1.52it/s]
1|11215|Loss: 0.8488165736198425:  43%|████▎     | 11214/25880 [2:18:23<2:40:44,  1.52it/s]
1|11215|Loss: 0.8488165736198425:  43%|████▎     | 11215/25880 [2:18:23<2:45:35,  1.48it/s]
1|11216|Loss: 0.8383213877677917:  43%|████▎     | 11215/25880 [2:18:24<2:45:35,  1.48it/s]
1|11216|Loss: 0.8383213877677917:  43%|████▎     | 11216/25880 [2:18:24<2:55:45,  1.39it/s]
1|11217|Loss: 0.7538813352584839:  43%|████▎     | 11216/25880 [2:18:24<2:55:45,  1.39it/s]
1|11217|Loss: 0.7538813352584839:  43%|████▎     | 11217/25880 [2:18:25<2:59:06,  1.36it/s]
1|11218|Loss: 0.7618299126625061:  43%|████▎     | 11217/25880 [2:18:25<2:59:06,  1.36it/s]
1|11218|Loss: 0.7618299126625061:  43%|████▎     | 11218/25880 [2:18:26<2:59:35,  1.36it/s]
1|11219|Loss: 1.0135360956192017:  43%|████▎     | 11218/25880 [2:18:26<2:59:35,  1.36it/s]
1|11219|Loss: 1.0135360956192017:  43%|████▎     | 11219/25880 [2:18:26<3:06:33,  1.31it/s]
1|11220|Loss: 0.9962354898452759:  43%|████▎     | 11219/25880 [2:18:27<3:06:33,  1.31it/s]
1|11220|Loss: 0.9962354898452759:  43%|████▎     | 11220/25880 [2:18:27<3:00:43,  1.35it/s]
1|11221|Loss: 0.8557677268981934:  43%|████▎     | 11220/25880 [2:18:27<3:00:43,  1.35it/s]
1|11221|Loss: 0.8557677268981934:  43%|████▎     | 11221/25880 [2:18:28<2:56:54,  1.38it/s]
1|11222|Loss: 0.9072890281677246:  43%|████▎     | 11221/25880 [2:18:28<2:56:54,  1.38it/s]
1|11222|Loss: 0.9072890281677246:  43%|████▎     | 11222/25880 [2:18:28<2:51:33,  1.42it/s]
1|11223|Loss: 0.823536217212677:  43%|████▎     | 11222/25880 [2:18:29<2:51:33,  1.42it/s] 
1|11223|Loss: 0.823536217212677:  43%|████▎     | 11223/25880 [2:18:29<2:55:19,  1.39it/s]
1|11224|Loss: 0.7916789650917053:  43%|████▎     | 11223/25880 [2:18:30<2:55:19,  1.39it/s]
1|11224|Loss: 0.7916789650917053:  43%|████▎     | 11224/25880 [2:18:30<2:48:18,  1.45it/s]
1|11225|Loss: 0.8699854612350464:  43%|████▎     | 11224/25880 [2:18:30<2:48:18,  1.45it/s]
1|11225|Loss: 0.8699854612350464:  43%|████▎     | 11225/25880 [2:18:31<2:59:57,  1.36it/s]
1|11226|Loss: 0.753358781337738:  43%|████▎     | 11225/25880 [2:18:31<2:59:57,  1.36it/s] 
1|11226|Loss: 0.753358781337738:  43%|████▎     | 11226/25880 [2:18:31<3:02:33,  1.34it/s]
1|11227|Loss: 0.7402501702308655:  43%|████▎     | 11226/25880 [2:18:32<3:02:33,  1.34it/s]
1|11227|Loss: 0.7402501702308655:  43%|████▎     | 11227/25880 [2:18:32<2:51:40,  1.42it/s]
1|11228|Loss: 0.8378714323043823:  43%|████▎     | 11227/25880 [2:18:32<2:51:40,  1.42it/s]
1|11228|Loss: 0.8378714323043823:  43%|████▎     | 11228/25880 [2:18:33<2:44:07,  1.49it/s]
1|11229|Loss: 0.9566360116004944:  43%|████▎     | 11228/25880 [2:18:33<2:44:07,  1.49it/s]
1|11229|Loss: 0.9566360116004944:  43%|████▎     | 11229/25880 [2:18:33<2:50:17,  1.43it/s]
1|11230|Loss: 0.8808217644691467:  43%|████▎     | 11229/25880 [2:18:34<2:50:17,  1.43it/s]
1|11230|Loss: 0.8808217644691467:  43%|████▎     | 11230/25880 [2:18:34<2:47:33,  1.46it/s]
1|11231|Loss: 0.9062293767929077:  43%|████▎     | 11230/25880 [2:18:34<2:47:33,  1.46it/s]
1|11231|Loss: 0.9062293767929077:  43%|████▎     | 11231/25880 [2:18:35<2:34:58,  1.58it/s]
1|11232|Loss: 0.7956076264381409:  43%|████▎     | 11231/25880 [2:18:35<2:34:58,  1.58it/s]
1|11232|Loss: 0.7956076264381409:  43%|████▎     | 11232/25880 [2:18:35<2:44:03,  1.49it/s]
1|11233|Loss: 0.8632849454879761:  43%|████▎     | 11232/25880 [2:18:36<2:44:03,  1.49it/s]
1|11233|Loss: 0.8632849454879761:  43%|████▎     | 11233/25880 [2:18:36<2:52:57,  1.41it/s]
1|11234|Loss: 0.8790722489356995:  43%|████▎     | 11233/25880 [2:18:37<2:52:57,  1.41it/s]
1|11234|Loss: 0.8790722489356995:  43%|████▎     | 11234/25880 [2:18:37<3:04:22,  1.32it/s]
1|11235|Loss: 0.778062105178833:  43%|████▎     | 11234/25880 [2:18:37<3:04:22,  1.32it/s] 
1|11235|Loss: 0.778062105178833:  43%|████▎     | 11235/25880 [2:18:38<2:58:31,  1.37it/s]
1|11236|Loss: 0.9200360178947449:  43%|████▎     | 11235/25880 [2:18:38<2:58:31,  1.37it/s]
1|11236|Loss: 0.9200360178947449:  43%|████▎     | 11236/25880 [2:18:38<2:56:57,  1.38it/s]
1|11237|Loss: 0.7544984817504883:  43%|████▎     | 11236/25880 [2:18:39<2:56:57,  1.38it/s]
1|11237|Loss: 0.7544984817504883:  43%|████▎     | 11237/25880 [2:18:39<2:56:46,  1.38it/s]
1|11238|Loss: 0.8830913305282593:  43%|████▎     | 11237/25880 [2:18:39<2:56:46,  1.38it/s]
1|11238|Loss: 0.8830913305282593:  43%|████▎     | 11238/25880 [2:18:40<3:01:21,  1.35it/s]
1|11239|Loss: 0.9162576794624329:  43%|████▎     | 11238/25880 [2:18:40<3:01:21,  1.35it/s]
1|11239|Loss: 0.9162576794624329:  43%|████▎     | 11239/25880 [2:18:40<2:54:30,  1.40it/s]
1|11240|Loss: 0.821950376033783:  43%|████▎     | 11239/25880 [2:18:41<2:54:30,  1.40it/s] 
1|11240|Loss: 0.821950376033783:  43%|████▎     | 11240/25880 [2:18:41<2:48:19,  1.45it/s]
1|11241|Loss: 0.7553614974021912:  43%|████▎     | 11240/25880 [2:18:41<2:48:19,  1.45it/s]
1|11241|Loss: 0.7553614974021912:  43%|████▎     | 11241/25880 [2:18:42<2:34:17,  1.58it/s]
1|11242|Loss: 0.8768779039382935:  43%|████▎     | 11241/25880 [2:18:42<2:34:17,  1.58it/s]
1|11242|Loss: 0.8768779039382935:  43%|████▎     | 11242/25880 [2:18:42<2:45:18,  1.48it/s]
1|11243|Loss: 0.8832345008850098:  43%|████▎     | 11242/25880 [2:18:43<2:45:18,  1.48it/s]
1|11243|Loss: 0.8832345008850098:  43%|████▎     | 11243/25880 [2:18:43<2:55:43,  1.39it/s]
1|11244|Loss: 0.7038385272026062:  43%|████▎     | 11243/25880 [2:18:44<2:55:43,  1.39it/s]
1|11244|Loss: 0.7038385272026062:  43%|████▎     | 11244/25880 [2:18:44<2:57:20,  1.38it/s]
1|11245|Loss: 0.7560403943061829:  43%|████▎     | 11244/25880 [2:18:44<2:57:20,  1.38it/s]
1|11245|Loss: 0.7560403943061829:  43%|████▎     | 11245/25880 [2:18:45<2:57:49,  1.37it/s]
1|11246|Loss: 0.8553866147994995:  43%|████▎     | 11245/25880 [2:18:45<2:57:49,  1.37it/s]
1|11246|Loss: 0.8553866147994995:  43%|████▎     | 11246/25880 [2:18:45<2:58:33,  1.37it/s]
1|11247|Loss: 0.7125886678695679:  43%|████▎     | 11246/25880 [2:18:46<2:58:33,  1.37it/s]
1|11247|Loss: 0.7125886678695679:  43%|████▎     | 11247/25880 [2:18:46<3:04:34,  1.32it/s]
1|11248|Loss: 0.8913339376449585:  43%|████▎     | 11247/25880 [2:18:47<3:04:34,  1.32it/s]
1|11248|Loss: 0.8913339376449585:  43%|████▎     | 11248/25880 [2:18:47<3:05:25,  1.32it/s]
1|11249|Loss: 0.944200873374939:  43%|████▎     | 11248/25880 [2:18:47<3:05:25,  1.32it/s] 
1|11249|Loss: 0.944200873374939:  43%|████▎     | 11249/25880 [2:18:48<3:08:21,  1.29it/s]
1|11250|Loss: 0.8644709587097168:  43%|████▎     | 11249/25880 [2:18:48<3:08:21,  1.29it/s]
1|11250|Loss: 0.8644709587097168:  43%|████▎     | 11250/25880 [2:18:49<3:15:08,  1.25it/s]
1|11251|Loss: 0.7076641321182251:  43%|████▎     | 11250/25880 [2:18:49<3:15:08,  1.25it/s]
1|11251|Loss: 0.7076641321182251:  43%|████▎     | 11251/25880 [2:18:49<3:10:41,  1.28it/s]
1|11252|Loss: 0.9462835192680359:  43%|████▎     | 11251/25880 [2:18:50<3:10:41,  1.28it/s]
1|11252|Loss: 0.9462835192680359:  43%|████▎     | 11252/25880 [2:18:50<3:06:25,  1.31it/s]
1|11253|Loss: 0.7943615913391113:  43%|████▎     | 11252/25880 [2:18:50<3:06:25,  1.31it/s]
1|11253|Loss: 0.7943615913391113:  43%|████▎     | 11253/25880 [2:18:51<2:53:14,  1.41it/s]
1|11254|Loss: 0.7645809650421143:  43%|████▎     | 11253/25880 [2:18:51<2:53:14,  1.41it/s]
1|11254|Loss: 0.7645809650421143:  43%|████▎     | 11254/25880 [2:18:51<2:31:05,  1.61it/s]
1|11255|Loss: 0.8988622426986694:  43%|████▎     | 11254/25880 [2:18:51<2:31:05,  1.61it/s]
1|11255|Loss: 0.8988622426986694:  43%|████▎     | 11255/25880 [2:18:52<2:29:41,  1.63it/s]
1|11256|Loss: 0.8112372159957886:  43%|████▎     | 11255/25880 [2:18:52<2:29:41,  1.63it/s]
1|11256|Loss: 0.8112372159957886:  43%|████▎     | 11256/25880 [2:18:52<2:28:32,  1.64it/s]
1|11257|Loss: 0.7488500475883484:  43%|████▎     | 11256/25880 [2:18:53<2:28:32,  1.64it/s]
1|11257|Loss: 0.7488500475883484:  43%|████▎     | 11257/25880 [2:18:53<2:43:48,  1.49it/s]
1|11258|Loss: 0.9519236087799072:  43%|████▎     | 11257/25880 [2:18:54<2:43:48,  1.49it/s]
1|11258|Loss: 0.9519236087799072:  44%|████▎     | 11258/25880 [2:18:54<2:53:55,  1.40it/s]
1|11259|Loss: 0.8859159350395203:  44%|████▎     | 11258/25880 [2:18:54<2:53:55,  1.40it/s]
1|11259|Loss: 0.8859159350395203:  44%|████▎     | 11259/25880 [2:18:55<2:54:46,  1.39it/s]
1|11260|Loss: 0.800368070602417:  44%|████▎     | 11259/25880 [2:18:55<2:54:46,  1.39it/s] 
1|11260|Loss: 0.800368070602417:  44%|████▎     | 11260/25880 [2:18:55<2:43:34,  1.49it/s]
1|11261|Loss: 0.8621712923049927:  44%|████▎     | 11260/25880 [2:18:56<2:43:34,  1.49it/s]
1|11261|Loss: 0.8621712923049927:  44%|████▎     | 11261/25880 [2:18:56<2:34:39,  1.58it/s]
1|11262|Loss: 0.7547309398651123:  44%|████▎     | 11261/25880 [2:18:56<2:34:39,  1.58it/s]
1|11262|Loss: 0.7547309398651123:  44%|████▎     | 11262/25880 [2:18:56<2:27:15,  1.65it/s]
1|11263|Loss: 0.8282055258750916:  44%|████▎     | 11262/25880 [2:18:57<2:27:15,  1.65it/s]
1|11263|Loss: 0.8282055258750916:  44%|████▎     | 11263/25880 [2:18:57<2:33:59,  1.58it/s]
1|11264|Loss: 0.889626681804657:  44%|████▎     | 11263/25880 [2:18:57<2:33:59,  1.58it/s] 
1|11264|Loss: 0.889626681804657:  44%|████▎     | 11264/25880 [2:18:58<2:47:18,  1.46it/s]
1|11265|Loss: 0.9171457290649414:  44%|████▎     | 11264/25880 [2:18:58<2:47:18,  1.46it/s]
1|11265|Loss: 0.9171457290649414:  44%|████▎     | 11265/25880 [2:18:59<2:52:47,  1.41it/s]
1|11266|Loss: 0.8150274753570557:  44%|████▎     | 11265/25880 [2:18:59<2:52:47,  1.41it/s]
1|11266|Loss: 0.8150274753570557:  44%|████▎     | 11266/25880 [2:18:59<2:49:08,  1.44it/s]
1|11267|Loss: 0.7589309811592102:  44%|████▎     | 11266/25880 [2:19:00<2:49:08,  1.44it/s]
1|11267|Loss: 0.7589309811592102:  44%|████▎     | 11267/25880 [2:19:00<2:56:13,  1.38it/s]
1|11268|Loss: 0.9894415140151978:  44%|████▎     | 11267/25880 [2:19:01<2:56:13,  1.38it/s]
1|11268|Loss: 0.9894415140151978:  44%|████▎     | 11268/25880 [2:19:01<3:03:42,  1.33it/s]
1|11269|Loss: 0.8175539374351501:  44%|████▎     | 11268/25880 [2:19:01<3:03:42,  1.33it/s]
1|11269|Loss: 0.8175539374351501:  44%|████▎     | 11269/25880 [2:19:02<3:06:10,  1.31it/s]
1|11270|Loss: 0.896508514881134:  44%|████▎     | 11269/25880 [2:19:02<3:06:10,  1.31it/s] 
1|11270|Loss: 0.896508514881134:  44%|████▎     | 11270/25880 [2:19:02<3:10:12,  1.28it/s]
1|11271|Loss: 0.7821927070617676:  44%|████▎     | 11270/25880 [2:19:03<3:10:12,  1.28it/s]
1|11271|Loss: 0.7821927070617676:  44%|████▎     | 11271/25880 [2:19:03<3:13:26,  1.26it/s]
1|11272|Loss: 0.7538132667541504:  44%|████▎     | 11271/25880 [2:19:04<3:13:26,  1.26it/s]
1|11272|Loss: 0.7538132667541504:  44%|████▎     | 11272/25880 [2:19:04<3:04:56,  1.32it/s]
1|11273|Loss: 0.9552635550498962:  44%|████▎     | 11272/25880 [2:19:04<3:04:56,  1.32it/s]
1|11273|Loss: 0.9552635550498962:  44%|████▎     | 11273/25880 [2:19:05<3:01:33,  1.34it/s]
1|11274|Loss: 0.8310987949371338:  44%|████▎     | 11273/25880 [2:19:05<3:01:33,  1.34it/s]
1|11274|Loss: 0.8310987949371338:  44%|████▎     | 11274/25880 [2:19:05<3:04:34,  1.32it/s]
1|11275|Loss: 0.7720282077789307:  44%|████▎     | 11274/25880 [2:19:06<3:04:34,  1.32it/s]
1|11275|Loss: 0.7720282077789307:  44%|████▎     | 11275/25880 [2:19:06<3:01:32,  1.34it/s]
1|11276|Loss: 0.6137732267379761:  44%|████▎     | 11275/25880 [2:19:07<3:01:32,  1.34it/s]
1|11276|Loss: 0.6137732267379761:  44%|████▎     | 11276/25880 [2:19:07<2:52:53,  1.41it/s]
1|11277|Loss: 0.8668041825294495:  44%|████▎     | 11276/25880 [2:19:07<2:52:53,  1.41it/s]
1|11277|Loss: 0.8668041825294495:  44%|████▎     | 11277/25880 [2:19:08<2:56:12,  1.38it/s]
1|11278|Loss: 0.8860509395599365:  44%|████▎     | 11277/25880 [2:19:08<2:56:12,  1.38it/s]
1|11278|Loss: 0.8860509395599365:  44%|████▎     | 11278/25880 [2:19:08<2:57:44,  1.37it/s]
1|11279|Loss: 0.8813412189483643:  44%|████▎     | 11278/25880 [2:19:09<2:57:44,  1.37it/s]
1|11279|Loss: 0.8813412189483643:  44%|████▎     | 11279/25880 [2:19:09<3:01:39,  1.34it/s]
1|11280|Loss: 0.8429381847381592:  44%|████▎     | 11279/25880 [2:19:10<3:01:39,  1.34it/s]
1|11280|Loss: 0.8429381847381592:  44%|████▎     | 11280/25880 [2:19:10<3:11:58,  1.27it/s]
1|11281|Loss: 0.7520120739936829:  44%|████▎     | 11280/25880 [2:19:10<3:11:58,  1.27it/s]
1|11281|Loss: 0.7520120739936829:  44%|████▎     | 11281/25880 [2:19:11<3:01:38,  1.34it/s]
1|11282|Loss: 0.839394748210907:  44%|████▎     | 11281/25880 [2:19:11<3:01:38,  1.34it/s] 
1|11282|Loss: 0.839394748210907:  44%|████▎     | 11282/25880 [2:19:11<2:52:51,  1.41it/s]
1|11283|Loss: 0.8236300945281982:  44%|████▎     | 11282/25880 [2:19:12<2:52:51,  1.41it/s]
1|11283|Loss: 0.8236300945281982:  44%|████▎     | 11283/25880 [2:19:12<2:56:36,  1.38it/s]
1|11284|Loss: 0.8017908334732056:  44%|████▎     | 11283/25880 [2:19:12<2:56:36,  1.38it/s]
1|11284|Loss: 0.8017908334732056:  44%|████▎     | 11284/25880 [2:19:13<2:58:14,  1.36it/s]
1|11285|Loss: 0.8050947785377502:  44%|████▎     | 11284/25880 [2:19:13<2:58:14,  1.36it/s]
1|11285|Loss: 0.8050947785377502:  44%|████▎     | 11285/25880 [2:19:14<2:56:26,  1.38it/s]
1|11286|Loss: 0.7760853171348572:  44%|████▎     | 11285/25880 [2:19:14<2:56:26,  1.38it/s]
1|11286|Loss: 0.7760853171348572:  44%|████▎     | 11286/25880 [2:19:14<3:07:03,  1.30it/s]
1|11287|Loss: 0.7900835871696472:  44%|████▎     | 11286/25880 [2:19:15<3:07:03,  1.30it/s]
1|11287|Loss: 0.7900835871696472:  44%|████▎     | 11287/25880 [2:19:15<3:07:35,  1.30it/s]
1|11288|Loss: 0.8725001811981201:  44%|████▎     | 11287/25880 [2:19:16<3:07:35,  1.30it/s]
1|11288|Loss: 0.8725001811981201:  44%|████▎     | 11288/25880 [2:19:16<3:03:27,  1.33it/s]
1|11289|Loss: 0.9107822775840759:  44%|████▎     | 11288/25880 [2:19:16<3:03:27,  1.33it/s]
1|11289|Loss: 0.9107822775840759:  44%|████▎     | 11289/25880 [2:19:17<3:07:48,  1.29it/s]
1|11290|Loss: 0.8690292835235596:  44%|████▎     | 11289/25880 [2:19:17<3:07:48,  1.29it/s]
1|11290|Loss: 0.8690292835235596:  44%|████▎     | 11290/25880 [2:19:17<3:00:14,  1.35it/s]
1|11291|Loss: 0.7197266817092896:  44%|████▎     | 11290/25880 [2:19:18<3:00:14,  1.35it/s]
1|11291|Loss: 0.7197266817092896:  44%|████▎     | 11291/25880 [2:19:18<2:52:21,  1.41it/s]
1|11292|Loss: 0.879213273525238:  44%|████▎     | 11291/25880 [2:19:18<2:52:21,  1.41it/s] 
1|11292|Loss: 0.879213273525238:  44%|████▎     | 11292/25880 [2:19:19<2:53:00,  1.41it/s]
1|11293|Loss: 1.01637864112854:  44%|████▎     | 11292/25880 [2:19:19<2:53:00,  1.41it/s] 
1|11293|Loss: 1.01637864112854:  44%|████▎     | 11293/25880 [2:19:19<2:53:14,  1.40it/s]
1|11294|Loss: 0.9942122101783752:  44%|████▎     | 11293/25880 [2:19:20<2:53:14,  1.40it/s]
1|11294|Loss: 0.9942122101783752:  44%|████▎     | 11294/25880 [2:19:20<2:40:44,  1.51it/s]
1|11295|Loss: 0.8693585395812988:  44%|████▎     | 11294/25880 [2:19:20<2:40:44,  1.51it/s]
1|11295|Loss: 0.8693585395812988:  44%|████▎     | 11295/25880 [2:19:21<2:40:14,  1.52it/s]
1|11296|Loss: 0.7933382391929626:  44%|████▎     | 11295/25880 [2:19:21<2:40:14,  1.52it/s]
1|11296|Loss: 0.7933382391929626:  44%|████▎     | 11296/25880 [2:19:21<2:48:43,  1.44it/s]
1|11297|Loss: 0.7967664003372192:  44%|████▎     | 11296/25880 [2:19:22<2:48:43,  1.44it/s]
1|11297|Loss: 0.7967664003372192:  44%|████▎     | 11297/25880 [2:19:22<2:47:24,  1.45it/s]
1|11298|Loss: 0.9519772529602051:  44%|████▎     | 11297/25880 [2:19:22<2:47:24,  1.45it/s]
1|11298|Loss: 0.9519772529602051:  44%|████▎     | 11298/25880 [2:19:23<2:44:22,  1.48it/s]
1|11299|Loss: 0.7048531770706177:  44%|████▎     | 11298/25880 [2:19:23<2:44:22,  1.48it/s]
1|11299|Loss: 0.7048531770706177:  44%|████▎     | 11299/25880 [2:19:23<2:38:17,  1.54it/s]
1|11300|Loss: 0.9527696371078491:  44%|████▎     | 11299/25880 [2:19:24<2:38:17,  1.54it/s]
1|11300|Loss: 0.9527696371078491:  44%|████▎     | 11300/25880 [2:19:24<2:40:20,  1.52it/s]
1|11301|Loss: 0.735377311706543:  44%|████▎     | 11300/25880 [2:19:24<2:40:20,  1.52it/s] 
1|11301|Loss: 0.735377311706543:  44%|████▎     | 11301/25880 [2:19:25<2:38:21,  1.53it/s]
1|11302|Loss: 0.6862687468528748:  44%|████▎     | 11301/25880 [2:19:25<2:38:21,  1.53it/s]
1|11302|Loss: 0.6862687468528748:  44%|████▎     | 11302/25880 [2:19:25<2:33:38,  1.58it/s]
1|11303|Loss: 0.756585955619812:  44%|████▎     | 11302/25880 [2:19:26<2:33:38,  1.58it/s] 
1|11303|Loss: 0.756585955619812:  44%|████▎     | 11303/25880 [2:19:26<2:39:24,  1.52it/s]
1|11304|Loss: 0.8416967988014221:  44%|████▎     | 11303/25880 [2:19:26<2:39:24,  1.52it/s]
1|11304|Loss: 0.8416967988014221:  44%|████▎     | 11304/25880 [2:19:27<2:43:53,  1.48it/s]
1|11305|Loss: 0.8474574685096741:  44%|████▎     | 11304/25880 [2:19:27<2:43:53,  1.48it/s]
1|11305|Loss: 0.8474574685096741:  44%|████▎     | 11305/25880 [2:19:27<2:47:22,  1.45it/s]
1|11306|Loss: 0.7236633896827698:  44%|████��     | 11305/25880 [2:19:28<2:47:22,  1.45it/s]
1|11306|Loss: 0.7236633896827698:  44%|████▎     | 11306/25880 [2:19:28<2:37:28,  1.54it/s]
1|11307|Loss: 0.7129947543144226:  44%|████▎     | 11306/25880 [2:19:28<2:37:28,  1.54it/s]
1|11307|Loss: 0.7129947543144226:  44%|████▎     | 11307/25880 [2:19:29<2:40:13,  1.52it/s]
1|11308|Loss: 0.7803924083709717:  44%|████▎     | 11307/25880 [2:19:29<2:40:13,  1.52it/s]
1|11308|Loss: 0.7803924083709717:  44%|████▎     | 11308/25880 [2:19:29<2:46:02,  1.46it/s]
1|11309|Loss: 0.9666231870651245:  44%|████▎     | 11308/25880 [2:19:30<2:46:02,  1.46it/s]
1|11309|Loss: 0.9666231870651245:  44%|████▎     | 11309/25880 [2:19:30<3:01:10,  1.34it/s]
1|11310|Loss: 0.8687505722045898:  44%|████▎     | 11309/25880 [2:19:31<3:01:10,  1.34it/s]
1|11310|Loss: 0.8687505722045898:  44%|████▎     | 11310/25880 [2:19:31<3:11:48,  1.27it/s]
1|11311|Loss: 0.7661967277526855:  44%|████▎     | 11310/25880 [2:19:32<3:11:48,  1.27it/s]
1|11311|Loss: 0.7661967277526855:  44%|████▎     | 11311/25880 [2:19:32<3:05:10,  1.31it/s]
1|11312|Loss: 0.9382376074790955:  44%|████▎     | 11311/25880 [2:19:32<3:05:10,  1.31it/s]
1|11312|Loss: 0.9382376074790955:  44%|████▎     | 11312/25880 [2:19:32<2:49:41,  1.43it/s]
1|11313|Loss: 0.9092239737510681:  44%|████▎     | 11312/25880 [2:19:33<2:49:41,  1.43it/s]
1|11313|Loss: 0.9092239737510681:  44%|████▎     | 11313/25880 [2:19:33<2:43:36,  1.48it/s]
1|11314|Loss: 0.7937845587730408:  44%|████▎     | 11313/25880 [2:19:33<2:43:36,  1.48it/s]
1|11314|Loss: 0.7937845587730408:  44%|████▎     | 11314/25880 [2:19:34<2:45:12,  1.47it/s]
1|11315|Loss: 0.9018833041191101:  44%|████▎     | 11314/25880 [2:19:34<2:45:12,  1.47it/s]
1|11315|Loss: 0.9018833041191101:  44%|████▎     | 11315/25880 [2:19:34<2:48:34,  1.44it/s]
1|11316|Loss: 0.9557046294212341:  44%|████▎     | 11315/25880 [2:19:35<2:48:34,  1.44it/s]
1|11316|Loss: 0.9557046294212341:  44%|████▎     | 11316/25880 [2:19:35<2:49:03,  1.44it/s]
1|11317|Loss: 0.8427272439002991:  44%|████▎     | 11316/25880 [2:19:35<2:49:03,  1.44it/s]
1|11317|Loss: 0.8427272439002991:  44%|████▎     | 11317/25880 [2:19:36<2:39:14,  1.52it/s]
1|11318|Loss: 0.909772515296936:  44%|████▎     | 11317/25880 [2:19:36<2:39:14,  1.52it/s] 
1|11318|Loss: 0.909772515296936:  44%|████▎     | 11318/25880 [2:19:36<2:41:25,  1.50it/s]
1|11319|Loss: 0.8020429611206055:  44%|████▎     | 11318/25880 [2:19:37<2:41:25,  1.50it/s]
1|11319|Loss: 0.8020429611206055:  44%|████▎     | 11319/25880 [2:19:37<2:50:17,  1.43it/s]
1|11320|Loss: 0.7507559657096863:  44%|████▎     | 11319/25880 [2:19:37<2:50:17,  1.43it/s]
1|11320|Loss: 0.7507559657096863:  44%|████▎     | 11320/25880 [2:19:38<2:39:10,  1.52it/s]
1|11321|Loss: 0.7659816145896912:  44%|████▎     | 11320/25880 [2:19:38<2:39:10,  1.52it/s]
1|11321|Loss: 0.7659816145896912:  44%|████▎     | 11321/25880 [2:19:38<2:41:28,  1.50it/s]
1|11322|Loss: 0.9745376706123352:  44%|████▎     | 11321/25880 [2:19:39<2:41:28,  1.50it/s]
1|11322|Loss: 0.9745376706123352:  44%|████▎     | 11322/25880 [2:19:39<2:40:42,  1.51it/s]
1|11323|Loss: 0.9366093277931213:  44%|████▎     | 11322/25880 [2:19:39<2:40:42,  1.51it/s]
1|11323|Loss: 0.9366093277931213:  44%|████▍     | 11323/25880 [2:19:40<2:37:03,  1.54it/s]
1|11324|Loss: 0.8173130750656128:  44%|████▍     | 11323/25880 [2:19:40<2:37:03,  1.54it/s]
1|11324|Loss: 0.8173130750656128:  44%|████▍     | 11324/25880 [2:19:40<2:41:26,  1.50it/s]
1|11325|Loss: 0.8274946808815002:  44%|████▍     | 11324/25880 [2:19:41<2:41:26,  1.50it/s]
1|11325|Loss: 0.8274946808815002:  44%|████▍     | 11325/25880 [2:19:41<2:41:01,  1.51it/s]
1|11326|Loss: 0.8274078965187073:  44%|████▍     | 11325/25880 [2:19:41<2:41:01,  1.51it/s]
1|11326|Loss: 0.8274078965187073:  44%|████▍     | 11326/25880 [2:19:42<2:50:30,  1.42it/s]
1|11327|Loss: 0.8357287049293518:  44%|████▍     | 11326/25880 [2:19:42<2:50:30,  1.42it/s]
1|11327|Loss: 0.8357287049293518:  44%|████▍     | 11327/25880 [2:19:43<3:00:47,  1.34it/s]
1|11328|Loss: 0.9002235531806946:  44%|████▍     | 11327/25880 [2:19:43<3:00:47,  1.34it/s]
1|11328|Loss: 0.9002235531806946:  44%|████▍     | 11328/25880 [2:19:43<3:01:57,  1.33it/s]
1|11329|Loss: 0.7981876730918884:  44%|████▍     | 11328/25880 [2:19:44<3:01:57,  1.33it/s]
1|11329|Loss: 0.7981876730918884:  44%|████▍     | 11329/25880 [2:19:44<3:11:33,  1.27it/s]
1|11330|Loss: 0.8215880990028381:  44%|████▍     | 11329/25880 [2:19:45<3:11:33,  1.27it/s]
1|11330|Loss: 0.8215880990028381:  44%|████▍     | 11330/25880 [2:19:45<2:57:18,  1.37it/s]
1|11331|Loss: 0.7069420218467712:  44%|████▍     | 11330/25880 [2:19:45<2:57:18,  1.37it/s]
1|11331|Loss: 0.7069420218467712:  44%|████▍     | 11331/25880 [2:19:46<2:54:29,  1.39it/s]
1|11332|Loss: 0.7913461923599243:  44%|████▍     | 11331/25880 [2:19:46<2:54:29,  1.39it/s]
1|11332|Loss: 0.7913461923599243:  44%|████▍     | 11332/25880 [2:19:46<2:48:48,  1.44it/s]
1|11333|Loss: 0.794122576713562:  44%|████▍     | 11332/25880 [2:19:47<2:48:48,  1.44it/s] 
1|11333|Loss: 0.794122576713562:  44%|████▍     | 11333/25880 [2:19:47<2:50:12,  1.42it/s]
1|11334|Loss: 0.879680871963501:  44%|████▍     | 11333/25880 [2:19:47<2:50:12,  1.42it/s]
1|11334|Loss: 0.879680871963501:  44%|████▍     | 11334/25880 [2:19:48<2:45:23,  1.47it/s]
1|11335|Loss: 0.9078309535980225:  44%|████▍     | 11334/25880 [2:19:48<2:45:23,  1.47it/s]
1|11335|Loss: 0.9078309535980225:  44%|████▍     | 11335/25880 [2:19:48<2:40:47,  1.51it/s]
1|11336|Loss: 0.8085834383964539:  44%|████▍     | 11335/25880 [2:19:49<2:40:47,  1.51it/s]
1|11336|Loss: 0.8085834383964539:  44%|████▍     | 11336/25880 [2:19:49<2:31:11,  1.60it/s]
1|11337|Loss: 0.8958425521850586:  44%|████▍     | 11336/25880 [2:19:49<2:31:11,  1.60it/s]
1|11337|Loss: 0.8958425521850586:  44%|████▍     | 11337/25880 [2:19:49<2:35:41,  1.56it/s]
1|11338|Loss: 0.7889993786811829:  44%|████▍     | 11337/25880 [2:19:50<2:35:41,  1.56it/s]
1|11338|Loss: 0.7889993786811829:  44%|████▍     | 11338/25880 [2:19:50<2:37:07,  1.54it/s]
1|11339|Loss: 0.8966838121414185:  44%|████▍     | 11338/25880 [2:19:50<2:37:07,  1.54it/s]
1|11339|Loss: 0.8966838121414185:  44%|████▍     | 11339/25880 [2:19:51<2:42:34,  1.49it/s]
1|11340|Loss: 0.9503095746040344:  44%|████▍     | 11339/25880 [2:19:51<2:42:34,  1.49it/s]
1|11340|Loss: 0.9503095746040344:  44%|████▍     | 11340/25880 [2:19:52<2:50:58,  1.42it/s]
1|11341|Loss: 0.7987700700759888:  44%|████▍     | 11340/25880 [2:19:52<2:50:58,  1.42it/s]
1|11341|Loss: 0.7987700700759888:  44%|████▍     | 11341/25880 [2:19:52<2:57:09,  1.37it/s]
1|11342|Loss: 0.7486222386360168:  44%|████▍     | 11341/25880 [2:19:53<2:57:09,  1.37it/s]
1|11342|Loss: 0.7486222386360168:  44%|████▍     | 11342/25880 [2:19:53<2:58:43,  1.36it/s]
1|11343|Loss: 0.9709419012069702:  44%|████▍     | 11342/25880 [2:19:54<2:58:43,  1.36it/s]
1|11343|Loss: 0.9709419012069702:  44%|████▍     | 11343/25880 [2:19:54<2:53:39,  1.40it/s]
1|11344|Loss: 0.7499047517776489:  44%|████▍     | 11343/25880 [2:19:54<2:53:39,  1.40it/s]
1|11344|Loss: 0.7499047517776489:  44%|████▍     | 11344/25880 [2:19:55<3:01:59,  1.33it/s]
1|11345|Loss: 0.7811769247055054:  44%|████▍     | 11344/25880 [2:19:55<3:01:59,  1.33it/s]
1|11345|Loss: 0.7811769247055054:  44%|████▍     | 11345/25880 [2:19:55<3:03:03,  1.32it/s]
1|11346|Loss: 0.840480625629425:  44%|████▍     | 11345/25880 [2:19:56<3:03:03,  1.32it/s] 
1|11346|Loss: 0.840480625629425:  44%|████▍     | 11346/25880 [2:19:56<2:48:23,  1.44it/s]
1|11347|Loss: 0.8680081963539124:  44%|████▍     | 11346/25880 [2:19:56<2:48:23,  1.44it/s]
1|11347|Loss: 0.8680081963539124:  44%|████▍     | 11347/25880 [2:19:57<2:45:42,  1.46it/s]
1|11348|Loss: 0.8634485602378845:  44%|████▍     | 11347/25880 [2:19:57<2:45:42,  1.46it/s]
1|11348|Loss: 0.8634485602378845:  44%|████▍     | 11348/25880 [2:19:57<2:53:10,  1.40it/s]
1|11349|Loss: 0.8008965253829956:  44%|████▍     | 11348/25880 [2:19:58<2:53:10,  1.40it/s]
1|11349|Loss: 0.8008965253829956:  44%|████▍     | 11349/25880 [2:19:58<2:42:30,  1.49it/s]
1|11350|Loss: 0.9319173693656921:  44%|████▍     | 11349/25880 [2:19:58<2:42:30,  1.49it/s]
1|11350|Loss: 0.9319173693656921:  44%|████▍     | 11350/25880 [2:19:59<2:46:44,  1.45it/s]
1|11351|Loss: 0.9207536578178406:  44%|████▍     | 11350/25880 [2:19:59<2:46:44,  1.45it/s]
1|11351|Loss: 0.9207536578178406:  44%|████▍     | 11351/25880 [2:20:00<2:57:21,  1.37it/s]
1|11352|Loss: 0.8884819149971008:  44%|████▍     | 11351/25880 [2:20:00<2:57:21,  1.37it/s]
1|11352|Loss: 0.8884819149971008:  44%|████▍     | 11352/25880 [2:20:00<3:07:06,  1.29it/s]
1|11353|Loss: 0.722085177898407:  44%|████▍     | 11352/25880 [2:20:01<3:07:06,  1.29it/s] 
1|11353|Loss: 0.722085177898407:  44%|████▍     | 11353/25880 [2:20:01<3:04:58,  1.31it/s]
1|11354|Loss: 0.9238258600234985:  44%|████▍     | 11353/25880 [2:20:01<3:04:58,  1.31it/s]
1|11354|Loss: 0.9238258600234985:  44%|████▍     | 11354/25880 [2:20:02<2:53:27,  1.40it/s]
1|11355|Loss: 0.9895185232162476:  44%|████▍     | 11354/25880 [2:20:02<2:53:27,  1.40it/s]
1|11355|Loss: 0.9895185232162476:  44%|████▍     | 11355/25880 [2:20:02<2:46:49,  1.45it/s]
1|11356|Loss: 0.7545008063316345:  44%|████▍     | 11355/25880 [2:20:03<2:46:49,  1.45it/s]
1|11356|Loss: 0.7545008063316345:  44%|████▍     | 11356/25880 [2:20:03<2:59:45,  1.35it/s]
1|11357|Loss: 0.9676681160926819:  44%|████▍     | 11356/25880 [2:20:04<2:59:45,  1.35it/s]
1|11357|Loss: 0.9676681160926819:  44%|████▍     | 11357/25880 [2:20:04<2:54:55,  1.38it/s]
1|11358|Loss: 0.8461931347846985:  44%|████▍     | 11357/25880 [2:20:04<2:54:55,  1.38it/s]
1|11358|Loss: 0.8461931347846985:  44%|████▍     | 11358/25880 [2:20:05<2:54:05,  1.39it/s]
1|11359|Loss: 1.0157698392868042:  44%|████▍     | 11358/25880 [2:20:05<2:54:05,  1.39it/s]
1|11359|Loss: 1.0157698392868042:  44%|████▍     | 11359/25880 [2:20:05<3:01:30,  1.33it/s]
1|11360|Loss: 0.6878311634063721:  44%|████▍     | 11359/25880 [2:20:06<3:01:30,  1.33it/s]
1|11360|Loss: 0.6878311634063721:  44%|████▍     | 11360/25880 [2:20:06<3:00:47,  1.34it/s]
1|11361|Loss: 0.8571711182594299:  44%|████▍     | 11360/25880 [2:20:07<3:00:47,  1.34it/s]
1|11361|Loss: 0.8571711182594299:  44%|████▍     | 11361/25880 [2:20:07<3:05:38,  1.30it/s]
1|11362|Loss: 0.8370118141174316:  44%|████▍     | 11361/25880 [2:20:07<3:05:38,  1.30it/s]
1|11362|Loss: 0.8370118141174316:  44%|████▍     | 11362/25880 [2:20:08<2:56:08,  1.37it/s]
1|11363|Loss: 0.7804168462753296:  44%|████▍     | 11362/25880 [2:20:08<2:56:08,  1.37it/s]
1|11363|Loss: 0.7804168462753296:  44%|████▍     | 11363/25880 [2:20:08<2:47:58,  1.44it/s]
1|11364|Loss: 0.8953937888145447:  44%|████▍     | 11363/25880 [2:20:09<2:47:58,  1.44it/s]
1|11364|Loss: 0.8953937888145447:  44%|████▍     | 11364/25880 [2:20:09<2:41:07,  1.50it/s]
1|11365|Loss: 0.9081548452377319:  44%|████▍     | 11364/25880 [2:20:09<2:41:07,  1.50it/s]
1|11365|Loss: 0.9081548452377319:  44%|████▍     | 11365/25880 [2:20:10<2:44:29,  1.47it/s]
1|11366|Loss: 0.8637565970420837:  44%|████▍     | 11365/25880 [2:20:10<2:44:29,  1.47it/s]
1|11366|Loss: 0.8637565970420837:  44%|████▍     | 11366/25880 [2:20:10<2:43:45,  1.48it/s]
1|11367|Loss: 0.9244931936264038:  44%|████▍     | 11366/25880 [2:20:11<2:43:45,  1.48it/s]
1|11367|Loss: 0.9244931936264038:  44%|████▍     | 11367/25880 [2:20:11<2:46:04,  1.46it/s]
1|11368|Loss: 0.9152482748031616:  44%|████▍     | 11367/25880 [2:20:11<2:46:04,  1.46it/s]
1|11368|Loss: 0.9152482748031616:  44%|████▍     | 11368/25880 [2:20:12<2:47:28,  1.44it/s]
1|11369|Loss: 0.7528552412986755:  44%|████▍     | 11368/25880 [2:20:12<2:47:28,  1.44it/s]
1|11369|Loss: 0.7528552412986755:  44%|████▍     | 11369/25880 [2:20:12<2:40:53,  1.50it/s]
1|11370|Loss: 0.7169749736785889:  44%|████▍     | 11369/25880 [2:20:13<2:40:53,  1.50it/s]
1|11370|Loss: 0.7169749736785889:  44%|████▍     | 11370/25880 [2:20:13<2:41:47,  1.49it/s]
1|11371|Loss: 0.7901870012283325:  44%|████▍     | 11370/25880 [2:20:13<2:41:47,  1.49it/s]
1|11371|Loss: 0.7901870012283325:  44%|████▍     | 11371/25880 [2:20:13<2:33:33,  1.57it/s]
1|11372|Loss: 0.7568924427032471:  44%|████▍     | 11371/25880 [2:20:14<2:33:33,  1.57it/s]
1|11372|Loss: 0.7568924427032471:  44%|████▍     | 11372/25880 [2:20:14<2:37:47,  1.53it/s]
1|11373|Loss: 0.8448771238327026:  44%|████▍     | 11372/25880 [2:20:15<2:37:47,  1.53it/s]
1|11373|Loss: 0.8448771238327026:  44%|████▍     | 11373/25880 [2:20:15<2:50:37,  1.42it/s]
1|11374|Loss: 0.9373980760574341:  44%|████▍     | 11373/25880 [2:20:15<2:50:37,  1.42it/s]
1|11374|Loss: 0.9373980760574341:  44%|████▍     | 11374/25880 [2:20:16<2:54:55,  1.38it/s]
1|11375|Loss: 0.7983103394508362:  44%|████▍     | 11374/25880 [2:20:16<2:54:55,  1.38it/s]
1|11375|Loss: 0.7983103394508362:  44%|████▍     | 11375/25880 [2:20:17<3:06:35,  1.30it/s]
1|11376|Loss: 0.9161689281463623:  44%|████▍     | 11375/25880 [2:20:17<3:06:35,  1.30it/s]
1|11376|Loss: 0.9161689281463623:  44%|████▍     | 11376/25880 [2:20:17<2:59:26,  1.35it/s]
1|11377|Loss: 0.795142412185669:  44%|████▍     | 11376/25880 [2:20:18<2:59:26,  1.35it/s] 
1|11377|Loss: 0.795142412185669:  44%|████▍     | 11377/25880 [2:20:18<2:48:23,  1.44it/s]
1|11378|Loss: 0.8757211565971375:  44%|████▍     | 11377/25880 [2:20:18<2:48:23,  1.44it/s]
1|11378|Loss: 0.8757211565971375:  44%|████▍     | 11378/25880 [2:20:19<2:54:24,  1.39it/s]
1|11379|Loss: 0.8028901815414429:  44%|████▍     | 11378/25880 [2:20:19<2:54:24,  1.39it/s]
1|11379|Loss: 0.8028901815414429:  44%|████▍     | 11379/25880 [2:20:20<3:04:23,  1.31it/s]
1|11380|Loss: 0.7215887904167175:  44%|████▍     | 11379/25880 [2:20:20<3:04:23,  1.31it/s]
1|11380|Loss: 0.7215887904167175:  44%|████▍     | 11380/25880 [2:20:20<2:51:57,  1.41it/s]
1|11381|Loss: 0.857003390789032:  44%|████▍     | 11380/25880 [2:20:20<2:51:57,  1.41it/s] 
1|11381|Loss: 0.857003390789032:  44%|████▍     | 11381/25880 [2:20:21<2:43:39,  1.48it/s]
1|11382|Loss: 0.8194777369499207:  44%|████▍     | 11381/25880 [2:20:21<2:43:39,  1.48it/s]
1|11382|Loss: 0.8194777369499207:  44%|████▍     | 11382/25880 [2:20:21<2:44:36,  1.47it/s]
1|11383|Loss: 0.8951843976974487:  44%|████▍     | 11382/25880 [2:20:22<2:44:36,  1.47it/s]
1|11383|Loss: 0.8951843976974487:  44%|████▍     | 11383/25880 [2:20:22<2:38:42,  1.52it/s]
1|11384|Loss: 0.7821431756019592:  44%|████▍     | 11383/25880 [2:20:22<2:38:42,  1.52it/s]
1|11384|Loss: 0.7821431756019592:  44%|████▍     | 11384/25880 [2:20:23<2:34:48,  1.56it/s]
1|11385|Loss: 0.9488785862922668:  44%|████▍     | 11384/25880 [2:20:23<2:34:48,  1.56it/s]
1|11385|Loss: 0.9488785862922668:  44%|████▍     | 11385/25880 [2:20:23<2:40:18,  1.51it/s]
1|11386|Loss: 0.8449251651763916:  44%|████▍     | 11385/25880 [2:20:24<2:40:18,  1.51it/s]
1|11386|Loss: 0.8449251651763916:  44%|████▍     | 11386/25880 [2:20:24<2:52:06,  1.40it/s]
1|11387|Loss: 0.7771425843238831:  44%|████▍     | 11386/25880 [2:20:25<2:52:06,  1.40it/s]
1|11387|Loss: 0.7771425843238831:  44%|████▍     | 11387/25880 [2:20:25<3:01:22,  1.33it/s]
1|11388|Loss: 0.9008951783180237:  44%|████▍     | 11387/25880 [2:20:25<3:01:22,  1.33it/s]
1|11388|Loss: 0.9008951783180237:  44%|████▍     | 11388/25880 [2:20:26<3:01:10,  1.33it/s]
1|11389|Loss: 1.0964241027832031:  44%|████▍     | 11388/25880 [2:20:26<3:01:10,  1.33it/s]
1|11389|Loss: 1.0964241027832031:  44%|████▍     | 11389/25880 [2:20:26<2:53:17,  1.39it/s]
1|11390|Loss: 0.7792774438858032:  44%|████▍     | 11389/25880 [2:20:27<2:53:17,  1.39it/s]
1|11390|Loss: 0.7792774438858032:  44%|████▍     | 11390/25880 [2:20:27<3:03:20,  1.32it/s]
1|11391|Loss: 0.8901903033256531:  44%|████▍     | 11390/25880 [2:20:28<3:03:20,  1.32it/s]
1|11391|Loss: 0.8901903033256531:  44%|████▍     | 11391/25880 [2:20:28<3:07:16,  1.29it/s]
1|11392|Loss: 0.7658548951148987:  44%|████▍     | 11391/25880 [2:20:29<3:07:16,  1.29it/s]
1|11392|Loss: 0.7658548951148987:  44%|████▍     | 11392/25880 [2:20:29<3:08:39,  1.28it/s]
1|11393|Loss: 0.8932584524154663:  44%|████▍     | 11392/25880 [2:20:29<3:08:39,  1.28it/s]
1|11393|Loss: 0.8932584524154663:  44%|████▍     | 11393/25880 [2:20:30<3:06:15,  1.30it/s]
1|11394|Loss: 1.1372737884521484:  44%|████▍     | 11393/25880 [2:20:30<3:06:15,  1.30it/s]
1|11394|Loss: 1.1372737884521484:  44%|████▍     | 11394/25880 [2:20:30<2:57:21,  1.36it/s]
1|11395|Loss: 0.7795643210411072:  44%|████▍     | 11394/25880 [2:20:31<2:57:21,  1.36it/s]
1|11395|Loss: 0.7795643210411072:  44%|████▍     | 11395/25880 [2:20:31<2:42:35,  1.48it/s]
1|11396|Loss: 0.7284021973609924:  44%|████▍     | 11395/25880 [2:20:31<2:42:35,  1.48it/s]
1|11396|Loss: 0.7284021973609924:  44%|████▍     | 11396/25880 [2:20:31<2:43:08,  1.48it/s]
1|11397|Loss: 0.6096899509429932:  44%|████▍     | 11396/25880 [2:20:32<2:43:08,  1.48it/s]
1|11397|Loss: 0.6096899509429932:  44%|████▍     | 11397/25880 [2:20:32<2:41:41,  1.49it/s]
1|11398|Loss: 0.7831451892852783:  44%|████▍     | 11397/25880 [2:20:33<2:41:41,  1.49it/s]
1|11398|Loss: 0.7831451892852783:  44%|████▍     | 11398/25880 [2:20:33<2:45:02,  1.46it/s]
1|11399|Loss: 0.9410706758499146:  44%|████▍     | 11398/25880 [2:20:33<2:45:02,  1.46it/s]
1|11399|Loss: 0.9410706758499146:  44%|████▍     | 11399/25880 [2:20:34<2:46:53,  1.45it/s]
1|11400|Loss: 0.8049063086509705:  44%|████▍     | 11399/25880 [2:20:34<2:46:53,  1.45it/s]
1|11400|Loss: 0.8049063086509705:  44%|████▍     | 11400/25880 [2:20:34<2:49:30,  1.42it/s]
1|11401|Loss: 0.9051695466041565:  44%|████▍     | 11400/25880 [2:20:35<2:49:30,  1.42it/s]
1|11401|Loss: 0.9051695466041565:  44%|████▍     | 11401/25880 [2:20:35<2:45:06,  1.46it/s]
1|11402|Loss: 0.8198635578155518:  44%|████▍     | 11401/25880 [2:20:35<2:45:06,  1.46it/s]
1|11402|Loss: 0.8198635578155518:  44%|████▍     | 11402/25880 [2:20:36<2:40:15,  1.51it/s]
1|11403|Loss: 0.8868824243545532:  44%|████▍     | 11402/25880 [2:20:36<2:40:15,  1.51it/s]
1|11403|Loss: 0.8868824243545532:  44%|████▍     | 11403/25880 [2:20:36<2:30:50,  1.60it/s]
1|11404|Loss: 0.9237478971481323:  44%|████▍     | 11403/25880 [2:20:36<2:30:50,  1.60it/s]
1|11404|Loss: 0.9237478971481323:  44%|████▍     | 11404/25880 [2:20:37<2:25:08,  1.66it/s]
1|11405|Loss: 0.7635532021522522:  44%|████▍     | 11404/25880 [2:20:37<2:25:08,  1.66it/s]
1|11405|Loss: 0.7635532021522522:  44%|████▍     | 11405/25880 [2:20:37<2:37:37,  1.53it/s]
1|11406|Loss: 0.8524397611618042:  44%|████▍     | 11405/25880 [2:20:38<2:37:37,  1.53it/s]
1|11406|Loss: 0.8524397611618042:  44%|████▍     | 11406/25880 [2:20:38<2:43:15,  1.48it/s]
1|11407|Loss: 0.8909499645233154:  44%|████▍     | 11406/25880 [2:20:39<2:43:15,  1.48it/s]
1|11407|Loss: 0.8909499645233154:  44%|████▍     | 11407/25880 [2:20:39<2:46:10,  1.45it/s]
1|11408|Loss: 0.8737410306930542:  44%|████▍     | 11407/25880 [2:20:39<2:46:10,  1.45it/s]
1|11408|Loss: 0.8737410306930542:  44%|████▍     | 11408/25880 [2:20:39<2:37:37,  1.53it/s]
1|11409|Loss: 0.825573205947876:  44%|████▍     | 11408/25880 [2:20:40<2:37:37,  1.53it/s] 
1|11409|Loss: 0.825573205947876:  44%|████▍     | 11409/25880 [2:20:40<2:31:24,  1.59it/s]
1|11410|Loss: 0.8107665777206421:  44%|████▍     | 11409/25880 [2:20:40<2:31:24,  1.59it/s]
1|11410|Loss: 0.8107665777206421:  44%|████▍     | 11410/25880 [2:20:41<2:31:32,  1.59it/s]
1|11411|Loss: 0.7173851132392883:  44%|████▍     | 11410/25880 [2:20:41<2:31:32,  1.59it/s]
1|11411|Loss: 0.7173851132392883:  44%|████▍     | 11411/25880 [2:20:42<2:56:01,  1.37it/s]
1|11412|Loss: 0.7881355881690979:  44%|████▍     | 11411/25880 [2:20:42<2:56:01,  1.37it/s]
1|11412|Loss: 0.7881355881690979:  44%|████▍     | 11412/25880 [2:20:42<3:07:36,  1.29it/s]
1|11413|Loss: 0.8557651042938232:  44%|████▍     | 11412/25880 [2:20:43<3:07:36,  1.29it/s]
1|11413|Loss: 0.8557651042938232:  44%|████▍     | 11413/25880 [2:20:43<3:06:07,  1.30it/s]
1|11414|Loss: 0.8676467537879944:  44%|████▍     | 11413/25880 [2:20:44<3:06:07,  1.30it/s]
1|11414|Loss: 0.8676467537879944:  44%|████▍     | 11414/25880 [2:20:44<3:10:05,  1.27it/s]
1|11415|Loss: 0.9366703629493713:  44%|████▍     | 11414/25880 [2:20:44<3:10:05,  1.27it/s]
1|11415|Loss: 0.9366703629493713:  44%|████▍     | 11415/25880 [2:20:45<3:06:09,  1.30it/s]
1|11416|Loss: 0.8130229115486145:  44%|████▍     | 11415/25880 [2:20:45<3:06:09,  1.30it/s]
1|11416|Loss: 0.8130229115486145:  44%|████▍     | 11416/25880 [2:20:46<3:08:11,  1.28it/s]
1|11417|Loss: 0.8725830316543579:  44%|████▍     | 11416/25880 [2:20:46<3:08:11,  1.28it/s]
1|11417|Loss: 0.8725830316543579:  44%|████▍     | 11417/25880 [2:20:46<3:10:12,  1.27it/s]
1|11418|Loss: 0.8809961080551147:  44%|████▍     | 11417/25880 [2:20:47<3:10:12,  1.27it/s]
1|11418|Loss: 0.8809961080551147:  44%|████▍     | 11418/25880 [2:20:47<3:06:30,  1.29it/s]
1|11419|Loss: 0.7259112000465393:  44%|████▍     | 11418/25880 [2:20:48<3:06:30,  1.29it/s]
1|11419|Loss: 0.7259112000465393:  44%|████▍     | 11419/25880 [2:20:48<3:11:15,  1.26it/s]
1|11420|Loss: 0.7427485585212708:  44%|████▍     | 11419/25880 [2:20:48<3:11:15,  1.26it/s]
1|11420|Loss: 0.7427485585212708:  44%|████▍     | 11420/25880 [2:20:49<3:10:00,  1.27it/s]
1|11421|Loss: 0.7766419649124146:  44%|████▍     | 11420/25880 [2:20:49<3:10:00,  1.27it/s]
1|11421|Loss: 0.7766419649124146:  44%|████▍     | 11421/25880 [2:20:49<2:53:33,  1.39it/s]
1|11422|Loss: 0.8965809345245361:  44%|████▍     | 11421/25880 [2:20:50<2:53:33,  1.39it/s]
1|11422|Loss: 0.8965809345245361:  44%|████▍     | 11422/25880 [2:20:50<2:56:27,  1.37it/s]
1|11423|Loss: 0.8161773681640625:  44%|████▍     | 11422/25880 [2:20:51<2:56:27,  1.37it/s]
1|11423|Loss: 0.8161773681640625:  44%|████▍     | 11423/25880 [2:20:51<2:58:01,  1.35it/s]
1|11424|Loss: 0.9497637152671814:  44%|████▍     | 11423/25880 [2:20:51<2:58:01,  1.35it/s]
1|11424|Loss: 0.9497637152671814:  44%|████▍     | 11424/25880 [2:20:51<2:41:05,  1.50it/s]
1|11425|Loss: 0.7647930383682251:  44%|████▍     | 11424/25880 [2:20:52<2:41:05,  1.50it/s]
1|11425|Loss: 0.7647930383682251:  44%|████▍     | 11425/25880 [2:20:52<2:40:49,  1.50it/s]
1|11426|Loss: 0.7457583546638489:  44%|████▍     | 11425/25880 [2:20:52<2:40:49,  1.50it/s]
1|11426|Loss: 0.7457583546638489:  44%|████▍     | 11426/25880 [2:20:53<2:54:30,  1.38it/s]
1|11427|Loss: 0.9033392667770386:  44%|████▍     | 11426/25880 [2:20:53<2:54:30,  1.38it/s]
1|11427|Loss: 0.9033392667770386:  44%|████▍     | 11427/25880 [2:20:54<3:05:57,  1.30it/s]
1|11428|Loss: 0.7838922739028931:  44%|████▍     | 11427/25880 [2:20:54<3:05:57,  1.30it/s]
1|11428|Loss: 0.7838922739028931:  44%|████▍     | 11428/25880 [2:20:55<3:05:45,  1.30it/s]
1|11429|Loss: 0.7602261304855347:  44%|████▍     | 11428/25880 [2:20:55<3:05:45,  1.30it/s]
1|11429|Loss: 0.7602261304855347:  44%|████▍     | 11429/25880 [2:20:55<3:08:18,  1.28it/s]
1|11430|Loss: 0.8149895071983337:  44%|████▍     | 11429/25880 [2:20:56<3:08:18,  1.28it/s]
1|11430|Loss: 0.8149895071983337:  44%|████▍     | 11430/25880 [2:20:56<3:16:20,  1.23it/s]
1|11431|Loss: 0.787812352180481:  44%|████▍     | 11430/25880 [2:20:57<3:16:20,  1.23it/s] 
1|11431|Loss: 0.787812352180481:  44%|████▍     | 11431/25880 [2:20:57<3:13:30,  1.24it/s]
1|11432|Loss: 0.8044632077217102:  44%|████▍     | 11431/25880 [2:20:57<3:13:30,  1.24it/s]
1|11432|Loss: 0.8044632077217102:  44%|████▍     | 11432/25880 [2:20:58<3:17:34,  1.22it/s]
1|11433|Loss: 0.864658534526825:  44%|████▍     | 11432/25880 [2:20:58<3:17:34,  1.22it/s] 
1|11433|Loss: 0.864658534526825:  44%|████▍     | 11433/25880 [2:20:59<3:13:21,  1.25it/s]
1|11434|Loss: 0.888375997543335:  44%|████▍     | 11433/25880 [2:20:59<3:13:21,  1.25it/s]
1|11434|Loss: 0.888375997543335:  44%|████▍     | 11434/25880 [2:20:59<2:59:20,  1.34it/s]
1|11435|Loss: 0.8434836864471436:  44%|████▍     | 11434/25880 [2:21:00<2:59:20,  1.34it/s]
1|11435|Loss: 0.8434836864471436:  44%|████▍     | 11435/25880 [2:21:00<2:54:36,  1.38it/s]
1|11436|Loss: 0.8711922764778137:  44%|████▍     | 11435/25880 [2:21:00<2:54:36,  1.38it/s]
1|11436|Loss: 0.8711922764778137:  44%|████▍     | 11436/25880 [2:21:01<2:49:04,  1.42it/s]
1|11437|Loss: 0.8091259002685547:  44%|████▍     | 11436/25880 [2:21:01<2:49:04,  1.42it/s]
1|11437|Loss: 0.8091259002685547:  44%|████▍     | 11437/25880 [2:21:01<2:39:34,  1.51it/s]
1|11438|Loss: 0.7622251510620117:  44%|████▍     | 11437/25880 [2:21:01<2:39:34,  1.51it/s]
1|11438|Loss: 0.7622251510620117:  44%|████▍     | 11438/25880 [2:21:02<2:39:56,  1.50it/s]
1|11439|Loss: 0.8073130249977112:  44%|████▍     | 11438/25880 [2:21:02<2:39:56,  1.50it/s]
1|11439|Loss: 0.8073130249977112:  44%|████▍     | 11439/25880 [2:21:03<2:44:19,  1.46it/s]
1|11440|Loss: 0.7925222516059875:  44%|████▍     | 11439/25880 [2:21:03<2:44:19,  1.46it/s]
1|11440|Loss: 0.7925222516059875:  44%|████▍     | 11440/25880 [2:21:03<2:45:38,  1.45it/s]
1|11441|Loss: 0.7817528247833252:  44%|████▍     | 11440/25880 [2:21:04<2:45:38,  1.45it/s]
1|11441|Loss: 0.7817528247833252:  44%|████▍     | 11441/25880 [2:21:04<2:35:03,  1.55it/s]
1|11442|Loss: 0.8689380884170532:  44%|████▍     | 11441/25880 [2:21:04<2:35:03,  1.55it/s]
1|11442|Loss: 0.8689380884170532:  44%|████▍     | 11442/25880 [2:21:04<2:32:52,  1.57it/s]
1|11443|Loss: 0.8604190945625305:  44%|████▍     | 11442/25880 [2:21:05<2:32:52,  1.57it/s]
1|11443|Loss: 0.8604190945625305:  44%|████▍     | 11443/25880 [2:21:05<2:45:49,  1.45it/s]
1|11444|Loss: 0.7175706028938293:  44%|████▍     | 11443/25880 [2:21:06<2:45:49,  1.45it/s]
1|11444|Loss: 0.7175706028938293:  44%|████▍     | 11444/25880 [2:21:06<2:57:49,  1.35it/s]
1|11445|Loss: 0.8142691254615784:  44%|████▍     | 11444/25880 [2:21:06<2:57:49,  1.35it/s]
1|11445|Loss: 0.8142691254615784:  44%|████▍     | 11445/25880 [2:21:07<2:57:33,  1.35it/s]
1|11446|Loss: 1.0786285400390625:  44%|████▍     | 11445/25880 [2:21:07<2:57:33,  1.35it/s]
1|11446|Loss: 1.0786285400390625:  44%|████▍     | 11446/25880 [2:21:08<3:02:41,  1.32it/s]
1|11447|Loss: 0.8511397838592529:  44%|████▍     | 11446/25880 [2:21:08<3:02:41,  1.32it/s]
1|11447|Loss: 0.8511397838592529:  44%|████▍     | 11447/25880 [2:21:08<3:02:29,  1.32it/s]
1|11448|Loss: 0.7391315698623657:  44%|████▍     | 11447/25880 [2:21:09<3:02:29,  1.32it/s]
1|11448|Loss: 0.7391315698623657:  44%|████▍     | 11448/25880 [2:21:09<2:47:37,  1.43it/s]
1|11449|Loss: 0.8765519261360168:  44%|████▍     | 11448/25880 [2:21:09<2:47:37,  1.43it/s]
1|11449|Loss: 0.8765519261360168:  44%|████▍     | 11449/25880 [2:21:10<2:40:17,  1.50it/s]
1|11450|Loss: 0.788817286491394:  44%|████▍     | 11449/25880 [2:21:10<2:40:17,  1.50it/s] 
1|11450|Loss: 0.788817286491394:  44%|████▍     | 11450/25880 [2:21:10<2:43:14,  1.47it/s]
1|11451|Loss: 0.816602349281311:  44%|████▍     | 11450/25880 [2:21:11<2:43:14,  1.47it/s]
1|11451|Loss: 0.816602349281311:  44%|████▍     | 11451/25880 [2:21:11<2:47:21,  1.44it/s]
1|11452|Loss: 0.7940214276313782:  44%|████▍     | 11451/25880 [2:21:11<2:47:21,  1.44it/s]
1|11452|Loss: 0.7940214276313782:  44%|████▍     | 11452/25880 [2:21:12<2:48:37,  1.43it/s]
1|11453|Loss: 0.7759236693382263:  44%|████▍     | 11452/25880 [2:21:12<2:48:37,  1.43it/s]
1|11453|Loss: 0.7759236693382263:  44%|████▍     | 11453/25880 [2:21:13<2:58:46,  1.34it/s]
1|11454|Loss: 0.876741886138916:  44%|████▍     | 11453/25880 [2:21:13<2:58:46,  1.34it/s] 
1|11454|Loss: 0.876741886138916:  44%|████▍     | 11454/25880 [2:21:13<3:06:45,  1.29it/s]
1|11455|Loss: 0.7728971838951111:  44%|████▍     | 11454/25880 [2:21:14<3:06:45,  1.29it/s]
1|11455|Loss: 0.7728971838951111:  44%|████▍     | 11455/25880 [2:21:14<3:11:48,  1.25it/s]
1|11456|Loss: 0.7458683252334595:  44%|████▍     | 11455/25880 [2:21:15<3:11:48,  1.25it/s]
1|11456|Loss: 0.7458683252334595:  44%|████▍     | 11456/25880 [2:21:15<3:08:54,  1.27it/s]
1|11457|Loss: 0.8221726417541504:  44%|████▍     | 11456/25880 [2:21:15<3:08:54,  1.27it/s]
1|11457|Loss: 0.8221726417541504:  44%|████▍     | 11457/25880 [2:21:16<3:03:12,  1.31it/s]
1|11458|Loss: 0.8212316632270813:  44%|████▍     | 11457/25880 [2:21:16<3:03:12,  1.31it/s]
1|11458|Loss: 0.8212316632270813:  44%|████▍     | 11458/25880 [2:21:16<3:03:33,  1.31it/s]
1|11459|Loss: 0.8419759273529053:  44%|████▍     | 11458/25880 [2:21:17<3:03:33,  1.31it/s]
1|11459|Loss: 0.8419759273529053:  44%|████▍     | 11459/25880 [2:21:17<3:00:50,  1.33it/s]
1|11460|Loss: 0.8771464824676514:  44%|████▍     | 11459/25880 [2:21:18<3:00:50,  1.33it/s]
1|11460|Loss: 0.8771464824676514:  44%|████▍     | 11460/25880 [2:21:18<2:58:32,  1.35it/s]
1|11461|Loss: 0.9053385257720947:  44%|████▍     | 11460/25880 [2:21:18<2:58:32,  1.35it/s]
1|11461|Loss: 0.9053385257720947:  44%|████▍     | 11461/25880 [2:21:19<2:50:56,  1.41it/s]
1|11462|Loss: 0.8093828558921814:  44%|████▍     | 11461/25880 [2:21:19<2:50:56,  1.41it/s]
1|11462|Loss: 0.8093828558921814:  44%|████▍     | 11462/25880 [2:21:19<2:56:11,  1.36it/s]
1|11463|Loss: 0.8971422910690308:  44%|████▍     | 11462/25880 [2:21:20<2:56:11,  1.36it/s]
1|11463|Loss: 0.8971422910690308:  44%|████▍     | 11463/25880 [2:21:20<3:08:14,  1.28it/s]
1|11464|Loss: 0.8827930092811584:  44%|████▍     | 11463/25880 [2:21:21<3:08:14,  1.28it/s]
1|11464|Loss: 0.8827930092811584:  44%|████▍     | 11464/25880 [2:21:21<3:11:36,  1.25it/s]
1|11465|Loss: 0.9813087582588196:  44%|████▍     | 11464/25880 [2:21:21<3:11:36,  1.25it/s]
1|11465|Loss: 0.9813087582588196:  44%|████▍     | 11465/25880 [2:21:22<3:02:44,  1.31it/s]
1|11466|Loss: 0.8938084840774536:  44%|████▍     | 11465/25880 [2:21:22<3:02:44,  1.31it/s]
1|11466|Loss: 0.8938084840774536:  44%|████▍     | 11466/25880 [2:21:22<2:54:19,  1.38it/s]
1|11467|Loss: 0.5940343737602234:  44%|████▍     | 11466/25880 [2:21:23<2:54:19,  1.38it/s]
1|11467|Loss: 0.5940343737602234:  44%|████▍     | 11467/25880 [2:21:23<2:53:28,  1.38it/s]
1|11468|Loss: 0.8027198910713196:  44%|████▍     | 11467/25880 [2:21:23<2:53:28,  1.38it/s]
1|11468|Loss: 0.8027198910713196:  44%|████▍     | 11468/25880 [2:21:24<2:52:32,  1.39it/s]
1|11469|Loss: 0.8048629760742188:  44%|████▍     | 11468/25880 [2:21:24<2:52:32,  1.39it/s]
1|11469|Loss: 0.8048629760742188:  44%|████▍     | 11469/25880 [2:21:25<3:04:08,  1.30it/s]
1|11470|Loss: 0.847130537033081:  44%|████▍     | 11469/25880 [2:21:25<3:04:08,  1.30it/s] 
1|11470|Loss: 0.847130537033081:  44%|████▍     | 11470/25880 [2:21:25<3:04:53,  1.30it/s]
1|11471|Loss: 0.8511117696762085:  44%|████▍     | 11470/25880 [2:21:26<3:04:53,  1.30it/s]
1|11471|Loss: 0.8511117696762085:  44%|████▍     | 11471/25880 [2:21:26<3:02:20,  1.32it/s]
1|11472|Loss: 0.8476845026016235:  44%|████▍     | 11471/25880 [2:21:27<3:02:20,  1.32it/s]
1|11472|Loss: 0.8476845026016235:  44%|████▍     | 11472/25880 [2:21:27<2:53:47,  1.38it/s]
1|11473|Loss: 0.7021828889846802:  44%|████▍     | 11472/25880 [2:21:27<2:53:47,  1.38it/s]
1|11473|Loss: 0.7021828889846802:  44%|████▍     | 11473/25880 [2:21:28<3:06:00,  1.29it/s]
1|11474|Loss: 0.7148178219795227:  44%|████▍     | 11473/25880 [2:21:28<3:06:00,  1.29it/s]
1|11474|Loss: 0.7148178219795227:  44%|████▍     | 11474/25880 [2:21:28<2:59:14,  1.34it/s]
1|11475|Loss: 0.904080331325531:  44%|████▍     | 11474/25880 [2:21:29<2:59:14,  1.34it/s] 
1|11475|Loss: 0.904080331325531:  44%|████▍     | 11475/25880 [2:21:29<3:04:32,  1.30it/s]
1|11476|Loss: 0.9091399312019348:  44%|████▍     | 11475/25880 [2:21:30<3:04:32,  1.30it/s]
1|11476|Loss: 0.9091399312019348:  44%|████▍     | 11476/25880 [2:21:30<3:17:50,  1.21it/s]
1|11477|Loss: 0.7098180651664734:  44%|████▍     | 11476/25880 [2:21:31<3:17:50,  1.21it/s]
1|11477|Loss: 0.7098180651664734:  44%|████▍     | 11477/25880 [2:21:31<3:20:44,  1.20it/s]
1|11478|Loss: 0.7494468092918396:  44%|████▍     | 11477/25880 [2:21:31<3:20:44,  1.20it/s]
1|11478|Loss: 0.7494468092918396:  44%|████▍     | 11478/25880 [2:21:32<3:25:10,  1.17it/s]
1|11479|Loss: 0.7382997274398804:  44%|████▍     | 11478/25880 [2:21:32<3:25:10,  1.17it/s]
1|11479|Loss: 0.7382997274398804:  44%|████▍     | 11479/25880 [2:21:33<3:17:05,  1.22it/s]
1|11480|Loss: 0.9328978061676025:  44%|████▍     | 11479/25880 [2:21:33<3:17:05,  1.22it/s]
1|11480|Loss: 0.9328978061676025:  44%|████▍     | 11480/25880 [2:21:33<3:10:23,  1.26it/s]
1|11481|Loss: 0.8409704566001892:  44%|████▍     | 11480/25880 [2:21:34<3:10:23,  1.26it/s]
1|11481|Loss: 0.8409704566001892:  44%|████▍     | 11481/25880 [2:21:34<3:11:48,  1.25it/s]
1|11482|Loss: 0.8788820505142212:  44%|████▍     | 11481/25880 [2:21:35<3:11:48,  1.25it/s]
1|11482|Loss: 0.8788820505142212:  44%|████▍     | 11482/25880 [2:21:35<3:08:35,  1.27it/s]
1|11483|Loss: 0.8217670321464539:  44%|████▍     | 11482/25880 [2:21:35<3:08:35,  1.27it/s]
1|11483|Loss: 0.8217670321464539:  44%|████▍     | 11483/25880 [2:21:36<3:03:20,  1.31it/s]
1|11484|Loss: 0.9109366536140442:  44%|████▍     | 11483/25880 [2:21:36<3:03:20,  1.31it/s]
1|11484|Loss: 0.9109366536140442:  44%|████▍     | 11484/25880 [2:21:36<3:04:23,  1.30it/s]
1|11485|Loss: 0.9315732717514038:  44%|████▍     | 11484/25880 [2:21:37<3:04:23,  1.30it/s]
1|11485|Loss: 0.9315732717514038:  44%|████▍     | 11485/25880 [2:21:37<3:08:15,  1.27it/s]
1|11486|Loss: 1.0313637256622314:  44%|████▍     | 11485/25880 [2:21:38<3:08:15,  1.27it/s]
1|11486|Loss: 1.0313637256622314:  44%|████▍     | 11486/25880 [2:21:38<3:06:28,  1.29it/s]
1|11487|Loss: 0.8425742387771606:  44%|████▍     | 11486/25880 [2:21:38<3:06:28,  1.29it/s]
1|11487|Loss: 0.8425742387771606:  44%|████▍     | 11487/25880 [2:21:39<3:07:25,  1.28it/s]
1|11488|Loss: 0.8176111578941345:  44%|████▍     | 11487/25880 [2:21:39<3:07:25,  1.28it/s]
1|11488|Loss: 0.8176111578941345:  44%|████▍     | 11488/25880 [2:21:40<3:03:08,  1.31it/s]
1|11489|Loss: 0.7157818675041199:  44%|████▍     | 11488/25880 [2:21:40<3:03:08,  1.31it/s]
1|11489|Loss: 0.7157818675041199:  44%|████▍     | 11489/25880 [2:21:40<3:06:14,  1.29it/s]
1|11490|Loss: 0.7407705783843994:  44%|████▍     | 11489/25880 [2:21:41<3:06:14,  1.29it/s]
1|11490|Loss: 0.7407705783843994:  44%|████▍     | 11490/25880 [2:21:41<3:19:12,  1.20it/s]
1|11491|Loss: 0.7832919955253601:  44%|████▍     | 11490/25880 [2:21:42<3:19:12,  1.20it/s]
1|11491|Loss: 0.7832919955253601:  44%|████▍     | 11491/25880 [2:21:42<3:25:35,  1.17it/s]
1|11492|Loss: 0.8570152521133423:  44%|████▍     | 11491/25880 [2:21:43<3:25:35,  1.17it/s]
1|11492|Loss: 0.8570152521133423:  44%|████▍     | 11492/25880 [2:21:43<3:17:13,  1.22it/s]
1|11493|Loss: 0.789413332939148:  44%|████▍     | 11492/25880 [2:21:43<3:17:13,  1.22it/s] 
1|11493|Loss: 0.789413332939148:  44%|████▍     | 11493/25880 [2:21:44<3:13:01,  1.24it/s]
1|11494|Loss: 0.773036539554596:  44%|████▍     | 11493/25880 [2:21:44<3:13:01,  1.24it/s]
1|11494|Loss: 0.773036539554596:  44%|████▍     | 11494/25880 [2:21:45<3:12:21,  1.25it/s]
1|11495|Loss: 0.8774584531784058:  44%|████▍     | 11494/25880 [2:21:45<3:12:21,  1.25it/s]
1|11495|Loss: 0.8774584531784058:  44%|████▍     | 11495/25880 [2:21:45<3:02:09,  1.32it/s]
1|11496|Loss: 0.7643625140190125:  44%|████▍     | 11495/25880 [2:21:46<3:02:09,  1.32it/s]
1|11496|Loss: 0.7643625140190125:  44%|████▍     | 11496/25880 [2:21:46<3:30:33,  1.14it/s]
1|11497|Loss: 0.8945243954658508:  44%|████▍     | 11496/25880 [2:21:47<3:30:33,  1.14it/s]
1|11497|Loss: 0.8945243954658508:  44%|████▍     | 11497/25880 [2:21:47<3:32:57,  1.13it/s]
1|11498|Loss: 0.8665395379066467:  44%|████▍     | 11497/25880 [2:21:48<3:32:57,  1.13it/s]
1|11498|Loss: 0.8665395379066467:  44%|████▍     | 11498/25880 [2:21:48<3:22:47,  1.18it/s]
1|11499|Loss: 0.7672159671783447:  44%|████▍     | 11498/25880 [2:21:48<3:22:47,  1.18it/s]
1|11499|Loss: 0.7672159671783447:  44%|████▍     | 11499/25880 [2:21:49<3:12:52,  1.24it/s]
1|11500|Loss: 0.8144574165344238:  44%|████▍     | 11499/25880 [2:21:49<3:12:52,  1.24it/s]
1|11500|Loss: 0.8144574165344238:  44%|████▍     | 11500/25880 [2:21:49<2:52:35,  1.39it/s]
1|11501|Loss: 0.751429557800293:  44%|████▍     | 11500/25880 [2:21:50<2:52:35,  1.39it/s] 
1|11501|Loss: 0.751429557800293:  44%|████▍     | 11501/25880 [2:21:50<2:35:30,  1.54it/s]
1|11502|Loss: 0.8821439146995544:  44%|████▍     | 11501/25880 [2:21:50<2:35:30,  1.54it/s]
1|11502|Loss: 0.8821439146995544:  44%|████▍     | 11502/25880 [2:21:50<2:32:17,  1.57it/s]
1|11503|Loss: 0.9210402369499207:  44%|████▍     | 11502/25880 [2:21:51<2:32:17,  1.57it/s]
1|11503|Loss: 0.9210402369499207:  44%|████▍     | 11503/25880 [2:21:51<2:46:05,  1.44it/s]
1|11504|Loss: 0.8110454678535461:  44%|████▍     | 11503/25880 [2:21:52<2:46:05,  1.44it/s]
1|11504|Loss: 0.8110454678535461:  44%|████▍     | 11504/25880 [2:21:52<3:02:05,  1.32it/s]
1|11505|Loss: 0.7395180463790894:  44%|████▍     | 11504/25880 [2:21:52<3:02:05,  1.32it/s]
1|11505|Loss: 0.7395180463790894:  44%|████▍     | 11505/25880 [2:21:53<2:52:18,  1.39it/s]
1|11506|Loss: 0.7434489727020264:  44%|████▍     | 11505/25880 [2:21:53<2:52:18,  1.39it/s]
1|11506|Loss: 0.7434489727020264:  44%|████▍     | 11506/25880 [2:21:53<2:45:14,  1.45it/s]
1|11507|Loss: 0.9373265504837036:  44%|████▍     | 11506/25880 [2:21:54<2:45:14,  1.45it/s]
1|11507|Loss: 0.9373265504837036:  44%|████▍     | 11507/25880 [2:21:54<2:51:00,  1.40it/s]
1|11508|Loss: 0.9397122859954834:  44%|████▍     | 11507/25880 [2:21:55<2:51:00,  1.40it/s]
1|11508|Loss: 0.9397122859954834:  44%|████▍     | 11508/25880 [2:21:55<2:53:52,  1.38it/s]
1|11509|Loss: 1.0481590032577515:  44%|████▍     | 11508/25880 [2:21:55<2:53:52,  1.38it/s]
1|11509|Loss: 1.0481590032577515:  44%|████▍     | 11509/25880 [2:21:56<3:00:11,  1.33it/s]
1|11510|Loss: 0.7260000109672546:  44%|████▍     | 11509/25880 [2:21:56<3:00:11,  1.33it/s]
1|11510|Loss: 0.7260000109672546:  44%|████▍     | 11510/25880 [2:21:56<2:54:49,  1.37it/s]
1|11511|Loss: 0.9723341464996338:  44%|████▍     | 11510/25880 [2:21:57<2:54:49,  1.37it/s]
1|11511|Loss: 0.9723341464996338:  44%|████▍     | 11511/25880 [2:21:57<2:52:06,  1.39it/s]
1|11512|Loss: 0.9048514366149902:  44%|████▍     | 11511/25880 [2:21:57<2:52:06,  1.39it/s]
1|11512|Loss: 0.9048514366149902:  44%|████▍     | 11512/25880 [2:21:58<2:58:05,  1.34it/s]
1|11513|Loss: 0.705645740032196:  44%|████▍     | 11512/25880 [2:21:58<2:58:05,  1.34it/s] 
1|11513|Loss: 0.705645740032196:  44%|████▍     | 11513/25880 [2:21:58<2:53:11,  1.38it/s]
1|11514|Loss: 0.9144954085350037:  44%|████▍     | 11513/25880 [2:21:59<2:53:11,  1.38it/s]
1|11514|Loss: 0.9144954085350037:  44%|████▍     | 11514/25880 [2:21:59<2:53:18,  1.38it/s]
1|11515|Loss: 0.7526477575302124:  44%|████▍     | 11514/25880 [2:22:00<2:53:18,  1.38it/s]
1|11515|Loss: 0.7526477575302124:  44%|████▍     | 11515/25880 [2:22:00<2:49:12,  1.41it/s]
1|11516|Loss: 0.9989590644836426:  44%|████▍     | 11515/25880 [2:22:00<2:49:12,  1.41it/s]
1|11516|Loss: 0.9989590644836426:  44%|████▍     | 11516/25880 [2:22:01<2:49:32,  1.41it/s]
1|11517|Loss: 0.9101728796958923:  44%|████▍     | 11516/25880 [2:22:01<2:49:32,  1.41it/s]
1|11517|Loss: 0.9101728796958923:  45%|████▍     | 11517/25880 [2:22:01<3:01:40,  1.32it/s]
1|11518|Loss: 0.7566154599189758:  45%|████▍     | 11517/25880 [2:22:02<3:01:40,  1.32it/s]
1|11518|Loss: 0.7566154599189758:  45%|████▍     | 11518/25880 [2:22:02<2:54:11,  1.37it/s]
1|11519|Loss: 0.706468939781189:  45%|████▍     | 11518/25880 [2:22:03<2:54:11,  1.37it/s] 
1|11519|Loss: 0.706468939781189:  45%|████▍     | 11519/25880 [2:22:03<2:59:12,  1.34it/s]
1|11520|Loss: 0.8569117188453674:  45%|████▍     | 11519/25880 [2:22:03<2:59:12,  1.34it/s]
1|11520|Loss: 0.8569117188453674:  45%|████▍     | 11520/25880 [2:22:04<3:00:16,  1.33it/s]
1|11521|Loss: 0.8984282612800598:  45%|████▍     | 11520/25880 [2:22:04<3:00:16,  1.33it/s]
1|11521|Loss: 0.8984282612800598:  45%|████▍     | 11521/25880 [2:22:05<3:07:12,  1.28it/s]
1|11522|Loss: 0.83137047290802:  45%|████▍     | 11521/25880 [2:22:05<3:07:12,  1.28it/s]  
1|11522|Loss: 0.83137047290802:  45%|████▍     | 11522/25880 [2:22:05<2:55:42,  1.36it/s]
1|11523|Loss: 0.8194589614868164:  45%|████▍     | 11522/25880 [2:22:06<2:55:42,  1.36it/s]
1|11523|Loss: 0.8194589614868164:  45%|████▍     | 11523/25880 [2:22:06<2:52:22,  1.39it/s]
1|11524|Loss: 0.8975804448127747:  45%|████▍     | 11523/25880 [2:22:06<2:52:22,  1.39it/s]
1|11524|Loss: 0.8975804448127747:  45%|████▍     | 11524/25880 [2:22:06<2:46:35,  1.44it/s]
1|11525|Loss: 0.7837730646133423:  45%|████▍     | 11524/25880 [2:22:07<2:46:35,  1.44it/s]
1|11525|Loss: 0.7837730646133423:  45%|████▍     | 11525/25880 [2:22:07<2:36:02,  1.53it/s]
1|11526|Loss: 0.9676791429519653:  45%|████▍     | 11525/25880 [2:22:07<2:36:02,  1.53it/s]
1|11526|Loss: 0.9676791429519653:  45%|████▍     | 11526/25880 [2:22:08<2:44:13,  1.46it/s]
1|11527|Loss: 0.8455055356025696:  45%|████▍     | 11526/25880 [2:22:08<2:44:13,  1.46it/s]
1|11527|Loss: 0.8455055356025696:  45%|████▍     | 11527/25880 [2:22:09<2:49:18,  1.41it/s]
1|11528|Loss: 0.871937096118927:  45%|████▍     | 11527/25880 [2:22:09<2:49:18,  1.41it/s] 
1|11528|Loss: 0.871937096118927:  45%|████▍     | 11528/25880 [2:22:09<2:46:00,  1.44it/s]
1|11529|Loss: 0.8145565390586853:  45%|████▍     | 11528/25880 [2:22:10<2:46:00,  1.44it/s]
1|11529|Loss: 0.8145565390586853:  45%|████▍     | 11529/25880 [2:22:10<2:53:08,  1.38it/s]
1|11530|Loss: 0.9616247415542603:  45%|████▍     | 11529/25880 [2:22:10<2:53:08,  1.38it/s]
1|11530|Loss: 0.9616247415542603:  45%|████▍     | 11530/25880 [2:22:11<2:46:20,  1.44it/s]
1|11531|Loss: 0.845441997051239:  45%|████▍     | 11530/25880 [2:22:11<2:46:20,  1.44it/s] 
1|11531|Loss: 0.845441997051239:  45%|████▍     | 11531/25880 [2:22:11<2:47:09,  1.43it/s]
1|11532|Loss: 0.9955147504806519:  45%|████▍     | 11531/25880 [2:22:12<2:47:09,  1.43it/s]
1|11532|Loss: 0.9955147504806519:  45%|████▍     | 11532/25880 [2:22:12<2:52:53,  1.38it/s]
1|11533|Loss: 0.8572005033493042:  45%|████▍     | 11532/25880 [2:22:13<2:52:53,  1.38it/s]
1|11533|Loss: 0.8572005033493042:  45%|████▍     | 11533/25880 [2:22:13<3:01:28,  1.32it/s]
1|11534|Loss: 0.8017051815986633:  45%|████▍     | 11533/25880 [2:22:13<3:01:28,  1.32it/s]
1|11534|Loss: 0.8017051815986633:  45%|████▍     | 11534/25880 [2:22:14<2:56:40,  1.35it/s]
1|11535|Loss: 0.8952891230583191:  45%|████▍     | 11534/25880 [2:22:14<2:56:40,  1.35it/s]
1|11535|Loss: 0.8952891230583191:  45%|████▍     | 11535/25880 [2:22:14<2:59:22,  1.33it/s]
1|11536|Loss: 0.9224058389663696:  45%|████▍     | 11535/25880 [2:22:15<2:59:22,  1.33it/s]
1|11536|Loss: 0.9224058389663696:  45%|████▍     | 11536/25880 [2:22:15<3:07:53,  1.27it/s]
1|11537|Loss: 0.8539704084396362:  45%|████▍     | 11536/25880 [2:22:16<3:07:53,  1.27it/s]
1|11537|Loss: 0.8539704084396362:  45%|████▍     | 11537/25880 [2:22:16<2:53:47,  1.38it/s]
1|11538|Loss: 0.6776471138000488:  45%|████▍     | 11537/25880 [2:22:16<2:53:47,  1.38it/s]
1|11538|Loss: 0.6776471138000488:  45%|████▍     | 11538/25880 [2:22:16<2:40:34,  1.49it/s]
1|11539|Loss: 0.7987003922462463:  45%|████▍     | 11538/25880 [2:22:17<2:40:34,  1.49it/s]
1|11539|Loss: 0.7987003922462463:  45%|████▍     | 11539/25880 [2:22:17<2:47:56,  1.42it/s]
1|11540|Loss: 0.8687474727630615:  45%|████▍     | 11539/25880 [2:22:18<2:47:56,  1.42it/s]
1|11540|Loss: 0.8687474727630615:  45%|████▍     | 11540/25880 [2:22:18<2:55:22,  1.36it/s]
1|11541|Loss: 0.892577052116394:  45%|████▍     | 11540/25880 [2:22:18<2:55:22,  1.36it/s] 
1|11541|Loss: 0.892577052116394:  45%|████▍     | 11541/25880 [2:22:19<2:49:21,  1.41it/s]
1|11542|Loss: 0.8815925717353821:  45%|████▍     | 11541/25880 [2:22:19<2:49:21,  1.41it/s]
1|11542|Loss: 0.8815925717353821:  45%|████▍     | 11542/25880 [2:22:19<2:43:43,  1.46it/s]
1|11543|Loss: 0.7457274794578552:  45%|████▍     | 11542/25880 [2:22:20<2:43:43,  1.46it/s]
1|11543|Loss: 0.7457274794578552:  45%|████▍     | 11543/25880 [2:22:20<2:45:47,  1.44it/s]
1|11544|Loss: 0.671225368976593:  45%|████▍     | 11543/25880 [2:22:20<2:45:47,  1.44it/s] 
1|11544|Loss: 0.671225368976593:  45%|████▍     | 11544/25880 [2:22:21<2:42:11,  1.47it/s]
1|11545|Loss: 0.849948525428772:  45%|████▍     | 11544/25880 [2:22:21<2:42:11,  1.47it/s]
1|11545|Loss: 0.849948525428772:  45%|████▍     | 11545/25880 [2:22:21<2:44:08,  1.46it/s]
1|11546|Loss: 0.775398313999176:  45%|████▍     | 11545/25880 [2:22:22<2:44:08,  1.46it/s]
1|11546|Loss: 0.775398313999176:  45%|████▍     | 11546/25880 [2:22:22<2:41:47,  1.48it/s]
1|11547|Loss: 0.8186079859733582:  45%|████▍     | 11546/25880 [2:22:22<2:41:47,  1.48it/s]
1|11547|Loss: 0.8186079859733582:  45%|████▍     | 11547/25880 [2:22:23<2:52:36,  1.38it/s]
1|11548|Loss: 0.8234685659408569:  45%|████▍     | 11547/25880 [2:22:23<2:52:36,  1.38it/s]
1|11548|Loss: 0.8234685659408569:  45%|████▍     | 11548/25880 [2:22:24<3:03:27,  1.30it/s]
1|11549|Loss: 0.7160080075263977:  45%|████▍     | 11548/25880 [2:22:24<3:03:27,  1.30it/s]
1|11549|Loss: 0.7160080075263977:  45%|████▍     | 11549/25880 [2:22:25<3:03:05,  1.30it/s]
1|11550|Loss: 0.7823086977005005:  45%|████▍     | 11549/25880 [2:22:25<3:03:05,  1.30it/s]
1|11550|Loss: 0.7823086977005005:  45%|████▍     | 11550/25880 [2:22:25<3:00:15,  1.32it/s]
1|11551|Loss: 0.7808043956756592:  45%|████▍     | 11550/25880 [2:22:26<3:00:15,  1.32it/s]
1|11551|Loss: 0.7808043956756592:  45%|████▍     | 11551/25880 [2:22:26<2:56:46,  1.35it/s]
1|11552|Loss: 0.767071008682251:  45%|████▍     | 11551/25880 [2:22:26<2:56:46,  1.35it/s] 
1|11552|Loss: 0.767071008682251:  45%|████▍     | 11552/25880 [2:22:27<2:48:41,  1.42it/s]
1|11553|Loss: 0.7355087995529175:  45%|████▍     | 11552/25880 [2:22:27<2:48:41,  1.42it/s]
1|11553|Loss: 0.7355087995529175:  45%|████▍     | 11553/25880 [2:22:27<2:55:56,  1.36it/s]
1|11554|Loss: 0.7111440896987915:  45%|████▍     | 11553/25880 [2:22:28<2:55:56,  1.36it/s]
1|11554|Loss: 0.7111440896987915:  45%|████▍     | 11554/25880 [2:22:28<3:04:42,  1.29it/s]
1|11555|Loss: 0.9190953969955444:  45%|████▍     | 11554/25880 [2:22:29<3:04:42,  1.29it/s]
1|11555|Loss: 0.9190953969955444:  45%|████▍     | 11555/25880 [2:22:29<2:59:02,  1.33it/s]
1|11556|Loss: 0.8765034079551697:  45%|████▍     | 11555/25880 [2:22:29<2:59:02,  1.33it/s]
1|11556|Loss: 0.8765034079551697:  45%|████▍     | 11556/25880 [2:22:30<2:54:44,  1.37it/s]
1|11557|Loss: 0.9261667728424072:  45%|████▍     | 11556/25880 [2:22:30<2:54:44,  1.37it/s]
1|11557|Loss: 0.9261667728424072:  45%|████▍     | 11557/25880 [2:22:30<2:53:35,  1.38it/s]
1|11558|Loss: 0.7143501043319702:  45%|████▍     | 11557/25880 [2:22:31<2:53:35,  1.38it/s]
1|11558|Loss: 0.7143501043319702:  45%|████▍     | 11558/25880 [2:22:31<2:44:57,  1.45it/s]
1|11559|Loss: 0.8195157647132874:  45%|████▍     | 11558/25880 [2:22:31<2:44:57,  1.45it/s]
1|11559|Loss: 0.8195157647132874:  45%|████▍     | 11559/25880 [2:22:32<2:43:42,  1.46it/s]
1|11560|Loss: 0.774696409702301:  45%|████▍     | 11559/25880 [2:22:32<2:43:42,  1.46it/s] 
1|11560|Loss: 0.774696409702301:  45%|████▍     | 11560/25880 [2:22:32<2:40:52,  1.48it/s]
1|11561|Loss: 0.7982136607170105:  45%|████▍     | 11560/25880 [2:22:33<2:40:52,  1.48it/s]
1|11561|Loss: 0.7982136607170105:  45%|████▍     | 11561/25880 [2:22:33<2:44:34,  1.45it/s]
1|11562|Loss: 0.9252658486366272:  45%|████▍     | 11561/25880 [2:22:33<2:44:34,  1.45it/s]
1|11562|Loss: 0.9252658486366272:  45%|████▍     | 11562/25880 [2:22:34<2:49:08,  1.41it/s]
1|11563|Loss: 0.924032986164093:  45%|████▍     | 11562/25880 [2:22:34<2:49:08,  1.41it/s] 
1|11563|Loss: 0.924032986164093:  45%|████▍     | 11563/25880 [2:22:34<2:51:10,  1.39it/s]
1|11564|Loss: 0.7932093143463135:  45%|████▍     | 11563/25880 [2:22:35<2:51:10,  1.39it/s]
1|11564|Loss: 0.7932093143463135:  45%|████▍     | 11564/25880 [2:22:35<2:39:12,  1.50it/s]
1|11565|Loss: 0.7847474217414856:  45%|████▍     | 11564/25880 [2:22:35<2:39:12,  1.50it/s]
1|11565|Loss: 0.7847474217414856:  45%|████▍     | 11565/25880 [2:22:36<2:49:16,  1.41it/s]
1|11566|Loss: 0.8172644972801208:  45%|████▍     | 11565/25880 [2:22:36<2:49:16,  1.41it/s]
1|11566|Loss: 0.8172644972801208:  45%|████▍     | 11566/25880 [2:22:37<2:58:11,  1.34it/s]
1|11567|Loss: 1.0248764753341675:  45%|████▍     | 11566/25880 [2:22:37<2:58:11,  1.34it/s]
1|11567|Loss: 1.0248764753341675:  45%|████▍     | 11567/25880 [2:22:37<2:58:35,  1.34it/s]
1|11568|Loss: 0.84610915184021:  45%|████▍     | 11567/25880 [2:22:38<2:58:35,  1.34it/s]  
1|11568|Loss: 0.84610915184021:  45%|████▍     | 11568/25880 [2:22:38<3:03:29,  1.30it/s]
1|11569|Loss: 1.125408411026001:  45%|████▍     | 11568/25880 [2:22:39<3:03:29,  1.30it/s]
1|11569|Loss: 1.125408411026001:  45%|████▍     | 11569/25880 [2:22:39<3:20:30,  1.19it/s]
1|11570|Loss: 0.9053365588188171:  45%|████▍     | 11569/25880 [2:22:40<3:20:30,  1.19it/s]
1|11570|Loss: 0.9053365588188171:  45%|████▍     | 11570/25880 [2:22:40<3:22:14,  1.18it/s]
1|11571|Loss: 0.7600873112678528:  45%|████▍     | 11570/25880 [2:22:41<3:22:14,  1.18it/s]
1|11571|Loss: 0.7600873112678528:  45%|████▍     | 11571/25880 [2:22:41<3:15:14,  1.22it/s]
1|11572|Loss: 0.9008862376213074:  45%|████▍     | 11571/25880 [2:22:41<3:15:14,  1.22it/s]
1|11572|Loss: 0.9008862376213074:  45%|████▍     | 11572/25880 [2:22:42<3:09:27,  1.26it/s]
1|11573|Loss: 0.9517725110054016:  45%|████▍     | 11572/25880 [2:22:42<3:09:27,  1.26it/s]
1|11573|Loss: 0.9517725110054016:  45%|████▍     | 11573/25880 [2:22:42<2:53:50,  1.37it/s]
1|11574|Loss: 0.8179372549057007:  45%|████▍     | 11573/25880 [2:22:43<2:53:50,  1.37it/s]
1|11574|Loss: 0.8179372549057007:  45%|████▍     | 11574/25880 [2:22:43<2:45:53,  1.44it/s]
1|11575|Loss: 0.9198707342147827:  45%|████▍     | 11574/25880 [2:22:43<2:45:53,  1.44it/s]
1|11575|Loss: 0.9198707342147827:  45%|████▍     | 11575/25880 [2:22:43<2:45:37,  1.44it/s]
1|11576|Loss: 0.8614880442619324:  45%|████▍     | 11575/25880 [2:22:44<2:45:37,  1.44it/s]
1|11576|Loss: 0.8614880442619324:  45%|████▍     | 11576/25880 [2:22:44<2:56:06,  1.35it/s]
1|11577|Loss: 0.7957978248596191:  45%|████▍     | 11576/25880 [2:22:45<2:56:06,  1.35it/s]
1|11577|Loss: 0.7957978248596191:  45%|████▍     | 11577/25880 [2:22:45<2:52:50,  1.38it/s]
1|11578|Loss: 0.8645393252372742:  45%|████▍     | 11577/25880 [2:22:45<2:52:50,  1.38it/s]
1|11578|Loss: 0.8645393252372742:  45%|████▍     | 11578/25880 [2:22:46<2:46:57,  1.43it/s]
1|11579|Loss: 0.9241873621940613:  45%|████▍     | 11578/25880 [2:22:46<2:46:57,  1.43it/s]
1|11579|Loss: 0.9241873621940613:  45%|████▍     | 11579/25880 [2:22:46<2:46:26,  1.43it/s]
1|11580|Loss: 0.8652800917625427:  45%|████▍     | 11579/25880 [2:22:47<2:46:26,  1.43it/s]
1|11580|Loss: 0.8652800917625427:  45%|████▍     | 11580/25880 [2:22:47<2:42:47,  1.46it/s]
1|11581|Loss: 0.9424821734428406:  45%|████▍     | 11580/25880 [2:22:47<2:42:47,  1.46it/s]
1|11581|Loss: 0.9424821734428406:  45%|████▍     | 11581/25880 [2:22:48<2:49:12,  1.41it/s]
1|11582|Loss: 0.7767934799194336:  45%|████▍     | 11581/25880 [2:22:48<2:49:12,  1.41it/s]
1|11582|Loss: 0.7767934799194336:  45%|████▍     | 11582/25880 [2:22:48<2:49:54,  1.40it/s]
1|11583|Loss: 0.8080499768257141:  45%|████▍     | 11582/25880 [2:22:49<2:49:54,  1.40it/s]
1|11583|Loss: 0.8080499768257141:  45%|████▍     | 11583/25880 [2:22:49<2:51:24,  1.39it/s]
1|11584|Loss: 0.8861064314842224:  45%|████▍     | 11583/25880 [2:22:50<2:51:24,  1.39it/s]
1|11584|Loss: 0.8861064314842224:  45%|████▍     | 11584/25880 [2:22:50<2:41:04,  1.48it/s]
1|11585|Loss: 0.7892891764640808:  45%|████▍     | 11584/25880 [2:22:50<2:41:04,  1.48it/s]
1|11585|Loss: 0.7892891764640808:  45%|████▍     | 11585/25880 [2:22:50<2:33:31,  1.55it/s]
1|11586|Loss: 0.7411055564880371:  45%|████▍     | 11585/25880 [2:22:51<2:33:31,  1.55it/s]
1|11586|Loss: 0.7411055564880371:  45%|████▍     | 11586/25880 [2:22:51<2:48:05,  1.42it/s]
1|11587|Loss: 0.7736307382583618:  45%|████▍     | 11586/25880 [2:22:52<2:48:05,  1.42it/s]
1|11587|Loss: 0.7736307382583618:  45%|████▍     | 11587/25880 [2:22:52<2:45:38,  1.44it/s]
1|11588|Loss: 0.8932855129241943:  45%|████▍     | 11587/25880 [2:22:52<2:45:38,  1.44it/s]
1|11588|Loss: 0.8932855129241943:  45%|████▍     | 11588/25880 [2:22:53<2:45:01,  1.44it/s]
1|11589|Loss: 0.7229833602905273:  45%|████▍     | 11588/25880 [2:22:53<2:45:01,  1.44it/s]
1|11589|Loss: 0.7229833602905273:  45%|████▍     | 11589/25880 [2:22:53<2:40:23,  1.48it/s]
1|11590|Loss: 0.7884916067123413:  45%|████▍     | 11589/25880 [2:22:54<2:40:23,  1.48it/s]
1|11590|Loss: 0.7884916067123413:  45%|████▍     | 11590/25880 [2:22:54<2:43:36,  1.46it/s]
1|11591|Loss: 0.7686842679977417:  45%|████▍     | 11590/25880 [2:22:54<2:43:36,  1.46it/s]
1|11591|Loss: 0.7686842679977417:  45%|████▍     | 11591/25880 [2:22:55<2:47:49,  1.42it/s]
1|11592|Loss: 0.8867557644844055:  45%|████▍     | 11591/25880 [2:22:55<2:47:49,  1.42it/s]
1|11592|Loss: 0.8867557644844055:  45%|████▍     | 11592/25880 [2:22:55<2:53:34,  1.37it/s]
1|11593|Loss: 0.812848687171936:  45%|████▍     | 11592/25880 [2:22:56<2:53:34,  1.37it/s] 
1|11593|Loss: 0.812848687171936:  45%|████▍     | 11593/25880 [2:22:56<2:48:31,  1.41it/s]
1|11594|Loss: 0.8047854900360107:  45%|████▍     | 11593/25880 [2:22:56<2:48:31,  1.41it/s]
1|11594|Loss: 0.8047854900360107:  45%|████▍     | 11594/25880 [2:22:57<2:49:18,  1.41it/s]
1|11595|Loss: 0.7949349284172058:  45%|████▍     | 11594/25880 [2:22:57<2:49:18,  1.41it/s]
1|11595|Loss: 0.7949349284172058:  45%|████▍     | 11595/25880 [2:22:58<3:01:58,  1.31it/s]
1|11596|Loss: 0.8954217433929443:  45%|████▍     | 11595/25880 [2:22:58<3:01:58,  1.31it/s]
1|11596|Loss: 0.8954217433929443:  45%|████▍     | 11596/25880 [2:22:59<3:06:03,  1.28it/s]
1|11597|Loss: 0.8548517227172852:  45%|████▍     | 11596/25880 [2:22:59<3:06:03,  1.28it/s]
1|11597|Loss: 0.8548517227172852:  45%|████▍     | 11597/25880 [2:22:59<3:03:06,  1.30it/s]
1|11598|Loss: 0.8789631724357605:  45%|████▍     | 11597/25880 [2:23:00<3:03:06,  1.30it/s]
1|11598|Loss: 0.8789631724357605:  45%|████▍     | 11598/25880 [2:23:00<2:54:57,  1.36it/s]
1|11599|Loss: 0.6212066411972046:  45%|████▍     | 11598/25880 [2:23:00<2:54:57,  1.36it/s]
1|11599|Loss: 0.6212066411972046:  45%|████▍     | 11599/25880 [2:23:01<2:51:40,  1.39it/s]
1|11600|Loss: 0.87040114402771:  45%|████▍     | 11599/25880 [2:23:01<2:51:40,  1.39it/s]  
1|11600|Loss: 0.87040114402771:  45%|████▍     | 11600/25880 [2:23:02<3:02:43,  1.30it/s]
1|11601|Loss: 0.7888816595077515:  45%|████▍     | 11600/25880 [2:23:02<3:02:43,  1.30it/s]
1|11601|Loss: 0.7888816595077515:  45%|████▍     | 11601/25880 [2:23:02<3:02:46,  1.30it/s]
1|11602|Loss: 0.7572802901268005:  45%|████▍     | 11601/25880 [2:23:03<3:02:46,  1.30it/s]
1|11602|Loss: 0.7572802901268005:  45%|████▍     | 11602/25880 [2:23:03<2:59:56,  1.32it/s]
1|11603|Loss: 0.7205955982208252:  45%|████▍     | 11602/25880 [2:23:03<2:59:56,  1.32it/s]
1|11603|Loss: 0.7205955982208252:  45%|████▍     | 11603/25880 [2:23:04<2:51:47,  1.39it/s]
1|11604|Loss: 0.8039843440055847:  45%|████▍     | 11603/25880 [2:23:04<2:51:47,  1.39it/s]
1|11604|Loss: 0.8039843440055847:  45%|████▍     | 11604/25880 [2:23:04<2:57:38,  1.34it/s]
1|11605|Loss: 0.8017616868019104:  45%|████▍     | 11604/25880 [2:23:05<2:57:38,  1.34it/s]
1|11605|Loss: 0.8017616868019104:  45%|████▍     | 11605/25880 [2:23:05<2:48:43,  1.41it/s]
1|11606|Loss: 0.8624168634414673:  45%|████▍     | 11605/25880 [2:23:05<2:48:43,  1.41it/s]
1|11606|Loss: 0.8624168634414673:  45%|████▍     | 11606/25880 [2:23:06<2:42:00,  1.47it/s]
1|11607|Loss: 0.9786797165870667:  45%|████▍     | 11606/25880 [2:23:06<2:42:00,  1.47it/s]
1|11607|Loss: 0.9786797165870667:  45%|████▍     | 11607/25880 [2:23:06<2:36:16,  1.52it/s]
1|11608|Loss: 0.8908321261405945:  45%|████▍     | 11607/25880 [2:23:07<2:36:16,  1.52it/s]
1|11608|Loss: 0.8908321261405945:  45%|████▍     | 11608/25880 [2:23:07<2:47:10,  1.42it/s]
1|11609|Loss: 0.7976706624031067:  45%|████▍     | 11608/25880 [2:23:08<2:47:10,  1.42it/s]
1|11609|Loss: 0.7976706624031067:  45%|████▍     | 11609/25880 [2:23:08<2:57:03,  1.34it/s]
1|11610|Loss: 0.8208825588226318:  45%|████▍     | 11609/25880 [2:23:08<2:57:03,  1.34it/s]
1|11610|Loss: 0.8208825588226318:  45%|████▍     | 11610/25880 [2:23:09<2:50:17,  1.40it/s]
1|11611|Loss: 0.7958676815032959:  45%|████▍     | 11610/25880 [2:23:09<2:50:17,  1.40it/s]
1|11611|Loss: 0.7958676815032959:  45%|████▍     | 11611/25880 [2:23:09<2:50:27,  1.40it/s]
1|11612|Loss: 0.8560039401054382:  45%|████▍     | 11611/25880 [2:23:10<2:50:27,  1.40it/s]
1|11612|Loss: 0.8560039401054382:  45%|████▍     | 11612/25880 [2:23:10<2:57:54,  1.34it/s]
1|11613|Loss: 0.9660351276397705:  45%|████▍     | 11612/25880 [2:23:11<2:57:54,  1.34it/s]
1|11613|Loss: 0.9660351276397705:  45%|████▍     | 11613/25880 [2:23:11<3:03:45,  1.29it/s]
1|11614|Loss: 1.0252292156219482:  45%|████▍     | 11613/25880 [2:23:11<3:03:45,  1.29it/s]
1|11614|Loss: 1.0252292156219482:  45%|████▍     | 11614/25880 [2:23:12<2:49:19,  1.40it/s]
1|11615|Loss: 0.8367648720741272:  45%|████▍     | 11614/25880 [2:23:12<2:49:19,  1.40it/s]
1|11615|Loss: 0.8367648720741272:  45%|████▍     | 11615/25880 [2:23:12<2:48:31,  1.41it/s]
1|11616|Loss: 0.8242971301078796:  45%|████▍     | 11615/25880 [2:23:13<2:48:31,  1.41it/s]
1|11616|Loss: 0.8242971301078796:  45%|████▍     | 11616/25880 [2:23:13<2:56:15,  1.35it/s]
1|11617|Loss: 0.7833759188652039:  45%|████▍     | 11616/25880 [2:23:13<2:56:15,  1.35it/s]
1|11617|Loss: 0.7833759188652039:  45%|████▍     | 11617/25880 [2:23:14<3:02:18,  1.30it/s]
1|11618|Loss: 0.8290219306945801:  45%|████▍     | 11617/25880 [2:23:14<3:02:18,  1.30it/s]
1|11618|Loss: 0.8290219306945801:  45%|████▍     | 11618/25880 [2:23:15<2:52:28,  1.38it/s]
1|11619|Loss: 0.9074015021324158:  45%|████▍     | 11618/25880 [2:23:15<2:52:28,  1.38it/s]
1|11619|Loss: 0.9074015021324158:  45%|████▍     | 11619/25880 [2:23:15<2:51:26,  1.39it/s]
1|11620|Loss: 0.8577936291694641:  45%|████▍     | 11619/25880 [2:23:16<2:51:26,  1.39it/s]
1|11620|Loss: 0.8577936291694641:  45%|████▍     | 11620/25880 [2:23:16<2:52:57,  1.37it/s]
1|11621|Loss: 0.8581123352050781:  45%|████▍     | 11620/25880 [2:23:16<2:52:57,  1.37it/s]
1|11621|Loss: 0.8581123352050781:  45%|████▍     | 11621/25880 [2:23:17<2:59:06,  1.33it/s]
1|11622|Loss: 0.9832038283348083:  45%|████▍     | 11621/25880 [2:23:17<2:59:06,  1.33it/s]
1|11622|Loss: 0.9832038283348083:  45%|████▍     | 11622/25880 [2:23:17<2:47:05,  1.42it/s]
1|11623|Loss: 0.8365143537521362:  45%|████▍     | 11622/25880 [2:23:18<2:47:05,  1.42it/s]
1|11623|Loss: 0.8365143537521362:  45%|████▍     | 11623/25880 [2:23:18<2:46:18,  1.43it/s]
1|11624|Loss: 0.9177860021591187:  45%|████▍     | 11623/25880 [2:23:18<2:46:18,  1.43it/s]
1|11624|Loss: 0.9177860021591187:  45%|████▍     | 11624/25880 [2:23:19<2:46:38,  1.43it/s]
1|11625|Loss: 0.8667203783988953:  45%|████▍     | 11624/25880 [2:23:19<2:46:38,  1.43it/s]
1|11625|Loss: 0.8667203783988953:  45%|████▍     | 11625/25880 [2:23:20<2:54:41,  1.36it/s]
1|11626|Loss: 1.0177658796310425:  45%|████▍     | 11625/25880 [2:23:20<2:54:41,  1.36it/s]
1|11626|Loss: 1.0177658796310425:  45%|████▍     | 11626/25880 [2:23:20<2:51:21,  1.39it/s]
1|11627|Loss: 0.8276735544204712:  45%|████▍     | 11626/25880 [2:23:21<2:51:21,  1.39it/s]
1|11627|Loss: 0.8276735544204712:  45%|████▍     | 11627/25880 [2:23:21<2:54:58,  1.36it/s]
1|11628|Loss: 0.7686233520507812:  45%|████▍     | 11627/25880 [2:23:21<2:54:58,  1.36it/s]
1|11628|Loss: 0.7686233520507812:  45%|████▍     | 11628/25880 [2:23:22<2:50:06,  1.40it/s]
1|11629|Loss: 0.9551304578781128:  45%|████▍     | 11628/25880 [2:23:22<2:50:06,  1.40it/s]
1|11629|Loss: 0.9551304578781128:  45%|████▍     | 11629/25880 [2:23:22<2:42:03,  1.47it/s]
1|11630|Loss: 0.9289321899414062:  45%|████▍     | 11629/25880 [2:23:23<2:42:03,  1.47it/s]
1|11630|Loss: 0.9289321899414062:  45%|████▍     | 11630/25880 [2:23:23<2:47:36,  1.42it/s]
1|11631|Loss: 0.9055948257446289:  45%|████▍     | 11630/25880 [2:23:23<2:47:36,  1.42it/s]
1|11631|Loss: 0.9055948257446289:  45%|████▍     | 11631/25880 [2:23:24<2:50:23,  1.39it/s]
1|11632|Loss: 0.9861983060836792:  45%|████▍     | 11631/25880 [2:23:24<2:50:23,  1.39it/s]
1|11632|Loss: 0.9861983060836792:  45%|████���     | 11632/25880 [2:23:24<2:37:08,  1.51it/s]
1|11633|Loss: 0.7727651596069336:  45%|████▍     | 11632/25880 [2:23:25<2:37:08,  1.51it/s]
1|11633|Loss: 0.7727651596069336:  45%|████▍     | 11633/25880 [2:23:25<2:45:21,  1.44it/s]
1|11634|Loss: 0.7031285166740417:  45%|████▍     | 11633/25880 [2:23:26<2:45:21,  1.44it/s]
1|11634|Loss: 0.7031285166740417:  45%|████▍     | 11634/25880 [2:23:26<2:50:48,  1.39it/s]
1|11635|Loss: 0.8079580664634705:  45%|████▍     | 11634/25880 [2:23:26<2:50:48,  1.39it/s]
1|11635|Loss: 0.8079580664634705:  45%|████▍     | 11635/25880 [2:23:27<2:59:34,  1.32it/s]
1|11636|Loss: 0.7203730940818787:  45%|████▍     | 11635/25880 [2:23:27<2:59:34,  1.32it/s]
1|11636|Loss: 0.7203730940818787:  45%|████▍     | 11636/25880 [2:23:27<2:59:28,  1.32it/s]
1|11637|Loss: 0.7249599099159241:  45%|████▍     | 11636/25880 [2:23:28<2:59:28,  1.32it/s]
1|11637|Loss: 0.7249599099159241:  45%|████▍     | 11637/25880 [2:23:28<2:58:06,  1.33it/s]
1|11638|Loss: 0.7823006510734558:  45%|████▍     | 11637/25880 [2:23:29<2:58:06,  1.33it/s]
1|11638|Loss: 0.7823006510734558:  45%|████▍     | 11638/25880 [2:23:29<2:55:17,  1.35it/s]
1|11639|Loss: 0.8620809316635132:  45%|████▍     | 11638/25880 [2:23:29<2:55:17,  1.35it/s]
1|11639|Loss: 0.8620809316635132:  45%|████▍     | 11639/25880 [2:23:30<2:54:10,  1.36it/s]
1|11640|Loss: 0.8855005502700806:  45%|████▍     | 11639/25880 [2:23:30<2:54:10,  1.36it/s]
1|11640|Loss: 0.8855005502700806:  45%|████▍     | 11640/25880 [2:23:30<2:42:53,  1.46it/s]
1|11641|Loss: 0.7330803275108337:  45%|████▍     | 11640/25880 [2:23:31<2:42:53,  1.46it/s]
1|11641|Loss: 0.7330803275108337:  45%|████▍     | 11641/25880 [2:23:31<2:43:05,  1.46it/s]
1|11642|Loss: 0.9455669522285461:  45%|████▍     | 11641/25880 [2:23:31<2:43:05,  1.46it/s]
1|11642|Loss: 0.9455669522285461:  45%|████▍     | 11642/25880 [2:23:32<2:41:29,  1.47it/s]
1|11643|Loss: 0.9821418523788452:  45%|████▍     | 11642/25880 [2:23:32<2:41:29,  1.47it/s]
1|11643|Loss: 0.9821418523788452:  45%|████▍     | 11643/25880 [2:23:32<2:47:53,  1.41it/s]
1|11644|Loss: 0.8927748203277588:  45%|████▍     | 11643/25880 [2:23:33<2:47:53,  1.41it/s]
1|11644|Loss: 0.8927748203277588:  45%|████▍     | 11644/25880 [2:23:33<2:34:54,  1.53it/s]
1|11645|Loss: 0.8166477084159851:  45%|████▍     | 11644/25880 [2:23:33<2:34:54,  1.53it/s]
1|11645|Loss: 0.8166477084159851:  45%|████▍     | 11645/25880 [2:23:33<2:29:20,  1.59it/s]
1|11646|Loss: 1.0149309635162354:  45%|████▍     | 11645/25880 [2:23:34<2:29:20,  1.59it/s]
1|11646|Loss: 1.0149309635162354:  45%|████▌     | 11646/25880 [2:23:34<2:23:39,  1.65it/s]
1|11647|Loss: 0.9854695200920105:  45%|████▌     | 11646/25880 [2:23:34<2:23:39,  1.65it/s]
1|11647|Loss: 0.9854695200920105:  45%|████▌     | 11647/25880 [2:23:35<2:18:20,  1.71it/s]
1|11648|Loss: 0.7899901866912842:  45%|████▌     | 11647/25880 [2:23:35<2:18:20,  1.71it/s]
1|11648|Loss: 0.7899901866912842:  45%|████▌     | 11648/25880 [2:23:35<2:25:59,  1.62it/s]
1|11649|Loss: 0.860210120677948:  45%|████▌     | 11648/25880 [2:23:36<2:25:59,  1.62it/s] 
1|11649|Loss: 0.860210120677948:  45%|████▌     | 11649/25880 [2:23:36<2:40:51,  1.47it/s]
1|11650|Loss: 0.8291839957237244:  45%|████▌     | 11649/25880 [2:23:36<2:40:51,  1.47it/s]
1|11650|Loss: 0.8291839957237244:  45%|████▌     | 11650/25880 [2:23:37<2:38:16,  1.50it/s]
1|11651|Loss: 0.9755746722221375:  45%|████▌     | 11650/25880 [2:23:37<2:38:16,  1.50it/s]
1|11651|Loss: 0.9755746722221375:  45%|████▌     | 11651/25880 [2:23:37<2:33:58,  1.54it/s]
1|11652|Loss: 0.8609923720359802:  45%|████▌     | 11651/25880 [2:23:38<2:33:58,  1.54it/s]
1|11652|Loss: 0.8609923720359802:  45%|████▌     | 11652/25880 [2:23:38<2:18:45,  1.71it/s]
1|11653|Loss: 0.7529610991477966:  45%|████▌     | 11652/25880 [2:23:38<2:18:45,  1.71it/s]
1|11653|Loss: 0.7529610991477966:  45%|████▌     | 11653/25880 [2:23:38<2:23:01,  1.66it/s]
1|11654|Loss: 0.6595908403396606:  45%|████▌     | 11653/25880 [2:23:39<2:23:01,  1.66it/s]
1|11654|Loss: 0.6595908403396606:  45%|████▌     | 11654/25880 [2:23:39<2:26:31,  1.62it/s]
1|11655|Loss: 0.7929965853691101:  45%|████▌     | 11654/25880 [2:23:39<2:26:31,  1.62it/s]
1|11655|Loss: 0.7929965853691101:  45%|████▌     | 11655/25880 [2:23:40<2:26:41,  1.62it/s]
1|11656|Loss: 0.9783020615577698:  45%|████▌     | 11655/25880 [2:23:40<2:26:41,  1.62it/s]
1|11656|Loss: 0.9783020615577698:  45%|████▌     | 11656/25880 [2:23:40<2:27:59,  1.60it/s]
1|11657|Loss: 0.8874531984329224:  45%|████▌     | 11656/25880 [2:23:41<2:27:59,  1.60it/s]
1|11657|Loss: 0.8874531984329224:  45%|████▌     | 11657/25880 [2:23:41<2:34:40,  1.53it/s]
1|11658|Loss: 0.850908637046814:  45%|████▌     | 11657/25880 [2:23:41<2:34:40,  1.53it/s] 
1|11658|Loss: 0.850908637046814:  45%|████▌     | 11658/25880 [2:23:42<2:40:36,  1.48it/s]
1|11659|Loss: 0.8482332229614258:  45%|████▌     | 11658/25880 [2:23:42<2:40:36,  1.48it/s]
1|11659|Loss: 0.8482332229614258:  45%|████▌     | 11659/25880 [2:23:42<2:44:10,  1.44it/s]
1|11660|Loss: 0.8955993056297302:  45%|████▌     | 11659/25880 [2:23:43<2:44:10,  1.44it/s]
1|11660|Loss: 0.8955993056297302:  45%|████▌     | 11660/25880 [2:23:43<2:41:46,  1.47it/s]
1|11661|Loss: 0.801428496837616:  45%|████▌     | 11660/25880 [2:23:43<2:41:46,  1.47it/s] 
1|11661|Loss: 0.801428496837616:  45%|████▌     | 11661/25880 [2:23:44<2:30:13,  1.58it/s]
1|11662|Loss: 0.749473512172699:  45%|████▌     | 11661/25880 [2:23:44<2:30:13,  1.58it/s]
1|11662|Loss: 0.749473512172699:  45%|████▌     | 11662/25880 [2:23:44<2:27:56,  1.60it/s]
1|11663|Loss: 0.9455878138542175:  45%|████▌     | 11662/25880 [2:23:45<2:27:56,  1.60it/s]
1|11663|Loss: 0.9455878138542175:  45%|████▌     | 11663/25880 [2:23:45<2:32:36,  1.55it/s]
1|11664|Loss: 0.8725584745407104:  45%|████▌     | 11663/25880 [2:23:45<2:32:36,  1.55it/s]
1|11664|Loss: 0.8725584745407104:  45%|████▌     | 11664/25880 [2:23:46<2:33:07,  1.55it/s]
1|11665|Loss: 0.9397502541542053:  45%|████▌     | 11664/25880 [2:23:46<2:33:07,  1.55it/s]
1|11665|Loss: 0.9397502541542053:  45%|████▌     | 11665/25880 [2:23:46<2:45:02,  1.44it/s]
1|11666|Loss: 0.8352735042572021:  45%|████▌     | 11665/25880 [2:23:47<2:45:02,  1.44it/s]
1|11666|Loss: 0.8352735042572021:  45%|████▌     | 11666/25880 [2:23:47<2:42:22,  1.46it/s]
1|11667|Loss: 0.8115608096122742:  45%|████▌     | 11666/25880 [2:23:47<2:42:22,  1.46it/s]
1|11667|Loss: 0.8115608096122742:  45%|████▌     | 11667/25880 [2:23:48<2:46:30,  1.42it/s]
1|11668|Loss: 1.0804705619812012:  45%|████▌     | 11667/25880 [2:23:48<2:46:30,  1.42it/s]
1|11668|Loss: 1.0804705619812012:  45%|████▌     | 11668/25880 [2:23:49<2:57:23,  1.34it/s]
1|11669|Loss: 0.8071391582489014:  45%|████▌     | 11668/25880 [2:23:49<2:57:23,  1.34it/s]
1|11669|Loss: 0.8071391582489014:  45%|████▌     | 11669/25880 [2:23:49<2:58:56,  1.32it/s]
1|11670|Loss: 0.8805877566337585:  45%|████▌     | 11669/25880 [2:23:50<2:58:56,  1.32it/s]
1|11670|Loss: 0.8805877566337585:  45%|████▌     | 11670/25880 [2:23:50<2:52:28,  1.37it/s]
1|11671|Loss: 0.9116442799568176:  45%|████▌     | 11670/25880 [2:23:51<2:52:28,  1.37it/s]
1|11671|Loss: 0.9116442799568176:  45%|████▌     | 11671/25880 [2:23:51<3:01:04,  1.31it/s]
1|11672|Loss: 0.8185781836509705:  45%|████▌     | 11671/25880 [2:23:51<3:01:04,  1.31it/s]
1|11672|Loss: 0.8185781836509705:  45%|████▌     | 11672/25880 [2:23:52<3:01:17,  1.31it/s]
1|11673|Loss: 0.8045162558555603:  45%|████▌     | 11672/25880 [2:23:52<3:01:17,  1.31it/s]
1|11673|Loss: 0.8045162558555603:  45%|████▌     | 11673/25880 [2:23:52<2:58:23,  1.33it/s]
1|11674|Loss: 0.9209262132644653:  45%|████▌     | 11673/25880 [2:23:53<2:58:23,  1.33it/s]
1|11674|Loss: 0.9209262132644653:  45%|████▌     | 11674/25880 [2:23:53<2:51:18,  1.38it/s]
1|11675|Loss: 0.7915471792221069:  45%|████▌     | 11674/25880 [2:23:53<2:51:18,  1.38it/s]
1|11675|Loss: 0.7915471792221069:  45%|████▌     | 11675/25880 [2:23:54<2:50:31,  1.39it/s]
1|11676|Loss: 0.9131981134414673:  45%|████▌     | 11675/25880 [2:23:54<2:50:31,  1.39it/s]
1|11676|Loss: 0.9131981134414673:  45%|████▌     | 11676/25880 [2:23:54<2:37:03,  1.51it/s]
1|11677|Loss: 0.8808291554450989:  45%|████▌     | 11676/25880 [2:23:55<2:37:03,  1.51it/s]
1|11677|Loss: 0.8808291554450989:  45%|████▌     | 11677/25880 [2:23:55<2:31:41,  1.56it/s]
1|11678|Loss: 0.8269248604774475:  45%|████▌     | 11677/25880 [2:23:55<2:31:41,  1.56it/s]
1|11678|Loss: 0.8269248604774475:  45%|████▌     | 11678/25880 [2:23:56<2:36:20,  1.51it/s]
1|11679|Loss: 0.768892228603363:  45%|████▌     | 11678/25880 [2:23:56<2:36:20,  1.51it/s] 
1|11679|Loss: 0.768892228603363:  45%|████▌     | 11679/25880 [2:23:56<2:39:39,  1.48it/s]
1|11680|Loss: 0.868033230304718:  45%|████▌     | 11679/25880 [2:23:57<2:39:39,  1.48it/s]
1|11680|Loss: 0.868033230304718:  45%|████▌     | 11680/25880 [2:23:57<2:30:13,  1.58it/s]
1|11681|Loss: 0.7155253887176514:  45%|████▌     | 11680/25880 [2:23:57<2:30:13,  1.58it/s]
1|11681|Loss: 0.7155253887176514:  45%|████▌     | 11681/25880 [2:23:58<2:28:36,  1.59it/s]
1|11682|Loss: 0.8738300204277039:  45%|████▌     | 11681/25880 [2:23:58<2:28:36,  1.59it/s]
1|11682|Loss: 0.8738300204277039:  45%|████▌     | 11682/25880 [2:23:58<2:38:01,  1.50it/s]
1|11683|Loss: 0.7388340830802917:  45%|████▌     | 11682/25880 [2:23:59<2:38:01,  1.50it/s]
1|11683|Loss: 0.7388340830802917:  45%|████▌     | 11683/25880 [2:23:59<2:32:14,  1.55it/s]
1|11684|Loss: 0.8622119426727295:  45%|████▌     | 11683/25880 [2:23:59<2:32:14,  1.55it/s]
1|11684|Loss: 0.8622119426727295:  45%|████▌     | 11684/25880 [2:24:00<2:34:02,  1.54it/s]
1|11685|Loss: 0.7957653999328613:  45%|████▌     | 11684/25880 [2:24:00<2:34:02,  1.54it/s]
1|11685|Loss: 0.7957653999328613:  45%|████▌     | 11685/25880 [2:24:00<2:39:37,  1.48it/s]
1|11686|Loss: 0.7662253975868225:  45%|████▌     | 11685/25880 [2:24:01<2:39:37,  1.48it/s]
1|11686|Loss: 0.7662253975868225:  45%|████▌     | 11686/25880 [2:24:01<2:32:01,  1.56it/s]
1|11687|Loss: 0.8276981711387634:  45%|████▌     | 11686/25880 [2:24:01<2:32:01,  1.56it/s]
1|11687|Loss: 0.8276981711387634:  45%|████▌     | 11687/25880 [2:24:02<2:41:04,  1.47it/s]
1|11688|Loss: 0.8672979474067688:  45%|████▌     | 11687/25880 [2:24:02<2:41:04,  1.47it/s]
1|11688|Loss: 0.8672979474067688:  45%|████▌     | 11688/25880 [2:24:02<2:51:42,  1.38it/s]
1|11689|Loss: 0.8474770188331604:  45%|████▌     | 11688/25880 [2:24:03<2:51:42,  1.38it/s]
1|11689|Loss: 0.8474770188331604:  45%|████▌     | 11689/25880 [2:24:03<2:37:41,  1.50it/s]
1|11690|Loss: 0.901668131351471:  45%|████▌     | 11689/25880 [2:24:03<2:37:41,  1.50it/s] 
1|11690|Loss: 0.901668131351471:  45%|████▌     | 11690/25880 [2:24:04<2:36:17,  1.51it/s]
1|11691|Loss: 0.760226309299469:  45%|████▌     | 11690/25880 [2:24:04<2:36:17,  1.51it/s]
1|11691|Loss: 0.760226309299469:  45%|████▌     | 11691/25880 [2:24:04<2:46:46,  1.42it/s]
1|11692|Loss: 0.9609907269477844:  45%|████▌     | 11691/25880 [2:24:05<2:46:46,  1.42it/s]
1|11692|Loss: 0.9609907269477844:  45%|████▌     | 11692/25880 [2:24:05<2:50:41,  1.39it/s]
1|11693|Loss: 0.7945666313171387:  45%|████▌     | 11692/25880 [2:24:06<2:50:41,  1.39it/s]
1|11693|Loss: 0.7945666313171387:  45%|████▌     | 11693/25880 [2:24:06<2:41:50,  1.46it/s]
1|11694|Loss: 0.9044840335845947:  45%|████▌     | 11693/25880 [2:24:06<2:41:50,  1.46it/s]
1|11694|Loss: 0.9044840335845947:  45%|████▌     | 11694/25880 [2:24:07<2:45:46,  1.43it/s]
1|11695|Loss: 0.8785250186920166:  45%|████▌     | 11694/25880 [2:24:07<2:45:46,  1.43it/s]
1|11695|Loss: 0.8785250186920166:  45%|████▌     | 11695/25880 [2:24:07<2:47:33,  1.41it/s]
1|11696|Loss: 0.9102842807769775:  45%|████▌     | 11695/25880 [2:24:08<2:47:33,  1.41it/s]
1|11696|Loss: 0.9102842807769775:  45%|████▌     | 11696/25880 [2:24:08<2:49:01,  1.40it/s]
1|11697|Loss: 0.8196612000465393:  45%|████▌     | 11696/25880 [2:24:08<2:49:01,  1.40it/s]
1|11697|Loss: 0.8196612000465393:  45%|████▌     | 11697/25880 [2:24:09<2:51:36,  1.38it/s]
1|11698|Loss: 0.9566192626953125:  45%|████▌     | 11697/25880 [2:24:09<2:51:36,  1.38it/s]
1|11698|Loss: 0.9566192626953125:  45%|████▌     | 11698/25880 [2:24:10<3:03:20,  1.29it/s]
1|11699|Loss: 0.8530852794647217:  45%|████▌     | 11698/25880 [2:24:10<3:03:20,  1.29it/s]
1|11699|Loss: 0.8530852794647217:  45%|████▌     | 11699/25880 [2:24:10<3:05:50,  1.27it/s]
1|11700|Loss: 0.8256652355194092:  45%|████▌     | 11699/25880 [2:24:11<3:05:50,  1.27it/s]
1|11700|Loss: 0.8256652355194092:  45%|████▌     | 11700/25880 [2:24:11<3:09:58,  1.24it/s]
1|11701|Loss: 0.6877561807632446:  45%|████▌     | 11700/25880 [2:24:12<3:09:58,  1.24it/s]
1|11701|Loss: 0.6877561807632446:  45%|████▌     | 11701/25880 [2:24:12<3:19:45,  1.18it/s]
1|11702|Loss: 0.865161120891571:  45%|████▌     | 11701/25880 [2:24:13<3:19:45,  1.18it/s] 
1|11702|Loss: 0.865161120891571:  45%|████▌     | 11702/25880 [2:24:13<3:09:16,  1.25it/s]
1|11703|Loss: 0.7007321119308472:  45%|████▌     | 11702/25880 [2:24:13<3:09:16,  1.25it/s]
1|11703|Loss: 0.7007321119308472:  45%|████▌     | 11703/25880 [2:24:14<2:56:19,  1.34it/s]
1|11704|Loss: 0.7171078324317932:  45%|████▌     | 11703/25880 [2:24:14<2:56:19,  1.34it/s]
1|11704|Loss: 0.7171078324317932:  45%|████▌     | 11704/25880 [2:24:14<2:48:31,  1.40it/s]
1|11705|Loss: 0.9667920470237732:  45%|████▌     | 11704/25880 [2:24:15<2:48:31,  1.40it/s]
1|11705|Loss: 0.9667920470237732:  45%|████▌     | 11705/25880 [2:24:15<2:54:44,  1.35it/s]
1|11706|Loss: 0.7825291752815247:  45%|████▌     | 11705/25880 [2:24:15<2:54:44,  1.35it/s]
1|11706|Loss: 0.7825291752815247:  45%|████▌     | 11706/25880 [2:24:16<2:53:42,  1.36it/s]
1|11707|Loss: 0.744965672492981:  45%|████▌     | 11706/25880 [2:24:16<2:53:42,  1.36it/s] 
1|11707|Loss: 0.744965672492981:  45%|████▌     | 11707/25880 [2:24:16<2:52:58,  1.37it/s]
1|11708|Loss: 0.9624317288398743:  45%|████▌     | 11707/25880 [2:24:17<2:52:58,  1.37it/s]
1|11708|Loss: 0.9624317288398743:  45%|████▌     | 11708/25880 [2:24:17<2:51:04,  1.38it/s]
1|11709|Loss: 0.8847699761390686:  45%|████▌     | 11708/25880 [2:24:17<2:51:04,  1.38it/s]
1|11709|Loss: 0.8847699761390686:  45%|████▌     | 11709/25880 [2:24:18<2:38:21,  1.49it/s]
1|11710|Loss: 0.8981359601020813:  45%|████▌     | 11709/25880 [2:24:18<2:38:21,  1.49it/s]
1|11710|Loss: 0.8981359601020813:  45%|████▌     | 11710/25880 [2:24:18<2:29:48,  1.58it/s]
1|11711|Loss: 0.8396376967430115:  45%|████▌     | 11710/25880 [2:24:19<2:29:48,  1.58it/s]
1|11711|Loss: 0.8396376967430115:  45%|████▌     | 11711/25880 [2:24:19<2:37:15,  1.50it/s]
1|11712|Loss: 0.812064528465271:  45%|████▌     | 11711/25880 [2:24:19<2:37:15,  1.50it/s] 
1|11712|Loss: 0.812064528465271:  45%|████▌     | 11712/25880 [2:24:20<2:38:20,  1.49it/s]
1|11713|Loss: 0.9704142808914185:  45%|████▌     | 11712/25880 [2:24:20<2:38:20,  1.49it/s]
1|11713|Loss: 0.9704142808914185:  45%|████▌     | 11713/25880 [2:24:20<2:33:49,  1.54it/s]
1|11714|Loss: 0.8054455518722534:  45%|████▌     | 11713/25880 [2:24:21<2:33:49,  1.54it/s]
1|11714|Loss: 0.8054455518722534:  45%|████▌     | 11714/25880 [2:24:21<2:40:07,  1.47it/s]
1|11715|Loss: 0.7970280051231384:  45%|████▌     | 11714/25880 [2:24:21<2:40:07,  1.47it/s]
1|11715|Loss: 0.7970280051231384:  45%|████▌     | 11715/25880 [2:24:22<2:53:21,  1.36it/s]
1|11716|Loss: 0.9061220288276672:  45%|████▌     | 11715/25880 [2:24:22<2:53:21,  1.36it/s]
1|11716|Loss: 0.9061220288276672:  45%|████▌     | 11716/25880 [2:24:22<2:47:30,  1.41it/s]
1|11717|Loss: 0.9334598183631897:  45%|████▌     | 11716/25880 [2:24:23<2:47:30,  1.41it/s]
1|11717|Loss: 0.9334598183631897:  45%|████▌     | 11717/25880 [2:24:23<2:40:08,  1.47it/s]
1|11718|Loss: 0.8439844250679016:  45%|████▌     | 11717/25880 [2:24:23<2:40:08,  1.47it/s]
1|11718|Loss: 0.8439844250679016:  45%|████▌     | 11718/25880 [2:24:24<2:21:53,  1.66it/s]
1|11719|Loss: 0.8514471650123596:  45%|████▌     | 11718/25880 [2:24:24<2:21:53,  1.66it/s]
1|11719|Loss: 0.8514471650123596:  45%|████▌     | 11719/25880 [2:24:24<2:20:10,  1.68it/s]
1|11720|Loss: 0.9843007326126099:  45%|████▌     | 11719/25880 [2:24:24<2:20:10,  1.68it/s]
1|11720|Loss: 0.9843007326126099:  45%|████▌     | 11720/25880 [2:24:25<2:28:05,  1.59it/s]
1|11721|Loss: 0.8755837082862854:  45%|████▌     | 11720/25880 [2:24:25<2:28:05,  1.59it/s]
1|11721|Loss: 0.8755837082862854:  45%|████▌     | 11721/25880 [2:24:25<2:28:55,  1.58it/s]
1|11722|Loss: 0.8163018822669983:  45%|████▌     | 11721/25880 [2:24:26<2:28:55,  1.58it/s]
1|11722|Loss: 0.8163018822669983:  45%|████▌     | 11722/25880 [2:24:26<2:32:37,  1.55it/s]
1|11723|Loss: 0.967242956161499:  45%|████▌     | 11722/25880 [2:24:26<2:32:37,  1.55it/s] 
1|11723|Loss: 0.967242956161499:  45%|████▌     | 11723/25880 [2:24:27<2:26:14,  1.61it/s]
1|11724|Loss: 0.7838165163993835:  45%|████▌     | 11723/25880 [2:24:27<2:26:14,  1.61it/s]
1|11724|Loss: 0.7838165163993835:  45%|████▌     | 11724/25880 [2:24:27<2:30:00,  1.57it/s]
1|11725|Loss: 1.061679482460022:  45%|████▌     | 11724/25880 [2:24:28<2:30:00,  1.57it/s] 
1|11725|Loss: 1.061679482460022:  45%|████▌     | 11725/25880 [2:24:28<2:46:31,  1.42it/s]
1|11726|Loss: 0.8193992972373962:  45%|████▌     | 11725/25880 [2:24:29<2:46:31,  1.42it/s]
1|11726|Loss: 0.8193992972373962:  45%|████▌     | 11726/25880 [2:24:29<2:56:17,  1.34it/s]
1|11727|Loss: 0.701911211013794:  45%|████▌     | 11726/25880 [2:24:29<2:56:17,  1.34it/s] 
1|11727|Loss: 0.701911211013794:  45%|████▌     | 11727/25880 [2:24:30<2:57:08,  1.33it/s]
1|11728|Loss: 0.8334559798240662:  45%|████▌     | 11727/25880 [2:24:30<2:57:08,  1.33it/s]
1|11728|Loss: 0.8334559798240662:  45%|████▌     | 11728/25880 [2:24:30<2:50:30,  1.38it/s]
1|11729|Loss: 0.7371906638145447:  45%|████▌     | 11728/25880 [2:24:31<2:50:30,  1.38it/s]
1|11729|Loss: 0.7371906638145447:  45%|████▌     | 11729/25880 [2:24:31<2:50:58,  1.38it/s]
1|11730|Loss: 0.8049299120903015:  45%|████▌     | 11729/25880 [2:24:32<2:50:58,  1.38it/s]
1|11730|Loss: 0.8049299120903015:  45%|████▌     | 11730/25880 [2:24:32<2:50:13,  1.39it/s]
1|11731|Loss: 0.9281415343284607:  45%|████▌     | 11730/25880 [2:24:32<2:50:13,  1.39it/s]
1|11731|Loss: 0.9281415343284607:  45%|████▌     | 11731/25880 [2:24:33<2:48:11,  1.40it/s]
1|11732|Loss: 0.7555767893791199:  45%|████▌     | 11731/25880 [2:24:33<2:48:11,  1.40it/s]
1|11732|Loss: 0.7555767893791199:  45%|████▌     | 11732/25880 [2:24:33<2:38:43,  1.49it/s]
1|11733|Loss: 0.9078445434570312:  45%|██��█▌     | 11732/25880 [2:24:34<2:38:43,  1.49it/s]
1|11733|Loss: 0.9078445434570312:  45%|████▌     | 11733/25880 [2:24:34<2:30:02,  1.57it/s]
1|11734|Loss: 0.7679567933082581:  45%|████▌     | 11733/25880 [2:24:34<2:30:02,  1.57it/s]
1|11734|Loss: 0.7679567933082581:  45%|████▌     | 11734/25880 [2:24:34<2:28:25,  1.59it/s]
1|11735|Loss: 0.9064705967903137:  45%|████▌     | 11734/25880 [2:24:35<2:28:25,  1.59it/s]
1|11735|Loss: 0.9064705967903137:  45%|████▌     | 11735/25880 [2:24:35<2:35:16,  1.52it/s]
1|11736|Loss: 0.8799198865890503:  45%|████▌     | 11735/25880 [2:24:35<2:35:16,  1.52it/s]
1|11736|Loss: 0.8799198865890503:  45%|████▌     | 11736/25880 [2:24:36<2:35:45,  1.51it/s]
1|11737|Loss: 0.7676172852516174:  45%|████▌     | 11736/25880 [2:24:36<2:35:45,  1.51it/s]
1|11737|Loss: 0.7676172852516174:  45%|████▌     | 11737/25880 [2:24:36<2:39:22,  1.48it/s]
1|11738|Loss: 0.8373336791992188:  45%|████▌     | 11737/25880 [2:24:37<2:39:22,  1.48it/s]
1|11738|Loss: 0.8373336791992188:  45%|████▌     | 11738/25880 [2:24:37<2:48:45,  1.40it/s]
1|11739|Loss: 0.902621328830719:  45%|████▌     | 11738/25880 [2:24:38<2:48:45,  1.40it/s] 
1|11739|Loss: 0.902621328830719:  45%|████▌     | 11739/25880 [2:24:38<2:55:20,  1.34it/s]
1|11740|Loss: 0.7882400751113892:  45%|████▌     | 11739/25880 [2:24:38<2:55:20,  1.34it/s]
1|11740|Loss: 0.7882400751113892:  45%|████▌     | 11740/25880 [2:24:39<2:55:09,  1.35it/s]
1|11741|Loss: 1.0723336935043335:  45%|████▌     | 11740/25880 [2:24:39<2:55:09,  1.35it/s]
1|11741|Loss: 1.0723336935043335:  45%|████▌     | 11741/25880 [2:24:40<2:54:32,  1.35it/s]
1|11742|Loss: 0.8223076462745667:  45%|████▌     | 11741/25880 [2:24:40<2:54:32,  1.35it/s]
1|11742|Loss: 0.8223076462745667:  45%|████▌     | 11742/25880 [2:24:40<3:07:55,  1.25it/s]
1|11743|Loss: 0.8310161828994751:  45%|████▌     | 11742/25880 [2:24:41<3:07:55,  1.25it/s]
1|11743|Loss: 0.8310161828994751:  45%|████▌     | 11743/25880 [2:24:41<3:17:55,  1.19it/s]
1|11744|Loss: 0.8842162489891052:  45%|████▌     | 11743/25880 [2:24:42<3:17:55,  1.19it/s]
1|11744|Loss: 0.8842162489891052:  45%|████▌     | 11744/25880 [2:24:42<3:11:35,  1.23it/s]
1|11745|Loss: 0.6350080966949463:  45%|████▌     | 11744/25880 [2:24:43<3:11:35,  1.23it/s]
1|11745|Loss: 0.6350080966949463:  45%|████▌     | 11745/25880 [2:24:43<3:20:45,  1.17it/s]
1|11746|Loss: 0.7947368621826172:  45%|████▌     | 11745/25880 [2:24:44<3:20:45,  1.17it/s]
1|11746|Loss: 0.7947368621826172:  45%|████▌     | 11746/25880 [2:24:44<3:01:21,  1.30it/s]
1|11747|Loss: 0.7647820711135864:  45%|████▌     | 11746/25880 [2:24:44<3:01:21,  1.30it/s]
1|11747|Loss: 0.7647820711135864:  45%|████▌     | 11747/25880 [2:24:44<2:52:38,  1.36it/s]
1|11748|Loss: 0.8375498652458191:  45%|████▌     | 11747/25880 [2:24:45<2:52:38,  1.36it/s]
1|11748|Loss: 0.8375498652458191:  45%|████▌     | 11748/25880 [2:24:45<2:51:45,  1.37it/s]
1|11749|Loss: 0.9788503050804138:  45%|████▌     | 11748/25880 [2:24:45<2:51:45,  1.37it/s]
1|11749|Loss: 0.9788503050804138:  45%|████▌     | 11749/25880 [2:24:46<2:45:08,  1.43it/s]
1|11750|Loss: 0.7258669137954712:  45%|████▌     | 11749/25880 [2:24:46<2:45:08,  1.43it/s]
1|11750|Loss: 0.7258669137954712:  45%|████▌     | 11750/25880 [2:24:46<2:38:54,  1.48it/s]
1|11751|Loss: 0.7139522433280945:  45%|████▌     | 11750/25880 [2:24:47<2:38:54,  1.48it/s]
1|11751|Loss: 0.7139522433280945:  45%|████▌     | 11751/25880 [2:24:47<2:39:17,  1.48it/s]
1|11752|Loss: 0.792580783367157:  45%|████▌     | 11751/25880 [2:24:47<2:39:17,  1.48it/s] 
1|11752|Loss: 0.792580783367157:  45%|████▌     | 11752/25880 [2:24:48<2:40:51,  1.46it/s]
1|11753|Loss: 1.0150508880615234:  45%|████▌     | 11752/25880 [2:24:48<2:40:51,  1.46it/s]
1|11753|Loss: 1.0150508880615234:  45%|████▌     | 11753/25880 [2:24:48<2:43:29,  1.44it/s]
1|11754|Loss: 0.7795528769493103:  45%|████▌     | 11753/25880 [2:24:49<2:43:29,  1.44it/s]
1|11754|Loss: 0.7795528769493103:  45%|████▌     | 11754/25880 [2:24:49<2:56:19,  1.34it/s]
1|11755|Loss: 0.8760761022567749:  45%|████▌     | 11754/25880 [2:24:50<2:56:19,  1.34it/s]
1|11755|Loss: 0.8760761022567749:  45%|████▌     | 11755/25880 [2:24:50<3:01:38,  1.30it/s]
1|11756|Loss: 0.9874001741409302:  45%|████▌     | 11755/25880 [2:24:51<3:01:38,  1.30it/s]
1|11756|Loss: 0.9874001741409302:  45%|████▌     | 11756/25880 [2:24:51<3:10:03,  1.24it/s]
1|11757|Loss: 0.7791923880577087:  45%|████▌     | 11756/25880 [2:24:52<3:10:03,  1.24it/s]
1|11757|Loss: 0.7791923880577087:  45%|████▌     | 11757/25880 [2:24:52<3:21:32,  1.17it/s]
1|11758|Loss: 0.8295459151268005:  45%|████▌     | 11757/25880 [2:24:52<3:21:32,  1.17it/s]
1|11758|Loss: 0.8295459151268005:  45%|████▌     | 11758/25880 [2:24:53<3:22:24,  1.16it/s]
1|11759|Loss: 0.8894174695014954:  45%|████▌     | 11758/25880 [2:24:53<3:22:24,  1.16it/s]
1|11759|Loss: 0.8894174695014954:  45%|████▌     | 11759/25880 [2:24:54<3:17:41,  1.19it/s]
1|11760|Loss: 0.872110903263092:  45%|████▌     | 11759/25880 [2:24:54<3:17:41,  1.19it/s] 
1|11760|Loss: 0.872110903263092:  45%|████▌     | 11760/25880 [2:24:54<3:04:37,  1.27it/s]
1|11761|Loss: 0.7827099561691284:  45%|████▌     | 11760/25880 [2:24:55<3:04:37,  1.27it/s]
1|11761|Loss: 0.7827099561691284:  45%|████▌     | 11761/25880 [2:24:55<3:09:53,  1.24it/s]
1|11762|Loss: 1.0940927267074585:  45%|████▌     | 11761/25880 [2:24:56<3:09:53,  1.24it/s]
1|11762|Loss: 1.0940927267074585:  45%|████▌     | 11762/25880 [2:24:56<3:14:08,  1.21it/s]
1|11763|Loss: 0.8194702863693237:  45%|████▌     | 11762/25880 [2:24:56<3:14:08,  1.21it/s]
1|11763|Loss: 0.8194702863693237:  45%|████▌     | 11763/25880 [2:24:57<3:04:41,  1.27it/s]
1|11764|Loss: 0.7963983416557312:  45%|████▌     | 11763/25880 [2:24:57<3:04:41,  1.27it/s]
1|11764|Loss: 0.7963983416557312:  45%|████▌     | 11764/25880 [2:24:58<3:06:11,  1.26it/s]
1|11765|Loss: 0.9112975597381592:  45%|████▌     | 11764/25880 [2:24:58<3:06:11,  1.26it/s]
1|11765|Loss: 0.9112975597381592:  45%|████▌     | 11765/25880 [2:24:58<2:54:10,  1.35it/s]
1|11766|Loss: 0.8708643913269043:  45%|████▌     | 11765/25880 [2:24:58<2:54:10,  1.35it/s]
1|11766|Loss: 0.8708643913269043:  45%|████▌     | 11766/25880 [2:24:59<2:45:16,  1.42it/s]
1|11767|Loss: 1.016919493675232:  45%|████▌     | 11766/25880 [2:24:59<2:45:16,  1.42it/s] 
1|11767|Loss: 1.016919493675232:  45%|████▌     | 11767/25880 [2:24:59<2:39:22,  1.48it/s]
1|11768|Loss: 0.7990030646324158:  45%|████▌     | 11767/25880 [2:25:00<2:39:22,  1.48it/s]
1|11768|Loss: 0.7990030646324158:  45%|████▌     | 11768/25880 [2:25:00<2:31:42,  1.55it/s]
1|11769|Loss: 0.7050570845603943:  45%|████▌     | 11768/25880 [2:25:00<2:31:42,  1.55it/s]
1|11769|Loss: 0.7050570845603943:  45%|████▌     | 11769/25880 [2:25:00<2:24:00,  1.63it/s]
1|11770|Loss: 0.8194509744644165:  45%|████▌     | 11769/25880 [2:25:01<2:24:00,  1.63it/s]
1|11770|Loss: 0.8194509744644165:  45%|████▌     | 11770/25880 [2:25:01<2:21:31,  1.66it/s]
1|11771|Loss: 0.8655545711517334:  45%|████▌     | 11770/25880 [2:25:01<2:21:31,  1.66it/s]
1|11771|Loss: 0.8655545711517334:  45%|████▌     | 11771/25880 [2:25:02<2:22:58,  1.64it/s]
1|11772|Loss: 0.8684076070785522:  45%|████▌     | 11771/25880 [2:25:02<2:22:58,  1.64it/s]
1|11772|Loss: 0.8684076070785522:  45%|████▌     | 11772/25880 [2:25:02<2:36:58,  1.50it/s]
1|11773|Loss: 0.8553085327148438:  45%|████▌     | 11772/25880 [2:25:03<2:36:58,  1.50it/s]
1|11773|Loss: 0.8553085327148438:  45%|████▌     | 11773/25880 [2:25:03<2:50:06,  1.38it/s]
1|11774|Loss: 0.7374249696731567:  45%|████▌     | 11773/25880 [2:25:04<2:50:06,  1.38it/s]
1|11774|Loss: 0.7374249696731567:  45%|████▌     | 11774/25880 [2:25:04<2:52:52,  1.36it/s]
1|11775|Loss: 0.8358492851257324:  45%|████▌     | 11774/25880 [2:25:04<2:52:52,  1.36it/s]
1|11775|Loss: 0.8358492851257324:  45%|████▌     | 11775/25880 [2:25:05<2:47:21,  1.40it/s]
1|11776|Loss: 0.6567975282669067:  45%|████▌     | 11775/25880 [2:25:05<2:47:21,  1.40it/s]
1|11776|Loss: 0.6567975282669067:  46%|████▌     | 11776/25880 [2:25:05<2:47:13,  1.41it/s]
1|11777|Loss: 0.8058308959007263:  46%|████▌     | 11776/25880 [2:25:06<2:47:13,  1.41it/s]
1|11777|Loss: 0.8058308959007263:  46%|████▌     | 11777/25880 [2:25:06<2:34:35,  1.52it/s]
1|11778|Loss: 0.7578872442245483:  46%|████▌     | 11777/25880 [2:25:06<2:34:35,  1.52it/s]
1|11778|Loss: 0.7578872442245483:  46%|████▌     | 11778/25880 [2:25:07<2:34:04,  1.53it/s]
1|11779|Loss: 0.8589485883712769:  46%|████▌     | 11778/25880 [2:25:07<2:34:04,  1.53it/s]
1|11779|Loss: 0.8589485883712769:  46%|████▌     | 11779/25880 [2:25:07<2:44:37,  1.43it/s]
1|11780|Loss: 0.9042696356773376:  46%|████▌     | 11779/25880 [2:25:08<2:44:37,  1.43it/s]
1|11780|Loss: 0.9042696356773376:  46%|████▌     | 11780/25880 [2:25:08<2:38:05,  1.49it/s]
1|11781|Loss: 1.0279769897460938:  46%|████▌     | 11780/25880 [2:25:08<2:38:05,  1.49it/s]
1|11781|Loss: 1.0279769897460938:  46%|████▌     | 11781/25880 [2:25:09<2:33:04,  1.54it/s]
1|11782|Loss: 0.7661395072937012:  46%|████▌     | 11781/25880 [2:25:09<2:33:04,  1.54it/s]
1|11782|Loss: 0.7661395072937012:  46%|████▌     | 11782/25880 [2:25:09<2:35:30,  1.51it/s]
1|11783|Loss: 1.084043025970459:  46%|████▌     | 11782/25880 [2:25:10<2:35:30,  1.51it/s] 
1|11783|Loss: 1.084043025970459:  46%|████▌     | 11783/25880 [2:25:10<2:34:42,  1.52it/s]
1|11784|Loss: 0.8613592982292175:  46%|████▌     | 11783/25880 [2:25:10<2:34:42,  1.52it/s]
1|11784|Loss: 0.8613592982292175:  46%|████▌     | 11784/25880 [2:25:11<2:38:29,  1.48it/s]
1|11785|Loss: 0.8125174641609192:  46%|████▌     | 11784/25880 [2:25:11<2:38:29,  1.48it/s]
1|11785|Loss: 0.8125174641609192:  46%|████▌     | 11785/25880 [2:25:11<2:45:25,  1.42it/s]
1|11786|Loss: 0.8654683232307434:  46%|████▌     | 11785/25880 [2:25:12<2:45:25,  1.42it/s]
1|11786|Loss: 0.8654683232307434:  46%|████▌     | 11786/25880 [2:25:12<2:48:03,  1.40it/s]
1|11787|Loss: 0.6772161722183228:  46%|████▌     | 11786/25880 [2:25:13<2:48:03,  1.40it/s]
1|11787|Loss: 0.6772161722183228:  46%|████▌     | 11787/25880 [2:25:13<2:36:16,  1.50it/s]
1|11788|Loss: 0.77605140209198:  46%|████▌     | 11787/25880 [2:25:13<2:36:16,  1.50it/s]  
1|11788|Loss: 0.77605140209198:  46%|████▌     | 11788/25880 [2:25:14<2:50:08,  1.38it/s]
1|11789|Loss: 0.8259931206703186:  46%|████▌     | 11788/25880 [2:25:14<2:50:08,  1.38it/s]
1|11789|Loss: 0.8259931206703186:  46%|████▌     | 11789/25880 [2:25:14<2:48:46,  1.39it/s]
1|11790|Loss: 0.7602088451385498:  46%|████▌     | 11789/25880 [2:25:15<2:48:46,  1.39it/s]
1|11790|Loss: 0.7602088451385498:  46%|████▌     | 11790/25880 [2:25:15<2:46:58,  1.41it/s]
1|11791|Loss: 0.7963325381278992:  46%|████▌     | 11790/25880 [2:25:15<2:46:58,  1.41it/s]
1|11791|Loss: 0.7963325381278992:  46%|████▌     | 11791/25880 [2:25:16<2:46:14,  1.41it/s]
1|11792|Loss: 0.8851361274719238:  46%|████▌     | 11791/25880 [2:25:16<2:46:14,  1.41it/s]
1|11792|Loss: 0.8851361274719238:  46%|████▌     | 11792/25880 [2:25:16<2:37:25,  1.49it/s]
1|11793|Loss: 0.8766468167304993:  46%|████▌     | 11792/25880 [2:25:17<2:37:25,  1.49it/s]
1|11793|Loss: 0.8766468167304993:  46%|████▌     | 11793/25880 [2:25:17<2:37:10,  1.49it/s]
1|11794|Loss: 0.8516883850097656:  46%|████▌     | 11793/25880 [2:25:17<2:37:10,  1.49it/s]
1|11794|Loss: 0.8516883850097656:  46%|████▌     | 11794/25880 [2:25:18<2:44:13,  1.43it/s]
1|11795|Loss: 0.8831865191459656:  46%|████▌     | 11794/25880 [2:25:18<2:44:13,  1.43it/s]
1|11795|Loss: 0.8831865191459656:  46%|████▌     | 11795/25880 [2:25:18<2:39:34,  1.47it/s]
1|11796|Loss: 0.8558204174041748:  46%|████▌     | 11795/25880 [2:25:19<2:39:34,  1.47it/s]
1|11796|Loss: 0.8558204174041748:  46%|████▌     | 11796/25880 [2:25:19<2:45:52,  1.42it/s]
1|11797|Loss: 0.8113961815834045:  46%|████▌     | 11796/25880 [2:25:20<2:45:52,  1.42it/s]
1|11797|Loss: 0.8113961815834045:  46%|████▌     | 11797/25880 [2:25:20<2:42:21,  1.45it/s]
1|11798|Loss: 0.8859800100326538:  46%|████▌     | 11797/25880 [2:25:20<2:42:21,  1.45it/s]
1|11798|Loss: 0.8859800100326538:  46%|████▌     | 11798/25880 [2:25:21<2:43:17,  1.44it/s]
1|11799|Loss: 0.8213649392127991:  46%|████▌     | 11798/25880 [2:25:21<2:43:17,  1.44it/s]
1|11799|Loss: 0.8213649392127991:  46%|████▌     | 11799/25880 [2:25:21<2:40:09,  1.47it/s]
1|11800|Loss: 0.8607184290885925:  46%|████▌     | 11799/25880 [2:25:22<2:40:09,  1.47it/s]
1|11800|Loss: 0.8607184290885925:  46%|████▌     | 11800/25880 [2:25:22<2:46:21,  1.41it/s]
1|11801|Loss: 0.9312047958374023:  46%|████▌     | 11800/25880 [2:25:22<2:46:21,  1.41it/s]
1|11801|Loss: 0.9312047958374023:  46%|████▌     | 11801/25880 [2:25:23<2:52:10,  1.36it/s]
1|11802|Loss: 0.8045106530189514:  46%|████▌     | 11801/25880 [2:25:23<2:52:10,  1.36it/s]
1|11802|Loss: 0.8045106530189514:  46%|████▌     | 11802/25880 [2:25:23<2:47:03,  1.40it/s]
1|11803|Loss: 0.6619504690170288:  46%|████▌     | 11802/25880 [2:25:24<2:47:03,  1.40it/s]
1|11803|Loss: 0.6619504690170288:  46%|████▌     | 11803/25880 [2:25:24<2:50:46,  1.37it/s]
1|11804|Loss: 0.8311380743980408:  46%|████▌     | 11803/25880 [2:25:25<2:50:46,  1.37it/s]
1|11804|Loss: 0.8311380743980408:  46%|████▌     | 11804/25880 [2:25:25<2:52:05,  1.36it/s]
1|11805|Loss: 0.8062241673469543:  46%|████▌     | 11804/25880 [2:25:25<2:52:05,  1.36it/s]
1|11805|Loss: 0.8062241673469543:  46%|████▌     | 11805/25880 [2:25:26<2:51:37,  1.37it/s]
1|11806|Loss: 0.9616773724555969:  46%|████▌     | 11805/25880 [2:25:26<2:51:37,  1.37it/s]
1|11806|Loss: 0.9616773724555969:  46%|████▌     | 11806/25880 [2:25:26<2:42:55,  1.44it/s]
1|11807|Loss: 0.9222093820571899:  46%|████▌     | 11806/25880 [2:25:27<2:42:55,  1.44it/s]
1|11807|Loss: 0.9222093820571899:  46%|████▌     | 11807/25880 [2:25:27<2:41:46,  1.45it/s]
1|11808|Loss: 0.9071193337440491:  46%|████▌     | 11807/25880 [2:25:27<2:41:46,  1.45it/s]
1|11808|Loss: 0.9071193337440491:  46%|████▌     | 11808/25880 [2:25:28<2:38:50,  1.48it/s]
1|11809|Loss: 0.6656680703163147:  46%|████▌     | 11808/25880 [2:25:28<2:38:50,  1.48it/s]
1|11809|Loss: 0.6656680703163147:  46%|████▌     | 11809/25880 [2:25:28<2:41:27,  1.45it/s]
1|11810|Loss: 0.8759470582008362:  46%|████▌     | 11809/25880 [2:25:29<2:41:27,  1.45it/s]
1|11810|Loss: 0.8759470582008362:  46%|████▌     | 11810/25880 [2:25:29<2:38:05,  1.48it/s]
1|11811|Loss: 0.8428962826728821:  46%|████▌     | 11810/25880 [2:25:29<2:38:05,  1.48it/s]
1|11811|Loss: 0.8428962826728821:  46%|████▌     | 11811/25880 [2:25:30<2:39:16,  1.47it/s]
1|11812|Loss: 0.7110685706138611:  46%|████▌     | 11811/25880 [2:25:30<2:39:16,  1.47it/s]
1|11812|Loss: 0.7110685706138611:  46%|████▌     | 11812/25880 [2:25:30<2:48:42,  1.39it/s]
1|11813|Loss: 0.8936370611190796:  46%|████▌     | 11812/25880 [2:25:31<2:48:42,  1.39it/s]
1|11813|Loss: 0.8936370611190796:  46%|████▌     | 11813/25880 [2:25:31<2:49:54,  1.38it/s]
1|11814|Loss: 0.8310250043869019:  46%|████▌     | 11813/25880 [2:25:32<2:49:54,  1.38it/s]
1|11814|Loss: 0.8310250043869019:  46%|████▌     | 11814/25880 [2:25:32<2:53:39,  1.35it/s]
1|11815|Loss: 0.8259298205375671:  46%|████▌     | 11814/25880 [2:25:32<2:53:39,  1.35it/s]
1|11815|Loss: 0.8259298205375671:  46%|████▌     | 11815/25880 [2:25:33<2:56:44,  1.33it/s]
1|11816|Loss: 0.8335267305374146:  46%|████▌     | 11815/25880 [2:25:33<2:56:44,  1.33it/s]
1|11816|Loss: 0.8335267305374146:  46%|████▌     | 11816/25880 [2:25:34<3:03:53,  1.27it/s]
1|11817|Loss: 0.8573792576789856:  46%|████▌     | 11816/25880 [2:25:34<3:03:53,  1.27it/s]
1|11817|Loss: 0.8573792576789856:  46%|████▌     | 11817/25880 [2:25:34<3:02:32,  1.28it/s]
1|11818|Loss: 0.8044440150260925:  46%|████▌     | 11817/25880 [2:25:35<3:02:32,  1.28it/s]
1|11818|Loss: 0.8044440150260925:  46%|████▌     | 11818/25880 [2:25:35<2:52:32,  1.36it/s]
1|11819|Loss: 0.7827565670013428:  46%|████▌     | 11818/25880 [2:25:35<2:52:32,  1.36it/s]
1|11819|Loss: 0.7827565670013428:  46%|████▌     | 11819/25880 [2:25:36<2:48:37,  1.39it/s]
1|11820|Loss: 0.7282557487487793:  46%|████▌     | 11819/25880 [2:25:36<2:48:37,  1.39it/s]
1|11820|Loss: 0.7282557487487793:  46%|████▌     | 11820/25880 [2:25:36<2:49:20,  1.38it/s]
1|11821|Loss: 0.703357994556427:  46%|████▌     | 11820/25880 [2:25:37<2:49:20,  1.38it/s] 
1|11821|Loss: 0.703357994556427:  46%|████▌     | 11821/25880 [2:25:37<2:39:19,  1.47it/s]
1|11822|Loss: 1.0384939908981323:  46%|████▌     | 11821/25880 [2:25:37<2:39:19,  1.47it/s]
1|11822|Loss: 1.0384939908981323:  46%|████▌     | 11822/25880 [2:25:38<2:44:14,  1.43it/s]
1|11823|Loss: 0.8186209797859192:  46%|████▌     | 11822/25880 [2:25:38<2:44:14,  1.43it/s]
1|11823|Loss: 0.8186209797859192:  46%|████▌     | 11823/25880 [2:25:39<2:55:40,  1.33it/s]
1|11824|Loss: 0.7050594687461853:  46%|████▌     | 11823/25880 [2:25:39<2:55:40,  1.33it/s]
1|11824|Loss: 0.7050594687461853:  46%|████▌     | 11824/25880 [2:25:39<2:52:11,  1.36it/s]
1|11825|Loss: 0.9101424813270569:  46%|████▌     | 11824/25880 [2:25:40<2:52:11,  1.36it/s]
1|11825|Loss: 0.9101424813270569:  46%|████▌     | 11825/25880 [2:25:40<2:51:12,  1.37it/s]
1|11826|Loss: 0.8784180283546448:  46%|████▌     | 11825/25880 [2:25:40<2:51:12,  1.37it/s]
1|11826|Loss: 0.8784180283546448:  46%|████▌     | 11826/25880 [2:25:41<2:49:56,  1.38it/s]
1|11827|Loss: 0.9007033109664917:  46%|████▌     | 11826/25880 [2:25:41<2:49:56,  1.38it/s]
1|11827|Loss: 0.9007033109664917:  46%|████▌     | 11827/25880 [2:25:42<2:56:37,  1.33it/s]
1|11828|Loss: 0.8621229529380798:  46%|████▌     | 11827/25880 [2:25:42<2:56:37,  1.33it/s]
1|11828|Loss: 0.8621229529380798:  46%|████▌     | 11828/25880 [2:25:42<3:04:55,  1.27it/s]
1|11829|Loss: 0.8009527921676636:  46%|████▌     | 11828/25880 [2:25:43<3:04:55,  1.27it/s]
1|11829|Loss: 0.8009527921676636:  46%|████▌     | 11829/25880 [2:25:43<2:57:11,  1.32it/s]
1|11830|Loss: 0.7523715496063232:  46%|████▌     | 11829/25880 [2:25:43<2:57:11,  1.32it/s]
1|11830|Loss: 0.7523715496063232:  46%|████▌     | 11830/25880 [2:25:44<2:47:23,  1.40it/s]
1|11831|Loss: 0.9214336276054382:  46%|████▌     | 11830/25880 [2:25:44<2:47:23,  1.40it/s]
1|11831|Loss: 0.9214336276054382:  46%|████▌     | 11831/25880 [2:25:45<2:53:42,  1.35it/s]
1|11832|Loss: 0.748637318611145:  46%|████▌     | 11831/25880 [2:25:45<2:53:42,  1.35it/s] 
1|11832|Loss: 0.748637318611145:  46%|████▌     | 11832/25880 [2:25:45<2:55:03,  1.34it/s]
1|11833|Loss: 0.8218737244606018:  46%|████▌     | 11832/25880 [2:25:46<2:55:03,  1.34it/s]
1|11833|Loss: 0.8218737244606018:  46%|████▌     | 11833/25880 [2:25:46<2:54:41,  1.34it/s]
1|11834|Loss: 0.9023419618606567:  46%|████▌     | 11833/25880 [2:25:46<2:54:41,  1.34it/s]
1|11834|Loss: 0.9023419618606567:  46%|████▌     | 11834/25880 [2:25:47<3:04:14,  1.27it/s]
1|11835|Loss: 0.7094832062721252:  46%|████▌     | 11834/25880 [2:25:47<3:04:14,  1.27it/s]
1|11835|Loss: 0.7094832062721252:  46%|████▌     | 11835/25880 [2:25:48<3:11:18,  1.22it/s]
1|11836|Loss: 0.8668701648712158:  46%|████▌     | 11835/25880 [2:25:48<3:11:18,  1.22it/s]
1|11836|Loss: 0.8668701648712158:  46%|████▌     | 11836/25880 [2:25:48<3:01:46,  1.29it/s]
1|11837|Loss: 0.8610445857048035:  46%|████▌     | 11836/25880 [2:25:49<3:01:46,  1.29it/s]
1|11837|Loss: 0.8610445857048035:  46%|████▌     | 11837/25880 [2:25:49<3:02:25,  1.28it/s]
1|11838|Loss: 0.8909149169921875:  46%|████▌     | 11837/25880 [2:25:50<3:02:25,  1.28it/s]
1|11838|Loss: 0.8909149169921875:  46%|████▌     | 11838/25880 [2:25:50<2:58:23,  1.31it/s]
1|11839|Loss: 0.8503466248512268:  46%|████▌     | 11838/25880 [2:25:50<2:58:23,  1.31it/s]
1|11839|Loss: 0.8503466248512268:  46%|████▌     | 11839/25880 [2:25:51<2:55:39,  1.33it/s]
1|11840|Loss: 0.8523561358451843:  46%|████▌     | 11839/25880 [2:25:51<2:55:39,  1.33it/s]
1|11840|Loss: 0.8523561358451843:  46%|████▌     | 11840/25880 [2:25:52<2:58:10,  1.31it/s]
1|11841|Loss: 0.8492481708526611:  46%|████▌     | 11840/25880 [2:25:52<2:58:10,  1.31it/s]
1|11841|Loss: 0.8492481708526611:  46%|████▌     | 11841/25880 [2:25:52<3:02:23,  1.28it/s]
1|11842|Loss: 0.7120593190193176:  46%|████▌     | 11841/25880 [2:25:53<3:02:23,  1.28it/s]
1|11842|Loss: 0.7120593190193176:  46%|████▌     | 11842/25880 [2:25:53<2:48:44,  1.39it/s]
1|11843|Loss: 0.862928032875061:  46%|████▌     | 11842/25880 [2:25:53<2:48:44,  1.39it/s] 
1|11843|Loss: 0.862928032875061:  46%|████▌     | 11843/25880 [2:25:54<2:41:23,  1.45it/s]
1|11844|Loss: 0.8009107112884521:  46%|████▌     | 11843/25880 [2:25:54<2:41:23,  1.45it/s]
1|11844|Loss: 0.8009107112884521:  46%|████▌     | 11844/25880 [2:25:54<2:49:52,  1.38it/s]
1|11845|Loss: 0.9124548435211182:  46%|████▌     | 11844/25880 [2:25:55<2:49:52,  1.38it/s]
1|11845|Loss: 0.9124548435211182:  46%|████▌     | 11845/25880 [2:25:55<2:52:06,  1.36it/s]
1|11846|Loss: 0.7984063029289246:  46%|████▌     | 11845/25880 [2:25:55<2:52:06,  1.36it/s]
1|11846|Loss: 0.7984063029289246:  46%|████▌     | 11846/25880 [2:25:56<2:50:03,  1.38it/s]
1|11847|Loss: 0.8961581587791443:  46%|████▌     | 11846/25880 [2:25:56<2:50:03,  1.38it/s]
1|11847|Loss: 0.8961581587791443:  46%|████▌     | 11847/25880 [2:25:56<2:38:14,  1.48it/s]
1|11848|Loss: 0.7998384237289429:  46%|████▌     | 11847/25880 [2:25:57<2:38:14,  1.48it/s]
1|11848|Loss: 0.7998384237289429:  46%|████▌     | 11848/25880 [2:25:57<2:37:45,  1.48it/s]
1|11849|Loss: 0.887544572353363:  46%|████▌     | 11848/25880 [2:25:57<2:37:45,  1.48it/s] 
1|11849|Loss: 0.887544572353363:  46%|████▌     | 11849/25880 [2:25:58<2:35:58,  1.50it/s]
1|11850|Loss: 0.8965902924537659:  46%|████▌     | 11849/25880 [2:25:58<2:35:58,  1.50it/s]
1|11850|Loss: 0.8965902924537659:  46%|████▌     | 11850/25880 [2:25:58<2:27:56,  1.58it/s]
1|11851|Loss: 0.8812011480331421:  46%|████▌     | 11850/25880 [2:25:59<2:27:56,  1.58it/s]
1|11851|Loss: 0.8812011480331421:  46%|████▌     | 11851/25880 [2:25:59<2:39:01,  1.47it/s]
1|11852|Loss: 0.8159238696098328:  46%|████▌     | 11851/25880 [2:25:59<2:39:01,  1.47it/s]
1|11852|Loss: 0.8159238696098328:  46%|████▌     | 11852/25880 [2:26:00<2:50:16,  1.37it/s]
1|11853|Loss: 0.8411887884140015:  46%|████▌     | 11852/25880 [2:26:00<2:50:16,  1.37it/s]
1|11853|Loss: 0.8411887884140015:  46%|████▌     | 11853/25880 [2:26:00<2:36:24,  1.49it/s]
1|11854|Loss: 0.9020963311195374:  46%|████▌     | 11853/25880 [2:26:01<2:36:24,  1.49it/s]
1|11854|Loss: 0.9020963311195374:  46%|████▌     | 11854/25880 [2:26:01<2:43:12,  1.43it/s]
1|11855|Loss: 0.88690584897995:  46%|████▌     | 11854/25880 [2:26:02<2:43:12,  1.43it/s]  
1|11855|Loss: 0.88690584897995:  46%|████▌     | 11855/25880 [2:26:02<2:56:32,  1.32it/s]
1|11856|Loss: 0.8736050724983215:  46%|████▌     | 11855/25880 [2:26:02<2:56:32,  1.32it/s]
1|11856|Loss: 0.8736050724983215:  46%|████▌     | 11856/25880 [2:26:03<2:58:35,  1.31it/s]
1|11857|Loss: 1.0067514181137085:  46%|████▌     | 11856/25880 [2:26:03<2:58:35,  1.31it/s]
1|11857|Loss: 1.0067514181137085:  46%|████▌     | 11857/25880 [2:26:04<2:55:37,  1.33it/s]
1|11858|Loss: 0.9190236926078796:  46%|████▌     | 11857/25880 [2:26:04<2:55:37,  1.33it/s]
1|11858|Loss: 0.9190236926078796:  46%|████▌     | 11858/25880 [2:26:04<3:03:37,  1.27it/s]
1|11859|Loss: 0.8555084466934204:  46%|████▌     | 11858/25880 [2:26:05<3:03:37,  1.27it/s]
1|11859|Loss: 0.8555084466934204:  46%|████▌     | 11859/25880 [2:26:05<2:57:23,  1.32it/s]
1|11860|Loss: 0.9119642376899719:  46%|████▌     | 11859/25880 [2:26:06<2:57:23,  1.32it/s]
1|11860|Loss: 0.9119642376899719:  46%|████▌     | 11860/25880 [2:26:06<2:54:45,  1.34it/s]
1|11861|Loss: 0.8458768129348755:  46%|████▌     | 11860/25880 [2:26:06<2:54:45,  1.34it/s]
1|11861|Loss: 0.8458768129348755:  46%|████▌     | 11861/25880 [2:26:07<2:57:30,  1.32it/s]
1|11862|Loss: 0.8813346028327942:  46%|████▌     | 11861/25880 [2:26:07<2:57:30,  1.32it/s]
1|11862|Loss: 0.8813346028327942:  46%|████▌     | 11862/25880 [2:26:07<2:48:22,  1.39it/s]
1|11863|Loss: 0.8674340844154358:  46%|████▌     | 11862/25880 [2:26:08<2:48:22,  1.39it/s]
1|11863|Loss: 0.8674340844154358:  46%|████▌     | 11863/25880 [2:26:08<2:34:28,  1.51it/s]
1|11864|Loss: 0.8255749940872192:  46%|████▌     | 11863/25880 [2:26:08<2:34:28,  1.51it/s]
1|11864|Loss: 0.8255749940872192:  46%|████▌     | 11864/25880 [2:26:08<2:34:36,  1.51it/s]
1|11865|Loss: 0.906913697719574:  46%|████▌     | 11864/25880 [2:26:09<2:34:36,  1.51it/s] 
1|11865|Loss: 0.906913697719574:  46%|████▌     | 11865/25880 [2:26:09<2:45:35,  1.41it/s]
1|11866|Loss: 0.9363483786582947:  46%|████▌     | 11865/25880 [2:26:10<2:45:35,  1.41it/s]
1|11866|Loss: 0.9363483786582947:  46%|████▌     | 11866/25880 [2:26:10<2:47:18,  1.40it/s]
1|11867|Loss: 0.7869903445243835:  46%|████▌     | 11866/25880 [2:26:10<2:47:18,  1.40it/s]
1|11867|Loss: 0.7869903445243835:  46%|████▌     | 11867/25880 [2:26:11<2:41:27,  1.45it/s]
1|11868|Loss: 0.9167075157165527:  46%|████▌     | 11867/25880 [2:26:11<2:41:27,  1.45it/s]
1|11868|Loss: 0.9167075157165527:  46%|████▌     | 11868/25880 [2:26:11<2:36:22,  1.49it/s]
1|11869|Loss: 0.8319708704948425:  46%|████▌     | 11868/25880 [2:26:12<2:36:22,  1.49it/s]
1|11869|Loss: 0.8319708704948425:  46%|████▌     | 11869/25880 [2:26:12<2:46:01,  1.41it/s]
1|11870|Loss: 0.7378301620483398:  46%|████▌     | 11869/25880 [2:26:12<2:46:01,  1.41it/s]
1|11870|Loss: 0.7378301620483398:  46%|████▌     | 11870/25880 [2:26:13<2:34:07,  1.51it/s]
1|11871|Loss: 0.7427771091461182:  46%|████▌     | 11870/25880 [2:26:13<2:34:07,  1.51it/s]
1|11871|Loss: 0.7427771091461182:  46%|████▌     | 11871/25880 [2:26:13<2:35:05,  1.51it/s]
1|11872|Loss: 0.9277743101119995:  46%|████▌     | 11871/25880 [2:26:14<2:35:05,  1.51it/s]
1|11872|Loss: 0.9277743101119995:  46%|████▌     | 11872/25880 [2:26:14<2:50:21,  1.37it/s]
1|11873|Loss: 0.906935453414917:  46%|████▌     | 11872/25880 [2:26:15<2:50:21,  1.37it/s] 
1|11873|Loss: 0.906935453414917:  46%|████▌     | 11873/25880 [2:26:15<2:51:30,  1.36it/s]
1|11874|Loss: 0.8998295068740845:  46%|████▌     | 11873/25880 [2:26:15<2:51:30,  1.36it/s]
1|11874|Loss: 0.8998295068740845:  46%|████▌     | 11874/25880 [2:26:16<2:51:51,  1.36it/s]
1|11875|Loss: 0.8254509568214417:  46%|████▌     | 11874/25880 [2:26:16<2:51:51,  1.36it/s]
1|11875|Loss: 0.8254509568214417:  46%|████▌     | 11875/25880 [2:26:16<2:46:50,  1.40it/s]
1|11876|Loss: 0.8680240511894226:  46%|████▌     | 11875/25880 [2:26:17<2:46:50,  1.40it/s]
1|11876|Loss: 0.8680240511894226:  46%|████▌     | 11876/25880 [2:26:17<2:54:35,  1.34it/s]
1|11877|Loss: 0.7948760390281677:  46%|████▌     | 11876/25880 [2:26:18<2:54:35,  1.34it/s]
1|11877|Loss: 0.7948760390281677:  46%|████▌     | 11877/25880 [2:26:18<2:55:30,  1.33it/s]
1|11878|Loss: 0.7408042550086975:  46%|████▌     | 11877/25880 [2:26:18<2:55:30,  1.33it/s]
1|11878|Loss: 0.7408042550086975:  46%|████▌     | 11878/25880 [2:26:19<3:00:26,  1.29it/s]
1|11879|Loss: 0.8646178245544434:  46%|████▌     | 11878/25880 [2:26:19<3:00:26,  1.29it/s]
1|11879|Loss: 0.8646178245544434:  46%|████▌     | 11879/25880 [2:26:19<2:59:25,  1.30it/s]
1|11880|Loss: 0.8901411890983582:  46%|████▌     | 11879/25880 [2:26:20<2:59:25,  1.30it/s]
1|11880|Loss: 0.8901411890983582:  46%|████▌     | 11880/25880 [2:26:20<2:55:00,  1.33it/s]
1|11881|Loss: 0.895592212677002:  46%|████▌     | 11880/25880 [2:26:21<2:55:00,  1.33it/s] 
1|11881|Loss: 0.895592212677002:  46%|████▌     | 11881/25880 [2:26:21<3:03:39,  1.27it/s]
1|11882|Loss: 0.8311511874198914:  46%|████▌     | 11881/25880 [2:26:21<3:03:39,  1.27it/s]
1|11882|Loss: 0.8311511874198914:  46%|████▌     | 11882/25880 [2:26:22<2:56:58,  1.32it/s]
1|11883|Loss: 0.8793392777442932:  46%|████▌     | 11882/25880 [2:26:22<2:56:58,  1.32it/s]
1|11883|Loss: 0.8793392777442932:  46%|████▌     | 11883/25880 [2:26:22<2:45:01,  1.41it/s]
1|11884|Loss: 0.8273312449455261:  46%|████▌     | 11883/25880 [2:26:23<2:45:01,  1.41it/s]
1|11884|Loss: 0.8273312449455261:  46%|████▌     | 11884/25880 [2:26:23<2:44:47,  1.42it/s]
1|11885|Loss: 0.8670417666435242:  46%|████▌     | 11884/25880 [2:26:23<2:44:47,  1.42it/s]
1|11885|Loss: 0.8670417666435242:  46%|████▌     | 11885/25880 [2:26:24<2:47:41,  1.39it/s]
1|11886|Loss: 0.9020891189575195:  46%|████▌     | 11885/25880 [2:26:24<2:47:41,  1.39it/s]
1|11886|Loss: 0.9020891189575195:  46%|████▌     | 11886/25880 [2:26:24<2:44:00,  1.42it/s]
1|11887|Loss: 0.7613192796707153:  46%|████▌     | 11886/25880 [2:26:25<2:44:00,  1.42it/s]
1|11887|Loss: 0.7613192796707153:  46%|████▌     | 11887/25880 [2:26:25<2:44:38,  1.42it/s]
1|11888|Loss: 0.8177857398986816:  46%|████▌     | 11887/25880 [2:26:25<2:44:38,  1.42it/s]
1|11888|Loss: 0.8177857398986816:  46%|████▌     | 11888/25880 [2:26:26<2:30:33,  1.55it/s]
1|11889|Loss: 0.967890739440918:  46%|████▌     | 11888/25880 [2:26:26<2:30:33,  1.55it/s] 
1|11889|Loss: 0.967890739440918:  46%|████▌     | 11889/25880 [2:26:26<2:32:16,  1.53it/s]
1|11890|Loss: 0.9714197516441345:  46%|████▌     | 11889/25880 [2:26:27<2:32:16,  1.53it/s]
1|11890|Loss: 0.9714197516441345:  46%|████▌     | 11890/25880 [2:26:27<2:44:03,  1.42it/s]
1|11891|Loss: 0.7633729577064514:  46%|████▌     | 11890/25880 [2:26:28<2:44:03,  1.42it/s]
1|11891|Loss: 0.7633729577064514:  46%|████▌     | 11891/25880 [2:26:28<2:41:08,  1.45it/s]
1|11892|Loss: 0.7987819314002991:  46%|████▌     | 11891/25880 [2:26:28<2:41:08,  1.45it/s]
1|11892|Loss: 0.7987819314002991:  46%|████▌     | 11892/25880 [2:26:29<2:49:01,  1.38it/s]
1|11893|Loss: 0.7393070459365845:  46%|████▌     | 11892/25880 [2:26:29<2:49:01,  1.38it/s]
1|11893|Loss: 0.7393070459365845:  46%|████▌     | 11893/25880 [2:26:29<2:46:23,  1.40it/s]
1|11894|Loss: 0.848621666431427:  46%|████▌     | 11893/25880 [2:26:30<2:46:23,  1.40it/s] 
1|11894|Loss: 0.848621666431427:  46%|████▌     | 11894/25880 [2:26:30<2:37:42,  1.48it/s]
1|11895|Loss: 0.7819275259971619:  46%|████▌     | 11894/25880 [2:26:30<2:37:42,  1.48it/s]
1|11895|Loss: 0.7819275259971619:  46%|████▌     | 11895/25880 [2:26:31<2:37:29,  1.48it/s]
1|11896|Loss: 0.8892543911933899:  46%|████▌     | 11895/25880 [2:26:31<2:37:29,  1.48it/s]
1|11896|Loss: 0.8892543911933899:  46%|████▌     | 11896/25880 [2:26:31<2:46:28,  1.40it/s]
1|11897|Loss: 0.9281854033470154:  46%|████▌     | 11896/25880 [2:26:32<2:46:28,  1.40it/s]
1|11897|Loss: 0.9281854033470154:  46%|████▌     | 11897/25880 [2:26:32<2:47:02,  1.40it/s]
1|11898|Loss: 0.8877706527709961:  46%|████▌     | 11897/25880 [2:26:32<2:47:02,  1.40it/s]
1|11898|Loss: 0.8877706527709961:  46%|████▌     | 11898/25880 [2:26:33<2:45:37,  1.41it/s]
1|11899|Loss: 0.8824871182441711:  46%|████▌     | 11898/25880 [2:26:33<2:45:37,  1.41it/s]
1|11899|Loss: 0.8824871182441711:  46%|████▌     | 11899/25880 [2:26:33<2:41:25,  1.44it/s]
1|11900|Loss: 0.7240262627601624:  46%|████▌     | 11899/25880 [2:26:34<2:41:25,  1.44it/s]
1|11900|Loss: 0.7240262627601624:  46%|████▌     | 11900/25880 [2:26:34<2:37:58,  1.47it/s]
1|11901|Loss: 0.7954544425010681:  46%|████▌     | 11900/25880 [2:26:34<2:37:58,  1.47it/s]
1|11901|Loss: 0.7954544425010681:  46%|████▌     | 11901/25880 [2:26:35<2:43:50,  1.42it/s]
1|11902|Loss: 0.8923389911651611:  46%|████▌     | 11901/25880 [2:26:35<2:43:50,  1.42it/s]
1|11902|Loss: 0.8923389911651611:  46%|████▌     | 11902/25880 [2:26:36<2:46:48,  1.40it/s]
1|11903|Loss: 0.9261815547943115:  46%|████▌     | 11902/25880 [2:26:36<2:46:48,  1.40it/s]
1|11903|Loss: 0.9261815547943115:  46%|████▌     | 11903/25880 [2:26:36<2:47:58,  1.39it/s]
1|11904|Loss: 0.8732240796089172:  46%|████▌     | 11903/25880 [2:26:37<2:47:58,  1.39it/s]
1|11904|Loss: 0.8732240796089172:  46%|████▌     | 11904/25880 [2:26:37<2:35:10,  1.50it/s]
1|11905|Loss: 0.9758622646331787:  46%|████▌     | 11904/25880 [2:26:37<2:35:10,  1.50it/s]
1|11905|Loss: 0.9758622646331787:  46%|████▌     | 11905/25880 [2:26:38<2:39:11,  1.46it/s]
1|11906|Loss: 0.8861194849014282:  46%|████▌     | 11905/25880 [2:26:38<2:39:11,  1.46it/s]
1|11906|Loss: 0.8861194849014282:  46%|████▌     | 11906/25880 [2:26:38<2:44:42,  1.41it/s]
1|11907|Loss: 0.8933656811714172:  46%|████▌     | 11906/25880 [2:26:39<2:44:42,  1.41it/s]
1|11907|Loss: 0.8933656811714172:  46%|████▌     | 11907/25880 [2:26:39<2:48:15,  1.38it/s]
1|11908|Loss: 0.8521177172660828:  46%|████▌     | 11907/25880 [2:26:40<2:48:15,  1.38it/s]
1|11908|Loss: 0.8521177172660828:  46%|████▌     | 11908/25880 [2:26:40<2:54:59,  1.33it/s]
1|11909|Loss: 0.916571855545044:  46%|████▌     | 11908/25880 [2:26:40<2:54:59,  1.33it/s] 
1|11909|Loss: 0.916571855545044:  46%|████▌     | 11909/25880 [2:26:41<3:03:19,  1.27it/s]
1|11910|Loss: 0.8410311937332153:  46%|████▌     | 11909/25880 [2:26:41<3:03:19,  1.27it/s]
1|11910|Loss: 0.8410311937332153:  46%|████▌     | 11910/25880 [2:26:42<3:02:33,  1.28it/s]
1|11911|Loss: 0.7472366690635681:  46%|████▌     | 11910/25880 [2:26:42<3:02:33,  1.28it/s]
1|11911|Loss: 0.7472366690635681:  46%|████▌     | 11911/25880 [2:26:42<3:10:17,  1.22it/s]
1|11912|Loss: 0.743548572063446:  46%|████▌     | 11911/25880 [2:26:43<3:10:17,  1.22it/s] 
1|11912|Loss: 0.743548572063446:  46%|████▌     | 11912/25880 [2:26:43<3:12:28,  1.21it/s]
1|11913|Loss: 0.6889549493789673:  46%|████▌     | 11912/25880 [2:26:44<3:12:28,  1.21it/s]
1|11913|Loss: 0.6889549493789673:  46%|████▌     | 11913/25880 [2:26:44<2:58:35,  1.30it/s]
1|11914|Loss: 0.8629408478736877:  46%|████▌     | 11913/25880 [2:26:44<2:58:35,  1.30it/s]
1|11914|Loss: 0.8629408478736877:  46%|████▌     | 11914/25880 [2:26:45<2:52:30,  1.35it/s]
1|11915|Loss: 0.8673177361488342:  46%|████▌     | 11914/25880 [2:26:45<2:52:30,  1.35it/s]
1|11915|Loss: 0.8673177361488342:  46%|████▌     | 11915/25880 [2:26:45<2:49:45,  1.37it/s]
1|11916|Loss: 0.8083683252334595:  46%|████▌     | 11915/25880 [2:26:46<2:49:45,  1.37it/s]
1|11916|Loss: 0.8083683252334595:  46%|████▌     | 11916/25880 [2:26:46<2:33:56,  1.51it/s]
1|11917|Loss: 0.8717952370643616:  46%|████▌     | 11916/25880 [2:26:46<2:33:56,  1.51it/s]
1|11917|Loss: 0.8717952370643616:  46%|████▌     | 11917/25880 [2:26:47<2:40:08,  1.45it/s]
1|11918|Loss: 0.814083456993103:  46%|████▌     | 11917/25880 [2:26:47<2:40:08,  1.45it/s] 
1|11918|Loss: 0.814083456993103:  46%|████▌     | 11918/25880 [2:26:47<2:42:42,  1.43it/s]
1|11919|Loss: 0.7807008028030396:  46%|████▌     | 11918/25880 [2:26:48<2:42:42,  1.43it/s]
1|11919|Loss: 0.7807008028030396:  46%|████▌     | 11919/25880 [2:26:48<2:34:20,  1.51it/s]
1|11920|Loss: 0.8562434911727905:  46%|████▌     | 11919/25880 [2:26:48<2:34:20,  1.51it/s]
1|11920|Loss: 0.8562434911727905:  46%|████▌     | 11920/25880 [2:26:49<2:39:59,  1.45it/s]
1|11921|Loss: 0.7468903064727783:  46%|████▌     | 11920/25880 [2:26:49<2:39:59,  1.45it/s]
1|11921|Loss: 0.7468903064727783:  46%|████▌     | 11921/25880 [2:26:49<2:44:14,  1.42it/s]
1|11922|Loss: 0.9487621784210205:  46%|████▌     | 11921/25880 [2:26:50<2:44:14,  1.42it/s]
1|11922|Loss: 0.9487621784210205:  46%|████▌     | 11922/25880 [2:26:50<2:45:41,  1.40it/s]
1|11923|Loss: 0.911329448223114:  46%|████▌     | 11922/25880 [2:26:51<2:45:41,  1.40it/s] 
1|11923|Loss: 0.911329448223114:  46%|████▌     | 11923/25880 [2:26:51<2:46:41,  1.40it/s]
1|11924|Loss: 1.0554331541061401:  46%|████▌     | 11923/25880 [2:26:51<2:46:41,  1.40it/s]
1|11924|Loss: 1.0554331541061401:  46%|████▌     | 11924/25880 [2:26:52<2:54:20,  1.33it/s]
1|11925|Loss: 1.02456533908844:  46%|████▌     | 11924/25880 [2:26:52<2:54:20,  1.33it/s]  
1|11925|Loss: 1.02456533908844:  46%|████▌     | 11925/25880 [2:26:53<3:01:02,  1.28it/s]
1|11926|Loss: 0.9407198429107666:  46%|████▌     | 11925/25880 [2:26:53<3:01:02,  1.28it/s]
1|11926|Loss: 0.9407198429107666:  46%|████▌     | 11926/25880 [2:26:53<2:57:17,  1.31it/s]
1|11927|Loss: 0.8033930659294128:  46%|████▌     | 11926/25880 [2:26:54<2:57:17,  1.31it/s]
1|11927|Loss: 0.8033930659294128:  46%|████▌     | 11927/25880 [2:26:54<2:42:12,  1.43it/s]
1|11928|Loss: 0.7359979748725891:  46%|████▌     | 11927/25880 [2:26:54<2:42:12,  1.43it/s]
1|11928|Loss: 0.7359979748725891:  46%|████▌     | 11928/25880 [2:26:55<2:45:36,  1.40it/s]
1|11929|Loss: 0.8437517881393433:  46%|████▌     | 11928/25880 [2:26:55<2:45:36,  1.40it/s]
1|11929|Loss: 0.8437517881393433:  46%|████▌     | 11929/25880 [2:26:55<2:46:19,  1.40it/s]
1|11930|Loss: 0.8128954768180847:  46%|████▌     | 11929/25880 [2:26:56<2:46:19,  1.40it/s]
1|11930|Loss: 0.8128954768180847:  46%|████▌     | 11930/25880 [2:26:56<2:47:10,  1.39it/s]
1|11931|Loss: 1.049553632736206:  46%|████▌     | 11930/25880 [2:26:56<2:47:10,  1.39it/s] 
1|11931|Loss: 1.049553632736206:  46%|████▌     | 11931/25880 [2:26:57<2:43:08,  1.43it/s]
1|11932|Loss: 0.8882696628570557:  46%|████▌     | 11931/25880 [2:26:57<2:43:08,  1.43it/s]
1|11932|Loss: 0.8882696628570557:  46%|████▌     | 11932/25880 [2:26:57<2:50:30,  1.36it/s]
1|11933|Loss: 0.7484229207038879:  46%|████▌     | 11932/25880 [2:26:58<2:50:30,  1.36it/s]
1|11933|Loss: 0.7484229207038879:  46%|████▌     | 11933/25880 [2:26:58<2:38:40,  1.46it/s]
1|11934|Loss: 0.8534900546073914:  46%|████▌     | 11933/25880 [2:26:58<2:38:40,  1.46it/s]
1|11934|Loss: 0.8534900546073914:  46%|████▌     | 11934/25880 [2:26:59<2:36:34,  1.48it/s]
1|11935|Loss: 0.910905122756958:  46%|████▌     | 11934/25880 [2:26:59<2:36:34,  1.48it/s] 
1|11935|Loss: 0.910905122756958:  46%|████▌     | 11935/25880 [2:26:59<2:41:01,  1.44it/s]
1|11936|Loss: 0.8639991283416748:  46%|████▌     | 11935/25880 [2:27:00<2:41:01,  1.44it/s]
1|11936|Loss: 0.8639991283416748:  46%|████▌     | 11936/25880 [2:27:00<2:49:40,  1.37it/s]
1|11937|Loss: 0.8926997184753418:  46%|████▌     | 11936/25880 [2:27:01<2:49:40,  1.37it/s]
1|11937|Loss: 0.8926997184753418:  46%|████▌     | 11937/25880 [2:27:01<2:46:00,  1.40it/s]
1|11938|Loss: 0.8487865924835205:  46%|████▌     | 11937/25880 [2:27:01<2:46:00,  1.40it/s]
1|11938|Loss: 0.8487865924835205:  46%|████▌     | 11938/25880 [2:27:02<2:41:10,  1.44it/s]
1|11939|Loss: 0.9447841644287109:  46%|████▌     | 11938/25880 [2:27:02<2:41:10,  1.44it/s]
1|11939|Loss: 0.9447841644287109:  46%|████▌     | 11939/25880 [2:27:02<2:34:05,  1.51it/s]
1|11940|Loss: 0.8216152191162109:  46%|████▌     | 11939/25880 [2:27:03<2:34:05,  1.51it/s]
1|11940|Loss: 0.8216152191162109:  46%|████▌     | 11940/25880 [2:27:03<2:51:08,  1.36it/s]
1|11941|Loss: 0.8563011288642883:  46%|████▌     | 11940/25880 [2:27:03<2:51:08,  1.36it/s]
1|11941|Loss: 0.8563011288642883:  46%|████▌     | 11941/25880 [2:27:04<2:49:45,  1.37it/s]
1|11942|Loss: 0.9537333846092224:  46%|████▌     | 11941/25880 [2:27:04<2:49:45,  1.37it/s]
1|11942|Loss: 0.9537333846092224:  46%|████▌     | 11942/25880 [2:27:04<2:42:07,  1.43it/s]
1|11943|Loss: 0.8687502145767212:  46%|████▌     | 11942/25880 [2:27:05<2:42:07,  1.43it/s]
1|11943|Loss: 0.8687502145767212:  46%|████▌     | 11943/25880 [2:27:05<2:43:08,  1.42it/s]
1|11944|Loss: 0.88588547706604:  46%|████▌     | 11943/25880 [2:27:05<2:43:08,  1.42it/s]  
1|11944|Loss: 0.88588547706604:  46%|████▌     | 11944/25880 [2:27:06<2:43:20,  1.42it/s]
1|11945|Loss: 0.8086642622947693:  46%|████▌     | 11944/25880 [2:27:06<2:43:20,  1.42it/s]
1|11945|Loss: 0.8086642622947693:  46%|████▌     | 11945/25880 [2:27:07<2:48:35,  1.38it/s]
1|11946|Loss: 0.9055611491203308:  46%|████▌     | 11945/25880 [2:27:07<2:48:35,  1.38it/s]
1|11946|Loss: 0.9055611491203308:  46%|████▌     | 11946/25880 [2:27:07<2:56:33,  1.32it/s]
1|11947|Loss: 0.7847567796707153:  46%|████▌     | 11946/25880 [2:27:08<2:56:33,  1.32it/s]
1|11947|Loss: 0.7847567796707153:  46%|████▌     | 11947/25880 [2:27:08<2:51:42,  1.35it/s]
1|11948|Loss: 0.8202952146530151:  46%|████▌     | 11947/25880 [2:27:09<2:51:42,  1.35it/s]
1|11948|Loss: 0.8202952146530151:  46%|████▌     | 11948/25880 [2:27:09<3:08:02,  1.23it/s]
1|11949|Loss: 0.7135493755340576:  46%|████▌     | 11948/25880 [2:27:10<3:08:02,  1.23it/s]
1|11949|Loss: 0.7135493755340576:  46%|████▌     | 11949/25880 [2:27:10<3:07:32,  1.24it/s]
1|11950|Loss: 0.8439080119132996:  46%|████▌     | 11949/25880 [2:27:10<3:07:32,  1.24it/s]
1|11950|Loss: 0.8439080119132996:  46%|████▌     | 11950/25880 [2:27:11<3:00:52,  1.28it/s]
1|11951|Loss: 0.8225796222686768:  46%|████▌     | 11950/25880 [2:27:11<3:00:52,  1.28it/s]
1|11951|Loss: 0.8225796222686768:  46%|████▌     | 11951/25880 [2:27:11<2:57:01,  1.31it/s]
1|11952|Loss: 0.7816715836524963:  46%|████▌     | 11951/25880 [2:27:12<2:57:01,  1.31it/s]
1|11952|Loss: 0.7816715836524963:  46%|████▌     | 11952/25880 [2:27:12<3:04:57,  1.26it/s]
1|11953|Loss: 0.9604387283325195:  46%|████▌     | 11952/25880 [2:27:13<3:04:57,  1.26it/s]
1|11953|Loss: 0.9604387283325195:  46%|████▌     | 11953/25880 [2:27:13<3:11:18,  1.21it/s]
1|11954|Loss: 0.9235764145851135:  46%|████▌     | 11953/25880 [2:27:13<3:11:18,  1.21it/s]
1|11954|Loss: 0.9235764145851135:  46%|████▌     | 11954/25880 [2:27:14<3:01:08,  1.28it/s]
1|11955|Loss: 0.8593220710754395:  46%|████▌     | 11954/25880 [2:27:14<3:01:08,  1.28it/s]
1|11955|Loss: 0.8593220710754395:  46%|████▌     | 11955/25880 [2:27:15<3:02:47,  1.27it/s]
1|11956|Loss: 0.8014767169952393:  46%|████▌     | 11955/25880 [2:27:15<3:02:47,  1.27it/s]
1|11956|Loss: 0.8014767169952393:  46%|████▌     | 11956/25880 [2:27:15<3:08:34,  1.23it/s]
1|11957|Loss: 0.7262125611305237:  46%|████▌     | 11956/25880 [2:27:16<3:08:34,  1.23it/s]
1|11957|Loss: 0.7262125611305237:  46%|████▌     | 11957/25880 [2:27:16<3:13:13,  1.20it/s]
1|11958|Loss: 0.8798274397850037:  46%|████▌     | 11957/25880 [2:27:17<3:13:13,  1.20it/s]
1|11958|Loss: 0.8798274397850037:  46%|████▌     | 11958/25880 [2:27:17<3:16:45,  1.18it/s]
1|11959|Loss: 0.8596621155738831:  46%|████▌     | 11958/25880 [2:27:18<3:16:45,  1.18it/s]
1|11959|Loss: 0.8596621155738831:  46%|████▌     | 11959/25880 [2:27:18<3:11:25,  1.21it/s]
1|11960|Loss: 0.8465697765350342:  46%|████▌     | 11959/25880 [2:27:18<3:11:25,  1.21it/s]
1|11960|Loss: 0.8465697765350342:  46%|████▌     | 11960/25880 [2:27:19<3:04:54,  1.25it/s]
1|11961|Loss: 0.9798411130905151:  46%|████▌     | 11960/25880 [2:27:19<3:04:54,  1.25it/s]
1|11961|Loss: 0.9798411130905151:  46%|████▌     | 11961/25880 [2:27:19<3:01:10,  1.28it/s]
1|11962|Loss: 0.8950541019439697:  46%|████▌     | 11961/25880 [2:27:20<3:01:10,  1.28it/s]
1|11962|Loss: 0.8950541019439697:  46%|████▌     | 11962/25880 [2:27:20<3:08:47,  1.23it/s]
1|11963|Loss: 0.9248668551445007:  46%|████▌     | 11962/25880 [2:27:21<3:08:47,  1.23it/s]
1|11963|Loss: 0.9248668551445007:  46%|████▌     | 11963/25880 [2:27:21<3:15:58,  1.18it/s]
1|11964|Loss: 0.7954434156417847:  46%|████▌     | 11963/25880 [2:27:22<3:15:58,  1.18it/s]
1|11964|Loss: 0.7954434156417847:  46%|████▌     | 11964/25880 [2:27:22<3:04:08,  1.26it/s]
1|11965|Loss: 0.6955969929695129:  46%|████▌     | 11964/25880 [2:27:22<3:04:08,  1.26it/s]
1|11965|Loss: 0.6955969929695129:  46%|████▌     | 11965/25880 [2:27:23<2:50:00,  1.36it/s]
1|11966|Loss: 0.7938712239265442:  46%|████▌     | 11965/25880 [2:27:23<2:50:00,  1.36it/s]
1|11966|Loss: 0.7938712239265442:  46%|████▌     | 11966/25880 [2:27:23<2:48:06,  1.38it/s]
1|11967|Loss: 0.7944931387901306:  46%|████▌     | 11966/25880 [2:27:24<2:48:06,  1.38it/s]
1|11967|Loss: 0.7944931387901306:  46%|████▌     | 11967/25880 [2:27:24<2:47:18,  1.39it/s]
1|11968|Loss: 0.7459793090820312:  46%|████▌     | 11967/25880 [2:27:24<2:47:18,  1.39it/s]
1|11968|Loss: 0.7459793090820312:  46%|████▌     | 11968/25880 [2:27:25<2:45:33,  1.40it/s]
1|11969|Loss: 0.8510629534721375:  46%|████▌     | 11968/25880 [2:27:25<2:45:33,  1.40it/s]
1|11969|Loss: 0.8510629534721375:  46%|████▌     | 11969/25880 [2:27:25<2:46:19,  1.39it/s]
1|11970|Loss: 0.9087110757827759:  46%|████▌     | 11969/25880 [2:27:26<2:46:19,  1.39it/s]
1|11970|Loss: 0.9087110757827759:  46%|████▋     | 11970/25880 [2:27:26<2:34:53,  1.50it/s]
1|11971|Loss: 0.8658381700515747:  46%|████▋     | 11970/25880 [2:27:26<2:34:53,  1.50it/s]
1|11971|Loss: 0.8658381700515747:  46%|████▋     | 11971/25880 [2:27:27<2:35:56,  1.49it/s]
1|11972|Loss: 0.8980688452720642:  46%|████▋     | 11971/25880 [2:27:27<2:35:56,  1.49it/s]
1|11972|Loss: 0.8980688452720642:  46%|████▋     | 11972/25880 [2:27:27<2:24:33,  1.60it/s]
1|11973|Loss: 0.7581391334533691:  46%|████▋     | 11972/25880 [2:27:27<2:24:33,  1.60it/s]
1|11973|Loss: 0.7581391334533691:  46%|████▋     | 11973/25880 [2:27:28<2:22:47,  1.62it/s]
1|11974|Loss: 0.9277154207229614:  46%|████▋     | 11973/25880 [2:27:28<2:22:47,  1.62it/s]
1|11974|Loss: 0.9277154207229614:  46%|████▋     | 11974/25880 [2:27:28<2:27:34,  1.57it/s]
1|11975|Loss: 0.8596783876419067:  46%|████▋     | 11974/25880 [2:27:29<2:27:34,  1.57it/s]
1|11975|Loss: 0.8596783876419067:  46%|████▋     | 11975/25880 [2:27:29<2:36:31,  1.48it/s]
1|11976|Loss: 0.7884860634803772:  46%|████▋     | 11975/25880 [2:27:30<2:36:31,  1.48it/s]
1|11976|Loss: 0.7884860634803772:  46%|████▋     | 11976/25880 [2:27:30<2:36:41,  1.48it/s]
1|11977|Loss: 0.8720643520355225:  46%|████▋     | 11976/25880 [2:27:30<2:36:41,  1.48it/s]
1|11977|Loss: 0.8720643520355225:  46%|████▋     | 11977/25880 [2:27:31<2:52:15,  1.35it/s]
1|11978|Loss: 0.7758042216300964:  46%|████▋     | 11977/25880 [2:27:31<2:52:15,  1.35it/s]
1|11978|Loss: 0.7758042216300964:  46%|████▋     | 11978/25880 [2:27:32<2:59:56,  1.29it/s]
1|11979|Loss: 0.9160341024398804:  46%|████▋     | 11978/25880 [2:27:32<2:59:56,  1.29it/s]
1|11979|Loss: 0.9160341024398804:  46%|████▋     | 11979/25880 [2:27:32<2:52:09,  1.35it/s]
1|11980|Loss: 0.8599750995635986:  46%|████▋     | 11979/25880 [2:27:33<2:52:09,  1.35it/s]
1|11980|Loss: 0.8599750995635986:  46%|████▋     | 11980/25880 [2:27:33<2:48:41,  1.37it/s]
1|11981|Loss: 0.7716063857078552:  46%|████▋     | 11980/25880 [2:27:33<2:48:41,  1.37it/s]
1|11981|Loss: 0.7716063857078552:  46%|████▋     | 11981/25880 [2:27:34<2:48:25,  1.38it/s]
1|11982|Loss: 0.7978904843330383:  46%|████▋     | 11981/25880 [2:27:34<2:48:25,  1.38it/s]
1|11982|Loss: 0.7978904843330383:  46%|████▋     | 11982/25880 [2:27:34<2:48:49,  1.37it/s]
1|11983|Loss: 0.933294951915741:  46%|████▋     | 11982/25880 [2:27:35<2:48:49,  1.37it/s] 
1|11983|Loss: 0.933294951915741:  46%|████▋     | 11983/25880 [2:27:35<2:55:11,  1.32it/s]
1|11984|Loss: 0.8098677396774292:  46%|████▋     | 11983/25880 [2:27:36<2:55:11,  1.32it/s]
1|11984|Loss: 0.8098677396774292:  46%|████▋     | 11984/25880 [2:27:36<3:04:07,  1.26it/s]
1|11985|Loss: 0.7818772792816162:  46%|████▋     | 11984/25880 [2:27:37<3:04:07,  1.26it/s]
1|11985|Loss: 0.7818772792816162:  46%|████▋     | 11985/25880 [2:27:37<2:55:54,  1.32it/s]
1|11986|Loss: 0.8033596873283386:  46%|████▋     | 11985/25880 [2:27:37<2:55:54,  1.32it/s]
1|11986|Loss: 0.8033596873283386:  46%|████▋     | 11986/25880 [2:27:38<3:00:43,  1.28it/s]
1|11987|Loss: 0.8924745917320251:  46%|████▋     | 11986/25880 [2:27:38<3:00:43,  1.28it/s]
1|11987|Loss: 0.8924745917320251:  46%|████▋     | 11987/25880 [2:27:38<2:53:16,  1.34it/s]
1|11988|Loss: 0.767072319984436:  46%|████▋     | 11987/25880 [2:27:39<2:53:16,  1.34it/s] 
1|11988|Loss: 0.767072319984436:  46%|████▋     | 11988/25880 [2:27:39<2:54:10,  1.33it/s]
1|11989|Loss: 0.9076482653617859:  46%|████▋     | 11988/25880 [2:27:39<2:54:10,  1.33it/s]
1|11989|Loss: 0.9076482653617859:  46%|████▋     | 11989/25880 [2:27:40<2:45:30,  1.40it/s]
1|11990|Loss: 0.7131810188293457:  46%|████▋     | 11989/25880 [2:27:40<2:45:30,  1.40it/s]
1|11990|Loss: 0.7131810188293457:  46%|████▋     | 11990/25880 [2:27:40<2:37:53,  1.47it/s]
1|11991|Loss: 0.8110548853874207:  46%|████▋     | 11990/25880 [2:27:41<2:37:53,  1.47it/s]
1|11991|Loss: 0.8110548853874207:  46%|████▋     | 11991/25880 [2:27:41<2:39:43,  1.45it/s]
1|11992|Loss: 0.8922834992408752:  46%|████▋     | 11991/25880 [2:27:41<2:39:43,  1.45it/s]
1|11992|Loss: 0.8922834992408752:  46%|████▋     | 11992/25880 [2:27:42<2:48:01,  1.38it/s]
1|11993|Loss: 0.9145046472549438:  46%|████▋     | 11992/25880 [2:27:42<2:48:01,  1.38it/s]
1|11993|Loss: 0.9145046472549438:  46%|████▋     | 11993/25880 [2:27:43<2:48:55,  1.37it/s]
1|11994|Loss: 0.8039052486419678:  46%|████▋     | 11993/25880 [2:27:43<2:48:55,  1.37it/s]
1|11994|Loss: 0.8039052486419678:  46%|████▋     | 11994/25880 [2:27:43<2:49:20,  1.37it/s]
1|11995|Loss: 0.8500100374221802:  46%|████▋     | 11994/25880 [2:27:44<2:49:20,  1.37it/s]
1|11995|Loss: 0.8500100374221802:  46%|████▋     | 11995/25880 [2:27:44<2:57:35,  1.30it/s]
1|11996|Loss: 0.8023210763931274:  46%|████▋     | 11995/25880 [2:27:45<2:57:35,  1.30it/s]
1|11996|Loss: 0.8023210763931274:  46%|████▋     | 11996/25880 [2:27:45<3:07:57,  1.23it/s]
1|11997|Loss: 0.9135687947273254:  46%|████▋     | 11996/25880 [2:27:45<3:07:57,  1.23it/s]
1|11997|Loss: 0.9135687947273254:  46%|████▋     | 11997/25880 [2:27:46<3:04:41,  1.25it/s]
1|11998|Loss: 0.8638312220573425:  46%|████▋     | 11997/25880 [2:27:46<3:04:41,  1.25it/s]
1|11998|Loss: 0.8638312220573425:  46%|████▋     | 11998/25880 [2:27:46<2:54:54,  1.32it/s]
1|11999|Loss: 0.9345263838768005:  46%|████▋     | 11998/25880 [2:27:47<2:54:54,  1.32it/s]
1|11999|Loss: 0.9345263838768005:  46%|████▋     | 11999/25880 [2:27:47<2:45:54,  1.39it/s]
1|12000|Loss: 0.7612314820289612:  46%|████▋     | 11999/25880 [2:27:47<2:45:54,  1.39it/s]
1|12000|Loss: 0.7612314820289612:  46%|████▋     | 12000/25880 [2:27:48<2:39:07,  1.45it/s]
1|12001|Loss: 1.0063101053237915:  46%|████▋     | 12000/25880 [2:27:48<2:39:07,  1.45it/s]
1|12001|Loss: 1.0063101053237915:  46%|████▋     | 12001/25880 [2:27:48<2:44:07,  1.41it/s]
1|12002|Loss: 0.8689844012260437:  46%|████▋     | 12001/25880 [2:27:49<2:44:07,  1.41it/s]
1|12002|Loss: 0.8689844012260437:  46%|████▋     | 12002/25880 [2:27:49<2:47:30,  1.38it/s]
1|12003|Loss: 0.7848902940750122:  46%|████▋     | 12002/25880 [2:27:50<2:47:30,  1.38it/s]
1|12003|Loss: 0.7848902940750122:  46%|████▋     | 12003/25880 [2:27:50<2:42:08,  1.43it/s]
1|12004|Loss: 0.8052721619606018:  46%|████▋     | 12003/25880 [2:27:50<2:42:08,  1.43it/s]
1|12004|Loss: 0.8052721619606018:  46%|████▋     | 12004/25880 [2:27:50<2:34:32,  1.50it/s]
1|12005|Loss: 0.7933629751205444:  46%|████▋     | 12004/25880 [2:27:51<2:34:32,  1.50it/s]
1|12005|Loss: 0.7933629751205444:  46%|████▋     | 12005/25880 [2:27:51<2:29:07,  1.55it/s]
1|12006|Loss: 0.7305471897125244:  46%|████▋     | 12005/25880 [2:27:51<2:29:07,  1.55it/s]
1|12006|Loss: 0.7305471897125244:  46%|████▋     | 12006/25880 [2:27:52<2:33:41,  1.50it/s]
1|12007|Loss: 0.9344727396965027:  46%|████▋     | 12006/25880 [2:27:52<2:33:41,  1.50it/s]
1|12007|Loss: 0.9344727396965027:  46%|████▋     | 12007/25880 [2:27:53<2:39:47,  1.45it/s]
1|12008|Loss: 0.9414279460906982:  46%|████▋     | 12007/25880 [2:27:53<2:39:47,  1.45it/s]
1|12008|Loss: 0.9414279460906982:  46%|████▋     | 12008/25880 [2:27:53<2:38:11,  1.46it/s]
1|12009|Loss: 0.802131175994873:  46%|████▋     | 12008/25880 [2:27:54<2:38:11,  1.46it/s] 
1|12009|Loss: 0.802131175994873:  46%|████▋     | 12009/25880 [2:27:54<2:39:03,  1.45it/s]
1|12010|Loss: 0.8113988041877747:  46%|████▋     | 12009/25880 [2:27:54<2:39:03,  1.45it/s]
1|12010|Loss: 0.8113988041877747:  46%|████▋     | 12010/25880 [2:27:55<2:35:32,  1.49it/s]
1|12011|Loss: 0.7207695245742798:  46%|████▋     | 12010/25880 [2:27:55<2:35:32,  1.49it/s]
1|12011|Loss: 0.7207695245742798:  46%|████▋     | 12011/25880 [2:27:55<2:38:38,  1.46it/s]
1|12012|Loss: 0.8544749021530151:  46%|████▋     | 12011/25880 [2:27:56<2:38:38,  1.46it/s]
1|12012|Loss: 0.8544749021530151:  46%|████▋     | 12012/25880 [2:27:56<2:37:17,  1.47it/s]
1|12013|Loss: 0.7640390396118164:  46%|████▋     | 12012/25880 [2:27:56<2:37:17,  1.47it/s]
1|12013|Loss: 0.7640390396118164:  46%|████▋     | 12013/25880 [2:27:57<2:46:21,  1.39it/s]
1|12014|Loss: 0.9086396098136902:  46%|████▋     | 12013/25880 [2:27:57<2:46:21,  1.39it/s]
1|12014|Loss: 0.9086396098136902:  46%|████▋     | 12014/25880 [2:27:57<2:47:46,  1.38it/s]
1|12015|Loss: 0.8088260889053345:  46%|████▋     | 12014/25880 [2:27:58<2:47:46,  1.38it/s]
1|12015|Loss: 0.8088260889053345:  46%|████▋     | 12015/25880 [2:27:58<2:47:57,  1.38it/s]
1|12016|Loss: 0.6505742073059082:  46%|████▋     | 12015/25880 [2:27:59<2:47:57,  1.38it/s]
1|12016|Loss: 0.6505742073059082:  46%|████▋     | 12016/25880 [2:27:59<2:46:56,  1.38it/s]
1|12017|Loss: 0.8085228204727173:  46%|████▋     | 12016/25880 [2:27:59<2:46:56,  1.38it/s]
1|12017|Loss: 0.8085228204727173:  46%|████▋     | 12017/25880 [2:28:00<2:53:39,  1.33it/s]
1|12018|Loss: 0.7286204099655151:  46%|████▋     | 12017/25880 [2:28:00<2:53:39,  1.33it/s]
1|12018|Loss: 0.7286204099655151:  46%|████▋     | 12018/25880 [2:28:01<2:59:40,  1.29it/s]
1|12019|Loss: 0.810043454170227:  46%|████▋     | 12018/25880 [2:28:01<2:59:40,  1.29it/s] 
1|12019|Loss: 0.810043454170227:  46%|████▋     | 12019/25880 [2:28:01<2:58:15,  1.30it/s]
1|12020|Loss: 0.6478741765022278:  46%|████▋     | 12019/25880 [2:28:02<2:58:15,  1.30it/s]
1|12020|Loss: 0.6478741765022278:  46%|████▋     | 12020/25880 [2:28:02<2:43:39,  1.41it/s]
1|12021|Loss: 0.8441281318664551:  46%|████▋     | 12020/25880 [2:28:03<2:43:39,  1.41it/s]
1|12021|Loss: 0.8441281318664551:  46%|████▋     | 12021/25880 [2:28:03<3:32:49,  1.09it/s]
1|12022|Loss: 0.8623343706130981:  46%|████▋     | 12021/25880 [2:28:04<3:32:49,  1.09it/s]
1|12022|Loss: 0.8623343706130981:  46%|████▋     | 12022/25880 [2:28:04<3:12:11,  1.20it/s]
1|12023|Loss: 0.8811678886413574:  46%|████▋     | 12022/25880 [2:28:04<3:12:11,  1.20it/s]
1|12023|Loss: 0.8811678886413574:  46%|████▋     | 12023/25880 [2:28:05<3:03:58,  1.26it/s]
1|12024|Loss: 0.8485339283943176:  46%|████▋     | 12023/25880 [2:28:05<3:03:58,  1.26it/s]
1|12024|Loss: 0.8485339283943176:  46%|████▋     | 12024/25880 [2:28:05<2:53:21,  1.33it/s]
1|12025|Loss: 0.776141345500946:  46%|████▋     | 12024/25880 [2:28:06<2:53:21,  1.33it/s] 
1|12025|Loss: 0.776141345500946:  46%|████▋     | 12025/25880 [2:28:06<2:48:34,  1.37it/s]
1|12026|Loss: 0.7939040064811707:  46%|████▋     | 12025/25880 [2:28:06<2:48:34,  1.37it/s]
1|12026|Loss: 0.7939040064811707:  46%|████▋     | 12026/25880 [2:28:07<2:46:27,  1.39it/s]
1|12027|Loss: 0.9652670621871948:  46%|████▋     | 12026/25880 [2:28:07<2:46:27,  1.39it/s]
1|12027|Loss: 0.9652670621871948:  46%|████▋     | 12027/25880 [2:28:07<2:46:52,  1.38it/s]
1|12028|Loss: 0.8150410652160645:  46%|████▋     | 12027/25880 [2:28:08<2:46:52,  1.38it/s]
1|12028|Loss: 0.8150410652160645:  46%|████▋     | 12028/25880 [2:28:08<2:46:37,  1.39it/s]
1|12029|Loss: 0.8465486168861389:  46%|████▋     | 12028/25880 [2:28:09<2:46:37,  1.39it/s]
1|12029|Loss: 0.8465486168861389:  46%|████▋     | 12029/25880 [2:28:09<2:47:08,  1.38it/s]
1|12030|Loss: 0.9572179913520813:  46%|████▋     | 12029/25880 [2:28:09<2:47:08,  1.38it/s]
1|12030|Loss: 0.9572179913520813:  46%|████▋     | 12030/25880 [2:28:10<2:48:11,  1.37it/s]
1|12031|Loss: 0.9320797920227051:  46%|████▋     | 12030/25880 [2:28:10<2:48:11,  1.37it/s]
1|12031|Loss: 0.9320797920227051:  46%|████▋     | 12031/25880 [2:28:10<2:48:46,  1.37it/s]
1|12032|Loss: 0.7659207582473755:  46%|████▋     | 12031/25880 [2:28:11<2:48:46,  1.37it/s]
1|12032|Loss: 0.7659207582473755:  46%|████▋     | 12032/25880 [2:28:11<2:41:22,  1.43it/s]
1|12033|Loss: 0.884490430355072:  46%|████▋     | 12032/25880 [2:28:11<2:41:22,  1.43it/s] 
1|12033|Loss: 0.884490430355072:  46%|████▋     | 12033/25880 [2:28:12<2:51:51,  1.34it/s]
1|12034|Loss: 0.8121346235275269:  46%|████▋     | 12033/25880 [2:28:12<2:51:51,  1.34it/s]
1|12034|Loss: 0.8121346235275269:  46%|████▋     | 12034/25880 [2:28:13<2:54:01,  1.33it/s]
1|12035|Loss: 0.8333417177200317:  46%|████▋     | 12034/25880 [2:28:13<2:54:01,  1.33it/s]
1|12035|Loss: 0.8333417177200317:  47%|████▋     | 12035/25880 [2:28:13<2:53:35,  1.33it/s]
1|12036|Loss: 0.7048825025558472:  47%|████▋     | 12035/25880 [2:28:14<2:53:35,  1.33it/s]
1|12036|Loss: 0.7048825025558472:  47%|████▋     | 12036/25880 [2:28:14<2:58:14,  1.29it/s]
1|12037|Loss: 0.8075153231620789:  47%|████▋     | 12036/25880 [2:28:15<2:58:14,  1.29it/s]
1|12037|Loss: 0.8075153231620789:  47%|████▋     | 12037/25880 [2:28:15<2:56:32,  1.31it/s]
1|12038|Loss: 0.8165087699890137:  47%|████▋     | 12037/25880 [2:28:15<2:56:32,  1.31it/s]
1|12038|Loss: 0.8165087699890137:  47%|████▋     | 12038/25880 [2:28:16<3:00:30,  1.28it/s]
1|12039|Loss: 0.720805287361145:  47%|████▋     | 12038/25880 [2:28:16<3:00:30,  1.28it/s] 
1|12039|Loss: 0.720805287361145:  47%|████▋     | 12039/25880 [2:28:16<2:43:45,  1.41it/s]
1|12040|Loss: 0.7874811887741089:  47%|████▋     | 12039/25880 [2:28:17<2:43:45,  1.41it/s]
1|12040|Loss: 0.7874811887741089:  47%|████▋     | 12040/25880 [2:28:17<2:46:44,  1.38it/s]
1|12041|Loss: 0.8918779492378235:  47%|████▋     | 12040/25880 [2:28:17<2:46:44,  1.38it/s]
1|12041|Loss: 0.8918779492378235:  47%|████▋     | 12041/25880 [2:28:18<2:54:01,  1.33it/s]
1|12042|Loss: 0.8682517409324646:  47%|████▋     | 12041/25880 [2:28:18<2:54:01,  1.33it/s]
1|12042|Loss: 0.8682517409324646:  47%|████▋     | 12042/25880 [2:28:19<2:53:23,  1.33it/s]
1|12043|Loss: 0.8342360258102417:  47%|████▋     | 12042/25880 [2:28:19<2:53:23,  1.33it/s]
1|12043|Loss: 0.8342360258102417:  47%|████▋     | 12043/25880 [2:28:19<2:55:49,  1.31it/s]
1|12044|Loss: 0.9129074215888977:  47%|████▋     | 12043/25880 [2:28:20<2:55:49,  1.31it/s]
1|12044|Loss: 0.9129074215888977:  47%|████▋     | 12044/25880 [2:28:20<2:54:27,  1.32it/s]
1|12045|Loss: 0.8252495527267456:  47%|████▋     | 12044/25880 [2:28:20<2:54:27,  1.32it/s]
1|12045|Loss: 0.8252495527267456:  47%|████▋     | 12045/25880 [2:28:21<2:46:13,  1.39it/s]
1|12046|Loss: 0.7450075149536133:  47%|████▋     | 12045/25880 [2:28:21<2:46:13,  1.39it/s]
1|12046|Loss: 0.7450075149536133:  47%|████▋     | 12046/25880 [2:28:21<2:40:02,  1.44it/s]
1|12047|Loss: 0.8134371042251587:  47%|████▋     | 12046/25880 [2:28:22<2:40:02,  1.44it/s]
1|12047|Loss: 0.8134371042251587:  47%|████▋     | 12047/25880 [2:28:22<2:39:53,  1.44it/s]
1|12048|Loss: 0.8129407167434692:  47%|████▋     | 12047/25880 [2:28:22<2:39:53,  1.44it/s]
1|12048|Loss: 0.8129407167434692:  47%|████▋     | 12048/25880 [2:28:23<2:47:01,  1.38it/s]
1|12049|Loss: 0.8019813299179077:  47%|████▋     | 12048/25880 [2:28:23<2:47:01,  1.38it/s]
1|12049|Loss: 0.8019813299179077:  47%|████▋     | 12049/25880 [2:28:24<2:48:18,  1.37it/s]
1|12050|Loss: 0.7602018713951111:  47%|████▋     | 12049/25880 [2:28:24<2:48:18,  1.37it/s]
1|12050|Loss: 0.7602018713951111:  47%|████▋     | 12050/25880 [2:28:24<2:51:57,  1.34it/s]
1|12051|Loss: 0.9427706003189087:  47%|████▋     | 12050/25880 [2:28:25<2:51:57,  1.34it/s]
1|12051|Loss: 0.9427706003189087:  47%|████▋     | 12051/25880 [2:28:25<2:49:47,  1.36it/s]
1|12052|Loss: 0.8855398297309875:  47%|████▋     | 12051/25880 [2:28:26<2:49:47,  1.36it/s]
1|12052|Loss: 0.8855398297309875:  47%|████▋     | 12052/25880 [2:28:26<2:48:34,  1.37it/s]
1|12053|Loss: 0.8447911739349365:  47%|████▋     | 12052/25880 [2:28:26<2:48:34,  1.37it/s]
1|12053|Loss: 0.8447911739349365:  47%|████▋     | 12053/25880 [2:28:26<2:43:27,  1.41it/s]
1|12054|Loss: 0.7179709672927856:  47%|████▋     | 12053/25880 [2:28:27<2:43:27,  1.41it/s]
1|12054|Loss: 0.7179709672927856:  47%|████▋     | 12054/25880 [2:28:27<2:50:16,  1.35it/s]
1|12055|Loss: 0.9240676164627075:  47%|████▋     | 12054/25880 [2:28:28<2:50:16,  1.35it/s]
1|12055|Loss: 0.9240676164627075:  47%|████▋     | 12055/25880 [2:28:28<3:04:13,  1.25it/s]
1|12056|Loss: 0.8125720024108887:  47%|████▋     | 12055/25880 [2:28:29<3:04:13,  1.25it/s]
1|12056|Loss: 0.8125720024108887:  47%|████▋     | 12056/25880 [2:28:29<3:08:22,  1.22it/s]
1|12057|Loss: 0.840021014213562:  47%|████▋     | 12056/25880 [2:28:30<3:08:22,  1.22it/s] 
1|12057|Loss: 0.840021014213562:  47%|████▋     | 12057/25880 [2:28:30<3:12:13,  1.20it/s]
1|12058|Loss: 0.977192223072052:  47%|████▋     | 12057/25880 [2:28:30<3:12:13,  1.20it/s]
1|12058|Loss: 0.977192223072052:  47%|████▋     | 12058/25880 [2:28:31<3:07:26,  1.23it/s]
1|12059|Loss: 0.9648106098175049:  47%|████▋     | 12058/25880 [2:28:31<3:07:26,  1.23it/s]
1|12059|Loss: 0.9648106098175049:  47%|████▋     | 12059/25880 [2:28:32<3:08:35,  1.22it/s]
1|12060|Loss: 0.8210357427597046:  47%|████▋     | 12059/25880 [2:28:32<3:08:35,  1.22it/s]
1|12060|Loss: 0.8210357427597046:  47%|████▋     | 12060/25880 [2:28:32<3:04:44,  1.25it/s]
1|12061|Loss: 0.875737726688385:  47%|████▋     | 12060/25880 [2:28:33<3:04:44,  1.25it/s] 
1|12061|Loss: 0.875737726688385:  47%|████▋     | 12061/25880 [2:28:33<2:58:39,  1.29it/s]
1|12062|Loss: 0.8288225531578064:  47%|████▋     | 12061/25880 [2:28:33<2:58:39,  1.29it/s]
1|12062|Loss: 0.8288225531578064:  47%|████▋     | 12062/25880 [2:28:34<2:55:27,  1.31it/s]
1|12063|Loss: 0.8693233728408813:  47%|████▋     | 12062/25880 [2:28:34<2:55:27,  1.31it/s]
1|12063|Loss: 0.8693233728408813:  47%|████▋     | 12063/25880 [2:28:34<2:43:37,  1.41it/s]
1|12064|Loss: 0.9272149801254272:  47%|████▋     | 12063/25880 [2:28:35<2:43:37,  1.41it/s]
1|12064|Loss: 0.9272149801254272:  47%|████▋     | 12064/25880 [2:28:35<2:33:55,  1.50it/s]
1|12065|Loss: 0.9049103856086731:  47%|████▋     | 12064/25880 [2:28:35<2:33:55,  1.50it/s]
1|12065|Loss: 0.9049103856086731:  47%|████▋     | 12065/25880 [2:28:36<2:30:26,  1.53it/s]
1|12066|Loss: 0.845565676689148:  47%|████▋     | 12065/25880 [2:28:36<2:30:26,  1.53it/s] 
1|12066|Loss: 0.845565676689148:  47%|████▋     | 12066/25880 [2:28:36<2:47:24,  1.38it/s]
1|12067|Loss: 0.82549649477005:  47%|████▋     | 12066/25880 [2:28:37<2:47:24,  1.38it/s] 
1|12067|Loss: 0.82549649477005:  47%|████▋     | 12067/25880 [2:28:37<2:35:27,  1.48it/s]
1|12068|Loss: 0.8896402716636658:  47%|████▋     | 12067/25880 [2:28:37<2:35:27,  1.48it/s]
1|12068|Loss: 0.8896402716636658:  47%|████▋     | 12068/25880 [2:28:38<2:28:53,  1.55it/s]
1|12069|Loss: 0.7460590600967407:  47%|████▋     | 12068/25880 [2:28:38<2:28:53,  1.55it/s]
1|12069|Loss: 0.7460590600967407:  47%|████▋     | 12069/25880 [2:28:38<2:27:59,  1.56it/s]
1|12070|Loss: 0.7598688006401062:  47%|████▋     | 12069/25880 [2:28:39<2:27:59,  1.56it/s]
1|12070|Loss: 0.7598688006401062:  47%|████▋     | 12070/25880 [2:28:39<2:43:33,  1.41it/s]
1|12071|Loss: 0.7884090542793274:  47%|████▋     | 12070/25880 [2:28:40<2:43:33,  1.41it/s]
1|12071|Loss: 0.7884090542793274:  47%|████▋     | 12071/25880 [2:28:40<2:47:45,  1.37it/s]
1|12072|Loss: 0.8387522101402283:  47%|████▋     | 12071/25880 [2:28:40<2:47:45,  1.37it/s]
1|12072|Loss: 0.8387522101402283:  47%|████▋     | 12072/25880 [2:28:40<2:39:38,  1.44it/s]
1|12073|Loss: 0.9604550004005432:  47%|████▋     | 12072/25880 [2:28:41<2:39:38,  1.44it/s]
1|12073|Loss: 0.9604550004005432:  47%|████▋     | 12073/25880 [2:28:41<2:41:23,  1.43it/s]
1|12074|Loss: 0.9123409986495972:  47%|████▋     | 12073/25880 [2:28:42<2:41:23,  1.43it/s]
1|12074|Loss: 0.9123409986495972:  47%|████▋     | 12074/25880 [2:28:42<2:44:24,  1.40it/s]
1|12075|Loss: 0.8367226719856262:  47%|████▋     | 12074/25880 [2:28:42<2:44:24,  1.40it/s]
1|12075|Loss: 0.8367226719856262:  47%|████▋     | 12075/25880 [2:28:43<2:46:02,  1.39it/s]
1|12076|Loss: 0.7543027400970459:  47%|████▋     | 12075/25880 [2:28:43<2:46:02,  1.39it/s]
1|12076|Loss: 0.7543027400970459:  47%|████▋     | 12076/25880 [2:28:43<2:50:03,  1.35it/s]
1|12077|Loss: 0.9960044026374817:  47%|████▋     | 12076/25880 [2:28:44<2:50:03,  1.35it/s]
1|12077|Loss: 0.9960044026374817:  47%|████▋     | 12077/25880 [2:28:44<2:45:34,  1.39it/s]
1|12078|Loss: 0.9260820746421814:  47%|████▋     | 12077/25880 [2:28:44<2:45:34,  1.39it/s]
1|12078|Loss: 0.9260820746421814:  47%|████▋     | 12078/25880 [2:28:45<2:40:13,  1.44it/s]
1|12079|Loss: 0.8268236517906189:  47%|████▋     | 12078/25880 [2:28:45<2:40:13,  1.44it/s]
1|12079|Loss: 0.8268236517906189:  47%|████▋     | 12079/25880 [2:28:45<2:42:05,  1.42it/s]
1|12080|Loss: 0.9536572694778442:  47%|████▋     | 12079/25880 [2:28:46<2:42:05,  1.42it/s]
1|12080|Loss: 0.9536572694778442:  47%|████▋     | 12080/25880 [2:28:46<2:32:02,  1.51it/s]
1|12081|Loss: 0.8683246970176697:  47%|████▋     | 12080/25880 [2:28:46<2:32:02,  1.51it/s]
1|12081|Loss: 0.8683246970176697:  47%|████▋     | 12081/25880 [2:28:47<2:37:47,  1.46it/s]
1|12082|Loss: 0.8959211707115173:  47%|████▋     | 12081/25880 [2:28:47<2:37:47,  1.46it/s]
1|12082|Loss: 0.8959211707115173:  47%|████▋     | 12082/25880 [2:28:48<2:40:02,  1.44it/s]
1|12083|Loss: 0.7154514789581299:  47%|████▋     | 12082/25880 [2:28:48<2:40:02,  1.44it/s]
1|12083|Loss: 0.7154514789581299:  47%|████▋     | 12083/25880 [2:28:48<2:47:02,  1.38it/s]
1|12084|Loss: 0.9839030504226685:  47%|████▋     | 12083/25880 [2:28:49<2:47:02,  1.38it/s]
1|12084|Loss: 0.9839030504226685:  47%|████▋     | 12084/25880 [2:28:49<2:42:19,  1.42it/s]
1|12085|Loss: 0.8234269022941589:  47%|████▋     | 12084/25880 [2:28:49<2:42:19,  1.42it/s]
1|12085|Loss: 0.8234269022941589:  47%|████▋     | 12085/25880 [2:28:50<2:46:50,  1.38it/s]
1|12086|Loss: 0.6598565578460693:  47%|████▋     | 12085/25880 [2:28:50<2:46:50,  1.38it/s]
1|12086|Loss: 0.6598565578460693:  47%|████▋     | 12086/25880 [2:28:50<2:47:59,  1.37it/s]
1|12087|Loss: 0.9358657598495483:  47%|████▋     | 12086/25880 [2:28:51<2:47:59,  1.37it/s]
1|12087|Loss: 0.9358657598495483:  47%|████▋     | 12087/25880 [2:28:51<2:46:13,  1.38it/s]
1|12088|Loss: 0.9108220934867859:  47%|████▋     | 12087/25880 [2:28:52<2:46:13,  1.38it/s]
1|12088|Loss: 0.9108220934867859:  47%|████▋     | 12088/25880 [2:28:52<2:45:02,  1.39it/s]
1|12089|Loss: 0.7528258562088013:  47%|████▋     | 12088/25880 [2:28:52<2:45:02,  1.39it/s]
1|12089|Loss: 0.7528258562088013:  47%|████▋     | 12089/25880 [2:28:53<2:45:16,  1.39it/s]
1|12090|Loss: 0.7902795076370239:  47%|████▋     | 12089/25880 [2:28:53<2:45:16,  1.39it/s]
1|12090|Loss: 0.7902795076370239:  47%|████▋     | 12090/25880 [2:28:53<2:48:56,  1.36it/s]
1|12091|Loss: 0.8009085059165955:  47%|████▋     | 12090/25880 [2:28:54<2:48:56,  1.36it/s]
1|12091|Loss: 0.8009085059165955:  47%|████▋     | 12091/25880 [2:28:54<2:49:43,  1.35it/s]
1|12092|Loss: 0.8666266798973083:  47%|████▋     | 12091/25880 [2:28:55<2:49:43,  1.35it/s]
1|12092|Loss: 0.8666266798973083:  47%|████▋     | 12092/25880 [2:28:55<2:47:40,  1.37it/s]
1|12093|Loss: 0.8424952030181885:  47%|████▋     | 12092/25880 [2:28:55<2:47:40,  1.37it/s]
1|12093|Loss: 0.8424952030181885:  47%|████▋     | 12093/25880 [2:28:56<2:45:54,  1.38it/s]
1|12094|Loss: 0.8102183938026428:  47%|████▋     | 12093/25880 [2:28:56<2:45:54,  1.38it/s]
1|12094|Loss: 0.8102183938026428:  47%|████▋     | 12094/25880 [2:28:56<2:49:26,  1.36it/s]
1|12095|Loss: 0.9106465578079224:  47%|████▋     | 12094/25880 [2:28:57<2:49:26,  1.36it/s]
1|12095|Loss: 0.9106465578079224:  47%|████▋     | 12095/25880 [2:28:57<2:45:19,  1.39it/s]
1|12096|Loss: 0.7859010696411133:  47%|████▋     | 12095/25880 [2:28:57<2:45:19,  1.39it/s]
1|12096|Loss: 0.7859010696411133:  47%|████▋     | 12096/25880 [2:28:58<2:36:47,  1.47it/s]
1|12097|Loss: 0.9694587588310242:  47%|████▋     | 12096/25880 [2:28:58<2:36:47,  1.47it/s]
1|12097|Loss: 0.9694587588310242:  47%|████▋     | 12097/25880 [2:28:58<2:42:17,  1.42it/s]
1|12098|Loss: 0.7548786997795105:  47%|████▋     | 12097/25880 [2:28:59<2:42:17,  1.42it/s]
1|12098|Loss: 0.7548786997795105:  47%|████▋     | 12098/25880 [2:28:59<2:38:40,  1.45it/s]
1|12099|Loss: 0.8596503138542175:  47%|████▋     | 12098/25880 [2:28:59<2:38:40,  1.45it/s]
1|12099|Loss: 0.8596503138542175:  47%|████▋     | 12099/25880 [2:29:00<2:39:40,  1.44it/s]
1|12100|Loss: 0.8036487102508545:  47%|████▋     | 12099/25880 [2:29:00<2:39:40,  1.44it/s]
1|12100|Loss: 0.8036487102508545:  47%|████▋     | 12100/25880 [2:29:00<2:35:49,  1.47it/s]
1|12101|Loss: 0.8377795815467834:  47%|████▋     | 12100/25880 [2:29:01<2:35:49,  1.47it/s]
1|12101|Loss: 0.8377795815467834:  47%|████▋     | 12101/25880 [2:29:01<2:37:50,  1.45it/s]
1|12102|Loss: 0.8547735810279846:  47%|████▋     | 12101/25880 [2:29:01<2:37:50,  1.45it/s]
1|12102|Loss: 0.8547735810279846:  47%|████▋     | 12102/25880 [2:29:02<2:46:31,  1.38it/s]
1|12103|Loss: 1.0443105697631836:  47%|████▋     | 12102/25880 [2:29:02<2:46:31,  1.38it/s]
1|12103|Loss: 1.0443105697631836:  47%|████▋     | 12103/25880 [2:29:03<2:48:20,  1.36it/s]
1|12104|Loss: 0.9972896575927734:  47%|████▋     | 12103/25880 [2:29:03<2:48:20,  1.36it/s]
1|12104|Loss: 0.9972896575927734:  47%|████▋     | 12104/25880 [2:29:03<2:53:21,  1.32it/s]
1|12105|Loss: 0.8341352343559265:  47%|████▋     | 12104/25880 [2:29:04<2:53:21,  1.32it/s]
1|12105|Loss: 0.8341352343559265:  47%|████▋     | 12105/25880 [2:29:04<2:58:29,  1.29it/s]
1|12106|Loss: 0.7979416251182556:  47%|████▋     | 12105/25880 [2:29:05<2:58:29,  1.29it/s]
1|12106|Loss: 0.7979416251182556:  47%|████▋     | 12106/25880 [2:29:05<2:47:49,  1.37it/s]
1|12107|Loss: 0.8386598825454712:  47%|████▋     | 12106/25880 [2:29:05<2:47:49,  1.37it/s]
1|12107|Loss: 0.8386598825454712:  47%|████▋     | 12107/25880 [2:29:06<2:50:57,  1.34it/s]
1|12108|Loss: 0.862219512462616:  47%|████▋     | 12107/25880 [2:29:06<2:50:57,  1.34it/s] 
1|12108|Loss: 0.862219512462616:  47%|████▋     | 12108/25880 [2:29:07<2:59:22,  1.28it/s]
1|12109|Loss: 0.7397781014442444:  47%|████▋     | 12108/25880 [2:29:07<2:59:22,  1.28it/s]
1|12109|Loss: 0.7397781014442444:  47%|████▋     | 12109/25880 [2:29:07<2:57:43,  1.29it/s]
1|12110|Loss: 0.7783143520355225:  47%|████▋     | 12109/25880 [2:29:08<2:57:43,  1.29it/s]
1|12110|Loss: 0.7783143520355225:  47%|████▋     | 12110/25880 [2:29:08<3:02:03,  1.26it/s]
1|12111|Loss: 0.8487907648086548:  47%|████▋     | 12110/25880 [2:29:09<3:02:03,  1.26it/s]
1|12111|Loss: 0.8487907648086548:  47%|████▋     | 12111/25880 [2:29:09<2:58:23,  1.29it/s]
1|12112|Loss: 0.9093490242958069:  47%|████▋     | 12111/25880 [2:29:09<2:58:23,  1.29it/s]
1|12112|Loss: 0.9093490242958069:  47%|████▋     | 12112/25880 [2:29:10<2:55:05,  1.31it/s]
1|12113|Loss: 0.8520492315292358:  47%|████▋     | 12112/25880 [2:29:10<2:55:05,  1.31it/s]
1|12113|Loss: 0.8520492315292358:  47%|████▋     | 12113/25880 [2:29:10<2:59:43,  1.28it/s]
1|12114|Loss: 0.8764604926109314:  47%|████▋     | 12113/25880 [2:29:11<2:59:43,  1.28it/s]
1|12114|Loss: 0.8764604926109314:  47%|████▋     | 12114/25880 [2:29:11<3:01:42,  1.26it/s]
1|12115|Loss: 0.8323138356208801:  47%|████▋     | 12114/25880 [2:29:12<3:01:42,  1.26it/s]
1|12115|Loss: 0.8323138356208801:  47%|████▋     | 12115/25880 [2:29:12<2:58:42,  1.28it/s]
1|12116|Loss: 0.9174593091011047:  47%|████▋     | 12115/25880 [2:29:12<2:58:42,  1.28it/s]
1|12116|Loss: 0.9174593091011047:  47%|████▋     | 12116/25880 [2:29:13<2:50:16,  1.35it/s]
1|12117|Loss: 0.8164450526237488:  47%|████▋     | 12116/25880 [2:29:13<2:50:16,  1.35it/s]
1|12117|Loss: 0.8164450526237488:  47%|████▋     | 12117/25880 [2:29:13<2:53:57,  1.32it/s]
1|12118|Loss: 0.8783547282218933:  47%|████▋     | 12117/25880 [2:29:14<2:53:57,  1.32it/s]
1|12118|Loss: 0.8783547282218933:  47%|████▋     | 12118/25880 [2:29:14<2:59:22,  1.28it/s]
1|12119|Loss: 0.8524795174598694:  47%|████▋     | 12118/25880 [2:29:15<2:59:22,  1.28it/s]
1|12119|Loss: 0.8524795174598694:  47%|████▋     | 12119/25880 [2:29:15<2:57:48,  1.29it/s]
1|12120|Loss: 0.7532995343208313:  47%|████▋     | 12119/25880 [2:29:15<2:57:48,  1.29it/s]
1|12120|Loss: 0.7532995343208313:  47%|████▋     | 12120/25880 [2:29:16<2:50:09,  1.35it/s]
1|12121|Loss: 0.7330926656723022:  47%|████▋     | 12120/25880 [2:29:16<2:50:09,  1.35it/s]
1|12121|Loss: 0.7330926656723022:  47%|████▋     | 12121/25880 [2:29:16<2:46:52,  1.37it/s]
1|12122|Loss: 0.7447206974029541:  47%|████▋     | 12121/25880 [2:29:17<2:46:52,  1.37it/s]
1|12122|Loss: 0.7447206974029541:  47%|████▋     | 12122/25880 [2:29:17<2:40:20,  1.43it/s]
1|12123|Loss: 0.8655569553375244:  47%|████▋     | 12122/25880 [2:29:17<2:40:20,  1.43it/s]
1|12123|Loss: 0.8655569553375244:  47%|████▋     | 12123/25880 [2:29:18<2:39:30,  1.44it/s]
1|12124|Loss: 0.8362690210342407:  47%|████▋     | 12123/25880 [2:29:18<2:39:30,  1.44it/s]
1|12124|Loss: 0.8362690210342407:  47%|████▋     | 12124/25880 [2:29:18<2:39:49,  1.43it/s]
1|12125|Loss: 0.7958197593688965:  47%|████▋     | 12124/25880 [2:29:19<2:39:49,  1.43it/s]
1|12125|Loss: 0.7958197593688965:  47%|████▋     | 12125/25880 [2:29:19<2:41:23,  1.42it/s]
1|12126|Loss: 0.9381147027015686:  47%|████▋     | 12125/25880 [2:29:20<2:41:23,  1.42it/s]
1|12126|Loss: 0.9381147027015686:  47%|████▋     | 12126/25880 [2:29:20<2:38:07,  1.45it/s]
1|12127|Loss: 0.898762047290802:  47%|████▋     | 12126/25880 [2:29:20<2:38:07,  1.45it/s] 
1|12127|Loss: 0.898762047290802:  47%|████▋     | 12127/25880 [2:29:21<2:46:10,  1.38it/s]
1|12128|Loss: 0.8421649932861328:  47%|████▋     | 12127/25880 [2:29:21<2:46:10,  1.38it/s]
1|12128|Loss: 0.8421649932861328:  47%|████▋     | 12128/25880 [2:29:21<2:43:27,  1.40it/s]
1|12129|Loss: 0.6594424247741699:  47%|████▋     | 12128/25880 [2:29:22<2:43:27,  1.40it/s]
1|12129|Loss: 0.6594424247741699:  47%|████▋     | 12129/25880 [2:29:22<2:49:59,  1.35it/s]
1|12130|Loss: 1.0782625675201416:  47%|████▋     | 12129/25880 [2:29:23<2:49:59,  1.35it/s]
1|12130|Loss: 1.0782625675201416:  47%|████▋     | 12130/25880 [2:29:23<2:44:45,  1.39it/s]
1|12131|Loss: 0.8665644526481628:  47%|████▋     | 12130/25880 [2:29:23<2:44:45,  1.39it/s]
1|12131|Loss: 0.8665644526481628:  47%|████▋     | 12131/25880 [2:29:23<2:44:00,  1.40it/s]
1|12132|Loss: 0.8543511033058167:  47%|████▋     | 12131/25880 [2:29:24<2:44:00,  1.40it/s]
1|12132|Loss: 0.8543511033058167:  47%|████▋     | 12132/25880 [2:29:24<2:44:42,  1.39it/s]
1|12133|Loss: 0.8149909973144531:  47%|████▋     | 12132/25880 [2:29:25<2:44:42,  1.39it/s]
1|12133|Loss: 0.8149909973144531:  47%|████▋     | 12133/25880 [2:29:25<2:40:22,  1.43it/s]
1|12134|Loss: 0.8738163709640503:  47%|████▋     | 12133/25880 [2:29:25<2:40:22,  1.43it/s]
1|12134|Loss: 0.8738163709640503:  47%|████▋     | 12134/25880 [2:29:26<2:39:35,  1.44it/s]
1|12135|Loss: 0.814268171787262:  47%|████▋     | 12134/25880 [2:29:26<2:39:35,  1.44it/s] 
1|12135|Loss: 0.814268171787262:  47%|████▋     | 12135/25880 [2:29:26<2:41:51,  1.42it/s]
1|12136|Loss: 0.8044474124908447:  47%|████▋     | 12135/25880 [2:29:27<2:41:51,  1.42it/s]
1|12136|Loss: 0.8044474124908447:  47%|████▋     | 12136/25880 [2:29:27<2:52:31,  1.33it/s]
1|12137|Loss: 0.8323581218719482:  47%|████▋     | 12136/25880 [2:29:28<2:52:31,  1.33it/s]
1|12137|Loss: 0.8323581218719482:  47%|████▋     | 12137/25880 [2:29:28<3:01:57,  1.26it/s]
1|12138|Loss: 0.9581784009933472:  47%|████▋     | 12137/25880 [2:29:28<3:01:57,  1.26it/s]
1|12138|Loss: 0.9581784009933472:  47%|████▋     | 12138/25880 [2:29:29<3:05:53,  1.23it/s]
1|12139|Loss: 0.8781813979148865:  47%|████▋     | 12138/25880 [2:29:29<3:05:53,  1.23it/s]
1|12139|Loss: 0.8781813979148865:  47%|████▋     | 12139/25880 [2:29:30<3:01:45,  1.26it/s]
1|12140|Loss: 0.9872808456420898:  47%|████▋     | 12139/25880 [2:29:30<3:01:45,  1.26it/s]
1|12140|Loss: 0.9872808456420898:  47%|████▋     | 12140/25880 [2:29:30<2:55:32,  1.30it/s]
1|12141|Loss: 0.9057982563972473:  47%|████▋     | 12140/25880 [2:29:31<2:55:32,  1.30it/s]
1|12141|Loss: 0.9057982563972473:  47%|████▋     | 12141/25880 [2:29:31<2:44:04,  1.40it/s]
1|12142|Loss: 0.8216978907585144:  47%|████▋     | 12141/25880 [2:29:31<2:44:04,  1.40it/s]
1|12142|Loss: 0.8216978907585144:  47%|████▋     | 12142/25880 [2:29:31<2:27:24,  1.55it/s]
1|12143|Loss: 0.8749869465827942:  47%|████▋     | 12142/25880 [2:29:32<2:27:24,  1.55it/s]
1|12143|Loss: 0.8749869465827942:  47%|████▋     | 12143/25880 [2:29:32<2:35:58,  1.47it/s]
1|12144|Loss: 0.7680099606513977:  47%|████▋     | 12143/25880 [2:29:33<2:35:58,  1.47it/s]
1|12144|Loss: 0.7680099606513977:  47%|████▋     | 12144/25880 [2:29:33<2:48:00,  1.36it/s]
1|12145|Loss: 0.6743913292884827:  47%|████▋     | 12144/25880 [2:29:34<2:48:00,  1.36it/s]
1|12145|Loss: 0.6743913292884827:  47%|████▋     | 12145/25880 [2:29:34<2:56:38,  1.30it/s]
1|12146|Loss: 0.8867329955101013:  47%|████▋     | 12145/25880 [2:29:34<2:56:38,  1.30it/s]
1|12146|Loss: 0.8867329955101013:  47%|████▋     | 12146/25880 [2:29:35<2:54:15,  1.31it/s]
1|12147|Loss: 0.7566528916358948:  47%|████▋     | 12146/25880 [2:29:35<2:54:15,  1.31it/s]
1|12147|Loss: 0.7566528916358948:  47%|████▋     | 12147/25880 [2:29:35<2:46:40,  1.37it/s]
1|12148|Loss: 0.8489216566085815:  47%|████▋     | 12147/25880 [2:29:36<2:46:40,  1.37it/s]
1|12148|Loss: 0.8489216566085815:  47%|████▋     | 12148/25880 [2:29:36<2:44:14,  1.39it/s]
1|12149|Loss: 0.7597264051437378:  47%|████▋     | 12148/25880 [2:29:36<2:44:14,  1.39it/s]
1|12149|Loss: 0.7597264051437378:  47%|████▋     | 12149/25880 [2:29:37<2:45:20,  1.38it/s]
1|12150|Loss: 0.8374013304710388:  47%|████▋     | 12149/25880 [2:29:37<2:45:20,  1.38it/s]
1|12150|Loss: 0.8374013304710388:  47%|████▋     | 12150/25880 [2:29:37<2:47:24,  1.37it/s]
1|12151|Loss: 0.8978165984153748:  47%|████▋     | 12150/25880 [2:29:38<2:47:24,  1.37it/s]
1|12151|Loss: 0.8978165984153748:  47%|████▋     | 12151/25880 [2:29:38<2:48:02,  1.36it/s]
1|12152|Loss: 0.8103958964347839:  47%|████▋     | 12151/25880 [2:29:39<2:48:02,  1.36it/s]
1|12152|Loss: 0.8103958964347839:  47%|████▋     | 12152/25880 [2:29:39<2:43:14,  1.40it/s]
1|12153|Loss: 0.796992301940918:  47%|████▋     | 12152/25880 [2:29:39<2:43:14,  1.40it/s] 
1|12153|Loss: 0.796992301940918:  47%|████▋     | 12153/25880 [2:29:40<2:50:17,  1.34it/s]
1|12154|Loss: 0.9917377233505249:  47%|████▋     | 12153/25880 [2:29:40<2:50:17,  1.34it/s]
1|12154|Loss: 0.9917377233505249:  47%|████▋     | 12154/25880 [2:29:41<2:57:54,  1.29it/s]
1|12155|Loss: 0.8730064630508423:  47%|████▋     | 12154/25880 [2:29:41<2:57:54,  1.29it/s]
1|12155|Loss: 0.8730064630508423:  47%|████▋     | 12155/25880 [2:29:41<2:51:53,  1.33it/s]
1|12156|Loss: 0.8949450254440308:  47%|████▋     | 12155/25880 [2:29:42<2:51:53,  1.33it/s]
1|12156|Loss: 0.8949450254440308:  47%|████▋     | 12156/25880 [2:29:42<2:49:48,  1.35it/s]
1|12157|Loss: 0.9128429889678955:  47%|████▋     | 12156/25880 [2:29:42<2:49:48,  1.35it/s]
1|12157|Loss: 0.9128429889678955:  47%|████▋     | 12157/25880 [2:29:43<2:53:24,  1.32it/s]
1|12158|Loss: 0.8088559508323669:  47%|████▋     | 12157/25880 [2:29:43<2:53:24,  1.32it/s]
1|12158|Loss: 0.8088559508323669:  47%|████▋     | 12158/25880 [2:29:43<2:50:41,  1.34it/s]
1|12159|Loss: 0.9727838635444641:  47%|████▋     | 12158/25880 [2:29:44<2:50:41,  1.34it/s]
1|12159|Loss: 0.9727838635444641:  47%|████▋     | 12159/25880 [2:29:44<2:47:21,  1.37it/s]
1|12160|Loss: 0.8685601949691772:  47%|████▋     | 12159/25880 [2:29:45<2:47:21,  1.37it/s]
1|12160|Loss: 0.8685601949691772:  47%|████▋     | 12160/25880 [2:29:45<2:51:53,  1.33it/s]
1|12161|Loss: 0.8962112069129944:  47%|████▋     | 12160/25880 [2:29:45<2:51:53,  1.33it/s]
1|12161|Loss: 0.8962112069129944:  47%|████▋     | 12161/25880 [2:29:46<2:38:14,  1.44it/s]
1|12162|Loss: 0.8553919196128845:  47%|████▋     | 12161/25880 [2:29:46<2:38:14,  1.44it/s]
1|12162|Loss: 0.8553919196128845:  47%|████▋     | 12162/25880 [2:29:46<2:30:56,  1.51it/s]
1|12163|Loss: 0.758920431137085:  47%|████▋     | 12162/25880 [2:29:46<2:30:56,  1.51it/s] 
1|12163|Loss: 0.758920431137085:  47%|████▋     | 12163/25880 [2:29:47<2:29:08,  1.53it/s]
1|12164|Loss: 0.9103468060493469:  47%|████▋     | 12163/25880 [2:29:47<2:29:08,  1.53it/s]
1|12164|Loss: 0.9103468060493469:  47%|████▋     | 12164/25880 [2:29:47<2:31:44,  1.51it/s]
1|12165|Loss: 0.7654283046722412:  47%|████▋     | 12164/25880 [2:29:48<2:31:44,  1.51it/s]
1|12165|Loss: 0.7654283046722412:  47%|████▋     | 12165/25880 [2:29:48<2:30:10,  1.52it/s]
1|12166|Loss: 0.9272397756576538:  47%|████▋     | 12165/25880 [2:29:48<2:30:10,  1.52it/s]
1|12166|Loss: 0.9272397756576538:  47%|████▋     | 12166/25880 [2:29:49<2:34:09,  1.48it/s]
1|12167|Loss: 0.8739858865737915:  47%|████▋     | 12166/25880 [2:29:49<2:34:09,  1.48it/s]
1|12167|Loss: 0.8739858865737915:  47%|████▋     | 12167/25880 [2:29:50<2:38:16,  1.44it/s]
1|12168|Loss: 0.8037934899330139:  47%|████▋     | 12167/25880 [2:29:50<2:38:16,  1.44it/s]
1|12168|Loss: 0.8037934899330139:  47%|████▋     | 12168/25880 [2:29:50<2:46:27,  1.37it/s]
1|12169|Loss: 0.8952798247337341:  47%|████▋     | 12168/25880 [2:29:51<2:46:27,  1.37it/s]
1|12169|Loss: 0.8952798247337341:  47%|████▋     | 12169/25880 [2:29:51<2:41:22,  1.42it/s]
1|12170|Loss: 0.8002864122390747:  47%|████▋     | 12169/25880 [2:29:51<2:41:22,  1.42it/s]
1|12170|Loss: 0.8002864122390747:  47%|████▋     | 12170/25880 [2:29:51<2:26:18,  1.56it/s]
1|12171|Loss: 0.9471353888511658:  47%|████▋     | 12170/25880 [2:29:52<2:26:18,  1.56it/s]
1|12171|Loss: 0.9471353888511658:  47%|████▋     | 12171/25880 [2:29:52<2:31:13,  1.51it/s]
1|12172|Loss: 0.840420663356781:  47%|████▋     | 12171/25880 [2:29:53<2:31:13,  1.51it/s] 
1|12172|Loss: 0.840420663356781:  47%|████▋     | 12172/25880 [2:29:53<2:41:19,  1.42it/s]
1|12173|Loss: 0.8243478536605835:  47%|████▋     | 12172/25880 [2:29:53<2:41:19,  1.42it/s]
1|12173|Loss: 0.8243478536605835:  47%|████▋     | 12173/25880 [2:29:54<2:44:11,  1.39it/s]
1|12174|Loss: 0.7938479781150818:  47%|████▋     | 12173/25880 [2:29:54<2:44:11,  1.39it/s]
1|12174|Loss: 0.7938479781150818:  47%|████▋     | 12174/25880 [2:29:54<2:44:14,  1.39it/s]
1|12175|Loss: 0.7491545081138611:  47%|████▋     | 12174/25880 [2:29:55<2:44:14,  1.39it/s]
1|12175|Loss: 0.7491545081138611:  47%|████▋     | 12175/25880 [2:29:55<2:47:45,  1.36it/s]
1|12176|Loss: 0.8946199417114258:  47%|████▋     | 12175/25880 [2:29:56<2:47:45,  1.36it/s]
1|12176|Loss: 0.8946199417114258:  47%|████▋     | 12176/25880 [2:29:56<2:42:31,  1.41it/s]
1|12177|Loss: 0.7963137030601501:  47%|████▋     | 12176/25880 [2:29:56<2:42:31,  1.41it/s]
1|12177|Loss: 0.7963137030601501:  47%|████▋     | 12177/25880 [2:29:57<2:42:58,  1.40it/s]
1|12178|Loss: 0.929714024066925:  47%|████▋     | 12177/25880 [2:29:57<2:42:58,  1.40it/s] 
1|12178|Loss: 0.929714024066925:  47%|████▋     | 12178/25880 [2:29:57<2:50:15,  1.34it/s]
1|12179|Loss: 0.8930659890174866:  47%|████▋     | 12178/25880 [2:29:58<2:50:15,  1.34it/s]
1|12179|Loss: 0.8930659890174866:  47%|████▋     | 12179/25880 [2:29:58<2:53:53,  1.31it/s]
1|12180|Loss: 0.7142028212547302:  47%|████▋     | 12179/25880 [2:29:59<2:53:53,  1.31it/s]
1|12180|Loss: 0.7142028212547302:  47%|████▋     | 12180/25880 [2:29:59<3:10:41,  1.20it/s]
1|12181|Loss: 0.777466356754303:  47%|████▋     | 12180/25880 [2:30:00<3:10:41,  1.20it/s] 
1|12181|Loss: 0.777466356754303:  47%|████▋     | 12181/25880 [2:30:00<3:16:18,  1.16it/s]
1|12182|Loss: 1.0152558088302612:  47%|████▋     | 12181/25880 [2:30:01<3:16:18,  1.16it/s]
1|12182|Loss: 1.0152558088302612:  47%|████▋     | 12182/25880 [2:30:01<3:14:12,  1.18it/s]
1|12183|Loss: 0.8045997619628906:  47%|████▋     | 12182/25880 [2:30:01<3:14:12,  1.18it/s]
1|12183|Loss: 0.8045997619628906:  47%|████▋     | 12183/25880 [2:30:02<3:07:21,  1.22it/s]
1|12184|Loss: 0.7624719738960266:  47%|████▋     | 12183/25880 [2:30:02<3:07:21,  1.22it/s]
1|12184|Loss: 0.7624719738960266:  47%|████▋     | 12184/25880 [2:30:02<2:55:37,  1.30it/s]
1|12185|Loss: 1.0117108821868896:  47%|███��▋     | 12184/25880 [2:30:03<2:55:37,  1.30it/s]
1|12185|Loss: 1.0117108821868896:  47%|████▋     | 12185/25880 [2:30:03<3:04:05,  1.24it/s]
1|12186|Loss: 0.6470892429351807:  47%|████▋     | 12185/25880 [2:30:04<3:04:05,  1.24it/s]
1|12186|Loss: 0.6470892429351807:  47%|████▋     | 12186/25880 [2:30:04<3:13:04,  1.18it/s]
1|12187|Loss: 0.9380504488945007:  47%|████▋     | 12186/25880 [2:30:05<3:13:04,  1.18it/s]
1|12187|Loss: 0.9380504488945007:  47%|████▋     | 12187/25880 [2:30:05<3:08:08,  1.21it/s]
1|12188|Loss: 0.8836244344711304:  47%|████▋     | 12187/25880 [2:30:05<3:08:08,  1.21it/s]
1|12188|Loss: 0.8836244344711304:  47%|████▋     | 12188/25880 [2:30:06<3:05:40,  1.23it/s]
1|12189|Loss: 0.9102494716644287:  47%|████▋     | 12188/25880 [2:30:06<3:05:40,  1.23it/s]
1|12189|Loss: 0.9102494716644287:  47%|████▋     | 12189/25880 [2:30:07<2:59:45,  1.27it/s]
1|12190|Loss: 0.8666850328445435:  47%|████▋     | 12189/25880 [2:30:07<2:59:45,  1.27it/s]
1|12190|Loss: 0.8666850328445435:  47%|████▋     | 12190/25880 [2:30:07<2:53:29,  1.32it/s]
1|12191|Loss: 0.8158586621284485:  47%|████▋     | 12190/25880 [2:30:08<2:53:29,  1.32it/s]
1|12191|Loss: 0.8158586621284485:  47%|████▋     | 12191/25880 [2:30:08<2:49:36,  1.35it/s]
1|12192|Loss: 0.7914884686470032:  47%|████▋     | 12191/25880 [2:30:08<2:49:36,  1.35it/s]
1|12192|Loss: 0.7914884686470032:  47%|████▋     | 12192/25880 [2:30:08<2:36:36,  1.46it/s]
1|12193|Loss: 0.8444714546203613:  47%|████▋     | 12192/25880 [2:30:09<2:36:36,  1.46it/s]
1|12193|Loss: 0.8444714546203613:  47%|████▋     | 12193/25880 [2:30:09<2:31:31,  1.51it/s]
1|12194|Loss: 0.8184925317764282:  47%|████▋     | 12193/25880 [2:30:09<2:31:31,  1.51it/s]
1|12194|Loss: 0.8184925317764282:  47%|████▋     | 12194/25880 [2:30:10<2:40:27,  1.42it/s]
1|12195|Loss: 1.0304055213928223:  47%|████▋     | 12194/25880 [2:30:10<2:40:27,  1.42it/s]
1|12195|Loss: 1.0304055213928223:  47%|████▋     | 12195/25880 [2:30:11<2:37:14,  1.45it/s]
1|12196|Loss: 0.8089814186096191:  47%|████▋     | 12195/25880 [2:30:11<2:37:14,  1.45it/s]
1|12196|Loss: 0.8089814186096191:  47%|████▋     | 12196/25880 [2:30:11<2:32:07,  1.50it/s]
1|12197|Loss: 0.8862574696540833:  47%|████▋     | 12196/25880 [2:30:11<2:32:07,  1.50it/s]
1|12197|Loss: 0.8862574696540833:  47%|████▋     | 12197/25880 [2:30:12<2:33:40,  1.48it/s]
1|12198|Loss: 0.8504324555397034:  47%|████▋     | 12197/25880 [2:30:12<2:33:40,  1.48it/s]
1|12198|Loss: 0.8504324555397034:  47%|████▋     | 12198/25880 [2:30:12<2:32:22,  1.50it/s]
1|12199|Loss: 0.8755736351013184:  47%|████▋     | 12198/25880 [2:30:13<2:32:22,  1.50it/s]
1|12199|Loss: 0.8755736351013184:  47%|████▋     | 12199/25880 [2:30:13<2:45:20,  1.38it/s]
1|12200|Loss: 0.8158818483352661:  47%|████▋     | 12199/25880 [2:30:14<2:45:20,  1.38it/s]
1|12200|Loss: 0.8158818483352661:  47%|████▋     | 12200/25880 [2:30:14<2:33:13,  1.49it/s]
1|12201|Loss: 0.9062986969947815:  47%|████▋     | 12200/25880 [2:30:14<2:33:13,  1.49it/s]
1|12201|Loss: 0.9062986969947815:  47%|████▋     | 12201/25880 [2:30:14<2:24:41,  1.58it/s]
1|12202|Loss: 1.188781499862671:  47%|████▋     | 12201/25880 [2:30:15<2:24:41,  1.58it/s] 
1|12202|Loss: 1.188781499862671:  47%|████▋     | 12202/25880 [2:30:15<2:37:05,  1.45it/s]
1|12203|Loss: 0.8993561863899231:  47%|████▋     | 12202/25880 [2:30:16<2:37:05,  1.45it/s]
1|12203|Loss: 0.8993561863899231:  47%|████▋     | 12203/25880 [2:30:16<2:55:08,  1.30it/s]
1|12204|Loss: 0.9224240779876709:  47%|████▋     | 12203/25880 [2:30:17<2:55:08,  1.30it/s]
1|12204|Loss: 0.9224240779876709:  47%|████▋     | 12204/25880 [2:30:17<3:00:11,  1.26it/s]
1|12205|Loss: 0.7861931920051575:  47%|████▋     | 12204/25880 [2:30:17<3:00:11,  1.26it/s]
1|12205|Loss: 0.7861931920051575:  47%|████▋     | 12205/25880 [2:30:18<2:50:49,  1.33it/s]
1|12206|Loss: 0.8420818448066711:  47%|████▋     | 12205/25880 [2:30:18<2:50:49,  1.33it/s]
1|12206|Loss: 0.8420818448066711:  47%|████▋     | 12206/25880 [2:30:19<2:58:15,  1.28it/s]
1|12207|Loss: 0.8712322115898132:  47%|████▋     | 12206/25880 [2:30:19<2:58:15,  1.28it/s]
1|12207|Loss: 0.8712322115898132:  47%|████▋     | 12207/25880 [2:30:19<2:55:57,  1.30it/s]
1|12208|Loss: 0.7744045257568359:  47%|████▋     | 12207/25880 [2:30:20<2:55:57,  1.30it/s]
1|12208|Loss: 0.7744045257568359:  47%|████▋     | 12208/25880 [2:30:20<2:58:16,  1.28it/s]
1|12209|Loss: 0.818946361541748:  47%|████▋     | 12208/25880 [2:30:20<2:58:16,  1.28it/s] 
1|12209|Loss: 0.818946361541748:  47%|████▋     | 12209/25880 [2:30:21<2:47:39,  1.36it/s]
1|12210|Loss: 0.8346424102783203:  47%|████▋     | 12209/25880 [2:30:21<2:47:39,  1.36it/s]
1|12210|Loss: 0.8346424102783203:  47%|████▋     | 12210/25880 [2:30:21<2:44:59,  1.38it/s]
1|12211|Loss: 1.0554885864257812:  47%|████▋     | 12210/25880 [2:30:22<2:44:59,  1.38it/s]
1|12211|Loss: 1.0554885864257812:  47%|████▋     | 12211/25880 [2:30:22<2:35:35,  1.46it/s]
1|12212|Loss: 0.904420018196106:  47%|████▋     | 12211/25880 [2:30:22<2:35:35,  1.46it/s] 
1|12212|Loss: 0.904420018196106:  47%|████▋     | 12212/25880 [2:30:23<2:29:43,  1.52it/s]
1|12213|Loss: 0.7842139005661011:  47%|████▋     | 12212/25880 [2:30:23<2:29:43,  1.52it/s]
1|12213|Loss: 0.7842139005661011:  47%|████▋     | 12213/25880 [2:30:23<2:33:11,  1.49it/s]
1|12214|Loss: 0.8564273118972778:  47%|████▋     | 12213/25880 [2:30:24<2:33:11,  1.49it/s]
1|12214|Loss: 0.8564273118972778:  47%|████▋     | 12214/25880 [2:30:24<2:45:48,  1.37it/s]
1|12215|Loss: 0.9698344469070435:  47%|████▋     | 12214/25880 [2:30:25<2:45:48,  1.37it/s]
1|12215|Loss: 0.9698344469070435:  47%|████▋     | 12215/25880 [2:30:25<2:54:55,  1.30it/s]
1|12216|Loss: 0.8070512413978577:  47%|████▋     | 12215/25880 [2:30:25<2:54:55,  1.30it/s]
1|12216|Loss: 0.8070512413978577:  47%|████▋     | 12216/25880 [2:30:26<2:49:38,  1.34it/s]
1|12217|Loss: 0.746490478515625:  47%|████▋     | 12216/25880 [2:30:26<2:49:38,  1.34it/s] 
1|12217|Loss: 0.746490478515625:  47%|████▋     | 12217/25880 [2:30:26<2:32:31,  1.49it/s]
1|12218|Loss: 0.8848927617073059:  47%|████▋     | 12217/25880 [2:30:27<2:32:31,  1.49it/s]
1|12218|Loss: 0.8848927617073059:  47%|████▋     | 12218/25880 [2:30:27<2:30:43,  1.51it/s]
1|12219|Loss: 0.7702720761299133:  47%|████▋     | 12218/25880 [2:30:27<2:30:43,  1.51it/s]
1|12219|Loss: 0.7702720761299133:  47%|████▋     | 12219/25880 [2:30:27<2:26:41,  1.55it/s]
1|12220|Loss: 0.8436590433120728:  47%|████▋     | 12219/25880 [2:30:28<2:26:41,  1.55it/s]
1|12220|Loss: 0.8436590433120728:  47%|████▋     | 12220/25880 [2:30:28<2:30:59,  1.51it/s]
1|12221|Loss: 0.8377822637557983:  47%|████▋     | 12220/25880 [2:30:29<2:30:59,  1.51it/s]
1|12221|Loss: 0.8377822637557983:  47%|████▋     | 12221/25880 [2:30:29<2:37:15,  1.45it/s]
1|12222|Loss: 0.7194534540176392:  47%|████▋     | 12221/25880 [2:30:29<2:37:15,  1.45it/s]
1|12222|Loss: 0.7194534540176392:  47%|████▋     | 12222/25880 [2:30:30<2:32:14,  1.50it/s]
1|12223|Loss: 0.8307427167892456:  47%|████▋     | 12222/25880 [2:30:30<2:32:14,  1.50it/s]
1|12223|Loss: 0.8307427167892456:  47%|████▋     | 12223/25880 [2:30:30<2:26:16,  1.56it/s]
1|12224|Loss: 0.8754191994667053:  47%|████▋     | 12223/25880 [2:30:31<2:26:16,  1.56it/s]
1|12224|Loss: 0.8754191994667053:  47%|████▋     | 12224/25880 [2:30:31<2:30:58,  1.51it/s]
1|12225|Loss: 0.7585510015487671:  47%|████▋     | 12224/25880 [2:30:31<2:30:58,  1.51it/s]
1|12225|Loss: 0.7585510015487671:  47%|████▋     | 12225/25880 [2:30:32<2:34:31,  1.47it/s]
1|12226|Loss: 0.9465673565864563:  47%|████▋     | 12225/25880 [2:30:32<2:34:31,  1.47it/s]
1|12226|Loss: 0.9465673565864563:  47%|████▋     | 12226/25880 [2:30:32<2:40:38,  1.42it/s]
1|12227|Loss: 0.8186337947845459:  47%|████▋     | 12226/25880 [2:30:33<2:40:38,  1.42it/s]
1|12227|Loss: 0.8186337947845459:  47%|████▋     | 12227/25880 [2:30:33<2:46:30,  1.37it/s]
1|12228|Loss: 0.882002055644989:  47%|████▋     | 12227/25880 [2:30:34<2:46:30,  1.37it/s] 
1|12228|Loss: 0.882002055644989:  47%|████▋     | 12228/25880 [2:30:34<2:48:47,  1.35it/s]
1|12229|Loss: 0.7180453538894653:  47%|████▋     | 12228/25880 [2:30:34<2:48:47,  1.35it/s]
1|12229|Loss: 0.7180453538894653:  47%|████▋     | 12229/25880 [2:30:34<2:33:50,  1.48it/s]
1|12230|Loss: 0.9639816284179688:  47%|████▋     | 12229/25880 [2:30:35<2:33:50,  1.48it/s]
1|12230|Loss: 0.9639816284179688:  47%|████▋     | 12230/25880 [2:30:35<2:38:52,  1.43it/s]
1|12231|Loss: 0.8350857496261597:  47%|████▋     | 12230/25880 [2:30:36<2:38:52,  1.43it/s]
1|12231|Loss: 0.8350857496261597:  47%|████▋     | 12231/25880 [2:30:36<2:46:20,  1.37it/s]
1|12232|Loss: 0.9043616652488708:  47%|████▋     | 12231/25880 [2:30:36<2:46:20,  1.37it/s]
1|12232|Loss: 0.9043616652488708:  47%|████▋     | 12232/25880 [2:30:37<2:52:48,  1.32it/s]
1|12233|Loss: 0.8176833987236023:  47%|████▋     | 12232/25880 [2:30:37<2:52:48,  1.32it/s]
1|12233|Loss: 0.8176833987236023:  47%|████▋     | 12233/25880 [2:30:38<2:57:20,  1.28it/s]
1|12234|Loss: 0.9310933947563171:  47%|████▋     | 12233/25880 [2:30:38<2:57:20,  1.28it/s]
1|12234|Loss: 0.9310933947563171:  47%|████▋     | 12234/25880 [2:30:38<2:55:19,  1.30it/s]
1|12235|Loss: 0.7809165120124817:  47%|████▋     | 12234/25880 [2:30:39<2:55:19,  1.30it/s]
1|12235|Loss: 0.7809165120124817:  47%|████▋     | 12235/25880 [2:30:39<2:56:58,  1.29it/s]
1|12236|Loss: 0.9497614502906799:  47%|████▋     | 12235/25880 [2:30:40<2:56:58,  1.29it/s]
1|12236|Loss: 0.9497614502906799:  47%|████▋     | 12236/25880 [2:30:40<2:55:18,  1.30it/s]
1|12237|Loss: 0.7777572870254517:  47%|████▋     | 12236/25880 [2:30:40<2:55:18,  1.30it/s]
1|12237|Loss: 0.7777572870254517:  47%|████▋     | 12237/25880 [2:30:41<2:51:44,  1.32it/s]
1|12238|Loss: 0.8597018122673035:  47%|████▋     | 12237/25880 [2:30:41<2:51:44,  1.32it/s]
1|12238|Loss: 0.8597018122673035:  47%|████▋     | 12238/25880 [2:30:41<2:53:06,  1.31it/s]
1|12239|Loss: 0.7875685095787048:  47%|████▋     | 12238/25880 [2:30:42<2:53:06,  1.31it/s]
1|12239|Loss: 0.7875685095787048:  47%|████▋     | 12239/25880 [2:30:42<2:53:14,  1.31it/s]
1|12240|Loss: 0.9037663340568542:  47%|████▋     | 12239/25880 [2:30:43<2:53:14,  1.31it/s]
1|12240|Loss: 0.9037663340568542:  47%|████▋     | 12240/25880 [2:30:43<2:36:48,  1.45it/s]
1|12241|Loss: 0.8854637145996094:  47%|████▋     | 12240/25880 [2:30:43<2:36:48,  1.45it/s]
1|12241|Loss: 0.8854637145996094:  47%|████▋     | 12241/25880 [2:30:43<2:35:24,  1.46it/s]
1|12242|Loss: 0.7364981174468994:  47%|████▋     | 12241/25880 [2:30:44<2:35:24,  1.46it/s]
1|12242|Loss: 0.7364981174468994:  47%|████▋     | 12242/25880 [2:30:44<2:30:16,  1.51it/s]
1|12243|Loss: 0.8640936017036438:  47%|████▋     | 12242/25880 [2:30:44<2:30:16,  1.51it/s]
1|12243|Loss: 0.8640936017036438:  47%|████▋     | 12243/25880 [2:30:45<2:39:11,  1.43it/s]
1|12244|Loss: 1.0428640842437744:  47%|████▋     | 12243/25880 [2:30:45<2:39:11,  1.43it/s]
1|12244|Loss: 1.0428640842437744:  47%|████▋     | 12244/25880 [2:30:46<2:46:10,  1.37it/s]
1|12245|Loss: 0.9873179197311401:  47%|████▋     | 12244/25880 [2:30:46<2:46:10,  1.37it/s]
1|12245|Loss: 0.9873179197311401:  47%|████▋     | 12245/25880 [2:30:46<2:40:56,  1.41it/s]
1|12246|Loss: 0.8802149891853333:  47%|████▋     | 12245/25880 [2:30:47<2:40:56,  1.41it/s]
1|12246|Loss: 0.8802149891853333:  47%|████▋     | 12246/25880 [2:30:47<2:39:17,  1.43it/s]
1|12247|Loss: 0.8458588719367981:  47%|████▋     | 12246/25880 [2:30:47<2:39:17,  1.43it/s]
1|12247|Loss: 0.8458588719367981:  47%|████▋     | 12247/25880 [2:30:48<2:40:52,  1.41it/s]
1|12248|Loss: 0.7860679626464844:  47%|████▋     | 12247/25880 [2:30:48<2:40:52,  1.41it/s]
1|12248|Loss: 0.7860679626464844:  47%|████▋     | 12248/25880 [2:30:48<2:42:40,  1.40it/s]
1|12249|Loss: 0.7099596261978149:  47%|████▋     | 12248/25880 [2:30:49<2:42:40,  1.40it/s]
1|12249|Loss: 0.7099596261978149:  47%|████▋     | 12249/25880 [2:30:49<2:39:02,  1.43it/s]
1|12250|Loss: 0.8686494827270508:  47%|████▋     | 12249/25880 [2:30:49<2:39:02,  1.43it/s]
1|12250|Loss: 0.8686494827270508:  47%|████▋     | 12250/25880 [2:30:50<2:46:42,  1.36it/s]
1|12251|Loss: 0.8758707046508789:  47%|████▋     | 12250/25880 [2:30:50<2:46:42,  1.36it/s]
1|12251|Loss: 0.8758707046508789:  47%|████▋     | 12251/25880 [2:30:51<2:42:14,  1.40it/s]
1|12252|Loss: 0.8611117005348206:  47%|████▋     | 12251/25880 [2:30:51<2:42:14,  1.40it/s]
1|12252|Loss: 0.8611117005348206:  47%|████▋     | 12252/25880 [2:30:51<2:47:54,  1.35it/s]
1|12253|Loss: 0.7779734134674072:  47%|████▋     | 12252/25880 [2:30:52<2:47:54,  1.35it/s]
1|12253|Loss: 0.7779734134674072:  47%|████▋     | 12253/25880 [2:30:52<2:58:34,  1.27it/s]
1|12254|Loss: 0.7288552522659302:  47%|████▋     | 12253/25880 [2:30:53<2:58:34,  1.27it/s]
1|12254|Loss: 0.7288552522659302:  47%|████▋     | 12254/25880 [2:30:53<2:51:52,  1.32it/s]
1|12255|Loss: 0.9332224726676941:  47%|████▋     | 12254/25880 [2:30:53<2:51:52,  1.32it/s]
1|12255|Loss: 0.9332224726676941:  47%|████▋     | 12255/25880 [2:30:54<2:42:34,  1.40it/s]
1|12256|Loss: 0.7526922225952148:  47%|████▋     | 12255/25880 [2:30:54<2:42:34,  1.40it/s]
1|12256|Loss: 0.7526922225952148:  47%|████▋     | 12256/25880 [2:30:54<2:50:01,  1.34it/s]
1|12257|Loss: 0.8304346799850464:  47%|████▋     | 12256/25880 [2:30:55<2:50:01,  1.34it/s]
1|12257|Loss: 0.8304346799850464:  47%|████▋     | 12257/25880 [2:30:55<2:57:20,  1.28it/s]
1|12258|Loss: 0.8199178576469421:  47%|████▋     | 12257/25880 [2:30:56<2:57:20,  1.28it/s]
1|12258|Loss: 0.8199178576469421:  47%|████▋     | 12258/25880 [2:30:56<2:58:55,  1.27it/s]
1|12259|Loss: 0.8935296535491943:  47%|████▋     | 12258/25880 [2:30:56<2:58:55,  1.27it/s]
1|12259|Loss: 0.8935296535491943:  47%|████▋     | 12259/25880 [2:30:57<2:55:57,  1.29it/s]
1|12260|Loss: 0.8270489573478699:  47%|████▋     | 12259/25880 [2:30:57<2:55:57,  1.29it/s]
1|12260|Loss: 0.8270489573478699:  47%|████▋     | 12260/25880 [2:30:57<2:46:39,  1.36it/s]
1|12261|Loss: 0.7210862040519714:  47%|████▋     | 12260/25880 [2:30:58<2:46:39,  1.36it/s]
1|12261|Loss: 0.7210862040519714:  47%|████▋     | 12261/25880 [2:30:58<2:48:11,  1.35it/s]
1|12262|Loss: 0.7988429069519043:  47%|████▋     | 12261/25880 [2:30:59<2:48:11,  1.35it/s]
1|12262|Loss: 0.7988429069519043:  47%|████▋     | 12262/25880 [2:30:59<2:47:01,  1.36it/s]
1|12263|Loss: 0.8334487080574036:  47%|████▋     | 12262/25880 [2:30:59<2:47:01,  1.36it/s]
1|12263|Loss: 0.8334487080574036:  47%|████▋     | 12263/25880 [2:31:00<2:47:09,  1.36it/s]
1|12264|Loss: 0.8724518418312073:  47%|████▋     | 12263/25880 [2:31:00<2:47:09,  1.36it/s]
1|12264|Loss: 0.8724518418312073:  47%|████▋     | 12264/25880 [2:31:00<2:47:31,  1.35it/s]
1|12265|Loss: 0.8910829424858093:  47%|████▋     | 12264/25880 [2:31:01<2:47:31,  1.35it/s]
1|12265|Loss: 0.8910829424858093:  47%|████▋     | 12265/25880 [2:31:01<2:48:44,  1.34it/s]
1|12266|Loss: 0.7326979041099548:  47%|████▋     | 12265/25880 [2:31:02<2:48:44,  1.34it/s]
1|12266|Loss: 0.7326979041099548:  47%|████▋     | 12266/25880 [2:31:02<2:46:47,  1.36it/s]
1|12267|Loss: 0.7736378312110901:  47%|████▋     | 12266/25880 [2:31:02<2:46:47,  1.36it/s]
1|12267|Loss: 0.7736378312110901:  47%|████▋     | 12267/25880 [2:31:02<2:40:59,  1.41it/s]
1|12268|Loss: 0.7309870719909668:  47%|████▋     | 12267/25880 [2:31:03<2:40:59,  1.41it/s]
1|12268|Loss: 0.7309870719909668:  47%|████▋     | 12268/25880 [2:31:03<2:54:07,  1.30it/s]
1|12269|Loss: 0.9761567115783691:  47%|████▋     | 12268/25880 [2:31:04<2:54:07,  1.30it/s]
1|12269|Loss: 0.9761567115783691:  47%|████▋     | 12269/25880 [2:31:04<2:48:38,  1.35it/s]
1|12270|Loss: 0.7189876437187195:  47%|████▋     | 12269/25880 [2:31:05<2:48:38,  1.35it/s]
1|12270|Loss: 0.7189876437187195:  47%|████▋     | 12270/25880 [2:31:05<2:58:55,  1.27it/s]
1|12271|Loss: 0.8209520578384399:  47%|████▋     | 12270/25880 [2:31:05<2:58:55,  1.27it/s]
1|12271|Loss: 0.8209520578384399:  47%|████▋     | 12271/25880 [2:31:06<2:58:12,  1.27it/s]
1|12272|Loss: 0.9259089231491089:  47%|████▋     | 12271/25880 [2:31:06<2:58:12,  1.27it/s]
1|12272|Loss: 0.9259089231491089:  47%|████▋     | 12272/25880 [2:31:07<3:04:13,  1.23it/s]
1|12273|Loss: 0.8753103613853455:  47%|████▋     | 12272/25880 [2:31:07<3:04:13,  1.23it/s]
1|12273|Loss: 0.8753103613853455:  47%|████▋     | 12273/25880 [2:31:07<3:09:13,  1.20it/s]
1|12274|Loss: 0.7599104642868042:  47%|████▋     | 12273/25880 [2:31:08<3:09:13,  1.20it/s]
1|12274|Loss: 0.7599104642868042:  47%|████▋     | 12274/25880 [2:31:08<3:08:39,  1.20it/s]
1|12275|Loss: 0.9036349058151245:  47%|████▋     | 12274/25880 [2:31:09<3:08:39,  1.20it/s]
1|12275|Loss: 0.9036349058151245:  47%|████▋     | 12275/25880 [2:31:09<2:50:47,  1.33it/s]
1|12276|Loss: 0.7976077198982239:  47%|████▋     | 12275/25880 [2:31:09<2:50:47,  1.33it/s]
1|12276|Loss: 0.7976077198982239:  47%|████▋     | 12276/25880 [2:31:10<2:44:30,  1.38it/s]
1|12277|Loss: 0.7650228142738342:  47%|████▋     | 12276/25880 [2:31:10<2:44:30,  1.38it/s]
1|12277|Loss: 0.7650228142738342:  47%|████▋     | 12277/25880 [2:31:10<2:47:41,  1.35it/s]
1|12278|Loss: 0.7833117246627808:  47%|████▋     | 12277/25880 [2:31:11<2:47:41,  1.35it/s]
1|12278|Loss: 0.7833117246627808:  47%|████▋     | 12278/25880 [2:31:11<2:48:27,  1.35it/s]
1|12279|Loss: 0.8593462109565735:  47%|████▋     | 12278/25880 [2:31:11<2:48:27,  1.35it/s]
1|12279|Loss: 0.8593462109565735:  47%|████▋     | 12279/25880 [2:31:12<2:41:33,  1.40it/s]
1|12280|Loss: 0.8071375489234924:  47%|████▋     | 12279/25880 [2:31:12<2:41:33,  1.40it/s]
1|12280|Loss: 0.8071375489234924:  47%|████▋     | 12280/25880 [2:31:12<2:39:27,  1.42it/s]
1|12281|Loss: 0.7949496507644653:  47%|████▋     | 12280/25880 [2:31:13<2:39:27,  1.42it/s]
1|12281|Loss: 0.7949496507644653:  47%|████▋     | 12281/25880 [2:31:13<2:51:23,  1.32it/s]
1|12282|Loss: 0.7134801745414734:  47%|████▋     | 12281/25880 [2:31:14<2:51:23,  1.32it/s]
1|12282|Loss: 0.7134801745414734:  47%|████▋     | 12282/25880 [2:31:14<2:41:34,  1.40it/s]
1|12283|Loss: 0.876518726348877:  47%|████▋     | 12282/25880 [2:31:14<2:41:34,  1.40it/s] 
1|12283|Loss: 0.876518726348877:  47%|████▋     | 12283/25880 [2:31:15<2:40:47,  1.41it/s]
1|12284|Loss: 0.9770245552062988:  47%|████▋     | 12283/25880 [2:31:15<2:40:47,  1.41it/s]
1|12284|Loss: 0.9770245552062988:  47%|████▋     | 12284/25880 [2:31:15<2:36:37,  1.45it/s]
1|12285|Loss: 0.8711807727813721:  47%|████▋     | 12284/25880 [2:31:16<2:36:37,  1.45it/s]
1|12285|Loss: 0.8711807727813721:  47%|████▋     | 12285/25880 [2:31:16<2:43:42,  1.38it/s]
1|12286|Loss: 0.7883872985839844:  47%|████▋     | 12285/25880 [2:31:16<2:43:42,  1.38it/s]
1|12286|Loss: 0.7883872985839844:  47%|████▋     | 12286/25880 [2:31:17<2:39:29,  1.42it/s]
1|12287|Loss: 0.8796080350875854:  47%|████▋     | 12286/25880 [2:31:17<2:39:29,  1.42it/s]
1|12287|Loss: 0.8796080350875854:  47%|████▋     | 12287/25880 [2:31:17<2:40:48,  1.41it/s]
1|12288|Loss: 0.7677316665649414:  47%|████▋     | 12287/25880 [2:31:18<2:40:48,  1.41it/s]
1|12288|Loss: 0.7677316665649414:  47%|████▋     | 12288/25880 [2:31:18<2:43:41,  1.38it/s]
1|12289|Loss: 0.8800433874130249:  47%|████▋     | 12288/25880 [2:31:19<2:43:41,  1.38it/s]
1|12289|Loss: 0.8800433874130249:  47%|████▋     | 12289/25880 [2:31:19<2:43:04,  1.39it/s]
1|12290|Loss: 0.8579078912734985:  47%|████▋     | 12289/25880 [2:31:19<2:43:04,  1.39it/s]
1|12290|Loss: 0.8579078912734985:  47%|████▋     | 12290/25880 [2:31:20<2:41:29,  1.40it/s]
1|12291|Loss: 0.9370101690292358:  47%|████▋     | 12290/25880 [2:31:20<2:41:29,  1.40it/s]
1|12291|Loss: 0.9370101690292358:  47%|████▋     | 12291/25880 [2:31:20<2:32:26,  1.49it/s]
1|12292|Loss: 0.8300155997276306:  47%|████▋     | 12291/25880 [2:31:21<2:32:26,  1.49it/s]
1|12292|Loss: 0.8300155997276306:  47%|████▋     | 12292/25880 [2:31:21<2:34:32,  1.47it/s]
1|12293|Loss: 0.8183462023735046:  47%|████▋     | 12292/25880 [2:31:21<2:34:32,  1.47it/s]
1|12293|Loss: 0.8183462023735046:  48%|████▊     | 12293/25880 [2:31:22<2:38:41,  1.43it/s]
1|12294|Loss: 0.829152524471283:  48%|████▊     | 12293/25880 [2:31:22<2:38:41,  1.43it/s] 
1|12294|Loss: 0.829152524471283:  48%|████▊     | 12294/25880 [2:31:22<2:42:14,  1.40it/s]
1|12295|Loss: 0.8875290751457214:  48%|████▊     | 12294/25880 [2:31:23<2:42:14,  1.40it/s]
1|12295|Loss: 0.8875290751457214:  48%|████▊     | 12295/25880 [2:31:23<2:39:14,  1.42it/s]
1|12296|Loss: 0.8429098129272461:  48%|████▊     | 12295/25880 [2:31:23<2:39:14,  1.42it/s]
1|12296|Loss: 0.8429098129272461:  48%|████▊     | 12296/25880 [2:31:24<2:47:53,  1.35it/s]
1|12297|Loss: 0.91818767786026:  48%|████▊     | 12296/25880 [2:31:24<2:47:53,  1.35it/s]  
1|12297|Loss: 0.91818767786026:  48%|████▊     | 12297/25880 [2:31:25<2:53:16,  1.31it/s]
1|12298|Loss: 0.9638771414756775:  48%|████▊     | 12297/25880 [2:31:25<2:53:16,  1.31it/s]
1|12298|Loss: 0.9638771414756775:  48%|████▊     | 12298/25880 [2:31:25<2:40:19,  1.41it/s]
1|12299|Loss: 0.7689141035079956:  48%|████▊     | 12298/25880 [2:31:26<2:40:19,  1.41it/s]
1|12299|Loss: 0.7689141035079956:  48%|████▊     | 12299/25880 [2:31:26<2:33:55,  1.47it/s]
1|12300|Loss: 0.8735173344612122:  48%|████▊     | 12299/25880 [2:31:26<2:33:55,  1.47it/s]
1|12300|Loss: 0.8735173344612122:  48%|████▊     | 12300/25880 [2:31:27<2:37:23,  1.44it/s]
1|12301|Loss: 0.9321587085723877:  48%|████▊     | 12300/25880 [2:31:27<2:37:23,  1.44it/s]
1|12301|Loss: 0.9321587085723877:  48%|████▊     | 12301/25880 [2:31:27<2:29:28,  1.51it/s]
1|12302|Loss: 0.709927499294281:  48%|████▊     | 12301/25880 [2:31:28<2:29:28,  1.51it/s] 
1|12302|Loss: 0.709927499294281:  48%|████▊     | 12302/25880 [2:31:28<2:31:28,  1.49it/s]
1|12303|Loss: 0.8254600167274475:  48%|████▊     | 12302/25880 [2:31:28<2:31:28,  1.49it/s]
1|12303|Loss: 0.8254600167274475:  48%|████▊     | 12303/25880 [2:31:29<2:35:50,  1.45it/s]
1|12304|Loss: 0.7662510275840759:  48%|████▊     | 12303/25880 [2:31:29<2:35:50,  1.45it/s]
1|12304|Loss: 0.7662510275840759:  48%|████▊     | 12304/25880 [2:31:29<2:46:29,  1.36it/s]
1|12305|Loss: 0.8213480710983276:  48%|████▊     | 12304/25880 [2:31:30<2:46:29,  1.36it/s]
1|12305|Loss: 0.8213480710983276:  48%|████▊     | 12305/25880 [2:31:30<2:42:37,  1.39it/s]
1|12306|Loss: 0.9614993929862976:  48%|████▊     | 12305/25880 [2:31:31<2:42:37,  1.39it/s]
1|12306|Loss: 0.9614993929862976:  48%|████▊     | 12306/25880 [2:31:31<2:41:54,  1.40it/s]
1|12307|Loss: 0.7341563701629639:  48%|████▊     | 12306/25880 [2:31:31<2:41:54,  1.40it/s]
1|12307|Loss: 0.7341563701629639:  48%|████▊     | 12307/25880 [2:31:32<2:41:13,  1.40it/s]
1|12308|Loss: 0.7809105515480042:  48%|████▊     | 12307/25880 [2:31:32<2:41:13,  1.40it/s]
1|12308|Loss: 0.7809105515480042:  48%|████▊     | 12308/25880 [2:31:32<2:47:44,  1.35it/s]
1|12309|Loss: 0.8430097699165344:  48%|████▊     | 12308/25880 [2:31:33<2:47:44,  1.35it/s]
1|12309|Loss: 0.8430097699165344:  48%|████▊     | 12309/25880 [2:31:33<2:46:57,  1.35it/s]
1|12310|Loss: 0.8888587951660156:  48%|████▊     | 12309/25880 [2:31:34<2:46:57,  1.35it/s]
1|12310|Loss: 0.8888587951660156:  48%|████▊     | 12310/25880 [2:31:34<2:50:56,  1.32it/s]
1|12311|Loss: 0.9249480366706848:  48%|████▊     | 12310/25880 [2:31:34<2:50:56,  1.32it/s]
1|12311|Loss: 0.9249480366706848:  48%|████▊     | 12311/25880 [2:31:35<2:56:47,  1.28it/s]
1|12312|Loss: 0.7300812602043152:  48%|████▊     | 12311/25880 [2:31:35<2:56:47,  1.28it/s]
1|12312|Loss: 0.7300812602043152:  48%|████▊     | 12312/25880 [2:31:36<3:02:13,  1.24it/s]
1|12313|Loss: 0.8577953577041626:  48%|████▊     | 12312/25880 [2:31:36<3:02:13,  1.24it/s]
1|12313|Loss: 0.8577953577041626:  48%|████▊     | 12313/25880 [2:31:37<3:11:40,  1.18it/s]
1|12314|Loss: 0.8553613424301147:  48%|████▊     | 12313/25880 [2:31:37<3:11:40,  1.18it/s]
1|12314|Loss: 0.8553613424301147:  48%|████▊     | 12314/25880 [2:31:37<3:07:29,  1.21it/s]
1|12315|Loss: 0.8887328505516052:  48%|████▊     | 12314/25880 [2:31:38<3:07:29,  1.21it/s]
1|12315|Loss: 0.8887328505516052:  48%|████▊     | 12315/25880 [2:31:38<3:11:58,  1.18it/s]
1|12316|Loss: 0.8942381143569946:  48%|████▊     | 12315/25880 [2:31:39<3:11:58,  1.18it/s]
1|12316|Loss: 0.8942381143569946:  48%|████▊     | 12316/25880 [2:31:39<3:05:21,  1.22it/s]
1|12317|Loss: 0.8114810585975647:  48%|████▊     | 12316/25880 [2:31:39<3:05:21,  1.22it/s]
1|12317|Loss: 0.8114810585975647:  48%|████▊     | 12317/25880 [2:31:40<3:02:50,  1.24it/s]
1|12318|Loss: 0.8551260828971863:  48%|████▊     | 12317/25880 [2:31:40<3:02:50,  1.24it/s]
1|12318|Loss: 0.8551260828971863:  48%|████▊     | 12318/25880 [2:31:40<2:56:26,  1.28it/s]
1|12319|Loss: 0.8180738091468811:  48%|████▊     | 12318/25880 [2:31:41<2:56:26,  1.28it/s]
1|12319|Loss: 0.8180738091468811:  48%|████▊     | 12319/25880 [2:31:41<2:47:28,  1.35it/s]
1|12320|Loss: 0.7636352181434631:  48%|████▊     | 12319/25880 [2:31:41<2:47:28,  1.35it/s]
1|12320|Loss: 0.7636352181434631:  48%|████▊     | 12320/25880 [2:31:42<2:43:50,  1.38it/s]
1|12321|Loss: 0.8922309279441833:  48%|████▊     | 12320/25880 [2:31:42<2:43:50,  1.38it/s]
1|12321|Loss: 0.8922309279441833:  48%|████▊     | 12321/25880 [2:31:43<2:50:12,  1.33it/s]
1|12322|Loss: 0.8304258584976196:  48%|████▊     | 12321/25880 [2:31:43<2:50:12,  1.33it/s]
1|12322|Loss: 0.8304258584976196:  48%|████▊     | 12322/25880 [2:31:43<2:44:47,  1.37it/s]
1|12323|Loss: 0.8361144065856934:  48%|████▊     | 12322/25880 [2:31:44<2:44:47,  1.37it/s]
1|12323|Loss: 0.8361144065856934:  48%|████▊     | 12323/25880 [2:31:44<2:36:12,  1.45it/s]
1|12324|Loss: 0.7978646755218506:  48%|████▊     | 12323/25880 [2:31:44<2:36:12,  1.45it/s]
1|12324|Loss: 0.7978646755218506:  48%|████▊     | 12324/25880 [2:31:45<2:35:32,  1.45it/s]
1|12325|Loss: 0.9287970066070557:  48%|████▊     | 12324/25880 [2:31:45<2:35:32,  1.45it/s]
1|12325|Loss: 0.9287970066070557:  48%|████▊     | 12325/25880 [2:31:45<2:43:53,  1.38it/s]
1|12326|Loss: 0.7972474098205566:  48%|████▊     | 12325/25880 [2:31:46<2:43:53,  1.38it/s]
1|12326|Loss: 0.7972474098205566:  48%|████▊     | 12326/25880 [2:31:46<2:34:06,  1.47it/s]
1|12327|Loss: 0.8068711757659912:  48%|████▊     | 12326/25880 [2:31:46<2:34:06,  1.47it/s]
1|12327|Loss: 0.8068711757659912:  48%|████▊     | 12327/25880 [2:31:47<2:28:23,  1.52it/s]
1|12328|Loss: 0.8342281579971313:  48%|████▊     | 12327/25880 [2:31:47<2:28:23,  1.52it/s]
1|12328|Loss: 0.8342281579971313:  48%|████▊     | 12328/25880 [2:31:47<2:30:34,  1.50it/s]
1|12329|Loss: 0.7791188955307007:  48%|████▊     | 12328/25880 [2:31:48<2:30:34,  1.50it/s]
1|12329|Loss: 0.7791188955307007:  48%|████▊     | 12329/25880 [2:31:48<2:29:28,  1.51it/s]
1|12330|Loss: 0.8507062792778015:  48%|████▊     | 12329/25880 [2:31:48<2:29:28,  1.51it/s]
1|12330|Loss: 0.8507062792778015:  48%|████▊     | 12330/25880 [2:31:49<2:35:48,  1.45it/s]
1|12331|Loss: 0.7894101142883301:  48%|████▊     | 12330/25880 [2:31:49<2:35:48,  1.45it/s]
1|12331|Loss: 0.7894101142883301:  48%|████▊     | 12331/25880 [2:31:49<2:33:38,  1.47it/s]
1|12332|Loss: 1.0119929313659668:  48%|████▊     | 12331/25880 [2:31:50<2:33:38,  1.47it/s]
1|12332|Loss: 1.0119929313659668:  48%|████▊     | 12332/25880 [2:31:50<2:39:43,  1.41it/s]
1|12333|Loss: 0.7602399587631226:  48%|████▊     | 12332/25880 [2:31:51<2:39:43,  1.41it/s]
1|12333|Loss: 0.7602399587631226:  48%|████▊     | 12333/25880 [2:31:51<2:45:57,  1.36it/s]
1|12334|Loss: 0.7971381545066833:  48%|████▊     | 12333/25880 [2:31:51<2:45:57,  1.36it/s]
1|12334|Loss: 0.7971381545066833:  48%|████▊     | 12334/25880 [2:31:52<2:38:47,  1.42it/s]
1|12335|Loss: 0.6810141205787659:  48%|████▊     | 12334/25880 [2:31:52<2:38:47,  1.42it/s]
1|12335|Loss: 0.6810141205787659:  48%|████▊     | 12335/25880 [2:31:52<2:39:22,  1.42it/s]
1|12336|Loss: 0.736641526222229:  48%|████▊     | 12335/25880 [2:31:53<2:39:22,  1.42it/s] 
1|12336|Loss: 0.736641526222229:  48%|████▊     | 12336/25880 [2:31:53<2:35:21,  1.45it/s]
1|12337|Loss: 0.9364705681800842:  48%|████▊     | 12336/25880 [2:31:53<2:35:21,  1.45it/s]
1|12337|Loss: 0.9364705681800842:  48%|████▊     | 12337/25880 [2:31:53<2:26:48,  1.54it/s]
1|12338|Loss: 0.9939777851104736:  48%|████▊     | 12337/25880 [2:31:54<2:26:48,  1.54it/s]
1|12338|Loss: 0.9939777851104736:  48%|████▊     | 12338/25880 [2:31:54<2:41:50,  1.39it/s]
1|12339|Loss: 0.8453439474105835:  48%|████▊     | 12338/25880 [2:31:55<2:41:50,  1.39it/s]
1|12339|Loss: 0.8453439474105835:  48%|████▊     | 12339/25880 [2:31:55<2:53:35,  1.30it/s]
1|12340|Loss: 0.9277957677841187:  48%|████▊     | 12339/25880 [2:31:56<2:53:35,  1.30it/s]
1|12340|Loss: 0.9277957677841187:  48%|████▊     | 12340/25880 [2:31:56<2:53:45,  1.30it/s]
1|12341|Loss: 0.8793913722038269:  48%|████▊     | 12340/25880 [2:31:56<2:53:45,  1.30it/s]
1|12341|Loss: 0.8793913722038269:  48%|████▊     | 12341/25880 [2:31:57<2:51:18,  1.32it/s]
1|12342|Loss: 0.9421558976173401:  48%|████▊     | 12341/25880 [2:31:57<2:51:18,  1.32it/s]
1|12342|Loss: 0.9421558976173401:  48%|████▊     | 12342/25880 [2:31:57<2:49:39,  1.33it/s]
1|12343|Loss: 0.9622340798377991:  48%|████▊     | 12342/25880 [2:31:58<2:49:39,  1.33it/s]
1|12343|Loss: 0.9622340798377991:  48%|████▊     | 12343/25880 [2:31:58<2:52:48,  1.31it/s]
1|12344|Loss: 0.8113940954208374:  48%|████▊     | 12343/25880 [2:31:59<2:52:48,  1.31it/s]
1|12344|Loss: 0.8113940954208374:  48%|████▊     | 12344/25880 [2:31:59<2:49:51,  1.33it/s]
1|12345|Loss: 0.8659809827804565:  48%|████▊     | 12344/25880 [2:31:59<2:49:51,  1.33it/s]
1|12345|Loss: 0.8659809827804565:  48%|████▊     | 12345/25880 [2:31:59<2:32:42,  1.48it/s]
1|12346|Loss: 0.8848004937171936:  48%|████▊     | 12345/25880 [2:32:00<2:32:42,  1.48it/s]
1|12346|Loss: 0.8848004937171936:  48%|████▊     | 12346/25880 [2:32:00<2:26:14,  1.54it/s]
1|12347|Loss: 0.9760991334915161:  48%|████▊     | 12346/25880 [2:32:00<2:26:14,  1.54it/s]
1|12347|Loss: 0.9760991334915161:  48%|████▊     | 12347/25880 [2:32:01<2:29:02,  1.51it/s]
1|12348|Loss: 1.056695580482483:  48%|████▊     | 12347/25880 [2:32:01<2:29:02,  1.51it/s] 
1|12348|Loss: 1.056695580482483:  48%|████▊     | 12348/25880 [2:32:02<2:39:59,  1.41it/s]
1|12349|Loss: 0.7260293960571289:  48%|████▊     | 12348/25880 [2:32:02<2:39:59,  1.41it/s]
1|12349|Loss: 0.7260293960571289:  48%|████▊     | 12349/25880 [2:32:02<2:41:36,  1.40it/s]
1|12350|Loss: 0.8326383233070374:  48%|████▊     | 12349/25880 [2:32:03<2:41:36,  1.40it/s]
1|12350|Loss: 0.8326383233070374:  48%|████▊     | 12350/25880 [2:32:03<2:48:34,  1.34it/s]
1|12351|Loss: 0.8082083463668823:  48%|████▊     | 12350/25880 [2:32:04<2:48:34,  1.34it/s]
1|12351|Loss: 0.8082083463668823:  48%|████▊     | 12351/25880 [2:32:04<2:49:21,  1.33it/s]
1|12352|Loss: 0.8095005750656128:  48%|████▊     | 12351/25880 [2:32:04<2:49:21,  1.33it/s]
1|12352|Loss: 0.8095005750656128:  48%|████▊     | 12352/25880 [2:32:05<2:53:30,  1.30it/s]
1|12353|Loss: 0.9050814509391785:  48%|████▊     | 12352/25880 [2:32:05<2:53:30,  1.30it/s]
1|12353|Loss: 0.9050814509391785:  48%|████▊     | 12353/25880 [2:32:05<2:52:16,  1.31it/s]
1|12354|Loss: 0.9341102838516235:  48%|████▊     | 12353/25880 [2:32:06<2:52:16,  1.31it/s]
1|12354|Loss: 0.9341102838516235:  48%|████▊     | 12354/25880 [2:32:06<2:50:22,  1.32it/s]
1|12355|Loss: 0.8389593362808228:  48%|████▊     | 12354/25880 [2:32:07<2:50:22,  1.32it/s]
1|12355|Loss: 0.8389593362808228:  48%|████▊     | 12355/25880 [2:32:07<2:52:12,  1.31it/s]
1|12356|Loss: 0.7949169874191284:  48%|████▊     | 12355/25880 [2:32:07<2:52:12,  1.31it/s]
1|12356|Loss: 0.7949169874191284:  48%|████▊     | 12356/25880 [2:32:08<2:49:24,  1.33it/s]
1|12357|Loss: 0.7666990160942078:  48%|████▊     | 12356/25880 [2:32:08<2:49:24,  1.33it/s]
1|12357|Loss: 0.7666990160942078:  48%|████▊     | 12357/25880 [2:32:08<2:47:10,  1.35it/s]
1|12358|Loss: 0.6330506205558777:  48%|████▊     | 12357/25880 [2:32:09<2:47:10,  1.35it/s]
1|12358|Loss: 0.6330506205558777:  48%|████▊     | 12358/25880 [2:32:09<2:54:33,  1.29it/s]
1|12359|Loss: 0.774520754814148:  48%|████▊     | 12358/25880 [2:32:10<2:54:33,  1.29it/s] 
1|12359|Loss: 0.774520754814148:  48%|████▊     | 12359/25880 [2:32:10<2:53:53,  1.30it/s]
1|12360|Loss: 0.8656554818153381:  48%|████▊     | 12359/25880 [2:32:10<2:53:53,  1.30it/s]
1|12360|Loss: 0.8656554818153381:  48%|████▊     | 12360/25880 [2:32:11<2:49:21,  1.33it/s]
1|12361|Loss: 0.8863797783851624:  48%|████▊     | 12360/25880 [2:32:11<2:49:21,  1.33it/s]
1|12361|Loss: 0.8863797783851624:  48%|████▊     | 12361/25880 [2:32:11<2:45:37,  1.36it/s]
1|12362|Loss: 0.8898807764053345:  48%|████▊     | 12361/25880 [2:32:12<2:45:37,  1.36it/s]
1|12362|Loss: 0.8898807764053345:  48%|████▊     | 12362/25880 [2:32:12<2:42:52,  1.38it/s]
1|12363|Loss: 0.8247253894805908:  48%|████▊     | 12362/25880 [2:32:13<2:42:52,  1.38it/s]
1|12363|Loss: 0.8247253894805908:  48%|████▊     | 12363/25880 [2:32:13<2:43:52,  1.37it/s]
1|12364|Loss: 0.8158934712409973:  48%|████▊     | 12363/25880 [2:32:13<2:43:52,  1.37it/s]
1|12364|Loss: 0.8158934712409973:  48%|████▊     | 12364/25880 [2:32:14<2:38:26,  1.42it/s]
1|12365|Loss: 0.9133360385894775:  48%|████▊     | 12364/25880 [2:32:14<2:38:26,  1.42it/s]
1|12365|Loss: 0.9133360385894775:  48%|████▊     | 12365/25880 [2:32:14<2:39:07,  1.42it/s]
1|12366|Loss: 0.8420961499214172:  48%|████▊     | 12365/25880 [2:32:15<2:39:07,  1.42it/s]
1|12366|Loss: 0.8420961499214172:  48%|████▊     | 12366/25880 [2:32:15<2:48:39,  1.34it/s]
1|12367|Loss: 0.7665207982063293:  48%|████▊     | 12366/25880 [2:32:16<2:48:39,  1.34it/s]
1|12367|Loss: 0.7665207982063293:  48%|████▊     | 12367/25880 [2:32:16<2:52:13,  1.31it/s]
1|12368|Loss: 0.8667929768562317:  48%|████▊     | 12367/25880 [2:32:16<2:52:13,  1.31it/s]
1|12368|Loss: 0.8667929768562317:  48%|████▊     | 12368/25880 [2:32:16<2:42:47,  1.38it/s]
1|12369|Loss: 0.8320580720901489:  48%|████▊     | 12368/25880 [2:32:17<2:42:47,  1.38it/s]
1|12369|Loss: 0.8320580720901489:  48%|████▊     | 12369/25880 [2:32:17<2:41:25,  1.39it/s]
1|12370|Loss: 0.7911698222160339:  48%|████▊     | 12369/25880 [2:32:18<2:41:25,  1.39it/s]
1|12370|Loss: 0.7911698222160339:  48%|████▊     | 12370/25880 [2:32:18<2:35:33,  1.45it/s]
1|12371|Loss: 0.8794646859169006:  48%|████▊     | 12370/25880 [2:32:18<2:35:33,  1.45it/s]
1|12371|Loss: 0.8794646859169006:  48%|████▊     | 12371/25880 [2:32:18<2:31:12,  1.49it/s]
1|12372|Loss: 0.7541109919548035:  48%|████▊     | 12371/25880 [2:32:19<2:31:12,  1.49it/s]
1|12372|Loss: 0.7541109919548035:  48%|████▊     | 12372/25880 [2:32:19<2:40:39,  1.40it/s]
1|12373|Loss: 0.779262363910675:  48%|████▊     | 12372/25880 [2:32:20<2:40:39,  1.40it/s] 
1|12373|Loss: 0.779262363910675:  48%|████▊     | 12373/25880 [2:32:20<2:54:08,  1.29it/s]
1|12374|Loss: 0.7347778081893921:  48%|████▊     | 12373/25880 [2:32:21<2:54:08,  1.29it/s]
1|12374|Loss: 0.7347778081893921:  48%|████▊     | 12374/25880 [2:32:21<2:48:40,  1.33it/s]
1|12375|Loss: 0.7897982001304626:  48%|████▊     | 12374/25880 [2:32:21<2:48:40,  1.33it/s]
1|12375|Loss: 0.7897982001304626:  48%|████▊     | 12375/25880 [2:32:22<2:44:42,  1.37it/s]
1|12376|Loss: 0.8074276447296143:  48%|████▊     | 12375/25880 [2:32:22<2:44:42,  1.37it/s]
1|12376|Loss: 0.8074276447296143:  48%|████▊     | 12376/25880 [2:32:22<2:50:29,  1.32it/s]
1|12377|Loss: 0.8030028343200684:  48%|████▊     | 12376/25880 [2:32:23<2:50:29,  1.32it/s]
1|12377|Loss: 0.8030028343200684:  48%|████▊     | 12377/25880 [2:32:23<2:50:57,  1.32it/s]
1|12378|Loss: 0.7991077899932861:  48%|████▊     | 12377/25880 [2:32:24<2:50:57,  1.32it/s]
1|12378|Loss: 0.7991077899932861:  48%|████▊     | 12378/25880 [2:32:24<2:43:07,  1.38it/s]
1|12379|Loss: 0.866165041923523:  48%|████▊     | 12378/25880 [2:32:24<2:43:07,  1.38it/s] 
1|12379|Loss: 0.866165041923523:  48%|████▊     | 12379/25880 [2:32:25<2:43:17,  1.38it/s]
1|12380|Loss: 1.0018999576568604:  48%|████▊     | 12379/25880 [2:32:25<2:43:17,  1.38it/s]
1|12380|Loss: 1.0018999576568604:  48%|████▊     | 12380/25880 [2:32:25<2:43:58,  1.37it/s]
1|12381|Loss: 0.741921603679657:  48%|████▊     | 12380/25880 [2:32:26<2:43:58,  1.37it/s] 
1|12381|Loss: 0.741921603679657:  48%|████▊     | 12381/25880 [2:32:26<2:49:20,  1.33it/s]
1|12382|Loss: 0.8175154328346252:  48%|████▊     | 12381/25880 [2:32:27<2:49:20,  1.33it/s]
1|12382|Loss: 0.8175154328346252:  48%|████▊     | 12382/25880 [2:32:27<2:56:09,  1.28it/s]
1|12383|Loss: 0.7606495022773743:  48%|████▊     | 12382/25880 [2:32:27<2:56:09,  1.28it/s]
1|12383|Loss: 0.7606495022773743:  48%|████▊     | 12383/25880 [2:32:28<2:50:01,  1.32it/s]
1|12384|Loss: 0.8267452716827393:  48%|████▊     | 12383/25880 [2:32:28<2:50:01,  1.32it/s]
1|12384|Loss: 0.8267452716827393:  48%|████▊     | 12384/25880 [2:32:28<2:52:46,  1.30it/s]
1|12385|Loss: 0.8277607560157776:  48%|████▊     | 12384/25880 [2:32:29<2:52:46,  1.30it/s]
1|12385|Loss: 0.8277607560157776:  48%|████▊     | 12385/25880 [2:32:29<2:58:40,  1.26it/s]
1|12386|Loss: 0.6981634497642517:  48%|████▊     | 12385/25880 [2:32:30<2:58:40,  1.26it/s]
1|12386|Loss: 0.6981634497642517:  48%|████▊     | 12386/25880 [2:32:30<3:11:26,  1.17it/s]
1|12387|Loss: 0.9090880751609802:  48%|████▊     | 12386/25880 [2:32:31<3:11:26,  1.17it/s]
1|12387|Loss: 0.9090880751609802:  48%|████▊     | 12387/25880 [2:32:31<3:20:52,  1.12it/s]
1|12388|Loss: 0.7475756406784058:  48%|████▊     | 12387/25880 [2:32:32<3:20:52,  1.12it/s]
1|12388|Loss: 0.7475756406784058:  48%|████▊     | 12388/25880 [2:32:32<3:06:52,  1.20it/s]
1|12389|Loss: 0.828732430934906:  48%|████▊     | 12388/25880 [2:32:32<3:06:52,  1.20it/s] 
1|12389|Loss: 0.828732430934906:  48%|████▊     | 12389/25880 [2:32:33<2:58:43,  1.26it/s]
1|12390|Loss: 0.7471004724502563:  48%|████▊     | 12389/25880 [2:32:33<2:58:43,  1.26it/s]
1|12390|Loss: 0.7471004724502563:  48%|████▊     | 12390/25880 [2:32:33<2:53:03,  1.30it/s]
1|12391|Loss: 0.757289707660675:  48%|████▊     | 12390/25880 [2:32:34<2:53:03,  1.30it/s] 
1|12391|Loss: 0.757289707660675:  48%|████▊     | 12391/25880 [2:32:34<2:56:28,  1.27it/s]
1|12392|Loss: 0.758575439453125:  48%|████▊     | 12391/25880 [2:32:35<2:56:28,  1.27it/s]
1|12392|Loss: 0.758575439453125:  48%|████▊     | 12392/25880 [2:32:35<2:49:00,  1.33it/s]
1|12393|Loss: 0.8585187792778015:  48%|████▊     | 12392/25880 [2:32:35<2:49:00,  1.33it/s]
1|12393|Loss: 0.8585187792778015:  48%|████▊     | 12393/25880 [2:32:36<2:54:06,  1.29it/s]
1|12394|Loss: 0.8531541228294373:  48%|████▊     | 12393/25880 [2:32:36<2:54:06,  1.29it/s]
1|12394|Loss: 0.8531541228294373:  48%|████▊     | 12394/25880 [2:32:36<2:47:26,  1.34it/s]
1|12395|Loss: 0.7182954549789429:  48%|████▊     | 12394/25880 [2:32:37<2:47:26,  1.34it/s]
1|12395|Loss: 0.7182954549789429:  48%|████▊     | 12395/25880 [2:32:37<2:45:51,  1.36it/s]
1|12396|Loss: 0.8796469569206238:  48%|████▊     | 12395/25880 [2:32:37<2:45:51,  1.36it/s]
1|12396|Loss: 0.8796469569206238:  48%|████▊     | 12396/25880 [2:32:38<2:37:49,  1.42it/s]
1|12397|Loss: 0.8052067756652832:  48%|████▊     | 12396/25880 [2:32:38<2:37:49,  1.42it/s]
1|12397|Loss: 0.8052067756652832:  48%|████▊     | 12397/25880 [2:32:38<2:31:23,  1.48it/s]
1|12398|Loss: 0.8641530275344849:  48%|████▊     | 12397/25880 [2:32:39<2:31:23,  1.48it/s]
1|12398|Loss: 0.8641530275344849:  48%|████▊     | 12398/25880 [2:32:39<2:34:36,  1.45it/s]
1|12399|Loss: 0.761135995388031:  48%|████▊     | 12398/25880 [2:32:39<2:34:36,  1.45it/s] 
1|12399|Loss: 0.761135995388031:  48%|████▊     | 12399/25880 [2:32:40<2:43:17,  1.38it/s]
1|12400|Loss: 0.6881414651870728:  48%|████▊     | 12399/25880 [2:32:40<2:43:17,  1.38it/s]
1|12400|Loss: 0.6881414651870728:  48%|████▊     | 12400/25880 [2:32:41<2:51:10,  1.31it/s]
1|12401|Loss: 0.9949778318405151:  48%|████▊     | 12400/25880 [2:32:41<2:51:10,  1.31it/s]
1|12401|Loss: 0.9949778318405151:  48%|████▊     | 12401/25880 [2:32:41<2:49:29,  1.33it/s]
1|12402|Loss: 0.7364223003387451:  48%|████▊     | 12401/25880 [2:32:42<2:49:29,  1.33it/s]
1|12402|Loss: 0.7364223003387451:  48%|████▊     | 12402/25880 [2:32:42<2:35:14,  1.45it/s]
1|12403|Loss: 0.8397130966186523:  48%|████▊     | 12402/25880 [2:32:42<2:35:14,  1.45it/s]
1|12403|Loss: 0.8397130966186523:  48%|████▊     | 12403/25880 [2:32:43<2:35:03,  1.45it/s]
1|12404|Loss: 0.933010995388031:  48%|████▊     | 12403/25880 [2:32:43<2:35:03,  1.45it/s] 
1|12404|Loss: 0.933010995388031:  48%|████▊     | 12404/25880 [2:32:43<2:38:10,  1.42it/s]
1|12405|Loss: 0.9443777799606323:  48%|████▊     | 12404/25880 [2:32:44<2:38:10,  1.42it/s]
1|12405|Loss: 0.9443777799606323:  48%|████▊     | 12405/25880 [2:32:44<2:40:23,  1.40it/s]
1|12406|Loss: 0.8584594130516052:  48%|████▊     | 12405/25880 [2:32:45<2:40:23,  1.40it/s]
1|12406|Loss: 0.8584594130516052:  48%|████▊     | 12406/25880 [2:32:45<2:45:04,  1.36it/s]
1|12407|Loss: 0.8221021294593811:  48%|████▊     | 12406/25880 [2:32:45<2:45:04,  1.36it/s]
1|12407|Loss: 0.8221021294593811:  48%|████▊     | 12407/25880 [2:32:46<2:44:23,  1.37it/s]
1|12408|Loss: 0.8351080417633057:  48%|████▊     | 12407/25880 [2:32:46<2:44:23,  1.37it/s]
1|12408|Loss: 0.8351080417633057:  48%|████▊     | 12408/25880 [2:32:46<2:50:02,  1.32it/s]
1|12409|Loss: 0.8407007455825806:  48%|████▊     | 12408/25880 [2:32:47<2:50:02,  1.32it/s]
1|12409|Loss: 0.8407007455825806:  48%|████▊     | 12409/25880 [2:32:47<2:55:11,  1.28it/s]
1|12410|Loss: 0.8827024698257446:  48%|████▊     | 12409/25880 [2:32:48<2:55:11,  1.28it/s]
1|12410|Loss: 0.8827024698257446:  48%|████▊     | 12410/25880 [2:32:48<2:59:24,  1.25it/s]
1|12411|Loss: 0.7103122472763062:  48%|████▊     | 12410/25880 [2:32:49<2:59:24,  1.25it/s]
1|12411|Loss: 0.7103122472763062:  48%|████▊     | 12411/25880 [2:32:49<2:51:49,  1.31it/s]
1|12412|Loss: 0.8495288491249084:  48%|████▊     | 12411/25880 [2:32:49<2:51:49,  1.31it/s]
1|12412|Loss: 0.8495288491249084:  48%|████▊     | 12412/25880 [2:32:49<2:37:25,  1.43it/s]
1|12413|Loss: 0.7779999375343323:  48%|████▊     | 12412/25880 [2:32:50<2:37:25,  1.43it/s]
1|12413|Loss: 0.7779999375343323:  48%|████▊     | 12413/25880 [2:32:50<2:35:10,  1.45it/s]
1|12414|Loss: 0.867249071598053:  48%|████▊     | 12413/25880 [2:32:50<2:35:10,  1.45it/s] 
1|12414|Loss: 0.867249071598053:  48%|████▊     | 12414/25880 [2:32:51<2:49:49,  1.32it/s]
1|12415|Loss: 0.6372647881507874:  48%|████▊     | 12414/25880 [2:32:51<2:49:49,  1.32it/s]
1|12415|Loss: 0.6372647881507874:  48%|████▊     | 12415/25880 [2:32:52<2:49:29,  1.32it/s]
1|12416|Loss: 0.8707244396209717:  48%|████▊     | 12415/25880 [2:32:52<2:49:29,  1.32it/s]
1|12416|Loss: 0.8707244396209717:  48%|████▊     | 12416/25880 [2:32:52<2:51:35,  1.31it/s]
1|12417|Loss: 0.8669779896736145:  48%|████▊     | 12416/25880 [2:32:53<2:51:35,  1.31it/s]
1|12417|Loss: 0.8669779896736145:  48%|████▊     | 12417/25880 [2:32:53<2:41:25,  1.39it/s]
1|12418|Loss: 0.7991896867752075:  48%|████▊     | 12417/25880 [2:32:54<2:41:25,  1.39it/s]
1|12418|Loss: 0.7991896867752075:  48%|████▊     | 12418/25880 [2:32:54<2:52:51,  1.30it/s]
1|12419|Loss: 0.8433108329772949:  48%|████▊     | 12418/25880 [2:32:54<2:52:51,  1.30it/s]
1|12419|Loss: 0.8433108329772949:  48%|████▊     | 12419/25880 [2:32:55<2:48:30,  1.33it/s]
1|12420|Loss: 0.7413886785507202:  48%|████▊     | 12419/25880 [2:32:55<2:48:30,  1.33it/s]
1|12420|Loss: 0.7413886785507202:  48%|████▊     | 12420/25880 [2:32:55<2:40:03,  1.40it/s]
1|12421|Loss: 0.8556572794914246:  48%|████▊     | 12420/25880 [2:32:56<2:40:03,  1.40it/s]
1|12421|Loss: 0.8556572794914246:  48%|████▊     | 12421/25880 [2:32:56<2:46:36,  1.35it/s]
1|12422|Loss: 0.8502282500267029:  48%|████▊     | 12421/25880 [2:32:57<2:46:36,  1.35it/s]
1|12422|Loss: 0.8502282500267029:  48%|████▊     | 12422/25880 [2:32:57<2:54:15,  1.29it/s]
1|12423|Loss: 0.7347978353500366:  48%|████▊     | 12422/25880 [2:32:57<2:54:15,  1.29it/s]
1|12423|Loss: 0.7347978353500366:  48%|████▊     | 12423/25880 [2:32:57<2:32:19,  1.47it/s]
1|12424|Loss: 0.8004521727561951:  48%|████▊     | 12423/25880 [2:32:58<2:32:19,  1.47it/s]
1|12424|Loss: 0.8004521727561951:  48%|████▊     | 12424/25880 [2:32:58<2:30:45,  1.49it/s]
1|12425|Loss: 0.9203922748565674:  48%|████▊     | 12424/25880 [2:32:58<2:30:45,  1.49it/s]
1|12425|Loss: 0.9203922748565674:  48%|████▊     | 12425/25880 [2:32:59<2:35:24,  1.44it/s]
1|12426|Loss: 0.7813358902931213:  48%|████▊     | 12425/25880 [2:32:59<2:35:24,  1.44it/s]
1|12426|Loss: 0.7813358902931213:  48%|████▊     | 12426/25880 [2:33:00<2:42:31,  1.38it/s]
1|12427|Loss: 0.7706515192985535:  48%|████▊     | 12426/25880 [2:33:00<2:42:31,  1.38it/s]
1|12427|Loss: 0.7706515192985535:  48%|████▊     | 12427/25880 [2:33:00<2:35:46,  1.44it/s]
1|12428|Loss: 0.7954474687576294:  48%|████▊     | 12427/25880 [2:33:01<2:35:46,  1.44it/s]
1|12428|Loss: 0.7954474687576294:  48%|████▊     | 12428/25880 [2:33:01<2:34:32,  1.45it/s]
1|12429|Loss: 0.7681975960731506:  48%|████▊     | 12428/25880 [2:33:01<2:34:32,  1.45it/s]
1|12429|Loss: 0.7681975960731506:  48%|████▊     | 12429/25880 [2:33:02<2:36:36,  1.43it/s]
1|12430|Loss: 0.9196157455444336:  48%|████▊     | 12429/25880 [2:33:02<2:36:36,  1.43it/s]
1|12430|Loss: 0.9196157455444336:  48%|████▊     | 12430/25880 [2:33:02<2:38:30,  1.41it/s]
1|12431|Loss: 0.9625606536865234:  48%|████▊     | 12430/25880 [2:33:03<2:38:30,  1.41it/s]
1|12431|Loss: 0.9625606536865234:  48%|████▊     | 12431/25880 [2:33:03<2:49:37,  1.32it/s]
1|12432|Loss: 0.8977909684181213:  48%|████▊     | 12431/25880 [2:33:04<2:49:37,  1.32it/s]
1|12432|Loss: 0.8977909684181213:  48%|████▊     | 12432/25880 [2:33:04<2:49:54,  1.32it/s]
1|12433|Loss: 0.6888560056686401:  48%|████▊     | 12432/25880 [2:33:04<2:49:54,  1.32it/s]
1|12433|Loss: 0.6888560056686401:  48%|████▊     | 12433/25880 [2:33:05<3:01:38,  1.23it/s]
1|12434|Loss: 0.720346212387085:  48%|████▊     | 12433/25880 [2:33:05<3:01:38,  1.23it/s] 
1|12434|Loss: 0.720346212387085:  48%|████▊     | 12434/25880 [2:33:05<2:45:11,  1.36it/s]
1|12435|Loss: 0.8090795278549194:  48%|████▊     | 12434/25880 [2:33:06<2:45:11,  1.36it/s]
1|12435|Loss: 0.8090795278549194:  48%|████▊     | 12435/25880 [2:33:06<2:52:37,  1.30it/s]
1|12436|Loss: 0.8691549301147461:  48%|████▊     | 12435/25880 [2:33:07<2:52:37,  1.30it/s]
1|12436|Loss: 0.8691549301147461:  48%|████▊     | 12436/25880 [2:33:07<2:57:04,  1.27it/s]
1|12437|Loss: 0.8334894180297852:  48%|████▊     | 12436/25880 [2:33:08<2:57:04,  1.27it/s]
1|12437|Loss: 0.8334894180297852:  48%|████▊     | 12437/25880 [2:33:08<2:52:30,  1.30it/s]
1|12438|Loss: 0.9613006711006165:  48%|████▊     | 12437/25880 [2:33:08<2:52:30,  1.30it/s]
1|12438|Loss: 0.9613006711006165:  48%|████▊     | 12438/25880 [2:33:09<2:44:21,  1.36it/s]
1|12439|Loss: 0.827340304851532:  48%|████▊     | 12438/25880 [2:33:09<2:44:21,  1.36it/s] 
1|12439|Loss: 0.827340304851532:  48%|████▊     | 12439/25880 [2:33:09<2:33:18,  1.46it/s]
1|12440|Loss: 0.8731911778450012:  48%|████▊     | 12439/25880 [2:33:09<2:33:18,  1.46it/s]
1|12440|Loss: 0.8731911778450012:  48%|████▊     | 12440/25880 [2:33:10<2:29:12,  1.50it/s]
1|12441|Loss: 0.752224326133728:  48%|████▊     | 12440/25880 [2:33:10<2:29:12,  1.50it/s] 
1|12441|Loss: 0.752224326133728:  48%|████▊     | 12441/25880 [2:33:11<2:40:36,  1.39it/s]
1|12442|Loss: 0.9458000063896179:  48%|████▊     | 12441/25880 [2:33:11<2:40:36,  1.39it/s]
1|12442|Loss: 0.9458000063896179:  48%|████▊     | 12442/25880 [2:33:11<2:32:07,  1.47it/s]
1|12443|Loss: 0.8991686105728149:  48%|████▊     | 12442/25880 [2:33:11<2:32:07,  1.47it/s]
1|12443|Loss: 0.8991686105728149:  48%|████▊     | 12443/25880 [2:33:12<2:24:45,  1.55it/s]
1|12444|Loss: 0.7877976894378662:  48%|████▊     | 12443/25880 [2:33:12<2:24:45,  1.55it/s]
1|12444|Loss: 0.7877976894378662:  48%|████▊     | 12444/25880 [2:33:12<2:29:29,  1.50it/s]
1|12445|Loss: 0.7341067790985107:  48%|████▊     | 12444/25880 [2:33:13<2:29:29,  1.50it/s]
1|12445|Loss: 0.7341067790985107:  48%|████▊     | 12445/25880 [2:33:13<2:27:58,  1.51it/s]
1|12446|Loss: 0.8205543160438538:  48%|████▊     | 12445/25880 [2:33:14<2:27:58,  1.51it/s]
1|12446|Loss: 0.8205543160438538:  48%|████▊     | 12446/25880 [2:33:14<2:36:13,  1.43it/s]
1|12447|Loss: 0.9036024212837219:  48%|████▊     | 12446/25880 [2:33:14<2:36:13,  1.43it/s]
1|12447|Loss: 0.9036024212837219:  48%|████▊     | 12447/25880 [2:33:15<2:42:50,  1.37it/s]
1|12448|Loss: 0.8200878500938416:  48%|████▊     | 12447/25880 [2:33:15<2:42:50,  1.37it/s]
1|12448|Loss: 0.8200878500938416:  48%|████▊     | 12448/25880 [2:33:15<2:42:25,  1.38it/s]
1|12449|Loss: 0.9428163170814514:  48%|████▊     | 12448/25880 [2:33:16<2:42:25,  1.38it/s]
1|12449|Loss: 0.9428163170814514:  48%|████▊     | 12449/25880 [2:33:16<2:45:07,  1.36it/s]
1|12450|Loss: 0.7474271059036255:  48%|████▊     | 12449/25880 [2:33:17<2:45:07,  1.36it/s]
1|12450|Loss: 0.7474271059036255:  48%|████▊     | 12450/25880 [2:33:17<2:40:49,  1.39it/s]
1|12451|Loss: 0.7849591374397278:  48%|████▊     | 12450/25880 [2:33:17<2:40:49,  1.39it/s]
1|12451|Loss: 0.7849591374397278:  48%|████▊     | 12451/25880 [2:33:18<2:40:23,  1.40it/s]
1|12452|Loss: 0.7834665775299072:  48%|████▊     | 12451/25880 [2:33:18<2:40:23,  1.40it/s]
1|12452|Loss: 0.7834665775299072:  48%|████▊     | 12452/25880 [2:33:18<2:48:21,  1.33it/s]
1|12453|Loss: 0.8097700476646423:  48%|████▊     | 12452/25880 [2:33:19<2:48:21,  1.33it/s]
1|12453|Loss: 0.8097700476646423:  48%|████▊     | 12453/25880 [2:33:19<2:52:36,  1.30it/s]
1|12454|Loss: 0.8313026428222656:  48%|████▊     | 12453/25880 [2:33:20<2:52:36,  1.30it/s]
1|12454|Loss: 0.8313026428222656:  48%|████▊     | 12454/25880 [2:33:20<2:57:09,  1.26it/s]
1|12455|Loss: 0.8515318036079407:  48%|████▊     | 12454/25880 [2:33:20<2:57:09,  1.26it/s]
1|12455|Loss: 0.8515318036079407:  48%|████▊     | 12455/25880 [2:33:21<2:58:05,  1.26it/s]
1|12456|Loss: 0.8491225838661194:  48%|████▊     | 12455/25880 [2:33:21<2:58:05,  1.26it/s]
1|12456|Loss: 0.8491225838661194:  48%|████▊     | 12456/25880 [2:33:22<2:55:29,  1.27it/s]
1|12457|Loss: 0.8006723523139954:  48%|████▊     | 12456/25880 [2:33:22<2:55:29,  1.27it/s]
1|12457|Loss: 0.8006723523139954:  48%|████▊     | 12457/25880 [2:33:22<2:58:20,  1.25it/s]
1|12458|Loss: 0.8330945372581482:  48%|████▊     | 12457/25880 [2:33:23<2:58:20,  1.25it/s]
1|12458|Loss: 0.8330945372581482:  48%|████▊     | 12458/25880 [2:33:23<2:56:02,  1.27it/s]
1|12459|Loss: 0.9692724347114563:  48%|████▊     | 12458/25880 [2:33:24<2:56:02,  1.27it/s]
1|12459|Loss: 0.9692724347114563:  48%|████▊     | 12459/25880 [2:33:24<2:53:00,  1.29it/s]
1|12460|Loss: 0.6894807815551758:  48%|████▊     | 12459/25880 [2:33:24<2:53:00,  1.29it/s]
1|12460|Loss: 0.6894807815551758:  48%|████▊     | 12460/25880 [2:33:25<3:04:46,  1.21it/s]
1|12461|Loss: 0.8736545443534851:  48%|████▊     | 12460/25880 [2:33:25<3:04:46,  1.21it/s]
1|12461|Loss: 0.8736545443534851:  48%|████▊     | 12461/25880 [2:33:26<3:10:00,  1.18it/s]
1|12462|Loss: 0.7928683161735535:  48%|████▊     | 12461/25880 [2:33:26<3:10:00,  1.18it/s]
1|12462|Loss: 0.7928683161735535:  48%|████▊     | 12462/25880 [2:33:27<3:02:38,  1.22it/s]
1|12463|Loss: 0.7665563821792603:  48%|████▊     | 12462/25880 [2:33:27<3:02:38,  1.22it/s]
1|12463|Loss: 0.7665563821792603:  48%|████▊     | 12463/25880 [2:33:27<3:06:50,  1.20it/s]
1|12464|Loss: 0.8665719032287598:  48%|████▊     | 12463/25880 [2:33:28<3:06:50,  1.20it/s]
1|12464|Loss: 0.8665719032287598:  48%|████▊     | 12464/25880 [2:33:28<3:01:05,  1.23it/s]
1|12465|Loss: 0.8599399328231812:  48%|████▊     | 12464/25880 [2:33:29<3:01:05,  1.23it/s]
1|12465|Loss: 0.8599399328231812:  48%|████▊     | 12465/25880 [2:33:29<3:00:46,  1.24it/s]
1|12466|Loss: 0.7885702252388:  48%|████▊     | 12465/25880 [2:33:29<3:00:46,  1.24it/s]   
1|12466|Loss: 0.7885702252388:  48%|████▊     | 12466/25880 [2:33:30<2:45:50,  1.35it/s]
1|12467|Loss: 0.6933107972145081:  48%|████▊     | 12466/25880 [2:33:30<2:45:50,  1.35it/s]
1|12467|Loss: 0.6933107972145081:  48%|████▊     | 12467/25880 [2:33:30<2:36:13,  1.43it/s]
1|12468|Loss: 0.7955905795097351:  48%|████▊     | 12467/25880 [2:33:31<2:36:13,  1.43it/s]
1|12468|Loss: 0.7955905795097351:  48%|████▊     | 12468/25880 [2:33:31<2:30:46,  1.48it/s]
1|12469|Loss: 0.8704622387886047:  48%|████▊     | 12468/25880 [2:33:31<2:30:46,  1.48it/s]
1|12469|Loss: 0.8704622387886047:  48%|████▊     | 12469/25880 [2:33:32<2:38:26,  1.41it/s]
1|12470|Loss: 0.8147363066673279:  48%|████▊     | 12469/25880 [2:33:32<2:38:26,  1.41it/s]
1|12470|Loss: 0.8147363066673279:  48%|████▊     | 12470/25880 [2:33:32<2:46:01,  1.35it/s]
1|12471|Loss: 0.8923822641372681:  48%|████▊     | 12470/25880 [2:33:33<2:46:01,  1.35it/s]
1|12471|Loss: 0.8923822641372681:  48%|████▊     | 12471/25880 [2:33:33<2:41:33,  1.38it/s]
1|12472|Loss: 0.8995891213417053:  48%|████▊     | 12471/25880 [2:33:33<2:41:33,  1.38it/s]
1|12472|Loss: 0.8995891213417053:  48%|████▊     | 12472/25880 [2:33:34<2:38:54,  1.41it/s]
1|12473|Loss: 0.6944493055343628:  48%|████▊     | 12472/25880 [2:33:34<2:38:54,  1.41it/s]
1|12473|Loss: 0.6944493055343628:  48%|████▊     | 12473/25880 [2:33:35<2:52:27,  1.30it/s]
1|12474|Loss: 0.7603506445884705:  48%|████▊     | 12473/25880 [2:33:35<2:52:27,  1.30it/s]
1|12474|Loss: 0.7603506445884705:  48%|████▊     | 12474/25880 [2:33:35<2:47:14,  1.34it/s]
1|12475|Loss: 0.8862809538841248:  48%|████▊     | 12474/25880 [2:33:36<2:47:14,  1.34it/s]
1|12475|Loss: 0.8862809538841248:  48%|████▊     | 12475/25880 [2:33:36<2:52:10,  1.30it/s]
1|12476|Loss: 0.7880262136459351:  48%|████▊     | 12475/25880 [2:33:37<2:52:10,  1.30it/s]
1|12476|Loss: 0.7880262136459351:  48%|████▊     | 12476/25880 [2:33:37<2:40:38,  1.39it/s]
1|12477|Loss: 0.8923417329788208:  48%|████▊     | 12476/25880 [2:33:37<2:40:38,  1.39it/s]
1|12477|Loss: 0.8923417329788208:  48%|████▊     | 12477/25880 [2:33:37<2:38:27,  1.41it/s]
1|12478|Loss: 0.7530028820037842:  48%|████▊     | 12477/25880 [2:33:38<2:38:27,  1.41it/s]
1|12478|Loss: 0.7530028820037842:  48%|████▊     | 12478/25880 [2:33:38<2:45:56,  1.35it/s]
1|12479|Loss: 0.8572945594787598:  48%|████▊     | 12478/25880 [2:33:39<2:45:56,  1.35it/s]
1|12479|Loss: 0.8572945594787598:  48%|████▊     | 12479/25880 [2:33:39<2:41:18,  1.38it/s]
1|12480|Loss: 0.7936744689941406:  48%|████▊     | 12479/25880 [2:33:39<2:41:18,  1.38it/s]
1|12480|Loss: 0.7936744689941406:  48%|████▊     | 12480/25880 [2:33:40<2:40:10,  1.39it/s]
1|12481|Loss: 0.8156272768974304:  48%|████▊     | 12480/25880 [2:33:40<2:40:10,  1.39it/s]
1|12481|Loss: 0.8156272768974304:  48%|████▊     | 12481/25880 [2:33:41<2:51:10,  1.30it/s]
1|12482|Loss: 0.8096309900283813:  48%|████▊     | 12481/25880 [2:33:41<2:51:10,  1.30it/s]
1|12482|Loss: 0.8096309900283813:  48%|████▊     | 12482/25880 [2:33:41<2:56:41,  1.26it/s]
1|12483|Loss: 0.8070947527885437:  48%|████▊     | 12482/25880 [2:33:42<2:56:41,  1.26it/s]
1|12483|Loss: 0.8070947527885437:  48%|████▊     | 12483/25880 [2:33:42<2:35:33,  1.44it/s]
1|12484|Loss: 0.818793535232544:  48%|████▊     | 12483/25880 [2:33:42<2:35:33,  1.44it/s] 
1|12484|Loss: 0.818793535232544:  48%|████▊     | 12484/25880 [2:33:43<2:34:13,  1.45it/s]
1|12485|Loss: 0.8147794604301453:  48%|████▊     | 12484/25880 [2:33:43<2:34:13,  1.45it/s]
1|12485|Loss: 0.8147794604301453:  48%|████▊     | 12485/25880 [2:33:43<2:41:34,  1.38it/s]
1|12486|Loss: 0.8736732602119446:  48%|████▊     | 12485/25880 [2:33:44<2:41:34,  1.38it/s]
1|12486|Loss: 0.8736732602119446:  48%|████▊     | 12486/25880 [2:33:44<2:37:42,  1.42it/s]
1|12487|Loss: 0.8694126605987549:  48%|████▊     | 12486/25880 [2:33:44<2:37:42,  1.42it/s]
1|12487|Loss: 0.8694126605987549:  48%|████▊     | 12487/25880 [2:33:45<2:36:26,  1.43it/s]
1|12488|Loss: 0.8000690937042236:  48%|████▊     | 12487/25880 [2:33:45<2:36:26,  1.43it/s]
1|12488|Loss: 0.8000690937042236:  48%|████▊     | 12488/25880 [2:33:45<2:38:37,  1.41it/s]
1|12489|Loss: 0.8270058035850525:  48%|████▊     | 12488/25880 [2:33:46<2:38:37,  1.41it/s]
1|12489|Loss: 0.8270058035850525:  48%|████▊     | 12489/25880 [2:33:46<2:29:34,  1.49it/s]
1|12490|Loss: 0.8198403716087341:  48%|████▊     | 12489/25880 [2:33:46<2:29:34,  1.49it/s]
1|12490|Loss: 0.8198403716087341:  48%|████▊     | 12490/25880 [2:33:47<2:36:03,  1.43it/s]
1|12491|Loss: 0.783637285232544:  48%|████▊     | 12490/25880 [2:33:47<2:36:03,  1.43it/s] 
1|12491|Loss: 0.783637285232544:  48%|████▊     | 12491/25880 [2:33:48<2:39:17,  1.40it/s]
1|12492|Loss: 0.9033140540122986:  48%|████▊     | 12491/25880 [2:33:48<2:39:17,  1.40it/s]
1|12492|Loss: 0.9033140540122986:  48%|████▊     | 12492/25880 [2:33:48<2:40:38,  1.39it/s]
1|12493|Loss: 0.7413031458854675:  48%|████▊     | 12492/25880 [2:33:49<2:40:38,  1.39it/s]
1|12493|Loss: 0.7413031458854675:  48%|████▊     | 12493/25880 [2:33:49<2:49:21,  1.32it/s]
1|12494|Loss: 0.6706715822219849:  48%|████▊     | 12493/25880 [2:33:50<2:49:21,  1.32it/s]
1|12494|Loss: 0.6706715822219849:  48%|████▊     | 12494/25880 [2:33:50<2:49:37,  1.32it/s]
1|12495|Loss: 0.8281653523445129:  48%|████▊     | 12494/25880 [2:33:50<2:49:37,  1.32it/s]
1|12495|Loss: 0.8281653523445129:  48%|████▊     | 12495/25880 [2:33:51<2:41:25,  1.38it/s]
1|12496|Loss: 0.8900101780891418:  48%|████▊     | 12495/25880 [2:33:51<2:41:25,  1.38it/s]
1|12496|Loss: 0.8900101780891418:  48%|████▊     | 12496/25880 [2:33:51<2:40:52,  1.39it/s]
1|12497|Loss: 0.7744086384773254:  48%|████▊     | 12496/25880 [2:33:52<2:40:52,  1.39it/s]
1|12497|Loss: 0.7744086384773254:  48%|████▊     | 12497/25880 [2:33:52<2:45:37,  1.35it/s]
1|12498|Loss: 0.8606202006340027:  48%|████▊     | 12497/25880 [2:33:52<2:45:37,  1.35it/s]
1|12498|Loss: 0.8606202006340027:  48%|████▊     | 12498/25880 [2:33:53<2:41:12,  1.38it/s]
1|12499|Loss: 0.9924893975257874:  48%|████▊     | 12498/25880 [2:33:53<2:41:12,  1.38it/s]
1|12499|Loss: 0.9924893975257874:  48%|████▊     | 12499/25880 [2:33:53<2:39:03,  1.40it/s]
1|12500|Loss: 0.8022231459617615:  48%|████▊     | 12499/25880 [2:33:54<2:39:03,  1.40it/s]
1|12500|Loss: 0.8022231459617615:  48%|████▊     | 12500/25880 [2:33:54<2:45:21,  1.35it/s]
1|12501|Loss: 0.7658414244651794:  48%|████▊     | 12500/25880 [2:33:55<2:45:21,  1.35it/s]
1|12501|Loss: 0.7658414244651794:  48%|████▊     | 12501/25880 [2:33:55<2:44:13,  1.36it/s]
1|12502|Loss: 0.8205787539482117:  48%|████▊     | 12501/25880 [2:33:55<2:44:13,  1.36it/s]
1|12502|Loss: 0.8205787539482117:  48%|████▊     | 12502/25880 [2:33:56<2:35:13,  1.44it/s]
1|12503|Loss: 0.8651419878005981:  48%|████▊     | 12502/25880 [2:33:56<2:35:13,  1.44it/s]
1|12503|Loss: 0.8651419878005981:  48%|████▊     | 12503/25880 [2:33:56<2:43:20,  1.36it/s]
1|12504|Loss: 0.7962740659713745:  48%|████▊     | 12503/25880 [2:33:57<2:43:20,  1.36it/s]
1|12504|Loss: 0.7962740659713745:  48%|████▊     | 12504/25880 [2:33:57<2:45:29,  1.35it/s]
1|12505|Loss: 0.7407583594322205:  48%|████▊     | 12504/25880 [2:33:58<2:45:29,  1.35it/s]
1|12505|Loss: 0.7407583594322205:  48%|████▊     | 12505/25880 [2:33:58<2:52:53,  1.29it/s]
1|12506|Loss: 0.9177106022834778:  48%|████▊     | 12505/25880 [2:33:58<2:52:53,  1.29it/s]
1|12506|Loss: 0.9177106022834778:  48%|████▊     | 12506/25880 [2:33:59<2:58:44,  1.25it/s]
1|12507|Loss: 0.8617268204689026:  48%|████▊     | 12506/25880 [2:33:59<2:58:44,  1.25it/s]
1|12507|Loss: 0.8617268204689026:  48%|████▊     | 12507/25880 [2:34:00<2:55:48,  1.27it/s]
1|12508|Loss: 0.9510499835014343:  48%|████▊     | 12507/25880 [2:34:00<2:55:48,  1.27it/s]
1|12508|Loss: 0.9510499835014343:  48%|████▊     | 12508/25880 [2:34:00<2:40:01,  1.39it/s]
1|12509|Loss: 0.8478453755378723:  48%|████▊     | 12508/25880 [2:34:00<2:40:01,  1.39it/s]
1|12509|Loss: 0.8478453755378723:  48%|████▊     | 12509/25880 [2:34:01<2:36:14,  1.43it/s]
1|12510|Loss: 0.8224501609802246:  48%|████▊     | 12509/25880 [2:34:01<2:36:14,  1.43it/s]
1|12510|Loss: 0.8224501609802246:  48%|████▊     | 12510/25880 [2:34:01<2:31:41,  1.47it/s]
1|12511|Loss: 0.7801486849784851:  48%|████▊     | 12510/25880 [2:34:02<2:31:41,  1.47it/s]
1|12511|Loss: 0.7801486849784851:  48%|████▊     | 12511/25880 [2:34:02<2:27:36,  1.51it/s]
1|12512|Loss: 1.051005244255066:  48%|████▊     | 12511/25880 [2:34:02<2:27:36,  1.51it/s] 
1|12512|Loss: 1.051005244255066:  48%|████▊     | 12512/25880 [2:34:03<2:24:26,  1.54it/s]
1|12513|Loss: 0.8166854977607727:  48%|████▊     | 12512/25880 [2:34:03<2:24:26,  1.54it/s]
1|12513|Loss: 0.8166854977607727:  48%|████▊     | 12513/25880 [2:34:03<2:26:57,  1.52it/s]
1|12514|Loss: 0.8451868891716003:  48%|████▊     | 12513/25880 [2:34:04<2:26:57,  1.52it/s]
1|12514|Loss: 0.8451868891716003:  48%|████▊     | 12514/25880 [2:34:04<2:37:31,  1.41it/s]
1|12515|Loss: 1.1013753414154053:  48%|████▊     | 12514/25880 [2:34:05<2:37:31,  1.41it/s]
1|12515|Loss: 1.1013753414154053:  48%|████▊     | 12515/25880 [2:34:05<2:36:17,  1.43it/s]
1|12516|Loss: 1.0100970268249512:  48%|████▊     | 12515/25880 [2:34:05<2:36:17,  1.43it/s]
1|12516|Loss: 1.0100970268249512:  48%|████▊     | 12516/25880 [2:34:06<2:36:42,  1.42it/s]
1|12517|Loss: 0.8121639490127563:  48%|████▊     | 12516/25880 [2:34:06<2:36:42,  1.42it/s]
1|12517|Loss: 0.8121639490127563:  48%|████▊     | 12517/25880 [2:34:06<2:44:54,  1.35it/s]
1|12518|Loss: 0.957488477230072:  48%|████▊     | 12517/25880 [2:34:07<2:44:54,  1.35it/s] 
1|12518|Loss: 0.957488477230072:  48%|████▊     | 12518/25880 [2:34:07<2:34:39,  1.44it/s]
1|12519|Loss: 0.7409363389015198:  48%|████▊     | 12518/25880 [2:34:07<2:34:39,  1.44it/s]
1|12519|Loss: 0.7409363389015198:  48%|████▊     | 12519/25880 [2:34:07<2:19:08,  1.60it/s]
1|12520|Loss: 0.8674445748329163:  48%|████▊     | 12519/25880 [2:34:08<2:19:08,  1.60it/s]
1|12520|Loss: 0.8674445748329163:  48%|████▊     | 12520/25880 [2:34:08<2:27:45,  1.51it/s]
1|12521|Loss: 0.8166295289993286:  48%|████▊     | 12520/25880 [2:34:09<2:27:45,  1.51it/s]
1|12521|Loss: 0.8166295289993286:  48%|████▊     | 12521/25880 [2:34:09<2:34:25,  1.44it/s]
1|12522|Loss: 0.8350251317024231:  48%|████▊     | 12521/25880 [2:34:09<2:34:25,  1.44it/s]
1|12522|Loss: 0.8350251317024231:  48%|████▊     | 12522/25880 [2:34:10<2:32:58,  1.46it/s]
1|12523|Loss: 0.8937804102897644:  48%|████▊     | 12522/25880 [2:34:10<2:32:58,  1.46it/s]
1|12523|Loss: 0.8937804102897644:  48%|████▊     | 12523/25880 [2:34:10<2:35:49,  1.43it/s]
1|12524|Loss: 0.8318406939506531:  48%|████▊     | 12523/25880 [2:34:11<2:35:49,  1.43it/s]
1|12524|Loss: 0.8318406939506531:  48%|████▊     | 12524/25880 [2:34:11<2:41:23,  1.38it/s]
1|12525|Loss: 0.8075243830680847:  48%|████▊     | 12524/25880 [2:34:12<2:41:23,  1.38it/s]
1|12525|Loss: 0.8075243830680847:  48%|████▊     | 12525/25880 [2:34:12<2:41:10,  1.38it/s]
1|12526|Loss: 0.8212298154830933:  48%|████▊     | 12525/25880 [2:34:12<2:41:10,  1.38it/s]
1|12526|Loss: 0.8212298154830933:  48%|████▊     | 12526/25880 [2:34:13<2:40:07,  1.39it/s]
1|12527|Loss: 0.7723644971847534:  48%|████▊     | 12526/25880 [2:34:13<2:40:07,  1.39it/s]
1|12527|Loss: 0.7723644971847534:  48%|████▊     | 12527/25880 [2:34:13<2:45:38,  1.34it/s]
1|12528|Loss: 0.8743999004364014:  48%|████▊     | 12527/25880 [2:34:14<2:45:38,  1.34it/s]
1|12528|Loss: 0.8743999004364014:  48%|████▊     | 12528/25880 [2:34:14<2:50:11,  1.31it/s]
1|12529|Loss: 0.8195653557777405:  48%|████▊     | 12528/25880 [2:34:15<2:50:11,  1.31it/s]
1|12529|Loss: 0.8195653557777405:  48%|████▊     | 12529/25880 [2:34:15<2:51:35,  1.30it/s]
1|12530|Loss: 0.9157379865646362:  48%|████▊     | 12529/25880 [2:34:15<2:51:35,  1.30it/s]
1|12530|Loss: 0.9157379865646362:  48%|████▊     | 12530/25880 [2:34:16<2:36:56,  1.42it/s]
1|12531|Loss: 0.8462148308753967:  48%|████▊     | 12530/25880 [2:34:16<2:36:56,  1.42it/s]
1|12531|Loss: 0.8462148308753967:  48%|████▊     | 12531/25880 [2:34:16<2:36:00,  1.43it/s]
1|12532|Loss: 0.8424155116081238:  48%|████▊     | 12531/25880 [2:34:17<2:36:00,  1.43it/s]
1|12532|Loss: 0.8424155116081238:  48%|████▊     | 12532/25880 [2:34:17<2:33:40,  1.45it/s]
1|12533|Loss: 0.8133381605148315:  48%|████▊     | 12532/25880 [2:34:17<2:33:40,  1.45it/s]
1|12533|Loss: 0.8133381605148315:  48%|████▊     | 12533/25880 [2:34:18<2:29:16,  1.49it/s]
1|12534|Loss: 0.8941072225570679:  48%|████▊     | 12533/25880 [2:34:18<2:29:16,  1.49it/s]
1|12534|Loss: 0.8941072225570679:  48%|████▊     | 12534/25880 [2:34:18<2:32:01,  1.46it/s]
1|12535|Loss: 0.805044412612915:  48%|████▊     | 12534/25880 [2:34:19<2:32:01,  1.46it/s] 
1|12535|Loss: 0.805044412612915:  48%|████▊     | 12535/25880 [2:34:19<2:40:25,  1.39it/s]
1|12536|Loss: 0.797936201095581:  48%|████▊     | 12535/25880 [2:34:19<2:40:25,  1.39it/s]
1|12536|Loss: 0.797936201095581:  48%|████▊     | 12536/25880 [2:34:20<2:46:12,  1.34it/s]
1|12537|Loss: 0.8318822383880615:  48%|████▊     | 12536/25880 [2:34:20<2:46:12,  1.34it/s]
1|12537|Loss: 0.8318822383880615:  48%|████▊     | 12537/25880 [2:34:21<2:46:21,  1.34it/s]
1|12538|Loss: 0.781378984451294:  48%|████▊     | 12537/25880 [2:34:21<2:46:21,  1.34it/s] 
1|12538|Loss: 0.781378984451294:  48%|████▊     | 12538/25880 [2:34:21<2:39:24,  1.39it/s]
1|12539|Loss: 0.9264348149299622:  48%|████▊     | 12538/25880 [2:34:22<2:39:24,  1.39it/s]
1|12539|Loss: 0.9264348149299622:  48%|████▊     | 12539/25880 [2:34:22<2:42:09,  1.37it/s]
1|12540|Loss: 0.9142370820045471:  48%|████▊     | 12539/25880 [2:34:22<2:42:09,  1.37it/s]
1|12540|Loss: 0.9142370820045471:  48%|████▊     | 12540/25880 [2:34:23<2:38:23,  1.40it/s]
1|12541|Loss: 0.8684225678443909:  48%|████▊     | 12540/25880 [2:34:23<2:38:23,  1.40it/s]
1|12541|Loss: 0.8684225678443909:  48%|████▊     | 12541/25880 [2:34:23<2:38:21,  1.40it/s]
1|12542|Loss: 0.8898923993110657:  48%|████▊     | 12541/25880 [2:34:24<2:38:21,  1.40it/s]
1|12542|Loss: 0.8898923993110657:  48%|████▊     | 12542/25880 [2:34:24<2:39:53,  1.39it/s]
1|12543|Loss: 0.8546051383018494:  48%|████▊     | 12542/25880 [2:34:25<2:39:53,  1.39it/s]
1|12543|Loss: 0.8546051383018494:  48%|████▊     | 12543/25880 [2:34:25<2:39:27,  1.39it/s]
1|12544|Loss: 0.7255521416664124:  48%|████▊     | 12543/25880 [2:34:25<2:39:27,  1.39it/s]
1|12544|Loss: 0.7255521416664124:  48%|████▊     | 12544/25880 [2:34:25<2:26:40,  1.52it/s]
1|12545|Loss: 0.9006589651107788:  48%|████▊     | 12544/25880 [2:34:26<2:26:40,  1.52it/s]
1|12545|Loss: 0.9006589651107788:  48%|████▊     | 12545/25880 [2:34:26<2:34:10,  1.44it/s]
1|12546|Loss: 0.9357041716575623:  48%|████▊     | 12545/25880 [2:34:27<2:34:10,  1.44it/s]
1|12546|Loss: 0.9357041716575623:  48%|████▊     | 12546/25880 [2:34:27<2:44:47,  1.35it/s]
1|12547|Loss: 0.8374643325805664:  48%|████▊     | 12546/25880 [2:34:27<2:44:47,  1.35it/s]
1|12547|Loss: 0.8374643325805664:  48%|████▊     | 12547/25880 [2:34:28<2:49:02,  1.31it/s]
1|12548|Loss: 0.824099600315094:  48%|████▊     | 12547/25880 [2:34:28<2:49:02,  1.31it/s] 
1|12548|Loss: 0.824099600315094:  48%|████▊     | 12548/25880 [2:34:28<2:43:11,  1.36it/s]
1|12549|Loss: 0.7325697541236877:  48%|████▊     | 12548/25880 [2:34:29<2:43:11,  1.36it/s]
1|12549|Loss: 0.7325697541236877:  48%|████▊     | 12549/25880 [2:34:29<2:41:49,  1.37it/s]
1|12550|Loss: 0.8884795904159546:  48%|████▊     | 12549/25880 [2:34:30<2:41:49,  1.37it/s]
1|12550|Loss: 0.8884795904159546:  48%|████▊     | 12550/25880 [2:34:30<2:51:49,  1.29it/s]
1|12551|Loss: 0.9231558442115784:  48%|████▊     | 12550/25880 [2:34:30<2:51:49,  1.29it/s]
1|12551|Loss: 0.9231558442115784:  48%|████▊     | 12551/25880 [2:34:31<2:45:09,  1.35it/s]
1|12552|Loss: 0.8028437495231628:  48%|████▊     | 12551/25880 [2:34:31<2:45:09,  1.35it/s]
1|12552|Loss: 0.8028437495231628:  49%|████▊     | 12552/25880 [2:34:31<2:36:34,  1.42it/s]
1|12553|Loss: 0.7711380124092102:  49%|████▊     | 12552/25880 [2:34:32<2:36:34,  1.42it/s]
1|12553|Loss: 0.7711380124092102:  49%|████▊     | 12553/25880 [2:34:32<2:28:45,  1.49it/s]
1|12554|Loss: 0.8724855780601501:  49%|████▊     | 12553/25880 [2:34:32<2:28:45,  1.49it/s]
1|12554|Loss: 0.8724855780601501:  49%|████▊     | 12554/25880 [2:34:33<2:25:54,  1.52it/s]
1|12555|Loss: 1.0075699090957642:  49%|████▊     | 12554/25880 [2:34:33<2:25:54,  1.52it/s]
1|12555|Loss: 1.0075699090957642:  49%|████▊     | 12555/25880 [2:34:33<2:33:24,  1.45it/s]
1|12556|Loss: 0.7435406446456909:  49%|████▊     | 12555/25880 [2:34:34<2:33:24,  1.45it/s]
1|12556|Loss: 0.7435406446456909:  49%|████▊     | 12556/25880 [2:34:34<2:50:30,  1.30it/s]
1|12557|Loss: 0.8286460638046265:  49%|████▊     | 12556/25880 [2:34:35<2:50:30,  1.30it/s]
1|12557|Loss: 0.8286460638046265:  49%|████▊     | 12557/25880 [2:34:35<2:50:30,  1.30it/s]
1|12558|Loss: 0.7614913582801819:  49%|████▊     | 12557/25880 [2:34:36<2:50:30,  1.30it/s]
1|12558|Loss: 0.7614913582801819:  49%|████▊     | 12558/25880 [2:34:36<3:01:05,  1.23it/s]
1|12559|Loss: 0.8770979046821594:  49%|████▊     | 12558/25880 [2:34:36<3:01:05,  1.23it/s]
1|12559|Loss: 0.8770979046821594:  49%|████▊     | 12559/25880 [2:34:37<3:03:35,  1.21it/s]
1|12560|Loss: 0.7812750339508057:  49%|████▊     | 12559/25880 [2:34:37<3:03:35,  1.21it/s]
1|12560|Loss: 0.7812750339508057:  49%|████▊     | 12560/25880 [2:34:37<2:53:21,  1.28it/s]
1|12561|Loss: 0.8429853916168213:  49%|████▊     | 12560/25880 [2:34:38<2:53:21,  1.28it/s]
1|12561|Loss: 0.8429853916168213:  49%|████▊     | 12561/25880 [2:34:38<2:47:31,  1.33it/s]
1|12562|Loss: 0.8186855316162109:  49%|████▊     | 12561/25880 [2:34:39<2:47:31,  1.33it/s]
1|12562|Loss: 0.8186855316162109:  49%|████▊     | 12562/25880 [2:34:39<2:52:15,  1.29it/s]
1|12563|Loss: 0.8626212477684021:  49%|████▊     | 12562/25880 [2:34:39<2:52:15,  1.29it/s]
1|12563|Loss: 0.8626212477684021:  49%|████▊     | 12563/25880 [2:34:39<2:33:10,  1.45it/s]
1|12564|Loss: 0.8905712962150574:  49%|████▊     | 12563/25880 [2:34:40<2:33:10,  1.45it/s]
1|12564|Loss: 0.8905712962150574:  49%|████▊     | 12564/25880 [2:34:40<2:34:36,  1.44it/s]
1|12565|Loss: 0.7911980152130127:  49%|████▊     | 12564/25880 [2:34:41<2:34:36,  1.44it/s]
1|12565|Loss: 0.7911980152130127:  49%|████▊     | 12565/25880 [2:34:41<2:38:18,  1.40it/s]
1|12566|Loss: 0.8775081634521484:  49%|████▊     | 12565/25880 [2:34:41<2:38:18,  1.40it/s]
1|12566|Loss: 0.8775081634521484:  49%|████▊     | 12566/25880 [2:34:42<2:30:21,  1.48it/s]
1|12567|Loss: 0.8707902431488037:  49%|████▊     | 12566/25880 [2:34:42<2:30:21,  1.48it/s]
1|12567|Loss: 0.8707902431488037:  49%|████▊     | 12567/25880 [2:34:42<2:26:19,  1.52it/s]
1|12568|Loss: 0.8221030235290527:  49%|████▊     | 12567/25880 [2:34:43<2:26:19,  1.52it/s]
1|12568|Loss: 0.8221030235290527:  49%|████▊     | 12568/25880 [2:34:43<2:28:29,  1.49it/s]
1|12569|Loss: 0.8049870729446411:  49%|████▊     | 12568/25880 [2:34:43<2:28:29,  1.49it/s]
1|12569|Loss: 0.8049870729446411:  49%|████▊     | 12569/25880 [2:34:44<2:32:19,  1.46it/s]
1|12570|Loss: 0.864026665687561:  49%|████▊     | 12569/25880 [2:34:44<2:32:19,  1.46it/s] 
1|12570|Loss: 0.864026665687561:  49%|████▊     | 12570/25880 [2:34:44<2:41:36,  1.37it/s]
1|12571|Loss: 0.9162830710411072:  49%|████▊     | 12570/25880 [2:34:45<2:41:36,  1.37it/s]
1|12571|Loss: 0.9162830710411072:  49%|████▊     | 12571/25880 [2:34:45<2:42:03,  1.37it/s]
1|12572|Loss: 0.721663236618042:  49%|████▊     | 12571/25880 [2:34:46<2:42:03,  1.37it/s] 
1|12572|Loss: 0.721663236618042:  49%|████▊     | 12572/25880 [2:34:46<2:39:43,  1.39it/s]
1|12573|Loss: 0.8546062707901001:  49%|████▊     | 12572/25880 [2:34:46<2:39:43,  1.39it/s]
1|12573|Loss: 0.8546062707901001:  49%|████▊     | 12573/25880 [2:34:46<2:28:58,  1.49it/s]
1|12574|Loss: 0.8385918736457825:  49%|████▊     | 12573/25880 [2:34:47<2:28:58,  1.49it/s]
1|12574|Loss: 0.8385918736457825:  49%|████▊     | 12574/25880 [2:34:47<2:15:23,  1.64it/s]
1|12575|Loss: 0.7901347279548645:  49%|████▊     | 12574/25880 [2:34:47<2:15:23,  1.64it/s]
1|12575|Loss: 0.7901347279548645:  49%|████▊     | 12575/25880 [2:34:48<2:24:45,  1.53it/s]
1|12576|Loss: 0.8654685020446777:  49%|████▊     | 12575/25880 [2:34:48<2:24:45,  1.53it/s]
1|12576|Loss: 0.8654685020446777:  49%|████▊     | 12576/25880 [2:34:48<2:19:57,  1.58it/s]
1|12577|Loss: 0.7435773611068726:  49%|████▊     | 12576/25880 [2:34:49<2:19:57,  1.58it/s]
1|12577|Loss: 0.7435773611068726:  49%|████▊     | 12577/25880 [2:34:49<2:26:40,  1.51it/s]
1|12578|Loss: 0.7631820440292358:  49%|████▊     | 12577/25880 [2:34:49<2:26:40,  1.51it/s]
1|12578|Loss: 0.7631820440292358:  49%|████▊     | 12578/25880 [2:34:50<2:32:23,  1.45it/s]
1|12579|Loss: 0.7624121308326721:  49%|████▊     | 12578/25880 [2:34:50<2:32:23,  1.45it/s]
1|12579|Loss: 0.7624121308326721:  49%|████▊     | 12579/25880 [2:34:51<2:41:21,  1.37it/s]
1|12580|Loss: 0.9685229063034058:  49%|████▊     | 12579/25880 [2:34:51<2:41:21,  1.37it/s]
1|12580|Loss: 0.9685229063034058:  49%|████▊     | 12580/25880 [2:34:51<2:48:58,  1.31it/s]
1|12581|Loss: 0.9422200918197632:  49%|████▊     | 12580/25880 [2:34:52<2:48:58,  1.31it/s]
1|12581|Loss: 0.9422200918197632:  49%|████▊     | 12581/25880 [2:34:52<2:43:35,  1.35it/s]
1|12582|Loss: 0.9511238932609558:  49%|████▊     | 12581/25880 [2:34:52<2:43:35,  1.35it/s]
1|12582|Loss: 0.9511238932609558:  49%|████▊     | 12582/25880 [2:34:53<2:41:53,  1.37it/s]
1|12583|Loss: 0.7044210433959961:  49%|████▊     | 12582/25880 [2:34:53<2:41:53,  1.37it/s]
1|12583|Loss: 0.7044210433959961:  49%|████▊     | 12583/25880 [2:34:54<2:46:47,  1.33it/s]
1|12584|Loss: 0.909824013710022:  49%|████▊     | 12583/25880 [2:34:54<2:46:47,  1.33it/s] 
1|12584|Loss: 0.909824013710022:  49%|████▊     | 12584/25880 [2:34:54<2:49:47,  1.31it/s]
1|12585|Loss: 0.7335419654846191:  49%|████▊     | 12584/25880 [2:34:55<2:49:47,  1.31it/s]
1|12585|Loss: 0.7335419654846191:  49%|████▊     | 12585/25880 [2:34:55<2:46:42,  1.33it/s]
1|12586|Loss: 0.7818893790245056:  49%|████▊     | 12585/25880 [2:34:55<2:46:42,  1.33it/s]
1|12586|Loss: 0.7818893790245056:  49%|████▊     | 12586/25880 [2:34:56<2:48:58,  1.31it/s]
1|12587|Loss: 0.7331951260566711:  49%|████▊     | 12586/25880 [2:34:56<2:48:58,  1.31it/s]
1|12587|Loss: 0.7331951260566711:  49%|████▊     | 12587/25880 [2:34:57<2:51:00,  1.30it/s]
1|12588|Loss: 0.8581854701042175:  49%|████▊     | 12587/25880 [2:34:57<2:51:00,  1.30it/s]
1|12588|Loss: 0.8581854701042175:  49%|████▊     | 12588/25880 [2:34:57<2:54:31,  1.27it/s]
1|12589|Loss: 0.9033426642417908:  49%|████▊     | 12588/25880 [2:34:58<2:54:31,  1.27it/s]
1|12589|Loss: 0.9033426642417908:  49%|████▊     | 12589/25880 [2:34:58<2:58:15,  1.24it/s]
1|12590|Loss: 0.6410547494888306:  49%|████▊     | 12589/25880 [2:34:59<2:58:15,  1.24it/s]
1|12590|Loss: 0.6410547494888306:  49%|████▊     | 12590/25880 [2:34:59<3:02:38,  1.21it/s]
1|12591|Loss: 0.7608383893966675:  49%|████▊     | 12590/25880 [2:35:00<3:02:38,  1.21it/s]
1|12591|Loss: 0.7608383893966675:  49%|████▊     | 12591/25880 [2:35:00<3:04:38,  1.20it/s]
1|12592|Loss: 0.9760719537734985:  49%|████▊     | 12591/25880 [2:35:00<3:04:38,  1.20it/s]
1|12592|Loss: 0.9760719537734985:  49%|████▊     | 12592/25880 [2:35:01<2:48:11,  1.32it/s]
1|12593|Loss: 0.8692735433578491:  49%|████▊     | 12592/25880 [2:35:01<2:48:11,  1.32it/s]
1|12593|Loss: 0.8692735433578491:  49%|████▊     | 12593/25880 [2:35:01<2:41:31,  1.37it/s]
1|12594|Loss: 0.8939348459243774:  49%|████▊     | 12593/25880 [2:35:02<2:41:31,  1.37it/s]
1|12594|Loss: 0.8939348459243774:  49%|████▊     | 12594/25880 [2:35:02<2:35:00,  1.43it/s]
1|12595|Loss: 0.9627825021743774:  49%|████▊     | 12594/25880 [2:35:02<2:35:00,  1.43it/s]
1|12595|Loss: 0.9627825021743774:  49%|████▊     | 12595/25880 [2:35:03<2:48:59,  1.31it/s]
1|12596|Loss: 0.8481760025024414:  49%|████▊     | 12595/25880 [2:35:03<2:48:59,  1.31it/s]
1|12596|Loss: 0.8481760025024414:  49%|████▊     | 12596/25880 [2:35:04<2:51:59,  1.29it/s]
1|12597|Loss: 0.828744113445282:  49%|████▊     | 12596/25880 [2:35:04<2:51:59,  1.29it/s] 
1|12597|Loss: 0.828744113445282:  49%|████▊     | 12597/25880 [2:35:04<2:53:28,  1.28it/s]
1|12598|Loss: 0.9014413356781006:  49%|████▊     | 12597/25880 [2:35:05<2:53:28,  1.28it/s]
1|12598|Loss: 0.9014413356781006:  49%|████▊     | 12598/25880 [2:35:05<2:56:22,  1.26it/s]
1|12599|Loss: 0.8243176937103271:  49%|████▊     | 12598/25880 [2:35:06<2:56:22,  1.26it/s]
1|12599|Loss: 0.8243176937103271:  49%|████▊     | 12599/25880 [2:35:06<2:48:16,  1.32it/s]
1|12600|Loss: 0.7433327436447144:  49%|████▊     | 12599/25880 [2:35:06<2:48:16,  1.32it/s]
1|12600|Loss: 0.7433327436447144:  49%|████▊     | 12600/25880 [2:35:07<2:39:06,  1.39it/s]
1|12601|Loss: 1.0290449857711792:  49%|████▊     | 12600/25880 [2:35:07<2:39:06,  1.39it/s]
1|12601|Loss: 1.0290449857711792:  49%|████▊     | 12601/25880 [2:35:07<2:43:43,  1.35it/s]
1|12602|Loss: 0.8261550664901733:  49%|████▊     | 12601/25880 [2:35:08<2:43:43,  1.35it/s]
1|12602|Loss: 0.8261550664901733:  49%|████▊     | 12602/25880 [2:35:08<2:39:31,  1.39it/s]
1|12603|Loss: 0.804790198802948:  49%|████▊     | 12602/25880 [2:35:08<2:39:31,  1.39it/s] 
1|12603|Loss: 0.804790198802948:  49%|████▊     | 12603/25880 [2:35:09<2:42:45,  1.36it/s]
1|12604|Loss: 0.8850923776626587:  49%|████▊     | 12603/25880 [2:35:09<2:42:45,  1.36it/s]
1|12604|Loss: 0.8850923776626587:  49%|████▊     | 12604/25880 [2:35:09<2:37:21,  1.41it/s]
1|12605|Loss: 0.7755650281906128:  49%|████▊     | 12604/25880 [2:35:10<2:37:21,  1.41it/s]
1|12605|Loss: 0.7755650281906128:  49%|████▊     | 12605/25880 [2:35:10<2:32:48,  1.45it/s]
1|12606|Loss: 0.7316324710845947:  49%|████▊     | 12605/25880 [2:35:11<2:32:48,  1.45it/s]
1|12606|Loss: 0.7316324710845947:  49%|████▊     | 12606/25880 [2:35:11<2:39:43,  1.39it/s]
1|12607|Loss: 0.8719300627708435:  49%|████▊     | 12606/25880 [2:35:11<2:39:43,  1.39it/s]
1|12607|Loss: 0.8719300627708435:  49%|████▊     | 12607/25880 [2:35:12<2:34:15,  1.43it/s]
1|12608|Loss: 0.7995402216911316:  49%|████▊     | 12607/25880 [2:35:12<2:34:15,  1.43it/s]
1|12608|Loss: 0.7995402216911316:  49%|████▊     | 12608/25880 [2:35:12<2:39:18,  1.39it/s]
1|12609|Loss: 0.7920200824737549:  49%|████▊     | 12608/25880 [2:35:13<2:39:18,  1.39it/s]
1|12609|Loss: 0.7920200824737549:  49%|████▊     | 12609/25880 [2:35:13<2:35:21,  1.42it/s]
1|12610|Loss: 0.7147380709648132:  49%|████▊     | 12609/25880 [2:35:13<2:35:21,  1.42it/s]
1|12610|Loss: 0.7147380709648132:  49%|████▊     | 12610/25880 [2:35:14<2:48:33,  1.31it/s]
1|12611|Loss: 0.7360204458236694:  49%|████▊     | 12610/25880 [2:35:14<2:48:33,  1.31it/s]
1|12611|Loss: 0.7360204458236694:  49%|████▊     | 12611/25880 [2:35:15<2:40:10,  1.38it/s]
1|12612|Loss: 0.7075940370559692:  49%|████▊     | 12611/25880 [2:35:15<2:40:10,  1.38it/s]
1|12612|Loss: 0.7075940370559692:  49%|████▊     | 12612/25880 [2:35:15<2:26:27,  1.51it/s]
1|12613|Loss: 0.8474016785621643:  49%|████▊     | 12612/25880 [2:35:15<2:26:27,  1.51it/s]
1|12613|Loss: 0.8474016785621643:  49%|████▊     | 12613/25880 [2:35:16<2:26:12,  1.51it/s]
1|12614|Loss: 0.7535398602485657:  49%|████▊     | 12613/25880 [2:35:16<2:26:12,  1.51it/s]
1|12614|Loss: 0.7535398602485657:  49%|████▊     | 12614/25880 [2:35:16<2:35:46,  1.42it/s]
1|12615|Loss: 0.6436379551887512:  49%|████▊     | 12614/25880 [2:35:17<2:35:46,  1.42it/s]
1|12615|Loss: 0.6436379551887512:  49%|████▊     | 12615/25880 [2:35:17<2:39:28,  1.39it/s]
1|12616|Loss: 0.8849694728851318:  49%|████▊     | 12615/25880 [2:35:18<2:39:28,  1.39it/s]
1|12616|Loss: 0.8849694728851318:  49%|████▊     | 12616/25880 [2:35:18<2:34:24,  1.43it/s]
1|12617|Loss: 0.8946703672409058:  49%|████▊     | 12616/25880 [2:35:18<2:34:24,  1.43it/s]
1|12617|Loss: 0.8946703672409058:  49%|████▉     | 12617/25880 [2:35:19<2:29:59,  1.47it/s]
1|12618|Loss: 0.8325572609901428:  49%|████▉     | 12617/25880 [2:35:19<2:29:59,  1.47it/s]
1|12618|Loss: 0.8325572609901428:  49%|████▉     | 12618/25880 [2:35:19<2:35:25,  1.42it/s]
1|12619|Loss: 0.8987134695053101:  49%|████▉     | 12618/25880 [2:35:20<2:35:25,  1.42it/s]
1|12619|Loss: 0.8987134695053101:  49%|████▉     | 12619/25880 [2:35:20<2:36:41,  1.41it/s]
1|12620|Loss: 0.7362740635871887:  49%|████▉     | 12619/25880 [2:35:20<2:36:41,  1.41it/s]
1|12620|Loss: 0.7362740635871887:  49%|████▉     | 12620/25880 [2:35:21<2:38:16,  1.40it/s]
1|12621|Loss: 0.9543122053146362:  49%|████▉     | 12620/25880 [2:35:21<2:38:16,  1.40it/s]
1|12621|Loss: 0.9543122053146362:  49%|████▉     | 12621/25880 [2:35:22<2:44:18,  1.34it/s]
1|12622|Loss: 0.9257072806358337:  49%|████▉     | 12621/25880 [2:35:22<2:44:18,  1.34it/s]
1|12622|Loss: 0.9257072806358337:  49%|████▉     | 12622/25880 [2:35:22<2:38:35,  1.39it/s]
1|12623|Loss: 0.8771400451660156:  49%|████▉     | 12622/25880 [2:35:23<2:38:35,  1.39it/s]
1|12623|Loss: 0.8771400451660156:  49%|████▉     | 12623/25880 [2:35:23<2:36:32,  1.41it/s]
1|12624|Loss: 0.9058592915534973:  49%|████▉     | 12623/25880 [2:35:23<2:36:32,  1.41it/s]
1|12624|Loss: 0.9058592915534973:  49%|████▉     | 12624/25880 [2:35:24<2:31:18,  1.46it/s]
1|12625|Loss: 0.8740965127944946:  49%|████▉     | 12624/25880 [2:35:24<2:31:18,  1.46it/s]
1|12625|Loss: 0.8740965127944946:  49%|████▉     | 12625/25880 [2:35:24<2:32:40,  1.45it/s]
1|12626|Loss: 0.9082247018814087:  49%|████▉     | 12625/25880 [2:35:25<2:32:40,  1.45it/s]
1|12626|Loss: 0.9082247018814087:  49%|████▉     | 12626/25880 [2:35:25<2:41:45,  1.37it/s]
1|12627|Loss: 0.9430896043777466:  49%|████▉     | 12626/25880 [2:35:25<2:41:45,  1.37it/s]
1|12627|Loss: 0.9430896043777466:  49%|████▉     | 12627/25880 [2:35:26<2:38:48,  1.39it/s]
1|12628|Loss: 0.749450147151947:  49%|████▉     | 12627/25880 [2:35:26<2:38:48,  1.39it/s] 
1|12628|Loss: 0.749450147151947:  49%|████▉     | 12628/25880 [2:35:26<2:39:11,  1.39it/s]
1|12629|Loss: 0.8960016965866089:  49%|████▉     | 12628/25880 [2:35:27<2:39:11,  1.39it/s]
1|12629|Loss: 0.8960016965866089:  49%|████▉     | 12629/25880 [2:35:27<2:41:35,  1.37it/s]
1|12630|Loss: 0.742334246635437:  49%|████▉     | 12629/25880 [2:35:28<2:41:35,  1.37it/s] 
1|12630|Loss: 0.742334246635437:  49%|████▉     | 12630/25880 [2:35:28<2:42:18,  1.36it/s]
1|12631|Loss: 0.7028307318687439:  49%|████▉     | 12630/25880 [2:35:28<2:42:18,  1.36it/s]
1|12631|Loss: 0.7028307318687439:  49%|████▉     | 12631/25880 [2:35:29<2:41:39,  1.37it/s]
1|12632|Loss: 0.7902840375900269:  49%|████▉     | 12631/25880 [2:35:29<2:41:39,  1.37it/s]
1|12632|Loss: 0.7902840375900269:  49%|████▉     | 12632/25880 [2:35:29<2:44:33,  1.34it/s]
1|12633|Loss: 0.8741493821144104:  49%|████▉     | 12632/25880 [2:35:30<2:44:33,  1.34it/s]
1|12633|Loss: 0.8741493821144104:  49%|████▉     | 12633/25880 [2:35:30<2:36:35,  1.41it/s]
1|12634|Loss: 0.8629099726676941:  49%|████▉     | 12633/25880 [2:35:30<2:36:35,  1.41it/s]
1|12634|Loss: 0.8629099726676941:  49%|████▉     | 12634/25880 [2:35:31<2:28:59,  1.48it/s]
1|12635|Loss: 0.8692213296890259:  49%|████▉     | 12634/25880 [2:35:31<2:28:59,  1.48it/s]
1|12635|Loss: 0.8692213296890259:  49%|████▉     | 12635/25880 [2:35:31<2:30:49,  1.46it/s]
1|12636|Loss: 0.7959979772567749:  49%|████▉     | 12635/25880 [2:35:32<2:30:49,  1.46it/s]
1|12636|Loss: 0.7959979772567749:  49%|████▉     | 12636/25880 [2:35:32<2:28:43,  1.48it/s]
1|12637|Loss: 0.8190020322799683:  49%|██��█▉     | 12636/25880 [2:35:32<2:28:43,  1.48it/s]
1|12637|Loss: 0.8190020322799683:  49%|████▉     | 12637/25880 [2:35:33<2:31:46,  1.45it/s]
1|12638|Loss: 0.6684523224830627:  49%|████▉     | 12637/25880 [2:35:33<2:31:46,  1.45it/s]
1|12638|Loss: 0.6684523224830627:  49%|████▉     | 12638/25880 [2:35:34<2:41:31,  1.37it/s]
1|12639|Loss: 0.8772026896476746:  49%|████▉     | 12638/25880 [2:35:34<2:41:31,  1.37it/s]
1|12639|Loss: 0.8772026896476746:  49%|████▉     | 12639/25880 [2:35:34<2:46:34,  1.32it/s]
1|12640|Loss: 0.8452178835868835:  49%|████▉     | 12639/25880 [2:35:35<2:46:34,  1.32it/s]
1|12640|Loss: 0.8452178835868835:  49%|████▉     | 12640/25880 [2:35:35<2:58:19,  1.24it/s]
1|12641|Loss: 0.8002716898918152:  49%|████▉     | 12640/25880 [2:35:36<2:58:19,  1.24it/s]
1|12641|Loss: 0.8002716898918152:  49%|████▉     | 12641/25880 [2:35:36<2:51:36,  1.29it/s]
1|12642|Loss: 0.8065243363380432:  49%|████▉     | 12641/25880 [2:35:36<2:51:36,  1.29it/s]
1|12642|Loss: 0.8065243363380432:  49%|████▉     | 12642/25880 [2:35:37<2:37:50,  1.40it/s]
1|12643|Loss: 0.9298516511917114:  49%|████▉     | 12642/25880 [2:35:37<2:37:50,  1.40it/s]
1|12643|Loss: 0.9298516511917114:  49%|████▉     | 12643/25880 [2:35:37<2:44:21,  1.34it/s]
1|12644|Loss: 0.867466151714325:  49%|████▉     | 12643/25880 [2:35:38<2:44:21,  1.34it/s] 
1|12644|Loss: 0.867466151714325:  49%|████▉     | 12644/25880 [2:35:38<2:49:59,  1.30it/s]
1|12645|Loss: 0.9588232040405273:  49%|████▉     | 12644/25880 [2:35:39<2:49:59,  1.30it/s]
1|12645|Loss: 0.9588232040405273:  49%|████▉     | 12645/25880 [2:35:39<2:51:19,  1.29it/s]
1|12646|Loss: 0.9314565658569336:  49%|████▉     | 12645/25880 [2:35:39<2:51:19,  1.29it/s]
1|12646|Loss: 0.9314565658569336:  49%|████▉     | 12646/25880 [2:35:40<2:54:25,  1.26it/s]
1|12647|Loss: 0.9068266749382019:  49%|████▉     | 12646/25880 [2:35:40<2:54:25,  1.26it/s]
1|12647|Loss: 0.9068266749382019:  49%|████▉     | 12647/25880 [2:35:41<2:51:14,  1.29it/s]
1|12648|Loss: 1.0025736093521118:  49%|████▉     | 12647/25880 [2:35:41<2:51:14,  1.29it/s]
1|12648|Loss: 1.0025736093521118:  49%|████▉     | 12648/25880 [2:35:41<2:51:11,  1.29it/s]
1|12649|Loss: 0.7850662469863892:  49%|████▉     | 12648/25880 [2:35:42<2:51:11,  1.29it/s]
1|12649|Loss: 0.7850662469863892:  49%|████▉     | 12649/25880 [2:35:42<2:50:04,  1.30it/s]
1|12650|Loss: 0.7799530029296875:  49%|████▉     | 12649/25880 [2:35:43<2:50:04,  1.30it/s]
1|12650|Loss: 0.7799530029296875:  49%|████▉     | 12650/25880 [2:35:43<2:47:32,  1.32it/s]
1|12651|Loss: 0.7690685391426086:  49%|████▉     | 12650/25880 [2:35:43<2:47:32,  1.32it/s]
1|12651|Loss: 0.7690685391426086:  49%|████▉     | 12651/25880 [2:35:44<2:50:30,  1.29it/s]
1|12652|Loss: 0.7747258543968201:  49%|████▉     | 12651/25880 [2:35:44<2:50:30,  1.29it/s]
1|12652|Loss: 0.7747258543968201:  49%|████▉     | 12652/25880 [2:35:44<2:47:37,  1.32it/s]
1|12653|Loss: 0.7607593536376953:  49%|████▉     | 12652/25880 [2:35:45<2:47:37,  1.32it/s]
1|12653|Loss: 0.7607593536376953:  49%|████▉     | 12653/25880 [2:35:45<2:38:49,  1.39it/s]
1|12654|Loss: 0.8566674590110779:  49%|████▉     | 12653/25880 [2:35:45<2:38:49,  1.39it/s]
1|12654|Loss: 0.8566674590110779:  49%|████▉     | 12654/25880 [2:35:46<2:28:35,  1.48it/s]
1|12655|Loss: 0.8956364989280701:  49%|████▉     | 12654/25880 [2:35:46<2:28:35,  1.48it/s]
1|12655|Loss: 0.8956364989280701:  49%|████▉     | 12655/25880 [2:35:46<2:21:48,  1.55it/s]
1|12656|Loss: 0.9871304035186768:  49%|████▉     | 12655/25880 [2:35:47<2:21:48,  1.55it/s]
1|12656|Loss: 0.9871304035186768:  49%|████▉     | 12656/25880 [2:35:47<2:24:16,  1.53it/s]
1|12657|Loss: 0.7496525645256042:  49%|████▉     | 12656/25880 [2:35:47<2:24:16,  1.53it/s]
1|12657|Loss: 0.7496525645256042:  49%|████▉     | 12657/25880 [2:35:48<2:28:53,  1.48it/s]
1|12658|Loss: 0.7583552002906799:  49%|████▉     | 12657/25880 [2:35:48<2:28:53,  1.48it/s]
1|12658|Loss: 0.7583552002906799:  49%|████▉     | 12658/25880 [2:35:48<2:20:37,  1.57it/s]
1|12659|Loss: 0.9343031644821167:  49%|████▉     | 12658/25880 [2:35:49<2:20:37,  1.57it/s]
1|12659|Loss: 0.9343031644821167:  49%|████▉     | 12659/25880 [2:35:49<2:30:00,  1.47it/s]
1|12660|Loss: 0.8508448600769043:  49%|████▉     | 12659/25880 [2:35:49<2:30:00,  1.47it/s]
1|12660|Loss: 0.8508448600769043:  49%|████▉     | 12660/25880 [2:35:50<2:39:36,  1.38it/s]
1|12661|Loss: 0.9452134966850281:  49%|████▉     | 12660/25880 [2:35:50<2:39:36,  1.38it/s]
1|12661|Loss: 0.9452134966850281:  49%|████▉     | 12661/25880 [2:35:50<2:40:54,  1.37it/s]
1|12662|Loss: 0.8827680349349976:  49%|████▉     | 12661/25880 [2:35:51<2:40:54,  1.37it/s]
1|12662|Loss: 0.8827680349349976:  49%|████▉     | 12662/25880 [2:35:51<2:39:13,  1.38it/s]
1|12663|Loss: 0.8039284944534302:  49%|████▉     | 12662/25880 [2:35:52<2:39:13,  1.38it/s]
1|12663|Loss: 0.8039284944534302:  49%|████▉     | 12663/25880 [2:35:52<2:44:14,  1.34it/s]
1|12664|Loss: 1.0568469762802124:  49%|████▉     | 12663/25880 [2:35:52<2:44:14,  1.34it/s]
1|12664|Loss: 1.0568469762802124:  49%|████▉     | 12664/25880 [2:35:53<2:39:34,  1.38it/s]
1|12665|Loss: 0.916528046131134:  49%|████▉     | 12664/25880 [2:35:53<2:39:34,  1.38it/s] 
1|12665|Loss: 0.916528046131134:  49%|████▉     | 12665/25880 [2:35:53<2:42:20,  1.36it/s]
1|12666|Loss: 0.9285032749176025:  49%|████▉     | 12665/25880 [2:35:54<2:42:20,  1.36it/s]
1|12666|Loss: 0.9285032749176025:  49%|████▉     | 12666/25880 [2:35:54<2:50:51,  1.29it/s]
1|12667|Loss: 0.775962233543396:  49%|████▉     | 12666/25880 [2:35:55<2:50:51,  1.29it/s] 
1|12667|Loss: 0.775962233543396:  49%|████▉     | 12667/25880 [2:35:55<2:44:09,  1.34it/s]
1|12668|Loss: 0.7717211842536926:  49%|████▉     | 12667/25880 [2:35:55<2:44:09,  1.34it/s]
1|12668|Loss: 0.7717211842536926:  49%|████▉     | 12668/25880 [2:35:56<2:41:56,  1.36it/s]
1|12669|Loss: 0.8264063596725464:  49%|████▉     | 12668/25880 [2:35:56<2:41:56,  1.36it/s]
1|12669|Loss: 0.8264063596725464:  49%|████▉     | 12669/25880 [2:35:56<2:37:18,  1.40it/s]
1|12670|Loss: 0.7144128680229187:  49%|████▉     | 12669/25880 [2:35:57<2:37:18,  1.40it/s]
1|12670|Loss: 0.7144128680229187:  49%|████▉     | 12670/25880 [2:35:57<2:38:15,  1.39it/s]
1|12671|Loss: 0.8631978631019592:  49%|████▉     | 12670/25880 [2:35:58<2:38:15,  1.39it/s]
1|12671|Loss: 0.8631978631019592:  49%|████▉     | 12671/25880 [2:35:58<2:40:43,  1.37it/s]
1|12672|Loss: 0.7454827427864075:  49%|████▉     | 12671/25880 [2:35:58<2:40:43,  1.37it/s]
1|12672|Loss: 0.7454827427864075:  49%|████▉     | 12672/25880 [2:35:59<2:36:37,  1.41it/s]
1|12673|Loss: 0.7782836556434631:  49%|████▉     | 12672/25880 [2:35:59<2:36:37,  1.41it/s]
1|12673|Loss: 0.7782836556434631:  49%|████▉     | 12673/25880 [2:35:59<2:36:46,  1.40it/s]
1|12674|Loss: 0.7345517873764038:  49%|████▉     | 12673/25880 [2:36:00<2:36:46,  1.40it/s]
1|12674|Loss: 0.7345517873764038:  49%|████▉     | 12674/25880 [2:36:00<2:33:17,  1.44it/s]
1|12675|Loss: 0.7144629955291748:  49%|████▉     | 12674/25880 [2:36:00<2:33:17,  1.44it/s]
1|12675|Loss: 0.7144629955291748:  49%|████▉     | 12675/25880 [2:36:00<2:23:07,  1.54it/s]
1|12676|Loss: 0.8858107328414917:  49%|████▉     | 12675/25880 [2:36:01<2:23:07,  1.54it/s]
1|12676|Loss: 0.8858107328414917:  49%|████▉     | 12676/25880 [2:36:01<2:29:00,  1.48it/s]
1|12677|Loss: 0.9103575348854065:  49%|████▉     | 12676/25880 [2:36:02<2:29:00,  1.48it/s]
1|12677|Loss: 0.9103575348854065:  49%|████▉     | 12677/25880 [2:36:02<2:28:44,  1.48it/s]
1|12678|Loss: 0.9126513004302979:  49%|████▉     | 12677/25880 [2:36:02<2:28:44,  1.48it/s]
1|12678|Loss: 0.9126513004302979:  49%|████▉     | 12678/25880 [2:36:02<2:25:06,  1.52it/s]
1|12679|Loss: 0.7909773588180542:  49%|████▉     | 12678/25880 [2:36:03<2:25:06,  1.52it/s]
1|12679|Loss: 0.7909773588180542:  49%|████▉     | 12679/25880 [2:36:03<2:28:27,  1.48it/s]
1|12680|Loss: 0.8944517970085144:  49%|████▉     | 12679/25880 [2:36:04<2:28:27,  1.48it/s]
1|12680|Loss: 0.8944517970085144:  49%|████▉     | 12680/25880 [2:36:04<2:38:29,  1.39it/s]
1|12681|Loss: 0.8534798622131348:  49%|████▉     | 12680/25880 [2:36:04<2:38:29,  1.39it/s]
1|12681|Loss: 0.8534798622131348:  49%|████▉     | 12681/25880 [2:36:05<2:36:28,  1.41it/s]
1|12682|Loss: 0.7862520217895508:  49%|████▉     | 12681/25880 [2:36:05<2:36:28,  1.41it/s]
1|12682|Loss: 0.7862520217895508:  49%|████▉     | 12682/25880 [2:36:05<2:36:46,  1.40it/s]
1|12683|Loss: 0.8482735753059387:  49%|████▉     | 12682/25880 [2:36:06<2:36:46,  1.40it/s]
1|12683|Loss: 0.8482735753059387:  49%|████▉     | 12683/25880 [2:36:06<2:23:25,  1.53it/s]
1|12684|Loss: 0.9756991267204285:  49%|████▉     | 12683/25880 [2:36:06<2:23:25,  1.53it/s]
1|12684|Loss: 0.9756991267204285:  49%|████▉     | 12684/25880 [2:36:07<2:27:33,  1.49it/s]
1|12685|Loss: 0.7939946055412292:  49%|████▉     | 12684/25880 [2:36:07<2:27:33,  1.49it/s]
1|12685|Loss: 0.7939946055412292:  49%|████▉     | 12685/25880 [2:36:07<2:24:40,  1.52it/s]
1|12686|Loss: 0.9151021242141724:  49%|████▉     | 12685/25880 [2:36:08<2:24:40,  1.52it/s]
1|12686|Loss: 0.9151021242141724:  49%|████▉     | 12686/25880 [2:36:08<2:21:10,  1.56it/s]
1|12687|Loss: 0.8424519896507263:  49%|████▉     | 12686/25880 [2:36:08<2:21:10,  1.56it/s]
1|12687|Loss: 0.8424519896507263:  49%|████▉     | 12687/25880 [2:36:09<2:26:17,  1.50it/s]
1|12688|Loss: 0.8220202326774597:  49%|████▉     | 12687/25880 [2:36:09<2:26:17,  1.50it/s]
1|12688|Loss: 0.8220202326774597:  49%|████▉     | 12688/25880 [2:36:09<2:37:27,  1.40it/s]
1|12689|Loss: 0.9181196093559265:  49%|████▉     | 12688/25880 [2:36:10<2:37:27,  1.40it/s]
1|12689|Loss: 0.9181196093559265:  49%|████▉     | 12689/25880 [2:36:10<2:38:37,  1.39it/s]
1|12690|Loss: 0.8370236158370972:  49%|████▉     | 12689/25880 [2:36:11<2:38:37,  1.39it/s]
1|12690|Loss: 0.8370236158370972:  49%|████▉     | 12690/25880 [2:36:11<2:43:41,  1.34it/s]
1|12691|Loss: 0.9293860793113708:  49%|████▉     | 12690/25880 [2:36:11<2:43:41,  1.34it/s]
1|12691|Loss: 0.9293860793113708:  49%|████▉     | 12691/25880 [2:36:12<2:37:56,  1.39it/s]
1|12692|Loss: 0.8182117342948914:  49%|████▉     | 12691/25880 [2:36:12<2:37:56,  1.39it/s]
1|12692|Loss: 0.8182117342948914:  49%|████▉     | 12692/25880 [2:36:12<2:32:21,  1.44it/s]
1|12693|Loss: 0.9079025983810425:  49%|████▉     | 12692/25880 [2:36:13<2:32:21,  1.44it/s]
1|12693|Loss: 0.9079025983810425:  49%|████▉     | 12693/25880 [2:36:13<2:32:23,  1.44it/s]
1|12694|Loss: 0.8045849800109863:  49%|████▉     | 12693/25880 [2:36:13<2:32:23,  1.44it/s]
1|12694|Loss: 0.8045849800109863:  49%|████▉     | 12694/25880 [2:36:14<2:29:33,  1.47it/s]
1|12695|Loss: 0.7616613507270813:  49%|████▉     | 12694/25880 [2:36:14<2:29:33,  1.47it/s]
1|12695|Loss: 0.7616613507270813:  49%|████▉     | 12695/25880 [2:36:14<2:25:38,  1.51it/s]
1|12696|Loss: 0.8938629031181335:  49%|████▉     | 12695/25880 [2:36:15<2:25:38,  1.51it/s]
1|12696|Loss: 0.8938629031181335:  49%|████▉     | 12696/25880 [2:36:15<2:36:41,  1.40it/s]
1|12697|Loss: 0.8770582675933838:  49%|████▉     | 12696/25880 [2:36:15<2:36:41,  1.40it/s]
1|12697|Loss: 0.8770582675933838:  49%|████▉     | 12697/25880 [2:36:16<2:40:20,  1.37it/s]
1|12698|Loss: 0.8062164783477783:  49%|████▉     | 12697/25880 [2:36:16<2:40:20,  1.37it/s]
1|12698|Loss: 0.8062164783477783:  49%|████▉     | 12698/25880 [2:36:16<2:27:16,  1.49it/s]
1|12699|Loss: 0.841859757900238:  49%|████▉     | 12698/25880 [2:36:17<2:27:16,  1.49it/s] 
1|12699|Loss: 0.841859757900238:  49%|████▉     | 12699/25880 [2:36:17<2:22:02,  1.55it/s]
1|12700|Loss: 0.8758878707885742:  49%|████▉     | 12699/25880 [2:36:17<2:22:02,  1.55it/s]
1|12700|Loss: 0.8758878707885742:  49%|████▉     | 12700/25880 [2:36:18<2:27:08,  1.49it/s]
1|12701|Loss: 0.911259114742279:  49%|████▉     | 12700/25880 [2:36:18<2:27:08,  1.49it/s] 
1|12701|Loss: 0.911259114742279:  49%|████▉     | 12701/25880 [2:36:18<2:19:52,  1.57it/s]
1|12702|Loss: 0.8968203067779541:  49%|████▉     | 12701/25880 [2:36:19<2:19:52,  1.57it/s]
1|12702|Loss: 0.8968203067779541:  49%|████▉     | 12702/25880 [2:36:19<2:22:41,  1.54it/s]
1|12703|Loss: 0.7905053496360779:  49%|████▉     | 12702/25880 [2:36:19<2:22:41,  1.54it/s]
1|12703|Loss: 0.7905053496360779:  49%|████▉     | 12703/25880 [2:36:20<2:26:37,  1.50it/s]
1|12704|Loss: 0.8147118091583252:  49%|████▉     | 12703/25880 [2:36:20<2:26:37,  1.50it/s]
1|12704|Loss: 0.8147118091583252:  49%|████▉     | 12704/25880 [2:36:20<2:30:35,  1.46it/s]
1|12705|Loss: 0.7398152351379395:  49%|████▉     | 12704/25880 [2:36:21<2:30:35,  1.46it/s]
1|12705|Loss: 0.7398152351379395:  49%|████▉     | 12705/25880 [2:36:21<2:31:28,  1.45it/s]
1|12706|Loss: 0.827183723449707:  49%|████▉     | 12705/25880 [2:36:21<2:31:28,  1.45it/s] 
1|12706|Loss: 0.827183723449707:  49%|████▉     | 12706/25880 [2:36:22<2:33:56,  1.43it/s]
1|12707|Loss: 0.9213437438011169:  49%|████▉     | 12706/25880 [2:36:22<2:33:56,  1.43it/s]
1|12707|Loss: 0.9213437438011169:  49%|████▉     | 12707/25880 [2:36:22<2:36:03,  1.41it/s]
1|12708|Loss: 0.8403480648994446:  49%|████▉     | 12707/25880 [2:36:23<2:36:03,  1.41it/s]
1|12708|Loss: 0.8403480648994446:  49%|████▉     | 12708/25880 [2:36:23<2:35:53,  1.41it/s]
1|12709|Loss: 0.9643347263336182:  49%|████▉     | 12708/25880 [2:36:24<2:35:53,  1.41it/s]
1|12709|Loss: 0.9643347263336182:  49%|████▉     | 12709/25880 [2:36:24<2:35:18,  1.41it/s]
1|12710|Loss: 0.6651617884635925:  49%|████▉     | 12709/25880 [2:36:24<2:35:18,  1.41it/s]
1|12710|Loss: 0.6651617884635925:  49%|████▉     | 12710/25880 [2:36:25<2:42:25,  1.35it/s]
1|12711|Loss: 0.8134304285049438:  49%|████▉     | 12710/25880 [2:36:25<2:42:25,  1.35it/s]
1|12711|Loss: 0.8134304285049438:  49%|████▉     | 12711/25880 [2:36:25<2:44:31,  1.33it/s]
1|12712|Loss: 0.8716423511505127:  49%|████▉     | 12711/25880 [2:36:26<2:44:31,  1.33it/s]
1|12712|Loss: 0.8716423511505127:  49%|████▉     | 12712/25880 [2:36:26<2:42:06,  1.35it/s]
1|12713|Loss: 0.7675427198410034:  49%|████▉     | 12712/25880 [2:36:27<2:42:06,  1.35it/s]
1|12713|Loss: 0.7675427198410034:  49%|████▉     | 12713/25880 [2:36:27<2:40:41,  1.37it/s]
1|12714|Loss: 0.8847222924232483:  49%|████▉     | 12713/25880 [2:36:27<2:40:41,  1.37it/s]
1|12714|Loss: 0.8847222924232483:  49%|████▉     | 12714/25880 [2:36:28<2:52:22,  1.27it/s]
1|12715|Loss: 0.7868131399154663:  49%|████▉     | 12714/25880 [2:36:28<2:52:22,  1.27it/s]
1|12715|Loss: 0.7868131399154663:  49%|████▉     | 12715/25880 [2:36:29<2:54:43,  1.26it/s]
1|12716|Loss: 0.881790280342102:  49%|████▉     | 12715/25880 [2:36:29<2:54:43,  1.26it/s] 
1|12716|Loss: 0.881790280342102:  49%|████▉     | 12716/25880 [2:36:29<2:44:14,  1.34it/s]
1|12717|Loss: 0.8412878513336182:  49%|████▉     | 12716/25880 [2:36:30<2:44:14,  1.34it/s]
1|12717|Loss: 0.8412878513336182:  49%|████▉     | 12717/25880 [2:36:30<2:46:02,  1.32it/s]
1|12718|Loss: 0.7771129012107849:  49%|████▉     | 12717/25880 [2:36:30<2:46:02,  1.32it/s]
1|12718|Loss: 0.7771129012107849:  49%|████▉     | 12718/25880 [2:36:31<2:39:27,  1.38it/s]
1|12719|Loss: 0.7714655995368958:  49%|████▉     | 12718/25880 [2:36:31<2:39:27,  1.38it/s]
1|12719|Loss: 0.7714655995368958:  49%|████▉     | 12719/25880 [2:36:32<2:48:05,  1.30it/s]
1|12720|Loss: 0.7799432873725891:  49%|████▉     | 12719/25880 [2:36:32<2:48:05,  1.30it/s]
1|12720|Loss: 0.7799432873725891:  49%|████▉     | 12720/25880 [2:36:32<2:48:14,  1.30it/s]
1|12721|Loss: 0.8110582232475281:  49%|████▉     | 12720/25880 [2:36:33<2:48:14,  1.30it/s]
1|12721|Loss: 0.8110582232475281:  49%|████▉     | 12721/25880 [2:36:33<2:46:17,  1.32it/s]
1|12722|Loss: 0.8331698179244995:  49%|████▉     | 12721/25880 [2:36:34<2:46:17,  1.32it/s]
1|12722|Loss: 0.8331698179244995:  49%|████▉     | 12722/25880 [2:36:34<2:47:04,  1.31it/s]
1|12723|Loss: 0.8988915681838989:  49%|████▉     | 12722/25880 [2:36:34<2:47:04,  1.31it/s]
1|12723|Loss: 0.8988915681838989:  49%|████▉     | 12723/25880 [2:36:35<2:45:45,  1.32it/s]
1|12724|Loss: 0.8449327945709229:  49%|████▉     | 12723/25880 [2:36:35<2:45:45,  1.32it/s]
1|12724|Loss: 0.8449327945709229:  49%|████▉     | 12724/25880 [2:36:35<2:49:33,  1.29it/s]
1|12725|Loss: 0.8299260139465332:  49%|████▉     | 12724/25880 [2:36:36<2:49:33,  1.29it/s]
1|12725|Loss: 0.8299260139465332:  49%|████▉     | 12725/25880 [2:36:36<2:48:23,  1.30it/s]
1|12726|Loss: 0.8031219840049744:  49%|████▉     | 12725/25880 [2:36:37<2:48:23,  1.30it/s]
1|12726|Loss: 0.8031219840049744:  49%|████▉     | 12726/25880 [2:36:37<2:35:21,  1.41it/s]
1|12727|Loss: 0.8600507974624634:  49%|████▉     | 12726/25880 [2:36:37<2:35:21,  1.41it/s]
1|12727|Loss: 0.8600507974624634:  49%|████▉     | 12727/25880 [2:36:37<2:26:27,  1.50it/s]
1|12728|Loss: 0.7041655778884888:  49%|████▉     | 12727/25880 [2:36:38<2:26:27,  1.50it/s]
1|12728|Loss: 0.7041655778884888:  49%|████▉     | 12728/25880 [2:36:38<2:40:13,  1.37it/s]
1|12729|Loss: 0.8037142157554626:  49%|████▉     | 12728/25880 [2:36:39<2:40:13,  1.37it/s]
1|12729|Loss: 0.8037142157554626:  49%|████▉     | 12729/25880 [2:36:39<2:50:39,  1.28it/s]
1|12730|Loss: 0.9288691282272339:  49%|████▉     | 12729/25880 [2:36:40<2:50:39,  1.28it/s]
1|12730|Loss: 0.9288691282272339:  49%|████▉     | 12730/25880 [2:36:40<2:52:52,  1.27it/s]
1|12731|Loss: 0.7912118434906006:  49%|████▉     | 12730/25880 [2:36:40<2:52:52,  1.27it/s]
1|12731|Loss: 0.7912118434906006:  49%|████▉     | 12731/25880 [2:36:41<2:57:13,  1.24it/s]
1|12732|Loss: 0.9394800662994385:  49%|████▉     | 12731/25880 [2:36:41<2:57:13,  1.24it/s]
1|12732|Loss: 0.9394800662994385:  49%|████▉     | 12732/25880 [2:36:41<2:46:16,  1.32it/s]
1|12733|Loss: 0.7585518956184387:  49%|████▉     | 12732/25880 [2:36:42<2:46:16,  1.32it/s]
1|12733|Loss: 0.7585518956184387:  49%|████▉     | 12733/25880 [2:36:42<2:36:24,  1.40it/s]
1|12734|Loss: 0.9073699116706848:  49%|████▉     | 12733/25880 [2:36:42<2:36:24,  1.40it/s]
1|12734|Loss: 0.9073699116706848:  49%|████▉     | 12734/25880 [2:36:43<2:34:31,  1.42it/s]
1|12735|Loss: 0.8669471740722656:  49%|████▉     | 12734/25880 [2:36:43<2:34:31,  1.42it/s]
1|12735|Loss: 0.8669471740722656:  49%|████▉     | 12735/25880 [2:36:43<2:36:40,  1.40it/s]
1|12736|Loss: 0.8199557662010193:  49%|████▉     | 12735/25880 [2:36:44<2:36:40,  1.40it/s]
1|12736|Loss: 0.8199557662010193:  49%|████▉     | 12736/25880 [2:36:44<2:23:39,  1.52it/s]
1|12737|Loss: 0.7371667623519897:  49%|████▉     | 12736/25880 [2:36:44<2:23:39,  1.52it/s]
1|12737|Loss: 0.7371667623519897:  49%|████▉     | 12737/25880 [2:36:45<2:28:07,  1.48it/s]
1|12738|Loss: 0.7599997520446777:  49%|████▉     | 12737/25880 [2:36:45<2:28:07,  1.48it/s]
1|12738|Loss: 0.7599997520446777:  49%|████▉     | 12738/25880 [2:36:45<2:18:27,  1.58it/s]
1|12739|Loss: 0.844784140586853:  49%|████▉     | 12738/25880 [2:36:46<2:18:27,  1.58it/s] 
1|12739|Loss: 0.844784140586853:  49%|████▉     | 12739/25880 [2:36:46<2:14:38,  1.63it/s]
1|12740|Loss: 0.8712557554244995:  49%|████▉     | 12739/25880 [2:36:46<2:14:38,  1.63it/s]
1|12740|Loss: 0.8712557554244995:  49%|████▉     | 12740/25880 [2:36:46<2:19:33,  1.57it/s]
1|12741|Loss: 0.8294581770896912:  49%|████▉     | 12740/25880 [2:36:47<2:19:33,  1.57it/s]
1|12741|Loss: 0.8294581770896912:  49%|████▉     | 12741/25880 [2:36:47<2:13:31,  1.64it/s]
1|12742|Loss: 0.9025406837463379:  49%|████▉     | 12741/25880 [2:36:47<2:13:31,  1.64it/s]
1|12742|Loss: 0.9025406837463379:  49%|████▉     | 12742/25880 [2:36:48<2:09:24,  1.69it/s]
1|12743|Loss: 0.9309453964233398:  49%|████▉     | 12742/25880 [2:36:48<2:09:24,  1.69it/s]
1|12743|Loss: 0.9309453964233398:  49%|████▉     | 12743/25880 [2:36:48<2:10:33,  1.68it/s]
1|12744|Loss: 0.737639844417572:  49%|████▉     | 12743/25880 [2:36:49<2:10:33,  1.68it/s] 
1|12744|Loss: 0.737639844417572:  49%|████▉     | 12744/25880 [2:36:49<2:23:28,  1.53it/s]
1|12745|Loss: 0.7677629590034485:  49%|████▉     | 12744/25880 [2:36:49<2:23:28,  1.53it/s]
1|12745|Loss: 0.7677629590034485:  49%|████▉     | 12745/25880 [2:36:50<2:23:25,  1.53it/s]
1|12746|Loss: 1.0363370180130005:  49%|████▉     | 12745/25880 [2:36:50<2:23:25,  1.53it/s]
1|12746|Loss: 1.0363370180130005:  49%|████▉     | 12746/25880 [2:36:50<2:27:28,  1.48it/s]
1|12747|Loss: 1.1157323122024536:  49%|████▉     | 12746/25880 [2:36:51<2:27:28,  1.48it/s]
1|12747|Loss: 1.1157323122024536:  49%|████▉     | 12747/25880 [2:36:51<2:18:50,  1.58it/s]
1|12748|Loss: 0.8545225858688354:  49%|████▉     | 12747/25880 [2:36:51<2:18:50,  1.58it/s]
1|12748|Loss: 0.8545225858688354:  49%|████▉     | 12748/25880 [2:36:51<2:16:47,  1.60it/s]
1|12749|Loss: 0.8410157561302185:  49%|████▉     | 12748/25880 [2:36:52<2:16:47,  1.60it/s]
1|12749|Loss: 0.8410157561302185:  49%|████▉     | 12749/25880 [2:36:52<2:25:56,  1.50it/s]
1|12750|Loss: 0.7091752290725708:  49%|████▉     | 12749/25880 [2:36:53<2:25:56,  1.50it/s]
1|12750|Loss: 0.7091752290725708:  49%|████▉     | 12750/25880 [2:36:53<2:36:01,  1.40it/s]
1|12751|Loss: 0.7539600729942322:  49%|████▉     | 12750/25880 [2:36:53<2:36:01,  1.40it/s]
1|12751|Loss: 0.7539600729942322:  49%|████▉     | 12751/25880 [2:36:54<2:30:54,  1.45it/s]
1|12752|Loss: 0.8930678963661194:  49%|████▉     | 12751/25880 [2:36:54<2:30:54,  1.45it/s]
1|12752|Loss: 0.8930678963661194:  49%|████▉     | 12752/25880 [2:36:54<2:37:27,  1.39it/s]
1|12753|Loss: 0.7273104190826416:  49%|████▉     | 12752/25880 [2:36:55<2:37:27,  1.39it/s]
1|12753|Loss: 0.7273104190826416:  49%|████▉     | 12753/25880 [2:36:55<2:25:39,  1.50it/s]
1|12754|Loss: 0.7572245001792908:  49%|████▉     | 12753/25880 [2:36:55<2:25:39,  1.50it/s]
1|12754|Loss: 0.7572245001792908:  49%|████▉     | 12754/25880 [2:36:56<2:25:26,  1.50it/s]
1|12755|Loss: 0.9333223104476929:  49%|████▉     | 12754/25880 [2:36:56<2:25:26,  1.50it/s]
1|12755|Loss: 0.9333223104476929:  49%|████▉     | 12755/25880 [2:36:56<2:32:51,  1.43it/s]
1|12756|Loss: 0.9180693626403809:  49%|████▉     | 12755/25880 [2:36:57<2:32:51,  1.43it/s]
1|12756|Loss: 0.9180693626403809:  49%|████▉     | 12756/25880 [2:36:58<3:02:31,  1.20it/s]
1|12757|Loss: 0.8257035613059998:  49%|████▉     | 12756/25880 [2:36:58<3:02:31,  1.20it/s]
1|12757|Loss: 0.8257035613059998:  49%|████▉     | 12757/25880 [2:36:59<3:09:15,  1.16it/s]
1|12758|Loss: 0.8884983062744141:  49%|████▉     | 12757/25880 [2:36:59<3:09:15,  1.16it/s]
1|12758|Loss: 0.8884983062744141:  49%|████▉     | 12758/25880 [2:36:59<2:56:29,  1.24it/s]
1|12759|Loss: 0.7776151299476624:  49%|████▉     | 12758/25880 [2:37:00<2:56:29,  1.24it/s]
1|12759|Loss: 0.7776151299476624:  49%|████▉     | 12759/25880 [2:37:00<3:00:23,  1.21it/s]
1|12760|Loss: 0.7711604833602905:  49%|████▉     | 12759/25880 [2:37:00<3:00:23,  1.21it/s]
1|12760|Loss: 0.7711604833602905:  49%|████▉     | 12760/25880 [2:37:01<2:52:05,  1.27it/s]
1|12761|Loss: 0.821702241897583:  49%|████▉     | 12760/25880 [2:37:01<2:52:05,  1.27it/s] 
1|12761|Loss: 0.821702241897583:  49%|████▉     | 12761/25880 [2:37:02<2:55:23,  1.25it/s]
1|12762|Loss: 0.8319240212440491:  49%|████▉     | 12761/25880 [2:37:02<2:55:23,  1.25it/s]
1|12762|Loss: 0.8319240212440491:  49%|████▉     | 12762/25880 [2:37:02<2:58:20,  1.23it/s]
1|12763|Loss: 0.7601524591445923:  49%|████▉     | 12762/25880 [2:37:03<2:58:20,  1.23it/s]
1|12763|Loss: 0.7601524591445923:  49%|████▉     | 12763/25880 [2:37:03<2:46:12,  1.32it/s]
1|12764|Loss: 0.9528638124465942:  49%|████▉     | 12763/25880 [2:37:03<2:46:12,  1.32it/s]
1|12764|Loss: 0.9528638124465942:  49%|████▉     | 12764/25880 [2:37:04<2:41:07,  1.36it/s]
1|12765|Loss: 0.7552410364151001:  49%|████▉     | 12764/25880 [2:37:04<2:41:07,  1.36it/s]
1|12765|Loss: 0.7552410364151001:  49%|████▉     | 12765/25880 [2:37:05<2:40:52,  1.36it/s]
1|12766|Loss: 0.7613533139228821:  49%|████▉     | 12765/25880 [2:37:05<2:40:52,  1.36it/s]
1|12766|Loss: 0.7613533139228821:  49%|████▉     | 12766/25880 [2:37:05<2:39:29,  1.37it/s]
1|12767|Loss: 0.8687200546264648:  49%|████▉     | 12766/25880 [2:37:06<2:39:29,  1.37it/s]
1|12767|Loss: 0.8687200546264648:  49%|████▉     | 12767/25880 [2:37:06<2:41:36,  1.35it/s]
1|12768|Loss: 0.7704200744628906:  49%|████▉     | 12767/25880 [2:37:06<2:41:36,  1.35it/s]
1|12768|Loss: 0.7704200744628906:  49%|████▉     | 12768/25880 [2:37:07<2:48:32,  1.30it/s]
1|12769|Loss: 0.7266191840171814:  49%|████▉     | 12768/25880 [2:37:07<2:48:32,  1.30it/s]
1|12769|Loss: 0.7266191840171814:  49%|████▉     | 12769/25880 [2:37:08<2:49:01,  1.29it/s]
1|12770|Loss: 0.7827179431915283:  49%|████▉     | 12769/25880 [2:37:08<2:49:01,  1.29it/s]
1|12770|Loss: 0.7827179431915283:  49%|████▉     | 12770/25880 [2:37:08<2:44:46,  1.33it/s]
1|12771|Loss: 0.7869264483451843:  49%|████▉     | 12770/25880 [2:37:09<2:44:46,  1.33it/s]
1|12771|Loss: 0.7869264483451843:  49%|████▉     | 12771/25880 [2:37:09<2:50:10,  1.28it/s]
1|12772|Loss: 0.8946447968482971:  49%|████▉     | 12771/25880 [2:37:10<2:50:10,  1.28it/s]
1|12772|Loss: 0.8946447968482971:  49%|████▉     | 12772/25880 [2:37:10<2:49:09,  1.29it/s]
1|12773|Loss: 0.8730390667915344:  49%|████▉     | 12772/25880 [2:37:10<2:49:09,  1.29it/s]
1|12773|Loss: 0.8730390667915344:  49%|████▉     | 12773/25880 [2:37:11<2:46:38,  1.31it/s]
1|12774|Loss: 0.8249630928039551:  49%|████▉     | 12773/25880 [2:37:11<2:46:38,  1.31it/s]
1|12774|Loss: 0.8249630928039551:  49%|████▉     | 12774/25880 [2:37:11<2:51:14,  1.28it/s]
1|12775|Loss: 0.8422213196754456:  49%|████▉     | 12774/25880 [2:37:12<2:51:14,  1.28it/s]
1|12775|Loss: 0.8422213196754456:  49%|████▉     | 12775/25880 [2:37:12<2:49:38,  1.29it/s]
1|12776|Loss: 0.834157407283783:  49%|████▉     | 12775/25880 [2:37:13<2:49:38,  1.29it/s] 
1|12776|Loss: 0.834157407283783:  49%|████▉     | 12776/25880 [2:37:13<2:52:59,  1.26it/s]
1|12777|Loss: 0.8028111457824707:  49%|████▉     | 12776/25880 [2:37:14<2:52:59,  1.26it/s]
1|12777|Loss: 0.8028111457824707:  49%|████▉     | 12777/25880 [2:37:14<2:53:40,  1.26it/s]
1|12778|Loss: 0.8920839428901672:  49%|████▉     | 12777/25880 [2:37:14<2:53:40,  1.26it/s]
1|12778|Loss: 0.8920839428901672:  49%|████▉     | 12778/25880 [2:37:15<2:53:56,  1.26it/s]
1|12779|Loss: 0.8671820163726807:  49%|████▉     | 12778/25880 [2:37:15<2:53:56,  1.26it/s]
1|12779|Loss: 0.8671820163726807:  49%|████▉     | 12779/25880 [2:37:15<2:50:05,  1.28it/s]
1|12780|Loss: 0.9369723796844482:  49%|████▉     | 12779/25880 [2:37:16<2:50:05,  1.28it/s]
1|12780|Loss: 0.9369723796844482:  49%|████▉     | 12780/25880 [2:37:16<2:40:43,  1.36it/s]
1|12781|Loss: 0.8740957975387573:  49%|████▉     | 12780/25880 [2:37:16<2:40:43,  1.36it/s]
1|12781|Loss: 0.8740957975387573:  49%|████▉     | 12781/25880 [2:37:17<2:27:20,  1.48it/s]
1|12782|Loss: 0.897223949432373:  49%|████▉     | 12781/25880 [2:37:17<2:27:20,  1.48it/s] 
1|12782|Loss: 0.897223949432373:  49%|████▉     | 12782/25880 [2:37:17<2:27:49,  1.48it/s]
1|12783|Loss: 0.7866391539573669:  49%|████▉     | 12782/25880 [2:37:18<2:27:49,  1.48it/s]
1|12783|Loss: 0.7866391539573669:  49%|████▉     | 12783/25880 [2:37:18<2:16:42,  1.60it/s]
1|12784|Loss: 0.9797473549842834:  49%|████▉     | 12783/25880 [2:37:18<2:16:42,  1.60it/s]
1|12784|Loss: 0.9797473549842834:  49%|████▉     | 12784/25880 [2:37:18<2:20:20,  1.56it/s]
1|12785|Loss: 0.8525867462158203:  49%|████▉     | 12784/25880 [2:37:19<2:20:20,  1.56it/s]
1|12785|Loss: 0.8525867462158203:  49%|████▉     | 12785/25880 [2:37:19<2:33:53,  1.42it/s]
1|12786|Loss: 0.8258255124092102:  49%|████▉     | 12785/25880 [2:37:20<2:33:53,  1.42it/s]
1|12786|Loss: 0.8258255124092102:  49%|████▉     | 12786/25880 [2:37:20<2:32:50,  1.43it/s]
1|12787|Loss: 0.7536941766738892:  49%|████▉     | 12786/25880 [2:37:20<2:32:50,  1.43it/s]
1|12787|Loss: 0.7536941766738892:  49%|████▉     | 12787/25880 [2:37:21<2:39:04,  1.37it/s]
1|12788|Loss: 0.8476362228393555:  49%|████▉     | 12787/25880 [2:37:21<2:39:04,  1.37it/s]
1|12788|Loss: 0.8476362228393555:  49%|████▉     | 12788/25880 [2:37:21<2:34:28,  1.41it/s]
1|12789|Loss: 0.7925831079483032:  49%|████▉     | 12788/25880 [2:37:22<2:34:28,  1.41it/s]
1|12789|Loss: 0.7925831079483032:  49%|████▉     | 12789/25880 [2:37:22<2:20:02,  1.56it/s]
1|12790|Loss: 0.6894872188568115:  49%|████▉     | 12789/25880 [2:37:22<2:20:02,  1.56it/s]
1|12790|Loss: 0.6894872188568115:  49%|████▉     | 12790/25880 [2:37:23<2:27:48,  1.48it/s]
1|12791|Loss: 0.8109647631645203:  49%|████▉     | 12790/25880 [2:37:23<2:27:48,  1.48it/s]
1|12791|Loss: 0.8109647631645203:  49%|████▉     | 12791/25880 [2:37:23<2:32:01,  1.43it/s]
1|12792|Loss: 1.0356712341308594:  49%|████▉     | 12791/25880 [2:37:24<2:32:01,  1.43it/s]
1|12792|Loss: 1.0356712341308594:  49%|████▉     | 12792/25880 [2:37:24<2:33:58,  1.42it/s]
1|12793|Loss: 0.785452663898468:  49%|████▉     | 12792/25880 [2:37:25<2:33:58,  1.42it/s] 
1|12793|Loss: 0.785452663898468:  49%|████▉     | 12793/25880 [2:37:25<2:36:25,  1.39it/s]
1|12794|Loss: 0.9041324257850647:  49%|████▉     | 12793/25880 [2:37:25<2:36:25,  1.39it/s]
1|12794|Loss: 0.9041324257850647:  49%|████▉     | 12794/25880 [2:37:26<2:37:54,  1.38it/s]
1|12795|Loss: 0.8842442035675049:  49%|████▉     | 12794/25880 [2:37:26<2:37:54,  1.38it/s]
1|12795|Loss: 0.8842442035675049:  49%|████▉     | 12795/25880 [2:37:26<2:38:20,  1.38it/s]
1|12796|Loss: 0.8762474060058594:  49%|████▉     | 12795/25880 [2:37:27<2:38:20,  1.38it/s]
1|12796|Loss: 0.8762474060058594:  49%|████▉     | 12796/25880 [2:37:27<2:47:58,  1.30it/s]
1|12797|Loss: 0.7292428612709045:  49%|████▉     | 12796/25880 [2:37:28<2:47:58,  1.30it/s]
1|12797|Loss: 0.7292428612709045:  49%|████▉     | 12797/25880 [2:37:28<2:48:21,  1.30it/s]
1|12798|Loss: 0.7619465589523315:  49%|████▉     | 12797/25880 [2:37:29<2:48:21,  1.30it/s]
1|12798|Loss: 0.7619465589523315:  49%|████▉     | 12798/25880 [2:37:29<2:56:28,  1.24it/s]
1|12799|Loss: 0.8807997703552246:  49%|████▉     | 12798/25880 [2:37:29<2:56:28,  1.24it/s]
1|12799|Loss: 0.8807997703552246:  49%|████▉     | 12799/25880 [2:37:30<2:52:07,  1.27it/s]
1|12800|Loss: 0.8107974529266357:  49%|████▉     | 12799/25880 [2:37:30<2:52:07,  1.27it/s]
1|12800|Loss: 0.8107974529266357:  49%|████▉     | 12800/25880 [2:37:30<2:42:51,  1.34it/s]
1|12801|Loss: 0.7664642930030823:  49%|████▉     | 12800/25880 [2:37:31<2:42:51,  1.34it/s]
1|12801|Loss: 0.7664642930030823:  49%|████▉     | 12801/25880 [2:37:31<2:55:46,  1.24it/s]
1|12802|Loss: 0.8097338676452637:  49%|████▉     | 12801/25880 [2:37:32<2:55:46,  1.24it/s]
1|12802|Loss: 0.8097338676452637:  49%|████▉     | 12802/25880 [2:37:32<3:05:49,  1.17it/s]
1|12803|Loss: 0.7881926894187927:  49%|████▉     | 12802/25880 [2:37:33<3:05:49,  1.17it/s]
1|12803|Loss: 0.7881926894187927:  49%|████▉     | 12803/25880 [2:37:33<3:00:40,  1.21it/s]
1|12804|Loss: 0.9278612732887268:  49%|████▉     | 12803/25880 [2:37:33<3:00:40,  1.21it/s]
1|12804|Loss: 0.9278612732887268:  49%|████▉     | 12804/25880 [2:37:34<2:57:46,  1.23it/s]
1|12805|Loss: 0.914686918258667:  49%|████▉     | 12804/25880 [2:37:34<2:57:46,  1.23it/s] 
1|12805|Loss: 0.914686918258667:  49%|████▉     | 12805/25880 [2:37:35<2:56:02,  1.24it/s]
1|12806|Loss: 0.8367337584495544:  49%|████▉     | 12805/25880 [2:37:35<2:56:02,  1.24it/s]
1|12806|Loss: 0.8367337584495544:  49%|████▉     | 12806/25880 [2:37:35<2:37:24,  1.38it/s]
1|12807|Loss: 0.8622449040412903:  49%|████▉     | 12806/25880 [2:37:35<2:37:24,  1.38it/s]
1|12807|Loss: 0.8622449040412903:  49%|████▉     | 12807/25880 [2:37:36<2:40:12,  1.36it/s]
1|12808|Loss: 0.9199560284614563:  49%|████▉     | 12807/25880 [2:37:36<2:40:12,  1.36it/s]
1|12808|Loss: 0.9199560284614563:  49%|████▉     | 12808/25880 [2:37:37<2:40:14,  1.36it/s]
1|12809|Loss: 0.8041477203369141:  49%|████▉     | 12808/25880 [2:37:37<2:40:14,  1.36it/s]
1|12809|Loss: 0.8041477203369141:  49%|████▉     | 12809/25880 [2:37:37<2:40:25,  1.36it/s]
1|12810|Loss: 0.8478875160217285:  49%|████▉     | 12809/25880 [2:37:38<2:40:25,  1.36it/s]
1|12810|Loss: 0.8478875160217285:  49%|████▉     | 12810/25880 [2:37:38<2:47:28,  1.30it/s]
1|12811|Loss: 0.8271562457084656:  49%|████▉     | 12810/25880 [2:37:39<2:47:28,  1.30it/s]
1|12811|Loss: 0.8271562457084656:  50%|████▉     | 12811/25880 [2:37:39<2:46:58,  1.30it/s]
1|12812|Loss: 0.8442104458808899:  50%|████▉     | 12811/25880 [2:37:39<2:46:58,  1.30it/s]
1|12812|Loss: 0.8442104458808899:  50%|████▉     | 12812/25880 [2:37:40<2:36:37,  1.39it/s]
1|12813|Loss: 0.8244003653526306:  50%|████▉     | 12812/25880 [2:37:40<2:36:37,  1.39it/s]
1|12813|Loss: 0.8244003653526306:  50%|████▉     | 12813/25880 [2:37:40<2:35:44,  1.40it/s]
1|12814|Loss: 0.7419427037239075:  50%|████▉     | 12813/25880 [2:37:41<2:35:44,  1.40it/s]
1|12814|Loss: 0.7419427037239075:  50%|████▉     | 12814/25880 [2:37:41<2:36:54,  1.39it/s]
1|12815|Loss: 0.8677833676338196:  50%|████▉     | 12814/25880 [2:37:41<2:36:54,  1.39it/s]
1|12815|Loss: 0.8677833676338196:  50%|████▉     | 12815/25880 [2:37:42<2:37:31,  1.38it/s]
1|12816|Loss: 0.8231886625289917:  50%|████▉     | 12815/25880 [2:37:42<2:37:31,  1.38it/s]
1|12816|Loss: 0.8231886625289917:  50%|████▉     | 12816/25880 [2:37:42<2:36:40,  1.39it/s]
1|12817|Loss: 0.8446452021598816:  50%|████▉     | 12816/25880 [2:37:43<2:36:40,  1.39it/s]
1|12817|Loss: 0.8446452021598816:  50%|████▉     | 12817/25880 [2:37:43<2:37:39,  1.38it/s]
1|12818|Loss: 0.7907332181930542:  50%|████▉     | 12817/25880 [2:37:44<2:37:39,  1.38it/s]
1|12818|Loss: 0.7907332181930542:  50%|████▉     | 12818/25880 [2:37:44<2:43:13,  1.33it/s]
1|12819|Loss: 0.8320073485374451:  50%|████▉     | 12818/25880 [2:37:44<2:43:13,  1.33it/s]
1|12819|Loss: 0.8320073485374451:  50%|████▉     | 12819/25880 [2:37:45<2:43:36,  1.33it/s]
1|12820|Loss: 0.8719484210014343:  50%|████▉     | 12819/25880 [2:37:45<2:43:36,  1.33it/s]
1|12820|Loss: 0.8719484210014343:  50%|████▉     | 12820/25880 [2:37:46<2:45:31,  1.31it/s]
1|12821|Loss: 0.8689634799957275:  50%|████▉     | 12820/25880 [2:37:46<2:45:31,  1.31it/s]
1|12821|Loss: 0.8689634799957275:  50%|████▉     | 12821/25880 [2:37:46<2:45:06,  1.32it/s]
1|12822|Loss: 0.8926143050193787:  50%|████▉     | 12821/25880 [2:37:47<2:45:06,  1.32it/s]
1|12822|Loss: 0.8926143050193787:  50%|████▉     | 12822/25880 [2:37:47<2:48:12,  1.29it/s]
1|12823|Loss: 0.7843324542045593:  50%|████▉     | 12822/25880 [2:37:47<2:48:12,  1.29it/s]
1|12823|Loss: 0.7843324542045593:  50%|████▉     | 12823/25880 [2:37:48<2:47:06,  1.30it/s]
1|12824|Loss: 0.9800230264663696:  50%|████▉     | 12823/25880 [2:37:48<2:47:06,  1.30it/s]
1|12824|Loss: 0.9800230264663696:  50%|████▉     | 12824/25880 [2:37:48<2:32:20,  1.43it/s]
1|12825|Loss: 0.7668433785438538:  50%|████▉     | 12824/25880 [2:37:49<2:32:20,  1.43it/s]
1|12825|Loss: 0.7668433785438538:  50%|████▉     | 12825/25880 [2:37:49<2:31:18,  1.44it/s]
1|12826|Loss: 0.8329634666442871:  50%|████▉     | 12825/25880 [2:37:49<2:31:18,  1.44it/s]
1|12826|Loss: 0.8329634666442871:  50%|████▉     | 12826/25880 [2:37:50<2:33:51,  1.41it/s]
1|12827|Loss: 0.7175252437591553:  50%|████▉     | 12826/25880 [2:37:50<2:33:51,  1.41it/s]
1|12827|Loss: 0.7175252437591553:  50%|████▉     | 12827/25880 [2:37:50<2:17:19,  1.58it/s]
1|12828|Loss: 0.8633361458778381:  50%|████▉     | 12827/25880 [2:37:51<2:17:19,  1.58it/s]
1|12828|Loss: 0.8633361458778381:  50%|████▉     | 12828/25880 [2:37:51<2:23:53,  1.51it/s]
1|12829|Loss: 0.7772019505500793:  50%|████▉     | 12828/25880 [2:37:51<2:23:53,  1.51it/s]
1|12829|Loss: 0.7772019505500793:  50%|████▉     | 12829/25880 [2:37:52<2:35:51,  1.40it/s]
1|12830|Loss: 0.8967087864875793:  50%|████▉     | 12829/25880 [2:37:52<2:35:51,  1.40it/s]
1|12830|Loss: 0.8967087864875793:  50%|████▉     | 12830/25880 [2:37:52<2:30:55,  1.44it/s]
1|12831|Loss: 0.8497767448425293:  50%|████▉     | 12830/25880 [2:37:53<2:30:55,  1.44it/s]
1|12831|Loss: 0.8497767448425293:  50%|████▉     | 12831/25880 [2:37:53<2:37:28,  1.38it/s]
1|12832|Loss: 0.8927862048149109:  50%|████▉     | 12831/25880 [2:37:54<2:37:28,  1.38it/s]
1|12832|Loss: 0.8927862048149109:  50%|████▉     | 12832/25880 [2:37:54<2:46:01,  1.31it/s]
1|12833|Loss: 0.7224830985069275:  50%|████▉     | 12832/25880 [2:37:55<2:46:01,  1.31it/s]
1|12833|Loss: 0.7224830985069275:  50%|████▉     | 12833/25880 [2:37:55<2:46:27,  1.31it/s]
1|12834|Loss: 0.6785492897033691:  50%|████▉     | 12833/25880 [2:37:55<2:46:27,  1.31it/s]
1|12834|Loss: 0.6785492897033691:  50%|████▉     | 12834/25880 [2:37:56<2:38:40,  1.37it/s]
1|12835|Loss: 0.8157464861869812:  50%|████▉     | 12834/25880 [2:37:56<2:38:40,  1.37it/s]
1|12835|Loss: 0.8157464861869812:  50%|████▉     | 12835/25880 [2:37:56<2:32:18,  1.43it/s]
1|12836|Loss: 0.8053929209709167:  50%|████▉     | 12835/25880 [2:37:57<2:32:18,  1.43it/s]
1|12836|Loss: 0.8053929209709167:  50%|████▉     | 12836/25880 [2:37:57<2:36:08,  1.39it/s]
1|12837|Loss: 0.8184903860092163:  50%|████▉     | 12836/25880 [2:37:57<2:36:08,  1.39it/s]
1|12837|Loss: 0.8184903860092163:  50%|████▉     | 12837/25880 [2:37:58<2:27:50,  1.47it/s]
1|12838|Loss: 0.8493752479553223:  50%|████▉     | 12837/25880 [2:37:58<2:27:50,  1.47it/s]
1|12838|Loss: 0.8493752479553223:  50%|████▉     | 12838/25880 [2:37:58<2:37:52,  1.38it/s]
1|12839|Loss: 0.8476307392120361:  50%|████▉     | 12838/25880 [2:37:59<2:37:52,  1.38it/s]
1|12839|Loss: 0.8476307392120361:  50%|████▉     | 12839/25880 [2:37:59<2:39:02,  1.37it/s]
1|12840|Loss: 0.8318191170692444:  50%|████▉     | 12839/25880 [2:37:59<2:39:02,  1.37it/s]
1|12840|Loss: 0.8318191170692444:  50%|████▉     | 12840/25880 [2:38:00<2:38:19,  1.37it/s]
1|12841|Loss: 0.8756430745124817:  50%|████▉     | 12840/25880 [2:38:00<2:38:19,  1.37it/s]
1|12841|Loss: 0.8756430745124817:  50%|████▉     | 12841/25880 [2:38:01<2:45:28,  1.31it/s]
1|12842|Loss: 0.8096770644187927:  50%|████▉     | 12841/25880 [2:38:01<2:45:28,  1.31it/s]
1|12842|Loss: 0.8096770644187927:  50%|████▉     | 12842/25880 [2:38:01<2:35:02,  1.40it/s]
1|12843|Loss: 0.7128437757492065:  50%|████▉     | 12842/25880 [2:38:02<2:35:02,  1.40it/s]
1|12843|Loss: 0.7128437757492065:  50%|████▉     | 12843/25880 [2:38:02<2:33:56,  1.41it/s]
1|12844|Loss: 0.8887556195259094:  50%|████▉     | 12843/25880 [2:38:02<2:33:56,  1.41it/s]
1|12844|Loss: 0.8887556195259094:  50%|████▉     | 12844/25880 [2:38:03<2:30:49,  1.44it/s]
1|12845|Loss: 0.996818482875824:  50%|████▉     | 12844/25880 [2:38:03<2:30:49,  1.44it/s] 
1|12845|Loss: 0.996818482875824:  50%|████▉     | 12845/25880 [2:38:03<2:41:39,  1.34it/s]
1|12846|Loss: 0.8238273859024048:  50%|████▉     | 12845/25880 [2:38:04<2:41:39,  1.34it/s]
1|12846|Loss: 0.8238273859024048:  50%|████▉     | 12846/25880 [2:38:04<2:43:37,  1.33it/s]
1|12847|Loss: 0.8605676293373108:  50%|████▉     | 12846/25880 [2:38:05<2:43:37,  1.33it/s]
1|12847|Loss: 0.8605676293373108:  50%|████▉     | 12847/25880 [2:38:05<2:42:35,  1.34it/s]
1|12848|Loss: 0.8381688594818115:  50%|████▉     | 12847/25880 [2:38:05<2:42:35,  1.34it/s]
1|12848|Loss: 0.8381688594818115:  50%|████▉     | 12848/25880 [2:38:06<2:36:16,  1.39it/s]
1|12849|Loss: 0.766377329826355:  50%|████▉     | 12848/25880 [2:38:06<2:36:16,  1.39it/s] 
1|12849|Loss: 0.766377329826355:  50%|████▉     | 12849/25880 [2:38:06<2:36:31,  1.39it/s]
1|12850|Loss: 0.8861549496650696:  50%|████▉     | 12849/25880 [2:38:07<2:36:31,  1.39it/s]
1|12850|Loss: 0.8861549496650696:  50%|████▉     | 12850/25880 [2:38:07<2:23:33,  1.51it/s]
1|12851|Loss: 0.8410433530807495:  50%|████▉     | 12850/25880 [2:38:07<2:23:33,  1.51it/s]
1|12851|Loss: 0.8410433530807495:  50%|████▉     | 12851/25880 [2:38:08<2:30:26,  1.44it/s]
1|12852|Loss: 0.9900856018066406:  50%|████▉     | 12851/25880 [2:38:08<2:30:26,  1.44it/s]
1|12852|Loss: 0.9900856018066406:  50%|████▉     | 12852/25880 [2:38:08<2:29:17,  1.45it/s]
1|12853|Loss: 0.8590251207351685:  50%|████▉     | 12852/25880 [2:38:09<2:29:17,  1.45it/s]
1|12853|Loss: 0.8590251207351685:  50%|████▉     | 12853/25880 [2:38:09<2:36:49,  1.38it/s]
1|12854|Loss: 0.7242586016654968:  50%|████▉     | 12853/25880 [2:38:09<2:36:49,  1.38it/s]
1|12854|Loss: 0.7242586016654968:  50%|████▉     | 12854/25880 [2:38:10<2:27:39,  1.47it/s]
1|12855|Loss: 0.7470152974128723:  50%|████▉     | 12854/25880 [2:38:10<2:27:39,  1.47it/s]
1|12855|Loss: 0.7470152974128723:  50%|████▉     | 12855/25880 [2:38:10<2:27:51,  1.47it/s]
1|12856|Loss: 0.9126030802726746:  50%|████▉     | 12855/25880 [2:38:11<2:27:51,  1.47it/s]
1|12856|Loss: 0.9126030802726746:  50%|████▉     | 12856/25880 [2:38:11<2:29:24,  1.45it/s]
1|12857|Loss: 0.7192930579185486:  50%|████▉     | 12856/25880 [2:38:12<2:29:24,  1.45it/s]
1|12857|Loss: 0.7192930579185486:  50%|████▉     | 12857/25880 [2:38:12<2:39:20,  1.36it/s]
1|12858|Loss: 0.8956842422485352:  50%|████▉     | 12857/25880 [2:38:12<2:39:20,  1.36it/s]
1|12858|Loss: 0.8956842422485352:  50%|████▉     | 12858/25880 [2:38:13<2:46:57,  1.30it/s]
1|12859|Loss: 0.7953490018844604:  50%|████▉     | 12858/25880 [2:38:13<2:46:57,  1.30it/s]
1|12859|Loss: 0.7953490018844604:  50%|████▉     | 12859/25880 [2:38:14<2:43:55,  1.32it/s]
1|12860|Loss: 0.9158817529678345:  50%|████▉     | 12859/25880 [2:38:14<2:43:55,  1.32it/s]
1|12860|Loss: 0.9158817529678345:  50%|████▉     | 12860/25880 [2:38:14<2:45:13,  1.31it/s]
1|12861|Loss: 0.8140426874160767:  50%|████▉     | 12860/25880 [2:38:15<2:45:13,  1.31it/s]
1|12861|Loss: 0.8140426874160767:  50%|████▉     | 12861/25880 [2:38:15<2:49:28,  1.28it/s]
1|12862|Loss: 0.9220685958862305:  50%|████▉     | 12861/25880 [2:38:16<2:49:28,  1.28it/s]
1|12862|Loss: 0.9220685958862305:  50%|████▉     | 12862/25880 [2:38:16<2:48:10,  1.29it/s]
1|12863|Loss: 0.7878791689872742:  50%|████▉     | 12862/25880 [2:38:16<2:48:10,  1.29it/s]
1|12863|Loss: 0.7878791689872742:  50%|████▉     | 12863/25880 [2:38:17<2:51:26,  1.27it/s]
1|12864|Loss: 0.7567802667617798:  50%|████▉     | 12863/25880 [2:38:17<2:51:26,  1.27it/s]
1|12864|Loss: 0.7567802667617798:  50%|████▉     | 12864/25880 [2:38:17<2:49:42,  1.28it/s]
1|12865|Loss: 0.8507481813430786:  50%|████▉     | 12864/25880 [2:38:18<2:49:42,  1.28it/s]
1|12865|Loss: 0.8507481813430786:  50%|████▉     | 12865/25880 [2:38:18<2:52:00,  1.26it/s]
1|12866|Loss: 0.913775622844696:  50%|████▉     | 12865/25880 [2:38:19<2:52:00,  1.26it/s] 
1|12866|Loss: 0.913775622844696:  50%|████▉     | 12866/25880 [2:38:19<2:50:39,  1.27it/s]
1|12867|Loss: 0.8034020662307739:  50%|████▉     | 12866/25880 [2:38:19<2:50:39,  1.27it/s]
1|12867|Loss: 0.8034020662307739:  50%|████▉     | 12867/25880 [2:38:20<2:41:50,  1.34it/s]
1|12868|Loss: 0.8298291563987732:  50%|████▉     | 12867/25880 [2:38:20<2:41:50,  1.34it/s]
1|12868|Loss: 0.8298291563987732:  50%|████▉     | 12868/25880 [2:38:20<2:39:10,  1.36it/s]
1|12869|Loss: 0.8520144820213318:  50%|████▉     | 12868/25880 [2:38:21<2:39:10,  1.36it/s]
1|12869|Loss: 0.8520144820213318:  50%|████▉     | 12869/25880 [2:38:21<2:32:23,  1.42it/s]
1|12870|Loss: 0.8934763669967651:  50%|████▉     | 12869/25880 [2:38:21<2:32:23,  1.42it/s]
1|12870|Loss: 0.8934763669967651:  50%|████▉     | 12870/25880 [2:38:22<2:24:59,  1.50it/s]
1|12871|Loss: 0.8004124164581299:  50%|████▉     | 12870/25880 [2:38:22<2:24:59,  1.50it/s]
1|12871|Loss: 0.8004124164581299:  50%|████▉     | 12871/25880 [2:38:22<2:27:13,  1.47it/s]
1|12872|Loss: 0.7177180051803589:  50%|████▉     | 12871/25880 [2:38:23<2:27:13,  1.47it/s]
1|12872|Loss: 0.7177180051803589:  50%|████▉     | 12872/25880 [2:38:23<2:26:36,  1.48it/s]
1|12873|Loss: 1.0487076044082642:  50%|████▉     | 12872/25880 [2:38:23<2:26:36,  1.48it/s]
1|12873|Loss: 1.0487076044082642:  50%|████▉     | 12873/25880 [2:38:24<2:35:20,  1.40it/s]
1|12874|Loss: 0.8879292607307434:  50%|████▉     | 12873/25880 [2:38:24<2:35:20,  1.40it/s]
1|12874|Loss: 0.8879292607307434:  50%|████▉     | 12874/25880 [2:38:24<2:29:24,  1.45it/s]
1|12875|Loss: 0.8286458849906921:  50%|████▉     | 12874/25880 [2:38:25<2:29:24,  1.45it/s]
1|12875|Loss: 0.8286458849906921:  50%|████▉     | 12875/25880 [2:38:25<2:24:57,  1.50it/s]
1|12876|Loss: 0.8275923728942871:  50%|████▉     | 12875/25880 [2:38:25<2:24:57,  1.50it/s]
1|12876|Loss: 0.8275923728942871:  50%|████▉     | 12876/25880 [2:38:26<2:18:42,  1.56it/s]
1|12877|Loss: 0.7707104086875916:  50%|████▉     | 12876/25880 [2:38:26<2:18:42,  1.56it/s]
1|12877|Loss: 0.7707104086875916:  50%|████▉     | 12877/25880 [2:38:26<2:28:29,  1.46it/s]
1|12878|Loss: 0.8676661252975464:  50%|████▉     | 12877/25880 [2:38:27<2:28:29,  1.46it/s]
1|12878|Loss: 0.8676661252975464:  50%|████▉     | 12878/25880 [2:38:27<2:36:19,  1.39it/s]
1|12879|Loss: 0.987633228302002:  50%|████▉     | 12878/25880 [2:38:28<2:36:19,  1.39it/s] 
1|12879|Loss: 0.987633228302002:  50%|████▉     | 12879/25880 [2:38:28<2:38:34,  1.37it/s]
1|12880|Loss: 0.7340167760848999:  50%|████▉     | 12879/25880 [2:38:28<2:38:34,  1.37it/s]
1|12880|Loss: 0.7340167760848999:  50%|████▉     | 12880/25880 [2:38:29<2:28:30,  1.46it/s]
1|12881|Loss: 0.8923043012619019:  50%|████▉     | 12880/25880 [2:38:29<2:28:30,  1.46it/s]
1|12881|Loss: 0.8923043012619019:  50%|████▉     | 12881/25880 [2:38:29<2:32:41,  1.42it/s]
1|12882|Loss: 0.8700957894325256:  50%|████▉     | 12881/25880 [2:38:30<2:32:41,  1.42it/s]
1|12882|Loss: 0.8700957894325256:  50%|████▉     | 12882/25880 [2:38:30<2:36:12,  1.39it/s]
1|12883|Loss: 0.9556716680526733:  50%|████▉     | 12882/25880 [2:38:30<2:36:12,  1.39it/s]
1|12883|Loss: 0.9556716680526733:  50%|████▉     | 12883/25880 [2:38:31<2:36:28,  1.38it/s]
1|12884|Loss: 0.745490550994873:  50%|████▉     | 12883/25880 [2:38:31<2:36:28,  1.38it/s] 
1|12884|Loss: 0.745490550994873:  50%|████▉     | 12884/25880 [2:38:32<2:35:00,  1.40it/s]
1|12885|Loss: 0.7905891537666321:  50%|████▉     | 12884/25880 [2:38:32<2:35:00,  1.40it/s]
1|12885|Loss: 0.7905891537666321:  50%|████▉     | 12885/25880 [2:38:32<2:35:24,  1.39it/s]
1|12886|Loss: 0.8540282845497131:  50%|████▉     | 12885/25880 [2:38:33<2:35:24,  1.39it/s]
1|12886|Loss: 0.8540282845497131:  50%|████▉     | 12886/25880 [2:38:33<2:34:36,  1.40it/s]
1|12887|Loss: 0.754130482673645:  50%|████▉     | 12886/25880 [2:38:33<2:34:36,  1.40it/s] 
1|12887|Loss: 0.754130482673645:  50%|████▉     | 12887/25880 [2:38:34<2:44:47,  1.31it/s]
1|12888|Loss: 0.7300849556922913:  50%|████▉     | 12887/25880 [2:38:34<2:44:47,  1.31it/s]
1|12888|Loss: 0.7300849556922913:  50%|████▉     | 12888/25880 [2:38:35<2:45:39,  1.31it/s]
1|12889|Loss: 0.8433293104171753:  50%|████▉     | 12888/25880 [2:38:35<2:45:39,  1.31it/s]
1|12889|Loss: 0.8433293104171753:  50%|████▉     | 12889/25880 [2:38:35<2:44:44,  1.31it/s]
1|12890|Loss: 0.9017736315727234:  50%|████▉     | 12889/25880 [2:38:36<2:44:44,  1.31it/s]
1|12890|Loss: 0.9017736315727234:  50%|████▉     | 12890/25880 [2:38:36<2:31:42,  1.43it/s]
1|12891|Loss: 0.732161283493042:  50%|████▉     | 12890/25880 [2:38:36<2:31:42,  1.43it/s] 
1|12891|Loss: 0.732161283493042:  50%|████▉     | 12891/25880 [2:38:36<2:20:17,  1.54it/s]
1|12892|Loss: 0.7712788581848145:  50%|████▉     | 12891/25880 [2:38:37<2:20:17,  1.54it/s]
1|12892|Loss: 0.7712788581848145:  50%|████▉     | 12892/25880 [2:38:37<2:29:22,  1.45it/s]
1|12893|Loss: 0.8134181499481201:  50%|████▉     | 12892/25880 [2:38:38<2:29:22,  1.45it/s]
1|12893|Loss: 0.8134181499481201:  50%|████▉     | 12893/25880 [2:38:38<2:34:38,  1.40it/s]
1|12894|Loss: 0.8672992587089539:  50%|████▉     | 12893/25880 [2:38:38<2:34:38,  1.40it/s]
1|12894|Loss: 0.8672992587089539:  50%|████▉     | 12894/25880 [2:38:39<2:35:06,  1.40it/s]
1|12895|Loss: 0.8238000869750977:  50%|████▉     | 12894/25880 [2:38:39<2:35:06,  1.40it/s]
1|12895|Loss: 0.8238000869750977:  50%|████▉     | 12895/25880 [2:38:39<2:17:59,  1.57it/s]
1|12896|Loss: 0.8333804607391357:  50%|████▉     | 12895/25880 [2:38:39<2:17:59,  1.57it/s]
1|12896|Loss: 0.8333804607391357:  50%|████▉     | 12896/25880 [2:38:40<2:20:13,  1.54it/s]
1|12897|Loss: 0.8236566781997681:  50%|████▉     | 12896/25880 [2:38:40<2:20:13,  1.54it/s]
1|12897|Loss: 0.8236566781997681:  50%|████▉     | 12897/25880 [2:38:41<2:29:00,  1.45it/s]
1|12898|Loss: 0.6032727956771851:  50%|████▉     | 12897/25880 [2:38:41<2:29:00,  1.45it/s]
1|12898|Loss: 0.6032727956771851:  50%|████▉     | 12898/25880 [2:38:41<2:40:00,  1.35it/s]
1|12899|Loss: 0.8510886430740356:  50%|████▉     | 12898/25880 [2:38:42<2:40:00,  1.35it/s]
1|12899|Loss: 0.8510886430740356:  50%|████▉     | 12899/25880 [2:38:42<2:42:10,  1.33it/s]
1|12900|Loss: 0.8203771710395813:  50%|████▉     | 12899/25880 [2:38:43<2:42:10,  1.33it/s]
1|12900|Loss: 0.8203771710395813:  50%|████▉     | 12900/25880 [2:38:43<2:41:27,  1.34it/s]
1|12901|Loss: 1.0161240100860596:  50%|████▉     | 12900/25880 [2:38:43<2:41:27,  1.34it/s]
1|12901|Loss: 1.0161240100860596:  50%|████▉     | 12901/25880 [2:38:44<2:40:06,  1.35it/s]
1|12902|Loss: 0.9982439875602722:  50%|████▉     | 12901/25880 [2:38:44<2:40:06,  1.35it/s]
1|12902|Loss: 0.9982439875602722:  50%|████▉     | 12902/25880 [2:38:44<2:33:10,  1.41it/s]
1|12903|Loss: 0.9160875082015991:  50%|████▉     | 12902/25880 [2:38:45<2:33:10,  1.41it/s]
1|12903|Loss: 0.9160875082015991:  50%|████▉     | 12903/25880 [2:38:45<2:25:50,  1.48it/s]
1|12904|Loss: 0.8914258480072021:  50%|████▉     | 12903/25880 [2:38:45<2:25:50,  1.48it/s]
1|12904|Loss: 0.8914258480072021:  50%|████▉     | 12904/25880 [2:38:45<2:16:04,  1.59it/s]
1|12905|Loss: 0.8539212346076965:  50%|████▉     | 12904/25880 [2:38:46<2:16:04,  1.59it/s]
1|12905|Loss: 0.8539212346076965:  50%|████▉     | 12905/25880 [2:38:46<2:24:50,  1.49it/s]
1|12906|Loss: 0.9033389091491699:  50%|████▉     | 12905/25880 [2:38:47<2:24:50,  1.49it/s]
1|12906|Loss: 0.9033389091491699:  50%|████▉     | 12906/25880 [2:38:47<2:33:37,  1.41it/s]
1|12907|Loss: 0.8581908345222473:  50%|████▉     | 12906/25880 [2:38:47<2:33:37,  1.41it/s]
1|12907|Loss: 0.8581908345222473:  50%|████▉     | 12907/25880 [2:38:48<2:36:39,  1.38it/s]
1|12908|Loss: 0.8585590124130249:  50%|████▉     | 12907/25880 [2:38:48<2:36:39,  1.38it/s]
1|12908|Loss: 0.8585590124130249:  50%|████▉     | 12908/25880 [2:38:49<2:37:15,  1.37it/s]
1|12909|Loss: 0.8616697192192078:  50%|████▉     | 12908/25880 [2:38:49<2:37:15,  1.37it/s]
1|12909|Loss: 0.8616697192192078:  50%|████▉     | 12909/25880 [2:38:49<2:35:32,  1.39it/s]
1|12910|Loss: 0.8575741052627563:  50%|████▉     | 12909/25880 [2:38:50<2:35:32,  1.39it/s]
1|12910|Loss: 0.8575741052627563:  50%|████▉     | 12910/25880 [2:38:50<2:39:34,  1.35it/s]
1|12911|Loss: 0.7942290306091309:  50%|████▉     | 12910/25880 [2:38:50<2:39:34,  1.35it/s]
1|12911|Loss: 0.7942290306091309:  50%|████▉     | 12911/25880 [2:38:51<2:38:24,  1.36it/s]
1|12912|Loss: 0.7721260190010071:  50%|████▉     | 12911/25880 [2:38:51<2:38:24,  1.36it/s]
1|12912|Loss: 0.7721260190010071:  50%|████▉     | 12912/25880 [2:38:51<2:30:03,  1.44it/s]
1|12913|Loss: 0.9095078110694885:  50%|████▉     | 12912/25880 [2:38:52<2:30:03,  1.44it/s]
1|12913|Loss: 0.9095078110694885:  50%|████▉     | 12913/25880 [2:38:52<2:30:33,  1.44it/s]
1|12914|Loss: 0.7053932547569275:  50%|████▉     | 12913/25880 [2:38:52<2:30:33,  1.44it/s]
1|12914|Loss: 0.7053932547569275:  50%|████▉     | 12914/25880 [2:38:53<2:26:46,  1.47it/s]
1|12915|Loss: 0.8766481280326843:  50%|████▉     | 12914/25880 [2:38:53<2:26:46,  1.47it/s]
1|12915|Loss: 0.8766481280326843:  50%|████▉     | 12915/25880 [2:38:54<2:40:52,  1.34it/s]
1|12916|Loss: 0.8919585347175598:  50%|████▉     | 12915/25880 [2:38:54<2:40:52,  1.34it/s]
1|12916|Loss: 0.8919585347175598:  50%|████▉     | 12916/25880 [2:38:54<2:37:10,  1.37it/s]
1|12917|Loss: 0.9223021268844604:  50%|████▉     | 12916/25880 [2:38:55<2:37:10,  1.37it/s]
1|12917|Loss: 0.9223021268844604:  50%|████▉     | 12917/25880 [2:38:55<2:38:48,  1.36it/s]
1|12918|Loss: 0.7277852892875671:  50%|████▉     | 12917/25880 [2:38:55<2:38:48,  1.36it/s]
1|12918|Loss: 0.7277852892875671:  50%|████▉     | 12918/25880 [2:38:56<2:44:28,  1.31it/s]
1|12919|Loss: 0.9063563346862793:  50%|████▉     | 12918/25880 [2:38:56<2:44:28,  1.31it/s]
1|12919|Loss: 0.9063563346862793:  50%|████▉     | 12919/25880 [2:38:57<2:44:19,  1.31it/s]
1|12920|Loss: 0.9268430471420288:  50%|████▉     | 12919/25880 [2:38:57<2:44:19,  1.31it/s]
1|12920|Loss: 0.9268430471420288:  50%|████▉     | 12920/25880 [2:38:57<2:42:38,  1.33it/s]
1|12921|Loss: 0.7576352953910828:  50%|████▉     | 12920/25880 [2:38:58<2:42:38,  1.33it/s]
1|12921|Loss: 0.7576352953910828:  50%|████▉     | 12921/25880 [2:38:58<2:42:02,  1.33it/s]
1|12922|Loss: 0.8198602199554443:  50%|████▉     | 12921/25880 [2:38:58<2:42:02,  1.33it/s]
1|12922|Loss: 0.8198602199554443:  50%|████▉     | 12922/25880 [2:38:59<2:33:35,  1.41it/s]
1|12923|Loss: 0.8563395738601685:  50%|████▉     | 12922/25880 [2:38:59<2:33:35,  1.41it/s]
1|12923|Loss: 0.8563395738601685:  50%|████▉     | 12923/25880 [2:38:59<2:33:43,  1.40it/s]
1|12924|Loss: 0.8652946949005127:  50%|████▉     | 12923/25880 [2:39:00<2:33:43,  1.40it/s]
1|12924|Loss: 0.8652946949005127:  50%|████▉     | 12924/25880 [2:39:00<2:43:10,  1.32it/s]
1|12925|Loss: 0.8441253304481506:  50%|████▉     | 12924/25880 [2:39:01<2:43:10,  1.32it/s]
1|12925|Loss: 0.8441253304481506:  50%|████▉     | 12925/25880 [2:39:01<2:48:57,  1.28it/s]
1|12926|Loss: 1.028444528579712:  50%|████▉     | 12925/25880 [2:39:02<2:48:57,  1.28it/s] 
1|12926|Loss: 1.028444528579712:  50%|████▉     | 12926/25880 [2:39:02<2:46:36,  1.30it/s]
1|12927|Loss: 0.8115058541297913:  50%|████▉     | 12926/25880 [2:39:02<2:46:36,  1.30it/s]
1|12927|Loss: 0.8115058541297913:  50%|████▉     | 12927/25880 [2:39:03<2:43:02,  1.32it/s]
1|12928|Loss: 0.8503321409225464:  50%|████▉     | 12927/25880 [2:39:03<2:43:02,  1.32it/s]
1|12928|Loss: 0.8503321409225464:  50%|████▉     | 12928/25880 [2:39:03<2:39:23,  1.35it/s]
1|12929|Loss: 0.8676609992980957:  50%|████▉     | 12928/25880 [2:39:04<2:39:23,  1.35it/s]
1|12929|Loss: 0.8676609992980957:  50%|████▉     | 12929/25880 [2:39:04<2:43:30,  1.32it/s]
1|12930|Loss: 0.7979795336723328:  50%|████▉     | 12929/25880 [2:39:04<2:43:30,  1.32it/s]
1|12930|Loss: 0.7979795336723328:  50%|████▉     | 12930/25880 [2:39:05<2:42:47,  1.33it/s]
1|12931|Loss: 0.8989183902740479:  50%|████▉     | 12930/25880 [2:39:05<2:42:47,  1.33it/s]
1|12931|Loss: 0.8989183902740479:  50%|████▉     | 12931/25880 [2:39:06<2:41:21,  1.34it/s]
1|12932|Loss: 0.8597894310951233:  50%|████▉     | 12931/25880 [2:39:06<2:41:21,  1.34it/s]
1|12932|Loss: 0.8597894310951233:  50%|████▉     | 12932/25880 [2:39:06<2:40:33,  1.34it/s]
1|12933|Loss: 0.8315770626068115:  50%|████▉     | 12932/25880 [2:39:07<2:40:33,  1.34it/s]
1|12933|Loss: 0.8315770626068115:  50%|████▉     | 12933/25880 [2:39:07<2:49:20,  1.27it/s]
1|12934|Loss: 0.8477654457092285:  50%|████▉     | 12933/25880 [2:39:08<2:49:20,  1.27it/s]
1|12934|Loss: 0.8477654457092285:  50%|████▉     | 12934/25880 [2:39:08<2:43:43,  1.32it/s]
1|12935|Loss: 0.717439591884613:  50%|████▉     | 12934/25880 [2:39:08<2:43:43,  1.32it/s] 
1|12935|Loss: 0.717439591884613:  50%|████▉     | 12935/25880 [2:39:09<2:49:17,  1.27it/s]
1|12936|Loss: 0.7634159922599792:  50%|████▉     | 12935/25880 [2:39:09<2:49:17,  1.27it/s]
1|12936|Loss: 0.7634159922599792:  50%|████▉     | 12936/25880 [2:39:09<2:42:09,  1.33it/s]
1|12937|Loss: 0.9013127088546753:  50%|████▉     | 12936/25880 [2:39:10<2:42:09,  1.33it/s]
1|12937|Loss: 0.9013127088546753:  50%|████▉     | 12937/25880 [2:39:10<2:49:14,  1.27it/s]
1|12938|Loss: 0.8927193284034729:  50%|████▉     | 12937/25880 [2:39:11<2:49:14,  1.27it/s]
1|12938|Loss: 0.8927193284034729:  50%|████▉     | 12938/25880 [2:39:11<2:56:05,  1.22it/s]
1|12939|Loss: 0.8717788457870483:  50%|████▉     | 12938/25880 [2:39:12<2:56:05,  1.22it/s]
1|12939|Loss: 0.8717788457870483:  50%|████▉     | 12939/25880 [2:39:12<2:46:59,  1.29it/s]
1|12940|Loss: 0.7980099320411682:  50%|████▉     | 12939/25880 [2:39:12<2:46:59,  1.29it/s]
1|12940|Loss: 0.7980099320411682:  50%|█████     | 12940/25880 [2:39:12<2:38:01,  1.36it/s]
1|12941|Loss: 1.0021990537643433:  50%|█████     | 12940/25880 [2:39:13<2:38:01,  1.36it/s]
1|12941|Loss: 1.0021990537643433:  50%|█████     | 12941/25880 [2:39:13<2:40:55,  1.34it/s]
1|12942|Loss: 0.7421602010726929:  50%|█████     | 12941/25880 [2:39:14<2:40:55,  1.34it/s]
1|12942|Loss: 0.7421602010726929:  50%|█████     | 12942/25880 [2:39:14<2:43:59,  1.31it/s]
1|12943|Loss: 0.8824292421340942:  50%|█████     | 12942/25880 [2:39:14<2:43:59,  1.31it/s]
1|12943|Loss: 0.8824292421340942:  50%|█████     | 12943/25880 [2:39:15<2:41:55,  1.33it/s]
1|12944|Loss: 0.850326657295227:  50%|█████     | 12943/25880 [2:39:15<2:41:55,  1.33it/s] 
1|12944|Loss: 0.850326657295227:  50%|█████     | 12944/25880 [2:39:15<2:39:56,  1.35it/s]
1|12945|Loss: 0.7369688153266907:  50%|█████     | 12944/25880 [2:39:16<2:39:56,  1.35it/s]
1|12945|Loss: 0.7369688153266907:  50%|█████     | 12945/25880 [2:39:16<2:42:01,  1.33it/s]
1|12946|Loss: 0.8306463360786438:  50%|█████     | 12945/25880 [2:39:17<2:42:01,  1.33it/s]
1|12946|Loss: 0.8306463360786438:  50%|█████     | 12946/25880 [2:39:17<2:42:44,  1.32it/s]
1|12947|Loss: 0.814216136932373:  50%|█████     | 12946/25880 [2:39:17<2:42:44,  1.32it/s] 
1|12947|Loss: 0.814216136932373:  50%|█████     | 12947/25880 [2:39:18<2:46:28,  1.29it/s]
1|12948|Loss: 0.7617701292037964:  50%|█████     | 12947/25880 [2:39:18<2:46:28,  1.29it/s]
1|12948|Loss: 0.7617701292037964:  50%|█████     | 12948/25880 [2:39:18<2:40:04,  1.35it/s]
1|12949|Loss: 0.778010368347168:  50%|█████     | 12948/25880 [2:39:19<2:40:04,  1.35it/s] 
1|12949|Loss: 0.778010368347168:  50%|█████     | 12949/25880 [2:39:19<2:18:54,  1.55it/s]
1|12950|Loss: 0.8691926598548889:  50%|█████     | 12949/25880 [2:39:19<2:18:54,  1.55it/s]
1|12950|Loss: 0.8691926598548889:  50%|█████     | 12950/25880 [2:39:20<2:18:27,  1.56it/s]
1|12951|Loss: 0.779714822769165:  50%|█████     | 12950/25880 [2:39:20<2:18:27,  1.56it/s] 
1|12951|Loss: 0.779714822769165:  50%|█████     | 12951/25880 [2:39:20<2:30:50,  1.43it/s]
1|12952|Loss: 0.9307971000671387:  50%|█████     | 12951/25880 [2:39:21<2:30:50,  1.43it/s]
1|12952|Loss: 0.9307971000671387:  50%|█████     | 12952/25880 [2:39:21<2:35:26,  1.39it/s]
1|12953|Loss: 0.8934820294380188:  50%|█████     | 12952/25880 [2:39:22<2:35:26,  1.39it/s]
1|12953|Loss: 0.8934820294380188:  50%|█████     | 12953/25880 [2:39:22<2:30:38,  1.43it/s]
1|12954|Loss: 0.7931878566741943:  50%|█████     | 12953/25880 [2:39:22<2:30:38,  1.43it/s]
1|12954|Loss: 0.7931878566741943:  50%|█████     | 12954/25880 [2:39:23<2:44:17,  1.31it/s]
1|12955|Loss: 0.9192197322845459:  50%|█████     | 12954/25880 [2:39:23<2:44:17,  1.31it/s]
1|12955|Loss: 0.9192197322845459:  50%|█████     | 12955/25880 [2:39:23<2:35:41,  1.38it/s]
1|12956|Loss: 1.0051771402359009:  50%|█████     | 12955/25880 [2:39:24<2:35:41,  1.38it/s]
1|12956|Loss: 1.0051771402359009:  50%|█████     | 12956/25880 [2:39:24<2:27:28,  1.46it/s]
1|12957|Loss: 0.7959198355674744:  50%|█████     | 12956/25880 [2:39:24<2:27:28,  1.46it/s]
1|12957|Loss: 0.7959198355674744:  50%|█████     | 12957/25880 [2:39:25<2:27:43,  1.46it/s]
1|12958|Loss: 0.9055110216140747:  50%|█████     | 12957/25880 [2:39:25<2:27:43,  1.46it/s]
1|12958|Loss: 0.9055110216140747:  50%|█████     | 12958/25880 [2:39:25<2:24:06,  1.49it/s]
1|12959|Loss: 0.8969911336898804:  50%|█████     | 12958/25880 [2:39:26<2:24:06,  1.49it/s]
1|12959|Loss: 0.8969911336898804:  50%|█████     | 12959/25880 [2:39:26<2:26:56,  1.47it/s]
1|12960|Loss: 0.7374873161315918:  50%|█████     | 12959/25880 [2:39:26<2:26:56,  1.47it/s]
1|12960|Loss: 0.7374873161315918:  50%|█████     | 12960/25880 [2:39:27<2:33:44,  1.40it/s]
1|12961|Loss: 0.8775349855422974:  50%|█████     | 12960/25880 [2:39:27<2:33:44,  1.40it/s]
1|12961|Loss: 0.8775349855422974:  50%|█████     | 12961/25880 [2:39:27<2:26:48,  1.47it/s]
1|12962|Loss: 0.7448793053627014:  50%|█████     | 12961/25880 [2:39:28<2:26:48,  1.47it/s]
1|12962|Loss: 0.7448793053627014:  50%|█████     | 12962/25880 [2:39:28<2:34:44,  1.39it/s]
1|12963|Loss: 0.9380475878715515:  50%|█████     | 12962/25880 [2:39:29<2:34:44,  1.39it/s]
1|12963|Loss: 0.9380475878715515:  50%|█████     | 12963/25880 [2:39:29<2:43:35,  1.32it/s]
1|12964|Loss: 0.904260516166687:  50%|█████     | 12963/25880 [2:39:29<2:43:35,  1.32it/s] 
1|12964|Loss: 0.904260516166687:  50%|█████     | 12964/25880 [2:39:30<2:38:57,  1.35it/s]
1|12965|Loss: 0.8968983888626099:  50%|█████     | 12964/25880 [2:39:30<2:38:57,  1.35it/s]
1|12965|Loss: 0.8968983888626099:  50%|█████     | 12965/25880 [2:39:30<2:42:31,  1.32it/s]
1|12966|Loss: 0.6963445544242859:  50%|█████     | 12965/25880 [2:39:31<2:42:31,  1.32it/s]
1|12966|Loss: 0.6963445544242859:  50%|█████     | 12966/25880 [2:39:31<2:45:11,  1.30it/s]
1|12967|Loss: 0.800457775592804:  50%|█████     | 12966/25880 [2:39:32<2:45:11,  1.30it/s] 
1|12967|Loss: 0.800457775592804:  50%|█████     | 12967/25880 [2:39:32<2:42:06,  1.33it/s]
1|12968|Loss: 0.7986370325088501:  50%|█████     | 12967/25880 [2:39:32<2:42:06,  1.33it/s]
1|12968|Loss: 0.7986370325088501:  50%|█████     | 12968/25880 [2:39:33<2:41:34,  1.33it/s]
1|12969|Loss: 0.9364342093467712:  50%|█████     | 12968/25880 [2:39:33<2:41:34,  1.33it/s]
1|12969|Loss: 0.9364342093467712:  50%|█████     | 12969/25880 [2:39:33<2:36:11,  1.38it/s]
1|12970|Loss: 0.7662187814712524:  50%|█████     | 12969/25880 [2:39:34<2:36:11,  1.38it/s]
1|12970|Loss: 0.7662187814712524:  50%|█████     | 12970/25880 [2:39:34<2:35:37,  1.38it/s]
1|12971|Loss: 0.9484297037124634:  50%|█████     | 12970/25880 [2:39:35<2:35:37,  1.38it/s]
1|12971|Loss: 0.9484297037124634:  50%|█████     | 12971/25880 [2:39:35<2:31:53,  1.42it/s]
1|12972|Loss: 0.8787667155265808:  50%|█████     | 12971/25880 [2:39:35<2:31:53,  1.42it/s]
1|12972|Loss: 0.8787667155265808:  50%|█████     | 12972/25880 [2:39:36<2:35:47,  1.38it/s]
1|12973|Loss: 1.2743923664093018:  50%|█████     | 12972/25880 [2:39:36<2:35:47,  1.38it/s]
1|12973|Loss: 1.2743923664093018:  50%|█████     | 12973/25880 [2:39:36<2:43:07,  1.32it/s]
1|12974|Loss: 0.8454307317733765:  50%|█████     | 12973/25880 [2:39:37<2:43:07,  1.32it/s]
1|12974|Loss: 0.8454307317733765:  50%|█████     | 12974/25880 [2:39:37<2:47:06,  1.29it/s]
1|12975|Loss: 0.8929557800292969:  50%|█████     | 12974/25880 [2:39:38<2:47:06,  1.29it/s]
1|12975|Loss: 0.8929557800292969:  50%|█████     | 12975/25880 [2:39:38<2:52:01,  1.25it/s]
1|12976|Loss: 0.907017171382904:  50%|█████     | 12975/25880 [2:39:39<2:52:01,  1.25it/s] 
1|12976|Loss: 0.907017171382904:  50%|█████     | 12976/25880 [2:39:39<2:54:41,  1.23it/s]
1|12977|Loss: 0.8191473484039307:  50%|█████     | 12976/25880 [2:39:39<2:54:41,  1.23it/s]
1|12977|Loss: 0.8191473484039307:  50%|█████     | 12977/25880 [2:39:40<2:49:38,  1.27it/s]
1|12978|Loss: 0.8618103861808777:  50%|█████     | 12977/25880 [2:39:40<2:49:38,  1.27it/s]
1|12978|Loss: 0.8618103861808777:  50%|█████     | 12978/25880 [2:39:40<2:44:11,  1.31it/s]
1|12979|Loss: 0.7425894737243652:  50%|█████     | 12978/25880 [2:39:41<2:44:11,  1.31it/s]
1|12979|Loss: 0.7425894737243652:  50%|█████     | 12979/25880 [2:39:41<2:39:55,  1.34it/s]
1|12980|Loss: 0.887036144733429:  50%|█████     | 12979/25880 [2:39:41<2:39:55,  1.34it/s] 
1|12980|Loss: 0.887036144733429:  50%|█████     | 12980/25880 [2:39:42<2:38:21,  1.36it/s]
1|12981|Loss: 0.8952330946922302:  50%|█████     | 12980/25880 [2:39:42<2:38:21,  1.36it/s]
1|12981|Loss: 0.8952330946922302:  50%|█████     | 12981/25880 [2:39:43<2:42:32,  1.32it/s]
1|12982|Loss: 0.8772446513175964:  50%|█████     | 12981/25880 [2:39:43<2:42:32,  1.32it/s]
1|12982|Loss: 0.8772446513175964:  50%|█████     | 12982/25880 [2:39:43<2:46:37,  1.29it/s]
1|12983|Loss: 0.8264196515083313:  50%|█████     | 12982/25880 [2:39:44<2:46:37,  1.29it/s]
1|12983|Loss: 0.8264196515083313:  50%|█████     | 12983/25880 [2:39:44<2:37:28,  1.37it/s]
1|12984|Loss: 0.8170561194419861:  50%|█████     | 12983/25880 [2:39:44<2:37:28,  1.37it/s]
1|12984|Loss: 0.8170561194419861:  50%|█████     | 12984/25880 [2:39:45<2:35:02,  1.39it/s]
1|12985|Loss: 0.9140070676803589:  50%|█████     | 12984/25880 [2:39:45<2:35:02,  1.39it/s]
1|12985|Loss: 0.9140070676803589:  50%|█████     | 12985/25880 [2:39:46<2:40:31,  1.34it/s]
1|12986|Loss: 0.8596344590187073:  50%|█████     | 12985/25880 [2:39:46<2:40:31,  1.34it/s]
1|12986|Loss: 0.8596344590187073:  50%|█████     | 12986/25880 [2:39:46<2:33:19,  1.40it/s]
1|12987|Loss: 0.8112159967422485:  50%|█████     | 12986/25880 [2:39:47<2:33:19,  1.40it/s]
1|12987|Loss: 0.8112159967422485:  50%|█████     | 12987/25880 [2:39:47<2:31:39,  1.42it/s]
1|12988|Loss: 0.8513747453689575:  50%|█████     | 12987/25880 [2:39:47<2:31:39,  1.42it/s]
1|12988|Loss: 0.8513747453689575:  50%|████���     | 12988/25880 [2:39:47<2:23:41,  1.50it/s]
1|12989|Loss: 0.8793208003044128:  50%|█████     | 12988/25880 [2:39:48<2:23:41,  1.50it/s]
1|12989|Loss: 0.8793208003044128:  50%|█████     | 12989/25880 [2:39:48<2:38:59,  1.35it/s]
1|12990|Loss: 0.9348739981651306:  50%|█████     | 12989/25880 [2:39:49<2:38:59,  1.35it/s]
1|12990|Loss: 0.9348739981651306:  50%|█████     | 12990/25880 [2:39:49<2:47:40,  1.28it/s]
1|12991|Loss: 0.8700929284095764:  50%|█████     | 12990/25880 [2:39:50<2:47:40,  1.28it/s]
1|12991|Loss: 0.8700929284095764:  50%|█████     | 12991/25880 [2:39:50<2:45:40,  1.30it/s]
1|12992|Loss: 0.873508632183075:  50%|█████     | 12991/25880 [2:39:50<2:45:40,  1.30it/s] 
1|12992|Loss: 0.873508632183075:  50%|█████     | 12992/25880 [2:39:51<2:43:40,  1.31it/s]
1|12993|Loss: 0.8267855644226074:  50%|█████     | 12992/25880 [2:39:51<2:43:40,  1.31it/s]
1|12993|Loss: 0.8267855644226074:  50%|█████     | 12993/25880 [2:39:51<2:41:57,  1.33it/s]
1|12994|Loss: 0.8475383520126343:  50%|█████     | 12993/25880 [2:39:52<2:41:57,  1.33it/s]
1|12994|Loss: 0.8475383520126343:  50%|█████     | 12994/25880 [2:39:52<2:34:17,  1.39it/s]
1|12995|Loss: 0.7430331707000732:  50%|█████     | 12994/25880 [2:39:52<2:34:17,  1.39it/s]
1|12995|Loss: 0.7430331707000732:  50%|█████     | 12995/25880 [2:39:53<2:36:16,  1.37it/s]
1|12996|Loss: 0.9825817942619324:  50%|█████     | 12995/25880 [2:39:53<2:36:16,  1.37it/s]
1|12996|Loss: 0.9825817942619324:  50%|█████     | 12996/25880 [2:39:53<2:31:30,  1.42it/s]
1|12997|Loss: 0.7076390385627747:  50%|█████     | 12996/25880 [2:39:54<2:31:30,  1.42it/s]
1|12997|Loss: 0.7076390385627747:  50%|█████     | 12997/25880 [2:39:54<2:23:49,  1.49it/s]
1|12998|Loss: 0.8191894888877869:  50%|█████     | 12997/25880 [2:39:54<2:23:49,  1.49it/s]
1|12998|Loss: 0.8191894888877869:  50%|█████     | 12998/25880 [2:39:55<2:17:52,  1.56it/s]
1|12999|Loss: 0.8508133292198181:  50%|█████     | 12998/25880 [2:39:55<2:17:52,  1.56it/s]
1|12999|Loss: 0.8508133292198181:  50%|█████     | 12999/25880 [2:39:55<2:22:34,  1.51it/s]
1|13000|Loss: 0.8065527081489563:  50%|█████     | 12999/25880 [2:39:56<2:22:34,  1.51it/s]Model checkpoint of size 25961 MB saved to output/alpaca-colorful-llama2-finetune/model_0_13000.ckpt
+Skipping uploading to HuggingFace Hub (no repo id specified)
+
1|13000|Loss: 0.8065527081489563:  50%|█████     | 13000/25880 [2:40:39<48:44:06, 13.62s/it]
1|13001|Loss: 0.9879862070083618:  50%|█████     | 13000/25880 [2:40:39<48:44:06, 13.62s/it]
1|13001|Loss: 0.9879862070083618:  50%|█████     | 13001/25880 [2:40:40<34:42:23,  9.70s/it]
1|13002|Loss: 0.8476510047912598:  50%|█████     | 13001/25880 [2:40:40<34:42:23,  9.70s/it]
1|13002|Loss: 0.8476510047912598:  50%|█████     | 13002/25880 [2:40:40<25:03:51,  7.01s/it]
1|13003|Loss: 0.7983641624450684:  50%|█████     | 13002/25880 [2:40:41<25:03:51,  7.01s/it]
1|13003|Loss: 0.7983641624450684:  50%|█████     | 13003/25880 [2:40:41<18:23:39,  5.14s/it]
1|13004|Loss: 0.7760686278343201:  50%|█████     | 13003/25880 [2:40:42<18:23:39,  5.14s/it]
1|13004|Loss: 0.7760686278343201:  50%|█████     | 13004/25880 [2:40:42<13:45:12,  3.85s/it]
1|13005|Loss: 0.9133033752441406:  50%|█████     | 13004/25880 [2:40:43<13:45:12,  3.85s/it]
1|13005|Loss: 0.9133033752441406:  50%|█████     | 13005/25880 [2:40:43<10:37:02,  2.97s/it]
1|13006|Loss: 0.9687508344650269:  50%|█████     | 13005/25880 [2:40:44<10:37:02,  2.97s/it]
1|13006|Loss: 0.9687508344650269:  50%|█████     | 13006/25880 [2:40:44<8:24:57,  2.35s/it] 
1|13007|Loss: 0.7683139443397522:  50%|█████     | 13006/25880 [2:40:44<8:24:57,  2.35s/it]
1|13007|Loss: 0.7683139443397522:  50%|█████     | 13007/25880 [2:40:45<6:37:36,  1.85s/it]
1|13008|Loss: 0.8272310495376587:  50%|█████     | 13007/25880 [2:40:45<6:37:36,  1.85s/it]
1|13008|Loss: 0.8272310495376587:  50%|█████     | 13008/25880 [2:40:45<5:11:24,  1.45s/it]
1|13009|Loss: 0.6836842894554138:  50%|█████     | 13008/25880 [2:40:45<5:11:24,  1.45s/it]
1|13009|Loss: 0.6836842894554138:  50%|█████     | 13009/25880 [2:40:46<4:14:13,  1.19s/it]
1|13010|Loss: 0.9133884310722351:  50%|█████     | 13009/25880 [2:40:46<4:14:13,  1.19s/it]
1|13010|Loss: 0.9133884310722351:  50%|█████     | 13010/25880 [2:40:46<3:37:08,  1.01s/it]
1|13011|Loss: 0.8559466004371643:  50%|█████     | 13010/25880 [2:40:47<3:37:08,  1.01s/it]
1|13011|Loss: 0.8559466004371643:  50%|█████     | 13011/25880 [2:40:47<3:22:03,  1.06it/s]
1|13012|Loss: 0.9541007280349731:  50%|█████     | 13011/25880 [2:40:47<3:22:03,  1.06it/s]
1|13012|Loss: 0.9541007280349731:  50%|█████     | 13012/25880 [2:40:48<3:00:03,  1.19it/s]
1|13013|Loss: 0.9717035293579102:  50%|█████     | 13012/25880 [2:40:48<3:00:03,  1.19it/s]
1|13013|Loss: 0.9717035293579102:  50%|█████     | 13013/25880 [2:40:48<2:55:06,  1.22it/s]
1|13014|Loss: 0.9067359566688538:  50%|█████     | 13013/25880 [2:40:49<2:55:06,  1.22it/s]
1|13014|Loss: 0.9067359566688538:  50%|█████     | 13014/25880 [2:40:49<2:48:26,  1.27it/s]
1|13015|Loss: 0.9230390191078186:  50%|█████     | 13014/25880 [2:40:50<2:48:26,  1.27it/s]
1|13015|Loss: 0.9230390191078186:  50%|█████     | 13015/25880 [2:40:50<2:44:13,  1.31it/s]
1|13016|Loss: 0.8491206765174866:  50%|█████     | 13015/25880 [2:40:50<2:44:13,  1.31it/s]
1|13016|Loss: 0.8491206765174866:  50%|█████     | 13016/25880 [2:40:51<2:41:28,  1.33it/s]
1|13017|Loss: 0.9104891419410706:  50%|█████     | 13016/25880 [2:40:51<2:41:28,  1.33it/s]
1|13017|Loss: 0.9104891419410706:  50%|█████     | 13017/25880 [2:40:51<2:27:50,  1.45it/s]
1|13018|Loss: 0.770788848400116:  50%|█████     | 13017/25880 [2:40:51<2:27:50,  1.45it/s] 
1|13018|Loss: 0.770788848400116:  50%|█████     | 13018/25880 [2:40:52<2:20:58,  1.52it/s]
1|13019|Loss: 0.9024507999420166:  50%|█████     | 13018/25880 [2:40:52<2:20:58,  1.52it/s]
1|13019|Loss: 0.9024507999420166:  50%|█████     | 13019/25880 [2:40:52<2:15:45,  1.58it/s]
1|13020|Loss: 0.9171387553215027:  50%|█████     | 13019/25880 [2:40:53<2:15:45,  1.58it/s]
1|13020|Loss: 0.9171387553215027:  50%|█████     | 13020/25880 [2:40:53<2:26:38,  1.46it/s]
1|13021|Loss: 0.8789604902267456:  50%|█████     | 13020/25880 [2:40:53<2:26:38,  1.46it/s]
1|13021|Loss: 0.8789604902267456:  50%|█████     | 13021/25880 [2:40:54<2:21:01,  1.52it/s]
1|13022|Loss: 0.8875847458839417:  50%|█████     | 13021/25880 [2:40:54<2:21:01,  1.52it/s]
1|13022|Loss: 0.8875847458839417:  50%|█████     | 13022/25880 [2:40:54<2:23:22,  1.49it/s]
1|13023|Loss: 0.9552322030067444:  50%|█████     | 13022/25880 [2:40:55<2:23:22,  1.49it/s]
1|13023|Loss: 0.9552322030067444:  50%|█████     | 13023/25880 [2:40:55<2:22:06,  1.51it/s]
1|13024|Loss: 0.8026067614555359:  50%|█████     | 13023/25880 [2:40:55<2:22:06,  1.51it/s]
1|13024|Loss: 0.8026067614555359:  50%|█████     | 13024/25880 [2:40:56<2:30:38,  1.42it/s]
1|13025|Loss: 0.830477237701416:  50%|█████     | 13024/25880 [2:40:56<2:30:38,  1.42it/s] 
1|13025|Loss: 0.830477237701416:  50%|█████     | 13025/25880 [2:40:57<2:43:07,  1.31it/s]
1|13026|Loss: 0.9157583117485046:  50%|█████     | 13025/25880 [2:40:57<2:43:07,  1.31it/s]
1|13026|Loss: 0.9157583117485046:  50%|█████     | 13026/25880 [2:40:58<2:49:40,  1.26it/s]
1|13027|Loss: 0.9043796062469482:  50%|█████     | 13026/25880 [2:40:58<2:49:40,  1.26it/s]
1|13027|Loss: 0.9043796062469482:  50%|█████     | 13027/25880 [2:40:58<2:47:11,  1.28it/s]
1|13028|Loss: 0.9433664679527283:  50%|█████     | 13027/25880 [2:40:59<2:47:11,  1.28it/s]
1|13028|Loss: 0.9433664679527283:  50%|█████     | 13028/25880 [2:40:59<2:43:44,  1.31it/s]
1|13029|Loss: 0.8777173161506653:  50%|█████     | 13028/25880 [2:40:59<2:43:44,  1.31it/s]
1|13029|Loss: 0.8777173161506653:  50%|█████     | 13029/25880 [2:41:00<2:41:07,  1.33it/s]
1|13030|Loss: 0.9198251366615295:  50%|█████     | 13029/25880 [2:41:00<2:41:07,  1.33it/s]
1|13030|Loss: 0.9198251366615295:  50%|█████     | 13030/25880 [2:41:01<2:39:40,  1.34it/s]
1|13031|Loss: 0.9780693650245667:  50%|█████     | 13030/25880 [2:41:01<2:39:40,  1.34it/s]
1|13031|Loss: 0.9780693650245667:  50%|█████     | 13031/25880 [2:41:01<2:38:42,  1.35it/s]
1|13032|Loss: 0.7879341244697571:  50%|█████     | 13031/25880 [2:41:02<2:38:42,  1.35it/s]
1|13032|Loss: 0.7879341244697571:  50%|█████     | 13032/25880 [2:41:02<2:36:12,  1.37it/s]
1|13033|Loss: 0.7748649716377258:  50%|█████     | 13032/25880 [2:41:02<2:36:12,  1.37it/s]
1|13033|Loss: 0.7748649716377258:  50%|█████     | 13033/25880 [2:41:03<2:35:42,  1.38it/s]
1|13034|Loss: 0.8483260869979858:  50%|█████     | 13033/25880 [2:41:03<2:35:42,  1.38it/s]
1|13034|Loss: 0.8483260869979858:  50%|█████     | 13034/25880 [2:41:03<2:36:43,  1.37it/s]
1|13035|Loss: 0.649998664855957:  50%|█████     | 13034/25880 [2:41:04<2:36:43,  1.37it/s] 
1|13035|Loss: 0.649998664855957:  50%|█████     | 13035/25880 [2:41:04<2:40:11,  1.34it/s]
1|13036|Loss: 0.8531448841094971:  50%|█████     | 13035/25880 [2:41:05<2:40:11,  1.34it/s]
1|13036|Loss: 0.8531448841094971:  50%|█████     | 13036/25880 [2:41:05<2:39:09,  1.34it/s]
1|13037|Loss: 0.7555831074714661:  50%|█████     | 13036/25880 [2:41:05<2:39:09,  1.34it/s]
1|13037|Loss: 0.7555831074714661:  50%|█████     | 13037/25880 [2:41:06<2:42:46,  1.32it/s]
1|13038|Loss: 0.8262208700180054:  50%|█████     | 13037/25880 [2:41:06<2:42:46,  1.32it/s]
1|13038|Loss: 0.8262208700180054:  50%|█████     | 13038/25880 [2:41:07<2:41:47,  1.32it/s]
1|13039|Loss: 0.8378345966339111:  50%|█████     | 13038/25880 [2:41:07<2:41:47,  1.32it/s]
1|13039|Loss: 0.8378345966339111:  50%|█████     | 13039/25880 [2:41:07<2:45:12,  1.30it/s]
1|13040|Loss: 0.5853205919265747:  50%|█████     | 13039/25880 [2:41:08<2:45:12,  1.30it/s]
1|13040|Loss: 0.5853205919265747:  50%|█████     | 13040/25880 [2:41:08<2:55:09,  1.22it/s]
1|13041|Loss: 0.816409170627594:  50%|█████     | 13040/25880 [2:41:09<2:55:09,  1.22it/s] 
1|13041|Loss: 0.816409170627594:  50%|█████     | 13041/25880 [2:41:09<2:44:31,  1.30it/s]
1|13042|Loss: 0.8128906488418579:  50%|█████     | 13041/25880 [2:41:09<2:44:31,  1.30it/s]
1|13042|Loss: 0.8128906488418579:  50%|█████     | 13042/25880 [2:41:10<2:44:51,  1.30it/s]
1|13043|Loss: 1.0294898748397827:  50%|█████     | 13042/25880 [2:41:10<2:44:51,  1.30it/s]
1|13043|Loss: 1.0294898748397827:  50%|█████     | 13043/25880 [2:41:10<2:35:25,  1.38it/s]
1|13044|Loss: 0.7323876023292542:  50%|█████     | 13043/25880 [2:41:11<2:35:25,  1.38it/s]
1|13044|Loss: 0.7323876023292542:  50%|█████     | 13044/25880 [2:41:11<2:28:38,  1.44it/s]
1|13045|Loss: 0.8585322499275208:  50%|█████     | 13044/25880 [2:41:11<2:28:38,  1.44it/s]
1|13045|Loss: 0.8585322499275208:  50%|█████     | 13045/25880 [2:41:12<2:35:36,  1.37it/s]
1|13046|Loss: 0.7716253399848938:  50%|█████     | 13045/25880 [2:41:12<2:35:36,  1.37it/s]
1|13046|Loss: 0.7716253399848938:  50%|█████     | 13046/25880 [2:41:12<2:31:26,  1.41it/s]
1|13047|Loss: 0.8866063356399536:  50%|█████     | 13046/25880 [2:41:13<2:31:26,  1.41it/s]
1|13047|Loss: 0.8866063356399536:  50%|█████     | 13047/25880 [2:41:13<2:34:56,  1.38it/s]
1|13048|Loss: 0.9055075645446777:  50%|█████     | 13047/25880 [2:41:14<2:34:56,  1.38it/s]
1|13048|Loss: 0.9055075645446777:  50%|█████     | 13048/25880 [2:41:14<2:39:46,  1.34it/s]
1|13049|Loss: 0.7921451330184937:  50%|█████     | 13048/25880 [2:41:14<2:39:46,  1.34it/s]
1|13049|Loss: 0.7921451330184937:  50%|█████     | 13049/25880 [2:41:15<2:49:05,  1.26it/s]
1|13050|Loss: 0.79399573802948:  50%|█████     | 13049/25880 [2:41:15<2:49:05,  1.26it/s]  
1|13050|Loss: 0.79399573802948:  50%|█████     | 13050/25880 [2:41:15<2:39:49,  1.34it/s]
1|13051|Loss: 0.9253824949264526:  50%|█████     | 13050/25880 [2:41:16<2:39:49,  1.34it/s]
1|13051|Loss: 0.9253824949264526:  50%|█████     | 13051/25880 [2:41:16<2:36:40,  1.36it/s]
1|13052|Loss: 0.8145651817321777:  50%|█████     | 13051/25880 [2:41:17<2:36:40,  1.36it/s]
1|13052|Loss: 0.8145651817321777:  50%|█████     | 13052/25880 [2:41:17<2:34:57,  1.38it/s]
1|13053|Loss: 0.7689085602760315:  50%|█████     | 13052/25880 [2:41:17<2:34:57,  1.38it/s]
1|13053|Loss: 0.7689085602760315:  50%|█████     | 13053/25880 [2:41:18<2:39:14,  1.34it/s]
1|13054|Loss: 0.8353838324546814:  50%|█████     | 13053/25880 [2:41:18<2:39:14,  1.34it/s]
1|13054|Loss: 0.8353838324546814:  50%|█████     | 13054/25880 [2:41:18<2:41:56,  1.32it/s]
1|13055|Loss: 0.8467881083488464:  50%|█████     | 13054/25880 [2:41:19<2:41:56,  1.32it/s]
1|13055|Loss: 0.8467881083488464:  50%|█████     | 13055/25880 [2:41:19<2:48:47,  1.27it/s]
1|13056|Loss: 0.8764752149581909:  50%|█████     | 13055/25880 [2:41:20<2:48:47,  1.27it/s]
1|13056|Loss: 0.8764752149581909:  50%|█████     | 13056/25880 [2:41:20<2:38:32,  1.35it/s]
1|13057|Loss: 0.9353500008583069:  50%|█████     | 13056/25880 [2:41:20<2:38:32,  1.35it/s]
1|13057|Loss: 0.9353500008583069:  50%|█████     | 13057/25880 [2:41:21<2:36:14,  1.37it/s]
1|13058|Loss: 0.9111497402191162:  50%|█████     | 13057/25880 [2:41:21<2:36:14,  1.37it/s]
1|13058|Loss: 0.9111497402191162:  50%|█████     | 13058/25880 [2:41:21<2:37:02,  1.36it/s]
1|13059|Loss: 0.8725504279136658:  50%|█████     | 13058/25880 [2:41:22<2:37:02,  1.36it/s]
1|13059|Loss: 0.8725504279136658:  50%|█████     | 13059/25880 [2:41:22<2:42:31,  1.31it/s]
1|13060|Loss: 0.7014644145965576:  50%|█████     | 13059/25880 [2:41:23<2:42:31,  1.31it/s]
1|13060|Loss: 0.7014644145965576:  50%|█████     | 13060/25880 [2:41:23<2:36:30,  1.37it/s]
1|13061|Loss: 0.8097920417785645:  50%|█████     | 13060/25880 [2:41:23<2:36:30,  1.37it/s]
1|13061|Loss: 0.8097920417785645:  50%|█████     | 13061/25880 [2:41:24<2:34:41,  1.38it/s]
1|13062|Loss: 0.783812403678894:  50%|█████     | 13061/25880 [2:41:24<2:34:41,  1.38it/s] 
1|13062|Loss: 0.783812403678894:  50%|█████     | 13062/25880 [2:41:24<2:37:33,  1.36it/s]
1|13063|Loss: 0.7969821095466614:  50%|█████     | 13062/25880 [2:41:25<2:37:33,  1.36it/s]
1|13063|Loss: 0.7969821095466614:  50%|█████     | 13063/25880 [2:41:25<2:31:48,  1.41it/s]
1|13064|Loss: 0.9676954746246338:  50%|█████     | 13063/25880 [2:41:25<2:31:48,  1.41it/s]
1|13064|Loss: 0.9676954746246338:  50%|█████     | 13064/25880 [2:41:26<2:22:27,  1.50it/s]
1|13065|Loss: 0.986487090587616:  50%|█████     | 13064/25880 [2:41:26<2:22:27,  1.50it/s] 
1|13065|Loss: 0.986487090587616:  50%|█████     | 13065/25880 [2:41:26<2:27:13,  1.45it/s]
1|13066|Loss: 0.8237674832344055:  50%|█████     | 13065/25880 [2:41:27<2:27:13,  1.45it/s]
1|13066|Loss: 0.8237674832344055:  50%|█████     | 13066/25880 [2:41:27<2:30:28,  1.42it/s]
1|13067|Loss: 0.844228982925415:  50%|█████     | 13066/25880 [2:41:27<2:30:28,  1.42it/s] 
1|13067|Loss: 0.844228982925415:  50%|█████     | 13067/25880 [2:41:28<2:25:51,  1.46it/s]
1|13068|Loss: 0.7824001312255859:  50%|█████     | 13067/25880 [2:41:28<2:25:51,  1.46it/s]
1|13068|Loss: 0.7824001312255859:  50%|█████     | 13068/25880 [2:41:28<2:30:59,  1.41it/s]
1|13069|Loss: 0.7630029320716858:  50%|█████     | 13068/25880 [2:41:29<2:30:59,  1.41it/s]
1|13069|Loss: 0.7630029320716858:  50%|█████     | 13069/25880 [2:41:29<2:44:52,  1.30it/s]
1|13070|Loss: 0.9241987466812134:  50%|█████     | 13069/25880 [2:41:30<2:44:52,  1.30it/s]
1|13070|Loss: 0.9241987466812134:  51%|█████     | 13070/25880 [2:41:30<2:43:35,  1.31it/s]
1|13071|Loss: 0.9403725862503052:  51%|█████     | 13070/25880 [2:41:31<2:43:35,  1.31it/s]
1|13071|Loss: 0.9403725862503052:  51%|█████     | 13071/25880 [2:41:31<2:39:30,  1.34it/s]
1|13072|Loss: 0.8260930180549622:  51%|█████     | 13071/25880 [2:41:31<2:39:30,  1.34it/s]
1|13072|Loss: 0.8260930180549622:  51%|█████     | 13072/25880 [2:41:32<2:37:49,  1.35it/s]
1|13073|Loss: 0.8727990388870239:  51%|█████     | 13072/25880 [2:41:32<2:37:49,  1.35it/s]
1|13073|Loss: 0.8727990388870239:  51%|█████     | 13073/25880 [2:41:32<2:39:46,  1.34it/s]
1|13074|Loss: 0.7569049000740051:  51%|█████     | 13073/25880 [2:41:33<2:39:46,  1.34it/s]
1|13074|Loss: 0.7569049000740051:  51%|█████     | 13074/25880 [2:41:33<2:46:09,  1.28it/s]
1|13075|Loss: 0.5567986965179443:  51%|█████     | 13074/25880 [2:41:34<2:46:09,  1.28it/s]
1|13075|Loss: 0.5567986965179443:  51%|█████     | 13075/25880 [2:41:34<2:48:12,  1.27it/s]
1|13076|Loss: 0.9573218822479248:  51%|█████     | 13075/25880 [2:41:34<2:48:12,  1.27it/s]
1|13076|Loss: 0.9573218822479248:  51%|█████     | 13076/25880 [2:41:35<2:37:56,  1.35it/s]
1|13077|Loss: 0.8129818439483643:  51%|█████     | 13076/25880 [2:41:35<2:37:56,  1.35it/s]
1|13077|Loss: 0.8129818439483643:  51%|█████     | 13077/25880 [2:41:35<2:30:30,  1.42it/s]
1|13078|Loss: 0.8952439427375793:  51%|█████     | 13077/25880 [2:41:36<2:30:30,  1.42it/s]
1|13078|Loss: 0.8952439427375793:  51%|█████     | 13078/25880 [2:41:36<2:36:59,  1.36it/s]
1|13079|Loss: 0.7822810411453247:  51%|█████     | 13078/25880 [2:41:37<2:36:59,  1.36it/s]
1|13079|Loss: 0.7822810411453247:  51%|█████     | 13079/25880 [2:41:37<2:51:21,  1.25it/s]
1|13080|Loss: 0.8638285994529724:  51%|█████     | 13079/25880 [2:41:37<2:51:21,  1.25it/s]
1|13080|Loss: 0.8638285994529724:  51%|█████     | 13080/25880 [2:41:38<2:51:35,  1.24it/s]
1|13081|Loss: 0.8766153454780579:  51%|█████     | 13080/25880 [2:41:38<2:51:35,  1.24it/s]
1|13081|Loss: 0.8766153454780579:  51%|█████     | 13081/25880 [2:41:39<2:45:52,  1.29it/s]
1|13082|Loss: 0.9908834099769592:  51%|█████     | 13081/25880 [2:41:39<2:45:52,  1.29it/s]
1|13082|Loss: 0.9908834099769592:  51%|█████     | 13082/25880 [2:41:39<2:45:03,  1.29it/s]
1|13083|Loss: 0.6835334897041321:  51%|█████     | 13082/25880 [2:41:40<2:45:03,  1.29it/s]
1|13083|Loss: 0.6835334897041321:  51%|█████     | 13083/25880 [2:41:40<2:56:57,  1.21it/s]
1|13084|Loss: 0.8717201352119446:  51%|█████     | 13083/25880 [2:41:41<2:56:57,  1.21it/s]
1|13084|Loss: 0.8717201352119446:  51%|█████     | 13084/25880 [2:41:41<2:57:45,  1.20it/s]
1|13085|Loss: 0.7583292722702026:  51%|█████     | 13084/25880 [2:41:41<2:57:45,  1.20it/s]
1|13085|Loss: 0.7583292722702026:  51%|█████     | 13085/25880 [2:41:42<2:37:31,  1.35it/s]
1|13086|Loss: 0.9201415181159973:  51%|█████     | 13085/25880 [2:41:42<2:37:31,  1.35it/s]
1|13086|Loss: 0.9201415181159973:  51%|█████     | 13086/25880 [2:41:42<2:33:05,  1.39it/s]
1|13087|Loss: 0.908273458480835:  51%|█████     | 13086/25880 [2:41:43<2:33:05,  1.39it/s] 
1|13087|Loss: 0.908273458480835:  51%|█████     | 13087/25880 [2:41:43<2:41:51,  1.32it/s]
1|13088|Loss: 0.8752869367599487:  51%|█████     | 13087/25880 [2:41:44<2:41:51,  1.32it/s]
1|13088|Loss: 0.8752869367599487:  51%|█████     | 13088/25880 [2:41:44<2:36:46,  1.36it/s]
1|13089|Loss: 0.8399390578269958:  51%|█████     | 13088/25880 [2:41:44<2:36:46,  1.36it/s]
1|13089|Loss: 0.8399390578269958:  51%|█████     | 13089/25880 [2:41:45<2:33:52,  1.39it/s]
1|13090|Loss: 0.9289723038673401:  51%|█████     | 13089/25880 [2:41:45<2:33:52,  1.39it/s]
1|13090|Loss: 0.9289723038673401:  51%|█████     | 13090/25880 [2:41:45<2:22:40,  1.49it/s]
1|13091|Loss: 0.7315869331359863:  51%|█████     | 13090/25880 [2:41:45<2:22:40,  1.49it/s]
1|13091|Loss: 0.7315869331359863:  51%|█████     | 13091/25880 [2:41:46<2:16:51,  1.56it/s]
1|13092|Loss: 0.7744408249855042:  51%|█████     | 13091/25880 [2:41:46<2:16:51,  1.56it/s]
1|13092|Loss: 0.7744408249855042:  51%|█████     | 13092/25880 [2:41:46<2:21:22,  1.51it/s]
1|13093|Loss: 0.8625562787055969:  51%|█████     | 13092/25880 [2:41:47<2:21:22,  1.51it/s]
1|13093|Loss: 0.8625562787055969:  51%|█████     | 13093/25880 [2:41:47<2:28:56,  1.43it/s]
1|13094|Loss: 0.7936898469924927:  51%|█████     | 13093/25880 [2:41:48<2:28:56,  1.43it/s]
1|13094|Loss: 0.7936898469924927:  51%|█████     | 13094/25880 [2:41:48<2:26:07,  1.46it/s]
1|13095|Loss: 0.7656301856040955:  51%|█████     | 13094/25880 [2:41:48<2:26:07,  1.46it/s]
1|13095|Loss: 0.7656301856040955:  51%|█████     | 13095/25880 [2:41:49<2:27:35,  1.44it/s]
1|13096|Loss: 0.8433628678321838:  51%|█████     | 13095/25880 [2:41:49<2:27:35,  1.44it/s]
1|13096|Loss: 0.8433628678321838:  51%|█████     | 13096/25880 [2:41:49<2:25:38,  1.46it/s]
1|13097|Loss: 0.9174104332923889:  51%|█████     | 13096/25880 [2:41:50<2:25:38,  1.46it/s]
1|13097|Loss: 0.9174104332923889:  51%|█████     | 13097/25880 [2:41:50<2:21:44,  1.50it/s]
1|13098|Loss: 0.7141985893249512:  51%|█████     | 13097/25880 [2:41:50<2:21:44,  1.50it/s]
1|13098|Loss: 0.7141985893249512:  51%|█████     | 13098/25880 [2:41:51<2:35:40,  1.37it/s]
1|13099|Loss: 0.8840753436088562:  51%|█████     | 13098/25880 [2:41:51<2:35:40,  1.37it/s]
1|13099|Loss: 0.8840753436088562:  51%|█████     | 13099/25880 [2:41:51<2:40:53,  1.32it/s]
1|13100|Loss: 0.8534495234489441:  51%|█████     | 13099/25880 [2:41:52<2:40:53,  1.32it/s]
1|13100|Loss: 0.8534495234489441:  51%|█████     | 13100/25880 [2:41:52<2:46:16,  1.28it/s]
1|13101|Loss: 0.8766916394233704:  51%|█████     | 13100/25880 [2:41:53<2:46:16,  1.28it/s]
1|13101|Loss: 0.8766916394233704:  51%|█████     | 13101/25880 [2:41:53<2:39:50,  1.33it/s]
1|13102|Loss: 0.8081547617912292:  51%|█████     | 13101/25880 [2:41:53<2:39:50,  1.33it/s]
1|13102|Loss: 0.8081547617912292:  51%|█████     | 13102/25880 [2:41:54<2:37:53,  1.35it/s]
1|13103|Loss: 0.8370593190193176:  51%|█████     | 13102/25880 [2:41:54<2:37:53,  1.35it/s]
1|13103|Loss: 0.8370593190193176:  51%|█████     | 13103/25880 [2:41:55<2:43:27,  1.30it/s]
1|13104|Loss: 0.7632186412811279:  51%|█████     | 13103/25880 [2:41:55<2:43:27,  1.30it/s]
1|13104|Loss: 0.7632186412811279:  51%|█████     | 13104/25880 [2:41:55<2:35:12,  1.37it/s]
1|13105|Loss: 0.8848726153373718:  51%|█████     | 13104/25880 [2:41:56<2:35:12,  1.37it/s]
1|13105|Loss: 0.8848726153373718:  51%|█████     | 13105/25880 [2:41:56<2:31:45,  1.40it/s]
1|13106|Loss: 0.850012481212616:  51%|█████     | 13105/25880 [2:41:56<2:31:45,  1.40it/s] 
1|13106|Loss: 0.850012481212616:  51%|█████     | 13106/25880 [2:41:57<2:30:53,  1.41it/s]
1|13107|Loss: 0.7944721579551697:  51%|█████     | 13106/25880 [2:41:57<2:30:53,  1.41it/s]
1|13107|Loss: 0.7944721579551697:  51%|█████     | 13107/25880 [2:41:57<2:31:39,  1.40it/s]
1|13108|Loss: 0.793046236038208:  51%|█████     | 13107/25880 [2:41:58<2:31:39,  1.40it/s] 
1|13108|Loss: 0.793046236038208:  51%|█████     | 13108/25880 [2:41:58<2:33:07,  1.39it/s]
1|13109|Loss: 0.6927093267440796:  51%|█████     | 13108/25880 [2:41:58<2:33:07,  1.39it/s]
1|13109|Loss: 0.6927093267440796:  51%|█████     | 13109/25880 [2:41:59<2:29:27,  1.42it/s]
1|13110|Loss: 0.7653298377990723:  51%|█████     | 13109/25880 [2:41:59<2:29:27,  1.42it/s]
1|13110|Loss: 0.7653298377990723:  51%|█████     | 13110/25880 [2:41:59<2:35:34,  1.37it/s]
1|13111|Loss: 0.8851394057273865:  51%|█████     | 13110/25880 [2:42:00<2:35:34,  1.37it/s]
1|13111|Loss: 0.8851394057273865:  51%|█████     | 13111/25880 [2:42:00<2:25:40,  1.46it/s]
1|13112|Loss: 0.7932877540588379:  51%|█████     | 13111/25880 [2:42:00<2:25:40,  1.46it/s]
1|13112|Loss: 0.7932877540588379:  51%|█████     | 13112/25880 [2:42:01<2:28:38,  1.43it/s]
1|13113|Loss: 0.7651395201683044:  51%|█████     | 13112/25880 [2:42:01<2:28:38,  1.43it/s]
1|13113|Loss: 0.7651395201683044:  51%|█████     | 13113/25880 [2:42:02<2:43:17,  1.30it/s]
1|13114|Loss: 0.8354125618934631:  51%|█████     | 13113/25880 [2:42:02<2:43:17,  1.30it/s]
1|13114|Loss: 0.8354125618934631:  51%|█████     | 13114/25880 [2:42:02<2:42:42,  1.31it/s]
1|13115|Loss: 0.8450813889503479:  51%|█████     | 13114/25880 [2:42:03<2:42:42,  1.31it/s]
1|13115|Loss: 0.8450813889503479:  51%|█████     | 13115/25880 [2:42:03<2:38:59,  1.34it/s]
1|13116|Loss: 0.893797755241394:  51%|█████     | 13115/25880 [2:42:04<2:38:59,  1.34it/s] 
1|13116|Loss: 0.893797755241394:  51%|█████     | 13116/25880 [2:42:04<2:49:11,  1.26it/s]
1|13117|Loss: 0.7945301532745361:  51%|█████     | 13116/25880 [2:42:05<2:49:11,  1.26it/s]
1|13117|Loss: 0.7945301532745361:  51%|█████     | 13117/25880 [2:42:05<2:48:48,  1.26it/s]
1|13118|Loss: 0.8086178302764893:  51%|█████     | 13117/25880 [2:42:05<2:48:48,  1.26it/s]
1|13118|Loss: 0.8086178302764893:  51%|█████     | 13118/25880 [2:42:06<2:46:05,  1.28it/s]
1|13119|Loss: 0.6847278475761414:  51%|█████     | 13118/25880 [2:42:06<2:46:05,  1.28it/s]
1|13119|Loss: 0.6847278475761414:  51%|█████     | 13119/25880 [2:42:06<2:43:25,  1.30it/s]
1|13120|Loss: 0.6994533538818359:  51%|█████     | 13119/25880 [2:42:07<2:43:25,  1.30it/s]
1|13120|Loss: 0.6994533538818359:  51%|█████     | 13120/25880 [2:42:07<2:47:52,  1.27it/s]
1|13121|Loss: 0.7724779844284058:  51%|█████     | 13120/25880 [2:42:08<2:47:52,  1.27it/s]
1|13121|Loss: 0.7724779844284058:  51%|█████     | 13121/25880 [2:42:08<2:46:08,  1.28it/s]
1|13122|Loss: 0.8639570474624634:  51%|█████     | 13121/25880 [2:42:08<2:46:08,  1.28it/s]
1|13122|Loss: 0.8639570474624634:  51%|█████     | 13122/25880 [2:42:09<2:38:05,  1.35it/s]
1|13123|Loss: 0.8396730422973633:  51%|█████     | 13122/25880 [2:42:09<2:38:05,  1.35it/s]
1|13123|Loss: 0.8396730422973633:  51%|█████     | 13123/25880 [2:42:09<2:45:31,  1.28it/s]
1|13124|Loss: 0.9946257472038269:  51%|█████     | 13123/25880 [2:42:10<2:45:31,  1.28it/s]
1|13124|Loss: 0.9946257472038269:  51%|█████     | 13124/25880 [2:42:10<2:51:12,  1.24it/s]
1|13125|Loss: 0.8022704124450684:  51%|█████     | 13124/25880 [2:42:11<2:51:12,  1.24it/s]
1|13125|Loss: 0.8022704124450684:  51%|█████     | 13125/25880 [2:42:11<2:43:02,  1.30it/s]
1|13126|Loss: 0.739916980266571:  51%|█████     | 13125/25880 [2:42:11<2:43:02,  1.30it/s] 
1|13126|Loss: 0.739916980266571:  51%|█████     | 13126/25880 [2:42:12<2:44:09,  1.29it/s]
1|13127|Loss: 0.9272394180297852:  51%|█████     | 13126/25880 [2:42:12<2:44:09,  1.29it/s]
1|13127|Loss: 0.9272394180297852:  51%|█████     | 13127/25880 [2:42:13<2:42:39,  1.31it/s]
1|13128|Loss: 0.8359684348106384:  51%|█████     | 13127/25880 [2:42:13<2:42:39,  1.31it/s]
1|13128|Loss: 0.8359684348106384:  51%|█████     | 13128/25880 [2:42:13<2:34:47,  1.37it/s]
1|13129|Loss: 0.7534170150756836:  51%|█████     | 13128/25880 [2:42:14<2:34:47,  1.37it/s]
1|13129|Loss: 0.7534170150756836:  51%|█████     | 13129/25880 [2:42:14<2:33:46,  1.38it/s]
1|13130|Loss: 0.9980480074882507:  51%|█████     | 13129/25880 [2:42:14<2:33:46,  1.38it/s]
1|13130|Loss: 0.9980480074882507:  51%|█████     | 13130/25880 [2:42:15<2:30:07,  1.42it/s]
1|13131|Loss: 1.029788613319397:  51%|█████     | 13130/25880 [2:42:15<2:30:07,  1.42it/s] 
1|13131|Loss: 1.029788613319397:  51%|█████     | 13131/25880 [2:42:15<2:29:16,  1.42it/s]
1|13132|Loss: 0.8566182255744934:  51%|█████     | 13131/25880 [2:42:16<2:29:16,  1.42it/s]
1|13132|Loss: 0.8566182255744934:  51%|█████     | 13132/25880 [2:42:16<2:29:06,  1.42it/s]
1|13133|Loss: 0.9360632300376892:  51%|█████     | 13132/25880 [2:42:16<2:29:06,  1.42it/s]
1|13133|Loss: 0.9360632300376892:  51%|█████     | 13133/25880 [2:42:17<2:34:04,  1.38it/s]
1|13134|Loss: 0.878682553768158:  51%|█████     | 13133/25880 [2:42:17<2:34:04,  1.38it/s] 
1|13134|Loss: 0.878682553768158:  51%|█████     | 13134/25880 [2:42:18<2:35:10,  1.37it/s]
1|13135|Loss: 0.7823377847671509:  51%|█████     | 13134/25880 [2:42:18<2:35:10,  1.37it/s]
1|13135|Loss: 0.7823377847671509:  51%|█████     | 13135/25880 [2:42:18<2:23:49,  1.48it/s]
1|13136|Loss: 0.9220930337905884:  51%|█████     | 13135/25880 [2:42:18<2:23:49,  1.48it/s]
1|13136|Loss: 0.9220930337905884:  51%|█████     | 13136/25880 [2:42:19<2:24:11,  1.47it/s]
1|13137|Loss: 0.8063305020332336:  51%|█████     | 13136/25880 [2:42:19<2:24:11,  1.47it/s]
1|13137|Loss: 0.8063305020332336:  51%|█████     | 13137/25880 [2:42:20<2:35:23,  1.37it/s]
1|13138|Loss: 0.8484756350517273:  51%|█████     | 13137/25880 [2:42:20<2:35:23,  1.37it/s]
1|13138|Loss: 0.8484756350517273:  51%|█████     | 13138/25880 [2:42:20<2:38:25,  1.34it/s]
1|13139|Loss: 0.8119220733642578:  51%|█████     | 13138/25880 [2:42:21<2:38:25,  1.34it/s]
1|13139|Loss: 0.8119220733642578:  51%|█████     | 13139/25880 [2:42:21<2:38:49,  1.34it/s]
1|13140|Loss: 0.783148467540741:  51%|█████     | 13139/25880 [2:42:22<2:38:49,  1.34it/s] 
1|13140|Loss: 0.783148467540741:  51%|█████     | 13140/25880 [2:42:22<2:44:35,  1.29it/s]
1|13141|Loss: 0.9409825801849365:  51%|█████     | 13140/25880 [2:42:22<2:44:35,  1.29it/s]
1|13141|Loss: 0.9409825801849365:  51%|█████     | 13141/25880 [2:42:23<2:41:59,  1.31it/s]
1|13142|Loss: 0.8349623084068298:  51%|█████     | 13141/25880 [2:42:23<2:41:59,  1.31it/s]
1|13142|Loss: 0.8349623084068298:  51%|█████     | 13142/25880 [2:42:23<2:40:28,  1.32it/s]
1|13143|Loss: 0.7570049166679382:  51%|█████     | 13142/25880 [2:42:24<2:40:28,  1.32it/s]
1|13143|Loss: 0.7570049166679382:  51%|█████     | 13143/25880 [2:42:24<2:34:40,  1.37it/s]
1|13144|Loss: 0.8142849206924438:  51%|█████     | 13143/25880 [2:42:24<2:34:40,  1.37it/s]
1|13144|Loss: 0.8142849206924438:  51%|█████     | 13144/25880 [2:42:25<2:29:08,  1.42it/s]
1|13145|Loss: 0.8116956353187561:  51%|█████     | 13144/25880 [2:42:25<2:29:08,  1.42it/s]
1|13145|Loss: 0.8116956353187561:  51%|█████     | 13145/25880 [2:42:25<2:28:27,  1.43it/s]
1|13146|Loss: 0.9656423926353455:  51%|█████     | 13145/25880 [2:42:26<2:28:27,  1.43it/s]
1|13146|Loss: 0.9656423926353455:  51%|█████     | 13146/25880 [2:42:26<2:28:21,  1.43it/s]
1|13147|Loss: 0.7669217586517334:  51%|█████     | 13146/25880 [2:42:26<2:28:21,  1.43it/s]
1|13147|Loss: 0.7669217586517334:  51%|█████     | 13147/25880 [2:42:27<2:23:47,  1.48it/s]
1|13148|Loss: 0.9386194348335266:  51%|█████     | 13147/25880 [2:42:27<2:23:47,  1.48it/s]
1|13148|Loss: 0.9386194348335266:  51%|█████     | 13148/25880 [2:42:27<2:17:40,  1.54it/s]
1|13149|Loss: 0.7961332201957703:  51%|█████     | 13148/25880 [2:42:28<2:17:40,  1.54it/s]
1|13149|Loss: 0.7961332201957703:  51%|█████     | 13149/25880 [2:42:28<2:20:23,  1.51it/s]
1|13150|Loss: 0.8602908253669739:  51%|█████     | 13149/25880 [2:42:28<2:20:23,  1.51it/s]
1|13150|Loss: 0.8602908253669739:  51%|█████     | 13150/25880 [2:42:29<2:34:16,  1.38it/s]
1|13151|Loss: 0.8888605237007141:  51%|█████     | 13150/25880 [2:42:29<2:34:16,  1.38it/s]
1|13151|Loss: 0.8888605237007141:  51%|█████     | 13151/25880 [2:42:30<2:37:14,  1.35it/s]
1|13152|Loss: 0.7083919048309326:  51%|█████     | 13151/25880 [2:42:30<2:37:14,  1.35it/s]
1|13152|Loss: 0.7083919048309326:  51%|█████     | 13152/25880 [2:42:30<2:36:51,  1.35it/s]
1|13153|Loss: 0.874680757522583:  51%|█████     | 13152/25880 [2:42:31<2:36:51,  1.35it/s] 
1|13153|Loss: 0.874680757522583:  51%|█████     | 13153/25880 [2:42:31<2:30:20,  1.41it/s]
1|13154|Loss: 1.0020904541015625:  51%|█████     | 13153/25880 [2:42:31<2:30:20,  1.41it/s]
1|13154|Loss: 1.0020904541015625:  51%|█████     | 13154/25880 [2:42:32<2:29:01,  1.42it/s]
1|13155|Loss: 1.0162636041641235:  51%|█████     | 13154/25880 [2:42:32<2:29:01,  1.42it/s]
1|13155|Loss: 1.0162636041641235:  51%|█████     | 13155/25880 [2:42:33<2:40:19,  1.32it/s]
1|13156|Loss: 0.9452788829803467:  51%|█████     | 13155/25880 [2:42:33<2:40:19,  1.32it/s]
1|13156|Loss: 0.9452788829803467:  51%|█████     | 13156/25880 [2:42:33<2:35:16,  1.37it/s]
1|13157|Loss: 0.9863951802253723:  51%|█████     | 13156/25880 [2:42:34<2:35:16,  1.37it/s]
1|13157|Loss: 0.9863951802253723:  51%|█████     | 13157/25880 [2:42:34<2:39:58,  1.33it/s]
1|13158|Loss: 0.8612939119338989:  51%|█████     | 13157/25880 [2:42:34<2:39:58,  1.33it/s]
1|13158|Loss: 0.8612939119338989:  51%|█████     | 13158/25880 [2:42:35<2:31:31,  1.40it/s]
1|13159|Loss: 0.8033429980278015:  51%|█████     | 13158/25880 [2:42:35<2:31:31,  1.40it/s]
1|13159|Loss: 0.8033429980278015:  51%|█████     | 13159/25880 [2:42:35<2:30:45,  1.41it/s]
1|13160|Loss: 0.8415488600730896:  51%|█████     | 13159/25880 [2:42:36<2:30:45,  1.41it/s]
1|13160|Loss: 0.8415488600730896:  51%|█████     | 13160/25880 [2:42:36<2:31:07,  1.40it/s]
1|13161|Loss: 0.8462583422660828:  51%|█████     | 13160/25880 [2:42:37<2:31:07,  1.40it/s]
1|13161|Loss: 0.8462583422660828:  51%|█████     | 13161/25880 [2:42:37<2:37:25,  1.35it/s]
1|13162|Loss: 0.7383132576942444:  51%|█████     | 13161/25880 [2:42:37<2:37:25,  1.35it/s]
1|13162|Loss: 0.7383132576942444:  51%|█████     | 13162/25880 [2:42:38<2:25:31,  1.46it/s]
1|13163|Loss: 0.7162955403327942:  51%|█████     | 13162/25880 [2:42:38<2:25:31,  1.46it/s]
1|13163|Loss: 0.7162955403327942:  51%|█████     | 13163/25880 [2:42:38<2:31:43,  1.40it/s]
1|13164|Loss: 0.9117633104324341:  51%|█████     | 13163/25880 [2:42:39<2:31:43,  1.40it/s]
1|13164|Loss: 0.9117633104324341:  51%|█████     | 13164/25880 [2:42:39<2:30:06,  1.41it/s]
1|13165|Loss: 0.8128191828727722:  51%|█████     | 13164/25880 [2:42:39<2:30:06,  1.41it/s]
1|13165|Loss: 0.8128191828727722:  51%|█████     | 13165/25880 [2:42:40<2:24:13,  1.47it/s]
1|13166|Loss: 0.8608824610710144:  51%|█████     | 13165/25880 [2:42:40<2:24:13,  1.47it/s]
1|13166|Loss: 0.8608824610710144:  51%|█████     | 13166/25880 [2:42:40<2:24:47,  1.46it/s]
1|13167|Loss: 0.8039059042930603:  51%|█████     | 13166/25880 [2:42:41<2:24:47,  1.46it/s]
1|13167|Loss: 0.8039059042930603:  51%|█████     | 13167/25880 [2:42:41<2:22:39,  1.49it/s]
1|13168|Loss: 0.8669714331626892:  51%|█████     | 13167/25880 [2:42:41<2:22:39,  1.49it/s]
1|13168|Loss: 0.8669714331626892:  51%|█████     | 13168/25880 [2:42:42<2:20:41,  1.51it/s]
1|13169|Loss: 0.8269519209861755:  51%|█████     | 13168/25880 [2:42:42<2:20:41,  1.51it/s]
1|13169|Loss: 0.8269519209861755:  51%|█████     | 13169/25880 [2:42:42<2:31:17,  1.40it/s]
1|13170|Loss: 0.9365871548652649:  51%|█████     | 13169/25880 [2:42:43<2:31:17,  1.40it/s]
1|13170|Loss: 0.9365871548652649:  51%|█████     | 13170/25880 [2:42:43<2:25:45,  1.45it/s]
1|13171|Loss: 0.7867591381072998:  51%|█████     | 13170/25880 [2:42:43<2:25:45,  1.45it/s]
1|13171|Loss: 0.7867591381072998:  51%|█████     | 13171/25880 [2:42:44<2:35:35,  1.36it/s]
1|13172|Loss: 0.9153279662132263:  51%|█████     | 13171/25880 [2:42:44<2:35:35,  1.36it/s]
1|13172|Loss: 0.9153279662132263:  51%|█████     | 13172/25880 [2:42:45<2:45:27,  1.28it/s]
1|13173|Loss: 0.89594966173172:  51%|█████     | 13172/25880 [2:42:45<2:45:27,  1.28it/s]  
1|13173|Loss: 0.89594966173172:  51%|█████     | 13173/25880 [2:42:46<2:43:07,  1.30it/s]
1|13174|Loss: 0.8767829537391663:  51%|█████     | 13173/25880 [2:42:46<2:43:07,  1.30it/s]
1|13174|Loss: 0.8767829537391663:  51%|█████     | 13174/25880 [2:42:46<2:47:35,  1.26it/s]
1|13175|Loss: 0.9069870710372925:  51%|█████     | 13174/25880 [2:42:47<2:47:35,  1.26it/s]
1|13175|Loss: 0.9069870710372925:  51%|█████     | 13175/25880 [2:42:47<2:45:56,  1.28it/s]
1|13176|Loss: 0.789335310459137:  51%|█████     | 13175/25880 [2:42:48<2:45:56,  1.28it/s] 
1|13176|Loss: 0.789335310459137:  51%|█████     | 13176/25880 [2:42:48<2:42:15,  1.30it/s]
1|13177|Loss: 0.7844645380973816:  51%|█████     | 13176/25880 [2:42:48<2:42:15,  1.30it/s]
1|13177|Loss: 0.7844645380973816:  51%|█████     | 13177/25880 [2:42:49<2:39:41,  1.33it/s]
1|13178|Loss: 0.8784765005111694:  51%|█████     | 13177/25880 [2:42:49<2:39:41,  1.33it/s]
1|13178|Loss: 0.8784765005111694:  51%|█████     | 13178/25880 [2:42:49<2:36:55,  1.35it/s]
1|13179|Loss: 0.9322724342346191:  51%|█████     | 13178/25880 [2:42:50<2:36:55,  1.35it/s]
1|13179|Loss: 0.9322724342346191:  51%|█████     | 13179/25880 [2:42:50<2:31:18,  1.40it/s]
1|13180|Loss: 0.8294341564178467:  51%|█████     | 13179/25880 [2:42:50<2:31:18,  1.40it/s]
1|13180|Loss: 0.8294341564178467:  51%|█████     | 13180/25880 [2:42:51<2:29:21,  1.42it/s]
1|13181|Loss: 0.8597838282585144:  51%|█████     | 13180/25880 [2:42:51<2:29:21,  1.42it/s]
1|13181|Loss: 0.8597838282585144:  51%|█████     | 13181/25880 [2:42:51<2:24:35,  1.46it/s]
1|13182|Loss: 0.8154230713844299:  51%|█████     | 13181/25880 [2:42:52<2:24:35,  1.46it/s]
1|13182|Loss: 0.8154230713844299:  51%|█████     | 13182/25880 [2:42:52<2:20:20,  1.51it/s]
1|13183|Loss: 0.9317618608474731:  51%|█████     | 13182/25880 [2:42:52<2:20:20,  1.51it/s]
1|13183|Loss: 0.9317618608474731:  51%|█████     | 13183/25880 [2:42:53<2:28:37,  1.42it/s]
1|13184|Loss: 0.7295492887496948:  51%|█████     | 13183/25880 [2:42:53<2:28:37,  1.42it/s]
1|13184|Loss: 0.7295492887496948:  51%|█████     | 13184/25880 [2:42:53<2:26:58,  1.44it/s]
1|13185|Loss: 0.7613730430603027:  51%|█████     | 13184/25880 [2:42:54<2:26:58,  1.44it/s]
1|13185|Loss: 0.7613730430603027:  51%|█████     | 13185/25880 [2:42:54<2:33:28,  1.38it/s]
1|13186|Loss: 0.7444935441017151:  51%|█████     | 13185/25880 [2:42:55<2:33:28,  1.38it/s]
1|13186|Loss: 0.7444935441017151:  51%|█████     | 13186/25880 [2:42:55<2:44:29,  1.29it/s]
1|13187|Loss: 0.7459925413131714:  51%|█████     | 13186/25880 [2:42:55<2:44:29,  1.29it/s]
1|13187|Loss: 0.7459925413131714:  51%|█████     | 13187/25880 [2:42:56<2:44:09,  1.29it/s]
1|13188|Loss: 0.8671069145202637:  51%|█████     | 13187/25880 [2:42:56<2:44:09,  1.29it/s]
1|13188|Loss: 0.8671069145202637:  51%|█████     | 13188/25880 [2:42:57<2:47:02,  1.27it/s]
1|13189|Loss: 0.9328924417495728:  51%|█████     | 13188/25880 [2:42:57<2:47:02,  1.27it/s]
1|13189|Loss: 0.9328924417495728:  51%|█████     | 13189/25880 [2:42:57<2:33:18,  1.38it/s]
1|13190|Loss: 0.7889562845230103:  51%|█████     | 13189/25880 [2:42:58<2:33:18,  1.38it/s]
1|13190|Loss: 0.7889562845230103:  51%|█████     | 13190/25880 [2:42:58<2:30:20,  1.41it/s]
1|13191|Loss: 0.6339677572250366:  51%|█████     | 13190/25880 [2:42:58<2:30:20,  1.41it/s]
1|13191|Loss: 0.6339677572250366:  51%|█████     | 13191/25880 [2:42:58<2:17:15,  1.54it/s]
1|13192|Loss: 0.8548490405082703:  51%|█████     | 13191/25880 [2:42:59<2:17:15,  1.54it/s]
1|13192|Loss: 0.8548490405082703:  51%|█████     | 13192/25880 [2:42:59<2:17:04,  1.54it/s]
1|13193|Loss: 0.741121232509613:  51%|█████     | 13192/25880 [2:42:59<2:17:04,  1.54it/s] 
1|13193|Loss: 0.741121232509613:  51%|█████     | 13193/25880 [2:43:00<2:21:59,  1.49it/s]
1|13194|Loss: 0.7671987414360046:  51%|█████     | 13193/25880 [2:43:00<2:21:59,  1.49it/s]
1|13194|Loss: 0.7671987414360046:  51%|█████     | 13194/25880 [2:43:01<2:26:25,  1.44it/s]
1|13195|Loss: 0.8665446639060974:  51%|█████     | 13194/25880 [2:43:01<2:26:25,  1.44it/s]
1|13195|Loss: 0.8665446639060974:  51%|█████     | 13195/25880 [2:43:01<2:38:14,  1.34it/s]
1|13196|Loss: 0.7689407467842102:  51%|█████     | 13195/25880 [2:43:02<2:38:14,  1.34it/s]
1|13196|Loss: 0.7689407467842102:  51%|█████     | 13196/25880 [2:43:02<2:33:46,  1.37it/s]
1|13197|Loss: 0.8462274074554443:  51%|█████     | 13196/25880 [2:43:02<2:33:46,  1.37it/s]
1|13197|Loss: 0.8462274074554443:  51%|█████     | 13197/25880 [2:43:03<2:31:25,  1.40it/s]
1|13198|Loss: 0.7437149286270142:  51%|█████     | 13197/25880 [2:43:03<2:31:25,  1.40it/s]
1|13198|Loss: 0.7437149286270142:  51%|█████     | 13198/25880 [2:43:03<2:27:21,  1.43it/s]
1|13199|Loss: 0.6681219339370728:  51%|█████     | 13198/25880 [2:43:04<2:27:21,  1.43it/s]
1|13199|Loss: 0.6681219339370728:  51%|█████     | 13199/25880 [2:43:04<2:35:28,  1.36it/s]
1|13200|Loss: 0.7749048471450806:  51%|█████     | 13199/25880 [2:43:05<2:35:28,  1.36it/s]
1|13200|Loss: 0.7749048471450806:  51%|█████     | 13200/25880 [2:43:05<2:35:25,  1.36it/s]
1|13201|Loss: 0.8365859389305115:  51%|█████     | 13200/25880 [2:43:05<2:35:25,  1.36it/s]
1|13201|Loss: 0.8365859389305115:  51%|█████     | 13201/25880 [2:43:06<2:38:13,  1.34it/s]
1|13202|Loss: 0.6804199814796448:  51%|█████     | 13201/25880 [2:43:06<2:38:13,  1.34it/s]
1|13202|Loss: 0.6804199814796448:  51%|█████     | 13202/25880 [2:43:06<2:36:20,  1.35it/s]
1|13203|Loss: 0.8353502154350281:  51%|█████     | 13202/25880 [2:43:07<2:36:20,  1.35it/s]
1|13203|Loss: 0.8353502154350281:  51%|█████     | 13203/25880 [2:43:07<2:28:12,  1.43it/s]
1|13204|Loss: 0.9196270108222961:  51%|█████     | 13203/25880 [2:43:07<2:28:12,  1.43it/s]
1|13204|Loss: 0.9196270108222961:  51%|█████     | 13204/25880 [2:43:08<2:27:50,  1.43it/s]
1|13205|Loss: 0.9282432794570923:  51%|█████     | 13204/25880 [2:43:08<2:27:50,  1.43it/s]
1|13205|Loss: 0.9282432794570923:  51%|█████     | 13205/25880 [2:43:09<2:39:09,  1.33it/s]
1|13206|Loss: 0.942004382610321:  51%|█████     | 13205/25880 [2:43:09<2:39:09,  1.33it/s] 
1|13206|Loss: 0.942004382610321:  51%|█████     | 13206/25880 [2:43:09<2:39:54,  1.32it/s]
1|13207|Loss: 0.7463304996490479:  51%|█████     | 13206/25880 [2:43:10<2:39:54,  1.32it/s]
1|13207|Loss: 0.7463304996490479:  51%|█████     | 13207/25880 [2:43:10<2:33:02,  1.38it/s]
1|13208|Loss: 0.8564963936805725:  51%|█████     | 13207/25880 [2:43:10<2:33:02,  1.38it/s]
1|13208|Loss: 0.8564963936805725:  51%|█████     | 13208/25880 [2:43:11<2:27:30,  1.43it/s]
1|13209|Loss: 0.9531054496765137:  51%|█████     | 13208/25880 [2:43:11<2:27:30,  1.43it/s]
1|13209|Loss: 0.9531054496765137:  51%|█████     | 13209/25880 [2:43:11<2:20:51,  1.50it/s]
1|13210|Loss: 0.7746772170066833:  51%|█████     | 13209/25880 [2:43:12<2:20:51,  1.50it/s]
1|13210|Loss: 0.7746772170066833:  51%|█████     | 13210/25880 [2:43:12<2:23:23,  1.47it/s]
1|13211|Loss: 0.8908372521400452:  51%|█████     | 13210/25880 [2:43:12<2:23:23,  1.47it/s]
1|13211|Loss: 0.8908372521400452:  51%|█████     | 13211/25880 [2:43:13<2:34:09,  1.37it/s]
1|13212|Loss: 0.914540708065033:  51%|█████     | 13211/25880 [2:43:13<2:34:09,  1.37it/s] 
1|13212|Loss: 0.914540708065033:  51%|█████     | 13212/25880 [2:43:13<2:24:05,  1.47it/s]
1|13213|Loss: 0.8342714309692383:  51%|█████     | 13212/25880 [2:43:14<2:24:05,  1.47it/s]
1|13213|Loss: 0.8342714309692383:  51%|█████     | 13213/25880 [2:43:14<2:12:35,  1.59it/s]
1|13214|Loss: 0.8342379331588745:  51%|█████     | 13213/25880 [2:43:14<2:12:35,  1.59it/s]
1|13214|Loss: 0.8342379331588745:  51%|█████     | 13214/25880 [2:43:15<2:10:18,  1.62it/s]
1|13215|Loss: 0.7012821435928345:  51%|█████     | 13214/25880 [2:43:15<2:10:18,  1.62it/s]
1|13215|Loss: 0.7012821435928345:  51%|█████     | 13215/25880 [2:43:15<2:17:09,  1.54it/s]
1|13216|Loss: 0.8548139333724976:  51%|█████     | 13215/25880 [2:43:16<2:17:09,  1.54it/s]
1|13216|Loss: 0.8548139333724976:  51%|█████     | 13216/25880 [2:43:16<2:11:38,  1.60it/s]
1|13217|Loss: 0.729457437992096:  51%|█████     | 13216/25880 [2:43:16<2:11:38,  1.60it/s] 
1|13217|Loss: 0.729457437992096:  51%|█████     | 13217/25880 [2:43:16<2:10:41,  1.61it/s]
1|13218|Loss: 0.8458629250526428:  51%|█████     | 13217/25880 [2:43:17<2:10:41,  1.61it/s]
1|13218|Loss: 0.8458629250526428:  51%|█████     | 13218/25880 [2:43:17<2:16:46,  1.54it/s]
1|13219|Loss: 0.7302606105804443:  51%|█████     | 13218/25880 [2:43:18<2:16:46,  1.54it/s]
1|13219|Loss: 0.7302606105804443:  51%|█████     | 13219/25880 [2:43:18<2:25:56,  1.45it/s]
1|13220|Loss: 0.8602026700973511:  51%|█████     | 13219/25880 [2:43:18<2:25:56,  1.45it/s]
1|13220|Loss: 0.8602026700973511:  51%|█████     | 13220/25880 [2:43:19<2:27:47,  1.43it/s]
1|13221|Loss: 0.8103384971618652:  51%|█████     | 13220/25880 [2:43:19<2:27:47,  1.43it/s]
1|13221|Loss: 0.8103384971618652:  51%|█████     | 13221/25880 [2:43:19<2:23:20,  1.47it/s]
1|13222|Loss: 0.8992077708244324:  51%|█████     | 13221/25880 [2:43:20<2:23:20,  1.47it/s]
1|13222|Loss: 0.8992077708244324:  51%|█████     | 13222/25880 [2:43:20<2:25:42,  1.45it/s]
1|13223|Loss: 0.8418325185775757:  51%|█████     | 13222/25880 [2:43:20<2:25:42,  1.45it/s]
1|13223|Loss: 0.8418325185775757:  51%|█████     | 13223/25880 [2:43:21<2:27:17,  1.43it/s]
1|13224|Loss: 0.8573645353317261:  51%|█████     | 13223/25880 [2:43:21<2:27:17,  1.43it/s]
1|13224|Loss: 0.8573645353317261:  51%|█████     | 13224/25880 [2:43:21<2:24:13,  1.46it/s]
1|13225|Loss: 0.8729161024093628:  51%|█████     | 13224/25880 [2:43:22<2:24:13,  1.46it/s]
1|13225|Loss: 0.8729161024093628:  51%|█████     | 13225/25880 [2:43:22<2:25:40,  1.45it/s]
1|13226|Loss: 0.9058290123939514:  51%|█████     | 13225/25880 [2:43:22<2:25:40,  1.45it/s]
1|13226|Loss: 0.9058290123939514:  51%|█████     | 13226/25880 [2:43:23<2:20:27,  1.50it/s]
1|13227|Loss: 0.8660466074943542:  51%|█████     | 13226/25880 [2:43:23<2:20:27,  1.50it/s]
1|13227|Loss: 0.8660466074943542:  51%|█████     | 13227/25880 [2:43:23<2:12:23,  1.59it/s]
1|13228|Loss: 0.8729742169380188:  51%|█████     | 13227/25880 [2:43:24<2:12:23,  1.59it/s]
1|13228|Loss: 0.8729742169380188:  51%|█████     | 13228/25880 [2:43:24<2:14:41,  1.57it/s]
1|13229|Loss: 0.8220735192298889:  51%|█████     | 13228/25880 [2:43:24<2:14:41,  1.57it/s]
1|13229|Loss: 0.8220735192298889:  51%|█████     | 13229/25880 [2:43:25<2:23:18,  1.47it/s]
1|13230|Loss: 0.8264086842536926:  51%|█████     | 13229/25880 [2:43:25<2:23:18,  1.47it/s]
1|13230|Loss: 0.8264086842536926:  51%|█████     | 13230/25880 [2:43:25<2:16:33,  1.54it/s]
1|13231|Loss: 0.8452740907669067:  51%|█████     | 13230/25880 [2:43:26<2:16:33,  1.54it/s]
1|13231|Loss: 0.8452740907669067:  51%|█████     | 13231/25880 [2:43:26<2:24:53,  1.45it/s]
1|13232|Loss: 0.8463125228881836:  51%|█████     | 13231/25880 [2:43:26<2:24:53,  1.45it/s]
1|13232|Loss: 0.8463125228881836:  51%|█████     | 13232/25880 [2:43:27<2:29:41,  1.41it/s]
1|13233|Loss: 0.8751324415206909:  51%|█████     | 13232/25880 [2:43:27<2:29:41,  1.41it/s]
1|13233|Loss: 0.8751324415206909:  51%|█████     | 13233/25880 [2:43:28<2:37:11,  1.34it/s]
1|13234|Loss: 0.8541469573974609:  51%|█████     | 13233/25880 [2:43:28<2:37:11,  1.34it/s]
1|13234|Loss: 0.8541469573974609:  51%|█████     | 13234/25880 [2:43:28<2:32:27,  1.38it/s]
1|13235|Loss: 0.8880078196525574:  51%|█████     | 13234/25880 [2:43:29<2:32:27,  1.38it/s]
1|13235|Loss: 0.8880078196525574:  51%|█████     | 13235/25880 [2:43:29<2:31:33,  1.39it/s]
1|13236|Loss: 0.9350000619888306:  51%|█████     | 13235/25880 [2:43:29<2:31:33,  1.39it/s]
1|13236|Loss: 0.9350000619888306:  51%|█████     | 13236/25880 [2:43:30<2:38:14,  1.33it/s]
1|13237|Loss: 0.8302448391914368:  51%|█████     | 13236/25880 [2:43:30<2:38:14,  1.33it/s]
1|13237|Loss: 0.8302448391914368:  51%|█████     | 13237/25880 [2:43:31<2:37:13,  1.34it/s]
1|13238|Loss: 0.7881201505661011:  51%|█████     | 13237/25880 [2:43:31<2:37:13,  1.34it/s]
1|13238|Loss: 0.7881201505661011:  51%|█████     | 13238/25880 [2:43:31<2:34:02,  1.37it/s]
1|13239|Loss: 0.8735727071762085:  51%|█████     | 13238/25880 [2:43:32<2:34:02,  1.37it/s]
1|13239|Loss: 0.8735727071762085:  51%|█████     | 13239/25880 [2:43:32<2:34:07,  1.37it/s]
1|13240|Loss: 0.7747942209243774:  51%|█████     | 13239/25880 [2:43:32<2:34:07,  1.37it/s]
1|13240|Loss: 0.7747942209243774:  51%|█████     | 13240/25880 [2:43:33<2:34:32,  1.36it/s]
1|13241|Loss: 0.7734366655349731:  51%|█████     | 13240/25880 [2:43:33<2:34:32,  1.36it/s]
1|13241|Loss: 0.7734366655349731:  51%|█████     | 13241/25880 [2:43:33<2:21:35,  1.49it/s]
1|13242|Loss: 0.9253278374671936:  51%|█████     | 13241/25880 [2:43:34<2:21:35,  1.49it/s]
1|13242|Loss: 0.9253278374671936:  51%|█████     | 13242/25880 [2:43:34<2:29:00,  1.41it/s]
1|13243|Loss: 0.7908172607421875:  51%|█████     | 13242/25880 [2:43:34<2:29:00,  1.41it/s]
1|13243|Loss: 0.7908172607421875:  51%|█████     | 13243/25880 [2:43:35<2:33:23,  1.37it/s]
1|13244|Loss: 0.8733342885971069:  51%|█████     | 13243/25880 [2:43:35<2:33:23,  1.37it/s]
1|13244|Loss: 0.8733342885971069:  51%|█████     | 13244/25880 [2:43:35<2:28:33,  1.42it/s]
1|13245|Loss: 0.9556800127029419:  51%|█████     | 13244/25880 [2:43:36<2:28:33,  1.42it/s]
1|13245|Loss: 0.9556800127029419:  51%|█████     | 13245/25880 [2:43:36<2:28:56,  1.41it/s]
1|13246|Loss: 0.8857589960098267:  51%|█████     | 13245/25880 [2:43:37<2:28:56,  1.41it/s]
1|13246|Loss: 0.8857589960098267:  51%|█████     | 13246/25880 [2:43:37<2:28:48,  1.42it/s]
1|13247|Loss: 0.7907109260559082:  51%|█████     | 13246/25880 [2:43:37<2:28:48,  1.42it/s]
1|13247|Loss: 0.7907109260559082:  51%|█████     | 13247/25880 [2:43:38<2:34:49,  1.36it/s]
1|13248|Loss: 0.7469089031219482:  51%|█████     | 13247/25880 [2:43:38<2:34:49,  1.36it/s]
1|13248|Loss: 0.7469089031219482:  51%|█████     | 13248/25880 [2:43:38<2:35:39,  1.35it/s]
1|13249|Loss: 0.957724928855896:  51%|█████     | 13248/25880 [2:43:39<2:35:39,  1.35it/s] 
1|13249|Loss: 0.957724928855896:  51%|█████     | 13249/25880 [2:43:39<2:40:05,  1.31it/s]
1|13250|Loss: 0.7851782441139221:  51%|█████     | 13249/25880 [2:43:40<2:40:05,  1.31it/s]
1|13250|Loss: 0.7851782441139221:  51%|█████     | 13250/25880 [2:43:40<2:39:22,  1.32it/s]
1|13251|Loss: 0.6556641459465027:  51%|█████     | 13250/25880 [2:43:40<2:39:22,  1.32it/s]
1|13251|Loss: 0.6556641459465027:  51%|█████     | 13251/25880 [2:43:41<2:30:24,  1.40it/s]
1|13252|Loss: 0.7278872728347778:  51%|█████     | 13251/25880 [2:43:41<2:30:24,  1.40it/s]
1|13252|Loss: 0.7278872728347778:  51%|█████     | 13252/25880 [2:43:41<2:11:32,  1.60it/s]
1|13253|Loss: 0.9614651203155518:  51%|█████     | 13252/25880 [2:43:41<2:11:32,  1.60it/s]
1|13253|Loss: 0.9614651203155518:  51%|█████     | 13253/25880 [2:43:42<2:19:31,  1.51it/s]
1|13254|Loss: 0.8615376353263855:  51%|█████     | 13253/25880 [2:43:42<2:19:31,  1.51it/s]
1|13254|Loss: 0.8615376353263855:  51%|█████     | 13254/25880 [2:43:43<2:25:53,  1.44it/s]
1|13255|Loss: 0.7750409841537476:  51%|█████     | 13254/25880 [2:43:43<2:25:53,  1.44it/s]
1|13255|Loss: 0.7750409841537476:  51%|█████     | 13255/25880 [2:43:43<2:33:16,  1.37it/s]
1|13256|Loss: 0.8455727696418762:  51%|█████     | 13255/25880 [2:43:44<2:33:16,  1.37it/s]
1|13256|Loss: 0.8455727696418762:  51%|█████     | 13256/25880 [2:43:44<2:34:14,  1.36it/s]
1|13257|Loss: 0.9603362679481506:  51%|█████     | 13256/25880 [2:43:44<2:34:14,  1.36it/s]
1|13257|Loss: 0.9603362679481506:  51%|█████     | 13257/25880 [2:43:45<2:29:22,  1.41it/s]
1|13258|Loss: 0.8347498178482056:  51%|█████     | 13257/25880 [2:43:45<2:29:22,  1.41it/s]
1|13258|Loss: 0.8347498178482056:  51%|█████     | 13258/25880 [2:43:45<2:25:16,  1.45it/s]
1|13259|Loss: 0.888837993144989:  51%|█████     | 13258/25880 [2:43:46<2:25:16,  1.45it/s] 
1|13259|Loss: 0.888837993144989:  51%|█████     | 13259/25880 [2:43:46<2:18:14,  1.52it/s]
1|13260|Loss: 0.9474375247955322:  51%|█████     | 13259/25880 [2:43:46<2:18:14,  1.52it/s]
1|13260|Loss: 0.9474375247955322:  51%|█████     | 13260/25880 [2:43:47<2:19:03,  1.51it/s]
1|13261|Loss: 0.7946130633354187:  51%|█████     | 13260/25880 [2:43:47<2:19:03,  1.51it/s]
1|13261|Loss: 0.7946130633354187:  51%|█████     | 13261/25880 [2:43:47<2:21:23,  1.49it/s]
1|13262|Loss: 0.8775643706321716:  51%|█████     | 13261/25880 [2:43:48<2:21:23,  1.49it/s]
1|13262|Loss: 0.8775643706321716:  51%|█████     | 13262/25880 [2:43:48<2:27:40,  1.42it/s]
1|13263|Loss: 0.7452157735824585:  51%|█████     | 13262/25880 [2:43:49<2:27:40,  1.42it/s]
1|13263|Loss: 0.7452157735824585:  51%|█████     | 13263/25880 [2:43:49<2:31:18,  1.39it/s]
1|13264|Loss: 1.1767269372940063:  51%|█████     | 13263/25880 [2:43:49<2:31:18,  1.39it/s]
1|13264|Loss: 1.1767269372940063:  51%|█████▏    | 13264/25880 [2:43:50<2:26:42,  1.43it/s]
1|13265|Loss: 0.7944012880325317:  51%|█████▏    | 13264/25880 [2:43:50<2:26:42,  1.43it/s]
1|13265|Loss: 0.7944012880325317:  51%|█████▏    | 13265/25880 [2:43:50<2:16:16,  1.54it/s]
1|13266|Loss: 1.019321322441101:  51%|█████▏    | 13265/25880 [2:43:50<2:16:16,  1.54it/s] 
1|13266|Loss: 1.019321322441101:  51%|█████▏    | 13266/25880 [2:43:51<2:21:21,  1.49it/s]
1|13267|Loss: 0.8086894154548645:  51%|█████▏    | 13266/25880 [2:43:51<2:21:21,  1.49it/s]
1|13267|Loss: 0.8086894154548645:  51%|█████▏    | 13267/25880 [2:43:51<2:18:29,  1.52it/s]
1|13268|Loss: 0.710545539855957:  51%|█████▏    | 13267/25880 [2:43:52<2:18:29,  1.52it/s] 
1|13268|Loss: 0.710545539855957:  51%|█████▏    | 13268/25880 [2:43:52<2:26:52,  1.43it/s]
1|13269|Loss: 0.8339255452156067:  51%|█████▏    | 13268/25880 [2:43:53<2:26:52,  1.43it/s]
1|13269|Loss: 0.8339255452156067:  51%|█████▏    | 13269/25880 [2:43:53<2:33:28,  1.37it/s]
1|13270|Loss: 0.8107277750968933:  51%|█████▏    | 13269/25880 [2:43:53<2:33:28,  1.37it/s]
1|13270|Loss: 0.8107277750968933:  51%|█████▏    | 13270/25880 [2:43:54<2:39:47,  1.32it/s]
1|13271|Loss: 0.7274121642112732:  51%|█████▏    | 13270/25880 [2:43:54<2:39:47,  1.32it/s]
1|13271|Loss: 0.7274121642112732:  51%|█████▏    | 13271/25880 [2:43:54<2:27:53,  1.42it/s]
1|13272|Loss: 0.8789405822753906:  51%|█████▏    | 13271/25880 [2:43:55<2:27:53,  1.42it/s]
1|13272|Loss: 0.8789405822753906:  51%|█████▏    | 13272/25880 [2:43:55<2:15:35,  1.55it/s]
1|13273|Loss: 0.8075434565544128:  51%|█████▏    | 13272/25880 [2:43:55<2:15:35,  1.55it/s]
1|13273|Loss: 0.8075434565544128:  51%|█████▏    | 13273/25880 [2:43:56<2:21:56,  1.48it/s]
1|13274|Loss: 0.8018028736114502:  51%|█████▏    | 13273/25880 [2:43:56<2:21:56,  1.48it/s]
1|13274|Loss: 0.8018028736114502:  51%|█████▏    | 13274/25880 [2:43:56<2:21:37,  1.48it/s]
1|13275|Loss: 0.9639731049537659:  51%|█████▏    | 13274/25880 [2:43:57<2:21:37,  1.48it/s]
1|13275|Loss: 0.9639731049537659:  51%|█████▏    | 13275/25880 [2:43:57<2:27:15,  1.43it/s]
1|13276|Loss: 0.9157684445381165:  51%|█████▏    | 13275/25880 [2:43:58<2:27:15,  1.43it/s]
1|13276|Loss: 0.9157684445381165:  51%|█████▏    | 13276/25880 [2:43:58<2:30:15,  1.40it/s]
1|13277|Loss: 0.8007410168647766:  51%|█████▏    | 13276/25880 [2:43:58<2:30:15,  1.40it/s]
1|13277|Loss: 0.8007410168647766:  51%|█████▏    | 13277/25880 [2:43:59<2:38:14,  1.33it/s]
1|13278|Loss: 0.8165556192398071:  51%|█████▏    | 13277/25880 [2:43:59<2:38:14,  1.33it/s]
1|13278|Loss: 0.8165556192398071:  51%|█████▏    | 13278/25880 [2:44:00<2:43:40,  1.28it/s]
1|13279|Loss: 0.829870343208313:  51%|█████▏    | 13278/25880 [2:44:00<2:43:40,  1.28it/s] 
1|13279|Loss: 0.829870343208313:  51%|█████▏    | 13279/25880 [2:44:00<2:40:02,  1.31it/s]
1|13280|Loss: 0.9858528971672058:  51%|█████▏    | 13279/25880 [2:44:01<2:40:02,  1.31it/s]
1|13280|Loss: 0.9858528971672058:  51%|█████▏    | 13280/25880 [2:44:01<2:42:51,  1.29it/s]
1|13281|Loss: 0.756973147392273:  51%|█████▏    | 13280/25880 [2:44:01<2:42:51,  1.29it/s] 
1|13281|Loss: 0.756973147392273:  51%|█████▏    | 13281/25880 [2:44:02<2:43:47,  1.28it/s]
1|13282|Loss: 0.7589864134788513:  51%|█████▏    | 13281/25880 [2:44:02<2:43:47,  1.28it/s]
1|13282|Loss: 0.7589864134788513:  51%|█████▏    | 13282/25880 [2:44:03<2:41:23,  1.30it/s]
1|13283|Loss: 0.9355660676956177:  51%|█████▏    | 13282/25880 [2:44:03<2:41:23,  1.30it/s]
1|13283|Loss: 0.9355660676956177:  51%|█████▏    | 13283/25880 [2:44:03<2:37:20,  1.33it/s]
1|13284|Loss: 0.8496617078781128:  51%|█████▏    | 13283/25880 [2:44:04<2:37:20,  1.33it/s]
1|13284|Loss: 0.8496617078781128:  51%|█████▏    | 13284/25880 [2:44:04<2:31:23,  1.39it/s]
1|13285|Loss: 0.8384194374084473:  51%|█████▏    | 13284/25880 [2:44:04<2:31:23,  1.39it/s]
1|13285|Loss: 0.8384194374084473:  51%|█████▏    | 13285/25880 [2:44:05<2:30:55,  1.39it/s]
1|13286|Loss: 0.8139384984970093:  51%|█████▏    | 13285/25880 [2:44:05<2:30:55,  1.39it/s]
1|13286|Loss: 0.8139384984970093:  51%|█████▏    | 13286/25880 [2:44:05<2:32:09,  1.38it/s]
1|13287|Loss: 0.9569833874702454:  51%|█████▏    | 13286/25880 [2:44:06<2:32:09,  1.38it/s]
1|13287|Loss: 0.9569833874702454:  51%|█████▏    | 13287/25880 [2:44:06<2:33:29,  1.37it/s]
1|13288|Loss: 0.8983264565467834:  51%|█████▏    | 13287/25880 [2:44:07<2:33:29,  1.37it/s]
1|13288|Loss: 0.8983264565467834:  51%|█████▏    | 13288/25880 [2:44:07<2:29:33,  1.40it/s]
1|13289|Loss: 0.7338822484016418:  51%|█████▏    | 13288/25880 [2:44:07<2:29:33,  1.40it/s]
1|13289|Loss: 0.7338822484016418:  51%|█████▏    | 13289/25880 [2:44:08<2:30:30,  1.39it/s]
1|13290|Loss: 1.0318862199783325:  51%|█████▏    | 13289/25880 [2:44:08<2:30:30,  1.39it/s]
1|13290|Loss: 1.0318862199783325:  51%|█████▏    | 13290/25880 [2:44:08<2:41:06,  1.30it/s]
1|13291|Loss: 0.9932319521903992:  51%|█████▏    | 13290/25880 [2:44:09<2:41:06,  1.30it/s]
1|13291|Loss: 0.9932319521903992:  51%|█████▏    | 13291/25880 [2:44:09<2:41:41,  1.30it/s]
1|13292|Loss: 0.78427654504776:  51%|█████▏    | 13291/25880 [2:44:10<2:41:41,  1.30it/s]  
1|13292|Loss: 0.78427654504776:  51%|█████▏    | 13292/25880 [2:44:10<2:35:01,  1.35it/s]
1|13293|Loss: 0.7953962683677673:  51%|█████▏    | 13292/25880 [2:44:10<2:35:01,  1.35it/s]
1|13293|Loss: 0.7953962683677673:  51%|█████▏    | 13293/25880 [2:44:11<2:46:02,  1.26it/s]
1|13294|Loss: 0.839992344379425:  51%|█████▏    | 13293/25880 [2:44:11<2:46:02,  1.26it/s] 
1|13294|Loss: 0.839992344379425:  51%|█████▏    | 13294/25880 [2:44:12<2:46:11,  1.26it/s]
1|13295|Loss: 0.8787165880203247:  51%|█████▏    | 13294/25880 [2:44:12<2:46:11,  1.26it/s]
1|13295|Loss: 0.8787165880203247:  51%|█████▏    | 13295/25880 [2:44:12<2:42:45,  1.29it/s]
1|13296|Loss: 0.7806370854377747:  51%|█████▏    | 13295/25880 [2:44:13<2:42:45,  1.29it/s]
1|13296|Loss: 0.7806370854377747:  51%|█████▏    | 13296/25880 [2:44:13<2:44:40,  1.27it/s]
1|13297|Loss: 0.7823342084884644:  51%|█████▏    | 13296/25880 [2:44:14<2:44:40,  1.27it/s]
1|13297|Loss: 0.7823342084884644:  51%|█████▏    | 13297/25880 [2:44:14<2:42:05,  1.29it/s]
1|13298|Loss: 0.6931125521659851:  51%|█████▏    | 13297/25880 [2:44:14<2:42:05,  1.29it/s]
1|13298|Loss: 0.6931125521659851:  51%|█████▏    | 13298/25880 [2:44:15<2:38:50,  1.32it/s]
1|13299|Loss: 0.9247146248817444:  51%|█████▏    | 13298/25880 [2:44:15<2:38:50,  1.32it/s]
1|13299|Loss: 0.9247146248817444:  51%|█████▏    | 13299/25880 [2:44:15<2:42:51,  1.29it/s]
1|13300|Loss: 0.9269590973854065:  51%|█████▏    | 13299/25880 [2:44:16<2:42:51,  1.29it/s]
1|13300|Loss: 0.9269590973854065:  51%|█████▏    | 13300/25880 [2:44:16<2:35:49,  1.35it/s]
1|13301|Loss: 0.8963539004325867:  51%|█████▏    | 13300/25880 [2:44:16<2:35:49,  1.35it/s]
1|13301|Loss: 0.8963539004325867:  51%|█████▏    | 13301/25880 [2:44:17<2:40:42,  1.30it/s]
1|13302|Loss: 0.7485307455062866:  51%|█████▏    | 13301/25880 [2:44:17<2:40:42,  1.30it/s]
1|13302|Loss: 0.7485307455062866:  51%|█████▏    | 13302/25880 [2:44:18<2:47:34,  1.25it/s]
1|13303|Loss: 0.8489422798156738:  51%|█████▏    | 13302/25880 [2:44:18<2:47:34,  1.25it/s]
1|13303|Loss: 0.8489422798156738:  51%|█████▏    | 13303/25880 [2:44:19<2:45:32,  1.27it/s]
1|13304|Loss: 0.8452696800231934:  51%|█████▏    | 13303/25880 [2:44:19<2:45:32,  1.27it/s]
1|13304|Loss: 0.8452696800231934:  51%|█████▏    | 13304/25880 [2:44:19<2:43:16,  1.28it/s]
1|13305|Loss: 0.8305996060371399:  51%|█████▏    | 13304/25880 [2:44:20<2:43:16,  1.28it/s]
1|13305|Loss: 0.8305996060371399:  51%|█████▏    | 13305/25880 [2:44:20<2:30:34,  1.39it/s]
1|13306|Loss: 0.7318616509437561:  51%|█████▏    | 13305/25880 [2:44:20<2:30:34,  1.39it/s]
1|13306|Loss: 0.7318616509437561:  51%|█████▏    | 13306/25880 [2:44:21<2:27:11,  1.42it/s]
1|13307|Loss: 0.7936649322509766:  51%|█████▏    | 13306/25880 [2:44:21<2:27:11,  1.42it/s]
1|13307|Loss: 0.7936649322509766:  51%|█████▏    | 13307/25880 [2:44:21<2:27:07,  1.42it/s]
1|13308|Loss: 0.6813731789588928:  51%|█████▏    | 13307/25880 [2:44:22<2:27:07,  1.42it/s]
1|13308|Loss: 0.6813731789588928:  51%|█████▏    | 13308/25880 [2:44:22<2:27:35,  1.42it/s]
1|13309|Loss: 0.910354733467102:  51%|█████▏    | 13308/25880 [2:44:22<2:27:35,  1.42it/s] 
1|13309|Loss: 0.910354733467102:  51%|█████▏    | 13309/25880 [2:44:23<2:29:10,  1.40it/s]
1|13310|Loss: 0.8460037112236023:  51%|█████▏    | 13309/25880 [2:44:23<2:29:10,  1.40it/s]
1|13310|Loss: 0.8460037112236023:  51%|█████▏    | 13310/25880 [2:44:23<2:24:45,  1.45it/s]
1|13311|Loss: 0.8071177005767822:  51%|█████▏    | 13310/25880 [2:44:24<2:24:45,  1.45it/s]
1|13311|Loss: 0.8071177005767822:  51%|█████▏    | 13311/25880 [2:44:24<2:16:59,  1.53it/s]
1|13312|Loss: 0.7683278322219849:  51%|█████▏    | 13311/25880 [2:44:24<2:16:59,  1.53it/s]
1|13312|Loss: 0.7683278322219849:  51%|█████▏    | 13312/25880 [2:44:24<2:14:01,  1.56it/s]
1|13313|Loss: 0.8869755864143372:  51%|█████▏    | 13312/25880 [2:44:25<2:14:01,  1.56it/s]
1|13313|Loss: 0.8869755864143372:  51%|█████▏    | 13313/25880 [2:44:25<2:13:01,  1.57it/s]
1|13314|Loss: 0.9525768756866455:  51%|█████▏    | 13313/25880 [2:44:26<2:13:01,  1.57it/s]
1|13314|Loss: 0.9525768756866455:  51%|█████▏    | 13314/25880 [2:44:26<2:22:38,  1.47it/s]
1|13315|Loss: 0.9336740374565125:  51%|█████▏    | 13314/25880 [2:44:26<2:22:38,  1.47it/s]
1|13315|Loss: 0.9336740374565125:  51%|█████▏    | 13315/25880 [2:44:27<2:25:10,  1.44it/s]
1|13316|Loss: 0.7047999501228333:  51%|█████▏    | 13315/25880 [2:44:27<2:25:10,  1.44it/s]
1|13316|Loss: 0.7047999501228333:  51%|█████▏    | 13316/25880 [2:44:27<2:27:35,  1.42it/s]
1|13317|Loss: 0.8146967887878418:  51%|█████▏    | 13316/25880 [2:44:28<2:27:35,  1.42it/s]
1|13317|Loss: 0.8146967887878418:  51%|█████▏    | 13317/25880 [2:44:28<2:23:49,  1.46it/s]
1|13318|Loss: 0.8691426515579224:  51%|█████▏    | 13317/25880 [2:44:28<2:23:49,  1.46it/s]
1|13318|Loss: 0.8691426515579224:  51%|█████▏    | 13318/25880 [2:44:29<2:25:22,  1.44it/s]
1|13319|Loss: 0.824383020401001:  51%|█████▏    | 13318/25880 [2:44:29<2:25:22,  1.44it/s] 
1|13319|Loss: 0.824383020401001:  51%|█████▏    | 13319/25880 [2:44:30<2:32:51,  1.37it/s]
1|13320|Loss: 0.8115205764770508:  51%|█████▏    | 13319/25880 [2:44:30<2:32:51,  1.37it/s]
1|13320|Loss: 0.8115205764770508:  51%|█████▏    | 13320/25880 [2:44:30<2:46:14,  1.26it/s]
1|13321|Loss: 0.820039689540863:  51%|█████▏    | 13320/25880 [2:44:31<2:46:14,  1.26it/s] 
1|13321|Loss: 0.820039689540863:  51%|█████▏    | 13321/25880 [2:44:31<2:40:58,  1.30it/s]
1|13322|Loss: 0.8189955949783325:  51%|█████▏    | 13321/25880 [2:44:32<2:40:58,  1.30it/s]
1|13322|Loss: 0.8189955949783325:  51%|█████▏    | 13322/25880 [2:44:32<2:43:38,  1.28it/s]
1|13323|Loss: 0.8575547933578491:  51%|█████▏    | 13322/25880 [2:44:32<2:43:38,  1.28it/s]
1|13323|Loss: 0.8575547933578491:  51%|█████▏    | 13323/25880 [2:44:33<2:42:03,  1.29it/s]
1|13324|Loss: 0.8385316133499146:  51%|█████▏    | 13323/25880 [2:44:33<2:42:03,  1.29it/s]
1|13324|Loss: 0.8385316133499146:  51%|█████▏    | 13324/25880 [2:44:33<2:39:23,  1.31it/s]
1|13325|Loss: 0.8376516699790955:  51%|█████▏    | 13324/25880 [2:44:34<2:39:23,  1.31it/s]
1|13325|Loss: 0.8376516699790955:  51%|█████▏    | 13325/25880 [2:44:34<2:26:13,  1.43it/s]
1|13326|Loss: 0.9523294568061829:  51%|█████▏    | 13325/25880 [2:44:34<2:26:13,  1.43it/s]
1|13326|Loss: 0.9523294568061829:  51%|█████▏    | 13326/25880 [2:44:35<2:17:57,  1.52it/s]
1|13327|Loss: 0.8570365905761719:  51%|█████▏    | 13326/25880 [2:44:35<2:17:57,  1.52it/s]
1|13327|Loss: 0.8570365905761719:  51%|█████▏    | 13327/25880 [2:44:35<2:21:16,  1.48it/s]
1|13328|Loss: 0.7498388886451721:  51%|█████▏    | 13327/25880 [2:44:36<2:21:16,  1.48it/s]
1|13328|Loss: 0.7498388886451721:  51%|█████▏    | 13328/25880 [2:44:36<2:27:49,  1.42it/s]
1|13329|Loss: 0.8693879842758179:  51%|█████▏    | 13328/25880 [2:44:36<2:27:49,  1.42it/s]
1|13329|Loss: 0.8693879842758179:  52%|█████▏    | 13329/25880 [2:44:37<2:18:49,  1.51it/s]
1|13330|Loss: 0.9042783975601196:  52%|█████▏    | 13329/25880 [2:44:37<2:18:49,  1.51it/s]
1|13330|Loss: 0.9042783975601196:  52%|█████▏    | 13330/25880 [2:44:37<2:20:27,  1.49it/s]
1|13331|Loss: 0.8367868065834045:  52%|█████▏    | 13330/25880 [2:44:38<2:20:27,  1.49it/s]
1|13331|Loss: 0.8367868065834045:  52%|█████▏    | 13331/25880 [2:44:38<2:17:51,  1.52it/s]
1|13332|Loss: 0.8197206258773804:  52%|█████▏    | 13331/25880 [2:44:38<2:17:51,  1.52it/s]
1|13332|Loss: 0.8197206258773804:  52%|█████▏    | 13332/25880 [2:44:39<2:31:52,  1.38it/s]
1|13333|Loss: 0.9414401650428772:  52%|█████▏    | 13332/25880 [2:44:39<2:31:52,  1.38it/s]
1|13333|Loss: 0.9414401650428772:  52%|█████▏    | 13333/25880 [2:44:40<2:33:29,  1.36it/s]
1|13334|Loss: 0.7705114483833313:  52%|█████▏    | 13333/25880 [2:44:40<2:33:29,  1.36it/s]
1|13334|Loss: 0.7705114483833313:  52%|█████▏    | 13334/25880 [2:44:40<2:37:35,  1.33it/s]
1|13335|Loss: 0.9065953493118286:  52%|█████▏    | 13334/25880 [2:44:41<2:37:35,  1.33it/s]
1|13335|Loss: 0.9065953493118286:  52%|█████▏    | 13335/25880 [2:44:41<2:37:07,  1.33it/s]
1|13336|Loss: 0.7727763056755066:  52%|█████▏    | 13335/25880 [2:44:42<2:37:07,  1.33it/s]
1|13336|Loss: 0.7727763056755066:  52%|█████▏    | 13336/25880 [2:44:42<2:31:25,  1.38it/s]
1|13337|Loss: 0.8506696224212646:  52%|█████▏    | 13336/25880 [2:44:42<2:31:25,  1.38it/s]
1|13337|Loss: 0.8506696224212646:  52%|█████▏    | 13337/25880 [2:44:43<2:40:38,  1.30it/s]
1|13338|Loss: 0.7678617835044861:  52%|█████▏    | 13337/25880 [2:44:43<2:40:38,  1.30it/s]
1|13338|Loss: 0.7678617835044861:  52%|█████▏    | 13338/25880 [2:44:43<2:40:38,  1.30it/s]
1|13339|Loss: 0.8560835719108582:  52%|█████▏    | 13338/25880 [2:44:44<2:40:38,  1.30it/s]
1|13339|Loss: 0.8560835719108582:  52%|█████▏    | 13339/25880 [2:44:44<2:38:45,  1.32it/s]
1|13340|Loss: 0.766011118888855:  52%|█████▏    | 13339/25880 [2:44:45<2:38:45,  1.32it/s] 
1|13340|Loss: 0.766011118888855:  52%|█████▏    | 13340/25880 [2:44:45<2:37:56,  1.32it/s]
1|13341|Loss: 0.7290279865264893:  52%|█████▏    | 13340/25880 [2:44:45<2:37:56,  1.32it/s]
1|13341|Loss: 0.7290279865264893:  52%|█████▏    | 13341/25880 [2:44:46<2:29:18,  1.40it/s]
1|13342|Loss: 0.6807935833930969:  52%|█████▏    | 13341/25880 [2:44:46<2:29:18,  1.40it/s]
1|13342|Loss: 0.6807935833930969:  52%|█████▏    | 13342/25880 [2:44:46<2:19:40,  1.50it/s]
1|13343|Loss: 0.8198132514953613:  52%|█████▏    | 13342/25880 [2:44:46<2:19:40,  1.50it/s]
1|13343|Loss: 0.8198132514953613:  52%|█████▏    | 13343/25880 [2:44:47<2:07:42,  1.64it/s]
1|13344|Loss: 0.9863644242286682:  52%|█████▏    | 13343/25880 [2:44:47<2:07:42,  1.64it/s]
1|13344|Loss: 0.9863644242286682:  52%|█████▏    | 13344/25880 [2:44:47<2:00:33,  1.73it/s]
1|13345|Loss: 0.8242514133453369:  52%|█████▏    | 13344/25880 [2:44:47<2:00:33,  1.73it/s]
1|13345|Loss: 0.8242514133453369:  52%|█████▏    | 13345/25880 [2:44:48<2:05:43,  1.66it/s]
1|13346|Loss: 0.9178654551506042:  52%|█████▏    | 13345/25880 [2:44:48<2:05:43,  1.66it/s]
1|13346|Loss: 0.9178654551506042:  52%|█████▏    | 13346/25880 [2:44:48<2:07:36,  1.64it/s]
1|13347|Loss: 0.8369249701499939:  52%|█████▏    | 13346/25880 [2:44:49<2:07:36,  1.64it/s]
1|13347|Loss: 0.8369249701499939:  52%|█████▏    | 13347/25880 [2:44:49<2:19:05,  1.50it/s]
1|13348|Loss: 0.7382063865661621:  52%|█████▏    | 13347/25880 [2:44:50<2:19:05,  1.50it/s]
1|13348|Loss: 0.7382063865661621:  52%|█████▏    | 13348/25880 [2:44:50<2:25:17,  1.44it/s]
1|13349|Loss: 0.9990094304084778:  52%|█████▏    | 13348/25880 [2:44:50<2:25:17,  1.44it/s]
1|13349|Loss: 0.9990094304084778:  52%|█████▏    | 13349/25880 [2:44:51<2:28:57,  1.40it/s]
1|13350|Loss: 0.8978372812271118:  52%|█████▏    | 13349/25880 [2:44:51<2:28:57,  1.40it/s]
1|13350|Loss: 0.8978372812271118:  52%|█████▏    | 13350/25880 [2:44:51<2:31:03,  1.38it/s]
1|13351|Loss: 0.771955668926239:  52%|█████▏    | 13350/25880 [2:44:52<2:31:03,  1.38it/s] 
1|13351|Loss: 0.771955668926239:  52%|█████▏    | 13351/25880 [2:44:52<2:24:16,  1.45it/s]
1|13352|Loss: 0.9235424399375916:  52%|█████▏    | 13351/25880 [2:44:52<2:24:16,  1.45it/s]
1|13352|Loss: 0.9235424399375916:  52%|█████▏    | 13352/25880 [2:44:53<2:27:20,  1.42it/s]
1|13353|Loss: 0.999966561794281:  52%|█████▏    | 13352/25880 [2:44:53<2:27:20,  1.42it/s] 
1|13353|Loss: 0.999966561794281:  52%|█████▏    | 13353/25880 [2:44:53<2:24:16,  1.45it/s]
1|13354|Loss: 0.8297915458679199:  52%|█████▏    | 13353/25880 [2:44:54<2:24:16,  1.45it/s]
1|13354|Loss: 0.8297915458679199:  52%|█████▏    | 13354/25880 [2:44:54<2:06:07,  1.66it/s]
1|13355|Loss: 0.7547908425331116:  52%|█████▏    | 13354/25880 [2:44:54<2:06:07,  1.66it/s]
1|13355|Loss: 0.7547908425331116:  52%|█████▏    | 13355/25880 [2:44:55<2:08:49,  1.62it/s]
1|13356|Loss: 0.9314482808113098:  52%|█████▏    | 13355/25880 [2:44:55<2:08:49,  1.62it/s]
1|13356|Loss: 0.9314482808113098:  52%|█████▏    | 13356/25880 [2:44:55<2:18:27,  1.51it/s]
1|13357|Loss: 0.7259896993637085:  52%|█████▏    | 13356/25880 [2:44:56<2:18:27,  1.51it/s]
1|13357|Loss: 0.7259896993637085:  52%|█████▏    | 13357/25880 [2:44:56<2:24:24,  1.45it/s]
1|13358|Loss: 0.8555635213851929:  52%|█████▏    | 13357/25880 [2:44:56<2:24:24,  1.45it/s]
1|13358|Loss: 0.8555635213851929:  52%|█████▏    | 13358/25880 [2:44:57<2:26:11,  1.43it/s]
1|13359|Loss: 0.9151117205619812:  52%|█████▏    | 13358/25880 [2:44:57<2:26:11,  1.43it/s]
1|13359|Loss: 0.9151117205619812:  52%|█████▏    | 13359/25880 [2:44:58<2:28:21,  1.41it/s]
1|13360|Loss: 0.8768108487129211:  52%|█████▏    | 13359/25880 [2:44:58<2:28:21,  1.41it/s]
1|13360|Loss: 0.8768108487129211:  52%|█████▏    | 13360/25880 [2:44:58<2:34:42,  1.35it/s]
1|13361|Loss: 0.7562254071235657:  52%|█████▏    | 13360/25880 [2:44:59<2:34:42,  1.35it/s]
1|13361|Loss: 0.7562254071235657:  52%|█████▏    | 13361/25880 [2:44:59<2:47:11,  1.25it/s]
1|13362|Loss: 0.6978283524513245:  52%|█████▏    | 13361/25880 [2:45:00<2:47:11,  1.25it/s]
1|13362|Loss: 0.6978283524513245:  52%|█████▏    | 13362/25880 [2:45:00<2:48:48,  1.24it/s]
1|13363|Loss: 1.0207220315933228:  52%|█████▏    | 13362/25880 [2:45:01<2:48:48,  1.24it/s]
1|13363|Loss: 1.0207220315933228:  52%|█████▏    | 13363/25880 [2:45:01<2:47:50,  1.24it/s]
1|13364|Loss: 0.8588316440582275:  52%|█████▏    | 13363/25880 [2:45:01<2:47:50,  1.24it/s]
1|13364|Loss: 0.8588316440582275:  52%|█████▏    | 13364/25880 [2:45:02<2:45:01,  1.26it/s]
1|13365|Loss: 0.870328426361084:  52%|█████▏    | 13364/25880 [2:45:02<2:45:01,  1.26it/s] 
1|13365|Loss: 0.870328426361084:  52%|█████▏    | 13365/25880 [2:45:02<2:47:38,  1.24it/s]
1|13366|Loss: 0.7561204433441162:  52%|█████▏    | 13365/25880 [2:45:03<2:47:38,  1.24it/s]
1|13366|Loss: 0.7561204433441162:  52%|█████▏    | 13366/25880 [2:45:03<2:37:22,  1.33it/s]
1|13367|Loss: 0.9097476601600647:  52%|█████▏    | 13366/25880 [2:45:04<2:37:22,  1.33it/s]
1|13367|Loss: 0.9097476601600647:  52%|█████▏    | 13367/25880 [2:45:04<2:39:51,  1.30it/s]
1|13368|Loss: 0.8563070297241211:  52%|█████▏    | 13367/25880 [2:45:04<2:39:51,  1.30it/s]
1|13368|Loss: 0.8563070297241211:  52%|█████▏    | 13368/25880 [2:45:05<2:42:07,  1.29it/s]
1|13369|Loss: 0.8449846506118774:  52%|█████▏    | 13368/25880 [2:45:05<2:42:07,  1.29it/s]
1|13369|Loss: 0.8449846506118774:  52%|█████▏    | 13369/25880 [2:45:06<2:47:16,  1.25it/s]
1|13370|Loss: 0.795977771282196:  52%|█████▏    | 13369/25880 [2:45:06<2:47:16,  1.25it/s] 
1|13370|Loss: 0.795977771282196:  52%|█████▏    | 13370/25880 [2:45:06<2:49:41,  1.23it/s]
1|13371|Loss: 0.8897778987884521:  52%|█████▏    | 13370/25880 [2:45:07<2:49:41,  1.23it/s]
1|13371|Loss: 0.8897778987884521:  52%|█████▏    | 13371/25880 [2:45:07<2:53:10,  1.20it/s]
1|13372|Loss: 0.8339667916297913:  52%|█████▏    | 13371/25880 [2:45:08<2:53:10,  1.20it/s]
1|13372|Loss: 0.8339667916297913:  52%|█████▏    | 13372/25880 [2:45:08<2:50:01,  1.23it/s]
1|13373|Loss: 0.8767671585083008:  52%|█████▏    | 13372/25880 [2:45:08<2:50:01,  1.23it/s]
1|13373|Loss: 0.8767671585083008:  52%|█████▏    | 13373/25880 [2:45:09<2:45:08,  1.26it/s]
1|13374|Loss: 0.6882309913635254:  52%|█████▏    | 13373/25880 [2:45:09<2:45:08,  1.26it/s]
1|13374|Loss: 0.6882309913635254:  52%|█████▏    | 13374/25880 [2:45:10<2:47:12,  1.25it/s]
1|13375|Loss: 0.8352876305580139:  52%|█████▏    | 13374/25880 [2:45:10<2:47:12,  1.25it/s]
1|13375|Loss: 0.8352876305580139:  52%|█████▏    | 13375/25880 [2:45:10<2:40:10,  1.30it/s]
1|13376|Loss: 0.8558374643325806:  52%|█████▏    | 13375/25880 [2:45:11<2:40:10,  1.30it/s]
1|13376|Loss: 0.8558374643325806:  52%|█████▏    | 13376/25880 [2:45:11<2:36:45,  1.33it/s]
1|13377|Loss: 0.6909504532814026:  52%|█████▏    | 13376/25880 [2:45:11<2:36:45,  1.33it/s]
1|13377|Loss: 0.6909504532814026:  52%|█████▏    | 13377/25880 [2:45:12<2:42:10,  1.28it/s]
1|13378|Loss: 0.8192878365516663:  52%|█████▏    | 13377/25880 [2:45:12<2:42:10,  1.28it/s]
1|13378|Loss: 0.8192878365516663:  52%|█████▏    | 13378/25880 [2:45:13<2:35:25,  1.34it/s]
1|13379|Loss: 1.0413545370101929:  52%|█████▏    | 13378/25880 [2:45:13<2:35:25,  1.34it/s]
1|13379|Loss: 1.0413545370101929:  52%|█████▏    | 13379/25880 [2:45:13<2:32:42,  1.36it/s]
1|13380|Loss: 0.814376711845398:  52%|█████▏    | 13379/25880 [2:45:14<2:32:42,  1.36it/s] 
1|13380|Loss: 0.814376711845398:  52%|█████▏    | 13380/25880 [2:45:14<2:40:01,  1.30it/s]
1|13381|Loss: 0.7703202366828918:  52%|█████▏    | 13380/25880 [2:45:15<2:40:01,  1.30it/s]
1|13381|Loss: 0.7703202366828918:  52%|█████▏    | 13381/25880 [2:45:15<2:40:21,  1.30it/s]
1|13382|Loss: 0.8062558174133301:  52%|█████▏    | 13381/25880 [2:45:15<2:40:21,  1.30it/s]
1|13382|Loss: 0.8062558174133301:  52%|█████▏    | 13382/25880 [2:45:16<2:38:43,  1.31it/s]
1|13383|Loss: 0.819291889667511:  52%|█████▏    | 13382/25880 [2:45:16<2:38:43,  1.31it/s] 
1|13383|Loss: 0.819291889667511:  52%|█████▏    | 13383/25880 [2:45:16<2:35:34,  1.34it/s]
1|13384|Loss: 0.8584255576133728:  52%|█████▏    | 13383/25880 [2:45:17<2:35:34,  1.34it/s]
1|13384|Loss: 0.8584255576133728:  52%|█████▏    | 13384/25880 [2:45:17<2:34:24,  1.35it/s]
1|13385|Loss: 0.7960648536682129:  52%|█████▏    | 13384/25880 [2:45:17<2:34:24,  1.35it/s]
1|13385|Loss: 0.7960648536682129:  52%|█████▏    | 13385/25880 [2:45:18<2:40:07,  1.30it/s]
1|13386|Loss: 0.917192280292511:  52%|█████▏    | 13385/25880 [2:45:18<2:40:07,  1.30it/s] 
1|13386|Loss: 0.917192280292511:  52%|█████▏    | 13386/25880 [2:45:19<2:44:26,  1.27it/s]
1|13387|Loss: 0.6678662896156311:  52%|█████▏    | 13386/25880 [2:45:19<2:44:26,  1.27it/s]
1|13387|Loss: 0.6678662896156311:  52%|█████▏    | 13387/25880 [2:45:20<2:46:51,  1.25it/s]
1|13388|Loss: 0.7809078097343445:  52%|█████▏    | 13387/25880 [2:45:20<2:46:51,  1.25it/s]
1|13388|Loss: 0.7809078097343445:  52%|█████▏    | 13388/25880 [2:45:20<2:43:17,  1.28it/s]
1|13389|Loss: 0.8006036281585693:  52%|█████▏    | 13388/25880 [2:45:21<2:43:17,  1.28it/s]
1|13389|Loss: 0.8006036281585693:  52%|█████▏    | 13389/25880 [2:45:21<2:40:46,  1.29it/s]
1|13390|Loss: 0.8992193341255188:  52%|█████▏    | 13389/25880 [2:45:21<2:40:46,  1.29it/s]
1|13390|Loss: 0.8992193341255188:  52%|█████▏    | 13390/25880 [2:45:22<2:33:28,  1.36it/s]
1|13391|Loss: 0.849829375743866:  52%|█████▏    | 13390/25880 [2:45:22<2:33:28,  1.36it/s] 
1|13391|Loss: 0.849829375743866:  52%|█████▏    | 13391/25880 [2:45:22<2:27:31,  1.41it/s]
1|13392|Loss: 0.9402711391448975:  52%|█████▏    | 13391/25880 [2:45:23<2:27:31,  1.41it/s]
1|13392|Loss: 0.9402711391448975:  52%|█████▏    | 13392/25880 [2:45:23<2:23:36,  1.45it/s]
1|13393|Loss: 0.7771162986755371:  52%|█████▏    | 13392/25880 [2:45:23<2:23:36,  1.45it/s]
1|13393|Loss: 0.7771162986755371:  52%|█████▏    | 13393/25880 [2:45:24<2:19:37,  1.49it/s]
1|13394|Loss: 0.9693177938461304:  52%|█████▏    | 13393/25880 [2:45:24<2:19:37,  1.49it/s]
1|13394|Loss: 0.9693177938461304:  52%|█████▏    | 13394/25880 [2:45:24<2:17:33,  1.51it/s]
1|13395|Loss: 0.8074198961257935:  52%|█████▏    | 13394/25880 [2:45:25<2:17:33,  1.51it/s]
1|13395|Loss: 0.8074198961257935:  52%|█████▏    | 13395/25880 [2:45:25<2:11:48,  1.58it/s]
1|13396|Loss: 0.7688125371932983:  52%|█████▏    | 13395/25880 [2:45:25<2:11:48,  1.58it/s]
1|13396|Loss: 0.7688125371932983:  52%|█████▏    | 13396/25880 [2:45:26<2:25:06,  1.43it/s]
1|13397|Loss: 0.9673672914505005:  52%|█████▏    | 13396/25880 [2:45:26<2:25:06,  1.43it/s]
1|13397|Loss: 0.9673672914505005:  52%|█████▏    | 13397/25880 [2:45:26<2:28:01,  1.41it/s]
1|13398|Loss: 0.72576504945755:  52%|█████▏    | 13397/25880 [2:45:27<2:28:01,  1.41it/s]  
1|13398|Loss: 0.72576504945755:  52%|█████▏    | 13398/25880 [2:45:27<2:18:57,  1.50it/s]
1|13399|Loss: 0.7648122906684875:  52%|█████▏    | 13398/25880 [2:45:27<2:18:57,  1.50it/s]
1|13399|Loss: 0.7648122906684875:  52%|█████▏    | 13399/25880 [2:45:28<2:25:18,  1.43it/s]
1|13400|Loss: 0.7457022666931152:  52%|█████▏    | 13399/25880 [2:45:28<2:25:18,  1.43it/s]
1|13400|Loss: 0.7457022666931152:  52%|█████▏    | 13400/25880 [2:45:29<2:29:24,  1.39it/s]
1|13401|Loss: 0.8899138569831848:  52%|█████▏    | 13400/25880 [2:45:29<2:29:24,  1.39it/s]
1|13401|Loss: 0.8899138569831848:  52%|█████▏    | 13401/25880 [2:45:29<2:40:11,  1.30it/s]
1|13402|Loss: 0.8640964031219482:  52%|█████▏    | 13401/25880 [2:45:30<2:40:11,  1.30it/s]
1|13402|Loss: 0.8640964031219482:  52%|█████▏    | 13402/25880 [2:45:30<2:46:36,  1.25it/s]
1|13403|Loss: 0.8809047937393188:  52%|█████▏    | 13402/25880 [2:45:31<2:46:36,  1.25it/s]
1|13403|Loss: 0.8809047937393188:  52%|█████▏    | 13403/25880 [2:45:31<2:38:29,  1.31it/s]
1|13404|Loss: 0.8682357668876648:  52%|█████▏    | 13403/25880 [2:45:31<2:38:29,  1.31it/s]
1|13404|Loss: 0.8682357668876648:  52%|█████▏    | 13404/25880 [2:45:32<2:35:33,  1.34it/s]
1|13405|Loss: 0.7963411211967468:  52%|█████▏    | 13404/25880 [2:45:32<2:35:33,  1.34it/s]
1|13405|Loss: 0.7963411211967468:  52%|█████▏    | 13405/25880 [2:45:32<2:25:49,  1.43it/s]
1|13406|Loss: 0.846713662147522:  52%|█████▏    | 13405/25880 [2:45:33<2:25:49,  1.43it/s] 
1|13406|Loss: 0.846713662147522:  52%|█████▏    | 13406/25880 [2:45:33<2:25:15,  1.43it/s]
1|13407|Loss: 0.9096270203590393:  52%|█████▏    | 13406/25880 [2:45:33<2:25:15,  1.43it/s]
1|13407|Loss: 0.9096270203590393:  52%|█████▏    | 13407/25880 [2:45:34<2:30:56,  1.38it/s]
1|13408|Loss: 0.831678569316864:  52%|█████▏    | 13407/25880 [2:45:34<2:30:56,  1.38it/s] 
1|13408|Loss: 0.831678569316864:  52%|█████▏    | 13408/25880 [2:45:34<2:31:57,  1.37it/s]
1|13409|Loss: 0.9029727578163147:  52%|█████▏    | 13408/25880 [2:45:35<2:31:57,  1.37it/s]
1|13409|Loss: 0.9029727578163147:  52%|█████▏    | 13409/25880 [2:45:35<2:41:22,  1.29it/s]
1|13410|Loss: 0.9807818531990051:  52%|█████▏    | 13409/25880 [2:45:36<2:41:22,  1.29it/s]
1|13410|Loss: 0.9807818531990051:  52%|█████▏    | 13410/25880 [2:45:36<2:30:32,  1.38it/s]
1|13411|Loss: 0.8611041307449341:  52%|█████▏    | 13410/25880 [2:45:36<2:30:32,  1.38it/s]
1|13411|Loss: 0.8611041307449341:  52%|█████▏    | 13411/25880 [2:45:37<2:23:33,  1.45it/s]
1|13412|Loss: 0.9586024880409241:  52%|█████▏    | 13411/25880 [2:45:37<2:23:33,  1.45it/s]
1|13412|Loss: 0.9586024880409241:  52%|█████▏    | 13412/25880 [2:45:37<2:24:55,  1.43it/s]
1|13413|Loss: 0.7544258832931519:  52%|█████▏    | 13412/25880 [2:45:38<2:24:55,  1.43it/s]
1|13413|Loss: 0.7544258832931519:  52%|█████▏    | 13413/25880 [2:45:38<2:30:47,  1.38it/s]
1|13414|Loss: 0.8663108348846436:  52%|█████▏    | 13413/25880 [2:45:39<2:30:47,  1.38it/s]
1|13414|Loss: 0.8663108348846436:  52%|█████▏    | 13414/25880 [2:45:39<2:41:32,  1.29it/s]
1|13415|Loss: 0.8070895075798035:  52%|█████▏    | 13414/25880 [2:45:39<2:41:32,  1.29it/s]
1|13415|Loss: 0.8070895075798035:  52%|█████▏    | 13415/25880 [2:45:40<2:40:24,  1.30it/s]
1|13416|Loss: 0.7679245471954346:  52%|█████▏    | 13415/25880 [2:45:40<2:40:24,  1.30it/s]
1|13416|Loss: 0.7679245471954346:  52%|█████▏    | 13416/25880 [2:45:40<2:33:01,  1.36it/s]
1|13417|Loss: 0.9480621814727783:  52%|█████▏    | 13416/25880 [2:45:41<2:33:01,  1.36it/s]
1|13417|Loss: 0.9480621814727783:  52%|█████▏    | 13417/25880 [2:45:41<2:26:59,  1.41it/s]
1|13418|Loss: 0.8437191843986511:  52%|█████▏    | 13417/25880 [2:45:41<2:26:59,  1.41it/s]
1|13418|Loss: 0.8437191843986511:  52%|█████▏    | 13418/25880 [2:45:42<2:31:00,  1.38it/s]
1|13419|Loss: 0.8971604108810425:  52%|█████▏    | 13418/25880 [2:45:42<2:31:00,  1.38it/s]
1|13419|Loss: 0.8971604108810425:  52%|█████▏    | 13419/25880 [2:45:43<2:32:20,  1.36it/s]
1|13420|Loss: 0.7709084153175354:  52%|█████▏    | 13419/25880 [2:45:43<2:32:20,  1.36it/s]
1|13420|Loss: 0.7709084153175354:  52%|█████▏    | 13420/25880 [2:45:43<2:37:30,  1.32it/s]
1|13421|Loss: 0.9011803865432739:  52%|█████▏    | 13420/25880 [2:45:44<2:37:30,  1.32it/s]
1|13421|Loss: 0.9011803865432739:  52%|█████▏    | 13421/25880 [2:45:44<2:23:09,  1.45it/s]
1|13422|Loss: 0.8180273771286011:  52%|█████▏    | 13421/25880 [2:45:44<2:23:09,  1.45it/s]
1|13422|Loss: 0.8180273771286011:  52%|█████▏    | 13422/25880 [2:45:45<2:27:00,  1.41it/s]
1|13423|Loss: 0.9265544414520264:  52%|█████▏    | 13422/25880 [2:45:45<2:27:00,  1.41it/s]
1|13423|Loss: 0.9265544414520264:  52%|█████▏    | 13423/25880 [2:45:45<2:34:23,  1.34it/s]
1|13424|Loss: 0.8255617618560791:  52%|█████▏    | 13423/25880 [2:45:46<2:34:23,  1.34it/s]
1|13424|Loss: 0.8255617618560791:  52%|█████▏    | 13424/25880 [2:45:46<2:30:28,  1.38it/s]
1|13425|Loss: 0.9528354406356812:  52%|█████▏    | 13424/25880 [2:45:47<2:30:28,  1.38it/s]
1|13425|Loss: 0.9528354406356812:  52%|█████▏    | 13425/25880 [2:45:47<2:28:51,  1.39it/s]
1|13426|Loss: 0.7926139831542969:  52%|█████▏    | 13425/25880 [2:45:47<2:28:51,  1.39it/s]
1|13426|Loss: 0.7926139831542969:  52%|█████▏    | 13426/25880 [2:45:48<2:27:37,  1.41it/s]
1|13427|Loss: 0.7654099464416504:  52%|█████▏    | 13426/25880 [2:45:48<2:27:37,  1.41it/s]
1|13427|Loss: 0.7654099464416504:  52%|█████▏    | 13427/25880 [2:45:48<2:28:42,  1.40it/s]
1|13428|Loss: 1.0105255842208862:  52%|█████▏    | 13427/25880 [2:45:49<2:28:42,  1.40it/s]
1|13428|Loss: 1.0105255842208862:  52%|█████▏    | 13428/25880 [2:45:49<2:35:46,  1.33it/s]
1|13429|Loss: 0.6837723851203918:  52%|█████▏    | 13428/25880 [2:45:50<2:35:46,  1.33it/s]
1|13429|Loss: 0.6837723851203918:  52%|█████▏    | 13429/25880 [2:45:50<2:31:11,  1.37it/s]
1|13430|Loss: 0.8986728191375732:  52%|█████▏    | 13429/25880 [2:45:50<2:31:11,  1.37it/s]
1|13430|Loss: 0.8986728191375732:  52%|█████▏    | 13430/25880 [2:45:50<2:22:51,  1.45it/s]
1|13431|Loss: 0.8700745105743408:  52%|█████▏    | 13430/25880 [2:45:51<2:22:51,  1.45it/s]
1|13431|Loss: 0.8700745105743408:  52%|█████▏    | 13431/25880 [2:45:51<2:24:38,  1.43it/s]
1|13432|Loss: 0.7472479939460754:  52%|█████▏    | 13431/25880 [2:45:51<2:24:38,  1.43it/s]
1|13432|Loss: 0.7472479939460754:  52%|█████▏    | 13432/25880 [2:45:52<2:17:12,  1.51it/s]
1|13433|Loss: 0.8067387938499451:  52%|█████▏    | 13432/25880 [2:45:52<2:17:12,  1.51it/s]
1|13433|Loss: 0.8067387938499451:  52%|█████▏    | 13433/25880 [2:45:52<2:17:20,  1.51it/s]
1|13434|Loss: 0.7871757745742798:  52%|█████▏    | 13433/25880 [2:45:53<2:17:20,  1.51it/s]
1|13434|Loss: 0.7871757745742798:  52%|█████▏    | 13434/25880 [2:45:53<2:26:01,  1.42it/s]
1|13435|Loss: 1.134265422821045:  52%|█████▏    | 13434/25880 [2:45:54<2:26:01,  1.42it/s] 
1|13435|Loss: 1.134265422821045:  52%|█████▏    | 13435/25880 [2:45:54<2:28:59,  1.39it/s]
1|13436|Loss: 0.8852590322494507:  52%|█████▏    | 13435/25880 [2:45:54<2:28:59,  1.39it/s]
1|13436|Loss: 0.8852590322494507:  52%|█████▏    | 13436/25880 [2:45:55<2:35:44,  1.33it/s]
1|13437|Loss: 0.8466636538505554:  52%|█████▏    | 13436/25880 [2:45:55<2:35:44,  1.33it/s]
1|13437|Loss: 0.8466636538505554:  52%|█████▏    | 13437/25880 [2:45:55<2:30:27,  1.38it/s]
1|13438|Loss: 0.8671289086341858:  52%|█████▏    | 13437/25880 [2:45:56<2:30:27,  1.38it/s]
1|13438|Loss: 0.8671289086341858:  52%|█████▏    | 13438/25880 [2:45:56<2:32:20,  1.36it/s]
1|13439|Loss: 0.6905204057693481:  52%|█████▏    | 13438/25880 [2:45:57<2:32:20,  1.36it/s]
1|13439|Loss: 0.6905204057693481:  52%|█████▏    | 13439/25880 [2:45:57<2:40:15,  1.29it/s]
1|13440|Loss: 0.8539062738418579:  52%|█████▏    | 13439/25880 [2:45:57<2:40:15,  1.29it/s]
1|13440|Loss: 0.8539062738418579:  52%|█████▏    | 13440/25880 [2:45:58<2:38:45,  1.31it/s]
1|13441|Loss: 0.883830189704895:  52%|█████▏    | 13440/25880 [2:45:58<2:38:45,  1.31it/s] 
1|13441|Loss: 0.883830189704895:  52%|█████▏    | 13441/25880 [2:45:58<2:37:08,  1.32it/s]
1|13442|Loss: 0.814389169216156:  52%|█████▏    | 13441/25880 [2:45:59<2:37:08,  1.32it/s]
1|13442|Loss: 0.814389169216156:  52%|█████▏    | 13442/25880 [2:45:59<2:17:46,  1.50it/s]
1|13443|Loss: 0.8246148824691772:  52%|█████▏    | 13442/25880 [2:45:59<2:17:46,  1.50it/s]
1|13443|Loss: 0.8246148824691772:  52%|█████▏    | 13443/25880 [2:46:00<2:21:29,  1.46it/s]
1|13444|Loss: 0.825049877166748:  52%|█████▏    | 13443/25880 [2:46:00<2:21:29,  1.46it/s] 
1|13444|Loss: 0.825049877166748:  52%|█████▏    | 13444/25880 [2:46:00<2:28:28,  1.40it/s]
1|13445|Loss: 0.8844188451766968:  52%|█████▏    | 13444/25880 [2:46:01<2:28:28,  1.40it/s]
1|13445|Loss: 0.8844188451766968:  52%|█████▏    | 13445/25880 [2:46:01<2:16:12,  1.52it/s]
1|13446|Loss: 0.775220513343811:  52%|█████▏    | 13445/25880 [2:46:01<2:16:12,  1.52it/s] 
1|13446|Loss: 0.775220513343811:  52%|█████▏    | 13446/25880 [2:46:02<2:22:47,  1.45it/s]
1|13447|Loss: 0.8625118732452393:  52%|█████▏    | 13446/25880 [2:46:02<2:22:47,  1.45it/s]
1|13447|Loss: 0.8625118732452393:  52%|█████▏    | 13447/25880 [2:46:02<2:25:54,  1.42it/s]
1|13448|Loss: 0.9230361580848694:  52%|█████▏    | 13447/25880 [2:46:03<2:25:54,  1.42it/s]
1|13448|Loss: 0.9230361580848694:  52%|█████▏    | 13448/25880 [2:46:03<2:25:59,  1.42it/s]
1|13449|Loss: 0.6981862187385559:  52%|█████▏    | 13448/25880 [2:46:04<2:25:59,  1.42it/s]
1|13449|Loss: 0.6981862187385559:  52%|█████▏    | 13449/25880 [2:46:04<2:33:51,  1.35it/s]
1|13450|Loss: 0.8375957608222961:  52%|█████▏    | 13449/25880 [2:46:04<2:33:51,  1.35it/s]
1|13450|Loss: 0.8375957608222961:  52%|█████▏    | 13450/25880 [2:46:05<2:35:22,  1.33it/s]
1|13451|Loss: 0.778078556060791:  52%|█████▏    | 13450/25880 [2:46:05<2:35:22,  1.33it/s] 
1|13451|Loss: 0.778078556060791:  52%|█████▏    | 13451/25880 [2:46:05<2:28:39,  1.39it/s]
1|13452|Loss: 0.8634573221206665:  52%|█████▏    | 13451/25880 [2:46:06<2:28:39,  1.39it/s]
1|13452|Loss: 0.8634573221206665:  52%|█████▏    | 13452/25880 [2:46:06<2:36:12,  1.33it/s]
1|13453|Loss: 0.9493398070335388:  52%|█████▏    | 13452/25880 [2:46:07<2:36:12,  1.33it/s]
1|13453|Loss: 0.9493398070335388:  52%|█████▏    | 13453/25880 [2:46:07<2:35:41,  1.33it/s]
1|13454|Loss: 0.7772358655929565:  52%|█████▏    | 13453/25880 [2:46:07<2:35:41,  1.33it/s]
1|13454|Loss: 0.7772358655929565:  52%|█████▏    | 13454/25880 [2:46:08<2:33:44,  1.35it/s]
1|13455|Loss: 0.8524728417396545:  52%|█████▏    | 13454/25880 [2:46:08<2:33:44,  1.35it/s]
1|13455|Loss: 0.8524728417396545:  52%|█████▏    | 13455/25880 [2:46:09<2:39:35,  1.30it/s]
1|13456|Loss: 0.7658184766769409:  52%|█████▏    | 13455/25880 [2:46:09<2:39:35,  1.30it/s]
1|13456|Loss: 0.7658184766769409:  52%|█████▏    | 13456/25880 [2:46:09<2:29:15,  1.39it/s]
1|13457|Loss: 0.8787388801574707:  52%|█████▏    | 13456/25880 [2:46:10<2:29:15,  1.39it/s]
1|13457|Loss: 0.8787388801574707:  52%|█████▏    | 13457/25880 [2:46:10<2:27:04,  1.41it/s]
1|13458|Loss: 0.8152957558631897:  52%|█████▏    | 13457/25880 [2:46:10<2:27:04,  1.41it/s]
1|13458|Loss: 0.8152957558631897:  52%|█████▏    | 13458/25880 [2:46:10<2:22:27,  1.45it/s]
1|13459|Loss: 0.8807677626609802:  52%|█████▏    | 13458/25880 [2:46:11<2:22:27,  1.45it/s]
1|13459|Loss: 0.8807677626609802:  52%|█████▏    | 13459/25880 [2:46:11<2:17:02,  1.51it/s]
1|13460|Loss: 0.8726831078529358:  52%|█████▏    | 13459/25880 [2:46:11<2:17:02,  1.51it/s]
1|13460|Loss: 0.8726831078529358:  52%|█████▏    | 13460/25880 [2:46:12<2:11:59,  1.57it/s]
1|13461|Loss: 0.9991288185119629:  52%|█████▏    | 13460/25880 [2:46:12<2:11:59,  1.57it/s]
1|13461|Loss: 0.9991288185119629:  52%|█████▏    | 13461/25880 [2:46:12<2:23:22,  1.44it/s]
1|13462|Loss: 0.7626813054084778:  52%|█████▏    | 13461/25880 [2:46:13<2:23:22,  1.44it/s]
1|13462|Loss: 0.7626813054084778:  52%|█████▏    | 13462/25880 [2:46:13<2:34:44,  1.34it/s]
1|13463|Loss: 0.8864531517028809:  52%|█████▏    | 13462/25880 [2:46:14<2:34:44,  1.34it/s]
1|13463|Loss: 0.8864531517028809:  52%|█████▏    | 13463/25880 [2:46:14<2:40:34,  1.29it/s]
1|13464|Loss: 0.8418422341346741:  52%|█████▏    | 13463/25880 [2:46:15<2:40:34,  1.29it/s]
1|13464|Loss: 0.8418422341346741:  52%|█████▏    | 13464/25880 [2:46:15<2:39:26,  1.30it/s]
1|13465|Loss: 0.7930432558059692:  52%|█████▏    | 13464/25880 [2:46:15<2:39:26,  1.30it/s]
1|13465|Loss: 0.7930432558059692:  52%|█████▏    | 13465/25880 [2:46:16<2:38:22,  1.31it/s]
1|13466|Loss: 1.0245604515075684:  52%|█████▏    | 13465/25880 [2:46:16<2:38:22,  1.31it/s]
1|13466|Loss: 1.0245604515075684:  52%|█████▏    | 13466/25880 [2:46:16<2:36:33,  1.32it/s]
1|13467|Loss: 0.8013195991516113:  52%|█████▏    | 13466/25880 [2:46:17<2:36:33,  1.32it/s]
1|13467|Loss: 0.8013195991516113:  52%|█████▏    | 13467/25880 [2:46:17<2:27:38,  1.40it/s]
1|13468|Loss: 0.7579857707023621:  52%|█████▏    | 13467/25880 [2:46:17<2:27:38,  1.40it/s]
1|13468|Loss: 0.7579857707023621:  52%|█████▏    | 13468/25880 [2:46:18<2:27:04,  1.41it/s]
1|13469|Loss: 0.8131101131439209:  52%|█████▏    | 13468/25880 [2:46:18<2:27:04,  1.41it/s]
1|13469|Loss: 0.8131101131439209:  52%|█████▏    | 13469/25880 [2:46:19<2:33:14,  1.35it/s]
1|13470|Loss: 0.8531320691108704:  52%|█████▏    | 13469/25880 [2:46:19<2:33:14,  1.35it/s]
1|13470|Loss: 0.8531320691108704:  52%|█████▏    | 13470/25880 [2:46:19<2:33:46,  1.35it/s]
1|13471|Loss: 0.7127701044082642:  52%|█████▏    | 13470/25880 [2:46:20<2:33:46,  1.35it/s]
1|13471|Loss: 0.7127701044082642:  52%|█████▏    | 13471/25880 [2:46:20<2:35:51,  1.33it/s]
1|13472|Loss: 0.8349249362945557:  52%|█████▏    | 13471/25880 [2:46:20<2:35:51,  1.33it/s]
1|13472|Loss: 0.8349249362945557:  52%|█████▏    | 13472/25880 [2:46:21<2:28:11,  1.40it/s]
1|13473|Loss: 0.8321491479873657:  52%|█████▏    | 13472/25880 [2:46:21<2:28:11,  1.40it/s]
1|13473|Loss: 0.8321491479873657:  52%|█████▏    | 13473/25880 [2:46:21<2:30:08,  1.38it/s]
1|13474|Loss: 0.7202540040016174:  52%|█████▏    | 13473/25880 [2:46:22<2:30:08,  1.38it/s]
1|13474|Loss: 0.7202540040016174:  52%|█████▏    | 13474/25880 [2:46:22<2:34:48,  1.34it/s]
1|13475|Loss: 0.7886513471603394:  52%|█████▏    | 13474/25880 [2:46:23<2:34:48,  1.34it/s]
1|13475|Loss: 0.7886513471603394:  52%|█████▏    | 13475/25880 [2:46:23<2:33:14,  1.35it/s]
1|13476|Loss: 0.8718555569648743:  52%|█████▏    | 13475/25880 [2:46:23<2:33:14,  1.35it/s]
1|13476|Loss: 0.8718555569648743:  52%|█████▏    | 13476/25880 [2:46:24<2:26:21,  1.41it/s]
1|13477|Loss: 0.9396844506263733:  52%|█████▏    | 13476/25880 [2:46:24<2:26:21,  1.41it/s]
1|13477|Loss: 0.9396844506263733:  52%|█████▏    | 13477/25880 [2:46:24<2:32:24,  1.36it/s]
1|13478|Loss: 0.7751492261886597:  52%|█████▏    | 13477/25880 [2:46:25<2:32:24,  1.36it/s]
1|13478|Loss: 0.7751492261886597:  52%|█████▏    | 13478/25880 [2:46:25<2:46:59,  1.24it/s]
1|13479|Loss: 0.8920329809188843:  52%|█████▏    | 13478/25880 [2:46:26<2:46:59,  1.24it/s]
1|13479|Loss: 0.8920329809188843:  52%|█████▏    | 13479/25880 [2:46:26<2:45:02,  1.25it/s]
1|13480|Loss: 0.9233295321464539:  52%|█████▏    | 13479/25880 [2:46:27<2:45:02,  1.25it/s]
1|13480|Loss: 0.9233295321464539:  52%|█████▏    | 13480/25880 [2:46:27<2:40:45,  1.29it/s]
1|13481|Loss: 0.8922956585884094:  52%|█████▏    | 13480/25880 [2:46:27<2:40:45,  1.29it/s]
1|13481|Loss: 0.8922956585884094:  52%|█████▏    | 13481/25880 [2:46:28<2:36:18,  1.32it/s]
1|13482|Loss: 0.8279038667678833:  52%|█████▏    | 13481/25880 [2:46:28<2:36:18,  1.32it/s]
1|13482|Loss: 0.8279038667678833:  52%|█████▏    | 13482/25880 [2:46:28<2:32:36,  1.35it/s]
1|13483|Loss: 0.710594892501831:  52%|█████▏    | 13482/25880 [2:46:29<2:32:36,  1.35it/s] 
1|13483|Loss: 0.710594892501831:  52%|█████▏    | 13483/25880 [2:46:29<2:35:02,  1.33it/s]
1|13484|Loss: 0.868367612361908:  52%|█████▏    | 13483/25880 [2:46:30<2:35:02,  1.33it/s]
1|13484|Loss: 0.868367612361908:  52%|█████▏    | 13484/25880 [2:46:30<2:40:39,  1.29it/s]
1|13485|Loss: 0.856555700302124:  52%|█████▏    | 13484/25880 [2:46:30<2:40:39,  1.29it/s]
1|13485|Loss: 0.856555700302124:  52%|█████▏    | 13485/25880 [2:46:31<2:29:46,  1.38it/s]
1|13486|Loss: 0.7447811961174011:  52%|█████▏    | 13485/25880 [2:46:31<2:29:46,  1.38it/s]
1|13486|Loss: 0.7447811961174011:  52%|█████▏    | 13486/25880 [2:46:31<2:22:04,  1.45it/s]
1|13487|Loss: 0.9170222282409668:  52%|█████▏    | 13486/25880 [2:46:32<2:22:04,  1.45it/s]
1|13487|Loss: 0.9170222282409668:  52%|█████▏    | 13487/25880 [2:46:32<2:16:42,  1.51it/s]
1|13488|Loss: 0.8910197615623474:  52%|█████▏    | 13487/25880 [2:46:32<2:16:42,  1.51it/s]
1|13488|Loss: 0.8910197615623474:  52%|█████▏    | 13488/25880 [2:46:32<2:17:43,  1.50it/s]
1|13489|Loss: 0.7658634185791016:  52%|█████▏    | 13488/25880 [2:46:33<2:17:43,  1.50it/s]
1|13489|Loss: 0.7658634185791016:  52%|█████▏    | 13489/25880 [2:46:33<2:25:48,  1.42it/s]
1|13490|Loss: 0.9317804574966431:  52%|█████▏    | 13489/25880 [2:46:34<2:25:48,  1.42it/s]
1|13490|Loss: 0.9317804574966431:  52%|█████▏    | 13490/25880 [2:46:34<2:21:48,  1.46it/s]
1|13491|Loss: 0.8517078757286072:  52%|█████▏    | 13490/25880 [2:46:34<2:21:48,  1.46it/s]
1|13491|Loss: 0.8517078757286072:  52%|█████▏    | 13491/25880 [2:46:35<2:21:17,  1.46it/s]
1|13492|Loss: 0.7397801876068115:  52%|█████▏    | 13491/25880 [2:46:35<2:21:17,  1.46it/s]
1|13492|Loss: 0.7397801876068115:  52%|█████▏    | 13492/25880 [2:46:35<2:23:43,  1.44it/s]
1|13493|Loss: 0.7719535231590271:  52%|█████▏    | 13492/25880 [2:46:36<2:23:43,  1.44it/s]
1|13493|Loss: 0.7719535231590271:  52%|█████▏    | 13493/25880 [2:46:36<2:19:58,  1.47it/s]
1|13494|Loss: 0.847081184387207:  52%|█████▏    | 13493/25880 [2:46:36<2:19:58,  1.47it/s] 
1|13494|Loss: 0.847081184387207:  52%|█████▏    | 13494/25880 [2:46:37<2:30:45,  1.37it/s]
1|13495|Loss: 0.9404995441436768:  52%|█████▏    | 13494/25880 [2:46:37<2:30:45,  1.37it/s]
1|13495|Loss: 0.9404995441436768:  52%|█████▏    | 13495/25880 [2:46:38<2:38:44,  1.30it/s]
1|13496|Loss: 0.707000732421875:  52%|█████▏    | 13495/25880 [2:46:38<2:38:44,  1.30it/s] 
1|13496|Loss: 0.707000732421875:  52%|█████▏    | 13496/25880 [2:46:38<2:33:52,  1.34it/s]
1|13497|Loss: 1.0143173933029175:  52%|█████▏    | 13496/25880 [2:46:39<2:33:52,  1.34it/s]
1|13497|Loss: 1.0143173933029175:  52%|█████▏    | 13497/25880 [2:46:39<2:27:18,  1.40it/s]
1|13498|Loss: 0.7553545236587524:  52%|█████▏    | 13497/25880 [2:46:39<2:27:18,  1.40it/s]
1|13498|Loss: 0.7553545236587524:  52%|█████▏    | 13498/25880 [2:46:40<2:27:34,  1.40it/s]
1|13499|Loss: 0.8749971389770508:  52%|█████▏    | 13498/25880 [2:46:40<2:27:34,  1.40it/s]
1|13499|Loss: 0.8749971389770508:  52%|█████▏    | 13499/25880 [2:46:40<2:29:47,  1.38it/s]
1|13500|Loss: 0.7774874567985535:  52%|█████▏    | 13499/25880 [2:46:41<2:29:47,  1.38it/s]
1|13500|Loss: 0.7774874567985535:  52%|█████▏    | 13500/25880 [2:46:41<2:24:56,  1.42it/s]
1|13501|Loss: 0.8800055384635925:  52%|█████▏    | 13500/25880 [2:46:41<2:24:56,  1.42it/s]
1|13501|Loss: 0.8800055384635925:  52%|█████▏    | 13501/25880 [2:46:42<2:19:32,  1.48it/s]
1|13502|Loss: 0.8065163493156433:  52%|█████▏    | 13501/25880 [2:46:42<2:19:32,  1.48it/s]
1|13502|Loss: 0.8065163493156433:  52%|█████▏    | 13502/25880 [2:46:42<2:17:21,  1.50it/s]
1|13503|Loss: 0.8287918567657471:  52%|█████▏    | 13502/25880 [2:46:43<2:17:21,  1.50it/s]
1|13503|Loss: 0.8287918567657471:  52%|█████▏    | 13503/25880 [2:46:43<2:18:57,  1.48it/s]
1|13504|Loss: 0.8242461085319519:  52%|█████▏    | 13503/25880 [2:46:43<2:18:57,  1.48it/s]
1|13504|Loss: 0.8242461085319519:  52%|█████▏    | 13504/25880 [2:46:44<2:08:32,  1.60it/s]
1|13505|Loss: 0.7876104712486267:  52%|█████▏    | 13504/25880 [2:46:44<2:08:32,  1.60it/s]
1|13505|Loss: 0.7876104712486267:  52%|█████▏    | 13505/25880 [2:46:44<2:02:50,  1.68it/s]
1|13506|Loss: 0.8055506944656372:  52%|█████▏    | 13505/25880 [2:46:44<2:02:50,  1.68it/s]
1|13506|Loss: 0.8055506944656372:  52%|█████▏    | 13506/25880 [2:46:45<2:07:21,  1.62it/s]
1|13507|Loss: 0.8259142637252808:  52%|█████▏    | 13506/25880 [2:46:45<2:07:21,  1.62it/s]
1|13507|Loss: 0.8259142637252808:  52%|█████▏    | 13507/25880 [2:46:46<2:16:44,  1.51it/s]
1|13508|Loss: 0.8630490899085999:  52%|█████▏    | 13507/25880 [2:46:46<2:16:44,  1.51it/s]
1|13508|Loss: 0.8630490899085999:  52%|█████▏    | 13508/25880 [2:46:46<2:17:22,  1.50it/s]
1|13509|Loss: 0.7786112427711487:  52%|█████▏    | 13508/25880 [2:46:47<2:17:22,  1.50it/s]
1|13509|Loss: 0.7786112427711487:  52%|█████▏    | 13509/25880 [2:46:47<2:10:24,  1.58it/s]
1|13510|Loss: 0.9155336618423462:  52%|█████▏    | 13509/25880 [2:46:47<2:10:24,  1.58it/s]
1|13510|Loss: 0.9155336618423462:  52%|█████▏    | 13510/25880 [2:46:47<2:06:26,  1.63it/s]
1|13511|Loss: 0.8175209164619446:  52%|█████▏    | 13510/25880 [2:46:48<2:06:26,  1.63it/s]
1|13511|Loss: 0.8175209164619446:  52%|█████▏    | 13511/25880 [2:46:48<2:07:09,  1.62it/s]
1|13512|Loss: 0.8604111075401306:  52%|█████▏    | 13511/25880 [2:46:48<2:07:09,  1.62it/s]
1|13512|Loss: 0.8604111075401306:  52%|█████▏    | 13512/25880 [2:46:49<2:13:16,  1.55it/s]
1|13513|Loss: 0.8049108386039734:  52%|█████▏    | 13512/25880 [2:46:49<2:13:16,  1.55it/s]
1|13513|Loss: 0.8049108386039734:  52%|█████▏    | 13513/25880 [2:46:49<2:18:03,  1.49it/s]
1|13514|Loss: 0.8112031817436218:  52%|█████▏    | 13513/25880 [2:46:50<2:18:03,  1.49it/s]
1|13514|Loss: 0.8112031817436218:  52%|█████▏    | 13514/25880 [2:46:50<2:24:21,  1.43it/s]
1|13515|Loss: 0.9548543095588684:  52%|█████▏    | 13514/25880 [2:46:51<2:24:21,  1.43it/s]
1|13515|Loss: 0.9548543095588684:  52%|█████▏    | 13515/25880 [2:46:51<2:32:00,  1.36it/s]
1|13516|Loss: 0.9168484210968018:  52%|█████▏    | 13515/25880 [2:46:51<2:32:00,  1.36it/s]
1|13516|Loss: 0.9168484210968018:  52%|█████▏    | 13516/25880 [2:46:52<2:27:56,  1.39it/s]
1|13517|Loss: 0.8727103471755981:  52%|█████▏    | 13516/25880 [2:46:52<2:27:56,  1.39it/s]
1|13517|Loss: 0.8727103471755981:  52%|█████▏    | 13517/25880 [2:46:52<2:28:44,  1.39it/s]
1|13518|Loss: 0.8570597767829895:  52%|█████▏    | 13517/25880 [2:46:53<2:28:44,  1.39it/s]
1|13518|Loss: 0.8570597767829895:  52%|█████▏    | 13518/25880 [2:46:53<2:25:17,  1.42it/s]
1|13519|Loss: 0.8291289210319519:  52%|█████▏    | 13518/25880 [2:46:53<2:25:17,  1.42it/s]
1|13519|Loss: 0.8291289210319519:  52%|█████▏    | 13519/25880 [2:46:54<2:31:31,  1.36it/s]
1|13520|Loss: 0.8710710406303406:  52%|█████▏    | 13519/25880 [2:46:54<2:31:31,  1.36it/s]
1|13520|Loss: 0.8710710406303406:  52%|█████▏    | 13520/25880 [2:46:54<2:19:05,  1.48it/s]
1|13521|Loss: 0.8282692432403564:  52%|█████▏    | 13520/25880 [2:46:55<2:19:05,  1.48it/s]
1|13521|Loss: 0.8282692432403564:  52%|█████▏    | 13521/25880 [2:46:55<2:25:37,  1.41it/s]
1|13522|Loss: 0.8994606733322144:  52%|█████▏    | 13521/25880 [2:46:56<2:25:37,  1.41it/s]
1|13522|Loss: 0.8994606733322144:  52%|█████▏    | 13522/25880 [2:46:56<2:30:01,  1.37it/s]
1|13523|Loss: 0.9781180620193481:  52%|█████▏    | 13522/25880 [2:46:56<2:30:01,  1.37it/s]
1|13523|Loss: 0.9781180620193481:  52%|█████▏    | 13523/25880 [2:46:57<2:34:23,  1.33it/s]
1|13524|Loss: 0.8115736842155457:  52%|█████▏    | 13523/25880 [2:46:57<2:34:23,  1.33it/s]
1|13524|Loss: 0.8115736842155457:  52%|█████▏    | 13524/25880 [2:46:57<2:28:25,  1.39it/s]
1|13525|Loss: 0.8331087827682495:  52%|█████▏    | 13524/25880 [2:46:58<2:28:25,  1.39it/s]
1|13525|Loss: 0.8331087827682495:  52%|█████▏    | 13525/25880 [2:46:58<2:22:06,  1.45it/s]
1|13526|Loss: 0.8461582064628601:  52%|█████▏    | 13525/25880 [2:46:58<2:22:06,  1.45it/s]
1|13526|Loss: 0.8461582064628601:  52%|█████▏    | 13526/25880 [2:46:59<2:23:28,  1.44it/s]
1|13527|Loss: 0.7426825761795044:  52%|█████▏    | 13526/25880 [2:46:59<2:23:28,  1.44it/s]
1|13527|Loss: 0.7426825761795044:  52%|█████▏    | 13527/25880 [2:46:59<2:21:30,  1.45it/s]
1|13528|Loss: 0.8716501593589783:  52%|█████▏    | 13527/25880 [2:47:00<2:21:30,  1.45it/s]
1|13528|Loss: 0.8716501593589783:  52%|█████▏    | 13528/25880 [2:47:00<2:24:25,  1.43it/s]
1|13529|Loss: 0.8835124373435974:  52%|█████▏    | 13528/25880 [2:47:01<2:24:25,  1.43it/s]
1|13529|Loss: 0.8835124373435974:  52%|█████▏    | 13529/25880 [2:47:01<2:31:44,  1.36it/s]
1|13530|Loss: 0.8763138651847839:  52%|█████▏    | 13529/25880 [2:47:01<2:31:44,  1.36it/s]
1|13530|Loss: 0.8763138651847839:  52%|█████▏    | 13530/25880 [2:47:02<2:31:14,  1.36it/s]
1|13531|Loss: 0.8285155296325684:  52%|█████▏    | 13530/25880 [2:47:02<2:31:14,  1.36it/s]
1|13531|Loss: 0.8285155296325684:  52%|█████▏    | 13531/25880 [2:47:02<2:20:28,  1.47it/s]
1|13532|Loss: 0.902929961681366:  52%|█████▏    | 13531/25880 [2:47:03<2:20:28,  1.47it/s] 
1|13532|Loss: 0.902929961681366:  52%|█████▏    | 13532/25880 [2:47:03<2:16:33,  1.51it/s]
1|13533|Loss: 0.7393606901168823:  52%|█████▏    | 13532/25880 [2:47:03<2:16:33,  1.51it/s]
1|13533|Loss: 0.7393606901168823:  52%|█████▏    | 13533/25880 [2:47:03<2:15:27,  1.52it/s]
1|13534|Loss: 0.7638059854507446:  52%|█████▏    | 13533/25880 [2:47:04<2:15:27,  1.52it/s]
1|13534|Loss: 0.7638059854507446:  52%|█████▏    | 13534/25880 [2:47:04<2:19:50,  1.47it/s]
1|13535|Loss: 0.6865020990371704:  52%|█████▏    | 13534/25880 [2:47:05<2:19:50,  1.47it/s]
1|13535|Loss: 0.6865020990371704:  52%|█████▏    | 13535/25880 [2:47:05<2:29:35,  1.38it/s]
1|13536|Loss: 0.7560441493988037:  52%|█████▏    | 13535/25880 [2:47:05<2:29:35,  1.38it/s]
1|13536|Loss: 0.7560441493988037:  52%|█████▏    | 13536/25880 [2:47:06<2:24:15,  1.43it/s]
1|13537|Loss: 0.7168436050415039:  52%|█████▏    | 13536/25880 [2:47:06<2:24:15,  1.43it/s]
1|13537|Loss: 0.7168436050415039:  52%|█████▏    | 13537/25880 [2:47:06<2:22:47,  1.44it/s]
1|13538|Loss: 0.8718043565750122:  52%|█████▏    | 13537/25880 [2:47:07<2:22:47,  1.44it/s]
1|13538|Loss: 0.8718043565750122:  52%|█████▏    | 13538/25880 [2:47:07<2:24:30,  1.42it/s]
1|13539|Loss: 0.8893076181411743:  52%|█████▏    | 13538/25880 [2:47:07<2:24:30,  1.42it/s]
1|13539|Loss: 0.8893076181411743:  52%|█████▏    | 13539/25880 [2:47:08<2:19:02,  1.48it/s]
1|13540|Loss: 0.8249668478965759:  52%|█████▏    | 13539/25880 [2:47:08<2:19:02,  1.48it/s]
1|13540|Loss: 0.8249668478965759:  52%|█████▏    | 13540/25880 [2:47:08<2:15:57,  1.51it/s]
1|13541|Loss: 0.8952639698982239:  52%|█████▏    | 13540/25880 [2:47:09<2:15:57,  1.51it/s]
1|13541|Loss: 0.8952639698982239:  52%|█████▏    | 13541/25880 [2:47:09<2:19:41,  1.47it/s]
1|13542|Loss: 0.7904658913612366:  52%|█████▏    | 13541/25880 [2:47:09<2:19:41,  1.47it/s]
1|13542|Loss: 0.7904658913612366:  52%|█████▏    | 13542/25880 [2:47:10<2:28:06,  1.39it/s]
1|13543|Loss: 0.9727657437324524:  52%|█████▏    | 13542/25880 [2:47:10<2:28:06,  1.39it/s]
1|13543|Loss: 0.9727657437324524:  52%|█████▏    | 13543/25880 [2:47:11<2:25:21,  1.41it/s]
1|13544|Loss: 0.8957303762435913:  52%|█████▏    | 13543/25880 [2:47:11<2:25:21,  1.41it/s]
1|13544|Loss: 0.8957303762435913:  52%|█████▏    | 13544/25880 [2:47:11<2:21:37,  1.45it/s]
1|13545|Loss: 0.8058169484138489:  52%|█████▏    | 13544/25880 [2:47:12<2:21:37,  1.45it/s]
1|13545|Loss: 0.8058169484138489:  52%|█████▏    | 13545/25880 [2:47:12<2:18:58,  1.48it/s]
1|13546|Loss: 0.7798475027084351:  52%|█████▏    | 13545/25880 [2:47:12<2:18:58,  1.48it/s]
1|13546|Loss: 0.7798475027084351:  52%|█████▏    | 13546/25880 [2:47:13<2:22:03,  1.45it/s]
1|13547|Loss: 0.7505946159362793:  52%|█████▏    | 13546/25880 [2:47:13<2:22:03,  1.45it/s]
1|13547|Loss: 0.7505946159362793:  52%|█████▏    | 13547/25880 [2:47:13<2:23:11,  1.44it/s]
1|13548|Loss: 0.8183773159980774:  52%|█████▏    | 13547/25880 [2:47:14<2:23:11,  1.44it/s]
1|13548|Loss: 0.8183773159980774:  52%|█████▏    | 13548/25880 [2:47:14<2:25:41,  1.41it/s]
1|13549|Loss: 0.8636645078659058:  52%|█████▏    | 13548/25880 [2:47:14<2:25:41,  1.41it/s]
1|13549|Loss: 0.8636645078659058:  52%|█████▏    | 13549/25880 [2:47:15<2:32:06,  1.35it/s]
1|13550|Loss: 0.8679162859916687:  52%|█████▏    | 13549/25880 [2:47:15<2:32:06,  1.35it/s]
1|13550|Loss: 0.8679162859916687:  52%|█████▏    | 13550/25880 [2:47:16<2:38:49,  1.29it/s]
1|13551|Loss: 0.8210576176643372:  52%|█████▏    | 13550/25880 [2:47:16<2:38:49,  1.29it/s]
1|13551|Loss: 0.8210576176643372:  52%|█████▏    | 13551/25880 [2:47:17<2:42:55,  1.26it/s]
1|13552|Loss: 0.836621105670929:  52%|█████▏    | 13551/25880 [2:47:17<2:42:55,  1.26it/s] 
1|13552|Loss: 0.836621105670929:  52%|█████▏    | 13552/25880 [2:47:17<2:30:26,  1.37it/s]
1|13553|Loss: 0.7923458218574524:  52%|█████▏    | 13552/25880 [2:47:17<2:30:26,  1.37it/s]
1|13553|Loss: 0.7923458218574524:  52%|█████▏    | 13553/25880 [2:47:18<2:19:11,  1.48it/s]
1|13554|Loss: 0.7943965196609497:  52%|█████▏    | 13553/25880 [2:47:18<2:19:11,  1.48it/s]
1|13554|Loss: 0.7943965196609497:  52%|█████▏    | 13554/25880 [2:47:18<2:20:45,  1.46it/s]
1|13555|Loss: 0.8102342486381531:  52%|█████▏    | 13554/25880 [2:47:19<2:20:45,  1.46it/s]
1|13555|Loss: 0.8102342486381531:  52%|█████▏    | 13555/25880 [2:47:19<2:16:43,  1.50it/s]
1|13556|Loss: 0.9665048718452454:  52%|█████▏    | 13555/25880 [2:47:19<2:16:43,  1.50it/s]
1|13556|Loss: 0.9665048718452454:  52%|█████▏    | 13556/25880 [2:47:20<2:09:13,  1.59it/s]
1|13557|Loss: 0.9249162673950195:  52%|█████▏    | 13556/25880 [2:47:20<2:09:13,  1.59it/s]
1|13557|Loss: 0.9249162673950195:  52%|█████▏    | 13557/25880 [2:47:20<2:13:52,  1.53it/s]
1|13558|Loss: 0.8881109952926636:  52%|█████▏    | 13557/25880 [2:47:21<2:13:52,  1.53it/s]
1|13558|Loss: 0.8881109952926636:  52%|█████▏    | 13558/25880 [2:47:21<2:14:42,  1.52it/s]
1|13559|Loss: 0.8046117424964905:  52%|█████▏    | 13558/25880 [2:47:21<2:14:42,  1.52it/s]
1|13559|Loss: 0.8046117424964905:  52%|█████▏    | 13559/25880 [2:47:22<2:17:53,  1.49it/s]
1|13560|Loss: 0.8163139224052429:  52%|█████▏    | 13559/25880 [2:47:22<2:17:53,  1.49it/s]
1|13560|Loss: 0.8163139224052429:  52%|█████▏    | 13560/25880 [2:47:22<2:23:58,  1.43it/s]
1|13561|Loss: 0.7835555076599121:  52%|█████▏    | 13560/25880 [2:47:23<2:23:58,  1.43it/s]
1|13561|Loss: 0.7835555076599121:  52%|█████▏    | 13561/25880 [2:47:23<2:22:13,  1.44it/s]
1|13562|Loss: 0.9822002053260803:  52%|█████▏    | 13561/25880 [2:47:23<2:22:13,  1.44it/s]
1|13562|Loss: 0.9822002053260803:  52%|█████▏    | 13562/25880 [2:47:24<2:28:05,  1.39it/s]
1|13563|Loss: 0.8330613374710083:  52%|█████▏    | 13562/25880 [2:47:24<2:28:05,  1.39it/s]
1|13563|Loss: 0.8330613374710083:  52%|█████▏    | 13563/25880 [2:47:25<2:29:56,  1.37it/s]
1|13564|Loss: 0.8051630854606628:  52%|█████▏    | 13563/25880 [2:47:25<2:29:56,  1.37it/s]
1|13564|Loss: 0.8051630854606628:  52%|█████▏    | 13564/25880 [2:47:25<2:28:15,  1.38it/s]
1|13565|Loss: 0.855432391166687:  52%|█████▏    | 13564/25880 [2:47:26<2:28:15,  1.38it/s] 
1|13565|Loss: 0.855432391166687:  52%|█████▏    | 13565/25880 [2:47:26<2:20:42,  1.46it/s]
1|13566|Loss: 0.6631057262420654:  52%|█████▏    | 13565/25880 [2:47:26<2:20:42,  1.46it/s]
1|13566|Loss: 0.6631057262420654:  52%|█████▏    | 13566/25880 [2:47:27<2:19:52,  1.47it/s]
1|13567|Loss: 0.7737686038017273:  52%|█████▏    | 13566/25880 [2:47:27<2:19:52,  1.47it/s]
1|13567|Loss: 0.7737686038017273:  52%|█████▏    | 13567/25880 [2:47:27<2:18:06,  1.49it/s]
1|13568|Loss: 0.8793395757675171:  52%|█████▏    | 13567/25880 [2:47:28<2:18:06,  1.49it/s]
1|13568|Loss: 0.8793395757675171:  52%|█████▏    | 13568/25880 [2:47:28<2:23:10,  1.43it/s]
1|13569|Loss: 0.8741412162780762:  52%|█████▏    | 13568/25880 [2:47:28<2:23:10,  1.43it/s]
1|13569|Loss: 0.8741412162780762:  52%|█████▏    | 13569/25880 [2:47:29<2:33:46,  1.33it/s]
1|13570|Loss: 0.8600789308547974:  52%|█████▏    | 13569/25880 [2:47:29<2:33:46,  1.33it/s]
1|13570|Loss: 0.8600789308547974:  52%|█████▏    | 13570/25880 [2:47:30<2:30:33,  1.36it/s]
1|13571|Loss: 0.9115652441978455:  52%|█████▏    | 13570/25880 [2:47:30<2:30:33,  1.36it/s]
1|13571|Loss: 0.9115652441978455:  52%|█████▏    | 13571/25880 [2:47:30<2:23:53,  1.43it/s]
1|13572|Loss: 0.7121226787567139:  52%|█████▏    | 13571/25880 [2:47:31<2:23:53,  1.43it/s]
1|13572|Loss: 0.7121226787567139:  52%|█████▏    | 13572/25880 [2:47:31<2:35:34,  1.32it/s]
1|13573|Loss: 0.7568314075469971:  52%|█████▏    | 13572/25880 [2:47:32<2:35:34,  1.32it/s]
1|13573|Loss: 0.7568314075469971:  52%|█████▏    | 13573/25880 [2:47:32<2:49:34,  1.21it/s]
1|13574|Loss: 0.8785799741744995:  52%|█████▏    | 13573/25880 [2:47:32<2:49:34,  1.21it/s]
1|13574|Loss: 0.8785799741744995:  52%|█████▏    | 13574/25880 [2:47:33<2:43:15,  1.26it/s]
1|13575|Loss: 0.8118018507957458:  52%|█████▏    | 13574/25880 [2:47:33<2:43:15,  1.26it/s]
1|13575|Loss: 0.8118018507957458:  52%|█████▏    | 13575/25880 [2:47:33<2:32:32,  1.34it/s]
1|13576|Loss: 0.997036337852478:  52%|█████▏    | 13575/25880 [2:47:34<2:32:32,  1.34it/s] 
1|13576|Loss: 0.997036337852478:  52%|█████▏    | 13576/25880 [2:47:34<2:37:10,  1.30it/s]
1|13577|Loss: 1.0065268278121948:  52%|█████▏    | 13576/25880 [2:47:35<2:37:10,  1.30it/s]
1|13577|Loss: 1.0065268278121948:  52%|█████▏    | 13577/25880 [2:47:35<2:40:23,  1.28it/s]
1|13578|Loss: 0.9496561288833618:  52%|█████▏    | 13577/25880 [2:47:35<2:40:23,  1.28it/s]
1|13578|Loss: 0.9496561288833618:  52%|█████▏    | 13578/25880 [2:47:36<2:33:30,  1.34it/s]
1|13579|Loss: 0.8373138904571533:  52%|█████▏    | 13578/25880 [2:47:36<2:33:30,  1.34it/s]
1|13579|Loss: 0.8373138904571533:  52%|█████▏    | 13579/25880 [2:47:36<2:25:38,  1.41it/s]
1|13580|Loss: 0.7276279330253601:  52%|█████▏    | 13579/25880 [2:47:37<2:25:38,  1.41it/s]
1|13580|Loss: 0.7276279330253601:  52%|█████▏    | 13580/25880 [2:47:37<2:38:22,  1.29it/s]
1|13581|Loss: 0.6823346614837646:  52%|█████▏    | 13580/25880 [2:47:38<2:38:22,  1.29it/s]
1|13581|Loss: 0.6823346614837646:  52%|█████▏    | 13581/25880 [2:47:38<2:38:05,  1.30it/s]
1|13582|Loss: 0.8177101612091064:  52%|█████▏    | 13581/25880 [2:47:38<2:38:05,  1.30it/s]
1|13582|Loss: 0.8177101612091064:  52%|█████▏    | 13582/25880 [2:47:39<2:29:12,  1.37it/s]
1|13583|Loss: 0.9683583974838257:  52%|█████▏    | 13582/25880 [2:47:39<2:29:12,  1.37it/s]
1|13583|Loss: 0.9683583974838257:  52%|█████▏    | 13583/25880 [2:47:39<2:28:46,  1.38it/s]
1|13584|Loss: 0.7767956256866455:  52%|█████▏    | 13583/25880 [2:47:40<2:28:46,  1.38it/s]
1|13584|Loss: 0.7767956256866455:  52%|█████▏    | 13584/25880 [2:47:40<2:18:46,  1.48it/s]
1|13585|Loss: 0.7208103537559509:  52%|█████▏    | 13584/25880 [2:47:40<2:18:46,  1.48it/s]
1|13585|Loss: 0.7208103537559509:  52%|█████▏    | 13585/25880 [2:47:41<2:18:00,  1.48it/s]
1|13586|Loss: 0.7074958682060242:  52%|█████▏    | 13585/25880 [2:47:41<2:18:00,  1.48it/s]
1|13586|Loss: 0.7074958682060242:  52%|█████▏    | 13586/25880 [2:47:41<2:01:52,  1.68it/s]
1|13587|Loss: 0.9027694463729858:  52%|█████▏    | 13586/25880 [2:47:41<2:01:52,  1.68it/s]
1|13587|Loss: 0.9027694463729858:  52%|█████▎    | 13587/25880 [2:47:42<2:05:17,  1.64it/s]
1|13588|Loss: 1.0296961069107056:  52%|█████▎    | 13587/25880 [2:47:42<2:05:17,  1.64it/s]
1|13588|Loss: 1.0296961069107056:  53%|█████▎    | 13588/25880 [2:47:42<2:11:41,  1.56it/s]
1|13589|Loss: 0.8186377286911011:  53%|█████▎    | 13588/25880 [2:47:43<2:11:41,  1.56it/s]
1|13589|Loss: 0.8186377286911011:  53%|█████▎    | 13589/25880 [2:47:43<2:11:12,  1.56it/s]
1|13590|Loss: 0.799137532711029:  53%|█████▎    | 13589/25880 [2:47:43<2:11:12,  1.56it/s] 
1|13590|Loss: 0.799137532711029:  53%|█████▎    | 13590/25880 [2:47:44<2:24:50,  1.41it/s]
1|13591|Loss: 0.7350578904151917:  53%|█████▎    | 13590/25880 [2:47:44<2:24:50,  1.41it/s]
1|13591|Loss: 0.7350578904151917:  53%|█████▎    | 13591/25880 [2:47:44<2:15:10,  1.52it/s]
1|13592|Loss: 0.8042678236961365:  53%|█████▎    | 13591/25880 [2:47:45<2:15:10,  1.52it/s]
1|13592|Loss: 0.8042678236961365:  53%|█████▎    | 13592/25880 [2:47:45<2:14:51,  1.52it/s]
1|13593|Loss: 0.8521391153335571:  53%|█████▎    | 13592/25880 [2:47:45<2:14:51,  1.52it/s]
1|13593|Loss: 0.8521391153335571:  53%|█████▎    | 13593/25880 [2:47:46<2:17:28,  1.49it/s]
1|13594|Loss: 0.9954981207847595:  53%|█████▎    | 13593/25880 [2:47:46<2:17:28,  1.49it/s]
1|13594|Loss: 0.9954981207847595:  53%|█████▎    | 13594/25880 [2:47:46<2:20:48,  1.45it/s]
1|13595|Loss: 0.7791088819503784:  53%|█████▎    | 13594/25880 [2:47:47<2:20:48,  1.45it/s]
1|13595|Loss: 0.7791088819503784:  53%|█████▎    | 13595/25880 [2:47:47<2:17:38,  1.49it/s]
1|13596|Loss: 0.8805785775184631:  53%|█████▎    | 13595/25880 [2:47:47<2:17:38,  1.49it/s]
1|13596|Loss: 0.8805785775184631:  53%|█████▎    | 13596/25880 [2:47:48<2:19:36,  1.47it/s]
1|13597|Loss: 0.7494999170303345:  53%|█████▎    | 13596/25880 [2:47:48<2:19:36,  1.47it/s]
1|13597|Loss: 0.7494999170303345:  53%|█████▎    | 13597/25880 [2:47:49<2:22:14,  1.44it/s]
1|13598|Loss: 0.8589665293693542:  53%|█████▎    | 13597/25880 [2:47:49<2:22:14,  1.44it/s]
1|13598|Loss: 0.8589665293693542:  53%|█████▎    | 13598/25880 [2:47:49<2:15:32,  1.51it/s]
1|13599|Loss: 0.8857209086418152:  53%|█████▎    | 13598/25880 [2:47:49<2:15:32,  1.51it/s]
1|13599|Loss: 0.8857209086418152:  53%|█████▎    | 13599/25880 [2:47:50<2:11:48,  1.55it/s]
1|13600|Loss: 0.9540558457374573:  53%|█████▎    | 13599/25880 [2:47:50<2:11:48,  1.55it/s]
1|13600|Loss: 0.9540558457374573:  53%|█████▎    | 13600/25880 [2:47:51<2:28:16,  1.38it/s]
1|13601|Loss: 0.7478488087654114:  53%|█████▎    | 13600/25880 [2:47:51<2:28:16,  1.38it/s]
1|13601|Loss: 0.7478488087654114:  53%|█████▎    | 13601/25880 [2:47:51<2:27:26,  1.39it/s]
1|13602|Loss: 0.6652015447616577:  53%|█████▎    | 13601/25880 [2:47:52<2:27:26,  1.39it/s]
1|13602|Loss: 0.6652015447616577:  53%|█████▎    | 13602/25880 [2:47:52<2:21:57,  1.44it/s]
1|13603|Loss: 0.773663341999054:  53%|█████▎    | 13602/25880 [2:47:52<2:21:57,  1.44it/s] 
1|13603|Loss: 0.773663341999054:  53%|█████▎    | 13603/25880 [2:47:53<2:17:33,  1.49it/s]
1|13604|Loss: 0.9546632170677185:  53%|█████▎    | 13603/25880 [2:47:53<2:17:33,  1.49it/s]
1|13604|Loss: 0.9546632170677185:  53%|█████▎    | 13604/25880 [2:47:53<2:20:41,  1.45it/s]
1|13605|Loss: 0.9429817795753479:  53%|█████▎    | 13604/25880 [2:47:54<2:20:41,  1.45it/s]
1|13605|Loss: 0.9429817795753479:  53%|█████▎    | 13605/25880 [2:47:54<2:32:36,  1.34it/s]
1|13606|Loss: 0.8350164294242859:  53%|█████▎    | 13605/25880 [2:47:55<2:32:36,  1.34it/s]
1|13606|Loss: 0.8350164294242859:  53%|█████▎    | 13606/25880 [2:47:55<2:43:00,  1.25it/s]
1|13607|Loss: 0.9598768353462219:  53%|█████▎    | 13606/25880 [2:47:56<2:43:00,  1.25it/s]
1|13607|Loss: 0.9598768353462219:  53%|█████▎    | 13607/25880 [2:47:56<2:41:49,  1.26it/s]
1|13608|Loss: 0.9050791263580322:  53%|█████▎    | 13607/25880 [2:47:56<2:41:49,  1.26it/s]
1|13608|Loss: 0.9050791263580322:  53%|█████▎    | 13608/25880 [2:47:57<2:37:23,  1.30it/s]
1|13609|Loss: 0.8511138558387756:  53%|█████▎    | 13608/25880 [2:47:57<2:37:23,  1.30it/s]
1|13609|Loss: 0.8511138558387756:  53%|█████▎    | 13609/25880 [2:47:57<2:28:53,  1.37it/s]
1|13610|Loss: 0.9339891076087952:  53%|█████▎    | 13609/25880 [2:47:58<2:28:53,  1.37it/s]
1|13610|Loss: 0.9339891076087952:  53%|█████▎    | 13610/25880 [2:47:58<2:17:00,  1.49it/s]
1|13611|Loss: 0.8994532227516174:  53%|█████▎    | 13610/25880 [2:47:58<2:17:00,  1.49it/s]
1|13611|Loss: 0.8994532227516174:  53%|█████▎    | 13611/25880 [2:47:59<2:24:01,  1.42it/s]
1|13612|Loss: 0.9208160638809204:  53%|█████▎    | 13611/25880 [2:47:59<2:24:01,  1.42it/s]
1|13612|Loss: 0.9208160638809204:  53%|█████▎    | 13612/25880 [2:47:59<2:27:32,  1.39it/s]
1|13613|Loss: 0.7946752905845642:  53%|█████▎    | 13612/25880 [2:48:00<2:27:32,  1.39it/s]
1|13613|Loss: 0.7946752905845642:  53%|█████▎    | 13613/25880 [2:48:00<2:23:35,  1.42it/s]
1|13614|Loss: 0.7410562038421631:  53%|█████▎    | 13613/25880 [2:48:00<2:23:35,  1.42it/s]
1|13614|Loss: 0.7410562038421631:  53%|█████▎    | 13614/25880 [2:48:01<2:37:50,  1.30it/s]
1|13615|Loss: 0.8932939171791077:  53%|█████▎    | 13614/25880 [2:48:01<2:37:50,  1.30it/s]
1|13615|Loss: 0.8932939171791077:  53%|█████▎    | 13615/25880 [2:48:02<2:29:39,  1.37it/s]
1|13616|Loss: 0.824629545211792:  53%|█████▎    | 13615/25880 [2:48:02<2:29:39,  1.37it/s] 
1|13616|Loss: 0.824629545211792:  53%|█████▎    | 13616/25880 [2:48:02<2:27:11,  1.39it/s]
1|13617|Loss: 0.9271879196166992:  53%|█████▎    | 13616/25880 [2:48:03<2:27:11,  1.39it/s]
1|13617|Loss: 0.9271879196166992:  53%|█████▎    | 13617/25880 [2:48:03<2:31:06,  1.35it/s]
1|13618|Loss: 0.8972691893577576:  53%|█████▎    | 13617/25880 [2:48:03<2:31:06,  1.35it/s]
1|13618|Loss: 0.8972691893577576:  53%|█████▎    | 13618/25880 [2:48:04<2:34:29,  1.32it/s]
1|13619|Loss: 0.8104868531227112:  53%|█████▎    | 13618/25880 [2:48:04<2:34:29,  1.32it/s]
1|13619|Loss: 0.8104868531227112:  53%|█████▎    | 13619/25880 [2:48:05<2:28:10,  1.38it/s]
1|13620|Loss: 0.8269981741905212:  53%|█████▎    | 13619/25880 [2:48:05<2:28:10,  1.38it/s]
1|13620|Loss: 0.8269981741905212:  53%|█████▎    | 13620/25880 [2:48:06<2:51:28,  1.19it/s]
1|13621|Loss: 0.7237076163291931:  53%|█████▎    | 13620/25880 [2:48:06<2:51:28,  1.19it/s]
1|13621|Loss: 0.7237076163291931:  53%|█████▎    | 13621/25880 [2:48:06<2:51:16,  1.19it/s]
1|13622|Loss: 0.8437588810920715:  53%|█████▎    | 13621/25880 [2:48:07<2:51:16,  1.19it/s]
1|13622|Loss: 0.8437588810920715:  53%|█████▎    | 13622/25880 [2:48:07<2:44:36,  1.24it/s]
1|13623|Loss: 0.8861333727836609:  53%|█████▎    | 13622/25880 [2:48:08<2:44:36,  1.24it/s]
1|13623|Loss: 0.8861333727836609:  53%|█████▎    | 13623/25880 [2:48:08<2:39:48,  1.28it/s]
1|13624|Loss: 0.9065250754356384:  53%|█████▎    | 13623/25880 [2:48:08<2:39:48,  1.28it/s]
1|13624|Loss: 0.9065250754356384:  53%|█████▎    | 13624/25880 [2:48:08<2:27:59,  1.38it/s]
1|13625|Loss: 0.7704456448554993:  53%|█████▎    | 13624/25880 [2:48:09<2:27:59,  1.38it/s]
1|13625|Loss: 0.7704456448554993:  53%|█████▎    | 13625/25880 [2:48:09<2:32:58,  1.34it/s]
1|13626|Loss: 0.8999505043029785:  53%|█████▎    | 13625/25880 [2:48:10<2:32:58,  1.34it/s]
1|13626|Loss: 0.8999505043029785:  53%|█████▎    | 13626/25880 [2:48:10<2:29:26,  1.37it/s]
1|13627|Loss: 0.992668628692627:  53%|█████▎    | 13626/25880 [2:48:10<2:29:26,  1.37it/s] 
1|13627|Loss: 0.992668628692627:  53%|█████▎    | 13627/25880 [2:48:11<2:33:31,  1.33it/s]
1|13628|Loss: 0.8752508759498596:  53%|█████▎    | 13627/25880 [2:48:11<2:33:31,  1.33it/s]
1|13628|Loss: 0.8752508759498596:  53%|█████▎    | 13628/25880 [2:48:12<2:35:59,  1.31it/s]
1|13629|Loss: 0.8452728390693665:  53%|█████▎    | 13628/25880 [2:48:12<2:35:59,  1.31it/s]
1|13629|Loss: 0.8452728390693665:  53%|█████▎    | 13629/25880 [2:48:12<2:37:48,  1.29it/s]
1|13630|Loss: 0.8476496934890747:  53%|█████▎    | 13629/25880 [2:48:13<2:37:48,  1.29it/s]
1|13630|Loss: 0.8476496934890747:  53%|█████▎    | 13630/25880 [2:48:13<2:51:49,  1.19it/s]
1|13631|Loss: 0.8000695705413818:  53%|█████▎    | 13630/25880 [2:48:14<2:51:49,  1.19it/s]
1|13631|Loss: 0.8000695705413818:  53%|█████▎    | 13631/25880 [2:48:14<2:48:44,  1.21it/s]
1|13632|Loss: 0.7704271674156189:  53%|█████▎    | 13631/25880 [2:48:15<2:48:44,  1.21it/s]
1|13632|Loss: 0.7704271674156189:  53%|█████▎    | 13632/25880 [2:48:15<2:42:34,  1.26it/s]
1|13633|Loss: 0.8773930072784424:  53%|█████▎    | 13632/25880 [2:48:15<2:42:34,  1.26it/s]
1|13633|Loss: 0.8773930072784424:  53%|█████▎    | 13633/25880 [2:48:16<2:41:30,  1.26it/s]
1|13634|Loss: 0.81308513879776:  53%|█████▎    | 13633/25880 [2:48:16<2:41:30,  1.26it/s]  
1|13634|Loss: 0.81308513879776:  53%|█████▎    | 13634/25880 [2:48:17<2:43:59,  1.24it/s]
1|13635|Loss: 0.8968983888626099:  53%|█████▎    | 13634/25880 [2:48:17<2:43:59,  1.24it/s]
1|13635|Loss: 0.8968983888626099:  53%|█████▎    | 13635/25880 [2:48:17<2:39:09,  1.28it/s]
1|13636|Loss: 0.7808119058609009:  53%|█████▎    | 13635/25880 [2:48:18<2:39:09,  1.28it/s]
1|13636|Loss: 0.7808119058609009:  53%|█████▎    | 13636/25880 [2:48:18<2:41:03,  1.27it/s]
1|13637|Loss: 0.717536449432373:  53%|█████▎    | 13636/25880 [2:48:18<2:41:03,  1.27it/s] 
1|13637|Loss: 0.717536449432373:  53%|█████▎    | 13637/25880 [2:48:19<2:37:19,  1.30it/s]
1|13638|Loss: 0.8267779350280762:  53%|█████▎    | 13637/25880 [2:48:19<2:37:19,  1.30it/s]
1|13638|Loss: 0.8267779350280762:  53%|█████▎    | 13638/25880 [2:48:20<2:40:57,  1.27it/s]
1|13639|Loss: 0.7797405123710632:  53%|█████▎    | 13638/25880 [2:48:20<2:40:57,  1.27it/s]
1|13639|Loss: 0.7797405123710632:  53%|█████▎    | 13639/25880 [2:48:20<2:34:08,  1.32it/s]
1|13640|Loss: 0.8401816487312317:  53%|█████▎    | 13639/25880 [2:48:21<2:34:08,  1.32it/s]
1|13640|Loss: 0.8401816487312317:  53%|█████▎    | 13640/25880 [2:48:21<2:29:54,  1.36it/s]
1|13641|Loss: 0.859392523765564:  53%|█████▎    | 13640/25880 [2:48:21<2:29:54,  1.36it/s] 
1|13641|Loss: 0.859392523765564:  53%|█████▎    | 13641/25880 [2:48:22<2:20:32,  1.45it/s]
1|13642|Loss: 0.7896590232849121:  53%|█████▎    | 13641/25880 [2:48:22<2:20:32,  1.45it/s]
1|13642|Loss: 0.7896590232849121:  53%|█████▎    | 13642/25880 [2:48:22<2:19:13,  1.47it/s]
1|13643|Loss: 0.6575262546539307:  53%|█████▎    | 13642/25880 [2:48:23<2:19:13,  1.47it/s]
1|13643|Loss: 0.6575262546539307:  53%|█████▎    | 13643/25880 [2:48:23<2:30:24,  1.36it/s]
1|13644|Loss: 0.8486020565032959:  53%|█████▎    | 13643/25880 [2:48:23<2:30:24,  1.36it/s]
1|13644|Loss: 0.8486020565032959:  53%|█████▎    | 13644/25880 [2:48:24<2:27:51,  1.38it/s]
1|13645|Loss: 1.0020248889923096:  53%|█████▎    | 13644/25880 [2:48:24<2:27:51,  1.38it/s]
1|13645|Loss: 1.0020248889923096:  53%|█████▎    | 13645/25880 [2:48:24<2:27:13,  1.39it/s]
1|13646|Loss: 0.9714198708534241:  53%|█████▎    | 13645/25880 [2:48:25<2:27:13,  1.39it/s]
1|13646|Loss: 0.9714198708534241:  53%|█████▎    | 13646/25880 [2:48:25<2:26:42,  1.39it/s]
1|13647|Loss: 0.9348607659339905:  53%|█████▎    | 13646/25880 [2:48:26<2:26:42,  1.39it/s]
1|13647|Loss: 0.9348607659339905:  53%|█████▎    | 13647/25880 [2:48:26<2:27:34,  1.38it/s]
1|13648|Loss: 0.8939181566238403:  53%|█████▎    | 13647/25880 [2:48:26<2:27:34,  1.38it/s]
1|13648|Loss: 0.8939181566238403:  53%|█████▎    | 13648/25880 [2:48:27<2:35:04,  1.31it/s]
1|13649|Loss: 0.9064493775367737:  53%|█████▎    | 13648/25880 [2:48:27<2:35:04,  1.31it/s]
1|13649|Loss: 0.9064493775367737:  53%|█████▎    | 13649/25880 [2:48:27<2:28:37,  1.37it/s]
1|13650|Loss: 0.8163674473762512:  53%|█████▎    | 13649/25880 [2:48:28<2:28:37,  1.37it/s]
1|13650|Loss: 0.8163674473762512:  53%|█████▎    | 13650/25880 [2:48:28<2:25:48,  1.40it/s]
1|13651|Loss: 0.8252566456794739:  53%|█████▎    | 13650/25880 [2:48:28<2:25:48,  1.40it/s]
1|13651|Loss: 0.8252566456794739:  53%|█████▎    | 13651/25880 [2:48:29<2:22:04,  1.43it/s]
1|13652|Loss: 0.9101431369781494:  53%|█████▎    | 13651/25880 [2:48:29<2:22:04,  1.43it/s]
1|13652|Loss: 0.9101431369781494:  53%|█████▎    | 13652/25880 [2:48:29<2:23:05,  1.42it/s]
1|13653|Loss: 0.9327654838562012:  53%|█████▎    | 13652/25880 [2:48:30<2:23:05,  1.42it/s]
1|13653|Loss: 0.9327654838562012:  53%|█████▎    | 13653/25880 [2:48:30<2:14:52,  1.51it/s]
1|13654|Loss: 0.8890351057052612:  53%|█████▎    | 13653/25880 [2:48:30<2:14:52,  1.51it/s]
1|13654|Loss: 0.8890351057052612:  53%|█████▎    | 13654/25880 [2:48:31<2:03:27,  1.65it/s]
1|13655|Loss: 0.8872430324554443:  53%|█████▎    | 13654/25880 [2:48:31<2:03:27,  1.65it/s]
1|13655|Loss: 0.8872430324554443:  53%|█████▎    | 13655/25880 [2:48:31<1:59:57,  1.70it/s]
1|13656|Loss: 0.9147430658340454:  53%|█████▎    | 13655/25880 [2:48:31<1:59:57,  1.70it/s]
1|13656|Loss: 0.9147430658340454:  53%|█████▎    | 13656/25880 [2:48:32<2:02:10,  1.67it/s]
1|13657|Loss: 0.8406473994255066:  53%|█████▎    | 13656/25880 [2:48:32<2:02:10,  1.67it/s]
1|13657|Loss: 0.8406473994255066:  53%|█████▎    | 13657/25880 [2:48:32<1:59:30,  1.70it/s]
1|13658|Loss: 0.8117773532867432:  53%|���████▎    | 13657/25880 [2:48:33<1:59:30,  1.70it/s]
1|13658|Loss: 0.8117773532867432:  53%|█████▎    | 13658/25880 [2:48:33<2:09:41,  1.57it/s]
1|13659|Loss: 0.8821195363998413:  53%|█████▎    | 13658/25880 [2:48:33<2:09:41,  1.57it/s]
1|13659|Loss: 0.8821195363998413:  53%|█████▎    | 13659/25880 [2:48:34<2:12:14,  1.54it/s]
1|13660|Loss: 0.8603895306587219:  53%|█████▎    | 13659/25880 [2:48:34<2:12:14,  1.54it/s]
1|13660|Loss: 0.8603895306587219:  53%|█████▎    | 13660/25880 [2:48:34<2:11:44,  1.55it/s]
1|13661|Loss: 0.9623616337776184:  53%|█████▎    | 13660/25880 [2:48:35<2:11:44,  1.55it/s]
1|13661|Loss: 0.9623616337776184:  53%|█████▎    | 13661/25880 [2:48:35<2:21:39,  1.44it/s]
1|13662|Loss: 0.8493624329566956:  53%|█████▎    | 13661/25880 [2:48:36<2:21:39,  1.44it/s]
1|13662|Loss: 0.8493624329566956:  53%|█████▎    | 13662/25880 [2:48:36<2:14:46,  1.51it/s]
1|13663|Loss: 0.8486064076423645:  53%|█████▎    | 13662/25880 [2:48:36<2:14:46,  1.51it/s]
1|13663|Loss: 0.8486064076423645:  53%|█████▎    | 13663/25880 [2:48:37<2:25:35,  1.40it/s]
1|13664|Loss: 0.7816956639289856:  53%|█████▎    | 13663/25880 [2:48:37<2:25:35,  1.40it/s]
1|13664|Loss: 0.7816956639289856:  53%|█████▎    | 13664/25880 [2:48:37<2:23:17,  1.42it/s]
1|13665|Loss: 0.8845964074134827:  53%|█████▎    | 13664/25880 [2:48:38<2:23:17,  1.42it/s]
1|13665|Loss: 0.8845964074134827:  53%|█████▎    | 13665/25880 [2:48:38<2:26:54,  1.39it/s]
1|13666|Loss: 0.8557116985321045:  53%|█████▎    | 13665/25880 [2:48:38<2:26:54,  1.39it/s]
1|13666|Loss: 0.8557116985321045:  53%|█████▎    | 13666/25880 [2:48:39<2:31:39,  1.34it/s]
1|13667|Loss: 0.8058648705482483:  53%|█████▎    | 13666/25880 [2:48:39<2:31:39,  1.34it/s]
1|13667|Loss: 0.8058648705482483:  53%|█████▎    | 13667/25880 [2:48:40<2:38:07,  1.29it/s]
1|13668|Loss: 0.7593278288841248:  53%|█████▎    | 13667/25880 [2:48:40<2:38:07,  1.29it/s]
1|13668|Loss: 0.7593278288841248:  53%|█████▎    | 13668/25880 [2:48:40<2:33:03,  1.33it/s]
1|13669|Loss: 0.8117082118988037:  53%|█████▎    | 13668/25880 [2:48:41<2:33:03,  1.33it/s]
1|13669|Loss: 0.8117082118988037:  53%|█████▎    | 13669/25880 [2:48:41<2:29:01,  1.37it/s]
1|13670|Loss: 0.787077784538269:  53%|█████▎    | 13669/25880 [2:48:42<2:29:01,  1.37it/s] 
1|13670|Loss: 0.787077784538269:  53%|█████▎    | 13670/25880 [2:48:42<2:40:04,  1.27it/s]
1|13671|Loss: 0.8485165238380432:  53%|█████▎    | 13670/25880 [2:48:42<2:40:04,  1.27it/s]
1|13671|Loss: 0.8485165238380432:  53%|█████▎    | 13671/25880 [2:48:43<2:35:18,  1.31it/s]
1|13672|Loss: 0.9769980907440186:  53%|█████▎    | 13671/25880 [2:48:43<2:35:18,  1.31it/s]
1|13672|Loss: 0.9769980907440186:  53%|█████▎    | 13672/25880 [2:48:43<2:26:33,  1.39it/s]
1|13673|Loss: 0.7749599814414978:  53%|█████▎    | 13672/25880 [2:48:44<2:26:33,  1.39it/s]
1|13673|Loss: 0.7749599814414978:  53%|█████▎    | 13673/25880 [2:48:44<2:24:34,  1.41it/s]
1|13674|Loss: 0.7202823758125305:  53%|█████▎    | 13673/25880 [2:48:44<2:24:34,  1.41it/s]
1|13674|Loss: 0.7202823758125305:  53%|█████▎    | 13674/25880 [2:48:45<2:18:50,  1.47it/s]
1|13675|Loss: 0.8934446573257446:  53%|█████▎    | 13674/25880 [2:48:45<2:18:50,  1.47it/s]
1|13675|Loss: 0.8934446573257446:  53%|█████▎    | 13675/25880 [2:48:45<2:19:43,  1.46it/s]
1|13676|Loss: 0.6517158150672913:  53%|█████▎    | 13675/25880 [2:48:46<2:19:43,  1.46it/s]
1|13676|Loss: 0.6517158150672913:  53%|█████▎    | 13676/25880 [2:48:46<2:33:15,  1.33it/s]
1|13677|Loss: 0.7777017951011658:  53%|█████▎    | 13676/25880 [2:48:47<2:33:15,  1.33it/s]
1|13677|Loss: 0.7777017951011658:  53%|█████▎    | 13677/25880 [2:48:47<2:34:30,  1.32it/s]
1|13678|Loss: 0.8674048781394958:  53%|█████▎    | 13677/25880 [2:48:47<2:34:30,  1.32it/s]
1|13678|Loss: 0.8674048781394958:  53%|█████▎    | 13678/25880 [2:48:48<2:32:59,  1.33it/s]
1|13679|Loss: 0.7372668385505676:  53%|█████▎    | 13678/25880 [2:48:48<2:32:59,  1.33it/s]
1|13679|Loss: 0.7372668385505676:  53%|█████▎    | 13679/25880 [2:48:48<2:29:59,  1.36it/s]
1|13680|Loss: 0.8211727738380432:  53%|█████▎    | 13679/25880 [2:48:49<2:29:59,  1.36it/s]
1|13680|Loss: 0.8211727738380432:  53%|█████▎    | 13680/25880 [2:48:49<2:23:34,  1.42it/s]
1|13681|Loss: 0.7743576169013977:  53%|█████▎    | 13680/25880 [2:48:49<2:23:34,  1.42it/s]
1|13681|Loss: 0.7743576169013977:  53%|█████▎    | 13681/25880 [2:48:50<2:12:59,  1.53it/s]
1|13682|Loss: 0.9329853653907776:  53%|█████▎    | 13681/25880 [2:48:50<2:12:59,  1.53it/s]
1|13682|Loss: 0.9329853653907776:  53%|█████▎    | 13682/25880 [2:48:50<2:14:59,  1.51it/s]
1|13683|Loss: 0.8183956146240234:  53%|█████▎    | 13682/25880 [2:48:51<2:14:59,  1.51it/s]
1|13683|Loss: 0.8183956146240234:  53%|█████▎    | 13683/25880 [2:48:51<2:26:06,  1.39it/s]
1|13684|Loss: 0.8620589375495911:  53%|█████▎    | 13683/25880 [2:48:52<2:26:06,  1.39it/s]
1|13684|Loss: 0.8620589375495911:  53%|█████▎    | 13684/25880 [2:48:52<2:34:20,  1.32it/s]
1|13685|Loss: 0.880823016166687:  53%|█████▎    | 13684/25880 [2:48:52<2:34:20,  1.32it/s] 
1|13685|Loss: 0.880823016166687:  53%|█████▎    | 13685/25880 [2:48:53<2:25:58,  1.39it/s]
1|13686|Loss: 0.9373077750205994:  53%|█████▎    | 13685/25880 [2:48:53<2:25:58,  1.39it/s]
1|13686|Loss: 0.9373077750205994:  53%|█████▎    | 13686/25880 [2:48:53<2:14:42,  1.51it/s]
1|13687|Loss: 0.7758238911628723:  53%|█████▎    | 13686/25880 [2:48:53<2:14:42,  1.51it/s]
1|13687|Loss: 0.7758238911628723:  53%|█████▎    | 13687/25880 [2:48:54<2:11:44,  1.54it/s]
1|13688|Loss: 0.9296348094940186:  53%|█████▎    | 13687/25880 [2:48:54<2:11:44,  1.54it/s]
1|13688|Loss: 0.9296348094940186:  53%|█████▎    | 13688/25880 [2:48:55<2:22:25,  1.43it/s]
1|13689|Loss: 0.815037190914154:  53%|█████▎    | 13688/25880 [2:48:55<2:22:25,  1.43it/s] 
1|13689|Loss: 0.815037190914154:  53%|█████▎    | 13689/25880 [2:48:55<2:21:45,  1.43it/s]
1|13690|Loss: 0.995150089263916:  53%|█████▎    | 13689/25880 [2:48:56<2:21:45,  1.43it/s]
1|13690|Loss: 0.995150089263916:  53%|█████▎    | 13690/25880 [2:48:56<2:22:34,  1.42it/s]
1|13691|Loss: 0.8656518459320068:  53%|█████▎    | 13690/25880 [2:48:56<2:22:34,  1.42it/s]
1|13691|Loss: 0.8656518459320068:  53%|█████▎    | 13691/25880 [2:48:57<2:17:21,  1.48it/s]
1|13692|Loss: 0.7732473611831665:  53%|█████▎    | 13691/25880 [2:48:57<2:17:21,  1.48it/s]
1|13692|Loss: 0.7732473611831665:  53%|█████▎    | 13692/25880 [2:48:57<2:28:08,  1.37it/s]
1|13693|Loss: 0.8090021014213562:  53%|█████▎    | 13692/25880 [2:48:58<2:28:08,  1.37it/s]
1|13693|Loss: 0.8090021014213562:  53%|█████▎    | 13693/25880 [2:48:58<2:24:44,  1.40it/s]
1|13694|Loss: 0.8749240040779114:  53%|█████▎    | 13693/25880 [2:48:58<2:24:44,  1.40it/s]
1|13694|Loss: 0.8749240040779114:  53%|█████▎    | 13694/25880 [2:48:59<2:15:42,  1.50it/s]
1|13695|Loss: 0.7848296761512756:  53%|█████▎    | 13694/25880 [2:48:59<2:15:42,  1.50it/s]
1|13695|Loss: 0.7848296761512756:  53%|█████▎    | 13695/25880 [2:48:59<2:17:34,  1.48it/s]
1|13696|Loss: 0.7647715210914612:  53%|█████▎    | 13695/25880 [2:49:00<2:17:34,  1.48it/s]
1|13696|Loss: 0.7647715210914612:  53%|█████▎    | 13696/25880 [2:49:00<2:15:33,  1.50it/s]
1|13697|Loss: 1.0010762214660645:  53%|█████▎    | 13696/25880 [2:49:00<2:15:33,  1.50it/s]
1|13697|Loss: 1.0010762214660645:  53%|█████▎    | 13697/25880 [2:49:01<2:18:08,  1.47it/s]
1|13698|Loss: 0.8364377021789551:  53%|█████▎    | 13697/25880 [2:49:01<2:18:08,  1.47it/s]
1|13698|Loss: 0.8364377021789551:  53%|█████▎    | 13698/25880 [2:49:01<2:13:39,  1.52it/s]
1|13699|Loss: 0.9220144152641296:  53%|█████▎    | 13698/25880 [2:49:02<2:13:39,  1.52it/s]
1|13699|Loss: 0.9220144152641296:  53%|█████▎    | 13699/25880 [2:49:02<2:14:53,  1.50it/s]
1|13700|Loss: 0.7864425182342529:  53%|█████▎    | 13699/25880 [2:49:02<2:14:53,  1.50it/s]
1|13700|Loss: 0.7864425182342529:  53%|█████▎    | 13700/25880 [2:49:03<2:31:07,  1.34it/s]
1|13701|Loss: 0.8804396986961365:  53%|█████▎    | 13700/25880 [2:49:03<2:31:07,  1.34it/s]
1|13701|Loss: 0.8804396986961365:  53%|█████▎    | 13701/25880 [2:49:04<2:34:22,  1.31it/s]
1|13702|Loss: 0.8914347290992737:  53%|█████▎    | 13701/25880 [2:49:04<2:34:22,  1.31it/s]
1|13702|Loss: 0.8914347290992737:  53%|█████▎    | 13702/25880 [2:49:04<2:31:24,  1.34it/s]
1|13703|Loss: 0.8404630422592163:  53%|█████▎    | 13702/25880 [2:49:05<2:31:24,  1.34it/s]
1|13703|Loss: 0.8404630422592163:  53%|█████▎    | 13703/25880 [2:49:05<2:35:02,  1.31it/s]
1|13704|Loss: 0.8476110696792603:  53%|█████▎    | 13703/25880 [2:49:06<2:35:02,  1.31it/s]
1|13704|Loss: 0.8476110696792603:  53%|█████▎    | 13704/25880 [2:49:06<2:29:47,  1.35it/s]
1|13705|Loss: 0.7392404079437256:  53%|█████▎    | 13704/25880 [2:49:06<2:29:47,  1.35it/s]
1|13705|Loss: 0.7392404079437256:  53%|█████▎    | 13705/25880 [2:49:07<2:37:02,  1.29it/s]
1|13706|Loss: 0.8949716091156006:  53%|█████▎    | 13705/25880 [2:49:07<2:37:02,  1.29it/s]
1|13706|Loss: 0.8949716091156006:  53%|█████▎    | 13706/25880 [2:49:08<2:42:39,  1.25it/s]
1|13707|Loss: 0.7766532301902771:  53%|█████▎    | 13706/25880 [2:49:08<2:42:39,  1.25it/s]
1|13707|Loss: 0.7766532301902771:  53%|█████▎    | 13707/25880 [2:49:08<2:34:42,  1.31it/s]
1|13708|Loss: 0.9498853087425232:  53%|█████▎    | 13707/25880 [2:49:09<2:34:42,  1.31it/s]
1|13708|Loss: 0.9498853087425232:  53%|█████▎    | 13708/25880 [2:49:09<2:36:03,  1.30it/s]
1|13709|Loss: 0.853781521320343:  53%|█████▎    | 13708/25880 [2:49:09<2:36:03,  1.30it/s] 
1|13709|Loss: 0.853781521320343:  53%|█████▎    | 13709/25880 [2:49:10<2:17:40,  1.47it/s]
1|13710|Loss: 0.7331781387329102:  53%|█████▎    | 13709/25880 [2:49:10<2:17:40,  1.47it/s]
1|13710|Loss: 0.7331781387329102:  53%|█████▎    | 13710/25880 [2:49:10<2:15:22,  1.50it/s]
1|13711|Loss: 0.8248199820518494:  53%|█████▎    | 13710/25880 [2:49:11<2:15:22,  1.50it/s]
1|13711|Loss: 0.8248199820518494:  53%|█████▎    | 13711/25880 [2:49:11<2:18:47,  1.46it/s]
1|13712|Loss: 0.9194835424423218:  53%|█████▎    | 13711/25880 [2:49:11<2:18:47,  1.46it/s]
1|13712|Loss: 0.9194835424423218:  53%|█████▎    | 13712/25880 [2:49:12<2:26:17,  1.39it/s]
1|13713|Loss: 0.9486217498779297:  53%|█████▎    | 13712/25880 [2:49:12<2:26:17,  1.39it/s]
1|13713|Loss: 0.9486217498779297:  53%|█████▎    | 13713/25880 [2:49:12<2:14:26,  1.51it/s]
1|13714|Loss: 0.7399107217788696:  53%|█████▎    | 13713/25880 [2:49:13<2:14:26,  1.51it/s]
1|13714|Loss: 0.7399107217788696:  53%|█████▎    | 13714/25880 [2:49:13<2:19:37,  1.45it/s]
1|13715|Loss: 0.726234495639801:  53%|█████▎    | 13714/25880 [2:49:13<2:19:37,  1.45it/s] 
1|13715|Loss: 0.726234495639801:  53%|█████▎    | 13715/25880 [2:49:14<2:16:09,  1.49it/s]
1|13716|Loss: 0.8663631677627563:  53%|█████▎    | 13715/25880 [2:49:14<2:16:09,  1.49it/s]
1|13716|Loss: 0.8663631677627563:  53%|█████▎    | 13716/25880 [2:49:14<2:05:28,  1.62it/s]
1|13717|Loss: 0.8140265941619873:  53%|█████▎    | 13716/25880 [2:49:14<2:05:28,  1.62it/s]
1|13717|Loss: 0.8140265941619873:  53%|█████▎    | 13717/25880 [2:49:15<2:09:04,  1.57it/s]
1|13718|Loss: 0.7352667450904846:  53%|█████▎    | 13717/25880 [2:49:15<2:09:04,  1.57it/s]
1|13718|Loss: 0.7352667450904846:  53%|█████▎    | 13718/25880 [2:49:16<2:15:19,  1.50it/s]
1|13719|Loss: 0.8731456995010376:  53%|█████▎    | 13718/25880 [2:49:16<2:15:19,  1.50it/s]
1|13719|Loss: 0.8731456995010376:  53%|█████▎    | 13719/25880 [2:49:16<2:22:19,  1.42it/s]
1|13720|Loss: 0.8341975808143616:  53%|█████▎    | 13719/25880 [2:49:17<2:22:19,  1.42it/s]
1|13720|Loss: 0.8341975808143616:  53%|█████▎    | 13720/25880 [2:49:17<2:25:47,  1.39it/s]
1|13721|Loss: 0.8882397413253784:  53%|█████▎    | 13720/25880 [2:49:18<2:25:47,  1.39it/s]
1|13721|Loss: 0.8882397413253784:  53%|█████▎    | 13721/25880 [2:49:18<2:25:47,  1.39it/s]
1|13722|Loss: 0.9050994515419006:  53%|█████▎    | 13721/25880 [2:49:18<2:25:47,  1.39it/s]
1|13722|Loss: 0.9050994515419006:  53%|█████▎    | 13722/25880 [2:49:19<2:26:42,  1.38it/s]
1|13723|Loss: 0.903632402420044:  53%|█████▎    | 13722/25880 [2:49:19<2:26:42,  1.38it/s] 
1|13723|Loss: 0.903632402420044:  53%|█████▎    | 13723/25880 [2:49:19<2:18:47,  1.46it/s]
1|13724|Loss: 0.8900451064109802:  53%|█████▎    | 13723/25880 [2:49:20<2:18:47,  1.46it/s]
1|13724|Loss: 0.8900451064109802:  53%|█████▎    | 13724/25880 [2:49:20<2:22:20,  1.42it/s]
1|13725|Loss: 0.7356734275817871:  53%|█████▎    | 13724/25880 [2:49:20<2:22:20,  1.42it/s]
1|13725|Loss: 0.7356734275817871:  53%|█████▎    | 13725/25880 [2:49:21<2:27:20,  1.37it/s]
1|13726|Loss: 0.8061304688453674:  53%|█████▎    | 13725/25880 [2:49:21<2:27:20,  1.37it/s]
1|13726|Loss: 0.8061304688453674:  53%|█████▎    | 13726/25880 [2:49:22<2:48:00,  1.21it/s]
1|13727|Loss: 0.8333615660667419:  53%|█████▎    | 13726/25880 [2:49:22<2:48:00,  1.21it/s]
1|13727|Loss: 0.8333615660667419:  53%|█████▎    | 13727/25880 [2:49:23<2:52:56,  1.17it/s]
1|13728|Loss: 0.7543926239013672:  53%|█████▎    | 13727/25880 [2:49:23<2:52:56,  1.17it/s]
1|13728|Loss: 0.7543926239013672:  53%|█████▎    | 13728/25880 [2:49:23<2:40:00,  1.27it/s]
1|13729|Loss: 0.7598738670349121:  53%|█████▎    | 13728/25880 [2:49:24<2:40:00,  1.27it/s]
1|13729|Loss: 0.7598738670349121:  53%|█████▎    | 13729/25880 [2:49:24<2:34:08,  1.31it/s]
1|13730|Loss: 0.8807895183563232:  53%|█████▎    | 13729/25880 [2:49:24<2:34:08,  1.31it/s]
1|13730|Loss: 0.8807895183563232:  53%|█████▎    | 13730/25880 [2:49:25<2:18:35,  1.46it/s]
1|13731|Loss: 0.8050360679626465:  53%|█████▎    | 13730/25880 [2:49:25<2:18:35,  1.46it/s]
1|13731|Loss: 0.8050360679626465:  53%|█████▎    | 13731/25880 [2:49:25<2:23:11,  1.41it/s]
1|13732|Loss: 0.8092079758644104:  53%|█████▎    | 13731/25880 [2:49:26<2:23:11,  1.41it/s]
1|13732|Loss: 0.8092079758644104:  53%|█████▎    | 13732/25880 [2:49:26<2:25:08,  1.39it/s]
1|13733|Loss: 0.7746856212615967:  53%|█████▎    | 13732/25880 [2:49:26<2:25:08,  1.39it/s]
1|13733|Loss: 0.7746856212615967:  53%|█████▎    | 13733/25880 [2:49:27<2:30:04,  1.35it/s]
1|13734|Loss: 0.8495054244995117:  53%|█████▎    | 13733/25880 [2:49:27<2:30:04,  1.35it/s]
1|13734|Loss: 0.8495054244995117:  53%|█████▎    | 13734/25880 [2:49:27<2:21:57,  1.43it/s]
1|13735|Loss: 0.9726003408432007:  53%|█████▎    | 13734/25880 [2:49:28<2:21:57,  1.43it/s]
1|13735|Loss: 0.9726003408432007:  53%|█████▎    | 13735/25880 [2:49:28<2:24:22,  1.40it/s]
1|13736|Loss: 0.8142012357711792:  53%|█████▎    | 13735/25880 [2:49:29<2:24:22,  1.40it/s]
1|13736|Loss: 0.8142012357711792:  53%|█████▎    | 13736/25880 [2:49:29<2:20:47,  1.44it/s]
1|13737|Loss: 0.8936662673950195:  53%|█████▎    | 13736/25880 [2:49:29<2:20:47,  1.44it/s]
1|13737|Loss: 0.8936662673950195:  53%|█████▎    | 13737/25880 [2:49:29<2:19:48,  1.45it/s]
1|13738|Loss: 0.8409754633903503:  53%|█████▎    | 13737/25880 [2:49:30<2:19:48,  1.45it/s]
1|13738|Loss: 0.8409754633903503:  53%|█████▎    | 13738/25880 [2:49:30<2:16:43,  1.48it/s]
1|13739|Loss: 0.7850517630577087:  53%|█████▎    | 13738/25880 [2:49:30<2:16:43,  1.48it/s]
1|13739|Loss: 0.7850517630577087:  53%|█████▎    | 13739/25880 [2:49:31<2:13:16,  1.52it/s]
1|13740|Loss: 0.9018287658691406:  53%|█████▎    | 13739/25880 [2:49:31<2:13:16,  1.52it/s]
1|13740|Loss: 0.9018287658691406:  53%|█████▎    | 13740/25880 [2:49:31<2:17:00,  1.48it/s]
1|13741|Loss: 0.8480891585350037:  53%|█████▎    | 13740/25880 [2:49:32<2:17:00,  1.48it/s]
1|13741|Loss: 0.8480891585350037:  53%|█████▎    | 13741/25880 [2:49:32<2:19:36,  1.45it/s]
1|13742|Loss: 0.8181324601173401:  53%|█████▎    | 13741/25880 [2:49:33<2:19:36,  1.45it/s]
1|13742|Loss: 0.8181324601173401:  53%|█████▎    | 13742/25880 [2:49:33<2:16:08,  1.49it/s]
1|13743|Loss: 0.8721924424171448:  53%|█████▎    | 13742/25880 [2:49:33<2:16:08,  1.49it/s]
1|13743|Loss: 0.8721924424171448:  53%|█████▎    | 13743/25880 [2:49:33<2:13:50,  1.51it/s]
1|13744|Loss: 0.9709085822105408:  53%|█████▎    | 13743/25880 [2:49:34<2:13:50,  1.51it/s]
1|13744|Loss: 0.9709085822105408:  53%|█████▎    | 13744/25880 [2:49:34<2:17:02,  1.48it/s]
1|13745|Loss: 0.8802452087402344:  53%|█████▎    | 13744/25880 [2:49:35<2:17:02,  1.48it/s]
1|13745|Loss: 0.8802452087402344:  53%|█████▎    | 13745/25880 [2:49:35<2:10:08,  1.55it/s]
1|13746|Loss: 0.9769628047943115:  53%|█████▎    | 13745/25880 [2:49:35<2:10:08,  1.55it/s]
1|13746|Loss: 0.9769628047943115:  53%|█████▎    | 13746/25880 [2:49:35<2:08:22,  1.58it/s]
1|13747|Loss: 0.8808905482292175:  53%|█████▎    | 13746/25880 [2:49:36<2:08:22,  1.58it/s]
1|13747|Loss: 0.8808905482292175:  53%|█████▎    | 13747/25880 [2:49:36<2:12:07,  1.53it/s]
1|13748|Loss: 0.8852676153182983:  53%|█████▎    | 13747/25880 [2:49:36<2:12:07,  1.53it/s]
1|13748|Loss: 0.8852676153182983:  53%|█████▎    | 13748/25880 [2:49:37<2:14:44,  1.50it/s]
1|13749|Loss: 0.8859257698059082:  53%|█████▎    | 13748/25880 [2:49:37<2:14:44,  1.50it/s]
1|13749|Loss: 0.8859257698059082:  53%|█████▎    | 13749/25880 [2:49:37<2:16:10,  1.48it/s]
1|13750|Loss: 0.717141330242157:  53%|█████▎    | 13749/25880 [2:49:38<2:16:10,  1.48it/s] 
1|13750|Loss: 0.717141330242157:  53%|█████▎    | 13750/25880 [2:49:38<2:24:44,  1.40it/s]
1|13751|Loss: 0.8465954661369324:  53%|█████▎    | 13750/25880 [2:49:39<2:24:44,  1.40it/s]
1|13751|Loss: 0.8465954661369324:  53%|█████▎    | 13751/25880 [2:49:39<2:27:32,  1.37it/s]
1|13752|Loss: 0.8073833584785461:  53%|█████▎    | 13751/25880 [2:49:39<2:27:32,  1.37it/s]
1|13752|Loss: 0.8073833584785461:  53%|█████▎    | 13752/25880 [2:49:40<2:20:23,  1.44it/s]
1|13753|Loss: 0.802915632724762:  53%|█████▎    | 13752/25880 [2:49:40<2:20:23,  1.44it/s] 
1|13753|Loss: 0.802915632724762:  53%|█████▎    | 13753/25880 [2:49:40<2:13:29,  1.51it/s]
1|13754|Loss: 0.8984097242355347:  53%|█████▎    | 13753/25880 [2:49:41<2:13:29,  1.51it/s]
1|13754|Loss: 0.8984097242355347:  53%|█████▎    | 13754/25880 [2:49:41<2:16:13,  1.48it/s]
1|13755|Loss: 0.8795683979988098:  53%|█████▎    | 13754/25880 [2:49:41<2:16:13,  1.48it/s]
1|13755|Loss: 0.8795683979988098:  53%|█████▎    | 13755/25880 [2:49:42<2:20:40,  1.44it/s]
1|13756|Loss: 0.8787199258804321:  53%|█████▎    | 13755/25880 [2:49:42<2:20:40,  1.44it/s]
1|13756|Loss: 0.8787199258804321:  53%|█████▎    | 13756/25880 [2:49:42<2:21:35,  1.43it/s]
1|13757|Loss: 0.7550929188728333:  53%|█████▎    | 13756/25880 [2:49:43<2:21:35,  1.43it/s]
1|13757|Loss: 0.7550929188728333:  53%|█████▎    | 13757/25880 [2:49:43<2:25:29,  1.39it/s]
1|13758|Loss: 0.7587307095527649:  53%|█████▎    | 13757/25880 [2:49:44<2:25:29,  1.39it/s]
1|13758|Loss: 0.7587307095527649:  53%|█████▎    | 13758/25880 [2:49:44<2:27:27,  1.37it/s]
1|13759|Loss: 0.791081428527832:  53%|█████▎    | 13758/25880 [2:49:44<2:27:27,  1.37it/s] 
1|13759|Loss: 0.791081428527832:  53%|█████▎    | 13759/25880 [2:49:45<2:27:35,  1.37it/s]
1|13760|Loss: 0.718752920627594:  53%|█████▎    | 13759/25880 [2:49:45<2:27:35,  1.37it/s]
1|13760|Loss: 0.718752920627594:  53%|█████▎    | 13760/25880 [2:49:45<2:22:40,  1.42it/s]
1|13761|Loss: 0.8180602192878723:  53%|█████▎    | 13760/25880 [2:49:46<2:22:40,  1.42it/s]
1|13761|Loss: 0.8180602192878723:  53%|█████▎    | 13761/25880 [2:49:46<2:27:19,  1.37it/s]
1|13762|Loss: 0.7834029197692871:  53%|█████▎    | 13761/25880 [2:49:46<2:27:19,  1.37it/s]
1|13762|Loss: 0.7834029197692871:  53%|█████▎    | 13762/25880 [2:49:47<2:20:51,  1.43it/s]
1|13763|Loss: 0.8300809860229492:  53%|█████▎    | 13762/25880 [2:49:47<2:20:51,  1.43it/s]
1|13763|Loss: 0.8300809860229492:  53%|█████▎    | 13763/25880 [2:49:47<2:21:32,  1.43it/s]
1|13764|Loss: 0.8993548154830933:  53%|█████▎    | 13763/25880 [2:49:48<2:21:32,  1.43it/s]
1|13764|Loss: 0.8993548154830933:  53%|█████▎    | 13764/25880 [2:49:48<2:16:40,  1.48it/s]
1|13765|Loss: 0.8893334269523621:  53%|█████▎    | 13764/25880 [2:49:48<2:16:40,  1.48it/s]
1|13765|Loss: 0.8893334269523621:  53%|█████▎    | 13765/25880 [2:49:49<2:21:26,  1.43it/s]
1|13766|Loss: 0.84611576795578:  53%|█████▎    | 13765/25880 [2:49:49<2:21:26,  1.43it/s]  
1|13766|Loss: 0.84611576795578:  53%|█████▎    | 13766/25880 [2:49:50<2:35:26,  1.30it/s]
1|13767|Loss: 0.7503264546394348:  53%|█████▎    | 13766/25880 [2:49:50<2:35:26,  1.30it/s]
1|13767|Loss: 0.7503264546394348:  53%|█████▎    | 13767/25880 [2:49:50<2:34:13,  1.31it/s]
1|13768|Loss: 0.8521745204925537:  53%|█████▎    | 13767/25880 [2:49:51<2:34:13,  1.31it/s]
1|13768|Loss: 0.8521745204925537:  53%|█████▎    | 13768/25880 [2:49:51<2:25:48,  1.38it/s]
1|13769|Loss: 0.8270602822303772:  53%|█████▎    | 13768/25880 [2:49:51<2:25:48,  1.38it/s]
1|13769|Loss: 0.8270602822303772:  53%|█████▎    | 13769/25880 [2:49:52<2:28:16,  1.36it/s]
1|13770|Loss: 0.8558722138404846:  53%|█████▎    | 13769/25880 [2:49:52<2:28:16,  1.36it/s]
1|13770|Loss: 0.8558722138404846:  53%|█████▎    | 13770/25880 [2:49:53<2:36:07,  1.29it/s]
1|13771|Loss: 0.8828040957450867:  53%|█████▎    | 13770/25880 [2:49:53<2:36:07,  1.29it/s]
1|13771|Loss: 0.8828040957450867:  53%|█████▎    | 13771/25880 [2:49:53<2:34:06,  1.31it/s]
1|13772|Loss: 1.0176881551742554:  53%|█████▎    | 13771/25880 [2:49:54<2:34:06,  1.31it/s]
1|13772|Loss: 1.0176881551742554:  53%|█████▎    | 13772/25880 [2:49:54<2:22:57,  1.41it/s]
1|13773|Loss: 0.7962873578071594:  53%|█████▎    | 13772/25880 [2:49:54<2:22:57,  1.41it/s]
1|13773|Loss: 0.7962873578071594:  53%|█████▎    | 13773/25880 [2:49:55<2:24:34,  1.40it/s]
1|13774|Loss: 0.8088251352310181:  53%|█████▎    | 13773/25880 [2:49:55<2:24:34,  1.40it/s]
1|13774|Loss: 0.8088251352310181:  53%|█████▎    | 13774/25880 [2:49:56<2:26:40,  1.38it/s]
1|13775|Loss: 0.749912440776825:  53%|█████▎    | 13774/25880 [2:49:56<2:26:40,  1.38it/s] 
1|13775|Loss: 0.749912440776825:  53%|█████▎    | 13775/25880 [2:49:56<2:25:59,  1.38it/s]
1|13776|Loss: 0.8178665637969971:  53%|█████▎    | 13775/25880 [2:49:57<2:25:59,  1.38it/s]
1|13776|Loss: 0.8178665637969971:  53%|█████▎    | 13776/25880 [2:49:57<2:25:50,  1.38it/s]
1|13777|Loss: 0.8448143005371094:  53%|█████▎    | 13776/25880 [2:49:57<2:25:50,  1.38it/s]
1|13777|Loss: 0.8448143005371094:  53%|█████▎    | 13777/25880 [2:49:58<2:24:20,  1.40it/s]
1|13778|Loss: 0.8238478899002075:  53%|█████▎    | 13777/25880 [2:49:58<2:24:20,  1.40it/s]
1|13778|Loss: 0.8238478899002075:  53%|█████▎    | 13778/25880 [2:49:58<2:23:01,  1.41it/s]
1|13779|Loss: 0.9006943702697754:  53%|█████▎    | 13778/25880 [2:49:59<2:23:01,  1.41it/s]
1|13779|Loss: 0.9006943702697754:  53%|█████▎    | 13779/25880 [2:49:59<2:17:55,  1.46it/s]
1|13780|Loss: 0.8467866778373718:  53%|█████▎    | 13779/25880 [2:49:59<2:17:55,  1.46it/s]
1|13780|Loss: 0.8467866778373718:  53%|█████▎    | 13780/25880 [2:50:00<2:19:24,  1.45it/s]
1|13781|Loss: 0.8147264122962952:  53%|█████▎    | 13780/25880 [2:50:00<2:19:24,  1.45it/s]
1|13781|Loss: 0.8147264122962952:  53%|█████▎    | 13781/25880 [2:50:00<2:21:43,  1.42it/s]
1|13782|Loss: 0.7686182856559753:  53%|█████▎    | 13781/25880 [2:50:01<2:21:43,  1.42it/s]
1|13782|Loss: 0.7686182856559753:  53%|█████▎    | 13782/25880 [2:50:01<2:21:51,  1.42it/s]
1|13783|Loss: 0.817909300327301:  53%|█████▎    | 13782/25880 [2:50:01<2:21:51,  1.42it/s] 
1|13783|Loss: 0.817909300327301:  53%|█████▎    | 13783/25880 [2:50:02<2:18:23,  1.46it/s]
1|13784|Loss: 0.8140740394592285:  53%|█████▎    | 13783/25880 [2:50:02<2:18:23,  1.46it/s]
1|13784|Loss: 0.8140740394592285:  53%|█████▎    | 13784/25880 [2:50:02<2:15:30,  1.49it/s]
1|13785|Loss: 0.7638179063796997:  53%|█████▎    | 13784/25880 [2:50:03<2:15:30,  1.49it/s]
1|13785|Loss: 0.7638179063796997:  53%|█████▎    | 13785/25880 [2:50:03<2:17:46,  1.46it/s]
1|13786|Loss: 0.9119718670845032:  53%|█████▎    | 13785/25880 [2:50:03<2:17:46,  1.46it/s]
1|13786|Loss: 0.9119718670845032:  53%|█████▎    | 13786/25880 [2:50:04<2:16:00,  1.48it/s]
1|13787|Loss: 0.8593266010284424:  53%|█████▎    | 13786/25880 [2:50:04<2:16:00,  1.48it/s]
1|13787|Loss: 0.8593266010284424:  53%|█████▎    | 13787/25880 [2:50:04<2:18:04,  1.46it/s]
1|13788|Loss: 0.857978343963623:  53%|█████▎    | 13787/25880 [2:50:05<2:18:04,  1.46it/s] 
1|13788|Loss: 0.857978343963623:  53%|█████▎    | 13788/25880 [2:50:05<2:25:11,  1.39it/s]
1|13789|Loss: 0.9177829027175903:  53%|█████▎    | 13788/25880 [2:50:06<2:25:11,  1.39it/s]
1|13789|Loss: 0.9177829027175903:  53%|█████▎    | 13789/25880 [2:50:06<2:18:26,  1.46it/s]
1|13790|Loss: 0.7681501507759094:  53%|█████▎    | 13789/25880 [2:50:06<2:18:26,  1.46it/s]
1|13790|Loss: 0.7681501507759094:  53%|█████▎    | 13790/25880 [2:50:06<2:13:21,  1.51it/s]
1|13791|Loss: 0.8687875270843506:  53%|█████▎    | 13790/25880 [2:50:07<2:13:21,  1.51it/s]
1|13791|Loss: 0.8687875270843506:  53%|█████▎    | 13791/25880 [2:50:07<2:16:56,  1.47it/s]
1|13792|Loss: 1.0128161907196045:  53%|█████▎    | 13791/25880 [2:50:08<2:16:56,  1.47it/s]
1|13792|Loss: 1.0128161907196045:  53%|█████▎    | 13792/25880 [2:50:08<2:31:46,  1.33it/s]
1|13793|Loss: 0.8829226493835449:  53%|█████▎    | 13792/25880 [2:50:09<2:31:46,  1.33it/s]
1|13793|Loss: 0.8829226493835449:  53%|█████▎    | 13793/25880 [2:50:09<2:36:27,  1.29it/s]
1|13794|Loss: 0.8649682402610779:  53%|█████▎    | 13793/25880 [2:50:09<2:36:27,  1.29it/s]
1|13794|Loss: 0.8649682402610779:  53%|█████▎    | 13794/25880 [2:50:10<2:35:49,  1.29it/s]
1|13795|Loss: 0.851729154586792:  53%|█████▎    | 13794/25880 [2:50:10<2:35:49,  1.29it/s] 
1|13795|Loss: 0.851729154586792:  53%|█████▎    | 13795/25880 [2:50:10<2:28:44,  1.35it/s]
1|13796|Loss: 0.9124466776847839:  53%|█████▎    | 13795/25880 [2:50:11<2:28:44,  1.35it/s]
1|13796|Loss: 0.9124466776847839:  53%|█████▎    | 13796/25880 [2:50:11<2:30:15,  1.34it/s]
1|13797|Loss: 0.9179619550704956:  53%|█████▎    | 13796/25880 [2:50:12<2:30:15,  1.34it/s]
1|13797|Loss: 0.9179619550704956:  53%|█████▎    | 13797/25880 [2:50:12<2:30:07,  1.34it/s]
1|13798|Loss: 0.9575324654579163:  53%|█████▎    | 13797/25880 [2:50:12<2:30:07,  1.34it/s]
1|13798|Loss: 0.9575324654579163:  53%|█████▎    | 13798/25880 [2:50:12<2:15:19,  1.49it/s]
1|13799|Loss: 0.7616113424301147:  53%|█████▎    | 13798/25880 [2:50:13<2:15:19,  1.49it/s]
1|13799|Loss: 0.7616113424301147:  53%|█████▎    | 13799/25880 [2:50:13<2:13:33,  1.51it/s]
1|13800|Loss: 0.7916103601455688:  53%|█████▎    | 13799/25880 [2:50:13<2:13:33,  1.51it/s]
1|13800|Loss: 0.7916103601455688:  53%|█████▎    | 13800/25880 [2:50:14<2:15:59,  1.48it/s]
1|13801|Loss: 0.7289191484451294:  53%|█████▎    | 13800/25880 [2:50:14<2:15:59,  1.48it/s]
1|13801|Loss: 0.7289191484451294:  53%|█████▎    | 13801/25880 [2:50:15<2:26:04,  1.38it/s]
1|13802|Loss: 0.8673063516616821:  53%|█████▎    | 13801/25880 [2:50:15<2:26:04,  1.38it/s]
1|13802|Loss: 0.8673063516616821:  53%|█████▎    | 13802/25880 [2:50:15<2:28:51,  1.35it/s]
1|13803|Loss: 0.8104038834571838:  53%|█████▎    | 13802/25880 [2:50:16<2:28:51,  1.35it/s]
1|13803|Loss: 0.8104038834571838:  53%|█████▎    | 13803/25880 [2:50:16<2:32:56,  1.32it/s]
1|13804|Loss: 0.7493013143539429:  53%|█████▎    | 13803/25880 [2:50:17<2:32:56,  1.32it/s]
1|13804|Loss: 0.7493013143539429:  53%|█████▎    | 13804/25880 [2:50:17<2:32:55,  1.32it/s]
1|13805|Loss: 0.8525524139404297:  53%|█████▎    | 13804/25880 [2:50:17<2:32:55,  1.32it/s]
1|13805|Loss: 0.8525524139404297:  53%|█████▎    | 13805/25880 [2:50:17<2:17:41,  1.46it/s]
1|13806|Loss: 0.8114526271820068:  53%|█████▎    | 13805/25880 [2:50:18<2:17:41,  1.46it/s]
1|13806|Loss: 0.8114526271820068:  53%|█████▎    | 13806/25880 [2:50:18<2:21:54,  1.42it/s]
1|13807|Loss: 0.7428978681564331:  53%|█████▎    | 13806/25880 [2:50:19<2:21:54,  1.42it/s]
1|13807|Loss: 0.7428978681564331:  53%|█████▎    | 13807/25880 [2:50:19<2:19:46,  1.44it/s]
1|13808|Loss: 0.8674448132514954:  53%|█████▎    | 13807/25880 [2:50:19<2:19:46,  1.44it/s]
1|13808|Loss: 0.8674448132514954:  53%|█████▎    | 13808/25880 [2:50:20<2:19:21,  1.44it/s]
1|13809|Loss: 0.8396016359329224:  53%|█████▎    | 13808/25880 [2:50:20<2:19:21,  1.44it/s]
1|13809|Loss: 0.8396016359329224:  53%|█████▎    | 13809/25880 [2:50:20<2:11:24,  1.53it/s]
1|13810|Loss: 0.7812885642051697:  53%|█████▎    | 13809/25880 [2:50:20<2:11:24,  1.53it/s]
1|13810|Loss: 0.7812885642051697:  53%|█████▎    | 13810/25880 [2:50:21<2:18:23,  1.45it/s]
1|13811|Loss: 0.8105898499488831:  53%|█████▎    | 13810/25880 [2:50:21<2:18:23,  1.45it/s]
1|13811|Loss: 0.8105898499488831:  53%|█████▎    | 13811/25880 [2:50:21<2:12:27,  1.52it/s]
1|13812|Loss: 0.830105721950531:  53%|█████▎    | 13811/25880 [2:50:22<2:12:27,  1.52it/s] 
1|13812|Loss: 0.830105721950531:  53%|█████▎    | 13812/25880 [2:50:22<2:05:50,  1.60it/s]
1|13813|Loss: 0.8893874287605286:  53%|█████▎    | 13812/25880 [2:50:22<2:05:50,  1.60it/s]
1|13813|Loss: 0.8893874287605286:  53%|█████▎    | 13813/25880 [2:50:23<2:05:32,  1.60it/s]
1|13814|Loss: 0.8382753133773804:  53%|█████▎    | 13813/25880 [2:50:23<2:05:32,  1.60it/s]
1|13814|Loss: 0.8382753133773804:  53%|█████▎    | 13814/25880 [2:50:23<2:05:19,  1.60it/s]
1|13815|Loss: 1.0000574588775635:  53%|█████▎    | 13814/25880 [2:50:24<2:05:19,  1.60it/s]
1|13815|Loss: 1.0000574588775635:  53%|█████▎    | 13815/25880 [2:50:24<2:08:54,  1.56it/s]
1|13816|Loss: 0.8555265069007874:  53%|█████▎    | 13815/25880 [2:50:24<2:08:54,  1.56it/s]
1|13816|Loss: 0.8555265069007874:  53%|█████▎    | 13816/25880 [2:50:25<2:14:09,  1.50it/s]
1|13817|Loss: 0.8859805464744568:  53%|█████▎    | 13816/25880 [2:50:25<2:14:09,  1.50it/s]
1|13817|Loss: 0.8859805464744568:  53%|█████▎    | 13817/25880 [2:50:25<2:13:35,  1.51it/s]
1|13818|Loss: 0.7851577401161194:  53%|█████▎    | 13817/25880 [2:50:26<2:13:35,  1.51it/s]
1|13818|Loss: 0.7851577401161194:  53%|█████▎    | 13818/25880 [2:50:26<2:29:49,  1.34it/s]
1|13819|Loss: 0.7377147078514099:  53%|█████▎    | 13818/25880 [2:50:27<2:29:49,  1.34it/s]
1|13819|Loss: 0.7377147078514099:  53%|█████▎    | 13819/25880 [2:50:27<2:32:59,  1.31it/s]
1|13820|Loss: 0.7248689532279968:  53%|█████▎    | 13819/25880 [2:50:27<2:32:59,  1.31it/s]
1|13820|Loss: 0.7248689532279968:  53%|█████▎    | 13820/25880 [2:50:28<2:24:23,  1.39it/s]
1|13821|Loss: 0.895078718662262:  53%|█████▎    | 13820/25880 [2:50:28<2:24:23,  1.39it/s] 
1|13821|Loss: 0.895078718662262:  53%|█████▎    | 13821/25880 [2:50:28<2:28:51,  1.35it/s]
1|13822|Loss: 0.8133408427238464:  53%|█████▎    | 13821/25880 [2:50:29<2:28:51,  1.35it/s]
1|13822|Loss: 0.8133408427238464:  53%|█████▎    | 13822/25880 [2:50:29<2:28:37,  1.35it/s]
1|13823|Loss: 0.9448274970054626:  53%|█████▎    | 13822/25880 [2:50:30<2:28:37,  1.35it/s]
1|13823|Loss: 0.9448274970054626:  53%|█████▎    | 13823/25880 [2:50:30<2:23:08,  1.40it/s]
1|13824|Loss: 0.7922089695930481:  53%|█████▎    | 13823/25880 [2:50:30<2:23:08,  1.40it/s]
1|13824|Loss: 0.7922089695930481:  53%|█████▎    | 13824/25880 [2:50:31<2:29:56,  1.34it/s]
1|13825|Loss: 0.8513449430465698:  53%|█████▎    | 13824/25880 [2:50:31<2:29:56,  1.34it/s]
1|13825|Loss: 0.8513449430465698:  53%|█████▎    | 13825/25880 [2:50:31<2:22:39,  1.41it/s]
1|13826|Loss: 0.8352192044258118:  53%|█████▎    | 13825/25880 [2:50:32<2:22:39,  1.41it/s]
1|13826|Loss: 0.8352192044258118:  53%|█████▎    | 13826/25880 [2:50:32<2:24:55,  1.39it/s]
1|13827|Loss: 0.8090517520904541:  53%|█████▎    | 13826/25880 [2:50:32<2:24:55,  1.39it/s]
1|13827|Loss: 0.8090517520904541:  53%|█████▎    | 13827/25880 [2:50:33<2:28:55,  1.35it/s]
1|13828|Loss: 0.844399631023407:  53%|█████▎    | 13827/25880 [2:50:33<2:28:55,  1.35it/s] 
1|13828|Loss: 0.844399631023407:  53%|█████▎    | 13828/25880 [2:50:34<2:33:37,  1.31it/s]
1|13829|Loss: 0.8526566028594971:  53%|█████▎    | 13828/25880 [2:50:34<2:33:37,  1.31it/s]
1|13829|Loss: 0.8526566028594971:  53%|█████▎    | 13829/25880 [2:50:34<2:28:04,  1.36it/s]
1|13830|Loss: 0.8031892776489258:  53%|█████▎    | 13829/25880 [2:50:35<2:28:04,  1.36it/s]
1|13830|Loss: 0.8031892776489258:  53%|█████▎    | 13830/25880 [2:50:35<2:22:05,  1.41it/s]
1|13831|Loss: 0.8608541488647461:  53%|█████▎    | 13830/25880 [2:50:35<2:22:05,  1.41it/s]
1|13831|Loss: 0.8608541488647461:  53%|█████▎    | 13831/25880 [2:50:36<2:23:21,  1.40it/s]
1|13832|Loss: 0.8935276865959167:  53%|█████▎    | 13831/25880 [2:50:36<2:23:21,  1.40it/s]
1|13832|Loss: 0.8935276865959167:  53%|█████▎    | 13832/25880 [2:50:37<2:31:30,  1.33it/s]
1|13833|Loss: 0.8798424601554871:  53%|█████▎    | 13832/25880 [2:50:37<2:31:30,  1.33it/s]
1|13833|Loss: 0.8798424601554871:  53%|█████▎    | 13833/25880 [2:50:37<2:30:25,  1.33it/s]
1|13834|Loss: 0.7701447010040283:  53%|█████▎    | 13833/25880 [2:50:38<2:30:25,  1.33it/s]
1|13834|Loss: 0.7701447010040283:  53%|█████▎    | 13834/25880 [2:50:38<2:33:54,  1.30it/s]
1|13835|Loss: 0.798328697681427:  53%|█████▎    | 13834/25880 [2:50:39<2:33:54,  1.30it/s] 
1|13835|Loss: 0.798328697681427:  53%|█████▎    | 13835/25880 [2:50:39<2:38:34,  1.27it/s]
1|13836|Loss: 0.8700213432312012:  53%|█████▎    | 13835/25880 [2:50:39<2:38:34,  1.27it/s]
1|13836|Loss: 0.8700213432312012:  53%|█████▎    | 13836/25880 [2:50:40<2:40:04,  1.25it/s]
1|13837|Loss: 1.0051093101501465:  53%|█████▎    | 13836/25880 [2:50:40<2:40:04,  1.25it/s]
1|13837|Loss: 1.0051093101501465:  53%|█████▎    | 13837/25880 [2:50:41<2:43:38,  1.23it/s]
1|13838|Loss: 0.7812015414237976:  53%|█████▎    | 13837/25880 [2:50:41<2:43:38,  1.23it/s]
1|13838|Loss: 0.7812015414237976:  53%|█████▎    | 13838/25880 [2:50:41<2:44:26,  1.22it/s]
1|13839|Loss: 0.879226565361023:  53%|█████▎    | 13838/25880 [2:50:42<2:44:26,  1.22it/s] 
1|13839|Loss: 0.879226565361023:  53%|█████▎    | 13839/25880 [2:50:42<2:32:36,  1.32it/s]
1|13840|Loss: 0.7941594123840332:  53%|█████▎    | 13839/25880 [2:50:42<2:32:36,  1.32it/s]
1|13840|Loss: 0.7941594123840332:  53%|█████▎    | 13840/25880 [2:50:43<2:32:21,  1.32it/s]
1|13841|Loss: 0.8494064211845398:  53%|█████▎    | 13840/25880 [2:50:43<2:32:21,  1.32it/s]
1|13841|Loss: 0.8494064211845398:  53%|█████▎    | 13841/25880 [2:50:43<2:24:09,  1.39it/s]
1|13842|Loss: 0.8042106628417969:  53%|█████▎    | 13841/25880 [2:50:44<2:24:09,  1.39it/s]
1|13842|Loss: 0.8042106628417969:  53%|█████▎    | 13842/25880 [2:50:44<2:12:08,  1.52it/s]
1|13843|Loss: 0.8281398415565491:  53%|█████▎    | 13842/25880 [2:50:44<2:12:08,  1.52it/s]
1|13843|Loss: 0.8281398415565491:  53%|█████▎    | 13843/25880 [2:50:45<2:24:26,  1.39it/s]
1|13844|Loss: 0.7634624242782593:  53%|█████▎    | 13843/25880 [2:50:45<2:24:26,  1.39it/s]
1|13844|Loss: 0.7634624242782593:  53%|█████▎    | 13844/25880 [2:50:46<2:25:57,  1.37it/s]
1|13845|Loss: 0.9216071367263794:  53%|█████▎    | 13844/25880 [2:50:46<2:25:57,  1.37it/s]
1|13845|Loss: 0.9216071367263794:  53%|█████▎    | 13845/25880 [2:50:46<2:12:02,  1.52it/s]
1|13846|Loss: 0.9428682327270508:  53%|█████▎    | 13845/25880 [2:50:46<2:12:02,  1.52it/s]
1|13846|Loss: 0.9428682327270508:  54%|█████▎    | 13846/25880 [2:50:47<2:11:25,  1.53it/s]
1|13847|Loss: 0.8542450666427612:  54%|█████▎    | 13846/25880 [2:50:47<2:11:25,  1.53it/s]
1|13847|Loss: 0.8542450666427612:  54%|█████▎    | 13847/25880 [2:50:47<2:11:10,  1.53it/s]
1|13848|Loss: 0.7575138211250305:  54%|█████▎    | 13847/25880 [2:50:48<2:11:10,  1.53it/s]
1|13848|Loss: 0.7575138211250305:  54%|█████▎    | 13848/25880 [2:50:48<2:14:39,  1.49it/s]
1|13849|Loss: 0.804002583026886:  54%|█████▎    | 13848/25880 [2:50:48<2:14:39,  1.49it/s] 
1|13849|Loss: 0.804002583026886:  54%|█████▎    | 13849/25880 [2:50:49<2:11:09,  1.53it/s]
1|13850|Loss: 0.8417136073112488:  54%|█████▎    | 13849/25880 [2:50:49<2:11:09,  1.53it/s]
1|13850|Loss: 0.8417136073112488:  54%|█████▎    | 13850/25880 [2:50:49<2:06:56,  1.58it/s]
1|13851|Loss: 0.8487523198127747:  54%|█████▎    | 13850/25880 [2:50:50<2:06:56,  1.58it/s]
1|13851|Loss: 0.8487523198127747:  54%|█████▎    | 13851/25880 [2:50:50<2:16:40,  1.47it/s]
1|13852|Loss: 0.7397704124450684:  54%|█████▎    | 13851/25880 [2:50:50<2:16:40,  1.47it/s]
1|13852|Loss: 0.7397704124450684:  54%|█████▎    | 13852/25880 [2:50:51<2:14:09,  1.49it/s]
1|13853|Loss: 0.8399876952171326:  54%|█████▎    | 13852/25880 [2:50:51<2:14:09,  1.49it/s]
1|13853|Loss: 0.8399876952171326:  54%|█████▎    | 13853/25880 [2:50:51<2:16:13,  1.47it/s]
1|13854|Loss: 0.896051287651062:  54%|█████▎    | 13853/25880 [2:50:52<2:16:13,  1.47it/s] 
1|13854|Loss: 0.896051287651062:  54%|█████▎    | 13854/25880 [2:50:52<2:06:10,  1.59it/s]
1|13855|Loss: 0.8647993803024292:  54%|███��█▎    | 13854/25880 [2:50:52<2:06:10,  1.59it/s]
1|13855|Loss: 0.8647993803024292:  54%|█████▎    | 13855/25880 [2:50:53<2:04:14,  1.61it/s]
1|13856|Loss: 1.0366233587265015:  54%|█████▎    | 13855/25880 [2:50:53<2:04:14,  1.61it/s]
1|13856|Loss: 1.0366233587265015:  54%|█████▎    | 13856/25880 [2:50:53<2:13:37,  1.50it/s]
1|13857|Loss: 0.8406164050102234:  54%|█████▎    | 13856/25880 [2:50:54<2:13:37,  1.50it/s]
1|13857|Loss: 0.8406164050102234:  54%|█████▎    | 13857/25880 [2:50:54<2:01:08,  1.65it/s]
1|13858|Loss: 0.8624616265296936:  54%|█████▎    | 13857/25880 [2:50:54<2:01:08,  1.65it/s]
1|13858|Loss: 0.8624616265296936:  54%|█████▎    | 13858/25880 [2:50:54<2:02:49,  1.63it/s]
1|13859|Loss: 0.7727683186531067:  54%|█████▎    | 13858/25880 [2:50:55<2:02:49,  1.63it/s]
1|13859|Loss: 0.7727683186531067:  54%|█████▎    | 13859/25880 [2:50:55<2:18:19,  1.45it/s]
1|13860|Loss: 0.8561955690383911:  54%|█████▎    | 13859/25880 [2:50:56<2:18:19,  1.45it/s]
1|13860|Loss: 0.8561955690383911:  54%|█████▎    | 13860/25880 [2:50:56<2:25:10,  1.38it/s]
1|13861|Loss: 0.8304926156997681:  54%|█████▎    | 13860/25880 [2:50:56<2:25:10,  1.38it/s]
1|13861|Loss: 0.8304926156997681:  54%|█████▎    | 13861/25880 [2:50:57<2:29:23,  1.34it/s]
1|13862|Loss: 0.7240566611289978:  54%|█████▎    | 13861/25880 [2:50:57<2:29:23,  1.34it/s]
1|13862|Loss: 0.7240566611289978:  54%|█████▎    | 13862/25880 [2:50:58<2:31:43,  1.32it/s]
1|13863|Loss: 0.7869057059288025:  54%|█████▎    | 13862/25880 [2:50:58<2:31:43,  1.32it/s]
1|13863|Loss: 0.7869057059288025:  54%|█████▎    | 13863/25880 [2:50:58<2:33:39,  1.30it/s]
1|13864|Loss: 0.7001127004623413:  54%|█████▎    | 13863/25880 [2:50:59<2:33:39,  1.30it/s]
1|13864|Loss: 0.7001127004623413:  54%|█████▎    | 13864/25880 [2:50:59<2:23:35,  1.39it/s]
1|13865|Loss: 0.7669967412948608:  54%|█████▎    | 13864/25880 [2:50:59<2:23:35,  1.39it/s]
1|13865|Loss: 0.7669967412948608:  54%|█████▎    | 13865/25880 [2:51:00<2:28:15,  1.35it/s]
1|13866|Loss: 0.7766451835632324:  54%|█████▎    | 13865/25880 [2:51:00<2:28:15,  1.35it/s]
1|13866|Loss: 0.7766451835632324:  54%|█████▎    | 13866/25880 [2:51:00<2:23:53,  1.39it/s]
1|13867|Loss: 0.8190165162086487:  54%|█████▎    | 13866/25880 [2:51:01<2:23:53,  1.39it/s]
1|13867|Loss: 0.8190165162086487:  54%|█████▎    | 13867/25880 [2:51:01<2:22:05,  1.41it/s]
1|13868|Loss: 0.9816964268684387:  54%|█████▎    | 13867/25880 [2:51:02<2:22:05,  1.41it/s]
1|13868|Loss: 0.9816964268684387:  54%|█████▎    | 13868/25880 [2:51:02<2:21:01,  1.42it/s]
1|13869|Loss: 0.8481084704399109:  54%|█████▎    | 13868/25880 [2:51:02<2:21:01,  1.42it/s]
1|13869|Loss: 0.8481084704399109:  54%|█████▎    | 13869/25880 [2:51:03<2:25:39,  1.37it/s]
1|13870|Loss: 0.7052597999572754:  54%|█████▎    | 13869/25880 [2:51:03<2:25:39,  1.37it/s]
1|13870|Loss: 0.7052597999572754:  54%|█████▎    | 13870/25880 [2:51:03<2:26:31,  1.37it/s]
1|13871|Loss: 0.755096435546875:  54%|█████▎    | 13870/25880 [2:51:04<2:26:31,  1.37it/s] 
1|13871|Loss: 0.755096435546875:  54%|█████▎    | 13871/25880 [2:51:04<2:12:40,  1.51it/s]
1|13872|Loss: 0.9070200324058533:  54%|█████▎    | 13871/25880 [2:51:04<2:12:40,  1.51it/s]
1|13872|Loss: 0.9070200324058533:  54%|█████▎    | 13872/25880 [2:51:05<2:11:24,  1.52it/s]
1|13873|Loss: 0.8885678052902222:  54%|█████▎    | 13872/25880 [2:51:05<2:11:24,  1.52it/s]
1|13873|Loss: 0.8885678052902222:  54%|█████▎    | 13873/25880 [2:51:05<2:05:28,  1.59it/s]
1|13874|Loss: 0.8399993777275085:  54%|█████▎    | 13873/25880 [2:51:05<2:05:28,  1.59it/s]
1|13874|Loss: 0.8399993777275085:  54%|█████▎    | 13874/25880 [2:51:06<2:03:28,  1.62it/s]
1|13875|Loss: 0.8083924651145935:  54%|█████▎    | 13874/25880 [2:51:06<2:03:28,  1.62it/s]
1|13875|Loss: 0.8083924651145935:  54%|█████▎    | 13875/25880 [2:51:06<1:57:58,  1.70it/s]
1|13876|Loss: 0.7817401885986328:  54%|█████▎    | 13875/25880 [2:51:07<1:57:58,  1.70it/s]
1|13876|Loss: 0.7817401885986328:  54%|█████▎    | 13876/25880 [2:51:07<2:06:08,  1.59it/s]
1|13877|Loss: 0.8364918231964111:  54%|█████▎    | 13876/25880 [2:51:07<2:06:08,  1.59it/s]
1|13877|Loss: 0.8364918231964111:  54%|█████▎    | 13877/25880 [2:51:08<2:13:03,  1.50it/s]
1|13878|Loss: 0.8755236268043518:  54%|█████▎    | 13877/25880 [2:51:08<2:13:03,  1.50it/s]
1|13878|Loss: 0.8755236268043518:  54%|█████▎    | 13878/25880 [2:51:08<2:17:20,  1.46it/s]
1|13879|Loss: 0.6670306324958801:  54%|█████▎    | 13878/25880 [2:51:09<2:17:20,  1.46it/s]
1|13879|Loss: 0.6670306324958801:  54%|█████▎    | 13879/25880 [2:51:09<2:19:50,  1.43it/s]
1|13880|Loss: 1.013048768043518:  54%|█████▎    | 13879/25880 [2:51:09<2:19:50,  1.43it/s] 
1|13880|Loss: 1.013048768043518:  54%|█████▎    | 13880/25880 [2:51:10<2:11:55,  1.52it/s]
1|13881|Loss: 0.8080711364746094:  54%|█████▎    | 13880/25880 [2:51:10<2:11:55,  1.52it/s]
1|13881|Loss: 0.8080711364746094:  54%|█████▎    | 13881/25880 [2:51:10<2:11:58,  1.52it/s]
1|13882|Loss: 0.8315617442131042:  54%|█████▎    | 13881/25880 [2:51:11<2:11:58,  1.52it/s]
1|13882|Loss: 0.8315617442131042:  54%|█████▎    | 13882/25880 [2:51:11<2:05:45,  1.59it/s]
1|13883|Loss: 0.920204758644104:  54%|█████▎    | 13882/25880 [2:51:11<2:05:45,  1.59it/s] 
1|13883|Loss: 0.920204758644104:  54%|█████▎    | 13883/25880 [2:51:12<2:18:05,  1.45it/s]
1|13884|Loss: 0.8391125798225403:  54%|█████▎    | 13883/25880 [2:51:12<2:18:05,  1.45it/s]
1|13884|Loss: 0.8391125798225403:  54%|█████▎    | 13884/25880 [2:51:13<2:22:48,  1.40it/s]
1|13885|Loss: 0.8483107686042786:  54%|█████▎    | 13884/25880 [2:51:13<2:22:48,  1.40it/s]
1|13885|Loss: 0.8483107686042786:  54%|█████▎    | 13885/25880 [2:51:13<2:22:57,  1.40it/s]
1|13886|Loss: 1.0058073997497559:  54%|█████▎    | 13885/25880 [2:51:14<2:22:57,  1.40it/s]
1|13886|Loss: 1.0058073997497559:  54%|█████▎    | 13886/25880 [2:51:14<2:22:34,  1.40it/s]
1|13887|Loss: 0.8757152557373047:  54%|█████▎    | 13886/25880 [2:51:14<2:22:34,  1.40it/s]
1|13887|Loss: 0.8757152557373047:  54%|█████▎    | 13887/25880 [2:51:15<2:22:59,  1.40it/s]
1|13888|Loss: 0.836979329586029:  54%|█████▎    | 13887/25880 [2:51:15<2:22:59,  1.40it/s] 
1|13888|Loss: 0.836979329586029:  54%|█████▎    | 13888/25880 [2:51:15<2:17:52,  1.45it/s]
1|13889|Loss: 0.8051499724388123:  54%|█████▎    | 13888/25880 [2:51:16<2:17:52,  1.45it/s]
1|13889|Loss: 0.8051499724388123:  54%|█████▎    | 13889/25880 [2:51:16<2:18:31,  1.44it/s]
1|13890|Loss: 0.9374513626098633:  54%|█████▎    | 13889/25880 [2:51:16<2:18:31,  1.44it/s]
1|13890|Loss: 0.9374513626098633:  54%|█████▎    | 13890/25880 [2:51:17<2:16:16,  1.47it/s]
1|13891|Loss: 0.8452901840209961:  54%|█████▎    | 13890/25880 [2:51:17<2:16:16,  1.47it/s]
1|13891|Loss: 0.8452901840209961:  54%|█████▎    | 13891/25880 [2:51:17<2:16:33,  1.46it/s]
1|13892|Loss: 0.8940167427062988:  54%|█████▎    | 13891/25880 [2:51:18<2:16:33,  1.46it/s]
1|13892|Loss: 0.8940167427062988:  54%|█████▎    | 13892/25880 [2:51:18<2:11:23,  1.52it/s]
1|13893|Loss: 0.8350903391838074:  54%|█████▎    | 13892/25880 [2:51:18<2:11:23,  1.52it/s]
1|13893|Loss: 0.8350903391838074:  54%|█████▎    | 13893/25880 [2:51:19<2:22:35,  1.40it/s]
1|13894|Loss: 0.8521791696548462:  54%|█████▎    | 13893/25880 [2:51:19<2:22:35,  1.40it/s]
1|13894|Loss: 0.8521791696548462:  54%|█████▎    | 13894/25880 [2:51:19<2:19:00,  1.44it/s]
1|13895|Loss: 0.9428427815437317:  54%|█████▎    | 13894/25880 [2:51:20<2:19:00,  1.44it/s]
1|13895|Loss: 0.9428427815437317:  54%|█████▎    | 13895/25880 [2:51:20<2:28:21,  1.35it/s]
1|13896|Loss: 0.932051420211792:  54%|█████▎    | 13895/25880 [2:51:21<2:28:21,  1.35it/s] 
1|13896|Loss: 0.932051420211792:  54%|█████▎    | 13896/25880 [2:51:21<2:24:33,  1.38it/s]
1|13897|Loss: 0.9570496678352356:  54%|█████▎    | 13896/25880 [2:51:21<2:24:33,  1.38it/s]
1|13897|Loss: 0.9570496678352356:  54%|█████▎    | 13897/25880 [2:51:22<2:16:27,  1.46it/s]
1|13898|Loss: 0.8385807275772095:  54%|█████▎    | 13897/25880 [2:51:22<2:16:27,  1.46it/s]
1|13898|Loss: 0.8385807275772095:  54%|█████▎    | 13898/25880 [2:51:22<2:16:21,  1.46it/s]
1|13899|Loss: 0.7782332301139832:  54%|█████▎    | 13898/25880 [2:51:23<2:16:21,  1.46it/s]
1|13899|Loss: 0.7782332301139832:  54%|█████▎    | 13899/25880 [2:51:23<2:18:41,  1.44it/s]
1|13900|Loss: 0.8429855704307556:  54%|█████▎    | 13899/25880 [2:51:23<2:18:41,  1.44it/s]
1|13900|Loss: 0.8429855704307556:  54%|█████▎    | 13900/25880 [2:51:24<2:29:46,  1.33it/s]
1|13901|Loss: 0.8138869404792786:  54%|█████▎    | 13900/25880 [2:51:24<2:29:46,  1.33it/s]
1|13901|Loss: 0.8138869404792786:  54%|█████▎    | 13901/25880 [2:51:25<2:31:33,  1.32it/s]
1|13902|Loss: 0.7478421926498413:  54%|█████▎    | 13901/25880 [2:51:25<2:31:33,  1.32it/s]
1|13902|Loss: 0.7478421926498413:  54%|█████▎    | 13902/25880 [2:51:25<2:30:11,  1.33it/s]
1|13903|Loss: 0.7430848479270935:  54%|█████▎    | 13902/25880 [2:51:26<2:30:11,  1.33it/s]
1|13903|Loss: 0.7430848479270935:  54%|█████▎    | 13903/25880 [2:51:26<2:37:13,  1.27it/s]
1|13904|Loss: 1.0010913610458374:  54%|█████▎    | 13903/25880 [2:51:27<2:37:13,  1.27it/s]
1|13904|Loss: 1.0010913610458374:  54%|█████▎    | 13904/25880 [2:51:27<2:40:34,  1.24it/s]
1|13905|Loss: 0.8836920261383057:  54%|█████▎    | 13904/25880 [2:51:27<2:40:34,  1.24it/s]
1|13905|Loss: 0.8836920261383057:  54%|█████▎    | 13905/25880 [2:51:28<2:30:34,  1.33it/s]
1|13906|Loss: 0.8498057723045349:  54%|█████▎    | 13905/25880 [2:51:28<2:30:34,  1.33it/s]
1|13906|Loss: 0.8498057723045349:  54%|█████▎    | 13906/25880 [2:51:28<2:27:39,  1.35it/s]
1|13907|Loss: 1.0919040441513062:  54%|█████▎    | 13906/25880 [2:51:29<2:27:39,  1.35it/s]
1|13907|Loss: 1.0919040441513062:  54%|█████▎    | 13907/25880 [2:51:29<2:17:50,  1.45it/s]
1|13908|Loss: 0.8620033264160156:  54%|█████▎    | 13907/25880 [2:51:29<2:17:50,  1.45it/s]
1|13908|Loss: 0.8620033264160156:  54%|█████▎    | 13908/25880 [2:51:29<2:04:21,  1.60it/s]
1|13909|Loss: 0.788323700428009:  54%|█████▎    | 13908/25880 [2:51:30<2:04:21,  1.60it/s] 
1|13909|Loss: 0.788323700428009:  54%|█████▎    | 13909/25880 [2:51:30<2:02:42,  1.63it/s]
1|13910|Loss: 0.7939473390579224:  54%|█████▎    | 13909/25880 [2:51:31<2:02:42,  1.63it/s]
1|13910|Loss: 0.7939473390579224:  54%|█████▎    | 13910/25880 [2:51:31<2:20:18,  1.42it/s]
1|13911|Loss: 0.7740046977996826:  54%|█████▎    | 13910/25880 [2:51:31<2:20:18,  1.42it/s]
1|13911|Loss: 0.7740046977996826:  54%|█████▍    | 13911/25880 [2:51:32<2:23:36,  1.39it/s]
1|13912|Loss: 0.8074663281440735:  54%|█████▍    | 13911/25880 [2:51:32<2:23:36,  1.39it/s]
1|13912|Loss: 0.8074663281440735:  54%|█████▍    | 13912/25880 [2:51:33<2:27:25,  1.35it/s]
1|13913|Loss: 0.8792142868041992:  54%|█████▍    | 13912/25880 [2:51:33<2:27:25,  1.35it/s]
1|13913|Loss: 0.8792142868041992:  54%|█████▍    | 13913/25880 [2:51:33<2:33:36,  1.30it/s]
1|13914|Loss: 0.8594120740890503:  54%|█████▍    | 13913/25880 [2:51:34<2:33:36,  1.30it/s]
1|13914|Loss: 0.8594120740890503:  54%|█████▍    | 13914/25880 [2:51:34<2:27:25,  1.35it/s]
1|13915|Loss: 0.8389813899993896:  54%|█████▍    | 13914/25880 [2:51:34<2:27:25,  1.35it/s]
1|13915|Loss: 0.8389813899993896:  54%|█████▍    | 13915/25880 [2:51:35<2:21:17,  1.41it/s]
1|13916|Loss: 0.7543728947639465:  54%|█████▍    | 13915/25880 [2:51:35<2:21:17,  1.41it/s]
1|13916|Loss: 0.7543728947639465:  54%|█████▍    | 13916/25880 [2:51:35<2:22:06,  1.40it/s]
1|13917|Loss: 0.8632224202156067:  54%|█████▍    | 13916/25880 [2:51:36<2:22:06,  1.40it/s]
1|13917|Loss: 0.8632224202156067:  54%|█████▍    | 13917/25880 [2:51:36<2:28:03,  1.35it/s]
1|13918|Loss: 0.7717049717903137:  54%|█████▍    | 13917/25880 [2:51:37<2:28:03,  1.35it/s]
1|13918|Loss: 0.7717049717903137:  54%|█████▍    | 13918/25880 [2:51:37<2:29:07,  1.34it/s]
1|13919|Loss: 0.894668459892273:  54%|█████▍    | 13918/25880 [2:51:37<2:29:07,  1.34it/s] 
1|13919|Loss: 0.894668459892273:  54%|█████▍    | 13919/25880 [2:51:38<2:24:34,  1.38it/s]
1|13920|Loss: 0.7680200934410095:  54%|█████▍    | 13919/25880 [2:51:38<2:24:34,  1.38it/s]
1|13920|Loss: 0.7680200934410095:  54%|█████▍    | 13920/25880 [2:51:38<2:24:04,  1.38it/s]
1|13921|Loss: 0.7486735582351685:  54%|█████▍    | 13920/25880 [2:51:39<2:24:04,  1.38it/s]
1|13921|Loss: 0.7486735582351685:  54%|█████▍    | 13921/25880 [2:51:39<2:29:16,  1.34it/s]
1|13922|Loss: 0.8655685186386108:  54%|█████▍    | 13921/25880 [2:51:40<2:29:16,  1.34it/s]
1|13922|Loss: 0.8655685186386108:  54%|█████▍    | 13922/25880 [2:51:40<2:36:12,  1.28it/s]
1|13923|Loss: 0.6826428771018982:  54%|█████▍    | 13922/25880 [2:51:40<2:36:12,  1.28it/s]
1|13923|Loss: 0.6826428771018982:  54%|█████▍    | 13923/25880 [2:51:41<2:35:26,  1.28it/s]
1|13924|Loss: 0.6904077529907227:  54%|█████▍    | 13923/25880 [2:51:41<2:35:26,  1.28it/s]
1|13924|Loss: 0.6904077529907227:  54%|█████▍    | 13924/25880 [2:51:42<2:36:25,  1.27it/s]
1|13925|Loss: 0.8783805966377258:  54%|█████▍    | 13924/25880 [2:51:42<2:36:25,  1.27it/s]
1|13925|Loss: 0.8783805966377258:  54%|█████▍    | 13925/25880 [2:51:42<2:28:21,  1.34it/s]
1|13926|Loss: 0.9248059988021851:  54%|█████▍    | 13925/25880 [2:51:43<2:28:21,  1.34it/s]
1|13926|Loss: 0.9248059988021851:  54%|█████▍    | 13926/25880 [2:51:43<2:34:49,  1.29it/s]
1|13927|Loss: 0.93087238073349:  54%|█████▍    | 13926/25880 [2:51:44<2:34:49,  1.29it/s]  
1|13927|Loss: 0.93087238073349:  54%|█████▍    | 13927/25880 [2:51:44<2:28:38,  1.34it/s]
1|13928|Loss: 0.9596846103668213:  54%|█████▍    | 13927/25880 [2:51:44<2:28:38,  1.34it/s]
1|13928|Loss: 0.9596846103668213:  54%|█████▍    | 13928/25880 [2:51:44<2:24:41,  1.38it/s]
1|13929|Loss: 0.7954087257385254:  54%|█████▍    | 13928/25880 [2:51:45<2:24:41,  1.38it/s]
1|13929|Loss: 0.7954087257385254:  54%|█████▍    | 13929/25880 [2:51:45<2:18:44,  1.44it/s]
1|13930|Loss: 0.8429425358772278:  54%|█████▍    | 13929/25880 [2:51:45<2:18:44,  1.44it/s]
1|13930|Loss: 0.8429425358772278:  54%|█████▍    | 13930/25880 [2:51:46<2:12:17,  1.51it/s]
1|13931|Loss: 0.8463205695152283:  54%|█████▍    | 13930/25880 [2:51:46<2:12:17,  1.51it/s]
1|13931|Loss: 0.8463205695152283:  54%|█████▍    | 13931/25880 [2:51:47<2:23:42,  1.39it/s]
1|13932|Loss: 0.9569215178489685:  54%|█████▍    | 13931/25880 [2:51:47<2:23:42,  1.39it/s]
1|13932|Loss: 0.9569215178489685:  54%|█████▍    | 13932/25880 [2:51:47<2:27:07,  1.35it/s]
1|13933|Loss: 0.8784388899803162:  54%|█████▍    | 13932/25880 [2:51:48<2:27:07,  1.35it/s]
1|13933|Loss: 0.8784388899803162:  54%|█████▍    | 13933/25880 [2:51:48<2:36:18,  1.27it/s]
1|13934|Loss: 0.9095175266265869:  54%|█████▍    | 13933/25880 [2:51:49<2:36:18,  1.27it/s]
1|13934|Loss: 0.9095175266265869:  54%|█████▍    | 13934/25880 [2:51:49<2:36:12,  1.27it/s]
1|13935|Loss: 0.8580362200737:  54%|█████▍    | 13934/25880 [2:51:49<2:36:12,  1.27it/s]   
1|13935|Loss: 0.8580362200737:  54%|█████▍    | 13935/25880 [2:51:50<2:36:12,  1.27it/s]
1|13936|Loss: 0.8346689343452454:  54%|█████▍    | 13935/25880 [2:51:50<2:36:12,  1.27it/s]
1|13936|Loss: 0.8346689343452454:  54%|█████▍    | 13936/25880 [2:51:51<2:39:03,  1.25it/s]
1|13937|Loss: 0.7783512473106384:  54%|█████▍    | 13936/25880 [2:51:51<2:39:03,  1.25it/s]
1|13937|Loss: 0.7783512473106384:  54%|█████▍    | 13937/25880 [2:51:51<2:39:53,  1.24it/s]
1|13938|Loss: 0.6663771271705627:  54%|█████▍    | 13937/25880 [2:51:52<2:39:53,  1.24it/s]
1|13938|Loss: 0.6663771271705627:  54%|█████▍    | 13938/25880 [2:51:52<2:47:28,  1.19it/s]
1|13939|Loss: 0.8405085802078247:  54%|█████▍    | 13938/25880 [2:51:53<2:47:28,  1.19it/s]
1|13939|Loss: 0.8405085802078247:  54%|█████▍    | 13939/25880 [2:51:53<2:39:22,  1.25it/s]
1|13940|Loss: 0.7233595848083496:  54%|█████▍    | 13939/25880 [2:51:53<2:39:22,  1.25it/s]
1|13940|Loss: 0.7233595848083496:  54%|█████▍    | 13940/25880 [2:51:54<2:43:12,  1.22it/s]
1|13941|Loss: 0.8419976830482483:  54%|█████▍    | 13940/25880 [2:51:54<2:43:12,  1.22it/s]
1|13941|Loss: 0.8419976830482483:  54%|█████▍    | 13941/25880 [2:51:55<2:43:36,  1.22it/s]
1|13942|Loss: 0.889843225479126:  54%|█████▍    | 13941/25880 [2:51:55<2:43:36,  1.22it/s] 
1|13942|Loss: 0.889843225479126:  54%|█████▍    | 13942/25880 [2:51:55<2:33:13,  1.30it/s]
1|13943|Loss: 0.7627397179603577:  54%|█████▍    | 13942/25880 [2:51:56<2:33:13,  1.30it/s]
1|13943|Loss: 0.7627397179603577:  54%|█████▍    | 13943/25880 [2:51:56<2:27:48,  1.35it/s]
1|13944|Loss: 0.7718454003334045:  54%|█████▍    | 13943/25880 [2:51:56<2:27:48,  1.35it/s]
1|13944|Loss: 0.7718454003334045:  54%|█████▍    | 13944/25880 [2:51:57<2:26:36,  1.36it/s]
1|13945|Loss: 0.7972371578216553:  54%|█████▍    | 13944/25880 [2:51:57<2:26:36,  1.36it/s]
1|13945|Loss: 0.7972371578216553:  54%|█████▍    | 13945/25880 [2:51:58<2:26:34,  1.36it/s]
1|13946|Loss: 0.9314722418785095:  54%|█████▍    | 13945/25880 [2:51:58<2:26:34,  1.36it/s]
1|13946|Loss: 0.9314722418785095:  54%|█████▍    | 13946/25880 [2:51:58<2:10:09,  1.53it/s]
1|13947|Loss: 0.9725566506385803:  54%|█████▍    | 13946/25880 [2:51:58<2:10:09,  1.53it/s]
1|13947|Loss: 0.9725566506385803:  54%|█████▍    | 13947/25880 [2:51:59<2:16:47,  1.45it/s]
1|13948|Loss: 0.7239971160888672:  54%|█████▍    | 13947/25880 [2:51:59<2:16:47,  1.45it/s]
1|13948|Loss: 0.7239971160888672:  54%|█████▍    | 13948/25880 [2:52:00<2:26:37,  1.36it/s]
1|13949|Loss: 0.6898624300956726:  54%|█████▍    | 13948/25880 [2:52:00<2:26:37,  1.36it/s]
1|13949|Loss: 0.6898624300956726:  54%|█████▍    | 13949/25880 [2:52:00<2:35:09,  1.28it/s]
1|13950|Loss: 0.7137957215309143:  54%|█████▍    | 13949/25880 [2:52:01<2:35:09,  1.28it/s]
1|13950|Loss: 0.7137957215309143:  54%|█████▍    | 13950/25880 [2:52:01<2:43:29,  1.22it/s]
1|13951|Loss: 0.7903607487678528:  54%|█████▍    | 13950/25880 [2:52:02<2:43:29,  1.22it/s]
1|13951|Loss: 0.7903607487678528:  54%|█████▍    | 13951/25880 [2:52:02<2:38:35,  1.25it/s]
1|13952|Loss: 0.7499147653579712:  54%|█████▍    | 13951/25880 [2:52:03<2:38:35,  1.25it/s]
1|13952|Loss: 0.7499147653579712:  54%|█████▍    | 13952/25880 [2:52:03<2:41:19,  1.23it/s]
1|13953|Loss: 0.7088403105735779:  54%|█████▍    | 13952/25880 [2:52:03<2:41:19,  1.23it/s]
1|13953|Loss: 0.7088403105735779:  54%|█████���    | 13953/25880 [2:52:04<2:38:11,  1.26it/s]
1|13954|Loss: 0.7819280624389648:  54%|█████▍    | 13953/25880 [2:52:04<2:38:11,  1.26it/s]
1|13954|Loss: 0.7819280624389648:  54%|█████▍    | 13954/25880 [2:52:04<2:34:05,  1.29it/s]
1|13955|Loss: 0.7706140875816345:  54%|█████▍    | 13954/25880 [2:52:05<2:34:05,  1.29it/s]
1|13955|Loss: 0.7706140875816345:  54%|█████▍    | 13955/25880 [2:52:05<2:34:09,  1.29it/s]
1|13956|Loss: 0.7709698677062988:  54%|█████▍    | 13955/25880 [2:52:06<2:34:09,  1.29it/s]
1|13956|Loss: 0.7709698677062988:  54%|█████▍    | 13956/25880 [2:52:06<2:37:17,  1.26it/s]
1|13957|Loss: 0.8554080128669739:  54%|█████▍    | 13956/25880 [2:52:06<2:37:17,  1.26it/s]
1|13957|Loss: 0.8554080128669739:  54%|█████▍    | 13957/25880 [2:52:07<2:27:34,  1.35it/s]
1|13958|Loss: 0.6828104257583618:  54%|█████▍    | 13957/25880 [2:52:07<2:27:34,  1.35it/s]
1|13958|Loss: 0.6828104257583618:  54%|█████▍    | 13958/25880 [2:52:07<2:20:34,  1.41it/s]
1|13959|Loss: 0.8021819591522217:  54%|█████▍    | 13958/25880 [2:52:08<2:20:34,  1.41it/s]
1|13959|Loss: 0.8021819591522217:  54%|█████▍    | 13959/25880 [2:52:08<2:10:19,  1.52it/s]
1|13960|Loss: 0.8119400143623352:  54%|█████▍    | 13959/25880 [2:52:08<2:10:19,  1.52it/s]
1|13960|Loss: 0.8119400143623352:  54%|█████▍    | 13960/25880 [2:52:09<2:10:38,  1.52it/s]
1|13961|Loss: 0.8405769467353821:  54%|█████▍    | 13960/25880 [2:52:09<2:10:38,  1.52it/s]
1|13961|Loss: 0.8405769467353821:  54%|█████▍    | 13961/25880 [2:52:09<2:15:03,  1.47it/s]
1|13962|Loss: 0.6564728021621704:  54%|█████▍    | 13961/25880 [2:52:10<2:15:03,  1.47it/s]
1|13962|Loss: 0.6564728021621704:  54%|█████▍    | 13962/25880 [2:52:10<2:22:41,  1.39it/s]
1|13963|Loss: 0.7944000363349915:  54%|█████▍    | 13962/25880 [2:52:10<2:22:41,  1.39it/s]
1|13963|Loss: 0.7944000363349915:  54%|█████▍    | 13963/25880 [2:52:11<2:24:38,  1.37it/s]
1|13964|Loss: 0.8054050803184509:  54%|█████▍    | 13963/25880 [2:52:11<2:24:38,  1.37it/s]
1|13964|Loss: 0.8054050803184509:  54%|█████▍    | 13964/25880 [2:52:12<2:24:46,  1.37it/s]
1|13965|Loss: 0.8097459673881531:  54%|█████▍    | 13964/25880 [2:52:12<2:24:46,  1.37it/s]
1|13965|Loss: 0.8097459673881531:  54%|█████▍    | 13965/25880 [2:52:12<2:19:36,  1.42it/s]
1|13966|Loss: 0.9082732200622559:  54%|█████▍    | 13965/25880 [2:52:13<2:19:36,  1.42it/s]
1|13966|Loss: 0.9082732200622559:  54%|█████▍    | 13966/25880 [2:52:13<2:28:41,  1.34it/s]
1|13967|Loss: 0.8848923444747925:  54%|█████▍    | 13966/25880 [2:52:14<2:28:41,  1.34it/s]
1|13967|Loss: 0.8848923444747925:  54%|█████▍    | 13967/25880 [2:52:14<2:34:14,  1.29it/s]
1|13968|Loss: 0.8983932733535767:  54%|█████▍    | 13967/25880 [2:52:14<2:34:14,  1.29it/s]
1|13968|Loss: 0.8983932733535767:  54%|█████▍    | 13968/25880 [2:52:15<2:39:23,  1.25it/s]
1|13969|Loss: 0.8611310720443726:  54%|█████▍    | 13968/25880 [2:52:15<2:39:23,  1.25it/s]
1|13969|Loss: 0.8611310720443726:  54%|█████▍    | 13969/25880 [2:52:16<2:48:14,  1.18it/s]
1|13970|Loss: 0.7913070917129517:  54%|█████▍    | 13969/25880 [2:52:16<2:48:14,  1.18it/s]
1|13970|Loss: 0.7913070917129517:  54%|█████▍    | 13970/25880 [2:52:17<2:49:55,  1.17it/s]
1|13971|Loss: 0.7144151329994202:  54%|█████▍    | 13970/25880 [2:52:17<2:49:55,  1.17it/s]
1|13971|Loss: 0.7144151329994202:  54%|█████▍    | 13971/25880 [2:52:17<2:42:41,  1.22it/s]
1|13972|Loss: 0.8669640421867371:  54%|█████▍    | 13971/25880 [2:52:18<2:42:41,  1.22it/s]
1|13972|Loss: 0.8669640421867371:  54%|█████▍    | 13972/25880 [2:52:18<2:31:28,  1.31it/s]
1|13973|Loss: 0.7929903864860535:  54%|█████▍    | 13972/25880 [2:52:18<2:31:28,  1.31it/s]
1|13973|Loss: 0.7929903864860535:  54%|█████▍    | 13973/25880 [2:52:19<2:23:33,  1.38it/s]
1|13974|Loss: 0.7972793579101562:  54%|█████▍    | 13973/25880 [2:52:19<2:23:33,  1.38it/s]
1|13974|Loss: 0.7972793579101562:  54%|█████▍    | 13974/25880 [2:52:19<2:29:27,  1.33it/s]
1|13975|Loss: 0.7494202256202698:  54%|█████▍    | 13974/25880 [2:52:20<2:29:27,  1.33it/s]
1|13975|Loss: 0.7494202256202698:  54%|█████▍    | 13975/25880 [2:52:20<2:25:41,  1.36it/s]
1|13976|Loss: 0.8770624399185181:  54%|█████▍    | 13975/25880 [2:52:20<2:25:41,  1.36it/s]
1|13976|Loss: 0.8770624399185181:  54%|█████▍    | 13976/25880 [2:52:21<2:19:05,  1.43it/s]
1|13977|Loss: 0.7959190607070923:  54%|█████▍    | 13976/25880 [2:52:21<2:19:05,  1.43it/s]
1|13977|Loss: 0.7959190607070923:  54%|█████▍    | 13977/25880 [2:52:21<2:13:57,  1.48it/s]
1|13978|Loss: 0.7652128338813782:  54%|█████▍    | 13977/25880 [2:52:22<2:13:57,  1.48it/s]
1|13978|Loss: 0.7652128338813782:  54%|█████▍    | 13978/25880 [2:52:22<2:19:27,  1.42it/s]
1|13979|Loss: 0.8758769035339355:  54%|█████▍    | 13978/25880 [2:52:22<2:19:27,  1.42it/s]
1|13979|Loss: 0.8758769035339355:  54%|█████▍    | 13979/25880 [2:52:23<2:14:46,  1.47it/s]
1|13980|Loss: 0.8163568377494812:  54%|█████▍    | 13979/25880 [2:52:23<2:14:46,  1.47it/s]
1|13980|Loss: 0.8163568377494812:  54%|█████▍    | 13980/25880 [2:52:23<2:16:19,  1.45it/s]
1|13981|Loss: 1.025020956993103:  54%|█████▍    | 13980/25880 [2:52:24<2:16:19,  1.45it/s] 
1|13981|Loss: 1.025020956993103:  54%|█████▍    | 13981/25880 [2:52:24<2:08:26,  1.54it/s]
1|13982|Loss: 0.8214213252067566:  54%|█████▍    | 13981/25880 [2:52:24<2:08:26,  1.54it/s]
1|13982|Loss: 0.8214213252067566:  54%|█████▍    | 13982/25880 [2:52:24<2:00:12,  1.65it/s]
1|13983|Loss: 0.7904484272003174:  54%|█████▍    | 13982/25880 [2:52:25<2:00:12,  1.65it/s]
1|13983|Loss: 0.7904484272003174:  54%|█████▍    | 13983/25880 [2:52:25<2:04:50,  1.59it/s]
1|13984|Loss: 0.8494962453842163:  54%|█████▍    | 13983/25880 [2:52:26<2:04:50,  1.59it/s]
1|13984|Loss: 0.8494962453842163:  54%|█████▍    | 13984/25880 [2:52:26<2:06:41,  1.56it/s]
1|13985|Loss: 0.8788116574287415:  54%|█████▍    | 13984/25880 [2:52:26<2:06:41,  1.56it/s]
1|13985|Loss: 0.8788116574287415:  54%|█████▍    | 13985/25880 [2:52:27<2:11:32,  1.51it/s]
1|13986|Loss: 0.8863967657089233:  54%|█████▍    | 13985/25880 [2:52:27<2:11:32,  1.51it/s]
1|13986|Loss: 0.8863967657089233:  54%|█████▍    | 13986/25880 [2:52:27<2:23:08,  1.38it/s]
1|13987|Loss: 0.8352131247520447:  54%|█████▍    | 13986/25880 [2:52:28<2:23:08,  1.38it/s]
1|13987|Loss: 0.8352131247520447:  54%|█████▍    | 13987/25880 [2:52:28<2:25:37,  1.36it/s]
1|13988|Loss: 0.8702605366706848:  54%|█████▍    | 13987/25880 [2:52:29<2:25:37,  1.36it/s]
1|13988|Loss: 0.8702605366706848:  54%|█████▍    | 13988/25880 [2:52:29<2:23:52,  1.38it/s]
1|13989|Loss: 0.7603733539581299:  54%|█████▍    | 13988/25880 [2:52:29<2:23:52,  1.38it/s]
1|13989|Loss: 0.7603733539581299:  54%|█████▍    | 13989/25880 [2:52:30<2:24:32,  1.37it/s]
1|13990|Loss: 0.7789155840873718:  54%|█████▍    | 13989/25880 [2:52:30<2:24:32,  1.37it/s]
1|13990|Loss: 0.7789155840873718:  54%|█████▍    | 13990/25880 [2:52:30<2:25:35,  1.36it/s]
1|13991|Loss: 0.652487576007843:  54%|█████▍    | 13990/25880 [2:52:31<2:25:35,  1.36it/s] 
1|13991|Loss: 0.652487576007843:  54%|█████▍    | 13991/25880 [2:52:31<2:25:26,  1.36it/s]
1|13992|Loss: 0.9248416423797607:  54%|█████▍    | 13991/25880 [2:52:31<2:25:26,  1.36it/s]
1|13992|Loss: 0.9248416423797607:  54%|█████▍    | 13992/25880 [2:52:32<2:19:39,  1.42it/s]
1|13993|Loss: 0.8576146960258484:  54%|█████▍    | 13992/25880 [2:52:32<2:19:39,  1.42it/s]
1|13993|Loss: 0.8576146960258484:  54%|█████▍    | 13993/25880 [2:52:32<2:15:24,  1.46it/s]
1|13994|Loss: 0.7967270612716675:  54%|█████▍    | 13993/25880 [2:52:33<2:15:24,  1.46it/s]
1|13994|Loss: 0.7967270612716675:  54%|█████▍    | 13994/25880 [2:52:33<2:23:46,  1.38it/s]
1|13995|Loss: 0.8495739698410034:  54%|█████▍    | 13994/25880 [2:52:34<2:23:46,  1.38it/s]
1|13995|Loss: 0.8495739698410034:  54%|█████▍    | 13995/25880 [2:52:34<2:25:38,  1.36it/s]
1|13996|Loss: 0.8863906264305115:  54%|█████▍    | 13995/25880 [2:52:34<2:25:38,  1.36it/s]
1|13996|Loss: 0.8863906264305115:  54%|█████▍    | 13996/25880 [2:52:35<2:20:40,  1.41it/s]
1|13997|Loss: 0.7275094389915466:  54%|█████▍    | 13996/25880 [2:52:35<2:20:40,  1.41it/s]
1|13997|Loss: 0.7275094389915466:  54%|█████▍    | 13997/25880 [2:52:35<2:20:49,  1.41it/s]
1|13998|Loss: 0.7711157202720642:  54%|█████▍    | 13997/25880 [2:52:36<2:20:49,  1.41it/s]
1|13998|Loss: 0.7711157202720642:  54%|█████▍    | 13998/25880 [2:52:36<2:22:03,  1.39it/s]
1|13999|Loss: 0.7938482761383057:  54%|█████▍    | 13998/25880 [2:52:36<2:22:03,  1.39it/s]
1|13999|Loss: 0.7938482761383057:  54%|█████▍    | 13999/25880 [2:52:37<2:23:47,  1.38it/s]
1|14000|Loss: 0.8840232491493225:  54%|█████▍    | 13999/25880 [2:52:37<2:23:47,  1.38it/s]
1|14000|Loss: 0.8840232491493225:  54%|█████▍    | 14000/25880 [2:52:38<2:23:25,  1.38it/s]
1|14001|Loss: 0.7849082350730896:  54%|█████▍    | 14000/25880 [2:52:38<2:23:25,  1.38it/s]
1|14001|Loss: 0.7849082350730896:  54%|█████▍    | 14001/25880 [2:52:38<2:16:16,  1.45it/s]
1|14002|Loss: 0.8522328734397888:  54%|█████▍    | 14001/25880 [2:52:38<2:16:16,  1.45it/s]
1|14002|Loss: 0.8522328734397888:  54%|█████▍    | 14002/25880 [2:52:39<2:16:50,  1.45it/s]
1|14003|Loss: 0.7844184041023254:  54%|█████▍    | 14002/25880 [2:52:39<2:16:50,  1.45it/s]
1|14003|Loss: 0.7844184041023254:  54%|█████▍    | 14003/25880 [2:52:40<2:24:38,  1.37it/s]
1|14004|Loss: 1.113465666770935:  54%|█████▍    | 14003/25880 [2:52:40<2:24:38,  1.37it/s] 
1|14004|Loss: 1.113465666770935:  54%|█████▍    | 14004/25880 [2:52:41<2:32:14,  1.30it/s]
1|14005|Loss: 0.7223618626594543:  54%|█████▍    | 14004/25880 [2:52:41<2:32:14,  1.30it/s]
1|14005|Loss: 0.7223618626594543:  54%|█████▍    | 14005/25880 [2:52:41<2:26:31,  1.35it/s]
1|14006|Loss: 0.737688422203064:  54%|█████▍    | 14005/25880 [2:52:42<2:26:31,  1.35it/s] 
1|14006|Loss: 0.737688422203064:  54%|█████▍    | 14006/25880 [2:52:42<2:27:19,  1.34it/s]
1|14007|Loss: 0.8156720399856567:  54%|█████▍    | 14006/25880 [2:52:42<2:27:19,  1.34it/s]
1|14007|Loss: 0.8156720399856567:  54%|█████▍    | 14007/25880 [2:52:43<2:27:36,  1.34it/s]
1|14008|Loss: 0.7991105318069458:  54%|█████▍    | 14007/25880 [2:52:43<2:27:36,  1.34it/s]
1|14008|Loss: 0.7991105318069458:  54%|█████▍    | 14008/25880 [2:52:43<2:28:10,  1.34it/s]
1|14009|Loss: 0.917219877243042:  54%|█████▍    | 14008/25880 [2:52:44<2:28:10,  1.34it/s] 
1|14009|Loss: 0.917219877243042:  54%|█████▍    | 14009/25880 [2:52:44<2:35:59,  1.27it/s]
1|14010|Loss: 0.7532075047492981:  54%|█████▍    | 14009/25880 [2:52:45<2:35:59,  1.27it/s]
1|14010|Loss: 0.7532075047492981:  54%|█████▍    | 14010/25880 [2:52:45<2:27:23,  1.34it/s]
1|14011|Loss: 0.6727074980735779:  54%|█████▍    | 14010/25880 [2:52:45<2:27:23,  1.34it/s]
1|14011|Loss: 0.6727074980735779:  54%|█████▍    | 14011/25880 [2:52:46<2:25:25,  1.36it/s]
1|14012|Loss: 0.8919270038604736:  54%|█████▍    | 14011/25880 [2:52:46<2:25:25,  1.36it/s]
1|14012|Loss: 0.8919270038604736:  54%|█████▍    | 14012/25880 [2:52:46<2:18:20,  1.43it/s]
1|14013|Loss: 0.9181944131851196:  54%|█████▍    | 14012/25880 [2:52:47<2:18:20,  1.43it/s]
1|14013|Loss: 0.9181944131851196:  54%|█████▍    | 14013/25880 [2:52:47<2:18:20,  1.43it/s]
1|14014|Loss: 1.043250322341919:  54%|█████▍    | 14013/25880 [2:52:47<2:18:20,  1.43it/s] 
1|14014|Loss: 1.043250322341919:  54%|█████▍    | 14014/25880 [2:52:48<2:20:45,  1.40it/s]
1|14015|Loss: 0.9365943074226379:  54%|█████▍    | 14014/25880 [2:52:48<2:20:45,  1.40it/s]
1|14015|Loss: 0.9365943074226379:  54%|█████▍    | 14015/25880 [2:52:48<2:18:07,  1.43it/s]
1|14016|Loss: 0.8138595819473267:  54%|█████▍    | 14015/25880 [2:52:49<2:18:07,  1.43it/s]
1|14016|Loss: 0.8138595819473267:  54%|█████▍    | 14016/25880 [2:52:49<2:19:52,  1.41it/s]
1|14017|Loss: 0.8839125633239746:  54%|█████▍    | 14016/25880 [2:52:49<2:19:52,  1.41it/s]
1|14017|Loss: 0.8839125633239746:  54%|█████▍    | 14017/25880 [2:52:50<2:13:21,  1.48it/s]
1|14018|Loss: 0.835371196269989:  54%|█████▍    | 14017/25880 [2:52:50<2:13:21,  1.48it/s] 
1|14018|Loss: 0.835371196269989:  54%|█████▍    | 14018/25880 [2:52:50<2:04:52,  1.58it/s]
1|14019|Loss: 0.7656278610229492:  54%|█████▍    | 14018/25880 [2:52:51<2:04:52,  1.58it/s]
1|14019|Loss: 0.7656278610229492:  54%|█████▍    | 14019/25880 [2:52:51<2:02:58,  1.61it/s]
1|14020|Loss: 0.9052467346191406:  54%|█████▍    | 14019/25880 [2:52:51<2:02:58,  1.61it/s]
1|14020|Loss: 0.9052467346191406:  54%|█████▍    | 14020/25880 [2:52:52<2:09:07,  1.53it/s]
1|14021|Loss: 0.8457343578338623:  54%|█████▍    | 14020/25880 [2:52:52<2:09:07,  1.53it/s]
1|14021|Loss: 0.8457343578338623:  54%|█████▍    | 14021/25880 [2:52:52<2:21:06,  1.40it/s]
1|14022|Loss: 0.7695406079292297:  54%|█████▍    | 14021/25880 [2:52:53<2:21:06,  1.40it/s]
1|14022|Loss: 0.7695406079292297:  54%|█████▍    | 14022/25880 [2:52:53<2:29:50,  1.32it/s]
1|14023|Loss: 0.9482776522636414:  54%|█████▍    | 14022/25880 [2:52:54<2:29:50,  1.32it/s]
1|14023|Loss: 0.9482776522636414:  54%|█████▍    | 14023/25880 [2:52:54<2:25:31,  1.36it/s]
1|14024|Loss: 0.8311952352523804:  54%|█████▍    | 14023/25880 [2:52:54<2:25:31,  1.36it/s]
1|14024|Loss: 0.8311952352523804:  54%|█████▍    | 14024/25880 [2:52:55<2:29:10,  1.32it/s]
1|14025|Loss: 0.7960593104362488:  54%|█████▍    | 14024/25880 [2:52:55<2:29:10,  1.32it/s]
1|14025|Loss: 0.7960593104362488:  54%|█████▍    | 14025/25880 [2:52:55<2:15:34,  1.46it/s]
1|14026|Loss: 0.8119983673095703:  54%|█████▍    | 14025/25880 [2:52:56<2:15:34,  1.46it/s]
1|14026|Loss: 0.8119983673095703:  54%|█████▍    | 14026/25880 [2:52:56<2:25:43,  1.36it/s]
1|14027|Loss: 0.8681657910346985:  54%|█████▍    | 14026/25880 [2:52:57<2:25:43,  1.36it/s]
1|14027|Loss: 0.8681657910346985:  54%|█████▍    | 14027/25880 [2:52:57<2:22:37,  1.39it/s]
1|14028|Loss: 0.762017011642456:  54%|█████▍    | 14027/25880 [2:52:57<2:22:37,  1.39it/s] 
1|14028|Loss: 0.762017011642456:  54%|█████▍    | 14028/25880 [2:52:58<2:27:21,  1.34it/s]
1|14029|Loss: 0.934484601020813:  54%|█████▍    | 14028/25880 [2:52:58<2:27:21,  1.34it/s]
1|14029|Loss: 0.934484601020813:  54%|█████▍    | 14029/25880 [2:52:59<2:35:08,  1.27it/s]
1|14030|Loss: 0.8911759853363037:  54%|█████▍    | 14029/25880 [2:52:59<2:35:08,  1.27it/s]
1|14030|Loss: 0.8911759853363037:  54%|█████▍    | 14030/25880 [2:52:59<2:34:56,  1.27it/s]
1|14031|Loss: 0.9184394478797913:  54%|█████▍    | 14030/25880 [2:53:00<2:34:56,  1.27it/s]
1|14031|Loss: 0.9184394478797913:  54%|█████▍    | 14031/25880 [2:53:00<2:25:02,  1.36it/s]
1|14032|Loss: 0.8700137138366699:  54%|█████▍    | 14031/25880 [2:53:00<2:25:02,  1.36it/s]
1|14032|Loss: 0.8700137138366699:  54%|█████▍    | 14032/25880 [2:53:01<2:16:28,  1.45it/s]
1|14033|Loss: 0.7632625102996826:  54%|█████▍    | 14032/25880 [2:53:01<2:16:28,  1.45it/s]
1|14033|Loss: 0.7632625102996826:  54%|█████▍    | 14033/25880 [2:53:01<2:11:43,  1.50it/s]
1|14034|Loss: 0.8243241310119629:  54%|█████▍    | 14033/25880 [2:53:02<2:11:43,  1.50it/s]
1|14034|Loss: 0.8243241310119629:  54%|█████▍    | 14034/25880 [2:53:02<2:14:01,  1.47it/s]
1|14035|Loss: 0.7866644859313965:  54%|█████▍    | 14034/25880 [2:53:02<2:14:01,  1.47it/s]
1|14035|Loss: 0.7866644859313965:  54%|█████▍    | 14035/25880 [2:53:02<2:06:31,  1.56it/s]
1|14036|Loss: 0.7989649176597595:  54%|█████▍    | 14035/25880 [2:53:03<2:06:31,  1.56it/s]
1|14036|Loss: 0.7989649176597595:  54%|█████▍    | 14036/25880 [2:53:03<2:07:45,  1.55it/s]
1|14037|Loss: 0.8669240474700928:  54%|█████▍    | 14036/25880 [2:53:03<2:07:45,  1.55it/s]
1|14037|Loss: 0.8669240474700928:  54%|█████▍    | 14037/25880 [2:53:04<2:11:04,  1.51it/s]
1|14038|Loss: 0.8011295199394226:  54%|█████▍    | 14037/25880 [2:53:04<2:11:04,  1.51it/s]
1|14038|Loss: 0.8011295199394226:  54%|█████▍    | 14038/25880 [2:53:04<2:13:17,  1.48it/s]
1|14039|Loss: 0.8938724398612976:  54%|█████▍    | 14038/25880 [2:53:05<2:13:17,  1.48it/s]
1|14039|Loss: 0.8938724398612976:  54%|█████▍    | 14039/25880 [2:53:05<2:14:33,  1.47it/s]
1|14040|Loss: 0.8736292719841003:  54%|█████▍    | 14039/25880 [2:53:06<2:14:33,  1.47it/s]
1|14040|Loss: 0.8736292719841003:  54%|█████▍    | 14040/25880 [2:53:06<2:21:33,  1.39it/s]
1|14041|Loss: 0.7295923829078674:  54%|█████▍    | 14040/25880 [2:53:06<2:21:33,  1.39it/s]
1|14041|Loss: 0.7295923829078674:  54%|█████▍    | 14041/25880 [2:53:07<2:22:03,  1.39it/s]
1|14042|Loss: 0.8273632526397705:  54%|█████▍    | 14041/25880 [2:53:07<2:22:03,  1.39it/s]
1|14042|Loss: 0.8273632526397705:  54%|█████▍    | 14042/25880 [2:53:07<2:17:59,  1.43it/s]
1|14043|Loss: 0.7783470749855042:  54%|█████▍    | 14042/25880 [2:53:08<2:17:59,  1.43it/s]
1|14043|Loss: 0.7783470749855042:  54%|█████▍    | 14043/25880 [2:53:08<2:18:38,  1.42it/s]
1|14044|Loss: 0.7841238379478455:  54%|█████▍    | 14043/25880 [2:53:08<2:18:38,  1.42it/s]
1|14044|Loss: 0.7841238379478455:  54%|█████▍    | 14044/25880 [2:53:09<2:20:32,  1.40it/s]
1|14045|Loss: 0.8918731212615967:  54%|█████▍    | 14044/25880 [2:53:09<2:20:32,  1.40it/s]
1|14045|Loss: 0.8918731212615967:  54%|█████▍    | 14045/25880 [2:53:10<2:21:17,  1.40it/s]
1|14046|Loss: 0.9032984972000122:  54%|█████▍    | 14045/25880 [2:53:10<2:21:17,  1.40it/s]
1|14046|Loss: 0.9032984972000122:  54%|█████▍    | 14046/25880 [2:53:10<2:22:38,  1.38it/s]
1|14047|Loss: 0.8674836754798889:  54%|█████▍    | 14046/25880 [2:53:11<2:22:38,  1.38it/s]
1|14047|Loss: 0.8674836754798889:  54%|█████▍    | 14047/25880 [2:53:11<2:21:57,  1.39it/s]
1|14048|Loss: 0.7687157988548279:  54%|█████▍    | 14047/25880 [2:53:11<2:21:57,  1.39it/s]
1|14048|Loss: 0.7687157988548279:  54%|█████▍    | 14048/25880 [2:53:12<2:26:48,  1.34it/s]
1|14049|Loss: 0.8246290683746338:  54%|█████▍    | 14048/25880 [2:53:12<2:26:48,  1.34it/s]
1|14049|Loss: 0.8246290683746338:  54%|█████▍    | 14049/25880 [2:53:12<2:21:16,  1.40it/s]
1|14050|Loss: 0.7770031094551086:  54%|█████▍    | 14049/25880 [2:53:13<2:21:16,  1.40it/s]
1|14050|Loss: 0.7770031094551086:  54%|█████▍    | 14050/25880 [2:53:13<2:20:29,  1.40it/s]
1|14051|Loss: 0.8246731758117676:  54%|█████▍    | 14050/25880 [2:53:14<2:20:29,  1.40it/s]
1|14051|Loss: 0.8246731758117676:  54%|█████▍    | 14051/25880 [2:53:14<2:25:55,  1.35it/s]
1|14052|Loss: 0.8814918994903564:  54%|█████▍    | 14051/25880 [2:53:14<2:25:55,  1.35it/s]
1|14052|Loss: 0.8814918994903564:  54%|█████▍    | 14052/25880 [2:53:14<2:16:12,  1.45it/s]
1|14053|Loss: 0.8612363338470459:  54%|█████▍    | 14052/25880 [2:53:15<2:16:12,  1.45it/s]
1|14053|Loss: 0.8612363338470459:  54%|█████▍    | 14053/25880 [2:53:15<2:11:13,  1.50it/s]
1|14054|Loss: 0.8161420822143555:  54%|█████▍    | 14053/25880 [2:53:16<2:11:13,  1.50it/s]
1|14054|Loss: 0.8161420822143555:  54%|█████▍    | 14054/25880 [2:53:16<2:18:54,  1.42it/s]
1|14055|Loss: 0.9201386570930481:  54%|█████▍    | 14054/25880 [2:53:16<2:18:54,  1.42it/s]
1|14055|Loss: 0.9201386570930481:  54%|█████▍    | 14055/25880 [2:53:17<2:23:56,  1.37it/s]
1|14056|Loss: 0.7969803214073181:  54%|█████▍    | 14055/25880 [2:53:17<2:23:56,  1.37it/s]
1|14056|Loss: 0.7969803214073181:  54%|█████▍    | 14056/25880 [2:53:17<2:20:28,  1.40it/s]
1|14057|Loss: 0.8293142318725586:  54%|█████▍    | 14056/25880 [2:53:18<2:20:28,  1.40it/s]
1|14057|Loss: 0.8293142318725586:  54%|█████▍    | 14057/25880 [2:53:18<2:20:17,  1.40it/s]
1|14058|Loss: 0.8334181308746338:  54%|█████▍    | 14057/25880 [2:53:18<2:20:17,  1.40it/s]
1|14058|Loss: 0.8334181308746338:  54%|█████▍    | 14058/25880 [2:53:19<2:19:45,  1.41it/s]
1|14059|Loss: 0.7792174220085144:  54%|█████▍    | 14058/25880 [2:53:19<2:19:45,  1.41it/s]
1|14059|Loss: 0.7792174220085144:  54%|█████▍    | 14059/25880 [2:53:19<2:16:06,  1.45it/s]
1|14060|Loss: 0.8925099968910217:  54%|█████▍    | 14059/25880 [2:53:20<2:16:06,  1.45it/s]
1|14060|Loss: 0.8925099968910217:  54%|█████▍    | 14060/25880 [2:53:20<2:19:43,  1.41it/s]
1|14061|Loss: 0.7251124382019043:  54%|█████▍    | 14060/25880 [2:53:21<2:19:43,  1.41it/s]
1|14061|Loss: 0.7251124382019043:  54%|█████▍    | 14061/25880 [2:53:21<2:21:43,  1.39it/s]
1|14062|Loss: 0.8607990741729736:  54%|█████▍    | 14061/25880 [2:53:21<2:21:43,  1.39it/s]
1|14062|Loss: 0.8607990741729736:  54%|█████▍    | 14062/25880 [2:53:22<2:27:03,  1.34it/s]
1|14063|Loss: 0.9513880610466003:  54%|█████▍    | 14062/25880 [2:53:22<2:27:03,  1.34it/s]
1|14063|Loss: 0.9513880610466003:  54%|█████▍    | 14063/25880 [2:53:23<2:32:49,  1.29it/s]
1|14064|Loss: 0.7635461688041687:  54%|█████▍    | 14063/25880 [2:53:23<2:32:49,  1.29it/s]
1|14064|Loss: 0.7635461688041687:  54%|█████▍    | 14064/25880 [2:53:23<2:23:50,  1.37it/s]
1|14065|Loss: 0.9013855457305908:  54%|█████▍    | 14064/25880 [2:53:24<2:23:50,  1.37it/s]
1|14065|Loss: 0.9013855457305908:  54%|█████▍    | 14065/25880 [2:53:24<2:21:43,  1.39it/s]
1|14066|Loss: 0.7702488303184509:  54%|█████▍    | 14065/25880 [2:53:24<2:21:43,  1.39it/s]
1|14066|Loss: 0.7702488303184509:  54%|█████▍    | 14066/25880 [2:53:25<2:23:13,  1.37it/s]
1|14067|Loss: 0.860942542552948:  54%|█████▍    | 14066/25880 [2:53:25<2:23:13,  1.37it/s] 
1|14067|Loss: 0.860942542552948:  54%|█████▍    | 14067/25880 [2:53:25<2:23:48,  1.37it/s]
1|14068|Loss: 0.8294002413749695:  54%|█████▍    | 14067/25880 [2:53:26<2:23:48,  1.37it/s]
1|14068|Loss: 0.8294002413749695:  54%|█████▍    | 14068/25880 [2:53:26<2:23:19,  1.37it/s]
1|14069|Loss: 0.699100136756897:  54%|█████▍    | 14068/25880 [2:53:27<2:23:19,  1.37it/s] 
1|14069|Loss: 0.699100136756897:  54%|█████▍    | 14069/25880 [2:53:27<2:29:14,  1.32it/s]
1|14070|Loss: 0.8790361285209656:  54%|█████▍    | 14069/25880 [2:53:27<2:29:14,  1.32it/s]
1|14070|Loss: 0.8790361285209656:  54%|█████▍    | 14070/25880 [2:53:28<2:28:03,  1.33it/s]
1|14071|Loss: 0.7528233528137207:  54%|█████▍    | 14070/25880 [2:53:28<2:28:03,  1.33it/s]
1|14071|Loss: 0.7528233528137207:  54%|█████▍    | 14071/25880 [2:53:28<2:24:55,  1.36it/s]
1|14072|Loss: 0.8470495939254761:  54%|█████▍    | 14071/25880 [2:53:29<2:24:55,  1.36it/s]
1|14072|Loss: 0.8470495939254761:  54%|█████▍    | 14072/25880 [2:53:29<2:19:26,  1.41it/s]
1|14073|Loss: 0.9121808409690857:  54%|█████▍    | 14072/25880 [2:53:29<2:19:26,  1.41it/s]
1|14073|Loss: 0.9121808409690857:  54%|█████▍    | 14073/25880 [2:53:30<2:20:28,  1.40it/s]
1|14074|Loss: 0.9014198184013367:  54%|█████▍    | 14073/25880 [2:53:30<2:20:28,  1.40it/s]
1|14074|Loss: 0.9014198184013367:  54%|█████▍    | 14074/25880 [2:53:31<2:26:45,  1.34it/s]
1|14075|Loss: 0.7981269955635071:  54%|█████▍    | 14074/25880 [2:53:31<2:26:45,  1.34it/s]
1|14075|Loss: 0.7981269955635071:  54%|█████▍    | 14075/25880 [2:53:31<2:33:16,  1.28it/s]
1|14076|Loss: 0.9369158148765564:  54%|█████▍    | 14075/25880 [2:53:32<2:33:16,  1.28it/s]
1|14076|Loss: 0.9369158148765564:  54%|█████▍    | 14076/25880 [2:53:32<2:34:51,  1.27it/s]
1|14077|Loss: 0.8367639780044556:  54%|█████▍    | 14076/25880 [2:53:33<2:34:51,  1.27it/s]
1|14077|Loss: 0.8367639780044556:  54%|█████▍    | 14077/25880 [2:53:33<2:26:59,  1.34it/s]
1|14078|Loss: 0.744962215423584:  54%|█████▍    | 14077/25880 [2:53:33<2:26:59,  1.34it/s] 
1|14078|Loss: 0.744962215423584:  54%|█████▍    | 14078/25880 [2:53:33<2:11:41,  1.49it/s]
1|14079|Loss: 0.8355312347412109:  54%|█████▍    | 14078/25880 [2:53:34<2:11:41,  1.49it/s]
1|14079|Loss: 0.8355312347412109:  54%|█████▍    | 14079/25880 [2:53:34<2:10:02,  1.51it/s]
1|14080|Loss: 0.8425837159156799:  54%|█████▍    | 14079/25880 [2:53:34<2:10:02,  1.51it/s]
1|14080|Loss: 0.8425837159156799:  54%|█████▍    | 14080/25880 [2:53:35<2:13:25,  1.47it/s]
1|14081|Loss: 0.780729353427887:  54%|█████▍    | 14080/25880 [2:53:35<2:13:25,  1.47it/s] 
1|14081|Loss: 0.780729353427887:  54%|█████▍    | 14081/25880 [2:53:35<2:10:50,  1.50it/s]
1|14082|Loss: 0.9763088226318359:  54%|█████▍    | 14081/25880 [2:53:36<2:10:50,  1.50it/s]
1|14082|Loss: 0.9763088226318359:  54%|█████▍    | 14082/25880 [2:53:36<2:03:46,  1.59it/s]
1|14083|Loss: 0.837030827999115:  54%|█████▍    | 14082/25880 [2:53:36<2:03:46,  1.59it/s] 
1|14083|Loss: 0.837030827999115:  54%|█████▍    | 14083/25880 [2:53:37<2:11:55,  1.49it/s]
1|14084|Loss: 0.8484443426132202:  54%|█████▍    | 14083/25880 [2:53:37<2:11:55,  1.49it/s]
1|14084|Loss: 0.8484443426132202:  54%|█████▍    | 14084/25880 [2:53:38<2:22:14,  1.38it/s]
1|14085|Loss: 0.8489992022514343:  54%|█████▍    | 14084/25880 [2:53:38<2:22:14,  1.38it/s]
1|14085|Loss: 0.8489992022514343:  54%|█████▍    | 14085/25880 [2:53:38<2:13:55,  1.47it/s]
1|14086|Loss: 0.848456859588623:  54%|█████▍    | 14085/25880 [2:53:38<2:13:55,  1.47it/s] 
1|14086|Loss: 0.848456859588623:  54%|█████▍    | 14086/25880 [2:53:39<2:08:47,  1.53it/s]
1|14087|Loss: 0.7348012328147888:  54%|█████▍    | 14086/25880 [2:53:39<2:08:47,  1.53it/s]
1|14087|Loss: 0.7348012328147888:  54%|█████▍    | 14087/25880 [2:53:40<2:18:48,  1.42it/s]
1|14088|Loss: 0.899492084980011:  54%|█████▍    | 14087/25880 [2:53:40<2:18:48,  1.42it/s] 
1|14088|Loss: 0.899492084980011:  54%|█████▍    | 14088/25880 [2:53:40<2:21:45,  1.39it/s]
1|14089|Loss: 0.9476862549781799:  54%|█████▍    | 14088/25880 [2:53:41<2:21:45,  1.39it/s]
1|14089|Loss: 0.9476862549781799:  54%|█████▍    | 14089/25880 [2:53:41<2:20:43,  1.40it/s]
1|14090|Loss: 0.9451271295547485:  54%|█████▍    | 14089/25880 [2:53:41<2:20:43,  1.40it/s]
1|14090|Loss: 0.9451271295547485:  54%|█████▍    | 14090/25880 [2:53:42<2:19:41,  1.41it/s]
1|14091|Loss: 0.8090124726295471:  54%|█████▍    | 14090/25880 [2:53:42<2:19:41,  1.41it/s]
1|14091|Loss: 0.8090124726295471:  54%|█████▍    | 14091/25880 [2:53:42<2:20:21,  1.40it/s]
1|14092|Loss: 0.9125195741653442:  54%|█████▍    | 14091/25880 [2:53:43<2:20:21,  1.40it/s]
1|14092|Loss: 0.9125195741653442:  54%|█████▍    | 14092/25880 [2:53:43<2:20:56,  1.39it/s]
1|14093|Loss: 0.8650105595588684:  54%|█████▍    | 14092/25880 [2:53:43<2:20:56,  1.39it/s]
1|14093|Loss: 0.8650105595588684:  54%|█████▍    | 14093/25880 [2:53:44<2:17:35,  1.43it/s]
1|14094|Loss: 0.8379416465759277:  54%|█████▍    | 14093/25880 [2:53:44<2:17:35,  1.43it/s]
1|14094|Loss: 0.8379416465759277:  54%|█████▍    | 14094/25880 [2:53:44<2:18:44,  1.42it/s]
1|14095|Loss: 0.7315472364425659:  54%|█████▍    | 14094/25880 [2:53:45<2:18:44,  1.42it/s]
1|14095|Loss: 0.7315472364425659:  54%|█████▍    | 14095/25880 [2:53:45<2:20:48,  1.39it/s]
1|14096|Loss: 0.9231719970703125:  54%|█████▍    | 14095/25880 [2:53:46<2:20:48,  1.39it/s]
1|14096|Loss: 0.9231719970703125:  54%|█████▍    | 14096/25880 [2:53:46<2:16:21,  1.44it/s]
1|14097|Loss: 0.8232313394546509:  54%|█████▍    | 14096/25880 [2:53:46<2:16:21,  1.44it/s]
1|14097|Loss: 0.8232313394546509:  54%|█████▍    | 14097/25880 [2:53:47<2:17:49,  1.42it/s]
1|14098|Loss: 0.7167164087295532:  54%|█████▍    | 14097/25880 [2:53:47<2:17:49,  1.42it/s]
1|14098|Loss: 0.7167164087295532:  54%|█████▍    | 14098/25880 [2:53:47<2:20:40,  1.40it/s]
1|14099|Loss: 0.8141392469406128:  54%|█████▍    | 14098/25880 [2:53:48<2:20:40,  1.40it/s]
1|14099|Loss: 0.8141392469406128:  54%|█████▍    | 14099/25880 [2:53:48<2:11:35,  1.49it/s]
1|14100|Loss: 0.7671573758125305:  54%|█████▍    | 14099/25880 [2:53:48<2:11:35,  1.49it/s]
1|14100|Loss: 0.7671573758125305:  54%|█████▍    | 14100/25880 [2:53:49<2:12:08,  1.49it/s]
1|14101|Loss: 0.9610554575920105:  54%|█████▍    | 14100/25880 [2:53:49<2:12:08,  1.49it/s]
1|14101|Loss: 0.9610554575920105:  54%|█████▍    | 14101/25880 [2:53:49<2:09:41,  1.51it/s]
1|14102|Loss: 0.7622750997543335:  54%|█████▍    | 14101/25880 [2:53:50<2:09:41,  1.51it/s]
1|14102|Loss: 0.7622750997543335:  54%|█████▍    | 14102/25880 [2:53:50<2:12:28,  1.48it/s]
1|14103|Loss: 0.8043552041053772:  54%|█████▍    | 14102/25880 [2:53:50<2:12:28,  1.48it/s]
1|14103|Loss: 0.8043552041053772:  54%|█████▍    | 14103/25880 [2:53:51<2:09:03,  1.52it/s]
1|14104|Loss: 1.0838265419006348:  54%|█████▍    | 14103/25880 [2:53:51<2:09:03,  1.52it/s]
1|14104|Loss: 1.0838265419006348:  54%|█████▍    | 14104/25880 [2:53:51<2:11:47,  1.49it/s]
1|14105|Loss: 0.802261233329773:  54%|█████▍    | 14104/25880 [2:53:52<2:11:47,  1.49it/s] 
1|14105|Loss: 0.802261233329773:  55%|█████▍    | 14105/25880 [2:53:52<2:11:02,  1.50it/s]
1|14106|Loss: 0.7920461893081665:  55%|█████▍    | 14105/25880 [2:53:52<2:11:02,  1.50it/s]
1|14106|Loss: 0.7920461893081665:  55%|█████▍    | 14106/25880 [2:53:53<2:09:22,  1.52it/s]
1|14107|Loss: 0.9254801273345947:  55%|█████▍    | 14106/25880 [2:53:53<2:09:22,  1.52it/s]
1|14107|Loss: 0.9254801273345947:  55%|█████▍    | 14107/25880 [2:53:53<2:13:20,  1.47it/s]
1|14108|Loss: 0.8350537419319153:  55%|█████▍    | 14107/25880 [2:53:54<2:13:20,  1.47it/s]
1|14108|Loss: 0.8350537419319153:  55%|█████▍    | 14108/25880 [2:53:54<2:16:41,  1.44it/s]
1|14109|Loss: 0.8582472801208496:  55%|█████▍    | 14108/25880 [2:53:54<2:16:41,  1.44it/s]
1|14109|Loss: 0.8582472801208496:  55%|█████▍    | 14109/25880 [2:53:55<2:18:49,  1.41it/s]
1|14110|Loss: 0.9157023429870605:  55%|█████▍    | 14109/25880 [2:53:55<2:18:49,  1.41it/s]
1|14110|Loss: 0.9157023429870605:  55%|█████▍    | 14110/25880 [2:53:55<2:19:08,  1.41it/s]
1|14111|Loss: 0.7636560797691345:  55%|█████▍    | 14110/25880 [2:53:56<2:19:08,  1.41it/s]
1|14111|Loss: 0.7636560797691345:  55%|█████▍    | 14111/25880 [2:53:56<2:12:46,  1.48it/s]
1|14112|Loss: 0.8417285680770874:  55%|█████▍    | 14111/25880 [2:53:56<2:12:46,  1.48it/s]
1|14112|Loss: 0.8417285680770874:  55%|█████▍    | 14112/25880 [2:53:57<2:14:23,  1.46it/s]
1|14113|Loss: 0.8592780828475952:  55%|█████▍    | 14112/25880 [2:53:57<2:14:23,  1.46it/s]
1|14113|Loss: 0.8592780828475952:  55%|█████▍    | 14113/25880 [2:53:57<2:04:15,  1.58it/s]
1|14114|Loss: 0.8855704665184021:  55%|█████▍    | 14113/25880 [2:53:58<2:04:15,  1.58it/s]
1|14114|Loss: 0.8855704665184021:  55%|█████▍    | 14114/25880 [2:53:58<2:11:57,  1.49it/s]
1|14115|Loss: 0.7517389059066772:  55%|█████▍    | 14114/25880 [2:53:58<2:11:57,  1.49it/s]
1|14115|Loss: 0.7517389059066772:  55%|█████▍    | 14115/25880 [2:53:59<2:13:11,  1.47it/s]
1|14116|Loss: 0.8861113786697388:  55%|█████▍    | 14115/25880 [2:53:59<2:13:11,  1.47it/s]
1|14116|Loss: 0.8861113786697388:  55%|█████▍    | 14116/25880 [2:54:00<2:17:58,  1.42it/s]
1|14117|Loss: 0.8136340379714966:  55%|█████▍    | 14116/25880 [2:54:00<2:17:58,  1.42it/s]
1|14117|Loss: 0.8136340379714966:  55%|█████▍    | 14117/25880 [2:54:00<2:24:54,  1.35it/s]
1|14118|Loss: 0.7991715669631958:  55%|█████▍    | 14117/25880 [2:54:01<2:24:54,  1.35it/s]
1|14118|Loss: 0.7991715669631958:  55%|█████▍    | 14118/25880 [2:54:01<2:25:18,  1.35it/s]
1|14119|Loss: 0.8907672166824341:  55%|█████▍    | 14118/25880 [2:54:01<2:25:18,  1.35it/s]
1|14119|Loss: 0.8907672166824341:  55%|█████▍    | 14119/25880 [2:54:02<2:17:55,  1.42it/s]
1|14120|Loss: 0.766350269317627:  55%|█████▍    | 14119/25880 [2:54:02<2:17:55,  1.42it/s] 
1|14120|Loss: 0.766350269317627:  55%|█████▍    | 14120/25880 [2:54:02<2:12:59,  1.47it/s]
1|14121|Loss: 0.8732879757881165:  55%|█████▍    | 14120/25880 [2:54:03<2:12:59,  1.47it/s]
1|14121|Loss: 0.8732879757881165:  55%|█████▍    | 14121/25880 [2:54:03<2:09:45,  1.51it/s]
1|14122|Loss: 0.9533820152282715:  55%|█████▍    | 14121/25880 [2:54:03<2:09:45,  1.51it/s]
1|14122|Loss: 0.9533820152282715:  55%|█████▍    | 14122/25880 [2:54:04<2:17:23,  1.43it/s]
1|14123|Loss: 0.8063480257987976:  55%|█████▍    | 14122/25880 [2:54:04<2:17:23,  1.43it/s]
1|14123|Loss: 0.8063480257987976:  55%|█████▍    | 14123/25880 [2:54:04<2:21:07,  1.39it/s]
1|14124|Loss: 0.7309136986732483:  55%|█████▍    | 14123/25880 [2:54:05<2:21:07,  1.39it/s]
1|14124|Loss: 0.7309136986732483:  55%|█████▍    | 14124/25880 [2:54:05<2:18:05,  1.42it/s]
1|14125|Loss: 0.9436420202255249:  55%|█████▍    | 14124/25880 [2:54:06<2:18:05,  1.42it/s]
1|14125|Loss: 0.9436420202255249:  55%|█████▍    | 14125/25880 [2:54:06<2:19:19,  1.41it/s]
1|14126|Loss: 0.9241383075714111:  55%|█████▍    | 14125/25880 [2:54:06<2:19:19,  1.41it/s]
1|14126|Loss: 0.9241383075714111:  55%|█████▍    | 14126/25880 [2:54:07<2:26:36,  1.34it/s]
1|14127|Loss: 0.7979743480682373:  55%|█████▍    | 14126/25880 [2:54:07<2:26:36,  1.34it/s]
1|14127|Loss: 0.7979743480682373:  55%|█████▍    | 14127/25880 [2:54:07<2:20:30,  1.39it/s]
1|14128|Loss: 0.872103750705719:  55%|█████▍    | 14127/25880 [2:54:08<2:20:30,  1.39it/s] 
1|14128|Loss: 0.872103750705719:  55%|█████▍    | 14128/25880 [2:54:08<2:09:14,  1.52it/s]
1|14129|Loss: 0.7861018180847168:  55%|█████▍    | 14128/25880 [2:54:08<2:09:14,  1.52it/s]
1|14129|Loss: 0.7861018180847168:  55%|█████▍    | 14129/25880 [2:54:09<2:09:10,  1.52it/s]
1|14130|Loss: 0.8632861375808716:  55%|█████▍    | 14129/25880 [2:54:09<2:09:10,  1.52it/s]
1|14130|Loss: 0.8632861375808716:  55%|█████▍    | 14130/25880 [2:54:09<2:13:12,  1.47it/s]
1|14131|Loss: 0.7663820385932922:  55%|█████▍    | 14130/25880 [2:54:10<2:13:12,  1.47it/s]
1|14131|Loss: 0.7663820385932922:  55%|█████▍    | 14131/25880 [2:54:10<2:19:14,  1.41it/s]
1|14132|Loss: 0.6630619764328003:  55%|█████▍    | 14131/25880 [2:54:11<2:19:14,  1.41it/s]
1|14132|Loss: 0.6630619764328003:  55%|█████▍    | 14132/25880 [2:54:11<2:27:06,  1.33it/s]
1|14133|Loss: 0.8801678419113159:  55%|█████▍    | 14132/25880 [2:54:11<2:27:06,  1.33it/s]
1|14133|Loss: 0.8801678419113159:  55%|█████▍    | 14133/25880 [2:54:12<2:23:19,  1.37it/s]
1|14134|Loss: 0.7575095295906067:  55%|█████▍    | 14133/25880 [2:54:12<2:23:19,  1.37it/s]
1|14134|Loss: 0.7575095295906067:  55%|█████▍    | 14134/25880 [2:54:12<2:17:52,  1.42it/s]
1|14135|Loss: 0.8212454319000244:  55%|█████▍    | 14134/25880 [2:54:13<2:17:52,  1.42it/s]
1|14135|Loss: 0.8212454319000244:  55%|█████▍    | 14135/25880 [2:54:13<2:16:47,  1.43it/s]
1|14136|Loss: 0.8603564500808716:  55%|█████▍    | 14135/25880 [2:54:13<2:16:47,  1.43it/s]
1|14136|Loss: 0.8603564500808716:  55%|█████▍    | 14136/25880 [2:54:13<2:08:33,  1.52it/s]
1|14137|Loss: 0.9853906631469727:  55%|█████▍    | 14136/25880 [2:54:14<2:08:33,  1.52it/s]
1|14137|Loss: 0.9853906631469727:  55%|█████▍    | 14137/25880 [2:54:14<2:15:06,  1.45it/s]
1|14138|Loss: 0.8387098908424377:  55%|█████▍    | 14137/25880 [2:54:15<2:15:06,  1.45it/s]
1|14138|Loss: 0.8387098908424377:  55%|█████▍    | 14138/25880 [2:54:15<2:13:31,  1.47it/s]
1|14139|Loss: 0.8741540908813477:  55%|█████▍    | 14138/25880 [2:54:15<2:13:31,  1.47it/s]
1|14139|Loss: 0.8741540908813477:  55%|█████▍    | 14139/25880 [2:54:16<2:14:52,  1.45it/s]
1|14140|Loss: 0.6973573565483093:  55%|█████▍    | 14139/25880 [2:54:16<2:14:52,  1.45it/s]
1|14140|Loss: 0.6973573565483093:  55%|█████▍    | 14140/25880 [2:54:16<2:21:56,  1.38it/s]
1|14141|Loss: 1.0256588459014893:  55%|█████▍    | 14140/25880 [2:54:17<2:21:56,  1.38it/s]
1|14141|Loss: 1.0256588459014893:  55%|█████▍    | 14141/25880 [2:54:17<2:26:57,  1.33it/s]
1|14142|Loss: 0.7634796500205994:  55%|█████▍    | 14141/25880 [2:54:18<2:26:57,  1.33it/s]
1|14142|Loss: 0.7634796500205994:  55%|█████▍    | 14142/25880 [2:54:18<2:27:09,  1.33it/s]
1|14143|Loss: 0.8735320568084717:  55%|█████▍    | 14142/25880 [2:54:18<2:27:09,  1.33it/s]
1|14143|Loss: 0.8735320568084717:  55%|█████▍    | 14143/25880 [2:54:19<2:30:54,  1.30it/s]
1|14144|Loss: 0.8215620517730713:  55%|█████▍    | 14143/25880 [2:54:19<2:30:54,  1.30it/s]
1|14144|Loss: 0.8215620517730713:  55%|█████▍    | 14144/25880 [2:54:20<2:32:50,  1.28it/s]
1|14145|Loss: 0.8983583450317383:  55%|█████▍    | 14144/25880 [2:54:20<2:32:50,  1.28it/s]
1|14145|Loss: 0.8983583450317383:  55%|█████▍    | 14145/25880 [2:54:20<2:21:06,  1.39it/s]
1|14146|Loss: 0.7801159024238586:  55%|█████▍    | 14145/25880 [2:54:21<2:21:06,  1.39it/s]
1|14146|Loss: 0.7801159024238586:  55%|█████▍    | 14146/25880 [2:54:21<2:19:18,  1.40it/s]
1|14147|Loss: 0.7679224610328674:  55%|█████▍    | 14146/25880 [2:54:21<2:19:18,  1.40it/s]
1|14147|Loss: 0.7679224610328674:  55%|█████▍    | 14147/25880 [2:54:21<2:08:32,  1.52it/s]
1|14148|Loss: 0.9487327337265015:  55%|█████▍    | 14147/25880 [2:54:22<2:08:32,  1.52it/s]
1|14148|Loss: 0.9487327337265015:  55%|█████▍    | 14148/25880 [2:54:22<2:13:10,  1.47it/s]
1|14149|Loss: 0.714526891708374:  55%|█████▍    | 14148/25880 [2:54:22<2:13:10,  1.47it/s] 
1|14149|Loss: 0.714526891708374:  55%|█████▍    | 14149/25880 [2:54:23<2:04:11,  1.57it/s]
1|14150|Loss: 0.7552086710929871:  55%|█████▍    | 14149/25880 [2:54:23<2:04:11,  1.57it/s]
1|14150|Loss: 0.7552086710929871:  55%|█████▍    | 14150/25880 [2:54:23<1:59:55,  1.63it/s]
1|14151|Loss: 0.9109943509101868:  55%|█████▍    | 14150/25880 [2:54:24<1:59:55,  1.63it/s]
1|14151|Loss: 0.9109943509101868:  55%|█████▍    | 14151/25880 [2:54:24<2:04:33,  1.57it/s]
1|14152|Loss: 0.9300543665885925:  55%|█████▍    | 14151/25880 [2:54:24<2:04:33,  1.57it/s]
1|14152|Loss: 0.9300543665885925:  55%|█████▍    | 14152/25880 [2:54:25<2:08:38,  1.52it/s]
1|14153|Loss: 0.7371834516525269:  55%|█████▍    | 14152/25880 [2:54:25<2:08:38,  1.52it/s]
1|14153|Loss: 0.7371834516525269:  55%|█████▍    | 14153/25880 [2:54:25<2:15:52,  1.44it/s]
1|14154|Loss: 0.7723681926727295:  55%|█████▍    | 14153/25880 [2:54:26<2:15:52,  1.44it/s]
1|14154|Loss: 0.7723681926727295:  55%|█████▍    | 14154/25880 [2:54:26<2:23:07,  1.37it/s]
1|14155|Loss: 0.9029423594474792:  55%|█████▍    | 14154/25880 [2:54:27<2:23:07,  1.37it/s]
1|14155|Loss: 0.9029423594474792:  55%|█████▍    | 14155/25880 [2:54:27<2:24:31,  1.35it/s]
1|14156|Loss: 0.9353817105293274:  55%|█████▍    | 14155/25880 [2:54:27<2:24:31,  1.35it/s]
1|14156|Loss: 0.9353817105293274:  55%|█████▍    | 14156/25880 [2:54:28<2:32:52,  1.28it/s]
1|14157|Loss: 0.748368501663208:  55%|█████▍    | 14156/25880 [2:54:28<2:32:52,  1.28it/s] 
1|14157|Loss: 0.748368501663208:  55%|█████▍    | 14157/25880 [2:54:29<2:32:22,  1.28it/s]
1|14158|Loss: 0.8826524615287781:  55%|█████▍    | 14157/25880 [2:54:29<2:32:22,  1.28it/s]
1|14158|Loss: 0.8826524615287781:  55%|█████▍    | 14158/25880 [2:54:29<2:29:47,  1.30it/s]
1|14159|Loss: 0.7686686515808105:  55%|█████▍    | 14158/25880 [2:54:30<2:29:47,  1.30it/s]
1|14159|Loss: 0.7686686515808105:  55%|█████▍    | 14159/25880 [2:54:30<2:26:23,  1.33it/s]
1|14160|Loss: 0.9237866997718811:  55%|█████▍    | 14159/25880 [2:54:31<2:26:23,  1.33it/s]
1|14160|Loss: 0.9237866997718811:  55%|█████▍    | 14160/25880 [2:54:31<2:35:55,  1.25it/s]
1|14161|Loss: 0.9368031620979309:  55%|█████▍    | 14160/25880 [2:54:31<2:35:55,  1.25it/s]
1|14161|Loss: 0.9368031620979309:  55%|█████▍    | 14161/25880 [2:54:32<2:35:18,  1.26it/s]
1|14162|Loss: 0.9700480103492737:  55%|█████▍    | 14161/25880 [2:54:32<2:35:18,  1.26it/s]
1|14162|Loss: 0.9700480103492737:  55%|█████▍    | 14162/25880 [2:54:33<2:34:26,  1.26it/s]
1|14163|Loss: 0.854602575302124:  55%|█████▍    | 14162/25880 [2:54:33<2:34:26,  1.26it/s] 
1|14163|Loss: 0.854602575302124:  55%|█████▍    | 14163/25880 [2:54:33<2:24:38,  1.35it/s]
1|14164|Loss: 0.8442813158035278:  55%|█████▍    | 14163/25880 [2:54:34<2:24:38,  1.35it/s]
1|14164|Loss: 0.8442813158035278:  55%|█████▍    | 14164/25880 [2:54:34<2:22:08,  1.37it/s]
1|14165|Loss: 0.795746386051178:  55%|█████▍    | 14164/25880 [2:54:34<2:22:08,  1.37it/s] 
1|14165|Loss: 0.795746386051178:  55%|█████▍    | 14165/25880 [2:54:35<2:17:06,  1.42it/s]
1|14166|Loss: 0.8676077127456665:  55%|█████▍    | 14165/25880 [2:54:35<2:17:06,  1.42it/s]
1|14166|Loss: 0.8676077127456665:  55%|█████▍    | 14166/25880 [2:54:35<2:12:57,  1.47it/s]
1|14167|Loss: 0.9073817133903503:  55%|█████▍    | 14166/25880 [2:54:36<2:12:57,  1.47it/s]
1|14167|Loss: 0.9073817133903503:  55%|█████▍    | 14167/25880 [2:54:36<2:14:51,  1.45it/s]
1|14168|Loss: 0.7991960048675537:  55%|█████▍    | 14167/25880 [2:54:36<2:14:51,  1.45it/s]
1|14168|Loss: 0.7991960048675537:  55%|█████▍    | 14168/25880 [2:54:37<2:11:52,  1.48it/s]
1|14169|Loss: 0.6887620687484741:  55%|█████▍    | 14168/25880 [2:54:37<2:11:52,  1.48it/s]
1|14169|Loss: 0.6887620687484741:  55%|█████▍    | 14169/25880 [2:54:37<2:03:43,  1.58it/s]
1|14170|Loss: 0.6648293733596802:  55%|█████▍    | 14169/25880 [2:54:37<2:03:43,  1.58it/s]
1|14170|Loss: 0.6648293733596802:  55%|█████▍    | 14170/25880 [2:54:38<2:00:19,  1.62it/s]
1|14171|Loss: 0.7996528744697571:  55%|█████▍    | 14170/25880 [2:54:38<2:00:19,  1.62it/s]
1|14171|Loss: 0.7996528744697571:  55%|█████▍    | 14171/25880 [2:54:38<2:07:42,  1.53it/s]
1|14172|Loss: 0.8746872544288635:  55%|█████▍    | 14171/25880 [2:54:39<2:07:42,  1.53it/s]
1|14172|Loss: 0.8746872544288635:  55%|█████▍    | 14172/25880 [2:54:39<2:17:34,  1.42it/s]
1|14173|Loss: 0.887984573841095:  55%|█████▍    | 14172/25880 [2:54:40<2:17:34,  1.42it/s] 
1|14173|Loss: 0.887984573841095:  55%|█████▍    | 14173/25880 [2:54:40<2:23:18,  1.36it/s]
1|14174|Loss: 0.8966901302337646:  55%|█████▍    | 14173/25880 [2:54:40<2:23:18,  1.36it/s]
1|14174|Loss: 0.8966901302337646:  55%|█████▍    | 14174/25880 [2:54:41<2:26:31,  1.33it/s]
1|14175|Loss: 0.9198209047317505:  55%|█████▍    | 14174/25880 [2:54:41<2:26:31,  1.33it/s]
1|14175|Loss: 0.9198209047317505:  55%|█████▍    | 14175/25880 [2:54:42<2:26:36,  1.33it/s]
1|14176|Loss: 0.8132866024971008:  55%|█████▍    | 14175/25880 [2:54:42<2:26:36,  1.33it/s]
1|14176|Loss: 0.8132866024971008:  55%|█████▍    | 14176/25880 [2:54:42<2:25:45,  1.34it/s]
1|14177|Loss: 0.793919563293457:  55%|█████▍    | 14176/25880 [2:54:43<2:25:45,  1.34it/s] 
1|14177|Loss: 0.793919563293457:  55%|█████▍    | 14177/25880 [2:54:43<2:31:07,  1.29it/s]
1|14178|Loss: 0.79018235206604:  55%|█████▍    | 14177/25880 [2:54:44<2:31:07,  1.29it/s] 
1|14178|Loss: 0.79018235206604:  55%|█████▍    | 14178/25880 [2:54:44<2:22:06,  1.37it/s]
1|14179|Loss: 0.7859674692153931:  55%|█████▍    | 14178/25880 [2:54:44<2:22:06,  1.37it/s]
1|14179|Loss: 0.7859674692153931:  55%|█████▍    | 14179/25880 [2:54:44<2:20:25,  1.39it/s]
1|14180|Loss: 0.9445916414260864:  55%|█████▍    | 14179/25880 [2:54:45<2:20:25,  1.39it/s]
1|14180|Loss: 0.9445916414260864:  55%|█████▍    | 14180/25880 [2:54:45<2:17:12,  1.42it/s]
1|14181|Loss: 0.7484623193740845:  55%|█████▍    | 14180/25880 [2:54:45<2:17:12,  1.42it/s]
1|14181|Loss: 0.7484623193740845:  55%|█████▍    | 14181/25880 [2:54:46<2:09:36,  1.50it/s]
1|14182|Loss: 0.9514322280883789:  55%|█████▍    | 14181/25880 [2:54:46<2:09:36,  1.50it/s]
1|14182|Loss: 0.9514322280883789:  55%|█████▍    | 14182/25880 [2:54:46<2:05:49,  1.55it/s]
1|14183|Loss: 0.8048068881034851:  55%|█████▍    | 14182/25880 [2:54:47<2:05:49,  1.55it/s]
1|14183|Loss: 0.8048068881034851:  55%|█████▍    | 14183/25880 [2:54:47<2:10:09,  1.50it/s]
1|14184|Loss: 0.8462421894073486:  55%|█████▍    | 14183/25880 [2:54:47<2:10:09,  1.50it/s]
1|14184|Loss: 0.8462421894073486:  55%|█████▍    | 14184/25880 [2:54:48<2:12:52,  1.47it/s]
1|14185|Loss: 0.8015674948692322:  55%|█████▍    | 14184/25880 [2:54:48<2:12:52,  1.47it/s]
1|14185|Loss: 0.8015674948692322:  55%|█████▍    | 14185/25880 [2:54:49<2:20:06,  1.39it/s]
1|14186|Loss: 0.7722585201263428:  55%|█████▍    | 14185/25880 [2:54:49<2:20:06,  1.39it/s]
1|14186|Loss: 0.7722585201263428:  55%|█████▍    | 14186/25880 [2:54:49<2:22:31,  1.37it/s]
1|14187|Loss: 0.866398811340332:  55%|█████▍    | 14186/25880 [2:54:50<2:22:31,  1.37it/s] 
1|14187|Loss: 0.866398811340332:  55%|█████▍    | 14187/25880 [2:54:50<2:28:51,  1.31it/s]
1|14188|Loss: 0.9452899098396301:  55%|█████▍    | 14187/25880 [2:54:51<2:28:51,  1.31it/s]
1|14188|Loss: 0.9452899098396301:  55%|█████▍    | 14188/25880 [2:54:51<2:24:23,  1.35it/s]
1|14189|Loss: 0.6740302443504333:  55%|█████▍    | 14188/25880 [2:54:51<2:24:23,  1.35it/s]
1|14189|Loss: 0.6740302443504333:  55%|█████▍    | 14189/25880 [2:54:51<2:17:16,  1.42it/s]
1|14190|Loss: 0.8253393769264221:  55%|█████▍    | 14189/25880 [2:54:52<2:17:16,  1.42it/s]
1|14190|Loss: 0.8253393769264221:  55%|█████▍    | 14190/25880 [2:54:52<2:20:50,  1.38it/s]
1|14191|Loss: 0.7797375917434692:  55%|█████▍    | 14190/25880 [2:54:53<2:20:50,  1.38it/s]
1|14191|Loss: 0.7797375917434692:  55%|█████▍    | 14191/25880 [2:54:53<2:20:48,  1.38it/s]
1|14192|Loss: 0.8531913757324219:  55%|█████▍    | 14191/25880 [2:54:53<2:20:48,  1.38it/s]
1|14192|Loss: 0.8531913757324219:  55%|█████▍    | 14192/25880 [2:54:54<2:26:42,  1.33it/s]
1|14193|Loss: 0.8087084293365479:  55%|█████▍    | 14192/25880 [2:54:54<2:26:42,  1.33it/s]
1|14193|Loss: 0.8087084293365479:  55%|█████▍    | 14193/25880 [2:54:54<2:20:50,  1.38it/s]
1|14194|Loss: 0.8962586522102356:  55%|█████▍    | 14193/25880 [2:54:55<2:20:50,  1.38it/s]
1|14194|Loss: 0.8962586522102356:  55%|█████▍    | 14194/25880 [2:54:55<2:22:36,  1.37it/s]
1|14195|Loss: 0.8973498940467834:  55%|█████▍    | 14194/25880 [2:54:56<2:22:36,  1.37it/s]
1|14195|Loss: 0.8973498940467834:  55%|█████▍    | 14195/25880 [2:54:56<2:23:50,  1.35it/s]
1|14196|Loss: 0.831683874130249:  55%|█████▍    | 14195/25880 [2:54:56<2:23:50,  1.35it/s] 
1|14196|Loss: 0.831683874130249:  55%|█████▍    | 14196/25880 [2:54:57<2:33:01,  1.27it/s]
1|14197|Loss: 0.8340954184532166:  55%|█████▍    | 14196/25880 [2:54:57<2:33:01,  1.27it/s]
1|14197|Loss: 0.8340954184532166:  55%|█████▍    | 14197/25880 [2:54:58<2:43:41,  1.19it/s]
1|14198|Loss: 0.9213167428970337:  55%|█████▍    | 14197/25880 [2:54:58<2:43:41,  1.19it/s]
1|14198|Loss: 0.9213167428970337:  55%|█████▍    | 14198/25880 [2:54:59<2:42:58,  1.19it/s]
1|14199|Loss: 0.8724253177642822:  55%|█████▍    | 14198/25880 [2:54:59<2:42:58,  1.19it/s]
1|14199|Loss: 0.8724253177642822:  55%|█████▍    | 14199/25880 [2:54:59<2:44:22,  1.18it/s]
1|14200|Loss: 1.0344018936157227:  55%|█████▍    | 14199/25880 [2:55:00<2:44:22,  1.18it/s]
1|14200|Loss: 1.0344018936157227:  55%|█████▍    | 14200/25880 [2:55:00<2:40:28,  1.21it/s]
1|14201|Loss: 0.8156081438064575:  55%|█████▍    | 14200/25880 [2:55:01<2:40:28,  1.21it/s]
1|14201|Loss: 0.8156081438064575:  55%|█████▍    | 14201/25880 [2:55:01<2:34:25,  1.26it/s]
1|14202|Loss: 0.7230943441390991:  55%|█████▍    | 14201/25880 [2:55:01<2:34:25,  1.26it/s]
1|14202|Loss: 0.7230943441390991:  55%|█████▍    | 14202/25880 [2:55:02<2:28:51,  1.31it/s]
1|14203|Loss: 0.7548882365226746:  55%|█████▍    | 14202/25880 [2:55:02<2:28:51,  1.31it/s]
1|14203|Loss: 0.7548882365226746:  55%|█████▍    | 14203/25880 [2:55:02<2:19:17,  1.40it/s]
1|14204|Loss: 0.781091570854187:  55%|█████▍    | 14203/25880 [2:55:03<2:19:17,  1.40it/s] 
1|14204|Loss: 0.781091570854187:  55%|█████▍    | 14204/25880 [2:55:03<2:08:09,  1.52it/s]
1|14205|Loss: 0.840630829334259:  55%|█████▍    | 14204/25880 [2:55:03<2:08:09,  1.52it/s]
1|14205|Loss: 0.840630829334259:  55%|█████▍    | 14205/25880 [2:55:04<2:16:40,  1.42it/s]
1|14206|Loss: 0.824547529220581:  55%|█████▍    | 14205/25880 [2:55:04<2:16:40,  1.42it/s]
1|14206|Loss: 0.824547529220581:  55%|█████▍    | 14206/25880 [2:55:04<2:15:16,  1.44it/s]
1|14207|Loss: 0.8143407106399536:  55%|█████▍    | 14206/25880 [2:55:05<2:15:16,  1.44it/s]
1|14207|Loss: 0.8143407106399536:  55%|█████▍    | 14207/25880 [2:55:05<2:16:14,  1.43it/s]
1|14208|Loss: 0.800060510635376:  55%|█████▍    | 14207/25880 [2:55:05<2:16:14,  1.43it/s] 
1|14208|Loss: 0.800060510635376:  55%|█████▍    | 14208/25880 [2:55:06<2:22:31,  1.36it/s]
1|14209|Loss: 0.886839747428894:  55%|█████▍    | 14208/25880 [2:55:06<2:22:31,  1.36it/s]
1|14209|Loss: 0.886839747428894:  55%|█████▍    | 14209/25880 [2:55:07<2:23:22,  1.36it/s]
1|14210|Loss: 0.7180130481719971:  55%|█████▍    | 14209/25880 [2:55:07<2:23:22,  1.36it/s]
1|14210|Loss: 0.7180130481719971:  55%|█████▍    | 14210/25880 [2:55:07<2:22:52,  1.36it/s]
1|14211|Loss: 0.7137812972068787:  55%|█████▍    | 14210/25880 [2:55:08<2:22:52,  1.36it/s]
1|14211|Loss: 0.7137812972068787:  55%|█████▍    | 14211/25880 [2:55:08<2:23:43,  1.35it/s]
1|14212|Loss: 0.8843502402305603:  55%|█████▍    | 14211/25880 [2:55:08<2:23:43,  1.35it/s]
1|14212|Loss: 0.8843502402305603:  55%|█████▍    | 14212/25880 [2:55:09<2:30:47,  1.29it/s]
1|14213|Loss: 0.8276413083076477:  55%|█████▍    | 14212/25880 [2:55:09<2:30:47,  1.29it/s]
1|14213|Loss: 0.8276413083076477:  55%|█████▍    | 14213/25880 [2:55:10<2:24:56,  1.34it/s]
1|14214|Loss: 0.885208249092102:  55%|█████▍    | 14213/25880 [2:55:10<2:24:56,  1.34it/s] 
1|14214|Loss: 0.885208249092102:  55%|█████▍    | 14214/25880 [2:55:10<2:28:14,  1.31it/s]
1|14215|Loss: 0.7596167922019958:  55%|█████▍    | 14214/25880 [2:55:11<2:28:14,  1.31it/s]
1|14215|Loss: 0.7596167922019958:  55%|█████▍    | 14215/25880 [2:55:11<2:24:03,  1.35it/s]
1|14216|Loss: 0.7547061443328857:  55%|█████▍    | 14215/25880 [2:55:11<2:24:03,  1.35it/s]
1|14216|Loss: 0.7547061443328857:  55%|█████▍    | 14216/25880 [2:55:12<2:22:06,  1.37it/s]
1|14217|Loss: 0.6889159679412842:  55%|█████▍    | 14216/25880 [2:55:12<2:22:06,  1.37it/s]
1|14217|Loss: 0.6889159679412842:  55%|█████▍    | 14217/25880 [2:55:12<2:16:31,  1.42it/s]
1|14218|Loss: 0.8199450969696045:  55%|█████▍    | 14217/25880 [2:55:13<2:16:31,  1.42it/s]
1|14218|Loss: 0.8199450969696045:  55%|█████▍    | 14218/25880 [2:55:13<2:12:43,  1.46it/s]
1|14219|Loss: 0.7368927001953125:  55%|█████▍    | 14218/25880 [2:55:13<2:12:43,  1.46it/s]
1|14219|Loss: 0.7368927001953125:  55%|█████▍    | 14219/25880 [2:55:14<2:01:12,  1.60it/s]
1|14220|Loss: 0.8824547529220581:  55%|█████▍    | 14219/25880 [2:55:14<2:01:12,  1.60it/s]
1|14220|Loss: 0.8824547529220581:  55%|█████▍    | 14220/25880 [2:55:14<2:04:54,  1.56it/s]
1|14221|Loss: 0.986463725566864:  55%|█████▍    | 14220/25880 [2:55:15<2:04:54,  1.56it/s] 
1|14221|Loss: 0.986463725566864:  55%|█████▍    | 14221/25880 [2:55:15<2:09:26,  1.50it/s]
1|14222|Loss: 0.8720227479934692:  55%|█████▍    | 14221/25880 [2:55:15<2:09:26,  1.50it/s]
1|14222|Loss: 0.8720227479934692:  55%|█████▍    | 14222/25880 [2:55:16<2:11:24,  1.48it/s]
1|14223|Loss: 0.9858130216598511:  55%|█████▍    | 14222/25880 [2:55:16<2:11:24,  1.48it/s]
1|14223|Loss: 0.9858130216598511:  55%|█████▍    | 14223/25880 [2:55:16<2:19:41,  1.39it/s]
1|14224|Loss: 0.9158697724342346:  55%|█████▍    | 14223/25880 [2:55:17<2:19:41,  1.39it/s]
1|14224|Loss: 0.9158697724342346:  55%|█████▍    | 14224/25880 [2:55:17<2:17:00,  1.42it/s]
1|14225|Loss: 0.7292715907096863:  55%|█████▍    | 14224/25880 [2:55:17<2:17:00,  1.42it/s]
1|14225|Loss: 0.7292715907096863:  55%|█████▍    | 14225/25880 [2:55:18<2:16:10,  1.43it/s]
1|14226|Loss: 0.942815363407135:  55%|█████▍    | 14225/25880 [2:55:18<2:16:10,  1.43it/s] 
1|14226|Loss: 0.942815363407135:  55%|█████▍    | 14226/25880 [2:55:18<2:12:14,  1.47it/s]
1|14227|Loss: 0.9004683494567871:  55%|█████▍    | 14226/25880 [2:55:19<2:12:14,  1.47it/s]
1|14227|Loss: 0.9004683494567871:  55%|█████▍    | 14227/25880 [2:55:19<2:08:49,  1.51it/s]
1|14228|Loss: 0.7905756235122681:  55%|█████▍    | 14227/25880 [2:55:19<2:08:49,  1.51it/s]
1|14228|Loss: 0.7905756235122681:  55%|█████▍    | 14228/25880 [2:55:20<2:11:36,  1.48it/s]
1|14229|Loss: 0.6520184874534607:  55%|█████▍    | 14228/25880 [2:55:20<2:11:36,  1.48it/s]
1|14229|Loss: 0.6520184874534607:  55%|█████▍    | 14229/25880 [2:55:21<2:23:34,  1.35it/s]
1|14230|Loss: 0.8162025213241577:  55%|█████▍    | 14229/25880 [2:55:21<2:23:34,  1.35it/s]
1|14230|Loss: 0.8162025213241577:  55%|█████▍    | 14230/25880 [2:55:21<2:25:07,  1.34it/s]
1|14231|Loss: 0.7242134213447571:  55%|█████▍    | 14230/25880 [2:55:22<2:25:07,  1.34it/s]
1|14231|Loss: 0.7242134213447571:  55%|█████▍    | 14231/25880 [2:55:22<2:18:28,  1.40it/s]
1|14232|Loss: 0.9498692154884338:  55%|█████▍    | 14231/25880 [2:55:22<2:18:28,  1.40it/s]
1|14232|Loss: 0.9498692154884338:  55%|█████▍    | 14232/25880 [2:55:23<2:16:51,  1.42it/s]
1|14233|Loss: 0.9340961575508118:  55%|█████▍    | 14232/25880 [2:55:23<2:16:51,  1.42it/s]
1|14233|Loss: 0.9340961575508118:  55%|█████▍    | 14233/25880 [2:55:24<2:20:42,  1.38it/s]
1|14234|Loss: 0.9132077693939209:  55%|█████▍    | 14233/25880 [2:55:24<2:20:42,  1.38it/s]
1|14234|Loss: 0.9132077693939209:  55%|█████▌    | 14234/25880 [2:55:24<2:17:31,  1.41it/s]
1|14235|Loss: 0.8557599186897278:  55%|█████▌    | 14234/25880 [2:55:25<2:17:31,  1.41it/s]
1|14235|Loss: 0.8557599186897278:  55%|█████▌    | 14235/25880 [2:55:25<2:13:54,  1.45it/s]
1|14236|Loss: 0.7551250457763672:  55%|█████▌    | 14235/25880 [2:55:25<2:13:54,  1.45it/s]
1|14236|Loss: 0.7551250457763672:  55%|█████▌    | 14236/25880 [2:55:26<2:18:45,  1.40it/s]
1|14237|Loss: 0.8397749662399292:  55%|█████▌    | 14236/25880 [2:55:26<2:18:45,  1.40it/s]
1|14237|Loss: 0.8397749662399292:  55%|█████▌    | 14237/25880 [2:55:26<2:25:09,  1.34it/s]
1|14238|Loss: 0.8147663474082947:  55%|█████▌    | 14237/25880 [2:55:27<2:25:09,  1.34it/s]
1|14238|Loss: 0.8147663474082947:  55%|█████▌    | 14238/25880 [2:55:27<2:30:47,  1.29it/s]
1|14239|Loss: 0.7815330624580383:  55%|█████▌    | 14238/25880 [2:55:28<2:30:47,  1.29it/s]
1|14239|Loss: 0.7815330624580383:  55%|█████▌    | 14239/25880 [2:55:28<2:33:04,  1.27it/s]
1|14240|Loss: 0.8194959163665771:  55%|█████▌    | 14239/25880 [2:55:28<2:33:04,  1.27it/s]
1|14240|Loss: 0.8194959163665771:  55%|█████▌    | 14240/25880 [2:55:29<2:26:08,  1.33it/s]
1|14241|Loss: 0.7592318058013916:  55%|█████▌    | 14240/25880 [2:55:29<2:26:08,  1.33it/s]
1|14241|Loss: 0.7592318058013916:  55%|█████▌    | 14241/25880 [2:55:29<2:11:08,  1.48it/s]
1|14242|Loss: 0.8416925072669983:  55%|█████▌    | 14241/25880 [2:55:30<2:11:08,  1.48it/s]
1|14242|Loss: 0.8416925072669983:  55%|█████▌    | 14242/25880 [2:55:30<2:13:34,  1.45it/s]
1|14243|Loss: 0.8288830518722534:  55%|█████▌    | 14242/25880 [2:55:30<2:13:34,  1.45it/s]
1|14243|Loss: 0.8288830518722534:  55%|█████▌    | 14243/25880 [2:55:31<2:11:47,  1.47it/s]
1|14244|Loss: 0.8381320238113403:  55%|█████▌    | 14243/25880 [2:55:31<2:11:47,  1.47it/s]
1|14244|Loss: 0.8381320238113403:  55%|█████▌    | 14244/25880 [2:55:31<2:14:35,  1.44it/s]
1|14245|Loss: 0.8827121257781982:  55%|█████▌    | 14244/25880 [2:55:32<2:14:35,  1.44it/s]
1|14245|Loss: 0.8827121257781982:  55%|█████▌    | 14245/25880 [2:55:32<2:13:08,  1.46it/s]
1|14246|Loss: 0.7072664499282837:  55%|█████▌    | 14245/25880 [2:55:32<2:13:08,  1.46it/s]
1|14246|Loss: 0.7072664499282837:  55%|█████▌    | 14246/25880 [2:55:33<2:19:20,  1.39it/s]
1|14247|Loss: 0.7659361362457275:  55%|█████▌    | 14246/25880 [2:55:33<2:19:20,  1.39it/s]
1|14247|Loss: 0.7659361362457275:  55%|█████▌    | 14247/25880 [2:55:33<2:15:55,  1.43it/s]
1|14248|Loss: 0.8877460360527039:  55%|█████▌    | 14247/25880 [2:55:34<2:15:55,  1.43it/s]
1|14248|Loss: 0.8877460360527039:  55%|█████▌    | 14248/25880 [2:55:34<2:21:41,  1.37it/s]
1|14249|Loss: 0.8523845076560974:  55%|█████▌    | 14248/25880 [2:55:35<2:21:41,  1.37it/s]
1|14249|Loss: 0.8523845076560974:  55%|█████▌    | 14249/25880 [2:55:35<2:16:23,  1.42it/s]
1|14250|Loss: 0.8428512811660767:  55%|█████▌    | 14249/25880 [2:55:35<2:16:23,  1.42it/s]
1|14250|Loss: 0.8428512811660767:  55%|█████▌    | 14250/25880 [2:55:36<2:15:10,  1.43it/s]
1|14251|Loss: 0.8841935992240906:  55%|█████▌    | 14250/25880 [2:55:36<2:15:10,  1.43it/s]
1|14251|Loss: 0.8841935992240906:  55%|█████▌    | 14251/25880 [2:55:36<2:12:15,  1.47it/s]
1|14252|Loss: 0.932811439037323:  55%|█████▌    | 14251/25880 [2:55:37<2:12:15,  1.47it/s] 
1|14252|Loss: 0.932811439037323:  55%|█████▌    | 14252/25880 [2:55:37<2:20:51,  1.38it/s]
1|14253|Loss: 0.7692847847938538:  55%|█████▌    | 14252/25880 [2:55:38<2:20:51,  1.38it/s]
1|14253|Loss: 0.7692847847938538:  55%|█████▌    | 14253/25880 [2:55:38<2:21:40,  1.37it/s]
1|14254|Loss: 0.815531849861145:  55%|█████▌    | 14253/25880 [2:55:38<2:21:40,  1.37it/s] 
1|14254|Loss: 0.815531849861145:  55%|█████▌    | 14254/25880 [2:55:39<2:23:43,  1.35it/s]
1|14255|Loss: 0.8453782796859741:  55%|█████▌    | 14254/25880 [2:55:39<2:23:43,  1.35it/s]
1|14255|Loss: 0.8453782796859741:  55%|█████▌    | 14255/25880 [2:55:39<2:22:45,  1.36it/s]
1|14256|Loss: 0.8521019220352173:  55%|█████▌    | 14255/25880 [2:55:40<2:22:45,  1.36it/s]
1|14256|Loss: 0.8521019220352173:  55%|█████▌    | 14256/25880 [2:55:40<2:28:32,  1.30it/s]
1|14257|Loss: 0.7277613878250122:  55%|█████▌    | 14256/25880 [2:55:41<2:28:32,  1.30it/s]
1|14257|Loss: 0.7277613878250122:  55%|█████▌    | 14257/25880 [2:55:41<2:28:50,  1.30it/s]
1|14258|Loss: 0.7965519428253174:  55%|█████▌    | 14257/25880 [2:55:41<2:28:50,  1.30it/s]
1|14258|Loss: 0.7965519428253174:  55%|█████▌    | 14258/25880 [2:55:42<2:25:50,  1.33it/s]
1|14259|Loss: 0.8903963565826416:  55%|█████▌    | 14258/25880 [2:55:42<2:25:50,  1.33it/s]
1|14259|Loss: 0.8903963565826416:  55%|█████▌    | 14259/25880 [2:55:42<2:24:07,  1.34it/s]
1|14260|Loss: 0.8921101689338684:  55%|█████▌    | 14259/25880 [2:55:43<2:24:07,  1.34it/s]
1|14260|Loss: 0.8921101689338684:  55%|█████▌    | 14260/25880 [2:55:43<2:22:44,  1.36it/s]
1|14261|Loss: 0.7459953427314758:  55%|█████▌    | 14260/25880 [2:55:43<2:22:44,  1.36it/s]
1|14261|Loss: 0.7459953427314758:  55%|█████▌    | 14261/25880 [2:55:44<2:16:46,  1.42it/s]
1|14262|Loss: 0.9868274927139282:  55%|█████▌    | 14261/25880 [2:55:44<2:16:46,  1.42it/s]
1|14262|Loss: 0.9868274927139282:  55%|█████▌    | 14262/25880 [2:55:44<2:12:27,  1.46it/s]
1|14263|Loss: 0.809794545173645:  55%|█████▌    | 14262/25880 [2:55:45<2:12:27,  1.46it/s] 
1|14263|Loss: 0.809794545173645:  55%|█████▌    | 14263/25880 [2:55:45<2:14:28,  1.44it/s]
1|14264|Loss: 0.8266268968582153:  55%|█████▌    | 14263/25880 [2:55:45<2:14:28,  1.44it/s]
1|14264|Loss: 0.8266268968582153:  55%|█████▌    | 14264/25880 [2:55:46<2:08:32,  1.51it/s]
1|14265|Loss: 0.9057055711746216:  55%|█████▌    | 14264/25880 [2:55:46<2:08:32,  1.51it/s]
1|14265|Loss: 0.9057055711746216:  55%|█████▌    | 14265/25880 [2:55:46<2:15:10,  1.43it/s]
1|14266|Loss: 0.861327052116394:  55%|█████▌    | 14265/25880 [2:55:47<2:15:10,  1.43it/s] 
1|14266|Loss: 0.861327052116394:  55%|█████▌    | 14266/25880 [2:55:47<2:16:34,  1.42it/s]
1|14267|Loss: 0.991144597530365:  55%|█████▌    | 14266/25880 [2:55:47<2:16:34,  1.42it/s]
1|14267|Loss: 0.991144597530365:  55%|█████▌    | 14267/25880 [2:55:48<2:04:38,  1.55it/s]
1|14268|Loss: 0.7666089534759521:  55%|█████▌    | 14267/25880 [2:55:48<2:04:38,  1.55it/s]
1|14268|Loss: 0.7666089534759521:  55%|█████▌    | 14268/25880 [2:55:48<2:12:43,  1.46it/s]
1|14269|Loss: 0.8369110226631165:  55%|█████▌    | 14268/25880 [2:55:49<2:12:43,  1.46it/s]
1|14269|Loss: 0.8369110226631165:  55%|█████▌    | 14269/25880 [2:55:49<2:17:12,  1.41it/s]
1|14270|Loss: 0.8149370551109314:  55%|█████▌    | 14269/25880 [2:55:50<2:17:12,  1.41it/s]
1|14270|Loss: 0.8149370551109314:  55%|█████▌    | 14270/25880 [2:55:50<2:18:58,  1.39it/s]
1|14271|Loss: 0.8537790775299072:  55%|█████▌    | 14270/25880 [2:55:50<2:18:58,  1.39it/s]
1|14271|Loss: 0.8537790775299072:  55%|█████▌    | 14271/25880 [2:55:51<2:14:36,  1.44it/s]
1|14272|Loss: 0.6772639751434326:  55%|█████▌    | 14271/25880 [2:55:51<2:14:36,  1.44it/s]
1|14272|Loss: 0.6772639751434326:  55%|█████▌    | 14272/25880 [2:55:51<2:03:55,  1.56it/s]
1|14273|Loss: 0.8982923030853271:  55%|█████▌    | 14272/25880 [2:55:51<2:03:55,  1.56it/s]
1|14273|Loss: 0.8982923030853271:  55%|█████▌    | 14273/25880 [2:55:52<2:10:56,  1.48it/s]
1|14274|Loss: 0.7814778089523315:  55%|█████▌    | 14273/25880 [2:55:52<2:10:56,  1.48it/s]
1|14274|Loss: 0.7814778089523315:  55%|█████▌    | 14274/25880 [2:55:53<2:22:19,  1.36it/s]
1|14275|Loss: 0.8890916109085083:  55%|█████▌    | 14274/25880 [2:55:53<2:22:19,  1.36it/s]
1|14275|Loss: 0.8890916109085083:  55%|█████▌    | 14275/25880 [2:55:53<2:17:44,  1.40it/s]
1|14276|Loss: 0.8170811533927917:  55%|█████▌    | 14275/25880 [2:55:54<2:17:44,  1.40it/s]
1|14276|Loss: 0.8170811533927917:  55%|█████▌    | 14276/25880 [2:55:54<2:25:53,  1.33it/s]
1|14277|Loss: 0.9205151200294495:  55%|█████▌    | 14276/25880 [2:55:55<2:25:53,  1.33it/s]
1|14277|Loss: 0.9205151200294495:  55%|█████▌    | 14277/25880 [2:55:55<2:29:11,  1.30it/s]
1|14278|Loss: 0.8071239590644836:  55%|█████▌    | 14277/25880 [2:55:55<2:29:11,  1.30it/s]
1|14278|Loss: 0.8071239590644836:  55%|█████▌    | 14278/25880 [2:55:56<2:17:31,  1.41it/s]
1|14279|Loss: 0.8989490270614624:  55%|█████▌    | 14278/25880 [2:55:56<2:17:31,  1.41it/s]
1|14279|Loss: 0.8989490270614624:  55%|█████▌    | 14279/25880 [2:55:56<2:18:39,  1.39it/s]
1|14280|Loss: 0.9622272253036499:  55%|█████▌    | 14279/25880 [2:55:57<2:18:39,  1.39it/s]
1|14280|Loss: 0.9622272253036499:  55%|█████▌    | 14280/25880 [2:55:57<2:18:49,  1.39it/s]
1|14281|Loss: 0.7680978775024414:  55%|█████▌    | 14280/25880 [2:55:58<2:18:49,  1.39it/s]
1|14281|Loss: 0.7680978775024414:  55%|█████▌    | 14281/25880 [2:55:58<2:26:20,  1.32it/s]
1|14282|Loss: 0.8518079519271851:  55%|█████▌    | 14281/25880 [2:55:58<2:26:20,  1.32it/s]
1|14282|Loss: 0.8518079519271851:  55%|█████▌    | 14282/25880 [2:55:59<2:21:51,  1.36it/s]
1|14283|Loss: 0.8070512413978577:  55%|█████▌    | 14282/25880 [2:55:59<2:21:51,  1.36it/s]
1|14283|Loss: 0.8070512413978577:  55%|█████▌    | 14283/25880 [2:55:59<2:13:51,  1.44it/s]
1|14284|Loss: 0.7758871912956238:  55%|█████▌    | 14283/25880 [2:56:00<2:13:51,  1.44it/s]
1|14284|Loss: 0.7758871912956238:  55%|█████▌    | 14284/25880 [2:56:00<2:19:18,  1.39it/s]
1|14285|Loss: 0.8466458320617676:  55%|█████▌    | 14284/25880 [2:56:00<2:19:18,  1.39it/s]
1|14285|Loss: 0.8466458320617676:  55%|█████▌    | 14285/25880 [2:56:01<2:19:32,  1.38it/s]
1|14286|Loss: 1.0305103063583374:  55%|█████▌    | 14285/25880 [2:56:01<2:19:32,  1.38it/s]
1|14286|Loss: 1.0305103063583374:  55%|█████▌    | 14286/25880 [2:56:02<2:25:23,  1.33it/s]
1|14287|Loss: 0.9186049103736877:  55%|█████▌    | 14286/25880 [2:56:02<2:25:23,  1.33it/s]
1|14287|Loss: 0.9186049103736877:  55%|█████▌    | 14287/25880 [2:56:02<2:24:31,  1.34it/s]
1|14288|Loss: 0.9122632145881653:  55%|█████▌    | 14287/25880 [2:56:03<2:24:31,  1.34it/s]
1|14288|Loss: 0.9122632145881653:  55%|█████▌    | 14288/25880 [2:56:03<2:21:37,  1.36it/s]
1|14289|Loss: 0.7887723445892334:  55%|█████▌    | 14288/25880 [2:56:03<2:21:37,  1.36it/s]
1|14289|Loss: 0.7887723445892334:  55%|█████▌    | 14289/25880 [2:56:04<2:14:04,  1.44it/s]
1|14290|Loss: 0.7925092577934265:  55%|█████▌    | 14289/25880 [2:56:04<2:14:04,  1.44it/s]
1|14290|Loss: 0.7925092577934265:  55%|█████▌    | 14290/25880 [2:56:04<2:06:19,  1.53it/s]
1|14291|Loss: 0.7693064212799072:  55%|█████▌    | 14290/25880 [2:56:05<2:06:19,  1.53it/s]
1|14291|Loss: 0.7693064212799072:  55%|█████▌    | 14291/25880 [2:56:05<2:14:24,  1.44it/s]
1|14292|Loss: 0.9196568131446838:  55%|█████▌    | 14291/25880 [2:56:05<2:14:24,  1.44it/s]
1|14292|Loss: 0.9196568131446838:  55%|█████▌    | 14292/25880 [2:56:06<2:18:29,  1.39it/s]
1|14293|Loss: 0.9038939476013184:  55%|█████▌    | 14292/25880 [2:56:06<2:18:29,  1.39it/s]
1|14293|Loss: 0.9038939476013184:  55%|█████▌    | 14293/25880 [2:56:07<2:26:30,  1.32it/s]
1|14294|Loss: 1.0980602502822876:  55%|█████▌    | 14293/25880 [2:56:07<2:26:30,  1.32it/s]
1|14294|Loss: 1.0980602502822876:  55%|█████▌    | 14294/25880 [2:56:07<2:31:46,  1.27it/s]
1|14295|Loss: 0.8298599720001221:  55%|█████▌    | 14294/25880 [2:56:08<2:31:46,  1.27it/s]
1|14295|Loss: 0.8298599720001221:  55%|█████▌    | 14295/25880 [2:56:08<2:33:47,  1.26it/s]
1|14296|Loss: 0.7877842783927917:  55%|█████▌    | 14295/25880 [2:56:09<2:33:47,  1.26it/s]
1|14296|Loss: 0.7877842783927917:  55%|█████▌    | 14296/25880 [2:56:09<2:31:52,  1.27it/s]
1|14297|Loss: 0.7705739736557007:  55%|█████▌    | 14296/25880 [2:56:09<2:31:52,  1.27it/s]
1|14297|Loss: 0.7705739736557007:  55%|█████▌    | 14297/25880 [2:56:10<2:37:39,  1.22it/s]
1|14298|Loss: 0.7952014803886414:  55%|█████▌    | 14297/25880 [2:56:10<2:37:39,  1.22it/s]
1|14298|Loss: 0.7952014803886414:  55%|█████▌    | 14298/25880 [2:56:11<2:35:08,  1.24it/s]
1|14299|Loss: 0.8316917419433594:  55%|█████▌    | 14298/25880 [2:56:11<2:35:08,  1.24it/s]
1|14299|Loss: 0.8316917419433594:  55%|█████▌    | 14299/25880 [2:56:11<2:33:49,  1.25it/s]
1|14300|Loss: 0.9525391459465027:  55%|█████▌    | 14299/25880 [2:56:12<2:33:49,  1.25it/s]
1|14300|Loss: 0.9525391459465027:  55%|█████▌    | 14300/25880 [2:56:12<2:29:26,  1.29it/s]
1|14301|Loss: 0.8436415195465088:  55%|█████▌    | 14300/25880 [2:56:13<2:29:26,  1.29it/s]
1|14301|Loss: 0.8436415195465088:  55%|█████▌    | 14301/25880 [2:56:13<2:26:42,  1.32it/s]
1|14302|Loss: 0.9007773995399475:  55%|█████▌    | 14301/25880 [2:56:13<2:26:42,  1.32it/s]
1|14302|Loss: 0.9007773995399475:  55%|█████▌    | 14302/25880 [2:56:14<2:24:06,  1.34it/s]
1|14303|Loss: 0.876650333404541:  55%|█████▌    | 14302/25880 [2:56:14<2:24:06,  1.34it/s] 
1|14303|Loss: 0.876650333404541:  55%|█████▌    | 14303/25880 [2:56:14<2:21:07,  1.37it/s]
1|14304|Loss: 0.942793607711792:  55%|█████▌    | 14303/25880 [2:56:15<2:21:07,  1.37it/s]
1|14304|Loss: 0.942793607711792:  55%|█████▌    | 14304/25880 [2:56:15<2:21:10,  1.37it/s]
1|14305|Loss: 0.9674673676490784:  55%|█████▌    | 14304/25880 [2:56:15<2:21:10,  1.37it/s]
1|14305|Loss: 0.9674673676490784:  55%|█████▌    | 14305/25880 [2:56:16<2:17:21,  1.40it/s]
1|14306|Loss: 0.8663155436515808:  55%|█████▌    | 14305/25880 [2:56:16<2:17:21,  1.40it/s]
1|14306|Loss: 0.8663155436515808:  55%|█████▌    | 14306/25880 [2:56:16<2:17:21,  1.40it/s]
1|14307|Loss: 0.7381359934806824:  55%|█████▌    | 14306/25880 [2:56:17<2:17:21,  1.40it/s]
1|14307|Loss: 0.7381359934806824:  55%|█████▌    | 14307/25880 [2:56:17<2:23:57,  1.34it/s]
1|14308|Loss: 0.8686040043830872:  55%|█████▌    | 14307/25880 [2:56:18<2:23:57,  1.34it/s]
1|14308|Loss: 0.8686040043830872:  55%|█████▌    | 14308/25880 [2:56:18<2:13:16,  1.45it/s]
1|14309|Loss: 0.8456061482429504:  55%|█████▌    | 14308/25880 [2:56:18<2:13:16,  1.45it/s]
1|14309|Loss: 0.8456061482429504:  55%|█████▌    | 14309/25880 [2:56:18<2:13:14,  1.45it/s]
1|14310|Loss: 0.7613409757614136:  55%|█████▌    | 14309/25880 [2:56:19<2:13:14,  1.45it/s]
1|14310|Loss: 0.7613409757614136:  55%|█████▌    | 14310/25880 [2:56:19<2:14:41,  1.43it/s]
1|14311|Loss: 0.8105860352516174:  55%|█████▌    | 14310/25880 [2:56:20<2:14:41,  1.43it/s]
1|14311|Loss: 0.8105860352516174:  55%|█████▌    | 14311/25880 [2:56:20<2:12:04,  1.46it/s]
1|14312|Loss: 0.820456862449646:  55%|█████▌    | 14311/25880 [2:56:20<2:12:04,  1.46it/s] 
1|14312|Loss: 0.820456862449646:  55%|█████▌    | 14312/25880 [2:56:21<2:13:46,  1.44it/s]
1|14313|Loss: 0.9174113869667053:  55%|█████▌    | 14312/25880 [2:56:21<2:13:46,  1.44it/s]
1|14313|Loss: 0.9174113869667053:  55%|█████▌    | 14313/25880 [2:56:21<2:27:45,  1.30it/s]
1|14314|Loss: 0.852177619934082:  55%|█████▌    | 14313/25880 [2:56:22<2:27:45,  1.30it/s] 
1|14314|Loss: 0.852177619934082:  55%|█████▌    | 14314/25880 [2:56:22<2:29:10,  1.29it/s]
1|14315|Loss: 0.8002410531044006:  55%|█████▌    | 14314/25880 [2:56:23<2:29:10,  1.29it/s]
1|14315|Loss: 0.8002410531044006:  55%|█████▌    | 14315/25880 [2:56:23<2:27:13,  1.31it/s]
1|14316|Loss: 0.8697634935379028:  55%|█████▌    | 14315/25880 [2:56:23<2:27:13,  1.31it/s]
1|14316|Loss: 0.8697634935379028:  55%|█████▌    | 14316/25880 [2:56:24<2:20:15,  1.37it/s]
1|14317|Loss: 0.8686171770095825:  55%|█████▌    | 14316/25880 [2:56:24<2:20:15,  1.37it/s]
1|14317|Loss: 0.8686171770095825:  55%|█████▌    | 14317/25880 [2:56:24<2:13:40,  1.44it/s]
1|14318|Loss: 0.7874025702476501:  55%|█████▌    | 14317/25880 [2:56:25<2:13:40,  1.44it/s]
1|14318|Loss: 0.7874025702476501:  55%|█████▌    | 14318/25880 [2:56:25<2:14:32,  1.43it/s]
1|14319|Loss: 0.7925419807434082:  55%|█████▌    | 14318/25880 [2:56:25<2:14:32,  1.43it/s]
1|14319|Loss: 0.7925419807434082:  55%|█████▌    | 14319/25880 [2:56:26<2:27:58,  1.30it/s]
1|14320|Loss: 0.8468043208122253:  55%|█████▌    | 14319/25880 [2:56:26<2:27:58,  1.30it/s]
1|14320|Loss: 0.8468043208122253:  55%|█████▌    | 14320/25880 [2:56:27<2:29:18,  1.29it/s]
1|14321|Loss: 0.5853393077850342:  55%|█████▌    | 14320/25880 [2:56:27<2:29:18,  1.29it/s]
1|14321|Loss: 0.5853393077850342:  55%|█████▌    | 14321/25880 [2:56:28<2:41:41,  1.19it/s]
1|14322|Loss: 0.7718287706375122:  55%|█████▌    | 14321/25880 [2:56:28<2:41:41,  1.19it/s]
1|14322|Loss: 0.7718287706375122:  55%|█████▌    | 14322/25880 [2:56:29<2:41:46,  1.19it/s]
1|14323|Loss: 0.9287018179893494:  55%|████���▌    | 14322/25880 [2:56:29<2:41:46,  1.19it/s]
1|14323|Loss: 0.9287018179893494:  55%|█████▌    | 14323/25880 [2:56:29<2:42:20,  1.19it/s]
1|14324|Loss: 0.8237334489822388:  55%|█████▌    | 14323/25880 [2:56:30<2:42:20,  1.19it/s]
1|14324|Loss: 0.8237334489822388:  55%|█████▌    | 14324/25880 [2:56:30<2:36:16,  1.23it/s]
1|14325|Loss: 0.7981579303741455:  55%|█████▌    | 14324/25880 [2:56:31<2:36:16,  1.23it/s]
1|14325|Loss: 0.7981579303741455:  55%|█████▌    | 14325/25880 [2:56:31<2:29:56,  1.28it/s]
1|14326|Loss: 0.7258239388465881:  55%|█████▌    | 14325/25880 [2:56:31<2:29:56,  1.28it/s]
1|14326|Loss: 0.7258239388465881:  55%|█████▌    | 14326/25880 [2:56:32<2:27:27,  1.31it/s]
1|14327|Loss: 0.906379222869873:  55%|█████▌    | 14326/25880 [2:56:32<2:27:27,  1.31it/s] 
1|14327|Loss: 0.906379222869873:  55%|█████▌    | 14327/25880 [2:56:32<2:25:51,  1.32it/s]
1|14328|Loss: 0.8475852012634277:  55%|█████▌    | 14327/25880 [2:56:33<2:25:51,  1.32it/s]
1|14328|Loss: 0.8475852012634277:  55%|█████▌    | 14328/25880 [2:56:33<2:18:48,  1.39it/s]
1|14329|Loss: 0.8333888053894043:  55%|█████▌    | 14328/25880 [2:56:33<2:18:48,  1.39it/s]
1|14329|Loss: 0.8333888053894043:  55%|█████▌    | 14329/25880 [2:56:33<2:08:37,  1.50it/s]
1|14330|Loss: 1.012415885925293:  55%|█████▌    | 14329/25880 [2:56:34<2:08:37,  1.50it/s] 
1|14330|Loss: 1.012415885925293:  55%|█████▌    | 14330/25880 [2:56:34<2:15:13,  1.42it/s]
1|14331|Loss: 0.9318203330039978:  55%|█████▌    | 14330/25880 [2:56:35<2:15:13,  1.42it/s]
1|14331|Loss: 0.9318203330039978:  55%|█████▌    | 14331/25880 [2:56:35<2:19:21,  1.38it/s]
1|14332|Loss: 0.8182066679000854:  55%|█████▌    | 14331/25880 [2:56:36<2:19:21,  1.38it/s]
1|14332|Loss: 0.8182066679000854:  55%|█████▌    | 14332/25880 [2:56:36<2:29:08,  1.29it/s]
1|14333|Loss: 0.9784969687461853:  55%|█████▌    | 14332/25880 [2:56:36<2:29:08,  1.29it/s]
1|14333|Loss: 0.9784969687461853:  55%|█████▌    | 14333/25880 [2:56:37<2:31:18,  1.27it/s]
1|14334|Loss: 0.7919813990592957:  55%|█████▌    | 14333/25880 [2:56:37<2:31:18,  1.27it/s]
1|14334|Loss: 0.7919813990592957:  55%|█████▌    | 14334/25880 [2:56:37<2:23:45,  1.34it/s]
1|14335|Loss: 0.8779381513595581:  55%|█████▌    | 14334/25880 [2:56:38<2:23:45,  1.34it/s]
1|14335|Loss: 0.8779381513595581:  55%|█████▌    | 14335/25880 [2:56:38<2:19:50,  1.38it/s]
1|14336|Loss: 0.8512815237045288:  55%|█████▌    | 14335/25880 [2:56:39<2:19:50,  1.38it/s]
1|14336|Loss: 0.8512815237045288:  55%|█████▌    | 14336/25880 [2:56:39<2:30:13,  1.28it/s]
1|14337|Loss: 0.8234367966651917:  55%|█████▌    | 14336/25880 [2:56:39<2:30:13,  1.28it/s]
1|14337|Loss: 0.8234367966651917:  55%|█████▌    | 14337/25880 [2:56:40<2:30:51,  1.28it/s]
1|14338|Loss: 0.805778443813324:  55%|█████▌    | 14337/25880 [2:56:40<2:30:51,  1.28it/s] 
1|14338|Loss: 0.805778443813324:  55%|█████▌    | 14338/25880 [2:56:41<2:28:10,  1.30it/s]
1|14339|Loss: 0.8295729756355286:  55%|█████▌    | 14338/25880 [2:56:41<2:28:10,  1.30it/s]
1|14339|Loss: 0.8295729756355286:  55%|█████▌    | 14339/25880 [2:56:41<2:21:36,  1.36it/s]
1|14340|Loss: 0.971114456653595:  55%|█████▌    | 14339/25880 [2:56:42<2:21:36,  1.36it/s] 
1|14340|Loss: 0.971114456653595:  55%|█████▌    | 14340/25880 [2:56:42<2:20:46,  1.37it/s]
1|14341|Loss: 0.8000537157058716:  55%|█████▌    | 14340/25880 [2:56:42<2:20:46,  1.37it/s]
1|14341|Loss: 0.8000537157058716:  55%|█████▌    | 14341/25880 [2:56:43<2:21:14,  1.36it/s]
1|14342|Loss: 0.8341712951660156:  55%|█████▌    | 14341/25880 [2:56:43<2:21:14,  1.36it/s]
1|14342|Loss: 0.8341712951660156:  55%|█████▌    | 14342/25880 [2:56:43<2:16:25,  1.41it/s]
1|14343|Loss: 0.7728745341300964:  55%|█████▌    | 14342/25880 [2:56:44<2:16:25,  1.41it/s]
1|14343|Loss: 0.7728745341300964:  55%|█████▌    | 14343/25880 [2:56:44<2:16:38,  1.41it/s]
1|14344|Loss: 0.6960667371749878:  55%|█████▌    | 14343/25880 [2:56:44<2:16:38,  1.41it/s]
1|14344|Loss: 0.6960667371749878:  55%|█████▌    | 14344/25880 [2:56:45<2:05:12,  1.54it/s]
1|14345|Loss: 0.8453716039657593:  55%|█████▌    | 14344/25880 [2:56:45<2:05:12,  1.54it/s]
1|14345|Loss: 0.8453716039657593:  55%|█████▌    | 14345/25880 [2:56:45<2:17:03,  1.40it/s]
1|14346|Loss: 0.7688691020011902:  55%|█████▌    | 14345/25880 [2:56:46<2:17:03,  1.40it/s]
1|14346|Loss: 0.7688691020011902:  55%|█████▌    | 14346/25880 [2:56:46<2:20:56,  1.36it/s]
1|14347|Loss: 0.7687514424324036:  55%|█████▌    | 14346/25880 [2:56:47<2:20:56,  1.36it/s]
1|14347|Loss: 0.7687514424324036:  55%|█████▌    | 14347/25880 [2:56:47<2:25:42,  1.32it/s]
1|14348|Loss: 0.8104198575019836:  55%|█████▌    | 14347/25880 [2:56:47<2:25:42,  1.32it/s]
1|14348|Loss: 0.8104198575019836:  55%|█████▌    | 14348/25880 [2:56:48<2:25:04,  1.32it/s]
1|14349|Loss: 0.7059711217880249:  55%|█████▌    | 14348/25880 [2:56:48<2:25:04,  1.32it/s]
1|14349|Loss: 0.7059711217880249:  55%|█████▌    | 14349/25880 [2:56:48<2:10:49,  1.47it/s]
1|14350|Loss: 0.8733549118041992:  55%|█████▌    | 14349/25880 [2:56:49<2:10:49,  1.47it/s]
1|14350|Loss: 0.8733549118041992:  55%|█████▌    | 14350/25880 [2:56:49<2:08:57,  1.49it/s]
1|14351|Loss: 0.7893428802490234:  55%|█████▌    | 14350/25880 [2:56:49<2:08:57,  1.49it/s]
1|14351|Loss: 0.7893428802490234:  55%|█████▌    | 14351/25880 [2:56:50<2:19:08,  1.38it/s]
1|14352|Loss: 0.7868101596832275:  55%|█████▌    | 14351/25880 [2:56:50<2:19:08,  1.38it/s]
1|14352|Loss: 0.7868101596832275:  55%|█████▌    | 14352/25880 [2:56:50<2:20:45,  1.36it/s]
1|14353|Loss: 0.9431948065757751:  55%|█████▌    | 14352/25880 [2:56:51<2:20:45,  1.36it/s]
1|14353|Loss: 0.9431948065757751:  55%|█████▌    | 14353/25880 [2:56:51<2:16:18,  1.41it/s]
1|14354|Loss: 0.9432950019836426:  55%|█████▌    | 14353/25880 [2:56:52<2:16:18,  1.41it/s]
1|14354|Loss: 0.9432950019836426:  55%|█████▌    | 14354/25880 [2:56:52<2:15:24,  1.42it/s]
1|14355|Loss: 0.736224889755249:  55%|█████▌    | 14354/25880 [2:56:52<2:15:24,  1.42it/s] 
1|14355|Loss: 0.736224889755249:  55%|█████▌    | 14355/25880 [2:56:53<2:22:30,  1.35it/s]
1|14356|Loss: 0.7979951500892639:  55%|█████▌    | 14355/25880 [2:56:53<2:22:30,  1.35it/s]
1|14356|Loss: 0.7979951500892639:  55%|█████▌    | 14356/25880 [2:56:53<2:14:11,  1.43it/s]
1|14357|Loss: 0.8402785062789917:  55%|█████▌    | 14356/25880 [2:56:54<2:14:11,  1.43it/s]
1|14357|Loss: 0.8402785062789917:  55%|█████▌    | 14357/25880 [2:56:54<2:20:53,  1.36it/s]
1|14358|Loss: 0.8111072778701782:  55%|█████▌    | 14357/25880 [2:56:54<2:20:53,  1.36it/s]
1|14358|Loss: 0.8111072778701782:  55%|█████▌    | 14358/25880 [2:56:55<2:17:41,  1.39it/s]
1|14359|Loss: 0.8715823292732239:  55%|█████▌    | 14358/25880 [2:56:55<2:17:41,  1.39it/s]
1|14359|Loss: 0.8715823292732239:  55%|█████▌    | 14359/25880 [2:56:56<2:20:40,  1.36it/s]
1|14360|Loss: 0.8222261071205139:  55%|█████▌    | 14359/25880 [2:56:56<2:20:40,  1.36it/s]
1|14360|Loss: 0.8222261071205139:  55%|█████▌    | 14360/25880 [2:56:56<2:12:11,  1.45it/s]
1|14361|Loss: 0.8516108393669128:  55%|█████▌    | 14360/25880 [2:56:56<2:12:11,  1.45it/s]
1|14361|Loss: 0.8516108393669128:  55%|█████▌    | 14361/25880 [2:56:57<2:12:11,  1.45it/s]
1|14362|Loss: 0.6803029179573059:  55%|█████▌    | 14361/25880 [2:56:57<2:12:11,  1.45it/s]
1|14362|Loss: 0.6803029179573059:  55%|█████▌    | 14362/25880 [2:56:58<2:14:32,  1.43it/s]
1|14363|Loss: 0.8712266087532043:  55%|█████▌    | 14362/25880 [2:56:58<2:14:32,  1.43it/s]
1|14363|Loss: 0.8712266087532043:  55%|█████▌    | 14363/25880 [2:56:58<2:09:20,  1.48it/s]
1|14364|Loss: 0.87330561876297:  55%|█████▌    | 14363/25880 [2:56:59<2:09:20,  1.48it/s]  
1|14364|Loss: 0.87330561876297:  56%|█████▌    | 14364/25880 [2:56:59<2:11:21,  1.46it/s]
1|14365|Loss: 0.7403343915939331:  56%|█████▌    | 14364/25880 [2:56:59<2:11:21,  1.46it/s]
1|14365|Loss: 0.7403343915939331:  56%|█████▌    | 14365/25880 [2:57:00<2:13:17,  1.44it/s]
1|14366|Loss: 0.9077270030975342:  56%|█████▌    | 14365/25880 [2:57:00<2:13:17,  1.44it/s]
1|14366|Loss: 0.9077270030975342:  56%|█████▌    | 14366/25880 [2:57:00<2:14:34,  1.43it/s]
1|14367|Loss: 0.8883829712867737:  56%|█████▌    | 14366/25880 [2:57:01<2:14:34,  1.43it/s]
1|14367|Loss: 0.8883829712867737:  56%|█████▌    | 14367/25880 [2:57:01<2:16:48,  1.40it/s]
1|14368|Loss: 0.8566844463348389:  56%|█████▌    | 14367/25880 [2:57:01<2:16:48,  1.40it/s]
1|14368|Loss: 0.8566844463348389:  56%|█████▌    | 14368/25880 [2:57:02<2:13:51,  1.43it/s]
1|14369|Loss: 0.6717628836631775:  56%|█████▌    | 14368/25880 [2:57:02<2:13:51,  1.43it/s]
1|14369|Loss: 0.6717628836631775:  56%|█████▌    | 14369/25880 [2:57:03<2:21:06,  1.36it/s]
1|14370|Loss: 0.7855428457260132:  56%|█████▌    | 14369/25880 [2:57:03<2:21:06,  1.36it/s]
1|14370|Loss: 0.7855428457260132:  56%|█████▌    | 14370/25880 [2:57:03<2:23:29,  1.34it/s]
1|14371|Loss: 0.7644058465957642:  56%|█████▌    | 14370/25880 [2:57:04<2:23:29,  1.34it/s]
1|14371|Loss: 0.7644058465957642:  56%|█████▌    | 14371/25880 [2:57:04<2:34:28,  1.24it/s]
1|14372|Loss: 0.8825170993804932:  56%|█████▌    | 14371/25880 [2:57:05<2:34:28,  1.24it/s]
1|14372|Loss: 0.8825170993804932:  56%|█████▌    | 14372/25880 [2:57:05<2:33:40,  1.25it/s]
1|14373|Loss: 0.6984139084815979:  56%|█████▌    | 14372/25880 [2:57:05<2:33:40,  1.25it/s]
1|14373|Loss: 0.6984139084815979:  56%|█████▌    | 14373/25880 [2:57:06<2:35:35,  1.23it/s]
1|14374|Loss: 0.782196581363678:  56%|█████▌    | 14373/25880 [2:57:06<2:35:35,  1.23it/s] 
1|14374|Loss: 0.782196581363678:  56%|█████▌    | 14374/25880 [2:57:07<2:31:11,  1.27it/s]
1|14375|Loss: 0.9346526861190796:  56%|█████▌    | 14374/25880 [2:57:07<2:31:11,  1.27it/s]
1|14375|Loss: 0.9346526861190796:  56%|█████▌    | 14375/25880 [2:57:07<2:23:07,  1.34it/s]
1|14376|Loss: 0.8564888834953308:  56%|█████▌    | 14375/25880 [2:57:08<2:23:07,  1.34it/s]
1|14376|Loss: 0.8564888834953308:  56%|█████▌    | 14376/25880 [2:57:08<2:17:12,  1.40it/s]
1|14377|Loss: 0.8213224411010742:  56%|█████▌    | 14376/25880 [2:57:08<2:17:12,  1.40it/s]
1|14377|Loss: 0.8213224411010742:  56%|█████▌    | 14377/25880 [2:57:09<2:23:15,  1.34it/s]
1|14378|Loss: 0.9420498609542847:  56%|█████▌    | 14377/25880 [2:57:09<2:23:15,  1.34it/s]
1|14378|Loss: 0.9420498609542847:  56%|█████▌    | 14378/25880 [2:57:09<2:22:41,  1.34it/s]
1|14379|Loss: 0.8590114116668701:  56%|█████▌    | 14378/25880 [2:57:10<2:22:41,  1.34it/s]
1|14379|Loss: 0.8590114116668701:  56%|█████▌    | 14379/25880 [2:57:10<2:26:00,  1.31it/s]
1|14380|Loss: 0.7838441133499146:  56%|█████▌    | 14379/25880 [2:57:11<2:26:00,  1.31it/s]
1|14380|Loss: 0.7838441133499146:  56%|█████▌    | 14380/25880 [2:57:11<2:29:26,  1.28it/s]
1|14381|Loss: 0.873847246170044:  56%|█████▌    | 14380/25880 [2:57:11<2:29:26,  1.28it/s] 
1|14381|Loss: 0.873847246170044:  56%|█████▌    | 14381/25880 [2:57:12<2:30:17,  1.28it/s]
1|14382|Loss: 0.7783963084220886:  56%|█████▌    | 14381/25880 [2:57:12<2:30:17,  1.28it/s]
1|14382|Loss: 0.7783963084220886:  56%|█████▌    | 14382/25880 [2:57:13<2:28:47,  1.29it/s]
1|14383|Loss: 0.8464809060096741:  56%|█████▌    | 14382/25880 [2:57:13<2:28:47,  1.29it/s]
1|14383|Loss: 0.8464809060096741:  56%|█████▌    | 14383/25880 [2:57:13<2:21:16,  1.36it/s]
1|14384|Loss: 0.7367748618125916:  56%|█████▌    | 14383/25880 [2:57:14<2:21:16,  1.36it/s]
1|14384|Loss: 0.7367748618125916:  56%|█████▌    | 14384/25880 [2:57:14<2:15:25,  1.41it/s]
1|14385|Loss: 0.9466663599014282:  56%|█████▌    | 14384/25880 [2:57:14<2:15:25,  1.41it/s]
1|14385|Loss: 0.9466663599014282:  56%|█████▌    | 14385/25880 [2:57:15<2:11:03,  1.46it/s]
1|14386|Loss: 0.7886425256729126:  56%|█████▌    | 14385/25880 [2:57:15<2:11:03,  1.46it/s]
1|14386|Loss: 0.7886425256729126:  56%|█████▌    | 14386/25880 [2:57:15<2:13:51,  1.43it/s]
1|14387|Loss: 0.7857332229614258:  56%|█████▌    | 14386/25880 [2:57:16<2:13:51,  1.43it/s]
1|14387|Loss: 0.7857332229614258:  56%|█████▌    | 14387/25880 [2:57:16<2:16:48,  1.40it/s]
1|14388|Loss: 0.7858412265777588:  56%|█████▌    | 14387/25880 [2:57:16<2:16:48,  1.40it/s]
1|14388|Loss: 0.7858412265777588:  56%|█████▌    | 14388/25880 [2:57:17<2:18:10,  1.39it/s]
1|14389|Loss: 0.8606148362159729:  56%|█████▌    | 14388/25880 [2:57:17<2:18:10,  1.39it/s]
1|14389|Loss: 0.8606148362159729:  56%|█████▌    | 14389/25880 [2:57:17<2:14:32,  1.42it/s]
1|14390|Loss: 0.7534419298171997:  56%|█████▌    | 14389/25880 [2:57:18<2:14:32,  1.42it/s]
1|14390|Loss: 0.7534419298171997:  56%|█████▌    | 14390/25880 [2:57:18<2:02:37,  1.56it/s]
1|14391|Loss: 0.8959035277366638:  56%|█████▌    | 14390/25880 [2:57:18<2:02:37,  1.56it/s]
1|14391|Loss: 0.8959035277366638:  56%|█████▌    | 14391/25880 [2:57:19<2:04:49,  1.53it/s]
1|14392|Loss: 1.0380299091339111:  56%|█████▌    | 14391/25880 [2:57:19<2:04:49,  1.53it/s]
1|14392|Loss: 1.0380299091339111:  56%|█████▌    | 14392/25880 [2:57:19<1:59:37,  1.60it/s]
1|14393|Loss: 0.8510765433311462:  56%|█████▌    | 14392/25880 [2:57:20<1:59:37,  1.60it/s]
1|14393|Loss: 0.8510765433311462:  56%|█████▌    | 14393/25880 [2:57:20<2:05:40,  1.52it/s]
1|14394|Loss: 0.8484232425689697:  56%|█████▌    | 14393/25880 [2:57:20<2:05:40,  1.52it/s]
1|14394|Loss: 0.8484232425689697:  56%|█████▌    | 14394/25880 [2:57:21<2:13:29,  1.43it/s]
1|14395|Loss: 0.8677801489830017:  56%|█████▌    | 14394/25880 [2:57:21<2:13:29,  1.43it/s]
1|14395|Loss: 0.8677801489830017:  56%|█████▌    | 14395/25880 [2:57:21<2:19:05,  1.38it/s]
1|14396|Loss: 0.8760210871696472:  56%|█████▌    | 14395/25880 [2:57:22<2:19:05,  1.38it/s]
1|14396|Loss: 0.8760210871696472:  56%|█████▌    | 14396/25880 [2:57:22<2:19:00,  1.38it/s]
1|14397|Loss: 0.8257458209991455:  56%|█████▌    | 14396/25880 [2:57:23<2:19:00,  1.38it/s]
1|14397|Loss: 0.8257458209991455:  56%|█████▌    | 14397/25880 [2:57:23<2:12:46,  1.44it/s]
1|14398|Loss: 1.0184366703033447:  56%|█████▌    | 14397/25880 [2:57:23<2:12:46,  1.44it/s]
1|14398|Loss: 1.0184366703033447:  56%|█████▌    | 14398/25880 [2:57:24<2:14:01,  1.43it/s]
1|14399|Loss: 0.9672168493270874:  56%|█████▌    | 14398/25880 [2:57:24<2:14:01,  1.43it/s]
1|14399|Loss: 0.9672168493270874:  56%|█████▌    | 14399/25880 [2:57:24<2:06:12,  1.52it/s]
1|14400|Loss: 0.852971613407135:  56%|█████▌    | 14399/25880 [2:57:24<2:06:12,  1.52it/s] 
1|14400|Loss: 0.852971613407135:  56%|█████▌    | 14400/25880 [2:57:25<2:12:13,  1.45it/s]
1|14401|Loss: 0.7727939486503601:  56%|█████▌    | 14400/25880 [2:57:25<2:12:13,  1.45it/s]
1|14401|Loss: 0.7727939486503601:  56%|█████▌    | 14401/25880 [2:57:26<2:21:57,  1.35it/s]
1|14402|Loss: 0.8658204078674316:  56%|█████▌    | 14401/25880 [2:57:26<2:21:57,  1.35it/s]
1|14402|Loss: 0.8658204078674316:  56%|█████▌    | 14402/25880 [2:57:26<2:19:00,  1.38it/s]
1|14403|Loss: 0.948325514793396:  56%|█████▌    | 14402/25880 [2:57:27<2:19:00,  1.38it/s] 
1|14403|Loss: 0.948325514793396:  56%|█████▌    | 14403/25880 [2:57:27<2:09:51,  1.47it/s]
1|14404|Loss: 0.6629582643508911:  56%|█████▌    | 14403/25880 [2:57:27<2:09:51,  1.47it/s]
1|14404|Loss: 0.6629582643508911:  56%|█████▌    | 14404/25880 [2:57:28<2:06:23,  1.51it/s]
1|14405|Loss: 0.8794638514518738:  56%|█████▌    | 14404/25880 [2:57:28<2:06:23,  1.51it/s]
1|14405|Loss: 0.8794638514518738:  56%|█████▌    | 14405/25880 [2:57:28<2:01:01,  1.58it/s]
1|14406|Loss: 0.7246636748313904:  56%|█████▌    | 14405/25880 [2:57:29<2:01:01,  1.58it/s]
1|14406|Loss: 0.7246636748313904:  56%|█████▌    | 14406/25880 [2:57:29<2:09:49,  1.47it/s]
1|14407|Loss: 0.8456034064292908:  56%|█████▌    | 14406/25880 [2:57:29<2:09:49,  1.47it/s]
1|14407|Loss: 0.8456034064292908:  56%|█████▌    | 14407/25880 [2:57:30<2:19:07,  1.37it/s]
1|14408|Loss: 0.8537643551826477:  56%|█████▌    | 14407/25880 [2:57:30<2:19:07,  1.37it/s]
1|14408|Loss: 0.8537643551826477:  56%|█████▌    | 14408/25880 [2:57:31<2:29:11,  1.28it/s]
1|14409|Loss: 0.8576866388320923:  56%|█████▌    | 14408/25880 [2:57:31<2:29:11,  1.28it/s]
1|14409|Loss: 0.8576866388320923:  56%|█████▌    | 14409/25880 [2:57:31<2:22:23,  1.34it/s]
1|14410|Loss: 0.7909955382347107:  56%|█████▌    | 14409/25880 [2:57:32<2:22:23,  1.34it/s]
1|14410|Loss: 0.7909955382347107:  56%|█████▌    | 14410/25880 [2:57:32<2:19:30,  1.37it/s]
1|14411|Loss: 0.7143847346305847:  56%|█████▌    | 14410/25880 [2:57:32<2:19:30,  1.37it/s]
1|14411|Loss: 0.7143847346305847:  56%|█████▌    | 14411/25880 [2:57:33<2:21:50,  1.35it/s]
1|14412|Loss: 0.9764864444732666:  56%|█████▌    | 14411/25880 [2:57:33<2:21:50,  1.35it/s]
1|14412|Loss: 0.9764864444732666:  56%|█████▌    | 14412/25880 [2:57:34<2:30:28,  1.27it/s]
1|14413|Loss: 0.8786402344703674:  56%|█████▌    | 14412/25880 [2:57:34<2:30:28,  1.27it/s]
1|14413|Loss: 0.8786402344703674:  56%|█████▌    | 14413/25880 [2:57:35<2:37:55,  1.21it/s]
1|14414|Loss: 0.8173482418060303:  56%|█████▌    | 14413/25880 [2:57:35<2:37:55,  1.21it/s]
1|14414|Loss: 0.8173482418060303:  56%|█████▌    | 14414/25880 [2:57:35<2:30:21,  1.27it/s]
1|14415|Loss: 0.9373992085456848:  56%|█████▌    | 14414/25880 [2:57:36<2:30:21,  1.27it/s]
1|14415|Loss: 0.9373992085456848:  56%|█████▌    | 14415/25880 [2:57:36<2:33:24,  1.25it/s]
1|14416|Loss: 0.7426562309265137:  56%|█████▌    | 14415/25880 [2:57:37<2:33:24,  1.25it/s]
1|14416|Loss: 0.7426562309265137:  56%|█████▌    | 14416/25880 [2:57:37<2:27:02,  1.30it/s]
1|14417|Loss: 0.7924483418464661:  56%|█████▌    | 14416/25880 [2:57:37<2:27:02,  1.30it/s]
1|14417|Loss: 0.7924483418464661:  56%|█████▌    | 14417/25880 [2:57:37<2:19:35,  1.37it/s]
1|14418|Loss: 0.9569743871688843:  56%|█████▌    | 14417/25880 [2:57:38<2:19:35,  1.37it/s]
1|14418|Loss: 0.9569743871688843:  56%|█████▌    | 14418/25880 [2:57:38<2:18:22,  1.38it/s]
1|14419|Loss: 0.9236911535263062:  56%|█████▌    | 14418/25880 [2:57:39<2:18:22,  1.38it/s]
1|14419|Loss: 0.9236911535263062:  56%|█████▌    | 14419/25880 [2:57:39<2:13:08,  1.43it/s]
1|14420|Loss: 0.7824671864509583:  56%|█████▌    | 14419/25880 [2:57:39<2:13:08,  1.43it/s]
1|14420|Loss: 0.7824671864509583:  56%|█████▌    | 14420/25880 [2:57:40<2:14:04,  1.42it/s]
1|14421|Loss: 0.9082563519477844:  56%|█████▌    | 14420/25880 [2:57:40<2:14:04,  1.42it/s]
1|14421|Loss: 0.9082563519477844:  56%|█████���    | 14421/25880 [2:57:40<2:14:41,  1.42it/s]
1|14422|Loss: 0.7466015815734863:  56%|█████▌    | 14421/25880 [2:57:41<2:14:41,  1.42it/s]
1|14422|Loss: 0.7466015815734863:  56%|█████▌    | 14422/25880 [2:57:41<2:03:25,  1.55it/s]
1|14423|Loss: 0.9286569952964783:  56%|█████▌    | 14422/25880 [2:57:41<2:03:25,  1.55it/s]
1|14423|Loss: 0.9286569952964783:  56%|█████▌    | 14423/25880 [2:57:41<2:04:52,  1.53it/s]
1|14424|Loss: 0.6902819871902466:  56%|█████▌    | 14423/25880 [2:57:42<2:04:52,  1.53it/s]
1|14424|Loss: 0.6902819871902466:  56%|█████▌    | 14424/25880 [2:57:42<2:09:39,  1.47it/s]
1|14425|Loss: 0.8925045728683472:  56%|█████▌    | 14424/25880 [2:57:43<2:09:39,  1.47it/s]
1|14425|Loss: 0.8925045728683472:  56%|█████▌    | 14425/25880 [2:57:43<2:08:36,  1.48it/s]
1|14426|Loss: 0.8096231818199158:  56%|█████▌    | 14425/25880 [2:57:43<2:08:36,  1.48it/s]
1|14426|Loss: 0.8096231818199158:  56%|█████▌    | 14426/25880 [2:57:43<2:06:49,  1.51it/s]
1|14427|Loss: 0.8444215059280396:  56%|█████▌    | 14426/25880 [2:57:44<2:06:49,  1.51it/s]
1|14427|Loss: 0.8444215059280396:  56%|█████▌    | 14427/25880 [2:57:44<2:09:39,  1.47it/s]
1|14428|Loss: 0.8241126537322998:  56%|█████▌    | 14427/25880 [2:57:45<2:09:39,  1.47it/s]
1|14428|Loss: 0.8241126537322998:  56%|█████▌    | 14428/25880 [2:57:45<2:08:46,  1.48it/s]
1|14429|Loss: 0.8353710174560547:  56%|█████▌    | 14428/25880 [2:57:45<2:08:46,  1.48it/s]
1|14429|Loss: 0.8353710174560547:  56%|█████▌    | 14429/25880 [2:57:46<2:09:32,  1.47it/s]
1|14430|Loss: 0.8842424750328064:  56%|█████▌    | 14429/25880 [2:57:46<2:09:32,  1.47it/s]
1|14430|Loss: 0.8842424750328064:  56%|█████▌    | 14430/25880 [2:57:46<2:12:31,  1.44it/s]
1|14431|Loss: 0.8520991206169128:  56%|█████▌    | 14430/25880 [2:57:47<2:12:31,  1.44it/s]
1|14431|Loss: 0.8520991206169128:  56%|█████▌    | 14431/25880 [2:57:47<2:15:29,  1.41it/s]
1|14432|Loss: 0.7979839444160461:  56%|█████▌    | 14431/25880 [2:57:47<2:15:29,  1.41it/s]
1|14432|Loss: 0.7979839444160461:  56%|█████▌    | 14432/25880 [2:57:48<2:17:05,  1.39it/s]
1|14433|Loss: 0.8538923859596252:  56%|█████▌    | 14432/25880 [2:57:48<2:17:05,  1.39it/s]
1|14433|Loss: 0.8538923859596252:  56%|█████▌    | 14433/25880 [2:57:48<2:12:36,  1.44it/s]
1|14434|Loss: 0.7969323396682739:  56%|█████▌    | 14433/25880 [2:57:49<2:12:36,  1.44it/s]
1|14434|Loss: 0.7969323396682739:  56%|█████▌    | 14434/25880 [2:57:49<2:02:57,  1.55it/s]
1|14435|Loss: 0.8733782172203064:  56%|█████▌    | 14434/25880 [2:57:49<2:02:57,  1.55it/s]
1|14435|Loss: 0.8733782172203064:  56%|█████▌    | 14435/25880 [2:57:50<2:08:00,  1.49it/s]
1|14436|Loss: 0.8010678887367249:  56%|█████▌    | 14435/25880 [2:57:50<2:08:00,  1.49it/s]
1|14436|Loss: 0.8010678887367249:  56%|█████▌    | 14436/25880 [2:57:50<2:12:31,  1.44it/s]
1|14437|Loss: 0.7629876732826233:  56%|█████▌    | 14436/25880 [2:57:51<2:12:31,  1.44it/s]
1|14437|Loss: 0.7629876732826233:  56%|█████▌    | 14437/25880 [2:57:51<2:10:43,  1.46it/s]
1|14438|Loss: 0.865384042263031:  56%|█████▌    | 14437/25880 [2:57:51<2:10:43,  1.46it/s] 
1|14438|Loss: 0.865384042263031:  56%|█████▌    | 14438/25880 [2:57:52<2:16:49,  1.39it/s]
1|14439|Loss: 1.031095266342163:  56%|█████▌    | 14438/25880 [2:57:52<2:16:49,  1.39it/s]
1|14439|Loss: 1.031095266342163:  56%|█████▌    | 14439/25880 [2:57:53<2:18:16,  1.38it/s]
1|14440|Loss: 0.6629554629325867:  56%|█████▌    | 14439/25880 [2:57:53<2:18:16,  1.38it/s]
1|14440|Loss: 0.6629554629325867:  56%|█████▌    | 14440/25880 [2:57:53<2:20:58,  1.35it/s]
1|14441|Loss: 0.8114832043647766:  56%|█████▌    | 14440/25880 [2:57:54<2:20:58,  1.35it/s]
1|14441|Loss: 0.8114832043647766:  56%|█████▌    | 14441/25880 [2:57:54<2:27:37,  1.29it/s]
1|14442|Loss: 0.677763044834137:  56%|█████▌    | 14441/25880 [2:57:55<2:27:37,  1.29it/s] 
1|14442|Loss: 0.677763044834137:  56%|█████▌    | 14442/25880 [2:57:55<2:38:37,  1.20it/s]
1|14443|Loss: 0.7170945405960083:  56%|█████▌    | 14442/25880 [2:57:56<2:38:37,  1.20it/s]
1|14443|Loss: 0.7170945405960083:  56%|█████▌    | 14443/25880 [2:57:56<2:36:24,  1.22it/s]
1|14444|Loss: 0.7864286303520203:  56%|█████▌    | 14443/25880 [2:57:56<2:36:24,  1.22it/s]
1|14444|Loss: 0.7864286303520203:  56%|█████▌    | 14444/25880 [2:57:57<2:42:00,  1.18it/s]
1|14445|Loss: 0.8288264274597168:  56%|█████▌    | 14444/25880 [2:57:57<2:42:00,  1.18it/s]
1|14445|Loss: 0.8288264274597168:  56%|█████▌    | 14445/25880 [2:57:58<2:38:38,  1.20it/s]
1|14446|Loss: 0.9554141163825989:  56%|█████▌    | 14445/25880 [2:57:58<2:38:38,  1.20it/s]
1|14446|Loss: 0.9554141163825989:  56%|█████▌    | 14446/25880 [2:57:59<2:37:41,  1.21it/s]
1|14447|Loss: 0.9998923540115356:  56%|█████▌    | 14446/25880 [2:57:59<2:37:41,  1.21it/s]
1|14447|Loss: 0.9998923540115356:  56%|█████▌    | 14447/25880 [2:57:59<2:38:44,  1.20it/s]
1|14448|Loss: 1.0514490604400635:  56%|█████▌    | 14447/25880 [2:58:00<2:38:44,  1.20it/s]
1|14448|Loss: 1.0514490604400635:  56%|█████▌    | 14448/25880 [2:58:00<2:28:40,  1.28it/s]
1|14449|Loss: 0.8601873517036438:  56%|█████▌    | 14448/25880 [2:58:00<2:28:40,  1.28it/s]
1|14449|Loss: 0.8601873517036438:  56%|█████▌    | 14449/25880 [2:58:01<2:20:01,  1.36it/s]
1|14450|Loss: 0.8064653873443604:  56%|█████▌    | 14449/25880 [2:58:01<2:20:01,  1.36it/s]
1|14450|Loss: 0.8064653873443604:  56%|█████▌    | 14450/25880 [2:58:01<2:14:39,  1.41it/s]
1|14451|Loss: 0.8487038612365723:  56%|█████▌    | 14450/25880 [2:58:02<2:14:39,  1.41it/s]
1|14451|Loss: 0.8487038612365723:  56%|█████▌    | 14451/25880 [2:58:02<2:19:53,  1.36it/s]
1|14452|Loss: 0.9592090249061584:  56%|█████▌    | 14451/25880 [2:58:03<2:19:53,  1.36it/s]
1|14452|Loss: 0.9592090249061584:  56%|█████▌    | 14452/25880 [2:58:03<2:26:02,  1.30it/s]
1|14453|Loss: 0.7380122542381287:  56%|█████▌    | 14452/25880 [2:58:03<2:26:02,  1.30it/s]
1|14453|Loss: 0.7380122542381287:  56%|█████▌    | 14453/25880 [2:58:04<2:34:31,  1.23it/s]
1|14454|Loss: 0.9443407654762268:  56%|█████▌    | 14453/25880 [2:58:04<2:34:31,  1.23it/s]
1|14454|Loss: 0.9443407654762268:  56%|█████▌    | 14454/25880 [2:58:05<2:30:46,  1.26it/s]
1|14455|Loss: 0.8538050055503845:  56%|█████▌    | 14454/25880 [2:58:05<2:30:46,  1.26it/s]
1|14455|Loss: 0.8538050055503845:  56%|█████▌    | 14455/25880 [2:58:05<2:13:58,  1.42it/s]
1|14456|Loss: 1.0806373357772827:  56%|█████▌    | 14455/25880 [2:58:05<2:13:58,  1.42it/s]
1|14456|Loss: 1.0806373357772827:  56%|█████▌    | 14456/25880 [2:58:06<2:12:34,  1.44it/s]
1|14457|Loss: 0.9573791027069092:  56%|█████▌    | 14456/25880 [2:58:06<2:12:34,  1.44it/s]
1|14457|Loss: 0.9573791027069092:  56%|█████▌    | 14457/25880 [2:58:06<2:14:00,  1.42it/s]
1|14458|Loss: 0.8040060997009277:  56%|█████▌    | 14457/25880 [2:58:07<2:14:00,  1.42it/s]
1|14458|Loss: 0.8040060997009277:  56%|█████▌    | 14458/25880 [2:58:07<2:17:52,  1.38it/s]
1|14459|Loss: 0.9286953806877136:  56%|█████▌    | 14458/25880 [2:58:08<2:17:52,  1.38it/s]
1|14459|Loss: 0.9286953806877136:  56%|█████▌    | 14459/25880 [2:58:08<2:22:29,  1.34it/s]
1|14460|Loss: 1.0286478996276855:  56%|█████▌    | 14459/25880 [2:58:09<2:22:29,  1.34it/s]
1|14460|Loss: 1.0286478996276855:  56%|█████▌    | 14460/25880 [2:58:09<2:27:25,  1.29it/s]
1|14461|Loss: 0.8623536229133606:  56%|█████▌    | 14460/25880 [2:58:09<2:27:25,  1.29it/s]
1|14461|Loss: 0.8623536229133606:  56%|█████▌    | 14461/25880 [2:58:10<2:30:34,  1.26it/s]
1|14462|Loss: 0.9680119156837463:  56%|█████▌    | 14461/25880 [2:58:10<2:30:34,  1.26it/s]
1|14462|Loss: 0.9680119156837463:  56%|█████▌    | 14462/25880 [2:58:10<2:15:38,  1.40it/s]
1|14463|Loss: 0.8051989078521729:  56%|█████▌    | 14462/25880 [2:58:11<2:15:38,  1.40it/s]
1|14463|Loss: 0.8051989078521729:  56%|█████▌    | 14463/25880 [2:58:11<2:18:55,  1.37it/s]
1|14464|Loss: 0.7824263572692871:  56%|█████▌    | 14463/25880 [2:58:11<2:18:55,  1.37it/s]
1|14464|Loss: 0.7824263572692871:  56%|█████▌    | 14464/25880 [2:58:12<2:16:41,  1.39it/s]
1|14465|Loss: 0.8110400438308716:  56%|█████▌    | 14464/25880 [2:58:12<2:16:41,  1.39it/s]
1|14465|Loss: 0.8110400438308716:  56%|█████▌    | 14465/25880 [2:58:13<2:21:10,  1.35it/s]
1|14466|Loss: 0.9371739625930786:  56%|█████▌    | 14465/25880 [2:58:13<2:21:10,  1.35it/s]
1|14466|Loss: 0.9371739625930786:  56%|█████▌    | 14466/25880 [2:58:13<2:23:58,  1.32it/s]
1|14467|Loss: 0.8454909920692444:  56%|█████▌    | 14466/25880 [2:58:14<2:23:58,  1.32it/s]
1|14467|Loss: 0.8454909920692444:  56%|█████▌    | 14467/25880 [2:58:14<2:23:17,  1.33it/s]
1|14468|Loss: 0.9531786441802979:  56%|█████▌    | 14467/25880 [2:58:14<2:23:17,  1.33it/s]
1|14468|Loss: 0.9531786441802979:  56%|█████▌    | 14468/25880 [2:58:15<2:26:19,  1.30it/s]
1|14469|Loss: 0.8203856348991394:  56%|█████▌    | 14468/25880 [2:58:15<2:26:19,  1.30it/s]
1|14469|Loss: 0.8203856348991394:  56%|█████▌    | 14469/25880 [2:58:16<2:25:21,  1.31it/s]
1|14470|Loss: 0.8484659194946289:  56%|█████▌    | 14469/25880 [2:58:16<2:25:21,  1.31it/s]
1|14470|Loss: 0.8484659194946289:  56%|█████▌    | 14470/25880 [2:58:16<2:14:36,  1.41it/s]
1|14471|Loss: 0.788425862789154:  56%|█████▌    | 14470/25880 [2:58:17<2:14:36,  1.41it/s] 
1|14471|Loss: 0.788425862789154:  56%|█████▌    | 14471/25880 [2:58:17<2:17:01,  1.39it/s]
1|14472|Loss: 0.9366519451141357:  56%|█████▌    | 14471/25880 [2:58:17<2:17:01,  1.39it/s]
1|14472|Loss: 0.9366519451141357:  56%|█████▌    | 14472/25880 [2:58:18<2:14:36,  1.41it/s]
1|14473|Loss: 0.7952702045440674:  56%|█████▌    | 14472/25880 [2:58:18<2:14:36,  1.41it/s]
1|14473|Loss: 0.7952702045440674:  56%|█████▌    | 14473/25880 [2:58:18<2:21:12,  1.35it/s]
1|14474|Loss: 0.9285822510719299:  56%|█████▌    | 14473/25880 [2:58:19<2:21:12,  1.35it/s]
1|14474|Loss: 0.9285822510719299:  56%|█████▌    | 14474/25880 [2:58:19<2:15:27,  1.40it/s]
1|14475|Loss: 0.9518997669219971:  56%|█████▌    | 14474/25880 [2:58:19<2:15:27,  1.40it/s]
1|14475|Loss: 0.9518997669219971:  56%|█████▌    | 14475/25880 [2:58:20<2:14:38,  1.41it/s]
1|14476|Loss: 0.9467286467552185:  56%|█████▌    | 14475/25880 [2:58:20<2:14:38,  1.41it/s]
1|14476|Loss: 0.9467286467552185:  56%|█████▌    | 14476/25880 [2:58:20<2:10:44,  1.45it/s]
1|14477|Loss: 0.7562734484672546:  56%|█████▌    | 14476/25880 [2:58:21<2:10:44,  1.45it/s]
1|14477|Loss: 0.7562734484672546:  56%|█████▌    | 14477/25880 [2:58:21<2:12:23,  1.44it/s]
1|14478|Loss: 0.8780568838119507:  56%|█████▌    | 14477/25880 [2:58:22<2:12:23,  1.44it/s]
1|14478|Loss: 0.8780568838119507:  56%|█████▌    | 14478/25880 [2:58:22<2:08:33,  1.48it/s]
1|14479|Loss: 0.7489537596702576:  56%|█████▌    | 14478/25880 [2:58:22<2:08:33,  1.48it/s]
1|14479|Loss: 0.7489537596702576:  56%|█████▌    | 14479/25880 [2:58:22<1:59:32,  1.59it/s]
1|14480|Loss: 0.7658212184906006:  56%|█████▌    | 14479/25880 [2:58:23<1:59:32,  1.59it/s]
1|14480|Loss: 0.7658212184906006:  56%|█████▌    | 14480/25880 [2:58:23<2:11:16,  1.45it/s]
1|14481|Loss: 0.8079173564910889:  56%|█████▌    | 14480/25880 [2:58:24<2:11:16,  1.45it/s]
1|14481|Loss: 0.8079173564910889:  56%|█████▌    | 14481/25880 [2:58:24<2:14:24,  1.41it/s]
1|14482|Loss: 0.886167585849762:  56%|█████▌    | 14481/25880 [2:58:24<2:14:24,  1.41it/s] 
1|14482|Loss: 0.886167585849762:  56%|█████▌    | 14482/25880 [2:58:25<2:10:18,  1.46it/s]
1|14483|Loss: 0.8709200024604797:  56%|█████▌    | 14482/25880 [2:58:25<2:10:18,  1.46it/s]
1|14483|Loss: 0.8709200024604797:  56%|█████▌    | 14483/25880 [2:58:25<2:17:05,  1.39it/s]
1|14484|Loss: 0.7884067296981812:  56%|█████▌    | 14483/25880 [2:58:26<2:17:05,  1.39it/s]
1|14484|Loss: 0.7884067296981812:  56%|█████▌    | 14484/25880 [2:58:26<2:17:47,  1.38it/s]
1|14485|Loss: 0.7135099768638611:  56%|█████▌    | 14484/25880 [2:58:26<2:17:47,  1.38it/s]
1|14485|Loss: 0.7135099768638611:  56%|█████▌    | 14485/25880 [2:58:27<2:19:47,  1.36it/s]
1|14486|Loss: 0.9471477270126343:  56%|█████▌    | 14485/25880 [2:58:27<2:19:47,  1.36it/s]
1|14486|Loss: 0.9471477270126343:  56%|█████▌    | 14486/25880 [2:58:27<2:07:30,  1.49it/s]
1|14487|Loss: 1.032731056213379:  56%|█████▌    | 14486/25880 [2:58:28<2:07:30,  1.49it/s] 
1|14487|Loss: 1.032731056213379:  56%|█████▌    | 14487/25880 [2:58:28<2:07:20,  1.49it/s]
1|14488|Loss: 0.8876246213912964:  56%|█████▌    | 14487/25880 [2:58:28<2:07:20,  1.49it/s]
1|14488|Loss: 0.8876246213912964:  56%|█████▌    | 14488/25880 [2:58:29<2:06:35,  1.50it/s]
1|14489|Loss: 0.7391552925109863:  56%|█████▌    | 14488/25880 [2:58:29<2:06:35,  1.50it/s]
1|14489|Loss: 0.7391552925109863:  56%|█████▌    | 14489/25880 [2:58:29<2:08:18,  1.48it/s]
1|14490|Loss: 0.738412082195282:  56%|█████▌    | 14489/25880 [2:58:30<2:08:18,  1.48it/s] 
1|14490|Loss: 0.738412082195282:  56%|█████▌    | 14490/25880 [2:58:30<2:10:49,  1.45it/s]
1|14491|Loss: 0.8865137100219727:  56%|█████▌    | 14490/25880 [2:58:30<2:10:49,  1.45it/s]
1|14491|Loss: 0.8865137100219727:  56%|█████▌    | 14491/25880 [2:58:31<2:08:49,  1.47it/s]
1|14492|Loss: 0.9507560729980469:  56%|█████▌    | 14491/25880 [2:58:31<2:08:49,  1.47it/s]
1|14492|Loss: 0.9507560729980469:  56%|█████▌    | 14492/25880 [2:58:31<1:58:03,  1.61it/s]
1|14493|Loss: 0.8982576131820679:  56%|█████▌    | 14492/25880 [2:58:32<1:58:03,  1.61it/s]
1|14493|Loss: 0.8982576131820679:  56%|█████▌    | 14493/25880 [2:58:32<1:56:30,  1.63it/s]
1|14494|Loss: 0.8105255961418152:  56%|█████▌    | 14493/25880 [2:58:32<1:56:30,  1.63it/s]
1|14494|Loss: 0.8105255961418152:  56%|█████▌    | 14494/25880 [2:58:33<2:02:14,  1.55it/s]
1|14495|Loss: 0.8136054277420044:  56%|█████▌    | 14494/25880 [2:58:33<2:02:14,  1.55it/s]
1|14495|Loss: 0.8136054277420044:  56%|█████▌    | 14495/25880 [2:58:33<2:07:56,  1.48it/s]
1|14496|Loss: 0.8068933486938477:  56%|█████▌    | 14495/25880 [2:58:34<2:07:56,  1.48it/s]
1|14496|Loss: 0.8068933486938477:  56%|█████▌    | 14496/25880 [2:58:34<2:11:44,  1.44it/s]
1|14497|Loss: 0.7749743461608887:  56%|█████▌    | 14496/25880 [2:58:34<2:11:44,  1.44it/s]
1|14497|Loss: 0.7749743461608887:  56%|█████▌    | 14497/25880 [2:58:35<2:13:36,  1.42it/s]
1|14498|Loss: 0.7659867405891418:  56%|█████▌    | 14497/25880 [2:58:35<2:13:36,  1.42it/s]
1|14498|Loss: 0.7659867405891418:  56%|█████▌    | 14498/25880 [2:58:35<2:09:01,  1.47it/s]
1|14499|Loss: 0.769169270992279:  56%|█████▌    | 14498/25880 [2:58:36<2:09:01,  1.47it/s] 
1|14499|Loss: 0.769169270992279:  56%|█████▌    | 14499/25880 [2:58:36<2:20:47,  1.35it/s]
1|14500|Loss: 0.9291093945503235:  56%|█████▌    | 14499/25880 [2:58:37<2:20:47,  1.35it/s]
1|14500|Loss: 0.9291093945503235:  56%|█████▌    | 14500/25880 [2:58:37<2:22:54,  1.33it/s]
1|14501|Loss: 0.8195247650146484:  56%|█████▌    | 14500/25880 [2:58:37<2:22:54,  1.33it/s]
1|14501|Loss: 0.8195247650146484:  56%|█████▌    | 14501/25880 [2:58:38<2:17:27,  1.38it/s]
1|14502|Loss: 0.8085278868675232:  56%|█████▌    | 14501/25880 [2:58:38<2:17:27,  1.38it/s]
1|14502|Loss: 0.8085278868675232:  56%|█████▌    | 14502/25880 [2:58:38<2:16:53,  1.39it/s]
1|14503|Loss: 0.8309000134468079:  56%|█████▌    | 14502/25880 [2:58:39<2:16:53,  1.39it/s]
1|14503|Loss: 0.8309000134468079:  56%|█████▌    | 14503/25880 [2:58:39<2:24:01,  1.32it/s]
1|14504|Loss: 0.7579617500305176:  56%|█████▌    | 14503/25880 [2:58:40<2:24:01,  1.32it/s]
1|14504|Loss: 0.7579617500305176:  56%|█████▌    | 14504/25880 [2:58:40<2:20:23,  1.35it/s]
1|14505|Loss: 0.9867995381355286:  56%|█████▌    | 14504/25880 [2:58:40<2:20:23,  1.35it/s]
1|14505|Loss: 0.9867995381355286:  56%|█████▌    | 14505/25880 [2:58:41<2:21:26,  1.34it/s]
1|14506|Loss: 0.8192347288131714:  56%|█████▌    | 14505/25880 [2:58:41<2:21:26,  1.34it/s]
1|14506|Loss: 0.8192347288131714:  56%|█████▌    | 14506/25880 [2:58:42<2:27:55,  1.28it/s]
1|14507|Loss: 0.7794577479362488:  56%|█████▌    | 14506/25880 [2:58:42<2:27:55,  1.28it/s]
1|14507|Loss: 0.7794577479362488:  56%|█████▌    | 14507/25880 [2:58:42<2:33:19,  1.24it/s]
1|14508|Loss: 0.9005060791969299:  56%|█████▌    | 14507/25880 [2:58:43<2:33:19,  1.24it/s]
1|14508|Loss: 0.9005060791969299:  56%|█████▌    | 14508/25880 [2:58:43<2:29:19,  1.27it/s]
1|14509|Loss: 0.815587043762207:  56%|█████▌    | 14508/25880 [2:58:44<2:29:19,  1.27it/s] 
1|14509|Loss: 0.815587043762207:  56%|█████▌    | 14509/25880 [2:58:44<2:29:56,  1.26it/s]
1|14510|Loss: 0.8868468403816223:  56%|█████▌    | 14509/25880 [2:58:44<2:29:56,  1.26it/s]
1|14510|Loss: 0.8868468403816223:  56%|█████▌    | 14510/25880 [2:58:45<2:27:44,  1.28it/s]
1|14511|Loss: 0.7049130201339722:  56%|█████▌    | 14510/25880 [2:58:45<2:27:44,  1.28it/s]
1|14511|Loss: 0.7049130201339722:  56%|█████▌    | 14511/25880 [2:58:45<2:19:22,  1.36it/s]
1|14512|Loss: 0.9299414753913879:  56%|█████▌    | 14511/25880 [2:58:46<2:19:22,  1.36it/s]
1|14512|Loss: 0.9299414753913879:  56%|█████▌    | 14512/25880 [2:58:46<2:11:38,  1.44it/s]
1|14513|Loss: 0.73367840051651:  56%|█████▌    | 14512/25880 [2:58:46<2:11:38,  1.44it/s]  
1|14513|Loss: 0.73367840051651:  56%|█████▌    | 14513/25880 [2:58:47<2:10:16,  1.45it/s]
1|14514|Loss: 0.9395415782928467:  56%|█████▌    | 14513/25880 [2:58:47<2:10:16,  1.45it/s]
1|14514|Loss: 0.9395415782928467:  56%|█████▌    | 14514/25880 [2:58:47<2:03:22,  1.54it/s]
1|14515|Loss: 0.8274385929107666:  56%|█████▌    | 14514/25880 [2:58:48<2:03:22,  1.54it/s]
1|14515|Loss: 0.8274385929107666:  56%|█████▌    | 14515/25880 [2:58:48<2:05:17,  1.51it/s]
1|14516|Loss: 0.8007398843765259:  56%|█████▌    | 14515/25880 [2:58:48<2:05:17,  1.51it/s]
1|14516|Loss: 0.8007398843765259:  56%|█████▌    | 14516/25880 [2:58:49<2:13:32,  1.42it/s]
1|14517|Loss: 0.8244660496711731:  56%|█████▌    | 14516/25880 [2:58:49<2:13:32,  1.42it/s]
1|14517|Loss: 0.8244660496711731:  56%|█████▌    | 14517/25880 [2:58:50<2:19:06,  1.36it/s]
1|14518|Loss: 0.7766086459159851:  56%|█████▌    | 14517/25880 [2:58:50<2:19:06,  1.36it/s]
1|14518|Loss: 0.7766086459159851:  56%|█████▌    | 14518/25880 [2:58:50<2:20:36,  1.35it/s]
1|14519|Loss: 0.8841040134429932:  56%|█████▌    | 14518/25880 [2:58:51<2:20:36,  1.35it/s]
1|14519|Loss: 0.8841040134429932:  56%|█████▌    | 14519/25880 [2:58:51<2:14:20,  1.41it/s]
1|14520|Loss: 0.6994291543960571:  56%|█████▌    | 14519/25880 [2:58:51<2:14:20,  1.41it/s]
1|14520|Loss: 0.6994291543960571:  56%|█████▌    | 14520/25880 [2:58:51<2:06:41,  1.49it/s]
1|14521|Loss: 0.8439099192619324:  56%|█████▌    | 14520/25880 [2:58:52<2:06:41,  1.49it/s]
1|14521|Loss: 0.8439099192619324:  56%|█████▌    | 14521/25880 [2:58:52<2:08:37,  1.47it/s]
1|14522|Loss: 0.9148756265640259:  56%|█████▌    | 14521/25880 [2:58:53<2:08:37,  1.47it/s]
1|14522|Loss: 0.9148756265640259:  56%|█████▌    | 14522/25880 [2:58:53<2:14:18,  1.41it/s]
1|14523|Loss: 0.8448935151100159:  56%|█████▌    | 14522/25880 [2:58:53<2:14:18,  1.41it/s]
1|14523|Loss: 0.8448935151100159:  56%|█████▌    | 14523/25880 [2:58:54<2:21:47,  1.33it/s]
1|14524|Loss: 0.6606658101081848:  56%|█████▌    | 14523/25880 [2:58:54<2:21:47,  1.33it/s]
1|14524|Loss: 0.6606658101081848:  56%|█████▌    | 14524/25880 [2:58:55<2:33:15,  1.23it/s]
1|14525|Loss: 0.8526695370674133:  56%|█████▌    | 14524/25880 [2:58:55<2:33:15,  1.23it/s]
1|14525|Loss: 0.8526695370674133:  56%|█████▌    | 14525/25880 [2:58:56<2:35:06,  1.22it/s]
1|14526|Loss: 0.8183838725090027:  56%|█████▌    | 14525/25880 [2:58:56<2:35:06,  1.22it/s]
1|14526|Loss: 0.8183838725090027:  56%|█████▌    | 14526/25880 [2:58:56<2:24:10,  1.31it/s]
1|14527|Loss: 0.7504309415817261:  56%|█████▌    | 14526/25880 [2:58:57<2:24:10,  1.31it/s]
1|14527|Loss: 0.7504309415817261:  56%|█████▌    | 14527/25880 [2:58:57<2:20:33,  1.35it/s]
1|14528|Loss: 1.111539363861084:  56%|█████▌    | 14527/25880 [2:58:57<2:20:33,  1.35it/s] 
1|14528|Loss: 1.111539363861084:  56%|█████▌    | 14528/25880 [2:58:58<2:28:12,  1.28it/s]
1|14529|Loss: 0.8195956349372864:  56%|█████▌    | 14528/25880 [2:58:58<2:28:12,  1.28it/s]
1|14529|Loss: 0.8195956349372864:  56%|█████▌    | 14529/25880 [2:58:59<2:35:49,  1.21it/s]
1|14530|Loss: 0.8316066861152649:  56%|█████▌    | 14529/25880 [2:58:59<2:35:49,  1.21it/s]
1|14530|Loss: 0.8316066861152649:  56%|█████▌    | 14530/25880 [2:59:00<2:39:35,  1.19it/s]
1|14531|Loss: 0.8008050322532654:  56%|█████▌    | 14530/25880 [2:59:00<2:39:35,  1.19it/s]
1|14531|Loss: 0.8008050322532654:  56%|█████▌    | 14531/25880 [2:59:00<2:31:29,  1.25it/s]
1|14532|Loss: 0.9469782114028931:  56%|█████▌    | 14531/25880 [2:59:01<2:31:29,  1.25it/s]
1|14532|Loss: 0.9469782114028931:  56%|█████▌    | 14532/25880 [2:59:01<2:25:23,  1.30it/s]
1|14533|Loss: 0.8432532548904419:  56%|█████▌    | 14532/25880 [2:59:01<2:25:23,  1.30it/s]
1|14533|Loss: 0.8432532548904419:  56%|█████▌    | 14533/25880 [2:59:02<2:21:59,  1.33it/s]
1|14534|Loss: 0.8328096270561218:  56%|█████▌    | 14533/25880 [2:59:02<2:21:59,  1.33it/s]
1|14534|Loss: 0.8328096270561218:  56%|█████▌    | 14534/25880 [2:59:03<2:25:24,  1.30it/s]
1|14535|Loss: 0.8393406867980957:  56%|█████▌    | 14534/25880 [2:59:03<2:25:24,  1.30it/s]
1|14535|Loss: 0.8393406867980957:  56%|█████▌    | 14535/25880 [2:59:03<2:23:31,  1.32it/s]
1|14536|Loss: 0.9662718176841736:  56%|█████▌    | 14535/25880 [2:59:04<2:23:31,  1.32it/s]
1|14536|Loss: 0.9662718176841736:  56%|█████▌    | 14536/25880 [2:59:04<2:17:06,  1.38it/s]
1|14537|Loss: 0.9348137378692627:  56%|█████▌    | 14536/25880 [2:59:04<2:17:06,  1.38it/s]
1|14537|Loss: 0.9348137378692627:  56%|█████▌    | 14537/25880 [2:59:05<2:21:15,  1.34it/s]
1|14538|Loss: 0.8321143388748169:  56%|█████▌    | 14537/25880 [2:59:05<2:21:15,  1.34it/s]
1|14538|Loss: 0.8321143388748169:  56%|█████▌    | 14538/25880 [2:59:06<2:26:01,  1.29it/s]
1|14539|Loss: 0.8157602548599243:  56%|█████▌    | 14538/25880 [2:59:06<2:26:01,  1.29it/s]
1|14539|Loss: 0.8157602548599243:  56%|█████▌    | 14539/25880 [2:59:06<2:19:46,  1.35it/s]
1|14540|Loss: 1.1047991514205933:  56%|█████▌    | 14539/25880 [2:59:07<2:19:46,  1.35it/s]
1|14540|Loss: 1.1047991514205933:  56%|█████▌    | 14540/25880 [2:59:07<2:24:51,  1.30it/s]
1|14541|Loss: 0.7465839982032776:  56%|█████▌    | 14540/25880 [2:59:07<2:24:51,  1.30it/s]
1|14541|Loss: 0.7465839982032776:  56%|█████▌    | 14541/25880 [2:59:08<2:27:32,  1.28it/s]
1|14542|Loss: 0.9325628876686096:  56%|█████▌    | 14541/25880 [2:59:08<2:27:32,  1.28it/s]
1|14542|Loss: 0.9325628876686096:  56%|█████▌    | 14542/25880 [2:59:09<2:29:50,  1.26it/s]
1|14543|Loss: 0.9344369769096375:  56%|█████▌    | 14542/25880 [2:59:09<2:29:50,  1.26it/s]
1|14543|Loss: 0.9344369769096375:  56%|█████▌    | 14543/25880 [2:59:09<2:23:08,  1.32it/s]
1|14544|Loss: 0.7819118499755859:  56%|█████▌    | 14543/25880 [2:59:10<2:23:08,  1.32it/s]
1|14544|Loss: 0.7819118499755859:  56%|█████▌    | 14544/25880 [2:59:10<2:27:42,  1.28it/s]
1|14545|Loss: 1.088915467262268:  56%|█████▌    | 14544/25880 [2:59:11<2:27:42,  1.28it/s] 
1|14545|Loss: 1.088915467262268:  56%|█████▌    | 14545/25880 [2:59:11<2:30:15,  1.26it/s]
1|14546|Loss: 0.8191388249397278:  56%|█████▌    | 14545/25880 [2:59:11<2:30:15,  1.26it/s]
1|14546|Loss: 0.8191388249397278:  56%|█████▌    | 14546/25880 [2:59:12<2:19:32,  1.35it/s]
1|14547|Loss: 0.7949846982955933:  56%|█████▌    | 14546/25880 [2:59:12<2:19:32,  1.35it/s]
1|14547|Loss: 0.7949846982955933:  56%|█████▌    | 14547/25880 [2:59:12<2:17:00,  1.38it/s]
1|14548|Loss: 0.8383305668830872:  56%|█████▌    | 14547/25880 [2:59:13<2:17:00,  1.38it/s]
1|14548|Loss: 0.8383305668830872:  56%|█████▌    | 14548/25880 [2:59:13<2:23:46,  1.31it/s]
1|14549|Loss: 0.8598918914794922:  56%|█████▌    | 14548/25880 [2:59:14<2:23:46,  1.31it/s]
1|14549|Loss: 0.8598918914794922:  56%|█████▌    | 14549/25880 [2:59:14<2:29:37,  1.26it/s]
1|14550|Loss: 0.9156083464622498:  56%|█████▌    | 14549/25880 [2:59:14<2:29:37,  1.26it/s]
1|14550|Loss: 0.9156083464622498:  56%|█████▌    | 14550/25880 [2:59:15<2:33:07,  1.23it/s]
1|14551|Loss: 0.8678337335586548:  56%|█████▌    | 14550/25880 [2:59:15<2:33:07,  1.23it/s]
1|14551|Loss: 0.8678337335586548:  56%|█████▌    | 14551/25880 [2:59:16<2:30:15,  1.26it/s]
1|14552|Loss: 0.7678419351577759:  56%|█████▌    | 14551/25880 [2:59:16<2:30:15,  1.26it/s]
1|14552|Loss: 0.7678419351577759:  56%|█████▌    | 14552/25880 [2:59:16<2:24:59,  1.30it/s]
1|14553|Loss: 0.8070915341377258:  56%|█████▌    | 14552/25880 [2:59:17<2:24:59,  1.30it/s]
1|14553|Loss: 0.8070915341377258:  56%|█████▌    | 14553/25880 [2:59:17<2:28:59,  1.27it/s]
1|14554|Loss: 0.8966429233551025:  56%|█████▌    | 14553/25880 [2:59:18<2:28:59,  1.27it/s]
1|14554|Loss: 0.8966429233551025:  56%|█████▌    | 14554/25880 [2:59:18<2:17:40,  1.37it/s]
1|14555|Loss: 0.9080254435539246:  56%|█████▌    | 14554/25880 [2:59:18<2:17:40,  1.37it/s]
1|14555|Loss: 0.9080254435539246:  56%|█████▌    | 14555/25880 [2:59:18<2:13:46,  1.41it/s]
1|14556|Loss: 0.8134745955467224:  56%|█████▌    | 14555/25880 [2:59:19<2:13:46,  1.41it/s]
1|14556|Loss: 0.8134745955467224:  56%|█████▌    | 14556/25880 [2:59:19<2:18:56,  1.36it/s]
1|14557|Loss: 0.8272270560264587:  56%|█████▌    | 14556/25880 [2:59:20<2:18:56,  1.36it/s]
1|14557|Loss: 0.8272270560264587:  56%|█████▌    | 14557/25880 [2:59:20<2:15:26,  1.39it/s]
1|14558|Loss: 0.8486242294311523:  56%|█████▌    | 14557/25880 [2:59:20<2:15:26,  1.39it/s]
1|14558|Loss: 0.8486242294311523:  56%|█████▋    | 14558/25880 [2:59:21<2:20:41,  1.34it/s]
1|14559|Loss: 0.7199959754943848:  56%|█████▋    | 14558/25880 [2:59:21<2:20:41,  1.34it/s]
1|14559|Loss: 0.7199959754943848:  56%|█████▋    | 14559/25880 [2:59:21<2:17:06,  1.38it/s]
1|14560|Loss: 0.9307436943054199:  56%|█████▋    | 14559/25880 [2:59:22<2:17:06,  1.38it/s]
1|14560|Loss: 0.9307436943054199:  56%|█████▋    | 14560/25880 [2:59:22<2:14:49,  1.40it/s]
1|14561|Loss: 0.8522487878799438:  56%|█████▋    | 14560/25880 [2:59:22<2:14:49,  1.40it/s]
1|14561|Loss: 0.8522487878799438:  56%|█████▋    | 14561/25880 [2:59:23<2:15:29,  1.39it/s]
1|14562|Loss: 0.7948046922683716:  56%|█████▋    | 14561/25880 [2:59:23<2:15:29,  1.39it/s]
1|14562|Loss: 0.7948046922683716:  56%|█████▋    | 14562/25880 [2:59:23<2:10:44,  1.44it/s]
1|14563|Loss: 0.778767466545105:  56%|█████▋    | 14562/25880 [2:59:24<2:10:44,  1.44it/s] 
1|14563|Loss: 0.778767466545105:  56%|█████▋    | 14563/25880 [2:59:24<2:17:40,  1.37it/s]
1|14564|Loss: 0.8719547390937805:  56%|█████▋    | 14563/25880 [2:59:25<2:17:40,  1.37it/s]
1|14564|Loss: 0.8719547390937805:  56%|█████▋    | 14564/25880 [2:59:25<2:18:23,  1.36it/s]
1|14565|Loss: 0.8567091822624207:  56%|█████▋    | 14564/25880 [2:59:25<2:18:23,  1.36it/s]
1|14565|Loss: 0.8567091822624207:  56%|█████▋    | 14565/25880 [2:59:26<2:14:13,  1.41it/s]
1|14566|Loss: 0.8796346187591553:  56%|█████▋    | 14565/25880 [2:59:26<2:14:13,  1.41it/s]
1|14566|Loss: 0.8796346187591553:  56%|█████▋    | 14566/25880 [2:59:26<2:07:44,  1.48it/s]
1|14567|Loss: 0.9536681771278381:  56%|█████▋    | 14566/25880 [2:59:27<2:07:44,  1.48it/s]
1|14567|Loss: 0.9536681771278381:  56%|█████▋    | 14567/25880 [2:59:27<2:04:52,  1.51it/s]
1|14568|Loss: 0.818081796169281:  56%|█████▋    | 14567/25880 [2:59:27<2:04:52,  1.51it/s] 
1|14568|Loss: 0.818081796169281:  56%|█████▋    | 14568/25880 [2:59:28<2:06:38,  1.49it/s]
1|14569|Loss: 0.8844603896141052:  56%|█████▋    | 14568/25880 [2:59:28<2:06:38,  1.49it/s]
1|14569|Loss: 0.8844603896141052:  56%|█████▋    | 14569/25880 [2:59:28<2:18:28,  1.36it/s]
1|14570|Loss: 0.7930744886398315:  56%|█████▋    | 14569/25880 [2:59:29<2:18:28,  1.36it/s]
1|14570|Loss: 0.7930744886398315:  56%|█████▋    | 14570/25880 [2:59:29<2:15:20,  1.39it/s]
1|14571|Loss: 0.7581077218055725:  56%|█████▋    | 14570/25880 [2:59:30<2:15:20,  1.39it/s]
1|14571|Loss: 0.7581077218055725:  56%|█████▋    | 14571/25880 [2:59:30<2:25:08,  1.30it/s]
1|14572|Loss: 0.9112027883529663:  56%|█████▋    | 14571/25880 [2:59:30<2:25:08,  1.30it/s]
1|14572|Loss: 0.9112027883529663:  56%|█████▋    | 14572/25880 [2:59:31<2:25:25,  1.30it/s]
1|14573|Loss: 0.8090418577194214:  56%|█████▋    | 14572/25880 [2:59:31<2:25:25,  1.30it/s]
1|14573|Loss: 0.8090418577194214:  56%|█████▋    | 14573/25880 [2:59:32<2:25:27,  1.30it/s]
1|14574|Loss: 0.7797136902809143:  56%|█████▋    | 14573/25880 [2:59:32<2:25:27,  1.30it/s]
1|14574|Loss: 0.7797136902809143:  56%|█████▋    | 14574/25880 [2:59:32<2:32:09,  1.24it/s]
1|14575|Loss: 0.8766849637031555:  56%|█████▋    | 14574/25880 [2:59:33<2:32:09,  1.24it/s]
1|14575|Loss: 0.8766849637031555:  56%|█████▋    | 14575/25880 [2:59:33<2:35:51,  1.21it/s]
1|14576|Loss: 0.8133220076560974:  56%|█████▋    | 14575/25880 [2:59:34<2:35:51,  1.21it/s]
1|14576|Loss: 0.8133220076560974:  56%|█████▋    | 14576/25880 [2:59:34<2:32:19,  1.24it/s]
1|14577|Loss: 0.9192283749580383:  56%|█████▋    | 14576/25880 [2:59:35<2:32:19,  1.24it/s]
1|14577|Loss: 0.9192283749580383:  56%|█████▋    | 14577/25880 [2:59:35<2:30:26,  1.25it/s]
1|14578|Loss: 0.8581774234771729:  56%|█████▋    | 14577/25880 [2:59:35<2:30:26,  1.25it/s]
1|14578|Loss: 0.8581774234771729:  56%|█████▋    | 14578/25880 [2:59:36<2:28:08,  1.27it/s]
1|14579|Loss: 0.7839338779449463:  56%|█████▋    | 14578/25880 [2:59:36<2:28:08,  1.27it/s]
1|14579|Loss: 0.7839338779449463:  56%|█████▋    | 14579/25880 [2:59:36<2:18:56,  1.36it/s]
1|14580|Loss: 0.7310448288917542:  56%|█████▋    | 14579/25880 [2:59:37<2:18:56,  1.36it/s]
1|14580|Loss: 0.7310448288917542:  56%|█████▋    | 14580/25880 [2:59:37<2:22:50,  1.32it/s]
1|14581|Loss: 0.8372322916984558:  56%|█████▋    | 14580/25880 [2:59:37<2:22:50,  1.32it/s]
1|14581|Loss: 0.8372322916984558:  56%|█████▋    | 14581/25880 [2:59:38<2:22:54,  1.32it/s]
1|14582|Loss: 0.8912513256072998:  56%|█████▋    | 14581/25880 [2:59:38<2:22:54,  1.32it/s]
1|14582|Loss: 0.8912513256072998:  56%|█████▋    | 14582/25880 [2:59:39<2:23:58,  1.31it/s]
1|14583|Loss: 0.806665301322937:  56%|█████▋    | 14582/25880 [2:59:39<2:23:58,  1.31it/s] 
1|14583|Loss: 0.806665301322937:  56%|█████▋    | 14583/25880 [2:59:39<2:23:00,  1.32it/s]
1|14584|Loss: 0.8604469895362854:  56%|█████▋    | 14583/25880 [2:59:40<2:23:00,  1.32it/s]
1|14584|Loss: 0.8604469895362854:  56%|█████▋    | 14584/25880 [2:59:40<2:11:17,  1.43it/s]
1|14585|Loss: 0.7836403846740723:  56%|█████▋    | 14584/25880 [2:59:40<2:11:17,  1.43it/s]
1|14585|Loss: 0.7836403846740723:  56%|█████▋    | 14585/25880 [2:59:40<2:02:35,  1.54it/s]
1|14586|Loss: 0.9362002015113831:  56%|█████▋    | 14585/25880 [2:59:41<2:02:35,  1.54it/s]
1|14586|Loss: 0.9362002015113831:  56%|█████▋    | 14586/25880 [2:59:41<2:00:39,  1.56it/s]
1|14587|Loss: 0.9576115608215332:  56%|█████▋    | 14586/25880 [2:59:41<2:00:39,  1.56it/s]
1|14587|Loss: 0.9576115608215332:  56%|█████▋    | 14587/25880 [2:59:42<2:09:25,  1.45it/s]
1|14588|Loss: 0.8269158005714417:  56%|█████▋    | 14587/25880 [2:59:42<2:09:25,  1.45it/s]
1|14588|Loss: 0.8269158005714417:  56%|█████▋    | 14588/25880 [2:59:43<2:13:02,  1.41it/s]
1|14589|Loss: 0.9929084181785583:  56%|█████▋    | 14588/25880 [2:59:43<2:13:02,  1.41it/s]
1|14589|Loss: 0.9929084181785583:  56%|█████▋    | 14589/25880 [2:59:43<2:19:23,  1.35it/s]
1|14590|Loss: 0.7530229687690735:  56%|█████▋    | 14589/25880 [2:59:44<2:19:23,  1.35it/s]
1|14590|Loss: 0.7530229687690735:  56%|█████▋    | 14590/25880 [2:59:44<2:07:21,  1.48it/s]
1|14591|Loss: 0.9735464453697205:  56%|█████▋    | 14590/25880 [2:59:44<2:07:21,  1.48it/s]
1|14591|Loss: 0.9735464453697205:  56%|█████▋    | 14591/25880 [2:59:44<1:56:08,  1.62it/s]
1|14592|Loss: 1.1703935861587524:  56%|█████▋    | 14591/25880 [2:59:45<1:56:08,  1.62it/s]
1|14592|Loss: 1.1703935861587524:  56%|█████▋    | 14592/25880 [2:59:45<2:10:05,  1.45it/s]
1|14593|Loss: 3.0981316566467285:  56%|█████▋    | 14592/25880 [2:59:46<2:10:05,  1.45it/s]
1|14593|Loss: 3.0981316566467285:  56%|█████▋    | 14593/25880 [2:59:46<2:18:29,  1.36it/s]
1|14594|Loss: 1.6847630739212036:  56%|█████▋    | 14593/25880 [2:59:46<2:18:29,  1.36it/s]
1|14594|Loss: 1.6847630739212036:  56%|█████▋    | 14594/25880 [2:59:47<2:06:28,  1.49it/s]
1|14595|Loss: 2.146003007888794:  56%|█████▋    | 14594/25880 [2:59:47<2:06:28,  1.49it/s] 
1|14595|Loss: 2.146003007888794:  56%|█████▋    | 14595/25880 [2:59:47<2:01:17,  1.55it/s]
1|14596|Loss: 1.3031809329986572:  56%|█████▋    | 14595/25880 [2:59:48<2:01:17,  1.55it/s]
1|14596|Loss: 1.3031809329986572:  56%|█████▋    | 14596/25880 [2:59:48<2:03:38,  1.52it/s]
1|14597|Loss: 1.1320286989212036:  56%|█████▋    | 14596/25880 [2:59:48<2:03:38,  1.52it/s]
1|14597|Loss: 1.1320286989212036:  56%|█████▋    | 14597/25880 [2:59:49<2:16:12,  1.38it/s]
1|14598|Loss: 1.2164443731307983:  56%|█████▋    | 14597/25880 [2:59:49<2:16:12,  1.38it/s]
1|14598|Loss: 1.2164443731307983:  56%|█████▋    | 14598/25880 [2:59:50<2:22:17,  1.32it/s]
1|14599|Loss: 1.1416015625:  56%|█████▋    | 14598/25880 [2:59:50<2:22:17,  1.32it/s]      
1|14599|Loss: 1.1416015625:  56%|█████▋    | 14599/25880 [2:59:50<2:20:11,  1.34it/s]
1|14600|Loss: 0.8579017519950867:  56%|█████▋    | 14599/25880 [2:59:51<2:20:11,  1.34it/s]
1|14600|Loss: 0.8579017519950867:  56%|█████▋    | 14600/25880 [2:59:51<2:17:05,  1.37it/s]
1|14601|Loss: 0.9224264025688171:  56%|█████▋    | 14600/25880 [2:59:51<2:17:05,  1.37it/s]
1|14601|Loss: 0.9224264025688171:  56%|█████▋    | 14601/25880 [2:59:52<2:12:41,  1.42it/s]
1|14602|Loss: 0.9094278812408447:  56%|█████▋    | 14601/25880 [2:59:52<2:12:41,  1.42it/s]
1|14602|Loss: 0.9094278812408447:  56%|█████▋    | 14602/25880 [2:59:52<2:00:40,  1.56it/s]
1|14603|Loss: 0.8194324970245361:  56%|█████▋    | 14602/25880 [2:59:53<2:00:40,  1.56it/s]
1|14603|Loss: 0.8194324970245361:  56%|█████▋    | 14603/25880 [2:59:53<2:13:16,  1.41it/s]
1|14604|Loss: 0.9617670774459839:  56%|█████▋    | 14603/25880 [2:59:54<2:13:16,  1.41it/s]
1|14604|Loss: 0.9617670774459839:  56%|█████▋    | 14604/25880 [2:59:54<2:15:59,  1.38it/s]
1|14605|Loss: 0.831089437007904:  56%|█████▋    | 14604/25880 [2:59:54<2:15:59,  1.38it/s] 
1|14605|Loss: 0.831089437007904:  56%|█████▋    | 14605/25880 [2:59:55<2:24:18,  1.30it/s]
1|14606|Loss: 1.042744517326355:  56%|█████▋    | 14605/25880 [2:59:55<2:24:18,  1.30it/s]
1|14606|Loss: 1.042744517326355:  56%|█████▋    | 14606/25880 [2:59:56<2:31:10,  1.24it/s]
1|14607|Loss: 0.7694836854934692:  56%|█████▋    | 14606/25880 [2:59:56<2:31:10,  1.24it/s]
1|14607|Loss: 0.7694836854934692:  56%|█████▋    | 14607/25880 [2:59:56<2:16:45,  1.37it/s]
1|14608|Loss: 0.9456349015235901:  56%|█████▋    | 14607/25880 [2:59:56<2:16:45,  1.37it/s]
1|14608|Loss: 0.9456349015235901:  56%|█████▋    | 14608/25880 [2:59:57<2:09:33,  1.45it/s]
1|14609|Loss: 0.7916819453239441:  56%|█████▋    | 14608/25880 [2:59:57<2:09:33,  1.45it/s]
1|14609|Loss: 0.7916819453239441:  56%|█████▋    | 14609/25880 [2:59:58<2:21:27,  1.33it/s]
1|14610|Loss: 1.014162302017212:  56%|█████▋    | 14609/25880 [2:59:58<2:21:27,  1.33it/s] 
1|14610|Loss: 1.014162302017212:  56%|█████▋    | 14610/25880 [2:59:58<2:14:58,  1.39it/s]
1|14611|Loss: 0.9115706086158752:  56%|█████▋    | 14610/25880 [2:59:59<2:14:58,  1.39it/s]
1|14611|Loss: 0.9115706086158752:  56%|█████▋    | 14611/25880 [2:59:59<2:07:22,  1.47it/s]
1|14612|Loss: 0.8478437066078186:  56%|█████▋    | 14611/25880 [2:59:59<2:07:22,  1.47it/s]
1|14612|Loss: 0.8478437066078186:  56%|█████▋    | 14612/25880 [3:00:00<2:13:16,  1.41it/s]
1|14613|Loss: 0.8940855860710144:  56%|█████▋    | 14612/25880 [3:00:00<2:13:16,  1.41it/s]
1|14613|Loss: 0.8940855860710144:  56%|█████▋    | 14613/25880 [3:00:00<2:05:40,  1.49it/s]
1|14614|Loss: 0.7681398391723633:  56%|█████▋    | 14613/25880 [3:00:01<2:05:40,  1.49it/s]
1|14614|Loss: 0.7681398391723633:  56%|█████▋    | 14614/25880 [3:00:01<2:02:11,  1.54it/s]
1|14615|Loss: 0.807927131652832:  56%|█████▋    | 14614/25880 [3:00:01<2:02:11,  1.54it/s] 
1|14615|Loss: 0.807927131652832:  56%|█████▋    | 14615/25880 [3:00:02<2:08:50,  1.46it/s]
1|14616|Loss: 1.042278528213501:  56%|█████▋    | 14615/25880 [3:00:02<2:08:50,  1.46it/s]
1|14616|Loss: 1.042278528213501:  56%|█████▋    | 14616/25880 [3:00:02<2:08:30,  1.46it/s]
1|14617|Loss: 0.8643030524253845:  56%|█████▋    | 14616/25880 [3:00:03<2:08:30,  1.46it/s]
1|14617|Loss: 0.8643030524253845:  56%|█████▋    | 14617/25880 [3:00:03<2:08:43,  1.46it/s]
1|14618|Loss: 0.8719233870506287:  56%|█████▋    | 14617/25880 [3:00:03<2:08:43,  1.46it/s]
1|14618|Loss: 0.8719233870506287:  56%|█████▋    | 14618/25880 [3:00:04<2:15:32,  1.38it/s]
1|14619|Loss: 0.7377517819404602:  56%|█████▋    | 14618/25880 [3:00:04<2:15:32,  1.38it/s]
1|14619|Loss: 0.7377517819404602:  56%|█████▋    | 14619/25880 [3:00:05<2:17:22,  1.37it/s]
1|14620|Loss: 0.8284538984298706:  56%|█████▋    | 14619/25880 [3:00:05<2:17:22,  1.37it/s]
1|14620|Loss: 0.8284538984298706:  56%|█████▋    | 14620/25880 [3:00:05<2:13:13,  1.41it/s]
1|14621|Loss: 0.8609426021575928:  56%|█████▋    | 14620/25880 [3:00:06<2:13:13,  1.41it/s]
1|14621|Loss: 0.8609426021575928:  56%|█████▋    | 14621/25880 [3:00:06<2:16:33,  1.37it/s]
1|14622|Loss: 0.9630555510520935:  56%|█████▋    | 14621/25880 [3:00:06<2:16:33,  1.37it/s]
1|14622|Loss: 0.9630555510520935:  56%|█████▋    | 14622/25880 [3:00:07<2:13:23,  1.41it/s]
1|14623|Loss: 0.9031556248664856:  56%|█████▋    | 14622/25880 [3:00:07<2:13:23,  1.41it/s]
1|14623|Loss: 0.9031556248664856:  57%|█████▋    | 14623/25880 [3:00:07<2:19:26,  1.35it/s]
1|14624|Loss: 0.8375515341758728:  57%|█████▋    | 14623/25880 [3:00:08<2:19:26,  1.35it/s]
1|14624|Loss: 0.8375515341758728:  57%|█████▋    | 14624/25880 [3:00:08<2:14:15,  1.40it/s]
1|14625|Loss: 0.8661009073257446:  57%|█████▋    | 14624/25880 [3:00:08<2:14:15,  1.40it/s]
1|14625|Loss: 0.8661009073257446:  57%|█████▋    | 14625/25880 [3:00:09<2:15:40,  1.38it/s]
1|14626|Loss: 0.760090172290802:  57%|█████▋    | 14625/25880 [3:00:09<2:15:40,  1.38it/s] 
1|14626|Loss: 0.760090172290802:  57%|█████▋    | 14626/25880 [3:00:10<2:12:51,  1.41it/s]
1|14627|Loss: 0.9647833108901978:  57%|█████▋    | 14626/25880 [3:00:10<2:12:51,  1.41it/s]
1|14627|Loss: 0.9647833108901978:  57%|█████▋    | 14627/25880 [3:00:10<2:08:13,  1.46it/s]
1|14628|Loss: 1.0860400199890137:  57%|█████▋    | 14627/25880 [3:00:10<2:08:13,  1.46it/s]
1|14628|Loss: 1.0860400199890137:  57%|█████▋    | 14628/25880 [3:00:11<2:00:47,  1.55it/s]
1|14629|Loss: 0.8937418460845947:  57%|█████▋    | 14628/25880 [3:00:11<2:00:47,  1.55it/s]
1|14629|Loss: 0.8937418460845947:  57%|█████▋    | 14629/25880 [3:00:11<1:53:22,  1.65it/s]
1|14630|Loss: 0.8758293986320496:  57%|█████▋    | 14629/25880 [3:00:12<1:53:22,  1.65it/s]
1|14630|Loss: 0.8758293986320496:  57%|█████▋    | 14630/25880 [3:00:12<1:54:01,  1.64it/s]
1|14631|Loss: 0.8662864565849304:  57%|█████▋    | 14630/25880 [3:00:12<1:54:01,  1.64it/s]
1|14631|Loss: 0.8662864565849304:  57%|█████▋    | 14631/25880 [3:00:12<1:54:46,  1.63it/s]
1|14632|Loss: 0.7682061791419983:  57%|█████▋    | 14631/25880 [3:00:13<1:54:46,  1.63it/s]
1|14632|Loss: 0.7682061791419983:  57%|█████▋    | 14632/25880 [3:00:13<2:00:14,  1.56it/s]
1|14633|Loss: 0.8276882171630859:  57%|█████▋    | 14632/25880 [3:00:14<2:00:14,  1.56it/s]
1|14633|Loss: 0.8276882171630859:  57%|█████▋    | 14633/25880 [3:00:14<2:03:48,  1.51it/s]
1|14634|Loss: 0.9078688025474548:  57%|█████▋    | 14633/25880 [3:00:14<2:03:48,  1.51it/s]
1|14634|Loss: 0.9078688025474548:  57%|█████▋    | 14634/25880 [3:00:15<2:13:50,  1.40it/s]
1|14635|Loss: 0.9888465404510498:  57%|█████▋    | 14634/25880 [3:00:15<2:13:50,  1.40it/s]
1|14635|Loss: 0.9888465404510498:  57%|█████▋    | 14635/25880 [3:00:16<2:23:16,  1.31it/s]
1|14636|Loss: 0.8306000828742981:  57%|█████▋    | 14635/25880 [3:00:16<2:23:16,  1.31it/s]
1|14636|Loss: 0.8306000828742981:  57%|█████▋    | 14636/25880 [3:00:16<2:18:09,  1.36it/s]
1|14637|Loss: 0.7932367324829102:  57%|█████▋    | 14636/25880 [3:00:17<2:18:09,  1.36it/s]
1|14637|Loss: 0.7932367324829102:  57%|█████▋    | 14637/25880 [3:00:17<2:17:03,  1.37it/s]
1|14638|Loss: 0.7601873278617859:  57%|█████▋    | 14637/25880 [3:00:17<2:17:03,  1.37it/s]
1|14638|Loss: 0.7601873278617859:  57%|█████▋    | 14638/25880 [3:00:18<2:17:34,  1.36it/s]
1|14639|Loss: 0.7608000040054321:  57%|█████▋    | 14638/25880 [3:00:18<2:17:34,  1.36it/s]
1|14639|Loss: 0.7608000040054321:  57%|█████▋    | 14639/25880 [3:00:18<2:11:57,  1.42it/s]
1|14640|Loss: 0.8856104612350464:  57%|█████▋    | 14639/25880 [3:00:19<2:11:57,  1.42it/s]
1|14640|Loss: 0.8856104612350464:  57%|█████▋    | 14640/25880 [3:00:19<2:16:34,  1.37it/s]
1|14641|Loss: 0.8516240119934082:  57%|█████▋    | 14640/25880 [3:00:19<2:16:34,  1.37it/s]
1|14641|Loss: 0.8516240119934082:  57%|█████▋    | 14641/25880 [3:00:20<2:08:45,  1.45it/s]
1|14642|Loss: 1.0027912855148315:  57%|█████▋    | 14641/25880 [3:00:20<2:08:45,  1.45it/s]
1|14642|Loss: 1.0027912855148315:  57%|█████▋    | 14642/25880 [3:00:20<2:07:38,  1.47it/s]
1|14643|Loss: 0.8648535013198853:  57%|█████▋    | 14642/25880 [3:00:21<2:07:38,  1.47it/s]
1|14643|Loss: 0.8648535013198853:  57%|█████▋    | 14643/25880 [3:00:21<2:05:09,  1.50it/s]
1|14644|Loss: 0.8920772075653076:  57%|█████▋    | 14643/25880 [3:00:21<2:05:09,  1.50it/s]
1|14644|Loss: 0.8920772075653076:  57%|█████▋    | 14644/25880 [3:00:22<2:07:34,  1.47it/s]
1|14645|Loss: 0.873997688293457:  57%|█████▋    | 14644/25880 [3:00:22<2:07:34,  1.47it/s] 
1|14645|Loss: 0.873997688293457:  57%|█████▋    | 14645/25880 [3:00:23<2:15:33,  1.38it/s]
1|14646|Loss: 1.001081943511963:  57%|█████▋    | 14645/25880 [3:00:23<2:15:33,  1.38it/s]
1|14646|Loss: 1.001081943511963:  57%|█████▋    | 14646/25880 [3:00:23<2:12:27,  1.41it/s]
1|14647|Loss: 0.9155605435371399:  57%|█████▋    | 14646/25880 [3:00:24<2:12:27,  1.41it/s]
1|14647|Loss: 0.9155605435371399:  57%|█████▋    | 14647/25880 [3:00:24<2:03:26,  1.52it/s]
1|14648|Loss: 0.8860793113708496:  57%|█████▋    | 14647/25880 [3:00:24<2:03:26,  1.52it/s]
1|14648|Loss: 0.8860793113708496:  57%|█████▋    | 14648/25880 [3:00:24<2:05:08,  1.50it/s]
1|14649|Loss: 0.9428630471229553:  57%|█████▋    | 14648/25880 [3:00:25<2:05:08,  1.50it/s]
1|14649|Loss: 0.9428630471229553:  57%|█████▋    | 14649/25880 [3:00:25<2:14:24,  1.39it/s]
1|14650|Loss: 0.8061661124229431:  57%|█████▋    | 14649/25880 [3:00:26<2:14:24,  1.39it/s]
1|14650|Loss: 0.8061661124229431:  57%|█████▋    | 14650/25880 [3:00:26<2:21:07,  1.33it/s]
1|14651|Loss: 0.8745996952056885:  57%|█████▋    | 14650/25880 [3:00:27<2:21:07,  1.33it/s]
1|14651|Loss: 0.8745996952056885:  57%|█████▋    | 14651/25880 [3:00:27<2:26:17,  1.28it/s]
1|14652|Loss: 0.8019747138023376:  57%|█████▋    | 14651/25880 [3:00:27<2:26:17,  1.28it/s]
1|14652|Loss: 0.8019747138023376:  57%|█████▋    | 14652/25880 [3:00:28<2:30:16,  1.25it/s]
1|14653|Loss: 0.8355902433395386:  57%|█████▋    | 14652/25880 [3:00:28<2:30:16,  1.25it/s]
1|14653|Loss: 0.8355902433395386:  57%|█████▋    | 14653/25880 [3:00:28<2:21:09,  1.33it/s]
1|14654|Loss: 0.8286396265029907:  57%|█████▋    | 14653/25880 [3:00:29<2:21:09,  1.33it/s]
1|14654|Loss: 0.8286396265029907:  57%|█████▋    | 14654/25880 [3:00:29<2:20:42,  1.33it/s]
1|14655|Loss: 0.8674540519714355:  57%|█████▋    | 14654/25880 [3:00:30<2:20:42,  1.33it/s]
1|14655|Loss: 0.8674540519714355:  57%|█████▋    | 14655/25880 [3:00:30<2:20:45,  1.33it/s]
1|14656|Loss: 0.9559266567230225:  57%|█████▋    | 14655/25880 [3:00:30<2:20:45,  1.33it/s]
1|14656|Loss: 0.9559266567230225:  57%|█████▋    | 14656/25880 [3:00:31<2:15:49,  1.38it/s]
1|14657|Loss: 0.8044995665550232:  57%|█████▋    | 14656/25880 [3:00:31<2:15:49,  1.38it/s]
1|14657|Loss: 0.8044995665550232:  57%|█████▋    | 14657/25880 [3:00:31<2:05:18,  1.49it/s]
1|14658|Loss: 0.9160897135734558:  57%|█████▋    | 14657/25880 [3:00:32<2:05:18,  1.49it/s]
1|14658|Loss: 0.9160897135734558:  57%|█████▋    | 14658/25880 [3:00:32<2:09:31,  1.44it/s]
1|14659|Loss: 0.8967486619949341:  57%|█████▋    | 14658/25880 [3:00:32<2:09:31,  1.44it/s]
1|14659|Loss: 0.8967486619949341:  57%|█████▋    | 14659/25880 [3:00:33<2:12:21,  1.41it/s]
1|14660|Loss: 0.789115309715271:  57%|█████▋    | 14659/25880 [3:00:33<2:12:21,  1.41it/s] 
1|14660|Loss: 0.789115309715271:  57%|█████▋    | 14660/25880 [3:00:33<2:03:49,  1.51it/s]
1|14661|Loss: 0.9589647650718689:  57%|█████▋    | 14660/25880 [3:00:34<2:03:49,  1.51it/s]
1|14661|Loss: 0.9589647650718689:  57%|█████▋    | 14661/25880 [3:00:34<2:08:12,  1.46it/s]
1|14662|Loss: 0.9188275933265686:  57%|█████▋    | 14661/25880 [3:00:34<2:08:12,  1.46it/s]
1|14662|Loss: 0.9188275933265686:  57%|█████▋    | 14662/25880 [3:00:35<2:07:28,  1.47it/s]
1|14663|Loss: 0.8631230592727661:  57%|█████▋    | 14662/25880 [3:00:35<2:07:28,  1.47it/s]
1|14663|Loss: 0.8631230592727661:  57%|█████▋    | 14663/25880 [3:00:35<2:15:48,  1.38it/s]
1|14664|Loss: 0.9481033086776733:  57%|█████▋    | 14663/25880 [3:00:36<2:15:48,  1.38it/s]
1|14664|Loss: 0.9481033086776733:  57%|█████▋    | 14664/25880 [3:00:36<2:13:57,  1.40it/s]
1|14665|Loss: 0.9260197281837463:  57%|█████▋    | 14664/25880 [3:00:37<2:13:57,  1.40it/s]
1|14665|Loss: 0.9260197281837463:  57%|█████▋    | 14665/25880 [3:00:37<2:14:36,  1.39it/s]
1|14666|Loss: 0.7803972363471985:  57%|█████▋    | 14665/25880 [3:00:37<2:14:36,  1.39it/s]
1|14666|Loss: 0.7803972363471985:  57%|█████▋    | 14666/25880 [3:00:38<2:15:56,  1.37it/s]
1|14667|Loss: 0.8538432121276855:  57%|█████▋    | 14666/25880 [3:00:38<2:15:56,  1.37it/s]
1|14667|Loss: 0.8538432121276855:  57%|█████▋    | 14667/25880 [3:00:38<2:15:01,  1.38it/s]
1|14668|Loss: 0.701129674911499:  57%|█████▋    | 14667/25880 [3:00:39<2:15:01,  1.38it/s] 
1|14668|Loss: 0.701129674911499:  57%|█████▋    | 14668/25880 [3:00:39<2:14:26,  1.39it/s]
1|14669|Loss: 0.7018572688102722:  57%|█████▋    | 14668/25880 [3:00:39<2:14:26,  1.39it/s]
1|14669|Loss: 0.7018572688102722:  57%|█████▋    | 14669/25880 [3:00:40<2:06:49,  1.47it/s]
1|14670|Loss: 0.7559410929679871:  57%|█████▋    | 14669/25880 [3:00:40<2:06:49,  1.47it/s]
1|14670|Loss: 0.7559410929679871:  57%|█████▋    | 14670/25880 [3:00:40<2:06:18,  1.48it/s]
1|14671|Loss: 1.1074070930480957:  57%|█████▋    | 14670/25880 [3:00:41<2:06:18,  1.48it/s]
1|14671|Loss: 1.1074070930480957:  57%|█████▋    | 14671/25880 [3:00:41<2:14:32,  1.39it/s]
1|14672|Loss: 0.7583087682723999:  57%|█████▋    | 14671/25880 [3:00:42<2:14:32,  1.39it/s]
1|14672|Loss: 0.7583087682723999:  57%|█████▋    | 14672/25880 [3:00:42<2:20:03,  1.33it/s]
1|14673|Loss: 0.8374998569488525:  57%|█████▋    | 14672/25880 [3:00:42<2:20:03,  1.33it/s]
1|14673|Loss: 0.8374998569488525:  57%|█████▋    | 14673/25880 [3:00:43<2:18:34,  1.35it/s]
1|14674|Loss: 0.818943440914154:  57%|█████▋    | 14673/25880 [3:00:43<2:18:34,  1.35it/s] 
1|14674|Loss: 0.818943440914154:  57%|█████▋    | 14674/25880 [3:00:43<2:21:15,  1.32it/s]
1|14675|Loss: 0.7617086172103882:  57%|█████▋    | 14674/25880 [3:00:44<2:21:15,  1.32it/s]
1|14675|Loss: 0.7617086172103882:  57%|█████▋    | 14675/25880 [3:00:44<2:26:55,  1.27it/s]
1|14676|Loss: 0.7905789017677307:  57%|█████▋    | 14675/25880 [3:00:45<2:26:55,  1.27it/s]
1|14676|Loss: 0.7905789017677307:  57%|█████▋    | 14676/25880 [3:00:45<2:31:59,  1.23it/s]
1|14677|Loss: 0.8596342206001282:  57%|█████▋    | 14676/25880 [3:00:46<2:31:59,  1.23it/s]
1|14677|Loss: 0.8596342206001282:  57%|█████▋    | 14677/25880 [3:00:46<2:35:21,  1.20it/s]
1|14678|Loss: 0.8680960536003113:  57%|█████▋    | 14677/25880 [3:00:46<2:35:21,  1.20it/s]
1|14678|Loss: 0.8680960536003113:  57%|█████▋    | 14678/25880 [3:00:47<2:22:23,  1.31it/s]
1|14679|Loss: 0.9310651421546936:  57%|█████▋    | 14678/25880 [3:00:47<2:22:23,  1.31it/s]
1|14679|Loss: 0.9310651421546936:  57%|█████▋    | 14679/25880 [3:00:47<2:23:37,  1.30it/s]
1|14680|Loss: 0.9517326951026917:  57%|█████▋    | 14679/25880 [3:00:48<2:23:37,  1.30it/s]
1|14680|Loss: 0.9517326951026917:  57%|█████▋    | 14680/25880 [3:00:48<2:16:46,  1.36it/s]
1|14681|Loss: 0.905678927898407:  57%|█████▋    | 14680/25880 [3:00:48<2:16:46,  1.36it/s] 
1|14681|Loss: 0.905678927898407:  57%|█████▋    | 14681/25880 [3:00:49<2:09:49,  1.44it/s]
1|14682|Loss: 0.9203582406044006:  57%|█████▋    | 14681/25880 [3:00:49<2:09:49,  1.44it/s]
1|14682|Loss: 0.9203582406044006:  57%|█████▋    | 14682/25880 [3:00:49<2:06:30,  1.48it/s]
1|14683|Loss: 0.9770897030830383:  57%|█████▋    | 14682/25880 [3:00:50<2:06:30,  1.48it/s]
1|14683|Loss: 0.9770897030830383:  57%|█████▋    | 14683/25880 [3:00:50<2:03:33,  1.51it/s]
1|14684|Loss: 0.8249709606170654:  57%|█████▋    | 14683/25880 [3:00:50<2:03:33,  1.51it/s]
1|14684|Loss: 0.8249709606170654:  57%|█████▋    | 14684/25880 [3:00:51<2:10:32,  1.43it/s]
1|14685|Loss: 0.7512015700340271:  57%|█████▋    | 14684/25880 [3:00:51<2:10:32,  1.43it/s]
1|14685|Loss: 0.7512015700340271:  57%|█████▋    | 14685/25880 [3:00:52<2:21:36,  1.32it/s]
1|14686|Loss: 0.8103322386741638:  57%|█████▋    | 14685/25880 [3:00:52<2:21:36,  1.32it/s]
1|14686|Loss: 0.8103322386741638:  57%|█████▋    | 14686/25880 [3:00:53<2:28:11,  1.26it/s]
1|14687|Loss: 0.9317849278450012:  57%|█████▋    | 14686/25880 [3:00:53<2:28:11,  1.26it/s]
1|14687|Loss: 0.9317849278450012:  57%|█████▋    | 14687/25880 [3:00:53<2:25:07,  1.29it/s]
1|14688|Loss: 0.9213014245033264:  57%|█████▋    | 14687/25880 [3:00:54<2:25:07,  1.29it/s]
1|14688|Loss: 0.9213014245033264:  57%|█████▋    | 14688/25880 [3:00:54<2:22:09,  1.31it/s]
1|14689|Loss: 0.7742369174957275:  57%|█████▋    | 14688/25880 [3:00:54<2:22:09,  1.31it/s]
1|14689|Loss: 0.7742369174957275:  57%|█████▋    | 14689/25880 [3:00:55<2:24:45,  1.29it/s]
1|14690|Loss: 0.800818145275116:  57%|█████▋    | 14689/25880 [3:00:55<2:24:45,  1.29it/s] 
1|14690|Loss: 0.800818145275116:  57%|█████▋    | 14690/25880 [3:00:56<2:33:39,  1.21it/s]
1|14691|Loss: 0.8882574439048767:  57%|█████▋    | 14690/25880 [3:00:56<2:33:39,  1.21it/s]
1|14691|Loss: 0.8882574439048767:  57%|█████▋    | 14691/25880 [3:00:57<2:35:41,  1.20it/s]
1|14692|Loss: 0.7649610042572021:  57%|█████▋    | 14691/25880 [3:00:57<2:35:41,  1.20it/s]
1|14692|Loss: 0.7649610042572021:  57%|██��██▋    | 14692/25880 [3:00:57<2:29:49,  1.24it/s]
1|14693|Loss: 0.8495725393295288:  57%|█████▋    | 14692/25880 [3:00:58<2:29:49,  1.24it/s]
1|14693|Loss: 0.8495725393295288:  57%|█████▋    | 14693/25880 [3:00:58<2:26:06,  1.28it/s]
1|14694|Loss: 0.9211963415145874:  57%|█████▋    | 14693/25880 [3:00:59<2:26:06,  1.28it/s]
1|14694|Loss: 0.9211963415145874:  57%|█████▋    | 14694/25880 [3:00:59<2:27:55,  1.26it/s]
1|14695|Loss: 0.7148886322975159:  57%|█████▋    | 14694/25880 [3:00:59<2:27:55,  1.26it/s]
1|14695|Loss: 0.7148886322975159:  57%|█████▋    | 14695/25880 [3:01:00<2:25:27,  1.28it/s]
1|14696|Loss: 0.6964914798736572:  57%|█████▋    | 14695/25880 [3:01:00<2:25:27,  1.28it/s]
1|14696|Loss: 0.6964914798736572:  57%|█████▋    | 14696/25880 [3:01:00<2:22:25,  1.31it/s]
1|14697|Loss: 0.8661743998527527:  57%|█████▋    | 14696/25880 [3:01:01<2:22:25,  1.31it/s]
1|14697|Loss: 0.8661743998527527:  57%|█████▋    | 14697/25880 [3:01:01<2:12:27,  1.41it/s]
1|14698|Loss: 0.870233952999115:  57%|█████▋    | 14697/25880 [3:01:01<2:12:27,  1.41it/s] 
1|14698|Loss: 0.870233952999115:  57%|█████▋    | 14698/25880 [3:01:02<2:06:20,  1.48it/s]
1|14699|Loss: 0.8749080896377563:  57%|█████▋    | 14698/25880 [3:01:02<2:06:20,  1.48it/s]
1|14699|Loss: 0.8749080896377563:  57%|█████▋    | 14699/25880 [3:01:02<2:04:08,  1.50it/s]
1|14700|Loss: 0.9067277908325195:  57%|█████▋    | 14699/25880 [3:01:03<2:04:08,  1.50it/s]
1|14700|Loss: 0.9067277908325195:  57%|█████▋    | 14700/25880 [3:01:03<2:06:50,  1.47it/s]
1|14701|Loss: 0.8644636869430542:  57%|█████▋    | 14700/25880 [3:01:03<2:06:50,  1.47it/s]
1|14701|Loss: 0.8644636869430542:  57%|█████▋    | 14701/25880 [3:01:04<2:08:02,  1.46it/s]
1|14702|Loss: 0.8136078119277954:  57%|█████▋    | 14701/25880 [3:01:04<2:08:02,  1.46it/s]
1|14702|Loss: 0.8136078119277954:  57%|█████▋    | 14702/25880 [3:01:04<2:02:01,  1.53it/s]
1|14703|Loss: 0.8467564582824707:  57%|█████▋    | 14702/25880 [3:01:05<2:02:01,  1.53it/s]
1|14703|Loss: 0.8467564582824707:  57%|█████▋    | 14703/25880 [3:01:05<2:04:04,  1.50it/s]
1|14704|Loss: 0.7967697978019714:  57%|█████▋    | 14703/25880 [3:01:05<2:04:04,  1.50it/s]
1|14704|Loss: 0.7967697978019714:  57%|█████▋    | 14704/25880 [3:01:06<2:10:12,  1.43it/s]
1|14705|Loss: 0.7713304758071899:  57%|█████▋    | 14704/25880 [3:01:06<2:10:12,  1.43it/s]
1|14705|Loss: 0.7713304758071899:  57%|█████▋    | 14705/25880 [3:01:06<2:15:37,  1.37it/s]
1|14706|Loss: 0.8828074932098389:  57%|█████▋    | 14705/25880 [3:01:07<2:15:37,  1.37it/s]
1|14706|Loss: 0.8828074932098389:  57%|█████▋    | 14706/25880 [3:01:07<2:16:27,  1.36it/s]
1|14707|Loss: 0.8353775143623352:  57%|█████▋    | 14706/25880 [3:01:08<2:16:27,  1.36it/s]
1|14707|Loss: 0.8353775143623352:  57%|█████▋    | 14707/25880 [3:01:08<2:11:02,  1.42it/s]
1|14708|Loss: 0.8660266995429993:  57%|█████▋    | 14707/25880 [3:01:08<2:11:02,  1.42it/s]
1|14708|Loss: 0.8660266995429993:  57%|█████▋    | 14708/25880 [3:01:09<2:10:33,  1.43it/s]
1|14709|Loss: 0.8186483979225159:  57%|█████▋    | 14708/25880 [3:01:09<2:10:33,  1.43it/s]
1|14709|Loss: 0.8186483979225159:  57%|█████▋    | 14709/25880 [3:01:09<2:16:53,  1.36it/s]
1|14710|Loss: 0.8861185908317566:  57%|█████▋    | 14709/25880 [3:01:10<2:16:53,  1.36it/s]
1|14710|Loss: 0.8861185908317566:  57%|█████▋    | 14710/25880 [3:01:10<2:28:28,  1.25it/s]
1|14711|Loss: 0.8538617491722107:  57%|█████▋    | 14710/25880 [3:01:11<2:28:28,  1.25it/s]
1|14711|Loss: 0.8538617491722107:  57%|█████▋    | 14711/25880 [3:01:11<2:16:23,  1.36it/s]
1|14712|Loss: 0.7664201259613037:  57%|█████▋    | 14711/25880 [3:01:11<2:16:23,  1.36it/s]
1|14712|Loss: 0.7664201259613037:  57%|█████▋    | 14712/25880 [3:01:11<2:08:13,  1.45it/s]
1|14713|Loss: 0.9707100987434387:  57%|█████▋    | 14712/25880 [3:01:12<2:08:13,  1.45it/s]
1|14713|Loss: 0.9707100987434387:  57%|█████▋    | 14713/25880 [3:01:12<2:05:09,  1.49it/s]
1|14714|Loss: 0.6290363073348999:  57%|█████▋    | 14713/25880 [3:01:12<2:05:09,  1.49it/s]
1|14714|Loss: 0.6290363073348999:  57%|█████▋    | 14714/25880 [3:01:13<1:59:40,  1.56it/s]
1|14715|Loss: 0.7767114043235779:  57%|█████▋    | 14714/25880 [3:01:13<1:59:40,  1.56it/s]
1|14715|Loss: 0.7767114043235779:  57%|█████▋    | 14715/25880 [3:01:13<2:08:09,  1.45it/s]
1|14716|Loss: 0.9228554368019104:  57%|█████▋    | 14715/25880 [3:01:14<2:08:09,  1.45it/s]
1|14716|Loss: 0.9228554368019104:  57%|█████▋    | 14716/25880 [3:01:14<2:08:17,  1.45it/s]
1|14717|Loss: 0.8750455379486084:  57%|█████▋    | 14716/25880 [3:01:15<2:08:17,  1.45it/s]
1|14717|Loss: 0.8750455379486084:  57%|█████▋    | 14717/25880 [3:01:15<2:05:47,  1.48it/s]
1|14718|Loss: 0.9306769967079163:  57%|█████▋    | 14717/25880 [3:01:15<2:05:47,  1.48it/s]
1|14718|Loss: 0.9306769967079163:  57%|█████▋    | 14718/25880 [3:01:16<2:08:16,  1.45it/s]
1|14719|Loss: 0.8816224336624146:  57%|█████▋    | 14718/25880 [3:01:16<2:08:16,  1.45it/s]
1|14719|Loss: 0.8816224336624146:  57%|█████▋    | 14719/25880 [3:01:16<2:11:26,  1.42it/s]
1|14720|Loss: 0.88406902551651:  57%|█████▋    | 14719/25880 [3:01:17<2:11:26,  1.42it/s]  
1|14720|Loss: 0.88406902551651:  57%|█████▋    | 14720/25880 [3:01:17<2:07:55,  1.45it/s]
1|14721|Loss: 0.8648010492324829:  57%|█████▋    | 14720/25880 [3:01:17<2:07:55,  1.45it/s]
1|14721|Loss: 0.8648010492324829:  57%|█████▋    | 14721/25880 [3:01:18<2:07:29,  1.46it/s]
1|14722|Loss: 0.809181809425354:  57%|█████▋    | 14721/25880 [3:01:18<2:07:29,  1.46it/s] 
1|14722|Loss: 0.809181809425354:  57%|█████▋    | 14722/25880 [3:01:18<2:03:23,  1.51it/s]
1|14723|Loss: 0.7464549541473389:  57%|█████▋    | 14722/25880 [3:01:19<2:03:23,  1.51it/s]
1|14723|Loss: 0.7464549541473389:  57%|█████▋    | 14723/25880 [3:01:19<2:15:48,  1.37it/s]
1|14724|Loss: 0.8309730887413025:  57%|█████▋    | 14723/25880 [3:01:20<2:15:48,  1.37it/s]
1|14724|Loss: 0.8309730887413025:  57%|█████▋    | 14724/25880 [3:01:20<2:14:19,  1.38it/s]
1|14725|Loss: 0.8120234608650208:  57%|█████▋    | 14724/25880 [3:01:20<2:14:19,  1.38it/s]
1|14725|Loss: 0.8120234608650208:  57%|█████▋    | 14725/25880 [3:01:21<2:18:21,  1.34it/s]
1|14726|Loss: 0.6881439089775085:  57%|█████▋    | 14725/25880 [3:01:21<2:18:21,  1.34it/s]
1|14726|Loss: 0.6881439089775085:  57%|█████▋    | 14726/25880 [3:01:22<2:29:48,  1.24it/s]
1|14727|Loss: 0.7924489974975586:  57%|█████▋    | 14726/25880 [3:01:22<2:29:48,  1.24it/s]
1|14727|Loss: 0.7924489974975586:  57%|█████▋    | 14727/25880 [3:01:22<2:24:34,  1.29it/s]
1|14728|Loss: 0.8240322470664978:  57%|█████▋    | 14727/25880 [3:01:23<2:24:34,  1.29it/s]
1|14728|Loss: 0.8240322470664978:  57%|█████▋    | 14728/25880 [3:01:23<2:27:32,  1.26it/s]
1|14729|Loss: 0.9256480932235718:  57%|█████▋    | 14728/25880 [3:01:24<2:27:32,  1.26it/s]
1|14729|Loss: 0.9256480932235718:  57%|█████▋    | 14729/25880 [3:01:24<2:32:10,  1.22it/s]
1|14730|Loss: 0.9053741097450256:  57%|█████▋    | 14729/25880 [3:01:24<2:32:10,  1.22it/s]
1|14730|Loss: 0.9053741097450256:  57%|█████▋    | 14730/25880 [3:01:25<2:31:41,  1.23it/s]
1|14731|Loss: 0.7649884223937988:  57%|█████▋    | 14730/25880 [3:01:25<2:31:41,  1.23it/s]
1|14731|Loss: 0.7649884223937988:  57%|█████▋    | 14731/25880 [3:01:26<2:35:58,  1.19it/s]
1|14732|Loss: 0.7273511290550232:  57%|█████▋    | 14731/25880 [3:01:26<2:35:58,  1.19it/s]
1|14732|Loss: 0.7273511290550232:  57%|█████▋    | 14732/25880 [3:01:27<2:36:22,  1.19it/s]
1|14733|Loss: 0.8535483479499817:  57%|█████▋    | 14732/25880 [3:01:27<2:36:22,  1.19it/s]
1|14733|Loss: 0.8535483479499817:  57%|█████▋    | 14733/25880 [3:01:27<2:26:02,  1.27it/s]
1|14734|Loss: 0.7888162136077881:  57%|█████▋    | 14733/25880 [3:01:28<2:26:02,  1.27it/s]
1|14734|Loss: 0.7888162136077881:  57%|█████▋    | 14734/25880 [3:01:28<2:27:51,  1.26it/s]
1|14735|Loss: 0.8678343892097473:  57%|█████▋    | 14734/25880 [3:01:28<2:27:51,  1.26it/s]
1|14735|Loss: 0.8678343892097473:  57%|█████▋    | 14735/25880 [3:01:29<2:29:11,  1.25it/s]
1|14736|Loss: 1.0404340028762817:  57%|█████▋    | 14735/25880 [3:01:29<2:29:11,  1.25it/s]
1|14736|Loss: 1.0404340028762817:  57%|█████▋    | 14736/25880 [3:01:30<2:24:33,  1.28it/s]
1|14737|Loss: 0.951600193977356:  57%|█████▋    | 14736/25880 [3:01:30<2:24:33,  1.28it/s] 
1|14737|Loss: 0.951600193977356:  57%|█████▋    | 14737/25880 [3:01:30<2:20:12,  1.32it/s]
1|14738|Loss: 0.9014281034469604:  57%|█████▋    | 14737/25880 [3:01:31<2:20:12,  1.32it/s]
1|14738|Loss: 0.9014281034469604:  57%|█████▋    | 14738/25880 [3:01:31<2:20:54,  1.32it/s]
1|14739|Loss: 0.9562146663665771:  57%|█████▋    | 14738/25880 [3:01:31<2:20:54,  1.32it/s]
1|14739|Loss: 0.9562146663665771:  57%|█████▋    | 14739/25880 [3:01:32<2:30:07,  1.24it/s]
1|14740|Loss: 0.7998496890068054:  57%|█████▋    | 14739/25880 [3:01:32<2:30:07,  1.24it/s]
1|14740|Loss: 0.7998496890068054:  57%|█████▋    | 14740/25880 [3:01:33<2:31:34,  1.22it/s]
1|14741|Loss: 0.8841645121574402:  57%|█████▋    | 14740/25880 [3:01:33<2:31:34,  1.22it/s]
1|14741|Loss: 0.8841645121574402:  57%|█████▋    | 14741/25880 [3:01:33<2:26:10,  1.27it/s]
1|14742|Loss: 0.7661753296852112:  57%|█████▋    | 14741/25880 [3:01:34<2:26:10,  1.27it/s]
1|14742|Loss: 0.7661753296852112:  57%|█████▋    | 14742/25880 [3:01:34<2:15:46,  1.37it/s]
1|14743|Loss: 0.9977431297302246:  57%|█████▋    | 14742/25880 [3:01:34<2:15:46,  1.37it/s]
1|14743|Loss: 0.9977431297302246:  57%|█████▋    | 14743/25880 [3:01:35<2:14:33,  1.38it/s]
1|14744|Loss: 0.8131505846977234:  57%|█████▋    | 14743/25880 [3:01:35<2:14:33,  1.38it/s]
1|14744|Loss: 0.8131505846977234:  57%|█████▋    | 14744/25880 [3:01:36<2:19:42,  1.33it/s]
1|14745|Loss: 0.809636116027832:  57%|█████▋    | 14744/25880 [3:01:36<2:19:42,  1.33it/s] 
1|14745|Loss: 0.809636116027832:  57%|█████▋    | 14745/25880 [3:01:36<2:18:16,  1.34it/s]
1|14746|Loss: 0.9152837991714478:  57%|█████▋    | 14745/25880 [3:01:37<2:18:16,  1.34it/s]
1|14746|Loss: 0.9152837991714478:  57%|█████▋    | 14746/25880 [3:01:37<2:11:53,  1.41it/s]
1|14747|Loss: 0.8452387452125549:  57%|█████▋    | 14746/25880 [3:01:37<2:11:53,  1.41it/s]
1|14747|Loss: 0.8452387452125549:  57%|█████▋    | 14747/25880 [3:01:38<2:10:17,  1.42it/s]
1|14748|Loss: 0.7557689547538757:  57%|█████▋    | 14747/25880 [3:01:38<2:10:17,  1.42it/s]
1|14748|Loss: 0.7557689547538757:  57%|█████▋    | 14748/25880 [3:01:38<2:14:19,  1.38it/s]
1|14749|Loss: 0.8605474829673767:  57%|█████▋    | 14748/25880 [3:01:39<2:14:19,  1.38it/s]
1|14749|Loss: 0.8605474829673767:  57%|█████▋    | 14749/25880 [3:01:39<2:11:34,  1.41it/s]
1|14750|Loss: 0.8286212682723999:  57%|█████▋    | 14749/25880 [3:01:40<2:11:34,  1.41it/s]
1|14750|Loss: 0.8286212682723999:  57%|█████▋    | 14750/25880 [3:01:40<2:20:07,  1.32it/s]
1|14751|Loss: 0.933928906917572:  57%|█████▋    | 14750/25880 [3:01:40<2:20:07,  1.32it/s] 
1|14751|Loss: 0.933928906917572:  57%|█████▋    | 14751/25880 [3:01:41<2:23:55,  1.29it/s]
1|14752|Loss: 0.9094976782798767:  57%|█████▋    | 14751/25880 [3:01:41<2:23:55,  1.29it/s]
1|14752|Loss: 0.9094976782798767:  57%|█████▋    | 14752/25880 [3:01:41<2:18:24,  1.34it/s]
1|14753|Loss: 0.7799151539802551:  57%|█████▋    | 14752/25880 [3:01:42<2:18:24,  1.34it/s]
1|14753|Loss: 0.7799151539802551:  57%|█████▋    | 14753/25880 [3:01:42<2:15:32,  1.37it/s]
1|14754|Loss: 0.7209318280220032:  57%|█████▋    | 14753/25880 [3:01:43<2:15:32,  1.37it/s]
1|14754|Loss: 0.7209318280220032:  57%|█████▋    | 14754/25880 [3:01:43<2:14:59,  1.37it/s]
1|14755|Loss: 0.9213897585868835:  57%|█████▋    | 14754/25880 [3:01:43<2:14:59,  1.37it/s]
1|14755|Loss: 0.9213897585868835:  57%|█████▋    | 14755/25880 [3:01:44<2:15:43,  1.37it/s]
1|14756|Loss: 0.8667989373207092:  57%|█████▋    | 14755/25880 [3:01:44<2:15:43,  1.37it/s]
1|14756|Loss: 0.8667989373207092:  57%|█████▋    | 14756/25880 [3:01:44<2:14:33,  1.38it/s]
1|14757|Loss: 0.8845759630203247:  57%|█████▋    | 14756/25880 [3:01:45<2:14:33,  1.38it/s]
1|14757|Loss: 0.8845759630203247:  57%|█████▋    | 14757/25880 [3:01:45<2:24:25,  1.28it/s]
1|14758|Loss: 0.88242107629776:  57%|█████▋    | 14757/25880 [3:01:46<2:24:25,  1.28it/s]  
1|14758|Loss: 0.88242107629776:  57%|█████▋    | 14758/25880 [3:01:46<2:11:54,  1.41it/s]
1|14759|Loss: 0.8521252274513245:  57%|█████▋    | 14758/25880 [3:01:46<2:11:54,  1.41it/s]
1|14759|Loss: 0.8521252274513245:  57%|█████▋    | 14759/25880 [3:01:46<2:09:32,  1.43it/s]
1|14760|Loss: 0.8797661662101746:  57%|█████▋    | 14759/25880 [3:01:47<2:09:32,  1.43it/s]
1|14760|Loss: 0.8797661662101746:  57%|█████▋    | 14760/25880 [3:01:47<2:06:05,  1.47it/s]
1|14761|Loss: 0.8147321939468384:  57%|█████▋    | 14760/25880 [3:01:48<2:06:05,  1.47it/s]
1|14761|Loss: 0.8147321939468384:  57%|█████▋    | 14761/25880 [3:01:48<2:15:39,  1.37it/s]
1|14762|Loss: 0.8531661033630371:  57%|█████▋    | 14761/25880 [3:01:48<2:15:39,  1.37it/s]
1|14762|Loss: 0.8531661033630371:  57%|█████▋    | 14762/25880 [3:01:49<2:16:06,  1.36it/s]
1|14763|Loss: 0.9032873511314392:  57%|█████▋    | 14762/25880 [3:01:49<2:16:06,  1.36it/s]
1|14763|Loss: 0.9032873511314392:  57%|█████▋    | 14763/25880 [3:01:49<2:20:01,  1.32it/s]
1|14764|Loss: 0.8375124335289001:  57%|█████▋    | 14763/25880 [3:01:50<2:20:01,  1.32it/s]
1|14764|Loss: 0.8375124335289001:  57%|█████▋    | 14764/25880 [3:01:50<2:25:10,  1.28it/s]
1|14765|Loss: 0.9578071236610413:  57%|█████▋    | 14764/25880 [3:01:51<2:25:10,  1.28it/s]
1|14765|Loss: 0.9578071236610413:  57%|█████▋    | 14765/25880 [3:01:51<2:30:30,  1.23it/s]
1|14766|Loss: 0.7536079287528992:  57%|█████▋    | 14765/25880 [3:01:52<2:30:30,  1.23it/s]
1|14766|Loss: 0.7536079287528992:  57%|█████▋    | 14766/25880 [3:01:52<2:28:15,  1.25it/s]
1|14767|Loss: 0.923935055732727:  57%|█████▋    | 14766/25880 [3:01:52<2:28:15,  1.25it/s] 
1|14767|Loss: 0.923935055732727:  57%|█████▋    | 14767/25880 [3:01:53<2:18:39,  1.34it/s]
1|14768|Loss: 0.7901920080184937:  57%|█████▋    | 14767/25880 [3:01:53<2:18:39,  1.34it/s]
1|14768|Loss: 0.7901920080184937:  57%|█████▋    | 14768/25880 [3:01:53<2:16:09,  1.36it/s]
1|14769|Loss: 0.7228744029998779:  57%|█████▋    | 14768/25880 [3:01:54<2:16:09,  1.36it/s]
1|14769|Loss: 0.7228744029998779:  57%|█████▋    | 14769/25880 [3:01:54<2:21:13,  1.31it/s]
1|14770|Loss: 0.9027414917945862:  57%|█████▋    | 14769/25880 [3:01:55<2:21:13,  1.31it/s]
1|14770|Loss: 0.9027414917945862:  57%|█████▋    | 14770/25880 [3:01:55<2:12:01,  1.40it/s]
1|14771|Loss: 0.8975123763084412:  57%|█████▋    | 14770/25880 [3:01:55<2:12:01,  1.40it/s]
1|14771|Loss: 0.8975123763084412:  57%|█████▋    | 14771/25880 [3:01:55<2:09:08,  1.43it/s]
1|14772|Loss: 0.7615364193916321:  57%|█████▋    | 14771/25880 [3:01:56<2:09:08,  1.43it/s]
1|14772|Loss: 0.7615364193916321:  57%|█████▋    | 14772/25880 [3:01:56<2:16:44,  1.35it/s]
1|14773|Loss: 0.9418219923973083:  57%|█████▋    | 14772/25880 [3:01:57<2:16:44,  1.35it/s]
1|14773|Loss: 0.9418219923973083:  57%|█████▋    | 14773/25880 [3:01:57<2:13:42,  1.38it/s]
1|14774|Loss: 0.8619117140769958:  57%|█████▋    | 14773/25880 [3:01:57<2:13:42,  1.38it/s]
1|14774|Loss: 0.8619117140769958:  57%|█████▋    | 14774/25880 [3:01:58<2:17:39,  1.34it/s]
1|14775|Loss: 0.8305709362030029:  57%|█████▋    | 14774/25880 [3:01:58<2:17:39,  1.34it/s]
1|14775|Loss: 0.8305709362030029:  57%|█████▋    | 14775/25880 [3:01:58<2:18:33,  1.34it/s]
1|14776|Loss: 0.816349446773529:  57%|█████▋    | 14775/25880 [3:01:59<2:18:33,  1.34it/s] 
1|14776|Loss: 0.816349446773529:  57%|█████▋    | 14776/25880 [3:01:59<2:28:21,  1.25it/s]
1|14777|Loss: 0.9080332517623901:  57%|█████▋    | 14776/25880 [3:02:00<2:28:21,  1.25it/s]
1|14777|Loss: 0.9080332517623901:  57%|█████▋    | 14777/25880 [3:02:00<2:21:30,  1.31it/s]
1|14778|Loss: 0.9054579138755798:  57%|█████▋    | 14777/25880 [3:02:00<2:21:30,  1.31it/s]
1|14778|Loss: 0.9054579138755798:  57%|█████▋    | 14778/25880 [3:02:01<2:05:40,  1.47it/s]
1|14779|Loss: 0.8183758854866028:  57%|█████▋    | 14778/25880 [3:02:01<2:05:40,  1.47it/s]
1|14779|Loss: 0.8183758854866028:  57%|█████▋    | 14779/25880 [3:02:01<2:10:37,  1.42it/s]
1|14780|Loss: 0.8316417932510376:  57%|█████▋    | 14779/25880 [3:02:02<2:10:37,  1.42it/s]
1|14780|Loss: 0.8316417932510376:  57%|█████▋    | 14780/25880 [3:02:02<2:06:58,  1.46it/s]
1|14781|Loss: 1.0482450723648071:  57%|█████▋    | 14780/25880 [3:02:02<2:06:58,  1.46it/s]
1|14781|Loss: 1.0482450723648071:  57%|█████▋    | 14781/25880 [3:02:03<2:07:47,  1.45it/s]
1|14782|Loss: 0.8937785029411316:  57%|█████▋    | 14781/25880 [3:02:03<2:07:47,  1.45it/s]
1|14782|Loss: 0.8937785029411316:  57%|█████▋    | 14782/25880 [3:02:03<2:09:39,  1.43it/s]
1|14783|Loss: 0.8301377296447754:  57%|█████▋    | 14782/25880 [3:02:04<2:09:39,  1.43it/s]
1|14783|Loss: 0.8301377296447754:  57%|█████▋    | 14783/25880 [3:02:04<2:15:23,  1.37it/s]
1|14784|Loss: 1.0110853910446167:  57%|█████▋    | 14783/25880 [3:02:05<2:15:23,  1.37it/s]
1|14784|Loss: 1.0110853910446167:  57%|█████▋    | 14784/25880 [3:02:05<2:08:14,  1.44it/s]
1|14785|Loss: 0.8416783809661865:  57%|█████▋    | 14784/25880 [3:02:05<2:08:14,  1.44it/s]
1|14785|Loss: 0.8416783809661865:  57%|█████▋    | 14785/25880 [3:02:05<1:55:57,  1.59it/s]
1|14786|Loss: 0.924762487411499:  57%|█████▋    | 14785/25880 [3:02:06<1:55:57,  1.59it/s] 
1|14786|Loss: 0.924762487411499:  57%|█████▋    | 14786/25880 [3:02:06<2:04:54,  1.48it/s]
1|14787|Loss: 0.8698029518127441:  57%|█████▋    | 14786/25880 [3:02:06<2:04:54,  1.48it/s]
1|14787|Loss: 0.8698029518127441:  57%|█████▋    | 14787/25880 [3:02:07<2:09:50,  1.42it/s]
1|14788|Loss: 0.943612813949585:  57%|█████▋    | 14787/25880 [3:02:07<2:09:50,  1.42it/s] 
1|14788|Loss: 0.943612813949585:  57%|█████▋    | 14788/25880 [3:02:07<2:07:26,  1.45it/s]
1|14789|Loss: 0.846434473991394:  57%|█████▋    | 14788/25880 [3:02:08<2:07:26,  1.45it/s]
1|14789|Loss: 0.846434473991394:  57%|█████▋    | 14789/25880 [3:02:08<1:59:51,  1.54it/s]
1|14790|Loss: 0.8529722690582275:  57%|█████▋    | 14789/25880 [3:02:08<1:59:51,  1.54it/s]
1|14790|Loss: 0.8529722690582275:  57%|█████▋    | 14790/25880 [3:02:09<2:05:31,  1.47it/s]
1|14791|Loss: 0.8417885303497314:  57%|█████▋    | 14790/25880 [3:02:09<2:05:31,  1.47it/s]
1|14791|Loss: 0.8417885303497314:  57%|█████▋    | 14791/25880 [3:02:10<2:09:03,  1.43it/s]
1|14792|Loss: 0.7381607890129089:  57%|█████▋    | 14791/25880 [3:02:10<2:09:03,  1.43it/s]
1|14792|Loss: 0.7381607890129089:  57%|█████▋    | 14792/25880 [3:02:10<2:13:46,  1.38it/s]
1|14793|Loss: 0.7891144752502441:  57%|█████▋    | 14792/25880 [3:02:11<2:13:46,  1.38it/s]
1|14793|Loss: 0.7891144752502441:  57%|█████▋    | 14793/25880 [3:02:11<2:14:33,  1.37it/s]
1|14794|Loss: 0.7196503281593323:  57%|█████▋    | 14793/25880 [3:02:11<2:14:33,  1.37it/s]
1|14794|Loss: 0.7196503281593323:  57%|█████▋    | 14794/25880 [3:02:12<2:19:59,  1.32it/s]
1|14795|Loss: 0.7308334708213806:  57%|█████▋    | 14794/25880 [3:02:12<2:19:59,  1.32it/s]
1|14795|Loss: 0.7308334708213806:  57%|█████▋    | 14795/25880 [3:02:13<2:16:10,  1.36it/s]
1|14796|Loss: 0.9638373255729675:  57%|█████▋    | 14795/25880 [3:02:13<2:16:10,  1.36it/s]
1|14796|Loss: 0.9638373255729675:  57%|█████▋    | 14796/25880 [3:02:13<2:13:16,  1.39it/s]
1|14797|Loss: 0.9079699516296387:  57%|█████▋    | 14796/25880 [3:02:14<2:13:16,  1.39it/s]
1|14797|Loss: 0.9079699516296387:  57%|█████▋    | 14797/25880 [3:02:14<2:11:56,  1.40it/s]
1|14798|Loss: 0.8668550848960876:  57%|█████▋    | 14797/25880 [3:02:14<2:11:56,  1.40it/s]
1|14798|Loss: 0.8668550848960876:  57%|█████▋    | 14798/25880 [3:02:15<2:16:43,  1.35it/s]
1|14799|Loss: 0.8496832847595215:  57%|█████▋    | 14798/25880 [3:02:15<2:16:43,  1.35it/s]
1|14799|Loss: 0.8496832847595215:  57%|█████▋    | 14799/25880 [3:02:16<2:23:13,  1.29it/s]
1|14800|Loss: 0.8850712180137634:  57%|█████▋    | 14799/25880 [3:02:16<2:23:13,  1.29it/s]
1|14800|Loss: 0.8850712180137634:  57%|█████▋    | 14800/25880 [3:02:16<2:24:40,  1.28it/s]
1|14801|Loss: 0.9300756454467773:  57%|█████▋    | 14800/25880 [3:02:17<2:24:40,  1.28it/s]
1|14801|Loss: 0.9300756454467773:  57%|█████▋    | 14801/25880 [3:02:17<2:21:09,  1.31it/s]
1|14802|Loss: 0.7804710865020752:  57%|█████▋    | 14801/25880 [3:02:18<2:21:09,  1.31it/s]
1|14802|Loss: 0.7804710865020752:  57%|█████▋    | 14802/25880 [3:02:18<2:21:16,  1.31it/s]
1|14803|Loss: 0.8537066578865051:  57%|█████▋    | 14802/25880 [3:02:18<2:21:16,  1.31it/s]
1|14803|Loss: 0.8537066578865051:  57%|█████▋    | 14803/25880 [3:02:19<2:18:40,  1.33it/s]
1|14804|Loss: 0.7842954993247986:  57%|█████▋    | 14803/25880 [3:02:19<2:18:40,  1.33it/s]
1|14804|Loss: 0.7842954993247986:  57%|█████▋    | 14804/25880 [3:02:19<2:25:14,  1.27it/s]
1|14805|Loss: 0.7885606288909912:  57%|█████▋    | 14804/25880 [3:02:20<2:25:14,  1.27it/s]
1|14805|Loss: 0.7885606288909912:  57%|█████▋    | 14805/25880 [3:02:20<2:19:13,  1.33it/s]
1|14806|Loss: 0.8346205353736877:  57%|█████▋    | 14805/25880 [3:02:21<2:19:13,  1.33it/s]
1|14806|Loss: 0.8346205353736877:  57%|█████▋    | 14806/25880 [3:02:21<2:17:28,  1.34it/s]
1|14807|Loss: 0.791100263595581:  57%|█████▋    | 14806/25880 [3:02:21<2:17:28,  1.34it/s] 
1|14807|Loss: 0.791100263595581:  57%|█████▋    | 14807/25880 [3:02:22<2:12:12,  1.40it/s]
1|14808|Loss: 0.7730101943016052:  57%|█████▋    | 14807/25880 [3:02:22<2:12:12,  1.40it/s]
1|14808|Loss: 0.7730101943016052:  57%|█████▋    | 14808/25880 [3:02:22<2:11:35,  1.40it/s]
1|14809|Loss: 0.8192103505134583:  57%|█████▋    | 14808/25880 [3:02:23<2:11:35,  1.40it/s]
1|14809|Loss: 0.8192103505134583:  57%|█████▋    | 14809/25880 [3:02:23<2:12:53,  1.39it/s]
1|14810|Loss: 0.7283562421798706:  57%|█████▋    | 14809/25880 [3:02:23<2:12:53,  1.39it/s]
1|14810|Loss: 0.7283562421798706:  57%|█████▋    | 14810/25880 [3:02:24<2:16:26,  1.35it/s]
1|14811|Loss: 0.8222032189369202:  57%|█████▋    | 14810/25880 [3:02:24<2:16:26,  1.35it/s]
1|14811|Loss: 0.8222032189369202:  57%|█████▋    | 14811/25880 [3:02:24<2:06:10,  1.46it/s]
1|14812|Loss: 0.700044572353363:  57%|█████▋    | 14811/25880 [3:02:25<2:06:10,  1.46it/s] 
1|14812|Loss: 0.700044572353363:  57%|█████▋    | 14812/25880 [3:02:25<2:12:17,  1.39it/s]
1|14813|Loss: 1.0245041847229004:  57%|█████▋    | 14812/25880 [3:02:26<2:12:17,  1.39it/s]
1|14813|Loss: 1.0245041847229004:  57%|█████▋    | 14813/25880 [3:02:26<2:08:38,  1.43it/s]
1|14814|Loss: 0.8072331547737122:  57%|█████▋    | 14813/25880 [3:02:26<2:08:38,  1.43it/s]
1|14814|Loss: 0.8072331547737122:  57%|█████▋    | 14814/25880 [3:02:26<2:02:21,  1.51it/s]
1|14815|Loss: 0.8800076842308044:  57%|█████▋    | 14814/25880 [3:02:27<2:02:21,  1.51it/s]
1|14815|Loss: 0.8800076842308044:  57%|█████▋    | 14815/25880 [3:02:27<2:07:38,  1.44it/s]
1|14816|Loss: 0.7504830956459045:  57%|█████▋    | 14815/25880 [3:02:27<2:07:38,  1.44it/s]
1|14816|Loss: 0.7504830956459045:  57%|█████▋    | 14816/25880 [3:02:28<2:06:38,  1.46it/s]
1|14817|Loss: 0.9387617707252502:  57%|█████▋    | 14816/25880 [3:02:28<2:06:38,  1.46it/s]
1|14817|Loss: 0.9387617707252502:  57%|█████▋    | 14817/25880 [3:02:29<2:08:51,  1.43it/s]
1|14818|Loss: 0.8939433693885803:  57%|█████▋    | 14817/25880 [3:02:29<2:08:51,  1.43it/s]
1|14818|Loss: 0.8939433693885803:  57%|█████▋    | 14818/25880 [3:02:29<2:10:03,  1.42it/s]
1|14819|Loss: 0.7114078998565674:  57%|█████▋    | 14818/25880 [3:02:30<2:10:03,  1.42it/s]
1|14819|Loss: 0.7114078998565674:  57%|█████▋    | 14819/25880 [3:02:30<2:16:15,  1.35it/s]
1|14820|Loss: 0.777837872505188:  57%|█████▋    | 14819/25880 [3:02:30<2:16:15,  1.35it/s] 
1|14820|Loss: 0.777837872505188:  57%|█████▋    | 14820/25880 [3:02:31<2:18:18,  1.33it/s]
1|14821|Loss: 0.8300637602806091:  57%|█████▋    | 14820/25880 [3:02:31<2:18:18,  1.33it/s]
1|14821|Loss: 0.8300637602806091:  57%|█████▋    | 14821/25880 [3:02:32<2:18:06,  1.33it/s]
1|14822|Loss: 0.7981677055358887:  57%|█████▋    | 14821/25880 [3:02:32<2:18:06,  1.33it/s]
1|14822|Loss: 0.7981677055358887:  57%|█████▋    | 14822/25880 [3:02:32<2:19:57,  1.32it/s]
1|14823|Loss: 0.9118267297744751:  57%|█████▋    | 14822/25880 [3:02:33<2:19:57,  1.32it/s]
1|14823|Loss: 0.9118267297744751:  57%|█████▋    | 14823/25880 [3:02:33<2:23:32,  1.28it/s]
1|14824|Loss: 0.9678608775138855:  57%|█████▋    | 14823/25880 [3:02:34<2:23:32,  1.28it/s]
1|14824|Loss: 0.9678608775138855:  57%|█████▋    | 14824/25880 [3:02:34<2:26:28,  1.26it/s]
1|14825|Loss: 0.8704627752304077:  57%|█████▋    | 14824/25880 [3:02:34<2:26:28,  1.26it/s]
1|14825|Loss: 0.8704627752304077:  57%|█████▋    | 14825/25880 [3:02:35<2:23:55,  1.28it/s]
1|14826|Loss: 0.7691890597343445:  57%|█████▋    | 14825/25880 [3:02:35<2:23:55,  1.28it/s]
1|14826|Loss: 0.7691890597343445:  57%|█████▋    | 14826/25880 [3:02:35<2:10:13,  1.41it/s]
1|14827|Loss: 0.8883699178695679:  57%|█████▋    | 14826/25880 [3:02:36<2:10:13,  1.41it/s]
1|14827|Loss: 0.8883699178695679:  57%|█████▋    | 14827/25880 [3:02:36<2:07:25,  1.45it/s]
1|14828|Loss: 0.7602085471153259:  57%|█████▋    | 14827/25880 [3:02:36<2:07:25,  1.45it/s]
1|14828|Loss: 0.7602085471153259:  57%|█████▋    | 14828/25880 [3:02:37<2:04:43,  1.48it/s]
1|14829|Loss: 1.0275490283966064:  57%|█████▋    | 14828/25880 [3:02:37<2:04:43,  1.48it/s]
1|14829|Loss: 1.0275490283966064:  57%|█████▋    | 14829/25880 [3:02:37<2:05:38,  1.47it/s]
1|14830|Loss: 0.7266491651535034:  57%|█████▋    | 14829/25880 [3:02:38<2:05:38,  1.47it/s]
1|14830|Loss: 0.7266491651535034:  57%|█████▋    | 14830/25880 [3:02:38<2:06:57,  1.45it/s]
1|14831|Loss: 0.8551337718963623:  57%|█████▋    | 14830/25880 [3:02:38<2:06:57,  1.45it/s]
1|14831|Loss: 0.8551337718963623:  57%|█████▋    | 14831/25880 [3:02:39<2:12:22,  1.39it/s]
1|14832|Loss: 0.9693020582199097:  57%|█████▋    | 14831/25880 [3:02:39<2:12:22,  1.39it/s]
1|14832|Loss: 0.9693020582199097:  57%|█████▋    | 14832/25880 [3:02:40<2:23:55,  1.28it/s]
1|14833|Loss: 0.8859975934028625:  57%|█████▋    | 14832/25880 [3:02:40<2:23:55,  1.28it/s]
1|14833|Loss: 0.8859975934028625:  57%|█████▋    | 14833/25880 [3:02:40<2:23:43,  1.28it/s]
1|14834|Loss: 0.8910021781921387:  57%|█████▋    | 14833/25880 [3:02:41<2:23:43,  1.28it/s]
1|14834|Loss: 0.8910021781921387:  57%|█████▋    | 14834/25880 [3:02:41<2:13:00,  1.38it/s]
1|14835|Loss: 0.7825452089309692:  57%|█████▋    | 14834/25880 [3:02:41<2:13:00,  1.38it/s]
1|14835|Loss: 0.7825452089309692:  57%|█████▋    | 14835/25880 [3:02:42<2:12:32,  1.39it/s]
1|14836|Loss: 0.8697167038917542:  57%|█████▋    | 14835/25880 [3:02:42<2:12:32,  1.39it/s]
1|14836|Loss: 0.8697167038917542:  57%|█████▋    | 14836/25880 [3:02:43<2:18:49,  1.33it/s]
1|14837|Loss: 0.7799810171127319:  57%|█████▋    | 14836/25880 [3:02:43<2:18:49,  1.33it/s]
1|14837|Loss: 0.7799810171127319:  57%|█████▋    | 14837/25880 [3:02:44<2:27:23,  1.25it/s]
1|14838|Loss: 0.8865789175033569:  57%|█████▋    | 14837/25880 [3:02:44<2:27:23,  1.25it/s]
1|14838|Loss: 0.8865789175033569:  57%|█████▋    | 14838/25880 [3:02:44<2:19:39,  1.32it/s]
1|14839|Loss: 0.8392733931541443:  57%|█████▋    | 14838/25880 [3:02:45<2:19:39,  1.32it/s]
1|14839|Loss: 0.8392733931541443:  57%|█████▋    | 14839/25880 [3:02:45<2:22:16,  1.29it/s]
1|14840|Loss: 0.92633455991745:  57%|█████▋    | 14839/25880 [3:02:45<2:22:16,  1.29it/s]  
1|14840|Loss: 0.92633455991745:  57%|█████▋    | 14840/25880 [3:02:46<2:16:36,  1.35it/s]
1|14841|Loss: 0.7818531394004822:  57%|█████▋    | 14840/25880 [3:02:46<2:16:36,  1.35it/s]
1|14841|Loss: 0.7818531394004822:  57%|█████▋    | 14841/25880 [3:02:46<2:14:59,  1.36it/s]
1|14842|Loss: 0.9356449842453003:  57%|█████▋    | 14841/25880 [3:02:47<2:14:59,  1.36it/s]
1|14842|Loss: 0.9356449842453003:  57%|█████▋    | 14842/25880 [3:02:47<2:08:16,  1.43it/s]
1|14843|Loss: 0.7186940908432007:  57%|█████▋    | 14842/25880 [3:02:47<2:08:16,  1.43it/s]
1|14843|Loss: 0.7186940908432007:  57%|█████▋    | 14843/25880 [3:02:48<2:04:13,  1.48it/s]
1|14844|Loss: 0.8219947218894958:  57%|█████▋    | 14843/25880 [3:02:48<2:04:13,  1.48it/s]
1|14844|Loss: 0.8219947218894958:  57%|█████▋    | 14844/25880 [3:02:48<2:05:07,  1.47it/s]
1|14845|Loss: 0.7489575147628784:  57%|█████▋    | 14844/25880 [3:02:49<2:05:07,  1.47it/s]
1|14845|Loss: 0.7489575147628784:  57%|█████▋    | 14845/25880 [3:02:49<2:03:14,  1.49it/s]
1|14846|Loss: 1.0458217859268188:  57%|█████▋    | 14845/25880 [3:02:49<2:03:14,  1.49it/s]
1|14846|Loss: 1.0458217859268188:  57%|█████▋    | 14846/25880 [3:02:50<2:08:40,  1.43it/s]
1|14847|Loss: 0.9308164119720459:  57%|█████▋    | 14846/25880 [3:02:50<2:08:40,  1.43it/s]
1|14847|Loss: 0.9308164119720459:  57%|█████▋    | 14847/25880 [3:02:51<2:16:19,  1.35it/s]
1|14848|Loss: 0.7370355725288391:  57%|█████▋    | 14847/25880 [3:02:51<2:16:19,  1.35it/s]
1|14848|Loss: 0.7370355725288391:  57%|█████▋    | 14848/25880 [3:02:51<2:23:05,  1.28it/s]
1|14849|Loss: 0.8111252188682556:  57%|█████▋    | 14848/25880 [3:02:52<2:23:05,  1.28it/s]
1|14849|Loss: 0.8111252188682556:  57%|█████▋    | 14849/25880 [3:02:52<2:22:16,  1.29it/s]
1|14850|Loss: 0.774670422077179:  57%|█████▋    | 14849/25880 [3:02:53<2:22:16,  1.29it/s] 
1|14850|Loss: 0.774670422077179:  57%|█████▋    | 14850/25880 [3:02:53<2:28:16,  1.24it/s]
1|14851|Loss: 0.8951190710067749:  57%|█████▋    | 14850/25880 [3:02:54<2:28:16,  1.24it/s]
1|14851|Loss: 0.8951190710067749:  57%|█████▋    | 14851/25880 [3:02:54<2:26:00,  1.26it/s]
1|14852|Loss: 0.8699723482131958:  57%|█████▋    | 14851/25880 [3:02:54<2:26:00,  1.26it/s]
1|14852|Loss: 0.8699723482131958:  57%|█████▋    | 14852/25880 [3:02:55<2:22:22,  1.29it/s]
1|14853|Loss: 0.8371542692184448:  57%|█████▋    | 14852/25880 [3:02:55<2:22:22,  1.29it/s]
1|14853|Loss: 0.8371542692184448:  57%|█████▋    | 14853/25880 [3:02:55<2:14:38,  1.36it/s]
1|14854|Loss: 0.8546752333641052:  57%|█████▋    | 14853/25880 [3:02:56<2:14:38,  1.36it/s]
1|14854|Loss: 0.8546752333641052:  57%|█████▋    | 14854/25880 [3:02:56<2:09:08,  1.42it/s]
1|14855|Loss: 0.8404790163040161:  57%|█████▋    | 14854/25880 [3:02:56<2:09:08,  1.42it/s]
1|14855|Loss: 0.8404790163040161:  57%|█████▋    | 14855/25880 [3:02:57<2:09:42,  1.42it/s]
1|14856|Loss: 0.8021689653396606:  57%|█████▋    | 14855/25880 [3:02:57<2:09:42,  1.42it/s]
1|14856|Loss: 0.8021689653396606:  57%|█████▋    | 14856/25880 [3:02:57<2:17:46,  1.33it/s]
1|14857|Loss: 0.6724023222923279:  57%|█████▋    | 14856/25880 [3:02:58<2:17:46,  1.33it/s]
1|14857|Loss: 0.6724023222923279:  57%|█████▋    | 14857/25880 [3:02:58<2:31:48,  1.21it/s]
1|14858|Loss: 0.8520041704177856:  57%|█████▋    | 14857/25880 [3:02:59<2:31:48,  1.21it/s]
1|14858|Loss: 0.8520041704177856:  57%|█████▋    | 14858/25880 [3:02:59<2:28:54,  1.23it/s]
1|14859|Loss: 0.8787172436714172:  57%|█████▋    | 14858/25880 [3:03:00<2:28:54,  1.23it/s]
1|14859|Loss: 0.8787172436714172:  57%|█████▋    | 14859/25880 [3:03:00<2:24:06,  1.27it/s]
1|14860|Loss: 0.796127438545227:  57%|█████▋    | 14859/25880 [3:03:00<2:24:06,  1.27it/s] 
1|14860|Loss: 0.796127438545227:  57%|█████▋    | 14860/25880 [3:03:01<2:23:31,  1.28it/s]
1|14861|Loss: 0.9116430878639221:  57%|█████▋    | 14860/25880 [3:03:01<2:23:31,  1.28it/s]
1|14861|Loss: 0.9116430878639221:  57%|█████▋    | 14861/25880 [3:03:02<2:26:16,  1.26it/s]
1|14862|Loss: 0.8506971001625061:  57%|█████▋    | 14861/25880 [3:03:02<2:26:16,  1.26it/s]
1|14862|Loss: 0.8506971001625061:  57%|█████▋    | 14862/25880 [3:03:02<2:24:44,  1.27it/s]
1|14863|Loss: 0.8866657018661499:  57%|█████▋    | 14862/25880 [3:03:03<2:24:44,  1.27it/s]
1|14863|Loss: 0.8866657018661499:  57%|█████▋    | 14863/25880 [3:03:03<2:22:25,  1.29it/s]
1|14864|Loss: 0.7371203899383545:  57%|█████▋    | 14863/25880 [3:03:03<2:22:25,  1.29it/s]
1|14864|Loss: 0.7371203899383545:  57%|█████▋    | 14864/25880 [3:03:04<2:12:27,  1.39it/s]
1|14865|Loss: 0.7831065654754639:  57%|█████▋    | 14864/25880 [3:03:04<2:12:27,  1.39it/s]
1|14865|Loss: 0.7831065654754639:  57%|█████▋    | 14865/25880 [3:03:04<2:10:46,  1.40it/s]
1|14866|Loss: 0.8621439933776855:  57%|█████▋    | 14865/25880 [3:03:05<2:10:46,  1.40it/s]
1|14866|Loss: 0.8621439933776855:  57%|█████▋    | 14866/25880 [3:03:05<2:06:30,  1.45it/s]
1|14867|Loss: 0.7613273859024048:  57%|█████▋    | 14866/25880 [3:03:05<2:06:30,  1.45it/s]
1|14867|Loss: 0.7613273859024048:  57%|█████▋    | 14867/25880 [3:03:06<2:08:07,  1.43it/s]
1|14868|Loss: 0.8674737811088562:  57%|█████▋    | 14867/25880 [3:03:06<2:08:07,  1.43it/s]
1|14868|Loss: 0.8674737811088562:  57%|█████▋    | 14868/25880 [3:03:06<2:10:22,  1.41it/s]
1|14869|Loss: 0.7369880676269531:  57%|█████▋    | 14868/25880 [3:03:07<2:10:22,  1.41it/s]
1|14869|Loss: 0.7369880676269531:  57%|█████▋    | 14869/25880 [3:03:07<2:10:06,  1.41it/s]
1|14870|Loss: 0.8153479695320129:  57%|█████▋    | 14869/25880 [3:03:07<2:10:06,  1.41it/s]
1|14870|Loss: 0.8153479695320129:  57%|█████▋    | 14870/25880 [3:03:08<2:04:07,  1.48it/s]
1|14871|Loss: 0.8948318362236023:  57%|█████▋    | 14870/25880 [3:03:08<2:04:07,  1.48it/s]
1|14871|Loss: 0.8948318362236023:  57%|█████▋    | 14871/25880 [3:03:08<2:03:55,  1.48it/s]
1|14872|Loss: 0.9524719715118408:  57%|█████▋    | 14871/25880 [3:03:09<2:03:55,  1.48it/s]
1|14872|Loss: 0.9524719715118408:  57%|█████▋    | 14872/25880 [3:03:09<2:09:58,  1.41it/s]
1|14873|Loss: 0.8480755090713501:  57%|█████▋    | 14872/25880 [3:03:10<2:09:58,  1.41it/s]
1|14873|Loss: 0.8480755090713501:  57%|█████▋    | 14873/25880 [3:03:10<2:07:56,  1.43it/s]
1|14874|Loss: 0.7628065347671509:  57%|█████▋    | 14873/25880 [3:03:10<2:07:56,  1.43it/s]
1|14874|Loss: 0.7628065347671509:  57%|█████▋    | 14874/25880 [3:03:11<2:09:05,  1.42it/s]
1|14875|Loss: 0.9190317988395691:  57%|█████▋    | 14874/25880 [3:03:11<2:09:05,  1.42it/s]
1|14875|Loss: 0.9190317988395691:  57%|█████▋    | 14875/25880 [3:03:11<2:06:42,  1.45it/s]
1|14876|Loss: 0.746828019618988:  57%|█████▋    | 14875/25880 [3:03:12<2:06:42,  1.45it/s] 
1|14876|Loss: 0.746828019618988:  57%|█████▋    | 14876/25880 [3:03:12<2:01:47,  1.51it/s]
1|14877|Loss: 0.9774462580680847:  57%|█████▋    | 14876/25880 [3:03:12<2:01:47,  1.51it/s]
1|14877|Loss: 0.9774462580680847:  57%|█████▋    | 14877/25880 [3:03:13<2:04:38,  1.47it/s]
1|14878|Loss: 0.8676451444625854:  57%|█████▋    | 14877/25880 [3:03:13<2:04:38,  1.47it/s]
1|14878|Loss: 0.8676451444625854:  57%|█████▋    | 14878/25880 [3:03:13<2:14:02,  1.37it/s]
1|14879|Loss: 0.7571813464164734:  57%|█████▋    | 14878/25880 [3:03:14<2:14:02,  1.37it/s]
1|14879|Loss: 0.7571813464164734:  57%|█████▋    | 14879/25880 [3:03:14<2:16:12,  1.35it/s]
1|14880|Loss: 0.8104419708251953:  57%|█████▋    | 14879/25880 [3:03:15<2:16:12,  1.35it/s]
1|14880|Loss: 0.8104419708251953:  57%|█████▋    | 14880/25880 [3:03:15<2:15:56,  1.35it/s]
1|14881|Loss: 0.9485638737678528:  57%|█████▋    | 14880/25880 [3:03:15<2:15:56,  1.35it/s]
1|14881|Loss: 0.9485638737678528:  57%|█████▊    | 14881/25880 [3:03:16<2:10:20,  1.41it/s]
1|14882|Loss: 0.8161461353302002:  57%|█████▊    | 14881/25880 [3:03:16<2:10:20,  1.41it/s]
1|14882|Loss: 0.8161461353302002:  58%|█████▊    | 14882/25880 [3:03:16<2:06:00,  1.45it/s]
1|14883|Loss: 0.8898454308509827:  58%|█████▊    | 14882/25880 [3:03:17<2:06:00,  1.45it/s]
1|14883|Loss: 0.8898454308509827:  58%|█████▊    | 14883/25880 [3:03:17<2:08:01,  1.43it/s]
1|14884|Loss: 0.9403788447380066:  58%|█████▊    | 14883/25880 [3:03:17<2:08:01,  1.43it/s]
1|14884|Loss: 0.9403788447380066:  58%|█████▊    | 14884/25880 [3:03:18<2:10:18,  1.41it/s]
1|14885|Loss: 0.8711503744125366:  58%|█████▊    | 14884/25880 [3:03:18<2:10:18,  1.41it/s]
1|14885|Loss: 0.8711503744125366:  58%|█████▊    | 14885/25880 [3:03:18<2:14:59,  1.36it/s]
1|14886|Loss: 0.8590110540390015:  58%|█████▊    | 14885/25880 [3:03:19<2:14:59,  1.36it/s]
1|14886|Loss: 0.8590110540390015:  58%|█████▊    | 14886/25880 [3:03:19<2:23:32,  1.28it/s]
1|14887|Loss: 0.8328689336776733:  58%|█████▊    | 14886/25880 [3:03:20<2:23:32,  1.28it/s]
1|14887|Loss: 0.8328689336776733:  58%|█████▊    | 14887/25880 [3:03:20<2:28:44,  1.23it/s]
1|14888|Loss: 0.7818678021430969:  58%|█████▊    | 14887/25880 [3:03:21<2:28:44,  1.23it/s]
1|14888|Loss: 0.7818678021430969:  58%|█████▊    | 14888/25880 [3:03:21<2:21:01,  1.30it/s]
1|14889|Loss: 0.8017875552177429:  58%|█████▊    | 14888/25880 [3:03:21<2:21:01,  1.30it/s]
1|14889|Loss: 0.8017875552177429:  58%|█████▊    | 14889/25880 [3:03:22<2:16:20,  1.34it/s]
1|14890|Loss: 0.913260817527771:  58%|█████▊    | 14889/25880 [3:03:22<2:16:20,  1.34it/s] 
1|14890|Loss: 0.913260817527771:  58%|█████▊    | 14890/25880 [3:03:22<2:10:53,  1.40it/s]
1|14891|Loss: 0.8933045864105225:  58%|█████▊    | 14890/25880 [3:03:23<2:10:53,  1.40it/s]
1|14891|Loss: 0.8933045864105225:  58%|█████▊    | 14891/25880 [3:03:23<2:11:53,  1.39it/s]
1|14892|Loss: 0.7545729279518127:  58%|█████▊    | 14891/25880 [3:03:23<2:11:53,  1.39it/s]
1|14892|Loss: 0.7545729279518127:  58%|█████▊    | 14892/25880 [3:03:24<2:08:57,  1.42it/s]
1|14893|Loss: 0.741288959980011:  58%|█████▊    | 14892/25880 [3:03:24<2:08:57,  1.42it/s] 
1|14893|Loss: 0.741288959980011:  58%|█████▊    | 14893/25880 [3:03:24<2:18:00,  1.33it/s]
1|14894|Loss: 0.7392009496688843:  58%|█████▊    | 14893/25880 [3:03:25<2:18:00,  1.33it/s]
1|14894|Loss: 0.7392009496688843:  58%|█████▊    | 14894/25880 [3:03:25<2:19:48,  1.31it/s]
1|14895|Loss: 0.8549988269805908:  58%|█████▊    | 14894/25880 [3:03:26<2:19:48,  1.31it/s]
1|14895|Loss: 0.8549988269805908:  58%|█████▊    | 14895/25880 [3:03:26<2:09:55,  1.41it/s]
1|14896|Loss: 0.6977198719978333:  58%|█████▊    | 14895/25880 [3:03:26<2:09:55,  1.41it/s]
1|14896|Loss: 0.6977198719978333:  58%|█████▊    | 14896/25880 [3:03:26<1:54:10,  1.60it/s]
1|14897|Loss: 0.843126654624939:  58%|█████▊    | 14896/25880 [3:03:27<1:54:10,  1.60it/s] 
1|14897|Loss: 0.843126654624939:  58%|█████▊    | 14897/25880 [3:03:27<2:02:09,  1.50it/s]
1|14898|Loss: 0.8301206827163696:  58%|█████▊    | 14897/25880 [3:03:27<2:02:09,  1.50it/s]
1|14898|Loss: 0.8301206827163696:  58%|█████▊    | 14898/25880 [3:03:28<2:02:08,  1.50it/s]
1|14899|Loss: 0.949409544467926:  58%|█████▊    | 14898/25880 [3:03:28<2:02:08,  1.50it/s] 
1|14899|Loss: 0.949409544467926:  58%|█████▊    | 14899/25880 [3:03:28<2:02:53,  1.49it/s]
1|14900|Loss: 0.8811771869659424:  58%|█████▊    | 14899/25880 [3:03:29<2:02:53,  1.49it/s]
1|14900|Loss: 0.8811771869659424:  58%|█████▊    | 14900/25880 [3:03:29<2:10:28,  1.40it/s]
1|14901|Loss: 0.9081071615219116:  58%|█████▊    | 14900/25880 [3:03:30<2:10:28,  1.40it/s]
1|14901|Loss: 0.9081071615219116:  58%|█████▊    | 14901/25880 [3:03:30<2:11:44,  1.39it/s]
1|14902|Loss: 0.8956784009933472:  58%|█████▊    | 14901/25880 [3:03:30<2:11:44,  1.39it/s]
1|14902|Loss: 0.8956784009933472:  58%|█████▊    | 14902/25880 [3:03:31<2:12:15,  1.38it/s]
1|14903|Loss: 0.8572611808776855:  58%|█████▊    | 14902/25880 [3:03:31<2:12:15,  1.38it/s]
1|14903|Loss: 0.8572611808776855:  58%|█████▊    | 14903/25880 [3:03:31<2:13:53,  1.37it/s]
1|14904|Loss: 0.9372193217277527:  58%|█████▊    | 14903/25880 [3:03:32<2:13:53,  1.37it/s]
1|14904|Loss: 0.9372193217277527:  58%|█████▊    | 14904/25880 [3:03:32<2:14:05,  1.36it/s]
1|14905|Loss: 0.8302357792854309:  58%|█████▊    | 14904/25880 [3:03:33<2:14:05,  1.36it/s]
1|14905|Loss: 0.8302357792854309:  58%|█████▊    | 14905/25880 [3:03:33<2:08:39,  1.42it/s]
1|14906|Loss: 0.7747892737388611:  58%|█████▊    | 14905/25880 [3:03:33<2:08:39,  1.42it/s]
1|14906|Loss: 0.7747892737388611:  58%|█████▊    | 14906/25880 [3:03:34<2:09:49,  1.41it/s]
1|14907|Loss: 0.748024582862854:  58%|█████▊    | 14906/25880 [3:03:34<2:09:49,  1.41it/s] 
1|14907|Loss: 0.748024582862854:  58%|█████▊    | 14907/25880 [3:03:34<2:01:45,  1.50it/s]
1|14908|Loss: 0.8099967837333679:  58%|█████▊    | 14907/25880 [3:03:34<2:01:45,  1.50it/s]
1|14908|Loss: 0.8099967837333679:  58%|█████▊    | 14908/25880 [3:03:35<2:02:22,  1.49it/s]
1|14909|Loss: 0.8693372011184692:  58%|█████▊    | 14908/25880 [3:03:35<2:02:22,  1.49it/s]
1|14909|Loss: 0.8693372011184692:  58%|█████▊    | 14909/25880 [3:03:35<1:57:38,  1.55it/s]
1|14910|Loss: 0.8760469555854797:  58%|█████▊    | 14909/25880 [3:03:36<1:57:38,  1.55it/s]
1|14910|Loss: 0.8760469555854797:  58%|█████▊    | 14910/25880 [3:03:36<1:58:59,  1.54it/s]
1|14911|Loss: 0.7059336304664612:  58%|█████▊    | 14910/25880 [3:03:36<1:58:59,  1.54it/s]
1|14911|Loss: 0.7059336304664612:  58%|█████▊    | 14911/25880 [3:03:37<2:09:43,  1.41it/s]
1|14912|Loss: 0.71232008934021:  58%|█████▊    | 14911/25880 [3:03:37<2:09:43,  1.41it/s]  
1|14912|Loss: 0.71232008934021:  58%|█████▊    | 14912/25880 [3:03:38<2:11:37,  1.39it/s]
1|14913|Loss: 0.8673813939094543:  58%|█████▊    | 14912/25880 [3:03:38<2:11:37,  1.39it/s]
1|14913|Loss: 0.8673813939094543:  58%|█████▊    | 14913/25880 [3:03:38<2:10:51,  1.40it/s]
1|14914|Loss: 0.8183083534240723:  58%|█████▊    | 14913/25880 [3:03:39<2:10:51,  1.40it/s]
1|14914|Loss: 0.8183083534240723:  58%|█████▊    | 14914/25880 [3:03:39<2:11:17,  1.39it/s]
1|14915|Loss: 0.8525750637054443:  58%|█████▊    | 14914/25880 [3:03:39<2:11:17,  1.39it/s]
1|14915|Loss: 0.8525750637054443:  58%|█████▊    | 14915/25880 [3:03:40<2:12:30,  1.38it/s]
1|14916|Loss: 0.9431813359260559:  58%|█████▊    | 14915/25880 [3:03:40<2:12:30,  1.38it/s]
1|14916|Loss: 0.9431813359260559:  58%|█████▊    | 14916/25880 [3:03:41<2:13:48,  1.37it/s]
1|14917|Loss: 1.0973230600357056:  58%|█████▊    | 14916/25880 [3:03:41<2:13:48,  1.37it/s]
1|14917|Loss: 1.0973230600357056:  58%|█████▊    | 14917/25880 [3:03:41<2:16:33,  1.34it/s]
1|14918|Loss: 0.6975489854812622:  58%|█████▊    | 14917/25880 [3:03:42<2:16:33,  1.34it/s]
1|14918|Loss: 0.6975489854812622:  58%|█████▊    | 14918/25880 [3:03:42<2:20:47,  1.30it/s]
1|14919|Loss: 0.8625818490982056:  58%|█████▊    | 14918/25880 [3:03:42<2:20:47,  1.30it/s]
1|14919|Loss: 0.8625818490982056:  58%|█████▊    | 14919/25880 [3:03:43<2:09:59,  1.41it/s]
1|14920|Loss: 0.8589504957199097:  58%|█████▊    | 14919/25880 [3:03:43<2:09:59,  1.41it/s]
1|14920|Loss: 0.8589504957199097:  58%|█████▊    | 14920/25880 [3:03:43<1:53:41,  1.61it/s]
1|14921|Loss: 0.8060804009437561:  58%|█████▊    | 14920/25880 [3:03:43<1:53:41,  1.61it/s]
1|14921|Loss: 0.8060804009437561:  58%|█████▊    | 14921/25880 [3:03:44<2:00:49,  1.51it/s]
1|14922|Loss: 0.9645895957946777:  58%|█████▊    | 14921/25880 [3:03:44<2:00:49,  1.51it/s]
1|14922|Loss: 0.9645895957946777:  58%|█████▊    | 14922/25880 [3:03:45<2:11:02,  1.39it/s]
1|14923|Loss: 0.7805070281028748:  58%|█████▊    | 14922/25880 [3:03:45<2:11:02,  1.39it/s]
1|14923|Loss: 0.7805070281028748:  58%|█████▊    | 14923/25880 [3:03:45<2:13:38,  1.37it/s]
1|14924|Loss: 0.8632581830024719:  58%|█████▊    | 14923/25880 [3:03:46<2:13:38,  1.37it/s]
1|14924|Loss: 0.8632581830024719:  58%|█████▊    | 14924/25880 [3:03:46<2:08:45,  1.42it/s]
1|14925|Loss: 0.9308820962905884:  58%|█████▊    | 14924/25880 [3:03:46<2:08:45,  1.42it/s]
1|14925|Loss: 0.9308820962905884:  58%|█████▊    | 14925/25880 [3:03:47<2:00:06,  1.52it/s]
1|14926|Loss: 0.8032333850860596:  58%|█████▊    | 14925/25880 [3:03:47<2:00:06,  1.52it/s]
1|14926|Loss: 0.8032333850860596:  58%|█████▊    | 14926/25880 [3:03:47<1:53:52,  1.60it/s]
1|14927|Loss: 0.941611111164093:  58%|█████▊    | 14926/25880 [3:03:48<1:53:52,  1.60it/s] 
1|14927|Loss: 0.941611111164093:  58%|█████▊    | 14927/25880 [3:03:48<2:00:12,  1.52it/s]
1|14928|Loss: 0.8073851466178894:  58%|█████▊    | 14927/25880 [3:03:48<2:00:12,  1.52it/s]
1|14928|Loss: 0.8073851466178894:  58%|█████▊    | 14928/25880 [3:03:49<2:07:47,  1.43it/s]
1|14929|Loss: 0.8157657384872437:  58%|█████▊    | 14928/25880 [3:03:49<2:07:47,  1.43it/s]
1|14929|Loss: 0.8157657384872437:  58%|█████▊    | 14929/25880 [3:03:49<2:04:04,  1.47it/s]
1|14930|Loss: 0.7396068572998047:  58%|█████▊    | 14929/25880 [3:03:50<2:04:04,  1.47it/s]
1|14930|Loss: 0.7396068572998047:  58%|█████▊    | 14930/25880 [3:03:50<2:04:50,  1.46it/s]
1|14931|Loss: 0.8621875047683716:  58%|█████▊    | 14930/25880 [3:03:50<2:04:50,  1.46it/s]
1|14931|Loss: 0.8621875047683716:  58%|█████▊    | 14931/25880 [3:03:51<2:07:12,  1.43it/s]
1|14932|Loss: 0.7388661503791809:  58%|█████▊    | 14931/25880 [3:03:51<2:07:12,  1.43it/s]
1|14932|Loss: 0.7388661503791809:  58%|█████▊    | 14932/25880 [3:03:51<2:02:21,  1.49it/s]
1|14933|Loss: 0.7402729392051697:  58%|█████▊    | 14932/25880 [3:03:52<2:02:21,  1.49it/s]
1|14933|Loss: 0.7402729392051697:  58%|█████▊    | 14933/25880 [3:03:52<2:14:18,  1.36it/s]
1|14934|Loss: 0.7045354247093201:  58%|█████▊    | 14933/25880 [3:03:53<2:14:18,  1.36it/s]
1|14934|Loss: 0.7045354247093201:  58%|█████▊    | 14934/25880 [3:03:53<2:12:06,  1.38it/s]
1|14935|Loss: 0.7646890878677368:  58%|█████▊    | 14934/25880 [3:03:53<2:12:06,  1.38it/s]
1|14935|Loss: 0.7646890878677368:  58%|█████▊    | 14935/25880 [3:03:54<2:04:29,  1.47it/s]
1|14936|Loss: 0.9316308498382568:  58%|█████▊    | 14935/25880 [3:03:54<2:04:29,  1.47it/s]
1|14936|Loss: 0.9316308498382568:  58%|█████▊    | 14936/25880 [3:03:54<2:11:54,  1.38it/s]
1|14937|Loss: 0.9407634735107422:  58%|█████▊    | 14936/25880 [3:03:55<2:11:54,  1.38it/s]
1|14937|Loss: 0.9407634735107422:  58%|█████▊    | 14937/25880 [3:03:55<2:14:34,  1.36it/s]
1|14938|Loss: 0.9059498310089111:  58%|█████▊    | 14937/25880 [3:03:56<2:14:34,  1.36it/s]
1|14938|Loss: 0.9059498310089111:  58%|█████▊    | 14938/25880 [3:03:56<2:14:30,  1.36it/s]
1|14939|Loss: 0.6710221171379089:  58%|█████▊    | 14938/25880 [3:03:56<2:14:30,  1.36it/s]
1|14939|Loss: 0.6710221171379089:  58%|█████▊    | 14939/25880 [3:03:57<2:23:44,  1.27it/s]
1|14940|Loss: 0.8537865281105042:  58%|█████▊    | 14939/25880 [3:03:57<2:23:44,  1.27it/s]
1|14940|Loss: 0.8537865281105042:  58%|█████▊    | 14940/25880 [3:03:58<2:23:12,  1.27it/s]
1|14941|Loss: 0.8753165006637573:  58%|█████▊    | 14940/25880 [3:03:58<2:23:12,  1.27it/s]
1|14941|Loss: 0.8753165006637573:  58%|█████▊    | 14941/25880 [3:03:58<2:28:45,  1.23it/s]
1|14942|Loss: 0.8945260047912598:  58%|█████▊    | 14941/25880 [3:03:59<2:28:45,  1.23it/s]
1|14942|Loss: 0.8945260047912598:  58%|█████▊    | 14942/25880 [3:03:59<2:22:34,  1.28it/s]
1|14943|Loss: 0.6624970436096191:  58%|█████▊    | 14942/25880 [3:04:00<2:22:34,  1.28it/s]
1|14943|Loss: 0.6624970436096191:  58%|█████▊    | 14943/25880 [3:04:00<2:25:23,  1.25it/s]
1|14944|Loss: 0.7963781356811523:  58%|█████▊    | 14943/25880 [3:04:00<2:25:23,  1.25it/s]
1|14944|Loss: 0.7963781356811523:  58%|█████▊    | 14944/25880 [3:04:01<2:23:36,  1.27it/s]
1|14945|Loss: 0.9362043738365173:  58%|█████▊    | 14944/25880 [3:04:01<2:23:36,  1.27it/s]
1|14945|Loss: 0.9362043738365173:  58%|█████▊    | 14945/25880 [3:04:01<2:16:44,  1.33it/s]
1|14946|Loss: 1.017585039138794:  58%|█████▊    | 14945/25880 [3:04:02<2:16:44,  1.33it/s] 
1|14946|Loss: 1.017585039138794:  58%|█████▊    | 14946/25880 [3:04:02<2:15:28,  1.35it/s]
1|14947|Loss: 0.8891499638557434:  58%|█████▊    | 14946/25880 [3:04:03<2:15:28,  1.35it/s]
1|14947|Loss: 0.8891499638557434:  58%|█████▊    | 14947/25880 [3:04:03<2:18:13,  1.32it/s]
1|14948|Loss: 0.8157728314399719:  58%|█████▊    | 14947/25880 [3:04:03<2:18:13,  1.32it/s]
1|14948|Loss: 0.8157728314399719:  58%|█████▊    | 14948/25880 [3:04:04<2:17:35,  1.32it/s]
1|14949|Loss: 0.8351696133613586:  58%|█████▊    | 14948/25880 [3:04:04<2:17:35,  1.32it/s]
1|14949|Loss: 0.8351696133613586:  58%|█████▊    | 14949/25880 [3:04:04<2:16:08,  1.34it/s]
1|14950|Loss: 0.8873196840286255:  58%|█████▊    | 14949/25880 [3:04:05<2:16:08,  1.34it/s]
1|14950|Loss: 0.8873196840286255:  58%|█████▊    | 14950/25880 [3:04:05<2:18:31,  1.32it/s]
1|14951|Loss: 0.785979151725769:  58%|█████▊    | 14950/25880 [3:04:06<2:18:31,  1.32it/s] 
1|14951|Loss: 0.785979151725769:  58%|█████▊    | 14951/25880 [3:04:06<2:25:48,  1.25it/s]
1|14952|Loss: 0.8602256774902344:  58%|█████▊    | 14951/25880 [3:04:07<2:25:48,  1.25it/s]
1|14952|Loss: 0.8602256774902344:  58%|█████▊    | 14952/25880 [3:04:07<2:16:11,  1.34it/s]
1|14953|Loss: 0.8608946204185486:  58%|█████▊    | 14952/25880 [3:04:07<2:16:11,  1.34it/s]
1|14953|Loss: 0.8608946204185486:  58%|█████▊    | 14953/25880 [3:04:07<2:09:10,  1.41it/s]
1|14954|Loss: 0.8024137616157532:  58%|█████▊    | 14953/25880 [3:04:08<2:09:10,  1.41it/s]
1|14954|Loss: 0.8024137616157532:  58%|█████▊    | 14954/25880 [3:04:08<2:01:33,  1.50it/s]
1|14955|Loss: 0.7186071872711182:  58%|█████▊    | 14954/25880 [3:04:08<2:01:33,  1.50it/s]
1|14955|Loss: 0.7186071872711182:  58%|█████▊    | 14955/25880 [3:04:09<2:03:24,  1.48it/s]
1|14956|Loss: 0.8772704601287842:  58%|█████▊    | 14955/25880 [3:04:09<2:03:24,  1.48it/s]
1|14956|Loss: 0.8772704601287842:  58%|█████▊    | 14956/25880 [3:04:09<2:05:02,  1.46it/s]
1|14957|Loss: 0.9425490498542786:  58%|█████▊    | 14956/25880 [3:04:10<2:05:02,  1.46it/s]
1|14957|Loss: 0.9425490498542786:  58%|█████▊    | 14957/25880 [3:04:10<2:12:12,  1.38it/s]
1|14958|Loss: 0.8672595024108887:  58%|█████▊    | 14957/25880 [3:04:11<2:12:12,  1.38it/s]
1|14958|Loss: 0.8672595024108887:  58%|█████▊    | 14958/25880 [3:04:11<2:17:03,  1.33it/s]
1|14959|Loss: 0.9071779847145081:  58%|█████▊    | 14958/25880 [3:04:11<2:17:03,  1.33it/s]
1|14959|Loss: 0.9071779847145081:  58%|█████▊    | 14959/25880 [3:04:12<2:04:33,  1.46it/s]
1|14960|Loss: 0.8750305771827698:  58%|█████▊    | 14959/25880 [3:04:12<2:04:33,  1.46it/s]
1|14960|Loss: 0.8750305771827698:  58%|█████▊    | 14960/25880 [3:04:12<1:57:26,  1.55it/s]
1|14961|Loss: 0.6991076469421387:  58%|█████▊    | 14960/25880 [3:04:12<1:57:26,  1.55it/s]
1|14961|Loss: 0.6991076469421387:  58%|█████▊    | 14961/25880 [3:04:13<2:00:50,  1.51it/s]
1|14962|Loss: 0.7527647614479065:  58%|█████▊    | 14961/25880 [3:04:13<2:00:50,  1.51it/s]
1|14962|Loss: 0.7527647614479065:  58%|█████▊    | 14962/25880 [3:04:13<2:03:10,  1.48it/s]
1|14963|Loss: 0.8626310229301453:  58%|█████▊    | 14962/25880 [3:04:14<2:03:10,  1.48it/s]
1|14963|Loss: 0.8626310229301453:  58%|█████▊    | 14963/25880 [3:04:14<2:05:17,  1.45it/s]
1|14964|Loss: 0.8696240186691284:  58%|█████▊    | 14963/25880 [3:04:15<2:05:17,  1.45it/s]
1|14964|Loss: 0.8696240186691284:  58%|█████▊    | 14964/25880 [3:04:15<2:11:41,  1.38it/s]
1|14965|Loss: 0.9886906743049622:  58%|█████▊    | 14964/25880 [3:04:15<2:11:41,  1.38it/s]
1|14965|Loss: 0.9886906743049622:  58%|█████▊    | 14965/25880 [3:04:16<2:18:20,  1.31it/s]
1|14966|Loss: 0.8698433637619019:  58%|█████▊    | 14965/25880 [3:04:16<2:18:20,  1.31it/s]
1|14966|Loss: 0.8698433637619019:  58%|█████▊    | 14966/25880 [3:04:17<2:17:10,  1.33it/s]
1|14967|Loss: 0.9676650762557983:  58%|█████▊    | 14966/25880 [3:04:17<2:17:10,  1.33it/s]
1|14967|Loss: 0.9676650762557983:  58%|█████▊    | 14967/25880 [3:04:17<2:11:48,  1.38it/s]
1|14968|Loss: 0.8486903309822083:  58%|█████▊    | 14967/25880 [3:04:18<2:11:48,  1.38it/s]
1|14968|Loss: 0.8486903309822083:  58%|█████▊    | 14968/25880 [3:04:18<2:10:17,  1.40it/s]
1|14969|Loss: 0.8688550591468811:  58%|█████▊    | 14968/25880 [3:04:18<2:10:17,  1.40it/s]
1|14969|Loss: 0.8688550591468811:  58%|█████▊    | 14969/25880 [3:04:19<2:15:08,  1.35it/s]
1|14970|Loss: 1.0016616582870483:  58%|█████▊    | 14969/25880 [3:04:19<2:15:08,  1.35it/s]
1|14970|Loss: 1.0016616582870483:  58%|█████▊    | 14970/25880 [3:04:19<2:15:46,  1.34it/s]
1|14971|Loss: 0.7600436806678772:  58%|█████▊    | 14970/25880 [3:04:20<2:15:46,  1.34it/s]
1|14971|Loss: 0.7600436806678772:  58%|█████▊    | 14971/25880 [3:04:20<2:18:13,  1.32it/s]
1|14972|Loss: 0.8677341938018799:  58%|█████▊    | 14971/25880 [3:04:21<2:18:13,  1.32it/s]
1|14972|Loss: 0.8677341938018799:  58%|█████▊    | 14972/25880 [3:04:21<2:18:21,  1.31it/s]
1|14973|Loss: 0.8537154197692871:  58%|█████▊    | 14972/25880 [3:04:21<2:18:21,  1.31it/s]
1|14973|Loss: 0.8537154197692871:  58%|█████▊    | 14973/25880 [3:04:22<2:13:16,  1.36it/s]
1|14974|Loss: 0.7618465423583984:  58%|█████▊    | 14973/25880 [3:04:22<2:13:16,  1.36it/s]
1|14974|Loss: 0.7618465423583984:  58%|█████▊    | 14974/25880 [3:04:22<2:08:22,  1.42it/s]
1|14975|Loss: 0.8798741698265076:  58%|█████▊    | 14974/25880 [3:04:23<2:08:22,  1.42it/s]
1|14975|Loss: 0.8798741698265076:  58%|█████▊    | 14975/25880 [3:04:23<2:12:02,  1.38it/s]
1|14976|Loss: 0.8361247181892395:  58%|█████▊    | 14975/25880 [3:04:24<2:12:02,  1.38it/s]
1|14976|Loss: 0.8361247181892395:  58%|█████▊    | 14976/25880 [3:04:24<2:16:17,  1.33it/s]
1|14977|Loss: 0.8965964913368225:  58%|█████▊    | 14976/25880 [3:04:24<2:16:17,  1.33it/s]
1|14977|Loss: 0.8965964913368225:  58%|█████▊    | 14977/25880 [3:04:25<2:11:58,  1.38it/s]
1|14978|Loss: 0.8765981793403625:  58%|█████▊    | 14977/25880 [3:04:25<2:11:58,  1.38it/s]
1|14978|Loss: 0.8765981793403625:  58%|█████▊    | 14978/25880 [3:04:25<2:10:57,  1.39it/s]
1|14979|Loss: 0.9517087936401367:  58%|█████▊    | 14978/25880 [3:04:26<2:10:57,  1.39it/s]
1|14979|Loss: 0.9517087936401367:  58%|█████▊    | 14979/25880 [3:04:26<2:07:24,  1.43it/s]
1|14980|Loss: 0.8896414637565613:  58%|█████▊    | 14979/25880 [3:04:26<2:07:24,  1.43it/s]
1|14980|Loss: 0.8896414637565613:  58%|█████▊    | 14980/25880 [3:04:27<2:06:55,  1.43it/s]
1|14981|Loss: 0.8353670835494995:  58%|█████▊    | 14980/25880 [3:04:27<2:06:55,  1.43it/s]
1|14981|Loss: 0.8353670835494995:  58%|█████▊    | 14981/25880 [3:04:27<2:00:44,  1.50it/s]
1|14982|Loss: 0.812760055065155:  58%|█████▊    | 14981/25880 [3:04:28<2:00:44,  1.50it/s] 
1|14982|Loss: 0.812760055065155:  58%|█████▊    | 14982/25880 [3:04:28<1:57:26,  1.55it/s]
1|14983|Loss: 0.8191878795623779:  58%|█████▊    | 14982/25880 [3:04:28<1:57:26,  1.55it/s]
1|14983|Loss: 0.8191878795623779:  58%|█████▊    | 14983/25880 [3:04:28<1:56:52,  1.55it/s]
1|14984|Loss: 0.9198316335678101:  58%|█████▊    | 14983/25880 [3:04:29<1:56:52,  1.55it/s]
1|14984|Loss: 0.9198316335678101:  58%|█████▊    | 14984/25880 [3:04:29<1:53:57,  1.59it/s]
1|14985|Loss: 0.8381520509719849:  58%|█████▊    | 14984/25880 [3:04:29<1:53:57,  1.59it/s]
1|14985|Loss: 0.8381520509719849:  58%|█████▊    | 14985/25880 [3:04:30<1:58:32,  1.53it/s]
1|14986|Loss: 0.8677908182144165:  58%|█████▊    | 14985/25880 [3:04:30<1:58:32,  1.53it/s]
1|14986|Loss: 0.8677908182144165:  58%|█████▊    | 14986/25880 [3:04:30<1:56:46,  1.55it/s]
1|14987|Loss: 0.9261037111282349:  58%|█████▊    | 14986/25880 [3:04:31<1:56:46,  1.55it/s]
1|14987|Loss: 0.9261037111282349:  58%|█████▊    | 14987/25880 [3:04:31<2:07:37,  1.42it/s]
1|14988|Loss: 0.7497721910476685:  58%|█████▊    | 14987/25880 [3:04:32<2:07:37,  1.42it/s]
1|14988|Loss: 0.7497721910476685:  58%|█████▊    | 14988/25880 [3:04:32<2:16:25,  1.33it/s]
1|14989|Loss: 0.7415169477462769:  58%|█████▊    | 14988/25880 [3:04:33<2:16:25,  1.33it/s]
1|14989|Loss: 0.7415169477462769:  58%|█████▊    | 14989/25880 [3:04:33<2:19:53,  1.30it/s]
1|14990|Loss: 0.8596442937850952:  58%|█████▊    | 14989/25880 [3:04:33<2:19:53,  1.30it/s]
1|14990|Loss: 0.8596442937850952:  58%|█████▊    | 14990/25880 [3:04:34<2:24:59,  1.25it/s]
1|14991|Loss: 0.8990429043769836:  58%|█████▊    | 14990/25880 [3:04:34<2:24:59,  1.25it/s]
1|14991|Loss: 0.8990429043769836:  58%|█████▊    | 14991/25880 [3:04:35<2:27:22,  1.23it/s]
1|14992|Loss: 0.7834972739219666:  58%|█████▊    | 14991/25880 [3:04:35<2:27:22,  1.23it/s]
1|14992|Loss: 0.7834972739219666:  58%|█████▊    | 14992/25880 [3:04:35<2:24:03,  1.26it/s]
1|14993|Loss: 0.8327686190605164:  58%|█████▊    | 14992/25880 [3:04:36<2:24:03,  1.26it/s]
1|14993|Loss: 0.8327686190605164:  58%|█████▊    | 14993/25880 [3:04:36<2:10:01,  1.40it/s]
1|14994|Loss: 0.8048239350318909:  58%|█████▊    | 14993/25880 [3:04:36<2:10:01,  1.40it/s]
1|14994|Loss: 0.8048239350318909:  58%|█████▊    | 14994/25880 [3:04:37<2:07:57,  1.42it/s]
1|14995|Loss: 0.941996157169342:  58%|█████▊    | 14994/25880 [3:04:37<2:07:57,  1.42it/s] 
1|14995|Loss: 0.941996157169342:  58%|█████▊    | 14995/25880 [3:04:37<2:07:59,  1.42it/s]
1|14996|Loss: 0.7808876037597656:  58%|█████▊    | 14995/25880 [3:04:38<2:07:59,  1.42it/s]
1|14996|Loss: 0.7808876037597656:  58%|█████▊    | 14996/25880 [3:04:38<2:07:32,  1.42it/s]
1|14997|Loss: 0.9809731245040894:  58%|█████▊    | 14996/25880 [3:04:38<2:07:32,  1.42it/s]
1|14997|Loss: 0.9809731245040894:  58%|█████▊    | 14997/25880 [3:04:39<2:04:33,  1.46it/s]
1|14998|Loss: 1.0504112243652344:  58%|█████▊    | 14997/25880 [3:04:39<2:04:33,  1.46it/s]
1|14998|Loss: 1.0504112243652344:  58%|█████▊    | 14998/25880 [3:04:40<2:14:03,  1.35it/s]
1|14999|Loss: 0.7738616466522217:  58%|█████▊    | 14998/25880 [3:04:40<2:14:03,  1.35it/s]
1|14999|Loss: 0.7738616466522217:  58%|█████▊    | 14999/25880 [3:04:40<2:14:05,  1.35it/s]
1|15000|Loss: 0.9061408042907715:  58%|█████▊    | 14999/25880 [3:04:41<2:14:05,  1.35it/s]
1|15000|Loss: 0.9061408042907715:  58%|█████▊    | 15000/25880 [3:04:41<2:17:48,  1.32it/s]
1|15001|Loss: 0.9556620121002197:  58%|█████▊    | 15000/25880 [3:04:41<2:17:48,  1.32it/s]
1|15001|Loss: 0.9556620121002197:  58%|█████▊    | 15001/25880 [3:04:42<2:13:25,  1.36it/s]
1|15002|Loss: 0.8408592343330383:  58%|█████▊    | 15001/25880 [3:04:42<2:13:25,  1.36it/s]
1|15002|Loss: 0.8408592343330383:  58%|█████▊    | 15002/25880 [3:04:42<2:08:38,  1.41it/s]
1|15003|Loss: 0.8745033740997314:  58%|█████▊    | 15002/25880 [3:04:43<2:08:38,  1.41it/s]
1|15003|Loss: 0.8745033740997314:  58%|█████▊    | 15003/25880 [3:04:43<2:05:10,  1.45it/s]
1|15004|Loss: 0.8143905997276306:  58%|█████▊    | 15003/25880 [3:04:43<2:05:10,  1.45it/s]
1|15004|Loss: 0.8143905997276306:  58%|█████▊    | 15004/25880 [3:04:44<2:13:29,  1.36it/s]
1|15005|Loss: 0.9028360843658447:  58%|█████▊    | 15004/25880 [3:04:44<2:13:29,  1.36it/s]
1|15005|Loss: 0.9028360843658447:  58%|█████▊    | 15005/25880 [3:04:45<2:16:07,  1.33it/s]
1|15006|Loss: 0.8081251978874207:  58%|█████▊    | 15005/25880 [3:04:45<2:16:07,  1.33it/s]
1|15006|Loss: 0.8081251978874207:  58%|█████▊    | 15006/25880 [3:04:46<2:21:44,  1.28it/s]
1|15007|Loss: 0.7481381893157959:  58%|█████▊    | 15006/25880 [3:04:46<2:21:44,  1.28it/s]
1|15007|Loss: 0.7481381893157959:  58%|█████▊    | 15007/25880 [3:04:46<2:20:45,  1.29it/s]
1|15008|Loss: 0.870249330997467:  58%|█████▊    | 15007/25880 [3:04:47<2:20:45,  1.29it/s] 
1|15008|Loss: 0.870249330997467:  58%|█████▊    | 15008/25880 [3:04:47<2:17:09,  1.32it/s]
1|15009|Loss: 1.2237714529037476:  58%|█████▊    | 15008/25880 [3:04:47<2:17:09,  1.32it/s]
1|15009|Loss: 1.2237714529037476:  58%|█████▊    | 15009/25880 [3:04:48<2:05:48,  1.44it/s]
1|15010|Loss: 0.8536746501922607:  58%|█████▊    | 15009/25880 [3:04:48<2:05:48,  1.44it/s]
1|15010|Loss: 0.8536746501922607:  58%|█████▊    | 15010/25880 [3:04:48<2:01:35,  1.49it/s]
1|15011|Loss: 0.9116158485412598:  58%|█████▊    | 15010/25880 [3:04:49<2:01:35,  1.49it/s]
1|15011|Loss: 0.9116158485412598:  58%|█████▊    | 15011/25880 [3:04:49<2:06:30,  1.43it/s]
1|15012|Loss: 0.7657103538513184:  58%|█████▊    | 15011/25880 [3:04:49<2:06:30,  1.43it/s]
1|15012|Loss: 0.7657103538513184:  58%|█████▊    | 15012/25880 [3:04:50<2:12:00,  1.37it/s]
1|15013|Loss: 0.8287432193756104:  58%|█████▊    | 15012/25880 [3:04:50<2:12:00,  1.37it/s]
1|15013|Loss: 0.8287432193756104:  58%|█████▊    | 15013/25880 [3:04:50<2:12:53,  1.36it/s]
1|15014|Loss: 0.7795473337173462:  58%|█████▊    | 15013/25880 [3:04:51<2:12:53,  1.36it/s]
1|15014|Loss: 0.7795473337173462:  58%|█████▊    | 15014/25880 [3:04:51<2:12:51,  1.36it/s]
1|15015|Loss: 0.798686683177948:  58%|█████▊    | 15014/25880 [3:04:52<2:12:51,  1.36it/s] 
1|15015|Loss: 0.798686683177948:  58%|█████▊    | 15015/25880 [3:04:52<2:17:33,  1.32it/s]
1|15016|Loss: 0.8000696897506714:  58%|█████▊    | 15015/25880 [3:04:52<2:17:33,  1.32it/s]
1|15016|Loss: 0.8000696897506714:  58%|█████▊    | 15016/25880 [3:04:53<2:21:52,  1.28it/s]
1|15017|Loss: 0.8262296915054321:  58%|█████▊    | 15016/25880 [3:04:53<2:21:52,  1.28it/s]
1|15017|Loss: 0.8262296915054321:  58%|█████▊    | 15017/25880 [3:04:54<2:25:09,  1.25it/s]
1|15018|Loss: 1.0320069789886475:  58%|█████▊    | 15017/25880 [3:04:54<2:25:09,  1.25it/s]
1|15018|Loss: 1.0320069789886475:  58%|█████▊    | 15018/25880 [3:04:54<2:24:01,  1.26it/s]
1|15019|Loss: 0.894978404045105:  58%|█████▊    | 15018/25880 [3:04:55<2:24:01,  1.26it/s] 
1|15019|Loss: 0.894978404045105:  58%|█████▊    | 15019/25880 [3:04:55<2:16:11,  1.33it/s]
1|15020|Loss: 0.8471038341522217:  58%|█████▊    | 15019/25880 [3:04:55<2:16:11,  1.33it/s]
1|15020|Loss: 0.8471038341522217:  58%|█████▊    | 15020/25880 [3:04:56<2:07:59,  1.41it/s]
1|15021|Loss: 0.7893877625465393:  58%|█████▊    | 15020/25880 [3:04:56<2:07:59,  1.41it/s]
1|15021|Loss: 0.7893877625465393:  58%|█████▊    | 15021/25880 [3:04:56<2:02:39,  1.48it/s]
1|15022|Loss: 0.9217738509178162:  58%|█████▊    | 15021/25880 [3:04:57<2:02:39,  1.48it/s]
1|15022|Loss: 0.9217738509178162:  58%|█████▊    | 15022/25880 [3:04:57<2:06:59,  1.43it/s]
1|15023|Loss: 0.8718703389167786:  58%|█████▊    | 15022/25880 [3:04:58<2:06:59,  1.43it/s]
1|15023|Loss: 0.8718703389167786:  58%|█████▊    | 15023/25880 [3:04:58<2:09:23,  1.40it/s]
1|15024|Loss: 0.7174709439277649:  58%|█████▊    | 15023/25880 [3:04:58<2:09:23,  1.40it/s]
1|15024|Loss: 0.7174709439277649:  58%|█████▊    | 15024/25880 [3:04:59<2:12:51,  1.36it/s]
1|15025|Loss: 0.9042840003967285:  58%|█████▊    | 15024/25880 [3:04:59<2:12:51,  1.36it/s]
1|15025|Loss: 0.9042840003967285:  58%|█████▊    | 15025/25880 [3:04:59<2:19:01,  1.30it/s]
1|15026|Loss: 0.9658682346343994:  58%|█████▊    | 15025/25880 [3:05:00<2:19:01,  1.30it/s]
1|15026|Loss: 0.9658682346343994:  58%|█████▊    | 15026/25880 [3:05:00<2:18:47,  1.30it/s]
1|15027|Loss: 0.9606941938400269:  58%|█████▊    | 15026/25880 [3:05:01<2:18:47,  1.30it/s]
1|15027|Loss: 0.9606941938400269:  58%|█████▊    | 15027/25880 [3:05:01<2:23:15,  1.26it/s]
1|15028|Loss: 0.961965799331665:  58%|█████▊    | 15027/25880 [3:05:02<2:23:15,  1.26it/s] 
1|15028|Loss: 0.961965799331665:  58%|█████▊    | 15028/25880 [3:05:02<2:26:07,  1.24it/s]
1|15029|Loss: 0.7898942828178406:  58%|█████▊    | 15028/25880 [3:05:02<2:26:07,  1.24it/s]
1|15029|Loss: 0.7898942828178406:  58%|█████▊    | 15029/25880 [3:05:03<2:18:05,  1.31it/s]
1|15030|Loss: 0.9282521605491638:  58%|█████▊    | 15029/25880 [3:05:03<2:18:05,  1.31it/s]
1|15030|Loss: 0.9282521605491638:  58%|█████▊    | 15030/25880 [3:05:03<2:07:31,  1.42it/s]
1|15031|Loss: 0.947390615940094:  58%|█████▊    | 15030/25880 [3:05:04<2:07:31,  1.42it/s] 
1|15031|Loss: 0.947390615940094:  58%|█████▊    | 15031/25880 [3:05:04<2:03:20,  1.47it/s]
1|15032|Loss: 0.7456408143043518:  58%|█████▊    | 15031/25880 [3:05:04<2:03:20,  1.47it/s]
1|15032|Loss: 0.7456408143043518:  58%|█████▊    | 15032/25880 [3:05:05<2:05:40,  1.44it/s]
1|15033|Loss: 0.9418646097183228:  58%|█████▊    | 15032/25880 [3:05:05<2:05:40,  1.44it/s]
1|15033|Loss: 0.9418646097183228:  58%|█████▊    | 15033/25880 [3:05:05<1:58:09,  1.53it/s]
1|15034|Loss: 0.7780675292015076:  58%|█████▊    | 15033/25880 [3:05:05<1:58:09,  1.53it/s]
1|15034|Loss: 0.7780675292015076:  58%|█████▊    | 15034/25880 [3:05:06<1:50:12,  1.64it/s]
1|15035|Loss: 0.7628551125526428:  58%|█████▊    | 15034/25880 [3:05:06<1:50:12,  1.64it/s]
1|15035|Loss: 0.7628551125526428:  58%|█████▊    | 15035/25880 [3:05:06<1:59:27,  1.51it/s]
1|15036|Loss: 0.8823496699333191:  58%|█████▊    | 15035/25880 [3:05:07<1:59:27,  1.51it/s]
1|15036|Loss: 0.8823496699333191:  58%|█████▊    | 15036/25880 [3:05:07<1:58:26,  1.53it/s]
1|15037|Loss: 0.834495484828949:  58%|█████▊    | 15036/25880 [3:05:07<1:58:26,  1.53it/s] 
1|15037|Loss: 0.834495484828949:  58%|█████▊    | 15037/25880 [3:05:08<2:03:38,  1.46it/s]
1|15038|Loss: 0.855624258518219:  58%|█████▊    | 15037/25880 [3:05:08<2:03:38,  1.46it/s]
1|15038|Loss: 0.855624258518219:  58%|█████▊    | 15038/25880 [3:05:09<2:09:33,  1.39it/s]
1|15039|Loss: 0.853630006313324:  58%|█████▊    | 15038/25880 [3:05:09<2:09:33,  1.39it/s]
1|15039|Loss: 0.853630006313324:  58%|█████▊    | 15039/25880 [3:05:09<2:09:44,  1.39it/s]
1|15040|Loss: 0.8875295519828796:  58%|█████▊    | 15039/25880 [3:05:10<2:09:44,  1.39it/s]
1|15040|Loss: 0.8875295519828796:  58%|█████▊    | 15040/25880 [3:05:10<2:15:24,  1.33it/s]
1|15041|Loss: 0.9125432372093201:  58%|█████▊    | 15040/25880 [3:05:11<2:15:24,  1.33it/s]
1|15041|Loss: 0.9125432372093201:  58%|█████▊    | 15041/25880 [3:05:11<2:22:48,  1.26it/s]
1|15042|Loss: 0.7475688457489014:  58%|█████▊    | 15041/25880 [3:05:11<2:22:48,  1.26it/s]
1|15042|Loss: 0.7475688457489014:  58%|█████▊    | 15042/25880 [3:05:12<2:15:24,  1.33it/s]
1|15043|Loss: 0.8475877046585083:  58%|█████▊    | 15042/25880 [3:05:12<2:15:24,  1.33it/s]
1|15043|Loss: 0.8475877046585083:  58%|█████▊    | 15043/25880 [3:05:12<2:12:50,  1.36it/s]
1|15044|Loss: 0.6937794089317322:  58%|█████▊    | 15043/25880 [3:05:13<2:12:50,  1.36it/s]
1|15044|Loss: 0.6937794089317322:  58%|█████▊    | 15044/25880 [3:05:13<2:08:26,  1.41it/s]
1|15045|Loss: 0.8504079580307007:  58%|█████▊    | 15044/25880 [3:05:13<2:08:26,  1.41it/s]
1|15045|Loss: 0.8504079580307007:  58%|█████▊    | 15045/25880 [3:05:14<2:09:26,  1.40it/s]
1|15046|Loss: 0.8603402972221375:  58%|█████▊    | 15045/25880 [3:05:14<2:09:26,  1.40it/s]
1|15046|Loss: 0.8603402972221375:  58%|█████▊    | 15046/25880 [3:05:15<2:13:11,  1.36it/s]
1|15047|Loss: 1.0056110620498657:  58%|█████▊    | 15046/25880 [3:05:15<2:13:11,  1.36it/s]
1|15047|Loss: 1.0056110620498657:  58%|█████▊    | 15047/25880 [3:05:15<2:18:28,  1.30it/s]
1|15048|Loss: 0.7983092069625854:  58%|█████▊    | 15047/25880 [3:05:16<2:18:28,  1.30it/s]
1|15048|Loss: 0.7983092069625854:  58%|█████▊    | 15048/25880 [3:05:16<2:21:59,  1.27it/s]
1|15049|Loss: 0.9362310767173767:  58%|█████▊    | 15048/25880 [3:05:17<2:21:59,  1.27it/s]
1|15049|Loss: 0.9362310767173767:  58%|█████▊    | 15049/25880 [3:05:17<2:15:10,  1.34it/s]
1|15050|Loss: 0.8375639915466309:  58%|█████▊    | 15049/25880 [3:05:17<2:15:10,  1.34it/s]
1|15050|Loss: 0.8375639915466309:  58%|█████▊    | 15050/25880 [3:05:18<2:13:14,  1.35it/s]
1|15051|Loss: 0.6854792237281799:  58%|█████▊    | 15050/25880 [3:05:18<2:13:14,  1.35it/s]
1|15051|Loss: 0.6854792237281799:  58%|█████▊    | 15051/25880 [3:05:18<2:13:09,  1.36it/s]
1|15052|Loss: 0.8082389235496521:  58%|█████▊    | 15051/25880 [3:05:19<2:13:09,  1.36it/s]
1|15052|Loss: 0.8082389235496521:  58%|█████▊    | 15052/25880 [3:05:19<2:11:41,  1.37it/s]
1|15053|Loss: 0.9145597815513611:  58%|█████▊    | 15052/25880 [3:05:19<2:11:41,  1.37it/s]
1|15053|Loss: 0.9145597815513611:  58%|█████▊    | 15053/25880 [3:05:20<2:19:41,  1.29it/s]
1|15054|Loss: 0.8474762439727783:  58%|█████▊    | 15053/25880 [3:05:20<2:19:41,  1.29it/s]
1|15054|Loss: 0.8474762439727783:  58%|█████▊    | 15054/25880 [3:05:21<2:12:19,  1.36it/s]
1|15055|Loss: 0.7840433716773987:  58%|█████▊    | 15054/25880 [3:05:21<2:12:19,  1.36it/s]
1|15055|Loss: 0.7840433716773987:  58%|█████▊    | 15055/25880 [3:05:21<2:03:48,  1.46it/s]
1|15056|Loss: 0.8642748594284058:  58%|█████▊    | 15055/25880 [3:05:21<2:03:48,  1.46it/s]
1|15056|Loss: 0.8642748594284058:  58%|█████▊    | 15056/25880 [3:05:22<2:04:36,  1.45it/s]
1|15057|Loss: 0.9053906202316284:  58%|█████▊    | 15056/25880 [3:05:22<2:04:36,  1.45it/s]
1|15057|Loss: 0.9053906202316284:  58%|█████▊    | 15057/25880 [3:05:22<2:02:54,  1.47it/s]
1|15058|Loss: 1.0305255651474:  58%|█████▊    | 15057/25880 [3:05:23<2:02:54,  1.47it/s]   
1|15058|Loss: 1.0305255651474:  58%|█████▊    | 15058/25880 [3:05:23<2:09:23,  1.39it/s]
1|15059|Loss: 0.9056220054626465:  58%|█████▊    | 15058/25880 [3:05:24<2:09:23,  1.39it/s]
1|15059|Loss: 0.9056220054626465:  58%|█████▊    | 15059/25880 [3:05:24<2:18:24,  1.30it/s]
1|15060|Loss: 0.7784652709960938:  58%|█████▊    | 15059/25880 [3:05:25<2:18:24,  1.30it/s]
1|15060|Loss: 0.7784652709960938:  58%|█████▊    | 15060/25880 [3:05:25<2:17:17,  1.31it/s]
1|15061|Loss: 1.0262861251831055:  58%|█████▊    | 15060/25880 [3:05:25<2:17:17,  1.31it/s]
1|15061|Loss: 1.0262861251831055:  58%|█████▊    | 15061/25880 [3:05:26<2:15:38,  1.33it/s]
1|15062|Loss: 1.0105911493301392:  58%|█████▊    | 15061/25880 [3:05:26<2:15:38,  1.33it/s]
1|15062|Loss: 1.0105911493301392:  58%|█████▊    | 15062/25880 [3:05:26<2:05:15,  1.44it/s]
1|15063|Loss: 0.7185943722724915:  58%|█████▊    | 15062/25880 [3:05:27<2:05:15,  1.44it/s]
1|15063|Loss: 0.7185943722724915:  58%|█████▊    | 15063/25880 [3:05:27<2:05:48,  1.43it/s]
1|15064|Loss: 0.8152838349342346:  58%|█████▊    | 15063/25880 [3:05:27<2:05:48,  1.43it/s]
1|15064|Loss: 0.8152838349342346:  58%|█████▊    | 15064/25880 [3:05:28<2:03:23,  1.46it/s]
1|15065|Loss: 0.9365792274475098:  58%|█████▊    | 15064/25880 [3:05:28<2:03:23,  1.46it/s]
1|15065|Loss: 0.9365792274475098:  58%|█████▊    | 15065/25880 [3:05:28<1:58:19,  1.52it/s]
1|15066|Loss: 0.917103111743927:  58%|█████▊    | 15065/25880 [3:05:29<1:58:19,  1.52it/s] 
1|15066|Loss: 0.917103111743927:  58%|█████▊    | 15066/25880 [3:05:29<2:01:07,  1.49it/s]
1|15067|Loss: 0.8948392868041992:  58%|█████▊    | 15066/25880 [3:05:29<2:01:07,  1.49it/s]
1|15067|Loss: 0.8948392868041992:  58%|█████▊    | 15067/25880 [3:05:30<2:06:53,  1.42it/s]
1|15068|Loss: 0.9774312376976013:  58%|█████▊    | 15067/25880 [3:05:30<2:06:53,  1.42it/s]
1|15068|Loss: 0.9774312376976013:  58%|█████▊    | 15068/25880 [3:05:30<2:05:24,  1.44it/s]
1|15069|Loss: 0.6281156539916992:  58%|█████▊    | 15068/25880 [3:05:31<2:05:24,  1.44it/s]
1|15069|Loss: 0.6281156539916992:  58%|█████▊    | 15069/25880 [3:05:31<2:02:33,  1.47it/s]
1|15070|Loss: 0.8258041143417358:  58%|█████▊    | 15069/25880 [3:05:31<2:02:33,  1.47it/s]
1|15070|Loss: 0.8258041143417358:  58%|█████▊    | 15070/25880 [3:05:32<2:00:46,  1.49it/s]
1|15071|Loss: 0.8729529976844788:  58%|█████▊    | 15070/25880 [3:05:32<2:00:46,  1.49it/s]
1|15071|Loss: 0.8729529976844788:  58%|█████▊    | 15071/25880 [3:05:32<2:11:31,  1.37it/s]
1|15072|Loss: 0.7356799840927124:  58%|█████▊    | 15071/25880 [3:05:33<2:11:31,  1.37it/s]
1|15072|Loss: 0.7356799840927124:  58%|█████▊    | 15072/25880 [3:05:33<2:16:01,  1.32it/s]
1|15073|Loss: 0.7522555589675903:  58%|█████▊    | 15072/25880 [3:05:34<2:16:01,  1.32it/s]
1|15073|Loss: 0.7522555589675903:  58%|█████▊    | 15073/25880 [3:05:34<2:14:19,  1.34it/s]
1|15074|Loss: 0.8516938090324402:  58%|█████▊    | 15073/25880 [3:05:34<2:14:19,  1.34it/s]
1|15074|Loss: 0.8516938090324402:  58%|█████▊    | 15074/25880 [3:05:35<2:09:17,  1.39it/s]
1|15075|Loss: 0.9480100870132446:  58%|█████▊    | 15074/25880 [3:05:35<2:09:17,  1.39it/s]
1|15075|Loss: 0.9480100870132446:  58%|█████▊    | 15075/25880 [3:05:35<2:08:01,  1.41it/s]
1|15076|Loss: 0.7519923448562622:  58%|█████▊    | 15075/25880 [3:05:36<2:08:01,  1.41it/s]
1|15076|Loss: 0.7519923448562622:  58%|█████▊    | 15076/25880 [3:05:36<2:07:31,  1.41it/s]
1|15077|Loss: 0.9096466898918152:  58%|█████▊    | 15076/25880 [3:05:36<2:07:31,  1.41it/s]
1|15077|Loss: 0.9096466898918152:  58%|█████▊    | 15077/25880 [3:05:37<2:03:29,  1.46it/s]
1|15078|Loss: 0.8830193877220154:  58%|█████▊    | 15077/25880 [3:05:37<2:03:29,  1.46it/s]
1|15078|Loss: 0.8830193877220154:  58%|█████▊    | 15078/25880 [3:05:37<2:09:23,  1.39it/s]
1|15079|Loss: 0.8176653981208801:  58%|█████▊    | 15078/25880 [3:05:38<2:09:23,  1.39it/s]
1|15079|Loss: 0.8176653981208801:  58%|█████▊    | 15079/25880 [3:05:38<2:04:37,  1.44it/s]
1|15080|Loss: 0.9028303623199463:  58%|█████▊    | 15079/25880 [3:05:39<2:04:37,  1.44it/s]
1|15080|Loss: 0.9028303623199463:  58%|█████▊    | 15080/25880 [3:05:39<2:11:02,  1.37it/s]
1|15081|Loss: 0.7857149243354797:  58%|█████▊    | 15080/25880 [3:05:39<2:11:02,  1.37it/s]
1|15081|Loss: 0.7857149243354797:  58%|█████▊    | 15081/25880 [3:05:39<2:01:18,  1.48it/s]
1|15082|Loss: 0.9250258803367615:  58%|█████▊    | 15081/25880 [3:05:40<2:01:18,  1.48it/s]
1|15082|Loss: 0.9250258803367615:  58%|█████▊    | 15082/25880 [3:05:40<2:05:07,  1.44it/s]
1|15083|Loss: 0.8590928912162781:  58%|█████▊    | 15082/25880 [3:05:41<2:05:07,  1.44it/s]
1|15083|Loss: 0.8590928912162781:  58%|█████▊    | 15083/25880 [3:05:41<1:58:09,  1.52it/s]
1|15084|Loss: 0.829353928565979:  58%|█████▊    | 15083/25880 [3:05:41<1:58:09,  1.52it/s] 
1|15084|Loss: 0.829353928565979:  58%|█████▊    | 15084/25880 [3:05:41<1:54:38,  1.57it/s]
1|15085|Loss: 0.7399200201034546:  58%|█████▊    | 15084/25880 [3:05:42<1:54:38,  1.57it/s]
1|15085|Loss: 0.7399200201034546:  58%|█████▊    | 15085/25880 [3:05:42<1:54:23,  1.57it/s]
1|15086|Loss: 0.9362464547157288:  58%|█████▊    | 15085/25880 [3:05:42<1:54:23,  1.57it/s]
1|15086|Loss: 0.9362464547157288:  58%|█████▊    | 15086/25880 [3:05:43<1:53:51,  1.58it/s]
1|15087|Loss: 0.8308262228965759:  58%|█████▊    | 15086/25880 [3:05:43<1:53:51,  1.58it/s]
1|15087|Loss: 0.8308262228965759:  58%|█████▊    | 15087/25880 [3:05:43<1:54:26,  1.57it/s]
1|15088|Loss: 0.7643357515335083:  58%|█████▊    | 15087/25880 [3:05:44<1:54:26,  1.57it/s]
1|15088|Loss: 0.7643357515335083:  58%|█████▊    | 15088/25880 [3:05:44<1:57:35,  1.53it/s]
1|15089|Loss: 0.860769510269165:  58%|█████▊    | 15088/25880 [3:05:44<1:57:35,  1.53it/s] 
1|15089|Loss: 0.860769510269165:  58%|█████▊    | 15089/25880 [3:05:45<1:54:44,  1.57it/s]
1|15090|Loss: 0.8604063391685486:  58%|█████▊    | 15089/25880 [3:05:45<1:54:44,  1.57it/s]
1|15090|Loss: 0.8604063391685486:  58%|█████▊    | 15090/25880 [3:05:45<1:57:51,  1.53it/s]
1|15091|Loss: 0.8987836837768555:  58%|█████▊    | 15090/25880 [3:05:46<1:57:51,  1.53it/s]
1|15091|Loss: 0.8987836837768555:  58%|█████▊    | 15091/25880 [3:05:46<1:57:41,  1.53it/s]
1|15092|Loss: 0.8843662738800049:  58%|█████▊    | 15091/25880 [3:05:46<1:57:41,  1.53it/s]
1|15092|Loss: 0.8843662738800049:  58%|█████▊    | 15092/25880 [3:05:47<2:03:12,  1.46it/s]
1|15093|Loss: 0.8004513382911682:  58%|█████▊    | 15092/25880 [3:05:47<2:03:12,  1.46it/s]
1|15093|Loss: 0.8004513382911682:  58%|█████▊    | 15093/25880 [3:05:47<1:55:55,  1.55it/s]
1|15094|Loss: 0.7978588342666626:  58%|█████▊    | 15093/25880 [3:05:48<1:55:55,  1.55it/s]
1|15094|Loss: 0.7978588342666626:  58%|█████▊    | 15094/25880 [3:05:48<2:02:50,  1.46it/s]
1|15095|Loss: 0.9299952983856201:  58%|█████▊    | 15094/25880 [3:05:48<2:02:50,  1.46it/s]
1|15095|Loss: 0.9299952983856201:  58%|█████▊    | 15095/25880 [3:05:49<2:07:33,  1.41it/s]
1|15096|Loss: 0.8369659781455994:  58%|█████▊    | 15095/25880 [3:05:49<2:07:33,  1.41it/s]
1|15096|Loss: 0.8369659781455994:  58%|█████▊    | 15096/25880 [3:05:49<2:05:18,  1.43it/s]
1|15097|Loss: 0.9541735649108887:  58%|█████▊    | 15096/25880 [3:05:50<2:05:18,  1.43it/s]
1|15097|Loss: 0.9541735649108887:  58%|█████▊    | 15097/25880 [3:05:50<2:01:20,  1.48it/s]
1|15098|Loss: 0.9686150550842285:  58%|█████▊    | 15097/25880 [3:05:50<2:01:20,  1.48it/s]
1|15098|Loss: 0.9686150550842285:  58%|█████▊    | 15098/25880 [3:05:51<2:03:36,  1.45it/s]
1|15099|Loss: 0.805062472820282:  58%|█████▊    | 15098/25880 [3:05:51<2:03:36,  1.45it/s] 
1|15099|Loss: 0.805062472820282:  58%|█████▊    | 15099/25880 [3:05:51<2:04:49,  1.44it/s]
1|15100|Loss: 0.818267822265625:  58%|█████▊    | 15099/25880 [3:05:52<2:04:49,  1.44it/s]
1|15100|Loss: 0.818267822265625:  58%|█████▊    | 15100/25880 [3:05:52<2:13:04,  1.35it/s]
1|15101|Loss: 0.7301719784736633:  58%|█████▊    | 15100/25880 [3:05:53<2:13:04,  1.35it/s]
1|15101|Loss: 0.7301719784736633:  58%|█████▊    | 15101/25880 [3:05:53<2:14:53,  1.33it/s]
1|15102|Loss: 0.8557392954826355:  58%|█████▊    | 15101/25880 [3:05:54<2:14:53,  1.33it/s]
1|15102|Loss: 0.8557392954826355:  58%|█████▊    | 15102/25880 [3:05:54<2:20:30,  1.28it/s]
1|15103|Loss: 0.8584665656089783:  58%|█████▊    | 15102/25880 [3:05:54<2:20:30,  1.28it/s]
1|15103|Loss: 0.8584665656089783:  58%|█████▊    | 15103/25880 [3:05:55<2:18:23,  1.30it/s]
1|15104|Loss: 0.7446122765541077:  58%|█████▊    | 15103/25880 [3:05:55<2:18:23,  1.30it/s]
1|15104|Loss: 0.7446122765541077:  58%|█████▊    | 15104/25880 [3:05:55<2:19:04,  1.29it/s]
1|15105|Loss: 0.8002669811248779:  58%|█████▊    | 15104/25880 [3:05:56<2:19:04,  1.29it/s]
1|15105|Loss: 0.8002669811248779:  58%|█████▊    | 15105/25880 [3:05:56<2:27:46,  1.22it/s]
1|15106|Loss: 0.8348355889320374:  58%|█████▊    | 15105/25880 [3:05:57<2:27:46,  1.22it/s]
1|15106|Loss: 0.8348355889320374:  58%|█████▊    | 15106/25880 [3:05:57<2:19:00,  1.29it/s]
1|15107|Loss: 0.7729551196098328:  58%|█████▊    | 15106/25880 [3:05:57<2:19:00,  1.29it/s]
1|15107|Loss: 0.7729551196098328:  58%|█████▊    | 15107/25880 [3:05:58<2:17:37,  1.30it/s]
1|15108|Loss: 0.8292149901390076:  58%|█████▊    | 15107/25880 [3:05:58<2:17:37,  1.30it/s]
1|15108|Loss: 0.8292149901390076:  58%|█████▊    | 15108/25880 [3:05:59<2:16:29,  1.32it/s]
1|15109|Loss: 0.809360146522522:  58%|█████▊    | 15108/25880 [3:05:59<2:16:29,  1.32it/s] 
1|15109|Loss: 0.809360146522522:  58%|█████▊    | 15109/25880 [3:05:59<2:14:33,  1.33it/s]
1|15110|Loss: 0.8005672693252563:  58%|█████▊    | 15109/25880 [3:06:00<2:14:33,  1.33it/s]
1|15110|Loss: 0.8005672693252563:  58%|█████▊    | 15110/25880 [3:06:00<2:16:12,  1.32it/s]
1|15111|Loss: 0.8491315245628357:  58%|█████▊    | 15110/25880 [3:06:00<2:16:12,  1.32it/s]
1|15111|Loss: 0.8491315245628357:  58%|█████▊    | 15111/25880 [3:06:01<2:03:18,  1.46it/s]
1|15112|Loss: 0.7737463712692261:  58%|█████▊    | 15111/25880 [3:06:01<2:03:18,  1.46it/s]
1|15112|Loss: 0.7737463712692261:  58%|█████▊    | 15112/25880 [3:06:01<1:57:35,  1.53it/s]
1|15113|Loss: 0.8959787487983704:  58%|█████▊    | 15112/25880 [3:06:02<1:57:35,  1.53it/s]
1|15113|Loss: 0.8959787487983704:  58%|█████▊    | 15113/25880 [3:06:02<2:08:38,  1.39it/s]
1|15114|Loss: 0.9307324886322021:  58%|█████▊    | 15113/25880 [3:06:02<2:08:38,  1.39it/s]
1|15114|Loss: 0.9307324886322021:  58%|█████▊    | 15114/25880 [3:06:03<2:04:47,  1.44it/s]
1|15115|Loss: 0.8874393701553345:  58%|█████▊    | 15114/25880 [3:06:03<2:04:47,  1.44it/s]
1|15115|Loss: 0.8874393701553345:  58%|█████▊    | 15115/25880 [3:06:03<2:05:36,  1.43it/s]
1|15116|Loss: 0.9449503421783447:  58%|█████▊    | 15115/25880 [3:06:04<2:05:36,  1.43it/s]
1|15116|Loss: 0.9449503421783447:  58%|█████▊    | 15116/25880 [3:06:04<2:03:51,  1.45it/s]
1|15117|Loss: 0.8252601027488708:  58%|█████▊    | 15116/25880 [3:06:04<2:03:51,  1.45it/s]
1|15117|Loss: 0.8252601027488708:  58%|█████▊    | 15117/25880 [3:06:05<2:01:02,  1.48it/s]
1|15118|Loss: 0.7570451498031616:  58%|█████▊    | 15117/25880 [3:06:05<2:01:02,  1.48it/s]
1|15118|Loss: 0.7570451498031616:  58%|█████▊    | 15118/25880 [3:06:05<2:01:58,  1.47it/s]
1|15119|Loss: 0.796614408493042:  58%|█████▊    | 15118/25880 [3:06:06<2:01:58,  1.47it/s] 
1|15119|Loss: 0.796614408493042:  58%|█████▊    | 15119/25880 [3:06:06<2:09:30,  1.38it/s]
1|15120|Loss: 0.8399681448936462:  58%|█████▊    | 15119/25880 [3:06:07<2:09:30,  1.38it/s]
1|15120|Loss: 0.8399681448936462:  58%|█████▊    | 15120/25880 [3:06:07<2:07:44,  1.40it/s]
1|15121|Loss: 0.8271864056587219:  58%|█████▊    | 15120/25880 [3:06:07<2:07:44,  1.40it/s]
1|15121|Loss: 0.8271864056587219:  58%|█████▊    | 15121/25880 [3:06:08<2:10:18,  1.38it/s]
1|15122|Loss: 0.7811285853385925:  58%|█████▊    | 15121/25880 [3:06:08<2:10:18,  1.38it/s]
1|15122|Loss: 0.7811285853385925:  58%|█████▊    | 15122/25880 [3:06:09<2:18:09,  1.30it/s]
1|15123|Loss: 0.777981698513031:  58%|█████▊    | 15122/25880 [3:06:09<2:18:09,  1.30it/s] 
1|15123|Loss: 0.777981698513031:  58%|█████▊    | 15123/25880 [3:06:09<2:20:54,  1.27it/s]
1|15124|Loss: 0.8563160300254822:  58%|█████▊    | 15123/25880 [3:06:10<2:20:54,  1.27it/s]
1|15124|Loss: 0.8563160300254822:  58%|█████▊    | 15124/25880 [3:06:10<2:06:37,  1.42it/s]
1|15125|Loss: 0.8794430494308472:  58%|█████▊    | 15124/25880 [3:06:10<2:06:37,  1.42it/s]
1|15125|Loss: 0.8794430494308472:  58%|█████▊    | 15125/25880 [3:06:10<1:58:24,  1.51it/s]
1|15126|Loss: 0.9169453978538513:  58%|█████▊    | 15125/25880 [3:06:11<1:58:24,  1.51it/s]
1|15126|Loss: 0.9169453978538513:  58%|█████▊    | 15126/25880 [3:06:11<2:05:11,  1.43it/s]
1|15127|Loss: 0.7870581150054932:  58%|█████▊    | 15126/25880 [3:06:12<2:05:11,  1.43it/s]
1|15127|Loss: 0.7870581150054932:  58%|█████▊    | 15127/25880 [3:06:12<2:16:14,  1.32it/s]
1|15128|Loss: 0.8558252453804016:  58%|█████▊    | 15127/25880 [3:06:13<2:16:14,  1.32it/s]
1|15128|Loss: 0.8558252453804016:  58%|█████▊    | 15128/25880 [3:06:13<2:17:25,  1.30it/s]
1|15129|Loss: 0.8335461616516113:  58%|█████▊    | 15128/25880 [3:06:13<2:17:25,  1.30it/s]
1|15129|Loss: 0.8335461616516113:  58%|█████▊    | 15129/25880 [3:06:14<2:20:16,  1.28it/s]
1|15130|Loss: 0.8354973196983337:  58%|█████▊    | 15129/25880 [3:06:14<2:20:16,  1.28it/s]
1|15130|Loss: 0.8354973196983337:  58%|█████▊    | 15130/25880 [3:06:14<2:10:01,  1.38it/s]
1|15131|Loss: 0.8505240678787231:  58%|█████▊    | 15130/25880 [3:06:15<2:10:01,  1.38it/s]
1|15131|Loss: 0.8505240678787231:  58%|█████▊    | 15131/25880 [3:06:15<2:04:09,  1.44it/s]
1|15132|Loss: 0.9685330390930176:  58%|█████▊    | 15131/25880 [3:06:15<2:04:09,  1.44it/s]
1|15132|Loss: 0.9685330390930176:  58%|█████▊    | 15132/25880 [3:06:16<2:07:48,  1.40it/s]
1|15133|Loss: 0.8872953057289124:  58%|█████▊    | 15132/25880 [3:06:16<2:07:48,  1.40it/s]
1|15133|Loss: 0.8872953057289124:  58%|█████▊    | 15133/25880 [3:06:16<2:09:15,  1.39it/s]
1|15134|Loss: 0.883516788482666:  58%|█████▊    | 15133/25880 [3:06:17<2:09:15,  1.39it/s] 
1|15134|Loss: 0.883516788482666:  58%|█████▊    | 15134/25880 [3:06:17<2:08:29,  1.39it/s]
1|15135|Loss: 0.9053043723106384:  58%|█████▊    | 15134/25880 [3:06:17<2:08:29,  1.39it/s]
1|15135|Loss: 0.9053043723106384:  58%|█████▊    | 15135/25880 [3:06:18<2:00:13,  1.49it/s]
1|15136|Loss: 0.7731153964996338:  58%|█████▊    | 15135/25880 [3:06:18<2:00:13,  1.49it/s]
1|15136|Loss: 0.7731153964996338:  58%|█████▊    | 15136/25880 [3:06:18<1:59:56,  1.49it/s]
1|15137|Loss: 0.8481022119522095:  58%|█████▊    | 15136/25880 [3:06:19<1:59:56,  1.49it/s]
1|15137|Loss: 0.8481022119522095:  58%|█████▊    | 15137/25880 [3:06:19<2:03:16,  1.45it/s]
1|15138|Loss: 0.8757724165916443:  58%|█████▊    | 15137/25880 [3:06:20<2:03:16,  1.45it/s]
1|15138|Loss: 0.8757724165916443:  58%|█████▊    | 15138/25880 [3:06:20<2:06:06,  1.42it/s]
1|15139|Loss: 0.7525339126586914:  58%|█████▊    | 15138/25880 [3:06:20<2:06:06,  1.42it/s]
1|15139|Loss: 0.7525339126586914:  58%|█████▊    | 15139/25880 [3:06:21<2:08:03,  1.40it/s]
1|15140|Loss: 0.9459241032600403:  58%|█████▊    | 15139/25880 [3:06:21<2:08:03,  1.40it/s]
1|15140|Loss: 0.9459241032600403:  59%|█████▊    | 15140/25880 [3:06:21<2:14:06,  1.33it/s]
1|15141|Loss: 0.8018739819526672:  59%|█████▊    | 15140/25880 [3:06:22<2:14:06,  1.33it/s]
1|15141|Loss: 0.8018739819526672:  59%|█████▊    | 15141/25880 [3:06:22<2:13:44,  1.34it/s]
1|15142|Loss: 0.8981288075447083:  59%|█████▊    | 15141/25880 [3:06:23<2:13:44,  1.34it/s]
1|15142|Loss: 0.8981288075447083:  59%|█████▊    | 15142/25880 [3:06:23<2:12:43,  1.35it/s]
1|15143|Loss: 0.7099871635437012:  59%|█████▊    | 15142/25880 [3:06:23<2:12:43,  1.35it/s]
1|15143|Loss: 0.7099871635437012:  59%|█████▊    | 15143/25880 [3:06:24<2:16:52,  1.31it/s]
1|15144|Loss: 0.7694252729415894:  59%|█████▊    | 15143/25880 [3:06:24<2:16:52,  1.31it/s]
1|15144|Loss: 0.7694252729415894:  59%|█████▊    | 15144/25880 [3:06:24<2:11:19,  1.36it/s]
1|15145|Loss: 0.7744882106781006:  59%|█████▊    | 15144/25880 [3:06:25<2:11:19,  1.36it/s]
1|15145|Loss: 0.7744882106781006:  59%|█████▊    | 15145/25880 [3:06:25<2:06:08,  1.42it/s]
1|15146|Loss: 0.9334651827812195:  59%|█████▊    | 15145/25880 [3:06:25<2:06:08,  1.42it/s]
1|15146|Loss: 0.9334651827812195:  59%|█████▊    | 15146/25880 [3:06:26<2:07:00,  1.41it/s]
1|15147|Loss: 0.6861792206764221:  59%|█████▊    | 15146/25880 [3:06:26<2:07:00,  1.41it/s]
1|15147|Loss: 0.6861792206764221:  59%|█████▊    | 15147/25880 [3:06:27<2:18:02,  1.30it/s]
1|15148|Loss: 0.7978227734565735:  59%|█████▊    | 15147/25880 [3:06:27<2:18:02,  1.30it/s]
1|15148|Loss: 0.7978227734565735:  59%|█████▊    | 15148/25880 [3:06:27<2:06:22,  1.42it/s]
1|15149|Loss: 0.8093020915985107:  59%|█████▊    | 15148/25880 [3:06:28<2:06:22,  1.42it/s]
1|15149|Loss: 0.8093020915985107:  59%|█████▊    | 15149/25880 [3:06:28<2:00:28,  1.48it/s]
1|15150|Loss: 0.8946524858474731:  59%|█████▊    | 15149/25880 [3:06:28<2:00:28,  1.48it/s]
1|15150|Loss: 0.8946524858474731:  59%|█████▊    | 15150/25880 [3:06:29<2:07:07,  1.41it/s]
1|15151|Loss: 0.9108858704566956:  59%|█████▊    | 15150/25880 [3:06:29<2:07:07,  1.41it/s]
1|15151|Loss: 0.9108858704566956:  59%|█████▊    | 15151/25880 [3:06:29<2:09:16,  1.38it/s]
1|15152|Loss: 0.6745268106460571:  59%|█████▊    | 15151/25880 [3:06:30<2:09:16,  1.38it/s]
1|15152|Loss: 0.6745268106460571:  59%|█████▊    | 15152/25880 [3:06:30<2:12:03,  1.35it/s]
1|15153|Loss: 0.8204149603843689:  59%|█████▊    | 15152/25880 [3:06:31<2:12:03,  1.35it/s]
1|15153|Loss: 0.8204149603843689:  59%|█████▊    | 15153/25880 [3:06:31<2:15:35,  1.32it/s]
1|15154|Loss: 0.7941165566444397:  59%|█████▊    | 15153/25880 [3:06:31<2:15:35,  1.32it/s]
1|15154|Loss: 0.7941165566444397:  59%|█████▊    | 15154/25880 [3:06:32<2:11:02,  1.36it/s]
1|15155|Loss: 0.9198670983314514:  59%|█████▊    | 15154/25880 [3:06:32<2:11:02,  1.36it/s]
1|15155|Loss: 0.9198670983314514:  59%|█████▊    | 15155/25880 [3:06:32<2:10:57,  1.37it/s]
1|15156|Loss: 0.8004550933837891:  59%|█████▊    | 15155/25880 [3:06:33<2:10:57,  1.37it/s]
1|15156|Loss: 0.8004550933837891:  59%|█████▊    | 15156/25880 [3:06:33<2:07:26,  1.40it/s]
1|15157|Loss: 0.7738243937492371:  59%|█████▊    | 15156/25880 [3:06:33<2:07:26,  1.40it/s]
1|15157|Loss: 0.7738243937492371:  59%|█████▊    | 15157/25880 [3:06:34<2:12:01,  1.35it/s]
1|15158|Loss: 0.8773860335350037:  59%|█████▊    | 15157/25880 [3:06:34<2:12:01,  1.35it/s]
1|15158|Loss: 0.8773860335350037:  59%|█████▊    | 15158/25880 [3:06:34<2:07:01,  1.41it/s]
1|15159|Loss: 0.884367048740387:  59%|█████▊    | 15158/25880 [3:06:35<2:07:01,  1.41it/s] 
1|15159|Loss: 0.884367048740387:  59%|█████▊    | 15159/25880 [3:06:35<2:01:36,  1.47it/s]
1|15160|Loss: 0.868600070476532:  59%|█████▊    | 15159/25880 [3:06:35<2:01:36,  1.47it/s]
1|15160|Loss: 0.868600070476532:  59%|█��███▊    | 15160/25880 [3:06:36<1:59:34,  1.49it/s]
1|15161|Loss: 0.8640238642692566:  59%|█████▊    | 15160/25880 [3:06:36<1:59:34,  1.49it/s]
1|15161|Loss: 0.8640238642692566:  59%|█████▊    | 15161/25880 [3:06:37<2:12:05,  1.35it/s]
1|15162|Loss: 0.9542146921157837:  59%|█████▊    | 15161/25880 [3:06:37<2:12:05,  1.35it/s]
1|15162|Loss: 0.9542146921157837:  59%|█████▊    | 15162/25880 [3:06:37<2:20:08,  1.27it/s]
1|15163|Loss: 0.810172975063324:  59%|█████▊    | 15162/25880 [3:06:38<2:20:08,  1.27it/s] 
1|15163|Loss: 0.810172975063324:  59%|█████▊    | 15163/25880 [3:06:38<2:19:13,  1.28it/s]
1|15164|Loss: 0.8264740109443665:  59%|█████▊    | 15163/25880 [3:06:39<2:19:13,  1.28it/s]
1|15164|Loss: 0.8264740109443665:  59%|█████▊    | 15164/25880 [3:06:39<2:16:57,  1.30it/s]
1|15165|Loss: 0.944266140460968:  59%|█████▊    | 15164/25880 [3:06:39<2:16:57,  1.30it/s] 
1|15165|Loss: 0.944266140460968:  59%|█████▊    | 15165/25880 [3:06:40<2:18:09,  1.29it/s]
1|15166|Loss: 0.9473946690559387:  59%|█████▊    | 15165/25880 [3:06:40<2:18:09,  1.29it/s]
1|15166|Loss: 0.9473946690559387:  59%|█████▊    | 15166/25880 [3:06:40<2:10:14,  1.37it/s]
1|15167|Loss: 0.7849968671798706:  59%|█████▊    | 15166/25880 [3:06:41<2:10:14,  1.37it/s]
1|15167|Loss: 0.7849968671798706:  59%|█████▊    | 15167/25880 [3:06:41<2:03:31,  1.45it/s]
1|15168|Loss: 0.8625658750534058:  59%|█████▊    | 15167/25880 [3:06:41<2:03:31,  1.45it/s]
1|15168|Loss: 0.8625658750534058:  59%|█████▊    | 15168/25880 [3:06:42<2:00:36,  1.48it/s]
1|15169|Loss: 0.8862215280532837:  59%|█████▊    | 15168/25880 [3:06:42<2:00:36,  1.48it/s]
1|15169|Loss: 0.8862215280532837:  59%|█████▊    | 15169/25880 [3:06:42<1:58:38,  1.50it/s]
1|15170|Loss: 0.8453688621520996:  59%|█████▊    | 15169/25880 [3:06:43<1:58:38,  1.50it/s]
1|15170|Loss: 0.8453688621520996:  59%|█████▊    | 15170/25880 [3:06:43<2:08:01,  1.39it/s]
1|15171|Loss: 0.9234635233879089:  59%|█████▊    | 15170/25880 [3:06:44<2:08:01,  1.39it/s]
1|15171|Loss: 0.9234635233879089:  59%|█████▊    | 15171/25880 [3:06:44<2:11:03,  1.36it/s]
1|15172|Loss: 0.9343724846839905:  59%|█████▊    | 15171/25880 [3:06:44<2:11:03,  1.36it/s]
1|15172|Loss: 0.9343724846839905:  59%|█████▊    | 15172/25880 [3:06:45<2:10:07,  1.37it/s]
1|15173|Loss: 0.8784183859825134:  59%|█████▊    | 15172/25880 [3:06:45<2:10:07,  1.37it/s]
1|15173|Loss: 0.8784183859825134:  59%|█████▊    | 15173/25880 [3:06:45<2:12:10,  1.35it/s]
1|15174|Loss: 0.8339503407478333:  59%|█████▊    | 15173/25880 [3:06:46<2:12:10,  1.35it/s]
1|15174|Loss: 0.8339503407478333:  59%|█████▊    | 15174/25880 [3:06:46<2:03:08,  1.45it/s]
1|15175|Loss: 0.7425203919410706:  59%|█████▊    | 15174/25880 [3:06:46<2:03:08,  1.45it/s]
1|15175|Loss: 0.7425203919410706:  59%|█████▊    | 15175/25880 [3:06:47<1:57:55,  1.51it/s]
1|15176|Loss: 0.9704376459121704:  59%|█████▊    | 15175/25880 [3:06:47<1:57:55,  1.51it/s]
1|15176|Loss: 0.9704376459121704:  59%|█████▊    | 15176/25880 [3:06:47<1:55:39,  1.54it/s]
1|15177|Loss: 0.742715060710907:  59%|█████▊    | 15176/25880 [3:06:48<1:55:39,  1.54it/s] 
1|15177|Loss: 0.742715060710907:  59%|█████▊    | 15177/25880 [3:06:48<1:57:52,  1.51it/s]
1|15178|Loss: 0.7145842909812927:  59%|█████▊    | 15177/25880 [3:06:48<1:57:52,  1.51it/s]
1|15178|Loss: 0.7145842909812927:  59%|█████▊    | 15178/25880 [3:06:49<2:01:40,  1.47it/s]
1|15179|Loss: 0.8014466762542725:  59%|█████▊    | 15178/25880 [3:06:49<2:01:40,  1.47it/s]
1|15179|Loss: 0.8014466762542725:  59%|█████▊    | 15179/25880 [3:06:49<2:04:58,  1.43it/s]
1|15180|Loss: 0.8935216069221497:  59%|█████▊    | 15179/25880 [3:06:50<2:04:58,  1.43it/s]
1|15180|Loss: 0.8935216069221497:  59%|█████▊    | 15180/25880 [3:06:50<1:52:20,  1.59it/s]
1|15181|Loss: 0.8239615559577942:  59%|█████▊    | 15180/25880 [3:06:50<1:52:20,  1.59it/s]
1|15181|Loss: 0.8239615559577942:  59%|█████▊    | 15181/25880 [3:06:51<1:57:28,  1.52it/s]
1|15182|Loss: 0.8205469250679016:  59%|█████▊    | 15181/25880 [3:06:51<1:57:28,  1.52it/s]
1|15182|Loss: 0.8205469250679016:  59%|█████▊    | 15182/25880 [3:06:51<2:01:56,  1.46it/s]
1|15183|Loss: 0.8718003630638123:  59%|█████▊    | 15182/25880 [3:06:52<2:01:56,  1.46it/s]
1|15183|Loss: 0.8718003630638123:  59%|█████▊    | 15183/25880 [3:06:52<2:04:13,  1.44it/s]
1|15184|Loss: 0.8237957954406738:  59%|█████▊    | 15183/25880 [3:06:52<2:04:13,  1.44it/s]
1|15184|Loss: 0.8237957954406738:  59%|█████▊    | 15184/25880 [3:06:53<2:09:27,  1.38it/s]
1|15185|Loss: 0.8234708905220032:  59%|█████▊    | 15184/25880 [3:06:53<2:09:27,  1.38it/s]
1|15185|Loss: 0.8234708905220032:  59%|█████▊    | 15185/25880 [3:06:54<2:09:23,  1.38it/s]
1|15186|Loss: 0.876142680644989:  59%|█████▊    | 15185/25880 [3:06:54<2:09:23,  1.38it/s] 
1|15186|Loss: 0.876142680644989:  59%|█████▊    | 15186/25880 [3:06:54<2:17:14,  1.30it/s]
1|15187|Loss: 0.7825110554695129:  59%|█████▊    | 15186/25880 [3:06:55<2:17:14,  1.30it/s]
1|15187|Loss: 0.7825110554695129:  59%|█████▊    | 15187/25880 [3:06:55<2:15:27,  1.32it/s]
1|15188|Loss: 0.9167840480804443:  59%|█████▊    | 15187/25880 [3:06:55<2:15:27,  1.32it/s]
1|15188|Loss: 0.9167840480804443:  59%|█████▊    | 15188/25880 [3:06:56<2:06:49,  1.41it/s]
1|15189|Loss: 0.8937960863113403:  59%|█████▊    | 15188/25880 [3:06:56<2:06:49,  1.41it/s]
1|15189|Loss: 0.8937960863113403:  59%|█████▊    | 15189/25880 [3:06:56<2:05:58,  1.41it/s]
1|15190|Loss: 0.8943039178848267:  59%|█████▊    | 15189/25880 [3:06:57<2:05:58,  1.41it/s]
1|15190|Loss: 0.8943039178848267:  59%|█████▊    | 15190/25880 [3:06:57<2:03:23,  1.44it/s]
1|15191|Loss: 0.9391384720802307:  59%|█████▊    | 15190/25880 [3:06:57<2:03:23,  1.44it/s]
1|15191|Loss: 0.9391384720802307:  59%|█████▊    | 15191/25880 [3:06:58<1:57:02,  1.52it/s]
1|15192|Loss: 0.950404167175293:  59%|█████▊    | 15191/25880 [3:06:58<1:57:02,  1.52it/s] 
1|15192|Loss: 0.950404167175293:  59%|█████▊    | 15192/25880 [3:06:58<1:59:00,  1.50it/s]
1|15193|Loss: 0.7665392756462097:  59%|█████▊    | 15192/25880 [3:06:59<1:59:00,  1.50it/s]
1|15193|Loss: 0.7665392756462097:  59%|█████▊    | 15193/25880 [3:06:59<1:56:04,  1.53it/s]
1|15194|Loss: 0.9472305178642273:  59%|█████▊    | 15193/25880 [3:06:59<1:56:04,  1.53it/s]
1|15194|Loss: 0.9472305178642273:  59%|█████▊    | 15194/25880 [3:07:00<1:53:46,  1.57it/s]
1|15195|Loss: 0.895845353603363:  59%|█████▊    | 15194/25880 [3:07:00<1:53:46,  1.57it/s] 
1|15195|Loss: 0.895845353603363:  59%|█████▊    | 15195/25880 [3:07:00<1:58:06,  1.51it/s]
1|15196|Loss: 0.6260747313499451:  59%|█████▊    | 15195/25880 [3:07:01<1:58:06,  1.51it/s]
1|15196|Loss: 0.6260747313499451:  59%|█████▊    | 15196/25880 [3:07:01<2:14:15,  1.33it/s]
1|15197|Loss: 0.8676421046257019:  59%|█████▊    | 15196/25880 [3:07:02<2:14:15,  1.33it/s]
1|15197|Loss: 0.8676421046257019:  59%|█████▊    | 15197/25880 [3:07:02<2:17:23,  1.30it/s]
1|15198|Loss: 0.916195273399353:  59%|█████▊    | 15197/25880 [3:07:02<2:17:23,  1.30it/s] 
1|15198|Loss: 0.916195273399353:  59%|█████▊    | 15198/25880 [3:07:03<2:11:33,  1.35it/s]
1|15199|Loss: 0.9032120108604431:  59%|█████▊    | 15198/25880 [3:07:03<2:11:33,  1.35it/s]
1|15199|Loss: 0.9032120108604431:  59%|█████▊    | 15199/25880 [3:07:04<2:14:20,  1.33it/s]
1|15200|Loss: 0.8095081448554993:  59%|█████▊    | 15199/25880 [3:07:04<2:14:20,  1.33it/s]
1|15200|Loss: 0.8095081448554993:  59%|█████▊    | 15200/25880 [3:07:04<2:07:46,  1.39it/s]
1|15201|Loss: 0.953332245349884:  59%|█████▊    | 15200/25880 [3:07:05<2:07:46,  1.39it/s] 
1|15201|Loss: 0.953332245349884:  59%|█████▊    | 15201/25880 [3:07:05<2:14:30,  1.32it/s]
1|15202|Loss: 0.8812255263328552:  59%|█████▊    | 15201/25880 [3:07:05<2:14:30,  1.32it/s]
1|15202|Loss: 0.8812255263328552:  59%|█████▊    | 15202/25880 [3:07:06<2:10:14,  1.37it/s]
1|15203|Loss: 0.6435518860816956:  59%|█████▊    | 15202/25880 [3:07:06<2:10:14,  1.37it/s]
1|15203|Loss: 0.6435518860816956:  59%|█████▊    | 15203/25880 [3:07:07<2:19:19,  1.28it/s]
1|15204|Loss: 0.9067279100418091:  59%|█████▊    | 15203/25880 [3:07:07<2:19:19,  1.28it/s]
1|15204|Loss: 0.9067279100418091:  59%|█████▊    | 15204/25880 [3:07:07<2:19:34,  1.27it/s]
1|15205|Loss: 0.9484049081802368:  59%|█████▊    | 15204/25880 [3:07:08<2:19:34,  1.27it/s]
1|15205|Loss: 0.9484049081802368:  59%|█████▉    | 15205/25880 [3:07:08<2:16:53,  1.30it/s]
1|15206|Loss: 0.9510167241096497:  59%|█████▉    | 15205/25880 [3:07:09<2:16:53,  1.30it/s]
1|15206|Loss: 0.9510167241096497:  59%|█████▉    | 15206/25880 [3:07:09<2:15:18,  1.31it/s]
1|15207|Loss: 0.7826902270317078:  59%|█████▉    | 15206/25880 [3:07:09<2:15:18,  1.31it/s]
1|15207|Loss: 0.7826902270317078:  59%|█████▉    | 15207/25880 [3:07:10<2:14:09,  1.33it/s]
1|15208|Loss: 0.8745231032371521:  59%|█████▉    | 15207/25880 [3:07:10<2:14:09,  1.33it/s]
1|15208|Loss: 0.8745231032371521:  59%|█████▉    | 15208/25880 [3:07:10<2:16:48,  1.30it/s]
1|15209|Loss: 0.943009078502655:  59%|█████▉    | 15208/25880 [3:07:11<2:16:48,  1.30it/s] 
1|15209|Loss: 0.943009078502655:  59%|█████▉    | 15209/25880 [3:07:11<2:14:01,  1.33it/s]
1|15210|Loss: 0.9172482490539551:  59%|█████▉    | 15209/25880 [3:07:12<2:14:01,  1.33it/s]
1|15210|Loss: 0.9172482490539551:  59%|█████▉    | 15210/25880 [3:07:12<2:20:13,  1.27it/s]
1|15211|Loss: 0.7106944918632507:  59%|█████▉    | 15210/25880 [3:07:13<2:20:13,  1.27it/s]
1|15211|Loss: 0.7106944918632507:  59%|█████▉    | 15211/25880 [3:07:13<2:30:35,  1.18it/s]
1|15212|Loss: 0.8809650540351868:  59%|█████▉    | 15211/25880 [3:07:13<2:30:35,  1.18it/s]
1|15212|Loss: 0.8809650540351868:  59%|█████▉    | 15212/25880 [3:07:14<2:23:55,  1.24it/s]
1|15213|Loss: 0.8328929543495178:  59%|█████▉    | 15212/25880 [3:07:14<2:23:55,  1.24it/s]
1|15213|Loss: 0.8328929543495178:  59%|█████▉    | 15213/25880 [3:07:15<2:25:05,  1.23it/s]
1|15214|Loss: 0.8270913362503052:  59%|█████▉    | 15213/25880 [3:07:15<2:25:05,  1.23it/s]
1|15214|Loss: 0.8270913362503052:  59%|█████▉    | 15214/25880 [3:07:15<2:26:38,  1.21it/s]
1|15215|Loss: 0.8252339363098145:  59%|█████▉    | 15214/25880 [3:07:16<2:26:38,  1.21it/s]
1|15215|Loss: 0.8252339363098145:  59%|█████▉    | 15215/25880 [3:07:16<2:21:14,  1.26it/s]
1|15216|Loss: 0.9403579235076904:  59%|█████▉    | 15215/25880 [3:07:16<2:21:14,  1.26it/s]
1|15216|Loss: 0.9403579235076904:  59%|█████▉    | 15216/25880 [3:07:17<2:10:45,  1.36it/s]
1|15217|Loss: 0.964591383934021:  59%|█████▉    | 15216/25880 [3:07:17<2:10:45,  1.36it/s] 
1|15217|Loss: 0.964591383934021:  59%|█████▉    | 15217/25880 [3:07:17<2:07:39,  1.39it/s]
1|15218|Loss: 0.7878177762031555:  59%|█████▉    | 15217/25880 [3:07:18<2:07:39,  1.39it/s]
1|15218|Loss: 0.7878177762031555:  59%|█████▉    | 15218/25880 [3:07:18<1:56:09,  1.53it/s]
1|15219|Loss: 0.8411903977394104:  59%|█████▉    | 15218/25880 [3:07:18<1:56:09,  1.53it/s]
1|15219|Loss: 0.8411903977394104:  59%|█████▉    | 15219/25880 [3:07:18<1:42:28,  1.73it/s]
1|15220|Loss: 0.8683692812919617:  59%|█████▉    | 15219/25880 [3:07:19<1:42:28,  1.73it/s]
1|15220|Loss: 0.8683692812919617:  59%|█████▉    | 15220/25880 [3:07:19<1:41:39,  1.75it/s]
1|15221|Loss: 0.748303234577179:  59%|█████▉    | 15220/25880 [3:07:19<1:41:39,  1.75it/s] 
1|15221|Loss: 0.748303234577179:  59%|█████▉    | 15221/25880 [3:07:20<1:47:37,  1.65it/s]
1|15222|Loss: 0.941125214099884:  59%|█████▉    | 15221/25880 [3:07:20<1:47:37,  1.65it/s]
1|15222|Loss: 0.941125214099884:  59%|█████▉    | 15222/25880 [3:07:20<1:58:02,  1.50it/s]
1|15223|Loss: 0.8225212097167969:  59%|█████▉    | 15222/25880 [3:07:21<1:58:02,  1.50it/s]
1|15223|Loss: 0.8225212097167969:  59%|█████▉    | 15223/25880 [3:07:21<1:55:55,  1.53it/s]
1|15224|Loss: 0.7429162859916687:  59%|█████▉    | 15223/25880 [3:07:21<1:55:55,  1.53it/s]
1|15224|Loss: 0.7429162859916687:  59%|█████▉    | 15224/25880 [3:07:22<1:58:38,  1.50it/s]
1|15225|Loss: 0.8016820549964905:  59%|█████▉    | 15224/25880 [3:07:22<1:58:38,  1.50it/s]
1|15225|Loss: 0.8016820549964905:  59%|█████▉    | 15225/25880 [3:07:22<1:57:16,  1.51it/s]
1|15226|Loss: 0.7549829483032227:  59%|█████▉    | 15225/25880 [3:07:23<1:57:16,  1.51it/s]
1|15226|Loss: 0.7549829483032227:  59%|█████▉    | 15226/25880 [3:07:23<1:55:22,  1.54it/s]
1|15227|Loss: 0.8889880776405334:  59%|█████▉    | 15226/25880 [3:07:23<1:55:22,  1.54it/s]
1|15227|Loss: 0.8889880776405334:  59%|█████▉    | 15227/25880 [3:07:24<2:03:00,  1.44it/s]
1|15228|Loss: 0.8133759498596191:  59%|█████▉    | 15227/25880 [3:07:24<2:03:00,  1.44it/s]
1|15228|Loss: 0.8133759498596191:  59%|█████▉    | 15228/25880 [3:07:24<2:05:49,  1.41it/s]
1|15229|Loss: 0.8211477994918823:  59%|█████▉    | 15228/25880 [3:07:25<2:05:49,  1.41it/s]
1|15229|Loss: 0.8211477994918823:  59%|█████▉    | 15229/25880 [3:07:25<2:11:02,  1.35it/s]
1|15230|Loss: 0.8310616612434387:  59%|█████▉    | 15229/25880 [3:07:26<2:11:02,  1.35it/s]
1|15230|Loss: 0.8310616612434387:  59%|█████▉    | 15230/25880 [3:07:26<2:19:44,  1.27it/s]
1|15231|Loss: 1.0092819929122925:  59%|█████▉    | 15230/25880 [3:07:27<2:19:44,  1.27it/s]
1|15231|Loss: 1.0092819929122925:  59%|█████▉    | 15231/25880 [3:07:27<2:18:57,  1.28it/s]
1|15232|Loss: 0.8939951062202454:  59%|█████▉    | 15231/25880 [3:07:27<2:18:57,  1.28it/s]
1|15232|Loss: 0.8939951062202454:  59%|█████▉    | 15232/25880 [3:07:28<2:16:52,  1.30it/s]
1|15233|Loss: 0.7510781288146973:  59%|█████▉    | 15232/25880 [3:07:28<2:16:52,  1.30it/s]
1|15233|Loss: 0.7510781288146973:  59%|█████▉    | 15233/25880 [3:07:28<2:11:36,  1.35it/s]
1|15234|Loss: 0.8252525329589844:  59%|█████▉    | 15233/25880 [3:07:29<2:11:36,  1.35it/s]
1|15234|Loss: 0.8252525329589844:  59%|█████▉    | 15234/25880 [3:07:29<2:05:17,  1.42it/s]
1|15235|Loss: 1.0004804134368896:  59%|█████▉    | 15234/25880 [3:07:29<2:05:17,  1.42it/s]
1|15235|Loss: 1.0004804134368896:  59%|█████▉    | 15235/25880 [3:07:30<2:05:09,  1.42it/s]
1|15236|Loss: 0.797069251537323:  59%|█████▉    | 15235/25880 [3:07:30<2:05:09,  1.42it/s] 
1|15236|Loss: 0.797069251537323:  59%|█████▉    | 15236/25880 [3:07:30<2:02:54,  1.44it/s]
1|15237|Loss: 0.8777869343757629:  59%|█████▉    | 15236/25880 [3:07:31<2:02:54,  1.44it/s]
1|15237|Loss: 0.8777869343757629:  59%|█████▉    | 15237/25880 [3:07:31<2:06:31,  1.40it/s]
1|15238|Loss: 0.8337334990501404:  59%|█████▉    | 15237/25880 [3:07:32<2:06:31,  1.40it/s]
1|15238|Loss: 0.8337334990501404:  59%|█████▉    | 15238/25880 [3:07:32<2:08:35,  1.38it/s]
1|15239|Loss: 0.8182034492492676:  59%|█████▉    | 15238/25880 [3:07:32<2:08:35,  1.38it/s]
1|15239|Loss: 0.8182034492492676:  59%|█████▉    | 15239/25880 [3:07:33<2:09:27,  1.37it/s]
1|15240|Loss: 0.7878583669662476:  59%|█████▉    | 15239/25880 [3:07:33<2:09:27,  1.37it/s]
1|15240|Loss: 0.7878583669662476:  59%|█████▉    | 15240/25880 [3:07:33<2:04:54,  1.42it/s]
1|15241|Loss: 0.9076464176177979:  59%|█████▉    | 15240/25880 [3:07:34<2:04:54,  1.42it/s]
1|15241|Loss: 0.9076464176177979:  59%|█████▉    | 15241/25880 [3:07:34<2:10:05,  1.36it/s]
1|15242|Loss: 0.8203189373016357:  59%|█████▉    | 15241/25880 [3:07:34<2:10:05,  1.36it/s]
1|15242|Loss: 0.8203189373016357:  59%|█████▉    | 15242/25880 [3:07:35<2:11:23,  1.35it/s]
1|15243|Loss: 0.93818199634552:  59%|█████▉    | 15242/25880 [3:07:35<2:11:23,  1.35it/s]  
1|15243|Loss: 0.93818199634552:  59%|█████▉    | 15243/25880 [3:07:36<2:15:44,  1.31it/s]
1|15244|Loss: 0.9228902459144592:  59%|█████▉    | 15243/25880 [3:07:36<2:15:44,  1.31it/s]
1|15244|Loss: 0.9228902459144592:  59%|█████▉    | 15244/25880 [3:07:36<2:14:29,  1.32it/s]
1|15245|Loss: 0.820052981376648:  59%|█████▉    | 15244/25880 [3:07:37<2:14:29,  1.32it/s] 
1|15245|Loss: 0.820052981376648:  59%|█████▉    | 15245/25880 [3:07:37<2:12:32,  1.34it/s]
1|15246|Loss: 0.8405895233154297:  59%|█████▉    | 15245/25880 [3:07:37<2:12:32,  1.34it/s]
1|15246|Loss: 0.8405895233154297:  59%|█████▉    | 15246/25880 [3:07:38<2:12:17,  1.34it/s]
1|15247|Loss: 0.9232831597328186:  59%|█████▉    | 15246/25880 [3:07:38<2:12:17,  1.34it/s]
1|15247|Loss: 0.9232831597328186:  59%|█████▉    | 15247/25880 [3:07:39<2:21:42,  1.25it/s]
1|15248|Loss: 0.817091166973114:  59%|█████▉    | 15247/25880 [3:07:39<2:21:42,  1.25it/s] 
1|15248|Loss: 0.817091166973114:  59%|█████▉    | 15248/25880 [3:07:39<2:14:49,  1.31it/s]
1|15249|Loss: 0.8656628727912903:  59%|█████▉    | 15248/25880 [3:07:40<2:14:49,  1.31it/s]
1|15249|Loss: 0.8656628727912903:  59%|█████▉    | 15249/25880 [3:07:40<2:11:19,  1.35it/s]
1|15250|Loss: 0.9226067066192627:  59%|█████▉    | 15249/25880 [3:07:41<2:11:19,  1.35it/s]
1|15250|Loss: 0.9226067066192627:  59%|█████▉    | 15250/25880 [3:07:41<2:10:20,  1.36it/s]
1|15251|Loss: 0.8431379199028015:  59%|█████▉    | 15250/25880 [3:07:41<2:10:20,  1.36it/s]
1|15251|Loss: 0.8431379199028015:  59%|█████▉    | 15251/25880 [3:07:42<2:13:02,  1.33it/s]
1|15252|Loss: 0.865816593170166:  59%|█████▉    | 15251/25880 [3:07:42<2:13:02,  1.33it/s] 
1|15252|Loss: 0.865816593170166:  59%|█████▉    | 15252/25880 [3:07:42<2:12:45,  1.33it/s]
1|15253|Loss: 0.88557368516922:  59%|█████▉    | 15252/25880 [3:07:43<2:12:45,  1.33it/s] 
1|15253|Loss: 0.88557368516922:  59%|█████▉    | 15253/25880 [3:07:43<2:06:31,  1.40it/s]
1|15254|Loss: 0.9404980540275574:  59%|█████▉    | 15253/25880 [3:07:43<2:06:31,  1.40it/s]
1|15254|Loss: 0.9404980540275574:  59%|█████▉    | 15254/25880 [3:07:44<2:08:39,  1.38it/s]
1|15255|Loss: 0.8118737936019897:  59%|█████▉    | 15254/25880 [3:07:44<2:08:39,  1.38it/s]
1|15255|Loss: 0.8118737936019897:  59%|█████▉    | 15255/25880 [3:07:45<2:19:25,  1.27it/s]
1|15256|Loss: 0.9717440605163574:  59%|█████▉    | 15255/25880 [3:07:45<2:19:25,  1.27it/s]
1|15256|Loss: 0.9717440605163574:  59%|█████▉    | 15256/25880 [3:07:46<2:21:27,  1.25it/s]
1|15257|Loss: 0.8443252444267273:  59%|█████▉    | 15256/25880 [3:07:46<2:21:27,  1.25it/s]
1|15257|Loss: 0.8443252444267273:  59%|█████▉    | 15257/25880 [3:07:46<2:18:32,  1.28it/s]
1|15258|Loss: 0.8750527501106262:  59%|█████▉    | 15257/25880 [3:07:47<2:18:32,  1.28it/s]
1|15258|Loss: 0.8750527501106262:  59%|█████▉    | 15258/25880 [3:07:47<2:14:17,  1.32it/s]
1|15259|Loss: 0.8685845732688904:  59%|█████▉    | 15258/25880 [3:07:47<2:14:17,  1.32it/s]
1|15259|Loss: 0.8685845732688904:  59%|█████▉    | 15259/25880 [3:07:48<2:18:18,  1.28it/s]
1|15260|Loss: 0.9458661079406738:  59%|█████▉    | 15259/25880 [3:07:48<2:18:18,  1.28it/s]
1|15260|Loss: 0.9458661079406738:  59%|█████▉    | 15260/25880 [3:07:49<2:17:50,  1.28it/s]
1|15261|Loss: 0.8681407570838928:  59%|█████▉    | 15260/25880 [3:07:49<2:17:50,  1.28it/s]
1|15261|Loss: 0.8681407570838928:  59%|█████▉    | 15261/25880 [3:07:49<2:15:35,  1.31it/s]
1|15262|Loss: 0.8081881999969482:  59%|█████▉    | 15261/25880 [3:07:50<2:15:35,  1.31it/s]
1|15262|Loss: 0.8081881999969482:  59%|█████▉    | 15262/25880 [3:07:50<2:21:21,  1.25it/s]
1|15263|Loss: 0.9035263061523438:  59%|█████▉    | 15262/25880 [3:07:51<2:21:21,  1.25it/s]
1|15263|Loss: 0.9035263061523438:  59%|█████▉    | 15263/25880 [3:07:51<2:13:42,  1.32it/s]
1|15264|Loss: 0.7407586574554443:  59%|█████▉    | 15263/25880 [3:07:51<2:13:42,  1.32it/s]
1|15264|Loss: 0.7407586574554443:  59%|█████▉    | 15264/25880 [3:07:52<2:13:01,  1.33it/s]
1|15265|Loss: 0.740882396697998:  59%|█████▉    | 15264/25880 [3:07:52<2:13:01,  1.33it/s] 
1|15265|Loss: 0.740882396697998:  59%|█████▉    | 15265/25880 [3:07:52<2:13:02,  1.33it/s]
1|15266|Loss: 0.903826117515564:  59%|█████▉    | 15265/25880 [3:07:53<2:13:02,  1.33it/s]
1|15266|Loss: 0.903826117515564:  59%|█████▉    | 15266/25880 [3:07:53<2:12:46,  1.33it/s]
1|15267|Loss: 0.7757773399353027:  59%|█████▉    | 15266/25880 [3:07:53<2:12:46,  1.33it/s]
1|15267|Loss: 0.7757773399353027:  59%|█████▉    | 15267/25880 [3:07:54<2:02:28,  1.44it/s]
1|15268|Loss: 0.766593873500824:  59%|█████▉    | 15267/25880 [3:07:54<2:02:28,  1.44it/s] 
1|15268|Loss: 0.766593873500824:  59%|█████▉    | 15268/25880 [3:07:54<2:06:09,  1.40it/s]
1|15269|Loss: 0.7599694728851318:  59%|█████▉    | 15268/25880 [3:07:55<2:06:09,  1.40it/s]
1|15269|Loss: 0.7599694728851318:  59%|█████▉    | 15269/25880 [3:07:55<2:07:48,  1.38it/s]
1|15270|Loss: 0.8028300404548645:  59%|█████▉    | 15269/25880 [3:07:56<2:07:48,  1.38it/s]
1|15270|Loss: 0.8028300404548645:  59%|█████▉    | 15270/25880 [3:07:56<2:08:06,  1.38it/s]
1|15271|Loss: 0.8928823471069336:  59%|█████▉    | 15270/25880 [3:07:56<2:08:06,  1.38it/s]
1|15271|Loss: 0.8928823471069336:  59%|█████▉    | 15271/25880 [3:07:57<2:12:35,  1.33it/s]
1|15272|Loss: 0.8382652997970581:  59%|█████▉    | 15271/25880 [3:07:57<2:12:35,  1.33it/s]
1|15272|Loss: 0.8382652997970581:  59%|█████▉    | 15272/25880 [3:07:57<2:11:24,  1.35it/s]
1|15273|Loss: 0.817760705947876:  59%|█████▉    | 15272/25880 [3:07:58<2:11:24,  1.35it/s] 
1|15273|Loss: 0.817760705947876:  59%|█████▉    | 15273/25880 [3:07:58<2:10:42,  1.35it/s]
1|15274|Loss: 0.7999346256256104:  59%|█████▉    | 15273/25880 [3:07:59<2:10:42,  1.35it/s]
1|15274|Loss: 0.7999346256256104:  59%|█████▉    | 15274/25880 [3:07:59<2:03:55,  1.43it/s]
1|15275|Loss: 0.8159962892532349:  59%|█████▉    | 15274/25880 [3:07:59<2:03:55,  1.43it/s]
1|15275|Loss: 0.8159962892532349:  59%|█████▉    | 15275/25880 [3:07:59<1:59:56,  1.47it/s]
1|15276|Loss: 0.9242108464241028:  59%|█████▉    | 15275/25880 [3:08:00<1:59:56,  1.47it/s]
1|15276|Loss: 0.9242108464241028:  59%|█████▉    | 15276/25880 [3:08:00<1:58:13,  1.49it/s]
1|15277|Loss: 0.8819819092750549:  59%|█████▉    | 15276/25880 [3:08:00<1:58:13,  1.49it/s]
1|15277|Loss: 0.8819819092750549:  59%|█████▉    | 15277/25880 [3:08:01<1:59:37,  1.48it/s]
1|15278|Loss: 0.9078119397163391:  59%|█████▉    | 15277/25880 [3:08:01<1:59:37,  1.48it/s]
1|15278|Loss: 0.9078119397163391:  59%|█████▉    | 15278/25880 [3:08:01<2:01:52,  1.45it/s]
1|15279|Loss: 0.7867583632469177:  59%|█████▉    | 15278/25880 [3:08:02<2:01:52,  1.45it/s]
1|15279|Loss: 0.7867583632469177:  59%|█████▉    | 15279/25880 [3:08:02<2:11:45,  1.34it/s]
1|15280|Loss: 1.0215849876403809:  59%|█████▉    | 15279/25880 [3:08:03<2:11:45,  1.34it/s]
1|15280|Loss: 1.0215849876403809:  59%|█████▉    | 15280/25880 [3:08:03<2:15:51,  1.30it/s]
1|15281|Loss: 0.8308610916137695:  59%|█████▉    | 15280/25880 [3:08:04<2:15:51,  1.30it/s]
1|15281|Loss: 0.8308610916137695:  59%|█████▉    | 15281/25880 [3:08:04<2:14:59,  1.31it/s]
1|15282|Loss: 0.7525050044059753:  59%|█████▉    | 15281/25880 [3:08:04<2:14:59,  1.31it/s]
1|15282|Loss: 0.7525050044059753:  59%|█████▉    | 15282/25880 [3:08:05<2:08:22,  1.38it/s]
1|15283|Loss: 0.9700977206230164:  59%|█████▉    | 15282/25880 [3:08:05<2:08:22,  1.38it/s]
1|15283|Loss: 0.9700977206230164:  59%|█████▉    | 15283/25880 [3:08:05<2:13:01,  1.33it/s]
1|15284|Loss: 0.8307787179946899:  59%|█████▉    | 15283/25880 [3:08:06<2:13:01,  1.33it/s]
1|15284|Loss: 0.8307787179946899:  59%|█████▉    | 15284/25880 [3:08:06<2:17:38,  1.28it/s]
1|15285|Loss: 0.8206716775894165:  59%|█████▉    | 15284/25880 [3:08:07<2:17:38,  1.28it/s]
1|15285|Loss: 0.8206716775894165:  59%|█████▉    | 15285/25880 [3:08:07<2:11:54,  1.34it/s]
1|15286|Loss: 0.7988556623458862:  59%|█████▉    | 15285/25880 [3:08:07<2:11:54,  1.34it/s]
1|15286|Loss: 0.7988556623458862:  59%|█████▉    | 15286/25880 [3:08:08<2:08:35,  1.37it/s]
1|15287|Loss: 0.8709103465080261:  59%|█████▉    | 15286/25880 [3:08:08<2:08:35,  1.37it/s]
1|15287|Loss: 0.8709103465080261:  59%|█████▉    | 15287/25880 [3:08:08<2:08:00,  1.38it/s]
1|15288|Loss: 0.885770320892334:  59%|█████▉    | 15287/25880 [3:08:09<2:08:00,  1.38it/s] 
1|15288|Loss: 0.885770320892334:  59%|█████▉    | 15288/25880 [3:08:09<2:04:25,  1.42it/s]
1|15289|Loss: 0.8409269452095032:  59%|█████▉    | 15288/25880 [3:08:09<2:04:25,  1.42it/s]
1|15289|Loss: 0.8409269452095032:  59%|█████▉    | 15289/25880 [3:08:10<2:10:10,  1.36it/s]
1|15290|Loss: 0.8157032132148743:  59%|█████▉    | 15289/25880 [3:08:10<2:10:10,  1.36it/s]
1|15290|Loss: 0.8157032132148743:  59%|█████▉    | 15290/25880 [3:08:11<2:14:25,  1.31it/s]
1|15291|Loss: 1.0809623003005981:  59%|█████▉    | 15290/25880 [3:08:11<2:14:25,  1.31it/s]
1|15291|Loss: 1.0809623003005981:  59%|█████▉    | 15291/25880 [3:08:11<2:07:14,  1.39it/s]
1|15292|Loss: 0.8570937514305115:  59%|█████▉    | 15291/25880 [3:08:12<2:07:14,  1.39it/s]
1|15292|Loss: 0.8570937514305115:  59%|█████▉    | 15292/25880 [3:08:12<2:11:03,  1.35it/s]
1|15293|Loss: 0.7941255569458008:  59%|█████▉    | 15292/25880 [3:08:12<2:11:03,  1.35it/s]
1|15293|Loss: 0.7941255569458008:  59%|█████▉    | 15293/25880 [3:08:13<2:07:05,  1.39it/s]
1|15294|Loss: 0.7794343829154968:  59%|█████▉    | 15293/25880 [3:08:13<2:07:05,  1.39it/s]
1|15294|Loss: 0.7794343829154968:  59%|█████▉    | 15294/25880 [3:08:13<2:06:49,  1.39it/s]
1|15295|Loss: 0.7915483117103577:  59%|█████▉    | 15294/25880 [3:08:14<2:06:49,  1.39it/s]
1|15295|Loss: 0.7915483117103577:  59%|█████▉    | 15295/25880 [3:08:14<2:14:12,  1.31it/s]
1|15296|Loss: 0.8033232092857361:  59%|█████▉    | 15295/25880 [3:08:15<2:14:12,  1.31it/s]
1|15296|Loss: 0.8033232092857361:  59%|█████▉    | 15296/25880 [3:08:15<2:14:35,  1.31it/s]
1|15297|Loss: 0.9066464900970459:  59%|█████▉    | 15296/25880 [3:08:15<2:14:35,  1.31it/s]
1|15297|Loss: 0.9066464900970459:  59%|█████▉    | 15297/25880 [3:08:15<2:00:48,  1.46it/s]
1|15298|Loss: 0.7416099309921265:  59%|█████▉    | 15297/25880 [3:08:16<2:00:48,  1.46it/s]
1|15298|Loss: 0.7416099309921265:  59%|█████▉    | 15298/25880 [3:08:16<2:04:32,  1.42it/s]
1|15299|Loss: 0.7172382473945618:  59%|█████▉    | 15298/25880 [3:08:17<2:04:32,  1.42it/s]
1|15299|Loss: 0.7172382473945618:  59%|█████▉    | 15299/25880 [3:08:17<2:07:31,  1.38it/s]
1|15300|Loss: 0.8135636448860168:  59%|█████▉    | 15299/25880 [3:08:17<2:07:31,  1.38it/s]
1|15300|Loss: 0.8135636448860168:  59%|█████▉    | 15300/25880 [3:08:18<2:08:08,  1.38it/s]
1|15301|Loss: 0.8221145272254944:  59%|█████▉    | 15300/25880 [3:08:18<2:08:08,  1.38it/s]
1|15301|Loss: 0.8221145272254944:  59%|█████▉    | 15301/25880 [3:08:18<2:03:08,  1.43it/s]
1|15302|Loss: 0.7251331806182861:  59%|█████▉    | 15301/25880 [3:08:19<2:03:08,  1.43it/s]
1|15302|Loss: 0.7251331806182861:  59%|█████▉    | 15302/25880 [3:08:19<1:59:31,  1.48it/s]
1|15303|Loss: 0.8899940252304077:  59%|█████▉    | 15302/25880 [3:08:19<1:59:31,  1.48it/s]
1|15303|Loss: 0.8899940252304077:  59%|█████▉    | 15303/25880 [3:08:20<2:02:00,  1.44it/s]
1|15304|Loss: 0.9422622919082642:  59%|█████▉    | 15303/25880 [3:08:20<2:02:00,  1.44it/s]
1|15304|Loss: 0.9422622919082642:  59%|█████▉    | 15304/25880 [3:08:20<1:59:46,  1.47it/s]
1|15305|Loss: 0.8473662734031677:  59%|█████▉    | 15304/25880 [3:08:21<1:59:46,  1.47it/s]
1|15305|Loss: 0.8473662734031677:  59%|█████▉    | 15305/25880 [3:08:21<1:56:32,  1.51it/s]
1|15306|Loss: 0.8072436451911926:  59%|█████▉    | 15305/25880 [3:08:21<1:56:32,  1.51it/s]
1|15306|Loss: 0.8072436451911926:  59%|█████▉    | 15306/25880 [3:08:22<2:03:26,  1.43it/s]
1|15307|Loss: 0.8484494090080261:  59%|█████▉    | 15306/25880 [3:08:22<2:03:26,  1.43it/s]
1|15307|Loss: 0.8484494090080261:  59%|█████▉    | 15307/25880 [3:08:22<2:01:39,  1.45it/s]
1|15308|Loss: 0.7700470089912415:  59%|█████▉    | 15307/25880 [3:08:23<2:01:39,  1.45it/s]
1|15308|Loss: 0.7700470089912415:  59%|█████▉    | 15308/25880 [3:08:23<2:06:09,  1.40it/s]
1|15309|Loss: 0.9033735990524292:  59%|█████▉    | 15308/25880 [3:08:24<2:06:09,  1.40it/s]
1|15309|Loss: 0.9033735990524292:  59%|█████▉    | 15309/25880 [3:08:24<2:03:24,  1.43it/s]
1|15310|Loss: 0.8238306045532227:  59%|█████▉    | 15309/25880 [3:08:24<2:03:24,  1.43it/s]
1|15310|Loss: 0.8238306045532227:  59%|█████▉    | 15310/25880 [3:08:25<2:06:12,  1.40it/s]
1|15311|Loss: 0.8666908740997314:  59%|█████▉    | 15310/25880 [3:08:25<2:06:12,  1.40it/s]
1|15311|Loss: 0.8666908740997314:  59%|█████▉    | 15311/25880 [3:08:25<2:11:49,  1.34it/s]
1|15312|Loss: 0.8128329515457153:  59%|█████▉    | 15311/25880 [3:08:26<2:11:49,  1.34it/s]
1|15312|Loss: 0.8128329515457153:  59%|█████▉    | 15312/25880 [3:08:26<2:11:50,  1.34it/s]
1|15313|Loss: 0.8686766028404236:  59%|█████▉    | 15312/25880 [3:08:27<2:11:50,  1.34it/s]
1|15313|Loss: 0.8686766028404236:  59%|█████▉    | 15313/25880 [3:08:27<2:06:03,  1.40it/s]
1|15314|Loss: 0.7011550068855286:  59%|█████▉    | 15313/25880 [3:08:27<2:06:03,  1.40it/s]
1|15314|Loss: 0.7011550068855286:  59%|█████▉    | 15314/25880 [3:08:27<1:56:22,  1.51it/s]
1|15315|Loss: 0.6634181141853333:  59%|█████▉    | 15314/25880 [3:08:28<1:56:22,  1.51it/s]
1|15315|Loss: 0.6634181141853333:  59%|█████▉    | 15315/25880 [3:08:28<1:59:56,  1.47it/s]
1|15316|Loss: 0.8301994204521179:  59%|█████▉    | 15315/25880 [3:08:29<1:59:56,  1.47it/s]
1|15316|Loss: 0.8301994204521179:  59%|█████▉    | 15316/25880 [3:08:29<2:08:27,  1.37it/s]
1|15317|Loss: 0.8279776573181152:  59%|█████▉    | 15316/25880 [3:08:29<2:08:27,  1.37it/s]
1|15317|Loss: 0.8279776573181152:  59%|█████▉    | 15317/25880 [3:08:30<2:05:55,  1.40it/s]
1|15318|Loss: 0.7987315654754639:  59%|█████▉    | 15317/25880 [3:08:30<2:05:55,  1.40it/s]
1|15318|Loss: 0.7987315654754639:  59%|█████▉    | 15318/25880 [3:08:30<2:11:54,  1.33it/s]
1|15319|Loss: 0.8013467788696289:  59%|█████▉    | 15318/25880 [3:08:31<2:11:54,  1.33it/s]
1|15319|Loss: 0.8013467788696289:  59%|█████▉    | 15319/25880 [3:08:31<2:15:46,  1.30it/s]
1|15320|Loss: 0.784222424030304:  59%|█████▉    | 15319/25880 [3:08:32<2:15:46,  1.30it/s] 
1|15320|Loss: 0.784222424030304:  59%|█████▉    | 15320/25880 [3:08:32<2:18:40,  1.27it/s]
1|15321|Loss: 0.7912226319313049:  59%|█████▉    | 15320/25880 [3:08:32<2:18:40,  1.27it/s]
1|15321|Loss: 0.7912226319313049:  59%|█████▉    | 15321/25880 [3:08:33<2:10:45,  1.35it/s]
1|15322|Loss: 0.8436256051063538:  59%|█████▉    | 15321/25880 [3:08:33<2:10:45,  1.35it/s]
1|15322|Loss: 0.8436256051063538:  59%|█████▉    | 15322/25880 [3:08:33<2:08:23,  1.37it/s]
1|15323|Loss: 0.9312485456466675:  59%|█████▉    | 15322/25880 [3:08:34<2:08:23,  1.37it/s]
1|15323|Loss: 0.9312485456466675:  59%|█████▉    | 15323/25880 [3:08:34<2:08:30,  1.37it/s]
1|15324|Loss: 0.8047653436660767:  59%|█████▉    | 15323/25880 [3:08:35<2:08:30,  1.37it/s]
1|15324|Loss: 0.8047653436660767:  59%|█████▉    | 15324/25880 [3:08:35<2:04:36,  1.41it/s]
1|15325|Loss: 0.8138695359230042:  59%|█████▉    | 15324/25880 [3:08:35<2:04:36,  1.41it/s]
1|15325|Loss: 0.8138695359230042:  59%|█████▉    | 15325/25880 [3:08:36<2:04:41,  1.41it/s]
1|15326|Loss: 0.7939457893371582:  59%|█████▉    | 15325/25880 [3:08:36<2:04:41,  1.41it/s]
1|15326|Loss: 0.7939457893371582:  59%|█████▉    | 15326/25880 [3:08:36<2:10:52,  1.34it/s]
1|15327|Loss: 0.8060780167579651:  59%|█████▉    | 15326/25880 [3:08:37<2:10:52,  1.34it/s]
1|15327|Loss: 0.8060780167579651:  59%|█████▉    | 15327/25880 [3:08:37<2:10:32,  1.35it/s]
1|15328|Loss: 0.7495245933532715:  59%|█████▉    | 15327/25880 [3:08:37<2:10:32,  1.35it/s]
1|15328|Loss: 0.7495245933532715:  59%|█████▉    | 15328/25880 [3:08:38<2:04:41,  1.41it/s]
1|15329|Loss: 0.8152897953987122:  59%|█████▉    | 15328/25880 [3:08:38<2:04:41,  1.41it/s]
1|15329|Loss: 0.8152897953987122:  59%|█████▉    | 15329/25880 [3:08:38<2:00:36,  1.46it/s]
1|15330|Loss: 0.7954274415969849:  59%|█████▉    | 15329/25880 [3:08:39<2:00:36,  1.46it/s]
1|15330|Loss: 0.7954274415969849:  59%|█████▉    | 15330/25880 [3:08:39<2:01:52,  1.44it/s]
1|15331|Loss: 0.8315415978431702:  59%|█████▉    | 15330/25880 [3:08:40<2:01:52,  1.44it/s]
1|15331|Loss: 0.8315415978431702:  59%|█████▉    | 15331/25880 [3:08:40<2:06:44,  1.39it/s]
1|15332|Loss: 0.7847908139228821:  59%|█████▉    | 15331/25880 [3:08:40<2:06:44,  1.39it/s]
1|15332|Loss: 0.7847908139228821:  59%|█████▉    | 15332/25880 [3:08:41<2:08:42,  1.37it/s]
1|15333|Loss: 0.8977258205413818:  59%|█████▉    | 15332/25880 [3:08:41<2:08:42,  1.37it/s]
1|15333|Loss: 0.8977258205413818:  59%|█████▉    | 15333/25880 [3:08:41<2:09:02,  1.36it/s]
1|15334|Loss: 0.9286772608757019:  59%|█████▉    | 15333/25880 [3:08:42<2:09:02,  1.36it/s]
1|15334|Loss: 0.9286772608757019:  59%|█████▉    | 15334/25880 [3:08:42<2:02:34,  1.43it/s]
1|15335|Loss: 0.8765763640403748:  59%|█████▉    | 15334/25880 [3:08:42<2:02:34,  1.43it/s]
1|15335|Loss: 0.8765763640403748:  59%|█████▉    | 15335/25880 [3:08:43<1:54:13,  1.54it/s]
1|15336|Loss: 0.7735475897789001:  59%|█████▉    | 15335/25880 [3:08:43<1:54:13,  1.54it/s]
1|15336|Loss: 0.7735475897789001:  59%|█████▉    | 15336/25880 [3:08:43<1:56:55,  1.50it/s]
1|15337|Loss: 0.7007066607475281:  59%|█████▉    | 15336/25880 [3:08:44<1:56:55,  1.50it/s]
1|15337|Loss: 0.7007066607475281:  59%|█████▉    | 15337/25880 [3:08:44<1:54:44,  1.53it/s]
1|15338|Loss: 0.8937000632286072:  59%|█████▉    | 15337/25880 [3:08:44<1:54:44,  1.53it/s]
1|15338|Loss: 0.8937000632286072:  59%|█████▉    | 15338/25880 [3:08:44<1:50:57,  1.58it/s]
1|15339|Loss: 0.8332236409187317:  59%|█████▉    | 15338/25880 [3:08:45<1:50:57,  1.58it/s]
1|15339|Loss: 0.8332236409187317:  59%|█████▉    | 15339/25880 [3:08:45<1:59:59,  1.46it/s]
1|15340|Loss: 0.7273067831993103:  59%|█████▉    | 15339/25880 [3:08:46<1:59:59,  1.46it/s]
1|15340|Loss: 0.7273067831993103:  59%|█████▉    | 15340/25880 [3:08:46<1:54:53,  1.53it/s]
1|15341|Loss: 0.7733080387115479:  59%|█████▉    | 15340/25880 [3:08:46<1:54:53,  1.53it/s]
1|15341|Loss: 0.7733080387115479:  59%|█████▉    | 15341/25880 [3:08:47<2:01:28,  1.45it/s]
1|15342|Loss: 0.7297756671905518:  59%|█████▉    | 15341/25880 [3:08:47<2:01:28,  1.45it/s]
1|15342|Loss: 0.7297756671905518:  59%|█████▉    | 15342/25880 [3:08:47<2:00:25,  1.46it/s]
1|15343|Loss: 0.8268154263496399:  59%|█████▉    | 15342/25880 [3:08:48<2:00:25,  1.46it/s]
1|15343|Loss: 0.8268154263496399:  59%|█████▉    | 15343/25880 [3:08:48<2:06:55,  1.38it/s]
1|15344|Loss: 0.7383034229278564:  59%|█████▉    | 15343/25880 [3:08:48<2:06:55,  1.38it/s]
1|15344|Loss: 0.7383034229278564:  59%|█████▉    | 15344/25880 [3:08:49<2:04:59,  1.40it/s]
1|15345|Loss: 0.8736075758934021:  59%|█████▉    | 15344/25880 [3:08:49<2:04:59,  1.40it/s]
1|15345|Loss: 0.8736075758934021:  59%|█████▉    | 15345/25880 [3:08:50<2:08:12,  1.37it/s]
1|15346|Loss: 0.8520480990409851:  59%|█████▉    | 15345/25880 [3:08:50<2:08:12,  1.37it/s]
1|15346|Loss: 0.8520480990409851:  59%|█████▉    | 15346/25880 [3:08:50<2:05:00,  1.40it/s]
1|15347|Loss: 0.8773353695869446:  59%|█████▉    | 15346/25880 [3:08:51<2:05:00,  1.40it/s]
1|15347|Loss: 0.8773353695869446:  59%|█████▉    | 15347/25880 [3:08:51<1:58:48,  1.48it/s]
1|15348|Loss: 0.7023081183433533:  59%|█████▉    | 15347/25880 [3:08:51<1:58:48,  1.48it/s]
1|15348|Loss: 0.7023081183433533:  59%|█████▉    | 15348/25880 [3:08:52<2:04:15,  1.41it/s]
1|15349|Loss: 0.8457013368606567:  59%|█████▉    | 15348/25880 [3:08:52<2:04:15,  1.41it/s]
1|15349|Loss: 0.8457013368606567:  59%|█████▉    | 15349/25880 [3:08:52<1:54:36,  1.53it/s]
1|15350|Loss: 0.8575555682182312:  59%|█████▉    | 15349/25880 [3:08:52<1:54:36,  1.53it/s]
1|15350|Loss: 0.8575555682182312:  59%|█████▉    | 15350/25880 [3:08:53<1:55:55,  1.51it/s]
1|15351|Loss: 0.8121394515037537:  59%|█████▉    | 15350/25880 [3:08:53<1:55:55,  1.51it/s]
1|15351|Loss: 0.8121394515037537:  59%|█████▉    | 15351/25880 [3:08:53<1:56:04,  1.51it/s]
1|15352|Loss: 0.836385190486908:  59%|█████▉    | 15351/25880 [3:08:54<1:56:04,  1.51it/s] 
1|15352|Loss: 0.836385190486908:  59%|█████▉    | 15352/25880 [3:08:54<1:54:03,  1.54it/s]
1|15353|Loss: 0.854731023311615:  59%|█████▉    | 15352/25880 [3:08:54<1:54:03,  1.54it/s]
1|15353|Loss: 0.854731023311615:  59%|█████▉    | 15353/25880 [3:08:55<1:53:18,  1.55it/s]
1|15354|Loss: 0.8146882057189941:  59%|█████▉    | 15353/25880 [3:08:55<1:53:18,  1.55it/s]
1|15354|Loss: 0.8146882057189941:  59%|█████▉    | 15354/25880 [3:08:55<1:59:10,  1.47it/s]
1|15355|Loss: 1.0024820566177368:  59%|█████▉    | 15354/25880 [3:08:56<1:59:10,  1.47it/s]
1|15355|Loss: 1.0024820566177368:  59%|█████▉    | 15355/25880 [3:08:56<2:03:09,  1.42it/s]
1|15356|Loss: 0.9668262004852295:  59%|█████▉    | 15355/25880 [3:08:57<2:03:09,  1.42it/s]
1|15356|Loss: 0.9668262004852295:  59%|█████▉    | 15356/25880 [3:08:57<1:53:18,  1.55it/s]
1|15357|Loss: 0.8215195536613464:  59%|█████▉    | 15356/25880 [3:08:57<1:53:18,  1.55it/s]
1|15357|Loss: 0.8215195536613464:  59%|█████▉    | 15357/25880 [3:08:57<1:56:49,  1.50it/s]
1|15358|Loss: 0.7067767977714539:  59%|█████▉    | 15357/25880 [3:08:58<1:56:49,  1.50it/s]
1|15358|Loss: 0.7067767977714539:  59%|█████▉    | 15358/25880 [3:08:58<1:59:53,  1.46it/s]
1|15359|Loss: 0.855981707572937:  59%|█████▉    | 15358/25880 [3:08:59<1:59:53,  1.46it/s] 
1|15359|Loss: 0.855981707572937:  59%|█████▉    | 15359/25880 [3:08:59<2:10:04,  1.35it/s]
1|15360|Loss: 0.7286689877510071:  59%|█████▉    | 15359/25880 [3:08:59<2:10:04,  1.35it/s]
1|15360|Loss: 0.7286689877510071:  59%|█████▉    | 15360/25880 [3:09:00<2:02:13,  1.43it/s]
1|15361|Loss: 0.7920784950256348:  59%|█████▉    | 15360/25880 [3:09:00<2:02:13,  1.43it/s]
1|15361|Loss: 0.7920784950256348:  59%|█████▉    | 15361/25880 [3:09:00<1:56:28,  1.51it/s]
1|15362|Loss: 0.9528599977493286:  59%|█████▉    | 15361/25880 [3:09:01<1:56:28,  1.51it/s]
1|15362|Loss: 0.9528599977493286:  59%|█████▉    | 15362/25880 [3:09:01<1:52:53,  1.55it/s]
1|15363|Loss: 0.7602992653846741:  59%|█████▉    | 15362/25880 [3:09:01<1:52:53,  1.55it/s]
1|15363|Loss: 0.7602992653846741:  59%|█████▉    | 15363/25880 [3:09:02<1:58:14,  1.48it/s]
1|15364|Loss: 0.7804903388023376:  59%|█████▉    | 15363/25880 [3:09:02<1:58:14,  1.48it/s]
1|15364|Loss: 0.7804903388023376:  59%|█████▉    | 15364/25880 [3:09:02<2:06:39,  1.38it/s]
1|15365|Loss: 0.909680187702179:  59%|█████▉    | 15364/25880 [3:09:03<2:06:39,  1.38it/s] 
1|15365|Loss: 0.909680187702179:  59%|█████▉    | 15365/25880 [3:09:03<2:14:39,  1.30it/s]
1|15366|Loss: 0.849677562713623:  59%|█████▉    | 15365/25880 [3:09:04<2:14:39,  1.30it/s]
1|15366|Loss: 0.849677562713623:  59%|█████▉    | 15366/25880 [3:09:04<2:16:58,  1.28it/s]
1|15367|Loss: 0.8296242356300354:  59%|█████▉    | 15366/25880 [3:09:04<2:16:58,  1.28it/s]
1|15367|Loss: 0.8296242356300354:  59%|█████▉    | 15367/25880 [3:09:05<2:06:35,  1.38it/s]
1|15368|Loss: 0.945797860622406:  59%|█████▉    | 15367/25880 [3:09:05<2:06:35,  1.38it/s] 
1|15368|Loss: 0.945797860622406:  59%|█████▉    | 15368/25880 [3:09:05<2:08:01,  1.37it/s]
1|15369|Loss: 0.8420937061309814:  59%|█████▉    | 15368/25880 [3:09:06<2:08:01,  1.37it/s]
1|15369|Loss: 0.8420937061309814:  59%|█████▉    | 15369/25880 [3:09:06<2:07:40,  1.37it/s]
1|15370|Loss: 0.7214437127113342:  59%|█████▉    | 15369/25880 [3:09:06<2:07:40,  1.37it/s]
1|15370|Loss: 0.7214437127113342:  59%|█████▉    | 15370/25880 [3:09:07<1:58:05,  1.48it/s]
1|15371|Loss: 0.8692578077316284:  59%|█████▉    | 15370/25880 [3:09:07<1:58:05,  1.48it/s]
1|15371|Loss: 0.8692578077316284:  59%|█████▉    | 15371/25880 [3:09:07<1:54:53,  1.52it/s]
1|15372|Loss: 0.8170785307884216:  59%|█████▉    | 15371/25880 [3:09:08<1:54:53,  1.52it/s]
1|15372|Loss: 0.8170785307884216:  59%|█████▉    | 15372/25880 [3:09:08<2:03:04,  1.42it/s]
1|15373|Loss: 0.7966565489768982:  59%|█████▉    | 15372/25880 [3:09:09<2:03:04,  1.42it/s]
1|15373|Loss: 0.7966565489768982:  59%|█████▉    | 15373/25880 [3:09:09<2:04:40,  1.40it/s]
1|15374|Loss: 0.777632474899292:  59%|█████▉    | 15373/25880 [3:09:09<2:04:40,  1.40it/s] 
1|15374|Loss: 0.777632474899292:  59%|█████▉    | 15374/25880 [3:09:09<1:55:44,  1.51it/s]
1|15375|Loss: 0.8696703910827637:  59%|█████▉    | 15374/25880 [3:09:10<1:55:44,  1.51it/s]
1|15375|Loss: 0.8696703910827637:  59%|█████▉    | 15375/25880 [3:09:10<2:04:40,  1.40it/s]
1|15376|Loss: 0.8983842730522156:  59%|█████▉    | 15375/25880 [3:09:11<2:04:40,  1.40it/s]
1|15376|Loss: 0.8983842730522156:  59%|█████▉    | 15376/25880 [3:09:11<2:07:45,  1.37it/s]
1|15377|Loss: 0.8180814385414124:  59%|█████▉    | 15376/25880 [3:09:11<2:07:45,  1.37it/s]
1|15377|Loss: 0.8180814385414124:  59%|█████▉    | 15377/25880 [3:09:12<2:08:04,  1.37it/s]
1|15378|Loss: 1.0813281536102295:  59%|█████▉    | 15377/25880 [3:09:12<2:08:04,  1.37it/s]
1|15378|Loss: 1.0813281536102295:  59%|█████▉    | 15378/25880 [3:09:12<2:04:01,  1.41it/s]
1|15379|Loss: 0.7668394446372986:  59%|█████▉    | 15378/25880 [3:09:13<2:04:01,  1.41it/s]
1|15379|Loss: 0.7668394446372986:  59%|█████▉    | 15379/25880 [3:09:13<2:00:31,  1.45it/s]
1|15380|Loss: 1.1216239929199219:  59%|█████▉    | 15379/25880 [3:09:13<2:00:31,  1.45it/s]
1|15380|Loss: 1.1216239929199219:  59%|█████▉    | 15380/25880 [3:09:14<2:06:58,  1.38it/s]
1|15381|Loss: 0.7854321002960205:  59%|█████▉    | 15380/25880 [3:09:14<2:06:58,  1.38it/s]
1|15381|Loss: 0.7854321002960205:  59%|█████▉    | 15381/25880 [3:09:15<2:14:44,  1.30it/s]
1|15382|Loss: 0.8571256399154663:  59%|█████▉    | 15381/25880 [3:09:15<2:14:44,  1.30it/s]
1|15382|Loss: 0.8571256399154663:  59%|█████▉    | 15382/25880 [3:09:16<2:16:39,  1.28it/s]
1|15383|Loss: 0.9086889624595642:  59%|█████▉    | 15382/25880 [3:09:16<2:16:39,  1.28it/s]
1|15383|Loss: 0.9086889624595642:  59%|█████▉    | 15383/25880 [3:09:16<2:05:56,  1.39it/s]
1|15384|Loss: 0.8078058958053589:  59%|█████▉    | 15383/25880 [3:09:16<2:05:56,  1.39it/s]
1|15384|Loss: 0.8078058958053589:  59%|█████▉    | 15384/25880 [3:09:17<2:02:54,  1.42it/s]
1|15385|Loss: 0.9559502601623535:  59%|█████▉    | 15384/25880 [3:09:17<2:02:54,  1.42it/s]
1|15385|Loss: 0.9559502601623535:  59%|█████▉    | 15385/25880 [3:09:17<1:58:15,  1.48it/s]
1|15386|Loss: 0.9654988050460815:  59%|█████▉    | 15385/25880 [3:09:18<1:58:15,  1.48it/s]
1|15386|Loss: 0.9654988050460815:  59%|█████▉    | 15386/25880 [3:09:18<1:58:17,  1.48it/s]
1|15387|Loss: 0.7830889821052551:  59%|█████▉    | 15386/25880 [3:09:18<1:58:17,  1.48it/s]
1|15387|Loss: 0.7830889821052551:  59%|█████▉    | 15387/25880 [3:09:19<2:06:02,  1.39it/s]
1|15388|Loss: 0.7115590572357178:  59%|█████▉    | 15387/25880 [3:09:19<2:06:02,  1.39it/s]
1|15388|Loss: 0.7115590572357178:  59%|█████▉    | 15388/25880 [3:09:20<2:14:15,  1.30it/s]
1|15389|Loss: 0.7318015098571777:  59%|█████▉    | 15388/25880 [3:09:20<2:14:15,  1.30it/s]
1|15389|Loss: 0.7318015098571777:  59%|█████▉    | 15389/25880 [3:09:20<2:10:30,  1.34it/s]
1|15390|Loss: 1.0884335041046143:  59%|█████▉    | 15389/25880 [3:09:21<2:10:30,  1.34it/s]
1|15390|Loss: 1.0884335041046143:  59%|█████▉    | 15390/25880 [3:09:21<1:58:30,  1.48it/s]
1|15391|Loss: 0.6990301609039307:  59%|█████▉    | 15390/25880 [3:09:21<1:58:30,  1.48it/s]
1|15391|Loss: 0.6990301609039307:  59%|█████▉    | 15391/25880 [3:09:22<2:03:28,  1.42it/s]
1|15392|Loss: 0.8229225277900696:  59%|█████▉    | 15391/25880 [3:09:22<2:03:28,  1.42it/s]
1|15392|Loss: 0.8229225277900696:  59%|█████▉    | 15392/25880 [3:09:22<2:05:31,  1.39it/s]
1|15393|Loss: 0.7788541316986084:  59%|█████▉    | 15392/25880 [3:09:23<2:05:31,  1.39it/s]
1|15393|Loss: 0.7788541316986084:  59%|█████▉    | 15393/25880 [3:09:23<2:06:08,  1.39it/s]
1|15394|Loss: 0.8744103908538818:  59%|█████▉    | 15393/25880 [3:09:24<2:06:08,  1.39it/s]
1|15394|Loss: 0.8744103908538818:  59%|█████▉    | 15394/25880 [3:09:24<2:05:33,  1.39it/s]
1|15395|Loss: 0.8505174517631531:  59%|█████▉    | 15394/25880 [3:09:24<2:05:33,  1.39it/s]
1|15395|Loss: 0.8505174517631531:  59%|█████▉    | 15395/25880 [3:09:25<2:09:51,  1.35it/s]
1|15396|Loss: 0.800660252571106:  59%|█████▉    | 15395/25880 [3:09:25<2:09:51,  1.35it/s] 
1|15396|Loss: 0.800660252571106:  59%|█████▉    | 15396/25880 [3:09:26<2:15:20,  1.29it/s]
1|15397|Loss: 0.7326590418815613:  59%|█████▉    | 15396/25880 [3:09:26<2:15:20,  1.29it/s]
1|15397|Loss: 0.7326590418815613:  59%|█████▉    | 15397/25880 [3:09:26<2:19:23,  1.25it/s]
1|15398|Loss: 0.8744987845420837:  59%|█████▉    | 15397/25880 [3:09:27<2:19:23,  1.25it/s]
1|15398|Loss: 0.8744987845420837:  59%|█████▉    | 15398/25880 [3:09:27<2:13:26,  1.31it/s]
1|15399|Loss: 0.9666393399238586:  59%|█████▉    | 15398/25880 [3:09:27<2:13:26,  1.31it/s]
1|15399|Loss: 0.9666393399238586:  60%|█████▉    | 15399/25880 [3:09:28<2:05:05,  1.40it/s]
1|15400|Loss: 0.7352171540260315:  60%|█████▉    | 15399/25880 [3:09:28<2:05:05,  1.40it/s]
1|15400|Loss: 0.7352171540260315:  60%|█████▉    | 15400/25880 [3:09:29<2:12:22,  1.32it/s]
1|15401|Loss: 0.8292257785797119:  60%|█████▉    | 15400/25880 [3:09:29<2:12:22,  1.32it/s]
1|15401|Loss: 0.8292257785797119:  60%|█████▉    | 15401/25880 [3:09:29<2:11:39,  1.33it/s]
1|15402|Loss: 0.8732134699821472:  60%|█████▉    | 15401/25880 [3:09:30<2:11:39,  1.33it/s]
1|15402|Loss: 0.8732134699821472:  60%|█████▉    | 15402/25880 [3:09:30<2:10:18,  1.34it/s]
1|15403|Loss: 0.7031473517417908:  60%|█████▉    | 15402/25880 [3:09:30<2:10:18,  1.34it/s]
1|15403|Loss: 0.7031473517417908:  60%|█████▉    | 15403/25880 [3:09:31<2:08:13,  1.36it/s]
1|15404|Loss: 0.9140598177909851:  60%|█████▉    | 15403/25880 [3:09:31<2:08:13,  1.36it/s]
1|15404|Loss: 0.9140598177909851:  60%|█████▉    | 15404/25880 [3:09:31<2:03:34,  1.41it/s]
1|15405|Loss: 0.8044041991233826:  60%|█████▉    | 15404/25880 [3:09:32<2:03:34,  1.41it/s]
1|15405|Loss: 0.8044041991233826:  60%|█████▉    | 15405/25880 [3:09:32<2:00:05,  1.45it/s]
1|15406|Loss: 0.7905352711677551:  60%|█████▉    | 15405/25880 [3:09:32<2:00:05,  1.45it/s]
1|15406|Loss: 0.7905352711677551:  60%|█████▉    | 15406/25880 [3:09:33<2:08:04,  1.36it/s]
1|15407|Loss: 0.803378701210022:  60%|█████▉    | 15406/25880 [3:09:33<2:08:04,  1.36it/s] 
1|15407|Loss: 0.803378701210022:  60%|█████▉    | 15407/25880 [3:09:34<2:16:25,  1.28it/s]
1|15408|Loss: 0.8102386593818665:  60%|█████▉    | 15407/25880 [3:09:34<2:16:25,  1.28it/s]
1|15408|Loss: 0.8102386593818665:  60%|█████▉    | 15408/25880 [3:09:35<2:18:03,  1.26it/s]
1|15409|Loss: 0.9496517777442932:  60%|█████▉    | 15408/25880 [3:09:35<2:18:03,  1.26it/s]
1|15409|Loss: 0.9496517777442932:  60%|█████▉    | 15409/25880 [3:09:35<2:20:45,  1.24it/s]
1|15410|Loss: 0.8357638716697693:  60%|█████▉    | 15409/25880 [3:09:36<2:20:45,  1.24it/s]
1|15410|Loss: 0.8357638716697693:  60%|█████▉    | 15410/25880 [3:09:36<2:22:36,  1.22it/s]
1|15411|Loss: 0.9041752219200134:  60%|█████▉    | 15410/25880 [3:09:37<2:22:36,  1.22it/s]
1|15411|Loss: 0.9041752219200134:  60%|█████▉    | 15411/25880 [3:09:37<2:18:15,  1.26it/s]
1|15412|Loss: 0.7847265005111694:  60%|█████▉    | 15411/25880 [3:09:37<2:18:15,  1.26it/s]
1|15412|Loss: 0.7847265005111694:  60%|█████▉    | 15412/25880 [3:09:38<2:16:49,  1.28it/s]
1|15413|Loss: 0.7253248691558838:  60%|█████▉    | 15412/25880 [3:09:38<2:16:49,  1.28it/s]
1|15413|Loss: 0.7253248691558838:  60%|█████▉    | 15413/25880 [3:09:39<2:14:38,  1.30it/s]
1|15414|Loss: 0.8310719132423401:  60%|█████▉    | 15413/25880 [3:09:39<2:14:38,  1.30it/s]
1|15414|Loss: 0.8310719132423401:  60%|█████▉    | 15414/25880 [3:09:39<2:12:39,  1.31it/s]
1|15415|Loss: 0.9221616983413696:  60%|█████▉    | 15414/25880 [3:09:40<2:12:39,  1.31it/s]
1|15415|Loss: 0.9221616983413696:  60%|█████▉    | 15415/25880 [3:09:40<2:06:43,  1.38it/s]
1|15416|Loss: 0.7616645097732544:  60%|█████▉    | 15415/25880 [3:09:40<2:06:43,  1.38it/s]
1|15416|Loss: 0.7616645097732544:  60%|█████▉    | 15416/25880 [3:09:41<2:05:46,  1.39it/s]
1|15417|Loss: 0.8501980900764465:  60%|█████▉    | 15416/25880 [3:09:41<2:05:46,  1.39it/s]
1|15417|Loss: 0.8501980900764465:  60%|█████▉    | 15417/25880 [3:09:41<2:11:34,  1.33it/s]
1|15418|Loss: 0.9734596610069275:  60%|█████▉    | 15417/25880 [3:09:42<2:11:34,  1.33it/s]
1|15418|Loss: 0.9734596610069275:  60%|█████▉    | 15418/25880 [3:09:42<2:14:56,  1.29it/s]
1|15419|Loss: 0.7858511805534363:  60%|█████▉    | 15418/25880 [3:09:43<2:14:56,  1.29it/s]
1|15419|Loss: 0.7858511805534363:  60%|█████▉    | 15419/25880 [3:09:43<2:16:22,  1.28it/s]
1|15420|Loss: 0.8044493198394775:  60%|█████▉    | 15419/25880 [3:09:43<2:16:22,  1.28it/s]
1|15420|Loss: 0.8044493198394775:  60%|█████▉    | 15420/25880 [3:09:44<2:10:37,  1.33it/s]
1|15421|Loss: 0.6605076193809509:  60%|█████▉    | 15420/25880 [3:09:44<2:10:37,  1.33it/s]
1|15421|Loss: 0.6605076193809509:  60%|█████▉    | 15421/25880 [3:09:45<2:11:45,  1.32it/s]
1|15422|Loss: 0.7980551719665527:  60%|█████▉    | 15421/25880 [3:09:45<2:11:45,  1.32it/s]
1|15422|Loss: 0.7980551719665527:  60%|█████▉    | 15422/25880 [3:09:45<2:07:40,  1.37it/s]
1|15423|Loss: 0.739413857460022:  60%|█████▉    | 15422/25880 [3:09:46<2:07:40,  1.37it/s] 
1|15423|Loss: 0.739413857460022:  60%|█████▉    | 15423/25880 [3:09:46<2:05:38,  1.39it/s]
1|15424|Loss: 0.8861336708068848:  60%|█████▉    | 15423/25880 [3:09:46<2:05:38,  1.39it/s]
1|15424|Loss: 0.8861336708068848:  60%|█████▉    | 15424/25880 [3:09:47<2:09:57,  1.34it/s]
1|15425|Loss: 0.8119962811470032:  60%|█████▉    | 15424/25880 [3:09:47<2:09:57,  1.34it/s]
1|15425|Loss: 0.8119962811470032:  60%|█████▉    | 15425/25880 [3:09:47<2:05:13,  1.39it/s]
1|15426|Loss: 0.6924967765808105:  60%|█████▉    | 15425/25880 [3:09:48<2:05:13,  1.39it/s]
1|15426|Loss: 0.6924967765808105:  60%|█████▉    | 15426/25880 [3:09:48<2:04:27,  1.40it/s]
1|15427|Loss: 0.854066014289856:  60%|█████▉    | 15426/25880 [3:09:48<2:04:27,  1.40it/s] 
1|15427|Loss: 0.854066014289856:  60%|█████▉    | 15427/25880 [3:09:49<2:05:02,  1.39it/s]
1|15428|Loss: 0.8484177589416504:  60%|█████▉    | 15427/25880 [3:09:49<2:05:02,  1.39it/s]
1|15428|Loss: 0.8484177589416504:  60%|█████▉    | 15428/25880 [3:09:50<2:06:07,  1.38it/s]
1|15429|Loss: 0.865257740020752:  60%|█████▉    | 15428/25880 [3:09:50<2:06:07,  1.38it/s] 
1|15429|Loss: 0.865257740020752:  60%|█████▉    | 15429/25880 [3:09:50<2:07:07,  1.37it/s]
1|15430|Loss: 0.7256401777267456:  60%|█████▉    | 15429/25880 [3:09:51<2:07:07,  1.37it/s]
1|15430|Loss: 0.7256401777267456:  60%|█████▉    | 15430/25880 [3:09:51<2:12:42,  1.31it/s]
1|15431|Loss: 0.8621520400047302:  60%|█████▉    | 15430/25880 [3:09:51<2:12:42,  1.31it/s]
1|15431|Loss: 0.8621520400047302:  60%|█████▉    | 15431/25880 [3:09:52<2:08:16,  1.36it/s]
1|15432|Loss: 0.8895197510719299:  60%|█████▉    | 15431/25880 [3:09:52<2:08:16,  1.36it/s]
1|15432|Loss: 0.8895197510719299:  60%|█████▉    | 15432/25880 [3:09:52<2:07:12,  1.37it/s]
1|15433|Loss: 0.8479952812194824:  60%|█████▉    | 15432/25880 [3:09:53<2:07:12,  1.37it/s]
1|15433|Loss: 0.8479952812194824:  60%|█████▉    | 15433/25880 [3:09:53<2:13:02,  1.31it/s]
1|15434|Loss: 0.8861438035964966:  60%|█████▉    | 15433/25880 [3:09:54<2:13:02,  1.31it/s]
1|15434|Loss: 0.8861438035964966:  60%|█████▉    | 15434/25880 [3:09:54<2:16:47,  1.27it/s]
1|15435|Loss: 0.729529082775116:  60%|█████▉    | 15434/25880 [3:09:55<2:16:47,  1.27it/s] 
1|15435|Loss: 0.729529082775116:  60%|█████▉    | 15435/25880 [3:09:55<2:03:07,  1.41it/s]
1|15436|Loss: 0.8523932695388794:  60%|█████▉    | 15435/25880 [3:09:55<2:03:07,  1.41it/s]
1|15436|Loss: 0.8523932695388794:  60%|█████▉    | 15436/25880 [3:09:55<2:08:34,  1.35it/s]
1|15437|Loss: 0.9871504902839661:  60%|█████▉    | 15436/25880 [3:09:56<2:08:34,  1.35it/s]
1|15437|Loss: 0.9871504902839661:  60%|█████▉    | 15437/25880 [3:09:56<2:08:45,  1.35it/s]
1|15438|Loss: 0.9058917164802551:  60%|█████▉    | 15437/25880 [3:09:57<2:08:45,  1.35it/s]
1|15438|Loss: 0.9058917164802551:  60%|█████▉    | 15438/25880 [3:09:57<2:13:45,  1.30it/s]
1|15439|Loss: 0.8520197868347168:  60%|█████▉    | 15438/25880 [3:09:58<2:13:45,  1.30it/s]
1|15439|Loss: 0.8520197868347168:  60%|█████▉    | 15439/25880 [3:09:58<2:17:53,  1.26it/s]
1|15440|Loss: 0.8377012014389038:  60%|█████▉    | 15439/25880 [3:09:58<2:17:53,  1.26it/s]
1|15440|Loss: 0.8377012014389038:  60%|█████▉    | 15440/25880 [3:09:59<2:15:52,  1.28it/s]
1|15441|Loss: 0.8277612328529358:  60%|█████▉    | 15440/25880 [3:09:59<2:15:52,  1.28it/s]
1|15441|Loss: 0.8277612328529358:  60%|█████▉    | 15441/25880 [3:09:59<2:13:19,  1.31it/s]
1|15442|Loss: 0.8263459205627441:  60%|█████▉    | 15441/25880 [3:10:00<2:13:19,  1.31it/s]
1|15442|Loss: 0.8263459205627441:  60%|█████▉    | 15442/25880 [3:10:00<2:21:18,  1.23it/s]
1|15443|Loss: 0.9528902769088745:  60%|█████▉    | 15442/25880 [3:10:01<2:21:18,  1.23it/s]
1|15443|Loss: 0.9528902769088745:  60%|█████▉    | 15443/25880 [3:10:01<2:18:21,  1.26it/s]
1|15444|Loss: 0.7686294317245483:  60%|█████▉    | 15443/25880 [3:10:02<2:18:21,  1.26it/s]
1|15444|Loss: 0.7686294317245483:  60%|█████▉    | 15444/25880 [3:10:02<2:19:36,  1.25it/s]
1|15445|Loss: 0.9467942118644714:  60%|█████▉    | 15444/25880 [3:10:02<2:19:36,  1.25it/s]
1|15445|Loss: 0.9467942118644714:  60%|█████▉    | 15445/25880 [3:10:03<2:27:11,  1.18it/s]
1|15446|Loss: 0.9475665092468262:  60%|█████▉    | 15445/25880 [3:10:03<2:27:11,  1.18it/s]
1|15446|Loss: 0.9475665092468262:  60%|█████▉    | 15446/25880 [3:10:04<2:23:47,  1.21it/s]
1|15447|Loss: 0.7609338164329529:  60%|█████▉    | 15446/25880 [3:10:04<2:23:47,  1.21it/s]
1|15447|Loss: 0.7609338164329529:  60%|█████▉    | 15447/25880 [3:10:04<2:11:23,  1.32it/s]
1|15448|Loss: 0.8735865354537964:  60%|█████▉    | 15447/25880 [3:10:05<2:11:23,  1.32it/s]
1|15448|Loss: 0.8735865354537964:  60%|█████▉    | 15448/25880 [3:10:05<2:07:56,  1.36it/s]
1|15449|Loss: 0.9012702107429504:  60%|█████▉    | 15448/25880 [3:10:05<2:07:56,  1.36it/s]
1|15449|Loss: 0.9012702107429504:  60%|█████▉    | 15449/25880 [3:10:05<1:59:05,  1.46it/s]
1|15450|Loss: 0.8438616991043091:  60%|█████▉    | 15449/25880 [3:10:06<1:59:05,  1.46it/s]
1|15450|Loss: 0.8438616991043091:  60%|█████▉    | 15450/25880 [3:10:06<2:02:21,  1.42it/s]
1|15451|Loss: 0.7594749331474304:  60%|█████▉    | 15450/25880 [3:10:07<2:02:21,  1.42it/s]
1|15451|Loss: 0.7594749331474304:  60%|█████▉    | 15451/25880 [3:10:07<2:14:23,  1.29it/s]
1|15452|Loss: 1.1145823001861572:  60%|█████▉    | 15451/25880 [3:10:08<2:14:23,  1.29it/s]
1|15452|Loss: 1.1145823001861572:  60%|█████▉    | 15452/25880 [3:10:08<2:14:05,  1.30it/s]
1|15453|Loss: 0.773676335811615:  60%|█████▉    | 15452/25880 [3:10:08<2:14:05,  1.30it/s] 
1|15453|Loss: 0.773676335811615:  60%|█████▉    | 15453/25880 [3:10:09<2:21:03,  1.23it/s]
1|15454|Loss: 0.8711878061294556:  60%|█████▉    | 15453/25880 [3:10:09<2:21:03,  1.23it/s]
1|15454|Loss: 0.8711878061294556:  60%|█████▉    | 15454/25880 [3:10:10<2:29:00,  1.17it/s]
1|15455|Loss: 0.9192546010017395:  60%|█████▉    | 15454/25880 [3:10:10<2:29:00,  1.17it/s]
1|15455|Loss: 0.9192546010017395:  60%|█████▉    | 15455/25880 [3:10:11<2:24:26,  1.20it/s]
1|15456|Loss: 0.8396616578102112:  60%|█████▉    | 15455/25880 [3:10:11<2:24:26,  1.20it/s]
1|15456|Loss: 0.8396616578102112:  60%|█████▉    | 15456/25880 [3:10:11<2:17:45,  1.26it/s]
1|15457|Loss: 0.9221134185791016:  60%|█████▉    | 15456/25880 [3:10:12<2:17:45,  1.26it/s]
1|15457|Loss: 0.9221134185791016:  60%|█████▉    | 15457/25880 [3:10:12<2:09:19,  1.34it/s]
1|15458|Loss: 0.7552890777587891:  60%|█████▉    | 15457/25880 [3:10:12<2:09:19,  1.34it/s]
1|15458|Loss: 0.7552890777587891:  60%|█████▉    | 15458/25880 [3:10:13<2:07:32,  1.36it/s]
1|15459|Loss: 0.7678612470626831:  60%|█████▉    | 15458/25880 [3:10:13<2:07:32,  1.36it/s]
1|15459|Loss: 0.7678612470626831:  60%|█████▉    | 15459/25880 [3:10:13<2:05:51,  1.38it/s]
1|15460|Loss: 0.8894343972206116:  60%|█████▉    | 15459/25880 [3:10:14<2:05:51,  1.38it/s]
1|15460|Loss: 0.8894343972206116:  60%|█████▉    | 15460/25880 [3:10:14<2:04:17,  1.40it/s]
1|15461|Loss: 0.8283586502075195:  60%|█████▉    | 15460/25880 [3:10:14<2:04:17,  1.40it/s]
1|15461|Loss: 0.8283586502075195:  60%|█████▉    | 15461/25880 [3:10:15<2:06:45,  1.37it/s]
1|15462|Loss: 0.8183084726333618:  60%|█████▉    | 15461/25880 [3:10:15<2:06:45,  1.37it/s]
1|15462|Loss: 0.8183084726333618:  60%|█████▉    | 15462/25880 [3:10:16<2:10:57,  1.33it/s]
1|15463|Loss: 0.8545771241188049:  60%|█████▉    | 15462/25880 [3:10:16<2:10:57,  1.33it/s]
1|15463|Loss: 0.8545771241188049:  60%|█████▉    | 15463/25880 [3:10:16<2:12:46,  1.31it/s]
1|15464|Loss: 0.8053273558616638:  60%|█████▉    | 15463/25880 [3:10:17<2:12:46,  1.31it/s]
1|15464|Loss: 0.8053273558616638:  60%|█████▉    | 15464/25880 [3:10:17<2:11:27,  1.32it/s]
1|15465|Loss: 0.733359158039093:  60%|█████▉    | 15464/25880 [3:10:18<2:11:27,  1.32it/s] 
1|15465|Loss: 0.733359158039093:  60%|█████▉    | 15465/25880 [3:10:18<2:08:45,  1.35it/s]
1|15466|Loss: 0.9422165751457214:  60%|█████▉    | 15465/25880 [3:10:18<2:08:45,  1.35it/s]
1|15466|Loss: 0.9422165751457214:  60%|█████▉    | 15466/25880 [3:10:18<1:56:15,  1.49it/s]
1|15467|Loss: 0.7707842588424683:  60%|█████▉    | 15466/25880 [3:10:19<1:56:15,  1.49it/s]
1|15467|Loss: 0.7707842588424683:  60%|█████▉    | 15467/25880 [3:10:19<1:55:57,  1.50it/s]
1|15468|Loss: 0.8264881372451782:  60%|█████▉    | 15467/25880 [3:10:19<1:55:57,  1.50it/s]
1|15468|Loss: 0.8264881372451782:  60%|█████▉    | 15468/25880 [3:10:20<1:59:58,  1.45it/s]
1|15469|Loss: 0.9047076106071472:  60%|█████▉    | 15468/25880 [3:10:20<1:59:58,  1.45it/s]
1|15469|Loss: 0.9047076106071472:  60%|█████▉    | 15469/25880 [3:10:20<2:02:18,  1.42it/s]
1|15470|Loss: 0.9245967864990234:  60%|█████▉    | 15469/25880 [3:10:21<2:02:18,  1.42it/s]
1|15470|Loss: 0.9245967864990234:  60%|█████▉    | 15470/25880 [3:10:21<2:03:26,  1.41it/s]
1|15471|Loss: 0.8480156660079956:  60%|█████▉    | 15470/25880 [3:10:22<2:03:26,  1.41it/s]
1|15471|Loss: 0.8480156660079956:  60%|█████▉    | 15471/25880 [3:10:22<2:12:21,  1.31it/s]
1|15472|Loss: 0.869537889957428:  60%|█████▉    | 15471/25880 [3:10:23<2:12:21,  1.31it/s] 
1|15472|Loss: 0.869537889957428:  60%|█████▉    | 15472/25880 [3:10:23<2:12:52,  1.31it/s]
1|15473|Loss: 0.6870502233505249:  60%|█████▉    | 15472/25880 [3:10:23<2:12:52,  1.31it/s]
1|15473|Loss: 0.6870502233505249:  60%|█████▉    | 15473/25880 [3:10:23<1:59:24,  1.45it/s]
1|15474|Loss: 0.9174501299858093:  60%|█████▉    | 15473/25880 [3:10:24<1:59:24,  1.45it/s]
1|15474|Loss: 0.9174501299858093:  60%|█████▉    | 15474/25880 [3:10:24<1:52:21,  1.54it/s]
1|15475|Loss: 0.8181353211402893:  60%|█████▉    | 15474/25880 [3:10:24<1:52:21,  1.54it/s]
1|15475|Loss: 0.8181353211402893:  60%|█████▉    | 15475/25880 [3:10:24<1:43:27,  1.68it/s]
1|15476|Loss: 0.7834234833717346:  60%|█████▉    | 15475/25880 [3:10:25<1:43:27,  1.68it/s]
1|15476|Loss: 0.7834234833717346:  60%|█████▉    | 15476/25880 [3:10:25<1:46:12,  1.63it/s]
1|15477|Loss: 0.8669201731681824:  60%|█████▉    | 15476/25880 [3:10:25<1:46:12,  1.63it/s]
1|15477|Loss: 0.8669201731681824:  60%|█████▉    | 15477/25880 [3:10:26<1:54:25,  1.52it/s]
1|15478|Loss: 0.7997722625732422:  60%|█████▉    | 15477/25880 [3:10:26<1:54:25,  1.52it/s]
1|15478|Loss: 0.7997722625732422:  60%|█████▉    | 15478/25880 [3:10:27<2:06:16,  1.37it/s]
1|15479|Loss: 0.8001627326011658:  60%|█████▉    | 15478/25880 [3:10:27<2:06:16,  1.37it/s]
1|15479|Loss: 0.8001627326011658:  60%|█████▉    | 15479/25880 [3:10:27<2:08:42,  1.35it/s]
1|15480|Loss: 0.8236321806907654:  60%|█████▉    | 15479/25880 [3:10:28<2:08:42,  1.35it/s]
1|15480|Loss: 0.8236321806907654:  60%|█████▉    | 15480/25880 [3:10:28<2:14:22,  1.29it/s]
1|15481|Loss: 0.9018194675445557:  60%|█████▉    | 15480/25880 [3:10:29<2:14:22,  1.29it/s]
1|15481|Loss: 0.9018194675445557:  60%|█████▉    | 15481/25880 [3:10:29<2:13:48,  1.30it/s]
1|15482|Loss: 0.7683354020118713:  60%|█████▉    | 15481/25880 [3:10:29<2:13:48,  1.30it/s]
1|15482|Loss: 0.7683354020118713:  60%|█████▉    | 15482/25880 [3:10:30<2:12:14,  1.31it/s]
1|15483|Loss: 0.7824717164039612:  60%|█████▉    | 15482/25880 [3:10:30<2:12:14,  1.31it/s]
1|15483|Loss: 0.7824717164039612:  60%|█████▉    | 15483/25880 [3:10:30<2:01:46,  1.42it/s]
1|15484|Loss: 0.8048326373100281:  60%|█████▉    | 15483/25880 [3:10:31<2:01:46,  1.42it/s]
1|15484|Loss: 0.8048326373100281:  60%|█████▉    | 15484/25880 [3:10:31<2:01:22,  1.43it/s]
1|15485|Loss: 0.8354280591011047:  60%|█████▉    | 15484/25880 [3:10:32<2:01:22,  1.43it/s]
1|15485|Loss: 0.8354280591011047:  60%|█████▉    | 15485/25880 [3:10:32<2:08:31,  1.35it/s]
1|15486|Loss: 0.8902326822280884:  60%|█████▉    | 15485/25880 [3:10:32<2:08:31,  1.35it/s]
1|15486|Loss: 0.8902326822280884:  60%|█████▉    | 15486/25880 [3:10:33<2:04:41,  1.39it/s]
1|15487|Loss: 0.7667918801307678:  60%|█████▉    | 15486/25880 [3:10:33<2:04:41,  1.39it/s]
1|15487|Loss: 0.7667918801307678:  60%|█████▉    | 15487/25880 [3:10:33<2:02:32,  1.41it/s]
1|15488|Loss: 0.6816662549972534:  60%|█████▉    | 15487/25880 [3:10:34<2:02:32,  1.41it/s]
1|15488|Loss: 0.6816662549972534:  60%|█████▉    | 15488/25880 [3:10:34<2:05:35,  1.38it/s]
1|15489|Loss: 0.830190896987915:  60%|█████▉    | 15488/25880 [3:10:34<2:05:35,  1.38it/s] 
1|15489|Loss: 0.830190896987915:  60%|█████▉    | 15489/25880 [3:10:35<2:07:04,  1.36it/s]
1|15490|Loss: 0.7921035289764404:  60%|█████▉    | 15489/25880 [3:10:35<2:07:04,  1.36it/s]
1|15490|Loss: 0.7921035289764404:  60%|█████▉    | 15490/25880 [3:10:36<2:05:57,  1.37it/s]
1|15491|Loss: 0.7822780013084412:  60%|█████▉    | 15490/25880 [3:10:36<2:05:57,  1.37it/s]
1|15491|Loss: 0.7822780013084412:  60%|█████▉    | 15491/25880 [3:10:36<2:05:42,  1.38it/s]
1|15492|Loss: 0.7463630437850952:  60%|█████▉    | 15491/25880 [3:10:37<2:05:42,  1.38it/s]
1|15492|Loss: 0.7463630437850952:  60%|█████▉    | 15492/25880 [3:10:37<1:59:25,  1.45it/s]
1|15493|Loss: 0.7512381672859192:  60%|█████▉    | 15492/25880 [3:10:37<1:59:25,  1.45it/s]
1|15493|Loss: 0.7512381672859192:  60%|█████▉    | 15493/25880 [3:10:38<2:03:50,  1.40it/s]
1|15494|Loss: 0.8797783255577087:  60%|█████▉    | 15493/25880 [3:10:38<2:03:50,  1.40it/s]
1|15494|Loss: 0.8797783255577087:  60%|█████▉    | 15494/25880 [3:10:38<2:05:29,  1.38it/s]
1|15495|Loss: 0.8889060616493225:  60%|█████▉    | 15494/25880 [3:10:39<2:05:29,  1.38it/s]
1|15495|Loss: 0.8889060616493225:  60%|█████▉    | 15495/25880 [3:10:39<2:04:18,  1.39it/s]
1|15496|Loss: 0.8349127173423767:  60%|█████▉    | 15495/25880 [3:10:39<2:04:18,  1.39it/s]
1|15496|Loss: 0.8349127173423767:  60%|█████▉    | 15496/25880 [3:10:40<2:03:18,  1.40it/s]
1|15497|Loss: 0.918157696723938:  60%|█████▉    | 15496/25880 [3:10:40<2:03:18,  1.40it/s] 
1|15497|Loss: 0.918157696723938:  60%|█████▉    | 15497/25880 [3:10:40<2:03:51,  1.40it/s]
1|15498|Loss: 0.7672715783119202:  60%|█████▉    | 15497/25880 [3:10:41<2:03:51,  1.40it/s]
1|15498|Loss: 0.7672715783119202:  60%|█████▉    | 15498/25880 [3:10:41<2:03:33,  1.40it/s]
1|15499|Loss: 0.786162793636322:  60%|█████▉    | 15498/25880 [3:10:42<2:03:33,  1.40it/s] 
1|15499|Loss: 0.786162793636322:  60%|█████▉    | 15499/25880 [3:10:42<2:02:50,  1.41it/s]
1|15500|Loss: 0.700065016746521:  60%|█████▉    | 15499/25880 [3:10:42<2:02:50,  1.41it/s]
1|15500|Loss: 0.700065016746521:  60%|█████▉    | 15500/25880 [3:10:43<1:59:01,  1.45it/s]
1|15501|Loss: 0.8698196411132812:  60%|█████▉    | 15500/25880 [3:10:43<1:59:01,  1.45it/s]
1|15501|Loss: 0.8698196411132812:  60%|█████▉    | 15501/25880 [3:10:43<2:04:06,  1.39it/s]
1|15502|Loss: 0.925724446773529:  60%|█████▉    | 15501/25880 [3:10:44<2:04:06,  1.39it/s] 
1|15502|Loss: 0.925724446773529:  60%|█████▉    | 15502/25880 [3:10:44<2:01:59,  1.42it/s]
1|15503|Loss: 0.7971977591514587:  60%|█████▉    | 15502/25880 [3:10:44<2:01:59,  1.42it/s]
1|15503|Loss: 0.7971977591514587:  60%|█████▉    | 15503/25880 [3:10:45<2:05:27,  1.38it/s]
1|15504|Loss: 0.7344626188278198:  60%|█████▉    | 15503/25880 [3:10:45<2:05:27,  1.38it/s]
1|15504|Loss: 0.7344626188278198:  60%|█████▉    | 15504/25880 [3:10:45<2:02:18,  1.41it/s]
1|15505|Loss: 0.8773486018180847:  60%|█████▉    | 15504/25880 [3:10:46<2:02:18,  1.41it/s]
1|15505|Loss: 0.8773486018180847:  60%|█████▉    | 15505/25880 [3:10:46<1:58:46,  1.46it/s]
1|15506|Loss: 0.8265027403831482:  60%|█████▉    | 15505/25880 [3:10:46<1:58:46,  1.46it/s]
1|15506|Loss: 0.8265027403831482:  60%|█████▉    | 15506/25880 [3:10:47<2:00:33,  1.43it/s]
1|15507|Loss: 0.7957680225372314:  60%|█████▉    | 15506/25880 [3:10:47<2:00:33,  1.43it/s]
1|15507|Loss: 0.7957680225372314:  60%|█████▉    | 15507/25880 [3:10:48<2:01:11,  1.43it/s]
1|15508|Loss: 0.7701727151870728:  60%|█████▉    | 15507/25880 [3:10:48<2:01:11,  1.43it/s]
1|15508|Loss: 0.7701727151870728:  60%|█████▉    | 15508/25880 [3:10:48<2:02:20,  1.41it/s]
1|15509|Loss: 0.8262382745742798:  60%|█████▉    | 15508/25880 [3:10:49<2:02:20,  1.41it/s]
1|15509|Loss: 0.8262382745742798:  60%|█████▉    | 15509/25880 [3:10:49<2:07:29,  1.36it/s]
1|15510|Loss: 1.006049633026123:  60%|█████▉    | 15509/25880 [3:10:49<2:07:29,  1.36it/s] 
1|15510|Loss: 1.006049633026123:  60%|█████▉    | 15510/25880 [3:10:50<2:12:53,  1.30it/s]
1|15511|Loss: 0.7798303365707397:  60%|█████▉    | 15510/25880 [3:10:50<2:12:53,  1.30it/s]
1|15511|Loss: 0.7798303365707397:  60%|█████▉    | 15511/25880 [3:10:51<2:14:13,  1.29it/s]
1|15512|Loss: 0.6929805278778076:  60%|█████▉    | 15511/25880 [3:10:51<2:14:13,  1.29it/s]
1|15512|Loss: 0.6929805278778076:  60%|█████▉    | 15512/25880 [3:10:51<2:11:30,  1.31it/s]
1|15513|Loss: 0.7418127059936523:  60%|█████▉    | 15512/25880 [3:10:52<2:11:30,  1.31it/s]
1|15513|Loss: 0.7418127059936523:  60%|█████▉    | 15513/25880 [3:10:52<2:09:52,  1.33it/s]
1|15514|Loss: 0.9307594895362854:  60%|█████▉    | 15513/25880 [3:10:53<2:09:52,  1.33it/s]
1|15514|Loss: 0.9307594895362854:  60%|█████▉    | 15514/25880 [3:10:53<2:07:56,  1.35it/s]
1|15515|Loss: 0.804099440574646:  60%|█████▉    | 15514/25880 [3:10:53<2:07:56,  1.35it/s] 
1|15515|Loss: 0.804099440574646:  60%|█████▉    | 15515/25880 [3:10:54<2:09:19,  1.34it/s]
1|15516|Loss: 0.8683622479438782:  60%|█████▉    | 15515/25880 [3:10:54<2:09:19,  1.34it/s]
1|15516|Loss: 0.8683622479438782:  60%|█████▉    | 15516/25880 [3:10:54<2:13:30,  1.29it/s]
1|15517|Loss: 0.9598945379257202:  60%|█████▉    | 15516/25880 [3:10:55<2:13:30,  1.29it/s]
1|15517|Loss: 0.9598945379257202:  60%|█████▉    | 15517/25880 [3:10:55<2:08:31,  1.34it/s]
1|15518|Loss: 0.7719987630844116:  60%|█████▉    | 15517/25880 [3:10:55<2:08:31,  1.34it/s]
1|15518|Loss: 0.7719987630844116:  60%|█████▉    | 15518/25880 [3:10:56<2:05:52,  1.37it/s]
1|15519|Loss: 0.7267162799835205:  60%|█████▉    | 15518/25880 [3:10:56<2:05:52,  1.37it/s]
1|15519|Loss: 0.7267162799835205:  60%|█████▉    | 15519/25880 [3:10:57<2:06:25,  1.37it/s]
1|15520|Loss: 0.8050907254219055:  60%|█████▉    | 15519/25880 [3:10:57<2:06:25,  1.37it/s]
1|15520|Loss: 0.8050907254219055:  60%|█████▉    | 15520/25880 [3:10:57<2:07:02,  1.36it/s]
1|15521|Loss: 0.8129551410675049:  60%|█████▉    | 15520/25880 [3:10:58<2:07:02,  1.36it/s]
1|15521|Loss: 0.8129551410675049:  60%|█████▉    | 15521/25880 [3:10:58<2:06:43,  1.36it/s]
1|15522|Loss: 0.821735680103302:  60%|█████▉    | 15521/25880 [3:10:58<2:06:43,  1.36it/s] 
1|15522|Loss: 0.821735680103302:  60%|█████▉    | 15522/25880 [3:10:59<1:59:04,  1.45it/s]
1|15523|Loss: 0.8288607597351074:  60%|█████▉    | 15522/25880 [3:10:59<1:59:04,  1.45it/s]
1|15523|Loss: 0.8288607597351074:  60%|█████▉    | 15523/25880 [3:10:59<1:59:48,  1.44it/s]
1|15524|Loss: 0.823211133480072:  60%|█████▉    | 15523/25880 [3:11:00<1:59:48,  1.44it/s] 
1|15524|Loss: 0.823211133480072:  60%|█████▉    | 15524/25880 [3:11:00<1:52:40,  1.53it/s]
1|15525|Loss: 0.7732037305831909:  60%|█████▉    | 15524/25880 [3:11:00<1:52:40,  1.53it/s]
1|15525|Loss: 0.7732037305831909:  60%|█████▉    | 15525/25880 [3:11:01<2:05:13,  1.38it/s]
1|15526|Loss: 0.8335886597633362:  60%|█████▉    | 15525/25880 [3:11:01<2:05:13,  1.38it/s]
1|15526|Loss: 0.8335886597633362:  60%|█████▉    | 15526/25880 [3:11:02<2:07:51,  1.35it/s]
1|15527|Loss: 0.8189703226089478:  60%|█████▉    | 15526/25880 [3:11:02<2:07:51,  1.35it/s]
1|15527|Loss: 0.8189703226089478:  60%|█████▉    | 15527/25880 [3:11:02<2:10:55,  1.32it/s]
1|15528|Loss: 0.7269867658615112:  60%|█████▉    | 15527/25880 [3:11:03<2:10:55,  1.32it/s]
1|15528|Loss: 0.7269867658615112:  60%|██████    | 15528/25880 [3:11:03<2:11:01,  1.32it/s]
1|15529|Loss: 0.8359410166740417:  60%|██████    | 15528/25880 [3:11:03<2:11:01,  1.32it/s]
1|15529|Loss: 0.8359410166740417:  60%|██████    | 15529/25880 [3:11:04<2:05:54,  1.37it/s]
1|15530|Loss: 0.8754101991653442:  60%|██████    | 15529/25880 [3:11:04<2:05:54,  1.37it/s]
1|15530|Loss: 0.8754101991653442:  60%|██████    | 15530/25880 [3:11:04<2:00:09,  1.44it/s]
1|15531|Loss: 0.6589012145996094:  60%|██████    | 15530/25880 [3:11:05<2:00:09,  1.44it/s]
1|15531|Loss: 0.6589012145996094:  60%|██████    | 15531/25880 [3:11:05<2:10:31,  1.32it/s]
1|15532|Loss: 1.0161142349243164:  60%|██████    | 15531/25880 [3:11:06<2:10:31,  1.32it/s]
1|15532|Loss: 1.0161142349243164:  60%|██████    | 15532/25880 [3:11:06<2:11:42,  1.31it/s]
1|15533|Loss: 0.7207456231117249:  60%|██████    | 15532/25880 [3:11:06<2:11:42,  1.31it/s]
1|15533|Loss: 0.7207456231117249:  60%|██████    | 15533/25880 [3:11:07<1:59:45,  1.44it/s]
1|15534|Loss: 0.7779045701026917:  60%|██████    | 15533/25880 [3:11:07<1:59:45,  1.44it/s]
1|15534|Loss: 0.7779045701026917:  60%|██████    | 15534/25880 [3:11:07<1:55:09,  1.50it/s]
1|15535|Loss: 0.8592597246170044:  60%|██████    | 15534/25880 [3:11:08<1:55:09,  1.50it/s]
1|15535|Loss: 0.8592597246170044:  60%|██████    | 15535/25880 [3:11:08<2:04:09,  1.39it/s]
1|15536|Loss: 0.822405993938446:  60%|██████    | 15535/25880 [3:11:08<2:04:09,  1.39it/s] 
1|15536|Loss: 0.822405993938446:  60%|██████    | 15536/25880 [3:11:09<2:06:59,  1.36it/s]
1|15537|Loss: 0.7794824242591858:  60%|██████    | 15536/25880 [3:11:09<2:06:59,  1.36it/s]
1|15537|Loss: 0.7794824242591858:  60%|██████    | 15537/25880 [3:11:10<2:11:15,  1.31it/s]
1|15538|Loss: 0.8380082249641418:  60%|██████    | 15537/25880 [3:11:10<2:11:15,  1.31it/s]
1|15538|Loss: 0.8380082249641418:  60%|██████    | 15538/25880 [3:11:10<2:14:58,  1.28it/s]
1|15539|Loss: 0.8934168219566345:  60%|██████    | 15538/25880 [3:11:11<2:14:58,  1.28it/s]
1|15539|Loss: 0.8934168219566345:  60%|██████    | 15539/25880 [3:11:11<2:08:47,  1.34it/s]
1|15540|Loss: 0.9308493733406067:  60%|██████    | 15539/25880 [3:11:11<2:08:47,  1.34it/s]
1|15540|Loss: 0.9308493733406067:  60%|██████    | 15540/25880 [3:11:12<2:01:12,  1.42it/s]
1|15541|Loss: 0.7534038424491882:  60%|██████    | 15540/25880 [3:11:12<2:01:12,  1.42it/s]
1|15541|Loss: 0.7534038424491882:  60%|██████    | 15541/25880 [3:11:12<2:00:49,  1.43it/s]
1|15542|Loss: 0.8379587531089783:  60%|██████    | 15541/25880 [3:11:13<2:00:49,  1.43it/s]
1|15542|Loss: 0.8379587531089783:  60%|██████    | 15542/25880 [3:11:13<2:02:46,  1.40it/s]
1|15543|Loss: 0.9274412989616394:  60%|██████    | 15542/25880 [3:11:14<2:02:46,  1.40it/s]
1|15543|Loss: 0.9274412989616394:  60%|██████    | 15543/25880 [3:11:14<1:59:21,  1.44it/s]
1|15544|Loss: 0.8388722538948059:  60%|██████    | 15543/25880 [3:11:14<1:59:21,  1.44it/s]
1|15544|Loss: 0.8388722538948059:  60%|██████    | 15544/25880 [3:11:15<2:05:12,  1.38it/s]
1|15545|Loss: 0.7772013545036316:  60%|██████    | 15544/25880 [3:11:15<2:05:12,  1.38it/s]
1|15545|Loss: 0.7772013545036316:  60%|██████    | 15545/25880 [3:11:15<2:00:37,  1.43it/s]
1|15546|Loss: 0.8421258330345154:  60%|██████    | 15545/25880 [3:11:16<2:00:37,  1.43it/s]
1|15546|Loss: 0.8421258330345154:  60%|██████    | 15546/25880 [3:11:16<1:59:50,  1.44it/s]
1|15547|Loss: 0.9108856320381165:  60%|██████    | 15546/25880 [3:11:16<1:59:50,  1.44it/s]
1|15547|Loss: 0.9108856320381165:  60%|██████    | 15547/25880 [3:11:17<2:04:14,  1.39it/s]
1|15548|Loss: 0.7520854473114014:  60%|██████    | 15547/25880 [3:11:17<2:04:14,  1.39it/s]
1|15548|Loss: 0.7520854473114014:  60%|██████    | 15548/25880 [3:11:17<2:05:27,  1.37it/s]
1|15549|Loss: 0.914051353931427:  60%|██████    | 15548/25880 [3:11:18<2:05:27,  1.37it/s] 
1|15549|Loss: 0.914051353931427:  60%|██████    | 15549/25880 [3:11:18<2:04:22,  1.38it/s]
1|15550|Loss: 0.7987244725227356:  60%|██████    | 15549/25880 [3:11:19<2:04:22,  1.38it/s]
1|15550|Loss: 0.7987244725227356:  60%|██████    | 15550/25880 [3:11:19<2:14:14,  1.28it/s]
1|15551|Loss: 0.9282695055007935:  60%|██████    | 15550/25880 [3:11:20<2:14:14,  1.28it/s]
1|15551|Loss: 0.9282695055007935:  60%|██████    | 15551/25880 [3:11:20<2:13:01,  1.29it/s]
1|15552|Loss: 0.8905463218688965:  60%|██████    | 15551/25880 [3:11:20<2:13:01,  1.29it/s]
1|15552|Loss: 0.8905463218688965:  60%|██████    | 15552/25880 [3:11:21<2:12:43,  1.30it/s]
1|15553|Loss: 0.9316322207450867:  60%|██████    | 15552/25880 [3:11:21<2:12:43,  1.30it/s]
1|15553|Loss: 0.9316322207450867:  60%|██████    | 15553/25880 [3:11:21<2:15:25,  1.27it/s]
1|15554|Loss: 0.7434310913085938:  60%|██████    | 15553/25880 [3:11:22<2:15:25,  1.27it/s]
1|15554|Loss: 0.7434310913085938:  60%|██████    | 15554/25880 [3:11:22<2:08:47,  1.34it/s]
1|15555|Loss: 0.9079582691192627:  60%|██████    | 15554/25880 [3:11:22<2:08:47,  1.34it/s]
1|15555|Loss: 0.9079582691192627:  60%|██████    | 15555/25880 [3:11:23<2:05:31,  1.37it/s]
1|15556|Loss: 0.7369956374168396:  60%|██████    | 15555/25880 [3:11:23<2:05:31,  1.37it/s]
1|15556|Loss: 0.7369956374168396:  60%|██████    | 15556/25880 [3:11:23<2:04:13,  1.39it/s]
1|15557|Loss: 0.9340034127235413:  60%|██████    | 15556/25880 [3:11:24<2:04:13,  1.39it/s]
1|15557|Loss: 0.9340034127235413:  60%|██████    | 15557/25880 [3:11:24<2:04:24,  1.38it/s]
1|15558|Loss: 0.9091034531593323:  60%|██████    | 15557/25880 [3:11:25<2:04:24,  1.38it/s]
1|15558|Loss: 0.9091034531593323:  60%|██████    | 15558/25880 [3:11:25<2:03:23,  1.39it/s]
1|15559|Loss: 0.9201972484588623:  60%|██████    | 15558/25880 [3:11:25<2:03:23,  1.39it/s]
1|15559|Loss: 0.9201972484588623:  60%|██████    | 15559/25880 [3:11:26<2:05:54,  1.37it/s]
1|15560|Loss: 0.8816590905189514:  60%|██████    | 15559/25880 [3:11:26<2:05:54,  1.37it/s]
1|15560|Loss: 0.8816590905189514:  60%|██████    | 15560/25880 [3:11:26<1:59:43,  1.44it/s]
1|15561|Loss: 0.9121357202529907:  60%|██████    | 15560/25880 [3:11:27<1:59:43,  1.44it/s]
1|15561|Loss: 0.9121357202529907:  60%|██████    | 15561/25880 [3:11:27<1:58:23,  1.45it/s]
1|15562|Loss: 0.7853806018829346:  60%|██████    | 15561/25880 [3:11:27<1:58:23,  1.45it/s]
1|15562|Loss: 0.7853806018829346:  60%|██████    | 15562/25880 [3:11:28<1:55:28,  1.49it/s]
1|15563|Loss: 0.6970491409301758:  60%|██████    | 15562/25880 [3:11:28<1:55:28,  1.49it/s]
1|15563|Loss: 0.6970491409301758:  60%|██████    | 15563/25880 [3:11:28<2:00:15,  1.43it/s]
1|15564|Loss: 0.7648847699165344:  60%|██████    | 15563/25880 [3:11:29<2:00:15,  1.43it/s]
1|15564|Loss: 0.7648847699165344:  60%|██████    | 15564/25880 [3:11:29<1:54:27,  1.50it/s]
1|15565|Loss: 0.7621778845787048:  60%|██████    | 15564/25880 [3:11:29<1:54:27,  1.50it/s]
1|15565|Loss: 0.7621778845787048:  60%|██████    | 15565/25880 [3:11:30<1:55:29,  1.49it/s]
1|15566|Loss: 0.8939728140830994:  60%|██████    | 15565/25880 [3:11:30<1:55:29,  1.49it/s]
1|15566|Loss: 0.8939728140830994:  60%|██████    | 15566/25880 [3:11:30<1:54:40,  1.50it/s]
1|15567|Loss: 0.8853566646575928:  60%|██████    | 15566/25880 [3:11:31<1:54:40,  1.50it/s]
1|15567|Loss: 0.8853566646575928:  60%|██████    | 15567/25880 [3:11:31<1:57:08,  1.47it/s]
1|15568|Loss: 0.772219181060791:  60%|██████    | 15567/25880 [3:11:31<1:57:08,  1.47it/s] 
1|15568|Loss: 0.772219181060791:  60%|██████    | 15568/25880 [3:11:32<1:49:22,  1.57it/s]
1|15569|Loss: 0.8232008218765259:  60%|██████    | 15568/25880 [3:11:32<1:49:22,  1.57it/s]
1|15569|Loss: 0.8232008218765259:  60%|██████    | 15569/25880 [3:11:32<1:57:14,  1.47it/s]
1|15570|Loss: 0.8815751671791077:  60%|██████    | 15569/25880 [3:11:33<1:57:14,  1.47it/s]
1|15570|Loss: 0.8815751671791077:  60%|██████    | 15570/25880 [3:11:33<2:09:36,  1.33it/s]
1|15571|Loss: 0.7462444305419922:  60%|██████    | 15570/25880 [3:11:34<2:09:36,  1.33it/s]
1|15571|Loss: 0.7462444305419922:  60%|██████    | 15571/25880 [3:11:34<2:10:08,  1.32it/s]
1|15572|Loss: 0.9069000482559204:  60%|██████    | 15571/25880 [3:11:34<2:10:08,  1.32it/s]
1|15572|Loss: 0.9069000482559204:  60%|██████    | 15572/25880 [3:11:35<2:08:56,  1.33it/s]
1|15573|Loss: 0.8139997124671936:  60%|██████    | 15572/25880 [3:11:35<2:08:56,  1.33it/s]
1|15573|Loss: 0.8139997124671936:  60%|██████    | 15573/25880 [3:11:35<2:00:39,  1.42it/s]
1|15574|Loss: 0.8479438424110413:  60%|██████    | 15573/25880 [3:11:36<2:00:39,  1.42it/s]
1|15574|Loss: 0.8479438424110413:  60%|██████    | 15574/25880 [3:11:36<2:02:37,  1.40it/s]
1|15575|Loss: 0.8656936883926392:  60%|██████    | 15574/25880 [3:11:36<2:02:37,  1.40it/s]
1|15575|Loss: 0.8656936883926392:  60%|██████    | 15575/25880 [3:11:37<2:04:11,  1.38it/s]
1|15576|Loss: 0.7503971457481384:  60%|██████    | 15575/25880 [3:11:37<2:04:11,  1.38it/s]
1|15576|Loss: 0.7503971457481384:  60%|██████    | 15576/25880 [3:11:38<2:06:41,  1.36it/s]
1|15577|Loss: 0.7728872895240784:  60%|██████    | 15576/25880 [3:11:38<2:06:41,  1.36it/s]
1|15577|Loss: 0.7728872895240784:  60%|██████    | 15577/25880 [3:11:38<1:58:08,  1.45it/s]
1|15578|Loss: 0.7689915895462036:  60%|██████    | 15577/25880 [3:11:39<1:58:08,  1.45it/s]
1|15578|Loss: 0.7689915895462036:  60%|██████    | 15578/25880 [3:11:39<2:02:45,  1.40it/s]
1|15579|Loss: 0.8764719367027283:  60%|██████    | 15578/25880 [3:11:39<2:02:45,  1.40it/s]
1|15579|Loss: 0.8764719367027283:  60%|██████    | 15579/25880 [3:11:40<1:58:56,  1.44it/s]
1|15580|Loss: 0.8971648812294006:  60%|██████    | 15579/25880 [3:11:40<1:58:56,  1.44it/s]
1|15580|Loss: 0.8971648812294006:  60%|██████    | 15580/25880 [3:11:40<1:59:29,  1.44it/s]
1|15581|Loss: 0.9932664632797241:  60%|██████    | 15580/25880 [3:11:41<1:59:29,  1.44it/s]
1|15581|Loss: 0.9932664632797241:  60%|██████    | 15581/25880 [3:11:41<1:57:22,  1.46it/s]
1|15582|Loss: 0.7901970148086548:  60%|██████    | 15581/25880 [3:11:41<1:57:22,  1.46it/s]
1|15582|Loss: 0.7901970148086548:  60%|██████    | 15582/25880 [3:11:41<1:49:35,  1.57it/s]
1|15583|Loss: 0.8129753470420837:  60%|██████    | 15582/25880 [3:11:42<1:49:35,  1.57it/s]
1|15583|Loss: 0.8129753470420837:  60%|██████    | 15583/25880 [3:11:42<1:52:37,  1.52it/s]
1|15584|Loss: 0.8295639753341675:  60%|██████    | 15583/25880 [3:11:43<1:52:37,  1.52it/s]
1|15584|Loss: 0.8295639753341675:  60%|██████    | 15584/25880 [3:11:43<1:57:03,  1.47it/s]
1|15585|Loss: 0.9219986200332642:  60%|██████    | 15584/25880 [3:11:43<1:57:03,  1.47it/s]
1|15585|Loss: 0.9219986200332642:  60%|██████    | 15585/25880 [3:11:44<1:59:57,  1.43it/s]
1|15586|Loss: 0.7508588433265686:  60%|██████    | 15585/25880 [3:11:44<1:59:57,  1.43it/s]
1|15586|Loss: 0.7508588433265686:  60%|██████    | 15586/25880 [3:11:44<1:55:54,  1.48it/s]
1|15587|Loss: 0.8562408685684204:  60%|██████    | 15586/25880 [3:11:45<1:55:54,  1.48it/s]
1|15587|Loss: 0.8562408685684204:  60%|██████    | 15587/25880 [3:11:45<1:59:37,  1.43it/s]
1|15588|Loss: 0.7792770266532898:  60%|██████    | 15587/25880 [3:11:45<1:59:37,  1.43it/s]
1|15588|Loss: 0.7792770266532898:  60%|██████    | 15588/25880 [3:11:46<2:02:20,  1.40it/s]
1|15589|Loss: 0.9869031310081482:  60%|██████    | 15588/25880 [3:11:46<2:02:20,  1.40it/s]
1|15589|Loss: 0.9869031310081482:  60%|██████    | 15589/25880 [3:11:47<2:11:27,  1.30it/s]
1|15590|Loss: 0.8278133869171143:  60%|██████    | 15589/25880 [3:11:47<2:11:27,  1.30it/s]
1|15590|Loss: 0.8278133869171143:  60%|██████    | 15590/25880 [3:11:47<2:04:22,  1.38it/s]
1|15591|Loss: 0.8365261554718018:  60%|██████    | 15590/25880 [3:11:48<2:04:22,  1.38it/s]
1|15591|Loss: 0.8365261554718018:  60%|██████    | 15591/25880 [3:11:48<2:03:26,  1.39it/s]
1|15592|Loss: 0.8421868085861206:  60%|██████    | 15591/25880 [3:11:48<2:03:26,  1.39it/s]
1|15592|Loss: 0.8421868085861206:  60%|██████    | 15592/25880 [3:11:49<2:11:53,  1.30it/s]
1|15593|Loss: 0.8390126824378967:  60%|██████    | 15592/25880 [3:11:49<2:11:53,  1.30it/s]
1|15593|Loss: 0.8390126824378967:  60%|██████    | 15593/25880 [3:11:50<2:10:34,  1.31it/s]
1|15594|Loss: 0.7975030541419983:  60%|██████    | 15593/25880 [3:11:50<2:10:34,  1.31it/s]
1|15594|Loss: 0.7975030541419983:  60%|██████    | 15594/25880 [3:11:50<2:04:57,  1.37it/s]
1|15595|Loss: 0.9033605456352234:  60%|██████    | 15594/25880 [3:11:51<2:04:57,  1.37it/s]
1|15595|Loss: 0.9033605456352234:  60%|██████    | 15595/25880 [3:11:51<2:11:34,  1.30it/s]
1|15596|Loss: 0.9845536351203918:  60%|██████    | 15595/25880 [3:11:52<2:11:34,  1.30it/s]
1|15596|Loss: 0.9845536351203918:  60%|██████    | 15596/25880 [3:11:52<2:04:23,  1.38it/s]
1|15597|Loss: 0.8448871374130249:  60%|██████    | 15596/25880 [3:11:52<2:04:23,  1.38it/s]
1|15597|Loss: 0.8448871374130249:  60%|██████    | 15597/25880 [3:11:53<2:05:08,  1.37it/s]
1|15598|Loss: 0.7010212540626526:  60%|██████    | 15597/25880 [3:11:53<2:05:08,  1.37it/s]
1|15598|Loss: 0.7010212540626526:  60%|██████    | 15598/25880 [3:11:53<2:04:51,  1.37it/s]
1|15599|Loss: 0.7671358585357666:  60%|██████    | 15598/25880 [3:11:54<2:04:51,  1.37it/s]
1|15599|Loss: 0.7671358585357666:  60%|██████    | 15599/25880 [3:11:54<2:04:49,  1.37it/s]
1|15600|Loss: 0.8557626008987427:  60%|██████    | 15599/25880 [3:11:54<2:04:49,  1.37it/s]
1|15600|Loss: 0.8557626008987427:  60%|██████    | 15600/25880 [3:11:55<1:59:16,  1.44it/s]
1|15601|Loss: 0.8926059007644653:  60%|██████    | 15600/25880 [3:11:55<1:59:16,  1.44it/s]
1|15601|Loss: 0.8926059007644653:  60%|██████    | 15601/25880 [3:11:55<2:02:07,  1.40it/s]
1|15602|Loss: 0.8426915407180786:  60%|██████    | 15601/25880 [3:11:56<2:02:07,  1.40it/s]
1|15602|Loss: 0.8426915407180786:  60%|██████    | 15602/25880 [3:11:56<2:10:13,  1.32it/s]
1|15603|Loss: 0.929290771484375:  60%|██████    | 15602/25880 [3:11:57<2:10:13,  1.32it/s] 
1|15603|Loss: 0.929290771484375:  60%|██████    | 15603/25880 [3:11:57<2:14:53,  1.27it/s]
1|15604|Loss: 0.8444076776504517:  60%|██████    | 15603/25880 [3:11:57<2:14:53,  1.27it/s]
1|15604|Loss: 0.8444076776504517:  60%|██████    | 15604/25880 [3:11:58<2:12:55,  1.29it/s]
1|15605|Loss: 0.8366968035697937:  60%|██████    | 15604/25880 [3:11:58<2:12:55,  1.29it/s]
1|15605|Loss: 0.8366968035697937:  60%|██████    | 15605/25880 [3:11:58<2:05:48,  1.36it/s]
1|15606|Loss: 0.8551775813102722:  60%|██████    | 15605/25880 [3:11:59<2:05:48,  1.36it/s]
1|15606|Loss: 0.8551775813102722:  60%|██████    | 15606/25880 [3:11:59<2:05:02,  1.37it/s]
1|15607|Loss: 0.8220980167388916:  60%|██████    | 15606/25880 [3:12:00<2:05:02,  1.37it/s]
1|15607|Loss: 0.8220980167388916:  60%|██████    | 15607/25880 [3:12:00<2:08:17,  1.33it/s]
1|15608|Loss: 0.833489179611206:  60%|██████    | 15607/25880 [3:12:00<2:08:17,  1.33it/s] 
1|15608|Loss: 0.833489179611206:  60%|██████    | 15608/25880 [3:12:01<2:02:19,  1.40it/s]
1|15609|Loss: 0.8829202055931091:  60%|██████    | 15608/25880 [3:12:01<2:02:19,  1.40it/s]
1|15609|Loss: 0.8829202055931091:  60%|██████    | 15609/25880 [3:12:01<1:52:56,  1.52it/s]
1|15610|Loss: 0.800681471824646:  60%|██████    | 15609/25880 [3:12:01<1:52:56,  1.52it/s] 
1|15610|Loss: 0.800681471824646:  60%|██████    | 15610/25880 [3:12:02<1:52:53,  1.52it/s]
1|15611|Loss: 0.8153785467147827:  60%|██████    | 15610/25880 [3:12:02<1:52:53,  1.52it/s]
1|15611|Loss: 0.8153785467147827:  60%|██████    | 15611/25880 [3:12:02<1:54:53,  1.49it/s]
1|15612|Loss: 0.7144675254821777:  60%|██████    | 15611/25880 [3:12:03<1:54:53,  1.49it/s]
1|15612|Loss: 0.7144675254821777:  60%|██████    | 15612/25880 [3:12:03<1:57:36,  1.46it/s]
1|15613|Loss: 0.7608587145805359:  60%|██████    | 15612/25880 [3:12:04<1:57:36,  1.46it/s]
1|15613|Loss: 0.7608587145805359:  60%|██████    | 15613/25880 [3:12:04<2:00:17,  1.42it/s]
1|15614|Loss: 0.9266483187675476:  60%|██████    | 15613/25880 [3:12:04<2:00:17,  1.42it/s]
1|15614|Loss: 0.9266483187675476:  60%|██████    | 15614/25880 [3:12:05<1:57:25,  1.46it/s]
1|15615|Loss: 0.6759775876998901:  60%|██████    | 15614/25880 [3:12:05<1:57:25,  1.46it/s]
1|15615|Loss: 0.6759775876998901:  60%|██████    | 15615/25880 [3:12:05<2:03:57,  1.38it/s]
1|15616|Loss: 0.7116820812225342:  60%|██████    | 15615/25880 [3:12:06<2:03:57,  1.38it/s]
1|15616|Loss: 0.7116820812225342:  60%|██████    | 15616/25880 [3:12:06<2:10:44,  1.31it/s]
1|15617|Loss: 0.7845706343650818:  60%|██████    | 15616/25880 [3:12:07<2:10:44,  1.31it/s]
1|15617|Loss: 0.7845706343650818:  60%|██████    | 15617/25880 [3:12:07<2:10:15,  1.31it/s]
1|15618|Loss: 0.8399247527122498:  60%|██████    | 15617/25880 [3:12:07<2:10:15,  1.31it/s]
1|15618|Loss: 0.8399247527122498:  60%|██████    | 15618/25880 [3:12:08<2:18:06,  1.24it/s]
1|15619|Loss: 0.8338187336921692:  60%|██████    | 15618/25880 [3:12:08<2:18:06,  1.24it/s]
1|15619|Loss: 0.8338187336921692:  60%|██████    | 15619/25880 [3:12:09<2:12:47,  1.29it/s]
1|15620|Loss: 0.7993618845939636:  60%|██████    | 15619/25880 [3:12:09<2:12:47,  1.29it/s]
1|15620|Loss: 0.7993618845939636:  60%|██████    | 15620/25880 [3:12:09<2:04:44,  1.37it/s]
1|15621|Loss: 0.8380083441734314:  60%|██████    | 15620/25880 [3:12:10<2:04:44,  1.37it/s]
1|15621|Loss: 0.8380083441734314:  60%|██████    | 15621/25880 [3:12:10<2:07:30,  1.34it/s]
1|15622|Loss: 0.7706369161605835:  60%|██████    | 15621/25880 [3:12:10<2:07:30,  1.34it/s]
1|15622|Loss: 0.7706369161605835:  60%|██████    | 15622/25880 [3:12:11<2:10:41,  1.31it/s]
1|15623|Loss: 0.7618900537490845:  60%|██████    | 15622/25880 [3:12:11<2:10:41,  1.31it/s]
1|15623|Loss: 0.7618900537490845:  60%|██████    | 15623/25880 [3:12:12<2:08:28,  1.33it/s]
1|15624|Loss: 0.88263338804245:  60%|██████    | 15623/25880 [3:12:12<2:08:28,  1.33it/s]  
1|15624|Loss: 0.88263338804245:  60%|██████    | 15624/25880 [3:12:12<2:07:33,  1.34it/s]
1|15625|Loss: 0.7886366844177246:  60%|██████    | 15624/25880 [3:12:13<2:07:33,  1.34it/s]
1|15625|Loss: 0.7886366844177246:  60%|██████    | 15625/25880 [3:12:13<2:03:27,  1.38it/s]
1|15626|Loss: 0.8699039220809937:  60%|██████    | 15625/25880 [3:12:13<2:03:27,  1.38it/s]
1|15626|Loss: 0.8699039220809937:  60%|██████    | 15626/25880 [3:12:14<2:03:21,  1.39it/s]
1|15627|Loss: 0.8780915141105652:  60%|██████    | 15626/25880 [3:12:14<2:03:21,  1.39it/s]
1|15627|Loss: 0.8780915141105652:  60%|██████    | 15627/25880 [3:12:14<1:59:26,  1.43it/s]
1|15628|Loss: 0.9991734027862549:  60%|██████    | 15627/25880 [3:12:15<1:59:26,  1.43it/s]
1|15628|Loss: 0.9991734027862549:  60%|██████    | 15628/25880 [3:12:15<1:55:00,  1.49it/s]
1|15629|Loss: 0.8636804223060608:  60%|██████    | 15628/25880 [3:12:15<1:55:00,  1.49it/s]
1|15629|Loss: 0.8636804223060608:  60%|██████    | 15629/25880 [3:12:16<1:53:09,  1.51it/s]
1|15630|Loss: 0.9041581749916077:  60%|██████    | 15629/25880 [3:12:16<1:53:09,  1.51it/s]
1|15630|Loss: 0.9041581749916077:  60%|██████    | 15630/25880 [3:12:16<1:59:41,  1.43it/s]
1|15631|Loss: 0.7340527176856995:  60%|██████    | 15630/25880 [3:12:17<1:59:41,  1.43it/s]
1|15631|Loss: 0.7340527176856995:  60%|██████    | 15631/25880 [3:12:17<2:01:06,  1.41it/s]
1|15632|Loss: 0.7116061449050903:  60%|██████    | 15631/25880 [3:12:18<2:01:06,  1.41it/s]
1|15632|Loss: 0.7116061449050903:  60%|██████    | 15632/25880 [3:12:18<2:02:27,  1.39it/s]
1|15633|Loss: 0.9072215557098389:  60%|██████    | 15632/25880 [3:12:18<2:02:27,  1.39it/s]
1|15633|Loss: 0.9072215557098389:  60%|██████    | 15633/25880 [3:12:19<2:02:27,  1.39it/s]
1|15634|Loss: 0.7249795794487:  60%|██████    | 15633/25880 [3:12:19<2:02:27,  1.39it/s]   
1|15634|Loss: 0.7249795794487:  60%|██████    | 15634/25880 [3:12:19<2:05:43,  1.36it/s]
1|15635|Loss: 0.7339445948600769:  60%|██████    | 15634/25880 [3:12:20<2:05:43,  1.36it/s]
1|15635|Loss: 0.7339445948600769:  60%|██████    | 15635/25880 [3:12:20<1:54:39,  1.49it/s]
1|15636|Loss: 0.9134910106658936:  60%|██████    | 15635/25880 [3:12:20<1:54:39,  1.49it/s]
1|15636|Loss: 0.9134910106658936:  60%|██████    | 15636/25880 [3:12:21<1:53:27,  1.50it/s]
1|15637|Loss: 0.8939298391342163:  60%|██████    | 15636/25880 [3:12:21<1:53:27,  1.50it/s]
1|15637|Loss: 0.8939298391342163:  60%|██████    | 15637/25880 [3:12:21<1:56:26,  1.47it/s]
1|15638|Loss: 0.8729053139686584:  60%|██████    | 15637/25880 [3:12:22<1:56:26,  1.47it/s]
1|15638|Loss: 0.8729053139686584:  60%|██████    | 15638/25880 [3:12:22<1:59:13,  1.43it/s]
1|15639|Loss: 0.7169669270515442:  60%|██████    | 15638/25880 [3:12:22<1:59:13,  1.43it/s]
1|15639|Loss: 0.7169669270515442:  60%|██████    | 15639/25880 [3:12:23<2:05:27,  1.36it/s]
1|15640|Loss: 0.7359237670898438:  60%|██████    | 15639/25880 [3:12:23<2:05:27,  1.36it/s]
1|15640|Loss: 0.7359237670898438:  60%|██████    | 15640/25880 [3:12:24<2:06:09,  1.35it/s]
1|15641|Loss: 0.8491083979606628:  60%|██████    | 15640/25880 [3:12:24<2:06:09,  1.35it/s]
1|15641|Loss: 0.8491083979606628:  60%|██████    | 15641/25880 [3:12:24<2:04:14,  1.37it/s]
1|15642|Loss: 0.8029712438583374:  60%|██████    | 15641/25880 [3:12:25<2:04:14,  1.37it/s]
1|15642|Loss: 0.8029712438583374:  60%|██████    | 15642/25880 [3:12:25<1:52:52,  1.51it/s]
1|15643|Loss: 0.8007103800773621:  60%|██████    | 15642/25880 [3:12:25<1:52:52,  1.51it/s]
1|15643|Loss: 0.8007103800773621:  60%|██████    | 15643/25880 [3:12:25<1:48:31,  1.57it/s]
1|15644|Loss: 0.8157398104667664:  60%|██████    | 15643/25880 [3:12:26<1:48:31,  1.57it/s]
1|15644|Loss: 0.8157398104667664:  60%|██████    | 15644/25880 [3:12:26<1:48:02,  1.58it/s]
1|15645|Loss: 0.7387552857398987:  60%|██████    | 15644/25880 [3:12:26<1:48:02,  1.58it/s]
1|15645|Loss: 0.7387552857398987:  60%|██████    | 15645/25880 [3:12:27<1:55:53,  1.47it/s]
1|15646|Loss: 0.8361743688583374:  60%|██████    | 15645/25880 [3:12:27<1:55:53,  1.47it/s]
1|15646|Loss: 0.8361743688583374:  60%|██████    | 15646/25880 [3:12:27<1:59:27,  1.43it/s]
1|15647|Loss: 0.7661769986152649:  60%|██████    | 15646/25880 [3:12:28<1:59:27,  1.43it/s]
1|15647|Loss: 0.7661769986152649:  60%|██████    | 15647/25880 [3:12:28<1:57:06,  1.46it/s]
1|15648|Loss: 1.013545274734497:  60%|██████    | 15647/25880 [3:12:29<1:57:06,  1.46it/s] 
1|15648|Loss: 1.013545274734497:  60%|██████    | 15648/25880 [3:12:29<1:57:26,  1.45it/s]
1|15649|Loss: 0.9059953689575195:  60%|██████    | 15648/25880 [3:12:29<1:57:26,  1.45it/s]
1|15649|Loss: 0.9059953689575195:  60%|██████    | 15649/25880 [3:12:29<1:45:15,  1.62it/s]
1|15650|Loss: 0.8083165287971497:  60%|██████    | 15649/25880 [3:12:30<1:45:15,  1.62it/s]
1|15650|Loss: 0.8083165287971497:  60%|██████    | 15650/25880 [3:12:30<1:37:54,  1.74it/s]
1|15651|Loss: 0.9140862822532654:  60%|██████    | 15650/25880 [3:12:30<1:37:54,  1.74it/s]
1|15651|Loss: 0.9140862822532654:  60%|██████    | 15651/25880 [3:12:30<1:39:20,  1.72it/s]
1|15652|Loss: 0.8500303030014038:  60%|██████    | 15651/25880 [3:12:31<1:39:20,  1.72it/s]
1|15652|Loss: 0.8500303030014038:  60%|██████    | 15652/25880 [3:12:31<1:36:40,  1.76it/s]
1|15653|Loss: 0.9112725853919983:  60%|██████    | 15652/25880 [3:12:31<1:36:40,  1.76it/s]
1|15653|Loss: 0.9112725853919983:  60%|██████    | 15653/25880 [3:12:32<1:39:07,  1.72it/s]
1|15654|Loss: 0.8267505168914795:  60%|██████    | 15653/25880 [3:12:32<1:39:07,  1.72it/s]
1|15654|Loss: 0.8267505168914795:  60%|██████    | 15654/25880 [3:12:32<1:38:53,  1.72it/s]
1|15655|Loss: 0.9111191034317017:  60%|██████    | 15654/25880 [3:12:32<1:38:53,  1.72it/s]
1|15655|Loss: 0.9111191034317017:  60%|██████    | 15655/25880 [3:12:33<1:40:07,  1.70it/s]
1|15656|Loss: 0.7991568446159363:  60%|██████    | 15655/25880 [3:12:33<1:40:07,  1.70it/s]
1|15656|Loss: 0.7991568446159363:  60%|██████    | 15656/25880 [3:12:33<1:40:15,  1.70it/s]
1|15657|Loss: 0.8741504549980164:  60%|██████    | 15656/25880 [3:12:34<1:40:15,  1.70it/s]
1|15657|Loss: 0.8741504549980164:  60%|██████    | 15657/25880 [3:12:34<1:49:59,  1.55it/s]
1|15658|Loss: 0.9329862594604492:  60%|██████    | 15657/25880 [3:12:35<1:49:59,  1.55it/s]
1|15658|Loss: 0.9329862594604492:  61%|██████    | 15658/25880 [3:12:35<2:02:50,  1.39it/s]
1|15659|Loss: 0.9333433508872986:  61%|██████    | 15658/25880 [3:12:35<2:02:50,  1.39it/s]
1|15659|Loss: 0.9333433508872986:  61%|██████    | 15659/25880 [3:12:36<2:13:17,  1.28it/s]
1|15660|Loss: 0.8435268998146057:  61%|██████    | 15659/25880 [3:12:36<2:13:17,  1.28it/s]
1|15660|Loss: 0.8435268998146057:  61%|██████    | 15660/25880 [3:12:37<2:12:45,  1.28it/s]
1|15661|Loss: 0.8710777759552002:  61%|██████    | 15660/25880 [3:12:37<2:12:45,  1.28it/s]
1|15661|Loss: 0.8710777759552002:  61%|██████    | 15661/25880 [3:12:37<2:14:50,  1.26it/s]
1|15662|Loss: 0.9323751926422119:  61%|██████    | 15661/25880 [3:12:38<2:14:50,  1.26it/s]
1|15662|Loss: 0.9323751926422119:  61%|██████    | 15662/25880 [3:12:38<2:11:28,  1.30it/s]
1|15663|Loss: 0.6787452697753906:  61%|██████    | 15662/25880 [3:12:39<2:11:28,  1.30it/s]
1|15663|Loss: 0.6787452697753906:  61%|██████    | 15663/25880 [3:12:39<2:07:52,  1.33it/s]
1|15664|Loss: 0.7558379173278809:  61%|██████    | 15663/25880 [3:12:39<2:07:52,  1.33it/s]
1|15664|Loss: 0.7558379173278809:  61%|██████    | 15664/25880 [3:12:40<2:12:03,  1.29it/s]
1|15665|Loss: 0.7891889214515686:  61%|██████    | 15664/25880 [3:12:40<2:12:03,  1.29it/s]
1|15665|Loss: 0.7891889214515686:  61%|██████    | 15665/25880 [3:12:40<2:10:20,  1.31it/s]
1|15666|Loss: 0.8664114475250244:  61%|██████    | 15665/25880 [3:12:41<2:10:20,  1.31it/s]
1|15666|Loss: 0.8664114475250244:  61%|██████    | 15666/25880 [3:12:41<2:11:44,  1.29it/s]
1|15667|Loss: 0.8786173462867737:  61%|██████    | 15666/25880 [3:12:42<2:11:44,  1.29it/s]
1|15667|Loss: 0.8786173462867737:  61%|██████    | 15667/25880 [3:12:42<2:06:27,  1.35it/s]
1|15668|Loss: 0.7958089709281921:  61%|██████    | 15667/25880 [3:12:42<2:06:27,  1.35it/s]
1|15668|Loss: 0.7958089709281921:  61%|██████    | 15668/25880 [3:12:43<2:04:03,  1.37it/s]
1|15669|Loss: 0.9095894694328308:  61%|██████    | 15668/25880 [3:12:43<2:04:03,  1.37it/s]
1|15669|Loss: 0.9095894694328308:  61%|██████    | 15669/25880 [3:12:43<1:58:56,  1.43it/s]
1|15670|Loss: 0.8181769847869873:  61%|██████    | 15669/25880 [3:12:44<1:58:56,  1.43it/s]
1|15670|Loss: 0.8181769847869873:  61%|██████    | 15670/25880 [3:12:44<1:55:32,  1.47it/s]
1|15671|Loss: 0.7858344316482544:  61%|██████    | 15670/25880 [3:12:44<1:55:32,  1.47it/s]
1|15671|Loss: 0.7858344316482544:  61%|██████    | 15671/25880 [3:12:45<1:57:09,  1.45it/s]
1|15672|Loss: 0.8275578618049622:  61%|██████    | 15671/25880 [3:12:45<1:57:09,  1.45it/s]
1|15672|Loss: 0.8275578618049622:  61%|██████    | 15672/25880 [3:12:45<1:59:40,  1.42it/s]
1|15673|Loss: 0.8313352465629578:  61%|██████    | 15672/25880 [3:12:46<1:59:40,  1.42it/s]
1|15673|Loss: 0.8313352465629578:  61%|██████    | 15673/25880 [3:12:46<1:58:01,  1.44it/s]
1|15674|Loss: 0.8253605961799622:  61%|██████    | 15673/25880 [3:12:46<1:58:01,  1.44it/s]
1|15674|Loss: 0.8253605961799622:  61%|██████    | 15674/25880 [3:12:47<2:03:13,  1.38it/s]
1|15675|Loss: 0.8186535239219666:  61%|██████    | 15674/25880 [3:12:47<2:03:13,  1.38it/s]
1|15675|Loss: 0.8186535239219666:  61%|██████    | 15675/25880 [3:12:47<2:00:55,  1.41it/s]
1|15676|Loss: 0.7743735313415527:  61%|██████    | 15675/25880 [3:12:48<2:00:55,  1.41it/s]
1|15676|Loss: 0.7743735313415527:  61%|██████    | 15676/25880 [3:12:48<2:03:29,  1.38it/s]
1|15677|Loss: 0.7679740786552429:  61%|██████    | 15676/25880 [3:12:49<2:03:29,  1.38it/s]
1|15677|Loss: 0.7679740786552429:  61%|██████    | 15677/25880 [3:12:49<2:00:01,  1.42it/s]
1|15678|Loss: 0.864234447479248:  61%|██████    | 15677/25880 [3:12:49<2:00:01,  1.42it/s] 
1|15678|Loss: 0.864234447479248:  61%|██████    | 15678/25880 [3:12:50<2:05:21,  1.36it/s]
1|15679|Loss: 0.7671694159507751:  61%|██████    | 15678/25880 [3:12:50<2:05:21,  1.36it/s]
1|15679|Loss: 0.7671694159507751:  61%|██████    | 15679/25880 [3:12:50<2:00:23,  1.41it/s]
1|15680|Loss: 0.7869548201560974:  61%|██████    | 15679/25880 [3:12:51<2:00:23,  1.41it/s]
1|15680|Loss: 0.7869548201560974:  61%|██████    | 15680/25880 [3:12:51<1:59:59,  1.42it/s]
1|15681|Loss: 0.8888004422187805:  61%|██████    | 15680/25880 [3:12:52<1:59:59,  1.42it/s]
1|15681|Loss: 0.8888004422187805:  61%|██████    | 15681/25880 [3:12:52<2:06:18,  1.35it/s]
1|15682|Loss: 0.9779235124588013:  61%|██████    | 15681/25880 [3:12:52<2:06:18,  1.35it/s]
1|15682|Loss: 0.9779235124588013:  61%|██████    | 15682/25880 [3:12:53<2:12:27,  1.28it/s]
1|15683|Loss: 0.8126106262207031:  61%|██████    | 15682/25880 [3:12:53<2:12:27,  1.28it/s]
1|15683|Loss: 0.8126106262207031:  61%|██████    | 15683/25880 [3:12:54<2:12:04,  1.29it/s]
1|15684|Loss: 1.007799506187439:  61%|██████    | 15683/25880 [3:12:54<2:12:04,  1.29it/s] 
1|15684|Loss: 1.007799506187439:  61%|██████    | 15684/25880 [3:12:54<2:17:10,  1.24it/s]
1|15685|Loss: 0.6709554195404053:  61%|██████    | 15684/25880 [3:12:55<2:17:10,  1.24it/s]
1|15685|Loss: 0.6709554195404053:  61%|██████    | 15685/25880 [3:12:55<2:10:59,  1.30it/s]
1|15686|Loss: 0.8684071898460388:  61%|██████    | 15685/25880 [3:12:55<2:10:59,  1.30it/s]
1|15686|Loss: 0.8684071898460388:  61%|██████    | 15686/25880 [3:12:56<2:00:45,  1.41it/s]
1|15687|Loss: 1.0308537483215332:  61%|██████    | 15686/25880 [3:12:56<2:00:45,  1.41it/s]
1|15687|Loss: 1.0308537483215332:  61%|██████    | 15687/25880 [3:12:56<2:00:22,  1.41it/s]
1|15688|Loss: 0.7320253252983093:  61%|██████    | 15687/25880 [3:12:57<2:00:22,  1.41it/s]
1|15688|Loss: 0.7320253252983093:  61%|██████    | 15688/25880 [3:12:57<1:57:26,  1.45it/s]
1|15689|Loss: 0.8641653656959534:  61%|██████    | 15688/25880 [3:12:57<1:57:26,  1.45it/s]
1|15689|Loss: 0.8641653656959534:  61%|██████    | 15689/25880 [3:12:58<1:54:44,  1.48it/s]
1|15690|Loss: 0.8483167886734009:  61%|██████    | 15689/25880 [3:12:58<1:54:44,  1.48it/s]
1|15690|Loss: 0.8483167886734009:  61%|██████    | 15690/25880 [3:12:58<2:00:56,  1.40it/s]
1|15691|Loss: 0.7111673355102539:  61%|██████    | 15690/25880 [3:12:59<2:00:56,  1.40it/s]
1|15691|Loss: 0.7111673355102539:  61%|██████    | 15691/25880 [3:12:59<2:01:54,  1.39it/s]
1|15692|Loss: 0.8782634735107422:  61%|██████    | 15691/25880 [3:13:00<2:01:54,  1.39it/s]
1|15692|Loss: 0.8782634735107422:  61%|██████    | 15692/25880 [3:13:00<2:03:05,  1.38it/s]
1|15693|Loss: 0.7128351330757141:  61%|██████    | 15692/25880 [3:13:00<2:03:05,  1.38it/s]
1|15693|Loss: 0.7128351330757141:  61%|██████    | 15693/25880 [3:13:01<1:58:02,  1.44it/s]
1|15694|Loss: 0.8295051455497742:  61%|██████    | 15693/25880 [3:13:01<1:58:02,  1.44it/s]
1|15694|Loss: 0.8295051455497742:  61%|██████    | 15694/25880 [3:13:01<1:56:49,  1.45it/s]
1|15695|Loss: 0.8659670352935791:  61%|██████    | 15694/25880 [3:13:02<1:56:49,  1.45it/s]
1|15695|Loss: 0.8659670352935791:  61%|██████    | 15695/25880 [3:13:02<1:57:20,  1.45it/s]
1|15696|Loss: 0.9622213244438171:  61%|██████    | 15695/25880 [3:13:02<1:57:20,  1.45it/s]
1|15696|Loss: 0.9622213244438171:  61%|██████    | 15696/25880 [3:13:03<1:55:20,  1.47it/s]
1|15697|Loss: 0.7857028841972351:  61%|██████    | 15696/25880 [3:13:03<1:55:20,  1.47it/s]
1|15697|Loss: 0.7857028841972351:  61%|██████    | 15697/25880 [3:13:03<1:57:05,  1.45it/s]
1|15698|Loss: 0.8037832379341125:  61%|██████    | 15697/25880 [3:13:04<1:57:05,  1.45it/s]
1|15698|Loss: 0.8037832379341125:  61%|██████    | 15698/25880 [3:13:04<1:59:23,  1.42it/s]
1|15699|Loss: 0.70689457654953:  61%|██████    | 15698/25880 [3:13:04<1:59:23,  1.42it/s]  
1|15699|Loss: 0.70689457654953:  61%|██████    | 15699/25880 [3:13:05<2:04:36,  1.36it/s]
1|15700|Loss: 0.6950725317001343:  61%|██████    | 15699/25880 [3:13:05<2:04:36,  1.36it/s]
1|15700|Loss: 0.6950725317001343:  61%|██████    | 15700/25880 [3:13:06<2:11:02,  1.29it/s]
1|15701|Loss: 0.9815431237220764:  61%|██████    | 15700/25880 [3:13:06<2:11:02,  1.29it/s]
1|15701|Loss: 0.9815431237220764:  61%|██████    | 15701/25880 [3:13:07<2:14:41,  1.26it/s]
1|15702|Loss: 0.7642208337783813:  61%|██████    | 15701/25880 [3:13:07<2:14:41,  1.26it/s]
1|15702|Loss: 0.7642208337783813:  61%|██████    | 15702/25880 [3:13:07<2:12:54,  1.28it/s]
1|15703|Loss: 0.94218510389328:  61%|██████    | 15702/25880 [3:13:08<2:12:54,  1.28it/s]  
1|15703|Loss: 0.94218510389328:  61%|██████    | 15703/25880 [3:13:08<2:05:47,  1.35it/s]
1|15704|Loss: 0.8640279173851013:  61%|██████    | 15703/25880 [3:13:08<2:05:47,  1.35it/s]
1|15704|Loss: 0.8640279173851013:  61%|██████    | 15704/25880 [3:13:09<2:02:47,  1.38it/s]
1|15705|Loss: 0.7948314547538757:  61%|██████    | 15704/25880 [3:13:09<2:02:47,  1.38it/s]
1|15705|Loss: 0.7948314547538757:  61%|██████    | 15705/25880 [3:13:09<2:05:29,  1.35it/s]
1|15706|Loss: 0.7603399753570557:  61%|██████    | 15705/25880 [3:13:10<2:05:29,  1.35it/s]
1|15706|Loss: 0.7603399753570557:  61%|██████    | 15706/25880 [3:13:10<2:08:44,  1.32it/s]
1|15707|Loss: 0.722142219543457:  61%|██████    | 15706/25880 [3:13:11<2:08:44,  1.32it/s] 
1|15707|Loss: 0.722142219543457:  61%|██████    | 15707/25880 [3:13:11<2:04:15,  1.36it/s]
1|15708|Loss: 0.7574671506881714:  61%|██████    | 15707/25880 [3:13:11<2:04:15,  1.36it/s]
1|15708|Loss: 0.7574671506881714:  61%|██████    | 15708/25880 [3:13:11<1:58:35,  1.43it/s]
1|15709|Loss: 0.8020563125610352:  61%|██████    | 15708/25880 [3:13:12<1:58:35,  1.43it/s]
1|15709|Loss: 0.8020563125610352:  61%|██████    | 15709/25880 [3:13:12<2:01:33,  1.39it/s]
1|15710|Loss: 0.9755848050117493:  61%|██████    | 15709/25880 [3:13:13<2:01:33,  1.39it/s]
1|15710|Loss: 0.9755848050117493:  61%|██████    | 15710/25880 [3:13:13<2:08:01,  1.32it/s]
1|15711|Loss: 0.8920544385910034:  61%|██████    | 15710/25880 [3:13:14<2:08:01,  1.32it/s]
1|15711|Loss: 0.8920544385910034:  61%|██████    | 15711/25880 [3:13:14<2:08:38,  1.32it/s]
1|15712|Loss: 0.7433543801307678:  61%|██████    | 15711/25880 [3:13:14<2:08:38,  1.32it/s]
1|15712|Loss: 0.7433543801307678:  61%|██████    | 15712/25880 [3:13:15<2:04:02,  1.37it/s]
1|15713|Loss: 0.7510222792625427:  61%|██████    | 15712/25880 [3:13:15<2:04:02,  1.37it/s]
1|15713|Loss: 0.7510222792625427:  61%|██████    | 15713/25880 [3:13:15<2:08:40,  1.32it/s]
1|15714|Loss: 1.06635582447052:  61%|██████    | 15713/25880 [3:13:16<2:08:40,  1.32it/s]  
1|15714|Loss: 1.06635582447052:  61%|██████    | 15714/25880 [3:13:16<2:02:45,  1.38it/s]
1|15715|Loss: 0.871737539768219:  61%|██████    | 15714/25880 [3:13:16<2:02:45,  1.38it/s]
1|15715|Loss: 0.871737539768219:  61%|██████    | 15715/25880 [3:13:17<1:56:36,  1.45it/s]
1|15716|Loss: 0.793296217918396:  61%|██████    | 15715/25880 [3:13:17<1:56:36,  1.45it/s]
1|15716|Loss: 0.793296217918396:  61%|██████    | 15716/25880 [3:13:17<1:52:11,  1.51it/s]
1|15717|Loss: 0.7634907960891724:  61%|██████    | 15716/25880 [3:13:18<1:52:11,  1.51it/s]
1|15717|Loss: 0.7634907960891724:  61%|██████    | 15717/25880 [3:13:18<1:56:16,  1.46it/s]
1|15718|Loss: 0.9619428515434265:  61%|██████    | 15717/25880 [3:13:18<1:56:16,  1.46it/s]
1|15718|Loss: 0.9619428515434265:  61%|██████    | 15718/25880 [3:13:19<1:58:59,  1.42it/s]
1|15719|Loss: 0.8238143920898438:  61%|██████    | 15718/25880 [3:13:19<1:58:59,  1.42it/s]
1|15719|Loss: 0.8238143920898438:  61%|██████    | 15719/25880 [3:13:19<2:01:02,  1.40it/s]
1|15720|Loss: 0.7853372693061829:  61%|██████    | 15719/25880 [3:13:20<2:01:02,  1.40it/s]
1|15720|Loss: 0.7853372693061829:  61%|██████    | 15720/25880 [3:13:20<1:55:07,  1.47it/s]
1|15721|Loss: 0.9233773946762085:  61%|██████    | 15720/25880 [3:13:20<1:55:07,  1.47it/s]
1|15721|Loss: 0.9233773946762085:  61%|██████    | 15721/25880 [3:13:21<1:58:55,  1.42it/s]
1|15722|Loss: 1.0182310342788696:  61%|██████    | 15721/25880 [3:13:21<1:58:55,  1.42it/s]
1|15722|Loss: 1.0182310342788696:  61%|██████    | 15722/25880 [3:13:22<2:00:58,  1.40it/s]
1|15723|Loss: 0.7925834655761719:  61%|██████    | 15722/25880 [3:13:22<2:00:58,  1.40it/s]
1|15723|Loss: 0.7925834655761719:  61%|██████    | 15723/25880 [3:13:22<2:00:37,  1.40it/s]
1|15724|Loss: 0.8596363663673401:  61%|██████    | 15723/25880 [3:13:23<2:00:37,  1.40it/s]
1|15724|Loss: 0.8596363663673401:  61%|██████    | 15724/25880 [3:13:23<2:01:39,  1.39it/s]
1|15725|Loss: 0.9636589884757996:  61%|██████    | 15724/25880 [3:13:23<2:01:39,  1.39it/s]
1|15725|Loss: 0.9636589884757996:  61%|██████    | 15725/25880 [3:13:24<1:58:50,  1.42it/s]
1|15726|Loss: 0.8842300176620483:  61%|██████    | 15725/25880 [3:13:24<1:58:50,  1.42it/s]
1|15726|Loss: 0.8842300176620483:  61%|██████    | 15726/25880 [3:13:24<2:02:11,  1.38it/s]
1|15727|Loss: 0.8554373979568481:  61%|██████    | 15726/25880 [3:13:25<2:02:11,  1.38it/s]
1|15727|Loss: 0.8554373979568481:  61%|██████    | 15727/25880 [3:13:25<1:59:37,  1.41it/s]
1|15728|Loss: 0.8381494283676147:  61%|██████    | 15727/25880 [3:13:25<1:59:37,  1.41it/s]
1|15728|Loss: 0.8381494283676147:  61%|██████    | 15728/25880 [3:13:26<1:55:14,  1.47it/s]
1|15729|Loss: 0.7831006050109863:  61%|██████    | 15728/25880 [3:13:26<1:55:14,  1.47it/s]
1|15729|Loss: 0.7831006050109863:  61%|██████    | 15729/25880 [3:13:27<2:02:29,  1.38it/s]
1|15730|Loss: 0.8782467842102051:  61%|██████    | 15729/25880 [3:13:27<2:02:29,  1.38it/s]
1|15730|Loss: 0.8782467842102051:  61%|██████    | 15730/25880 [3:13:27<2:00:01,  1.41it/s]
1|15731|Loss: 0.9024794101715088:  61%|██████    | 15730/25880 [3:13:28<2:00:01,  1.41it/s]
1|15731|Loss: 0.9024794101715088:  61%|██████    | 15731/25880 [3:13:28<1:58:58,  1.42it/s]
1|15732|Loss: 0.9352786540985107:  61%|██████    | 15731/25880 [3:13:28<1:58:58,  1.42it/s]
1|15732|Loss: 0.9352786540985107:  61%|██████    | 15732/25880 [3:13:29<2:02:18,  1.38it/s]
1|15733|Loss: 0.8454397916793823:  61%|██████    | 15732/25880 [3:13:29<2:02:18,  1.38it/s]
1|15733|Loss: 0.8454397916793823:  61%|██████    | 15733/25880 [3:13:29<2:03:29,  1.37it/s]
1|15734|Loss: 0.9221034646034241:  61%|██████    | 15733/25880 [3:13:30<2:03:29,  1.37it/s]
1|15734|Loss: 0.9221034646034241:  61%|██████    | 15734/25880 [3:13:30<1:59:44,  1.41it/s]
1|15735|Loss: 0.7263079285621643:  61%|██████    | 15734/25880 [3:13:30<1:59:44,  1.41it/s]
1|15735|Loss: 0.7263079285621643:  61%|██████    | 15735/25880 [3:13:31<1:51:55,  1.51it/s]
1|15736|Loss: 0.7837855219841003:  61%|██████    | 15735/25880 [3:13:31<1:51:55,  1.51it/s]
1|15736|Loss: 0.7837855219841003:  61%|██████    | 15736/25880 [3:13:31<1:51:52,  1.51it/s]
1|15737|Loss: 0.9329718947410583:  61%|██████    | 15736/25880 [3:13:32<1:51:52,  1.51it/s]
1|15737|Loss: 0.9329718947410583:  61%|██████    | 15737/25880 [3:13:32<1:45:46,  1.60it/s]
1|15738|Loss: 0.8722257614135742:  61%|██████    | 15737/25880 [3:13:32<1:45:46,  1.60it/s]
1|15738|Loss: 0.8722257614135742:  61%|██████    | 15738/25880 [3:13:33<1:53:34,  1.49it/s]
1|15739|Loss: 0.8666603565216064:  61%|██████    | 15738/25880 [3:13:33<1:53:34,  1.49it/s]
1|15739|Loss: 0.8666603565216064:  61%|██████    | 15739/25880 [3:13:33<2:03:48,  1.37it/s]
1|15740|Loss: 1.0570499897003174:  61%|██████    | 15739/25880 [3:13:34<2:03:48,  1.37it/s]
1|15740|Loss: 1.0570499897003174:  61%|██████    | 15740/25880 [3:13:34<2:08:32,  1.31it/s]
1|15741|Loss: 0.8595708012580872:  61%|██████    | 15740/25880 [3:13:35<2:08:32,  1.31it/s]
1|15741|Loss: 0.8595708012580872:  61%|██████    | 15741/25880 [3:13:35<2:04:16,  1.36it/s]
1|15742|Loss: 0.947151243686676:  61%|██████    | 15741/25880 [3:13:35<2:04:16,  1.36it/s] 
1|15742|Loss: 0.947151243686676:  61%|██████    | 15742/25880 [3:13:36<1:58:22,  1.43it/s]
1|15743|Loss: 0.7446854710578918:  61%|██████    | 15742/25880 [3:13:36<1:58:22,  1.43it/s]
1|15743|Loss: 0.7446854710578918:  61%|██████    | 15743/25880 [3:13:36<1:47:10,  1.58it/s]
1|15744|Loss: 0.7787103056907654:  61%|██████    | 15743/25880 [3:13:36<1:47:10,  1.58it/s]
1|15744|Loss: 0.7787103056907654:  61%|██████    | 15744/25880 [3:13:37<1:54:05,  1.48it/s]
1|15745|Loss: 0.8756207823753357:  61%|██████    | 15744/25880 [3:13:37<1:54:05,  1.48it/s]
1|15745|Loss: 0.8756207823753357:  61%|██████    | 15745/25880 [3:13:38<1:57:11,  1.44it/s]
1|15746|Loss: 0.7795777916908264:  61%|██████    | 15745/25880 [3:13:38<1:57:11,  1.44it/s]
1|15746|Loss: 0.7795777916908264:  61%|██████    | 15746/25880 [3:13:38<2:06:26,  1.34it/s]
1|15747|Loss: 0.9539068341255188:  61%|██████    | 15746/25880 [3:13:39<2:06:26,  1.34it/s]
1|15747|Loss: 0.9539068341255188:  61%|██████    | 15747/25880 [3:13:39<2:07:28,  1.32it/s]
1|15748|Loss: 0.6160940527915955:  61%|██████    | 15747/25880 [3:13:40<2:07:28,  1.32it/s]
1|15748|Loss: 0.6160940527915955:  61%|██████    | 15748/25880 [3:13:41<2:42:31,  1.04it/s]
1|15749|Loss: 0.9355615377426147:  61%|██████    | 15748/25880 [3:13:41<2:42:31,  1.04it/s]
1|15749|Loss: 0.9355615377426147:  61%|██████    | 15749/25880 [3:13:42<2:46:09,  1.02it/s]
1|15750|Loss: 0.7467848062515259:  61%|██████    | 15749/25880 [3:13:42<2:46:09,  1.02it/s]
1|15750|Loss: 0.7467848062515259:  61%|██████    | 15750/25880 [3:13:43<2:37:17,  1.07it/s]
1|15751|Loss: 0.8190542459487915:  61%|██████    | 15750/25880 [3:13:43<2:37:17,  1.07it/s]
1|15751|Loss: 0.8190542459487915:  61%|██████    | 15751/25880 [3:13:43<2:32:39,  1.11it/s]
1|15752|Loss: 0.8531327843666077:  61%|██████    | 15751/25880 [3:13:44<2:32:39,  1.11it/s]
1|15752|Loss: 0.8531327843666077:  61%|██████    | 15752/25880 [3:13:44<2:30:26,  1.12it/s]
1|15753|Loss: 0.9123101830482483:  61%|██████    | 15752/25880 [3:13:45<2:30:26,  1.12it/s]
1|15753|Loss: 0.9123101830482483:  61%|██████    | 15753/25880 [3:13:45<2:15:48,  1.24it/s]
1|15754|Loss: 0.7570641040802002:  61%|██████    | 15753/25880 [3:13:45<2:15:48,  1.24it/s]
1|15754|Loss: 0.7570641040802002:  61%|██████    | 15754/25880 [3:13:45<2:05:26,  1.35it/s]
1|15755|Loss: 0.8630431294441223:  61%|██████    | 15754/25880 [3:13:46<2:05:26,  1.35it/s]
1|15755|Loss: 0.8630431294441223:  61%|██████    | 15755/25880 [3:13:46<2:03:39,  1.36it/s]
1|15756|Loss: 0.873676061630249:  61%|██████    | 15755/25880 [3:13:46<2:03:39,  1.36it/s] 
1|15756|Loss: 0.873676061630249:  61%|██████    | 15756/25880 [3:13:47<1:54:34,  1.47it/s]
1|15757|Loss: 0.7831619381904602:  61%|██████    | 15756/25880 [3:13:47<1:54:34,  1.47it/s]
1|15757|Loss: 0.7831619381904602:  61%|██████    | 15757/25880 [3:13:48<2:02:10,  1.38it/s]
1|15758|Loss: 0.787494421005249:  61%|██████    | 15757/25880 [3:13:48<2:02:10,  1.38it/s] 
1|15758|Loss: 0.787494421005249:  61%|██████    | 15758/25880 [3:13:48<2:04:39,  1.35it/s]
1|15759|Loss: 0.8551666736602783:  61%|██████    | 15758/25880 [3:13:49<2:04:39,  1.35it/s]
1|15759|Loss: 0.8551666736602783:  61%|██████    | 15759/25880 [3:13:49<2:06:53,  1.33it/s]
1|15760|Loss: 0.8321940898895264:  61%|██████    | 15759/25880 [3:13:49<2:06:53,  1.33it/s]
1|15760|Loss: 0.8321940898895264:  61%|██████    | 15760/25880 [3:13:50<2:05:14,  1.35it/s]
1|15761|Loss: 0.9986633658409119:  61%|██████    | 15760/25880 [3:13:50<2:05:14,  1.35it/s]
1|15761|Loss: 0.9986633658409119:  61%|██████    | 15761/25880 [3:13:50<1:53:07,  1.49it/s]
1|15762|Loss: 0.8786279559135437:  61%|██████    | 15761/25880 [3:13:51<1:53:07,  1.49it/s]
1|15762|Loss: 0.8786279559135437:  61%|██████    | 15762/25880 [3:13:51<1:48:24,  1.56it/s]
1|15763|Loss: 0.7890573143959045:  61%|██████    | 15762/25880 [3:13:51<1:48:24,  1.56it/s]
1|15763|Loss: 0.7890573143959045:  61%|██████    | 15763/25880 [3:13:51<1:45:26,  1.60it/s]
1|15764|Loss: 0.8080919981002808:  61%|██████    | 15763/25880 [3:13:52<1:45:26,  1.60it/s]
1|15764|Loss: 0.8080919981002808:  61%|██████    | 15764/25880 [3:13:52<1:44:36,  1.61it/s]
1|15765|Loss: 0.8101953864097595:  61%|██████    | 15764/25880 [3:13:52<1:44:36,  1.61it/s]
1|15765|Loss: 0.8101953864097595:  61%|██████    | 15765/25880 [3:13:53<1:51:20,  1.51it/s]
1|15766|Loss: 0.9647476077079773:  61%|██████    | 15765/25880 [3:13:53<1:51:20,  1.51it/s]
1|15766|Loss: 0.9647476077079773:  61%|██████    | 15766/25880 [3:13:53<1:52:14,  1.50it/s]
1|15767|Loss: 0.90943443775177:  61%|██████    | 15766/25880 [3:13:54<1:52:14,  1.50it/s]  
1|15767|Loss: 0.90943443775177:  61%|██████    | 15767/25880 [3:13:54<1:50:02,  1.53it/s]
1|15768|Loss: 0.8036602139472961:  61%|██████    | 15767/25880 [3:13:54<1:50:02,  1.53it/s]
1|15768|Loss: 0.8036602139472961:  61%|██████    | 15768/25880 [3:13:55<1:49:11,  1.54it/s]
1|15769|Loss: 0.7833607792854309:  61%|██████    | 15768/25880 [3:13:55<1:49:11,  1.54it/s]
1|15769|Loss: 0.7833607792854309:  61%|██████    | 15769/25880 [3:13:55<1:52:09,  1.50it/s]
1|15770|Loss: 0.830493688583374:  61%|██████    | 15769/25880 [3:13:56<1:52:09,  1.50it/s] 
1|15770|Loss: 0.830493688583374:  61%|██████    | 15770/25880 [3:13:56<1:55:15,  1.46it/s]
1|15771|Loss: 0.7729212045669556:  61%|██████    | 15770/25880 [3:13:57<1:55:15,  1.46it/s]
1|15771|Loss: 0.7729212045669556:  61%|██████    | 15771/25880 [3:13:57<1:46:26,  1.58it/s]
1|15772|Loss: 0.8341919779777527:  61%|██████    | 15771/25880 [3:13:57<1:46:26,  1.58it/s]
1|15772|Loss: 0.8341919779777527:  61%|██████    | 15772/25880 [3:13:57<1:44:31,  1.61it/s]
1|15773|Loss: 0.961359441280365:  61%|██████    | 15772/25880 [3:13:58<1:44:31,  1.61it/s] 
1|15773|Loss: 0.961359441280365:  61%|██████    | 15773/25880 [3:13:58<1:55:30,  1.46it/s]
1|15774|Loss: 1.0612982511520386:  61%|██████    | 15773/25880 [3:13:59<1:55:30,  1.46it/s]
1|15774|Loss: 1.0612982511520386:  61%|██████    | 15774/25880 [3:14:00<2:33:42,  1.10it/s]
1|15775|Loss: 0.8798990249633789:  61%|██████    | 15774/25880 [3:14:00<2:33:42,  1.10it/s]
1|15775|Loss: 0.8798990249633789:  61%|██████    | 15775/25880 [3:14:00<2:28:23,  1.13it/s]
1|15776|Loss: 0.9272719025611877:  61%|██████    | 15775/25880 [3:14:01<2:28:23,  1.13it/s]
1|15776|Loss: 0.9272719025611877:  61%|██████    | 15776/25880 [3:14:01<2:21:34,  1.19it/s]
1|15777|Loss: 0.8871983289718628:  61%|██████    | 15776/25880 [3:14:01<2:21:34,  1.19it/s]
1|15777|Loss: 0.8871983289718628:  61%|██████    | 15777/25880 [3:14:02<2:09:04,  1.30it/s]
1|15778|Loss: 0.8530508875846863:  61%|██████    | 15777/25880 [3:14:02<2:09:04,  1.30it/s]
1|15778|Loss: 0.8530508875846863:  61%|██████    | 15778/25880 [3:14:02<1:57:11,  1.44it/s]
1|15779|Loss: 0.7369376420974731:  61%|██████    | 15778/25880 [3:14:03<1:57:11,  1.44it/s]
1|15779|Loss: 0.7369376420974731:  61%|██████    | 15779/25880 [3:14:03<2:01:58,  1.38it/s]
1|15780|Loss: 0.9476523995399475:  61%|██████    | 15779/25880 [3:14:03<2:01:58,  1.38it/s]
1|15780|Loss: 0.9476523995399475:  61%|██████    | 15780/25880 [3:14:04<1:58:11,  1.42it/s]
1|15781|Loss: 0.9129334688186646:  61%|██████    | 15780/25880 [3:14:04<1:58:11,  1.42it/s]
1|15781|Loss: 0.9129334688186646:  61%|██████    | 15781/25880 [3:14:04<1:56:59,  1.44it/s]
1|15782|Loss: 0.825674831867218:  61%|██████    | 15781/25880 [3:14:05<1:56:59,  1.44it/s] 
1|15782|Loss: 0.825674831867218:  61%|██████    | 15782/25880 [3:14:05<1:53:46,  1.48it/s]
1|15783|Loss: 0.7307947278022766:  61%|██████    | 15782/25880 [3:14:05<1:53:46,  1.48it/s]
1|15783|Loss: 0.7307947278022766:  61%|██████    | 15783/25880 [3:14:06<1:57:36,  1.43it/s]
1|15784|Loss: 0.9711855053901672:  61%|██████    | 15783/25880 [3:14:06<1:57:36,  1.43it/s]
1|15784|Loss: 0.9711855053901672:  61%|██████    | 15784/25880 [3:14:06<1:59:45,  1.41it/s]
1|15785|Loss: 0.8786537051200867:  61%|██████    | 15784/25880 [3:14:07<1:59:45,  1.41it/s]
1|15785|Loss: 0.8786537051200867:  61%|██████    | 15785/25880 [3:14:07<2:07:51,  1.32it/s]
1|15786|Loss: 0.8534420728683472:  61%|██████    | 15785/25880 [3:14:08<2:07:51,  1.32it/s]
1|15786|Loss: 0.8534420728683472:  61%|██████    | 15786/25880 [3:14:08<2:03:29,  1.36it/s]
1|15787|Loss: 0.8182870149612427:  61%|██████    | 15786/25880 [3:14:08<2:03:29,  1.36it/s]
1|15787|Loss: 0.8182870149612427:  61%|██████    | 15787/25880 [3:14:09<2:01:22,  1.39it/s]
1|15788|Loss: 0.8414478302001953:  61%|██████    | 15787/25880 [3:14:09<2:01:22,  1.39it/s]
1|15788|Loss: 0.8414478302001953:  61%|██████    | 15788/25880 [3:14:09<1:55:23,  1.46it/s]
1|15789|Loss: 0.7152796983718872:  61%|██████    | 15788/25880 [3:14:10<1:55:23,  1.46it/s]
1|15789|Loss: 0.7152796983718872:  61%|██████    | 15789/25880 [3:14:10<2:00:00,  1.40it/s]
1|15790|Loss: 0.8558275103569031:  61%|██████    | 15789/25880 [3:14:11<2:00:00,  1.40it/s]
1|15790|Loss: 0.8558275103569031:  61%|██████    | 15790/25880 [3:14:11<1:56:59,  1.44it/s]
1|15791|Loss: 0.8266341090202332:  61%|██████    | 15790/25880 [3:14:11<1:56:59,  1.44it/s]
1|15791|Loss: 0.8266341090202332:  61%|██████    | 15791/25880 [3:14:12<2:02:17,  1.38it/s]
1|15792|Loss: 0.7353850603103638:  61%|██████    | 15791/25880 [3:14:12<2:02:17,  1.38it/s]
1|15792|Loss: 0.7353850603103638:  61%|██████    | 15792/25880 [3:14:12<2:12:00,  1.27it/s]
1|15793|Loss: 0.8252846002578735:  61%|██████    | 15792/25880 [3:14:13<2:12:00,  1.27it/s]
1|15793|Loss: 0.8252846002578735:  61%|██████    | 15793/25880 [3:14:13<2:06:28,  1.33it/s]
1|15794|Loss: 0.6657255291938782:  61%|██████    | 15793/25880 [3:14:14<2:06:28,  1.33it/s]
1|15794|Loss: 0.6657255291938782:  61%|██████    | 15794/25880 [3:14:14<2:08:44,  1.31it/s]
1|15795|Loss: 0.8595567345619202:  61%|██████    | 15794/25880 [3:14:14<2:08:44,  1.31it/s]
1|15795|Loss: 0.8595567345619202:  61%|██████    | 15795/25880 [3:14:15<2:08:53,  1.30it/s]
1|15796|Loss: 0.9531626105308533:  61%|██████    | 15795/25880 [3:14:15<2:08:53,  1.30it/s]
1|15796|Loss: 0.9531626105308533:  61%|██████    | 15796/25880 [3:14:15<2:02:45,  1.37it/s]
1|15797|Loss: 0.9026312828063965:  61%|██████    | 15796/25880 [3:14:16<2:02:45,  1.37it/s]
1|15797|Loss: 0.9026312828063965:  61%|██████    | 15797/25880 [3:14:16<2:05:24,  1.34it/s]
1|15798|Loss: 1.0171061754226685:  61%|██████    | 15797/25880 [3:14:17<2:05:24,  1.34it/s]
1|15798|Loss: 1.0171061754226685:  61%|██████    | 15798/25880 [3:14:17<2:13:22,  1.26it/s]
1|15799|Loss: 0.9087011218070984:  61%|██████    | 15798/25880 [3:14:17<2:13:22,  1.26it/s]
1|15799|Loss: 0.9087011218070984:  61%|██████    | 15799/25880 [3:14:18<2:06:21,  1.33it/s]
1|15800|Loss: 0.9024608731269836:  61%|██████    | 15799/25880 [3:14:18<2:06:21,  1.33it/s]
1|15800|Loss: 0.9024608731269836:  61%|██████    | 15800/25880 [3:14:18<1:57:38,  1.43it/s]
1|15801|Loss: 0.8256487846374512:  61%|██████    | 15800/25880 [3:14:19<1:57:38,  1.43it/s]
1|15801|Loss: 0.8256487846374512:  61%|██████    | 15801/25880 [3:14:19<1:56:29,  1.44it/s]
1|15802|Loss: 0.794977068901062:  61%|██████    | 15801/25880 [3:14:19<1:56:29,  1.44it/s] 
1|15802|Loss: 0.794977068901062:  61%|██████    | 15802/25880 [3:14:20<1:58:11,  1.42it/s]
1|15803|Loss: 0.8847560882568359:  61%|██████    | 15802/25880 [3:14:20<1:58:11,  1.42it/s]
1|15803|Loss: 0.8847560882568359:  61%|██████    | 15803/25880 [3:14:20<2:01:38,  1.38it/s]
1|15804|Loss: 0.811938464641571:  61%|██████    | 15803/25880 [3:14:21<2:01:38,  1.38it/s] 
1|15804|Loss: 0.811938464641571:  61%|██████    | 15804/25880 [3:14:21<1:59:20,  1.41it/s]
1|15805|Loss: 0.828433096408844:  61%|██████    | 15804/25880 [3:14:22<1:59:20,  1.41it/s]
1|15805|Loss: 0.828433096408844:  61%|██████    | 15805/25880 [3:14:22<2:01:35,  1.38it/s]
1|15806|Loss: 0.8606765866279602:  61%|██████    | 15805/25880 [3:14:22<2:01:35,  1.38it/s]
1|15806|Loss: 0.8606765866279602:  61%|██████    | 15806/25880 [3:14:23<2:03:20,  1.36it/s]
1|15807|Loss: 0.8122966885566711:  61%|██████    | 15806/25880 [3:14:23<2:03:20,  1.36it/s]
1|15807|Loss: 0.8122966885566711:  61%|██████    | 15807/25880 [3:14:23<2:04:09,  1.35it/s]
1|15808|Loss: 0.8861919045448303:  61%|██████    | 15807/25880 [3:14:24<2:04:09,  1.35it/s]
1|15808|Loss: 0.8861919045448303:  61%|██████    | 15808/25880 [3:14:24<2:00:38,  1.39it/s]
1|15809|Loss: 0.8318864107131958:  61%|██████    | 15808/25880 [3:14:24<2:00:38,  1.39it/s]
1|15809|Loss: 0.8318864107131958:  61%|██████    | 15809/25880 [3:14:25<1:56:09,  1.44it/s]
1|15810|Loss: 0.8241217732429504:  61%|██████    | 15809/25880 [3:14:25<1:56:09,  1.44it/s]
1|15810|Loss: 0.8241217732429504:  61%|██████    | 15810/25880 [3:14:25<1:53:35,  1.48it/s]
1|15811|Loss: 0.9168392419815063:  61%|██████    | 15810/25880 [3:14:26<1:53:35,  1.48it/s]
1|15811|Loss: 0.9168392419815063:  61%|██████    | 15811/25880 [3:14:26<1:49:56,  1.53it/s]
1|15812|Loss: 0.8126652240753174:  61%|██████    | 15811/25880 [3:14:26<1:49:56,  1.53it/s]
1|15812|Loss: 0.8126652240753174:  61%|██████    | 15812/25880 [3:14:27<1:52:02,  1.50it/s]
1|15813|Loss: 0.8246996998786926:  61%|██████    | 15812/25880 [3:14:27<1:52:02,  1.50it/s]
1|15813|Loss: 0.8246996998786926:  61%|██████    | 15813/25880 [3:14:27<1:56:03,  1.45it/s]
1|15814|Loss: 0.8936493396759033:  61%|██████    | 15813/25880 [3:14:28<1:56:03,  1.45it/s]
1|15814|Loss: 0.8936493396759033:  61%|██████    | 15814/25880 [3:14:28<1:54:42,  1.46it/s]
1|15815|Loss: 0.7249995470046997:  61%|██████    | 15814/25880 [3:14:28<1:54:42,  1.46it/s]
1|15815|Loss: 0.7249995470046997:  61%|██████    | 15815/25880 [3:14:29<1:56:09,  1.44it/s]
1|15816|Loss: 1.022340178489685:  61%|██████    | 15815/25880 [3:14:29<1:56:09,  1.44it/s] 
1|15816|Loss: 1.022340178489685:  61%|██████    | 15816/25880 [3:14:29<1:52:07,  1.50it/s]
1|15817|Loss: 0.9674471020698547:  61%|██████    | 15816/25880 [3:14:30<1:52:07,  1.50it/s]
1|15817|Loss: 0.9674471020698547:  61%|██████    | 15817/25880 [3:14:30<2:01:28,  1.38it/s]
1|15818|Loss: 0.8347949981689453:  61%|██████    | 15817/25880 [3:14:31<2:01:28,  1.38it/s]
1|15818|Loss: 0.8347949981689453:  61%|██████    | 15818/25880 [3:14:31<2:02:38,  1.37it/s]
1|15819|Loss: 0.8790814876556396:  61%|██████    | 15818/25880 [3:14:31<2:02:38,  1.37it/s]
1|15819|Loss: 0.8790814876556396:  61%|██████    | 15819/25880 [3:14:32<2:02:55,  1.36it/s]
1|15820|Loss: 0.84940105676651:  61%|██████    | 15819/25880 [3:14:32<2:02:55,  1.36it/s]  
1|15820|Loss: 0.84940105676651:  61%|██████    | 15820/25880 [3:14:33<2:08:07,  1.31it/s]
1|15821|Loss: 0.8409523367881775:  61%|██████    | 15820/25880 [3:14:33<2:08:07,  1.31it/s]
1|15821|Loss: 0.8409523367881775:  61%|██████    | 15821/25880 [3:14:33<2:06:37,  1.32it/s]
1|15822|Loss: 0.8634423613548279:  61%|██████    | 15821/25880 [3:14:34<2:06:37,  1.32it/s]
1|15822|Loss: 0.8634423613548279:  61%|██████    | 15822/25880 [3:14:34<2:12:26,  1.27it/s]
1|15823|Loss: 0.9027408957481384:  61%|██████    | 15822/25880 [3:14:35<2:12:26,  1.27it/s]
1|15823|Loss: 0.9027408957481384:  61%|██████    | 15823/25880 [3:14:35<2:06:40,  1.32it/s]
1|15824|Loss: 0.8230346441268921:  61%|██████    | 15823/25880 [3:14:35<2:06:40,  1.32it/s]
1|15824|Loss: 0.8230346441268921:  61%|██████    | 15824/25880 [3:14:36<2:03:08,  1.36it/s]
1|15825|Loss: 0.9348065853118896:  61%|██████    | 15824/25880 [3:14:36<2:03:08,  1.36it/s]
1|15825|Loss: 0.9348065853118896:  61%|██████    | 15825/25880 [3:14:36<2:01:28,  1.38it/s]
1|15826|Loss: 0.9303802251815796:  61%|██████    | 15825/25880 [3:14:37<2:01:28,  1.38it/s]
1|15826|Loss: 0.9303802251815796:  61%|██████    | 15826/25880 [3:14:37<2:05:33,  1.33it/s]
1|15827|Loss: 0.836093544960022:  61%|██████    | 15826/25880 [3:14:37<2:05:33,  1.33it/s] 
1|15827|Loss: 0.836093544960022:  61%|██████    | 15827/25880 [3:14:38<2:05:29,  1.34it/s]
1|15828|Loss: 0.7649586200714111:  61%|██████    | 15827/25880 [3:14:38<2:05:29,  1.34it/s]
1|15828|Loss: 0.7649586200714111:  61%|██████    | 15828/25880 [3:14:39<2:07:11,  1.32it/s]
1|15829|Loss: 0.8535467982292175:  61%|██████    | 15828/25880 [3:14:39<2:07:11,  1.32it/s]
1|15829|Loss: 0.8535467982292175:  61%|██████    | 15829/25880 [3:14:39<2:08:33,  1.30it/s]
1|15830|Loss: 0.847551703453064:  61%|██████    | 15829/25880 [3:14:40<2:08:33,  1.30it/s] 
1|15830|Loss: 0.847551703453064:  61%|██████    | 15830/25880 [3:14:40<2:07:19,  1.32it/s]
1|15831|Loss: 0.9091658592224121:  61%|██████    | 15830/25880 [3:14:40<2:07:19,  1.32it/s]
1|15831|Loss: 0.9091658592224121:  61%|██████    | 15831/25880 [3:14:41<1:58:41,  1.41it/s]
1|15832|Loss: 0.7865283489227295:  61%|██████    | 15831/25880 [3:14:41<1:58:41,  1.41it/s]
1|15832|Loss: 0.7865283489227295:  61%|██████    | 15832/25880 [3:14:41<1:48:07,  1.55it/s]
1|15833|Loss: 0.7051212787628174:  61%|██████    | 15832/25880 [3:14:42<1:48:07,  1.55it/s]
1|15833|Loss: 0.7051212787628174:  61%|██████    | 15833/25880 [3:14:42<1:48:41,  1.54it/s]
1|15834|Loss: 0.7910603284835815:  61%|██████    | 15833/25880 [3:14:42<1:48:41,  1.54it/s]
1|15834|Loss: 0.7910603284835815:  61%|██████    | 15834/25880 [3:14:43<1:56:23,  1.44it/s]
1|15835|Loss: 0.742733895778656:  61%|██████    | 15834/25880 [3:14:43<1:56:23,  1.44it/s] 
1|15835|Loss: 0.742733895778656:  61%|██████    | 15835/25880 [3:14:43<1:59:23,  1.40it/s]
1|15836|Loss: 0.9157789945602417:  61%|██████    | 15835/25880 [3:14:44<1:59:23,  1.40it/s]
1|15836|Loss: 0.9157789945602417:  61%|██████    | 15836/25880 [3:14:44<1:56:55,  1.43it/s]
1|15837|Loss: 0.747603178024292:  61%|██████    | 15836/25880 [3:14:45<1:56:55,  1.43it/s] 
1|15837|Loss: 0.747603178024292:  61%|██████    | 15837/25880 [3:14:45<2:02:32,  1.37it/s]
1|15838|Loss: 0.8973387479782104:  61%|██████    | 15837/25880 [3:14:45<2:02:32,  1.37it/s]
1|15838|Loss: 0.8973387479782104:  61%|██████    | 15838/25880 [3:14:46<2:00:14,  1.39it/s]
1|15839|Loss: 0.8877085447311401:  61%|██████    | 15838/25880 [3:14:46<2:00:14,  1.39it/s]
1|15839|Loss: 0.8877085447311401:  61%|██████    | 15839/25880 [3:14:46<2:01:57,  1.37it/s]
1|15840|Loss: 0.7353625893592834:  61%|██████    | 15839/25880 [3:14:47<2:01:57,  1.37it/s]
1|15840|Loss: 0.7353625893592834:  61%|██████    | 15840/25880 [3:14:47<1:58:01,  1.42it/s]
1|15841|Loss: 0.8121451735496521:  61%|██████    | 15840/25880 [3:14:47<1:58:01,  1.42it/s]
1|15841|Loss: 0.8121451735496521:  61%|██████    | 15841/25880 [3:14:48<1:56:52,  1.43it/s]
1|15842|Loss: 0.9460504651069641:  61%|██████    | 15841/25880 [3:14:48<1:56:52,  1.43it/s]
1|15842|Loss: 0.9460504651069641:  61%|██████    | 15842/25880 [3:14:48<1:50:12,  1.52it/s]
1|15843|Loss: 0.8337966203689575:  61%|██████    | 15842/25880 [3:14:49<1:50:12,  1.52it/s]
1|15843|Loss: 0.8337966203689575:  61%|██████    | 15843/25880 [3:14:49<1:51:38,  1.50it/s]
1|15844|Loss: 0.7780294418334961:  61%|██████    | 15843/25880 [3:14:49<1:51:38,  1.50it/s]
1|15844|Loss: 0.7780294418334961:  61%|██████    | 15844/25880 [3:14:49<1:43:58,  1.61it/s]
1|15845|Loss: 0.7841612696647644:  61%|██████    | 15844/25880 [3:14:50<1:43:58,  1.61it/s]
1|15845|Loss: 0.7841612696647644:  61%|██████    | 15845/25880 [3:14:50<1:37:33,  1.71it/s]
1|15846|Loss: 0.8443160057067871:  61%|██████    | 15845/25880 [3:14:50<1:37:33,  1.71it/s]
1|15846|Loss: 0.8443160057067871:  61%|██████    | 15846/25880 [3:14:51<1:39:05,  1.69it/s]
1|15847|Loss: 0.8904208540916443:  61%|██████    | 15846/25880 [3:14:51<1:39:05,  1.69it/s]
1|15847|Loss: 0.8904208540916443:  61%|██████    | 15847/25880 [3:14:51<1:51:01,  1.51it/s]
1|15848|Loss: 0.9607694745063782:  61%|██████    | 15847/25880 [3:14:52<1:51:01,  1.51it/s]
1|15848|Loss: 0.9607694745063782:  61%|██████    | 15848/25880 [3:14:52<1:45:12,  1.59it/s]
1|15849|Loss: 0.7243891358375549:  61%|██████    | 15848/25880 [3:14:52<1:45:12,  1.59it/s]
1|15849|Loss: 0.7243891358375549:  61%|██████    | 15849/25880 [3:14:53<1:52:52,  1.48it/s]
1|15850|Loss: 0.7550083994865417:  61%|██████    | 15849/25880 [3:14:53<1:52:52,  1.48it/s]
1|15850|Loss: 0.7550083994865417:  61%|██████    | 15850/25880 [3:14:53<1:49:16,  1.53it/s]
1|15851|Loss: 0.8029928803443909:  61%|██████    | 15850/25880 [3:14:54<1:49:16,  1.53it/s]
1|15851|Loss: 0.8029928803443909:  61%|██████    | 15851/25880 [3:14:54<1:57:13,  1.43it/s]
1|15852|Loss: 0.83259117603302:  61%|██████    | 15851/25880 [3:14:55<1:57:13,  1.43it/s]  
1|15852|Loss: 0.83259117603302:  61%|██████▏   | 15852/25880 [3:14:55<1:57:04,  1.43it/s]
1|15853|Loss: 0.7595694065093994:  61%|██████▏   | 15852/25880 [3:14:55<1:57:04,  1.43it/s]
1|15853|Loss: 0.7595694065093994:  61%|██████▏   | 15853/25880 [3:14:55<1:53:05,  1.48it/s]
1|15854|Loss: 0.9357544779777527:  61%|██████▏   | 15853/25880 [3:14:56<1:53:05,  1.48it/s]
1|15854|Loss: 0.9357544779777527:  61%|██████▏   | 15854/25880 [3:14:56<1:56:53,  1.43it/s]
1|15855|Loss: 0.7904559373855591:  61%|██████▏   | 15854/25880 [3:14:57<1:56:53,  1.43it/s]
1|15855|Loss: 0.7904559373855591:  61%|██████▏   | 15855/25880 [3:14:57<2:01:35,  1.37it/s]
1|15856|Loss: 0.9907002449035645:  61%|██████▏   | 15855/25880 [3:14:57<2:01:35,  1.37it/s]
1|15856|Loss: 0.9907002449035645:  61%|██████▏   | 15856/25880 [3:14:58<2:11:57,  1.27it/s]
1|15857|Loss: 0.750621497631073:  61%|██████▏   | 15856/25880 [3:14:58<2:11:57,  1.27it/s] 
1|15857|Loss: 0.750621497631073:  61%|██████▏   | 15857/25880 [3:14:59<2:12:02,  1.27it/s]
1|15858|Loss: 0.8932115435600281:  61%|██████▏   | 15857/25880 [3:14:59<2:12:02,  1.27it/s]
1|15858|Loss: 0.8932115435600281:  61%|██████▏   | 15858/25880 [3:15:00<2:13:10,  1.25it/s]
1|15859|Loss: 0.8849183320999146:  61%|██████▏   | 15858/25880 [3:15:00<2:13:10,  1.25it/s]
1|15859|Loss: 0.8849183320999146:  61%|██████▏   | 15859/25880 [3:15:00<2:13:38,  1.25it/s]
1|15860|Loss: 1.0004209280014038:  61%|██████▏   | 15859/25880 [3:15:01<2:13:38,  1.25it/s]
1|15860|Loss: 1.0004209280014038:  61%|██████▏   | 15860/25880 [3:15:01<2:13:38,  1.25it/s]
1|15861|Loss: 0.9016929864883423:  61%|██████▏   | 15860/25880 [3:15:02<2:13:38,  1.25it/s]
1|15861|Loss: 0.9016929864883423:  61%|██████▏   | 15861/25880 [3:15:02<2:11:04,  1.27it/s]
1|15862|Loss: 0.8260371088981628:  61%|██████▏   | 15861/25880 [3:15:02<2:11:04,  1.27it/s]
1|15862|Loss: 0.8260371088981628:  61%|██████▏   | 15862/25880 [3:15:03<2:05:03,  1.34it/s]
1|15863|Loss: 0.7185512781143188:  61%|██████▏   | 15862/25880 [3:15:03<2:05:03,  1.34it/s]
1|15863|Loss: 0.7185512781143188:  61%|██████▏   | 15863/25880 [3:15:03<1:48:40,  1.54it/s]
1|15864|Loss: 0.6811137199401855:  61%|██████▏   | 15863/25880 [3:15:03<1:48:40,  1.54it/s]
1|15864|Loss: 0.6811137199401855:  61%|██████▏   | 15864/25880 [3:15:04<1:43:08,  1.62it/s]
1|15865|Loss: 0.8083898425102234:  61%|██████▏   | 15864/25880 [3:15:04<1:43:08,  1.62it/s]
1|15865|Loss: 0.8083898425102234:  61%|██████▏   | 15865/25880 [3:15:04<1:38:47,  1.69it/s]
1|15866|Loss: 0.7799577713012695:  61%|██████▏   | 15865/25880 [3:15:04<1:38:47,  1.69it/s]
1|15866|Loss: 0.7799577713012695:  61%|██████▏   | 15866/25880 [3:15:05<1:45:42,  1.58it/s]
1|15867|Loss: 0.8860155344009399:  61%|██████▏   | 15866/25880 [3:15:05<1:45:42,  1.58it/s]
1|15867|Loss: 0.8860155344009399:  61%|██████▏   | 15867/25880 [3:15:06<1:52:03,  1.49it/s]
1|15868|Loss: 0.9073250889778137:  61%|██████▏   | 15867/25880 [3:15:06<1:52:03,  1.49it/s]
1|15868|Loss: 0.9073250889778137:  61%|██████▏   | 15868/25880 [3:15:06<1:59:07,  1.40it/s]
1|15869|Loss: 0.7866663932800293:  61%|██████▏   | 15868/25880 [3:15:07<1:59:07,  1.40it/s]
1|15869|Loss: 0.7866663932800293:  61%|██████▏   | 15869/25880 [3:15:07<1:56:58,  1.43it/s]
1|15870|Loss: 0.9089741110801697:  61%|██████▏   | 15869/25880 [3:15:07<1:56:58,  1.43it/s]
1|15870|Loss: 0.9089741110801697:  61%|██████▏   | 15870/25880 [3:15:08<1:53:01,  1.48it/s]
1|15871|Loss: 0.8299088478088379:  61%|██████▏   | 15870/25880 [3:15:08<1:53:01,  1.48it/s]
1|15871|Loss: 0.8299088478088379:  61%|██████▏   | 15871/25880 [3:15:08<1:55:02,  1.45it/s]
1|15872|Loss: 0.8202496767044067:  61%|██████▏   | 15871/25880 [3:15:09<1:55:02,  1.45it/s]
1|15872|Loss: 0.8202496767044067:  61%|██████▏   | 15872/25880 [3:15:09<1:57:28,  1.42it/s]
1|15873|Loss: 0.8469581604003906:  61%|██████▏   | 15872/25880 [3:15:10<1:57:28,  1.42it/s]
1|15873|Loss: 0.8469581604003906:  61%|██████▏   | 15873/25880 [3:15:10<2:00:52,  1.38it/s]
1|15874|Loss: 0.8076832294464111:  61%|██████▏   | 15873/25880 [3:15:10<2:00:52,  1.38it/s]
1|15874|Loss: 0.8076832294464111:  61%|██████▏   | 15874/25880 [3:15:10<1:56:15,  1.43it/s]
1|15875|Loss: 0.821626603603363:  61%|██████▏   | 15874/25880 [3:15:11<1:56:15,  1.43it/s] 
1|15875|Loss: 0.821626603603363:  61%|██████▏   | 15875/25880 [3:15:11<1:55:08,  1.45it/s]
1|15876|Loss: 0.9430436491966248:  61%|██████▏   | 15875/25880 [3:15:12<1:55:08,  1.45it/s]
1|15876|Loss: 0.9430436491966248:  61%|██████▏   | 15876/25880 [3:15:12<1:52:03,  1.49it/s]
1|15877|Loss: 0.8143718242645264:  61%|██████▏   | 15876/25880 [3:15:12<1:52:03,  1.49it/s]
1|15877|Loss: 0.8143718242645264:  61%|██████▏   | 15877/25880 [3:15:12<1:50:16,  1.51it/s]
1|15878|Loss: 0.9297240972518921:  61%|██████▏   | 15877/25880 [3:15:13<1:50:16,  1.51it/s]
1|15878|Loss: 0.9297240972518921:  61%|██████▏   | 15878/25880 [3:15:13<1:49:10,  1.53it/s]
1|15879|Loss: 0.7362585663795471:  61%|██████▏   | 15878/25880 [3:15:13<1:49:10,  1.53it/s]
1|15879|Loss: 0.7362585663795471:  61%|██████▏   | 15879/25880 [3:15:14<1:47:32,  1.55it/s]
1|15880|Loss: 0.9879143238067627:  61%|██████▏   | 15879/25880 [3:15:14<1:47:32,  1.55it/s]
1|15880|Loss: 0.9879143238067627:  61%|██████▏   | 15880/25880 [3:15:14<1:47:02,  1.56it/s]
1|15881|Loss: 0.9502792954444885:  61%|██████▏   | 15880/25880 [3:15:15<1:47:02,  1.56it/s]
1|15881|Loss: 0.9502792954444885:  61%|██████▏   | 15881/25880 [3:15:15<1:56:06,  1.44it/s]
1|15882|Loss: 0.8357527852058411:  61%|██████▏   | 15881/25880 [3:15:16<1:56:06,  1.44it/s]
1|15882|Loss: 0.8357527852058411:  61%|██████▏   | 15882/25880 [3:15:16<2:04:53,  1.33it/s]
1|15883|Loss: 0.8382419943809509:  61%|██████▏   | 15882/25880 [3:15:17<2:04:53,  1.33it/s]
1|15883|Loss: 0.8382419943809509:  61%|██████▏   | 15883/25880 [3:15:17<2:13:00,  1.25it/s]
1|15884|Loss: 0.7425700426101685:  61%|██████▏   | 15883/25880 [3:15:17<2:13:00,  1.25it/s]
1|15884|Loss: 0.7425700426101685:  61%|██████▏   | 15884/25880 [3:15:18<2:10:52,  1.27it/s]
1|15885|Loss: 0.7430680990219116:  61%|██████▏   | 15884/25880 [3:15:18<2:10:52,  1.27it/s]
1|15885|Loss: 0.7430680990219116:  61%|██████▏   | 15885/25880 [3:15:19<2:15:38,  1.23it/s]
1|15886|Loss: 0.9102060794830322:  61%|██████▏   | 15885/25880 [3:15:19<2:15:38,  1.23it/s]
1|15886|Loss: 0.9102060794830322:  61%|██████▏   | 15886/25880 [3:15:19<2:08:47,  1.29it/s]
1|15887|Loss: 0.7526124715805054:  61%|██████▏   | 15886/25880 [3:15:20<2:08:47,  1.29it/s]
1|15887|Loss: 0.7526124715805054:  61%|██████▏   | 15887/25880 [3:15:20<2:04:21,  1.34it/s]
1|15888|Loss: 0.7257407903671265:  61%|██████▏   | 15887/25880 [3:15:20<2:04:21,  1.34it/s]
1|15888|Loss: 0.7257407903671265:  61%|██████▏   | 15888/25880 [3:15:21<1:58:42,  1.40it/s]
1|15889|Loss: 0.7773470282554626:  61%|██████▏   | 15888/25880 [3:15:21<1:58:42,  1.40it/s]
1|15889|Loss: 0.7773470282554626:  61%|██████▏   | 15889/25880 [3:15:21<2:08:40,  1.29it/s]
1|15890|Loss: 0.9373132586479187:  61%|██████▏   | 15889/25880 [3:15:22<2:08:40,  1.29it/s]
1|15890|Loss: 0.9373132586479187:  61%|██████▏   | 15890/25880 [3:15:22<2:09:22,  1.29it/s]
1|15891|Loss: 0.7751926779747009:  61%|██████▏   | 15890/25880 [3:15:23<2:09:22,  1.29it/s]
1|15891|Loss: 0.7751926779747009:  61%|██████▏   | 15891/25880 [3:15:23<2:07:10,  1.31it/s]
1|15892|Loss: 0.835088312625885:  61%|██████▏   | 15891/25880 [3:15:23<2:07:10,  1.31it/s] 
1|15892|Loss: 0.835088312625885:  61%|██████▏   | 15892/25880 [3:15:24<2:02:13,  1.36it/s]
1|15893|Loss: 0.8241604566574097:  61%|██████▏   | 15892/25880 [3:15:24<2:02:13,  1.36it/s]
1|15893|Loss: 0.8241604566574097:  61%|██████▏   | 15893/25880 [3:15:24<2:06:12,  1.32it/s]
1|15894|Loss: 0.8228553533554077:  61%|██████▏   | 15893/25880 [3:15:25<2:06:12,  1.32it/s]
1|15894|Loss: 0.8228553533554077:  61%|██████▏   | 15894/25880 [3:15:25<2:02:35,  1.36it/s]
1|15895|Loss: 0.8558757901191711:  61%|██████▏   | 15894/25880 [3:15:26<2:02:35,  1.36it/s]
1|15895|Loss: 0.8558757901191711:  61%|██████▏   | 15895/25880 [3:15:26<2:02:02,  1.36it/s]
1|15896|Loss: 0.7956250905990601:  61%|██████▏   | 15895/25880 [3:15:26<2:02:02,  1.36it/s]
1|15896|Loss: 0.7956250905990601:  61%|██████▏   | 15896/25880 [3:15:27<2:05:34,  1.33it/s]
1|15897|Loss: 0.6950094103813171:  61%|██████▏   | 15896/25880 [3:15:27<2:05:34,  1.33it/s]
1|15897|Loss: 0.6950094103813171:  61%|██████▏   | 15897/25880 [3:15:27<2:00:31,  1.38it/s]
1|15898|Loss: 0.8622502684593201:  61%|██████▏   | 15897/25880 [3:15:28<2:00:31,  1.38it/s]
1|15898|Loss: 0.8622502684593201:  61%|██████▏   | 15898/25880 [3:15:28<1:58:31,  1.40it/s]
1|15899|Loss: 0.7544978857040405:  61%|██████▏   | 15898/25880 [3:15:28<1:58:31,  1.40it/s]
1|15899|Loss: 0.7544978857040405:  61%|██████▏   | 15899/25880 [3:15:29<1:59:35,  1.39it/s]
1|15900|Loss: 0.8108136057853699:  61%|██████▏   | 15899/25880 [3:15:29<1:59:35,  1.39it/s]
1|15900|Loss: 0.8108136057853699:  61%|██████▏   | 15900/25880 [3:15:30<2:00:14,  1.38it/s]
1|15901|Loss: 0.8956870436668396:  61%|██████▏   | 15900/25880 [3:15:30<2:00:14,  1.38it/s]
1|15901|Loss: 0.8956870436668396:  61%|██████▏   | 15901/25880 [3:15:30<2:02:50,  1.35it/s]
1|15902|Loss: 0.7984062433242798:  61%|██████▏   | 15901/25880 [3:15:31<2:02:50,  1.35it/s]
1|15902|Loss: 0.7984062433242798:  61%|██████▏   | 15902/25880 [3:15:31<1:50:13,  1.51it/s]
1|15903|Loss: 0.7881478071212769:  61%|██████▏   | 15902/25880 [3:15:31<1:50:13,  1.51it/s]
1|15903|Loss: 0.7881478071212769:  61%|██████▏   | 15903/25880 [3:15:31<1:52:59,  1.47it/s]
1|15904|Loss: 0.7576562166213989:  61%|██████▏   | 15903/25880 [3:15:32<1:52:59,  1.47it/s]
1|15904|Loss: 0.7576562166213989:  61%|██████▏   | 15904/25880 [3:15:32<1:52:47,  1.47it/s]
1|15905|Loss: 0.9799168109893799:  61%|██████▏   | 15904/25880 [3:15:33<1:52:47,  1.47it/s]
1|15905|Loss: 0.9799168109893799:  61%|██████▏   | 15905/25880 [3:15:33<1:49:51,  1.51it/s]
1|15906|Loss: 0.853122353553772:  61%|██████▏   | 15905/25880 [3:15:33<1:49:51,  1.51it/s] 
1|15906|Loss: 0.853122353553772:  61%|██████▏   | 15906/25880 [3:15:33<1:46:08,  1.57it/s]
1|15907|Loss: 0.9481896162033081:  61%|██████▏   | 15906/25880 [3:15:34<1:46:08,  1.57it/s]
1|15907|Loss: 0.9481896162033081:  61%|██████▏   | 15907/25880 [3:15:34<1:45:26,  1.58it/s]
1|15908|Loss: 0.9277722835540771:  61%|██████▏   | 15907/25880 [3:15:34<1:45:26,  1.58it/s]
1|15908|Loss: 0.9277722835540771:  61%|██████▏   | 15908/25880 [3:15:35<1:55:37,  1.44it/s]
1|15909|Loss: 0.6695729494094849:  61%|██████▏   | 15908/25880 [3:15:35<1:55:37,  1.44it/s]
1|15909|Loss: 0.6695729494094849:  61%|██████▏   | 15909/25880 [3:15:36<2:04:33,  1.33it/s]
1|15910|Loss: 0.8217738270759583:  61%|██████▏   | 15909/25880 [3:15:36<2:04:33,  1.33it/s]
1|15910|Loss: 0.8217738270759583:  61%|██████▏   | 15910/25880 [3:15:37<2:12:39,  1.25it/s]
1|15911|Loss: 0.8513998985290527:  61%|██████▏   | 15910/25880 [3:15:37<2:12:39,  1.25it/s]
1|15911|Loss: 0.8513998985290527:  61%|██████▏   | 15911/25880 [3:15:37<2:07:31,  1.30it/s]
1|15912|Loss: 0.8050802946090698:  61%|██████▏   | 15911/25880 [3:15:38<2:07:31,  1.30it/s]
1|15912|Loss: 0.8050802946090698:  61%|██████▏   | 15912/25880 [3:15:38<2:07:20,  1.30it/s]
1|15913|Loss: 0.825840175151825:  61%|██████▏   | 15912/25880 [3:15:39<2:07:20,  1.30it/s] 
1|15913|Loss: 0.825840175151825:  61%|██████▏   | 15913/25880 [3:15:39<2:06:44,  1.31it/s]
1|15914|Loss: 0.7689037919044495:  61%|██████▏   | 15913/25880 [3:15:39<2:06:44,  1.31it/s]
1|15914|Loss: 0.7689037919044495:  61%|██████▏   | 15914/25880 [3:15:40<2:06:07,  1.32it/s]
1|15915|Loss: 0.9152530431747437:  61%|██████▏   | 15914/25880 [3:15:40<2:06:07,  1.32it/s]
1|15915|Loss: 0.9152530431747437:  61%|██████▏   | 15915/25880 [3:15:40<2:05:03,  1.33it/s]
1|15916|Loss: 0.9196417331695557:  61%|██████▏   | 15915/25880 [3:15:41<2:05:03,  1.33it/s]
1|15916|Loss: 0.9196417331695557:  61%|██████▏   | 15916/25880 [3:15:41<2:03:52,  1.34it/s]
1|15917|Loss: 0.8390188813209534:  61%|██████▏   | 15916/25880 [3:15:41<2:03:52,  1.34it/s]
1|15917|Loss: 0.8390188813209534:  62%|██████▏   | 15917/25880 [3:15:42<2:07:42,  1.30it/s]
1|15918|Loss: 0.9244742393493652:  62%|██████▏   | 15917/25880 [3:15:42<2:07:42,  1.30it/s]
1|15918|Loss: 0.9244742393493652:  62%|██████▏   | 15918/25880 [3:15:43<2:02:45,  1.35it/s]
1|15919|Loss: 0.7831053733825684:  62%|██████▏   | 15918/25880 [3:15:43<2:02:45,  1.35it/s]
1|15919|Loss: 0.7831053733825684:  62%|██████▏   | 15919/25880 [3:15:43<2:01:38,  1.36it/s]
1|15920|Loss: 0.8932532072067261:  62%|██████▏   | 15919/25880 [3:15:44<2:01:38,  1.36it/s]
1|15920|Loss: 0.8932532072067261:  62%|██████▏   | 15920/25880 [3:15:44<2:07:33,  1.30it/s]
1|15921|Loss: 0.8652971386909485:  62%|██████▏   | 15920/25880 [3:15:45<2:07:33,  1.30it/s]
1|15921|Loss: 0.8652971386909485:  62%|██████▏   | 15921/25880 [3:15:45<2:06:15,  1.31it/s]
1|15922|Loss: 0.894661545753479:  62%|██████▏   | 15921/25880 [3:15:45<2:06:15,  1.31it/s] 
1|15922|Loss: 0.894661545753479:  62%|██████▏   | 15922/25880 [3:15:46<2:01:03,  1.37it/s]
1|15923|Loss: 0.7721590995788574:  62%|██████▏   | 15922/25880 [3:15:46<2:01:03,  1.37it/s]
1|15923|Loss: 0.7721590995788574:  62%|██████▏   | 15923/25880 [3:15:46<1:55:51,  1.43it/s]
1|15924|Loss: 0.8345866203308105:  62%|██████▏   | 15923/25880 [3:15:46<1:55:51,  1.43it/s]
1|15924|Loss: 0.8345866203308105:  62%|██████▏   | 15924/25880 [3:15:47<1:52:39,  1.47it/s]
1|15925|Loss: 0.8531895279884338:  62%|██████▏   | 15924/25880 [3:15:47<1:52:39,  1.47it/s]
1|15925|Loss: 0.8531895279884338:  62%|██████▏   | 15925/25880 [3:15:47<1:49:39,  1.51it/s]
1|15926|Loss: 0.844348132610321:  62%|██████▏   | 15925/25880 [3:15:48<1:49:39,  1.51it/s] 
1|15926|Loss: 0.844348132610321:  62%|██████▏   | 15926/25880 [3:15:48<1:51:52,  1.48it/s]
1|15927|Loss: 0.794524073600769:  62%|██████▏   | 15926/25880 [3:15:49<1:51:52,  1.48it/s]
1|15927|Loss: 0.794524073600769:  62%|██████▏   | 15927/25880 [3:15:49<1:57:07,  1.42it/s]
1|15928|Loss: 0.7167706489562988:  62%|██████▏   | 15927/25880 [3:15:49<1:57:07,  1.42it/s]
1|15928|Loss: 0.7167706489562988:  62%|██████▏   | 15928/25880 [3:15:50<1:55:05,  1.44it/s]
1|15929|Loss: 0.8066756725311279:  62%|██████▏   | 15928/25880 [3:15:50<1:55:05,  1.44it/s]
1|15929|Loss: 0.8066756725311279:  62%|██████▏   | 15929/25880 [3:15:50<1:54:32,  1.45it/s]
1|15930|Loss: 0.8214045763015747:  62%|██████▏   | 15929/25880 [3:15:51<1:54:32,  1.45it/s]
1|15930|Loss: 0.8214045763015747:  62%|██████▏   | 15930/25880 [3:15:51<1:56:27,  1.42it/s]
1|15931|Loss: 0.8582260012626648:  62%|██████▏   | 15930/25880 [3:15:51<1:56:27,  1.42it/s]
1|15931|Loss: 0.8582260012626648:  62%|██████▏   | 15931/25880 [3:15:52<1:54:48,  1.44it/s]
1|15932|Loss: 0.855545699596405:  62%|██████▏   | 15931/25880 [3:15:52<1:54:48,  1.44it/s] 
1|15932|Loss: 0.855545699596405:  62%|██████▏   | 15932/25880 [3:15:52<1:51:21,  1.49it/s]
1|15933|Loss: 0.8613865375518799:  62%|██████▏   | 15932/25880 [3:15:53<1:51:21,  1.49it/s]
1|15933|Loss: 0.8613865375518799:  62%|██████▏   | 15933/25880 [3:15:53<1:51:56,  1.48it/s]
1|15934|Loss: 0.8694955110549927:  62%|██████▏   | 15933/25880 [3:15:53<1:51:56,  1.48it/s]
1|15934|Loss: 0.8694955110549927:  62%|██████▏   | 15934/25880 [3:15:54<1:50:41,  1.50it/s]
1|15935|Loss: 0.8762054443359375:  62%|██████▏   | 15934/25880 [3:15:54<1:50:41,  1.50it/s]
1|15935|Loss: 0.8762054443359375:  62%|██████▏   | 15935/25880 [3:15:54<1:57:51,  1.41it/s]
1|15936|Loss: 0.8294162154197693:  62%|██████▏   | 15935/25880 [3:15:55<1:57:51,  1.41it/s]
1|15936|Loss: 0.8294162154197693:  62%|██████▏   | 15936/25880 [3:15:55<1:51:18,  1.49it/s]
1|15937|Loss: 0.8844024538993835:  62%|██████▏   | 15936/25880 [3:15:55<1:51:18,  1.49it/s]
1|15937|Loss: 0.8844024538993835:  62%|██████▏   | 15937/25880 [3:15:56<1:46:05,  1.56it/s]
1|15938|Loss: 0.8338906168937683:  62%|██████▏   | 15937/25880 [3:15:56<1:46:05,  1.56it/s]
1|15938|Loss: 0.8338906168937683:  62%|██████▏   | 15938/25880 [3:15:56<1:43:13,  1.61it/s]
1|15939|Loss: 0.8015126585960388:  62%|██████▏   | 15938/25880 [3:15:56<1:43:13,  1.61it/s]
1|15939|Loss: 0.8015126585960388:  62%|██████▏   | 15939/25880 [3:15:57<1:43:28,  1.60it/s]
1|15940|Loss: 0.7562574744224548:  62%|██████▏   | 15939/25880 [3:15:57<1:43:28,  1.60it/s]
1|15940|Loss: 0.7562574744224548:  62%|██████▏   | 15940/25880 [3:15:57<1:48:04,  1.53it/s]
1|15941|Loss: 0.7641526460647583:  62%|██████▏   | 15940/25880 [3:15:58<1:48:04,  1.53it/s]
1|15941|Loss: 0.7641526460647583:  62%|██████▏   | 15941/25880 [3:15:58<1:46:29,  1.56it/s]
1|15942|Loss: 0.7425531148910522:  62%|██████▏   | 15941/25880 [3:15:58<1:46:29,  1.56it/s]
1|15942|Loss: 0.7425531148910522:  62%|██████▏   | 15942/25880 [3:15:59<1:48:37,  1.52it/s]
1|15943|Loss: 0.9099828004837036:  62%|██████▏   | 15942/25880 [3:15:59<1:48:37,  1.52it/s]
1|15943|Loss: 0.9099828004837036:  62%|██████▏   | 15943/25880 [3:16:00<1:52:08,  1.48it/s]
1|15944|Loss: 0.833103597164154:  62%|██████▏   | 15943/25880 [3:16:00<1:52:08,  1.48it/s] 
1|15944|Loss: 0.833103597164154:  62%|██████▏   | 15944/25880 [3:16:00<1:54:51,  1.44it/s]
1|15945|Loss: 0.8896384835243225:  62%|██████▏   | 15944/25880 [3:16:01<1:54:51,  1.44it/s]
1|15945|Loss: 0.8896384835243225:  62%|██████▏   | 15945/25880 [3:16:01<1:52:13,  1.48it/s]
1|15946|Loss: 0.9884517788887024:  62%|██████▏   | 15945/25880 [3:16:01<1:52:13,  1.48it/s]
1|15946|Loss: 0.9884517788887024:  62%|██████▏   | 15946/25880 [3:16:02<1:54:16,  1.45it/s]
1|15947|Loss: 0.8519790768623352:  62%|██████▏   | 15946/25880 [3:16:02<1:54:16,  1.45it/s]
1|15947|Loss: 0.8519790768623352:  62%|██████▏   | 15947/25880 [3:16:02<1:57:20,  1.41it/s]
1|15948|Loss: 0.7747586965560913:  62%|██████▏   | 15947/25880 [3:16:03<1:57:20,  1.41it/s]
1|15948|Loss: 0.7747586965560913:  62%|██████▏   | 15948/25880 [3:16:03<2:07:56,  1.29it/s]
1|15949|Loss: 0.7417104840278625:  62%|██████▏   | 15948/25880 [3:16:04<2:07:56,  1.29it/s]
1|15949|Loss: 0.7417104840278625:  62%|██████▏   | 15949/25880 [3:16:04<2:13:46,  1.24it/s]
1|15950|Loss: 0.8966531753540039:  62%|██████▏   | 15949/25880 [3:16:05<2:13:46,  1.24it/s]
1|15950|Loss: 0.8966531753540039:  62%|██████▏   | 15950/25880 [3:16:05<2:15:16,  1.22it/s]
1|15951|Loss: 0.7223131060600281:  62%|██████▏   | 15950/25880 [3:16:05<2:15:16,  1.22it/s]
1|15951|Loss: 0.7223131060600281:  62%|██████▏   | 15951/25880 [3:16:06<2:12:23,  1.25it/s]
1|15952|Loss: 0.936188817024231:  62%|██████▏   | 15951/25880 [3:16:06<2:12:23,  1.25it/s] 
1|15952|Loss: 0.936188817024231:  62%|██████▏   | 15952/25880 [3:16:06<2:04:38,  1.33it/s]
1|15953|Loss: 0.8014894723892212:  62%|██████▏   | 15952/25880 [3:16:07<2:04:38,  1.33it/s]
1|15953|Loss: 0.8014894723892212:  62%|██████▏   | 15953/25880 [3:16:07<2:08:25,  1.29it/s]
1|15954|Loss: 0.9578017592430115:  62%|██████▏   | 15953/25880 [3:16:08<2:08:25,  1.29it/s]
1|15954|Loss: 0.9578017592430115:  62%|██████▏   | 15954/25880 [3:16:08<2:07:41,  1.30it/s]
1|15955|Loss: 0.769235372543335:  62%|██████▏   | 15954/25880 [3:16:08<2:07:41,  1.30it/s] 
1|15955|Loss: 0.769235372543335:  62%|██████▏   | 15955/25880 [3:16:09<2:04:08,  1.33it/s]
1|15956|Loss: 0.7751893997192383:  62%|██████▏   | 15955/25880 [3:16:09<2:04:08,  1.33it/s]
1|15956|Loss: 0.7751893997192383:  62%|██████▏   | 15956/25880 [3:16:09<1:54:33,  1.44it/s]
1|15957|Loss: 0.8291476368904114:  62%|██████▏   | 15956/25880 [3:16:10<1:54:33,  1.44it/s]
1|15957|Loss: 0.8291476368904114:  62%|██████▏   | 15957/25880 [3:16:10<1:50:52,  1.49it/s]
1|15958|Loss: 0.7876437902450562:  62%|██████▏   | 15957/25880 [3:16:10<1:50:52,  1.49it/s]
1|15958|Loss: 0.7876437902450562:  62%|██████▏   | 15958/25880 [3:16:11<1:49:41,  1.51it/s]
1|15959|Loss: 0.8140316009521484:  62%|██████▏   | 15958/25880 [3:16:11<1:49:41,  1.51it/s]
1|15959|Loss: 0.8140316009521484:  62%|██████▏   | 15959/25880 [3:16:11<1:54:34,  1.44it/s]
1|15960|Loss: 0.7975329756736755:  62%|██████▏   | 15959/25880 [3:16:12<1:54:34,  1.44it/s]
1|15960|Loss: 0.7975329756736755:  62%|██████▏   | 15960/25880 [3:16:12<1:53:44,  1.45it/s]
1|15961|Loss: 0.8902457356452942:  62%|██████▏   | 15960/25880 [3:16:12<1:53:44,  1.45it/s]
1|15961|Loss: 0.8902457356452942:  62%|██████▏   | 15961/25880 [3:16:13<1:54:11,  1.45it/s]
1|15962|Loss: 0.7689006328582764:  62%|██████▏   | 15961/25880 [3:16:13<1:54:11,  1.45it/s]
1|15962|Loss: 0.7689006328582764:  62%|██████▏   | 15962/25880 [3:16:13<1:42:15,  1.62it/s]
1|15963|Loss: 0.7800435423851013:  62%|██████▏   | 15962/25880 [3:16:13<1:42:15,  1.62it/s]
1|15963|Loss: 0.7800435423851013:  62%|██████▏   | 15963/25880 [3:16:14<1:44:41,  1.58it/s]
1|15964|Loss: 0.9320945739746094:  62%|██████▏   | 15963/25880 [3:16:14<1:44:41,  1.58it/s]
1|15964|Loss: 0.9320945739746094:  62%|██████▏   | 15964/25880 [3:16:14<1:42:14,  1.62it/s]
1|15965|Loss: 0.7263678908348083:  62%|██████▏   | 15964/25880 [3:16:15<1:42:14,  1.62it/s]
1|15965|Loss: 0.7263678908348083:  62%|██████▏   | 15965/25880 [3:16:15<1:48:46,  1.52it/s]
1|15966|Loss: 0.8753357529640198:  62%|██████▏   | 15965/25880 [3:16:16<1:48:46,  1.52it/s]
1|15966|Loss: 0.8753357529640198:  62%|██████▏   | 15966/25880 [3:16:16<1:53:21,  1.46it/s]
1|15967|Loss: 0.8539525270462036:  62%|██████▏   | 15966/25880 [3:16:16<1:53:21,  1.46it/s]
1|15967|Loss: 0.8539525270462036:  62%|██████▏   | 15967/25880 [3:16:17<1:51:03,  1.49it/s]
1|15968|Loss: 0.7366327047348022:  62%|██████▏   | 15967/25880 [3:16:17<1:51:03,  1.49it/s]
1|15968|Loss: 0.7366327047348022:  62%|██████▏   | 15968/25880 [3:16:17<1:53:28,  1.46it/s]
1|15969|Loss: 0.9066603779792786:  62%|██████▏   | 15968/25880 [3:16:18<1:53:28,  1.46it/s]
1|15969|Loss: 0.9066603779792786:  62%|██████▏   | 15969/25880 [3:16:18<1:58:52,  1.39it/s]
1|15970|Loss: 0.9416093230247498:  62%|██████▏   | 15969/25880 [3:16:18<1:58:52,  1.39it/s]
1|15970|Loss: 0.9416093230247498:  62%|██████▏   | 15970/25880 [3:16:19<1:55:33,  1.43it/s]
1|15971|Loss: 0.9393961429595947:  62%|██████▏   | 15970/25880 [3:16:19<1:55:33,  1.43it/s]
1|15971|Loss: 0.9393961429595947:  62%|██████▏   | 15971/25880 [3:16:19<1:49:00,  1.51it/s]
1|15972|Loss: 0.8727375268936157:  62%|██████▏   | 15971/25880 [3:16:20<1:49:00,  1.51it/s]
1|15972|Loss: 0.8727375268936157:  62%|██████▏   | 15972/25880 [3:16:20<1:50:44,  1.49it/s]
1|15973|Loss: 1.0001459121704102:  62%|██████▏   | 15972/25880 [3:16:20<1:50:44,  1.49it/s]
1|15973|Loss: 1.0001459121704102:  62%|██████▏   | 15973/25880 [3:16:21<1:50:01,  1.50it/s]
1|15974|Loss: 0.7410305738449097:  62%|██████▏   | 15973/25880 [3:16:21<1:50:01,  1.50it/s]
1|15974|Loss: 0.7410305738449097:  62%|██████▏   | 15974/25880 [3:16:21<1:52:31,  1.47it/s]
1|15975|Loss: 0.9847015142440796:  62%|██████▏   | 15974/25880 [3:16:22<1:52:31,  1.47it/s]
1|15975|Loss: 0.9847015142440796:  62%|██████▏   | 15975/25880 [3:16:22<1:57:24,  1.41it/s]
1|15976|Loss: 0.9006513953208923:  62%|██████▏   | 15975/25880 [3:16:22<1:57:24,  1.41it/s]
1|15976|Loss: 0.9006513953208923:  62%|██████▏   | 15976/25880 [3:16:23<1:55:32,  1.43it/s]
1|15977|Loss: 0.8049624562263489:  62%|██████▏   | 15976/25880 [3:16:23<1:55:32,  1.43it/s]
1|15977|Loss: 0.8049624562263489:  62%|██████▏   | 15977/25880 [3:16:24<2:00:59,  1.36it/s]
1|15978|Loss: 0.9485929012298584:  62%|██████▏   | 15977/25880 [3:16:24<2:00:59,  1.36it/s]
1|15978|Loss: 0.9485929012298584:  62%|██████▏   | 15978/25880 [3:16:24<2:02:08,  1.35it/s]
1|15979|Loss: 0.8359956741333008:  62%|██████▏   | 15978/25880 [3:16:25<2:02:08,  1.35it/s]
1|15979|Loss: 0.8359956741333008:  62%|██████▏   | 15979/25880 [3:16:25<1:55:59,  1.42it/s]
1|15980|Loss: 0.7946956157684326:  62%|██████▏   | 15979/25880 [3:16:25<1:55:59,  1.42it/s]
1|15980|Loss: 0.7946956157684326:  62%|██████▏   | 15980/25880 [3:16:26<1:54:37,  1.44it/s]
1|15981|Loss: 0.749681293964386:  62%|██████▏   | 15980/25880 [3:16:26<1:54:37,  1.44it/s] 
1|15981|Loss: 0.749681293964386:  62%|██████▏   | 15981/25880 [3:16:26<2:03:44,  1.33it/s]
1|15982|Loss: 0.8515642285346985:  62%|██████▏   | 15981/25880 [3:16:27<2:03:44,  1.33it/s]
1|15982|Loss: 0.8515642285346985:  62%|██████▏   | 15982/25880 [3:16:27<2:05:09,  1.32it/s]
1|15983|Loss: 0.7666042447090149:  62%|██████▏   | 15982/25880 [3:16:28<2:05:09,  1.32it/s]
1|15983|Loss: 0.7666042447090149:  62%|██████▏   | 15983/25880 [3:16:28<1:58:01,  1.40it/s]
1|15984|Loss: 0.7542008757591248:  62%|██████▏   | 15983/25880 [3:16:28<1:58:01,  1.40it/s]
1|15984|Loss: 0.7542008757591248:  62%|██████▏   | 15984/25880 [3:16:29<1:53:33,  1.45it/s]
1|15985|Loss: 0.7953348755836487:  62%|██████▏   | 15984/25880 [3:16:29<1:53:33,  1.45it/s]
1|15985|Loss: 0.7953348755836487:  62%|██████▏   | 15985/25880 [3:16:29<1:51:12,  1.48it/s]
1|15986|Loss: 0.8820456862449646:  62%|██████▏   | 15985/25880 [3:16:30<1:51:12,  1.48it/s]
1|15986|Loss: 0.8820456862449646:  62%|██████▏   | 15986/25880 [3:16:30<1:56:13,  1.42it/s]
1|15987|Loss: 0.7658241391181946:  62%|██████▏   | 15986/25880 [3:16:30<1:56:13,  1.42it/s]
1|15987|Loss: 0.7658241391181946:  62%|██████▏   | 15987/25880 [3:16:31<2:02:14,  1.35it/s]
1|15988|Loss: 0.9261728525161743:  62%|██████▏   | 15987/25880 [3:16:31<2:02:14,  1.35it/s]
1|15988|Loss: 0.9261728525161743:  62%|██████▏   | 15988/25880 [3:16:31<2:01:47,  1.35it/s]
1|15989|Loss: 0.9190206527709961:  62%|██████▏   | 15988/25880 [3:16:32<2:01:47,  1.35it/s]
1|15989|Loss: 0.9190206527709961:  62%|██████▏   | 15989/25880 [3:16:32<2:03:39,  1.33it/s]
1|15990|Loss: 0.9845790266990662:  62%|██████▏   | 15989/25880 [3:16:33<2:03:39,  1.33it/s]
1|15990|Loss: 0.9845790266990662:  62%|██████▏   | 15990/25880 [3:16:33<1:54:45,  1.44it/s]
1|15991|Loss: 0.8500750660896301:  62%|██████▏   | 15990/25880 [3:16:33<1:54:45,  1.44it/s]
1|15991|Loss: 0.8500750660896301:  62%|██████▏   | 15991/25880 [3:16:34<1:54:42,  1.44it/s]
1|15992|Loss: 0.8857519030570984:  62%|██████▏   | 15991/25880 [3:16:34<1:54:42,  1.44it/s]
1|15992|Loss: 0.8857519030570984:  62%|██████▏   | 15992/25880 [3:16:34<2:04:14,  1.33it/s]
1|15993|Loss: 0.8704610466957092:  62%|██████▏   | 15992/25880 [3:16:35<2:04:14,  1.33it/s]
1|15993|Loss: 0.8704610466957092:  62%|██████▏   | 15993/25880 [3:16:35<2:09:58,  1.27it/s]
1|15994|Loss: 0.7588250637054443:  62%|██████▏   | 15993/25880 [3:16:36<2:09:58,  1.27it/s]
1|15994|Loss: 0.7588250637054443:  62%|██████▏   | 15994/25880 [3:16:36<2:08:47,  1.28it/s]
1|15995|Loss: 0.8049619793891907:  62%|██████▏   | 15994/25880 [3:16:36<2:08:47,  1.28it/s]
1|15995|Loss: 0.8049619793891907:  62%|██████▏   | 15995/25880 [3:16:37<2:06:02,  1.31it/s]
1|15996|Loss: 0.7990058660507202:  62%|██████▏   | 15995/25880 [3:16:37<2:06:02,  1.31it/s]
1|15996|Loss: 0.7990058660507202:  62%|██████▏   | 15996/25880 [3:16:37<2:00:41,  1.36it/s]
1|15997|Loss: 0.8567173480987549:  62%|██████▏   | 15996/25880 [3:16:38<2:00:41,  1.36it/s]
1|15997|Loss: 0.8567173480987549:  62%|██████▏   | 15997/25880 [3:16:38<2:05:34,  1.31it/s]
1|15998|Loss: 0.9132493734359741:  62%|██████▏   | 15997/25880 [3:16:39<2:05:34,  1.31it/s]
1|15998|Loss: 0.9132493734359741:  62%|██████▏   | 15998/25880 [3:16:39<2:00:17,  1.37it/s]
1|15999|Loss: 0.774836003780365:  62%|██████▏   | 15998/25880 [3:16:39<2:00:17,  1.37it/s] 
1|15999|Loss: 0.774836003780365:  62%|██████▏   | 15999/25880 [3:16:40<2:02:37,  1.34it/s]
1|16000|Loss: 0.8140594363212585:  62%|██████▏   | 15999/25880 [3:16:40<2:02:37,  1.34it/s]
1|16000|Loss: 0.8140594363212585:  62%|██████▏   | 16000/25880 [3:16:41<2:10:08,  1.27it/s]
1|16001|Loss: 0.7201571464538574:  62%|██████▏   | 16000/25880 [3:16:41<2:10:08,  1.27it/s]
1|16001|Loss: 0.7201571464538574:  62%|██████▏   | 16001/25880 [3:16:41<2:15:09,  1.22it/s]
1|16002|Loss: 0.856086015701294:  62%|██████▏   | 16001/25880 [3:16:42<2:15:09,  1.22it/s] 
1|16002|Loss: 0.856086015701294:  62%|██████▏   | 16002/25880 [3:16:42<2:16:38,  1.20it/s]
1|16003|Loss: 0.9379974603652954:  62%|██████▏   | 16002/25880 [3:16:43<2:16:38,  1.20it/s]
1|16003|Loss: 0.9379974603652954:  62%|██████▏   | 16003/25880 [3:16:43<2:08:09,  1.28it/s]
1|16004|Loss: 0.8507481217384338:  62%|██████▏   | 16003/25880 [3:16:43<2:08:09,  1.28it/s]
1|16004|Loss: 0.8507481217384338:  62%|██████▏   | 16004/25880 [3:16:44<2:08:28,  1.28it/s]
1|16005|Loss: 0.839003324508667:  62%|██████▏   | 16004/25880 [3:16:44<2:08:28,  1.28it/s] 
1|16005|Loss: 0.839003324508667:  62%|██████▏   | 16005/25880 [3:16:44<2:03:14,  1.34it/s]
1|16006|Loss: 1.0498586893081665:  62%|██████▏   | 16005/25880 [3:16:45<2:03:14,  1.34it/s]
1|16006|Loss: 1.0498586893081665:  62%|██████▏   | 16006/25880 [3:16:45<1:55:32,  1.42it/s]
1|16007|Loss: 0.7167706489562988:  62%|██████▏   | 16006/25880 [3:16:45<1:55:32,  1.42it/s]
1|16007|Loss: 0.7167706489562988:  62%|██████▏   | 16007/25880 [3:16:46<1:50:44,  1.49it/s]
1|16008|Loss: 0.8240348100662231:  62%|██████▏   | 16007/25880 [3:16:46<1:50:44,  1.49it/s]
1|16008|Loss: 0.8240348100662231:  62%|██████▏   | 16008/25880 [3:16:46<1:48:41,  1.51it/s]
1|16009|Loss: 0.7478967905044556:  62%|██████▏   | 16008/25880 [3:16:47<1:48:41,  1.51it/s]
1|16009|Loss: 0.7478967905044556:  62%|██████▏   | 16009/25880 [3:16:47<1:45:23,  1.56it/s]
1|16010|Loss: 0.7409130930900574:  62%|██████▏   | 16009/25880 [3:16:47<1:45:23,  1.56it/s]
1|16010|Loss: 0.7409130930900574:  62%|██████▏   | 16010/25880 [3:16:47<1:37:34,  1.69it/s]
1|16011|Loss: 0.7541847825050354:  62%|██████▏   | 16010/25880 [3:16:48<1:37:34,  1.69it/s]
1|16011|Loss: 0.7541847825050354:  62%|██████▏   | 16011/25880 [3:16:48<1:50:38,  1.49it/s]
1|16012|Loss: 0.9576051831245422:  62%|██████▏   | 16011/25880 [3:16:49<1:50:38,  1.49it/s]
1|16012|Loss: 0.9576051831245422:  62%|██████▏   | 16012/25880 [3:16:49<2:00:00,  1.37it/s]
1|16013|Loss: 0.8988155722618103:  62%|██████▏   | 16012/25880 [3:16:49<2:00:00,  1.37it/s]
1|16013|Loss: 0.8988155722618103:  62%|██████▏   | 16013/25880 [3:16:50<1:56:40,  1.41it/s]
1|16014|Loss: 0.8225249648094177:  62%|██████▏   | 16013/25880 [3:16:50<1:56:40,  1.41it/s]
1|16014|Loss: 0.8225249648094177:  62%|██████▏   | 16014/25880 [3:16:50<1:53:18,  1.45it/s]
1|16015|Loss: 0.828035295009613:  62%|██████▏   | 16014/25880 [3:16:51<1:53:18,  1.45it/s] 
1|16015|Loss: 0.828035295009613:  62%|██████▏   | 16015/25880 [3:16:51<1:50:00,  1.49it/s]
1|16016|Loss: 0.7627257108688354:  62%|██████▏   | 16015/25880 [3:16:51<1:50:00,  1.49it/s]
1|16016|Loss: 0.7627257108688354:  62%|██████▏   | 16016/25880 [3:16:52<1:50:46,  1.48it/s]
1|16017|Loss: 0.9750251770019531:  62%|██████▏   | 16016/25880 [3:16:52<1:50:46,  1.48it/s]
1|16017|Loss: 0.9750251770019531:  62%|██████▏   | 16017/25880 [3:16:53<1:58:53,  1.38it/s]
1|16018|Loss: 1.0648505687713623:  62%|██████▏   | 16017/25880 [3:16:53<1:58:53,  1.38it/s]
1|16018|Loss: 1.0648505687713623:  62%|██████▏   | 16018/25880 [3:16:53<2:04:58,  1.32it/s]
1|16019|Loss: 0.8053268194198608:  62%|██████▏   | 16018/25880 [3:16:54<2:04:58,  1.32it/s]
1|16019|Loss: 0.8053268194198608:  62%|██████▏   | 16019/25880 [3:16:54<1:58:23,  1.39it/s]
1|16020|Loss: 0.7749001979827881:  62%|██████▏   | 16019/25880 [3:16:54<1:58:23,  1.39it/s]
1|16020|Loss: 0.7749001979827881:  62%|██████▏   | 16020/25880 [3:16:55<1:57:11,  1.40it/s]
1|16021|Loss: 0.8482744693756104:  62%|██████▏   | 16020/25880 [3:16:55<1:57:11,  1.40it/s]
1|16021|Loss: 0.8482744693756104:  62%|██████▏   | 16021/25880 [3:16:55<1:57:53,  1.39it/s]
1|16022|Loss: 0.8324224948883057:  62%|██████▏   | 16021/25880 [3:16:56<1:57:53,  1.39it/s]
1|16022|Loss: 0.8324224948883057:  62%|██████▏   | 16022/25880 [3:16:56<1:49:36,  1.50it/s]
1|16023|Loss: 0.8000634908676147:  62%|██████▏   | 16022/25880 [3:16:56<1:49:36,  1.50it/s]
1|16023|Loss: 0.8000634908676147:  62%|██████▏   | 16023/25880 [3:16:57<1:46:47,  1.54it/s]
1|16024|Loss: 0.768562376499176:  62%|██████▏   | 16023/25880 [3:16:57<1:46:47,  1.54it/s] 
1|16024|Loss: 0.768562376499176:  62%|██████▏   | 16024/25880 [3:16:57<1:50:06,  1.49it/s]
1|16025|Loss: 0.74131178855896:  62%|██████▏   | 16024/25880 [3:16:58<1:50:06,  1.49it/s] 
1|16025|Loss: 0.74131178855896:  62%|██████▏   | 16025/25880 [3:16:58<2:04:11,  1.32it/s]
1|16026|Loss: 0.9269137382507324:  62%|██████▏   | 16025/25880 [3:16:59<2:04:11,  1.32it/s]
1|16026|Loss: 0.9269137382507324:  62%|██████▏   | 16026/25880 [3:16:59<2:10:32,  1.26it/s]
1|16027|Loss: 0.7615352272987366:  62%|██████▏   | 16026/25880 [3:17:00<2:10:32,  1.26it/s]
1|16027|Loss: 0.7615352272987366:  62%|██████▏   | 16027/25880 [3:17:00<2:18:08,  1.19it/s]
1|16028|Loss: 0.7569172978401184:  62%|██████▏   | 16027/25880 [3:17:01<2:18:08,  1.19it/s]
1|16028|Loss: 0.7569172978401184:  62%|██████▏   | 16028/25880 [3:17:01<2:17:42,  1.19it/s]
1|16029|Loss: 0.8333151340484619:  62%|██████▏   | 16028/25880 [3:17:01<2:17:42,  1.19it/s]
1|16029|Loss: 0.8333151340484619:  62%|██████▏   | 16029/25880 [3:17:02<2:11:54,  1.24it/s]
1|16030|Loss: 0.8657878637313843:  62%|██████▏   | 16029/25880 [3:17:02<2:11:54,  1.24it/s]
1|16030|Loss: 0.8657878637313843:  62%|██████▏   | 16030/25880 [3:17:02<2:12:37,  1.24it/s]
1|16031|Loss: 0.8269091248512268:  62%|██████▏   | 16030/25880 [3:17:03<2:12:37,  1.24it/s]
1|16031|Loss: 0.8269091248512268:  62%|██████▏   | 16031/25880 [3:17:03<2:15:51,  1.21it/s]
1|16032|Loss: 0.941026508808136:  62%|██████▏   | 16031/25880 [3:17:04<2:15:51,  1.21it/s] 
1|16032|Loss: 0.941026508808136:  62%|██████▏   | 16032/25880 [3:17:04<2:17:02,  1.20it/s]
1|16033|Loss: 0.8482135534286499:  62%|██████▏   | 16032/25880 [3:17:05<2:17:02,  1.20it/s]
1|16033|Loss: 0.8482135534286499:  62%|██████▏   | 16033/25880 [3:17:05<2:11:38,  1.25it/s]
1|16034|Loss: 0.9599334001541138:  62%|██████▏   | 16033/25880 [3:17:05<2:11:38,  1.25it/s]
1|16034|Loss: 0.9599334001541138:  62%|██████▏   | 16034/25880 [3:17:06<2:13:24,  1.23it/s]
1|16035|Loss: 0.7336419224739075:  62%|██████▏   | 16034/25880 [3:17:06<2:13:24,  1.23it/s]
1|16035|Loss: 0.7336419224739075:  62%|██████▏   | 16035/25880 [3:17:06<2:05:12,  1.31it/s]
1|16036|Loss: 0.7986161112785339:  62%|██████▏   | 16035/25880 [3:17:07<2:05:12,  1.31it/s]
1|16036|Loss: 0.7986161112785339:  62%|██████▏   | 16036/25880 [3:17:07<2:04:16,  1.32it/s]
1|16037|Loss: 0.6751996874809265:  62%|██████▏   | 16036/25880 [3:17:08<2:04:16,  1.32it/s]
1|16037|Loss: 0.6751996874809265:  62%|██████▏   | 16037/25880 [3:17:08<1:59:58,  1.37it/s]
1|16038|Loss: 0.8754001259803772:  62%|██████▏   | 16037/25880 [3:17:08<1:59:58,  1.37it/s]
1|16038|Loss: 0.8754001259803772:  62%|██████▏   | 16038/25880 [3:17:09<2:00:03,  1.37it/s]
1|16039|Loss: 0.9487960934638977:  62%|██████▏   | 16038/25880 [3:17:09<2:00:03,  1.37it/s]
1|16039|Loss: 0.9487960934638977:  62%|██████▏   | 16039/25880 [3:17:09<2:06:13,  1.30it/s]
1|16040|Loss: 0.7602631449699402:  62%|██████▏   | 16039/25880 [3:17:10<2:06:13,  1.30it/s]
1|16040|Loss: 0.7602631449699402:  62%|██████▏   | 16040/25880 [3:17:10<2:02:19,  1.34it/s]
1|16041|Loss: 0.9434253573417664:  62%|██████▏   | 16040/25880 [3:17:10<2:02:19,  1.34it/s]
1|16041|Loss: 0.9434253573417664:  62%|██████▏   | 16041/25880 [3:17:11<1:51:53,  1.47it/s]
1|16042|Loss: 0.8145692944526672:  62%|██████▏   | 16041/25880 [3:17:11<1:51:53,  1.47it/s]
1|16042|Loss: 0.8145692944526672:  62%|██████▏   | 16042/25880 [3:17:11<1:43:31,  1.58it/s]
1|16043|Loss: 0.6986697912216187:  62%|██████▏   | 16042/25880 [3:17:12<1:43:31,  1.58it/s]
1|16043|Loss: 0.6986697912216187:  62%|██████▏   | 16043/25880 [3:17:12<1:46:52,  1.53it/s]
1|16044|Loss: 0.8643956780433655:  62%|██████▏   | 16043/25880 [3:17:12<1:46:52,  1.53it/s]
1|16044|Loss: 0.8643956780433655:  62%|██████▏   | 16044/25880 [3:17:12<1:44:20,  1.57it/s]
1|16045|Loss: 0.9094306230545044:  62%|██████▏   | 16044/25880 [3:17:13<1:44:20,  1.57it/s]
1|16045|Loss: 0.9094306230545044:  62%|██████▏   | 16045/25880 [3:17:13<1:51:01,  1.48it/s]
1|16046|Loss: 0.9018372893333435:  62%|██████▏   | 16045/25880 [3:17:14<1:51:01,  1.48it/s]
1|16046|Loss: 0.9018372893333435:  62%|██████▏   | 16046/25880 [3:17:14<1:46:10,  1.54it/s]
1|16047|Loss: 0.8231784701347351:  62%|██████▏   | 16046/25880 [3:17:14<1:46:10,  1.54it/s]
1|16047|Loss: 0.8231784701347351:  62%|██████▏   | 16047/25880 [3:17:14<1:47:55,  1.52it/s]
1|16048|Loss: 0.7628545165061951:  62%|██████▏   | 16047/25880 [3:17:15<1:47:55,  1.52it/s]
1|16048|Loss: 0.7628545165061951:  62%|██████▏   | 16048/25880 [3:17:15<1:51:27,  1.47it/s]
1|16049|Loss: 0.8613128066062927:  62%|██████▏   | 16048/25880 [3:17:16<1:51:27,  1.47it/s]
1|16049|Loss: 0.8613128066062927:  62%|██████▏   | 16049/25880 [3:17:16<1:53:44,  1.44it/s]
1|16050|Loss: 0.9119044542312622:  62%|██████▏   | 16049/25880 [3:17:16<1:53:44,  1.44it/s]
1|16050|Loss: 0.9119044542312622:  62%|██████▏   | 16050/25880 [3:17:17<1:55:27,  1.42it/s]
1|16051|Loss: 0.8292571902275085:  62%|██████▏   | 16050/25880 [3:17:17<1:55:27,  1.42it/s]
1|16051|Loss: 0.8292571902275085:  62%|██████▏   | 16051/25880 [3:17:17<1:57:02,  1.40it/s]
1|16052|Loss: 0.9282591342926025:  62%|██████▏   | 16051/25880 [3:17:18<1:57:02,  1.40it/s]
1|16052|Loss: 0.9282591342926025:  62%|██████▏   | 16052/25880 [3:17:18<1:50:04,  1.49it/s]
1|16053|Loss: 0.8529806137084961:  62%|██████▏   | 16052/25880 [3:17:18<1:50:04,  1.49it/s]
1|16053|Loss: 0.8529806137084961:  62%|██████▏   | 16053/25880 [3:17:18<1:36:51,  1.69it/s]
1|16054|Loss: 0.8275359869003296:  62%|██████▏   | 16053/25880 [3:17:19<1:36:51,  1.69it/s]
1|16054|Loss: 0.8275359869003296:  62%|██████▏   | 16054/25880 [3:17:19<1:34:26,  1.73it/s]
1|16055|Loss: 0.8835991024971008:  62%|██████▏   | 16054/25880 [3:17:19<1:34:26,  1.73it/s]
1|16055|Loss: 0.8835991024971008:  62%|██████▏   | 16055/25880 [3:17:20<1:45:51,  1.55it/s]
1|16056|Loss: 0.9233989119529724:  62%|██████▏   | 16055/25880 [3:17:20<1:45:51,  1.55it/s]
1|16056|Loss: 0.9233989119529724:  62%|██████▏   | 16056/25880 [3:17:21<1:51:41,  1.47it/s]
1|16057|Loss: 0.9628722667694092:  62%|██████▏   | 16056/25880 [3:17:21<1:51:41,  1.47it/s]
1|16057|Loss: 0.9628722667694092:  62%|██████▏   | 16057/25880 [3:17:21<1:56:41,  1.40it/s]
1|16058|Loss: 0.8299724459648132:  62%|██████▏   | 16057/25880 [3:17:22<1:56:41,  1.40it/s]
1|16058|Loss: 0.8299724459648132:  62%|██████▏   | 16058/25880 [3:17:22<2:02:28,  1.34it/s]
1|16059|Loss: 0.7991988062858582:  62%|██████▏   | 16058/25880 [3:17:23<2:02:28,  1.34it/s]
1|16059|Loss: 0.7991988062858582:  62%|██████▏   | 16059/25880 [3:17:23<1:58:52,  1.38it/s]
1|16060|Loss: 0.7621236443519592:  62%|██████▏   | 16059/25880 [3:17:23<1:58:52,  1.38it/s]
1|16060|Loss: 0.7621236443519592:  62%|██████▏   | 16060/25880 [3:17:24<2:30:34,  1.09it/s]
1|16061|Loss: 0.8056365251541138:  62%|██████▏   | 16060/25880 [3:17:25<2:30:34,  1.09it/s]
1|16061|Loss: 0.8056365251541138:  62%|██████▏   | 16061/25880 [3:17:25<2:26:05,  1.12it/s]
1|16062|Loss: 0.664780855178833:  62%|██████▏   | 16061/25880 [3:17:25<2:26:05,  1.12it/s] 
1|16062|Loss: 0.664780855178833:  62%|██████▏   | 16062/25880 [3:17:26<2:26:21,  1.12it/s]
1|16063|Loss: 0.9952535033226013:  62%|██████▏   | 16062/25880 [3:17:26<2:26:21,  1.12it/s]
1|16063|Loss: 0.9952535033226013:  62%|██████▏   | 16063/25880 [3:17:27<2:15:57,  1.20it/s]
1|16064|Loss: 0.7125721573829651:  62%|██████▏   | 16063/25880 [3:17:27<2:15:57,  1.20it/s]
1|16064|Loss: 0.7125721573829651:  62%|██████▏   | 16064/25880 [3:17:27<2:10:39,  1.25it/s]
1|16065|Loss: 0.7694736123085022:  62%|██████▏   | 16064/25880 [3:17:28<2:10:39,  1.25it/s]
1|16065|Loss: 0.7694736123085022:  62%|██████▏   | 16065/25880 [3:17:28<2:08:17,  1.28it/s]
1|16066|Loss: 0.8810645341873169:  62%|██████▏   | 16065/25880 [3:17:28<2:08:17,  1.28it/s]
1|16066|Loss: 0.8810645341873169:  62%|██████▏   | 16066/25880 [3:17:29<2:06:37,  1.29it/s]
1|16067|Loss: 0.8166502118110657:  62%|██████▏   | 16066/25880 [3:17:29<2:06:37,  1.29it/s]
1|16067|Loss: 0.8166502118110657:  62%|██████▏   | 16067/25880 [3:17:30<2:03:41,  1.32it/s]
1|16068|Loss: 0.7849894762039185:  62%|██████▏   | 16067/25880 [3:17:30<2:03:41,  1.32it/s]
1|16068|Loss: 0.7849894762039185:  62%|██████▏   | 16068/25880 [3:17:30<1:57:25,  1.39it/s]
1|16069|Loss: 0.8441049456596375:  62%|██████▏   | 16068/25880 [3:17:31<1:57:25,  1.39it/s]
1|16069|Loss: 0.8441049456596375:  62%|██████▏   | 16069/25880 [3:17:31<1:57:08,  1.40it/s]
1|16070|Loss: 0.8400102257728577:  62%|██████▏   | 16069/25880 [3:17:31<1:57:08,  1.40it/s]
1|16070|Loss: 0.8400102257728577:  62%|██████▏   | 16070/25880 [3:17:32<1:54:09,  1.43it/s]
1|16071|Loss: 0.876193642616272:  62%|██████▏   | 16070/25880 [3:17:32<1:54:09,  1.43it/s] 
1|16071|Loss: 0.876193642616272:  62%|██████▏   | 16071/25880 [3:17:32<1:51:31,  1.47it/s]
1|16072|Loss: 0.900394082069397:  62%|██████▏   | 16071/25880 [3:17:33<1:51:31,  1.47it/s]
1|16072|Loss: 0.900394082069397:  62%|██████▏   | 16072/25880 [3:17:33<1:48:35,  1.51it/s]
1|16073|Loss: 0.779776394367218:  62%|██████▏   | 16072/25880 [3:17:33<1:48:35,  1.51it/s]
1|16073|Loss: 0.779776394367218:  62%|██████▏   | 16073/25880 [3:17:34<1:51:22,  1.47it/s]
1|16074|Loss: 0.7974346876144409:  62%|██████▏   | 16073/25880 [3:17:34<1:51:22,  1.47it/s]
1|16074|Loss: 0.7974346876144409:  62%|██████▏   | 16074/25880 [3:17:34<1:47:45,  1.52it/s]
1|16075|Loss: 0.8837701678276062:  62%|██████▏   | 16074/25880 [3:17:34<1:47:45,  1.52it/s]
1|16075|Loss: 0.8837701678276062:  62%|██████▏   | 16075/25880 [3:17:35<1:49:44,  1.49it/s]
1|16076|Loss: 0.8236811757087708:  62%|██████▏   | 16075/25880 [3:17:35<1:49:44,  1.49it/s]
1|16076|Loss: 0.8236811757087708:  62%|██████▏   | 16076/25880 [3:17:35<1:48:56,  1.50it/s]
1|16077|Loss: 0.876736044883728:  62%|██████▏   | 16076/25880 [3:17:36<1:48:56,  1.50it/s] 
1|16077|Loss: 0.876736044883728:  62%|██████▏   | 16077/25880 [3:17:36<1:50:25,  1.48it/s]
1|16078|Loss: 0.8965825438499451:  62%|██████▏   | 16077/25880 [3:17:37<1:50:25,  1.48it/s]
1|16078|Loss: 0.8965825438499451:  62%|██████▏   | 16078/25880 [3:17:37<1:48:24,  1.51it/s]
1|16079|Loss: 0.8660097122192383:  62%|██████▏   | 16078/25880 [3:17:37<1:48:24,  1.51it/s]
1|16079|Loss: 0.8660097122192383:  62%|██████▏   | 16079/25880 [3:17:37<1:42:34,  1.59it/s]
1|16080|Loss: 0.7695515155792236:  62%|██████▏   | 16079/25880 [3:17:38<1:42:34,  1.59it/s]
1|16080|Loss: 0.7695515155792236:  62%|██████▏   | 16080/25880 [3:17:38<1:31:25,  1.79it/s]
1|16081|Loss: 0.8536345362663269:  62%|██████▏   | 16080/25880 [3:17:38<1:31:25,  1.79it/s]
1|16081|Loss: 0.8536345362663269:  62%|██████▏   | 16081/25880 [3:17:38<1:37:31,  1.67it/s]
1|16082|Loss: 0.7408463954925537:  62%|██████▏   | 16081/25880 [3:17:39<1:37:31,  1.67it/s]
1|16082|Loss: 0.7408463954925537:  62%|██████▏   | 16082/25880 [3:17:39<1:52:03,  1.46it/s]
1|16083|Loss: 0.8453554511070251:  62%|██████▏   | 16082/25880 [3:17:40<1:52:03,  1.46it/s]
1|16083|Loss: 0.8453554511070251:  62%|██████▏   | 16083/25880 [3:17:40<1:54:46,  1.42it/s]
1|16084|Loss: 0.7515063285827637:  62%|██████▏   | 16083/25880 [3:17:40<1:54:46,  1.42it/s]
1|16084|Loss: 0.7515063285827637:  62%|██████▏   | 16084/25880 [3:17:41<1:50:22,  1.48it/s]
1|16085|Loss: 0.7781999707221985:  62%|██████▏   | 16084/25880 [3:17:41<1:50:22,  1.48it/s]
1|16085|Loss: 0.7781999707221985:  62%|██████▏   | 16085/25880 [3:17:42<1:57:14,  1.39it/s]
1|16086|Loss: 0.6635395884513855:  62%|██████▏   | 16085/25880 [3:17:42<1:57:14,  1.39it/s]
1|16086|Loss: 0.6635395884513855:  62%|██████▏   | 16086/25880 [3:17:42<1:56:15,  1.40it/s]
1|16087|Loss: 0.9040485620498657:  62%|██████▏   | 16086/25880 [3:17:43<1:56:15,  1.40it/s]
1|16087|Loss: 0.9040485620498657:  62%|██████▏   | 16087/25880 [3:17:43<1:53:06,  1.44it/s]
1|16088|Loss: 0.8268076181411743:  62%|██████▏   | 16087/25880 [3:17:43<1:53:06,  1.44it/s]
1|16088|Loss: 0.8268076181411743:  62%|██████▏   | 16088/25880 [3:17:44<1:58:04,  1.38it/s]
1|16089|Loss: 1.020713448524475:  62%|██████▏   | 16088/25880 [3:17:44<1:58:04,  1.38it/s] 
1|16089|Loss: 1.020713448524475:  62%|██████▏   | 16089/25880 [3:17:44<2:02:50,  1.33it/s]
1|16090|Loss: 0.9166449904441833:  62%|██████▏   | 16089/25880 [3:17:45<2:02:50,  1.33it/s]
1|16090|Loss: 0.9166449904441833:  62%|██████▏   | 16090/25880 [3:17:45<2:06:04,  1.29it/s]
1|16091|Loss: 0.893337607383728:  62%|██████▏   | 16090/25880 [3:17:46<2:06:04,  1.29it/s] 
1|16091|Loss: 0.893337607383728:  62%|██████▏   | 16091/25880 [3:17:46<1:56:22,  1.40it/s]
1|16092|Loss: 0.8393229246139526:  62%|██████▏   | 16091/25880 [3:17:46<1:56:22,  1.40it/s]
1|16092|Loss: 0.8393229246139526:  62%|██████▏   | 16092/25880 [3:17:46<1:51:22,  1.46it/s]
1|16093|Loss: 0.8152318596839905:  62%|██████▏   | 16092/25880 [3:17:47<1:51:22,  1.46it/s]
1|16093|Loss: 0.8152318596839905:  62%|██████▏   | 16093/25880 [3:17:47<1:49:00,  1.50it/s]
1|16094|Loss: 0.900981068611145:  62%|██████▏   | 16093/25880 [3:17:48<1:49:00,  1.50it/s] 
1|16094|Loss: 0.900981068611145:  62%|██████▏   | 16094/25880 [3:17:48<1:56:03,  1.41it/s]
1|16095|Loss: 0.8730680346488953:  62%|██████▏   | 16094/25880 [3:17:48<1:56:03,  1.41it/s]
1|16095|Loss: 0.8730680346488953:  62%|██████▏   | 16095/25880 [3:17:49<1:55:17,  1.41it/s]
1|16096|Loss: 0.8970704078674316:  62%|██████▏   | 16095/25880 [3:17:49<1:55:17,  1.41it/s]
1|16096|Loss: 0.8970704078674316:  62%|██████▏   | 16096/25880 [3:17:49<1:51:04,  1.47it/s]
1|16097|Loss: 0.8348830938339233:  62%|██████▏   | 16096/25880 [3:17:50<1:51:04,  1.47it/s]
1|16097|Loss: 0.8348830938339233:  62%|██████▏   | 16097/25880 [3:17:50<1:53:04,  1.44it/s]
1|16098|Loss: 0.7629675269126892:  62%|██████▏   | 16097/25880 [3:17:50<1:53:04,  1.44it/s]
1|16098|Loss: 0.7629675269126892:  62%|██████▏   | 16098/25880 [3:17:51<1:54:40,  1.42it/s]
1|16099|Loss: 0.9797239899635315:  62%|██████▏   | 16098/25880 [3:17:51<1:54:40,  1.42it/s]
1|16099|Loss: 0.9797239899635315:  62%|██████▏   | 16099/25880 [3:17:51<1:46:15,  1.53it/s]
1|16100|Loss: 0.8443543910980225:  62%|██████▏   | 16099/25880 [3:17:52<1:46:15,  1.53it/s]
1|16100|Loss: 0.8443543910980225:  62%|██████▏   | 16100/25880 [3:17:52<1:49:36,  1.49it/s]
1|16101|Loss: 0.7850714325904846:  62%|██████▏   | 16100/25880 [3:17:52<1:49:36,  1.49it/s]
1|16101|Loss: 0.7850714325904846:  62%|██████▏   | 16101/25880 [3:17:53<1:53:17,  1.44it/s]
1|16102|Loss: 0.8400338888168335:  62%|██████▏   | 16101/25880 [3:17:53<1:53:17,  1.44it/s]
1|16102|Loss: 0.8400338888168335:  62%|██████▏   | 16102/25880 [3:17:53<1:53:52,  1.43it/s]
1|16103|Loss: 0.6396977305412292:  62%|██████▏   | 16102/25880 [3:17:54<1:53:52,  1.43it/s]
1|16103|Loss: 0.6396977305412292:  62%|██████▏   | 16103/25880 [3:17:54<2:05:09,  1.30it/s]
1|16104|Loss: 0.7447469830513:  62%|██████▏   | 16103/25880 [3:17:55<2:05:09,  1.30it/s]   
1|16104|Loss: 0.7447469830513:  62%|██████▏   | 16104/25880 [3:17:55<2:07:20,  1.28it/s]
1|16105|Loss: 0.8577694296836853:  62%|██████▏   | 16104/25880 [3:17:56<2:07:20,  1.28it/s]
1|16105|Loss: 0.8577694296836853:  62%|██████▏   | 16105/25880 [3:17:56<1:59:28,  1.36it/s]
1|16106|Loss: 0.7557250261306763:  62%|██████▏   | 16105/25880 [3:17:56<1:59:28,  1.36it/s]
1|16106|Loss: 0.7557250261306763:  62%|██████▏   | 16106/25880 [3:17:56<1:58:10,  1.38it/s]
1|16107|Loss: 0.8297670483589172:  62%|██████▏   | 16106/25880 [3:17:57<1:58:10,  1.38it/s]
1|16107|Loss: 0.8297670483589172:  62%|██████▏   | 16107/25880 [3:17:57<1:52:54,  1.44it/s]
1|16108|Loss: 0.7678583860397339:  62%|██████▏   | 16107/25880 [3:17:58<1:52:54,  1.44it/s]
1|16108|Loss: 0.7678583860397339:  62%|██████▏   | 16108/25880 [3:17:58<2:02:36,  1.33it/s]
1|16109|Loss: 0.8334611654281616:  62%|██████▏   | 16108/25880 [3:17:58<2:02:36,  1.33it/s]
1|16109|Loss: 0.8334611654281616:  62%|██████▏   | 16109/25880 [3:17:59<2:06:56,  1.28it/s]
1|16110|Loss: 0.7110334634780884:  62%|██████▏   | 16109/25880 [3:17:59<2:06:56,  1.28it/s]
1|16110|Loss: 0.7110334634780884:  62%|██████▏   | 16110/25880 [3:17:59<2:01:26,  1.34it/s]
1|16111|Loss: 0.8239785432815552:  62%|██████▏   | 16110/25880 [3:18:00<2:01:26,  1.34it/s]
1|16111|Loss: 0.8239785432815552:  62%|██████▏   | 16111/25880 [3:18:00<1:56:04,  1.40it/s]
1|16112|Loss: 0.8234322667121887:  62%|██████▏   | 16111/25880 [3:18:01<1:56:04,  1.40it/s]
1|16112|Loss: 0.8234322667121887:  62%|██████▏   | 16112/25880 [3:18:01<1:56:11,  1.40it/s]
1|16113|Loss: 0.8000292181968689:  62%|██████▏   | 16112/25880 [3:18:01<1:56:11,  1.40it/s]
1|16113|Loss: 0.8000292181968689:  62%|██████▏   | 16113/25880 [3:18:01<1:49:43,  1.48it/s]
1|16114|Loss: 0.9732541441917419:  62%|██████▏   | 16113/25880 [3:18:02<1:49:43,  1.48it/s]
1|16114|Loss: 0.9732541441917419:  62%|██████▏   | 16114/25880 [3:18:02<1:50:39,  1.47it/s]
1|16115|Loss: 0.8068274855613708:  62%|██████▏   | 16114/25880 [3:18:03<1:50:39,  1.47it/s]
1|16115|Loss: 0.8068274855613708:  62%|██████▏   | 16115/25880 [3:18:03<1:56:53,  1.39it/s]
1|16116|Loss: 0.7478218674659729:  62%|██████▏   | 16115/25880 [3:18:03<1:56:53,  1.39it/s]
1|16116|Loss: 0.7478218674659729:  62%|██████▏   | 16116/25880 [3:18:04<1:52:32,  1.45it/s]
1|16117|Loss: 0.8712692260742188:  62%|██████▏   | 16116/25880 [3:18:04<1:52:32,  1.45it/s]
1|16117|Loss: 0.8712692260742188:  62%|██████▏   | 16117/25880 [3:18:04<1:44:14,  1.56it/s]
1|16118|Loss: 0.7662171125411987:  62%|██████▏   | 16117/25880 [3:18:04<1:44:14,  1.56it/s]
1|16118|Loss: 0.7662171125411987:  62%|██████▏   | 16118/25880 [3:18:05<1:50:51,  1.47it/s]
1|16119|Loss: 0.6060190796852112:  62%|██████▏   | 16118/25880 [3:18:05<1:50:51,  1.47it/s]
1|16119|Loss: 0.6060190796852112:  62%|██████▏   | 16119/25880 [3:18:06<2:02:08,  1.33it/s]
1|16120|Loss: 0.938845157623291:  62%|██████▏   | 16119/25880 [3:18:06<2:02:08,  1.33it/s] 
1|16120|Loss: 0.938845157623291:  62%|██████▏   | 16120/25880 [3:18:06<1:58:44,  1.37it/s]
1|16121|Loss: 1.0011041164398193:  62%|██████▏   | 16120/25880 [3:18:07<1:58:44,  1.37it/s]
1|16121|Loss: 1.0011041164398193:  62%|██████▏   | 16121/25880 [3:18:07<1:54:15,  1.42it/s]
1|16122|Loss: 0.8341130018234253:  62%|██████▏   | 16121/25880 [3:18:07<1:54:15,  1.42it/s]
1|16122|Loss: 0.8341130018234253:  62%|██████▏   | 16122/25880 [3:18:08<1:53:19,  1.44it/s]
1|16123|Loss: 1.0690721273422241:  62%|██████▏   | 16122/25880 [3:18:08<1:53:19,  1.44it/s]
1|16123|Loss: 1.0690721273422241:  62%|██████▏   | 16123/25880 [3:18:08<1:54:56,  1.41it/s]
1|16124|Loss: 0.721503734588623:  62%|██████▏   | 16123/25880 [3:18:09<1:54:56,  1.41it/s] 
1|16124|Loss: 0.721503734588623:  62%|██████▏   | 16124/25880 [3:18:09<2:00:25,  1.35it/s]
1|16125|Loss: 0.8059345483779907:  62%|██████▏   | 16124/25880 [3:18:10<2:00:25,  1.35it/s]
1|16125|Loss: 0.8059345483779907:  62%|██████▏   | 16125/25880 [3:18:10<1:57:17,  1.39it/s]
1|16126|Loss: 0.8843221664428711:  62%|██████▏   | 16125/25880 [3:18:10<1:57:17,  1.39it/s]
1|16126|Loss: 0.8843221664428711:  62%|██████▏   | 16126/25880 [3:18:11<1:53:34,  1.43it/s]
1|16127|Loss: 0.8002617359161377:  62%|██████▏   | 16126/25880 [3:18:11<1:53:34,  1.43it/s]
1|16127|Loss: 0.8002617359161377:  62%|██████▏   | 16127/25880 [3:18:12<2:04:48,  1.30it/s]
1|16128|Loss: 0.9612166881561279:  62%|██████▏   | 16127/25880 [3:18:12<2:04:48,  1.30it/s]
1|16128|Loss: 0.9612166881561279:  62%|██████▏   | 16128/25880 [3:18:12<1:59:20,  1.36it/s]
1|16129|Loss: 0.7378767132759094:  62%|██████▏   | 16128/25880 [3:18:13<1:59:20,  1.36it/s]
1|16129|Loss: 0.7378767132759094:  62%|██████▏   | 16129/25880 [3:18:13<2:02:21,  1.33it/s]
1|16130|Loss: 0.7474372386932373:  62%|██████▏   | 16129/25880 [3:18:13<2:02:21,  1.33it/s]
1|16130|Loss: 0.7474372386932373:  62%|██████▏   | 16130/25880 [3:18:14<1:56:47,  1.39it/s]
1|16131|Loss: 0.7032589316368103:  62%|██████▏   | 16130/25880 [3:18:14<1:56:47,  1.39it/s]
1|16131|Loss: 0.7032589316368103:  62%|██████▏   | 16131/25880 [3:18:14<1:59:31,  1.36it/s]
1|16132|Loss: 0.8005644083023071:  62%|██████▏   | 16131/25880 [3:18:15<1:59:31,  1.36it/s]
1|16132|Loss: 0.8005644083023071:  62%|██████▏   | 16132/25880 [3:18:15<1:54:55,  1.41it/s]
1|16133|Loss: 0.8377500772476196:  62%|██████▏   | 16132/25880 [3:18:15<1:54:55,  1.41it/s]
1|16133|Loss: 0.8377500772476196:  62%|██████▏   | 16133/25880 [3:18:16<1:54:59,  1.41it/s]
1|16134|Loss: 0.8674936294555664:  62%|██████▏   | 16133/25880 [3:18:16<1:54:59,  1.41it/s]
1|16134|Loss: 0.8674936294555664:  62%|██████▏   | 16134/25880 [3:18:17<1:57:09,  1.39it/s]
1|16135|Loss: 0.9251450300216675:  62%|██████▏   | 16134/25880 [3:18:17<1:57:09,  1.39it/s]
1|16135|Loss: 0.9251450300216675:  62%|██████▏   | 16135/25880 [3:18:17<1:58:45,  1.37it/s]
1|16136|Loss: 0.9877178072929382:  62%|██████▏   | 16135/25880 [3:18:18<1:58:45,  1.37it/s]
1|16136|Loss: 0.9877178072929382:  62%|██████▏   | 16136/25880 [3:18:18<1:55:03,  1.41it/s]
1|16137|Loss: 0.79015052318573:  62%|██████▏   | 16136/25880 [3:18:18<1:55:03,  1.41it/s]  
1|16137|Loss: 0.79015052318573:  62%|██████▏   | 16137/25880 [3:18:19<1:55:29,  1.41it/s]
1|16138|Loss: 0.7722136378288269:  62%|██████▏   | 16137/25880 [3:18:19<1:55:29,  1.41it/s]
1|16138|Loss: 0.7722136378288269:  62%|██████▏   | 16138/25880 [3:18:19<1:53:40,  1.43it/s]
1|16139|Loss: 0.717840313911438:  62%|██████▏   | 16138/25880 [3:18:20<1:53:40,  1.43it/s] 
1|16139|Loss: 0.717840313911438:  62%|██████▏   | 16139/25880 [3:18:20<1:54:39,  1.42it/s]
1|16140|Loss: 0.8176082968711853:  62%|██████▏   | 16139/25880 [3:18:21<1:54:39,  1.42it/s]
1|16140|Loss: 0.8176082968711853:  62%|██████▏   | 16140/25880 [3:18:21<2:04:55,  1.30it/s]
1|16141|Loss: 1.06244957447052:  62%|██████▏   | 16140/25880 [3:18:21<2:04:55,  1.30it/s]  
1|16141|Loss: 1.06244957447052:  62%|██████▏   | 16141/25880 [3:18:22<2:05:04,  1.30it/s]
1|16142|Loss: 0.9152417778968811:  62%|██████▏   | 16141/25880 [3:18:22<2:05:04,  1.30it/s]
1|16142|Loss: 0.9152417778968811:  62%|██████▏   | 16142/25880 [3:18:23<2:05:12,  1.30it/s]
1|16143|Loss: 0.8461001515388489:  62%|██████▏   | 16142/25880 [3:18:23<2:05:12,  1.30it/s]
1|16143|Loss: 0.8461001515388489:  62%|██████▏   | 16143/25880 [3:18:23<2:09:26,  1.25it/s]
1|16144|Loss: 0.7932919263839722:  62%|██████▏   | 16143/25880 [3:18:24<2:09:26,  1.25it/s]
1|16144|Loss: 0.7932919263839722:  62%|██████▏   | 16144/25880 [3:18:24<2:13:27,  1.22it/s]
1|16145|Loss: 0.6833399534225464:  62%|██████▏   | 16144/25880 [3:18:25<2:13:27,  1.22it/s]
1|16145|Loss: 0.6833399534225464:  62%|██████▏   | 16145/25880 [3:18:25<2:14:33,  1.21it/s]
1|16146|Loss: 0.8183711171150208:  62%|██████▏   | 16145/25880 [3:18:26<2:14:33,  1.21it/s]
1|16146|Loss: 0.8183711171150208:  62%|██████▏   | 16146/25880 [3:18:26<2:15:08,  1.20it/s]
1|16147|Loss: 0.7698060274124146:  62%|██████▏   | 16146/25880 [3:18:26<2:15:08,  1.20it/s]
1|16147|Loss: 0.7698060274124146:  62%|██████▏   | 16147/25880 [3:18:27<2:12:16,  1.23it/s]
1|16148|Loss: 0.8443936109542847:  62%|██████▏   | 16147/25880 [3:18:27<2:12:16,  1.23it/s]
1|16148|Loss: 0.8443936109542847:  62%|██████▏   | 16148/25880 [3:18:27<2:08:29,  1.26it/s]
1|16149|Loss: 0.7394471168518066:  62%|██████▏   | 16148/25880 [3:18:28<2:08:29,  1.26it/s]
1|16149|Loss: 0.7394471168518066:  62%|██████▏   | 16149/25880 [3:18:28<1:58:18,  1.37it/s]
1|16150|Loss: 0.7717620134353638:  62%|██████▏   | 16149/25880 [3:18:28<1:58:18,  1.37it/s]
1|16150|Loss: 0.7717620134353638:  62%|██████▏   | 16150/25880 [3:18:29<1:52:06,  1.45it/s]
1|16151|Loss: 0.829759418964386:  62%|██████▏   | 16150/25880 [3:18:29<1:52:06,  1.45it/s] 
1|16151|Loss: 0.829759418964386:  62%|██████▏   | 16151/25880 [3:18:29<1:53:12,  1.43it/s]
1|16152|Loss: 0.8052225708961487:  62%|██████▏   | 16151/25880 [3:18:30<1:53:12,  1.43it/s]
1|16152|Loss: 0.8052225708961487:  62%|██████▏   | 16152/25880 [3:18:30<1:55:26,  1.40it/s]
1|16153|Loss: 0.7442851662635803:  62%|██████▏   | 16152/25880 [3:18:30<1:55:26,  1.40it/s]
1|16153|Loss: 0.7442851662635803:  62%|██████▏   | 16153/25880 [3:18:31<1:55:18,  1.41it/s]
1|16154|Loss: 0.7572693228721619:  62%|██████▏   | 16153/25880 [3:18:31<1:55:18,  1.41it/s]
1|16154|Loss: 0.7572693228721619:  62%|██████▏   | 16154/25880 [3:18:31<1:52:01,  1.45it/s]
1|16155|Loss: 0.8026189208030701:  62%|██████▏   | 16154/25880 [3:18:32<1:52:01,  1.45it/s]
1|16155|Loss: 0.8026189208030701:  62%|██████▏   | 16155/25880 [3:18:32<1:47:18,  1.51it/s]
1|16156|Loss: 0.7806046605110168:  62%|██████▏   | 16155/25880 [3:18:32<1:47:18,  1.51it/s]
1|16156|Loss: 0.7806046605110168:  62%|██████▏   | 16156/25880 [3:18:33<1:45:26,  1.54it/s]
1|16157|Loss: 0.9823235273361206:  62%|██████▏   | 16156/25880 [3:18:33<1:45:26,  1.54it/s]
1|16157|Loss: 0.9823235273361206:  62%|██████▏   | 16157/25880 [3:18:33<1:53:12,  1.43it/s]
1|16158|Loss: 0.8976444005966187:  62%|██████▏   | 16157/25880 [3:18:34<1:53:12,  1.43it/s]
1|16158|Loss: 0.8976444005966187:  62%|██████▏   | 16158/25880 [3:18:34<1:56:37,  1.39it/s]
1|16159|Loss: 0.8919563293457031:  62%|██████▏   | 16158/25880 [3:18:35<1:56:37,  1.39it/s]
1|16159|Loss: 0.8919563293457031:  62%|██████▏   | 16159/25880 [3:18:35<1:56:28,  1.39it/s]
1|16160|Loss: 0.999562680721283:  62%|██████▏   | 16159/25880 [3:18:35<1:56:28,  1.39it/s] 
1|16160|Loss: 0.999562680721283:  62%|██████▏   | 16160/25880 [3:18:36<1:58:31,  1.37it/s]
1|16161|Loss: 0.8037224411964417:  62%|██████▏   | 16160/25880 [3:18:36<1:58:31,  1.37it/s]
1|16161|Loss: 0.8037224411964417:  62%|██████▏   | 16161/25880 [3:18:37<2:03:01,  1.32it/s]
1|16162|Loss: 0.8707450032234192:  62%|██████▏   | 16161/25880 [3:18:37<2:03:01,  1.32it/s]
1|16162|Loss: 0.8707450032234192:  62%|██████▏   | 16162/25880 [3:18:37<2:02:22,  1.32it/s]
1|16163|Loss: 0.8833017945289612:  62%|██████▏   | 16162/25880 [3:18:38<2:02:22,  1.32it/s]
1|16163|Loss: 0.8833017945289612:  62%|██████▏   | 16163/25880 [3:18:38<2:01:39,  1.33it/s]
1|16164|Loss: 0.7433797717094421:  62%|██████▏   | 16163/25880 [3:18:38<2:01:39,  1.33it/s]
1|16164|Loss: 0.7433797717094421:  62%|██████▏   | 16164/25880 [3:18:39<2:05:45,  1.29it/s]
1|16165|Loss: 0.8134133219718933:  62%|██████▏   | 16164/25880 [3:18:39<2:05:45,  1.29it/s]
1|16165|Loss: 0.8134133219718933:  62%|██████▏   | 16165/25880 [3:18:40<2:01:21,  1.33it/s]
1|16166|Loss: 0.8398610353469849:  62%|██████▏   | 16165/25880 [3:18:40<2:01:21,  1.33it/s]
1|16166|Loss: 0.8398610353469849:  62%|██████▏   | 16166/25880 [3:18:40<1:53:49,  1.42it/s]
1|16167|Loss: 0.8920289874076843:  62%|██████▏   | 16166/25880 [3:18:41<1:53:49,  1.42it/s]
1|16167|Loss: 0.8920289874076843:  62%|██████▏   | 16167/25880 [3:18:41<1:57:37,  1.38it/s]
1|16168|Loss: 0.8230615854263306:  62%|██████▏   | 16167/25880 [3:18:41<1:57:37,  1.38it/s]
1|16168|Loss: 0.8230615854263306:  62%|██████▏   | 16168/25880 [3:18:42<1:50:51,  1.46it/s]
1|16169|Loss: 0.7052257657051086:  62%|██████▏   | 16168/25880 [3:18:42<1:50:51,  1.46it/s]
1|16169|Loss: 0.7052257657051086:  62%|██████▏   | 16169/25880 [3:18:42<1:51:01,  1.46it/s]
1|16170|Loss: 0.8188087344169617:  62%|██████▏   | 16169/25880 [3:18:43<1:51:01,  1.46it/s]
1|16170|Loss: 0.8188087344169617:  62%|██████▏   | 16170/25880 [3:18:43<1:52:51,  1.43it/s]
1|16171|Loss: 0.9481844305992126:  62%|██████▏   | 16170/25880 [3:18:43<1:52:51,  1.43it/s]
1|16171|Loss: 0.9481844305992126:  62%|██████▏   | 16171/25880 [3:18:44<1:54:54,  1.41it/s]
1|16172|Loss: 0.8353337645530701:  62%|██████▏   | 16171/25880 [3:18:44<1:54:54,  1.41it/s]
1|16172|Loss: 0.8353337645530701:  62%|██████▏   | 16172/25880 [3:18:44<1:45:19,  1.54it/s]
1|16173|Loss: 0.9414494037628174:  62%|██████▏   | 16172/25880 [3:18:45<1:45:19,  1.54it/s]
1|16173|Loss: 0.9414494037628174:  62%|██████▏   | 16173/25880 [3:18:45<1:47:03,  1.51it/s]
1|16174|Loss: 0.8700896501541138:  62%|██████▏   | 16173/25880 [3:18:45<1:47:03,  1.51it/s]
1|16174|Loss: 0.8700896501541138:  62%|██████▏   | 16174/25880 [3:18:46<1:51:19,  1.45it/s]
1|16175|Loss: 0.7805249094963074:  62%|██████▏   | 16174/25880 [3:18:46<1:51:19,  1.45it/s]
1|16175|Loss: 0.7805249094963074:  62%|██████▎   | 16175/25880 [3:18:46<1:54:18,  1.42it/s]
1|16176|Loss: 0.9160638451576233:  62%|██████▎   | 16175/25880 [3:18:47<1:54:18,  1.42it/s]
1|16176|Loss: 0.9160638451576233:  63%|██████▎   | 16176/25880 [3:18:47<1:56:17,  1.39it/s]
1|16177|Loss: 0.8135033249855042:  63%|██████▎   | 16176/25880 [3:18:48<1:56:17,  1.39it/s]
1|16177|Loss: 0.8135033249855042:  63%|██████▎   | 16177/25880 [3:18:48<2:00:39,  1.34it/s]
1|16178|Loss: 0.6305351853370667:  63%|██████▎   | 16177/25880 [3:18:48<2:00:39,  1.34it/s]
1|16178|Loss: 0.6305351853370667:  63%|██████▎   | 16178/25880 [3:18:49<2:00:54,  1.34it/s]
1|16179|Loss: 0.8635116219520569:  63%|██████▎   | 16178/25880 [3:18:49<2:00:54,  1.34it/s]
1|16179|Loss: 0.8635116219520569:  63%|██████▎   | 16179/25880 [3:18:50<2:09:50,  1.25it/s]
1|16180|Loss: 0.8299614191055298:  63%|██████▎   | 16179/25880 [3:18:50<2:09:50,  1.25it/s]
1|16180|Loss: 0.8299614191055298:  63%|██████▎   | 16180/25880 [3:18:50<2:13:21,  1.21it/s]
1|16181|Loss: 0.8520541787147522:  63%|██████▎   | 16180/25880 [3:18:51<2:13:21,  1.21it/s]
1|16181|Loss: 0.8520541787147522:  63%|██████▎   | 16181/25880 [3:18:51<2:06:07,  1.28it/s]
1|16182|Loss: 0.8007655739784241:  63%|██████▎   | 16181/25880 [3:18:51<2:06:07,  1.28it/s]
1|16182|Loss: 0.8007655739784241:  63%|██████▎   | 16182/25880 [3:18:52<1:49:49,  1.47it/s]
1|16183|Loss: 0.8223350048065186:  63%|██████▎   | 16182/25880 [3:18:52<1:49:49,  1.47it/s]
1|16183|Loss: 0.8223350048065186:  63%|██████▎   | 16183/25880 [3:18:52<1:49:21,  1.48it/s]
1|16184|Loss: 0.8079128861427307:  63%|██████▎   | 16183/25880 [3:18:53<1:49:21,  1.48it/s]
1|16184|Loss: 0.8079128861427307:  63%|██████▎   | 16184/25880 [3:18:53<1:48:21,  1.49it/s]
1|16185|Loss: 0.82545006275177:  63%|██████▎   | 16184/25880 [3:18:53<1:48:21,  1.49it/s]  
1|16185|Loss: 0.82545006275177:  63%|██████▎   | 16185/25880 [3:18:54<1:50:21,  1.46it/s]
1|16186|Loss: 0.8637934923171997:  63%|██████▎   | 16185/25880 [3:18:54<1:50:21,  1.46it/s]
1|16186|Loss: 0.8637934923171997:  63%|██████▎   | 16186/25880 [3:18:54<1:48:01,  1.50it/s]
1|16187|Loss: 0.8807181715965271:  63%|██████▎   | 16186/25880 [3:18:55<1:48:01,  1.50it/s]
1|16187|Loss: 0.8807181715965271:  63%|██████▎   | 16187/25880 [3:18:55<1:45:31,  1.53it/s]
1|16188|Loss: 0.9687831997871399:  63%|██████▎   | 16187/25880 [3:18:55<1:45:31,  1.53it/s]
1|16188|Loss: 0.9687831997871399:  63%|██████▎   | 16188/25880 [3:18:55<1:42:37,  1.57it/s]
1|16189|Loss: 0.9450514316558838:  63%|██████▎   | 16188/25880 [3:18:56<1:42:37,  1.57it/s]
1|16189|Loss: 0.9450514316558838:  63%|██████▎   | 16189/25880 [3:18:56<1:42:09,  1.58it/s]
1|16190|Loss: 0.7423728704452515:  63%|██████▎   | 16189/25880 [3:18:57<1:42:09,  1.58it/s]
1|16190|Loss: 0.7423728704452515:  63%|██████▎   | 16190/25880 [3:18:57<1:51:26,  1.45it/s]
1|16191|Loss: 0.7872059941291809:  63%|██████▎   | 16190/25880 [3:18:57<1:51:26,  1.45it/s]
1|16191|Loss: 0.7872059941291809:  63%|██████▎   | 16191/25880 [3:18:58<1:55:45,  1.40it/s]
1|16192|Loss: 0.843275785446167:  63%|██████▎   | 16191/25880 [3:18:58<1:55:45,  1.40it/s] 
1|16192|Loss: 0.843275785446167:  63%|██████▎   | 16192/25880 [3:18:58<1:56:45,  1.38it/s]
1|16193|Loss: 0.8609267473220825:  63%|██████▎   | 16192/25880 [3:18:59<1:56:45,  1.38it/s]
1|16193|Loss: 0.8609267473220825:  63%|██████▎   | 16193/25880 [3:18:59<2:00:57,  1.33it/s]
1|16194|Loss: 0.9484548568725586:  63%|██████▎   | 16193/25880 [3:19:00<2:00:57,  1.33it/s]
1|16194|Loss: 0.9484548568725586:  63%|██████▎   | 16194/25880 [3:19:00<2:04:38,  1.30it/s]
1|16195|Loss: 0.9003806710243225:  63%|██████▎   | 16194/25880 [3:19:01<2:04:38,  1.30it/s]
1|16195|Loss: 0.9003806710243225:  63%|██████▎   | 16195/25880 [3:19:01<2:02:11,  1.32it/s]
1|16196|Loss: 0.7525545358657837:  63%|██████▎   | 16195/25880 [3:19:01<2:02:11,  1.32it/s]
1|16196|Loss: 0.7525545358657837:  63%|██████▎   | 16196/25880 [3:19:01<1:54:35,  1.41it/s]
1|16197|Loss: 0.7631480693817139:  63%|██████▎   | 16196/25880 [3:19:02<1:54:35,  1.41it/s]
1|16197|Loss: 0.7631480693817139:  63%|██████▎   | 16197/25880 [3:19:02<1:50:24,  1.46it/s]
1|16198|Loss: 0.7386194467544556:  63%|██████▎   | 16197/25880 [3:19:02<1:50:24,  1.46it/s]
1|16198|Loss: 0.7386194467544556:  63%|██████▎   | 16198/25880 [3:19:03<1:47:19,  1.50it/s]
1|16199|Loss: 0.7689017057418823:  63%|██████▎   | 16198/25880 [3:19:03<1:47:19,  1.50it/s]
1|16199|Loss: 0.7689017057418823:  63%|██████▎   | 16199/25880 [3:19:04<1:58:24,  1.36it/s]
1|16200|Loss: 0.8495952486991882:  63%|██████▎   | 16199/25880 [3:19:04<1:58:24,  1.36it/s]
1|16200|Loss: 0.8495952486991882:  63%|██████▎   | 16200/25880 [3:19:04<1:56:04,  1.39it/s]
1|16201|Loss: 0.8249188661575317:  63%|██████▎   | 16200/25880 [3:19:05<1:56:04,  1.39it/s]
1|16201|Loss: 0.8249188661575317:  63%|██████▎   | 16201/25880 [3:19:05<1:55:20,  1.40it/s]
1|16202|Loss: 0.8115922808647156:  63%|██████▎   | 16201/25880 [3:19:05<1:55:20,  1.40it/s]
1|16202|Loss: 0.8115922808647156:  63%|██████▎   | 16202/25880 [3:19:06<1:54:57,  1.40it/s]
1|16203|Loss: 0.7970256209373474:  63%|██████▎   | 16202/25880 [3:19:06<1:54:57,  1.40it/s]
1|16203|Loss: 0.7970256209373474:  63%|██████▎   | 16203/25880 [3:19:06<1:59:49,  1.35it/s]
1|16204|Loss: 0.8381673097610474:  63%|██████▎   | 16203/25880 [3:19:07<1:59:49,  1.35it/s]
1|16204|Loss: 0.8381673097610474:  63%|██████▎   | 16204/25880 [3:19:07<2:07:28,  1.27it/s]
1|16205|Loss: 0.7376765012741089:  63%|██████▎   | 16204/25880 [3:19:08<2:07:28,  1.27it/s]
1|16205|Loss: 0.7376765012741089:  63%|██████▎   | 16205/25880 [3:19:08<1:55:20,  1.40it/s]
1|16206|Loss: 0.6979041695594788:  63%|██████▎   | 16205/25880 [3:19:08<1:55:20,  1.40it/s]
1|16206|Loss: 0.6979041695594788:  63%|██████▎   | 16206/25880 [3:19:08<1:47:10,  1.50it/s]
1|16207|Loss: 0.8941079378128052:  63%|██████▎   | 16206/25880 [3:19:09<1:47:10,  1.50it/s]
1|16207|Loss: 0.8941079378128052:  63%|██████▎   | 16207/25880 [3:19:09<1:51:30,  1.45it/s]
1|16208|Loss: 0.8562756776809692:  63%|██████▎   | 16207/25880 [3:19:10<1:51:30,  1.45it/s]
1|16208|Loss: 0.8562756776809692:  63%|██████▎   | 16208/25880 [3:19:10<1:53:43,  1.42it/s]
1|16209|Loss: 0.850214421749115:  63%|██████▎   | 16208/25880 [3:19:10<1:53:43,  1.42it/s] 
1|16209|Loss: 0.850214421749115:  63%|██████▎   | 16209/25880 [3:19:11<1:59:37,  1.35it/s]
1|16210|Loss: 0.6757274270057678:  63%|██████▎   | 16209/25880 [3:19:11<1:59:37,  1.35it/s]
1|16210|Loss: 0.6757274270057678:  63%|██████▎   | 16210/25880 [3:19:11<1:52:14,  1.44it/s]
1|16211|Loss: 0.7943556904792786:  63%|██████▎   | 16210/25880 [3:19:12<1:52:14,  1.44it/s]
1|16211|Loss: 0.7943556904792786:  63%|██████▎   | 16211/25880 [3:19:12<1:43:19,  1.56it/s]
1|16212|Loss: 0.8057257533073425:  63%|██████▎   | 16211/25880 [3:19:12<1:43:19,  1.56it/s]
1|16212|Loss: 0.8057257533073425:  63%|██████▎   | 16212/25880 [3:19:12<1:39:44,  1.62it/s]
1|16213|Loss: 0.7716213464736938:  63%|██████▎   | 16212/25880 [3:19:13<1:39:44,  1.62it/s]
1|16213|Loss: 0.7716213464736938:  63%|██████▎   | 16213/25880 [3:19:13<1:36:44,  1.67it/s]
1|16214|Loss: 0.8786565065383911:  63%|██████▎   | 16213/25880 [3:19:13<1:36:44,  1.67it/s]
1|16214|Loss: 0.8786565065383911:  63%|██████▎   | 16214/25880 [3:19:14<1:37:00,  1.66it/s]
1|16215|Loss: 0.7823765277862549:  63%|██████▎   | 16214/25880 [3:19:14<1:37:00,  1.66it/s]
1|16215|Loss: 0.7823765277862549:  63%|██████▎   | 16215/25880 [3:19:14<1:42:29,  1.57it/s]
1|16216|Loss: 0.8597506284713745:  63%|██████▎   | 16215/25880 [3:19:15<1:42:29,  1.57it/s]
1|16216|Loss: 0.8597506284713745:  63%|██████▎   | 16216/25880 [3:19:15<1:52:58,  1.43it/s]
1|16217|Loss: 0.9269416928291321:  63%|██████▎   | 16216/25880 [3:19:16<1:52:58,  1.43it/s]
1|16217|Loss: 0.9269416928291321:  63%|██████▎   | 16217/25880 [3:19:16<1:54:56,  1.40it/s]
1|16218|Loss: 0.8218874335289001:  63%|██████▎   | 16217/25880 [3:19:16<1:54:56,  1.40it/s]
1|16218|Loss: 0.8218874335289001:  63%|██████▎   | 16218/25880 [3:19:17<1:55:10,  1.40it/s]
1|16219|Loss: 0.8852896690368652:  63%|██████▎   | 16218/25880 [3:19:17<1:55:10,  1.40it/s]
1|16219|Loss: 0.8852896690368652:  63%|██████▎   | 16219/25880 [3:19:17<1:55:20,  1.40it/s]
1|16220|Loss: 0.788190484046936:  63%|██████▎   | 16219/25880 [3:19:18<1:55:20,  1.40it/s] 
1|16220|Loss: 0.788190484046936:  63%|██████▎   | 16220/25880 [3:19:18<1:50:24,  1.46it/s]
1|16221|Loss: 0.9043279886245728:  63%|██████▎   | 16220/25880 [3:19:18<1:50:24,  1.46it/s]
1|16221|Loss: 0.9043279886245728:  63%|██████▎   | 16221/25880 [3:19:19<1:51:33,  1.44it/s]
1|16222|Loss: 0.7829838991165161:  63%|██████▎   | 16221/25880 [3:19:19<1:51:33,  1.44it/s]
1|16222|Loss: 0.7829838991165161:  63%|██████▎   | 16222/25880 [3:19:19<1:46:57,  1.50it/s]
1|16223|Loss: 0.842808723449707:  63%|██████▎   | 16222/25880 [3:19:20<1:46:57,  1.50it/s] 
1|16223|Loss: 0.842808723449707:  63%|██████▎   | 16223/25880 [3:19:20<1:48:35,  1.48it/s]
1|16224|Loss: 0.8033992648124695:  63%|██████▎   | 16223/25880 [3:19:20<1:48:35,  1.48it/s]
1|16224|Loss: 0.8033992648124695:  63%|██████▎   | 16224/25880 [3:19:21<1:51:55,  1.44it/s]
1|16225|Loss: 0.9340040683746338:  63%|██████▎   | 16224/25880 [3:19:21<1:51:55,  1.44it/s]
1|16225|Loss: 0.9340040683746338:  63%|██████▎   | 16225/25880 [3:19:21<1:54:27,  1.41it/s]
1|16226|Loss: 0.7498080134391785:  63%|██████▎   | 16225/25880 [3:19:22<1:54:27,  1.41it/s]
1|16226|Loss: 0.7498080134391785:  63%|██████▎   | 16226/25880 [3:19:22<1:56:16,  1.38it/s]
1|16227|Loss: 0.8079395294189453:  63%|██████▎   | 16226/25880 [3:19:23<1:56:16,  1.38it/s]
1|16227|Loss: 0.8079395294189453:  63%|██████▎   | 16227/25880 [3:19:23<1:53:35,  1.42it/s]
1|16228|Loss: 0.9740384817123413:  63%|██████▎   | 16227/25880 [3:19:23<1:53:35,  1.42it/s]
1|16228|Loss: 0.9740384817123413:  63%|██████▎   | 16228/25880 [3:19:24<1:58:03,  1.36it/s]
1|16229|Loss: 0.6452839374542236:  63%|██████▎   | 16228/25880 [3:19:24<1:58:03,  1.36it/s]
1|16229|Loss: 0.6452839374542236:  63%|██████▎   | 16229/25880 [3:19:25<2:08:28,  1.25it/s]
1|16230|Loss: 0.9540697336196899:  63%|██████▎   | 16229/25880 [3:19:25<2:08:28,  1.25it/s]
1|16230|Loss: 0.9540697336196899:  63%|██████▎   | 16230/25880 [3:19:25<2:02:55,  1.31it/s]
1|16231|Loss: 0.9178563952445984:  63%|██████▎   | 16230/25880 [3:19:26<2:02:55,  1.31it/s]
1|16231|Loss: 0.9178563952445984:  63%|██████▎   | 16231/25880 [3:19:26<1:55:50,  1.39it/s]
1|16232|Loss: 0.6645915508270264:  63%|██████▎   | 16231/25880 [3:19:26<1:55:50,  1.39it/s]
1|16232|Loss: 0.6645915508270264:  63%|██████▎   | 16232/25880 [3:19:26<1:46:58,  1.50it/s]
1|16233|Loss: 0.7570777535438538:  63%|██████▎   | 16232/25880 [3:19:27<1:46:58,  1.50it/s]
1|16233|Loss: 0.7570777535438538:  63%|██████▎   | 16233/25880 [3:19:27<1:43:28,  1.55it/s]
1|16234|Loss: 0.8020381331443787:  63%|██████▎   | 16233/25880 [3:19:27<1:43:28,  1.55it/s]
1|16234|Loss: 0.8020381331443787:  63%|██████▎   | 16234/25880 [3:19:28<1:50:29,  1.45it/s]
1|16235|Loss: 0.8780051469802856:  63%|██████▎   | 16234/25880 [3:19:28<1:50:29,  1.45it/s]
1|16235|Loss: 0.8780051469802856:  63%|██████▎   | 16235/25880 [3:19:29<1:58:16,  1.36it/s]
1|16236|Loss: 0.9143585562705994:  63%|██████▎   | 16235/25880 [3:19:29<1:58:16,  1.36it/s]
1|16236|Loss: 0.9143585562705994:  63%|██████▎   | 16236/25880 [3:19:30<2:01:47,  1.32it/s]
1|16237|Loss: 0.7235949635505676:  63%|██████▎   | 16236/25880 [3:19:30<2:01:47,  1.32it/s]
1|16237|Loss: 0.7235949635505676:  63%|██████▎   | 16237/25880 [3:19:30<2:01:32,  1.32it/s]
1|16238|Loss: 0.9251065254211426:  63%|██████▎   | 16237/25880 [3:19:31<2:01:32,  1.32it/s]
1|16238|Loss: 0.9251065254211426:  63%|██████▎   | 16238/25880 [3:19:31<1:59:48,  1.34it/s]
1|16239|Loss: 0.8337146639823914:  63%|██████▎   | 16238/25880 [3:19:31<1:59:48,  1.34it/s]
1|16239|Loss: 0.8337146639823914:  63%|██████▎   | 16239/25880 [3:19:32<2:02:44,  1.31it/s]
1|16240|Loss: 0.7947211265563965:  63%|██████▎   | 16239/25880 [3:19:32<2:02:44,  1.31it/s]
1|16240|Loss: 0.7947211265563965:  63%|██████▎   | 16240/25880 [3:19:33<2:00:54,  1.33it/s]
1|16241|Loss: 0.8678284883499146:  63%|██████▎   | 16240/25880 [3:19:33<2:00:54,  1.33it/s]
1|16241|Loss: 0.8678284883499146:  63%|██████▎   | 16241/25880 [3:19:33<1:58:27,  1.36it/s]
1|16242|Loss: 0.7982168793678284:  63%|██████▎   | 16241/25880 [3:19:34<1:58:27,  1.36it/s]
1|16242|Loss: 0.7982168793678284:  63%|██████▎   | 16242/25880 [3:19:34<2:00:17,  1.34it/s]
1|16243|Loss: 0.8665657043457031:  63%|██████▎   | 16242/25880 [3:19:34<2:00:17,  1.34it/s]
1|16243|Loss: 0.8665657043457031:  63%|██████▎   | 16243/25880 [3:19:35<1:55:54,  1.39it/s]
1|16244|Loss: 0.8190916776657104:  63%|██████▎   | 16243/25880 [3:19:35<1:55:54,  1.39it/s]
1|16244|Loss: 0.8190916776657104:  63%|██████▎   | 16244/25880 [3:19:35<1:49:32,  1.47it/s]
1|16245|Loss: 0.9142243266105652:  63%|██████▎   | 16244/25880 [3:19:36<1:49:32,  1.47it/s]
1|16245|Loss: 0.9142243266105652:  63%|██████▎   | 16245/25880 [3:19:36<1:46:03,  1.51it/s]
1|16246|Loss: 0.764503538608551:  63%|██████▎   | 16245/25880 [3:19:36<1:46:03,  1.51it/s] 
1|16246|Loss: 0.764503538608551:  63%|██████▎   | 16246/25880 [3:19:36<1:43:01,  1.56it/s]
1|16247|Loss: 0.7233710289001465:  63%|██████▎   | 16246/25880 [3:19:37<1:43:01,  1.56it/s]
1|16247|Loss: 0.7233710289001465:  63%|██████▎   | 16247/25880 [3:19:37<1:41:24,  1.58it/s]
1|16248|Loss: 0.692956268787384:  63%|██████▎   | 16247/25880 [3:19:37<1:41:24,  1.58it/s] 
1|16248|Loss: 0.692956268787384:  63%|██████▎   | 16248/25880 [3:19:38<1:48:47,  1.48it/s]
1|16249|Loss: 0.8087530136108398:  63%|██████▎   | 16248/25880 [3:19:38<1:48:47,  1.48it/s]
1|16249|Loss: 0.8087530136108398:  63%|██████▎   | 16249/25880 [3:19:39<1:54:32,  1.40it/s]
1|16250|Loss: 0.8764363527297974:  63%|██████▎   | 16249/25880 [3:19:39<1:54:32,  1.40it/s]
1|16250|Loss: 0.8764363527297974:  63%|██████▎   | 16250/25880 [3:19:39<1:48:25,  1.48it/s]
1|16251|Loss: 0.7399624586105347:  63%|██████▎   | 16250/25880 [3:19:40<1:48:25,  1.48it/s]
1|16251|Loss: 0.7399624586105347:  63%|██████▎   | 16251/25880 [3:19:40<1:44:43,  1.53it/s]
1|16252|Loss: 0.9005951285362244:  63%|██████▎   | 16251/25880 [3:19:40<1:44:43,  1.53it/s]
1|16252|Loss: 0.9005951285362244:  63%|██████▎   | 16252/25880 [3:19:40<1:40:39,  1.59it/s]
1|16253|Loss: 0.8465380668640137:  63%|██████▎   | 16252/25880 [3:19:41<1:40:39,  1.59it/s]
1|16253|Loss: 0.8465380668640137:  63%|██████▎   | 16253/25880 [3:19:41<1:40:14,  1.60it/s]
1|16254|Loss: 0.666510283946991:  63%|██████▎   | 16253/25880 [3:19:41<1:40:14,  1.60it/s] 
1|16254|Loss: 0.666510283946991:  63%|██████▎   | 16254/25880 [3:19:42<1:47:00,  1.50it/s]
1|16255|Loss: 0.790574848651886:  63%|██████▎   | 16254/25880 [3:19:42<1:47:00,  1.50it/s]
1|16255|Loss: 0.790574848651886:  63%|██████▎   | 16255/25880 [3:19:43<1:57:30,  1.37it/s]
1|16256|Loss: 0.9730637669563293:  63%|██████▎   | 16255/25880 [3:19:43<1:57:30,  1.37it/s]
1|16256|Loss: 0.9730637669563293:  63%|██████▎   | 16256/25880 [3:19:43<1:59:08,  1.35it/s]
1|16257|Loss: 0.8000469207763672:  63%|██████▎   | 16256/25880 [3:19:44<1:59:08,  1.35it/s]
1|16257|Loss: 0.8000469207763672:  63%|██████▎   | 16257/25880 [3:19:44<2:02:25,  1.31it/s]
1|16258|Loss: 0.743437647819519:  63%|██████▎   | 16257/25880 [3:19:45<2:02:25,  1.31it/s] 
1|16258|Loss: 0.743437647819519:  63%|██████▎   | 16258/25880 [3:19:45<2:00:45,  1.33it/s]
1|16259|Loss: 0.6986382603645325:  63%|██████▎   | 16258/25880 [3:19:45<2:00:45,  1.33it/s]
1|16259|Loss: 0.6986382603645325:  63%|██████▎   | 16259/25880 [3:19:46<2:04:06,  1.29it/s]
1|16260|Loss: 0.6429122090339661:  63%|██████▎   | 16259/25880 [3:19:46<2:04:06,  1.29it/s]
1|16260|Loss: 0.6429122090339661:  63%|██████▎   | 16260/25880 [3:19:47<2:02:25,  1.31it/s]
1|16261|Loss: 0.886125922203064:  63%|██████▎   | 16260/25880 [3:19:47<2:02:25,  1.31it/s] 
1|16261|Loss: 0.886125922203064:  63%|██████▎   | 16261/25880 [3:19:47<2:05:41,  1.28it/s]
1|16262|Loss: 0.8235463500022888:  63%|██████▎   | 16261/25880 [3:19:48<2:05:41,  1.28it/s]
1|16262|Loss: 0.8235463500022888:  63%|██████▎   | 16262/25880 [3:19:48<2:08:39,  1.25it/s]
1|16263|Loss: 0.8798958659172058:  63%|██████▎   | 16262/25880 [3:19:49<2:08:39,  1.25it/s]
1|16263|Loss: 0.8798958659172058:  63%|██████▎   | 16263/25880 [3:19:49<2:06:23,  1.27it/s]
1|16264|Loss: 0.7872556447982788:  63%|██████▎   | 16263/25880 [3:19:49<2:06:23,  1.27it/s]
1|16264|Loss: 0.7872556447982788:  63%|██████▎   | 16264/25880 [3:19:50<1:58:28,  1.35it/s]
1|16265|Loss: 0.8886917233467102:  63%|██████▎   | 16264/25880 [3:19:50<1:58:28,  1.35it/s]
1|16265|Loss: 0.8886917233467102:  63%|██████▎   | 16265/25880 [3:19:50<1:56:39,  1.37it/s]
1|16266|Loss: 0.8508915901184082:  63%|██████▎   | 16265/25880 [3:19:51<1:56:39,  1.37it/s]
1|16266|Loss: 0.8508915901184082:  63%|██████▎   | 16266/25880 [3:19:51<1:52:29,  1.42it/s]
1|16267|Loss: 0.8733430504798889:  63%|██████▎   | 16266/25880 [3:19:51<1:52:29,  1.42it/s]
1|16267|Loss: 0.8733430504798889:  63%|██████▎   | 16267/25880 [3:19:52<1:51:33,  1.44it/s]
1|16268|Loss: 0.8644111752510071:  63%|██████▎   | 16267/25880 [3:19:52<1:51:33,  1.44it/s]
1|16268|Loss: 0.8644111752510071:  63%|██████▎   | 16268/25880 [3:19:52<1:41:42,  1.58it/s]
1|16269|Loss: 0.7828069925308228:  63%|██████▎   | 16268/25880 [3:19:52<1:41:42,  1.58it/s]
1|16269|Loss: 0.7828069925308228:  63%|██████▎   | 16269/25880 [3:19:53<1:48:26,  1.48it/s]
1|16270|Loss: 0.7757675647735596:  63%|██████▎   | 16269/25880 [3:19:53<1:48:26,  1.48it/s]
1|16270|Loss: 0.7757675647735596:  63%|██████▎   | 16270/25880 [3:19:54<1:53:02,  1.42it/s]
1|16271|Loss: 0.941779375076294:  63%|██████▎   | 16270/25880 [3:19:54<1:53:02,  1.42it/s] 
1|16271|Loss: 0.941779375076294:  63%|██████▎   | 16271/25880 [3:19:55<2:03:40,  1.29it/s]
1|16272|Loss: 0.8230825662612915:  63%|██████▎   | 16271/25880 [3:19:55<2:03:40,  1.29it/s]
1|16272|Loss: 0.8230825662612915:  63%|██████▎   | 16272/25880 [3:19:55<2:05:54,  1.27it/s]
1|16273|Loss: 0.8156101107597351:  63%|██████▎   | 16272/25880 [3:19:56<2:05:54,  1.27it/s]
1|16273|Loss: 0.8156101107597351:  63%|██████▎   | 16273/25880 [3:19:56<2:02:48,  1.30it/s]
1|16274|Loss: 0.8861296772956848:  63%|██████▎   | 16273/25880 [3:19:56<2:02:48,  1.30it/s]
1|16274|Loss: 0.8861296772956848:  63%|██████▎   | 16274/25880 [3:19:57<1:54:56,  1.39it/s]
1|16275|Loss: 0.8555256724357605:  63%|██████▎   | 16274/25880 [3:19:57<1:54:56,  1.39it/s]
1|16275|Loss: 0.8555256724357605:  63%|██████▎   | 16275/25880 [3:19:57<1:54:06,  1.40it/s]
1|16276|Loss: 0.8525451421737671:  63%|██████▎   | 16275/25880 [3:19:58<1:54:06,  1.40it/s]
1|16276|Loss: 0.8525451421737671:  63%|██████▎   | 16276/25880 [3:19:58<1:53:51,  1.41it/s]
1|16277|Loss: 0.8350285291671753:  63%|██████▎   | 16276/25880 [3:19:59<1:53:51,  1.41it/s]
1|16277|Loss: 0.8350285291671753:  63%|██████▎   | 16277/25880 [3:19:59<1:54:40,  1.40it/s]
1|16278|Loss: 0.8998532295227051:  63%|██████▎   | 16277/25880 [3:19:59<1:54:40,  1.40it/s]
1|16278|Loss: 0.8998532295227051:  63%|██████▎   | 16278/25880 [3:19:59<1:49:39,  1.46it/s]
1|16279|Loss: 1.0089274644851685:  63%|██████▎   | 16278/25880 [3:20:00<1:49:39,  1.46it/s]
1|16279|Loss: 1.0089274644851685:  63%|██████▎   | 16279/25880 [3:20:00<1:50:31,  1.45it/s]
1|16280|Loss: 0.9105649590492249:  63%|██████▎   | 16279/25880 [3:20:01<1:50:31,  1.45it/s]
1|16280|Loss: 0.9105649590492249:  63%|██████▎   | 16280/25880 [3:20:01<1:53:31,  1.41it/s]
1|16281|Loss: 0.8685855269432068:  63%|██████▎   | 16280/25880 [3:20:01<1:53:31,  1.41it/s]
1|16281|Loss: 0.8685855269432068:  63%|██████▎   | 16281/25880 [3:20:02<1:50:50,  1.44it/s]
1|16282|Loss: 0.776634156703949:  63%|██████▎   | 16281/25880 [3:20:02<1:50:50,  1.44it/s] 
1|16282|Loss: 0.776634156703949:  63%|██████▎   | 16282/25880 [3:20:02<1:55:24,  1.39it/s]
1|16283|Loss: 0.8921375274658203:  63%|██████▎   | 16282/25880 [3:20:03<1:55:24,  1.39it/s]
1|16283|Loss: 0.8921375274658203:  63%|██████▎   | 16283/25880 [3:20:03<1:57:13,  1.36it/s]
1|16284|Loss: 1.004582405090332:  63%|██████▎   | 16283/25880 [3:20:04<1:57:13,  1.36it/s] 
1|16284|Loss: 1.004582405090332:  63%|██████▎   | 16284/25880 [3:20:04<1:57:26,  1.36it/s]
1|16285|Loss: 0.7691026329994202:  63%|██████▎   | 16284/25880 [3:20:04<1:57:26,  1.36it/s]
1|16285|Loss: 0.7691026329994202:  63%|██████▎   | 16285/25880 [3:20:05<2:03:10,  1.30it/s]
1|16286|Loss: 0.8923007845878601:  63%|██████▎   | 16285/25880 [3:20:05<2:03:10,  1.30it/s]
1|16286|Loss: 0.8923007845878601:  63%|██████▎   | 16286/25880 [3:20:06<2:12:06,  1.21it/s]
1|16287|Loss: 0.9102407693862915:  63%|██████▎   | 16286/25880 [3:20:06<2:12:06,  1.21it/s]
1|16287|Loss: 0.9102407693862915:  63%|██████▎   | 16287/25880 [3:20:06<2:05:10,  1.28it/s]
1|16288|Loss: 0.7537009119987488:  63%|██████▎   | 16287/25880 [3:20:07<2:05:10,  1.28it/s]
1|16288|Loss: 0.7537009119987488:  63%|██████▎   | 16288/25880 [3:20:07<2:06:09,  1.27it/s]
1|16289|Loss: 0.8536993265151978:  63%|██████▎   | 16288/25880 [3:20:08<2:06:09,  1.27it/s]
1|16289|Loss: 0.8536993265151978:  63%|██████▎   | 16289/25880 [3:20:08<2:09:33,  1.23it/s]
1|16290|Loss: 0.7606857419013977:  63%|██████▎   | 16289/25880 [3:20:08<2:09:33,  1.23it/s]
1|16290|Loss: 0.7606857419013977:  63%|██████▎   | 16290/25880 [3:20:09<2:07:25,  1.25it/s]
1|16291|Loss: 0.8012320399284363:  63%|██████▎   | 16290/25880 [3:20:09<2:07:25,  1.25it/s]
1|16291|Loss: 0.8012320399284363:  63%|██████▎   | 16291/25880 [3:20:10<2:07:30,  1.25it/s]
1|16292|Loss: 0.8174403309822083:  63%|██████▎   | 16291/25880 [3:20:10<2:07:30,  1.25it/s]
1|16292|Loss: 0.8174403309822083:  63%|██████▎   | 16292/25880 [3:20:10<1:57:11,  1.36it/s]
1|16293|Loss: 0.8852959275245667:  63%|██████▎   | 16292/25880 [3:20:11<1:57:11,  1.36it/s]
1|16293|Loss: 0.8852959275245667:  63%|██████▎   | 16293/25880 [3:20:11<1:51:38,  1.43it/s]
1|16294|Loss: 0.7532101273536682:  63%|██████▎   | 16293/25880 [3:20:11<1:51:38,  1.43it/s]
1|16294|Loss: 0.7532101273536682:  63%|██████▎   | 16294/25880 [3:20:12<1:57:55,  1.35it/s]
1|16295|Loss: 0.8330193161964417:  63%|██████▎   | 16294/25880 [3:20:12<1:57:55,  1.35it/s]
1|16295|Loss: 0.8330193161964417:  63%|██████▎   | 16295/25880 [3:20:12<2:01:27,  1.32it/s]
1|16296|Loss: 0.8107764720916748:  63%|██████▎   | 16295/25880 [3:20:13<2:01:27,  1.32it/s]
1|16296|Loss: 0.8107764720916748:  63%|██████▎   | 16296/25880 [3:20:13<1:56:25,  1.37it/s]
1|16297|Loss: 0.8275113105773926:  63%|██████▎   | 16296/25880 [3:20:13<1:56:25,  1.37it/s]
1|16297|Loss: 0.8275113105773926:  63%|██████▎   | 16297/25880 [3:20:14<1:56:03,  1.38it/s]
1|16298|Loss: 0.7605381011962891:  63%|██████▎   | 16297/25880 [3:20:14<1:56:03,  1.38it/s]
1|16298|Loss: 0.7605381011962891:  63%|██████▎   | 16298/25880 [3:20:15<2:03:46,  1.29it/s]
1|16299|Loss: 0.838826596736908:  63%|██████▎   | 16298/25880 [3:20:15<2:03:46,  1.29it/s] 
1|16299|Loss: 0.838826596736908:  63%|██████▎   | 16299/25880 [3:20:16<2:08:03,  1.25it/s]
1|16300|Loss: 0.9375755786895752:  63%|██████▎   | 16299/25880 [3:20:16<2:08:03,  1.25it/s]
1|16300|Loss: 0.9375755786895752:  63%|██████▎   | 16300/25880 [3:20:16<2:02:31,  1.30it/s]
1|16301|Loss: 1.1021994352340698:  63%|██████▎   | 16300/25880 [3:20:17<2:02:31,  1.30it/s]
1|16301|Loss: 1.1021994352340698:  63%|██████▎   | 16301/25880 [3:20:17<2:04:43,  1.28it/s]
1|16302|Loss: 0.7480800747871399:  63%|██████▎   | 16301/25880 [3:20:17<2:04:43,  1.28it/s]
1|16302|Loss: 0.7480800747871399:  63%|██████▎   | 16302/25880 [3:20:18<2:00:29,  1.32it/s]
1|16303|Loss: 0.9064334034919739:  63%|██████▎   | 16302/25880 [3:20:18<2:00:29,  1.32it/s]
1|16303|Loss: 0.9064334034919739:  63%|██████▎   | 16303/25880 [3:20:19<2:06:06,  1.27it/s]
1|16304|Loss: 0.8708617687225342:  63%|██████▎   | 16303/25880 [3:20:19<2:06:06,  1.27it/s]
1|16304|Loss: 0.8708617687225342:  63%|██████▎   | 16304/25880 [3:20:19<2:00:29,  1.32it/s]
1|16305|Loss: 0.9005849957466125:  63%|██████▎   | 16304/25880 [3:20:20<2:00:29,  1.32it/s]
1|16305|Loss: 0.9005849957466125:  63%|██████▎   | 16305/25880 [3:20:20<1:57:59,  1.35it/s]
1|16306|Loss: 0.9022888541221619:  63%|██████▎   | 16305/25880 [3:20:20<1:57:59,  1.35it/s]
1|16306|Loss: 0.9022888541221619:  63%|██████▎   | 16306/25880 [3:20:21<2:02:27,  1.30it/s]
1|16307|Loss: 0.9267051219940186:  63%|██████▎   | 16306/25880 [3:20:21<2:02:27,  1.30it/s]
1|16307|Loss: 0.9267051219940186:  63%|██████▎   | 16307/25880 [3:20:21<1:56:17,  1.37it/s]
1|16308|Loss: 0.9234063625335693:  63%|██████▎   | 16307/25880 [3:20:22<1:56:17,  1.37it/s]
1|16308|Loss: 0.9234063625335693:  63%|██████▎   | 16308/25880 [3:20:22<2:03:45,  1.29it/s]
1|16309|Loss: 0.9179118275642395:  63%|██████▎   | 16308/25880 [3:20:23<2:03:45,  1.29it/s]
1|16309|Loss: 0.9179118275642395:  63%|██████▎   | 16309/25880 [3:20:23<2:02:46,  1.30it/s]
1|16310|Loss: 0.8376136422157288:  63%|██████▎   | 16309/25880 [3:20:24<2:02:46,  1.30it/s]
1|16310|Loss: 0.8376136422157288:  63%|██████▎   | 16310/25880 [3:20:24<2:00:55,  1.32it/s]
1|16311|Loss: 0.881278395652771:  63%|██████▎   | 16310/25880 [3:20:24<2:00:55,  1.32it/s] 
1|16311|Loss: 0.881278395652771:  63%|██████▎   | 16311/25880 [3:20:25<2:00:07,  1.33it/s]
1|16312|Loss: 0.7968176007270813:  63%|██████▎   | 16311/25880 [3:20:25<2:00:07,  1.33it/s]
1|16312|Loss: 0.7968176007270813:  63%|██████▎   | 16312/25880 [3:20:25<1:58:30,  1.35it/s]
1|16313|Loss: 0.9063681960105896:  63%|██████▎   | 16312/25880 [3:20:26<1:58:30,  1.35it/s]
1|16313|Loss: 0.9063681960105896:  63%|██████▎   | 16313/25880 [3:20:26<2:02:09,  1.31it/s]
1|16314|Loss: 1.0395830869674683:  63%|██████▎   | 16313/25880 [3:20:27<2:02:09,  1.31it/s]
1|16314|Loss: 1.0395830869674683:  63%|██████▎   | 16314/25880 [3:20:27<1:53:25,  1.41it/s]
1|16315|Loss: 0.766494631767273:  63%|██████▎   | 16314/25880 [3:20:27<1:53:25,  1.41it/s] 
1|16315|Loss: 0.766494631767273:  63%|██████▎   | 16315/25880 [3:20:28<1:57:11,  1.36it/s]
1|16316|Loss: 0.874627411365509:  63%|██████▎   | 16315/25880 [3:20:28<1:57:11,  1.36it/s]
1|16316|Loss: 0.874627411365509:  63%|██████▎   | 16316/25880 [3:20:28<1:54:05,  1.40it/s]
1|16317|Loss: 0.817869246006012:  63%|██████▎   | 16316/25880 [3:20:29<1:54:05,  1.40it/s]
1|16317|Loss: 0.817869246006012:  63%|██████▎   | 16317/25880 [3:20:29<2:03:54,  1.29it/s]
1|16318|Loss: 0.8224087357521057:  63%|██████▎   | 16317/25880 [3:20:30<2:03:54,  1.29it/s]
1|16318|Loss: 0.8224087357521057:  63%|██████▎   | 16318/25880 [3:20:30<2:04:35,  1.28it/s]
1|16319|Loss: 0.7765692472457886:  63%|██████▎   | 16318/25880 [3:20:30<2:04:35,  1.28it/s]
1|16319|Loss: 0.7765692472457886:  63%|██████▎   | 16319/25880 [3:20:31<2:06:53,  1.26it/s]
1|16320|Loss: 0.8824118971824646:  63%|██████▎   | 16319/25880 [3:20:31<2:06:53,  1.26it/s]
1|16320|Loss: 0.8824118971824646:  63%|██████▎   | 16320/25880 [3:20:32<2:05:31,  1.27it/s]
1|16321|Loss: 0.8307578563690186:  63%|██████▎   | 16320/25880 [3:20:32<2:05:31,  1.27it/s]
1|16321|Loss: 0.8307578563690186:  63%|██████▎   | 16321/25880 [3:20:32<1:58:37,  1.34it/s]
1|16322|Loss: 0.9693888425827026:  63%|██████▎   | 16321/25880 [3:20:33<1:58:37,  1.34it/s]
1|16322|Loss: 0.9693888425827026:  63%|██████▎   | 16322/25880 [3:20:33<1:57:31,  1.36it/s]
1|16323|Loss: 0.835214376449585:  63%|██████▎   | 16322/25880 [3:20:33<1:57:31,  1.36it/s] 
1|16323|Loss: 0.835214376449585:  63%|██████▎   | 16323/25880 [3:20:34<2:01:34,  1.31it/s]
1|16324|Loss: 0.8548190593719482:  63%|██████▎   | 16323/25880 [3:20:34<2:01:34,  1.31it/s]
1|16324|Loss: 0.8548190593719482:  63%|██████▎   | 16324/25880 [3:20:34<1:54:15,  1.39it/s]
1|16325|Loss: 0.7935829162597656:  63%|██████▎   | 16324/25880 [3:20:35<1:54:15,  1.39it/s]
1|16325|Loss: 0.7935829162597656:  63%|██████▎   | 16325/25880 [3:20:35<1:59:07,  1.34it/s]
1|16326|Loss: 0.7800180315971375:  63%|██████▎   | 16325/25880 [3:20:36<1:59:07,  1.34it/s]
1|16326|Loss: 0.7800180315971375:  63%|██████▎   | 16326/25880 [3:20:36<1:59:07,  1.34it/s]
1|16327|Loss: 0.7448627352714539:  63%|██████▎   | 16326/25880 [3:20:36<1:59:07,  1.34it/s]
1|16327|Loss: 0.7448627352714539:  63%|██████▎   | 16327/25880 [3:20:36<1:49:32,  1.45it/s]
1|16328|Loss: 0.9009569883346558:  63%|██████▎   | 16327/25880 [3:20:37<1:49:32,  1.45it/s]
1|16328|Loss: 0.9009569883346558:  63%|██████▎   | 16328/25880 [3:20:37<1:49:23,  1.46it/s]
1|16329|Loss: 0.7267159819602966:  63%|██████▎   | 16328/25880 [3:20:37<1:49:23,  1.46it/s]
1|16329|Loss: 0.7267159819602966:  63%|██████▎   | 16329/25880 [3:20:38<1:48:02,  1.47it/s]
1|16330|Loss: 0.9192199110984802:  63%|██████▎   | 16329/25880 [3:20:38<1:48:02,  1.47it/s]
1|16330|Loss: 0.9192199110984802:  63%|██████▎   | 16330/25880 [3:20:38<1:45:03,  1.52it/s]
1|16331|Loss: 0.8383849263191223:  63%|██████▎   | 16330/25880 [3:20:39<1:45:03,  1.52it/s]
1|16331|Loss: 0.8383849263191223:  63%|██████▎   | 16331/25880 [3:20:39<1:47:34,  1.48it/s]
1|16332|Loss: 0.7309868335723877:  63%|██████▎   | 16331/25880 [3:20:39<1:47:34,  1.48it/s]
1|16332|Loss: 0.7309868335723877:  63%|██████▎   | 16332/25880 [3:20:40<1:46:14,  1.50it/s]
1|16333|Loss: 0.8618749380111694:  63%|██████▎   | 16332/25880 [3:20:40<1:46:14,  1.50it/s]
1|16333|Loss: 0.8618749380111694:  63%|██████▎   | 16333/25880 [3:20:40<1:46:52,  1.49it/s]
1|16334|Loss: 0.9114099144935608:  63%|██████▎   | 16333/25880 [3:20:41<1:46:52,  1.49it/s]
1|16334|Loss: 0.9114099144935608:  63%|██████▎   | 16334/25880 [3:20:41<1:44:10,  1.53it/s]
1|16335|Loss: 0.765675961971283:  63%|██████▎   | 16334/25880 [3:20:41<1:44:10,  1.53it/s] 
1|16335|Loss: 0.765675961971283:  63%|██████▎   | 16335/25880 [3:20:42<1:53:39,  1.40it/s]
1|16336|Loss: 0.741536557674408:  63%|██████▎   | 16335/25880 [3:20:42<1:53:39,  1.40it/s]
1|16336|Loss: 0.741536557674408:  63%|██████▎   | 16336/25880 [3:20:43<1:51:50,  1.42it/s]
1|16337|Loss: 0.9832959175109863:  63%|██████▎   | 16336/25880 [3:20:43<1:51:50,  1.42it/s]
1|16337|Loss: 0.9832959175109863:  63%|██████▎   | 16337/25880 [3:20:43<1:47:38,  1.48it/s]
1|16338|Loss: 0.812229335308075:  63%|██████▎   | 16337/25880 [3:20:44<1:47:38,  1.48it/s] 
1|16338|Loss: 0.812229335308075:  63%|██████▎   | 16338/25880 [3:20:44<1:49:33,  1.45it/s]
1|16339|Loss: 0.8782685399055481:  63%|██████▎   | 16338/25880 [3:20:44<1:49:33,  1.45it/s]
1|16339|Loss: 0.8782685399055481:  63%|██████▎   | 16339/25880 [3:20:45<1:47:19,  1.48it/s]
1|16340|Loss: 0.6922609806060791:  63%|██████▎   | 16339/25880 [3:20:45<1:47:19,  1.48it/s]
1|16340|Loss: 0.6922609806060791:  63%|██████▎   | 16340/25880 [3:20:45<1:59:41,  1.33it/s]
1|16341|Loss: 0.7348181009292603:  63%|██████▎   | 16340/25880 [3:20:46<1:59:41,  1.33it/s]
1|16341|Loss: 0.7348181009292603:  63%|██████▎   | 16341/25880 [3:20:47<2:16:48,  1.16it/s]
1|16342|Loss: 0.9645802974700928:  63%|██████▎   | 16341/25880 [3:20:47<2:16:48,  1.16it/s]
1|16342|Loss: 0.9645802974700928:  63%|██████▎   | 16342/25880 [3:20:47<2:13:31,  1.19it/s]
1|16343|Loss: 0.7842415571212769:  63%|██████▎   | 16342/25880 [3:20:48<2:13:31,  1.19it/s]
1|16343|Loss: 0.7842415571212769:  63%|██████▎   | 16343/25880 [3:20:48<1:59:43,  1.33it/s]
1|16344|Loss: 0.9009976387023926:  63%|██████▎   | 16343/25880 [3:20:48<1:59:43,  1.33it/s]
1|16344|Loss: 0.9009976387023926:  63%|██████▎   | 16344/25880 [3:20:48<1:48:11,  1.47it/s]
1|16345|Loss: 0.8144045472145081:  63%|██████▎   | 16344/25880 [3:20:49<1:48:11,  1.47it/s]
1|16345|Loss: 0.8144045472145081:  63%|██████▎   | 16345/25880 [3:20:49<1:44:04,  1.53it/s]
1|16346|Loss: 0.8319244384765625:  63%|██████▎   | 16345/25880 [3:20:49<1:44:04,  1.53it/s]
1|16346|Loss: 0.8319244384765625:  63%|██████▎   | 16346/25880 [3:20:50<1:46:34,  1.49it/s]
1|16347|Loss: 0.7872453331947327:  63%|██████▎   | 16346/25880 [3:20:50<1:46:34,  1.49it/s]
1|16347|Loss: 0.7872453331947327:  63%|██████▎   | 16347/25880 [3:20:51<1:54:30,  1.39it/s]
1|16348|Loss: 0.7792145013809204:  63%|██████▎   | 16347/25880 [3:20:51<1:54:30,  1.39it/s]
1|16348|Loss: 0.7792145013809204:  63%|██████▎   | 16348/25880 [3:20:51<1:50:55,  1.43it/s]
1|16349|Loss: 0.8367553353309631:  63%|██████▎   | 16348/25880 [3:20:52<1:50:55,  1.43it/s]
1|16349|Loss: 0.8367553353309631:  63%|██████▎   | 16349/25880 [3:20:52<1:54:03,  1.39it/s]
1|16350|Loss: 0.8283316493034363:  63%|██████▎   | 16349/25880 [3:20:52<1:54:03,  1.39it/s]
1|16350|Loss: 0.8283316493034363:  63%|██████▎   | 16350/25880 [3:20:53<2:02:20,  1.30it/s]
1|16351|Loss: 0.8279138803482056:  63%|██████▎   | 16350/25880 [3:20:53<2:02:20,  1.30it/s]
1|16351|Loss: 0.8279138803482056:  63%|██████▎   | 16351/25880 [3:20:53<1:53:56,  1.39it/s]
1|16352|Loss: 0.8277565240859985:  63%|██████▎   | 16351/25880 [3:20:54<1:53:56,  1.39it/s]
1|16352|Loss: 0.8277565240859985:  63%|██████▎   | 16352/25880 [3:20:54<1:51:22,  1.43it/s]
1|16353|Loss: 0.9754028916358948:  63%|██████▎   | 16352/25880 [3:20:55<1:51:22,  1.43it/s]
1|16353|Loss: 0.9754028916358948:  63%|██████▎   | 16353/25880 [3:20:55<1:51:28,  1.42it/s]
1|16354|Loss: 0.8317290544509888:  63%|██████▎   | 16353/25880 [3:20:55<1:51:28,  1.42it/s]
1|16354|Loss: 0.8317290544509888:  63%|██████▎   | 16354/25880 [3:20:55<1:48:55,  1.46it/s]
1|16355|Loss: 0.8432757258415222:  63%|██████▎   | 16354/25880 [3:20:56<1:48:55,  1.46it/s]
1|16355|Loss: 0.8432757258415222:  63%|██████▎   | 16355/25880 [3:20:56<1:43:31,  1.53it/s]
1|16356|Loss: 0.9314541220664978:  63%|██████▎   | 16355/25880 [3:20:56<1:43:31,  1.53it/s]
1|16356|Loss: 0.9314541220664978:  63%|██████▎   | 16356/25880 [3:20:57<1:45:28,  1.51it/s]
1|16357|Loss: 0.7257168292999268:  63%|██████▎   | 16356/25880 [3:20:57<1:45:28,  1.51it/s]
1|16357|Loss: 0.7257168292999268:  63%|██████▎   | 16357/25880 [3:20:57<1:38:02,  1.62it/s]
1|16358|Loss: 0.7944188117980957:  63%|██████▎   | 16357/25880 [3:20:58<1:38:02,  1.62it/s]
1|16358|Loss: 0.7944188117980957:  63%|██████▎   | 16358/25880 [3:20:58<1:40:55,  1.57it/s]
1|16359|Loss: 0.8042622804641724:  63%|██████▎   | 16358/25880 [3:20:58<1:40:55,  1.57it/s]
1|16359|Loss: 0.8042622804641724:  63%|██████▎   | 16359/25880 [3:20:59<1:53:17,  1.40it/s]
1|16360|Loss: 0.9710975289344788:  63%|██████▎   | 16359/25880 [3:20:59<1:53:17,  1.40it/s]
1|16360|Loss: 0.9710975289344788:  63%|██████▎   | 16360/25880 [3:21:00<1:51:20,  1.43it/s]
1|16361|Loss: 0.8156363368034363:  63%|██████▎   | 16360/25880 [3:21:00<1:51:20,  1.43it/s]
1|16361|Loss: 0.8156363368034363:  63%|██████▎   | 16361/25880 [3:21:00<1:51:28,  1.42it/s]
1|16362|Loss: 1.08036470413208:  63%|██████▎   | 16361/25880 [3:21:01<1:51:28,  1.42it/s]  
1|16362|Loss: 1.08036470413208:  63%|██████▎   | 16362/25880 [3:21:01<1:49:15,  1.45it/s]
1|16363|Loss: 0.7632125616073608:  63%|██████▎   | 16362/25880 [3:21:01<1:49:15,  1.45it/s]
1|16363|Loss: 0.7632125616073608:  63%|██████▎   | 16363/25880 [3:21:01<1:45:56,  1.50it/s]
1|16364|Loss: 0.8898922801017761:  63%|██████▎   | 16363/25880 [3:21:02<1:45:56,  1.50it/s]
1|16364|Loss: 0.8898922801017761:  63%|██████▎   | 16364/25880 [3:21:02<1:51:24,  1.42it/s]
1|16365|Loss: 0.7951198816299438:  63%|██████▎   | 16364/25880 [3:21:03<1:51:24,  1.42it/s]
1|16365|Loss: 0.7951198816299438:  63%|██████▎   | 16365/25880 [3:21:03<1:52:48,  1.41it/s]
1|16366|Loss: 0.8819717168807983:  63%|██████▎   | 16365/25880 [3:21:03<1:52:48,  1.41it/s]
1|16366|Loss: 0.8819717168807983:  63%|██████▎   | 16366/25880 [3:21:04<1:42:30,  1.55it/s]
1|16367|Loss: 0.6926326155662537:  63%|██████▎   | 16366/25880 [3:21:04<1:42:30,  1.55it/s]
1|16367|Loss: 0.6926326155662537:  63%|██████▎   | 16367/25880 [3:21:04<1:43:58,  1.52it/s]
1|16368|Loss: 0.7855309844017029:  63%|██████▎   | 16367/25880 [3:21:05<1:43:58,  1.52it/s]
1|16368|Loss: 0.7855309844017029:  63%|██████▎   | 16368/25880 [3:21:05<1:44:11,  1.52it/s]
1|16369|Loss: 1.012402892112732:  63%|██████▎   | 16368/25880 [3:21:05<1:44:11,  1.52it/s] 
1|16369|Loss: 1.012402892112732:  63%|██████▎   | 16369/25880 [3:21:06<1:50:09,  1.44it/s]
1|16370|Loss: 0.9560145139694214:  63%|██████▎   | 16369/25880 [3:21:06<1:50:09,  1.44it/s]
1|16370|Loss: 0.9560145139694214:  63%|██████▎   | 16370/25880 [3:21:07<2:01:21,  1.31it/s]
1|16371|Loss: 0.8998140096664429:  63%|██████▎   | 16370/25880 [3:21:07<2:01:21,  1.31it/s]
1|16371|Loss: 0.8998140096664429:  63%|██████▎   | 16371/25880 [3:21:07<2:00:45,  1.31it/s]
1|16372|Loss: 0.8980045914649963:  63%|██████▎   | 16371/25880 [3:21:08<2:00:45,  1.31it/s]
1|16372|Loss: 0.8980045914649963:  63%|██████▎   | 16372/25880 [3:21:08<1:54:29,  1.38it/s]
1|16373|Loss: 0.846528172492981:  63%|██████▎   | 16372/25880 [3:21:08<1:54:29,  1.38it/s] 
1|16373|Loss: 0.846528172492981:  63%|██████▎   | 16373/25880 [3:21:09<1:53:37,  1.39it/s]
1|16374|Loss: 0.7512137293815613:  63%|██████▎   | 16373/25880 [3:21:09<1:53:37,  1.39it/s]
1|16374|Loss: 0.7512137293815613:  63%|██████▎   | 16374/25880 [3:21:09<1:59:43,  1.32it/s]
1|16375|Loss: 0.8805119395256042:  63%|██████▎   | 16374/25880 [3:21:10<1:59:43,  1.32it/s]
1|16375|Loss: 0.8805119395256042:  63%|██████▎   | 16375/25880 [3:21:10<2:00:20,  1.32it/s]
1|16376|Loss: 0.8381780982017517:  63%|██████▎   | 16375/25880 [3:21:11<2:00:20,  1.32it/s]
1|16376|Loss: 0.8381780982017517:  63%|██████▎   | 16376/25880 [3:21:11<1:54:31,  1.38it/s]
1|16377|Loss: 0.8225599527359009:  63%|██████▎   | 16376/25880 [3:21:11<1:54:31,  1.38it/s]
1|16377|Loss: 0.8225599527359009:  63%|██████▎   | 16377/25880 [3:21:11<1:45:25,  1.50it/s]
1|16378|Loss: 0.7633939385414124:  63%|██████▎   | 16377/25880 [3:21:12<1:45:25,  1.50it/s]
1|16378|Loss: 0.7633939385414124:  63%|██████▎   | 16378/25880 [3:21:12<1:55:05,  1.38it/s]
1|16379|Loss: 0.7361664772033691:  63%|██████▎   | 16378/25880 [3:21:13<1:55:05,  1.38it/s]
1|16379|Loss: 0.7361664772033691:  63%|██████▎   | 16379/25880 [3:21:13<1:50:48,  1.43it/s]
1|16380|Loss: 0.8170579671859741:  63%|██████▎   | 16379/25880 [3:21:13<1:50:48,  1.43it/s]
1|16380|Loss: 0.8170579671859741:  63%|██████▎   | 16380/25880 [3:21:14<1:50:45,  1.43it/s]
1|16381|Loss: 0.9549258351325989:  63%|██████▎   | 16380/25880 [3:21:14<1:50:45,  1.43it/s]
1|16381|Loss: 0.9549258351325989:  63%|██████▎   | 16381/25880 [3:21:14<1:46:22,  1.49it/s]
1|16382|Loss: 0.7726457118988037:  63%|██████▎   | 16381/25880 [3:21:15<1:46:22,  1.49it/s]
1|16382|Loss: 0.7726457118988037:  63%|██████▎   | 16382/25880 [3:21:15<1:46:46,  1.48it/s]
1|16383|Loss: 0.8657833337783813:  63%|██████▎   | 16382/25880 [3:21:15<1:46:46,  1.48it/s]
1|16383|Loss: 0.8657833337783813:  63%|██████▎   | 16383/25880 [3:21:15<1:40:46,  1.57it/s]
1|16384|Loss: 0.7230217456817627:  63%|██████▎   | 16383/25880 [3:21:16<1:40:46,  1.57it/s]
1|16384|Loss: 0.7230217456817627:  63%|██████▎   | 16384/25880 [3:21:16<1:48:49,  1.45it/s]
1|16385|Loss: 0.8236888647079468:  63%|██████▎   | 16384/25880 [3:21:17<1:48:49,  1.45it/s]
1|16385|Loss: 0.8236888647079468:  63%|██████▎   | 16385/25880 [3:21:17<1:51:56,  1.41it/s]
1|16386|Loss: 0.7849498391151428:  63%|██████▎   | 16385/25880 [3:21:17<1:51:56,  1.41it/s]
1|16386|Loss: 0.7849498391151428:  63%|██████▎   | 16386/25880 [3:21:18<1:53:23,  1.40it/s]
1|16387|Loss: 0.7853109836578369:  63%|██████▎   | 16386/25880 [3:21:18<1:53:23,  1.40it/s]
1|16387|Loss: 0.7853109836578369:  63%|██████▎   | 16387/25880 [3:21:19<1:57:14,  1.35it/s]
1|16388|Loss: 0.779464602470398:  63%|██████▎   | 16387/25880 [3:21:19<1:57:14,  1.35it/s] 
1|16388|Loss: 0.779464602470398:  63%|██████▎   | 16388/25880 [3:21:19<1:56:14,  1.36it/s]
1|16389|Loss: 0.7209003567695618:  63%|██████▎   | 16388/25880 [3:21:20<1:56:14,  1.36it/s]
1|16389|Loss: 0.7209003567695618:  63%|██████▎   | 16389/25880 [3:21:20<1:58:05,  1.34it/s]
1|16390|Loss: 0.8228777647018433:  63%|██████▎   | 16389/25880 [3:21:20<1:58:05,  1.34it/s]
1|16390|Loss: 0.8228777647018433:  63%|██████▎   | 16390/25880 [3:21:21<1:54:42,  1.38it/s]
1|16391|Loss: 0.8736838698387146:  63%|██████▎   | 16390/25880 [3:21:21<1:54:42,  1.38it/s]
1|16391|Loss: 0.8736838698387146:  63%|██████▎   | 16391/25880 [3:21:22<1:57:03,  1.35it/s]
1|16392|Loss: 0.9137728810310364:  63%|██████▎   | 16391/25880 [3:21:22<1:57:03,  1.35it/s]
1|16392|Loss: 0.9137728810310364:  63%|██████▎   | 16392/25880 [3:21:22<1:55:50,  1.37it/s]
1|16393|Loss: 0.7787145972251892:  63%|██████▎   | 16392/25880 [3:21:23<1:55:50,  1.37it/s]
1|16393|Loss: 0.7787145972251892:  63%|██████▎   | 16393/25880 [3:21:23<1:55:32,  1.37it/s]
1|16394|Loss: 0.8383129835128784:  63%|██████▎   | 16393/25880 [3:21:23<1:55:32,  1.37it/s]
1|16394|Loss: 0.8383129835128784:  63%|██████▎   | 16394/25880 [3:21:24<1:51:19,  1.42it/s]
1|16395|Loss: 0.8765152096748352:  63%|██████▎   | 16394/25880 [3:21:24<1:51:19,  1.42it/s]
1|16395|Loss: 0.8765152096748352:  63%|██████▎   | 16395/25880 [3:21:24<1:51:23,  1.42it/s]
1|16396|Loss: 0.852177083492279:  63%|██████▎   | 16395/25880 [3:21:25<1:51:23,  1.42it/s] 
1|16396|Loss: 0.852177083492279:  63%|██████▎   | 16396/25880 [3:21:25<1:56:58,  1.35it/s]
1|16397|Loss: 0.8584510684013367:  63%|██████▎   | 16396/25880 [3:21:26<1:56:58,  1.35it/s]
1|16397|Loss: 0.8584510684013367:  63%|██████▎   | 16397/25880 [3:21:26<1:58:09,  1.34it/s]
1|16398|Loss: 0.8333128690719604:  63%|██████▎   | 16397/25880 [3:21:26<1:58:09,  1.34it/s]
1|16398|Loss: 0.8333128690719604:  63%|██████▎   | 16398/25880 [3:21:27<2:01:11,  1.30it/s]
1|16399|Loss: 0.7636386156082153:  63%|██████▎   | 16398/25880 [3:21:27<2:01:11,  1.30it/s]
1|16399|Loss: 0.7636386156082153:  63%|██████▎   | 16399/25880 [3:21:27<2:00:26,  1.31it/s]
1|16400|Loss: 0.8414717316627502:  63%|██████▎   | 16399/25880 [3:21:28<2:00:26,  1.31it/s]
1|16400|Loss: 0.8414717316627502:  63%|██████▎   | 16400/25880 [3:21:28<1:53:46,  1.39it/s]
1|16401|Loss: 0.9343488812446594:  63%|██████▎   | 16400/25880 [3:21:28<1:53:46,  1.39it/s]
1|16401|Loss: 0.9343488812446594:  63%|██████▎   | 16401/25880 [3:21:29<1:53:13,  1.40it/s]
1|16402|Loss: 0.8854547142982483:  63%|██████▎   | 16401/25880 [3:21:29<1:53:13,  1.40it/s]
1|16402|Loss: 0.8854547142982483:  63%|██████▎   | 16402/25880 [3:21:30<2:01:20,  1.30it/s]
1|16403|Loss: 0.8430845141410828:  63%|██████▎   | 16402/25880 [3:21:30<2:01:20,  1.30it/s]
1|16403|Loss: 0.8430845141410828:  63%|██████▎   | 16403/25880 [3:21:30<1:56:51,  1.35it/s]
1|16404|Loss: 0.7207349538803101:  63%|██████▎   | 16403/25880 [3:21:31<1:56:51,  1.35it/s]
1|16404|Loss: 0.7207349538803101:  63%|██████▎   | 16404/25880 [3:21:31<1:55:27,  1.37it/s]
1|16405|Loss: 0.876765787601471:  63%|██████▎   | 16404/25880 [3:21:31<1:55:27,  1.37it/s] 
1|16405|Loss: 0.876765787601471:  63%|██████▎   | 16405/25880 [3:21:32<1:51:01,  1.42it/s]
1|16406|Loss: 0.9558110237121582:  63%|██████▎   | 16405/25880 [3:21:32<1:51:01,  1.42it/s]
1|16406|Loss: 0.9558110237121582:  63%|██████▎   | 16406/25880 [3:21:32<1:55:01,  1.37it/s]
1|16407|Loss: 0.8609362244606018:  63%|██████▎   | 16406/25880 [3:21:33<1:55:01,  1.37it/s]
1|16407|Loss: 0.8609362244606018:  63%|██████▎   | 16407/25880 [3:21:33<2:00:12,  1.31it/s]
1|16408|Loss: 0.8666071891784668:  63%|██████▎   | 16407/25880 [3:21:34<2:00:12,  1.31it/s]
1|16408|Loss: 0.8666071891784668:  63%|██████▎   | 16408/25880 [3:21:34<1:56:48,  1.35it/s]
1|16409|Loss: 0.8766888380050659:  63%|██████▎   | 16408/25880 [3:21:34<1:56:48,  1.35it/s]
1|16409|Loss: 0.8766888380050659:  63%|██████▎   | 16409/25880 [3:21:35<1:50:24,  1.43it/s]
1|16410|Loss: 0.9491928219795227:  63%|██████▎   | 16409/25880 [3:21:35<1:50:24,  1.43it/s]
1|16410|Loss: 0.9491928219795227:  63%|██████▎   | 16410/25880 [3:21:35<1:53:11,  1.39it/s]
1|16411|Loss: 0.7998341917991638:  63%|██████▎   | 16410/25880 [3:21:36<1:53:11,  1.39it/s]
1|16411|Loss: 0.7998341917991638:  63%|██████▎   | 16411/25880 [3:21:36<1:50:06,  1.43it/s]
1|16412|Loss: 0.7556155920028687:  63%|██████▎   | 16411/25880 [3:21:36<1:50:06,  1.43it/s]
1|16412|Loss: 0.7556155920028687:  63%|██████▎   | 16412/25880 [3:21:37<1:39:52,  1.58it/s]
1|16413|Loss: 1.012561321258545:  63%|██████▎   | 16412/25880 [3:21:37<1:39:52,  1.58it/s] 
1|16413|Loss: 1.012561321258545:  63%|██████▎   | 16413/25880 [3:21:37<1:42:22,  1.54it/s]
1|16414|Loss: 0.8643459677696228:  63%|██████▎   | 16413/25880 [3:21:38<1:42:22,  1.54it/s]
1|16414|Loss: 0.8643459677696228:  63%|██████▎   | 16414/25880 [3:21:38<1:45:24,  1.50it/s]
1|16415|Loss: 0.8828770518302917:  63%|██████▎   | 16414/25880 [3:21:38<1:45:24,  1.50it/s]
1|16415|Loss: 0.8828770518302917:  63%|██████▎   | 16415/25880 [3:21:39<1:50:02,  1.43it/s]
1|16416|Loss: 0.7381162643432617:  63%|██████▎   | 16415/25880 [3:21:39<1:50:02,  1.43it/s]
1|16416|Loss: 0.7381162643432617:  63%|██████▎   | 16416/25880 [3:21:39<1:47:49,  1.46it/s]
1|16417|Loss: 0.7580194473266602:  63%|██████▎   | 16416/25880 [3:21:40<1:47:49,  1.46it/s]
1|16417|Loss: 0.7580194473266602:  63%|██████▎   | 16417/25880 [3:21:40<1:47:42,  1.46it/s]
1|16418|Loss: 0.8823574185371399:  63%|██████▎   | 16417/25880 [3:21:40<1:47:42,  1.46it/s]
1|16418|Loss: 0.8823574185371399:  63%|██████▎   | 16418/25880 [3:21:41<1:51:47,  1.41it/s]
1|16419|Loss: 0.7606179118156433:  63%|██████▎   | 16418/25880 [3:21:41<1:51:47,  1.41it/s]
1|16419|Loss: 0.7606179118156433:  63%|██████▎   | 16419/25880 [3:21:41<1:48:01,  1.46it/s]
1|16420|Loss: 0.8592437505722046:  63%|██████▎   | 16419/25880 [3:21:42<1:48:01,  1.46it/s]
1|16420|Loss: 0.8592437505722046:  63%|██████▎   | 16420/25880 [3:21:42<1:55:36,  1.36it/s]
1|16421|Loss: 0.8082509636878967:  63%|██████▎   | 16420/25880 [3:21:43<1:55:36,  1.36it/s]
1|16421|Loss: 0.8082509636878967:  63%|██████▎   | 16421/25880 [3:21:43<1:59:48,  1.32it/s]
1|16422|Loss: 0.8873916864395142:  63%|██████▎   | 16421/25880 [3:21:43<1:59:48,  1.32it/s]
1|16422|Loss: 0.8873916864395142:  63%|██████▎   | 16422/25880 [3:21:44<1:55:49,  1.36it/s]
1|16423|Loss: 0.7064977884292603:  63%|██████▎   | 16422/25880 [3:21:44<1:55:49,  1.36it/s]
1|16423|Loss: 0.7064977884292603:  63%|██████▎   | 16423/25880 [3:21:44<1:55:30,  1.36it/s]
1|16424|Loss: 0.8229079842567444:  63%|██████▎   | 16423/25880 [3:21:45<1:55:30,  1.36it/s]
1|16424|Loss: 0.8229079842567444:  63%|██████▎   | 16424/25880 [3:21:45<1:51:12,  1.42it/s]
1|16425|Loss: 0.9862731099128723:  63%|██████▎   | 16424/25880 [3:21:46<1:51:12,  1.42it/s]
1|16425|Loss: 0.9862731099128723:  63%|██████▎   | 16425/25880 [3:21:46<1:53:24,  1.39it/s]
1|16426|Loss: 0.747507631778717:  63%|██████▎   | 16425/25880 [3:21:46<1:53:24,  1.39it/s] 
1|16426|Loss: 0.747507631778717:  63%|██████▎   | 16426/25880 [3:21:47<1:51:23,  1.41it/s]
1|16427|Loss: 0.5873990058898926:  63%|██████▎   | 16426/25880 [3:21:47<1:51:23,  1.41it/s]
1|16427|Loss: 0.5873990058898926:  63%|██████▎   | 16427/25880 [3:21:47<1:48:18,  1.45it/s]
1|16428|Loss: 0.8249388933181763:  63%|██████▎   | 16427/25880 [3:21:48<1:48:18,  1.45it/s]
1|16428|Loss: 0.8249388933181763:  63%|██████▎   | 16428/25880 [3:21:48<1:41:51,  1.55it/s]
1|16429|Loss: 0.818013608455658:  63%|██████▎   | 16428/25880 [3:21:48<1:41:51,  1.55it/s] 
1|16429|Loss: 0.818013608455658:  63%|██████▎   | 16429/25880 [3:21:48<1:42:52,  1.53it/s]
1|16430|Loss: 0.7666295170783997:  63%|██████▎   | 16429/25880 [3:21:49<1:42:52,  1.53it/s]
1|16430|Loss: 0.7666295170783997:  63%|██████▎   | 16430/25880 [3:21:49<1:45:11,  1.50it/s]
1|16431|Loss: 0.7592145800590515:  63%|██████▎   | 16430/25880 [3:21:49<1:45:11,  1.50it/s]
1|16431|Loss: 0.7592145800590515:  63%|██████▎   | 16431/25880 [3:21:50<1:41:58,  1.54it/s]
1|16432|Loss: 1.026648998260498:  63%|██████▎   | 16431/25880 [3:21:50<1:41:58,  1.54it/s] 
1|16432|Loss: 1.026648998260498:  63%|██████▎   | 16432/25880 [3:21:50<1:43:05,  1.53it/s]
1|16433|Loss: 0.7377960681915283:  63%|██████▎   | 16432/25880 [3:21:51<1:43:05,  1.53it/s]
1|16433|Loss: 0.7377960681915283:  63%|██████▎   | 16433/25880 [3:21:51<1:48:37,  1.45it/s]
1|16434|Loss: 0.886768639087677:  63%|██████▎   | 16433/25880 [3:21:52<1:48:37,  1.45it/s] 
1|16434|Loss: 0.886768639087677:  64%|██████▎   | 16434/25880 [3:21:52<1:51:08,  1.42it/s]
1|16435|Loss: 0.6386778354644775:  64%|██████▎   | 16434/25880 [3:21:52<1:51:08,  1.42it/s]
1|16435|Loss: 0.6386778354644775:  64%|██████▎   | 16435/25880 [3:21:53<1:55:52,  1.36it/s]
1|16436|Loss: 0.870662271976471:  64%|██████▎   | 16435/25880 [3:21:53<1:55:52,  1.36it/s] 
1|16436|Loss: 0.870662271976471:  64%|██████▎   | 16436/25880 [3:21:54<1:59:16,  1.32it/s]
1|16437|Loss: 0.8890334367752075:  64%|██████▎   | 16436/25880 [3:21:54<1:59:16,  1.32it/s]
1|16437|Loss: 0.8890334367752075:  64%|██████▎   | 16437/25880 [3:21:54<1:55:03,  1.37it/s]
1|16438|Loss: 0.7225408554077148:  64%|██████▎   | 16437/25880 [3:21:55<1:55:03,  1.37it/s]
1|16438|Loss: 0.7225408554077148:  64%|██████▎   | 16438/25880 [3:21:55<1:54:14,  1.38it/s]
1|16439|Loss: 0.9553676843643188:  64%|██████▎   | 16438/25880 [3:21:55<1:54:14,  1.38it/s]
1|16439|Loss: 0.9553676843643188:  64%|██████▎   | 16439/25880 [3:21:56<1:54:25,  1.38it/s]
1|16440|Loss: 0.8828354477882385:  64%|██████▎   | 16439/25880 [3:21:56<1:54:25,  1.38it/s]
1|16440|Loss: 0.8828354477882385:  64%|██████▎   | 16440/25880 [3:21:56<2:00:09,  1.31it/s]
1|16441|Loss: 0.7591456174850464:  64%|██████▎   | 16440/25880 [3:21:57<2:00:09,  1.31it/s]
1|16441|Loss: 0.7591456174850464:  64%|██████▎   | 16441/25880 [3:21:57<2:02:14,  1.29it/s]
1|16442|Loss: 0.7815284132957458:  64%|██████▎   | 16441/25880 [3:21:58<2:02:14,  1.29it/s]
1|16442|Loss: 0.7815284132957458:  64%|██████▎   | 16442/25880 [3:21:58<1:59:29,  1.32it/s]
1|16443|Loss: 0.870061457157135:  64%|██████▎   | 16442/25880 [3:21:58<1:59:29,  1.32it/s] 
1|16443|Loss: 0.870061457157135:  64%|██████▎   | 16443/25880 [3:21:59<1:57:56,  1.33it/s]
1|16444|Loss: 0.961074948310852:  64%|██████▎   | 16443/25880 [3:21:59<1:57:56,  1.33it/s]
1|16444|Loss: 0.961074948310852:  64%|██████▎   | 16444/25880 [3:21:59<1:57:08,  1.34it/s]
1|16445|Loss: 0.6816494464874268:  64%|██████▎   | 16444/25880 [3:22:00<1:57:08,  1.34it/s]
1|16445|Loss: 0.6816494464874268:  64%|██████▎   | 16445/25880 [3:22:00<1:56:03,  1.35it/s]
1|16446|Loss: 0.8244456648826599:  64%|██████▎   | 16445/25880 [3:22:01<1:56:03,  1.35it/s]
1|16446|Loss: 0.8244456648826599:  64%|██████▎   | 16446/25880 [3:22:01<1:48:06,  1.45it/s]
1|16447|Loss: 0.7621210217475891:  64%|██████▎   | 16446/25880 [3:22:01<1:48:06,  1.45it/s]
1|16447|Loss: 0.7621210217475891:  64%|██████▎   | 16447/25880 [3:22:01<1:48:46,  1.45it/s]
1|16448|Loss: 0.8204808831214905:  64%|██████▎   | 16447/25880 [3:22:02<1:48:46,  1.45it/s]
1|16448|Loss: 0.8204808831214905:  64%|██████▎   | 16448/25880 [3:22:02<1:50:13,  1.43it/s]
1|16449|Loss: 0.8200131058692932:  64%|██████▎   | 16448/25880 [3:22:03<1:50:13,  1.43it/s]
1|16449|Loss: 0.8200131058692932:  64%|██████▎   | 16449/25880 [3:22:03<1:50:38,  1.42it/s]
1|16450|Loss: 0.7716572284698486:  64%|██████▎   | 16449/25880 [3:22:03<1:50:38,  1.42it/s]
1|16450|Loss: 0.7716572284698486:  64%|██████▎   | 16450/25880 [3:22:04<1:53:53,  1.38it/s]
1|16451|Loss: 0.7112748026847839:  64%|██████▎   | 16450/25880 [3:22:04<1:53:53,  1.38it/s]
1|16451|Loss: 0.7112748026847839:  64%|██████▎   | 16451/25880 [3:22:05<2:04:27,  1.26it/s]
1|16452|Loss: 0.8193003535270691:  64%|██████▎   | 16451/25880 [3:22:05<2:04:27,  1.26it/s]
1|16452|Loss: 0.8193003535270691:  64%|██████▎   | 16452/25880 [3:22:05<1:58:35,  1.32it/s]
1|16453|Loss: 0.9727047681808472:  64%|██████▎   | 16452/25880 [3:22:06<1:58:35,  1.32it/s]
1|16453|Loss: 0.9727047681808472:  64%|██████▎   | 16453/25880 [3:22:06<1:55:23,  1.36it/s]
1|16454|Loss: 0.8840504884719849:  64%|██████▎   | 16453/25880 [3:22:06<1:55:23,  1.36it/s]
1|16454|Loss: 0.8840504884719849:  64%|██████▎   | 16454/25880 [3:22:07<1:57:13,  1.34it/s]
1|16455|Loss: 0.7216029167175293:  64%|██████▎   | 16454/25880 [3:22:07<1:57:13,  1.34it/s]
1|16455|Loss: 0.7216029167175293:  64%|██████▎   | 16455/25880 [3:22:07<1:57:36,  1.34it/s]
1|16456|Loss: 0.8472212553024292:  64%|██████▎   | 16455/25880 [3:22:08<1:57:36,  1.34it/s]
1|16456|Loss: 0.8472212553024292:  64%|██████▎   | 16456/25880 [3:22:08<2:00:42,  1.30it/s]
1|16457|Loss: 0.8478235006332397:  64%|██████▎   | 16456/25880 [3:22:09<2:00:42,  1.30it/s]
1|16457|Loss: 0.8478235006332397:  64%|██████▎   | 16457/25880 [3:22:09<1:56:22,  1.35it/s]
1|16458|Loss: 0.8188149929046631:  64%|██████▎   | 16457/25880 [3:22:09<1:56:22,  1.35it/s]
1|16458|Loss: 0.8188149929046631:  64%|██████▎   | 16458/25880 [3:22:10<1:57:55,  1.33it/s]
1|16459|Loss: 0.7209010124206543:  64%|██████▎   | 16458/25880 [3:22:10<1:57:55,  1.33it/s]
1|16459|Loss: 0.7209010124206543:  64%|██████▎   | 16459/25880 [3:22:11<1:57:29,  1.34it/s]
1|16460|Loss: 0.7624791860580444:  64%|██████▎   | 16459/25880 [3:22:11<1:57:29,  1.34it/s]
1|16460|Loss: 0.7624791860580444:  64%|██████▎   | 16460/25880 [3:22:11<2:03:27,  1.27it/s]
1|16461|Loss: 0.8635366559028625:  64%|██████▎   | 16460/25880 [3:22:12<2:03:27,  1.27it/s]
1|16461|Loss: 0.8635366559028625:  64%|██████▎   | 16461/25880 [3:22:12<2:02:22,  1.28it/s]
1|16462|Loss: 0.8233409523963928:  64%|██████▎   | 16461/25880 [3:22:13<2:02:22,  1.28it/s]
1|16462|Loss: 0.8233409523963928:  64%|██████▎   | 16462/25880 [3:22:13<1:59:46,  1.31it/s]
1|16463|Loss: 0.9575554132461548:  64%|██████▎   | 16462/25880 [3:22:13<1:59:46,  1.31it/s]
1|16463|Loss: 0.9575554132461548:  64%|██████▎   | 16463/25880 [3:22:14<2:06:58,  1.24it/s]
1|16464|Loss: 0.8194138407707214:  64%|██████▎   | 16463/25880 [3:22:14<2:06:58,  1.24it/s]
1|16464|Loss: 0.8194138407707214:  64%|██████▎   | 16464/25880 [3:22:15<2:07:44,  1.23it/s]
1|16465|Loss: 0.8152825832366943:  64%|██████▎   | 16464/25880 [3:22:15<2:07:44,  1.23it/s]
1|16465|Loss: 0.8152825832366943:  64%|██████▎   | 16465/25880 [3:22:15<2:06:36,  1.24it/s]
1|16466|Loss: 0.8424474000930786:  64%|██████▎   | 16465/25880 [3:22:16<2:06:36,  1.24it/s]
1|16466|Loss: 0.8424474000930786:  64%|██████▎   | 16466/25880 [3:22:16<2:00:18,  1.30it/s]
1|16467|Loss: 0.8488361239433289:  64%|██████▎   | 16466/25880 [3:22:16<2:00:18,  1.30it/s]
1|16467|Loss: 0.8488361239433289:  64%|██████▎   | 16467/25880 [3:22:17<1:53:28,  1.38it/s]
1|16468|Loss: 0.94322669506073:  64%|██████▎   | 16467/25880 [3:22:17<1:53:28,  1.38it/s]  
1|16468|Loss: 0.94322669506073:  64%|██████▎   | 16468/25880 [3:22:18<1:57:21,  1.34it/s]
1|16469|Loss: 0.8264840841293335:  64%|██████▎   | 16468/25880 [3:22:18<1:57:21,  1.34it/s]
1|16469|Loss: 0.8264840841293335:  64%|██████▎   | 16469/25880 [3:22:18<2:03:25,  1.27it/s]
1|16470|Loss: 0.7951585650444031:  64%|██████▎   | 16469/25880 [3:22:19<2:03:25,  1.27it/s]
1|16470|Loss: 0.7951585650444031:  64%|██████▎   | 16470/25880 [3:22:19<1:56:38,  1.34it/s]
1|16471|Loss: 0.7436498403549194:  64%|██████▎   | 16470/25880 [3:22:19<1:56:38,  1.34it/s]
1|16471|Loss: 0.7436498403549194:  64%|██████▎   | 16471/25880 [3:22:20<1:55:03,  1.36it/s]
1|16472|Loss: 0.9455061554908752:  64%|██████▎   | 16471/25880 [3:22:20<1:55:03,  1.36it/s]
1|16472|Loss: 0.9455061554908752:  64%|██████▎   | 16472/25880 [3:22:20<1:55:40,  1.36it/s]
1|16473|Loss: 0.8349764347076416:  64%|██████▎   | 16472/25880 [3:22:21<1:55:40,  1.36it/s]
1|16473|Loss: 0.8349764347076416:  64%|██████▎   | 16473/25880 [3:22:21<1:54:36,  1.37it/s]
1|16474|Loss: 0.8368245959281921:  64%|██████▎   | 16473/25880 [3:22:22<1:54:36,  1.37it/s]
1|16474|Loss: 0.8368245959281921:  64%|██████▎   | 16474/25880 [3:22:22<1:53:19,  1.38it/s]
1|16475|Loss: 0.8557687997817993:  64%|██████▎   | 16474/25880 [3:22:22<1:53:19,  1.38it/s]
1|16475|Loss: 0.8557687997817993:  64%|██████▎   | 16475/25880 [3:22:22<1:46:51,  1.47it/s]
1|16476|Loss: 0.7943525910377502:  64%|██████▎   | 16475/25880 [3:22:23<1:46:51,  1.47it/s]
1|16476|Loss: 0.7943525910377502:  64%|██████▎   | 16476/25880 [3:22:23<1:50:03,  1.42it/s]
1|16477|Loss: 0.8953322768211365:  64%|██████▎   | 16476/25880 [3:22:24<1:50:03,  1.42it/s]
1|16477|Loss: 0.8953322768211365:  64%|██████▎   | 16477/25880 [3:22:24<1:52:09,  1.40it/s]
1|16478|Loss: 0.955704391002655:  64%|██████▎   | 16477/25880 [3:22:24<1:52:09,  1.40it/s] 
1|16478|Loss: 0.955704391002655:  64%|██████▎   | 16478/25880 [3:22:25<1:51:52,  1.40it/s]
1|16479|Loss: 0.9699726104736328:  64%|██████▎   | 16478/25880 [3:22:25<1:51:52,  1.40it/s]
1|16479|Loss: 0.9699726104736328:  64%|██████▎   | 16479/25880 [3:22:25<1:48:55,  1.44it/s]
1|16480|Loss: 0.791577935218811:  64%|██████▎   | 16479/25880 [3:22:26<1:48:55,  1.44it/s] 
1|16480|Loss: 0.791577935218811:  64%|██████▎   | 16480/25880 [3:22:26<1:45:39,  1.48it/s]
1|16481|Loss: 0.7779397368431091:  64%|██████▎   | 16480/25880 [3:22:26<1:45:39,  1.48it/s]
1|16481|Loss: 0.7779397368431091:  64%|██████▎   | 16481/25880 [3:22:27<1:47:31,  1.46it/s]
1|16482|Loss: 0.7658819556236267:  64%|██████▎   | 16481/25880 [3:22:27<1:47:31,  1.46it/s]
1|16482|Loss: 0.7658819556236267:  64%|██████▎   | 16482/25880 [3:22:27<1:53:32,  1.38it/s]
1|16483|Loss: 0.8768376111984253:  64%|██████▎   | 16482/25880 [3:22:28<1:53:32,  1.38it/s]
1|16483|Loss: 0.8768376111984253:  64%|██████▎   | 16483/25880 [3:22:28<1:50:39,  1.42it/s]
1|16484|Loss: 0.8736318349838257:  64%|██████▎   | 16483/25880 [3:22:29<1:50:39,  1.42it/s]
1|16484|Loss: 0.8736318349838257:  64%|██████▎   | 16484/25880 [3:22:29<1:49:31,  1.43it/s]
1|16485|Loss: 0.7626059055328369:  64%|██████▎   | 16484/25880 [3:22:29<1:49:31,  1.43it/s]
1|16485|Loss: 0.7626059055328369:  64%|██████▎   | 16485/25880 [3:22:29<1:43:59,  1.51it/s]
1|16486|Loss: 0.9137992262840271:  64%|██████▎   | 16485/25880 [3:22:30<1:43:59,  1.51it/s]
1|16486|Loss: 0.9137992262840271:  64%|██████▎   | 16486/25880 [3:22:30<1:39:48,  1.57it/s]
1|16487|Loss: 0.8759804368019104:  64%|██████▎   | 16486/25880 [3:22:30<1:39:48,  1.57it/s]
1|16487|Loss: 0.8759804368019104:  64%|██████▎   | 16487/25880 [3:22:31<1:44:53,  1.49it/s]
1|16488|Loss: 0.7927596569061279:  64%|██████▎   | 16487/25880 [3:22:31<1:44:53,  1.49it/s]
1|16488|Loss: 0.7927596569061279:  64%|██████▎   | 16488/25880 [3:22:32<1:51:23,  1.41it/s]
1|16489|Loss: 0.7645100951194763:  64%|██████▎   | 16488/25880 [3:22:32<1:51:23,  1.41it/s]
1|16489|Loss: 0.7645100951194763:  64%|██████▎   | 16489/25880 [3:22:32<1:49:45,  1.43it/s]
1|16490|Loss: 0.7718201875686646:  64%|██████▎   | 16489/25880 [3:22:33<1:49:45,  1.43it/s]
1|16490|Loss: 0.7718201875686646:  64%|██████▎   | 16490/25880 [3:22:33<1:50:12,  1.42it/s]
1|16491|Loss: 0.7983875870704651:  64%|██████▎   | 16490/25880 [3:22:33<1:50:12,  1.42it/s]
1|16491|Loss: 0.7983875870704651:  64%|██████▎   | 16491/25880 [3:22:34<1:55:16,  1.36it/s]
1|16492|Loss: 0.9107491374015808:  64%|██████▎   | 16491/25880 [3:22:34<1:55:16,  1.36it/s]
1|16492|Loss: 0.9107491374015808:  64%|██████▎   | 16492/25880 [3:22:35<1:56:13,  1.35it/s]
1|16493|Loss: 0.7676687836647034:  64%|██████▎   | 16492/25880 [3:22:35<1:56:13,  1.35it/s]
1|16493|Loss: 0.7676687836647034:  64%|██████▎   | 16493/25880 [3:22:35<1:55:40,  1.35it/s]
1|16494|Loss: 0.7506014108657837:  64%|██████▎   | 16493/25880 [3:22:36<1:55:40,  1.35it/s]
1|16494|Loss: 0.7506014108657837:  64%|██████▎   | 16494/25880 [3:22:36<1:51:44,  1.40it/s]
1|16495|Loss: 0.8562201857566833:  64%|██████▎   | 16494/25880 [3:22:36<1:51:44,  1.40it/s]
1|16495|Loss: 0.8562201857566833:  64%|██████▎   | 16495/25880 [3:22:37<1:52:02,  1.40it/s]
1|16496|Loss: 0.6791256666183472:  64%|██████▎   | 16495/25880 [3:22:37<1:52:02,  1.40it/s]
1|16496|Loss: 0.6791256666183472:  64%|██████▎   | 16496/25880 [3:22:37<1:49:40,  1.43it/s]
1|16497|Loss: 0.9202040433883667:  64%|██████▎   | 16496/25880 [3:22:38<1:49:40,  1.43it/s]
1|16497|Loss: 0.9202040433883667:  64%|██████▎   | 16497/25880 [3:22:38<1:46:49,  1.46it/s]
1|16498|Loss: 0.7539440989494324:  64%|██████▎   | 16497/25880 [3:22:38<1:46:49,  1.46it/s]
1|16498|Loss: 0.7539440989494324:  64%|██████▎   | 16498/25880 [3:22:39<1:47:09,  1.46it/s]
1|16499|Loss: 0.8139238357543945:  64%|██████▎   | 16498/25880 [3:22:39<1:47:09,  1.46it/s]
1|16499|Loss: 0.8139238357543945:  64%|██████▍   | 16499/25880 [3:22:39<1:52:53,  1.39it/s]
1|16500|Loss: 0.8121137022972107:  64%|██████▍   | 16499/25880 [3:22:40<1:52:53,  1.39it/s]
1|16500|Loss: 0.8121137022972107:  64%|██████▍   | 16500/25880 [3:22:40<2:02:49,  1.27it/s]
1|16501|Loss: 0.7849827408790588:  64%|██████▍   | 16500/25880 [3:22:41<2:02:49,  1.27it/s]
1|16501|Loss: 0.7849827408790588:  64%|██████▍   | 16501/25880 [3:22:41<2:02:14,  1.28it/s]
1|16502|Loss: 1.0240168571472168:  64%|██████▍   | 16501/25880 [3:22:42<2:02:14,  1.28it/s]
1|16502|Loss: 1.0240168571472168:  64%|██████▍   | 16502/25880 [3:22:42<2:00:07,  1.30it/s]
1|16503|Loss: 0.7622706890106201:  64%|██████▍   | 16502/25880 [3:22:42<2:00:07,  1.30it/s]
1|16503|Loss: 0.7622706890106201:  64%|██████▍   | 16503/25880 [3:22:43<1:57:34,  1.33it/s]
1|16504|Loss: 0.705687403678894:  64%|██████▍   | 16503/25880 [3:22:43<1:57:34,  1.33it/s] 
1|16504|Loss: 0.705687403678894:  64%|██████▍   | 16504/25880 [3:22:43<2:00:17,  1.30it/s]
1|16505|Loss: 0.839532732963562:  64%|██████▍   | 16504/25880 [3:22:44<2:00:17,  1.30it/s]
1|16505|Loss: 0.839532732963562:  64%|██████▍   | 16505/25880 [3:22:44<1:59:47,  1.30it/s]
1|16506|Loss: 0.8817314505577087:  64%|██████▍   | 16505/25880 [3:22:45<1:59:47,  1.30it/s]
1|16506|Loss: 0.8817314505577087:  64%|██████▍   | 16506/25880 [3:22:45<1:58:19,  1.32it/s]
1|16507|Loss: 0.8865273594856262:  64%|██████▍   | 16506/25880 [3:22:45<1:58:19,  1.32it/s]
1|16507|Loss: 0.8865273594856262:  64%|██████▍   | 16507/25880 [3:22:46<1:52:37,  1.39it/s]
1|16508|Loss: 0.6886533498764038:  64%|██████▍   | 16507/25880 [3:22:46<1:52:37,  1.39it/s]
1|16508|Loss: 0.6886533498764038:  64%|██████▍   | 16508/25880 [3:22:46<1:55:26,  1.35it/s]
1|16509|Loss: 0.7365246415138245:  64%|██████▍   | 16508/25880 [3:22:47<1:55:26,  1.35it/s]
1|16509|Loss: 0.7365246415138245:  64%|██████▍   | 16509/25880 [3:22:47<1:52:33,  1.39it/s]
1|16510|Loss: 0.8653243184089661:  64%|██████▍   | 16509/25880 [3:22:47<1:52:33,  1.39it/s]
1|16510|Loss: 0.8653243184089661:  64%|██████▍   | 16510/25880 [3:22:48<1:52:12,  1.39it/s]
1|16511|Loss: 0.8998218178749084:  64%|██████▍   | 16510/25880 [3:22:48<1:52:12,  1.39it/s]
1|16511|Loss: 0.8998218178749084:  64%|██████▍   | 16511/25880 [3:22:48<1:49:09,  1.43it/s]
1|16512|Loss: 0.8006843328475952:  64%|██████▍   | 16511/25880 [3:22:49<1:49:09,  1.43it/s]
1|16512|Loss: 0.8006843328475952:  64%|██████▍   | 16512/25880 [3:22:49<1:56:49,  1.34it/s]
1|16513|Loss: 0.8297222256660461:  64%|██████▍   | 16512/25880 [3:22:50<1:56:49,  1.34it/s]
1|16513|Loss: 0.8297222256660461:  64%|██████▍   | 16513/25880 [3:22:50<1:56:21,  1.34it/s]
1|16514|Loss: 0.8748990893363953:  64%|██████▍   | 16513/25880 [3:22:50<1:56:21,  1.34it/s]
1|16514|Loss: 0.8748990893363953:  64%|██████▍   | 16514/25880 [3:22:51<1:49:43,  1.42it/s]
1|16515|Loss: 0.9190985560417175:  64%|██████▍   | 16514/25880 [3:22:51<1:49:43,  1.42it/s]
1|16515|Loss: 0.9190985560417175:  64%|██████▍   | 16515/25880 [3:22:51<1:46:14,  1.47it/s]
1|16516|Loss: 0.9101216793060303:  64%|██████▍   | 16515/25880 [3:22:52<1:46:14,  1.47it/s]
1|16516|Loss: 0.9101216793060303:  64%|██████▍   | 16516/25880 [3:22:52<1:46:34,  1.46it/s]
1|16517|Loss: 0.849056601524353:  64%|██████▍   | 16516/25880 [3:22:52<1:46:34,  1.46it/s] 
1|16517|Loss: 0.849056601524353:  64%|██████▍   | 16517/25880 [3:22:53<1:47:28,  1.45it/s]
1|16518|Loss: 0.85318922996521:  64%|██████▍   | 16517/25880 [3:22:53<1:47:28,  1.45it/s] 
1|16518|Loss: 0.85318922996521:  64%|██████▍   | 16518/25880 [3:22:53<1:48:59,  1.43it/s]
1|16519|Loss: 0.7295113801956177:  64%|██████▍   | 16518/25880 [3:22:54<1:48:59,  1.43it/s]
1|16519|Loss: 0.7295113801956177:  64%|██████▍   | 16519/25880 [3:22:54<1:43:48,  1.50it/s]
1|16520|Loss: 0.8567448854446411:  64%|██████▍   | 16519/25880 [3:22:54<1:43:48,  1.50it/s]
1|16520|Loss: 0.8567448854446411:  64%|██████▍   | 16520/25880 [3:22:54<1:39:27,  1.57it/s]
1|16521|Loss: 0.7666538953781128:  64%|██████▍   | 16520/25880 [3:22:55<1:39:27,  1.57it/s]
1|16521|Loss: 0.7666538953781128:  64%|██████▍   | 16521/25880 [3:22:55<1:42:17,  1.52it/s]
1|16522|Loss: 0.8610643744468689:  64%|██████▍   | 16521/25880 [3:22:56<1:42:17,  1.52it/s]
1|16522|Loss: 0.8610643744468689:  64%|██████▍   | 16522/25880 [3:22:56<1:42:06,  1.53it/s]
1|16523|Loss: 0.88563472032547:  64%|██████▍   | 16522/25880 [3:22:56<1:42:06,  1.53it/s]  
1|16523|Loss: 0.88563472032547:  64%|██████▍   | 16523/25880 [3:22:57<1:50:24,  1.41it/s]
1|16524|Loss: 0.6914252042770386:  64%|██████▍   | 16523/25880 [3:22:57<1:50:24,  1.41it/s]
1|16524|Loss: 0.6914252042770386:  64%|██████▍   | 16524/25880 [3:22:57<1:52:04,  1.39it/s]
1|16525|Loss: 0.892905592918396:  64%|██████▍   | 16524/25880 [3:22:58<1:52:04,  1.39it/s] 
1|16525|Loss: 0.892905592918396:  64%|██████▍   | 16525/25880 [3:22:58<1:47:49,  1.45it/s]
1|16526|Loss: 0.8288322687149048:  64%|██████▍   | 16525/25880 [3:22:58<1:47:49,  1.45it/s]
1|16526|Loss: 0.8288322687149048:  64%|██████▍   | 16526/25880 [3:22:59<1:48:29,  1.44it/s]
1|16527|Loss: 0.7106198072433472:  64%|���█████▍   | 16526/25880 [3:22:59<1:48:29,  1.44it/s]
1|16527|Loss: 0.7106198072433472:  64%|██████▍   | 16527/25880 [3:23:00<1:58:28,  1.32it/s]
1|16528|Loss: 0.7428450584411621:  64%|██████▍   | 16527/25880 [3:23:00<1:58:28,  1.32it/s]
1|16528|Loss: 0.7428450584411621:  64%|██████▍   | 16528/25880 [3:23:00<1:54:58,  1.36it/s]
1|16529|Loss: 0.8030110597610474:  64%|██████▍   | 16528/25880 [3:23:01<1:54:58,  1.36it/s]
1|16529|Loss: 0.8030110597610474:  64%|██████▍   | 16529/25880 [3:23:01<1:56:21,  1.34it/s]
1|16530|Loss: 0.7595243453979492:  64%|██████▍   | 16529/25880 [3:23:02<1:56:21,  1.34it/s]
1|16530|Loss: 0.7595243453979492:  64%|██████▍   | 16530/25880 [3:23:02<2:05:35,  1.24it/s]
1|16531|Loss: 0.7624520063400269:  64%|██████▍   | 16530/25880 [3:23:03<2:05:35,  1.24it/s]
1|16531|Loss: 0.7624520063400269:  64%|██████▍   | 16531/25880 [3:23:03<2:07:36,  1.22it/s]
1|16532|Loss: 0.8138918876647949:  64%|██████▍   | 16531/25880 [3:23:03<2:07:36,  1.22it/s]
1|16532|Loss: 0.8138918876647949:  64%|██████▍   | 16532/25880 [3:23:04<2:03:48,  1.26it/s]
1|16533|Loss: 0.7666047215461731:  64%|██████▍   | 16532/25880 [3:23:04<2:03:48,  1.26it/s]
1|16533|Loss: 0.7666047215461731:  64%|██████▍   | 16533/25880 [3:23:04<1:54:10,  1.36it/s]
1|16534|Loss: 0.8151301741600037:  64%|██████▍   | 16533/25880 [3:23:05<1:54:10,  1.36it/s]
1|16534|Loss: 0.8151301741600037:  64%|██████▍   | 16534/25880 [3:23:05<1:58:09,  1.32it/s]
1|16535|Loss: 0.8283167481422424:  64%|██████▍   | 16534/25880 [3:23:05<1:58:09,  1.32it/s]
1|16535|Loss: 0.8283167481422424:  64%|██████▍   | 16535/25880 [3:23:06<1:55:16,  1.35it/s]
1|16536|Loss: 0.9775826930999756:  64%|██████▍   | 16535/25880 [3:23:06<1:55:16,  1.35it/s]
1|16536|Loss: 0.9775826930999756:  64%|██████▍   | 16536/25880 [3:23:06<1:52:54,  1.38it/s]
1|16537|Loss: 0.7416709661483765:  64%|██████▍   | 16536/25880 [3:23:07<1:52:54,  1.38it/s]
1|16537|Loss: 0.7416709661483765:  64%|██████▍   | 16537/25880 [3:23:07<1:55:51,  1.34it/s]
1|16538|Loss: 0.9445869326591492:  64%|██████▍   | 16537/25880 [3:23:08<1:55:51,  1.34it/s]
1|16538|Loss: 0.9445869326591492:  64%|██████▍   | 16538/25880 [3:23:08<1:56:00,  1.34it/s]
1|16539|Loss: 0.9126050472259521:  64%|██████▍   | 16538/25880 [3:23:08<1:56:00,  1.34it/s]
1|16539|Loss: 0.9126050472259521:  64%|██████▍   | 16539/25880 [3:23:09<1:59:39,  1.30it/s]
1|16540|Loss: 0.8210052847862244:  64%|██████▍   | 16539/25880 [3:23:09<1:59:39,  1.30it/s]
1|16540|Loss: 0.8210052847862244:  64%|██████▍   | 16540/25880 [3:23:09<1:55:41,  1.35it/s]
1|16541|Loss: 0.8946967720985413:  64%|██████▍   | 16540/25880 [3:23:10<1:55:41,  1.35it/s]
1|16541|Loss: 0.8946967720985413:  64%|██████▍   | 16541/25880 [3:23:10<1:54:27,  1.36it/s]
1|16542|Loss: 0.94303297996521:  64%|██████▍   | 16541/25880 [3:23:11<1:54:27,  1.36it/s]  
1|16542|Loss: 0.94303297996521:  64%|██████▍   | 16542/25880 [3:23:11<1:53:11,  1.37it/s]
1|16543|Loss: 0.9041504859924316:  64%|██████▍   | 16542/25880 [3:23:11<1:53:11,  1.37it/s]
1|16543|Loss: 0.9041504859924316:  64%|██████▍   | 16543/25880 [3:23:12<1:51:47,  1.39it/s]
1|16544|Loss: 0.8606106042861938:  64%|██████▍   | 16543/25880 [3:23:12<1:51:47,  1.39it/s]
1|16544|Loss: 0.8606106042861938:  64%|██████▍   | 16544/25880 [3:23:12<1:47:51,  1.44it/s]
1|16545|Loss: 0.837489664554596:  64%|██████▍   | 16544/25880 [3:23:13<1:47:51,  1.44it/s] 
1|16545|Loss: 0.837489664554596:  64%|██████▍   | 16545/25880 [3:23:13<1:48:34,  1.43it/s]
1|16546|Loss: 0.8137944340705872:  64%|██████▍   | 16545/25880 [3:23:13<1:48:34,  1.43it/s]
1|16546|Loss: 0.8137944340705872:  64%|██████▍   | 16546/25880 [3:23:14<1:50:11,  1.41it/s]
1|16547|Loss: 0.7665460109710693:  64%|██████▍   | 16546/25880 [3:23:14<1:50:11,  1.41it/s]
1|16547|Loss: 0.7665460109710693:  64%|██████▍   | 16547/25880 [3:23:14<1:45:42,  1.47it/s]
1|16548|Loss: 1.0408660173416138:  64%|██████▍   | 16547/25880 [3:23:15<1:45:42,  1.47it/s]
1|16548|Loss: 1.0408660173416138:  64%|██████▍   | 16548/25880 [3:23:15<1:42:25,  1.52it/s]
1|16549|Loss: 0.7541387677192688:  64%|██████▍   | 16548/25880 [3:23:15<1:42:25,  1.52it/s]
1|16549|Loss: 0.7541387677192688:  64%|██████▍   | 16549/25880 [3:23:16<1:48:26,  1.43it/s]
1|16550|Loss: 0.8366654515266418:  64%|██████▍   | 16549/25880 [3:23:16<1:48:26,  1.43it/s]
1|16550|Loss: 0.8366654515266418:  64%|██████▍   | 16550/25880 [3:23:16<1:46:30,  1.46it/s]
1|16551|Loss: 0.8462488055229187:  64%|██████▍   | 16550/25880 [3:23:17<1:46:30,  1.46it/s]
1|16551|Loss: 0.8462488055229187:  64%|██████▍   | 16551/25880 [3:23:17<1:46:31,  1.46it/s]
1|16552|Loss: 0.7888209819793701:  64%|██████▍   | 16551/25880 [3:23:17<1:46:31,  1.46it/s]
1|16552|Loss: 0.7888209819793701:  64%|██████▍   | 16552/25880 [3:23:18<1:48:35,  1.43it/s]
1|16553|Loss: 0.8714269995689392:  64%|██████▍   | 16552/25880 [3:23:18<1:48:35,  1.43it/s]
1|16553|Loss: 0.8714269995689392:  64%|██████▍   | 16553/25880 [3:23:18<1:47:04,  1.45it/s]
1|16554|Loss: 0.7178399562835693:  64%|██████▍   | 16553/25880 [3:23:19<1:47:04,  1.45it/s]
1|16554|Loss: 0.7178399562835693:  64%|██████▍   | 16554/25880 [3:23:19<1:52:50,  1.38it/s]
1|16555|Loss: 1.0453100204467773:  64%|██████▍   | 16554/25880 [3:23:20<1:52:50,  1.38it/s]
1|16555|Loss: 1.0453100204467773:  64%|██████▍   | 16555/25880 [3:23:20<1:59:23,  1.30it/s]
1|16556|Loss: 0.7930680513381958:  64%|██████▍   | 16555/25880 [3:23:20<1:59:23,  1.30it/s]
1|16556|Loss: 0.7930680513381958:  64%|██████▍   | 16556/25880 [3:23:21<1:52:58,  1.38it/s]
1|16557|Loss: 0.7040610909461975:  64%|██████▍   | 16556/25880 [3:23:21<1:52:58,  1.38it/s]
1|16557|Loss: 0.7040610909461975:  64%|██████▍   | 16557/25880 [3:23:22<2:00:06,  1.29it/s]
1|16558|Loss: 0.6759268045425415:  64%|██████▍   | 16557/25880 [3:23:22<2:00:06,  1.29it/s]
1|16558|Loss: 0.6759268045425415:  64%|██████▍   | 16558/25880 [3:23:22<1:59:19,  1.30it/s]
1|16559|Loss: 0.7567315101623535:  64%|██████▍   | 16558/25880 [3:23:23<1:59:19,  1.30it/s]
1|16559|Loss: 0.7567315101623535:  64%|██████▍   | 16559/25880 [3:23:23<1:49:51,  1.41it/s]
1|16560|Loss: 0.7423787713050842:  64%|██████▍   | 16559/25880 [3:23:23<1:49:51,  1.41it/s]
1|16560|Loss: 0.7423787713050842:  64%|██████▍   | 16560/25880 [3:23:24<1:44:41,  1.48it/s]
1|16561|Loss: 0.9402683973312378:  64%|██████▍   | 16560/25880 [3:23:24<1:44:41,  1.48it/s]
1|16561|Loss: 0.9402683973312378:  64%|██████▍   | 16561/25880 [3:23:24<1:51:26,  1.39it/s]
1|16562|Loss: 0.9557780027389526:  64%|██████▍   | 16561/25880 [3:23:25<1:51:26,  1.39it/s]
1|16562|Loss: 0.9557780027389526:  64%|██████▍   | 16562/25880 [3:23:25<1:59:09,  1.30it/s]
1|16563|Loss: 0.9642096757888794:  64%|██████▍   | 16562/25880 [3:23:26<1:59:09,  1.30it/s]
1|16563|Loss: 0.9642096757888794:  64%|██████▍   | 16563/25880 [3:23:26<1:55:44,  1.34it/s]
1|16564|Loss: 0.7665842771530151:  64%|██████▍   | 16563/25880 [3:23:26<1:55:44,  1.34it/s]
1|16564|Loss: 0.7665842771530151:  64%|██████▍   | 16564/25880 [3:23:27<1:57:53,  1.32it/s]
1|16565|Loss: 0.9458736181259155:  64%|██████▍   | 16564/25880 [3:23:27<1:57:53,  1.32it/s]
1|16565|Loss: 0.9458736181259155:  64%|██████▍   | 16565/25880 [3:23:27<1:57:30,  1.32it/s]
1|16566|Loss: 0.8703884482383728:  64%|██████▍   | 16565/25880 [3:23:28<1:57:30,  1.32it/s]
1|16566|Loss: 0.8703884482383728:  64%|██████▍   | 16566/25880 [3:23:28<1:48:11,  1.43it/s]
1|16567|Loss: 0.8780472278594971:  64%|██████▍   | 16566/25880 [3:23:28<1:48:11,  1.43it/s]
1|16567|Loss: 0.8780472278594971:  64%|██████▍   | 16567/25880 [3:23:29<1:47:26,  1.44it/s]
1|16568|Loss: 0.7558343410491943:  64%|██████▍   | 16567/25880 [3:23:29<1:47:26,  1.44it/s]
1|16568|Loss: 0.7558343410491943:  64%|██████▍   | 16568/25880 [3:23:29<1:51:45,  1.39it/s]
1|16569|Loss: 0.8449363112449646:  64%|██████▍   | 16568/25880 [3:23:30<1:51:45,  1.39it/s]
1|16569|Loss: 0.8449363112449646:  64%|██████▍   | 16569/25880 [3:23:30<1:48:44,  1.43it/s]
1|16570|Loss: 0.9030701518058777:  64%|██████▍   | 16569/25880 [3:23:31<1:48:44,  1.43it/s]
1|16570|Loss: 0.9030701518058777:  64%|██████▍   | 16570/25880 [3:23:31<1:52:05,  1.38it/s]
1|16571|Loss: 0.8167247772216797:  64%|██████▍   | 16570/25880 [3:23:31<1:52:05,  1.38it/s]
1|16571|Loss: 0.8167247772216797:  64%|██████▍   | 16571/25880 [3:23:32<1:49:13,  1.42it/s]
1|16572|Loss: 0.7733910083770752:  64%|██████▍   | 16571/25880 [3:23:32<1:49:13,  1.42it/s]
1|16572|Loss: 0.7733910083770752:  64%|██████▍   | 16572/25880 [3:23:32<1:49:59,  1.41it/s]
1|16573|Loss: 0.803281307220459:  64%|██████▍   | 16572/25880 [3:23:33<1:49:59,  1.41it/s] 
1|16573|Loss: 0.803281307220459:  64%|██████▍   | 16573/25880 [3:23:33<1:51:04,  1.40it/s]
1|16574|Loss: 0.8207168579101562:  64%|██████▍   | 16573/25880 [3:23:33<1:51:04,  1.40it/s]
1|16574|Loss: 0.8207168579101562:  64%|██████▍   | 16574/25880 [3:23:34<2:00:17,  1.29it/s]
1|16575|Loss: 1.112815499305725:  64%|██████▍   | 16574/25880 [3:23:34<2:00:17,  1.29it/s] 
1|16575|Loss: 1.112815499305725:  64%|██████▍   | 16575/25880 [3:23:35<2:01:09,  1.28it/s]
1|16576|Loss: 0.7931619882583618:  64%|██████▍   | 16575/25880 [3:23:35<2:01:09,  1.28it/s]
1|16576|Loss: 0.7931619882583618:  64%|██████▍   | 16576/25880 [3:23:35<1:56:01,  1.34it/s]
1|16577|Loss: 0.832336962223053:  64%|██████▍   | 16576/25880 [3:23:36<1:56:01,  1.34it/s] 
1|16577|Loss: 0.832336962223053:  64%|██████▍   | 16577/25880 [3:23:36<1:53:16,  1.37it/s]
1|16578|Loss: 0.7130020260810852:  64%|██████▍   | 16577/25880 [3:23:36<1:53:16,  1.37it/s]
1|16578|Loss: 0.7130020260810852:  64%|██████▍   | 16578/25880 [3:23:37<1:53:05,  1.37it/s]
1|16579|Loss: 0.88984614610672:  64%|██████▍   | 16578/25880 [3:23:37<1:53:05,  1.37it/s]  
1|16579|Loss: 0.88984614610672:  64%|██████▍   | 16579/25880 [3:23:38<2:00:00,  1.29it/s]
1|16580|Loss: 0.9704052209854126:  64%|██████▍   | 16579/25880 [3:23:38<2:00:00,  1.29it/s]
1|16580|Loss: 0.9704052209854126:  64%|██████▍   | 16580/25880 [3:23:38<1:53:55,  1.36it/s]
1|16581|Loss: 0.8200186491012573:  64%|██████▍   | 16580/25880 [3:23:39<1:53:55,  1.36it/s]
1|16581|Loss: 0.8200186491012573:  64%|██████▍   | 16581/25880 [3:23:39<1:52:40,  1.38it/s]
1|16582|Loss: 0.8219722509384155:  64%|██████▍   | 16581/25880 [3:23:39<1:52:40,  1.38it/s]
1|16582|Loss: 0.8219722509384155:  64%|██████▍   | 16582/25880 [3:23:40<1:58:17,  1.31it/s]
1|16583|Loss: 0.7716659903526306:  64%|██████▍   | 16582/25880 [3:23:40<1:58:17,  1.31it/s]
1|16583|Loss: 0.7716659903526306:  64%|██████▍   | 16583/25880 [3:23:40<1:48:08,  1.43it/s]
1|16584|Loss: 0.8826347589492798:  64%|██████▍   | 16583/25880 [3:23:41<1:48:08,  1.43it/s]
1|16584|Loss: 0.8826347589492798:  64%|██████▍   | 16584/25880 [3:23:41<1:46:51,  1.45it/s]
1|16585|Loss: 0.8942418694496155:  64%|██████▍   | 16584/25880 [3:23:41<1:46:51,  1.45it/s]
1|16585|Loss: 0.8942418694496155:  64%|██████▍   | 16585/25880 [3:23:42<1:45:18,  1.47it/s]
1|16586|Loss: 0.7143718004226685:  64%|██████▍   | 16585/25880 [3:23:42<1:45:18,  1.47it/s]
1|16586|Loss: 0.7143718004226685:  64%|██████▍   | 16586/25880 [3:23:42<1:41:08,  1.53it/s]
1|16587|Loss: 0.826370894908905:  64%|██████▍   | 16586/25880 [3:23:43<1:41:08,  1.53it/s] 
1|16587|Loss: 0.826370894908905:  64%|██████▍   | 16587/25880 [3:23:43<1:42:17,  1.51it/s]
1|16588|Loss: 1.0187911987304688:  64%|██████▍   | 16587/25880 [3:23:43<1:42:17,  1.51it/s]
1|16588|Loss: 1.0187911987304688:  64%|██████▍   | 16588/25880 [3:23:44<1:39:37,  1.55it/s]
1|16589|Loss: 0.9058101773262024:  64%|██████▍   | 16588/25880 [3:23:44<1:39:37,  1.55it/s]
1|16589|Loss: 0.9058101773262024:  64%|██████▍   | 16589/25880 [3:23:44<1:46:44,  1.45it/s]
1|16590|Loss: 0.8420581221580505:  64%|██████▍   | 16589/25880 [3:23:45<1:46:44,  1.45it/s]
1|16590|Loss: 0.8420581221580505:  64%|██████▍   | 16590/25880 [3:23:45<1:55:13,  1.34it/s]
1|16591|Loss: 0.6118837594985962:  64%|██████▍   | 16590/25880 [3:23:46<1:55:13,  1.34it/s]
1|16591|Loss: 0.6118837594985962:  64%|██████▍   | 16591/25880 [3:23:46<1:58:30,  1.31it/s]
1|16592|Loss: 1.0081596374511719:  64%|██████▍   | 16591/25880 [3:23:46<1:58:30,  1.31it/s]
1|16592|Loss: 1.0081596374511719:  64%|██████▍   | 16592/25880 [3:23:47<1:52:04,  1.38it/s]
1|16593|Loss: 0.7565263509750366:  64%|██████▍   | 16592/25880 [3:23:47<1:52:04,  1.38it/s]
1|16593|Loss: 0.7565263509750366:  64%|██████▍   | 16593/25880 [3:23:47<1:43:27,  1.50it/s]
1|16594|Loss: 0.837500810623169:  64%|██████▍   | 16593/25880 [3:23:48<1:43:27,  1.50it/s] 
1|16594|Loss: 0.837500810623169:  64%|██████▍   | 16594/25880 [3:23:48<1:44:30,  1.48it/s]
1|16595|Loss: 0.8113995790481567:  64%|██████▍   | 16594/25880 [3:23:48<1:44:30,  1.48it/s]
1|16595|Loss: 0.8113995790481567:  64%|██████▍   | 16595/25880 [3:23:49<1:40:28,  1.54it/s]
1|16596|Loss: 0.9181585907936096:  64%|██████▍   | 16595/25880 [3:23:49<1:40:28,  1.54it/s]
1|16596|Loss: 0.9181585907936096:  64%|██████▍   | 16596/25880 [3:23:49<1:41:31,  1.52it/s]
1|16597|Loss: 0.7764316201210022:  64%|██████▍   | 16596/25880 [3:23:50<1:41:31,  1.52it/s]
1|16597|Loss: 0.7764316201210022:  64%|██████▍   | 16597/25880 [3:23:50<1:37:01,  1.59it/s]
1|16598|Loss: 0.831413209438324:  64%|██████▍   | 16597/25880 [3:23:50<1:37:01,  1.59it/s] 
1|16598|Loss: 0.831413209438324:  64%|██████▍   | 16598/25880 [3:23:50<1:35:36,  1.62it/s]
1|16599|Loss: 0.9246549606323242:  64%|██████▍   | 16598/25880 [3:23:51<1:35:36,  1.62it/s]
1|16599|Loss: 0.9246549606323242:  64%|��█████▍   | 16599/25880 [3:23:51<1:46:54,  1.45it/s]
1|16600|Loss: 0.7668945789337158:  64%|██████▍   | 16599/25880 [3:23:52<1:46:54,  1.45it/s]
1|16600|Loss: 0.7668945789337158:  64%|██████▍   | 16600/25880 [3:23:52<1:49:05,  1.42it/s]
1|16601|Loss: 0.7817508578300476:  64%|██████▍   | 16600/25880 [3:23:52<1:49:05,  1.42it/s]
1|16601|Loss: 0.7817508578300476:  64%|██████▍   | 16601/25880 [3:23:53<1:48:58,  1.42it/s]
1|16602|Loss: 0.8936135172843933:  64%|██████▍   | 16601/25880 [3:23:53<1:48:58,  1.42it/s]
1|16602|Loss: 0.8936135172843933:  64%|██████▍   | 16602/25880 [3:23:54<1:54:40,  1.35it/s]
1|16603|Loss: 0.7515732049942017:  64%|██████▍   | 16602/25880 [3:23:54<1:54:40,  1.35it/s]
1|16603|Loss: 0.7515732049942017:  64%|██████▍   | 16603/25880 [3:23:54<1:54:40,  1.35it/s]
1|16604|Loss: 0.802939236164093:  64%|██████▍   | 16603/25880 [3:23:55<1:54:40,  1.35it/s] 
1|16604|Loss: 0.802939236164093:  64%|██████▍   | 16604/25880 [3:23:55<1:53:46,  1.36it/s]
1|16605|Loss: 0.7294216156005859:  64%|██████▍   | 16604/25880 [3:23:55<1:53:46,  1.36it/s]
1|16605|Loss: 0.7294216156005859:  64%|██████▍   | 16605/25880 [3:23:56<1:53:04,  1.37it/s]
1|16606|Loss: 0.7313011884689331:  64%|██████▍   | 16605/25880 [3:23:56<1:53:04,  1.37it/s]
1|16606|Loss: 0.7313011884689331:  64%|██████▍   | 16606/25880 [3:23:56<1:47:07,  1.44it/s]
1|16607|Loss: 0.885704755783081:  64%|██████▍   | 16606/25880 [3:23:57<1:47:07,  1.44it/s] 
1|16607|Loss: 0.885704755783081:  64%|██████▍   | 16607/25880 [3:23:57<1:43:03,  1.50it/s]
1|16608|Loss: 0.7407606840133667:  64%|██████▍   | 16607/25880 [3:23:57<1:43:03,  1.50it/s]
1|16608|Loss: 0.7407606840133667:  64%|██████▍   | 16608/25880 [3:23:58<1:53:21,  1.36it/s]
1|16609|Loss: 0.9576494097709656:  64%|██████▍   | 16608/25880 [3:23:58<1:53:21,  1.36it/s]
1|16609|Loss: 0.9576494097709656:  64%|██████▍   | 16609/25880 [3:23:58<1:49:45,  1.41it/s]
1|16610|Loss: 0.8864128589630127:  64%|██████▍   | 16609/25880 [3:23:59<1:49:45,  1.41it/s]
1|16610|Loss: 0.8864128589630127:  64%|██████▍   | 16610/25880 [3:23:59<1:45:59,  1.46it/s]
1|16611|Loss: 0.8429136872291565:  64%|██████▍   | 16610/25880 [3:23:59<1:45:59,  1.46it/s]
1|16611|Loss: 0.8429136872291565:  64%|██████▍   | 16611/25880 [3:24:00<1:44:00,  1.49it/s]
1|16612|Loss: 0.8783424496650696:  64%|██████▍   | 16611/25880 [3:24:00<1:44:00,  1.49it/s]
1|16612|Loss: 0.8783424496650696:  64%|██████▍   | 16612/25880 [3:24:01<1:48:20,  1.43it/s]
1|16613|Loss: 0.8683523535728455:  64%|██████▍   | 16612/25880 [3:24:01<1:48:20,  1.43it/s]
1|16613|Loss: 0.8683523535728455:  64%|██████▍   | 16613/25880 [3:24:01<1:50:38,  1.40it/s]
1|16614|Loss: 0.7846805453300476:  64%|██████▍   | 16613/25880 [3:24:02<1:50:38,  1.40it/s]
1|16614|Loss: 0.7846805453300476:  64%|██████▍   | 16614/25880 [3:24:02<1:55:35,  1.34it/s]
1|16615|Loss: 0.9107004404067993:  64%|██████▍   | 16614/25880 [3:24:02<1:55:35,  1.34it/s]
1|16615|Loss: 0.9107004404067993:  64%|██████▍   | 16615/25880 [3:24:03<1:55:47,  1.33it/s]
1|16616|Loss: 0.8858165144920349:  64%|██████▍   | 16615/25880 [3:24:03<1:55:47,  1.33it/s]
1|16616|Loss: 0.8858165144920349:  64%|██████▍   | 16616/25880 [3:24:04<2:01:46,  1.27it/s]
1|16617|Loss: 0.754962682723999:  64%|██████▍   | 16616/25880 [3:24:04<2:01:46,  1.27it/s] 
1|16617|Loss: 0.754962682723999:  64%|██████▍   | 16617/25880 [3:24:05<2:04:37,  1.24it/s]
1|16618|Loss: 0.8472276329994202:  64%|██████▍   | 16617/25880 [3:24:05<2:04:37,  1.24it/s]
1|16618|Loss: 0.8472276329994202:  64%|██████▍   | 16618/25880 [3:24:05<2:02:31,  1.26it/s]
1|16619|Loss: 0.9338945150375366:  64%|██████▍   | 16618/25880 [3:24:06<2:02:31,  1.26it/s]
1|16619|Loss: 0.9338945150375366:  64%|██████▍   | 16619/25880 [3:24:06<2:02:24,  1.26it/s]
1|16620|Loss: 0.8407169580459595:  64%|██████▍   | 16619/25880 [3:24:07<2:02:24,  1.26it/s]
1|16620|Loss: 0.8407169580459595:  64%|██████▍   | 16620/25880 [3:24:07<2:05:11,  1.23it/s]
1|16621|Loss: 0.801108181476593:  64%|██████▍   | 16620/25880 [3:24:07<2:05:11,  1.23it/s] 
1|16621|Loss: 0.801108181476593:  64%|██████▍   | 16621/25880 [3:24:08<1:57:34,  1.31it/s]
1|16622|Loss: 0.7531551122665405:  64%|██████▍   | 16621/25880 [3:24:08<1:57:34,  1.31it/s]
1|16622|Loss: 0.7531551122665405:  64%|██████▍   | 16622/25880 [3:24:08<1:49:40,  1.41it/s]
1|16623|Loss: 0.7319048643112183:  64%|██████▍   | 16622/25880 [3:24:09<1:49:40,  1.41it/s]
1|16623|Loss: 0.7319048643112183:  64%|██████▍   | 16623/25880 [3:24:09<1:49:35,  1.41it/s]
1|16624|Loss: 0.7981206178665161:  64%|██████▍   | 16623/25880 [3:24:09<1:49:35,  1.41it/s]
1|16624|Loss: 0.7981206178665161:  64%|██████▍   | 16624/25880 [3:24:10<1:54:26,  1.35it/s]
1|16625|Loss: 1.0277553796768188:  64%|██████▍   | 16624/25880 [3:24:10<1:54:26,  1.35it/s]
1|16625|Loss: 1.0277553796768188:  64%|██████▍   | 16625/25880 [3:24:11<1:56:47,  1.32it/s]
1|16626|Loss: 0.8583024144172668:  64%|██████▍   | 16625/25880 [3:24:11<1:56:47,  1.32it/s]
1|16626|Loss: 0.8583024144172668:  64%|██████▍   | 16626/25880 [3:24:11<1:56:01,  1.33it/s]
1|16627|Loss: 0.9435222148895264:  64%|██████▍   | 16626/25880 [3:24:12<1:56:01,  1.33it/s]
1|16627|Loss: 0.9435222148895264:  64%|██████▍   | 16627/25880 [3:24:12<1:51:32,  1.38it/s]
1|16628|Loss: 0.7983365654945374:  64%|██████▍   | 16627/25880 [3:24:12<1:51:32,  1.38it/s]
1|16628|Loss: 0.7983365654945374:  64%|██████▍   | 16628/25880 [3:24:13<1:51:43,  1.38it/s]
1|16629|Loss: 0.8152250051498413:  64%|██████▍   | 16628/25880 [3:24:13<1:51:43,  1.38it/s]
1|16629|Loss: 0.8152250051498413:  64%|██████▍   | 16629/25880 [3:24:13<1:56:01,  1.33it/s]
1|16630|Loss: 0.9051109552383423:  64%|██████▍   | 16629/25880 [3:24:14<1:56:01,  1.33it/s]
1|16630|Loss: 0.9051109552383423:  64%|██████▍   | 16630/25880 [3:24:14<1:56:50,  1.32it/s]
1|16631|Loss: 0.7804468274116516:  64%|██████▍   | 16630/25880 [3:24:15<1:56:50,  1.32it/s]
1|16631|Loss: 0.7804468274116516:  64%|██████▍   | 16631/25880 [3:24:15<1:56:33,  1.32it/s]
1|16632|Loss: 0.8359953165054321:  64%|██████▍   | 16631/25880 [3:24:15<1:56:33,  1.32it/s]
1|16632|Loss: 0.8359953165054321:  64%|██████▍   | 16632/25880 [3:24:16<1:54:38,  1.34it/s]
1|16633|Loss: 0.7890677452087402:  64%|██████▍   | 16632/25880 [3:24:16<1:54:38,  1.34it/s]
1|16633|Loss: 0.7890677452087402:  64%|██████▍   | 16633/25880 [3:24:16<1:52:47,  1.37it/s]
1|16634|Loss: 0.6514881253242493:  64%|██████▍   | 16633/25880 [3:24:17<1:52:47,  1.37it/s]
1|16634|Loss: 0.6514881253242493:  64%|██████▍   | 16634/25880 [3:24:17<1:48:53,  1.42it/s]
1|16635|Loss: 0.8954740762710571:  64%|██████▍   | 16634/25880 [3:24:17<1:48:53,  1.42it/s]
1|16635|Loss: 0.8954740762710571:  64%|██████▍   | 16635/25880 [3:24:18<1:51:45,  1.38it/s]
1|16636|Loss: 0.7986669540405273:  64%|██████▍   | 16635/25880 [3:24:18<1:51:45,  1.38it/s]
1|16636|Loss: 0.7986669540405273:  64%|██████▍   | 16636/25880 [3:24:19<1:55:35,  1.33it/s]
1|16637|Loss: 0.9420202374458313:  64%|██████▍   | 16636/25880 [3:24:19<1:55:35,  1.33it/s]
1|16637|Loss: 0.9420202374458313:  64%|██████▍   | 16637/25880 [3:24:19<1:57:49,  1.31it/s]
1|16638|Loss: 0.8262739777565002:  64%|██████▍   | 16637/25880 [3:24:20<1:57:49,  1.31it/s]
1|16638|Loss: 0.8262739777565002:  64%|██████▍   | 16638/25880 [3:24:20<1:57:06,  1.32it/s]
1|16639|Loss: 0.7446424961090088:  64%|██████▍   | 16638/25880 [3:24:21<1:57:06,  1.32it/s]
1|16639|Loss: 0.7446424961090088:  64%|██████▍   | 16639/25880 [3:24:21<1:59:00,  1.29it/s]
1|16640|Loss: 0.9398245215415955:  64%|██████▍   | 16639/25880 [3:24:21<1:59:00,  1.29it/s]
1|16640|Loss: 0.9398245215415955:  64%|██████▍   | 16640/25880 [3:24:22<1:48:43,  1.42it/s]
1|16641|Loss: 0.7268904447555542:  64%|██████▍   | 16640/25880 [3:24:22<1:48:43,  1.42it/s]
1|16641|Loss: 0.7268904447555542:  64%|██████▍   | 16641/25880 [3:24:22<1:46:22,  1.45it/s]
1|16642|Loss: 0.9251478910446167:  64%|██████▍   | 16641/25880 [3:24:23<1:46:22,  1.45it/s]
1|16642|Loss: 0.9251478910446167:  64%|██████▍   | 16642/25880 [3:24:23<1:53:29,  1.36it/s]
1|16643|Loss: 1.028509497642517:  64%|██████▍   | 16642/25880 [3:24:23<1:53:29,  1.36it/s] 
1|16643|Loss: 1.028509497642517:  64%|██████▍   | 16643/25880 [3:24:24<1:49:28,  1.41it/s]
1|16644|Loss: 0.7563669681549072:  64%|██████▍   | 16643/25880 [3:24:24<1:49:28,  1.41it/s]
1|16644|Loss: 0.7563669681549072:  64%|██████▍   | 16644/25880 [3:24:24<1:52:27,  1.37it/s]
1|16645|Loss: 0.8315339088439941:  64%|██████▍   | 16644/25880 [3:24:25<1:52:27,  1.37it/s]
1|16645|Loss: 0.8315339088439941:  64%|██████▍   | 16645/25880 [3:24:25<1:55:18,  1.33it/s]
1|16646|Loss: 0.8077596426010132:  64%|██████▍   | 16645/25880 [3:24:26<1:55:18,  1.33it/s]
1|16646|Loss: 0.8077596426010132:  64%|██████▍   | 16646/25880 [3:24:26<2:00:20,  1.28it/s]
1|16647|Loss: 0.9043119549751282:  64%|██████▍   | 16646/25880 [3:24:27<2:00:20,  1.28it/s]
1|16647|Loss: 0.9043119549751282:  64%|██████▍   | 16647/25880 [3:24:27<2:04:38,  1.23it/s]
1|16648|Loss: 0.7674362063407898:  64%|██████▍   | 16647/25880 [3:24:27<2:04:38,  1.23it/s]
1|16648|Loss: 0.7674362063407898:  64%|██████▍   | 16648/25880 [3:24:28<1:58:12,  1.30it/s]
1|16649|Loss: 0.8307420015335083:  64%|██████▍   | 16648/25880 [3:24:28<1:58:12,  1.30it/s]
1|16649|Loss: 0.8307420015335083:  64%|██████▍   | 16649/25880 [3:24:29<2:05:26,  1.23it/s]
1|16650|Loss: 0.792031466960907:  64%|██████▍   | 16649/25880 [3:24:29<2:05:26,  1.23it/s] 
1|16650|Loss: 0.792031466960907:  64%|██████▍   | 16650/25880 [3:24:29<2:03:49,  1.24it/s]
1|16651|Loss: 0.8803073167800903:  64%|██████▍   | 16650/25880 [3:24:30<2:03:49,  1.24it/s]
1|16651|Loss: 0.8803073167800903:  64%|██████▍   | 16651/25880 [3:24:30<2:05:32,  1.23it/s]
1|16652|Loss: 0.8021734952926636:  64%|██████▍   | 16651/25880 [3:24:31<2:05:32,  1.23it/s]
1|16652|Loss: 0.8021734952926636:  64%|██████▍   | 16652/25880 [3:24:31<2:05:12,  1.23it/s]
1|16653|Loss: 0.7443360686302185:  64%|██████▍   | 16652/25880 [3:24:31<2:05:12,  1.23it/s]
1|16653|Loss: 0.7443360686302185:  64%|██████▍   | 16653/25880 [3:24:32<2:01:09,  1.27it/s]
1|16654|Loss: 0.7806716561317444:  64%|██████▍   | 16653/25880 [3:24:32<2:01:09,  1.27it/s]
1|16654|Loss: 0.7806716561317444:  64%|██████▍   | 16654/25880 [3:24:33<2:04:54,  1.23it/s]
1|16655|Loss: 0.8281956315040588:  64%|██████▍   | 16654/25880 [3:24:33<2:04:54,  1.23it/s]
1|16655|Loss: 0.8281956315040588:  64%|██████▍   | 16655/25880 [3:24:33<2:02:37,  1.25it/s]
1|16656|Loss: 0.7944623827934265:  64%|██████▍   | 16655/25880 [3:24:34<2:02:37,  1.25it/s]
1|16656|Loss: 0.7944623827934265:  64%|██████▍   | 16656/25880 [3:24:34<1:55:19,  1.33it/s]
1|16657|Loss: 0.9452289938926697:  64%|██████▍   | 16656/25880 [3:24:34<1:55:19,  1.33it/s]
1|16657|Loss: 0.9452289938926697:  64%|██████▍   | 16657/25880 [3:24:35<1:48:20,  1.42it/s]
1|16658|Loss: 0.7706841230392456:  64%|██████▍   | 16657/25880 [3:24:35<1:48:20,  1.42it/s]
1|16658|Loss: 0.7706841230392456:  64%|██████▍   | 16658/25880 [3:24:35<1:44:45,  1.47it/s]
1|16659|Loss: 0.7412790060043335:  64%|██████▍   | 16658/25880 [3:24:36<1:44:45,  1.47it/s]
1|16659|Loss: 0.7412790060043335:  64%|██████▍   | 16659/25880 [3:24:36<1:46:38,  1.44it/s]
1|16660|Loss: 0.8376867771148682:  64%|██████▍   | 16659/25880 [3:24:36<1:46:38,  1.44it/s]
1|16660|Loss: 0.8376867771148682:  64%|██████▍   | 16660/25880 [3:24:37<1:49:04,  1.41it/s]
1|16661|Loss: 1.0022555589675903:  64%|██████▍   | 16660/25880 [3:24:37<1:49:04,  1.41it/s]
1|16661|Loss: 1.0022555589675903:  64%|██████▍   | 16661/25880 [3:24:37<1:40:00,  1.54it/s]
1|16662|Loss: 0.7392394542694092:  64%|██████▍   | 16661/25880 [3:24:37<1:40:00,  1.54it/s]
1|16662|Loss: 0.7392394542694092:  64%|██████▍   | 16662/25880 [3:24:38<1:27:38,  1.75it/s]
1|16663|Loss: 0.7595338821411133:  64%|██████▍   | 16662/25880 [3:24:38<1:27:38,  1.75it/s]
1|16663|Loss: 0.7595338821411133:  64%|██████▍   | 16663/25880 [3:24:38<1:36:23,  1.59it/s]
1|16664|Loss: 0.919626772403717:  64%|██████▍   | 16663/25880 [3:24:39<1:36:23,  1.59it/s] 
1|16664|Loss: 0.919626772403717:  64%|██████▍   | 16664/25880 [3:24:39<1:36:02,  1.60it/s]
1|16665|Loss: 0.9266225099563599:  64%|██████▍   | 16664/25880 [3:24:39<1:36:02,  1.60it/s]
1|16665|Loss: 0.9266225099563599:  64%|██████▍   | 16665/25880 [3:24:39<1:30:18,  1.70it/s]
1|16666|Loss: 0.7772126197814941:  64%|██████▍   | 16665/25880 [3:24:40<1:30:18,  1.70it/s]
1|16666|Loss: 0.7772126197814941:  64%|██████▍   | 16666/25880 [3:24:40<1:34:22,  1.63it/s]
1|16667|Loss: 0.7876254320144653:  64%|██████▍   | 16666/25880 [3:24:41<1:34:22,  1.63it/s]
1|16667|Loss: 0.7876254320144653:  64%|██████▍   | 16667/25880 [3:24:41<1:42:36,  1.50it/s]
1|16668|Loss: 0.7639628052711487:  64%|██████▍   | 16667/25880 [3:24:41<1:42:36,  1.50it/s]
1|16668|Loss: 0.7639628052711487:  64%|██████▍   | 16668/25880 [3:24:42<1:48:47,  1.41it/s]
1|16669|Loss: 0.7348200678825378:  64%|██████▍   | 16668/25880 [3:24:42<1:48:47,  1.41it/s]
1|16669|Loss: 0.7348200678825378:  64%|██████▍   | 16669/25880 [3:24:43<1:50:20,  1.39it/s]
1|16670|Loss: 0.8066440224647522:  64%|██████▍   | 16669/25880 [3:24:43<1:50:20,  1.39it/s]
1|16670|Loss: 0.8066440224647522:  64%|██████▍   | 16670/25880 [3:24:43<1:50:32,  1.39it/s]
1|16671|Loss: 0.808769941329956:  64%|██████▍   | 16670/25880 [3:24:44<1:50:32,  1.39it/s] 
1|16671|Loss: 0.808769941329956:  64%|██████▍   | 16671/25880 [3:24:44<1:45:42,  1.45it/s]
1|16672|Loss: 0.7814124822616577:  64%|██████▍   | 16671/25880 [3:24:44<1:45:42,  1.45it/s]
1|16672|Loss: 0.7814124822616577:  64%|██████▍   | 16672/25880 [3:24:45<1:50:44,  1.39it/s]
1|16673|Loss: 0.9568998217582703:  64%|██████▍   | 16672/25880 [3:24:45<1:50:44,  1.39it/s]
1|16673|Loss: 0.9568998217582703:  64%|██████▍   | 16673/25880 [3:24:45<1:56:21,  1.32it/s]
1|16674|Loss: 0.6419968605041504:  64%|██████▍   | 16673/25880 [3:24:46<1:56:21,  1.32it/s]
1|16674|Loss: 0.6419968605041504:  64%|██████▍   | 16674/25880 [3:24:46<1:56:28,  1.32it/s]
1|16675|Loss: 0.910436749458313:  64%|██████▍   | 16674/25880 [3:24:47<1:56:28,  1.32it/s] 
1|16675|Loss: 0.910436749458313:  64%|██████▍   | 16675/25880 [3:24:47<1:57:50,  1.30it/s]
1|16676|Loss: 0.7157264351844788:  64%|██████▍   | 16675/25880 [3:24:47<1:57:50,  1.30it/s]
1|16676|Loss: 0.7157264351844788:  64%|██████▍   | 16676/25880 [3:24:48<2:01:05,  1.27it/s]
1|16677|Loss: 0.714311957359314:  64%|██████▍   | 16676/25880 [3:24:48<2:01:05,  1.27it/s] 
1|16677|Loss: 0.714311957359314:  64%|██████▍   | 16677/25880 [3:24:49<1:54:09,  1.34it/s]
1|16678|Loss: 0.7857896685600281:  64%|██████▍   | 16677/25880 [3:24:49<1:54:09,  1.34it/s]
1|16678|Loss: 0.7857896685600281:  64%|██████▍   | 16678/25880 [3:24:49<1:48:11,  1.42it/s]
1|16679|Loss: 0.87193363904953:  64%|██████▍   | 16678/25880 [3:24:50<1:48:11,  1.42it/s]  
1|16679|Loss: 0.87193363904953:  64%|██████▍   | 16679/25880 [3:24:50<1:52:59,  1.36it/s]
1|16680|Loss: 0.7590629458427429:  64%|██████▍   | 16679/25880 [3:24:50<1:52:59,  1.36it/s]
1|16680|Loss: 0.7590629458427429:  64%|██████▍   | 16680/25880 [3:24:51<1:59:34,  1.28it/s]
1|16681|Loss: 0.8008696436882019:  64%|██████▍   | 16680/25880 [3:24:51<1:59:34,  1.28it/s]
1|16681|Loss: 0.8008696436882019:  64%|██████▍   | 16681/25880 [3:24:52<1:55:43,  1.32it/s]
1|16682|Loss: 0.9047108888626099:  64%|██████▍   | 16681/25880 [3:24:52<1:55:43,  1.32it/s]
1|16682|Loss: 0.9047108888626099:  64%|██████▍   | 16682/25880 [3:24:52<1:46:49,  1.44it/s]
1|16683|Loss: 0.94162517786026:  64%|██████▍   | 16682/25880 [3:24:52<1:46:49,  1.44it/s]  
1|16683|Loss: 0.94162517786026:  64%|██████▍   | 16683/25880 [3:24:53<1:40:02,  1.53it/s]
1|16684|Loss: 0.990912139415741:  64%|██████▍   | 16683/25880 [3:24:53<1:40:02,  1.53it/s]
1|16684|Loss: 0.990912139415741:  64%|██████▍   | 16684/25880 [3:24:53<1:42:17,  1.50it/s]
1|16685|Loss: 0.9327581524848938:  64%|██████▍   | 16684/25880 [3:24:54<1:42:17,  1.50it/s]
1|16685|Loss: 0.9327581524848938:  64%|██████▍   | 16685/25880 [3:24:54<1:38:11,  1.56it/s]
1|16686|Loss: 0.7633373737335205:  64%|██████▍   | 16685/25880 [3:24:54<1:38:11,  1.56it/s]
1|16686|Loss: 0.7633373737335205:  64%|██████▍   | 16686/25880 [3:24:55<1:40:11,  1.53it/s]
1|16687|Loss: 0.925519585609436:  64%|██████▍   | 16686/25880 [3:24:55<1:40:11,  1.53it/s] 
1|16687|Loss: 0.925519585609436:  64%|██████▍   | 16687/25880 [3:24:55<1:42:16,  1.50it/s]
1|16688|Loss: 0.982549250125885:  64%|██████▍   | 16687/25880 [3:24:56<1:42:16,  1.50it/s]
1|16688|Loss: 0.982549250125885:  64%|██████▍   | 16688/25880 [3:24:56<1:44:50,  1.46it/s]
1|16689|Loss: 0.7850801348686218:  64%|██████▍   | 16688/25880 [3:24:56<1:44:50,  1.46it/s]
1|16689|Loss: 0.7850801348686218:  64%|██████▍   | 16689/25880 [3:24:57<1:46:57,  1.43it/s]
1|16690|Loss: 0.822528064250946:  64%|██████▍   | 16689/25880 [3:24:57<1:46:57,  1.43it/s] 
1|16690|Loss: 0.822528064250946:  64%|██████▍   | 16690/25880 [3:24:57<1:47:06,  1.43it/s]
1|16691|Loss: 0.6958532333374023:  64%|██████▍   | 16690/25880 [3:24:58<1:47:06,  1.43it/s]
1|16691|Loss: 0.6958532333374023:  64%|██████▍   | 16691/25880 [3:24:58<1:48:13,  1.42it/s]
1|16692|Loss: 0.7646079659461975:  64%|██████▍   | 16691/25880 [3:24:59<1:48:13,  1.42it/s]
1|16692|Loss: 0.7646079659461975:  64%|██████▍   | 16692/25880 [3:24:59<1:49:43,  1.40it/s]
1|16693|Loss: 0.9391027092933655:  64%|██████▍   | 16692/25880 [3:24:59<1:49:43,  1.40it/s]
1|16693|Loss: 0.9391027092933655:  65%|██████▍   | 16693/25880 [3:25:00<1:46:32,  1.44it/s]
1|16694|Loss: 0.7437511086463928:  65%|██████▍   | 16693/25880 [3:25:00<1:46:32,  1.44it/s]
1|16694|Loss: 0.7437511086463928:  65%|██████▍   | 16694/25880 [3:25:00<1:51:56,  1.37it/s]
1|16695|Loss: 0.7789838910102844:  65%|██████▍   | 16694/25880 [3:25:01<1:51:56,  1.37it/s]
1|16695|Loss: 0.7789838910102844:  65%|██████▍   | 16695/25880 [3:25:01<1:52:12,  1.36it/s]
1|16696|Loss: 1.023812174797058:  65%|██████▍   | 16695/25880 [3:25:01<1:52:12,  1.36it/s] 
1|16696|Loss: 1.023812174797058:  65%|██████▍   | 16696/25880 [3:25:02<1:48:22,  1.41it/s]
1|16697|Loss: 0.861825168132782:  65%|██████▍   | 16696/25880 [3:25:02<1:48:22,  1.41it/s]
1|16697|Loss: 0.861825168132782:  65%|██████▍   | 16697/25880 [3:25:02<1:45:21,  1.45it/s]
1|16698|Loss: 0.8034922480583191:  65%|██████▍   | 16697/25880 [3:25:03<1:45:21,  1.45it/s]
1|16698|Loss: 0.8034922480583191:  65%|██████▍   | 16698/25880 [3:25:03<1:55:03,  1.33it/s]
1|16699|Loss: 0.9400200247764587:  65%|██████▍   | 16698/25880 [3:25:04<1:55:03,  1.33it/s]
1|16699|Loss: 0.9400200247764587:  65%|██████▍   | 16699/25880 [3:25:04<2:03:23,  1.24it/s]
1|16700|Loss: 0.8380867838859558:  65%|██████▍   | 16699/25880 [3:25:05<2:03:23,  1.24it/s]
1|16700|Loss: 0.8380867838859558:  65%|██████▍   | 16700/25880 [3:25:05<2:02:10,  1.25it/s]
1|16701|Loss: 0.9784145355224609:  65%|██████▍   | 16700/25880 [3:25:05<2:02:10,  1.25it/s]
1|16701|Loss: 0.9784145355224609:  65%|██████▍   | 16701/25880 [3:25:06<1:55:56,  1.32it/s]
1|16702|Loss: 0.8192797899246216:  65%|██████▍   | 16701/25880 [3:25:06<1:55:56,  1.32it/s]
1|16702|Loss: 0.8192797899246216:  65%|██████▍   | 16702/25880 [3:25:06<1:54:17,  1.34it/s]
1|16703|Loss: 0.8961050510406494:  65%|██████▍   | 16702/25880 [3:25:07<1:54:17,  1.34it/s]
1|16703|Loss: 0.8961050510406494:  65%|██████▍   | 16703/25880 [3:25:07<1:48:58,  1.40it/s]
1|16704|Loss: 0.8604632019996643:  65%|██████▍   | 16703/25880 [3:25:07<1:48:58,  1.40it/s]
1|16704|Loss: 0.8604632019996643:  65%|██████▍   | 16704/25880 [3:25:08<1:48:35,  1.41it/s]
1|16705|Loss: 0.8564956784248352:  65%|██████▍   | 16704/25880 [3:25:08<1:48:35,  1.41it/s]
1|16705|Loss: 0.8564956784248352:  65%|██████▍   | 16705/25880 [3:25:08<1:43:56,  1.47it/s]
1|16706|Loss: 0.7604206800460815:  65%|██████▍   | 16705/25880 [3:25:09<1:43:56,  1.47it/s]
1|16706|Loss: 0.7604206800460815:  65%|██████▍   | 16706/25880 [3:25:09<1:54:08,  1.34it/s]
1|16707|Loss: 0.9364507794380188:  65%|██████▍   | 16706/25880 [3:25:10<1:54:08,  1.34it/s]
1|16707|Loss: 0.9364507794380188:  65%|██████▍   | 16707/25880 [3:25:10<1:52:58,  1.35it/s]
1|16708|Loss: 0.8202453851699829:  65%|██████▍   | 16707/25880 [3:25:10<1:52:58,  1.35it/s]
1|16708|Loss: 0.8202453851699829:  65%|██████▍   | 16708/25880 [3:25:11<1:51:56,  1.37it/s]
1|16709|Loss: 0.8863977789878845:  65%|██████▍   | 16708/25880 [3:25:11<1:51:56,  1.37it/s]
1|16709|Loss: 0.8863977789878845:  65%|██████▍   | 16709/25880 [3:25:11<1:46:17,  1.44it/s]
1|16710|Loss: 0.7896666526794434:  65%|██████▍   | 16709/25880 [3:25:12<1:46:17,  1.44it/s]
1|16710|Loss: 0.7896666526794434:  65%|██████▍   | 16710/25880 [3:25:12<1:43:07,  1.48it/s]
1|16711|Loss: 0.9537422060966492:  65%|██████▍   | 16710/25880 [3:25:12<1:43:07,  1.48it/s]
1|16711|Loss: 0.9537422060966492:  65%|██████▍   | 16711/25880 [3:25:13<1:44:57,  1.46it/s]
1|16712|Loss: 0.8235751986503601:  65%|██████▍   | 16711/25880 [3:25:13<1:44:57,  1.46it/s]
1|16712|Loss: 0.8235751986503601:  65%|██████▍   | 16712/25880 [3:25:13<1:51:55,  1.37it/s]
1|16713|Loss: 0.8333843946456909:  65%|██████▍   | 16712/25880 [3:25:14<1:51:55,  1.37it/s]
1|16713|Loss: 0.8333843946456909:  65%|██████▍   | 16713/25880 [3:25:14<1:46:00,  1.44it/s]
1|16714|Loss: 0.7663866877555847:  65%|██████▍   | 16713/25880 [3:25:14<1:46:00,  1.44it/s]
1|16714|Loss: 0.7663866877555847:  65%|██████▍   | 16714/25880 [3:25:15<1:46:05,  1.44it/s]
1|16715|Loss: 0.7378632426261902:  65%|██████▍   | 16714/25880 [3:25:15<1:46:05,  1.44it/s]
1|16715|Loss: 0.7378632426261902:  65%|██████▍   | 16715/25880 [3:25:15<1:42:36,  1.49it/s]
1|16716|Loss: 0.8586753010749817:  65%|██████▍   | 16715/25880 [3:25:16<1:42:36,  1.49it/s]
1|16716|Loss: 0.8586753010749817:  65%|██████▍   | 16716/25880 [3:25:16<1:49:11,  1.40it/s]
1|16717|Loss: 0.8963616490364075:  65%|██████▍   | 16716/25880 [3:25:17<1:49:11,  1.40it/s]
1|16717|Loss: 0.8963616490364075:  65%|██████▍   | 16717/25880 [3:25:17<1:54:07,  1.34it/s]
1|16718|Loss: 0.7944577932357788:  65%|██████▍   | 16717/25880 [3:25:17<1:54:07,  1.34it/s]
1|16718|Loss: 0.7944577932357788:  65%|██████▍   | 16718/25880 [3:25:18<1:56:03,  1.32it/s]
1|16719|Loss: 0.7761638164520264:  65%|██████▍   | 16718/25880 [3:25:18<1:56:03,  1.32it/s]
1|16719|Loss: 0.7761638164520264:  65%|██████▍   | 16719/25880 [3:25:19<1:54:21,  1.34it/s]
1|16720|Loss: 0.7149813175201416:  65%|██████▍   | 16719/25880 [3:25:19<1:54:21,  1.34it/s]
1|16720|Loss: 0.7149813175201416:  65%|██████▍   | 16720/25880 [3:25:20<2:04:46,  1.22it/s]
1|16721|Loss: 0.9320977330207825:  65%|██████▍   | 16720/25880 [3:25:20<2:04:46,  1.22it/s]
1|16721|Loss: 0.9320977330207825:  65%|██████▍   | 16721/25880 [3:25:20<2:08:34,  1.19it/s]
1|16722|Loss: 0.8257171511650085:  65%|██████▍   | 16721/25880 [3:25:21<2:08:34,  1.19it/s]
1|16722|Loss: 0.8257171511650085:  65%|██████▍   | 16722/25880 [3:25:21<2:05:27,  1.22it/s]
1|16723|Loss: 0.8730226755142212:  65%|██████▍   | 16722/25880 [3:25:22<2:05:27,  1.22it/s]
1|16723|Loss: 0.8730226755142212:  65%|██████▍   | 16723/25880 [3:25:22<1:55:12,  1.32it/s]
1|16724|Loss: 0.9682121872901917:  65%|██████▍   | 16723/25880 [3:25:22<1:55:12,  1.32it/s]
1|16724|Loss: 0.9682121872901917:  65%|██████▍   | 16724/25880 [3:25:22<1:49:09,  1.40it/s]
1|16725|Loss: 0.8087335824966431:  65%|██████▍   | 16724/25880 [3:25:23<1:49:09,  1.40it/s]
1|16725|Loss: 0.8087335824966431:  65%|██████▍   | 16725/25880 [3:25:23<1:48:51,  1.40it/s]
1|16726|Loss: 0.7932644486427307:  65%|██████▍   | 16725/25880 [3:25:23<1:48:51,  1.40it/s]
1|16726|Loss: 0.7932644486427307:  65%|██████▍   | 16726/25880 [3:25:24<1:44:09,  1.46it/s]
1|16727|Loss: 0.8529388904571533:  65%|██████▍   | 16726/25880 [3:25:24<1:44:09,  1.46it/s]
1|16727|Loss: 0.8529388904571533:  65%|██████▍   | 16727/25880 [3:25:24<1:40:32,  1.52it/s]
1|16728|Loss: 0.7975956201553345:  65%|██████▍   | 16727/25880 [3:25:25<1:40:32,  1.52it/s]
1|16728|Loss: 0.7975956201553345:  65%|██████▍   | 16728/25880 [3:25:25<1:41:38,  1.50it/s]
1|16729|Loss: 0.8425206542015076:  65%|██████▍   | 16728/25880 [3:25:25<1:41:38,  1.50it/s]
1|16729|Loss: 0.8425206542015076:  65%|██████▍   | 16729/25880 [3:25:26<1:43:06,  1.48it/s]
1|16730|Loss: 0.7694272994995117:  65%|██████▍   | 16729/25880 [3:25:26<1:43:06,  1.48it/s]
1|16730|Loss: 0.7694272994995117:  65%|██████▍   | 16730/25880 [3:25:26<1:44:04,  1.47it/s]
1|16731|Loss: 0.7775257229804993:  65%|██████▍   | 16730/25880 [3:25:27<1:44:04,  1.47it/s]
1|16731|Loss: 0.7775257229804993:  65%|██████▍   | 16731/25880 [3:25:27<1:49:42,  1.39it/s]
1|16732|Loss: 0.8643954396247864:  65%|██████▍   | 16731/25880 [3:25:28<1:49:42,  1.39it/s]
1|16732|Loss: 0.8643954396247864:  65%|██████▍   | 16732/25880 [3:25:28<1:51:01,  1.37it/s]
1|16733|Loss: 0.8608515858650208:  65%|██████▍   | 16732/25880 [3:25:28<1:51:01,  1.37it/s]
1|16733|Loss: 0.8608515858650208:  65%|██████▍   | 16733/25880 [3:25:29<1:44:22,  1.46it/s]
1|16734|Loss: 0.7598478198051453:  65%|██████▍   | 16733/25880 [3:25:29<1:44:22,  1.46it/s]
1|16734|Loss: 0.7598478198051453:  65%|██████▍   | 16734/25880 [3:25:29<1:45:10,  1.45it/s]
1|16735|Loss: 0.7739184498786926:  65%|██████▍   | 16734/25880 [3:25:30<1:45:10,  1.45it/s]
1|16735|Loss: 0.7739184498786926:  65%|██████▍   | 16735/25880 [3:25:30<1:47:28,  1.42it/s]
1|16736|Loss: 0.6566020846366882:  65%|██████▍   | 16735/25880 [3:25:30<1:47:28,  1.42it/s]
1|16736|Loss: 0.6566020846366882:  65%|██████▍   | 16736/25880 [3:25:31<1:53:13,  1.35it/s]
1|16737|Loss: 0.8555041551589966:  65%|██████▍   | 16736/25880 [3:25:31<1:53:13,  1.35it/s]
1|16737|Loss: 0.8555041551589966:  65%|██████▍   | 16737/25880 [3:25:31<1:49:06,  1.40it/s]
1|16738|Loss: 0.808948814868927:  65%|██████▍   | 16737/25880 [3:25:32<1:49:06,  1.40it/s] 
1|16738|Loss: 0.808948814868927:  65%|██████▍   | 16738/25880 [3:25:32<1:44:01,  1.46it/s]
1|16739|Loss: 0.8065478801727295:  65%|██████▍   | 16738/25880 [3:25:32<1:44:01,  1.46it/s]
1|16739|Loss: 0.8065478801727295:  65%|██████▍   | 16739/25880 [3:25:33<1:35:14,  1.60it/s]
1|16740|Loss: 0.7850928902626038:  65%|██████▍   | 16739/25880 [3:25:33<1:35:14,  1.60it/s]
1|16740|Loss: 0.7850928902626038:  65%|██████▍   | 16740/25880 [3:25:33<1:37:47,  1.56it/s]
1|16741|Loss: 0.8785642385482788:  65%|██████▍   | 16740/25880 [3:25:34<1:37:47,  1.56it/s]
1|16741|Loss: 0.8785642385482788:  65%|██████▍   | 16741/25880 [3:25:34<1:38:17,  1.55it/s]
1|16742|Loss: 0.9708030819892883:  65%|██████▍   | 16741/25880 [3:25:34<1:38:17,  1.55it/s]
1|16742|Loss: 0.9708030819892883:  65%|██████▍   | 16742/25880 [3:25:35<1:46:47,  1.43it/s]
1|16743|Loss: 0.9249058961868286:  65%|██████▍   | 16742/25880 [3:25:35<1:46:47,  1.43it/s]
1|16743|Loss: 0.9249058961868286:  65%|██████▍   | 16743/25880 [3:25:35<1:42:35,  1.48it/s]
1|16744|Loss: 0.8687451481819153:  65%|██████▍   | 16743/25880 [3:25:36<1:42:35,  1.48it/s]
1|16744|Loss: 0.8687451481819153:  65%|██████▍   | 16744/25880 [3:25:36<1:42:22,  1.49it/s]
1|16745|Loss: 0.8685257434844971:  65%|██████▍   | 16744/25880 [3:25:36<1:42:22,  1.49it/s]
1|16745|Loss: 0.8685257434844971:  65%|██████▍   | 16745/25880 [3:25:37<1:53:40,  1.34it/s]
1|16746|Loss: 0.9117287397384644:  65%|██████▍   | 16745/25880 [3:25:37<1:53:40,  1.34it/s]
1|16746|Loss: 0.9117287397384644:  65%|██████▍   | 16746/25880 [3:25:38<1:55:48,  1.31it/s]
1|16747|Loss: 0.7938756346702576:  65%|██████▍   | 16746/25880 [3:25:38<1:55:48,  1.31it/s]
1|16747|Loss: 0.7938756346702576:  65%|██████▍   | 16747/25880 [3:25:39<2:00:07,  1.27it/s]
1|16748|Loss: 0.7592728734016418:  65%|██████▍   | 16747/25880 [3:25:39<2:00:07,  1.27it/s]
1|16748|Loss: 0.7592728734016418:  65%|██████▍   | 16748/25880 [3:25:39<1:59:01,  1.28it/s]
1|16749|Loss: 0.8337122201919556:  65%|██████▍   | 16748/25880 [3:25:40<1:59:01,  1.28it/s]
1|16749|Loss: 0.8337122201919556:  65%|██████▍   | 16749/25880 [3:25:40<1:52:33,  1.35it/s]
1|16750|Loss: 0.8354653716087341:  65%|██████▍   | 16749/25880 [3:25:40<1:52:33,  1.35it/s]
1|16750|Loss: 0.8354653716087341:  65%|██████▍   | 16750/25880 [3:25:41<1:51:05,  1.37it/s]
1|16751|Loss: 0.7836171984672546:  65%|██████▍   | 16750/25880 [3:25:41<1:51:05,  1.37it/s]
1|16751|Loss: 0.7836171984672546:  65%|██████▍   | 16751/25880 [3:25:41<1:53:26,  1.34it/s]
1|16752|Loss: 0.9220221638679504:  65%|██████▍   | 16751/25880 [3:25:42<1:53:26,  1.34it/s]
1|16752|Loss: 0.9220221638679504:  65%|██████▍   | 16752/25880 [3:25:42<1:49:58,  1.38it/s]
1|16753|Loss: 0.8914480805397034:  65%|██████▍   | 16752/25880 [3:25:43<1:49:58,  1.38it/s]
1|16753|Loss: 0.8914480805397034:  65%|██████▍   | 16753/25880 [3:25:43<1:50:02,  1.38it/s]
1|16754|Loss: 0.8406200408935547:  65%|██████▍   | 16753/25880 [3:25:43<1:50:02,  1.38it/s]
1|16754|Loss: 0.8406200408935547:  65%|██████▍   | 16754/25880 [3:25:44<1:53:18,  1.34it/s]
1|16755|Loss: 0.7834012508392334:  65%|██████▍   | 16754/25880 [3:25:44<1:53:18,  1.34it/s]
1|16755|Loss: 0.7834012508392334:  65%|██████▍   | 16755/25880 [3:25:44<1:50:00,  1.38it/s]
1|16756|Loss: 0.789334237575531:  65%|██████▍   | 16755/25880 [3:25:45<1:50:00,  1.38it/s] 
1|16756|Loss: 0.789334237575531:  65%|██████▍   | 16756/25880 [3:25:45<1:49:32,  1.39it/s]
1|16757|Loss: 0.7979997992515564:  65%|██████▍   | 16756/25880 [3:25:45<1:49:32,  1.39it/s]
1|16757|Loss: 0.7979997992515564:  65%|██████▍   | 16757/25880 [3:25:46<1:52:27,  1.35it/s]
1|16758|Loss: 0.87776118516922:  65%|██████▍   | 16757/25880 [3:25:46<1:52:27,  1.35it/s]  
1|16758|Loss: 0.87776118516922:  65%|██████▍   | 16758/25880 [3:25:47<1:52:18,  1.35it/s]
1|16759|Loss: 0.9028829336166382:  65%|██████▍   | 16758/25880 [3:25:47<1:52:18,  1.35it/s]
1|16759|Loss: 0.9028829336166382:  65%|██████▍   | 16759/25880 [3:25:47<1:48:26,  1.40it/s]
1|16760|Loss: 0.9185596704483032:  65%|██████▍   | 16759/25880 [3:25:48<1:48:26,  1.40it/s]
1|16760|Loss: 0.9185596704483032:  65%|██████▍   | 16760/25880 [3:25:48<1:54:06,  1.33it/s]
1|16761|Loss: 0.9684478044509888:  65%|██████▍   | 16760/25880 [3:25:48<1:54:06,  1.33it/s]
1|16761|Loss: 0.9684478044509888:  65%|██████▍   | 16761/25880 [3:25:49<1:49:38,  1.39it/s]
1|16762|Loss: 0.8130838871002197:  65%|██████▍   | 16761/25880 [3:25:49<1:49:38,  1.39it/s]
1|16762|Loss: 0.8130838871002197:  65%|██████▍   | 16762/25880 [3:25:50<1:52:21,  1.35it/s]
1|16763|Loss: 0.7117685675621033:  65%|██████▍   | 16762/25880 [3:25:50<1:52:21,  1.35it/s]
1|16763|Loss: 0.7117685675621033:  65%|██████▍   | 16763/25880 [3:25:50<1:59:36,  1.27it/s]
1|16764|Loss: 0.8213403820991516:  65%|██████▍   | 16763/25880 [3:25:51<1:59:36,  1.27it/s]
1|16764|Loss: 0.8213403820991516:  65%|██████▍   | 16764/25880 [3:25:51<2:03:27,  1.23it/s]
1|16765|Loss: 0.9269763827323914:  65%|██████▍   | 16764/25880 [3:25:52<2:03:27,  1.23it/s]
1|16765|Loss: 0.9269763827323914:  65%|██████▍   | 16765/25880 [3:25:52<2:03:39,  1.23it/s]
1|16766|Loss: 0.815867006778717:  65%|██████▍   | 16765/25880 [3:25:53<2:03:39,  1.23it/s] 
1|16766|Loss: 0.815867006778717:  65%|██████▍   | 16766/25880 [3:25:53<2:07:29,  1.19it/s]
1|16767|Loss: 0.8029151558876038:  65%|██████▍   | 16766/25880 [3:25:53<2:07:29,  1.19it/s]
1|16767|Loss: 0.8029151558876038:  65%|██████▍   | 16767/25880 [3:25:54<1:58:58,  1.28it/s]
1|16768|Loss: 0.7814009785652161:  65%|██████▍   | 16767/25880 [3:25:54<1:58:58,  1.28it/s]
1|16768|Loss: 0.7814009785652161:  65%|██████▍   | 16768/25880 [3:25:54<1:56:01,  1.31it/s]
1|16769|Loss: 0.7497852444648743:  65%|██████▍   | 16768/25880 [3:25:55<1:56:01,  1.31it/s]
1|16769|Loss: 0.7497852444648743:  65%|██████▍   | 16769/25880 [3:25:55<1:51:44,  1.36it/s]
1|16770|Loss: 0.8888066411018372:  65%|██████▍   | 16769/25880 [3:25:55<1:51:44,  1.36it/s]
1|16770|Loss: 0.8888066411018372:  65%|██████▍   | 16770/25880 [3:25:56<1:46:28,  1.43it/s]
1|16771|Loss: 0.8177583813667297:  65%|██████▍   | 16770/25880 [3:25:56<1:46:28,  1.43it/s]
1|16771|Loss: 0.8177583813667297:  65%|██████▍   | 16771/25880 [3:25:56<1:45:53,  1.43it/s]
1|16772|Loss: 0.7828699350357056:  65%|██████▍   | 16771/25880 [3:25:57<1:45:53,  1.43it/s]
1|16772|Loss: 0.7828699350357056:  65%|██████▍   | 16772/25880 [3:25:57<1:47:12,  1.42it/s]
1|16773|Loss: 0.8825696110725403:  65%|██████▍   | 16772/25880 [3:25:57<1:47:12,  1.42it/s]
1|16773|Loss: 0.8825696110725403:  65%|██████▍   | 16773/25880 [3:25:58<1:41:58,  1.49it/s]
1|16774|Loss: 0.9073702692985535:  65%|██████▍   | 16773/25880 [3:25:58<1:41:58,  1.49it/s]
1|16774|Loss: 0.9073702692985535:  65%|██████▍   | 16774/25880 [3:25:58<1:46:19,  1.43it/s]
1|16775|Loss: 0.7811885476112366:  65%|██████▍   | 16774/25880 [3:25:59<1:46:19,  1.43it/s]
1|16775|Loss: 0.7811885476112366:  65%|██████▍   | 16775/25880 [3:25:59<1:48:38,  1.40it/s]
1|16776|Loss: 0.86505526304245:  65%|██████▍   | 16775/25880 [3:26:00<1:48:38,  1.40it/s]  
1|16776|Loss: 0.86505526304245:  65%|██████▍   | 16776/25880 [3:26:00<1:51:49,  1.36it/s]
1|16777|Loss: 0.836581289768219:  65%|██████▍   | 16776/25880 [3:26:00<1:51:49,  1.36it/s]
1|16777|Loss: 0.836581289768219:  65%|██████▍   | 16777/25880 [3:26:01<1:55:31,  1.31it/s]
1|16778|Loss: 0.792176365852356:  65%|██████▍   | 16777/25880 [3:26:01<1:55:31,  1.31it/s]
1|16778|Loss: 0.792176365852356:  65%|██████▍   | 16778/25880 [3:26:02<1:54:04,  1.33it/s]
1|16779|Loss: 0.872341513633728:  65%|██████▍   | 16778/25880 [3:26:02<1:54:04,  1.33it/s]
1|16779|Loss: 0.872341513633728:  65%|██████▍   | 16779/25880 [3:26:02<1:52:49,  1.34it/s]
1|16780|Loss: 0.811021089553833:  65%|██████▍   | 16779/25880 [3:26:03<1:52:49,  1.34it/s]
1|16780|Loss: 0.811021089553833:  65%|██████▍   | 16780/25880 [3:26:03<1:52:28,  1.35it/s]
1|16781|Loss: 0.673742949962616:  65%|██████▍   | 16780/25880 [3:26:03<1:52:28,  1.35it/s]
1|16781|Loss: 0.673742949962616:  65%|██████▍   | 16781/25880 [3:26:04<1:52:00,  1.35it/s]
1|16782|Loss: 0.7005416750907898:  65%|██████▍   | 16781/25880 [3:26:04<1:52:00,  1.35it/s]
1|16782|Loss: 0.7005416750907898:  65%|██████▍   | 16782/25880 [3:26:04<1:52:03,  1.35it/s]
1|16783|Loss: 0.7494228482246399:  65%|██████▍   | 16782/25880 [3:26:05<1:52:03,  1.35it/s]
1|16783|Loss: 0.7494228482246399:  65%|██████▍   | 16783/25880 [3:26:05<1:51:18,  1.36it/s]
1|16784|Loss: 0.7454447746276855:  65%|██████▍   | 16783/25880 [3:26:06<1:51:18,  1.36it/s]
1|16784|Loss: 0.7454447746276855:  65%|██████▍   | 16784/25880 [3:26:06<1:53:30,  1.34it/s]
1|16785|Loss: 0.7029130458831787:  65%|██████▍   | 16784/25880 [3:26:06<1:53:30,  1.34it/s]
1|16785|Loss: 0.7029130458831787:  65%|██████▍   | 16785/25880 [3:26:07<1:48:50,  1.39it/s]
1|16786|Loss: 0.8585764169692993:  65%|██████▍   | 16785/25880 [3:26:07<1:48:50,  1.39it/s]
1|16786|Loss: 0.8585764169692993:  65%|██████▍   | 16786/25880 [3:26:07<1:50:27,  1.37it/s]
1|16787|Loss: 0.9030422568321228:  65%|██████▍   | 16786/25880 [3:26:08<1:50:27,  1.37it/s]
1|16787|Loss: 0.9030422568321228:  65%|██████▍   | 16787/25880 [3:26:08<1:55:34,  1.31it/s]
1|16788|Loss: 0.8510065078735352:  65%|██████▍   | 16787/25880 [3:26:09<1:55:34,  1.31it/s]
1|16788|Loss: 0.8510065078735352:  65%|██████▍   | 16788/25880 [3:26:09<1:59:48,  1.26it/s]
1|16789|Loss: 0.8614127039909363:  65%|██████▍   | 16788/25880 [3:26:10<1:59:48,  1.26it/s]
1|16789|Loss: 0.8614127039909363:  65%|██████▍   | 16789/25880 [3:26:10<2:01:50,  1.24it/s]
1|16790|Loss: 0.7565680146217346:  65%|██████▍   | 16789/25880 [3:26:10<2:01:50,  1.24it/s]
1|16790|Loss: 0.7565680146217346:  65%|██████▍   | 16790/25880 [3:26:10<1:51:53,  1.35it/s]
1|16791|Loss: 0.7519965767860413:  65%|██████▍   | 16790/25880 [3:26:11<1:51:53,  1.35it/s]
1|16791|Loss: 0.7519965767860413:  65%|██████▍   | 16791/25880 [3:26:11<1:56:26,  1.30it/s]
1|16792|Loss: 0.8444342613220215:  65%|██████▍   | 16791/25880 [3:26:12<1:56:26,  1.30it/s]
1|16792|Loss: 0.8444342613220215:  65%|██████▍   | 16792/25880 [3:26:12<2:00:01,  1.26it/s]
1|16793|Loss: 0.7062259316444397:  65%|██████▍   | 16792/25880 [3:26:13<2:00:01,  1.26it/s]
1|16793|Loss: 0.7062259316444397:  65%|██████▍   | 16793/25880 [3:26:13<1:54:03,  1.33it/s]
1|16794|Loss: 0.8106396794319153:  65%|██████▍   | 16793/25880 [3:26:13<1:54:03,  1.33it/s]
1|16794|Loss: 0.8106396794319153:  65%|██████▍   | 16794/25880 [3:26:14<1:54:37,  1.32it/s]
1|16795|Loss: 0.9144592881202698:  65%|██████▍   | 16794/25880 [3:26:14<1:54:37,  1.32it/s]
1|16795|Loss: 0.9144592881202698:  65%|██████▍   | 16795/25880 [3:26:14<1:57:27,  1.29it/s]
1|16796|Loss: 0.9389124512672424:  65%|██████▍   | 16795/25880 [3:26:15<1:57:27,  1.29it/s]
1|16796|Loss: 0.9389124512672424:  65%|██████▍   | 16796/25880 [3:26:15<1:49:44,  1.38it/s]
1|16797|Loss: 0.8803249001502991:  65%|██████▍   | 16796/25880 [3:26:15<1:49:44,  1.38it/s]
1|16797|Loss: 0.8803249001502991:  65%|██████▍   | 16797/25880 [3:26:16<1:48:21,  1.40it/s]
1|16798|Loss: 0.7537341117858887:  65%|██████▍   | 16797/25880 [3:26:16<1:48:21,  1.40it/s]
1|16798|Loss: 0.7537341117858887:  65%|██████▍   | 16798/25880 [3:26:17<1:55:50,  1.31it/s]
1|16799|Loss: 0.9783189296722412:  65%|██████▍   | 16798/25880 [3:26:17<1:55:50,  1.31it/s]
1|16799|Loss: 0.9783189296722412:  65%|██████▍   | 16799/25880 [3:26:17<1:58:55,  1.27it/s]
1|16800|Loss: 0.8448848724365234:  65%|██████▍   | 16799/25880 [3:26:18<1:58:55,  1.27it/s]
1|16800|Loss: 0.8448848724365234:  65%|██████▍   | 16800/25880 [3:26:18<2:00:59,  1.25it/s]
1|16801|Loss: 0.8375231623649597:  65%|██████▍   | 16800/25880 [3:26:19<2:00:59,  1.25it/s]
1|16801|Loss: 0.8375231623649597:  65%|██████▍   | 16801/25880 [3:26:19<1:55:31,  1.31it/s]
1|16802|Loss: 0.9731969237327576:  65%|██████▍   | 16801/25880 [3:26:19<1:55:31,  1.31it/s]
1|16802|Loss: 0.9731969237327576:  65%|██████▍   | 16802/25880 [3:26:20<1:50:07,  1.37it/s]
1|16803|Loss: 0.6865994930267334:  65%|██████▍   | 16802/25880 [3:26:20<1:50:07,  1.37it/s]
1|16803|Loss: 0.6865994930267334:  65%|██████▍   | 16803/25880 [3:26:21<1:59:55,  1.26it/s]
1|16804|Loss: 0.9357393980026245:  65%|██████▍   | 16803/25880 [3:26:21<1:59:55,  1.26it/s]
1|16804|Loss: 0.9357393980026245:  65%|██████▍   | 16804/25880 [3:26:21<2:04:55,  1.21it/s]
1|16805|Loss: 0.7476939558982849:  65%|██████▍   | 16804/25880 [3:26:22<2:04:55,  1.21it/s]
1|16805|Loss: 0.7476939558982849:  65%|██████▍   | 16805/25880 [3:26:22<1:57:53,  1.28it/s]
1|16806|Loss: 0.788862943649292:  65%|██████▍   | 16805/25880 [3:26:22<1:57:53,  1.28it/s] 
1|16806|Loss: 0.788862943649292:  65%|██████▍   | 16806/25880 [3:26:23<1:49:27,  1.38it/s]
1|16807|Loss: 0.879883885383606:  65%|██████▍   | 16806/25880 [3:26:23<1:49:27,  1.38it/s]
1|16807|Loss: 0.879883885383606:  65%|██████▍   | 16807/25880 [3:26:23<1:44:15,  1.45it/s]
1|16808|Loss: 0.8057101368904114:  65%|██████▍   | 16807/25880 [3:26:24<1:44:15,  1.45it/s]
1|16808|Loss: 0.8057101368904114:  65%|██████▍   | 16808/25880 [3:26:24<1:45:44,  1.43it/s]
1|16809|Loss: 0.817057192325592:  65%|██████▍   | 16808/25880 [3:26:24<1:45:44,  1.43it/s] 
1|16809|Loss: 0.817057192325592:  65%|██████▍   | 16809/25880 [3:26:25<1:50:58,  1.36it/s]
1|16810|Loss: 0.7792090177536011:  65%|██████▍   | 16809/25880 [3:26:25<1:50:58,  1.36it/s]
1|16810|Loss: 0.7792090177536011:  65%|██████▍   | 16810/25880 [3:26:26<1:58:20,  1.28it/s]
1|16811|Loss: 0.7483730912208557:  65%|██████▍   | 16810/25880 [3:26:26<1:58:20,  1.28it/s]
1|16811|Loss: 0.7483730912208557:  65%|██████▍   | 16811/25880 [3:26:26<1:54:21,  1.32it/s]
1|16812|Loss: 0.8331537246704102:  65%|██████▍   | 16811/25880 [3:26:27<1:54:21,  1.32it/s]
1|16812|Loss: 0.8331537246704102:  65%|██████▍   | 16812/25880 [3:26:27<2:00:57,  1.25it/s]
1|16813|Loss: 0.9279839992523193:  65%|██████▍   | 16812/25880 [3:26:28<2:00:57,  1.25it/s]
1|16813|Loss: 0.9279839992523193:  65%|██████▍   | 16813/25880 [3:26:28<2:03:50,  1.22it/s]
1|16814|Loss: 0.8559717535972595:  65%|██████▍   | 16813/25880 [3:26:29<2:03:50,  1.22it/s]
1|16814|Loss: 0.8559717535972595:  65%|██████▍   | 16814/25880 [3:26:29<2:00:24,  1.25it/s]
1|16815|Loss: 0.7949684262275696:  65%|██████▍   | 16814/25880 [3:26:29<2:00:24,  1.25it/s]
1|16815|Loss: 0.7949684262275696:  65%|██████▍   | 16815/25880 [3:26:30<1:56:13,  1.30it/s]
1|16816|Loss: 0.8129239678382874:  65%|██████▍   | 16815/25880 [3:26:30<1:56:13,  1.30it/s]
1|16816|Loss: 0.8129239678382874:  65%|██████▍   | 16816/25880 [3:26:30<1:56:49,  1.29it/s]
1|16817|Loss: 0.9043997526168823:  65%|█████���▍   | 16816/25880 [3:26:31<1:56:49,  1.29it/s]
1|16817|Loss: 0.9043997526168823:  65%|██████▍   | 16817/25880 [3:26:31<1:55:51,  1.30it/s]
1|16818|Loss: 0.8717638254165649:  65%|██████▍   | 16817/25880 [3:26:31<1:55:51,  1.30it/s]
1|16818|Loss: 0.8717638254165649:  65%|██████▍   | 16818/25880 [3:26:32<1:41:25,  1.49it/s]
1|16819|Loss: 0.8969148397445679:  65%|██████▍   | 16818/25880 [3:26:32<1:41:25,  1.49it/s]
1|16819|Loss: 0.8969148397445679:  65%|██████▍   | 16819/25880 [3:26:32<1:41:09,  1.49it/s]
1|16820|Loss: 0.9156443476676941:  65%|██████▍   | 16819/25880 [3:26:33<1:41:09,  1.49it/s]
1|16820|Loss: 0.9156443476676941:  65%|██████▍   | 16820/25880 [3:26:33<1:42:48,  1.47it/s]
1|16821|Loss: 0.7022594213485718:  65%|██████▍   | 16820/25880 [3:26:33<1:42:48,  1.47it/s]
1|16821|Loss: 0.7022594213485718:  65%|██████▍   | 16821/25880 [3:26:34<1:43:54,  1.45it/s]
1|16822|Loss: 0.6855921149253845:  65%|██████▍   | 16821/25880 [3:26:34<1:43:54,  1.45it/s]
1|16822|Loss: 0.6855921149253845:  65%|██████▌   | 16822/25880 [3:26:35<1:50:53,  1.36it/s]
1|16823|Loss: 0.6464790105819702:  65%|██████▌   | 16822/25880 [3:26:35<1:50:53,  1.36it/s]
1|16823|Loss: 0.6464790105819702:  65%|██████▌   | 16823/25880 [3:26:35<1:51:12,  1.36it/s]
1|16824|Loss: 0.7689040899276733:  65%|██████▌   | 16823/25880 [3:26:36<1:51:12,  1.36it/s]
1|16824|Loss: 0.7689040899276733:  65%|██████▌   | 16824/25880 [3:26:36<1:40:28,  1.50it/s]
1|16825|Loss: 0.7197151780128479:  65%|██████▌   | 16824/25880 [3:26:36<1:40:28,  1.50it/s]
1|16825|Loss: 0.7197151780128479:  65%|██████▌   | 16825/25880 [3:26:37<1:43:21,  1.46it/s]
1|16826|Loss: 0.8077146410942078:  65%|██████▌   | 16825/25880 [3:26:37<1:43:21,  1.46it/s]
1|16826|Loss: 0.8077146410942078:  65%|██████▌   | 16826/25880 [3:26:37<1:49:25,  1.38it/s]
1|16827|Loss: 0.8060237765312195:  65%|██████▌   | 16826/25880 [3:26:38<1:49:25,  1.38it/s]
1|16827|Loss: 0.8060237765312195:  65%|██████▌   | 16827/25880 [3:26:38<1:49:37,  1.38it/s]
1|16828|Loss: 0.8110144734382629:  65%|██████▌   | 16827/25880 [3:26:38<1:49:37,  1.38it/s]
1|16828|Loss: 0.8110144734382629:  65%|██████▌   | 16828/25880 [3:26:39<1:43:50,  1.45it/s]
1|16829|Loss: 0.878221869468689:  65%|██████▌   | 16828/25880 [3:26:39<1:43:50,  1.45it/s] 
1|16829|Loss: 0.878221869468689:  65%|██████▌   | 16829/25880 [3:26:39<1:44:49,  1.44it/s]
1|16830|Loss: 0.7074428200721741:  65%|██████▌   | 16829/25880 [3:26:40<1:44:49,  1.44it/s]
1|16830|Loss: 0.7074428200721741:  65%|██████▌   | 16830/25880 [3:26:40<1:50:21,  1.37it/s]
1|16831|Loss: 0.9321247935295105:  65%|██████▌   | 16830/25880 [3:26:41<1:50:21,  1.37it/s]
1|16831|Loss: 0.9321247935295105:  65%|██████▌   | 16831/25880 [3:26:41<1:50:05,  1.37it/s]
1|16832|Loss: 0.8301597833633423:  65%|██████▌   | 16831/25880 [3:26:41<1:50:05,  1.37it/s]
1|16832|Loss: 0.8301597833633423:  65%|██████▌   | 16832/25880 [3:26:42<1:49:42,  1.37it/s]
1|16833|Loss: 0.8815336227416992:  65%|██████▌   | 16832/25880 [3:26:42<1:49:42,  1.37it/s]
1|16833|Loss: 0.8815336227416992:  65%|██████▌   | 16833/25880 [3:26:42<1:54:13,  1.32it/s]
1|16834|Loss: 0.9001981616020203:  65%|██████▌   | 16833/25880 [3:26:43<1:54:13,  1.32it/s]
1|16834|Loss: 0.9001981616020203:  65%|██████▌   | 16834/25880 [3:26:43<1:56:20,  1.30it/s]
1|16835|Loss: 0.7723979353904724:  65%|██████▌   | 16834/25880 [3:26:44<1:56:20,  1.30it/s]
1|16835|Loss: 0.7723979353904724:  65%|██████▌   | 16835/25880 [3:26:44<1:58:45,  1.27it/s]
1|16836|Loss: 0.9476707577705383:  65%|██████▌   | 16835/25880 [3:26:45<1:58:45,  1.27it/s]
1|16836|Loss: 0.9476707577705383:  65%|██████▌   | 16836/25880 [3:26:45<1:57:00,  1.29it/s]
1|16837|Loss: 0.8912380933761597:  65%|██████▌   | 16836/25880 [3:26:45<1:57:00,  1.29it/s]
1|16837|Loss: 0.8912380933761597:  65%|██████▌   | 16837/25880 [3:26:45<1:48:30,  1.39it/s]
1|16838|Loss: 0.7401869893074036:  65%|██████▌   | 16837/25880 [3:26:46<1:48:30,  1.39it/s]
1|16838|Loss: 0.7401869893074036:  65%|██████▌   | 16838/25880 [3:26:46<1:54:15,  1.32it/s]
1|16839|Loss: 0.7872499227523804:  65%|██████▌   | 16838/25880 [3:26:47<1:54:15,  1.32it/s]
1|16839|Loss: 0.7872499227523804:  65%|██████▌   | 16839/25880 [3:26:47<1:45:49,  1.42it/s]
1|16840|Loss: 0.7320795655250549:  65%|██████▌   | 16839/25880 [3:26:47<1:45:49,  1.42it/s]
1|16840|Loss: 0.7320795655250549:  65%|██████▌   | 16840/25880 [3:26:47<1:39:13,  1.52it/s]
1|16841|Loss: 0.6497936248779297:  65%|██████▌   | 16840/25880 [3:26:48<1:39:13,  1.52it/s]
1|16841|Loss: 0.6497936248779297:  65%|██████▌   | 16841/25880 [3:26:48<1:44:38,  1.44it/s]
1|16842|Loss: 0.8296397924423218:  65%|██████▌   | 16841/25880 [3:26:49<1:44:38,  1.44it/s]
1|16842|Loss: 0.8296397924423218:  65%|██████▌   | 16842/25880 [3:26:49<1:46:19,  1.42it/s]
1|16843|Loss: 0.880454957485199:  65%|██████▌   | 16842/25880 [3:26:49<1:46:19,  1.42it/s] 
1|16843|Loss: 0.880454957485199:  65%|██████▌   | 16843/25880 [3:26:50<1:49:50,  1.37it/s]
1|16844|Loss: 0.8801414966583252:  65%|██████▌   | 16843/25880 [3:26:50<1:49:50,  1.37it/s]
1|16844|Loss: 0.8801414966583252:  65%|██████▌   | 16844/25880 [3:26:50<1:50:27,  1.36it/s]
1|16845|Loss: 0.87554931640625:  65%|██████▌   | 16844/25880 [3:26:51<1:50:27,  1.36it/s]  
1|16845|Loss: 0.87554931640625:  65%|██████▌   | 16845/25880 [3:26:51<1:46:10,  1.42it/s]
1|16846|Loss: 0.9559968709945679:  65%|██████▌   | 16845/25880 [3:26:51<1:46:10,  1.42it/s]
1|16846|Loss: 0.9559968709945679:  65%|██████▌   | 16846/25880 [3:26:52<1:39:19,  1.52it/s]
1|16847|Loss: 0.9124882817268372:  65%|██████▌   | 16846/25880 [3:26:52<1:39:19,  1.52it/s]
1|16847|Loss: 0.9124882817268372:  65%|██████▌   | 16847/25880 [3:26:52<1:39:21,  1.52it/s]
1|16848|Loss: 0.7905189990997314:  65%|██████▌   | 16847/25880 [3:26:53<1:39:21,  1.52it/s]
1|16848|Loss: 0.7905189990997314:  65%|██████▌   | 16848/25880 [3:26:53<1:42:32,  1.47it/s]
1|16849|Loss: 0.890357255935669:  65%|██████▌   | 16848/25880 [3:26:53<1:42:32,  1.47it/s] 
1|16849|Loss: 0.890357255935669:  65%|██████▌   | 16849/25880 [3:26:54<1:44:54,  1.43it/s]
1|16850|Loss: 0.7087928652763367:  65%|██████▌   | 16849/25880 [3:26:54<1:44:54,  1.43it/s]
1|16850|Loss: 0.7087928652763367:  65%|██████▌   | 16850/25880 [3:26:55<1:48:21,  1.39it/s]
1|16851|Loss: 0.9445915818214417:  65%|██████▌   | 16850/25880 [3:26:55<1:48:21,  1.39it/s]
1|16851|Loss: 0.9445915818214417:  65%|██████▌   | 16851/25880 [3:26:55<1:53:01,  1.33it/s]
1|16852|Loss: 0.7669145464897156:  65%|██████▌   | 16851/25880 [3:26:56<1:53:01,  1.33it/s]
1|16852|Loss: 0.7669145464897156:  65%|██████▌   | 16852/25880 [3:26:56<1:57:01,  1.29it/s]
1|16853|Loss: 0.981220543384552:  65%|██████▌   | 16852/25880 [3:26:57<1:57:01,  1.29it/s] 
1|16853|Loss: 0.981220543384552:  65%|██████▌   | 16853/25880 [3:26:57<2:00:33,  1.25it/s]
1|16854|Loss: 0.8674277067184448:  65%|██████▌   | 16853/25880 [3:26:57<2:00:33,  1.25it/s]
1|16854|Loss: 0.8674277067184448:  65%|██████▌   | 16854/25880 [3:26:58<1:52:59,  1.33it/s]
1|16855|Loss: 0.965091347694397:  65%|██████▌   | 16854/25880 [3:26:58<1:52:59,  1.33it/s] 
1|16855|Loss: 0.965091347694397:  65%|██████▌   | 16855/25880 [3:26:58<1:47:23,  1.40it/s]
1|16856|Loss: 0.8016161918640137:  65%|██████▌   | 16855/25880 [3:26:59<1:47:23,  1.40it/s]
1|16856|Loss: 0.8016161918640137:  65%|██████▌   | 16856/25880 [3:26:59<1:47:18,  1.40it/s]
1|16857|Loss: 0.8060925006866455:  65%|██████▌   | 16856/25880 [3:26:59<1:47:18,  1.40it/s]
1|16857|Loss: 0.8060925006866455:  65%|██████▌   | 16857/25880 [3:27:00<1:50:21,  1.36it/s]
1|16858|Loss: 0.7983801960945129:  65%|██████▌   | 16857/25880 [3:27:00<1:50:21,  1.36it/s]
1|16858|Loss: 0.7983801960945129:  65%|██████▌   | 16858/25880 [3:27:01<1:59:03,  1.26it/s]
1|16859|Loss: 0.7257359623908997:  65%|██████▌   | 16858/25880 [3:27:01<1:59:03,  1.26it/s]
1|16859|Loss: 0.7257359623908997:  65%|██████▌   | 16859/25880 [3:27:01<1:54:53,  1.31it/s]
1|16860|Loss: 0.768814742565155:  65%|██████▌   | 16859/25880 [3:27:02<1:54:53,  1.31it/s] 
1|16860|Loss: 0.768814742565155:  65%|██████▌   | 16860/25880 [3:27:02<1:45:50,  1.42it/s]
1|16861|Loss: 0.880393385887146:  65%|██████▌   | 16860/25880 [3:27:02<1:45:50,  1.42it/s]
1|16861|Loss: 0.880393385887146:  65%|██████▌   | 16861/25880 [3:27:03<1:48:40,  1.38it/s]
1|16862|Loss: 0.7479384541511536:  65%|██████▌   | 16861/25880 [3:27:03<1:48:40,  1.38it/s]
1|16862|Loss: 0.7479384541511536:  65%|██████▌   | 16862/25880 [3:27:03<1:41:45,  1.48it/s]
1|16863|Loss: 0.7862528562545776:  65%|██████▌   | 16862/25880 [3:27:04<1:41:45,  1.48it/s]
1|16863|Loss: 0.7862528562545776:  65%|██████▌   | 16863/25880 [3:27:04<1:38:00,  1.53it/s]
1|16864|Loss: 0.7669453024864197:  65%|██████▌   | 16863/25880 [3:27:04<1:38:00,  1.53it/s]
1|16864|Loss: 0.7669453024864197:  65%|██████▌   | 16864/25880 [3:27:05<1:39:18,  1.51it/s]
1|16865|Loss: 0.8041700124740601:  65%|██████▌   | 16864/25880 [3:27:05<1:39:18,  1.51it/s]
1|16865|Loss: 0.8041700124740601:  65%|██████▌   | 16865/25880 [3:27:05<1:45:38,  1.42it/s]
1|16866|Loss: 0.8547071218490601:  65%|██████▌   | 16865/25880 [3:27:06<1:45:38,  1.42it/s]
1|16866|Loss: 0.8547071218490601:  65%|██████▌   | 16866/25880 [3:27:06<1:37:20,  1.54it/s]
1|16867|Loss: 0.9137676954269409:  65%|██████▌   | 16866/25880 [3:27:06<1:37:20,  1.54it/s]
1|16867|Loss: 0.9137676954269409:  65%|██████▌   | 16867/25880 [3:27:07<1:41:02,  1.49it/s]
1|16868|Loss: 0.7086784243583679:  65%|██████▌   | 16867/25880 [3:27:07<1:41:02,  1.49it/s]
1|16868|Loss: 0.7086784243583679:  65%|██████▌   | 16868/25880 [3:27:07<1:44:02,  1.44it/s]
1|16869|Loss: 0.7742179036140442:  65%|██████▌   | 16868/25880 [3:27:08<1:44:02,  1.44it/s]
1|16869|Loss: 0.7742179036140442:  65%|██████▌   | 16869/25880 [3:27:08<1:41:13,  1.48it/s]
1|16870|Loss: 0.7959002256393433:  65%|██████▌   | 16869/25880 [3:27:08<1:41:13,  1.48it/s]
1|16870|Loss: 0.7959002256393433:  65%|██████▌   | 16870/25880 [3:27:09<1:43:16,  1.45it/s]
1|16871|Loss: 0.7945452332496643:  65%|██████▌   | 16870/25880 [3:27:09<1:43:16,  1.45it/s]
1|16871|Loss: 0.7945452332496643:  65%|██████▌   | 16871/25880 [3:27:09<1:45:15,  1.43it/s]
1|16872|Loss: 0.8281382918357849:  65%|██████▌   | 16871/25880 [3:27:10<1:45:15,  1.43it/s]
1|16872|Loss: 0.8281382918357849:  65%|██████▌   | 16872/25880 [3:27:10<1:46:29,  1.41it/s]
1|16873|Loss: 0.8463094830513:  65%|██████▌   | 16872/25880 [3:27:11<1:46:29,  1.41it/s]   
1|16873|Loss: 0.8463094830513:  65%|██████▌   | 16873/25880 [3:27:11<1:47:09,  1.40it/s]
1|16874|Loss: 0.8327820897102356:  65%|██████▌   | 16873/25880 [3:27:11<1:47:09,  1.40it/s]
1|16874|Loss: 0.8327820897102356:  65%|██████▌   | 16874/25880 [3:27:12<1:54:31,  1.31it/s]
1|16875|Loss: 0.9767438769340515:  65%|██████▌   | 16874/25880 [3:27:12<1:54:31,  1.31it/s]
1|16875|Loss: 0.9767438769340515:  65%|██████▌   | 16875/25880 [3:27:13<1:55:00,  1.31it/s]
1|16876|Loss: 0.897291362285614:  65%|██████▌   | 16875/25880 [3:27:13<1:55:00,  1.31it/s] 
1|16876|Loss: 0.897291362285614:  65%|██████▌   | 16876/25880 [3:27:13<1:55:40,  1.30it/s]
1|16877|Loss: 0.7934964299201965:  65%|██████▌   | 16876/25880 [3:27:14<1:55:40,  1.30it/s]
1|16877|Loss: 0.7934964299201965:  65%|██████▌   | 16877/25880 [3:27:14<1:54:15,  1.31it/s]
1|16878|Loss: 0.8251515030860901:  65%|██████▌   | 16877/25880 [3:27:15<1:54:15,  1.31it/s]
1|16878|Loss: 0.8251515030860901:  65%|██████▌   | 16878/25880 [3:27:15<1:56:45,  1.29it/s]
1|16879|Loss: 0.8559208512306213:  65%|██████▌   | 16878/25880 [3:27:15<1:56:45,  1.29it/s]
1|16879|Loss: 0.8559208512306213:  65%|██████▌   | 16879/25880 [3:27:16<1:52:30,  1.33it/s]
1|16880|Loss: 0.8379213213920593:  65%|██████▌   | 16879/25880 [3:27:16<1:52:30,  1.33it/s]
1|16880|Loss: 0.8379213213920593:  65%|██████▌   | 16880/25880 [3:27:16<1:52:49,  1.33it/s]
1|16881|Loss: 0.8479512929916382:  65%|██████▌   | 16880/25880 [3:27:17<1:52:49,  1.33it/s]
1|16881|Loss: 0.8479512929916382:  65%|██████▌   | 16881/25880 [3:27:17<1:49:16,  1.37it/s]
1|16882|Loss: 0.7346049547195435:  65%|██████▌   | 16881/25880 [3:27:17<1:49:16,  1.37it/s]
1|16882|Loss: 0.7346049547195435:  65%|██████▌   | 16882/25880 [3:27:18<1:40:41,  1.49it/s]
1|16883|Loss: 0.8165151476860046:  65%|██████▌   | 16882/25880 [3:27:18<1:40:41,  1.49it/s]
1|16883|Loss: 0.8165151476860046:  65%|██████▌   | 16883/25880 [3:27:18<1:40:52,  1.49it/s]
1|16884|Loss: 0.7084234356880188:  65%|██████▌   | 16883/25880 [3:27:19<1:40:52,  1.49it/s]
1|16884|Loss: 0.7084234356880188:  65%|██████▌   | 16884/25880 [3:27:19<1:42:55,  1.46it/s]
1|16885|Loss: 0.8313215970993042:  65%|██████▌   | 16884/25880 [3:27:19<1:42:55,  1.46it/s]
1|16885|Loss: 0.8313215970993042:  65%|██████▌   | 16885/25880 [3:27:20<1:41:23,  1.48it/s]
1|16886|Loss: 0.601169764995575:  65%|██████▌   | 16885/25880 [3:27:20<1:41:23,  1.48it/s] 
1|16886|Loss: 0.601169764995575:  65%|██████▌   | 16886/25880 [3:27:21<2:26:15,  1.02it/s]
1|16887|Loss: 0.9114459753036499:  65%|██████▌   | 16886/25880 [3:27:22<2:26:15,  1.02it/s]
1|16887|Loss: 0.9114459753036499:  65%|██████▌   | 16887/25880 [3:27:22<2:22:43,  1.05it/s]
1|16888|Loss: 0.6136006712913513:  65%|██████▌   | 16887/25880 [3:27:23<2:22:43,  1.05it/s]
1|16888|Loss: 0.6136006712913513:  65%|██████▌   | 16888/25880 [3:27:23<2:11:41,  1.14it/s]
1|16889|Loss: 0.7568000555038452:  65%|██████▌   | 16888/25880 [3:27:23<2:11:41,  1.14it/s]
1|16889|Loss: 0.7568000555038452:  65%|██████▌   | 16889/25880 [3:27:24<2:03:55,  1.21it/s]
1|16890|Loss: 0.7457191348075867:  65%|██████▌   | 16889/25880 [3:27:24<2:03:55,  1.21it/s]
1|16890|Loss: 0.7457191348075867:  65%|██████▌   | 16890/25880 [3:27:24<1:52:32,  1.33it/s]
1|16891|Loss: 0.7717805504798889:  65%|██████▌   | 16890/25880 [3:27:25<1:52:32,  1.33it/s]
1|16891|Loss: 0.7717805504798889:  65%|██████▌   | 16891/25880 [3:27:25<1:48:39,  1.38it/s]
1|16892|Loss: 0.9851551055908203:  65%|██████▌   | 16891/25880 [3:27:25<1:48:39,  1.38it/s]
1|16892|Loss: 0.9851551055908203:  65%|██████▌   | 16892/25880 [3:27:26<1:45:11,  1.42it/s]
1|16893|Loss: 0.9071125388145447:  65%|██████▌   | 16892/25880 [3:27:26<1:45:11,  1.42it/s]
1|16893|Loss: 0.9071125388145447:  65%|██████▌   | 16893/25880 [3:27:26<1:49:49,  1.36it/s]
1|16894|Loss: 0.9468539953231812:  65%|██████▌   | 16893/25880 [3:27:27<1:49:49,  1.36it/s]
1|16894|Loss: 0.9468539953231812:  65%|██████▌   | 16894/25880 [3:27:27<1:51:25,  1.34it/s]
1|16895|Loss: 0.881877601146698:  65%|██████▌   | 16894/25880 [3:27:27<1:51:25,  1.34it/s] 
1|16895|Loss: 0.881877601146698:  65%|██████▌   | 16895/25880 [3:27:28<1:50:08,  1.36it/s]
1|16896|Loss: 0.8216513395309448:  65%|██████▌   | 16895/25880 [3:27:28<1:50:08,  1.36it/s]
1|16896|Loss: 0.8216513395309448:  65%|██████▌   | 16896/25880 [3:27:29<1:56:10,  1.29it/s]
1|16897|Loss: 0.8946359157562256:  65%|██████▌   | 16896/25880 [3:27:29<1:56:10,  1.29it/s]
1|16897|Loss: 0.8946359157562256:  65%|██████▌   | 16897/25880 [3:27:29<1:52:14,  1.33it/s]
1|16898|Loss: 0.8508411049842834:  65%|██████▌   | 16897/25880 [3:27:30<1:52:14,  1.33it/s]
1|16898|Loss: 0.8508411049842834:  65%|██████▌   | 16898/25880 [3:27:30<1:42:19,  1.46it/s]
1|16899|Loss: 0.80512535572052:  65%|██████▌   | 16898/25880 [3:27:30<1:42:19,  1.46it/s]  
1|16899|Loss: 0.80512535572052:  65%|██████▌   | 16899/25880 [3:27:31<1:42:27,  1.46it/s]
1|16900|Loss: 0.7724078297615051:  65%|██████▌   | 16899/25880 [3:27:31<1:42:27,  1.46it/s]
1|16900|Loss: 0.7724078297615051:  65%|██████▌   | 16900/25880 [3:27:31<1:43:48,  1.44it/s]
1|16901|Loss: 1.0160775184631348:  65%|██████▌   | 16900/25880 [3:27:32<1:43:48,  1.44it/s]
1|16901|Loss: 1.0160775184631348:  65%|██████▌   | 16901/25880 [3:27:32<1:50:29,  1.35it/s]
1|16902|Loss: 0.9287528991699219:  65%|██████▌   | 16901/25880 [3:27:33<1:50:29,  1.35it/s]
1|16902|Loss: 0.9287528991699219:  65%|██████▌   | 16902/25880 [3:27:33<1:47:28,  1.39it/s]
1|16903|Loss: 0.8761401176452637:  65%|██████▌   | 16902/25880 [3:27:33<1:47:28,  1.39it/s]
1|16903|Loss: 0.8761401176452637:  65%|██████▌   | 16903/25880 [3:27:33<1:40:26,  1.49it/s]
1|16904|Loss: 0.9365562200546265:  65%|██████▌   | 16903/25880 [3:27:34<1:40:26,  1.49it/s]
1|16904|Loss: 0.9365562200546265:  65%|██████▌   | 16904/25880 [3:27:34<1:35:58,  1.56it/s]
1|16905|Loss: 0.9033485054969788:  65%|██████▌   | 16904/25880 [3:27:34<1:35:58,  1.56it/s]
1|16905|Loss: 0.9033485054969788:  65%|██████▌   | 16905/25880 [3:27:35<1:40:46,  1.48it/s]
1|16906|Loss: 0.9729995131492615:  65%|██████▌   | 16905/25880 [3:27:35<1:40:46,  1.48it/s]
1|16906|Loss: 0.9729995131492615:  65%|██████▌   | 16906/25880 [3:27:36<1:47:16,  1.39it/s]
1|16907|Loss: 0.6969029903411865:  65%|██████▌   | 16906/25880 [3:27:36<1:47:16,  1.39it/s]
1|16907|Loss: 0.6969029903411865:  65%|██████▌   | 16907/25880 [3:27:36<1:47:46,  1.39it/s]
1|16908|Loss: 0.8667230010032654:  65%|██████▌   | 16907/25880 [3:27:37<1:47:46,  1.39it/s]
1|16908|Loss: 0.8667230010032654:  65%|██████▌   | 16908/25880 [3:27:37<1:44:35,  1.43it/s]
1|16909|Loss: 0.835914671421051:  65%|██████▌   | 16908/25880 [3:27:37<1:44:35,  1.43it/s] 
1|16909|Loss: 0.835914671421051:  65%|██████▌   | 16909/25880 [3:27:37<1:39:31,  1.50it/s]
1|16910|Loss: 0.7194513082504272:  65%|██████▌   | 16909/25880 [3:27:38<1:39:31,  1.50it/s]
1|16910|Loss: 0.7194513082504272:  65%|██████▌   | 16910/25880 [3:27:38<1:39:52,  1.50it/s]
1|16911|Loss: 0.8637822270393372:  65%|██████▌   | 16910/25880 [3:27:39<1:39:52,  1.50it/s]
1|16911|Loss: 0.8637822270393372:  65%|██████▌   | 16911/25880 [3:27:39<1:44:52,  1.43it/s]
1|16912|Loss: 0.7428396344184875:  65%|██████▌   | 16911/25880 [3:27:39<1:44:52,  1.43it/s]
1|16912|Loss: 0.7428396344184875:  65%|██████▌   | 16912/25880 [3:27:40<1:43:06,  1.45it/s]
1|16913|Loss: 0.8307103514671326:  65%|██████▌   | 16912/25880 [3:27:40<1:43:06,  1.45it/s]
1|16913|Loss: 0.8307103514671326:  65%|██████▌   | 16913/25880 [3:27:40<1:46:51,  1.40it/s]
1|16914|Loss: 0.8979508876800537:  65%|██████▌   | 16913/25880 [3:27:41<1:46:51,  1.40it/s]
1|16914|Loss: 0.8979508876800537:  65%|██████▌   | 16914/25880 [3:27:41<1:44:04,  1.44it/s]
1|16915|Loss: 0.9957586526870728:  65%|██████▌   | 16914/25880 [3:27:41<1:44:04,  1.44it/s]
1|16915|Loss: 0.9957586526870728:  65%|██████▌   | 16915/25880 [3:27:42<1:41:17,  1.48it/s]
1|16916|Loss: 0.8093489408493042:  65%|██████▌   | 16915/25880 [3:27:42<1:41:17,  1.48it/s]
1|16916|Loss: 0.8093489408493042:  65%|██████▌   | 16916/25880 [3:27:42<1:39:31,  1.50it/s]
1|16917|Loss: 0.9666310548782349:  65%|██████▌   | 16916/25880 [3:27:43<1:39:31,  1.50it/s]
1|16917|Loss: 0.9666310548782349:  65%|██████▌   | 16917/25880 [3:27:43<1:38:17,  1.52it/s]
1|16918|Loss: 0.8612489700317383:  65%|██████▌   | 16917/25880 [3:27:43<1:38:17,  1.52it/s]
1|16918|Loss: 0.8612489700317383:  65%|██████▌   | 16918/25880 [3:27:44<1:45:30,  1.42it/s]
1|16919|Loss: 0.7673915028572083:  65%|██████▌   | 16918/25880 [3:27:44<1:45:30,  1.42it/s]
1|16919|Loss: 0.7673915028572083:  65%|██████▌   | 16919/25880 [3:27:45<1:50:38,  1.35it/s]
1|16920|Loss: 0.9383640885353088:  65%|██████▌   | 16919/25880 [3:27:45<1:50:38,  1.35it/s]
1|16920|Loss: 0.9383640885353088:  65%|██████▌   | 16920/25880 [3:27:45<1:47:48,  1.39it/s]
1|16921|Loss: 0.7590205073356628:  65%|██████▌   | 16920/25880 [3:27:46<1:47:48,  1.39it/s]
1|16921|Loss: 0.7590205073356628:  65%|██████▌   | 16921/25880 [3:27:46<1:50:02,  1.36it/s]
1|16922|Loss: 0.8506731390953064:  65%|██████▌   | 16921/25880 [3:27:46<1:50:02,  1.36it/s]
1|16922|Loss: 0.8506731390953064:  65%|██████▌   | 16922/25880 [3:27:47<1:50:27,  1.35it/s]
1|16923|Loss: 0.808643639087677:  65%|██████▌   | 16922/25880 [3:27:47<1:50:27,  1.35it/s] 
1|16923|Loss: 0.808643639087677:  65%|██████▌   | 16923/25880 [3:27:48<1:56:55,  1.28it/s]
1|16924|Loss: 0.6872366666793823:  65%|██████▌   | 16923/25880 [3:27:48<1:56:55,  1.28it/s]
1|16924|Loss: 0.6872366666793823:  65%|██████▌   | 16924/25880 [3:27:48<1:59:29,  1.25it/s]
1|16925|Loss: 0.9080508947372437:  65%|██████▌   | 16924/25880 [3:27:49<1:59:29,  1.25it/s]
1|16925|Loss: 0.9080508947372437:  65%|██████▌   | 16925/25880 [3:27:49<1:53:53,  1.31it/s]
1|16926|Loss: 0.7833316922187805:  65%|██████▌   | 16925/25880 [3:27:50<1:53:53,  1.31it/s]
1|16926|Loss: 0.7833316922187805:  65%|██████▌   | 16926/25880 [3:27:50<1:56:13,  1.28it/s]
1|16927|Loss: 0.7607021331787109:  65%|██████▌   | 16926/25880 [3:27:50<1:56:13,  1.28it/s]
1|16927|Loss: 0.7607021331787109:  65%|██████▌   | 16927/25880 [3:27:51<1:45:27,  1.42it/s]
1|16928|Loss: 0.9644187092781067:  65%|██████▌   | 16927/25880 [3:27:51<1:45:27,  1.42it/s]
1|16928|Loss: 0.9644187092781067:  65%|██████▌   | 16928/25880 [3:27:51<1:40:15,  1.49it/s]
1|16929|Loss: 0.8900106549263:  65%|██████▌   | 16928/25880 [3:27:51<1:40:15,  1.49it/s]   
1|16929|Loss: 0.8900106549263:  65%|██████▌   | 16929/25880 [3:27:52<1:38:41,  1.51it/s]
1|16930|Loss: 0.6995415687561035:  65%|██████▌   | 16929/25880 [3:27:52<1:38:41,  1.51it/s]
1|16930|Loss: 0.6995415687561035:  65%|██████▌   | 16930/25880 [3:27:53<1:46:09,  1.41it/s]
1|16931|Loss: 0.9508270621299744:  65%|██████▌   | 16930/25880 [3:27:53<1:46:09,  1.41it/s]
1|16931|Loss: 0.9508270621299744:  65%|██████▌   | 16931/25880 [3:27:53<1:43:01,  1.45it/s]
1|16932|Loss: 0.7669329643249512:  65%|██████▌   | 16931/25880 [3:27:54<1:43:01,  1.45it/s]
1|16932|Loss: 0.7669329643249512:  65%|██████▌   | 16932/25880 [3:27:54<1:36:54,  1.54it/s]
1|16933|Loss: 0.8654047250747681:  65%|██████▌   | 16932/25880 [3:27:54<1:36:54,  1.54it/s]
1|16933|Loss: 0.8654047250747681:  65%|██████▌   | 16933/25880 [3:27:54<1:32:21,  1.61it/s]
1|16934|Loss: 0.8779215812683105:  65%|██████▌   | 16933/25880 [3:27:55<1:32:21,  1.61it/s]
1|16934|Loss: 0.8779215812683105:  65%|██████▌   | 16934/25880 [3:27:55<1:39:13,  1.50it/s]
1|16935|Loss: 0.8973722457885742:  65%|██████▌   | 16934/25880 [3:27:55<1:39:13,  1.50it/s]
1|16935|Loss: 0.8973722457885742:  65%|██████▌   | 16935/25880 [3:27:56<1:38:30,  1.51it/s]
1|16936|Loss: 0.9250327348709106:  65%|██████▌   | 16935/25880 [3:27:56<1:38:30,  1.51it/s]
1|16936|Loss: 0.9250327348709106:  65%|██████▌   | 16936/25880 [3:27:57<1:45:38,  1.41it/s]
1|16937|Loss: 0.8225732445716858:  65%|██████▌   | 16936/25880 [3:27:57<1:45:38,  1.41it/s]
1|16937|Loss: 0.8225732445716858:  65%|██████▌   | 16937/25880 [3:27:57<1:55:01,  1.30it/s]
1|16938|Loss: 0.8614546656608582:  65%|██████▌   | 16937/25880 [3:27:58<1:55:01,  1.30it/s]
1|16938|Loss: 0.8614546656608582:  65%|██████▌   | 16938/25880 [3:27:58<1:54:28,  1.30it/s]
1|16939|Loss: 0.7327077984809875:  65%|██████▌   | 16938/25880 [3:27:59<1:54:28,  1.30it/s]
1|16939|Loss: 0.7327077984809875:  65%|██████▌   | 16939/25880 [3:27:59<1:47:07,  1.39it/s]
1|16940|Loss: 0.8149140477180481:  65%|██████▌   | 16939/25880 [3:27:59<1:47:07,  1.39it/s]
1|16940|Loss: 0.8149140477180481:  65%|██████▌   | 16940/25880 [3:28:00<1:46:10,  1.40it/s]
1|16941|Loss: 0.8715395331382751:  65%|██████▌   | 16940/25880 [3:28:00<1:46:10,  1.40it/s]
1|16941|Loss: 0.8715395331382751:  65%|██████▌   | 16941/25880 [3:28:00<1:55:17,  1.29it/s]
1|16942|Loss: 0.8930001258850098:  65%|██████▌   | 16941/25880 [3:28:01<1:55:17,  1.29it/s]
1|16942|Loss: 0.8930001258850098:  65%|██████▌   | 16942/25880 [3:28:01<1:51:13,  1.34it/s]
1|16943|Loss: 0.751141369342804:  65%|██████▌   | 16942/25880 [3:28:01<1:51:13,  1.34it/s] 
1|16943|Loss: 0.751141369342804:  65%|██████▌   | 16943/25880 [3:28:02<1:43:01,  1.45it/s]
1|16944|Loss: 0.8546420335769653:  65%|██████▌   | 16943/25880 [3:28:02<1:43:01,  1.45it/s]
1|16944|Loss: 0.8546420335769653:  65%|██████▌   | 16944/25880 [3:28:02<1:38:56,  1.51it/s]
1|16945|Loss: 0.798142671585083:  65%|██████▌   | 16944/25880 [3:28:03<1:38:56,  1.51it/s] 
1|16945|Loss: 0.798142671585083:  65%|██████▌   | 16945/25880 [3:28:03<1:40:59,  1.47it/s]
1|16946|Loss: 0.7001213431358337:  65%|██████▌   | 16945/25880 [3:28:03<1:40:59,  1.47it/s]
1|16946|Loss: 0.7001213431358337:  65%|██████▌   | 16946/25880 [3:28:04<1:48:22,  1.37it/s]
1|16947|Loss: 0.8136304020881653:  65%|██████▌   | 16946/25880 [3:28:04<1:48:22,  1.37it/s]
1|16947|Loss: 0.8136304020881653:  65%|██████▌   | 16947/25880 [3:28:04<1:43:46,  1.43it/s]
1|16948|Loss: 0.8137248158454895:  65%|██████▌   | 16947/25880 [3:28:05<1:43:46,  1.43it/s]
1|16948|Loss: 0.8137248158454895:  65%|██████▌   | 16948/25880 [3:28:05<1:40:22,  1.48it/s]
1|16949|Loss: 0.8844999670982361:  65%|██████▌   | 16948/25880 [3:28:05<1:40:22,  1.48it/s]
1|16949|Loss: 0.8844999670982361:  65%|██████▌   | 16949/25880 [3:28:06<1:38:02,  1.52it/s]
1|16950|Loss: 0.891090989112854:  65%|██████▌   | 16949/25880 [3:28:06<1:38:02,  1.52it/s] 
1|16950|Loss: 0.891090989112854:  65%|██████▌   | 16950/25880 [3:28:06<1:35:10,  1.56it/s]
1|16951|Loss: 0.7422108054161072:  65%|██████▌   | 16950/25880 [3:28:07<1:35:10,  1.56it/s]
1|16951|Loss: 0.7422108054161072:  65%|██████▌   | 16951/25880 [3:28:07<1:32:38,  1.61it/s]
1|16952|Loss: 0.7977041602134705:  65%|██████▌   | 16951/25880 [3:28:07<1:32:38,  1.61it/s]
1|16952|Loss: 0.7977041602134705:  66%|██████▌   | 16952/25880 [3:28:08<1:40:39,  1.48it/s]
1|16953|Loss: 0.6906581521034241:  66%|██████▌   | 16952/25880 [3:28:08<1:40:39,  1.48it/s]
1|16953|Loss: 0.6906581521034241:  66%|██████▌   | 16953/25880 [3:28:08<1:38:58,  1.50it/s]
1|16954|Loss: 0.8496896624565125:  66%|██████▌   | 16953/25880 [3:28:09<1:38:58,  1.50it/s]
1|16954|Loss: 0.8496896624565125:  66%|██████▌   | 16954/25880 [3:28:09<1:40:41,  1.48it/s]
1|16955|Loss: 0.8100568056106567:  66%|██████▌   | 16954/25880 [3:28:09<1:40:41,  1.48it/s]
1|16955|Loss: 0.8100568056106567:  66%|██████▌   | 16955/25880 [3:28:10<1:38:54,  1.50it/s]
1|16956|Loss: 0.8385326862335205:  66%|██████▌   | 16955/25880 [3:28:10<1:38:54,  1.50it/s]
1|16956|Loss: 0.8385326862335205:  66%|██████▌   | 16956/25880 [3:28:10<1:44:46,  1.42it/s]
1|16957|Loss: 0.9672859311103821:  66%|██████▌   | 16956/25880 [3:28:11<1:44:46,  1.42it/s]
1|16957|Loss: 0.9672859311103821:  66%|██████▌   | 16957/25880 [3:28:11<1:42:16,  1.45it/s]
1|16958|Loss: 0.8450247645378113:  66%|██████▌   | 16957/25880 [3:28:12<1:42:16,  1.45it/s]
1|16958|Loss: 0.8450247645378113:  66%|██████▌   | 16958/25880 [3:28:12<1:43:17,  1.44it/s]
1|16959|Loss: 0.7522352933883667:  66%|██████▌   | 16958/25880 [3:28:12<1:43:17,  1.44it/s]
1|16959|Loss: 0.7522352933883667:  66%|██████▌   | 16959/25880 [3:28:13<1:45:08,  1.41it/s]
1|16960|Loss: 0.8608403205871582:  66%|██████▌   | 16959/25880 [3:28:13<1:45:08,  1.41it/s]
1|16960|Loss: 0.8608403205871582:  66%|██████▌   | 16960/25880 [3:28:13<1:48:38,  1.37it/s]
1|16961|Loss: 0.7034057378768921:  66%|██████▌   | 16960/25880 [3:28:14<1:48:38,  1.37it/s]
1|16961|Loss: 0.7034057378768921:  66%|██████▌   | 16961/25880 [3:28:14<1:49:30,  1.36it/s]
1|16962|Loss: 0.8655805587768555:  66%|██████▌   | 16961/25880 [3:28:14<1:49:30,  1.36it/s]
1|16962|Loss: 0.8655805587768555:  66%|██████▌   | 16962/25880 [3:28:15<1:45:11,  1.41it/s]
1|16963|Loss: 0.933872640132904:  66%|██████▌   | 16962/25880 [3:28:15<1:45:11,  1.41it/s] 
1|16963|Loss: 0.933872640132904:  66%|██████▌   | 16963/25880 [3:28:16<1:47:03,  1.39it/s]
1|16964|Loss: 0.7071259021759033:  66%|██████▌   | 16963/25880 [3:28:16<1:47:03,  1.39it/s]
1|16964|Loss: 0.7071259021759033:  66%|██████▌   | 16964/25880 [3:28:16<1:42:38,  1.45it/s]
1|16965|Loss: 0.7936263084411621:  66%|██████▌   | 16964/25880 [3:28:17<1:42:38,  1.45it/s]
1|16965|Loss: 0.7936263084411621:  66%|██████▌   | 16965/25880 [3:28:17<1:44:43,  1.42it/s]
1|16966|Loss: 0.8229063153266907:  66%|██████▌   | 16965/25880 [3:28:17<1:44:43,  1.42it/s]
1|16966|Loss: 0.8229063153266907:  66%|██████▌   | 16966/25880 [3:28:18<1:49:56,  1.35it/s]
1|16967|Loss: 0.8214349746704102:  66%|██████▌   | 16966/25880 [3:28:18<1:49:56,  1.35it/s]
1|16967|Loss: 0.8214349746704102:  66%|██████▌   | 16967/25880 [3:28:18<1:51:03,  1.34it/s]
1|16968|Loss: 0.8967068791389465:  66%|██████▌   | 16967/25880 [3:28:19<1:51:03,  1.34it/s]
1|16968|Loss: 0.8967068791389465:  66%|██████▌   | 16968/25880 [3:28:19<1:49:34,  1.36it/s]
1|16969|Loss: 0.8363804221153259:  66%|██████▌   | 16968/25880 [3:28:20<1:49:34,  1.36it/s]
1|16969|Loss: 0.8363804221153259:  66%|██████▌   | 16969/25880 [3:28:20<1:47:39,  1.38it/s]
1|16970|Loss: 0.7953711152076721:  66%|██████▌   | 16969/25880 [3:28:20<1:47:39,  1.38it/s]
1|16970|Loss: 0.7953711152076721:  66%|██████▌   | 16970/25880 [3:28:20<1:41:58,  1.46it/s]
1|16971|Loss: 0.8468542695045471:  66%|██████▌   | 16970/25880 [3:28:21<1:41:58,  1.46it/s]
1|16971|Loss: 0.8468542695045471:  66%|██████▌   | 16971/25880 [3:28:21<1:38:54,  1.50it/s]
1|16972|Loss: 0.868636965751648:  66%|██████▌   | 16971/25880 [3:28:21<1:38:54,  1.50it/s] 
1|16972|Loss: 0.868636965751648:  66%|██████▌   | 16972/25880 [3:28:22<1:40:05,  1.48it/s]
1|16973|Loss: 0.8856998682022095:  66%|██████▌   | 16972/25880 [3:28:22<1:40:05,  1.48it/s]
1|16973|Loss: 0.8856998682022095:  66%|██████▌   | 16973/25880 [3:28:23<1:44:22,  1.42it/s]
1|16974|Loss: 0.7643800973892212:  66%|██████▌   | 16973/25880 [3:28:23<1:44:22,  1.42it/s]
1|16974|Loss: 0.7643800973892212:  66%|██████▌   | 16974/25880 [3:28:23<1:36:20,  1.54it/s]
1|16975|Loss: 0.8301154375076294:  66%|██████▌   | 16974/25880 [3:28:23<1:36:20,  1.54it/s]
1|16975|Loss: 0.8301154375076294:  66%|██████▌   | 16975/25880 [3:28:24<1:33:09,  1.59it/s]
1|16976|Loss: 0.7060275673866272:  66%|██████▌   | 16975/25880 [3:28:24<1:33:09,  1.59it/s]
1|16976|Loss: 0.7060275673866272:  66%|██████▌   | 16976/25880 [3:28:24<1:41:13,  1.47it/s]
1|16977|Loss: 0.92734295129776:  66%|██████▌   | 16976/25880 [3:28:25<1:41:13,  1.47it/s]  
1|16977|Loss: 0.92734295129776:  66%|██████▌   | 16977/25880 [3:28:25<1:43:52,  1.43it/s]
1|16978|Loss: 0.863264799118042:  66%|██████▌   | 16977/25880 [3:28:26<1:43:52,  1.43it/s]
1|16978|Loss: 0.863264799118042:  66%|██████▌   | 16978/25880 [3:28:26<1:48:24,  1.37it/s]
1|16979|Loss: 0.7333787679672241:  66%|██████▌   | 16978/25880 [3:28:26<1:48:24,  1.37it/s]
1|16979|Loss: 0.7333787679672241:  66%|██████▌   | 16979/25880 [3:28:27<1:49:41,  1.35it/s]
1|16980|Loss: 0.828191876411438:  66%|██████▌   | 16979/25880 [3:28:27<1:49:41,  1.35it/s] 
1|16980|Loss: 0.828191876411438:  66%|██████▌   | 16980/25880 [3:28:27<1:41:28,  1.46it/s]
1|16981|Loss: 0.827276349067688:  66%|██████▌   | 16980/25880 [3:28:28<1:41:28,  1.46it/s]
1|16981|Loss: 0.827276349067688:  66%|██████▌   | 16981/25880 [3:28:28<1:37:21,  1.52it/s]
1|16982|Loss: 0.7752451300621033:  66%|██████▌   | 16981/25880 [3:28:28<1:37:21,  1.52it/s]
1|16982|Loss: 0.7752451300621033:  66%|██████▌   | 16982/25880 [3:28:29<1:36:26,  1.54it/s]
1|16983|Loss: 0.8192442655563354:  66%|██████▌   | 16982/25880 [3:28:29<1:36:26,  1.54it/s]
1|16983|Loss: 0.8192442655563354:  66%|██████▌   | 16983/25880 [3:28:29<1:29:19,  1.66it/s]
1|16984|Loss: 0.7267369031906128:  66%|██████▌   | 16983/25880 [3:28:29<1:29:19,  1.66it/s]
1|16984|Loss: 0.7267369031906128:  66%|██████▌   | 16984/25880 [3:28:30<1:26:03,  1.72it/s]
1|16985|Loss: 0.8183794617652893:  66%|██████▌   | 16984/25880 [3:28:30<1:26:03,  1.72it/s]
1|16985|Loss: 0.8183794617652893:  66%|██████▌   | 16985/25880 [3:28:30<1:33:18,  1.59it/s]
1|16986|Loss: 0.8931108713150024:  66%|██████▌   | 16985/25880 [3:28:31<1:33:18,  1.59it/s]
1|16986|Loss: 0.8931108713150024:  66%|██████▌   | 16986/25880 [3:28:31<1:39:04,  1.50it/s]
1|16987|Loss: 0.8479942083358765:  66%|██████▌   | 16986/25880 [3:28:31<1:39:04,  1.50it/s]
1|16987|Loss: 0.8479942083358765:  66%|██████▌   | 16987/25880 [3:28:32<1:36:10,  1.54it/s]
1|16988|Loss: 0.9541928768157959:  66%|██████▌   | 16987/25880 [3:28:32<1:36:10,  1.54it/s]
1|16988|Loss: 0.9541928768157959:  66%|██████▌   | 16988/25880 [3:28:32<1:37:25,  1.52it/s]
1|16989|Loss: 0.8625489473342896:  66%|██████▌   | 16988/25880 [3:28:33<1:37:25,  1.52it/s]
1|16989|Loss: 0.8625489473342896:  66%|██████▌   | 16989/25880 [3:28:33<1:36:10,  1.54it/s]
1|16990|Loss: 0.7676748037338257:  66%|██████▌   | 16989/25880 [3:28:33<1:36:10,  1.54it/s]
1|16990|Loss: 0.7676748037338257:  66%|██████▌   | 16990/25880 [3:28:34<1:37:42,  1.52it/s]
1|16991|Loss: 0.8360525369644165:  66%|██████▌   | 16990/25880 [3:28:34<1:37:42,  1.52it/s]
1|16991|Loss: 0.8360525369644165:  66%|██████▌   | 16991/25880 [3:28:34<1:32:33,  1.60it/s]
1|16992|Loss: 0.8508642911911011:  66%|██████▌   | 16991/25880 [3:28:35<1:32:33,  1.60it/s]
1|16992|Loss: 0.8508642911911011:  66%|██████▌   | 16992/25880 [3:28:35<1:37:06,  1.53it/s]
1|16993|Loss: 0.9966033101081848:  66%|██████▌   | 16992/25880 [3:28:35<1:37:06,  1.53it/s]
1|16993|Loss: 0.9966033101081848:  66%|██████▌   | 16993/25880 [3:28:36<1:43:09,  1.44it/s]
1|16994|Loss: 0.9659560918807983:  66%|██████▌   | 16993/25880 [3:28:36<1:43:09,  1.44it/s]
1|16994|Loss: 0.9659560918807983:  66%|██████▌   | 16994/25880 [3:28:37<1:49:21,  1.35it/s]
1|16995|Loss: 1.015297770500183:  66%|██████▌   | 16994/25880 [3:28:37<1:49:21,  1.35it/s] 
1|16995|Loss: 1.015297770500183:  66%|██████▌   | 16995/25880 [3:28:37<1:54:41,  1.29it/s]
1|16996|Loss: 0.8492208123207092:  66%|██████▌   | 16995/25880 [3:28:38<1:54:41,  1.29it/s]
1|16996|Loss: 0.8492208123207092:  66%|██████▌   | 16996/25880 [3:28:38<1:58:04,  1.25it/s]
1|16997|Loss: 0.8351073265075684:  66%|██████▌   | 16996/25880 [3:28:39<1:58:04,  1.25it/s]
1|16997|Loss: 0.8351073265075684:  66%|██████▌   | 16997/25880 [3:28:39<1:55:25,  1.28it/s]
1|16998|Loss: 0.9108879566192627:  66%|██████▌   | 16997/25880 [3:28:39<1:55:25,  1.28it/s]
1|16998|Loss: 0.9108879566192627:  66%|██████▌   | 16998/25880 [3:28:40<1:53:03,  1.31it/s]
1|16999|Loss: 1.0051343441009521:  66%|██████▌   | 16998/25880 [3:28:40<1:53:03,  1.31it/s]
1|16999|Loss: 1.0051343441009521:  66%|██████▌   | 16999/25880 [3:28:40<1:47:23,  1.38it/s]
1|17000|Loss: 0.8528256416320801:  66%|██████▌   | 16999/25880 [3:28:41<1:47:23,  1.38it/s]
1|17000|Loss: 0.8528256416320801:  66%|██████▌   | 17000/25880 [3:28:41<1:50:34,  1.34it/s]
1|17001|Loss: 0.8498835563659668:  66%|██████▌   | 17000/25880 [3:28:42<1:50:34,  1.34it/s]
1|17001|Loss: 0.8498835563659668:  66%|██████▌   | 17001/25880 [3:28:42<1:51:35,  1.33it/s]
1|17002|Loss: 0.7046913504600525:  66%|██████▌   | 17001/25880 [3:28:42<1:51:35,  1.33it/s]
1|17002|Loss: 0.7046913504600525:  66%|██████▌   | 17002/25880 [3:28:43<1:44:22,  1.42it/s]
1|17003|Loss: 0.857659637928009:  66%|██████▌   | 17002/25880 [3:28:43<1:44:22,  1.42it/s] 
1|17003|Loss: 0.857659637928009:  66%|██████▌   | 17003/25880 [3:28:43<1:50:18,  1.34it/s]
1|17004|Loss: 0.6761733293533325:  66%|██████▌   | 17003/25880 [3:28:44<1:50:18,  1.34it/s]
1|17004|Loss: 0.6761733293533325:  66%|██████▌   | 17004/25880 [3:28:44<1:59:23,  1.24it/s]
1|17005|Loss: 0.7802795767784119:  66%|██████▌   | 17004/25880 [3:28:45<1:59:23,  1.24it/s]
1|17005|Loss: 0.7802795767784119:  66%|██████▌   | 17005/25880 [3:28:45<1:58:12,  1.25it/s]
1|17006|Loss: 0.8733015060424805:  66%|██████▌   | 17005/25880 [3:28:45<1:58:12,  1.25it/s]
1|17006|Loss: 0.8733015060424805:  66%|██████▌   | 17006/25880 [3:28:46<1:54:28,  1.29it/s]
1|17007|Loss: 0.8066997528076172:  66%|██████▌   | 17006/25880 [3:28:46<1:54:28,  1.29it/s]
1|17007|Loss: 0.8066997528076172:  66%|██████▌   | 17007/25880 [3:28:47<1:54:21,  1.29it/s]
1|17008|Loss: 0.8330201506614685:  66%|██████▌   | 17007/25880 [3:28:47<1:54:21,  1.29it/s]
1|17008|Loss: 0.8330201506614685:  66%|██████▌   | 17008/25880 [3:28:47<1:47:47,  1.37it/s]
1|17009|Loss: 1.0755997896194458:  66%|██████▌   | 17008/25880 [3:28:48<1:47:47,  1.37it/s]
1|17009|Loss: 1.0755997896194458:  66%|██████▌   | 17009/25880 [3:28:48<1:42:22,  1.44it/s]
1|17010|Loss: 0.9741142988204956:  66%|██████▌   | 17009/25880 [3:28:48<1:42:22,  1.44it/s]
1|17010|Loss: 0.9741142988204956:  66%|██████▌   | 17010/25880 [3:28:48<1:37:33,  1.52it/s]
1|17011|Loss: 0.9286418557167053:  66%|██████▌   | 17010/25880 [3:28:49<1:37:33,  1.52it/s]
1|17011|Loss: 0.9286418557167053:  66%|██████▌   | 17011/25880 [3:28:49<1:34:56,  1.56it/s]
1|17012|Loss: 0.7026143670082092:  66%|██████▌   | 17011/25880 [3:28:49<1:34:56,  1.56it/s]
1|17012|Loss: 0.7026143670082092:  66%|██████▌   | 17012/25880 [3:28:49<1:27:56,  1.68it/s]
1|17013|Loss: 0.9272005558013916:  66%|██████▌   | 17012/25880 [3:28:50<1:27:56,  1.68it/s]
1|17013|Loss: 0.9272005558013916:  66%|██████▌   | 17013/25880 [3:28:50<1:30:58,  1.62it/s]
1|17014|Loss: 0.7813434600830078:  66%|██████▌   | 17013/25880 [3:28:51<1:30:58,  1.62it/s]
1|17014|Loss: 0.7813434600830078:  66%|██████▌   | 17014/25880 [3:28:51<1:36:08,  1.54it/s]
1|17015|Loss: 0.8388053178787231:  66%|██████▌   | 17014/25880 [3:28:51<1:36:08,  1.54it/s]
1|17015|Loss: 0.8388053178787231:  66%|██████▌   | 17015/25880 [3:28:52<1:42:49,  1.44it/s]
1|17016|Loss: 0.8521150946617126:  66%|██████▌   | 17015/25880 [3:28:52<1:42:49,  1.44it/s]
1|17016|Loss: 0.8521150946617126:  66%|██████▌   | 17016/25880 [3:28:52<1:45:33,  1.40it/s]
1|17017|Loss: 0.7498245239257812:  66%|██████▌   | 17016/25880 [3:28:53<1:45:33,  1.40it/s]
1|17017|Loss: 0.7498245239257812:  66%|██████▌   | 17017/25880 [3:28:53<1:46:20,  1.39it/s]
1|17018|Loss: 0.8775922656059265:  66%|██████▌   | 17017/25880 [3:28:54<1:46:20,  1.39it/s]
1|17018|Loss: 0.8775922656059265:  66%|██████▌   | 17018/25880 [3:28:54<1:48:33,  1.36it/s]
1|17019|Loss: 0.8797242045402527:  66%|██████▌   | 17018/25880 [3:28:54<1:48:33,  1.36it/s]
1|17019|Loss: 0.8797242045402527:  66%|██████▌   | 17019/25880 [3:28:55<1:45:03,  1.41it/s]
1|17020|Loss: 0.8507946729660034:  66%|██████▌   | 17019/25880 [3:28:55<1:45:03,  1.41it/s]
1|17020|Loss: 0.8507946729660034:  66%|██████▌   | 17020/25880 [3:28:55<1:44:52,  1.41it/s]
1|17021|Loss: 0.7940894961357117:  66%|██████▌   | 17020/25880 [3:28:56<1:44:52,  1.41it/s]
1|17021|Loss: 0.7940894961357117:  66%|██████▌   | 17021/25880 [3:28:56<1:45:52,  1.39it/s]
1|17022|Loss: 0.8421226143836975:  66%|██████▌   | 17021/25880 [3:28:57<1:45:52,  1.39it/s]
1|17022|Loss: 0.8421226143836975:  66%|██████▌   | 17022/25880 [3:28:57<1:54:34,  1.29it/s]
1|17023|Loss: 0.8359887003898621:  66%|██████▌   | 17022/25880 [3:28:57<1:54:34,  1.29it/s]
1|17023|Loss: 0.8359887003898621:  66%|██████▌   | 17023/25880 [3:28:58<1:53:11,  1.30it/s]
1|17024|Loss: 0.8496336936950684:  66%|██████▌   | 17023/25880 [3:28:58<1:53:11,  1.30it/s]
1|17024|Loss: 0.8496336936950684:  66%|██████▌   | 17024/25880 [3:28:59<1:55:23,  1.28it/s]
1|17025|Loss: 0.9223171472549438:  66%|██████▌   | 17024/25880 [3:28:59<1:55:23,  1.28it/s]
1|17025|Loss: 0.9223171472549438:  66%|██████▌   | 17025/25880 [3:28:59<1:50:07,  1.34it/s]
1|17026|Loss: 0.7447818517684937:  66%|██████▌   | 17025/25880 [3:29:00<1:50:07,  1.34it/s]
1|17026|Loss: 0.7447818517684937:  66%|██████▌   | 17026/25880 [3:29:00<1:42:57,  1.43it/s]
1|17027|Loss: 0.7736122608184814:  66%|██████▌   | 17026/25880 [3:29:00<1:42:57,  1.43it/s]
1|17027|Loss: 0.7736122608184814:  66%|██████▌   | 17027/25880 [3:29:00<1:41:57,  1.45it/s]
1|17028|Loss: 0.8245972394943237:  66%|██████▌   | 17027/25880 [3:29:01<1:41:57,  1.45it/s]
1|17028|Loss: 0.8245972394943237:  66%|██████▌   | 17028/25880 [3:29:01<1:43:17,  1.43it/s]
1|17029|Loss: 1.0014736652374268:  66%|██████▌   | 17028/25880 [3:29:02<1:43:17,  1.43it/s]
1|17029|Loss: 1.0014736652374268:  66%|██████▌   | 17029/25880 [3:29:02<1:40:18,  1.47it/s]
1|17030|Loss: 0.8200493454933167:  66%|██████▌   | 17029/25880 [3:29:02<1:40:18,  1.47it/s]
1|17030|Loss: 0.8200493454933167:  66%|██████▌   | 17030/25880 [3:29:03<1:42:14,  1.44it/s]
1|17031|Loss: 0.7786034345626831:  66%|██████▌   | 17030/25880 [3:29:03<1:42:14,  1.44it/s]
1|17031|Loss: 0.7786034345626831:  66%|██████▌   | 17031/25880 [3:29:03<1:43:59,  1.42it/s]
1|17032|Loss: 0.6954046487808228:  66%|██████▌   | 17031/25880 [3:29:04<1:43:59,  1.42it/s]
1|17032|Loss: 0.6954046487808228:  66%|██████▌   | 17032/25880 [3:29:04<1:53:51,  1.30it/s]
1|17033|Loss: 0.8563035726547241:  66%|██████▌   | 17032/25880 [3:29:05<1:53:51,  1.30it/s]
1|17033|Loss: 0.8563035726547241:  66%|██████▌   | 17033/25880 [3:29:05<1:59:15,  1.24it/s]
1|17034|Loss: 0.7912909984588623:  66%|██████▌   | 17033/25880 [3:29:06<1:59:15,  1.24it/s]
1|17034|Loss: 0.7912909984588623:  66%|██████▌   | 17034/25880 [3:29:06<1:57:16,  1.26it/s]
1|17035|Loss: 0.7738781571388245:  66%|██████▌   | 17034/25880 [3:29:06<1:57:16,  1.26it/s]
1|17035|Loss: 0.7738781571388245:  66%|██████▌   | 17035/25880 [3:29:06<1:48:57,  1.35it/s]
1|17036|Loss: 0.8481626510620117:  66%|██████▌   | 17035/25880 [3:29:07<1:48:57,  1.35it/s]
1|17036|Loss: 0.8481626510620117:  66%|██████▌   | 17036/25880 [3:29:07<1:49:05,  1.35it/s]
1|17037|Loss: 0.862301230430603:  66%|██████▌   | 17036/25880 [3:29:08<1:49:05,  1.35it/s] 
1|17037|Loss: 0.862301230430603:  66%|██████▌   | 17037/25880 [3:29:08<1:49:30,  1.35it/s]
1|17038|Loss: 0.780506432056427:  66%|██████▌   | 17037/25880 [3:29:08<1:49:30,  1.35it/s]
1|17038|Loss: 0.780506432056427:  66%|██████▌   | 17038/25880 [3:29:09<1:47:38,  1.37it/s]
1|17039|Loss: 0.7843099236488342:  66%|██████▌   | 17038/25880 [3:29:09<1:47:38,  1.37it/s]
1|17039|Loss: 0.7843099236488342:  66%|██████▌   | 17039/25880 [3:29:09<1:45:53,  1.39it/s]
1|17040|Loss: 0.7753840684890747:  66%|██████▌   | 17039/25880 [3:29:10<1:45:53,  1.39it/s]
1|17040|Loss: 0.7753840684890747:  66%|██████▌   | 17040/25880 [3:29:10<1:44:51,  1.41it/s]
1|17041|Loss: 0.7893176078796387:  66%|██████▌   | 17040/25880 [3:29:10<1:44:51,  1.41it/s]
1|17041|Loss: 0.7893176078796387:  66%|██████▌   | 17041/25880 [3:29:11<1:48:39,  1.36it/s]
1|17042|Loss: 0.8991938829421997:  66%|██████▌   | 17041/25880 [3:29:11<1:48:39,  1.36it/s]
1|17042|Loss: 0.8991938829421997:  66%|██████▌   | 17042/25880 [3:29:11<1:41:20,  1.45it/s]
1|17043|Loss: 0.7411190271377563:  66%|██████▌   | 17042/25880 [3:29:12<1:41:20,  1.45it/s]
1|17043|Loss: 0.7411190271377563:  66%|██████▌   | 17043/25880 [3:29:12<1:40:15,  1.47it/s]
1|17044|Loss: 0.7050445675849915:  66%|██████▌   | 17043/25880 [3:29:12<1:40:15,  1.47it/s]
1|17044|Loss: 0.7050445675849915:  66%|██████▌   | 17044/25880 [3:29:13<1:37:21,  1.51it/s]
1|17045|Loss: 0.7823655009269714:  66%|██████▌   | 17044/25880 [3:29:13<1:37:21,  1.51it/s]
1|17045|Loss: 0.7823655009269714:  66%|██████▌   | 17045/25880 [3:29:13<1:35:36,  1.54it/s]
1|17046|Loss: 0.9060592651367188:  66%|██████▌   | 17045/25880 [3:29:14<1:35:36,  1.54it/s]
1|17046|Loss: 0.9060592651367188:  66%|██████▌   | 17046/25880 [3:29:14<1:37:19,  1.51it/s]
1|17047|Loss: 0.9263131618499756:  66%|██████▌   | 17046/25880 [3:29:14<1:37:19,  1.51it/s]
1|17047|Loss: 0.9263131618499756:  66%|██████▌   | 17047/25880 [3:29:15<1:32:51,  1.59it/s]
1|17048|Loss: 0.7941219210624695:  66%|██████▌   | 17047/25880 [3:29:15<1:32:51,  1.59it/s]
1|17048|Loss: 0.7941219210624695:  66%|██████▌   | 17048/25880 [3:29:15<1:35:20,  1.54it/s]
1|17049|Loss: 0.8447708487510681:  66%|██████▌   | 17048/25880 [3:29:16<1:35:20,  1.54it/s]
1|17049|Loss: 0.8447708487510681:  66%|██████▌   | 17049/25880 [3:29:16<1:35:47,  1.54it/s]
1|17050|Loss: 0.8491485118865967:  66%|██████▌   | 17049/25880 [3:29:16<1:35:47,  1.54it/s]
1|17050|Loss: 0.8491485118865967:  66%|██████▌   | 17050/25880 [3:29:17<1:44:17,  1.41it/s]
1|17051|Loss: 0.7496526837348938:  66%|██████▌   | 17050/25880 [3:29:17<1:44:17,  1.41it/s]
1|17051|Loss: 0.7496526837348938:  66%|██████▌   | 17051/25880 [3:29:17<1:45:47,  1.39it/s]
1|17052|Loss: 0.7716884613037109:  66%|██████▌   | 17051/25880 [3:29:18<1:45:47,  1.39it/s]
1|17052|Loss: 0.7716884613037109:  66%|██████▌   | 17052/25880 [3:29:18<1:38:32,  1.49it/s]
1|17053|Loss: 0.8328440189361572:  66%|██████▌   | 17052/25880 [3:29:18<1:38:32,  1.49it/s]
1|17053|Loss: 0.8328440189361572:  66%|██████▌   | 17053/25880 [3:29:19<1:35:03,  1.55it/s]
1|17054|Loss: 0.8128286600112915:  66%|██████▌   | 17053/25880 [3:29:19<1:35:03,  1.55it/s]
1|17054|Loss: 0.8128286600112915:  66%|██████▌   | 17054/25880 [3:29:19<1:41:50,  1.44it/s]
1|17055|Loss: 0.8105541467666626:  66%|██████▌   | 17054/25880 [3:29:20<1:41:50,  1.44it/s]
1|17055|Loss: 0.8105541467666626:  66%|██████▌   | 17055/25880 [3:29:20<1:44:32,  1.41it/s]
1|17056|Loss: 0.7962254881858826:  66%|██████▌   | 17055/25880 [3:29:21<1:44:32,  1.41it/s]
1|17056|Loss: 0.7962254881858826:  66%|██████▌   | 17056/25880 [3:29:21<1:45:07,  1.40it/s]
1|17057|Loss: 0.7282004952430725:  66%|██████▌   | 17056/25880 [3:29:21<1:45:07,  1.40it/s]
1|17057|Loss: 0.7282004952430725:  66%|██████▌   | 17057/25880 [3:29:22<1:51:54,  1.31it/s]
1|17058|Loss: 0.7361001968383789:  66%|██████▌   | 17057/25880 [3:29:22<1:51:54,  1.31it/s]
1|17058|Loss: 0.7361001968383789:  66%|██████▌   | 17058/25880 [3:29:22<1:47:45,  1.36it/s]
1|17059|Loss: 0.7949710488319397:  66%|██████▌   | 17058/25880 [3:29:23<1:47:45,  1.36it/s]
1|17059|Loss: 0.7949710488319397:  66%|██████▌   | 17059/25880 [3:29:23<1:48:56,  1.35it/s]
1|17060|Loss: 0.7777916789054871:  66%|██████▌   | 17059/25880 [3:29:24<1:48:56,  1.35it/s]
1|17060|Loss: 0.7777916789054871:  66%|██████▌   | 17060/25880 [3:29:24<1:52:22,  1.31it/s]
1|17061|Loss: 0.9792900681495667:  66%|██████▌   | 17060/25880 [3:29:24<1:52:22,  1.31it/s]
1|17061|Loss: 0.9792900681495667:  66%|██████▌   | 17061/25880 [3:29:25<1:57:59,  1.25it/s]
1|17062|Loss: 0.7985179424285889:  66%|██████▌   | 17061/25880 [3:29:25<1:57:59,  1.25it/s]
1|17062|Loss: 0.7985179424285889:  66%|██████▌   | 17062/25880 [3:29:26<2:03:07,  1.19it/s]
1|17063|Loss: 0.7647183537483215:  66%|██████▌   | 17062/25880 [3:29:26<2:03:07,  1.19it/s]
1|17063|Loss: 0.7647183537483215:  66%|██████▌   | 17063/25880 [3:29:27<2:05:44,  1.17it/s]
1|17064|Loss: 0.7920650839805603:  66%|██████▌   | 17063/25880 [3:29:27<2:05:44,  1.17it/s]
1|17064|Loss: 0.7920650839805603:  66%|██████▌   | 17064/25880 [3:29:28<2:07:13,  1.15it/s]
1|17065|Loss: 0.7891173362731934:  66%|██████▌   | 17064/25880 [3:29:28<2:07:13,  1.15it/s]
1|17065|Loss: 0.7891173362731934:  66%|██████▌   | 17065/25880 [3:29:28<1:57:16,  1.25it/s]
1|17066|Loss: 0.9010329246520996:  66%|██████▌   | 17065/25880 [3:29:29<1:57:16,  1.25it/s]
1|17066|Loss: 0.9010329246520996:  66%|██████▌   | 17066/25880 [3:29:29<1:48:40,  1.35it/s]
1|17067|Loss: 0.9709691405296326:  66%|██████▌   | 17066/25880 [3:29:29<1:48:40,  1.35it/s]
1|17067|Loss: 0.9709691405296326:  66%|██████▌   | 17067/25880 [3:29:30<1:50:35,  1.33it/s]
1|17068|Loss: 0.8310384750366211:  66%|██████▌   | 17067/25880 [3:29:30<1:50:35,  1.33it/s]
1|17068|Loss: 0.8310384750366211:  66%|██████▌   | 17068/25880 [3:29:30<1:54:36,  1.28it/s]
1|17069|Loss: 0.9513905644416809:  66%|██████▌   | 17068/25880 [3:29:31<1:54:36,  1.28it/s]
1|17069|Loss: 0.9513905644416809:  66%|██████▌   | 17069/25880 [3:29:31<1:52:43,  1.30it/s]
1|17070|Loss: 0.9995643496513367:  66%|██████▌   | 17069/25880 [3:29:32<1:52:43,  1.30it/s]
1|17070|Loss: 0.9995643496513367:  66%|██████▌   | 17070/25880 [3:29:32<1:50:31,  1.33it/s]
1|17071|Loss: 0.9013489484786987:  66%|██████▌   | 17070/25880 [3:29:32<1:50:31,  1.33it/s]
1|17071|Loss: 0.9013489484786987:  66%|██████▌   | 17071/25880 [3:29:33<1:49:09,  1.34it/s]
1|17072|Loss: 0.8561822772026062:  66%|██████▌   | 17071/25880 [3:29:33<1:49:09,  1.34it/s]
1|17072|Loss: 0.8561822772026062:  66%|██████▌   | 17072/25880 [3:29:33<1:48:33,  1.35it/s]
1|17073|Loss: 0.8471855521202087:  66%|██████▌   | 17072/25880 [3:29:34<1:48:33,  1.35it/s]
1|17073|Loss: 0.8471855521202087:  66%|██████▌   | 17073/25880 [3:29:34<1:52:25,  1.31it/s]
1|17074|Loss: 0.9292406439781189:  66%|██████▌   | 17073/25880 [3:29:35<1:52:25,  1.31it/s]
1|17074|Loss: 0.9292406439781189:  66%|██████▌   | 17074/25880 [3:29:35<1:51:10,  1.32it/s]
1|17075|Loss: 1.0362929105758667:  66%|██████▌   | 17074/25880 [3:29:35<1:51:10,  1.32it/s]
1|17075|Loss: 1.0362929105758667:  66%|██████▌   | 17075/25880 [3:29:36<1:44:41,  1.40it/s]
1|17076|Loss: 0.8142378330230713:  66%|██████▌   | 17075/25880 [3:29:36<1:44:41,  1.40it/s]
1|17076|Loss: 0.8142378330230713:  66%|██████▌   | 17076/25880 [3:29:36<1:43:03,  1.42it/s]
1|17077|Loss: 0.8123822808265686:  66%|██████▌   | 17076/25880 [3:29:37<1:43:03,  1.42it/s]
1|17077|Loss: 0.8123822808265686:  66%|██████▌   | 17077/25880 [3:29:37<1:39:58,  1.47it/s]
1|17078|Loss: 0.773758590221405:  66%|██████▌   | 17077/25880 [3:29:37<1:39:58,  1.47it/s] 
1|17078|Loss: 0.773758590221405:  66%|██████▌   | 17078/25880 [3:29:37<1:35:02,  1.54it/s]
1|17079|Loss: 0.7948428988456726:  66%|██████▌   | 17078/25880 [3:29:38<1:35:02,  1.54it/s]
1|17079|Loss: 0.7948428988456726:  66%|██████▌   | 17079/25880 [3:29:38<1:36:04,  1.53it/s]
1|17080|Loss: 0.7698469161987305:  66%|██████▌   | 17079/25880 [3:29:39<1:36:04,  1.53it/s]
1|17080|Loss: 0.7698469161987305:  66%|██████▌   | 17080/25880 [3:29:39<1:47:23,  1.37it/s]
1|17081|Loss: 0.79593425989151:  66%|██████▌   | 17080/25880 [3:29:40<1:47:23,  1.37it/s]  
1|17081|Loss: 0.79593425989151:  66%|██████▌   | 17081/25880 [3:29:40<1:55:59,  1.26it/s]
1|17082|Loss: 0.6384249329566956:  66%|██████▌   | 17081/25880 [3:29:40<1:55:59,  1.26it/s]
1|17082|Loss: 0.6384249329566956:  66%|██████▌   | 17082/25880 [3:29:41<1:51:31,  1.31it/s]
1|17083|Loss: 0.7404420375823975:  66%|██████▌   | 17082/25880 [3:29:41<1:51:31,  1.31it/s]
1|17083|Loss: 0.7404420375823975:  66%|██████▌   | 17083/25880 [3:29:41<1:54:50,  1.28it/s]
1|17084|Loss: 0.7873679995536804:  66%|██████▌   | 17083/25880 [3:29:42<1:54:50,  1.28it/s]
1|17084|Loss: 0.7873679995536804:  66%|██████▌   | 17084/25880 [3:29:42<1:50:14,  1.33it/s]
1|17085|Loss: 0.7712459564208984:  66%|██████▌   | 17084/25880 [3:29:42<1:50:14,  1.33it/s]
1|17085|Loss: 0.7712459564208984:  66%|██████▌   | 17085/25880 [3:29:43<1:38:34,  1.49it/s]
1|17086|Loss: 0.8356586694717407:  66%|██████▌   | 17085/25880 [3:29:43<1:38:34,  1.49it/s]
1|17086|Loss: 0.8356586694717407:  66%|██████▌   | 17086/25880 [3:29:43<1:44:52,  1.40it/s]
1|17087|Loss: 0.7660508155822754:  66%|██████▌   | 17086/25880 [3:29:44<1:44:52,  1.40it/s]
1|17087|Loss: 0.7660508155822754:  66%|██████▌   | 17087/25880 [3:29:44<1:42:42,  1.43it/s]
1|17088|Loss: 0.9792351722717285:  66%|██████▌   | 17087/25880 [3:29:45<1:42:42,  1.43it/s]
1|17088|Loss: 0.9792351722717285:  66%|██████▌   | 17088/25880 [3:29:45<1:42:49,  1.42it/s]
1|17089|Loss: 0.756333589553833:  66%|██████▌   | 17088/25880 [3:29:45<1:42:49,  1.42it/s] 
1|17089|Loss: 0.756333589553833:  66%|██████▌   | 17089/25880 [3:29:45<1:39:59,  1.47it/s]
1|17090|Loss: 0.7838428616523743:  66%|██████▌   | 17089/25880 [3:29:46<1:39:59,  1.47it/s]
1|17090|Loss: 0.7838428616523743:  66%|██████▌   | 17090/25880 [3:29:46<1:44:41,  1.40it/s]
1|17091|Loss: 0.8055528402328491:  66%|██████▌   | 17090/25880 [3:29:47<1:44:41,  1.40it/s]
1|17091|Loss: 0.8055528402328491:  66%|██████▌   | 17091/25880 [3:29:47<1:50:53,  1.32it/s]
1|17092|Loss: 0.8555983901023865:  66%|██████▌   | 17091/25880 [3:29:48<1:50:53,  1.32it/s]
1|17092|Loss: 0.8555983901023865:  66%|██████▌   | 17092/25880 [3:29:48<1:55:34,  1.27it/s]
1|17093|Loss: 0.9912957549095154:  66%|██████▌   | 17092/25880 [3:29:48<1:55:34,  1.27it/s]
1|17093|Loss: 0.9912957549095154:  66%|██████▌   | 17093/25880 [3:29:49<1:54:57,  1.27it/s]
1|17094|Loss: 1.0169789791107178:  66%|██████▌   | 17093/25880 [3:29:49<1:54:57,  1.27it/s]
1|17094|Loss: 1.0169789791107178:  66%|██████▌   | 17094/25880 [3:29:50<1:52:41,  1.30it/s]
1|17095|Loss: 0.9013335704803467:  66%|██████▌   | 17094/25880 [3:29:50<1:52:41,  1.30it/s]
1|17095|Loss: 0.9013335704803467:  66%|██████▌   | 17095/25880 [3:29:50<1:54:26,  1.28it/s]
1|17096|Loss: 0.8894717693328857:  66%|██████▌   | 17095/25880 [3:29:51<1:54:26,  1.28it/s]
1|17096|Loss: 0.8894717693328857:  66%|██████▌   | 17096/25880 [3:29:51<1:45:54,  1.38it/s]
1|17097|Loss: 0.7323002815246582:  66%|██████▌   | 17096/25880 [3:29:51<1:45:54,  1.38it/s]
1|17097|Loss: 0.7323002815246582:  66%|██████▌   | 17097/25880 [3:29:52<1:44:04,  1.41it/s]
1|17098|Loss: 0.8510995507240295:  66%|██████▌   | 17097/25880 [3:29:52<1:44:04,  1.41it/s]
1|17098|Loss: 0.8510995507240295:  66%|██████▌   | 17098/25880 [3:29:52<1:35:06,  1.54it/s]
1|17099|Loss: 0.8832322955131531:  66%|██████▌   | 17098/25880 [3:29:52<1:35:06,  1.54it/s]
1|17099|Loss: 0.8832322955131531:  66%|██████▌   | 17099/25880 [3:29:53<1:40:01,  1.46it/s]
1|17100|Loss: 0.7312237620353699:  66%|██████▌   | 17099/25880 [3:29:53<1:40:01,  1.46it/s]
1|17100|Loss: 0.7312237620353699:  66%|██████▌   | 17100/25880 [3:29:54<1:39:16,  1.47it/s]
1|17101|Loss: 0.8735650181770325:  66%|██████▌   | 17100/25880 [3:29:54<1:39:16,  1.47it/s]
1|17101|Loss: 0.8735650181770325:  66%|██████▌   | 17101/25880 [3:29:54<1:37:17,  1.50it/s]
1|17102|Loss: 0.8455943465232849:  66%|██████▌   | 17101/25880 [3:29:55<1:37:17,  1.50it/s]
1|17102|Loss: 0.8455943465232849:  66%|██████▌   | 17102/25880 [3:29:55<1:44:20,  1.40it/s]
1|17103|Loss: 0.8975098729133606:  66%|██████▌   | 17102/25880 [3:29:55<1:44:20,  1.40it/s]
1|17103|Loss: 0.8975098729133606:  66%|██████▌   | 17103/25880 [3:29:56<1:43:27,  1.41it/s]
1|17104|Loss: 0.8449532389640808:  66%|██████▌   | 17103/25880 [3:29:56<1:43:27,  1.41it/s]
1|17104|Loss: 0.8449532389640808:  66%|██████▌   | 17104/25880 [3:29:56<1:40:30,  1.46it/s]
1|17105|Loss: 0.8002927303314209:  66%|██████▌   | 17104/25880 [3:29:57<1:40:30,  1.46it/s]
1|17105|Loss: 0.8002927303314209:  66%|██████▌   | 17105/25880 [3:29:57<1:40:55,  1.45it/s]
1|17106|Loss: 0.9398199319839478:  66%|██████▌   | 17105/25880 [3:29:57<1:40:55,  1.45it/s]
1|17106|Loss: 0.9398199319839478:  66%|██████▌   | 17106/25880 [3:29:58<1:41:31,  1.44it/s]
1|17107|Loss: 0.7666905522346497:  66%|██████��   | 17106/25880 [3:29:58<1:41:31,  1.44it/s]
1|17107|Loss: 0.7666905522346497:  66%|██████▌   | 17107/25880 [3:29:58<1:43:21,  1.41it/s]
1|17108|Loss: 0.8797568678855896:  66%|██████▌   | 17107/25880 [3:29:59<1:43:21,  1.41it/s]
1|17108|Loss: 0.8797568678855896:  66%|██████▌   | 17108/25880 [3:29:59<1:48:41,  1.35it/s]
1|17109|Loss: 0.8343417048454285:  66%|██████▌   | 17108/25880 [3:30:00<1:48:41,  1.35it/s]
1|17109|Loss: 0.8343417048454285:  66%|██████▌   | 17109/25880 [3:30:00<1:49:05,  1.34it/s]
1|17110|Loss: 0.8825505375862122:  66%|██████▌   | 17109/25880 [3:30:00<1:49:05,  1.34it/s]
1|17110|Loss: 0.8825505375862122:  66%|██████▌   | 17110/25880 [3:30:01<1:51:39,  1.31it/s]
1|17111|Loss: 0.8618404865264893:  66%|██████▌   | 17110/25880 [3:30:01<1:51:39,  1.31it/s]
1|17111|Loss: 0.8618404865264893:  66%|██████▌   | 17111/25880 [3:30:02<1:47:35,  1.36it/s]
1|17112|Loss: 0.9146803617477417:  66%|██████▌   | 17111/25880 [3:30:02<1:47:35,  1.36it/s]
1|17112|Loss: 0.9146803617477417:  66%|██████▌   | 17112/25880 [3:30:02<1:45:32,  1.38it/s]
1|17113|Loss: 0.8104409575462341:  66%|██████▌   | 17112/25880 [3:30:03<1:45:32,  1.38it/s]
1|17113|Loss: 0.8104409575462341:  66%|██████▌   | 17113/25880 [3:30:03<1:45:38,  1.38it/s]
1|17114|Loss: 0.7134973406791687:  66%|██████▌   | 17113/25880 [3:30:03<1:45:38,  1.38it/s]
1|17114|Loss: 0.7134973406791687:  66%|██████▌   | 17114/25880 [3:30:03<1:37:57,  1.49it/s]
1|17115|Loss: 0.7330899238586426:  66%|██████▌   | 17114/25880 [3:30:04<1:37:57,  1.49it/s]
1|17115|Loss: 0.7330899238586426:  66%|██████▌   | 17115/25880 [3:30:04<1:35:20,  1.53it/s]
1|17116|Loss: 0.8576162457466125:  66%|██████▌   | 17115/25880 [3:30:04<1:35:20,  1.53it/s]
1|17116|Loss: 0.8576162457466125:  66%|██████▌   | 17116/25880 [3:30:05<1:33:54,  1.56it/s]
1|17117|Loss: 0.9043352603912354:  66%|██████▌   | 17116/25880 [3:30:05<1:33:54,  1.56it/s]
1|17117|Loss: 0.9043352603912354:  66%|██████▌   | 17117/25880 [3:30:05<1:32:43,  1.58it/s]
1|17118|Loss: 0.6697642803192139:  66%|██████▌   | 17117/25880 [3:30:06<1:32:43,  1.58it/s]
1|17118|Loss: 0.6697642803192139:  66%|██████▌   | 17118/25880 [3:30:06<1:40:41,  1.45it/s]
1|17119|Loss: 0.8688519597053528:  66%|██████▌   | 17118/25880 [3:30:07<1:40:41,  1.45it/s]
1|17119|Loss: 0.8688519597053528:  66%|██████▌   | 17119/25880 [3:30:07<1:43:42,  1.41it/s]
1|17120|Loss: 0.8140133023262024:  66%|██████▌   | 17119/25880 [3:30:07<1:43:42,  1.41it/s]
1|17120|Loss: 0.8140133023262024:  66%|██████▌   | 17120/25880 [3:30:08<1:41:28,  1.44it/s]
1|17121|Loss: 0.9979639649391174:  66%|██████▌   | 17120/25880 [3:30:08<1:41:28,  1.44it/s]
1|17121|Loss: 0.9979639649391174:  66%|██████▌   | 17121/25880 [3:30:08<1:47:19,  1.36it/s]
1|17122|Loss: 0.9876259565353394:  66%|██████▌   | 17121/25880 [3:30:09<1:47:19,  1.36it/s]
1|17122|Loss: 0.9876259565353394:  66%|██████▌   | 17122/25880 [3:30:09<1:48:19,  1.35it/s]
1|17123|Loss: 0.9371694922447205:  66%|██████▌   | 17122/25880 [3:30:10<1:48:19,  1.35it/s]
1|17123|Loss: 0.9371694922447205:  66%|██████▌   | 17123/25880 [3:30:10<1:44:33,  1.40it/s]
1|17124|Loss: 0.9656899571418762:  66%|██████▌   | 17123/25880 [3:30:10<1:44:33,  1.40it/s]
1|17124|Loss: 0.9656899571418762:  66%|██████▌   | 17124/25880 [3:30:11<1:44:36,  1.40it/s]
1|17125|Loss: 0.8618283271789551:  66%|██████▌   | 17124/25880 [3:30:11<1:44:36,  1.40it/s]
1|17125|Loss: 0.8618283271789551:  66%|██████▌   | 17125/25880 [3:30:11<1:48:49,  1.34it/s]
1|17126|Loss: 0.9197089672088623:  66%|██████▌   | 17125/25880 [3:30:12<1:48:49,  1.34it/s]
1|17126|Loss: 0.9197089672088623:  66%|██████▌   | 17126/25880 [3:30:12<1:42:41,  1.42it/s]
1|17127|Loss: 0.9484277963638306:  66%|██████▌   | 17126/25880 [3:30:12<1:42:41,  1.42it/s]
1|17127|Loss: 0.9484277963638306:  66%|██████▌   | 17127/25880 [3:30:13<1:42:38,  1.42it/s]
1|17128|Loss: 0.8431476950645447:  66%|██████▌   | 17127/25880 [3:30:13<1:42:38,  1.42it/s]
1|17128|Loss: 0.8431476950645447:  66%|██████▌   | 17128/25880 [3:30:13<1:48:18,  1.35it/s]
1|17129|Loss: 0.7917054295539856:  66%|██████▌   | 17128/25880 [3:30:14<1:48:18,  1.35it/s]
1|17129|Loss: 0.7917054295539856:  66%|██████▌   | 17129/25880 [3:30:14<1:51:30,  1.31it/s]
1|17130|Loss: 0.9090049862861633:  66%|██████▌   | 17129/25880 [3:30:15<1:51:30,  1.31it/s]
1|17130|Loss: 0.9090049862861633:  66%|██████▌   | 17130/25880 [3:30:15<1:50:40,  1.32it/s]
1|17131|Loss: 0.8306986689567566:  66%|██████▌   | 17130/25880 [3:30:15<1:50:40,  1.32it/s]
1|17131|Loss: 0.8306986689567566:  66%|██████▌   | 17131/25880 [3:30:16<1:55:53,  1.26it/s]
1|17132|Loss: 0.8181090354919434:  66%|██████▌   | 17131/25880 [3:30:16<1:55:53,  1.26it/s]
1|17132|Loss: 0.8181090354919434:  66%|██████▌   | 17132/25880 [3:30:17<1:51:19,  1.31it/s]
1|17133|Loss: 0.9269667863845825:  66%|██████▌   | 17132/25880 [3:30:17<1:51:19,  1.31it/s]
1|17133|Loss: 0.9269667863845825:  66%|██████▌   | 17133/25880 [3:30:17<1:49:59,  1.33it/s]
1|17134|Loss: 0.7980166077613831:  66%|██████▌   | 17133/25880 [3:30:18<1:49:59,  1.33it/s]
1|17134|Loss: 0.7980166077613831:  66%|██████▌   | 17134/25880 [3:30:18<1:46:08,  1.37it/s]
1|17135|Loss: 0.9057499766349792:  66%|██████▌   | 17134/25880 [3:30:18<1:46:08,  1.37it/s]
1|17135|Loss: 0.9057499766349792:  66%|██████▌   | 17135/25880 [3:30:19<1:47:29,  1.36it/s]
1|17136|Loss: 0.7935675978660583:  66%|██████▌   | 17135/25880 [3:30:19<1:47:29,  1.36it/s]
1|17136|Loss: 0.7935675978660583:  66%|██████▌   | 17136/25880 [3:30:20<1:49:47,  1.33it/s]
1|17137|Loss: 0.8523482084274292:  66%|██████▌   | 17136/25880 [3:30:20<1:49:47,  1.33it/s]
1|17137|Loss: 0.8523482084274292:  66%|██████▌   | 17137/25880 [3:30:20<1:49:20,  1.33it/s]
1|17138|Loss: 0.667054295539856:  66%|██████▌   | 17137/25880 [3:30:21<1:49:20,  1.33it/s] 
1|17138|Loss: 0.667054295539856:  66%|██████▌   | 17138/25880 [3:30:21<1:44:45,  1.39it/s]
1|17139|Loss: 0.8236687779426575:  66%|██████▌   | 17138/25880 [3:30:21<1:44:45,  1.39it/s]
1|17139|Loss: 0.8236687779426575:  66%|██████▌   | 17139/25880 [3:30:22<1:47:55,  1.35it/s]
1|17140|Loss: 0.835667610168457:  66%|██████▌   | 17139/25880 [3:30:22<1:47:55,  1.35it/s] 
1|17140|Loss: 0.835667610168457:  66%|██████▌   | 17140/25880 [3:30:23<1:52:45,  1.29it/s]
1|17141|Loss: 0.778173565864563:  66%|██████▌   | 17140/25880 [3:30:23<1:52:45,  1.29it/s]
1|17141|Loss: 0.778173565864563:  66%|██████▌   | 17141/25880 [3:30:23<1:49:03,  1.34it/s]
1|17142|Loss: 0.8298959136009216:  66%|██████▌   | 17141/25880 [3:30:24<1:49:03,  1.34it/s]
1|17142|Loss: 0.8298959136009216:  66%|██████▌   | 17142/25880 [3:30:24<1:47:32,  1.35it/s]
1|17143|Loss: 0.8422542214393616:  66%|██████▌   | 17142/25880 [3:30:24<1:47:32,  1.35it/s]
1|17143|Loss: 0.8422542214393616:  66%|██████▌   | 17143/25880 [3:30:25<1:46:44,  1.36it/s]
1|17144|Loss: 0.828636884689331:  66%|██████▌   | 17143/25880 [3:30:25<1:46:44,  1.36it/s] 
1|17144|Loss: 0.828636884689331:  66%|██████▌   | 17144/25880 [3:30:25<1:42:30,  1.42it/s]
1|17145|Loss: 0.9349464178085327:  66%|██████▌   | 17144/25880 [3:30:26<1:42:30,  1.42it/s]
1|17145|Loss: 0.9349464178085327:  66%|██████▌   | 17145/25880 [3:30:26<1:45:10,  1.38it/s]
1|17146|Loss: 0.9691542387008667:  66%|██████▌   | 17145/25880 [3:30:27<1:45:10,  1.38it/s]
1|17146|Loss: 0.9691542387008667:  66%|██████▋   | 17146/25880 [3:30:27<1:45:26,  1.38it/s]
1|17147|Loss: 0.6447570323944092:  66%|██████▋   | 17146/25880 [3:30:27<1:45:26,  1.38it/s]
1|17147|Loss: 0.6447570323944092:  66%|██████▋   | 17147/25880 [3:30:27<1:38:17,  1.48it/s]
1|17148|Loss: 0.9467465877532959:  66%|██████▋   | 17147/25880 [3:30:28<1:38:17,  1.48it/s]
1|17148|Loss: 0.9467465877532959:  66%|██████▋   | 17148/25880 [3:30:28<1:38:37,  1.48it/s]
1|17149|Loss: 0.8097575902938843:  66%|██████▋   | 17148/25880 [3:30:28<1:38:37,  1.48it/s]
1|17149|Loss: 0.8097575902938843:  66%|██████▋   | 17149/25880 [3:30:29<1:39:50,  1.46it/s]
1|17150|Loss: 0.9266325831413269:  66%|██████▋   | 17149/25880 [3:30:29<1:39:50,  1.46it/s]
1|17150|Loss: 0.9266325831413269:  66%|██████▋   | 17150/25880 [3:30:29<1:37:36,  1.49it/s]
1|17151|Loss: 0.7989745736122131:  66%|██████▋   | 17150/25880 [3:30:30<1:37:36,  1.49it/s]
1|17151|Loss: 0.7989745736122131:  66%|██████▋   | 17151/25880 [3:30:30<1:41:07,  1.44it/s]
1|17152|Loss: 0.8818964958190918:  66%|██████▋   | 17151/25880 [3:30:31<1:41:07,  1.44it/s]
1|17152|Loss: 0.8818964958190918:  66%|██████▋   | 17152/25880 [3:30:31<1:47:30,  1.35it/s]
1|17153|Loss: 0.9085517525672913:  66%|██████▋   | 17152/25880 [3:30:31<1:47:30,  1.35it/s]
1|17153|Loss: 0.9085517525672913:  66%|██████▋   | 17153/25880 [3:30:32<1:41:17,  1.44it/s]
1|17154|Loss: 0.966700553894043:  66%|██████▋   | 17153/25880 [3:30:32<1:41:17,  1.44it/s] 
1|17154|Loss: 0.966700553894043:  66%|██████▋   | 17154/25880 [3:30:32<1:37:29,  1.49it/s]
1|17155|Loss: 0.8859856724739075:  66%|██████▋   | 17154/25880 [3:30:33<1:37:29,  1.49it/s]
1|17155|Loss: 0.8859856724739075:  66%|██████▋   | 17155/25880 [3:30:33<1:38:15,  1.48it/s]
1|17156|Loss: 0.8311590552330017:  66%|██████▋   | 17155/25880 [3:30:33<1:38:15,  1.48it/s]
1|17156|Loss: 0.8311590552330017:  66%|██████▋   | 17156/25880 [3:30:34<1:43:30,  1.40it/s]
1|17157|Loss: 0.9692996144294739:  66%|██████▋   | 17156/25880 [3:30:34<1:43:30,  1.40it/s]
1|17157|Loss: 0.9692996144294739:  66%|██████▋   | 17157/25880 [3:30:34<1:43:56,  1.40it/s]
1|17158|Loss: 0.783384382724762:  66%|██████▋   | 17157/25880 [3:30:35<1:43:56,  1.40it/s] 
1|17158|Loss: 0.783384382724762:  66%|██████▋   | 17158/25880 [3:30:35<1:41:02,  1.44it/s]
1|17159|Loss: 0.8071991205215454:  66%|██████▋   | 17158/25880 [3:30:35<1:41:02,  1.44it/s]
1|17159|Loss: 0.8071991205215454:  66%|██████▋   | 17159/25880 [3:30:36<1:45:49,  1.37it/s]
1|17160|Loss: 0.8695026636123657:  66%|██████▋   | 17159/25880 [3:30:36<1:45:49,  1.37it/s]
1|17160|Loss: 0.8695026636123657:  66%|██████▋   | 17160/25880 [3:30:37<1:43:07,  1.41it/s]
1|17161|Loss: 0.893896758556366:  66%|██████▋   | 17160/25880 [3:30:37<1:43:07,  1.41it/s] 
1|17161|Loss: 0.893896758556366:  66%|██████▋   | 17161/25880 [3:30:37<1:43:29,  1.40it/s]
1|17162|Loss: 0.8865067362785339:  66%|██████▋   | 17161/25880 [3:30:38<1:43:29,  1.40it/s]
1|17162|Loss: 0.8865067362785339:  66%|██████▋   | 17162/25880 [3:30:38<1:43:36,  1.40it/s]
1|17163|Loss: 0.8296715021133423:  66%|██████▋   | 17162/25880 [3:30:38<1:43:36,  1.40it/s]
1|17163|Loss: 0.8296715021133423:  66%|██████▋   | 17163/25880 [3:30:39<1:43:53,  1.40it/s]
1|17164|Loss: 0.8503068685531616:  66%|██████▋   | 17163/25880 [3:30:39<1:43:53,  1.40it/s]
1|17164|Loss: 0.8503068685531616:  66%|██████▋   | 17164/25880 [3:30:39<1:46:22,  1.37it/s]
1|17165|Loss: 0.8420363664627075:  66%|██████▋   | 17164/25880 [3:30:40<1:46:22,  1.37it/s]
1|17165|Loss: 0.8420363664627075:  66%|██████▋   | 17165/25880 [3:30:40<1:37:08,  1.50it/s]
1|17166|Loss: 0.7990629076957703:  66%|██████▋   | 17165/25880 [3:30:40<1:37:08,  1.50it/s]
1|17166|Loss: 0.7990629076957703:  66%|██████▋   | 17166/25880 [3:30:41<1:45:07,  1.38it/s]
1|17167|Loss: 0.8402834534645081:  66%|██████▋   | 17166/25880 [3:30:41<1:45:07,  1.38it/s]
1|17167|Loss: 0.8402834534645081:  66%|██████▋   | 17167/25880 [3:30:42<1:50:55,  1.31it/s]
1|17168|Loss: 0.838343620300293:  66%|██████▋   | 17167/25880 [3:30:42<1:50:55,  1.31it/s] 
1|17168|Loss: 0.838343620300293:  66%|██████▋   | 17168/25880 [3:30:42<1:40:31,  1.44it/s]
1|17169|Loss: 0.8927873969078064:  66%|██████▋   | 17168/25880 [3:30:43<1:40:31,  1.44it/s]
1|17169|Loss: 0.8927873969078064:  66%|██████▋   | 17169/25880 [3:30:43<1:38:32,  1.47it/s]
1|17170|Loss: 0.7349977493286133:  66%|██████▋   | 17169/25880 [3:30:43<1:38:32,  1.47it/s]
1|17170|Loss: 0.7349977493286133:  66%|██████▋   | 17170/25880 [3:30:44<1:45:14,  1.38it/s]
1|17171|Loss: 0.8061809539794922:  66%|██████▋   | 17170/25880 [3:30:44<1:45:14,  1.38it/s]
1|17171|Loss: 0.8061809539794922:  66%|██████▋   | 17171/25880 [3:30:44<1:42:47,  1.41it/s]
1|17172|Loss: 0.7326105833053589:  66%|██████▋   | 17171/25880 [3:30:45<1:42:47,  1.41it/s]
1|17172|Loss: 0.7326105833053589:  66%|██████▋   | 17172/25880 [3:30:45<1:42:49,  1.41it/s]
1|17173|Loss: 0.9116052985191345:  66%|██████▋   | 17172/25880 [3:30:45<1:42:49,  1.41it/s]
1|17173|Loss: 0.9116052985191345:  66%|██████▋   | 17173/25880 [3:30:46<1:37:40,  1.49it/s]
1|17174|Loss: 0.6651709079742432:  66%|██████▋   | 17173/25880 [3:30:46<1:37:40,  1.49it/s]
1|17174|Loss: 0.6651709079742432:  66%|██████▋   | 17174/25880 [3:30:47<1:45:11,  1.38it/s]
1|17175|Loss: 0.7354395985603333:  66%|██████▋   | 17174/25880 [3:30:47<1:45:11,  1.38it/s]
1|17175|Loss: 0.7354395985603333:  66%|██████▋   | 17175/25880 [3:30:47<1:39:07,  1.46it/s]
1|17176|Loss: 0.7015131711959839:  66%|██████▋   | 17175/25880 [3:30:47<1:39:07,  1.46it/s]
1|17176|Loss: 0.7015131711959839:  66%|██████▋   | 17176/25880 [3:30:48<1:39:20,  1.46it/s]
1|17177|Loss: 0.9154857993125916:  66%|██████▋   | 17176/25880 [3:30:48<1:39:20,  1.46it/s]
1|17177|Loss: 0.9154857993125916:  66%|██████▋   | 17177/25880 [3:30:48<1:35:23,  1.52it/s]
1|17178|Loss: 0.6509877443313599:  66%|██████▋   | 17177/25880 [3:30:49<1:35:23,  1.52it/s]
1|17178|Loss: 0.6509877443313599:  66%|██████▋   | 17178/25880 [3:30:49<1:43:28,  1.40it/s]
1|17179|Loss: 0.7659973502159119:  66%|██████▋   | 17178/25880 [3:30:50<1:43:28,  1.40it/s]
1|17179|Loss: 0.7659973502159119:  66%|██████���   | 17179/25880 [3:30:50<1:45:44,  1.37it/s]
1|17180|Loss: 0.8383171558380127:  66%|██████▋   | 17179/25880 [3:30:50<1:45:44,  1.37it/s]
1|17180|Loss: 0.8383171558380127:  66%|██████▋   | 17180/25880 [3:30:51<1:44:58,  1.38it/s]
1|17181|Loss: 0.8130465149879456:  66%|██████▋   | 17180/25880 [3:30:51<1:44:58,  1.38it/s]
1|17181|Loss: 0.8130465149879456:  66%|██████▋   | 17181/25880 [3:30:51<1:43:45,  1.40it/s]
1|17182|Loss: 0.8438842296600342:  66%|██████▋   | 17181/25880 [3:30:52<1:43:45,  1.40it/s]
1|17182|Loss: 0.8438842296600342:  66%|██████▋   | 17182/25880 [3:30:52<1:49:01,  1.33it/s]
1|17183|Loss: 0.8341012001037598:  66%|██████▋   | 17182/25880 [3:30:53<1:49:01,  1.33it/s]
1|17183|Loss: 0.8341012001037598:  66%|██████▋   | 17183/25880 [3:30:53<1:48:34,  1.34it/s]
1|17184|Loss: 0.81919926404953:  66%|██████▋   | 17183/25880 [3:30:53<1:48:34,  1.34it/s]  
1|17184|Loss: 0.81919926404953:  66%|██████▋   | 17184/25880 [3:30:54<1:50:09,  1.32it/s]
1|17185|Loss: 0.9247899055480957:  66%|██████▋   | 17184/25880 [3:30:54<1:50:09,  1.32it/s]
1|17185|Loss: 0.9247899055480957:  66%|██████▋   | 17185/25880 [3:30:54<1:46:10,  1.36it/s]
1|17186|Loss: 0.7002261877059937:  66%|██████▋   | 17185/25880 [3:30:55<1:46:10,  1.36it/s]
1|17186|Loss: 0.7002261877059937:  66%|██████▋   | 17186/25880 [3:30:55<1:44:06,  1.39it/s]
1|17187|Loss: 0.8498371839523315:  66%|██████▋   | 17186/25880 [3:30:55<1:44:06,  1.39it/s]
1|17187|Loss: 0.8498371839523315:  66%|██████▋   | 17187/25880 [3:30:56<1:40:13,  1.45it/s]
1|17188|Loss: 0.9521501064300537:  66%|██████▋   | 17187/25880 [3:30:56<1:40:13,  1.45it/s]
1|17188|Loss: 0.9521501064300537:  66%|██████▋   | 17188/25880 [3:30:56<1:40:57,  1.43it/s]
1|17189|Loss: 0.7412422895431519:  66%|██████▋   | 17188/25880 [3:30:57<1:40:57,  1.43it/s]
1|17189|Loss: 0.7412422895431519:  66%|██████▋   | 17189/25880 [3:30:57<1:37:10,  1.49it/s]
1|17190|Loss: 0.8913974761962891:  66%|██████▋   | 17189/25880 [3:30:57<1:37:10,  1.49it/s]
1|17190|Loss: 0.8913974761962891:  66%|██████▋   | 17190/25880 [3:30:58<1:39:02,  1.46it/s]
1|17191|Loss: 0.8693065643310547:  66%|██████▋   | 17190/25880 [3:30:58<1:39:02,  1.46it/s]
1|17191|Loss: 0.8693065643310547:  66%|██████▋   | 17191/25880 [3:30:59<1:46:02,  1.37it/s]
1|17192|Loss: 0.8451535105705261:  66%|██████▋   | 17191/25880 [3:30:59<1:46:02,  1.37it/s]
1|17192|Loss: 0.8451535105705261:  66%|██████▋   | 17192/25880 [3:30:59<1:47:21,  1.35it/s]
1|17193|Loss: 0.8376953601837158:  66%|██████▋   | 17192/25880 [3:31:00<1:47:21,  1.35it/s]
1|17193|Loss: 0.8376953601837158:  66%|██████▋   | 17193/25880 [3:31:00<1:43:43,  1.40it/s]
1|17194|Loss: 0.7408351898193359:  66%|██████▋   | 17193/25880 [3:31:00<1:43:43,  1.40it/s]
1|17194|Loss: 0.7408351898193359:  66%|██████▋   | 17194/25880 [3:31:01<1:42:29,  1.41it/s]
1|17195|Loss: 0.8572140336036682:  66%|██████▋   | 17194/25880 [3:31:01<1:42:29,  1.41it/s]
1|17195|Loss: 0.8572140336036682:  66%|██████▋   | 17195/25880 [3:31:01<1:38:50,  1.46it/s]
1|17196|Loss: 0.7797039151191711:  66%|██████▋   | 17195/25880 [3:31:02<1:38:50,  1.46it/s]
1|17196|Loss: 0.7797039151191711:  66%|██████▋   | 17196/25880 [3:31:02<1:39:51,  1.45it/s]
1|17197|Loss: 0.7486444711685181:  66%|██████▋   | 17196/25880 [3:31:02<1:39:51,  1.45it/s]
1|17197|Loss: 0.7486444711685181:  66%|██████▋   | 17197/25880 [3:31:03<1:41:25,  1.43it/s]
1|17198|Loss: 0.8107990026473999:  66%|██████▋   | 17197/25880 [3:31:03<1:41:25,  1.43it/s]
1|17198|Loss: 0.8107990026473999:  66%|██████▋   | 17198/25880 [3:31:04<1:41:26,  1.43it/s]
1|17199|Loss: 0.839833676815033:  66%|██████▋   | 17198/25880 [3:31:04<1:41:26,  1.43it/s] 
1|17199|Loss: 0.839833676815033:  66%|██████▋   | 17199/25880 [3:31:04<1:42:19,  1.41it/s]
1|17200|Loss: 0.8267616629600525:  66%|██████▋   | 17199/25880 [3:31:05<1:42:19,  1.41it/s]
1|17200|Loss: 0.8267616629600525:  66%|██████▋   | 17200/25880 [3:31:05<1:42:10,  1.42it/s]
1|17201|Loss: 0.8269996047019958:  66%|██████▋   | 17200/25880 [3:31:05<1:42:10,  1.42it/s]
1|17201|Loss: 0.8269996047019958:  66%|██████▋   | 17201/25880 [3:31:06<1:42:44,  1.41it/s]
1|17202|Loss: 0.7875486612319946:  66%|██████▋   | 17201/25880 [3:31:06<1:42:44,  1.41it/s]
1|17202|Loss: 0.7875486612319946:  66%|██████▋   | 17202/25880 [3:31:06<1:43:08,  1.40it/s]
1|17203|Loss: 0.9234355688095093:  66%|██████▋   | 17202/25880 [3:31:07<1:43:08,  1.40it/s]
1|17203|Loss: 0.9234355688095093:  66%|██████▋   | 17203/25880 [3:31:07<1:43:39,  1.40it/s]
1|17204|Loss: 0.9796303510665894:  66%|██████▋   | 17203/25880 [3:31:07<1:43:39,  1.40it/s]
1|17204|Loss: 0.9796303510665894:  66%|██████▋   | 17204/25880 [3:31:08<1:44:08,  1.39it/s]
1|17205|Loss: 1.0156614780426025:  66%|██████▋   | 17204/25880 [3:31:08<1:44:08,  1.39it/s]
1|17205|Loss: 1.0156614780426025:  66%|██████▋   | 17205/25880 [3:31:09<1:48:58,  1.33it/s]
1|17206|Loss: 0.6813955903053284:  66%|██████▋   | 17205/25880 [3:31:09<1:48:58,  1.33it/s]
1|17206|Loss: 0.6813955903053284:  66%|██████▋   | 17206/25880 [3:31:09<1:49:26,  1.32it/s]
1|17207|Loss: 0.8192500472068787:  66%|██████▋   | 17206/25880 [3:31:10<1:49:26,  1.32it/s]
1|17207|Loss: 0.8192500472068787:  66%|██████▋   | 17207/25880 [3:31:10<1:48:37,  1.33it/s]
1|17208|Loss: 0.8779212832450867:  66%|██████▋   | 17207/25880 [3:31:11<1:48:37,  1.33it/s]
1|17208|Loss: 0.8779212832450867:  66%|██████▋   | 17208/25880 [3:31:11<1:47:45,  1.34it/s]
1|17209|Loss: 0.8277989625930786:  66%|██████▋   | 17208/25880 [3:31:11<1:47:45,  1.34it/s]
1|17209|Loss: 0.8277989625930786:  66%|██████▋   | 17209/25880 [3:31:11<1:38:19,  1.47it/s]
1|17210|Loss: 0.7343494892120361:  66%|██████▋   | 17209/25880 [3:31:12<1:38:19,  1.47it/s]
1|17210|Loss: 0.7343494892120361:  66%|██████▋   | 17210/25880 [3:31:12<1:41:45,  1.42it/s]
1|17211|Loss: 0.8732422590255737:  66%|██████▋   | 17210/25880 [3:31:13<1:41:45,  1.42it/s]
1|17211|Loss: 0.8732422590255737:  67%|██████▋   | 17211/25880 [3:31:13<1:39:53,  1.45it/s]
1|17212|Loss: 0.8223726749420166:  67%|██████▋   | 17211/25880 [3:31:13<1:39:53,  1.45it/s]
1|17212|Loss: 0.8223726749420166:  67%|██████▋   | 17212/25880 [3:31:14<1:40:49,  1.43it/s]
1|17213|Loss: 0.8598195910453796:  67%|██████▋   | 17212/25880 [3:31:14<1:40:49,  1.43it/s]
1|17213|Loss: 0.8598195910453796:  67%|██████▋   | 17213/25880 [3:31:14<1:44:10,  1.39it/s]
1|17214|Loss: 0.7995482087135315:  67%|██████▋   | 17213/25880 [3:31:15<1:44:10,  1.39it/s]
1|17214|Loss: 0.7995482087135315:  67%|██████▋   | 17214/25880 [3:31:15<1:43:59,  1.39it/s]
1|17215|Loss: 0.9376492500305176:  67%|██████▋   | 17214/25880 [3:31:15<1:43:59,  1.39it/s]
1|17215|Loss: 0.9376492500305176:  67%|██████▋   | 17215/25880 [3:31:16<1:47:30,  1.34it/s]
1|17216|Loss: 0.782614529132843:  67%|██████▋   | 17215/25880 [3:31:16<1:47:30,  1.34it/s] 
1|17216|Loss: 0.782614529132843:  67%|██████▋   | 17216/25880 [3:31:16<1:39:46,  1.45it/s]
1|17217|Loss: 0.8304063081741333:  67%|██████▋   | 17216/25880 [3:31:17<1:39:46,  1.45it/s]
1|17217|Loss: 0.8304063081741333:  67%|██████▋   | 17217/25880 [3:31:17<1:36:09,  1.50it/s]
1|17218|Loss: 0.7930886149406433:  67%|██████▋   | 17217/25880 [3:31:17<1:36:09,  1.50it/s]
1|17218|Loss: 0.7930886149406433:  67%|██████▋   | 17218/25880 [3:31:18<1:41:49,  1.42it/s]
1|17219|Loss: 0.8906543850898743:  67%|██████▋   | 17218/25880 [3:31:18<1:41:49,  1.42it/s]
1|17219|Loss: 0.8906543850898743:  67%|██████▋   | 17219/25880 [3:31:19<1:44:07,  1.39it/s]
1|17220|Loss: 0.8330545425415039:  67%|██████▋   | 17219/25880 [3:31:19<1:44:07,  1.39it/s]
1|17220|Loss: 0.8330545425415039:  67%|██████▋   | 17220/25880 [3:31:19<1:44:29,  1.38it/s]
1|17221|Loss: 0.9469516277313232:  67%|██████▋   | 17220/25880 [3:31:20<1:44:29,  1.38it/s]
1|17221|Loss: 0.9469516277313232:  67%|██████▋   | 17221/25880 [3:31:20<1:44:23,  1.38it/s]
1|17222|Loss: 0.8997093439102173:  67%|██████▋   | 17221/25880 [3:31:20<1:44:23,  1.38it/s]
1|17222|Loss: 0.8997093439102173:  67%|██████▋   | 17222/25880 [3:31:21<1:48:23,  1.33it/s]
1|17223|Loss: 0.9115973711013794:  67%|██████▋   | 17222/25880 [3:31:21<1:48:23,  1.33it/s]
1|17223|Loss: 0.9115973711013794:  67%|██████▋   | 17223/25880 [3:31:22<1:48:51,  1.33it/s]
1|17224|Loss: 0.8041535019874573:  67%|██████▋   | 17223/25880 [3:31:22<1:48:51,  1.33it/s]
1|17224|Loss: 0.8041535019874573:  67%|██████▋   | 17224/25880 [3:31:22<1:47:10,  1.35it/s]
1|17225|Loss: 0.983410120010376:  67%|██████▋   | 17224/25880 [3:31:23<1:47:10,  1.35it/s] 
1|17225|Loss: 0.983410120010376:  67%|██████▋   | 17225/25880 [3:31:23<1:43:10,  1.40it/s]
1|17226|Loss: 0.9405000805854797:  67%|██████▋   | 17225/25880 [3:31:23<1:43:10,  1.40it/s]
1|17226|Loss: 0.9405000805854797:  67%|██████▋   | 17226/25880 [3:31:24<1:42:08,  1.41it/s]
1|17227|Loss: 0.9318288564682007:  67%|██████▋   | 17226/25880 [3:31:24<1:42:08,  1.41it/s]
1|17227|Loss: 0.9318288564682007:  67%|██████▋   | 17227/25880 [3:31:24<1:43:02,  1.40it/s]
1|17228|Loss: 0.8829745650291443:  67%|██████▋   | 17227/25880 [3:31:25<1:43:02,  1.40it/s]
1|17228|Loss: 0.8829745650291443:  67%|██████▋   | 17228/25880 [3:31:25<1:42:50,  1.40it/s]
1|17229|Loss: 0.8229141235351562:  67%|██████▋   | 17228/25880 [3:31:25<1:42:50,  1.40it/s]
1|17229|Loss: 0.8229141235351562:  67%|██████▋   | 17229/25880 [3:31:26<1:39:08,  1.45it/s]
1|17230|Loss: 0.7596122026443481:  67%|██████▋   | 17229/25880 [3:31:26<1:39:08,  1.45it/s]
1|17230|Loss: 0.7596122026443481:  67%|██████▋   | 17230/25880 [3:31:26<1:34:47,  1.52it/s]
1|17231|Loss: 0.926693856716156:  67%|██████▋   | 17230/25880 [3:31:27<1:34:47,  1.52it/s] 
1|17231|Loss: 0.926693856716156:  67%|██████▋   | 17231/25880 [3:31:27<1:36:38,  1.49it/s]
1|17232|Loss: 0.8761488795280457:  67%|██████▋   | 17231/25880 [3:31:27<1:36:38,  1.49it/s]
1|17232|Loss: 0.8761488795280457:  67%|██████▋   | 17232/25880 [3:31:28<1:36:03,  1.50it/s]
1|17233|Loss: 0.8762091398239136:  67%|██████▋   | 17232/25880 [3:31:28<1:36:03,  1.50it/s]
1|17233|Loss: 0.8762091398239136:  67%|██████▋   | 17233/25880 [3:31:28<1:40:18,  1.44it/s]
1|17234|Loss: 0.8873862028121948:  67%|██████▋   | 17233/25880 [3:31:29<1:40:18,  1.44it/s]
1|17234|Loss: 0.8873862028121948:  67%|██████▋   | 17234/25880 [3:31:29<1:46:52,  1.35it/s]
1|17235|Loss: 0.8894246816635132:  67%|██████▋   | 17234/25880 [3:31:30<1:46:52,  1.35it/s]
1|17235|Loss: 0.8894246816635132:  67%|██████▋   | 17235/25880 [3:31:30<1:44:33,  1.38it/s]
1|17236|Loss: 0.8609697818756104:  67%|██████▋   | 17235/25880 [3:31:30<1:44:33,  1.38it/s]
1|17236|Loss: 0.8609697818756104:  67%|██████▋   | 17236/25880 [3:31:31<1:48:40,  1.33it/s]
1|17237|Loss: 0.9128119349479675:  67%|██████▋   | 17236/25880 [3:31:31<1:48:40,  1.33it/s]
1|17237|Loss: 0.9128119349479675:  67%|██████▋   | 17237/25880 [3:31:31<1:46:19,  1.35it/s]
1|17238|Loss: 0.8499655723571777:  67%|██████▋   | 17237/25880 [3:31:32<1:46:19,  1.35it/s]
1|17238|Loss: 0.8499655723571777:  67%|██████▋   | 17238/25880 [3:31:32<1:45:15,  1.37it/s]
1|17239|Loss: 0.8728420734405518:  67%|██████▋   | 17238/25880 [3:31:33<1:45:15,  1.37it/s]
1|17239|Loss: 0.8728420734405518:  67%|██████▋   | 17239/25880 [3:31:33<1:47:34,  1.34it/s]
1|17240|Loss: 0.910007119178772:  67%|██████▋   | 17239/25880 [3:31:33<1:47:34,  1.34it/s] 
1|17240|Loss: 0.910007119178772:  67%|██████▋   | 17240/25880 [3:31:34<1:46:32,  1.35it/s]
1|17241|Loss: 0.8760426044464111:  67%|██████▋   | 17240/25880 [3:31:34<1:46:32,  1.35it/s]
1|17241|Loss: 0.8760426044464111:  67%|██████▋   | 17241/25880 [3:31:34<1:46:25,  1.35it/s]
1|17242|Loss: 0.9053604602813721:  67%|██████▋   | 17241/25880 [3:31:35<1:46:25,  1.35it/s]
1|17242|Loss: 0.9053604602813721:  67%|██████▋   | 17242/25880 [3:31:35<1:43:02,  1.40it/s]
1|17243|Loss: 0.8989244699478149:  67%|██████▋   | 17242/25880 [3:31:36<1:43:02,  1.40it/s]
1|17243|Loss: 0.8989244699478149:  67%|██████▋   | 17243/25880 [3:31:36<1:43:19,  1.39it/s]
1|17244|Loss: 0.8025896549224854:  67%|██████▋   | 17243/25880 [3:31:36<1:43:19,  1.39it/s]
1|17244|Loss: 0.8025896549224854:  67%|██████▋   | 17244/25880 [3:31:36<1:40:05,  1.44it/s]
1|17245|Loss: 0.8748069405555725:  67%|██████▋   | 17244/25880 [3:31:37<1:40:05,  1.44it/s]
1|17245|Loss: 0.8748069405555725:  67%|██████▋   | 17245/25880 [3:31:37<1:41:03,  1.42it/s]
1|17246|Loss: 0.7733784914016724:  67%|██████▋   | 17245/25880 [3:31:38<1:41:03,  1.42it/s]
1|17246|Loss: 0.7733784914016724:  67%|██████▋   | 17246/25880 [3:31:38<1:41:35,  1.42it/s]
1|17247|Loss: 0.7671933174133301:  67%|██████▋   | 17246/25880 [3:31:38<1:41:35,  1.42it/s]
1|17247|Loss: 0.7671933174133301:  67%|██████▋   | 17247/25880 [3:31:39<1:38:23,  1.46it/s]
1|17248|Loss: 0.8419116735458374:  67%|██████▋   | 17247/25880 [3:31:39<1:38:23,  1.46it/s]
1|17248|Loss: 0.8419116735458374:  67%|██████▋   | 17248/25880 [3:31:39<1:35:26,  1.51it/s]
1|17249|Loss: 0.7908437252044678:  67%|██████▋   | 17248/25880 [3:31:40<1:35:26,  1.51it/s]
1|17249|Loss: 0.7908437252044678:  67%|██████▋   | 17249/25880 [3:31:40<1:37:29,  1.48it/s]
1|17250|Loss: 0.9286466240882874:  67%|██████▋   | 17249/25880 [3:31:40<1:37:29,  1.48it/s]
1|17250|Loss: 0.9286466240882874:  67%|██████▋   | 17250/25880 [3:31:41<1:40:26,  1.43it/s]
1|17251|Loss: 0.8704262971878052:  67%|██████▋   | 17250/25880 [3:31:41<1:40:26,  1.43it/s]
1|17251|Loss: 0.8704262971878052:  67%|██████▋   | 17251/25880 [3:31:41<1:36:57,  1.48it/s]
1|17252|Loss: 0.9366147518157959:  67%|█████���▋   | 17251/25880 [3:31:42<1:36:57,  1.48it/s]
1|17252|Loss: 0.9366147518157959:  67%|██████▋   | 17252/25880 [3:31:42<1:42:15,  1.41it/s]
1|17253|Loss: 0.8218016624450684:  67%|██████▋   | 17252/25880 [3:31:42<1:42:15,  1.41it/s]
1|17253|Loss: 0.8218016624450684:  67%|██████▋   | 17253/25880 [3:31:43<1:34:55,  1.51it/s]
1|17254|Loss: 0.8725371956825256:  67%|██████▋   | 17253/25880 [3:31:43<1:34:55,  1.51it/s]
1|17254|Loss: 0.8725371956825256:  67%|██████▋   | 17254/25880 [3:31:43<1:34:26,  1.52it/s]
1|17255|Loss: 0.6023141741752625:  67%|██████▋   | 17254/25880 [3:31:44<1:34:26,  1.52it/s]
1|17255|Loss: 0.6023141741752625:  67%|██████▋   | 17255/25880 [3:31:44<1:47:02,  1.34it/s]
1|17256|Loss: 0.8570186495780945:  67%|██████▋   | 17255/25880 [3:31:45<1:47:02,  1.34it/s]
1|17256|Loss: 0.8570186495780945:  67%|██████▋   | 17256/25880 [3:31:45<1:54:51,  1.25it/s]
1|17257|Loss: 0.8838844895362854:  67%|██████▋   | 17256/25880 [3:31:46<1:54:51,  1.25it/s]
1|17257|Loss: 0.8838844895362854:  67%|██████▋   | 17257/25880 [3:31:46<1:49:03,  1.32it/s]
1|17258|Loss: 0.7334602475166321:  67%|██████▋   | 17257/25880 [3:31:46<1:49:03,  1.32it/s]
1|17258|Loss: 0.7334602475166321:  67%|██████▋   | 17258/25880 [3:31:46<1:46:49,  1.35it/s]
1|17259|Loss: 0.8361531496047974:  67%|██████▋   | 17258/25880 [3:31:47<1:46:49,  1.35it/s]
1|17259|Loss: 0.8361531496047974:  67%|██████▋   | 17259/25880 [3:31:47<1:46:49,  1.34it/s]
1|17260|Loss: 1.1820653676986694:  67%|██████▋   | 17259/25880 [3:31:48<1:46:49,  1.34it/s]
1|17260|Loss: 1.1820653676986694:  67%|██████▋   | 17260/25880 [3:31:48<1:45:27,  1.36it/s]
1|17261|Loss: 0.8895843625068665:  67%|██████▋   | 17260/25880 [3:31:48<1:45:27,  1.36it/s]
1|17261|Loss: 0.8895843625068665:  67%|██████▋   | 17261/25880 [3:31:49<1:51:29,  1.29it/s]
1|17262|Loss: 0.8380557298660278:  67%|██████▋   | 17261/25880 [3:31:49<1:51:29,  1.29it/s]
1|17262|Loss: 0.8380557298660278:  67%|██████▋   | 17262/25880 [3:31:50<1:51:17,  1.29it/s]
1|17263|Loss: 0.7405481934547424:  67%|██████▋   | 17262/25880 [3:31:50<1:51:17,  1.29it/s]
1|17263|Loss: 0.7405481934547424:  67%|██████▋   | 17263/25880 [3:31:50<1:46:19,  1.35it/s]
1|17264|Loss: 0.8112150430679321:  67%|██████▋   | 17263/25880 [3:31:51<1:46:19,  1.35it/s]
1|17264|Loss: 0.8112150430679321:  67%|██████▋   | 17264/25880 [3:31:51<1:49:33,  1.31it/s]
1|17265|Loss: 0.725304901599884:  67%|██████▋   | 17264/25880 [3:31:52<1:49:33,  1.31it/s] 
1|17265|Loss: 0.725304901599884:  67%|██████▋   | 17265/25880 [3:31:52<1:52:55,  1.27it/s]
1|17266|Loss: 1.0119426250457764:  67%|██████▋   | 17265/25880 [3:31:52<1:52:55,  1.27it/s]
1|17266|Loss: 1.0119426250457764:  67%|██████▋   | 17266/25880 [3:31:53<1:56:05,  1.24it/s]
1|17267|Loss: 0.8407232761383057:  67%|██████▋   | 17266/25880 [3:31:53<1:56:05,  1.24it/s]
1|17267|Loss: 0.8407232761383057:  67%|██████▋   | 17267/25880 [3:31:54<1:54:31,  1.25it/s]
1|17268|Loss: 0.8384436964988708:  67%|██████▋   | 17267/25880 [3:31:54<1:54:31,  1.25it/s]
1|17268|Loss: 0.8384436964988708:  67%|██████▋   | 17268/25880 [3:31:54<1:47:51,  1.33it/s]
1|17269|Loss: 0.8542178273200989:  67%|██████▋   | 17268/25880 [3:31:55<1:47:51,  1.33it/s]
1|17269|Loss: 0.8542178273200989:  67%|██████▋   | 17269/25880 [3:31:55<1:50:44,  1.30it/s]
1|17270|Loss: 0.8077174425125122:  67%|██████▋   | 17269/25880 [3:31:55<1:50:44,  1.30it/s]
1|17270|Loss: 0.8077174425125122:  67%|██████▋   | 17270/25880 [3:31:55<1:38:46,  1.45it/s]
1|17271|Loss: 0.936310350894928:  67%|██████▋   | 17270/25880 [3:31:56<1:38:46,  1.45it/s] 
1|17271|Loss: 0.936310350894928:  67%|██████▋   | 17271/25880 [3:31:56<1:30:43,  1.58it/s]
1|17272|Loss: 0.7802153825759888:  67%|██████▋   | 17271/25880 [3:31:56<1:30:43,  1.58it/s]
1|17272|Loss: 0.7802153825759888:  67%|██████▋   | 17272/25880 [3:31:57<1:32:46,  1.55it/s]
1|17273|Loss: 0.8340648412704468:  67%|██████▋   | 17272/25880 [3:31:57<1:32:46,  1.55it/s]
1|17273|Loss: 0.8340648412704468:  67%|██████▋   | 17273/25880 [3:31:57<1:36:17,  1.49it/s]
1|17274|Loss: 0.8571709394454956:  67%|██████▋   | 17273/25880 [3:31:58<1:36:17,  1.49it/s]
1|17274|Loss: 0.8571709394454956:  67%|██████▋   | 17274/25880 [3:31:58<1:43:03,  1.39it/s]
1|17275|Loss: 0.9894139170646667:  67%|██████▋   | 17274/25880 [3:31:59<1:43:03,  1.39it/s]
1|17275|Loss: 0.9894139170646667:  67%|██████▋   | 17275/25880 [3:31:59<1:41:45,  1.41it/s]
1|17276|Loss: 0.946985125541687:  67%|██████▋   | 17275/25880 [3:31:59<1:41:45,  1.41it/s] 
1|17276|Loss: 0.946985125541687:  67%|██████▋   | 17276/25880 [3:32:00<1:45:26,  1.36it/s]
1|17277|Loss: 0.8910915851593018:  67%|██████▋   | 17276/25880 [3:32:00<1:45:26,  1.36it/s]
1|17277|Loss: 0.8910915851593018:  67%|██████▋   | 17277/25880 [3:32:01<1:50:02,  1.30it/s]
1|17278|Loss: 0.8139415383338928:  67%|██████▋   | 17277/25880 [3:32:01<1:50:02,  1.30it/s]
1|17278|Loss: 0.8139415383338928:  67%|██████▋   | 17278/25880 [3:32:01<1:53:55,  1.26it/s]
1|17279|Loss: 0.8664928674697876:  67%|██████▋   | 17278/25880 [3:32:02<1:53:55,  1.26it/s]
1|17279|Loss: 0.8664928674697876:  67%|██████▋   | 17279/25880 [3:32:02<1:56:35,  1.23it/s]
1|17280|Loss: 0.8750086426734924:  67%|██████▋   | 17279/25880 [3:32:03<1:56:35,  1.23it/s]
1|17280|Loss: 0.8750086426734924:  67%|██████▋   | 17280/25880 [3:32:03<1:57:37,  1.22it/s]
1|17281|Loss: 0.8393560647964478:  67%|██████▋   | 17280/25880 [3:32:04<1:57:37,  1.22it/s]
1|17281|Loss: 0.8393560647964478:  67%|██████▋   | 17281/25880 [3:32:04<1:57:00,  1.22it/s]
1|17282|Loss: 0.7581693530082703:  67%|██████▋   | 17281/25880 [3:32:04<1:57:00,  1.22it/s]
1|17282|Loss: 0.7581693530082703:  67%|██████▋   | 17282/25880 [3:32:05<1:48:42,  1.32it/s]
1|17283|Loss: 0.9594123363494873:  67%|██████▋   | 17282/25880 [3:32:05<1:48:42,  1.32it/s]
1|17283|Loss: 0.9594123363494873:  67%|██████▋   | 17283/25880 [3:32:05<1:45:19,  1.36it/s]
1|17284|Loss: 1.0489051342010498:  67%|██████▋   | 17283/25880 [3:32:06<1:45:19,  1.36it/s]
1|17284|Loss: 1.0489051342010498:  67%|██████▋   | 17284/25880 [3:32:06<1:40:53,  1.42it/s]
1|17285|Loss: 0.848065197467804:  67%|██████▋   | 17284/25880 [3:32:06<1:40:53,  1.42it/s] 
1|17285|Loss: 0.848065197467804:  67%|██████▋   | 17285/25880 [3:32:07<1:46:16,  1.35it/s]
1|17286|Loss: 0.8784690499305725:  67%|██████▋   | 17285/25880 [3:32:07<1:46:16,  1.35it/s]
1|17286|Loss: 0.8784690499305725:  67%|██████▋   | 17286/25880 [3:32:08<1:56:53,  1.23it/s]
1|17287|Loss: 0.7498944997787476:  67%|██████▋   | 17286/25880 [3:32:08<1:56:53,  1.23it/s]
1|17287|Loss: 0.7498944997787476:  67%|██████▋   | 17287/25880 [3:32:09<2:04:55,  1.15it/s]
1|17288|Loss: 0.789455235004425:  67%|██████▋   | 17287/25880 [3:32:09<2:04:55,  1.15it/s] 
1|17288|Loss: 0.789455235004425:  67%|██████▋   | 17288/25880 [3:32:10<2:04:06,  1.15it/s]
1|17289|Loss: 0.6609506011009216:  67%|██████▋   | 17288/25880 [3:32:10<2:04:06,  1.15it/s]
1|17289|Loss: 0.6609506011009216:  67%|██████▋   | 17289/25880 [3:32:10<2:05:22,  1.14it/s]
1|17290|Loss: 0.6973839402198792:  67%|██████▋   | 17289/25880 [3:32:11<2:05:22,  1.14it/s]
1|17290|Loss: 0.6973839402198792:  67%|██████▋   | 17290/25880 [3:32:11<2:00:51,  1.18it/s]
1|17291|Loss: 0.8907707333564758:  67%|██████▋   | 17290/25880 [3:32:12<2:00:51,  1.18it/s]
1|17291|Loss: 0.8907707333564758:  67%|██████▋   | 17291/25880 [3:32:12<1:50:19,  1.30it/s]
1|17292|Loss: 0.7831589579582214:  67%|██████▋   | 17291/25880 [3:32:12<1:50:19,  1.30it/s]
1|17292|Loss: 0.7831589579582214:  67%|██████▋   | 17292/25880 [3:32:12<1:42:26,  1.40it/s]
1|17293|Loss: 0.7054386138916016:  67%|██████▋   | 17292/25880 [3:32:13<1:42:26,  1.40it/s]
1|17293|Loss: 0.7054386138916016:  67%|██████▋   | 17293/25880 [3:32:13<1:41:38,  1.41it/s]
1|17294|Loss: 0.8763809204101562:  67%|██████▋   | 17293/25880 [3:32:13<1:41:38,  1.41it/s]
1|17294|Loss: 0.8763809204101562:  67%|██████▋   | 17294/25880 [3:32:14<1:45:03,  1.36it/s]
1|17295|Loss: 0.7209119200706482:  67%|██████▋   | 17294/25880 [3:32:14<1:45:03,  1.36it/s]
1|17295|Loss: 0.7209119200706482:  67%|██████▋   | 17295/25880 [3:32:15<1:45:36,  1.35it/s]
1|17296|Loss: 0.7530816793441772:  67%|██████▋   | 17295/25880 [3:32:15<1:45:36,  1.35it/s]
1|17296|Loss: 0.7530816793441772:  67%|██████▋   | 17296/25880 [3:32:15<1:47:51,  1.33it/s]
1|17297|Loss: 0.7980471253395081:  67%|██████▋   | 17296/25880 [3:32:16<1:47:51,  1.33it/s]
1|17297|Loss: 0.7980471253395081:  67%|██████▋   | 17297/25880 [3:32:16<1:44:25,  1.37it/s]
1|17298|Loss: 0.7887691259384155:  67%|██████▋   | 17297/25880 [3:32:16<1:44:25,  1.37it/s]
1|17298|Loss: 0.7887691259384155:  67%|██████▋   | 17298/25880 [3:32:17<1:42:38,  1.39it/s]
1|17299|Loss: 0.8547565937042236:  67%|██████▋   | 17298/25880 [3:32:17<1:42:38,  1.39it/s]
1|17299|Loss: 0.8547565937042236:  67%|██████▋   | 17299/25880 [3:32:18<1:47:37,  1.33it/s]
1|17300|Loss: 0.9218649864196777:  67%|██████▋   | 17299/25880 [3:32:18<1:47:37,  1.33it/s]
1|17300|Loss: 0.9218649864196777:  67%|██████▋   | 17300/25880 [3:32:18<1:45:04,  1.36it/s]
1|17301|Loss: 0.7423250079154968:  67%|██████▋   | 17300/25880 [3:32:19<1:45:04,  1.36it/s]
1|17301|Loss: 0.7423250079154968:  67%|██████▋   | 17301/25880 [3:32:19<1:43:08,  1.39it/s]
1|17302|Loss: 0.6954622864723206:  67%|██████▋   | 17301/25880 [3:32:19<1:43:08,  1.39it/s]
1|17302|Loss: 0.6954622864723206:  67%|██████▋   | 17302/25880 [3:32:20<1:42:16,  1.40it/s]
1|17303|Loss: 0.7508782148361206:  67%|██████▋   | 17302/25880 [3:32:20<1:42:16,  1.40it/s]
1|17303|Loss: 0.7508782148361206:  67%|██████▋   | 17303/25880 [3:32:21<1:46:47,  1.34it/s]
1|17304|Loss: 0.8819747567176819:  67%|██████▋   | 17303/25880 [3:32:21<1:46:47,  1.34it/s]
1|17304|Loss: 0.8819747567176819:  67%|██████▋   | 17304/25880 [3:32:21<1:49:55,  1.30it/s]
1|17305|Loss: 0.7421157956123352:  67%|██████▋   | 17304/25880 [3:32:22<1:49:55,  1.30it/s]
1|17305|Loss: 0.7421157956123352:  67%|██████▋   | 17305/25880 [3:32:22<1:48:00,  1.32it/s]
1|17306|Loss: 0.9455946683883667:  67%|██████▋   | 17305/25880 [3:32:22<1:48:00,  1.32it/s]
1|17306|Loss: 0.9455946683883667:  67%|██████▋   | 17306/25880 [3:32:23<1:39:50,  1.43it/s]
1|17307|Loss: 0.8517857789993286:  67%|██████▋   | 17306/25880 [3:32:23<1:39:50,  1.43it/s]
1|17307|Loss: 0.8517857789993286:  67%|██████▋   | 17307/25880 [3:32:23<1:45:59,  1.35it/s]
1|17308|Loss: 0.8775349855422974:  67%|██████▋   | 17307/25880 [3:32:24<1:45:59,  1.35it/s]
1|17308|Loss: 0.8775349855422974:  67%|██████▋   | 17308/25880 [3:32:24<1:44:14,  1.37it/s]
1|17309|Loss: 0.7893009781837463:  67%|██████▋   | 17308/25880 [3:32:24<1:44:14,  1.37it/s]
1|17309|Loss: 0.7893009781837463:  67%|██████▋   | 17309/25880 [3:32:25<1:31:25,  1.56it/s]
1|17310|Loss: 0.7948817014694214:  67%|██████▋   | 17309/25880 [3:32:25<1:31:25,  1.56it/s]
1|17310|Loss: 0.7948817014694214:  67%|██████▋   | 17310/25880 [3:32:25<1:35:47,  1.49it/s]
1|17311|Loss: 0.9054544568061829:  67%|██████▋   | 17310/25880 [3:32:26<1:35:47,  1.49it/s]
1|17311|Loss: 0.9054544568061829:  67%|██████▋   | 17311/25880 [3:32:26<1:34:10,  1.52it/s]
1|17312|Loss: 0.9189448356628418:  67%|██████▋   | 17311/25880 [3:32:26<1:34:10,  1.52it/s]
1|17312|Loss: 0.9189448356628418:  67%|██████▋   | 17312/25880 [3:32:26<1:27:23,  1.63it/s]
1|17313|Loss: 0.7636318206787109:  67%|██████▋   | 17312/25880 [3:32:27<1:27:23,  1.63it/s]
1|17313|Loss: 0.7636318206787109:  67%|██████▋   | 17313/25880 [3:32:27<1:29:27,  1.60it/s]
1|17314|Loss: 1.0578432083129883:  67%|██████▋   | 17313/25880 [3:32:27<1:29:27,  1.60it/s]
1|17314|Loss: 1.0578432083129883:  67%|██████▋   | 17314/25880 [3:32:28<1:28:31,  1.61it/s]
1|17315|Loss: 0.8427981734275818:  67%|██████▋   | 17314/25880 [3:32:28<1:28:31,  1.61it/s]
1|17315|Loss: 0.8427981734275818:  67%|██████▋   | 17315/25880 [3:32:28<1:26:42,  1.65it/s]
1|17316|Loss: 0.798434853553772:  67%|██████▋   | 17315/25880 [3:32:29<1:26:42,  1.65it/s] 
1|17316|Loss: 0.798434853553772:  67%|██████▋   | 17316/25880 [3:32:29<1:34:40,  1.51it/s]
1|17317|Loss: 0.9102018475532532:  67%|██████▋   | 17316/25880 [3:32:30<1:34:40,  1.51it/s]
1|17317|Loss: 0.9102018475532532:  67%|██████▋   | 17317/25880 [3:32:30<1:39:02,  1.44it/s]
1|17318|Loss: 0.7665736675262451:  67%|██████▋   | 17317/25880 [3:32:30<1:39:02,  1.44it/s]
1|17318|Loss: 0.7665736675262451:  67%|██████▋   | 17318/25880 [3:32:30<1:35:48,  1.49it/s]
1|17319|Loss: 0.7945449948310852:  67%|██████▋   | 17318/25880 [3:32:31<1:35:48,  1.49it/s]
1|17319|Loss: 0.7945449948310852:  67%|██████▋   | 17319/25880 [3:32:31<1:39:01,  1.44it/s]
1|17320|Loss: 0.7912301421165466:  67%|██████▋   | 17319/25880 [3:32:32<1:39:01,  1.44it/s]
1|17320|Loss: 0.7912301421165466:  67%|██████▋   | 17320/25880 [3:32:32<1:37:28,  1.46it/s]
1|17321|Loss: 0.8627500534057617:  67%|██████▋   | 17320/25880 [3:32:32<1:37:28,  1.46it/s]
1|17321|Loss: 0.8627500534057617:  67%|██████▋   | 17321/25880 [3:32:33<1:43:52,  1.37it/s]
1|17322|Loss: 0.9434276819229126:  67%|██████▋   | 17321/25880 [3:32:33<1:43:52,  1.37it/s]
1|17322|Loss: 0.9434276819229126:  67%|██████▋   | 17322/25880 [3:32:34<1:46:07,  1.34it/s]
1|17323|Loss: 0.8860427141189575:  67%|██████▋   | 17322/25880 [3:32:34<1:46:07,  1.34it/s]
1|17323|Loss: 0.8860427141189575:  67%|██████▋   | 17323/25880 [3:32:34<1:54:01,  1.25it/s]
1|17324|Loss: 0.7174545526504517:  67%|██████▋   | 17323/25880 [3:32:35<1:54:01,  1.25it/s]
1|17324|Loss: 0.7174545526504517:  67%|██████▋   | 17324/25880 [3:32:35<1:46:58,  1.33it/s]
1|17325|Loss: 0.7962344288825989:  67%|██████▋   | 17324/25880 [3:32:35<1:46:58,  1.33it/s]
1|17325|Loss: 0.7962344288825989:  67%|██████▋   | 17325/25880 [3:32:36<1:43:37,  1.38it/s]
1|17326|Loss: 0.6773178577423096:  67%|██████▋   | 17325/25880 [3:32:36<1:43:37,  1.38it/s]
1|17326|Loss: 0.6773178577423096:  67%|██████▋   | 17326/25880 [3:32:37<1:53:04,  1.26it/s]
1|17327|Loss: 0.7347180843353271:  67%|██████▋   | 17326/25880 [3:32:37<1:53:04,  1.26it/s]
1|17327|Loss: 0.7347180843353271:  67%|██████▋   | 17327/25880 [3:32:37<1:48:03,  1.32it/s]
1|17328|Loss: 0.8999842405319214:  67%|██████▋   | 17327/25880 [3:32:38<1:48:03,  1.32it/s]
1|17328|Loss: 0.8999842405319214:  67%|██████▋   | 17328/25880 [3:32:38<1:49:38,  1.30it/s]
1|17329|Loss: 0.7987841963768005:  67%|██████▋   | 17328/25880 [3:32:39<1:49:38,  1.30it/s]
1|17329|Loss: 0.7987841963768005:  67%|██████▋   | 17329/25880 [3:32:39<1:49:12,  1.31it/s]
1|17330|Loss: 0.809212327003479:  67%|██████▋   | 17329/25880 [3:32:39<1:49:12,  1.31it/s] 
1|17330|Loss: 0.809212327003479:  67%|██████▋   | 17330/25880 [3:32:40<1:48:02,  1.32it/s]
1|17331|Loss: 0.8503641486167908:  67%|██████▋   | 17330/25880 [3:32:40<1:48:02,  1.32it/s]
1|17331|Loss: 0.8503641486167908:  67%|██████▋   | 17331/25880 [3:32:41<1:51:52,  1.27it/s]
1|17332|Loss: 0.7971498370170593:  67%|██████▋   | 17331/25880 [3:32:41<1:51:52,  1.27it/s]
1|17332|Loss: 0.7971498370170593:  67%|██████▋   | 17332/25880 [3:32:41<1:59:14,  1.19it/s]
1|17333|Loss: 0.7365345358848572:  67%|██████▋   | 17332/25880 [3:32:42<1:59:14,  1.19it/s]
1|17333|Loss: 0.7365345358848572:  67%|██████▋   | 17333/25880 [3:32:42<1:57:12,  1.22it/s]
1|17334|Loss: 0.8018013834953308:  67%|██████▋   | 17333/25880 [3:32:43<1:57:12,  1.22it/s]
1|17334|Loss: 0.8018013834953308:  67%|██████▋   | 17334/25880 [3:32:43<1:53:36,  1.25it/s]
1|17335|Loss: 0.8504348993301392:  67%|██████▋   | 17334/25880 [3:32:43<1:53:36,  1.25it/s]
1|17335|Loss: 0.8504348993301392:  67%|██████▋   | 17335/25880 [3:32:44<1:45:36,  1.35it/s]
1|17336|Loss: 0.7438429594039917:  67%|██████▋   | 17335/25880 [3:32:44<1:45:36,  1.35it/s]
1|17336|Loss: 0.7438429594039917:  67%|██████▋   | 17336/25880 [3:32:44<1:47:59,  1.32it/s]
1|17337|Loss: 0.6827662587165833:  67%|██████▋   | 17336/25880 [3:32:45<1:47:59,  1.32it/s]
1|17337|Loss: 0.6827662587165833:  67%|██████▋   | 17337/25880 [3:32:45<1:54:23,  1.24it/s]
1|17338|Loss: 0.8254160284996033:  67%|██████▋   | 17337/25880 [3:32:46<1:54:23,  1.24it/s]
1|17338|Loss: 0.8254160284996033:  67%|██████▋   | 17338/25880 [3:32:46<1:54:39,  1.24it/s]
1|17339|Loss: 0.6888376474380493:  67%|██████▋   | 17338/25880 [3:32:47<1:54:39,  1.24it/s]
1|17339|Loss: 0.6888376474380493:  67%|██████▋   | 17339/25880 [3:32:47<1:52:25,  1.27it/s]
1|17340|Loss: 0.9145205020904541:  67%|██████▋   | 17339/25880 [3:32:47<1:52:25,  1.27it/s]
1|17340|Loss: 0.9145205020904541:  67%|██████▋   | 17340/25880 [3:32:48<1:50:19,  1.29it/s]
1|17341|Loss: 0.8408575654029846:  67%|██████▋   | 17340/25880 [3:32:48<1:50:19,  1.29it/s]
1|17341|Loss: 0.8408575654029846:  67%|██████▋   | 17341/25880 [3:32:48<1:45:27,  1.35it/s]
1|17342|Loss: 0.8540156483650208:  67%|██████▋   | 17341/25880 [3:32:49<1:45:27,  1.35it/s]
1|17342|Loss: 0.8540156483650208:  67%|██████▋   | 17342/25880 [3:32:49<1:39:37,  1.43it/s]
1|17343|Loss: 0.9103749394416809:  67%|██████▋   | 17342/25880 [3:32:49<1:39:37,  1.43it/s]
1|17343|Loss: 0.9103749394416809:  67%|██████▋   | 17343/25880 [3:32:50<1:42:00,  1.39it/s]
1|17344|Loss: 0.8173450827598572:  67%|██████▋   | 17343/25880 [3:32:50<1:42:00,  1.39it/s]
1|17344|Loss: 0.8173450827598572:  67%|██████▋   | 17344/25880 [3:32:50<1:44:47,  1.36it/s]
1|17345|Loss: 0.8620116114616394:  67%|██████▋   | 17344/25880 [3:32:51<1:44:47,  1.36it/s]
1|17345|Loss: 0.8620116114616394:  67%|██████▋   | 17345/25880 [3:32:51<1:37:42,  1.46it/s]
1|17346|Loss: 0.8907411098480225:  67%|██████▋   | 17345/25880 [3:32:51<1:37:42,  1.46it/s]
1|17346|Loss: 0.8907411098480225:  67%|██████▋   | 17346/25880 [3:32:52<1:32:39,  1.53it/s]
1|17347|Loss: 0.8875855803489685:  67%|██████▋   | 17346/25880 [3:32:52<1:32:39,  1.53it/s]
1|17347|Loss: 0.8875855803489685:  67%|██████▋   | 17347/25880 [3:32:52<1:40:49,  1.41it/s]
1|17348|Loss: 1.0176892280578613:  67%|██████▋   | 17347/25880 [3:32:53<1:40:49,  1.41it/s]
1|17348|Loss: 1.0176892280578613:  67%|██████▋   | 17348/25880 [3:32:53<1:47:14,  1.33it/s]
1|17349|Loss: 0.8576734066009521:  67%|██████▋   | 17348/25880 [3:32:54<1:47:14,  1.33it/s]
1|17349|Loss: 0.8576734066009521:  67%|██████▋   | 17349/25880 [3:32:54<1:47:46,  1.32it/s]
1|17350|Loss: 0.9252726435661316:  67%|██████▋   | 17349/25880 [3:32:54<1:47:46,  1.32it/s]
1|17350|Loss: 0.9252726435661316:  67%|██████▋   | 17350/25880 [3:32:55<1:47:15,  1.33it/s]
1|17351|Loss: 0.7157434821128845:  67%|██████▋   | 17350/25880 [3:32:55<1:47:15,  1.33it/s]
1|17351|Loss: 0.7157434821128845:  67%|██████▋   | 17351/25880 [3:32:56<1:48:34,  1.31it/s]
1|17352|Loss: 0.7525556087493896:  67%|██████▋   | 17351/25880 [3:32:56<1:48:34,  1.31it/s]
1|17352|Loss: 0.7525556087493896:  67%|██████▋   | 17352/25880 [3:32:56<1:44:44,  1.36it/s]
1|17353|Loss: 0.8272237777709961:  67%|██████▋   | 17352/25880 [3:32:57<1:44:44,  1.36it/s]
1|17353|Loss: 0.8272237777709961:  67%|██████▋   | 17353/25880 [3:32:57<1:46:56,  1.33it/s]
1|17354|Loss: 0.9595228433609009:  67%|██████▋   | 17353/25880 [3:32:57<1:46:56,  1.33it/s]
1|17354|Loss: 0.9595228433609009:  67%|██████▋   | 17354/25880 [3:32:58<1:45:47,  1.34it/s]
1|17355|Loss: 1.030594825744629:  67%|██████▋   | 17354/25880 [3:32:58<1:45:47,  1.34it/s] 
1|17355|Loss: 1.030594825744629:  67%|██████▋   | 17355/25880 [3:32:59<2:04:14,  1.14it/s]
1|17356|Loss: 0.8163630962371826:  67%|██████▋   | 17355/25880 [3:32:59<2:04:14,  1.14it/s]
1|17356|Loss: 0.8163630962371826:  67%|██████▋   | 17356/25880 [3:33:00<2:03:04,  1.15it/s]
1|17357|Loss: 0.7377945780754089:  67%|██████▋   | 17356/25880 [3:33:00<2:03:04,  1.15it/s]
1|17357|Loss: 0.7377945780754089:  67%|██████▋   | 17357/25880 [3:33:00<1:54:11,  1.24it/s]
1|17358|Loss: 0.8071137070655823:  67%|██████▋   | 17357/25880 [3:33:01<1:54:11,  1.24it/s]
1|17358|Loss: 0.8071137070655823:  67%|██████▋   | 17358/25880 [3:33:01<1:58:25,  1.20it/s]
1|17359|Loss: 0.8685133457183838:  67%|██████▋   | 17358/25880 [3:33:02<1:58:25,  1.20it/s]
1|17359|Loss: 0.8685133457183838:  67%|██████▋   | 17359/25880 [3:33:02<1:55:26,  1.23it/s]
1|17360|Loss: 0.9766968488693237:  67%|██████▋   | 17359/25880 [3:33:02<1:55:26,  1.23it/s]
1|17360|Loss: 0.9766968488693237:  67%|██████▋   | 17360/25880 [3:33:03<1:51:32,  1.27it/s]
1|17361|Loss: 0.8066371083259583:  67%|██████▋   | 17360/25880 [3:33:03<1:51:32,  1.27it/s]
1|17361|Loss: 0.8066371083259583:  67%|██████▋   | 17361/25880 [3:33:03<1:43:46,  1.37it/s]
1|17362|Loss: 0.8728896379470825:  67%|██████▋   | 17361/25880 [3:33:04<1:43:46,  1.37it/s]
1|17362|Loss: 0.8728896379470825:  67%|██████▋   | 17362/25880 [3:33:04<1:36:28,  1.47it/s]
1|17363|Loss: 0.7788729071617126:  67%|██████▋   | 17362/25880 [3:33:04<1:36:28,  1.47it/s]
1|17363|Loss: 0.7788729071617126:  67%|██████▋   | 17363/25880 [3:33:05<1:29:35,  1.58it/s]
1|17364|Loss: 0.8064746260643005:  67%|██████▋   | 17363/25880 [3:33:05<1:29:35,  1.58it/s]
1|17364|Loss: 0.8064746260643005:  67%|██████▋   | 17364/25880 [3:33:05<1:24:54,  1.67it/s]
1|17365|Loss: 0.8808898329734802:  67%|██████▋   | 17364/25880 [3:33:05<1:24:54,  1.67it/s]
1|17365|Loss: 0.8808898329734802:  67%|██████▋   | 17365/25880 [3:33:06<1:35:13,  1.49it/s]
1|17366|Loss: 0.8636679649353027:  67%|██████▋   | 17365/25880 [3:33:06<1:35:13,  1.49it/s]
1|17366|Loss: 0.8636679649353027:  67%|██████▋   | 17366/25880 [3:33:07<1:35:37,  1.48it/s]
1|17367|Loss: 0.781417191028595:  67%|██████▋   | 17366/25880 [3:33:07<1:35:37,  1.48it/s] 
1|17367|Loss: 0.781417191028595:  67%|██████▋   | 17367/25880 [3:33:07<1:31:01,  1.56it/s]
1|17368|Loss: 0.7984012961387634:  67%|██████▋   | 17367/25880 [3:33:07<1:31:01,  1.56it/s]
1|17368|Loss: 0.7984012961387634:  67%|██████▋   | 17368/25880 [3:33:08<1:29:18,  1.59it/s]
1|17369|Loss: 0.8248577117919922:  67%|██████▋   | 17368/25880 [3:33:08<1:29:18,  1.59it/s]
1|17369|Loss: 0.8248577117919922:  67%|██████▋   | 17369/25880 [3:33:08<1:29:35,  1.58it/s]
1|17370|Loss: 0.7880203723907471:  67%|██████▋   | 17369/25880 [3:33:09<1:29:35,  1.58it/s]
1|17370|Loss: 0.7880203723907471:  67%|██████▋   | 17370/25880 [3:33:09<1:30:06,  1.57it/s]
1|17371|Loss: 0.7878288626670837:  67%|██████▋   | 17370/25880 [3:33:09<1:30:06,  1.57it/s]
1|17371|Loss: 0.7878288626670837:  67%|██████▋   | 17371/25880 [3:33:10<1:30:30,  1.57it/s]
1|17372|Loss: 0.7818682193756104:  67%|██████▋   | 17371/25880 [3:33:10<1:30:30,  1.57it/s]
1|17372|Loss: 0.7818682193756104:  67%|██████▋   | 17372/25880 [3:33:11<1:39:57,  1.42it/s]
1|17373|Loss: 0.8449087738990784:  67%|██████▋   | 17372/25880 [3:33:11<1:39:57,  1.42it/s]
1|17373|Loss: 0.8449087738990784:  67%|██████▋   | 17373/25880 [3:33:11<1:38:32,  1.44it/s]
1|17374|Loss: 0.7552825808525085:  67%|██████▋   | 17373/25880 [3:33:12<1:38:32,  1.44it/s]
1|17374|Loss: 0.7552825808525085:  67%|██████▋   | 17374/25880 [3:33:12<1:38:57,  1.43it/s]
1|17375|Loss: 0.7498188614845276:  67%|██████▋   | 17374/25880 [3:33:12<1:38:57,  1.43it/s]
1|17375|Loss: 0.7498188614845276:  67%|██████▋   | 17375/25880 [3:33:13<1:37:05,  1.46it/s]
1|17376|Loss: 0.7195598483085632:  67%|██████▋   | 17375/25880 [3:33:13<1:37:05,  1.46it/s]
1|17376|Loss: 0.7195598483085632:  67%|██████▋   | 17376/25880 [3:33:13<1:37:40,  1.45it/s]
1|17377|Loss: 0.9648498296737671:  67%|██████▋   | 17376/25880 [3:33:14<1:37:40,  1.45it/s]
1|17377|Loss: 0.9648498296737671:  67%|██████▋   | 17377/25880 [3:33:14<1:44:25,  1.36it/s]
1|17378|Loss: 0.868462085723877:  67%|██████▋   | 17377/25880 [3:33:15<1:44:25,  1.36it/s] 
1|17378|Loss: 0.868462085723877:  67%|██████▋   | 17378/25880 [3:33:15<1:50:50,  1.28it/s]
1|17379|Loss: 0.7652499079704285:  67%|██████▋   | 17378/25880 [3:33:15<1:50:50,  1.28it/s]
1|17379|Loss: 0.7652499079704285:  67%|██████▋   | 17379/25880 [3:33:16<1:50:24,  1.28it/s]
1|17380|Loss: 0.8854519724845886:  67%|██████▋   | 17379/25880 [3:33:16<1:50:24,  1.28it/s]
1|17380|Loss: 0.8854519724845886:  67%|██████▋   | 17380/25880 [3:33:16<1:47:28,  1.32it/s]
1|17381|Loss: 0.8533748388290405:  67%|██████▋   | 17380/25880 [3:33:17<1:47:28,  1.32it/s]
1|17381|Loss: 0.8533748388290405:  67%|██████▋   | 17381/25880 [3:33:17<1:46:39,  1.33it/s]
1|17382|Loss: 0.7897141575813293:  67%|██████▋   | 17381/25880 [3:33:18<1:46:39,  1.33it/s]
1|17382|Loss: 0.7897141575813293:  67%|██████▋   | 17382/25880 [3:33:18<1:45:06,  1.35it/s]
1|17383|Loss: 0.8263562321662903:  67%|██████▋   | 17382/25880 [3:33:18<1:45:06,  1.35it/s]
1|17383|Loss: 0.8263562321662903:  67%|██████▋   | 17383/25880 [3:33:19<1:49:14,  1.30it/s]
1|17384|Loss: 0.721766471862793:  67%|██████▋   | 17383/25880 [3:33:19<1:49:14,  1.30it/s] 
1|17384|Loss: 0.721766471862793:  67%|██████▋   | 17384/25880 [3:33:19<1:48:13,  1.31it/s]
1|17385|Loss: 0.8078327178955078:  67%|██████▋   | 17384/25880 [3:33:20<1:48:13,  1.31it/s]
1|17385|Loss: 0.8078327178955078:  67%|██████▋   | 17385/25880 [3:33:20<1:49:50,  1.29it/s]
1|17386|Loss: 0.8247668743133545:  67%|██████▋   | 17385/25880 [3:33:21<1:49:50,  1.29it/s]
1|17386|Loss: 0.8247668743133545:  67%|██████▋   | 17386/25880 [3:33:21<1:48:53,  1.30it/s]
1|17387|Loss: 0.8456228375434875:  67%|██████▋   | 17386/25880 [3:33:21<1:48:53,  1.30it/s]
1|17387|Loss: 0.8456228375434875:  67%|██████▋   | 17387/25880 [3:33:22<1:51:27,  1.27it/s]
1|17388|Loss: 0.9413242936134338:  67%|██████▋   | 17387/25880 [3:33:22<1:51:27,  1.27it/s]
1|17388|Loss: 0.9413242936134338:  67%|██████▋   | 17388/25880 [3:33:22<1:42:49,  1.38it/s]
1|17389|Loss: 0.8416556119918823:  67%|██████▋   | 17388/25880 [3:33:23<1:42:49,  1.38it/s]
1|17389|Loss: 0.8416556119918823:  67%|██████▋   | 17389/25880 [3:33:23<1:39:56,  1.42it/s]
1|17390|Loss: 0.9229983687400818:  67%|██████▋   | 17389/25880 [3:33:24<1:39:56,  1.42it/s]
1|17390|Loss: 0.9229983687400818:  67%|██████▋   | 17390/25880 [3:33:24<1:44:51,  1.35it/s]
1|17391|Loss: 0.8701574802398682:  67%|██████▋   | 17390/25880 [3:33:24<1:44:51,  1.35it/s]
1|17391|Loss: 0.8701574802398682:  67%|██████▋   | 17391/25880 [3:33:25<1:45:36,  1.34it/s]
1|17392|Loss: 0.7544246315956116:  67%|██████▋   | 17391/25880 [3:33:25<1:45:36,  1.34it/s]
1|17392|Loss: 0.7544246315956116:  67%|██████▋   | 17392/25880 [3:33:25<1:43:44,  1.36it/s]
1|17393|Loss: 0.8153978586196899:  67%|██████▋   | 17392/25880 [3:33:26<1:43:44,  1.36it/s]
1|17393|Loss: 0.8153978586196899:  67%|██████▋   | 17393/25880 [3:33:26<1:43:22,  1.37it/s]
1|17394|Loss: 0.8826903104782104:  67%|██████▋   | 17393/25880 [3:33:26<1:43:22,  1.37it/s]
1|17394|Loss: 0.8826903104782104:  67%|██████▋   | 17394/25880 [3:33:27<1:35:55,  1.47it/s]
1|17395|Loss: 0.7019930481910706:  67%|██████▋   | 17394/25880 [3:33:27<1:35:55,  1.47it/s]
1|17395|Loss: 0.7019930481910706:  67%|██████▋   | 17395/25880 [3:33:27<1:36:39,  1.46it/s]
1|17396|Loss: 0.8438850045204163:  67%|██████▋   | 17395/25880 [3:33:28<1:36:39,  1.46it/s]
1|17396|Loss: 0.8438850045204163:  67%|██████▋   | 17396/25880 [3:33:28<1:34:58,  1.49it/s]
1|17397|Loss: 0.8927786946296692:  67%|██���███▋   | 17396/25880 [3:33:28<1:34:58,  1.49it/s]
1|17397|Loss: 0.8927786946296692:  67%|██████▋   | 17397/25880 [3:33:28<1:24:17,  1.68it/s]
1|17398|Loss: 0.9048105478286743:  67%|██████▋   | 17397/25880 [3:33:29<1:24:17,  1.68it/s]
1|17398|Loss: 0.9048105478286743:  67%|██████▋   | 17398/25880 [3:33:29<1:29:03,  1.59it/s]
1|17399|Loss: 0.7771679759025574:  67%|██████▋   | 17398/25880 [3:33:30<1:29:03,  1.59it/s]
1|17399|Loss: 0.7771679759025574:  67%|██████▋   | 17399/25880 [3:33:30<1:26:36,  1.63it/s]
1|17400|Loss: 0.9532231092453003:  67%|██████▋   | 17399/25880 [3:33:30<1:26:36,  1.63it/s]
1|17400|Loss: 0.9532231092453003:  67%|██████▋   | 17400/25880 [3:33:30<1:29:52,  1.57it/s]
1|17401|Loss: 0.7346410751342773:  67%|██████▋   | 17400/25880 [3:33:31<1:29:52,  1.57it/s]
1|17401|Loss: 0.7346410751342773:  67%|██████▋   | 17401/25880 [3:33:31<1:41:59,  1.39it/s]
1|17402|Loss: 0.8360303640365601:  67%|██████▋   | 17401/25880 [3:33:32<1:41:59,  1.39it/s]
1|17402|Loss: 0.8360303640365601:  67%|██████▋   | 17402/25880 [3:33:32<1:45:02,  1.35it/s]
1|17403|Loss: 1.0274616479873657:  67%|██████▋   | 17402/25880 [3:33:33<1:45:02,  1.35it/s]
1|17403|Loss: 1.0274616479873657:  67%|██████▋   | 17403/25880 [3:33:33<1:48:09,  1.31it/s]
1|17404|Loss: 0.8598248958587646:  67%|██████▋   | 17403/25880 [3:33:33<1:48:09,  1.31it/s]
1|17404|Loss: 0.8598248958587646:  67%|██████▋   | 17404/25880 [3:33:34<1:46:21,  1.33it/s]
1|17405|Loss: 0.7926639914512634:  67%|██████▋   | 17404/25880 [3:33:34<1:46:21,  1.33it/s]
1|17405|Loss: 0.7926639914512634:  67%|██████▋   | 17405/25880 [3:33:34<1:45:00,  1.35it/s]
1|17406|Loss: 0.8357619643211365:  67%|██████▋   | 17405/25880 [3:33:35<1:45:00,  1.35it/s]
1|17406|Loss: 0.8357619643211365:  67%|██████▋   | 17406/25880 [3:33:36<2:00:21,  1.17it/s]
1|17407|Loss: 0.7918064594268799:  67%|██████▋   | 17406/25880 [3:33:36<2:00:21,  1.17it/s]
1|17407|Loss: 0.7918064594268799:  67%|██████▋   | 17407/25880 [3:33:36<2:02:38,  1.15it/s]
1|17408|Loss: 0.9408881664276123:  67%|██████▋   | 17407/25880 [3:33:37<2:02:38,  1.15it/s]
1|17408|Loss: 0.9408881664276123:  67%|██████▋   | 17408/25880 [3:33:37<1:57:33,  1.20it/s]
1|17409|Loss: 0.8634762167930603:  67%|██████▋   | 17408/25880 [3:33:38<1:57:33,  1.20it/s]
1|17409|Loss: 0.8634762167930603:  67%|██████▋   | 17409/25880 [3:33:38<1:53:17,  1.25it/s]
1|17410|Loss: 0.6949740052223206:  67%|██████▋   | 17409/25880 [3:33:38<1:53:17,  1.25it/s]
1|17410|Loss: 0.6949740052223206:  67%|██████▋   | 17410/25880 [3:33:39<1:50:16,  1.28it/s]
1|17411|Loss: 0.7880684733390808:  67%|██████▋   | 17410/25880 [3:33:39<1:50:16,  1.28it/s]
1|17411|Loss: 0.7880684733390808:  67%|██████▋   | 17411/25880 [3:33:39<1:47:05,  1.32it/s]
1|17412|Loss: 0.8083854913711548:  67%|██████▋   | 17411/25880 [3:33:40<1:47:05,  1.32it/s]
1|17412|Loss: 0.8083854913711548:  67%|██████▋   | 17412/25880 [3:33:40<1:41:36,  1.39it/s]
1|17413|Loss: 0.6917495727539062:  67%|██████▋   | 17412/25880 [3:33:40<1:41:36,  1.39it/s]
1|17413|Loss: 0.6917495727539062:  67%|██████▋   | 17413/25880 [3:33:41<1:45:10,  1.34it/s]
1|17414|Loss: 0.7653846740722656:  67%|██████▋   | 17413/25880 [3:33:41<1:45:10,  1.34it/s]
1|17414|Loss: 0.7653846740722656:  67%|██████▋   | 17414/25880 [3:33:42<1:51:53,  1.26it/s]
1|17415|Loss: 0.8441838026046753:  67%|██████▋   | 17414/25880 [3:33:42<1:51:53,  1.26it/s]
1|17415|Loss: 0.8441838026046753:  67%|██████▋   | 17415/25880 [3:33:43<1:54:03,  1.24it/s]
1|17416|Loss: 0.8206556439399719:  67%|██████▋   | 17415/25880 [3:33:43<1:54:03,  1.24it/s]
1|17416|Loss: 0.8206556439399719:  67%|██████▋   | 17416/25880 [3:33:43<1:57:50,  1.20it/s]
1|17417|Loss: 0.9786328077316284:  67%|██████▋   | 17416/25880 [3:33:44<1:57:50,  1.20it/s]
1|17417|Loss: 0.9786328077316284:  67%|██████▋   | 17417/25880 [3:33:44<1:59:01,  1.19it/s]
1|17418|Loss: 0.8292547464370728:  67%|██████▋   | 17417/25880 [3:33:45<1:59:01,  1.19it/s]
1|17418|Loss: 0.8292547464370728:  67%|██████▋   | 17418/25880 [3:33:45<1:55:41,  1.22it/s]
1|17419|Loss: 0.8101428151130676:  67%|██████▋   | 17418/25880 [3:33:45<1:55:41,  1.22it/s]
1|17419|Loss: 0.8101428151130676:  67%|██████▋   | 17419/25880 [3:33:46<1:48:18,  1.30it/s]
1|17420|Loss: 0.8660358786582947:  67%|██████▋   | 17419/25880 [3:33:46<1:48:18,  1.30it/s]
1|17420|Loss: 0.8660358786582947:  67%|██████▋   | 17420/25880 [3:33:46<1:41:43,  1.39it/s]
1|17421|Loss: 0.8139720559120178:  67%|██████▋   | 17420/25880 [3:33:47<1:41:43,  1.39it/s]
1|17421|Loss: 0.8139720559120178:  67%|██████▋   | 17421/25880 [3:33:47<1:41:13,  1.39it/s]
1|17422|Loss: 0.8165812492370605:  67%|██████▋   | 17421/25880 [3:33:47<1:41:13,  1.39it/s]
1|17422|Loss: 0.8165812492370605:  67%|██████▋   | 17422/25880 [3:33:48<1:45:02,  1.34it/s]
1|17423|Loss: 0.8050210475921631:  67%|██████▋   | 17422/25880 [3:33:48<1:45:02,  1.34it/s]
1|17423|Loss: 0.8050210475921631:  67%|██████▋   | 17423/25880 [3:33:49<1:44:28,  1.35it/s]
1|17424|Loss: 0.8303797245025635:  67%|██████▋   | 17423/25880 [3:33:49<1:44:28,  1.35it/s]
1|17424|Loss: 0.8303797245025635:  67%|██████▋   | 17424/25880 [3:33:49<1:42:53,  1.37it/s]
1|17425|Loss: 1.0080546140670776:  67%|██████▋   | 17424/25880 [3:33:50<1:42:53,  1.37it/s]
1|17425|Loss: 1.0080546140670776:  67%|██████▋   | 17425/25880 [3:33:50<1:36:29,  1.46it/s]
1|17426|Loss: 0.7348068952560425:  67%|██████▋   | 17425/25880 [3:33:50<1:36:29,  1.46it/s]
1|17426|Loss: 0.7348068952560425:  67%|██████▋   | 17426/25880 [3:33:51<1:40:24,  1.40it/s]
1|17427|Loss: 0.6951467990875244:  67%|██████▋   | 17426/25880 [3:33:51<1:40:24,  1.40it/s]
1|17427|Loss: 0.6951467990875244:  67%|██████▋   | 17427/25880 [3:33:51<1:42:14,  1.38it/s]
1|17428|Loss: 0.7410778403282166:  67%|██████▋   | 17427/25880 [3:33:52<1:42:14,  1.38it/s]
1|17428|Loss: 0.7410778403282166:  67%|██████▋   | 17428/25880 [3:33:52<1:42:46,  1.37it/s]
1|17429|Loss: 0.7540088295936584:  67%|██████▋   | 17428/25880 [3:33:53<1:42:46,  1.37it/s]
1|17429|Loss: 0.7540088295936584:  67%|██████▋   | 17429/25880 [3:33:53<1:46:16,  1.33it/s]
1|17430|Loss: 0.8948773145675659:  67%|██████▋   | 17429/25880 [3:33:53<1:46:16,  1.33it/s]
1|17430|Loss: 0.8948773145675659:  67%|██████▋   | 17430/25880 [3:33:54<1:42:51,  1.37it/s]
1|17431|Loss: 1.0322977304458618:  67%|██████▋   | 17430/25880 [3:33:54<1:42:51,  1.37it/s]
1|17431|Loss: 1.0322977304458618:  67%|██████▋   | 17431/25880 [3:33:54<1:38:10,  1.43it/s]
1|17432|Loss: 0.7589594721794128:  67%|██████▋   | 17431/25880 [3:33:55<1:38:10,  1.43it/s]
1|17432|Loss: 0.7589594721794128:  67%|██████▋   | 17432/25880 [3:33:55<1:35:33,  1.47it/s]
1|17433|Loss: 0.8226197957992554:  67%|██████▋   | 17432/25880 [3:33:55<1:35:33,  1.47it/s]
1|17433|Loss: 0.8226197957992554:  67%|██████▋   | 17433/25880 [3:33:56<1:41:34,  1.39it/s]
1|17434|Loss: 0.8010473847389221:  67%|██████▋   | 17433/25880 [3:33:56<1:41:34,  1.39it/s]
1|17434|Loss: 0.8010473847389221:  67%|██████▋   | 17434/25880 [3:33:57<1:47:17,  1.31it/s]
1|17435|Loss: 0.8861383199691772:  67%|██████▋   | 17434/25880 [3:33:57<1:47:17,  1.31it/s]
1|17435|Loss: 0.8861383199691772:  67%|██████▋   | 17435/25880 [3:33:57<1:42:39,  1.37it/s]
1|17436|Loss: 1.083250880241394:  67%|██████▋   | 17435/25880 [3:33:58<1:42:39,  1.37it/s] 
1|17436|Loss: 1.083250880241394:  67%|██████▋   | 17436/25880 [3:33:58<2:00:17,  1.17it/s]
1|17437|Loss: 0.9774394035339355:  67%|██████▋   | 17436/25880 [3:33:59<2:00:17,  1.17it/s]
1|17437|Loss: 0.9774394035339355:  67%|██████▋   | 17437/25880 [3:33:59<2:00:27,  1.17it/s]
1|17438|Loss: 0.7948839664459229:  67%|██████▋   | 17437/25880 [3:34:00<2:00:27,  1.17it/s]
1|17438|Loss: 0.7948839664459229:  67%|██████▋   | 17438/25880 [3:34:00<1:51:39,  1.26it/s]
1|17439|Loss: 0.8436013460159302:  67%|██████▋   | 17438/25880 [3:34:00<1:51:39,  1.26it/s]
1|17439|Loss: 0.8436013460159302:  67%|██████▋   | 17439/25880 [3:34:01<1:47:50,  1.30it/s]
1|17440|Loss: 0.7671905755996704:  67%|██████▋   | 17439/25880 [3:34:01<1:47:50,  1.30it/s]
1|17440|Loss: 0.7671905755996704:  67%|██████▋   | 17440/25880 [3:34:01<1:41:01,  1.39it/s]
1|17441|Loss: 0.861173152923584:  67%|██████▋   | 17440/25880 [3:34:01<1:41:01,  1.39it/s] 
1|17441|Loss: 0.861173152923584:  67%|██████▋   | 17441/25880 [3:34:02<1:38:59,  1.42it/s]
1|17442|Loss: 0.7928929328918457:  67%|██████▋   | 17441/25880 [3:34:02<1:38:59,  1.42it/s]
1|17442|Loss: 0.7928929328918457:  67%|██████▋   | 17442/25880 [3:34:02<1:36:43,  1.45it/s]
1|17443|Loss: 0.9314221143722534:  67%|██████▋   | 17442/25880 [3:34:03<1:36:43,  1.45it/s]
1|17443|Loss: 0.9314221143722534:  67%|██████▋   | 17443/25880 [3:34:03<1:33:55,  1.50it/s]
1|17444|Loss: 0.8377283811569214:  67%|██████▋   | 17443/25880 [3:34:03<1:33:55,  1.50it/s]
1|17444|Loss: 0.8377283811569214:  67%|██████▋   | 17444/25880 [3:34:04<1:39:35,  1.41it/s]
1|17445|Loss: 0.8259724378585815:  67%|██████▋   | 17444/25880 [3:34:04<1:39:35,  1.41it/s]
1|17445|Loss: 0.8259724378585815:  67%|██████▋   | 17445/25880 [3:34:04<1:32:19,  1.52it/s]
1|17446|Loss: 0.7986028790473938:  67%|██████▋   | 17445/25880 [3:34:05<1:32:19,  1.52it/s]
1|17446|Loss: 0.7986028790473938:  67%|██████▋   | 17446/25880 [3:34:05<1:36:43,  1.45it/s]
1|17447|Loss: 0.8331292867660522:  67%|██████▋   | 17446/25880 [3:34:06<1:36:43,  1.45it/s]
1|17447|Loss: 0.8331292867660522:  67%|██████▋   | 17447/25880 [3:34:06<1:40:21,  1.40it/s]
1|17448|Loss: 0.9644336104393005:  67%|██████▋   | 17447/25880 [3:34:06<1:40:21,  1.40it/s]
1|17448|Loss: 0.9644336104393005:  67%|██████▋   | 17448/25880 [3:34:07<1:40:07,  1.40it/s]
1|17449|Loss: 0.8824635148048401:  67%|██████▋   | 17448/25880 [3:34:07<1:40:07,  1.40it/s]
1|17449|Loss: 0.8824635148048401:  67%|██████▋   | 17449/25880 [3:34:07<1:29:03,  1.58it/s]
1|17450|Loss: 0.8095229864120483:  67%|██████▋   | 17449/25880 [3:34:07<1:29:03,  1.58it/s]
1|17450|Loss: 0.8095229864120483:  67%|██████▋   | 17450/25880 [3:34:08<1:24:39,  1.66it/s]
1|17451|Loss: 0.8379402756690979:  67%|██████▋   | 17450/25880 [3:34:08<1:24:39,  1.66it/s]
1|17451|Loss: 0.8379402756690979:  67%|██████▋   | 17451/25880 [3:34:08<1:33:14,  1.51it/s]
1|17452|Loss: 0.7554687857627869:  67%|██████▋   | 17451/25880 [3:34:09<1:33:14,  1.51it/s]
1|17452|Loss: 0.7554687857627869:  67%|██████▋   | 17452/25880 [3:34:09<1:36:21,  1.46it/s]
1|17453|Loss: 0.7784398198127747:  67%|██████▋   | 17452/25880 [3:34:10<1:36:21,  1.46it/s]
1|17453|Loss: 0.7784398198127747:  67%|██████▋   | 17453/25880 [3:34:10<1:37:47,  1.44it/s]
1|17454|Loss: 0.7875111103057861:  67%|██████▋   | 17453/25880 [3:34:10<1:37:47,  1.44it/s]
1|17454|Loss: 0.7875111103057861:  67%|██████▋   | 17454/25880 [3:34:11<1:38:04,  1.43it/s]
1|17455|Loss: 0.8343549966812134:  67%|██████▋   | 17454/25880 [3:34:11<1:38:04,  1.43it/s]
1|17455|Loss: 0.8343549966812134:  67%|██████▋   | 17455/25880 [3:34:11<1:41:39,  1.38it/s]
1|17456|Loss: 0.7535586357116699:  67%|██████▋   | 17455/25880 [3:34:12<1:41:39,  1.38it/s]
1|17456|Loss: 0.7535586357116699:  67%|██████▋   | 17456/25880 [3:34:12<1:44:29,  1.34it/s]
1|17457|Loss: 0.7753280401229858:  67%|██████▋   | 17456/25880 [3:34:13<1:44:29,  1.34it/s]
1|17457|Loss: 0.7753280401229858:  67%|██████▋   | 17457/25880 [3:34:13<1:44:30,  1.34it/s]
1|17458|Loss: 0.7045428156852722:  67%|██████▋   | 17457/25880 [3:34:13<1:44:30,  1.34it/s]
1|17458|Loss: 0.7045428156852722:  67%|██████▋   | 17458/25880 [3:34:14<1:38:41,  1.42it/s]
1|17459|Loss: 0.8100966215133667:  67%|██████▋   | 17458/25880 [3:34:14<1:38:41,  1.42it/s]
1|17459|Loss: 0.8100966215133667:  67%|██████▋   | 17459/25880 [3:34:14<1:41:58,  1.38it/s]
1|17460|Loss: 0.9648638963699341:  67%|██████▋   | 17459/25880 [3:34:15<1:41:58,  1.38it/s]
1|17460|Loss: 0.9648638963699341:  67%|██████▋   | 17460/25880 [3:34:15<1:42:47,  1.37it/s]
1|17461|Loss: 0.9168156981468201:  67%|██████▋   | 17460/25880 [3:34:15<1:42:47,  1.37it/s]
1|17461|Loss: 0.9168156981468201:  67%|██████▋   | 17461/25880 [3:34:16<1:44:08,  1.35it/s]
1|17462|Loss: 0.8339357376098633:  67%|██████▋   | 17461/25880 [3:34:16<1:44:08,  1.35it/s]
1|17462|Loss: 0.8339357376098633:  67%|██████▋   | 17462/25880 [3:34:17<1:44:30,  1.34it/s]
1|17463|Loss: 0.825276792049408:  67%|██████▋   | 17462/25880 [3:34:17<1:44:30,  1.34it/s] 
1|17463|Loss: 0.825276792049408:  67%|██████▋   | 17463/25880 [3:34:17<1:44:04,  1.35it/s]
1|17464|Loss: 0.9402055740356445:  67%|██████▋   | 17463/25880 [3:34:18<1:44:04,  1.35it/s]
1|17464|Loss: 0.9402055740356445:  67%|██████▋   | 17464/25880 [3:34:18<1:46:35,  1.32it/s]
1|17465|Loss: 0.884562075138092:  67%|██████▋   | 17464/25880 [3:34:19<1:46:35,  1.32it/s] 
1|17465|Loss: 0.884562075138092:  67%|██████▋   | 17465/25880 [3:34:19<1:48:29,  1.29it/s]
1|17466|Loss: 0.7660974264144897:  67%|██████▋   | 17465/25880 [3:34:19<1:48:29,  1.29it/s]
1|17466|Loss: 0.7660974264144897:  67%|██████▋   | 17466/25880 [3:34:20<1:49:07,  1.29it/s]
1|17467|Loss: 0.8895639777183533:  67%|██████▋   | 17466/25880 [3:34:20<1:49:07,  1.29it/s]
1|17467|Loss: 0.8895639777183533:  67%|██████▋   | 17467/25880 [3:34:20<1:44:05,  1.35it/s]
1|17468|Loss: 0.8522325754165649:  67%|██████▋   | 17467/25880 [3:34:21<1:44:05,  1.35it/s]
1|17468|Loss: 0.8522325754165649:  67%|██████▋   | 17468/25880 [3:34:21<1:39:41,  1.41it/s]
1|17469|Loss: 0.9185152053833008:  67%|██████▋   | 17468/25880 [3:34:21<1:39:41,  1.41it/s]
1|17469|Loss: 0.9185152053833008:  68%|���█████▊   | 17469/25880 [3:34:22<1:36:44,  1.45it/s]
1|17470|Loss: 0.8716941475868225:  68%|██████▊   | 17469/25880 [3:34:22<1:36:44,  1.45it/s]
1|17470|Loss: 0.8716941475868225:  68%|██████▊   | 17470/25880 [3:34:22<1:36:49,  1.45it/s]
1|17471|Loss: 0.834699809551239:  68%|██████▊   | 17470/25880 [3:34:23<1:36:49,  1.45it/s] 
1|17471|Loss: 0.834699809551239:  68%|██████▊   | 17471/25880 [3:34:23<1:37:19,  1.44it/s]
1|17472|Loss: 0.9130722880363464:  68%|██████▊   | 17471/25880 [3:34:23<1:37:19,  1.44it/s]
1|17472|Loss: 0.9130722880363464:  68%|██████▊   | 17472/25880 [3:34:24<1:37:49,  1.43it/s]
1|17473|Loss: 0.7569312453269958:  68%|██████▊   | 17472/25880 [3:34:24<1:37:49,  1.43it/s]
1|17473|Loss: 0.7569312453269958:  68%|██████▊   | 17473/25880 [3:34:24<1:35:45,  1.46it/s]
1|17474|Loss: 0.8454548120498657:  68%|██████▊   | 17473/25880 [3:34:25<1:35:45,  1.46it/s]
1|17474|Loss: 0.8454548120498657:  68%|██████▊   | 17474/25880 [3:34:25<1:33:51,  1.49it/s]
1|17475|Loss: 0.8605254888534546:  68%|██████▊   | 17474/25880 [3:34:25<1:33:51,  1.49it/s]
1|17475|Loss: 0.8605254888534546:  68%|██████▊   | 17475/25880 [3:34:26<1:34:56,  1.48it/s]
1|17476|Loss: 0.91459721326828:  68%|██████▊   | 17475/25880 [3:34:26<1:34:56,  1.48it/s]  
1|17476|Loss: 0.91459721326828:  68%|██████▊   | 17476/25880 [3:34:26<1:31:45,  1.53it/s]
1|17477|Loss: 0.7679184675216675:  68%|██████▊   | 17476/25880 [3:34:27<1:31:45,  1.53it/s]
1|17477|Loss: 0.7679184675216675:  68%|██████▊   | 17477/25880 [3:34:27<1:33:39,  1.50it/s]
1|17478|Loss: 0.9377683401107788:  68%|██████▊   | 17477/25880 [3:34:27<1:33:39,  1.50it/s]
1|17478|Loss: 0.9377683401107788:  68%|██████▊   | 17478/25880 [3:34:28<1:41:27,  1.38it/s]
1|17479|Loss: 0.8206148147583008:  68%|██████▊   | 17478/25880 [3:34:28<1:41:27,  1.38it/s]
1|17479|Loss: 0.8206148147583008:  68%|██████▊   | 17479/25880 [3:34:29<1:38:17,  1.42it/s]
1|17480|Loss: 0.8844049572944641:  68%|██████▊   | 17479/25880 [3:34:29<1:38:17,  1.42it/s]
1|17480|Loss: 0.8844049572944641:  68%|██████▊   | 17480/25880 [3:34:29<1:28:53,  1.57it/s]
1|17481|Loss: 0.917930543422699:  68%|██████▊   | 17480/25880 [3:34:29<1:28:53,  1.57it/s] 
1|17481|Loss: 0.917930543422699:  68%|██████▊   | 17481/25880 [3:34:30<1:30:16,  1.55it/s]
1|17482|Loss: 0.7891592979431152:  68%|██████▊   | 17481/25880 [3:34:30<1:30:16,  1.55it/s]
1|17482|Loss: 0.7891592979431152:  68%|██████▊   | 17482/25880 [3:34:30<1:30:57,  1.54it/s]
1|17483|Loss: 0.8702692985534668:  68%|██████▊   | 17482/25880 [3:34:31<1:30:57,  1.54it/s]
1|17483|Loss: 0.8702692985534668:  68%|██████▊   | 17483/25880 [3:34:31<1:32:36,  1.51it/s]
1|17484|Loss: 0.7727727293968201:  68%|██████▊   | 17483/25880 [3:34:31<1:32:36,  1.51it/s]
1|17484|Loss: 0.7727727293968201:  68%|██████▊   | 17484/25880 [3:34:32<1:38:24,  1.42it/s]
1|17485|Loss: 0.7040947079658508:  68%|██████▊   | 17484/25880 [3:34:32<1:38:24,  1.42it/s]
1|17485|Loss: 0.7040947079658508:  68%|██████▊   | 17485/25880 [3:34:33<1:39:20,  1.41it/s]
1|17486|Loss: 0.688050389289856:  68%|██████▊   | 17485/25880 [3:34:33<1:39:20,  1.41it/s] 
1|17486|Loss: 0.688050389289856:  68%|██████▊   | 17486/25880 [3:34:33<1:42:27,  1.37it/s]
1|17487|Loss: 0.7019932270050049:  68%|██████▊   | 17486/25880 [3:34:34<1:42:27,  1.37it/s]
1|17487|Loss: 0.7019932270050049:  68%|██████▊   | 17487/25880 [3:34:34<1:42:57,  1.36it/s]
1|17488|Loss: 0.7139966487884521:  68%|██████▊   | 17487/25880 [3:34:34<1:42:57,  1.36it/s]
1|17488|Loss: 0.7139966487884521:  68%|██████▊   | 17488/25880 [3:34:35<1:37:57,  1.43it/s]
1|17489|Loss: 0.7676624655723572:  68%|██████▊   | 17488/25880 [3:34:35<1:37:57,  1.43it/s]
1|17489|Loss: 0.7676624655723572:  68%|██████▊   | 17489/25880 [3:34:35<1:37:53,  1.43it/s]
1|17490|Loss: 0.8609164953231812:  68%|██████▊   | 17489/25880 [3:34:36<1:37:53,  1.43it/s]
1|17490|Loss: 0.8609164953231812:  68%|██████▊   | 17490/25880 [3:34:36<1:35:18,  1.47it/s]
1|17491|Loss: 0.7521756291389465:  68%|██████▊   | 17490/25880 [3:34:36<1:35:18,  1.47it/s]
1|17491|Loss: 0.7521756291389465:  68%|██████▊   | 17491/25880 [3:34:37<1:33:20,  1.50it/s]
1|17492|Loss: 0.8401960134506226:  68%|██████▊   | 17491/25880 [3:34:37<1:33:20,  1.50it/s]
1|17492|Loss: 0.8401960134506226:  68%|██████▊   | 17492/25880 [3:34:37<1:32:21,  1.51it/s]
1|17493|Loss: 0.8795087933540344:  68%|██████▊   | 17492/25880 [3:34:38<1:32:21,  1.51it/s]
1|17493|Loss: 0.8795087933540344:  68%|██████▊   | 17493/25880 [3:34:38<1:30:45,  1.54it/s]
1|17494|Loss: 0.7872587442398071:  68%|██████▊   | 17493/25880 [3:34:38<1:30:45,  1.54it/s]
1|17494|Loss: 0.7872587442398071:  68%|██████▊   | 17494/25880 [3:34:39<1:36:12,  1.45it/s]
1|17495|Loss: 0.7477889657020569:  68%|██████▊   | 17494/25880 [3:34:39<1:36:12,  1.45it/s]
1|17495|Loss: 0.7477889657020569:  68%|██████▊   | 17495/25880 [3:34:39<1:31:57,  1.52it/s]
1|17496|Loss: 0.78238445520401:  68%|██████▊   | 17495/25880 [3:34:40<1:31:57,  1.52it/s]  
1|17496|Loss: 0.78238445520401:  68%|██████▊   | 17496/25880 [3:34:40<1:32:05,  1.52it/s]
1|17497|Loss: 0.7810461521148682:  68%|██████▊   | 17496/25880 [3:34:40<1:32:05,  1.52it/s]
1|17497|Loss: 0.7810461521148682:  68%|██████▊   | 17497/25880 [3:34:41<1:33:37,  1.49it/s]
1|17498|Loss: 0.915788471698761:  68%|██████▊   | 17497/25880 [3:34:41<1:33:37,  1.49it/s] 
1|17498|Loss: 0.915788471698761:  68%|██████▊   | 17498/25880 [3:34:41<1:29:03,  1.57it/s]
1|17499|Loss: 0.8804650902748108:  68%|██████▊   | 17498/25880 [3:34:42<1:29:03,  1.57it/s]
1|17499|Loss: 0.8804650902748108:  68%|██████▊   | 17499/25880 [3:34:42<1:37:32,  1.43it/s]
1|17500|Loss: 0.8846021294593811:  68%|██████▊   | 17499/25880 [3:34:43<1:37:32,  1.43it/s]
1|17500|Loss: 0.8846021294593811:  68%|██████▊   | 17500/25880 [3:34:43<1:45:30,  1.32it/s]
1|17501|Loss: 0.7164059281349182:  68%|██████▊   | 17500/25880 [3:34:44<1:45:30,  1.32it/s]
1|17501|Loss: 0.7164059281349182:  68%|██████▊   | 17501/25880 [3:34:45<2:28:00,  1.06s/it]
1|17502|Loss: 0.8101744651794434:  68%|██████▊   | 17501/25880 [3:34:45<2:28:00,  1.06s/it]
1|17502|Loss: 0.8101744651794434:  68%|██████▊   | 17502/25880 [3:34:46<2:32:35,  1.09s/it]
1|17503|Loss: 0.9099865555763245:  68%|██████▊   | 17502/25880 [3:34:46<2:32:35,  1.09s/it]
1|17503|Loss: 0.9099865555763245:  68%|██████▊   | 17503/25880 [3:34:47<2:24:27,  1.03s/it]
1|17504|Loss: 0.7014841437339783:  68%|██████▊   | 17503/25880 [3:34:47<2:24:27,  1.03s/it]
1|17504|Loss: 0.7014841437339783:  68%|██████▊   | 17504/25880 [3:34:48<2:16:27,  1.02it/s]
1|17505|Loss: 0.8632953763008118:  68%|██████▊   | 17504/25880 [3:34:48<2:16:27,  1.02it/s]
1|17505|Loss: 0.8632953763008118:  68%|██████▊   | 17505/25880 [3:34:48<2:05:42,  1.11it/s]
1|17506|Loss: 0.9053924083709717:  68%|██████▊   | 17505/25880 [3:34:49<2:05:42,  1.11it/s]
1|17506|Loss: 0.9053924083709717:  68%|██████▊   | 17506/25880 [3:34:49<1:54:39,  1.22it/s]
1|17507|Loss: 0.8996219635009766:  68%|██████▊   | 17506/25880 [3:34:49<1:54:39,  1.22it/s]
1|17507|Loss: 0.8996219635009766:  68%|██████▊   | 17507/25880 [3:34:50<1:50:05,  1.27it/s]
1|17508|Loss: 0.7838789224624634:  68%|██████▊   | 17507/25880 [3:34:50<1:50:05,  1.27it/s]
1|17508|Loss: 0.7838789224624634:  68%|██████▊   | 17508/25880 [3:34:51<1:55:00,  1.21it/s]
1|17509|Loss: 0.7859220504760742:  68%|██████▊   | 17508/25880 [3:34:51<1:55:00,  1.21it/s]
1|17509|Loss: 0.7859220504760742:  68%|██████▊   | 17509/25880 [3:34:51<1:56:28,  1.20it/s]
1|17510|Loss: 0.9643418192863464:  68%|██████▊   | 17509/25880 [3:34:52<1:56:28,  1.20it/s]
1|17510|Loss: 0.9643418192863464:  68%|██████▊   | 17510/25880 [3:34:52<1:56:17,  1.20it/s]
1|17511|Loss: 0.7717670202255249:  68%|██████▊   | 17510/25880 [3:34:53<1:56:17,  1.20it/s]
1|17511|Loss: 0.7717670202255249:  68%|██████▊   | 17511/25880 [3:34:53<1:58:59,  1.17it/s]
1|17512|Loss: 0.8114219903945923:  68%|██████▊   | 17511/25880 [3:34:54<1:58:59,  1.17it/s]
1|17512|Loss: 0.8114219903945923:  68%|██████▊   | 17512/25880 [3:34:54<1:48:03,  1.29it/s]
1|17513|Loss: 0.8083645701408386:  68%|██████▊   | 17512/25880 [3:34:54<1:48:03,  1.29it/s]
1|17513|Loss: 0.8083645701408386:  68%|██████▊   | 17513/25880 [3:34:55<1:46:06,  1.31it/s]
1|17514|Loss: 0.8360608220100403:  68%|██████▊   | 17513/25880 [3:34:55<1:46:06,  1.31it/s]
1|17514|Loss: 0.8360608220100403:  68%|██████▊   | 17514/25880 [3:34:55<1:38:03,  1.42it/s]
1|17515|Loss: 0.895751416683197:  68%|██████▊   | 17514/25880 [3:34:55<1:38:03,  1.42it/s] 
1|17515|Loss: 0.895751416683197:  68%|██████▊   | 17515/25880 [3:34:56<1:30:08,  1.55it/s]
1|17516|Loss: 0.8295179605484009:  68%|██████▊   | 17515/25880 [3:34:56<1:30:08,  1.55it/s]
1|17516|Loss: 0.8295179605484009:  68%|██████▊   | 17516/25880 [3:34:56<1:31:47,  1.52it/s]
1|17517|Loss: 0.9354535937309265:  68%|██████▊   | 17516/25880 [3:34:57<1:31:47,  1.52it/s]
1|17517|Loss: 0.9354535937309265:  68%|██████▊   | 17517/25880 [3:34:57<1:28:13,  1.58it/s]
1|17518|Loss: 0.8932731747627258:  68%|██████▊   | 17517/25880 [3:34:57<1:28:13,  1.58it/s]
1|17518|Loss: 0.8932731747627258:  68%|██████▊   | 17518/25880 [3:34:57<1:25:44,  1.63it/s]
1|17519|Loss: 0.7305066585540771:  68%|██████▊   | 17518/25880 [3:34:58<1:25:44,  1.63it/s]
1|17519|Loss: 0.7305066585540771:  68%|██████▊   | 17519/25880 [3:34:58<1:24:20,  1.65it/s]
1|17520|Loss: 0.8820735216140747:  68%|██████▊   | 17519/25880 [3:34:58<1:24:20,  1.65it/s]
1|17520|Loss: 0.8820735216140747:  68%|██████▊   | 17520/25880 [3:34:59<1:28:45,  1.57it/s]
1|17521|Loss: 0.7155046463012695:  68%|██████▊   | 17520/25880 [3:34:59<1:28:45,  1.57it/s]
1|17521|Loss: 0.7155046463012695:  68%|██████▊   | 17521/25880 [3:34:59<1:29:10,  1.56it/s]
1|17522|Loss: 0.9085291624069214:  68%|██████▊   | 17521/25880 [3:35:00<1:29:10,  1.56it/s]
1|17522|Loss: 0.9085291624069214:  68%|██████▊   | 17522/25880 [3:35:00<1:32:04,  1.51it/s]
1|17523|Loss: 0.852325439453125:  68%|██████▊   | 17522/25880 [3:35:01<1:32:04,  1.51it/s] 
1|17523|Loss: 0.852325439453125:  68%|██████▊   | 17523/25880 [3:35:01<1:39:07,  1.41it/s]
1|17524|Loss: 0.8091204762458801:  68%|██████▊   | 17523/25880 [3:35:01<1:39:07,  1.41it/s]
1|17524|Loss: 0.8091204762458801:  68%|██████▊   | 17524/25880 [3:35:02<1:35:18,  1.46it/s]
1|17525|Loss: 0.9256700873374939:  68%|██████▊   | 17524/25880 [3:35:02<1:35:18,  1.46it/s]
1|17525|Loss: 0.9256700873374939:  68%|██████▊   | 17525/25880 [3:35:02<1:35:04,  1.46it/s]
1|17526|Loss: 0.682172417640686:  68%|██████▊   | 17525/25880 [3:35:03<1:35:04,  1.46it/s] 
1|17526|Loss: 0.682172417640686:  68%|██████▊   | 17526/25880 [3:35:03<1:39:56,  1.39it/s]
1|17527|Loss: 0.8871424794197083:  68%|██████▊   | 17526/25880 [3:35:03<1:39:56,  1.39it/s]
1|17527|Loss: 0.8871424794197083:  68%|██████▊   | 17527/25880 [3:35:04<1:38:14,  1.42it/s]
1|17528|Loss: 0.7847451567649841:  68%|██████▊   | 17527/25880 [3:35:04<1:38:14,  1.42it/s]
1|17528|Loss: 0.7847451567649841:  68%|██████▊   | 17528/25880 [3:35:04<1:34:52,  1.47it/s]
1|17529|Loss: 0.9554979801177979:  68%|██████▊   | 17528/25880 [3:35:05<1:34:52,  1.47it/s]
1|17529|Loss: 0.9554979801177979:  68%|██████▊   | 17529/25880 [3:35:05<1:40:25,  1.39it/s]
1|17530|Loss: 0.945999801158905:  68%|██████▊   | 17529/25880 [3:35:06<1:40:25,  1.39it/s] 
1|17530|Loss: 0.945999801158905:  68%|██████▊   | 17530/25880 [3:35:06<1:48:12,  1.29it/s]
1|17531|Loss: 0.8204775452613831:  68%|██████▊   | 17530/25880 [3:35:06<1:48:12,  1.29it/s]
1|17531|Loss: 0.8204775452613831:  68%|██████▊   | 17531/25880 [3:35:07<1:44:01,  1.34it/s]
1|17532|Loss: 0.8937986493110657:  68%|██████▊   | 17531/25880 [3:35:07<1:44:01,  1.34it/s]
1|17532|Loss: 0.8937986493110657:  68%|██████▊   | 17532/25880 [3:35:07<1:35:42,  1.45it/s]
1|17533|Loss: 0.8175272345542908:  68%|██████▊   | 17532/25880 [3:35:08<1:35:42,  1.45it/s]
1|17533|Loss: 0.8175272345542908:  68%|██████▊   | 17533/25880 [3:35:08<1:38:58,  1.41it/s]
1|17534|Loss: 0.7669299244880676:  68%|██████▊   | 17533/25880 [3:35:08<1:38:58,  1.41it/s]
1|17534|Loss: 0.7669299244880676:  68%|██████▊   | 17534/25880 [3:35:09<1:35:31,  1.46it/s]
1|17535|Loss: 0.7823251485824585:  68%|██████▊   | 17534/25880 [3:35:09<1:35:31,  1.46it/s]
1|17535|Loss: 0.7823251485824585:  68%|██████▊   | 17535/25880 [3:35:09<1:32:10,  1.51it/s]
1|17536|Loss: 0.8827536106109619:  68%|██████▊   | 17535/25880 [3:35:10<1:32:10,  1.51it/s]
1|17536|Loss: 0.8827536106109619:  68%|██████▊   | 17536/25880 [3:35:10<1:41:49,  1.37it/s]
1|17537|Loss: 0.7153016328811646:  68%|██████▊   | 17536/25880 [3:35:11<1:41:49,  1.37it/s]
1|17537|Loss: 0.7153016328811646:  68%|██████▊   | 17537/25880 [3:35:11<1:47:54,  1.29it/s]
1|17538|Loss: 0.7814658880233765:  68%|██████▊   | 17537/25880 [3:35:12<1:47:54,  1.29it/s]
1|17538|Loss: 0.7814658880233765:  68%|██████▊   | 17538/25880 [3:35:12<1:49:31,  1.27it/s]
1|17539|Loss: 0.8397501111030579:  68%|██████▊   | 17538/25880 [3:35:12<1:49:31,  1.27it/s]
1|17539|Loss: 0.8397501111030579:  68%|██████▊   | 17539/25880 [3:35:13<1:44:50,  1.33it/s]
1|17540|Loss: 0.9380017518997192:  68%|██████▊   | 17539/25880 [3:35:13<1:44:50,  1.33it/s]
1|17540|Loss: 0.9380017518997192:  68%|██████▊   | 17540/25880 [3:35:13<1:33:53,  1.48it/s]
1|17541|Loss: 0.8193027973175049:  68%|██████▊   | 17540/25880 [3:35:13<1:33:53,  1.48it/s]
1|17541|Loss: 0.8193027973175049:  68%|██████▊   | 17541/25880 [3:35:14<1:34:01,  1.48it/s]
1|17542|Loss: 0.9018988609313965:  68%|██████▊   | 17541/25880 [3:35:14<1:34:01,  1.48it/s]
1|17542|Loss: 0.9018988609313965:  68%|██████▊   | 17542/25880 [3:35:14<1:32:49,  1.50it/s]
1|17543|Loss: 0.9169549345970154:  68%|██████▊   | 17542/25880 [3:35:15<1:32:49,  1.50it/s]
1|17543|Loss: 0.9169549345970154:  68%|██████▊   | 17543/25880 [3:35:15<1:38:21,  1.41it/s]
1|17544|Loss: 0.8189884424209595:  68%|██████▊   | 17543/25880 [3:35:16<1:38:21,  1.41it/s]
1|17544|Loss: 0.8189884424209595:  68%|██████▊   | 17544/25880 [3:35:16<1:46:44,  1.30it/s]
1|17545|Loss: 0.9234541058540344:  68%|██████▊   | 17544/25880 [3:35:16<1:46:44,  1.30it/s]
1|17545|Loss: 0.9234541058540344:  68%|██████▊   | 17545/25880 [3:35:17<1:37:15,  1.43it/s]
1|17546|Loss: 0.8101295232772827:  68%|██████▊   | 17545/25880 [3:35:17<1:37:15,  1.43it/s]
1|17546|Loss: 0.8101295232772827:  68%|██████▊   | 17546/25880 [3:35:17<1:36:38,  1.44it/s]
1|17547|Loss: 0.7873448133468628:  68%|██████▊   | 17546/25880 [3:35:18<1:36:38,  1.44it/s]
1|17547|Loss: 0.7873448133468628:  68%|██████▊   | 17547/25880 [3:35:18<1:42:04,  1.36it/s]
1|17548|Loss: 0.8993880748748779:  68%|██████▊   | 17547/25880 [3:35:19<1:42:04,  1.36it/s]
1|17548|Loss: 0.8993880748748779:  68%|██████▊   | 17548/25880 [3:35:19<1:43:05,  1.35it/s]
1|17549|Loss: 0.9148695468902588:  68%|██████▊   | 17548/25880 [3:35:19<1:43:05,  1.35it/s]
1|17549|Loss: 0.9148695468902588:  68%|██████▊   | 17549/25880 [3:35:20<1:46:55,  1.30it/s]
1|17550|Loss: 1.0355043411254883:  68%|██████▊   | 17549/25880 [3:35:20<1:46:55,  1.30it/s]
1|17550|Loss: 1.0355043411254883:  68%|██████▊   | 17550/25880 [3:35:21<1:46:50,  1.30it/s]
1|17551|Loss: 0.8979378342628479:  68%|██████▊   | 17550/25880 [3:35:21<1:46:50,  1.30it/s]
1|17551|Loss: 0.8979378342628479:  68%|██████▊   | 17551/25880 [3:35:21<1:53:17,  1.23it/s]
1|17552|Loss: 0.8551695346832275:  68%|██████▊   | 17551/25880 [3:35:22<1:53:17,  1.23it/s]
1|17552|Loss: 0.8551695346832275:  68%|██████▊   | 17552/25880 [3:35:22<1:48:26,  1.28it/s]
1|17553|Loss: 0.9226583242416382:  68%|██████▊   | 17552/25880 [3:35:23<1:48:26,  1.28it/s]
1|17553|Loss: 0.9226583242416382:  68%|██████▊   | 17553/25880 [3:35:23<1:46:15,  1.31it/s]
1|17554|Loss: 0.8435207009315491:  68%|██████▊   | 17553/25880 [3:35:23<1:46:15,  1.31it/s]
1|17554|Loss: 0.8435207009315491:  68%|██████▊   | 17554/25880 [3:35:24<1:48:23,  1.28it/s]
1|17555|Loss: 0.8769522309303284:  68%|██████▊   | 17554/25880 [3:35:24<1:48:23,  1.28it/s]
1|17555|Loss: 0.8769522309303284:  68%|██████▊   | 17555/25880 [3:35:24<1:49:33,  1.27it/s]
1|17556|Loss: 0.8090717792510986:  68%|██████▊   | 17555/25880 [3:35:25<1:49:33,  1.27it/s]
1|17556|Loss: 0.8090717792510986:  68%|██████▊   | 17556/25880 [3:35:25<1:53:53,  1.22it/s]
1|17557|Loss: 0.87139892578125:  68%|██████▊   | 17556/25880 [3:35:26<1:53:53,  1.22it/s]  
1|17557|Loss: 0.87139892578125:  68%|██████▊   | 17557/25880 [3:35:26<1:53:59,  1.22it/s]
1|17558|Loss: 0.8405420780181885:  68%|██████▊   | 17557/25880 [3:35:27<1:53:59,  1.22it/s]
1|17558|Loss: 0.8405420780181885:  68%|██████▊   | 17558/25880 [3:35:27<1:50:48,  1.25it/s]
1|17559|Loss: 0.8162731528282166:  68%|██████▊   | 17558/25880 [3:35:27<1:50:48,  1.25it/s]
1|17559|Loss: 0.8162731528282166:  68%|██████▊   | 17559/25880 [3:35:28<1:44:03,  1.33it/s]
1|17560|Loss: 0.9696536660194397:  68%|██████▊   | 17559/25880 [3:35:28<1:44:03,  1.33it/s]
1|17560|Loss: 0.9696536660194397:  68%|██████▊   | 17560/25880 [3:35:28<1:42:07,  1.36it/s]
1|17561|Loss: 0.7975872755050659:  68%|██████▊   | 17560/25880 [3:35:29<1:42:07,  1.36it/s]
1|17561|Loss: 0.7975872755050659:  68%|██████▊   | 17561/25880 [3:35:29<1:38:39,  1.41it/s]
1|17562|Loss: 0.901357114315033:  68%|██████▊   | 17561/25880 [3:35:29<1:38:39,  1.41it/s] 
1|17562|Loss: 0.901357114315033:  68%|██████▊   | 17562/25880 [3:35:30<1:38:37,  1.41it/s]
1|17563|Loss: 0.8492839932441711:  68%|██████▊   | 17562/25880 [3:35:30<1:38:37,  1.41it/s]
1|17563|Loss: 0.8492839932441711:  68%|██████▊   | 17563/25880 [3:35:30<1:35:02,  1.46it/s]
1|17564|Loss: 0.8001250624656677:  68%|██████▊   | 17563/25880 [3:35:31<1:35:02,  1.46it/s]
1|17564|Loss: 0.8001250624656677:  68%|██████▊   | 17564/25880 [3:35:31<1:32:37,  1.50it/s]
1|17565|Loss: 0.8575109243392944:  68%|██████▊   | 17564/25880 [3:35:31<1:32:37,  1.50it/s]
1|17565|Loss: 0.8575109243392944:  68%|██████▊   | 17565/25880 [3:35:32<1:38:23,  1.41it/s]
1|17566|Loss: 0.8908816576004028:  68%|██████▊   | 17565/25880 [3:35:32<1:38:23,  1.41it/s]
1|17566|Loss: 0.8908816576004028:  68%|██████▊   | 17566/25880 [3:35:33<1:43:34,  1.34it/s]
1|17567|Loss: 0.8278453946113586:  68%|██████▊   | 17566/25880 [3:35:33<1:43:34,  1.34it/s]
1|17567|Loss: 0.8278453946113586:  68%|██████▊   | 17567/25880 [3:35:33<1:43:29,  1.34it/s]
1|17568|Loss: 0.8653467297554016:  68%|██████▊   | 17567/25880 [3:35:34<1:43:29,  1.34it/s]
1|17568|Loss: 0.8653467297554016:  68%|██████▊   | 17568/25880 [3:35:34<1:39:18,  1.40it/s]
1|17569|Loss: 0.7612854242324829:  68%|██████▊   | 17568/25880 [3:35:34<1:39:18,  1.40it/s]
1|17569|Loss: 0.7612854242324829:  68%|██████▊   | 17569/25880 [3:35:35<1:36:00,  1.44it/s]
1|17570|Loss: 0.8505064845085144:  68%|██████▊   | 17569/25880 [3:35:35<1:36:00,  1.44it/s]
1|17570|Loss: 0.8505064845085144:  68%|██████▊   | 17570/25880 [3:35:35<1:36:57,  1.43it/s]
1|17571|Loss: 0.832099437713623:  68%|██████▊   | 17570/25880 [3:35:36<1:36:57,  1.43it/s] 
1|17571|Loss: 0.832099437713623:  68%|██████▊   | 17571/25880 [3:35:36<1:38:28,  1.41it/s]
1|17572|Loss: 0.7577901482582092:  68%|██████▊   | 17571/25880 [3:35:36<1:38:28,  1.41it/s]
1|17572|Loss: 0.7577901482582092:  68%|██████▊   | 17572/25880 [3:35:37<1:45:47,  1.31it/s]
1|17573|Loss: 1.0279924869537354:  68%|██████▊   | 17572/25880 [3:35:37<1:45:47,  1.31it/s]
1|17573|Loss: 1.0279924869537354:  68%|██████▊   | 17573/25880 [3:35:38<1:46:29,  1.30it/s]
1|17574|Loss: 0.6759758591651917:  68%|██████▊   | 17573/25880 [3:35:38<1:46:29,  1.30it/s]
1|17574|Loss: 0.6759758591651917:  68%|██████▊   | 17574/25880 [3:35:38<1:45:11,  1.32it/s]
1|17575|Loss: 0.8654817342758179:  68%|██████▊   | 17574/25880 [3:35:39<1:45:11,  1.32it/s]
1|17575|Loss: 0.8654817342758179:  68%|██████▊   | 17575/25880 [3:35:39<1:46:36,  1.30it/s]
1|17576|Loss: 0.9271324872970581:  68%|██████▊   | 17575/25880 [3:35:40<1:46:36,  1.30it/s]
1|17576|Loss: 0.9271324872970581:  68%|██████▊   | 17576/25880 [3:35:40<1:45:31,  1.31it/s]
1|17577|Loss: 0.8708628416061401:  68%|██████▊   | 17576/25880 [3:35:40<1:45:31,  1.31it/s]
1|17577|Loss: 0.8708628416061401:  68%|██████▊   | 17577/25880 [3:35:41<1:44:08,  1.33it/s]
1|17578|Loss: 1.0240718126296997:  68%|██████▊   | 17577/25880 [3:35:41<1:44:08,  1.33it/s]
1|17578|Loss: 1.0240718126296997:  68%|██████▊   | 17578/25880 [3:35:41<1:39:15,  1.39it/s]
1|17579|Loss: 0.8838611245155334:  68%|██████▊   | 17578/25880 [3:35:42<1:39:15,  1.39it/s]
1|17579|Loss: 0.8838611245155334:  68%|██████▊   | 17579/25880 [3:35:42<1:39:25,  1.39it/s]
1|17580|Loss: 0.7307961583137512:  68%|██████▊   | 17579/25880 [3:35:42<1:39:25,  1.39it/s]
1|17580|Loss: 0.7307961583137512:  68%|██████▊   | 17580/25880 [3:35:43<1:40:34,  1.38it/s]
1|17581|Loss: 0.8783848881721497:  68%|██████▊   | 17580/25880 [3:35:43<1:40:34,  1.38it/s]
1|17581|Loss: 0.8783848881721497:  68%|██████▊   | 17581/25880 [3:35:44<1:41:30,  1.36it/s]
1|17582|Loss: 0.821803092956543:  68%|██████▊   | 17581/25880 [3:35:44<1:41:30,  1.36it/s] 
1|17582|Loss: 0.821803092956543:  68%|██████▊   | 17582/25880 [3:35:44<1:45:26,  1.31it/s]
1|17583|Loss: 0.9269894957542419:  68%|██████▊   | 17582/25880 [3:35:45<1:45:26,  1.31it/s]
1|17583|Loss: 0.9269894957542419:  68%|██████▊   | 17583/25880 [3:35:45<1:47:15,  1.29it/s]
1|17584|Loss: 0.9173542261123657:  68%|██████▊   | 17583/25880 [3:35:46<1:47:15,  1.29it/s]
1|17584|Loss: 0.9173542261123657:  68%|██████▊   | 17584/25880 [3:35:46<1:46:40,  1.30it/s]
1|17585|Loss: 0.7746622562408447:  68%|██████▊   | 17584/25880 [3:35:46<1:46:40,  1.30it/s]
1|17585|Loss: 0.7746622562408447:  68%|██████▊   | 17585/25880 [3:35:47<1:53:00,  1.22it/s]
1|17586|Loss: 0.9987713098526001:  68%|██████▊   | 17585/25880 [3:35:47<1:53:00,  1.22it/s]
1|17586|Loss: 0.9987713098526001:  68%|██████▊   | 17586/25880 [3:35:48<1:51:25,  1.24it/s]
1|17587|Loss: 0.9118658304214478:  68%|██████▊   | 17586/25880 [3:35:48<1:51:25,  1.24it/s]
1|17587|Loss: 0.9118658304214478:  68%|██████▊   | 17587/25880 [3:35:48<1:43:38,  1.33it/s]
1|17588|Loss: 0.7228266000747681:  68%|██████▊   | 17587/25880 [3:35:49<1:43:38,  1.33it/s]
1|17588|Loss: 0.7228266000747681:  68%|██████▊   | 17588/25880 [3:35:49<1:49:58,  1.26it/s]
1|17589|Loss: 0.8398526906967163:  68%|██████▊   | 17588/25880 [3:35:50<1:49:58,  1.26it/s]
1|17589|Loss: 0.8398526906967163:  68%|██████▊   | 17589/25880 [3:35:50<1:51:48,  1.24it/s]
1|17590|Loss: 0.8056831955909729:  68%|██████▊   | 17589/25880 [3:35:50<1:51:48,  1.24it/s]
1|17590|Loss: 0.8056831955909729:  68%|██████▊   | 17590/25880 [3:35:51<1:46:25,  1.30it/s]
1|17591|Loss: 0.8390892148017883:  68%|██████▊   | 17590/25880 [3:35:51<1:46:25,  1.30it/s]
1|17591|Loss: 0.8390892148017883:  68%|██████▊   | 17591/25880 [3:35:51<1:43:59,  1.33it/s]
1|17592|Loss: 0.9058725237846375:  68%|██████▊   | 17591/25880 [3:35:52<1:43:59,  1.33it/s]
1|17592|Loss: 0.9058725237846375:  68%|██████▊   | 17592/25880 [3:35:52<1:41:50,  1.36it/s]
1|17593|Loss: 0.8350652456283569:  68%|██████▊   | 17592/25880 [3:35:53<1:41:50,  1.36it/s]
1|17593|Loss: 0.8350652456283569:  68%|██████▊   | 17593/25880 [3:35:53<1:45:21,  1.31it/s]
1|17594|Loss: 0.8812228441238403:  68%|██████▊   | 17593/25880 [3:35:53<1:45:21,  1.31it/s]
1|17594|Loss: 0.8812228441238403:  68%|██████▊   | 17594/25880 [3:35:54<1:42:26,  1.35it/s]
1|17595|Loss: 0.8198084831237793:  68%|██████▊   | 17594/25880 [3:35:54<1:42:26,  1.35it/s]
1|17595|Loss: 0.8198084831237793:  68%|██████▊   | 17595/25880 [3:35:54<1:40:22,  1.38it/s]
1|17596|Loss: 0.8748636245727539:  68%|██████▊   | 17595/25880 [3:35:55<1:40:22,  1.38it/s]
1|17596|Loss: 0.8748636245727539:  68%|██████▊   | 17596/25880 [3:35:55<1:37:09,  1.42it/s]
1|17597|Loss: 0.8682852387428284:  68%|██████▊   | 17596/25880 [3:35:55<1:37:09,  1.42it/s]
1|17597|Loss: 0.8682852387428284:  68%|██████▊   | 17597/25880 [3:35:56<1:32:47,  1.49it/s]
1|17598|Loss: 0.7894972562789917:  68%|██████▊   | 17597/25880 [3:35:56<1:32:47,  1.49it/s]
1|17598|Loss: 0.7894972562789917:  68%|██████▊   | 17598/25880 [3:35:56<1:41:45,  1.36it/s]
1|17599|Loss: 0.8363814949989319:  68%|██████▊   | 17598/25880 [3:35:57<1:41:45,  1.36it/s]
1|17599|Loss: 0.8363814949989319:  68%|██████▊   | 17599/25880 [3:35:57<1:52:42,  1.22it/s]
1|17600|Loss: 0.7704068422317505:  68%|██████▊   | 17599/25880 [3:35:58<1:52:42,  1.22it/s]
1|17600|Loss: 0.7704068422317505:  68%|██████▊   | 17600/25880 [3:35:58<1:54:15,  1.21it/s]
1|17601|Loss: 0.8060302138328552:  68%|██████▊   | 17600/25880 [3:35:59<1:54:15,  1.21it/s]
1|17601|Loss: 0.8060302138328552:  68%|██████▊   | 17601/25880 [3:35:59<1:45:33,  1.31it/s]
1|17602|Loss: 0.8363299369812012:  68%|██████▊   | 17601/25880 [3:35:59<1:45:33,  1.31it/s]
1|17602|Loss: 0.8363299369812012:  68%|██████▊   | 17602/25880 [3:36:00<1:43:21,  1.33it/s]
1|17603|Loss: 0.8136806488037109:  68%|██████▊   | 17602/25880 [3:36:00<1:43:21,  1.33it/s]
1|17603|Loss: 0.8136806488037109:  68%|██████▊   | 17603/25880 [3:36:00<1:39:07,  1.39it/s]
1|17604|Loss: 0.9262903928756714:  68%|██████▊   | 17603/25880 [3:36:01<1:39:07,  1.39it/s]
1|17604|Loss: 0.9262903928756714:  68%|██████▊   | 17604/25880 [3:36:01<1:42:05,  1.35it/s]
1|17605|Loss: 0.820591390132904:  68%|██████▊   | 17604/25880 [3:36:01<1:42:05,  1.35it/s] 
1|17605|Loss: 0.820591390132904:  68%|██████▊   | 17605/25880 [3:36:02<1:37:44,  1.41it/s]
1|17606|Loss: 0.7407896518707275:  68%|██████▊   | 17605/25880 [3:36:02<1:37:44,  1.41it/s]
1|17606|Loss: 0.7407896518707275:  68%|██████▊   | 17606/25880 [3:36:02<1:32:34,  1.49it/s]
1|17607|Loss: 0.7168047428131104:  68%|██████▊   | 17606/25880 [3:36:03<1:32:34,  1.49it/s]
1|17607|Loss: 0.7168047428131104:  68%|██████▊   | 17607/25880 [3:36:03<1:38:36,  1.40it/s]
1|17608|Loss: 0.8170144557952881:  68%|██████▊   | 17607/25880 [3:36:04<1:38:36,  1.40it/s]
1|17608|Loss: 0.8170144557952881:  68%|██████▊   | 17608/25880 [3:36:04<1:41:21,  1.36it/s]
1|17609|Loss: 0.6790612936019897:  68%|██████▊   | 17608/25880 [3:36:04<1:41:21,  1.36it/s]
1|17609|Loss: 0.6790612936019897:  68%|██████▊   | 17609/25880 [3:36:05<1:45:25,  1.31it/s]
1|17610|Loss: 0.8695782423019409:  68%|██████▊   | 17609/25880 [3:36:05<1:45:25,  1.31it/s]
1|17610|Loss: 0.8695782423019409:  68%|██████▊   | 17610/25880 [3:36:05<1:41:30,  1.36it/s]
1|17611|Loss: 0.8930985927581787:  68%|██████▊   | 17610/25880 [3:36:06<1:41:30,  1.36it/s]
1|17611|Loss: 0.8930985927581787:  68%|██████▊   | 17611/25880 [3:36:06<1:40:53,  1.37it/s]
1|17612|Loss: 0.8069561719894409:  68%|██████▊   | 17611/25880 [3:36:07<1:40:53,  1.37it/s]
1|17612|Loss: 0.8069561719894409:  68%|██████▊   | 17612/25880 [3:36:07<1:40:16,  1.37it/s]
1|17613|Loss: 0.8032011389732361:  68%|██████▊   | 17612/25880 [3:36:07<1:40:16,  1.37it/s]
1|17613|Loss: 0.8032011389732361:  68%|██████▊   | 17613/25880 [3:36:08<1:40:17,  1.37it/s]
1|17614|Loss: 0.8354354500770569:  68%|██████▊   | 17613/25880 [3:36:08<1:40:17,  1.37it/s]
1|17614|Loss: 0.8354354500770569:  68%|██████▊   | 17614/25880 [3:36:08<1:39:15,  1.39it/s]
1|17615|Loss: 0.7586745023727417:  68%|██████▊   | 17614/25880 [3:36:09<1:39:15,  1.39it/s]
1|17615|Loss: 0.7586745023727417:  68%|██████▊   | 17615/25880 [3:36:09<1:38:25,  1.40it/s]
1|17616|Loss: 0.8996378183364868:  68%|██████▊   | 17615/25880 [3:36:09<1:38:25,  1.40it/s]
1|17616|Loss: 0.8996378183364868:  68%|██████▊   | 17616/25880 [3:36:10<1:42:05,  1.35it/s]
1|17617|Loss: 0.791688084602356:  68%|██████▊   | 17616/25880 [3:36:10<1:42:05,  1.35it/s] 
1|17617|Loss: 0.791688084602356:  68%|██████▊   | 17617/25880 [3:36:11<1:44:22,  1.32it/s]
1|17618|Loss: 0.7337920665740967:  68%|██████▊   | 17617/25880 [3:36:11<1:44:22,  1.32it/s]
1|17618|Loss: 0.7337920665740967:  68%|██████▊   | 17618/25880 [3:36:11<1:42:50,  1.34it/s]
1|17619|Loss: 0.9910951852798462:  68%|██████▊   | 17618/25880 [3:36:12<1:42:50,  1.34it/s]
1|17619|Loss: 0.9910951852798462:  68%|██████▊   | 17619/25880 [3:36:12<1:36:04,  1.43it/s]
1|17620|Loss: 0.7430967092514038:  68%|██████▊   | 17619/25880 [3:36:12<1:36:04,  1.43it/s]
1|17620|Loss: 0.7430967092514038:  68%|██████▊   | 17620/25880 [3:36:13<1:34:57,  1.45it/s]
1|17621|Loss: 0.8524264097213745:  68%|██████▊   | 17620/25880 [3:36:13<1:34:57,  1.45it/s]
1|17621|Loss: 0.8524264097213745:  68%|██████▊   | 17621/25880 [3:36:13<1:36:47,  1.42it/s]
1|17622|Loss: 0.9687229990959167:  68%|██████▊   | 17621/25880 [3:36:14<1:36:47,  1.42it/s]
1|17622|Loss: 0.9687229990959167:  68%|██████▊   | 17622/25880 [3:36:14<1:30:56,  1.51it/s]
1|17623|Loss: 0.8737692832946777:  68%|██████▊   | 17622/25880 [3:36:14<1:30:56,  1.51it/s]
1|17623|Loss: 0.8737692832946777:  68%|██████▊   | 17623/25880 [3:36:14<1:27:01,  1.58it/s]
1|17624|Loss: 0.7538416981697083:  68%|██████▊   | 17623/25880 [3:36:15<1:27:01,  1.58it/s]
1|17624|Loss: 0.7538416981697083:  68%|██████▊   | 17624/25880 [3:36:15<1:21:40,  1.68it/s]
1|17625|Loss: 0.749293863773346:  68%|██████▊   | 17624/25880 [3:36:15<1:21:40,  1.68it/s] 
1|17625|Loss: 0.749293863773346:  68%|██████▊   | 17625/25880 [3:36:16<1:25:01,  1.62it/s]
1|17626|Loss: 0.8970926403999329:  68%|██████▊   | 17625/25880 [3:36:16<1:25:01,  1.62it/s]
1|17626|Loss: 0.8970926403999329:  68%|██████▊   | 17626/25880 [3:36:16<1:28:35,  1.55it/s]
1|17627|Loss: 0.9507413506507874:  68%|██████▊   | 17626/25880 [3:36:17<1:28:35,  1.55it/s]
1|17627|Loss: 0.9507413506507874:  68%|██████▊   | 17627/25880 [3:36:17<1:33:38,  1.47it/s]
1|17628|Loss: 0.7596074342727661:  68%|██████▊   | 17627/25880 [3:36:17<1:33:38,  1.47it/s]
1|17628|Loss: 0.7596074342727661:  68%|██████▊   | 17628/25880 [3:36:18<1:38:12,  1.40it/s]
1|17629|Loss: 0.7706325650215149:  68%|██████▊   | 17628/25880 [3:36:18<1:38:12,  1.40it/s]
1|17629|Loss: 0.7706325650215149:  68%|██████▊   | 17629/25880 [3:36:19<1:44:05,  1.32it/s]
1|17630|Loss: 0.837600588798523:  68%|██████▊   | 17629/25880 [3:36:19<1:44:05,  1.32it/s] 
1|17630|Loss: 0.837600588798523:  68%|██████▊   | 17630/25880 [3:36:19<1:41:23,  1.36it/s]
1|17631|Loss: 0.9009003043174744:  68%|██████▊   | 17630/25880 [3:36:20<1:41:23,  1.36it/s]
1|17631|Loss: 0.9009003043174744:  68%|██████▊   | 17631/25880 [3:36:20<1:40:22,  1.37it/s]
1|17632|Loss: 0.895908534526825:  68%|██████▊   | 17631/25880 [3:36:21<1:40:22,  1.37it/s] 
1|17632|Loss: 0.895908534526825:  68%|██████▊   | 17632/25880 [3:36:21<1:42:13,  1.34it/s]
1|17633|Loss: 0.7737448215484619:  68%|██████▊   | 17632/25880 [3:36:21<1:42:13,  1.34it/s]
1|17633|Loss: 0.7737448215484619:  68%|██████▊   | 17633/25880 [3:36:22<1:44:11,  1.32it/s]
1|17634|Loss: 0.7699743509292603:  68%|██████▊   | 17633/25880 [3:36:22<1:44:11,  1.32it/s]
1|17634|Loss: 0.7699743509292603:  68%|██████▊   | 17634/25880 [3:36:22<1:45:41,  1.30it/s]
1|17635|Loss: 0.8018166422843933:  68%|██████▊   | 17634/25880 [3:36:23<1:45:41,  1.30it/s]
1|17635|Loss: 0.8018166422843933:  68%|██████▊   | 17635/25880 [3:36:23<1:46:37,  1.29it/s]
1|17636|Loss: 0.7493982911109924:  68%|██████▊   | 17635/25880 [3:36:24<1:46:37,  1.29it/s]
1|17636|Loss: 0.7493982911109924:  68%|██████▊   | 17636/25880 [3:36:24<1:47:51,  1.27it/s]
1|17637|Loss: 0.9180073738098145:  68%|██████▊   | 17636/25880 [3:36:24<1:47:51,  1.27it/s]
1|17637|Loss: 0.9180073738098145:  68%|██████▊   | 17637/25880 [3:36:25<1:45:12,  1.31it/s]
1|17638|Loss: 0.9165445566177368:  68%|██████▊   | 17637/25880 [3:36:25<1:45:12,  1.31it/s]
1|17638|Loss: 0.9165445566177368:  68%|██████▊   | 17638/25880 [3:36:26<1:43:46,  1.32it/s]
1|17639|Loss: 0.8329116702079773:  68%|██████▊   | 17638/25880 [3:36:26<1:43:46,  1.32it/s]
1|17639|Loss: 0.8329116702079773:  68%|██████▊   | 17639/25880 [3:36:26<1:39:57,  1.37it/s]
1|17640|Loss: 0.688591718673706:  68%|██████▊   | 17639/25880 [3:36:27<1:39:57,  1.37it/s] 
1|17640|Loss: 0.688591718673706:  68%|██████▊   | 17640/25880 [3:36:27<1:47:03,  1.28it/s]
1|17641|Loss: 0.8978555202484131:  68%|██████▊   | 17640/25880 [3:36:28<1:47:03,  1.28it/s]
1|17641|Loss: 0.8978555202484131:  68%|██████▊   | 17641/25880 [3:36:28<1:47:18,  1.28it/s]
1|17642|Loss: 0.8468692302703857:  68%|██████▊   | 17641/25880 [3:36:28<1:47:18,  1.28it/s]
1|17642|Loss: 0.8468692302703857:  68%|██████▊   | 17642/25880 [3:36:29<1:45:33,  1.30it/s]
1|17643|Loss: 0.8822790384292603:  68%|██████▊   | 17642/25880 [3:36:29<1:45:33,  1.30it/s]
1|17643|Loss: 0.8822790384292603:  68%|██████▊   | 17643/25880 [3:36:30<1:51:40,  1.23it/s]
1|17644|Loss: 0.8992519974708557:  68%|██████▊   | 17643/25880 [3:36:30<1:51:40,  1.23it/s]
1|17644|Loss: 0.8992519974708557:  68%|██████▊   | 17644/25880 [3:36:30<1:49:15,  1.26it/s]
1|17645|Loss: 0.7726935744285583:  68%|██████▊   | 17644/25880 [3:36:31<1:49:15,  1.26it/s]
1|17645|Loss: 0.7726935744285583:  68%|██████▊   | 17645/25880 [3:36:31<1:48:52,  1.26it/s]
1|17646|Loss: 1.0356967449188232:  68%|██████▊   | 17645/25880 [3:36:32<1:48:52,  1.26it/s]
1|17646|Loss: 1.0356967449188232:  68%|██████▊   | 17646/25880 [3:36:32<1:49:21,  1.25it/s]
1|17647|Loss: 0.7492760419845581:  68%|██████▊   | 17646/25880 [3:36:32<1:49:21,  1.25it/s]
1|17647|Loss: 0.7492760419845581:  68%|██████▊   | 17647/25880 [3:36:33<1:44:14,  1.32it/s]
1|17648|Loss: 0.8773502707481384:  68%|██████▊   | 17647/25880 [3:36:33<1:44:14,  1.32it/s]
1|17648|Loss: 0.8773502707481384:  68%|██████▊   | 17648/25880 [3:36:33<1:41:05,  1.36it/s]
1|17649|Loss: 0.616156280040741:  68%|██████▊   | 17648/25880 [3:36:34<1:41:05,  1.36it/s] 
1|17649|Loss: 0.616156280040741:  68%|██████▊   | 17649/25880 [3:36:34<1:39:31,  1.38it/s]
1|17650|Loss: 0.7928063273429871:  68%|██████▊   | 17649/25880 [3:36:34<1:39:31,  1.38it/s]
1|17650|Loss: 0.7928063273429871:  68%|██████▊   | 17650/25880 [3:36:35<1:40:01,  1.37it/s]
1|17651|Loss: 0.8377005457878113:  68%|██████▊   | 17650/25880 [3:36:35<1:40:01,  1.37it/s]
1|17651|Loss: 0.8377005457878113:  68%|██████▊   | 17651/25880 [3:36:35<1:39:34,  1.38it/s]
1|17652|Loss: 0.9886696338653564:  68%|██████▊   | 17651/25880 [3:36:36<1:39:34,  1.38it/s]
1|17652|Loss: 0.9886696338653564:  68%|██████▊   | 17652/25880 [3:36:36<1:41:28,  1.35it/s]
1|17653|Loss: 0.8751652836799622:  68%|██████▊   | 17652/25880 [3:36:37<1:41:28,  1.35it/s]
1|17653|Loss: 0.8751652836799622:  68%|██████▊   | 17653/25880 [3:36:37<1:42:00,  1.34it/s]
1|17654|Loss: 0.8827574253082275:  68%|██████▊   | 17653/25880 [3:36:37<1:42:00,  1.34it/s]
1|17654|Loss: 0.8827574253082275:  68%|██████▊   | 17654/25880 [3:36:38<1:40:37,  1.36it/s]
1|17655|Loss: 0.7554547190666199:  68%|██████▊   | 17654/25880 [3:36:38<1:40:37,  1.36it/s]
1|17655|Loss: 0.7554547190666199:  68%|██████▊   | 17655/25880 [3:36:38<1:39:07,  1.38it/s]
1|17656|Loss: 0.9577545523643494:  68%|██████▊   | 17655/25880 [3:36:39<1:39:07,  1.38it/s]
1|17656|Loss: 0.9577545523643494:  68%|██████▊   | 17656/25880 [3:36:39<1:42:19,  1.34it/s]
1|17657|Loss: 0.896847128868103:  68%|██████▊   | 17656/25880 [3:36:39<1:42:19,  1.34it/s] 
1|17657|Loss: 0.896847128868103:  68%|██████▊   | 17657/25880 [3:36:40<1:30:27,  1.51it/s]
1|17658|Loss: 0.8262084126472473:  68%|██████▊   | 17657/25880 [3:36:40<1:30:27,  1.51it/s]
1|17658|Loss: 0.8262084126472473:  68%|██████▊   | 17658/25880 [3:36:40<1:30:00,  1.52it/s]
1|17659|Loss: 0.8394400477409363:  68%|██████▊   | 17658/25880 [3:36:41<1:30:00,  1.52it/s]
1|17659|Loss: 0.8394400477409363:  68%|██████▊   | 17659/25880 [3:36:41<1:33:18,  1.47it/s]
1|17660|Loss: 0.8217049837112427:  68%|██████▊   | 17659/25880 [3:36:41<1:33:18,  1.47it/s]
1|17660|Loss: 0.8217049837112427:  68%|██████▊   | 17660/25880 [3:36:42<1:36:14,  1.42it/s]
1|17661|Loss: 0.9334820508956909:  68%|██████▊   | 17660/25880 [3:36:42<1:36:14,  1.42it/s]
1|17661|Loss: 0.9334820508956909:  68%|██████▊   | 17661/25880 [3:36:42<1:36:57,  1.41it/s]
1|17662|Loss: 0.9384869933128357:  68%|██████▊   | 17661/25880 [3:36:43<1:36:57,  1.41it/s]
1|17662|Loss: 0.9384869933128357:  68%|██████▊   | 17662/25880 [3:36:43<1:34:30,  1.45it/s]
1|17663|Loss: 0.8714323043823242:  68%|██████▊   | 17662/25880 [3:36:44<1:34:30,  1.45it/s]
1|17663|Loss: 0.8714323043823242:  68%|██████▊   | 17663/25880 [3:36:44<1:41:06,  1.35it/s]
1|17664|Loss: 0.8149816989898682:  68%|██████▊   | 17663/25880 [3:36:44<1:41:06,  1.35it/s]
1|17664|Loss: 0.8149816989898682:  68%|██████▊   | 17664/25880 [3:36:45<1:39:12,  1.38it/s]
1|17665|Loss: 0.8318639993667603:  68%|██████▊   | 17664/25880 [3:36:45<1:39:12,  1.38it/s]
1|17665|Loss: 0.8318639993667603:  68%|██████▊   | 17665/25880 [3:36:45<1:34:10,  1.45it/s]
1|17666|Loss: 0.9114443063735962:  68%|██████▊   | 17665/25880 [3:36:46<1:34:10,  1.45it/s]
1|17666|Loss: 0.9114443063735962:  68%|██████▊   | 17666/25880 [3:36:46<1:36:59,  1.41it/s]
1|17667|Loss: 0.7611463069915771:  68%|██████▊   | 17666/25880 [3:36:46<1:36:59,  1.41it/s]
1|17667|Loss: 0.7611463069915771:  68%|██████▊   | 17667/25880 [3:36:47<1:34:45,  1.44it/s]
1|17668|Loss: 0.8228891491889954:  68%|██████▊   | 17667/25880 [3:36:47<1:34:45,  1.44it/s]
1|17668|Loss: 0.8228891491889954:  68%|██████▊   | 17668/25880 [3:36:47<1:32:16,  1.48it/s]
1|17669|Loss: 0.8523600101470947:  68%|██████▊   | 17668/25880 [3:36:48<1:32:16,  1.48it/s]
1|17669|Loss: 0.8523600101470947:  68%|██████▊   | 17669/25880 [3:36:48<1:33:11,  1.47it/s]
1|17670|Loss: 1.0120264291763306:  68%|██████▊   | 17669/25880 [3:36:48<1:33:11,  1.47it/s]
1|17670|Loss: 1.0120264291763306:  68%|██████▊   | 17670/25880 [3:36:49<1:37:12,  1.41it/s]
1|17671|Loss: 0.7254175543785095:  68%|██████▊   | 17670/25880 [3:36:49<1:37:12,  1.41it/s]
1|17671|Loss: 0.7254175543785095:  68%|██████▊   | 17671/25880 [3:36:49<1:34:56,  1.44it/s]
1|17672|Loss: 0.7881828546524048:  68%|██████▊   | 17671/25880 [3:36:50<1:34:56,  1.44it/s]
1|17672|Loss: 0.7881828546524048:  68%|██████▊   | 17672/25880 [3:36:50<1:32:36,  1.48it/s]
1|17673|Loss: 0.9186782836914062:  68%|██████▊   | 17672/25880 [3:36:50<1:32:36,  1.48it/s]
1|17673|Loss: 0.9186782836914062:  68%|██████▊   | 17673/25880 [3:36:51<1:30:29,  1.51it/s]
1|17674|Loss: 0.9479861855506897:  68%|██████▊   | 17673/25880 [3:36:51<1:30:29,  1.51it/s]
1|17674|Loss: 0.9479861855506897:  68%|██████▊   | 17674/25880 [3:36:52<1:37:24,  1.40it/s]
1|17675|Loss: 0.7888311147689819:  68%|██████▊   | 17674/25880 [3:36:52<1:37:24,  1.40it/s]
1|17675|Loss: 0.7888311147689819:  68%|██████▊   | 17675/25880 [3:36:52<1:35:52,  1.43it/s]
1|17676|Loss: 0.7974515557289124:  68%|██████▊   | 17675/25880 [3:36:53<1:35:52,  1.43it/s]
1|17676|Loss: 0.7974515557289124:  68%|██████▊   | 17676/25880 [3:36:53<1:38:34,  1.39it/s]
1|17677|Loss: 0.6738749742507935:  68%|██████▊   | 17676/25880 [3:36:53<1:38:34,  1.39it/s]
1|17677|Loss: 0.6738749742507935:  68%|██████▊   | 17677/25880 [3:36:54<1:40:03,  1.37it/s]
1|17678|Loss: 0.8504754900932312:  68%|██████▊   | 17677/25880 [3:36:54<1:40:03,  1.37it/s]
1|17678|Loss: 0.8504754900932312:  68%|██████▊   | 17678/25880 [3:36:55<1:44:21,  1.31it/s]
1|17679|Loss: 0.7827684283256531:  68%|██████▊   | 17678/25880 [3:36:55<1:44:21,  1.31it/s]
1|17679|Loss: 0.7827684283256531:  68%|██████▊   | 17679/25880 [3:36:55<1:39:10,  1.38it/s]
1|17680|Loss: 0.8785212635993958:  68%|██████▊   | 17679/25880 [3:36:56<1:39:10,  1.38it/s]
1|17680|Loss: 0.8785212635993958:  68%|██████▊   | 17680/25880 [3:36:56<1:41:20,  1.35it/s]
1|17681|Loss: 0.8288736939430237:  68%|██████▊   | 17680/25880 [3:36:56<1:41:20,  1.35it/s]
1|17681|Loss: 0.8288736939430237:  68%|██████▊   | 17681/25880 [3:36:57<1:37:53,  1.40it/s]
1|17682|Loss: 0.7724531888961792:  68%|██████▊   | 17681/25880 [3:36:57<1:37:53,  1.40it/s]
1|17682|Loss: 0.7724531888961792:  68%|██████▊   | 17682/25880 [3:36:57<1:30:52,  1.50it/s]
1|17683|Loss: 0.8720467686653137:  68%|██████▊   | 17682/25880 [3:36:58<1:30:52,  1.50it/s]
1|17683|Loss: 0.8720467686653137:  68%|██████▊   | 17683/25880 [3:36:58<1:30:49,  1.50it/s]
1|17684|Loss: 0.7728144526481628:  68%|██████▊   | 17683/25880 [3:36:58<1:30:49,  1.50it/s]
1|17684|Loss: 0.7728144526481628:  68%|██████▊   | 17684/25880 [3:36:59<1:33:31,  1.46it/s]
1|17685|Loss: 0.9140923619270325:  68%|██████▊   | 17684/25880 [3:36:59<1:33:31,  1.46it/s]
1|17685|Loss: 0.9140923619270325:  68%|██████▊   | 17685/25880 [3:36:59<1:30:49,  1.50it/s]
1|17686|Loss: 0.8578384518623352:  68%|██████▊   | 17685/25880 [3:37:00<1:30:49,  1.50it/s]
1|17686|Loss: 0.8578384518623352:  68%|██████▊   | 17686/25880 [3:37:00<1:29:10,  1.53it/s]
1|17687|Loss: 1.0111565589904785:  68%|██████▊   | 17686/25880 [3:37:00<1:29:10,  1.53it/s]
1|17687|Loss: 1.0111565589904785:  68%|██████▊   | 17687/25880 [3:37:00<1:30:49,  1.50it/s]
1|17688|Loss: 0.8588566780090332:  68%|██████▊   | 17687/25880 [3:37:01<1:30:49,  1.50it/s]
1|17688|Loss: 0.8588566780090332:  68%|██████▊   | 17688/25880 [3:37:01<1:38:04,  1.39it/s]
1|17689|Loss: 0.7831119894981384:  68%|██████▊   | 17688/25880 [3:37:02<1:38:04,  1.39it/s]
1|17689|Loss: 0.7831119894981384:  68%|██████▊   | 17689/25880 [3:37:02<1:42:21,  1.33it/s]
1|17690|Loss: 0.7270079851150513:  68%|██████▊   | 17689/25880 [3:37:03<1:42:21,  1.33it/s]
1|17690|Loss: 0.7270079851150513:  68%|██████▊   | 17690/25880 [3:37:03<1:46:54,  1.28it/s]
1|17691|Loss: 0.8957894444465637:  68%|██████▊   | 17690/25880 [3:37:03<1:46:54,  1.28it/s]
1|17691|Loss: 0.8957894444465637:  68%|██████▊   | 17691/25880 [3:37:04<1:46:05,  1.29it/s]
1|17692|Loss: 0.8123071193695068:  68%|██████▊   | 17691/25880 [3:37:04<1:46:05,  1.29it/s]
1|17692|Loss: 0.8123071193695068:  68%|██████▊   | 17692/25880 [3:37:05<1:47:27,  1.27it/s]
1|17693|Loss: 0.8894363641738892:  68%|██████▊   | 17692/25880 [3:37:05<1:47:27,  1.27it/s]
1|17693|Loss: 0.8894363641738892:  68%|██████▊   | 17693/25880 [3:37:05<1:38:41,  1.38it/s]
1|17694|Loss: 0.8197078704833984:  68%|██████▊   | 17693/25880 [3:37:06<1:38:41,  1.38it/s]
1|17694|Loss: 0.8197078704833984:  68%|██████▊   | 17694/25880 [3:37:06<1:37:34,  1.40it/s]
1|17695|Loss: 0.7766273021697998:  68%|██████▊   | 17694/25880 [3:37:06<1:37:34,  1.40it/s]
1|17695|Loss: 0.7766273021697998:  68%|██████▊   | 17695/25880 [3:37:07<1:34:58,  1.44it/s]
1|17696|Loss: 0.8145813345909119:  68%|██████▊   | 17695/25880 [3:37:07<1:34:58,  1.44it/s]
1|17696|Loss: 0.8145813345909119:  68%|██████▊   | 17696/25880 [3:37:07<1:34:51,  1.44it/s]
1|17697|Loss: 0.8636569380760193:  68%|██████▊   | 17696/25880 [3:37:08<1:34:51,  1.44it/s]
1|17697|Loss: 0.8636569380760193:  68%|██████▊   | 17697/25880 [3:37:08<1:38:37,  1.38it/s]
1|17698|Loss: 0.8298857808113098:  68%|██████▊   | 17697/25880 [3:37:08<1:38:37,  1.38it/s]
1|17698|Loss: 0.8298857808113098:  68%|██████▊   | 17698/25880 [3:37:09<1:39:45,  1.37it/s]
1|17699|Loss: 0.7434676289558411:  68%|██████▊   | 17698/25880 [3:37:09<1:39:45,  1.37it/s]
1|17699|Loss: 0.7434676289558411:  68%|██████▊   | 17699/25880 [3:37:09<1:36:05,  1.42it/s]
1|17700|Loss: 0.8606432676315308:  68%|██████▊   | 17699/25880 [3:37:10<1:36:05,  1.42it/s]
1|17700|Loss: 0.8606432676315308:  68%|██████▊   | 17700/25880 [3:37:10<1:37:53,  1.39it/s]
1|17701|Loss: 1.010266900062561:  68%|██████▊   | 17700/25880 [3:37:11<1:37:53,  1.39it/s] 
1|17701|Loss: 1.010266900062561:  68%|██████▊   | 17701/25880 [3:37:11<1:39:06,  1.38it/s]
1|17702|Loss: 0.7483000159263611:  68%|██████▊   | 17701/25880 [3:37:11<1:39:06,  1.38it/s]
1|17702|Loss: 0.7483000159263611:  68%|██████▊   | 17702/25880 [3:37:11<1:30:59,  1.50it/s]
1|17703|Loss: 0.8906275629997253:  68%|██████▊   | 17702/25880 [3:37:12<1:30:59,  1.50it/s]
1|17703|Loss: 0.8906275629997253:  68%|██████▊   | 17703/25880 [3:37:12<1:31:18,  1.49it/s]
1|17704|Loss: 0.9067308306694031:  68%|██████▊   | 17703/25880 [3:37:13<1:31:18,  1.49it/s]
1|17704|Loss: 0.9067308306694031:  68%|██████▊   | 17704/25880 [3:37:13<1:34:05,  1.45it/s]
1|17705|Loss: 0.8582248091697693:  68%|██████▊   | 17704/25880 [3:37:13<1:34:05,  1.45it/s]
1|17705|Loss: 0.8582248091697693:  68%|██████▊   | 17705/25880 [3:37:14<1:36:04,  1.42it/s]
1|17706|Loss: 0.8369350433349609:  68%|██████▊   | 17705/25880 [3:37:14<1:36:04,  1.42it/s]
1|17706|Loss: 0.8369350433349609:  68%|██████▊   | 17706/25880 [3:37:14<1:42:08,  1.33it/s]
1|17707|Loss: 0.7583058476448059:  68%|██████▊   | 17706/25880 [3:37:15<1:42:08,  1.33it/s]
1|17707|Loss: 0.7583058476448059:  68%|██████▊   | 17707/25880 [3:37:15<1:39:05,  1.37it/s]
1|17708|Loss: 0.8057082891464233:  68%|██████▊   | 17707/25880 [3:37:16<1:39:05,  1.37it/s]
1|17708|Loss: 0.8057082891464233:  68%|██████▊   | 17708/25880 [3:37:16<1:42:54,  1.32it/s]
1|17709|Loss: 0.8648067712783813:  68%|██████▊   | 17708/25880 [3:37:16<1:42:54,  1.32it/s]
1|17709|Loss: 0.8648067712783813:  68%|██████▊   | 17709/25880 [3:37:17<1:38:28,  1.38it/s]
1|17710|Loss: 0.8793783783912659:  68%|██████▊   | 17709/25880 [3:37:17<1:38:28,  1.38it/s]
1|17710|Loss: 0.8793783783912659:  68%|██████▊   | 17710/25880 [3:37:17<1:31:47,  1.48it/s]
1|17711|Loss: 0.8641163110733032:  68%|██████▊   | 17710/25880 [3:37:18<1:31:47,  1.48it/s]
1|17711|Loss: 0.8641163110733032:  68%|██████▊   | 17711/25880 [3:37:18<1:34:55,  1.43it/s]
1|17712|Loss: 0.8089038729667664:  68%|██████▊   | 17711/25880 [3:37:18<1:34:55,  1.43it/s]
1|17712|Loss: 0.8089038729667664:  68%|██████▊   | 17712/25880 [3:37:19<1:40:42,  1.35it/s]
1|17713|Loss: 0.6801837682723999:  68%|██████▊   | 17712/25880 [3:37:19<1:40:42,  1.35it/s]
1|17713|Loss: 0.6801837682723999:  68%|██████▊   | 17713/25880 [3:37:20<1:44:26,  1.30it/s]
1|17714|Loss: 0.8041223287582397:  68%|██████▊   | 17713/25880 [3:37:20<1:44:26,  1.30it/s]
1|17714|Loss: 0.8041223287582397:  68%|██████▊   | 17714/25880 [3:37:20<1:39:16,  1.37it/s]
1|17715|Loss: 0.7392098903656006:  68%|██████▊   | 17714/25880 [3:37:21<1:39:16,  1.37it/s]
1|17715|Loss: 0.7392098903656006:  68%|██████▊   | 17715/25880 [3:37:21<1:35:02,  1.43it/s]
1|17716|Loss: 0.8720940351486206:  68%|██████▊   | 17715/25880 [3:37:21<1:35:02,  1.43it/s]
1|17716|Loss: 0.8720940351486206:  68%|██████▊   | 17716/25880 [3:37:22<1:35:37,  1.42it/s]
1|17717|Loss: 0.7140787839889526:  68%|██████▊   | 17716/25880 [3:37:22<1:35:37,  1.42it/s]
1|17717|Loss: 0.7140787839889526:  68%|██████▊   | 17717/25880 [3:37:22<1:35:33,  1.42it/s]
1|17718|Loss: 0.8567365407943726:  68%|██████▊   | 17717/25880 [3:37:23<1:35:33,  1.42it/s]
1|17718|Loss: 0.8567365407943726:  68%|██████▊   | 17718/25880 [3:37:23<1:35:24,  1.43it/s]
1|17719|Loss: 0.8634095788002014:  68%|██████▊   | 17718/25880 [3:37:23<1:35:24,  1.43it/s]
1|17719|Loss: 0.8634095788002014:  68%|██████▊   | 17719/25880 [3:37:24<1:39:31,  1.37it/s]
1|17720|Loss: 0.7396578788757324:  68%|██████▊   | 17719/25880 [3:37:24<1:39:31,  1.37it/s]
1|17720|Loss: 0.7396578788757324:  68%|██████▊   | 17720/25880 [3:37:25<1:43:33,  1.31it/s]
1|17721|Loss: 0.8856815099716187:  68%|██████▊   | 17720/25880 [3:37:25<1:43:33,  1.31it/s]
1|17721|Loss: 0.8856815099716187:  68%|██████▊   | 17721/25880 [3:37:25<1:47:06,  1.27it/s]
1|17722|Loss: 0.8802443742752075:  68%|██████▊   | 17721/25880 [3:37:26<1:47:06,  1.27it/s]
1|17722|Loss: 0.8802443742752075:  68%|██████▊   | 17722/25880 [3:37:26<1:48:07,  1.26it/s]
1|17723|Loss: 0.9546740055084229:  68%|██████▊   | 17722/25880 [3:37:27<1:48:07,  1.26it/s]
1|17723|Loss: 0.9546740055084229:  68%|██████▊   | 17723/25880 [3:37:27<1:37:05,  1.40it/s]
1|17724|Loss: 0.8800111413002014:  68%|██████▊   | 17723/25880 [3:37:27<1:37:05,  1.40it/s]
1|17724|Loss: 0.8800111413002014:  68%|██████▊   | 17724/25880 [3:37:28<1:38:33,  1.38it/s]
1|17725|Loss: 1.0107227563858032:  68%|██████▊   | 17724/25880 [3:37:28<1:38:33,  1.38it/s]
1|17725|Loss: 1.0107227563858032:  68%|██████▊   | 17725/25880 [3:37:28<1:39:39,  1.36it/s]
1|17726|Loss: 0.8407557010650635:  68%|██████▊   | 17725/25880 [3:37:29<1:39:39,  1.36it/s]
1|17726|Loss: 0.8407557010650635:  68%|██████▊   | 17726/25880 [3:37:29<1:35:48,  1.42it/s]
1|17727|Loss: 0.8423146605491638:  68%|██████▊   | 17726/25880 [3:37:29<1:35:48,  1.42it/s]
1|17727|Loss: 0.8423146605491638:  68%|██████▊   | 17727/25880 [3:37:29<1:30:07,  1.51it/s]
1|17728|Loss: 0.8072522878646851:  68%|██████▊   | 17727/25880 [3:37:30<1:30:07,  1.51it/s]
1|17728|Loss: 0.8072522878646851:  69%|██████▊   | 17728/25880 [3:37:30<1:31:27,  1.49it/s]
1|17729|Loss: 0.7893406748771667:  69%|██████▊   | 17728/25880 [3:37:31<1:31:27,  1.49it/s]
1|17729|Loss: 0.7893406748771667:  69%|██████▊   | 17729/25880 [3:37:31<1:37:35,  1.39it/s]
1|17730|Loss: 0.9250406622886658:  69%|██████▊   | 17729/25880 [3:37:31<1:37:35,  1.39it/s]
1|17730|Loss: 0.9250406622886658:  69%|██████▊   | 17730/25880 [3:37:32<1:38:21,  1.38it/s]
1|17731|Loss: 0.8609839677810669:  69%|██████▊   | 17730/25880 [3:37:32<1:38:21,  1.38it/s]
1|17731|Loss: 0.8609839677810669:  69%|██████▊   | 17731/25880 [3:37:32<1:38:23,  1.38it/s]
1|17732|Loss: 0.811470627784729:  69%|██████▊   | 17731/25880 [3:37:33<1:38:23,  1.38it/s] 
1|17732|Loss: 0.811470627784729:  69%|██████▊   | 17732/25880 [3:37:33<1:41:54,  1.33it/s]
1|17733|Loss: 0.8276466131210327:  69%|██████▊   | 17732/25880 [3:37:34<1:41:54,  1.33it/s]
1|17733|Loss: 0.8276466131210327:  69%|██████▊   | 17733/25880 [3:37:34<1:34:41,  1.43it/s]
1|17734|Loss: 0.8067217469215393:  69%|██████▊   | 17733/25880 [3:37:34<1:34:41,  1.43it/s]
1|17734|Loss: 0.8067217469215393:  69%|██████▊   | 17734/25880 [3:37:34<1:31:01,  1.49it/s]
1|17735|Loss: 0.8197601437568665:  69%|██████▊   | 17734/25880 [3:37:35<1:31:01,  1.49it/s]
1|17735|Loss: 0.8197601437568665:  69%|██████▊   | 17735/25880 [3:37:35<1:25:36,  1.59it/s]
1|17736|Loss: 0.7835230827331543:  69%|██████▊   | 17735/25880 [3:37:35<1:25:36,  1.59it/s]
1|17736|Loss: 0.7835230827331543:  69%|██████▊   | 17736/25880 [3:37:36<1:31:09,  1.49it/s]
1|17737|Loss: 0.8819350004196167:  69%|██████▊   | 17736/25880 [3:37:36<1:31:09,  1.49it/s]
1|17737|Loss: 0.8819350004196167:  69%|██████▊   | 17737/25880 [3:37:37<1:34:39,  1.43it/s]
1|17738|Loss: 0.949440598487854:  69%|██████▊   | 17737/25880 [3:37:37<1:34:39,  1.43it/s] 
1|17738|Loss: 0.949440598487854:  69%|██████▊   | 17738/25880 [3:37:37<1:32:36,  1.47it/s]
1|17739|Loss: 0.8413100242614746:  69%|██████▊   | 17738/25880 [3:37:38<1:32:36,  1.47it/s]
1|17739|Loss: 0.8413100242614746:  69%|██████▊   | 17739/25880 [3:37:38<1:32:53,  1.46it/s]
1|17740|Loss: 0.89915531873703:  69%|██████▊   | 17739/25880 [3:37:38<1:32:53,  1.46it/s]  
1|17740|Loss: 0.89915531873703:  69%|██████▊   | 17740/25880 [3:37:39<1:33:36,  1.45it/s]
1|17741|Loss: 0.8477524518966675:  69%|██████▊   | 17740/25880 [3:37:39<1:33:36,  1.45it/s]
1|17741|Loss: 0.8477524518966675:  69%|██████▊   | 17741/25880 [3:37:39<1:32:05,  1.47it/s]
1|17742|Loss: 0.8581914305686951:  69%|██████▊   | 17741/25880 [3:37:40<1:32:05,  1.47it/s]
1|17742|Loss: 0.8581914305686951:  69%|██████▊   | 17742/25880 [3:37:40<1:33:27,  1.45it/s]
1|17743|Loss: 0.7714101076126099:  69%|██████▊   | 17742/25880 [3:37:40<1:33:27,  1.45it/s]
1|17743|Loss: 0.7714101076126099:  69%|██████▊   | 17743/25880 [3:37:41<1:34:07,  1.44it/s]
1|17744|Loss: 0.8505954146385193:  69%|██████▊   | 17743/25880 [3:37:41<1:34:07,  1.44it/s]
1|17744|Loss: 0.8505954146385193:  69%|██████▊   | 17744/25880 [3:37:41<1:39:10,  1.37it/s]
1|17745|Loss: 0.8174185156822205:  69%|██████▊   | 17744/25880 [3:37:42<1:39:10,  1.37it/s]
1|17745|Loss: 0.8174185156822205:  69%|██████▊   | 17745/25880 [3:37:42<1:40:37,  1.35it/s]
1|17746|Loss: 0.8198447227478027:  69%|██████▊   | 17745/25880 [3:37:43<1:40:37,  1.35it/s]
1|17746|Loss: 0.8198447227478027:  69%|██████▊   | 17746/25880 [3:37:43<1:35:40,  1.42it/s]
1|17747|Loss: 0.8657912611961365:  69%|██████▊   | 17746/25880 [3:37:43<1:35:40,  1.42it/s]
1|17747|Loss: 0.8657912611961365:  69%|██████▊   | 17747/25880 [3:37:43<1:30:53,  1.49it/s]
1|17748|Loss: 0.9576595425605774:  69%|██████▊   | 17747/25880 [3:37:44<1:30:53,  1.49it/s]
1|17748|Loss: 0.9576595425605774:  69%|██████▊   | 17748/25880 [3:37:44<1:29:04,  1.52it/s]
1|17749|Loss: 0.8354612588882446:  69%|██████▊   | 17748/25880 [3:37:44<1:29:04,  1.52it/s]
1|17749|Loss: 0.8354612588882446:  69%|██████▊   | 17749/25880 [3:37:45<1:24:12,  1.61it/s]
1|17750|Loss: 0.9688522815704346:  69%|██████▊   | 17749/25880 [3:37:45<1:24:12,  1.61it/s]
1|17750|Loss: 0.9688522815704346:  69%|██████▊   | 17750/25880 [3:37:45<1:31:16,  1.48it/s]
1|17751|Loss: 0.8381989002227783:  69%|██████▊   | 17750/25880 [3:37:46<1:31:16,  1.48it/s]
1|17751|Loss: 0.8381989002227783:  69%|██████▊   | 17751/25880 [3:37:46<1:39:28,  1.36it/s]
1|17752|Loss: 0.8193163871765137:  69%|██████▊   | 17751/25880 [3:37:47<1:39:28,  1.36it/s]
1|17752|Loss: 0.8193163871765137:  69%|██████▊   | 17752/25880 [3:37:47<1:33:37,  1.45it/s]
1|17753|Loss: 0.7634831666946411:  69%|██████▊   | 17752/25880 [3:37:47<1:33:37,  1.45it/s]
1|17753|Loss: 0.7634831666946411:  69%|██████▊   | 17753/25880 [3:37:48<1:42:56,  1.32it/s]
1|17754|Loss: 0.9435372352600098:  69%|██████▊   | 17753/25880 [3:37:48<1:42:56,  1.32it/s]
1|17754|Loss: 0.9435372352600098:  69%|██████▊   | 17754/25880 [3:37:49<1:48:52,  1.24it/s]
1|17755|Loss: 0.8362811207771301:  69%|██████▊   | 17754/25880 [3:37:49<1:48:52,  1.24it/s]
1|17755|Loss: 0.8362811207771301:  69%|██████▊   | 17755/25880 [3:37:50<1:50:47,  1.22it/s]
1|17756|Loss: 0.8482734560966492:  69%|██████▊   | 17755/25880 [3:37:50<1:50:47,  1.22it/s]
1|17756|Loss: 0.8482734560966492:  69%|██████▊   | 17756/25880 [3:37:50<1:50:22,  1.23it/s]
1|17757|Loss: 0.7896843552589417:  69%|██████▊   | 17756/25880 [3:37:51<1:50:22,  1.23it/s]
1|17757|Loss: 0.7896843552589417:  69%|██████▊   | 17757/25880 [3:37:51<1:41:52,  1.33it/s]
1|17758|Loss: 0.8832041025161743:  69%|██████▊   | 17757/25880 [3:37:51<1:41:52,  1.33it/s]
1|17758|Loss: 0.8832041025161743:  69%|██████▊   | 17758/25880 [3:37:52<1:36:31,  1.40it/s]
1|17759|Loss: 0.7017974853515625:  69%|██████▊   | 17758/25880 [3:37:52<1:36:31,  1.40it/s]
1|17759|Loss: 0.7017974853515625:  69%|██████▊   | 17759/25880 [3:37:52<1:37:05,  1.39it/s]
1|17760|Loss: 0.7759178876876831:  69%|██████▊   | 17759/25880 [3:37:53<1:37:05,  1.39it/s]
1|17760|Loss: 0.7759178876876831:  69%|██████▊   | 17760/25880 [3:37:53<1:37:08,  1.39it/s]
1|17761|Loss: 0.7713255286216736:  69%|██████▊   | 17760/25880 [3:37:53<1:37:08,  1.39it/s]
1|17761|Loss: 0.7713255286216736:  69%|██████▊   | 17761/25880 [3:37:54<1:44:58,  1.29it/s]
1|17762|Loss: 0.9022793173789978:  69%|██████▊   | 17761/25880 [3:37:54<1:44:58,  1.29it/s]
1|17762|Loss: 0.9022793173789978:  69%|██████▊   | 17762/25880 [3:37:55<1:44:06,  1.30it/s]
1|17763|Loss: 0.8265713453292847:  69%|██████▊   | 17762/25880 [3:37:55<1:44:06,  1.30it/s]
1|17763|Loss: 0.8265713453292847:  69%|██████▊   | 17763/25880 [3:37:55<1:42:26,  1.32it/s]
1|17764|Loss: 0.7724098563194275:  69%|██████▊   | 17763/25880 [3:37:56<1:42:26,  1.32it/s]
1|17764|Loss: 0.7724098563194275:  69%|██████▊   | 17764/25880 [3:37:56<1:37:34,  1.39it/s]
1|17765|Loss: 0.8095933198928833:  69%|██████▊   | 17764/25880 [3:37:56<1:37:34,  1.39it/s]
1|17765|Loss: 0.8095933198928833:  69%|██████▊   | 17765/25880 [3:37:57<1:37:22,  1.39it/s]
1|17766|Loss: 0.7914219498634338:  69%|██████▊   | 17765/25880 [3:37:57<1:37:22,  1.39it/s]
1|17766|Loss: 0.7914219498634338:  69%|██████▊   | 17766/25880 [3:37:57<1:37:10,  1.39it/s]
1|17767|Loss: 0.9552422761917114:  69%|██████▊   | 17766/25880 [3:37:58<1:37:10,  1.39it/s]
1|17767|Loss: 0.9552422761917114:  69%|██████▊   | 17767/25880 [3:37:58<1:37:39,  1.38it/s]
1|17768|Loss: 0.8833982348442078:  69%|██████▊   | 17767/25880 [3:37:59<1:37:39,  1.38it/s]
1|17768|Loss: 0.8833982348442078:  69%|██████▊   | 17768/25880 [3:37:59<1:30:16,  1.50it/s]
1|17769|Loss: 0.7173734307289124:  69%|██████▊   | 17768/25880 [3:37:59<1:30:16,  1.50it/s]
1|17769|Loss: 0.7173734307289124:  69%|██████▊   | 17769/25880 [3:37:59<1:33:20,  1.45it/s]
1|17770|Loss: 0.814954936504364:  69%|██████▊   | 17769/25880 [3:38:00<1:33:20,  1.45it/s] 
1|17770|Loss: 0.814954936504364:  69%|██████▊   | 17770/25880 [3:38:00<1:31:49,  1.47it/s]
1|17771|Loss: 0.9246596097946167:  69%|██████▊   | 17770/25880 [3:38:00<1:31:49,  1.47it/s]
1|17771|Loss: 0.9246596097946167:  69%|██████▊   | 17771/25880 [3:38:01<1:29:20,  1.51it/s]
1|17772|Loss: 0.8237336874008179:  69%|██████▊   | 17771/25880 [3:38:01<1:29:20,  1.51it/s]
1|17772|Loss: 0.8237336874008179:  69%|██████▊   | 17772/25880 [3:38:01<1:26:36,  1.56it/s]
1|17773|Loss: 0.886961042881012:  69%|██████▊   | 17772/25880 [3:38:02<1:26:36,  1.56it/s] 
1|17773|Loss: 0.886961042881012:  69%|██████▊   | 17773/25880 [3:38:02<1:25:09,  1.59it/s]
1|17774|Loss: 0.7891048192977905:  69%|██████▊   | 17773/25880 [3:38:02<1:25:09,  1.59it/s]
1|17774|Loss: 0.7891048192977905:  69%|██████▊   | 17774/25880 [3:38:03<1:28:17,  1.53it/s]
1|17775|Loss: 0.8878530859947205:  69%|██████▊   | 17774/25880 [3:38:03<1:28:17,  1.53it/s]
1|17775|Loss: 0.8878530859947205:  69%|██████▊   | 17775/25880 [3:38:03<1:28:12,  1.53it/s]
1|17776|Loss: 0.8090585470199585:  69%|██████▊   | 17775/25880 [3:38:04<1:28:12,  1.53it/s]
1|17776|Loss: 0.8090585470199585:  69%|██████▊   | 17776/25880 [3:38:04<1:34:43,  1.43it/s]
1|17777|Loss: 0.891140341758728:  69%|██████▊   | 17776/25880 [3:38:05<1:34:43,  1.43it/s] 
1|17777|Loss: 0.891140341758728:  69%|██████▊   | 17777/25880 [3:38:05<1:36:12,  1.40it/s]
1|17778|Loss: 0.9326454401016235:  69%|██████▊   | 17777/25880 [3:38:05<1:36:12,  1.40it/s]
1|17778|Loss: 0.9326454401016235:  69%|██████▊   | 17778/25880 [3:38:06<1:33:32,  1.44it/s]
1|17779|Loss: 0.9048932790756226:  69%|██████▊   | 17778/25880 [3:38:06<1:33:32,  1.44it/s]
1|17779|Loss: 0.9048932790756226:  69%|██████▊   | 17779/25880 [3:38:06<1:33:23,  1.45it/s]
1|17780|Loss: 0.7253289818763733:  69%|██████▊   | 17779/25880 [3:38:07<1:33:23,  1.45it/s]
1|17780|Loss: 0.7253289818763733:  69%|██████▊   | 17780/25880 [3:38:07<1:28:56,  1.52it/s]
1|17781|Loss: 0.7794870734214783:  69%|██████▊   | 17780/25880 [3:38:07<1:28:56,  1.52it/s]
1|17781|Loss: 0.7794870734214783:  69%|██████▊   | 17781/25880 [3:38:07<1:29:16,  1.51it/s]
1|17782|Loss: 0.8345699310302734:  69%|██████▊   | 17781/25880 [3:38:08<1:29:16,  1.51it/s]
1|17782|Loss: 0.8345699310302734:  69%|██████▊   | 17782/25880 [3:38:08<1:28:09,  1.53it/s]
1|17783|Loss: 0.8774685263633728:  69%|██████▊   | 17782/25880 [3:38:08<1:28:09,  1.53it/s]
1|17783|Loss: 0.8774685263633728:  69%|██████▊   | 17783/25880 [3:38:09<1:34:24,  1.43it/s]
1|17784|Loss: 0.801618218421936:  69%|██████▊   | 17783/25880 [3:38:09<1:34:24,  1.43it/s] 
1|17784|Loss: 0.801618218421936:  69%|██████▊   | 17784/25880 [3:38:10<1:33:53,  1.44it/s]
1|17785|Loss: 0.7991406917572021:  69%|██████▊   | 17784/25880 [3:38:10<1:33:53,  1.44it/s]
1|17785|Loss: 0.7991406917572021:  69%|██████▊   | 17785/25880 [3:38:10<1:27:56,  1.53it/s]
1|17786|Loss: 0.8513048887252808:  69%|██████▊   | 17785/25880 [3:38:10<1:27:56,  1.53it/s]
1|17786|Loss: 0.8513048887252808:  69%|██████▊   | 17786/25880 [3:38:11<1:31:11,  1.48it/s]
1|17787|Loss: 0.8001840710639954:  69%|██████▊   | 17786/25880 [3:38:11<1:31:11,  1.48it/s]
1|17787|Loss: 0.8001840710639954:  69%|██████▊   | 17787/25880 [3:38:12<1:37:45,  1.38it/s]
1|17788|Loss: 0.9009658694267273:  69%|██████▊   | 17787/25880 [3:38:12<1:37:45,  1.38it/s]
1|17788|Loss: 0.9009658694267273:  69%|██████▊   | 17788/25880 [3:38:12<1:39:06,  1.36it/s]
1|17789|Loss: 0.9008232951164246:  69%|██████▊   | 17788/25880 [3:38:13<1:39:06,  1.36it/s]
1|17789|Loss: 0.9008232951164246:  69%|██████▊   | 17789/25880 [3:38:13<1:35:46,  1.41it/s]
1|17790|Loss: 0.9755426049232483:  69%|██████▊   | 17789/25880 [3:38:13<1:35:46,  1.41it/s]
1|17790|Loss: 0.9755426049232483:  69%|██████▊   | 17790/25880 [3:38:14<1:36:08,  1.40it/s]
1|17791|Loss: 0.7532774209976196:  69%|██████▊   | 17790/25880 [3:38:14<1:36:08,  1.40it/s]
1|17791|Loss: 0.7532774209976196:  69%|██████▊   | 17791/25880 [3:38:14<1:33:20,  1.44it/s]
1|17792|Loss: 0.8671146631240845:  69%|██████▊   | 17791/25880 [3:38:15<1:33:20,  1.44it/s]
1|17792|Loss: 0.8671146631240845:  69%|██████▊   | 17792/25880 [3:38:15<1:33:56,  1.43it/s]
1|17793|Loss: 0.9195314645767212:  69%|██████▊   | 17792/25880 [3:38:16<1:33:56,  1.43it/s]
1|17793|Loss: 0.9195314645767212:  69%|██████▉   | 17793/25880 [3:38:16<1:35:28,  1.41it/s]
1|17794|Loss: 0.6034739017486572:  69%|██████▉   | 17793/25880 [3:38:16<1:35:28,  1.41it/s]
1|17794|Loss: 0.6034739017486572:  69%|██████▉   | 17794/25880 [3:38:17<1:40:22,  1.34it/s]
1|17795|Loss: 0.7949642539024353:  69%|██████▉   | 17794/25880 [3:38:17<1:40:22,  1.34it/s]
1|17795|Loss: 0.7949642539024353:  69%|██████▉   | 17795/25880 [3:38:17<1:39:55,  1.35it/s]
1|17796|Loss: 0.9004853963851929:  69%|██████▉   | 17795/25880 [3:38:18<1:39:55,  1.35it/s]
1|17796|Loss: 0.9004853963851929:  69%|██████▉   | 17796/25880 [3:38:18<1:37:56,  1.38it/s]
1|17797|Loss: 0.8666332960128784:  69%|██████▉   | 17796/25880 [3:38:19<1:37:56,  1.38it/s]
1|17797|Loss: 0.8666332960128784:  69%|██████▉   | 17797/25880 [3:38:19<1:41:32,  1.33it/s]
1|17798|Loss: 0.8408567309379578:  69%|██████▉   | 17797/25880 [3:38:19<1:41:32,  1.33it/s]
1|17798|Loss: 0.8408567309379578:  69%|██████▉   | 17798/25880 [3:38:20<1:44:07,  1.29it/s]
1|17799|Loss: 0.8662678599357605:  69%|██████▉   | 17798/25880 [3:38:20<1:44:07,  1.29it/s]
1|17799|Loss: 0.8662678599357605:  69%|██████▉   | 17799/25880 [3:38:20<1:40:00,  1.35it/s]
1|17800|Loss: 0.8987740278244019:  69%|██████▉   | 17799/25880 [3:38:21<1:40:00,  1.35it/s]
1|17800|Loss: 0.8987740278244019:  69%|██████▉   | 17800/25880 [3:38:21<1:38:06,  1.37it/s]
1|17801|Loss: 0.8247765302658081:  69%|██████▉   | 17800/25880 [3:38:22<1:38:06,  1.37it/s]
1|17801|Loss: 0.8247765302658081:  69%|██████▉   | 17801/25880 [3:38:22<1:34:13,  1.43it/s]
1|17802|Loss: 0.8367772102355957:  69%|██████▉   | 17801/25880 [3:38:22<1:34:13,  1.43it/s]
1|17802|Loss: 0.8367772102355957:  69%|██████▉   | 17802/25880 [3:38:23<1:38:34,  1.37it/s]
1|17803|Loss: 0.8480740189552307:  69%|██████▉   | 17802/25880 [3:38:23<1:38:34,  1.37it/s]
1|17803|Loss: 0.8480740189552307:  69%|██████▉   | 17803/25880 [3:38:23<1:41:25,  1.33it/s]
1|17804|Loss: 0.9409293532371521:  69%|██████▉   | 17803/25880 [3:38:24<1:41:25,  1.33it/s]
1|17804|Loss: 0.9409293532371521:  69%|██████▉   | 17804/25880 [3:38:24<1:41:12,  1.33it/s]
1|17805|Loss: 0.9409503936767578:  69%|██████▉   | 17804/25880 [3:38:25<1:41:12,  1.33it/s]
1|17805|Loss: 0.9409503936767578:  69%|██████▉   | 17805/25880 [3:38:25<1:39:19,  1.35it/s]
1|17806|Loss: 0.8173441290855408:  69%|██████▉   | 17805/25880 [3:38:25<1:39:19,  1.35it/s]
1|17806|Loss: 0.8173441290855408:  69%|██████▉   | 17806/25880 [3:38:26<1:44:40,  1.29it/s]
1|17807|Loss: 0.8202452659606934:  69%|██████▉   | 17806/25880 [3:38:26<1:44:40,  1.29it/s]
1|17807|Loss: 0.8202452659606934:  69%|██████▉   | 17807/25880 [3:38:26<1:41:10,  1.33it/s]
1|17808|Loss: 1.0399140119552612:  69%|██████▉   | 17807/25880 [3:38:27<1:41:10,  1.33it/s]
1|17808|Loss: 1.0399140119552612:  69%|██████▉   | 17808/25880 [3:38:27<1:41:24,  1.33it/s]
1|17809|Loss: 0.9665799140930176:  69%|██████▉   | 17808/25880 [3:38:28<1:41:24,  1.33it/s]
1|17809|Loss: 0.9665799140930176:  69%|██████▉   | 17809/25880 [3:38:28<1:44:34,  1.29it/s]
1|17810|Loss: 0.886785089969635:  69%|██████▉   | 17809/25880 [3:38:28<1:44:34,  1.29it/s] 
1|17810|Loss: 0.886785089969635:  69%|██████▉   | 17810/25880 [3:38:29<1:49:19,  1.23it/s]
1|17811|Loss: 0.9331347346305847:  69%|██████▉   | 17810/25880 [3:38:29<1:49:19,  1.23it/s]
1|17811|Loss: 0.9331347346305847:  69%|██████▉   | 17811/25880 [3:38:30<1:47:30,  1.25it/s]
1|17812|Loss: 0.9036910533905029:  69%|██████▉   | 17811/25880 [3:38:30<1:47:30,  1.25it/s]
1|17812|Loss: 0.9036910533905029:  69%|██████▉   | 17812/25880 [3:38:30<1:44:12,  1.29it/s]
1|17813|Loss: 0.879365086555481:  69%|██████▉   | 17812/25880 [3:38:31<1:44:12,  1.29it/s] 
1|17813|Loss: 0.879365086555481:  69%|██████▉   | 17813/25880 [3:38:31<1:42:20,  1.31it/s]
1|17814|Loss: 0.9071859121322632:  69%|██████▉   | 17813/25880 [3:38:31<1:42:20,  1.31it/s]
1|17814|Loss: 0.9071859121322632:  69%|██████▉   | 17814/25880 [3:38:32<1:32:28,  1.45it/s]
1|17815|Loss: 0.8905655741691589:  69%|██████▉   | 17814/25880 [3:38:32<1:32:28,  1.45it/s]
1|17815|Loss: 0.8905655741691589:  69%|██████▉   | 17815/25880 [3:38:32<1:30:52,  1.48it/s]
1|17816|Loss: 0.8208199143409729:  69%|██████▉   | 17815/25880 [3:38:33<1:30:52,  1.48it/s]
1|17816|Loss: 0.8208199143409729:  69%|██████▉   | 17816/25880 [3:38:33<1:34:43,  1.42it/s]
1|17817|Loss: 0.8732922673225403:  69%|██████▉   | 17816/25880 [3:38:33<1:34:43,  1.42it/s]
1|17817|Loss: 0.8732922673225403:  69%|██████▉   | 17817/25880 [3:38:34<1:36:33,  1.39it/s]
1|17818|Loss: 0.903294026851654:  69%|██████▉   | 17817/25880 [3:38:34<1:36:33,  1.39it/s] 
1|17818|Loss: 0.903294026851654:  69%|██████▉   | 17818/25880 [3:38:35<1:37:23,  1.38it/s]
1|17819|Loss: 0.8601441383361816:  69%|██████▉   | 17818/25880 [3:38:35<1:37:23,  1.38it/s]
1|17819|Loss: 0.8601441383361816:  69%|██████▉   | 17819/25880 [3:38:35<1:45:34,  1.27it/s]
1|17820|Loss: 0.8212120532989502:  69%|██████▉   | 17819/25880 [3:38:36<1:45:34,  1.27it/s]
1|17820|Loss: 0.8212120532989502:  69%|██████▉   | 17820/25880 [3:38:36<1:52:58,  1.19it/s]
1|17821|Loss: 0.7272869944572449:  69%|██████▉   | 17820/25880 [3:38:37<1:52:58,  1.19it/s]
1|17821|Loss: 0.7272869944572449:  69%|██████▉   | 17821/25880 [3:38:37<1:49:25,  1.23it/s]
1|17822|Loss: 0.8724320530891418:  69%|██████▉   | 17821/25880 [3:38:38<1:49:25,  1.23it/s]
1|17822|Loss: 0.8724320530891418:  69%|██████▉   | 17822/25880 [3:38:38<1:45:00,  1.28it/s]
1|17823|Loss: 0.8303278088569641:  69%|██████▉   | 17822/25880 [3:38:38<1:45:00,  1.28it/s]
1|17823|Loss: 0.8303278088569641:  69%|██████▉   | 17823/25880 [3:38:38<1:34:32,  1.42it/s]
1|17824|Loss: 1.0112768411636353:  69%|██████▉   | 17823/25880 [3:38:39<1:34:32,  1.42it/s]
1|17824|Loss: 1.0112768411636353:  69%|██████▉   | 17824/25880 [3:38:39<1:36:47,  1.39it/s]
1|17825|Loss: 0.8151957988739014:  69%|██████▉   | 17824/25880 [3:38:40<1:36:47,  1.39it/s]
1|17825|Loss: 0.8151957988739014:  69%|██████▉   | 17825/25880 [3:38:40<1:35:01,  1.41it/s]
1|17826|Loss: 0.7908532023429871:  69%|██████▉   | 17825/25880 [3:38:40<1:35:01,  1.41it/s]
1|17826|Loss: 0.7908532023429871:  69%|██████▉   | 17826/25880 [3:38:41<1:32:05,  1.46it/s]
1|17827|Loss: 0.8177419900894165:  69%|██████▉   | 17826/25880 [3:38:41<1:32:05,  1.46it/s]
1|17827|Loss: 0.8177419900894165:  69%|██████▉   | 17827/25880 [3:38:41<1:38:00,  1.37it/s]
1|17828|Loss: 0.8200092911720276:  69%|██████▉   | 17827/25880 [3:38:42<1:38:00,  1.37it/s]
1|17828|Loss: 0.8200092911720276:  69%|██████▉   | 17828/25880 [3:38:42<1:32:27,  1.45it/s]
1|17829|Loss: 0.8698341846466064:  69%|██████▉   | 17828/25880 [3:38:42<1:32:27,  1.45it/s]
1|17829|Loss: 0.8698341846466064:  69%|██████▉   | 17829/25880 [3:38:43<1:31:22,  1.47it/s]
1|17830|Loss: 0.7968167662620544:  69%|██████▉   | 17829/25880 [3:38:43<1:31:22,  1.47it/s]
1|17830|Loss: 0.7968167662620544:  69%|██████▉   | 17830/25880 [3:38:43<1:30:06,  1.49it/s]
1|17831|Loss: 0.8024740815162659:  69%|██████▉   | 17830/25880 [3:38:44<1:30:06,  1.49it/s]
1|17831|Loss: 0.8024740815162659:  69%|██████▉   | 17831/25880 [3:38:44<1:30:52,  1.48it/s]
1|17832|Loss: 0.8865690231323242:  69%|██████▉   | 17831/25880 [3:38:44<1:30:52,  1.48it/s]
1|17832|Loss: 0.8865690231323242:  69%|██████▉   | 17832/25880 [3:38:45<1:33:17,  1.44it/s]
1|17833|Loss: 0.8805949091911316:  69%|██████▉   | 17832/25880 [3:38:45<1:33:17,  1.44it/s]
1|17833|Loss: 0.8805949091911316:  69%|██████▉   | 17833/25880 [3:38:45<1:36:55,  1.38it/s]
1|17834|Loss: 0.9978564381599426:  69%|██████▉   | 17833/25880 [3:38:46<1:36:55,  1.38it/s]
1|17834|Loss: 0.9978564381599426:  69%|██████▉   | 17834/25880 [3:38:46<1:34:18,  1.42it/s]
1|17835|Loss: 0.7746264338493347:  69%|██████▉   | 17834/25880 [3:38:46<1:34:18,  1.42it/s]
1|17835|Loss: 0.7746264338493347:  69%|██████▉   | 17835/25880 [3:38:47<1:33:26,  1.43it/s]
1|17836|Loss: 0.7189236879348755:  69%|██████▉   | 17835/25880 [3:38:47<1:33:26,  1.43it/s]
1|17836|Loss: 0.7189236879348755:  69%|██████▉   | 17836/25880 [3:38:48<1:34:12,  1.42it/s]
1|17837|Loss: 0.6609221696853638:  69%|██████▉   | 17836/25880 [3:38:48<1:34:12,  1.42it/s]
1|17837|Loss: 0.6609221696853638:  69%|██████▉   | 17837/25880 [3:38:49<1:47:07,  1.25it/s]
1|17838|Loss: 0.8876110911369324:  69%|██████▉   | 17837/25880 [3:38:49<1:47:07,  1.25it/s]
1|17838|Loss: 0.8876110911369324:  69%|██████▉   | 17838/25880 [3:38:49<1:47:59,  1.24it/s]
1|17839|Loss: 0.9121996164321899:  69%|██████▉   | 17838/25880 [3:38:50<1:47:59,  1.24it/s]
1|17839|Loss: 0.9121996164321899:  69%|██████▉   | 17839/25880 [3:38:50<1:40:11,  1.34it/s]
1|17840|Loss: 0.784412145614624:  69%|██████▉   | 17839/25880 [3:38:50<1:40:11,  1.34it/s] 
1|17840|Loss: 0.784412145614624:  69%|██████▉   | 17840/25880 [3:38:51<1:38:30,  1.36it/s]
1|17841|Loss: 0.9320195913314819:  69%|██████▉   | 17840/25880 [3:38:51<1:38:30,  1.36it/s]
1|17841|Loss: 0.9320195913314819:  69%|██████▉   | 17841/25880 [3:38:51<1:41:42,  1.32it/s]
1|17842|Loss: 1.0079538822174072:  69%|██████▉   | 17841/25880 [3:38:52<1:41:42,  1.32it/s]
1|17842|Loss: 1.0079538822174072:  69%|██████▉   | 17842/25880 [3:38:52<1:40:18,  1.34it/s]
1|17843|Loss: 0.814255952835083:  69%|██████▉   | 17842/25880 [3:38:53<1:40:18,  1.34it/s] 
1|17843|Loss: 0.814255952835083:  69%|██████▉   | 17843/25880 [3:38:53<1:43:15,  1.30it/s]
1|17844|Loss: 0.7975704669952393:  69%|██████▉   | 17843/25880 [3:38:54<1:43:15,  1.30it/s]
1|17844|Loss: 0.7975704669952393:  69%|██████▉   | 17844/25880 [3:38:54<1:46:45,  1.25it/s]
1|17845|Loss: 0.9132922291755676:  69%|██████▉   | 17844/25880 [3:38:54<1:46:45,  1.25it/s]
1|17845|Loss: 0.9132922291755676:  69%|██████▉   | 17845/25880 [3:38:55<1:41:41,  1.32it/s]
1|17846|Loss: 0.8547890782356262:  69%|██████▉   | 17845/25880 [3:38:55<1:41:41,  1.32it/s]
1|17846|Loss: 0.8547890782356262:  69%|██████▉   | 17846/25880 [3:38:55<1:35:54,  1.40it/s]
1|17847|Loss: 0.7277810573577881:  69%|██████▉   | 17846/25880 [3:38:56<1:35:54,  1.40it/s]
1|17847|Loss: 0.7277810573577881:  69%|██████▉   | 17847/25880 [3:38:56<1:34:42,  1.41it/s]
1|17848|Loss: 0.8291755318641663:  69%|██████▉   | 17847/25880 [3:38:56<1:34:42,  1.41it/s]
1|17848|Loss: 0.8291755318641663:  69%|██████▉   | 17848/25880 [3:38:56<1:26:16,  1.55it/s]
1|17849|Loss: 0.7966523170471191:  69%|██████▉   | 17848/25880 [3:38:57<1:26:16,  1.55it/s]
1|17849|Loss: 0.7966523170471191:  69%|██████▉   | 17849/25880 [3:38:57<1:30:40,  1.48it/s]
1|17850|Loss: 0.8479541540145874:  69%|██████▉   | 17849/25880 [3:38:58<1:30:40,  1.48it/s]
1|17850|Loss: 0.8479541540145874:  69%|██████▉   | 17850/25880 [3:38:58<1:36:46,  1.38it/s]
1|17851|Loss: 0.837638258934021:  69%|██████▉   | 17850/25880 [3:38:58<1:36:46,  1.38it/s] 
1|17851|Loss: 0.837638258934021:  69%|██████▉   | 17851/25880 [3:38:59<1:34:54,  1.41it/s]
1|17852|Loss: 0.8843106627464294:  69%|██████▉   | 17851/25880 [3:38:59<1:34:54,  1.41it/s]
1|17852|Loss: 0.8843106627464294:  69%|██████▉   | 17852/25880 [3:38:59<1:32:09,  1.45it/s]
1|17853|Loss: 0.8792432546615601:  69%|██████▉   | 17852/25880 [3:39:00<1:32:09,  1.45it/s]
1|17853|Loss: 0.8792432546615601:  69%|██████▉   | 17853/25880 [3:39:00<1:36:26,  1.39it/s]
1|17854|Loss: 1.0539320707321167:  69%|██████▉   | 17853/25880 [3:39:01<1:36:26,  1.39it/s]
1|17854|Loss: 1.0539320707321167:  69%|██████▉   | 17854/25880 [3:39:01<1:39:24,  1.35it/s]
1|17855|Loss: 0.9095975756645203:  69%|██████▉   | 17854/25880 [3:39:01<1:39:24,  1.35it/s]
1|17855|Loss: 0.9095975756645203:  69%|██████▉   | 17855/25880 [3:39:02<1:39:52,  1.34it/s]
1|17856|Loss: 0.9098768830299377:  69%|██████▉   | 17855/25880 [3:39:02<1:39:52,  1.34it/s]
1|17856|Loss: 0.9098768830299377:  69%|██████▉   | 17856/25880 [3:39:02<1:35:34,  1.40it/s]
1|17857|Loss: 0.8514081835746765:  69%|██████▉   | 17856/25880 [3:39:03<1:35:34,  1.40it/s]
1|17857|Loss: 0.8514081835746765:  69%|██████▉   | 17857/25880 [3:39:03<1:39:31,  1.34it/s]
1|17858|Loss: 0.7731358408927917:  69%|██████▉   | 17857/25880 [3:39:03<1:39:31,  1.34it/s]
1|17858|Loss: 0.7731358408927917:  69%|██████▉   | 17858/25880 [3:39:04<1:37:26,  1.37it/s]
1|17859|Loss: 0.9137111306190491:  69%|██████▉   | 17858/25880 [3:39:04<1:37:26,  1.37it/s]
1|17859|Loss: 0.9137111306190491:  69%|██████▉   | 17859/25880 [3:39:04<1:35:55,  1.39it/s]
1|17860|Loss: 0.9573113918304443:  69%|██████▉   | 17859/25880 [3:39:05<1:35:55,  1.39it/s]
1|17860|Loss: 0.9573113918304443:  69%|██████▉   | 17860/25880 [3:39:05<1:39:11,  1.35it/s]
1|17861|Loss: 0.8907395601272583:  69%|██████▉   | 17860/25880 [3:39:06<1:39:11,  1.35it/s]
1|17861|Loss: 0.8907395601272583:  69%|██████▉   | 17861/25880 [3:39:06<1:36:21,  1.39it/s]
1|17862|Loss: 0.7811450362205505:  69%|██████▉   | 17861/25880 [3:39:06<1:36:21,  1.39it/s]
1|17862|Loss: 0.7811450362205505:  69%|██████▉   | 17862/25880 [3:39:07<1:36:03,  1.39it/s]
1|17863|Loss: 0.7885425090789795:  69%|██████▉   | 17862/25880 [3:39:07<1:36:03,  1.39it/s]
1|17863|Loss: 0.7885425090789795:  69%|██████▉   | 17863/25880 [3:39:07<1:33:24,  1.43it/s]
1|17864|Loss: 0.8559497594833374:  69%|██████▉   | 17863/25880 [3:39:08<1:33:24,  1.43it/s]
1|17864|Loss: 0.8559497594833374:  69%|██████▉   | 17864/25880 [3:39:08<1:34:04,  1.42it/s]
1|17865|Loss: 0.7270427346229553:  69%|██████▉   | 17864/25880 [3:39:08<1:34:04,  1.42it/s]
1|17865|Loss: 0.7270427346229553:  69%|██████▉   | 17865/25880 [3:39:09<1:30:13,  1.48it/s]
1|17866|Loss: 0.76209956407547:  69%|██████▉   | 17865/25880 [3:39:09<1:30:13,  1.48it/s]  
1|17866|Loss: 0.76209956407547:  69%|██████▉   | 17866/25880 [3:39:09<1:34:34,  1.41it/s]
1|17867|Loss: 0.9245350360870361:  69%|██████▉   | 17866/25880 [3:39:10<1:34:34,  1.41it/s]
1|17867|Loss: 0.9245350360870361:  69%|██████▉   | 17867/25880 [3:39:10<1:32:28,  1.44it/s]
1|17868|Loss: 0.8742474913597107:  69%|██████▉   | 17867/25880 [3:39:10<1:32:28,  1.44it/s]
1|17868|Loss: 0.8742474913597107:  69%|██████▉   | 17868/25880 [3:39:11<1:32:12,  1.45it/s]
1|17869|Loss: 0.8500677347183228:  69%|██████▉   | 17868/25880 [3:39:11<1:32:12,  1.45it/s]
1|17869|Loss: 0.8500677347183228:  69%|██████▉   | 17869/25880 [3:39:11<1:28:37,  1.51it/s]
1|17870|Loss: 0.7128701210021973:  69%|██████▉   | 17869/25880 [3:39:12<1:28:37,  1.51it/s]
1|17870|Loss: 0.7128701210021973:  69%|██████▉   | 17870/25880 [3:39:12<1:26:26,  1.54it/s]
1|17871|Loss: 0.9255995154380798:  69%|██████▉   | 17870/25880 [3:39:12<1:26:26,  1.54it/s]
1|17871|Loss: 0.9255995154380798:  69%|██████▉   | 17871/25880 [3:39:13<1:29:10,  1.50it/s]
1|17872|Loss: 0.8660252094268799:  69%|██████▉   | 17871/25880 [3:39:13<1:29:10,  1.50it/s]
1|17872|Loss: 0.8660252094268799:  69%|██████▉   | 17872/25880 [3:39:13<1:27:53,  1.52it/s]
1|17873|Loss: 0.752993106842041:  69%|██████▉   | 17872/25880 [3:39:14<1:27:53,  1.52it/s] 
1|17873|Loss: 0.752993106842041:  69%|██████▉   | 17873/25880 [3:39:14<1:29:14,  1.50it/s]
1|17874|Loss: 0.7617048621177673:  69%|██████▉   | 17873/25880 [3:39:14<1:29:14,  1.50it/s]
1|17874|Loss: 0.7617048621177673:  69%|██████▉   | 17874/25880 [3:39:15<1:36:05,  1.39it/s]
1|17875|Loss: 0.7620258331298828:  69%|██████▉   | 17874/25880 [3:39:15<1:36:05,  1.39it/s]
1|17875|Loss: 0.7620258331298828:  69%|██████▉   | 17875/25880 [3:39:16<1:36:57,  1.38it/s]
1|17876|Loss: 0.8020894527435303:  69%|██████▉   | 17875/25880 [3:39:16<1:36:57,  1.38it/s]
1|17876|Loss: 0.8020894527435303:  69%|██████▉   | 17876/25880 [3:39:16<1:37:15,  1.37it/s]
1|17877|Loss: 0.7486381530761719:  69%|██████▉   | 17876/25880 [3:39:17<1:37:15,  1.37it/s]
1|17877|Loss: 0.7486381530761719:  69%|██████▉   | 17877/25880 [3:39:17<1:32:36,  1.44it/s]
1|17878|Loss: 0.8592612743377686:  69%|██████▉   | 17877/25880 [3:39:17<1:32:36,  1.44it/s]
1|17878|Loss: 0.8592612743377686:  69%|██████▉   | 17878/25880 [3:39:18<1:35:45,  1.39it/s]
1|17879|Loss: 0.8108730316162109:  69%|██████▉   | 17878/25880 [3:39:18<1:35:45,  1.39it/s]
1|17879|Loss: 0.8108730316162109:  69%|██████▉   | 17879/25880 [3:39:18<1:32:09,  1.45it/s]
1|17880|Loss: 0.8399285674095154:  69%|██████▉   | 17879/25880 [3:39:19<1:32:09,  1.45it/s]
1|17880|Loss: 0.8399285674095154:  69%|██████▉   | 17880/25880 [3:39:19<1:32:44,  1.44it/s]
1|17881|Loss: 0.8472930788993835:  69%|██████▉   | 17880/25880 [3:39:19<1:32:44,  1.44it/s]
1|17881|Loss: 0.8472930788993835:  69%|██████▉   | 17881/25880 [3:39:20<1:30:01,  1.48it/s]
1|17882|Loss: 0.7566408514976501:  69%|██████▉   | 17881/25880 [3:39:20<1:30:01,  1.48it/s]
1|17882|Loss: 0.7566408514976501:  69%|██████▉   | 17882/25880 [3:39:20<1:26:37,  1.54it/s]
1|17883|Loss: 0.8144211173057556:  69%|██████▉   | 17882/25880 [3:39:21<1:26:37,  1.54it/s]
1|17883|Loss: 0.8144211173057556:  69%|██████▉   | 17883/25880 [3:39:21<1:27:38,  1.52it/s]
1|17884|Loss: 0.7281896471977234:  69%|██████▉   | 17883/25880 [3:39:21<1:27:38,  1.52it/s]
1|17884|Loss: 0.7281896471977234:  69%|██████▉   | 17884/25880 [3:39:22<1:33:18,  1.43it/s]
1|17885|Loss: 0.8351538777351379:  69%|██████▉   | 17884/25880 [3:39:22<1:33:18,  1.43it/s]
1|17885|Loss: 0.8351538777351379:  69%|██████▉   | 17885/25880 [3:39:23<1:36:50,  1.38it/s]
1|17886|Loss: 0.8536946773529053:  69%|██████▉   | 17885/25880 [3:39:23<1:36:50,  1.38it/s]
1|17886|Loss: 0.8536946773529053:  69%|██████▉   | 17886/25880 [3:39:23<1:37:54,  1.36it/s]
1|17887|Loss: 0.8362098336219788:  69%|██████▉   | 17886/25880 [3:39:24<1:37:54,  1.36it/s]
1|17887|Loss: 0.8362098336219788:  69%|██████▉   | 17887/25880 [3:39:24<1:35:09,  1.40it/s]
1|17888|Loss: 0.8164682984352112:  69%|██████▉   | 17887/25880 [3:39:24<1:35:09,  1.40it/s]
1|17888|Loss: 0.8164682984352112:  69%|██████▉   | 17888/25880 [3:39:25<1:41:14,  1.32it/s]
1|17889|Loss: 0.8368715643882751:  69%|██████▉   | 17888/25880 [3:39:25<1:41:14,  1.32it/s]
1|17889|Loss: 0.8368715643882751:  69%|██████▉   | 17889/25880 [3:39:26<1:40:40,  1.32it/s]
1|17890|Loss: 0.808477520942688:  69%|██████▉   | 17889/25880 [3:39:26<1:40:40,  1.32it/s] 
1|17890|Loss: 0.808477520942688:  69%|██████▉   | 17890/25880 [3:39:26<1:39:19,  1.34it/s]
1|17891|Loss: 0.8351840972900391:  69%|██████▉   | 17890/25880 [3:39:27<1:39:19,  1.34it/s]
1|17891|Loss: 0.8351840972900391:  69%|██████▉   | 17891/25880 [3:39:27<1:30:45,  1.47it/s]
1|17892|Loss: 0.8083423376083374:  69%|██████▉   | 17891/25880 [3:39:27<1:30:45,  1.47it/s]
1|17892|Loss: 0.8083423376083374:  69%|██████▉   | 17892/25880 [3:39:27<1:27:37,  1.52it/s]
1|17893|Loss: 0.6678073406219482:  69%|██████▉   | 17892/25880 [3:39:28<1:27:37,  1.52it/s]
1|17893|Loss: 0.6678073406219482:  69%|██████▉   | 17893/25880 [3:39:28<1:29:57,  1.48it/s]
1|17894|Loss: 0.7346561551094055:  69%|██████▉   | 17893/25880 [3:39:29<1:29:57,  1.48it/s]
1|17894|Loss: 0.7346561551094055:  69%|██████▉   | 17894/25880 [3:39:29<1:37:11,  1.37it/s]
1|17895|Loss: 0.8928970098495483:  69%|██████▉   | 17894/25880 [3:39:29<1:37:11,  1.37it/s]
1|17895|Loss: 0.8928970098495483:  69%|██████▉   | 17895/25880 [3:39:30<1:40:32,  1.32it/s]
1|17896|Loss: 0.815701425075531:  69%|██████▉   | 17895/25880 [3:39:30<1:40:32,  1.32it/s] 
1|17896|Loss: 0.815701425075531:  69%|██████▉   | 17896/25880 [3:39:30<1:36:17,  1.38it/s]
1|17897|Loss: 0.9897871017456055:  69%|██████▉   | 17896/25880 [3:39:31<1:36:17,  1.38it/s]
1|17897|Loss: 0.9897871017456055:  69%|██████▉   | 17897/25880 [3:39:31<1:35:48,  1.39it/s]
1|17898|Loss: 0.9239071011543274:  69%|██████▉   | 17897/25880 [3:39:32<1:35:48,  1.39it/s]
1|17898|Loss: 0.9239071011543274:  69%|██████▉   | 17898/25880 [3:39:32<1:36:28,  1.38it/s]
1|17899|Loss: 0.8822240829467773:  69%|██████▉   | 17898/25880 [3:39:32<1:36:28,  1.38it/s]
1|17899|Loss: 0.8822240829467773:  69%|██████▉   | 17899/25880 [3:39:33<1:37:32,  1.36it/s]
1|17900|Loss: 0.8891798853874207:  69%|██████▉   | 17899/25880 [3:39:33<1:37:32,  1.36it/s]
1|17900|Loss: 0.8891798853874207:  69%|██████▉   | 17900/25880 [3:39:33<1:31:20,  1.46it/s]
1|17901|Loss: 0.7839363813400269:  69%|██████▉   | 17900/25880 [3:39:34<1:31:20,  1.46it/s]
1|17901|Loss: 0.7839363813400269:  69%|██████▉   | 17901/25880 [3:39:34<1:28:32,  1.50it/s]
1|17902|Loss: 0.8818303346633911:  69%|██████▉   | 17901/25880 [3:39:34<1:28:32,  1.50it/s]
1|17902|Loss: 0.8818303346633911:  69%|██████▉   | 17902/25880 [3:39:35<1:32:46,  1.43it/s]
1|17903|Loss: 0.8866812586784363:  69%|██████▉   | 17902/25880 [3:39:35<1:32:46,  1.43it/s]
1|17903|Loss: 0.8866812586784363:  69%|██████▉   | 17903/25880 [3:39:35<1:28:14,  1.51it/s]
1|17904|Loss: 0.8042086958885193:  69%|██████▉   | 17903/25880 [3:39:36<1:28:14,  1.51it/s]
1|17904|Loss: 0.8042086958885193:  69%|██████▉   | 17904/25880 [3:39:36<1:29:17,  1.49it/s]
1|17905|Loss: 0.9377089142799377:  69%|██████▉   | 17904/25880 [3:39:36<1:29:17,  1.49it/s]
1|17905|Loss: 0.9377089142799377:  69%|██████▉   | 17905/25880 [3:39:36<1:22:46,  1.61it/s]
1|17906|Loss: 0.8261559009552002:  69%|██████▉   | 17905/25880 [3:39:37<1:22:46,  1.61it/s]
1|17906|Loss: 0.8261559009552002:  69%|██████▉   | 17906/25880 [3:39:37<1:29:10,  1.49it/s]
1|17907|Loss: 0.9669197797775269:  69%|██████▉   | 17906/25880 [3:39:38<1:29:10,  1.49it/s]
1|17907|Loss: 0.9669197797775269:  69%|██████▉   | 17907/25880 [3:39:38<1:37:39,  1.36it/s]
1|17908|Loss: 0.7430288195610046:  69%|██████▉   | 17907/25880 [3:39:38<1:37:39,  1.36it/s]
1|17908|Loss: 0.7430288195610046:  69%|██████▉   | 17908/25880 [3:39:39<1:30:01,  1.48it/s]
1|17909|Loss: 0.9197484254837036:  69%|██████▉   | 17908/25880 [3:39:39<1:30:01,  1.48it/s]
1|17909|Loss: 0.9197484254837036:  69%|██████▉   | 17909/25880 [3:39:39<1:26:44,  1.53it/s]
1|17910|Loss: 0.8237473368644714:  69%|██████▉   | 17909/25880 [3:39:40<1:26:44,  1.53it/s]
1|17910|Loss: 0.8237473368644714:  69%|██████▉   | 17910/25880 [3:39:40<1:32:35,  1.43it/s]
1|17911|Loss: 0.7732709050178528:  69%|██████▉   | 17910/25880 [3:39:40<1:32:35,  1.43it/s]
1|17911|Loss: 0.7732709050178528:  69%|██████▉   | 17911/25880 [3:39:41<1:31:45,  1.45it/s]
1|17912|Loss: 0.8500459790229797:  69%|██████▉   | 17911/25880 [3:39:41<1:31:45,  1.45it/s]
1|17912|Loss: 0.8500459790229797:  69%|██████▉   | 17912/25880 [3:39:41<1:32:46,  1.43it/s]
1|17913|Loss: 0.8578233122825623:  69%|██████▉   | 17912/25880 [3:39:42<1:32:46,  1.43it/s]
1|17913|Loss: 0.8578233122825623:  69%|██████▉   | 17913/25880 [3:39:42<1:31:21,  1.45it/s]
1|17914|Loss: 0.8137514591217041:  69%|██████▉   | 17913/25880 [3:39:43<1:31:21,  1.45it/s]
1|17914|Loss: 0.8137514591217041:  69%|██████▉   | 17914/25880 [3:39:43<1:39:45,  1.33it/s]
1|17915|Loss: 0.7911811470985413:  69%|██████▉   | 17914/25880 [3:39:43<1:39:45,  1.33it/s]
1|17915|Loss: 0.7911811470985413:  69%|██████▉   | 17915/25880 [3:39:44<1:35:08,  1.40it/s]
1|17916|Loss: 0.7498081922531128:  69%|██████▉   | 17915/25880 [3:39:44<1:35:08,  1.40it/s]
1|17916|Loss: 0.7498081922531128:  69%|██████▉   | 17916/25880 [3:39:44<1:38:09,  1.35it/s]
1|17917|Loss: 0.8806180953979492:  69%|██████▉   | 17916/25880 [3:39:45<1:38:09,  1.35it/s]
1|17917|Loss: 0.8806180953979492:  69%|██████▉   | 17917/25880 [3:39:45<1:38:06,  1.35it/s]
1|17918|Loss: 0.79097580909729:  69%|██████▉   | 17917/25880 [3:39:45<1:38:06,  1.35it/s]  
1|17918|Loss: 0.79097580909729:  69%|██████▉   | 17918/25880 [3:39:46<1:34:29,  1.40it/s]
1|17919|Loss: 0.8226998448371887:  69%|██████▉   | 17918/25880 [3:39:46<1:34:29,  1.40it/s]
1|17919|Loss: 0.8226998448371887:  69%|██████▉   | 17919/25880 [3:39:47<1:40:32,  1.32it/s]
1|17920|Loss: 0.9033096432685852:  69%|██████▉   | 17919/25880 [3:39:47<1:40:32,  1.32it/s]
1|17920|Loss: 0.9033096432685852:  69%|██████▉   | 17920/25880 [3:39:47<1:38:14,  1.35it/s]
1|17921|Loss: 0.9139410853385925:  69%|██████▉   | 17920/25880 [3:39:48<1:38:14,  1.35it/s]
1|17921|Loss: 0.9139410853385925:  69%|██████▉   | 17921/25880 [3:39:48<1:37:30,  1.36it/s]
1|17922|Loss: 0.8010489344596863:  69%|██████▉   | 17921/25880 [3:39:48<1:37:30,  1.36it/s]
1|17922|Loss: 0.8010489344596863:  69%|██████▉   | 17922/25880 [3:39:49<1:37:55,  1.35it/s]
1|17923|Loss: 0.9633737802505493:  69%|██████▉   | 17922/25880 [3:39:49<1:37:55,  1.35it/s]
1|17923|Loss: 0.9633737802505493:  69%|██████▉   | 17923/25880 [3:39:49<1:30:53,  1.46it/s]
1|17924|Loss: 0.8497501015663147:  69%|██████▉   | 17923/25880 [3:39:50<1:30:53,  1.46it/s]
1|17924|Loss: 0.8497501015663147:  69%|██████▉   | 17924/25880 [3:39:50<1:33:14,  1.42it/s]
1|17925|Loss: 0.7764449715614319:  69%|██████▉   | 17924/25880 [3:39:51<1:33:14,  1.42it/s]
1|17925|Loss: 0.7764449715614319:  69%|██████▉   | 17925/25880 [3:39:51<1:38:19,  1.35it/s]
1|17926|Loss: 0.8148621320724487:  69%|██████▉   | 17925/25880 [3:39:51<1:38:19,  1.35it/s]
1|17926|Loss: 0.8148621320724487:  69%|██████▉   | 17926/25880 [3:39:52<1:31:58,  1.44it/s]
1|17927|Loss: 0.8676441311836243:  69%|██████▉   | 17926/25880 [3:39:52<1:31:58,  1.44it/s]
1|17927|Loss: 0.8676441311836243:  69%|██████▉   | 17927/25880 [3:39:52<1:33:17,  1.42it/s]
1|17928|Loss: 0.6781734228134155:  69%|██████▉   | 17927/25880 [3:39:53<1:33:17,  1.42it/s]
1|17928|Loss: 0.6781734228134155:  69%|██████��   | 17928/25880 [3:39:53<1:35:09,  1.39it/s]
1|17929|Loss: 0.8656507730484009:  69%|██████▉   | 17928/25880 [3:39:53<1:35:09,  1.39it/s]
1|17929|Loss: 0.8656507730484009:  69%|██████▉   | 17929/25880 [3:39:54<1:36:13,  1.38it/s]
1|17930|Loss: 0.7756099104881287:  69%|██████▉   | 17929/25880 [3:39:54<1:36:13,  1.38it/s]
1|17930|Loss: 0.7756099104881287:  69%|██████▉   | 17930/25880 [3:39:54<1:33:04,  1.42it/s]
1|17931|Loss: 0.8830999732017517:  69%|██████▉   | 17930/25880 [3:39:55<1:33:04,  1.42it/s]
1|17931|Loss: 0.8830999732017517:  69%|██████▉   | 17931/25880 [3:39:55<1:33:20,  1.42it/s]
1|17932|Loss: 0.8151080012321472:  69%|██████▉   | 17931/25880 [3:39:55<1:33:20,  1.42it/s]
1|17932|Loss: 0.8151080012321472:  69%|██████▉   | 17932/25880 [3:39:56<1:30:38,  1.46it/s]
1|17933|Loss: 0.9812216758728027:  69%|██████▉   | 17932/25880 [3:39:56<1:30:38,  1.46it/s]
1|17933|Loss: 0.9812216758728027:  69%|██████▉   | 17933/25880 [3:39:56<1:30:31,  1.46it/s]
1|17934|Loss: 0.9656333923339844:  69%|██████▉   | 17933/25880 [3:39:57<1:30:31,  1.46it/s]
1|17934|Loss: 0.9656333923339844:  69%|██████▉   | 17934/25880 [3:39:57<1:29:16,  1.48it/s]
1|17935|Loss: 0.7682594656944275:  69%|██████▉   | 17934/25880 [3:39:57<1:29:16,  1.48it/s]
1|17935|Loss: 0.7682594656944275:  69%|██████▉   | 17935/25880 [3:39:58<1:33:59,  1.41it/s]
1|17936|Loss: 0.8994805216789246:  69%|██████▉   | 17935/25880 [3:39:58<1:33:59,  1.41it/s]
1|17936|Loss: 0.8994805216789246:  69%|██████▉   | 17936/25880 [3:39:59<1:41:15,  1.31it/s]
1|17937|Loss: 0.881456196308136:  69%|██████▉   | 17936/25880 [3:39:59<1:41:15,  1.31it/s] 
1|17937|Loss: 0.881456196308136:  69%|██████▉   | 17937/25880 [3:40:00<1:46:07,  1.25it/s]
1|17938|Loss: 0.8380090594291687:  69%|██████▉   | 17937/25880 [3:40:00<1:46:07,  1.25it/s]
1|17938|Loss: 0.8380090594291687:  69%|██████▉   | 17938/25880 [3:40:01<1:47:56,  1.23it/s]
1|17939|Loss: 0.740013062953949:  69%|██████▉   | 17938/25880 [3:40:01<1:47:56,  1.23it/s] 
1|17939|Loss: 0.740013062953949:  69%|██████▉   | 17939/25880 [3:40:01<1:44:38,  1.26it/s]
1|17940|Loss: 0.6555047035217285:  69%|██████▉   | 17939/25880 [3:40:02<1:44:38,  1.26it/s]
1|17940|Loss: 0.6555047035217285:  69%|██████▉   | 17940/25880 [3:40:02<1:47:39,  1.23it/s]
1|17941|Loss: 0.9523077011108398:  69%|██████▉   | 17940/25880 [3:40:03<1:47:39,  1.23it/s]
1|17941|Loss: 0.9523077011108398:  69%|██████▉   | 17941/25880 [3:40:03<1:44:50,  1.26it/s]
1|17942|Loss: 0.812807559967041:  69%|██████▉   | 17941/25880 [3:40:03<1:44:50,  1.26it/s] 
1|17942|Loss: 0.812807559967041:  69%|██████▉   | 17942/25880 [3:40:03<1:36:28,  1.37it/s]
1|17943|Loss: 0.8604602217674255:  69%|██████▉   | 17942/25880 [3:40:04<1:36:28,  1.37it/s]
1|17943|Loss: 0.8604602217674255:  69%|██████▉   | 17943/25880 [3:40:04<1:31:24,  1.45it/s]
1|17944|Loss: 0.959057092666626:  69%|██████▉   | 17943/25880 [3:40:04<1:31:24,  1.45it/s] 
1|17944|Loss: 0.959057092666626:  69%|██████▉   | 17944/25880 [3:40:05<1:31:04,  1.45it/s]
1|17945|Loss: 0.841325581073761:  69%|██████▉   | 17944/25880 [3:40:05<1:31:04,  1.45it/s]
1|17945|Loss: 0.841325581073761:  69%|██████▉   | 17945/25880 [3:40:05<1:29:34,  1.48it/s]
1|17946|Loss: 0.8477613925933838:  69%|██████▉   | 17945/25880 [3:40:06<1:29:34,  1.48it/s]
1|17946|Loss: 0.8477613925933838:  69%|██████▉   | 17946/25880 [3:40:06<1:30:56,  1.45it/s]
1|17947|Loss: 0.9255382418632507:  69%|██████▉   | 17946/25880 [3:40:06<1:30:56,  1.45it/s]
1|17947|Loss: 0.9255382418632507:  69%|██████▉   | 17947/25880 [3:40:07<1:33:04,  1.42it/s]
1|17948|Loss: 0.7526830434799194:  69%|██████▉   | 17947/25880 [3:40:07<1:33:04,  1.42it/s]
1|17948|Loss: 0.7526830434799194:  69%|██████▉   | 17948/25880 [3:40:08<1:37:16,  1.36it/s]
1|17949|Loss: 0.8819352388381958:  69%|██████▉   | 17948/25880 [3:40:08<1:37:16,  1.36it/s]
1|17949|Loss: 0.8819352388381958:  69%|██████▉   | 17949/25880 [3:40:08<1:37:55,  1.35it/s]
1|17950|Loss: 0.8875988721847534:  69%|██████▉   | 17949/25880 [3:40:09<1:37:55,  1.35it/s]
1|17950|Loss: 0.8875988721847534:  69%|██████▉   | 17950/25880 [3:40:09<1:34:58,  1.39it/s]
1|17951|Loss: 0.9740898013114929:  69%|██████▉   | 17950/25880 [3:40:09<1:34:58,  1.39it/s]
1|17951|Loss: 0.9740898013114929:  69%|██████▉   | 17951/25880 [3:40:10<1:31:51,  1.44it/s]
1|17952|Loss: 0.9583442211151123:  69%|██████▉   | 17951/25880 [3:40:10<1:31:51,  1.44it/s]
1|17952|Loss: 0.9583442211151123:  69%|██████▉   | 17952/25880 [3:40:10<1:36:29,  1.37it/s]
1|17953|Loss: 0.7226895093917847:  69%|██████▉   | 17952/25880 [3:40:11<1:36:29,  1.37it/s]
1|17953|Loss: 0.7226895093917847:  69%|██████▉   | 17953/25880 [3:40:12<1:50:40,  1.19it/s]
1|17954|Loss: 0.8024375438690186:  69%|██████▉   | 17953/25880 [3:40:12<1:50:40,  1.19it/s]
1|17954|Loss: 0.8024375438690186:  69%|██████▉   | 17954/25880 [3:40:12<1:46:05,  1.25it/s]
1|17955|Loss: 0.8365702033042908:  69%|██████▉   | 17954/25880 [3:40:13<1:46:05,  1.25it/s]
1|17955|Loss: 0.8365702033042908:  69%|██████▉   | 17955/25880 [3:40:13<1:47:11,  1.23it/s]
1|17956|Loss: 0.7403460741043091:  69%|██████▉   | 17955/25880 [3:40:13<1:47:11,  1.23it/s]
1|17956|Loss: 0.7403460741043091:  69%|██████▉   | 17956/25880 [3:40:14<1:34:23,  1.40it/s]
1|17957|Loss: 0.8161038756370544:  69%|██████▉   | 17956/25880 [3:40:14<1:34:23,  1.40it/s]
1|17957|Loss: 0.8161038756370544:  69%|██████▉   | 17957/25880 [3:40:14<1:36:51,  1.36it/s]
1|17958|Loss: 0.8668930530548096:  69%|██████▉   | 17957/25880 [3:40:15<1:36:51,  1.36it/s]
1|17958|Loss: 0.8668930530548096:  69%|██████▉   | 17958/25880 [3:40:15<1:42:25,  1.29it/s]
1|17959|Loss: 0.8529037833213806:  69%|██████▉   | 17958/25880 [3:40:16<1:42:25,  1.29it/s]
1|17959|Loss: 0.8529037833213806:  69%|██████▉   | 17959/25880 [3:40:16<1:42:02,  1.29it/s]
1|17960|Loss: 0.6469275951385498:  69%|██████▉   | 17959/25880 [3:40:16<1:42:02,  1.29it/s]
1|17960|Loss: 0.6469275951385498:  69%|██████▉   | 17960/25880 [3:40:17<1:40:34,  1.31it/s]
1|17961|Loss: 0.878928005695343:  69%|██████▉   | 17960/25880 [3:40:17<1:40:34,  1.31it/s] 
1|17961|Loss: 0.878928005695343:  69%|██████▉   | 17961/25880 [3:40:18<1:41:09,  1.30it/s]
1|17962|Loss: 0.8099422454833984:  69%|██████▉   | 17961/25880 [3:40:18<1:41:09,  1.30it/s]
1|17962|Loss: 0.8099422454833984:  69%|██████▉   | 17962/25880 [3:40:18<1:39:27,  1.33it/s]
1|17963|Loss: 0.7434123158454895:  69%|██████▉   | 17962/25880 [3:40:19<1:39:27,  1.33it/s]
1|17963|Loss: 0.7434123158454895:  69%|██████▉   | 17963/25880 [3:40:19<1:37:17,  1.36it/s]
1|17964|Loss: 0.9964631795883179:  69%|██████▉   | 17963/25880 [3:40:19<1:37:17,  1.36it/s]
1|17964|Loss: 0.9964631795883179:  69%|██████▉   | 17964/25880 [3:40:20<1:35:28,  1.38it/s]
1|17965|Loss: 0.9192055463790894:  69%|██████▉   | 17964/25880 [3:40:20<1:35:28,  1.38it/s]
1|17965|Loss: 0.9192055463790894:  69%|██████▉   | 17965/25880 [3:40:20<1:39:10,  1.33it/s]
1|17966|Loss: 0.7726143002510071:  69%|██████▉   | 17965/25880 [3:40:21<1:39:10,  1.33it/s]
1|17966|Loss: 0.7726143002510071:  69%|██████▉   | 17966/25880 [3:40:21<1:36:39,  1.36it/s]
1|17967|Loss: 0.7414866089820862:  69%|██████▉   | 17966/25880 [3:40:22<1:36:39,  1.36it/s]
1|17967|Loss: 0.7414866089820862:  69%|██████▉   | 17967/25880 [3:40:22<1:35:39,  1.38it/s]
1|17968|Loss: 0.6998068690299988:  69%|██████▉   | 17967/25880 [3:40:22<1:35:39,  1.38it/s]
1|17968|Loss: 0.6998068690299988:  69%|██████▉   | 17968/25880 [3:40:23<1:38:57,  1.33it/s]
1|17969|Loss: 0.8394904136657715:  69%|██████▉   | 17968/25880 [3:40:23<1:38:57,  1.33it/s]
1|17969|Loss: 0.8394904136657715:  69%|██████▉   | 17969/25880 [3:40:23<1:39:09,  1.33it/s]
1|17970|Loss: 1.1527382135391235:  69%|██████▉   | 17969/25880 [3:40:24<1:39:09,  1.33it/s]
1|17970|Loss: 1.1527382135391235:  69%|██████▉   | 17970/25880 [3:40:24<1:45:39,  1.25it/s]
1|17971|Loss: 0.7687341570854187:  69%|██████▉   | 17970/25880 [3:40:25<1:45:39,  1.25it/s]
1|17971|Loss: 0.7687341570854187:  69%|██████▉   | 17971/25880 [3:40:25<1:44:33,  1.26it/s]
1|17972|Loss: 0.8719506859779358:  69%|██████▉   | 17971/25880 [3:40:26<1:44:33,  1.26it/s]
1|17972|Loss: 0.8719506859779358:  69%|██████▉   | 17972/25880 [3:40:26<1:42:25,  1.29it/s]
1|17973|Loss: 0.8435268402099609:  69%|██████▉   | 17972/25880 [3:40:26<1:42:25,  1.29it/s]
1|17973|Loss: 0.8435268402099609:  69%|██████▉   | 17973/25880 [3:40:27<1:46:52,  1.23it/s]
1|17974|Loss: 0.7992693781852722:  69%|██████▉   | 17973/25880 [3:40:27<1:46:52,  1.23it/s]
1|17974|Loss: 0.7992693781852722:  69%|██████▉   | 17974/25880 [3:40:28<1:47:35,  1.22it/s]
1|17975|Loss: 0.9184828400611877:  69%|██████▉   | 17974/25880 [3:40:28<1:47:35,  1.22it/s]
1|17975|Loss: 0.9184828400611877:  69%|██████▉   | 17975/25880 [3:40:28<1:47:35,  1.22it/s]
1|17976|Loss: 0.748144268989563:  69%|██████▉   | 17975/25880 [3:40:29<1:47:35,  1.22it/s] 
1|17976|Loss: 0.748144268989563:  69%|██████▉   | 17976/25880 [3:40:29<1:46:52,  1.23it/s]
1|17977|Loss: 0.8702626824378967:  69%|██████▉   | 17976/25880 [3:40:30<1:46:52,  1.23it/s]
1|17977|Loss: 0.8702626824378967:  69%|██████▉   | 17977/25880 [3:40:30<1:43:39,  1.27it/s]
1|17978|Loss: 0.71229487657547:  69%|██████▉   | 17977/25880 [3:40:30<1:43:39,  1.27it/s]  
1|17978|Loss: 0.71229487657547:  69%|██████▉   | 17978/25880 [3:40:31<1:40:53,  1.31it/s]
1|17979|Loss: 0.8566448092460632:  69%|██████▉   | 17978/25880 [3:40:31<1:40:53,  1.31it/s]
1|17979|Loss: 0.8566448092460632:  69%|██████▉   | 17979/25880 [3:40:31<1:35:42,  1.38it/s]
1|17980|Loss: 0.9104911088943481:  69%|██████▉   | 17979/25880 [3:40:32<1:35:42,  1.38it/s]
1|17980|Loss: 0.9104911088943481:  69%|██████▉   | 17980/25880 [3:40:32<1:38:23,  1.34it/s]
1|17981|Loss: 0.7441221475601196:  69%|██████▉   | 17980/25880 [3:40:33<1:38:23,  1.34it/s]
1|17981|Loss: 0.7441221475601196:  69%|██████▉   | 17981/25880 [3:40:33<1:41:36,  1.30it/s]
1|17982|Loss: 0.8720390200614929:  69%|██████▉   | 17981/25880 [3:40:33<1:41:36,  1.30it/s]
1|17982|Loss: 0.8720390200614929:  69%|██████▉   | 17982/25880 [3:40:34<1:35:51,  1.37it/s]
1|17983|Loss: 0.9177947044372559:  69%|██████▉   | 17982/25880 [3:40:34<1:35:51,  1.37it/s]
1|17983|Loss: 0.9177947044372559:  69%|██████▉   | 17983/25880 [3:40:34<1:36:34,  1.36it/s]
1|17984|Loss: 0.8580641150474548:  69%|██████▉   | 17983/25880 [3:40:35<1:36:34,  1.36it/s]
1|17984|Loss: 0.8580641150474548:  69%|██████▉   | 17984/25880 [3:40:35<1:36:09,  1.37it/s]
1|17985|Loss: 0.9599064588546753:  69%|██████▉   | 17984/25880 [3:40:35<1:36:09,  1.37it/s]
1|17985|Loss: 0.9599064588546753:  69%|██████▉   | 17985/25880 [3:40:36<1:32:04,  1.43it/s]
1|17986|Loss: 0.9052042961120605:  69%|██████▉   | 17985/25880 [3:40:36<1:32:04,  1.43it/s]
1|17986|Loss: 0.9052042961120605:  69%|██████▉   | 17986/25880 [3:40:36<1:32:40,  1.42it/s]
1|17987|Loss: 1.0135774612426758:  69%|██████▉   | 17986/25880 [3:40:37<1:32:40,  1.42it/s]
1|17987|Loss: 1.0135774612426758:  70%|██████▉   | 17987/25880 [3:40:37<1:39:54,  1.32it/s]
1|17988|Loss: 0.9667882919311523:  70%|██████▉   | 17987/25880 [3:40:38<1:39:54,  1.32it/s]
1|17988|Loss: 0.9667882919311523:  70%|██████▉   | 17988/25880 [3:40:38<1:34:46,  1.39it/s]
1|17989|Loss: 0.8809796571731567:  70%|██████▉   | 17988/25880 [3:40:38<1:34:46,  1.39it/s]
1|17989|Loss: 0.8809796571731567:  70%|██████▉   | 17989/25880 [3:40:39<1:30:40,  1.45it/s]
1|17990|Loss: 0.8548271059989929:  70%|██████▉   | 17989/25880 [3:40:39<1:30:40,  1.45it/s]
1|17990|Loss: 0.8548271059989929:  70%|██████▉   | 17990/25880 [3:40:39<1:32:15,  1.43it/s]
1|17991|Loss: 0.8142662644386292:  70%|██████▉   | 17990/25880 [3:40:40<1:32:15,  1.43it/s]
1|17991|Loss: 0.8142662644386292:  70%|██████▉   | 17991/25880 [3:40:40<1:34:10,  1.40it/s]
1|17992|Loss: 0.6827909350395203:  70%|██████▉   | 17991/25880 [3:40:40<1:34:10,  1.40it/s]
1|17992|Loss: 0.6827909350395203:  70%|██████▉   | 17992/25880 [3:40:41<1:34:49,  1.39it/s]
1|17993|Loss: 0.7535420656204224:  70%|██████▉   | 17992/25880 [3:40:41<1:34:49,  1.39it/s]
1|17993|Loss: 0.7535420656204224:  70%|██████▉   | 17993/25880 [3:40:41<1:35:11,  1.38it/s]
1|17994|Loss: 0.8803382515907288:  70%|██████▉   | 17993/25880 [3:40:42<1:35:11,  1.38it/s]
1|17994|Loss: 0.8803382515907288:  70%|██████▉   | 17994/25880 [3:40:42<1:41:44,  1.29it/s]
1|17995|Loss: 0.9595878720283508:  70%|██████▉   | 17994/25880 [3:40:43<1:41:44,  1.29it/s]
1|17995|Loss: 0.9595878720283508:  70%|██████▉   | 17995/25880 [3:40:43<1:36:38,  1.36it/s]
1|17996|Loss: 0.8736022114753723:  70%|██████▉   | 17995/25880 [3:40:43<1:36:38,  1.36it/s]
1|17996|Loss: 0.8736022114753723:  70%|██████▉   | 17996/25880 [3:40:44<1:35:06,  1.38it/s]
1|17997|Loss: 0.8656925559043884:  70%|██████▉   | 17996/25880 [3:40:44<1:35:06,  1.38it/s]
1|17997|Loss: 0.8656925559043884:  70%|██████▉   | 17997/25880 [3:40:44<1:37:52,  1.34it/s]
1|17998|Loss: 0.8516393303871155:  70%|██████▉   | 17997/25880 [3:40:45<1:37:52,  1.34it/s]
1|17998|Loss: 0.8516393303871155:  70%|██████▉   | 17998/25880 [3:40:45<1:41:39,  1.29it/s]
1|17999|Loss: 0.9401212930679321:  70%|██████▉   | 17998/25880 [3:40:46<1:41:39,  1.29it/s]
1|17999|Loss: 0.9401212930679321:  70%|██████▉   | 17999/25880 [3:40:46<1:44:04,  1.26it/s]
1|18000|Loss: 0.8409852385520935:  70%|██████▉   | 17999/25880 [3:40:47<1:44:04,  1.26it/s]
1|18000|Loss: 0.8409852385520935:  70%|██████▉   | 18000/25880 [3:40:47<1:45:11,  1.25it/s]
1|18001|Loss: 0.9160203337669373:  70%|██████��   | 18000/25880 [3:40:47<1:45:11,  1.25it/s]
1|18001|Loss: 0.9160203337669373:  70%|██████▉   | 18001/25880 [3:40:48<1:40:05,  1.31it/s]
1|18002|Loss: 1.00849187374115:  70%|██████▉   | 18001/25880 [3:40:48<1:40:05,  1.31it/s]  
1|18002|Loss: 1.00849187374115:  70%|██████▉   | 18002/25880 [3:40:48<1:31:56,  1.43it/s]
1|18003|Loss: 0.8067790865898132:  70%|██████▉   | 18002/25880 [3:40:49<1:31:56,  1.43it/s]
1|18003|Loss: 0.8067790865898132:  70%|██████▉   | 18003/25880 [3:40:49<1:31:28,  1.44it/s]
1|18004|Loss: 0.7135526537895203:  70%|██████▉   | 18003/25880 [3:40:49<1:31:28,  1.44it/s]
1|18004|Loss: 0.7135526537895203:  70%|██████▉   | 18004/25880 [3:40:50<1:28:58,  1.48it/s]
1|18005|Loss: 0.8626757860183716:  70%|██████▉   | 18004/25880 [3:40:50<1:28:58,  1.48it/s]
1|18005|Loss: 0.8626757860183716:  70%|██████▉   | 18005/25880 [3:40:50<1:22:19,  1.59it/s]
1|18006|Loss: 0.764521598815918:  70%|██████▉   | 18005/25880 [3:40:50<1:22:19,  1.59it/s] 
1|18006|Loss: 0.764521598815918:  70%|██████▉   | 18006/25880 [3:40:51<1:24:14,  1.56it/s]
1|18007|Loss: 0.8285558223724365:  70%|██████▉   | 18006/25880 [3:40:51<1:24:14,  1.56it/s]
1|18007|Loss: 0.8285558223724365:  70%|██████▉   | 18007/25880 [3:40:51<1:27:40,  1.50it/s]
1|18008|Loss: 0.8932116627693176:  70%|██████▉   | 18007/25880 [3:40:52<1:27:40,  1.50it/s]
1|18008|Loss: 0.8932116627693176:  70%|██████▉   | 18008/25880 [3:40:52<1:31:39,  1.43it/s]
1|18009|Loss: 0.9771439433097839:  70%|██████▉   | 18008/25880 [3:40:53<1:31:39,  1.43it/s]
1|18009|Loss: 0.9771439433097839:  70%|██████▉   | 18009/25880 [3:40:53<1:35:52,  1.37it/s]
1|18010|Loss: 0.7763808369636536:  70%|██████▉   | 18009/25880 [3:40:53<1:35:52,  1.37it/s]
1|18010|Loss: 0.7763808369636536:  70%|██████▉   | 18010/25880 [3:40:54<1:36:36,  1.36it/s]
1|18011|Loss: 0.7656584978103638:  70%|██████▉   | 18010/25880 [3:40:54<1:36:36,  1.36it/s]
1|18011|Loss: 0.7656584978103638:  70%|██████▉   | 18011/25880 [3:40:54<1:36:36,  1.36it/s]
1|18012|Loss: 0.9202513098716736:  70%|██████▉   | 18011/25880 [3:40:55<1:36:36,  1.36it/s]
1|18012|Loss: 0.9202513098716736:  70%|██████▉   | 18012/25880 [3:40:55<1:42:27,  1.28it/s]
1|18013|Loss: 0.6945337653160095:  70%|██████▉   | 18012/25880 [3:40:56<1:42:27,  1.28it/s]
1|18013|Loss: 0.6945337653160095:  70%|██████▉   | 18013/25880 [3:40:56<1:42:00,  1.29it/s]
1|18014|Loss: 0.8147252798080444:  70%|██████▉   | 18013/25880 [3:40:57<1:42:00,  1.29it/s]
1|18014|Loss: 0.8147252798080444:  70%|██████▉   | 18014/25880 [3:40:57<1:43:54,  1.26it/s]
1|18015|Loss: 0.9142011404037476:  70%|██████▉   | 18014/25880 [3:40:57<1:43:54,  1.26it/s]
1|18015|Loss: 0.9142011404037476:  70%|██████▉   | 18015/25880 [3:40:58<1:39:05,  1.32it/s]
1|18016|Loss: 0.7746624946594238:  70%|██████▉   | 18015/25880 [3:40:58<1:39:05,  1.32it/s]
1|18016|Loss: 0.7746624946594238:  70%|██████▉   | 18016/25880 [3:40:58<1:37:27,  1.34it/s]
1|18017|Loss: 0.7607918977737427:  70%|██████▉   | 18016/25880 [3:40:59<1:37:27,  1.34it/s]
1|18017|Loss: 0.7607918977737427:  70%|██████▉   | 18017/25880 [3:40:59<1:34:23,  1.39it/s]
1|18018|Loss: 0.9782137274742126:  70%|██████▉   | 18017/25880 [3:40:59<1:34:23,  1.39it/s]
1|18018|Loss: 0.9782137274742126:  70%|██████▉   | 18018/25880 [3:41:00<1:38:07,  1.34it/s]
1|18019|Loss: 0.8843020796775818:  70%|██████▉   | 18018/25880 [3:41:00<1:38:07,  1.34it/s]
1|18019|Loss: 0.8843020796775818:  70%|██████▉   | 18019/25880 [3:41:01<1:38:56,  1.32it/s]
1|18020|Loss: 0.7602431178092957:  70%|██████▉   | 18019/25880 [3:41:01<1:38:56,  1.32it/s]
1|18020|Loss: 0.7602431178092957:  70%|██████▉   | 18020/25880 [3:41:01<1:41:26,  1.29it/s]
1|18021|Loss: 0.7564103007316589:  70%|██████▉   | 18020/25880 [3:41:02<1:41:26,  1.29it/s]
1|18021|Loss: 0.7564103007316589:  70%|██████▉   | 18021/25880 [3:41:02<1:40:33,  1.30it/s]
1|18022|Loss: 0.8956546783447266:  70%|██████▉   | 18021/25880 [3:41:03<1:40:33,  1.30it/s]
1|18022|Loss: 0.8956546783447266:  70%|██████▉   | 18022/25880 [3:41:03<1:34:25,  1.39it/s]
1|18023|Loss: 0.8208634257316589:  70%|██████▉   | 18022/25880 [3:41:03<1:34:25,  1.39it/s]
1|18023|Loss: 0.8208634257316589:  70%|██████▉   | 18023/25880 [3:41:03<1:30:00,  1.45it/s]
1|18024|Loss: 0.7950893044471741:  70%|██████▉   | 18023/25880 [3:41:04<1:30:00,  1.45it/s]
1|18024|Loss: 0.7950893044471741:  70%|██████▉   | 18024/25880 [3:41:04<1:27:04,  1.50it/s]
1|18025|Loss: 0.9057210683822632:  70%|██████▉   | 18024/25880 [3:41:04<1:27:04,  1.50it/s]
1|18025|Loss: 0.9057210683822632:  70%|██████▉   | 18025/25880 [3:41:05<1:32:46,  1.41it/s]
1|18026|Loss: 0.888312578201294:  70%|██████▉   | 18025/25880 [3:41:05<1:32:46,  1.41it/s] 
1|18026|Loss: 0.888312578201294:  70%|██████▉   | 18026/25880 [3:41:06<1:34:47,  1.38it/s]
1|18027|Loss: 0.8595895171165466:  70%|██████▉   | 18026/25880 [3:41:06<1:34:47,  1.38it/s]
1|18027|Loss: 0.8595895171165466:  70%|██████▉   | 18027/25880 [3:41:06<1:35:17,  1.37it/s]
1|18028|Loss: 0.8436642289161682:  70%|██████▉   | 18027/25880 [3:41:07<1:35:17,  1.37it/s]
1|18028|Loss: 0.8436642289161682:  70%|██████▉   | 18028/25880 [3:41:07<1:30:14,  1.45it/s]
1|18029|Loss: 0.8210200071334839:  70%|██████▉   | 18028/25880 [3:41:07<1:30:14,  1.45it/s]
1|18029|Loss: 0.8210200071334839:  70%|██████▉   | 18029/25880 [3:41:08<1:29:48,  1.46it/s]
1|18030|Loss: 0.8313422799110413:  70%|██████▉   | 18029/25880 [3:41:08<1:29:48,  1.46it/s]
1|18030|Loss: 0.8313422799110413:  70%|██████▉   | 18030/25880 [3:41:08<1:36:48,  1.35it/s]
1|18031|Loss: 0.8040473461151123:  70%|██████▉   | 18030/25880 [3:41:09<1:36:48,  1.35it/s]
1|18031|Loss: 0.8040473461151123:  70%|██████▉   | 18031/25880 [3:41:09<1:41:34,  1.29it/s]
1|18032|Loss: 0.9053288698196411:  70%|██████▉   | 18031/25880 [3:41:10<1:41:34,  1.29it/s]
1|18032|Loss: 0.9053288698196411:  70%|██████▉   | 18032/25880 [3:41:10<1:44:35,  1.25it/s]
1|18033|Loss: 0.8615628480911255:  70%|██████▉   | 18032/25880 [3:41:11<1:44:35,  1.25it/s]
1|18033|Loss: 0.8615628480911255:  70%|██████▉   | 18033/25880 [3:41:11<1:43:02,  1.27it/s]
1|18034|Loss: 0.6390379071235657:  70%|██████▉   | 18033/25880 [3:41:11<1:43:02,  1.27it/s]
1|18034|Loss: 0.6390379071235657:  70%|██████▉   | 18034/25880 [3:41:11<1:32:55,  1.41it/s]
1|18035|Loss: 0.8631809949874878:  70%|██████▉   | 18034/25880 [3:41:12<1:32:55,  1.41it/s]
1|18035|Loss: 0.8631809949874878:  70%|██████▉   | 18035/25880 [3:41:12<1:35:13,  1.37it/s]
1|18036|Loss: 0.9172822833061218:  70%|██████▉   | 18035/25880 [3:41:13<1:35:13,  1.37it/s]
1|18036|Loss: 0.9172822833061218:  70%|██████▉   | 18036/25880 [3:41:13<1:42:24,  1.28it/s]
1|18037|Loss: 0.8749959468841553:  70%|██████▉   | 18036/25880 [3:41:14<1:42:24,  1.28it/s]
1|18037|Loss: 0.8749959468841553:  70%|██████▉   | 18037/25880 [3:41:14<1:39:12,  1.32it/s]
1|18038|Loss: 0.7720597982406616:  70%|██████▉   | 18037/25880 [3:41:14<1:39:12,  1.32it/s]
1|18038|Loss: 0.7720597982406616:  70%|██████▉   | 18038/25880 [3:41:15<1:37:54,  1.33it/s]
1|18039|Loss: 0.9022383689880371:  70%|██████▉   | 18038/25880 [3:41:15<1:37:54,  1.33it/s]
1|18039|Loss: 0.9022383689880371:  70%|██████▉   | 18039/25880 [3:41:15<1:40:33,  1.30it/s]
1|18040|Loss: 0.8044183254241943:  70%|██████▉   | 18039/25880 [3:41:16<1:40:33,  1.30it/s]
1|18040|Loss: 0.8044183254241943:  70%|██████▉   | 18040/25880 [3:41:16<1:44:41,  1.25it/s]
1|18041|Loss: 0.786674439907074:  70%|██████▉   | 18040/25880 [3:41:17<1:44:41,  1.25it/s] 
1|18041|Loss: 0.786674439907074:  70%|██████▉   | 18041/25880 [3:41:17<1:43:57,  1.26it/s]
1|18042|Loss: 0.8536465764045715:  70%|██████▉   | 18041/25880 [3:41:17<1:43:57,  1.26it/s]
1|18042|Loss: 0.8536465764045715:  70%|██████▉   | 18042/25880 [3:41:18<1:41:24,  1.29it/s]
1|18043|Loss: 0.7659169435501099:  70%|██████▉   | 18042/25880 [3:41:18<1:41:24,  1.29it/s]
1|18043|Loss: 0.7659169435501099:  70%|██████▉   | 18043/25880 [3:41:18<1:35:51,  1.36it/s]
1|18044|Loss: 0.7576037645339966:  70%|██████▉   | 18043/25880 [3:41:19<1:35:51,  1.36it/s]
1|18044|Loss: 0.7576037645339966:  70%|██████▉   | 18044/25880 [3:41:19<1:35:29,  1.37it/s]
1|18045|Loss: 0.8846410512924194:  70%|██████▉   | 18044/25880 [3:41:20<1:35:29,  1.37it/s]
1|18045|Loss: 0.8846410512924194:  70%|██████▉   | 18045/25880 [3:41:20<1:30:32,  1.44it/s]
1|18046|Loss: 0.7497375011444092:  70%|██████▉   | 18045/25880 [3:41:20<1:30:32,  1.44it/s]
1|18046|Loss: 0.7497375011444092:  70%|██████▉   | 18046/25880 [3:41:20<1:26:21,  1.51it/s]
1|18047|Loss: 0.8840500116348267:  70%|██████▉   | 18046/25880 [3:41:21<1:26:21,  1.51it/s]
1|18047|Loss: 0.8840500116348267:  70%|██████▉   | 18047/25880 [3:41:21<1:25:05,  1.53it/s]
1|18048|Loss: 0.7710583806037903:  70%|██████▉   | 18047/25880 [3:41:21<1:25:05,  1.53it/s]
1|18048|Loss: 0.7710583806037903:  70%|██████▉   | 18048/25880 [3:41:22<1:24:43,  1.54it/s]
1|18049|Loss: 0.8195362091064453:  70%|██████▉   | 18048/25880 [3:41:22<1:24:43,  1.54it/s]
1|18049|Loss: 0.8195362091064453:  70%|██████▉   | 18049/25880 [3:41:22<1:23:25,  1.56it/s]
1|18050|Loss: 0.6750648617744446:  70%|██████▉   | 18049/25880 [3:41:23<1:23:25,  1.56it/s]
1|18050|Loss: 0.6750648617744446:  70%|██████▉   | 18050/25880 [3:41:23<1:30:09,  1.45it/s]
1|18051|Loss: 0.7894787788391113:  70%|██████▉   | 18050/25880 [3:41:23<1:30:09,  1.45it/s]
1|18051|Loss: 0.7894787788391113:  70%|██████▉   | 18051/25880 [3:41:24<1:30:00,  1.45it/s]
1|18052|Loss: 0.8984699249267578:  70%|██████▉   | 18051/25880 [3:41:24<1:30:00,  1.45it/s]
1|18052|Loss: 0.8984699249267578:  70%|██████▉   | 18052/25880 [3:41:24<1:27:18,  1.49it/s]
1|18053|Loss: 0.7229189276695251:  70%|██████▉   | 18052/25880 [3:41:25<1:27:18,  1.49it/s]
1|18053|Loss: 0.7229189276695251:  70%|██████▉   | 18053/25880 [3:41:25<1:27:52,  1.48it/s]
1|18054|Loss: 0.8227345943450928:  70%|██████▉   | 18053/25880 [3:41:25<1:27:52,  1.48it/s]
1|18054|Loss: 0.8227345943450928:  70%|██████▉   | 18054/25880 [3:41:26<1:29:43,  1.45it/s]
1|18055|Loss: 0.6583400368690491:  70%|██████▉   | 18054/25880 [3:41:26<1:29:43,  1.45it/s]
1|18055|Loss: 0.6583400368690491:  70%|██████▉   | 18055/25880 [3:41:26<1:24:29,  1.54it/s]
1|18056|Loss: 0.7801687121391296:  70%|██████▉   | 18055/25880 [3:41:27<1:24:29,  1.54it/s]
1|18056|Loss: 0.7801687121391296:  70%|██████▉   | 18056/25880 [3:41:27<1:29:26,  1.46it/s]
1|18057|Loss: 0.7486693263053894:  70%|██████▉   | 18056/25880 [3:41:27<1:29:26,  1.46it/s]
1|18057|Loss: 0.7486693263053894:  70%|██████▉   | 18057/25880 [3:41:28<1:27:25,  1.49it/s]
1|18058|Loss: 0.8470548987388611:  70%|██████▉   | 18057/25880 [3:41:28<1:27:25,  1.49it/s]
1|18058|Loss: 0.8470548987388611:  70%|██████▉   | 18058/25880 [3:41:28<1:27:31,  1.49it/s]
1|18059|Loss: 0.7676396369934082:  70%|██████▉   | 18058/25880 [3:41:29<1:27:31,  1.49it/s]
1|18059|Loss: 0.7676396369934082:  70%|██████▉   | 18059/25880 [3:41:29<1:28:36,  1.47it/s]
1|18060|Loss: 0.7108994126319885:  70%|██████▉   | 18059/25880 [3:41:29<1:28:36,  1.47it/s]
1|18060|Loss: 0.7108994126319885:  70%|██████▉   | 18060/25880 [3:41:30<1:27:10,  1.50it/s]
1|18061|Loss: 0.852195143699646:  70%|██████▉   | 18060/25880 [3:41:30<1:27:10,  1.50it/s] 
1|18061|Loss: 0.852195143699646:  70%|██████▉   | 18061/25880 [3:41:30<1:26:07,  1.51it/s]
1|18062|Loss: 0.9643486738204956:  70%|██████▉   | 18061/25880 [3:41:31<1:26:07,  1.51it/s]
1|18062|Loss: 0.9643486738204956:  70%|██████▉   | 18062/25880 [3:41:31<1:25:25,  1.53it/s]
1|18063|Loss: 1.0224298238754272:  70%|██████▉   | 18062/25880 [3:41:31<1:25:25,  1.53it/s]
1|18063|Loss: 1.0224298238754272:  70%|██████▉   | 18063/25880 [3:41:32<1:31:25,  1.43it/s]
1|18064|Loss: 0.6743494868278503:  70%|██████▉   | 18063/25880 [3:41:32<1:31:25,  1.43it/s]
1|18064|Loss: 0.6743494868278503:  70%|██████▉   | 18064/25880 [3:41:33<1:41:56,  1.28it/s]
1|18065|Loss: 0.7890322804450989:  70%|██████▉   | 18064/25880 [3:41:33<1:41:56,  1.28it/s]
1|18065|Loss: 0.7890322804450989:  70%|██████▉   | 18065/25880 [3:41:34<1:39:33,  1.31it/s]
1|18066|Loss: 0.698162853717804:  70%|██████▉   | 18065/25880 [3:41:34<1:39:33,  1.31it/s] 
1|18066|Loss: 0.698162853717804:  70%|██████▉   | 18066/25880 [3:41:34<1:41:56,  1.28it/s]
1|18067|Loss: 0.7864364385604858:  70%|██████▉   | 18066/25880 [3:41:35<1:41:56,  1.28it/s]
1|18067|Loss: 0.7864364385604858:  70%|██████▉   | 18067/25880 [3:41:35<1:44:56,  1.24it/s]
1|18068|Loss: 0.6899474859237671:  70%|██████▉   | 18067/25880 [3:41:36<1:44:56,  1.24it/s]
1|18068|Loss: 0.6899474859237671:  70%|██████▉   | 18068/25880 [3:41:36<1:39:43,  1.31it/s]
1|18069|Loss: 0.8575883507728577:  70%|██████▉   | 18068/25880 [3:41:36<1:39:43,  1.31it/s]
1|18069|Loss: 0.8575883507728577:  70%|██████▉   | 18069/25880 [3:41:37<1:36:36,  1.35it/s]
1|18070|Loss: 0.7875288724899292:  70%|██████▉   | 18069/25880 [3:41:37<1:36:36,  1.35it/s]
1|18070|Loss: 0.7875288724899292:  70%|██████▉   | 18070/25880 [3:41:37<1:35:56,  1.36it/s]
1|18071|Loss: 0.7632758617401123:  70%|██████▉   | 18070/25880 [3:41:38<1:35:56,  1.36it/s]
1|18071|Loss: 0.7632758617401123:  70%|██████▉   | 18071/25880 [3:41:38<1:30:53,  1.43it/s]
1|18072|Loss: 0.7519885301589966:  70%|██████▉   | 18071/25880 [3:41:38<1:30:53,  1.43it/s]
1|18072|Loss: 0.7519885301589966:  70%|██████▉   | 18072/25880 [3:41:39<1:27:43,  1.48it/s]
1|18073|Loss: 0.8398428559303284:  70%|██████▉   | 18072/25880 [3:41:39<1:27:43,  1.48it/s]
1|18073|Loss: 0.8398428559303284:  70%|█████��▉   | 18073/25880 [3:41:39<1:28:58,  1.46it/s]
1|18074|Loss: 0.7983770370483398:  70%|██████▉   | 18073/25880 [3:41:40<1:28:58,  1.46it/s]
1|18074|Loss: 0.7983770370483398:  70%|██████▉   | 18074/25880 [3:41:40<1:32:26,  1.41it/s]
1|18075|Loss: 0.8504392504692078:  70%|██████▉   | 18074/25880 [3:41:40<1:32:26,  1.41it/s]
1|18075|Loss: 0.8504392504692078:  70%|██████▉   | 18075/25880 [3:41:41<1:35:43,  1.36it/s]
1|18076|Loss: 0.9314623475074768:  70%|██████▉   | 18075/25880 [3:41:41<1:35:43,  1.36it/s]
1|18076|Loss: 0.9314623475074768:  70%|██████▉   | 18076/25880 [3:41:42<1:35:03,  1.37it/s]
1|18077|Loss: 0.9034005403518677:  70%|██████▉   | 18076/25880 [3:41:42<1:35:03,  1.37it/s]
1|18077|Loss: 0.9034005403518677:  70%|██████▉   | 18077/25880 [3:41:42<1:34:58,  1.37it/s]
1|18078|Loss: 0.7656504511833191:  70%|██████▉   | 18077/25880 [3:41:43<1:34:58,  1.37it/s]
1|18078|Loss: 0.7656504511833191:  70%|██████▉   | 18078/25880 [3:41:43<1:35:39,  1.36it/s]
1|18079|Loss: 0.912533164024353:  70%|██████▉   | 18078/25880 [3:41:43<1:35:39,  1.36it/s] 
1|18079|Loss: 0.912533164024353:  70%|██████▉   | 18079/25880 [3:41:44<1:27:14,  1.49it/s]
1|18080|Loss: 0.7062515616416931:  70%|██████▉   | 18079/25880 [3:41:44<1:27:14,  1.49it/s]
1|18080|Loss: 0.7062515616416931:  70%|██████▉   | 18080/25880 [3:41:44<1:27:27,  1.49it/s]
1|18081|Loss: 0.8596081137657166:  70%|██████▉   | 18080/25880 [3:41:45<1:27:27,  1.49it/s]
1|18081|Loss: 0.8596081137657166:  70%|██████▉   | 18081/25880 [3:41:45<1:30:23,  1.44it/s]
1|18082|Loss: 0.8208739161491394:  70%|██████▉   | 18081/25880 [3:41:45<1:30:23,  1.44it/s]
1|18082|Loss: 0.8208739161491394:  70%|██████▉   | 18082/25880 [3:41:46<1:31:17,  1.42it/s]
1|18083|Loss: 0.7766329050064087:  70%|██████▉   | 18082/25880 [3:41:46<1:31:17,  1.42it/s]
1|18083|Loss: 0.7766329050064087:  70%|██████▉   | 18083/25880 [3:41:47<1:39:01,  1.31it/s]
1|18084|Loss: 0.7796109914779663:  70%|██████▉   | 18083/25880 [3:41:47<1:39:01,  1.31it/s]
1|18084|Loss: 0.7796109914779663:  70%|██████▉   | 18084/25880 [3:41:47<1:38:28,  1.32it/s]
1|18085|Loss: 0.7447100877761841:  70%|██████▉   | 18084/25880 [3:41:48<1:38:28,  1.32it/s]
1|18085|Loss: 0.7447100877761841:  70%|██████▉   | 18085/25880 [3:41:48<1:41:48,  1.28it/s]
1|18086|Loss: 0.7629769444465637:  70%|██████▉   | 18085/25880 [3:41:49<1:41:48,  1.28it/s]
1|18086|Loss: 0.7629769444465637:  70%|██████▉   | 18086/25880 [3:41:49<1:43:17,  1.26it/s]
1|18087|Loss: 0.9682740569114685:  70%|██████▉   | 18086/25880 [3:41:49<1:43:17,  1.26it/s]
1|18087|Loss: 0.9682740569114685:  70%|██████▉   | 18087/25880 [3:41:50<1:38:21,  1.32it/s]
1|18088|Loss: 0.7805622220039368:  70%|██████▉   | 18087/25880 [3:41:50<1:38:21,  1.32it/s]
1|18088|Loss: 0.7805622220039368:  70%|██████▉   | 18088/25880 [3:41:50<1:36:02,  1.35it/s]
1|18089|Loss: 0.8735960721969604:  70%|██████▉   | 18088/25880 [3:41:51<1:36:02,  1.35it/s]
1|18089|Loss: 0.8735960721969604:  70%|██████▉   | 18089/25880 [3:41:51<1:28:31,  1.47it/s]
1|18090|Loss: 0.8206557035446167:  70%|██████▉   | 18089/25880 [3:41:51<1:28:31,  1.47it/s]
1|18090|Loss: 0.8206557035446167:  70%|██████▉   | 18090/25880 [3:41:52<1:30:32,  1.43it/s]
1|18091|Loss: 0.8435465097427368:  70%|██████▉   | 18090/25880 [3:41:52<1:30:32,  1.43it/s]
1|18091|Loss: 0.8435465097427368:  70%|██████▉   | 18091/25880 [3:41:52<1:29:30,  1.45it/s]
1|18092|Loss: 0.7689622640609741:  70%|██████▉   | 18091/25880 [3:41:53<1:29:30,  1.45it/s]
1|18092|Loss: 0.7689622640609741:  70%|██████▉   | 18092/25880 [3:41:53<1:36:07,  1.35it/s]
1|18093|Loss: 0.9227113723754883:  70%|██████▉   | 18092/25880 [3:41:54<1:36:07,  1.35it/s]
1|18093|Loss: 0.9227113723754883:  70%|██████▉   | 18093/25880 [3:41:54<1:36:18,  1.35it/s]
1|18094|Loss: 0.8657531142234802:  70%|██████▉   | 18093/25880 [3:41:54<1:36:18,  1.35it/s]
1|18094|Loss: 0.8657531142234802:  70%|██████▉   | 18094/25880 [3:41:55<1:32:44,  1.40it/s]
1|18095|Loss: 0.8291205763816833:  70%|██████▉   | 18094/25880 [3:41:55<1:32:44,  1.40it/s]
1|18095|Loss: 0.8291205763816833:  70%|██████▉   | 18095/25880 [3:41:55<1:32:53,  1.40it/s]
1|18096|Loss: 0.8328378200531006:  70%|██████▉   | 18095/25880 [3:41:56<1:32:53,  1.40it/s]
1|18096|Loss: 0.8328378200531006:  70%|██████▉   | 18096/25880 [3:41:56<1:37:12,  1.33it/s]
1|18097|Loss: 0.7080516815185547:  70%|██████▉   | 18096/25880 [3:41:57<1:37:12,  1.33it/s]
1|18097|Loss: 0.7080516815185547:  70%|██████▉   | 18097/25880 [3:41:57<1:36:36,  1.34it/s]
1|18098|Loss: 0.8284733295440674:  70%|██████▉   | 18097/25880 [3:41:57<1:36:36,  1.34it/s]
1|18098|Loss: 0.8284733295440674:  70%|██████▉   | 18098/25880 [3:41:57<1:29:02,  1.46it/s]
1|18099|Loss: 0.9049192070960999:  70%|██████▉   | 18098/25880 [3:41:58<1:29:02,  1.46it/s]
1|18099|Loss: 0.9049192070960999:  70%|██████▉   | 18099/25880 [3:41:58<1:29:16,  1.45it/s]
1|18100|Loss: 0.7785420417785645:  70%|██████▉   | 18099/25880 [3:41:58<1:29:16,  1.45it/s]
1|18100|Loss: 0.7785420417785645:  70%|██████▉   | 18100/25880 [3:41:59<1:25:51,  1.51it/s]
1|18101|Loss: 0.8578459620475769:  70%|██████▉   | 18100/25880 [3:41:59<1:25:51,  1.51it/s]
1|18101|Loss: 0.8578459620475769:  70%|██████▉   | 18101/25880 [3:41:59<1:30:49,  1.43it/s]
1|18102|Loss: 0.8446754217147827:  70%|██████▉   | 18101/25880 [3:42:00<1:30:49,  1.43it/s]
1|18102|Loss: 0.8446754217147827:  70%|██████▉   | 18102/25880 [3:42:00<1:32:01,  1.41it/s]
1|18103|Loss: 0.77176433801651:  70%|██████▉   | 18102/25880 [3:42:01<1:32:01,  1.41it/s]  
1|18103|Loss: 0.77176433801651:  70%|██████▉   | 18103/25880 [3:42:01<1:31:42,  1.41it/s]
1|18104|Loss: 1.1865702867507935:  70%|██████▉   | 18103/25880 [3:42:01<1:31:42,  1.41it/s]
1|18104|Loss: 1.1865702867507935:  70%|██████▉   | 18104/25880 [3:42:02<1:28:44,  1.46it/s]
1|18105|Loss: 0.746739387512207:  70%|██████▉   | 18104/25880 [3:42:02<1:28:44,  1.46it/s] 
1|18105|Loss: 0.746739387512207:  70%|██████▉   | 18105/25880 [3:42:02<1:26:44,  1.49it/s]
1|18106|Loss: 0.8016628623008728:  70%|██████▉   | 18105/25880 [3:42:03<1:26:44,  1.49it/s]
1|18106|Loss: 0.8016628623008728:  70%|██████▉   | 18106/25880 [3:42:03<1:30:09,  1.44it/s]
1|18107|Loss: 0.8264054656028748:  70%|██████▉   | 18106/25880 [3:42:03<1:30:09,  1.44it/s]
1|18107|Loss: 0.8264054656028748:  70%|██████▉   | 18107/25880 [3:42:04<1:39:21,  1.30it/s]
1|18108|Loss: 0.94291752576828:  70%|██████▉   | 18107/25880 [3:42:04<1:39:21,  1.30it/s]  
1|18108|Loss: 0.94291752576828:  70%|██████▉   | 18108/25880 [3:42:05<1:44:12,  1.24it/s]
1|18109|Loss: 0.7776749730110168:  70%|██████▉   | 18108/25880 [3:42:05<1:44:12,  1.24it/s]
1|18109|Loss: 0.7776749730110168:  70%|██████▉   | 18109/25880 [3:42:05<1:42:01,  1.27it/s]
1|18110|Loss: 0.9924643635749817:  70%|██████▉   | 18109/25880 [3:42:06<1:42:01,  1.27it/s]
1|18110|Loss: 0.9924643635749817:  70%|██████▉   | 18110/25880 [3:42:06<1:36:41,  1.34it/s]
1|18111|Loss: 0.9353445768356323:  70%|██████▉   | 18110/25880 [3:42:06<1:36:41,  1.34it/s]
1|18111|Loss: 0.9353445768356323:  70%|██████▉   | 18111/25880 [3:42:07<1:26:43,  1.49it/s]
1|18112|Loss: 0.8433662056922913:  70%|██████▉   | 18111/25880 [3:42:07<1:26:43,  1.49it/s]
1|18112|Loss: 0.8433662056922913:  70%|██████▉   | 18112/25880 [3:42:07<1:20:37,  1.61it/s]
1|18113|Loss: 0.7692500352859497:  70%|██████▉   | 18112/25880 [3:42:08<1:20:37,  1.61it/s]
1|18113|Loss: 0.7692500352859497:  70%|██████▉   | 18113/25880 [3:42:08<1:25:16,  1.52it/s]
1|18114|Loss: 0.8536889553070068:  70%|██████▉   | 18113/25880 [3:42:08<1:25:16,  1.52it/s]
1|18114|Loss: 0.8536889553070068:  70%|██████▉   | 18114/25880 [3:42:09<1:35:46,  1.35it/s]
1|18115|Loss: 0.7476141452789307:  70%|██████▉   | 18114/25880 [3:42:09<1:35:46,  1.35it/s]
1|18115|Loss: 0.7476141452789307:  70%|██████▉   | 18115/25880 [3:42:10<1:37:18,  1.33it/s]
1|18116|Loss: 0.7370641231536865:  70%|██████▉   | 18115/25880 [3:42:10<1:37:18,  1.33it/s]
1|18116|Loss: 0.7370641231536865:  70%|███████   | 18116/25880 [3:42:10<1:38:31,  1.31it/s]
1|18117|Loss: 0.8809643387794495:  70%|███████   | 18116/25880 [3:42:11<1:38:31,  1.31it/s]
1|18117|Loss: 0.8809643387794495:  70%|███████   | 18117/25880 [3:42:11<1:36:54,  1.34it/s]
1|18118|Loss: 0.8662422895431519:  70%|███████   | 18117/25880 [3:42:12<1:36:54,  1.34it/s]
1|18118|Loss: 0.8662422895431519:  70%|███████   | 18118/25880 [3:42:12<1:40:17,  1.29it/s]
1|18119|Loss: 0.9088079333305359:  70%|███████   | 18118/25880 [3:42:12<1:40:17,  1.29it/s]
1|18119|Loss: 0.9088079333305359:  70%|███████   | 18119/25880 [3:42:13<1:39:46,  1.30it/s]
1|18120|Loss: 0.9346281290054321:  70%|███████   | 18119/25880 [3:42:13<1:39:46,  1.30it/s]
1|18120|Loss: 0.9346281290054321:  70%|███████   | 18120/25880 [3:42:13<1:38:31,  1.31it/s]
1|18121|Loss: 0.8492176532745361:  70%|███████   | 18120/25880 [3:42:14<1:38:31,  1.31it/s]
1|18121|Loss: 0.8492176532745361:  70%|███████   | 18121/25880 [3:42:14<1:42:02,  1.27it/s]
1|18122|Loss: 0.8900326490402222:  70%|███████   | 18121/25880 [3:42:15<1:42:02,  1.27it/s]
1|18122|Loss: 0.8900326490402222:  70%|███████   | 18122/25880 [3:42:15<1:40:40,  1.28it/s]
1|18123|Loss: 0.713946521282196:  70%|███████   | 18122/25880 [3:42:15<1:40:40,  1.28it/s] 
1|18123|Loss: 0.713946521282196:  70%|███████   | 18123/25880 [3:42:16<1:43:01,  1.25it/s]
1|18124|Loss: 0.880576491355896:  70%|███████   | 18123/25880 [3:42:16<1:43:01,  1.25it/s]
1|18124|Loss: 0.880576491355896:  70%|███████   | 18124/25880 [3:42:17<1:44:02,  1.24it/s]
1|18125|Loss: 0.9039490222930908:  70%|███████   | 18124/25880 [3:42:17<1:44:02,  1.24it/s]
1|18125|Loss: 0.9039490222930908:  70%|███████   | 18125/25880 [3:42:18<1:44:00,  1.24it/s]
1|18126|Loss: 0.7470318078994751:  70%|███████   | 18125/25880 [3:42:18<1:44:00,  1.24it/s]
1|18126|Loss: 0.7470318078994751:  70%|███████   | 18126/25880 [3:42:18<1:40:57,  1.28it/s]
1|18127|Loss: 0.7772650718688965:  70%|███████   | 18126/25880 [3:42:19<1:40:57,  1.28it/s]
1|18127|Loss: 0.7772650718688965:  70%|███████   | 18127/25880 [3:42:19<1:41:33,  1.27it/s]
1|18128|Loss: 0.9079472422599792:  70%|███████   | 18127/25880 [3:42:19<1:41:33,  1.27it/s]
1|18128|Loss: 0.9079472422599792:  70%|███████   | 18128/25880 [3:42:20<1:35:33,  1.35it/s]
1|18129|Loss: 0.6947997808456421:  70%|███████   | 18128/25880 [3:42:20<1:35:33,  1.35it/s]
1|18129|Loss: 0.6947997808456421:  70%|███████   | 18129/25880 [3:42:20<1:31:15,  1.42it/s]
1|18130|Loss: 0.8290554285049438:  70%|███████   | 18129/25880 [3:42:21<1:31:15,  1.42it/s]
1|18130|Loss: 0.8290554285049438:  70%|███████   | 18130/25880 [3:42:21<1:36:15,  1.34it/s]
1|18131|Loss: 0.8339612483978271:  70%|███████   | 18130/25880 [3:42:22<1:36:15,  1.34it/s]
1|18131|Loss: 0.8339612483978271:  70%|███████   | 18131/25880 [3:42:22<1:37:02,  1.33it/s]
1|18132|Loss: 0.7991145253181458:  70%|███████   | 18131/25880 [3:42:22<1:37:02,  1.33it/s]
1|18132|Loss: 0.7991145253181458:  70%|███████   | 18132/25880 [3:42:23<1:36:07,  1.34it/s]
1|18133|Loss: 0.8491820693016052:  70%|███████   | 18132/25880 [3:42:23<1:36:07,  1.34it/s]
1|18133|Loss: 0.8491820693016052:  70%|███████   | 18133/25880 [3:42:23<1:37:13,  1.33it/s]
1|18134|Loss: 0.8938016295433044:  70%|███████   | 18133/25880 [3:42:24<1:37:13,  1.33it/s]
1|18134|Loss: 0.8938016295433044:  70%|███████   | 18134/25880 [3:42:24<1:41:26,  1.27it/s]
1|18135|Loss: 0.7586935758590698:  70%|███████   | 18134/25880 [3:42:25<1:41:26,  1.27it/s]
1|18135|Loss: 0.7586935758590698:  70%|███████   | 18135/25880 [3:42:25<1:37:50,  1.32it/s]
1|18136|Loss: 0.8263044357299805:  70%|███████   | 18135/25880 [3:42:25<1:37:50,  1.32it/s]
1|18136|Loss: 0.8263044357299805:  70%|███████   | 18136/25880 [3:42:26<1:39:09,  1.30it/s]
1|18137|Loss: 0.8535912036895752:  70%|███████   | 18136/25880 [3:42:26<1:39:09,  1.30it/s]
1|18137|Loss: 0.8535912036895752:  70%|███████   | 18137/25880 [3:42:27<1:39:00,  1.30it/s]
1|18138|Loss: 0.836336076259613:  70%|███████   | 18137/25880 [3:42:27<1:39:00,  1.30it/s] 
1|18138|Loss: 0.836336076259613:  70%|███████   | 18138/25880 [3:42:27<1:38:01,  1.32it/s]
1|18139|Loss: 0.789351224899292:  70%|███████   | 18138/25880 [3:42:28<1:38:01,  1.32it/s]
1|18139|Loss: 0.789351224899292:  70%|███████   | 18139/25880 [3:42:28<1:38:38,  1.31it/s]
1|18140|Loss: 0.917590856552124:  70%|███████   | 18139/25880 [3:42:28<1:38:38,  1.31it/s]
1|18140|Loss: 0.917590856552124:  70%|███████   | 18140/25880 [3:42:29<1:37:08,  1.33it/s]
1|18141|Loss: 0.75718754529953:  70%|███████   | 18140/25880 [3:42:29<1:37:08,  1.33it/s] 
1|18141|Loss: 0.75718754529953:  70%|███████   | 18141/25880 [3:42:29<1:36:23,  1.34it/s]
1|18142|Loss: 0.7418836355209351:  70%|███████   | 18141/25880 [3:42:30<1:36:23,  1.34it/s]
1|18142|Loss: 0.7418836355209351:  70%|███████   | 18142/25880 [3:42:30<1:36:03,  1.34it/s]
1|18143|Loss: 0.9037401080131531:  70%|███████   | 18142/25880 [3:42:31<1:36:03,  1.34it/s]
1|18143|Loss: 0.9037401080131531:  70%|███████   | 18143/25880 [3:42:31<1:38:30,  1.31it/s]
1|18144|Loss: 0.9016433954238892:  70%|███████   | 18143/25880 [3:42:31<1:38:30,  1.31it/s]
1|18144|Loss: 0.9016433954238892:  70%|███████   | 18144/25880 [3:42:32<1:38:12,  1.31it/s]
1|18145|Loss: 0.7884038090705872:  70%|███████   | 18144/25880 [3:42:32<1:38:12,  1.31it/s]
1|18145|Loss: 0.7884038090705872:  70%|███████   | 18145/25880 [3:42:33<1:37:13,  1.33it/s]
1|18146|Loss: 0.8378399610519409:  70%|███████   | 18145/25880 [3:42:33<1:37:13,  1.33it/s]
1|18146|Loss: 0.8378399610519409:  70%|███████   | 18146/25880 [3:42:33<1:36:48,  1.33it/s]
1|18147|Loss: 0.8313430547714233:  70%|███████   | 18146/25880 [3:42:34<1:36:48,  1.33it/s]
1|18147|Loss: 0.8313430547714233:  70%|███████   | 18147/25880 [3:42:34<1:36:27,  1.34it/s]
1|18148|Loss: 0.8937427997589111:  70%|███████   | 18147/25880 [3:42:34<1:36:27,  1.34it/s]
1|18148|Loss: 0.8937427997589111:  70%|███████   | 18148/25880 [3:42:35<1:34:49,  1.36it/s]
1|18149|Loss: 0.7203341126441956:  70%|███████   | 18148/25880 [3:42:35<1:34:49,  1.36it/s]
1|18149|Loss: 0.7203341126441956:  70%|███████   | 18149/25880 [3:42:35<1:34:22,  1.37it/s]
1|18150|Loss: 0.9423739314079285:  70%|███████   | 18149/25880 [3:42:36<1:34:22,  1.37it/s]
1|18150|Loss: 0.9423739314079285:  70%|███████   | 18150/25880 [3:42:36<1:31:26,  1.41it/s]
1|18151|Loss: 1.0685478448867798:  70%|███████   | 18150/25880 [3:42:36<1:31:26,  1.41it/s]
1|18151|Loss: 1.0685478448867798:  70%|███████   | 18151/25880 [3:42:37<1:27:09,  1.48it/s]
1|18152|Loss: 0.8574586510658264:  70%|███████   | 18151/25880 [3:42:37<1:27:09,  1.48it/s]
1|18152|Loss: 0.8574586510658264:  70%|███████   | 18152/25880 [3:42:37<1:31:40,  1.40it/s]
1|18153|Loss: 0.7893795967102051:  70%|███████   | 18152/25880 [3:42:38<1:31:40,  1.40it/s]
1|18153|Loss: 0.7893795967102051:  70%|███████   | 18153/25880 [3:42:38<1:30:02,  1.43it/s]
1|18154|Loss: 0.8251461386680603:  70%|███████   | 18153/25880 [3:42:38<1:30:02,  1.43it/s]
1|18154|Loss: 0.8251461386680603:  70%|███████   | 18154/25880 [3:42:39<1:24:55,  1.52it/s]
1|18155|Loss: 0.8221949338912964:  70%|███████   | 18154/25880 [3:42:39<1:24:55,  1.52it/s]
1|18155|Loss: 0.8221949338912964:  70%|███████   | 18155/25880 [3:42:40<1:29:08,  1.44it/s]
1|18156|Loss: 0.882612407207489:  70%|███████   | 18155/25880 [3:42:40<1:29:08,  1.44it/s] 
1|18156|Loss: 0.882612407207489:  70%|███████   | 18156/25880 [3:42:40<1:31:43,  1.40it/s]
1|18157|Loss: 0.8895514011383057:  70%|███████   | 18156/25880 [3:42:41<1:31:43,  1.40it/s]
1|18157|Loss: 0.8895514011383057:  70%|███████   | 18157/25880 [3:42:41<1:29:49,  1.43it/s]
1|18158|Loss: 0.7898938059806824:  70%|███████   | 18157/25880 [3:42:41<1:29:49,  1.43it/s]
1|18158|Loss: 0.7898938059806824:  70%|███████   | 18158/25880 [3:42:42<1:31:00,  1.41it/s]
1|18159|Loss: 1.0604724884033203:  70%|███████   | 18158/25880 [3:42:42<1:31:00,  1.41it/s]
1|18159|Loss: 1.0604724884033203:  70%|███████   | 18159/25880 [3:42:42<1:29:29,  1.44it/s]
1|18160|Loss: 0.6763264536857605:  70%|███████   | 18159/25880 [3:42:43<1:29:29,  1.44it/s]
1|18160|Loss: 0.6763264536857605:  70%|███████   | 18160/25880 [3:42:43<1:29:23,  1.44it/s]
1|18161|Loss: 0.8186947703361511:  70%|███████   | 18160/25880 [3:42:43<1:29:23,  1.44it/s]
1|18161|Loss: 0.8186947703361511:  70%|███████   | 18161/25880 [3:42:44<1:26:53,  1.48it/s]
1|18162|Loss: 0.8009732961654663:  70%|███████   | 18161/25880 [3:42:44<1:26:53,  1.48it/s]
1|18162|Loss: 0.8009732961654663:  70%|███████   | 18162/25880 [3:42:44<1:30:16,  1.42it/s]
1|18163|Loss: 0.7988328337669373:  70%|███████   | 18162/25880 [3:42:45<1:30:16,  1.42it/s]
1|18163|Loss: 0.7988328337669373:  70%|███████   | 18163/25880 [3:42:45<1:39:36,  1.29it/s]
1|18164|Loss: 0.9226571321487427:  70%|███████   | 18163/25880 [3:42:46<1:39:36,  1.29it/s]
1|18164|Loss: 0.9226571321487427:  70%|███████   | 18164/25880 [3:42:46<1:44:53,  1.23it/s]
1|18165|Loss: 0.7787598967552185:  70%|███████   | 18164/25880 [3:42:47<1:44:53,  1.23it/s]
1|18165|Loss: 0.7787598967552185:  70%|███████   | 18165/25880 [3:42:47<1:38:37,  1.30it/s]
1|18166|Loss: 0.9239533543586731:  70%|███████   | 18165/25880 [3:42:47<1:38:37,  1.30it/s]
1|18166|Loss: 0.9239533543586731:  70%|███████   | 18166/25880 [3:42:48<1:31:29,  1.41it/s]
1|18167|Loss: 0.8312296271324158:  70%|███████   | 18166/25880 [3:42:48<1:31:29,  1.41it/s]
1|18167|Loss: 0.8312296271324158:  70%|███████   | 18167/25880 [3:42:48<1:30:09,  1.43it/s]
1|18168|Loss: 0.7485859990119934:  70%|███████   | 18167/25880 [3:42:49<1:30:09,  1.43it/s]
1|18168|Loss: 0.7485859990119934:  70%|███████   | 18168/25880 [3:42:49<1:26:31,  1.49it/s]
1|18169|Loss: 0.7838248014450073:  70%|███████   | 18168/25880 [3:42:49<1:26:31,  1.49it/s]
1|18169|Loss: 0.7838248014450073:  70%|███████   | 18169/25880 [3:42:50<1:31:01,  1.41it/s]
1|18170|Loss: 0.9284929633140564:  70%|███████   | 18169/25880 [3:42:50<1:31:01,  1.41it/s]
1|18170|Loss: 0.9284929633140564:  70%|███████   | 18170/25880 [3:42:50<1:33:11,  1.38it/s]
1|18171|Loss: 0.859879732131958:  70%|███████   | 18170/25880 [3:42:51<1:33:11,  1.38it/s] 
1|18171|Loss: 0.859879732131958:  70%|███████   | 18171/25880 [3:42:51<1:34:07,  1.36it/s]
1|18172|Loss: 0.7465987801551819:  70%|███████   | 18171/25880 [3:42:52<1:34:07,  1.36it/s]
1|18172|Loss: 0.7465987801551819:  70%|███████   | 18172/25880 [3:42:52<1:40:04,  1.28it/s]
1|18173|Loss: 0.7063732147216797:  70%|███████   | 18172/25880 [3:42:53<1:40:04,  1.28it/s]
1|18173|Loss: 0.7063732147216797:  70%|███████   | 18173/25880 [3:42:53<1:47:51,  1.19it/s]
1|18174|Loss: 0.8789780139923096:  70%|███████   | 18173/25880 [3:42:53<1:47:51,  1.19it/s]
1|18174|Loss: 0.8789780139923096:  70%|███████   | 18174/25880 [3:42:54<1:45:12,  1.22it/s]
1|18175|Loss: 0.7653405070304871:  70%|███████   | 18174/25880 [3:42:54<1:45:12,  1.22it/s]
1|18175|Loss: 0.7653405070304871:  70%|███████   | 18175/25880 [3:42:55<1:44:45,  1.23it/s]
1|18176|Loss: 0.8584319949150085:  70%|███████   | 18175/25880 [3:42:55<1:44:45,  1.23it/s]
1|18176|Loss: 0.8584319949150085:  70%|███████   | 18176/25880 [3:42:55<1:41:04,  1.27it/s]
1|18177|Loss: 0.9385716319084167:  70%|███████   | 18176/25880 [3:42:56<1:41:04,  1.27it/s]
1|18177|Loss: 0.9385716319084167:  70%|███████   | 18177/25880 [3:42:56<1:41:37,  1.26it/s]
1|18178|Loss: 0.8386518359184265:  70%|███████   | 18177/25880 [3:42:56<1:41:37,  1.26it/s]
1|18178|Loss: 0.8386518359184265:  70%|███████   | 18178/25880 [3:42:57<1:39:03,  1.30it/s]
1|18179|Loss: 0.8462055921554565:  70%|███████   | 18178/25880 [3:42:57<1:39:03,  1.30it/s]
1|18179|Loss: 0.8462055921554565:  70%|███████   | 18179/25880 [3:42:58<1:37:20,  1.32it/s]
1|18180|Loss: 0.8177843689918518:  70%|███████   | 18179/25880 [3:42:58<1:37:20,  1.32it/s]
1|18180|Loss: 0.8177843689918518:  70%|███████   | 18180/25880 [3:42:58<1:33:12,  1.38it/s]
1|18181|Loss: 0.961525559425354:  70%|███████   | 18180/25880 [3:42:59<1:33:12,  1.38it/s] 
1|18181|Loss: 0.961525559425354:  70%|███████   | 18181/25880 [3:42:59<1:32:51,  1.38it/s]
1|18182|Loss: 0.8955226540565491:  70%|███████   | 18181/25880 [3:42:59<1:32:51,  1.38it/s]
1|18182|Loss: 0.8955226540565491:  70%|███████   | 18182/25880 [3:43:00<1:36:59,  1.32it/s]
1|18183|Loss: 0.8140934705734253:  70%|███████   | 18182/25880 [3:43:00<1:36:59,  1.32it/s]
1|18183|Loss: 0.8140934705734253:  70%|███████   | 18183/25880 [3:43:01<1:38:52,  1.30it/s]
1|18184|Loss: 0.8293718695640564:  70%|███████   | 18183/25880 [3:43:01<1:38:52,  1.30it/s]
1|18184|Loss: 0.8293718695640564:  70%|███████   | 18184/25880 [3:43:01<1:37:09,  1.32it/s]
1|18185|Loss: 0.7752119898796082:  70%|███████   | 18184/25880 [3:43:02<1:37:09,  1.32it/s]
1|18185|Loss: 0.7752119898796082:  70%|███████   | 18185/25880 [3:43:02<1:38:46,  1.30it/s]
1|18186|Loss: 0.85633784532547:  70%|███████   | 18185/25880 [3:43:02<1:38:46,  1.30it/s]  
1|18186|Loss: 0.85633784532547:  70%|███████   | 18186/25880 [3:43:03<1:37:51,  1.31it/s]
1|18187|Loss: 0.6928937435150146:  70%|███████   | 18186/25880 [3:43:03<1:37:51,  1.31it/s]
1|18187|Loss: 0.6928937435150146:  70%|███████   | 18187/25880 [3:43:03<1:28:48,  1.44it/s]
1|18188|Loss: 0.7415745854377747:  70%|███████   | 18187/25880 [3:43:04<1:28:48,  1.44it/s]
1|18188|Loss: 0.7415745854377747:  70%|███████   | 18188/25880 [3:43:04<1:31:21,  1.40it/s]
1|18189|Loss: 0.7430790662765503:  70%|███████   | 18188/25880 [3:43:05<1:31:21,  1.40it/s]
1|18189|Loss: 0.7430790662765503:  70%|███████   | 18189/25880 [3:43:05<1:32:52,  1.38it/s]
1|18190|Loss: 0.8554976582527161:  70%|███████   | 18189/25880 [3:43:05<1:32:52,  1.38it/s]
1|18190|Loss: 0.8554976582527161:  70%|███████   | 18190/25880 [3:43:06<1:33:08,  1.38it/s]
1|18191|Loss: 0.9600901007652283:  70%|███████   | 18190/25880 [3:43:06<1:33:08,  1.38it/s]
1|18191|Loss: 0.9600901007652283:  70%|███████   | 18191/25880 [3:43:06<1:35:40,  1.34it/s]
1|18192|Loss: 0.96351158618927:  70%|███████   | 18191/25880 [3:43:07<1:35:40,  1.34it/s]  
1|18192|Loss: 0.96351158618927:  70%|███████   | 18192/25880 [3:43:07<1:35:54,  1.34it/s]
1|18193|Loss: 0.6981094479560852:  70%|███████   | 18192/25880 [3:43:08<1:35:54,  1.34it/s]
1|18193|Loss: 0.6981094479560852:  70%|███████   | 18193/25880 [3:43:08<1:35:44,  1.34it/s]
1|18194|Loss: 0.8098917603492737:  70%|███████   | 18193/25880 [3:43:08<1:35:44,  1.34it/s]
1|18194|Loss: 0.8098917603492737:  70%|███████   | 18194/25880 [3:43:09<1:35:26,  1.34it/s]
1|18195|Loss: 0.8845941424369812:  70%|███████   | 18194/25880 [3:43:09<1:35:26,  1.34it/s]
1|18195|Loss: 0.8845941424369812:  70%|███████   | 18195/25880 [3:43:09<1:32:08,  1.39it/s]
1|18196|Loss: 0.8827765583992004:  70%|███████   | 18195/25880 [3:43:10<1:32:08,  1.39it/s]
1|18196|Loss: 0.8827765583992004:  70%|███████   | 18196/25880 [3:43:10<1:30:53,  1.41it/s]
1|18197|Loss: 0.8515902757644653:  70%|███████   | 18196/25880 [3:43:10<1:30:53,  1.41it/s]
1|18197|Loss: 0.8515902757644653:  70%|███████   | 18197/25880 [3:43:11<1:38:31,  1.30it/s]
1|18198|Loss: 0.8429814577102661:  70%|███████   | 18197/25880 [3:43:11<1:38:31,  1.30it/s]
1|18198|Loss: 0.8429814577102661:  70%|███████   | 18198/25880 [3:43:12<1:34:22,  1.36it/s]
1|18199|Loss: 0.7846657037734985:  70%|███████   | 18198/25880 [3:43:12<1:34:22,  1.36it/s]
1|18199|Loss: 0.7846657037734985:  70%|███████   | 18199/25880 [3:43:12<1:29:13,  1.43it/s]
1|18200|Loss: 0.817664384841919:  70%|███████   | 18199/25880 [3:43:12<1:29:13,  1.43it/s] 
1|18200|Loss: 0.817664384841919:  70%|███████   | 18200/25880 [3:43:13<1:29:28,  1.43it/s]
1|18201|Loss: 0.9388656616210938:  70%|███████   | 18200/25880 [3:43:13<1:29:28,  1.43it/s]
1|18201|Loss: 0.9388656616210938:  70%|███████   | 18201/25880 [3:43:14<1:31:14,  1.40it/s]
1|18202|Loss: 0.6576753258705139:  70%|███████   | 18201/25880 [3:43:14<1:31:14,  1.40it/s]
1|18202|Loss: 0.6576753258705139:  70%|███████   | 18202/25880 [3:43:14<1:28:04,  1.45it/s]
1|18203|Loss: 0.764995276927948:  70%|███████   | 18202/25880 [3:43:15<1:28:04,  1.45it/s] 
1|18203|Loss: 0.764995276927948:  70%|███████   | 18203/25880 [3:43:15<1:25:46,  1.49it/s]
1|18204|Loss: 0.8013461232185364:  70%|███████   | 18203/25880 [3:43:15<1:25:46,  1.49it/s]
1|18204|Loss: 0.8013461232185364:  70%|███████   | 18204/25880 [3:43:16<1:33:18,  1.37it/s]
1|18205|Loss: 0.9809697270393372:  70%|███████   | 18204/25880 [3:43:16<1:33:18,  1.37it/s]
1|18205|Loss: 0.9809697270393372:  70%|███████   | 18205/25880 [3:43:17<1:39:11,  1.29it/s]
1|18206|Loss: 0.7900161147117615:  70%|███████   | 18205/25880 [3:43:17<1:39:11,  1.29it/s]
1|18206|Loss: 0.7900161147117615:  70%|███████   | 18206/25880 [3:43:17<1:37:44,  1.31it/s]
1|18207|Loss: 0.8623836636543274:  70%|███████   | 18206/25880 [3:43:18<1:37:44,  1.31it/s]
1|18207|Loss: 0.8623836636543274:  70%|███████   | 18207/25880 [3:43:18<1:36:09,  1.33it/s]
1|18208|Loss: 0.898045539855957:  70%|███████   | 18207/25880 [3:43:18<1:36:09,  1.33it/s] 
1|18208|Loss: 0.898045539855957:  70%|███████   | 18208/25880 [3:43:19<1:35:16,  1.34it/s]
1|18209|Loss: 0.7636781334877014:  70%|███████   | 18208/25880 [3:43:19<1:35:16,  1.34it/s]
1|18209|Loss: 0.7636781334877014:  70%|███████   | 18209/25880 [3:43:19<1:29:51,  1.42it/s]
1|18210|Loss: 0.7797756195068359:  70%|███████   | 18209/25880 [3:43:20<1:29:51,  1.42it/s]
1|18210|Loss: 0.7797756195068359:  70%|███████   | 18210/25880 [3:43:20<1:32:00,  1.39it/s]
1|18211|Loss: 0.8402941226959229:  70%|███████   | 18210/25880 [3:43:21<1:32:00,  1.39it/s]
1|18211|Loss: 0.8402941226959229:  70%|███████   | 18211/25880 [3:43:21<1:36:06,  1.33it/s]
1|18212|Loss: 0.6896277070045471:  70%|███████   | 18211/25880 [3:43:21<1:36:06,  1.33it/s]
1|18212|Loss: 0.6896277070045471:  70%|███████   | 18212/25880 [3:43:22<1:29:35,  1.43it/s]
1|18213|Loss: 0.7995040416717529:  70%|███████   | 18212/25880 [3:43:22<1:29:35,  1.43it/s]
1|18213|Loss: 0.7995040416717529:  70%|███████   | 18213/25880 [3:43:22<1:28:03,  1.45it/s]
1|18214|Loss: 0.8646500110626221:  70%|███████   | 18213/25880 [3:43:23<1:28:03,  1.45it/s]
1|18214|Loss: 0.8646500110626221:  70%|███████   | 18214/25880 [3:43:23<1:29:14,  1.43it/s]
1|18215|Loss: 0.8639305830001831:  70%|███████   | 18214/25880 [3:43:23<1:29:14,  1.43it/s]
1|18215|Loss: 0.8639305830001831:  70%|███████   | 18215/25880 [3:43:24<1:33:26,  1.37it/s]
1|18216|Loss: 0.8386138677597046:  70%|███████   | 18215/25880 [3:43:24<1:33:26,  1.37it/s]
1|18216|Loss: 0.8386138677597046:  70%|███████   | 18216/25880 [3:43:24<1:29:28,  1.43it/s]
1|18217|Loss: 0.7412853837013245:  70%|███████   | 18216/25880 [3:43:25<1:29:28,  1.43it/s]
1|18217|Loss: 0.7412853837013245:  70%|███████   | 18217/25880 [3:43:25<1:25:50,  1.49it/s]
1|18218|Loss: 0.8334041833877563:  70%|███████   | 18217/25880 [3:43:25<1:25:50,  1.49it/s]
1|18218|Loss: 0.8334041833877563:  70%|███████   | 18218/25880 [3:43:26<1:27:11,  1.46it/s]
1|18219|Loss: 1.082425832748413:  70%|███████   | 18218/25880 [3:43:26<1:27:11,  1.46it/s] 
1|18219|Loss: 1.082425832748413:  70%|███████   | 18219/25880 [3:43:26<1:28:00,  1.45it/s]
1|18220|Loss: 0.8106234073638916:  70%|███████   | 18219/25880 [3:43:27<1:28:00,  1.45it/s]
1|18220|Loss: 0.8106234073638916:  70%|███████   | 18220/25880 [3:43:27<1:29:39,  1.42it/s]
1|18221|Loss: 0.845214307308197:  70%|███████   | 18220/25880 [3:43:28<1:29:39,  1.42it/s] 
1|18221|Loss: 0.845214307308197:  70%|███████   | 18221/25880 [3:43:28<1:29:57,  1.42it/s]
1|18222|Loss: 0.8486654162406921:  70%|███████   | 18221/25880 [3:43:28<1:29:57,  1.42it/s]
1|18222|Loss: 0.8486654162406921:  70%|███████   | 18222/25880 [3:43:29<1:30:23,  1.41it/s]
1|18223|Loss: 0.8379303216934204:  70%|███████   | 18222/25880 [3:43:29<1:30:23,  1.41it/s]
1|18223|Loss: 0.8379303216934204:  70%|███████   | 18223/25880 [3:43:29<1:31:21,  1.40it/s]
1|18224|Loss: 0.7684751152992249:  70%|███████   | 18223/25880 [3:43:30<1:31:21,  1.40it/s]
1|18224|Loss: 0.7684751152992249:  70%|███████   | 18224/25880 [3:43:30<1:29:14,  1.43it/s]
1|18225|Loss: 0.8979288339614868:  70%|███████   | 18224/25880 [3:43:30<1:29:14,  1.43it/s]
1|18225|Loss: 0.8979288339614868:  70%|███████   | 18225/25880 [3:43:31<1:26:10,  1.48it/s]
1|18226|Loss: 0.8040791153907776:  70%|███████   | 18225/25880 [3:43:31<1:26:10,  1.48it/s]
1|18226|Loss: 0.8040791153907776:  70%|███████   | 18226/25880 [3:43:31<1:27:19,  1.46it/s]
1|18227|Loss: 0.9542771577835083:  70%|███████   | 18226/25880 [3:43:32<1:27:19,  1.46it/s]
1|18227|Loss: 0.9542771577835083:  70%|███████   | 18227/25880 [3:43:32<1:33:07,  1.37it/s]
1|18228|Loss: 0.8432064652442932:  70%|███████   | 18227/25880 [3:43:33<1:33:07,  1.37it/s]
1|18228|Loss: 0.8432064652442932:  70%|███████   | 18228/25880 [3:43:33<1:41:31,  1.26it/s]
1|18229|Loss: 0.8946440815925598:  70%|███████   | 18228/25880 [3:43:34<1:41:31,  1.26it/s]
1|18229|Loss: 0.8946440815925598:  70%|███████   | 18229/25880 [3:43:34<1:43:24,  1.23it/s]
1|18230|Loss: 0.6953544020652771:  70%|███████   | 18229/25880 [3:43:34<1:43:24,  1.23it/s]
1|18230|Loss: 0.6953544020652771:  70%|███████   | 18230/25880 [3:43:35<1:45:18,  1.21it/s]
1|18231|Loss: 0.8295417428016663:  70%|███████   | 18230/25880 [3:43:35<1:45:18,  1.21it/s]
1|18231|Loss: 0.8295417428016663:  70%|███████   | 18231/25880 [3:43:35<1:38:36,  1.29it/s]
1|18232|Loss: 0.8182353973388672:  70%|███████   | 18231/25880 [3:43:36<1:38:36,  1.29it/s]
1|18232|Loss: 0.8182353973388672:  70%|███████   | 18232/25880 [3:43:36<1:29:54,  1.42it/s]
1|18233|Loss: 0.8359124064445496:  70%|███████   | 18232/25880 [3:43:36<1:29:54,  1.42it/s]
1|18233|Loss: 0.8359124064445496:  70%|███████   | 18233/25880 [3:43:37<1:31:23,  1.39it/s]
1|18234|Loss: 0.8019534945487976:  70%|███████   | 18233/25880 [3:43:37<1:31:23,  1.39it/s]
1|18234|Loss: 0.8019534945487976:  70%|███████   | 18234/25880 [3:43:37<1:32:51,  1.37it/s]
1|18235|Loss: 0.7925271987915039:  70%|███████   | 18234/25880 [3:43:38<1:32:51,  1.37it/s]
1|18235|Loss: 0.7925271987915039:  70%|███████   | 18235/25880 [3:43:38<1:36:16,  1.32it/s]
1|18236|Loss: 0.8657858371734619:  70%|███████   | 18235/25880 [3:43:39<1:36:16,  1.32it/s]
1|18236|Loss: 0.8657858371734619:  70%|███████   | 18236/25880 [3:43:39<1:31:29,  1.39it/s]
1|18237|Loss: 0.9201214909553528:  70%|███████   | 18236/25880 [3:43:39<1:31:29,  1.39it/s]
1|18237|Loss: 0.9201214909553528:  70%|███████   | 18237/25880 [3:43:40<1:27:24,  1.46it/s]
1|18238|Loss: 0.8065969347953796:  70%|███████   | 18237/25880 [3:43:40<1:27:24,  1.46it/s]
1|18238|Loss: 0.8065969347953796:  70%|███████   | 18238/25880 [3:43:40<1:28:52,  1.43it/s]
1|18239|Loss: 0.9014429450035095:  70%|███████   | 18238/25880 [3:43:41<1:28:52,  1.43it/s]
1|18239|Loss: 0.9014429450035095:  70%|███████   | 18239/25880 [3:43:41<1:30:36,  1.41it/s]
1|18240|Loss: 0.7078818678855896:  70%|███████   | 18239/25880 [3:43:41<1:30:36,  1.41it/s]
1|18240|Loss: 0.7078818678855896:  70%|███████   | 18240/25880 [3:43:42<1:33:41,  1.36it/s]
1|18241|Loss: 0.9009851217269897:  70%|███████   | 18240/25880 [3:43:42<1:33:41,  1.36it/s]
1|18241|Loss: 0.9009851217269897:  70%|███████   | 18241/25880 [3:43:43<1:36:57,  1.31it/s]
1|18242|Loss: 0.7596221566200256:  70%|███████   | 18241/25880 [3:43:43<1:36:57,  1.31it/s]
1|18242|Loss: 0.7596221566200256:  70%|███████   | 18242/25880 [3:43:43<1:32:53,  1.37it/s]
1|18243|Loss: 0.9347864985466003:  70%|███████   | 18242/25880 [3:43:44<1:32:53,  1.37it/s]
1|18243|Loss: 0.9347864985466003:  70%|███████   | 18243/25880 [3:43:44<1:37:32,  1.31it/s]
1|18244|Loss: 0.8871887922286987:  70%|███████   | 18243/25880 [3:43:45<1:37:32,  1.31it/s]
1|18244|Loss: 0.8871887922286987:  70%|███████   | 18244/25880 [3:43:45<1:37:47,  1.30it/s]
1|18245|Loss: 0.9881347417831421:  70%|███████   | 18244/25880 [3:43:45<1:37:47,  1.30it/s]
1|18245|Loss: 0.9881347417831421:  70%|███████   | 18245/25880 [3:43:46<1:39:01,  1.29it/s]
1|18246|Loss: 0.8796040415763855:  70%|███████   | 18245/25880 [3:43:46<1:39:01,  1.29it/s]
1|18246|Loss: 0.8796040415763855:  71%|███████   | 18246/25880 [3:43:47<1:41:21,  1.26it/s]
1|18247|Loss: 0.8392427563667297:  71%|███████   | 18246/25880 [3:43:47<1:41:21,  1.26it/s]
1|18247|Loss: 0.8392427563667297:  71%|███████   | 18247/25880 [3:43:47<1:42:14,  1.24it/s]
1|18248|Loss: 0.9534567594528198:  71%|███████   | 18247/25880 [3:43:48<1:42:14,  1.24it/s]
1|18248|Loss: 0.9534567594528198:  71%|███████   | 18248/25880 [3:43:48<1:36:39,  1.32it/s]
1|18249|Loss: 0.7911157011985779:  71%|███████   | 18248/25880 [3:43:48<1:36:39,  1.32it/s]
1|18249|Loss: 0.7911157011985779:  71%|███████   | 18249/25880 [3:43:49<1:30:10,  1.41it/s]
1|18250|Loss: 0.8518445491790771:  71%|███████   | 18249/25880 [3:43:49<1:30:10,  1.41it/s]
1|18250|Loss: 0.8518445491790771:  71%|███████   | 18250/25880 [3:43:49<1:34:12,  1.35it/s]
1|18251|Loss: 0.7850615978240967:  71%|███████   | 18250/25880 [3:43:50<1:34:12,  1.35it/s]
1|18251|Loss: 0.7850615978240967:  71%|███████   | 18251/25880 [3:43:50<1:39:25,  1.28it/s]
1|18252|Loss: 0.8761482238769531:  71%|███████   | 18251/25880 [3:43:51<1:39:25,  1.28it/s]
1|18252|Loss: 0.8761482238769531:  71%|███████   | 18252/25880 [3:43:51<1:42:24,  1.24it/s]
1|18253|Loss: 0.8206186890602112:  71%|███████   | 18252/25880 [3:43:52<1:42:24,  1.24it/s]
1|18253|Loss: 0.8206186890602112:  71%|███████   | 18253/25880 [3:43:52<1:39:34,  1.28it/s]
1|18254|Loss: 0.8292661905288696:  71%|███████   | 18253/25880 [3:43:52<1:39:34,  1.28it/s]
1|18254|Loss: 0.8292661905288696:  71%|███████   | 18254/25880 [3:43:53<1:39:07,  1.28it/s]
1|18255|Loss: 0.7651911973953247:  71%|███████   | 18254/25880 [3:43:53<1:39:07,  1.28it/s]
1|18255|Loss: 0.7651911973953247:  71%|███████   | 18255/25880 [3:43:53<1:38:13,  1.29it/s]
1|18256|Loss: 0.9132948517799377:  71%|███████   | 18255/25880 [3:43:54<1:38:13,  1.29it/s]
1|18256|Loss: 0.9132948517799377:  71%|███████   | 18256/25880 [3:43:54<1:37:21,  1.31it/s]
1|18257|Loss: 0.8317892551422119:  71%|███████   | 18256/25880 [3:43:55<1:37:21,  1.31it/s]
1|18257|Loss: 0.8317892551422119:  71%|███████   | 18257/25880 [3:43:55<1:43:01,  1.23it/s]
1|18258|Loss: 0.7307579517364502:  71%|███████   | 18257/25880 [3:43:56<1:43:01,  1.23it/s]
1|18258|Loss: 0.7307579517364502:  71%|███████   | 18258/25880 [3:43:56<1:41:34,  1.25it/s]
1|18259|Loss: 0.8438361287117004:  71%|███████   | 18258/25880 [3:43:56<1:41:34,  1.25it/s]
1|18259|Loss: 0.8438361287117004:  71%|███████   | 18259/25880 [3:43:56<1:34:11,  1.35it/s]
1|18260|Loss: 0.7054296135902405:  71%|███████   | 18259/25880 [3:43:57<1:34:11,  1.35it/s]
1|18260|Loss: 0.7054296135902405:  71%|███████   | 18260/25880 [3:43:57<1:28:56,  1.43it/s]
1|18261|Loss: 0.866345226764679:  71%|███████   | 18260/25880 [3:43:57<1:28:56,  1.43it/s] 
1|18261|Loss: 0.866345226764679:  71%|███████   | 18261/25880 [3:43:58<1:21:47,  1.55it/s]
1|18262|Loss: 0.8687455058097839:  71%|███████   | 18261/25880 [3:43:58<1:21:47,  1.55it/s]
1|18262|Loss: 0.8687455058097839:  71%|███████   | 18262/25880 [3:43:58<1:17:06,  1.65it/s]
1|18263|Loss: 0.8492794036865234:  71%|███████   | 18262/25880 [3:43:58<1:17:06,  1.65it/s]
1|18263|Loss: 0.8492794036865234:  71%|███████   | 18263/25880 [3:43:59<1:20:29,  1.58it/s]
1|18264|Loss: 0.9047729969024658:  71%|███████   | 18263/25880 [3:43:59<1:20:29,  1.58it/s]
1|18264|Loss: 0.9047729969024658:  71%|███████   | 18264/25880 [3:43:59<1:23:47,  1.51it/s]
1|18265|Loss: 0.7196140885353088:  71%|███████   | 18264/25880 [3:44:00<1:23:47,  1.51it/s]
1|18265|Loss: 0.7196140885353088:  71%|███████   | 18265/25880 [3:44:00<1:29:26,  1.42it/s]
1|18266|Loss: 0.7759219408035278:  71%|███████   | 18265/25880 [3:44:01<1:29:26,  1.42it/s]
1|18266|Loss: 0.7759219408035278:  71%|███████   | 18266/25880 [3:44:01<1:31:28,  1.39it/s]
1|18267|Loss: 0.7481752634048462:  71%|███████   | 18266/25880 [3:44:01<1:31:28,  1.39it/s]
1|18267|Loss: 0.7481752634048462:  71%|███████   | 18267/25880 [3:44:02<1:31:25,  1.39it/s]
1|18268|Loss: 0.8772019743919373:  71%|███████   | 18267/25880 [3:44:02<1:31:25,  1.39it/s]
1|18268|Loss: 0.8772019743919373:  71%|███████   | 18268/25880 [3:44:03<1:31:46,  1.38it/s]
1|18269|Loss: 0.8284417986869812:  71%|███████   | 18268/25880 [3:44:03<1:31:46,  1.38it/s]
1|18269|Loss: 0.8284417986869812:  71%|███████   | 18269/25880 [3:44:03<1:32:26,  1.37it/s]
1|18270|Loss: 0.8016870021820068:  71%|███████   | 18269/25880 [3:44:04<1:32:26,  1.37it/s]
1|18270|Loss: 0.8016870021820068:  71%|███████   | 18270/25880 [3:44:04<1:34:43,  1.34it/s]
1|18271|Loss: 0.8827888369560242:  71%|███████   | 18270/25880 [3:44:04<1:34:43,  1.34it/s]
1|18271|Loss: 0.8827888369560242:  71%|███████   | 18271/25880 [3:44:05<1:36:23,  1.32it/s]
1|18272|Loss: 0.7712507843971252:  71%|███████   | 18271/25880 [3:44:05<1:36:23,  1.32it/s]
1|18272|Loss: 0.7712507843971252:  71%|███████   | 18272/25880 [3:44:06<1:33:02,  1.36it/s]
1|18273|Loss: 0.7202328443527222:  71%|███████   | 18272/25880 [3:44:06<1:33:02,  1.36it/s]
1|18273|Loss: 0.7202328443527222:  71%|███████   | 18273/25880 [3:44:06<1:28:04,  1.44it/s]
1|18274|Loss: 1.004015564918518:  71%|███████   | 18273/25880 [3:44:06<1:28:04,  1.44it/s] 
1|18274|Loss: 1.004015564918518:  71%|███████   | 18274/25880 [3:44:07<1:25:17,  1.49it/s]
1|18275|Loss: 0.8337631821632385:  71%|███████   | 18274/25880 [3:44:07<1:25:17,  1.49it/s]
1|18275|Loss: 0.8337631821632385:  71%|███████   | 18275/25880 [3:44:07<1:23:22,  1.52it/s]
1|18276|Loss: 0.7966076135635376:  71%|███████   | 18275/25880 [3:44:08<1:23:22,  1.52it/s]
1|18276|Loss: 0.7966076135635376:  71%|███████   | 18276/25880 [3:44:08<1:25:51,  1.48it/s]
1|18277|Loss: 0.8214269280433655:  71%|███████   | 18276/25880 [3:44:08<1:25:51,  1.48it/s]
1|18277|Loss: 0.8214269280433655:  71%|███████   | 18277/25880 [3:44:09<1:24:38,  1.50it/s]
1|18278|Loss: 0.9175971746444702:  71%|███████   | 18277/25880 [3:44:09<1:24:38,  1.50it/s]
1|18278|Loss: 0.9175971746444702:  71%|███████   | 18278/25880 [3:44:10<1:31:39,  1.38it/s]
1|18279|Loss: 0.7692005038261414:  71%|███████   | 18278/25880 [3:44:10<1:31:39,  1.38it/s]
1|18279|Loss: 0.7692005038261414:  71%|███████   | 18279/25880 [3:44:10<1:29:55,  1.41it/s]
1|18280|Loss: 0.7002565264701843:  71%|███████   | 18279/25880 [3:44:11<1:29:55,  1.41it/s]
1|18280|Loss: 0.7002565264701843:  71%|███████   | 18280/25880 [3:44:11<1:23:45,  1.51it/s]
1|18281|Loss: 0.9287429451942444:  71%|███████   | 18280/25880 [3:44:11<1:23:45,  1.51it/s]
1|18281|Loss: 0.9287429451942444:  71%|███████   | 18281/25880 [3:44:11<1:21:54,  1.55it/s]
1|18282|Loss: 0.7095592617988586:  71%|███████   | 18281/25880 [3:44:12<1:21:54,  1.55it/s]
1|18282|Loss: 0.7095592617988586:  71%|███████   | 18282/25880 [3:44:12<1:26:41,  1.46it/s]
1|18283|Loss: 0.7974783778190613:  71%|███████   | 18282/25880 [3:44:13<1:26:41,  1.46it/s]
1|18283|Loss: 0.7974783778190613:  71%|███████   | 18283/25880 [3:44:13<1:32:24,  1.37it/s]
1|18284|Loss: 0.7927129864692688:  71%|███████   | 18283/25880 [3:44:14<1:32:24,  1.37it/s]
1|18284|Loss: 0.7927129864692688:  71%|███████   | 18284/25880 [3:44:14<1:39:14,  1.28it/s]
1|18285|Loss: 0.7617092132568359:  71%|███████   | 18284/25880 [3:44:14<1:39:14,  1.28it/s]
1|18285|Loss: 0.7617092132568359:  71%|███████   | 18285/25880 [3:44:15<1:44:31,  1.21it/s]
1|18286|Loss: 0.8947104215621948:  71%|███████   | 18285/25880 [3:44:15<1:44:31,  1.21it/s]
1|18286|Loss: 0.8947104215621948:  71%|███████   | 18286/25880 [3:44:16<1:48:07,  1.17it/s]
1|18287|Loss: 0.7280578017234802:  71%|███████   | 18286/25880 [3:44:16<1:48:07,  1.17it/s]
1|18287|Loss: 0.7280578017234802:  71%|███████   | 18287/25880 [3:44:17<1:44:04,  1.22it/s]
1|18288|Loss: 0.8644734025001526:  71%|███████   | 18287/25880 [3:44:17<1:44:04,  1.22it/s]
1|18288|Loss: 0.8644734025001526:  71%|███████   | 18288/25880 [3:44:17<1:39:23,  1.27it/s]
1|18289|Loss: 0.8391255140304565:  71%|███████   | 18288/25880 [3:44:18<1:39:23,  1.27it/s]
1|18289|Loss: 0.8391255140304565:  71%|███████   | 18289/25880 [3:44:18<1:36:17,  1.31it/s]
1|18290|Loss: 0.8716366291046143:  71%|███████   | 18289/25880 [3:44:18<1:36:17,  1.31it/s]
1|18290|Loss: 0.8716366291046143:  71%|███████   | 18290/25880 [3:44:19<1:34:03,  1.34it/s]
1|18291|Loss: 0.8828505873680115:  71%|███████   | 18290/25880 [3:44:19<1:34:03,  1.34it/s]
1|18291|Loss: 0.8828505873680115:  71%|███████   | 18291/25880 [3:44:19<1:33:17,  1.36it/s]
1|18292|Loss: 0.7744088172912598:  71%|███████   | 18291/25880 [3:44:20<1:33:17,  1.36it/s]
1|18292|Loss: 0.7744088172912598:  71%|███████   | 18292/25880 [3:44:20<1:38:42,  1.28it/s]
1|18293|Loss: 0.8867513537406921:  71%|███████   | 18292/25880 [3:44:21<1:38:42,  1.28it/s]
1|18293|Loss: 0.8867513537406921:  71%|███████   | 18293/25880 [3:44:21<1:39:52,  1.27it/s]
1|18294|Loss: 0.8285894393920898:  71%|███████   | 18293/25880 [3:44:22<1:39:52,  1.27it/s]
1|18294|Loss: 0.8285894393920898:  71%|███████   | 18294/25880 [3:44:22<1:42:32,  1.23it/s]
1|18295|Loss: 0.8741082549095154:  71%|███████   | 18294/25880 [3:44:22<1:42:32,  1.23it/s]
1|18295|Loss: 0.8741082549095154:  71%|███████   | 18295/25880 [3:44:23<1:42:56,  1.23it/s]
1|18296|Loss: 0.9796450734138489:  71%|███████   | 18295/25880 [3:44:23<1:42:56,  1.23it/s]
1|18296|Loss: 0.9796450734138489:  71%|███████   | 18296/25880 [3:44:24<1:42:24,  1.23it/s]
1|18297|Loss: 0.8090167045593262:  71%|███████   | 18296/25880 [3:44:24<1:42:24,  1.23it/s]
1|18297|Loss: 0.8090167045593262:  71%|███████   | 18297/25880 [3:44:24<1:40:11,  1.26it/s]
1|18298|Loss: 0.7830658555030823:  71%|███████   | 18297/25880 [3:44:25<1:40:11,  1.26it/s]
1|18298|Loss: 0.7830658555030823:  71%|███████   | 18298/25880 [3:44:25<1:34:40,  1.33it/s]
1|18299|Loss: 0.7849891185760498:  71%|███████   | 18298/25880 [3:44:25<1:34:40,  1.33it/s]
1|18299|Loss: 0.7849891185760498:  71%|███████   | 18299/25880 [3:44:26<1:32:10,  1.37it/s]
1|18300|Loss: 0.8954306244850159:  71%|███████   | 18299/25880 [3:44:26<1:32:10,  1.37it/s]
1|18300|Loss: 0.8954306244850159:  71%|███████   | 18300/25880 [3:44:26<1:30:58,  1.39it/s]
1|18301|Loss: 0.732918381690979:  71%|███████   | 18300/25880 [3:44:27<1:30:58,  1.39it/s] 
1|18301|Loss: 0.732918381690979:  71%|███████   | 18301/25880 [3:44:27<1:30:55,  1.39it/s]
1|18302|Loss: 0.8980392813682556:  71%|███████   | 18301/25880 [3:44:27<1:30:55,  1.39it/s]
1|18302|Loss: 0.8980392813682556:  71%|███████   | 18302/25880 [3:44:28<1:35:34,  1.32it/s]
1|18303|Loss: 0.8570677638053894:  71%|███████   | 18302/25880 [3:44:28<1:35:34,  1.32it/s]
1|18303|Loss: 0.8570677638053894:  71%|███████   | 18303/25880 [3:44:29<1:40:35,  1.26it/s]
1|18304|Loss: 0.9241802096366882:  71%|███████   | 18303/25880 [3:44:29<1:40:35,  1.26it/s]
1|18304|Loss: 0.9241802096366882:  71%|███████   | 18304/25880 [3:44:30<1:39:41,  1.27it/s]
1|18305|Loss: 0.7479924559593201:  71%|███████   | 18304/25880 [3:44:30<1:39:41,  1.27it/s]
1|18305|Loss: 0.7479924559593201:  71%|███████   | 18305/25880 [3:44:30<1:41:18,  1.25it/s]
1|18306|Loss: 0.8170979022979736:  71%|███████   | 18305/25880 [3:44:31<1:41:18,  1.25it/s]
1|18306|Loss: 0.8170979022979736:  71%|███████   | 18306/25880 [3:44:31<1:36:32,  1.31it/s]
1|18307|Loss: 0.9761785268783569:  71%|███████   | 18306/25880 [3:44:31<1:36:32,  1.31it/s]
1|18307|Loss: 0.9761785268783569:  71%|███████   | 18307/25880 [3:44:32<1:36:25,  1.31it/s]
1|18308|Loss: 0.865692675113678:  71%|███████   | 18307/25880 [3:44:32<1:36:25,  1.31it/s] 
1|18308|Loss: 0.865692675113678:  71%|███████   | 18308/25880 [3:44:32<1:32:43,  1.36it/s]
1|18309|Loss: 1.009569525718689:  71%|███████   | 18308/25880 [3:44:33<1:32:43,  1.36it/s]
1|18309|Loss: 1.009569525718689:  71%|███████   | 18309/25880 [3:44:33<1:35:03,  1.33it/s]
1|18310|Loss: 0.8437336087226868:  71%|███████   | 18309/25880 [3:44:34<1:35:03,  1.33it/s]
1|18310|Loss: 0.8437336087226868:  71%|███████   | 18310/25880 [3:44:34<1:31:27,  1.38it/s]
1|18311|Loss: 0.7786388397216797:  71%|███████   | 18310/25880 [3:44:34<1:31:27,  1.38it/s]
1|18311|Loss: 0.7786388397216797:  71%|███████   | 18311/25880 [3:44:35<1:26:50,  1.45it/s]
1|18312|Loss: 0.9455322027206421:  71%|███████   | 18311/25880 [3:44:35<1:26:50,  1.45it/s]
1|18312|Loss: 0.9455322027206421:  71%|███████   | 18312/25880 [3:44:35<1:26:13,  1.46it/s]
1|18313|Loss: 0.8462584614753723:  71%|███████   | 18312/25880 [3:44:36<1:26:13,  1.46it/s]
1|18313|Loss: 0.8462584614753723:  71%|███████   | 18313/25880 [3:44:36<1:23:38,  1.51it/s]
1|18314|Loss: 0.8500379920005798:  71%|███████   | 18313/25880 [3:44:36<1:23:38,  1.51it/s]
1|18314|Loss: 0.8500379920005798:  71%|███████   | 18314/25880 [3:44:37<1:28:05,  1.43it/s]
1|18315|Loss: 0.9844198822975159:  71%|███████   | 18314/25880 [3:44:37<1:28:05,  1.43it/s]
1|18315|Loss: 0.9844198822975159:  71%|███████   | 18315/25880 [3:44:37<1:33:18,  1.35it/s]
1|18316|Loss: 1.00523841381073:  71%|███████   | 18315/25880 [3:44:38<1:33:18,  1.35it/s]  
1|18316|Loss: 1.00523841381073:  71%|███████   | 18316/25880 [3:44:38<1:37:34,  1.29it/s]
1|18317|Loss: 0.7304590940475464:  71%|███████   | 18316/25880 [3:44:39<1:37:34,  1.29it/s]
1|18317|Loss: 0.7304590940475464:  71%|███████   | 18317/25880 [3:44:39<1:41:13,  1.25it/s]
1|18318|Loss: 0.8124487996101379:  71%|███████   | 18317/25880 [3:44:40<1:41:13,  1.25it/s]
1|18318|Loss: 0.8124487996101379:  71%|███████   | 18318/25880 [3:44:40<1:36:57,  1.30it/s]
1|18319|Loss: 0.8408674001693726:  71%|███████   | 18318/25880 [3:44:40<1:36:57,  1.30it/s]
1|18319|Loss: 0.8408674001693726:  71%|███████   | 18319/25880 [3:44:41<1:42:00,  1.24it/s]
1|18320|Loss: 0.9984205961227417:  71%|███████   | 18319/25880 [3:44:41<1:42:00,  1.24it/s]
1|18320|Loss: 0.9984205961227417:  71%|███████   | 18320/25880 [3:44:42<1:41:25,  1.24it/s]
1|18321|Loss: 0.8489247560501099:  71%|███████   | 18320/25880 [3:44:42<1:41:25,  1.24it/s]
1|18321|Loss: 0.8489247560501099:  71%|███████   | 18321/25880 [3:44:42<1:40:43,  1.25it/s]
1|18322|Loss: 0.7701113224029541:  71%|███████   | 18321/25880 [3:44:43<1:40:43,  1.25it/s]
1|18322|Loss: 0.7701113224029541:  71%|███████   | 18322/25880 [3:44:43<1:38:35,  1.28it/s]
1|18323|Loss: 0.817283570766449:  71%|███████   | 18322/25880 [3:44:43<1:38:35,  1.28it/s] 
1|18323|Loss: 0.817283570766449:  71%|███████   | 18323/25880 [3:44:44<1:33:57,  1.34it/s]
1|18324|Loss: 0.8787279725074768:  71%|███████   | 18323/25880 [3:44:44<1:33:57,  1.34it/s]
1|18324|Loss: 0.8787279725074768:  71%|███████   | 18324/25880 [3:44:44<1:29:57,  1.40it/s]
1|18325|Loss: 0.821997880935669:  71%|███████   | 18324/25880 [3:44:45<1:29:57,  1.40it/s] 
1|18325|Loss: 0.821997880935669:  71%|███████   | 18325/25880 [3:44:45<1:26:22,  1.46it/s]
1|18326|Loss: 0.8379124999046326:  71%|███████   | 18325/25880 [3:44:45<1:26:22,  1.46it/s]
1|18326|Loss: 0.8379124999046326:  71%|███████   | 18326/25880 [3:44:46<1:31:41,  1.37it/s]
1|18327|Loss: 0.8325467705726624:  71%|███████   | 18326/25880 [3:44:46<1:31:41,  1.37it/s]
1|18327|Loss: 0.8325467705726624:  71%|███████   | 18327/25880 [3:44:47<1:33:08,  1.35it/s]
1|18328|Loss: 0.7994845509529114:  71%|███████   | 18327/25880 [3:44:47<1:33:08,  1.35it/s]
1|18328|Loss: 0.7994845509529114:  71%|███████   | 18328/25880 [3:44:47<1:31:59,  1.37it/s]
1|18329|Loss: 0.8002898693084717:  71%|███████   | 18328/25880 [3:44:48<1:31:59,  1.37it/s]
1|18329|Loss: 0.8002898693084717:  71%|███████   | 18329/25880 [3:44:48<1:37:07,  1.30it/s]
1|18330|Loss: 0.7366520166397095:  71%|███████   | 18329/25880 [3:44:49<1:37:07,  1.30it/s]
1|18330|Loss: 0.7366520166397095:  71%|███████   | 18330/25880 [3:44:49<1:36:42,  1.30it/s]
1|18331|Loss: 0.726117730140686:  71%|███████   | 18330/25880 [3:44:49<1:36:42,  1.30it/s] 
1|18331|Loss: 0.726117730140686:  71%|███████   | 18331/25880 [3:44:49<1:28:22,  1.42it/s]
1|18332|Loss: 0.870144248008728:  71%|███████   | 18331/25880 [3:44:50<1:28:22,  1.42it/s]
1|18332|Loss: 0.870144248008728:  71%|███████   | 18332/25880 [3:44:50<1:27:38,  1.44it/s]
1|18333|Loss: 0.7586997151374817:  71%|███████   | 18332/25880 [3:44:50<1:27:38,  1.44it/s]
1|18333|Loss: 0.7586997151374817:  71%|███████   | 18333/25880 [3:44:51<1:21:21,  1.55it/s]
1|18334|Loss: 0.8871708512306213:  71%|███████   | 18333/25880 [3:44:51<1:21:21,  1.55it/s]
1|18334|Loss: 0.8871708512306213:  71%|███████   | 18334/25880 [3:44:51<1:26:58,  1.45it/s]
1|18335|Loss: 0.7447355389595032:  71%|███████   | 18334/25880 [3:44:52<1:26:58,  1.45it/s]
1|18335|Loss: 0.7447355389595032:  71%|███████   | 18335/25880 [3:44:52<1:25:41,  1.47it/s]
1|18336|Loss: 0.7186391353607178:  71%|███████   | 18335/25880 [3:44:52<1:25:41,  1.47it/s]
1|18336|Loss: 0.7186391353607178:  71%|███████   | 18336/25880 [3:44:53<1:20:14,  1.57it/s]
1|18337|Loss: 0.8976673483848572:  71%|███████   | 18336/25880 [3:44:53<1:20:14,  1.57it/s]
1|18337|Loss: 0.8976673483848572:  71%|███████   | 18337/25880 [3:44:53<1:22:23,  1.53it/s]
1|18338|Loss: 0.9014453291893005:  71%|███████   | 18337/25880 [3:44:54<1:22:23,  1.53it/s]
1|18338|Loss: 0.9014453291893005:  71%|███████   | 18338/25880 [3:44:54<1:20:14,  1.57it/s]
1|18339|Loss: 0.7391302585601807:  71%|███████   | 18338/25880 [3:44:54<1:20:14,  1.57it/s]
1|18339|Loss: 0.7391302585601807:  71%|███████   | 18339/25880 [3:44:54<1:10:29,  1.78it/s]
1|18340|Loss: 0.7550749778747559:  71%|███████   | 18339/25880 [3:44:55<1:10:29,  1.78it/s]
1|18340|Loss: 0.7550749778747559:  71%|███████   | 18340/25880 [3:44:55<1:10:01,  1.79it/s]
1|18341|Loss: 0.8882129192352295:  71%|███████   | 18340/25880 [3:44:55<1:10:01,  1.79it/s]
1|18341|Loss: 0.8882129192352295:  71%|███████   | 18341/25880 [3:44:56<1:15:51,  1.66it/s]
1|18342|Loss: 0.8074057698249817:  71%|███████   | 18341/25880 [3:44:56<1:15:51,  1.66it/s]
1|18342|Loss: 0.8074057698249817:  71%|███████   | 18342/25880 [3:44:56<1:23:53,  1.50it/s]
1|18343|Loss: 0.8914973735809326:  71%|███████   | 18342/25880 [3:44:57<1:23:53,  1.50it/s]
1|18343|Loss: 0.8914973735809326:  71%|███████   | 18343/25880 [3:44:57<1:27:26,  1.44it/s]
1|18344|Loss: 0.8001338243484497:  71%|███████   | 18343/25880 [3:44:58<1:27:26,  1.44it/s]
1|18344|Loss: 0.8001338243484497:  71%|███████   | 18344/25880 [3:44:58<1:31:03,  1.38it/s]
1|18345|Loss: 0.8716099262237549:  71%|███████   | 18344/25880 [3:44:58<1:31:03,  1.38it/s]
1|18345|Loss: 0.8716099262237549:  71%|███████   | 18345/25880 [3:44:59<1:31:50,  1.37it/s]
1|18346|Loss: 0.8814017176628113:  71%|███████   | 18345/25880 [3:44:59<1:31:50,  1.37it/s]
1|18346|Loss: 0.8814017176628113:  71%|███████   | 18346/25880 [3:45:00<1:37:46,  1.28it/s]
1|18347|Loss: 0.7091206908226013:  71%|███████   | 18346/25880 [3:45:00<1:37:46,  1.28it/s]
1|18347|Loss: 0.7091206908226013:  71%|███████   | 18347/25880 [3:45:00<1:31:57,  1.37it/s]
1|18348|Loss: 0.9466138482093811:  71%|███████   | 18347/25880 [3:45:01<1:31:57,  1.37it/s]
1|18348|Loss: 0.9466138482093811:  71%|███████   | 18348/25880 [3:45:01<1:30:08,  1.39it/s]
1|18349|Loss: 0.9335995316505432:  71%|███████   | 18348/25880 [3:45:01<1:30:08,  1.39it/s]
1|18349|Loss: 0.9335995316505432:  71%|███████   | 18349/25880 [3:45:02<1:24:58,  1.48it/s]
1|18350|Loss: 0.8142080903053284:  71%|███████   | 18349/25880 [3:45:02<1:24:58,  1.48it/s]
1|18350|Loss: 0.8142080903053284:  71%|███████   | 18350/25880 [3:45:02<1:18:05,  1.61it/s]
1|18351|Loss: 0.871474027633667:  71%|███████   | 18350/25880 [3:45:02<1:18:05,  1.61it/s] 
1|18351|Loss: 0.871474027633667:  71%|███████   | 18351/25880 [3:45:03<1:20:11,  1.56it/s]
1|18352|Loss: 0.9640485644340515:  71%|███████   | 18351/25880 [3:45:03<1:20:11,  1.56it/s]
1|18352|Loss: 0.9640485644340515:  71%|███████   | 18352/25880 [3:45:03<1:20:45,  1.55it/s]
1|18353|Loss: 0.866018533706665:  71%|███████   | 18352/25880 [3:45:04<1:20:45,  1.55it/s] 
1|18353|Loss: 0.866018533706665:  71%|███████   | 18353/25880 [3:45:04<1:23:12,  1.51it/s]
1|18354|Loss: 0.8737569451332092:  71%|███████   | 18353/25880 [3:45:04<1:23:12,  1.51it/s]
1|18354|Loss: 0.8737569451332092:  71%|███████   | 18354/25880 [3:45:05<1:29:28,  1.40it/s]
1|18355|Loss: 0.8870428204536438:  71%|███████   | 18354/25880 [3:45:05<1:29:28,  1.40it/s]
1|18355|Loss: 0.8870428204536438:  71%|███████   | 18355/25880 [3:45:06<1:28:07,  1.42it/s]
1|18356|Loss: 0.841095507144928:  71%|███████   | 18355/25880 [3:45:06<1:28:07,  1.42it/s] 
1|18356|Loss: 0.841095507144928:  71%|███████   | 18356/25880 [3:45:06<1:21:38,  1.54it/s]
1|18357|Loss: 0.8856555223464966:  71%|███████   | 18356/25880 [3:45:06<1:21:38,  1.54it/s]
1|18357|Loss: 0.8856555223464966:  71%|███████   | 18357/25880 [3:45:07<1:18:20,  1.60it/s]
1|18358|Loss: 0.8598955869674683:  71%|███████   | 18357/25880 [3:45:07<1:18:20,  1.60it/s]
1|18358|Loss: 0.8598955869674683:  71%|███████   | 18358/25880 [3:45:08<1:26:42,  1.45it/s]
1|18359|Loss: 0.7657942771911621:  71%|███████   | 18358/25880 [3:45:08<1:26:42,  1.45it/s]
1|18359|Loss: 0.7657942771911621:  71%|███████   | 18359/25880 [3:45:08<1:29:30,  1.40it/s]
1|18360|Loss: 0.7805743217468262:  71%|███████   | 18359/25880 [3:45:09<1:29:30,  1.40it/s]
1|18360|Loss: 0.7805743217468262:  71%|███████   | 18360/25880 [3:45:09<1:26:01,  1.46it/s]
1|18361|Loss: 0.9226170182228088:  71%|███████   | 18360/25880 [3:45:09<1:26:01,  1.46it/s]
1|18361|Loss: 0.9226170182228088:  71%|███████   | 18361/25880 [3:45:10<1:26:59,  1.44it/s]
1|18362|Loss: 0.836591362953186:  71%|███████   | 18361/25880 [3:45:10<1:26:59,  1.44it/s] 
1|18362|Loss: 0.836591362953186:  71%|███████   | 18362/25880 [3:45:10<1:26:02,  1.46it/s]
1|18363|Loss: 0.8928287625312805:  71%|███████   | 18362/25880 [3:45:11<1:26:02,  1.46it/s]
1|18363|Loss: 0.8928287625312805:  71%|███████   | 18363/25880 [3:45:11<1:31:22,  1.37it/s]
1|18364|Loss: 0.8911923170089722:  71%|███████   | 18363/25880 [3:45:12<1:31:22,  1.37it/s]
1|18364|Loss: 0.8911923170089722:  71%|███████   | 18364/25880 [3:45:12<1:32:30,  1.35it/s]
1|18365|Loss: 0.846747875213623:  71%|███████   | 18364/25880 [3:45:12<1:32:30,  1.35it/s] 
1|18365|Loss: 0.846747875213623:  71%|███████   | 18365/25880 [3:45:12<1:27:50,  1.43it/s]
1|18366|Loss: 0.8301700949668884:  71%|███████   | 18365/25880 [3:45:13<1:27:50,  1.43it/s]
1|18366|Loss: 0.8301700949668884:  71%|███████   | 18366/25880 [3:45:13<1:30:03,  1.39it/s]
1|18367|Loss: 0.8830680847167969:  71%|███████   | 18366/25880 [3:45:14<1:30:03,  1.39it/s]
1|18367|Loss: 0.8830680847167969:  71%|███████   | 18367/25880 [3:45:14<1:30:52,  1.38it/s]
1|18368|Loss: 0.794521152973175:  71%|███████   | 18367/25880 [3:45:14<1:30:52,  1.38it/s] 
1|18368|Loss: 0.794521152973175:  71%|███████   | 18368/25880 [3:45:15<1:26:38,  1.44it/s]
1|18369|Loss: 0.8312830328941345:  71%|███████   | 18368/25880 [3:45:15<1:26:38,  1.44it/s]
1|18369|Loss: 0.8312830328941345:  71%|███████   | 18369/25880 [3:45:15<1:27:02,  1.44it/s]
1|18370|Loss: 0.6228038668632507:  71%|███████   | 18369/25880 [3:45:16<1:27:02,  1.44it/s]
1|18370|Loss: 0.6228038668632507:  71%|███████   | 18370/25880 [3:45:16<1:22:49,  1.51it/s]
1|18371|Loss: 0.9363179206848145:  71%|███████   | 18370/25880 [3:45:16<1:22:49,  1.51it/s]
1|18371|Loss: 0.9363179206848145:  71%|███████   | 18371/25880 [3:45:17<1:26:11,  1.45it/s]
1|18372|Loss: 0.725547194480896:  71%|███████   | 18371/25880 [3:45:17<1:26:11,  1.45it/s] 
1|18372|Loss: 0.725547194480896:  71%|███████   | 18372/25880 [3:45:17<1:27:38,  1.43it/s]
1|18373|Loss: 0.8068042397499084:  71%|███████   | 18372/25880 [3:45:18<1:27:38,  1.43it/s]
1|18373|Loss: 0.8068042397499084:  71%|███████   | 18373/25880 [3:45:18<1:28:47,  1.41it/s]
1|18374|Loss: 0.9472618103027344:  71%|███████   | 18373/25880 [3:45:19<1:28:47,  1.41it/s]
1|18374|Loss: 0.9472618103027344:  71%|███████   | 18374/25880 [3:45:19<1:34:23,  1.33it/s]
1|18375|Loss: 0.8544328808784485:  71%|███████   | 18374/25880 [3:45:19<1:34:23,  1.33it/s]
1|18375|Loss: 0.8544328808784485:  71%|███████   | 18375/25880 [3:45:20<1:35:16,  1.31it/s]
1|18376|Loss: 0.8886106014251709:  71%|███████   | 18375/25880 [3:45:20<1:35:16,  1.31it/s]
1|18376|Loss: 0.8886106014251709:  71%|███████   | 18376/25880 [3:45:21<1:36:01,  1.30it/s]
1|18377|Loss: 0.9995830655097961:  71%|███████   | 18376/25880 [3:45:21<1:36:01,  1.30it/s]
1|18377|Loss: 0.9995830655097961:  71%|███████   | 18377/25880 [3:45:21<1:35:33,  1.31it/s]
1|18378|Loss: 0.7119470238685608:  71%|███████   | 18377/25880 [3:45:22<1:35:33,  1.31it/s]
1|18378|Loss: 0.7119470238685608:  71%|███████   | 18378/25880 [3:45:22<1:34:44,  1.32it/s]
1|18379|Loss: 0.8346218466758728:  71%|███████   | 18378/25880 [3:45:22<1:34:44,  1.32it/s]
1|18379|Loss: 0.8346218466758728:  71%|███████   | 18379/25880 [3:45:23<1:30:41,  1.38it/s]
1|18380|Loss: 0.7828042507171631:  71%|███████   | 18379/25880 [3:45:23<1:30:41,  1.38it/s]
1|18380|Loss: 0.7828042507171631:  71%|███████   | 18380/25880 [3:45:23<1:34:37,  1.32it/s]
1|18381|Loss: 0.6625034213066101:  71%|███████   | 18380/25880 [3:45:24<1:34:37,  1.32it/s]
1|18381|Loss: 0.6625034213066101:  71%|███████   | 18381/25880 [3:45:24<1:34:58,  1.32it/s]
1|18382|Loss: 0.8309600353240967:  71%|███████   | 18381/25880 [3:45:25<1:34:58,  1.32it/s]
1|18382|Loss: 0.8309600353240967:  71%|███████   | 18382/25880 [3:45:25<1:36:53,  1.29it/s]
1|18383|Loss: 0.8089684247970581:  71%|███████   | 18382/25880 [3:45:25<1:36:53,  1.29it/s]
1|18383|Loss: 0.8089684247970581:  71%|███████   | 18383/25880 [3:45:26<1:36:13,  1.30it/s]
1|18384|Loss: 0.8667705655097961:  71%|███████   | 18383/25880 [3:45:26<1:36:13,  1.30it/s]
1|18384|Loss: 0.8667705655097961:  71%|███████   | 18384/25880 [3:45:26<1:31:45,  1.36it/s]
1|18385|Loss: 0.949407160282135:  71%|███████   | 18384/25880 [3:45:27<1:31:45,  1.36it/s] 
1|18385|Loss: 0.949407160282135:  71%|███████   | 18385/25880 [3:45:27<1:27:24,  1.43it/s]
1|18386|Loss: 0.8409773707389832:  71%|███████   | 18385/25880 [3:45:27<1:27:24,  1.43it/s]
1|18386|Loss: 0.8409773707389832:  71%|███████   | 18386/25880 [3:45:28<1:19:29,  1.57it/s]
1|18387|Loss: 0.72818922996521:  71%|███████   | 18386/25880 [3:45:28<1:19:29,  1.57it/s]  
1|18387|Loss: 0.72818922996521:  71%|███████   | 18387/25880 [3:45:28<1:19:48,  1.56it/s]
1|18388|Loss: 0.7175896167755127:  71%|███████   | 18387/25880 [3:45:29<1:19:48,  1.56it/s]
1|18388|Loss: 0.7175896167755127:  71%|███████   | 18388/25880 [3:45:29<1:23:01,  1.50it/s]
1|18389|Loss: 0.7836459875106812:  71%|███████   | 18388/25880 [3:45:29<1:23:01,  1.50it/s]
1|18389|Loss: 0.7836459875106812:  71%|███████   | 18389/25880 [3:45:30<1:22:42,  1.51it/s]
1|18390|Loss: 0.8066474795341492:  71%|███████   | 18389/25880 [3:45:30<1:22:42,  1.51it/s]
1|18390|Loss: 0.8066474795341492:  71%|███████   | 18390/25880 [3:45:30<1:24:52,  1.47it/s]
1|18391|Loss: 0.8459933400154114:  71%|███████   | 18390/25880 [3:45:31<1:24:52,  1.47it/s]
1|18391|Loss: 0.8459933400154114:  71%|███████   | 18391/25880 [3:45:31<1:26:49,  1.44it/s]
1|18392|Loss: 0.9799555540084839:  71%|███████   | 18391/25880 [3:45:31<1:26:49,  1.44it/s]
1|18392|Loss: 0.9799555540084839:  71%|███████   | 18392/25880 [3:45:32<1:28:10,  1.42it/s]
1|18393|Loss: 0.7244393825531006:  71%|███████   | 18392/25880 [3:45:32<1:28:10,  1.42it/s]
1|18393|Loss: 0.7244393825531006:  71%|███████   | 18393/25880 [3:45:33<1:43:48,  1.20it/s]
1|18394|Loss: 0.9087335467338562:  71%|███████   | 18393/25880 [3:45:33<1:43:48,  1.20it/s]
1|18394|Loss: 0.9087335467338562:  71%|███████   | 18394/25880 [3:45:34<1:41:22,  1.23it/s]
1|18395|Loss: 0.8410253524780273:  71%|███████   | 18394/25880 [3:45:34<1:41:22,  1.23it/s]
1|18395|Loss: 0.8410253524780273:  71%|███████   | 18395/25880 [3:45:34<1:34:59,  1.31it/s]
1|18396|Loss: 0.7809617519378662:  71%|███████   | 18395/25880 [3:45:35<1:34:59,  1.31it/s]
1|18396|Loss: 0.7809617519378662:  71%|███████   | 18396/25880 [3:45:35<1:33:10,  1.34it/s]
1|18397|Loss: 0.5993191599845886:  71%|███████   | 18396/25880 [3:45:35<1:33:10,  1.34it/s]
1|18397|Loss: 0.5993191599845886:  71%|███████   | 18397/25880 [3:45:36<1:37:08,  1.28it/s]
1|18398|Loss: 0.7900223135948181:  71%|███████   | 18397/25880 [3:45:36<1:37:08,  1.28it/s]
1|18398|Loss: 0.7900223135948181:  71%|███████   | 18398/25880 [3:45:37<1:40:14,  1.24it/s]
1|18399|Loss: 0.7728525400161743:  71%|███████   | 18398/25880 [3:45:37<1:40:14,  1.24it/s]
1|18399|Loss: 0.7728525400161743:  71%|███████   | 18399/25880 [3:45:38<1:41:35,  1.23it/s]
1|18400|Loss: 0.795937180519104:  71%|███████   | 18399/25880 [3:45:38<1:41:35,  1.23it/s] 
1|18400|Loss: 0.795937180519104:  71%|███████   | 18400/25880 [3:45:38<1:38:22,  1.27it/s]
1|18401|Loss: 0.8647507429122925:  71%|███████   | 18400/25880 [3:45:39<1:38:22,  1.27it/s]
1|18401|Loss: 0.8647507429122925:  71%|███████   | 18401/25880 [3:45:39<1:36:09,  1.30it/s]
1|18402|Loss: 0.9213965535163879:  71%|███████   | 18401/25880 [3:45:39<1:36:09,  1.30it/s]
1|18402|Loss: 0.9213965535163879:  71%|███████   | 18402/25880 [3:45:40<1:33:40,  1.33it/s]
1|18403|Loss: 0.9991993308067322:  71%|███████   | 18402/25880 [3:45:40<1:33:40,  1.33it/s]
1|18403|Loss: 0.9991993308067322:  71%|███████   | 18403/25880 [3:45:41<1:34:35,  1.32it/s]
1|18404|Loss: 0.9372684359550476:  71%|███████   | 18403/25880 [3:45:41<1:34:35,  1.32it/s]
1|18404|Loss: 0.9372684359550476:  71%|███████   | 18404/25880 [3:45:41<1:33:59,  1.33it/s]
1|18405|Loss: 0.8227425217628479:  71%|███████   | 18404/25880 [3:45:42<1:33:59,  1.33it/s]
1|18405|Loss: 0.8227425217628479:  71%|███████   | 18405/25880 [3:45:42<1:33:02,  1.34it/s]
1|18406|Loss: 0.8173524737358093:  71%|███████   | 18405/25880 [3:45:42<1:33:02,  1.34it/s]
1|18406|Loss: 0.8173524737358093:  71%|███████   | 18406/25880 [3:45:43<1:34:23,  1.32it/s]
1|18407|Loss: 0.846423864364624:  71%|███████   | 18406/25880 [3:45:43<1:34:23,  1.32it/s] 
1|18407|Loss: 0.846423864364624:  71%|███████   | 18407/25880 [3:45:43<1:30:34,  1.38it/s]
1|18408|Loss: 0.8769108653068542:  71%|███████   | 18407/25880 [3:45:44<1:30:34,  1.38it/s]
1|18408|Loss: 0.8769108653068542:  71%|███████   | 18408/25880 [3:45:44<1:21:39,  1.53it/s]
1|18409|Loss: 0.9635900855064392:  71%|███████   | 18408/25880 [3:45:44<1:21:39,  1.53it/s]
1|18409|Loss: 0.9635900855064392:  71%|███████   | 18409/25880 [3:45:45<1:19:34,  1.56it/s]
1|18410|Loss: 0.8248242139816284:  71%|███████   | 18409/25880 [3:45:45<1:19:34,  1.56it/s]
1|18410|Loss: 0.8248242139816284:  71%|███████   | 18410/25880 [3:45:45<1:21:30,  1.53it/s]
1|18411|Loss: 0.8634526133537292:  71%|███████   | 18410/25880 [3:45:46<1:21:30,  1.53it/s]
1|18411|Loss: 0.8634526133537292:  71%|███████   | 18411/25880 [3:45:46<1:24:05,  1.48it/s]
1|18412|Loss: 0.9554455280303955:  71%|███████   | 18411/25880 [3:45:46<1:24:05,  1.48it/s]
1|18412|Loss: 0.9554455280303955:  71%|███████   | 18412/25880 [3:45:47<1:25:12,  1.46it/s]
1|18413|Loss: 0.8522761464118958:  71%|███████   | 18412/25880 [3:45:47<1:25:12,  1.46it/s]
1|18413|Loss: 0.8522761464118958:  71%|███████   | 18413/25880 [3:45:47<1:23:57,  1.48it/s]
1|18414|Loss: 0.9343254566192627:  71%|███████   | 18413/25880 [3:45:48<1:23:57,  1.48it/s]
1|18414|Loss: 0.9343254566192627:  71%|███████   | 18414/25880 [3:45:48<1:27:11,  1.43it/s]
1|18415|Loss: 1.0011881589889526:  71%|███████   | 18414/25880 [3:45:49<1:27:11,  1.43it/s]
1|18415|Loss: 1.0011881589889526:  71%|███████   | 18415/25880 [3:45:49<1:31:52,  1.35it/s]
1|18416|Loss: 0.8687993884086609:  71%|███████   | 18415/25880 [3:45:49<1:31:52,  1.35it/s]
1|18416|Loss: 0.8687993884086609:  71%|███████   | 18416/25880 [3:45:50<1:29:30,  1.39it/s]
1|18417|Loss: 0.9927100539207458:  71%|███████   | 18416/25880 [3:45:50<1:29:30,  1.39it/s]
1|18417|Loss: 0.9927100539207458:  71%|███████   | 18417/25880 [3:45:50<1:32:51,  1.34it/s]
1|18418|Loss: 0.9233365058898926:  71%|███████   | 18417/25880 [3:45:51<1:32:51,  1.34it/s]
1|18418|Loss: 0.9233365058898926:  71%|███████   | 18418/25880 [3:45:51<1:33:35,  1.33it/s]
1|18419|Loss: 0.7778971195220947:  71%|███████   | 18418/25880 [3:45:52<1:33:35,  1.33it/s]
1|18419|Loss: 0.7778971195220947:  71%|███████   | 18419/25880 [3:45:52<1:29:43,  1.39it/s]
1|18420|Loss: 0.8241788744926453:  71%|███████   | 18419/25880 [3:45:52<1:29:43,  1.39it/s]
1|18420|Loss: 0.8241788744926453:  71%|███████   | 18420/25880 [3:45:53<1:29:16,  1.39it/s]
1|18421|Loss: 0.73470139503479:  71%|███████   | 18420/25880 [3:45:53<1:29:16,  1.39it/s]  
1|18421|Loss: 0.73470139503479:  71%|███████   | 18421/25880 [3:45:53<1:26:19,  1.44it/s]
1|18422|Loss: 0.8555288910865784:  71%|███████   | 18421/25880 [3:45:54<1:26:19,  1.44it/s]
1|18422|Loss: 0.8555288910865784:  71%|███████   | 18422/25880 [3:45:54<1:27:10,  1.43it/s]
1|18423|Loss: 0.7826481461524963:  71%|███████   | 18422/25880 [3:45:54<1:27:10,  1.43it/s]
1|18423|Loss: 0.7826481461524963:  71%|███████   | 18423/25880 [3:45:55<1:30:00,  1.38it/s]
1|18424|Loss: 0.8764117956161499:  71%|███████   | 18423/25880 [3:45:55<1:30:00,  1.38it/s]
1|18424|Loss: 0.8764117956161499:  71%|███████   | 18424/25880 [3:45:55<1:28:13,  1.41it/s]
1|18425|Loss: 0.8441959619522095:  71%|███████   | 18424/25880 [3:45:56<1:28:13,  1.41it/s]
1|18425|Loss: 0.8441959619522095:  71%|███████   | 18425/25880 [3:45:56<1:28:35,  1.40it/s]
1|18426|Loss: 0.8913871049880981:  71%|███████   | 18425/25880 [3:45:56<1:28:35,  1.40it/s]
1|18426|Loss: 0.8913871049880981:  71%|███████   | 18426/25880 [3:45:57<1:28:24,  1.41it/s]
1|18427|Loss: 0.7987308502197266:  71%|███████   | 18426/25880 [3:45:57<1:28:24,  1.41it/s]
1|18427|Loss: 0.7987308502197266:  71%|███████   | 18427/25880 [3:45:57<1:26:04,  1.44it/s]
1|18428|Loss: 0.8652167320251465:  71%|███████   | 18427/25880 [3:45:58<1:26:04,  1.44it/s]
1|18428|Loss: 0.8652167320251465:  71%|███████   | 18428/25880 [3:45:58<1:22:27,  1.51it/s]
1|18429|Loss: 0.6913201212882996:  71%|███████   | 18428/25880 [3:45:58<1:22:27,  1.51it/s]
1|18429|Loss: 0.6913201212882996:  71%|███████   | 18429/25880 [3:45:59<1:24:13,  1.47it/s]
1|18430|Loss: 0.9509202241897583:  71%|███████   | 18429/25880 [3:45:59<1:24:13,  1.47it/s]
1|18430|Loss: 0.9509202241897583:  71%|███████   | 18430/25880 [3:45:59<1:23:37,  1.48it/s]
1|18431|Loss: 0.8505536913871765:  71%|███████   | 18430/25880 [3:46:00<1:23:37,  1.48it/s]
1|18431|Loss: 0.8505536913871765:  71%|███████   | 18431/25880 [3:46:00<1:18:00,  1.59it/s]
1|18432|Loss: 0.8234308362007141:  71%|███████   | 18431/25880 [3:46:00<1:18:00,  1.59it/s]
1|18432|Loss: 0.8234308362007141:  71%|███████   | 18432/25880 [3:46:01<1:24:12,  1.47it/s]
1|18433|Loss: 0.8059589862823486:  71%|███████   | 18432/25880 [3:46:01<1:24:12,  1.47it/s]
1|18433|Loss: 0.8059589862823486:  71%|███████   | 18433/25880 [3:46:01<1:23:56,  1.48it/s]
1|18434|Loss: 0.7907251119613647:  71%|███████   | 18433/25880 [3:46:02<1:23:56,  1.48it/s]
1|18434|Loss: 0.7907251119613647:  71%|███████   | 18434/25880 [3:46:02<1:25:21,  1.45it/s]
1|18435|Loss: 0.803252637386322:  71%|███████   | 18434/25880 [3:46:02<1:25:21,  1.45it/s] 
1|18435|Loss: 0.803252637386322:  71%|███████   | 18435/25880 [3:46:03<1:27:49,  1.41it/s]
1|18436|Loss: 0.7280554175376892:  71%|███████   | 18435/25880 [3:46:03<1:27:49,  1.41it/s]
1|18436|Loss: 0.7280554175376892:  71%|███████   | 18436/25880 [3:46:04<1:51:59,  1.11it/s]
1|18437|Loss: 0.8392741680145264:  71%|███████   | 18436/25880 [3:46:05<1:51:59,  1.11it/s]
1|18437|Loss: 0.8392741680145264:  71%|███████   | 18437/25880 [3:46:05<1:43:19,  1.20it/s]
1|18438|Loss: 0.8286956548690796:  71%|███████   | 18437/25880 [3:46:05<1:43:19,  1.20it/s]
1|18438|Loss: 0.8286956548690796:  71%|███████   | 18438/25880 [3:46:06<1:40:28,  1.23it/s]
1|18439|Loss: 0.8610354661941528:  71%|███████   | 18438/25880 [3:46:06<1:40:28,  1.23it/s]
1|18439|Loss: 0.8610354661941528:  71%|███████   | 18439/25880 [3:46:06<1:29:53,  1.38it/s]
1|18440|Loss: 0.8124849200248718:  71%|███████   | 18439/25880 [3:46:06<1:29:53,  1.38it/s]
1|18440|Loss: 0.8124849200248718:  71%|███████▏  | 18440/25880 [3:46:07<1:27:04,  1.42it/s]
1|18441|Loss: 0.9373533725738525:  71%|███████▏  | 18440/25880 [3:46:07<1:27:04,  1.42it/s]
1|18441|Loss: 0.9373533725738525:  71%|███████▏  | 18441/25880 [3:46:08<1:27:58,  1.41it/s]
1|18442|Loss: 0.8062533736228943:  71%|███████▏  | 18441/25880 [3:46:08<1:27:58,  1.41it/s]
1|18442|Loss: 0.8062533736228943:  71%|███████▏  | 18442/25880 [3:46:08<1:25:42,  1.45it/s]
1|18443|Loss: 1.0943512916564941:  71%|███████▏  | 18442/25880 [3:46:08<1:25:42,  1.45it/s]
1|18443|Loss: 1.0943512916564941:  71%|███████▏  | 18443/25880 [3:46:09<1:20:38,  1.54it/s]
1|18444|Loss: 0.8107876181602478:  71%|███████▏  | 18443/25880 [3:46:09<1:20:38,  1.54it/s]
1|18444|Loss: 0.8107876181602478:  71%|███████▏  | 18444/25880 [3:46:09<1:18:37,  1.58it/s]
1|18445|Loss: 0.9022719860076904:  71%|███████▏  | 18444/25880 [3:46:10<1:18:37,  1.58it/s]
1|18445|Loss: 0.9022719860076904:  71%|███████▏  | 18445/25880 [3:46:10<1:21:26,  1.52it/s]
1|18446|Loss: 0.7906279563903809:  71%|███████▏  | 18445/25880 [3:46:10<1:21:26,  1.52it/s]
1|18446|Loss: 0.7906279563903809:  71%|███████▏  | 18446/25880 [3:46:11<1:19:57,  1.55it/s]
1|18447|Loss: 0.8945844769477844:  71%|███████▏  | 18446/25880 [3:46:11<1:19:57,  1.55it/s]
1|18447|Loss: 0.8945844769477844:  71%|███████▏  | 18447/25880 [3:46:11<1:15:32,  1.64it/s]
1|18448|Loss: 0.8286622166633606:  71%|███████▏  | 18447/25880 [3:46:12<1:15:32,  1.64it/s]
1|18448|Loss: 0.8286622166633606:  71%|███████▏  | 18448/25880 [3:46:12<1:18:39,  1.57it/s]
1|18449|Loss: 0.8210646510124207:  71%|███████▏  | 18448/25880 [3:46:12<1:18:39,  1.57it/s]
1|18449|Loss: 0.8210646510124207:  71%|███████▏  | 18449/25880 [3:46:13<1:22:34,  1.50it/s]
1|18450|Loss: 0.9957436919212341:  71%|███████▏  | 18449/25880 [3:46:13<1:22:34,  1.50it/s]
1|18450|Loss: 0.9957436919212341:  71%|███████▏  | 18450/25880 [3:46:13<1:24:11,  1.47it/s]
1|18451|Loss: 0.936063289642334:  71%|███████▏  | 18450/25880 [3:46:14<1:24:11,  1.47it/s] 
1|18451|Loss: 0.936063289642334:  71%|███████▏  | 18451/25880 [3:46:14<1:25:45,  1.44it/s]
1|18452|Loss: 0.7481505274772644:  71%|███████▏  | 18451/25880 [3:46:14<1:25:45,  1.44it/s]
1|18452|Loss: 0.7481505274772644:  71%|███████▏  | 18452/25880 [3:46:15<1:23:38,  1.48it/s]
1|18453|Loss: 0.8330336809158325:  71%|███████▏  | 18452/25880 [3:46:15<1:23:38,  1.48it/s]
1|18453|Loss: 0.8330336809158325:  71%|███████▏  | 18453/25880 [3:46:15<1:28:05,  1.41it/s]
1|18454|Loss: 0.9745550751686096:  71%|███████▏  | 18453/25880 [3:46:16<1:28:05,  1.41it/s]
1|18454|Loss: 0.9745550751686096:  71%|███████▏  | 18454/25880 [3:46:16<1:32:23,  1.34it/s]
1|18455|Loss: 0.8555252552032471:  71%|███████▏  | 18454/25880 [3:46:17<1:32:23,  1.34it/s]
1|18455|Loss: 0.8555252552032471:  71%|███████▏  | 18455/25880 [3:46:17<1:32:29,  1.34it/s]
1|18456|Loss: 0.627128005027771:  71%|███████▏  | 18455/25880 [3:46:17<1:32:29,  1.34it/s] 
1|18456|Loss: 0.627128005027771:  71%|███████▏  | 18456/25880 [3:46:18<1:28:34,  1.40it/s]
1|18457|Loss: 0.7674738168716431:  71%|███████▏  | 18456/25880 [3:46:18<1:28:34,  1.40it/s]
1|18457|Loss: 0.7674738168716431:  71%|███████▏  | 18457/25880 [3:46:18<1:19:59,  1.55it/s]
1|18458|Loss: 0.8852123022079468:  71%|███████▏  | 18457/25880 [3:46:18<1:19:59,  1.55it/s]
1|18458|Loss: 0.8852123022079468:  71%|███████▏  | 18458/25880 [3:46:19<1:18:26,  1.58it/s]
1|18459|Loss: 0.7728685736656189:  71%|███████▏  | 18458/25880 [3:46:19<1:18:26,  1.58it/s]
1|18459|Loss: 0.7728685736656189:  71%|███████▏  | 18459/25880 [3:46:19<1:18:44,  1.57it/s]
1|18460|Loss: 0.8160645365715027:  71%|███████▏  | 18459/25880 [3:46:20<1:18:44,  1.57it/s]
1|18460|Loss: 0.8160645365715027:  71%|███████▏  | 18460/25880 [3:46:20<1:26:13,  1.43it/s]
1|18461|Loss: 0.8436280488967896:  71%|███████▏  | 18460/25880 [3:46:21<1:26:13,  1.43it/s]
1|18461|Loss: 0.8436280488967896:  71%|███████▏  | 18461/25880 [3:46:21<1:28:00,  1.41it/s]
1|18462|Loss: 0.7713246941566467:  71%|███████▏  | 18461/25880 [3:46:21<1:28:00,  1.41it/s]
1|18462|Loss: 0.7713246941566467:  71%|███████▏  | 18462/25880 [3:46:22<1:28:54,  1.39it/s]
1|18463|Loss: 0.7487265467643738:  71%|███████▏  | 18462/25880 [3:46:22<1:28:54,  1.39it/s]
1|18463|Loss: 0.7487265467643738:  71%|███████▏  | 18463/25880 [3:46:22<1:28:55,  1.39it/s]
1|18464|Loss: 0.8629826903343201:  71%|███████▏  | 18463/25880 [3:46:23<1:28:55,  1.39it/s]
1|18464|Loss: 0.8629826903343201:  71%|███████▏  | 18464/25880 [3:46:23<1:33:22,  1.32it/s]
1|18465|Loss: 0.794792115688324:  71%|███████▏  | 18464/25880 [3:46:24<1:33:22,  1.32it/s] 
1|18465|Loss: 0.794792115688324:  71%|███████▏  | 18465/25880 [3:46:24<1:38:46,  1.25it/s]
1|18466|Loss: 0.8088831901550293:  71%|███████▏  | 18465/25880 [3:46:25<1:38:46,  1.25it/s]
1|18466|Loss: 0.8088831901550293:  71%|███████▏  | 18466/25880 [3:46:25<1:34:39,  1.31it/s]
1|18467|Loss: 0.8246257901191711:  71%|███████▏  | 18466/25880 [3:46:25<1:34:39,  1.31it/s]
1|18467|Loss: 0.8246257901191711:  71%|███████▏  | 18467/25880 [3:46:26<1:38:12,  1.26it/s]
1|18468|Loss: 0.7842628359794617:  71%|███████▏  | 18467/25880 [3:46:26<1:38:12,  1.26it/s]
1|18468|Loss: 0.7842628359794617:  71%|███████▏  | 18468/25880 [3:46:26<1:34:25,  1.31it/s]
1|18469|Loss: 0.7641769051551819:  71%|███████▏  | 18468/25880 [3:46:27<1:34:25,  1.31it/s]
1|18469|Loss: 0.7641769051551819:  71%|███████▏  | 18469/25880 [3:46:27<1:32:24,  1.34it/s]
1|18470|Loss: 0.7300551533699036:  71%|███████▏  | 18469/25880 [3:46:28<1:32:24,  1.34it/s]
1|18470|Loss: 0.7300551533699036:  71%|███████▏  | 18470/25880 [3:46:28<1:32:01,  1.34it/s]
1|18471|Loss: 0.7546067237854004:  71%|███████▏  | 18470/25880 [3:46:28<1:32:01,  1.34it/s]
1|18471|Loss: 0.7546067237854004:  71%|███████▏  | 18471/25880 [3:46:29<1:34:40,  1.30it/s]
1|18472|Loss: 0.8069278001785278:  71%|███████▏  | 18471/25880 [3:46:29<1:34:40,  1.30it/s]
1|18472|Loss: 0.8069278001785278:  71%|███████▏  | 18472/25880 [3:46:29<1:31:21,  1.35it/s]
1|18473|Loss: 0.8558114767074585:  71%|███████▏  | 18472/25880 [3:46:30<1:31:21,  1.35it/s]
1|18473|Loss: 0.8558114767074585:  71%|███████▏  | 18473/25880 [3:46:30<1:27:45,  1.41it/s]
1|18474|Loss: 0.8473585844039917:  71%|███████▏  | 18473/25880 [3:46:30<1:27:45,  1.41it/s]
1|18474|Loss: 0.8473585844039917:  71%|███████▏  | 18474/25880 [3:46:31<1:22:46,  1.49it/s]
1|18475|Loss: 0.8182896971702576:  71%|███████▏  | 18474/25880 [3:46:31<1:22:46,  1.49it/s]
1|18475|Loss: 0.8182896971702576:  71%|███████▏  | 18475/25880 [3:46:31<1:26:30,  1.43it/s]
1|18476|Loss: 0.9820258021354675:  71%|███████▏  | 18475/25880 [3:46:32<1:26:30,  1.43it/s]
1|18476|Loss: 0.9820258021354675:  71%|███████▏  | 18476/25880 [3:46:32<1:31:42,  1.35it/s]
1|18477|Loss: 0.8179147839546204:  71%|███████▏  | 18476/25880 [3:46:33<1:31:42,  1.35it/s]
1|18477|Loss: 0.8179147839546204:  71%|███████▏  | 18477/25880 [3:46:33<1:32:15,  1.34it/s]
1|18478|Loss: 0.7865886092185974:  71%|███████▏  | 18477/25880 [3:46:33<1:32:15,  1.34it/s]
1|18478|Loss: 0.7865886092185974:  71%|███████▏  | 18478/25880 [3:46:34<1:37:06,  1.27it/s]
1|18479|Loss: 0.9735516905784607:  71%|███████▏  | 18478/25880 [3:46:34<1:37:06,  1.27it/s]
1|18479|Loss: 0.9735516905784607:  71%|███████▏  | 18479/25880 [3:46:35<1:32:04,  1.34it/s]
1|18480|Loss: 0.7487053871154785:  71%|███████▏  | 18479/25880 [3:46:35<1:32:04,  1.34it/s]
1|18480|Loss: 0.7487053871154785:  71%|███████▏  | 18480/25880 [3:46:35<1:32:07,  1.34it/s]
1|18481|Loss: 0.9967077374458313:  71%|███████▏  | 18480/25880 [3:46:36<1:32:07,  1.34it/s]
1|18481|Loss: 0.9967077374458313:  71%|███████▏  | 18481/25880 [3:46:36<1:35:37,  1.29it/s]
1|18482|Loss: 0.7755587697029114:  71%|███████▏  | 18481/25880 [3:46:37<1:35:37,  1.29it/s]
1|18482|Loss: 0.7755587697029114:  71%|███████▏  | 18482/25880 [3:46:37<1:31:39,  1.35it/s]
1|18483|Loss: 0.8253744840621948:  71%|███████▏  | 18482/25880 [3:46:37<1:31:39,  1.35it/s]
1|18483|Loss: 0.8253744840621948:  71%|███████▏  | 18483/25880 [3:46:37<1:30:50,  1.36it/s]
1|18484|Loss: 0.8042521476745605:  71%|███████▏  | 18483/25880 [3:46:38<1:30:50,  1.36it/s]
1|18484|Loss: 0.8042521476745605:  71%|███████▏  | 18484/25880 [3:46:38<1:26:34,  1.42it/s]
1|18485|Loss: 0.8123806715011597:  71%|███████▏  | 18484/25880 [3:46:38<1:26:34,  1.42it/s]
1|18485|Loss: 0.8123806715011597:  71%|███████▏  | 18485/25880 [3:46:39<1:26:41,  1.42it/s]
1|18486|Loss: 0.7458788752555847:  71%|███████▏  | 18485/25880 [3:46:39<1:26:41,  1.42it/s]
1|18486|Loss: 0.7458788752555847:  71%|███████▏  | 18486/25880 [3:46:40<1:27:48,  1.40it/s]
1|18487|Loss: 0.9250649213790894:  71%|███████▏  | 18486/25880 [3:46:40<1:27:48,  1.40it/s]
1|18487|Loss: 0.9250649213790894:  71%|███████▏  | 18487/25880 [3:46:40<1:25:14,  1.45it/s]
1|18488|Loss: 0.789204478263855:  71%|███████▏  | 18487/25880 [3:46:41<1:25:14,  1.45it/s] 
1|18488|Loss: 0.789204478263855:  71%|███████▏  | 18488/25880 [3:46:41<1:22:56,  1.49it/s]
1|18489|Loss: 1.06382417678833:  71%|███████▏  | 18488/25880 [3:46:41<1:22:56,  1.49it/s] 
1|18489|Loss: 1.06382417678833:  71%|███████▏  | 18489/25880 [3:46:42<1:26:06,  1.43it/s]
1|18490|Loss: 0.7385610342025757:  71%|███████▏  | 18489/25880 [3:46:42<1:26:06,  1.43it/s]
1|18490|Loss: 0.7385610342025757:  71%|███████▏  | 18490/25880 [3:46:42<1:19:42,  1.55it/s]
1|18491|Loss: 0.8123209476470947:  71%|███████▏  | 18490/25880 [3:46:42<1:19:42,  1.55it/s]
1|18491|Loss: 0.8123209476470947:  71%|███████▏  | 18491/25880 [3:46:43<1:18:00,  1.58it/s]
1|18492|Loss: 0.7280268669128418:  71%|███████▏  | 18491/25880 [3:46:43<1:18:00,  1.58it/s]
1|18492|Loss: 0.7280268669128418:  71%|███████▏  | 18492/25880 [3:46:44<1:24:01,  1.47it/s]
1|18493|Loss: 0.8294536471366882:  71%|███████▏  | 18492/25880 [3:46:44<1:24:01,  1.47it/s]
1|18493|Loss: 0.8294536471366882:  71%|███████▏  | 18493/25880 [3:46:44<1:26:19,  1.43it/s]
1|18494|Loss: 0.8692267537117004:  71%|███████▏  | 18493/25880 [3:46:45<1:26:19,  1.43it/s]
1|18494|Loss: 0.8692267537117004:  71%|███████▏  | 18494/25880 [3:46:45<1:24:38,  1.45it/s]
1|18495|Loss: 0.8978564143180847:  71%|███████▏  | 18494/25880 [3:46:45<1:24:38,  1.45it/s]
1|18495|Loss: 0.8978564143180847:  71%|███████▏  | 18495/25880 [3:46:46<1:22:57,  1.48it/s]
1|18496|Loss: 0.8261806964874268:  71%|███████▏  | 18495/25880 [3:46:46<1:22:57,  1.48it/s]
1|18496|Loss: 0.8261806964874268:  71%|███████▏  | 18496/25880 [3:46:46<1:21:11,  1.52it/s]
1|18497|Loss: 0.8722729682922363:  71%|███████▏  | 18496/25880 [3:46:47<1:21:11,  1.52it/s]
1|18497|Loss: 0.8722729682922363:  71%|███████▏  | 18497/25880 [3:46:47<1:19:40,  1.54it/s]
1|18498|Loss: 0.8856446146965027:  71%|███████▏  | 18497/25880 [3:46:47<1:19:40,  1.54it/s]
1|18498|Loss: 0.8856446146965027:  71%|███████▏  | 18498/25880 [3:46:47<1:15:56,  1.62it/s]
1|18499|Loss: 0.7477148175239563:  71%|███████▏  | 18498/25880 [3:46:48<1:15:56,  1.62it/s]
1|18499|Loss: 0.7477148175239563:  71%|███████▏  | 18499/25880 [3:46:48<1:10:33,  1.74it/s]
1|18500|Loss: 0.7575111389160156:  71%|███████▏  | 18499/25880 [3:46:48<1:10:33,  1.74it/s]
1|18500|Loss: 0.7575111389160156:  71%|███████▏  | 18500/25880 [3:46:49<1:14:38,  1.65it/s]
1|18501|Loss: 0.8324257135391235:  71%|███████▏  | 18500/25880 [3:46:49<1:14:38,  1.65it/s]
1|18501|Loss: 0.8324257135391235:  71%|███████▏  | 18501/25880 [3:46:49<1:15:14,  1.63it/s]
1|18502|Loss: 0.823905885219574:  71%|███████▏  | 18501/25880 [3:46:49<1:15:14,  1.63it/s] 
1|18502|Loss: 0.823905885219574:  71%|███████▏  | 18502/25880 [3:46:50<1:15:14,  1.63it/s]
1|18503|Loss: 0.8744117021560669:  71%|███████▏  | 18502/25880 [3:46:50<1:15:14,  1.63it/s]
1|18503|Loss: 0.8744117021560669:  71%|███████▏  | 18503/25880 [3:46:50<1:18:47,  1.56it/s]
1|18504|Loss: 0.9850366115570068:  71%|███████▏  | 18503/25880 [3:46:51<1:18:47,  1.56it/s]
1|18504|Loss: 0.9850366115570068:  71%|███████▏  | 18504/25880 [3:46:51<1:22:21,  1.49it/s]
1|18505|Loss: 0.7345244288444519:  71%|███████▏  | 18504/25880 [3:46:52<1:22:21,  1.49it/s]
1|18505|Loss: 0.7345244288444519:  72%|███████▏  | 18505/25880 [3:46:52<1:26:36,  1.42it/s]
1|18506|Loss: 0.7747548222541809:  72%|███████▏  | 18505/25880 [3:46:52<1:26:36,  1.42it/s]
1|18506|Loss: 0.7747548222541809:  72%|███████▏  | 18506/25880 [3:46:53<1:21:45,  1.50it/s]
1|18507|Loss: 0.7662417888641357:  72%|███████▏  | 18506/25880 [3:46:53<1:21:45,  1.50it/s]
1|18507|Loss: 0.7662417888641357:  72%|███████▏  | 18507/25880 [3:46:53<1:19:43,  1.54it/s]
1|18508|Loss: 0.41986292600631714:  72%|███████▏  | 18507/25880 [3:46:54<1:19:43,  1.54it/s]
1|18508|Loss: 0.41986292600631714:  72%|███████▏  | 18508/25880 [3:46:54<1:29:36,  1.37it/s]
1|18509|Loss: 0.8441808223724365:  72%|███████▏  | 18508/25880 [3:46:55<1:29:36,  1.37it/s] 
1|18509|Loss: 0.8441808223724365:  72%|███████▏  | 18509/25880 [3:46:55<1:32:24,  1.33it/s]
1|18510|Loss: 0.8472440242767334:  72%|███████▏  | 18509/25880 [3:46:55<1:32:24,  1.33it/s]
1|18510|Loss: 0.8472440242767334:  72%|███████▏  | 18510/25880 [3:46:56<1:28:38,  1.39it/s]
1|18511|Loss: 0.8201882839202881:  72%|███████▏  | 18510/25880 [3:46:56<1:28:38,  1.39it/s]
1|18511|Loss: 0.8201882839202881:  72%|███████▏  | 18511/25880 [3:46:56<1:30:23,  1.36it/s]
1|18512|Loss: 0.8545061945915222:  72%|███████▏  | 18511/25880 [3:46:57<1:30:23,  1.36it/s]
1|18512|Loss: 0.8545061945915222:  72%|███████▏  | 18512/25880 [3:46:57<1:25:26,  1.44it/s]
1|18513|Loss: 0.9168442487716675:  72%|███████▏  | 18512/25880 [3:46:57<1:25:26,  1.44it/s]
1|18513|Loss: 0.9168442487716675:  72%|███████▏  | 18513/25880 [3:46:58<1:27:10,  1.41it/s]
1|18514|Loss: 0.839523434638977:  72%|███████▏  | 18513/25880 [3:46:58<1:27:10,  1.41it/s] 
1|18514|Loss: 0.839523434638977:  72%|███████▏  | 18514/25880 [3:46:58<1:28:50,  1.38it/s]
1|18515|Loss: 0.9880673885345459:  72%|███████▏  | 18514/25880 [3:46:59<1:28:50,  1.38it/s]
1|18515|Loss: 0.9880673885345459:  72%|███████▏  | 18515/25880 [3:46:59<1:21:05,  1.51it/s]
1|18516|Loss: 0.9084650278091431:  72%|███████▏  | 18515/25880 [3:46:59<1:21:05,  1.51it/s]
1|18516|Loss: 0.9084650278091431:  72%|███████▏  | 18516/25880 [3:46:59<1:17:57,  1.57it/s]
1|18517|Loss: 0.7636235356330872:  72%|███████▏  | 18516/25880 [3:47:00<1:17:57,  1.57it/s]
1|18517|Loss: 0.7636235356330872:  72%|███████▏  | 18517/25880 [3:47:00<1:17:51,  1.58it/s]
1|18518|Loss: 0.7891251444816589:  72%|███████▏  | 18517/25880 [3:47:01<1:17:51,  1.58it/s]
1|18518|Loss: 0.7891251444816589:  72%|███████▏  | 18518/25880 [3:47:01<1:21:27,  1.51it/s]
1|18519|Loss: 0.9140104651451111:  72%|███████▏  | 18518/25880 [3:47:01<1:21:27,  1.51it/s]
1|18519|Loss: 0.9140104651451111:  72%|███████▏  | 18519/25880 [3:47:02<1:24:47,  1.45it/s]
1|18520|Loss: 0.9139761924743652:  72%|███████▏  | 18519/25880 [3:47:02<1:24:47,  1.45it/s]
1|18520|Loss: 0.9139761924743652:  72%|███████▏  | 18520/25880 [3:47:02<1:23:49,  1.46it/s]
1|18521|Loss: 0.8639318346977234:  72%|███████▏  | 18520/25880 [3:47:03<1:23:49,  1.46it/s]
1|18521|Loss: 0.8639318346977234:  72%|███████▏  | 18521/25880 [3:47:03<1:26:41,  1.41it/s]
1|18522|Loss: 0.8315381407737732:  72%|███████▏  | 18521/25880 [3:47:03<1:26:41,  1.41it/s]
1|18522|Loss: 0.8315381407737732:  72%|███████▏  | 18522/25880 [3:47:04<1:23:12,  1.47it/s]
1|18523|Loss: 0.7144518494606018:  72%|███████▏  | 18522/25880 [3:47:04<1:23:12,  1.47it/s]
1|18523|Loss: 0.7144518494606018:  72%|███████▏  | 18523/25880 [3:47:04<1:24:14,  1.46it/s]
1|18524|Loss: 0.8521804809570312:  72%|███████▏  | 18523/25880 [3:47:05<1:24:14,  1.46it/s]
1|18524|Loss: 0.8521804809570312:  72%|███████▏  | 18524/25880 [3:47:05<1:26:05,  1.42it/s]
1|18525|Loss: 0.6924810409545898:  72%|███████▏  | 18524/25880 [3:47:06<1:26:05,  1.42it/s]
1|18525|Loss: 0.6924810409545898:  72%|███████▏  | 18525/25880 [3:47:06<1:31:09,  1.34it/s]
1|18526|Loss: 0.8339055776596069:  72%|███████▏  | 18525/25880 [3:47:06<1:31:09,  1.34it/s]
1|18526|Loss: 0.8339055776596069:  72%|███████▏  | 18526/25880 [3:47:07<1:32:13,  1.33it/s]
1|18527|Loss: 0.8229256272315979:  72%|███████▏  | 18526/25880 [3:47:07<1:32:13,  1.33it/s]
1|18527|Loss: 0.8229256272315979:  72%|███████▏  | 18527/25880 [3:47:07<1:31:38,  1.34it/s]
1|18528|Loss: 0.8199248313903809:  72%|███████▏  | 18527/25880 [3:47:08<1:31:38,  1.34it/s]
1|18528|Loss: 0.8199248313903809:  72%|███████▏  | 18528/25880 [3:47:08<1:26:40,  1.41it/s]
1|18529|Loss: 0.8564009070396423:  72%|███████▏  | 18528/25880 [3:47:08<1:26:40,  1.41it/s]
1|18529|Loss: 0.8564009070396423:  72%|███████▏  | 18529/25880 [3:47:09<1:30:38,  1.35it/s]
1|18530|Loss: 0.7678695917129517:  72%|███████▏  | 18529/25880 [3:47:09<1:30:38,  1.35it/s]
1|18530|Loss: 0.7678695917129517:  72%|███████▏  | 18530/25880 [3:47:10<1:28:10,  1.39it/s]
1|18531|Loss: 0.7633714079856873:  72%|██��████▏  | 18530/25880 [3:47:10<1:28:10,  1.39it/s]
1|18531|Loss: 0.7633714079856873:  72%|███████▏  | 18531/25880 [3:47:10<1:31:45,  1.33it/s]
1|18532|Loss: 0.7924432158470154:  72%|███████▏  | 18531/25880 [3:47:11<1:31:45,  1.33it/s]
1|18532|Loss: 0.7924432158470154:  72%|███████▏  | 18532/25880 [3:47:11<1:29:41,  1.37it/s]
1|18533|Loss: 0.9564149379730225:  72%|███████▏  | 18532/25880 [3:47:11<1:29:41,  1.37it/s]
1|18533|Loss: 0.9564149379730225:  72%|███████▏  | 18533/25880 [3:47:12<1:22:32,  1.48it/s]
1|18534|Loss: 0.7117785811424255:  72%|███████▏  | 18533/25880 [3:47:12<1:22:32,  1.48it/s]
1|18534|Loss: 0.7117785811424255:  72%|███████▏  | 18534/25880 [3:47:12<1:22:50,  1.48it/s]
1|18535|Loss: 0.752099871635437:  72%|███████▏  | 18534/25880 [3:47:13<1:22:50,  1.48it/s] 
1|18535|Loss: 0.752099871635437:  72%|███████▏  | 18535/25880 [3:47:13<1:31:30,  1.34it/s]
1|18536|Loss: 0.6866576671600342:  72%|███████▏  | 18535/25880 [3:47:14<1:31:30,  1.34it/s]
1|18536|Loss: 0.6866576671600342:  72%|███████▏  | 18536/25880 [3:47:14<1:28:11,  1.39it/s]
1|18537|Loss: 0.8833010196685791:  72%|███████▏  | 18536/25880 [3:47:14<1:28:11,  1.39it/s]
1|18537|Loss: 0.8833010196685791:  72%|███████▏  | 18537/25880 [3:47:15<1:27:28,  1.40it/s]
1|18538|Loss: 0.7055841684341431:  72%|███████▏  | 18537/25880 [3:47:15<1:27:28,  1.40it/s]
1|18538|Loss: 0.7055841684341431:  72%|███████▏  | 18538/25880 [3:47:15<1:31:36,  1.34it/s]
1|18539|Loss: 0.8289438486099243:  72%|███████▏  | 18538/25880 [3:47:16<1:31:36,  1.34it/s]
1|18539|Loss: 0.8289438486099243:  72%|███████▏  | 18539/25880 [3:47:16<1:32:21,  1.32it/s]
1|18540|Loss: 0.9160811305046082:  72%|███████▏  | 18539/25880 [3:47:17<1:32:21,  1.32it/s]
1|18540|Loss: 0.9160811305046082:  72%|███████▏  | 18540/25880 [3:47:17<1:37:23,  1.26it/s]
1|18541|Loss: 0.7442898154258728:  72%|███████▏  | 18540/25880 [3:47:18<1:37:23,  1.26it/s]
1|18541|Loss: 0.7442898154258728:  72%|███████▏  | 18541/25880 [3:47:18<1:38:28,  1.24it/s]
1|18542|Loss: 0.8690944314002991:  72%|███████▏  | 18541/25880 [3:47:18<1:38:28,  1.24it/s]
1|18542|Loss: 0.8690944314002991:  72%|███████▏  | 18542/25880 [3:47:19<1:35:41,  1.28it/s]
1|18543|Loss: 0.8057529330253601:  72%|███████▏  | 18542/25880 [3:47:19<1:35:41,  1.28it/s]
1|18543|Loss: 0.8057529330253601:  72%|███████▏  | 18543/25880 [3:47:19<1:29:17,  1.37it/s]
1|18544|Loss: 0.8015934824943542:  72%|███████▏  | 18543/25880 [3:47:20<1:29:17,  1.37it/s]
1|18544|Loss: 0.8015934824943542:  72%|███████▏  | 18544/25880 [3:47:20<1:28:12,  1.39it/s]
1|18545|Loss: 0.8822368383407593:  72%|███████▏  | 18544/25880 [3:47:20<1:28:12,  1.39it/s]
1|18545|Loss: 0.8822368383407593:  72%|███████▏  | 18545/25880 [3:47:21<1:32:42,  1.32it/s]
1|18546|Loss: 0.8401046991348267:  72%|███████▏  | 18545/25880 [3:47:21<1:32:42,  1.32it/s]
1|18546|Loss: 0.8401046991348267:  72%|███████▏  | 18546/25880 [3:47:22<1:33:27,  1.31it/s]
1|18547|Loss: 0.8092802166938782:  72%|███████▏  | 18546/25880 [3:47:22<1:33:27,  1.31it/s]
1|18547|Loss: 0.8092802166938782:  72%|███████▏  | 18547/25880 [3:47:22<1:29:50,  1.36it/s]
1|18548|Loss: 0.8692389726638794:  72%|███████▏  | 18547/25880 [3:47:23<1:29:50,  1.36it/s]
1|18548|Loss: 0.8692389726638794:  72%|███████▏  | 18548/25880 [3:47:23<1:26:27,  1.41it/s]
1|18549|Loss: 0.8374635577201843:  72%|███████▏  | 18548/25880 [3:47:23<1:26:27,  1.41it/s]
1|18549|Loss: 0.8374635577201843:  72%|███████▏  | 18549/25880 [3:47:24<1:25:56,  1.42it/s]
1|18550|Loss: 0.9099960923194885:  72%|███████▏  | 18549/25880 [3:47:24<1:25:56,  1.42it/s]
1|18550|Loss: 0.9099960923194885:  72%|███████▏  | 18550/25880 [3:47:24<1:26:30,  1.41it/s]
1|18551|Loss: 0.8707141876220703:  72%|███████▏  | 18550/25880 [3:47:25<1:26:30,  1.41it/s]
1|18551|Loss: 0.8707141876220703:  72%|███████▏  | 18551/25880 [3:47:25<1:31:07,  1.34it/s]
1|18552|Loss: 0.9761093854904175:  72%|███████▏  | 18551/25880 [3:47:25<1:31:07,  1.34it/s]
1|18552|Loss: 0.9761093854904175:  72%|███████▏  | 18552/25880 [3:47:26<1:29:11,  1.37it/s]
1|18553|Loss: 0.7508399486541748:  72%|███████▏  | 18552/25880 [3:47:26<1:29:11,  1.37it/s]
1|18553|Loss: 0.7508399486541748:  72%|███████▏  | 18553/25880 [3:47:26<1:23:32,  1.46it/s]
1|18554|Loss: 0.7432149052619934:  72%|███████▏  | 18553/25880 [3:47:27<1:23:32,  1.46it/s]
1|18554|Loss: 0.7432149052619934:  72%|███████▏  | 18554/25880 [3:47:27<1:19:40,  1.53it/s]
1|18555|Loss: 0.8336313366889954:  72%|███████▏  | 18554/25880 [3:47:27<1:19:40,  1.53it/s]
1|18555|Loss: 0.8336313366889954:  72%|███████▏  | 18555/25880 [3:47:28<1:17:00,  1.59it/s]
1|18556|Loss: 0.7482128143310547:  72%|███████▏  | 18555/25880 [3:47:28<1:17:00,  1.59it/s]
1|18556|Loss: 0.7482128143310547:  72%|███████▏  | 18556/25880 [3:47:28<1:21:15,  1.50it/s]
1|18557|Loss: 0.932546854019165:  72%|███████▏  | 18556/25880 [3:47:29<1:21:15,  1.50it/s] 
1|18557|Loss: 0.932546854019165:  72%|███████▏  | 18557/25880 [3:47:29<1:26:10,  1.42it/s]
1|18558|Loss: 0.837806224822998:  72%|███████▏  | 18557/25880 [3:47:29<1:26:10,  1.42it/s]
1|18558|Loss: 0.837806224822998:  72%|███████▏  | 18558/25880 [3:47:30<1:27:32,  1.39it/s]
1|18559|Loss: 0.9371871948242188:  72%|███████▏  | 18558/25880 [3:47:30<1:27:32,  1.39it/s]
1|18559|Loss: 0.9371871948242188:  72%|███████▏  | 18559/25880 [3:47:31<1:29:51,  1.36it/s]
1|18560|Loss: 0.9047200083732605:  72%|███████▏  | 18559/25880 [3:47:31<1:29:51,  1.36it/s]
1|18560|Loss: 0.9047200083732605:  72%|███████▏  | 18560/25880 [3:47:31<1:29:19,  1.37it/s]
1|18561|Loss: 1.0146764516830444:  72%|███████▏  | 18560/25880 [3:47:32<1:29:19,  1.37it/s]
1|18561|Loss: 1.0146764516830444:  72%|███████▏  | 18561/25880 [3:47:32<1:30:49,  1.34it/s]
1|18562|Loss: 0.7418157458305359:  72%|███████▏  | 18561/25880 [3:47:32<1:30:49,  1.34it/s]
1|18562|Loss: 0.7418157458305359:  72%|███████▏  | 18562/25880 [3:47:33<1:27:34,  1.39it/s]
1|18563|Loss: 0.9079803824424744:  72%|███████▏  | 18562/25880 [3:47:33<1:27:34,  1.39it/s]
1|18563|Loss: 0.9079803824424744:  72%|███████▏  | 18563/25880 [3:47:33<1:27:15,  1.40it/s]
1|18564|Loss: 0.7703211903572083:  72%|███████▏  | 18563/25880 [3:47:34<1:27:15,  1.40it/s]
1|18564|Loss: 0.7703211903572083:  72%|███████▏  | 18564/25880 [3:47:34<1:30:31,  1.35it/s]
1|18565|Loss: 0.7995532155036926:  72%|███████▏  | 18564/25880 [3:47:35<1:30:31,  1.35it/s]
1|18565|Loss: 0.7995532155036926:  72%|███████▏  | 18565/25880 [3:47:35<1:27:22,  1.40it/s]
1|18566|Loss: 0.7751978039741516:  72%|███████▏  | 18565/25880 [3:47:35<1:27:22,  1.40it/s]
1|18566|Loss: 0.7751978039741516:  72%|███████▏  | 18566/25880 [3:47:36<1:24:18,  1.45it/s]
1|18567|Loss: 0.9068764448165894:  72%|███████▏  | 18566/25880 [3:47:36<1:24:18,  1.45it/s]
1|18567|Loss: 0.9068764448165894:  72%|███████▏  | 18567/25880 [3:47:36<1:20:41,  1.51it/s]
1|18568|Loss: 0.8202961683273315:  72%|███████▏  | 18567/25880 [3:47:37<1:20:41,  1.51it/s]
1|18568|Loss: 0.8202961683273315:  72%|███████▏  | 18568/25880 [3:47:37<1:22:41,  1.47it/s]
1|18569|Loss: 0.7488479018211365:  72%|███████▏  | 18568/25880 [3:47:37<1:22:41,  1.47it/s]
1|18569|Loss: 0.7488479018211365:  72%|███████▏  | 18569/25880 [3:47:38<1:27:01,  1.40it/s]
1|18570|Loss: 0.8189683556556702:  72%|███████▏  | 18569/25880 [3:47:38<1:27:01,  1.40it/s]
1|18570|Loss: 0.8189683556556702:  72%|███████▏  | 18570/25880 [3:47:38<1:28:30,  1.38it/s]
1|18571|Loss: 0.8431776165962219:  72%|███████▏  | 18570/25880 [3:47:39<1:28:30,  1.38it/s]
1|18571|Loss: 0.8431776165962219:  72%|███████▏  | 18571/25880 [3:47:39<1:25:27,  1.43it/s]
1|18572|Loss: 0.8744198679924011:  72%|███████▏  | 18571/25880 [3:47:39<1:25:27,  1.43it/s]
1|18572|Loss: 0.8744198679924011:  72%|███████▏  | 18572/25880 [3:47:40<1:30:57,  1.34it/s]
1|18573|Loss: 0.8633807897567749:  72%|███████▏  | 18572/25880 [3:47:40<1:30:57,  1.34it/s]
1|18573|Loss: 0.8633807897567749:  72%|███████▏  | 18573/25880 [3:47:41<1:32:02,  1.32it/s]
1|18574|Loss: 0.799953818321228:  72%|███████▏  | 18573/25880 [3:47:41<1:32:02,  1.32it/s] 
1|18574|Loss: 0.799953818321228:  72%|███████▏  | 18574/25880 [3:47:42<1:35:40,  1.27it/s]
1|18575|Loss: 0.8088434934616089:  72%|███████▏  | 18574/25880 [3:47:42<1:35:40,  1.27it/s]
1|18575|Loss: 0.8088434934616089:  72%|███████▏  | 18575/25880 [3:47:42<1:37:12,  1.25it/s]
1|18576|Loss: 0.7547768354415894:  72%|███████▏  | 18575/25880 [3:47:43<1:37:12,  1.25it/s]
1|18576|Loss: 0.7547768354415894:  72%|███████▏  | 18576/25880 [3:47:43<1:30:55,  1.34it/s]
1|18577|Loss: 0.8284494876861572:  72%|███████▏  | 18576/25880 [3:47:43<1:30:55,  1.34it/s]
1|18577|Loss: 0.8284494876861572:  72%|███████▏  | 18577/25880 [3:47:43<1:21:10,  1.50it/s]
1|18578|Loss: 1.0072112083435059:  72%|███████▏  | 18577/25880 [3:47:44<1:21:10,  1.50it/s]
1|18578|Loss: 1.0072112083435059:  72%|███████▏  | 18578/25880 [3:47:44<1:21:31,  1.49it/s]
1|18579|Loss: 0.7409611940383911:  72%|███████▏  | 18578/25880 [3:47:45<1:21:31,  1.49it/s]
1|18579|Loss: 0.7409611940383911:  72%|███████▏  | 18579/25880 [3:47:45<1:25:31,  1.42it/s]
1|18580|Loss: 0.8935413956642151:  72%|███████▏  | 18579/25880 [3:47:45<1:25:31,  1.42it/s]
1|18580|Loss: 0.8935413956642151:  72%|███████▏  | 18580/25880 [3:47:46<1:24:32,  1.44it/s]
1|18581|Loss: 0.7537894248962402:  72%|███████▏  | 18580/25880 [3:47:46<1:24:32,  1.44it/s]
1|18581|Loss: 0.7537894248962402:  72%|███████▏  | 18581/25880 [3:47:46<1:27:52,  1.38it/s]
1|18582|Loss: 0.7768040895462036:  72%|███████▏  | 18581/25880 [3:47:47<1:27:52,  1.38it/s]
1|18582|Loss: 0.7768040895462036:  72%|███████▏  | 18582/25880 [3:47:47<1:28:39,  1.37it/s]
1|18583|Loss: 0.7531343698501587:  72%|███████▏  | 18582/25880 [3:47:48<1:28:39,  1.37it/s]
1|18583|Loss: 0.7531343698501587:  72%|███████▏  | 18583/25880 [3:47:48<1:32:17,  1.32it/s]
1|18584|Loss: 0.8149241209030151:  72%|███████▏  | 18583/25880 [3:47:48<1:32:17,  1.32it/s]
1|18584|Loss: 0.8149241209030151:  72%|███████▏  | 18584/25880 [3:47:49<1:32:04,  1.32it/s]
1|18585|Loss: 0.8091691732406616:  72%|███████▏  | 18584/25880 [3:47:49<1:32:04,  1.32it/s]
1|18585|Loss: 0.8091691732406616:  72%|███████▏  | 18585/25880 [3:47:49<1:28:15,  1.38it/s]
1|18586|Loss: 0.9043972492218018:  72%|███████▏  | 18585/25880 [3:47:50<1:28:15,  1.38it/s]
1|18586|Loss: 0.9043972492218018:  72%|███████▏  | 18586/25880 [3:47:50<1:33:09,  1.30it/s]
1|18587|Loss: 0.7444770932197571:  72%|███████▏  | 18586/25880 [3:47:51<1:33:09,  1.30it/s]
1|18587|Loss: 0.7444770932197571:  72%|███████▏  | 18587/25880 [3:47:51<1:30:28,  1.34it/s]
1|18588|Loss: 0.7300664782524109:  72%|███████▏  | 18587/25880 [3:47:51<1:30:28,  1.34it/s]
1|18588|Loss: 0.7300664782524109:  72%|███████▏  | 18588/25880 [3:47:52<1:26:08,  1.41it/s]
1|18589|Loss: 0.9480828046798706:  72%|███████▏  | 18588/25880 [3:47:52<1:26:08,  1.41it/s]
1|18589|Loss: 0.9480828046798706:  72%|███████▏  | 18589/25880 [3:47:52<1:28:28,  1.37it/s]
1|18590|Loss: 0.8166258335113525:  72%|███████▏  | 18589/25880 [3:47:53<1:28:28,  1.37it/s]
1|18590|Loss: 0.8166258335113525:  72%|███████▏  | 18590/25880 [3:47:53<1:28:22,  1.37it/s]
1|18591|Loss: 0.8590357303619385:  72%|███████▏  | 18590/25880 [3:47:53<1:28:22,  1.37it/s]
1|18591|Loss: 0.8590357303619385:  72%|███████▏  | 18591/25880 [3:47:54<1:30:21,  1.34it/s]
1|18592|Loss: 0.8719159364700317:  72%|███████▏  | 18591/25880 [3:47:54<1:30:21,  1.34it/s]
1|18592|Loss: 0.8719159364700317:  72%|███████▏  | 18592/25880 [3:47:55<1:33:41,  1.30it/s]
1|18593|Loss: 0.8113962411880493:  72%|███████▏  | 18592/25880 [3:47:55<1:33:41,  1.30it/s]
1|18593|Loss: 0.8113962411880493:  72%|███████▏  | 18593/25880 [3:47:55<1:30:57,  1.34it/s]
1|18594|Loss: 0.715151309967041:  72%|███████▏  | 18593/25880 [3:47:56<1:30:57,  1.34it/s] 
1|18594|Loss: 0.715151309967041:  72%|███████▏  | 18594/25880 [3:47:56<1:27:05,  1.39it/s]
1|18595|Loss: 0.8728527426719666:  72%|███████▏  | 18594/25880 [3:47:56<1:27:05,  1.39it/s]
1|18595|Loss: 0.8728527426719666:  72%|███████▏  | 18595/25880 [3:47:57<1:27:23,  1.39it/s]
1|18596|Loss: 0.8910729289054871:  72%|███████▏  | 18595/25880 [3:47:57<1:27:23,  1.39it/s]
1|18596|Loss: 0.8910729289054871:  72%|███████▏  | 18596/25880 [3:47:57<1:28:45,  1.37it/s]
1|18597|Loss: 0.8991726040840149:  72%|███████▏  | 18596/25880 [3:47:58<1:28:45,  1.37it/s]
1|18597|Loss: 0.8991726040840149:  72%|███████▏  | 18597/25880 [3:47:58<1:32:39,  1.31it/s]
1|18598|Loss: 0.8442114591598511:  72%|███████▏  | 18597/25880 [3:47:59<1:32:39,  1.31it/s]
1|18598|Loss: 0.8442114591598511:  72%|███████▏  | 18598/25880 [3:47:59<1:31:27,  1.33it/s]
1|18599|Loss: 0.7550967335700989:  72%|███████▏  | 18598/25880 [3:47:59<1:31:27,  1.33it/s]
1|18599|Loss: 0.7550967335700989:  72%|███████▏  | 18599/25880 [3:48:00<1:29:49,  1.35it/s]
1|18600|Loss: 0.811170220375061:  72%|███████▏  | 18599/25880 [3:48:00<1:29:49,  1.35it/s] 
1|18600|Loss: 0.811170220375061:  72%|███████▏  | 18600/25880 [3:48:00<1:25:58,  1.41it/s]
1|18601|Loss: 0.8380259275436401:  72%|███████▏  | 18600/25880 [3:48:01<1:25:58,  1.41it/s]
1|18601|Loss: 0.8380259275436401:  72%|███████▏  | 18601/25880 [3:48:01<1:25:06,  1.43it/s]
1|18602|Loss: 0.7610671520233154:  72%|███████▏  | 18601/25880 [3:48:01<1:25:06,  1.43it/s]
1|18602|Loss: 0.7610671520233154:  72%|███████▏  | 18602/25880 [3:48:02<1:25:51,  1.41it/s]
1|18603|Loss: 0.7556236386299133:  72%|███████▏  | 18602/25880 [3:48:02<1:25:51,  1.41it/s]
1|18603|Loss: 0.7556236386299133:  72%|███████▏  | 18603/25880 [3:48:03<1:29:35,  1.35it/s]
1|18604|Loss: 0.7960065007209778:  72%|███████▏  | 18603/25880 [3:48:03<1:29:35,  1.35it/s]
1|18604|Loss: 0.7960065007209778:  72%|███████▏  | 18604/25880 [3:48:03<1:33:23,  1.30it/s]
1|18605|Loss: 0.8029869794845581:  72%|███████▏  | 18604/25880 [3:48:04<1:33:23,  1.30it/s]
1|18605|Loss: 0.8029869794845581:  72%|███████▏  | 18605/25880 [3:48:04<1:34:44,  1.28it/s]
1|18606|Loss: 0.7970980405807495:  72%|███████▏  | 18605/25880 [3:48:05<1:34:44,  1.28it/s]
1|18606|Loss: 0.7970980405807495:  72%|███████▏  | 18606/25880 [3:48:05<1:35:09,  1.27it/s]
1|18607|Loss: 0.900507926940918:  72%|███████▏  | 18606/25880 [3:48:05<1:35:09,  1.27it/s] 
1|18607|Loss: 0.900507926940918:  72%|███████▏  | 18607/25880 [3:48:06<1:33:43,  1.29it/s]
1|18608|Loss: 0.6236703395843506:  72%|███████▏  | 18607/25880 [3:48:06<1:33:43,  1.29it/s]
1|18608|Loss: 0.6236703395843506:  72%|███████▏  | 18608/25880 [3:48:07<1:35:29,  1.27it/s]
1|18609|Loss: 0.8427494764328003:  72%|███████▏  | 18608/25880 [3:48:07<1:35:29,  1.27it/s]
1|18609|Loss: 0.8427494764328003:  72%|███████▏  | 18609/25880 [3:48:07<1:34:16,  1.29it/s]
1|18610|Loss: 0.8177473545074463:  72%|███████▏  | 18609/25880 [3:48:08<1:34:16,  1.29it/s]
1|18610|Loss: 0.8177473545074463:  72%|███████▏  | 18610/25880 [3:48:08<1:28:04,  1.38it/s]
1|18611|Loss: 0.857757568359375:  72%|███████▏  | 18610/25880 [3:48:08<1:28:04,  1.38it/s] 
1|18611|Loss: 0.857757568359375:  72%|███████▏  | 18611/25880 [3:48:09<1:27:15,  1.39it/s]
1|18612|Loss: 0.8092992305755615:  72%|███████▏  | 18611/25880 [3:48:09<1:27:15,  1.39it/s]
1|18612|Loss: 0.8092992305755615:  72%|███████▏  | 18612/25880 [3:48:09<1:27:57,  1.38it/s]
1|18613|Loss: 0.9159223437309265:  72%|███████▏  | 18612/25880 [3:48:10<1:27:57,  1.38it/s]
1|18613|Loss: 0.9159223437309265:  72%|███████▏  | 18613/25880 [3:48:10<1:31:38,  1.32it/s]
1|18614|Loss: 0.8394293785095215:  72%|███████▏  | 18613/25880 [3:48:11<1:31:38,  1.32it/s]
1|18614|Loss: 0.8394293785095215:  72%|███████▏  | 18614/25880 [3:48:11<1:29:10,  1.36it/s]
1|18615|Loss: 0.685334324836731:  72%|███████▏  | 18614/25880 [3:48:11<1:29:10,  1.36it/s] 
1|18615|Loss: 0.685334324836731:  72%|███████▏  | 18615/25880 [3:48:12<1:28:47,  1.36it/s]
1|18616|Loss: 0.8821131587028503:  72%|███████▏  | 18615/25880 [3:48:12<1:28:47,  1.36it/s]
1|18616|Loss: 0.8821131587028503:  72%|███████▏  | 18616/25880 [3:48:12<1:32:03,  1.32it/s]
1|18617|Loss: 0.8842213153839111:  72%|███████▏  | 18616/25880 [3:48:13<1:32:03,  1.32it/s]
1|18617|Loss: 0.8842213153839111:  72%|███████▏  | 18617/25880 [3:48:13<1:28:26,  1.37it/s]
1|18618|Loss: 0.8478500247001648:  72%|███████▏  | 18617/25880 [3:48:14<1:28:26,  1.37it/s]
1|18618|Loss: 0.8478500247001648:  72%|███████▏  | 18618/25880 [3:48:14<1:26:56,  1.39it/s]
1|18619|Loss: 1.1207449436187744:  72%|███████▏  | 18618/25880 [3:48:14<1:26:56,  1.39it/s]
1|18619|Loss: 1.1207449436187744:  72%|███████▏  | 18619/25880 [3:48:15<1:27:29,  1.38it/s]
1|18620|Loss: 0.8526878952980042:  72%|███████▏  | 18619/25880 [3:48:15<1:27:29,  1.38it/s]
1|18620|Loss: 0.8526878952980042:  72%|███████▏  | 18620/25880 [3:48:15<1:25:20,  1.42it/s]
1|18621|Loss: 0.8608272075653076:  72%|███████▏  | 18620/25880 [3:48:16<1:25:20,  1.42it/s]
1|18621|Loss: 0.8608272075653076:  72%|███████▏  | 18621/25880 [3:48:16<1:26:17,  1.40it/s]
1|18622|Loss: 0.9047405123710632:  72%|███████▏  | 18621/25880 [3:48:16<1:26:17,  1.40it/s]
1|18622|Loss: 0.9047405123710632:  72%|███████▏  | 18622/25880 [3:48:17<1:26:32,  1.40it/s]
1|18623|Loss: 0.868424117565155:  72%|███████▏  | 18622/25880 [3:48:17<1:26:32,  1.40it/s] 
1|18623|Loss: 0.868424117565155:  72%|███████▏  | 18623/25880 [3:48:17<1:27:29,  1.38it/s]
1|18624|Loss: 0.9182009100914001:  72%|███████▏  | 18623/25880 [3:48:18<1:27:29,  1.38it/s]
1|18624|Loss: 0.9182009100914001:  72%|███████▏  | 18624/25880 [3:48:18<1:33:28,  1.29it/s]
1|18625|Loss: 0.8897366523742676:  72%|███████▏  | 18624/25880 [3:48:19<1:33:28,  1.29it/s]
1|18625|Loss: 0.8897366523742676:  72%|███████▏  | 18625/25880 [3:48:19<1:32:16,  1.31it/s]
1|18626|Loss: 0.8787813186645508:  72%|███████▏  | 18625/25880 [3:48:19<1:32:16,  1.31it/s]
1|18626|Loss: 0.8787813186645508:  72%|███████▏  | 18626/25880 [3:48:20<1:28:08,  1.37it/s]
1|18627|Loss: 0.8378756046295166:  72%|███████▏  | 18626/25880 [3:48:20<1:28:08,  1.37it/s]
1|18627|Loss: 0.8378756046295166:  72%|███████▏  | 18627/25880 [3:48:20<1:28:01,  1.37it/s]
1|18628|Loss: 0.8451305031776428:  72%|███████▏  | 18627/25880 [3:48:21<1:28:01,  1.37it/s]
1|18628|Loss: 0.8451305031776428:  72%|███████▏  | 18628/25880 [3:48:21<1:28:59,  1.36it/s]
1|18629|Loss: 1.0171270370483398:  72%|███████▏  | 18628/25880 [3:48:22<1:28:59,  1.36it/s]
1|18629|Loss: 1.0171270370483398:  72%|███████▏  | 18629/25880 [3:48:22<1:23:09,  1.45it/s]
1|18630|Loss: 0.7318978309631348:  72%|███████▏  | 18629/25880 [3:48:22<1:23:09,  1.45it/s]
1|18630|Loss: 0.7318978309631348:  72%|███████▏  | 18630/25880 [3:48:23<1:26:50,  1.39it/s]
1|18631|Loss: 0.9344605803489685:  72%|███████▏  | 18630/25880 [3:48:23<1:26:50,  1.39it/s]
1|18631|Loss: 0.9344605803489685:  72%|███████▏  | 18631/25880 [3:48:23<1:32:46,  1.30it/s]
1|18632|Loss: 0.870589017868042:  72%|███████▏  | 18631/25880 [3:48:24<1:32:46,  1.30it/s] 
1|18632|Loss: 0.870589017868042:  72%|███████▏  | 18632/25880 [3:48:24<1:30:19,  1.34it/s]
1|18633|Loss: 0.9136155843734741:  72%|███████▏  | 18632/25880 [3:48:25<1:30:19,  1.34it/s]
1|18633|Loss: 0.9136155843734741:  72%|███████▏  | 18633/25880 [3:48:25<1:32:13,  1.31it/s]
1|18634|Loss: 1.1604857444763184:  72%|███████▏  | 18633/25880 [3:48:25<1:32:13,  1.31it/s]
1|18634|Loss: 1.1604857444763184:  72%|███████▏  | 18634/25880 [3:48:26<1:27:42,  1.38it/s]
1|18635|Loss: 0.86543869972229:  72%|███████▏  | 18634/25880 [3:48:26<1:27:42,  1.38it/s]  
1|18635|Loss: 0.86543869972229:  72%|███████▏  | 18635/25880 [3:48:26<1:26:35,  1.39it/s]
1|18636|Loss: 0.8575583100318909:  72%|███████▏  | 18635/25880 [3:48:27<1:26:35,  1.39it/s]
1|18636|Loss: 0.8575583100318909:  72%|███████▏  | 18636/25880 [3:48:27<1:30:17,  1.34it/s]
1|18637|Loss: 0.779725193977356:  72%|███████▏  | 18636/25880 [3:48:28<1:30:17,  1.34it/s] 
1|18637|Loss: 0.779725193977356:  72%|███████▏  | 18637/25880 [3:48:28<1:38:20,  1.23it/s]
1|18638|Loss: 0.8763450980186462:  72%|███████▏  | 18637/25880 [3:48:29<1:38:20,  1.23it/s]
1|18638|Loss: 0.8763450980186462:  72%|███████▏  | 18638/25880 [3:48:29<1:41:08,  1.19it/s]
1|18639|Loss: 0.8330129981040955:  72%|███████▏  | 18638/25880 [3:48:29<1:41:08,  1.19it/s]
1|18639|Loss: 0.8330129981040955:  72%|███████▏  | 18639/25880 [3:48:30<1:40:29,  1.20it/s]
1|18640|Loss: 0.7257062196731567:  72%|███████▏  | 18639/25880 [3:48:30<1:40:29,  1.20it/s]
1|18640|Loss: 0.7257062196731567:  72%|███████▏  | 18640/25880 [3:48:31<1:36:29,  1.25it/s]
1|18641|Loss: 0.854515790939331:  72%|███████▏  | 18640/25880 [3:48:31<1:36:29,  1.25it/s] 
1|18641|Loss: 0.854515790939331:  72%|███████▏  | 18641/25880 [3:48:31<1:33:54,  1.28it/s]
1|18642|Loss: 1.0370341539382935:  72%|███████▏  | 18641/25880 [3:48:32<1:33:54,  1.28it/s]
1|18642|Loss: 1.0370341539382935:  72%|███████▏  | 18642/25880 [3:48:32<1:36:15,  1.25it/s]
1|18643|Loss: 0.8507555723190308:  72%|███████▏  | 18642/25880 [3:48:33<1:36:15,  1.25it/s]
1|18643|Loss: 0.8507555723190308:  72%|███████▏  | 18643/25880 [3:48:33<1:34:08,  1.28it/s]
1|18644|Loss: 0.9063679575920105:  72%|███████▏  | 18643/25880 [3:48:33<1:34:08,  1.28it/s]
1|18644|Loss: 0.9063679575920105:  72%|███████▏  | 18644/25880 [3:48:33<1:25:48,  1.41it/s]
1|18645|Loss: 0.9389713406562805:  72%|███████▏  | 18644/25880 [3:48:34<1:25:48,  1.41it/s]
1|18645|Loss: 0.9389713406562805:  72%|███████▏  | 18645/25880 [3:48:34<1:25:15,  1.41it/s]
1|18646|Loss: 0.8978310227394104:  72%|███████▏  | 18645/25880 [3:48:34<1:25:15,  1.41it/s]
1|18646|Loss: 0.8978310227394104:  72%|███████▏  | 18646/25880 [3:48:35<1:28:02,  1.37it/s]
1|18647|Loss: 0.6710246801376343:  72%|███████▏  | 18646/25880 [3:48:35<1:28:02,  1.37it/s]
1|18647|Loss: 0.6710246801376343:  72%|███████▏  | 18647/25880 [3:48:36<1:30:11,  1.34it/s]
1|18648|Loss: 0.7586431503295898:  72%|███████▏  | 18647/25880 [3:48:36<1:30:11,  1.34it/s]
1|18648|Loss: 0.7586431503295898:  72%|███████▏  | 18648/25880 [3:48:36<1:30:05,  1.34it/s]
1|18649|Loss: 0.8680779337882996:  72%|███████▏  | 18648/25880 [3:48:37<1:30:05,  1.34it/s]
1|18649|Loss: 0.8680779337882996:  72%|███████▏  | 18649/25880 [3:48:37<1:28:46,  1.36it/s]
1|18650|Loss: 0.8036900162696838:  72%|███████▏  | 18649/25880 [3:48:37<1:28:46,  1.36it/s]
1|18650|Loss: 0.8036900162696838:  72%|███████▏  | 18650/25880 [3:48:38<1:21:51,  1.47it/s]
1|18651|Loss: 0.880902886390686:  72%|███████▏  | 18650/25880 [3:48:38<1:21:51,  1.47it/s] 
1|18651|Loss: 0.880902886390686:  72%|███████▏  | 18651/25880 [3:48:38<1:26:20,  1.40it/s]
1|18652|Loss: 0.9093225598335266:  72%|███████▏  | 18651/25880 [3:48:39<1:26:20,  1.40it/s]
1|18652|Loss: 0.9093225598335266:  72%|███████▏  | 18652/25880 [3:48:39<1:33:28,  1.29it/s]
1|18653|Loss: 0.9063495397567749:  72%|███████▏  | 18652/25880 [3:48:40<1:33:28,  1.29it/s]
1|18653|Loss: 0.9063495397567749:  72%|███████▏  | 18653/25880 [3:48:40<1:33:08,  1.29it/s]
1|18654|Loss: 0.6727555990219116:  72%|███████▏  | 18653/25880 [3:48:40<1:33:08,  1.29it/s]
1|18654|Loss: 0.6727555990219116:  72%|███████▏  | 18654/25880 [3:48:41<1:27:11,  1.38it/s]
1|18655|Loss: 0.8806122541427612:  72%|███████▏  | 18654/25880 [3:48:41<1:27:11,  1.38it/s]
1|18655|Loss: 0.8806122541427612:  72%|███████▏  | 18655/25880 [3:48:41<1:22:57,  1.45it/s]
1|18656|Loss: 0.9032637476921082:  72%|███████▏  | 18655/25880 [3:48:42<1:22:57,  1.45it/s]
1|18656|Loss: 0.9032637476921082:  72%|███████▏  | 18656/25880 [3:48:42<1:17:48,  1.55it/s]
1|18657|Loss: 0.8611774444580078:  72%|███████▏  | 18656/25880 [3:48:42<1:17:48,  1.55it/s]
1|18657|Loss: 0.8611774444580078:  72%|███████▏  | 18657/25880 [3:48:43<1:23:29,  1.44it/s]
1|18658|Loss: 0.9071928858757019:  72%|███████▏  | 18657/25880 [3:48:43<1:23:29,  1.44it/s]
1|18658|Loss: 0.9071928858757019:  72%|███████▏  | 18658/25880 [3:48:43<1:26:16,  1.40it/s]
1|18659|Loss: 0.8742004036903381:  72%|███████▏  | 18658/25880 [3:48:44<1:26:16,  1.40it/s]
1|18659|Loss: 0.8742004036903381:  72%|███████▏  | 18659/25880 [3:48:44<1:24:23,  1.43it/s]
1|18660|Loss: 0.9050434231758118:  72%|███████▏  | 18659/25880 [3:48:45<1:24:23,  1.43it/s]
1|18660|Loss: 0.9050434231758118:  72%|███████▏  | 18660/25880 [3:48:45<1:24:01,  1.43it/s]
1|18661|Loss: 0.8328185677528381:  72%|███████▏  | 18660/25880 [3:48:45<1:24:01,  1.43it/s]
1|18661|Loss: 0.8328185677528381:  72%|███████▏  | 18661/25880 [3:48:45<1:16:45,  1.57it/s]
1|18662|Loss: 0.8512091636657715:  72%|███████▏  | 18661/25880 [3:48:46<1:16:45,  1.57it/s]
1|18662|Loss: 0.8512091636657715:  72%|███████▏  | 18662/25880 [3:48:46<1:17:06,  1.56it/s]
1|18663|Loss: 0.8507969379425049:  72%|███████▏  | 18662/25880 [3:48:46<1:17:06,  1.56it/s]
1|18663|Loss: 0.8507969379425049:  72%|███████▏  | 18663/25880 [3:48:47<1:21:45,  1.47it/s]
1|18664|Loss: 0.8853400945663452:  72%|███████▏  | 18663/25880 [3:48:47<1:21:45,  1.47it/s]
1|18664|Loss: 0.8853400945663452:  72%|███████▏  | 18664/25880 [3:48:47<1:23:25,  1.44it/s]
1|18665|Loss: 0.8923993706703186:  72%|███████▏  | 18664/25880 [3:48:48<1:23:25,  1.44it/s]
1|18665|Loss: 0.8923993706703186:  72%|███████▏  | 18665/25880 [3:48:48<1:27:20,  1.38it/s]
1|18666|Loss: 0.7528252005577087:  72%|███████▏  | 18665/25880 [3:48:49<1:27:20,  1.38it/s]
1|18666|Loss: 0.7528252005577087:  72%|███████▏  | 18666/25880 [3:48:49<1:28:12,  1.36it/s]
1|18667|Loss: 0.7824936509132385:  72%|███████▏  | 18666/25880 [3:48:49<1:28:12,  1.36it/s]
1|18667|Loss: 0.7824936509132385:  72%|███████▏  | 18667/25880 [3:48:50<1:23:58,  1.43it/s]
1|18668|Loss: 0.7190370559692383:  72%|███████▏  | 18667/25880 [3:48:50<1:23:58,  1.43it/s]
1|18668|Loss: 0.7190370559692383:  72%|███████▏  | 18668/25880 [3:48:50<1:27:41,  1.37it/s]
1|18669|Loss: 0.7524110078811646:  72%|███████▏  | 18668/25880 [3:48:51<1:27:41,  1.37it/s]
1|18669|Loss: 0.7524110078811646:  72%|███████▏  | 18669/25880 [3:48:51<1:27:47,  1.37it/s]
1|18670|Loss: 1.0143518447875977:  72%|███████▏  | 18669/25880 [3:48:52<1:27:47,  1.37it/s]
1|18670|Loss: 1.0143518447875977:  72%|███████▏  | 18670/25880 [3:48:52<1:29:36,  1.34it/s]
1|18671|Loss: 0.7268403172492981:  72%|███████▏  | 18670/25880 [3:48:52<1:29:36,  1.34it/s]
1|18671|Loss: 0.7268403172492981:  72%|███████▏  | 18671/25880 [3:48:53<1:30:06,  1.33it/s]
1|18672|Loss: 0.6951806545257568:  72%|███████▏  | 18671/25880 [3:48:53<1:30:06,  1.33it/s]
1|18672|Loss: 0.6951806545257568:  72%|███████▏  | 18672/25880 [3:48:53<1:28:47,  1.35it/s]
1|18673|Loss: 0.828938364982605:  72%|███████▏  | 18672/25880 [3:48:54<1:28:47,  1.35it/s] 
1|18673|Loss: 0.828938364982605:  72%|███████▏  | 18673/25880 [3:48:54<1:29:46,  1.34it/s]
1|18674|Loss: 0.7445287108421326:  72%|███████▏  | 18673/25880 [3:48:55<1:29:46,  1.34it/s]
1|18674|Loss: 0.7445287108421326:  72%|███████▏  | 18674/25880 [3:48:55<1:22:51,  1.45it/s]
1|18675|Loss: 0.7392920255661011:  72%|███████▏  | 18674/25880 [3:48:55<1:22:51,  1.45it/s]
1|18675|Loss: 0.7392920255661011:  72%|███████▏  | 18675/25880 [3:48:55<1:22:30,  1.46it/s]
1|18676|Loss: 0.7900672554969788:  72%|███████▏  | 18675/25880 [3:48:56<1:22:30,  1.46it/s]
1|18676|Loss: 0.7900672554969788:  72%|███████▏  | 18676/25880 [3:48:56<1:23:13,  1.44it/s]
1|18677|Loss: 0.8603700995445251:  72%|███████▏  | 18676/25880 [3:48:56<1:23:13,  1.44it/s]
1|18677|Loss: 0.8603700995445251:  72%|███████▏  | 18677/25880 [3:48:57<1:16:14,  1.57it/s]
1|18678|Loss: 0.7884894609451294:  72%|███████▏  | 18677/25880 [3:48:57<1:16:14,  1.57it/s]
1|18678|Loss: 0.7884894609451294:  72%|███████▏  | 18678/25880 [3:48:57<1:17:32,  1.55it/s]
1|18679|Loss: 0.5347090363502502:  72%|███████▏  | 18678/25880 [3:48:58<1:17:32,  1.55it/s]
1|18679|Loss: 0.5347090363502502:  72%|███████▏  | 18679/25880 [3:48:58<1:20:34,  1.49it/s]
1|18680|Loss: 0.9551825523376465:  72%|███████▏  | 18679/25880 [3:48:58<1:20:34,  1.49it/s]
1|18680|Loss: 0.9551825523376465:  72%|███████▏  | 18680/25880 [3:48:59<1:18:35,  1.53it/s]
1|18681|Loss: 0.8055480718612671:  72%|███████▏  | 18680/25880 [3:48:59<1:18:35,  1.53it/s]
1|18681|Loss: 0.8055480718612671:  72%|███████▏  | 18681/25880 [3:48:59<1:20:31,  1.49it/s]
1|18682|Loss: 0.8340752124786377:  72%|███████▏  | 18681/25880 [3:49:00<1:20:31,  1.49it/s]
1|18682|Loss: 0.8340752124786377:  72%|███████▏  | 18682/25880 [3:49:00<1:19:25,  1.51it/s]
1|18683|Loss: 0.735465943813324:  72%|███████▏  | 18682/25880 [3:49:00<1:19:25,  1.51it/s] 
1|18683|Loss: 0.735465943813324:  72%|███████▏  | 18683/25880 [3:49:01<1:14:38,  1.61it/s]
1|18684|Loss: 0.8235563039779663:  72%|███████▏  | 18683/25880 [3:49:01<1:14:38,  1.61it/s]
1|18684|Loss: 0.8235563039779663:  72%|███████▏  | 18684/25880 [3:49:01<1:15:51,  1.58it/s]
1|18685|Loss: 0.8981698155403137:  72%|███████▏  | 18684/25880 [3:49:02<1:15:51,  1.58it/s]
1|18685|Loss: 0.8981698155403137:  72%|███████▏  | 18685/25880 [3:49:02<1:21:57,  1.46it/s]
1|18686|Loss: 0.8679375648498535:  72%|███████▏  | 18685/25880 [3:49:02<1:21:57,  1.46it/s]
1|18686|Loss: 0.8679375648498535:  72%|███████▏  | 18686/25880 [3:49:03<1:24:26,  1.42it/s]
1|18687|Loss: 0.7828188538551331:  72%|███████▏  | 18686/25880 [3:49:03<1:24:26,  1.42it/s]
1|18687|Loss: 0.7828188538551331:  72%|███████▏  | 18687/25880 [3:49:03<1:23:04,  1.44it/s]
1|18688|Loss: 0.7680678963661194:  72%|███████▏  | 18687/25880 [3:49:04<1:23:04,  1.44it/s]
1|18688|Loss: 0.7680678963661194:  72%|███████▏  | 18688/25880 [3:49:04<1:24:26,  1.42it/s]
1|18689|Loss: 0.7953853607177734:  72%|███████▏  | 18688/25880 [3:49:05<1:24:26,  1.42it/s]
1|18689|Loss: 0.7953853607177734:  72%|███████▏  | 18689/25880 [3:49:05<1:25:36,  1.40it/s]
1|18690|Loss: 0.7551480531692505:  72%|███████▏  | 18689/25880 [3:49:05<1:25:36,  1.40it/s]
1|18690|Loss: 0.7551480531692505:  72%|███████▏  | 18690/25880 [3:49:06<1:28:49,  1.35it/s]
1|18691|Loss: 0.8737345337867737:  72%|███████▏  | 18690/25880 [3:49:06<1:28:49,  1.35it/s]
1|18691|Loss: 0.8737345337867737:  72%|███████▏  | 18691/25880 [3:49:06<1:25:46,  1.40it/s]
1|18692|Loss: 0.9040316939353943:  72%|███████▏  | 18691/25880 [3:49:07<1:25:46,  1.40it/s]
1|18692|Loss: 0.9040316939353943:  72%|███████▏  | 18692/25880 [3:49:07<1:24:50,  1.41it/s]
1|18693|Loss: 1.085481882095337:  72%|███████▏  | 18692/25880 [3:49:07<1:24:50,  1.41it/s] 
1|18693|Loss: 1.085481882095337:  72%|███████▏  | 18693/25880 [3:49:08<1:21:23,  1.47it/s]
1|18694|Loss: 0.9051578640937805:  72%|███████▏  | 18693/25880 [3:49:08<1:21:23,  1.47it/s]
1|18694|Loss: 0.9051578640937805:  72%|███████▏  | 18694/25880 [3:49:08<1:17:05,  1.55it/s]
1|18695|Loss: 0.7290628552436829:  72%|███████▏  | 18694/25880 [3:49:09<1:17:05,  1.55it/s]
1|18695|Loss: 0.7290628552436829:  72%|███████▏  | 18695/25880 [3:49:09<1:16:10,  1.57it/s]
1|18696|Loss: 0.7779339551925659:  72%|███████▏  | 18695/25880 [3:49:09<1:16:10,  1.57it/s]
1|18696|Loss: 0.7779339551925659:  72%|███████▏  | 18696/25880 [3:49:10<1:21:03,  1.48it/s]
1|18697|Loss: 0.8465849161148071:  72%|███████▏  | 18696/25880 [3:49:10<1:21:03,  1.48it/s]
1|18697|Loss: 0.8465849161148071:  72%|███████▏  | 18697/25880 [3:49:10<1:25:26,  1.40it/s]
1|18698|Loss: 0.8009031414985657:  72%|███████▏  | 18697/25880 [3:49:11<1:25:26,  1.40it/s]
1|18698|Loss: 0.8009031414985657:  72%|███████▏  | 18698/25880 [3:49:11<1:24:02,  1.42it/s]
1|18699|Loss: 0.8680303692817688:  72%|███████▏  | 18698/25880 [3:49:11<1:24:02,  1.42it/s]
1|18699|Loss: 0.8680303692817688:  72%|███████▏  | 18699/25880 [3:49:12<1:24:18,  1.42it/s]
1|18700|Loss: 0.7844849228858948:  72%|███████▏  | 18699/25880 [3:49:12<1:24:18,  1.42it/s]
1|18700|Loss: 0.7844849228858948:  72%|███████▏  | 18700/25880 [3:49:12<1:24:21,  1.42it/s]
1|18701|Loss: 0.8902266621589661:  72%|███████▏  | 18700/25880 [3:49:13<1:24:21,  1.42it/s]
1|18701|Loss: 0.8902266621589661:  72%|███████▏  | 18701/25880 [3:49:13<1:24:01,  1.42it/s]
1|18702|Loss: 0.9174244999885559:  72%|███████▏  | 18701/25880 [3:49:14<1:24:01,  1.42it/s]
1|18702|Loss: 0.9174244999885559:  72%|███████▏  | 18702/25880 [3:49:14<1:30:07,  1.33it/s]
1|18703|Loss: 0.8518999814987183:  72%|███████▏  | 18702/25880 [3:49:15<1:30:07,  1.33it/s]
1|18703|Loss: 0.8518999814987183:  72%|███████▏  | 18703/25880 [3:49:15<1:32:41,  1.29it/s]
1|18704|Loss: 0.7533954977989197:  72%|███████▏  | 18703/25880 [3:49:15<1:32:41,  1.29it/s]
1|18704|Loss: 0.7533954977989197:  72%|███████▏  | 18704/25880 [3:49:16<1:27:23,  1.37it/s]
1|18705|Loss: 0.8492103815078735:  72%|███████▏  | 18704/25880 [3:49:16<1:27:23,  1.37it/s]
1|18705|Loss: 0.8492103815078735:  72%|███████▏  | 18705/25880 [3:49:16<1:29:03,  1.34it/s]
1|18706|Loss: 0.8380762934684753:  72%|███████▏  | 18705/25880 [3:49:17<1:29:03,  1.34it/s]
1|18706|Loss: 0.8380762934684753:  72%|███████▏  | 18706/25880 [3:49:17<1:22:56,  1.44it/s]
1|18707|Loss: 0.844653308391571:  72%|███████▏  | 18706/25880 [3:49:17<1:22:56,  1.44it/s] 
1|18707|Loss: 0.844653308391571:  72%|███████▏  | 18707/25880 [3:49:18<1:23:17,  1.44it/s]
1|18708|Loss: 0.8941892981529236:  72%|███████▏  | 18707/25880 [3:49:18<1:23:17,  1.44it/s]
1|18708|Loss: 0.8941892981529236:  72%|███████▏  | 18708/25880 [3:49:18<1:26:55,  1.38it/s]
1|18709|Loss: 0.8008573651313782:  72%|███████▏  | 18708/25880 [3:49:19<1:26:55,  1.38it/s]
1|18709|Loss: 0.8008573651313782:  72%|███████▏  | 18709/25880 [3:49:19<1:21:40,  1.46it/s]
1|18710|Loss: 0.8098511695861816:  72%|███████▏  | 18709/25880 [3:49:19<1:21:40,  1.46it/s]
1|18710|Loss: 0.8098511695861816:  72%|███████▏  | 18710/25880 [3:49:20<1:20:59,  1.48it/s]
1|18711|Loss: 0.8197125792503357:  72%|███████▏  | 18710/25880 [3:49:20<1:20:59,  1.48it/s]
1|18711|Loss: 0.8197125792503357:  72%|███████▏  | 18711/25880 [3:49:20<1:26:16,  1.38it/s]
1|18712|Loss: 0.7832635045051575:  72%|███████▏  | 18711/25880 [3:49:21<1:26:16,  1.38it/s]
1|18712|Loss: 0.7832635045051575:  72%|███████▏  | 18712/25880 [3:49:21<1:31:10,  1.31it/s]
1|18713|Loss: 0.7861914038658142:  72%|███████▏  | 18712/25880 [3:49:22<1:31:10,  1.31it/s]
1|18713|Loss: 0.7861914038658142:  72%|███████▏  | 18713/25880 [3:49:22<1:30:33,  1.32it/s]
1|18714|Loss: 0.7516858577728271:  72%|███████▏  | 18713/25880 [3:49:22<1:30:33,  1.32it/s]
1|18714|Loss: 0.7516858577728271:  72%|███████▏  | 18714/25880 [3:49:23<1:28:42,  1.35it/s]
1|18715|Loss: 0.8017347455024719:  72%|███████▏  | 18714/25880 [3:49:23<1:28:42,  1.35it/s]
1|18715|Loss: 0.8017347455024719:  72%|███████▏  | 18715/25880 [3:49:23<1:27:02,  1.37it/s]
1|18716|Loss: 0.9326499104499817:  72%|███████▏  | 18715/25880 [3:49:24<1:27:02,  1.37it/s]
1|18716|Loss: 0.9326499104499817:  72%|███████▏  | 18716/25880 [3:49:24<1:26:46,  1.38it/s]
1|18717|Loss: 0.82761150598526:  72%|███████▏  | 18716/25880 [3:49:25<1:26:46,  1.38it/s]  
1|18717|Loss: 0.82761150598526:  72%|███████▏  | 18717/25880 [3:49:25<1:25:57,  1.39it/s]
1|18718|Loss: 0.8328751921653748:  72%|███████▏  | 18717/25880 [3:49:25<1:25:57,  1.39it/s]
1|18718|Loss: 0.8328751921653748:  72%|███████▏  | 18718/25880 [3:49:26<1:26:06,  1.39it/s]
1|18719|Loss: 0.7656155228614807:  72%|███████▏  | 18718/25880 [3:49:26<1:26:06,  1.39it/s]
1|18719|Loss: 0.7656155228614807:  72%|███████▏  | 18719/25880 [3:49:26<1:31:04,  1.31it/s]
1|18720|Loss: 0.9583816528320312:  72%|███████▏  | 18719/25880 [3:49:27<1:31:04,  1.31it/s]
1|18720|Loss: 0.9583816528320312:  72%|███████▏  | 18720/25880 [3:49:27<1:33:24,  1.28it/s]
1|18721|Loss: 0.8283843398094177:  72%|███████▏  | 18720/25880 [3:49:28<1:33:24,  1.28it/s]
1|18721|Loss: 0.8283843398094177:  72%|███████▏  | 18721/25880 [3:49:28<1:36:21,  1.24it/s]
1|18722|Loss: 0.727533757686615:  72%|███████▏  | 18721/25880 [3:49:29<1:36:21,  1.24it/s] 
1|18722|Loss: 0.727533757686615:  72%|███████▏  | 18722/25880 [3:49:29<1:31:41,  1.30it/s]
1|18723|Loss: 0.8608160018920898:  72%|███████▏  | 18722/25880 [3:49:29<1:31:41,  1.30it/s]
1|18723|Loss: 0.8608160018920898:  72%|███████▏  | 18723/25880 [3:49:30<1:29:56,  1.33it/s]
1|18724|Loss: 0.807083010673523:  72%|███████▏  | 18723/25880 [3:49:30<1:29:56,  1.33it/s] 
1|18724|Loss: 0.807083010673523:  72%|███████▏  | 18724/25880 [3:49:30<1:29:48,  1.33it/s]
1|18725|Loss: 0.8949522376060486:  72%|███████▏  | 18724/25880 [3:49:31<1:29:48,  1.33it/s]
1|18725|Loss: 0.8949522376060486:  72%|███████▏  | 18725/25880 [3:49:31<1:28:30,  1.35it/s]
1|18726|Loss: 0.7663095593452454:  72%|███████▏  | 18725/25880 [3:49:31<1:28:30,  1.35it/s]
1|18726|Loss: 0.7663095593452454:  72%|███████▏  | 18726/25880 [3:49:32<1:23:39,  1.43it/s]
1|18727|Loss: 0.8667999505996704:  72%|███████▏  | 18726/25880 [3:49:32<1:23:39,  1.43it/s]
1|18727|Loss: 0.8667999505996704:  72%|███████▏  | 18727/25880 [3:49:32<1:19:16,  1.50it/s]
1|18728|Loss: 0.6745514869689941:  72%|███████▏  | 18727/25880 [3:49:33<1:19:16,  1.50it/s]
1|18728|Loss: 0.6745514869689941:  72%|███████▏  | 18728/25880 [3:49:33<1:20:41,  1.48it/s]
1|18729|Loss: 0.9504343271255493:  72%|███████▏  | 18728/25880 [3:49:33<1:20:41,  1.48it/s]
1|18729|Loss: 0.9504343271255493:  72%|███████▏  | 18729/25880 [3:49:34<1:19:58,  1.49it/s]
1|18730|Loss: 0.9337112903594971:  72%|███████▏  | 18729/25880 [3:49:34<1:19:58,  1.49it/s]
1|18730|Loss: 0.9337112903594971:  72%|███████▏  | 18730/25880 [3:49:34<1:18:16,  1.52it/s]
1|18731|Loss: 0.7996196150779724:  72%|███████▏  | 18730/25880 [3:49:35<1:18:16,  1.52it/s]
1|18731|Loss: 0.7996196150779724:  72%|███████▏  | 18731/25880 [3:49:35<1:22:00,  1.45it/s]
1|18732|Loss: 0.885137140750885:  72%|███████▏  | 18731/25880 [3:49:35<1:22:00,  1.45it/s] 
1|18732|Loss: 0.885137140750885:  72%|███████▏  | 18732/25880 [3:49:36<1:26:15,  1.38it/s]
1|18733|Loss: 0.8549308776855469:  72%|███████▏  | 18732/25880 [3:49:36<1:26:15,  1.38it/s]
1|18733|Loss: 0.8549308776855469:  72%|███████▏  | 18733/25880 [3:49:36<1:24:36,  1.41it/s]
1|18734|Loss: 0.9239997863769531:  72%|███████▏  | 18733/25880 [3:49:37<1:24:36,  1.41it/s]
1|18734|Loss: 0.9239997863769531:  72%|███████▏  | 18734/25880 [3:49:37<1:22:18,  1.45it/s]
1|18735|Loss: 0.8370220065116882:  72%|███████▏  | 18734/25880 [3:49:37<1:22:18,  1.45it/s]
1|18735|Loss: 0.8370220065116882:  72%|███████▏  | 18735/25880 [3:49:38<1:23:12,  1.43it/s]
1|18736|Loss: 0.9471138715744019:  72%|███████▏  | 18735/25880 [3:49:38<1:23:12,  1.43it/s]
1|18736|Loss: 0.9471138715744019:  72%|███████▏  | 18736/25880 [3:49:39<1:25:48,  1.39it/s]
1|18737|Loss: 0.8515176773071289:  72%|███████▏  | 18736/25880 [3:49:39<1:25:48,  1.39it/s]
1|18737|Loss: 0.8515176773071289:  72%|███████▏  | 18737/25880 [3:49:39<1:26:52,  1.37it/s]
1|18738|Loss: 0.7982380390167236:  72%|███████▏  | 18737/25880 [3:49:40<1:26:52,  1.37it/s]
1|18738|Loss: 0.7982380390167236:  72%|███████▏  | 18738/25880 [3:49:40<1:26:04,  1.38it/s]
1|18739|Loss: 1.003957986831665:  72%|███████▏  | 18738/25880 [3:49:40<1:26:04,  1.38it/s] 
1|18739|Loss: 1.003957986831665:  72%|███████▏  | 18739/25880 [3:49:41<1:22:42,  1.44it/s]
1|18740|Loss: 0.9112368226051331:  72%|███████▏  | 18739/25880 [3:49:41<1:22:42,  1.44it/s]
1|18740|Loss: 0.9112368226051331:  72%|███████▏  | 18740/25880 [3:49:41<1:20:46,  1.47it/s]
1|18741|Loss: 0.8629180192947388:  72%|███████▏  | 18740/25880 [3:49:42<1:20:46,  1.47it/s]
1|18741|Loss: 0.8629180192947388:  72%|███████▏  | 18741/25880 [3:49:42<1:22:40,  1.44it/s]
1|18742|Loss: 0.8861826062202454:  72%|███████▏  | 18741/25880 [3:49:42<1:22:40,  1.44it/s]
1|18742|Loss: 0.8861826062202454:  72%|███████▏  | 18742/25880 [3:49:43<1:28:09,  1.35it/s]
1|18743|Loss: 0.8929269313812256:  72%|███████▏  | 18742/25880 [3:49:43<1:28:09,  1.35it/s]
1|18743|Loss: 0.8929269313812256:  72%|███████▏  | 18743/25880 [3:49:44<1:25:50,  1.39it/s]
1|18744|Loss: 0.9077885746955872:  72%|███████▏  | 18743/25880 [3:49:44<1:25:50,  1.39it/s]
1|18744|Loss: 0.9077885746955872:  72%|███████▏  | 18744/25880 [3:49:44<1:25:18,  1.39it/s]
1|18745|Loss: 0.7987871170043945:  72%|███████▏  | 18744/25880 [3:49:45<1:25:18,  1.39it/s]
1|18745|Loss: 0.7987871170043945:  72%|███████▏  | 18745/25880 [3:49:45<1:25:33,  1.39it/s]
1|18746|Loss: 0.6914114952087402:  72%|███████▏  | 18745/25880 [3:49:45<1:25:33,  1.39it/s]
1|18746|Loss: 0.6914114952087402:  72%|███████▏  | 18746/25880 [3:49:46<1:24:56,  1.40it/s]
1|18747|Loss: 0.8523383140563965:  72%|███████▏  | 18746/25880 [3:49:46<1:24:56,  1.40it/s]
1|18747|Loss: 0.8523383140563965:  72%|███████▏  | 18747/25880 [3:49:46<1:22:25,  1.44it/s]
1|18748|Loss: 0.9649246335029602:  72%|███████▏  | 18747/25880 [3:49:47<1:22:25,  1.44it/s]
1|18748|Loss: 0.9649246335029602:  72%|███████▏  | 18748/25880 [3:49:47<1:26:06,  1.38it/s]
1|18749|Loss: 0.8660078048706055:  72%|███████▏  | 18748/25880 [3:49:48<1:26:06,  1.38it/s]
1|18749|Loss: 0.8660078048706055:  72%|███████▏  | 18749/25880 [3:49:48<1:25:57,  1.38it/s]
1|18750|Loss: 0.8667972683906555:  72%|███████▏  | 18749/25880 [3:49:48<1:25:57,  1.38it/s]
1|18750|Loss: 0.8667972683906555:  72%|███████▏  | 18750/25880 [3:49:48<1:22:53,  1.43it/s]
1|18751|Loss: 0.7858012914657593:  72%|███████▏  | 18750/25880 [3:49:49<1:22:53,  1.43it/s]
1|18751|Loss: 0.7858012914657593:  72%|███████▏  | 18751/25880 [3:49:49<1:20:01,  1.48it/s]
1|18752|Loss: 0.870038628578186:  72%|███████▏  | 18751/25880 [3:49:49<1:20:01,  1.48it/s] 
1|18752|Loss: 0.870038628578186:  72%|███████▏  | 18752/25880 [3:49:50<1:14:46,  1.59it/s]
1|18753|Loss: 0.735503613948822:  72%|███████▏  | 18752/25880 [3:49:50<1:14:46,  1.59it/s]
1|18753|Loss: 0.735503613948822:  72%|███████▏  | 18753/25880 [3:49:50<1:19:33,  1.49it/s]
1|18754|Loss: 0.7430638074874878:  72%|███████▏  | 18753/25880 [3:49:51<1:19:33,  1.49it/s]
1|18754|Loss: 0.7430638074874878:  72%|███████▏  | 18754/25880 [3:49:51<1:19:08,  1.50it/s]
1|18755|Loss: 0.8414708375930786:  72%|███████▏  | 18754/25880 [3:49:51<1:19:08,  1.50it/s]
1|18755|Loss: 0.8414708375930786:  72%|███████▏  | 18755/25880 [3:49:52<1:18:04,  1.52it/s]
1|18756|Loss: 0.9494224190711975:  72%|███████▏  | 18755/25880 [3:49:52<1:18:04,  1.52it/s]
1|18756|Loss: 0.9494224190711975:  72%|███████▏  | 18756/25880 [3:49:52<1:23:23,  1.42it/s]
1|18757|Loss: 0.8382683396339417:  72%|███████▏  | 18756/25880 [3:49:53<1:23:23,  1.42it/s]
1|18757|Loss: 0.8382683396339417:  72%|███████▏  | 18757/25880 [3:49:53<1:22:47,  1.43it/s]
1|18758|Loss: 0.804040789604187:  72%|███████▏  | 18757/25880 [3:49:54<1:22:47,  1.43it/s] 
1|18758|Loss: 0.804040789604187:  72%|███████▏  | 18758/25880 [3:49:54<1:19:59,  1.48it/s]
1|18759|Loss: 0.732906699180603:  72%|███████▏  | 18758/25880 [3:49:54<1:19:59,  1.48it/s]
1|18759|Loss: 0.732906699180603:  72%|███████▏  | 18759/25880 [3:49:54<1:17:49,  1.52it/s]
1|18760|Loss: 0.7880977988243103:  72%|███████▏  | 18759/25880 [3:49:55<1:17:49,  1.52it/s]
1|18760|Loss: 0.7880977988243103:  72%|███████▏  | 18760/25880 [3:49:55<1:13:27,  1.62it/s]
1|18761|Loss: 0.8148568272590637:  72%|███████▏  | 18760/25880 [3:49:55<1:13:27,  1.62it/s]
1|18761|Loss: 0.8148568272590637:  72%|███████▏  | 18761/25880 [3:49:56<1:16:12,  1.56it/s]
1|18762|Loss: 0.8592513203620911:  72%|███████▏  | 18761/25880 [3:49:56<1:16:12,  1.56it/s]
1|18762|Loss: 0.8592513203620911:  72%|███████▏  | 18762/25880 [3:49:56<1:19:44,  1.49it/s]
1|18763|Loss: 0.7605369687080383:  72%|███████▏  | 18762/25880 [3:49:57<1:19:44,  1.49it/s]
1|18763|Loss: 0.7605369687080383:  72%|███████▎  | 18763/25880 [3:49:57<1:22:07,  1.44it/s]
1|18764|Loss: 0.6528616547584534:  72%|███████▎  | 18763/25880 [3:49:57<1:22:07,  1.44it/s]
1|18764|Loss: 0.6528616547584534:  73%|███████▎  | 18764/25880 [3:49:58<1:17:41,  1.53it/s]
1|18765|Loss: 0.9103946685791016:  73%|███████▎  | 18764/25880 [3:49:58<1:17:41,  1.53it/s]
1|18765|Loss: 0.9103946685791016:  73%|███████▎  | 18765/25880 [3:49:58<1:17:57,  1.52it/s]
1|18766|Loss: 0.7555999755859375:  73%|███████▎  | 18765/25880 [3:49:59<1:17:57,  1.52it/s]
1|18766|Loss: 0.7555999755859375:  73%|███████▎  | 18766/25880 [3:49:59<1:20:12,  1.48it/s]
1|18767|Loss: 0.7853268384933472:  73%|███████▎  | 18766/25880 [3:49:59<1:20:12,  1.48it/s]
1|18767|Loss: 0.7853268384933472:  73%|███████▎  | 18767/25880 [3:50:00<1:15:35,  1.57it/s]
1|18768|Loss: 0.8807909488677979:  73%|███████▎  | 18767/25880 [3:50:00<1:15:35,  1.57it/s]
1|18768|Loss: 0.8807909488677979:  73%|███████▎  | 18768/25880 [3:50:00<1:12:58,  1.62it/s]
1|18769|Loss: 0.8783841133117676:  73%|███████▎  | 18768/25880 [3:50:01<1:12:58,  1.62it/s]
1|18769|Loss: 0.8783841133117676:  73%|███████▎  | 18769/25880 [3:50:01<1:18:05,  1.52it/s]
1|18770|Loss: 0.8591641187667847:  73%|███████▎  | 18769/25880 [3:50:01<1:18:05,  1.52it/s]
1|18770|Loss: 0.8591641187667847:  73%|███████▎  | 18770/25880 [3:50:02<1:18:31,  1.51it/s]
1|18771|Loss: 0.8265902996063232:  73%|███████▎  | 18770/25880 [3:50:02<1:18:31,  1.51it/s]
1|18771|Loss: 0.8265902996063232:  73%|███████▎  | 18771/25880 [3:50:02<1:20:02,  1.48it/s]
1|18772|Loss: 0.8711262941360474:  73%|███████▎  | 18771/25880 [3:50:03<1:20:02,  1.48it/s]
1|18772|Loss: 0.8711262941360474:  73%|███████▎  | 18772/25880 [3:50:03<1:17:23,  1.53it/s]
1|18773|Loss: 0.8584710955619812:  73%|███████▎  | 18772/25880 [3:50:03<1:17:23,  1.53it/s]
1|18773|Loss: 0.8584710955619812:  73%|███████▎  | 18773/25880 [3:50:04<1:16:06,  1.56it/s]
1|18774|Loss: 0.8071044683456421:  73%|███████▎  | 18773/25880 [3:50:04<1:16:06,  1.56it/s]
1|18774|Loss: 0.8071044683456421:  73%|███████▎  | 18774/25880 [3:50:04<1:11:40,  1.65it/s]
1|18775|Loss: 0.892405092716217:  73%|███████▎  | 18774/25880 [3:50:04<1:11:40,  1.65it/s] 
1|18775|Loss: 0.892405092716217:  73%|███████▎  | 18775/25880 [3:50:05<1:10:56,  1.67it/s]
1|18776|Loss: 0.8823578357696533:  73%|███████▎  | 18775/25880 [3:50:05<1:10:56,  1.67it/s]
1|18776|Loss: 0.8823578357696533:  73%|███████▎  | 18776/25880 [3:50:05<1:15:22,  1.57it/s]
1|18777|Loss: 0.8531478643417358:  73%|███████▎  | 18776/25880 [3:50:06<1:15:22,  1.57it/s]
1|18777|Loss: 0.8531478643417358:  73%|███████▎  | 18777/25880 [3:50:06<1:11:13,  1.66it/s]
1|18778|Loss: 0.8824567198753357:  73%|███████▎  | 18777/25880 [3:50:06<1:11:13,  1.66it/s]
1|18778|Loss: 0.8824567198753357:  73%|███████▎  | 18778/25880 [3:50:07<1:13:44,  1.61it/s]
1|18779|Loss: 0.8347678780555725:  73%|███████▎  | 18778/25880 [3:50:07<1:13:44,  1.61it/s]
1|18779|Loss: 0.8347678780555725:  73%|███████▎  | 18779/25880 [3:50:07<1:14:53,  1.58it/s]
1|18780|Loss: 0.87102210521698:  73%|███████▎  | 18779/25880 [3:50:08<1:14:53,  1.58it/s]  
1|18780|Loss: 0.87102210521698:  73%|███████▎  | 18780/25880 [3:50:08<1:19:25,  1.49it/s]
1|18781|Loss: 0.9186899662017822:  73%|███████▎  | 18780/25880 [3:50:08<1:19:25,  1.49it/s]
1|18781|Loss: 0.9186899662017822:  73%|███████▎  | 18781/25880 [3:50:09<1:24:16,  1.40it/s]
1|18782|Loss: 0.8345198631286621:  73%|███████▎  | 18781/25880 [3:50:09<1:24:16,  1.40it/s]
1|18782|Loss: 0.8345198631286621:  73%|███████▎  | 18782/25880 [3:50:10<1:28:19,  1.34it/s]
1|18783|Loss: 0.9964742064476013:  73%|███████▎  | 18782/25880 [3:50:10<1:28:19,  1.34it/s]
1|18783|Loss: 0.9964742064476013:  73%|███████▎  | 18783/25880 [3:50:10<1:24:16,  1.40it/s]
1|18784|Loss: 0.8281850218772888:  73%|███████▎  | 18783/25880 [3:50:11<1:24:16,  1.40it/s]
1|18784|Loss: 0.8281850218772888:  73%|███████▎  | 18784/25880 [3:50:11<1:23:42,  1.41it/s]
1|18785|Loss: 0.7896378040313721:  73%|███████▎  | 18784/25880 [3:50:11<1:23:42,  1.41it/s]
1|18785|Loss: 0.7896378040313721:  73%|███████▎  | 18785/25880 [3:50:12<1:28:31,  1.34it/s]
1|18786|Loss: 0.7209790349006653:  73%|███████▎  | 18785/25880 [3:50:12<1:28:31,  1.34it/s]
1|18786|Loss: 0.7209790349006653:  73%|███████▎  | 18786/25880 [3:50:12<1:23:59,  1.41it/s]
1|18787|Loss: 0.7392832040786743:  73%|███████▎  | 18786/25880 [3:50:13<1:23:59,  1.41it/s]
1|18787|Loss: 0.7392832040786743:  73%|███████▎  | 18787/25880 [3:50:13<1:26:36,  1.36it/s]
1|18788|Loss: 0.9117913842201233:  73%|███████▎  | 18787/25880 [3:50:14<1:26:36,  1.36it/s]
1|18788|Loss: 0.9117913842201233:  73%|███████▎  | 18788/25880 [3:50:14<1:27:59,  1.34it/s]
1|18789|Loss: 0.766196608543396:  73%|███████▎  | 18788/25880 [3:50:14<1:27:59,  1.34it/s] 
1|18789|Loss: 0.766196608543396:  73%|███████▎  | 18789/25880 [3:50:15<1:30:01,  1.31it/s]
1|18790|Loss: 0.8758650422096252:  73%|███████▎  | 18789/25880 [3:50:15<1:30:01,  1.31it/s]
1|18790|Loss: 0.8758650422096252:  73%|███████▎  | 18790/25880 [3:50:16<1:29:21,  1.32it/s]
1|18791|Loss: 0.900492787361145:  73%|███████▎  | 18790/25880 [3:50:16<1:29:21,  1.32it/s] 
1|18791|Loss: 0.900492787361145:  73%|███████▎  | 18791/25880 [3:50:16<1:25:45,  1.38it/s]
1|18792|Loss: 0.8219795823097229:  73%|███████▎  | 18791/25880 [3:50:17<1:25:45,  1.38it/s]
1|18792|Loss: 0.8219795823097229:  73%|███████▎  | 18792/25880 [3:50:17<1:27:31,  1.35it/s]
1|18793|Loss: 0.809920072555542:  73%|███████▎  | 18792/25880 [3:50:17<1:27:31,  1.35it/s] 
1|18793|Loss: 0.809920072555542:  73%|███████▎  | 18793/25880 [3:50:18<1:29:16,  1.32it/s]
1|18794|Loss: 0.8966048955917358:  73%|███████▎  | 18793/25880 [3:50:18<1:29:16,  1.32it/s]
1|18794|Loss: 0.8966048955917358:  73%|███████▎  | 18794/25880 [3:50:18<1:23:06,  1.42it/s]
1|18795|Loss: 0.7994232773780823:  73%|███████▎  | 18794/25880 [3:50:19<1:23:06,  1.42it/s]
1|18795|Loss: 0.7994232773780823:  73%|███████▎  | 18795/25880 [3:50:19<1:20:01,  1.48it/s]
1|18796|Loss: 0.9226011633872986:  73%|███████▎  | 18795/25880 [3:50:19<1:20:01,  1.48it/s]
1|18796|Loss: 0.9226011633872986:  73%|███████▎  | 18796/25880 [3:50:19<1:15:13,  1.57it/s]
1|18797|Loss: 0.8416889309883118:  73%|███████▎  | 18796/25880 [3:50:20<1:15:13,  1.57it/s]
1|18797|Loss: 0.8416889309883118:  73%|███████▎  | 18797/25880 [3:50:20<1:14:33,  1.58it/s]
1|18798|Loss: 0.7702415585517883:  73%|███████▎  | 18797/25880 [3:50:21<1:14:33,  1.58it/s]
1|18798|Loss: 0.7702415585517883:  73%|███████▎  | 18798/25880 [3:50:21<1:22:59,  1.42it/s]
1|18799|Loss: 0.8119223117828369:  73%|███████▎  | 18798/25880 [3:50:21<1:22:59,  1.42it/s]
1|18799|Loss: 0.8119223117828369:  73%|███████▎  | 18799/25880 [3:50:22<1:24:21,  1.40it/s]
1|18800|Loss: 0.8453242778778076:  73%|███████▎  | 18799/25880 [3:50:22<1:24:21,  1.40it/s]
1|18800|Loss: 0.8453242778778076:  73%|███████▎  | 18800/25880 [3:50:22<1:24:40,  1.39it/s]
1|18801|Loss: 0.7897971272468567:  73%|███████▎  | 18800/25880 [3:50:23<1:24:40,  1.39it/s]
1|18801|Loss: 0.7897971272468567:  73%|███████▎  | 18801/25880 [3:50:23<1:25:34,  1.38it/s]
1|18802|Loss: 0.8987586498260498:  73%|███████▎  | 18801/25880 [3:50:24<1:25:34,  1.38it/s]
1|18802|Loss: 0.8987586498260498:  73%|███████▎  | 18802/25880 [3:50:24<1:23:27,  1.41it/s]
1|18803|Loss: 0.9155494570732117:  73%|███████▎  | 18802/25880 [3:50:24<1:23:27,  1.41it/s]
1|18803|Loss: 0.9155494570732117:  73%|███████▎  | 18803/25880 [3:50:25<1:23:39,  1.41it/s]
1|18804|Loss: 0.8543447256088257:  73%|███████▎  | 18803/25880 [3:50:25<1:23:39,  1.41it/s]
1|18804|Loss: 0.8543447256088257:  73%|███████▎  | 18804/25880 [3:50:25<1:27:38,  1.35it/s]
1|18805|Loss: 0.8629623055458069:  73%|███████▎  | 18804/25880 [3:50:26<1:27:38,  1.35it/s]
1|18805|Loss: 0.8629623055458069:  73%|███████▎  | 18805/25880 [3:50:26<1:31:13,  1.29it/s]
1|18806|Loss: 0.786096453666687:  73%|███████▎  | 18805/25880 [3:50:27<1:31:13,  1.29it/s] 
1|18806|Loss: 0.786096453666687:  73%|███████▎  | 18806/25880 [3:50:27<1:30:59,  1.30it/s]
1|18807|Loss: 0.8576285243034363:  73%|███████▎  | 18806/25880 [3:50:27<1:30:59,  1.30it/s]
1|18807|Loss: 0.8576285243034363:  73%|███████▎  | 18807/25880 [3:50:28<1:29:53,  1.31it/s]
1|18808|Loss: 0.89111328125:  73%|███████▎  | 18807/25880 [3:50:28<1:29:53,  1.31it/s]     
1|18808|Loss: 0.89111328125:  73%|███████▎  | 18808/25880 [3:50:29<1:30:51,  1.30it/s]
1|18809|Loss: 0.7946666479110718:  73%|███████▎  | 18808/25880 [3:50:29<1:30:51,  1.30it/s]
1|18809|Loss: 0.7946666479110718:  73%|███████▎  | 18809/25880 [3:50:29<1:26:03,  1.37it/s]
1|18810|Loss: 0.8870852589607239:  73%|███████▎  | 18809/25880 [3:50:30<1:26:03,  1.37it/s]
1|18810|Loss: 0.8870852589607239:  73%|███████▎  | 18810/25880 [3:50:30<1:28:29,  1.33it/s]
1|18811|Loss: 0.8996931910514832:  73%|███████▎  | 18810/25880 [3:50:30<1:28:29,  1.33it/s]
1|18811|Loss: 0.8996931910514832:  73%|███████▎  | 18811/25880 [3:50:31<1:30:59,  1.29it/s]
1|18812|Loss: 0.8879378437995911:  73%|███████▎  | 18811/25880 [3:50:31<1:30:59,  1.29it/s]
1|18812|Loss: 0.8879378437995911:  73%|███████▎  | 18812/25880 [3:50:31<1:29:14,  1.32it/s]
1|18813|Loss: 0.9388788938522339:  73%|███████▎  | 18812/25880 [3:50:32<1:29:14,  1.32it/s]
1|18813|Loss: 0.9388788938522339:  73%|███████▎  | 18813/25880 [3:50:32<1:31:41,  1.28it/s]
1|18814|Loss: 0.738619327545166:  73%|███████▎  | 18813/25880 [3:50:33<1:31:41,  1.28it/s] 
1|18814|Loss: 0.738619327545166:  73%|███████▎  | 18814/25880 [3:50:33<1:30:20,  1.30it/s]
1|18815|Loss: 0.8031989932060242:  73%|███████▎  | 18814/25880 [3:50:33<1:30:20,  1.30it/s]
1|18815|Loss: 0.8031989932060242:  73%|███████▎  | 18815/25880 [3:50:34<1:30:45,  1.30it/s]
1|18816|Loss: 0.8805804252624512:  73%|███████▎  | 18815/25880 [3:50:34<1:30:45,  1.30it/s]
1|18816|Loss: 0.8805804252624512:  73%|███████▎  | 18816/25880 [3:50:34<1:23:39,  1.41it/s]
1|18817|Loss: 0.7908874750137329:  73%|███████▎  | 18816/25880 [3:50:35<1:23:39,  1.41it/s]
1|18817|Loss: 0.7908874750137329:  73%|███████▎  | 18817/25880 [3:50:35<1:26:06,  1.37it/s]
1|18818|Loss: 0.6532564759254456:  73%|███████▎  | 18817/25880 [3:50:36<1:26:06,  1.37it/s]
1|18818|Loss: 0.6532564759254456:  73%|███████▎  | 18818/25880 [3:50:36<1:27:02,  1.35it/s]
1|18819|Loss: 0.7578151226043701:  73%|███████▎  | 18818/25880 [3:50:36<1:27:02,  1.35it/s]
1|18819|Loss: 0.7578151226043701:  73%|███████▎  | 18819/25880 [3:50:37<1:22:20,  1.43it/s]
1|18820|Loss: 0.7969521284103394:  73%|███████▎  | 18819/25880 [3:50:37<1:22:20,  1.43it/s]
1|18820|Loss: 0.7969521284103394:  73%|███████▎  | 18820/25880 [3:50:37<1:16:17,  1.54it/s]
1|18821|Loss: 0.8951218128204346:  73%|███████▎  | 18820/25880 [3:50:37<1:16:17,  1.54it/s]
1|18821|Loss: 0.8951218128204346:  73%|███████▎  | 18821/25880 [3:50:38<1:13:26,  1.60it/s]
1|18822|Loss: 0.755315363407135:  73%|███████▎  | 18821/25880 [3:50:38<1:13:26,  1.60it/s] 
1|18822|Loss: 0.755315363407135:  73%|███████▎  | 18822/25880 [3:50:38<1:16:05,  1.55it/s]
1|18823|Loss: 0.8851973414421082:  73%|███████▎  | 18822/25880 [3:50:39<1:16:05,  1.55it/s]
1|18823|Loss: 0.8851973414421082:  73%|███████▎  | 18823/25880 [3:50:39<1:18:18,  1.50it/s]
1|18824|Loss: 0.800140917301178:  73%|███████▎  | 18823/25880 [3:50:39<1:18:18,  1.50it/s] 
1|18824|Loss: 0.800140917301178:  73%|███████▎  | 18824/25880 [3:50:40<1:21:58,  1.43it/s]
1|18825|Loss: 0.7578339576721191:  73%|███████▎  | 18824/25880 [3:50:40<1:21:58,  1.43it/s]
1|18825|Loss: 0.7578339576721191:  73%|███████▎  | 18825/25880 [3:50:41<1:23:36,  1.41it/s]
1|18826|Loss: 0.8324029445648193:  73%|███████▎  | 18825/25880 [3:50:41<1:23:36,  1.41it/s]
1|18826|Loss: 0.8324029445648193:  73%|███████▎  | 18826/25880 [3:50:41<1:25:51,  1.37it/s]
1|18827|Loss: 0.8942586183547974:  73%|███████▎  | 18826/25880 [3:50:42<1:25:51,  1.37it/s]
1|18827|Loss: 0.8942586183547974:  73%|███████▎  | 18827/25880 [3:50:42<1:26:31,  1.36it/s]
1|18828|Loss: 0.8289875388145447:  73%|███████▎  | 18827/25880 [3:50:42<1:26:31,  1.36it/s]
1|18828|Loss: 0.8289875388145447:  73%|███████▎  | 18828/25880 [3:50:43<1:20:45,  1.46it/s]
1|18829|Loss: 0.8777341246604919:  73%|███████▎  | 18828/25880 [3:50:43<1:20:45,  1.46it/s]
1|18829|Loss: 0.8777341246604919:  73%|███████▎  | 18829/25880 [3:50:43<1:20:48,  1.45it/s]
1|18830|Loss: 0.7455275654792786:  73%|███████▎  | 18829/25880 [3:50:44<1:20:48,  1.45it/s]
1|18830|Loss: 0.7455275654792786:  73%|███████▎  | 18830/25880 [3:50:44<1:24:59,  1.38it/s]
1|18831|Loss: 0.9346793293952942:  73%|███████▎  | 18830/25880 [3:50:45<1:24:59,  1.38it/s]
1|18831|Loss: 0.9346793293952942:  73%|███████▎  | 18831/25880 [3:50:45<1:25:29,  1.37it/s]
1|18832|Loss: 0.8893166780471802:  73%|███████▎  | 18831/25880 [3:50:45<1:25:29,  1.37it/s]
1|18832|Loss: 0.8893166780471802:  73%|███████▎  | 18832/25880 [3:50:46<1:28:21,  1.33it/s]
1|18833|Loss: 1.0971425771713257:  73%|███████▎  | 18832/25880 [3:50:46<1:28:21,  1.33it/s]
1|18833|Loss: 1.0971425771713257:  73%|███████▎  | 18833/25880 [3:50:46<1:25:07,  1.38it/s]
1|18834|Loss: 0.7805449366569519:  73%|███████▎  | 18833/25880 [3:50:47<1:25:07,  1.38it/s]
1|18834|Loss: 0.7805449366569519:  73%|███████▎  | 18834/25880 [3:50:47<1:24:28,  1.39it/s]
1|18835|Loss: 0.8127487897872925:  73%|███████▎  | 18834/25880 [3:50:48<1:24:28,  1.39it/s]
1|18835|Loss: 0.8127487897872925:  73%|███████▎  | 18835/25880 [3:50:48<1:27:07,  1.35it/s]
1|18836|Loss: 0.8063931465148926:  73%|███████▎  | 18835/25880 [3:50:48<1:27:07,  1.35it/s]
1|18836|Loss: 0.8063931465148926:  73%|███████▎  | 18836/25880 [3:50:49<1:23:01,  1.41it/s]
1|18837|Loss: 0.8679460287094116:  73%|███████▎  | 18836/25880 [3:50:49<1:23:01,  1.41it/s]
1|18837|Loss: 0.8679460287094116:  73%|███████▎  | 18837/25880 [3:50:49<1:24:21,  1.39it/s]
1|18838|Loss: 0.8206480145454407:  73%|███████▎  | 18837/25880 [3:50:50<1:24:21,  1.39it/s]
1|18838|Loss: 0.8206480145454407:  73%|███████▎  | 18838/25880 [3:50:50<1:27:03,  1.35it/s]
1|18839|Loss: 0.8482523560523987:  73%|███████▎  | 18838/25880 [3:50:51<1:27:03,  1.35it/s]
1|18839|Loss: 0.8482523560523987:  73%|███████▎  | 18839/25880 [3:50:51<1:30:29,  1.30it/s]
1|18840|Loss: 0.7945193648338318:  73%|███████▎  | 18839/25880 [3:50:51<1:30:29,  1.30it/s]
1|18840|Loss: 0.7945193648338318:  73%|███████▎  | 18840/25880 [3:50:52<1:29:22,  1.31it/s]
1|18841|Loss: 0.7512772083282471:  73%|███████▎  | 18840/25880 [3:50:52<1:29:22,  1.31it/s]
1|18841|Loss: 0.7512772083282471:  73%|███████▎  | 18841/25880 [3:50:52<1:24:40,  1.39it/s]
1|18842|Loss: 0.9672666192054749:  73%|███████▎  | 18841/25880 [3:50:53<1:24:40,  1.39it/s]
1|18842|Loss: 0.9672666192054749:  73%|███████▎  | 18842/25880 [3:50:53<1:26:00,  1.36it/s]
1|18843|Loss: 0.7350320219993591:  73%|███████▎  | 18842/25880 [3:50:53<1:26:00,  1.36it/s]
1|18843|Loss: 0.7350320219993591:  73%|███████▎  | 18843/25880 [3:50:54<1:29:08,  1.32it/s]
1|18844|Loss: 0.8218600153923035:  73%|███████▎  | 18843/25880 [3:50:54<1:29:08,  1.32it/s]
1|18844|Loss: 0.8218600153923035:  73%|███████▎  | 18844/25880 [3:50:55<1:26:04,  1.36it/s]
1|18845|Loss: 0.7599996328353882:  73%|███████▎  | 18844/25880 [3:50:55<1:26:04,  1.36it/s]
1|18845|Loss: 0.7599996328353882:  73%|███████▎  | 18845/25880 [3:50:55<1:28:03,  1.33it/s]
1|18846|Loss: 0.8834789395332336:  73%|███████▎  | 18845/25880 [3:50:56<1:28:03,  1.33it/s]
1|18846|Loss: 0.8834789395332336:  73%|███████▎  | 18846/25880 [3:50:56<1:27:46,  1.34it/s]
1|18847|Loss: 0.8572226166725159:  73%|███████▎  | 18846/25880 [3:50:56<1:27:46,  1.34it/s]
1|18847|Loss: 0.8572226166725159:  73%|███████▎  | 18847/25880 [3:50:57<1:31:19,  1.28it/s]
1|18848|Loss: 0.788476824760437:  73%|███████▎  | 18847/25880 [3:50:57<1:31:19,  1.28it/s] 
1|18848|Loss: 0.788476824760437:  73%|███████▎  | 18848/25880 [3:50:58<1:32:46,  1.26it/s]
1|18849|Loss: 0.763679027557373:  73%|███████▎  | 18848/25880 [3:50:58<1:32:46,  1.26it/s]
1|18849|Loss: 0.763679027557373:  73%|███████▎  | 18849/25880 [3:50:58<1:30:17,  1.30it/s]
1|18850|Loss: 0.7880017161369324:  73%|███████▎  | 18849/25880 [3:50:59<1:30:17,  1.30it/s]
1|18850|Loss: 0.7880017161369324:  73%|███████▎  | 18850/25880 [3:50:59<1:24:35,  1.38it/s]
1|18851|Loss: 0.823270857334137:  73%|███████▎  | 18850/25880 [3:50:59<1:24:35,  1.38it/s] 
1|18851|Loss: 0.823270857334137:  73%|███████▎  | 18851/25880 [3:51:00<1:22:56,  1.41it/s]
1|18852|Loss: 0.8015606999397278:  73%|███████▎  | 18851/25880 [3:51:00<1:22:56,  1.41it/s]
1|18852|Loss: 0.8015606999397278:  73%|███████▎  | 18852/25880 [3:51:00<1:20:48,  1.45it/s]
1|18853|Loss: 0.8433236479759216:  73%|███████▎  | 18852/25880 [3:51:01<1:20:48,  1.45it/s]
1|18853|Loss: 0.8433236479759216:  73%|███████▎  | 18853/25880 [3:51:01<1:18:15,  1.50it/s]
1|18854|Loss: 0.8758395910263062:  73%|███████▎  | 18853/25880 [3:51:01<1:18:15,  1.50it/s]
1|18854|Loss: 0.8758395910263062:  73%|███████▎  | 18854/25880 [3:51:02<1:20:20,  1.46it/s]
1|18855|Loss: 0.8515523076057434:  73%|███████▎  | 18854/25880 [3:51:02<1:20:20,  1.46it/s]
1|18855|Loss: 0.8515523076057434:  73%|███████▎  | 18855/25880 [3:51:03<1:25:48,  1.36it/s]
1|18856|Loss: 0.8168463110923767:  73%|███████▎  | 18855/25880 [3:51:03<1:25:48,  1.36it/s]
1|18856|Loss: 0.8168463110923767:  73%|███████▎  | 18856/25880 [3:51:03<1:26:02,  1.36it/s]
1|18857|Loss: 0.7569632530212402:  73%|███████▎  | 18856/25880 [3:51:04<1:26:02,  1.36it/s]
1|18857|Loss: 0.7569632530212402:  73%|███████▎  | 18857/25880 [3:51:04<1:22:26,  1.42it/s]
1|18858|Loss: 0.8050810694694519:  73%|███████▎  | 18857/25880 [3:51:04<1:22:26,  1.42it/s]
1|18858|Loss: 0.8050810694694519:  73%|███████▎  | 18858/25880 [3:51:05<1:25:28,  1.37it/s]
1|18859|Loss: 0.8499928116798401:  73%|███████▎  | 18858/25880 [3:51:05<1:25:28,  1.37it/s]
1|18859|Loss: 0.8499928116798401:  73%|███████▎  | 18859/25880 [3:51:05<1:25:11,  1.37it/s]
1|18860|Loss: 0.7973808646202087:  73%|███████▎  | 18859/25880 [3:51:06<1:25:11,  1.37it/s]
1|18860|Loss: 0.7973808646202087:  73%|███████▎  | 18860/25880 [3:51:06<1:20:37,  1.45it/s]
1|18861|Loss: 0.7639875411987305:  73%|███████▎  | 18860/25880 [3:51:06<1:20:37,  1.45it/s]
1|18861|Loss: 0.7639875411987305:  73%|███████▎  | 18861/25880 [3:51:07<1:20:56,  1.45it/s]
1|18862|Loss: 0.7117058634757996:  73%|███████▎  | 18861/25880 [3:51:07<1:20:56,  1.45it/s]
1|18862|Loss: 0.7117058634757996:  73%|███████▎  | 18862/25880 [3:51:07<1:22:42,  1.41it/s]
1|18863|Loss: 0.8253281712532043:  73%|███████▎  | 18862/25880 [3:51:08<1:22:42,  1.41it/s]
1|18863|Loss: 0.8253281712532043:  73%|███████▎  | 18863/25880 [3:51:08<1:23:11,  1.41it/s]
1|18864|Loss: 0.6948591470718384:  73%|███████▎  | 18863/25880 [3:51:09<1:23:11,  1.41it/s]
1|18864|Loss: 0.6948591470718384:  73%|███████▎  | 18864/25880 [3:51:09<1:26:42,  1.35it/s]
1|18865|Loss: 0.6785988211631775:  73%|███████▎  | 18864/25880 [3:51:09<1:26:42,  1.35it/s]
1|18865|Loss: 0.6785988211631775:  73%|███████▎  | 18865/25880 [3:51:10<1:27:24,  1.34it/s]
1|18866|Loss: 0.8331291675567627:  73%|███████▎  | 18865/25880 [3:51:10<1:27:24,  1.34it/s]
1|18866|Loss: 0.8331291675567627:  73%|███████▎  | 18866/25880 [3:51:11<1:27:10,  1.34it/s]
1|18867|Loss: 0.8676022291183472:  73%|███████▎  | 18866/25880 [3:51:11<1:27:10,  1.34it/s]
1|18867|Loss: 0.8676022291183472:  73%|███████▎  | 18867/25880 [3:51:11<1:20:20,  1.45it/s]
1|18868|Loss: 0.8698030114173889:  73%|███████▎  | 18867/25880 [3:51:11<1:20:20,  1.45it/s]
1|18868|Loss: 0.8698030114173889:  73%|███████▎  | 18868/25880 [3:51:12<1:19:20,  1.47it/s]
1|18869|Loss: 0.8116783499717712:  73%|███████▎  | 18868/25880 [3:51:12<1:19:20,  1.47it/s]
1|18869|Loss: 0.8116783499717712:  73%|███████▎  | 18869/25880 [3:51:12<1:20:13,  1.46it/s]
1|18870|Loss: 0.7912166714668274:  73%|███████▎  | 18869/25880 [3:51:13<1:20:13,  1.46it/s]
1|18870|Loss: 0.7912166714668274:  73%|███████▎  | 18870/25880 [3:51:13<1:23:30,  1.40it/s]
1|18871|Loss: 0.8451076149940491:  73%|███████▎  | 18870/25880 [3:51:14<1:23:30,  1.40it/s]
1|18871|Loss: 0.8451076149940491:  73%|███████▎  | 18871/25880 [3:51:14<1:23:41,  1.40it/s]
1|18872|Loss: 0.8172468543052673:  73%|███████▎  | 18871/25880 [3:51:14<1:23:41,  1.40it/s]
1|18872|Loss: 0.8172468543052673:  73%|███████▎  | 18872/25880 [3:51:15<1:27:10,  1.34it/s]
1|18873|Loss: 0.827756404876709:  73%|███████▎  | 18872/25880 [3:51:15<1:27:10,  1.34it/s] 
1|18873|Loss: 0.827756404876709:  73%|███████▎  | 18873/25880 [3:51:15<1:23:29,  1.40it/s]
1|18874|Loss: 0.9693654179573059:  73%|███████▎  | 18873/25880 [3:51:16<1:23:29,  1.40it/s]
1|18874|Loss: 0.9693654179573059:  73%|███████▎  | 18874/25880 [3:51:16<1:23:14,  1.40it/s]
1|18875|Loss: 0.6993730664253235:  73%|███████▎  | 18874/25880 [3:51:16<1:23:14,  1.40it/s]
1|18875|Loss: 0.6993730664253235:  73%|███████▎  | 18875/25880 [3:51:17<1:20:57,  1.44it/s]
1|18876|Loss: 0.9025604128837585:  73%|███████▎  | 18875/25880 [3:51:17<1:20:57,  1.44it/s]
1|18876|Loss: 0.9025604128837585:  73%|███████▎  | 18876/25880 [3:51:18<1:24:59,  1.37it/s]
1|18877|Loss: 1.0978631973266602:  73%|███████▎  | 18876/25880 [3:51:18<1:24:59,  1.37it/s]
1|18877|Loss: 1.0978631973266602:  73%|███████▎  | 18877/25880 [3:51:18<1:25:18,  1.37it/s]
1|18878|Loss: 0.8614146113395691:  73%|███████▎  | 18877/25880 [3:51:19<1:25:18,  1.37it/s]
1|18878|Loss: 0.8614146113395691:  73%|███████▎  | 18878/25880 [3:51:19<1:27:51,  1.33it/s]
1|18879|Loss: 0.8864656090736389:  73%|███████▎  | 18878/25880 [3:51:19<1:27:51,  1.33it/s]
1|18879|Loss: 0.8864656090736389:  73%|███████▎  | 18879/25880 [3:51:20<1:23:30,  1.40it/s]
1|18880|Loss: 0.8201981782913208:  73%|███████▎  | 18879/25880 [3:51:20<1:23:30,  1.40it/s]
1|18880|Loss: 0.8201981782913208:  73%|███████▎  | 18880/25880 [3:51:20<1:16:04,  1.53it/s]
1|18881|Loss: 0.812961995601654:  73%|███████▎  | 18880/25880 [3:51:21<1:16:04,  1.53it/s] 
1|18881|Loss: 0.812961995601654:  73%|███████▎  | 18881/25880 [3:51:21<1:19:54,  1.46it/s]
1|18882|Loss: 0.836467981338501:  73%|███████▎  | 18881/25880 [3:51:21<1:19:54,  1.46it/s]
1|18882|Loss: 0.836467981338501:  73%|███████▎  | 18882/25880 [3:51:22<1:19:02,  1.48it/s]
1|18883|Loss: 0.8893104195594788:  73%|███████▎  | 18882/25880 [3:51:22<1:19:02,  1.48it/s]
1|18883|Loss: 0.8893104195594788:  73%|███████▎  | 18883/25880 [3:51:22<1:20:40,  1.45it/s]
1|18884|Loss: 0.8076837062835693:  73%|███████▎  | 18883/25880 [3:51:23<1:20:40,  1.45it/s]
1|18884|Loss: 0.8076837062835693:  73%|███████▎  | 18884/25880 [3:51:23<1:23:59,  1.39it/s]
1|18885|Loss: 0.939967155456543:  73%|███████▎  | 18884/25880 [3:51:24<1:23:59,  1.39it/s] 
1|18885|Loss: 0.939967155456543:  73%|███████▎  | 18885/25880 [3:51:24<1:22:29,  1.41it/s]
1|18886|Loss: 0.6608213186264038:  73%|███████▎  | 18885/25880 [3:51:24<1:22:29,  1.41it/s]
1|18886|Loss: 0.6608213186264038:  73%|███████▎  | 18886/25880 [3:51:25<1:22:01,  1.42it/s]
1|18887|Loss: 0.7970153093338013:  73%|███████▎  | 18886/25880 [3:51:25<1:22:01,  1.42it/s]
1|18887|Loss: 0.7970153093338013:  73%|███████▎  | 18887/25880 [3:51:25<1:22:29,  1.41it/s]
1|18888|Loss: 0.7462022304534912:  73%|███████▎  | 18887/25880 [3:51:26<1:22:29,  1.41it/s]
1|18888|Loss: 0.7462022304534912:  73%|███████▎  | 18888/25880 [3:51:26<1:25:00,  1.37it/s]
1|18889|Loss: 0.6343289613723755:  73%|███████▎  | 18888/25880 [3:51:26<1:25:00,  1.37it/s]
1|18889|Loss: 0.6343289613723755:  73%|███████▎  | 18889/25880 [3:51:27<1:19:12,  1.47it/s]
1|18890|Loss: 0.8927046656608582:  73%|███████▎  | 18889/25880 [3:51:27<1:19:12,  1.47it/s]
1|18890|Loss: 0.8927046656608582:  73%|███████▎  | 18890/25880 [3:51:27<1:19:34,  1.46it/s]
1|18891|Loss: 0.7543675303459167:  73%|███████▎  | 18890/25880 [3:51:28<1:19:34,  1.46it/s]
1|18891|Loss: 0.7543675303459167:  73%|███████▎  | 18891/25880 [3:51:28<1:18:17,  1.49it/s]
1|18892|Loss: 0.8015774488449097:  73%|███████▎  | 18891/25880 [3:51:28<1:18:17,  1.49it/s]
1|18892|Loss: 0.8015774488449097:  73%|███████▎  | 18892/25880 [3:51:29<1:24:43,  1.37it/s]
1|18893|Loss: 0.8905194401741028:  73%|███████▎  | 18892/25880 [3:51:29<1:24:43,  1.37it/s]
1|18893|Loss: 0.8905194401741028:  73%|███████▎  | 18893/25880 [3:51:29<1:23:28,  1.40it/s]
1|18894|Loss: 0.7876766920089722:  73%|███████▎  | 18893/25880 [3:51:30<1:23:28,  1.40it/s]
1|18894|Loss: 0.7876766920089722:  73%|███████▎  | 18894/25880 [3:51:30<1:24:53,  1.37it/s]
1|18895|Loss: 0.8334643244743347:  73%|███████▎  | 18894/25880 [3:51:31<1:24:53,  1.37it/s]
1|18895|Loss: 0.8334643244743347:  73%|███████▎  | 18895/25880 [3:51:31<1:24:27,  1.38it/s]
1|18896|Loss: 0.8103334903717041:  73%|███████▎  | 18895/25880 [3:51:31<1:24:27,  1.38it/s]
1|18896|Loss: 0.8103334903717041:  73%|███████▎  | 18896/25880 [3:51:32<1:24:22,  1.38it/s]
1|18897|Loss: 0.9456132650375366:  73%|███████▎  | 18896/25880 [3:51:32<1:24:22,  1.38it/s]
1|18897|Loss: 0.9456132650375366:  73%|███████▎  | 18897/25880 [3:51:32<1:17:47,  1.50it/s]
1|18898|Loss: 0.801364004611969:  73%|███████▎  | 18897/25880 [3:51:33<1:17:47,  1.50it/s] 
1|18898|Loss: 0.801364004611969:  73%|███████▎  | 18898/25880 [3:51:33<1:18:04,  1.49it/s]
1|18899|Loss: 0.8673453330993652:  73%|███████▎  | 18898/25880 [3:51:33<1:18:04,  1.49it/s]
1|18899|Loss: 0.8673453330993652:  73%|███████▎  | 18899/25880 [3:51:34<1:16:59,  1.51it/s]
1|18900|Loss: 0.9262083768844604:  73%|███████▎  | 18899/25880 [3:51:34<1:16:59,  1.51it/s]
1|18900|Loss: 0.9262083768844604:  73%|███████▎  | 18900/25880 [3:51:34<1:18:42,  1.48it/s]
1|18901|Loss: 0.7477636337280273:  73%|███████▎  | 18900/25880 [3:51:35<1:18:42,  1.48it/s]
1|18901|Loss: 0.7477636337280273:  73%|███████▎  | 18901/25880 [3:51:35<1:31:43,  1.27it/s]
1|18902|Loss: 0.7894913554191589:  73%|███████▎  | 18901/25880 [3:51:36<1:31:43,  1.27it/s]
1|18902|Loss: 0.7894913554191589:  73%|███████▎  | 18902/25880 [3:51:36<1:35:32,  1.22it/s]
1|18903|Loss: 0.8808169960975647:  73%|███████▎  | 18902/25880 [3:51:37<1:35:32,  1.22it/s]
1|18903|Loss: 0.8808169960975647:  73%|███████▎  | 18903/25880 [3:51:37<1:36:00,  1.21it/s]
1|18904|Loss: 0.9852750897407532:  73%|███████▎  | 18903/25880 [3:51:37<1:36:00,  1.21it/s]
1|18904|Loss: 0.9852750897407532:  73%|███████▎  | 18904/25880 [3:51:38<1:32:37,  1.26it/s]
1|18905|Loss: 0.8745941519737244:  73%|███████▎  | 18904/25880 [3:51:38<1:32:37,  1.26it/s]
1|18905|Loss: 0.8745941519737244:  73%|███████▎  | 18905/25880 [3:51:39<1:33:51,  1.24it/s]
1|18906|Loss: 1.018279790878296:  73%|███████▎  | 18905/25880 [3:51:39<1:33:51,  1.24it/s] 
1|18906|Loss: 1.018279790878296:  73%|███████▎  | 18906/25880 [3:51:39<1:32:08,  1.26it/s]
1|18907|Loss: 0.8884439468383789:  73%|███████▎  | 18906/25880 [3:51:40<1:32:08,  1.26it/s]
1|18907|Loss: 0.8884439468383789:  73%|███████▎  | 18907/25880 [3:51:40<1:22:08,  1.41it/s]
1|18908|Loss: 0.819046139717102:  73%|███████▎  | 18907/25880 [3:51:40<1:22:08,  1.41it/s] 
1|18908|Loss: 0.819046139717102:  73%|███████▎  | 18908/25880 [3:51:41<1:21:24,  1.43it/s]
1|18909|Loss: 0.8384601473808289:  73%|███████▎  | 18908/25880 [3:51:41<1:21:24,  1.43it/s]
1|18909|Loss: 0.8384601473808289:  73%|███████▎  | 18909/25880 [3:51:41<1:23:00,  1.40it/s]
1|18910|Loss: 0.829142153263092:  73%|███████▎  | 18909/25880 [3:51:42<1:23:00,  1.40it/s] 
1|18910|Loss: 0.829142153263092:  73%|█████��█▎  | 18910/25880 [3:51:42<1:23:50,  1.39it/s]
1|18911|Loss: 0.8228628039360046:  73%|███████▎  | 18910/25880 [3:51:42<1:23:50,  1.39it/s]
1|18911|Loss: 0.8228628039360046:  73%|███████▎  | 18911/25880 [3:51:43<1:27:13,  1.33it/s]
1|18912|Loss: 0.8986514806747437:  73%|███████▎  | 18911/25880 [3:51:43<1:27:13,  1.33it/s]
1|18912|Loss: 0.8986514806747437:  73%|███████▎  | 18912/25880 [3:51:43<1:22:40,  1.40it/s]
1|18913|Loss: 0.8053090572357178:  73%|███████▎  | 18912/25880 [3:51:44<1:22:40,  1.40it/s]
1|18913|Loss: 0.8053090572357178:  73%|███████▎  | 18913/25880 [3:51:44<1:22:29,  1.41it/s]
1|18914|Loss: 0.7616775631904602:  73%|███████▎  | 18913/25880 [3:51:45<1:22:29,  1.41it/s]
1|18914|Loss: 0.7616775631904602:  73%|███████▎  | 18914/25880 [3:51:45<1:28:42,  1.31it/s]
1|18915|Loss: 0.7726061940193176:  73%|███████▎  | 18914/25880 [3:51:46<1:28:42,  1.31it/s]
1|18915|Loss: 0.7726061940193176:  73%|███████▎  | 18915/25880 [3:51:46<1:29:00,  1.30it/s]
1|18916|Loss: 0.7787742614746094:  73%|███████▎  | 18915/25880 [3:51:46<1:29:00,  1.30it/s]
1|18916|Loss: 0.7787742614746094:  73%|███████▎  | 18916/25880 [3:51:46<1:23:30,  1.39it/s]
1|18917|Loss: 0.828032374382019:  73%|███████▎  | 18916/25880 [3:51:47<1:23:30,  1.39it/s] 
1|18917|Loss: 0.828032374382019:  73%|███████▎  | 18917/25880 [3:51:47<1:24:44,  1.37it/s]
1|18918|Loss: 0.7069059610366821:  73%|███████▎  | 18917/25880 [3:51:48<1:24:44,  1.37it/s]
1|18918|Loss: 0.7069059610366821:  73%|███████▎  | 18918/25880 [3:51:48<1:25:15,  1.36it/s]
1|18919|Loss: 0.7775163054466248:  73%|███████▎  | 18918/25880 [3:51:48<1:25:15,  1.36it/s]
1|18919|Loss: 0.7775163054466248:  73%|███████▎  | 18919/25880 [3:51:49<1:22:45,  1.40it/s]
1|18920|Loss: 0.7116048336029053:  73%|███████▎  | 18919/25880 [3:51:49<1:22:45,  1.40it/s]
1|18920|Loss: 0.7116048336029053:  73%|███████▎  | 18920/25880 [3:51:49<1:26:21,  1.34it/s]
1|18921|Loss: 0.8149747848510742:  73%|███████▎  | 18920/25880 [3:51:50<1:26:21,  1.34it/s]
1|18921|Loss: 0.8149747848510742:  73%|███████▎  | 18921/25880 [3:51:50<1:21:30,  1.42it/s]
1|18922|Loss: 0.8244729042053223:  73%|███████▎  | 18921/25880 [3:51:50<1:21:30,  1.42it/s]
1|18922|Loss: 0.8244729042053223:  73%|███████▎  | 18922/25880 [3:51:51<1:20:49,  1.43it/s]
1|18923|Loss: 0.8233246803283691:  73%|███████▎  | 18922/25880 [3:51:51<1:20:49,  1.43it/s]
1|18923|Loss: 0.8233246803283691:  73%|███████▎  | 18923/25880 [3:51:51<1:16:52,  1.51it/s]
1|18924|Loss: 0.9740332961082458:  73%|███████▎  | 18923/25880 [3:51:52<1:16:52,  1.51it/s]
1|18924|Loss: 0.9740332961082458:  73%|███████▎  | 18924/25880 [3:51:52<1:20:41,  1.44it/s]
1|18925|Loss: 0.8598763942718506:  73%|███████▎  | 18924/25880 [3:51:52<1:20:41,  1.44it/s]
1|18925|Loss: 0.8598763942718506:  73%|███████▎  | 18925/25880 [3:51:53<1:20:08,  1.45it/s]
1|18926|Loss: 0.796188235282898:  73%|███████▎  | 18925/25880 [3:51:53<1:20:08,  1.45it/s] 
1|18926|Loss: 0.796188235282898:  73%|███████▎  | 18926/25880 [3:51:54<1:24:19,  1.37it/s]
1|18927|Loss: 0.9233353734016418:  73%|███████▎  | 18926/25880 [3:51:54<1:24:19,  1.37it/s]
1|18927|Loss: 0.9233353734016418:  73%|███████▎  | 18927/25880 [3:51:54<1:25:20,  1.36it/s]
1|18928|Loss: 0.8351564407348633:  73%|███████▎  | 18927/25880 [3:51:55<1:25:20,  1.36it/s]
1|18928|Loss: 0.8351564407348633:  73%|███████▎  | 18928/25880 [3:51:55<1:25:13,  1.36it/s]
1|18929|Loss: 0.6718869805335999:  73%|███████▎  | 18928/25880 [3:51:55<1:25:13,  1.36it/s]
1|18929|Loss: 0.6718869805335999:  73%|███████▎  | 18929/25880 [3:51:56<1:27:43,  1.32it/s]
1|18930|Loss: 0.832734227180481:  73%|███████▎  | 18929/25880 [3:51:56<1:27:43,  1.32it/s] 
1|18930|Loss: 0.832734227180481:  73%|███████▎  | 18930/25880 [3:51:57<1:32:37,  1.25it/s]
1|18931|Loss: 0.9745664596557617:  73%|███████▎  | 18930/25880 [3:51:57<1:32:37,  1.25it/s]
1|18931|Loss: 0.9745664596557617:  73%|███████▎  | 18931/25880 [3:51:58<1:33:28,  1.24it/s]
1|18932|Loss: 0.816108226776123:  73%|███████▎  | 18931/25880 [3:51:58<1:33:28,  1.24it/s] 
1|18932|Loss: 0.816108226776123:  73%|███████▎  | 18932/25880 [3:51:58<1:31:46,  1.26it/s]
1|18933|Loss: 0.8494383692741394:  73%|███████▎  | 18932/25880 [3:51:59<1:31:46,  1.26it/s]
1|18933|Loss: 0.8494383692741394:  73%|███████▎  | 18933/25880 [3:51:59<1:26:44,  1.33it/s]
1|18934|Loss: 0.8621152639389038:  73%|███████▎  | 18933/25880 [3:51:59<1:26:44,  1.33it/s]
1|18934|Loss: 0.8621152639389038:  73%|███████▎  | 18934/25880 [3:52:00<1:25:24,  1.36it/s]
1|18935|Loss: 0.9010477662086487:  73%|███████▎  | 18934/25880 [3:52:00<1:25:24,  1.36it/s]
1|18935|Loss: 0.9010477662086487:  73%|███████▎  | 18935/25880 [3:52:00<1:18:59,  1.47it/s]
1|18936|Loss: 0.9638257622718811:  73%|███████▎  | 18935/25880 [3:52:01<1:18:59,  1.47it/s]
1|18936|Loss: 0.9638257622718811:  73%|███████▎  | 18936/25880 [3:52:01<1:15:58,  1.52it/s]
1|18937|Loss: 0.8218054175376892:  73%|███████▎  | 18936/25880 [3:52:01<1:15:58,  1.52it/s]
1|18937|Loss: 0.8218054175376892:  73%|███████▎  | 18937/25880 [3:52:02<1:18:12,  1.48it/s]
1|18938|Loss: 0.8175891041755676:  73%|███████▎  | 18937/25880 [3:52:02<1:18:12,  1.48it/s]
1|18938|Loss: 0.8175891041755676:  73%|███████▎  | 18938/25880 [3:52:02<1:20:42,  1.43it/s]
1|18939|Loss: 0.9215795993804932:  73%|███████▎  | 18938/25880 [3:52:03<1:20:42,  1.43it/s]
1|18939|Loss: 0.9215795993804932:  73%|███████▎  | 18939/25880 [3:52:03<1:22:19,  1.41it/s]
1|18940|Loss: 0.8994506001472473:  73%|███████▎  | 18939/25880 [3:52:03<1:22:19,  1.41it/s]
1|18940|Loss: 0.8994506001472473:  73%|███████▎  | 18940/25880 [3:52:04<1:23:27,  1.39it/s]
1|18941|Loss: 0.7837363481521606:  73%|███████▎  | 18940/25880 [3:52:04<1:23:27,  1.39it/s]
1|18941|Loss: 0.7837363481521606:  73%|███████▎  | 18941/25880 [3:52:04<1:21:28,  1.42it/s]
1|18942|Loss: 0.6731274127960205:  73%|███████▎  | 18941/25880 [3:52:05<1:21:28,  1.42it/s]
1|18942|Loss: 0.6731274127960205:  73%|███████▎  | 18942/25880 [3:52:05<1:24:29,  1.37it/s]
1|18943|Loss: 0.8470678925514221:  73%|███████▎  | 18942/25880 [3:52:06<1:24:29,  1.37it/s]
1|18943|Loss: 0.8470678925514221:  73%|███████▎  | 18943/25880 [3:52:06<1:24:33,  1.37it/s]
1|18944|Loss: 0.8859764337539673:  73%|███████▎  | 18943/25880 [3:52:06<1:24:33,  1.37it/s]
1|18944|Loss: 0.8859764337539673:  73%|███████▎  | 18944/25880 [3:52:07<1:25:05,  1.36it/s]
1|18945|Loss: 0.8089799284934998:  73%|███████▎  | 18944/25880 [3:52:07<1:25:05,  1.36it/s]
1|18945|Loss: 0.8089799284934998:  73%|███████▎  | 18945/25880 [3:52:07<1:15:28,  1.53it/s]
1|18946|Loss: 0.7674619555473328:  73%|███████▎  | 18945/25880 [3:52:08<1:15:28,  1.53it/s]
1|18946|Loss: 0.7674619555473328:  73%|███████▎  | 18946/25880 [3:52:08<1:19:42,  1.45it/s]
1|18947|Loss: 0.6754763722419739:  73%|███████▎  | 18946/25880 [3:52:08<1:19:42,  1.45it/s]
1|18947|Loss: 0.6754763722419739:  73%|███████▎  | 18947/25880 [3:52:09<1:16:16,  1.51it/s]
1|18948|Loss: 0.902126669883728:  73%|███████▎  | 18947/25880 [3:52:09<1:16:16,  1.51it/s] 
1|18948|Loss: 0.902126669883728:  73%|███████▎  | 18948/25880 [3:52:09<1:17:09,  1.50it/s]
1|18949|Loss: 0.8115469217300415:  73%|███████▎  | 18948/25880 [3:52:10<1:17:09,  1.50it/s]
1|18949|Loss: 0.8115469217300415:  73%|███████▎  | 18949/25880 [3:52:10<1:19:20,  1.46it/s]
1|18950|Loss: 0.8319467902183533:  73%|███████▎  | 18949/25880 [3:52:10<1:19:20,  1.46it/s]
1|18950|Loss: 0.8319467902183533:  73%|███████▎  | 18950/25880 [3:52:11<1:15:28,  1.53it/s]
1|18951|Loss: 0.771300196647644:  73%|███████▎  | 18950/25880 [3:52:11<1:15:28,  1.53it/s] 
1|18951|Loss: 0.771300196647644:  73%|███████▎  | 18951/25880 [3:52:11<1:16:34,  1.51it/s]
1|18952|Loss: 0.7946149110794067:  73%|███████▎  | 18951/25880 [3:52:12<1:16:34,  1.51it/s]
1|18952|Loss: 0.7946149110794067:  73%|███████▎  | 18952/25880 [3:52:12<1:16:24,  1.51it/s]
1|18953|Loss: 0.9468410611152649:  73%|███████▎  | 18952/25880 [3:52:12<1:16:24,  1.51it/s]
1|18953|Loss: 0.9468410611152649:  73%|███████▎  | 18953/25880 [3:52:13<1:18:26,  1.47it/s]
1|18954|Loss: 0.8484806418418884:  73%|███████▎  | 18953/25880 [3:52:13<1:18:26,  1.47it/s]
1|18954|Loss: 0.8484806418418884:  73%|███████▎  | 18954/25880 [3:52:13<1:19:37,  1.45it/s]
1|18955|Loss: 0.9183378219604492:  73%|███████▎  | 18954/25880 [3:52:14<1:19:37,  1.45it/s]
1|18955|Loss: 0.9183378219604492:  73%|███████▎  | 18955/25880 [3:52:14<1:25:49,  1.34it/s]
1|18956|Loss: 0.7440662980079651:  73%|███████▎  | 18955/25880 [3:52:15<1:25:49,  1.34it/s]
1|18956|Loss: 0.7440662980079651:  73%|███████▎  | 18956/25880 [3:52:15<1:24:11,  1.37it/s]
1|18957|Loss: 0.8272786736488342:  73%|███████▎  | 18956/25880 [3:52:15<1:24:11,  1.37it/s]
1|18957|Loss: 0.8272786736488342:  73%|███████▎  | 18957/25880 [3:52:16<1:19:46,  1.45it/s]
1|18958|Loss: 0.8493858575820923:  73%|███████▎  | 18957/25880 [3:52:16<1:19:46,  1.45it/s]
1|18958|Loss: 0.8493858575820923:  73%|███████▎  | 18958/25880 [3:52:16<1:24:00,  1.37it/s]
1|18959|Loss: 0.7647883892059326:  73%|███████▎  | 18958/25880 [3:52:17<1:24:00,  1.37it/s]
1|18959|Loss: 0.7647883892059326:  73%|███████▎  | 18959/25880 [3:52:17<1:25:02,  1.36it/s]
1|18960|Loss: 0.9008192420005798:  73%|███████▎  | 18959/25880 [3:52:17<1:25:02,  1.36it/s]
1|18960|Loss: 0.9008192420005798:  73%|███████▎  | 18960/25880 [3:52:18<1:24:03,  1.37it/s]
1|18961|Loss: 0.9183561205863953:  73%|███████▎  | 18960/25880 [3:52:18<1:24:03,  1.37it/s]
1|18961|Loss: 0.9183561205863953:  73%|███████▎  | 18961/25880 [3:52:18<1:21:32,  1.41it/s]
1|18962|Loss: 0.8258461356163025:  73%|███████▎  | 18961/25880 [3:52:19<1:21:32,  1.41it/s]
1|18962|Loss: 0.8258461356163025:  73%|███████▎  | 18962/25880 [3:52:19<1:18:46,  1.46it/s]
1|18963|Loss: 0.846699059009552:  73%|███████▎  | 18962/25880 [3:52:19<1:18:46,  1.46it/s] 
1|18963|Loss: 0.846699059009552:  73%|███████▎  | 18963/25880 [3:52:20<1:18:56,  1.46it/s]
1|18964|Loss: 0.8896719813346863:  73%|███████▎  | 18963/25880 [3:52:20<1:18:56,  1.46it/s]
1|18964|Loss: 0.8896719813346863:  73%|███████▎  | 18964/25880 [3:52:20<1:17:11,  1.49it/s]
1|18965|Loss: 0.8040691018104553:  73%|███████▎  | 18964/25880 [3:52:21<1:17:11,  1.49it/s]
1|18965|Loss: 0.8040691018104553:  73%|███████▎  | 18965/25880 [3:52:21<1:18:54,  1.46it/s]
1|18966|Loss: 0.7562394142150879:  73%|███████▎  | 18965/25880 [3:52:21<1:18:54,  1.46it/s]
1|18966|Loss: 0.7562394142150879:  73%|███████▎  | 18966/25880 [3:52:22<1:13:53,  1.56it/s]
1|18967|Loss: 0.8770577311515808:  73%|███████▎  | 18966/25880 [3:52:22<1:13:53,  1.56it/s]
1|18967|Loss: 0.8770577311515808:  73%|███████▎  | 18967/25880 [3:52:22<1:15:07,  1.53it/s]
1|18968|Loss: 0.8558878302574158:  73%|███████▎  | 18967/25880 [3:52:23<1:15:07,  1.53it/s]
1|18968|Loss: 0.8558878302574158:  73%|███████▎  | 18968/25880 [3:52:23<1:18:18,  1.47it/s]
1|18969|Loss: 0.7881577014923096:  73%|███████▎  | 18968/25880 [3:52:23<1:18:18,  1.47it/s]
1|18969|Loss: 0.7881577014923096:  73%|███████▎  | 18969/25880 [3:52:24<1:20:27,  1.43it/s]
1|18970|Loss: 0.9339985847473145:  73%|███████▎  | 18969/25880 [3:52:24<1:20:27,  1.43it/s]
1|18970|Loss: 0.9339985847473145:  73%|███████▎  | 18970/25880 [3:52:25<1:25:14,  1.35it/s]
1|18971|Loss: 1.0123064517974854:  73%|███████▎  | 18970/25880 [3:52:25<1:25:14,  1.35it/s]
1|18971|Loss: 1.0123064517974854:  73%|███████▎  | 18971/25880 [3:52:25<1:19:49,  1.44it/s]
1|18972|Loss: 0.7651240825653076:  73%|███████▎  | 18971/25880 [3:52:26<1:19:49,  1.44it/s]
1|18972|Loss: 0.7651240825653076:  73%|███████▎  | 18972/25880 [3:52:26<1:19:39,  1.45it/s]
1|18973|Loss: 0.8798037767410278:  73%|███████▎  | 18972/25880 [3:52:26<1:19:39,  1.45it/s]
1|18973|Loss: 0.8798037767410278:  73%|███████▎  | 18973/25880 [3:52:27<1:23:12,  1.38it/s]
1|18974|Loss: 0.7524616122245789:  73%|███████▎  | 18973/25880 [3:52:27<1:23:12,  1.38it/s]
1|18974|Loss: 0.7524616122245789:  73%|███████▎  | 18974/25880 [3:52:28<1:26:32,  1.33it/s]
1|18975|Loss: 0.7946611046791077:  73%|███████▎  | 18974/25880 [3:52:28<1:26:32,  1.33it/s]
1|18975|Loss: 0.7946611046791077:  73%|███████▎  | 18975/25880 [3:52:28<1:22:16,  1.40it/s]
1|18976|Loss: 0.8986705541610718:  73%|███████▎  | 18975/25880 [3:52:29<1:22:16,  1.40it/s]
1|18976|Loss: 0.8986705541610718:  73%|███████▎  | 18976/25880 [3:52:29<1:25:05,  1.35it/s]
1|18977|Loss: 0.858458399772644:  73%|███████▎  | 18976/25880 [3:52:29<1:25:05,  1.35it/s] 
1|18977|Loss: 0.858458399772644:  73%|███████▎  | 18977/25880 [3:52:30<1:19:46,  1.44it/s]
1|18978|Loss: 0.8991913795471191:  73%|███████▎  | 18977/25880 [3:52:30<1:19:46,  1.44it/s]
1|18978|Loss: 0.8991913795471191:  73%|███████▎  | 18978/25880 [3:52:30<1:23:13,  1.38it/s]
1|18979|Loss: 0.767731249332428:  73%|███████▎  | 18978/25880 [3:52:31<1:23:13,  1.38it/s] 
1|18979|Loss: 0.767731249332428:  73%|███████▎  | 18979/25880 [3:52:31<1:20:26,  1.43it/s]
1|18980|Loss: 0.8882312774658203:  73%|███████▎  | 18979/25880 [3:52:31<1:20:26,  1.43it/s]
1|18980|Loss: 0.8882312774658203:  73%|███████▎  | 18980/25880 [3:52:32<1:19:31,  1.45it/s]
1|18981|Loss: 0.9204275608062744:  73%|███████▎  | 18980/25880 [3:52:32<1:19:31,  1.45it/s]
1|18981|Loss: 0.9204275608062744:  73%|███████▎  | 18981/25880 [3:52:32<1:18:02,  1.47it/s]
1|18982|Loss: 0.8181342482566833:  73%|███████▎  | 18981/25880 [3:52:33<1:18:02,  1.47it/s]
1|18982|Loss: 0.8181342482566833:  73%|███████▎  | 18982/25880 [3:52:33<1:19:18,  1.45it/s]
1|18983|Loss: 0.982631504535675:  73%|███████▎  | 18982/25880 [3:52:33<1:19:18,  1.45it/s] 
1|18983|Loss: 0.982631504535675:  73%|███████▎  | 18983/25880 [3:52:34<1:20:46,  1.42it/s]
1|18984|Loss: 0.7420444488525391:  73%|███████▎  | 18983/25880 [3:52:34<1:20:46,  1.42it/s]
1|18984|Loss: 0.7420444488525391:  73%|███████▎  | 18984/25880 [3:52:35<1:25:09,  1.35it/s]
1|18985|Loss: 0.8542990684509277:  73%|███████▎  | 18984/25880 [3:52:35<1:25:09,  1.35it/s]
1|18985|Loss: 0.8542990684509277:  73%|███████▎  | 18985/25880 [3:52:35<1:27:20,  1.32it/s]
1|18986|Loss: 0.8303216099739075:  73%|███████▎  | 18985/25880 [3:52:36<1:27:20,  1.32it/s]
1|18986|Loss: 0.8303216099739075:  73%|███████▎  | 18986/25880 [3:52:36<1:21:50,  1.40it/s]
1|18987|Loss: 0.7719143033027649:  73%|███████▎  | 18986/25880 [3:52:36<1:21:50,  1.40it/s]
1|18987|Loss: 0.7719143033027649:  73%|███████▎  | 18987/25880 [3:52:37<1:23:48,  1.37it/s]
1|18988|Loss: 0.814946711063385:  73%|███████▎  | 18987/25880 [3:52:37<1:23:48,  1.37it/s] 
1|18988|Loss: 0.814946711063385:  73%|███████▎  | 18988/25880 [3:52:38<1:24:22,  1.36it/s]
1|18989|Loss: 0.8935911059379578:  73%|███████▎  | 18988/25880 [3:52:38<1:24:22,  1.36it/s]
1|18989|Loss: 0.8935911059379578:  73%|███████▎  | 18989/25880 [3:52:38<1:16:37,  1.50it/s]
1|18990|Loss: 0.8087037205696106:  73%|███████▎  | 18989/25880 [3:52:38<1:16:37,  1.50it/s]
1|18990|Loss: 0.8087037205696106:  73%|███████▎  | 18990/25880 [3:52:39<1:14:15,  1.55it/s]
1|18991|Loss: 0.8869308233261108:  73%|███████▎  | 18990/25880 [3:52:39<1:14:15,  1.55it/s]
1|18991|Loss: 0.8869308233261108:  73%|███████▎  | 18991/25880 [3:52:39<1:20:02,  1.43it/s]
1|18992|Loss: 0.8190072178840637:  73%|███████▎  | 18991/25880 [3:52:40<1:20:02,  1.43it/s]
1|18992|Loss: 0.8190072178840637:  73%|███████▎  | 18992/25880 [3:52:40<1:21:09,  1.41it/s]
1|18993|Loss: 0.8315039277076721:  73%|███████▎  | 18992/25880 [3:52:41<1:21:09,  1.41it/s]
1|18993|Loss: 0.8315039277076721:  73%|███████▎  | 18993/25880 [3:52:41<1:23:14,  1.38it/s]
1|18994|Loss: 0.8035427927970886:  73%|███████▎  | 18993/25880 [3:52:41<1:23:14,  1.38it/s]
1|18994|Loss: 0.8035427927970886:  73%|███████▎  | 18994/25880 [3:52:42<1:21:04,  1.42it/s]
1|18995|Loss: 0.7423906326293945:  73%|███████▎  | 18994/25880 [3:52:42<1:21:04,  1.42it/s]
1|18995|Loss: 0.7423906326293945:  73%|███████▎  | 18995/25880 [3:52:42<1:20:22,  1.43it/s]
1|18996|Loss: 0.8245043754577637:  73%|███████▎  | 18995/25880 [3:52:43<1:20:22,  1.43it/s]
1|18996|Loss: 0.8245043754577637:  73%|███████▎  | 18996/25880 [3:52:43<1:20:16,  1.43it/s]
1|18997|Loss: 0.7635015249252319:  73%|███████▎  | 18996/25880 [3:52:43<1:20:16,  1.43it/s]
1|18997|Loss: 0.7635015249252319:  73%|███████▎  | 18997/25880 [3:52:44<1:18:28,  1.46it/s]
1|18998|Loss: 0.8607609272003174:  73%|███████▎  | 18997/25880 [3:52:44<1:18:28,  1.46it/s]
1|18998|Loss: 0.8607609272003174:  73%|███████▎  | 18998/25880 [3:52:44<1:19:17,  1.45it/s]
1|18999|Loss: 0.843878448009491:  73%|███████▎  | 18998/25880 [3:52:45<1:19:17,  1.45it/s] 
1|18999|Loss: 0.843878448009491:  73%|███████▎  | 18999/25880 [3:52:45<1:22:33,  1.39it/s]
1|19000|Loss: 0.9080069065093994:  73%|███████▎  | 18999/25880 [3:52:46<1:22:33,  1.39it/s]
1|19000|Loss: 0.9080069065093994:  73%|███████▎  | 19000/25880 [3:52:46<1:25:09,  1.35it/s]
1|19001|Loss: 0.7424412369728088:  73%|███████▎  | 19000/25880 [3:52:46<1:25:09,  1.35it/s]
1|19001|Loss: 0.7424412369728088:  73%|███████▎  | 19001/25880 [3:52:47<1:24:48,  1.35it/s]
1|19002|Loss: 0.750377893447876:  73%|███████▎  | 19001/25880 [3:52:47<1:24:48,  1.35it/s] 
1|19002|Loss: 0.750377893447876:  73%|███████▎  | 19002/25880 [3:52:47<1:23:29,  1.37it/s]
1|19003|Loss: 0.8200559020042419:  73%|███████▎  | 19002/25880 [3:52:48<1:23:29,  1.37it/s]
1|19003|Loss: 0.8200559020042419:  73%|███████▎  | 19003/25880 [3:52:48<1:23:03,  1.38it/s]
1|19004|Loss: 0.7744088768959045:  73%|███████▎  | 19003/25880 [3:52:48<1:23:03,  1.38it/s]
1|19004|Loss: 0.7744088768959045:  73%|███████▎  | 19004/25880 [3:52:49<1:23:44,  1.37it/s]
1|19005|Loss: 0.7050092220306396:  73%|███████▎  | 19004/25880 [3:52:49<1:23:44,  1.37it/s]
1|19005|Loss: 0.7050092220306396:  73%|███████▎  | 19005/25880 [3:52:49<1:19:00,  1.45it/s]
1|19006|Loss: 0.8249950408935547:  73%|███████▎  | 19005/25880 [3:52:50<1:19:00,  1.45it/s]
1|19006|Loss: 0.8249950408935547:  73%|███████▎  | 19006/25880 [3:52:50<1:21:52,  1.40it/s]
1|19007|Loss: 1.0507938861846924:  73%|███████▎  | 19006/25880 [3:52:51<1:21:52,  1.40it/s]
1|19007|Loss: 1.0507938861846924:  73%|███████▎  | 19007/25880 [3:52:51<1:28:08,  1.30it/s]
1|19008|Loss: 0.7463007569313049:  73%|███████▎  | 19007/25880 [3:52:52<1:28:08,  1.30it/s]
1|19008|Loss: 0.7463007569313049:  73%|███████▎  | 19008/25880 [3:52:52<1:28:10,  1.30it/s]
1|19009|Loss: 0.7516247034072876:  73%|███████▎  | 19008/25880 [3:52:52<1:28:10,  1.30it/s]
1|19009|Loss: 0.7516247034072876:  73%|███████▎  | 19009/25880 [3:52:52<1:20:40,  1.42it/s]
1|19010|Loss: 0.8874764442443848:  73%|███████▎  | 19009/25880 [3:52:53<1:20:40,  1.42it/s]
1|19010|Loss: 0.8874764442443848:  73%|███████▎  | 19010/25880 [3:52:53<1:20:01,  1.43it/s]
1|19011|Loss: 0.6603679656982422:  73%|███████▎  | 19010/25880 [3:52:54<1:20:01,  1.43it/s]
1|19011|Loss: 0.6603679656982422:  73%|███████▎  | 19011/25880 [3:52:54<1:24:26,  1.36it/s]
1|19012|Loss: 0.7663643956184387:  73%|███████▎  | 19011/25880 [3:52:54<1:24:26,  1.36it/s]
1|19012|Loss: 0.7663643956184387:  73%|███████▎  | 19012/25880 [3:52:55<1:32:12,  1.24it/s]
1|19013|Loss: 0.914729654788971:  73%|███████▎  | 19012/25880 [3:52:55<1:32:12,  1.24it/s] 
1|19013|Loss: 0.914729654788971:  73%|███████▎  | 19013/25880 [3:52:56<1:31:36,  1.25it/s]
1|19014|Loss: 0.9414902925491333:  73%|███████▎  | 19013/25880 [3:52:56<1:31:36,  1.25it/s]
1|19014|Loss: 0.9414902925491333:  73%|███████▎  | 19014/25880 [3:52:56<1:26:34,  1.32it/s]
1|19015|Loss: 0.7136701941490173:  73%|███████▎  | 19014/25880 [3:52:57<1:26:34,  1.32it/s]
1|19015|Loss: 0.7136701941490173:  73%|███████▎  | 19015/25880 [3:52:57<1:25:36,  1.34it/s]
1|19016|Loss: 0.776557445526123:  73%|███████▎  | 19015/25880 [3:52:58<1:25:36,  1.34it/s] 
1|19016|Loss: 0.776557445526123:  73%|███████▎  | 19016/25880 [3:52:58<1:30:19,  1.27it/s]
1|19017|Loss: 0.6407162547111511:  73%|███████▎  | 19016/25880 [3:52:58<1:30:19,  1.27it/s]
1|19017|Loss: 0.6407162547111511:  73%|███████▎  | 19017/25880 [3:52:59<1:24:02,  1.36it/s]
1|19018|Loss: 0.8081766366958618:  73%|███████▎  | 19017/25880 [3:52:59<1:24:02,  1.36it/s]
1|19018|Loss: 0.8081766366958618:  73%|███████▎  | 19018/25880 [3:52:59<1:17:35,  1.47it/s]
1|19019|Loss: 0.8782113194465637:  73%|███████▎  | 19018/25880 [3:52:59<1:17:35,  1.47it/s]
1|19019|Loss: 0.8782113194465637:  73%|███████▎  | 19019/25880 [3:53:00<1:18:25,  1.46it/s]
1|19020|Loss: 0.7942376136779785:  73%|███████▎  | 19019/25880 [3:53:00<1:18:25,  1.46it/s]
1|19020|Loss: 0.7942376136779785:  73%|███████▎  | 19020/25880 [3:53:01<1:22:11,  1.39it/s]
1|19021|Loss: 0.8101534843444824:  73%|███████▎  | 19020/25880 [3:53:01<1:22:11,  1.39it/s]
1|19021|Loss: 0.8101534843444824:  73%|███████▎  | 19021/25880 [3:53:01<1:23:30,  1.37it/s]
1|19022|Loss: 0.7802181243896484:  73%|███████▎  | 19021/25880 [3:53:02<1:23:30,  1.37it/s]
1|19022|Loss: 0.7802181243896484:  74%|███████▎  | 19022/25880 [3:53:02<1:23:40,  1.37it/s]
1|19023|Loss: 0.7963600158691406:  74%|███████▎  | 19022/25880 [3:53:02<1:23:40,  1.37it/s]
1|19023|Loss: 0.7963600158691406:  74%|███████▎  | 19023/25880 [3:53:03<1:19:45,  1.43it/s]
1|19024|Loss: 0.8859893679618835:  74%|███████▎  | 19023/25880 [3:53:03<1:19:45,  1.43it/s]
1|19024|Loss: 0.8859893679618835:  74%|███████▎  | 19024/25880 [3:53:03<1:20:01,  1.43it/s]
1|19025|Loss: 0.8934316039085388:  74%|███████▎  | 19024/25880 [3:53:04<1:20:01,  1.43it/s]
1|19025|Loss: 0.8934316039085388:  74%|███████▎  | 19025/25880 [3:53:04<1:15:10,  1.52it/s]
1|19026|Loss: 0.8252323865890503:  74%|███████▎  | 19025/25880 [3:53:04<1:15:10,  1.52it/s]
1|19026|Loss: 0.8252323865890503:  74%|███████▎  | 19026/25880 [3:53:05<1:16:13,  1.50it/s]
1|19027|Loss: 0.8532986640930176:  74%|███████▎  | 19026/25880 [3:53:05<1:16:13,  1.50it/s]
1|19027|Loss: 0.8532986640930176:  74%|███████▎  | 19027/25880 [3:53:05<1:15:28,  1.51it/s]
1|19028|Loss: 0.7991989254951477:  74%|███████▎  | 19027/25880 [3:53:06<1:15:28,  1.51it/s]
1|19028|Loss: 0.7991989254951477:  74%|███████▎  | 19028/25880 [3:53:06<1:14:17,  1.54it/s]
1|19029|Loss: 0.7753207087516785:  74%|███████▎  | 19028/25880 [3:53:06<1:14:17,  1.54it/s]
1|19029|Loss: 0.7753207087516785:  74%|███████▎  | 19029/25880 [3:53:07<1:19:07,  1.44it/s]
1|19030|Loss: 0.8135314583778381:  74%|███████▎  | 19029/25880 [3:53:07<1:19:07,  1.44it/s]
1|19030|Loss: 0.8135314583778381:  74%|███████▎  | 19030/25880 [3:53:07<1:18:55,  1.45it/s]
1|19031|Loss: 0.8534920811653137:  74%|███████▎  | 19030/25880 [3:53:08<1:18:55,  1.45it/s]
1|19031|Loss: 0.8534920811653137:  74%|███████▎  | 19031/25880 [3:53:08<1:17:20,  1.48it/s]
1|19032|Loss: 0.8292403817176819:  74%|███████▎  | 19031/25880 [3:53:08<1:17:20,  1.48it/s]
1|19032|Loss: 0.8292403817176819:  74%|███████▎  | 19032/25880 [3:53:09<1:18:49,  1.45it/s]
1|19033|Loss: 0.7930400371551514:  74%|███████▎  | 19032/25880 [3:53:09<1:18:49,  1.45it/s]
1|19033|Loss: 0.7930400371551514:  74%|███████▎  | 19033/25880 [3:53:10<1:23:20,  1.37it/s]
1|19034|Loss: 0.7503190040588379:  74%|███████▎  | 19033/25880 [3:53:10<1:23:20,  1.37it/s]
1|19034|Loss: 0.7503190040588379:  74%|███████▎  | 19034/25880 [3:53:10<1:20:37,  1.42it/s]
1|19035|Loss: 0.7858127951622009:  74%|███████▎  | 19034/25880 [3:53:11<1:20:37,  1.42it/s]
1|19035|Loss: 0.7858127951622009:  74%|███████▎  | 19035/25880 [3:53:11<1:18:02,  1.46it/s]
1|19036|Loss: 0.8605397939682007:  74%|███████▎  | 19035/25880 [3:53:11<1:18:02,  1.46it/s]
1|19036|Loss: 0.8605397939682007:  74%|███████▎  | 19036/25880 [3:53:12<1:22:14,  1.39it/s]
1|19037|Loss: 0.7900995016098022:  74%|███████▎  | 19036/25880 [3:53:12<1:22:14,  1.39it/s]
1|19037|Loss: 0.7900995016098022:  74%|███████▎  | 19037/25880 [3:53:12<1:17:37,  1.47it/s]
1|19038|Loss: 0.9468957781791687:  74%|███████▎  | 19037/25880 [3:53:13<1:17:37,  1.47it/s]
1|19038|Loss: 0.9468957781791687:  74%|███████▎  | 19038/25880 [3:53:13<1:20:35,  1.41it/s]
1|19039|Loss: 1.1387330293655396:  74%|███████▎  | 19038/25880 [3:53:14<1:20:35,  1.41it/s]
1|19039|Loss: 1.1387330293655396:  74%|███████▎  | 19039/25880 [3:53:14<1:33:20,  1.22it/s]
1|19040|Loss: 1.0012485980987549:  74%|███████▎  | 19039/25880 [3:53:15<1:33:20,  1.22it/s]
1|19040|Loss: 1.0012485980987549:  74%|███████▎  | 19040/25880 [3:53:15<1:32:36,  1.23it/s]
1|19041|Loss: 0.9124268293380737:  74%|███████▎  | 19040/25880 [3:53:15<1:32:36,  1.23it/s]
1|19041|Loss: 0.9124268293380737:  74%|███████▎  | 19041/25880 [3:53:16<1:33:39,  1.22it/s]
1|19042|Loss: 0.8924315571784973:  74%|███████▎  | 19041/25880 [3:53:16<1:33:39,  1.22it/s]
1|19042|Loss: 0.8924315571784973:  74%|███████▎  | 19042/25880 [3:53:17<1:31:38,  1.24it/s]
1|19043|Loss: 0.9024592638015747:  74%|███████▎  | 19042/25880 [3:53:17<1:31:38,  1.24it/s]
1|19043|Loss: 0.9024592638015747:  74%|███████▎  | 19043/25880 [3:53:17<1:31:42,  1.24it/s]
1|19044|Loss: 0.8648397326469421:  74%|███████▎  | 19043/25880 [3:53:18<1:31:42,  1.24it/s]
1|19044|Loss: 0.8648397326469421:  74%|███████▎  | 19044/25880 [3:53:18<1:23:47,  1.36it/s]
1|19045|Loss: 0.7899307608604431:  74%|███████▎  | 19044/25880 [3:53:18<1:23:47,  1.36it/s]
1|19045|Loss: 0.7899307608604431:  74%|███████▎  | 19045/25880 [3:53:19<1:18:47,  1.45it/s]
1|19046|Loss: 0.7371174097061157:  74%|███████▎  | 19045/25880 [3:53:19<1:18:47,  1.45it/s]
1|19046|Loss: 0.7371174097061157:  74%|███████▎  | 19046/25880 [3:53:19<1:11:51,  1.58it/s]
1|19047|Loss: 0.8340131640434265:  74%|███████▎  | 19046/25880 [3:53:19<1:11:51,  1.58it/s]
1|19047|Loss: 0.8340131640434265:  74%|███████▎  | 19047/25880 [3:53:20<1:10:48,  1.61it/s]
1|19048|Loss: 0.9831526875495911:  74%|███████▎  | 19047/25880 [3:53:20<1:10:48,  1.61it/s]
1|19048|Loss: 0.9831526875495911:  74%|███████▎  | 19048/25880 [3:53:20<1:13:56,  1.54it/s]
1|19049|Loss: 0.669394850730896:  74%|███████▎  | 19048/25880 [3:53:21<1:13:56,  1.54it/s] 
1|19049|Loss: 0.669394850730896:  74%|███████▎  | 19049/25880 [3:53:21<1:11:38,  1.59it/s]
1|19050|Loss: 0.697230339050293:  74%|███████▎  | 19049/25880 [3:53:21<1:11:38,  1.59it/s]
1|19050|Loss: 0.697230339050293:  74%|███████▎  | 19050/25880 [3:53:21<1:06:27,  1.71it/s]
1|19051|Loss: 0.7483882308006287:  74%|███████▎  | 19050/25880 [3:53:22<1:06:27,  1.71it/s]
1|19051|Loss: 0.7483882308006287:  74%|███████▎  | 19051/25880 [3:53:22<1:10:57,  1.60it/s]
1|19052|Loss: 0.8503811359405518:  74%|███████▎  | 19051/25880 [3:53:22<1:10:57,  1.60it/s]
1|19052|Loss: 0.8503811359405518:  74%|███████▎  | 19052/25880 [3:53:23<1:09:11,  1.64it/s]
1|19053|Loss: 0.783083438873291:  74%|███████▎  | 19052/25880 [3:53:23<1:09:11,  1.64it/s] 
1|19053|Loss: 0.783083438873291:  74%|███████▎  | 19053/25880 [3:53:23<1:11:53,  1.58it/s]
1|19054|Loss: 0.6652148962020874:  74%|███████▎  | 19053/25880 [3:53:24<1:11:53,  1.58it/s]
1|19054|Loss: 0.6652148962020874:  74%|███████▎  | 19054/25880 [3:53:24<1:15:18,  1.51it/s]
1|19055|Loss: 0.8745894432067871:  74%|███████▎  | 19054/25880 [3:53:25<1:15:18,  1.51it/s]
1|19055|Loss: 0.8745894432067871:  74%|███████▎  | 19055/25880 [3:53:25<1:23:53,  1.36it/s]
1|19056|Loss: 0.7951931953430176:  74%|███████▎  | 19055/25880 [3:53:25<1:23:53,  1.36it/s]
1|19056|Loss: 0.7951931953430176:  74%|███████▎  | 19056/25880 [3:53:26<1:28:56,  1.28it/s]
1|19057|Loss: 0.8810949921607971:  74%|███████▎  | 19056/25880 [3:53:26<1:28:56,  1.28it/s]
1|19057|Loss: 0.8810949921607971:  74%|███████▎  | 19057/25880 [3:53:27<1:23:28,  1.36it/s]
1|19058|Loss: 0.8403406143188477:  74%|███████▎  | 19057/25880 [3:53:27<1:23:28,  1.36it/s]
1|19058|Loss: 0.8403406143188477:  74%|███████▎  | 19058/25880 [3:53:27<1:18:55,  1.44it/s]
1|19059|Loss: 0.8884022235870361:  74%|███████▎  | 19058/25880 [3:53:27<1:18:55,  1.44it/s]
1|19059|Loss: 0.8884022235870361:  74%|███████▎  | 19059/25880 [3:53:28<1:20:55,  1.40it/s]
1|19060|Loss: 0.957358717918396:  74%|███████▎  | 19059/25880 [3:53:28<1:20:55,  1.40it/s] 
1|19060|Loss: 0.957358717918396:  74%|███████▎  | 19060/25880 [3:53:29<1:18:55,  1.44it/s]
1|19061|Loss: 0.770993709564209:  74%|███████▎  | 19060/25880 [3:53:29<1:18:55,  1.44it/s]
1|19061|Loss: 0.770993709564209:  74%|███████▎  | 19061/25880 [3:53:29<1:19:23,  1.43it/s]
1|19062|Loss: 0.7249326705932617:  74%|███████▎  | 19061/25880 [3:53:30<1:19:23,  1.43it/s]
1|19062|Loss: 0.7249326705932617:  74%|███████▎  | 19062/25880 [3:53:30<1:20:52,  1.41it/s]
1|19063|Loss: 0.9282172322273254:  74%|███████▎  | 19062/25880 [3:53:30<1:20:52,  1.41it/s]
1|19063|Loss: 0.9282172322273254:  74%|███████▎  | 19063/25880 [3:53:31<1:23:22,  1.36it/s]
1|19064|Loss: 0.8364212512969971:  74%|███████▎  | 19063/25880 [3:53:31<1:23:22,  1.36it/s]
1|19064|Loss: 0.8364212512969971:  74%|███████▎  | 19064/25880 [3:53:31<1:20:38,  1.41it/s]
1|19065|Loss: 0.7464079260826111:  74%|███████▎  | 19064/25880 [3:53:32<1:20:38,  1.41it/s]
1|19065|Loss: 0.7464079260826111:  74%|███████▎  | 19065/25880 [3:53:32<1:20:02,  1.42it/s]
1|19066|Loss: 0.8467960953712463:  74%|███████▎  | 19065/25880 [3:53:32<1:20:02,  1.42it/s]
1|19066|Loss: 0.8467960953712463:  74%|███████▎  | 19066/25880 [3:53:33<1:20:40,  1.41it/s]
1|19067|Loss: 0.9917920231819153:  74%|███████▎  | 19066/25880 [3:53:33<1:20:40,  1.41it/s]
1|19067|Loss: 0.9917920231819153:  74%|███████▎  | 19067/25880 [3:53:33<1:18:14,  1.45it/s]
1|19068|Loss: 0.8191591501235962:  74%|███████▎  | 19067/25880 [3:53:34<1:18:14,  1.45it/s]
1|19068|Loss: 0.8191591501235962:  74%|███████▎  | 19068/25880 [3:53:34<1:09:17,  1.64it/s]
1|19069|Loss: 0.972861647605896:  74%|███████▎  | 19068/25880 [3:53:34<1:09:17,  1.64it/s] 
1|19069|Loss: 0.972861647605896:  74%|███████▎  | 19069/25880 [3:53:35<1:12:29,  1.57it/s]
1|19070|Loss: 0.7461195588111877:  74%|███████▎  | 19069/25880 [3:53:35<1:12:29,  1.57it/s]
1|19070|Loss: 0.7461195588111877:  74%|███████▎  | 19070/25880 [3:53:35<1:16:51,  1.48it/s]
1|19071|Loss: 0.7947970628738403:  74%|███████▎  | 19070/25880 [3:53:36<1:16:51,  1.48it/s]
1|19071|Loss: 0.7947970628738403:  74%|███████▎  | 19071/25880 [3:53:36<1:15:59,  1.49it/s]
1|19072|Loss: 0.9894818067550659:  74%|███████▎  | 19071/25880 [3:53:36<1:15:59,  1.49it/s]
1|19072|Loss: 0.9894818067550659:  74%|███████▎  | 19072/25880 [3:53:37<1:17:10,  1.47it/s]
1|19073|Loss: 0.841252863407135:  74%|███████▎  | 19072/25880 [3:53:37<1:17:10,  1.47it/s] 
1|19073|Loss: 0.841252863407135:  74%|███████▎  | 19073/25880 [3:53:38<1:21:17,  1.40it/s]
1|19074|Loss: 0.8651761412620544:  74%|███████▎  | 19073/25880 [3:53:38<1:21:17,  1.40it/s]
1|19074|Loss: 0.8651761412620544:  74%|███████▎  | 19074/25880 [3:53:38<1:19:18,  1.43it/s]
1|19075|Loss: 0.7138395309448242:  74%|███████▎  | 19074/25880 [3:53:39<1:19:18,  1.43it/s]
1|19075|Loss: 0.7138395309448242:  74%|███████▎  | 19075/25880 [3:53:39<1:18:58,  1.44it/s]
1|19076|Loss: 0.9600686430931091:  74%|███████▎  | 19075/25880 [3:53:39<1:18:58,  1.44it/s]
1|19076|Loss: 0.9600686430931091:  74%|███████▎  | 19076/25880 [3:53:40<1:26:40,  1.31it/s]
1|19077|Loss: 0.7561989426612854:  74%|███████▎  | 19076/25880 [3:53:40<1:26:40,  1.31it/s]
1|19077|Loss: 0.7561989426612854:  74%|███████▎  | 19077/25880 [3:53:41<1:31:12,  1.24it/s]
1|19078|Loss: 0.8217149376869202:  74%|███████▎  | 19077/25880 [3:53:41<1:31:12,  1.24it/s]
1|19078|Loss: 0.8217149376869202:  74%|███████▎  | 19078/25880 [3:53:41<1:20:31,  1.41it/s]
1|19079|Loss: 0.9024677276611328:  74%|███████▎  | 19078/25880 [3:53:42<1:20:31,  1.41it/s]
1|19079|Loss: 0.9024677276611328:  74%|███████▎  | 19079/25880 [3:53:42<1:21:23,  1.39it/s]
1|19080|Loss: 0.7765637040138245:  74%|███████▎  | 19079/25880 [3:53:42<1:21:23,  1.39it/s]
1|19080|Loss: 0.7765637040138245:  74%|███████▎  | 19080/25880 [3:53:43<1:18:45,  1.44it/s]
1|19081|Loss: 0.9914888143539429:  74%|███████▎  | 19080/25880 [3:53:43<1:18:45,  1.44it/s]
1|19081|Loss: 0.9914888143539429:  74%|███████▎  | 19081/25880 [3:53:43<1:16:20,  1.48it/s]
1|19082|Loss: 0.8704797029495239:  74%|███████▎  | 19081/25880 [3:53:44<1:16:20,  1.48it/s]
1|19082|Loss: 0.8704797029495239:  74%|███████▎  | 19082/25880 [3:53:44<1:21:24,  1.39it/s]
1|19083|Loss: 0.8894593715667725:  74%|███████▎  | 19082/25880 [3:53:44<1:21:24,  1.39it/s]
1|19083|Loss: 0.8894593715667725:  74%|███████▎  | 19083/25880 [3:53:45<1:20:21,  1.41it/s]
1|19084|Loss: 0.8615368604660034:  74%|███████▎  | 19083/25880 [3:53:45<1:20:21,  1.41it/s]
1|19084|Loss: 0.8615368604660034:  74%|███████▎  | 19084/25880 [3:53:45<1:17:19,  1.46it/s]
1|19085|Loss: 0.7426390051841736:  74%|███████▎  | 19084/25880 [3:53:46<1:17:19,  1.46it/s]
1|19085|Loss: 0.7426390051841736:  74%|███████▎  | 19085/25880 [3:53:46<1:22:16,  1.38it/s]
1|19086|Loss: 0.8902029395103455:  74%|███████▎  | 19085/25880 [3:53:47<1:22:16,  1.38it/s]
1|19086|Loss: 0.8902029395103455:  74%|███████▎  | 19086/25880 [3:53:47<1:19:38,  1.42it/s]
1|19087|Loss: 0.8504578471183777:  74%|███████▎  | 19086/25880 [3:53:47<1:19:38,  1.42it/s]
1|19087|Loss: 0.8504578471183777:  74%|███████▍  | 19087/25880 [3:53:47<1:16:24,  1.48it/s]
1|19088|Loss: 0.9604532718658447:  74%|███████▍  | 19087/25880 [3:53:48<1:16:24,  1.48it/s]
1|19088|Loss: 0.9604532718658447:  74%|███████▍  | 19088/25880 [3:53:48<1:21:40,  1.39it/s]
1|19089|Loss: 0.7745261788368225:  74%|███████▍  | 19088/25880 [3:53:49<1:21:40,  1.39it/s]
1|19089|Loss: 0.7745261788368225:  74%|███████▍  | 19089/25880 [3:53:49<1:28:20,  1.28it/s]
1|19090|Loss: 0.7882862091064453:  74%|███████▍  | 19089/25880 [3:53:50<1:28:20,  1.28it/s]
1|19090|Loss: 0.7882862091064453:  74%|███████▍  | 19090/25880 [3:53:50<1:27:49,  1.29it/s]
1|19091|Loss: 0.7692317962646484:  74%|███████▍  | 19090/25880 [3:53:50<1:27:49,  1.29it/s]
1|19091|Loss: 0.7692317962646484:  74%|███████▍  | 19091/25880 [3:53:50<1:19:35,  1.42it/s]
1|19092|Loss: 0.9026230573654175:  74%|███████▍  | 19091/25880 [3:53:51<1:19:35,  1.42it/s]
1|19092|Loss: 0.9026230573654175:  74%|███████▍  | 19092/25880 [3:53:51<1:22:00,  1.38it/s]
1|19093|Loss: 0.707335889339447:  74%|███████▍  | 19092/25880 [3:53:52<1:22:00,  1.38it/s] 
1|19093|Loss: 0.707335889339447:  74%|███████▍  | 19093/25880 [3:53:52<1:23:08,  1.36it/s]
1|19094|Loss: 0.9037899374961853:  74%|███████▍  | 19093/25880 [3:53:52<1:23:08,  1.36it/s]
1|19094|Loss: 0.9037899374961853:  74%|███████▍  | 19094/25880 [3:53:53<1:22:12,  1.38it/s]
1|19095|Loss: 0.7220149636268616:  74%|███████▍  | 19094/25880 [3:53:53<1:22:12,  1.38it/s]
1|19095|Loss: 0.7220149636268616:  74%|███████▍  | 19095/25880 [3:53:53<1:15:22,  1.50it/s]
1|19096|Loss: 0.8638663291931152:  74%|███████▍  | 19095/25880 [3:53:54<1:15:22,  1.50it/s]
1|19096|Loss: 0.8638663291931152:  74%|███████▍  | 19096/25880 [3:53:54<1:16:04,  1.49it/s]
1|19097|Loss: 0.7438856363296509:  74%|███████▍  | 19096/25880 [3:53:54<1:16:04,  1.49it/s]
1|19097|Loss: 0.7438856363296509:  74%|███████▍  | 19097/25880 [3:53:55<1:21:10,  1.39it/s]
1|19098|Loss: 0.7859088778495789:  74%|███████▍  | 19097/25880 [3:53:55<1:21:10,  1.39it/s]
1|19098|Loss: 0.7859088778495789:  74%|███████▍  | 19098/25880 [3:53:55<1:22:14,  1.37it/s]
1|19099|Loss: 0.7924383878707886:  74%|███████▍  | 19098/25880 [3:53:56<1:22:14,  1.37it/s]
1|19099|Loss: 0.7924383878707886:  74%|███████▍  | 19099/25880 [3:53:56<1:19:57,  1.41it/s]
1|19100|Loss: 0.7817661166191101:  74%|███████▍  | 19099/25880 [3:53:56<1:19:57,  1.41it/s]
1|19100|Loss: 0.7817661166191101:  74%|███████▍  | 19100/25880 [3:53:57<1:17:13,  1.46it/s]
1|19101|Loss: 0.922717273235321:  74%|███████▍  | 19100/25880 [3:53:57<1:17:13,  1.46it/s] 
1|19101|Loss: 0.922717273235321:  74%|███████▍  | 19101/25880 [3:53:57<1:17:37,  1.46it/s]
1|19102|Loss: 0.851614773273468:  74%|███████▍  | 19101/25880 [3:53:58<1:17:37,  1.46it/s]
1|19102|Loss: 0.851614773273468:  74%|███████▍  | 19102/25880 [3:53:58<1:16:20,  1.48it/s]
1|19103|Loss: 0.6735519766807556:  74%|███████▍  | 19102/25880 [3:53:58<1:16:20,  1.48it/s]
1|19103|Loss: 0.6735519766807556:  74%|███████▍  | 19103/25880 [3:53:59<1:19:08,  1.43it/s]
1|19104|Loss: 0.7991082668304443:  74%|███████▍  | 19103/25880 [3:53:59<1:19:08,  1.43it/s]
1|19104|Loss: 0.7991082668304443:  74%|███████▍  | 19104/25880 [3:54:00<1:22:09,  1.37it/s]
1|19105|Loss: 0.8749374151229858:  74%|███████▍  | 19104/25880 [3:54:00<1:22:09,  1.37it/s]
1|19105|Loss: 0.8749374151229858:  74%|███████▍  | 19105/25880 [3:54:00<1:22:33,  1.37it/s]
1|19106|Loss: 0.7918556928634644:  74%|███████▍  | 19105/25880 [3:54:01<1:22:33,  1.37it/s]
1|19106|Loss: 0.7918556928634644:  74%|███████▍  | 19106/25880 [3:54:01<1:24:00,  1.34it/s]
1|19107|Loss: 0.8923184871673584:  74%|███████▍  | 19106/25880 [3:54:02<1:24:00,  1.34it/s]
1|19107|Loss: 0.8923184871673584:  74%|███████▍  | 19107/25880 [3:54:02<1:25:38,  1.32it/s]
1|19108|Loss: 0.9214995503425598:  74%|███████▍  | 19107/25880 [3:54:02<1:25:38,  1.32it/s]
1|19108|Loss: 0.9214995503425598:  74%|███████▍  | 19108/25880 [3:54:03<1:24:37,  1.33it/s]
1|19109|Loss: 0.8537142276763916:  74%|███████▍  | 19108/25880 [3:54:03<1:24:37,  1.33it/s]
1|19109|Loss: 0.8537142276763916:  74%|███████▍  | 19109/25880 [3:54:03<1:26:25,  1.31it/s]
1|19110|Loss: 0.7998504638671875:  74%|███████▍  | 19109/25880 [3:54:04<1:26:25,  1.31it/s]
1|19110|Loss: 0.7998504638671875:  74%|███████▍  | 19110/25880 [3:54:04<1:23:17,  1.35it/s]
1|19111|Loss: 0.8300343751907349:  74%|███████▍  | 19110/25880 [3:54:05<1:23:17,  1.35it/s]
1|19111|Loss: 0.8300343751907349:  74%|███████▍  | 19111/25880 [3:54:05<1:24:07,  1.34it/s]
1|19112|Loss: 0.9544814825057983:  74%|███████▍  | 19111/25880 [3:54:05<1:24:07,  1.34it/s]
1|19112|Loss: 0.9544814825057983:  74%|███████▍  | 19112/25880 [3:54:06<1:24:01,  1.34it/s]
1|19113|Loss: 0.8148069977760315:  74%|███████▍  | 19112/25880 [3:54:06<1:24:01,  1.34it/s]
1|19113|Loss: 0.8148069977760315:  74%|███████▍  | 19113/25880 [3:54:06<1:23:41,  1.35it/s]
1|19114|Loss: 0.8628764152526855:  74%|███████▍  | 19113/25880 [3:54:07<1:23:41,  1.35it/s]
1|19114|Loss: 0.8628764152526855:  74%|███████▍  | 19114/25880 [3:54:07<1:13:42,  1.53it/s]
1|19115|Loss: 0.9392083287239075:  74%|███████▍  | 19114/25880 [3:54:07<1:13:42,  1.53it/s]
1|19115|Loss: 0.9392083287239075:  74%|███████▍  | 19115/25880 [3:54:07<1:13:16,  1.54it/s]
1|19116|Loss: 0.8876559734344482:  74%|███████▍  | 19115/25880 [3:54:08<1:13:16,  1.54it/s]
1|19116|Loss: 0.8876559734344482:  74%|███████▍  | 19116/25880 [3:54:08<1:11:54,  1.57it/s]
1|19117|Loss: 0.8445451855659485:  74%|███████▍  | 19116/25880 [3:54:09<1:11:54,  1.57it/s]
1|19117|Loss: 0.8445451855659485:  74%|███████▍  | 19117/25880 [3:54:09<1:22:44,  1.36it/s]
1|19118|Loss: 0.8470744490623474:  74%|███████▍  | 19117/25880 [3:54:09<1:22:44,  1.36it/s]
1|19118|Loss: 0.8470744490623474:  74%|███████▍  | 19118/25880 [3:54:10<1:17:12,  1.46it/s]
1|19119|Loss: 0.9330461621284485:  74%|███████▍  | 19118/25880 [3:54:10<1:17:12,  1.46it/s]
1|19119|Loss: 0.9330461621284485:  74%|███████▍  | 19119/25880 [3:54:10<1:10:45,  1.59it/s]
1|19120|Loss: 0.9056407809257507:  74%|███████▍  | 19119/25880 [3:54:10<1:10:45,  1.59it/s]
1|19120|Loss: 0.9056407809257507:  74%|███████▍  | 19120/25880 [3:54:11<1:10:14,  1.60it/s]
1|19121|Loss: 0.7800759673118591:  74%|███████▍  | 19120/25880 [3:54:11<1:10:14,  1.60it/s]
1|19121|Loss: 0.7800759673118591:  74%|███████▍  | 19121/25880 [3:54:12<1:18:24,  1.44it/s]
1|19122|Loss: 1.3256086111068726:  74%|███████▍  | 19121/25880 [3:54:12<1:18:24,  1.44it/s]
1|19122|Loss: 1.3256086111068726:  74%|███████▍  | 19122/25880 [3:54:12<1:23:58,  1.34it/s]
1|19123|Loss: 0.6974734663963318:  74%|███████▍  | 19122/25880 [3:54:13<1:23:58,  1.34it/s]
1|19123|Loss: 0.6974734663963318:  74%|███████▍  | 19123/25880 [3:54:13<1:22:09,  1.37it/s]
1|19124|Loss: 0.8258196115493774:  74%|███████▍  | 19123/25880 [3:54:14<1:22:09,  1.37it/s]
1|19124|Loss: 0.8258196115493774:  74%|███████▍  | 19124/25880 [3:54:14<1:23:04,  1.36it/s]
1|19125|Loss: 0.8707258105278015:  74%|███████▍  | 19124/25880 [3:54:14<1:23:04,  1.36it/s]
1|19125|Loss: 0.8707258105278015:  74%|███████▍  | 19125/25880 [3:54:15<1:21:04,  1.39it/s]
1|19126|Loss: 0.8454955220222473:  74%|███████▍  | 19125/25880 [3:54:15<1:21:04,  1.39it/s]
1|19126|Loss: 0.8454955220222473:  74%|███████▍  | 19126/25880 [3:54:16<1:27:47,  1.28it/s]
1|19127|Loss: 0.8506482243537903:  74%|███████▍  | 19126/25880 [3:54:16<1:27:47,  1.28it/s]
1|19127|Loss: 0.8506482243537903:  74%|███████▍  | 19127/25880 [3:54:16<1:25:39,  1.31it/s]
1|19128|Loss: 0.8174580335617065:  74%|███████▍  | 19127/25880 [3:54:17<1:25:39,  1.31it/s]
1|19128|Loss: 0.8174580335617065:  74%|███████▍  | 19128/25880 [3:54:17<1:27:00,  1.29it/s]
1|19129|Loss: 0.8774664402008057:  74%|███████▍  | 19128/25880 [3:54:17<1:27:00,  1.29it/s]
1|19129|Loss: 0.8774664402008057:  74%|███████▍  | 19129/25880 [3:54:18<1:20:57,  1.39it/s]
1|19130|Loss: 0.8866710066795349:  74%|███████▍  | 19129/25880 [3:54:18<1:20:57,  1.39it/s]
1|19130|Loss: 0.8866710066795349:  74%|███████▍  | 19130/25880 [3:54:18<1:20:03,  1.41it/s]
1|19131|Loss: 0.7679184079170227:  74%|███████▍  | 19130/25880 [3:54:19<1:20:03,  1.41it/s]
1|19131|Loss: 0.7679184079170227:  74%|███████▍  | 19131/25880 [3:54:19<1:16:32,  1.47it/s]
1|19132|Loss: 0.7896188497543335:  74%|███████▍  | 19131/25880 [3:54:19<1:16:32,  1.47it/s]
1|19132|Loss: 0.7896188497543335:  74%|███████▍  | 19132/25880 [3:54:20<1:23:25,  1.35it/s]
1|19133|Loss: 0.8778484463691711:  74%|███████▍  | 19132/25880 [3:54:20<1:23:25,  1.35it/s]
1|19133|Loss: 0.8778484463691711:  74%|███████▍  | 19133/25880 [3:54:21<1:27:25,  1.29it/s]
1|19134|Loss: 0.7601420879364014:  74%|███████▍  | 19133/25880 [3:54:21<1:27:25,  1.29it/s]
1|19134|Loss: 0.7601420879364014:  74%|███████▍  | 19134/25880 [3:54:21<1:26:47,  1.30it/s]
1|19135|Loss: 0.8717122673988342:  74%|███████▍  | 19134/25880 [3:54:22<1:26:47,  1.30it/s]
1|19135|Loss: 0.8717122673988342:  74%|███████▍  | 19135/25880 [3:54:22<1:31:47,  1.22it/s]
1|19136|Loss: 0.9545412659645081:  74%|███████▍  | 19135/25880 [3:54:23<1:31:47,  1.22it/s]
1|19136|Loss: 0.9545412659645081:  74%|███████▍  | 19136/25880 [3:54:23<1:32:28,  1.22it/s]
1|19137|Loss: 0.867172122001648:  74%|███████▍  | 19136/25880 [3:54:24<1:32:28,  1.22it/s] 
1|19137|Loss: 0.867172122001648:  74%|███████▍  | 19137/25880 [3:54:24<1:25:54,  1.31it/s]
1|19138|Loss: 0.8683134317398071:  74%|███████▍  | 19137/25880 [3:54:24<1:25:54,  1.31it/s]
1|19138|Loss: 0.8683134317398071:  74%|███████▍  | 19138/25880 [3:54:24<1:17:48,  1.44it/s]
1|19139|Loss: 0.8974939584732056:  74%|███████▍  | 19138/25880 [3:54:25<1:17:48,  1.44it/s]
1|19139|Loss: 0.8974939584732056:  74%|███████▍  | 19139/25880 [3:54:25<1:17:46,  1.44it/s]
1|19140|Loss: 0.6716915965080261:  74%|███████▍  | 19139/25880 [3:54:25<1:17:46,  1.44it/s]
1|19140|Loss: 0.6716915965080261:  74%|███████▍  | 19140/25880 [3:54:26<1:16:52,  1.46it/s]
1|19141|Loss: 0.8608464598655701:  74%|███████▍  | 19140/25880 [3:54:26<1:16:52,  1.46it/s]
1|19141|Loss: 0.8608464598655701:  74%|███████▍  | 19141/25880 [3:54:26<1:19:51,  1.41it/s]
1|19142|Loss: 1.0014580488204956:  74%|███████▍  | 19141/25880 [3:54:27<1:19:51,  1.41it/s]
1|19142|Loss: 1.0014580488204956:  74%|███████▍  | 19142/25880 [3:54:27<1:25:55,  1.31it/s]
1|19143|Loss: 0.8321617245674133:  74%|███████▍  | 19142/25880 [3:54:28<1:25:55,  1.31it/s]
1|19143|Loss: 0.8321617245674133:  74%|███████▍  | 19143/25880 [3:54:28<1:25:19,  1.32it/s]
1|19144|Loss: 0.9031438827514648:  74%|███████▍  | 19143/25880 [3:54:29<1:25:19,  1.32it/s]
1|19144|Loss: 0.9031438827514648:  74%|███████▍  | 19144/25880 [3:54:29<1:27:41,  1.28it/s]
1|19145|Loss: 0.9835305213928223:  74%|███████▍  | 19144/25880 [3:54:29<1:27:41,  1.28it/s]
1|19145|Loss: 0.9835305213928223:  74%|███████▍  | 19145/25880 [3:54:30<1:27:19,  1.29it/s]
1|19146|Loss: 0.8915966153144836:  74%|███████▍  | 19145/25880 [3:54:30<1:27:19,  1.29it/s]
1|19146|Loss: 0.8915966153144836:  74%|███████▍  | 19146/25880 [3:54:30<1:25:15,  1.32it/s]
1|19147|Loss: 0.7476580142974854:  74%|███████▍  | 19146/25880 [3:54:31<1:25:15,  1.32it/s]
1|19147|Loss: 0.7476580142974854:  74%|███████▍  | 19147/25880 [3:54:31<1:20:58,  1.39it/s]
1|19148|Loss: 0.9646652936935425:  74%|███████▍  | 19147/25880 [3:54:31<1:20:58,  1.39it/s]
1|19148|Loss: 0.9646652936935425:  74%|███████▍  | 19148/25880 [3:54:32<1:18:03,  1.44it/s]
1|19149|Loss: 0.7982730269432068:  74%|███████▍  | 19148/25880 [3:54:32<1:18:03,  1.44it/s]
1|19149|Loss: 0.7982730269432068:  74%|███████▍  | 19149/25880 [3:54:32<1:17:57,  1.44it/s]
1|19150|Loss: 0.8580628633499146:  74%|███████▍  | 19149/25880 [3:54:33<1:17:57,  1.44it/s]
1|19150|Loss: 0.8580628633499146:  74%|███████▍  | 19150/25880 [3:54:33<1:19:02,  1.42it/s]
1|19151|Loss: 0.7893063426017761:  74%|███████▍  | 19150/25880 [3:54:34<1:19:02,  1.42it/s]
1|19151|Loss: 0.7893063426017761:  74%|███████▍  | 19151/25880 [3:54:34<1:19:57,  1.40it/s]
1|19152|Loss: 0.7311514019966125:  74%|███████▍  | 19151/25880 [3:54:34<1:19:57,  1.40it/s]
1|19152|Loss: 0.7311514019966125:  74%|███████▍  | 19152/25880 [3:54:35<1:18:05,  1.44it/s]
1|19153|Loss: 0.8632447123527527:  74%|███████▍  | 19152/25880 [3:54:35<1:18:05,  1.44it/s]
1|19153|Loss: 0.8632447123527527:  74%|███████▍  | 19153/25880 [3:54:35<1:15:29,  1.49it/s]
1|19154|Loss: 0.9274736642837524:  74%|███████▍  | 19153/25880 [3:54:35<1:15:29,  1.49it/s]
1|19154|Loss: 0.9274736642837524:  74%|███████▍  | 19154/25880 [3:54:36<1:14:06,  1.51it/s]
1|19155|Loss: 0.8505836725234985:  74%|███████▍  | 19154/25880 [3:54:36<1:14:06,  1.51it/s]
1|19155|Loss: 0.8505836725234985:  74%|███████▍  | 19155/25880 [3:54:36<1:15:06,  1.49it/s]
1|19156|Loss: 0.7947081923484802:  74%|███████▍  | 19155/25880 [3:54:37<1:15:06,  1.49it/s]
1|19156|Loss: 0.7947081923484802:  74%|███████▍  | 19156/25880 [3:54:37<1:16:08,  1.47it/s]
1|19157|Loss: 0.8831108808517456:  74%|███████▍  | 19156/25880 [3:54:38<1:16:08,  1.47it/s]
1|19157|Loss: 0.8831108808517456:  74%|███████▍  | 19157/25880 [3:54:38<1:18:11,  1.43it/s]
1|19158|Loss: 0.8424455523490906:  74%|███████▍  | 19157/25880 [3:54:38<1:18:11,  1.43it/s]
1|19158|Loss: 0.8424455523490906:  74%|███████▍  | 19158/25880 [3:54:39<1:19:27,  1.41it/s]
1|19159|Loss: 1.0087271928787231:  74%|███████▍  | 19158/25880 [3:54:39<1:19:27,  1.41it/s]
1|19159|Loss: 1.0087271928787231:  74%|███████▍  | 19159/25880 [3:54:39<1:20:05,  1.40it/s]
1|19160|Loss: 0.8440349698066711:  74%|███████▍  | 19159/25880 [3:54:40<1:20:05,  1.40it/s]
1|19160|Loss: 0.8440349698066711:  74%|███████▍  | 19160/25880 [3:54:40<1:18:13,  1.43it/s]
1|19161|Loss: 0.9957277178764343:  74%|███████▍  | 19160/25880 [3:54:40<1:18:13,  1.43it/s]
1|19161|Loss: 0.9957277178764343:  74%|███████▍  | 19161/25880 [3:54:41<1:15:40,  1.48it/s]
1|19162|Loss: 0.7685850262641907:  74%|███████▍  | 19161/25880 [3:54:41<1:15:40,  1.48it/s]
1|19162|Loss: 0.7685850262641907:  74%|███████▍  | 19162/25880 [3:54:41<1:14:27,  1.50it/s]
1|19163|Loss: 0.8049052953720093:  74%|███████▍  | 19162/25880 [3:54:42<1:14:27,  1.50it/s]
1|19163|Loss: 0.8049052953720093:  74%|███████▍  | 19163/25880 [3:54:42<1:13:39,  1.52it/s]
1|19164|Loss: 0.8374152183532715:  74%|███████▍  | 19163/25880 [3:54:42<1:13:39,  1.52it/s]
1|19164|Loss: 0.8374152183532715:  74%|███████▍  | 19164/25880 [3:54:43<1:19:27,  1.41it/s]
1|19165|Loss: 0.9932646155357361:  74%|███████▍  | 19164/25880 [3:54:43<1:19:27,  1.41it/s]
1|19165|Loss: 0.9932646155357361:  74%|███████▍  | 19165/25880 [3:54:44<1:20:40,  1.39it/s]
1|19166|Loss: 0.8191635012626648:  74%|███████▍  | 19165/25880 [3:54:44<1:20:40,  1.39it/s]
1|19166|Loss: 0.8191635012626648:  74%|███████▍  | 19166/25880 [3:54:44<1:27:04,  1.29it/s]
1|19167|Loss: 0.7835775017738342:  74%|███████▍  | 19166/25880 [3:54:45<1:27:04,  1.29it/s]
1|19167|Loss: 0.7835775017738342:  74%|███████▍  | 19167/25880 [3:54:45<1:23:07,  1.35it/s]
1|19168|Loss: 0.7471741437911987:  74%|███████▍  | 19167/25880 [3:54:45<1:23:07,  1.35it/s]
1|19168|Loss: 0.7471741437911987:  74%|███████▍  | 19168/25880 [3:54:46<1:19:06,  1.41it/s]
1|19169|Loss: 0.9636089205741882:  74%|███████▍  | 19168/25880 [3:54:46<1:19:06,  1.41it/s]
1|19169|Loss: 0.9636089205741882:  74%|███████▍  | 19169/25880 [3:54:47<1:23:00,  1.35it/s]
1|19170|Loss: 0.730083167552948:  74%|███████▍  | 19169/25880 [3:54:47<1:23:00,  1.35it/s] 
1|19170|Loss: 0.730083167552948:  74%|███████▍  | 19170/25880 [3:54:47<1:26:19,  1.30it/s]
1|19171|Loss: 0.7089532017707825:  74%|███████▍  | 19170/25880 [3:54:48<1:26:19,  1.30it/s]
1|19171|Loss: 0.7089532017707825:  74%|███████▍  | 19171/25880 [3:54:48<1:22:27,  1.36it/s]
1|19172|Loss: 0.8860495090484619:  74%|███████▍  | 19171/25880 [3:54:48<1:22:27,  1.36it/s]
1|19172|Loss: 0.8860495090484619:  74%|███████▍  | 19172/25880 [3:54:49<1:18:20,  1.43it/s]
1|19173|Loss: 0.7220883965492249:  74%|███████▍  | 19172/25880 [3:54:49<1:18:20,  1.43it/s]
1|19173|Loss: 0.7220883965492249:  74%|███████▍  | 19173/25880 [3:54:49<1:18:50,  1.42it/s]
1|19174|Loss: 0.8854149580001831:  74%|███████▍  | 19173/25880 [3:54:50<1:18:50,  1.42it/s]
1|19174|Loss: 0.8854149580001831:  74%|███████▍  | 19174/25880 [3:54:50<1:19:08,  1.41it/s]
1|19175|Loss: 0.8765209317207336:  74%|███████▍  | 19174/25880 [3:54:50<1:19:08,  1.41it/s]
1|19175|Loss: 0.8765209317207336:  74%|███████▍  | 19175/25880 [3:54:51<1:18:52,  1.42it/s]
1|19176|Loss: 0.8201779723167419:  74%|███████▍  | 19175/25880 [3:54:51<1:18:52,  1.42it/s]
1|19176|Loss: 0.8201779723167419:  74%|███████▍  | 19176/25880 [3:54:52<1:25:42,  1.30it/s]
1|19177|Loss: 0.9001896381378174:  74%|███████▍  | 19176/25880 [3:54:52<1:25:42,  1.30it/s]
1|19177|Loss: 0.9001896381378174:  74%|███████▍  | 19177/25880 [3:54:52<1:20:03,  1.40it/s]
1|19178|Loss: 0.8264928460121155:  74%|███████▍  | 19177/25880 [3:54:53<1:20:03,  1.40it/s]
1|19178|Loss: 0.8264928460121155:  74%|███████▍  | 19178/25880 [3:54:53<1:21:01,  1.38it/s]
1|19179|Loss: 0.7916476130485535:  74%|███████▍  | 19178/25880 [3:54:53<1:21:01,  1.38it/s]
1|19179|Loss: 0.7916476130485535:  74%|███████▍  | 19179/25880 [3:54:54<1:23:14,  1.34it/s]
1|19180|Loss: 0.8028503656387329:  74%|███████▍  | 19179/25880 [3:54:54<1:23:14,  1.34it/s]
1|19180|Loss: 0.8028503656387329:  74%|███████▍  | 19180/25880 [3:54:54<1:21:00,  1.38it/s]
1|19181|Loss: 0.8378228545188904:  74%|███████▍  | 19180/25880 [3:54:55<1:21:00,  1.38it/s]
1|19181|Loss: 0.8378228545188904:  74%|███████▍  | 19181/25880 [3:54:55<1:22:31,  1.35it/s]
1|19182|Loss: 0.9515584707260132:  74%|███████▍  | 19181/25880 [3:54:56<1:22:31,  1.35it/s]
1|19182|Loss: 0.9515584707260132:  74%|███████▍  | 19182/25880 [3:54:56<1:22:43,  1.35it/s]
1|19183|Loss: 0.8191508650779724:  74%|███████▍  | 19182/25880 [3:54:56<1:22:43,  1.35it/s]
1|19183|Loss: 0.8191508650779724:  74%|███████▍  | 19183/25880 [3:54:57<1:17:39,  1.44it/s]
1|19184|Loss: 0.7633137702941895:  74%|███████▍  | 19183/25880 [3:54:57<1:17:39,  1.44it/s]
1|19184|Loss: 0.7633137702941895:  74%|███████▍  | 19184/25880 [3:54:57<1:15:09,  1.48it/s]
1|19185|Loss: 0.7719969153404236:  74%|███████▍  | 19184/25880 [3:54:58<1:15:09,  1.48it/s]
1|19185|Loss: 0.7719969153404236:  74%|███████▍  | 19185/25880 [3:54:58<1:12:22,  1.54it/s]
1|19186|Loss: 0.7215873003005981:  74%|███████▍  | 19185/25880 [3:54:58<1:12:22,  1.54it/s]
1|19186|Loss: 0.7215873003005981:  74%|███████▍  | 19186/25880 [3:54:59<1:18:57,  1.41it/s]
1|19187|Loss: 0.7638486623764038:  74%|███████▍  | 19186/25880 [3:54:59<1:18:57,  1.41it/s]
1|19187|Loss: 0.7638486623764038:  74%|███████▍  | 19187/25880 [3:54:59<1:11:12,  1.57it/s]
1|19188|Loss: 0.9923152327537537:  74%|███████▍  | 19187/25880 [3:54:59<1:11:12,  1.57it/s]
1|19188|Loss: 0.9923152327537537:  74%|███████▍  | 19188/25880 [3:55:00<1:15:10,  1.48it/s]
1|19189|Loss: 0.8191640973091125:  74%|███████▍  | 19188/25880 [3:55:00<1:15:10,  1.48it/s]
1|19189|Loss: 0.8191640973091125:  74%|███████▍  | 19189/25880 [3:55:01<1:18:08,  1.43it/s]
1|19190|Loss: 0.9183282852172852:  74%|███████▍  | 19189/25880 [3:55:01<1:18:08,  1.43it/s]
1|19190|Loss: 0.9183282852172852:  74%|███████▍  | 19190/25880 [3:55:01<1:19:14,  1.41it/s]
1|19191|Loss: 0.7142818570137024:  74%|███████▍  | 19190/25880 [3:55:02<1:19:14,  1.41it/s]
1|19191|Loss: 0.7142818570137024:  74%|███████▍  | 19191/25880 [3:55:02<1:19:45,  1.40it/s]
1|19192|Loss: 0.9886403679847717:  74%|███████▍  | 19191/25880 [3:55:03<1:19:45,  1.40it/s]
1|19192|Loss: 0.9886403679847717:  74%|███████▍  | 19192/25880 [3:55:03<1:22:56,  1.34it/s]
1|19193|Loss: 0.9793705940246582:  74%|███████▍  | 19192/25880 [3:55:03<1:22:56,  1.34it/s]
1|19193|Loss: 0.9793705940246582:  74%|███████▍  | 19193/25880 [3:55:04<1:23:28,  1.34it/s]
1|19194|Loss: 0.7354385852813721:  74%|███████▍  | 19193/25880 [3:55:04<1:23:28,  1.34it/s]
1|19194|Loss: 0.7354385852813721:  74%|███████▍  | 19194/25880 [3:55:04<1:23:32,  1.33it/s]
1|19195|Loss: 0.8697859048843384:  74%|███████▍  | 19194/25880 [3:55:05<1:23:32,  1.33it/s]
1|19195|Loss: 0.8697859048843384:  74%|███████▍  | 19195/25880 [3:55:05<1:22:14,  1.35it/s]
1|19196|Loss: 0.7901736497879028:  74%|███████▍  | 19195/25880 [3:55:06<1:22:14,  1.35it/s]
1|19196|Loss: 0.7901736497879028:  74%|███████▍  | 19196/25880 [3:55:06<1:21:51,  1.36it/s]
1|19197|Loss: 0.8576911687850952:  74%|███████▍  | 19196/25880 [3:55:06<1:21:51,  1.36it/s]
1|19197|Loss: 0.8576911687850952:  74%|███████▍  | 19197/25880 [3:55:06<1:16:17,  1.46it/s]
1|19198|Loss: 0.9373440146446228:  74%|███████▍  | 19197/25880 [3:55:07<1:16:17,  1.46it/s]
1|19198|Loss: 0.9373440146446228:  74%|███████▍  | 19198/25880 [3:55:07<1:16:24,  1.46it/s]
1|19199|Loss: 0.8660330772399902:  74%|███████▍  | 19198/25880 [3:55:08<1:16:24,  1.46it/s]
1|19199|Loss: 0.8660330772399902:  74%|███████▍  | 19199/25880 [3:55:08<1:15:33,  1.47it/s]
1|19200|Loss: 0.8998020887374878:  74%|███████▍  | 19199/25880 [3:55:08<1:15:33,  1.47it/s]
1|19200|Loss: 0.8998020887374878:  74%|███████▍  | 19200/25880 [3:55:08<1:13:44,  1.51it/s]
1|19201|Loss: 0.823455810546875:  74%|███████▍  | 19200/25880 [3:55:09<1:13:44,  1.51it/s] 
1|19201|Loss: 0.823455810546875:  74%|███████▍  | 19201/25880 [3:55:09<1:22:10,  1.35it/s]
1|19202|Loss: 0.8198678493499756:  74%|███████▍  | 19201/25880 [3:55:10<1:22:10,  1.35it/s]
1|19202|Loss: 0.8198678493499756:  74%|███████▍  | 19202/25880 [3:55:10<1:20:22,  1.38it/s]
1|19203|Loss: 1.0119630098342896:  74%|███████▍  | 19202/25880 [3:55:10<1:20:22,  1.38it/s]
1|19203|Loss: 1.0119630098342896:  74%|███████▍  | 19203/25880 [3:55:11<1:22:37,  1.35it/s]
1|19204|Loss: 0.8831933736801147:  74%|███████▍  | 19203/25880 [3:55:11<1:22:37,  1.35it/s]
1|19204|Loss: 0.8831933736801147:  74%|███████▍  | 19204/25880 [3:55:11<1:19:23,  1.40it/s]
1|19205|Loss: 0.8883928060531616:  74%|███████▍  | 19204/25880 [3:55:12<1:19:23,  1.40it/s]
1|19205|Loss: 0.8883928060531616:  74%|███████▍  | 19205/25880 [3:55:12<1:20:49,  1.38it/s]
1|19206|Loss: 0.8171180486679077:  74%|███████▍  | 19205/25880 [3:55:13<1:20:49,  1.38it/s]
1|19206|Loss: 0.8171180486679077:  74%|███████▍  | 19206/25880 [3:55:13<1:25:30,  1.30it/s]
1|19207|Loss: 0.8380831480026245:  74%|███████▍  | 19206/25880 [3:55:14<1:25:30,  1.30it/s]
1|19207|Loss: 0.8380831480026245:  74%|███████▍  | 19207/25880 [3:55:14<1:25:36,  1.30it/s]
1|19208|Loss: 1.0372394323349:  74%|███████▍  | 19207/25880 [3:55:14<1:25:36,  1.30it/s]   
1|19208|Loss: 1.0372394323349:  74%|███████▍  | 19208/25880 [3:55:15<1:24:50,  1.31it/s]
1|19209|Loss: 0.7240128517150879:  74%|███████▍  | 19208/25880 [3:55:15<1:24:50,  1.31it/s]
1|19209|Loss: 0.7240128517150879:  74%|███████▍  | 19209/25880 [3:55:15<1:21:28,  1.36it/s]
1|19210|Loss: 0.8306058049201965:  74%|███████▍  | 19209/25880 [3:55:16<1:21:28,  1.36it/s]
1|19210|Loss: 0.8306058049201965:  74%|███████▍  | 19210/25880 [3:55:16<1:20:50,  1.38it/s]
1|19211|Loss: 0.8569639325141907:  74%|███████▍  | 19210/25880 [3:55:16<1:20:50,  1.38it/s]
1|19211|Loss: 0.8569639325141907:  74%|███████▍  | 19211/25880 [3:55:17<1:20:15,  1.38it/s]
1|19212|Loss: 0.7534006834030151:  74%|███████▍  | 19211/25880 [3:55:17<1:20:15,  1.38it/s]
1|19212|Loss: 0.7534006834030151:  74%|███████▍  | 19212/25880 [3:55:18<1:23:57,  1.32it/s]
1|19213|Loss: 0.8914798498153687:  74%|███████▍  | 19212/25880 [3:55:18<1:23:57,  1.32it/s]
1|19213|Loss: 0.8914798498153687:  74%|███████▍  | 19213/25880 [3:55:18<1:23:59,  1.32it/s]
1|19214|Loss: 0.8915414214134216:  74%|███████▍  | 19213/25880 [3:55:19<1:23:59,  1.32it/s]
1|19214|Loss: 0.8915414214134216:  74%|███████▍  | 19214/25880 [3:55:19<1:20:25,  1.38it/s]
1|19215|Loss: 0.8191519379615784:  74%|███████▍  | 19214/25880 [3:55:19<1:20:25,  1.38it/s]
1|19215|Loss: 0.8191519379615784:  74%|███████▍  | 19215/25880 [3:55:19<1:14:13,  1.50it/s]
1|19216|Loss: 0.7405194044113159:  74%|███████▍  | 19215/25880 [3:55:20<1:14:13,  1.50it/s]
1|19216|Loss: 0.7405194044113159:  74%|███████▍  | 19216/25880 [3:55:20<1:14:53,  1.48it/s]
1|19217|Loss: 1.0073206424713135:  74%|███████▍  | 19216/25880 [3:55:21<1:14:53,  1.48it/s]
1|19217|Loss: 1.0073206424713135:  74%|███████▍  | 19217/25880 [3:55:21<1:16:39,  1.45it/s]
1|19218|Loss: 0.8440544605255127:  74%|███████▍  | 19217/25880 [3:55:21<1:16:39,  1.45it/s]
1|19218|Loss: 0.8440544605255127:  74%|███████▍  | 19218/25880 [3:55:22<1:17:16,  1.44it/s]
1|19219|Loss: 0.8118448853492737:  74%|███████▍  | 19218/25880 [3:55:22<1:17:16,  1.44it/s]
1|19219|Loss: 0.8118448853492737:  74%|███████▍  | 19219/25880 [3:55:22<1:21:28,  1.36it/s]
1|19220|Loss: 0.9044060111045837:  74%|███████▍  | 19219/25880 [3:55:23<1:21:28,  1.36it/s]
1|19220|Loss: 0.9044060111045837:  74%|███████▍  | 19220/25880 [3:55:23<1:25:03,  1.30it/s]
1|19221|Loss: 0.8142697811126709:  74%|███████▍  | 19220/25880 [3:55:24<1:25:03,  1.30it/s]
1|19221|Loss: 0.8142697811126709:  74%|███████▍  | 19221/25880 [3:55:24<1:23:50,  1.32it/s]
1|19222|Loss: 0.7387449145317078:  74%|███████▍  | 19221/25880 [3:55:24<1:23:50,  1.32it/s]
1|19222|Loss: 0.7387449145317078:  74%|███████▍  | 19222/25880 [3:55:25<1:25:57,  1.29it/s]
1|19223|Loss: 0.8385239839553833:  74%|███████▍  | 19222/25880 [3:55:25<1:25:57,  1.29it/s]
1|19223|Loss: 0.8385239839553833:  74%|███████▍  | 19223/25880 [3:55:26<1:25:53,  1.29it/s]
1|19224|Loss: 0.9301015138626099:  74%|███████▍  | 19223/25880 [3:55:26<1:25:53,  1.29it/s]
1|19224|Loss: 0.9301015138626099:  74%|███████▍  | 19224/25880 [3:55:26<1:21:06,  1.37it/s]
1|19225|Loss: 0.8754592537879944:  74%|███████▍  | 19224/25880 [3:55:27<1:21:06,  1.37it/s]
1|19225|Loss: 0.8754592537879944:  74%|███████▍  | 19225/25880 [3:55:27<1:19:00,  1.40it/s]
1|19226|Loss: 0.7309504747390747:  74%|███████▍  | 19225/25880 [3:55:27<1:19:00,  1.40it/s]
1|19226|Loss: 0.7309504747390747:  74%|███████▍  | 19226/25880 [3:55:28<1:19:34,  1.39it/s]
1|19227|Loss: 0.7208365201950073:  74%|███████▍  | 19226/25880 [3:55:28<1:19:34,  1.39it/s]
1|19227|Loss: 0.7208365201950073:  74%|███████▍  | 19227/25880 [3:55:28<1:20:35,  1.38it/s]
1|19228|Loss: 0.7679858207702637:  74%|███████▍  | 19227/25880 [3:55:29<1:20:35,  1.38it/s]
1|19228|Loss: 0.7679858207702637:  74%|███████▍  | 19228/25880 [3:55:29<1:24:27,  1.31it/s]
1|19229|Loss: 0.8930463790893555:  74%|███████▍  | 19228/25880 [3:55:30<1:24:27,  1.31it/s]
1|19229|Loss: 0.8930463790893555:  74%|███████▍  | 19229/25880 [3:55:30<1:23:41,  1.32it/s]
1|19230|Loss: 0.9012969136238098:  74%|███████▍  | 19229/25880 [3:55:30<1:23:41,  1.32it/s]
1|19230|Loss: 0.9012969136238098:  74%|███████▍  | 19230/25880 [3:55:31<1:19:31,  1.39it/s]
1|19231|Loss: 0.8553577661514282:  74%|███████▍  | 19230/25880 [3:55:31<1:19:31,  1.39it/s]
1|19231|Loss: 0.8553577661514282:  74%|███████▍  | 19231/25880 [3:55:31<1:19:13,  1.40it/s]
1|19232|Loss: 0.860021710395813:  74%|███████▍  | 19231/25880 [3:55:32<1:19:13,  1.40it/s] 
1|19232|Loss: 0.860021710395813:  74%|███████▍  | 19232/25880 [3:55:32<1:18:51,  1.40it/s]
1|19233|Loss: 0.8364061713218689:  74%|███████▍  | 19232/25880 [3:55:32<1:18:51,  1.40it/s]
1|19233|Loss: 0.8364061713218689:  74%|███████▍  | 19233/25880 [3:55:33<1:18:43,  1.41it/s]
1|19234|Loss: 0.8209514021873474:  74%|███████▍  | 19233/25880 [3:55:33<1:18:43,  1.41it/s]
1|19234|Loss: 0.8209514021873474:  74%|███████▍  | 19234/25880 [3:55:33<1:18:24,  1.41it/s]
1|19235|Loss: 0.8069707751274109:  74%|███████▍  | 19234/25880 [3:55:34<1:18:24,  1.41it/s]
1|19235|Loss: 0.8069707751274109:  74%|███████▍  | 19235/25880 [3:55:34<1:12:28,  1.53it/s]
1|19236|Loss: 0.7587327361106873:  74%|███████▍  | 19235/25880 [3:55:34<1:12:28,  1.53it/s]
1|19236|Loss: 0.7587327361106873:  74%|███████▍  | 19236/25880 [3:55:34<1:07:35,  1.64it/s]
1|19237|Loss: 0.7754669785499573:  74%|███████▍  | 19236/25880 [3:55:35<1:07:35,  1.64it/s]
1|19237|Loss: 0.7754669785499573:  74%|███████▍  | 19237/25880 [3:55:35<1:07:01,  1.65it/s]
1|19238|Loss: 0.8624122738838196:  74%|███████▍  | 19237/25880 [3:55:35<1:07:01,  1.65it/s]
1|19238|Loss: 0.8624122738838196:  74%|███████▍  | 19238/25880 [3:55:36<1:05:10,  1.70it/s]
1|19239|Loss: 0.8246118426322937:  74%|███████▍  | 19238/25880 [3:55:36<1:05:10,  1.70it/s]
1|19239|Loss: 0.8246118426322937:  74%|███████▍  | 19239/25880 [3:55:36<1:11:14,  1.55it/s]
1|19240|Loss: 0.7955353856086731:  74%|███████▍  | 19239/25880 [3:55:37<1:11:14,  1.55it/s]
1|19240|Loss: 0.7955353856086731:  74%|███████▍  | 19240/25880 [3:55:37<1:12:17,  1.53it/s]
1|19241|Loss: 0.7534496188163757:  74%|███████▍  | 19240/25880 [3:55:37<1:12:17,  1.53it/s]
1|19241|Loss: 0.7534496188163757:  74%|███████▍  | 19241/25880 [3:55:38<1:17:30,  1.43it/s]
1|19242|Loss: 0.772382378578186:  74%|███████▍  | 19241/25880 [3:55:38<1:17:30,  1.43it/s] 
1|19242|Loss: 0.772382378578186:  74%|███████▍  | 19242/25880 [3:55:39<1:17:06,  1.43it/s]
1|19243|Loss: 0.8304707407951355:  74%|███████▍  | 19242/25880 [3:55:39<1:17:06,  1.43it/s]
1|19243|Loss: 0.8304707407951355:  74%|███████▍  | 19243/25880 [3:55:39<1:15:16,  1.47it/s]
1|19244|Loss: 0.8486843109130859:  74%|███████▍  | 19243/25880 [3:55:40<1:15:16,  1.47it/s]
1|19244|Loss: 0.8486843109130859:  74%|███████▍  | 19244/25880 [3:55:40<1:19:02,  1.40it/s]
1|19245|Loss: 0.9038336873054504:  74%|███████▍  | 19244/25880 [3:55:40<1:19:02,  1.40it/s]
1|19245|Loss: 0.9038336873054504:  74%|███████▍  | 19245/25880 [3:55:41<1:17:46,  1.42it/s]
1|19246|Loss: 0.7734915614128113:  74%|███████▍  | 19245/25880 [3:55:41<1:17:46,  1.42it/s]
1|19246|Loss: 0.7734915614128113:  74%|███████▍  | 19246/25880 [3:55:41<1:17:32,  1.43it/s]
1|19247|Loss: 0.8179984092712402:  74%|███████▍  | 19246/25880 [3:55:42<1:17:32,  1.43it/s]
1|19247|Loss: 0.8179984092712402:  74%|███████▍  | 19247/25880 [3:55:42<1:12:56,  1.52it/s]
1|19248|Loss: 0.9059973359107971:  74%|███████▍  | 19247/25880 [3:55:42<1:12:56,  1.52it/s]
1|19248|Loss: 0.9059973359107971:  74%|███████▍  | 19248/25880 [3:55:43<1:13:04,  1.51it/s]
1|19249|Loss: 0.7698304653167725:  74%|███████▍  | 19248/25880 [3:55:43<1:13:04,  1.51it/s]
1|19249|Loss: 0.7698304653167725:  74%|███████▍  | 19249/25880 [3:55:43<1:12:46,  1.52it/s]
1|19250|Loss: 0.7696791887283325:  74%|███████▍  | 19249/25880 [3:55:44<1:12:46,  1.52it/s]
1|19250|Loss: 0.7696791887283325:  74%|███████▍  | 19250/25880 [3:55:44<1:12:12,  1.53it/s]
1|19251|Loss: 0.7848189473152161:  74%|███████▍  | 19250/25880 [3:55:44<1:12:12,  1.53it/s]
1|19251|Loss: 0.7848189473152161:  74%|███████▍  | 19251/25880 [3:55:44<1:11:41,  1.54it/s]
1|19252|Loss: 0.745417594909668:  74%|███████▍  | 19251/25880 [3:55:45<1:11:41,  1.54it/s] 
1|19252|Loss: 0.745417594909668:  74%|███████▍  | 19252/25880 [3:55:45<1:14:16,  1.49it/s]
1|19253|Loss: 0.7783816456794739:  74%|███████▍  | 19252/25880 [3:55:46<1:14:16,  1.49it/s]
1|19253|Loss: 0.7783816456794739:  74%|███████▍  | 19253/25880 [3:55:46<1:10:58,  1.56it/s]
1|19254|Loss: 0.8339555263519287:  74%|███████▍  | 19253/25880 [3:55:46<1:10:58,  1.56it/s]
1|19254|Loss: 0.8339555263519287:  74%|███████▍  | 19254/25880 [3:55:46<1:11:41,  1.54it/s]
1|19255|Loss: 0.9110146760940552:  74%|███████▍  | 19254/25880 [3:55:47<1:11:41,  1.54it/s]
1|19255|Loss: 0.9110146760940552:  74%|███████▍  | 19255/25880 [3:55:47<1:14:07,  1.49it/s]
1|19256|Loss: 0.9104256629943848:  74%|███████▍  | 19255/25880 [3:55:48<1:14:07,  1.49it/s]
1|19256|Loss: 0.9104256629943848:  74%|███████▍  | 19256/25880 [3:55:48<1:15:17,  1.47it/s]
1|19257|Loss: 0.7269448041915894:  74%|███████▍  | 19256/25880 [3:55:48<1:15:17,  1.47it/s]
1|19257|Loss: 0.7269448041915894:  74%|███████▍  | 19257/25880 [3:55:49<1:17:09,  1.43it/s]
1|19258|Loss: 0.8981642127037048:  74%|███████▍  | 19257/25880 [3:55:49<1:17:09,  1.43it/s]
1|19258|Loss: 0.8981642127037048:  74%|███████▍  | 19258/25880 [3:55:49<1:21:27,  1.35it/s]
1|19259|Loss: 0.7609024047851562:  74%|███████▍  | 19258/25880 [3:55:50<1:21:27,  1.35it/s]
1|19259|Loss: 0.7609024047851562:  74%|███████▍  | 19259/25880 [3:55:50<1:25:24,  1.29it/s]
1|19260|Loss: 0.8612363338470459:  74%|███████▍  | 19259/25880 [3:55:51<1:25:24,  1.29it/s]
1|19260|Loss: 0.8612363338470459:  74%|███████▍  | 19260/25880 [3:55:51<1:24:18,  1.31it/s]
1|19261|Loss: 0.8191447854042053:  74%|███████▍  | 19260/25880 [3:55:51<1:24:18,  1.31it/s]
1|19261|Loss: 0.8191447854042053:  74%|███████▍  | 19261/25880 [3:55:52<1:26:14,  1.28it/s]
1|19262|Loss: 0.9536022543907166:  74%|███████▍  | 19261/25880 [3:55:52<1:26:14,  1.28it/s]
1|19262|Loss: 0.9536022543907166:  74%|███████▍  | 19262/25880 [3:55:53<1:28:09,  1.25it/s]
1|19263|Loss: 0.766217827796936:  74%|███████▍  | 19262/25880 [3:55:53<1:28:09,  1.25it/s] 
1|19263|Loss: 0.766217827796936:  74%|███████▍  | 19263/25880 [3:55:53<1:24:12,  1.31it/s]
1|19264|Loss: 0.8402250409126282:  74%|███████▍  | 19263/25880 [3:55:54<1:24:12,  1.31it/s]
1|19264|Loss: 0.8402250409126282:  74%|███████▍  | 19264/25880 [3:55:54<1:22:40,  1.33it/s]
1|19265|Loss: 0.8005772233009338:  74%|███████▍  | 19264/25880 [3:55:55<1:22:40,  1.33it/s]
1|19265|Loss: 0.8005772233009338:  74%|███████▍  | 19265/25880 [3:55:55<1:26:00,  1.28it/s]
1|19266|Loss: 0.9111132621765137:  74%|███████▍  | 19265/25880 [3:55:55<1:26:00,  1.28it/s]
1|19266|Loss: 0.9111132621765137:  74%|███████▍  | 19266/25880 [3:55:56<1:24:52,  1.30it/s]
1|19267|Loss: 0.7998318672180176:  74%|███████▍  | 19266/25880 [3:55:56<1:24:52,  1.30it/s]
1|19267|Loss: 0.7998318672180176:  74%|███████▍  | 19267/25880 [3:55:56<1:22:29,  1.34it/s]
1|19268|Loss: 0.8758813738822937:  74%|███████▍  | 19267/25880 [3:55:57<1:22:29,  1.34it/s]
1|19268|Loss: 0.8758813738822937:  74%|███████▍  | 19268/25880 [3:55:57<1:18:33,  1.40it/s]
1|19269|Loss: 0.7597609758377075:  74%|███████▍  | 19268/25880 [3:55:57<1:18:33,  1.40it/s]
1|19269|Loss: 0.7597609758377075:  74%|███████▍  | 19269/25880 [3:55:58<1:15:09,  1.47it/s]
1|19270|Loss: 0.8779842257499695:  74%|███████▍  | 19269/25880 [3:55:58<1:15:09,  1.47it/s]
1|19270|Loss: 0.8779842257499695:  74%|███████▍  | 19270/25880 [3:55:58<1:13:45,  1.49it/s]
1|19271|Loss: 0.9175845384597778:  74%|███████▍  | 19270/25880 [3:55:59<1:13:45,  1.49it/s]
1|19271|Loss: 0.9175845384597778:  74%|███████▍  | 19271/25880 [3:55:59<1:11:33,  1.54it/s]
1|19272|Loss: 0.7449722290039062:  74%|███████▍  | 19271/25880 [3:55:59<1:11:33,  1.54it/s]
1|19272|Loss: 0.7449722290039062:  74%|███████▍  | 19272/25880 [3:56:00<1:14:58,  1.47it/s]
1|19273|Loss: 0.7627072930335999:  74%|███████▍  | 19272/25880 [3:56:00<1:14:58,  1.47it/s]
1|19273|Loss: 0.7627072930335999:  74%|███████▍  | 19273/25880 [3:56:00<1:14:36,  1.48it/s]
1|19274|Loss: 0.7300869226455688:  74%|███████▍  | 19273/25880 [3:56:01<1:14:36,  1.48it/s]
1|19274|Loss: 0.7300869226455688:  74%|███████▍  | 19274/25880 [3:56:01<1:11:45,  1.53it/s]
1|19275|Loss: 0.8277646899223328:  74%|███████▍  | 19274/25880 [3:56:01<1:11:45,  1.53it/s]
1|19275|Loss: 0.8277646899223328:  74%|███████▍  | 19275/25880 [3:56:02<1:12:46,  1.51it/s]
1|19276|Loss: 0.7424660921096802:  74%|███████▍  | 19275/25880 [3:56:02<1:12:46,  1.51it/s]
1|19276|Loss: 0.7424660921096802:  74%|███████▍  | 19276/25880 [3:56:02<1:17:23,  1.42it/s]
1|19277|Loss: 0.8132143616676331:  74%|███████▍  | 19276/25880 [3:56:03<1:17:23,  1.42it/s]
1|19277|Loss: 0.8132143616676331:  74%|███████▍  | 19277/25880 [3:56:03<1:19:17,  1.39it/s]
1|19278|Loss: 0.6841493248939514:  74%|███████▍  | 19277/25880 [3:56:04<1:19:17,  1.39it/s]
1|19278|Loss: 0.6841493248939514:  74%|███████▍  | 19278/25880 [3:56:04<1:29:41,  1.23it/s]
1|19279|Loss: 0.9902502298355103:  74%|███████▍  | 19278/25880 [3:56:05<1:29:41,  1.23it/s]
1|19279|Loss: 0.9902502298355103:  74%|███████▍  | 19279/25880 [3:56:05<1:29:54,  1.22it/s]
1|19280|Loss: 0.9109767079353333:  74%|███████▍  | 19279/25880 [3:56:05<1:29:54,  1.22it/s]
1|19280|Loss: 0.9109767079353333:  74%|███████▍  | 19280/25880 [3:56:06<1:27:35,  1.26it/s]
1|19281|Loss: 0.7463130354881287:  74%|███████▍  | 19280/25880 [3:56:06<1:27:35,  1.26it/s]
1|19281|Loss: 0.7463130354881287:  75%|███████▍  | 19281/25880 [3:56:06<1:24:49,  1.30it/s]
1|19282|Loss: 0.9381968379020691:  75%|███████▍  | 19281/25880 [3:56:07<1:24:49,  1.30it/s]
1|19282|Loss: 0.9381968379020691:  75%|███████▍  | 19282/25880 [3:56:07<1:28:12,  1.25it/s]
1|19283|Loss: 0.7568202614784241:  75%|███████▍  | 19282/25880 [3:56:08<1:28:12,  1.25it/s]
1|19283|Loss: 0.7568202614784241:  75%|███████▍  | 19283/25880 [3:56:08<1:23:01,  1.32it/s]
1|19284|Loss: 0.8505719304084778:  75%|███████▍  | 19283/25880 [3:56:08<1:23:01,  1.32it/s]
1|19284|Loss: 0.8505719304084778:  75%|███████▍  | 19284/25880 [3:56:09<1:18:30,  1.40it/s]
1|19285|Loss: 0.8614595532417297:  75%|███████▍  | 19284/25880 [3:56:09<1:18:30,  1.40it/s]
1|19285|Loss: 0.8614595532417297:  75%|███████▍  | 19285/25880 [3:56:09<1:14:49,  1.47it/s]
1|19286|Loss: 0.8093850612640381:  75%|███████▍  | 19285/25880 [3:56:10<1:14:49,  1.47it/s]
1|19286|Loss: 0.8093850612640381:  75%|███████▍  | 19286/25880 [3:56:10<1:18:08,  1.41it/s]
1|19287|Loss: 0.8731285333633423:  75%|███████▍  | 19286/25880 [3:56:10<1:18:08,  1.41it/s]
1|19287|Loss: 0.8731285333633423:  75%|███████▍  | 19287/25880 [3:56:11<1:16:27,  1.44it/s]
1|19288|Loss: 0.8105452656745911:  75%|███████▍  | 19287/25880 [3:56:11<1:16:27,  1.44it/s]
1|19288|Loss: 0.8105452656745911:  75%|███████▍  | 19288/25880 [3:56:11<1:14:31,  1.47it/s]
1|19289|Loss: 0.9281691908836365:  75%|███████▍  | 19288/25880 [3:56:12<1:14:31,  1.47it/s]
1|19289|Loss: 0.9281691908836365:  75%|███████▍  | 19289/25880 [3:56:12<1:12:38,  1.51it/s]
1|19290|Loss: 0.9021883010864258:  75%|███████▍  | 19289/25880 [3:56:12<1:12:38,  1.51it/s]
1|19290|Loss: 0.9021883010864258:  75%|███████▍  | 19290/25880 [3:56:13<1:14:34,  1.47it/s]
1|19291|Loss: 0.8509886860847473:  75%|███████▍  | 19290/25880 [3:56:13<1:14:34,  1.47it/s]
1|19291|Loss: 0.8509886860847473:  75%|███████▍  | 19291/25880 [3:56:13<1:16:32,  1.43it/s]
1|19292|Loss: 0.7791488766670227:  75%|███████▍  | 19291/25880 [3:56:14<1:16:32,  1.43it/s]
1|19292|Loss: 0.7791488766670227:  75%|███████▍  | 19292/25880 [3:56:14<1:14:36,  1.47it/s]
1|19293|Loss: 0.815680205821991:  75%|███████▍  | 19292/25880 [3:56:14<1:14:36,  1.47it/s] 
1|19293|Loss: 0.815680205821991:  75%|███████▍  | 19293/25880 [3:56:15<1:11:00,  1.55it/s]
1|19294|Loss: 0.8363751769065857:  75%|███████▍  | 19293/25880 [3:56:15<1:11:00,  1.55it/s]
1|19294|Loss: 0.8363751769065857:  75%|███████▍  | 19294/25880 [3:56:15<1:12:45,  1.51it/s]
1|19295|Loss: 0.7547082304954529:  75%|███████▍  | 19294/25880 [3:56:16<1:12:45,  1.51it/s]
1|19295|Loss: 0.7547082304954529:  75%|███████▍  | 19295/25880 [3:56:16<1:12:03,  1.52it/s]
1|19296|Loss: 0.8190432190895081:  75%|███████▍  | 19295/25880 [3:56:16<1:12:03,  1.52it/s]
1|19296|Loss: 0.8190432190895081:  75%|███████▍  | 19296/25880 [3:56:17<1:16:19,  1.44it/s]
1|19297|Loss: 0.8558499813079834:  75%|███████▍  | 19296/25880 [3:56:17<1:16:19,  1.44it/s]
1|19297|Loss: 0.8558499813079834:  75%|███████▍  | 19297/25880 [3:56:18<1:20:38,  1.36it/s]
1|19298|Loss: 0.8277698159217834:  75%|███████▍  | 19297/25880 [3:56:18<1:20:38,  1.36it/s]
1|19298|Loss: 0.8277698159217834:  75%|███████▍  | 19298/25880 [3:56:18<1:20:18,  1.37it/s]
1|19299|Loss: 0.8237779140472412:  75%|███████▍  | 19298/25880 [3:56:19<1:20:18,  1.37it/s]
1|19299|Loss: 0.8237779140472412:  75%|███████▍  | 19299/25880 [3:56:19<1:22:59,  1.32it/s]
1|19300|Loss: 0.8780336976051331:  75%|███████▍  | 19299/25880 [3:56:19<1:22:59,  1.32it/s]
1|19300|Loss: 0.8780336976051331:  75%|███████▍  | 19300/25880 [3:56:20<1:22:15,  1.33it/s]
1|19301|Loss: 0.7708739638328552:  75%|███████▍  | 19300/25880 [3:56:20<1:22:15,  1.33it/s]
1|19301|Loss: 0.7708739638328552:  75%|███████▍  | 19301/25880 [3:56:21<1:21:22,  1.35it/s]
1|19302|Loss: 0.738776445388794:  75%|███████▍  | 19301/25880 [3:56:21<1:21:22,  1.35it/s] 
1|19302|Loss: 0.738776445388794:  75%|███████▍  | 19302/25880 [3:56:21<1:24:04,  1.30it/s]
1|19303|Loss: 0.8119398355484009:  75%|███████▍  | 19302/25880 [3:56:22<1:24:04,  1.30it/s]
1|19303|Loss: 0.8119398355484009:  75%|███████▍  | 19303/25880 [3:56:22<1:19:17,  1.38it/s]
1|19304|Loss: 0.8449336886405945:  75%|███████▍  | 19303/25880 [3:56:22<1:19:17,  1.38it/s]
1|19304|Loss: 0.8449336886405945:  75%|███████▍  | 19304/25880 [3:56:23<1:18:17,  1.40it/s]
1|19305|Loss: 1.000935673713684:  75%|███████▍  | 19304/25880 [3:56:23<1:18:17,  1.40it/s] 
1|19305|Loss: 1.000935673713684:  75%|███████▍  | 19305/25880 [3:56:23<1:14:55,  1.46it/s]
1|19306|Loss: 0.8730568885803223:  75%|███████▍  | 19305/25880 [3:56:24<1:14:55,  1.46it/s]
1|19306|Loss: 0.8730568885803223:  75%|███████▍  | 19306/25880 [3:56:24<1:18:33,  1.39it/s]
1|19307|Loss: 0.9853803515434265:  75%|███████▍  | 19306/25880 [3:56:24<1:18:33,  1.39it/s]
1|19307|Loss: 0.9853803515434265:  75%|███████▍  | 19307/25880 [3:56:25<1:16:03,  1.44it/s]
1|19308|Loss: 0.8272678256034851:  75%|███████▍  | 19307/25880 [3:56:25<1:16:03,  1.44it/s]
1|19308|Loss: 0.8272678256034851:  75%|███████▍  | 19308/25880 [3:56:25<1:16:36,  1.43it/s]
1|19309|Loss: 0.9029480218887329:  75%|███████▍  | 19308/25880 [3:56:26<1:16:36,  1.43it/s]
1|19309|Loss: 0.9029480218887329:  75%|███████▍  | 19309/25880 [3:56:26<1:14:54,  1.46it/s]
1|19310|Loss: 0.796629786491394:  75%|███████▍  | 19309/25880 [3:56:26<1:14:54,  1.46it/s] 
1|19310|Loss: 0.796629786491394:  75%|███████▍  | 19310/25880 [3:56:27<1:18:54,  1.39it/s]
1|19311|Loss: 0.7452040910720825:  75%|███████▍  | 19310/25880 [3:56:27<1:18:54,  1.39it/s]
1|19311|Loss: 0.7452040910720825:  75%|███████▍  | 19311/25880 [3:56:28<1:23:27,  1.31it/s]
1|19312|Loss: 0.864585816860199:  75%|███████▍  | 19311/25880 [3:56:28<1:23:27,  1.31it/s] 
1|19312|Loss: 0.864585816860199:  75%|███████▍  | 19312/25880 [3:56:28<1:20:14,  1.36it/s]
1|19313|Loss: 0.8643059134483337:  75%|███████▍  | 19312/25880 [3:56:29<1:20:14,  1.36it/s]
1|19313|Loss: 0.8643059134483337:  75%|███████▍  | 19313/25880 [3:56:29<1:18:39,  1.39it/s]
1|19314|Loss: 0.9374862909317017:  75%|███████▍  | 19313/25880 [3:56:30<1:18:39,  1.39it/s]
1|19314|Loss: 0.9374862909317017:  75%|███████▍  | 19314/25880 [3:56:30<1:22:27,  1.33it/s]
1|19315|Loss: 0.9097314476966858:  75%|███████▍  | 19314/25880 [3:56:30<1:22:27,  1.33it/s]
1|19315|Loss: 0.9097314476966858:  75%|███████▍  | 19315/25880 [3:56:31<1:23:14,  1.31it/s]
1|19316|Loss: 0.8451699614524841:  75%|███████▍  | 19315/25880 [3:56:31<1:23:14,  1.31it/s]
1|19316|Loss: 0.8451699614524841:  75%|███████▍  | 19316/25880 [3:56:31<1:15:24,  1.45it/s]
1|19317|Loss: 0.9173386096954346:  75%|███████▍  | 19316/25880 [3:56:32<1:15:24,  1.45it/s]
1|19317|Loss: 0.9173386096954346:  75%|███████▍  | 19317/25880 [3:56:32<1:17:19,  1.41it/s]
1|19318|Loss: 0.8628315329551697:  75%|███████▍  | 19317/25880 [3:56:32<1:17:19,  1.41it/s]
1|19318|Loss: 0.8628315329551697:  75%|███████▍  | 19318/25880 [3:56:33<1:18:48,  1.39it/s]
1|19319|Loss: 0.8727080821990967:  75%|███████▍  | 19318/25880 [3:56:33<1:18:48,  1.39it/s]
1|19319|Loss: 0.8727080821990967:  75%|███████▍  | 19319/25880 [3:56:33<1:19:33,  1.37it/s]
1|19320|Loss: 0.7342334389686584:  75%|███████▍  | 19319/25880 [3:56:34<1:19:33,  1.37it/s]
1|19320|Loss: 0.7342334389686584:  75%|███████▍  | 19320/25880 [3:56:34<1:22:48,  1.32it/s]
1|19321|Loss: 0.8230074644088745:  75%|███████▍  | 19320/25880 [3:56:35<1:22:48,  1.32it/s]
1|19321|Loss: 0.8230074644088745:  75%|███████▍  | 19321/25880 [3:56:35<1:15:29,  1.45it/s]
1|19322|Loss: 0.8190418481826782:  75%|███████▍  | 19321/25880 [3:56:35<1:15:29,  1.45it/s]
1|19322|Loss: 0.8190418481826782:  75%|███████▍  | 19322/25880 [3:56:36<1:16:13,  1.43it/s]
1|19323|Loss: 0.8702912330627441:  75%|███████▍  | 19322/25880 [3:56:36<1:16:13,  1.43it/s]
1|19323|Loss: 0.8702912330627441:  75%|███████▍  | 19323/25880 [3:56:36<1:21:28,  1.34it/s]
1|19324|Loss: 0.8056722283363342:  75%|███████▍  | 19323/25880 [3:56:37<1:21:28,  1.34it/s]
1|19324|Loss: 0.8056722283363342:  75%|███████▍  | 19324/25880 [3:56:37<1:22:29,  1.32it/s]
1|19325|Loss: 0.836364209651947:  75%|███████▍  | 19324/25880 [3:56:38<1:22:29,  1.32it/s] 
1|19325|Loss: 0.836364209651947:  75%|███████▍  | 19325/25880 [3:56:38<1:19:01,  1.38it/s]
1|19326|Loss: 0.9824581742286682:  75%|███████▍  | 19325/25880 [3:56:38<1:19:01,  1.38it/s]
1|19326|Loss: 0.9824581742286682:  75%|███████▍  | 19326/25880 [3:56:39<1:22:07,  1.33it/s]
1|19327|Loss: 0.8004373908042908:  75%|███████▍  | 19326/25880 [3:56:39<1:22:07,  1.33it/s]
1|19327|Loss: 0.8004373908042908:  75%|███████▍  | 19327/25880 [3:56:39<1:16:40,  1.42it/s]
1|19328|Loss: 0.8831624388694763:  75%|███████▍  | 19327/25880 [3:56:40<1:16:40,  1.42it/s]
1|19328|Loss: 0.8831624388694763:  75%|███████▍  | 19328/25880 [3:56:40<1:15:58,  1.44it/s]
1|19329|Loss: 0.760907769203186:  75%|███████▍  | 19328/25880 [3:56:40<1:15:58,  1.44it/s] 
1|19329|Loss: 0.760907769203186:  75%|███████▍  | 19329/25880 [3:56:41<1:16:18,  1.43it/s]
1|19330|Loss: 0.8083482980728149:  75%|███████▍  | 19329/25880 [3:56:41<1:16:18,  1.43it/s]
1|19330|Loss: 0.8083482980728149:  75%|███████▍  | 19330/25880 [3:56:41<1:17:08,  1.42it/s]
1|19331|Loss: 0.7560907602310181:  75%|███████▍  | 19330/25880 [3:56:42<1:17:08,  1.42it/s]
1|19331|Loss: 0.7560907602310181:  75%|███████▍  | 19331/25880 [3:56:42<1:21:30,  1.34it/s]
1|19332|Loss: 0.8030105233192444:  75%|███████▍  | 19331/25880 [3:56:43<1:21:30,  1.34it/s]
1|19332|Loss: 0.8030105233192444:  75%|███████▍  | 19332/25880 [3:56:43<1:22:07,  1.33it/s]
1|19333|Loss: 0.705147922039032:  75%|███████▍  | 19332/25880 [3:56:43<1:22:07,  1.33it/s] 
1|19333|Loss: 0.705147922039032:  75%|███████▍  | 19333/25880 [3:56:44<1:20:34,  1.35it/s]
1|19334|Loss: 0.8986717462539673:  75%|███████▍  | 19333/25880 [3:56:44<1:20:34,  1.35it/s]
1|19334|Loss: 0.8986717462539673:  75%|███████▍  | 19334/25880 [3:56:44<1:17:53,  1.40it/s]
1|19335|Loss: 0.771174967288971:  75%|███████▍  | 19334/25880 [3:56:45<1:17:53,  1.40it/s] 
1|19335|Loss: 0.771174967288971:  75%|███████▍  | 19335/25880 [3:56:45<1:21:09,  1.34it/s]
1|19336|Loss: 0.7171496152877808:  75%|███████▍  | 19335/25880 [3:56:46<1:21:09,  1.34it/s]
1|19336|Loss: 0.7171496152877808:  75%|███████▍  | 19336/25880 [3:56:46<1:19:19,  1.37it/s]
1|19337|Loss: 0.8632517457008362:  75%|███████▍  | 19336/25880 [3:56:46<1:19:19,  1.37it/s]
1|19337|Loss: 0.8632517457008362:  75%|███████▍  | 19337/25880 [3:56:47<1:18:07,  1.40it/s]
1|19338|Loss: 0.8459529876708984:  75%|███████▍  | 19337/25880 [3:56:47<1:18:07,  1.40it/s]
1|19338|Loss: 0.8459529876708984:  75%|███████▍  | 19338/25880 [3:56:47<1:20:21,  1.36it/s]
1|19339|Loss: 0.8557268381118774:  75%|███████▍  | 19338/25880 [3:56:48<1:20:21,  1.36it/s]
1|19339|Loss: 0.8557268381118774:  75%|███████▍  | 19339/25880 [3:56:48<1:20:31,  1.35it/s]
1|19340|Loss: 0.8129433393478394:  75%|███████▍  | 19339/25880 [3:56:48<1:20:31,  1.35it/s]
1|19340|Loss: 0.8129433393478394:  75%|███████▍  | 19340/25880 [3:56:49<1:20:19,  1.36it/s]
1|19341|Loss: 0.8357834815979004:  75%|███████▍  | 19340/25880 [3:56:49<1:20:19,  1.36it/s]
1|19341|Loss: 0.8357834815979004:  75%|███████▍  | 19341/25880 [3:56:49<1:13:37,  1.48it/s]
1|19342|Loss: 0.9595484137535095:  75%|███████▍  | 19341/25880 [3:56:50<1:13:37,  1.48it/s]
1|19342|Loss: 0.9595484137535095:  75%|███████▍  | 19342/25880 [3:56:50<1:16:24,  1.43it/s]
1|19343|Loss: 0.7354595065116882:  75%|███████▍  | 19342/25880 [3:56:50<1:16:24,  1.43it/s]
1|19343|Loss: 0.7354595065116882:  75%|███████▍  | 19343/25880 [3:56:51<1:13:24,  1.48it/s]
1|19344|Loss: 0.8170075416564941:  75%|███████▍  | 19343/25880 [3:56:51<1:13:24,  1.48it/s]
1|19344|Loss: 0.8170075416564941:  75%|███████▍  | 19344/25880 [3:56:51<1:13:26,  1.48it/s]
1|19345|Loss: 0.7559798955917358:  75%|███████▍  | 19344/25880 [3:56:52<1:13:26,  1.48it/s]
1|19345|Loss: 0.7559798955917358:  75%|███████▍  | 19345/25880 [3:56:52<1:14:09,  1.47it/s]
1|19346|Loss: 0.7790045142173767:  75%|███████▍  | 19345/25880 [3:56:52<1:14:09,  1.47it/s]
1|19346|Loss: 0.7790045142173767:  75%|███████▍  | 19346/25880 [3:56:53<1:10:51,  1.54it/s]
1|19347|Loss: 0.8484798073768616:  75%|███████▍  | 19346/25880 [3:56:53<1:10:51,  1.54it/s]
1|19347|Loss: 0.8484798073768616:  75%|███████▍  | 19347/25880 [3:56:53<1:12:45,  1.50it/s]
1|19348|Loss: 0.75234055519104:  75%|███████▍  | 19347/25880 [3:56:54<1:12:45,  1.50it/s]  
1|19348|Loss: 0.75234055519104:  75%|███████▍  | 19348/25880 [3:56:54<1:18:24,  1.39it/s]
1|19349|Loss: 0.8185762166976929:  75%|███████▍  | 19348/25880 [3:56:55<1:18:24,  1.39it/s]
1|19349|Loss: 0.8185762166976929:  75%|███████▍  | 19349/25880 [3:56:55<1:23:30,  1.30it/s]
1|19350|Loss: 0.8035028576850891:  75%|███████▍  | 19349/25880 [3:56:56<1:23:30,  1.30it/s]
1|19350|Loss: 0.8035028576850891:  75%|███████▍  | 19350/25880 [3:56:56<1:25:11,  1.28it/s]
1|19351|Loss: 0.8616428375244141:  75%|███████▍  | 19350/25880 [3:56:56<1:25:11,  1.28it/s]
1|19351|Loss: 0.8616428375244141:  75%|███████▍  | 19351/25880 [3:56:57<1:21:30,  1.33it/s]
1|19352|Loss: 0.7777513265609741:  75%|███████▍  | 19351/25880 [3:56:57<1:21:30,  1.33it/s]
1|19352|Loss: 0.7777513265609741:  75%|███████▍  | 19352/25880 [3:56:57<1:22:55,  1.31it/s]
1|19353|Loss: 0.8933721780776978:  75%|███████▍  | 19352/25880 [3:56:58<1:22:55,  1.31it/s]
1|19353|Loss: 0.8933721780776978:  75%|███████▍  | 19353/25880 [3:56:58<1:27:21,  1.25it/s]
1|19354|Loss: 0.806248664855957:  75%|███████▍  | 19353/25880 [3:56:59<1:27:21,  1.25it/s] 
1|19354|Loss: 0.806248664855957:  75%|███████▍  | 19354/25880 [3:56:59<1:25:32,  1.27it/s]
1|19355|Loss: 0.9081263542175293:  75%|███████▍  | 19354/25880 [3:56:59<1:25:32,  1.27it/s]
1|19355|Loss: 0.9081263542175293:  75%|███████▍  | 19355/25880 [3:57:00<1:21:13,  1.34it/s]
1|19356|Loss: 0.9282013773918152:  75%|███████▍  | 19355/25880 [3:57:00<1:21:13,  1.34it/s]
1|19356|Loss: 0.9282013773918152:  75%|███████▍  | 19356/25880 [3:57:00<1:21:59,  1.33it/s]
1|19357|Loss: 0.7364927530288696:  75%|███████▍  | 19356/25880 [3:57:01<1:21:59,  1.33it/s]
1|19357|Loss: 0.7364927530288696:  75%|███████▍  | 19357/25880 [3:57:01<1:26:43,  1.25it/s]
1|19358|Loss: 0.8571109771728516:  75%|███████▍  | 19357/25880 [3:57:02<1:26:43,  1.25it/s]
1|19358|Loss: 0.8571109771728516:  75%|███████▍  | 19358/25880 [3:57:02<1:29:41,  1.21it/s]
1|19359|Loss: 0.8656768202781677:  75%|███████▍  | 19358/25880 [3:57:03<1:29:41,  1.21it/s]
1|19359|Loss: 0.8656768202781677:  75%|███████▍  | 19359/25880 [3:57:03<1:27:01,  1.25it/s]
1|19360|Loss: 0.8001884818077087:  75%|███████▍  | 19359/25880 [3:57:03<1:27:01,  1.25it/s]
1|19360|Loss: 0.8001884818077087:  75%|███████▍  | 19360/25880 [3:57:04<1:27:27,  1.24it/s]
1|19361|Loss: 0.7729599475860596:  75%|███████▍  | 19360/25880 [3:57:04<1:27:27,  1.24it/s]
1|19361|Loss: 0.7729599475860596:  75%|███████▍  | 19361/25880 [3:57:04<1:23:42,  1.30it/s]
1|19362|Loss: 0.8702982664108276:  75%|███████▍  | 19361/25880 [3:57:05<1:23:42,  1.30it/s]
1|19362|Loss: 0.8702982664108276:  75%|███████▍  | 19362/25880 [3:57:05<1:16:45,  1.42it/s]
1|19363|Loss: 0.7836138606071472:  75%|███████▍  | 19362/25880 [3:57:05<1:16:45,  1.42it/s]
1|19363|Loss: 0.7836138606071472:  75%|███████▍  | 19363/25880 [3:57:06<1:12:22,  1.50it/s]
1|19364|Loss: 0.7812093496322632:  75%|███████▍  | 19363/25880 [3:57:06<1:12:22,  1.50it/s]
1|19364|Loss: 0.7812093496322632:  75%|███████▍  | 19364/25880 [3:57:06<1:10:24,  1.54it/s]
1|19365|Loss: 0.7408043742179871:  75%|███████▍  | 19364/25880 [3:57:07<1:10:24,  1.54it/s]
1|19365|Loss: 0.7408043742179871:  75%|███████▍  | 19365/25880 [3:57:07<1:17:22,  1.40it/s]
1|19366|Loss: 0.7786014080047607:  75%|███████▍  | 19365/25880 [3:57:08<1:17:22,  1.40it/s]
1|19366|Loss: 0.7786014080047607:  75%|███████▍  | 19366/25880 [3:57:08<1:22:20,  1.32it/s]
1|19367|Loss: 0.852526068687439:  75%|███████▍  | 19366/25880 [3:57:08<1:22:20,  1.32it/s] 
1|19367|Loss: 0.852526068687439:  75%|███████▍  | 19367/25880 [3:57:09<1:22:28,  1.32it/s]
1|19368|Loss: 0.901905357837677:  75%|███████▍  | 19367/25880 [3:57:09<1:22:28,  1.32it/s]
1|19368|Loss: 0.901905357837677:  75%|███████▍  | 19368/25880 [3:57:09<1:12:05,  1.51it/s]
1|19369|Loss: 0.8712077140808105:  75%|███████▍  | 19368/25880 [3:57:09<1:12:05,  1.51it/s]
1|19369|Loss: 0.8712077140808105:  75%|███████▍  | 19369/25880 [3:57:10<1:09:18,  1.57it/s]
1|19370|Loss: 0.7604082822799683:  75%|███████▍  | 19369/25880 [3:57:10<1:09:18,  1.57it/s]
1|19370|Loss: 0.7604082822799683:  75%|███████▍  | 19370/25880 [3:57:10<1:09:11,  1.57it/s]
1|19371|Loss: 0.8862334489822388:  75%|███████▍  | 19370/25880 [3:57:11<1:09:11,  1.57it/s]
1|19371|Loss: 0.8862334489822388:  75%|███████▍  | 19371/25880 [3:57:11<1:13:14,  1.48it/s]
1|19372|Loss: 0.7170714735984802:  75%|███████▍  | 19371/25880 [3:57:11<1:13:14,  1.48it/s]
1|19372|Loss: 0.7170714735984802:  75%|███████▍  | 19372/25880 [3:57:12<1:15:23,  1.44it/s]
1|19373|Loss: 0.7523534893989563:  75%|███████▍  | 19372/25880 [3:57:12<1:15:23,  1.44it/s]
1|19373|Loss: 0.7523534893989563:  75%|███████▍  | 19373/25880 [3:57:12<1:12:36,  1.49it/s]
1|19374|Loss: 0.849210262298584:  75%|███████▍  | 19373/25880 [3:57:13<1:12:36,  1.49it/s] 
1|19374|Loss: 0.849210262298584:  75%|███████▍  | 19374/25880 [3:57:13<1:16:32,  1.42it/s]
1|19375|Loss: 0.8972290754318237:  75%|███████▍  | 19374/25880 [3:57:14<1:16:32,  1.42it/s]
1|19375|Loss: 0.8972290754318237:  75%|███████▍  | 19375/25880 [3:57:14<1:19:40,  1.36it/s]
1|19376|Loss: 0.7085129022598267:  75%|███████▍  | 19375/25880 [3:57:14<1:19:40,  1.36it/s]
1|19376|Loss: 0.7085129022598267:  75%|███████▍  | 19376/25880 [3:57:15<1:16:00,  1.43it/s]
1|19377|Loss: 0.9697641134262085:  75%|███████▍  | 19376/25880 [3:57:15<1:16:00,  1.43it/s]
1|19377|Loss: 0.9697641134262085:  75%|███████▍  | 19377/25880 [3:57:15<1:17:53,  1.39it/s]
1|19378|Loss: 0.8626691699028015:  75%|███████▍  | 19377/25880 [3:57:16<1:17:53,  1.39it/s]
1|19378|Loss: 0.8626691699028015:  75%|███████▍  | 19378/25880 [3:57:16<1:12:29,  1.49it/s]
1|19379|Loss: 0.8603541254997253:  75%|███████▍  | 19378/25880 [3:57:16<1:12:29,  1.49it/s]
1|19379|Loss: 0.8603541254997253:  75%|███████▍  | 19379/25880 [3:57:17<1:12:42,  1.49it/s]
1|19380|Loss: 0.9361733794212341:  75%|███████▍  | 19379/25880 [3:57:17<1:12:42,  1.49it/s]
1|19380|Loss: 0.9361733794212341:  75%|███████▍  | 19380/25880 [3:57:17<1:17:39,  1.40it/s]
1|19381|Loss: 0.9022300839424133:  75%|███████▍  | 19380/25880 [3:57:18<1:17:39,  1.40it/s]
1|19381|Loss: 0.9022300839424133:  75%|███████▍  | 19381/25880 [3:57:18<1:18:34,  1.38it/s]
1|19382|Loss: 0.8090544939041138:  75%|███████▍  | 19381/25880 [3:57:19<1:18:34,  1.38it/s]
1|19382|Loss: 0.8090544939041138:  75%|███████▍  | 19382/25880 [3:57:19<1:18:39,  1.38it/s]
1|19383|Loss: 0.9392443299293518:  75%|███████▍  | 19382/25880 [3:57:19<1:18:39,  1.38it/s]
1|19383|Loss: 0.9392443299293518:  75%|███████▍  | 19383/25880 [3:57:20<1:19:19,  1.36it/s]
1|19384|Loss: 0.8106914162635803:  75%|███████▍  | 19383/25880 [3:57:20<1:19:19,  1.36it/s]
1|19384|Loss: 0.8106914162635803:  75%|███████▍  | 19384/25880 [3:57:20<1:19:27,  1.36it/s]
1|19385|Loss: 0.8813552260398865:  75%|███████▍  | 19384/25880 [3:57:21<1:19:27,  1.36it/s]
1|19385|Loss: 0.8813552260398865:  75%|███████▍  | 19385/25880 [3:57:21<1:16:09,  1.42it/s]
1|19386|Loss: 0.8345731496810913:  75%|███████▍  | 19385/25880 [3:57:21<1:16:09,  1.42it/s]
1|19386|Loss: 0.8345731496810913:  75%|███████▍  | 19386/25880 [3:57:22<1:16:52,  1.41it/s]
1|19387|Loss: 1.0585622787475586:  75%|███████▍  | 19386/25880 [3:57:22<1:16:52,  1.41it/s]
1|19387|Loss: 1.0585622787475586:  75%|███████▍  | 19387/25880 [3:57:23<1:18:18,  1.38it/s]
1|19388|Loss: 0.7478453516960144:  75%|███████▍  | 19387/25880 [3:57:23<1:18:18,  1.38it/s]
1|19388|Loss: 0.7478453516960144:  75%|███████▍  | 19388/25880 [3:57:23<1:16:24,  1.42it/s]
1|19389|Loss: 0.7832754850387573:  75%|███████▍  | 19388/25880 [3:57:24<1:16:24,  1.42it/s]
1|19389|Loss: 0.7832754850387573:  75%|███████▍  | 19389/25880 [3:57:24<1:16:29,  1.41it/s]
1|19390|Loss: 0.833342432975769:  75%|███████▍  | 19389/25880 [3:57:24<1:16:29,  1.41it/s] 
1|19390|Loss: 0.833342432975769:  75%|███████▍  | 19390/25880 [3:57:25<1:14:45,  1.45it/s]
1|19391|Loss: 0.9050784111022949:  75%|███████▍  | 19390/25880 [3:57:25<1:14:45,  1.45it/s]
1|19391|Loss: 0.9050784111022949:  75%|███████▍  | 19391/25880 [3:57:25<1:13:00,  1.48it/s]
1|19392|Loss: 0.8741055727005005:  75%|███████▍  | 19391/25880 [3:57:26<1:13:00,  1.48it/s]
1|19392|Loss: 0.8741055727005005:  75%|███████▍  | 19392/25880 [3:57:26<1:11:11,  1.52it/s]
1|19393|Loss: 1.0060226917266846:  75%|███████▍  | 19392/25880 [3:57:26<1:11:11,  1.52it/s]
1|19393|Loss: 1.0060226917266846:  75%|███████▍  | 19393/25880 [3:57:27<1:12:59,  1.48it/s]
1|19394|Loss: 0.9977760314941406:  75%|███████▍  | 19393/25880 [3:57:27<1:12:59,  1.48it/s]
1|19394|Loss: 0.9977760314941406:  75%|███████▍  | 19394/25880 [3:57:27<1:18:40,  1.37it/s]
1|19395|Loss: 0.8596922755241394:  75%|███████▍  | 19394/25880 [3:57:28<1:18:40,  1.37it/s]
1|19395|Loss: 0.8596922755241394:  75%|███████▍  | 19395/25880 [3:57:28<1:20:20,  1.35it/s]
1|19396|Loss: 0.7534714937210083:  75%|███████▍  | 19395/25880 [3:57:29<1:20:20,  1.35it/s]
1|19396|Loss: 0.7534714937210083:  75%|███████▍  | 19396/25880 [3:57:29<1:14:51,  1.44it/s]
1|19397|Loss: 0.8186681270599365:  75%|███████▍  | 19396/25880 [3:57:29<1:14:51,  1.44it/s]
1|19397|Loss: 0.8186681270599365:  75%|███████▍  | 19397/25880 [3:57:30<1:18:16,  1.38it/s]
1|19398|Loss: 0.801867663860321:  75%|███████▍  | 19397/25880 [3:57:30<1:18:16,  1.38it/s] 
1|19398|Loss: 0.801867663860321:  75%|███████▍  | 19398/25880 [3:57:30<1:19:53,  1.35it/s]
1|19399|Loss: 0.8413470387458801:  75%|███████▍  | 19398/25880 [3:57:31<1:19:53,  1.35it/s]
1|19399|Loss: 0.8413470387458801:  75%|███████▍  | 19399/25880 [3:57:31<1:19:48,  1.35it/s]
1|19400|Loss: 0.9187514185905457:  75%|███████▍  | 19399/25880 [3:57:31<1:19:48,  1.35it/s]
1|19400|Loss: 0.9187514185905457:  75%|███████▍  | 19400/25880 [3:57:32<1:18:52,  1.37it/s]
1|19401|Loss: 0.6792077422142029:  75%|███████▍  | 19400/25880 [3:57:32<1:18:52,  1.37it/s]
1|19401|Loss: 0.6792077422142029:  75%|███████▍  | 19401/25880 [3:57:33<1:23:18,  1.30it/s]
1|19402|Loss: 0.7732356786727905:  75%|███████▍  | 19401/25880 [3:57:33<1:23:18,  1.30it/s]
1|19402|Loss: 0.7732356786727905:  75%|███████▍  | 19402/25880 [3:57:33<1:23:01,  1.30it/s]
1|19403|Loss: 0.7629076838493347:  75%|███████▍  | 19402/25880 [3:57:34<1:23:01,  1.30it/s]
1|19403|Loss: 0.7629076838493347:  75%|███████▍  | 19403/25880 [3:57:34<1:25:39,  1.26it/s]
1|19404|Loss: 0.9495434165000916:  75%|███████▍  | 19403/25880 [3:57:35<1:25:39,  1.26it/s]
1|19404|Loss: 0.9495434165000916:  75%|███████▍  | 19404/25880 [3:57:35<1:26:45,  1.24it/s]
1|19405|Loss: 0.7863110303878784:  75%|███████▍  | 19404/25880 [3:57:35<1:26:45,  1.24it/s]
1|19405|Loss: 0.7863110303878784:  75%|███████▍  | 19405/25880 [3:57:36<1:24:48,  1.27it/s]
1|19406|Loss: 0.7583265900611877:  75%|███████▍  | 19405/25880 [3:57:36<1:24:48,  1.27it/s]
1|19406|Loss: 0.7583265900611877:  75%|███████▍  | 19406/25880 [3:57:37<1:22:56,  1.30it/s]
1|19407|Loss: 0.851272463798523:  75%|███████▍  | 19406/25880 [3:57:37<1:22:56,  1.30it/s] 
1|19407|Loss: 0.851272463798523:  75%|███████▍  | 19407/25880 [3:57:37<1:19:16,  1.36it/s]
1|19408|Loss: 0.8183252811431885:  75%|███████▍  | 19407/25880 [3:57:38<1:19:16,  1.36it/s]
1|19408|Loss: 0.8183252811431885:  75%|███████▍  | 19408/25880 [3:57:38<1:18:27,  1.37it/s]
1|19409|Loss: 0.8709222674369812:  75%|███████▍  | 19408/25880 [3:57:38<1:18:27,  1.37it/s]
1|19409|Loss: 0.8709222674369812:  75%|███████▍  | 19409/25880 [3:57:39<1:17:53,  1.38it/s]
1|19410|Loss: 0.782474935054779:  75%|███████▍  | 19409/25880 [3:57:39<1:17:53,  1.38it/s] 
1|19410|Loss: 0.782474935054779:  75%|███████▌  | 19410/25880 [3:57:39<1:21:31,  1.32it/s]
1|19411|Loss: 0.8393701314926147:  75%|███████▌  | 19410/25880 [3:57:40<1:21:31,  1.32it/s]
1|19411|Loss: 0.8393701314926147:  75%|███████▌  | 19411/25880 [3:57:40<1:21:55,  1.32it/s]
1|19412|Loss: 0.7229154109954834:  75%|███████▌  | 19411/25880 [3:57:41<1:21:55,  1.32it/s]
1|19412|Loss: 0.7229154109954834:  75%|███████▌  | 19412/25880 [3:57:41<1:18:46,  1.37it/s]
1|19413|Loss: 0.9022181034088135:  75%|███████▌  | 19412/25880 [3:57:41<1:18:46,  1.37it/s]
1|19413|Loss: 0.9022181034088135:  75%|███████▌  | 19413/25880 [3:57:42<1:18:36,  1.37it/s]
1|19414|Loss: 0.7697407603263855:  75%|███████▌  | 19413/25880 [3:57:42<1:18:36,  1.37it/s]
1|19414|Loss: 0.7697407603263855:  75%|███████▌  | 19414/25880 [3:57:43<1:24:44,  1.27it/s]
1|19415|Loss: 0.8152533173561096:  75%|███████▌  | 19414/25880 [3:57:43<1:24:44,  1.27it/s]
1|19415|Loss: 0.8152533173561096:  75%|███████▌  | 19415/25880 [3:57:43<1:22:07,  1.31it/s]
1|19416|Loss: 0.8749113082885742:  75%|███████▌  | 19415/25880 [3:57:44<1:22:07,  1.31it/s]
1|19416|Loss: 0.8749113082885742:  75%|███████▌  | 19416/25880 [3:57:44<1:16:00,  1.42it/s]
1|19417|Loss: 0.631980299949646:  75%|███████▌  | 19416/25880 [3:57:44<1:16:00,  1.42it/s] 
1|19417|Loss: 0.631980299949646:  75%|███████▌  | 19417/25880 [3:57:45<1:22:06,  1.31it/s]
1|19418|Loss: 0.8160591721534729:  75%|███████▌  | 19417/25880 [3:57:45<1:22:06,  1.31it/s]
1|19418|Loss: 0.8160591721534729:  75%|███████▌  | 19418/25880 [3:57:45<1:15:52,  1.42it/s]
1|19419|Loss: 0.8952115774154663:  75%|███████▌  | 19418/25880 [3:57:46<1:15:52,  1.42it/s]
1|19419|Loss: 0.8952115774154663:  75%|███████▌  | 19419/25880 [3:57:46<1:15:04,  1.43it/s]
1|19420|Loss: 0.9302815198898315:  75%|███████▌  | 19419/25880 [3:57:46<1:15:04,  1.43it/s]
1|19420|Loss: 0.9302815198898315:  75%|███████▌  | 19420/25880 [3:57:47<1:14:12,  1.45it/s]
1|19421|Loss: 0.7080099582672119:  75%|███████▌  | 19420/25880 [3:57:47<1:14:12,  1.45it/s]
1|19421|Loss: 0.7080099582672119:  75%|███████▌  | 19421/25880 [3:57:47<1:14:11,  1.45it/s]
1|19422|Loss: 0.8423696160316467:  75%|███████▌  | 19421/25880 [3:57:48<1:14:11,  1.45it/s]
1|19422|Loss: 0.8423696160316467:  75%|███████▌  | 19422/25880 [3:57:48<1:09:57,  1.54it/s]
1|19423|Loss: 0.8226804733276367:  75%|███████▌  | 19422/25880 [3:57:48<1:09:57,  1.54it/s]
1|19423|Loss: 0.8226804733276367:  75%|███████▌  | 19423/25880 [3:57:49<1:12:42,  1.48it/s]
1|19424|Loss: 0.9287393093109131:  75%|███████▌  | 19423/25880 [3:57:49<1:12:42,  1.48it/s]
1|19424|Loss: 0.9287393093109131:  75%|███████▌  | 19424/25880 [3:57:49<1:17:36,  1.39it/s]
1|19425|Loss: 0.8057539463043213:  75%|███████▌  | 19424/25880 [3:57:50<1:17:36,  1.39it/s]
1|19425|Loss: 0.8057539463043213:  75%|███████▌  | 19425/25880 [3:57:50<1:16:29,  1.41it/s]
1|19426|Loss: 0.7577319741249084:  75%|███████▌  | 19425/25880 [3:57:50<1:16:29,  1.41it/s]
1|19426|Loss: 0.7577319741249084:  75%|███████▌  | 19426/25880 [3:57:51<1:15:51,  1.42it/s]
1|19427|Loss: 0.7905063629150391:  75%|███████▌  | 19426/25880 [3:57:51<1:15:51,  1.42it/s]
1|19427|Loss: 0.7905063629150391:  75%|███████▌  | 19427/25880 [3:57:52<1:16:46,  1.40it/s]
1|19428|Loss: 0.7681172490119934:  75%|███████▌  | 19427/25880 [3:57:52<1:16:46,  1.40it/s]
1|19428|Loss: 0.7681172490119934:  75%|███████▌  | 19428/25880 [3:57:52<1:19:09,  1.36it/s]
1|19429|Loss: 0.8381890058517456:  75%|███████▌  | 19428/25880 [3:57:53<1:19:09,  1.36it/s]
1|19429|Loss: 0.8381890058517456:  75%|███████▌  | 19429/25880 [3:57:53<1:18:55,  1.36it/s]
1|19430|Loss: 0.8737524151802063:  75%|███████▌  | 19429/25880 [3:57:53<1:18:55,  1.36it/s]
1|19430|Loss: 0.8737524151802063:  75%|███████▌  | 19430/25880 [3:57:54<1:20:00,  1.34it/s]
1|19431|Loss: 0.898593008518219:  75%|███████▌  | 19430/25880 [3:57:54<1:20:00,  1.34it/s] 
1|19431|Loss: 0.898593008518219:  75%|███████▌  | 19431/25880 [3:57:55<1:20:06,  1.34it/s]
1|19432|Loss: 0.9362963438034058:  75%|███████▌  | 19431/25880 [3:57:55<1:20:06,  1.34it/s]
1|19432|Loss: 0.9362963438034058:  75%|███████▌  | 19432/25880 [3:57:55<1:16:56,  1.40it/s]
1|19433|Loss: 0.7984730005264282:  75%|███████▌  | 19432/25880 [3:57:56<1:16:56,  1.40it/s]
1|19433|Loss: 0.7984730005264282:  75%|███████▌  | 19433/25880 [3:57:56<1:19:42,  1.35it/s]
1|19434|Loss: 0.6783644556999207:  75%|███████▌  | 19433/25880 [3:57:56<1:19:42,  1.35it/s]
1|19434|Loss: 0.6783644556999207:  75%|███████▌  | 19434/25880 [3:57:57<1:19:34,  1.35it/s]
1|19435|Loss: 0.8118067383766174:  75%|███████▌  | 19434/25880 [3:57:57<1:19:34,  1.35it/s]
1|19435|Loss: 0.8118067383766174:  75%|███████▌  | 19435/25880 [3:57:58<1:20:31,  1.33it/s]
1|19436|Loss: 0.8624058365821838:  75%|███████▌  | 19435/25880 [3:57:58<1:20:31,  1.33it/s]
1|19436|Loss: 0.8624058365821838:  75%|███████▌  | 19436/25880 [3:57:58<1:18:06,  1.38it/s]
1|19437|Loss: 0.8110906481742859:  75%|███████▌  | 19436/25880 [3:57:59<1:18:06,  1.38it/s]
1|19437|Loss: 0.8110906481742859:  75%|███████▌  | 19437/25880 [3:57:59<1:13:44,  1.46it/s]
1|19438|Loss: 0.896345853805542:  75%|███████▌  | 19437/25880 [3:57:59<1:13:44,  1.46it/s] 
1|19438|Loss: 0.896345853805542:  75%|███████▌  | 19438/25880 [3:57:59<1:10:15,  1.53it/s]
1|19439|Loss: 0.8750190734863281:  75%|███████▌  | 19438/25880 [3:58:00<1:10:15,  1.53it/s]
1|19439|Loss: 0.8750190734863281:  75%|███████▌  | 19439/25880 [3:58:00<1:11:05,  1.51it/s]
1|19440|Loss: 0.9021706581115723:  75%|███████▌  | 19439/25880 [3:58:00<1:11:05,  1.51it/s]
1|19440|Loss: 0.9021706581115723:  75%|███████▌  | 19440/25880 [3:58:01<1:10:41,  1.52it/s]
1|19441|Loss: 1.02040696144104:  75%|███████▌  | 19440/25880 [3:58:01<1:10:41,  1.52it/s]  
1|19441|Loss: 1.02040696144104:  75%|███████▌  | 19441/25880 [3:58:01<1:11:58,  1.49it/s]
1|19442|Loss: 0.7868895530700684:  75%|███████▌  | 19441/25880 [3:58:02<1:11:58,  1.49it/s]
1|19442|Loss: 0.7868895530700684:  75%|███████▌  | 19442/25880 [3:58:02<1:09:56,  1.53it/s]
1|19443|Loss: 0.9288910627365112:  75%|███████▌  | 19442/25880 [3:58:02<1:09:56,  1.53it/s]
1|19443|Loss: 0.9288910627365112:  75%|███████▌  | 19443/25880 [3:58:03<1:11:54,  1.49it/s]
1|19444|Loss: 0.8773819208145142:  75%|███████▌  | 19443/25880 [3:58:03<1:11:54,  1.49it/s]
1|19444|Loss: 0.8773819208145142:  75%|███████▌  | 19444/25880 [3:58:03<1:13:17,  1.46it/s]
1|19445|Loss: 0.8651448488235474:  75%|███████▌  | 19444/25880 [3:58:04<1:13:17,  1.46it/s]
1|19445|Loss: 0.8651448488235474:  75%|███████▌  | 19445/25880 [3:58:04<1:14:21,  1.44it/s]
1|19446|Loss: 0.8632134199142456:  75%|███████▌  | 19445/25880 [3:58:05<1:14:21,  1.44it/s]
1|19446|Loss: 0.8632134199142456:  75%|███████▌  | 19446/25880 [3:58:05<1:15:56,  1.41it/s]
1|19447|Loss: 0.851832389831543:  75%|███████▌  | 19446/25880 [3:58:05<1:15:56,  1.41it/s] 
1|19447|Loss: 0.851832389831543:  75%|███████▌  | 19447/25880 [3:58:06<1:20:05,  1.34it/s]
1|19448|Loss: 0.9842978715896606:  75%|███████▌  | 19447/25880 [3:58:06<1:20:05,  1.34it/s]
1|19448|Loss: 0.9842978715896606:  75%|███████▌  | 19448/25880 [3:58:07<1:26:28,  1.24it/s]
1|19449|Loss: 0.9319455623626709:  75%|███████▌  | 19448/25880 [3:58:07<1:26:28,  1.24it/s]
1|19449|Loss: 0.9319455623626709:  75%|███████▌  | 19449/25880 [3:58:08<1:28:13,  1.21it/s]
1|19450|Loss: 0.7863219380378723:  75%|███████▌  | 19449/25880 [3:58:08<1:28:13,  1.21it/s]
1|19450|Loss: 0.7863219380378723:  75%|███████▌  | 19450/25880 [3:58:08<1:25:25,  1.25it/s]
1|19451|Loss: 0.8062636256217957:  75%|███████▌  | 19450/25880 [3:58:09<1:25:25,  1.25it/s]
1|19451|Loss: 0.8062636256217957:  75%|███████▌  | 19451/25880 [3:58:09<1:22:16,  1.30it/s]
1|19452|Loss: 0.8686924576759338:  75%|███████▌  | 19451/25880 [3:58:09<1:22:16,  1.30it/s]
1|19452|Loss: 0.8686924576759338:  75%|███████▌  | 19452/25880 [3:58:10<1:18:26,  1.37it/s]
1|19453|Loss: 0.889899730682373:  75%|███████▌  | 19452/25880 [3:58:10<1:18:26,  1.37it/s] 
1|19453|Loss: 0.889899730682373:  75%|███████▌  | 19453/25880 [3:58:10<1:14:57,  1.43it/s]
1|19454|Loss: 0.7372483015060425:  75%|███████▌  | 19453/25880 [3:58:11<1:14:57,  1.43it/s]
1|19454|Loss: 0.7372483015060425:  75%|███████▌  | 19454/25880 [3:58:11<1:12:18,  1.48it/s]
1|19455|Loss: 0.8318780064582825:  75%|███████▌  | 19454/25880 [3:58:11<1:12:18,  1.48it/s]
1|19455|Loss: 0.8318780064582825:  75%|███████▌  | 19455/25880 [3:58:12<1:13:35,  1.46it/s]
1|19456|Loss: 0.680127739906311:  75%|███████▌  | 19455/25880 [3:58:12<1:13:35,  1.46it/s] 
1|19456|Loss: 0.680127739906311:  75%|███████▌  | 19456/25880 [3:58:12<1:12:11,  1.48it/s]
1|19457|Loss: 0.8887491226196289:  75%|███████▌  | 19456/25880 [3:58:13<1:12:11,  1.48it/s]
1|19457|Loss: 0.8887491226196289:  75%|███████▌  | 19457/25880 [3:58:13<1:13:17,  1.46it/s]
1|19458|Loss: 0.8910462856292725:  75%|███████▌  | 19457/25880 [3:58:13<1:13:17,  1.46it/s]
1|19458|Loss: 0.8910462856292725:  75%|███████▌  | 19458/25880 [3:58:14<1:13:51,  1.45it/s]
1|19459|Loss: 0.7929649353027344:  75%|███████▌  | 19458/25880 [3:58:14<1:13:51,  1.45it/s]
1|19459|Loss: 0.7929649353027344:  75%|███████▌  | 19459/25880 [3:58:14<1:12:25,  1.48it/s]
1|19460|Loss: 0.8055509328842163:  75%|███████▌  | 19459/25880 [3:58:15<1:12:25,  1.48it/s]
1|19460|Loss: 0.8055509328842163:  75%|███████▌  | 19460/25880 [3:58:15<1:13:30,  1.46it/s]
1|19461|Loss: 0.7973835468292236:  75%|███████▌  | 19460/25880 [3:58:15<1:13:30,  1.46it/s]
1|19461|Loss: 0.7973835468292236:  75%|███████▌  | 19461/25880 [3:58:16<1:11:01,  1.51it/s]
1|19462|Loss: 0.9303686618804932:  75%|███████▌  | 19461/25880 [3:58:16<1:11:01,  1.51it/s]
1|19462|Loss: 0.9303686618804932:  75%|███████▌  | 19462/25880 [3:58:16<1:12:33,  1.47it/s]
1|19463|Loss: 0.9031517505645752:  75%|███████▌  | 19462/25880 [3:58:17<1:12:33,  1.47it/s]
1|19463|Loss: 0.9031517505645752:  75%|███████▌  | 19463/25880 [3:58:17<1:12:13,  1.48it/s]
1|19464|Loss: 0.7386157512664795:  75%|███████▌  | 19463/25880 [3:58:17<1:12:13,  1.48it/s]
1|19464|Loss: 0.7386157512664795:  75%|███████▌  | 19464/25880 [3:58:18<1:12:36,  1.47it/s]
1|19465|Loss: 0.7921214699745178:  75%|███████▌  | 19464/25880 [3:58:18<1:12:36,  1.47it/s]
1|19465|Loss: 0.7921214699745178:  75%|███████▌  | 19465/25880 [3:58:18<1:10:59,  1.51it/s]
1|19466|Loss: 0.7841354012489319:  75%|███████▌  | 19465/25880 [3:58:19<1:10:59,  1.51it/s]
1|19466|Loss: 0.7841354012489319:  75%|███████▌  | 19466/25880 [3:58:19<1:12:30,  1.47it/s]
1|19467|Loss: 0.6668327450752258:  75%|███████▌  | 19466/25880 [3:58:19<1:12:30,  1.47it/s]
1|19467|Loss: 0.6668327450752258:  75%|███████▌  | 19467/25880 [3:58:20<1:17:38,  1.38it/s]
1|19468|Loss: 0.8112568259239197:  75%|███████▌  | 19467/25880 [3:58:20<1:17:38,  1.38it/s]
1|19468|Loss: 0.8112568259239197:  75%|███████▌  | 19468/25880 [3:58:21<1:19:10,  1.35it/s]
1|19469|Loss: 0.8814483284950256:  75%|███████▌  | 19468/25880 [3:58:21<1:19:10,  1.35it/s]
1|19469|Loss: 0.8814483284950256:  75%|███████▌  | 19469/25880 [3:58:21<1:15:30,  1.42it/s]
1|19470|Loss: 0.8046790361404419:  75%|███████▌  | 19469/25880 [3:58:22<1:15:30,  1.42it/s]
1|19470|Loss: 0.8046790361404419:  75%|███████▌  | 19470/25880 [3:58:22<1:15:41,  1.41it/s]
1|19471|Loss: 0.8252836465835571:  75%|███████▌  | 19470/25880 [3:58:22<1:15:41,  1.41it/s]
1|19471|Loss: 0.8252836465835571:  75%|███████▌  | 19471/25880 [3:58:23<1:19:18,  1.35it/s]
1|19472|Loss: 0.8044267892837524:  75%|███████▌  | 19471/25880 [3:58:23<1:19:18,  1.35it/s]
1|19472|Loss: 0.8044267892837524:  75%|███████▌  | 19472/25880 [3:58:23<1:16:39,  1.39it/s]
1|19473|Loss: 0.7733786702156067:  75%|███████▌  | 19472/25880 [3:58:24<1:16:39,  1.39it/s]
1|19473|Loss: 0.7733786702156067:  75%|███████▌  | 19473/25880 [3:58:24<1:22:59,  1.29it/s]
1|19474|Loss: 0.9481409788131714:  75%|███████▌  | 19473/25880 [3:58:25<1:22:59,  1.29it/s]
1|19474|Loss: 0.9481409788131714:  75%|███████▌  | 19474/25880 [3:58:25<1:27:11,  1.22it/s]
1|19475|Loss: 1.0995715856552124:  75%|███████▌  | 19474/25880 [3:58:26<1:27:11,  1.22it/s]
1|19475|Loss: 1.0995715856552124:  75%|███████▌  | 19475/25880 [3:58:26<1:26:03,  1.24it/s]
1|19476|Loss: 0.7764561772346497:  75%|███████▌  | 19475/25880 [3:58:26<1:26:03,  1.24it/s]
1|19476|Loss: 0.7764561772346497:  75%|███████▌  | 19476/25880 [3:58:27<1:24:09,  1.27it/s]
1|19477|Loss: 0.8275762796401978:  75%|███████▌  | 19476/25880 [3:58:27<1:24:09,  1.27it/s]
1|19477|Loss: 0.8275762796401978:  75%|███████▌  | 19477/25880 [3:58:28<1:24:53,  1.26it/s]
1|19478|Loss: 0.7937543392181396:  75%|███████▌  | 19477/25880 [3:58:28<1:24:53,  1.26it/s]
1|19478|Loss: 0.7937543392181396:  75%|███████▌  | 19478/25880 [3:58:29<1:28:05,  1.21it/s]
1|19479|Loss: 0.8188324570655823:  75%|███████▌  | 19478/25880 [3:58:29<1:28:05,  1.21it/s]
1|19479|Loss: 0.8188324570655823:  75%|███████▌  | 19479/25880 [3:58:29<1:27:37,  1.22it/s]
1|19480|Loss: 0.8784732818603516:  75%|███████▌  | 19479/25880 [3:58:30<1:27:37,  1.22it/s]
1|19480|Loss: 0.8784732818603516:  75%|███████▌  | 19480/25880 [3:58:30<1:30:12,  1.18it/s]
1|19481|Loss: 0.8411020636558533:  75%|███████▌  | 19480/25880 [3:58:31<1:30:12,  1.18it/s]
1|19481|Loss: 0.8411020636558533:  75%|███████▌  | 19481/25880 [3:58:31<1:29:33,  1.19it/s]
1|19482|Loss: 0.9693310856819153:  75%|███████▌  | 19481/25880 [3:58:31<1:29:33,  1.19it/s]
1|19482|Loss: 0.9693310856819153:  75%|███████▌  | 19482/25880 [3:58:32<1:26:40,  1.23it/s]
1|19483|Loss: 0.7112633585929871:  75%|███████▌  | 19482/25880 [3:58:32<1:26:40,  1.23it/s]
1|19483|Loss: 0.7112633585929871:  75%|███████▌  | 19483/25880 [3:58:32<1:18:51,  1.35it/s]
1|19484|Loss: 0.7862036824226379:  75%|███████▌  | 19483/25880 [3:58:33<1:18:51,  1.35it/s]
1|19484|Loss: 0.7862036824226379:  75%|███████▌  | 19484/25880 [3:58:33<1:13:31,  1.45it/s]
1|19485|Loss: 0.7342311143875122:  75%|███████▌  | 19484/25880 [3:58:33<1:13:31,  1.45it/s]
1|19485|Loss: 0.7342311143875122:  75%|███████▌  | 19485/25880 [3:58:34<1:13:05,  1.46it/s]
1|19486|Loss: 0.7408528923988342:  75%|███████▌  | 19485/25880 [3:58:34<1:13:05,  1.46it/s]
1|19486|Loss: 0.7408528923988342:  75%|███████▌  | 19486/25880 [3:58:34<1:15:36,  1.41it/s]
1|19487|Loss: 0.7654274106025696:  75%|███████▌  | 19486/25880 [3:58:35<1:15:36,  1.41it/s]
1|19487|Loss: 0.7654274106025696:  75%|███████▌  | 19487/25880 [3:58:35<1:14:30,  1.43it/s]
1|19488|Loss: 0.9343955516815186:  75%|███████▌  | 19487/25880 [3:58:35<1:14:30,  1.43it/s]
1|19488|Loss: 0.9343955516815186:  75%|███████▌  | 19488/25880 [3:58:36<1:09:22,  1.54it/s]
1|19489|Loss: 0.8162226676940918:  75%|███████▌  | 19488/25880 [3:58:36<1:09:22,  1.54it/s]
1|19489|Loss: 0.8162226676940918:  75%|███████▌  | 19489/25880 [3:58:36<1:08:01,  1.57it/s]
1|19490|Loss: 0.9949662685394287:  75%|███████▌  | 19489/25880 [3:58:37<1:08:01,  1.57it/s]
1|19490|Loss: 0.9949662685394287:  75%|███████▌  | 19490/25880 [3:58:37<1:13:30,  1.45it/s]
1|19491|Loss: 0.8729926347732544:  75%|███████▌  | 19490/25880 [3:58:37<1:13:30,  1.45it/s]
1|19491|Loss: 0.8729926347732544:  75%|███████▌  | 19491/25880 [3:58:38<1:19:10,  1.34it/s]
1|19492|Loss: 0.9705073237419128:  75%|███████▌  | 19491/25880 [3:58:38<1:19:10,  1.34it/s]
1|19492|Loss: 0.9705073237419128:  75%|███████▌  | 19492/25880 [3:58:39<1:16:22,  1.39it/s]
1|19493|Loss: 0.8195256590843201:  75%|███████▌  | 19492/25880 [3:58:39<1:16:22,  1.39it/s]
1|19493|Loss: 0.8195256590843201:  75%|███████▌  | 19493/25880 [3:58:39<1:12:58,  1.46it/s]
1|19494|Loss: 0.7847141027450562:  75%|███████▌  | 19493/25880 [3:58:40<1:12:58,  1.46it/s]
1|19494|Loss: 0.7847141027450562:  75%|███████▌  | 19494/25880 [3:58:40<1:10:45,  1.50it/s]
1|19495|Loss: 0.8557256460189819:  75%|███████▌  | 19494/25880 [3:58:40<1:10:45,  1.50it/s]
1|19495|Loss: 0.8557256460189819:  75%|███████▌  | 19495/25880 [3:58:40<1:12:18,  1.47it/s]
1|19496|Loss: 0.8673579692840576:  75%|███████▌  | 19495/25880 [3:58:41<1:12:18,  1.47it/s]
1|19496|Loss: 0.8673579692840576:  75%|███████▌  | 19496/25880 [3:58:41<1:14:48,  1.42it/s]
1|19497|Loss: 0.9380308389663696:  75%|███████▌  | 19496/25880 [3:58:42<1:14:48,  1.42it/s]
1|19497|Loss: 0.9380308389663696:  75%|███████▌  | 19497/25880 [3:58:42<1:12:58,  1.46it/s]
1|19498|Loss: 0.7565872073173523:  75%|███████▌  | 19497/25880 [3:58:42<1:12:58,  1.46it/s]
1|19498|Loss: 0.7565872073173523:  75%|███████▌  | 19498/25880 [3:58:43<1:15:38,  1.41it/s]
1|19499|Loss: 0.87715744972229:  75%|███████▌  | 19498/25880 [3:58:43<1:15:38,  1.41it/s]  
1|19499|Loss: 0.87715744972229:  75%|███████▌  | 19499/25880 [3:58:43<1:09:44,  1.52it/s]
1|19500|Loss: 0.769137442111969:  75%|███████▌  | 19499/25880 [3:58:44<1:09:44,  1.52it/s]Model checkpoint of size 25961 MB saved to output/alpaca-colorful-llama2-finetune/model_0_19500.ckpt
+Skipping uploading to HuggingFace Hub (no repo id specified)
+
1|19500|Loss: 0.769137442111969:  75%|███████▌  | 19500/25880 [3:59:25<22:50:23, 12.89s/it]
1|19501|Loss: 0.721324622631073:  75%|███████▌  | 19500/25880 [3:59:25<22:50:23, 12.89s/it]
1|19501|Loss: 0.721324622631073:  75%|███████▌  | 19501/25880 [3:59:25<16:11:12,  9.14s/it]
1|19502|Loss: 0.8708783984184265:  75%|███████▌  | 19501/25880 [3:59:25<16:11:12,  9.14s/it]
1|19502|Loss: 0.8708783984184265:  75%|███████▌  | 19502/25880 [3:59:26<11:41:16,  6.60s/it]
1|19503|Loss: 0.8407660126686096:  75%|███████▌  | 19502/25880 [3:59:26<11:41:16,  6.60s/it]
1|19503|Loss: 0.8407660126686096:  75%|███████▌  | 19503/25880 [3:59:26<8:35:49,  4.85s/it] 
1|19504|Loss: 0.8303831219673157:  75%|███████▌  | 19503/25880 [3:59:27<8:35:49,  4.85s/it]
1|19504|Loss: 0.8303831219673157:  75%|███████▌  | 19504/25880 [3:59:27<6:20:30,  3.58s/it]
1|19505|Loss: 0.7522693276405334:  75%|███████▌  | 19504/25880 [3:59:27<6:20:30,  3.58s/it]
1|19505|Loss: 0.7522693276405334:  75%|███████▌  | 19505/25880 [3:59:28<4:49:36,  2.73s/it]
1|19506|Loss: 0.9028357863426208:  75%|███████▌  | 19505/25880 [3:59:28<4:49:36,  2.73s/it]
1|19506|Loss: 0.9028357863426208:  75%|███████▌  | 19506/25880 [3:59:29<3:49:37,  2.16s/it]
1|19507|Loss: 0.950400710105896:  75%|███████▌  | 19506/25880 [3:59:29<3:49:37,  2.16s/it] 
1|19507|Loss: 0.950400710105896:  75%|███████▌  | 19507/25880 [3:59:29<3:04:04,  1.73s/it]
1|19508|Loss: 0.6490040421485901:  75%|███████▌  | 19507/25880 [3:59:30<3:04:04,  1.73s/it]
1|19508|Loss: 0.6490040421485901:  75%|███████▌  | 19508/25880 [3:59:30<2:31:33,  1.43s/it]
1|19509|Loss: 0.7910213470458984:  75%|███████▌  | 19508/25880 [3:59:30<2:31:33,  1.43s/it]
1|19509|Loss: 0.7910213470458984:  75%|███████▌  | 19509/25880 [3:59:31<2:08:29,  1.21s/it]
1|19510|Loss: 0.7380012273788452:  75%|███████▌  | 19509/25880 [3:59:31<2:08:29,  1.21s/it]
1|19510|Loss: 0.7380012273788452:  75%|███████▌  | 19510/25880 [3:59:32<1:53:12,  1.07s/it]
1|19511|Loss: 0.8502973318099976:  75%|███████▌  | 19510/25880 [3:59:32<1:53:12,  1.07s/it]
1|19511|Loss: 0.8502973318099976:  75%|███████▌  | 19511/25880 [3:59:32<1:42:25,  1.04it/s]
1|19512|Loss: 0.8047649264335632:  75%|███████▌  | 19511/25880 [3:59:33<1:42:25,  1.04it/s]
1|19512|Loss: 0.8047649264335632:  75%|███████▌  | 19512/25880 [3:59:33<1:38:01,  1.08it/s]
1|19513|Loss: 0.9205475449562073:  75%|███████▌  | 19512/25880 [3:59:33<1:38:01,  1.08it/s]
1|19513|Loss: 0.9205475449562073:  75%|███████▌  | 19513/25880 [3:59:34<1:28:51,  1.19it/s]
1|19514|Loss: 0.7729528546333313:  75%|███████▌  | 19513/25880 [3:59:34<1:28:51,  1.19it/s]
1|19514|Loss: 0.7729528546333313:  75%|███████▌  | 19514/25880 [3:59:34<1:25:44,  1.24it/s]
1|19515|Loss: 0.9238383769989014:  75%|███████▌  | 19514/25880 [3:59:35<1:25:44,  1.24it/s]
1|19515|Loss: 0.9238383769989014:  75%|███████▌  | 19515/25880 [3:59:35<1:20:44,  1.31it/s]
1|19516|Loss: 0.8634716272354126:  75%|███████▌  | 19515/25880 [3:59:35<1:20:44,  1.31it/s]
1|19516|Loss: 0.8634716272354126:  75%|███████▌  | 19516/25880 [3:59:36<1:16:38,  1.38it/s]
1|19517|Loss: 0.7909631133079529:  75%|███████▌  | 19516/25880 [3:59:36<1:16:38,  1.38it/s]
1|19517|Loss: 0.7909631133079529:  75%|███████▌  | 19517/25880 [3:59:37<1:17:40,  1.37it/s]
1|19518|Loss: 0.7640379071235657:  75%|███████▌  | 19517/25880 [3:59:37<1:17:40,  1.37it/s]
1|19518|Loss: 0.7640379071235657:  75%|███████▌  | 19518/25880 [3:59:37<1:15:40,  1.40it/s]
1|19519|Loss: 0.7649967074394226:  75%|███████▌  | 19518/25880 [3:59:38<1:15:40,  1.40it/s]
1|19519|Loss: 0.7649967074394226:  75%|███████▌  | 19519/25880 [3:59:38<1:15:34,  1.40it/s]
1|19520|Loss: 0.7315748929977417:  75%|███████▌  | 19519/25880 [3:59:38<1:15:34,  1.40it/s]
1|19520|Loss: 0.7315748929977417:  75%|███████▌  | 19520/25880 [3:59:39<1:15:03,  1.41it/s]
1|19521|Loss: 0.9289531111717224:  75%|███████▌  | 19520/25880 [3:59:39<1:15:03,  1.41it/s]
1|19521|Loss: 0.9289531111717224:  75%|███████▌  | 19521/25880 [3:59:39<1:14:25,  1.42it/s]
1|19522|Loss: 0.8712247014045715:  75%|███████▌  | 19521/25880 [3:59:40<1:14:25,  1.42it/s]
1|19522|Loss: 0.8712247014045715:  75%|███████▌  | 19522/25880 [3:59:40<1:18:43,  1.35it/s]
1|19523|Loss: 0.8828175067901611:  75%|███████▌  | 19522/25880 [3:59:41<1:18:43,  1.35it/s]
1|19523|Loss: 0.8828175067901611:  75%|███████▌  | 19523/25880 [3:59:41<1:23:56,  1.26it/s]
1|19524|Loss: 0.9363583922386169:  75%|███████▌  | 19523/25880 [3:59:41<1:23:56,  1.26it/s]
1|19524|Loss: 0.9363583922386169:  75%|███████▌  | 19524/25880 [3:59:42<1:20:07,  1.32it/s]
1|19525|Loss: 0.8456419706344604:  75%|███████▌  | 19524/25880 [3:59:42<1:20:07,  1.32it/s]
1|19525|Loss: 0.8456419706344604:  75%|███████▌  | 19525/25880 [3:59:42<1:20:44,  1.31it/s]
1|19526|Loss: 0.7678734064102173:  75%|███████▌  | 19525/25880 [3:59:43<1:20:44,  1.31it/s]
1|19526|Loss: 0.7678734064102173:  75%|███████▌  | 19526/25880 [3:59:43<1:20:09,  1.32it/s]
1|19527|Loss: 0.8300653100013733:  75%|███████▌  | 19526/25880 [3:59:44<1:20:09,  1.32it/s]
1|19527|Loss: 0.8300653100013733:  75%|███████▌  | 19527/25880 [3:59:45<1:41:52,  1.04it/s]
1|19528|Loss: 0.8680014610290527:  75%|███████▌  | 19527/25880 [3:59:45<1:41:52,  1.04it/s]
1|19528|Loss: 0.8680014610290527:  75%|███████▌  | 19528/25880 [3:59:45<1:31:38,  1.16it/s]
1|19529|Loss: 0.7376671433448792:  75%|███████▌  | 19528/25880 [3:59:46<1:31:38,  1.16it/s]
1|19529|Loss: 0.7376671433448792:  75%|███████▌  | 19529/25880 [3:59:46<1:29:33,  1.18it/s]
1|19530|Loss: 0.875171959400177:  75%|███████▌  | 19529/25880 [3:59:46<1:29:33,  1.18it/s] 
1|19530|Loss: 0.875171959400177:  75%|███████▌  | 19530/25880 [3:59:47<1:23:35,  1.27it/s]
1|19531|Loss: 0.8073537349700928:  75%|███████▌  | 19530/25880 [3:59:47<1:23:35,  1.27it/s]
1|19531|Loss: 0.8073537349700928:  75%|███████▌  | 19531/25880 [3:59:48<1:22:47,  1.28it/s]
1|19532|Loss: 0.7163047194480896:  75%|███████▌  | 19531/25880 [3:59:48<1:22:47,  1.28it/s]
1|19532|Loss: 0.7163047194480896:  75%|███████▌  | 19532/25880 [3:59:48<1:18:01,  1.36it/s]
1|19533|Loss: 0.8707301616668701:  75%|███████▌  | 19532/25880 [3:59:49<1:18:01,  1.36it/s]
1|19533|Loss: 0.8707301616668701:  75%|███████▌  | 19533/25880 [3:59:49<1:20:21,  1.32it/s]
1|19534|Loss: 0.7618716359138489:  75%|███████▌  | 19533/25880 [3:59:49<1:20:21,  1.32it/s]
1|19534|Loss: 0.7618716359138489:  75%|███████▌  | 19534/25880 [3:59:50<1:23:39,  1.26it/s]
1|19535|Loss: 0.8422808051109314:  75%|███████▌  | 19534/25880 [3:59:50<1:23:39,  1.26it/s]
1|19535|Loss: 0.8422808051109314:  75%|███████▌  | 19535/25880 [3:59:51<1:22:06,  1.29it/s]
1|19536|Loss: 0.9345546364784241:  75%|███████▌  | 19535/25880 [3:59:51<1:22:06,  1.29it/s]
1|19536|Loss: 0.9345546364784241:  75%|███████▌  | 19536/25880 [3:59:51<1:20:16,  1.32it/s]
1|19537|Loss: 0.7890745997428894:  75%|███████▌  | 19536/25880 [3:59:52<1:20:16,  1.32it/s]
1|19537|Loss: 0.7890745997428894:  75%|███████▌  | 19537/25880 [3:59:52<1:18:24,  1.35it/s]
1|19538|Loss: 0.7781046628952026:  75%|███████▌  | 19537/25880 [3:59:52<1:18:24,  1.35it/s]
1|19538|Loss: 0.7781046628952026:  75%|███████▌  | 19538/25880 [3:59:53<1:20:39,  1.31it/s]
1|19539|Loss: 1.0278973579406738:  75%|███████▌  | 19538/25880 [3:59:53<1:20:39,  1.31it/s]
1|19539|Loss: 1.0278973579406738:  75%|███████▌  | 19539/25880 [3:59:53<1:17:57,  1.36it/s]
1|19540|Loss: 0.8330135941505432:  75%|███████▌  | 19539/25880 [3:59:54<1:17:57,  1.36it/s]
1|19540|Loss: 0.8330135941505432:  76%|███████▌  | 19540/25880 [3:59:54<1:14:53,  1.41it/s]
1|19541|Loss: 0.823716402053833:  76%|███████▌  | 19540/25880 [3:59:54<1:14:53,  1.41it/s] 
1|19541|Loss: 0.823716402053833:  76%|███████▌  | 19541/25880 [3:59:55<1:10:37,  1.50it/s]
1|19542|Loss: 0.9029999375343323:  76%|███████▌  | 19541/25880 [3:59:55<1:10:37,  1.50it/s]
1|19542|Loss: 0.9029999375343323:  76%|███████▌  | 19542/25880 [3:59:55<1:13:52,  1.43it/s]
1|19543|Loss: 0.7774232029914856:  76%|███████▌  | 19542/25880 [3:59:56<1:13:52,  1.43it/s]
1|19543|Loss: 0.7774232029914856:  76%|███████▌  | 19543/25880 [3:59:56<1:15:48,  1.39it/s]
1|19544|Loss: 0.8320837020874023:  76%|███████▌  | 19543/25880 [3:59:57<1:15:48,  1.39it/s]
1|19544|Loss: 0.8320837020874023:  76%|███████▌  | 19544/25880 [3:59:57<1:18:48,  1.34it/s]
1|19545|Loss: 0.8898813724517822:  76%|███████▌  | 19544/25880 [3:59:57<1:18:48,  1.34it/s]
1|19545|Loss: 0.8898813724517822:  76%|███████▌  | 19545/25880 [3:59:58<1:18:04,  1.35it/s]
1|19546|Loss: 0.8727932572364807:  76%|███████▌  | 19545/25880 [3:59:58<1:18:04,  1.35it/s]
1|19546|Loss: 0.8727932572364807:  76%|███████▌  | 19546/25880 [3:59:58<1:17:37,  1.36it/s]
1|19547|Loss: 0.8156663179397583:  76%|███████▌  | 19546/25880 [3:59:59<1:17:37,  1.36it/s]
1|19547|Loss: 0.8156663179397583:  76%|███████▌  | 19547/25880 [3:59:59<1:14:28,  1.42it/s]
1|19548|Loss: 0.8923953175544739:  76%|███████▌  | 19547/25880 [4:00:00<1:14:28,  1.42it/s]
1|19548|Loss: 0.8923953175544739:  76%|███████▌  | 19548/25880 [4:00:00<1:14:38,  1.41it/s]
1|19549|Loss: 0.884087324142456:  76%|███████▌  | 19548/25880 [4:00:00<1:14:38,  1.41it/s] 
1|19549|Loss: 0.884087324142456:  76%|███████▌  | 19549/25880 [4:00:01<1:14:35,  1.41it/s]
1|19550|Loss: 0.7395687103271484:  76%|███████▌  | 19549/25880 [4:00:01<1:14:35,  1.41it/s]
1|19550|Loss: 0.7395687103271484:  76%|███████▌  | 19550/25880 [4:00:01<1:10:30,  1.50it/s]
1|19551|Loss: 0.9418498277664185:  76%|███████▌  | 19550/25880 [4:00:01<1:10:30,  1.50it/s]
1|19551|Loss: 0.9418498277664185:  76%|███████▌  | 19551/25880 [4:00:02<1:11:09,  1.48it/s]
1|19552|Loss: 0.863050103187561:  76%|███████▌  | 19551/25880 [4:00:02<1:11:09,  1.48it/s] 
1|19552|Loss: 0.863050103187561:  76%|███████▌  | 19552/25880 [4:00:02<1:06:30,  1.59it/s]
1|19553|Loss: 0.8387139439582825:  76%|███████▌  | 19552/25880 [4:00:03<1:06:30,  1.59it/s]
1|19553|Loss: 0.8387139439582825:  76%|███████▌  | 19553/25880 [4:00:03<1:08:00,  1.55it/s]
1|19554|Loss: 0.9247843623161316:  76%|███████▌  | 19553/25880 [4:00:03<1:08:00,  1.55it/s]
1|19554|Loss: 0.9247843623161316:  76%|███████▌  | 19554/25880 [4:00:04<1:12:42,  1.45it/s]
1|19555|Loss: 0.7961317300796509:  76%|███████▌  | 19554/25880 [4:00:04<1:12:42,  1.45it/s]
1|19555|Loss: 0.7961317300796509:  76%|███████▌  | 19555/25880 [4:00:05<1:17:43,  1.36it/s]
1|19556|Loss: 0.69321608543396:  76%|███████▌  | 19555/25880 [4:00:05<1:17:43,  1.36it/s]  
1|19556|Loss: 0.69321608543396:  76%|███████▌  | 19556/25880 [4:00:05<1:18:46,  1.34it/s]
1|19557|Loss: 0.793890655040741:  76%|███████▌  | 19556/25880 [4:00:06<1:18:46,  1.34it/s]
1|19557|Loss: 0.793890655040741:  76%|███████▌  | 19557/25880 [4:00:06<1:11:23,  1.48it/s]
1|19558|Loss: 0.7603073716163635:  76%|███████▌  | 19557/25880 [4:00:06<1:11:23,  1.48it/s]
1|19558|Loss: 0.7603073716163635:  76%|███████▌  | 19558/25880 [4:00:07<1:14:47,  1.41it/s]
1|19559|Loss: 0.8863873481750488:  76%|███████▌  | 19558/25880 [4:00:07<1:14:47,  1.41it/s]
1|19559|Loss: 0.8863873481750488:  76%|███████▌  | 19559/25880 [4:00:08<1:19:30,  1.33it/s]
1|19560|Loss: 0.8754894137382507:  76%|███████▌  | 19559/25880 [4:00:08<1:19:30,  1.33it/s]
1|19560|Loss: 0.8754894137382507:  76%|███████▌  | 19560/25880 [4:00:08<1:20:08,  1.31it/s]
1|19561|Loss: 0.8465295433998108:  76%|███████▌  | 19560/25880 [4:00:09<1:20:08,  1.31it/s]
1|19561|Loss: 0.8465295433998108:  76%|███████▌  | 19561/25880 [4:00:09<1:19:13,  1.33it/s]
1|19562|Loss: 0.8175569772720337:  76%|███████▌  | 19561/25880 [4:00:10<1:19:13,  1.33it/s]
1|19562|Loss: 0.8175569772720337:  76%|███████▌  | 19562/25880 [4:00:10<1:20:17,  1.31it/s]
1|19563|Loss: 0.9212393164634705:  76%|███████▌  | 19562/25880 [4:00:10<1:20:17,  1.31it/s]
1|19563|Loss: 0.9212393164634705:  76%|███████▌  | 19563/25880 [4:00:10<1:15:09,  1.40it/s]
1|19564|Loss: 0.8308088183403015:  76%|███████▌  | 19563/25880 [4:00:11<1:15:09,  1.40it/s]
1|19564|Loss: 0.8308088183403015:  76%|███████▌  | 19564/25880 [4:00:11<1:11:39,  1.47it/s]
1|19565|Loss: 0.6743866205215454:  76%|███████▌  | 19564/25880 [4:00:11<1:11:39,  1.47it/s]
1|19565|Loss: 0.6743866205215454:  76%|███████▌  | 19565/25880 [4:00:12<1:12:57,  1.44it/s]
1|19566|Loss: 0.809389591217041:  76%|███████▌  | 19565/25880 [4:00:12<1:12:57,  1.44it/s] 
1|19566|Loss: 0.809389591217041:  76%|███████▌  | 19566/25880 [4:00:13<1:14:23,  1.41it/s]
1|19567|Loss: 0.8063795566558838:  76%|███████▌  | 19566/25880 [4:00:13<1:14:23,  1.41it/s]
1|19567|Loss: 0.8063795566558838:  76%|███████▌  | 19567/25880 [4:00:13<1:17:55,  1.35it/s]
1|19568|Loss: 0.7832632064819336:  76%|███████▌  | 19567/25880 [4:00:14<1:17:55,  1.35it/s]
1|19568|Loss: 0.7832632064819336:  76%|███████▌  | 19568/25880 [4:00:14<1:19:47,  1.32it/s]
1|19569|Loss: 0.87883061170578:  76%|███████▌  | 19568/25880 [4:00:15<1:19:47,  1.32it/s]  
1|19569|Loss: 0.87883061170578:  76%|███████▌  | 19569/25880 [4:00:15<1:17:06,  1.36it/s]
1|19570|Loss: 0.9375737905502319:  76%|███████▌  | 19569/25880 [4:00:15<1:17:06,  1.36it/s]
1|19570|Loss: 0.9375737905502319:  76%|███████▌  | 19570/25880 [4:00:16<1:16:53,  1.37it/s]
1|19571|Loss: 0.8071783185005188:  76%|███████▌  | 19570/25880 [4:00:16<1:16:53,  1.37it/s]
1|19571|Loss: 0.8071783185005188:  76%|███████▌  | 19571/25880 [4:00:16<1:16:18,  1.38it/s]
1|19572|Loss: 0.7083533406257629:  76%|███████▌  | 19571/25880 [4:00:17<1:16:18,  1.38it/s]
1|19572|Loss: 0.7083533406257629:  76%|███████▌  | 19572/25880 [4:00:17<1:18:40,  1.34it/s]
1|19573|Loss: 0.8560009002685547:  76%|███████▌  | 19572/25880 [4:00:17<1:18:40,  1.34it/s]
1|19573|Loss: 0.8560009002685547:  76%|███████▌  | 19573/25880 [4:00:18<1:16:30,  1.37it/s]
1|19574|Loss: 0.7752167582511902:  76%|███████▌  | 19573/25880 [4:00:18<1:16:30,  1.37it/s]
1|19574|Loss: 0.7752167582511902:  76%|███████▌  | 19574/25880 [4:00:19<1:17:27,  1.36it/s]
1|19575|Loss: 0.7113389372825623:  76%|███████▌  | 19574/25880 [4:00:19<1:17:27,  1.36it/s]
1|19575|Loss: 0.7113389372825623:  76%|███████▌  | 19575/25880 [4:00:19<1:17:39,  1.35it/s]
1|19576|Loss: 0.7426987886428833:  76%|███████▌  | 19575/25880 [4:00:20<1:17:39,  1.35it/s]
1|19576|Loss: 0.7426987886428833:  76%|███████▌  | 19576/25880 [4:00:20<1:17:25,  1.36it/s]
1|19577|Loss: 0.6306914687156677:  76%|███████▌  | 19576/25880 [4:00:20<1:17:25,  1.36it/s]
1|19577|Loss: 0.6306914687156677:  76%|███████▌  | 19577/25880 [4:00:21<1:19:08,  1.33it/s]
1|19578|Loss: 0.8973348140716553:  76%|███████▌  | 19577/25880 [4:00:21<1:19:08,  1.33it/s]
1|19578|Loss: 0.8973348140716553:  76%|███████▌  | 19578/25880 [4:00:22<1:20:35,  1.30it/s]
1|19579|Loss: 0.8077390789985657:  76%|███████▌  | 19578/25880 [4:00:22<1:20:35,  1.30it/s]
1|19579|Loss: 0.8077390789985657:  76%|███████▌  | 19579/25880 [4:00:22<1:22:22,  1.27it/s]
1|19580|Loss: 0.7391053438186646:  76%|███████▌  | 19579/25880 [4:00:23<1:22:22,  1.27it/s]
1|19580|Loss: 0.7391053438186646:  76%|███████▌  | 19580/25880 [4:00:23<1:24:19,  1.25it/s]
1|19581|Loss: 0.8776810765266418:  76%|███████▌  | 19580/25880 [4:00:24<1:24:19,  1.25it/s]
1|19581|Loss: 0.8776810765266418:  76%|███████▌  | 19581/25880 [4:00:24<1:22:42,  1.27it/s]
1|19582|Loss: 0.8815226554870605:  76%|███████▌  | 19581/25880 [4:00:24<1:22:42,  1.27it/s]
1|19582|Loss: 0.8815226554870605:  76%|███████▌  | 19582/25880 [4:00:25<1:23:31,  1.26it/s]
1|19583|Loss: 0.880122721195221:  76%|███████▌  | 19582/25880 [4:00:25<1:23:31,  1.26it/s] 
1|19583|Loss: 0.880122721195221:  76%|███████▌  | 19583/25880 [4:00:26<1:24:32,  1.24it/s]
1|19584|Loss: 0.877315878868103:  76%|███████▌  | 19583/25880 [4:00:26<1:24:32,  1.24it/s]
1|19584|Loss: 0.877315878868103:  76%|███████▌  | 19584/25880 [4:00:27<1:27:32,  1.20it/s]
1|19585|Loss: 0.8516950607299805:  76%|███████▌  | 19584/25880 [4:00:27<1:27:32,  1.20it/s]
1|19585|Loss: 0.8516950607299805:  76%|███████▌  | 19585/25880 [4:00:27<1:25:10,  1.23it/s]
1|19586|Loss: 0.7841677665710449:  76%|███████▌  | 19585/25880 [4:00:28<1:25:10,  1.23it/s]
1|19586|Loss: 0.7841677665710449:  76%|███████▌  | 19586/25880 [4:00:28<1:27:06,  1.20it/s]
1|19587|Loss: 0.8518558144569397:  76%|███████▌  | 19586/25880 [4:00:29<1:27:06,  1.20it/s]
1|19587|Loss: 0.8518558144569397:  76%|███████▌  | 19587/25880 [4:00:29<1:25:18,  1.23it/s]
1|19588|Loss: 0.6698147654533386:  76%|███████▌  | 19587/25880 [4:00:29<1:25:18,  1.23it/s]
1|19588|Loss: 0.6698147654533386:  76%|███████▌  | 19588/25880 [4:00:30<1:24:13,  1.25it/s]
1|19589|Loss: 0.7715885043144226:  76%|███████▌  | 19588/25880 [4:00:30<1:24:13,  1.25it/s]
1|19589|Loss: 0.7715885043144226:  76%|███████▌  | 19589/25880 [4:00:30<1:22:31,  1.27it/s]
1|19590|Loss: 0.8613902926445007:  76%|███████▌  | 19589/25880 [4:00:31<1:22:31,  1.27it/s]
1|19590|Loss: 0.8613902926445007:  76%|███████▌  | 19590/25880 [4:00:31<1:20:53,  1.30it/s]
1|19591|Loss: 0.8562330603599548:  76%|███████▌  | 19590/25880 [4:00:32<1:20:53,  1.30it/s]
1|19591|Loss: 0.8562330603599548:  76%|███████▌  | 19591/25880 [4:00:32<1:22:19,  1.27it/s]
1|19592|Loss: 0.9031416177749634:  76%|███████▌  | 19591/25880 [4:00:32<1:22:19,  1.27it/s]
1|19592|Loss: 0.9031416177749634:  76%|███████▌  | 19592/25880 [4:00:33<1:18:46,  1.33it/s]
1|19593|Loss: 0.9175775647163391:  76%|███████▌  | 19592/25880 [4:00:33<1:18:46,  1.33it/s]
1|19593|Loss: 0.9175775647163391:  76%|███████▌  | 19593/25880 [4:00:33<1:15:08,  1.39it/s]
1|19594|Loss: 0.815324068069458:  76%|███████▌  | 19593/25880 [4:00:34<1:15:08,  1.39it/s] 
1|19594|Loss: 0.815324068069458:  76%|███████▌  | 19594/25880 [4:00:34<1:14:13,  1.41it/s]
1|19595|Loss: 0.8145185112953186:  76%|███████▌  | 19594/25880 [4:00:34<1:14:13,  1.41it/s]
1|19595|Loss: 0.8145185112953186:  76%|███████▌  | 19595/25880 [4:00:35<1:12:22,  1.45it/s]
1|19596|Loss: 0.8863359689712524:  76%|███████▌  | 19595/25880 [4:00:35<1:12:22,  1.45it/s]
1|19596|Loss: 0.8863359689712524:  76%|███████▌  | 19596/25880 [4:00:35<1:15:36,  1.39it/s]
1|19597|Loss: 0.7798940539360046:  76%|███████▌  | 19596/25880 [4:00:36<1:15:36,  1.39it/s]
1|19597|Loss: 0.7798940539360046:  76%|███████���  | 19597/25880 [4:00:36<1:16:34,  1.37it/s]
1|19598|Loss: 0.8073948621749878:  76%|███████▌  | 19597/25880 [4:00:37<1:16:34,  1.37it/s]
1|19598|Loss: 0.8073948621749878:  76%|███████▌  | 19598/25880 [4:00:37<1:19:44,  1.31it/s]
1|19599|Loss: 0.9759396314620972:  76%|███████▌  | 19598/25880 [4:00:38<1:19:44,  1.31it/s]
1|19599|Loss: 0.9759396314620972:  76%|███████▌  | 19599/25880 [4:00:38<1:22:03,  1.28it/s]
1|19600|Loss: 0.8792751431465149:  76%|███████▌  | 19599/25880 [4:00:38<1:22:03,  1.28it/s]
1|19600|Loss: 0.8792751431465149:  76%|███████▌  | 19600/25880 [4:00:39<1:23:22,  1.26it/s]
1|19601|Loss: 0.7292645573616028:  76%|███████▌  | 19600/25880 [4:00:39<1:23:22,  1.26it/s]
1|19601|Loss: 0.7292645573616028:  76%|███████▌  | 19601/25880 [4:00:39<1:22:02,  1.28it/s]
1|19602|Loss: 0.9988719820976257:  76%|███████▌  | 19601/25880 [4:00:40<1:22:02,  1.28it/s]
1|19602|Loss: 0.9988719820976257:  76%|███████▌  | 19602/25880 [4:00:40<1:20:25,  1.30it/s]
1|19603|Loss: 0.8198038339614868:  76%|███████▌  | 19602/25880 [4:00:41<1:20:25,  1.30it/s]
1|19603|Loss: 0.8198038339614868:  76%|███████▌  | 19603/25880 [4:00:41<1:22:15,  1.27it/s]
1|19604|Loss: 0.7358077168464661:  76%|███████▌  | 19603/25880 [4:00:42<1:22:15,  1.27it/s]
1|19604|Loss: 0.7358077168464661:  76%|███████▌  | 19604/25880 [4:00:42<1:26:05,  1.22it/s]
1|19605|Loss: 0.647628903388977:  76%|███████▌  | 19604/25880 [4:00:42<1:26:05,  1.22it/s] 
1|19605|Loss: 0.647628903388977:  76%|███████▌  | 19605/25880 [4:00:43<1:20:30,  1.30it/s]
1|19606|Loss: 0.8914307951927185:  76%|███████▌  | 19605/25880 [4:00:43<1:20:30,  1.30it/s]
1|19606|Loss: 0.8914307951927185:  76%|███████▌  | 19606/25880 [4:00:43<1:15:45,  1.38it/s]
1|19607|Loss: 0.866116464138031:  76%|███████▌  | 19606/25880 [4:00:44<1:15:45,  1.38it/s] 
1|19607|Loss: 0.866116464138031:  76%|███████▌  | 19607/25880 [4:00:44<1:14:43,  1.40it/s]
1|19608|Loss: 0.618985116481781:  76%|███████▌  | 19607/25880 [4:00:44<1:14:43,  1.40it/s]
1|19608|Loss: 0.618985116481781:  76%|███████▌  | 19608/25880 [4:00:45<1:21:25,  1.28it/s]
1|19609|Loss: 0.870447039604187:  76%|███████▌  | 19608/25880 [4:00:45<1:21:25,  1.28it/s]
1|19609|Loss: 0.870447039604187:  76%|███████▌  | 19609/25880 [4:00:46<1:22:25,  1.27it/s]
1|19610|Loss: 0.8244746327400208:  76%|███████▌  | 19609/25880 [4:00:46<1:22:25,  1.27it/s]
1|19610|Loss: 0.8244746327400208:  76%|███████▌  | 19610/25880 [4:00:47<1:24:21,  1.24it/s]
1|19611|Loss: 0.8771262168884277:  76%|███████▌  | 19610/25880 [4:00:47<1:24:21,  1.24it/s]
1|19611|Loss: 0.8771262168884277:  76%|███████▌  | 19611/25880 [4:00:47<1:22:25,  1.27it/s]
1|19612|Loss: 0.8584492206573486:  76%|███████▌  | 19611/25880 [4:00:48<1:22:25,  1.27it/s]
1|19612|Loss: 0.8584492206573486:  76%|███████▌  | 19612/25880 [4:00:48<1:22:12,  1.27it/s]
1|19613|Loss: 0.7531401515007019:  76%|███████▌  | 19612/25880 [4:00:48<1:22:12,  1.27it/s]
1|19613|Loss: 0.7531401515007019:  76%|███████▌  | 19613/25880 [4:00:49<1:24:29,  1.24it/s]
1|19614|Loss: 0.8852032423019409:  76%|███████▌  | 19613/25880 [4:00:49<1:24:29,  1.24it/s]
1|19614|Loss: 0.8852032423019409:  76%|███████▌  | 19614/25880 [4:00:50<1:24:50,  1.23it/s]
1|19615|Loss: 0.8248623013496399:  76%|███████▌  | 19614/25880 [4:00:50<1:24:50,  1.23it/s]
1|19615|Loss: 0.8248623013496399:  76%|███████▌  | 19615/25880 [4:00:50<1:22:46,  1.26it/s]
1|19616|Loss: 0.9189407825469971:  76%|███████▌  | 19615/25880 [4:00:51<1:22:46,  1.26it/s]
1|19616|Loss: 0.9189407825469971:  76%|███████▌  | 19616/25880 [4:00:51<1:26:30,  1.21it/s]
1|19617|Loss: 0.764754593372345:  76%|███████▌  | 19616/25880 [4:00:52<1:26:30,  1.21it/s] 
1|19617|Loss: 0.764754593372345:  76%|███████▌  | 19617/25880 [4:00:52<1:26:21,  1.21it/s]
1|19618|Loss: 0.8446294665336609:  76%|███████▌  | 19617/25880 [4:00:53<1:26:21,  1.21it/s]
1|19618|Loss: 0.8446294665336609:  76%|███████▌  | 19618/25880 [4:00:53<1:21:02,  1.29it/s]
1|19619|Loss: 0.8103068470954895:  76%|███████▌  | 19618/25880 [4:00:53<1:21:02,  1.29it/s]
1|19619|Loss: 0.8103068470954895:  76%|███████▌  | 19619/25880 [4:00:54<1:19:00,  1.32it/s]
1|19620|Loss: 0.7887503504753113:  76%|███████▌  | 19619/25880 [4:00:54<1:19:00,  1.32it/s]
1|19620|Loss: 0.7887503504753113:  76%|███████▌  | 19620/25880 [4:00:54<1:12:57,  1.43it/s]
1|19621|Loss: 0.7796609997749329:  76%|███████▌  | 19620/25880 [4:00:55<1:12:57,  1.43it/s]
1|19621|Loss: 0.7796609997749329:  76%|███████▌  | 19621/25880 [4:00:55<1:16:17,  1.37it/s]
1|19622|Loss: 0.9177233576774597:  76%|███████▌  | 19621/25880 [4:00:55<1:16:17,  1.37it/s]
1|19622|Loss: 0.9177233576774597:  76%|███████▌  | 19622/25880 [4:00:56<1:14:23,  1.40it/s]
1|19623|Loss: 0.8229913711547852:  76%|███████▌  | 19622/25880 [4:00:56<1:14:23,  1.40it/s]
1|19623|Loss: 0.8229913711547852:  76%|███████▌  | 19623/25880 [4:00:56<1:08:39,  1.52it/s]
1|19624|Loss: 0.8766208291053772:  76%|███████▌  | 19623/25880 [4:00:56<1:08:39,  1.52it/s]
1|19624|Loss: 0.8766208291053772:  76%|███████▌  | 19624/25880 [4:00:57<1:07:02,  1.56it/s]
1|19625|Loss: 0.7547496557235718:  76%|███████▌  | 19624/25880 [4:00:57<1:07:02,  1.56it/s]
1|19625|Loss: 0.7547496557235718:  76%|███████▌  | 19625/25880 [4:00:57<1:06:49,  1.56it/s]
1|19626|Loss: 0.8941062092781067:  76%|███████▌  | 19625/25880 [4:00:58<1:06:49,  1.56it/s]
1|19626|Loss: 0.8941062092781067:  76%|███████▌  | 19626/25880 [4:00:58<1:06:09,  1.58it/s]
1|19627|Loss: 0.8488898277282715:  76%|███████▌  | 19626/25880 [4:00:58<1:06:09,  1.58it/s]
1|19627|Loss: 0.8488898277282715:  76%|███████▌  | 19627/25880 [4:00:59<1:10:23,  1.48it/s]
1|19628|Loss: 0.9811698198318481:  76%|███████▌  | 19627/25880 [4:00:59<1:10:23,  1.48it/s]
1|19628|Loss: 0.9811698198318481:  76%|███████▌  | 19628/25880 [4:00:59<1:09:08,  1.51it/s]
1|19629|Loss: 0.8031008839607239:  76%|███████▌  | 19628/25880 [4:01:00<1:09:08,  1.51it/s]
1|19629|Loss: 0.8031008839607239:  76%|███████▌  | 19629/25880 [4:01:00<1:09:36,  1.50it/s]
1|19630|Loss: 0.7324265241622925:  76%|███████▌  | 19629/25880 [4:01:01<1:09:36,  1.50it/s]
1|19630|Loss: 0.7324265241622925:  76%|███████▌  | 19630/25880 [4:01:01<1:16:06,  1.37it/s]
1|19631|Loss: 0.8413489460945129:  76%|███████▌  | 19630/25880 [4:01:01<1:16:06,  1.37it/s]
1|19631|Loss: 0.8413489460945129:  76%|███████▌  | 19631/25880 [4:01:02<1:17:37,  1.34it/s]
1|19632|Loss: 0.8755468726158142:  76%|███████▌  | 19631/25880 [4:01:02<1:17:37,  1.34it/s]
1|19632|Loss: 0.8755468726158142:  76%|███████▌  | 19632/25880 [4:01:02<1:14:34,  1.40it/s]
1|19633|Loss: 0.884156346321106:  76%|███████▌  | 19632/25880 [4:01:03<1:14:34,  1.40it/s] 
1|19633|Loss: 0.884156346321106:  76%|███████▌  | 19633/25880 [4:01:03<1:12:09,  1.44it/s]
1|19634|Loss: 0.9037361741065979:  76%|███████▌  | 19633/25880 [4:01:03<1:12:09,  1.44it/s]
1|19634|Loss: 0.9037361741065979:  76%|███████▌  | 19634/25880 [4:01:04<1:13:01,  1.43it/s]
1|19635|Loss: 0.7370149493217468:  76%|███████▌  | 19634/25880 [4:01:04<1:13:01,  1.43it/s]
1|19635|Loss: 0.7370149493217468:  76%|███████▌  | 19635/25880 [4:01:05<1:16:27,  1.36it/s]
1|19636|Loss: 0.6383291482925415:  76%|███████▌  | 19635/25880 [4:01:05<1:16:27,  1.36it/s]
1|19636|Loss: 0.6383291482925415:  76%|███████▌  | 19636/25880 [4:01:05<1:14:42,  1.39it/s]
1|19637|Loss: 0.8074455857276917:  76%|███████▌  | 19636/25880 [4:01:06<1:14:42,  1.39it/s]
1|19637|Loss: 0.8074455857276917:  76%|███████▌  | 19637/25880 [4:01:06<1:14:59,  1.39it/s]
1|19638|Loss: 0.8085957169532776:  76%|███████▌  | 19637/25880 [4:01:06<1:14:59,  1.39it/s]
1|19638|Loss: 0.8085957169532776:  76%|███████▌  | 19638/25880 [4:01:07<1:19:23,  1.31it/s]
1|19639|Loss: 0.9667110443115234:  76%|███████▌  | 19638/25880 [4:01:07<1:19:23,  1.31it/s]
1|19639|Loss: 0.9667110443115234:  76%|███████▌  | 19639/25880 [4:01:08<1:19:53,  1.30it/s]
1|19640|Loss: 0.8926768898963928:  76%|███████▌  | 19639/25880 [4:01:08<1:19:53,  1.30it/s]
1|19640|Loss: 0.8926768898963928:  76%|███████▌  | 19640/25880 [4:01:08<1:21:56,  1.27it/s]
1|19641|Loss: 0.949975848197937:  76%|███████▌  | 19640/25880 [4:01:09<1:21:56,  1.27it/s] 
1|19641|Loss: 0.949975848197937:  76%|███████▌  | 19641/25880 [4:01:09<1:18:47,  1.32it/s]
1|19642|Loss: 0.8173635005950928:  76%|███████▌  | 19641/25880 [4:01:10<1:18:47,  1.32it/s]
1|19642|Loss: 0.8173635005950928:  76%|███████▌  | 19642/25880 [4:01:10<1:17:34,  1.34it/s]
1|19643|Loss: 0.8166812658309937:  76%|███████▌  | 19642/25880 [4:01:10<1:17:34,  1.34it/s]
1|19643|Loss: 0.8166812658309937:  76%|███████▌  | 19643/25880 [4:01:11<1:16:25,  1.36it/s]
1|19644|Loss: 0.7098355889320374:  76%|███████▌  | 19643/25880 [4:01:11<1:16:25,  1.36it/s]
1|19644|Loss: 0.7098355889320374:  76%|███████▌  | 19644/25880 [4:01:11<1:15:22,  1.38it/s]
1|19645|Loss: 0.8595434427261353:  76%|███��███▌  | 19644/25880 [4:01:12<1:15:22,  1.38it/s]
1|19645|Loss: 0.8595434427261353:  76%|███████▌  | 19645/25880 [4:01:12<1:12:26,  1.43it/s]
1|19646|Loss: 0.9015050530433655:  76%|███████▌  | 19645/25880 [4:01:12<1:12:26,  1.43it/s]
1|19646|Loss: 0.9015050530433655:  76%|███████▌  | 19646/25880 [4:01:13<1:12:43,  1.43it/s]
1|19647|Loss: 0.8137199878692627:  76%|███████▌  | 19646/25880 [4:01:13<1:12:43,  1.43it/s]
1|19647|Loss: 0.8137199878692627:  76%|███████▌  | 19647/25880 [4:01:13<1:11:17,  1.46it/s]
1|19648|Loss: 0.728140652179718:  76%|███████▌  | 19647/25880 [4:01:14<1:11:17,  1.46it/s] 
1|19648|Loss: 0.728140652179718:  76%|███████▌  | 19648/25880 [4:01:14<1:09:10,  1.50it/s]
1|19649|Loss: 0.8900765180587769:  76%|███████▌  | 19648/25880 [4:01:14<1:09:10,  1.50it/s]
1|19649|Loss: 0.8900765180587769:  76%|███████▌  | 19649/25880 [4:01:14<1:03:40,  1.63it/s]
1|19650|Loss: 0.7704746723175049:  76%|███████▌  | 19649/25880 [4:01:15<1:03:40,  1.63it/s]
1|19650|Loss: 0.7704746723175049:  76%|███████▌  | 19650/25880 [4:01:15<1:03:14,  1.64it/s]
1|19651|Loss: 0.8987578749656677:  76%|███████▌  | 19650/25880 [4:01:15<1:03:14,  1.64it/s]
1|19651|Loss: 0.8987578749656677:  76%|███████▌  | 19651/25880 [4:01:16<1:03:40,  1.63it/s]
1|19652|Loss: 0.800118625164032:  76%|███████▌  | 19651/25880 [4:01:16<1:03:40,  1.63it/s] 
1|19652|Loss: 0.800118625164032:  76%|███████▌  | 19652/25880 [4:01:16<1:06:49,  1.55it/s]
1|19653|Loss: 0.9294335246086121:  76%|███████▌  | 19652/25880 [4:01:17<1:06:49,  1.55it/s]
1|19653|Loss: 0.9294335246086121:  76%|███████▌  | 19653/25880 [4:01:17<1:07:33,  1.54it/s]
1|19654|Loss: 1.0119117498397827:  76%|███████▌  | 19653/25880 [4:01:17<1:07:33,  1.54it/s]
1|19654|Loss: 1.0119117498397827:  76%|███████▌  | 19654/25880 [4:01:18<1:08:43,  1.51it/s]
1|19655|Loss: 0.7958749532699585:  76%|███████▌  | 19654/25880 [4:01:18<1:08:43,  1.51it/s]
1|19655|Loss: 0.7958749532699585:  76%|███████▌  | 19655/25880 [4:01:18<1:05:30,  1.58it/s]
1|19656|Loss: 0.9329892992973328:  76%|███████▌  | 19655/25880 [4:01:19<1:05:30,  1.58it/s]
1|19656|Loss: 0.9329892992973328:  76%|███████▌  | 19656/25880 [4:01:19<1:09:33,  1.49it/s]
1|19657|Loss: 0.8074183464050293:  76%|███████▌  | 19656/25880 [4:01:19<1:09:33,  1.49it/s]
1|19657|Loss: 0.8074183464050293:  76%|███████▌  | 19657/25880 [4:01:20<1:09:05,  1.50it/s]
1|19658|Loss: 0.9189943671226501:  76%|███████▌  | 19657/25880 [4:01:20<1:09:05,  1.50it/s]
1|19658|Loss: 0.9189943671226501:  76%|███████▌  | 19658/25880 [4:01:20<1:07:31,  1.54it/s]
1|19659|Loss: 0.8670773506164551:  76%|███████▌  | 19658/25880 [4:01:21<1:07:31,  1.54it/s]
1|19659|Loss: 0.8670773506164551:  76%|███████▌  | 19659/25880 [4:01:21<1:09:28,  1.49it/s]
1|19660|Loss: 0.8418393731117249:  76%|███████▌  | 19659/25880 [4:01:21<1:09:28,  1.49it/s]
1|19660|Loss: 0.8418393731117249:  76%|███████▌  | 19660/25880 [4:01:22<1:10:38,  1.47it/s]
1|19661|Loss: 0.8186421990394592:  76%|███████▌  | 19660/25880 [4:01:22<1:10:38,  1.47it/s]
1|19661|Loss: 0.8186421990394592:  76%|███████▌  | 19661/25880 [4:01:22<1:12:22,  1.43it/s]
1|19662|Loss: 0.7386054396629333:  76%|███████▌  | 19661/25880 [4:01:23<1:12:22,  1.43it/s]
1|19662|Loss: 0.7386054396629333:  76%|███████▌  | 19662/25880 [4:01:23<1:13:55,  1.40it/s]
1|19663|Loss: 0.8050140738487244:  76%|███████▌  | 19662/25880 [4:01:24<1:13:55,  1.40it/s]
1|19663|Loss: 0.8050140738487244:  76%|███████▌  | 19663/25880 [4:01:24<1:11:51,  1.44it/s]
1|19664|Loss: 0.8677037358283997:  76%|███████▌  | 19663/25880 [4:01:24<1:11:51,  1.44it/s]
1|19664|Loss: 0.8677037358283997:  76%|███████▌  | 19664/25880 [4:01:25<1:14:53,  1.38it/s]
1|19665|Loss: 0.7691978812217712:  76%|███████▌  | 19664/25880 [4:01:25<1:14:53,  1.38it/s]
1|19665|Loss: 0.7691978812217712:  76%|███████▌  | 19665/25880 [4:01:25<1:18:15,  1.32it/s]
1|19666|Loss: 0.8263781070709229:  76%|███████▌  | 19665/25880 [4:01:26<1:18:15,  1.32it/s]
1|19666|Loss: 0.8263781070709229:  76%|███████▌  | 19666/25880 [4:01:26<1:18:21,  1.32it/s]
1|19667|Loss: 0.8324670791625977:  76%|███████▌  | 19666/25880 [4:01:27<1:18:21,  1.32it/s]
1|19667|Loss: 0.8324670791625977:  76%|███████▌  | 19667/25880 [4:01:27<1:17:43,  1.33it/s]
1|19668|Loss: 0.9866023063659668:  76%|███████▌  | 19667/25880 [4:01:27<1:17:43,  1.33it/s]
1|19668|Loss: 0.9866023063659668:  76%|███████▌  | 19668/25880 [4:01:28<1:21:50,  1.27it/s]
1|19669|Loss: 0.8991295099258423:  76%|███████▌  | 19668/25880 [4:01:28<1:21:50,  1.27it/s]
1|19669|Loss: 0.8991295099258423:  76%|███████▌  | 19669/25880 [4:01:29<1:18:49,  1.31it/s]
1|19670|Loss: 0.8144064545631409:  76%|███████▌  | 19669/25880 [4:01:29<1:18:49,  1.31it/s]
1|19670|Loss: 0.8144064545631409:  76%|███████▌  | 19670/25880 [4:01:29<1:17:44,  1.33it/s]
1|19671|Loss: 0.8711481094360352:  76%|███████▌  | 19670/25880 [4:01:30<1:17:44,  1.33it/s]
1|19671|Loss: 0.8711481094360352:  76%|███████▌  | 19671/25880 [4:01:30<1:17:43,  1.33it/s]
1|19672|Loss: 0.7931851744651794:  76%|███████▌  | 19671/25880 [4:01:30<1:17:43,  1.33it/s]
1|19672|Loss: 0.7931851744651794:  76%|███████▌  | 19672/25880 [4:01:31<1:14:25,  1.39it/s]
1|19673|Loss: 0.9080672860145569:  76%|███████▌  | 19672/25880 [4:01:31<1:14:25,  1.39it/s]
1|19673|Loss: 0.9080672860145569:  76%|███████▌  | 19673/25880 [4:01:31<1:11:12,  1.45it/s]
1|19674|Loss: 0.8617760539054871:  76%|███████▌  | 19673/25880 [4:01:32<1:11:12,  1.45it/s]
1|19674|Loss: 0.8617760539054871:  76%|███████▌  | 19674/25880 [4:01:32<1:08:10,  1.52it/s]
1|19675|Loss: 0.838081955909729:  76%|███████▌  | 19674/25880 [4:01:32<1:08:10,  1.52it/s] 
1|19675|Loss: 0.838081955909729:  76%|███████▌  | 19675/25880 [4:01:33<1:08:38,  1.51it/s]
1|19676|Loss: 0.750730574131012:  76%|███████▌  | 19675/25880 [4:01:33<1:08:38,  1.51it/s]
1|19676|Loss: 0.750730574131012:  76%|███████▌  | 19676/25880 [4:01:33<1:09:29,  1.49it/s]
1|19677|Loss: 0.809502899646759:  76%|███████▌  | 19676/25880 [4:01:34<1:09:29,  1.49it/s]
1|19677|Loss: 0.809502899646759:  76%|███████▌  | 19677/25880 [4:01:34<1:15:24,  1.37it/s]
1|19678|Loss: 0.8286519050598145:  76%|███████▌  | 19677/25880 [4:01:34<1:15:24,  1.37it/s]
1|19678|Loss: 0.8286519050598145:  76%|███████▌  | 19678/25880 [4:01:35<1:15:49,  1.36it/s]
1|19679|Loss: 0.6916899085044861:  76%|███████▌  | 19678/25880 [4:01:35<1:15:49,  1.36it/s]
1|19679|Loss: 0.6916899085044861:  76%|███████▌  | 19679/25880 [4:01:35<1:11:54,  1.44it/s]
1|19680|Loss: 0.9147747755050659:  76%|███████▌  | 19679/25880 [4:01:36<1:11:54,  1.44it/s]
1|19680|Loss: 0.9147747755050659:  76%|███████▌  | 19680/25880 [4:01:36<1:15:03,  1.38it/s]
1|19681|Loss: 0.8924816846847534:  76%|███████▌  | 19680/25880 [4:01:37<1:15:03,  1.38it/s]
1|19681|Loss: 0.8924816846847534:  76%|███████▌  | 19681/25880 [4:01:37<1:13:15,  1.41it/s]
1|19682|Loss: 0.8926544785499573:  76%|███████▌  | 19681/25880 [4:01:37<1:13:15,  1.41it/s]
1|19682|Loss: 0.8926544785499573:  76%|███████▌  | 19682/25880 [4:01:37<1:10:21,  1.47it/s]
1|19683|Loss: 0.8088622093200684:  76%|███████▌  | 19682/25880 [4:01:38<1:10:21,  1.47it/s]
1|19683|Loss: 0.8088622093200684:  76%|███████▌  | 19683/25880 [4:01:38<1:08:21,  1.51it/s]
1|19684|Loss: 0.7368650436401367:  76%|███████▌  | 19683/25880 [4:01:38<1:08:21,  1.51it/s]
1|19684|Loss: 0.7368650436401367:  76%|███████▌  | 19684/25880 [4:01:39<1:07:35,  1.53it/s]
1|19685|Loss: 0.8022862076759338:  76%|███████▌  | 19684/25880 [4:01:39<1:07:35,  1.53it/s]
1|19685|Loss: 0.8022862076759338:  76%|███████▌  | 19685/25880 [4:01:39<1:09:24,  1.49it/s]
1|19686|Loss: 0.9132238030433655:  76%|███████▌  | 19685/25880 [4:01:40<1:09:24,  1.49it/s]
1|19686|Loss: 0.9132238030433655:  76%|███████▌  | 19686/25880 [4:01:40<1:08:19,  1.51it/s]
1|19687|Loss: 0.9582235217094421:  76%|███████▌  | 19686/25880 [4:01:40<1:08:19,  1.51it/s]
1|19687|Loss: 0.9582235217094421:  76%|███████▌  | 19687/25880 [4:01:41<1:10:06,  1.47it/s]
1|19688|Loss: 0.7951650619506836:  76%|███████▌  | 19687/25880 [4:01:41<1:10:06,  1.47it/s]
1|19688|Loss: 0.7951650619506836:  76%|███████▌  | 19688/25880 [4:01:42<1:15:00,  1.38it/s]
1|19689|Loss: 0.7656227946281433:  76%|███████▌  | 19688/25880 [4:01:42<1:15:00,  1.38it/s]
1|19689|Loss: 0.7656227946281433:  76%|███████▌  | 19689/25880 [4:01:43<1:20:47,  1.28it/s]
1|19690|Loss: 0.7475629448890686:  76%|███████▌  | 19689/25880 [4:01:43<1:20:47,  1.28it/s]
1|19690|Loss: 0.7475629448890686:  76%|███████▌  | 19690/25880 [4:01:43<1:20:33,  1.28it/s]
1|19691|Loss: 0.7917566895484924:  76%|███████▌  | 19690/25880 [4:01:44<1:20:33,  1.28it/s]
1|19691|Loss: 0.7917566895484924:  76%|███████▌  | 19691/25880 [4:01:44<1:30:42,  1.14it/s]
1|19692|Loss: 0.9403822422027588:  76%|███████▌  | 19691/25880 [4:01:45<1:30:42,  1.14it/s]
1|19692|Loss: 0.9403822422027588:  76%|███████▌  | 19692/25880 [4:01:45<1:25:52,  1.20it/s]
1|19693|Loss: 0.8140441179275513:  76%|███████▌  | 19692/25880 [4:01:46<1:25:52,  1.20it/s]
1|19693|Loss: 0.8140441179275513:  76%|███████▌  | 19693/25880 [4:01:46<1:21:02,  1.27it/s]
1|19694|Loss: 0.8902842998504639:  76%|███████▌  | 19693/25880 [4:01:46<1:21:02,  1.27it/s]
1|19694|Loss: 0.8902842998504639:  76%|███████▌  | 19694/25880 [4:01:47<1:19:16,  1.30it/s]
1|19695|Loss: 0.7502332329750061:  76%|███████▌  | 19694/25880 [4:01:47<1:19:16,  1.30it/s]
1|19695|Loss: 0.7502332329750061:  76%|███████▌  | 19695/25880 [4:01:47<1:15:56,  1.36it/s]
1|19696|Loss: 0.7462069988250732:  76%|███████▌  | 19695/25880 [4:01:48<1:15:56,  1.36it/s]
1|19696|Loss: 0.7462069988250732:  76%|███████▌  | 19696/25880 [4:01:48<1:18:05,  1.32it/s]
1|19697|Loss: 0.9959121942520142:  76%|███████▌  | 19696/25880 [4:01:48<1:18:05,  1.32it/s]
1|19697|Loss: 0.9959121942520142:  76%|███████▌  | 19697/25880 [4:01:49<1:18:32,  1.31it/s]
1|19698|Loss: 0.9099341630935669:  76%|███████▌  | 19697/25880 [4:01:49<1:18:32,  1.31it/s]
1|19698|Loss: 0.9099341630935669:  76%|███████▌  | 19698/25880 [4:01:50<1:18:02,  1.32it/s]
1|19699|Loss: 0.844398558139801:  76%|███████▌  | 19698/25880 [4:01:50<1:18:02,  1.32it/s] 
1|19699|Loss: 0.844398558139801:  76%|███████▌  | 19699/25880 [4:01:50<1:15:07,  1.37it/s]
1|19700|Loss: 0.8444890379905701:  76%|███████▌  | 19699/25880 [4:01:51<1:15:07,  1.37it/s]
1|19700|Loss: 0.8444890379905701:  76%|███████▌  | 19700/25880 [4:01:51<1:14:53,  1.38it/s]
1|19701|Loss: 0.8959758281707764:  76%|███████▌  | 19700/25880 [4:01:51<1:14:53,  1.38it/s]
1|19701|Loss: 0.8959758281707764:  76%|███████▌  | 19701/25880 [4:01:52<1:17:00,  1.34it/s]
1|19702|Loss: 0.8657654523849487:  76%|███████▌  | 19701/25880 [4:01:52<1:17:00,  1.34it/s]
1|19702|Loss: 0.8657654523849487:  76%|███████▌  | 19702/25880 [4:01:52<1:16:51,  1.34it/s]
1|19703|Loss: 0.7763761281967163:  76%|███████▌  | 19702/25880 [4:01:53<1:16:51,  1.34it/s]
1|19703|Loss: 0.7763761281967163:  76%|███████▌  | 19703/25880 [4:01:53<1:17:51,  1.32it/s]
1|19704|Loss: 0.8226568698883057:  76%|███████▌  | 19703/25880 [4:01:54<1:17:51,  1.32it/s]
1|19704|Loss: 0.8226568698883057:  76%|███████▌  | 19704/25880 [4:01:54<1:19:33,  1.29it/s]
1|19705|Loss: 0.9346959590911865:  76%|███████▌  | 19704/25880 [4:01:54<1:19:33,  1.29it/s]
1|19705|Loss: 0.9346959590911865:  76%|███████▌  | 19705/25880 [4:01:55<1:11:48,  1.43it/s]
1|19706|Loss: 0.8863260746002197:  76%|███████▌  | 19705/25880 [4:01:55<1:11:48,  1.43it/s]
1|19706|Loss: 0.8863260746002197:  76%|███████▌  | 19706/25880 [4:01:55<1:10:36,  1.46it/s]
1|19707|Loss: 0.8269885182380676:  76%|███████▌  | 19706/25880 [4:01:56<1:10:36,  1.46it/s]
1|19707|Loss: 0.8269885182380676:  76%|███████▌  | 19707/25880 [4:01:56<1:11:51,  1.43it/s]
1|19708|Loss: 0.8452390432357788:  76%|███████▌  | 19707/25880 [4:01:56<1:11:51,  1.43it/s]
1|19708|Loss: 0.8452390432357788:  76%|███████▌  | 19708/25880 [4:01:57<1:07:51,  1.52it/s]
1|19709|Loss: 0.8988007307052612:  76%|███████▌  | 19708/25880 [4:01:57<1:07:51,  1.52it/s]
1|19709|Loss: 0.8988007307052612:  76%|███████▌  | 19709/25880 [4:01:57<1:10:44,  1.45it/s]
1|19710|Loss: 0.7043249607086182:  76%|███████▌  | 19709/25880 [4:01:58<1:10:44,  1.45it/s]
1|19710|Loss: 0.7043249607086182:  76%|███████▌  | 19710/25880 [4:01:58<1:17:10,  1.33it/s]
1|19711|Loss: 0.7879610061645508:  76%|███████▌  | 19710/25880 [4:01:59<1:17:10,  1.33it/s]
1|19711|Loss: 0.7879610061645508:  76%|███████▌  | 19711/25880 [4:01:59<1:13:32,  1.40it/s]
1|19712|Loss: 0.7115179300308228:  76%|███████▌  | 19711/25880 [4:01:59<1:13:32,  1.40it/s]
1|19712|Loss: 0.7115179300308228:  76%|███████▌  | 19712/25880 [4:01:59<1:07:30,  1.52it/s]
1|19713|Loss: 0.9620245099067688:  76%|███████▌  | 19712/25880 [4:02:00<1:07:30,  1.52it/s]
1|19713|Loss: 0.9620245099067688:  76%|███████▌  | 19713/25880 [4:02:00<1:09:49,  1.47it/s]
1|19714|Loss: 0.9018087387084961:  76%|███████▌  | 19713/25880 [4:02:00<1:09:49,  1.47it/s]
1|19714|Loss: 0.9018087387084961:  76%|███████▌  | 19714/25880 [4:02:01<1:09:49,  1.47it/s]
1|19715|Loss: 0.7816349864006042:  76%|███████▌  | 19714/25880 [4:02:01<1:09:49,  1.47it/s]
1|19715|Loss: 0.7816349864006042:  76%|███████▌  | 19715/25880 [4:02:01<1:04:11,  1.60it/s]
1|19716|Loss: 0.8365188837051392:  76%|███████▌  | 19715/25880 [4:02:02<1:04:11,  1.60it/s]
1|19716|Loss: 0.8365188837051392:  76%|███████▌  | 19716/25880 [4:02:02<1:05:47,  1.56it/s]
1|19717|Loss: 0.8193082809448242:  76%|███████▌  | 19716/25880 [4:02:02<1:05:47,  1.56it/s]
1|19717|Loss: 0.8193082809448242:  76%|███████▌  | 19717/25880 [4:02:03<1:09:16,  1.48it/s]
1|19718|Loss: 0.790450930595398:  76%|███████▌  | 19717/25880 [4:02:03<1:09:16,  1.48it/s] 
1|19718|Loss: 0.790450930595398:  76%|███████▌  | 19718/25880 [4:02:03<1:11:43,  1.43it/s]
1|19719|Loss: 0.8197034001350403:  76%|███████▌  | 19718/25880 [4:02:04<1:11:43,  1.43it/s]
1|19719|Loss: 0.8197034001350403:  76%|███████▌  | 19719/25880 [4:02:04<1:10:21,  1.46it/s]
1|19720|Loss: 0.9068822860717773:  76%|███████▌  | 19719/25880 [4:02:05<1:10:21,  1.46it/s]
1|19720|Loss: 0.9068822860717773:  76%|███████▌  | 19720/25880 [4:02:05<1:13:04,  1.41it/s]
1|19721|Loss: 0.8663214445114136:  76%|███████▌  | 19720/25880 [4:02:05<1:13:04,  1.41it/s]
1|19721|Loss: 0.8663214445114136:  76%|███████▌  | 19721/25880 [4:02:06<1:16:42,  1.34it/s]
1|19722|Loss: 0.722187876701355:  76%|███████▌  | 19721/25880 [4:02:06<1:16:42,  1.34it/s] 
1|19722|Loss: 0.722187876701355:  76%|███████▌  | 19722/25880 [4:02:07<1:19:16,  1.29it/s]
1|19723|Loss: 0.7677433490753174:  76%|███████▌  | 19722/25880 [4:02:07<1:19:16,  1.29it/s]
1|19723|Loss: 0.7677433490753174:  76%|███████▌  | 19723/25880 [4:02:07<1:17:45,  1.32it/s]
1|19724|Loss: 0.8783002495765686:  76%|███████▌  | 19723/25880 [4:02:08<1:17:45,  1.32it/s]
1|19724|Loss: 0.8783002495765686:  76%|███████▌  | 19724/25880 [4:02:08<1:14:27,  1.38it/s]
1|19725|Loss: 0.761680006980896:  76%|███████▌  | 19724/25880 [4:02:08<1:14:27,  1.38it/s] 
1|19725|Loss: 0.761680006980896:  76%|███████▌  | 19725/25880 [4:02:09<1:17:52,  1.32it/s]
1|19726|Loss: 0.7199612855911255:  76%|███████▌  | 19725/25880 [4:02:09<1:17:52,  1.32it/s]
1|19726|Loss: 0.7199612855911255:  76%|███████▌  | 19726/25880 [4:02:09<1:14:16,  1.38it/s]
1|19727|Loss: 0.8555633425712585:  76%|███████▌  | 19726/25880 [4:02:10<1:14:16,  1.38it/s]
1|19727|Loss: 0.8555633425712585:  76%|███████▌  | 19727/25880 [4:02:10<1:10:14,  1.46it/s]
1|19728|Loss: 0.9131101369857788:  76%|███████▌  | 19727/25880 [4:02:10<1:10:14,  1.46it/s]
1|19728|Loss: 0.9131101369857788:  76%|███████▌  | 19728/25880 [4:02:10<1:03:57,  1.60it/s]
1|19729|Loss: 0.8830190300941467:  76%|███████▌  | 19728/25880 [4:02:11<1:03:57,  1.60it/s]
1|19729|Loss: 0.8830190300941467:  76%|███████▌  | 19729/25880 [4:02:11<1:04:44,  1.58it/s]
1|19730|Loss: 0.7947204113006592:  76%|███████▌  | 19729/25880 [4:02:12<1:04:44,  1.58it/s]
1|19730|Loss: 0.7947204113006592:  76%|███████▌  | 19730/25880 [4:02:12<1:08:59,  1.49it/s]
1|19731|Loss: 0.8954882621765137:  76%|███████▌  | 19730/25880 [4:02:12<1:08:59,  1.49it/s]
1|19731|Loss: 0.8954882621765137:  76%|███████▌  | 19731/25880 [4:02:13<1:07:39,  1.51it/s]
1|19732|Loss: 0.9023175835609436:  76%|███████▌  | 19731/25880 [4:02:13<1:07:39,  1.51it/s]
1|19732|Loss: 0.9023175835609436:  76%|███████▌  | 19732/25880 [4:02:13<1:04:40,  1.58it/s]
1|19733|Loss: 0.9547140598297119:  76%|███████▌  | 19732/25880 [4:02:13<1:04:40,  1.58it/s]
1|19733|Loss: 0.9547140598297119:  76%|███████▌  | 19733/25880 [4:02:14<1:06:42,  1.54it/s]
1|19734|Loss: 0.7729784846305847:  76%|███████▌  | 19733/25880 [4:02:14<1:06:42,  1.54it/s]
1|19734|Loss: 0.7729784846305847:  76%|███████▋  | 19734/25880 [4:02:15<1:10:37,  1.45it/s]
1|19735|Loss: 0.9742297530174255:  76%|███████▋  | 19734/25880 [4:02:15<1:10:37,  1.45it/s]
1|19735|Loss: 0.9742297530174255:  76%|███████▋  | 19735/25880 [4:02:15<1:11:43,  1.43it/s]
1|19736|Loss: 1.0687522888183594:  76%|███████▋  | 19735/25880 [4:02:16<1:11:43,  1.43it/s]
1|19736|Loss: 1.0687522888183594:  76%|███████▋  | 19736/25880 [4:02:16<1:09:29,  1.47it/s]
1|19737|Loss: 0.8503779768943787:  76%|███████▋  | 19736/25880 [4:02:16<1:09:29,  1.47it/s]
1|19737|Loss: 0.8503779768943787:  76%|███████▋  | 19737/25880 [4:02:17<1:10:23,  1.45it/s]
1|19738|Loss: 0.6791688203811646:  76%|███████▋  | 19737/25880 [4:02:17<1:10:23,  1.45it/s]
1|19738|Loss: 0.6791688203811646:  76%|███████▋  | 19738/25880 [4:02:17<1:11:28,  1.43it/s]
1|19739|Loss: 0.8264042139053345:  76%|███████▋  | 19738/25880 [4:02:18<1:11:28,  1.43it/s]
1|19739|Loss: 0.8264042139053345:  76%|███████▋  | 19739/25880 [4:02:18<1:07:00,  1.53it/s]
1|19740|Loss: 0.8950850367546082:  76%|███████▋  | 19739/25880 [4:02:18<1:07:00,  1.53it/s]
1|19740|Loss: 0.8950850367546082:  76%|███████▋  | 19740/25880 [4:02:19<1:07:44,  1.51it/s]
1|19741|Loss: 0.7701996564865112:  76%|███████▋  | 19740/25880 [4:02:19<1:07:44,  1.51it/s]
1|19741|Loss: 0.7701996564865112:  76%|███████▋  | 19741/25880 [4:02:19<1:11:34,  1.43it/s]
1|19742|Loss: 0.7458010315895081:  76%|███████▋  | 19741/25880 [4:02:20<1:11:34,  1.43it/s]
1|19742|Loss: 0.7458010315895081:  76%|███████▋  | 19742/25880 [4:02:20<1:15:20,  1.36it/s]
1|19743|Loss: 0.9305750727653503:  76%|███████▋  | 19742/25880 [4:02:21<1:15:20,  1.36it/s]
1|19743|Loss: 0.9305750727653503:  76%|███████▋  | 19743/25880 [4:02:21<1:13:23,  1.39it/s]
1|19744|Loss: 0.9065539240837097:  76%|███████▋  | 19743/25880 [4:02:21<1:13:23,  1.39it/s]
1|19744|Loss: 0.9065539240837097:  76%|███████▋  | 19744/25880 [4:02:22<1:14:36,  1.37it/s]
1|19745|Loss: 0.741908073425293:  76%|███████▋  | 19744/25880 [4:02:22<1:14:36,  1.37it/s] 
1|19745|Loss: 0.741908073425293:  76%|███████▋  | 19745/25880 [4:02:22<1:18:12,  1.31it/s]
1|19746|Loss: 0.8562198281288147:  76%|███████▋  | 19745/25880 [4:02:23<1:18:12,  1.31it/s]
1|19746|Loss: 0.8562198281288147:  76%|███████▋  | 19746/25880 [4:02:23<1:12:45,  1.41it/s]
1|19747|Loss: 0.9811519384384155:  76%|███████▋  | 19746/25880 [4:02:23<1:12:45,  1.41it/s]
1|19747|Loss: 0.9811519384384155:  76%|███████▋  | 19747/25880 [4:02:24<1:06:29,  1.54it/s]
1|19748|Loss: 0.6753420233726501:  76%|███████▋  | 19747/25880 [4:02:24<1:06:29,  1.54it/s]
1|19748|Loss: 0.6753420233726501:  76%|███████▋  | 19748/25880 [4:02:24<1:05:09,  1.57it/s]
1|19749|Loss: 0.8745346665382385:  76%|███████▋  | 19748/25880 [4:02:25<1:05:09,  1.57it/s]
1|19749|Loss: 0.8745346665382385:  76%|███████▋  | 19749/25880 [4:02:25<1:10:30,  1.45it/s]
1|19750|Loss: 0.7746877074241638:  76%|███████▋  | 19749/25880 [4:02:25<1:10:30,  1.45it/s]
1|19750|Loss: 0.7746877074241638:  76%|███████▋  | 19750/25880 [4:02:26<1:15:10,  1.36it/s]
1|19751|Loss: 0.9337634444236755:  76%|███████▋  | 19750/25880 [4:02:26<1:15:10,  1.36it/s]
1|19751|Loss: 0.9337634444236755:  76%|███████▋  | 19751/25880 [4:02:27<1:14:59,  1.36it/s]
1|19752|Loss: 0.7681201100349426:  76%|███████▋  | 19751/25880 [4:02:27<1:14:59,  1.36it/s]
1|19752|Loss: 0.7681201100349426:  76%|███████▋  | 19752/25880 [4:02:27<1:10:58,  1.44it/s]
1|19753|Loss: 0.7513977885246277:  76%|███████▋  | 19752/25880 [4:02:28<1:10:58,  1.44it/s]
1|19753|Loss: 0.7513977885246277:  76%|███████▋  | 19753/25880 [4:02:28<1:11:20,  1.43it/s]
1|19754|Loss: 0.8839520812034607:  76%|███████▋  | 19753/25880 [4:02:28<1:11:20,  1.43it/s]
1|19754|Loss: 0.8839520812034607:  76%|███████▋  | 19754/25880 [4:02:29<1:15:02,  1.36it/s]
1|19755|Loss: 0.8222717046737671:  76%|███████▋  | 19754/25880 [4:02:29<1:15:02,  1.36it/s]
1|19755|Loss: 0.8222717046737671:  76%|███████▋  | 19755/25880 [4:02:30<1:19:15,  1.29it/s]
1|19756|Loss: 0.9039523005485535:  76%|███████▋  | 19755/25880 [4:02:30<1:19:15,  1.29it/s]
1|19756|Loss: 0.9039523005485535:  76%|███████▋  | 19756/25880 [4:02:30<1:19:14,  1.29it/s]
1|19757|Loss: 0.8333597183227539:  76%|███████▋  | 19756/25880 [4:02:31<1:19:14,  1.29it/s]
1|19757|Loss: 0.8333597183227539:  76%|███████▋  | 19757/25880 [4:02:31<1:15:50,  1.35it/s]
1|19758|Loss: 0.829094409942627:  76%|███████▋  | 19757/25880 [4:02:31<1:15:50,  1.35it/s] 
1|19758|Loss: 0.829094409942627:  76%|███████▋  | 19758/25880 [4:02:32<1:16:34,  1.33it/s]
1|19759|Loss: 0.8147674798965454:  76%|███████▋  | 19758/25880 [4:02:32<1:16:34,  1.33it/s]
1|19759|Loss: 0.8147674798965454:  76%|███████▋  | 19759/25880 [4:02:33<1:21:03,  1.26it/s]
1|19760|Loss: 0.8604351878166199:  76%|███████▋  | 19759/25880 [4:02:33<1:21:03,  1.26it/s]
1|19760|Loss: 0.8604351878166199:  76%|███████▋  | 19760/25880 [4:02:33<1:14:57,  1.36it/s]
1|19761|Loss: 0.8547093272209167:  76%|███████▋  | 19760/25880 [4:02:34<1:14:57,  1.36it/s]
1|19761|Loss: 0.8547093272209167:  76%|███████▋  | 19761/25880 [4:02:34<1:16:01,  1.34it/s]
1|19762|Loss: 0.8177448511123657:  76%|███████▋  | 19761/25880 [4:02:34<1:16:01,  1.34it/s]
1|19762|Loss: 0.8177448511123657:  76%|███████▋  | 19762/25880 [4:02:35<1:15:29,  1.35it/s]
1|19763|Loss: 0.8452674150466919:  76%|███████▋  | 19762/25880 [4:02:35<1:15:29,  1.35it/s]
1|19763|Loss: 0.8452674150466919:  76%|███████▋  | 19763/25880 [4:02:36<1:18:17,  1.30it/s]
1|19764|Loss: 0.82270348072052:  76%|███████▋  | 19763/25880 [4:02:36<1:18:17,  1.30it/s]  
1|19764|Loss: 0.82270348072052:  76%|███████▋  | 19764/25880 [4:02:36<1:21:43,  1.25it/s]
1|19765|Loss: 0.6781814098358154:  76%|███████▋  | 19764/25880 [4:02:37<1:21:43,  1.25it/s]
1|19765|Loss: 0.6781814098358154:  76%|███████▋  | 19765/25880 [4:02:38<1:28:29,  1.15it/s]
1|19766|Loss: 0.9395614862442017:  76%|███████▋  | 19765/25880 [4:02:38<1:28:29,  1.15it/s]
1|19766|Loss: 0.9395614862442017:  76%|███████▋  | 19766/25880 [4:02:38<1:26:31,  1.18it/s]
1|19767|Loss: 0.8154410123825073:  76%|███████▋  | 19766/25880 [4:02:39<1:26:31,  1.18it/s]
1|19767|Loss: 0.8154410123825073:  76%|███████▋  | 19767/25880 [4:02:39<1:26:37,  1.18it/s]
1|19768|Loss: 0.8289623856544495:  76%|███████▋  | 19767/25880 [4:02:40<1:26:37,  1.18it/s]
1|19768|Loss: 0.8289623856544495:  76%|███████▋  | 19768/25880 [4:02:40<1:27:28,  1.16it/s]
1|19769|Loss: 0.9335881471633911:  76%|███████▋  | 19768/25880 [4:02:40<1:27:28,  1.16it/s]
1|19769|Loss: 0.9335881471633911:  76%|███████▋  | 19769/25880 [4:02:41<1:24:58,  1.20it/s]
1|19770|Loss: 0.848109245300293:  76%|███████▋  | 19769/25880 [4:02:41<1:24:58,  1.20it/s] 
1|19770|Loss: 0.848109245300293:  76%|███████▋  | 19770/25880 [4:02:41<1:19:51,  1.28it/s]
1|19771|Loss: 0.9846158027648926:  76%|███████▋  | 19770/25880 [4:02:42<1:19:51,  1.28it/s]
1|19771|Loss: 0.9846158027648926:  76%|███████▋  | 19771/25880 [4:02:42<1:22:20,  1.24it/s]
1|19772|Loss: 0.8020525574684143:  76%|███████▋  | 19771/25880 [4:02:43<1:22:20,  1.24it/s]
1|19772|Loss: 0.8020525574684143:  76%|███████▋  | 19772/25880 [4:02:43<1:21:22,  1.25it/s]
1|19773|Loss: 0.8199127912521362:  76%|███████▋  | 19772/25880 [4:02:44<1:21:22,  1.25it/s]
1|19773|Loss: 0.8199127912521362:  76%|███████▋  | 19773/25880 [4:02:44<1:17:06,  1.32it/s]
1|19774|Loss: 0.868516206741333:  76%|███████▋  | 19773/25880 [4:02:44<1:17:06,  1.32it/s] 
1|19774|Loss: 0.868516206741333:  76%|███████▋  | 19774/25880 [4:02:45<1:19:32,  1.28it/s]
1|19775|Loss: 0.9482069611549377:  76%|███████▋  | 19774/25880 [4:02:45<1:19:32,  1.28it/s]
1|19775|Loss: 0.9482069611549377:  76%|███████▋  | 19775/25880 [4:02:45<1:16:22,  1.33it/s]
1|19776|Loss: 0.8753415942192078:  76%|███████▋  | 19775/25880 [4:02:46<1:16:22,  1.33it/s]
1|19776|Loss: 0.8753415942192078:  76%|███████▋  | 19776/25880 [4:02:46<1:15:21,  1.35it/s]
1|19777|Loss: 0.8157457113265991:  76%|███████▋  | 19776/25880 [4:02:46<1:15:21,  1.35it/s]
1|19777|Loss: 0.8157457113265991:  76%|███████▋  | 19777/25880 [4:02:47<1:14:40,  1.36it/s]
1|19778|Loss: 0.7775207757949829:  76%|███████▋  | 19777/25880 [4:02:47<1:14:40,  1.36it/s]
1|19778|Loss: 0.7775207757949829:  76%|███████▋  | 19778/25880 [4:02:47<1:11:25,  1.42it/s]
1|19779|Loss: 0.8008094429969788:  76%|███████▋  | 19778/25880 [4:02:48<1:11:25,  1.42it/s]
1|19779|Loss: 0.8008094429969788:  76%|███████▋  | 19779/25880 [4:02:48<1:13:52,  1.38it/s]
1|19780|Loss: 0.986206591129303:  76%|███████▋  | 19779/25880 [4:02:49<1:13:52,  1.38it/s] 
1|19780|Loss: 0.986206591129303:  76%|███████▋  | 19780/25880 [4:02:49<1:14:53,  1.36it/s]
1|19781|Loss: 0.8752139806747437:  76%|███████▋  | 19780/25880 [4:02:49<1:14:53,  1.36it/s]
1|19781|Loss: 0.8752139806747437:  76%|███████▋  | 19781/25880 [4:02:50<1:14:18,  1.37it/s]
1|19782|Loss: 0.8843610286712646:  76%|███████▋  | 19781/25880 [4:02:50<1:14:18,  1.37it/s]
1|19782|Loss: 0.8843610286712646:  76%|███████▋  | 19782/25880 [4:02:50<1:13:30,  1.38it/s]
1|19783|Loss: 0.9773248434066772:  76%|███████▋  | 19782/25880 [4:02:51<1:13:30,  1.38it/s]
1|19783|Loss: 0.9773248434066772:  76%|███████▋  | 19783/25880 [4:02:51<1:13:27,  1.38it/s]
1|19784|Loss: 0.7989347577095032:  76%|███████▋  | 19783/25880 [4:02:52<1:13:27,  1.38it/s]
1|19784|Loss: 0.7989347577095032:  76%|███████▋  | 19784/25880 [4:02:52<1:17:21,  1.31it/s]
1|19785|Loss: 0.8480724692344666:  76%|███████▋  | 19784/25880 [4:02:52<1:17:21,  1.31it/s]
1|19785|Loss: 0.8480724692344666:  76%|███████▋  | 19785/25880 [4:02:53<1:17:05,  1.32it/s]
1|19786|Loss: 0.806212306022644:  76%|███████▋  | 19785/25880 [4:02:53<1:17:05,  1.32it/s] 
1|19786|Loss: 0.806212306022644:  76%|███████▋  | 19786/25880 [4:02:54<1:20:43,  1.26it/s]
1|19787|Loss: 0.744848370552063:  76%|███████▋  | 19786/25880 [4:02:54<1:20:43,  1.26it/s]
1|19787|Loss: 0.744848370552063:  76%|███████▋  | 19787/25880 [4:02:54<1:17:47,  1.31it/s]
1|19788|Loss: 0.9066799283027649:  76%|███████▋  | 19787/25880 [4:02:55<1:17:47,  1.31it/s]
1|19788|Loss: 0.9066799283027649:  76%|███████▋  | 19788/25880 [4:02:55<1:14:07,  1.37it/s]
1|19789|Loss: 0.8428065776824951:  76%|███████▋  | 19788/25880 [4:02:55<1:14:07,  1.37it/s]
1|19789|Loss: 0.8428065776824951:  76%|███████▋  | 19789/25880 [4:02:56<1:13:12,  1.39it/s]
1|19790|Loss: 0.704440712928772:  76%|███████▋  | 19789/25880 [4:02:56<1:13:12,  1.39it/s] 
1|19790|Loss: 0.704440712928772:  76%|███████▋  | 19790/25880 [4:02:56<1:12:44,  1.40it/s]
1|19791|Loss: 1.136603593826294:  76%|███████▋  | 19790/25880 [4:02:57<1:12:44,  1.40it/s]
1|19791|Loss: 1.136603593826294:  76%|███████▋  | 19791/25880 [4:02:57<1:12:51,  1.39it/s]
1|19792|Loss: 0.9315950870513916:  76%|███████▋  | 19791/25880 [4:02:57<1:12:51,  1.39it/s]
1|19792|Loss: 0.9315950870513916:  76%|███████▋  | 19792/25880 [4:02:58<1:15:33,  1.34it/s]
1|19793|Loss: 0.9627544283866882:  76%|███████▋  | 19792/25880 [4:02:58<1:15:33,  1.34it/s]
1|19793|Loss: 0.9627544283866882:  76%|███████▋  | 19793/25880 [4:02:59<1:17:11,  1.31it/s]
1|19794|Loss: 0.9293729662895203:  76%|███████▋  | 19793/25880 [4:02:59<1:17:11,  1.31it/s]
1|19794|Loss: 0.9293729662895203:  76%|███████▋  | 19794/25880 [4:03:00<1:21:15,  1.25it/s]
1|19795|Loss: 0.7747914791107178:  76%|███████▋  | 19794/25880 [4:03:00<1:21:15,  1.25it/s]
1|19795|Loss: 0.7747914791107178:  76%|███████▋  | 19795/25880 [4:03:00<1:22:46,  1.23it/s]
1|19796|Loss: 0.7651079297065735:  76%|███████▋  | 19795/25880 [4:03:01<1:22:46,  1.23it/s]
1|19796|Loss: 0.7651079297065735:  76%|███████▋  | 19796/25880 [4:03:01<1:15:54,  1.34it/s]
1|19797|Loss: 0.8220174312591553:  76%|███████▋  | 19796/25880 [4:03:01<1:15:54,  1.34it/s]
1|19797|Loss: 0.8220174312591553:  76%|███████▋  | 19797/25880 [4:03:02<1:13:19,  1.38it/s]
1|19798|Loss: 0.6348711252212524:  76%|███████▋  | 19797/25880 [4:03:02<1:13:19,  1.38it/s]
1|19798|Loss: 0.6348711252212524:  76%|███████▋  | 19798/25880 [4:03:03<1:21:13,  1.25it/s]
1|19799|Loss: 0.8741673231124878:  76%|███████▋  | 19798/25880 [4:03:03<1:21:13,  1.25it/s]
1|19799|Loss: 0.8741673231124878:  77%|███████▋  | 19799/25880 [4:03:03<1:23:38,  1.21it/s]
1|19800|Loss: 0.8456062078475952:  77%|███████▋  | 19799/25880 [4:03:04<1:23:38,  1.21it/s]
1|19800|Loss: 0.8456062078475952:  77%|███████▋  | 19800/25880 [4:03:04<1:20:41,  1.26it/s]
1|19801|Loss: 0.8226838111877441:  77%|███████▋  | 19800/25880 [4:03:05<1:20:41,  1.26it/s]
1|19801|Loss: 0.8226838111877441:  77%|███████▋  | 19801/25880 [4:03:05<1:15:56,  1.33it/s]
1|19802|Loss: 0.8765822052955627:  77%|███████▋  | 19801/25880 [4:03:05<1:15:56,  1.33it/s]
1|19802|Loss: 0.8765822052955627:  77%|███████▋  | 19802/25880 [4:03:06<1:15:17,  1.35it/s]
1|19803|Loss: 0.7295302152633667:  77%|███████▋  | 19802/25880 [4:03:06<1:15:17,  1.35it/s]
1|19803|Loss: 0.7295302152633667:  77%|███████▋  | 19803/25880 [4:03:06<1:19:37,  1.27it/s]
1|19804|Loss: 0.7990413308143616:  77%|███████▋  | 19803/25880 [4:03:07<1:19:37,  1.27it/s]
1|19804|Loss: 0.7990413308143616:  77%|███████▋  | 19804/25880 [4:03:07<1:20:19,  1.26it/s]
1|19805|Loss: 0.7477820515632629:  77%|███████▋  | 19804/25880 [4:03:08<1:20:19,  1.26it/s]
1|19805|Loss: 0.7477820515632629:  77%|███████▋  | 19805/25880 [4:03:08<1:18:14,  1.29it/s]
1|19806|Loss: 0.7336705923080444:  77%|███████▋  | 19805/25880 [4:03:08<1:18:14,  1.29it/s]
1|19806|Loss: 0.7336705923080444:  77%|███████▋  | 19806/25880 [4:03:09<1:18:11,  1.29it/s]
1|19807|Loss: 0.7853341102600098:  77%|███████▋  | 19806/25880 [4:03:09<1:18:11,  1.29it/s]
1|19807|Loss: 0.7853341102600098:  77%|███████▋  | 19807/25880 [4:03:10<1:17:27,  1.31it/s]
1|19808|Loss: 0.7818012833595276:  77%|███████▋  | 19807/25880 [4:03:10<1:17:27,  1.31it/s]
1|19808|Loss: 0.7818012833595276:  77%|███████▋  | 19808/25880 [4:03:10<1:16:44,  1.32it/s]
1|19809|Loss: 0.9552093744277954:  77%|███████▋  | 19808/25880 [4:03:11<1:16:44,  1.32it/s]
1|19809|Loss: 0.9552093744277954:  77%|███████▋  | 19809/25880 [4:03:11<1:11:13,  1.42it/s]
1|19810|Loss: 0.7605571746826172:  77%|███████▋  | 19809/25880 [4:03:11<1:11:13,  1.42it/s]
1|19810|Loss: 0.7605571746826172:  77%|███████▋  | 19810/25880 [4:03:12<1:14:29,  1.36it/s]
1|19811|Loss: 1.0150686502456665:  77%|██████���▋  | 19810/25880 [4:03:12<1:14:29,  1.36it/s]
1|19811|Loss: 1.0150686502456665:  77%|███████▋  | 19811/25880 [4:03:12<1:13:19,  1.38it/s]
1|19812|Loss: 1.0023813247680664:  77%|███████▋  | 19811/25880 [4:03:13<1:13:19,  1.38it/s]
1|19812|Loss: 1.0023813247680664:  77%|███████▋  | 19812/25880 [4:03:13<1:15:50,  1.33it/s]
1|19813|Loss: 0.8767761588096619:  77%|███████▋  | 19812/25880 [4:03:14<1:15:50,  1.33it/s]
1|19813|Loss: 0.8767761588096619:  77%|███████▋  | 19813/25880 [4:03:14<1:13:48,  1.37it/s]
1|19814|Loss: 1.0048658847808838:  77%|███████▋  | 19813/25880 [4:03:14<1:13:48,  1.37it/s]
1|19814|Loss: 1.0048658847808838:  77%|███████▋  | 19814/25880 [4:03:15<1:16:45,  1.32it/s]
1|19815|Loss: 0.7717359662055969:  77%|███████▋  | 19814/25880 [4:03:15<1:16:45,  1.32it/s]
1|19815|Loss: 0.7717359662055969:  77%|███████▋  | 19815/25880 [4:03:16<1:20:00,  1.26it/s]
1|19816|Loss: 0.8396672606468201:  77%|███████▋  | 19815/25880 [4:03:16<1:20:00,  1.26it/s]
1|19816|Loss: 0.8396672606468201:  77%|███████▋  | 19816/25880 [4:03:16<1:18:22,  1.29it/s]
1|19817|Loss: 0.7390268445014954:  77%|███████▋  | 19816/25880 [4:03:17<1:18:22,  1.29it/s]
1|19817|Loss: 0.7390268445014954:  77%|███████▋  | 19817/25880 [4:03:17<1:14:26,  1.36it/s]
1|19818|Loss: 0.8565315008163452:  77%|███████▋  | 19817/25880 [4:03:17<1:14:26,  1.36it/s]
1|19818|Loss: 0.8565315008163452:  77%|███████▋  | 19818/25880 [4:03:18<1:14:00,  1.37it/s]
1|19819|Loss: 0.8078703284263611:  77%|███████▋  | 19818/25880 [4:03:18<1:14:00,  1.37it/s]
1|19819|Loss: 0.8078703284263611:  77%|███████▋  | 19819/25880 [4:03:18<1:17:08,  1.31it/s]
1|19820|Loss: 0.7859414219856262:  77%|███████▋  | 19819/25880 [4:03:19<1:17:08,  1.31it/s]
1|19820|Loss: 0.7859414219856262:  77%|███████▋  | 19820/25880 [4:03:19<1:12:41,  1.39it/s]
1|19821|Loss: 0.8633849620819092:  77%|███████▋  | 19820/25880 [4:03:19<1:12:41,  1.39it/s]
1|19821|Loss: 0.8633849620819092:  77%|███████▋  | 19821/25880 [4:03:20<1:08:14,  1.48it/s]
1|19822|Loss: 0.7672628164291382:  77%|███████▋  | 19821/25880 [4:03:20<1:08:14,  1.48it/s]
1|19822|Loss: 0.7672628164291382:  77%|███████▋  | 19822/25880 [4:03:20<1:11:14,  1.42it/s]
1|19823|Loss: 0.887006938457489:  77%|███████▋  | 19822/25880 [4:03:21<1:11:14,  1.42it/s] 
1|19823|Loss: 0.887006938457489:  77%|███████▋  | 19823/25880 [4:03:21<1:15:45,  1.33it/s]
1|19824|Loss: 0.846145510673523:  77%|███████▋  | 19823/25880 [4:03:22<1:15:45,  1.33it/s]
1|19824|Loss: 0.846145510673523:  77%|███████▋  | 19824/25880 [4:03:22<1:20:40,  1.25it/s]
1|19825|Loss: 0.8506918549537659:  77%|███████▋  | 19824/25880 [4:03:23<1:20:40,  1.25it/s]
1|19825|Loss: 0.8506918549537659:  77%|███████▋  | 19825/25880 [4:03:23<1:13:06,  1.38it/s]
1|19826|Loss: 0.9130556583404541:  77%|███████▋  | 19825/25880 [4:03:23<1:13:06,  1.38it/s]
1|19826|Loss: 0.9130556583404541:  77%|███████▋  | 19826/25880 [4:03:24<1:14:03,  1.36it/s]
1|19827|Loss: 0.7818242907524109:  77%|███████▋  | 19826/25880 [4:03:24<1:14:03,  1.36it/s]
1|19827|Loss: 0.7818242907524109:  77%|███████▋  | 19827/25880 [4:03:24<1:12:21,  1.39it/s]
1|19828|Loss: 0.8275761604309082:  77%|███████▋  | 19827/25880 [4:03:25<1:12:21,  1.39it/s]
1|19828|Loss: 0.8275761604309082:  77%|███████▋  | 19828/25880 [4:03:25<1:12:02,  1.40it/s]
1|19829|Loss: 0.9685482978820801:  77%|███████▋  | 19828/25880 [4:03:25<1:12:02,  1.40it/s]
1|19829|Loss: 0.9685482978820801:  77%|███████▋  | 19829/25880 [4:03:26<1:12:32,  1.39it/s]
1|19830|Loss: 0.9607478976249695:  77%|███████▋  | 19829/25880 [4:03:26<1:12:32,  1.39it/s]
1|19830|Loss: 0.9607478976249695:  77%|███████▋  | 19830/25880 [4:03:26<1:10:20,  1.43it/s]
1|19831|Loss: 0.9153478145599365:  77%|███████▋  | 19830/25880 [4:03:27<1:10:20,  1.43it/s]
1|19831|Loss: 0.9153478145599365:  77%|███████▋  | 19831/25880 [4:03:27<1:12:06,  1.40it/s]
1|19832|Loss: 0.7774563431739807:  77%|███████▋  | 19831/25880 [4:03:27<1:12:06,  1.40it/s]
1|19832|Loss: 0.7774563431739807:  77%|███████▋  | 19832/25880 [4:03:28<1:12:23,  1.39it/s]
1|19833|Loss: 0.8063051104545593:  77%|███████▋  | 19832/25880 [4:03:28<1:12:23,  1.39it/s]
1|19833|Loss: 0.8063051104545593:  77%|███████▋  | 19833/25880 [4:03:29<1:14:21,  1.36it/s]
1|19834|Loss: 0.9383500218391418:  77%|███████▋  | 19833/25880 [4:03:29<1:14:21,  1.36it/s]
1|19834|Loss: 0.9383500218391418:  77%|███████▋  | 19834/25880 [4:03:29<1:14:02,  1.36it/s]
1|19835|Loss: 0.8524445295333862:  77%|███████▋  | 19834/25880 [4:03:30<1:14:02,  1.36it/s]
1|19835|Loss: 0.8524445295333862:  77%|███████▋  | 19835/25880 [4:03:30<1:12:58,  1.38it/s]
1|19836|Loss: 0.8329530358314514:  77%|███████▋  | 19835/25880 [4:03:30<1:12:58,  1.38it/s]
1|19836|Loss: 0.8329530358314514:  77%|███████▋  | 19836/25880 [4:03:31<1:10:51,  1.42it/s]
1|19837|Loss: 0.8001219034194946:  77%|███████▋  | 19836/25880 [4:03:31<1:10:51,  1.42it/s]
1|19837|Loss: 0.8001219034194946:  77%|███████▋  | 19837/25880 [4:03:31<1:08:55,  1.46it/s]
1|19838|Loss: 0.6615173816680908:  77%|███████▋  | 19837/25880 [4:03:32<1:08:55,  1.46it/s]
1|19838|Loss: 0.6615173816680908:  77%|███████▋  | 19838/25880 [4:03:32<1:00:02,  1.68it/s]
1|19839|Loss: 0.8761487603187561:  77%|███████▋  | 19838/25880 [4:03:32<1:00:02,  1.68it/s]
1|19839|Loss: 0.8761487603187561:  77%|███████▋  | 19839/25880 [4:03:32<1:02:51,  1.60it/s]
1|19840|Loss: 0.817413330078125:  77%|███████▋  | 19839/25880 [4:03:33<1:02:51,  1.60it/s] 
1|19840|Loss: 0.817413330078125:  77%|███████▋  | 19840/25880 [4:03:33<1:06:56,  1.50it/s]
1|19841|Loss: 0.7145717740058899:  77%|███████▋  | 19840/25880 [4:03:33<1:06:56,  1.50it/s]
1|19841|Loss: 0.7145717740058899:  77%|███████▋  | 19841/25880 [4:03:34<1:06:55,  1.50it/s]
1|19842|Loss: 0.6926933526992798:  77%|███████▋  | 19841/25880 [4:03:34<1:06:55,  1.50it/s]
1|19842|Loss: 0.6926933526992798:  77%|███████▋  | 19842/25880 [4:03:35<1:13:01,  1.38it/s]
1|19843|Loss: 0.4799920320510864:  77%|███████▋  | 19842/25880 [4:03:35<1:13:01,  1.38it/s]
1|19843|Loss: 0.4799920320510864:  77%|███████▋  | 19843/25880 [4:03:36<1:24:23,  1.19it/s]
1|19844|Loss: 0.6249288320541382:  77%|███████▋  | 19843/25880 [4:03:36<1:24:23,  1.19it/s]
1|19844|Loss: 0.6249288320541382:  77%|███████▋  | 19844/25880 [4:03:37<1:27:22,  1.15it/s]
1|19845|Loss: 0.8727009296417236:  77%|███████▋  | 19844/25880 [4:03:37<1:27:22,  1.15it/s]
1|19845|Loss: 0.8727009296417236:  77%|███████▋  | 19845/25880 [4:03:38<1:26:05,  1.17it/s]
1|19846|Loss: 0.8317639827728271:  77%|███████▋  | 19845/25880 [4:03:38<1:26:05,  1.17it/s]
1|19846|Loss: 0.8317639827728271:  77%|███████▋  | 19846/25880 [4:03:38<1:25:12,  1.18it/s]
1|19847|Loss: 0.7943166494369507:  77%|███████▋  | 19846/25880 [4:03:39<1:25:12,  1.18it/s]
1|19847|Loss: 0.7943166494369507:  77%|███████▋  | 19847/25880 [4:03:39<1:22:14,  1.22it/s]
1|19848|Loss: 0.9553149342536926:  77%|███████▋  | 19847/25880 [4:03:39<1:22:14,  1.22it/s]
1|19848|Loss: 0.9553149342536926:  77%|███████▋  | 19848/25880 [4:03:40<1:18:42,  1.28it/s]
1|19849|Loss: 0.8291862607002258:  77%|███████▋  | 19848/25880 [4:03:40<1:18:42,  1.28it/s]
1|19849|Loss: 0.8291862607002258:  77%|███████▋  | 19849/25880 [4:03:41<1:16:59,  1.31it/s]
1|19850|Loss: 0.8214866518974304:  77%|███████▋  | 19849/25880 [4:03:41<1:16:59,  1.31it/s]
1|19850|Loss: 0.8214866518974304:  77%|███████▋  | 19850/25880 [4:03:41<1:20:21,  1.25it/s]
1|19851|Loss: 0.8991888165473938:  77%|███████▋  | 19850/25880 [4:03:42<1:20:21,  1.25it/s]
1|19851|Loss: 0.8991888165473938:  77%|███████▋  | 19851/25880 [4:03:42<1:14:02,  1.36it/s]
1|19852|Loss: 0.8165979981422424:  77%|███████▋  | 19851/25880 [4:03:42<1:14:02,  1.36it/s]
1|19852|Loss: 0.8165979981422424:  77%|███████▋  | 19852/25880 [4:03:43<1:11:37,  1.40it/s]
1|19853|Loss: 0.8644511103630066:  77%|███████▋  | 19852/25880 [4:03:43<1:11:37,  1.40it/s]
1|19853|Loss: 0.8644511103630066:  77%|███████▋  | 19853/25880 [4:03:43<1:13:44,  1.36it/s]
1|19854|Loss: 0.8264999389648438:  77%|███████▋  | 19853/25880 [4:03:44<1:13:44,  1.36it/s]
1|19854|Loss: 0.8264999389648438:  77%|███████▋  | 19854/25880 [4:03:44<1:17:39,  1.29it/s]
1|19855|Loss: 0.8602480888366699:  77%|███████▋  | 19854/25880 [4:03:45<1:17:39,  1.29it/s]
1|19855|Loss: 0.8602480888366699:  77%|███████▋  | 19855/25880 [4:03:45<1:18:50,  1.27it/s]
1|19856|Loss: 0.8926990032196045:  77%|███████▋  | 19855/25880 [4:03:46<1:18:50,  1.27it/s]
1|19856|Loss: 0.8926990032196045:  77%|███████▋  | 19856/25880 [4:03:46<1:17:42,  1.29it/s]
1|19857|Loss: 0.8238823413848877:  77%|███████▋  | 19856/25880 [4:03:46<1:17:42,  1.29it/s]
1|19857|Loss: 0.8238823413848877:  77%|███████▋  | 19857/25880 [4:03:47<1:18:06,  1.29it/s]
1|19858|Loss: 0.8678441643714905:  77%|███████▋  | 19857/25880 [4:03:47<1:18:06,  1.29it/s]
1|19858|Loss: 0.8678441643714905:  77%|███████▋  | 19858/25880 [4:03:47<1:12:52,  1.38it/s]
1|19859|Loss: 0.8029938340187073:  77%|███████▋  | 19858/25880 [4:03:48<1:12:52,  1.38it/s]
1|19859|Loss: 0.8029938340187073:  77%|███████▋  | 19859/25880 [4:03:48<1:16:37,  1.31it/s]
1|19860|Loss: 0.9077883958816528:  77%|███████▋  | 19859/25880 [4:03:48<1:16:37,  1.31it/s]
1|19860|Loss: 0.9077883958816528:  77%|███████▋  | 19860/25880 [4:03:49<1:12:03,  1.39it/s]
1|19861|Loss: 0.8792015910148621:  77%|███████▋  | 19860/25880 [4:03:49<1:12:03,  1.39it/s]
1|19861|Loss: 0.8792015910148621:  77%|███████▋  | 19861/25880 [4:03:49<1:11:30,  1.40it/s]
1|19862|Loss: 0.819688618183136:  77%|███████▋  | 19861/25880 [4:03:50<1:11:30,  1.40it/s] 
1|19862|Loss: 0.819688618183136:  77%|███████▋  | 19862/25880 [4:03:50<1:12:25,  1.38it/s]
1|19863|Loss: 0.782159149646759:  77%|███████▋  | 19862/25880 [4:03:51<1:12:25,  1.38it/s]
1|19863|Loss: 0.782159149646759:  77%|███████▋  | 19863/25880 [4:03:51<1:10:08,  1.43it/s]
1|19864|Loss: 0.9359298348426819:  77%|███████▋  | 19863/25880 [4:03:51<1:10:08,  1.43it/s]
1|19864|Loss: 0.9359298348426819:  77%|███████▋  | 19864/25880 [4:03:52<1:12:49,  1.38it/s]
1|19865|Loss: 0.7841370701789856:  77%|███████▋  | 19864/25880 [4:03:52<1:12:49,  1.38it/s]
1|19865|Loss: 0.7841370701789856:  77%|███████▋  | 19865/25880 [4:03:52<1:14:07,  1.35it/s]
1|19866|Loss: 0.7577210068702698:  77%|███████▋  | 19865/25880 [4:03:53<1:14:07,  1.35it/s]
1|19866|Loss: 0.7577210068702698:  77%|███████▋  | 19866/25880 [4:03:53<1:14:10,  1.35it/s]
1|19867|Loss: 0.8925926089286804:  77%|███████▋  | 19866/25880 [4:03:53<1:14:10,  1.35it/s]
1|19867|Loss: 0.8925926089286804:  77%|███████▋  | 19867/25880 [4:03:54<1:13:20,  1.37it/s]
1|19868|Loss: 0.9432967305183411:  77%|███████▋  | 19867/25880 [4:03:54<1:13:20,  1.37it/s]
1|19868|Loss: 0.9432967305183411:  77%|███████▋  | 19868/25880 [4:03:55<1:13:04,  1.37it/s]
1|19869|Loss: 0.8334389328956604:  77%|███████▋  | 19868/25880 [4:03:55<1:13:04,  1.37it/s]
1|19869|Loss: 0.8334389328956604:  77%|███████▋  | 19869/25880 [4:03:55<1:09:23,  1.44it/s]
1|19870|Loss: 0.7977483868598938:  77%|███████▋  | 19869/25880 [4:03:55<1:09:23,  1.44it/s]
1|19870|Loss: 0.7977483868598938:  77%|███████▋  | 19870/25880 [4:03:56<1:02:59,  1.59it/s]
1|19871|Loss: 0.7749905586242676:  77%|███████▋  | 19870/25880 [4:03:56<1:02:59,  1.59it/s]
1|19871|Loss: 0.7749905586242676:  77%|███████▋  | 19871/25880 [4:03:56<58:58,  1.70it/s]  
1|19872|Loss: 0.714610755443573:  77%|███████▋  | 19871/25880 [4:03:56<58:58,  1.70it/s] 
1|19872|Loss: 0.714610755443573:  77%|███████▋  | 19872/25880 [4:03:57<1:01:09,  1.64it/s]
1|19873|Loss: 0.9245678782463074:  77%|███████▋  | 19872/25880 [4:03:57<1:01:09,  1.64it/s]
1|19873|Loss: 0.9245678782463074:  77%|███████▋  | 19873/25880 [4:03:58<1:04:34,  1.55it/s]
1|19874|Loss: 0.8859441876411438:  77%|███████▋  | 19873/25880 [4:03:58<1:04:34,  1.55it/s]
1|19874|Loss: 0.8859441876411438:  77%|███████▋  | 19874/25880 [4:03:58<1:12:50,  1.37it/s]
1|19875|Loss: 0.917701780796051:  77%|███████▋  | 19874/25880 [4:03:59<1:12:50,  1.37it/s] 
1|19875|Loss: 0.917701780796051:  77%|███████▋  | 19875/25880 [4:03:59<1:17:00,  1.30it/s]
1|19876|Loss: 0.7930089831352234:  77%|███████▋  | 19875/25880 [4:04:00<1:17:00,  1.30it/s]
1|19876|Loss: 0.7930089831352234:  77%|███████▋  | 19876/25880 [4:04:00<1:13:45,  1.36it/s]
1|19877|Loss: 0.7896938323974609:  77%|███████▋  | 19876/25880 [4:04:00<1:13:45,  1.36it/s]
1|19877|Loss: 0.7896938323974609:  77%|███████▋  | 19877/25880 [4:04:01<1:12:50,  1.37it/s]
1|19878|Loss: 0.8376306891441345:  77%|███████▋  | 19877/25880 [4:04:01<1:12:50,  1.37it/s]
1|19878|Loss: 0.8376306891441345:  77%|███████▋  | 19878/25880 [4:04:01<1:10:56,  1.41it/s]
1|19879|Loss: 0.7473083734512329:  77%|███████▋  | 19878/25880 [4:04:02<1:10:56,  1.41it/s]
1|19879|Loss: 0.7473083734512329:  77%|███████▋  | 19879/25880 [4:04:02<1:11:09,  1.41it/s]
1|19880|Loss: 0.8358703851699829:  77%|███████▋  | 19879/25880 [4:04:02<1:11:09,  1.41it/s]
1|19880|Loss: 0.8358703851699829:  77%|███████▋  | 19880/25880 [4:04:03<1:11:48,  1.39it/s]
1|19881|Loss: 0.8794196844100952:  77%|███████▋  | 19880/25880 [4:04:03<1:11:48,  1.39it/s]
1|19881|Loss: 0.8794196844100952:  77%|███████▋  | 19881/25880 [4:04:03<1:06:48,  1.50it/s]
1|19882|Loss: 0.6936849355697632:  77%|███████▋  | 19881/25880 [4:04:04<1:06:48,  1.50it/s]
1|19882|Loss: 0.6936849355697632:  77%|███████▋  | 19882/25880 [4:04:04<1:01:56,  1.61it/s]
1|19883|Loss: 0.7845161557197571:  77%|███████▋  | 19882/25880 [4:04:04<1:01:56,  1.61it/s]
1|19883|Loss: 0.7845161557197571:  77%|███████▋  | 19883/25880 [4:04:05<1:04:17,  1.55it/s]
1|19884|Loss: 0.6161472797393799:  77%|███████▋  | 19883/25880 [4:04:05<1:04:17,  1.55it/s]
1|19884|Loss: 0.6161472797393799:  77%|███████▋  | 19884/25880 [4:04:05<1:03:53,  1.56it/s]
1|19885|Loss: 0.8979796767234802:  77%|███████▋  | 19884/25880 [4:04:06<1:03:53,  1.56it/s]
1|19885|Loss: 0.8979796767234802:  77%|███████▋  | 19885/25880 [4:04:06<1:05:55,  1.52it/s]
1|19886|Loss: 0.7000482082366943:  77%|███████▋  | 19885/25880 [4:04:06<1:05:55,  1.52it/s]
1|19886|Loss: 0.7000482082366943:  77%|███████▋  | 19886/25880 [4:04:07<1:07:16,  1.48it/s]
1|19887|Loss: 0.8442782163619995:  77%|███████▋  | 19886/25880 [4:04:07<1:07:16,  1.48it/s]
1|19887|Loss: 0.8442782163619995:  77%|███████▋  | 19887/25880 [4:04:07<1:08:30,  1.46it/s]
1|19888|Loss: 0.8708024621009827:  77%|███████▋  | 19887/25880 [4:04:08<1:08:30,  1.46it/s]
1|19888|Loss: 0.8708024621009827:  77%|███████▋  | 19888/25880 [4:04:08<1:12:42,  1.37it/s]
1|19889|Loss: 0.7687281370162964:  77%|███████▋  | 19888/25880 [4:04:09<1:12:42,  1.37it/s]
1|19889|Loss: 0.7687281370162964:  77%|███████▋  | 19889/25880 [4:04:09<1:15:23,  1.32it/s]
1|19890|Loss: 0.7646939754486084:  77%|███████▋  | 19889/25880 [4:04:09<1:15:23,  1.32it/s]
1|19890|Loss: 0.7646939754486084:  77%|███████▋  | 19890/25880 [4:04:10<1:15:08,  1.33it/s]
1|19891|Loss: 0.75089031457901:  77%|███████▋  | 19890/25880 [4:04:10<1:15:08,  1.33it/s]  
1|19891|Loss: 0.75089031457901:  77%|███████▋  | 19891/25880 [4:04:10<1:14:42,  1.34it/s]
1|19892|Loss: 0.8879535794258118:  77%|███████▋  | 19891/25880 [4:04:11<1:14:42,  1.34it/s]
1|19892|Loss: 0.8879535794258118:  77%|███████▋  | 19892/25880 [4:04:11<1:12:15,  1.38it/s]
1|19893|Loss: 0.7419195771217346:  77%|███████▋  | 19892/25880 [4:04:12<1:12:15,  1.38it/s]
1|19893|Loss: 0.7419195771217346:  77%|███████▋  | 19893/25880 [4:04:12<1:15:30,  1.32it/s]
1|19894|Loss: 0.7226383686065674:  77%|███████▋  | 19893/25880 [4:04:12<1:15:30,  1.32it/s]
1|19894|Loss: 0.7226383686065674:  77%|███████▋  | 19894/25880 [4:04:13<1:21:27,  1.22it/s]
1|19895|Loss: 0.767723798751831:  77%|███████▋  | 19894/25880 [4:04:13<1:21:27,  1.22it/s] 
1|19895|Loss: 0.767723798751831:  77%|███████▋  | 19895/25880 [4:04:14<1:24:08,  1.19it/s]
1|19896|Loss: 0.9351341724395752:  77%|███████▋  | 19895/25880 [4:04:14<1:24:08,  1.19it/s]
1|19896|Loss: 0.9351341724395752:  77%|███████▋  | 19896/25880 [4:04:15<1:23:29,  1.19it/s]
1|19897|Loss: 0.8672537803649902:  77%|███████▋  | 19896/25880 [4:04:15<1:23:29,  1.19it/s]
1|19897|Loss: 0.8672537803649902:  77%|███████▋  | 19897/25880 [4:04:15<1:18:20,  1.27it/s]
1|19898|Loss: 0.7129116058349609:  77%|███████▋  | 19897/25880 [4:04:16<1:18:20,  1.27it/s]
1|19898|Loss: 0.7129116058349609:  77%|███████▋  | 19898/25880 [4:04:16<1:11:16,  1.40it/s]
1|19899|Loss: 0.9098263382911682:  77%|███████▋  | 19898/25880 [4:04:16<1:11:16,  1.40it/s]
1|19899|Loss: 0.9098263382911682:  77%|███████▋  | 19899/25880 [4:04:16<1:06:52,  1.49it/s]
1|19900|Loss: 0.6195699572563171:  77%|███████▋  | 19899/25880 [4:04:17<1:06:52,  1.49it/s]
1|19900|Loss: 0.6195699572563171:  77%|███████▋  | 19900/25880 [4:04:17<1:09:34,  1.43it/s]
1|19901|Loss: 0.7274367809295654:  77%|███████▋  | 19900/25880 [4:04:18<1:09:34,  1.43it/s]
1|19901|Loss: 0.7274367809295654:  77%|███████▋  | 19901/25880 [4:04:18<1:08:43,  1.45it/s]
1|19902|Loss: 0.8549668788909912:  77%|███████▋  | 19901/25880 [4:04:18<1:08:43,  1.45it/s]
1|19902|Loss: 0.8549668788909912:  77%|███████▋  | 19902/25880 [4:04:18<1:05:47,  1.51it/s]
1|19903|Loss: 0.7968041300773621:  77%|███████▋  | 19902/25880 [4:04:19<1:05:47,  1.51it/s]
1|19903|Loss: 0.7968041300773621:  77%|███████▋  | 19903/25880 [4:04:19<1:09:31,  1.43it/s]
1|19904|Loss: 0.7422361969947815:  77%|███████▋  | 19903/25880 [4:04:20<1:09:31,  1.43it/s]
1|19904|Loss: 0.7422361969947815:  77%|███████▋  | 19904/25880 [4:04:20<1:12:18,  1.38it/s]
1|19905|Loss: 0.8325920701026917:  77%|███████▋  | 19904/25880 [4:04:20<1:12:18,  1.38it/s]
1|19905|Loss: 0.8325920701026917:  77%|███████▋  | 19905/25880 [4:04:21<1:12:29,  1.37it/s]
1|19906|Loss: 0.8945211172103882:  77%|███████▋  | 19905/25880 [4:04:21<1:12:29,  1.37it/s]
1|19906|Loss: 0.8945211172103882:  77%|███████▋  | 19906/25880 [4:04:21<1:11:39,  1.39it/s]
1|19907|Loss: 0.8482396006584167:  77%|███████▋  | 19906/25880 [4:04:22<1:11:39,  1.39it/s]
1|19907|Loss: 0.8482396006584167:  77%|███████▋  | 19907/25880 [4:04:22<1:09:35,  1.43it/s]
1|19908|Loss: 0.900078296661377:  77%|███████▋  | 19907/25880 [4:04:22<1:09:35,  1.43it/s] 
1|19908|Loss: 0.900078296661377:  77%|███████▋  | 19908/25880 [4:04:23<1:09:13,  1.44it/s]
1|19909|Loss: 0.8420416712760925:  77%|███████▋  | 19908/25880 [4:04:23<1:09:13,  1.44it/s]
1|19909|Loss: 0.8420416712760925:  77%|███████▋  | 19909/25880 [4:04:23<1:06:26,  1.50it/s]
1|19910|Loss: 0.8106290698051453:  77%|███████▋  | 19909/25880 [4:04:24<1:06:26,  1.50it/s]
1|19910|Loss: 0.8106290698051453:  77%|███████▋  | 19910/25880 [4:04:24<1:09:41,  1.43it/s]
1|19911|Loss: 0.9023234248161316:  77%|███████▋  | 19910/25880 [4:04:25<1:09:41,  1.43it/s]
1|19911|Loss: 0.9023234248161316:  77%|███████▋  | 19911/25880 [4:04:25<1:12:41,  1.37it/s]
1|19912|Loss: 0.8818585276603699:  77%|███████▋  | 19911/25880 [4:04:25<1:12:41,  1.37it/s]
1|19912|Loss: 0.8818585276603699:  77%|███████▋  | 19912/25880 [4:04:25<1:06:37,  1.49it/s]
1|19913|Loss: 0.8597390651702881:  77%|███████▋  | 19912/25880 [4:04:26<1:06:37,  1.49it/s]
1|19913|Loss: 0.8597390651702881:  77%|███████▋  | 19913/25880 [4:04:26<1:04:01,  1.55it/s]
1|19914|Loss: 0.7064266800880432:  77%|███████▋  | 19913/25880 [4:04:26<1:04:01,  1.55it/s]
1|19914|Loss: 0.7064266800880432:  77%|███████▋  | 19914/25880 [4:04:27<1:05:52,  1.51it/s]
1|19915|Loss: 0.8434145450592041:  77%|███████▋  | 19914/25880 [4:04:27<1:05:52,  1.51it/s]
1|19915|Loss: 0.8434145450592041:  77%|███████▋  | 19915/25880 [4:04:28<1:10:14,  1.42it/s]
1|19916|Loss: 0.8836249709129333:  77%|███████▋  | 19915/25880 [4:04:28<1:10:14,  1.42it/s]
1|19916|Loss: 0.8836249709129333:  77%|███████▋  | 19916/25880 [4:04:28<1:11:21,  1.39it/s]
1|19917|Loss: 0.8777816295623779:  77%|███████▋  | 19916/25880 [4:04:29<1:11:21,  1.39it/s]
1|19917|Loss: 0.8777816295623779:  77%|███████▋  | 19917/25880 [4:04:29<1:13:31,  1.35it/s]
1|19918|Loss: 0.7708774209022522:  77%|███████▋  | 19917/25880 [4:04:30<1:13:31,  1.35it/s]
1|19918|Loss: 0.7708774209022522:  77%|███████▋  | 19918/25880 [4:04:30<1:18:01,  1.27it/s]
1|19919|Loss: 0.8577675223350525:  77%|███████▋  | 19918/25880 [4:04:30<1:18:01,  1.27it/s]
1|19919|Loss: 0.8577675223350525:  77%|███████▋  | 19919/25880 [4:04:31<1:12:11,  1.38it/s]
1|19920|Loss: 0.8220669627189636:  77%|███████▋  | 19919/25880 [4:04:31<1:12:11,  1.38it/s]
1|19920|Loss: 0.8220669627189636:  77%|███████▋  | 19920/25880 [4:04:31<1:07:37,  1.47it/s]
1|19921|Loss: 0.8141348361968994:  77%|███████▋  | 19920/25880 [4:04:32<1:07:37,  1.47it/s]
1|19921|Loss: 0.8141348361968994:  77%|███████▋  | 19921/25880 [4:04:32<1:08:12,  1.46it/s]
1|19922|Loss: 0.7938366532325745:  77%|███████▋  | 19921/25880 [4:04:32<1:08:12,  1.46it/s]
1|19922|Loss: 0.7938366532325745:  77%|███████▋  | 19922/25880 [4:04:33<1:09:01,  1.44it/s]
1|19923|Loss: 0.7028552889823914:  77%|███████▋  | 19922/25880 [4:04:33<1:09:01,  1.44it/s]
1|19923|Loss: 0.7028552889823914:  77%|███████▋  | 19923/25880 [4:04:33<1:07:40,  1.47it/s]
1|19924|Loss: 0.7949197888374329:  77%|███████▋  | 19923/25880 [4:04:34<1:07:40,  1.47it/s]
1|19924|Loss: 0.7949197888374329:  77%|███████▋  | 19924/25880 [4:04:34<1:06:33,  1.49it/s]
1|19925|Loss: 0.6968559622764587:  77%|███████▋  | 19924/25880 [4:04:34<1:06:33,  1.49it/s]
1|19925|Loss: 0.6968559622764587:  77%|███████▋  | 19925/25880 [4:04:35<1:07:01,  1.48it/s]
1|19926|Loss: 0.8347516059875488:  77%|███████▋  | 19925/25880 [4:04:35<1:07:01,  1.48it/s]
1|19926|Loss: 0.8347516059875488:  77%|███████▋  | 19926/25880 [4:04:35<1:05:35,  1.51it/s]
1|19927|Loss: 0.9410106539726257:  77%|███████▋  | 19926/25880 [4:04:36<1:05:35,  1.51it/s]
1|19927|Loss: 0.9410106539726257:  77%|███████▋  | 19927/25880 [4:04:36<1:03:26,  1.56it/s]
1|19928|Loss: 0.8965023159980774:  77%|███████▋  | 19927/25880 [4:04:36<1:03:26,  1.56it/s]
1|19928|Loss: 0.8965023159980774:  77%|███████▋  | 19928/25880 [4:04:36<1:02:36,  1.58it/s]
1|19929|Loss: 0.9131290316581726:  77%|███████▋  | 19928/25880 [4:04:37<1:02:36,  1.58it/s]
1|19929|Loss: 0.9131290316581726:  77%|███████▋  | 19929/25880 [4:04:37<59:12,  1.68it/s]  
1|19930|Loss: 0.8676894903182983:  77%|███████▋  | 19929/25880 [4:04:37<59:12,  1.68it/s]
1|19930|Loss: 0.8676894903182983:  77%|███████▋  | 19930/25880 [4:04:38<1:00:59,  1.63it/s]
1|19931|Loss: 0.7516684532165527:  77%|███████▋  | 19930/25880 [4:04:38<1:00:59,  1.63it/s]
1|19931|Loss: 0.7516684532165527:  77%|███████▋  | 19931/25880 [4:04:38<1:05:36,  1.51it/s]
1|19932|Loss: 0.6769176721572876:  77%|███████▋  | 19931/25880 [4:04:39<1:05:36,  1.51it/s]
1|19932|Loss: 0.6769176721572876:  77%|███████▋  | 19932/25880 [4:04:39<1:04:23,  1.54it/s]
1|19933|Loss: 0.850327730178833:  77%|███████▋  | 19932/25880 [4:04:39<1:04:23,  1.54it/s] 
1|19933|Loss: 0.850327730178833:  77%|███████▋  | 19933/25880 [4:04:40<1:05:28,  1.51it/s]
1|19934|Loss: 0.8529534935951233:  77%|███████▋  | 19933/25880 [4:04:40<1:05:28,  1.51it/s]
1|19934|Loss: 0.8529534935951233:  77%|███████▋  | 19934/25880 [4:04:40<1:04:49,  1.53it/s]
1|19935|Loss: 0.8376657962799072:  77%|███████▋  | 19934/25880 [4:04:41<1:04:49,  1.53it/s]
1|19935|Loss: 0.8376657962799072:  77%|███████▋  | 19935/25880 [4:04:41<1:11:00,  1.40it/s]
1|19936|Loss: 0.8898104429244995:  77%|███████▋  | 19935/25880 [4:04:42<1:11:00,  1.40it/s]
1|19936|Loss: 0.8898104429244995:  77%|███████▋  | 19936/25880 [4:04:42<1:09:49,  1.42it/s]
1|19937|Loss: 0.7900468707084656:  77%|███████▋  | 19936/25880 [4:04:42<1:09:49,  1.42it/s]
1|19937|Loss: 0.7900468707084656:  77%|███████▋  | 19937/25880 [4:04:43<1:10:10,  1.41it/s]
1|19938|Loss: 0.9936612844467163:  77%|███████▋  | 19937/25880 [4:04:43<1:10:10,  1.41it/s]
1|19938|Loss: 0.9936612844467163:  77%|███████▋  | 19938/25880 [4:04:43<1:08:56,  1.44it/s]
1|19939|Loss: 0.7855826020240784:  77%|███████▋  | 19938/25880 [4:04:44<1:08:56,  1.44it/s]
1|19939|Loss: 0.7855826020240784:  77%|███████▋  | 19939/25880 [4:04:44<1:07:14,  1.47it/s]
1|19940|Loss: 0.9473481178283691:  77%|███████▋  | 19939/25880 [4:04:44<1:07:14,  1.47it/s]
1|19940|Loss: 0.9473481178283691:  77%|███████▋  | 19940/25880 [4:04:44<1:04:41,  1.53it/s]
1|19941|Loss: 0.8217121958732605:  77%|███████▋  | 19940/25880 [4:04:45<1:04:41,  1.53it/s]
1|19941|Loss: 0.8217121958732605:  77%|███████▋  | 19941/25880 [4:04:45<1:02:29,  1.58it/s]
1|19942|Loss: 0.8749005198478699:  77%|███████▋  | 19941/25880 [4:04:45<1:02:29,  1.58it/s]
1|19942|Loss: 0.8749005198478699:  77%|███████▋  | 19942/25880 [4:04:46<1:00:57,  1.62it/s]
1|19943|Loss: 0.7027743458747864:  77%|███████▋  | 19942/25880 [4:04:46<1:00:57,  1.62it/s]
1|19943|Loss: 0.7027743458747864:  77%|███████▋  | 19943/25880 [4:04:46<1:02:48,  1.58it/s]
1|19944|Loss: 0.68870609998703:  77%|███████▋  | 19943/25880 [4:04:47<1:02:48,  1.58it/s]  
1|19944|Loss: 0.68870609998703:  77%|███████▋  | 19944/25880 [4:04:47<1:03:21,  1.56it/s]
1|19945|Loss: 0.7659207582473755:  77%|███████▋  | 19944/25880 [4:04:47<1:03:21,  1.56it/s]
1|19945|Loss: 0.7659207582473755:  77%|███████▋  | 19945/25880 [4:04:48<1:03:20,  1.56it/s]
1|19946|Loss: 0.8510124087333679:  77%|███████▋  | 19945/25880 [4:04:48<1:03:20,  1.56it/s]
1|19946|Loss: 0.8510124087333679:  77%|███████▋  | 19946/25880 [4:04:48<1:05:33,  1.51it/s]
1|19947|Loss: 0.8896492719650269:  77%|███████▋  | 19946/25880 [4:04:49<1:05:33,  1.51it/s]
1|19947|Loss: 0.8896492719650269:  77%|███████▋  | 19947/25880 [4:04:49<1:07:38,  1.46it/s]
1|19948|Loss: 0.8998264074325562:  77%|███████▋  | 19947/25880 [4:04:49<1:07:38,  1.46it/s]
1|19948|Loss: 0.8998264074325562:  77%|███████▋  | 19948/25880 [4:04:50<1:09:20,  1.43it/s]
1|19949|Loss: 0.7609083652496338:  77%|███████▋  | 19948/25880 [4:04:50<1:09:20,  1.43it/s]
1|19949|Loss: 0.7609083652496338:  77%|███████▋  | 19949/25880 [4:04:51<1:12:37,  1.36it/s]
1|19950|Loss: 0.7630948424339294:  77%|███████▋  | 19949/25880 [4:04:51<1:12:37,  1.36it/s]
1|19950|Loss: 0.7630948424339294:  77%|███████▋  | 19950/25880 [4:04:51<1:09:20,  1.43it/s]
1|19951|Loss: 0.8398065567016602:  77%|███████▋  | 19950/25880 [4:04:52<1:09:20,  1.43it/s]
1|19951|Loss: 0.8398065567016602:  77%|███████▋  | 19951/25880 [4:04:52<1:10:34,  1.40it/s]
1|19952|Loss: 0.8948603272438049:  77%|███████▋  | 19951/25880 [4:04:52<1:10:34,  1.40it/s]
1|19952|Loss: 0.8948603272438049:  77%|███████▋  | 19952/25880 [4:04:53<1:09:24,  1.42it/s]
1|19953|Loss: 0.8493567705154419:  77%|███████▋  | 19952/25880 [4:04:53<1:09:24,  1.42it/s]
1|19953|Loss: 0.8493567705154419:  77%|███████▋  | 19953/25880 [4:04:53<1:09:31,  1.42it/s]
1|19954|Loss: 0.8667515516281128:  77%|███████▋  | 19953/25880 [4:04:54<1:09:31,  1.42it/s]
1|19954|Loss: 0.8667515516281128:  77%|███████▋  | 19954/25880 [4:04:54<1:09:21,  1.42it/s]
1|19955|Loss: 0.7609646320343018:  77%|███████▋  | 19954/25880 [4:04:54<1:09:21,  1.42it/s]
1|19955|Loss: 0.7609646320343018:  77%|███████▋  | 19955/25880 [4:04:55<1:11:40,  1.38it/s]
1|19956|Loss: 0.9727916717529297:  77%|███████▋  | 19955/25880 [4:04:55<1:11:40,  1.38it/s]
1|19956|Loss: 0.9727916717529297:  77%|███████▋  | 19956/25880 [4:04:56<1:12:06,  1.37it/s]
1|19957|Loss: 0.8386391997337341:  77%|███████▋  | 19956/25880 [4:04:56<1:12:06,  1.37it/s]
1|19957|Loss: 0.8386391997337341:  77%|███████▋  | 19957/25880 [4:04:56<1:11:23,  1.38it/s]
1|19958|Loss: 0.8542640805244446:  77%|███████▋  | 19957/25880 [4:04:57<1:11:23,  1.38it/s]
1|19958|Loss: 0.8542640805244446:  77%|███████▋  | 19958/25880 [4:04:57<1:10:43,  1.40it/s]
1|19959|Loss: 1.0332759618759155:  77%|███████▋  | 19958/25880 [4:04:57<1:10:43,  1.40it/s]
1|19959|Loss: 1.0332759618759155:  77%|███████▋  | 19959/25880 [4:04:58<1:08:10,  1.45it/s]
1|19960|Loss: 0.8387013673782349:  77%|███████▋  | 19959/25880 [4:04:58<1:08:10,  1.45it/s]
1|19960|Loss: 0.8387013673782349:  77%|███████▋  | 19960/25880 [4:04:58<1:07:59,  1.45it/s]
1|19961|Loss: 0.8854957222938538:  77%|███████▋  | 19960/25880 [4:04:59<1:07:59,  1.45it/s]
1|19961|Loss: 0.8854957222938538:  77%|███████▋  | 19961/25880 [4:04:59<1:10:46,  1.39it/s]
1|19962|Loss: 0.7903952598571777:  77%|███████▋  | 19961/25880 [4:04:59<1:10:46,  1.39it/s]
1|19962|Loss: 0.7903952598571777:  77%|███████▋  | 19962/25880 [4:05:00<1:14:08,  1.33it/s]
1|19963|Loss: 0.8604387640953064:  77%|███████▋  | 19962/25880 [4:05:00<1:14:08,  1.33it/s]
1|19963|Loss: 0.8604387640953064:  77%|███████▋  | 19963/25880 [4:05:01<1:14:24,  1.33it/s]
1|19964|Loss: 0.9735369086265564:  77%|███████▋  | 19963/25880 [4:05:01<1:14:24,  1.33it/s]
1|19964|Loss: 0.9735369086265564:  77%|███████▋  | 19964/25880 [4:05:01<1:11:44,  1.37it/s]
1|19965|Loss: 0.8178142309188843:  77%|███████▋  | 19964/25880 [4:05:02<1:11:44,  1.37it/s]
1|19965|Loss: 0.8178142309188843:  77%|███████▋  | 19965/25880 [4:05:02<1:11:19,  1.38it/s]
1|19966|Loss: 0.8133047819137573:  77%|███████▋  | 19965/25880 [4:05:02<1:11:19,  1.38it/s]
1|19966|Loss: 0.8133047819137573:  77%|███████▋  | 19966/25880 [4:05:03<1:13:57,  1.33it/s]
1|19967|Loss: 0.8147147297859192:  77%|███████▋  | 19966/25880 [4:05:03<1:13:57,  1.33it/s]
1|19967|Loss: 0.8147147297859192:  77%|███████▋  | 19967/25880 [4:05:04<1:13:46,  1.34it/s]
1|19968|Loss: 0.9963181018829346:  77%|███████▋  | 19967/25880 [4:05:04<1:13:46,  1.34it/s]
1|19968|Loss: 0.9963181018829346:  77%|███████▋  | 19968/25880 [4:05:04<1:15:21,  1.31it/s]
1|19969|Loss: 0.85007643699646:  77%|███████▋  | 19968/25880 [4:05:05<1:15:21,  1.31it/s]  
1|19969|Loss: 0.85007643699646:  77%|███████▋  | 19969/25880 [4:05:05<1:14:46,  1.32it/s]
1|19970|Loss: 0.883073091506958:  77%|███████▋  | 19969/25880 [4:05:06<1:14:46,  1.32it/s]
1|19970|Loss: 0.883073091506958:  77%|███████▋  | 19970/25880 [4:05:06<1:13:09,  1.35it/s]
1|19971|Loss: 0.8865901827812195:  77%|███████▋  | 19970/25880 [4:05:06<1:13:09,  1.35it/s]
1|19971|Loss: 0.8865901827812195:  77%|███████▋  | 19971/25880 [4:05:06<1:09:54,  1.41it/s]
1|19972|Loss: 1.0156993865966797:  77%|███████▋  | 19971/25880 [4:05:07<1:09:54,  1.41it/s]
1|19972|Loss: 1.0156993865966797:  77%|███████▋  | 19972/25880 [4:05:07<1:04:18,  1.53it/s]
1|19973|Loss: 0.9107998609542847:  77%|███████▋  | 19972/25880 [4:05:07<1:04:18,  1.53it/s]
1|19973|Loss: 0.9107998609542847:  77%|███████▋  | 19973/25880 [4:05:08<1:05:13,  1.51it/s]
1|19974|Loss: 1.0022249221801758:  77%|███████▋  | 19973/25880 [4:05:08<1:05:13,  1.51it/s]
1|19974|Loss: 1.0022249221801758:  77%|███████▋  | 19974/25880 [4:05:08<1:07:27,  1.46it/s]
1|19975|Loss: 0.7467310428619385:  77%|███████▋  | 19974/25880 [4:05:09<1:07:27,  1.46it/s]
1|19975|Loss: 0.7467310428619385:  77%|███████▋  | 19975/25880 [4:05:09<1:11:57,  1.37it/s]
1|19976|Loss: 0.8183397650718689:  77%|███████▋  | 19975/25880 [4:05:10<1:11:57,  1.37it/s]
1|19976|Loss: 0.8183397650718689:  77%|███████▋  | 19976/25880 [4:05:10<1:06:18,  1.48it/s]
1|19977|Loss: 0.8074177503585815:  77%|███████▋  | 19976/25880 [4:05:10<1:06:18,  1.48it/s]
1|19977|Loss: 0.8074177503585815:  77%|███████▋  | 19977/25880 [4:05:10<1:06:15,  1.48it/s]
1|19978|Loss: 0.8618744611740112:  77%|███████▋  | 19977/25880 [4:05:11<1:06:15,  1.48it/s]
1|19978|Loss: 0.8618744611740112:  77%|███████▋  | 19978/25880 [4:05:11<1:05:14,  1.51it/s]
1|19979|Loss: 0.8752538561820984:  77%|███████▋  | 19978/25880 [4:05:11<1:05:14,  1.51it/s]
1|19979|Loss: 0.8752538561820984:  77%|███████▋  | 19979/25880 [4:05:12<1:03:01,  1.56it/s]
1|19980|Loss: 0.9126479625701904:  77%|███████▋  | 19979/25880 [4:05:12<1:03:01,  1.56it/s]
1|19980|Loss: 0.9126479625701904:  77%|███████▋  | 19980/25880 [4:05:12<59:41,  1.65it/s]  
1|19981|Loss: 0.9522402286529541:  77%|███████▋  | 19980/25880 [4:05:13<59:41,  1.65it/s]
1|19981|Loss: 0.9522402286529541:  77%|███████▋  | 19981/25880 [4:05:13<59:26,  1.65it/s]
1|19982|Loss: 1.024623155593872:  77%|███████▋  | 19981/25880 [4:05:13<59:26,  1.65it/s] 
1|19982|Loss: 1.024623155593872:  77%|███████▋  | 19982/25880 [4:05:13<56:13,  1.75it/s]
1|19983|Loss: 0.7868301272392273:  77%|███████▋  | 19982/25880 [4:05:14<56:13,  1.75it/s]
1|19983|Loss: 0.7868301272392273:  77%|███████▋  | 19983/25880 [4:05:14<57:03,  1.72it/s]
1|19984|Loss: 0.919560968875885:  77%|███████▋  | 19983/25880 [4:05:14<57:03,  1.72it/s] 
1|19984|Loss: 0.919560968875885:  77%|███████▋  | 19984/25880 [4:05:15<1:01:10,  1.61it/s]
1|19985|Loss: 0.8396318554878235:  77%|███████▋  | 19984/25880 [4:05:15<1:01:10,  1.61it/s]
1|19985|Loss: 0.8396318554878235:  77%|███████▋  | 19985/25880 [4:05:15<1:06:53,  1.47it/s]
1|19986|Loss: 0.8321890830993652:  77%|███████▋  | 19985/25880 [4:05:16<1:06:53,  1.47it/s]
1|19986|Loss: 0.8321890830993652:  77%|███████▋  | 19986/25880 [4:05:16<1:05:47,  1.49it/s]
1|19987|Loss: 0.9959434270858765:  77%|███████▋  | 19986/25880 [4:05:16<1:05:47,  1.49it/s]
1|19987|Loss: 0.9959434270858765:  77%|███████▋  | 19987/25880 [4:05:17<1:06:41,  1.47it/s]
1|19988|Loss: 0.8011597394943237:  77%|███████▋  | 19987/25880 [4:05:17<1:06:41,  1.47it/s]
1|19988|Loss: 0.8011597394943237:  77%|███████▋  | 19988/25880 [4:05:17<1:05:37,  1.50it/s]
1|19989|Loss: 0.768017053604126:  77%|███████▋  | 19988/25880 [4:05:18<1:05:37,  1.50it/s] 
1|19989|Loss: 0.768017053604126:  77%|███████▋  | 19989/25880 [4:05:18<1:11:27,  1.37it/s]
1|19990|Loss: 0.9015354514122009:  77%|███████▋  | 19989/25880 [4:05:19<1:11:27,  1.37it/s]
1|19990|Loss: 0.9015354514122009:  77%|███████▋  | 19990/25880 [4:05:19<1:07:39,  1.45it/s]
1|19991|Loss: 0.8909581899642944:  77%|███████▋  | 19990/25880 [4:05:19<1:07:39,  1.45it/s]
1|19991|Loss: 0.8909581899642944:  77%|███████▋  | 19991/25880 [4:05:20<1:11:54,  1.36it/s]
1|19992|Loss: 0.6980155110359192:  77%|███████▋  | 19991/25880 [4:05:20<1:11:54,  1.36it/s]
1|19992|Loss: 0.6980155110359192:  77%|███████▋  | 19992/25880 [4:05:20<1:12:50,  1.35it/s]
1|19993|Loss: 0.67125004529953:  77%|███████▋  | 19992/25880 [4:05:21<1:12:50,  1.35it/s]  
1|19993|Loss: 0.67125004529953:  77%|███████▋  | 19993/25880 [4:05:21<1:09:50,  1.40it/s]
1|19994|Loss: 0.8435280323028564:  77%|███████▋  | 19993/25880 [4:05:22<1:09:50,  1.40it/s]
1|19994|Loss: 0.8435280323028564:  77%|███████▋  | 19994/25880 [4:05:22<1:09:00,  1.42it/s]
1|19995|Loss: 0.7776029109954834:  77%|███████▋  | 19994/25880 [4:05:22<1:09:00,  1.42it/s]
1|19995|Loss: 0.7776029109954834:  77%|███████▋  | 19995/25880 [4:05:22<1:06:55,  1.47it/s]
1|19996|Loss: 0.8347913026809692:  77%|███████▋  | 19995/25880 [4:05:23<1:06:55,  1.47it/s]
1|19996|Loss: 0.8347913026809692:  77%|███████▋  | 19996/25880 [4:05:23<1:09:19,  1.41it/s]
1|19997|Loss: 0.803981363773346:  77%|███████▋  | 19996/25880 [4:05:24<1:09:19,  1.41it/s] 
1|19997|Loss: 0.803981363773346:  77%|███████▋  | 19997/25880 [4:05:24<1:09:45,  1.41it/s]
1|19998|Loss: 0.8615670204162598:  77%|███████▋  | 19997/25880 [4:05:24<1:09:45,  1.41it/s]
1|19998|Loss: 0.8615670204162598:  77%|███████▋  | 19998/25880 [4:05:25<1:07:28,  1.45it/s]
1|19999|Loss: 0.7017617225646973:  77%|███████▋  | 19998/25880 [4:05:25<1:07:28,  1.45it/s]
1|19999|Loss: 0.7017617225646973:  77%|███████▋  | 19999/25880 [4:05:25<1:06:07,  1.48it/s]
1|20000|Loss: 0.845727801322937:  77%|███████▋  | 19999/25880 [4:05:26<1:06:07,  1.48it/s] 
1|20000|Loss: 0.845727801322937:  77%|███████▋  | 20000/25880 [4:05:26<1:03:47,  1.54it/s]
1|20001|Loss: 0.8935768008232117:  77%|███████▋  | 20000/25880 [4:05:26<1:03:47,  1.54it/s]
1|20001|Loss: 0.8935768008232117:  77%|███████▋  | 20001/25880 [4:05:27<1:07:00,  1.46it/s]
1|20002|Loss: 0.7915931344032288:  77%|███████▋  | 20001/25880 [4:05:27<1:07:00,  1.46it/s]
1|20002|Loss: 0.7915931344032288:  77%|███████▋  | 20002/25880 [4:05:27<1:06:04,  1.48it/s]
1|20003|Loss: 0.8831510543823242:  77%|███████▋  | 20002/25880 [4:05:28<1:06:04,  1.48it/s]
1|20003|Loss: 0.8831510543823242:  77%|███████▋  | 20003/25880 [4:05:28<1:08:24,  1.43it/s]
1|20004|Loss: 0.8295325636863708:  77%|███████▋  | 20003/25880 [4:05:28<1:08:24,  1.43it/s]
1|20004|Loss: 0.8295325636863708:  77%|███████▋  | 20004/25880 [4:05:29<1:12:52,  1.34it/s]
1|20005|Loss: 1.0182459354400635:  77%|███████▋  | 20004/25880 [4:05:29<1:12:52,  1.34it/s]
1|20005|Loss: 1.0182459354400635:  77%|███████▋  | 20005/25880 [4:05:30<1:15:09,  1.30it/s]
1|20006|Loss: 0.8724881410598755:  77%|███████▋  | 20005/25880 [4:05:30<1:15:09,  1.30it/s]
1|20006|Loss: 0.8724881410598755:  77%|███████▋  | 20006/25880 [4:05:31<1:19:50,  1.23it/s]
1|20007|Loss: 0.802768349647522:  77%|███████▋  | 20006/25880 [4:05:31<1:19:50,  1.23it/s] 
1|20007|Loss: 0.802768349647522:  77%|███████▋  | 20007/25880 [4:05:31<1:16:29,  1.28it/s]
1|20008|Loss: 0.8065643310546875:  77%|███████▋  | 20007/25880 [4:05:32<1:16:29,  1.28it/s]
1|20008|Loss: 0.8065643310546875:  77%|███████▋  | 20008/25880 [4:05:32<1:16:51,  1.27it/s]
1|20009|Loss: 0.8680754899978638:  77%|███████▋  | 20008/25880 [4:05:33<1:16:51,  1.27it/s]
1|20009|Loss: 0.8680754899978638:  77%|███████▋  | 20009/25880 [4:05:33<1:19:20,  1.23it/s]
1|20010|Loss: 0.8440093994140625:  77%|███████▋  | 20009/25880 [4:05:34<1:19:20,  1.23it/s]
1|20010|Loss: 0.8440093994140625:  77%|███████▋  | 20010/25880 [4:05:34<1:31:14,  1.07it/s]
1|20011|Loss: 0.7240204215049744:  77%|███████▋  | 20010/25880 [4:05:35<1:31:14,  1.07it/s]
1|20011|Loss: 0.7240204215049744:  77%|███████▋  | 20011/25880 [4:05:35<1:26:32,  1.13it/s]
1|20012|Loss: 0.760595977306366:  77%|███████▋  | 20011/25880 [4:05:35<1:26:32,  1.13it/s] 
1|20012|Loss: 0.760595977306366:  77%|███████▋  | 20012/25880 [4:05:36<1:21:33,  1.20it/s]
1|20013|Loss: 0.8248032927513123:  77%|███████▋  | 20012/25880 [4:05:36<1:21:33,  1.20it/s]
1|20013|Loss: 0.8248032927513123:  77%|███████▋  | 20013/25880 [4:05:37<1:22:45,  1.18it/s]
1|20014|Loss: 0.8252687454223633:  77%|███████▋  | 20013/25880 [4:05:37<1:22:45,  1.18it/s]
1|20014|Loss: 0.8252687454223633:  77%|███████▋  | 20014/25880 [4:05:37<1:20:33,  1.21it/s]
1|20015|Loss: 0.9169349074363708:  77%|███████▋  | 20014/25880 [4:05:38<1:20:33,  1.21it/s]
1|20015|Loss: 0.9169349074363708:  77%|███████▋  | 20015/25880 [4:05:38<1:15:39,  1.29it/s]
1|20016|Loss: 0.780540406703949:  77%|███████▋  | 20015/25880 [4:05:38<1:15:39,  1.29it/s] 
1|20016|Loss: 0.780540406703949:  77%|███████▋  | 20016/25880 [4:05:39<1:11:45,  1.36it/s]
1|20017|Loss: 0.7737016677856445:  77%|███████▋  | 20016/25880 [4:05:39<1:11:45,  1.36it/s]
1|20017|Loss: 0.7737016677856445:  77%|███████▋  | 20017/25880 [4:05:39<1:08:36,  1.42it/s]
1|20018|Loss: 0.9607844352722168:  77%|███████▋  | 20017/25880 [4:05:40<1:08:36,  1.42it/s]
1|20018|Loss: 0.9607844352722168:  77%|███████▋  | 20018/25880 [4:05:40<1:11:23,  1.37it/s]
1|20019|Loss: 0.8727133274078369:  77%|███████▋  | 20018/25880 [4:05:40<1:11:23,  1.37it/s]
1|20019|Loss: 0.8727133274078369:  77%|███████▋  | 20019/25880 [4:05:41<1:09:57,  1.40it/s]
1|20020|Loss: 0.846877932548523:  77%|███████▋  | 20019/25880 [4:05:41<1:09:57,  1.40it/s] 
1|20020|Loss: 0.846877932548523:  77%|███████▋  | 20020/25880 [4:05:42<1:13:16,  1.33it/s]
1|20021|Loss: 0.8755040764808655:  77%|███████▋  | 20020/25880 [4:05:42<1:13:16,  1.33it/s]
1|20021|Loss: 0.8755040764808655:  77%|███████▋  | 20021/25880 [4:05:42<1:11:32,  1.36it/s]
1|20022|Loss: 0.7438715100288391:  77%|███████▋  | 20021/25880 [4:05:43<1:11:32,  1.36it/s]
1|20022|Loss: 0.7438715100288391:  77%|███████▋  | 20022/25880 [4:05:43<1:08:40,  1.42it/s]
1|20023|Loss: 0.9392663836479187:  77%|███████▋  | 20022/25880 [4:05:43<1:08:40,  1.42it/s]
1|20023|Loss: 0.9392663836479187:  77%|███████▋  | 20023/25880 [4:05:44<1:06:52,  1.46it/s]
1|20024|Loss: 0.6896467208862305:  77%|███████▋  | 20023/25880 [4:05:44<1:06:52,  1.46it/s]
1|20024|Loss: 0.6896467208862305:  77%|███████▋  | 20024/25880 [4:05:44<1:09:52,  1.40it/s]
1|20025|Loss: 0.809461772441864:  77%|███████▋  | 20024/25880 [4:05:45<1:09:52,  1.40it/s] 
1|20025|Loss: 0.809461772441864:  77%|███████▋  | 20025/25880 [4:05:45<1:08:01,  1.43it/s]
1|20026|Loss: 0.750927209854126:  77%|███████▋  | 20025/25880 [4:05:45<1:08:01,  1.43it/s]
1|20026|Loss: 0.750927209854126:  77%|███████▋  | 20026/25880 [4:05:46<1:08:30,  1.42it/s]
1|20027|Loss: 0.7932950258255005:  77%|███████▋  | 20026/25880 [4:05:46<1:08:30,  1.42it/s]
1|20027|Loss: 0.7932950258255005:  77%|███████▋  | 20027/25880 [4:05:46<1:08:56,  1.41it/s]
1|20028|Loss: 0.8799754977226257:  77%|███████▋  | 20027/25880 [4:05:47<1:08:56,  1.41it/s]
1|20028|Loss: 0.8799754977226257:  77%|███████▋  | 20028/25880 [4:05:47<1:13:14,  1.33it/s]
1|20029|Loss: 0.7847414612770081:  77%|███████▋  | 20028/25880 [4:05:48<1:13:14,  1.33it/s]
1|20029|Loss: 0.7847414612770081:  77%|███████▋  | 20029/25880 [4:05:48<1:11:34,  1.36it/s]
1|20030|Loss: 0.7981998324394226:  77%|███████▋  | 20029/25880 [4:05:48<1:11:34,  1.36it/s]
1|20030|Loss: 0.7981998324394226:  77%|███████▋  | 20030/25880 [4:05:49<1:14:09,  1.31it/s]
1|20031|Loss: 0.6107595562934875:  77%|███████▋  | 20030/25880 [4:05:49<1:14:09,  1.31it/s]
1|20031|Loss: 0.6107595562934875:  77%|███████▋  | 20031/25880 [4:05:49<1:12:07,  1.35it/s]
1|20032|Loss: 0.8262139558792114:  77%|███████▋  | 20031/25880 [4:05:50<1:12:07,  1.35it/s]
1|20032|Loss: 0.8262139558792114:  77%|███████▋  | 20032/25880 [4:05:50<1:08:39,  1.42it/s]
1|20033|Loss: 0.8519321084022522:  77%|███████▋  | 20032/25880 [4:05:50<1:08:39,  1.42it/s]
1|20033|Loss: 0.8519321084022522:  77%|███████▋  | 20033/25880 [4:05:51<1:08:04,  1.43it/s]
1|20034|Loss: 0.7800281047821045:  77%|███████▋  | 20033/25880 [4:05:51<1:08:04,  1.43it/s]
1|20034|Loss: 0.7800281047821045:  77%|███████▋  | 20034/25880 [4:05:51<1:08:47,  1.42it/s]
1|20035|Loss: 0.8841092586517334:  77%|███████▋  | 20034/25880 [4:05:52<1:08:47,  1.42it/s]
1|20035|Loss: 0.8841092586517334:  77%|███████▋  | 20035/25880 [4:05:52<1:13:52,  1.32it/s]
1|20036|Loss: 0.8935109972953796:  77%|███████▋  | 20035/25880 [4:05:53<1:13:52,  1.32it/s]
1|20036|Loss: 0.8935109972953796:  77%|███████▋  | 20036/25880 [4:05:53<1:13:26,  1.33it/s]
1|20037|Loss: 0.7482768893241882:  77%|███████▋  | 20036/25880 [4:05:54<1:13:26,  1.33it/s]
1|20037|Loss: 0.7482768893241882:  77%|███████▋  | 20037/25880 [4:05:54<1:14:15,  1.31it/s]
1|20038|Loss: 0.767434298992157:  77%|███████▋  | 20037/25880 [4:05:54<1:14:15,  1.31it/s] 
1|20038|Loss: 0.767434298992157:  77%|███████▋  | 20038/25880 [4:05:55<1:21:19,  1.20it/s]
1|20039|Loss: 0.7003995180130005:  77%|███████▋  | 20038/25880 [4:05:55<1:21:19,  1.20it/s]
1|20039|Loss: 0.7003995180130005:  77%|███████▋  | 20039/25880 [4:05:56<1:18:06,  1.25it/s]
1|20040|Loss: 0.7987955808639526:  77%|███████▋  | 20039/25880 [4:05:56<1:18:06,  1.25it/s]
1|20040|Loss: 0.7987955808639526:  77%|███████▋  | 20040/25880 [4:05:56<1:15:21,  1.29it/s]
1|20041|Loss: 0.8732496500015259:  77%|███████▋  | 20040/25880 [4:05:57<1:15:21,  1.29it/s]
1|20041|Loss: 0.8732496500015259:  77%|███████▋  | 20041/25880 [4:05:57<1:16:47,  1.27it/s]
1|20042|Loss: 0.8837488293647766:  77%|███████▋  | 20041/25880 [4:05:58<1:16:47,  1.27it/s]
1|20042|Loss: 0.8837488293647766:  77%|███████▋  | 20042/25880 [4:05:58<1:16:22,  1.27it/s]
1|20043|Loss: 0.9404880404472351:  77%|███████▋  | 20042/25880 [4:05:58<1:16:22,  1.27it/s]
1|20043|Loss: 0.9404880404472351:  77%|███████▋  | 20043/25880 [4:05:59<1:12:30,  1.34it/s]
1|20044|Loss: 0.6700842380523682:  77%|███████▋  | 20043/25880 [4:05:59<1:12:30,  1.34it/s]
1|20044|Loss: 0.6700842380523682:  77%|███████▋  | 20044/25880 [4:05:59<1:12:39,  1.34it/s]
1|20045|Loss: 0.8334826827049255:  77%|███████▋  | 20044/25880 [4:06:00<1:12:39,  1.34it/s]
1|20045|Loss: 0.8334826827049255:  77%|███████▋  | 20045/25880 [4:06:00<1:15:25,  1.29it/s]
1|20046|Loss: 0.9372045397758484:  77%|███████▋  | 20045/25880 [4:06:01<1:15:25,  1.29it/s]
1|20046|Loss: 0.9372045397758484:  77%|███████▋  | 20046/25880 [4:06:01<1:15:08,  1.29it/s]
1|20047|Loss: 0.8326172828674316:  77%|███████▋  | 20046/25880 [4:06:01<1:15:08,  1.29it/s]
1|20047|Loss: 0.8326172828674316:  77%|███████▋  | 20047/25880 [4:06:02<1:11:56,  1.35it/s]
1|20048|Loss: 0.7530921101570129:  77%|███████▋  | 20047/25880 [4:06:02<1:11:56,  1.35it/s]
1|20048|Loss: 0.7530921101570129:  77%|███████▋  | 20048/25880 [4:06:02<1:09:02,  1.41it/s]
1|20049|Loss: 0.9578306674957275:  77%|███████▋  | 20048/25880 [4:06:03<1:09:02,  1.41it/s]
1|20049|Loss: 0.9578306674957275:  77%|███████▋  | 20049/25880 [4:06:03<1:10:58,  1.37it/s]
1|20050|Loss: 0.9578437209129333:  77%|███████▋  | 20049/25880 [4:06:03<1:10:58,  1.37it/s]
1|20050|Loss: 0.9578437209129333:  77%|███████▋  | 20050/25880 [4:06:04<1:04:56,  1.50it/s]
1|20051|Loss: 0.798138439655304:  77%|███████▋  | 20050/25880 [4:06:04<1:04:56,  1.50it/s] 
1|20051|Loss: 0.798138439655304:  77%|███████▋  | 20051/25880 [4:06:04<1:04:15,  1.51it/s]
1|20052|Loss: 0.5725930333137512:  77%|███████▋  | 20051/25880 [4:06:05<1:04:15,  1.51it/s]
1|20052|Loss: 0.5725930333137512:  77%|███████▋  | 20052/25880 [4:06:05<1:11:34,  1.36it/s]
1|20053|Loss: 0.6719628572463989:  77%|███████▋  | 20052/25880 [4:06:05<1:11:34,  1.36it/s]
1|20053|Loss: 0.6719628572463989:  77%|███████▋  | 20053/25880 [4:06:06<1:08:43,  1.41it/s]
1|20054|Loss: 0.7364686727523804:  77%|███████▋  | 20053/25880 [4:06:06<1:08:43,  1.41it/s]
1|20054|Loss: 0.7364686727523804:  77%|███████▋  | 20054/25880 [4:06:06<1:09:41,  1.39it/s]
1|20055|Loss: 0.8501118421554565:  77%|███████▋  | 20054/25880 [4:06:07<1:09:41,  1.39it/s]
1|20055|Loss: 0.8501118421554565:  77%|███████▋  | 20055/25880 [4:06:07<1:13:00,  1.33it/s]
1|20056|Loss: 0.954446017742157:  77%|███████▋  | 20055/25880 [4:06:08<1:13:00,  1.33it/s] 
1|20056|Loss: 0.954446017742157:  77%|███████▋  | 20056/25880 [4:06:08<1:13:00,  1.33it/s]
1|20057|Loss: 0.7806100249290466:  77%|███████▋  | 20056/25880 [4:06:09<1:13:00,  1.33it/s]
1|20057|Loss: 0.7806100249290466:  78%|███████▊  | 20057/25880 [4:06:09<1:16:46,  1.26it/s]
1|20058|Loss: 0.7899311184883118:  78%|███████▊  | 20057/25880 [4:06:09<1:16:46,  1.26it/s]
1|20058|Loss: 0.7899311184883118:  78%|███████▊  | 20058/25880 [4:06:10<1:12:49,  1.33it/s]
1|20059|Loss: 0.810158908367157:  78%|███████▊  | 20058/25880 [4:06:10<1:12:49,  1.33it/s] 
1|20059|Loss: 0.810158908367157:  78%|███████▊  | 20059/25880 [4:06:10<1:11:21,  1.36it/s]
1|20060|Loss: 0.9962839484214783:  78%|███████▊  | 20059/25880 [4:06:11<1:11:21,  1.36it/s]
1|20060|Loss: 0.9962839484214783:  78%|███████▊  | 20060/25880 [4:06:11<1:11:13,  1.36it/s]
1|20061|Loss: 0.8044156432151794:  78%|███████▊  | 20060/25880 [4:06:11<1:11:13,  1.36it/s]
1|20061|Loss: 0.8044156432151794:  78%|███████▊  | 20061/25880 [4:06:12<1:11:42,  1.35it/s]
1|20062|Loss: 0.9138795733451843:  78%|███████▊  | 20061/25880 [4:06:12<1:11:42,  1.35it/s]
1|20062|Loss: 0.9138795733451843:  78%|███████▊  | 20062/25880 [4:06:12<1:09:03,  1.40it/s]
1|20063|Loss: 0.8889389038085938:  78%|███████▊  | 20062/25880 [4:06:13<1:09:03,  1.40it/s]
1|20063|Loss: 0.8889389038085938:  78%|███████▊  | 20063/25880 [4:06:13<1:12:34,  1.34it/s]
1|20064|Loss: 0.8583157062530518:  78%|███████▊  | 20063/25880 [4:06:14<1:12:34,  1.34it/s]
1|20064|Loss: 0.8583157062530518:  78%|███████▊  | 20064/25880 [4:06:14<1:12:54,  1.33it/s]
1|20065|Loss: 0.9312640428543091:  78%|███████▊  | 20064/25880 [4:06:14<1:12:54,  1.33it/s]
1|20065|Loss: 0.9312640428543091:  78%|███████▊  | 20065/25880 [4:06:15<1:09:06,  1.40it/s]
1|20066|Loss: 0.9314598441123962:  78%|███████▊  | 20065/25880 [4:06:15<1:09:06,  1.40it/s]
1|20066|Loss: 0.9314598441123962:  78%|███████▊  | 20066/25880 [4:06:15<1:11:11,  1.36it/s]
1|20067|Loss: 0.7760049700737:  78%|███████▊  | 20066/25880 [4:06:16<1:11:11,  1.36it/s]   
1|20067|Loss: 0.7760049700737:  78%|███████▊  | 20067/25880 [4:06:16<1:13:54,  1.31it/s]
1|20068|Loss: 1.0815335512161255:  78%|███████▊  | 20067/25880 [4:06:17<1:13:54,  1.31it/s]
1|20068|Loss: 1.0815335512161255:  78%|███████▊  | 20068/25880 [4:06:17<1:14:45,  1.30it/s]
1|20069|Loss: 0.8992013931274414:  78%|███████▊  | 20068/25880 [4:06:17<1:14:45,  1.30it/s]
1|20069|Loss: 0.8992013931274414:  78%|███████▊  | 20069/25880 [4:06:18<1:14:06,  1.31it/s]
1|20070|Loss: 0.8513219952583313:  78%|███████▊  | 20069/25880 [4:06:18<1:14:06,  1.31it/s]
1|20070|Loss: 0.8513219952583313:  78%|███████▊  | 20070/25880 [4:06:19<1:15:50,  1.28it/s]
1|20071|Loss: 0.7944523096084595:  78%|███████▊  | 20070/25880 [4:06:19<1:15:50,  1.28it/s]
1|20071|Loss: 0.7944523096084595:  78%|███████▊  | 20071/25880 [4:06:19<1:15:09,  1.29it/s]
1|20072|Loss: 0.8653333783149719:  78%|███████���  | 20071/25880 [4:06:20<1:15:09,  1.29it/s]
1|20072|Loss: 0.8653333783149719:  78%|███████▊  | 20072/25880 [4:06:20<1:13:54,  1.31it/s]
1|20073|Loss: 0.9191677570343018:  78%|███████▊  | 20072/25880 [4:06:21<1:13:54,  1.31it/s]
1|20073|Loss: 0.9191677570343018:  78%|███████▊  | 20073/25880 [4:06:21<1:14:36,  1.30it/s]
1|20074|Loss: 0.9976992011070251:  78%|███████▊  | 20073/25880 [4:06:21<1:14:36,  1.30it/s]
1|20074|Loss: 0.9976992011070251:  78%|███████▊  | 20074/25880 [4:06:22<1:16:07,  1.27it/s]
1|20075|Loss: 0.8408479690551758:  78%|███████▊  | 20074/25880 [4:06:22<1:16:07,  1.27it/s]
1|20075|Loss: 0.8408479690551758:  78%|███████▊  | 20075/25880 [4:06:23<1:17:16,  1.25it/s]
1|20076|Loss: 0.865017294883728:  78%|███████▊  | 20075/25880 [4:06:23<1:17:16,  1.25it/s] 
1|20076|Loss: 0.865017294883728:  78%|███████▊  | 20076/25880 [4:06:23<1:15:08,  1.29it/s]
1|20077|Loss: 0.9435538649559021:  78%|███████▊  | 20076/25880 [4:06:24<1:15:08,  1.29it/s]
1|20077|Loss: 0.9435538649559021:  78%|███████▊  | 20077/25880 [4:06:24<1:11:21,  1.36it/s]
1|20078|Loss: 0.8417130708694458:  78%|███████▊  | 20077/25880 [4:06:24<1:11:21,  1.36it/s]
1|20078|Loss: 0.8417130708694458:  78%|███████▊  | 20078/25880 [4:06:25<1:10:51,  1.36it/s]
1|20079|Loss: 0.8024228811264038:  78%|███████▊  | 20078/25880 [4:06:25<1:10:51,  1.36it/s]
1|20079|Loss: 0.8024228811264038:  78%|███████▊  | 20079/25880 [4:06:26<1:15:14,  1.28it/s]
1|20080|Loss: 0.8108426928520203:  78%|███████▊  | 20079/25880 [4:06:26<1:15:14,  1.28it/s]
1|20080|Loss: 0.8108426928520203:  78%|███████▊  | 20080/25880 [4:06:26<1:16:24,  1.27it/s]
1|20081|Loss: 0.7942680716514587:  78%|███████▊  | 20080/25880 [4:06:27<1:16:24,  1.27it/s]
1|20081|Loss: 0.7942680716514587:  78%|███████▊  | 20081/25880 [4:06:27<1:13:01,  1.32it/s]
1|20082|Loss: 0.753663957118988:  78%|███████▊  | 20081/25880 [4:06:27<1:13:01,  1.32it/s] 
1|20082|Loss: 0.753663957118988:  78%|███████▊  | 20082/25880 [4:06:28<1:16:20,  1.27it/s]
1|20083|Loss: 0.9161831736564636:  78%|███████▊  | 20082/25880 [4:06:28<1:16:20,  1.27it/s]
1|20083|Loss: 0.9161831736564636:  78%|███████▊  | 20083/25880 [4:06:29<1:16:04,  1.27it/s]
1|20084|Loss: 0.8340529203414917:  78%|███████▊  | 20083/25880 [4:06:29<1:16:04,  1.27it/s]
1|20084|Loss: 0.8340529203414917:  78%|███████▊  | 20084/25880 [4:06:29<1:12:36,  1.33it/s]
1|20085|Loss: 0.9129968285560608:  78%|███████▊  | 20084/25880 [4:06:30<1:12:36,  1.33it/s]
1|20085|Loss: 0.9129968285560608:  78%|███████▊  | 20085/25880 [4:06:30<1:09:00,  1.40it/s]
1|20086|Loss: 1.0157322883605957:  78%|███████▊  | 20085/25880 [4:06:30<1:09:00,  1.40it/s]
1|20086|Loss: 1.0157322883605957:  78%|███████▊  | 20086/25880 [4:06:31<1:11:12,  1.36it/s]
1|20087|Loss: 0.895905077457428:  78%|███████▊  | 20086/25880 [4:06:31<1:11:12,  1.36it/s] 
1|20087|Loss: 0.895905077457428:  78%|███████▊  | 20087/25880 [4:06:32<1:15:45,  1.27it/s]
1|20088|Loss: 0.8377460241317749:  78%|███████▊  | 20087/25880 [4:06:32<1:15:45,  1.27it/s]
1|20088|Loss: 0.8377460241317749:  78%|███████▊  | 20088/25880 [4:06:32<1:16:51,  1.26it/s]
1|20089|Loss: 0.815398633480072:  78%|███████▊  | 20088/25880 [4:06:33<1:16:51,  1.26it/s] 
1|20089|Loss: 0.815398633480072:  78%|███████▊  | 20089/25880 [4:06:33<1:13:18,  1.32it/s]
1|20090|Loss: 0.7777056694030762:  78%|███████▊  | 20089/25880 [4:06:34<1:13:18,  1.32it/s]
1|20090|Loss: 0.7777056694030762:  78%|███████▊  | 20090/25880 [4:06:34<1:12:14,  1.34it/s]
1|20091|Loss: 0.6655241847038269:  78%|███████▊  | 20090/25880 [4:06:34<1:12:14,  1.34it/s]
1|20091|Loss: 0.6655241847038269:  78%|███████▊  | 20091/25880 [4:06:35<1:15:06,  1.28it/s]
1|20092|Loss: 0.8516833782196045:  78%|███████▊  | 20091/25880 [4:06:35<1:15:06,  1.28it/s]
1|20092|Loss: 0.8516833782196045:  78%|███████▊  | 20092/25880 [4:06:35<1:12:08,  1.34it/s]
1|20093|Loss: 0.7761574387550354:  78%|███████▊  | 20092/25880 [4:06:36<1:12:08,  1.34it/s]
1|20093|Loss: 0.7761574387550354:  78%|███████▊  | 20093/25880 [4:06:36<1:08:33,  1.41it/s]
1|20094|Loss: 0.775779128074646:  78%|███████▊  | 20093/25880 [4:06:36<1:08:33,  1.41it/s] 
1|20094|Loss: 0.775779128074646:  78%|███████▊  | 20094/25880 [4:06:37<1:06:31,  1.45it/s]
1|20095|Loss: 0.9797746539115906:  78%|███████▊  | 20094/25880 [4:06:37<1:06:31,  1.45it/s]
1|20095|Loss: 0.9797746539115906:  78%|███████▊  | 20095/25880 [4:06:37<1:09:29,  1.39it/s]
1|20096|Loss: 0.766851007938385:  78%|███████▊  | 20095/25880 [4:06:38<1:09:29,  1.39it/s] 
1|20096|Loss: 0.766851007938385:  78%|███████▊  | 20096/25880 [4:06:38<1:09:55,  1.38it/s]
1|20097|Loss: 0.8668236136436462:  78%|███████▊  | 20096/25880 [4:06:39<1:09:55,  1.38it/s]
1|20097|Loss: 0.8668236136436462:  78%|███████▊  | 20097/25880 [4:06:39<1:12:26,  1.33it/s]
1|20098|Loss: 0.8320731520652771:  78%|███████▊  | 20097/25880 [4:06:39<1:12:26,  1.33it/s]
1|20098|Loss: 0.8320731520652771:  78%|███████▊  | 20098/25880 [4:06:40<1:12:36,  1.33it/s]
1|20099|Loss: 0.9265486001968384:  78%|███████▊  | 20098/25880 [4:06:40<1:12:36,  1.33it/s]
1|20099|Loss: 0.9265486001968384:  78%|███████▊  | 20099/25880 [4:06:40<1:09:53,  1.38it/s]
1|20100|Loss: 0.8813173770904541:  78%|███████▊  | 20099/25880 [4:06:41<1:09:53,  1.38it/s]
1|20100|Loss: 0.8813173770904541:  78%|███████▊  | 20100/25880 [4:06:41<1:06:05,  1.46it/s]
1|20101|Loss: 0.7694992423057556:  78%|███████▊  | 20100/25880 [4:06:41<1:06:05,  1.46it/s]
1|20101|Loss: 0.7694992423057556:  78%|███████▊  | 20101/25880 [4:06:42<1:04:18,  1.50it/s]
1|20102|Loss: 0.7772548198699951:  78%|███████▊  | 20101/25880 [4:06:42<1:04:18,  1.50it/s]
1|20102|Loss: 0.7772548198699951:  78%|███████▊  | 20102/25880 [4:06:42<1:05:39,  1.47it/s]
1|20103|Loss: 0.7112991213798523:  78%|███████▊  | 20102/25880 [4:06:43<1:05:39,  1.47it/s]
1|20103|Loss: 0.7112991213798523:  78%|███████▊  | 20103/25880 [4:06:43<1:04:52,  1.48it/s]
1|20104|Loss: 0.8000186681747437:  78%|███████▊  | 20103/25880 [4:06:43<1:04:52,  1.48it/s]
1|20104|Loss: 0.8000186681747437:  78%|███████▊  | 20104/25880 [4:06:44<1:08:17,  1.41it/s]
1|20105|Loss: 0.7298474907875061:  78%|███████▊  | 20104/25880 [4:06:44<1:08:17,  1.41it/s]
1|20105|Loss: 0.7298474907875061:  78%|███████▊  | 20105/25880 [4:06:44<1:06:12,  1.45it/s]
1|20106|Loss: 0.6530848741531372:  78%|███████▊  | 20105/25880 [4:06:45<1:06:12,  1.45it/s]
1|20106|Loss: 0.6530848741531372:  78%|███████▊  | 20106/25880 [4:06:45<1:10:06,  1.37it/s]
1|20107|Loss: 0.8428613543510437:  78%|███████▊  | 20106/25880 [4:06:46<1:10:06,  1.37it/s]
1|20107|Loss: 0.8428613543510437:  78%|███████▊  | 20107/25880 [4:06:46<1:14:30,  1.29it/s]
1|20108|Loss: 0.7984617352485657:  78%|███████▊  | 20107/25880 [4:06:47<1:14:30,  1.29it/s]
1|20108|Loss: 0.7984617352485657:  78%|███████▊  | 20108/25880 [4:06:47<1:11:06,  1.35it/s]
1|20109|Loss: 0.9352105259895325:  78%|███████▊  | 20108/25880 [4:06:47<1:11:06,  1.35it/s]
1|20109|Loss: 0.9352105259895325:  78%|███████▊  | 20109/25880 [4:06:47<1:06:39,  1.44it/s]
1|20110|Loss: 0.8523196578025818:  78%|███████▊  | 20109/25880 [4:06:48<1:06:39,  1.44it/s]
1|20110|Loss: 0.8523196578025818:  78%|███████▊  | 20110/25880 [4:06:48<1:06:43,  1.44it/s]
1|20111|Loss: 0.7554346323013306:  78%|███████▊  | 20110/25880 [4:06:48<1:06:43,  1.44it/s]
1|20111|Loss: 0.7554346323013306:  78%|███████▊  | 20111/25880 [4:06:49<1:05:39,  1.46it/s]
1|20112|Loss: 1.2041280269622803:  78%|███████▊  | 20111/25880 [4:06:49<1:05:39,  1.46it/s]
1|20112|Loss: 1.2041280269622803:  78%|███████▊  | 20112/25880 [4:06:49<1:06:34,  1.44it/s]
1|20113|Loss: 0.6966177821159363:  78%|███████▊  | 20112/25880 [4:06:50<1:06:34,  1.44it/s]
1|20113|Loss: 0.6966177821159363:  78%|███████▊  | 20113/25880 [4:06:50<1:09:47,  1.38it/s]
1|20114|Loss: 0.837172269821167:  78%|███████▊  | 20113/25880 [4:06:51<1:09:47,  1.38it/s] 
1|20114|Loss: 0.837172269821167:  78%|███████▊  | 20114/25880 [4:06:51<1:12:47,  1.32it/s]
1|20115|Loss: 0.8101775646209717:  78%|███████▊  | 20114/25880 [4:06:51<1:12:47,  1.32it/s]
1|20115|Loss: 0.8101775646209717:  78%|███████▊  | 20115/25880 [4:06:52<1:09:50,  1.38it/s]
1|20116|Loss: 0.767864465713501:  78%|███████▊  | 20115/25880 [4:06:52<1:09:50,  1.38it/s] 
1|20116|Loss: 0.767864465713501:  78%|███████▊  | 20116/25880 [4:06:52<1:05:49,  1.46it/s]
1|20117|Loss: 0.7813238501548767:  78%|███████▊  | 20116/25880 [4:06:53<1:05:49,  1.46it/s]
1|20117|Loss: 0.7813238501548767:  78%|███████▊  | 20117/25880 [4:06:53<1:02:51,  1.53it/s]
1|20118|Loss: 0.7734871506690979:  78%|███████▊  | 20117/25880 [4:06:53<1:02:51,  1.53it/s]
1|20118|Loss: 0.7734871506690979:  78%|███████▊  | 20118/25880 [4:06:53<58:30,  1.64it/s]  
1|20119|Loss: 0.8425515294075012:  78%|███████▊  | 20118/25880 [4:06:54<58:30,  1.64it/s]
1|20119|Loss: 0.8425515294075012:  78%|███████▊  | 20119/25880 [4:06:54<58:21,  1.65it/s]
1|20120|Loss: 0.9145058393478394:  78%|███████▊  | 20119/25880 [4:06:54<58:21,  1.65it/s]
1|20120|Loss: 0.9145058393478394:  78%|███████▊  | 20120/25880 [4:06:55<1:03:58,  1.50it/s]
1|20121|Loss: 0.8393504619598389:  78%|███████▊  | 20120/25880 [4:06:55<1:03:58,  1.50it/s]
1|20121|Loss: 0.8393504619598389:  78%|███████▊  | 20121/25880 [4:06:56<1:07:45,  1.42it/s]
1|20122|Loss: 0.756325900554657:  78%|███████▊  | 20121/25880 [4:06:56<1:07:45,  1.42it/s] 
1|20122|Loss: 0.756325900554657:  78%|███████▊  | 20122/25880 [4:06:56<1:10:07,  1.37it/s]
1|20123|Loss: 0.8189638257026672:  78%|███████▊  | 20122/25880 [4:06:57<1:10:07,  1.37it/s]
1|20123|Loss: 0.8189638257026672:  78%|███████▊  | 20123/25880 [4:06:57<1:14:37,  1.29it/s]
1|20124|Loss: 0.8555586338043213:  78%|███████▊  | 20123/25880 [4:06:58<1:14:37,  1.29it/s]
1|20124|Loss: 0.8555586338043213:  78%|███████▊  | 20124/25880 [4:06:58<1:11:08,  1.35it/s]
1|20125|Loss: 0.7973803281784058:  78%|███████▊  | 20124/25880 [4:06:58<1:11:08,  1.35it/s]
1|20125|Loss: 0.7973803281784058:  78%|███████▊  | 20125/25880 [4:06:59<1:07:06,  1.43it/s]
1|20126|Loss: 0.7587292194366455:  78%|███████▊  | 20125/25880 [4:06:59<1:07:06,  1.43it/s]
1|20126|Loss: 0.7587292194366455:  78%|███████▊  | 20126/25880 [4:06:59<1:10:10,  1.37it/s]
1|20127|Loss: 0.7741972208023071:  78%|███████▊  | 20126/25880 [4:07:00<1:10:10,  1.37it/s]
1|20127|Loss: 0.7741972208023071:  78%|███████▊  | 20127/25880 [4:07:00<1:10:53,  1.35it/s]
1|20128|Loss: 0.9398408532142639:  78%|███████▊  | 20127/25880 [4:07:01<1:10:53,  1.35it/s]
1|20128|Loss: 0.9398408532142639:  78%|███████▊  | 20128/25880 [4:07:01<1:09:53,  1.37it/s]
1|20129|Loss: 0.9054349660873413:  78%|███████▊  | 20128/25880 [4:07:01<1:09:53,  1.37it/s]
1|20129|Loss: 0.9054349660873413:  78%|███████▊  | 20129/25880 [4:07:01<1:04:43,  1.48it/s]
1|20130|Loss: 0.8626484870910645:  78%|███████▊  | 20129/25880 [4:07:02<1:04:43,  1.48it/s]
1|20130|Loss: 0.8626484870910645:  78%|███████▊  | 20130/25880 [4:07:02<1:02:47,  1.53it/s]
1|20131|Loss: 0.7544214129447937:  78%|███████▊  | 20130/25880 [4:07:02<1:02:47,  1.53it/s]
1|20131|Loss: 0.7544214129447937:  78%|███████▊  | 20131/25880 [4:07:03<1:07:58,  1.41it/s]
1|20132|Loss: 0.7483363747596741:  78%|███████▊  | 20131/25880 [4:07:03<1:07:58,  1.41it/s]
1|20132|Loss: 0.7483363747596741:  78%|███████▊  | 20132/25880 [4:07:04<1:11:49,  1.33it/s]
1|20133|Loss: 0.9128041863441467:  78%|███████▊  | 20132/25880 [4:07:04<1:11:49,  1.33it/s]
1|20133|Loss: 0.9128041863441467:  78%|███████▊  | 20133/25880 [4:07:04<1:09:07,  1.39it/s]
1|20134|Loss: 0.9602028727531433:  78%|███████▊  | 20133/25880 [4:07:05<1:09:07,  1.39it/s]
1|20134|Loss: 0.9602028727531433:  78%|███████▊  | 20134/25880 [4:07:05<1:08:05,  1.41it/s]
1|20135|Loss: 0.7864370346069336:  78%|███████▊  | 20134/25880 [4:07:05<1:08:05,  1.41it/s]
1|20135|Loss: 0.7864370346069336:  78%|███████▊  | 20135/25880 [4:07:06<1:08:46,  1.39it/s]
1|20136|Loss: 0.8949242234230042:  78%|███████▊  | 20135/25880 [4:07:06<1:08:46,  1.39it/s]
1|20136|Loss: 0.8949242234230042:  78%|███████▊  | 20136/25880 [4:07:07<1:09:35,  1.38it/s]
1|20137|Loss: 1.01344895362854:  78%|███████▊  | 20136/25880 [4:07:07<1:09:35,  1.38it/s]  
1|20137|Loss: 1.01344895362854:  78%|███████▊  | 20137/25880 [4:07:07<1:09:48,  1.37it/s]
1|20138|Loss: 0.7984275817871094:  78%|███████▊  | 20137/25880 [4:07:08<1:09:48,  1.37it/s]
1|20138|Loss: 0.7984275817871094:  78%|███████▊  | 20138/25880 [4:07:08<1:11:02,  1.35it/s]
1|20139|Loss: 0.7688246369361877:  78%|███████▊  | 20138/25880 [4:07:08<1:11:02,  1.35it/s]
1|20139|Loss: 0.7688246369361877:  78%|███████▊  | 20139/25880 [4:07:09<1:15:31,  1.27it/s]
1|20140|Loss: 0.8368897438049316:  78%|███████▊  | 20139/25880 [4:07:09<1:15:31,  1.27it/s]
1|20140|Loss: 0.8368897438049316:  78%|███████▊  | 20140/25880 [4:07:10<1:11:28,  1.34it/s]
1|20141|Loss: 0.6846437454223633:  78%|███████▊  | 20140/25880 [4:07:10<1:11:28,  1.34it/s]
1|20141|Loss: 0.6846437454223633:  78%|███████▊  | 20141/25880 [4:07:10<1:11:42,  1.33it/s]
1|20142|Loss: 0.8361726403236389:  78%|███████▊  | 20141/25880 [4:07:11<1:11:42,  1.33it/s]
1|20142|Loss: 0.8361726403236389:  78%|███████▊  | 20142/25880 [4:07:11<1:13:50,  1.30it/s]
1|20143|Loss: 0.8003393411636353:  78%|███████▊  | 20142/25880 [4:07:12<1:13:50,  1.30it/s]
1|20143|Loss: 0.8003393411636353:  78%|███████▊  | 20143/25880 [4:07:12<1:13:42,  1.30it/s]
1|20144|Loss: 0.9523226022720337:  78%|███████▊  | 20143/25880 [4:07:12<1:13:42,  1.30it/s]
1|20144|Loss: 0.9523226022720337:  78%|███████▊  | 20144/25880 [4:07:13<1:10:12,  1.36it/s]
1|20145|Loss: 0.9123556613922119:  78%|███████▊  | 20144/25880 [4:07:13<1:10:12,  1.36it/s]
1|20145|Loss: 0.9123556613922119:  78%|███████▊  | 20145/25880 [4:07:13<1:10:53,  1.35it/s]
1|20146|Loss: 0.799439549446106:  78%|███████▊  | 20145/25880 [4:07:14<1:10:53,  1.35it/s] 
1|20146|Loss: 0.799439549446106:  78%|███████▊  | 20146/25880 [4:07:14<1:13:42,  1.30it/s]
1|20147|Loss: 0.8081084489822388:  78%|███████▊  | 20146/25880 [4:07:15<1:13:42,  1.30it/s]
1|20147|Loss: 0.8081084489822388:  78%|███████▊  | 20147/25880 [4:07:15<1:17:27,  1.23it/s]
1|20148|Loss: 0.8448306918144226:  78%|███████▊  | 20147/25880 [4:07:16<1:17:27,  1.23it/s]
1|20148|Loss: 0.8448306918144226:  78%|███████▊  | 20148/25880 [4:07:16<1:20:37,  1.18it/s]
1|20149|Loss: 0.8258973956108093:  78%|███████▊  | 20148/25880 [4:07:16<1:20:37,  1.18it/s]
1|20149|Loss: 0.8258973956108093:  78%|███████▊  | 20149/25880 [4:07:17<1:20:04,  1.19it/s]
1|20150|Loss: 0.7047683000564575:  78%|███████▊  | 20149/25880 [4:07:17<1:20:04,  1.19it/s]
1|20150|Loss: 0.7047683000564575:  78%|███████▊  | 20150/25880 [4:07:17<1:15:17,  1.27it/s]
1|20151|Loss: 0.84605473279953:  78%|███████▊  | 20150/25880 [4:07:18<1:15:17,  1.27it/s]  
1|20151|Loss: 0.84605473279953:  78%|███████▊  | 20151/25880 [4:07:18<1:12:36,  1.32it/s]
1|20152|Loss: 0.8736852407455444:  78%|███████▊  | 20151/25880 [4:07:19<1:12:36,  1.32it/s]
1|20152|Loss: 0.8736852407455444:  78%|███████▊  | 20152/25880 [4:07:19<1:10:50,  1.35it/s]
1|20153|Loss: 0.7569072246551514:  78%|███████▊  | 20152/25880 [4:07:19<1:10:50,  1.35it/s]
1|20153|Loss: 0.7569072246551514:  78%|███████▊  | 20153/25880 [4:07:20<1:12:17,  1.32it/s]
1|20154|Loss: 0.7508351802825928:  78%|███████▊  | 20153/25880 [4:07:20<1:12:17,  1.32it/s]
1|20154|Loss: 0.7508351802825928:  78%|███████▊  | 20154/25880 [4:07:20<1:11:14,  1.34it/s]
1|20155|Loss: 0.9333276152610779:  78%|███████▊  | 20154/25880 [4:07:21<1:11:14,  1.34it/s]
1|20155|Loss: 0.9333276152610779:  78%|███████▊  | 20155/25880 [4:07:21<1:10:37,  1.35it/s]
1|20156|Loss: 0.9102392196655273:  78%|███████▊  | 20155/25880 [4:07:22<1:10:37,  1.35it/s]
1|20156|Loss: 0.9102392196655273:  78%|███████▊  | 20156/25880 [4:07:22<1:10:37,  1.35it/s]
1|20157|Loss: 0.8186197280883789:  78%|███████▊  | 20156/25880 [4:07:22<1:10:37,  1.35it/s]
1|20157|Loss: 0.8186197280883789:  78%|███████▊  | 20157/25880 [4:07:23<1:08:21,  1.40it/s]
1|20158|Loss: 0.8536220788955688:  78%|███████▊  | 20157/25880 [4:07:23<1:08:21,  1.40it/s]
1|20158|Loss: 0.8536220788955688:  78%|███████▊  | 20158/25880 [4:07:23<1:06:06,  1.44it/s]
1|20159|Loss: 0.8383443355560303:  78%|███████▊  | 20158/25880 [4:07:24<1:06:06,  1.44it/s]
1|20159|Loss: 0.8383443355560303:  78%|███████▊  | 20159/25880 [4:07:24<1:11:07,  1.34it/s]
1|20160|Loss: 0.8861271739006042:  78%|███████▊  | 20159/25880 [4:07:25<1:11:07,  1.34it/s]
1|20160|Loss: 0.8861271739006042:  78%|███████▊  | 20160/25880 [4:07:25<1:17:12,  1.23it/s]
1|20161|Loss: 0.8777032494544983:  78%|███████▊  | 20160/25880 [4:07:25<1:17:12,  1.23it/s]
1|20161|Loss: 0.8777032494544983:  78%|███████▊  | 20161/25880 [4:07:26<1:13:39,  1.29it/s]
1|20162|Loss: 0.8099506497383118:  78%|███████▊  | 20161/25880 [4:07:26<1:13:39,  1.29it/s]
1|20162|Loss: 0.8099506497383118:  78%|███████▊  | 20162/25880 [4:07:26<1:09:08,  1.38it/s]
1|20163|Loss: 0.8927429914474487:  78%|███████▊  | 20162/25880 [4:07:27<1:09:08,  1.38it/s]
1|20163|Loss: 0.8927429914474487:  78%|███████▊  | 20163/25880 [4:07:27<1:14:03,  1.29it/s]
1|20164|Loss: 0.869210422039032:  78%|███████▊  | 20163/25880 [4:07:28<1:14:03,  1.29it/s] 
1|20164|Loss: 0.869210422039032:  78%|███████▊  | 20164/25880 [4:07:28<1:13:22,  1.30it/s]
1|20165|Loss: 0.8463174104690552:  78%|███████▊  | 20164/25880 [4:07:28<1:13:22,  1.30it/s]
1|20165|Loss: 0.8463174104690552:  78%|███████▊  | 20165/25880 [4:07:29<1:16:16,  1.25it/s]
1|20166|Loss: 0.868187665939331:  78%|███████▊  | 20165/25880 [4:07:29<1:16:16,  1.25it/s] 
1|20166|Loss: 0.868187665939331:  78%|███████▊  | 20166/25880 [4:07:30<1:18:23,  1.21it/s]
1|20167|Loss: 0.8186843991279602:  78%|█���█████▊  | 20166/25880 [4:07:30<1:18:23,  1.21it/s]
1|20167|Loss: 0.8186843991279602:  78%|███████▊  | 20167/25880 [4:07:31<1:19:24,  1.20it/s]
1|20168|Loss: 0.7922120094299316:  78%|███████▊  | 20167/25880 [4:07:31<1:19:24,  1.20it/s]
1|20168|Loss: 0.7922120094299316:  78%|███████▊  | 20168/25880 [4:07:31<1:16:43,  1.24it/s]
1|20169|Loss: 0.879689633846283:  78%|███████▊  | 20168/25880 [4:07:32<1:16:43,  1.24it/s] 
1|20169|Loss: 0.879689633846283:  78%|███████▊  | 20169/25880 [4:07:32<1:14:21,  1.28it/s]
1|20170|Loss: 0.8384068608283997:  78%|███████▊  | 20169/25880 [4:07:32<1:14:21,  1.28it/s]
1|20170|Loss: 0.8384068608283997:  78%|███████▊  | 20170/25880 [4:07:33<1:12:54,  1.31it/s]
1|20171|Loss: 0.7260733246803284:  78%|███████▊  | 20170/25880 [4:07:33<1:12:54,  1.31it/s]
1|20171|Loss: 0.7260733246803284:  78%|███████▊  | 20171/25880 [4:07:33<1:11:17,  1.33it/s]
1|20172|Loss: 0.7000181674957275:  78%|███████▊  | 20171/25880 [4:07:34<1:11:17,  1.33it/s]
1|20172|Loss: 0.7000181674957275:  78%|███████▊  | 20172/25880 [4:07:34<1:08:33,  1.39it/s]
1|20173|Loss: 0.8036174178123474:  78%|███████▊  | 20172/25880 [4:07:35<1:08:33,  1.39it/s]
1|20173|Loss: 0.8036174178123474:  78%|███████▊  | 20173/25880 [4:07:35<1:11:03,  1.34it/s]
1|20174|Loss: 0.8533222079277039:  78%|███████▊  | 20173/25880 [4:07:35<1:11:03,  1.34it/s]
1|20174|Loss: 0.8533222079277039:  78%|███████▊  | 20174/25880 [4:07:36<1:08:05,  1.40it/s]
1|20175|Loss: 0.9774239659309387:  78%|███████▊  | 20174/25880 [4:07:36<1:08:05,  1.40it/s]
1|20175|Loss: 0.9774239659309387:  78%|███████▊  | 20175/25880 [4:07:36<1:08:57,  1.38it/s]
1|20176|Loss: 0.7843454480171204:  78%|███████▊  | 20175/25880 [4:07:37<1:08:57,  1.38it/s]
1|20176|Loss: 0.7843454480171204:  78%|███████▊  | 20176/25880 [4:07:37<1:09:01,  1.38it/s]
1|20177|Loss: 0.9824671745300293:  78%|███████▊  | 20176/25880 [4:07:37<1:09:01,  1.38it/s]
1|20177|Loss: 0.9824671745300293:  78%|███████▊  | 20177/25880 [4:07:38<1:09:05,  1.38it/s]
1|20178|Loss: 0.8469627499580383:  78%|███████▊  | 20177/25880 [4:07:38<1:09:05,  1.38it/s]
1|20178|Loss: 0.8469627499580383:  78%|███████▊  | 20178/25880 [4:07:39<1:11:45,  1.32it/s]
1|20179|Loss: 0.952308714389801:  78%|███████▊  | 20178/25880 [4:07:39<1:11:45,  1.32it/s] 
1|20179|Loss: 0.952308714389801:  78%|███████▊  | 20179/25880 [4:07:39<1:14:39,  1.27it/s]
1|20180|Loss: 0.7559102773666382:  78%|███████▊  | 20179/25880 [4:07:40<1:14:39,  1.27it/s]
1|20180|Loss: 0.7559102773666382:  78%|███████▊  | 20180/25880 [4:07:40<1:11:58,  1.32it/s]
1|20181|Loss: 0.6624972820281982:  78%|███████▊  | 20180/25880 [4:07:41<1:11:58,  1.32it/s]
1|20181|Loss: 0.6624972820281982:  78%|███████▊  | 20181/25880 [4:07:41<1:10:59,  1.34it/s]
1|20182|Loss: 0.9358293414115906:  78%|███████▊  | 20181/25880 [4:07:41<1:10:59,  1.34it/s]
1|20182|Loss: 0.9358293414115906:  78%|███████▊  | 20182/25880 [4:07:42<1:11:04,  1.34it/s]
1|20183|Loss: 0.82530677318573:  78%|███████▊  | 20182/25880 [4:07:42<1:11:04,  1.34it/s]  
1|20183|Loss: 0.82530677318573:  78%|███████▊  | 20183/25880 [4:07:42<1:12:14,  1.31it/s]
1|20184|Loss: 0.7636916041374207:  78%|███████▊  | 20183/25880 [4:07:43<1:12:14,  1.31it/s]
1|20184|Loss: 0.7636916041374207:  78%|███████▊  | 20184/25880 [4:07:43<1:13:35,  1.29it/s]
1|20185|Loss: 0.7198882699012756:  78%|███████▊  | 20184/25880 [4:07:44<1:13:35,  1.29it/s]
1|20185|Loss: 0.7198882699012756:  78%|███████▊  | 20185/25880 [4:07:44<1:11:59,  1.32it/s]
1|20186|Loss: 0.7186927795410156:  78%|███████▊  | 20185/25880 [4:07:44<1:11:59,  1.32it/s]
1|20186|Loss: 0.7186927795410156:  78%|███████▊  | 20186/25880 [4:07:45<1:10:49,  1.34it/s]
1|20187|Loss: 0.7355039119720459:  78%|███████▊  | 20186/25880 [4:07:45<1:10:49,  1.34it/s]
1|20187|Loss: 0.7355039119720459:  78%|███████▊  | 20187/25880 [4:07:46<1:15:59,  1.25it/s]
1|20188|Loss: 0.8845035433769226:  78%|███████▊  | 20187/25880 [4:07:46<1:15:59,  1.25it/s]
1|20188|Loss: 0.8845035433769226:  78%|███████▊  | 20188/25880 [4:07:46<1:15:14,  1.26it/s]
1|20189|Loss: 0.7275839447975159:  78%|███████▊  | 20188/25880 [4:07:47<1:15:14,  1.26it/s]
1|20189|Loss: 0.7275839447975159:  78%|███████▊  | 20189/25880 [4:07:47<1:13:41,  1.29it/s]
1|20190|Loss: 0.9499928951263428:  78%|███████▊  | 20189/25880 [4:07:47<1:13:41,  1.29it/s]
1|20190|Loss: 0.9499928951263428:  78%|███████▊  | 20190/25880 [4:07:48<1:09:50,  1.36it/s]
1|20191|Loss: 0.8673483729362488:  78%|███████▊  | 20190/25880 [4:07:48<1:09:50,  1.36it/s]
1|20191|Loss: 0.8673483729362488:  78%|███████▊  | 20191/25880 [4:07:48<1:06:46,  1.42it/s]
1|20192|Loss: 0.8242706656455994:  78%|███████▊  | 20191/25880 [4:07:49<1:06:46,  1.42it/s]
1|20192|Loss: 0.8242706656455994:  78%|███████▊  | 20192/25880 [4:07:49<1:06:23,  1.43it/s]
1|20193|Loss: 0.9419082999229431:  78%|███████▊  | 20192/25880 [4:07:49<1:06:23,  1.43it/s]
1|20193|Loss: 0.9419082999229431:  78%|███████▊  | 20193/25880 [4:07:49<59:19,  1.60it/s]  
1|20194|Loss: 0.7597655057907104:  78%|███████▊  | 20193/25880 [4:07:50<59:19,  1.60it/s]
1|20194|Loss: 0.7597655057907104:  78%|███████▊  | 20194/25880 [4:07:50<1:00:39,  1.56it/s]
1|20195|Loss: 0.7085159420967102:  78%|███████▊  | 20194/25880 [4:07:51<1:00:39,  1.56it/s]
1|20195|Loss: 0.7085159420967102:  78%|███████▊  | 20195/25880 [4:07:51<1:02:38,  1.51it/s]
1|20196|Loss: 0.8396885395050049:  78%|███████▊  | 20195/25880 [4:07:51<1:02:38,  1.51it/s]
1|20196|Loss: 0.8396885395050049:  78%|███████▊  | 20196/25880 [4:07:52<1:03:54,  1.48it/s]
1|20197|Loss: 0.9829639792442322:  78%|███████▊  | 20196/25880 [4:07:52<1:03:54,  1.48it/s]
1|20197|Loss: 0.9829639792442322:  78%|███████▊  | 20197/25880 [4:07:52<1:01:47,  1.53it/s]
1|20198|Loss: 0.7339240312576294:  78%|███████▊  | 20197/25880 [4:07:52<1:01:47,  1.53it/s]
1|20198|Loss: 0.7339240312576294:  78%|███████▊  | 20198/25880 [4:07:53<58:26,  1.62it/s]  
1|20199|Loss: 0.8413252234458923:  78%|███████▊  | 20198/25880 [4:07:53<58:26,  1.62it/s]
1|20199|Loss: 0.8413252234458923:  78%|███████▊  | 20199/25880 [4:07:53<1:00:20,  1.57it/s]
1|20200|Loss: 0.7706454992294312:  78%|███████▊  | 20199/25880 [4:07:54<1:00:20,  1.57it/s]
1|20200|Loss: 0.7706454992294312:  78%|███████▊  | 20200/25880 [4:07:54<1:03:03,  1.50it/s]
1|20201|Loss: 0.7166067361831665:  78%|███████▊  | 20200/25880 [4:07:55<1:03:03,  1.50it/s]
1|20201|Loss: 0.7166067361831665:  78%|███████▊  | 20201/25880 [4:07:55<1:06:01,  1.43it/s]
1|20202|Loss: 0.9455264210700989:  78%|███████▊  | 20201/25880 [4:07:55<1:06:01,  1.43it/s]
1|20202|Loss: 0.9455264210700989:  78%|███████▊  | 20202/25880 [4:07:56<1:05:11,  1.45it/s]
1|20203|Loss: 0.9155299663543701:  78%|███████▊  | 20202/25880 [4:07:56<1:05:11,  1.45it/s]
1|20203|Loss: 0.9155299663543701:  78%|███████▊  | 20203/25880 [4:07:56<1:09:03,  1.37it/s]
1|20204|Loss: 0.9165859222412109:  78%|███████▊  | 20203/25880 [4:07:57<1:09:03,  1.37it/s]
1|20204|Loss: 0.9165859222412109:  78%|███████▊  | 20204/25880 [4:07:57<1:08:06,  1.39it/s]
1|20205|Loss: 0.8462451100349426:  78%|███████▊  | 20204/25880 [4:07:57<1:08:06,  1.39it/s]
1|20205|Loss: 0.8462451100349426:  78%|███████▊  | 20205/25880 [4:07:58<1:08:05,  1.39it/s]
1|20206|Loss: 0.709682822227478:  78%|███████▊  | 20205/25880 [4:07:58<1:08:05,  1.39it/s] 
1|20206|Loss: 0.709682822227478:  78%|███████▊  | 20206/25880 [4:07:58<1:00:15,  1.57it/s]
1|20207|Loss: 0.87043696641922:  78%|███████▊  | 20206/25880 [4:07:59<1:00:15,  1.57it/s] 
1|20207|Loss: 0.87043696641922:  78%|███████▊  | 20207/25880 [4:07:59<58:17,  1.62it/s]  
1|20208|Loss: 0.7578027844429016:  78%|███████▊  | 20207/25880 [4:07:59<58:17,  1.62it/s]
1|20208|Loss: 0.7578027844429016:  78%|███████▊  | 20208/25880 [4:07:59<58:37,  1.61it/s]
1|20209|Loss: 0.9463203549385071:  78%|███████▊  | 20208/25880 [4:08:00<58:37,  1.61it/s]
1|20209|Loss: 0.9463203549385071:  78%|███████▊  | 20209/25880 [4:08:00<1:02:32,  1.51it/s]
1|20210|Loss: 0.9509545564651489:  78%|███████▊  | 20209/25880 [4:08:01<1:02:32,  1.51it/s]
1|20210|Loss: 0.9509545564651489:  78%|███████▊  | 20210/25880 [4:08:01<1:03:00,  1.50it/s]
1|20211|Loss: 0.8406820297241211:  78%|███████▊  | 20210/25880 [4:08:01<1:03:00,  1.50it/s]
1|20211|Loss: 0.8406820297241211:  78%|███████▊  | 20211/25880 [4:08:02<1:03:36,  1.49it/s]
1|20212|Loss: 0.6683993339538574:  78%|███████▊  | 20211/25880 [4:08:02<1:03:36,  1.49it/s]
1|20212|Loss: 0.6683993339538574:  78%|███████▊  | 20212/25880 [4:08:02<1:07:18,  1.40it/s]
1|20213|Loss: 0.7595071196556091:  78%|███████▊  | 20212/25880 [4:08:03<1:07:18,  1.40it/s]
1|20213|Loss: 0.7595071196556091:  78%|███████▊  | 20213/25880 [4:08:03<1:11:27,  1.32it/s]
1|20214|Loss: 0.7309805154800415:  78%|███████▊  | 20213/25880 [4:08:04<1:11:27,  1.32it/s]
1|20214|Loss: 0.7309805154800415:  78%|��██████▊  | 20214/25880 [4:08:04<1:09:03,  1.37it/s]
1|20215|Loss: 0.8761892318725586:  78%|███████▊  | 20214/25880 [4:08:04<1:09:03,  1.37it/s]
1|20215|Loss: 0.8761892318725586:  78%|███████▊  | 20215/25880 [4:08:05<1:05:13,  1.45it/s]
1|20216|Loss: 0.7454054951667786:  78%|███████▊  | 20215/25880 [4:08:05<1:05:13,  1.45it/s]
1|20216|Loss: 0.7454054951667786:  78%|███████▊  | 20216/25880 [4:08:05<1:05:28,  1.44it/s]
1|20217|Loss: 0.8969343304634094:  78%|███████▊  | 20216/25880 [4:08:06<1:05:28,  1.44it/s]
1|20217|Loss: 0.8969343304634094:  78%|███████▊  | 20217/25880 [4:08:06<1:06:55,  1.41it/s]
1|20218|Loss: 0.8874646425247192:  78%|███████▊  | 20217/25880 [4:08:06<1:06:55,  1.41it/s]
1|20218|Loss: 0.8874646425247192:  78%|███████▊  | 20218/25880 [4:08:07<1:07:46,  1.39it/s]
1|20219|Loss: 0.7213620543479919:  78%|███████▊  | 20218/25880 [4:08:07<1:07:46,  1.39it/s]
1|20219|Loss: 0.7213620543479919:  78%|███████▊  | 20219/25880 [4:08:07<1:07:25,  1.40it/s]
1|20220|Loss: 0.8346037864685059:  78%|███████▊  | 20219/25880 [4:08:08<1:07:25,  1.40it/s]
1|20220|Loss: 0.8346037864685059:  78%|███████▊  | 20220/25880 [4:08:08<59:32,  1.58it/s]  
1|20221|Loss: 0.9277079105377197:  78%|███████▊  | 20220/25880 [4:08:08<59:32,  1.58it/s]
1|20221|Loss: 0.9277079105377197:  78%|███████▊  | 20221/25880 [4:08:08<55:26,  1.70it/s]
1|20222|Loss: 0.7869480848312378:  78%|███████▊  | 20221/25880 [4:08:09<55:26,  1.70it/s]
1|20222|Loss: 0.7869480848312378:  78%|███████▊  | 20222/25880 [4:08:09<57:19,  1.65it/s]
1|20223|Loss: 0.6898642778396606:  78%|███████▊  | 20222/25880 [4:08:09<57:19,  1.65it/s]
1|20223|Loss: 0.6898642778396606:  78%|███████▊  | 20223/25880 [4:08:10<57:07,  1.65it/s]
1|20224|Loss: 0.9340735673904419:  78%|███████▊  | 20223/25880 [4:08:10<57:07,  1.65it/s]
1|20224|Loss: 0.9340735673904419:  78%|███████▊  | 20224/25880 [4:08:10<57:37,  1.64it/s]
1|20225|Loss: 0.7984791994094849:  78%|███████▊  | 20224/25880 [4:08:11<57:37,  1.64it/s]
1|20225|Loss: 0.7984791994094849:  78%|███████▊  | 20225/25880 [4:08:11<1:00:06,  1.57it/s]
1|20226|Loss: 0.7739152312278748:  78%|███████▊  | 20225/25880 [4:08:11<1:00:06,  1.57it/s]
1|20226|Loss: 0.7739152312278748:  78%|███████▊  | 20226/25880 [4:08:12<1:04:12,  1.47it/s]
1|20227|Loss: 0.9487810134887695:  78%|███████▊  | 20226/25880 [4:08:12<1:04:12,  1.47it/s]
1|20227|Loss: 0.9487810134887695:  78%|███████▊  | 20227/25880 [4:08:12<59:41,  1.58it/s]  
1|20228|Loss: 0.774077832698822:  78%|███████▊  | 20227/25880 [4:08:13<59:41,  1.58it/s] 
1|20228|Loss: 0.774077832698822:  78%|███████▊  | 20228/25880 [4:08:13<1:04:59,  1.45it/s]
1|20229|Loss: 0.8327080607414246:  78%|███████▊  | 20228/25880 [4:08:13<1:04:59,  1.45it/s]
1|20229|Loss: 0.8327080607414246:  78%|███████▊  | 20229/25880 [4:08:14<1:03:13,  1.49it/s]
1|20230|Loss: 0.8271191716194153:  78%|███████▊  | 20229/25880 [4:08:14<1:03:13,  1.49it/s]
1|20230|Loss: 0.8271191716194153:  78%|███████▊  | 20230/25880 [4:08:14<1:03:49,  1.48it/s]
1|20231|Loss: 0.7877733111381531:  78%|███████▊  | 20230/25880 [4:08:15<1:03:49,  1.48it/s]
1|20231|Loss: 0.7877733111381531:  78%|███████▊  | 20231/25880 [4:08:15<1:06:22,  1.42it/s]
1|20232|Loss: 0.840819239616394:  78%|███████▊  | 20231/25880 [4:08:16<1:06:22,  1.42it/s] 
1|20232|Loss: 0.840819239616394:  78%|███████▊  | 20232/25880 [4:08:16<1:05:22,  1.44it/s]
1|20233|Loss: 0.7026169300079346:  78%|███████▊  | 20232/25880 [4:08:16<1:05:22,  1.44it/s]
1|20233|Loss: 0.7026169300079346:  78%|███████▊  | 20233/25880 [4:08:16<1:03:43,  1.48it/s]
1|20234|Loss: 0.8180950284004211:  78%|███████▊  | 20233/25880 [4:08:17<1:03:43,  1.48it/s]
1|20234|Loss: 0.8180950284004211:  78%|███████▊  | 20234/25880 [4:08:17<1:06:29,  1.42it/s]
1|20235|Loss: 1.0297740697860718:  78%|███████▊  | 20234/25880 [4:08:18<1:06:29,  1.42it/s]
1|20235|Loss: 1.0297740697860718:  78%|███████▊  | 20235/25880 [4:08:18<1:04:58,  1.45it/s]
1|20236|Loss: 0.7591899037361145:  78%|███████▊  | 20235/25880 [4:08:18<1:04:58,  1.45it/s]
1|20236|Loss: 0.7591899037361145:  78%|███████▊  | 20236/25880 [4:08:18<1:01:24,  1.53it/s]
1|20237|Loss: 0.7741042375564575:  78%|███████▊  | 20236/25880 [4:08:19<1:01:24,  1.53it/s]
1|20237|Loss: 0.7741042375564575:  78%|███████▊  | 20237/25880 [4:08:19<1:02:43,  1.50it/s]
1|20238|Loss: 0.7871524691581726:  78%|███████▊  | 20237/25880 [4:08:20<1:02:43,  1.50it/s]
1|20238|Loss: 0.7871524691581726:  78%|███████▊  | 20238/25880 [4:08:20<1:05:59,  1.42it/s]
1|20239|Loss: 0.8499817848205566:  78%|███████▊  | 20238/25880 [4:08:20<1:05:59,  1.42it/s]
1|20239|Loss: 0.8499817848205566:  78%|███████▊  | 20239/25880 [4:08:21<1:07:27,  1.39it/s]
1|20240|Loss: 0.8989315629005432:  78%|███████▊  | 20239/25880 [4:08:21<1:07:27,  1.39it/s]
1|20240|Loss: 0.8989315629005432:  78%|███████▊  | 20240/25880 [4:08:21<1:08:13,  1.38it/s]
1|20241|Loss: 0.7559053897857666:  78%|███████▊  | 20240/25880 [4:08:22<1:08:13,  1.38it/s]
1|20241|Loss: 0.7559053897857666:  78%|███████▊  | 20241/25880 [4:08:22<1:08:49,  1.37it/s]
1|20242|Loss: 0.8313814997673035:  78%|███████▊  | 20241/25880 [4:08:23<1:08:49,  1.37it/s]
1|20242|Loss: 0.8313814997673035:  78%|███████▊  | 20242/25880 [4:08:23<1:06:52,  1.41it/s]
1|20243|Loss: 0.8715091943740845:  78%|███████▊  | 20242/25880 [4:08:23<1:06:52,  1.41it/s]
1|20243|Loss: 0.8715091943740845:  78%|███████▊  | 20243/25880 [4:08:24<1:08:12,  1.38it/s]
1|20244|Loss: 0.9300407767295837:  78%|███████▊  | 20243/25880 [4:08:24<1:08:12,  1.38it/s]
1|20244|Loss: 0.9300407767295837:  78%|███████▊  | 20244/25880 [4:08:24<1:08:47,  1.37it/s]
1|20245|Loss: 0.7861171960830688:  78%|███████▊  | 20244/25880 [4:08:25<1:08:47,  1.37it/s]
1|20245|Loss: 0.7861171960830688:  78%|███████▊  | 20245/25880 [4:08:25<1:10:06,  1.34it/s]
1|20246|Loss: 0.920637845993042:  78%|███████▊  | 20245/25880 [4:08:26<1:10:06,  1.34it/s] 
1|20246|Loss: 0.920637845993042:  78%|███████▊  | 20246/25880 [4:08:26<1:09:22,  1.35it/s]
1|20247|Loss: 0.8119093775749207:  78%|███████▊  | 20246/25880 [4:08:26<1:09:22,  1.35it/s]
1|20247|Loss: 0.8119093775749207:  78%|███████▊  | 20247/25880 [4:08:26<1:04:24,  1.46it/s]
1|20248|Loss: 0.792976975440979:  78%|███████▊  | 20247/25880 [4:08:27<1:04:24,  1.46it/s] 
1|20248|Loss: 0.792976975440979:  78%|███████▊  | 20248/25880 [4:08:27<1:03:41,  1.47it/s]
1|20249|Loss: 0.7262691855430603:  78%|███████▊  | 20248/25880 [4:08:27<1:03:41,  1.47it/s]
1|20249|Loss: 0.7262691855430603:  78%|███████▊  | 20249/25880 [4:08:28<1:04:58,  1.44it/s]
1|20250|Loss: 0.7671467661857605:  78%|███████▊  | 20249/25880 [4:08:28<1:04:58,  1.44it/s]
1|20250|Loss: 0.7671467661857605:  78%|███████▊  | 20250/25880 [4:08:29<1:06:11,  1.42it/s]
1|20251|Loss: 0.8340244293212891:  78%|███████▊  | 20250/25880 [4:08:29<1:06:11,  1.42it/s]
1|20251|Loss: 0.8340244293212891:  78%|███████▊  | 20251/25880 [4:08:29<1:09:45,  1.35it/s]
1|20252|Loss: 0.8137390613555908:  78%|███████▊  | 20251/25880 [4:08:30<1:09:45,  1.35it/s]
1|20252|Loss: 0.8137390613555908:  78%|███████▊  | 20252/25880 [4:08:30<1:10:19,  1.33it/s]
1|20253|Loss: 0.7042169570922852:  78%|███████▊  | 20252/25880 [4:08:30<1:10:19,  1.33it/s]
1|20253|Loss: 0.7042169570922852:  78%|███████▊  | 20253/25880 [4:08:31<1:06:28,  1.41it/s]
1|20254|Loss: 0.7092651724815369:  78%|███████▊  | 20253/25880 [4:08:31<1:06:28,  1.41it/s]
1|20254|Loss: 0.7092651724815369:  78%|███████▊  | 20254/25880 [4:08:31<1:06:20,  1.41it/s]
1|20255|Loss: 0.7967446446418762:  78%|███████▊  | 20254/25880 [4:08:32<1:06:20,  1.41it/s]
1|20255|Loss: 0.7967446446418762:  78%|███████▊  | 20255/25880 [4:08:32<1:09:24,  1.35it/s]
1|20256|Loss: 0.7699238061904907:  78%|███████▊  | 20255/25880 [4:08:33<1:09:24,  1.35it/s]
1|20256|Loss: 0.7699238061904907:  78%|███████▊  | 20256/25880 [4:08:33<1:04:41,  1.45it/s]
1|20257|Loss: 0.7921348214149475:  78%|███████▊  | 20256/25880 [4:08:33<1:04:41,  1.45it/s]
1|20257|Loss: 0.7921348214149475:  78%|███████▊  | 20257/25880 [4:08:33<1:02:06,  1.51it/s]
1|20258|Loss: 0.9430729150772095:  78%|███████▊  | 20257/25880 [4:08:34<1:02:06,  1.51it/s]
1|20258|Loss: 0.9430729150772095:  78%|███████▊  | 20258/25880 [4:08:34<1:03:55,  1.47it/s]
1|20259|Loss: 0.8607360124588013:  78%|███████▊  | 20258/25880 [4:08:35<1:03:55,  1.47it/s]
1|20259|Loss: 0.8607360124588013:  78%|███████▊  | 20259/25880 [4:08:35<1:05:00,  1.44it/s]
1|20260|Loss: 0.8220441341400146:  78%|███████▊  | 20259/25880 [4:08:35<1:05:00,  1.44it/s]
1|20260|Loss: 0.8220441341400146:  78%|███████▊  | 20260/25880 [4:08:36<1:03:53,  1.47it/s]
1|20261|Loss: 0.858267605304718:  78%|███████▊  | 20260/25880 [4:08:36<1:03:53,  1.47it/s] 
1|20261|Loss: 0.858267605304718:  78%|███████▊  | 20261/25880 [4:08:36<1:02:07,  1.51it/s]
1|20262|Loss: 0.7272347807884216:  78%|██���████▊  | 20261/25880 [4:08:37<1:02:07,  1.51it/s]
1|20262|Loss: 0.7272347807884216:  78%|███████▊  | 20262/25880 [4:08:37<1:03:22,  1.48it/s]
1|20263|Loss: 0.8284600377082825:  78%|███████▊  | 20262/25880 [4:08:37<1:03:22,  1.48it/s]
1|20263|Loss: 0.8284600377082825:  78%|███████▊  | 20263/25880 [4:08:38<1:04:52,  1.44it/s]
1|20264|Loss: 0.7624375820159912:  78%|███████▊  | 20263/25880 [4:08:38<1:04:52,  1.44it/s]
1|20264|Loss: 0.7624375820159912:  78%|███████▊  | 20264/25880 [4:08:38<1:05:30,  1.43it/s]
1|20265|Loss: 0.8681022524833679:  78%|███████▊  | 20264/25880 [4:08:39<1:05:30,  1.43it/s]
1|20265|Loss: 0.8681022524833679:  78%|███████▊  | 20265/25880 [4:08:39<1:04:09,  1.46it/s]
1|20266|Loss: 0.8701453804969788:  78%|███████▊  | 20265/25880 [4:08:39<1:04:09,  1.46it/s]
1|20266|Loss: 0.8701453804969788:  78%|███████▊  | 20266/25880 [4:08:40<1:05:13,  1.43it/s]
1|20267|Loss: 0.792634129524231:  78%|███████▊  | 20266/25880 [4:08:40<1:05:13,  1.43it/s] 
1|20267|Loss: 0.792634129524231:  78%|███████▊  | 20267/25880 [4:08:40<1:00:45,  1.54it/s]
1|20268|Loss: 0.8789158463478088:  78%|███████▊  | 20267/25880 [4:08:41<1:00:45,  1.54it/s]
1|20268|Loss: 0.8789158463478088:  78%|███████▊  | 20268/25880 [4:08:41<1:04:21,  1.45it/s]
1|20269|Loss: 0.8858539462089539:  78%|███████▊  | 20268/25880 [4:08:41<1:04:21,  1.45it/s]
1|20269|Loss: 0.8858539462089539:  78%|███████▊  | 20269/25880 [4:08:42<1:07:28,  1.39it/s]
1|20270|Loss: 0.7223891019821167:  78%|███████▊  | 20269/25880 [4:08:42<1:07:28,  1.39it/s]
1|20270|Loss: 0.7223891019821167:  78%|███████▊  | 20270/25880 [4:08:43<1:11:09,  1.31it/s]
1|20271|Loss: 0.8808650374412537:  78%|███████▊  | 20270/25880 [4:08:43<1:11:09,  1.31it/s]
1|20271|Loss: 0.8808650374412537:  78%|███████▊  | 20271/25880 [4:08:43<1:06:19,  1.41it/s]
1|20272|Loss: 0.8213123679161072:  78%|███████▊  | 20271/25880 [4:08:44<1:06:19,  1.41it/s]
1|20272|Loss: 0.8213123679161072:  78%|███████▊  | 20272/25880 [4:08:44<1:08:11,  1.37it/s]
1|20273|Loss: 0.918204665184021:  78%|███████▊  | 20272/25880 [4:08:44<1:08:11,  1.37it/s] 
1|20273|Loss: 0.918204665184021:  78%|███████▊  | 20273/25880 [4:08:45<1:09:14,  1.35it/s]
1|20274|Loss: 0.9133052825927734:  78%|███████▊  | 20273/25880 [4:08:45<1:09:14,  1.35it/s]
1|20274|Loss: 0.9133052825927734:  78%|███████▊  | 20274/25880 [4:08:46<1:13:22,  1.27it/s]
1|20275|Loss: 0.7697083353996277:  78%|███████▊  | 20274/25880 [4:08:46<1:13:22,  1.27it/s]
1|20275|Loss: 0.7697083353996277:  78%|███████▊  | 20275/25880 [4:08:46<1:09:45,  1.34it/s]
1|20276|Loss: 0.7987735271453857:  78%|███████▊  | 20275/25880 [4:08:47<1:09:45,  1.34it/s]
1|20276|Loss: 0.7987735271453857:  78%|███████▊  | 20276/25880 [4:08:47<1:08:21,  1.37it/s]
1|20277|Loss: 0.7702814340591431:  78%|███████▊  | 20276/25880 [4:08:47<1:08:21,  1.37it/s]
1|20277|Loss: 0.7702814340591431:  78%|███████▊  | 20277/25880 [4:08:48<1:09:56,  1.34it/s]
1|20278|Loss: 1.151044487953186:  78%|███████▊  | 20277/25880 [4:08:48<1:09:56,  1.34it/s] 
1|20278|Loss: 1.151044487953186:  78%|███████▊  | 20278/25880 [4:08:49<1:14:12,  1.26it/s]
1|20279|Loss: 0.7384517192840576:  78%|███████▊  | 20278/25880 [4:08:49<1:14:12,  1.26it/s]
1|20279|Loss: 0.7384517192840576:  78%|███████▊  | 20279/25880 [4:08:49<1:09:01,  1.35it/s]
1|20280|Loss: 0.8197898864746094:  78%|███████▊  | 20279/25880 [4:08:50<1:09:01,  1.35it/s]
1|20280|Loss: 0.8197898864746094:  78%|███████▊  | 20280/25880 [4:08:50<1:11:55,  1.30it/s]
1|20281|Loss: 0.864652156829834:  78%|███████▊  | 20280/25880 [4:08:51<1:11:55,  1.30it/s] 
1|20281|Loss: 0.864652156829834:  78%|███████▊  | 20281/25880 [4:08:51<1:12:09,  1.29it/s]
1|20282|Loss: 0.7929397821426392:  78%|███████▊  | 20281/25880 [4:08:51<1:12:09,  1.29it/s]
1|20282|Loss: 0.7929397821426392:  78%|███████▊  | 20282/25880 [4:08:52<1:13:18,  1.27it/s]
1|20283|Loss: 0.8113420009613037:  78%|███████▊  | 20282/25880 [4:08:52<1:13:18,  1.27it/s]
1|20283|Loss: 0.8113420009613037:  78%|███████▊  | 20283/25880 [4:08:52<1:09:12,  1.35it/s]
1|20284|Loss: 0.7841693162918091:  78%|███████▊  | 20283/25880 [4:08:53<1:09:12,  1.35it/s]
1|20284|Loss: 0.7841693162918091:  78%|███████▊  | 20284/25880 [4:08:53<1:04:50,  1.44it/s]
1|20285|Loss: 0.7528591156005859:  78%|███████▊  | 20284/25880 [4:08:53<1:04:50,  1.44it/s]
1|20285|Loss: 0.7528591156005859:  78%|███████▊  | 20285/25880 [4:08:54<1:02:53,  1.48it/s]
1|20286|Loss: 0.9337496757507324:  78%|███████▊  | 20285/25880 [4:08:54<1:02:53,  1.48it/s]
1|20286|Loss: 0.9337496757507324:  78%|███████▊  | 20286/25880 [4:08:54<1:05:12,  1.43it/s]
1|20287|Loss: 0.906273603439331:  78%|███████▊  | 20286/25880 [4:08:55<1:05:12,  1.43it/s] 
1|20287|Loss: 0.906273603439331:  78%|███████▊  | 20287/25880 [4:08:55<1:08:42,  1.36it/s]
1|20288|Loss: 0.8409748077392578:  78%|███████▊  | 20287/25880 [4:08:56<1:08:42,  1.36it/s]
1|20288|Loss: 0.8409748077392578:  78%|███████▊  | 20288/25880 [4:08:56<1:09:01,  1.35it/s]
1|20289|Loss: 0.8815072774887085:  78%|███████▊  | 20288/25880 [4:08:56<1:09:01,  1.35it/s]
1|20289|Loss: 0.8815072774887085:  78%|███████▊  | 20289/25880 [4:08:57<1:07:54,  1.37it/s]
1|20290|Loss: 0.9706659913063049:  78%|███████▊  | 20289/25880 [4:08:57<1:07:54,  1.37it/s]
1|20290|Loss: 0.9706659913063049:  78%|███████▊  | 20290/25880 [4:08:57<1:10:30,  1.32it/s]
1|20291|Loss: 0.7315937280654907:  78%|███████▊  | 20290/25880 [4:08:58<1:10:30,  1.32it/s]
1|20291|Loss: 0.7315937280654907:  78%|███████▊  | 20291/25880 [4:08:58<1:10:54,  1.31it/s]
1|20292|Loss: 0.8407632112503052:  78%|███████▊  | 20291/25880 [4:08:59<1:10:54,  1.31it/s]
1|20292|Loss: 0.8407632112503052:  78%|███████▊  | 20292/25880 [4:08:59<1:08:18,  1.36it/s]
1|20293|Loss: 1.0164289474487305:  78%|███████▊  | 20292/25880 [4:08:59<1:08:18,  1.36it/s]
1|20293|Loss: 1.0164289474487305:  78%|███████▊  | 20293/25880 [4:09:00<1:10:26,  1.32it/s]
1|20294|Loss: 0.8433709144592285:  78%|███████▊  | 20293/25880 [4:09:00<1:10:26,  1.32it/s]
1|20294|Loss: 0.8433709144592285:  78%|███████▊  | 20294/25880 [4:09:00<1:10:47,  1.32it/s]
1|20295|Loss: 0.8291838765144348:  78%|███████▊  | 20294/25880 [4:09:01<1:10:47,  1.32it/s]
1|20295|Loss: 0.8291838765144348:  78%|███████▊  | 20295/25880 [4:09:01<1:08:06,  1.37it/s]
1|20296|Loss: 0.6425257325172424:  78%|███████▊  | 20295/25880 [4:09:01<1:08:06,  1.37it/s]
1|20296|Loss: 0.6425257325172424:  78%|███████▊  | 20296/25880 [4:09:02<1:04:59,  1.43it/s]
1|20297|Loss: 0.7991760969161987:  78%|███████▊  | 20296/25880 [4:09:02<1:04:59,  1.43it/s]
1|20297|Loss: 0.7991760969161987:  78%|███████▊  | 20297/25880 [4:09:03<1:06:33,  1.40it/s]
1|20298|Loss: 0.7919905781745911:  78%|███████▊  | 20297/25880 [4:09:03<1:06:33,  1.40it/s]
1|20298|Loss: 0.7919905781745911:  78%|███████▊  | 20298/25880 [4:09:03<1:11:31,  1.30it/s]
1|20299|Loss: 0.8577505946159363:  78%|███████▊  | 20298/25880 [4:09:04<1:11:31,  1.30it/s]
1|20299|Loss: 0.8577505946159363:  78%|███████▊  | 20299/25880 [4:09:04<1:11:23,  1.30it/s]
1|20300|Loss: 0.9556340575218201:  78%|███████▊  | 20299/25880 [4:09:05<1:11:23,  1.30it/s]
1|20300|Loss: 0.9556340575218201:  78%|███████▊  | 20300/25880 [4:09:05<1:10:20,  1.32it/s]
1|20301|Loss: 0.8600206971168518:  78%|███████▊  | 20300/25880 [4:09:05<1:10:20,  1.32it/s]
1|20301|Loss: 0.8600206971168518:  78%|███████▊  | 20301/25880 [4:09:05<1:03:23,  1.47it/s]
1|20302|Loss: 0.8882262706756592:  78%|███████▊  | 20301/25880 [4:09:06<1:03:23,  1.47it/s]
1|20302|Loss: 0.8882262706756592:  78%|███████▊  | 20302/25880 [4:09:06<1:05:53,  1.41it/s]
1|20303|Loss: 0.7172743678092957:  78%|███████▊  | 20302/25880 [4:09:07<1:05:53,  1.41it/s]
1|20303|Loss: 0.7172743678092957:  78%|███████▊  | 20303/25880 [4:09:07<1:09:57,  1.33it/s]
1|20304|Loss: 0.8290681838989258:  78%|███████▊  | 20303/25880 [4:09:07<1:09:57,  1.33it/s]
1|20304|Loss: 0.8290681838989258:  78%|███████▊  | 20304/25880 [4:09:08<1:11:19,  1.30it/s]
1|20305|Loss: 0.7412247061729431:  78%|███████▊  | 20304/25880 [4:09:08<1:11:19,  1.30it/s]
1|20305|Loss: 0.7412247061729431:  78%|███████▊  | 20305/25880 [4:09:09<1:12:52,  1.27it/s]
1|20306|Loss: 0.8779852390289307:  78%|███████▊  | 20305/25880 [4:09:09<1:12:52,  1.27it/s]
1|20306|Loss: 0.8779852390289307:  78%|███████▊  | 20306/25880 [4:09:09<1:09:49,  1.33it/s]
1|20307|Loss: 0.8316237926483154:  78%|███████▊  | 20306/25880 [4:09:10<1:09:49,  1.33it/s]
1|20307|Loss: 0.8316237926483154:  78%|███████▊  | 20307/25880 [4:09:10<1:08:56,  1.35it/s]
1|20308|Loss: 0.846981942653656:  78%|███████▊  | 20307/25880 [4:09:10<1:08:56,  1.35it/s] 
1|20308|Loss: 0.846981942653656:  78%|███████▊  | 20308/25880 [4:09:11<1:06:43,  1.39it/s]
1|20309|Loss: 0.8127350807189941:  78%|███████▊  | 20308/25880 [4:09:11<1:06:43,  1.39it/s]
1|20309|Loss: 0.8127350807189941:  78%|███████▊  | 20309/25880 [4:09:11<1:06:51,  1.39it/s]
1|20310|Loss: 0.9258490800857544:  78%|███████▊  | 20309/25880 [4:09:12<1:06:51,  1.39it/s]
1|20310|Loss: 0.9258490800857544:  78%|███████▊  | 20310/25880 [4:09:12<1:09:38,  1.33it/s]
1|20311|Loss: 0.8167170882225037:  78%|███████▊  | 20310/25880 [4:09:13<1:09:38,  1.33it/s]
1|20311|Loss: 0.8167170882225037:  78%|███████▊  | 20311/25880 [4:09:13<1:06:23,  1.40it/s]
1|20312|Loss: 0.8302882313728333:  78%|███████▊  | 20311/25880 [4:09:13<1:06:23,  1.40it/s]
1|20312|Loss: 0.8302882313728333:  78%|███████▊  | 20312/25880 [4:09:14<1:06:05,  1.40it/s]
1|20313|Loss: 0.9071834683418274:  78%|███████▊  | 20312/25880 [4:09:14<1:06:05,  1.40it/s]
1|20313|Loss: 0.9071834683418274:  78%|███████▊  | 20313/25880 [4:09:14<1:06:53,  1.39it/s]
1|20314|Loss: 0.785014808177948:  78%|███████▊  | 20313/25880 [4:09:15<1:06:53,  1.39it/s] 
1|20314|Loss: 0.785014808177948:  78%|███████▊  | 20314/25880 [4:09:15<1:07:19,  1.38it/s]
1|20315|Loss: 0.9618306159973145:  78%|███████▊  | 20314/25880 [4:09:16<1:07:19,  1.38it/s]
1|20315|Loss: 0.9618306159973145:  78%|███████▊  | 20315/25880 [4:09:16<1:08:45,  1.35it/s]
1|20316|Loss: 0.864560067653656:  78%|███████▊  | 20315/25880 [4:09:16<1:08:45,  1.35it/s] 
1|20316|Loss: 0.864560067653656:  79%|███████▊  | 20316/25880 [4:09:17<1:08:19,  1.36it/s]
1|20317|Loss: 0.986733615398407:  79%|███████▊  | 20316/25880 [4:09:17<1:08:19,  1.36it/s]
1|20317|Loss: 0.986733615398407:  79%|███████▊  | 20317/25880 [4:09:17<1:11:08,  1.30it/s]
1|20318|Loss: 0.7405096292495728:  79%|███████▊  | 20317/25880 [4:09:18<1:11:08,  1.30it/s]
1|20318|Loss: 0.7405096292495728:  79%|███████▊  | 20318/25880 [4:09:18<1:09:00,  1.34it/s]
1|20319|Loss: 0.7597968578338623:  79%|███████▊  | 20318/25880 [4:09:18<1:09:00,  1.34it/s]
1|20319|Loss: 0.7597968578338623:  79%|███████▊  | 20319/25880 [4:09:19<1:07:32,  1.37it/s]
1|20320|Loss: 0.9466195106506348:  79%|███████▊  | 20319/25880 [4:09:19<1:07:32,  1.37it/s]
1|20320|Loss: 0.9466195106506348:  79%|███████▊  | 20320/25880 [4:09:19<1:05:21,  1.42it/s]
1|20321|Loss: 0.8429437875747681:  79%|███████▊  | 20320/25880 [4:09:20<1:05:21,  1.42it/s]
1|20321|Loss: 0.8429437875747681:  79%|███████▊  | 20321/25880 [4:09:20<1:05:51,  1.41it/s]
1|20322|Loss: 0.7315681576728821:  79%|███████▊  | 20321/25880 [4:09:21<1:05:51,  1.41it/s]
1|20322|Loss: 0.7315681576728821:  79%|███████▊  | 20322/25880 [4:09:22<1:25:53,  1.08it/s]
1|20323|Loss: 0.8268721103668213:  79%|███████▊  | 20322/25880 [4:09:22<1:25:53,  1.08it/s]
1|20323|Loss: 0.8268721103668213:  79%|███████▊  | 20323/25880 [4:09:22<1:21:29,  1.14it/s]
1|20324|Loss: 0.8835039734840393:  79%|███████▊  | 20323/25880 [4:09:23<1:21:29,  1.14it/s]
1|20324|Loss: 0.8835039734840393:  79%|███████▊  | 20324/25880 [4:09:23<1:14:20,  1.25it/s]
1|20325|Loss: 0.9982060790061951:  79%|███████▊  | 20324/25880 [4:09:23<1:14:20,  1.25it/s]
1|20325|Loss: 0.9982060790061951:  79%|███████▊  | 20325/25880 [4:09:24<1:14:03,  1.25it/s]
1|20326|Loss: 0.7868505120277405:  79%|███████▊  | 20325/25880 [4:09:24<1:14:03,  1.25it/s]
1|20326|Loss: 0.7868505120277405:  79%|███████▊  | 20326/25880 [4:09:25<1:14:53,  1.24it/s]
1|20327|Loss: 0.8428964018821716:  79%|███████▊  | 20326/25880 [4:09:25<1:14:53,  1.24it/s]
1|20327|Loss: 0.8428964018821716:  79%|███████▊  | 20327/25880 [4:09:25<1:10:48,  1.31it/s]
1|20328|Loss: 0.718277633190155:  79%|███████▊  | 20327/25880 [4:09:26<1:10:48,  1.31it/s] 
1|20328|Loss: 0.718277633190155:  79%|███████▊  | 20328/25880 [4:09:26<1:12:19,  1.28it/s]
1|20329|Loss: 0.8464817404747009:  79%|███████▊  | 20328/25880 [4:09:27<1:12:19,  1.28it/s]
1|20329|Loss: 0.8464817404747009:  79%|███████▊  | 20329/25880 [4:09:27<1:09:57,  1.32it/s]
1|20330|Loss: 0.8955472111701965:  79%|███████▊  | 20329/25880 [4:09:27<1:09:57,  1.32it/s]
1|20330|Loss: 0.8955472111701965:  79%|███████▊  | 20330/25880 [4:09:28<1:08:59,  1.34it/s]
1|20331|Loss: 0.7324639558792114:  79%|███████▊  | 20330/25880 [4:09:28<1:08:59,  1.34it/s]
1|20331|Loss: 0.7324639558792114:  79%|███████▊  | 20331/25880 [4:09:28<1:05:45,  1.41it/s]
1|20332|Loss: 0.8011220693588257:  79%|███████▊  | 20331/25880 [4:09:29<1:05:45,  1.41it/s]
1|20332|Loss: 0.8011220693588257:  79%|███████▊  | 20332/25880 [4:09:29<1:03:00,  1.47it/s]
1|20333|Loss: 0.6404826045036316:  79%|███████▊  | 20332/25880 [4:09:29<1:03:00,  1.47it/s]
1|20333|Loss: 0.6404826045036316:  79%|███████▊  | 20333/25880 [4:09:30<1:12:21,  1.28it/s]
1|20334|Loss: 0.9235101342201233:  79%|███████▊  | 20333/25880 [4:09:30<1:12:21,  1.28it/s]
1|20334|Loss: 0.9235101342201233:  79%|███████▊  | 20334/25880 [4:09:31<1:13:17,  1.26it/s]
1|20335|Loss: 0.891635000705719:  79%|███████▊  | 20334/25880 [4:09:31<1:13:17,  1.26it/s] 
1|20335|Loss: 0.891635000705719:  79%|███████▊  | 20335/25880 [4:09:31<1:14:16,  1.24it/s]
1|20336|Loss: 0.9683952331542969:  79%|███████▊  | 20335/25880 [4:09:32<1:14:16,  1.24it/s]
1|20336|Loss: 0.9683952331542969:  79%|███████▊  | 20336/25880 [4:09:32<1:09:16,  1.33it/s]
1|20337|Loss: 0.7372893691062927:  79%|███████▊  | 20336/25880 [4:09:32<1:09:16,  1.33it/s]
1|20337|Loss: 0.7372893691062927:  79%|███████▊  | 20337/25880 [4:09:33<1:08:06,  1.36it/s]
1|20338|Loss: 0.8984752297401428:  79%|███████▊  | 20337/25880 [4:09:33<1:08:06,  1.36it/s]
1|20338|Loss: 0.8984752297401428:  79%|███████▊  | 20338/25880 [4:09:34<1:10:33,  1.31it/s]
1|20339|Loss: 0.786628246307373:  79%|███████▊  | 20338/25880 [4:09:34<1:10:33,  1.31it/s] 
1|20339|Loss: 0.786628246307373:  79%|███████▊  | 20339/25880 [4:09:34<1:05:26,  1.41it/s]
1|20340|Loss: 0.9105592370033264:  79%|███████▊  | 20339/25880 [4:09:35<1:05:26,  1.41it/s]
1|20340|Loss: 0.9105592370033264:  79%|███████▊  | 20340/25880 [4:09:35<1:02:19,  1.48it/s]
1|20341|Loss: 0.7996723651885986:  79%|███████▊  | 20340/25880 [4:09:35<1:02:19,  1.48it/s]
1|20341|Loss: 0.7996723651885986:  79%|███████▊  | 20341/25880 [4:09:35<1:02:32,  1.48it/s]
1|20342|Loss: 0.9644147157669067:  79%|███████▊  | 20341/25880 [4:09:36<1:02:32,  1.48it/s]
1|20342|Loss: 0.9644147157669067:  79%|███████▊  | 20342/25880 [4:09:36<1:03:50,  1.45it/s]
1|20343|Loss: 0.8850783705711365:  79%|███████▊  | 20342/25880 [4:09:37<1:03:50,  1.45it/s]
1|20343|Loss: 0.8850783705711365:  79%|███████▊  | 20343/25880 [4:09:37<1:03:00,  1.46it/s]
1|20344|Loss: 0.9698199033737183:  79%|███████▊  | 20343/25880 [4:09:37<1:03:00,  1.46it/s]
1|20344|Loss: 0.9698199033737183:  79%|███████▊  | 20344/25880 [4:09:37<1:00:34,  1.52it/s]
1|20345|Loss: 0.7023311853408813:  79%|███████▊  | 20344/25880 [4:09:38<1:00:34,  1.52it/s]
1|20345|Loss: 0.7023311853408813:  79%|███████▊  | 20345/25880 [4:09:38<1:04:49,  1.42it/s]
1|20346|Loss: 0.7639375329017639:  79%|███████▊  | 20345/25880 [4:09:39<1:04:49,  1.42it/s]
1|20346|Loss: 0.7639375329017639:  79%|███████▊  | 20346/25880 [4:09:39<1:04:04,  1.44it/s]
1|20347|Loss: 0.8694044351577759:  79%|███████▊  | 20346/25880 [4:09:39<1:04:04,  1.44it/s]
1|20347|Loss: 0.8694044351577759:  79%|███████▊  | 20347/25880 [4:09:40<1:07:50,  1.36it/s]
1|20348|Loss: 0.8294098377227783:  79%|███████▊  | 20347/25880 [4:09:40<1:07:50,  1.36it/s]
1|20348|Loss: 0.8294098377227783:  79%|███████▊  | 20348/25880 [4:09:41<1:09:02,  1.34it/s]
1|20349|Loss: 0.6982534527778625:  79%|███████▊  | 20348/25880 [4:09:41<1:09:02,  1.34it/s]
1|20349|Loss: 0.6982534527778625:  79%|███████▊  | 20349/25880 [4:09:41<1:09:04,  1.33it/s]
1|20350|Loss: 0.7277150750160217:  79%|███████▊  | 20349/25880 [4:09:42<1:09:04,  1.33it/s]
1|20350|Loss: 0.7277150750160217:  79%|███████▊  | 20350/25880 [4:09:42<1:08:45,  1.34it/s]
1|20351|Loss: 0.8401781320571899:  79%|███████▊  | 20350/25880 [4:09:42<1:08:45,  1.34it/s]
1|20351|Loss: 0.8401781320571899:  79%|███████▊  | 20351/25880 [4:09:43<1:10:30,  1.31it/s]
1|20352|Loss: 0.7889817953109741:  79%|███████▊  | 20351/25880 [4:09:43<1:10:30,  1.31it/s]
1|20352|Loss: 0.7889817953109741:  79%|███████▊  | 20352/25880 [4:09:44<1:11:32,  1.29it/s]
1|20353|Loss: 0.7983624339103699:  79%|███████▊  | 20352/25880 [4:09:44<1:11:32,  1.29it/s]
1|20353|Loss: 0.7983624339103699:  79%|███████▊  | 20353/25880 [4:09:44<1:13:44,  1.25it/s]
1|20354|Loss: 0.913281261920929:  79%|███████▊  | 20353/25880 [4:09:45<1:13:44,  1.25it/s] 
1|20354|Loss: 0.913281261920929:  79%|███████▊  | 20354/25880 [4:09:45<1:12:46,  1.27it/s]
1|20355|Loss: 0.8276475667953491:  79%|███████▊  | 20354/25880 [4:09:46<1:12:46,  1.27it/s]
1|20355|Loss: 0.8276475667953491:  79%|███████▊  | 20355/25880 [4:09:46<1:09:01,  1.33it/s]
1|20356|Loss: 0.7437988519668579:  79%|███████▊  | 20355/25880 [4:09:46<1:09:01,  1.33it/s]
1|20356|Loss: 0.7437988519668579:  79%|███████▊  | 20356/25880 [4:09:47<1:08:20,  1.35it/s]
1|20357|Loss: 0.7510954737663269:  79%|███████▊  | 20356/25880 [4:09:47<1:08:20,  1.35it/s]
1|20357|Loss: 0.7510954737663269:  79%|███████▊  | 20357/25880 [4:09:47<1:03:48,  1.44it/s]
1|20358|Loss: 0.8900434374809265:  79%|███████▊  | 20357/25880 [4:09:48<1:03:48,  1.44it/s]
1|20358|Loss: 0.8900434374809265:  79%|███████▊  | 20358/25880 [4:09:48<1:01:33,  1.50it/s]
1|20359|Loss: 0.8072354197502136:  79%|███████▊  | 20358/25880 [4:09:48<1:01:33,  1.50it/s]
1|20359|Loss: 0.8072354197502136:  79%|███████▊  | 20359/25880 [4:09:49<1:05:55,  1.40it/s]
1|20360|Loss: 0.8718977570533752:  79%|███████▊  | 20359/25880 [4:09:49<1:05:55,  1.40it/s]
1|20360|Loss: 0.8718977570533752:  79%|███████▊  | 20360/25880 [4:09:49<1:04:54,  1.42it/s]
1|20361|Loss: 0.7755385637283325:  79%|███████▊  | 20360/25880 [4:09:50<1:04:54,  1.42it/s]
1|20361|Loss: 0.7755385637283325:  79%|███████▊  | 20361/25880 [4:09:50<1:04:53,  1.42it/s]
1|20362|Loss: 0.9701498746871948:  79%|███████▊  | 20361/25880 [4:09:50<1:04:53,  1.42it/s]
1|20362|Loss: 0.9701498746871948:  79%|███████▊  | 20362/25880 [4:09:51<1:05:19,  1.41it/s]
1|20363|Loss: 0.8344629406929016:  79%|███████▊  | 20362/25880 [4:09:51<1:05:19,  1.41it/s]
1|20363|Loss: 0.8344629406929016:  79%|███████▊  | 20363/25880 [4:09:51<1:05:46,  1.40it/s]
1|20364|Loss: 1.059303641319275:  79%|███████▊  | 20363/25880 [4:09:52<1:05:46,  1.40it/s] 
1|20364|Loss: 1.059303641319275:  79%|███████▊  | 20364/25880 [4:09:52<1:08:45,  1.34it/s]
1|20365|Loss: 0.7411038875579834:  79%|███████▊  | 20364/25880 [4:09:53<1:08:45,  1.34it/s]
1|20365|Loss: 0.7411038875579834:  79%|███████▊  | 20365/25880 [4:09:53<1:10:18,  1.31it/s]
1|20366|Loss: 0.9609940052032471:  79%|███████▊  | 20365/25880 [4:09:54<1:10:18,  1.31it/s]
1|20366|Loss: 0.9609940052032471:  79%|███████▊  | 20366/25880 [4:09:54<1:09:09,  1.33it/s]
1|20367|Loss: 0.7106174826622009:  79%|███████▊  | 20366/25880 [4:09:54<1:09:09,  1.33it/s]
1|20367|Loss: 0.7106174826622009:  79%|███████▊  | 20367/25880 [4:09:55<1:07:39,  1.36it/s]
1|20368|Loss: 0.8067520260810852:  79%|███████▊  | 20367/25880 [4:09:55<1:07:39,  1.36it/s]
1|20368|Loss: 0.8067520260810852:  79%|███████▊  | 20368/25880 [4:09:55<1:04:02,  1.43it/s]
1|20369|Loss: 0.8672178387641907:  79%|███████▊  | 20368/25880 [4:09:56<1:04:02,  1.43it/s]
1|20369|Loss: 0.8672178387641907:  79%|███████▊  | 20369/25880 [4:09:56<1:04:10,  1.43it/s]
1|20370|Loss: 0.750595211982727:  79%|███████▊  | 20369/25880 [4:09:56<1:04:10,  1.43it/s] 
1|20370|Loss: 0.750595211982727:  79%|███████▊  | 20370/25880 [4:09:57<1:10:41,  1.30it/s]
1|20371|Loss: 0.8676342964172363:  79%|███████▊  | 20370/25880 [4:09:57<1:10:41,  1.30it/s]
1|20371|Loss: 0.8676342964172363:  79%|███████▊  | 20371/25880 [4:09:58<1:11:45,  1.28it/s]
1|20372|Loss: 0.8509759902954102:  79%|███████▊  | 20371/25880 [4:09:58<1:11:45,  1.28it/s]
1|20372|Loss: 0.8509759902954102:  79%|███████▊  | 20372/25880 [4:09:58<1:12:41,  1.26it/s]
1|20373|Loss: 0.8003107309341431:  79%|███████▊  | 20372/25880 [4:09:59<1:12:41,  1.26it/s]
1|20373|Loss: 0.8003107309341431:  79%|███████▊  | 20373/25880 [4:09:59<1:12:44,  1.26it/s]
1|20374|Loss: 0.8906224370002747:  79%|███████▊  | 20373/25880 [4:10:00<1:12:44,  1.26it/s]
1|20374|Loss: 0.8906224370002747:  79%|███████▊  | 20374/25880 [4:10:00<1:11:32,  1.28it/s]
1|20375|Loss: 0.8928312659263611:  79%|███████▊  | 20374/25880 [4:10:00<1:11:32,  1.28it/s]
1|20375|Loss: 0.8928312659263611:  79%|███████▊  | 20375/25880 [4:10:01<1:07:40,  1.36it/s]
1|20376|Loss: 0.845557689666748:  79%|███████▊  | 20375/25880 [4:10:01<1:07:40,  1.36it/s] 
1|20376|Loss: 0.845557689666748:  79%|███████▊  | 20376/25880 [4:10:01<1:06:49,  1.37it/s]
1|20377|Loss: 0.8131695985794067:  79%|███████▊  | 20376/25880 [4:10:02<1:06:49,  1.37it/s]
1|20377|Loss: 0.8131695985794067:  79%|███████▊  | 20377/25880 [4:10:02<1:06:47,  1.37it/s]
1|20378|Loss: 0.8836914896965027:  79%|███████▊  | 20377/25880 [4:10:02<1:06:47,  1.37it/s]
1|20378|Loss: 0.8836914896965027:  79%|███████▊  | 20378/25880 [4:10:03<1:06:57,  1.37it/s]
1|20379|Loss: 0.7679824829101562:  79%|███████▊  | 20378/25880 [4:10:03<1:06:57,  1.37it/s]
1|20379|Loss: 0.7679824829101562:  79%|███████▊  | 20379/25880 [4:10:04<1:14:04,  1.24it/s]
1|20380|Loss: 0.8327115178108215:  79%|███████▊  | 20379/25880 [4:10:04<1:14:04,  1.24it/s]
1|20380|Loss: 0.8327115178108215:  79%|███████▊  | 20380/25880 [4:10:04<1:11:42,  1.28it/s]
1|20381|Loss: 0.9013366103172302:  79%|███████▊  | 20380/25880 [4:10:05<1:11:42,  1.28it/s]
1|20381|Loss: 0.9013366103172302:  79%|███████▉  | 20381/25880 [4:10:05<1:11:57,  1.27it/s]
1|20382|Loss: 0.8686460852622986:  79%|███████▉  | 20381/25880 [4:10:06<1:11:57,  1.27it/s]
1|20382|Loss: 0.8686460852622986:  79%|███████▉  | 20382/25880 [4:10:06<1:06:09,  1.38it/s]
1|20383|Loss: 0.8260296583175659:  79%|███████▉  | 20382/25880 [4:10:06<1:06:09,  1.38it/s]
1|20383|Loss: 0.8260296583175659:  79%|███████▉  | 20383/25880 [4:10:07<1:04:32,  1.42it/s]
1|20384|Loss: 0.8148897886276245:  79%|███████▉  | 20383/25880 [4:10:07<1:04:32,  1.42it/s]
1|20384|Loss: 0.8148897886276245:  79%|███████▉  | 20384/25880 [4:10:07<1:05:16,  1.40it/s]
1|20385|Loss: 0.9399197101593018:  79%|███████▉  | 20384/25880 [4:10:08<1:05:16,  1.40it/s]
1|20385|Loss: 0.9399197101593018:  79%|███████▉  | 20385/25880 [4:10:08<1:08:32,  1.34it/s]
1|20386|Loss: 0.8773449063301086:  79%|███████▉  | 20385/25880 [4:10:09<1:08:32,  1.34it/s]
1|20386|Loss: 0.8773449063301086:  79%|███████▉  | 20386/25880 [4:10:09<1:11:29,  1.28it/s]
1|20387|Loss: 0.7863428592681885:  79%|███████▉  | 20386/25880 [4:10:09<1:11:29,  1.28it/s]
1|20387|Loss: 0.7863428592681885:  79%|███████▉  | 20387/25880 [4:10:10<1:13:02,  1.25it/s]
1|20388|Loss: 0.8207780718803406:  79%|███████▉  | 20387/25880 [4:10:10<1:13:02,  1.25it/s]
1|20388|Loss: 0.8207780718803406:  79%|███████▉  | 20388/25880 [4:10:11<1:12:01,  1.27it/s]
1|20389|Loss: 0.8556610345840454:  79%|███████▉  | 20388/25880 [4:10:11<1:12:01,  1.27it/s]
1|20389|Loss: 0.8556610345840454:  79%|███████▉  | 20389/25880 [4:10:11<1:12:55,  1.25it/s]
1|20390|Loss: 0.841076135635376:  79%|███████▉  | 20389/25880 [4:10:12<1:12:55,  1.25it/s] 
1|20390|Loss: 0.841076135635376:  79%|███████▉  | 20390/25880 [4:10:12<1:15:40,  1.21it/s]
1|20391|Loss: 0.9052566885948181:  79%|███████▉  | 20390/25880 [4:10:13<1:15:40,  1.21it/s]
1|20391|Loss: 0.9052566885948181:  79%|███████▉  | 20391/25880 [4:10:13<1:12:11,  1.27it/s]
1|20392|Loss: 0.6699336171150208:  79%|███████▉  | 20391/25880 [4:10:13<1:12:11,  1.27it/s]
1|20392|Loss: 0.6699336171150208:  79%|███████▉  | 20392/25880 [4:10:14<1:18:28,  1.17it/s]
1|20393|Loss: 0.7590077519416809:  79%|███████▉  | 20392/25880 [4:10:14<1:18:28,  1.17it/s]
1|20393|Loss: 0.7590077519416809:  79%|███████▉  | 20393/25880 [4:10:15<1:18:47,  1.16it/s]
1|20394|Loss: 0.8040776252746582:  79%|███████▉  | 20393/25880 [4:10:15<1:18:47,  1.16it/s]
1|20394|Loss: 0.8040776252746582:  79%|███████▉  | 20394/25880 [4:10:16<1:15:52,  1.20it/s]
1|20395|Loss: 0.8521344065666199:  79%|███████▉  | 20394/25880 [4:10:16<1:15:52,  1.20it/s]
1|20395|Loss: 0.8521344065666199:  79%|███████▉  | 20395/25880 [4:10:16<1:12:45,  1.26it/s]
1|20396|Loss: 0.848399817943573:  79%|███████▉  | 20395/25880 [4:10:17<1:12:45,  1.26it/s] 
1|20396|Loss: 0.848399817943573:  79%|███████▉  | 20396/25880 [4:10:17<1:10:40,  1.29it/s]
1|20397|Loss: 0.7962084412574768:  79%|███████▉  | 20396/25880 [4:10:17<1:10:40,  1.29it/s]
1|20397|Loss: 0.7962084412574768:  79%|███████▉  | 20397/25880 [4:10:18<1:12:22,  1.26it/s]
1|20398|Loss: 0.8978279829025269:  79%|███████▉  | 20397/25880 [4:10:18<1:12:22,  1.26it/s]
1|20398|Loss: 0.8978279829025269:  79%|███████▉  | 20398/25880 [4:10:19<1:11:44,  1.27it/s]
1|20399|Loss: 0.7806583642959595:  79%|███████▉  | 20398/25880 [4:10:19<1:11:44,  1.27it/s]
1|20399|Loss: 0.7806583642959595:  79%|███████▉  | 20399/25880 [4:10:19<1:10:33,  1.29it/s]
1|20400|Loss: 0.9447740912437439:  79%|███████▉  | 20399/25880 [4:10:20<1:10:33,  1.29it/s]
1|20400|Loss: 0.9447740912437439:  79%|███████▉  | 20400/25880 [4:10:20<1:09:42,  1.31it/s]
1|20401|Loss: 0.8996973633766174:  79%|███████▉  | 20400/25880 [4:10:21<1:09:42,  1.31it/s]
1|20401|Loss: 0.8996973633766174:  79%|███████▉  | 20401/25880 [4:10:21<1:08:59,  1.32it/s]
1|20402|Loss: 0.8133577108383179:  79%|███████▉  | 20401/25880 [4:10:21<1:08:59,  1.32it/s]
1|20402|Loss: 0.8133577108383179:  79%|███████▉  | 20402/25880 [4:10:22<1:08:00,  1.34it/s]
1|20403|Loss: 0.8272064924240112:  79%|███████▉  | 20402/25880 [4:10:22<1:08:00,  1.34it/s]
1|20403|Loss: 0.8272064924240112:  79%|███████▉  | 20403/25880 [4:10:22<1:06:57,  1.36it/s]
1|20404|Loss: 1.0631780624389648:  79%|███████▉  | 20403/25880 [4:10:23<1:06:57,  1.36it/s]
1|20404|Loss: 1.0631780624389648:  79%|███████▉  | 20404/25880 [4:10:23<1:07:08,  1.36it/s]
1|20405|Loss: 0.8977798819541931:  79%|███████▉  | 20404/25880 [4:10:23<1:07:08,  1.36it/s]
1|20405|Loss: 0.8977798819541931:  79%|███████▉  | 20405/25880 [4:10:24<1:07:37,  1.35it/s]
1|20406|Loss: 0.859165608882904:  79%|███████▉  | 20405/25880 [4:10:24<1:07:37,  1.35it/s] 
1|20406|Loss: 0.859165608882904:  79%|███████▉  | 20406/25880 [4:10:25<1:08:53,  1.32it/s]
1|20407|Loss: 0.9165981411933899:  79%|███████▉  | 20406/25880 [4:10:25<1:08:53,  1.32it/s]
1|20407|Loss: 0.9165981411933899:  79%|███████▉  | 20407/25880 [4:10:25<1:08:51,  1.32it/s]
1|20408|Loss: 0.7857091426849365:  79%|███████▉  | 20407/25880 [4:10:26<1:08:51,  1.32it/s]
1|20408|Loss: 0.7857091426849365:  79%|███████▉  | 20408/25880 [4:10:26<1:12:33,  1.26it/s]
1|20409|Loss: 0.8239607810974121:  79%|███████▉  | 20408/25880 [4:10:27<1:12:33,  1.26it/s]
1|20409|Loss: 0.8239607810974121:  79%|███████▉  | 20409/25880 [4:10:27<1:11:07,  1.28it/s]
1|20410|Loss: 0.7560995221138:  79%|███████▉  | 20409/25880 [4:10:27<1:11:07,  1.28it/s]   
1|20410|Loss: 0.7560995221138:  79%|███████▉  | 20410/25880 [4:10:28<1:11:35,  1.27it/s]
1|20411|Loss: 0.8357728123664856:  79%|███████▉  | 20410/25880 [4:10:28<1:11:35,  1.27it/s]
1|20411|Loss: 0.8357728123664856:  79%|███████▉  | 20411/25880 [4:10:29<1:12:38,  1.25it/s]
1|20412|Loss: 0.8785600066184998:  79%|███████▉  | 20411/25880 [4:10:29<1:12:38,  1.25it/s]
1|20412|Loss: 0.8785600066184998:  79%|███████▉  | 20412/25880 [4:10:29<1:10:37,  1.29it/s]
1|20413|Loss: 1.0051829814910889:  79%|███████▉  | 20412/25880 [4:10:30<1:10:37,  1.29it/s]
1|20413|Loss: 1.0051829814910889:  79%|███████▉  | 20413/25880 [4:10:30<1:05:47,  1.39it/s]
1|20414|Loss: 0.8777651786804199:  79%|███████▉  | 20413/25880 [4:10:30<1:05:47,  1.39it/s]
1|20414|Loss: 0.8777651786804199:  79%|███████▉  | 20414/25880 [4:10:31<1:04:43,  1.41it/s]
1|20415|Loss: 0.8168019652366638:  79%|███████▉  | 20414/25880 [4:10:31<1:04:43,  1.41it/s]
1|20415|Loss: 0.8168019652366638:  79%|███████▉  | 20415/25880 [4:10:31<1:03:14,  1.44it/s]
1|20416|Loss: 0.7756299376487732:  79%|███████▉  | 20415/25880 [4:10:32<1:03:14,  1.44it/s]
1|20416|Loss: 0.7756299376487732:  79%|███████▉  | 20416/25880 [4:10:32<1:00:40,  1.50it/s]
1|20417|Loss: 0.7436658143997192:  79%|███████▉  | 20416/25880 [4:10:32<1:00:40,  1.50it/s]
1|20417|Loss: 0.7436658143997192:  79%|███████▉  | 20417/25880 [4:10:32<58:35,  1.55it/s]  
1|20418|Loss: 0.8108131885528564:  79%|███████▉  | 20417/25880 [4:10:33<58:35,  1.55it/s]
1|20418|Loss: 0.8108131885528564:  79%|███████▉  | 20418/25880 [4:10:33<58:01,  1.57it/s]
1|20419|Loss: 0.8084292411804199:  79%|███████▉  | 20418/25880 [4:10:33<58:01,  1.57it/s]
1|20419|Loss: 0.8084292411804199:  79%|███████▉  | 20419/25880 [4:10:34<1:00:18,  1.51it/s]
1|20420|Loss: 0.7074146866798401:  79%|███████▉  | 20419/25880 [4:10:34<1:00:18,  1.51it/s]
1|20420|Loss: 0.7074146866798401:  79%|███████▉  | 20420/25880 [4:10:34<1:00:25,  1.51it/s]
1|20421|Loss: 0.889693021774292:  79%|███████▉  | 20420/25880 [4:10:35<1:00:25,  1.51it/s] 
1|20421|Loss: 0.889693021774292:  79%|███████▉  | 20421/25880 [4:10:35<59:58,  1.52it/s]  
1|20422|Loss: 0.7186005711555481:  79%|███████▉  | 20421/25880 [4:10:35<59:58,  1.52it/s]
1|20422|Loss: 0.7186005711555481:  79%|███████▉  | 20422/25880 [4:10:36<1:03:27,  1.43it/s]
1|20423|Loss: 0.8567841053009033:  79%|███████▉  | 20422/25880 [4:10:36<1:03:27,  1.43it/s]
1|20423|Loss: 0.8567841053009033:  79%|███████▉  | 20423/25880 [4:10:37<1:05:11,  1.40it/s]
1|20424|Loss: 0.7851485013961792:  79%|███████▉  | 20423/25880 [4:10:37<1:05:11,  1.40it/s]
1|20424|Loss: 0.7851485013961792:  79%|███████▉  | 20424/25880 [4:10:37<1:02:27,  1.46it/s]
1|20425|Loss: 0.8959019780158997:  79%|███████▉  | 20424/25880 [4:10:38<1:02:27,  1.46it/s]
1|20425|Loss: 0.8959019780158997:  79%|███████▉  | 20425/25880 [4:10:38<1:04:20,  1.41it/s]
1|20426|Loss: 0.9173609018325806:  79%|███████▉  | 20425/25880 [4:10:38<1:04:20,  1.41it/s]
1|20426|Loss: 0.9173609018325806:  79%|███████▉  | 20426/25880 [4:10:39<1:07:42,  1.34it/s]
1|20427|Loss: 0.8055709004402161:  79%|███████▉  | 20426/25880 [4:10:39<1:07:42,  1.34it/s]
1|20427|Loss: 0.8055709004402161:  79%|███████▉  | 20427/25880 [4:10:39<1:03:53,  1.42it/s]
1|20428|Loss: 0.7957434058189392:  79%|███████��  | 20427/25880 [4:10:40<1:03:53,  1.42it/s]
1|20428|Loss: 0.7957434058189392:  79%|███████▉  | 20428/25880 [4:10:40<1:05:51,  1.38it/s]
1|20429|Loss: 0.6685149669647217:  79%|███████▉  | 20428/25880 [4:10:41<1:05:51,  1.38it/s]
1|20429|Loss: 0.6685149669647217:  79%|███████▉  | 20429/25880 [4:10:41<1:11:26,  1.27it/s]
1|20430|Loss: 0.8723276853561401:  79%|███████▉  | 20429/25880 [4:10:42<1:11:26,  1.27it/s]
1|20430|Loss: 0.8723276853561401:  79%|███████▉  | 20430/25880 [4:10:42<1:11:41,  1.27it/s]
1|20431|Loss: 0.7997217178344727:  79%|███████▉  | 20430/25880 [4:10:42<1:11:41,  1.27it/s]
1|20431|Loss: 0.7997217178344727:  79%|███████▉  | 20431/25880 [4:10:43<1:08:21,  1.33it/s]
1|20432|Loss: 0.7961773872375488:  79%|███████▉  | 20431/25880 [4:10:43<1:08:21,  1.33it/s]
1|20432|Loss: 0.7961773872375488:  79%|███████▉  | 20432/25880 [4:10:43<1:02:30,  1.45it/s]
1|20433|Loss: 0.7111408114433289:  79%|███████▉  | 20432/25880 [4:10:44<1:02:30,  1.45it/s]
1|20433|Loss: 0.7111408114433289:  79%|███████▉  | 20433/25880 [4:10:44<1:02:44,  1.45it/s]
1|20434|Loss: 0.7598884701728821:  79%|███████▉  | 20433/25880 [4:10:44<1:02:44,  1.45it/s]
1|20434|Loss: 0.7598884701728821:  79%|███████▉  | 20434/25880 [4:10:45<1:06:40,  1.36it/s]
1|20435|Loss: 0.8864039182662964:  79%|███████▉  | 20434/25880 [4:10:45<1:06:40,  1.36it/s]
1|20435|Loss: 0.8864039182662964:  79%|███████▉  | 20435/25880 [4:10:46<1:09:37,  1.30it/s]
1|20436|Loss: 0.8017966747283936:  79%|███████▉  | 20435/25880 [4:10:46<1:09:37,  1.30it/s]
1|20436|Loss: 0.8017966747283936:  79%|███████▉  | 20436/25880 [4:10:46<1:09:16,  1.31it/s]
1|20437|Loss: 0.8265649676322937:  79%|███████▉  | 20436/25880 [4:10:47<1:09:16,  1.31it/s]
1|20437|Loss: 0.8265649676322937:  79%|███████▉  | 20437/25880 [4:10:47<1:08:16,  1.33it/s]
1|20438|Loss: 0.7035103440284729:  79%|███████▉  | 20437/25880 [4:10:47<1:08:16,  1.33it/s]
1|20438|Loss: 0.7035103440284729:  79%|███████▉  | 20438/25880 [4:10:48<1:12:30,  1.25it/s]
1|20439|Loss: 0.8603730201721191:  79%|███████▉  | 20438/25880 [4:10:48<1:12:30,  1.25it/s]
1|20439|Loss: 0.8603730201721191:  79%|███████▉  | 20439/25880 [4:10:49<1:11:19,  1.27it/s]
1|20440|Loss: 0.7464829087257385:  79%|███████▉  | 20439/25880 [4:10:49<1:11:19,  1.27it/s]
1|20440|Loss: 0.7464829087257385:  79%|███████▉  | 20440/25880 [4:10:49<1:09:42,  1.30it/s]
1|20441|Loss: 0.8052670359611511:  79%|███████▉  | 20440/25880 [4:10:50<1:09:42,  1.30it/s]
1|20441|Loss: 0.8052670359611511:  79%|███████▉  | 20441/25880 [4:10:50<1:07:54,  1.33it/s]
1|20442|Loss: 0.8725119829177856:  79%|███████▉  | 20441/25880 [4:10:50<1:07:54,  1.33it/s]
1|20442|Loss: 0.8725119829177856:  79%|███████▉  | 20442/25880 [4:10:51<1:07:04,  1.35it/s]
1|20443|Loss: 0.9300850033760071:  79%|███████▉  | 20442/25880 [4:10:51<1:07:04,  1.35it/s]
1|20443|Loss: 0.9300850033760071:  79%|███████▉  | 20443/25880 [4:10:52<1:06:09,  1.37it/s]
1|20444|Loss: 0.8686951398849487:  79%|███████▉  | 20443/25880 [4:10:52<1:06:09,  1.37it/s]
1|20444|Loss: 0.8686951398849487:  79%|███████▉  | 20444/25880 [4:10:52<1:06:05,  1.37it/s]
1|20445|Loss: 0.8350778222084045:  79%|███████▉  | 20444/25880 [4:10:53<1:06:05,  1.37it/s]
1|20445|Loss: 0.8350778222084045:  79%|███████▉  | 20445/25880 [4:10:53<1:10:07,  1.29it/s]
1|20446|Loss: 0.8342645168304443:  79%|███████▉  | 20445/25880 [4:10:53<1:10:07,  1.29it/s]
1|20446|Loss: 0.8342645168304443:  79%|███████▉  | 20446/25880 [4:10:54<1:03:56,  1.42it/s]
1|20447|Loss: 0.8787660002708435:  79%|███████▉  | 20446/25880 [4:10:54<1:03:56,  1.42it/s]
1|20447|Loss: 0.8787660002708435:  79%|███████▉  | 20447/25880 [4:10:54<1:03:03,  1.44it/s]
1|20448|Loss: 0.7123816609382629:  79%|███████▉  | 20447/25880 [4:10:55<1:03:03,  1.44it/s]
1|20448|Loss: 0.7123816609382629:  79%|███████▉  | 20448/25880 [4:10:55<1:07:07,  1.35it/s]
1|20449|Loss: 0.7815514802932739:  79%|███████▉  | 20448/25880 [4:10:56<1:07:07,  1.35it/s]
1|20449|Loss: 0.7815514802932739:  79%|███████▉  | 20449/25880 [4:10:56<1:04:54,  1.39it/s]
1|20450|Loss: 0.6805705428123474:  79%|███████▉  | 20449/25880 [4:10:56<1:04:54,  1.39it/s]
1|20450|Loss: 0.6805705428123474:  79%|███████▉  | 20450/25880 [4:10:57<1:03:38,  1.42it/s]
1|20451|Loss: 0.5847560167312622:  79%|███████▉  | 20450/25880 [4:10:57<1:03:38,  1.42it/s]
1|20451|Loss: 0.5847560167312622:  79%|███████▉  | 20451/25880 [4:10:57<1:08:10,  1.33it/s]
1|20452|Loss: 0.891506016254425:  79%|███████▉  | 20451/25880 [4:10:58<1:08:10,  1.33it/s] 
1|20452|Loss: 0.891506016254425:  79%|███████▉  | 20452/25880 [4:10:58<1:08:35,  1.32it/s]
1|20453|Loss: 0.7461512088775635:  79%|███████▉  | 20452/25880 [4:10:59<1:08:35,  1.32it/s]
1|20453|Loss: 0.7461512088775635:  79%|███████▉  | 20453/25880 [4:10:59<1:11:00,  1.27it/s]
1|20454|Loss: 0.819085955619812:  79%|███████▉  | 20453/25880 [4:10:59<1:11:00,  1.27it/s] 
1|20454|Loss: 0.819085955619812:  79%|███████▉  | 20454/25880 [4:11:00<1:09:54,  1.29it/s]
1|20455|Loss: 0.7688294053077698:  79%|███████▉  | 20454/25880 [4:11:00<1:09:54,  1.29it/s]
1|20455|Loss: 0.7688294053077698:  79%|███████▉  | 20455/25880 [4:11:01<1:08:56,  1.31it/s]
1|20456|Loss: 0.7863803505897522:  79%|███████▉  | 20455/25880 [4:11:01<1:08:56,  1.31it/s]
1|20456|Loss: 0.7863803505897522:  79%|███████▉  | 20456/25880 [4:11:01<1:08:19,  1.32it/s]
1|20457|Loss: 0.8209267854690552:  79%|███████▉  | 20456/25880 [4:11:02<1:08:19,  1.32it/s]
1|20457|Loss: 0.8209267854690552:  79%|███████▉  | 20457/25880 [4:11:02<1:08:59,  1.31it/s]
1|20458|Loss: 0.9030561447143555:  79%|███████▉  | 20457/25880 [4:11:02<1:08:59,  1.31it/s]
1|20458|Loss: 0.9030561447143555:  79%|███████▉  | 20458/25880 [4:11:03<1:08:54,  1.31it/s]
1|20459|Loss: 0.7899672389030457:  79%|███████▉  | 20458/25880 [4:11:03<1:08:54,  1.31it/s]
1|20459|Loss: 0.7899672389030457:  79%|███████▉  | 20459/25880 [4:11:04<1:08:24,  1.32it/s]
1|20460|Loss: 0.8094238042831421:  79%|███████▉  | 20459/25880 [4:11:04<1:08:24,  1.32it/s]
1|20460|Loss: 0.8094238042831421:  79%|███████▉  | 20460/25880 [4:11:04<1:05:34,  1.38it/s]
1|20461|Loss: 0.861316978931427:  79%|███████▉  | 20460/25880 [4:11:04<1:05:34,  1.38it/s] 
1|20461|Loss: 0.861316978931427:  79%|███████▉  | 20461/25880 [4:11:05<59:48,  1.51it/s]  
1|20462|Loss: 0.7630897164344788:  79%|███████▉  | 20461/25880 [4:11:05<59:48,  1.51it/s]
1|20462|Loss: 0.7630897164344788:  79%|███████▉  | 20462/25880 [4:11:05<59:47,  1.51it/s]
1|20463|Loss: 0.7682153582572937:  79%|███████▉  | 20462/25880 [4:11:06<59:47,  1.51it/s]
1|20463|Loss: 0.7682153582572937:  79%|███████▉  | 20463/25880 [4:11:06<1:01:39,  1.46it/s]
1|20464|Loss: 0.7626359462738037:  79%|███████▉  | 20463/25880 [4:11:06<1:01:39,  1.46it/s]
1|20464|Loss: 0.7626359462738037:  79%|███████▉  | 20464/25880 [4:11:07<58:49,  1.53it/s]  
1|20465|Loss: 0.7474460005760193:  79%|███████▉  | 20464/25880 [4:11:07<58:49,  1.53it/s]
1|20465|Loss: 0.7474460005760193:  79%|███████▉  | 20465/25880 [4:11:07<57:45,  1.56it/s]
1|20466|Loss: 0.9447510242462158:  79%|███████▉  | 20465/25880 [4:11:08<57:45,  1.56it/s]
1|20466|Loss: 0.9447510242462158:  79%|███████▉  | 20466/25880 [4:11:08<1:01:45,  1.46it/s]
1|20467|Loss: 0.8333826661109924:  79%|███████▉  | 20466/25880 [4:11:09<1:01:45,  1.46it/s]
1|20467|Loss: 0.8333826661109924:  79%|███████▉  | 20467/25880 [4:11:09<1:05:42,  1.37it/s]
1|20468|Loss: 0.9618169069290161:  79%|███████▉  | 20467/25880 [4:11:09<1:05:42,  1.37it/s]
1|20468|Loss: 0.9618169069290161:  79%|███████▉  | 20468/25880 [4:11:10<1:05:33,  1.38it/s]
1|20469|Loss: 0.7218099236488342:  79%|███████▉  | 20468/25880 [4:11:10<1:05:33,  1.38it/s]
1|20469|Loss: 0.7218099236488342:  79%|███████▉  | 20469/25880 [4:11:11<1:09:29,  1.30it/s]
1|20470|Loss: 0.8448151350021362:  79%|███████▉  | 20469/25880 [4:11:11<1:09:29,  1.30it/s]
1|20470|Loss: 0.8448151350021362:  79%|███████▉  | 20470/25880 [4:11:11<1:10:55,  1.27it/s]
1|20471|Loss: 0.9496732354164124:  79%|███████▉  | 20470/25880 [4:11:12<1:10:55,  1.27it/s]
1|20471|Loss: 0.9496732354164124:  79%|███████▉  | 20471/25880 [4:11:12<1:07:21,  1.34it/s]
1|20472|Loss: 0.9340371489524841:  79%|███████▉  | 20471/25880 [4:11:12<1:07:21,  1.34it/s]
1|20472|Loss: 0.9340371489524841:  79%|███████▉  | 20472/25880 [4:11:13<1:01:56,  1.46it/s]
1|20473|Loss: 0.906221330165863:  79%|███████▉  | 20472/25880 [4:11:13<1:01:56,  1.46it/s] 
1|20473|Loss: 0.906221330165863:  79%|███████▉  | 20473/25880 [4:11:13<1:05:17,  1.38it/s]
1|20474|Loss: 0.8028085827827454:  79%|███████▉  | 20473/25880 [4:11:14<1:05:17,  1.38it/s]
1|20474|Loss: 0.8028085827827454:  79%|███████▉  | 20474/25880 [4:11:14<1:08:23,  1.32it/s]
1|20475|Loss: 0.728996217250824:  79%|███████▉  | 20474/25880 [4:11:15<1:08:23,  1.32it/s] 
1|20475|Loss: 0.728996217250824:  79%|██████��▉  | 20475/25880 [4:11:15<1:07:54,  1.33it/s]
1|20476|Loss: 0.8991100788116455:  79%|███████▉  | 20475/25880 [4:11:15<1:07:54,  1.33it/s]
1|20476|Loss: 0.8991100788116455:  79%|███████▉  | 20476/25880 [4:11:16<1:07:01,  1.34it/s]
1|20477|Loss: 0.8604763150215149:  79%|███████▉  | 20476/25880 [4:11:16<1:07:01,  1.34it/s]
1|20477|Loss: 0.8604763150215149:  79%|███████▉  | 20477/25880 [4:11:16<1:07:41,  1.33it/s]
1|20478|Loss: 0.791662871837616:  79%|███████▉  | 20477/25880 [4:11:17<1:07:41,  1.33it/s] 
1|20478|Loss: 0.791662871837616:  79%|███████▉  | 20478/25880 [4:11:17<1:07:55,  1.33it/s]
1|20479|Loss: 0.73944091796875:  79%|███████▉  | 20478/25880 [4:11:18<1:07:55,  1.33it/s] 
1|20479|Loss: 0.73944091796875:  79%|███████▉  | 20479/25880 [4:11:18<1:07:29,  1.33it/s]
1|20480|Loss: 0.8480084538459778:  79%|███████▉  | 20479/25880 [4:11:18<1:07:29,  1.33it/s]
1|20480|Loss: 0.8480084538459778:  79%|███████▉  | 20480/25880 [4:11:19<1:11:06,  1.27it/s]
1|20481|Loss: 0.8591317534446716:  79%|███████▉  | 20480/25880 [4:11:19<1:11:06,  1.27it/s]
1|20481|Loss: 0.8591317534446716:  79%|███████▉  | 20481/25880 [4:11:19<1:08:05,  1.32it/s]
1|20482|Loss: 0.8803882002830505:  79%|███████▉  | 20481/25880 [4:11:20<1:08:05,  1.32it/s]
1|20482|Loss: 0.8803882002830505:  79%|███████▉  | 20482/25880 [4:11:20<1:08:54,  1.31it/s]
1|20483|Loss: 0.717265248298645:  79%|███████▉  | 20482/25880 [4:11:21<1:08:54,  1.31it/s] 
1|20483|Loss: 0.717265248298645:  79%|███████▉  | 20483/25880 [4:11:21<1:12:27,  1.24it/s]
1|20484|Loss: 0.8289496302604675:  79%|███████▉  | 20483/25880 [4:11:22<1:12:27,  1.24it/s]
1|20484|Loss: 0.8289496302604675:  79%|███████▉  | 20484/25880 [4:11:22<1:13:34,  1.22it/s]
1|20485|Loss: 0.7607032060623169:  79%|███████▉  | 20484/25880 [4:11:22<1:13:34,  1.22it/s]
1|20485|Loss: 0.7607032060623169:  79%|███████▉  | 20485/25880 [4:11:23<1:06:30,  1.35it/s]
1|20486|Loss: 0.7480367422103882:  79%|███████▉  | 20485/25880 [4:11:23<1:06:30,  1.35it/s]
1|20486|Loss: 0.7480367422103882:  79%|███████▉  | 20486/25880 [4:11:23<1:01:33,  1.46it/s]
1|20487|Loss: 0.750610888004303:  79%|███████▉  | 20486/25880 [4:11:23<1:01:33,  1.46it/s] 
1|20487|Loss: 0.750610888004303:  79%|███████▉  | 20487/25880 [4:11:24<59:49,  1.50it/s]  
1|20488|Loss: 0.8656237125396729:  79%|███████▉  | 20487/25880 [4:11:24<59:49,  1.50it/s]
1|20488|Loss: 0.8656237125396729:  79%|███████▉  | 20488/25880 [4:11:24<53:41,  1.67it/s]
1|20489|Loss: 0.8551568388938904:  79%|███████▉  | 20488/25880 [4:11:25<53:41,  1.67it/s]
1|20489|Loss: 0.8551568388938904:  79%|███████▉  | 20489/25880 [4:11:25<57:10,  1.57it/s]
1|20490|Loss: 0.8279385566711426:  79%|███████▉  | 20489/25880 [4:11:25<57:10,  1.57it/s]
1|20490|Loss: 0.8279385566711426:  79%|███████▉  | 20490/25880 [4:11:26<58:13,  1.54it/s]
1|20491|Loss: 0.8094990253448486:  79%|███████▉  | 20490/25880 [4:11:26<58:13,  1.54it/s]
1|20491|Loss: 0.8094990253448486:  79%|███████▉  | 20491/25880 [4:11:26<57:24,  1.56it/s]
1|20492|Loss: 0.8781855702400208:  79%|███████▉  | 20491/25880 [4:11:27<57:24,  1.56it/s]
1|20492|Loss: 0.8781855702400208:  79%|███████▉  | 20492/25880 [4:11:27<1:00:50,  1.48it/s]
1|20493|Loss: 0.6814549565315247:  79%|███████▉  | 20492/25880 [4:11:27<1:00:50,  1.48it/s]
1|20493|Loss: 0.6814549565315247:  79%|███████▉  | 20493/25880 [4:11:28<1:05:14,  1.38it/s]
1|20494|Loss: 0.7566500306129456:  79%|███████▉  | 20493/25880 [4:11:28<1:05:14,  1.38it/s]
1|20494|Loss: 0.7566500306129456:  79%|███████▉  | 20494/25880 [4:11:29<1:08:08,  1.32it/s]
1|20495|Loss: 0.7157519459724426:  79%|███████▉  | 20494/25880 [4:11:29<1:08:08,  1.32it/s]
1|20495|Loss: 0.7157519459724426:  79%|███████▉  | 20495/25880 [4:11:29<1:07:45,  1.32it/s]
1|20496|Loss: 1.00315523147583:  79%|███████▉  | 20495/25880 [4:11:30<1:07:45,  1.32it/s]  
1|20496|Loss: 1.00315523147583:  79%|███████▉  | 20496/25880 [4:11:30<1:09:15,  1.30it/s]
1|20497|Loss: 0.9180058240890503:  79%|███████▉  | 20496/25880 [4:11:31<1:09:15,  1.30it/s]
1|20497|Loss: 0.9180058240890503:  79%|███████▉  | 20497/25880 [4:11:31<1:08:06,  1.32it/s]
1|20498|Loss: 0.8202567100524902:  79%|███████▉  | 20497/25880 [4:11:31<1:08:06,  1.32it/s]
1|20498|Loss: 0.8202567100524902:  79%|███████▉  | 20498/25880 [4:11:32<1:09:47,  1.29it/s]
1|20499|Loss: 0.8369337320327759:  79%|███████▉  | 20498/25880 [4:11:32<1:09:47,  1.29it/s]
1|20499|Loss: 0.8369337320327759:  79%|███████▉  | 20499/25880 [4:11:32<1:07:19,  1.33it/s]
1|20500|Loss: 0.8577263355255127:  79%|███████▉  | 20499/25880 [4:11:33<1:07:19,  1.33it/s]
1|20500|Loss: 0.8577263355255127:  79%|███████▉  | 20500/25880 [4:11:33<1:04:16,  1.39it/s]
1|20501|Loss: 0.8438043594360352:  79%|███████▉  | 20500/25880 [4:11:33<1:04:16,  1.39it/s]
1|20501|Loss: 0.8438043594360352:  79%|███████▉  | 20501/25880 [4:11:34<1:05:19,  1.37it/s]
1|20502|Loss: 0.824100136756897:  79%|███████▉  | 20501/25880 [4:11:34<1:05:19,  1.37it/s] 
1|20502|Loss: 0.824100136756897:  79%|███████▉  | 20502/25880 [4:11:35<1:03:57,  1.40it/s]
1|20503|Loss: 0.8291055560112:  79%|███████▉  | 20502/25880 [4:11:35<1:03:57,  1.40it/s]  
1|20503|Loss: 0.8291055560112:  79%|███████▉  | 20503/25880 [4:11:35<1:03:28,  1.41it/s]
1|20504|Loss: 0.8466911911964417:  79%|███████▉  | 20503/25880 [4:11:36<1:03:28,  1.41it/s]
1|20504|Loss: 0.8466911911964417:  79%|███████▉  | 20504/25880 [4:11:36<1:09:05,  1.30it/s]
1|20505|Loss: 0.8334187865257263:  79%|███████▉  | 20504/25880 [4:11:37<1:09:05,  1.30it/s]
1|20505|Loss: 0.8334187865257263:  79%|███████▉  | 20505/25880 [4:11:37<1:08:35,  1.31it/s]
1|20506|Loss: 0.8128559589385986:  79%|███████▉  | 20505/25880 [4:11:37<1:08:35,  1.31it/s]
1|20506|Loss: 0.8128559589385986:  79%|███████▉  | 20506/25880 [4:11:38<1:07:27,  1.33it/s]
1|20507|Loss: 0.770469605922699:  79%|███████▉  | 20506/25880 [4:11:38<1:07:27,  1.33it/s] 
1|20507|Loss: 0.770469605922699:  79%|███████▉  | 20507/25880 [4:11:38<1:06:33,  1.35it/s]
1|20508|Loss: 0.7871620059013367:  79%|███████▉  | 20507/25880 [4:11:39<1:06:33,  1.35it/s]
1|20508|Loss: 0.7871620059013367:  79%|███████▉  | 20508/25880 [4:11:39<1:02:44,  1.43it/s]
1|20509|Loss: 0.8393386006355286:  79%|███████▉  | 20508/25880 [4:11:39<1:02:44,  1.43it/s]
1|20509|Loss: 0.8393386006355286:  79%|███████▉  | 20509/25880 [4:11:40<1:04:43,  1.38it/s]
1|20510|Loss: 0.6912484765052795:  79%|███████▉  | 20509/25880 [4:11:40<1:04:43,  1.38it/s]
1|20510|Loss: 0.6912484765052795:  79%|███████▉  | 20510/25880 [4:11:40<1:00:34,  1.48it/s]
1|20511|Loss: 1.0287762880325317:  79%|███████▉  | 20510/25880 [4:11:41<1:00:34,  1.48it/s]
1|20511|Loss: 1.0287762880325317:  79%|███████▉  | 20511/25880 [4:11:41<58:27,  1.53it/s]  
1|20512|Loss: 0.7147006988525391:  79%|███████▉  | 20511/25880 [4:11:41<58:27,  1.53it/s]
1|20512|Loss: 0.7147006988525391:  79%|███████▉  | 20512/25880 [4:11:42<1:00:21,  1.48it/s]
1|20513|Loss: 0.7585068941116333:  79%|███████▉  | 20512/25880 [4:11:42<1:00:21,  1.48it/s]
1|20513|Loss: 0.7585068941116333:  79%|███████▉  | 20513/25880 [4:11:42<58:57,  1.52it/s]  
1|20514|Loss: 0.8262155055999756:  79%|███████▉  | 20513/25880 [4:11:43<58:57,  1.52it/s]
1|20514|Loss: 0.8262155055999756:  79%|███████▉  | 20514/25880 [4:11:43<1:00:31,  1.48it/s]
1|20515|Loss: 0.9178429841995239:  79%|███████▉  | 20514/25880 [4:11:43<1:00:31,  1.48it/s]
1|20515|Loss: 0.9178429841995239:  79%|███████▉  | 20515/25880 [4:11:44<1:04:54,  1.38it/s]
1|20516|Loss: 0.838960587978363:  79%|███████▉  | 20515/25880 [4:11:44<1:04:54,  1.38it/s] 
1|20516|Loss: 0.838960587978363:  79%|███████▉  | 20516/25880 [4:11:45<1:05:50,  1.36it/s]
1|20517|Loss: 0.7551122307777405:  79%|███████▉  | 20516/25880 [4:11:45<1:05:50,  1.36it/s]
1|20517|Loss: 0.7551122307777405:  79%|███████▉  | 20517/25880 [4:11:45<1:09:47,  1.28it/s]
1|20518|Loss: 0.8370424509048462:  79%|███████▉  | 20517/25880 [4:11:46<1:09:47,  1.28it/s]
1|20518|Loss: 0.8370424509048462:  79%|███████▉  | 20518/25880 [4:11:46<1:09:32,  1.29it/s]
1|20519|Loss: 0.7839393019676208:  79%|███████▉  | 20518/25880 [4:11:47<1:09:32,  1.29it/s]
1|20519|Loss: 0.7839393019676208:  79%|███████▉  | 20519/25880 [4:11:47<1:10:27,  1.27it/s]
1|20520|Loss: 0.8887245655059814:  79%|███████▉  | 20519/25880 [4:11:47<1:10:27,  1.27it/s]
1|20520|Loss: 0.8887245655059814:  79%|███████▉  | 20520/25880 [4:11:48<1:11:04,  1.26it/s]
1|20521|Loss: 0.6080631017684937:  79%|███████▉  | 20520/25880 [4:11:48<1:11:04,  1.26it/s]
1|20521|Loss: 0.6080631017684937:  79%|███████▉  | 20521/25880 [4:11:49<1:09:08,  1.29it/s]
1|20522|Loss: 0.6964433193206787:  79%|███████▉  | 20521/25880 [4:11:49<1:09:08,  1.29it/s]
1|20522|Loss: 0.6964433193206787:  79%|███████▉  | 20522/25880 [4:11:49<1:07:54,  1.32it/s]
1|20523|Loss: 0.825961709022522:  79%|███████▉  | 20522/25880 [4:11:50<1:07:54,  1.32it/s] 
1|20523|Loss: 0.825961709022522:  79%|███████▉  | 20523/25880 [4:11:50<1:09:14,  1.29it/s]
1|20524|Loss: 0.7726938128471375:  79%|███████▉  | 20523/25880 [4:11:51<1:09:14,  1.29it/s]
1|20524|Loss: 0.7726938128471375:  79%|███████▉  | 20524/25880 [4:11:51<1:10:08,  1.27it/s]
1|20525|Loss: 0.8977522850036621:  79%|███████▉  | 20524/25880 [4:11:51<1:10:08,  1.27it/s]
1|20525|Loss: 0.8977522850036621:  79%|███████▉  | 20525/25880 [4:11:52<1:07:00,  1.33it/s]
1|20526|Loss: 0.8520337343215942:  79%|███████▉  | 20525/25880 [4:11:52<1:07:00,  1.33it/s]
1|20526|Loss: 0.8520337343215942:  79%|███████▉  | 20526/25880 [4:11:52<1:08:26,  1.30it/s]
1|20527|Loss: 0.8479335308074951:  79%|███████▉  | 20526/25880 [4:11:53<1:08:26,  1.30it/s]
1|20527|Loss: 0.8479335308074951:  79%|███████▉  | 20527/25880 [4:11:53<1:08:26,  1.30it/s]
1|20528|Loss: 0.8073940873146057:  79%|███████▉  | 20527/25880 [4:11:54<1:08:26,  1.30it/s]
1|20528|Loss: 0.8073940873146057:  79%|███████▉  | 20528/25880 [4:11:54<1:05:45,  1.36it/s]
1|20529|Loss: 0.8341159820556641:  79%|███████▉  | 20528/25880 [4:11:54<1:05:45,  1.36it/s]
1|20529|Loss: 0.8341159820556641:  79%|███████▉  | 20529/25880 [4:11:54<1:01:52,  1.44it/s]
1|20530|Loss: 0.8686057329177856:  79%|███████▉  | 20529/25880 [4:11:55<1:01:52,  1.44it/s]
1|20530|Loss: 0.8686057329177856:  79%|███████▉  | 20530/25880 [4:11:55<1:02:07,  1.44it/s]
1|20531|Loss: 0.8899418115615845:  79%|███████▉  | 20530/25880 [4:11:56<1:02:07,  1.44it/s]
1|20531|Loss: 0.8899418115615845:  79%|███████▉  | 20531/25880 [4:11:56<1:06:18,  1.34it/s]
1|20532|Loss: 0.7838824987411499:  79%|███████▉  | 20531/25880 [4:11:56<1:06:18,  1.34it/s]
1|20532|Loss: 0.7838824987411499:  79%|███████▉  | 20532/25880 [4:11:57<1:06:50,  1.33it/s]
1|20533|Loss: 1.0459672212600708:  79%|███████▉  | 20532/25880 [4:11:57<1:06:50,  1.33it/s]
1|20533|Loss: 1.0459672212600708:  79%|███████▉  | 20533/25880 [4:11:57<1:02:32,  1.42it/s]
1|20534|Loss: 0.8848865032196045:  79%|███████▉  | 20533/25880 [4:11:58<1:02:32,  1.42it/s]
1|20534|Loss: 0.8848865032196045:  79%|███████▉  | 20534/25880 [4:11:58<59:23,  1.50it/s]  
1|20535|Loss: 0.7580259442329407:  79%|███████▉  | 20534/25880 [4:11:58<59:23,  1.50it/s]
1|20535|Loss: 0.7580259442329407:  79%|███████▉  | 20535/25880 [4:11:59<59:43,  1.49it/s]
1|20536|Loss: 0.6638522148132324:  79%|███████▉  | 20535/25880 [4:11:59<59:43,  1.49it/s]
1|20536|Loss: 0.6638522148132324:  79%|███████▉  | 20536/25880 [4:11:59<1:04:23,  1.38it/s]
1|20537|Loss: 0.8389918804168701:  79%|███████▉  | 20536/25880 [4:12:00<1:04:23,  1.38it/s]
1|20537|Loss: 0.8389918804168701:  79%|███████▉  | 20537/25880 [4:12:00<1:08:47,  1.29it/s]
1|20538|Loss: 0.9582219123840332:  79%|███████▉  | 20537/25880 [4:12:01<1:08:47,  1.29it/s]
1|20538|Loss: 0.9582219123840332:  79%|███████▉  | 20538/25880 [4:12:01<1:06:12,  1.34it/s]
1|20539|Loss: 0.8838366270065308:  79%|███████▉  | 20538/25880 [4:12:01<1:06:12,  1.34it/s]
1|20539|Loss: 0.8838366270065308:  79%|███████▉  | 20539/25880 [4:12:02<1:04:40,  1.38it/s]
1|20540|Loss: 0.9443677663803101:  79%|███████▉  | 20539/25880 [4:12:02<1:04:40,  1.38it/s]
1|20540|Loss: 0.9443677663803101:  79%|███████▉  | 20540/25880 [4:12:03<1:08:41,  1.30it/s]
1|20541|Loss: 0.873497724533081:  79%|███████▉  | 20540/25880 [4:12:03<1:08:41,  1.30it/s] 
1|20541|Loss: 0.873497724533081:  79%|███████▉  | 20541/25880 [4:12:03<1:08:11,  1.30it/s]
1|20542|Loss: 0.7364462018013:  79%|███████▉  | 20541/25880 [4:12:04<1:08:11,  1.30it/s]  
1|20542|Loss: 0.7364462018013:  79%|███████▉  | 20542/25880 [4:12:04<1:08:49,  1.29it/s]
1|20543|Loss: 0.8637385368347168:  79%|███████▉  | 20542/25880 [4:12:04<1:08:49,  1.29it/s]
1|20543|Loss: 0.8637385368347168:  79%|███████▉  | 20543/25880 [4:12:05<1:07:20,  1.32it/s]
1|20544|Loss: 0.7888236045837402:  79%|███████▉  | 20543/25880 [4:12:05<1:07:20,  1.32it/s]
1|20544|Loss: 0.7888236045837402:  79%|███████▉  | 20544/25880 [4:12:06<1:06:44,  1.33it/s]
1|20545|Loss: 0.7835962176322937:  79%|███████▉  | 20544/25880 [4:12:06<1:06:44,  1.33it/s]
1|20545|Loss: 0.7835962176322937:  79%|███████▉  | 20545/25880 [4:12:06<1:06:40,  1.33it/s]
1|20546|Loss: 0.9328959584236145:  79%|███████▉  | 20545/25880 [4:12:07<1:06:40,  1.33it/s]
1|20546|Loss: 0.9328959584236145:  79%|███████▉  | 20546/25880 [4:12:07<1:06:35,  1.34it/s]
1|20547|Loss: 0.7672016024589539:  79%|███████▉  | 20546/25880 [4:12:07<1:06:35,  1.34it/s]
1|20547|Loss: 0.7672016024589539:  79%|███████▉  | 20547/25880 [4:12:08<1:06:39,  1.33it/s]
1|20548|Loss: 0.7751032710075378:  79%|███████▉  | 20547/25880 [4:12:08<1:06:39,  1.33it/s]
1|20548|Loss: 0.7751032710075378:  79%|███████▉  | 20548/25880 [4:12:09<1:08:47,  1.29it/s]
1|20549|Loss: 0.8327922224998474:  79%|███████▉  | 20548/25880 [4:12:09<1:08:47,  1.29it/s]
1|20549|Loss: 0.8327922224998474:  79%|███████▉  | 20549/25880 [4:12:09<1:09:56,  1.27it/s]
1|20550|Loss: 0.8230457305908203:  79%|███████▉  | 20549/25880 [4:12:10<1:09:56,  1.27it/s]
1|20550|Loss: 0.8230457305908203:  79%|███████▉  | 20550/25880 [4:12:10<1:09:02,  1.29it/s]
1|20551|Loss: 0.8295705914497375:  79%|███████▉  | 20550/25880 [4:12:11<1:09:02,  1.29it/s]
1|20551|Loss: 0.8295705914497375:  79%|███████▉  | 20551/25880 [4:12:11<1:06:12,  1.34it/s]
1|20552|Loss: 0.7844271063804626:  79%|███████▉  | 20551/25880 [4:12:11<1:06:12,  1.34it/s]
1|20552|Loss: 0.7844271063804626:  79%|███████▉  | 20552/25880 [4:12:11<1:02:56,  1.41it/s]
1|20553|Loss: 0.8849524259567261:  79%|███████▉  | 20552/25880 [4:12:12<1:02:56,  1.41it/s]
1|20553|Loss: 0.8849524259567261:  79%|███████▉  | 20553/25880 [4:12:12<1:04:12,  1.38it/s]
1|20554|Loss: 0.8549824953079224:  79%|███████▉  | 20553/25880 [4:12:13<1:04:12,  1.38it/s]
1|20554|Loss: 0.8549824953079224:  79%|███████▉  | 20554/25880 [4:12:13<1:00:09,  1.48it/s]
1|20555|Loss: 0.8297608494758606:  79%|███████▉  | 20554/25880 [4:12:13<1:00:09,  1.48it/s]
1|20555|Loss: 0.8297608494758606:  79%|███████▉  | 20555/25880 [4:12:13<1:00:21,  1.47it/s]
1|20556|Loss: 0.9071580171585083:  79%|███████▉  | 20555/25880 [4:12:14<1:00:21,  1.47it/s]
1|20556|Loss: 0.9071580171585083:  79%|███████▉  | 20556/25880 [4:12:14<1:03:18,  1.40it/s]
1|20557|Loss: 0.8851853609085083:  79%|███████▉  | 20556/25880 [4:12:15<1:03:18,  1.40it/s]
1|20557|Loss: 0.8851853609085083:  79%|███████▉  | 20557/25880 [4:12:15<1:05:25,  1.36it/s]
1|20558|Loss: 0.8045069575309753:  79%|███████▉  | 20557/25880 [4:12:15<1:05:25,  1.36it/s]
1|20558|Loss: 0.8045069575309753:  79%|███████▉  | 20558/25880 [4:12:16<1:05:07,  1.36it/s]
1|20559|Loss: 0.9660459160804749:  79%|███████▉  | 20558/25880 [4:12:16<1:05:07,  1.36it/s]
1|20559|Loss: 0.9660459160804749:  79%|███████▉  | 20559/25880 [4:12:17<1:07:36,  1.31it/s]
1|20560|Loss: 0.7921268343925476:  79%|███████▉  | 20559/25880 [4:12:17<1:07:36,  1.31it/s]
1|20560|Loss: 0.7921268343925476:  79%|███████▉  | 20560/25880 [4:12:18<1:11:30,  1.24it/s]
1|20561|Loss: 0.8182049989700317:  79%|███████▉  | 20560/25880 [4:12:18<1:11:30,  1.24it/s]
1|20561|Loss: 0.8182049989700317:  79%|███████▉  | 20561/25880 [4:12:18<1:14:21,  1.19it/s]
1|20562|Loss: 0.8435397744178772:  79%|███████▉  | 20561/25880 [4:12:19<1:14:21,  1.19it/s]
1|20562|Loss: 0.8435397744178772:  79%|███████▉  | 20562/25880 [4:12:19<1:14:40,  1.19it/s]
1|20563|Loss: 0.8554283976554871:  79%|███████▉  | 20562/25880 [4:12:20<1:14:40,  1.19it/s]
1|20563|Loss: 0.8554283976554871:  79%|███████▉  | 20563/25880 [4:12:20<1:10:32,  1.26it/s]
1|20564|Loss: 0.9053789377212524:  79%|███████▉  | 20563/25880 [4:12:20<1:10:32,  1.26it/s]
1|20564|Loss: 0.9053789377212524:  79%|███████▉  | 20564/25880 [4:12:21<1:04:05,  1.38it/s]
1|20565|Loss: 0.7836909890174866:  79%|███████▉  | 20564/25880 [4:12:21<1:04:05,  1.38it/s]
1|20565|Loss: 0.7836909890174866:  79%|███████▉  | 20565/25880 [4:12:21<1:05:19,  1.36it/s]
1|20566|Loss: 0.7754930853843689:  79%|███████▉  | 20565/25880 [4:12:22<1:05:19,  1.36it/s]
1|20566|Loss: 0.7754930853843689:  79%|███████▉  | 20566/25880 [4:12:22<1:01:53,  1.43it/s]
1|20567|Loss: 0.8488838076591492:  79%|███████▉  | 20566/25880 [4:12:22<1:01:53,  1.43it/s]
1|20567|Loss: 0.8488838076591492:  79%|███████▉  | 20567/25880 [4:12:23<59:44,  1.48it/s]  
1|20568|Loss: 0.8196856379508972:  79%|███████▉  | 20567/25880 [4:12:23<59:44,  1.48it/s]
1|20568|Loss: 0.8196856379508972:  79%|███████▉  | 20568/25880 [4:12:23<1:03:05,  1.40it/s]
1|20569|Loss: 0.6946054100990295:  79%|███████▉  | 20568/25880 [4:12:24<1:03:05,  1.40it/s]
1|20569|Loss: 0.6946054100990295:  79%|███████▉  | 20569/25880 [4:12:24<1:06:58,  1.32it/s]
1|20570|Loss: 0.7860917448997498:  79%|███████▉  | 20569/25880 [4:12:25<1:06:58,  1.32it/s]
1|20570|Loss: 0.7860917448997498:  79%|███████▉  | 20570/25880 [4:12:25<1:04:51,  1.36it/s]
1|20571|Loss: 0.7485862374305725:  79%|███████▉  | 20570/25880 [4:12:25<1:04:51,  1.36it/s]
1|20571|Loss: 0.7485862374305725:  79%|███████▉  | 20571/25880 [4:12:26<1:08:14,  1.30it/s]
1|20572|Loss: 0.8943356871604919:  79%|███████▉  | 20571/25880 [4:12:26<1:08:14,  1.30it/s]
1|20572|Loss: 0.8943356871604919:  79%|███████▉  | 20572/25880 [4:12:27<1:08:25,  1.29it/s]
1|20573|Loss: 0.8554142117500305:  79%|███████▉  | 20572/25880 [4:12:27<1:08:25,  1.29it/s]
1|20573|Loss: 0.8554142117500305:  79%|███████▉  | 20573/25880 [4:12:27<1:05:39,  1.35it/s]
1|20574|Loss: 0.9134590029716492:  79%|███████▉  | 20573/25880 [4:12:28<1:05:39,  1.35it/s]
1|20574|Loss: 0.9134590029716492:  79%|███████▉  | 20574/25880 [4:12:28<1:04:17,  1.38it/s]
1|20575|Loss: 0.8930570483207703:  79%|███████▉  | 20574/25880 [4:12:28<1:04:17,  1.38it/s]
1|20575|Loss: 0.8930570483207703:  80%|███████▉  | 20575/25880 [4:12:28<1:01:04,  1.45it/s]
1|20576|Loss: 0.8902994990348816:  80%|███████▉  | 20575/25880 [4:12:29<1:01:04,  1.45it/s]
1|20576|Loss: 0.8902994990348816:  80%|███████▉  | 20576/25880 [4:12:29<1:01:42,  1.43it/s]
1|20577|Loss: 0.794662356376648:  80%|███████▉  | 20576/25880 [4:12:30<1:01:42,  1.43it/s] 
1|20577|Loss: 0.794662356376648:  80%|███████▉  | 20577/25880 [4:12:30<1:02:12,  1.42it/s]
1|20578|Loss: 0.8781559467315674:  80%|███████▉  | 20577/25880 [4:12:30<1:02:12,  1.42it/s]
1|20578|Loss: 0.8781559467315674:  80%|███████▉  | 20578/25880 [4:12:31<1:03:59,  1.38it/s]
1|20579|Loss: 0.8285617828369141:  80%|███████▉  | 20578/25880 [4:12:31<1:03:59,  1.38it/s]
1|20579|Loss: 0.8285617828369141:  80%|███████▉  | 20579/25880 [4:12:31<1:02:04,  1.42it/s]
1|20580|Loss: 0.8268019556999207:  80%|███████▉  | 20579/25880 [4:12:32<1:02:04,  1.42it/s]
1|20580|Loss: 0.8268019556999207:  80%|███████▉  | 20580/25880 [4:12:32<1:04:18,  1.37it/s]
1|20581|Loss: 0.7740439772605896:  80%|███████▉  | 20580/25880 [4:12:33<1:04:18,  1.37it/s]
1|20581|Loss: 0.7740439772605896:  80%|███████▉  | 20581/25880 [4:12:33<1:07:45,  1.30it/s]
1|20582|Loss: 0.6536628007888794:  80%|███████▉  | 20581/25880 [4:12:33<1:07:45,  1.30it/s]
1|20582|Loss: 0.6536628007888794:  80%|███████▉  | 20582/25880 [4:12:34<1:07:42,  1.30it/s]
1|20583|Loss: 0.6296400427818298:  80%|███████▉  | 20582/25880 [4:12:34<1:07:42,  1.30it/s]
1|20583|Loss: 0.6296400427818298:  80%|███████▉  | 20583/25880 [4:12:35<1:08:16,  1.29it/s]
1|20584|Loss: 0.8712262511253357:  80%|███████▉  | 20583/25880 [4:12:35<1:08:16,  1.29it/s]
1|20584|Loss: 0.8712262511253357:  80%|███████▉  | 20584/25880 [4:12:35<1:08:37,  1.29it/s]
1|20585|Loss: 0.7485443949699402:  80%|███████▉  | 20584/25880 [4:12:36<1:08:37,  1.29it/s]
1|20585|Loss: 0.7485443949699402:  80%|███████▉  | 20585/25880 [4:12:36<1:09:50,  1.26it/s]
1|20586|Loss: 0.9636446237564087:  80%|███████▉  | 20585/25880 [4:12:37<1:09:50,  1.26it/s]
1|20586|Loss: 0.9636446237564087:  80%|███████▉  | 20586/25880 [4:12:37<1:08:39,  1.29it/s]
1|20587|Loss: 0.8411800265312195:  80%|███████▉  | 20586/25880 [4:12:37<1:08:39,  1.29it/s]
1|20587|Loss: 0.8411800265312195:  80%|███████▉  | 20587/25880 [4:12:38<1:07:16,  1.31it/s]
1|20588|Loss: 0.807732880115509:  80%|███████▉  | 20587/25880 [4:12:38<1:07:16,  1.31it/s] 
1|20588|Loss: 0.807732880115509:  80%|███████▉  | 20588/25880 [4:12:38<1:06:35,  1.32it/s]
1|20589|Loss: 0.7793790698051453:  80%|███████▉  | 20588/25880 [4:12:39<1:06:35,  1.32it/s]
1|20589|Loss: 0.7793790698051453:  80%|███████▉  | 20589/25880 [4:12:39<1:08:44,  1.28it/s]
1|20590|Loss: 0.8900471329689026:  80%|███████▉  | 20589/25880 [4:12:40<1:08:44,  1.28it/s]
1|20590|Loss: 0.8900471329689026:  80%|███████▉  | 20590/25880 [4:12:40<1:08:11,  1.29it/s]
1|20591|Loss: 0.7645833492279053:  80%|███████▉  | 20590/25880 [4:12:40<1:08:11,  1.29it/s]
1|20591|Loss: 0.7645833492279053:  80%|███████▉  | 20591/25880 [4:12:41<1:11:52,  1.23it/s]
1|20592|Loss: 0.6844353675842285:  80%|███████▉  | 20591/25880 [4:12:41<1:11:52,  1.23it/s]
1|20592|Loss: 0.6844353675842285:  80%|███████▉  | 20592/25880 [4:12:42<1:10:56,  1.24it/s]
1|20593|Loss: 0.7306749820709229:  80%|███████▉  | 20592/25880 [4:12:42<1:10:56,  1.24it/s]
1|20593|Loss: 0.7306749820709229:  80%|███████▉  | 20593/25880 [4:12:42<1:09:25,  1.27it/s]
1|20594|Loss: 0.7685803174972534:  80%|███████▉  | 20593/25880 [4:12:43<1:09:25,  1.27it/s]
1|20594|Loss: 0.7685803174972534:  80%|███████▉  | 20594/25880 [4:12:43<1:10:17,  1.25it/s]
1|20595|Loss: 0.8578124642372131:  80%|███████▉  | 20594/25880 [4:12:44<1:10:17,  1.25it/s]
1|20595|Loss: 0.8578124642372131:  80%|███████▉  | 20595/25880 [4:12:44<1:11:11,  1.24it/s]
1|20596|Loss: 1.0409108400344849:  80%|███████▉  | 20595/25880 [4:12:45<1:11:11,  1.24it/s]
1|20596|Loss: 1.0409108400344849:  80%|███████▉  | 20596/25880 [4:12:45<1:12:28,  1.22it/s]
1|20597|Loss: 0.7391653656959534:  80%|███████▉  | 20596/25880 [4:12:45<1:12:28,  1.22it/s]
1|20597|Loss: 0.7391653656959534:  80%|███████▉  | 20597/25880 [4:12:46<1:12:03,  1.22it/s]
1|20598|Loss: 0.773362934589386:  80%|███████▉  | 20597/25880 [4:12:46<1:12:03,  1.22it/s] 
1|20598|Loss: 0.773362934589386:  80%|███████▉  | 20598/25880 [4:12:46<1:09:34,  1.27it/s]
1|20599|Loss: 0.9024061560630798:  80%|███████▉  | 20598/25880 [4:12:47<1:09:34,  1.27it/s]
1|20599|Loss: 0.9024061560630798:  80%|███████▉  | 20599/25880 [4:12:47<1:08:06,  1.29it/s]
1|20600|Loss: 0.847446620464325:  80%|███████▉  | 20599/25880 [4:12:48<1:08:06,  1.29it/s] 
1|20600|Loss: 0.847446620464325:  80%|███████▉  | 20600/25880 [4:12:48<1:07:14,  1.31it/s]
1|20601|Loss: 0.8625860214233398:  80%|███████▉  | 20600/25880 [4:12:48<1:07:14,  1.31it/s]
1|20601|Loss: 0.8625860214233398:  80%|███████▉  | 20601/25880 [4:12:49<1:06:47,  1.32it/s]
1|20602|Loss: 0.7731573581695557:  80%|███████▉  | 20601/25880 [4:12:49<1:06:47,  1.32it/s]
1|20602|Loss: 0.7731573581695557:  80%|███████▉  | 20602/25880 [4:12:49<1:04:00,  1.37it/s]
1|20603|Loss: 0.817649245262146:  80%|███████▉  | 20602/25880 [4:12:50<1:04:00,  1.37it/s] 
1|20603|Loss: 0.817649245262146:  80%|███████▉  | 20603/25880 [4:12:50<1:01:41,  1.43it/s]
1|20604|Loss: 0.8874857425689697:  80%|███████▉  | 20603/25880 [4:12:50<1:01:41,  1.43it/s]
1|20604|Loss: 0.8874857425689697:  80%|███████▉  | 20604/25880 [4:12:51<1:01:44,  1.42it/s]
1|20605|Loss: 0.8980743288993835:  80%|███████▉  | 20604/25880 [4:12:51<1:01:44,  1.42it/s]
1|20605|Loss: 0.8980743288993835:  80%|███████▉  | 20605/25880 [4:12:51<1:00:24,  1.46it/s]
1|20606|Loss: 0.8988310694694519:  80%|███████▉  | 20605/25880 [4:12:52<1:00:24,  1.46it/s]
1|20606|Loss: 0.8988310694694519:  80%|███████▉  | 20606/25880 [4:12:52<1:01:07,  1.44it/s]
1|20607|Loss: 0.7839475870132446:  80%|███████▉  | 20606/25880 [4:12:52<1:01:07,  1.44it/s]
1|20607|Loss: 0.7839475870132446:  80%|███████▉  | 20607/25880 [4:12:53<59:41,  1.47it/s]  
1|20608|Loss: 0.9528412818908691:  80%|███████▉  | 20607/25880 [4:12:53<59:41,  1.47it/s]
1|20608|Loss: 0.9528412818908691:  80%|███████▉  | 20608/25880 [4:12:53<57:34,  1.53it/s]
1|20609|Loss: 0.8006263971328735:  80%|███████▉  | 20608/25880 [4:12:54<57:34,  1.53it/s]
1|20609|Loss: 0.8006263971328735:  80%|███████▉  | 20609/25880 [4:12:54<56:50,  1.55it/s]
1|20610|Loss: 0.9049683213233948:  80%|███████▉  | 20609/25880 [4:12:54<56:50,  1.55it/s]
1|20610|Loss: 0.9049683213233948:  80%|███████▉  | 20610/25880 [4:12:55<56:36,  1.55it/s]
1|20611|Loss: 0.7500772476196289:  80%|███████▉  | 20610/25880 [4:12:55<56:36,  1.55it/s]
1|20611|Loss: 0.7500772476196289:  80%|███████▉  | 20611/25880 [4:12:55<1:02:27,  1.41it/s]
1|20612|Loss: 0.7360665798187256:  80%|███████▉  | 20611/25880 [4:12:56<1:02:27,  1.41it/s]
1|20612|Loss: 0.7360665798187256:  80%|███████▉  | 20612/25880 [4:12:56<1:08:52,  1.27it/s]
1|20613|Loss: 0.8789548277854919:  80%|███████▉  | 20612/25880 [4:12:57<1:08:52,  1.27it/s]
1|20613|Loss: 0.8789548277854919:  80%|███████▉  | 20613/25880 [4:12:57<1:11:20,  1.23it/s]
1|20614|Loss: 0.8247721791267395:  80%|███████▉  | 20613/25880 [4:12:58<1:11:20,  1.23it/s]
1|20614|Loss: 0.8247721791267395:  80%|███████▉  | 20614/25880 [4:12:58<1:08:11,  1.29it/s]
1|20615|Loss: 1.0088762044906616:  80%|███████▉  | 20614/25880 [4:12:58<1:08:11,  1.29it/s]
1|20615|Loss: 1.0088762044906616:  80%|███████▉  | 20615/25880 [4:12:59<1:06:02,  1.33it/s]
1|20616|Loss: 0.9061118364334106:  80%|███████▉  | 20615/25880 [4:12:59<1:06:02,  1.33it/s]
1|20616|Loss: 0.9061118364334106:  80%|███████▉  | 20616/25880 [4:12:59<1:07:39,  1.30it/s]
1|20617|Loss: 0.880851149559021:  80%|███████▉  | 20616/25880 [4:13:00<1:07:39,  1.30it/s] 
1|20617|Loss: 0.880851149559021:  80%|███████▉  | 20617/25880 [4:13:00<1:07:07,  1.31it/s]
1|20618|Loss: 0.7581713795661926:  80%|███████▉  | 20617/25880 [4:13:01<1:07:07,  1.31it/s]
1|20618|Loss: 0.7581713795661926:  80%|███████▉  | 20618/25880 [4:13:01<1:06:06,  1.33it/s]
1|20619|Loss: 0.9217736721038818:  80%|███████▉  | 20618/25880 [4:13:01<1:06:06,  1.33it/s]
1|20619|Loss: 0.9217736721038818:  80%|███████▉  | 20619/25880 [4:13:02<1:08:11,  1.29it/s]
1|20620|Loss: 0.8797601461410522:  80%|███████▉  | 20619/25880 [4:13:02<1:08:11,  1.29it/s]
1|20620|Loss: 0.8797601461410522:  80%|███████▉  | 20620/25880 [4:13:02<1:05:17,  1.34it/s]
1|20621|Loss: 0.7190015316009521:  80%|███████▉  | 20620/25880 [4:13:03<1:05:17,  1.34it/s]
1|20621|Loss: 0.7190015316009521:  80%|███████▉  | 20621/25880 [4:13:03<1:06:44,  1.31it/s]
1|20622|Loss: 0.9110569953918457:  80%|███████▉  | 20621/25880 [4:13:04<1:06:44,  1.31it/s]
1|20622|Loss: 0.9110569953918457:  80%|███████▉  | 20622/25880 [4:13:04<1:06:54,  1.31it/s]
1|20623|Loss: 0.8494697213172913:  80%|███████▉  | 20622/25880 [4:13:04<1:06:54,  1.31it/s]
1|20623|Loss: 0.8494697213172913:  80%|███████▉  | 20623/25880 [4:13:05<1:06:52,  1.31it/s]
1|20624|Loss: 0.8565889596939087:  80%|███████▉  | 20623/25880 [4:13:05<1:06:52,  1.31it/s]
1|20624|Loss: 0.8565889596939087:  80%|███████▉  | 20624/25880 [4:13:06<1:08:15,  1.28it/s]
1|20625|Loss: 0.844491183757782:  80%|███████▉  | 20624/25880 [4:13:06<1:08:15,  1.28it/s] 
1|20625|Loss: 0.844491183757782:  80%|███████▉  | 20625/25880 [4:13:06<1:07:36,  1.30it/s]
1|20626|Loss: 0.8134269714355469:  80%|███████▉  | 20625/25880 [4:13:07<1:07:36,  1.30it/s]
1|20626|Loss: 0.8134269714355469:  80%|███████▉  | 20626/25880 [4:13:07<1:08:40,  1.28it/s]
1|20627|Loss: 0.9536681771278381:  80%|███████▉  | 20626/25880 [4:13:08<1:08:40,  1.28it/s]
1|20627|Loss: 0.9536681771278381:  80%|███████▉  | 20627/25880 [4:13:08<1:05:44,  1.33it/s]
1|20628|Loss: 0.8724246025085449:  80%|███████▉  | 20627/25880 [4:13:08<1:05:44,  1.33it/s]
1|20628|Loss: 0.8724246025085449:  80%|███████▉  | 20628/25880 [4:13:09<1:04:00,  1.37it/s]
1|20629|Loss: 0.8890490531921387:  80%|███████▉  | 20628/25880 [4:13:09<1:04:00,  1.37it/s]
1|20629|Loss: 0.8890490531921387:  80%|███████▉  | 20629/25880 [4:13:09<1:03:02,  1.39it/s]
1|20630|Loss: 0.6996605396270752:  80%|███████▉  | 20629/25880 [4:13:10<1:03:02,  1.39it/s]
1|20630|Loss: 0.6996605396270752:  80%|███████▉  | 20630/25880 [4:13:10<57:07,  1.53it/s]  
1|20631|Loss: 0.7965366244316101:  80%|███████▉  | 20630/25880 [4:13:10<57:07,  1.53it/s]
1|20631|Loss: 0.7965366244316101:  80%|███████▉  | 20631/25880 [4:13:10<55:41,  1.57it/s]
1|20632|Loss: 0.8163225054740906:  80%|███████▉  | 20631/25880 [4:13:11<55:41,  1.57it/s]
1|20632|Loss: 0.8163225054740906:  80%|███████▉  | 20632/25880 [4:13:11<57:10,  1.53it/s]
1|20633|Loss: 0.9734115600585938:  80%|███████▉  | 20632/25880 [4:13:11<57:10,  1.53it/s]
1|20633|Loss: 0.9734115600585938:  80%|███████▉  | 20633/25880 [4:13:12<1:01:05,  1.43it/s]
1|20634|Loss: 0.7585151195526123:  80%|███████▉  | 20633/25880 [4:13:12<1:01:05,  1.43it/s]
1|20634|Loss: 0.7585151195526123:  80%|███████▉  | 20634/25880 [4:13:13<1:02:52,  1.39it/s]
1|20635|Loss: 0.8796120882034302:  80%|███████▉  | 20634/25880 [4:13:13<1:02:52,  1.39it/s]
1|20635|Loss: 0.8796120882034302:  80%|███████▉  | 20635/25880 [4:13:13<1:05:54,  1.33it/s]
1|20636|Loss: 0.7102668881416321:  80%|███████▉  | 20635/25880 [4:13:14<1:05:54,  1.33it/s]
1|20636|Loss: 0.7102668881416321:  80%|███████▉  | 20636/25880 [4:13:14<1:09:54,  1.25it/s]
1|20637|Loss: 0.7834904789924622:  80%|███████▉  | 20636/25880 [4:13:15<1:09:54,  1.25it/s]
1|20637|Loss: 0.7834904789924622:  80%|███████▉  | 20637/25880 [4:13:15<1:10:35,  1.24it/s]
1|20638|Loss: 0.9663422703742981:  80%|███████▉  | 20637/25880 [4:13:16<1:10:35,  1.24it/s]
1|20638|Loss: 0.9663422703742981:  80%|███████▉  | 20638/25880 [4:13:16<1:06:30,  1.31it/s]
1|20639|Loss: 0.7018669843673706:  80%|███████▉  | 20638/25880 [4:13:16<1:06:30,  1.31it/s]
1|20639|Loss: 0.7018669843673706:  80%|███████▉  | 20639/25880 [4:13:16<1:03:04,  1.38it/s]
1|20640|Loss: 0.8353101015090942:  80%|███████▉  | 20639/25880 [4:13:17<1:03:04,  1.38it/s]
1|20640|Loss: 0.8353101015090942:  80%|███████▉  | 20640/25880 [4:13:17<1:05:33,  1.33it/s]
1|20641|Loss: 0.8396158814430237:  80%|███████▉  | 20640/25880 [4:13:18<1:05:33,  1.33it/s]
1|20641|Loss: 0.8396158814430237:  80%|███████▉  | 20641/25880 [4:13:18<1:10:38,  1.24it/s]
1|20642|Loss: 0.7349240779876709:  80%|███████▉  | 20641/25880 [4:13:19<1:10:38,  1.24it/s]
1|20642|Loss: 0.7349240779876709:  80%|███████▉  | 20642/25880 [4:13:19<1:09:48,  1.25it/s]
1|20643|Loss: 1.125850796699524:  80%|███████▉  | 20642/25880 [4:13:19<1:09:48,  1.25it/s] 
1|20643|Loss: 1.125850796699524:  80%|███████▉  | 20643/25880 [4:13:19<1:02:57,  1.39it/s]
1|20644|Loss: 0.6769206523895264:  80%|███████▉  | 20643/25880 [4:13:20<1:02:57,  1.39it/s]
1|20644|Loss: 0.6769206523895264:  80%|███████▉  | 20644/25880 [4:13:20<1:01:18,  1.42it/s]
1|20645|Loss: 0.8273507952690125:  80%|███████▉  | 20644/25880 [4:13:21<1:01:18,  1.42it/s]
1|20645|Loss: 0.8273507952690125:  80%|███████▉  | 20645/25880 [4:13:21<59:26,  1.47it/s]  
1|20646|Loss: 0.7730178833007812:  80%|███████▉  | 20645/25880 [4:13:21<59:26,  1.47it/s]
1|20646|Loss: 0.7730178833007812:  80%|███████▉  | 20646/25880 [4:13:21<1:00:03,  1.45it/s]
1|20647|Loss: 0.8673081398010254:  80%|███████▉  | 20646/25880 [4:13:22<1:00:03,  1.45it/s]
1|20647|Loss: 0.8673081398010254:  80%|███████▉  | 20647/25880 [4:13:22<1:00:33,  1.44it/s]
1|20648|Loss: 0.7462371587753296:  80%|███████▉  | 20647/25880 [4:13:23<1:00:33,  1.44it/s]
1|20648|Loss: 0.7462371587753296:  80%|███████▉  | 20648/25880 [4:13:23<1:02:27,  1.40it/s]
1|20649|Loss: 0.750439465045929:  80%|███████▉  | 20648/25880 [4:13:23<1:02:27,  1.40it/s] 
1|20649|Loss: 0.750439465045929:  80%|███████▉  | 20649/25880 [4:13:24<58:04,  1.50it/s]  
1|20650|Loss: 0.8126169443130493:  80%|███████▉  | 20649/25880 [4:13:24<58:04,  1.50it/s]
1|20650|Loss: 0.8126169443130493:  80%|███████▉  | 20650/25880 [4:13:24<56:21,  1.55it/s]
1|20651|Loss: 0.8018056750297546:  80%|███████▉  | 20650/25880 [4:13:24<56:21,  1.55it/s]
1|20651|Loss: 0.8018056750297546:  80%|███████▉  | 20651/25880 [4:13:25<57:58,  1.50it/s]
1|20652|Loss: 0.8965951204299927:  80%|███████▉  | 20651/25880 [4:13:25<57:58,  1.50it/s]
1|20652|Loss: 0.8965951204299927:  80%|███████▉  | 20652/25880 [4:13:26<1:01:13,  1.42it/s]
1|20653|Loss: 0.8856522440910339:  80%|███████▉  | 20652/25880 [4:13:26<1:01:13,  1.42it/s]
1|20653|Loss: 0.8856522440910339:  80%|███████▉  | 20653/25880 [4:13:26<1:01:48,  1.41it/s]
1|20654|Loss: 1.0953867435455322:  80%|███████▉  | 20653/25880 [4:13:27<1:01:48,  1.41it/s]
1|20654|Loss: 1.0953867435455322:  80%|███████▉  | 20654/25880 [4:13:27<59:50,  1.46it/s]  
1|20655|Loss: 0.934104323387146:  80%|███████▉  | 20654/25880 [4:13:27<59:50,  1.46it/s] 
1|20655|Loss: 0.934104323387146:  80%|███████▉  | 20655/25880 [4:13:28<59:51,  1.45it/s]
1|20656|Loss: 0.8589888215065002:  80%|███████▉  | 20655/25880 [4:13:28<59:51,  1.45it/s]
1|20656|Loss: 0.8589888215065002:  80%|███████▉  | 20656/25880 [4:13:29<1:04:43,  1.35it/s]
1|20657|Loss: 0.8564847111701965:  80%|███████▉  | 20656/25880 [4:13:29<1:04:43,  1.35it/s]
1|20657|Loss: 0.8564847111701965:  80%|███████▉  | 20657/25880 [4:13:29<1:05:20,  1.33it/s]
1|20658|Loss: 0.892545759677887:  80%|███████▉  | 20657/25880 [4:13:30<1:05:20,  1.33it/s] 
1|20658|Loss: 0.892545759677887:  80%|███████▉  | 20658/25880 [4:13:30<1:08:02,  1.28it/s]
1|20659|Loss: 0.977530837059021:  80%|███████▉  | 20658/25880 [4:13:31<1:08:02,  1.28it/s]
1|20659|Loss: 0.977530837059021:  80%|███████▉  | 20659/25880 [4:13:31<1:05:44,  1.32it/s]
1|20660|Loss: 0.8068864345550537:  80%|███████▉  | 20659/25880 [4:13:31<1:05:44,  1.32it/s]
1|20660|Loss: 0.8068864345550537:  80%|███████▉  | 20660/25880 [4:13:32<1:07:54,  1.28it/s]
1|20661|Loss: 0.724179744720459:  80%|███████▉  | 20660/25880 [4:13:32<1:07:54,  1.28it/s] 
1|20661|Loss: 0.724179744720459:  80%|███████▉  | 20661/25880 [4:13:32<1:03:22,  1.37it/s]
1|20662|Loss: 0.7552306056022644:  80%|███████▉  | 20661/25880 [4:13:33<1:03:22,  1.37it/s]
1|20662|Loss: 0.7552306056022644:  80%|███████▉  | 20662/25880 [4:13:33<1:00:16,  1.44it/s]
1|20663|Loss: 0.7829157114028931:  80%|███████▉  | 20662/25880 [4:13:33<1:00:16,  1.44it/s]
1|20663|Loss: 0.7829157114028931:  80%|███████▉  | 20663/25880 [4:13:34<1:00:42,  1.43it/s]
1|20664|Loss: 0.8289878368377686:  80%|███████▉  | 20663/25880 [4:13:34<1:00:42,  1.43it/s]
1|20664|Loss: 0.8289878368377686:  80%|███████▉  | 20664/25880 [4:13:34<1:05:19,  1.33it/s]
1|20665|Loss: 0.8811954259872437:  80%|███████▉  | 20664/25880 [4:13:35<1:05:19,  1.33it/s]
1|20665|Loss: 0.8811954259872437:  80%|███████▉  | 20665/25880 [4:13:35<1:05:06,  1.33it/s]
1|20666|Loss: 0.7795625329017639:  80%|███████▉  | 20665/25880 [4:13:36<1:05:06,  1.33it/s]
1|20666|Loss: 0.7795625329017639:  80%|███████▉  | 20666/25880 [4:13:36<1:04:26,  1.35it/s]
1|20667|Loss: 1.0049012899398804:  80%|███████▉  | 20666/25880 [4:13:36<1:04:26,  1.35it/s]
1|20667|Loss: 1.0049012899398804:  80%|███████▉  | 20667/25880 [4:13:37<1:04:16,  1.35it/s]
1|20668|Loss: 0.8206365704536438:  80%|███████▉  | 20667/25880 [4:13:37<1:04:16,  1.35it/s]
1|20668|Loss: 0.8206365704536438:  80%|███████▉  | 20668/25880 [4:13:37<1:04:25,  1.35it/s]
1|20669|Loss: 0.7120508551597595:  80%|███████▉  | 20668/25880 [4:13:38<1:04:25,  1.35it/s]
1|20669|Loss: 0.7120508551597595:  80%|███████▉  | 20669/25880 [4:13:38<1:06:20,  1.31it/s]
1|20670|Loss: 0.7894371151924133:  80%|███████▉  | 20669/25880 [4:13:39<1:06:20,  1.31it/s]
1|20670|Loss: 0.7894371151924133:  80%|███████▉  | 20670/25880 [4:13:39<1:00:50,  1.43it/s]
1|20671|Loss: 0.7351331114768982:  80%|███████▉  | 20670/25880 [4:13:39<1:00:50,  1.43it/s]
1|20671|Loss: 0.7351331114768982:  80%|███████▉  | 20671/25880 [4:13:39<57:53,  1.50it/s]  
1|20672|Loss: 0.9153134822845459:  80%|███████▉  | 20671/25880 [4:13:40<57:53,  1.50it/s]
1|20672|Loss: 0.9153134822845459:  80%|███████▉  | 20672/25880 [4:13:40<1:00:08,  1.44it/s]
1|20673|Loss: 1.0060521364212036:  80%|███████▉  | 20672/25880 [4:13:41<1:00:08,  1.44it/s]
1|20673|Loss: 1.0060521364212036:  80%|███████▉  | 20673/25880 [4:13:41<57:49,  1.50it/s]  
1|20674|Loss: 0.8410627245903015:  80%|███████▉  | 20673/25880 [4:13:41<57:49,  1.50it/s]
1|20674|Loss: 0.8410627245903015:  80%|███████▉  | 20674/25880 [4:13:41<56:26,  1.54it/s]
1|20675|Loss: 0.7756622433662415:  80%|███████▉  | 20674/25880 [4:13:42<56:26,  1.54it/s]
1|20675|Loss: 0.7756622433662415:  80%|███████▉  | 20675/25880 [4:13:42<1:03:34,  1.36it/s]
1|20676|Loss: 0.7942090630531311:  80%|███████▉  | 20675/25880 [4:13:43<1:03:34,  1.36it/s]
1|20676|Loss: 0.7942090630531311:  80%|███████▉  | 20676/25880 [4:13:43<1:04:36,  1.34it/s]
1|20677|Loss: 0.7553364634513855:  80%|███████▉  | 20676/25880 [4:13:43<1:04:36,  1.34it/s]
1|20677|Loss: 0.7553364634513855:  80%|███████▉  | 20677/25880 [4:13:44<1:00:20,  1.44it/s]
1|20678|Loss: 0.8205757141113281:  80%|███████▉  | 20677/25880 [4:13:44<1:00:20,  1.44it/s]
1|20678|Loss: 0.8205757141113281:  80%|███████▉  | 20678/25880 [4:13:44<1:00:27,  1.43it/s]
1|20679|Loss: 0.8825298547744751:  80%|███████▉  | 20678/25880 [4:13:45<1:00:27,  1.43it/s]
1|20679|Loss: 0.8825298547744751:  80%|███████▉  | 20679/25880 [4:13:45<59:35,  1.45it/s]  
1|20680|Loss: 0.8027712106704712:  80%|███████▉  | 20679/25880 [4:13:45<59:35,  1.45it/s]
1|20680|Loss: 0.8027712106704712:  80%|███████▉  | 20680/25880 [4:13:46<1:01:29,  1.41it/s]
1|20681|Loss: 0.7494577169418335:  80%|███████▉  | 20680/25880 [4:13:46<1:01:29,  1.41it/s]
1|20681|Loss: 0.7494577169418335:  80%|███████▉  | 20681/25880 [4:13:46<1:00:00,  1.44it/s]
1|20682|Loss: 0.7436476349830627:  80%|███████▉  | 20681/25880 [4:13:47<1:00:00,  1.44it/s]
1|20682|Loss: 0.7436476349830627:  80%|███████▉  | 20682/25880 [4:13:47<58:33,  1.48it/s]  
1|20683|Loss: 0.8515920042991638:  80%|███████▉  | 20682/25880 [4:13:47<58:33,  1.48it/s]
1|20683|Loss: 0.8515920042991638:  80%|███████▉  | 20683/25880 [4:13:48<57:43,  1.50it/s]
1|20684|Loss: 0.9852272868156433:  80%|███████▉  | 20683/25880 [4:13:48<57:43,  1.50it/s]
1|20684|Loss: 0.9852272868156433:  80%|███████▉  | 20684/25880 [4:13:48<58:52,  1.47it/s]
1|20685|Loss: 0.9028015732765198:  80%|███████▉  | 20684/25880 [4:13:49<58:52,  1.47it/s]
1|20685|Loss: 0.9028015732765198:  80%|███████▉  | 20685/25880 [4:13:49<58:15,  1.49it/s]
1|20686|Loss: 0.8557759523391724:  80%|███████▉  | 20685/25880 [4:13:49<58:15,  1.49it/s]
1|20686|Loss: 0.8557759523391724:  80%|███████▉  | 20686/25880 [4:13:50<53:33,  1.62it/s]
1|20687|Loss: 0.8874101042747498:  80%|███████▉  | 20686/25880 [4:13:50<53:33,  1.62it/s]
1|20687|Loss: 0.8874101042747498:  80%|███████▉  | 20687/25880 [4:13:50<52:30,  1.65it/s]
1|20688|Loss: 0.8615396618843079:  80%|███████▉  | 20687/25880 [4:13:50<52:30,  1.65it/s]
1|20688|Loss: 0.8615396618843079:  80%|███████▉  | 20688/25880 [4:13:51<52:48,  1.64it/s]
1|20689|Loss: 0.9352521300315857:  80%|███████▉  | 20688/25880 [4:13:51<52:48,  1.64it/s]
1|20689|Loss: 0.9352521300315857:  80%|██████���▉  | 20689/25880 [4:13:52<57:29,  1.50it/s]
1|20690|Loss: 0.917513906955719:  80%|███████▉  | 20689/25880 [4:13:52<57:29,  1.50it/s] 
1|20690|Loss: 0.917513906955719:  80%|███████▉  | 20690/25880 [4:13:52<1:00:09,  1.44it/s]
1|20691|Loss: 0.862359344959259:  80%|███████▉  | 20690/25880 [4:13:53<1:00:09,  1.44it/s]
1|20691|Loss: 0.862359344959259:  80%|███████▉  | 20691/25880 [4:13:53<1:04:13,  1.35it/s]
1|20692|Loss: 0.8674654364585876:  80%|███████▉  | 20691/25880 [4:13:54<1:04:13,  1.35it/s]
1|20692|Loss: 0.8674654364585876:  80%|███████▉  | 20692/25880 [4:13:54<1:02:21,  1.39it/s]
1|20693|Loss: 0.8584524393081665:  80%|███████▉  | 20692/25880 [4:13:54<1:02:21,  1.39it/s]
1|20693|Loss: 0.8584524393081665:  80%|███████▉  | 20693/25880 [4:13:55<1:04:10,  1.35it/s]
1|20694|Loss: 0.9498205780982971:  80%|███████▉  | 20693/25880 [4:13:55<1:04:10,  1.35it/s]
1|20694|Loss: 0.9498205780982971:  80%|███████▉  | 20694/25880 [4:13:55<1:05:30,  1.32it/s]
1|20695|Loss: 0.9814960360527039:  80%|███████▉  | 20694/25880 [4:13:56<1:05:30,  1.32it/s]
1|20695|Loss: 0.9814960360527039:  80%|███████▉  | 20695/25880 [4:13:56<1:06:51,  1.29it/s]
1|20696|Loss: 0.8959670066833496:  80%|███████▉  | 20695/25880 [4:13:57<1:06:51,  1.29it/s]
1|20696|Loss: 0.8959670066833496:  80%|███████▉  | 20696/25880 [4:13:57<1:06:10,  1.31it/s]
1|20697|Loss: 0.8627015352249146:  80%|███████▉  | 20696/25880 [4:13:57<1:06:10,  1.31it/s]
1|20697|Loss: 0.8627015352249146:  80%|███████▉  | 20697/25880 [4:13:58<1:06:37,  1.30it/s]
1|20698|Loss: 0.8644172549247742:  80%|███████▉  | 20697/25880 [4:13:58<1:06:37,  1.30it/s]
1|20698|Loss: 0.8644172549247742:  80%|███████▉  | 20698/25880 [4:13:58<1:01:25,  1.41it/s]
1|20699|Loss: 0.8108118772506714:  80%|███████▉  | 20698/25880 [4:13:59<1:01:25,  1.41it/s]
1|20699|Loss: 0.8108118772506714:  80%|███████▉  | 20699/25880 [4:13:59<56:10,  1.54it/s]  
1|20700|Loss: 0.7594283223152161:  80%|███████▉  | 20699/25880 [4:13:59<56:10,  1.54it/s]
1|20700|Loss: 0.7594283223152161:  80%|███████▉  | 20700/25880 [4:13:59<51:14,  1.68it/s]
1|20701|Loss: 0.8365278244018555:  80%|███████▉  | 20700/25880 [4:14:00<51:14,  1.68it/s]
1|20701|Loss: 0.8365278244018555:  80%|███████▉  | 20701/25880 [4:14:00<55:56,  1.54it/s]
1|20702|Loss: 0.6506169438362122:  80%|███████▉  | 20701/25880 [4:14:01<55:56,  1.54it/s]
1|20702|Loss: 0.6506169438362122:  80%|███████▉  | 20702/25880 [4:14:01<59:18,  1.46it/s]
1|20703|Loss: 0.8990146517753601:  80%|███████▉  | 20702/25880 [4:14:01<59:18,  1.46it/s]
1|20703|Loss: 0.8990146517753601:  80%|███████▉  | 20703/25880 [4:14:02<1:00:05,  1.44it/s]
1|20704|Loss: 0.7309730052947998:  80%|███████▉  | 20703/25880 [4:14:02<1:00:05,  1.44it/s]
1|20704|Loss: 0.7309730052947998:  80%|████████  | 20704/25880 [4:14:02<1:00:57,  1.42it/s]
1|20705|Loss: 0.7681301832199097:  80%|████████  | 20704/25880 [4:14:03<1:00:57,  1.42it/s]
1|20705|Loss: 0.7681301832199097:  80%|████████  | 20705/25880 [4:14:03<1:01:58,  1.39it/s]
1|20706|Loss: 0.8664088249206543:  80%|████████  | 20705/25880 [4:14:03<1:01:58,  1.39it/s]
1|20706|Loss: 0.8664088249206543:  80%|████████  | 20706/25880 [4:14:04<1:03:43,  1.35it/s]
1|20707|Loss: 0.9435794949531555:  80%|████████  | 20706/25880 [4:14:04<1:03:43,  1.35it/s]
1|20707|Loss: 0.9435794949531555:  80%|████████  | 20707/25880 [4:14:05<1:05:40,  1.31it/s]
1|20708|Loss: 0.8599229454994202:  80%|████████  | 20707/25880 [4:14:05<1:05:40,  1.31it/s]
1|20708|Loss: 0.8599229454994202:  80%|████████  | 20708/25880 [4:14:05<1:04:44,  1.33it/s]
1|20709|Loss: 0.8800041079521179:  80%|████████  | 20708/25880 [4:14:06<1:04:44,  1.33it/s]
1|20709|Loss: 0.8800041079521179:  80%|████████  | 20709/25880 [4:14:06<1:03:38,  1.35it/s]
1|20710|Loss: 0.8418982028961182:  80%|████████  | 20709/25880 [4:14:06<1:03:38,  1.35it/s]
1|20710|Loss: 0.8418982028961182:  80%|████████  | 20710/25880 [4:14:07<1:02:49,  1.37it/s]
1|20711|Loss: 0.8016542196273804:  80%|████████  | 20710/25880 [4:14:07<1:02:49,  1.37it/s]
1|20711|Loss: 0.8016542196273804:  80%|████████  | 20711/25880 [4:14:08<1:02:54,  1.37it/s]
1|20712|Loss: 0.9042142033576965:  80%|████████  | 20711/25880 [4:14:08<1:02:54,  1.37it/s]
1|20712|Loss: 0.9042142033576965:  80%|████████  | 20712/25880 [4:14:08<1:02:43,  1.37it/s]
1|20713|Loss: 0.8290334939956665:  80%|████████  | 20712/25880 [4:14:09<1:02:43,  1.37it/s]
1|20713|Loss: 0.8290334939956665:  80%|████████  | 20713/25880 [4:14:09<1:04:52,  1.33it/s]
1|20714|Loss: 0.8210726380348206:  80%|████████  | 20713/25880 [4:14:09<1:04:52,  1.33it/s]
1|20714|Loss: 0.8210726380348206:  80%|████████  | 20714/25880 [4:14:10<1:01:12,  1.41it/s]
1|20715|Loss: 0.9180735349655151:  80%|████████  | 20714/25880 [4:14:10<1:01:12,  1.41it/s]
1|20715|Loss: 0.9180735349655151:  80%|████████  | 20715/25880 [4:14:10<58:47,  1.46it/s]  
1|20716|Loss: 0.8749853372573853:  80%|████████  | 20715/25880 [4:14:11<58:47,  1.46it/s]
1|20716|Loss: 0.8749853372573853:  80%|████████  | 20716/25880 [4:14:11<59:59,  1.43it/s]
1|20717|Loss: 0.8261191248893738:  80%|████████  | 20716/25880 [4:14:11<59:59,  1.43it/s]
1|20717|Loss: 0.8261191248893738:  80%|████████  | 20717/25880 [4:14:12<59:14,  1.45it/s]
1|20718|Loss: 0.8146364092826843:  80%|████████  | 20717/25880 [4:14:12<59:14,  1.45it/s]
1|20718|Loss: 0.8146364092826843:  80%|████████  | 20718/25880 [4:14:12<56:15,  1.53it/s]
1|20719|Loss: 0.7225776314735413:  80%|████████  | 20718/25880 [4:14:13<56:15,  1.53it/s]
1|20719|Loss: 0.7225776314735413:  80%|████████  | 20719/25880 [4:14:13<55:24,  1.55it/s]
1|20720|Loss: 0.8778592348098755:  80%|████████  | 20719/25880 [4:14:13<55:24,  1.55it/s]
1|20720|Loss: 0.8778592348098755:  80%|████████  | 20720/25880 [4:14:14<1:00:10,  1.43it/s]
1|20721|Loss: 0.7018243670463562:  80%|████████  | 20720/25880 [4:14:14<1:00:10,  1.43it/s]
1|20721|Loss: 0.7018243670463562:  80%|████████  | 20721/25880 [4:14:14<1:01:11,  1.41it/s]
1|20722|Loss: 0.7480754852294922:  80%|████████  | 20721/25880 [4:14:15<1:01:11,  1.41it/s]
1|20722|Loss: 0.7480754852294922:  80%|████████  | 20722/25880 [4:14:15<1:00:51,  1.41it/s]
1|20723|Loss: 0.7340273261070251:  80%|████████  | 20722/25880 [4:14:16<1:00:51,  1.41it/s]
1|20723|Loss: 0.7340273261070251:  80%|████████  | 20723/25880 [4:14:16<1:00:38,  1.42it/s]
1|20724|Loss: 0.8817873001098633:  80%|████████  | 20723/25880 [4:14:16<1:00:38,  1.42it/s]
1|20724|Loss: 0.8817873001098633:  80%|████████  | 20724/25880 [4:14:16<58:44,  1.46it/s]  
1|20725|Loss: 0.8594663739204407:  80%|████████  | 20724/25880 [4:14:17<58:44,  1.46it/s]
1|20725|Loss: 0.8594663739204407:  80%|████████  | 20725/25880 [4:14:17<59:20,  1.45it/s]
1|20726|Loss: 0.9084215760231018:  80%|████████  | 20725/25880 [4:14:18<59:20,  1.45it/s]
1|20726|Loss: 0.9084215760231018:  80%|████████  | 20726/25880 [4:14:18<1:05:09,  1.32it/s]
1|20727|Loss: 0.9421504735946655:  80%|████████  | 20726/25880 [4:14:19<1:05:09,  1.32it/s]
1|20727|Loss: 0.9421504735946655:  80%|████████  | 20727/25880 [4:14:19<1:08:56,  1.25it/s]
1|20728|Loss: 0.8916401863098145:  80%|████████  | 20727/25880 [4:14:19<1:08:56,  1.25it/s]
1|20728|Loss: 0.8916401863098145:  80%|████████  | 20728/25880 [4:14:20<1:08:11,  1.26it/s]
1|20729|Loss: 0.7329526543617249:  80%|████████  | 20728/25880 [4:14:20<1:08:11,  1.26it/s]
1|20729|Loss: 0.7329526543617249:  80%|████████  | 20729/25880 [4:14:20<1:00:59,  1.41it/s]
1|20730|Loss: 0.9418967366218567:  80%|████████  | 20729/25880 [4:14:21<1:00:59,  1.41it/s]
1|20730|Loss: 0.9418967366218567:  80%|████████  | 20730/25880 [4:14:21<1:02:18,  1.38it/s]
1|20731|Loss: 0.823001503944397:  80%|████████  | 20730/25880 [4:14:21<1:02:18,  1.38it/s] 
1|20731|Loss: 0.823001503944397:  80%|████████  | 20731/25880 [4:14:22<1:01:26,  1.40it/s]
1|20732|Loss: 0.8466348648071289:  80%|████████  | 20731/25880 [4:14:22<1:01:26,  1.40it/s]
1|20732|Loss: 0.8466348648071289:  80%|████████  | 20732/25880 [4:14:22<1:00:49,  1.41it/s]
1|20733|Loss: 0.8756626844406128:  80%|████████  | 20732/25880 [4:14:23<1:00:49,  1.41it/s]
1|20733|Loss: 0.8756626844406128:  80%|████████  | 20733/25880 [4:14:23<58:45,  1.46it/s]  
1|20734|Loss: 0.8094607591629028:  80%|████████  | 20733/25880 [4:14:24<58:45,  1.46it/s]
1|20734|Loss: 0.8094607591629028:  80%|████████  | 20734/25880 [4:14:24<1:03:12,  1.36it/s]
1|20735|Loss: 0.908877432346344:  80%|████████  | 20734/25880 [4:14:24<1:03:12,  1.36it/s] 
1|20735|Loss: 0.908877432346344:  80%|████████  | 20735/25880 [4:14:25<1:06:04,  1.30it/s]
1|20736|Loss: 0.7534151077270508:  80%|████████  | 20735/25880 [4:14:25<1:06:04,  1.30it/s]
1|20736|Loss: 0.7534151077270508:  80%|████████  | 20736/25880 [4:14:26<1:07:32,  1.27it/s]
1|20737|Loss: 0.9006831645965576:  80%|████████  | 20736/25880 [4:14:26<1:07:32,  1.27it/s]
1|20737|Loss: 0.9006831645965576:  80%|████████  | 20737/25880 [4:14:26<1:08:38,  1.25it/s]
1|20738|Loss: 0.6763861775398254:  80%|████████  | 20737/25880 [4:14:27<1:08:38,  1.25it/s]
1|20738|Loss: 0.6763861775398254:  80%|████████  | 20738/25880 [4:14:27<1:04:20,  1.33it/s]
1|20739|Loss: 0.8966547250747681:  80%|████████  | 20738/25880 [4:14:27<1:04:20,  1.33it/s]
1|20739|Loss: 0.8966547250747681:  80%|████████  | 20739/25880 [4:14:28<1:03:13,  1.36it/s]
1|20740|Loss: 0.8091005682945251:  80%|████████  | 20739/25880 [4:14:28<1:03:13,  1.36it/s]
1|20740|Loss: 0.8091005682945251:  80%|████████  | 20740/25880 [4:14:29<1:07:57,  1.26it/s]
1|20741|Loss: 1.0111498832702637:  80%|████████  | 20740/25880 [4:14:29<1:07:57,  1.26it/s]
1|20741|Loss: 1.0111498832702637:  80%|████████  | 20741/25880 [4:14:30<1:09:37,  1.23it/s]
1|20742|Loss: 0.8295353651046753:  80%|████████  | 20741/25880 [4:14:30<1:09:37,  1.23it/s]
1|20742|Loss: 0.8295353651046753:  80%|████████  | 20742/25880 [4:14:30<1:05:49,  1.30it/s]
1|20743|Loss: 0.8229387402534485:  80%|████████  | 20742/25880 [4:14:31<1:05:49,  1.30it/s]
1|20743|Loss: 0.8229387402534485:  80%|████████  | 20743/25880 [4:14:31<1:04:24,  1.33it/s]
1|20744|Loss: 0.9128792881965637:  80%|████████  | 20743/25880 [4:14:31<1:04:24,  1.33it/s]
1|20744|Loss: 0.9128792881965637:  80%|████████  | 20744/25880 [4:14:32<1:01:34,  1.39it/s]
1|20745|Loss: 0.8468329906463623:  80%|████████  | 20744/25880 [4:14:32<1:01:34,  1.39it/s]
1|20745|Loss: 0.8468329906463623:  80%|████████  | 20745/25880 [4:14:32<59:13,  1.45it/s]  
1|20746|Loss: 0.8037055134773254:  80%|████████  | 20745/25880 [4:14:33<59:13,  1.45it/s]
1|20746|Loss: 0.8037055134773254:  80%|████████  | 20746/25880 [4:14:33<59:09,  1.45it/s]
1|20747|Loss: 0.8292442560195923:  80%|████████  | 20746/25880 [4:14:33<59:09,  1.45it/s]
1|20747|Loss: 0.8292442560195923:  80%|████████  | 20747/25880 [4:14:34<1:00:21,  1.42it/s]
1|20748|Loss: 0.736160159111023:  80%|████████  | 20747/25880 [4:14:34<1:00:21,  1.42it/s] 
1|20748|Loss: 0.736160159111023:  80%|████████  | 20748/25880 [4:14:34<1:02:21,  1.37it/s]
1|20749|Loss: 0.71660977602005:  80%|████████  | 20748/25880 [4:14:35<1:02:21,  1.37it/s] 
1|20749|Loss: 0.71660977602005:  80%|████████  | 20749/25880 [4:14:35<1:05:07,  1.31it/s]
1|20750|Loss: 0.959757387638092:  80%|████████  | 20749/25880 [4:14:36<1:05:07,  1.31it/s]
1|20750|Loss: 0.959757387638092:  80%|████████  | 20750/25880 [4:14:36<1:08:19,  1.25it/s]
1|20751|Loss: 0.7922127842903137:  80%|████████  | 20750/25880 [4:14:37<1:08:19,  1.25it/s]
1|20751|Loss: 0.7922127842903137:  80%|████████  | 20751/25880 [4:14:37<1:03:31,  1.35it/s]
1|20752|Loss: 0.8652317523956299:  80%|████████  | 20751/25880 [4:14:37<1:03:31,  1.35it/s]
1|20752|Loss: 0.8652317523956299:  80%|████████  | 20752/25880 [4:14:37<59:40,  1.43it/s]  
1|20753|Loss: 0.8494196534156799:  80%|████████  | 20752/25880 [4:14:38<59:40,  1.43it/s]
1|20753|Loss: 0.8494196534156799:  80%|████████  | 20753/25880 [4:14:38<1:01:57,  1.38it/s]
1|20754|Loss: 0.913933515548706:  80%|████████  | 20753/25880 [4:14:39<1:01:57,  1.38it/s] 
1|20754|Loss: 0.913933515548706:  80%|████████  | 20754/25880 [4:14:39<1:06:32,  1.28it/s]
1|20755|Loss: 0.8189613223075867:  80%|████████  | 20754/25880 [4:14:40<1:06:32,  1.28it/s]
1|20755|Loss: 0.8189613223075867:  80%|████████  | 20755/25880 [4:14:40<1:08:20,  1.25it/s]
1|20756|Loss: 0.895207941532135:  80%|████████  | 20755/25880 [4:14:40<1:08:20,  1.25it/s] 
1|20756|Loss: 0.895207941532135:  80%|████████  | 20756/25880 [4:14:41<1:06:29,  1.28it/s]
1|20757|Loss: 0.9049167633056641:  80%|████████  | 20756/25880 [4:14:41<1:06:29,  1.28it/s]
1|20757|Loss: 0.9049167633056641:  80%|████████  | 20757/25880 [4:14:41<1:05:05,  1.31it/s]
1|20758|Loss: 0.8071869015693665:  80%|████████  | 20757/25880 [4:14:42<1:05:05,  1.31it/s]
1|20758|Loss: 0.8071869015693665:  80%|████████  | 20758/25880 [4:14:42<1:02:21,  1.37it/s]
1|20759|Loss: 0.7253011465072632:  80%|████████  | 20758/25880 [4:14:42<1:02:21,  1.37it/s]
1|20759|Loss: 0.7253011465072632:  80%|████████  | 20759/25880 [4:14:43<1:00:11,  1.42it/s]
1|20760|Loss: 0.8705282211303711:  80%|████████  | 20759/25880 [4:14:43<1:00:11,  1.42it/s]
1|20760|Loss: 0.8705282211303711:  80%|████████  | 20760/25880 [4:14:43<1:02:54,  1.36it/s]
1|20761|Loss: 0.866272509098053:  80%|���███████  | 20760/25880 [4:14:44<1:02:54,  1.36it/s] 
1|20761|Loss: 0.866272509098053:  80%|████████  | 20761/25880 [4:14:44<1:03:52,  1.34it/s]
1|20762|Loss: 0.8795588612556458:  80%|████████  | 20761/25880 [4:14:45<1:03:52,  1.34it/s]
1|20762|Loss: 0.8795588612556458:  80%|████████  | 20762/25880 [4:14:45<1:05:33,  1.30it/s]
1|20763|Loss: 0.7527770400047302:  80%|████████  | 20762/25880 [4:14:45<1:05:33,  1.30it/s]
1|20763|Loss: 0.7527770400047302:  80%|████████  | 20763/25880 [4:14:46<1:04:32,  1.32it/s]
1|20764|Loss: 0.7101699709892273:  80%|████████  | 20763/25880 [4:14:46<1:04:32,  1.32it/s]
1|20764|Loss: 0.7101699709892273:  80%|████████  | 20764/25880 [4:14:46<1:00:28,  1.41it/s]
1|20765|Loss: 0.8275176286697388:  80%|████████  | 20764/25880 [4:14:47<1:00:28,  1.41it/s]
1|20765|Loss: 0.8275176286697388:  80%|████████  | 20765/25880 [4:14:47<1:02:44,  1.36it/s]
1|20766|Loss: 0.8221145868301392:  80%|████████  | 20765/25880 [4:14:48<1:02:44,  1.36it/s]
1|20766|Loss: 0.8221145868301392:  80%|████████  | 20766/25880 [4:14:48<58:53,  1.45it/s]  
1|20767|Loss: 0.8624448776245117:  80%|████████  | 20766/25880 [4:14:48<58:53,  1.45it/s]
1|20767|Loss: 0.8624448776245117:  80%|████████  | 20767/25880 [4:14:48<58:39,  1.45it/s]
1|20768|Loss: 0.8398023843765259:  80%|████████  | 20767/25880 [4:14:49<58:39,  1.45it/s]
1|20768|Loss: 0.8398023843765259:  80%|████████  | 20768/25880 [4:14:49<59:04,  1.44it/s]
1|20769|Loss: 0.8448647856712341:  80%|████████  | 20768/25880 [4:14:50<59:04,  1.44it/s]
1|20769|Loss: 0.8448647856712341:  80%|████████  | 20769/25880 [4:14:50<59:53,  1.42it/s]
1|20770|Loss: 0.8287439346313477:  80%|████████  | 20769/25880 [4:14:50<59:53,  1.42it/s]
1|20770|Loss: 0.8287439346313477:  80%|████████  | 20770/25880 [4:14:51<58:17,  1.46it/s]
1|20771|Loss: 0.8328008055686951:  80%|████████  | 20770/25880 [4:14:51<58:17,  1.46it/s]
1|20771|Loss: 0.8328008055686951:  80%|████████  | 20771/25880 [4:14:51<58:51,  1.45it/s]
1|20772|Loss: 0.7763934135437012:  80%|████████  | 20771/25880 [4:14:52<58:51,  1.45it/s]
1|20772|Loss: 0.7763934135437012:  80%|████████  | 20772/25880 [4:14:52<56:48,  1.50it/s]
1|20773|Loss: 0.8972262144088745:  80%|████████  | 20772/25880 [4:14:52<56:48,  1.50it/s]
1|20773|Loss: 0.8972262144088745:  80%|████████  | 20773/25880 [4:14:53<57:03,  1.49it/s]
1|20774|Loss: 0.8150197267532349:  80%|████████  | 20773/25880 [4:14:53<57:03,  1.49it/s]
1|20774|Loss: 0.8150197267532349:  80%|████████  | 20774/25880 [4:14:53<59:34,  1.43it/s]
1|20775|Loss: 0.8287789821624756:  80%|████████  | 20774/25880 [4:14:54<59:34,  1.43it/s]
1|20775|Loss: 0.8287789821624756:  80%|████████  | 20775/25880 [4:14:54<1:02:44,  1.36it/s]
1|20776|Loss: 0.7475702166557312:  80%|████████  | 20775/25880 [4:14:55<1:02:44,  1.36it/s]
1|20776|Loss: 0.7475702166557312:  80%|████████  | 20776/25880 [4:14:55<1:04:30,  1.32it/s]
1|20777|Loss: 0.857454776763916:  80%|████████  | 20776/25880 [4:14:55<1:04:30,  1.32it/s] 
1|20777|Loss: 0.857454776763916:  80%|████████  | 20777/25880 [4:14:56<1:01:38,  1.38it/s]
1|20778|Loss: 0.8229911923408508:  80%|████████  | 20777/25880 [4:14:56<1:01:38,  1.38it/s]
1|20778|Loss: 0.8229911923408508:  80%|████████  | 20778/25880 [4:14:56<1:02:19,  1.36it/s]
1|20779|Loss: 0.8840490579605103:  80%|████████  | 20778/25880 [4:14:57<1:02:19,  1.36it/s]
1|20779|Loss: 0.8840490579605103:  80%|████████  | 20779/25880 [4:14:57<1:02:42,  1.36it/s]
1|20780|Loss: 0.8355453610420227:  80%|████████  | 20779/25880 [4:14:57<1:02:42,  1.36it/s]
1|20780|Loss: 0.8355453610420227:  80%|████████  | 20780/25880 [4:14:58<1:02:53,  1.35it/s]
1|20781|Loss: 0.7870327234268188:  80%|████████  | 20780/25880 [4:14:58<1:02:53,  1.35it/s]
1|20781|Loss: 0.7870327234268188:  80%|████████  | 20781/25880 [4:14:58<58:19,  1.46it/s]  
1|20782|Loss: 0.7874735593795776:  80%|████████  | 20781/25880 [4:14:59<58:19,  1.46it/s]
1|20782|Loss: 0.7874735593795776:  80%|████████  | 20782/25880 [4:14:59<1:00:11,  1.41it/s]
1|20783|Loss: 0.8399799466133118:  80%|████████  | 20782/25880 [4:15:00<1:00:11,  1.41it/s]
1|20783|Loss: 0.8399799466133118:  80%|████████  | 20783/25880 [4:15:00<1:01:14,  1.39it/s]
1|20784|Loss: 0.8247803449630737:  80%|████████  | 20783/25880 [4:15:00<1:01:14,  1.39it/s]
1|20784|Loss: 0.8247803449630737:  80%|████████  | 20784/25880 [4:15:01<1:01:22,  1.38it/s]
1|20785|Loss: 0.8695583343505859:  80%|████████  | 20784/25880 [4:15:01<1:01:22,  1.38it/s]
1|20785|Loss: 0.8695583343505859:  80%|████████  | 20785/25880 [4:15:01<1:03:03,  1.35it/s]
1|20786|Loss: 0.855705738067627:  80%|████████  | 20785/25880 [4:15:02<1:03:03,  1.35it/s] 
1|20786|Loss: 0.855705738067627:  80%|████████  | 20786/25880 [4:15:02<1:03:01,  1.35it/s]
1|20787|Loss: 0.9404675364494324:  80%|████████  | 20786/25880 [4:15:03<1:03:01,  1.35it/s]
1|20787|Loss: 0.9404675364494324:  80%|████████  | 20787/25880 [4:15:03<58:38,  1.45it/s]  
1|20788|Loss: 0.8625562191009521:  80%|████████  | 20787/25880 [4:15:03<58:38,  1.45it/s]
1|20788|Loss: 0.8625562191009521:  80%|████████  | 20788/25880 [4:15:03<56:15,  1.51it/s]
1|20789|Loss: 1.03316330909729:  80%|████████  | 20788/25880 [4:15:04<56:15,  1.51it/s]  
1|20789|Loss: 1.03316330909729:  80%|████████  | 20789/25880 [4:15:04<56:47,  1.49it/s]
1|20790|Loss: 0.9192978739738464:  80%|████████  | 20789/25880 [4:15:04<56:47,  1.49it/s]
1|20790|Loss: 0.9192978739738464:  80%|████████  | 20790/25880 [4:15:05<55:21,  1.53it/s]
1|20791|Loss: 0.8292959928512573:  80%|████████  | 20790/25880 [4:15:05<55:21,  1.53it/s]
1|20791|Loss: 0.8292959928512573:  80%|████████  | 20791/25880 [4:15:05<50:50,  1.67it/s]
1|20792|Loss: 0.7053135633468628:  80%|████████  | 20791/25880 [4:15:05<50:50,  1.67it/s]
1|20792|Loss: 0.7053135633468628:  80%|████████  | 20792/25880 [4:15:06<55:31,  1.53it/s]
1|20793|Loss: 0.8118155598640442:  80%|████████  | 20792/25880 [4:15:06<55:31,  1.53it/s]
1|20793|Loss: 0.8118155598640442:  80%|████████  | 20793/25880 [4:15:07<56:32,  1.50it/s]
1|20794|Loss: 0.7613135576248169:  80%|████████  | 20793/25880 [4:15:07<56:32,  1.50it/s]
1|20794|Loss: 0.7613135576248169:  80%|████████  | 20794/25880 [4:15:07<59:00,  1.44it/s]
1|20795|Loss: 0.837451696395874:  80%|████████  | 20794/25880 [4:15:08<59:00,  1.44it/s] 
1|20795|Loss: 0.837451696395874:  80%|████████  | 20795/25880 [4:15:08<58:31,  1.45it/s]
1|20796|Loss: 0.9256396293640137:  80%|████████  | 20795/25880 [4:15:08<58:31,  1.45it/s]
1|20796|Loss: 0.9256396293640137:  80%|████████  | 20796/25880 [4:15:09<53:32,  1.58it/s]
1|20797|Loss: 0.8091435432434082:  80%|████████  | 20796/25880 [4:15:09<53:32,  1.58it/s]
1|20797|Loss: 0.8091435432434082:  80%|████████  | 20797/25880 [4:15:09<54:25,  1.56it/s]
1|20798|Loss: 0.7218524217605591:  80%|████████  | 20797/25880 [4:15:10<54:25,  1.56it/s]
1|20798|Loss: 0.7218524217605591:  80%|████████  | 20798/25880 [4:15:10<52:57,  1.60it/s]
1|20799|Loss: 0.9248871803283691:  80%|████████  | 20798/25880 [4:15:10<52:57,  1.60it/s]
1|20799|Loss: 0.9248871803283691:  80%|████████  | 20799/25880 [4:15:10<54:37,  1.55it/s]
1|20800|Loss: 0.8474059104919434:  80%|████████  | 20799/25880 [4:15:11<54:37,  1.55it/s]
1|20800|Loss: 0.8474059104919434:  80%|████████  | 20800/25880 [4:15:11<57:55,  1.46it/s]
1|20801|Loss: 0.8333696126937866:  80%|████████  | 20800/25880 [4:15:12<57:55,  1.46it/s]
1|20801|Loss: 0.8333696126937866:  80%|████████  | 20801/25880 [4:15:12<57:08,  1.48it/s]
1|20802|Loss: 0.9274938702583313:  80%|████████  | 20801/25880 [4:15:12<57:08,  1.48it/s]
1|20802|Loss: 0.9274938702583313:  80%|████████  | 20802/25880 [4:15:13<58:05,  1.46it/s]
1|20803|Loss: 0.8231875896453857:  80%|████████  | 20802/25880 [4:15:13<58:05,  1.46it/s]
1|20803|Loss: 0.8231875896453857:  80%|████████  | 20803/25880 [4:15:13<58:42,  1.44it/s]
1|20804|Loss: 0.9207019209861755:  80%|████████  | 20803/25880 [4:15:14<58:42,  1.44it/s]
1|20804|Loss: 0.9207019209861755:  80%|████████  | 20804/25880 [4:15:14<1:01:34,  1.37it/s]
1|20805|Loss: 0.8809124827384949:  80%|████████  | 20804/25880 [4:15:15<1:01:34,  1.37it/s]
1|20805|Loss: 0.8809124827384949:  80%|████████  | 20805/25880 [4:15:15<1:03:18,  1.34it/s]
1|20806|Loss: 0.8061568737030029:  80%|████████  | 20805/25880 [4:15:15<1:03:18,  1.34it/s]
1|20806|Loss: 0.8061568737030029:  80%|████████  | 20806/25880 [4:15:16<1:01:04,  1.38it/s]
1|20807|Loss: 0.8025221228599548:  80%|████████  | 20806/25880 [4:15:16<1:01:04,  1.38it/s]
1|20807|Loss: 0.8025221228599548:  80%|████████  | 20807/25880 [4:15:16<1:03:06,  1.34it/s]
1|20808|Loss: 0.8740442991256714:  80%|████████  | 20807/25880 [4:15:17<1:03:06,  1.34it/s]
1|20808|Loss: 0.8740442991256714:  80%|████████  | 20808/25880 [4:15:17<1:01:09,  1.38it/s]
1|20809|Loss: 0.9204694628715515:  80%|████████  | 20808/25880 [4:15:17<1:01:09,  1.38it/s]
1|20809|Loss: 0.9204694628715515:  80%|████████  | 20809/25880 [4:15:18<1:01:56,  1.36it/s]
1|20810|Loss: 0.7547062039375305:  80%|████████  | 20809/25880 [4:15:18<1:01:56,  1.36it/s]
1|20810|Loss: 0.7547062039375305:  80%|████████  | 20810/25880 [4:15:19<1:04:41,  1.31it/s]
1|20811|Loss: 0.8130369186401367:  80%|████████  | 20810/25880 [4:15:19<1:04:41,  1.31it/s]
1|20811|Loss: 0.8130369186401367:  80%|████████  | 20811/25880 [4:15:19<1:04:00,  1.32it/s]
1|20812|Loss: 0.8300617337226868:  80%|████████  | 20811/25880 [4:15:20<1:04:00,  1.32it/s]
1|20812|Loss: 0.8300617337226868:  80%|████████  | 20812/25880 [4:15:20<1:04:11,  1.32it/s]
1|20813|Loss: 0.9811753630638123:  80%|████████  | 20812/25880 [4:15:21<1:04:11,  1.32it/s]
1|20813|Loss: 0.9811753630638123:  80%|████████  | 20813/25880 [4:15:21<1:05:19,  1.29it/s]
1|20814|Loss: 0.8295246958732605:  80%|████████  | 20813/25880 [4:15:21<1:05:19,  1.29it/s]
1|20814|Loss: 0.8295246958732605:  80%|████████  | 20814/25880 [4:15:22<1:04:55,  1.30it/s]
1|20815|Loss: 0.7019057869911194:  80%|████████  | 20814/25880 [4:15:22<1:04:55,  1.30it/s]
1|20815|Loss: 0.7019057869911194:  80%|████████  | 20815/25880 [4:15:23<1:05:26,  1.29it/s]
1|20816|Loss: 0.8546719551086426:  80%|████████  | 20815/25880 [4:15:23<1:05:26,  1.29it/s]
1|20816|Loss: 0.8546719551086426:  80%|████████  | 20816/25880 [4:15:23<1:07:05,  1.26it/s]
1|20817|Loss: 0.8262000679969788:  80%|████████  | 20816/25880 [4:15:24<1:07:05,  1.26it/s]
1|20817|Loss: 0.8262000679969788:  80%|████████  | 20817/25880 [4:15:24<1:10:07,  1.20it/s]
1|20818|Loss: 1.0284702777862549:  80%|████████  | 20817/25880 [4:15:25<1:10:07,  1.20it/s]
1|20818|Loss: 1.0284702777862549:  80%|████████  | 20818/25880 [4:15:25<1:08:42,  1.23it/s]
1|20819|Loss: 0.9969019293785095:  80%|████████  | 20818/25880 [4:15:25<1:08:42,  1.23it/s]
1|20819|Loss: 0.9969019293785095:  80%|████████  | 20819/25880 [4:15:26<1:06:45,  1.26it/s]
1|20820|Loss: 0.8360607624053955:  80%|████████  | 20819/25880 [4:15:26<1:06:45,  1.26it/s]
1|20820|Loss: 0.8360607624053955:  80%|████████  | 20820/25880 [4:15:26<1:02:47,  1.34it/s]
1|20821|Loss: 0.7680487036705017:  80%|████████  | 20820/25880 [4:15:27<1:02:47,  1.34it/s]
1|20821|Loss: 0.7680487036705017:  80%|████████  | 20821/25880 [4:15:27<1:03:42,  1.32it/s]
1|20822|Loss: 0.7993452548980713:  80%|████████  | 20821/25880 [4:15:28<1:03:42,  1.32it/s]
1|20822|Loss: 0.7993452548980713:  80%|████████  | 20822/25880 [4:15:28<1:01:39,  1.37it/s]
1|20823|Loss: 0.7978882789611816:  80%|████████  | 20822/25880 [4:15:28<1:01:39,  1.37it/s]
1|20823|Loss: 0.7978882789611816:  80%|████████  | 20823/25880 [4:15:29<1:01:12,  1.38it/s]
1|20824|Loss: 0.7258027195930481:  80%|████████  | 20823/25880 [4:15:29<1:01:12,  1.38it/s]
1|20824|Loss: 0.7258027195930481:  80%|████████  | 20824/25880 [4:15:29<58:18,  1.45it/s]  
1|20825|Loss: 0.9325333833694458:  80%|████████  | 20824/25880 [4:15:30<58:18,  1.45it/s]
1|20825|Loss: 0.9325333833694458:  80%|████████  | 20825/25880 [4:15:30<56:41,  1.49it/s]
1|20826|Loss: 0.8741902709007263:  80%|████████  | 20825/25880 [4:15:30<56:41,  1.49it/s]
1|20826|Loss: 0.8741902709007263:  80%|████████  | 20826/25880 [4:15:30<56:02,  1.50it/s]
1|20827|Loss: 0.8956124782562256:  80%|████████  | 20826/25880 [4:15:31<56:02,  1.50it/s]
1|20827|Loss: 0.8956124782562256:  80%|████████  | 20827/25880 [4:15:31<57:15,  1.47it/s]
1|20828|Loss: 0.860567569732666:  80%|████████  | 20827/25880 [4:15:32<57:15,  1.47it/s] 
1|20828|Loss: 0.860567569732666:  80%|████████  | 20828/25880 [4:15:32<1:00:38,  1.39it/s]
1|20829|Loss: 0.8240464329719543:  80%|████████  | 20828/25880 [4:15:32<1:00:38,  1.39it/s]
1|20829|Loss: 0.8240464329719543:  80%|████████  | 20829/25880 [4:15:33<1:03:39,  1.32it/s]
1|20830|Loss: 0.7311376333236694:  80%|████████  | 20829/25880 [4:15:33<1:03:39,  1.32it/s]
1|20830|Loss: 0.7311376333236694:  80%|████████  | 20830/25880 [4:15:34<1:01:37,  1.37it/s]
1|20831|Loss: 0.7722654342651367:  80%|████████  | 20830/25880 [4:15:34<1:01:37,  1.37it/s]
1|20831|Loss: 0.7722654342651367:  80%|████████  | 20831/25880 [4:15:34<1:04:55,  1.30it/s]
1|20832|Loss: 0.8358598947525024:  80%|████████  | 20831/25880 [4:15:35<1:04:55,  1.30it/s]
1|20832|Loss: 0.8358598947525024:  80%|████████  | 20832/25880 [4:15:35<1:01:55,  1.36it/s]
1|20833|Loss: 0.751563310623169:  80%|████████  | 20832/25880 [4:15:35<1:01:55,  1.36it/s] 
1|20833|Loss: 0.751563310623169:  80%|████████  | 20833/25880 [4:15:36<57:29,  1.46it/s]  
1|20834|Loss: 0.8231214880943298:  80%|████████  | 20833/25880 [4:15:36<57:29,  1.46it/s]
1|20834|Loss: 0.8231214880943298:  81%|████████  | 20834/25880 [4:15:36<55:01,  1.53it/s]
1|20835|Loss: 0.8473268151283264:  81%|████████  | 20834/25880 [4:15:37<55:01,  1.53it/s]
1|20835|Loss: 0.8473268151283264:  81%|████████  | 20835/25880 [4:15:37<56:26,  1.49it/s]
1|20836|Loss: 0.7563650012016296:  81%|████████  | 20835/25880 [4:15:37<56:26,  1.49it/s]
1|20836|Loss: 0.7563650012016296:  81%|████████  | 20836/25880 [4:15:38<58:24,  1.44it/s]
1|20837|Loss: 0.84382164478302:  81%|████████  | 20836/25880 [4:15:38<58:24,  1.44it/s]  
1|20837|Loss: 0.84382164478302:  81%|████████  | 20837/25880 [4:15:38<59:32,  1.41it/s]
1|20838|Loss: 0.779205322265625:  81%|████████  | 20837/25880 [4:15:39<59:32,  1.41it/s]
1|20838|Loss: 0.779205322265625:  81%|████████  | 20838/25880 [4:15:39<1:00:22,  1.39it/s]
1|20839|Loss: 0.7931894063949585:  81%|████████  | 20838/25880 [4:15:40<1:00:22,  1.39it/s]
1|20839|Loss: 0.7931894063949585:  81%|████████  | 20839/25880 [4:15:40<1:03:55,  1.31it/s]
1|20840|Loss: 0.8670669198036194:  81%|████████  | 20839/25880 [4:15:40<1:03:55,  1.31it/s]
1|20840|Loss: 0.8670669198036194:  81%|████████  | 20840/25880 [4:15:41<1:00:01,  1.40it/s]
1|20841|Loss: 0.676968514919281:  81%|████████  | 20840/25880 [4:15:41<1:00:01,  1.40it/s] 
1|20841|Loss: 0.676968514919281:  81%|████████  | 20841/25880 [4:15:41<58:40,  1.43it/s]  
1|20842|Loss: 0.838817834854126:  81%|████████  | 20841/25880 [4:15:42<58:40,  1.43it/s]
1|20842|Loss: 0.838817834854126:  81%|████████  | 20842/25880 [4:15:42<59:37,  1.41it/s]
1|20843|Loss: 0.758844792842865:  81%|████████  | 20842/25880 [4:15:42<59:37,  1.41it/s]
1|20843|Loss: 0.758844792842865:  81%|████████  | 20843/25880 [4:15:43<1:01:49,  1.36it/s]
1|20844|Loss: 0.814113974571228:  81%|████████  | 20843/25880 [4:15:43<1:01:49,  1.36it/s]
1|20844|Loss: 0.814113974571228:  81%|████████  | 20844/25880 [4:15:43<1:00:21,  1.39it/s]
1|20845|Loss: 0.9102280735969543:  81%|████████  | 20844/25880 [4:15:44<1:00:21,  1.39it/s]
1|20845|Loss: 0.9102280735969543:  81%|████████  | 20845/25880 [4:15:44<1:00:19,  1.39it/s]
1|20846|Loss: 0.8012779355049133:  81%|████████  | 20845/25880 [4:15:45<1:00:19,  1.39it/s]
1|20846|Loss: 0.8012779355049133:  81%|████████  | 20846/25880 [4:15:45<1:03:03,  1.33it/s]
1|20847|Loss: 0.6754809617996216:  81%|████████  | 20846/25880 [4:15:45<1:03:03,  1.33it/s]
1|20847|Loss: 0.6754809617996216:  81%|████████  | 20847/25880 [4:15:46<1:07:09,  1.25it/s]
1|20848|Loss: 0.8731504082679749:  81%|████████  | 20847/25880 [4:15:46<1:07:09,  1.25it/s]
1|20848|Loss: 0.8731504082679749:  81%|████████  | 20848/25880 [4:15:47<1:06:25,  1.26it/s]
1|20849|Loss: 0.819233775138855:  81%|████████  | 20848/25880 [4:15:47<1:06:25,  1.26it/s] 
1|20849|Loss: 0.819233775138855:  81%|████████  | 20849/25880 [4:15:47<1:05:15,  1.28it/s]
1|20850|Loss: 0.8745959997177124:  81%|████████  | 20849/25880 [4:15:48<1:05:15,  1.28it/s]
1|20850|Loss: 0.8745959997177124:  81%|████████  | 20850/25880 [4:15:48<1:07:07,  1.25it/s]
1|20851|Loss: 0.8831109404563904:  81%|████████  | 20850/25880 [4:15:49<1:07:07,  1.25it/s]
1|20851|Loss: 0.8831109404563904:  81%|████████  | 20851/25880 [4:15:49<1:08:12,  1.23it/s]
1|20852|Loss: 0.8288974761962891:  81%|████████  | 20851/25880 [4:15:50<1:08:12,  1.23it/s]
1|20852|Loss: 0.8288974761962891:  81%|████████  | 20852/25880 [4:15:50<1:08:32,  1.22it/s]
1|20853|Loss: 0.9395803809165955:  81%|████████  | 20852/25880 [4:15:50<1:08:32,  1.22it/s]
1|20853|Loss: 0.9395803809165955:  81%|████████  | 20853/25880 [4:15:51<1:06:37,  1.26it/s]
1|20854|Loss: 0.9490046501159668:  81%|████████  | 20853/25880 [4:15:51<1:06:37,  1.26it/s]
1|20854|Loss: 0.9490046501159668:  81%|████████  | 20854/25880 [4:15:51<1:02:59,  1.33it/s]
1|20855|Loss: 0.7457852959632874:  81%|████████  | 20854/25880 [4:15:52<1:02:59,  1.33it/s]
1|20855|Loss: 0.7457852959632874:  81%|████████  | 20855/25880 [4:15:52<1:01:21,  1.36it/s]
1|20856|Loss: 0.8346199989318848:  81%|████████  | 20855/25880 [4:15:52<1:01:21,  1.36it/s]
1|20856|Loss: 0.8346199989318848:  81%|████████  | 20856/25880 [4:15:53<1:03:03,  1.33it/s]
1|20857|Loss: 0.824303388595581:  81%|████████  | 20856/25880 [4:15:53<1:03:03,  1.33it/s] 
1|20857|Loss: 0.824303388595581:  81%|████████  | 20857/25880 [4:15:54<1:03:03,  1.33it/s]
1|20858|Loss: 0.978660523891449:  81%|████████  | 20857/25880 [4:15:54<1:03:03,  1.33it/s]
1|20858|Loss: 0.978660523891449:  81%|████████  | 20858/25880 [4:15:54<1:00:46,  1.38it/s]
1|20859|Loss: 0.7669664621353149:  81%|████████  | 20858/25880 [4:15:55<1:00:46,  1.38it/s]
1|20859|Loss: 0.7669664621353149:  81%|████████  | 20859/25880 [4:15:55<1:03:27,  1.32it/s]
1|20860|Loss: 0.8631558418273926:  81%|████████  | 20859/25880 [4:15:56<1:03:27,  1.32it/s]
1|20860|Loss: 0.8631558418273926:  81%|████████  | 20860/25880 [4:15:56<1:07:17,  1.24it/s]
1|20861|Loss: 0.9601358771324158:  81%|████████  | 20860/25880 [4:15:56<1:07:17,  1.24it/s]
1|20861|Loss: 0.9601358771324158:  81%|████████  | 20861/25880 [4:15:57<1:02:11,  1.34it/s]
1|20862|Loss: 0.8334744572639465:  81%|████████  | 20861/25880 [4:15:57<1:02:11,  1.34it/s]
1|20862|Loss: 0.8334744572639465:  81%|████████  | 20862/25880 [4:15:57<1:00:43,  1.38it/s]
1|20863|Loss: 0.9235778450965881:  81%|████████  | 20862/25880 [4:15:58<1:00:43,  1.38it/s]
1|20863|Loss: 0.9235778450965881:  81%|████████  | 20863/25880 [4:15:58<58:40,  1.43it/s]  
1|20864|Loss: 0.8145778179168701:  81%|████████  | 20863/25880 [4:15:58<58:40,  1.43it/s]
1|20864|Loss: 0.8145778179168701:  81%|████████  | 20864/25880 [4:15:59<57:05,  1.46it/s]
1|20865|Loss: 0.8482763767242432:  81%|████████  | 20864/25880 [4:15:59<57:05,  1.46it/s]
1|20865|Loss: 0.8482763767242432:  81%|████████  | 20865/25880 [4:15:59<1:00:45,  1.38it/s]
1|20866|Loss: 0.7611773610115051:  81%|████████  | 20865/25880 [4:16:00<1:00:45,  1.38it/s]
1|20866|Loss: 0.7611773610115051:  81%|████████  | 20866/25880 [4:16:00<59:55,  1.39it/s]  
1|20867|Loss: 0.8017005920410156:  81%|████████  | 20866/25880 [4:16:00<59:55,  1.39it/s]
1|20867|Loss: 0.8017005920410156:  81%|████████  | 20867/25880 [4:16:01<1:00:10,  1.39it/s]
1|20868|Loss: 0.9024085402488708:  81%|████████  | 20867/25880 [4:16:01<1:00:10,  1.39it/s]
1|20868|Loss: 0.9024085402488708:  81%|████████  | 20868/25880 [4:16:01<57:04,  1.46it/s]  
1|20869|Loss: 0.8079900145530701:  81%|████████  | 20868/25880 [4:16:02<57:04,  1.46it/s]
1|20869|Loss: 0.8079900145530701:  81%|████████  | 20869/25880 [4:16:02<55:30,  1.50it/s]
1|20870|Loss: 0.7366442084312439:  81%|████████  | 20869/25880 [4:16:02<55:30,  1.50it/s]
1|20870|Loss: 0.7366442084312439:  81%|████████  | 20870/25880 [4:16:03<54:30,  1.53it/s]
1|20871|Loss: 0.7389566898345947:  81%|████████  | 20870/25880 [4:16:03<54:30,  1.53it/s]
1|20871|Loss: 0.7389566898345947:  81%|████████  | 20871/25880 [4:16:03<58:31,  1.43it/s]
1|20872|Loss: 0.9167653322219849:  81%|████████  | 20871/25880 [4:16:04<58:31,  1.43it/s]
1|20872|Loss: 0.9167653322219849:  81%|████████  | 20872/25880 [4:16:04<1:00:59,  1.37it/s]
1|20873|Loss: 0.863305926322937:  81%|████████  | 20872/25880 [4:16:05<1:00:59,  1.37it/s] 
1|20873|Loss: 0.863305926322937:  81%|████████  | 20873/25880 [4:16:05<58:15,  1.43it/s]  
1|20874|Loss: 0.8882896304130554:  81%|████████  | 20873/25880 [4:16:05<58:15,  1.43it/s]
1|20874|Loss: 0.8882896304130554:  81%|████████  | 20874/25880 [4:16:06<1:02:14,  1.34it/s]
1|20875|Loss: 0.7688826322555542:  81%|████████  | 20874/25880 [4:16:06<1:02:14,  1.34it/s]
1|20875|Loss: 0.7688826322555542:  81%|████████  | 20875/25880 [4:16:07<1:02:21,  1.34it/s]
1|20876|Loss: 0.8096664547920227:  81%|████████  | 20875/25880 [4:16:07<1:02:21,  1.34it/s]
1|20876|Loss: 0.8096664547920227:  81%|████████  | 20876/25880 [4:16:07<1:01:46,  1.35it/s]
1|20877|Loss: 0.8603644371032715:  81%|████████  | 20876/25880 [4:16:08<1:01:46,  1.35it/s]
1|20877|Loss: 0.8603644371032715:  81%|████████  | 20877/25880 [4:16:08<58:28,  1.43it/s]  
1|20878|Loss: 0.8440549373626709:  81%|████████  | 20877/25880 [4:16:08<58:28,  1.43it/s]
1|20878|Loss: 0.8440549373626709:  81%|████████  | 20878/25880 [4:16:09<1:00:55,  1.37it/s]
1|20879|Loss: 0.8577212691307068:  81%|████████  | 20878/25880 [4:16:09<1:00:55,  1.37it/s]
1|20879|Loss: 0.8577212691307068:  81%|████████  | 20879/25880 [4:16:09<1:01:44,  1.35it/s]
1|20880|Loss: 0.8062364459037781:  81%|████████  | 20879/25880 [4:16:10<1:01:44,  1.35it/s]
1|20880|Loss: 0.8062364459037781:  81%|████████  | 20880/25880 [4:16:10<1:00:51,  1.37it/s]
1|20881|Loss: 0.7823610305786133:  81%|████████  | 20880/25880 [4:16:11<1:00:51,  1.37it/s]
1|20881|Loss: 0.7823610305786133:  81%|████████  | 20881/25880 [4:16:11<1:00:51,  1.37it/s]
1|20882|Loss: 0.8483197689056396:  81%|████████  | 20881/25880 [4:16:11<1:00:51,  1.37it/s]
1|20882|Loss: 0.8483197689056396:  81%|████████  | 20882/25880 [4:16:12<1:02:00,  1.34it/s]
1|20883|Loss: 0.77080237865448:  81%|████████  | 20882/25880 [4:16:12<1:02:00,  1.34it/s]  
1|20883|Loss: 0.77080237865448:  81%|████████  | 20883/25880 [4:16:12<1:04:11,  1.30it/s]
1|20884|Loss: 0.7938891053199768:  81%|████████  | 20883/25880 [4:16:13<1:04:11,  1.30it/s]
1|20884|Loss: 0.7938891053199768:  81%|████████  | 20884/25880 [4:16:13<1:03:19,  1.32it/s]
1|20885|Loss: 0.8332126140594482:  81%|████████  | 20884/25880 [4:16:14<1:03:19,  1.32it/s]
1|20885|Loss: 0.8332126140594482:  81%|████████  | 20885/25880 [4:16:14<1:02:29,  1.33it/s]
1|20886|Loss: 0.9253849387168884:  81%|████████  | 20885/25880 [4:16:14<1:02:29,  1.33it/s]
1|20886|Loss: 0.9253849387168884:  81%|████████  | 20886/25880 [4:16:15<59:06,  1.41it/s]  
1|20887|Loss: 0.831004798412323:  81%|████████  | 20886/25880 [4:16:15<59:06,  1.41it/s] 
1|20887|Loss: 0.831004798412323:  81%|████████  | 20887/25880 [4:16:15<58:52,  1.41it/s]
1|20888|Loss: 0.8346561789512634:  81%|████████  | 20887/25880 [4:16:16<58:52,  1.41it/s]
1|20888|Loss: 0.8346561789512634:  81%|████████  | 20888/25880 [4:16:16<1:03:05,  1.32it/s]
1|20889|Loss: 0.8042834401130676:  81%|████████  | 20888/25880 [4:16:17<1:03:05,  1.32it/s]
1|20889|Loss: 0.8042834401130676:  81%|████████  | 20889/25880 [4:16:17<1:01:31,  1.35it/s]
1|20890|Loss: 0.8259552121162415:  81%|████████  | 20889/25880 [4:16:17<1:01:31,  1.35it/s]
1|20890|Loss: 0.8259552121162415:  81%|████████  | 20890/25880 [4:16:18<1:00:10,  1.38it/s]
1|20891|Loss: 0.8091433048248291:  81%|████████  | 20890/25880 [4:16:18<1:00:10,  1.38it/s]
1|20891|Loss: 0.8091433048248291:  81%|████████  | 20891/25880 [4:16:18<1:00:15,  1.38it/s]
1|20892|Loss: 0.7879858016967773:  81%|████████  | 20891/25880 [4:16:19<1:00:15,  1.38it/s]
1|20892|Loss: 0.7879858016967773:  81%|████████  | 20892/25880 [4:16:19<1:01:54,  1.34it/s]
1|20893|Loss: 0.8313454389572144:  81%|████████  | 20892/25880 [4:16:19<1:01:54,  1.34it/s]
1|20893|Loss: 0.8313454389572144:  81%|████████  | 20893/25880 [4:16:20<1:04:50,  1.28it/s]
1|20894|Loss: 0.7855541110038757:  81%|████████  | 20893/25880 [4:16:20<1:04:50,  1.28it/s]
1|20894|Loss: 0.7855541110038757:  81%|████████  | 20894/25880 [4:16:21<1:04:27,  1.29it/s]
1|20895|Loss: 0.8753995299339294:  81%|████████  | 20894/25880 [4:16:21<1:04:27,  1.29it/s]
1|20895|Loss: 0.8753995299339294:  81%|████████  | 20895/25880 [4:16:21<1:04:36,  1.29it/s]
1|20896|Loss: 0.985791027545929:  81%|████████  | 20895/25880 [4:16:22<1:04:36,  1.29it/s] 
1|20896|Loss: 0.985791027545929:  81%|████████  | 20896/25880 [4:16:22<1:00:20,  1.38it/s]
1|20897|Loss: 0.7358317375183105:  81%|████████  | 20896/25880 [4:16:22<1:00:20,  1.38it/s]
1|20897|Loss: 0.7358317375183105:  81%|████████  | 20897/25880 [4:16:23<54:01,  1.54it/s]  
1|20898|Loss: 0.8165606260299683:  81%|████████  | 20897/25880 [4:16:23<54:01,  1.54it/s]
1|20898|Loss: 0.8165606260299683:  81%|████████  | 20898/25880 [4:16:23<57:28,  1.44it/s]
1|20899|Loss: 0.8971694707870483:  81%|████████  | 20898/25880 [4:16:24<57:28,  1.44it/s]
1|20899|Loss: 0.8971694707870483:  81%|████████  | 20899/25880 [4:16:24<59:00,  1.41it/s]
1|20900|Loss: 0.9058877825737:  81%|████████  | 20899/25880 [4:16:25<59:00,  1.41it/s]   
1|20900|Loss: 0.9058877825737:  81%|████████  | 20900/25880 [4:16:25<1:03:58,  1.30it/s]
1|20901|Loss: 0.705470860004425:  81%|████████  | 20900/25880 [4:16:25<1:03:58,  1.30it/s]
1|20901|Loss: 0.705470860004425:  81%|████████  | 20901/25880 [4:16:26<1:04:19,  1.29it/s]
1|20902|Loss: 0.8369117975234985:  81%|████████  | 20901/25880 [4:16:26<1:04:19,  1.29it/s]
1|20902|Loss: 0.8369117975234985:  81%|████████  | 20902/25880 [4:16:27<1:06:35,  1.25it/s]
1|20903|Loss: 0.7122659683227539:  81%|████████  | 20902/25880 [4:16:27<1:06:35,  1.25it/s]
1|20903|Loss: 0.7122659683227539:  81%|████████  | 20903/25880 [4:16:28<1:08:47,  1.21it/s]
1|20904|Loss: 0.8574071526527405:  81%|████████  | 20903/25880 [4:16:28<1:08:47,  1.21it/s]
1|20904|Loss: 0.8574071526527405:  81%|████████  | 20904/25880 [4:16:28<1:08:29,  1.21it/s]
1|20905|Loss: 0.6748114228248596:  81%|████████  | 20904/25880 [4:16:29<1:08:29,  1.21it/s]
1|20905|Loss: 0.6748114228248596:  81%|████████  | 20905/25880 [4:16:29<1:09:15,  1.20it/s]
1|20906|Loss: 1.0169388055801392:  81%|████████  | 20905/25880 [4:16:30<1:09:15,  1.20it/s]
1|20906|Loss: 1.0169388055801392:  81%|████████  | 20906/25880 [4:16:30<1:07:04,  1.24it/s]
1|20907|Loss: 0.8426518440246582:  81%|████████  | 20906/25880 [4:16:30<1:07:04,  1.24it/s]
1|20907|Loss: 0.8426518440246582:  81%|████████  | 20907/25880 [4:16:31<1:02:03,  1.34it/s]
1|20908|Loss: 0.8296089768409729:  81%|████████  | 20907/25880 [4:16:31<1:02:03,  1.34it/s]
1|20908|Loss: 0.8296089768409729:  81%|████████  | 20908/25880 [4:16:31<57:49,  1.43it/s]  
1|20909|Loss: 0.9193172454833984:  81%|████████  | 20908/25880 [4:16:32<57:49,  1.43it/s]
1|20909|Loss: 0.9193172454833984:  81%|████████  | 20909/25880 [4:16:32<59:27,  1.39it/s]
1|20910|Loss: 0.7571840286254883:  81%|████████  | 20909/25880 [4:16:32<59:27,  1.39it/s]
1|20910|Loss: 0.7571840286254883:  81%|████████  | 20910/25880 [4:16:33<1:00:05,  1.38it/s]
1|20911|Loss: 0.8151570558547974:  81%|████████  | 20910/25880 [4:16:33<1:00:05,  1.38it/s]
1|20911|Loss: 0.8151570558547974:  81%|████████  | 20911/25880 [4:16:33<58:00,  1.43it/s]  
1|20912|Loss: 0.8353399634361267:  81%|████████  | 20911/25880 [4:16:34<58:00,  1.43it/s]
1|20912|Loss: 0.8353399634361267:  81%|████████  | 20912/25880 [4:16:34<57:37,  1.44it/s]
1|20913|Loss: 0.8013250231742859:  81%|████████  | 20912/25880 [4:16:34<57:37,  1.44it/s]
1|20913|Loss: 0.8013250231742859:  81%|████████  | 20913/25880 [4:16:35<56:01,  1.48it/s]
1|20914|Loss: 0.9411687254905701:  81%|████████  | 20913/25880 [4:16:35<56:01,  1.48it/s]
1|20914|Loss: 0.9411687254905701:  81%|████████  | 20914/25880 [4:16:35<58:53,  1.41it/s]
1|20915|Loss: 0.7812255024909973:  81%|████████  | 20914/25880 [4:16:36<58:53,  1.41it/s]
1|20915|Loss: 0.7812255024909973:  81%|████████  | 20915/25880 [4:16:36<1:00:17,  1.37it/s]
1|20916|Loss: 0.8557586073875427:  81%|████████  | 20915/25880 [4:16:37<1:00:17,  1.37it/s]
1|20916|Loss: 0.8557586073875427:  81%|████████  | 20916/25880 [4:16:37<1:02:37,  1.32it/s]
1|20917|Loss: 0.7784039974212646:  81%|████████  | 20916/25880 [4:16:37<1:02:37,  1.32it/s]
1|20917|Loss: 0.7784039974212646:  81%|████████  | 20917/25880 [4:16:38<1:06:02,  1.25it/s]
1|20918|Loss: 0.7641297578811646:  81%|████████  | 20917/25880 [4:16:38<1:06:02,  1.25it/s]
1|20918|Loss: 0.7641297578811646:  81%|████████  | 20918/25880 [4:16:39<1:05:28,  1.26it/s]
1|20919|Loss: 0.9358512163162231:  81%|████████  | 20918/25880 [4:16:39<1:05:28,  1.26it/s]
1|20919|Loss: 0.9358512163162231:  81%|████████  | 20919/25880 [4:16:39<58:36,  1.41it/s]  
1|20920|Loss: 0.7376853823661804:  81%|████████  | 20919/25880 [4:16:40<58:36,  1.41it/s]
1|20920|Loss: 0.7376853823661804:  81%|████████  | 20920/25880 [4:16:40<1:00:46,  1.36it/s]
1|20921|Loss: 0.7780521512031555:  81%|████████  | 20920/25880 [4:16:40<1:00:46,  1.36it/s]
1|20921|Loss: 0.7780521512031555:  81%|████████  | 20921/25880 [4:16:41<1:03:09,  1.31it/s]
1|20922|Loss: 0.8975252509117126:  81%|████████  | 20921/25880 [4:16:41<1:03:09,  1.31it/s]
1|20922|Loss: 0.8975252509117126:  81%|████████  | 20922/25880 [4:16:42<1:02:53,  1.31it/s]
1|20923|Loss: 0.8376813530921936:  81%|████████  | 20922/25880 [4:16:42<1:02:53,  1.31it/s]
1|20923|Loss: 0.8376813530921936:  81%|████████  | 20923/25880 [4:16:42<1:07:02,  1.23it/s]
1|20924|Loss: 0.8575640916824341:  81%|████████  | 20923/25880 [4:16:43<1:07:02,  1.23it/s]
1|20924|Loss: 0.8575640916824341:  81%|████████  | 20924/25880 [4:16:43<1:05:35,  1.26it/s]
1|20925|Loss: 0.7043138742446899:  81%|████████  | 20924/25880 [4:16:44<1:05:35,  1.26it/s]
1|20925|Loss: 0.7043138742446899:  81%|████████  | 20925/25880 [4:16:44<1:04:59,  1.27it/s]
1|20926|Loss: 0.8071759939193726:  81%|████████  | 20925/25880 [4:16:44<1:04:59,  1.27it/s]
1|20926|Loss: 0.8071759939193726:  81%|████████  | 20926/25880 [4:16:45<1:02:07,  1.33it/s]
1|20927|Loss: 0.8889215588569641:  81%|████████  | 20926/25880 [4:16:45<1:02:07,  1.33it/s]
1|20927|Loss: 0.8889215588569641:  81%|████████  | 20927/25880 [4:16:45<57:47,  1.43it/s]  
1|20928|Loss: 0.8483980894088745:  81%|█��██████  | 20927/25880 [4:16:46<57:47,  1.43it/s]
1|20928|Loss: 0.8483980894088745:  81%|████████  | 20928/25880 [4:16:46<55:49,  1.48it/s]
1|20929|Loss: 0.6846259236335754:  81%|████████  | 20928/25880 [4:16:46<55:49,  1.48it/s]
1|20929|Loss: 0.6846259236335754:  81%|████████  | 20929/25880 [4:16:46<52:44,  1.56it/s]
1|20930|Loss: 0.8840599656105042:  81%|████████  | 20929/25880 [4:16:47<52:44,  1.56it/s]
1|20930|Loss: 0.8840599656105042:  81%|████████  | 20930/25880 [4:16:47<56:17,  1.47it/s]
1|20931|Loss: 0.5969070792198181:  81%|████████  | 20930/25880 [4:16:48<56:17,  1.47it/s]
1|20931|Loss: 0.5969070792198181:  81%|████████  | 20931/25880 [4:16:48<58:18,  1.41it/s]
1|20932|Loss: 0.8912549614906311:  81%|████████  | 20931/25880 [4:16:48<58:18,  1.41it/s]
1|20932|Loss: 0.8912549614906311:  81%|████████  | 20932/25880 [4:16:49<56:51,  1.45it/s]
1|20933|Loss: 0.9496466517448425:  81%|████████  | 20932/25880 [4:16:49<56:51,  1.45it/s]
1|20933|Loss: 0.9496466517448425:  81%|████████  | 20933/25880 [4:16:49<57:23,  1.44it/s]
1|20934|Loss: 0.8378896117210388:  81%|████████  | 20933/25880 [4:16:50<57:23,  1.44it/s]
1|20934|Loss: 0.8378896117210388:  81%|████████  | 20934/25880 [4:16:50<55:54,  1.47it/s]
1|20935|Loss: 0.9878314733505249:  81%|████████  | 20934/25880 [4:16:50<55:54,  1.47it/s]
1|20935|Loss: 0.9878314733505249:  81%|████████  | 20935/25880 [4:16:51<59:37,  1.38it/s]
1|20936|Loss: 0.7548069953918457:  81%|████████  | 20935/25880 [4:16:51<59:37,  1.38it/s]
1|20936|Loss: 0.7548069953918457:  81%|████████  | 20936/25880 [4:16:52<1:02:11,  1.33it/s]
1|20937|Loss: 0.8633025288581848:  81%|████████  | 20936/25880 [4:16:52<1:02:11,  1.33it/s]
1|20937|Loss: 0.8633025288581848:  81%|████████  | 20937/25880 [4:16:52<1:02:10,  1.32it/s]
1|20938|Loss: 0.8115077614784241:  81%|████████  | 20937/25880 [4:16:53<1:02:10,  1.32it/s]
1|20938|Loss: 0.8115077614784241:  81%|████████  | 20938/25880 [4:16:53<1:01:41,  1.34it/s]
1|20939|Loss: 0.8758224248886108:  81%|████████  | 20938/25880 [4:16:53<1:01:41,  1.34it/s]
1|20939|Loss: 0.8758224248886108:  81%|████████  | 20939/25880 [4:16:54<59:16,  1.39it/s]  
1|20940|Loss: 0.8360011577606201:  81%|████████  | 20939/25880 [4:16:54<59:16,  1.39it/s]
1|20940|Loss: 0.8360011577606201:  81%|████████  | 20940/25880 [4:16:54<56:56,  1.45it/s]
1|20941|Loss: 0.7569378018379211:  81%|████████  | 20940/25880 [4:16:55<56:56,  1.45it/s]
1|20941|Loss: 0.7569378018379211:  81%|████████  | 20941/25880 [4:16:55<50:38,  1.63it/s]
1|20942|Loss: 0.7952924966812134:  81%|████████  | 20941/25880 [4:16:55<50:38,  1.63it/s]
1|20942|Loss: 0.7952924966812134:  81%|████████  | 20942/25880 [4:16:56<53:58,  1.52it/s]
1|20943|Loss: 0.7524733543395996:  81%|████████  | 20942/25880 [4:16:56<53:58,  1.52it/s]
1|20943|Loss: 0.7524733543395996:  81%|████████  | 20943/25880 [4:16:56<55:40,  1.48it/s]
1|20944|Loss: 0.839743971824646:  81%|████████  | 20943/25880 [4:16:57<55:40,  1.48it/s] 
1|20944|Loss: 0.839743971824646:  81%|████████  | 20944/25880 [4:16:57<58:18,  1.41it/s]
1|20945|Loss: 0.8098227977752686:  81%|████████  | 20944/25880 [4:16:58<58:18,  1.41it/s]
1|20945|Loss: 0.8098227977752686:  81%|████████  | 20945/25880 [4:16:58<59:35,  1.38it/s]
1|20946|Loss: 0.8232722878456116:  81%|████████  | 20945/25880 [4:16:58<59:35,  1.38it/s]
1|20946|Loss: 0.8232722878456116:  81%|████████  | 20946/25880 [4:16:59<1:02:20,  1.32it/s]
1|20947|Loss: 0.879206657409668:  81%|████████  | 20946/25880 [4:16:59<1:02:20,  1.32it/s] 
1|20947|Loss: 0.879206657409668:  81%|████████  | 20947/25880 [4:17:00<1:06:56,  1.23it/s]
1|20948|Loss: 0.7317609786987305:  81%|████████  | 20947/25880 [4:17:00<1:06:56,  1.23it/s]
1|20948|Loss: 0.7317609786987305:  81%|████████  | 20948/25880 [4:17:00<1:03:07,  1.30it/s]
1|20949|Loss: 0.8077939748764038:  81%|████████  | 20948/25880 [4:17:01<1:03:07,  1.30it/s]
1|20949|Loss: 0.8077939748764038:  81%|████████  | 20949/25880 [4:17:01<1:01:54,  1.33it/s]
1|20950|Loss: 0.8596909046173096:  81%|████████  | 20949/25880 [4:17:01<1:01:54,  1.33it/s]
1|20950|Loss: 0.8596909046173096:  81%|████████  | 20950/25880 [4:17:02<1:04:11,  1.28it/s]
1|20951|Loss: 0.8578852415084839:  81%|████████  | 20950/25880 [4:17:02<1:04:11,  1.28it/s]
1|20951|Loss: 0.8578852415084839:  81%|████████  | 20951/25880 [4:17:03<1:03:13,  1.30it/s]
1|20952|Loss: 0.8247261047363281:  81%|████████  | 20951/25880 [4:17:03<1:03:13,  1.30it/s]
1|20952|Loss: 0.8247261047363281:  81%|████████  | 20952/25880 [4:17:03<1:00:15,  1.36it/s]
1|20953|Loss: 0.9206448793411255:  81%|████████  | 20952/25880 [4:17:04<1:00:15,  1.36it/s]
1|20953|Loss: 0.9206448793411255:  81%|████████  | 20953/25880 [4:17:04<59:12,  1.39it/s]  
1|20954|Loss: 0.7918205261230469:  81%|████████  | 20953/25880 [4:17:04<59:12,  1.39it/s]
1|20954|Loss: 0.7918205261230469:  81%|████████  | 20954/25880 [4:17:05<57:25,  1.43it/s]
1|20955|Loss: 0.8130639791488647:  81%|████████  | 20954/25880 [4:17:05<57:25,  1.43it/s]
1|20955|Loss: 0.8130639791488647:  81%|████████  | 20955/25880 [4:17:05<57:05,  1.44it/s]
1|20956|Loss: 0.7636008858680725:  81%|████████  | 20955/25880 [4:17:06<57:05,  1.44it/s]
1|20956|Loss: 0.7636008858680725:  81%|████████  | 20956/25880 [4:17:06<52:09,  1.57it/s]
1|20957|Loss: 0.8671684265136719:  81%|████████  | 20956/25880 [4:17:06<52:09,  1.57it/s]
1|20957|Loss: 0.8671684265136719:  81%|████████  | 20957/25880 [4:17:06<53:19,  1.54it/s]
1|20958|Loss: 0.9202666282653809:  81%|████████  | 20957/25880 [4:17:07<53:19,  1.54it/s]
1|20958|Loss: 0.9202666282653809:  81%|████████  | 20958/25880 [4:17:07<52:39,  1.56it/s]
1|20959|Loss: 0.838756799697876:  81%|████████  | 20958/25880 [4:17:07<52:39,  1.56it/s] 
1|20959|Loss: 0.838756799697876:  81%|████████  | 20959/25880 [4:17:08<54:12,  1.51it/s]
1|20960|Loss: 0.6689760088920593:  81%|████████  | 20959/25880 [4:17:08<54:12,  1.51it/s]
1|20960|Loss: 0.6689760088920593:  81%|████████  | 20960/25880 [4:17:09<57:48,  1.42it/s]
1|20961|Loss: 0.8723881840705872:  81%|████████  | 20960/25880 [4:17:09<57:48,  1.42it/s]
1|20961|Loss: 0.8723881840705872:  81%|████████  | 20961/25880 [4:17:09<58:28,  1.40it/s]
1|20962|Loss: 0.8660906553268433:  81%|████████  | 20961/25880 [4:17:10<58:28,  1.40it/s]
1|20962|Loss: 0.8660906553268433:  81%|████████  | 20962/25880 [4:17:10<55:53,  1.47it/s]
1|20963|Loss: 1.052646517753601:  81%|████████  | 20962/25880 [4:17:10<55:53,  1.47it/s] 
1|20963|Loss: 1.052646517753601:  81%|████████  | 20963/25880 [4:17:11<59:00,  1.39it/s]
1|20964|Loss: 0.8481165170669556:  81%|████████  | 20963/25880 [4:17:11<59:00,  1.39it/s]
1|20964|Loss: 0.8481165170669556:  81%|████████  | 20964/25880 [4:17:11<55:39,  1.47it/s]
1|20965|Loss: 0.7818174958229065:  81%|████████  | 20964/25880 [4:17:12<55:39,  1.47it/s]
1|20965|Loss: 0.7818174958229065:  81%|████████  | 20965/25880 [4:17:12<55:45,  1.47it/s]
1|20966|Loss: 0.7488381862640381:  81%|████████  | 20965/25880 [4:17:12<55:45,  1.47it/s]
1|20966|Loss: 0.7488381862640381:  81%|████████  | 20966/25880 [4:17:13<57:14,  1.43it/s]
1|20967|Loss: 0.7999141216278076:  81%|████████  | 20966/25880 [4:17:13<57:14,  1.43it/s]
1|20967|Loss: 0.7999141216278076:  81%|████████  | 20967/25880 [4:17:13<56:09,  1.46it/s]
1|20968|Loss: 0.7567551732063293:  81%|████████  | 20967/25880 [4:17:14<56:09,  1.46it/s]
1|20968|Loss: 0.7567551732063293:  81%|████████  | 20968/25880 [4:17:14<58:14,  1.41it/s]
1|20969|Loss: 0.743983268737793:  81%|████████  | 20968/25880 [4:17:14<58:14,  1.41it/s] 
1|20969|Loss: 0.743983268737793:  81%|████████  | 20969/25880 [4:17:15<52:19,  1.56it/s]
1|20970|Loss: 0.6538665890693665:  81%|████████  | 20969/25880 [4:17:15<52:19,  1.56it/s]
1|20970|Loss: 0.6538665890693665:  81%|████████  | 20970/25880 [4:17:15<47:40,  1.72it/s]
1|20971|Loss: 0.7414833903312683:  81%|████████  | 20970/25880 [4:17:15<47:40,  1.72it/s]
1|20971|Loss: 0.7414833903312683:  81%|████████  | 20971/25880 [4:17:16<49:06,  1.67it/s]
1|20972|Loss: 0.8596537113189697:  81%|████████  | 20971/25880 [4:17:16<49:06,  1.67it/s]
1|20972|Loss: 0.8596537113189697:  81%|████████  | 20972/25880 [4:17:16<52:25,  1.56it/s]
1|20973|Loss: 0.9227071404457092:  81%|████████  | 20972/25880 [4:17:17<52:25,  1.56it/s]
1|20973|Loss: 0.9227071404457092:  81%|████████  | 20973/25880 [4:17:17<54:23,  1.50it/s]
1|20974|Loss: 0.9234705567359924:  81%|████████  | 20973/25880 [4:17:18<54:23,  1.50it/s]
1|20974|Loss: 0.9234705567359924:  81%|████████  | 20974/25880 [4:17:18<53:33,  1.53it/s]
1|20975|Loss: 0.8079589009284973:  81%|████████  | 20974/25880 [4:17:18<53:33,  1.53it/s]
1|20975|Loss: 0.8079589009284973:  81%|████████  | 20975/25880 [4:17:19<55:56,  1.46it/s]
1|20976|Loss: 0.864314079284668:  81%|████████  | 20975/25880 [4:17:19<55:56,  1.46it/s] 
1|20976|Loss: 0.864314079284668:  81%|████████  | 20976/25880 [4:17:19<57:33,  1.42it/s]
1|20977|Loss: 0.7513181567192078:  81%|████████  | 20976/25880 [4:17:20<57:33,  1.42it/s]
1|20977|Loss: 0.7513181567192078:  81%|████████  | 20977/25880 [4:17:20<58:38,  1.39it/s]
1|20978|Loss: 0.8381227850914001:  81%|████████  | 20977/25880 [4:17:20<58:38,  1.39it/s]
1|20978|Loss: 0.8381227850914001:  81%|████████  | 20978/25880 [4:17:21<59:05,  1.38it/s]
1|20979|Loss: 0.8596093058586121:  81%|████████  | 20978/25880 [4:17:21<59:05,  1.38it/s]
1|20979|Loss: 0.8596093058586121:  81%|████████  | 20979/25880 [4:17:22<58:40,  1.39it/s]
1|20980|Loss: 0.8072400093078613:  81%|████████  | 20979/25880 [4:17:22<58:40,  1.39it/s]
1|20980|Loss: 0.8072400093078613:  81%|████████  | 20980/25880 [4:17:22<54:25,  1.50it/s]
1|20981|Loss: 0.7629817724227905:  81%|████████  | 20980/25880 [4:17:22<54:25,  1.50it/s]
1|20981|Loss: 0.7629817724227905:  81%|████████  | 20981/25880 [4:17:23<54:20,  1.50it/s]
1|20982|Loss: 0.7748956680297852:  81%|████████  | 20981/25880 [4:17:23<54:20,  1.50it/s]
1|20982|Loss: 0.7748956680297852:  81%|████████  | 20982/25880 [4:17:23<55:13,  1.48it/s]
1|20983|Loss: 0.8752437233924866:  81%|████████  | 20982/25880 [4:17:24<55:13,  1.48it/s]
1|20983|Loss: 0.8752437233924866:  81%|████████  | 20983/25880 [4:17:24<57:31,  1.42it/s]
1|20984|Loss: 0.8141115307807922:  81%|████████  | 20983/25880 [4:17:25<57:31,  1.42it/s]
1|20984|Loss: 0.8141115307807922:  81%|████████  | 20984/25880 [4:17:25<57:53,  1.41it/s]
1|20985|Loss: 0.7047243714332581:  81%|████████  | 20984/25880 [4:17:25<57:53,  1.41it/s]
1|20985|Loss: 0.7047243714332581:  81%|████████  | 20985/25880 [4:17:26<55:18,  1.47it/s]
1|20986|Loss: 0.7730458378791809:  81%|████████  | 20985/25880 [4:17:26<55:18,  1.47it/s]
1|20986|Loss: 0.7730458378791809:  81%|████████  | 20986/25880 [4:17:26<57:08,  1.43it/s]
1|20987|Loss: 0.8391542434692383:  81%|████████  | 20986/25880 [4:17:27<57:08,  1.43it/s]
1|20987|Loss: 0.8391542434692383:  81%|████████  | 20987/25880 [4:17:27<57:29,  1.42it/s]
1|20988|Loss: 0.8842248320579529:  81%|████████  | 20987/25880 [4:17:27<57:29,  1.42it/s]
1|20988|Loss: 0.8842248320579529:  81%|████████  | 20988/25880 [4:17:28<57:53,  1.41it/s]
1|20989|Loss: 0.8487922549247742:  81%|████████  | 20988/25880 [4:17:28<57:53,  1.41it/s]
1|20989|Loss: 0.8487922549247742:  81%|████████  | 20989/25880 [4:17:28<56:34,  1.44it/s]
1|20990|Loss: 0.7672264575958252:  81%|████████  | 20989/25880 [4:17:29<56:34,  1.44it/s]
1|20990|Loss: 0.7672264575958252:  81%|████████  | 20990/25880 [4:17:29<54:01,  1.51it/s]
1|20991|Loss: 0.835871160030365:  81%|████████  | 20990/25880 [4:17:29<54:01,  1.51it/s] 
1|20991|Loss: 0.835871160030365:  81%|████████  | 20991/25880 [4:17:30<53:05,  1.53it/s]
1|20992|Loss: 0.7181835174560547:  81%|████████  | 20991/25880 [4:17:30<53:05,  1.53it/s]
1|20992|Loss: 0.7181835174560547:  81%|████████  | 20992/25880 [4:17:31<59:55,  1.36it/s]
1|20993|Loss: 0.8779036998748779:  81%|████████  | 20992/25880 [4:17:31<59:55,  1.36it/s]
1|20993|Loss: 0.8779036998748779:  81%|████████  | 20993/25880 [4:17:31<1:03:31,  1.28it/s]
1|20994|Loss: 0.8881028294563293:  81%|████████  | 20993/25880 [4:17:32<1:03:31,  1.28it/s]
1|20994|Loss: 0.8881028294563293:  81%|████████  | 20994/25880 [4:17:32<1:04:45,  1.26it/s]
1|20995|Loss: 0.8819126486778259:  81%|████████  | 20994/25880 [4:17:33<1:04:45,  1.26it/s]
1|20995|Loss: 0.8819126486778259:  81%|████████  | 20995/25880 [4:17:33<1:03:35,  1.28it/s]
1|20996|Loss: 0.9002492427825928:  81%|████████  | 20995/25880 [4:17:33<1:03:35,  1.28it/s]
1|20996|Loss: 0.9002492427825928:  81%|████████  | 20996/25880 [4:17:34<1:03:22,  1.28it/s]
1|20997|Loss: 0.8793533444404602:  81%|████████  | 20996/25880 [4:17:34<1:03:22,  1.28it/s]
1|20997|Loss: 0.8793533444404602:  81%|████████  | 20997/25880 [4:17:34<1:00:25,  1.35it/s]
1|20998|Loss: 0.7701675891876221:  81%|████████  | 20997/25880 [4:17:35<1:00:25,  1.35it/s]
1|20998|Loss: 0.7701675891876221:  81%|████████  | 20998/25880 [4:17:35<59:33,  1.37it/s]  
1|20999|Loss: 0.8222399353981018:  81%|████████  | 20998/25880 [4:17:36<59:33,  1.37it/s]
1|20999|Loss: 0.8222399353981018:  81%|████████  | 20999/25880 [4:17:36<1:00:33,  1.34it/s]
1|21000|Loss: 0.872145414352417:  81%|████████  | 20999/25880 [4:17:36<1:00:33,  1.34it/s] 
1|21000|Loss: 0.872145414352417:  81%|████████  | 21000/25880 [4:17:37<57:37,  1.41it/s]  
1|21001|Loss: 0.920418918132782:  81%|████████  | 21000/25880 [4:17:37<57:37,  1.41it/s]
1|21001|Loss: 0.920418918132782:  81%|████████  | 21001/25880 [4:17:37<56:50,  1.43it/s]
1|21002|Loss: 0.8375258445739746:  81%|████████  | 21001/25880 [4:17:38<56:50,  1.43it/s]
1|21002|Loss: 0.8375258445739746:  81%|████████  | 21002/25880 [4:17:38<55:13,  1.47it/s]
1|21003|Loss: 0.7616440057754517:  81%|████████  | 21002/25880 [4:17:38<55:13,  1.47it/s]
1|21003|Loss: 0.7616440057754517:  81%|████████  | 21003/25880 [4:17:38<53:32,  1.52it/s]
1|21004|Loss: 0.8119887113571167:  81%|████████  | 21003/25880 [4:17:39<53:32,  1.52it/s]
1|21004|Loss: 0.8119887113571167:  81%|████████  | 21004/25880 [4:17:39<57:32,  1.41it/s]
1|21005|Loss: 0.8422845602035522:  81%|████████  | 21004/25880 [4:17:40<57:32,  1.41it/s]
1|21005|Loss: 0.8422845602035522:  81%|████████  | 21005/25880 [4:17:40<58:21,  1.39it/s]
1|21006|Loss: 0.8169056177139282:  81%|████████  | 21005/25880 [4:17:40<58:21,  1.39it/s]
1|21006|Loss: 0.8169056177139282:  81%|████████  | 21006/25880 [4:17:41<56:45,  1.43it/s]
1|21007|Loss: 0.9075690507888794:  81%|████████  | 21006/25880 [4:17:41<56:45,  1.43it/s]
1|21007|Loss: 0.9075690507888794:  81%|████████  | 21007/25880 [4:17:41<54:53,  1.48it/s]
1|21008|Loss: 0.8624342083930969:  81%|████████  | 21007/25880 [4:17:42<54:53,  1.48it/s]
1|21008|Loss: 0.8624342083930969:  81%|████████  | 21008/25880 [4:17:42<57:32,  1.41it/s]
1|21009|Loss: 0.7663663625717163:  81%|████████  | 21008/25880 [4:17:42<57:32,  1.41it/s]
1|21009|Loss: 0.7663663625717163:  81%|████████  | 21009/25880 [4:17:43<57:55,  1.40it/s]
1|21010|Loss: 0.7617421746253967:  81%|████████  | 21009/25880 [4:17:43<57:55,  1.40it/s]
1|21010|Loss: 0.7617421746253967:  81%|████████  | 21010/25880 [4:17:43<56:34,  1.43it/s]
1|21011|Loss: 0.8354817628860474:  81%|████████  | 21010/25880 [4:17:44<56:34,  1.43it/s]
1|21011|Loss: 0.8354817628860474:  81%|████████  | 21011/25880 [4:17:44<58:18,  1.39it/s]
1|21012|Loss: 0.8713912963867188:  81%|████████  | 21011/25880 [4:17:45<58:18,  1.39it/s]
1|21012|Loss: 0.8713912963867188:  81%|████████  | 21012/25880 [4:17:45<54:14,  1.50it/s]
1|21013|Loss: 0.9004939198493958:  81%|████████  | 21012/25880 [4:17:45<54:14,  1.50it/s]
1|21013|Loss: 0.9004939198493958:  81%|████████  | 21013/25880 [4:17:45<54:30,  1.49it/s]
1|21014|Loss: 0.8874863386154175:  81%|████████  | 21013/25880 [4:17:46<54:30,  1.49it/s]
1|21014|Loss: 0.8874863386154175:  81%|████████  | 21014/25880 [4:17:46<59:42,  1.36it/s]
1|21015|Loss: 0.8057733774185181:  81%|████████  | 21014/25880 [4:17:47<59:42,  1.36it/s]
1|21015|Loss: 0.8057733774185181:  81%|████████  | 21015/25880 [4:17:47<1:00:24,  1.34it/s]
1|21016|Loss: 0.8222959637641907:  81%|████████  | 21015/25880 [4:17:47<1:00:24,  1.34it/s]
1|21016|Loss: 0.8222959637641907:  81%|████████  | 21016/25880 [4:17:48<58:23,  1.39it/s]  
1|21017|Loss: 0.8107202649116516:  81%|████████  | 21016/25880 [4:17:48<58:23,  1.39it/s]
1|21017|Loss: 0.8107202649116516:  81%|████████  | 21017/25880 [4:17:48<58:17,  1.39it/s]
1|21018|Loss: 0.8286941051483154:  81%|████████  | 21017/25880 [4:17:49<58:17,  1.39it/s]
1|21018|Loss: 0.8286941051483154:  81%|████████  | 21018/25880 [4:17:49<59:42,  1.36it/s]
1|21019|Loss: 0.8070971965789795:  81%|████████  | 21018/25880 [4:17:50<59:42,  1.36it/s]
1|21019|Loss: 0.8070971965789795:  81%|████████  | 21019/25880 [4:17:50<1:00:02,  1.35it/s]
1|21020|Loss: 0.7758674621582031:  81%|████████  | 21019/25880 [4:17:50<1:00:02,  1.35it/s]
1|21020|Loss: 0.7758674621582031:  81%|████████  | 21020/25880 [4:17:51<1:00:43,  1.33it/s]
1|21021|Loss: 0.76421719789505:  81%|████████  | 21020/25880 [4:17:51<1:00:43,  1.33it/s]  
1|21021|Loss: 0.76421719789505:  81%|████████  | 21021/25880 [4:17:51<59:57,  1.35it/s]  
1|21022|Loss: 0.8569685816764832:  81%|████████  | 21021/25880 [4:17:52<59:57,  1.35it/s]
1|21022|Loss: 0.8569685816764832:  81%|████████  | 21022/25880 [4:17:52<1:02:26,  1.30it/s]
1|21023|Loss: 0.8175434470176697:  81%|████████  | 21022/25880 [4:17:53<1:02:26,  1.30it/s]
1|21023|Loss: 0.8175434470176697:  81%|████████  | 21023/25880 [4:17:53<1:02:14,  1.30it/s]
1|21024|Loss: 0.8428165912628174:  81%|████████  | 21023/25880 [4:17:54<1:02:14,  1.30it/s]
1|21024|Loss: 0.8428165912628174:  81%|████████  | 21024/25880 [4:17:54<1:04:08,  1.26it/s]
1|21025|Loss: 0.8174523711204529:  81%|████████  | 21024/25880 [4:17:54<1:04:08,  1.26it/s]
1|21025|Loss: 0.8174523711204529:  81%|████████  | 21025/25880 [4:17:55<1:01:40,  1.31it/s]
1|21026|Loss: 0.9330134391784668:  81%|████████  | 21025/25880 [4:17:55<1:01:40,  1.31it/s]
1|21026|Loss: 0.9330134391784668:  81%|████████  | 21026/25880 [4:17:55<1:00:16,  1.34it/s]
1|21027|Loss: 0.8536438941955566:  81%|████████  | 21026/25880 [4:17:56<1:00:16,  1.34it/s]
1|21027|Loss: 0.8536438941955566:  81%|████████  | 21027/25880 [4:17:56<1:03:37,  1.27it/s]
1|21028|Loss: 0.7639312744140625:  81%|████████  | 21027/25880 [4:17:57<1:03:37,  1.27it/s]
1|21028|Loss: 0.7639312744140625:  81%|████████▏ | 21028/25880 [4:17:57<1:04:12,  1.26it/s]
1|21029|Loss: 0.784234344959259:  81%|████████▏ | 21028/25880 [4:17:57<1:04:12,  1.26it/s] 
1|21029|Loss: 0.784234344959259:  81%|████████▏ | 21029/25880 [4:17:58<58:38,  1.38it/s]  
1|21030|Loss: 0.8704037666320801:  81%|████████▏ | 21029/25880 [4:17:58<58:38,  1.38it/s]
1|21030|Loss: 0.8704037666320801:  81%|████████▏ | 21030/25880 [4:17:58<58:59,  1.37it/s]
1|21031|Loss: 0.9251672029495239:  81%|████████▏ | 21030/25880 [4:17:59<58:59,  1.37it/s]
1|21031|Loss: 0.9251672029495239:  81%|████████▏ | 21031/25880 [4:17:59<1:00:46,  1.33it/s]
1|21032|Loss: 0.8935614228248596:  81%|████████▏ | 21031/25880 [4:18:00<1:00:46,  1.33it/s]
1|21032|Loss: 0.8935614228248596:  81%|████████▏ | 21032/25880 [4:18:00<1:01:45,  1.31it/s]
1|21033|Loss: 1.0510751008987427:  81%|████████▏ | 21032/25880 [4:18:00<1:01:45,  1.31it/s]
1|21033|Loss: 1.0510751008987427:  81%|████████▏ | 21033/25880 [4:18:01<1:09:52,  1.16it/s]
1|21034|Loss: 0.9418332576751709:  81%|████████▏ | 21033/25880 [4:18:02<1:09:52,  1.16it/s]
1|21034|Loss: 0.9418332576751709:  81%|████████▏ | 21034/25880 [4:18:02<1:08:55,  1.17it/s]
1|21035|Loss: 0.7884326577186584:  81%|████████▏ | 21034/25880 [4:18:02<1:08:55,  1.17it/s]
1|21035|Loss: 0.7884326577186584:  81%|████████▏ | 21035/25880 [4:18:03<1:05:56,  1.22it/s]
1|21036|Loss: 0.9163989424705505:  81%|████████▏ | 21035/25880 [4:18:03<1:05:56,  1.22it/s]
1|21036|Loss: 0.9163989424705505:  81%|████████▏ | 21036/25880 [4:18:03<1:01:29,  1.31it/s]
1|21037|Loss: 0.9458022713661194:  81%|████████▏ | 21036/25880 [4:18:04<1:01:29,  1.31it/s]
1|21037|Loss: 0.9458022713661194:  81%|████████▏ | 21037/25880 [4:18:04<58:28,  1.38it/s]  
1|21038|Loss: 0.8608739376068115:  81%|████████▏ | 21037/25880 [4:18:04<58:28,  1.38it/s]
1|21038|Loss: 0.8608739376068115:  81%|████████▏ | 21038/25880 [4:18:05<1:01:58,  1.30it/s]
1|21039|Loss: 0.9255337715148926:  81%|████████▏ | 21038/25880 [4:18:05<1:01:58,  1.30it/s]
1|21039|Loss: 0.9255337715148926:  81%|████████▏ | 21039/25880 [4:18:06<1:02:26,  1.29it/s]
1|21040|Loss: 0.8086163997650146:  81%|████████▏ | 21039/25880 [4:18:06<1:02:26,  1.29it/s]
1|21040|Loss: 0.8086163997650146:  81%|████████▏ | 21040/25880 [4:18:06<1:01:09,  1.32it/s]
1|21041|Loss: 0.8429908752441406:  81%|████████▏ | 21040/25880 [4:18:07<1:01:09,  1.32it/s]
1|21041|Loss: 0.8429908752441406:  81%|████████▏ | 21041/25880 [4:18:07<53:16,  1.51it/s]  
1|21042|Loss: 0.8917735815048218:  81%|████████▏ | 21041/25880 [4:18:07<53:16,  1.51it/s]
1|21042|Loss: 0.8917735815048218:  81%|████████▏ | 21042/25880 [4:18:07<48:41,  1.66it/s]
1|21043|Loss: 0.7947004437446594:  81%|████████▏ | 21042/25880 [4:18:08<48:41,  1.66it/s]
1|21043|Loss: 0.7947004437446594:  81%|████████▏ | 21043/25880 [4:18:08<52:45,  1.53it/s]
1|21044|Loss: 0.9642455577850342:  81%|████████▏ | 21043/25880 [4:18:08<52:45,  1.53it/s]
1|21044|Loss: 0.9642455577850342:  81%|████████▏ | 21044/25880 [4:18:09<54:45,  1.47it/s]
1|21045|Loss: 0.855580747127533:  81%|████████▏ | 21044/25880 [4:18:09<54:45,  1.47it/s] 
1|21045|Loss: 0.855580747127533:  81%|████████▏ | 21045/25880 [4:18:09<55:46,  1.44it/s]
1|21046|Loss: 0.8965844511985779:  81%|████████▏ | 21045/25880 [4:18:10<55:46,  1.44it/s]
1|21046|Loss: 0.8965844511985779:  81%|████████▏ | 21046/25880 [4:18:10<53:07,  1.52it/s]
1|21047|Loss: 0.9794839024543762:  81%|████████▏ | 21046/25880 [4:18:10<53:07,  1.52it/s]
1|21047|Loss: 0.9794839024543762:  81%|████████▏ | 21047/25880 [4:18:11<54:08,  1.49it/s]
1|21048|Loss: 0.731063187122345:  81%|████████▏ | 21047/25880 [4:18:11<54:08,  1.49it/s] 
1|21048|Loss: 0.731063187122345:  81%|████████▏ | 21048/25880 [4:18:11<55:05,  1.46it/s]
1|21049|Loss: 0.6882100105285645:  81%|████████▏ | 21048/25880 [4:18:12<55:05,  1.46it/s]
1|21049|Loss: 0.6882100105285645:  81%|████████▏ | 21049/25880 [4:18:12<50:31,  1.59it/s]
1|21050|Loss: 0.8919318914413452:  81%|████████▏ | 21049/25880 [4:18:12<50:31,  1.59it/s]
1|21050|Loss: 0.8919318914413452:  81%|████████▏ | 21050/25880 [4:18:13<51:31,  1.56it/s]
1|21051|Loss: 0.7775590419769287:  81%|████████▏ | 21050/25880 [4:18:13<51:31,  1.56it/s]
1|21051|Loss: 0.7775590419769287:  81%|████████▏ | 21051/25880 [4:18:13<53:05,  1.52it/s]
1|21052|Loss: 0.9206967949867249:  81%|████████▏ | 21051/25880 [4:18:14<53:05,  1.52it/s]
1|21052|Loss: 0.9206967949867249:  81%|████████▏ | 21052/25880 [4:18:14<49:08,  1.64it/s]
1|21053|Loss: 0.8822831511497498:  81%|████████▏ | 21052/25880 [4:18:14<49:08,  1.64it/s]
1|21053|Loss: 0.8822831511497498:  81%|████████▏ | 21053/25880 [4:18:14<48:55,  1.64it/s]
1|21054|Loss: 0.8746693134307861:  81%|████████▏ | 21053/25880 [4:18:15<48:55,  1.64it/s]
1|21054|Loss: 0.8746693134307861:  81%|████████▏ | 21054/25880 [4:18:15<51:00,  1.58it/s]
1|21055|Loss: 0.7187792062759399:  81%|████████▏ | 21054/25880 [4:18:15<51:00,  1.58it/s]
1|21055|Loss: 0.7187792062759399:  81%|████████▏ | 21055/25880 [4:18:16<51:22,  1.57it/s]
1|21056|Loss: 0.7427295446395874:  81%|████████▏ | 21055/25880 [4:18:16<51:22,  1.57it/s]
1|21056|Loss: 0.7427295446395874:  81%|████████▏ | 21056/25880 [4:18:16<55:10,  1.46it/s]
1|21057|Loss: 0.8899960517883301:  81%|████████▏ | 21056/25880 [4:18:17<55:10,  1.46it/s]
1|21057|Loss: 0.8899960517883301:  81%|████████▏ | 21057/25880 [4:18:17<58:58,  1.36it/s]
1|21058|Loss: 0.9444133639335632:  81%|████████▏ | 21057/25880 [4:18:18<58:58,  1.36it/s]
1|21058|Loss: 0.9444133639335632:  81%|████████▏ | 21058/25880 [4:18:18<1:02:28,  1.29it/s]
1|21059|Loss: 0.9525626301765442:  81%|████████▏ | 21058/25880 [4:18:19<1:02:28,  1.29it/s]
1|21059|Loss: 0.9525626301765442:  81%|████████▏ | 21059/25880 [4:18:19<1:02:16,  1.29it/s]
1|21060|Loss: 0.8502627611160278:  81%|████████▏ | 21059/25880 [4:18:19<1:02:16,  1.29it/s]
1|21060|Loss: 0.8502627611160278:  81%|████████▏ | 21060/25880 [4:18:20<1:01:28,  1.31it/s]
1|21061|Loss: 1.1646947860717773:  81%|████████▏ | 21060/25880 [4:18:20<1:01:28,  1.31it/s]
1|21061|Loss: 1.1646947860717773:  81%|████████▏ | 21061/25880 [4:18:20<1:01:00,  1.32it/s]
1|21062|Loss: 0.8746114373207092:  81%|████████▏ | 21061/25880 [4:18:21<1:01:00,  1.32it/s]
1|21062|Loss: 0.8746114373207092:  81%|████████▏ | 21062/25880 [4:18:21<1:00:43,  1.32it/s]
1|21063|Loss: 0.8197289109230042:  81%|████████▏ | 21062/25880 [4:18:22<1:00:43,  1.32it/s]
1|21063|Loss: 0.8197289109230042:  81%|████████▏ | 21063/25880 [4:18:22<58:00,  1.38it/s]  
1|21064|Loss: 0.7629430890083313:  81%|████████▏ | 21063/25880 [4:18:22<58:00,  1.38it/s]
1|21064|Loss: 0.7629430890083313:  81%|████████▏ | 21064/25880 [4:18:23<1:00:24,  1.33it/s]
1|21065|Loss: 0.8138514757156372:  81%|████████▏ | 21064/25880 [4:18:23<1:00:24,  1.33it/s]
1|21065|Loss: 0.8138514757156372:  81%|████████▏ | 21065/25880 [4:18:23<58:43,  1.37it/s]  
1|21066|Loss: 0.87748122215271:  81%|████████▏ | 21065/25880 [4:18:24<58:43,  1.37it/s]  
1|21066|Loss: 0.87748122215271:  81%|████████▏ | 21066/25880 [4:18:24<57:41,  1.39it/s]
1|21067|Loss: 0.7878811359405518:  81%|████████▏ | 21066/25880 [4:18:24<57:41,  1.39it/s]
1|21067|Loss: 0.7878811359405518:  81%|████████▏ | 21067/25880 [4:18:25<58:50,  1.36it/s]
1|21068|Loss: 0.7967406511306763:  81%|████████▏ | 21067/25880 [4:18:25<58:50,  1.36it/s]
1|21068|Loss: 0.7967406511306763:  81%|████████▏ | 21068/25880 [4:18:25<56:11,  1.43it/s]
1|21069|Loss: 0.8668195009231567:  81%|████████▏ | 21068/25880 [4:18:26<56:11,  1.43it/s]
1|21069|Loss: 0.8668195009231567:  81%|████████▏ | 21069/25880 [4:18:26<56:28,  1.42it/s]
1|21070|Loss: 0.7670726180076599:  81%|████████▏ | 21069/25880 [4:18:27<56:28,  1.42it/s]
1|21070|Loss: 0.7670726180076599:  81%|████████▏ | 21070/25880 [4:18:27<55:38,  1.44it/s]
1|21071|Loss: 0.8827670812606812:  81%|████████▏ | 21070/25880 [4:18:27<55:38,  1.44it/s]
1|21071|Loss: 0.8827670812606812:  81%|████████▏ | 21071/25880 [4:18:27<53:55,  1.49it/s]
1|21072|Loss: 0.8556395769119263:  81%|████████▏ | 21071/25880 [4:18:28<53:55,  1.49it/s]
1|21072|Loss: 0.8556395769119263:  81%|████████▏ | 21072/25880 [4:18:28<59:11,  1.35it/s]
1|21073|Loss: 0.8340203166007996:  81%|████████▏ | 21072/25880 [4:18:29<59:11,  1.35it/s]
1|21073|Loss: 0.8340203166007996:  81%|████████▏ | 21073/25880 [4:18:29<1:03:58,  1.25it/s]
1|21074|Loss: 0.7754126191139221:  81%|████████▏ | 21073/25880 [4:18:30<1:03:58,  1.25it/s]
1|21074|Loss: 0.7754126191139221:  81%|████████▏ | 21074/25880 [4:18:30<1:04:20,  1.25it/s]
1|21075|Loss: 1.0100749731063843:  81%|████████▏ | 21074/25880 [4:18:31<1:04:20,  1.25it/s]
1|21075|Loss: 1.0100749731063843:  81%|████████▏ | 21075/25880 [4:18:31<1:05:22,  1.23it/s]
1|21076|Loss: 0.8724342584609985:  81%|████████▏ | 21075/25880 [4:18:31<1:05:22,  1.23it/s]
1|21076|Loss: 0.8724342584609985:  81%|████████▏ | 21076/25880 [4:18:32<1:02:11,  1.29it/s]
1|21077|Loss: 0.840006947517395:  81%|████████▏ | 21076/25880 [4:18:32<1:02:11,  1.29it/s] 
1|21077|Loss: 0.840006947517395:  81%|████████▏ | 21077/25880 [4:18:32<1:01:48,  1.29it/s]
1|21078|Loss: 0.8711893558502197:  81%|████████▏ | 21077/25880 [4:18:33<1:01:48,  1.29it/s]
1|21078|Loss: 0.8711893558502197:  81%|████████▏ | 21078/25880 [4:18:33<1:00:36,  1.32it/s]
1|21079|Loss: 0.7672213912010193:  81%|████████▏ | 21078/25880 [4:18:34<1:00:36,  1.32it/s]
1|21079|Loss: 0.7672213912010193:  81%|████████▏ | 21079/25880 [4:18:34<1:00:16,  1.33it/s]
1|21080|Loss: 0.8546107411384583:  81%|████████▏ | 21079/25880 [4:18:34<1:00:16,  1.33it/s]
1|21080|Loss: 0.8546107411384583:  81%|████████▏ | 21080/25880 [4:18:35<1:01:47,  1.29it/s]
1|21081|Loss: 0.9036160707473755:  81%|████████▏ | 21080/25880 [4:18:35<1:01:47,  1.29it/s]
1|21081|Loss: 0.9036160707473755:  81%|████████▏ | 21081/25880 [4:18:36<1:03:07,  1.27it/s]
1|21082|Loss: 0.7693716287612915:  81%|████████▏ | 21081/25880 [4:18:36<1:03:07,  1.27it/s]
1|21082|Loss: 0.7693716287612915:  81%|████████▏ | 21082/25880 [4:18:36<1:00:21,  1.33it/s]
1|21083|Loss: 0.8993964791297913:  81%|████████▏ | 21082/25880 [4:18:37<1:00:21,  1.33it/s]
1|21083|Loss: 0.8993964791297913:  81%|████████▏ | 21083/25880 [4:18:37<58:51,  1.36it/s]  
1|21084|Loss: 0.8535960912704468:  81%|████████▏ | 21083/25880 [4:18:37<58:51,  1.36it/s]
1|21084|Loss: 0.8535960912704468:  81%|████████▏ | 21084/25880 [4:18:38<56:57,  1.40it/s]
1|21085|Loss: 0.8230260610580444:  81%|████████▏ | 21084/25880 [4:18:38<56:57,  1.40it/s]
1|21085|Loss: 0.8230260610580444:  81%|████████▏ | 21085/25880 [4:18:38<59:20,  1.35it/s]
1|21086|Loss: 0.8471211791038513:  81%|████████▏ | 21085/25880 [4:18:39<59:20,  1.35it/s]
1|21086|Loss: 0.8471211791038513:  81%|████████▏ | 21086/25880 [4:18:39<57:37,  1.39it/s]
1|21087|Loss: 0.8814086318016052:  81%|████████▏ | 21086/25880 [4:18:39<57:37,  1.39it/s]
1|21087|Loss: 0.8814086318016052:  81%|████████▏ | 21087/25880 [4:18:40<53:14,  1.50it/s]
1|21088|Loss: 0.8541569113731384:  81%|████████▏ | 21087/25880 [4:18:40<53:14,  1.50it/s]
1|21088|Loss: 0.8541569113731384:  81%|████████▏ | 21088/25880 [4:18:40<50:49,  1.57it/s]
1|21089|Loss: 0.8723699450492859:  81%|████████▏ | 21088/25880 [4:18:40<50:49,  1.57it/s]
1|21089|Loss: 0.8723699450492859:  81%|████████▏ | 21089/25880 [4:18:41<52:41,  1.52it/s]
1|21090|Loss: 0.7611457109451294:  81%|████████▏ | 21089/25880 [4:18:41<52:41,  1.52it/s]
1|21090|Loss: 0.7611457109451294:  81%|████████▏ | 21090/25880 [4:18:42<57:11,  1.40it/s]
1|21091|Loss: 0.8475651144981384:  81%|████████▏ | 21090/25880 [4:18:42<57:11,  1.40it/s]
1|21091|Loss: 0.8475651144981384:  81%|████████▏ | 21091/25880 [4:18:42<56:36,  1.41it/s]
1|21092|Loss: 0.9017711877822876:  81%|████████▏ | 21091/25880 [4:18:43<56:36,  1.41it/s]
1|21092|Loss: 0.9017711877822876:  81%|████████▏ | 21092/25880 [4:18:43<49:47,  1.60it/s]
1|21093|Loss: 0.7230813503265381:  81%|████████▏ | 21092/25880 [4:18:43<49:47,  1.60it/s]
1|21093|Loss: 0.7230813503265381:  82%|████████▏ | 21093/25880 [4:18:43<48:33,  1.64it/s]
1|21094|Loss: 0.7389443516731262:  82%|████████▏ | 21093/25880 [4:18:44<48:33,  1.64it/s]
1|21094|Loss: 0.7389443516731262:  82%|████████▏ | 21094/25880 [4:18:44<53:08,  1.50it/s]
1|21095|Loss: 0.9240859150886536:  82%|████████▏ | 21094/25880 [4:18:45<53:08,  1.50it/s]
1|21095|Loss: 0.9240859150886536:  82%|████████▏ | 21095/25880 [4:18:45<51:53,  1.54it/s]
1|21096|Loss: 0.830456554889679:  82%|████████▏ | 21095/25880 [4:18:45<51:53,  1.54it/s] 
1|21096|Loss: 0.830456554889679:  82%|████████▏ | 21096/25880 [4:18:45<50:49,  1.57it/s]
1|21097|Loss: 0.8900902271270752:  82%|████████▏ | 21096/25880 [4:18:46<50:49,  1.57it/s]
1|21097|Loss: 0.8900902271270752:  82%|████████▏ | 21097/25880 [4:18:46<52:26,  1.52it/s]
1|21098|Loss: 0.8772498369216919:  82%|████████▏ | 21097/25880 [4:18:46<52:26,  1.52it/s]
1|21098|Loss: 0.8772498369216919:  82%|████████▏ | 21098/25880 [4:18:47<51:54,  1.54it/s]
1|21099|Loss: 0.8211592435836792:  82%|████████▏ | 21098/25880 [4:18:47<51:54,  1.54it/s]
1|21099|Loss: 0.8211592435836792:  82%|████████▏ | 21099/25880 [4:18:47<48:02,  1.66it/s]
1|21100|Loss: 0.9176520705223083:  82%|████████▏ | 21099/25880 [4:18:48<48:02,  1.66it/s]
1|21100|Loss: 0.9176520705223083:  82%|████████▏ | 21100/25880 [4:18:48<49:21,  1.61it/s]
1|21101|Loss: 0.9009860157966614:  82%|████████▏ | 21100/25880 [4:18:48<49:21,  1.61it/s]
1|21101|Loss: 0.9009860157966614:  82%|████████▏ | 21101/25880 [4:18:49<53:55,  1.48it/s]
1|21102|Loss: 0.7729212045669556:  82%|████████▏ | 21101/25880 [4:18:49<53:55,  1.48it/s]
1|21102|Loss: 0.7729212045669556:  82%|████████▏ | 21102/25880 [4:18:50<56:50,  1.40it/s]
1|21103|Loss: 0.8293032646179199:  82%|████████▏ | 21102/25880 [4:18:50<56:50,  1.40it/s]
1|21103|Loss: 0.8293032646179199:  82%|████████▏ | 21103/25880 [4:18:50<1:03:15,  1.26it/s]
1|21104|Loss: 0.8170695900917053:  82%|████████▏ | 21103/25880 [4:18:51<1:03:15,  1.26it/s]
1|21104|Loss: 0.8170695900917053:  82%|████████▏ | 21104/25880 [4:18:51<1:02:01,  1.28it/s]
1|21105|Loss: 0.855968713760376:  82%|████████▏ | 21104/25880 [4:18:52<1:02:01,  1.28it/s] 
1|21105|Loss: 0.855968713760376:  82%|████████▏ | 21105/25880 [4:18:52<1:02:23,  1.28it/s]
1|21106|Loss: 0.9088267683982849:  82%|████████▏ | 21105/25880 [4:18:53<1:02:23,  1.28it/s]
1|21106|Loss: 0.9088267683982849:  82%|████████▏ | 21106/25880 [4:18:53<1:06:04,  1.20it/s]
1|21107|Loss: 0.8897721767425537:  82%|████████▏ | 21106/25880 [4:18:53<1:06:04,  1.20it/s]
1|21107|Loss: 0.8897721767425537:  82%|████████▏ | 21107/25880 [4:18:54<1:02:38,  1.27it/s]
1|21108|Loss: 0.8557888269424438:  82%|████████▏ | 21107/25880 [4:18:54<1:02:38,  1.27it/s]
1|21108|Loss: 0.8557888269424438:  82%|████████▏ | 21108/25880 [4:18:54<59:01,  1.35it/s]  
1|21109|Loss: 0.8254390954971313:  82%|████████▏ | 21108/25880 [4:18:55<59:01,  1.35it/s]
1|21109|Loss: 0.8254390954971313:  82%|████████▏ | 21109/25880 [4:18:55<58:32,  1.36it/s]
1|21110|Loss: 0.7750394940376282:  82%|████████▏ | 21109/25880 [4:18:55<58:32,  1.36it/s]
1|21110|Loss: 0.7750394940376282:  82%|████████▏ | 21110/25880 [4:18:56<57:48,  1.38it/s]
1|21111|Loss: 0.816564679145813:  82%|████████▏ | 21110/25880 [4:18:56<57:48,  1.38it/s] 
1|21111|Loss: 0.816564679145813:  82%|████████▏ | 21111/25880 [4:18:57<59:30,  1.34it/s]
1|21112|Loss: 0.8342750072479248:  82%|████████▏ | 21111/25880 [4:18:57<59:30,  1.34it/s]
1|21112|Loss: 0.8342750072479248:  82%|████████▏ | 21112/25880 [4:18:57<56:46,  1.40it/s]
1|21113|Loss: 0.7430992126464844:  82%|████████▏ | 21112/25880 [4:18:57<56:46,  1.40it/s]
1|21113|Loss: 0.7430992126464844:  82%|████████▏ | 21113/25880 [4:18:58<53:45,  1.48it/s]
1|21114|Loss: 0.7901217937469482:  82%|████████▏ | 21113/25880 [4:18:58<53:45,  1.48it/s]
1|21114|Loss: 0.7901217937469482:  82%|████████▏ | 21114/25880 [4:18:58<54:19,  1.46it/s]
1|21115|Loss: 0.8923150897026062:  82%|████████▏ | 21114/25880 [4:18:59<54:19,  1.46it/s]
1|21115|Loss: 0.8923150897026062:  82%|████████▏ | 21115/25880 [4:18:59<52:34,  1.51it/s]
1|21116|Loss: 0.8389965295791626:  82%|████████▏ | 21115/25880 [4:18:59<52:34,  1.51it/s]
1|21116|Loss: 0.8389965295791626:  82%|████████▏ | 21116/25880 [4:19:00<53:33,  1.48it/s]
1|21117|Loss: 0.8785138130187988:  82%|████████▏ | 21116/25880 [4:19:00<53:33,  1.48it/s]
1|21117|Loss: 0.8785138130187988:  82%|████████▏ | 21117/25880 [4:19:00<52:06,  1.52it/s]
1|21118|Loss: 0.9886822700500488:  82%|████████▏ | 21117/25880 [4:19:01<52:06,  1.52it/s]
1|21118|Loss: 0.9886822700500488:  82%|████████▏ | 21118/25880 [4:19:01<53:26,  1.49it/s]
1|21119|Loss: 0.891619861125946:  82%|████████▏ | 21118/25880 [4:19:01<53:26,  1.49it/s] 
1|21119|Loss: 0.891619861125946:  82%|████████▏ | 21119/25880 [4:19:02<50:43,  1.56it/s]
1|21120|Loss: 0.8581971526145935:  82%|████████▏ | 21119/25880 [4:19:02<50:43,  1.56it/s]
1|21120|Loss: 0.8581971526145935:  82%|████████▏ | 21120/25880 [4:19:02<53:46,  1.48it/s]
1|21121|Loss: 0.8175427913665771:  82%|████████▏ | 21120/25880 [4:19:03<53:46,  1.48it/s]
1|21121|Loss: 0.8175427913665771:  82%|████████▏ | 21121/25880 [4:19:03<57:13,  1.39it/s]
1|21122|Loss: 0.7607924938201904:  82%|████████▏ | 21121/25880 [4:19:04<57:13,  1.39it/s]
1|21122|Loss: 0.7607924938201904:  82%|████████▏ | 21122/25880 [4:19:04<54:55,  1.44it/s]
1|21123|Loss: 0.9553916454315186:  82%|████████▏ | 21122/25880 [4:19:04<54:55,  1.44it/s]
1|21123|Loss: 0.9553916454315186:  82%|████████▏ | 21123/25880 [4:19:05<54:56,  1.44it/s]
1|21124|Loss: 0.7763035297393799:  82%|████████▏ | 21123/25880 [4:19:05<54:56,  1.44it/s]
1|21124|Loss: 0.7763035297393799:  82%|████████▏ | 21124/25880 [4:19:05<52:55,  1.50it/s]
1|21125|Loss: 0.7147080898284912:  82%|████████▏ | 21124/25880 [4:19:06<52:55,  1.50it/s]
1|21125|Loss: 0.7147080898284912:  82%|████████▏ | 21125/25880 [4:19:06<59:19,  1.34it/s]
1|21126|Loss: 0.7455066442489624:  82%|████████▏ | 21125/25880 [4:19:07<59:19,  1.34it/s]
1|21126|Loss: 0.7455066442489624:  82%|████████▏ | 21126/25880 [4:19:07<58:46,  1.35it/s]
1|21127|Loss: 0.9077754616737366:  82%|████████▏ | 21126/25880 [4:19:07<58:46,  1.35it/s]
1|21127|Loss: 0.9077754616737366:  82%|████████▏ | 21127/25880 [4:19:07<55:49,  1.42it/s]
1|21128|Loss: 0.9161633253097534:  82%|████████▏ | 21127/25880 [4:19:08<55:49,  1.42it/s]
1|21128|Loss: 0.9161633253097534:  82%|████████▏ | 21128/25880 [4:19:08<58:51,  1.35it/s]
1|21129|Loss: 0.656506359577179:  82%|████████▏ | 21128/25880 [4:19:09<58:51,  1.35it/s] 
1|21129|Loss: 0.656506359577179:  82%|████████▏ | 21129/25880 [4:19:09<58:59,  1.34it/s]
1|21130|Loss: 0.8564891815185547:  82%|████████▏ | 21129/25880 [4:19:09<58:59,  1.34it/s]
1|21130|Loss: 0.8564891815185547:  82%|████████▏ | 21130/25880 [4:19:10<58:06,  1.36it/s]
1|21131|Loss: 0.9999396204948425:  82%|████████▏ | 21130/25880 [4:19:10<58:06,  1.36it/s]
1|21131|Loss: 0.9999396204948425:  82%|████████▏ | 21131/25880 [4:19:11<59:43,  1.33it/s]
1|21132|Loss: 0.8693126440048218:  82%|████████▏ | 21131/25880 [4:19:11<59:43,  1.33it/s]
1|21132|Loss: 0.8693126440048218:  82%|████████▏ | 21132/25880 [4:19:11<56:40,  1.40it/s]
1|21133|Loss: 0.8137782216072083:  82%|████████▏ | 21132/25880 [4:19:12<56:40,  1.40it/s]
1|21133|Loss: 0.8137782216072083:  82%|████████▏ | 21133/25880 [4:19:12<58:05,  1.36it/s]
1|21134|Loss: 0.7605485320091248:  82%|████████▏ | 21133/25880 [4:19:12<58:05,  1.36it/s]
1|21134|Loss: 0.7605485320091248:  82%|████████▏ | 21134/25880 [4:19:13<56:47,  1.39it/s]
1|21135|Loss: 0.8281713724136353:  82%|████████▏ | 21134/25880 [4:19:13<56:47,  1.39it/s]
1|21135|Loss: 0.8281713724136353:  82%|████████▏ | 21135/25880 [4:19:13<57:03,  1.39it/s]
1|21136|Loss: 0.9469744563102722:  82%|████████▏ | 21135/25880 [4:19:14<57:03,  1.39it/s]
1|21136|Loss: 0.9469744563102722:  82%|████████▏ | 21136/25880 [4:19:14<58:21,  1.35it/s]
1|21137|Loss: 0.714163064956665:  82%|████████▏ | 21136/25880 [4:19:15<58:21,  1.35it/s] 
1|21137|Loss: 0.714163064956665:  82%|████████▏ | 21137/25880 [4:19:15<1:00:02,  1.32it/s]
1|21138|Loss: 0.863878607749939:  82%|████████▏ | 21137/25880 [4:19:15<1:00:02,  1.32it/s]
1|21138|Loss: 0.863878607749939:  82%|████████▏ | 21138/25880 [4:19:16<55:49,  1.42it/s]  
1|21139|Loss: 0.8689637780189514:  82%|████████▏ | 21138/25880 [4:19:16<55:49,  1.42it/s]
1|21139|Loss: 0.8689637780189514:  82%|████████▏ | 21139/25880 [4:19:16<56:27,  1.40it/s]
1|21140|Loss: 0.7995820045471191:  82%|████████▏ | 21139/25880 [4:19:17<56:27,  1.40it/s]
1|21140|Loss: 0.7995820045471191:  82%|████████▏ | 21140/25880 [4:19:17<55:25,  1.43it/s]
1|21141|Loss: 0.7597213983535767:  82%|████████▏ | 21140/25880 [4:19:17<55:25,  1.43it/s]
1|21141|Loss: 0.7597213983535767:  82%|████████▏ | 21141/25880 [4:19:18<56:00,  1.41it/s]
1|21142|Loss: 0.6999675035476685:  82%|████████▏ | 21141/25880 [4:19:18<56:00,  1.41it/s]
1|21142|Loss: 0.6999675035476685:  82%|████████▏ | 21142/25880 [4:19:18<54:31,  1.45it/s]
1|21143|Loss: 0.7884094715118408:  82%|████████▏ | 21142/25880 [4:19:19<54:31,  1.45it/s]
1|21143|Loss: 0.7884094715118408:  82%|████████▏ | 21143/25880 [4:19:19<58:26,  1.35it/s]
1|21144|Loss: 0.6785719394683838:  82%|████████▏ | 21143/25880 [4:19:20<58:26,  1.35it/s]
1|21144|Loss: 0.6785719394683838:  82%|████████▏ | 21144/25880 [4:19:20<55:37,  1.42it/s]
1|21145|Loss: 0.9058119058609009:  82%|████████▏ | 21144/25880 [4:19:20<55:37,  1.42it/s]
1|21145|Loss: 0.9058119058609009:  82%|████████▏ | 21145/25880 [4:19:21<57:10,  1.38it/s]
1|21146|Loss: 0.8301799893379211:  82%|████████▏ | 21145/25880 [4:19:21<57:10,  1.38it/s]
1|21146|Loss: 0.8301799893379211:  82%|████████▏ | 21146/25880 [4:19:21<1:00:16,  1.31it/s]
1|21147|Loss: 0.8747556209564209:  82%|████████▏ | 21146/25880 [4:19:22<1:00:16,  1.31it/s]
1|21147|Loss: 0.8747556209564209:  82%|████████▏ | 21147/25880 [4:19:22<59:38,  1.32it/s]  
1|21148|Loss: 0.903659462928772:  82%|████████▏ | 21147/25880 [4:19:23<59:38,  1.32it/s] 
1|21148|Loss: 0.903659462928772:  82%|████████▏ | 21148/25880 [4:19:23<58:59,  1.34it/s]
1|21149|Loss: 0.8281075358390808:  82%|████████▏ | 21148/25880 [4:19:23<58:59,  1.34it/s]
1|21149|Loss: 0.8281075358390808:  82%|████████▏ | 21149/25880 [4:19:24<56:28,  1.40it/s]
1|21150|Loss: 0.8262993097305298:  82%|████████▏ | 21149/25880 [4:19:24<56:28,  1.40it/s]
1|21150|Loss: 0.8262993097305298:  82%|████████▏ | 21150/25880 [4:19:24<1:00:39,  1.30it/s]
1|21151|Loss: 0.8233470320701599:  82%|████████▏ | 21150/25880 [4:19:25<1:00:39,  1.30it/s]
1|21151|Loss: 0.8233470320701599:  82%|████████▏ | 21151/25880 [4:19:25<1:02:13,  1.27it/s]
1|21152|Loss: 0.8016490936279297:  82%|████████▏ | 21151/25880 [4:19:26<1:02:13,  1.27it/s]
1|21152|Loss: 0.8016490936279297:  82%|████████▏ | 21152/25880 [4:19:26<1:02:08,  1.27it/s]
1|21153|Loss: 0.853431761264801:  82%|████████▏ | 21152/25880 [4:19:26<1:02:08,  1.27it/s] 
1|21153|Loss: 0.853431761264801:  82%|████████▏ | 21153/25880 [4:19:27<58:16,  1.35it/s]  
1|21154|Loss: 0.8199790716171265:  82%|████████▏ | 21153/25880 [4:19:27<58:16,  1.35it/s]
1|21154|Loss: 0.8199790716171265:  82%|████████▏ | 21154/25880 [4:19:27<57:32,  1.37it/s]
1|21155|Loss: 0.897723913192749:  82%|████████▏ | 21154/25880 [4:19:28<57:32,  1.37it/s] 
1|21155|Loss: 0.897723913192749:  82%|████████▏ | 21155/25880 [4:19:28<57:02,  1.38it/s]
1|21156|Loss: 0.7952297329902649:  82%|████████▏ | 21155/25880 [4:19:28<57:02,  1.38it/s]
1|21156|Loss: 0.7952297329902649:  82%|████████▏ | 21156/25880 [4:19:29<55:10,  1.43it/s]
1|21157|Loss: 0.7307864427566528:  82%|████████▏ | 21156/25880 [4:19:29<55:10,  1.43it/s]
1|21157|Loss: 0.7307864427566528:  82%|████████▏ | 21157/25880 [4:19:29<55:19,  1.42it/s]
1|21158|Loss: 0.7041603326797485:  82%|████████▏ | 21157/25880 [4:19:30<55:19,  1.42it/s]
1|21158|Loss: 0.7041603326797485:  82%|████████▏ | 21158/25880 [4:19:30<55:15,  1.42it/s]
1|21159|Loss: 0.9107913970947266:  82%|████████▏ | 21158/25880 [4:19:31<55:15,  1.42it/s]
1|21159|Loss: 0.9107913970947266:  82%|████████▏ | 21159/25880 [4:19:31<55:35,  1.42it/s]
1|21160|Loss: 0.8552253246307373:  82%|████████▏ | 21159/25880 [4:19:31<55:35,  1.42it/s]
1|21160|Loss: 0.8552253246307373:  82%|████████▏ | 21160/25880 [4:19:32<57:13,  1.37it/s]
1|21161|Loss: 0.8059187531471252:  82%|████████▏ | 21160/25880 [4:19:32<57:13,  1.37it/s]
1|21161|Loss: 0.8059187531471252:  82%|████████▏ | 21161/25880 [4:19:32<56:00,  1.40it/s]
1|21162|Loss: 0.8346874713897705:  82%|████████▏ | 21161/25880 [4:19:33<56:00,  1.40it/s]
1|21162|Loss: 0.8346874713897705:  82%|████████▏ | 21162/25880 [4:19:33<55:25,  1.42it/s]
1|21163|Loss: 0.8545366525650024:  82%|████████▏ | 21162/25880 [4:19:33<55:25,  1.42it/s]
1|21163|Loss: 0.8545366525650024:  82%|████████▏ | 21163/25880 [4:19:34<55:40,  1.41it/s]
1|21164|Loss: 0.8482437133789062:  82%|████████▏ | 21163/25880 [4:19:34<55:40,  1.41it/s]
1|21164|Loss: 0.8482437133789062:  82%|████████▏ | 21164/25880 [4:19:34<56:10,  1.40it/s]
1|21165|Loss: 0.8554293513298035:  82%|████████▏ | 21164/25880 [4:19:35<56:10,  1.40it/s]
1|21165|Loss: 0.8554293513298035:  82%|████████▏ | 21165/25880 [4:19:35<58:23,  1.35it/s]
1|21166|Loss: 0.9038064479827881:  82%|████████▏ | 21165/25880 [4:19:36<58:23,  1.35it/s]
1|21166|Loss: 0.9038064479827881:  82%|████████▏ | 21166/25880 [4:19:36<1:00:18,  1.30it/s]
1|21167|Loss: 1.03781259059906:  82%|████████▏ | 21166/25880 [4:19:36<1:00:18,  1.30it/s]  
1|21167|Loss: 1.03781259059906:  82%|████████▏ | 21167/25880 [4:19:37<59:59,  1.31it/s]  
1|21168|Loss: 0.8763579726219177:  82%|████████▏ | 21167/25880 [4:19:37<59:59,  1.31it/s]
1|21168|Loss: 0.8763579726219177:  82%|████████▏ | 21168/25880 [4:19:37<57:42,  1.36it/s]
1|21169|Loss: 0.7584306001663208:  82%|████████▏ | 21168/25880 [4:19:38<57:42,  1.36it/s]
1|21169|Loss: 0.7584306001663208:  82%|████████▏ | 21169/25880 [4:19:38<55:06,  1.42it/s]
1|21170|Loss: 0.8104995489120483:  82%|████████▏ | 21169/25880 [4:19:38<55:06,  1.42it/s]
1|21170|Loss: 0.8104995489120483:  82%|████████▏ | 21170/25880 [4:19:39<55:34,  1.41it/s]
1|21171|Loss: 0.8055407404899597:  82%|████████▏ | 21170/25880 [4:19:39<55:34,  1.41it/s]
1|21171|Loss: 0.8055407404899597:  82%|████████▏ | 21171/25880 [4:19:40<58:14,  1.35it/s]
1|21172|Loss: 0.9309256672859192:  82%|████████▏ | 21171/25880 [4:19:40<58:14,  1.35it/s]
1|21172|Loss: 0.9309256672859192:  82%|████████▏ | 21172/25880 [4:19:40<57:47,  1.36it/s]
1|21173|Loss: 0.725091814994812:  82%|████████▏ | 21172/25880 [4:19:41<57:47,  1.36it/s] 
1|21173|Loss: 0.725091814994812:  82%|████████▏ | 21173/25880 [4:19:41<57:30,  1.36it/s]
1|21174|Loss: 0.8933658003807068:  82%|████████▏ | 21173/25880 [4:19:41<57:30,  1.36it/s]
1|21174|Loss: 0.8933658003807068:  82%|████████▏ | 21174/25880 [4:19:42<57:14,  1.37it/s]
1|21175|Loss: 0.6749357581138611:  82%|████████▏ | 21174/25880 [4:19:42<57:14,  1.37it/s]
1|21175|Loss: 0.6749357581138611:  82%|████████▏ | 21175/25880 [4:19:42<54:58,  1.43it/s]
1|21176|Loss: 0.7414544224739075:  82%|████████▏ | 21175/25880 [4:19:43<54:58,  1.43it/s]
1|21176|Loss: 0.7414544224739075:  82%|████████▏ | 21176/25880 [4:19:43<54:45,  1.43it/s]
1|21177|Loss: 0.8656696677207947:  82%|████████▏ | 21176/25880 [4:19:44<54:45,  1.43it/s]
1|21177|Loss: 0.8656696677207947:  82%|████████▏ | 21177/25880 [4:19:44<58:14,  1.35it/s]
1|21178|Loss: 0.7443118095397949:  82%|████████▏ | 21177/25880 [4:19:44<58:14,  1.35it/s]
1|21178|Loss: 0.7443118095397949:  82%|████████▏ | 21178/25880 [4:19:45<53:32,  1.46it/s]
1|21179|Loss: 0.8971299529075623:  82%|████████▏ | 21178/25880 [4:19:45<53:32,  1.46it/s]
1|21179|Loss: 0.8971299529075623:  82%|████████▏ | 21179/25880 [4:19:45<49:54,  1.57it/s]
1|21180|Loss: 0.8456743359565735:  82%|████████▏ | 21179/25880 [4:19:45<49:54,  1.57it/s]
1|21180|Loss: 0.8456743359565735:  82%|████████▏ | 21180/25880 [4:19:46<51:26,  1.52it/s]
1|21181|Loss: 0.9233745336532593:  82%|████████▏ | 21180/25880 [4:19:46<51:26,  1.52it/s]
1|21181|Loss: 0.9233745336532593:  82%|████████▏ | 21181/25880 [4:19:46<51:32,  1.52it/s]
1|21182|Loss: 0.7665390968322754:  82%|████████▏ | 21181/25880 [4:19:47<51:32,  1.52it/s]
1|21182|Loss: 0.7665390968322754:  82%|████████▏ | 21182/25880 [4:19:47<52:46,  1.48it/s]
1|21183|Loss: 0.8903713822364807:  82%|████████▏ | 21182/25880 [4:19:48<52:46,  1.48it/s]
1|21183|Loss: 0.8903713822364807:  82%|████████▏ | 21183/25880 [4:19:48<55:50,  1.40it/s]
1|21184|Loss: 0.9384201169013977:  82%|████████▏ | 21183/25880 [4:19:48<55:50,  1.40it/s]
1|21184|Loss: 0.9384201169013977:  82%|████████▏ | 21184/25880 [4:19:49<58:27,  1.34it/s]
1|21185|Loss: 0.8965505361557007:  82%|████████▏ | 21184/25880 [4:19:49<58:27,  1.34it/s]
1|21185|Loss: 0.8965505361557007:  82%|████████▏ | 21185/25880 [4:19:50<59:36,  1.31it/s]
1|21186|Loss: 0.7222275137901306:  82%|████████▏ | 21185/25880 [4:19:50<59:36,  1.31it/s]
1|21186|Loss: 0.7222275137901306:  82%|████████▏ | 21186/25880 [4:19:50<57:36,  1.36it/s]
1|21187|Loss: 0.8684728741645813:  82%|████████▏ | 21186/25880 [4:19:51<57:36,  1.36it/s]
1|21187|Loss: 0.8684728741645813:  82%|████████▏ | 21187/25880 [4:19:51<56:37,  1.38it/s]
1|21188|Loss: 0.8335002660751343:  82%|████████▏ | 21187/25880 [4:19:51<56:37,  1.38it/s]
1|21188|Loss: 0.8335002660751343:  82%|████████▏ | 21188/25880 [4:19:52<53:14,  1.47it/s]
1|21189|Loss: 0.890051007270813:  82%|████████▏ | 21188/25880 [4:19:52<53:14,  1.47it/s] 
1|21189|Loss: 0.890051007270813:  82%|████████▏ | 21189/25880 [4:19:52<56:11,  1.39it/s]
1|21190|Loss: 0.8587736487388611:  82%|████████▏ | 21189/25880 [4:19:53<56:11,  1.39it/s]
1|21190|Loss: 0.8587736487388611:  82%|████████▏ | 21190/25880 [4:19:53<56:38,  1.38it/s]
1|21191|Loss: 0.9428065419197083:  82%|████████▏ | 21190/25880 [4:19:53<56:38,  1.38it/s]
1|21191|Loss: 0.9428065419197083:  82%|████████▏ | 21191/25880 [4:19:54<56:28,  1.38it/s]
1|21192|Loss: 0.8968657851219177:  82%|████████▏ | 21191/25880 [4:19:54<56:28,  1.38it/s]
1|21192|Loss: 0.8968657851219177:  82%|████████▏ | 21192/25880 [4:19:55<56:56,  1.37it/s]
1|21193|Loss: 0.894790768623352:  82%|████████▏ | 21192/25880 [4:19:55<56:56,  1.37it/s] 
1|21193|Loss: 0.894790768623352:  82%|████████▏ | 21193/25880 [4:19:55<59:33,  1.31it/s]
1|21194|Loss: 0.7754156589508057:  82%|████████▏ | 21193/25880 [4:19:56<59:33,  1.31it/s]
1|21194|Loss: 0.7754156589508057:  82%|████████▏ | 21194/25880 [4:19:56<56:38,  1.38it/s]
1|21195|Loss: 0.9818235635757446:  82%|████████▏ | 21194/25880 [4:19:56<56:38,  1.38it/s]
1|21195|Loss: 0.9818235635757446:  82%|████████▏ | 21195/25880 [4:19:57<51:18,  1.52it/s]
1|21196|Loss: 0.8658220767974854:  82%|████████▏ | 21195/25880 [4:19:57<51:18,  1.52it/s]
1|21196|Loss: 0.8658220767974854:  82%|████████▏ | 21196/25880 [4:19:57<51:11,  1.52it/s]
1|21197|Loss: 0.7900429964065552:  82%|████████▏ | 21196/25880 [4:19:58<51:11,  1.52it/s]
1|21197|Loss: 0.7900429964065552:  82%|████████▏ | 21197/25880 [4:19:58<51:04,  1.53it/s]
1|21198|Loss: 0.658796489238739:  82%|████████▏ | 21197/25880 [4:19:58<51:04,  1.53it/s] 
1|21198|Loss: 0.658796489238739:  82%|████████▏ | 21198/25880 [4:19:58<50:16,  1.55it/s]
1|21199|Loss: 0.840214192867279:  82%|████████▏ | 21198/25880 [4:19:59<50:16,  1.55it/s]
1|21199|Loss: 0.840214192867279:  82%|████████▏ | 21199/25880 [4:19:59<48:53,  1.60it/s]
1|21200|Loss: 0.8025496006011963:  82%|████████▏ | 21199/25880 [4:19:59<48:53,  1.60it/s]
1|21200|Loss: 0.8025496006011963:  82%|████████▏ | 21200/25880 [4:20:00<50:32,  1.54it/s]
1|21201|Loss: 0.8592579960823059:  82%|████████▏ | 21200/25880 [4:20:00<50:32,  1.54it/s]
1|21201|Loss: 0.8592579960823059:  82%|████████▏ | 21201/25880 [4:20:01<54:15,  1.44it/s]
1|21202|Loss: 0.7658702731132507:  82%|████████▏ | 21201/25880 [4:20:01<54:15,  1.44it/s]
1|21202|Loss: 0.7658702731132507:  82%|████████▏ | 21202/25880 [4:20:01<53:49,  1.45it/s]
1|21203|Loss: 0.9751905202865601:  82%|████████▏ | 21202/25880 [4:20:02<53:49,  1.45it/s]
1|21203|Loss: 0.9751905202865601:  82%|████████▏ | 21203/25880 [4:20:02<50:31,  1.54it/s]
1|21204|Loss: 0.8340066075325012:  82%|████████▏ | 21203/25880 [4:20:02<50:31,  1.54it/s]
1|21204|Loss: 0.8340066075325012:  82%|████████▏ | 21204/25880 [4:20:02<48:27,  1.61it/s]
1|21205|Loss: 0.8902804851531982:  82%|████████▏ | 21204/25880 [4:20:03<48:27,  1.61it/s]
1|21205|Loss: 0.8902804851531982:  82%|████████▏ | 21205/25880 [4:20:03<45:00,  1.73it/s]
1|21206|Loss: 0.7470296025276184:  82%|████████▏ | 21205/25880 [4:20:03<45:00,  1.73it/s]
1|21206|Loss: 0.7470296025276184:  82%|████████▏ | 21206/25880 [4:20:03<44:53,  1.74it/s]
1|21207|Loss: 0.8236115574836731:  82%|████████▏ | 21206/25880 [4:20:04<44:53,  1.74it/s]
1|21207|Loss: 0.8236115574836731:  82%|████████▏ | 21207/25880 [4:20:04<50:50,  1.53it/s]
1|21208|Loss: 0.8681603074073792:  82%|████████▏ | 21207/25880 [4:20:05<50:50,  1.53it/s]
1|21208|Loss: 0.8681603074073792:  82%|████████▏ | 21208/25880 [4:20:05<53:26,  1.46it/s]
1|21209|Loss: 0.8390445113182068:  82%|████████▏ | 21208/25880 [4:20:05<53:26,  1.46it/s]
1|21209|Loss: 0.8390445113182068:  82%|████████▏ | 21209/25880 [4:20:06<52:12,  1.49it/s]
1|21210|Loss: 0.8974238038063049:  82%|████████▏ | 21209/25880 [4:20:06<52:12,  1.49it/s]
1|21210|Loss: 0.8974238038063049:  82%|████████▏ | 21210/25880 [4:20:06<56:24,  1.38it/s]
1|21211|Loss: 0.8539503216743469:  82%|████████▏ | 21210/25880 [4:20:07<56:24,  1.38it/s]
1|21211|Loss: 0.8539503216743469:  82%|████████▏ | 21211/25880 [4:20:07<56:50,  1.37it/s]
1|21212|Loss: 0.8321788311004639:  82%|████████▏ | 21211/25880 [4:20:08<56:50,  1.37it/s]
1|21212|Loss: 0.8321788311004639:  82%|████████▏ | 21212/25880 [4:20:08<56:55,  1.37it/s]
1|21213|Loss: 0.8142342567443848:  82%|████████▏ | 21212/25880 [4:20:08<56:55,  1.37it/s]
1|21213|Loss: 0.8142342567443848:  82%|████████▏ | 21213/25880 [4:20:09<56:26,  1.38it/s]
1|21214|Loss: 0.8919551968574524:  82%|████████▏ | 21213/25880 [4:20:09<56:26,  1.38it/s]
1|21214|Loss: 0.8919551968574524:  82%|████████▏ | 21214/25880 [4:20:10<59:59,  1.30it/s]
1|21215|Loss: 0.8488830924034119:  82%|████████▏ | 21214/25880 [4:20:10<59:59,  1.30it/s]
1|21215|Loss: 0.8488830924034119:  82%|████████▏ | 21215/25880 [4:20:10<59:16,  1.31it/s]
1|21216|Loss: 0.9087201356887817:  82%|████████▏ | 21215/25880 [4:20:11<59:16,  1.31it/s]
1|21216|Loss: 0.9087201356887817:  82%|████████▏ | 21216/25880 [4:20:11<58:23,  1.33it/s]
1|21217|Loss: 0.8666852116584778:  82%|████████▏ | 21216/25880 [4:20:11<58:23,  1.33it/s]
1|21217|Loss: 0.8666852116584778:  82%|████████▏ | 21217/25880 [4:20:12<59:44,  1.30it/s]
1|21218|Loss: 0.8561757206916809:  82%|████████▏ | 21217/25880 [4:20:12<59:44,  1.30it/s]
1|21218|Loss: 0.8561757206916809:  82%|████████▏ | 21218/25880 [4:20:12<57:36,  1.35it/s]
1|21219|Loss: 0.8098064064979553:  82%|████████▏ | 21218/25880 [4:20:13<57:36,  1.35it/s]
1|21219|Loss: 0.8098064064979553:  82%|████████▏ | 21219/25880 [4:20:13<59:35,  1.30it/s]
1|21220|Loss: 0.9320721626281738:  82%|████████▏ | 21219/25880 [4:20:14<59:35,  1.30it/s]
1|21220|Loss: 0.9320721626281738:  82%|████████▏ | 21220/25880 [4:20:14<54:18,  1.43it/s]
1|21221|Loss: 0.8657057285308838:  82%|████████▏ | 21220/25880 [4:20:14<54:18,  1.43it/s]
1|21221|Loss: 0.8657057285308838:  82%|████████▏ | 21221/25880 [4:20:15<53:49,  1.44it/s]
1|21222|Loss: 0.9116013050079346:  82%|████████▏ | 21221/25880 [4:20:15<53:49,  1.44it/s]
1|21222|Loss: 0.9116013050079346:  82%|████████▏ | 21222/25880 [4:20:15<56:41,  1.37it/s]
1|21223|Loss: 0.8503120541572571:  82%|████████▏ | 21222/25880 [4:20:16<56:41,  1.37it/s]
1|21223|Loss: 0.8503120541572571:  82%|████████▏ | 21223/25880 [4:20:16<58:13,  1.33it/s]
1|21224|Loss: 0.9211330413818359:  82%|████████▏ | 21223/25880 [4:20:17<58:13,  1.33it/s]
1|21224|Loss: 0.9211330413818359:  82%|████████▏ | 21224/25880 [4:20:17<58:11,  1.33it/s]
1|21225|Loss: 0.8031049370765686:  82%|████████▏ | 21224/25880 [4:20:17<58:11,  1.33it/s]
1|21225|Loss: 0.8031049370765686:  82%|████████▏ | 21225/25880 [4:20:18<56:06,  1.38it/s]
1|21226|Loss: 0.8244954943656921:  82%|████████▏ | 21225/25880 [4:20:18<56:06,  1.38it/s]
1|21226|Loss: 0.8244954943656921:  82%|████████▏ | 21226/25880 [4:20:18<54:13,  1.43it/s]
1|21227|Loss: 0.7576498985290527:  82%|████████▏ | 21226/25880 [4:20:19<54:13,  1.43it/s]
1|21227|Loss: 0.7576498985290527:  82%|████████▏ | 21227/25880 [4:20:19<52:51,  1.47it/s]
1|21228|Loss: 0.9115768671035767:  82%|████████▏ | 21227/25880 [4:20:19<52:51,  1.47it/s]
1|21228|Loss: 0.9115768671035767:  82%|████████▏ | 21228/25880 [4:20:20<53:36,  1.45it/s]
1|21229|Loss: 0.8046788573265076:  82%|████████▏ | 21228/25880 [4:20:20<53:36,  1.45it/s]
1|21229|Loss: 0.8046788573265076:  82%|████████▏ | 21229/25880 [4:20:20<52:16,  1.48it/s]
1|21230|Loss: 0.6800908446311951:  82%|████████▏ | 21229/25880 [4:20:21<52:16,  1.48it/s]
1|21230|Loss: 0.6800908446311951:  82%|████████▏ | 21230/25880 [4:20:21<52:31,  1.48it/s]
1|21231|Loss: 0.9148417115211487:  82%|████████▏ | 21230/25880 [4:20:21<52:31,  1.48it/s]
1|21231|Loss: 0.9148417115211487:  82%|████████▏ | 21231/25880 [4:20:22<52:54,  1.46it/s]
1|21232|Loss: 0.908655047416687:  82%|████████▏ | 21231/25880 [4:20:22<52:54,  1.46it/s] 
1|21232|Loss: 0.908655047416687:  82%|████████▏ | 21232/25880 [4:20:22<51:40,  1.50it/s]
1|21233|Loss: 0.8636447191238403:  82%|████████▏ | 21232/25880 [4:20:23<51:40,  1.50it/s]
1|21233|Loss: 0.8636447191238403:  82%|████████▏ | 21233/25880 [4:20:23<54:50,  1.41it/s]
1|21234|Loss: 0.8296570181846619:  82%|████████▏ | 21233/25880 [4:20:23<54:50,  1.41it/s]
1|21234|Loss: 0.8296570181846619:  82%|████████▏ | 21234/25880 [4:20:24<53:52,  1.44it/s]
1|21235|Loss: 0.8797839283943176:  82%|████████▏ | 21234/25880 [4:20:24<53:52,  1.44it/s]
1|21235|Loss: 0.8797839283943176:  82%|████████▏ | 21235/25880 [4:20:24<51:57,  1.49it/s]
1|21236|Loss: 0.9225869178771973:  82%|████████▏ | 21235/25880 [4:20:25<51:57,  1.49it/s]
1|21236|Loss: 0.9225869178771973:  82%|████████▏ | 21236/25880 [4:20:25<50:04,  1.55it/s]
1|21237|Loss: 0.8779350519180298:  82%|████████▏ | 21236/25880 [4:20:25<50:04,  1.55it/s]
1|21237|Loss: 0.8779350519180298:  82%|████████▏ | 21237/25880 [4:20:26<51:17,  1.51it/s]
1|21238|Loss: 0.9013264775276184:  82%|████████▏ | 21237/25880 [4:20:26<51:17,  1.51it/s]
1|21238|Loss: 0.9013264775276184:  82%|████████▏ | 21238/25880 [4:20:26<54:37,  1.42it/s]
1|21239|Loss: 0.9809136390686035:  82%|████████▏ | 21238/25880 [4:20:27<54:37,  1.42it/s]
1|21239|Loss: 0.9809136390686035:  82%|████████▏ | 21239/25880 [4:20:27<55:55,  1.38it/s]
1|21240|Loss: 0.7559847235679626:  82%|████████▏ | 21239/25880 [4:20:28<55:55,  1.38it/s]
1|21240|Loss: 0.7559847235679626:  82%|████████▏ | 21240/25880 [4:20:28<56:13,  1.38it/s]
1|21241|Loss: 1.024827480316162:  82%|████████▏ | 21240/25880 [4:20:28<56:13,  1.38it/s] 
1|21241|Loss: 1.024827480316162:  82%|████████▏ | 21241/25880 [4:20:28<53:35,  1.44it/s]
1|21242|Loss: 0.8289582133293152:  82%|████████▏ | 21241/25880 [4:20:29<53:35,  1.44it/s]
1|21242|Loss: 0.8289582133293152:  82%|████████▏ | 21242/25880 [4:20:29<51:56,  1.49it/s]
1|21243|Loss: 0.9342031478881836:  82%|████████▏ | 21242/25880 [4:20:29<51:56,  1.49it/s]
1|21243|Loss: 0.9342031478881836:  82%|████████▏ | 21243/25880 [4:20:30<47:44,  1.62it/s]
1|21244|Loss: 0.7605052590370178:  82%|████████▏ | 21243/25880 [4:20:30<47:44,  1.62it/s]
1|21244|Loss: 0.7605052590370178:  82%|████████▏ | 21244/25880 [4:20:30<50:23,  1.53it/s]
1|21245|Loss: 0.9196705222129822:  82%|████████▏ | 21244/25880 [4:20:31<50:23,  1.53it/s]
1|21245|Loss: 0.9196705222129822:  82%|████████▏ | 21245/25880 [4:20:31<50:32,  1.53it/s]
1|21246|Loss: 0.904987633228302:  82%|████████▏ | 21245/25880 [4:20:31<50:32,  1.53it/s] 
1|21246|Loss: 0.904987633228302:  82%|████████▏ | 21246/25880 [4:20:32<49:59,  1.54it/s]
1|21247|Loss: 0.6617987751960754:  82%|████████▏ | 21246/25880 [4:20:32<49:59,  1.54it/s]
1|21247|Loss: 0.6617987751960754:  82%|████████▏ | 21247/25880 [4:20:32<52:32,  1.47it/s]
1|21248|Loss: 0.7853705286979675:  82%|████████▏ | 21247/25880 [4:20:33<52:32,  1.47it/s]
1|21248|Loss: 0.7853705286979675:  82%|████████▏ | 21248/25880 [4:20:33<55:52,  1.38it/s]
1|21249|Loss: 0.8034581542015076:  82%|████████▏ | 21248/25880 [4:20:34<55:52,  1.38it/s]
1|21249|Loss: 0.8034581542015076:  82%|████████▏ | 21249/25880 [4:20:34<54:49,  1.41it/s]
1|21250|Loss: 0.7654030919075012:  82%|████████▏ | 21249/25880 [4:20:34<54:49,  1.41it/s]
1|21250|Loss: 0.7654030919075012:  82%|████████▏ | 21250/25880 [4:20:35<53:08,  1.45it/s]
1|21251|Loss: 0.9321922063827515:  82%|████████▏ | 21250/25880 [4:20:35<53:08,  1.45it/s]
1|21251|Loss: 0.9321922063827515:  82%|████████▏ | 21251/25880 [4:20:35<54:41,  1.41it/s]
1|21252|Loss: 0.704862654209137:  82%|████████▏ | 21251/25880 [4:20:36<54:41,  1.41it/s] 
1|21252|Loss: 0.704862654209137:  82%|████████▏ | 21252/25880 [4:20:36<51:51,  1.49it/s]
1|21253|Loss: 0.9075986742973328:  82%|████████▏ | 21252/25880 [4:20:36<51:51,  1.49it/s]
1|21253|Loss: 0.9075986742973328:  82%|████████▏ | 21253/25880 [4:20:37<52:06,  1.48it/s]
1|21254|Loss: 0.8892034888267517:  82%|████████▏ | 21253/25880 [4:20:37<52:06,  1.48it/s]
1|21254|Loss: 0.8892034888267517:  82%|████████▏ | 21254/25880 [4:20:37<53:36,  1.44it/s]
1|21255|Loss: 0.8750768899917603:  82%|████████▏ | 21254/25880 [4:20:38<53:36,  1.44it/s]
1|21255|Loss: 0.8750768899917603:  82%|████████▏ | 21255/25880 [4:20:38<54:35,  1.41it/s]
1|21256|Loss: 0.8609368801116943:  82%|████████▏ | 21255/25880 [4:20:38<54:35,  1.41it/s]
1|21256|Loss: 0.8609368801116943:  82%|████████▏ | 21256/25880 [4:20:39<56:24,  1.37it/s]
1|21257|Loss: 0.8978311419487:  82%|████████▏ | 21256/25880 [4:20:39<56:24,  1.37it/s]   
1|21257|Loss: 0.8978311419487:  82%|████████▏ | 21257/25880 [4:20:39<53:27,  1.44it/s]
1|21258|Loss: 0.9448155164718628:  82%|████████▏ | 21257/25880 [4:20:40<53:27,  1.44it/s]
1|21258|Loss: 0.9448155164718628:  82%|████████▏ | 21258/25880 [4:20:40<50:12,  1.53it/s]
1|21259|Loss: 0.8875837922096252:  82%|████████▏ | 21258/25880 [4:20:40<50:12,  1.53it/s]
1|21259|Loss: 0.8875837922096252:  82%|████████▏ | 21259/25880 [4:20:41<50:41,  1.52it/s]
1|21260|Loss: 0.8323240876197815:  82%|████████▏ | 21259/25880 [4:20:41<50:41,  1.52it/s]
1|21260|Loss: 0.8323240876197815:  82%|████████▏ | 21260/25880 [4:20:41<53:30,  1.44it/s]
1|21261|Loss: 0.7769526839256287:  82%|████████▏ | 21260/25880 [4:20:42<53:30,  1.44it/s]
1|21261|Loss: 0.7769526839256287:  82%|████████▏ | 21261/25880 [4:20:42<54:32,  1.41it/s]
1|21262|Loss: 0.957596480846405:  82%|████████▏ | 21261/25880 [4:20:43<54:32,  1.41it/s] 
1|21262|Loss: 0.957596480846405:  82%|████████▏ | 21262/25880 [4:20:43<58:20,  1.32it/s]
1|21263|Loss: 0.9626899361610413:  82%|████████▏ | 21262/25880 [4:20:43<58:20,  1.32it/s]
1|21263|Loss: 0.9626899361610413:  82%|████████▏ | 21263/25880 [4:20:44<59:53,  1.28it/s]
1|21264|Loss: 0.8191022872924805:  82%|████████▏ | 21263/25880 [4:20:44<59:53,  1.28it/s]
1|21264|Loss: 0.8191022872924805:  82%|████████▏ | 21264/25880 [4:20:45<57:23,  1.34it/s]
1|21265|Loss: 0.7395203113555908:  82%|████████▏ | 21264/25880 [4:20:45<57:23,  1.34it/s]
1|21265|Loss: 0.7395203113555908:  82%|████████▏ | 21265/25880 [4:20:45<58:57,  1.30it/s]
1|21266|Loss: 0.8874406814575195:  82%|████████▏ | 21265/25880 [4:20:46<58:57,  1.30it/s]
1|21266|Loss: 0.8874406814575195:  82%|████████▏ | 21266/25880 [4:20:46<57:09,  1.35it/s]
1|21267|Loss: 0.8317236304283142:  82%|████████▏ | 21266/25880 [4:20:46<57:09,  1.35it/s]
1|21267|Loss: 0.8317236304283142:  82%|████████▏ | 21267/25880 [4:20:47<56:30,  1.36it/s]
1|21268|Loss: 0.8433949947357178:  82%|████████▏ | 21267/25880 [4:20:47<56:30,  1.36it/s]
1|21268|Loss: 0.8433949947357178:  82%|████████▏ | 21268/25880 [4:20:47<56:31,  1.36it/s]
1|21269|Loss: 0.7879269123077393:  82%|████████▏ | 21268/25880 [4:20:48<56:31,  1.36it/s]
1|21269|Loss: 0.7879269123077393:  82%|████████▏ | 21269/25880 [4:20:48<54:27,  1.41it/s]
1|21270|Loss: 0.8578388094902039:  82%|████████▏ | 21269/25880 [4:20:49<54:27,  1.41it/s]
1|21270|Loss: 0.8578388094902039:  82%|████████▏ | 21270/25880 [4:20:49<56:06,  1.37it/s]
1|21271|Loss: 1.065627098083496:  82%|████████▏ | 21270/25880 [4:20:49<56:06,  1.37it/s] 
1|21271|Loss: 1.065627098083496:  82%|████████▏ | 21271/25880 [4:20:49<52:51,  1.45it/s]
1|21272|Loss: 0.9054828882217407:  82%|████████▏ | 21271/25880 [4:20:50<52:51,  1.45it/s]
1|21272|Loss: 0.9054828882217407:  82%|████████▏ | 21272/25880 [4:20:50<53:58,  1.42it/s]
1|21273|Loss: 0.870702862739563:  82%|████████▏ | 21272/25880 [4:20:51<53:58,  1.42it/s] 
1|21273|Loss: 0.870702862739563:  82%|████████▏ | 21273/25880 [4:20:51<52:29,  1.46it/s]
1|21274|Loss: 0.768281102180481:  82%|████████▏ | 21273/25880 [4:20:51<52:29,  1.46it/s]
1|21274|Loss: 0.768281102180481:  82%|████████▏ | 21274/25880 [4:20:52<54:55,  1.40it/s]
1|21275|Loss: 0.9339651465415955:  82%|████████▏ | 21274/25880 [4:20:52<54:55,  1.40it/s]
1|21275|Loss: 0.9339651465415955:  82%|████████▏ | 21275/25880 [4:20:53<58:42,  1.31it/s]
1|21276|Loss: 0.9380979537963867:  82%|████████▏ | 21275/25880 [4:20:53<58:42,  1.31it/s]
1|21276|Loss: 0.9380979537963867:  82%|████████▏ | 21276/25880 [4:20:53<58:55,  1.30it/s]
1|21277|Loss: 0.836478590965271:  82%|████████▏ | 21276/25880 [4:20:54<58:55,  1.30it/s] 
1|21277|Loss: 0.836478590965271:  82%|████████▏ | 21277/25880 [4:20:54<57:35,  1.33it/s]
1|21278|Loss: 0.9902372360229492:  82%|████████▏ | 21277/25880 [4:20:54<57:35,  1.33it/s]
1|21278|Loss: 0.9902372360229492:  82%|████████▏ | 21278/25880 [4:20:55<52:48,  1.45it/s]
1|21279|Loss: 0.7231572270393372:  82%|████████▏ | 21278/25880 [4:20:55<52:48,  1.45it/s]
1|21279|Loss: 0.7231572270393372:  82%|████████▏ | 21279/25880 [4:20:55<50:31,  1.52it/s]
1|21280|Loss: 0.9205185174942017:  82%|████████▏ | 21279/25880 [4:20:56<50:31,  1.52it/s]
1|21280|Loss: 0.9205185174942017:  82%|████████▏ | 21280/25880 [4:20:56<53:25,  1.43it/s]
1|21281|Loss: 0.8188908696174622:  82%|████████▏ | 21280/25880 [4:20:56<53:25,  1.43it/s]
1|21281|Loss: 0.8188908696174622:  82%|████████▏ | 21281/25880 [4:20:57<52:04,  1.47it/s]
1|21282|Loss: 0.8021547198295593:  82%|████████▏ | 21281/25880 [4:20:57<52:04,  1.47it/s]
1|21282|Loss: 0.8021547198295593:  82%|████████▏ | 21282/25880 [4:20:57<52:32,  1.46it/s]
1|21283|Loss: 0.7874653935432434:  82%|████████▏ | 21282/25880 [4:20:58<52:32,  1.46it/s]
1|21283|Loss: 0.7874653935432434:  82%|████████▏ | 21283/25880 [4:20:58<51:56,  1.48it/s]
1|21284|Loss: 0.7191837430000305:  82%|████████▏ | 21283/25880 [4:20:58<51:56,  1.48it/s]
1|21284|Loss: 0.7191837430000305:  82%|████████▏ | 21284/25880 [4:20:59<52:12,  1.47it/s]
1|21285|Loss: 0.7891317009925842:  82%|████████▏ | 21284/25880 [4:20:59<52:12,  1.47it/s]
1|21285|Loss: 0.7891317009925842:  82%|████████▏ | 21285/25880 [4:20:59<51:30,  1.49it/s]
1|21286|Loss: 0.8488643765449524:  82%|████████▏ | 21285/25880 [4:21:00<51:30,  1.49it/s]
1|21286|Loss: 0.8488643765449524:  82%|████████▏ | 21286/25880 [4:21:00<47:21,  1.62it/s]
1|21287|Loss: 0.7875894904136658:  82%|████████▏ | 21286/25880 [4:21:00<47:21,  1.62it/s]
1|21287|Loss: 0.7875894904136658:  82%|████████▏ | 21287/25880 [4:21:01<50:28,  1.52it/s]
1|21288|Loss: 0.8052883148193359:  82%|████████▏ | 21287/25880 [4:21:01<50:28,  1.52it/s]
1|21288|Loss: 0.8052883148193359:  82%|████████▏ | 21288/25880 [4:21:01<52:05,  1.47it/s]
1|21289|Loss: 0.9721798896789551:  82%|████████▏ | 21288/25880 [4:21:02<52:05,  1.47it/s]
1|21289|Loss: 0.9721798896789551:  82%|████████▏ | 21289/25880 [4:21:02<52:30,  1.46it/s]
1|21290|Loss: 0.7564246654510498:  82%|████████▏ | 21289/25880 [4:21:02<52:30,  1.46it/s]
1|21290|Loss: 0.7564246654510498:  82%|████████▏ | 21290/25880 [4:21:03<51:13,  1.49it/s]
1|21291|Loss: 0.9665400981903076:  82%|████████▏ | 21290/25880 [4:21:03<51:13,  1.49it/s]
1|21291|Loss: 0.9665400981903076:  82%|████████▏ | 21291/25880 [4:21:03<53:56,  1.42it/s]
1|21292|Loss: 0.7711388468742371:  82%|████████▏ | 21291/25880 [4:21:04<53:56,  1.42it/s]
1|21292|Loss: 0.7711388468742371:  82%|████████▏ | 21292/25880 [4:21:04<56:40,  1.35it/s]
1|21293|Loss: 0.8924258947372437:  82%|████████▏ | 21292/25880 [4:21:05<56:40,  1.35it/s]
1|21293|Loss: 0.8924258947372437:  82%|████████▏ | 21293/25880 [4:21:05<54:41,  1.40it/s]
1|21294|Loss: 0.7266987562179565:  82%|████████▏ | 21293/25880 [4:21:05<54:41,  1.40it/s]
1|21294|Loss: 0.7266987562179565:  82%|████████▏ | 21294/25880 [4:21:06<56:47,  1.35it/s]
1|21295|Loss: 0.8188003301620483:  82%|████████▏ | 21294/25880 [4:21:06<56:47,  1.35it/s]
1|21295|Loss: 0.8188003301620483:  82%|████████▏ | 21295/25880 [4:21:06<56:33,  1.35it/s]
1|21296|Loss: 0.9338160157203674:  82%|████████▏ | 21295/25880 [4:21:07<56:33,  1.35it/s]
1|21296|Loss: 0.9338160157203674:  82%|████████▏ | 21296/25880 [4:21:07<55:42,  1.37it/s]
1|21297|Loss: 0.8089783191680908:  82%|████████▏ | 21296/25880 [4:21:08<55:42,  1.37it/s]
1|21297|Loss: 0.8089783191680908:  82%|████████▏ | 21297/25880 [4:21:08<58:59,  1.29it/s]
1|21298|Loss: 0.7835867404937744:  82%|████████▏ | 21297/25880 [4:21:08<58:59,  1.29it/s]
1|21298|Loss: 0.7835867404937744:  82%|████████▏ | 21298/25880 [4:21:09<56:48,  1.34it/s]
1|21299|Loss: 0.847343921661377:  82%|████████▏ | 21298/25880 [4:21:09<56:48,  1.34it/s] 
1|21299|Loss: 0.847343921661377:  82%|████████▏ | 21299/25880 [4:21:09<55:55,  1.37it/s]
1|21300|Loss: 0.7942726612091064:  82%|████████▏ | 21299/25880 [4:21:10<55:55,  1.37it/s]
1|21300|Loss: 0.7942726612091064:  82%|████████▏ | 21300/25880 [4:21:10<57:41,  1.32it/s]
1|21301|Loss: 0.7154831290245056:  82%|████████▏ | 21300/25880 [4:21:11<57:41,  1.32it/s]
1|21301|Loss: 0.7154831290245056:  82%|████████▏ | 21301/25880 [4:21:11<1:01:55,  1.23it/s]
1|21302|Loss: 0.8708301186561584:  82%|████████▏ | 21301/25880 [4:21:12<1:01:55,  1.23it/s]
1|21302|Loss: 0.8708301186561584:  82%|████████▏ | 21302/25880 [4:21:12<1:01:19,  1.24it/s]
1|21303|Loss: 0.8578614592552185:  82%|████████▏ | 21302/25880 [4:21:12<1:01:19,  1.24it/s]
1|21303|Loss: 0.8578614592552185:  82%|████████▏ | 21303/25880 [4:21:13<56:58,  1.34it/s]  
1|21304|Loss: 0.8705810904502869:  82%|████████▏ | 21303/25880 [4:21:13<56:58,  1.34it/s]
1|21304|Loss: 0.8705810904502869:  82%|████████▏ | 21304/25880 [4:21:13<55:50,  1.37it/s]
1|21305|Loss: 0.8398347496986389:  82%|████████▏ | 21304/25880 [4:21:14<55:50,  1.37it/s]
1|21305|Loss: 0.8398347496986389:  82%|████████▏ | 21305/25880 [4:21:14<53:43,  1.42it/s]
1|21306|Loss: 0.6799845695495605:  82%|████████▏ | 21305/25880 [4:21:14<53:43,  1.42it/s]
1|21306|Loss: 0.6799845695495605:  82%|████████▏ | 21306/25880 [4:21:14<51:56,  1.47it/s]
1|21307|Loss: 0.7609128355979919:  82%|████████▏ | 21306/25880 [4:21:15<51:56,  1.47it/s]
1|21307|Loss: 0.7609128355979919:  82%|████████▏ | 21307/25880 [4:21:15<54:56,  1.39it/s]
1|21308|Loss: 0.8091223835945129:  82%|████████▏ | 21307/25880 [4:21:16<54:56,  1.39it/s]
1|21308|Loss: 0.8091223835945129:  82%|████████▏ | 21308/25880 [4:21:16<55:24,  1.38it/s]
1|21309|Loss: 0.7961240410804749:  82%|████████▏ | 21308/25880 [4:21:16<55:24,  1.38it/s]
1|21309|Loss: 0.7961240410804749:  82%|████████▏ | 21309/25880 [4:21:17<55:20,  1.38it/s]
1|21310|Loss: 0.896705687046051:  82%|████████▏ | 21309/25880 [4:21:17<55:20,  1.38it/s] 
1|21310|Loss: 0.896705687046051:  82%|████████▏ | 21310/25880 [4:21:17<55:43,  1.37it/s]
1|21311|Loss: 0.9421169757843018:  82%|████████▏ | 21310/25880 [4:21:18<55:43,  1.37it/s]
1|21311|Loss: 0.9421169757843018:  82%|████████▏ | 21311/25880 [4:21:18<55:50,  1.36it/s]
1|21312|Loss: 0.9136201739311218:  82%|████████▏ | 21311/25880 [4:21:19<55:50,  1.36it/s]
1|21312|Loss: 0.9136201739311218:  82%|████████▏ | 21312/25880 [4:21:19<53:35,  1.42it/s]
1|21313|Loss: 0.787824273109436:  82%|████████▏ | 21312/25880 [4:21:19<53:35,  1.42it/s] 
1|21313|Loss: 0.787824273109436:  82%|████████▏ | 21313/25880 [4:21:20<54:46,  1.39it/s]
1|21314|Loss: 0.836056649684906:  82%|████████▏ | 21313/25880 [4:21:20<54:46,  1.39it/s]
1|21314|Loss: 0.836056649684906:  82%|████████▏ | 21314/25880 [4:21:20<56:46,  1.34it/s]
1|21315|Loss: 0.8391232490539551:  82%|████████▏ | 21314/25880 [4:21:21<56:46,  1.34it/s]
1|21315|Loss: 0.8391232490539551:  82%|████████▏ | 21315/25880 [4:21:21<59:25,  1.28it/s]
1|21316|Loss: 0.8646581172943115:  82%|████████▏ | 21315/25880 [4:21:22<59:25,  1.28it/s]
1|21316|Loss: 0.8646581172943115:  82%|████████▏ | 21316/25880 [4:21:22<55:52,  1.36it/s]
1|21317|Loss: 0.9413641095161438:  82%|████████▏ | 21316/25880 [4:21:22<55:52,  1.36it/s]
1|21317|Loss: 0.9413641095161438:  82%|████████▏ | 21317/25880 [4:21:23<52:32,  1.45it/s]
1|21318|Loss: 0.7801276445388794:  82%|████████▏ | 21317/25880 [4:21:23<52:32,  1.45it/s]
1|21318|Loss: 0.7801276445388794:  82%|████████▏ | 21318/25880 [4:21:23<57:02,  1.33it/s]
1|21319|Loss: 0.7996513843536377:  82%|████████▏ | 21318/25880 [4:21:24<57:02,  1.33it/s]
1|21319|Loss: 0.7996513843536377:  82%|████████▏ | 21319/25880 [4:21:24<59:46,  1.27it/s]
1|21320|Loss: 0.8043484091758728:  82%|████████▏ | 21319/25880 [4:21:25<59:46,  1.27it/s]
1|21320|Loss: 0.8043484091758728:  82%|████████▏ | 21320/25880 [4:21:25<56:33,  1.34it/s]
1|21321|Loss: 0.8753577470779419:  82%|████████▏ | 21320/25880 [4:21:25<56:33,  1.34it/s]
1|21321|Loss: 0.8753577470779419:  82%|████████▏ | 21321/25880 [4:21:26<55:36,  1.37it/s]
1|21322|Loss: 0.7461491823196411:  82%|████████▏ | 21321/25880 [4:21:26<55:36,  1.37it/s]
1|21322|Loss: 0.7461491823196411:  82%|████████▏ | 21322/25880 [4:21:26<55:11,  1.38it/s]
1|21323|Loss: 0.8496009111404419:  82%|████████▏ | 21322/25880 [4:21:27<55:11,  1.38it/s]
1|21323|Loss: 0.8496009111404419:  82%|████████▏ | 21323/25880 [4:21:27<55:29,  1.37it/s]
1|21324|Loss: 0.7768979668617249:  82%|████████▏ | 21323/25880 [4:21:27<55:29,  1.37it/s]
1|21324|Loss: 0.7768979668617249:  82%|████████▏ | 21324/25880 [4:21:28<51:13,  1.48it/s]
1|21325|Loss: 0.7535213232040405:  82%|████████▏ | 21324/25880 [4:21:28<51:13,  1.48it/s]
1|21325|Loss: 0.7535213232040405:  82%|████████▏ | 21325/25880 [4:21:28<54:03,  1.40it/s]
1|21326|Loss: 0.8219854235649109:  82%|████████▏ | 21325/25880 [4:21:29<54:03,  1.40it/s]
1|21326|Loss: 0.8219854235649109:  82%|████████▏ | 21326/25880 [4:21:29<57:04,  1.33it/s]
1|21327|Loss: 0.9005206227302551:  82%|████████▏ | 21326/25880 [4:21:30<57:04,  1.33it/s]
1|21327|Loss: 0.9005206227302551:  82%|████████▏ | 21327/25880 [4:21:30<57:25,  1.32it/s]
1|21328|Loss: 0.7295809984207153:  82%|████████▏ | 21327/25880 [4:21:30<57:25,  1.32it/s]
1|21328|Loss: 0.7295809984207153:  82%|████████▏ | 21328/25880 [4:21:31<57:08,  1.33it/s]
1|21329|Loss: 0.8032688498497009:  82%|████████▏ | 21328/25880 [4:21:31<57:08,  1.33it/s]
1|21329|Loss: 0.8032688498497009:  82%|████████▏ | 21329/25880 [4:21:31<54:50,  1.38it/s]
1|21330|Loss: 0.884144127368927:  82%|████████▏ | 21329/25880 [4:21:32<54:50,  1.38it/s] 
1|21330|Loss: 0.884144127368927:  82%|████████▏ | 21330/25880 [4:21:32<56:49,  1.33it/s]
1|21331|Loss: 0.8942153453826904:  82%|████████▏ | 21330/25880 [4:21:33<56:49,  1.33it/s]
1|21331|Loss: 0.8942153453826904:  82%|████████▏ | 21331/25880 [4:21:33<1:00:14,  1.26it/s]
1|21332|Loss: 0.785380482673645:  82%|████████▏ | 21331/25880 [4:21:34<1:00:14,  1.26it/s] 
1|21332|Loss: 0.785380482673645:  82%|████████▏ | 21332/25880 [4:21:34<1:01:00,  1.24it/s]
1|21333|Loss: 0.9038748741149902:  82%|████████▏ | 21332/25880 [4:21:34<1:01:00,  1.24it/s]
1|21333|Loss: 0.9038748741149902:  82%|████████▏ | 21333/25880 [4:21:35<1:01:44,  1.23it/s]
1|21334|Loss: 0.8287559747695923:  82%|████████▏ | 21333/25880 [4:21:35<1:01:44,  1.23it/s]
1|21334|Loss: 0.8287559747695923:  82%|████████▏ | 21334/25880 [4:21:36<1:03:16,  1.20it/s]
1|21335|Loss: 0.8734150528907776:  82%|████████▏ | 21334/25880 [4:21:36<1:03:16,  1.20it/s]
1|21335|Loss: 0.8734150528907776:  82%|████████▏ | 21335/25880 [4:21:36<57:14,  1.32it/s]  
1|21336|Loss: 0.7781636714935303:  82%|████████▏ | 21335/25880 [4:21:37<57:14,  1.32it/s]
1|21336|Loss: 0.7781636714935303:  82%|████████▏ | 21336/25880 [4:21:37<58:10,  1.30it/s]
1|21337|Loss: 0.8610106706619263:  82%|████████▏ | 21336/25880 [4:21:37<58:10,  1.30it/s]
1|21337|Loss: 0.8610106706619263:  82%|████████▏ | 21337/25880 [4:21:38<54:54,  1.38it/s]
1|21338|Loss: 0.8180003762245178:  82%|████████▏ | 21337/25880 [4:21:38<54:54,  1.38it/s]
1|21338|Loss: 0.8180003762245178:  82%|████████▏ | 21338/25880 [4:21:38<55:08,  1.37it/s]
1|21339|Loss: 0.8249876499176025:  82%|████████▏ | 21338/25880 [4:21:39<55:08,  1.37it/s]
1|21339|Loss: 0.8249876499176025:  82%|████████▏ | 21339/25880 [4:21:39<55:39,  1.36it/s]
1|21340|Loss: 1.0271661281585693:  82%|████████▏ | 21339/25880 [4:21:40<55:39,  1.36it/s]
1|21340|Loss: 1.0271661281585693:  82%|████████▏ | 21340/25880 [4:21:40<53:20,  1.42it/s]
1|21341|Loss: 0.9468322992324829:  82%|████████▏ | 21340/25880 [4:21:40<53:20,  1.42it/s]
1|21341|Loss: 0.9468322992324829:  82%|████████▏ | 21341/25880 [4:21:40<52:50,  1.43it/s]
1|21342|Loss: 0.9275186061859131:  82%|████████▏ | 21341/25880 [4:21:41<52:50,  1.43it/s]
1|21342|Loss: 0.9275186061859131:  82%|████████▏ | 21342/25880 [4:21:41<55:36,  1.36it/s]
1|21343|Loss: 0.7264679074287415:  82%|████████▏ | 21342/25880 [4:21:42<55:36,  1.36it/s]
1|21343|Loss: 0.7264679074287415:  82%|████████▏ | 21343/25880 [4:21:42<56:24,  1.34it/s]
1|21344|Loss: 0.7621076703071594:  82%|████████▏ | 21343/25880 [4:21:42<56:24,  1.34it/s]
1|21344|Loss: 0.7621076703071594:  82%|████████▏ | 21344/25880 [4:21:43<56:11,  1.35it/s]
1|21345|Loss: 0.8425679206848145:  82%|████████▏ | 21344/25880 [4:21:43<56:11,  1.35it/s]
1|21345|Loss: 0.8425679206848145:  82%|████████▏ | 21345/25880 [4:21:44<57:00,  1.33it/s]
1|21346|Loss: 0.7202844619750977:  82%|████████▏ | 21345/25880 [4:21:44<57:00,  1.33it/s]
1|21346|Loss: 0.7202844619750977:  82%|████████▏ | 21346/25880 [4:21:44<57:07,  1.32it/s]
1|21347|Loss: 0.8976844549179077:  82%|████████▏ | 21346/25880 [4:21:45<57:07,  1.32it/s]
1|21347|Loss: 0.8976844549179077:  82%|████████▏ | 21347/25880 [4:21:45<57:46,  1.31it/s]
1|21348|Loss: 0.8802451491355896:  82%|████████▏ | 21347/25880 [4:21:46<57:46,  1.31it/s]
1|21348|Loss: 0.8802451491355896:  82%|████████▏ | 21348/25880 [4:21:46<59:39,  1.27it/s]
1|21349|Loss: 0.8156195878982544:  82%|████████▏ | 21348/25880 [4:21:46<59:39,  1.27it/s]
1|21349|Loss: 0.8156195878982544:  82%|████████▏ | 21349/25880 [4:21:47<59:10,  1.28it/s]
1|21350|Loss: 0.8452631831169128:  82%|████████▏ | 21349/25880 [4:21:47<59:10,  1.28it/s]
1|21350|Loss: 0.8452631831169128:  82%|████████▏ | 21350/25880 [4:21:48<1:00:07,  1.26it/s]
1|21351|Loss: 0.8592653274536133:  82%|████████▏ | 21350/25880 [4:21:48<1:00:07,  1.26it/s]
1|21351|Loss: 0.8592653274536133:  82%|████████▎ | 21351/25880 [4:21:48<58:50,  1.28it/s]  
1|21352|Loss: 0.7686877846717834:  82%|████████▎ | 21351/25880 [4:21:49<58:50,  1.28it/s]
1|21352|Loss: 0.7686877846717834:  83%|████████▎ | 21352/25880 [4:21:49<55:03,  1.37it/s]
1|21353|Loss: 0.7439532279968262:  83%|████████▎ | 21352/25880 [4:21:49<55:03,  1.37it/s]
1|21353|Loss: 0.7439532279968262:  83%|████████▎ | 21353/25880 [4:21:50<56:26,  1.34it/s]
1|21354|Loss: 0.8902232646942139:  83%|████████▎ | 21353/25880 [4:21:50<56:26,  1.34it/s]
1|21354|Loss: 0.8902232646942139:  83%|████████▎ | 21354/25880 [4:21:50<56:07,  1.34it/s]
1|21355|Loss: 0.8158560395240784:  83%|████████▎ | 21354/25880 [4:21:51<56:07,  1.34it/s]
1|21355|Loss: 0.8158560395240784:  83%|████████▎ | 21355/25880 [4:21:51<55:41,  1.35it/s]
1|21356|Loss: 0.8127392530441284:  83%|████████▎ | 21355/25880 [4:21:52<55:41,  1.35it/s]
1|21356|Loss: 0.8127392530441284:  83%|████████▎ | 21356/25880 [4:21:52<55:26,  1.36it/s]
1|21357|Loss: 0.8124908208847046:  83%|████████▎ | 21356/25880 [4:21:52<55:26,  1.36it/s]
1|21357|Loss: 0.8124908208847046:  83%|████████▎ | 21357/25880 [4:21:53<58:31,  1.29it/s]
1|21358|Loss: 0.8078337907791138:  83%|████████▎ | 21357/25880 [4:21:53<58:31,  1.29it/s]
1|21358|Loss: 0.8078337907791138:  83%|████████▎ | 21358/25880 [4:21:54<1:01:34,  1.22it/s]
1|21359|Loss: 0.977019727230072:  83%|████████▎ | 21358/25880 [4:21:54<1:01:34,  1.22it/s] 
1|21359|Loss: 0.977019727230072:  83%|████████▎ | 21359/25880 [4:21:54<59:49,  1.26it/s]  
1|21360|Loss: 0.787416934967041:  83%|████████▎ | 21359/25880 [4:21:55<59:49,  1.26it/s]
1|21360|Loss: 0.787416934967041:  83%|████████▎ | 21360/25880 [4:21:55<57:35,  1.31it/s]
1|21361|Loss: 0.8509160876274109:  83%|████████▎ | 21360/25880 [4:21:56<57:35,  1.31it/s]
1|21361|Loss: 0.8509160876274109:  83%|████████▎ | 21361/25880 [4:21:56<58:43,  1.28it/s]
1|21362|Loss: 0.7994699478149414:  83%|████████▎ | 21361/25880 [4:21:56<58:43,  1.28it/s]
1|21362|Loss: 0.7994699478149414:  83%|████████▎ | 21362/25880 [4:21:57<59:33,  1.26it/s]
1|21363|Loss: 0.8019796013832092:  83%|████████▎ | 21362/25880 [4:21:57<59:33,  1.26it/s]
1|21363|Loss: 0.8019796013832092:  83%|████████▎ | 21363/25880 [4:21:58<1:01:53,  1.22it/s]
1|21364|Loss: 0.6826009750366211:  83%|████████▎ | 21363/25880 [4:21:58<1:01:53,  1.22it/s]
1|21364|Loss: 0.6826009750366211:  83%|████████▎ | 21364/25880 [4:21:59<1:02:24,  1.21it/s]
1|21365|Loss: 0.8146986961364746:  83%|████████▎ | 21364/25880 [4:21:59<1:02:24,  1.21it/s]
1|21365|Loss: 0.8146986961364746:  83%|████████▎ | 21365/25880 [4:21:59<58:31,  1.29it/s]  
1|21366|Loss: 0.8563321828842163:  83%|████████▎ | 21365/25880 [4:22:00<58:31,  1.29it/s]
1|21366|Loss: 0.8563321828842163:  83%|████████▎ | 21366/25880 [4:22:00<54:53,  1.37it/s]
1|21367|Loss: 0.717387855052948:  83%|████████▎ | 21366/25880 [4:22:00<54:53,  1.37it/s] 
1|21367|Loss: 0.717387855052948:  83%|████████▎ | 21367/25880 [4:22:00<54:00,  1.39it/s]
1|21368|Loss: 0.782198429107666:  83%|████████▎ | 21367/25880 [4:22:01<54:00,  1.39it/s]
1|21368|Loss: 0.782198429107666:  83%|████████▎ | 21368/25880 [4:22:01<53:30,  1.41it/s]
1|21369|Loss: 0.8863317966461182:  83%|████████▎ | 21368/25880 [4:22:02<53:30,  1.41it/s]
1|21369|Loss: 0.8863317966461182:  83%|████████▎ | 21369/25880 [4:22:02<52:06,  1.44it/s]
1|21370|Loss: 0.7576248645782471:  83%|████████▎ | 21369/25880 [4:22:02<52:06,  1.44it/s]
1|21370|Loss: 0.7576248645782471:  83%|████████▎ | 21370/25880 [4:22:03<52:05,  1.44it/s]
1|21371|Loss: 0.9707455635070801:  83%|████████▎ | 21370/25880 [4:22:03<52:05,  1.44it/s]
1|21371|Loss: 0.9707455635070801:  83%|████████▎ | 21371/25880 [4:22:03<53:09,  1.41it/s]
1|21372|Loss: 0.6822731494903564:  83%|████████▎ | 21371/25880 [4:22:04<53:09,  1.41it/s]
1|21372|Loss: 0.6822731494903564:  83%|████████▎ | 21372/25880 [4:22:04<54:11,  1.39it/s]
1|21373|Loss: 0.7905383110046387:  83%|████████▎ | 21372/25880 [4:22:04<54:11,  1.39it/s]
1|21373|Loss: 0.7905383110046387:  83%|████████▎ | 21373/25880 [4:22:05<56:16,  1.33it/s]
1|21374|Loss: 0.76689612865448:  83%|████████▎ | 21373/25880 [4:22:05<56:16,  1.33it/s]  
1|21374|Loss: 0.76689612865448:  83%|████████▎ | 21374/25880 [4:22:05<52:42,  1.43it/s]
1|21375|Loss: 0.777672290802002:  83%|████████▎ | 21374/25880 [4:22:06<52:42,  1.43it/s]
1|21375|Loss: 0.777672290802002:  83%|████████▎ | 21375/25880 [4:22:06<51:48,  1.45it/s]
1|21376|Loss: 0.725977897644043:  83%|████████▎ | 21375/25880 [4:22:06<51:48,  1.45it/s]
1|21376|Loss: 0.725977897644043:  83%|████████▎ | 21376/25880 [4:22:07<53:28,  1.40it/s]
1|21377|Loss: 0.78481125831604:  83%|████████▎ | 21376/25880 [4:22:07<53:28,  1.40it/s] 
1|21377|Loss: 0.78481125831604:  83%|████████▎ | 21377/25880 [4:22:08<52:46,  1.42it/s]
1|21378|Loss: 0.7976943254470825:  83%|████████▎ | 21377/25880 [4:22:08<52:46,  1.42it/s]
1|21378|Loss: 0.7976943254470825:  83%|████████▎ | 21378/25880 [4:22:08<47:56,  1.57it/s]
1|21379|Loss: 0.7830621600151062:  83%|███��████▎ | 21378/25880 [4:22:08<47:56,  1.57it/s]
1|21379|Loss: 0.7830621600151062:  83%|████████▎ | 21379/25880 [4:22:09<47:03,  1.59it/s]
1|21380|Loss: 0.9591742157936096:  83%|████████▎ | 21379/25880 [4:22:09<47:03,  1.59it/s]
1|21380|Loss: 0.9591742157936096:  83%|████████▎ | 21380/25880 [4:22:09<46:55,  1.60it/s]
1|21381|Loss: 0.9233232140541077:  83%|████████▎ | 21380/25880 [4:22:10<46:55,  1.60it/s]
1|21381|Loss: 0.9233232140541077:  83%|████████▎ | 21381/25880 [4:22:10<49:00,  1.53it/s]
1|21382|Loss: 0.8444027900695801:  83%|████████▎ | 21381/25880 [4:22:10<49:00,  1.53it/s]
1|21382|Loss: 0.8444027900695801:  83%|████████▎ | 21382/25880 [4:22:11<48:43,  1.54it/s]
1|21383|Loss: 0.8404452204704285:  83%|████████▎ | 21382/25880 [4:22:11<48:43,  1.54it/s]
1|21383|Loss: 0.8404452204704285:  83%|████████▎ | 21383/25880 [4:22:11<49:30,  1.51it/s]
1|21384|Loss: 0.8086048364639282:  83%|████████▎ | 21383/25880 [4:22:12<49:30,  1.51it/s]
1|21384|Loss: 0.8086048364639282:  83%|████████▎ | 21384/25880 [4:22:12<50:23,  1.49it/s]
1|21385|Loss: 0.8250269889831543:  83%|████████▎ | 21384/25880 [4:22:12<50:23,  1.49it/s]
1|21385|Loss: 0.8250269889831543:  83%|████████▎ | 21385/25880 [4:22:13<49:52,  1.50it/s]
1|21386|Loss: 0.8333104848861694:  83%|████████▎ | 21385/25880 [4:22:13<49:52,  1.50it/s]
1|21386|Loss: 0.8333104848861694:  83%|████████▎ | 21386/25880 [4:22:13<51:18,  1.46it/s]
1|21387|Loss: 0.9631269574165344:  83%|████████▎ | 21386/25880 [4:22:14<51:18,  1.46it/s]
1|21387|Loss: 0.9631269574165344:  83%|████████▎ | 21387/25880 [4:22:14<49:51,  1.50it/s]
1|21388|Loss: 0.9886762499809265:  83%|████████▎ | 21387/25880 [4:22:14<49:51,  1.50it/s]
1|21388|Loss: 0.9886762499809265:  83%|████████▎ | 21388/25880 [4:22:15<50:07,  1.49it/s]
1|21389|Loss: 0.8980815410614014:  83%|████████▎ | 21388/25880 [4:22:15<50:07,  1.49it/s]
1|21389|Loss: 0.8980815410614014:  83%|████████▎ | 21389/25880 [4:22:15<53:07,  1.41it/s]
1|21390|Loss: 0.7031714916229248:  83%|████████▎ | 21389/25880 [4:22:16<53:07,  1.41it/s]
1|21390|Loss: 0.7031714916229248:  83%|████████▎ | 21390/25880 [4:22:16<58:49,  1.27it/s]
1|21391|Loss: 0.9297252297401428:  83%|████████▎ | 21390/25880 [4:22:17<58:49,  1.27it/s]
1|21391|Loss: 0.9297252297401428:  83%|████████▎ | 21391/25880 [4:22:17<1:01:08,  1.22it/s]
1|21392|Loss: 0.7756956219673157:  83%|████████▎ | 21391/25880 [4:22:18<1:01:08,  1.22it/s]
1|21392|Loss: 0.7756956219673157:  83%|████████▎ | 21392/25880 [4:22:18<1:03:46,  1.17it/s]
1|21393|Loss: 0.7633367776870728:  83%|████████▎ | 21392/25880 [4:22:19<1:03:46,  1.17it/s]
1|21393|Loss: 0.7633367776870728:  83%|████████▎ | 21393/25880 [4:22:19<1:05:21,  1.14it/s]
1|21394|Loss: 0.9096555113792419:  83%|████████▎ | 21393/25880 [4:22:20<1:05:21,  1.14it/s]
1|21394|Loss: 0.9096555113792419:  83%|████████▎ | 21394/25880 [4:22:20<1:04:44,  1.15it/s]
1|21395|Loss: 0.7286994457244873:  83%|████████▎ | 21394/25880 [4:22:20<1:04:44,  1.15it/s]
1|21395|Loss: 0.7286994457244873:  83%|████████▎ | 21395/25880 [4:22:21<1:00:03,  1.24it/s]
1|21396|Loss: 0.7956385016441345:  83%|████████▎ | 21395/25880 [4:22:21<1:00:03,  1.24it/s]
1|21396|Loss: 0.7956385016441345:  83%|████████▎ | 21396/25880 [4:22:21<58:00,  1.29it/s]  
1|21397|Loss: 0.869873046875:  83%|████████▎ | 21396/25880 [4:22:22<58:00,  1.29it/s]    
1|21397|Loss: 0.869873046875:  83%|████████▎ | 21397/25880 [4:22:22<55:22,  1.35it/s]
1|21398|Loss: 0.7340081334114075:  83%|████████▎ | 21397/25880 [4:22:22<55:22,  1.35it/s]
1|21398|Loss: 0.7340081334114075:  83%|████████▎ | 21398/25880 [4:22:23<55:58,  1.33it/s]
1|21399|Loss: 0.8141716122627258:  83%|████████▎ | 21398/25880 [4:22:23<55:58,  1.33it/s]
1|21399|Loss: 0.8141716122627258:  83%|████████▎ | 21399/25880 [4:22:24<57:43,  1.29it/s]
1|21400|Loss: 0.778264582157135:  83%|████████▎ | 21399/25880 [4:22:24<57:43,  1.29it/s] 
1|21400|Loss: 0.778264582157135:  83%|████████▎ | 21400/25880 [4:22:24<54:22,  1.37it/s]
1|21401|Loss: 0.9029974937438965:  83%|████████▎ | 21400/25880 [4:22:25<54:22,  1.37it/s]
1|21401|Loss: 0.9029974937438965:  83%|████████▎ | 21401/25880 [4:22:25<53:57,  1.38it/s]
1|21402|Loss: 0.7423710227012634:  83%|████████▎ | 21401/25880 [4:22:25<53:57,  1.38it/s]
1|21402|Loss: 0.7423710227012634:  83%|████████▎ | 21402/25880 [4:22:26<52:13,  1.43it/s]
1|21403|Loss: 0.8642281293869019:  83%|████████▎ | 21402/25880 [4:22:26<52:13,  1.43it/s]
1|21403|Loss: 0.8642281293869019:  83%|████████▎ | 21403/25880 [4:22:26<55:01,  1.36it/s]
1|21404|Loss: 0.6868547797203064:  83%|████████▎ | 21403/25880 [4:22:27<55:01,  1.36it/s]
1|21404|Loss: 0.6868547797203064:  83%|████████▎ | 21404/25880 [4:22:27<55:54,  1.33it/s]
1|21405|Loss: 0.7174707651138306:  83%|████████▎ | 21404/25880 [4:22:28<55:54,  1.33it/s]
1|21405|Loss: 0.7174707651138306:  83%|████████▎ | 21405/25880 [4:22:28<55:39,  1.34it/s]
1|21406|Loss: 0.8648543953895569:  83%|████████▎ | 21405/25880 [4:22:28<55:39,  1.34it/s]
1|21406|Loss: 0.8648543953895569:  83%|████████▎ | 21406/25880 [4:22:29<55:35,  1.34it/s]
1|21407|Loss: 0.874047040939331:  83%|████████▎ | 21406/25880 [4:22:29<55:35,  1.34it/s] 
1|21407|Loss: 0.874047040939331:  83%|████████▎ | 21407/25880 [4:22:30<58:04,  1.28it/s]
1|21408|Loss: 1.0515607595443726:  83%|████████▎ | 21407/25880 [4:22:30<58:04,  1.28it/s]
1|21408|Loss: 1.0515607595443726:  83%|████████▎ | 21408/25880 [4:22:30<57:53,  1.29it/s]
1|21409|Loss: 0.838075578212738:  83%|████████▎ | 21408/25880 [4:22:31<57:53,  1.29it/s] 
1|21409|Loss: 0.838075578212738:  83%|████████▎ | 21409/25880 [4:22:31<1:01:01,  1.22it/s]
1|21410|Loss: 0.8500782251358032:  83%|████████▎ | 21409/25880 [4:22:32<1:01:01,  1.22it/s]
1|21410|Loss: 0.8500782251358032:  83%|████████▎ | 21410/25880 [4:22:32<1:01:21,  1.21it/s]
1|21411|Loss: 0.7571812272071838:  83%|████████▎ | 21410/25880 [4:22:33<1:01:21,  1.21it/s]
1|21411|Loss: 0.7571812272071838:  83%|████████▎ | 21411/25880 [4:22:33<59:39,  1.25it/s]  
1|21412|Loss: 0.9640343189239502:  83%|████████▎ | 21411/25880 [4:22:33<59:39,  1.25it/s]
1|21412|Loss: 0.9640343189239502:  83%|████████▎ | 21412/25880 [4:22:34<56:27,  1.32it/s]
1|21413|Loss: 0.8610635995864868:  83%|████████▎ | 21412/25880 [4:22:34<56:27,  1.32it/s]
1|21413|Loss: 0.8610635995864868:  83%|████████▎ | 21413/25880 [4:22:34<50:35,  1.47it/s]
1|21414|Loss: 0.6933671236038208:  83%|████████▎ | 21413/25880 [4:22:34<50:35,  1.47it/s]
1|21414|Loss: 0.6933671236038208:  83%|████████▎ | 21414/25880 [4:22:35<53:01,  1.40it/s]
1|21415|Loss: 0.8912917971611023:  83%|████████▎ | 21414/25880 [4:22:35<53:01,  1.40it/s]
1|21415|Loss: 0.8912917971611023:  83%|████████▎ | 21415/25880 [4:22:36<56:38,  1.31it/s]
1|21416|Loss: 0.8368867635726929:  83%|████████▎ | 21415/25880 [4:22:36<56:38,  1.31it/s]
1|21416|Loss: 0.8368867635726929:  83%|████████▎ | 21416/25880 [4:22:36<56:11,  1.32it/s]
1|21417|Loss: 0.9151374101638794:  83%|████████▎ | 21416/25880 [4:22:37<56:11,  1.32it/s]
1|21417|Loss: 0.9151374101638794:  83%|████████▎ | 21417/25880 [4:22:37<55:05,  1.35it/s]
1|21418|Loss: 0.9273937940597534:  83%|████████▎ | 21417/25880 [4:22:37<55:05,  1.35it/s]
1|21418|Loss: 0.9273937940597534:  83%|████████▎ | 21418/25880 [4:22:38<53:06,  1.40it/s]
1|21419|Loss: 0.8248746991157532:  83%|████████▎ | 21418/25880 [4:22:38<53:06,  1.40it/s]
1|21419|Loss: 0.8248746991157532:  83%|████████▎ | 21419/25880 [4:22:38<53:26,  1.39it/s]
1|21420|Loss: 0.7857470512390137:  83%|████████▎ | 21419/25880 [4:22:39<53:26,  1.39it/s]
1|21420|Loss: 0.7857470512390137:  83%|████████▎ | 21420/25880 [4:22:39<51:27,  1.44it/s]
1|21421|Loss: 0.7213179469108582:  83%|████████▎ | 21420/25880 [4:22:39<51:27,  1.44it/s]
1|21421|Loss: 0.7213179469108582:  83%|████████▎ | 21421/25880 [4:22:40<51:04,  1.46it/s]
1|21422|Loss: 0.7297284007072449:  83%|████████▎ | 21421/25880 [4:22:40<51:04,  1.46it/s]
1|21422|Loss: 0.7297284007072449:  83%|████████▎ | 21422/25880 [4:22:40<49:09,  1.51it/s]
1|21423|Loss: 0.8160923719406128:  83%|████████▎ | 21422/25880 [4:22:41<49:09,  1.51it/s]
1|21423|Loss: 0.8160923719406128:  83%|████████▎ | 21423/25880 [4:22:41<49:27,  1.50it/s]
1|21424|Loss: 0.8707231879234314:  83%|████████▎ | 21423/25880 [4:22:41<49:27,  1.50it/s]
1|21424|Loss: 0.8707231879234314:  83%|████████▎ | 21424/25880 [4:22:42<52:27,  1.42it/s]
1|21425|Loss: 0.8695322871208191:  83%|████████▎ | 21424/25880 [4:22:42<52:27,  1.42it/s]
1|21425|Loss: 0.8695322871208191:  83%|████████▎ | 21425/25880 [4:22:43<55:28,  1.34it/s]
1|21426|Loss: 0.9347529411315918:  83%|████████▎ | 21425/25880 [4:22:43<55:28,  1.34it/s]
1|21426|Loss: 0.9347529411315918:  83%|████████▎ | 21426/25880 [4:22:43<55:10,  1.35it/s]
1|21427|Loss: 0.7553182244300842:  83%|████████▎ | 21426/25880 [4:22:44<55:10,  1.35it/s]
1|21427|Loss: 0.7553182244300842:  83%|████████▎ | 21427/25880 [4:22:44<54:40,  1.36it/s]
1|21428|Loss: 0.8605857491493225:  83%|████████▎ | 21427/25880 [4:22:45<54:40,  1.36it/s]
1|21428|Loss: 0.8605857491493225:  83%|████████▎ | 21428/25880 [4:22:45<52:32,  1.41it/s]
1|21429|Loss: 0.8161953091621399:  83%|████████▎ | 21428/25880 [4:22:45<52:32,  1.41it/s]
1|21429|Loss: 0.8161953091621399:  83%|████████▎ | 21429/25880 [4:22:45<50:57,  1.46it/s]
1|21430|Loss: 0.7896320223808289:  83%|████████▎ | 21429/25880 [4:22:46<50:57,  1.46it/s]
1|21430|Loss: 0.7896320223808289:  83%|████████▎ | 21430/25880 [4:22:46<51:44,  1.43it/s]
1|21431|Loss: 0.7632765173912048:  83%|████████▎ | 21430/25880 [4:22:47<51:44,  1.43it/s]
1|21431|Loss: 0.7632765173912048:  83%|████████▎ | 21431/25880 [4:22:47<48:30,  1.53it/s]
1|21432|Loss: 1.1571701765060425:  83%|████████▎ | 21431/25880 [4:22:47<48:30,  1.53it/s]
1|21432|Loss: 1.1571701765060425:  83%|████████▎ | 21432/25880 [4:22:48<53:41,  1.38it/s]
1|21433|Loss: 0.95854651927948:  83%|████████▎ | 21432/25880 [4:22:48<53:41,  1.38it/s]  
1|21433|Loss: 0.95854651927948:  83%|████████▎ | 21433/25880 [4:22:49<57:56,  1.28it/s]
1|21434|Loss: 0.8046779036521912:  83%|████████▎ | 21433/25880 [4:22:49<57:56,  1.28it/s]
1|21434|Loss: 0.8046779036521912:  83%|████████▎ | 21434/25880 [4:22:49<58:40,  1.26it/s]
1|21435|Loss: 0.894053041934967:  83%|████████▎ | 21434/25880 [4:22:50<58:40,  1.26it/s] 
1|21435|Loss: 0.894053041934967:  83%|████████▎ | 21435/25880 [4:22:50<53:45,  1.38it/s]
1|21436|Loss: 0.7507871985435486:  83%|████████▎ | 21435/25880 [4:22:50<53:45,  1.38it/s]
1|21436|Loss: 0.7507871985435486:  83%|████████▎ | 21436/25880 [4:22:51<52:48,  1.40it/s]
1|21437|Loss: 0.9632325768470764:  83%|████████▎ | 21436/25880 [4:22:51<52:48,  1.40it/s]
1|21437|Loss: 0.9632325768470764:  83%|████████▎ | 21437/25880 [4:22:51<54:14,  1.37it/s]
1|21438|Loss: 0.865827202796936:  83%|████████▎ | 21437/25880 [4:22:52<54:14,  1.37it/s] 
1|21438|Loss: 0.865827202796936:  83%|████████▎ | 21438/25880 [4:22:52<51:59,  1.42it/s]
1|21439|Loss: 0.8367213010787964:  83%|████████▎ | 21438/25880 [4:22:52<51:59,  1.42it/s]
1|21439|Loss: 0.8367213010787964:  83%|████████▎ | 21439/25880 [4:22:53<53:51,  1.37it/s]
1|21440|Loss: 0.8251796364784241:  83%|████████▎ | 21439/25880 [4:22:53<53:51,  1.37it/s]
1|21440|Loss: 0.8251796364784241:  83%|████████▎ | 21440/25880 [4:22:53<52:46,  1.40it/s]
1|21441|Loss: 0.8505286574363708:  83%|████████▎ | 21440/25880 [4:22:54<52:46,  1.40it/s]
1|21441|Loss: 0.8505286574363708:  83%|████████▎ | 21441/25880 [4:22:54<52:09,  1.42it/s]
1|21442|Loss: 0.7623952627182007:  83%|████████▎ | 21441/25880 [4:22:55<52:09,  1.42it/s]
1|21442|Loss: 0.7623952627182007:  83%|████████▎ | 21442/25880 [4:22:55<50:19,  1.47it/s]
1|21443|Loss: 0.6743525266647339:  83%|████████▎ | 21442/25880 [4:22:55<50:19,  1.47it/s]
1|21443|Loss: 0.6743525266647339:  83%|████████▎ | 21443/25880 [4:22:55<45:57,  1.61it/s]
1|21444|Loss: 0.816783607006073:  83%|████████▎ | 21443/25880 [4:22:56<45:57,  1.61it/s] 
1|21444|Loss: 0.816783607006073:  83%|████████▎ | 21444/25880 [4:22:56<46:56,  1.58it/s]
1|21445|Loss: 0.8662289381027222:  83%|████████▎ | 21444/25880 [4:22:56<46:56,  1.58it/s]
1|21445|Loss: 0.8662289381027222:  83%|████████▎ | 21445/25880 [4:22:57<48:27,  1.53it/s]
1|21446|Loss: 0.9396864175796509:  83%|████████▎ | 21445/25880 [4:22:57<48:27,  1.53it/s]
1|21446|Loss: 0.9396864175796509:  83%|████████▎ | 21446/25880 [4:22:57<52:23,  1.41it/s]
1|21447|Loss: 0.8829317688941956:  83%|████████▎ | 21446/25880 [4:22:58<52:23,  1.41it/s]
1|21447|Loss: 0.8829317688941956:  83%|████████▎ | 21447/25880 [4:22:58<54:44,  1.35it/s]
1|21448|Loss: 0.8512250185012817:  83%|████████▎ | 21447/25880 [4:22:59<54:44,  1.35it/s]
1|21448|Loss: 0.8512250185012817:  83%|████████▎ | 21448/25880 [4:22:59<54:13,  1.36it/s]
1|21449|Loss: 0.8253090977668762:  83%|████████▎ | 21448/25880 [4:22:59<54:13,  1.36it/s]
1|21449|Loss: 0.8253090977668762:  83%|████████▎ | 21449/25880 [4:23:00<55:19,  1.33it/s]
1|21450|Loss: 1.0350021123886108:  83%|████████▎ | 21449/25880 [4:23:00<55:19,  1.33it/s]
1|21450|Loss: 1.0350021123886108:  83%|████████▎ | 21450/25880 [4:23:01<55:05,  1.34it/s]
1|21451|Loss: 0.8589015007019043:  83%|████████▎ | 21450/25880 [4:23:01<55:05,  1.34it/s]
1|21451|Loss: 0.8589015007019043:  83%|████████▎ | 21451/25880 [4:23:01<51:59,  1.42it/s]
1|21452|Loss: 0.8506023287773132:  83%|████████▎ | 21451/25880 [4:23:02<51:59,  1.42it/s]
1|21452|Loss: 0.8506023287773132:  83%|████████▎ | 21452/25880 [4:23:02<52:50,  1.40it/s]
1|21453|Loss: 0.9016780853271484:  83%|████████▎ | 21452/25880 [4:23:02<52:50,  1.40it/s]
1|21453|Loss: 0.9016780853271484:  83%|████████▎ | 21453/25880 [4:23:03<56:37,  1.30it/s]
1|21454|Loss: 0.7557629346847534:  83%|████████▎ | 21453/25880 [4:23:03<56:37,  1.30it/s]
1|21454|Loss: 0.7557629346847534:  83%|████████▎ | 21454/25880 [4:23:04<56:29,  1.31it/s]
1|21455|Loss: 0.8201730251312256:  83%|████████▎ | 21454/25880 [4:23:04<56:29,  1.31it/s]
1|21455|Loss: 0.8201730251312256:  83%|████████▎ | 21455/25880 [4:23:04<53:33,  1.38it/s]
1|21456|Loss: 0.7548480033874512:  83%|████████▎ | 21455/25880 [4:23:05<53:33,  1.38it/s]
1|21456|Loss: 0.7548480033874512:  83%|████████▎ | 21456/25880 [4:23:05<51:33,  1.43it/s]
1|21457|Loss: 0.7936419248580933:  83%|████████▎ | 21456/25880 [4:23:05<51:33,  1.43it/s]
1|21457|Loss: 0.7936419248580933:  83%|████████▎ | 21457/25880 [4:23:06<51:51,  1.42it/s]
1|21458|Loss: 0.8256464600563049:  83%|████████▎ | 21457/25880 [4:23:06<51:51,  1.42it/s]
1|21458|Loss: 0.8256464600563049:  83%|████████▎ | 21458/25880 [4:23:06<52:43,  1.40it/s]
1|21459|Loss: 0.8431354761123657:  83%|████████▎ | 21458/25880 [4:23:07<52:43,  1.40it/s]
1|21459|Loss: 0.8431354761123657:  83%|████████▎ | 21459/25880 [4:23:07<53:28,  1.38it/s]
1|21460|Loss: 0.7537068128585815:  83%|████████▎ | 21459/25880 [4:23:07<53:28,  1.38it/s]
1|21460|Loss: 0.7537068128585815:  83%|████████▎ | 21460/25880 [4:23:08<52:05,  1.41it/s]
1|21461|Loss: 0.9351603984832764:  83%|████████▎ | 21460/25880 [4:23:08<52:05,  1.41it/s]
1|21461|Loss: 0.9351603984832764:  83%|████████▎ | 21461/25880 [4:23:08<52:04,  1.41it/s]
1|21462|Loss: 0.8539724349975586:  83%|████████▎ | 21461/25880 [4:23:09<52:04,  1.41it/s]
1|21462|Loss: 0.8539724349975586:  83%|████████▎ | 21462/25880 [4:23:09<53:47,  1.37it/s]
1|21463|Loss: 0.8293955326080322:  83%|████████▎ | 21462/25880 [4:23:10<53:47,  1.37it/s]
1|21463|Loss: 0.8293955326080322:  83%|████████▎ | 21463/25880 [4:23:10<55:00,  1.34it/s]
1|21464|Loss: 0.7956197261810303:  83%|████████▎ | 21463/25880 [4:23:10<55:00,  1.34it/s]
1|21464|Loss: 0.7956197261810303:  83%|████████▎ | 21464/25880 [4:23:10<50:35,  1.45it/s]
1|21465|Loss: 0.779593825340271:  83%|████████▎ | 21464/25880 [4:23:11<50:35,  1.45it/s] 
1|21465|Loss: 0.779593825340271:  83%|████████▎ | 21465/25880 [4:23:11<52:14,  1.41it/s]
1|21466|Loss: 0.7990063428878784:  83%|████████▎ | 21465/25880 [4:23:12<52:14,  1.41it/s]
1|21466|Loss: 0.7990063428878784:  83%|████████▎ | 21466/25880 [4:23:12<49:10,  1.50it/s]
1|21467|Loss: 0.6471748948097229:  83%|████████▎ | 21466/25880 [4:23:12<49:10,  1.50it/s]
1|21467|Loss: 0.6471748948097229:  83%|████████▎ | 21467/25880 [4:23:12<45:37,  1.61it/s]
1|21468|Loss: 0.8182759881019592:  83%|████████▎ | 21467/25880 [4:23:13<45:37,  1.61it/s]
1|21468|Loss: 0.8182759881019592:  83%|████████▎ | 21468/25880 [4:23:13<46:57,  1.57it/s]
1|21469|Loss: 0.8578053116798401:  83%|████████▎ | 21468/25880 [4:23:13<46:57,  1.57it/s]
1|21469|Loss: 0.8578053116798401:  83%|████████▎ | 21469/25880 [4:23:14<48:34,  1.51it/s]
1|21470|Loss: 0.7432472705841064:  83%|████████▎ | 21469/25880 [4:23:14<48:34,  1.51it/s]
1|21470|Loss: 0.7432472705841064:  83%|████████▎ | 21470/25880 [4:23:14<50:26,  1.46it/s]
1|21471|Loss: 0.7931092977523804:  83%|████████▎ | 21470/25880 [4:23:15<50:26,  1.46it/s]
1|21471|Loss: 0.7931092977523804:  83%|████████▎ | 21471/25880 [4:23:15<52:57,  1.39it/s]
1|21472|Loss: 0.7990356683731079:  83%|████████▎ | 21471/25880 [4:23:16<52:57,  1.39it/s]
1|21472|Loss: 0.7990356683731079:  83%|████████▎ | 21472/25880 [4:23:16<55:17,  1.33it/s]
1|21473|Loss: 0.8980964422225952:  83%|████████▎ | 21472/25880 [4:23:17<55:17,  1.33it/s]
1|21473|Loss: 0.8980964422225952:  83%|████████▎ | 21473/25880 [4:23:17<57:02,  1.29it/s]
1|21474|Loss: 0.6744969487190247:  83%|████████▎ | 21473/25880 [4:23:17<57:02,  1.29it/s]
1|21474|Loss: 0.6744969487190247:  83%|████████▎ | 21474/25880 [4:23:18<55:56,  1.31it/s]
1|21475|Loss: 0.830163836479187:  83%|████████▎ | 21474/25880 [4:23:18<55:56,  1.31it/s] 
1|21475|Loss: 0.830163836479187:  83%|████████▎ | 21475/25880 [4:23:18<55:11,  1.33it/s]
1|21476|Loss: 0.7940376400947571:  83%|████████▎ | 21475/25880 [4:23:19<55:11,  1.33it/s]
1|21476|Loss: 0.7940376400947571:  83%|████████▎ | 21476/25880 [4:23:19<50:52,  1.44it/s]
1|21477|Loss: 0.901708722114563:  83%|████████▎ | 21476/25880 [4:23:19<50:52,  1.44it/s] 
1|21477|Loss: 0.901708722114563:  83%|████████▎ | 21477/25880 [4:23:20<50:36,  1.45it/s]
1|21478|Loss: 1.0033782720565796:  83%|████████▎ | 21477/25880 [4:23:20<50:36,  1.45it/s]
1|21478|Loss: 1.0033782720565796:  83%|████████▎ | 21478/25880 [4:23:20<53:31,  1.37it/s]
1|21479|Loss: 0.9485669136047363:  83%|████████▎ | 21478/25880 [4:23:21<53:31,  1.37it/s]
1|21479|Loss: 0.9485669136047363:  83%|████████▎ | 21479/25880 [4:23:21<56:17,  1.30it/s]
1|21480|Loss: 0.8242610692977905:  83%|████████▎ | 21479/25880 [4:23:22<56:17,  1.30it/s]
1|21480|Loss: 0.8242610692977905:  83%|████████▎ | 21480/25880 [4:23:22<1:00:15,  1.22it/s]
1|21481|Loss: 0.843851625919342:  83%|████████▎ | 21480/25880 [4:23:23<1:00:15,  1.22it/s] 
1|21481|Loss: 0.843851625919342:  83%|████████▎ | 21481/25880 [4:23:23<1:02:48,  1.17it/s]
1|21482|Loss: 0.8350528478622437:  83%|████████▎ | 21481/25880 [4:23:24<1:02:48,  1.17it/s]
1|21482|Loss: 0.8350528478622437:  83%|████████▎ | 21482/25880 [4:23:24<59:21,  1.23it/s]  
1|21483|Loss: 0.9161562323570251:  83%|████████▎ | 21482/25880 [4:23:24<59:21,  1.23it/s]
1|21483|Loss: 0.9161562323570251:  83%|████████▎ | 21483/25880 [4:23:24<53:25,  1.37it/s]
1|21484|Loss: 0.9649370312690735:  83%|████████▎ | 21483/25880 [4:23:25<53:25,  1.37it/s]
1|21484|Loss: 0.9649370312690735:  83%|████████▎ | 21484/25880 [4:23:25<49:49,  1.47it/s]
1|21485|Loss: 0.7456163167953491:  83%|████████▎ | 21484/25880 [4:23:25<49:49,  1.47it/s]
1|21485|Loss: 0.7456163167953491:  83%|████████▎ | 21485/25880 [4:23:26<51:18,  1.43it/s]
1|21486|Loss: 0.9209033250808716:  83%|████████▎ | 21485/25880 [4:23:26<51:18,  1.43it/s]
1|21486|Loss: 0.9209033250808716:  83%|████████▎ | 21486/25880 [4:23:27<54:24,  1.35it/s]
1|21487|Loss: 0.8928643465042114:  83%|████████▎ | 21486/25880 [4:23:27<54:24,  1.35it/s]
1|21487|Loss: 0.8928643465042114:  83%|████████▎ | 21487/25880 [4:23:27<56:07,  1.30it/s]
1|21488|Loss: 0.6756629943847656:  83%|████████▎ | 21487/25880 [4:23:28<56:07,  1.30it/s]
1|21488|Loss: 0.6756629943847656:  83%|████████▎ | 21488/25880 [4:23:28<55:11,  1.33it/s]
1|21489|Loss: 0.7121740579605103:  83%|████████▎ | 21488/25880 [4:23:29<55:11,  1.33it/s]
1|21489|Loss: 0.7121740579605103:  83%|████████▎ | 21489/25880 [4:23:29<58:59,  1.24it/s]
1|21490|Loss: 0.9584822654724121:  83%|████████▎ | 21489/25880 [4:23:30<58:59,  1.24it/s]
1|21490|Loss: 0.9584822654724121:  83%|████████▎ | 21490/25880 [4:23:30<58:14,  1.26it/s]
1|21491|Loss: 0.807369589805603:  83%|████████▎ | 21490/25880 [4:23:30<58:14,  1.26it/s] 
1|21491|Loss: 0.807369589805603:  83%|████████▎ | 21491/25880 [4:23:31<56:03,  1.30it/s]
1|21492|Loss: 0.8752114176750183:  83%|████████▎ | 21491/25880 [4:23:31<56:03,  1.30it/s]
1|21492|Loss: 0.8752114176750183:  83%|████████▎ | 21492/25880 [4:23:31<54:34,  1.34it/s]
1|21493|Loss: 0.8327916264533997:  83%|████████▎ | 21492/25880 [4:23:32<54:34,  1.34it/s]
1|21493|Loss: 0.8327916264533997:  83%|████████▎ | 21493/25880 [4:23:32<56:07,  1.30it/s]
1|21494|Loss: 0.8659775257110596:  83%|████████▎ | 21493/25880 [4:23:32<56:07,  1.30it/s]
1|21494|Loss: 0.8659775257110596:  83%|████████▎ | 21494/25880 [4:23:33<55:51,  1.31it/s]
1|21495|Loss: 0.7539531588554382:  83%|████████▎ | 21494/25880 [4:23:33<55:51,  1.31it/s]
1|21495|Loss: 0.7539531588554382:  83%|████████▎ | 21495/25880 [4:23:34<57:06,  1.28it/s]
1|21496|Loss: 0.8237816691398621:  83%|████████▎ | 21495/25880 [4:23:34<57:06,  1.28it/s]
1|21496|Loss: 0.8237816691398621:  83%|████████▎ | 21496/25880 [4:23:34<53:56,  1.35it/s]
1|21497|Loss: 0.6801174283027649:  83%|████████▎ | 21496/25880 [4:23:35<53:56,  1.35it/s]
1|21497|Loss: 0.6801174283027649:  83%|████████▎ | 21497/25880 [4:23:35<53:11,  1.37it/s]
1|21498|Loss: 0.8683343529701233:  83%|████████▎ | 21497/25880 [4:23:35<53:11,  1.37it/s]
1|21498|Loss: 0.8683343529701233:  83%|████████▎ | 21498/25880 [4:23:36<50:43,  1.44it/s]
1|21499|Loss: 0.9423758387565613:  83%|████████▎ | 21498/25880 [4:23:36<50:43,  1.44it/s]
1|21499|Loss: 0.9423758387565613:  83%|████████▎ | 21499/25880 [4:23:36<53:14,  1.37it/s]
1|21500|Loss: 0.9098477959632874:  83%|████████▎ | 21499/25880 [4:23:37<53:14,  1.37it/s]
1|21500|Loss: 0.9098477959632874:  83%|████████▎ | 21500/25880 [4:23:37<53:56,  1.35it/s]
1|21501|Loss: 0.9327616095542908:  83%|████████▎ | 21500/25880 [4:23:38<53:56,  1.35it/s]
1|21501|Loss: 0.9327616095542908:  83%|████████▎ | 21501/25880 [4:23:38<55:27,  1.32it/s]
1|21502|Loss: 0.7768995761871338:  83%|████████▎ | 21501/25880 [4:23:38<55:27,  1.32it/s]
1|21502|Loss: 0.7768995761871338:  83%|████████▎ | 21502/25880 [4:23:39<56:54,  1.28it/s]
1|21503|Loss: 0.7754746079444885:  83%|████████▎ | 21502/25880 [4:23:39<56:54,  1.28it/s]
1|21503|Loss: 0.7754746079444885:  83%|████████▎ | 21503/25880 [4:23:40<58:01,  1.26it/s]
1|21504|Loss: 0.891605019569397:  83%|████████▎ | 21503/25880 [4:23:40<58:01,  1.26it/s] 
1|21504|Loss: 0.891605019569397:  83%|████████▎ | 21504/25880 [4:23:40<59:24,  1.23it/s]
1|21505|Loss: 1.0096608400344849:  83%|████████▎ | 21504/25880 [4:23:41<59:24,  1.23it/s]
1|21505|Loss: 1.0096608400344849:  83%|████████▎ | 21505/25880 [4:23:41<59:18,  1.23it/s]
1|21506|Loss: 1.021515130996704:  83%|████████▎ | 21505/25880 [4:23:42<59:18,  1.23it/s] 
1|21506|Loss: 1.021515130996704:  83%|████████▎ | 21506/25880 [4:23:42<55:15,  1.32it/s]
1|21507|Loss: 0.9772238731384277:  83%|████████▎ | 21506/25880 [4:23:42<55:15,  1.32it/s]
1|21507|Loss: 0.9772238731384277:  83%|████████▎ | 21507/25880 [4:23:42<49:44,  1.47it/s]
1|21508|Loss: 0.8996033072471619:  83%|████████▎ | 21507/25880 [4:23:43<49:44,  1.47it/s]
1|21508|Loss: 0.8996033072471619:  83%|████████▎ | 21508/25880 [4:23:43<51:27,  1.42it/s]
1|21509|Loss: 0.8343321681022644:  83%|████████▎ | 21508/25880 [4:23:44<51:27,  1.42it/s]
1|21509|Loss: 0.8343321681022644:  83%|████████▎ | 21509/25880 [4:23:44<54:36,  1.33it/s]
1|21510|Loss: 0.7502213716506958:  83%|████████▎ | 21509/25880 [4:23:45<54:36,  1.33it/s]
1|21510|Loss: 0.7502213716506958:  83%|████████▎ | 21510/25880 [4:23:45<57:25,  1.27it/s]
1|21511|Loss: 0.8214749693870544:  83%|████████▎ | 21510/25880 [4:23:45<57:25,  1.27it/s]
1|21511|Loss: 0.8214749693870544:  83%|████████▎ | 21511/25880 [4:23:46<57:10,  1.27it/s]
1|21512|Loss: 0.6780951023101807:  83%|████████▎ | 21511/25880 [4:23:46<57:10,  1.27it/s]
1|21512|Loss: 0.6780951023101807:  83%|████████▎ | 21512/25880 [4:23:47<1:00:14,  1.21it/s]
1|21513|Loss: 1.0573173761367798:  83%|████████▎ | 21512/25880 [4:23:47<1:00:14,  1.21it/s]
1|21513|Loss: 1.0573173761367798:  83%|████████▎ | 21513/25880 [4:23:48<1:01:21,  1.19it/s]
1|21514|Loss: 0.7069848775863647:  83%|████████▎ | 21513/25880 [4:23:48<1:01:21,  1.19it/s]
1|21514|Loss: 0.7069848775863647:  83%|████████▎ | 21514/25880 [4:23:48<57:00,  1.28it/s]  
1|21515|Loss: 0.9087086915969849:  83%|████████▎ | 21514/25880 [4:23:48<57:00,  1.28it/s]
1|21515|Loss: 0.9087086915969849:  83%|████████▎ | 21515/25880 [4:23:49<53:12,  1.37it/s]
1|21516|Loss: 0.8544334769248962:  83%|████████▎ | 21515/25880 [4:23:49<53:12,  1.37it/s]
1|21516|Loss: 0.8544334769248962:  83%|████████▎ | 21516/25880 [4:23:49<51:04,  1.42it/s]
1|21517|Loss: 0.7579789757728577:  83%|████████▎ | 21516/25880 [4:23:50<51:04,  1.42it/s]
1|21517|Loss: 0.7579789757728577:  83%|████████▎ | 21517/25880 [4:23:50<53:50,  1.35it/s]
1|21518|Loss: 0.7700945734977722:  83%|████████▎ | 21517/25880 [4:23:51<53:50,  1.35it/s]
1|21518|Loss: 0.7700945734977722:  83%|████████▎ | 21518/25880 [4:23:51<54:36,  1.33it/s]
1|21519|Loss: 0.7970348596572876:  83%|████████▎ | 21518/25880 [4:23:51<54:36,  1.33it/s]
1|21519|Loss: 0.7970348596572876:  83%|████████▎ | 21519/25880 [4:23:52<54:20,  1.34it/s]
1|21520|Loss: 0.8758676052093506:  83%|████████▎ | 21519/25880 [4:23:52<54:20,  1.34it/s]
1|21520|Loss: 0.8758676052093506:  83%|████████▎ | 21520/25880 [4:23:52<51:16,  1.42it/s]
1|21521|Loss: 0.8116293549537659:  83%|████████�� | 21520/25880 [4:23:53<51:16,  1.42it/s]
1|21521|Loss: 0.8116293549537659:  83%|████████▎ | 21521/25880 [4:23:53<51:14,  1.42it/s]
1|21522|Loss: 0.8552564382553101:  83%|████████▎ | 21521/25880 [4:23:53<51:14,  1.42it/s]
1|21522|Loss: 0.8552564382553101:  83%|████████▎ | 21522/25880 [4:23:54<51:54,  1.40it/s]
1|21523|Loss: 0.841860294342041:  83%|████████▎ | 21522/25880 [4:23:54<51:54,  1.40it/s] 
1|21523|Loss: 0.841860294342041:  83%|████████▎ | 21523/25880 [4:23:54<50:42,  1.43it/s]
1|21524|Loss: 0.8116820454597473:  83%|████████▎ | 21523/25880 [4:23:55<50:42,  1.43it/s]
1|21524|Loss: 0.8116820454597473:  83%|████████▎ | 21524/25880 [4:23:55<48:32,  1.50it/s]
1|21525|Loss: 0.8633866310119629:  83%|████████▎ | 21524/25880 [4:23:55<48:32,  1.50it/s]
1|21525|Loss: 0.8633866310119629:  83%|████████▎ | 21525/25880 [4:23:56<49:14,  1.47it/s]
1|21526|Loss: 0.8263312578201294:  83%|████████▎ | 21525/25880 [4:23:56<49:14,  1.47it/s]
1|21526|Loss: 0.8263312578201294:  83%|████████▎ | 21526/25880 [4:23:56<48:49,  1.49it/s]
1|21527|Loss: 0.9233060479164124:  83%|████████▎ | 21526/25880 [4:23:57<48:49,  1.49it/s]
1|21527|Loss: 0.9233060479164124:  83%|████████▎ | 21527/25880 [4:23:57<50:47,  1.43it/s]
1|21528|Loss: 0.848959743976593:  83%|████████▎ | 21527/25880 [4:23:58<50:47,  1.43it/s] 
1|21528|Loss: 0.848959743976593:  83%|████████▎ | 21528/25880 [4:23:58<54:57,  1.32it/s]
1|21529|Loss: 0.9858270883560181:  83%|████████▎ | 21528/25880 [4:23:58<54:57,  1.32it/s]
1|21529|Loss: 0.9858270883560181:  83%|████████▎ | 21529/25880 [4:23:59<53:27,  1.36it/s]
1|21530|Loss: 0.9031072854995728:  83%|████████▎ | 21529/25880 [4:23:59<53:27,  1.36it/s]
1|21530|Loss: 0.9031072854995728:  83%|████████▎ | 21530/25880 [4:23:59<52:58,  1.37it/s]
1|21531|Loss: 0.8827961683273315:  83%|████████▎ | 21530/25880 [4:24:00<52:58,  1.37it/s]
1|21531|Loss: 0.8827961683273315:  83%|████████▎ | 21531/25880 [4:24:00<55:31,  1.31it/s]
1|21532|Loss: 0.868787944316864:  83%|████████▎ | 21531/25880 [4:24:01<55:31,  1.31it/s] 
1|21532|Loss: 0.868787944316864:  83%|████████▎ | 21532/25880 [4:24:01<55:39,  1.30it/s]
1|21533|Loss: 0.7249709367752075:  83%|████████▎ | 21532/25880 [4:24:02<55:39,  1.30it/s]
1|21533|Loss: 0.7249709367752075:  83%|████████▎ | 21533/25880 [4:24:02<55:13,  1.31it/s]
1|21534|Loss: 0.7491195797920227:  83%|████████▎ | 21533/25880 [4:24:02<55:13,  1.31it/s]
1|21534|Loss: 0.7491195797920227:  83%|████████▎ | 21534/25880 [4:24:02<52:16,  1.39it/s]
1|21535|Loss: 0.7471358180046082:  83%|████████▎ | 21534/25880 [4:24:03<52:16,  1.39it/s]
1|21535|Loss: 0.7471358180046082:  83%|████████▎ | 21535/25880 [4:24:03<51:16,  1.41it/s]
1|21536|Loss: 0.8283134698867798:  83%|████████▎ | 21535/25880 [4:24:04<51:16,  1.41it/s]
1|21536|Loss: 0.8283134698867798:  83%|████████▎ | 21536/25880 [4:24:04<52:50,  1.37it/s]
1|21537|Loss: 0.8272098302841187:  83%|████████▎ | 21536/25880 [4:24:04<52:50,  1.37it/s]
1|21537|Loss: 0.8272098302841187:  83%|████████▎ | 21537/25880 [4:24:05<53:21,  1.36it/s]
1|21538|Loss: 0.8269531726837158:  83%|████████▎ | 21537/25880 [4:24:05<53:21,  1.36it/s]
1|21538|Loss: 0.8269531726837158:  83%|████████▎ | 21538/25880 [4:24:05<53:18,  1.36it/s]
1|21539|Loss: 0.9938108921051025:  83%|████████▎ | 21538/25880 [4:24:06<53:18,  1.36it/s]
1|21539|Loss: 0.9938108921051025:  83%|████████▎ | 21539/25880 [4:24:06<51:48,  1.40it/s]
1|21540|Loss: 0.7346592545509338:  83%|████████▎ | 21539/25880 [4:24:07<51:48,  1.40it/s]
1|21540|Loss: 0.7346592545509338:  83%|████████▎ | 21540/25880 [4:24:07<54:20,  1.33it/s]
1|21541|Loss: 0.8659238219261169:  83%|████████▎ | 21540/25880 [4:24:07<54:20,  1.33it/s]
1|21541|Loss: 0.8659238219261169:  83%|████████▎ | 21541/25880 [4:24:08<52:12,  1.39it/s]
1|21542|Loss: 0.8223264813423157:  83%|████████▎ | 21541/25880 [4:24:08<52:12,  1.39it/s]
1|21542|Loss: 0.8223264813423157:  83%|████████▎ | 21542/25880 [4:24:08<50:06,  1.44it/s]
1|21543|Loss: 0.7369674444198608:  83%|████████▎ | 21542/25880 [4:24:09<50:06,  1.44it/s]
1|21543|Loss: 0.7369674444198608:  83%|████████▎ | 21543/25880 [4:24:09<51:29,  1.40it/s]
1|21544|Loss: 0.7807390093803406:  83%|████████▎ | 21543/25880 [4:24:09<51:29,  1.40it/s]
1|21544|Loss: 0.7807390093803406:  83%|████████▎ | 21544/25880 [4:24:10<55:25,  1.30it/s]
1|21545|Loss: 0.7697430849075317:  83%|████████▎ | 21544/25880 [4:24:10<55:25,  1.30it/s]
1|21545|Loss: 0.7697430849075317:  83%|████████▎ | 21545/25880 [4:24:11<57:15,  1.26it/s]
1|21546|Loss: 0.8531126379966736:  83%|████████▎ | 21545/25880 [4:24:11<57:15,  1.26it/s]
1|21546|Loss: 0.8531126379966736:  83%|████████▎ | 21546/25880 [4:24:11<57:17,  1.26it/s]
1|21547|Loss: 0.8152598142623901:  83%|████████▎ | 21546/25880 [4:24:12<57:17,  1.26it/s]
1|21547|Loss: 0.8152598142623901:  83%|████████▎ | 21547/25880 [4:24:12<57:19,  1.26it/s]
1|21548|Loss: 0.9536651968955994:  83%|████████▎ | 21547/25880 [4:24:13<57:19,  1.26it/s]
1|21548|Loss: 0.9536651968955994:  83%|████████▎ | 21548/25880 [4:24:13<56:13,  1.28it/s]
1|21549|Loss: 0.9831101298332214:  83%|████████▎ | 21548/25880 [4:24:13<56:13,  1.28it/s]
1|21549|Loss: 0.9831101298332214:  83%|████████▎ | 21549/25880 [4:24:14<52:40,  1.37it/s]
1|21550|Loss: 0.8231387734413147:  83%|████████▎ | 21549/25880 [4:24:14<52:40,  1.37it/s]
1|21550|Loss: 0.8231387734413147:  83%|████████▎ | 21550/25880 [4:24:14<52:22,  1.38it/s]
1|21551|Loss: 0.752326250076294:  83%|████████▎ | 21550/25880 [4:24:15<52:22,  1.38it/s] 
1|21551|Loss: 0.752326250076294:  83%|████████▎ | 21551/25880 [4:24:15<55:56,  1.29it/s]
1|21552|Loss: 0.8006239533424377:  83%|████████▎ | 21551/25880 [4:24:16<55:56,  1.29it/s]
1|21552|Loss: 0.8006239533424377:  83%|████████▎ | 21552/25880 [4:24:16<52:20,  1.38it/s]
1|21553|Loss: 0.809129536151886:  83%|████████▎ | 21552/25880 [4:24:16<52:20,  1.38it/s] 
1|21553|Loss: 0.809129536151886:  83%|████████▎ | 21553/25880 [4:24:16<49:59,  1.44it/s]
1|21554|Loss: 0.8805270195007324:  83%|████████▎ | 21553/25880 [4:24:17<49:59,  1.44it/s]
1|21554|Loss: 0.8805270195007324:  83%|████████▎ | 21554/25880 [4:24:17<51:23,  1.40it/s]
1|21555|Loss: 0.9057310223579407:  83%|████████▎ | 21554/25880 [4:24:18<51:23,  1.40it/s]
1|21555|Loss: 0.9057310223579407:  83%|████████▎ | 21555/25880 [4:24:18<49:28,  1.46it/s]
1|21556|Loss: 0.7422280311584473:  83%|████████▎ | 21555/25880 [4:24:18<49:28,  1.46it/s]
1|21556|Loss: 0.7422280311584473:  83%|████████▎ | 21556/25880 [4:24:19<49:42,  1.45it/s]
1|21557|Loss: 0.7584980130195618:  83%|████████▎ | 21556/25880 [4:24:19<49:42,  1.45it/s]
1|21557|Loss: 0.7584980130195618:  83%|████████▎ | 21557/25880 [4:24:19<54:35,  1.32it/s]
1|21558|Loss: 0.7611222267150879:  83%|████████▎ | 21557/25880 [4:24:20<54:35,  1.32it/s]
1|21558|Loss: 0.7611222267150879:  83%|████████▎ | 21558/25880 [4:24:20<56:56,  1.27it/s]
1|21559|Loss: 0.8213370442390442:  83%|████████▎ | 21558/25880 [4:24:21<56:56,  1.27it/s]
1|21559|Loss: 0.8213370442390442:  83%|████████▎ | 21559/25880 [4:24:21<56:11,  1.28it/s]
1|21560|Loss: 0.8707196116447449:  83%|████████▎ | 21559/25880 [4:24:22<56:11,  1.28it/s]
1|21560|Loss: 0.8707196116447449:  83%|████████▎ | 21560/25880 [4:24:22<55:18,  1.30it/s]
1|21561|Loss: 0.7424394488334656:  83%|████████▎ | 21560/25880 [4:24:22<55:18,  1.30it/s]
1|21561|Loss: 0.7424394488334656:  83%|████████▎ | 21561/25880 [4:24:23<54:10,  1.33it/s]
1|21562|Loss: 0.7725334763526917:  83%|████████▎ | 21561/25880 [4:24:23<54:10,  1.33it/s]
1|21562|Loss: 0.7725334763526917:  83%|████████▎ | 21562/25880 [4:24:23<53:00,  1.36it/s]
1|21563|Loss: 0.8249002695083618:  83%|████████▎ | 21562/25880 [4:24:24<53:00,  1.36it/s]
1|21563|Loss: 0.8249002695083618:  83%|████████▎ | 21563/25880 [4:24:24<55:20,  1.30it/s]
1|21564|Loss: 0.8418566584587097:  83%|████████▎ | 21563/25880 [4:24:25<55:20,  1.30it/s]
1|21564|Loss: 0.8418566584587097:  83%|████████▎ | 21564/25880 [4:24:25<55:27,  1.30it/s]
1|21565|Loss: 0.7963852286338806:  83%|████████▎ | 21564/25880 [4:24:25<55:27,  1.30it/s]
1|21565|Loss: 0.7963852286338806:  83%|████████▎ | 21565/25880 [4:24:26<57:02,  1.26it/s]
1|21566|Loss: 0.8781810402870178:  83%|████████▎ | 21565/25880 [4:24:26<57:02,  1.26it/s]
1|21566|Loss: 0.8781810402870178:  83%|████████▎ | 21566/25880 [4:24:26<54:46,  1.31it/s]
1|21567|Loss: 0.7761935591697693:  83%|████████▎ | 21566/25880 [4:24:27<54:46,  1.31it/s]
1|21567|Loss: 0.7761935591697693:  83%|████████▎ | 21567/25880 [4:24:27<55:26,  1.30it/s]
1|21568|Loss: 1.0552265644073486:  83%|████████▎ | 21567/25880 [4:24:28<55:26,  1.30it/s]
1|21568|Loss: 1.0552265644073486:  83%|███��████▎ | 21568/25880 [4:24:28<52:42,  1.36it/s]
1|21569|Loss: 0.9409764409065247:  83%|████████▎ | 21568/25880 [4:24:28<52:42,  1.36it/s]
1|21569|Loss: 0.9409764409065247:  83%|████████▎ | 21569/25880 [4:24:29<53:59,  1.33it/s]
1|21570|Loss: 0.8175481557846069:  83%|████████▎ | 21569/25880 [4:24:29<53:59,  1.33it/s]
1|21570|Loss: 0.8175481557846069:  83%|████████▎ | 21570/25880 [4:24:29<53:31,  1.34it/s]
1|21571|Loss: 0.7054720520973206:  83%|████████▎ | 21570/25880 [4:24:30<53:31,  1.34it/s]
1|21571|Loss: 0.7054720520973206:  83%|████████▎ | 21571/25880 [4:24:30<54:02,  1.33it/s]
1|21572|Loss: 0.824125349521637:  83%|████████▎ | 21571/25880 [4:24:31<54:02,  1.33it/s] 
1|21572|Loss: 0.824125349521637:  83%|████████▎ | 21572/25880 [4:24:31<52:27,  1.37it/s]
1|21573|Loss: 0.7491744160652161:  83%|████████▎ | 21572/25880 [4:24:31<52:27,  1.37it/s]
1|21573|Loss: 0.7491744160652161:  83%|████████▎ | 21573/25880 [4:24:32<52:10,  1.38it/s]
1|21574|Loss: 0.8934119939804077:  83%|████████▎ | 21573/25880 [4:24:32<52:10,  1.38it/s]
1|21574|Loss: 0.8934119939804077:  83%|████████▎ | 21574/25880 [4:24:32<51:51,  1.38it/s]
1|21575|Loss: 0.7021701335906982:  83%|████████▎ | 21574/25880 [4:24:33<51:51,  1.38it/s]
1|21575|Loss: 0.7021701335906982:  83%|████████▎ | 21575/25880 [4:24:33<50:15,  1.43it/s]
1|21576|Loss: 0.9090535640716553:  83%|████████▎ | 21575/25880 [4:24:33<50:15,  1.43it/s]
1|21576|Loss: 0.9090535640716553:  83%|████████▎ | 21576/25880 [4:24:34<51:47,  1.38it/s]
1|21577|Loss: 0.8444094657897949:  83%|████████▎ | 21576/25880 [4:24:34<51:47,  1.38it/s]
1|21577|Loss: 0.8444094657897949:  83%|████████▎ | 21577/25880 [4:24:34<49:06,  1.46it/s]
1|21578|Loss: 0.7468713521957397:  83%|████████▎ | 21577/25880 [4:24:35<49:06,  1.46it/s]
1|21578|Loss: 0.7468713521957397:  83%|████████▎ | 21578/25880 [4:24:35<49:17,  1.45it/s]
1|21579|Loss: 0.9885008931159973:  83%|████████▎ | 21578/25880 [4:24:35<49:17,  1.45it/s]
1|21579|Loss: 0.9885008931159973:  83%|████████▎ | 21579/25880 [4:24:36<50:14,  1.43it/s]
1|21580|Loss: 0.7639992833137512:  83%|████████▎ | 21579/25880 [4:24:36<50:14,  1.43it/s]
1|21580|Loss: 0.7639992833137512:  83%|████████▎ | 21580/25880 [4:24:36<51:04,  1.40it/s]
1|21581|Loss: 0.9516148567199707:  83%|████████▎ | 21580/25880 [4:24:37<51:04,  1.40it/s]
1|21581|Loss: 0.9516148567199707:  83%|████████▎ | 21581/25880 [4:24:37<49:57,  1.43it/s]
1|21582|Loss: 0.7937518954277039:  83%|████████▎ | 21581/25880 [4:24:37<49:57,  1.43it/s]
1|21582|Loss: 0.7937518954277039:  83%|████████▎ | 21582/25880 [4:24:38<48:22,  1.48it/s]
1|21583|Loss: 0.8541325926780701:  83%|████████▎ | 21582/25880 [4:24:38<48:22,  1.48it/s]
1|21583|Loss: 0.8541325926780701:  83%|████████▎ | 21583/25880 [4:24:38<48:48,  1.47it/s]
1|21584|Loss: 0.7088249921798706:  83%|████████▎ | 21583/25880 [4:24:39<48:48,  1.47it/s]
1|21584|Loss: 0.7088249921798706:  83%|████████▎ | 21584/25880 [4:24:39<47:41,  1.50it/s]
1|21585|Loss: 0.8013546466827393:  83%|████████▎ | 21584/25880 [4:24:39<47:41,  1.50it/s]
1|21585|Loss: 0.8013546466827393:  83%|████████▎ | 21585/25880 [4:24:40<48:06,  1.49it/s]
1|21586|Loss: 0.8094106316566467:  83%|████████▎ | 21585/25880 [4:24:40<48:06,  1.49it/s]
1|21586|Loss: 0.8094106316566467:  83%|████████▎ | 21586/25880 [4:24:41<50:16,  1.42it/s]
1|21587|Loss: 0.9167636632919312:  83%|████████▎ | 21586/25880 [4:24:41<50:16,  1.42it/s]
1|21587|Loss: 0.9167636632919312:  83%|████████▎ | 21587/25880 [4:24:41<51:06,  1.40it/s]
1|21588|Loss: 0.917250394821167:  83%|████████▎ | 21587/25880 [4:24:42<51:06,  1.40it/s] 
1|21588|Loss: 0.917250394821167:  83%|████████▎ | 21588/25880 [4:24:42<51:28,  1.39it/s]
1|21589|Loss: 0.9281049370765686:  83%|████████▎ | 21588/25880 [4:24:42<51:28,  1.39it/s]
1|21589|Loss: 0.9281049370765686:  83%|████████▎ | 21589/25880 [4:24:43<52:51,  1.35it/s]
1|21590|Loss: 0.838358461856842:  83%|████████▎ | 21589/25880 [4:24:43<52:51,  1.35it/s] 
1|21590|Loss: 0.838358461856842:  83%|████████▎ | 21590/25880 [4:24:44<53:01,  1.35it/s]
1|21591|Loss: 0.8017294406890869:  83%|████████▎ | 21590/25880 [4:24:44<53:01,  1.35it/s]
1|21591|Loss: 0.8017294406890869:  83%|████████▎ | 21591/25880 [4:24:44<52:59,  1.35it/s]
1|21592|Loss: 0.5783655643463135:  83%|████████▎ | 21591/25880 [4:24:45<52:59,  1.35it/s]
1|21592|Loss: 0.5783655643463135:  83%|████████▎ | 21592/25880 [4:24:45<52:46,  1.35it/s]
1|21593|Loss: 0.8889525532722473:  83%|████████▎ | 21592/25880 [4:24:45<52:46,  1.35it/s]
1|21593|Loss: 0.8889525532722473:  83%|████████▎ | 21593/25880 [4:24:46<54:09,  1.32it/s]
1|21594|Loss: 0.7422615885734558:  83%|████████▎ | 21593/25880 [4:24:46<54:09,  1.32it/s]
1|21594|Loss: 0.7422615885734558:  83%|████████▎ | 21594/25880 [4:24:47<55:56,  1.28it/s]
1|21595|Loss: 0.7915330529212952:  83%|████████▎ | 21594/25880 [4:24:47<55:56,  1.28it/s]
1|21595|Loss: 0.7915330529212952:  83%|████████▎ | 21595/25880 [4:24:47<54:54,  1.30it/s]
1|21596|Loss: 0.7872473001480103:  83%|████████▎ | 21595/25880 [4:24:48<54:54,  1.30it/s]
1|21596|Loss: 0.7872473001480103:  83%|████████▎ | 21596/25880 [4:24:48<51:12,  1.39it/s]
1|21597|Loss: 0.8686603903770447:  83%|████████▎ | 21596/25880 [4:24:48<51:12,  1.39it/s]
1|21597|Loss: 0.8686603903770447:  83%|████████▎ | 21597/25880 [4:24:49<51:50,  1.38it/s]
1|21598|Loss: 0.8560364842414856:  83%|████████▎ | 21597/25880 [4:24:49<51:50,  1.38it/s]
1|21598|Loss: 0.8560364842414856:  83%|████████▎ | 21598/25880 [4:24:49<52:19,  1.36it/s]
1|21599|Loss: 0.8507654666900635:  83%|████████▎ | 21598/25880 [4:24:50<52:19,  1.36it/s]
1|21599|Loss: 0.8507654666900635:  83%|████████▎ | 21599/25880 [4:24:50<52:15,  1.37it/s]
1|21600|Loss: 0.9345384836196899:  83%|████████▎ | 21599/25880 [4:24:51<52:15,  1.37it/s]
1|21600|Loss: 0.9345384836196899:  83%|████████▎ | 21600/25880 [4:24:51<54:08,  1.32it/s]
1|21601|Loss: 0.7857072949409485:  83%|████████▎ | 21600/25880 [4:24:51<54:08,  1.32it/s]
1|21601|Loss: 0.7857072949409485:  83%|████████▎ | 21601/25880 [4:24:52<54:17,  1.31it/s]
1|21602|Loss: 0.8218523859977722:  83%|████████▎ | 21601/25880 [4:24:52<54:17,  1.31it/s]
1|21602|Loss: 0.8218523859977722:  83%|████████▎ | 21602/25880 [4:24:52<51:48,  1.38it/s]
1|21603|Loss: 0.8378148078918457:  83%|████████▎ | 21602/25880 [4:24:53<51:48,  1.38it/s]
1|21603|Loss: 0.8378148078918457:  83%|████████▎ | 21603/25880 [4:24:53<53:32,  1.33it/s]
1|21604|Loss: 0.6145140528678894:  83%|████████▎ | 21603/25880 [4:24:54<53:32,  1.33it/s]
1|21604|Loss: 0.6145140528678894:  83%|████████▎ | 21604/25880 [4:24:54<58:36,  1.22it/s]
1|21605|Loss: 0.885958731174469:  83%|████████▎ | 21604/25880 [4:24:55<58:36,  1.22it/s] 
1|21605|Loss: 0.885958731174469:  83%|████████▎ | 21605/25880 [4:24:55<59:50,  1.19it/s]
1|21606|Loss: 0.876637876033783:  83%|████████▎ | 21605/25880 [4:24:55<59:50,  1.19it/s]
1|21606|Loss: 0.876637876033783:  83%|████████▎ | 21606/25880 [4:24:56<55:13,  1.29it/s]
1|21607|Loss: 0.8582566380500793:  83%|████████▎ | 21606/25880 [4:24:56<55:13,  1.29it/s]
1|21607|Loss: 0.8582566380500793:  83%|████████▎ | 21607/25880 [4:24:56<51:12,  1.39it/s]
1|21608|Loss: 0.8113105297088623:  83%|████████▎ | 21607/25880 [4:24:57<51:12,  1.39it/s]
1|21608|Loss: 0.8113105297088623:  83%|████████▎ | 21608/25880 [4:24:57<50:08,  1.42it/s]
1|21609|Loss: 0.6591435670852661:  83%|████████▎ | 21608/25880 [4:24:57<50:08,  1.42it/s]
1|21609|Loss: 0.6591435670852661:  83%|████████▎ | 21609/25880 [4:24:58<54:36,  1.30it/s]
1|21610|Loss: 0.8957393169403076:  83%|████████▎ | 21609/25880 [4:24:58<54:36,  1.30it/s]
1|21610|Loss: 0.8957393169403076:  84%|████████▎ | 21610/25880 [4:24:59<54:24,  1.31it/s]
1|21611|Loss: 0.9361843466758728:  84%|████████▎ | 21610/25880 [4:24:59<54:24,  1.31it/s]
1|21611|Loss: 0.9361843466758728:  84%|████████▎ | 21611/25880 [4:24:59<54:32,  1.30it/s]
1|21612|Loss: 0.7062944173812866:  84%|████████▎ | 21611/25880 [4:25:00<54:32,  1.30it/s]
1|21612|Loss: 0.7062944173812866:  84%|████████▎ | 21612/25880 [4:25:00<52:30,  1.35it/s]
1|21613|Loss: 0.7076379656791687:  84%|████████▎ | 21612/25880 [4:25:00<52:30,  1.35it/s]
1|21613|Loss: 0.7076379656791687:  84%|████████▎ | 21613/25880 [4:25:01<51:25,  1.38it/s]
1|21614|Loss: 0.8553164005279541:  84%|████████▎ | 21613/25880 [4:25:01<51:25,  1.38it/s]
1|21614|Loss: 0.8553164005279541:  84%|████████▎ | 21614/25880 [4:25:01<49:26,  1.44it/s]
1|21615|Loss: 0.8831818699836731:  84%|████████▎ | 21614/25880 [4:25:02<49:26,  1.44it/s]
1|21615|Loss: 0.8831818699836731:  84%|████████▎ | 21615/25880 [4:25:02<50:38,  1.40it/s]
1|21616|Loss: 0.7443320155143738:  84%|████████▎ | 21615/25880 [4:25:03<50:38,  1.40it/s]
1|21616|Loss: 0.7443320155143738:  84%|████████▎ | 21616/25880 [4:25:03<51:33,  1.38it/s]
1|21617|Loss: 0.8506067395210266:  84%|████████▎ | 21616/25880 [4:25:03<51:33,  1.38it/s]
1|21617|Loss: 0.8506067395210266:  84%|████████▎ | 21617/25880 [4:25:04<51:52,  1.37it/s]
1|21618|Loss: 0.7357401847839355:  84%|████████▎ | 21617/25880 [4:25:04<51:52,  1.37it/s]
1|21618|Loss: 0.7357401847839355:  84%|████████▎ | 21618/25880 [4:25:04<49:17,  1.44it/s]
1|21619|Loss: 0.9158165454864502:  84%|████████▎ | 21618/25880 [4:25:05<49:17,  1.44it/s]
1|21619|Loss: 0.9158165454864502:  84%|████████▎ | 21619/25880 [4:25:05<49:22,  1.44it/s]
1|21620|Loss: 0.7872405052185059:  84%|████████▎ | 21619/25880 [4:25:05<49:22,  1.44it/s]
1|21620|Loss: 0.7872405052185059:  84%|████████▎ | 21620/25880 [4:25:06<50:02,  1.42it/s]
1|21621|Loss: 0.8637979030609131:  84%|████████▎ | 21620/25880 [4:25:06<50:02,  1.42it/s]
1|21621|Loss: 0.8637979030609131:  84%|████████▎ | 21621/25880 [4:25:06<48:32,  1.46it/s]
1|21622|Loss: 0.9543654322624207:  84%|████████▎ | 21621/25880 [4:25:07<48:32,  1.46it/s]
1|21622|Loss: 0.9543654322624207:  84%|████████▎ | 21622/25880 [4:25:07<46:37,  1.52it/s]
1|21623|Loss: 0.8040533065795898:  84%|████████▎ | 21622/25880 [4:25:07<46:37,  1.52it/s]
1|21623|Loss: 0.8040533065795898:  84%|████████▎ | 21623/25880 [4:25:08<46:04,  1.54it/s]
1|21624|Loss: 0.8801310658454895:  84%|████████▎ | 21623/25880 [4:25:08<46:04,  1.54it/s]
1|21624|Loss: 0.8801310658454895:  84%|████████▎ | 21624/25880 [4:25:08<47:31,  1.49it/s]
1|21625|Loss: 0.834078311920166:  84%|████████▎ | 21624/25880 [4:25:09<47:31,  1.49it/s] 
1|21625|Loss: 0.834078311920166:  84%|████████▎ | 21625/25880 [4:25:09<48:48,  1.45it/s]
1|21626|Loss: 0.9134799838066101:  84%|████████▎ | 21625/25880 [4:25:09<48:48,  1.45it/s]
1|21626|Loss: 0.9134799838066101:  84%|████████▎ | 21626/25880 [4:25:10<49:07,  1.44it/s]
1|21627|Loss: 0.7645404934883118:  84%|████████▎ | 21626/25880 [4:25:10<49:07,  1.44it/s]
1|21627|Loss: 0.7645404934883118:  84%|████████▎ | 21627/25880 [4:25:10<49:49,  1.42it/s]
1|21628|Loss: 0.6808599233627319:  84%|████████▎ | 21627/25880 [4:25:11<49:49,  1.42it/s]
1|21628|Loss: 0.6808599233627319:  84%|████████▎ | 21628/25880 [4:25:11<48:26,  1.46it/s]
1|21629|Loss: 0.899718701839447:  84%|████████▎ | 21628/25880 [4:25:11<48:26,  1.46it/s] 
1|21629|Loss: 0.899718701839447:  84%|████████▎ | 21629/25880 [4:25:12<48:27,  1.46it/s]
1|21630|Loss: 1.0479774475097656:  84%|████████▎ | 21629/25880 [4:25:12<48:27,  1.46it/s]
1|21630|Loss: 1.0479774475097656:  84%|████████▎ | 21630/25880 [4:25:13<51:23,  1.38it/s]
1|21631|Loss: 0.762188732624054:  84%|████████▎ | 21630/25880 [4:25:13<51:23,  1.38it/s] 
1|21631|Loss: 0.762188732624054:  84%|████████▎ | 21631/25880 [4:25:13<53:25,  1.33it/s]
1|21632|Loss: 0.8160610198974609:  84%|████████▎ | 21631/25880 [4:25:14<53:25,  1.33it/s]
1|21632|Loss: 0.8160610198974609:  84%|████████▎ | 21632/25880 [4:25:14<51:42,  1.37it/s]
1|21633|Loss: 0.7556267380714417:  84%|████████▎ | 21632/25880 [4:25:14<51:42,  1.37it/s]
1|21633|Loss: 0.7556267380714417:  84%|████████▎ | 21633/25880 [4:25:15<52:21,  1.35it/s]
1|21634|Loss: 0.8460643291473389:  84%|████████▎ | 21633/25880 [4:25:15<52:21,  1.35it/s]
1|21634|Loss: 0.8460643291473389:  84%|████████▎ | 21634/25880 [4:25:16<52:02,  1.36it/s]
1|21635|Loss: 0.8690076470375061:  84%|████████▎ | 21634/25880 [4:25:16<52:02,  1.36it/s]
1|21635|Loss: 0.8690076470375061:  84%|████████▎ | 21635/25880 [4:25:16<52:03,  1.36it/s]
1|21636|Loss: 0.8739031553268433:  84%|████████▎ | 21635/25880 [4:25:17<52:03,  1.36it/s]
1|21636|Loss: 0.8739031553268433:  84%|████████▎ | 21636/25880 [4:25:17<52:20,  1.35it/s]
1|21637|Loss: 0.8849403858184814:  84%|████████▎ | 21636/25880 [4:25:17<52:20,  1.35it/s]
1|21637|Loss: 0.8849403858184814:  84%|████████▎ | 21637/25880 [4:25:18<53:35,  1.32it/s]
1|21638|Loss: 0.6917116045951843:  84%|████████▎ | 21637/25880 [4:25:18<53:35,  1.32it/s]
1|21638|Loss: 0.6917116045951843:  84%|████████▎ | 21638/25880 [4:25:19<53:36,  1.32it/s]
1|21639|Loss: 0.8141573071479797:  84%|████████▎ | 21638/25880 [4:25:19<53:36,  1.32it/s]
1|21639|Loss: 0.8141573071479797:  84%|████████▎ | 21639/25880 [4:25:19<53:19,  1.33it/s]
1|21640|Loss: 0.7042425870895386:  84%|████████▎ | 21639/25880 [4:25:20<53:19,  1.33it/s]
1|21640|Loss: 0.7042425870895386:  84%|████████▎ | 21640/25880 [4:25:20<55:03,  1.28it/s]
1|21641|Loss: 0.733547568321228:  84%|████████▎ | 21640/25880 [4:25:21<55:03,  1.28it/s] 
1|21641|Loss: 0.733547568321228:  84%|████████▎ | 21641/25880 [4:25:21<54:11,  1.30it/s]
1|21642|Loss: 0.7440634965896606:  84%|████████▎ | 21641/25880 [4:25:21<54:11,  1.30it/s]
1|21642|Loss: 0.7440634965896606:  84%|████████▎ | 21642/25880 [4:25:22<50:48,  1.39it/s]
1|21643|Loss: 0.773597776889801:  84%|████████▎ | 21642/25880 [4:25:22<50:48,  1.39it/s] 
1|21643|Loss: 0.773597776889801:  84%|████████▎ | 21643/25880 [4:25:22<45:50,  1.54it/s]
1|21644|Loss: 0.9095967411994934:  84%|████████▎ | 21643/25880 [4:25:22<45:50,  1.54it/s]
1|21644|Loss: 0.9095967411994934:  84%|████████▎ | 21644/25880 [4:25:23<48:42,  1.45it/s]
1|21645|Loss: 0.8620663285255432:  84%|████████▎ | 21644/25880 [4:25:23<48:42,  1.45it/s]
1|21645|Loss: 0.8620663285255432:  84%|████████▎ | 21645/25880 [4:25:23<45:35,  1.55it/s]
1|21646|Loss: 0.6758043766021729:  84%|████████▎ | 21645/25880 [4:25:24<45:35,  1.55it/s]
1|21646|Loss: 0.6758043766021729:  84%|████████▎ | 21646/25880 [4:25:24<46:13,  1.53it/s]
1|21647|Loss: 0.8877788186073303:  84%|████████▎ | 21646/25880 [4:25:24<46:13,  1.53it/s]
1|21647|Loss: 0.8877788186073303:  84%|████████▎ | 21647/25880 [4:25:25<51:03,  1.38it/s]
1|21648|Loss: 0.8630357384681702:  84%|████████▎ | 21647/25880 [4:25:25<51:03,  1.38it/s]
1|21648|Loss: 0.8630357384681702:  84%|████████▎ | 21648/25880 [4:25:26<54:23,  1.30it/s]
1|21649|Loss: 0.8860313892364502:  84%|████████▎ | 21648/25880 [4:25:26<54:23,  1.30it/s]
1|21649|Loss: 0.8860313892364502:  84%|████████▎ | 21649/25880 [4:25:27<54:18,  1.30it/s]
1|21650|Loss: 0.7440341114997864:  84%|████████▎ | 21649/25880 [4:25:27<54:18,  1.30it/s]
1|21650|Loss: 0.7440341114997864:  84%|████████▎ | 21650/25880 [4:25:27<52:54,  1.33it/s]
1|21651|Loss: 0.7350170612335205:  84%|████████▎ | 21650/25880 [4:25:28<52:54,  1.33it/s]
1|21651|Loss: 0.7350170612335205:  84%|████████▎ | 21651/25880 [4:25:28<54:54,  1.28it/s]
1|21652|Loss: 0.890282392501831:  84%|████████▎ | 21651/25880 [4:25:29<54:54,  1.28it/s] 
1|21652|Loss: 0.890282392501831:  84%|████████▎ | 21652/25880 [4:25:29<54:46,  1.29it/s]
1|21653|Loss: 0.8428537845611572:  84%|████████▎ | 21652/25880 [4:25:29<54:46,  1.29it/s]
1|21653|Loss: 0.8428537845611572:  84%|████████▎ | 21653/25880 [4:25:30<55:57,  1.26it/s]
1|21654|Loss: 0.7876453399658203:  84%|████████▎ | 21653/25880 [4:25:30<55:57,  1.26it/s]
1|21654|Loss: 0.7876453399658203:  84%|████████▎ | 21654/25880 [4:25:30<53:11,  1.32it/s]
1|21655|Loss: 0.8884491920471191:  84%|████████▎ | 21654/25880 [4:25:31<53:11,  1.32it/s]
1|21655|Loss: 0.8884491920471191:  84%|████████▎ | 21655/25880 [4:25:31<54:45,  1.29it/s]
1|21656|Loss: 0.8095930218696594:  84%|████████▎ | 21655/25880 [4:25:32<54:45,  1.29it/s]
1|21656|Loss: 0.8095930218696594:  84%|████████▎ | 21656/25880 [4:25:32<54:31,  1.29it/s]
1|21657|Loss: 0.9049633741378784:  84%|████████▎ | 21656/25880 [4:25:32<54:31,  1.29it/s]
1|21657|Loss: 0.9049633741378784:  84%|████████▎ | 21657/25880 [4:25:33<54:03,  1.30it/s]
1|21658|Loss: 0.819536030292511:  84%|████████▎ | 21657/25880 [4:25:33<54:03,  1.30it/s] 
1|21658|Loss: 0.819536030292511:  84%|████████▎ | 21658/25880 [4:25:34<55:03,  1.28it/s]
1|21659|Loss: 0.8075813055038452:  84%|████████▎ | 21658/25880 [4:25:34<55:03,  1.28it/s]
1|21659|Loss: 0.8075813055038452:  84%|████████▎ | 21659/25880 [4:25:34<51:49,  1.36it/s]
1|21660|Loss: 0.7816373109817505:  84%|████████▎ | 21659/25880 [4:25:35<51:49,  1.36it/s]
1|21660|Loss: 0.7816373109817505:  84%|████████▎ | 21660/25880 [4:25:35<51:59,  1.35it/s]
1|21661|Loss: 1.0166070461273193:  84%|████████▎ | 21660/25880 [4:25:35<51:59,  1.35it/s]
1|21661|Loss: 1.0166070461273193:  84%|████████▎ | 21661/25880 [4:25:36<50:38,  1.39it/s]
1|21662|Loss: 0.7373554706573486:  84%|████████▎ | 21661/25880 [4:25:36<50:38,  1.39it/s]
1|21662|Loss: 0.7373554706573486:  84%|████████▎ | 21662/25880 [4:25:36<51:28,  1.37it/s]
1|21663|Loss: 0.8803573250770569:  84%|████████▎ | 21662/25880 [4:25:37<51:28,  1.37it/s]
1|21663|Loss: 0.8803573250770569:  84%|████████▎ | 21663/25880 [4:25:37<51:50,  1.36it/s]
1|21664|Loss: 0.8293972611427307:  84%|████████▎ | 21663/25880 [4:25:37<51:50,  1.36it/s]
1|21664|Loss: 0.8293972611427307:  84%|████████▎ | 21664/25880 [4:25:38<48:55,  1.44it/s]
1|21665|Loss: 0.8924686908721924:  84%|████████▎ | 21664/25880 [4:25:38<48:55,  1.44it/s]
1|21665|Loss: 0.8924686908721924:  84%|████████▎ | 21665/25880 [4:25:38<47:21,  1.48it/s]
1|21666|Loss: 0.8552095890045166:  84%|████████▎ | 21665/25880 [4:25:39<47:21,  1.48it/s]
1|21666|Loss: 0.8552095890045166:  84%|████████▎ | 21666/25880 [4:25:39<46:34,  1.51it/s]
1|21667|Loss: 0.8843741416931152:  84%|████████▎ | 21666/25880 [4:25:39<46:34,  1.51it/s]
1|21667|Loss: 0.8843741416931152:  84%|████████▎ | 21667/25880 [4:25:40<47:31,  1.48it/s]
1|21668|Loss: 0.8629825711250305:  84%|████████▎ | 21667/25880 [4:25:40<47:31,  1.48it/s]
1|21668|Loss: 0.8629825711250305:  84%|████████▎ | 21668/25880 [4:25:40<49:33,  1.42it/s]
1|21669|Loss: 0.8182045817375183:  84%|████████▎ | 21668/25880 [4:25:41<49:33,  1.42it/s]
1|21669|Loss: 0.8182045817375183:  84%|████████▎ | 21669/25880 [4:25:41<53:33,  1.31it/s]
1|21670|Loss: 0.8567410707473755:  84%|████████▎ | 21669/25880 [4:25:42<53:33,  1.31it/s]
1|21670|Loss: 0.8567410707473755:  84%|████████▎ | 21670/25880 [4:25:42<54:35,  1.29it/s]
1|21671|Loss: 0.8041407465934753:  84%|████████▎ | 21670/25880 [4:25:43<54:35,  1.29it/s]
1|21671|Loss: 0.8041407465934753:  84%|████████▎ | 21671/25880 [4:25:43<55:38,  1.26it/s]
1|21672|Loss: 0.7117137312889099:  84%|████████▎ | 21671/25880 [4:25:43<55:38,  1.26it/s]
1|21672|Loss: 0.7117137312889099:  84%|████████▎ | 21672/25880 [4:25:44<53:12,  1.32it/s]
1|21673|Loss: 0.8261178135871887:  84%|████████▎ | 21672/25880 [4:25:44<53:12,  1.32it/s]
1|21673|Loss: 0.8261178135871887:  84%|████████▎ | 21673/25880 [4:25:44<52:24,  1.34it/s]
1|21674|Loss: 0.8444423675537109:  84%|████████▎ | 21673/25880 [4:25:45<52:24,  1.34it/s]
1|21674|Loss: 0.8444423675537109:  84%|████████▎ | 21674/25880 [4:25:45<53:23,  1.31it/s]
1|21675|Loss: 0.8246675729751587:  84%|████████▎ | 21674/25880 [4:25:46<53:23,  1.31it/s]
1|21675|Loss: 0.8246675729751587:  84%|████████▍ | 21675/25880 [4:25:46<55:23,  1.27it/s]
1|21676|Loss: 0.7995766401290894:  84%|████████▍ | 21675/25880 [4:25:46<55:23,  1.27it/s]
1|21676|Loss: 0.7995766401290894:  84%|████████▍ | 21676/25880 [4:25:47<55:06,  1.27it/s]
1|21677|Loss: 0.9546321630477905:  84%|████████▍ | 21676/25880 [4:25:47<55:06,  1.27it/s]
1|21677|Loss: 0.9546321630477905:  84%|████████▍ | 21677/25880 [4:25:48<53:43,  1.30it/s]
1|21678|Loss: 0.9068681001663208:  84%|████████▍ | 21677/25880 [4:25:48<53:43,  1.30it/s]
1|21678|Loss: 0.9068681001663208:  84%|████████▍ | 21678/25880 [4:25:48<50:14,  1.39it/s]
1|21679|Loss: 0.7035817503929138:  84%|████████▍ | 21678/25880 [4:25:49<50:14,  1.39it/s]
1|21679|Loss: 0.7035817503929138:  84%|████████▍ | 21679/25880 [4:25:49<49:47,  1.41it/s]
1|21680|Loss: 0.8242293000221252:  84%|████████▍ | 21679/25880 [4:25:49<49:47,  1.41it/s]
1|21680|Loss: 0.8242293000221252:  84%|████████▍ | 21680/25880 [4:25:50<50:19,  1.39it/s]
1|21681|Loss: 0.7984506487846375:  84%|████████▍ | 21680/25880 [4:25:50<50:19,  1.39it/s]
1|21681|Loss: 0.7984506487846375:  84%|████████▍ | 21681/25880 [4:25:50<50:46,  1.38it/s]
1|21682|Loss: 0.8518255949020386:  84%|████████▍ | 21681/25880 [4:25:51<50:46,  1.38it/s]
1|21682|Loss: 0.8518255949020386:  84%|████████▍ | 21682/25880 [4:25:51<51:05,  1.37it/s]
1|21683|Loss: 0.8135424852371216:  84%|████████▍ | 21682/25880 [4:25:51<51:05,  1.37it/s]
1|21683|Loss: 0.8135424852371216:  84%|████████▍ | 21683/25880 [4:25:52<49:17,  1.42it/s]
1|21684|Loss: 0.7776585221290588:  84%|████████▍ | 21683/25880 [4:25:52<49:17,  1.42it/s]
1|21684|Loss: 0.7776585221290588:  84%|████████▍ | 21684/25880 [4:25:52<49:30,  1.41it/s]
1|21685|Loss: 0.9060481190681458:  84%|████████▍ | 21684/25880 [4:25:53<49:30,  1.41it/s]
1|21685|Loss: 0.9060481190681458:  84%|████████▍ | 21685/25880 [4:25:53<48:14,  1.45it/s]
1|21686|Loss: 0.7589617967605591:  84%|████████▍ | 21685/25880 [4:25:53<48:14,  1.45it/s]
1|21686|Loss: 0.7589617967605591:  84%|████████▍ | 21686/25880 [4:25:54<50:40,  1.38it/s]
1|21687|Loss: 0.6651307344436646:  84%|████████▍ | 21686/25880 [4:25:54<50:40,  1.38it/s]
1|21687|Loss: 0.6651307344436646:  84%|████████▍ | 21687/25880 [4:25:55<51:28,  1.36it/s]
1|21688|Loss: 0.9284016489982605:  84%|████████▍ | 21687/25880 [4:25:55<51:28,  1.36it/s]
1|21688|Loss: 0.9284016489982605:  84%|████████▍ | 21688/25880 [4:25:56<53:51,  1.30it/s]
1|21689|Loss: 0.8399531245231628:  84%|████████▍ | 21688/25880 [4:25:56<53:51,  1.30it/s]
1|21689|Loss: 0.8399531245231628:  84%|████████▍ | 21689/25880 [4:25:56<52:13,  1.34it/s]
1|21690|Loss: 0.7962950468063354:  84%|████████▍ | 21689/25880 [4:25:57<52:13,  1.34it/s]
1|21690|Loss: 0.7962950468063354:  84%|████████▍ | 21690/25880 [4:25:57<49:55,  1.40it/s]
1|21691|Loss: 0.8319603800773621:  84%|████████▍ | 21690/25880 [4:25:57<49:55,  1.40it/s]
1|21691|Loss: 0.8319603800773621:  84%|████████▍ | 21691/25880 [4:25:58<51:26,  1.36it/s]
1|21692|Loss: 0.7701754570007324:  84%|████████▍ | 21691/25880 [4:25:58<51:26,  1.36it/s]
1|21692|Loss: 0.7701754570007324:  84%|████████▍ | 21692/25880 [4:25:58<53:39,  1.30it/s]
1|21693|Loss: 0.8888543844223022:  84%|████████▍ | 21692/25880 [4:25:59<53:39,  1.30it/s]
1|21693|Loss: 0.8888543844223022:  84%|████████▍ | 21693/25880 [4:25:59<53:30,  1.30it/s]
1|21694|Loss: 0.8011201620101929:  84%|████████▍ | 21693/25880 [4:26:00<53:30,  1.30it/s]
1|21694|Loss: 0.8011201620101929:  84%|████████▍ | 21694/25880 [4:26:00<55:52,  1.25it/s]
1|21695|Loss: 0.786389946937561:  84%|████████▍ | 21694/25880 [4:26:01<55:52,  1.25it/s] 
1|21695|Loss: 0.786389946937561:  84%|████████▍ | 21695/25880 [4:26:01<54:39,  1.28it/s]
1|21696|Loss: 0.9232866168022156:  84%|████████▍ | 21695/25880 [4:26:01<54:39,  1.28it/s]
1|21696|Loss: 0.9232866168022156:  84%|████████▍ | 21696/25880 [4:26:01<49:49,  1.40it/s]
1|21697|Loss: 0.7078537940979004:  84%|████████▍ | 21696/25880 [4:26:02<49:49,  1.40it/s]
1|21697|Loss: 0.7078537940979004:  84%|████████▍ | 21697/25880 [4:26:02<45:33,  1.53it/s]
1|21698|Loss: 0.8226193785667419:  84%|████████▍ | 21697/25880 [4:26:02<45:33,  1.53it/s]
1|21698|Loss: 0.8226193785667419:  84%|████████▍ | 21698/25880 [4:26:02<42:37,  1.64it/s]
1|21699|Loss: 0.7011298537254333:  84%|████████▍ | 21698/25880 [4:26:03<42:37,  1.64it/s]
1|21699|Loss: 0.7011298537254333:  84%|████████▍ | 21699/25880 [4:26:03<45:23,  1.54it/s]
1|21700|Loss: 0.7533126473426819:  84%|████████▍ | 21699/25880 [4:26:04<45:23,  1.54it/s]
1|21700|Loss: 0.7533126473426819:  84%|████████▍ | 21700/25880 [4:26:04<45:20,  1.54it/s]
1|21701|Loss: 0.8655807971954346:  84%|████████▍ | 21700/25880 [4:26:04<45:20,  1.54it/s]
1|21701|Loss: 0.8655807971954346:  84%|████████▍ | 21701/25880 [4:26:04<44:06,  1.58it/s]
1|21702|Loss: 0.7197500467300415:  84%|████████▍ | 21701/25880 [4:26:05<44:06,  1.58it/s]
1|21702|Loss: 0.7197500467300415:  84%|████████▍ | 21702/25880 [4:26:05<53:22,  1.30it/s]
1|21703|Loss: 0.9088317155838013:  84%|████████▍ | 21702/25880 [4:26:06<53:22,  1.30it/s]
1|21703|Loss: 0.9088317155838013:  84%|████████▍ | 21703/25880 [4:26:06<54:40,  1.27it/s]
1|21704|Loss: 0.833165168762207:  84%|████████▍ | 21703/25880 [4:26:07<54:40,  1.27it/s] 
1|21704|Loss: 0.833165168762207:  84%|████████▍ | 21704/25880 [4:26:07<53:00,  1.31it/s]
1|21705|Loss: 0.9530050158500671:  84%|████████▍ | 21704/25880 [4:26:07<53:00,  1.31it/s]
1|21705|Loss: 0.9530050158500671:  84%|████████▍ | 21705/25880 [4:26:08<52:10,  1.33it/s]
1|21706|Loss: 0.9191108345985413:  84%|████████▍ | 21705/25880 [4:26:08<52:10,  1.33it/s]
1|21706|Loss: 0.9191108345985413:  84%|████████▍ | 21706/25880 [4:26:08<52:08,  1.33it/s]
1|21707|Loss: 0.8615881204605103:  84%|████████▍ | 21706/25880 [4:26:09<52:08,  1.33it/s]
1|21707|Loss: 0.8615881204605103:  84%|████████▍ | 21707/25880 [4:26:09<50:27,  1.38it/s]
1|21708|Loss: 0.8048768639564514:  84%|████████▍ | 21707/25880 [4:26:10<50:27,  1.38it/s]
1|21708|Loss: 0.8048768639564514:  84%|████████▍ | 21708/25880 [4:26:10<49:40,  1.40it/s]
1|21709|Loss: 0.8023414015769958:  84%|████████▍ | 21708/25880 [4:26:10<49:40,  1.40it/s]
1|21709|Loss: 0.8023414015769958:  84%|████████▍ | 21709/25880 [4:26:10<46:10,  1.51it/s]
1|21710|Loss: 0.7545635104179382:  84%|████████▍ | 21709/25880 [4:26:11<46:10,  1.51it/s]
1|21710|Loss: 0.7545635104179382:  84%|████████▍ | 21710/25880 [4:26:11<44:36,  1.56it/s]
1|21711|Loss: 0.8867436647415161:  84%|████████▍ | 21710/25880 [4:26:11<44:36,  1.56it/s]
1|21711|Loss: 0.8867436647415161:  84%|████████▍ | 21711/25880 [4:26:12<47:54,  1.45it/s]
1|21712|Loss: 0.9525080919265747:  84%|████████▍ | 21711/25880 [4:26:12<47:54,  1.45it/s]
1|21712|Loss: 0.9525080919265747:  84%|████████▍ | 21712/25880 [4:26:13<51:19,  1.35it/s]
1|21713|Loss: 0.777296245098114:  84%|████████▍ | 21712/25880 [4:26:13<51:19,  1.35it/s] 
1|21713|Loss: 0.777296245098114:  84%|████████▍ | 21713/25880 [4:26:13<49:46,  1.40it/s]
1|21714|Loss: 0.8094650506973267:  84%|████████▍ | 21713/25880 [4:26:14<49:46,  1.40it/s]
1|21714|Loss: 0.8094650506973267:  84%|████████▍ | 21714/25880 [4:26:14<46:12,  1.50it/s]
1|21715|Loss: 0.8528011441230774:  84%|████████▍ | 21714/25880 [4:26:14<46:12,  1.50it/s]
1|21715|Loss: 0.8528011441230774:  84%|████████▍ | 21715/25880 [4:26:15<48:47,  1.42it/s]
1|21716|Loss: 0.9454231858253479:  84%|████████▍ | 21715/25880 [4:26:15<48:47,  1.42it/s]
1|21716|Loss: 0.9454231858253479:  84%|████████▍ | 21716/25880 [4:26:15<50:07,  1.38it/s]
1|21717|Loss: 0.7898035049438477:  84%|████████▍ | 21716/25880 [4:26:16<50:07,  1.38it/s]
1|21717|Loss: 0.7898035049438477:  84%|████████▍ | 21717/25880 [4:26:16<50:00,  1.39it/s]
1|21718|Loss: 0.7288125157356262:  84%|████████▍ | 21717/25880 [4:26:17<50:00,  1.39it/s]
1|21718|Loss: 0.7288125157356262:  84%|████████▍ | 21718/25880 [4:26:17<51:20,  1.35it/s]
1|21719|Loss: 0.801524817943573:  84%|████████▍ | 21718/25880 [4:26:17<51:20,  1.35it/s] 
1|21719|Loss: 0.801524817943573:  84%|████████▍ | 21719/25880 [4:26:18<50:59,  1.36it/s]
1|21720|Loss: 0.7409036755561829:  84%|████████▍ | 21719/25880 [4:26:18<50:59,  1.36it/s]
1|21720|Loss: 0.7409036755561829:  84%|████████▍ | 21720/25880 [4:26:18<49:07,  1.41it/s]
1|21721|Loss: 0.9318931102752686:  84%|████████▍ | 21720/25880 [4:26:19<49:07,  1.41it/s]
1|21721|Loss: 0.9318931102752686:  84%|████████▍ | 21721/25880 [4:26:19<47:40,  1.45it/s]
1|21722|Loss: 0.7883183360099792:  84%|████████▍ | 21721/25880 [4:26:19<47:40,  1.45it/s]
1|21722|Loss: 0.7883183360099792:  84%|████████▍ | 21722/25880 [4:26:20<48:24,  1.43it/s]
1|21723|Loss: 0.7080691456794739:  84%|████████▍ | 21722/25880 [4:26:20<48:24,  1.43it/s]
1|21723|Loss: 0.7080691456794739:  84%|████████▍ | 21723/25880 [4:26:20<47:39,  1.45it/s]
1|21724|Loss: 0.8150926828384399:  84%|████████▍ | 21723/25880 [4:26:21<47:39,  1.45it/s]
1|21724|Loss: 0.8150926828384399:  84%|████████▍ | 21724/25880 [4:26:21<45:10,  1.53it/s]
1|21725|Loss: 0.8167896270751953:  84%|████████▍ | 21724/25880 [4:26:21<45:10,  1.53it/s]
1|21725|Loss: 0.8167896270751953:  84%|████████▍ | 21725/25880 [4:26:22<49:06,  1.41it/s]
1|21726|Loss: 0.7527177929878235:  84%|████████▍ | 21725/25880 [4:26:22<49:06,  1.41it/s]
1|21726|Loss: 0.7527177929878235:  84%|████████▍ | 21726/25880 [4:26:23<53:31,  1.29it/s]
1|21727|Loss: 0.8608877658843994:  84%|████████▍ | 21726/25880 [4:26:23<53:31,  1.29it/s]
1|21727|Loss: 0.8608877658843994:  84%|████████▍ | 21727/25880 [4:26:23<51:33,  1.34it/s]
1|21728|Loss: 0.9057018756866455:  84%|████████▍ | 21727/25880 [4:26:24<51:33,  1.34it/s]
1|21728|Loss: 0.9057018756866455:  84%|████████▍ | 21728/25880 [4:26:24<50:19,  1.38it/s]
1|21729|Loss: 0.8692243099212646:  84%|████████▍ | 21728/25880 [4:26:24<50:19,  1.38it/s]
1|21729|Loss: 0.8692243099212646:  84%|████████▍ | 21729/25880 [4:26:25<49:46,  1.39it/s]
1|21730|Loss: 0.8161411881446838:  84%|████████▍ | 21729/25880 [4:26:25<49:46,  1.39it/s]
1|21730|Loss: 0.8161411881446838:  84%|████████▍ | 21730/25880 [4:26:25<50:07,  1.38it/s]
1|21731|Loss: 0.8232026696205139:  84%|████████▍ | 21730/25880 [4:26:26<50:07,  1.38it/s]
1|21731|Loss: 0.8232026696205139:  84%|████████▍ | 21731/25880 [4:26:26<49:49,  1.39it/s]
1|21732|Loss: 0.8767555356025696:  84%|████████▍ | 21731/25880 [4:26:27<49:49,  1.39it/s]
1|21732|Loss: 0.8767555356025696:  84%|████████▍ | 21732/25880 [4:26:27<48:24,  1.43it/s]
1|21733|Loss: 0.7964911460876465:  84%|████████▍ | 21732/25880 [4:26:27<48:24,  1.43it/s]
1|21733|Loss: 0.7964911460876465:  84%|████████▍ | 21733/25880 [4:26:28<50:44,  1.36it/s]
1|21734|Loss: 0.9364763498306274:  84%|████████▍ | 21733/25880 [4:26:28<50:44,  1.36it/s]
1|21734|Loss: 0.9364763498306274:  84%|████████▍ | 21734/25880 [4:26:28<48:49,  1.42it/s]
1|21735|Loss: 0.7971877455711365:  84%|████████▍ | 21734/25880 [4:26:29<48:49,  1.42it/s]
1|21735|Loss: 0.7971877455711365:  84%|████████▍ | 21735/25880 [4:26:29<49:35,  1.39it/s]
1|21736|Loss: 0.707278847694397:  84%|████████▍ | 21735/25880 [4:26:29<49:35,  1.39it/s] 
1|21736|Loss: 0.707278847694397:  84%|████████▍ | 21736/25880 [4:26:30<50:09,  1.38it/s]
1|21737|Loss: 0.8366482257843018:  84%|████████▍ | 21736/25880 [4:26:30<50:09,  1.38it/s]
1|21737|Loss: 0.8366482257843018:  84%|████████▍ | 21737/25880 [4:26:31<52:16,  1.32it/s]
1|21738|Loss: 0.9247021079063416:  84%|████████▍ | 21737/25880 [4:26:31<52:16,  1.32it/s]
1|21738|Loss: 0.9247021079063416:  84%|████████▍ | 21738/25880 [4:26:31<51:53,  1.33it/s]
1|21739|Loss: 0.7459614276885986:  84%|████████▍ | 21738/25880 [4:26:32<51:53,  1.33it/s]
1|21739|Loss: 0.7459614276885986:  84%|████████▍ | 21739/25880 [4:26:32<50:46,  1.36it/s]
1|21740|Loss: 1.0295215845108032:  84%|████████▍ | 21739/25880 [4:26:32<50:46,  1.36it/s]
1|21740|Loss: 1.0295215845108032:  84%|████████▍ | 21740/25880 [4:26:33<52:30,  1.31it/s]
1|21741|Loss: 0.804204523563385:  84%|████████▍ | 21740/25880 [4:26:33<52:30,  1.31it/s] 
1|21741|Loss: 0.804204523563385:  84%|████████▍ | 21741/25880 [4:26:34<50:30,  1.37it/s]
1|21742|Loss: 0.8072754740715027:  84%|████████▍ | 21741/25880 [4:26:34<50:30,  1.37it/s]
1|21742|Loss: 0.8072754740715027:  84%|████████▍ | 21742/25880 [4:26:34<51:42,  1.33it/s]
1|21743|Loss: 0.8667394518852234:  84%|████████▍ | 21742/25880 [4:26:35<51:42,  1.33it/s]
1|21743|Loss: 0.8667394518852234:  84%|████████▍ | 21743/25880 [4:26:35<49:51,  1.38it/s]
1|21744|Loss: 0.7560453414916992:  84%|████████▍ | 21743/25880 [4:26:35<49:51,  1.38it/s]
1|21744|Loss: 0.7560453414916992:  84%|████████▍ | 21744/25880 [4:26:36<51:53,  1.33it/s]
1|21745|Loss: 0.8151721358299255:  84%|████████▍ | 21744/25880 [4:26:36<51:53,  1.33it/s]
1|21745|Loss: 0.8151721358299255:  84%|████████▍ | 21745/25880 [4:26:37<53:52,  1.28it/s]
1|21746|Loss: 0.6662250757217407:  84%|████████▍ | 21745/25880 [4:26:37<53:52,  1.28it/s]
1|21746|Loss: 0.6662250757217407:  84%|████████▍ | 21746/25880 [4:26:37<48:36,  1.42it/s]
1|21747|Loss: 0.7320159673690796:  84%|████████▍ | 21746/25880 [4:26:38<48:36,  1.42it/s]
1|21747|Loss: 0.7320159673690796:  84%|████████▍ | 21747/25880 [4:26:38<48:07,  1.43it/s]
1|21748|Loss: 0.9240189790725708:  84%|████████▍ | 21747/25880 [4:26:38<48:07,  1.43it/s]
1|21748|Loss: 0.9240189790725708:  84%|████████▍ | 21748/25880 [4:26:39<49:05,  1.40it/s]
1|21749|Loss: 0.9457963705062866:  84%|████████▍ | 21748/25880 [4:26:39<49:05,  1.40it/s]
1|21749|Loss: 0.9457963705062866:  84%|████████▍ | 21749/25880 [4:26:39<49:22,  1.39it/s]
1|21750|Loss: 0.7313523292541504:  84%|████████▍ | 21749/25880 [4:26:40<49:22,  1.39it/s]
1|21750|Loss: 0.7313523292541504:  84%|████████▍ | 21750/25880 [4:26:40<47:32,  1.45it/s]
1|21751|Loss: 0.8580330014228821:  84%|████████▍ | 21750/25880 [4:26:40<47:32,  1.45it/s]
1|21751|Loss: 0.8580330014228821:  84%|████████▍ | 21751/25880 [4:26:41<45:54,  1.50it/s]
1|21752|Loss: 0.8687941431999207:  84%|████████▍ | 21751/25880 [4:26:41<45:54,  1.50it/s]
1|21752|Loss: 0.8687941431999207:  84%|████████▍ | 21752/25880 [4:26:41<45:07,  1.52it/s]
1|21753|Loss: 0.8576222658157349:  84%|████████▍ | 21752/25880 [4:26:42<45:07,  1.52it/s]
1|21753|Loss: 0.8576222658157349:  84%|████████▍ | 21753/25880 [4:26:42<44:47,  1.54it/s]
1|21754|Loss: 0.956236720085144:  84%|████████▍ | 21753/25880 [4:26:42<44:47,  1.54it/s] 
1|21754|Loss: 0.956236720085144:  84%|████████▍ | 21754/25880 [4:26:42<44:14,  1.55it/s]
1|21755|Loss: 0.8405992984771729:  84%|████████▍ | 21754/25880 [4:26:43<44:14,  1.55it/s]
1|21755|Loss: 0.8405992984771729:  84%|████████▍ | 21755/25880 [4:26:43<45:06,  1.52it/s]
1|21756|Loss: 0.7879496812820435:  84%|████████▍ | 21755/25880 [4:26:44<45:06,  1.52it/s]
1|21756|Loss: 0.7879496812820435:  84%|████████▍ | 21756/25880 [4:26:44<46:30,  1.48it/s]
1|21757|Loss: 0.8996381759643555:  84%|████████▍ | 21756/25880 [4:26:44<46:30,  1.48it/s]
1|21757|Loss: 0.8996381759643555:  84%|████████▍ | 21757/25880 [4:26:45<48:29,  1.42it/s]
1|21758|Loss: 0.6933314204216003:  84%|████████▍ | 21757/25880 [4:26:45<48:29,  1.42it/s]
1|21758|Loss: 0.6933314204216003:  84%|████████▍ | 21758/25880 [4:26:45<49:31,  1.39it/s]
1|21759|Loss: 0.7962344288825989:  84%|████████▍ | 21758/25880 [4:26:46<49:31,  1.39it/s]
1|21759|Loss: 0.7962344288825989:  84%|████████▍ | 21759/25880 [4:26:46<49:23,  1.39it/s]
1|21760|Loss: 0.8602763414382935:  84%|████████▍ | 21759/25880 [4:26:47<49:23,  1.39it/s]
1|21760|Loss: 0.8602763414382935:  84%|████████▍ | 21760/25880 [4:26:47<51:43,  1.33it/s]
1|21761|Loss: 0.9499424695968628:  84%|████████▍ | 21760/25880 [4:26:47<51:43,  1.33it/s]
1|21761|Loss: 0.9499424695968628:  84%|████████▍ | 21761/25880 [4:26:48<50:33,  1.36it/s]
1|21762|Loss: 0.8031298518180847:  84%|████████▍ | 21761/25880 [4:26:48<50:33,  1.36it/s]
1|21762|Loss: 0.8031298518180847:  84%|████████▍ | 21762/25880 [4:26:48<49:38,  1.38it/s]
1|21763|Loss: 0.773898184299469:  84%|████████▍ | 21762/25880 [4:26:49<49:38,  1.38it/s] 
1|21763|Loss: 0.773898184299469:  84%|████████▍ | 21763/25880 [4:26:49<51:38,  1.33it/s]
1|21764|Loss: 0.7522655129432678:  84%|████████▍ | 21763/25880 [4:26:50<51:38,  1.33it/s]
1|21764|Loss: 0.7522655129432678:  84%|████████▍ | 21764/25880 [4:26:50<51:21,  1.34it/s]
1|21765|Loss: 0.8343982100486755:  84%|████████▍ | 21764/25880 [4:26:50<51:21,  1.34it/s]
1|21765|Loss: 0.8343982100486755:  84%|████████▍ | 21765/25880 [4:26:51<49:17,  1.39it/s]
1|21766|Loss: 0.8868920803070068:  84%|████████▍ | 21765/25880 [4:26:51<49:17,  1.39it/s]
1|21766|Loss: 0.8868920803070068:  84%|████████▍ | 21766/25880 [4:26:51<47:38,  1.44it/s]
1|21767|Loss: 0.8217527270317078:  84%|████████▍ | 21766/25880 [4:26:52<47:38,  1.44it/s]
1|21767|Loss: 0.8217527270317078:  84%|████████▍ | 21767/25880 [4:26:52<48:17,  1.42it/s]
1|21768|Loss: 0.8028074502944946:  84%|████████▍ | 21767/25880 [4:26:52<48:17,  1.42it/s]
1|21768|Loss: 0.8028074502944946:  84%|████████▍ | 21768/25880 [4:26:53<49:06,  1.40it/s]
1|21769|Loss: 0.8477717638015747:  84%|████████▍ | 21768/25880 [4:26:53<49:06,  1.40it/s]
1|21769|Loss: 0.8477717638015747:  84%|████████▍ | 21769/25880 [4:26:53<50:56,  1.35it/s]
1|21770|Loss: 0.9191224575042725:  84%|████████▍ | 21769/25880 [4:26:54<50:56,  1.35it/s]
1|21770|Loss: 0.9191224575042725:  84%|████████▍ | 21770/25880 [4:26:54<50:32,  1.36it/s]
1|21771|Loss: 0.8497909903526306:  84%|████████▍ | 21770/25880 [4:26:55<50:32,  1.36it/s]
1|21771|Loss: 0.8497909903526306:  84%|████████▍ | 21771/25880 [4:26:55<50:11,  1.36it/s]
1|21772|Loss: 0.8876770734786987:  84%|████████▍ | 21771/25880 [4:26:55<50:11,  1.36it/s]
1|21772|Loss: 0.8876770734786987:  84%|████████▍ | 21772/25880 [4:26:55<45:29,  1.51it/s]
1|21773|Loss: 0.843096137046814:  84%|████████▍ | 21772/25880 [4:26:56<45:29,  1.51it/s] 
1|21773|Loss: 0.843096137046814:  84%|████████▍ | 21773/25880 [4:26:56<43:43,  1.57it/s]
1|21774|Loss: 0.8719139099121094:  84%|████████▍ | 21773/25880 [4:26:56<43:43,  1.57it/s]
1|21774|Loss: 0.8719139099121094:  84%|████████▍ | 21774/25880 [4:26:57<43:14,  1.58it/s]
1|21775|Loss: 0.892170786857605:  84%|████████▍ | 21774/25880 [4:26:57<43:14,  1.58it/s] 
1|21775|Loss: 0.892170786857605:  84%|████████▍ | 21775/25880 [4:26:57<44:51,  1.53it/s]
1|21776|Loss: 0.7624257206916809:  84%|████████▍ | 21775/25880 [4:26:58<44:51,  1.53it/s]
1|21776|Loss: 0.7624257206916809:  84%|████████▍ | 21776/25880 [4:26:58<43:53,  1.56it/s]
1|21777|Loss: 0.7103274464607239:  84%|████████▍ | 21776/25880 [4:26:58<43:53,  1.56it/s]
1|21777|Loss: 0.7103274464607239:  84%|████████▍ | 21777/25880 [4:26:59<48:47,  1.40it/s]
1|21778|Loss: 0.7821968197822571:  84%|████████▍ | 21777/25880 [4:26:59<48:47,  1.40it/s]
1|21778|Loss: 0.7821968197822571:  84%|████████▍ | 21778/25880 [4:27:00<52:26,  1.30it/s]
1|21779|Loss: 0.9378070831298828:  84%|████████▍ | 21778/25880 [4:27:00<52:26,  1.30it/s]
1|21779|Loss: 0.9378070831298828:  84%|████████▍ | 21779/25880 [4:27:00<50:49,  1.34it/s]
1|21780|Loss: 0.8524630665779114:  84%|████████▍ | 21779/25880 [4:27:01<50:49,  1.34it/s]
1|21780|Loss: 0.8524630665779114:  84%|████████▍ | 21780/25880 [4:27:01<49:42,  1.37it/s]
1|21781|Loss: 0.764072835445404:  84%|████████▍ | 21780/25880 [4:27:01<49:42,  1.37it/s] 
1|21781|Loss: 0.764072835445404:  84%|████████▍ | 21781/25880 [4:27:02<49:42,  1.37it/s]
1|21782|Loss: 0.8497390151023865:  84%|████████▍ | 21781/25880 [4:27:02<49:42,  1.37it/s]
1|21782|Loss: 0.8497390151023865:  84%|████████▍ | 21782/25880 [4:27:03<49:12,  1.39it/s]
1|21783|Loss: 0.803809404373169:  84%|████████▍ | 21782/25880 [4:27:03<49:12,  1.39it/s] 
1|21783|Loss: 0.803809404373169:  84%|████████▍ | 21783/25880 [4:27:03<52:27,  1.30it/s]
1|21784|Loss: 0.6315935254096985:  84%|████████▍ | 21783/25880 [4:27:04<52:27,  1.30it/s]
1|21784|Loss: 0.6315935254096985:  84%|████████▍ | 21784/25880 [4:27:04<54:06,  1.26it/s]
1|21785|Loss: 0.8547525405883789:  84%|████████▍ | 21784/25880 [4:27:05<54:06,  1.26it/s]
1|21785|Loss: 0.8547525405883789:  84%|████████▍ | 21785/25880 [4:27:05<54:44,  1.25it/s]
1|21786|Loss: 0.8645966649055481:  84%|████████▍ | 21785/25880 [4:27:05<54:44,  1.25it/s]
1|21786|Loss: 0.8645966649055481:  84%|████████▍ | 21786/25880 [4:27:06<54:54,  1.24it/s]
1|21787|Loss: 0.8633240461349487:  84%|████████▍ | 21786/25880 [4:27:06<54:54,  1.24it/s]
1|21787|Loss: 0.8633240461349487:  84%|████████▍ | 21787/25880 [4:27:07<51:24,  1.33it/s]
1|21788|Loss: 0.7968873381614685:  84%|████████▍ | 21787/25880 [4:27:07<51:24,  1.33it/s]
1|21788|Loss: 0.7968873381614685:  84%|████████▍ | 21788/25880 [4:27:07<45:39,  1.49it/s]
1|21789|Loss: 0.824012041091919:  84%|████████▍ | 21788/25880 [4:27:07<45:39,  1.49it/s] 
1|21789|Loss: 0.824012041091919:  84%|████████▍ | 21789/25880 [4:27:07<42:24,  1.61it/s]
1|21790|Loss: 0.8524845242500305:  84%|████████▍ | 21789/25880 [4:27:08<42:24,  1.61it/s]
1|21790|Loss: 0.8524845242500305:  84%|████████▍ | 21790/25880 [4:27:08<44:10,  1.54it/s]
1|21791|Loss: 0.9567230343818665:  84%|████████▍ | 21790/25880 [4:27:09<44:10,  1.54it/s]
1|21791|Loss: 0.9567230343818665:  84%|████████▍ | 21791/25880 [4:27:09<47:44,  1.43it/s]
1|21792|Loss: 0.8599910140037537:  84%|████████▍ | 21791/25880 [4:27:09<47:44,  1.43it/s]
1|21792|Loss: 0.8599910140037537:  84%|████████▍ | 21792/25880 [4:27:10<48:22,  1.41it/s]
1|21793|Loss: 0.9876645803451538:  84%|████████▍ | 21792/25880 [4:27:10<48:22,  1.41it/s]
1|21793|Loss: 0.9876645803451538:  84%|████████▍ | 21793/25880 [4:27:11<49:53,  1.37it/s]
1|21794|Loss: 0.862606942653656:  84%|████████▍ | 21793/25880 [4:27:11<49:53,  1.37it/s] 
1|21794|Loss: 0.862606942653656:  84%|████████▍ | 21794/25880 [4:27:11<48:11,  1.41it/s]
1|21795|Loss: 0.8011994361877441:  84%|████████▍ | 21794/25880 [4:27:12<48:11,  1.41it/s]
1|21795|Loss: 0.8011994361877441:  84%|████████▍ | 21795/25880 [4:27:12<47:47,  1.42it/s]
1|21796|Loss: 0.9497038722038269:  84%|████████▍ | 21795/25880 [4:27:12<47:47,  1.42it/s]
1|21796|Loss: 0.9497038722038269:  84%|████████▍ | 21796/25880 [4:27:13<46:40,  1.46it/s]
1|21797|Loss: 0.7852365970611572:  84%|████████▍ | 21796/25880 [4:27:13<46:40,  1.46it/s]
1|21797|Loss: 0.7852365970611572:  84%|████████▍ | 21797/25880 [4:27:13<45:44,  1.49it/s]
1|21798|Loss: 0.817478358745575:  84%|████████▍ | 21797/25880 [4:27:14<45:44,  1.49it/s] 
1|21798|Loss: 0.817478358745575:  84%|████████▍ | 21798/25880 [4:27:14<46:09,  1.47it/s]
1|21799|Loss: 0.7845260500907898:  84%|████████▍ | 21798/25880 [4:27:14<46:09,  1.47it/s]
1|21799|Loss: 0.7845260500907898:  84%|████████▍ | 21799/25880 [4:27:15<45:31,  1.49it/s]
1|21800|Loss: 0.7082784175872803:  84%|████████▍ | 21799/25880 [4:27:15<45:31,  1.49it/s]
1|21800|Loss: 0.7082784175872803:  84%|████████▍ | 21800/25880 [4:27:15<48:42,  1.40it/s]
1|21801|Loss: 0.9061646461486816:  84%|████████▍ | 21800/25880 [4:27:16<48:42,  1.40it/s]
1|21801|Loss: 0.9061646461486816:  84%|████████▍ | 21801/25880 [4:27:16<48:08,  1.41it/s]
1|21802|Loss: 0.7768147587776184:  84%|████████▍ | 21801/25880 [4:27:16<48:08,  1.41it/s]
1|21802|Loss: 0.7768147587776184:  84%|████████▍ | 21802/25880 [4:27:17<46:23,  1.47it/s]
1|21803|Loss: 0.919308602809906:  84%|████████▍ | 21802/25880 [4:27:17<46:23,  1.47it/s] 
1|21803|Loss: 0.919308602809906:  84%|████████▍ | 21803/25880 [4:27:17<48:08,  1.41it/s]
1|21804|Loss: 0.6761502027511597:  84%|████████▍ | 21803/25880 [4:27:18<48:08,  1.41it/s]
1|21804|Loss: 0.6761502027511597:  84%|████████▍ | 21804/25880 [4:27:18<48:48,  1.39it/s]
1|21805|Loss: 0.838239848613739:  84%|████████▍ | 21804/25880 [4:27:19<48:48,  1.39it/s] 
1|21805|Loss: 0.838239848613739:  84%|████████▍ | 21805/25880 [4:27:19<48:33,  1.40it/s]
1|21806|Loss: 0.8064837455749512:  84%|████████▍ | 21805/25880 [4:27:19<48:33,  1.40it/s]
1|21806|Loss: 0.8064837455749512:  84%|████████▍ | 21806/25880 [4:27:20<48:55,  1.39it/s]
1|21807|Loss: 0.8099299073219299:  84%|████████▍ | 21806/25880 [4:27:20<48:55,  1.39it/s]
1|21807|Loss: 0.8099299073219299:  84%|████████▍ | 21807/25880 [4:27:20<49:15,  1.38it/s]
1|21808|Loss: 0.8460670113563538:  84%|████████▍ | 21807/25880 [4:27:21<49:15,  1.38it/s]
1|21808|Loss: 0.8460670113563538:  84%|████████▍ | 21808/25880 [4:27:21<48:53,  1.39it/s]
1|21809|Loss: 0.8568009734153748:  84%|████████▍ | 21808/25880 [4:27:21<48:53,  1.39it/s]
1|21809|Loss: 0.8568009734153748:  84%|████████▍ | 21809/25880 [4:27:22<51:59,  1.31it/s]
1|21810|Loss: 0.8338025212287903:  84%|████████▍ | 21809/25880 [4:27:22<51:59,  1.31it/s]
1|21810|Loss: 0.8338025212287903:  84%|████████▍ | 21810/25880 [4:27:23<51:28,  1.32it/s]
1|21811|Loss: 0.7475464344024658:  84%|████████▍ | 21810/25880 [4:27:23<51:28,  1.32it/s]
1|21811|Loss: 0.7475464344024658:  84%|████████▍ | 21811/25880 [4:27:23<47:50,  1.42it/s]
1|21812|Loss: 0.7728656530380249:  84%|████████▍ | 21811/25880 [4:27:24<47:50,  1.42it/s]
1|21812|Loss: 0.7728656530380249:  84%|████████▍ | 21812/25880 [4:27:24<47:34,  1.43it/s]
1|21813|Loss: 0.8865988254547119:  84%|████████▍ | 21812/25880 [4:27:24<47:34,  1.43it/s]
1|21813|Loss: 0.8865988254547119:  84%|████████▍ | 21813/25880 [4:27:25<46:37,  1.45it/s]
1|21814|Loss: 0.9123155474662781:  84%|████████▍ | 21813/25880 [4:27:25<46:37,  1.45it/s]
1|21814|Loss: 0.9123155474662781:  84%|████████▍ | 21814/25880 [4:27:25<46:42,  1.45it/s]
1|21815|Loss: 0.8816307783126831:  84%|████████▍ | 21814/25880 [4:27:26<46:42,  1.45it/s]
1|21815|Loss: 0.8816307783126831:  84%|████████▍ | 21815/25880 [4:27:26<47:24,  1.43it/s]
1|21816|Loss: 0.7414873242378235:  84%|████████▍ | 21815/25880 [4:27:26<47:24,  1.43it/s]
1|21816|Loss: 0.7414873242378235:  84%|████████▍ | 21816/25880 [4:27:27<47:31,  1.43it/s]
1|21817|Loss: 0.8105865120887756:  84%|████████▍ | 21816/25880 [4:27:27<47:31,  1.43it/s]
1|21817|Loss: 0.8105865120887756:  84%|████████▍ | 21817/25880 [4:27:27<45:29,  1.49it/s]
1|21818|Loss: 0.7270274758338928:  84%|████████▍ | 21817/25880 [4:27:28<45:29,  1.49it/s]
1|21818|Loss: 0.7270274758338928:  84%|████████▍ | 21818/25880 [4:27:28<45:34,  1.49it/s]
1|21819|Loss: 0.8827531337738037:  84%|████████▍ | 21818/25880 [4:27:28<45:34,  1.49it/s]
1|21819|Loss: 0.8827531337738037:  84%|████████▍ | 21819/25880 [4:27:29<48:15,  1.40it/s]
1|21820|Loss: 0.8544868230819702:  84%|████████▍ | 21819/25880 [4:27:29<48:15,  1.40it/s]
1|21820|Loss: 0.8544868230819702:  84%|████████▍ | 21820/25880 [4:27:29<47:11,  1.43it/s]
1|21821|Loss: 0.7509965896606445:  84%|████████▍ | 21820/25880 [4:27:30<47:11,  1.43it/s]
1|21821|Loss: 0.7509965896606445:  84%|████████▍ | 21821/25880 [4:27:30<45:34,  1.48it/s]
1|21822|Loss: 0.828008770942688:  84%|████████▍ | 21821/25880 [4:27:30<45:34,  1.48it/s] 
1|21822|Loss: 0.828008770942688:  84%|████████▍ | 21822/25880 [4:27:31<42:41,  1.58it/s]
1|21823|Loss: 0.8536103963851929:  84%|████████▍ | 21822/25880 [4:27:31<42:41,  1.58it/s]
1|21823|Loss: 0.8536103963851929:  84%|████████▍ | 21823/25880 [4:27:31<44:56,  1.50it/s]
1|21824|Loss: 0.82619309425354:  84%|████████▍ | 21823/25880 [4:27:32<44:56,  1.50it/s]  
1|21824|Loss: 0.82619309425354:  84%|████████▍ | 21824/25880 [4:27:32<48:09,  1.40it/s]
1|21825|Loss: 0.8562054634094238:  84%|████████▍ | 21824/25880 [4:27:33<48:09,  1.40it/s]
1|21825|Loss: 0.8562054634094238:  84%|████████▍ | 21825/25880 [4:27:33<50:34,  1.34it/s]
1|21826|Loss: 0.6590677499771118:  84%|████████▍ | 21825/25880 [4:27:33<50:34,  1.34it/s]
1|21826|Loss: 0.6590677499771118:  84%|████████▍ | 21826/25880 [4:27:34<48:09,  1.40it/s]
1|21827|Loss: 0.9985204339027405:  84%|████████▍ | 21826/25880 [4:27:34<48:09,  1.40it/s]
1|21827|Loss: 0.9985204339027405:  84%|████████▍ | 21827/25880 [4:27:34<47:54,  1.41it/s]
1|21828|Loss: 0.7639228701591492:  84%|████████▍ | 21827/25880 [4:27:35<47:54,  1.41it/s]
1|21828|Loss: 0.7639228701591492:  84%|████████▍ | 21828/25880 [4:27:35<49:34,  1.36it/s]
1|21829|Loss: 0.9339251518249512:  84%|████████▍ | 21828/25880 [4:27:36<49:34,  1.36it/s]
1|21829|Loss: 0.9339251518249512:  84%|████████▍ | 21829/25880 [4:27:36<48:09,  1.40it/s]
1|21830|Loss: 0.730405867099762:  84%|████████▍ | 21829/25880 [4:27:36<48:09,  1.40it/s] 
1|21830|Loss: 0.730405867099762:  84%|████████▍ | 21830/25880 [4:27:37<49:58,  1.35it/s]
1|21831|Loss: 0.8727357387542725:  84%|████████▍ | 21830/25880 [4:27:37<49:58,  1.35it/s]
1|21831|Loss: 0.8727357387542725:  84%|████████▍ | 21831/25880 [4:27:37<51:18,  1.32it/s]
1|21832|Loss: 0.7490529417991638:  84%|████████▍ | 21831/25880 [4:27:38<51:18,  1.32it/s]
1|21832|Loss: 0.7490529417991638:  84%|████████▍ | 21832/25880 [4:27:38<53:35,  1.26it/s]
1|21833|Loss: 0.7831657528877258:  84%|████████▍ | 21832/25880 [4:27:39<53:35,  1.26it/s]
1|21833|Loss: 0.7831657528877258:  84%|████████▍ | 21833/25880 [4:27:39<51:41,  1.30it/s]
1|21834|Loss: 0.8305155634880066:  84%|████████▍ | 21833/25880 [4:27:39<51:41,  1.30it/s]
1|21834|Loss: 0.8305155634880066:  84%|████████▍ | 21834/25880 [4:27:40<53:41,  1.26it/s]
1|21835|Loss: 0.7214545607566833:  84%|████████▍ | 21834/25880 [4:27:40<53:41,  1.26it/s]
1|21835|Loss: 0.7214545607566833:  84%|████████▍ | 21835/25880 [4:27:40<49:09,  1.37it/s]
1|21836|Loss: 0.8853728175163269:  84%|████████▍ | 21835/25880 [4:27:41<49:09,  1.37it/s]
1|21836|Loss: 0.8853728175163269:  84%|████████▍ | 21836/25880 [4:27:41<48:10,  1.40it/s]
1|21837|Loss: 0.8756394982337952:  84%|████████▍ | 21836/25880 [4:27:42<48:10,  1.40it/s]
1|21837|Loss: 0.8756394982337952:  84%|████████▍ | 21837/25880 [4:27:42<50:04,  1.35it/s]
1|21838|Loss: 0.7384238839149475:  84%|████████▍ | 21837/25880 [4:27:42<50:04,  1.35it/s]
1|21838|Loss: 0.7384238839149475:  84%|████████▍ | 21838/25880 [4:27:43<53:08,  1.27it/s]
1|21839|Loss: 0.7972726821899414:  84%|████████▍ | 21838/25880 [4:27:43<53:08,  1.27it/s]
1|21839|Loss: 0.7972726821899414:  84%|████████▍ | 21839/25880 [4:27:44<52:38,  1.28it/s]
1|21840|Loss: 0.8427021503448486:  84%|████████▍ | 21839/25880 [4:27:44<52:38,  1.28it/s]
1|21840|Loss: 0.8427021503448486:  84%|████████▍ | 21840/25880 [4:27:44<51:45,  1.30it/s]
1|21841|Loss: 0.8709970712661743:  84%|████████▍ | 21840/25880 [4:27:45<51:45,  1.30it/s]
1|21841|Loss: 0.8709970712661743:  84%|████████▍ | 21841/25880 [4:27:45<53:07,  1.27it/s]
1|21842|Loss: 0.7977409362792969:  84%|████████▍ | 21841/25880 [4:27:46<53:07,  1.27it/s]
1|21842|Loss: 0.7977409362792969:  84%|████████▍ | 21842/25880 [4:27:46<52:12,  1.29it/s]
1|21843|Loss: 0.9212732911109924:  84%|████████▍ | 21842/25880 [4:27:46<52:12,  1.29it/s]
1|21843|Loss: 0.9212732911109924:  84%|████████▍ | 21843/25880 [4:27:47<51:21,  1.31it/s]
1|21844|Loss: 0.7913731932640076:  84%|████████▍ | 21843/25880 [4:27:47<51:21,  1.31it/s]
1|21844|Loss: 0.7913731932640076:  84%|████████▍ | 21844/25880 [4:27:47<50:51,  1.32it/s]
1|21845|Loss: 0.8119977116584778:  84%|████████▍ | 21844/25880 [4:27:48<50:51,  1.32it/s]
1|21845|Loss: 0.8119977116584778:  84%|████████▍ | 21845/25880 [4:27:48<47:07,  1.43it/s]
1|21846|Loss: 0.7757720351219177:  84%|████████▍ | 21845/25880 [4:27:48<47:07,  1.43it/s]
1|21846|Loss: 0.7757720351219177:  84%|████████▍ | 21846/25880 [4:27:49<47:51,  1.40it/s]
1|21847|Loss: 0.760029673576355:  84%|████████▍ | 21846/25880 [4:27:49<47:51,  1.40it/s] 
1|21847|Loss: 0.760029673576355:  84%|████████▍ | 21847/25880 [4:27:49<44:09,  1.52it/s]
1|21848|Loss: 0.748502790927887:  84%|████████▍ | 21847/25880 [4:27:50<44:09,  1.52it/s]
1|21848|Loss: 0.748502790927887:  84%|████████▍ | 21848/25880 [4:27:50<44:28,  1.51it/s]
1|21849|Loss: 0.7959555983543396:  84%|████████▍ | 21848/25880 [4:27:50<44:28,  1.51it/s]
1|21849|Loss: 0.7959555983543396:  84%|████████▍ | 21849/25880 [4:27:51<47:43,  1.41it/s]
1|21850|Loss: 0.9877234101295471:  84%|████████▍ | 21849/25880 [4:27:51<47:43,  1.41it/s]
1|21850|Loss: 0.9877234101295471:  84%|████████▍ | 21850/25880 [4:27:51<48:35,  1.38it/s]
1|21851|Loss: 0.729555070400238:  84%|████████▍ | 21850/25880 [4:27:52<48:35,  1.38it/s] 
1|21851|Loss: 0.729555070400238:  84%|████████▍ | 21851/25880 [4:27:52<48:18,  1.39it/s]
1|21852|Loss: 0.8048179149627686:  84%|████████▍ | 21851/25880 [4:27:53<48:18,  1.39it/s]
1|21852|Loss: 0.8048179149627686:  84%|████████▍ | 21852/25880 [4:27:53<46:58,  1.43it/s]
1|21853|Loss: 0.7976230978965759:  84%|████████▍ | 21852/25880 [4:27:53<46:58,  1.43it/s]
1|21853|Loss: 0.7976230978965759:  84%|████████▍ | 21853/25880 [4:27:54<47:17,  1.42it/s]
1|21854|Loss: 0.7921879291534424:  84%|████████▍ | 21853/25880 [4:27:54<47:17,  1.42it/s]
1|21854|Loss: 0.7921879291534424:  84%|████████▍ | 21854/25880 [4:27:54<50:58,  1.32it/s]
1|21855|Loss: 0.8652129769325256:  84%|████████▍ | 21854/25880 [4:27:55<50:58,  1.32it/s]
1|21855|Loss: 0.8652129769325256:  84%|████████▍ | 21855/25880 [4:27:55<51:28,  1.30it/s]
1|21856|Loss: 0.8311672210693359:  84%|████████▍ | 21855/25880 [4:27:56<51:28,  1.30it/s]
1|21856|Loss: 0.8311672210693359:  84%|████████▍ | 21856/25880 [4:27:56<53:11,  1.26it/s]
1|21857|Loss: 0.8761424422264099:  84%|████████▍ | 21856/25880 [4:27:56<53:11,  1.26it/s]
1|21857|Loss: 0.8761424422264099:  84%|████████▍ | 21857/25880 [4:27:57<52:10,  1.28it/s]
1|21858|Loss: 0.7785293459892273:  84%|████████▍ | 21857/25880 [4:27:57<52:10,  1.28it/s]
1|21858|Loss: 0.7785293459892273:  84%|████████▍ | 21858/25880 [4:27:57<49:38,  1.35it/s]
1|21859|Loss: 0.6942733526229858:  84%|████████▍ | 21858/25880 [4:27:58<49:38,  1.35it/s]
1|21859|Loss: 0.6942733526229858:  84%|████████▍ | 21859/25880 [4:27:58<49:18,  1.36it/s]
1|21860|Loss: 0.9397931098937988:  84%|████████▍ | 21859/25880 [4:27:59<49:18,  1.36it/s]
1|21860|Loss: 0.9397931098937988:  84%|████████▍ | 21860/25880 [4:27:59<50:54,  1.32it/s]
1|21861|Loss: 0.8410122394561768:  84%|████████▍ | 21860/25880 [4:27:59<50:54,  1.32it/s]
1|21861|Loss: 0.8410122394561768:  84%|████████▍ | 21861/25880 [4:28:00<49:15,  1.36it/s]
1|21862|Loss: 0.9695628881454468:  84%|████████▍ | 21861/25880 [4:28:00<49:15,  1.36it/s]
1|21862|Loss: 0.9695628881454468:  84%|████████▍ | 21862/25880 [4:28:00<48:56,  1.37it/s]
1|21863|Loss: 0.7904821634292603:  84%|████████▍ | 21862/25880 [4:28:01<48:56,  1.37it/s]
1|21863|Loss: 0.7904821634292603:  84%|████████▍ | 21863/25880 [4:28:01<47:09,  1.42it/s]
1|21864|Loss: 0.7389316558837891:  84%|████████▍ | 21863/25880 [4:28:01<47:09,  1.42it/s]
1|21864|Loss: 0.7389316558837891:  84%|████████▍ | 21864/25880 [4:28:02<47:18,  1.42it/s]
1|21865|Loss: 0.7041857838630676:  84%|████████▍ | 21864/25880 [4:28:02<47:18,  1.42it/s]
1|21865|Loss: 0.7041857838630676:  84%|████████▍ | 21865/25880 [4:28:02<46:08,  1.45it/s]
1|21866|Loss: 0.7115787267684937:  84%|████████▍ | 21865/25880 [4:28:03<46:08,  1.45it/s]
1|21866|Loss: 0.7115787267684937:  84%|████████▍ | 21866/25880 [4:28:03<46:44,  1.43it/s]
1|21867|Loss: 0.8228309750556946:  84%|████████▍ | 21866/25880 [4:28:03<46:44,  1.43it/s]
1|21867|Loss: 0.8228309750556946:  84%|████████▍ | 21867/25880 [4:28:04<44:00,  1.52it/s]
1|21868|Loss: 0.7965967059135437:  84%|████████▍ | 21867/25880 [4:28:04<44:00,  1.52it/s]
1|21868|Loss: 0.7965967059135437:  84%|████████▍ | 21868/25880 [4:28:04<44:42,  1.50it/s]
1|21869|Loss: 0.8731491565704346:  84%|████████▍ | 21868/25880 [4:28:05<44:42,  1.50it/s]
1|21869|Loss: 0.8731491565704346:  85%|████████▍ | 21869/25880 [4:28:05<46:22,  1.44it/s]
1|21870|Loss: 0.7624920606613159:  85%|████████▍ | 21869/25880 [4:28:06<46:22,  1.44it/s]
1|21870|Loss: 0.7624920606613159:  85%|████████▍ | 21870/25880 [4:28:06<48:14,  1.39it/s]
1|21871|Loss: 0.7982874512672424:  85%|████████▍ | 21870/25880 [4:28:06<48:14,  1.39it/s]
1|21871|Loss: 0.7982874512672424:  85%|████████▍ | 21871/25880 [4:28:07<48:37,  1.37it/s]
1|21872|Loss: 0.8919535279273987:  85%|████████▍ | 21871/25880 [4:28:07<48:37,  1.37it/s]
1|21872|Loss: 0.8919535279273987:  85%|████████▍ | 21872/25880 [4:28:07<48:50,  1.37it/s]
1|21873|Loss: 0.9099334478378296:  85%|████████▍ | 21872/25880 [4:28:08<48:50,  1.37it/s]
1|21873|Loss: 0.9099334478378296:  85%|████████▍ | 21873/25880 [4:28:08<46:45,  1.43it/s]
1|21874|Loss: 0.9192082285881042:  85%|████████▍ | 21873/25880 [4:28:08<46:45,  1.43it/s]
1|21874|Loss: 0.9192082285881042:  85%|████████▍ | 21874/25880 [4:28:09<43:26,  1.54it/s]
1|21875|Loss: 0.7165951728820801:  85%|████████▍ | 21874/25880 [4:28:09<43:26,  1.54it/s]
1|21875|Loss: 0.7165951728820801:  85%|████████▍ | 21875/25880 [4:28:09<42:24,  1.57it/s]
1|21876|Loss: 0.7808818221092224:  85%|████████▍ | 21875/25880 [4:28:10<42:24,  1.57it/s]
1|21876|Loss: 0.7808818221092224:  85%|████████▍ | 21876/25880 [4:28:10<42:02,  1.59it/s]
1|21877|Loss: 0.8457011580467224:  85%|████████▍ | 21876/25880 [4:28:10<42:02,  1.59it/s]
1|21877|Loss: 0.8457011580467224:  85%|████████▍ | 21877/25880 [4:28:11<45:53,  1.45it/s]
1|21878|Loss: 0.7725669741630554:  85%|████████▍ | 21877/25880 [4:28:11<45:53,  1.45it/s]
1|21878|Loss: 0.7725669741630554:  85%|████████▍ | 21878/25880 [4:28:11<48:20,  1.38it/s]
1|21879|Loss: 0.853089451789856:  85%|████████▍ | 21878/25880 [4:28:12<48:20,  1.38it/s] 
1|21879|Loss: 0.853089451789856:  85%|████████▍ | 21879/25880 [4:28:12<48:27,  1.38it/s]
1|21880|Loss: 0.8949921727180481:  85%|████████▍ | 21879/25880 [4:28:13<48:27,  1.38it/s]
1|21880|Loss: 0.8949921727180481:  85%|████████▍ | 21880/25880 [4:28:13<48:20,  1.38it/s]
1|21881|Loss: 0.8883916139602661:  85%|████████▍ | 21880/25880 [4:28:13<48:20,  1.38it/s]
1|21881|Loss: 0.8883916139602661:  85%|████████▍ | 21881/25880 [4:28:13<43:55,  1.52it/s]
1|21882|Loss: 0.7972317934036255:  85%|████████▍ | 21881/25880 [4:28:14<43:55,  1.52it/s]
1|21882|Loss: 0.7972317934036255:  85%|████████▍ | 21882/25880 [4:28:14<45:11,  1.47it/s]
1|21883|Loss: 0.9118857383728027:  85%|████████▍ | 21882/25880 [4:28:14<45:11,  1.47it/s]
1|21883|Loss: 0.9118857383728027:  85%|████████▍ | 21883/25880 [4:28:15<44:09,  1.51it/s]
1|21884|Loss: 0.8773228526115417:  85%|████████▍ | 21883/25880 [4:28:15<44:09,  1.51it/s]
1|21884|Loss: 0.8773228526115417:  85%|████████▍ | 21884/25880 [4:28:15<46:04,  1.45it/s]
1|21885|Loss: 0.8129736185073853:  85%|████████▍ | 21884/25880 [4:28:16<46:04,  1.45it/s]
1|21885|Loss: 0.8129736185073853:  85%|████████▍ | 21885/25880 [4:28:16<41:36,  1.60it/s]
1|21886|Loss: 0.7009285688400269:  85%|████████▍ | 21885/25880 [4:28:16<41:36,  1.60it/s]
1|21886|Loss: 0.7009285688400269:  85%|████████▍ | 21886/25880 [4:28:17<42:01,  1.58it/s]
1|21887|Loss: 0.7775036096572876:  85%|████████▍ | 21886/25880 [4:28:17<42:01,  1.58it/s]
1|21887|Loss: 0.7775036096572876:  85%|████████▍ | 21887/25880 [4:28:17<42:25,  1.57it/s]
1|21888|Loss: 0.8757727742195129:  85%|████████▍ | 21887/25880 [4:28:18<42:25,  1.57it/s]
1|21888|Loss: 0.8757727742195129:  85%|████████▍ | 21888/25880 [4:28:18<42:30,  1.57it/s]
1|21889|Loss: 0.923393964767456:  85%|████████▍ | 21888/25880 [4:28:18<42:30,  1.57it/s] 
1|21889|Loss: 0.923393964767456:  85%|████████▍ | 21889/25880 [4:28:19<44:11,  1.51it/s]
1|21890|Loss: 0.7730770111083984:  85%|████████▍ | 21889/25880 [4:28:19<44:11,  1.51it/s]
1|21890|Loss: 0.7730770111083984:  85%|████████▍ | 21890/25880 [4:28:19<45:37,  1.46it/s]
1|21891|Loss: 1.0043567419052124:  85%|████████▍ | 21890/25880 [4:28:20<45:37,  1.46it/s]
1|21891|Loss: 1.0043567419052124:  85%|████████▍ | 21891/25880 [4:28:20<46:29,  1.43it/s]
1|21892|Loss: 0.8707993626594543:  85%|████████▍ | 21891/25880 [4:28:20<46:29,  1.43it/s]
1|21892|Loss: 0.8707993626594543:  85%|████████▍ | 21892/25880 [4:28:21<47:16,  1.41it/s]
1|21893|Loss: 0.7517986297607422:  85%|████████▍ | 21892/25880 [4:28:21<47:16,  1.41it/s]
1|21893|Loss: 0.7517986297607422:  85%|████████▍ | 21893/25880 [4:28:21<45:24,  1.46it/s]
1|21894|Loss: 0.8643045425415039:  85%|████████▍ | 21893/25880 [4:28:22<45:24,  1.46it/s]
1|21894|Loss: 0.8643045425415039:  85%|████████▍ | 21894/25880 [4:28:22<45:50,  1.45it/s]
1|21895|Loss: 0.8011930584907532:  85%|████████▍ | 21894/25880 [4:28:23<45:50,  1.45it/s]
1|21895|Loss: 0.8011930584907532:  85%|████████▍ | 21895/25880 [4:28:23<46:49,  1.42it/s]
1|21896|Loss: 0.7885033488273621:  85%|████████▍ | 21895/25880 [4:28:23<46:49,  1.42it/s]
1|21896|Loss: 0.7885033488273621:  85%|████████▍ | 21896/25880 [4:28:24<48:30,  1.37it/s]
1|21897|Loss: 0.7815780639648438:  85%|████████▍ | 21896/25880 [4:28:24<48:30,  1.37it/s]
1|21897|Loss: 0.7815780639648438:  85%|████████▍ | 21897/25880 [4:28:24<46:57,  1.41it/s]
1|21898|Loss: 0.8218046426773071:  85%|████████▍ | 21897/25880 [4:28:25<46:57,  1.41it/s]
1|21898|Loss: 0.8218046426773071:  85%|████████▍ | 21898/25880 [4:28:25<45:11,  1.47it/s]
1|21899|Loss: 0.9121237397193909:  85%|████████▍ | 21898/25880 [4:28:25<45:11,  1.47it/s]
1|21899|Loss: 0.9121237397193909:  85%|████████▍ | 21899/25880 [4:28:26<42:55,  1.55it/s]
1|21900|Loss: 0.8664484620094299:  85%|████████▍ | 21899/25880 [4:28:26<42:55,  1.55it/s]
1|21900|Loss: 0.8664484620094299:  85%|██████���█▍ | 21900/25880 [4:28:26<43:28,  1.53it/s]
1|21901|Loss: 0.8207045197486877:  85%|████████▍ | 21900/25880 [4:28:27<43:28,  1.53it/s]
1|21901|Loss: 0.8207045197486877:  85%|████████▍ | 21901/25880 [4:28:27<44:59,  1.47it/s]
1|21902|Loss: 0.8658747673034668:  85%|████████▍ | 21901/25880 [4:28:27<44:59,  1.47it/s]
1|21902|Loss: 0.8658747673034668:  85%|████████▍ | 21902/25880 [4:28:28<47:18,  1.40it/s]
1|21903|Loss: 0.8362700343132019:  85%|████████▍ | 21902/25880 [4:28:28<47:18,  1.40it/s]
1|21903|Loss: 0.8362700343132019:  85%|████████▍ | 21903/25880 [4:28:29<50:46,  1.31it/s]
1|21904|Loss: 0.7189977765083313:  85%|████████▍ | 21903/25880 [4:28:29<50:46,  1.31it/s]
1|21904|Loss: 0.7189977765083313:  85%|████████▍ | 21904/25880 [4:28:29<50:49,  1.30it/s]
1|21905|Loss: 0.7942043542861938:  85%|████████▍ | 21904/25880 [4:28:30<50:49,  1.30it/s]
1|21905|Loss: 0.7942043542861938:  85%|████████▍ | 21905/25880 [4:28:30<51:44,  1.28it/s]
1|21906|Loss: 0.8107969760894775:  85%|████████▍ | 21905/25880 [4:28:31<51:44,  1.28it/s]
1|21906|Loss: 0.8107969760894775:  85%|████████▍ | 21906/25880 [4:28:31<51:13,  1.29it/s]
1|21907|Loss: 1.0005308389663696:  85%|████████▍ | 21906/25880 [4:28:31<51:13,  1.29it/s]
1|21907|Loss: 1.0005308389663696:  85%|████████▍ | 21907/25880 [4:28:32<52:18,  1.27it/s]
1|21908|Loss: 0.8866568803787231:  85%|████████▍ | 21907/25880 [4:28:32<52:18,  1.27it/s]
1|21908|Loss: 0.8866568803787231:  85%|████████▍ | 21908/25880 [4:28:32<49:56,  1.33it/s]
1|21909|Loss: 0.7270223498344421:  85%|████████▍ | 21908/25880 [4:28:33<49:56,  1.33it/s]
1|21909|Loss: 0.7270223498344421:  85%|████████▍ | 21909/25880 [4:28:33<46:09,  1.43it/s]
1|21910|Loss: 0.8216965794563293:  85%|████████▍ | 21909/25880 [4:28:33<46:09,  1.43it/s]
1|21910|Loss: 0.8216965794563293:  85%|████████▍ | 21910/25880 [4:28:34<45:57,  1.44it/s]
1|21911|Loss: 0.773503303527832:  85%|████████▍ | 21910/25880 [4:28:34<45:57,  1.44it/s] 
1|21911|Loss: 0.773503303527832:  85%|████████▍ | 21911/25880 [4:28:34<44:46,  1.48it/s]
1|21912|Loss: 0.9159094095230103:  85%|████████▍ | 21911/25880 [4:28:35<44:46,  1.48it/s]
1|21912|Loss: 0.9159094095230103:  85%|████████▍ | 21912/25880 [4:28:35<48:25,  1.37it/s]
1|21913|Loss: 0.8114749789237976:  85%|████████▍ | 21912/25880 [4:28:36<48:25,  1.37it/s]
1|21913|Loss: 0.8114749789237976:  85%|████████▍ | 21913/25880 [4:28:36<47:16,  1.40it/s]
1|21914|Loss: 0.7809727191925049:  85%|████████▍ | 21913/25880 [4:28:36<47:16,  1.40it/s]
1|21914|Loss: 0.7809727191925049:  85%|████████▍ | 21914/25880 [4:28:37<47:20,  1.40it/s]
1|21915|Loss: 0.7462177276611328:  85%|████████▍ | 21914/25880 [4:28:37<47:20,  1.40it/s]
1|21915|Loss: 0.7462177276611328:  85%|████████▍ | 21915/25880 [4:28:37<49:20,  1.34it/s]
1|21916|Loss: 0.8046075105667114:  85%|████████▍ | 21915/25880 [4:28:38<49:20,  1.34it/s]
1|21916|Loss: 0.8046075105667114:  85%|████████▍ | 21916/25880 [4:28:38<50:33,  1.31it/s]
1|21917|Loss: 0.8106611967086792:  85%|████████▍ | 21916/25880 [4:28:39<50:33,  1.31it/s]
1|21917|Loss: 0.8106611967086792:  85%|████████▍ | 21917/25880 [4:28:39<51:19,  1.29it/s]
1|21918|Loss: 0.8378347158432007:  85%|████████▍ | 21917/25880 [4:28:39<51:19,  1.29it/s]
1|21918|Loss: 0.8378347158432007:  85%|████████▍ | 21918/25880 [4:28:40<50:55,  1.30it/s]
1|21919|Loss: 0.8159469366073608:  85%|████████▍ | 21918/25880 [4:28:40<50:55,  1.30it/s]
1|21919|Loss: 0.8159469366073608:  85%|████████▍ | 21919/25880 [4:28:41<50:32,  1.31it/s]
1|21920|Loss: 0.8548431992530823:  85%|████████▍ | 21919/25880 [4:28:41<50:32,  1.31it/s]
1|21920|Loss: 0.8548431992530823:  85%|████████▍ | 21920/25880 [4:28:41<48:10,  1.37it/s]
1|21921|Loss: 0.85225909948349:  85%|████████▍ | 21920/25880 [4:28:42<48:10,  1.37it/s]  
1|21921|Loss: 0.85225909948349:  85%|████████▍ | 21921/25880 [4:28:42<48:49,  1.35it/s]
1|21922|Loss: 0.8322001695632935:  85%|████████▍ | 21921/25880 [4:28:42<48:49,  1.35it/s]
1|21922|Loss: 0.8322001695632935:  85%|████████▍ | 21922/25880 [4:28:43<47:05,  1.40it/s]
1|21923|Loss: 0.7501356601715088:  85%|████████▍ | 21922/25880 [4:28:43<47:05,  1.40it/s]
1|21923|Loss: 0.7501356601715088:  85%|████████▍ | 21923/25880 [4:28:43<48:53,  1.35it/s]
1|21924|Loss: 0.802455723285675:  85%|████████▍ | 21923/25880 [4:28:44<48:53,  1.35it/s] 
1|21924|Loss: 0.802455723285675:  85%|████████▍ | 21924/25880 [4:28:44<45:25,  1.45it/s]
1|21925|Loss: 0.8834061026573181:  85%|████████▍ | 21924/25880 [4:28:44<45:25,  1.45it/s]
1|21925|Loss: 0.8834061026573181:  85%|████████▍ | 21925/25880 [4:28:45<44:41,  1.48it/s]
1|21926|Loss: 0.6505998373031616:  85%|████████▍ | 21925/25880 [4:28:45<44:41,  1.48it/s]
1|21926|Loss: 0.6505998373031616:  85%|████████▍ | 21926/25880 [4:28:45<42:02,  1.57it/s]
1|21927|Loss: 0.779532253742218:  85%|████████▍ | 21926/25880 [4:28:46<42:02,  1.57it/s] 
1|21927|Loss: 0.779532253742218:  85%|████████▍ | 21927/25880 [4:28:46<43:02,  1.53it/s]
1|21928|Loss: 0.8392198085784912:  85%|████████▍ | 21927/25880 [4:28:46<43:02,  1.53it/s]
1|21928|Loss: 0.8392198085784912:  85%|████████▍ | 21928/25880 [4:28:47<45:51,  1.44it/s]
1|21929|Loss: 0.9762266874313354:  85%|████████▍ | 21928/25880 [4:28:47<45:51,  1.44it/s]
1|21929|Loss: 0.9762266874313354:  85%|████████▍ | 21929/25880 [4:28:47<46:21,  1.42it/s]
1|21930|Loss: 0.953363835811615:  85%|████████▍ | 21929/25880 [4:28:48<46:21,  1.42it/s] 
1|21930|Loss: 0.953363835811615:  85%|████████▍ | 21930/25880 [4:28:48<44:54,  1.47it/s]
1|21931|Loss: 0.8886061310768127:  85%|████████▍ | 21930/25880 [4:28:48<44:54,  1.47it/s]
1|21931|Loss: 0.8886061310768127:  85%|████████▍ | 21931/25880 [4:28:49<41:54,  1.57it/s]
1|21932|Loss: 0.8783307075500488:  85%|████████▍ | 21931/25880 [4:28:49<41:54,  1.57it/s]
1|21932|Loss: 0.8783307075500488:  85%|████████▍ | 21932/25880 [4:28:49<45:04,  1.46it/s]
1|21933|Loss: 0.8944814205169678:  85%|████████▍ | 21932/25880 [4:28:50<45:04,  1.46it/s]
1|21933|Loss: 0.8944814205169678:  85%|████████▍ | 21933/25880 [4:28:50<42:49,  1.54it/s]
1|21934|Loss: 0.8000231981277466:  85%|████████▍ | 21933/25880 [4:28:50<42:49,  1.54it/s]
1|21934|Loss: 0.8000231981277466:  85%|████████▍ | 21934/25880 [4:28:50<39:56,  1.65it/s]
1|21935|Loss: 0.7437903881072998:  85%|████████▍ | 21934/25880 [4:28:51<39:56,  1.65it/s]
1|21935|Loss: 0.7437903881072998:  85%|████████▍ | 21935/25880 [4:28:51<40:56,  1.61it/s]
1|21936|Loss: 0.7141582369804382:  85%|████████▍ | 21935/25880 [4:28:51<40:56,  1.61it/s]
1|21936|Loss: 0.7141582369804382:  85%|████████▍ | 21936/25880 [4:28:52<43:00,  1.53it/s]
1|21937|Loss: 0.6766714453697205:  85%|████████▍ | 21936/25880 [4:28:52<43:00,  1.53it/s]
1|21937|Loss: 0.6766714453697205:  85%|████████▍ | 21937/25880 [4:28:53<48:52,  1.34it/s]
1|21938|Loss: 0.8655021786689758:  85%|████████▍ | 21937/25880 [4:28:53<48:52,  1.34it/s]
1|21938|Loss: 0.8655021786689758:  85%|████████▍ | 21938/25880 [4:28:54<51:05,  1.29it/s]
1|21939|Loss: 0.8765830397605896:  85%|████████▍ | 21938/25880 [4:28:54<51:05,  1.29it/s]
1|21939|Loss: 0.8765830397605896:  85%|████████▍ | 21939/25880 [4:28:54<50:31,  1.30it/s]
1|21940|Loss: 0.8242557644844055:  85%|████████▍ | 21939/25880 [4:28:55<50:31,  1.30it/s]
1|21940|Loss: 0.8242557644844055:  85%|████████▍ | 21940/25880 [4:28:55<52:09,  1.26it/s]
1|21941|Loss: 0.7697085738182068:  85%|████████▍ | 21940/25880 [4:28:56<52:09,  1.26it/s]
1|21941|Loss: 0.7697085738182068:  85%|████████▍ | 21941/25880 [4:28:56<48:29,  1.35it/s]
1|21942|Loss: 0.9339509606361389:  85%|████████▍ | 21941/25880 [4:28:56<48:29,  1.35it/s]
1|21942|Loss: 0.9339509606361389:  85%|████████▍ | 21942/25880 [4:28:56<45:59,  1.43it/s]
1|21943|Loss: 0.912473201751709:  85%|████████▍ | 21942/25880 [4:28:57<45:59,  1.43it/s] 
1|21943|Loss: 0.912473201751709:  85%|████████▍ | 21943/25880 [4:28:57<46:26,  1.41it/s]
1|21944|Loss: 0.7882803082466125:  85%|████████▍ | 21943/25880 [4:28:57<46:26,  1.41it/s]
1|21944|Loss: 0.7882803082466125:  85%|████████▍ | 21944/25880 [4:28:58<43:29,  1.51it/s]
1|21945|Loss: 0.8159341812133789:  85%|████████▍ | 21944/25880 [4:28:58<43:29,  1.51it/s]
1|21945|Loss: 0.8159341812133789:  85%|████████▍ | 21945/25880 [4:28:58<43:25,  1.51it/s]
1|21946|Loss: 0.843090832233429:  85%|████████▍ | 21945/25880 [4:28:59<43:25,  1.51it/s] 
1|21946|Loss: 0.843090832233429:  85%|████████▍ | 21946/25880 [4:28:59<44:54,  1.46it/s]
1|21947|Loss: 0.747642457485199:  85%|████████▍ | 21946/25880 [4:29:00<44:54,  1.46it/s]
1|21947|Loss: 0.747642457485199:  85%|████████▍ | 21947/25880 [4:29:00<47:54,  1.37it/s]
1|21948|Loss: 0.8428548574447632:  85%|████████▍ | 21947/25880 [4:29:00<47:54,  1.37it/s]
1|21948|Loss: 0.8428548574447632:  85%|████████▍ | 21948/25880 [4:29:01<47:07,  1.39it/s]
1|21949|Loss: 0.7886873483657837:  85%|████████▍ | 21948/25880 [4:29:01<47:07,  1.39it/s]
1|21949|Loss: 0.7886873483657837:  85%|████████▍ | 21949/25880 [4:29:01<46:49,  1.40it/s]
1|21950|Loss: 0.798329770565033:  85%|████████▍ | 21949/25880 [4:29:02<46:49,  1.40it/s] 
1|21950|Loss: 0.798329770565033:  85%|████████▍ | 21950/25880 [4:29:02<47:03,  1.39it/s]
1|21951|Loss: 0.7881360054016113:  85%|████████▍ | 21950/25880 [4:29:02<47:03,  1.39it/s]
1|21951|Loss: 0.7881360054016113:  85%|████████▍ | 21951/25880 [4:29:03<45:55,  1.43it/s]
1|21952|Loss: 0.904644250869751:  85%|████████▍ | 21951/25880 [4:29:03<45:55,  1.43it/s] 
1|21952|Loss: 0.904644250869751:  85%|████████▍ | 21952/25880 [4:29:03<44:22,  1.48it/s]
1|21953|Loss: 0.8891795873641968:  85%|████████▍ | 21952/25880 [4:29:04<44:22,  1.48it/s]
1|21953|Loss: 0.8891795873641968:  85%|████████▍ | 21953/25880 [4:29:04<47:03,  1.39it/s]
1|21954|Loss: 0.9235290288925171:  85%|████████▍ | 21953/25880 [4:29:05<47:03,  1.39it/s]
1|21954|Loss: 0.9235290288925171:  85%|████████▍ | 21954/25880 [4:29:05<46:08,  1.42it/s]
1|21955|Loss: 0.8806843161582947:  85%|████████▍ | 21954/25880 [4:29:05<46:08,  1.42it/s]
1|21955|Loss: 0.8806843161582947:  85%|████████▍ | 21955/25880 [4:29:05<42:46,  1.53it/s]
1|21956|Loss: 0.8825143575668335:  85%|████████▍ | 21955/25880 [4:29:06<42:46,  1.53it/s]
1|21956|Loss: 0.8825143575668335:  85%|████████▍ | 21956/25880 [4:29:06<40:14,  1.62it/s]
1|21957|Loss: 0.962928295135498:  85%|████████▍ | 21956/25880 [4:29:06<40:14,  1.62it/s] 
1|21957|Loss: 0.962928295135498:  85%|████████▍ | 21957/25880 [4:29:07<40:14,  1.62it/s]
1|21958|Loss: 0.8933674097061157:  85%|████████▍ | 21957/25880 [4:29:07<40:14,  1.62it/s]
1|21958|Loss: 0.8933674097061157:  85%|████████▍ | 21958/25880 [4:29:07<40:21,  1.62it/s]
1|21959|Loss: 0.9464125037193298:  85%|████████▍ | 21958/25880 [4:29:08<40:21,  1.62it/s]
1|21959|Loss: 0.9464125037193298:  85%|████████▍ | 21959/25880 [4:29:08<42:20,  1.54it/s]
1|21960|Loss: 0.7637040615081787:  85%|████████▍ | 21959/25880 [4:29:08<42:20,  1.54it/s]
1|21960|Loss: 0.7637040615081787:  85%|████████▍ | 21960/25880 [4:29:08<42:15,  1.55it/s]
1|21961|Loss: 0.90993332862854:  85%|████████▍ | 21960/25880 [4:29:09<42:15,  1.55it/s]  
1|21961|Loss: 0.90993332862854:  85%|████████▍ | 21961/25880 [4:29:09<42:58,  1.52it/s]
1|21962|Loss: 0.707772433757782:  85%|████████▍ | 21961/25880 [4:29:10<42:58,  1.52it/s]
1|21962|Loss: 0.707772433757782:  85%|████████▍ | 21962/25880 [4:29:10<40:28,  1.61it/s]
1|21963|Loss: 0.7788541913032532:  85%|████████▍ | 21962/25880 [4:29:10<40:28,  1.61it/s]
1|21963|Loss: 0.7788541913032532:  85%|████████▍ | 21963/25880 [4:29:10<38:09,  1.71it/s]
1|21964|Loss: 0.8883128762245178:  85%|████████▍ | 21963/25880 [4:29:11<38:09,  1.71it/s]
1|21964|Loss: 0.8883128762245178:  85%|████████▍ | 21964/25880 [4:29:11<38:35,  1.69it/s]
1|21965|Loss: 0.8986650109291077:  85%|████████▍ | 21964/25880 [4:29:11<38:35,  1.69it/s]
1|21965|Loss: 0.8986650109291077:  85%|████████▍ | 21965/25880 [4:29:12<40:32,  1.61it/s]
1|21966|Loss: 0.8171800374984741:  85%|████████▍ | 21965/25880 [4:29:12<40:32,  1.61it/s]
1|21966|Loss: 0.8171800374984741:  85%|████████▍ | 21966/25880 [4:29:12<45:26,  1.44it/s]
1|21967|Loss: 0.8421040177345276:  85%|████████▍ | 21966/25880 [4:29:13<45:26,  1.44it/s]
1|21967|Loss: 0.8421040177345276:  85%|████████▍ | 21967/25880 [4:29:13<47:00,  1.39it/s]
1|21968|Loss: 0.9692007899284363:  85%|████████▍ | 21967/25880 [4:29:14<47:00,  1.39it/s]
1|21968|Loss: 0.9692007899284363:  85%|████████▍ | 21968/25880 [4:29:14<48:23,  1.35it/s]
1|21969|Loss: 0.8308634757995605:  85%|████████▍ | 21968/25880 [4:29:14<48:23,  1.35it/s]
1|21969|Loss: 0.8308634757995605:  85%|████████▍ | 21969/25880 [4:29:15<50:10,  1.30it/s]
1|21970|Loss: 0.8141081929206848:  85%|████████▍ | 21969/25880 [4:29:15<50:10,  1.30it/s]
1|21970|Loss: 0.8141081929206848:  85%|████████▍ | 21970/25880 [4:29:16<50:41,  1.29it/s]
1|21971|Loss: 0.8588511943817139:  85%|████████▍ | 21970/25880 [4:29:16<50:41,  1.29it/s]
1|21971|Loss: 0.8588511943817139:  85%|████████▍ | 21971/25880 [4:29:16<47:43,  1.37it/s]
1|21972|Loss: 0.7838004231452942:  85%|████████▍ | 21971/25880 [4:29:17<47:43,  1.37it/s]
1|21972|Loss: 0.7838004231452942:  85%|████████▍ | 21972/25880 [4:29:17<46:31,  1.40it/s]
1|21973|Loss: 0.8043010234832764:  85%|████████▍ | 21972/25880 [4:29:17<46:31,  1.40it/s]
1|21973|Loss: 0.8043010234832764:  85%|████████▍ | 21973/25880 [4:29:18<48:26,  1.34it/s]
1|21974|Loss: 0.7336633801460266:  85%|████████▍ | 21973/25880 [4:29:18<48:26,  1.34it/s]
1|21974|Loss: 0.7336633801460266:  85%|████████▍ | 21974/25880 [4:29:19<49:43,  1.31it/s]
1|21975|Loss: 0.9482059478759766:  85%|████████▍ | 21974/25880 [4:29:19<49:43,  1.31it/s]
1|21975|Loss: 0.9482059478759766:  85%|████████▍ | 21975/25880 [4:29:19<49:22,  1.32it/s]
1|21976|Loss: 0.849636435508728:  85%|████████▍ | 21975/25880 [4:29:20<49:22,  1.32it/s] 
1|21976|Loss: 0.849636435508728:  85%|████████▍ | 21976/25880 [4:29:20<48:41,  1.34it/s]
1|21977|Loss: 0.899522066116333:  85%|████████▍ | 21976/25880 [4:29:20<48:41,  1.34it/s]
1|21977|Loss: 0.899522066116333:  85%|████████▍ | 21977/25880 [4:29:21<48:36,  1.34it/s]
1|21978|Loss: 1.0183621644973755:  85%|████████▍ | 21977/25880 [4:29:21<48:36,  1.34it/s]
1|21978|Loss: 1.0183621644973755:  85%|████████▍ | 21978/25880 [4:29:21<47:04,  1.38it/s]
1|21979|Loss: 0.9088993668556213:  85%|████████▍ | 21978/25880 [4:29:22<47:04,  1.38it/s]
1|21979|Loss: 0.9088993668556213:  85%|████████▍ | 21979/25880 [4:29:22<46:25,  1.40it/s]
1|21980|Loss: 0.8267877101898193:  85%|████████▍ | 21979/25880 [4:29:22<46:25,  1.40it/s]
1|21980|Loss: 0.8267877101898193:  85%|████████▍ | 21980/25880 [4:29:23<46:31,  1.40it/s]
1|21981|Loss: 0.8218030333518982:  85%|████████▍ | 21980/25880 [4:29:23<46:31,  1.40it/s]
1|21981|Loss: 0.8218030333518982:  85%|████████▍ | 21981/25880 [4:29:24<46:21,  1.40it/s]
1|21982|Loss: 0.7347634434700012:  85%|████████▍ | 21981/25880 [4:29:24<46:21,  1.40it/s]
1|21982|Loss: 0.7347634434700012:  85%|████████▍ | 21982/25880 [4:29:24<44:48,  1.45it/s]
1|21983|Loss: 0.8751413226127625:  85%|████████▍ | 21982/25880 [4:29:25<44:48,  1.45it/s]
1|21983|Loss: 0.8751413226127625:  85%|████████▍ | 21983/25880 [4:29:25<44:40,  1.45it/s]
1|21984|Loss: 0.750557541847229:  85%|████████▍ | 21983/25880 [4:29:25<44:40,  1.45it/s] 
1|21984|Loss: 0.750557541847229:  85%|████████▍ | 21984/25880 [4:29:26<45:19,  1.43it/s]
1|21985|Loss: 0.7746673226356506:  85%|████████▍ | 21984/25880 [4:29:26<45:19,  1.43it/s]
1|21985|Loss: 0.7746673226356506:  85%|████████▍ | 21985/25880 [4:29:26<47:44,  1.36it/s]
1|21986|Loss: 0.7303630709648132:  85%|████████▍ | 21985/25880 [4:29:27<47:44,  1.36it/s]
1|21986|Loss: 0.7303630709648132:  85%|████████▍ | 21986/25880 [4:29:27<47:41,  1.36it/s]
1|21987|Loss: 0.8643586039543152:  85%|████████▍ | 21986/25880 [4:29:27<47:41,  1.36it/s]
1|21987|Loss: 0.8643586039543152:  85%|████████▍ | 21987/25880 [4:29:28<46:55,  1.38it/s]
1|21988|Loss: 0.8383451700210571:  85%|████████▍ | 21987/25880 [4:29:28<46:55,  1.38it/s]
1|21988|Loss: 0.8383451700210571:  85%|████████▍ | 21988/25880 [4:29:28<43:23,  1.49it/s]
1|21989|Loss: 0.8820652961730957:  85%|████████▍ | 21988/25880 [4:29:29<43:23,  1.49it/s]
1|21989|Loss: 0.8820652961730957:  85%|████████▍ | 21989/25880 [4:29:29<43:51,  1.48it/s]
1|21990|Loss: 0.8405412435531616:  85%|████████▍ | 21989/25880 [4:29:29<43:51,  1.48it/s]
1|21990|Loss: 0.8405412435531616:  85%|████████▍ | 21990/25880 [4:29:30<43:39,  1.49it/s]
1|21991|Loss: 0.8988093137741089:  85%|████████▍ | 21990/25880 [4:29:30<43:39,  1.49it/s]
1|21991|Loss: 0.8988093137741089:  85%|████████▍ | 21991/25880 [4:29:31<46:54,  1.38it/s]
1|21992|Loss: 0.8864516615867615:  85%|████████▍ | 21991/25880 [4:29:31<46:54,  1.38it/s]
1|21992|Loss: 0.8864516615867615:  85%|████████▍ | 21992/25880 [4:29:31<45:02,  1.44it/s]
1|21993|Loss: 0.8854937553405762:  85%|████████▍ | 21992/25880 [4:29:32<45:02,  1.44it/s]
1|21993|Loss: 0.8854937553405762:  85%|████████▍ | 21993/25880 [4:29:32<44:53,  1.44it/s]
1|21994|Loss: 0.9238442778587341:  85%|████████▍ | 21993/25880 [4:29:32<44:53,  1.44it/s]
1|21994|Loss: 0.9238442778587341:  85%|████████▍ | 21994/25880 [4:29:32<43:47,  1.48it/s]
1|21995|Loss: 0.897270143032074:  85%|████████▍ | 21994/25880 [4:29:33<43:47,  1.48it/s] 
1|21995|Loss: 0.897270143032074:  85%|���███████▍ | 21995/25880 [4:29:33<42:33,  1.52it/s]
1|21996|Loss: 0.7199087142944336:  85%|████████▍ | 21995/25880 [4:29:33<42:33,  1.52it/s]
1|21996|Loss: 0.7199087142944336:  85%|████████▍ | 21996/25880 [4:29:34<43:30,  1.49it/s]
1|21997|Loss: 0.8042625188827515:  85%|████████▍ | 21996/25880 [4:29:34<43:30,  1.49it/s]
1|21997|Loss: 0.8042625188827515:  85%|████████▍ | 21997/25880 [4:29:34<41:10,  1.57it/s]
1|21998|Loss: 0.8828757405281067:  85%|████████▍ | 21997/25880 [4:29:35<41:10,  1.57it/s]
1|21998|Loss: 0.8828757405281067:  85%|████████▌ | 21998/25880 [4:29:35<42:09,  1.53it/s]
1|21999|Loss: 0.8994753360748291:  85%|████████▌ | 21998/25880 [4:29:35<42:09,  1.53it/s]
1|21999|Loss: 0.8994753360748291:  85%|████████▌ | 21999/25880 [4:29:36<42:15,  1.53it/s]
1|22000|Loss: 0.7350285053253174:  85%|████████▌ | 21999/25880 [4:29:36<42:15,  1.53it/s]
1|22000|Loss: 0.7350285053253174:  85%|████████▌ | 22000/25880 [4:29:36<43:25,  1.49it/s]
1|22001|Loss: 0.9219297170639038:  85%|████████▌ | 22000/25880 [4:29:37<43:25,  1.49it/s]
1|22001|Loss: 0.9219297170639038:  85%|████████▌ | 22001/25880 [4:29:37<44:35,  1.45it/s]
1|22002|Loss: 0.8771095871925354:  85%|████████▌ | 22001/25880 [4:29:38<44:35,  1.45it/s]
1|22002|Loss: 0.8771095871925354:  85%|████████▌ | 22002/25880 [4:29:38<43:01,  1.50it/s]
1|22003|Loss: 0.8189603090286255:  85%|████████▌ | 22002/25880 [4:29:38<43:01,  1.50it/s]
1|22003|Loss: 0.8189603090286255:  85%|████████▌ | 22003/25880 [4:29:38<43:49,  1.47it/s]
1|22004|Loss: 0.7790700197219849:  85%|████████▌ | 22003/25880 [4:29:39<43:49,  1.47it/s]
1|22004|Loss: 0.7790700197219849:  85%|████████▌ | 22004/25880 [4:29:39<46:47,  1.38it/s]
1|22005|Loss: 0.7355687618255615:  85%|████████▌ | 22004/25880 [4:29:40<46:47,  1.38it/s]
1|22005|Loss: 0.7355687618255615:  85%|████████▌ | 22005/25880 [4:29:40<47:45,  1.35it/s]
1|22006|Loss: 0.8518049120903015:  85%|████████▌ | 22005/25880 [4:29:41<47:45,  1.35it/s]
1|22006|Loss: 0.8518049120903015:  85%|████████▌ | 22006/25880 [4:29:41<49:18,  1.31it/s]
1|22007|Loss: 0.8801751136779785:  85%|████████▌ | 22006/25880 [4:29:41<49:18,  1.31it/s]
1|22007|Loss: 0.8801751136779785:  85%|████████▌ | 22007/25880 [4:29:42<48:34,  1.33it/s]
1|22008|Loss: 0.8234275579452515:  85%|████████▌ | 22007/25880 [4:29:42<48:34,  1.33it/s]
1|22008|Loss: 0.8234275579452515:  85%|████████▌ | 22008/25880 [4:29:42<49:06,  1.31it/s]
1|22009|Loss: 0.937584400177002:  85%|████████▌ | 22008/25880 [4:29:43<49:06,  1.31it/s] 
1|22009|Loss: 0.937584400177002:  85%|████████▌ | 22009/25880 [4:29:43<49:53,  1.29it/s]
1|22010|Loss: 0.7739154696464539:  85%|████████▌ | 22009/25880 [4:29:44<49:53,  1.29it/s]
1|22010|Loss: 0.7739154696464539:  85%|████████▌ | 22010/25880 [4:29:44<46:08,  1.40it/s]
1|22011|Loss: 0.9623480439186096:  85%|████████▌ | 22010/25880 [4:29:44<46:08,  1.40it/s]
1|22011|Loss: 0.9623480439186096:  85%|████████▌ | 22011/25880 [4:29:44<45:12,  1.43it/s]
1|22012|Loss: 0.7512357831001282:  85%|████████▌ | 22011/25880 [4:29:45<45:12,  1.43it/s]
1|22012|Loss: 0.7512357831001282:  85%|████████▌ | 22012/25880 [4:29:45<43:48,  1.47it/s]
1|22013|Loss: 0.8541219234466553:  85%|████████▌ | 22012/25880 [4:29:45<43:48,  1.47it/s]
1|22013|Loss: 0.8541219234466553:  85%|████████▌ | 22013/25880 [4:29:46<44:30,  1.45it/s]
1|22014|Loss: 0.9759971499443054:  85%|████████▌ | 22013/25880 [4:29:46<44:30,  1.45it/s]
1|22014|Loss: 0.9759971499443054:  85%|████████▌ | 22014/25880 [4:29:46<43:59,  1.46it/s]
1|22015|Loss: 0.8850905895233154:  85%|████████▌ | 22014/25880 [4:29:47<43:59,  1.46it/s]
1|22015|Loss: 0.8850905895233154:  85%|████████▌ | 22015/25880 [4:29:47<44:43,  1.44it/s]
1|22016|Loss: 0.8773723244667053:  85%|████████▌ | 22015/25880 [4:29:48<44:43,  1.44it/s]
1|22016|Loss: 0.8773723244667053:  85%|████████▌ | 22016/25880 [4:29:48<47:49,  1.35it/s]
1|22017|Loss: 0.867377758026123:  85%|████████▌ | 22016/25880 [4:29:48<47:49,  1.35it/s] 
1|22017|Loss: 0.867377758026123:  85%|████████▌ | 22017/25880 [4:29:49<45:40,  1.41it/s]
1|22018|Loss: 0.9116116762161255:  85%|████████▌ | 22017/25880 [4:29:49<45:40,  1.41it/s]
1|22018|Loss: 0.9116116762161255:  85%|████████▌ | 22018/25880 [4:29:49<41:56,  1.53it/s]
1|22019|Loss: 0.8610164523124695:  85%|████████▌ | 22018/25880 [4:29:50<41:56,  1.53it/s]
1|22019|Loss: 0.8610164523124695:  85%|████████▌ | 22019/25880 [4:29:50<45:21,  1.42it/s]
1|22020|Loss: 0.8504539728164673:  85%|████████▌ | 22019/25880 [4:29:50<45:21,  1.42it/s]
1|22020|Loss: 0.8504539728164673:  85%|████████▌ | 22020/25880 [4:29:51<48:27,  1.33it/s]
1|22021|Loss: 0.8062602281570435:  85%|████████▌ | 22020/25880 [4:29:51<48:27,  1.33it/s]
1|22021|Loss: 0.8062602281570435:  85%|████████▌ | 22021/25880 [4:29:52<51:31,  1.25it/s]
1|22022|Loss: 0.6563835740089417:  85%|████████▌ | 22021/25880 [4:29:52<51:31,  1.25it/s]
1|22022|Loss: 0.6563835740089417:  85%|████████▌ | 22022/25880 [4:29:52<48:43,  1.32it/s]
1|22023|Loss: 0.8874400854110718:  85%|████████▌ | 22022/25880 [4:29:53<48:43,  1.32it/s]
1|22023|Loss: 0.8874400854110718:  85%|████████▌ | 22023/25880 [4:29:53<47:09,  1.36it/s]
1|22024|Loss: 0.906245231628418:  85%|████████▌ | 22023/25880 [4:29:53<47:09,  1.36it/s] 
1|22024|Loss: 0.906245231628418:  85%|████████▌ | 22024/25880 [4:29:54<45:08,  1.42it/s]
1|22025|Loss: 0.8975853323936462:  85%|████████▌ | 22024/25880 [4:29:54<45:08,  1.42it/s]
1|22025|Loss: 0.8975853323936462:  85%|████████▌ | 22025/25880 [4:29:54<44:45,  1.44it/s]
1|22026|Loss: 0.8199623227119446:  85%|████████▌ | 22025/25880 [4:29:55<44:45,  1.44it/s]
1|22026|Loss: 0.8199623227119446:  85%|████████▌ | 22026/25880 [4:29:55<46:10,  1.39it/s]
1|22027|Loss: 0.8047677874565125:  85%|████████▌ | 22026/25880 [4:29:56<46:10,  1.39it/s]
1|22027|Loss: 0.8047677874565125:  85%|████████▌ | 22027/25880 [4:29:56<46:40,  1.38it/s]
1|22028|Loss: 0.9057338237762451:  85%|████████▌ | 22027/25880 [4:29:56<46:40,  1.38it/s]
1|22028|Loss: 0.9057338237762451:  85%|████████▌ | 22028/25880 [4:29:57<46:58,  1.37it/s]
1|22029|Loss: 0.7355310320854187:  85%|████████▌ | 22028/25880 [4:29:57<46:58,  1.37it/s]
1|22029|Loss: 0.7355310320854187:  85%|████████▌ | 22029/25880 [4:29:57<47:24,  1.35it/s]
1|22030|Loss: 0.7865445613861084:  85%|████████▌ | 22029/25880 [4:29:58<47:24,  1.35it/s]
1|22030|Loss: 0.7865445613861084:  85%|████████▌ | 22030/25880 [4:29:58<47:38,  1.35it/s]
1|22031|Loss: 0.7578853368759155:  85%|████████▌ | 22030/25880 [4:29:59<47:38,  1.35it/s]
1|22031|Loss: 0.7578853368759155:  85%|████████▌ | 22031/25880 [4:29:59<46:12,  1.39it/s]
1|22032|Loss: 0.8679541945457458:  85%|████████▌ | 22031/25880 [4:29:59<46:12,  1.39it/s]
1|22032|Loss: 0.8679541945457458:  85%|████████▌ | 22032/25880 [4:29:59<43:38,  1.47it/s]
1|22033|Loss: 0.9367226362228394:  85%|████████▌ | 22032/25880 [4:30:00<43:38,  1.47it/s]
1|22033|Loss: 0.9367226362228394:  85%|████████▌ | 22033/25880 [4:30:00<48:11,  1.33it/s]
1|22034|Loss: 0.8697185516357422:  85%|████████▌ | 22033/25880 [4:30:01<48:11,  1.33it/s]
1|22034|Loss: 0.8697185516357422:  85%|████████▌ | 22034/25880 [4:30:01<47:39,  1.35it/s]
1|22035|Loss: 0.9499942660331726:  85%|████████▌ | 22034/25880 [4:30:01<47:39,  1.35it/s]
1|22035|Loss: 0.9499942660331726:  85%|████████▌ | 22035/25880 [4:30:02<47:08,  1.36it/s]
1|22036|Loss: 0.8646929264068604:  85%|████████▌ | 22035/25880 [4:30:02<47:08,  1.36it/s]
1|22036|Loss: 0.8646929264068604:  85%|████████▌ | 22036/25880 [4:30:03<46:33,  1.38it/s]
1|22037|Loss: 0.8786510229110718:  85%|████████▌ | 22036/25880 [4:30:03<46:33,  1.38it/s]
1|22037|Loss: 0.8786510229110718:  85%|████████▌ | 22037/25880 [4:30:03<47:39,  1.34it/s]
1|22038|Loss: 0.8090129494667053:  85%|████████▌ | 22037/25880 [4:30:04<47:39,  1.34it/s]
1|22038|Loss: 0.8090129494667053:  85%|████████▌ | 22038/25880 [4:30:04<47:39,  1.34it/s]
1|22039|Loss: 0.8378850817680359:  85%|████████▌ | 22038/25880 [4:30:04<47:39,  1.34it/s]
1|22039|Loss: 0.8378850817680359:  85%|████████▌ | 22039/25880 [4:30:05<45:58,  1.39it/s]
1|22040|Loss: 0.8388230800628662:  85%|████████▌ | 22039/25880 [4:30:05<45:58,  1.39it/s]
1|22040|Loss: 0.8388230800628662:  85%|████████▌ | 22040/25880 [4:30:06<48:44,  1.31it/s]
1|22041|Loss: 0.7466648817062378:  85%|████████▌ | 22040/25880 [4:30:06<48:44,  1.31it/s]
1|22041|Loss: 0.7466648817062378:  85%|████████▌ | 22041/25880 [4:30:06<49:43,  1.29it/s]
1|22042|Loss: 0.9666432738304138:  85%|████████▌ | 22041/25880 [4:30:07<49:43,  1.29it/s]
1|22042|Loss: 0.9666432738304138:  85%|████████▌ | 22042/25880 [4:30:07<49:16,  1.30it/s]
1|22043|Loss: 0.8514400720596313:  85%|████████▌ | 22042/25880 [4:30:08<49:16,  1.30it/s]
1|22043|Loss: 0.8514400720596313:  85%|████████▌ | 22043/25880 [4:30:08<51:32,  1.24it/s]
1|22044|Loss: 0.8636474609375:  85%|████████▌ | 22043/25880 [4:30:08<51:32,  1.24it/s]   
1|22044|Loss: 0.8636474609375:  85%|████████▌ | 22044/25880 [4:30:09<47:20,  1.35it/s]
1|22045|Loss: 0.7275439500808716:  85%|████████▌ | 22044/25880 [4:30:09<47:20,  1.35it/s]
1|22045|Loss: 0.7275439500808716:  85%|████████▌ | 22045/25880 [4:30:10<50:08,  1.27it/s]
1|22046|Loss: 0.8139297962188721:  85%|████████▌ | 22045/25880 [4:30:10<50:08,  1.27it/s]
1|22046|Loss: 0.8139297962188721:  85%|████████▌ | 22046/25880 [4:30:10<51:57,  1.23it/s]
1|22047|Loss: 0.7583655118942261:  85%|████████▌ | 22046/25880 [4:30:11<51:57,  1.23it/s]
1|22047|Loss: 0.7583655118942261:  85%|████████▌ | 22047/25880 [4:30:11<53:09,  1.20it/s]
1|22048|Loss: 0.9571107029914856:  85%|████████▌ | 22047/25880 [4:30:12<53:09,  1.20it/s]
1|22048|Loss: 0.9571107029914856:  85%|████████▌ | 22048/25880 [4:30:12<52:08,  1.22it/s]
1|22049|Loss: 0.8781846761703491:  85%|████████▌ | 22048/25880 [4:30:12<52:08,  1.22it/s]
1|22049|Loss: 0.8781846761703491:  85%|████████▌ | 22049/25880 [4:30:13<50:51,  1.26it/s]
1|22050|Loss: 0.7940656542778015:  85%|████████▌ | 22049/25880 [4:30:13<50:51,  1.26it/s]
1|22050|Loss: 0.7940656542778015:  85%|████████▌ | 22050/25880 [4:30:13<48:21,  1.32it/s]
1|22051|Loss: 0.7470254898071289:  85%|████████▌ | 22050/25880 [4:30:14<48:21,  1.32it/s]
1|22051|Loss: 0.7470254898071289:  85%|████████▌ | 22051/25880 [4:30:14<48:40,  1.31it/s]
1|22052|Loss: 0.9040330648422241:  85%|████████▌ | 22051/25880 [4:30:15<48:40,  1.31it/s]
1|22052|Loss: 0.9040330648422241:  85%|████████▌ | 22052/25880 [4:30:15<49:33,  1.29it/s]
1|22053|Loss: 0.785368800163269:  85%|████████▌ | 22052/25880 [4:30:15<49:33,  1.29it/s] 
1|22053|Loss: 0.785368800163269:  85%|████████▌ | 22053/25880 [4:30:16<48:58,  1.30it/s]
1|22054|Loss: 0.9215711951255798:  85%|████████▌ | 22053/25880 [4:30:16<48:58,  1.30it/s]
1|22054|Loss: 0.9215711951255798:  85%|████████▌ | 22054/25880 [4:30:17<48:16,  1.32it/s]
1|22055|Loss: 0.8919581174850464:  85%|████████▌ | 22054/25880 [4:30:17<48:16,  1.32it/s]
1|22055|Loss: 0.8919581174850464:  85%|████████▌ | 22055/25880 [4:30:17<49:32,  1.29it/s]
1|22056|Loss: 0.7985692620277405:  85%|████████▌ | 22055/25880 [4:30:18<49:32,  1.29it/s]
1|22056|Loss: 0.7985692620277405:  85%|████████▌ | 22056/25880 [4:30:18<47:56,  1.33it/s]
1|22057|Loss: 0.8662189245223999:  85%|████████▌ | 22056/25880 [4:30:18<47:56,  1.33it/s]
1|22057|Loss: 0.8662189245223999:  85%|████████▌ | 22057/25880 [4:30:19<45:51,  1.39it/s]
1|22058|Loss: 0.862825334072113:  85%|████████▌ | 22057/25880 [4:30:19<45:51,  1.39it/s] 
1|22058|Loss: 0.862825334072113:  85%|████████▌ | 22058/25880 [4:30:19<45:12,  1.41it/s]
1|22059|Loss: 0.7397182583808899:  85%|████████▌ | 22058/25880 [4:30:20<45:12,  1.41it/s]
1|22059|Loss: 0.7397182583808899:  85%|████████▌ | 22059/25880 [4:30:20<45:38,  1.40it/s]
1|22060|Loss: 0.8137283325195312:  85%|████████▌ | 22059/25880 [4:30:21<45:38,  1.40it/s]
1|22060|Loss: 0.8137283325195312:  85%|████████▌ | 22060/25880 [4:30:21<47:34,  1.34it/s]
1|22061|Loss: 0.7544283270835876:  85%|████████▌ | 22060/25880 [4:30:21<47:34,  1.34it/s]
1|22061|Loss: 0.7544283270835876:  85%|████████▌ | 22061/25880 [4:30:22<48:27,  1.31it/s]
1|22062|Loss: 0.7122192978858948:  85%|████████▌ | 22061/25880 [4:30:22<48:27,  1.31it/s]
1|22062|Loss: 0.7122192978858948:  85%|████████▌ | 22062/25880 [4:30:23<54:31,  1.17it/s]
1|22063|Loss: 0.8909775018692017:  85%|████████▌ | 22062/25880 [4:30:23<54:31,  1.17it/s]
1|22063|Loss: 0.8909775018692017:  85%|████████▌ | 22063/25880 [4:30:24<51:43,  1.23it/s]
1|22064|Loss: 0.851206362247467:  85%|████████▌ | 22063/25880 [4:30:24<51:43,  1.23it/s] 
1|22064|Loss: 0.851206362247467:  85%|████████▌ | 22064/25880 [4:30:24<49:08,  1.29it/s]
1|22065|Loss: 0.6959056258201599:  85%|████████▌ | 22064/25880 [4:30:25<49:08,  1.29it/s]
1|22065|Loss: 0.6959056258201599:  85%|████████▌ | 22065/25880 [4:30:25<46:32,  1.37it/s]
1|22066|Loss: 0.8002753853797913:  85%|████████▌ | 22065/25880 [4:30:25<46:32,  1.37it/s]
1|22066|Loss: 0.8002753853797913:  85%|████████▌ | 22066/25880 [4:30:26<47:02,  1.35it/s]
1|22067|Loss: 0.8187083005905151:  85%|████████▌ | 22066/25880 [4:30:26<47:02,  1.35it/s]
1|22067|Loss: 0.8187083005905151:  85%|████████▌ | 22067/25880 [4:30:26<47:17,  1.34it/s]
1|22068|Loss: 0.8714004158973694:  85%|████████▌ | 22067/25880 [4:30:27<47:17,  1.34it/s]
1|22068|Loss: 0.8714004158973694:  85%|████████▌ | 22068/25880 [4:30:27<51:05,  1.24it/s]
1|22069|Loss: 0.8259265422821045:  85%|████████▌ | 22068/25880 [4:30:28<51:05,  1.24it/s]
1|22069|Loss: 0.8259265422821045:  85%|████████▌ | 22069/25880 [4:30:28<50:28,  1.26it/s]
1|22070|Loss: 0.7749683260917664:  85%|████████▌ | 22069/25880 [4:30:28<50:28,  1.26it/s]
1|22070|Loss: 0.7749683260917664:  85%|████████▌ | 22070/25880 [4:30:29<50:01,  1.27it/s]
1|22071|Loss: 1.0642811059951782:  85%|████████▌ | 22070/25880 [4:30:29<50:01,  1.27it/s]
1|22071|Loss: 1.0642811059951782:  85%|████████▌ | 22071/25880 [4:30:30<47:54,  1.33it/s]
1|22072|Loss: 0.7571442723274231:  85%|████████▌ | 22071/25880 [4:30:30<47:54,  1.33it/s]
1|22072|Loss: 0.7571442723274231:  85%|████████▌ | 22072/25880 [4:30:30<47:07,  1.35it/s]
1|22073|Loss: 0.8825793266296387:  85%|████████▌ | 22072/25880 [4:30:31<47:07,  1.35it/s]
1|22073|Loss: 0.8825793266296387:  85%|████████▌ | 22073/25880 [4:30:31<47:55,  1.32it/s]
1|22074|Loss: 0.9224034547805786:  85%|████████▌ | 22073/25880 [4:30:31<47:55,  1.32it/s]
1|22074|Loss: 0.9224034547805786:  85%|████████▌ | 22074/25880 [4:30:32<46:12,  1.37it/s]
1|22075|Loss: 0.7091992497444153:  85%|████████▌ | 22074/25880 [4:30:32<46:12,  1.37it/s]
1|22075|Loss: 0.7091992497444153:  85%|████████▌ | 22075/25880 [4:30:32<44:33,  1.42it/s]
1|22076|Loss: 0.7961340546607971:  85%|████████▌ | 22075/25880 [4:30:33<44:33,  1.42it/s]
1|22076|Loss: 0.7961340546607971:  85%|████████▌ | 22076/25880 [4:30:33<46:54,  1.35it/s]
1|22077|Loss: 0.7538655996322632:  85%|████████▌ | 22076/25880 [4:30:34<46:54,  1.35it/s]
1|22077|Loss: 0.7538655996322632:  85%|████████▌ | 22077/25880 [4:30:34<47:24,  1.34it/s]
1|22078|Loss: 0.8360791206359863:  85%|████████▌ | 22077/25880 [4:30:34<47:24,  1.34it/s]
1|22078|Loss: 0.8360791206359863:  85%|████████▌ | 22078/25880 [4:30:35<47:09,  1.34it/s]
1|22079|Loss: 0.9601262211799622:  85%|████████▌ | 22078/25880 [4:30:35<47:09,  1.34it/s]
1|22079|Loss: 0.9601262211799622:  85%|████████▌ | 22079/25880 [4:30:35<48:06,  1.32it/s]
1|22080|Loss: 0.8022255301475525:  85%|████████▌ | 22079/25880 [4:30:36<48:06,  1.32it/s]
1|22080|Loss: 0.8022255301475525:  85%|████████▌ | 22080/25880 [4:30:36<48:58,  1.29it/s]
1|22081|Loss: 0.878007173538208:  85%|████████▌ | 22080/25880 [4:30:37<48:58,  1.29it/s] 
1|22081|Loss: 0.878007173538208:  85%|████████▌ | 22081/25880 [4:30:37<47:04,  1.35it/s]
1|22082|Loss: 0.8659464716911316:  85%|████████▌ | 22081/25880 [4:30:37<47:04,  1.35it/s]
1|22082|Loss: 0.8659464716911316:  85%|████████▌ | 22082/25880 [4:30:38<46:48,  1.35it/s]
1|22083|Loss: 0.784484326839447:  85%|████████▌ | 22082/25880 [4:30:38<46:48,  1.35it/s] 
1|22083|Loss: 0.784484326839447:  85%|████████▌ | 22083/25880 [4:30:38<45:02,  1.41it/s]
1|22084|Loss: 0.8212452530860901:  85%|████████▌ | 22083/25880 [4:30:39<45:02,  1.41it/s]
1|22084|Loss: 0.8212452530860901:  85%|████████▌ | 22084/25880 [4:30:39<46:31,  1.36it/s]
1|22085|Loss: 0.7052004933357239:  85%|████████▌ | 22084/25880 [4:30:39<46:31,  1.36it/s]
1|22085|Loss: 0.7052004933357239:  85%|████████▌ | 22085/25880 [4:30:40<45:26,  1.39it/s]
1|22086|Loss: 0.7682492733001709:  85%|████████▌ | 22085/25880 [4:30:40<45:26,  1.39it/s]
1|22086|Loss: 0.7682492733001709:  85%|████████▌ | 22086/25880 [4:30:40<45:02,  1.40it/s]
1|22087|Loss: 0.9686378240585327:  85%|████████▌ | 22086/25880 [4:30:41<45:02,  1.40it/s]
1|22087|Loss: 0.9686378240585327:  85%|████████▌ | 22087/25880 [4:30:41<41:57,  1.51it/s]
1|22088|Loss: 0.8854148983955383:  85%|████████▌ | 22087/25880 [4:30:41<41:57,  1.51it/s]
1|22088|Loss: 0.8854148983955383:  85%|████████▌ | 22088/25880 [4:30:42<41:04,  1.54it/s]
1|22089|Loss: 0.8070767521858215:  85%|████████▌ | 22088/25880 [4:30:42<41:04,  1.54it/s]
1|22089|Loss: 0.8070767521858215:  85%|████████▌ | 22089/25880 [4:30:42<40:55,  1.54it/s]
1|22090|Loss: 0.8931159377098083:  85%|████████▌ | 22089/25880 [4:30:43<40:55,  1.54it/s]
1|22090|Loss: 0.8931159377098083:  85%|████████▌ | 22090/25880 [4:30:43<45:41,  1.38it/s]
1|22091|Loss: 0.7799714803695679:  85%|████████▌ | 22090/25880 [4:30:44<45:41,  1.38it/s]
1|22091|Loss: 0.7799714803695679:  85%|████████▌ | 22091/25880 [4:30:44<44:25,  1.42it/s]
1|22092|Loss: 0.7576223611831665:  85%|████████▌ | 22091/25880 [4:30:44<44:25,  1.42it/s]
1|22092|Loss: 0.7576223611831665:  85%|████████▌ | 22092/25880 [4:30:45<47:30,  1.33it/s]
1|22093|Loss: 0.9254254698753357:  85%|████████▌ | 22092/25880 [4:30:45<47:30,  1.33it/s]
1|22093|Loss: 0.9254254698753357:  85%|████████▌ | 22093/25880 [4:30:45<46:30,  1.36it/s]
1|22094|Loss: 0.8652663826942444:  85%|████████▌ | 22093/25880 [4:30:46<46:30,  1.36it/s]
1|22094|Loss: 0.8652663826942444:  85%|████████▌ | 22094/25880 [4:30:46<45:47,  1.38it/s]
1|22095|Loss: 0.7385057210922241:  85%|████████▌ | 22094/25880 [4:30:46<45:47,  1.38it/s]
1|22095|Loss: 0.7385057210922241:  85%|████████▌ | 22095/25880 [4:30:47<41:30,  1.52it/s]
1|22096|Loss: 0.7799525260925293:  85%|████████▌ | 22095/25880 [4:30:47<41:30,  1.52it/s]
1|22096|Loss: 0.7799525260925293:  85%|████████▌ | 22096/25880 [4:30:47<43:30,  1.45it/s]
1|22097|Loss: 1.0255540609359741:  85%|████████▌ | 22096/25880 [4:30:48<43:30,  1.45it/s]
1|22097|Loss: 1.0255540609359741:  85%|████████▌ | 22097/25880 [4:30:48<45:35,  1.38it/s]
1|22098|Loss: 0.786794126033783:  85%|████████▌ | 22097/25880 [4:30:49<45:35,  1.38it/s] 
1|22098|Loss: 0.786794126033783:  85%|████████▌ | 22098/25880 [4:30:49<47:05,  1.34it/s]
1|22099|Loss: 0.8641670346260071:  85%|████████▌ | 22098/25880 [4:30:49<47:05,  1.34it/s]
1|22099|Loss: 0.8641670346260071:  85%|████████▌ | 22099/25880 [4:30:50<44:51,  1.40it/s]
1|22100|Loss: 0.7144431471824646:  85%|████████▌ | 22099/25880 [4:30:50<44:51,  1.40it/s]
1|22100|Loss: 0.7144431471824646:  85%|████████▌ | 22100/25880 [4:30:50<44:39,  1.41it/s]
1|22101|Loss: 0.7325713038444519:  85%|████████▌ | 22100/25880 [4:30:51<44:39,  1.41it/s]
1|22101|Loss: 0.7325713038444519:  85%|████████▌ | 22101/25880 [4:30:51<46:45,  1.35it/s]
1|22102|Loss: 0.7538614869117737:  85%|████████▌ | 22101/25880 [4:30:52<46:45,  1.35it/s]
1|22102|Loss: 0.7538614869117737:  85%|████████▌ | 22102/25880 [4:30:52<46:52,  1.34it/s]
1|22103|Loss: 0.9002503752708435:  85%|████████▌ | 22102/25880 [4:30:52<46:52,  1.34it/s]
1|22103|Loss: 0.9002503752708435:  85%|████████▌ | 22103/25880 [4:30:53<47:38,  1.32it/s]
1|22104|Loss: 0.803163468837738:  85%|████████▌ | 22103/25880 [4:30:53<47:38,  1.32it/s] 
1|22104|Loss: 0.803163468837738:  85%|████████▌ | 22104/25880 [4:30:53<48:12,  1.31it/s]
1|22105|Loss: 0.7834119200706482:  85%|████████▌ | 22104/25880 [4:30:54<48:12,  1.31it/s]
1|22105|Loss: 0.7834119200706482:  85%|████████▌ | 22105/25880 [4:30:54<47:57,  1.31it/s]
1|22106|Loss: 0.8821098208427429:  85%|████████▌ | 22105/25880 [4:30:55<47:57,  1.31it/s]
1|22106|Loss: 0.8821098208427429:  85%|████████▌ | 22106/25880 [4:30:55<50:58,  1.23it/s]
1|22107|Loss: 0.784153163433075:  85%|████████▌ | 22106/25880 [4:30:56<50:58,  1.23it/s] 
1|22107|Loss: 0.784153163433075:  85%|████████▌ | 22107/25880 [4:30:56<50:30,  1.25it/s]
1|22108|Loss: 0.8993861675262451:  85%|████████▌ | 22107/25880 [4:30:56<50:30,  1.25it/s]
1|22108|Loss: 0.8993861675262451:  85%|████████▌ | 22108/25880 [4:30:57<51:32,  1.22it/s]
1|22109|Loss: 0.6529380083084106:  85%|████████▌ | 22108/25880 [4:30:57<51:32,  1.22it/s]
1|22109|Loss: 0.6529380083084106:  85%|████████▌ | 22109/25880 [4:30:58<53:29,  1.17it/s]
1|22110|Loss: 0.7691230177879333:  85%|████████▌ | 22109/25880 [4:30:58<53:29,  1.17it/s]
1|22110|Loss: 0.7691230177879333:  85%|████████▌ | 22110/25880 [4:30:58<51:50,  1.21it/s]
1|22111|Loss: 0.6816403269767761:  85%|████████▌ | 22110/25880 [4:30:59<51:50,  1.21it/s]
1|22111|Loss: 0.6816403269767761:  85%|████████▌ | 22111/25880 [4:30:59<50:17,  1.25it/s]
1|22112|Loss: 0.7263367176055908:  85%|████████▌ | 22111/25880 [4:31:00<50:17,  1.25it/s]
1|22112|Loss: 0.7263367176055908:  85%|████████▌ | 22112/25880 [4:31:00<50:13,  1.25it/s]
1|22113|Loss: 1.0857794284820557:  85%|████████▌ | 22112/25880 [4:31:00<50:13,  1.25it/s]
1|22113|Loss: 1.0857794284820557:  85%|████████▌ | 22113/25880 [4:31:01<49:06,  1.28it/s]
1|22114|Loss: 0.863246500492096:  85%|██████��█▌ | 22113/25880 [4:31:01<49:06,  1.28it/s] 
1|22114|Loss: 0.863246500492096:  85%|████████▌ | 22114/25880 [4:31:01<48:11,  1.30it/s]
1|22115|Loss: 0.9155389666557312:  85%|████████▌ | 22114/25880 [4:31:02<48:11,  1.30it/s]
1|22115|Loss: 0.9155389666557312:  85%|████████▌ | 22115/25880 [4:31:02<46:04,  1.36it/s]
1|22116|Loss: 0.8228856325149536:  85%|████████▌ | 22115/25880 [4:31:03<46:04,  1.36it/s]
1|22116|Loss: 0.8228856325149536:  85%|████████▌ | 22116/25880 [4:31:03<47:06,  1.33it/s]
1|22117|Loss: 0.8184141516685486:  85%|████████▌ | 22116/25880 [4:31:03<47:06,  1.33it/s]
1|22117|Loss: 0.8184141516685486:  85%|████████▌ | 22117/25880 [4:31:03<43:44,  1.43it/s]
1|22118|Loss: 0.7857145071029663:  85%|████████▌ | 22117/25880 [4:31:04<43:44,  1.43it/s]
1|22118|Loss: 0.7857145071029663:  85%|████████▌ | 22118/25880 [4:31:04<45:21,  1.38it/s]
1|22119|Loss: 0.8295521140098572:  85%|████████▌ | 22118/25880 [4:31:05<45:21,  1.38it/s]
1|22119|Loss: 0.8295521140098572:  85%|████████▌ | 22119/25880 [4:31:05<45:56,  1.36it/s]
1|22120|Loss: 0.9181366562843323:  85%|████████▌ | 22119/25880 [4:31:05<45:56,  1.36it/s]
1|22120|Loss: 0.9181366562843323:  85%|████████▌ | 22120/25880 [4:31:06<47:43,  1.31it/s]
1|22121|Loss: 0.8439884185791016:  85%|████████▌ | 22120/25880 [4:31:06<47:43,  1.31it/s]
1|22121|Loss: 0.8439884185791016:  85%|████████▌ | 22121/25880 [4:31:06<45:28,  1.38it/s]
1|22122|Loss: 0.8278608918190002:  85%|████████▌ | 22121/25880 [4:31:07<45:28,  1.38it/s]
1|22122|Loss: 0.8278608918190002:  85%|████████▌ | 22122/25880 [4:31:07<43:14,  1.45it/s]
1|22123|Loss: 0.765921950340271:  85%|████████▌ | 22122/25880 [4:31:08<43:14,  1.45it/s] 
1|22123|Loss: 0.765921950340271:  85%|████████▌ | 22123/25880 [4:31:08<47:34,  1.32it/s]
1|22124|Loss: 0.9342849254608154:  85%|████████▌ | 22123/25880 [4:31:09<47:34,  1.32it/s]
1|22124|Loss: 0.9342849254608154:  85%|████████▌ | 22124/25880 [4:31:09<50:21,  1.24it/s]
1|22125|Loss: 0.829565703868866:  85%|████████▌ | 22124/25880 [4:31:09<50:21,  1.24it/s] 
1|22125|Loss: 0.829565703868866:  85%|████████▌ | 22125/25880 [4:31:10<47:57,  1.30it/s]
1|22126|Loss: 0.8831440806388855:  85%|████████▌ | 22125/25880 [4:31:10<47:57,  1.30it/s]
1|22126|Loss: 0.8831440806388855:  85%|████████▌ | 22126/25880 [4:31:10<47:56,  1.31it/s]
1|22127|Loss: 0.8214618563652039:  85%|████████▌ | 22126/25880 [4:31:11<47:56,  1.31it/s]
1|22127|Loss: 0.8214618563652039:  85%|████████▌ | 22127/25880 [4:31:11<50:12,  1.25it/s]
1|22128|Loss: 0.8367751240730286:  85%|████████▌ | 22127/25880 [4:31:12<50:12,  1.25it/s]
1|22128|Loss: 0.8367751240730286:  86%|████████▌ | 22128/25880 [4:31:12<49:20,  1.27it/s]
1|22129|Loss: 0.8863313794136047:  86%|████████▌ | 22128/25880 [4:31:12<49:20,  1.27it/s]
1|22129|Loss: 0.8863313794136047:  86%|████████▌ | 22129/25880 [4:31:13<46:06,  1.36it/s]
1|22130|Loss: 0.8452438712120056:  86%|████████▌ | 22129/25880 [4:31:13<46:06,  1.36it/s]
1|22130|Loss: 0.8452438712120056:  86%|████████▌ | 22130/25880 [4:31:13<43:07,  1.45it/s]
1|22131|Loss: 0.939944863319397:  86%|████████▌ | 22130/25880 [4:31:14<43:07,  1.45it/s] 
1|22131|Loss: 0.939944863319397:  86%|████████▌ | 22131/25880 [4:31:14<43:15,  1.44it/s]
1|22132|Loss: 0.9140501022338867:  86%|████████▌ | 22131/25880 [4:31:14<43:15,  1.44it/s]
1|22132|Loss: 0.9140501022338867:  86%|████████▌ | 22132/25880 [4:31:15<42:08,  1.48it/s]
1|22133|Loss: 0.8327379822731018:  86%|████████▌ | 22132/25880 [4:31:15<42:08,  1.48it/s]
1|22133|Loss: 0.8327379822731018:  86%|████████▌ | 22133/25880 [4:31:15<40:40,  1.54it/s]
1|22134|Loss: 0.8736779689788818:  86%|████████▌ | 22133/25880 [4:31:15<40:40,  1.54it/s]
1|22134|Loss: 0.8736779689788818:  86%|████████▌ | 22134/25880 [4:31:16<38:56,  1.60it/s]
1|22135|Loss: 0.7487062215805054:  86%|████████▌ | 22134/25880 [4:31:16<38:56,  1.60it/s]
1|22135|Loss: 0.7487062215805054:  86%|████████▌ | 22135/25880 [4:31:16<36:04,  1.73it/s]
1|22136|Loss: 0.873896598815918:  86%|████████▌ | 22135/25880 [4:31:16<36:04,  1.73it/s] 
1|22136|Loss: 0.873896598815918:  86%|████████▌ | 22136/25880 [4:31:17<35:29,  1.76it/s]
1|22137|Loss: 0.8785684108734131:  86%|████████▌ | 22136/25880 [4:31:17<35:29,  1.76it/s]
1|22137|Loss: 0.8785684108734131:  86%|████████▌ | 22137/25880 [4:31:17<36:10,  1.72it/s]
1|22138|Loss: 0.9325224161148071:  86%|████████▌ | 22137/25880 [4:31:18<36:10,  1.72it/s]
1|22138|Loss: 0.9325224161148071:  86%|████████▌ | 22138/25880 [4:31:18<39:55,  1.56it/s]
1|22139|Loss: 0.841206967830658:  86%|████████▌ | 22138/25880 [4:31:19<39:55,  1.56it/s] 
1|22139|Loss: 0.841206967830658:  86%|████████▌ | 22139/25880 [4:31:19<42:13,  1.48it/s]
1|22140|Loss: 0.9179696440696716:  86%|████████▌ | 22139/25880 [4:31:19<42:13,  1.48it/s]
1|22140|Loss: 0.9179696440696716:  86%|████████▌ | 22140/25880 [4:31:20<43:36,  1.43it/s]
1|22141|Loss: 0.95162034034729:  86%|████████▌ | 22140/25880 [4:31:20<43:36,  1.43it/s]  
1|22141|Loss: 0.95162034034729:  86%|████████▌ | 22141/25880 [4:31:20<44:33,  1.40it/s]
1|22142|Loss: 0.7308709025382996:  86%|████████▌ | 22141/25880 [4:31:21<44:33,  1.40it/s]
1|22142|Loss: 0.7308709025382996:  86%|████████▌ | 22142/25880 [4:31:21<43:39,  1.43it/s]
1|22143|Loss: 0.8614530563354492:  86%|████████▌ | 22142/25880 [4:31:21<43:39,  1.43it/s]
1|22143|Loss: 0.8614530563354492:  86%|████████▌ | 22143/25880 [4:31:22<44:00,  1.42it/s]
1|22144|Loss: 0.8946777582168579:  86%|████████▌ | 22143/25880 [4:31:22<44:00,  1.42it/s]
1|22144|Loss: 0.8946777582168579:  86%|████████▌ | 22144/25880 [4:31:22<42:54,  1.45it/s]
1|22145|Loss: 0.849364161491394:  86%|████████▌ | 22144/25880 [4:31:23<42:54,  1.45it/s] 
1|22145|Loss: 0.849364161491394:  86%|████████▌ | 22145/25880 [4:31:23<40:14,  1.55it/s]
1|22146|Loss: 0.8704846501350403:  86%|████████▌ | 22145/25880 [4:31:23<40:14,  1.55it/s]
1|22146|Loss: 0.8704846501350403:  86%|████████▌ | 22146/25880 [4:31:24<42:09,  1.48it/s]
1|22147|Loss: 0.8082864880561829:  86%|████████▌ | 22146/25880 [4:31:24<42:09,  1.48it/s]
1|22147|Loss: 0.8082864880561829:  86%|████████▌ | 22147/25880 [4:31:24<43:45,  1.42it/s]
1|22148|Loss: 0.7046260237693787:  86%|████████▌ | 22147/25880 [4:31:25<43:45,  1.42it/s]
1|22148|Loss: 0.7046260237693787:  86%|████████▌ | 22148/25880 [4:31:25<44:35,  1.39it/s]
1|22149|Loss: 0.8220931887626648:  86%|████████▌ | 22148/25880 [4:31:26<44:35,  1.39it/s]
1|22149|Loss: 0.8220931887626648:  86%|████████▌ | 22149/25880 [4:31:26<44:56,  1.38it/s]
1|22150|Loss: 0.997347354888916:  86%|████████▌ | 22149/25880 [4:31:26<44:56,  1.38it/s] 
1|22150|Loss: 0.997347354888916:  86%|████████▌ | 22150/25880 [4:31:27<45:08,  1.38it/s]
1|22151|Loss: 0.8337460160255432:  86%|████████▌ | 22150/25880 [4:31:27<45:08,  1.38it/s]
1|22151|Loss: 0.8337460160255432:  86%|████████▌ | 22151/25880 [4:31:27<42:30,  1.46it/s]
1|22152|Loss: 0.8573477268218994:  86%|████████▌ | 22151/25880 [4:31:28<42:30,  1.46it/s]
1|22152|Loss: 0.8573477268218994:  86%|████████▌ | 22152/25880 [4:31:28<42:53,  1.45it/s]
1|22153|Loss: 0.8681602478027344:  86%|████████▌ | 22152/25880 [4:31:28<42:53,  1.45it/s]
1|22153|Loss: 0.8681602478027344:  86%|████████▌ | 22153/25880 [4:31:29<46:01,  1.35it/s]
1|22154|Loss: 0.7699492573738098:  86%|████████▌ | 22153/25880 [4:31:29<46:01,  1.35it/s]
1|22154|Loss: 0.7699492573738098:  86%|████████▌ | 22154/25880 [4:31:29<43:11,  1.44it/s]
1|22155|Loss: 0.7926891446113586:  86%|████████▌ | 22154/25880 [4:31:30<43:11,  1.44it/s]
1|22155|Loss: 0.7926891446113586:  86%|████████▌ | 22155/25880 [4:31:30<42:53,  1.45it/s]
1|22156|Loss: 0.7625651359558105:  86%|████████▌ | 22155/25880 [4:31:30<42:53,  1.45it/s]
1|22156|Loss: 0.7625651359558105:  86%|████████▌ | 22156/25880 [4:31:31<41:51,  1.48it/s]
1|22157|Loss: 0.7489335536956787:  86%|████████▌ | 22156/25880 [4:31:31<41:51,  1.48it/s]
1|22157|Loss: 0.7489335536956787:  86%|████████▌ | 22157/25880 [4:31:32<43:58,  1.41it/s]
1|22158|Loss: 0.9742493033409119:  86%|████████▌ | 22157/25880 [4:31:32<43:58,  1.41it/s]
1|22158|Loss: 0.9742493033409119:  86%|████████▌ | 22158/25880 [4:31:32<45:41,  1.36it/s]
1|22159|Loss: 0.7126416563987732:  86%|████████▌ | 22158/25880 [4:31:33<45:41,  1.36it/s]
1|22159|Loss: 0.7126416563987732:  86%|████████▌ | 22159/25880 [4:31:33<48:07,  1.29it/s]
1|22160|Loss: 0.8301052451133728:  86%|████████▌ | 22159/25880 [4:31:34<48:07,  1.29it/s]
1|22160|Loss: 0.8301052451133728:  86%|████████▌ | 22160/25880 [4:31:34<49:28,  1.25it/s]
1|22161|Loss: 0.8132962584495544:  86%|████████▌ | 22160/25880 [4:31:34<49:28,  1.25it/s]
1|22161|Loss: 0.8132962584495544:  86%|████████▌ | 22161/25880 [4:31:35<48:47,  1.27it/s]
1|22162|Loss: 0.8777881264686584:  86%|████████▌ | 22161/25880 [4:31:35<48:47,  1.27it/s]
1|22162|Loss: 0.8777881264686584:  86%|████████▌ | 22162/25880 [4:31:36<48:02,  1.29it/s]
1|22163|Loss: 0.8591329455375671:  86%|████████▌ | 22162/25880 [4:31:36<48:02,  1.29it/s]
1|22163|Loss: 0.8591329455375671:  86%|████████▌ | 22163/25880 [4:31:36<47:01,  1.32it/s]
1|22164|Loss: 0.956845223903656:  86%|████████▌ | 22163/25880 [4:31:37<47:01,  1.32it/s] 
1|22164|Loss: 0.956845223903656:  86%|████████▌ | 22164/25880 [4:31:37<49:47,  1.24it/s]
1|22165|Loss: 0.8105777502059937:  86%|████████▌ | 22164/25880 [4:31:38<49:47,  1.24it/s]
1|22165|Loss: 0.8105777502059937:  86%|████████▌ | 22165/25880 [4:31:38<49:14,  1.26it/s]
1|22166|Loss: 0.8744603395462036:  86%|████████▌ | 22165/25880 [4:31:38<49:14,  1.26it/s]
1|22166|Loss: 0.8744603395462036:  86%|████████▌ | 22166/25880 [4:31:39<48:18,  1.28it/s]
1|22167|Loss: 0.8607969284057617:  86%|████████▌ | 22166/25880 [4:31:39<48:18,  1.28it/s]
1|22167|Loss: 0.8607969284057617:  86%|████████▌ | 22167/25880 [4:31:40<48:35,  1.27it/s]
1|22168|Loss: 0.8357045650482178:  86%|████████▌ | 22167/25880 [4:31:40<48:35,  1.27it/s]
1|22168|Loss: 0.8357045650482178:  86%|████████▌ | 22168/25880 [4:31:40<47:51,  1.29it/s]
1|22169|Loss: 0.7743287086486816:  86%|████████▌ | 22168/25880 [4:31:41<47:51,  1.29it/s]
1|22169|Loss: 0.7743287086486816:  86%|████████▌ | 22169/25880 [4:31:41<48:10,  1.28it/s]
1|22170|Loss: 0.7423223853111267:  86%|████████▌ | 22169/25880 [4:31:41<48:10,  1.28it/s]
1|22170|Loss: 0.7423223853111267:  86%|████████▌ | 22170/25880 [4:31:42<47:46,  1.29it/s]
1|22171|Loss: 0.8963072896003723:  86%|████████▌ | 22170/25880 [4:31:42<47:46,  1.29it/s]
1|22171|Loss: 0.8963072896003723:  86%|████████▌ | 22171/25880 [4:31:42<45:46,  1.35it/s]
1|22172|Loss: 0.8781172633171082:  86%|████████▌ | 22171/25880 [4:31:43<45:46,  1.35it/s]
1|22172|Loss: 0.8781172633171082:  86%|████████▌ | 22172/25880 [4:31:43<47:30,  1.30it/s]
1|22173|Loss: 0.8711545467376709:  86%|████████▌ | 22172/25880 [4:31:44<47:30,  1.30it/s]
1|22173|Loss: 0.8711545467376709:  86%|████████▌ | 22173/25880 [4:31:44<47:27,  1.30it/s]
1|22174|Loss: 0.7539448738098145:  86%|████████▌ | 22173/25880 [4:31:44<47:27,  1.30it/s]
1|22174|Loss: 0.7539448738098145:  86%|████████▌ | 22174/25880 [4:31:45<45:01,  1.37it/s]
1|22175|Loss: 0.8892363905906677:  86%|████████▌ | 22174/25880 [4:31:45<45:01,  1.37it/s]
1|22175|Loss: 0.8892363905906677:  86%|████████▌ | 22175/25880 [4:31:45<43:21,  1.42it/s]
1|22176|Loss: 0.7838134765625:  86%|████████▌ | 22175/25880 [4:31:46<43:21,  1.42it/s]   
1|22176|Loss: 0.7838134765625:  86%|████████▌ | 22176/25880 [4:31:46<43:37,  1.41it/s]
1|22177|Loss: 0.8734281659126282:  86%|████████▌ | 22176/25880 [4:31:46<43:37,  1.41it/s]
1|22177|Loss: 0.8734281659126282:  86%|████████▌ | 22177/25880 [4:31:47<44:50,  1.38it/s]
1|22178|Loss: 0.8096379041671753:  86%|████████▌ | 22177/25880 [4:31:47<44:50,  1.38it/s]
1|22178|Loss: 0.8096379041671753:  86%|████████▌ | 22178/25880 [4:31:48<46:27,  1.33it/s]
1|22179|Loss: 0.8520214557647705:  86%|████████▌ | 22178/25880 [4:31:48<46:27,  1.33it/s]
1|22179|Loss: 0.8520214557647705:  86%|████████▌ | 22179/25880 [4:31:48<45:54,  1.34it/s]
1|22180|Loss: 0.8822770714759827:  86%|████████▌ | 22179/25880 [4:31:49<45:54,  1.34it/s]
1|22180|Loss: 0.8822770714759827:  86%|████████▌ | 22180/25880 [4:31:49<46:59,  1.31it/s]
1|22181|Loss: 0.8476243019104004:  86%|████████▌ | 22180/25880 [4:31:50<46:59,  1.31it/s]
1|22181|Loss: 0.8476243019104004:  86%|████████▌ | 22181/25880 [4:31:50<43:27,  1.42it/s]
1|22182|Loss: 0.820846676826477:  86%|████████▌ | 22181/25880 [4:31:50<43:27,  1.42it/s] 
1|22182|Loss: 0.820846676826477:  86%|████████▌ | 22182/25880 [4:31:50<42:39,  1.44it/s]
1|22183|Loss: 0.8767386078834534:  86%|████████▌ | 22182/25880 [4:31:51<42:39,  1.44it/s]
1|22183|Loss: 0.8767386078834534:  86%|████████▌ | 22183/25880 [4:31:51<42:51,  1.44it/s]
1|22184|Loss: 0.8640531301498413:  86%|████████▌ | 22183/25880 [4:31:52<42:51,  1.44it/s]
1|22184|Loss: 0.8640531301498413:  86%|████████▌ | 22184/25880 [4:31:52<45:28,  1.35it/s]
1|22185|Loss: 0.8408649563789368:  86%|████████▌ | 22184/25880 [4:31:52<45:28,  1.35it/s]
1|22185|Loss: 0.8408649563789368:  86%|████████▌ | 22185/25880 [4:31:53<44:17,  1.39it/s]
1|22186|Loss: 0.7964870929718018:  86%|████████▌ | 22185/25880 [4:31:53<44:17,  1.39it/s]
1|22186|Loss: 0.7964870929718018:  86%|████████▌ | 22186/25880 [4:31:53<43:33,  1.41it/s]
1|22187|Loss: 0.8677130341529846:  86%|████████▌ | 22186/25880 [4:31:54<43:33,  1.41it/s]
1|22187|Loss: 0.8677130341529846:  86%|████████▌ | 22187/25880 [4:31:54<41:28,  1.48it/s]
1|22188|Loss: 0.8556065559387207:  86%|████████▌ | 22187/25880 [4:31:54<41:28,  1.48it/s]
1|22188|Loss: 0.8556065559387207:  86%|████████▌ | 22188/25880 [4:31:54<39:13,  1.57it/s]
1|22189|Loss: 0.7843859791755676:  86%|████████▌ | 22188/25880 [4:31:55<39:13,  1.57it/s]
1|22189|Loss: 0.7843859791755676:  86%|████████▌ | 22189/25880 [4:31:55<38:47,  1.59it/s]
1|22190|Loss: 0.8012856245040894:  86%|████████▌ | 22189/25880 [4:31:55<38:47,  1.59it/s]
1|22190|Loss: 0.8012856245040894:  86%|████████▌ | 22190/25880 [4:31:56<41:12,  1.49it/s]
1|22191|Loss: 0.9585708975791931:  86%|████████▌ | 22190/25880 [4:31:56<41:12,  1.49it/s]
1|22191|Loss: 0.9585708975791931:  86%|████████▌ | 22191/25880 [4:31:57<44:00,  1.40it/s]
1|22192|Loss: 0.8673247694969177:  86%|████████▌ | 22191/25880 [4:31:57<44:00,  1.40it/s]
1|22192|Loss: 0.8673247694969177:  86%|████████▌ | 22192/25880 [4:31:57<44:10,  1.39it/s]
1|22193|Loss: 0.8952075839042664:  86%|████████▌ | 22192/25880 [4:31:58<44:10,  1.39it/s]
1|22193|Loss: 0.8952075839042664:  86%|████████▌ | 22193/25880 [4:31:58<43:48,  1.40it/s]
1|22194|Loss: 0.8335731029510498:  86%|████████▌ | 22193/25880 [4:31:59<43:48,  1.40it/s]
1|22194|Loss: 0.8335731029510498:  86%|████████▌ | 22194/25880 [4:31:59<46:04,  1.33it/s]
1|22195|Loss: 0.8824357986450195:  86%|████████▌ | 22194/25880 [4:31:59<46:04,  1.33it/s]
1|22195|Loss: 0.8824357986450195:  86%|████████▌ | 22195/25880 [4:32:00<43:06,  1.42it/s]
1|22196|Loss: 0.8819376230239868:  86%|████████▌ | 22195/25880 [4:32:00<43:06,  1.42it/s]
1|22196|Loss: 0.8819376230239868:  86%|████████▌ | 22196/25880 [4:32:00<42:56,  1.43it/s]
1|22197|Loss: 0.6905393004417419:  86%|████████▌ | 22196/25880 [4:32:01<42:56,  1.43it/s]
1|22197|Loss: 0.6905393004417419:  86%|████████▌ | 22197/25880 [4:32:01<43:36,  1.41it/s]
1|22198|Loss: 0.8565674424171448:  86%|████████▌ | 22197/25880 [4:32:01<43:36,  1.41it/s]
1|22198|Loss: 0.8565674424171448:  86%|████████▌ | 22198/25880 [4:32:01<40:30,  1.51it/s]
1|22199|Loss: 0.761193037033081:  86%|████████▌ | 22198/25880 [4:32:02<40:30,  1.51it/s] 
1|22199|Loss: 0.761193037033081:  86%|████████▌ | 22199/25880 [4:32:02<38:42,  1.59it/s]
1|22200|Loss: 0.7362239956855774:  86%|████████▌ | 22199/25880 [4:32:02<38:42,  1.59it/s]
1|22200|Loss: 0.7362239956855774:  86%|████████▌ | 22200/25880 [4:32:03<38:32,  1.59it/s]
1|22201|Loss: 0.8967484831809998:  86%|████████▌ | 22200/25880 [4:32:03<38:32,  1.59it/s]
1|22201|Loss: 0.8967484831809998:  86%|████████▌ | 22201/25880 [4:32:03<40:21,  1.52it/s]
1|22202|Loss: 0.7516855001449585:  86%|████████▌ | 22201/25880 [4:32:04<40:21,  1.52it/s]
1|22202|Loss: 0.7516855001449585:  86%|████████▌ | 22202/25880 [4:32:04<41:41,  1.47it/s]
1|22203|Loss: 0.8898612260818481:  86%|████████▌ | 22202/25880 [4:32:05<41:41,  1.47it/s]
1|22203|Loss: 0.8898612260818481:  86%|████████▌ | 22203/25880 [4:32:05<42:36,  1.44it/s]
1|22204|Loss: 0.7202796936035156:  86%|████████▌ | 22203/25880 [4:32:05<42:36,  1.44it/s]
1|22204|Loss: 0.7202796936035156:  86%|████████▌ | 22204/25880 [4:32:06<43:02,  1.42it/s]
1|22205|Loss: 0.7588043212890625:  86%|████████▌ | 22204/25880 [4:32:06<43:02,  1.42it/s]
1|22205|Loss: 0.7588043212890625:  86%|████████▌ | 22205/25880 [4:32:06<41:58,  1.46it/s]
1|22206|Loss: 0.8590614199638367:  86%|████████▌ | 22205/25880 [4:32:07<41:58,  1.46it/s]
1|22206|Loss: 0.8590614199638367:  86%|████████▌ | 22206/25880 [4:32:07<41:06,  1.49it/s]
1|22207|Loss: 0.8097547292709351:  86%|████████▌ | 22206/25880 [4:32:07<41:06,  1.49it/s]
1|22207|Loss: 0.8097547292709351:  86%|████████▌ | 22207/25880 [4:32:08<41:30,  1.47it/s]
1|22208|Loss: 0.8116735219955444:  86%|████████▌ | 22207/25880 [4:32:08<41:30,  1.47it/s]
1|22208|Loss: 0.8116735219955444:  86%|████████▌ | 22208/25880 [4:32:08<44:56,  1.36it/s]
1|22209|Loss: 0.8583137392997742:  86%|████████▌ | 22208/25880 [4:32:09<44:56,  1.36it/s]
1|22209|Loss: 0.8583137392997742:  86%|████████▌ | 22209/25880 [4:32:09<47:37,  1.28it/s]
1|22210|Loss: 0.8641496300697327:  86%|████████▌ | 22209/25880 [4:32:10<47:37,  1.28it/s]
1|22210|Loss: 0.8641496300697327:  86%|████████▌ | 22210/25880 [4:32:10<47:00,  1.30it/s]
1|22211|Loss: 0.9259521961212158:  86%|████████▌ | 22210/25880 [4:32:10<47:00,  1.30it/s]
1|22211|Loss: 0.9259521961212158:  86%|████████▌ | 22211/25880 [4:32:11<44:26,  1.38it/s]
1|22212|Loss: 0.805422842502594:  86%|████████▌ | 22211/25880 [4:32:11<44:26,  1.38it/s] 
1|22212|Loss: 0.805422842502594:  86%|████████▌ | 22212/25880 [4:32:11<44:16,  1.38it/s]
1|22213|Loss: 1.2562053203582764:  86%|████████▌ | 22212/25880 [4:32:12<44:16,  1.38it/s]
1|22213|Loss: 1.2562053203582764:  86%|████████▌ | 22213/25880 [4:32:12<49:56,  1.22it/s]
1|22214|Loss: 0.9009578824043274:  86%|████████▌ | 22213/25880 [4:32:13<49:56,  1.22it/s]
1|22214|Loss: 0.9009578824043274:  86%|████████▌ | 22214/25880 [4:32:13<50:03,  1.22it/s]
1|22215|Loss: 0.6685104966163635:  86%|████████▌ | 22214/25880 [4:32:14<50:03,  1.22it/s]
1|22215|Loss: 0.6685104966163635:  86%|████████▌ | 22215/25880 [4:32:14<49:16,  1.24it/s]
1|22216|Loss: 0.9058822393417358:  86%|████████▌ | 22215/25880 [4:32:14<49:16,  1.24it/s]
1|22216|Loss: 0.9058822393417358:  86%|████████▌ | 22216/25880 [4:32:15<48:52,  1.25it/s]
1|22217|Loss: 0.9302659034729004:  86%|████████▌ | 22216/25880 [4:32:15<48:52,  1.25it/s]
1|22217|Loss: 0.9302659034729004:  86%|████████▌ | 22217/25880 [4:32:16<49:13,  1.24it/s]
1|22218|Loss: 0.7951813340187073:  86%|████████▌ | 22217/25880 [4:32:16<49:13,  1.24it/s]
1|22218|Loss: 0.7951813340187073:  86%|████████▌ | 22218/25880 [4:32:16<44:50,  1.36it/s]
1|22219|Loss: 0.8961359858512878:  86%|████████▌ | 22218/25880 [4:32:17<44:50,  1.36it/s]
1|22219|Loss: 0.8961359858512878:  86%|████████▌ | 22219/25880 [4:32:17<44:00,  1.39it/s]
1|22220|Loss: 0.7355453968048096:  86%|████████▌ | 22219/25880 [4:32:17<44:00,  1.39it/s]
1|22220|Loss: 0.7355453968048096:  86%|████████▌ | 22220/25880 [4:32:18<46:16,  1.32it/s]
1|22221|Loss: 0.8381590843200684:  86%|████████▌ | 22220/25880 [4:32:18<46:16,  1.32it/s]
1|22221|Loss: 0.8381590843200684:  86%|████████▌ | 22221/25880 [4:32:18<45:55,  1.33it/s]
1|22222|Loss: 0.8368896842002869:  86%|████████▌ | 22221/25880 [4:32:19<45:55,  1.33it/s]
1|22222|Loss: 0.8368896842002869:  86%|████████▌ | 22222/25880 [4:32:19<43:52,  1.39it/s]
1|22223|Loss: 0.9756510257720947:  86%|████████▌ | 22222/25880 [4:32:19<43:52,  1.39it/s]
1|22223|Loss: 0.9756510257720947:  86%|████████▌ | 22223/25880 [4:32:20<41:42,  1.46it/s]
1|22224|Loss: 0.8704596161842346:  86%|████████▌ | 22223/25880 [4:32:20<41:42,  1.46it/s]
1|22224|Loss: 0.8704596161842346:  86%|████████▌ | 22224/25880 [4:32:21<44:04,  1.38it/s]
1|22225|Loss: 0.7394415140151978:  86%|████████▌ | 22224/25880 [4:32:21<44:04,  1.38it/s]
1|22225|Loss: 0.7394415140151978:  86%|████████▌ | 22225/25880 [4:32:21<44:44,  1.36it/s]
1|22226|Loss: 0.8094186186790466:  86%|████████▌ | 22225/25880 [4:32:22<44:44,  1.36it/s]
1|22226|Loss: 0.8094186186790466:  86%|████████▌ | 22226/25880 [4:32:22<44:52,  1.36it/s]
1|22227|Loss: 0.8274083733558655:  86%|████████▌ | 22226/25880 [4:32:22<44:52,  1.36it/s]
1|22227|Loss: 0.8274083733558655:  86%|████████▌ | 22227/25880 [4:32:23<43:09,  1.41it/s]
1|22228|Loss: 0.7655177712440491:  86%|████████▌ | 22227/25880 [4:32:23<43:09,  1.41it/s]
1|22228|Loss: 0.7655177712440491:  86%|████████▌ | 22228/25880 [4:32:23<43:59,  1.38it/s]
1|22229|Loss: 0.8698107600212097:  86%|████████▌ | 22228/25880 [4:32:24<43:59,  1.38it/s]
1|22229|Loss: 0.8698107600212097:  86%|████████▌ | 22229/25880 [4:32:24<45:58,  1.32it/s]
1|22230|Loss: 0.8160650134086609:  86%|████████▌ | 22229/25880 [4:32:25<45:58,  1.32it/s]
1|22230|Loss: 0.8160650134086609:  86%|████████▌ | 22230/25880 [4:32:25<44:06,  1.38it/s]
1|22231|Loss: 0.9185229539871216:  86%|████████▌ | 22230/25880 [4:32:25<44:06,  1.38it/s]
1|22231|Loss: 0.9185229539871216:  86%|████████▌ | 22231/25880 [4:32:25<40:24,  1.50it/s]
1|22232|Loss: 0.8241915106773376:  86%|████████▌ | 22231/25880 [4:32:26<40:24,  1.50it/s]
1|22232|Loss: 0.8241915106773376:  86%|████████▌ | 22232/25880 [4:32:26<40:19,  1.51it/s]
1|22233|Loss: 0.8656744360923767:  86%|████████▌ | 22232/25880 [4:32:26<40:19,  1.51it/s]
1|22233|Loss: 0.8656744360923767:  86%|████████▌ | 22233/25880 [4:32:27<39:46,  1.53it/s]
1|22234|Loss: 0.8882825970649719:  86%|████████▌ | 22233/25880 [4:32:27<39:46,  1.53it/s]
1|22234|Loss: 0.8882825970649719:  86%|████████▌ | 22234/25880 [4:32:28<42:43,  1.42it/s]
1|22235|Loss: 0.742242157459259:  86%|████████▌ | 22234/25880 [4:32:28<42:43,  1.42it/s] 
1|22235|Loss: 0.742242157459259:  86%|████████▌ | 22235/25880 [4:32:28<43:45,  1.39it/s]
1|22236|Loss: 0.866718053817749:  86%|████████▌ | 22235/25880 [4:32:29<43:45,  1.39it/s]
1|22236|Loss: 0.866718053817749:  86%|████████▌ | 22236/25880 [4:32:29<43:25,  1.40it/s]
1|22237|Loss: 0.872768759727478:  86%|████████▌ | 22236/25880 [4:32:29<43:25,  1.40it/s]
1|22237|Loss: 0.872768759727478:  86%|████████▌ | 22237/25880 [4:32:30<43:03,  1.41it/s]
1|22238|Loss: 0.8433690667152405:  86%|████████▌ | 22237/25880 [4:32:30<43:03,  1.41it/s]
1|22238|Loss: 0.8433690667152405:  86%|████████▌ | 22238/25880 [4:32:30<42:50,  1.42it/s]
1|22239|Loss: 0.9385899901390076:  86%|████████▌ | 22238/25880 [4:32:31<42:50,  1.42it/s]
1|22239|Loss: 0.9385899901390076:  86%|████████▌ | 22239/25880 [4:32:31<43:23,  1.40it/s]
1|22240|Loss: 0.6850098371505737:  86%|████████▌ | 22239/25880 [4:32:32<43:23,  1.40it/s]
1|22240|Loss: 0.6850098371505737:  86%|████████▌ | 22240/25880 [4:32:32<43:43,  1.39it/s]
1|22241|Loss: 0.9794778823852539:  86%|████████▌ | 22240/25880 [4:32:32<43:43,  1.39it/s]
1|22241|Loss: 0.9794778823852539:  86%|████████▌ | 22241/25880 [4:32:32<41:36,  1.46it/s]
1|22242|Loss: 0.8608128428459167:  86%|████████▌ | 22241/25880 [4:32:33<41:36,  1.46it/s]
1|22242|Loss: 0.8608128428459167:  86%|████████▌ | 22242/25880 [4:32:33<41:58,  1.44it/s]
1|22243|Loss: 0.7604668736457825:  86%|████████▌ | 22242/25880 [4:32:34<41:58,  1.44it/s]
1|22243|Loss: 0.7604668736457825:  86%|████████▌ | 22243/25880 [4:32:34<43:51,  1.38it/s]
1|22244|Loss: 0.6628788113594055:  86%|████████▌ | 22243/25880 [4:32:34<43:51,  1.38it/s]
1|22244|Loss: 0.6628788113594055:  86%|████████▌ | 22244/25880 [4:32:35<43:40,  1.39it/s]
1|22245|Loss: 0.8379940986633301:  86%|████████▌ | 22244/25880 [4:32:35<43:40,  1.39it/s]
1|22245|Loss: 0.8379940986633301:  86%|████████▌ | 22245/25880 [4:32:35<44:41,  1.36it/s]
1|22246|Loss: 0.8493227958679199:  86%|████████▌ | 22245/25880 [4:32:36<44:41,  1.36it/s]
1|22246|Loss: 0.8493227958679199:  86%|████████▌ | 22246/25880 [4:32:36<44:18,  1.37it/s]
1|22247|Loss: 0.7871735692024231:  86%|████████▌ | 22246/25880 [4:32:37<44:18,  1.37it/s]
1|22247|Loss: 0.7871735692024231:  86%|████████▌ | 22247/25880 [4:32:37<45:53,  1.32it/s]
1|22248|Loss: 0.8430978655815125:  86%|████████▌ | 22247/25880 [4:32:37<45:53,  1.32it/s]
1|22248|Loss: 0.8430978655815125:  86%|████████▌ | 22248/25880 [4:32:38<45:23,  1.33it/s]
1|22249|Loss: 0.6592015027999878:  86%|████████▌ | 22248/25880 [4:32:38<45:23,  1.33it/s]
1|22249|Loss: 0.6592015027999878:  86%|████████▌ | 22249/25880 [4:32:38<45:08,  1.34it/s]
1|22250|Loss: 0.9660764336585999:  86%|████████▌ | 22249/25880 [4:32:39<45:08,  1.34it/s]
1|22250|Loss: 0.9660764336585999:  86%|████████▌ | 22250/25880 [4:32:39<44:57,  1.35it/s]
1|22251|Loss: 0.8310787081718445:  86%|████████▌ | 22250/25880 [4:32:40<44:57,  1.35it/s]
1|22251|Loss: 0.8310787081718445:  86%|████████▌ | 22251/25880 [4:32:40<44:35,  1.36it/s]
1|22252|Loss: 0.8201401829719543:  86%|████████▌ | 22251/25880 [4:32:40<44:35,  1.36it/s]
1|22252|Loss: 0.8201401829719543:  86%|████████▌ | 22252/25880 [4:32:41<42:44,  1.41it/s]
1|22253|Loss: 0.8977433443069458:  86%|████████▌ | 22252/25880 [4:32:41<42:44,  1.41it/s]
1|22253|Loss: 0.8977433443069458:  86%|████████▌ | 22253/25880 [4:32:41<44:54,  1.35it/s]
1|22254|Loss: 0.9507839679718018:  86%|████████▌ | 22253/25880 [4:32:42<44:54,  1.35it/s]
1|22254|Loss: 0.9507839679718018:  86%|████████▌ | 22254/25880 [4:32:42<45:34,  1.33it/s]
1|22255|Loss: 0.7617964744567871:  86%|████████▌ | 22254/25880 [4:32:43<45:34,  1.33it/s]
1|22255|Loss: 0.7617964744567871:  86%|████████▌ | 22255/25880 [4:32:43<46:39,  1.30it/s]
1|22256|Loss: 0.7282056212425232:  86%|████████▌ | 22255/25880 [4:32:43<46:39,  1.30it/s]
1|22256|Loss: 0.7282056212425232:  86%|████████▌ | 22256/25880 [4:32:44<46:24,  1.30it/s]
1|22257|Loss: 0.7455202341079712:  86%|████████▌ | 22256/25880 [4:32:44<46:24,  1.30it/s]
1|22257|Loss: 0.7455202341079712:  86%|████████▌ | 22257/25880 [4:32:44<44:34,  1.35it/s]
1|22258|Loss: 0.7813681960105896:  86%|████████▌ | 22257/25880 [4:32:45<44:34,  1.35it/s]
1|22258|Loss: 0.7813681960105896:  86%|████████▌ | 22258/25880 [4:32:45<44:10,  1.37it/s]
1|22259|Loss: 0.834969699382782:  86%|████████▌ | 22258/25880 [4:32:46<44:10,  1.37it/s] 
1|22259|Loss: 0.834969699382782:  86%|████████▌ | 22259/25880 [4:32:46<42:49,  1.41it/s]
1|22260|Loss: 0.8032886385917664:  86%|████████▌ | 22259/25880 [4:32:46<42:49,  1.41it/s]
1|22260|Loss: 0.8032886385917664:  86%|████████▌ | 22260/25880 [4:32:47<42:23,  1.42it/s]
1|22261|Loss: 0.7303035855293274:  86%|████████▌ | 22260/25880 [4:32:47<42:23,  1.42it/s]
1|22261|Loss: 0.7303035855293274:  86%|████████▌ | 22261/25880 [4:32:47<41:08,  1.47it/s]
1|22262|Loss: 0.7947961688041687:  86%|████████▌ | 22261/25880 [4:32:47<41:08,  1.47it/s]
1|22262|Loss: 0.7947961688041687:  86%|████████▌ | 22262/25880 [4:32:48<40:16,  1.50it/s]
1|22263|Loss: 0.81048583984375:  86%|████████▌ | 22262/25880 [4:32:48<40:16,  1.50it/s]  
1|22263|Loss: 0.81048583984375:  86%|████████▌ | 22263/25880 [4:32:49<41:22,  1.46it/s]
1|22264|Loss: 1.0183831453323364:  86%|████████▌ | 22263/25880 [4:32:49<41:22,  1.46it/s]
1|22264|Loss: 1.0183831453323364:  86%|████████▌ | 22264/25880 [4:32:49<45:50,  1.31it/s]
1|22265|Loss: 0.7252055406570435:  86%|████████▌ | 22264/25880 [4:32:50<45:50,  1.31it/s]
1|22265|Loss: 0.7252055406570435:  86%|████████▌ | 22265/25880 [4:32:50<46:34,  1.29it/s]
1|22266|Loss: 0.9376006126403809:  86%|████████▌ | 22265/25880 [4:32:51<46:34,  1.29it/s]
1|22266|Loss: 0.9376006126403809:  86%|████████▌ | 22266/25880 [4:32:51<44:19,  1.36it/s]
1|22267|Loss: 0.8130674362182617:  86%|████████▌ | 22266/25880 [4:32:51<44:19,  1.36it/s]
1|22267|Loss: 0.8130674362182617:  86%|████████▌ | 22267/25880 [4:32:52<43:44,  1.38it/s]
1|22268|Loss: 0.7767636179924011:  86%|████████▌ | 22267/25880 [4:32:52<43:44,  1.38it/s]
1|22268|Loss: 0.7767636179924011:  86%|████████▌ | 22268/25880 [4:32:52<43:13,  1.39it/s]
1|22269|Loss: 0.8237404227256775:  86%|████████▌ | 22268/25880 [4:32:53<43:13,  1.39it/s]
1|22269|Loss: 0.8237404227256775:  86%|████████▌ | 22269/25880 [4:32:53<43:22,  1.39it/s]
1|22270|Loss: 0.7339779734611511:  86%|████████▌ | 22269/25880 [4:32:53<43:22,  1.39it/s]
1|22270|Loss: 0.7339779734611511:  86%|████████▌ | 22270/25880 [4:32:54<44:57,  1.34it/s]
1|22271|Loss: 1.0136808156967163:  86%|████████▌ | 22270/25880 [4:32:54<44:57,  1.34it/s]
1|22271|Loss: 1.0136808156967163:  86%|████████▌ | 22271/25880 [4:32:55<46:21,  1.30it/s]
1|22272|Loss: 0.8795740604400635:  86%|████████▌ | 22271/25880 [4:32:55<46:21,  1.30it/s]
1|22272|Loss: 0.8795740604400635:  86%|████████▌ | 22272/25880 [4:32:55<45:31,  1.32it/s]
1|22273|Loss: 1.04390549659729:  86%|████████▌ | 22272/25880 [4:32:56<45:31,  1.32it/s]  
1|22273|Loss: 1.04390549659729:  86%|████████▌ | 22273/25880 [4:32:56<45:42,  1.32it/s]
1|22274|Loss: 0.7745851874351501:  86%|████████▌ | 22273/25880 [4:32:57<45:42,  1.32it/s]
1|22274|Loss: 0.7745851874351501:  86%|████████▌ | 22274/25880 [4:32:57<46:14,  1.30it/s]
1|22275|Loss: 0.8224813342094421:  86%|████████▌ | 22274/25880 [4:32:57<46:14,  1.30it/s]
1|22275|Loss: 0.8224813342094421:  86%|████████▌ | 22275/25880 [4:32:58<43:50,  1.37it/s]
1|22276|Loss: 0.7536554336547852:  86%|████████▌ | 22275/25880 [4:32:58<43:50,  1.37it/s]
1|22276|Loss: 0.7536554336547852:  86%|████████▌ | 22276/25880 [4:32:58<41:15,  1.46it/s]
1|22277|Loss: 0.7280640006065369:  86%|████████▌ | 22276/25880 [4:32:58<41:15,  1.46it/s]
1|22277|Loss: 0.7280640006065369:  86%|████████▌ | 22277/25880 [4:32:59<39:23,  1.52it/s]
1|22278|Loss: 0.8424949049949646:  86%|████████▌ | 22277/25880 [4:32:59<39:23,  1.52it/s]
1|22278|Loss: 0.8424949049949646:  86%|████████▌ | 22278/25880 [4:32:59<40:05,  1.50it/s]
1|22279|Loss: 0.8840065002441406:  86%|████████▌ | 22278/25880 [4:33:00<40:05,  1.50it/s]
1|22279|Loss: 0.8840065002441406:  86%|████████▌ | 22279/25880 [4:33:00<39:47,  1.51it/s]
1|22280|Loss: 0.993015468120575:  86%|████████▌ | 22279/25880 [4:33:00<39:47,  1.51it/s] 
1|22280|Loss: 0.993015468120575:  86%|████████▌ | 22280/25880 [4:33:01<41:40,  1.44it/s]
1|22281|Loss: 0.8713890314102173:  86%|████████▌ | 22280/25880 [4:33:01<41:40,  1.44it/s]
1|22281|Loss: 0.8713890314102173:  86%|████████▌ | 22281/25880 [4:33:02<42:43,  1.40it/s]
1|22282|Loss: 0.8857596516609192:  86%|████████▌ | 22281/25880 [4:33:02<42:43,  1.40it/s]
1|22282|Loss: 0.8857596516609192:  86%|████████▌ | 22282/25880 [4:33:02<42:41,  1.40it/s]
1|22283|Loss: 0.9565984606742859:  86%|████████▌ | 22282/25880 [4:33:03<42:41,  1.40it/s]
1|22283|Loss: 0.9565984606742859:  86%|████████▌ | 22283/25880 [4:33:03<41:31,  1.44it/s]
1|22284|Loss: 0.9509316086769104:  86%|████████▌ | 22283/25880 [4:33:03<41:31,  1.44it/s]
1|22284|Loss: 0.9509316086769104:  86%|████████▌ | 22284/25880 [4:33:04<38:55,  1.54it/s]
1|22285|Loss: 0.8915730118751526:  86%|████████▌ | 22284/25880 [4:33:04<38:55,  1.54it/s]
1|22285|Loss: 0.8915730118751526:  86%|████████▌ | 22285/25880 [4:33:04<39:48,  1.50it/s]
1|22286|Loss: 0.7953418493270874:  86%|████████▌ | 22285/25880 [4:33:05<39:48,  1.50it/s]
1|22286|Loss: 0.7953418493270874:  86%|████████▌ | 22286/25880 [4:33:05<40:59,  1.46it/s]
1|22287|Loss: 0.8675168752670288:  86%|████████▌ | 22286/25880 [4:33:05<40:59,  1.46it/s]
1|22287|Loss: 0.8675168752670288:  86%|████████▌ | 22287/25880 [4:33:06<41:54,  1.43it/s]
1|22288|Loss: 0.7863587737083435:  86%|████████▌ | 22287/25880 [4:33:06<41:54,  1.43it/s]
1|22288|Loss: 0.7863587737083435:  86%|████████▌ | 22288/25880 [4:33:06<42:30,  1.41it/s]
1|22289|Loss: 0.7448129653930664:  86%|████████▌ | 22288/25880 [4:33:07<42:30,  1.41it/s]
1|22289|Loss: 0.7448129653930664:  86%|████████▌ | 22289/25880 [4:33:07<40:51,  1.46it/s]
1|22290|Loss: 0.9625521302223206:  86%|████████▌ | 22289/25880 [4:33:07<40:51,  1.46it/s]
1|22290|Loss: 0.9625521302223206:  86%|████████▌ | 22290/25880 [4:33:08<40:34,  1.47it/s]
1|22291|Loss: 0.8196098208427429:  86%|████████▌ | 22290/25880 [4:33:08<40:34,  1.47it/s]
1|22291|Loss: 0.8196098208427429:  86%|████████▌ | 22291/25880 [4:33:08<39:38,  1.51it/s]
1|22292|Loss: 0.7687857747077942:  86%|████████▌ | 22291/25880 [4:33:09<39:38,  1.51it/s]
1|22292|Loss: 0.7687857747077942:  86%|████████▌ | 22292/25880 [4:33:09<42:07,  1.42it/s]
1|22293|Loss: 0.9459771513938904:  86%|████████▌ | 22292/25880 [4:33:10<42:07,  1.42it/s]
1|22293|Loss: 0.9459771513938904:  86%|████████▌ | 22293/25880 [4:33:10<41:47,  1.43it/s]
1|22294|Loss: 0.869253933429718:  86%|████████▌ | 22293/25880 [4:33:10<41:47,  1.43it/s] 
1|22294|Loss: 0.869253933429718:  86%|████████▌ | 22294/25880 [4:33:11<41:37,  1.44it/s]
1|22295|Loss: 0.8084028959274292:  86%|████████▌ | 22294/25880 [4:33:11<41:37,  1.44it/s]
1|22295|Loss: 0.8084028959274292:  86%|████████▌ | 22295/25880 [4:33:11<45:24,  1.32it/s]
1|22296|Loss: 0.691112756729126:  86%|████████▌ | 22295/25880 [4:33:12<45:24,  1.32it/s] 
1|22296|Loss: 0.691112756729126:  86%|████████▌ | 22296/25880 [4:33:12<44:02,  1.36it/s]
1|22297|Loss: 0.7622499465942383:  86%|████████▌ | 22296/25880 [4:33:12<44:02,  1.36it/s]
1|22297|Loss: 0.7622499465942383:  86%|████████▌ | 22297/25880 [4:33:13<41:23,  1.44it/s]
1|22298|Loss: 0.7389090061187744:  86%|████████▌ | 22297/25880 [4:33:13<41:23,  1.44it/s]
1|22298|Loss: 0.7389090061187744:  86%|████████▌ | 22298/25880 [4:33:14<44:09,  1.35it/s]
1|22299|Loss: 0.7802452445030212:  86%|████████▌ | 22298/25880 [4:33:14<44:09,  1.35it/s]
1|22299|Loss: 0.7802452445030212:  86%|████████▌ | 22299/25880 [4:33:14<44:04,  1.35it/s]
1|22300|Loss: 0.8416699767112732:  86%|████████▌ | 22299/25880 [4:33:15<44:04,  1.35it/s]
1|22300|Loss: 0.8416699767112732:  86%|████████▌ | 22300/25880 [4:33:15<43:19,  1.38it/s]
1|22301|Loss: 0.9265545010566711:  86%|████████▌ | 22300/25880 [4:33:15<43:19,  1.38it/s]
1|22301|Loss: 0.9265545010566711:  86%|████████▌ | 22301/25880 [4:33:16<41:31,  1.44it/s]
1|22302|Loss: 0.8049619197845459:  86%|████████▌ | 22301/25880 [4:33:16<41:31,  1.44it/s]
1|22302|Loss: 0.8049619197845459:  86%|████████▌ | 22302/25880 [4:33:16<39:57,  1.49it/s]
1|22303|Loss: 0.8755072355270386:  86%|████████▌ | 22302/25880 [4:33:17<39:57,  1.49it/s]
1|22303|Loss: 0.8755072355270386:  86%|████████▌ | 22303/25880 [4:33:17<42:03,  1.42it/s]
1|22304|Loss: 0.8886617422103882:  86%|████████▌ | 22303/25880 [4:33:17<42:03,  1.42it/s]
1|22304|Loss: 0.8886617422103882:  86%|████████▌ | 22304/25880 [4:33:18<46:10,  1.29it/s]
1|22305|Loss: 0.786007285118103:  86%|████████▌ | 22304/25880 [4:33:18<46:10,  1.29it/s] 
1|22305|Loss: 0.786007285118103:  86%|████████▌ | 22305/25880 [4:33:19<49:00,  1.22it/s]
1|22306|Loss: 0.8671067357063293:  86%|████████▌ | 22305/25880 [4:33:19<49:00,  1.22it/s]
1|22306|Loss: 0.8671067357063293:  86%|████████▌ | 22306/25880 [4:33:20<49:19,  1.21it/s]
1|22307|Loss: 0.7464898824691772:  86%|████████▌ | 22306/25880 [4:33:20<49:19,  1.21it/s]
1|22307|Loss: 0.7464898824691772:  86%|████████▌ | 22307/25880 [4:33:20<43:49,  1.36it/s]
1|22308|Loss: 0.8332865834236145:  86%|████████▌ | 22307/25880 [4:33:21<43:49,  1.36it/s]
1|22308|Loss: 0.8332865834236145:  86%|████████▌ | 22308/25880 [4:33:21<39:05,  1.52it/s]
1|22309|Loss: 0.7191862463951111:  86%|████████▌ | 22308/25880 [4:33:21<39:05,  1.52it/s]
1|22309|Loss: 0.7191862463951111:  86%|████████▌ | 22309/25880 [4:33:21<39:01,  1.53it/s]
1|22310|Loss: 0.868065357208252:  86%|████████▌ | 22309/25880 [4:33:22<39:01,  1.53it/s] 
1|22310|Loss: 0.868065357208252:  86%|████████▌ | 22310/25880 [4:33:22<38:48,  1.53it/s]
1|22311|Loss: 1.0413872003555298:  86%|████████▌ | 22310/25880 [4:33:22<38:48,  1.53it/s]
1|22311|Loss: 1.0413872003555298:  86%|████████▌ | 22311/25880 [4:33:23<39:51,  1.49it/s]
1|22312|Loss: 0.8098738789558411:  86%|████████▌ | 22311/25880 [4:33:23<39:51,  1.49it/s]
1|22312|Loss: 0.8098738789558411:  86%|████████▌ | 22312/25880 [4:33:23<37:58,  1.57it/s]
1|22313|Loss: 0.89918452501297:  86%|████████▌ | 22312/25880 [4:33:24<37:58,  1.57it/s]  
1|22313|Loss: 0.89918452501297:  86%|████████▌ | 22313/25880 [4:33:24<39:03,  1.52it/s]
1|22314|Loss: 0.8059595823287964:  86%|████████▌ | 22313/25880 [4:33:24<39:03,  1.52it/s]
1|22314|Loss: 0.8059595823287964:  86%|████████▌ | 22314/25880 [4:33:25<41:47,  1.42it/s]
1|22315|Loss: 0.8864137530326843:  86%|████████▌ | 22314/25880 [4:33:25<41:47,  1.42it/s]
1|22315|Loss: 0.8864137530326843:  86%|████████▌ | 22315/25880 [4:33:26<42:41,  1.39it/s]
1|22316|Loss: 0.870472252368927:  86%|████████▌ | 22315/25880 [4:33:26<42:41,  1.39it/s] 
1|22316|Loss: 0.870472252368927:  86%|████████▌ | 22316/25880 [4:33:26<45:43,  1.30it/s]
1|22317|Loss: 0.743781328201294:  86%|████████▌ | 22316/25880 [4:33:27<45:43,  1.30it/s]
1|22317|Loss: 0.743781328201294:  86%|████████▌ | 22317/25880 [4:33:27<40:25,  1.47it/s]
1|22318|Loss: 0.8072768449783325:  86%|████████▌ | 22317/25880 [4:33:27<40:25,  1.47it/s]
1|22318|Loss: 0.8072768449783325:  86%|████████▌ | 22318/25880 [4:33:28<39:57,  1.49it/s]
1|22319|Loss: 0.8451761603355408:  86%|████████▌ | 22318/25880 [4:33:28<39:57,  1.49it/s]
1|22319|Loss: 0.8451761603355408:  86%|████████▌ | 22319/25880 [4:33:28<39:17,  1.51it/s]
1|22320|Loss: 0.88076251745224:  86%|████████▌ | 22319/25880 [4:33:29<39:17,  1.51it/s]  
1|22320|Loss: 0.88076251745224:  86%|████████▌ | 22320/25880 [4:33:29<41:49,  1.42it/s]
1|22321|Loss: 0.7853536605834961:  86%|████████▌ | 22320/25880 [4:33:29<41:49,  1.42it/s]
1|22321|Loss: 0.7853536605834961:  86%|████████▌ | 22321/25880 [4:33:30<43:53,  1.35it/s]
1|22322|Loss: 0.8023780584335327:  86%|████████▌ | 22321/25880 [4:33:30<43:53,  1.35it/s]
1|22322|Loss: 0.8023780584335327:  86%|████████▋ | 22322/25880 [4:33:30<41:27,  1.43it/s]
1|22323|Loss: 0.8486360907554626:  86%|████████▋ | 22322/25880 [4:33:31<41:27,  1.43it/s]
1|22323|Loss: 0.8486360907554626:  86%|████████▋ | 22323/25880 [4:33:31<40:53,  1.45it/s]
1|22324|Loss: 0.8437329530715942:  86%|████████▋ | 22323/25880 [4:33:31<40:53,  1.45it/s]
1|22324|Loss: 0.8437329530715942:  86%|████████▋ | 22324/25880 [4:33:32<38:55,  1.52it/s]
1|22325|Loss: 0.8005003333091736:  86%|████████▋ | 22324/25880 [4:33:32<38:55,  1.52it/s]
1|22325|Loss: 0.8005003333091736:  86%|████████▋ | 22325/25880 [4:33:32<40:37,  1.46it/s]
1|22326|Loss: 0.8715794682502747:  86%|████████▋ | 22325/25880 [4:33:33<40:37,  1.46it/s]
1|22326|Loss: 0.8715794682502747:  86%|████████▋ | 22326/25880 [4:33:33<39:38,  1.49it/s]
1|22327|Loss: 0.7790771126747131:  86%|████████▋ | 22326/25880 [4:33:33<39:38,  1.49it/s]
1|22327|Loss: 0.7790771126747131:  86%|███████���▋ | 22327/25880 [4:33:34<39:34,  1.50it/s]
1|22328|Loss: 0.6758788824081421:  86%|████████▋ | 22327/25880 [4:33:34<39:34,  1.50it/s]
1|22328|Loss: 0.6758788824081421:  86%|████████▋ | 22328/25880 [4:33:34<40:03,  1.48it/s]
1|22329|Loss: 0.8167411088943481:  86%|████████▋ | 22328/25880 [4:33:35<40:03,  1.48it/s]
1|22329|Loss: 0.8167411088943481:  86%|████████▋ | 22329/25880 [4:33:35<40:21,  1.47it/s]
1|22330|Loss: 0.7489979267120361:  86%|████████▋ | 22329/25880 [4:33:36<40:21,  1.47it/s]
1|22330|Loss: 0.7489979267120361:  86%|████████▋ | 22330/25880 [4:33:36<43:37,  1.36it/s]
1|22331|Loss: 0.8794912099838257:  86%|████████▋ | 22330/25880 [4:33:36<43:37,  1.36it/s]
1|22331|Loss: 0.8794912099838257:  86%|████████▋ | 22331/25880 [4:33:37<44:10,  1.34it/s]
1|22332|Loss: 0.8426960706710815:  86%|████████▋ | 22331/25880 [4:33:37<44:10,  1.34it/s]
1|22332|Loss: 0.8426960706710815:  86%|████████▋ | 22332/25880 [4:33:37<44:12,  1.34it/s]
1|22333|Loss: 0.9747351408004761:  86%|████████▋ | 22332/25880 [4:33:38<44:12,  1.34it/s]
1|22333|Loss: 0.9747351408004761:  86%|████████▋ | 22333/25880 [4:33:38<43:33,  1.36it/s]
1|22334|Loss: 0.7514405846595764:  86%|████████▋ | 22333/25880 [4:33:39<43:33,  1.36it/s]
1|22334|Loss: 0.7514405846595764:  86%|████████▋ | 22334/25880 [4:33:39<44:05,  1.34it/s]
1|22335|Loss: 0.8113466501235962:  86%|████████▋ | 22334/25880 [4:33:39<44:05,  1.34it/s]
1|22335|Loss: 0.8113466501235962:  86%|████████▋ | 22335/25880 [4:33:40<46:10,  1.28it/s]
1|22336|Loss: 0.7535154819488525:  86%|████████▋ | 22335/25880 [4:33:40<46:10,  1.28it/s]
1|22336|Loss: 0.7535154819488525:  86%|████████▋ | 22336/25880 [4:33:41<45:32,  1.30it/s]
1|22337|Loss: 0.7451800107955933:  86%|████████▋ | 22336/25880 [4:33:41<45:32,  1.30it/s]
1|22337|Loss: 0.7451800107955933:  86%|████████▋ | 22337/25880 [4:33:41<42:27,  1.39it/s]
1|22338|Loss: 0.8877550959587097:  86%|████████▋ | 22337/25880 [4:33:42<42:27,  1.39it/s]
1|22338|Loss: 0.8877550959587097:  86%|████████▋ | 22338/25880 [4:33:42<42:14,  1.40it/s]
1|22339|Loss: 0.9330087304115295:  86%|████████▋ | 22338/25880 [4:33:42<42:14,  1.40it/s]
1|22339|Loss: 0.9330087304115295:  86%|████████▋ | 22339/25880 [4:33:43<42:39,  1.38it/s]
1|22340|Loss: 1.0099786520004272:  86%|████████▋ | 22339/25880 [4:33:43<42:39,  1.38it/s]
1|22340|Loss: 1.0099786520004272:  86%|████████▋ | 22340/25880 [4:33:43<41:05,  1.44it/s]
1|22341|Loss: 0.8247361183166504:  86%|████████▋ | 22340/25880 [4:33:44<41:05,  1.44it/s]
1|22341|Loss: 0.8247361183166504:  86%|████████▋ | 22341/25880 [4:33:44<42:54,  1.37it/s]
1|22342|Loss: 0.8567573428153992:  86%|████████▋ | 22341/25880 [4:33:45<42:54,  1.37it/s]
1|22342|Loss: 0.8567573428153992:  86%|████████▋ | 22342/25880 [4:33:45<43:33,  1.35it/s]
1|22343|Loss: 0.8244513273239136:  86%|████████▋ | 22342/25880 [4:33:45<43:33,  1.35it/s]
1|22343|Loss: 0.8244513273239136:  86%|████████▋ | 22343/25880 [4:33:46<43:51,  1.34it/s]
1|22344|Loss: 0.9052888751029968:  86%|████████▋ | 22343/25880 [4:33:46<43:51,  1.34it/s]
1|22344|Loss: 0.9052888751029968:  86%|████████▋ | 22344/25880 [4:33:46<45:57,  1.28it/s]
1|22345|Loss: 0.9286592602729797:  86%|████████▋ | 22344/25880 [4:33:47<45:57,  1.28it/s]
1|22345|Loss: 0.9286592602729797:  86%|████████▋ | 22345/25880 [4:33:47<43:27,  1.36it/s]
1|22346|Loss: 0.8177975416183472:  86%|████████▋ | 22345/25880 [4:33:47<43:27,  1.36it/s]
1|22346|Loss: 0.8177975416183472:  86%|████████▋ | 22346/25880 [4:33:48<42:43,  1.38it/s]
1|22347|Loss: 0.874014675617218:  86%|████████▋ | 22346/25880 [4:33:48<42:43,  1.38it/s] 
1|22347|Loss: 0.874014675617218:  86%|████████▋ | 22347/25880 [4:33:49<43:31,  1.35it/s]
1|22348|Loss: 0.7396594285964966:  86%|████████▋ | 22347/25880 [4:33:49<43:31,  1.35it/s]
1|22348|Loss: 0.7396594285964966:  86%|████████▋ | 22348/25880 [4:33:49<46:53,  1.26it/s]
1|22349|Loss: 0.8217923641204834:  86%|████████▋ | 22348/25880 [4:33:50<46:53,  1.26it/s]
1|22349|Loss: 0.8217923641204834:  86%|████████▋ | 22349/25880 [4:33:50<45:59,  1.28it/s]
1|22350|Loss: 0.7416117191314697:  86%|████████▋ | 22349/25880 [4:33:51<45:59,  1.28it/s]
1|22350|Loss: 0.7416117191314697:  86%|████████▋ | 22350/25880 [4:33:51<43:12,  1.36it/s]
1|22351|Loss: 0.9062324166297913:  86%|████████▋ | 22350/25880 [4:33:51<43:12,  1.36it/s]
1|22351|Loss: 0.9062324166297913:  86%|████████▋ | 22351/25880 [4:33:52<44:57,  1.31it/s]
1|22352|Loss: 0.8428012728691101:  86%|████████▋ | 22351/25880 [4:33:52<44:57,  1.31it/s]
1|22352|Loss: 0.8428012728691101:  86%|████████▋ | 22352/25880 [4:33:52<44:40,  1.32it/s]
1|22353|Loss: 0.8004582524299622:  86%|████████▋ | 22352/25880 [4:33:53<44:40,  1.32it/s]
1|22353|Loss: 0.8004582524299622:  86%|████████▋ | 22353/25880 [4:33:53<40:48,  1.44it/s]
1|22354|Loss: 0.7822893261909485:  86%|████████▋ | 22353/25880 [4:33:53<40:48,  1.44it/s]
1|22354|Loss: 0.7822893261909485:  86%|████████▋ | 22354/25880 [4:33:53<36:42,  1.60it/s]
1|22355|Loss: 0.841103732585907:  86%|████████▋ | 22354/25880 [4:33:54<36:42,  1.60it/s] 
1|22355|Loss: 0.841103732585907:  86%|████████▋ | 22355/25880 [4:33:54<37:25,  1.57it/s]
1|22356|Loss: 0.9169700741767883:  86%|████████▋ | 22355/25880 [4:33:54<37:25,  1.57it/s]
1|22356|Loss: 0.9169700741767883:  86%|████████▋ | 22356/25880 [4:33:55<36:52,  1.59it/s]
1|22357|Loss: 0.9424354434013367:  86%|████████▋ | 22356/25880 [4:33:55<36:52,  1.59it/s]
1|22357|Loss: 0.9424354434013367:  86%|████████▋ | 22357/25880 [4:33:55<34:09,  1.72it/s]
1|22358|Loss: 0.7841053009033203:  86%|████████▋ | 22357/25880 [4:33:56<34:09,  1.72it/s]
1|22358|Loss: 0.7841053009033203:  86%|████████▋ | 22358/25880 [4:33:56<36:27,  1.61it/s]
1|22359|Loss: 0.8066166043281555:  86%|████████▋ | 22358/25880 [4:33:56<36:27,  1.61it/s]
1|22359|Loss: 0.8066166043281555:  86%|████████▋ | 22359/25880 [4:33:56<33:45,  1.74it/s]
1|22360|Loss: 0.744500994682312:  86%|████████▋ | 22359/25880 [4:33:57<33:45,  1.74it/s] 
1|22360|Loss: 0.744500994682312:  86%|████████▋ | 22360/25880 [4:33:57<35:41,  1.64it/s]
1|22361|Loss: 0.9295839667320251:  86%|████████▋ | 22360/25880 [4:33:57<35:41,  1.64it/s]
1|22361|Loss: 0.9295839667320251:  86%|████████▋ | 22361/25880 [4:33:58<36:12,  1.62it/s]
1|22362|Loss: 0.786918580532074:  86%|████████▋ | 22361/25880 [4:33:58<36:12,  1.62it/s] 
1|22362|Loss: 0.786918580532074:  86%|████████▋ | 22362/25880 [4:33:58<37:41,  1.56it/s]
1|22363|Loss: 1.0074045658111572:  86%|████████▋ | 22362/25880 [4:33:59<37:41,  1.56it/s]
1|22363|Loss: 1.0074045658111572:  86%|████████▋ | 22363/25880 [4:33:59<38:51,  1.51it/s]
1|22364|Loss: 0.907163143157959:  86%|████████▋ | 22363/25880 [4:34:00<38:51,  1.51it/s] 
1|22364|Loss: 0.907163143157959:  86%|████████▋ | 22364/25880 [4:34:00<40:06,  1.46it/s]
1|22365|Loss: 0.7608645558357239:  86%|████████▋ | 22364/25880 [4:34:00<40:06,  1.46it/s]
1|22365|Loss: 0.7608645558357239:  86%|████████▋ | 22365/25880 [4:34:01<41:04,  1.43it/s]
1|22366|Loss: 0.7638707756996155:  86%|████████▋ | 22365/25880 [4:34:01<41:04,  1.43it/s]
1|22366|Loss: 0.7638707756996155:  86%|████████▋ | 22366/25880 [4:34:01<44:16,  1.32it/s]
1|22367|Loss: 0.8065119981765747:  86%|████████▋ | 22366/25880 [4:34:02<44:16,  1.32it/s]
1|22367|Loss: 0.8065119981765747:  86%|████████▋ | 22367/25880 [4:34:02<46:06,  1.27it/s]
1|22368|Loss: 0.884200394153595:  86%|████████▋ | 22367/25880 [4:34:03<46:06,  1.27it/s] 
1|22368|Loss: 0.884200394153595:  86%|████████▋ | 22368/25880 [4:34:03<44:06,  1.33it/s]
1|22369|Loss: 0.7962167859077454:  86%|████████▋ | 22368/25880 [4:34:03<44:06,  1.33it/s]
1|22369|Loss: 0.7962167859077454:  86%|████████▋ | 22369/25880 [4:34:04<41:59,  1.39it/s]
1|22370|Loss: 0.8348259329795837:  86%|████████▋ | 22369/25880 [4:34:04<41:59,  1.39it/s]
1|22370|Loss: 0.8348259329795837:  86%|████████▋ | 22370/25880 [4:34:04<38:49,  1.51it/s]
1|22371|Loss: 0.7932517528533936:  86%|████████▋ | 22370/25880 [4:34:05<38:49,  1.51it/s]
1|22371|Loss: 0.7932517528533936:  86%|████████▋ | 22371/25880 [4:34:05<37:31,  1.56it/s]
1|22372|Loss: 0.9441177248954773:  86%|████████▋ | 22371/25880 [4:34:05<37:31,  1.56it/s]
1|22372|Loss: 0.9441177248954773:  86%|████████▋ | 22372/25880 [4:34:05<38:18,  1.53it/s]
1|22373|Loss: 0.8036646842956543:  86%|████████▋ | 22372/25880 [4:34:06<38:18,  1.53it/s]
1|22373|Loss: 0.8036646842956543:  86%|████████▋ | 22373/25880 [4:34:06<41:23,  1.41it/s]
1|22374|Loss: 0.8381631374359131:  86%|████████▋ | 22373/25880 [4:34:07<41:23,  1.41it/s]
1|22374|Loss: 0.8381631374359131:  86%|████████▋ | 22374/25880 [4:34:07<40:45,  1.43it/s]
1|22375|Loss: 0.774181604385376:  86%|████████▋ | 22374/25880 [4:34:07<40:45,  1.43it/s] 
1|22375|Loss: 0.774181604385376:  86%|████████▋ | 22375/25880 [4:34:08<42:18,  1.38it/s]
1|22376|Loss: 0.8329828977584839:  86%|████████▋ | 22375/25880 [4:34:08<42:18,  1.38it/s]
1|22376|Loss: 0.8329828977584839:  86%|████████▋ | 22376/25880 [4:34:08<37:37,  1.55it/s]
1|22377|Loss: 0.6903828978538513:  86%|████████▋ | 22376/25880 [4:34:09<37:37,  1.55it/s]
1|22377|Loss: 0.6903828978538513:  86%|████████▋ | 22377/25880 [4:34:09<41:18,  1.41it/s]
1|22378|Loss: 0.7706021070480347:  86%|████████▋ | 22377/25880 [4:34:10<41:18,  1.41it/s]
1|22378|Loss: 0.7706021070480347:  86%|████████▋ | 22378/25880 [4:34:10<42:48,  1.36it/s]
1|22379|Loss: 0.7849442362785339:  86%|████████▋ | 22378/25880 [4:34:10<42:48,  1.36it/s]
1|22379|Loss: 0.7849442362785339:  86%|████████▋ | 22379/25880 [4:34:11<44:06,  1.32it/s]
1|22380|Loss: 0.8985492587089539:  86%|████████▋ | 22379/25880 [4:34:11<44:06,  1.32it/s]
1|22380|Loss: 0.8985492587089539:  86%|████████▋ | 22380/25880 [4:34:11<44:50,  1.30it/s]
1|22381|Loss: 0.8539086580276489:  86%|████████▋ | 22380/25880 [4:34:12<44:50,  1.30it/s]
1|22381|Loss: 0.8539086580276489:  86%|████████▋ | 22381/25880 [4:34:12<45:48,  1.27it/s]
1|22382|Loss: 0.8012784719467163:  86%|████████▋ | 22381/25880 [4:34:13<45:48,  1.27it/s]
1|22382|Loss: 0.8012784719467163:  86%|████████▋ | 22382/25880 [4:34:13<45:10,  1.29it/s]
1|22383|Loss: 0.8501170873641968:  86%|████████▋ | 22382/25880 [4:34:13<45:10,  1.29it/s]
1|22383|Loss: 0.8501170873641968:  86%|████████▋ | 22383/25880 [4:34:14<46:18,  1.26it/s]
1|22384|Loss: 0.8891320824623108:  86%|████████▋ | 22383/25880 [4:34:14<46:18,  1.26it/s]
1|22384|Loss: 0.8891320824623108:  86%|████████▋ | 22384/25880 [4:34:15<45:43,  1.27it/s]
1|22385|Loss: 0.8208823800086975:  86%|████████▋ | 22384/25880 [4:34:15<45:43,  1.27it/s]
1|22385|Loss: 0.8208823800086975:  86%|████████▋ | 22385/25880 [4:34:15<45:33,  1.28it/s]
1|22386|Loss: 0.7805667519569397:  86%|████████▋ | 22385/25880 [4:34:16<45:33,  1.28it/s]
1|22386|Loss: 0.7805667519569397:  86%|████████▋ | 22386/25880 [4:34:16<43:33,  1.34it/s]
1|22387|Loss: 0.9346719980239868:  86%|████████▋ | 22386/25880 [4:34:16<43:33,  1.34it/s]
1|22387|Loss: 0.9346719980239868:  87%|████████▋ | 22387/25880 [4:34:17<41:16,  1.41it/s]
1|22388|Loss: 0.7555595636367798:  87%|████████▋ | 22387/25880 [4:34:17<41:16,  1.41it/s]
1|22388|Loss: 0.7555595636367798:  87%|████████▋ | 22388/25880 [4:34:17<42:14,  1.38it/s]
1|22389|Loss: 0.9384890794754028:  87%|████████▋ | 22388/25880 [4:34:18<42:14,  1.38it/s]
1|22389|Loss: 0.9384890794754028:  87%|████████▋ | 22389/25880 [4:34:18<45:03,  1.29it/s]
1|22390|Loss: 0.8452779650688171:  87%|████████▋ | 22389/25880 [4:34:19<45:03,  1.29it/s]
1|22390|Loss: 0.8452779650688171:  87%|████████▋ | 22390/25880 [4:34:19<46:18,  1.26it/s]
1|22391|Loss: 0.7978308796882629:  87%|████████▋ | 22390/25880 [4:34:20<46:18,  1.26it/s]
1|22391|Loss: 0.7978308796882629:  87%|████████▋ | 22391/25880 [4:34:20<45:23,  1.28it/s]
1|22392|Loss: 0.8232664465904236:  87%|████████▋ | 22391/25880 [4:34:20<45:23,  1.28it/s]
1|22392|Loss: 0.8232664465904236:  87%|████████▋ | 22392/25880 [4:34:21<48:20,  1.20it/s]
1|22393|Loss: 0.7636241316795349:  87%|████████▋ | 22392/25880 [4:34:21<48:20,  1.20it/s]
1|22393|Loss: 0.7636241316795349:  87%|████████▋ | 22393/25880 [4:34:22<49:57,  1.16it/s]
1|22394|Loss: 0.8911253809928894:  87%|████████▋ | 22393/25880 [4:34:22<49:57,  1.16it/s]
1|22394|Loss: 0.8911253809928894:  87%|████████▋ | 22394/25880 [4:34:23<49:41,  1.17it/s]
1|22395|Loss: 0.7950559258460999:  87%|████████▋ | 22394/25880 [4:34:23<49:41,  1.17it/s]
1|22395|Loss: 0.7950559258460999:  87%|████████▋ | 22395/25880 [4:34:23<46:30,  1.25it/s]
1|22396|Loss: 0.9356380105018616:  87%|████████▋ | 22395/25880 [4:34:24<46:30,  1.25it/s]
1|22396|Loss: 0.9356380105018616:  87%|████████▋ | 22396/25880 [4:34:24<44:31,  1.30it/s]
1|22397|Loss: 0.9005687832832336:  87%|████████▋ | 22396/25880 [4:34:24<44:31,  1.30it/s]
1|22397|Loss: 0.9005687832832336:  87%|████████▋ | 22397/25880 [4:34:25<41:35,  1.40it/s]
1|22398|Loss: 0.8889429569244385:  87%|████████▋ | 22397/25880 [4:34:25<41:35,  1.40it/s]
1|22398|Loss: 0.8889429569244385:  87%|████████▋ | 22398/25880 [4:34:25<40:48,  1.42it/s]
1|22399|Loss: 0.881515622138977:  87%|████████▋ | 22398/25880 [4:34:26<40:48,  1.42it/s] 
1|22399|Loss: 0.881515622138977:  87%|████████▋ | 22399/25880 [4:34:26<43:41,  1.33it/s]
1|22400|Loss: 0.8091644644737244:  87%|████████▋ | 22399/25880 [4:34:27<43:41,  1.33it/s]
1|22400|Loss: 0.8091644644737244:  87%|████████▋ | 22400/25880 [4:34:27<43:27,  1.33it/s]
1|22401|Loss: 0.868204653263092:  87%|████████▋ | 22400/25880 [4:34:27<43:27,  1.33it/s] 
1|22401|Loss: 0.868204653263092:  87%|████████▋ | 22401/25880 [4:34:28<42:57,  1.35it/s]
1|22402|Loss: 0.864420473575592:  87%|████████▋ | 22401/25880 [4:34:28<42:57,  1.35it/s]
1|22402|Loss: 0.864420473575592:  87%|████████▋ | 22402/25880 [4:34:28<42:45,  1.36it/s]
1|22403|Loss: 0.9999955892562866:  87%|████████▋ | 22402/25880 [4:34:29<42:45,  1.36it/s]
1|22403|Loss: 0.9999955892562866:  87%|████████▋ | 22403/25880 [4:34:29<42:51,  1.35it/s]
1|22404|Loss: 0.8977075815200806:  87%|████████▋ | 22403/25880 [4:34:30<42:51,  1.35it/s]
1|22404|Loss: 0.8977075815200806:  87%|████████▋ | 22404/25880 [4:34:30<44:42,  1.30it/s]
1|22405|Loss: 0.8576128482818604:  87%|████████▋ | 22404/25880 [4:34:30<44:42,  1.30it/s]
1|22405|Loss: 0.8576128482818604:  87%|████████▋ | 22405/25880 [4:34:31<47:11,  1.23it/s]
1|22406|Loss: 0.8502174615859985:  87%|████████▋ | 22405/25880 [4:34:31<47:11,  1.23it/s]
1|22406|Loss: 0.8502174615859985:  87%|████████▋ | 22406/25880 [4:34:32<47:06,  1.23it/s]
1|22407|Loss: 0.8568683862686157:  87%|████████▋ | 22406/25880 [4:34:32<47:06,  1.23it/s]
1|22407|Loss: 0.8568683862686157:  87%|████████▋ | 22407/25880 [4:34:32<47:11,  1.23it/s]
1|22408|Loss: 0.9052092432975769:  87%|████████▋ | 22407/25880 [4:34:33<47:11,  1.23it/s]
1|22408|Loss: 0.9052092432975769:  87%|████████▋ | 22408/25880 [4:34:33<47:18,  1.22it/s]
1|22409|Loss: 0.8763025999069214:  87%|████████▋ | 22408/25880 [4:34:34<47:18,  1.22it/s]
1|22409|Loss: 0.8763025999069214:  87%|████████▋ | 22409/25880 [4:34:34<45:40,  1.27it/s]
1|22410|Loss: 1.001541256904602:  87%|████████▋ | 22409/25880 [4:34:34<45:40,  1.27it/s] 
1|22410|Loss: 1.001541256904602:  87%|████████▋ | 22410/25880 [4:34:35<42:49,  1.35it/s]
1|22411|Loss: 0.9402235150337219:  87%|████████▋ | 22410/25880 [4:34:35<42:49,  1.35it/s]
1|22411|Loss: 0.9402235150337219:  87%|████████▋ | 22411/25880 [4:34:35<40:36,  1.42it/s]
1|22412|Loss: 0.8151794672012329:  87%|████████▋ | 22411/25880 [4:34:36<40:36,  1.42it/s]
1|22412|Loss: 0.8151794672012329:  87%|████████▋ | 22412/25880 [4:34:36<40:43,  1.42it/s]
1|22413|Loss: 0.7407644987106323:  87%|████████▋ | 22412/25880 [4:34:36<40:43,  1.42it/s]
1|22413|Loss: 0.7407644987106323:  87%|████████▋ | 22413/25880 [4:34:37<39:54,  1.45it/s]
1|22414|Loss: 1.0101639032363892:  87%|████████▋ | 22413/25880 [4:34:37<39:54,  1.45it/s]
1|22414|Loss: 1.0101639032363892:  87%|████████▋ | 22414/25880 [4:34:37<38:37,  1.50it/s]
1|22415|Loss: 0.866077184677124:  87%|████████▋ | 22414/25880 [4:34:38<38:37,  1.50it/s] 
1|22415|Loss: 0.866077184677124:  87%|████████▋ | 22415/25880 [4:34:38<39:18,  1.47it/s]
1|22416|Loss: 0.894219696521759:  87%|████████▋ | 22415/25880 [4:34:38<39:18,  1.47it/s]
1|22416|Loss: 0.894219696521759:  87%|████████▋ | 22416/25880 [4:34:39<43:23,  1.33it/s]
1|22417|Loss: 0.7440401315689087:  87%|████████▋ | 22416/25880 [4:34:39<43:23,  1.33it/s]
1|22417|Loss: 0.7440401315689087:  87%|████████▋ | 22417/25880 [4:34:40<46:27,  1.24it/s]
1|22418|Loss: 0.7371789216995239:  87%|████████▋ | 22417/25880 [4:34:40<46:27,  1.24it/s]
1|22418|Loss: 0.7371789216995239:  87%|████████▋ | 22418/25880 [4:34:40<43:13,  1.33it/s]
1|22419|Loss: 0.8399511575698853:  87%|████████▋ | 22418/25880 [4:34:41<43:13,  1.33it/s]
1|22419|Loss: 0.8399511575698853:  87%|████████▋ | 22419/25880 [4:34:41<44:10,  1.31it/s]
1|22420|Loss: 0.6596881747245789:  87%|████████▋ | 22419/25880 [4:34:42<44:10,  1.31it/s]
1|22420|Loss: 0.6596881747245789:  87%|████████▋ | 22420/25880 [4:34:42<45:27,  1.27it/s]
1|22421|Loss: 0.8758602142333984:  87%|████████▋ | 22420/25880 [4:34:42<45:27,  1.27it/s]
1|22421|Loss: 0.8758602142333984:  87%|████████▋ | 22421/25880 [4:34:43<44:22,  1.30it/s]
1|22422|Loss: 0.6112740635871887:  87%|████████▋ | 22421/25880 [4:34:43<44:22,  1.30it/s]
1|22422|Loss: 0.6112740635871887:  87%|████████▋ | 22422/25880 [4:34:44<45:59,  1.25it/s]
1|22423|Loss: 0.9693529009819031:  87%|████████▋ | 22422/25880 [4:34:44<45:59,  1.25it/s]
1|22423|Loss: 0.9693529009819031:  87%|████████▋ | 22423/25880 [4:34:45<47:27,  1.21it/s]
1|22424|Loss: 0.7926027774810791:  87%|████████▋ | 22423/25880 [4:34:45<47:27,  1.21it/s]
1|22424|Loss: 0.7926027774810791:  87%|████████▋ | 22424/25880 [4:34:45<44:01,  1.31it/s]
1|22425|Loss: 0.9117967486381531:  87%|████████▋ | 22424/25880 [4:34:46<44:01,  1.31it/s]
1|22425|Loss: 0.9117967486381531:  87%|████████▋ | 22425/25880 [4:34:46<44:10,  1.30it/s]
1|22426|Loss: 0.8213907480239868:  87%|████████▋ | 22425/25880 [4:34:46<44:10,  1.30it/s]
1|22426|Loss: 0.8213907480239868:  87%|████████▋ | 22426/25880 [4:34:47<43:29,  1.32it/s]
1|22427|Loss: 0.8642706871032715:  87%|████████▋ | 22426/25880 [4:34:47<43:29,  1.32it/s]
1|22427|Loss: 0.8642706871032715:  87%|████████▋ | 22427/25880 [4:34:47<42:53,  1.34it/s]
1|22428|Loss: 0.8586620092391968:  87%|████████▋ | 22427/25880 [4:34:48<42:53,  1.34it/s]
1|22428|Loss: 0.8586620092391968:  87%|████████▋ | 22428/25880 [4:34:48<42:36,  1.35it/s]
1|22429|Loss: 0.780154824256897:  87%|████████▋ | 22428/25880 [4:34:49<42:36,  1.35it/s] 
1|22429|Loss: 0.780154824256897:  87%|████████▋ | 22429/25880 [4:34:49<42:07,  1.37it/s]
1|22430|Loss: 1.007665753364563:  87%|████████▋ | 22429/25880 [4:34:49<42:07,  1.37it/s]
1|22430|Loss: 1.007665753364563:  87%|████████▋ | 22430/25880 [4:34:50<44:01,  1.31it/s]
1|22431|Loss: 0.784298300743103:  87%|████████▋ | 22430/25880 [4:34:50<44:01,  1.31it/s]
1|22431|Loss: 0.784298300743103:  87%|████████▋ | 22431/25880 [4:34:50<42:51,  1.34it/s]
1|22432|Loss: 0.9301325678825378:  87%|████████▋ | 22431/25880 [4:34:51<42:51,  1.34it/s]
1|22432|Loss: 0.9301325678825378:  87%|████████▋ | 22432/25880 [4:34:51<40:21,  1.42it/s]
1|22433|Loss: 0.9285724759101868:  87%|████████▋ | 22432/25880 [4:34:51<40:21,  1.42it/s]
1|22433|Loss: 0.9285724759101868:  87%|████████▋ | 22433/25880 [4:34:52<40:01,  1.44it/s]
1|22434|Loss: 0.8288759589195251:  87%|████████▋ | 22433/25880 [4:34:52<40:01,  1.44it/s]
1|22434|Loss: 0.8288759589195251:  87%|████████▋ | 22434/25880 [4:34:52<42:08,  1.36it/s]
1|22435|Loss: 0.8749960064888:  87%|████████▋ | 22434/25880 [4:34:53<42:08,  1.36it/s]   
1|22435|Loss: 0.8749960064888:  87%|████████▋ | 22435/25880 [4:34:53<42:47,  1.34it/s]
1|22436|Loss: 0.8283581137657166:  87%|████████▋ | 22435/25880 [4:34:54<42:47,  1.34it/s]
1|22436|Loss: 0.8283581137657166:  87%|████████▋ | 22436/25880 [4:34:54<42:47,  1.34it/s]
1|22437|Loss: 0.7880780100822449:  87%|████████▋ | 22436/25880 [4:34:54<42:47,  1.34it/s]
1|22437|Loss: 0.7880780100822449:  87%|████████▋ | 22437/25880 [4:34:55<39:39,  1.45it/s]
1|22438|Loss: 0.8416571021080017:  87%|████████▋ | 22437/25880 [4:34:55<39:39,  1.45it/s]
1|22438|Loss: 0.8416571021080017:  87%|████████▋ | 22438/25880 [4:34:55<39:50,  1.44it/s]
1|22439|Loss: 0.9632778763771057:  87%|████████▋ | 22438/25880 [4:34:56<39:50,  1.44it/s]
1|22439|Loss: 0.9632778763771057:  87%|████████▋ | 22439/25880 [4:34:56<40:44,  1.41it/s]
1|22440|Loss: 0.8942332863807678:  87%|████████▋ | 22439/25880 [4:34:56<40:44,  1.41it/s]
1|22440|Loss: 0.8942332863807678:  87%|████████▋ | 22440/25880 [4:34:57<38:29,  1.49it/s]
1|22441|Loss: 0.9307405352592468:  87%|████████▋ | 22440/25880 [4:34:57<38:29,  1.49it/s]
1|22441|Loss: 0.9307405352592468:  87%|████████▋ | 22441/25880 [4:34:57<38:49,  1.48it/s]
1|22442|Loss: 0.9989210963249207:  87%|████████▋ | 22441/25880 [4:34:58<38:49,  1.48it/s]
1|22442|Loss: 0.9989210963249207:  87%|████████▋ | 22442/25880 [4:34:58<37:41,  1.52it/s]
1|22443|Loss: 0.770534873008728:  87%|████████▋ | 22442/25880 [4:34:58<37:41,  1.52it/s] 
1|22443|Loss: 0.770534873008728:  87%|████████▋ | 22443/25880 [4:34:59<38:25,  1.49it/s]
1|22444|Loss: 0.700868546962738:  87%|████████▋ | 22443/25880 [4:34:59<38:25,  1.49it/s]
1|22444|Loss: 0.700868546962738:  87%|████████▋ | 22444/25880 [4:34:59<40:47,  1.40it/s]
1|22445|Loss: 0.8816591501235962:  87%|████████▋ | 22444/25880 [4:35:00<40:47,  1.40it/s]
1|22445|Loss: 0.8816591501235962:  87%|████████▋ | 22445/25880 [4:35:00<39:18,  1.46it/s]
1|22446|Loss: 0.8867701292037964:  87%|████████▋ | 22445/25880 [4:35:00<39:18,  1.46it/s]
1|22446|Loss: 0.8867701292037964:  87%|████████▋ | 22446/25880 [4:35:01<39:47,  1.44it/s]
1|22447|Loss: 0.7214910984039307:  87%|████████▋ | 22446/25880 [4:35:01<39:47,  1.44it/s]
1|22447|Loss: 0.7214910984039307:  87%|████████▋ | 22447/25880 [4:35:02<40:48,  1.40it/s]
1|22448|Loss: 0.7974851727485657:  87%|████████▋ | 22447/25880 [4:35:02<40:48,  1.40it/s]
1|22448|Loss: 0.7974851727485657:  87%|████████▋ | 22448/25880 [4:35:02<38:48,  1.47it/s]
1|22449|Loss: 0.8438367247581482:  87%|████████▋ | 22448/25880 [4:35:03<38:48,  1.47it/s]
1|22449|Loss: 0.8438367247581482:  87%|████████▋ | 22449/25880 [4:35:03<40:12,  1.42it/s]
1|22450|Loss: 0.8612087965011597:  87%|████████▋ | 22449/25880 [4:35:03<40:12,  1.42it/s]
1|22450|Loss: 0.8612087965011597:  87%|████████▋ | 22450/25880 [4:35:04<39:22,  1.45it/s]
1|22451|Loss: 0.8235507607460022:  87%|████████▋ | 22450/25880 [4:35:04<39:22,  1.45it/s]
1|22451|Loss: 0.8235507607460022:  87%|████████▋ | 22451/25880 [4:35:04<39:39,  1.44it/s]
1|22452|Loss: 0.7705616354942322:  87%|████████▋ | 22451/25880 [4:35:05<39:39,  1.44it/s]
1|22452|Loss: 0.7705616354942322:  87%|████████▋ | 22452/25880 [4:35:05<39:00,  1.46it/s]
1|22453|Loss: 0.89129638671875:  87%|████████▋ | 22452/25880 [4:35:05<39:00,  1.46it/s]  
1|22453|Loss: 0.89129638671875:  87%|████████▋ | 22453/25880 [4:35:06<39:11,  1.46it/s]
1|22454|Loss: 0.784909725189209:  87%|████████▋ | 22453/25880 [4:35:06<39:11,  1.46it/s]
1|22454|Loss: 0.784909725189209:  87%|████████▋ | 22454/25880 [4:35:06<38:08,  1.50it/s]
1|22455|Loss: 0.7933961153030396:  87%|████████▋ | 22454/25880 [4:35:07<38:08,  1.50it/s]
1|22455|Loss: 0.7933961153030396:  87%|████████▋ | 22455/25880 [4:35:07<39:38,  1.44it/s]
1|22456|Loss: 0.8590421080589294:  87%|████████▋ | 22455/25880 [4:35:07<39:38,  1.44it/s]
1|22456|Loss: 0.8590421080589294:  87%|████████▋ | 22456/25880 [4:35:08<40:36,  1.41it/s]
1|22457|Loss: 0.7510493397712708:  87%|████████▋ | 22456/25880 [4:35:08<40:36,  1.41it/s]
1|22457|Loss: 0.7510493397712708:  87%|████████▋ | 22457/25880 [4:35:08<39:43,  1.44it/s]
1|22458|Loss: 0.8247998356819153:  87%|████████▋ | 22457/25880 [4:35:09<39:43,  1.44it/s]
1|22458|Loss: 0.8247998356819153:  87%|████████▋ | 22458/25880 [4:35:09<40:51,  1.40it/s]
1|22459|Loss: 0.8331698775291443:  87%|████████▋ | 22458/25880 [4:35:10<40:51,  1.40it/s]
1|22459|Loss: 0.8331698775291443:  87%|████████▋ | 22459/25880 [4:35:10<42:22,  1.35it/s]
1|22460|Loss: 0.8991785645484924:  87%|████████▋ | 22459/25880 [4:35:10<42:22,  1.35it/s]
1|22460|Loss: 0.8991785645484924:  87%|████████▋ | 22460/25880 [4:35:11<41:55,  1.36it/s]
1|22461|Loss: 0.7802656292915344:  87%|████████▋ | 22460/25880 [4:35:11<41:55,  1.36it/s]
1|22461|Loss: 0.7802656292915344:  87%|████████▋ | 22461/25880 [4:35:11<42:26,  1.34it/s]
1|22462|Loss: 0.7725685238838196:  87%|████████▋ | 22461/25880 [4:35:12<42:26,  1.34it/s]
1|22462|Loss: 0.7725685238838196:  87%|████████▋ | 22462/25880 [4:35:12<40:25,  1.41it/s]
1|22463|Loss: 0.6440850496292114:  87%|████████▋ | 22462/25880 [4:35:12<40:25,  1.41it/s]
1|22463|Loss: 0.6440850496292114:  87%|████████▋ | 22463/25880 [4:35:13<40:23,  1.41it/s]
1|22464|Loss: 0.942470133304596:  87%|████████▋ | 22463/25880 [4:35:13<40:23,  1.41it/s] 
1|22464|Loss: 0.942470133304596:  87%|████████▋ | 22464/25880 [4:35:14<40:53,  1.39it/s]
1|22465|Loss: 0.7430317401885986:  87%|████████▋ | 22464/25880 [4:35:14<40:53,  1.39it/s]
1|22465|Loss: 0.7430317401885986:  87%|████████▋ | 22465/25880 [4:35:14<40:46,  1.40it/s]
1|22466|Loss: 0.8073621988296509:  87%|████████▋ | 22465/25880 [4:35:15<40:46,  1.40it/s]
1|22466|Loss: 0.8073621988296509:  87%|████████▋ | 22466/25880 [4:35:15<38:24,  1.48it/s]
1|22467|Loss: 0.8714349269866943:  87%|████████▋ | 22466/25880 [4:35:15<38:24,  1.48it/s]
1|22467|Loss: 0.8714349269866943:  87%|████████▋ | 22467/25880 [4:35:16<40:19,  1.41it/s]
1|22468|Loss: 0.8066902756690979:  87%|████████▋ | 22467/25880 [4:35:16<40:19,  1.41it/s]
1|22468|Loss: 0.8066902756690979:  87%|████████▋ | 22468/25880 [4:35:16<39:51,  1.43it/s]
1|22469|Loss: 0.8026549220085144:  87%|████████▋ | 22468/25880 [4:35:17<39:51,  1.43it/s]
1|22469|Loss: 0.8026549220085144:  87%|████████▋ | 22469/25880 [4:35:17<40:07,  1.42it/s]
1|22470|Loss: 0.7991142272949219:  87%|████████▋ | 22469/25880 [4:35:17<40:07,  1.42it/s]
1|22470|Loss: 0.7991142272949219:  87%|████████▋ | 22470/25880 [4:35:18<40:45,  1.39it/s]
1|22471|Loss: 0.8194704651832581:  87%|████████▋ | 22470/25880 [4:35:18<40:45,  1.39it/s]
1|22471|Loss: 0.8194704651832581:  87%|████████▋ | 22471/25880 [4:35:19<41:54,  1.36it/s]
1|22472|Loss: 0.9335496425628662:  87%|████████▋ | 22471/25880 [4:35:19<41:54,  1.36it/s]
1|22472|Loss: 0.9335496425628662:  87%|████████▋ | 22472/25880 [4:35:19<39:21,  1.44it/s]
1|22473|Loss: 0.8308255672454834:  87%|████████▋ | 22472/25880 [4:35:20<39:21,  1.44it/s]
1|22473|Loss: 0.8308255672454834:  87%|████████▋ | 22473/25880 [4:35:20<40:49,  1.39it/s]
1|22474|Loss: 0.8971124291419983:  87%|████████▋ | 22473/25880 [4:35:20<40:49,  1.39it/s]
1|22474|Loss: 0.8971124291419983:  87%|████████▋ | 22474/25880 [4:35:21<43:25,  1.31it/s]
1|22475|Loss: 0.9302821755409241:  87%|████████▋ | 22474/25880 [4:35:21<43:25,  1.31it/s]
1|22475|Loss: 0.9302821755409241:  87%|████████▋ | 22475/25880 [4:35:22<43:27,  1.31it/s]
1|22476|Loss: 0.7836195230484009:  87%|████████▋ | 22475/25880 [4:35:22<43:27,  1.31it/s]
1|22476|Loss: 0.7836195230484009:  87%|████████▋ | 22476/25880 [4:35:22<40:31,  1.40it/s]
1|22477|Loss: 0.8437616229057312:  87%|████████▋ | 22476/25880 [4:35:22<40:31,  1.40it/s]
1|22477|Loss: 0.8437616229057312:  87%|████████▋ | 22477/25880 [4:35:23<40:20,  1.41it/s]
1|22478|Loss: 0.8276121020317078:  87%|████████▋ | 22477/25880 [4:35:23<40:20,  1.41it/s]
1|22478|Loss: 0.8276121020317078:  87%|████████▋ | 22478/25880 [4:35:24<40:18,  1.41it/s]
1|22479|Loss: 0.8636983633041382:  87%|████████▋ | 22478/25880 [4:35:24<40:18,  1.41it/s]
1|22479|Loss: 0.8636983633041382:  87%|████████▋ | 22479/25880 [4:35:24<39:18,  1.44it/s]
1|22480|Loss: 0.8552070260047913:  87%|████████▋ | 22479/25880 [4:35:25<39:18,  1.44it/s]
1|22480|Loss: 0.8552070260047913:  87%|████████▋ | 22480/25880 [4:35:25<41:15,  1.37it/s]
1|22481|Loss: 0.8590704202651978:  87%|████████▋ | 22480/25880 [4:35:25<41:15,  1.37it/s]
1|22481|Loss: 0.8590704202651978:  87%|████████▋ | 22481/25880 [4:35:26<43:55,  1.29it/s]
1|22482|Loss: 0.8783977031707764:  87%|████████▋ | 22481/25880 [4:35:26<43:55,  1.29it/s]
1|22482|Loss: 0.8783977031707764:  87%|████████▋ | 22482/25880 [4:35:27<43:55,  1.29it/s]
1|22483|Loss: 1.0274006128311157:  87%|████████▋ | 22482/25880 [4:35:27<43:55,  1.29it/s]
1|22483|Loss: 1.0274006128311157:  87%|████████▋ | 22483/25880 [4:35:27<42:10,  1.34it/s]
1|22484|Loss: 0.9834234118461609:  87%|████████▋ | 22483/25880 [4:35:28<42:10,  1.34it/s]
1|22484|Loss: 0.9834234118461609:  87%|████████▋ | 22484/25880 [4:35:28<40:03,  1.41it/s]
1|22485|Loss: 0.8458378314971924:  87%|████████▋ | 22484/25880 [4:35:28<40:03,  1.41it/s]
1|22485|Loss: 0.8458378314971924:  87%|████████▋ | 22485/25880 [4:35:29<40:04,  1.41it/s]
1|22486|Loss: 0.7008658647537231:  87%|████████▋ | 22485/25880 [4:35:29<40:04,  1.41it/s]
1|22486|Loss: 0.7008658647537231:  87%|████████▋ | 22486/25880 [4:35:29<40:24,  1.40it/s]
1|22487|Loss: 0.8646579384803772:  87%|████████▋ | 22486/25880 [4:35:30<40:24,  1.40it/s]
1|22487|Loss: 0.8646579384803772:  87%|████████▋ | 22487/25880 [4:35:30<41:27,  1.36it/s]
1|22488|Loss: 0.7207670211791992:  87%|████████▋ | 22487/25880 [4:35:31<41:27,  1.36it/s]
1|22488|Loss: 0.7207670211791992:  87%|████████▋ | 22488/25880 [4:35:31<41:42,  1.36it/s]
1|22489|Loss: 0.7239402532577515:  87%|████████▋ | 22488/25880 [4:35:31<41:42,  1.36it/s]
1|22489|Loss: 0.7239402532577515:  87%|████████▋ | 22489/25880 [4:35:32<42:24,  1.33it/s]
1|22490|Loss: 0.9689365029335022:  87%|████████▋ | 22489/25880 [4:35:32<42:24,  1.33it/s]
1|22490|Loss: 0.9689365029335022:  87%|████████▋ | 22490/25880 [4:35:32<41:55,  1.35it/s]
1|22491|Loss: 0.8898864984512329:  87%|████████▋ | 22490/25880 [4:35:33<41:55,  1.35it/s]
1|22491|Loss: 0.8898864984512329:  87%|████████▋ | 22491/25880 [4:35:33<42:23,  1.33it/s]
1|22492|Loss: 0.8052240610122681:  87%|████████▋ | 22491/25880 [4:35:34<42:23,  1.33it/s]
1|22492|Loss: 0.8052240610122681:  87%|████████▋ | 22492/25880 [4:35:34<42:17,  1.34it/s]
1|22493|Loss: 0.812552809715271:  87%|████████▋ | 22492/25880 [4:35:34<42:17,  1.34it/s] 
1|22493|Loss: 0.812552809715271:  87%|████████▋ | 22493/25880 [4:35:35<41:30,  1.36it/s]
1|22494|Loss: 0.7963425517082214:  87%|████████▋ | 22493/25880 [4:35:35<41:30,  1.36it/s]
1|22494|Loss: 0.7963425517082214:  87%|████████▋ | 22494/25880 [4:35:35<39:47,  1.42it/s]
1|22495|Loss: 0.8311526775360107:  87%|████████▋ | 22494/25880 [4:35:36<39:47,  1.42it/s]
1|22495|Loss: 0.8311526775360107:  87%|████████▋ | 22495/25880 [4:35:36<40:53,  1.38it/s]
1|22496|Loss: 0.7333793640136719:  87%|████████▋ | 22495/25880 [4:35:36<40:53,  1.38it/s]
1|22496|Loss: 0.7333793640136719:  87%|████████▋ | 22496/25880 [4:35:37<42:31,  1.33it/s]
1|22497|Loss: 0.8075774312019348:  87%|████████▋ | 22496/25880 [4:35:37<42:31,  1.33it/s]
1|22497|Loss: 0.8075774312019348:  87%|████████▋ | 22497/25880 [4:35:38<44:06,  1.28it/s]
1|22498|Loss: 0.7416796684265137:  87%|████████▋ | 22497/25880 [4:35:38<44:06,  1.28it/s]
1|22498|Loss: 0.7416796684265137:  87%|████████▋ | 22498/25880 [4:35:38<42:08,  1.34it/s]
1|22499|Loss: 0.8129703402519226:  87%|████████▋ | 22498/25880 [4:35:39<42:08,  1.34it/s]
1|22499|Loss: 0.8129703402519226:  87%|████████▋ | 22499/25880 [4:35:39<41:43,  1.35it/s]
1|22500|Loss: 0.8450762033462524:  87%|████████▋ | 22499/25880 [4:35:40<41:43,  1.35it/s]
1|22500|Loss: 0.8450762033462524:  87%|████████▋ | 22500/25880 [4:35:40<44:12,  1.27it/s]
1|22501|Loss: 0.7666635513305664:  87%|████████▋ | 22500/25880 [4:35:40<44:12,  1.27it/s]
1|22501|Loss: 0.7666635513305664:  87%|████████▋ | 22501/25880 [4:35:41<42:44,  1.32it/s]
1|22502|Loss: 0.7867143750190735:  87%|████████▋ | 22501/25880 [4:35:41<42:44,  1.32it/s]
1|22502|Loss: 0.7867143750190735:  87%|████████▋ | 22502/25880 [4:35:42<43:59,  1.28it/s]
1|22503|Loss: 0.8956322073936462:  87%|████████▋ | 22502/25880 [4:35:42<43:59,  1.28it/s]
1|22503|Loss: 0.8956322073936462:  87%|████████▋ | 22503/25880 [4:35:42<45:01,  1.25it/s]
1|22504|Loss: 0.9050779938697815:  87%|████████▋ | 22503/25880 [4:35:43<45:01,  1.25it/s]
1|22504|Loss: 0.9050779938697815:  87%|████████▋ | 22504/25880 [4:35:43<46:42,  1.20it/s]
1|22505|Loss: 0.9615854620933533:  87%|████████▋ | 22504/25880 [4:35:44<46:42,  1.20it/s]
1|22505|Loss: 0.9615854620933533:  87%|████████▋ | 22505/25880 [4:35:44<45:49,  1.23it/s]
1|22506|Loss: 0.9446901679039001:  87%|████████▋ | 22505/25880 [4:35:44<45:49,  1.23it/s]
1|22506|Loss: 0.9446901679039001:  87%|████████▋ | 22506/25880 [4:35:45<41:12,  1.36it/s]
1|22507|Loss: 0.692182183265686:  87%|████████▋ | 22506/25880 [4:35:45<41:12,  1.36it/s] 
1|22507|Loss: 0.692182183265686:  87%|████████▋ | 22507/25880 [4:35:45<37:34,  1.50it/s]
1|22508|Loss: 0.779957115650177:  87%|████████▋ | 22507/25880 [4:35:45<37:34,  1.50it/s]
1|22508|Loss: 0.779957115650177:  87%|████████▋ | 22508/25880 [4:35:46<36:44,  1.53it/s]
1|22509|Loss: 0.7797670960426331:  87%|████████▋ | 22508/25880 [4:35:46<36:44,  1.53it/s]
1|22509|Loss: 0.7797670960426331:  87%|████████▋ | 22509/25880 [4:35:46<36:35,  1.54it/s]
1|22510|Loss: 0.7505484819412231:  87%|████████▋ | 22509/25880 [4:35:47<36:35,  1.54it/s]
1|22510|Loss: 0.7505484819412231:  87%|████████▋ | 22510/25880 [4:35:47<37:22,  1.50it/s]
1|22511|Loss: 0.8759217262268066:  87%|████████▋ | 22510/25880 [4:35:47<37:22,  1.50it/s]
1|22511|Loss: 0.8759217262268066:  87%|████████▋ | 22511/25880 [4:35:48<38:24,  1.46it/s]
1|22512|Loss: 0.8631588220596313:  87%|████████▋ | 22511/25880 [4:35:48<38:24,  1.46it/s]
1|22512|Loss: 0.8631588220596313:  87%|████████▋ | 22512/25880 [4:35:49<39:09,  1.43it/s]
1|22513|Loss: 0.876741886138916:  87%|████████▋ | 22512/25880 [4:35:49<39:09,  1.43it/s] 
1|22513|Loss: 0.876741886138916:  87%|████████▋ | 22513/25880 [4:35:49<41:39,  1.35it/s]
1|22514|Loss: 0.6890073418617249:  87%|████████▋ | 22513/25880 [4:35:50<41:39,  1.35it/s]
1|22514|Loss: 0.6890073418617249:  87%|████████▋ | 22514/25880 [4:35:50<43:35,  1.29it/s]
1|22515|Loss: 0.8613476753234863:  87%|████████▋ | 22514/25880 [4:35:51<43:35,  1.29it/s]
1|22515|Loss: 0.8613476753234863:  87%|████████▋ | 22515/25880 [4:35:51<40:54,  1.37it/s]
1|22516|Loss: 0.7623368501663208:  87%|████████▋ | 22515/25880 [4:35:51<40:54,  1.37it/s]
1|22516|Loss: 0.7623368501663208:  87%|████████▋ | 22516/25880 [4:35:51<38:13,  1.47it/s]
1|22517|Loss: 0.8668162226676941:  87%|████████▋ | 22516/25880 [4:35:52<38:13,  1.47it/s]
1|22517|Loss: 0.8668162226676941:  87%|████████▋ | 22517/25880 [4:35:52<38:31,  1.45it/s]
1|22518|Loss: 0.7401353120803833:  87%|████████▋ | 22517/25880 [4:35:53<38:31,  1.45it/s]
1|22518|Loss: 0.7401353120803833:  87%|████████▋ | 22518/25880 [4:35:53<40:49,  1.37it/s]
1|22519|Loss: 0.6418473720550537:  87%|████████▋ | 22518/25880 [4:35:53<40:49,  1.37it/s]
1|22519|Loss: 0.6418473720550537:  87%|████████▋ | 22519/25880 [4:35:54<43:21,  1.29it/s]
1|22520|Loss: 0.8164635300636292:  87%|████████▋ | 22519/25880 [4:35:54<43:21,  1.29it/s]
1|22520|Loss: 0.8164635300636292:  87%|████████▋ | 22520/25880 [4:35:55<53:03,  1.06it/s]
1|22521|Loss: 0.8067286610603333:  87%|████████▋ | 22520/25880 [4:35:56<53:03,  1.06it/s]
1|22521|Loss: 0.8067286610603333:  87%|████████▋ | 22521/25880 [4:35:56<52:11,  1.07it/s]
1|22522|Loss: 0.8153489828109741:  87%|████████▋ | 22521/25880 [4:35:56<52:11,  1.07it/s]
1|22522|Loss: 0.8153489828109741:  87%|████████▋ | 22522/25880 [4:35:57<46:53,  1.19it/s]
1|22523|Loss: 0.8313191533088684:  87%|████████▋ | 22522/25880 [4:35:57<46:53,  1.19it/s]
1|22523|Loss: 0.8313191533088684:  87%|████████▋ | 22523/25880 [4:35:57<43:17,  1.29it/s]
1|22524|Loss: 0.8618531227111816:  87%|████████▋ | 22523/25880 [4:35:58<43:17,  1.29it/s]
1|22524|Loss: 0.8618531227111816:  87%|████████▋ | 22524/25880 [4:35:58<43:14,  1.29it/s]
1|22525|Loss: 0.8001573085784912:  87%|████████▋ | 22524/25880 [4:35:59<43:14,  1.29it/s]
1|22525|Loss: 0.8001573085784912:  87%|████████▋ | 22525/25880 [4:35:59<44:24,  1.26it/s]
1|22526|Loss: 0.8795920610427856:  87%|████████▋ | 22525/25880 [4:35:59<44:24,  1.26it/s]
1|22526|Loss: 0.8795920610427856:  87%|████████▋ | 22526/25880 [4:36:00<43:33,  1.28it/s]
1|22527|Loss: 0.8769188523292542:  87%|████████▋ | 22526/25880 [4:36:00<43:33,  1.28it/s]
1|22527|Loss: 0.8769188523292542:  87%|████████▋ | 22527/25880 [4:36:00<42:17,  1.32it/s]
1|22528|Loss: 0.790851354598999:  87%|████████▋ | 22527/25880 [4:36:01<42:17,  1.32it/s] 
1|22528|Loss: 0.790851354598999:  87%|████████▋ | 22528/25880 [4:36:01<40:26,  1.38it/s]
1|22529|Loss: 0.9180300831794739:  87%|████████▋ | 22528/25880 [4:36:01<40:26,  1.38it/s]
1|22529|Loss: 0.9180300831794739:  87%|████████▋ | 22529/25880 [4:36:02<36:25,  1.53it/s]
1|22530|Loss: 0.7343683242797852:  87%|████████▋ | 22529/25880 [4:36:02<36:25,  1.53it/s]
1|22530|Loss: 0.7343683242797852:  87%|████████▋ | 22530/25880 [4:36:02<32:58,  1.69it/s]
1|22531|Loss: 0.793865978717804:  87%|████████▋ | 22530/25880 [4:36:02<32:58,  1.69it/s] 
1|22531|Loss: 0.793865978717804:  87%|████████▋ | 22531/25880 [4:36:03<32:17,  1.73it/s]
1|22532|Loss: 0.80301833152771:  87%|████████▋ | 22531/25880 [4:36:03<32:17,  1.73it/s] 
1|22532|Loss: 0.80301833152771:  87%|████████▋ | 22532/25880 [4:36:03<32:12,  1.73it/s]
1|22533|Loss: 0.94343501329422:  87%|████████▋ | 22532/25880 [4:36:03<32:12,  1.73it/s]
1|22533|Loss: 0.94343501329422:  87%|████████▋ | 22533/25880 [4:36:04<33:53,  1.65it/s]
1|22534|Loss: 0.8243893384933472:  87%|████████▋ | 22533/25880 [4:36:04<33:53,  1.65it/s]
1|22534|Loss: 0.8243893384933472:  87%|████████▋ | 22534/25880 [4:36:04<33:30,  1.66it/s]
1|22535|Loss: 0.9595552682876587:  87%|████████▋ | 22534/25880 [4:36:05<33:30,  1.66it/s]
1|22535|Loss: 0.9595552682876587:  87%|████████▋ | 22535/25880 [4:36:05<33:03,  1.69it/s]
1|22536|Loss: 0.8117083311080933:  87%|████████▋ | 22535/25880 [4:36:05<33:03,  1.69it/s]
1|22536|Loss: 0.8117083311080933:  87%|████████▋ | 22536/25880 [4:36:06<34:52,  1.60it/s]
1|22537|Loss: 0.7965563535690308:  87%|████████▋ | 22536/25880 [4:36:06<34:52,  1.60it/s]
1|22537|Loss: 0.7965563535690308:  87%|████████▋ | 22537/25880 [4:36:06<34:38,  1.61it/s]
1|22538|Loss: 0.8619018197059631:  87%|████████▋ | 22537/25880 [4:36:07<34:38,  1.61it/s]
1|22538|Loss: 0.8619018197059631:  87%|████████▋ | 22538/25880 [4:36:07<33:59,  1.64it/s]
1|22539|Loss: 0.8437349796295166:  87%|████████▋ | 22538/25880 [4:36:07<33:59,  1.64it/s]
1|22539|Loss: 0.8437349796295166:  87%|████████▋ | 22539/25880 [4:36:07<33:37,  1.66it/s]
1|22540|Loss: 0.9355111122131348:  87%|████████▋ | 22539/25880 [4:36:08<33:37,  1.66it/s]
1|22540|Loss: 0.9355111122131348:  87%|████████▋ | 22540/25880 [4:36:08<35:25,  1.57it/s]
1|22541|Loss: 0.7827197909355164:  87%|████████▋ | 22540/25880 [4:36:09<35:25,  1.57it/s]
1|22541|Loss: 0.7827197909355164:  87%|████████▋ | 22541/25880 [4:36:09<39:47,  1.40it/s]
1|22542|Loss: 0.7448799014091492:  87%|████████▋ | 22541/25880 [4:36:09<39:47,  1.40it/s]
1|22542|Loss: 0.7448799014091492:  87%|████████▋ | 22542/25880 [4:36:10<40:43,  1.37it/s]
1|22543|Loss: 0.7740830183029175:  87%|████████▋ | 22542/25880 [4:36:10<40:43,  1.37it/s]
1|22543|Loss: 0.7740830183029175:  87%|████████▋ | 22543/25880 [4:36:11<43:09,  1.29it/s]
1|22544|Loss: 0.7281365394592285:  87%|████████▋ | 22543/25880 [4:36:11<43:09,  1.29it/s]
1|22544|Loss: 0.7281365394592285:  87%|████████▋ | 22544/25880 [4:36:11<42:40,  1.30it/s]
1|22545|Loss: 0.8654372692108154:  87%|████████▋ | 22544/25880 [4:36:12<42:40,  1.30it/s]
1|22545|Loss: 0.8654372692108154:  87%|████████▋ | 22545/25880 [4:36:12<40:20,  1.38it/s]
1|22546|Loss: 0.7348573803901672:  87%|████████▋ | 22545/25880 [4:36:12<40:20,  1.38it/s]
1|22546|Loss: 0.7348573803901672:  87%|████████▋ | 22546/25880 [4:36:13<37:56,  1.46it/s]
1|22547|Loss: 0.8206824064254761:  87%|████████▋ | 22546/25880 [4:36:13<37:56,  1.46it/s]
1|22547|Loss: 0.8206824064254761:  87%|████████▋ | 22547/25880 [4:36:13<39:26,  1.41it/s]
1|22548|Loss: 0.7757879495620728:  87%|████████▋ | 22547/25880 [4:36:14<39:26,  1.41it/s]
1|22548|Loss: 0.7757879495620728:  87%|████████▋ | 22548/25880 [4:36:14<38:36,  1.44it/s]
1|22549|Loss: 0.9231869578361511:  87%|████████▋ | 22548/25880 [4:36:14<38:36,  1.44it/s]
1|22549|Loss: 0.9231869578361511:  87%|████████▋ | 22549/25880 [4:36:15<36:33,  1.52it/s]
1|22550|Loss: 0.8971396088600159:  87%|████████▋ | 22549/25880 [4:36:15<36:33,  1.52it/s]
1|22550|Loss: 0.8971396088600159:  87%|████████▋ | 22550/25880 [4:36:15<35:39,  1.56it/s]
1|22551|Loss: 0.7672885060310364:  87%|████████▋ | 22550/25880 [4:36:16<35:39,  1.56it/s]
1|22551|Loss: 0.7672885060310364:  87%|████████▋ | 22551/25880 [4:36:16<36:28,  1.52it/s]
1|22552|Loss: 0.8501734733581543:  87%|████████▋ | 22551/25880 [4:36:16<36:28,  1.52it/s]
1|22552|Loss: 0.8501734733581543:  87%|████████▋ | 22552/25880 [4:36:17<38:36,  1.44it/s]
1|22553|Loss: 0.8859660029411316:  87%|████████▋ | 22552/25880 [4:36:17<38:36,  1.44it/s]
1|22553|Loss: 0.8859660029411316:  87%|████████▋ | 22553/25880 [4:36:17<38:59,  1.42it/s]
1|22554|Loss: 0.7748395800590515:  87%|████████▋ | 22553/25880 [4:36:18<38:59,  1.42it/s]
1|22554|Loss: 0.7748395800590515:  87%|████████▋ | 22554/25880 [4:36:18<39:32,  1.40it/s]
1|22555|Loss: 0.7246829271316528:  87%|████████▋ | 22554/25880 [4:36:19<39:32,  1.40it/s]
1|22555|Loss: 0.7246829271316528:  87%|████████▋ | 22555/25880 [4:36:19<38:27,  1.44it/s]
1|22556|Loss: 0.7823891639709473:  87%|████████▋ | 22555/25880 [4:36:19<38:27,  1.44it/s]
1|22556|Loss: 0.7823891639709473:  87%|████████▋ | 22556/25880 [4:36:19<35:01,  1.58it/s]
1|22557|Loss: 0.788226306438446:  87%|████████▋ | 22556/25880 [4:36:20<35:01,  1.58it/s] 
1|22557|Loss: 0.788226306438446:  87%|████████▋ | 22557/25880 [4:36:20<35:34,  1.56it/s]
1|22558|Loss: 0.8104414343833923:  87%|████████▋ | 22557/25880 [4:36:20<35:34,  1.56it/s]
1|22558|Loss: 0.8104414343833923:  87%|████████▋ | 22558/25880 [4:36:21<35:26,  1.56it/s]
1|22559|Loss: 0.812367856502533:  87%|████████▋ | 22558/25880 [4:36:21<35:26,  1.56it/s] 
1|22559|Loss: 0.812367856502533:  87%|████████▋ | 22559/25880 [4:36:21<38:16,  1.45it/s]
1|22560|Loss: 0.7753028273582458:  87%|████████▋ | 22559/25880 [4:36:22<38:16,  1.45it/s]
1|22560|Loss: 0.7753028273582458:  87%|████████▋ | 22560/25880 [4:36:22<40:27,  1.37it/s]
1|22561|Loss: 0.8037324547767639:  87%|████████▋ | 22560/25880 [4:36:23<40:27,  1.37it/s]
1|22561|Loss: 0.8037324547767639:  87%|████████▋ | 22561/25880 [4:36:23<40:42,  1.36it/s]
1|22562|Loss: 0.8395755290985107:  87%|████████▋ | 22561/25880 [4:36:23<40:42,  1.36it/s]
1|22562|Loss: 0.8395755290985107:  87%|████████▋ | 22562/25880 [4:36:24<39:26,  1.40it/s]
1|22563|Loss: 0.8284223675727844:  87%|████████▋ | 22562/25880 [4:36:24<39:26,  1.40it/s]
1|22563|Loss: 0.8284223675727844:  87%|████████▋ | 22563/25880 [4:36:24<38:11,  1.45it/s]
1|22564|Loss: 0.8502832651138306:  87%|████████▋ | 22563/25880 [4:36:25<38:11,  1.45it/s]
1|22564|Loss: 0.8502832651138306:  87%|████████▋ | 22564/25880 [4:36:25<38:30,  1.44it/s]
1|22565|Loss: 0.9887161254882812:  87%|████████▋ | 22564/25880 [4:36:25<38:30,  1.44it/s]
1|22565|Loss: 0.9887161254882812:  87%|████████▋ | 22565/25880 [4:36:26<36:17,  1.52it/s]
1|22566|Loss: 0.9313139915466309:  87%|████████▋ | 22565/25880 [4:36:26<36:17,  1.52it/s]
1|22566|Loss: 0.9313139915466309:  87%|████████▋ | 22566/25880 [4:36:26<38:21,  1.44it/s]
1|22567|Loss: 0.8605540990829468:  87%|████████▋ | 22566/25880 [4:36:27<38:21,  1.44it/s]
1|22567|Loss: 0.8605540990829468:  87%|████████▋ | 22567/25880 [4:36:27<41:04,  1.34it/s]
1|22568|Loss: 0.7436476349830627:  87%|████████▋ | 22567/25880 [4:36:28<41:04,  1.34it/s]
1|22568|Loss: 0.7436476349830627:  87%|████████▋ | 22568/25880 [4:36:28<41:32,  1.33it/s]
1|22569|Loss: 0.8988211154937744:  87%|████████▋ | 22568/25880 [4:36:28<41:32,  1.33it/s]
1|22569|Loss: 0.8988211154937744:  87%|████████▋ | 22569/25880 [4:36:29<43:04,  1.28it/s]
1|22570|Loss: 1.0649065971374512:  87%|████████▋ | 22569/25880 [4:36:29<43:04,  1.28it/s]
1|22570|Loss: 1.0649065971374512:  87%|████████▋ | 22570/25880 [4:36:30<45:18,  1.22it/s]
1|22571|Loss: 0.7422254085540771:  87%|████████▋ | 22570/25880 [4:36:30<45:18,  1.22it/s]
1|22571|Loss: 0.7422254085540771:  87%|████████▋ | 22571/25880 [4:36:31<44:28,  1.24it/s]
1|22572|Loss: 0.753481924533844:  87%|████████▋ | 22571/25880 [4:36:31<44:28,  1.24it/s] 
1|22572|Loss: 0.753481924533844:  87%|████████▋ | 22572/25880 [4:36:31<41:39,  1.32it/s]
1|22573|Loss: 0.8442966938018799:  87%|████████▋ | 22572/25880 [4:36:32<41:39,  1.32it/s]
1|22573|Loss: 0.8442966938018799:  87%|████████▋ | 22573/25880 [4:36:32<40:45,  1.35it/s]
1|22574|Loss: 1.058130145072937:  87%|████████▋ | 22573/25880 [4:36:32<40:45,  1.35it/s] 
1|22574|Loss: 1.058130145072937:  87%|████████▋ | 22574/25880 [4:36:32<38:47,  1.42it/s]
1|22575|Loss: 0.7398675680160522:  87%|████████▋ | 22574/25880 [4:36:33<38:47,  1.42it/s]
1|22575|Loss: 0.7398675680160522:  87%|████████▋ | 22575/25880 [4:36:33<40:16,  1.37it/s]
1|22576|Loss: 0.8879042267799377:  87%|████████▋ | 22575/25880 [4:36:34<40:16,  1.37it/s]
1|22576|Loss: 0.8879042267799377:  87%|████████▋ | 22576/25880 [4:36:34<40:48,  1.35it/s]
1|22577|Loss: 0.8325253129005432:  87%|████████▋ | 22576/25880 [4:36:34<40:48,  1.35it/s]
1|22577|Loss: 0.8325253129005432:  87%|████████▋ | 22577/25880 [4:36:35<39:08,  1.41it/s]
1|22578|Loss: 0.8123443722724915:  87%|████████▋ | 22577/25880 [4:36:35<39:08,  1.41it/s]
1|22578|Loss: 0.8123443722724915:  87%|████████▋ | 22578/25880 [4:36:35<39:09,  1.41it/s]
1|22579|Loss: 0.8308002948760986:  87%|████████▋ | 22578/25880 [4:36:36<39:09,  1.41it/s]
1|22579|Loss: 0.8308002948760986:  87%|████████▋ | 22579/25880 [4:36:36<39:08,  1.41it/s]
1|22580|Loss: 0.9566373229026794:  87%|████████▋ | 22579/25880 [4:36:36<39:08,  1.41it/s]
1|22580|Loss: 0.9566373229026794:  87%|████████▋ | 22580/25880 [4:36:37<36:20,  1.51it/s]
1|22581|Loss: 0.7711237072944641:  87%|████████▋ | 22580/25880 [4:36:37<36:20,  1.51it/s]
1|22581|Loss: 0.7711237072944641:  87%|████████▋ | 22581/25880 [4:36:37<36:45,  1.50it/s]
1|22582|Loss: 0.9300186038017273:  87%|████████▋ | 22581/25880 [4:36:38<36:45,  1.50it/s]
1|22582|Loss: 0.9300186038017273:  87%|████████▋ | 22582/25880 [4:36:38<37:49,  1.45it/s]
1|22583|Loss: 0.9430608749389648:  87%|████████▋ | 22582/25880 [4:36:38<37:49,  1.45it/s]
1|22583|Loss: 0.9430608749389648:  87%|████████▋ | 22583/25880 [4:36:39<36:30,  1.50it/s]
1|22584|Loss: 0.8779048323631287:  87%|████████▋ | 22583/25880 [4:36:39<36:30,  1.50it/s]
1|22584|Loss: 0.8779048323631287:  87%|████████▋ | 22584/25880 [4:36:39<36:41,  1.50it/s]
1|22585|Loss: 0.8450648188591003:  87%|████████▋ | 22584/25880 [4:36:40<36:41,  1.50it/s]
1|22585|Loss: 0.8450648188591003:  87%|████████▋ | 22585/25880 [4:36:40<38:33,  1.42it/s]
1|22586|Loss: 0.8750630021095276:  87%|████████▋ | 22585/25880 [4:36:41<38:33,  1.42it/s]
1|22586|Loss: 0.8750630021095276:  87%|████████▋ | 22586/25880 [4:36:41<37:32,  1.46it/s]
1|22587|Loss: 0.8756020069122314:  87%|████████▋ | 22586/25880 [4:36:41<37:32,  1.46it/s]
1|22587|Loss: 0.8756020069122314:  87%|████████▋ | 22587/25880 [4:36:42<38:43,  1.42it/s]
1|22588|Loss: 0.9123635292053223:  87%|████████▋ | 22587/25880 [4:36:42<38:43,  1.42it/s]
1|22588|Loss: 0.9123635292053223:  87%|████████▋ | 22588/25880 [4:36:42<41:26,  1.32it/s]
1|22589|Loss: 0.8519554138183594:  87%|████████▋ | 22588/25880 [4:36:43<41:26,  1.32it/s]
1|22589|Loss: 0.8519554138183594:  87%|████████▋ | 22589/25880 [4:36:43<43:21,  1.27it/s]
1|22590|Loss: 0.6960704922676086:  87%|████████▋ | 22589/25880 [4:36:44<43:21,  1.27it/s]
1|22590|Loss: 0.6960704922676086:  87%|████████▋ | 22590/25880 [4:36:44<44:26,  1.23it/s]
1|22591|Loss: 0.8872522711753845:  87%|████████▋ | 22590/25880 [4:36:45<44:26,  1.23it/s]
1|22591|Loss: 0.8872522711753845:  87%|████████▋ | 22591/25880 [4:36:45<43:45,  1.25it/s]
1|22592|Loss: 0.7868550419807434:  87%|████████▋ | 22591/25880 [4:36:45<43:45,  1.25it/s]
1|22592|Loss: 0.7868550419807434:  87%|████████▋ | 22592/25880 [4:36:46<41:13,  1.33it/s]
1|22593|Loss: 0.8504889011383057:  87%|████████▋ | 22592/25880 [4:36:46<41:13,  1.33it/s]
1|22593|Loss: 0.8504889011383057:  87%|████████▋ | 22593/25880 [4:36:46<42:29,  1.29it/s]
1|22594|Loss: 0.9187238812446594:  87%|████████▋ | 22593/25880 [4:36:47<42:29,  1.29it/s]
1|22594|Loss: 0.9187238812446594:  87%|████████▋ | 22594/25880 [4:36:47<43:37,  1.26it/s]
1|22595|Loss: 0.9469490051269531:  87%|████████▋ | 22594/25880 [4:36:48<43:37,  1.26it/s]
1|22595|Loss: 0.9469490051269531:  87%|████████▋ | 22595/25880 [4:36:48<44:23,  1.23it/s]
1|22596|Loss: 0.7341144680976868:  87%|████████▋ | 22595/25880 [4:36:49<44:23,  1.23it/s]
1|22596|Loss: 0.7341144680976868:  87%|████████▋ | 22596/25880 [4:36:49<45:01,  1.22it/s]
1|22597|Loss: 0.9556472301483154:  87%|████████▋ | 22596/25880 [4:36:49<45:01,  1.22it/s]
1|22597|Loss: 0.9556472301483154:  87%|████████▋ | 22597/25880 [4:36:50<44:43,  1.22it/s]
1|22598|Loss: 0.8058215379714966:  87%|████████▋ | 22597/25880 [4:36:50<44:43,  1.22it/s]
1|22598|Loss: 0.8058215379714966:  87%|████████▋ | 22598/25880 [4:36:50<42:17,  1.29it/s]
1|22599|Loss: 0.7071624994277954:  87%|████████▋ | 22598/25880 [4:36:51<42:17,  1.29it/s]
1|22599|Loss: 0.7071624994277954:  87%|████████▋ | 22599/25880 [4:36:51<37:41,  1.45it/s]
1|22600|Loss: 0.7549542188644409:  87%|████████▋ | 22599/25880 [4:36:51<37:41,  1.45it/s]
1|22600|Loss: 0.7549542188644409:  87%|████████▋ | 22600/25880 [4:36:52<37:02,  1.48it/s]
1|22601|Loss: 0.8694863319396973:  87%|████████▋ | 22600/25880 [4:36:52<37:02,  1.48it/s]
1|22601|Loss: 0.8694863319396973:  87%|████████▋ | 22601/25880 [4:36:52<37:46,  1.45it/s]
1|22602|Loss: 0.9528876543045044:  87%|████████▋ | 22601/25880 [4:36:53<37:46,  1.45it/s]
1|22602|Loss: 0.9528876543045044:  87%|████████▋ | 22602/25880 [4:36:53<38:38,  1.41it/s]
1|22603|Loss: 0.7944270968437195:  87%|████████▋ | 22602/25880 [4:36:53<38:38,  1.41it/s]
1|22603|Loss: 0.7944270968437195:  87%|████████▋ | 22603/25880 [4:36:54<37:52,  1.44it/s]
1|22604|Loss: 0.7798619270324707:  87%|████████▋ | 22603/25880 [4:36:54<37:52,  1.44it/s]
1|22604|Loss: 0.7798619270324707:  87%|████████▋ | 22604/25880 [4:36:54<38:12,  1.43it/s]
1|22605|Loss: 0.8034186959266663:  87%|████████▋ | 22604/25880 [4:36:55<38:12,  1.43it/s]
1|22605|Loss: 0.8034186959266663:  87%|████████▋ | 22605/25880 [4:36:55<38:59,  1.40it/s]
1|22606|Loss: 0.8641359210014343:  87%|████████▋ | 22605/25880 [4:36:55<38:59,  1.40it/s]
1|22606|Loss: 0.8641359210014343:  87%|████████▋ | 22606/25880 [4:36:56<37:23,  1.46it/s]
1|22607|Loss: 0.7104372978210449:  87%|████████▋ | 22606/25880 [4:36:56<37:23,  1.46it/s]
1|22607|Loss: 0.7104372978210449:  87%|████████▋ | 22607/25880 [4:36:56<37:48,  1.44it/s]
1|22608|Loss: 0.8911806344985962:  87%|████████▋ | 22607/25880 [4:36:57<37:48,  1.44it/s]
1|22608|Loss: 0.8911806344985962:  87%|████████▋ | 22608/25880 [4:36:57<40:08,  1.36it/s]
1|22609|Loss: 0.8487591743469238:  87%|████████▋ | 22608/25880 [4:36:58<40:08,  1.36it/s]
1|22609|Loss: 0.8487591743469238:  87%|████████▋ | 22609/25880 [4:36:58<42:36,  1.28it/s]
1|22610|Loss: 0.7539413571357727:  87%|████████▋ | 22609/25880 [4:36:59<42:36,  1.28it/s]
1|22610|Loss: 0.7539413571357727:  87%|████████▋ | 22610/25880 [4:36:59<42:24,  1.29it/s]
1|22611|Loss: 0.8317365646362305:  87%|████████▋ | 22610/25880 [4:36:59<42:24,  1.29it/s]
1|22611|Loss: 0.8317365646362305:  87%|████████▋ | 22611/25880 [4:37:00<41:07,  1.32it/s]
1|22612|Loss: 0.7650837898254395:  87%|████████▋ | 22611/25880 [4:37:00<41:07,  1.32it/s]
1|22612|Loss: 0.7650837898254395:  87%|████████▋ | 22612/25880 [4:37:00<40:30,  1.34it/s]
1|22613|Loss: 0.8132962584495544:  87%|████████▋ | 22612/25880 [4:37:01<40:30,  1.34it/s]
1|22613|Loss: 0.8132962584495544:  87%|████████▋ | 22613/25880 [4:37:01<41:02,  1.33it/s]
1|22614|Loss: 0.8108140826225281:  87%|████████▋ | 22613/25880 [4:37:02<41:02,  1.33it/s]
1|22614|Loss: 0.8108140826225281:  87%|████████▋ | 22614/25880 [4:37:02<41:43,  1.30it/s]
1|22615|Loss: 0.7917490005493164:  87%|████████▋ | 22614/25880 [4:37:02<41:43,  1.30it/s]
1|22615|Loss: 0.7917490005493164:  87%|████████▋ | 22615/25880 [4:37:03<39:39,  1.37it/s]
1|22616|Loss: 0.916779100894928:  87%|████████▋ | 22615/25880 [4:37:03<39:39,  1.37it/s] 
1|22616|Loss: 0.916779100894928:  87%|████████▋ | 22616/25880 [4:37:03<39:12,  1.39it/s]
1|22617|Loss: 0.8380878567695618:  87%|████████▋ | 22616/25880 [4:37:04<39:12,  1.39it/s]
1|22617|Loss: 0.8380878567695618:  87%|████████▋ | 22617/25880 [4:37:04<41:01,  1.33it/s]
1|22618|Loss: 0.8318922519683838:  87%|████████▋ | 22617/25880 [4:37:05<41:01,  1.33it/s]
1|22618|Loss: 0.8318922519683838:  87%|████████▋ | 22618/25880 [4:37:05<40:43,  1.33it/s]
1|22619|Loss: 0.847198486328125:  87%|████████▋ | 22618/25880 [4:37:05<40:43,  1.33it/s] 
1|22619|Loss: 0.847198486328125:  87%|████████▋ | 22619/25880 [4:37:06<41:39,  1.30it/s]
1|22620|Loss: 0.6758647561073303:  87%|████████▋ | 22619/25880 [4:37:06<41:39,  1.30it/s]
1|22620|Loss: 0.6758647561073303:  87%|████████▋ | 22620/25880 [4:37:06<36:37,  1.48it/s]
1|22621|Loss: 0.7222643494606018:  87%|████████▋ | 22620/25880 [4:37:06<36:37,  1.48it/s]
1|22621|Loss: 0.7222643494606018:  87%|████████▋ | 22621/25880 [4:37:07<35:14,  1.54it/s]
1|22622|Loss: 0.8550338745117188:  87%|████████▋ | 22621/25880 [4:37:07<35:14,  1.54it/s]
1|22622|Loss: 0.8550338745117188:  87%|████████▋ | 22622/25880 [4:37:07<32:45,  1.66it/s]
1|22623|Loss: 0.994300127029419:  87%|████████▋ | 22622/25880 [4:37:08<32:45,  1.66it/s] 
1|22623|Loss: 0.994300127029419:  87%|████████▋ | 22623/25880 [4:37:08<33:26,  1.62it/s]
1|22624|Loss: 0.9239010810852051:  87%|████████▋ | 22623/25880 [4:37:08<33:26,  1.62it/s]
1|22624|Loss: 0.9239010810852051:  87%|████████▋ | 22624/25880 [4:37:09<35:17,  1.54it/s]
1|22625|Loss: 0.8569308519363403:  87%|████████▋ | 22624/25880 [4:37:09<35:17,  1.54it/s]
1|22625|Loss: 0.8569308519363403:  87%|████████▋ | 22625/25880 [4:37:09<37:25,  1.45it/s]
1|22626|Loss: 0.7339549660682678:  87%|████████▋ | 22625/25880 [4:37:10<37:25,  1.45it/s]
1|22626|Loss: 0.7339549660682678:  87%|████████▋ | 22626/25880 [4:37:10<38:30,  1.41it/s]
1|22627|Loss: 0.9226623773574829:  87%|████████▋ | 22626/25880 [4:37:10<38:30,  1.41it/s]
1|22627|Loss: 0.9226623773574829:  87%|████████▋ | 22627/25880 [4:37:11<37:20,  1.45it/s]
1|22628|Loss: 0.6947258114814758:  87%|████████▋ | 22627/25880 [4:37:11<37:20,  1.45it/s]
1|22628|Loss: 0.6947258114814758:  87%|████████▋ | 22628/25880 [4:37:12<38:53,  1.39it/s]
1|22629|Loss: 0.9105347394943237:  87%|████████▋ | 22628/25880 [4:37:12<38:53,  1.39it/s]
1|22629|Loss: 0.9105347394943237:  87%|████████▋ | 22629/25880 [4:37:12<37:32,  1.44it/s]
1|22630|Loss: 0.6564885973930359:  87%|████████▋ | 22629/25880 [4:37:13<37:32,  1.44it/s]
1|22630|Loss: 0.6564885973930359:  87%|████████▋ | 22630/25880 [4:37:13<38:28,  1.41it/s]
1|22631|Loss: 0.8051462173461914:  87%|████████▋ | 22630/25880 [4:37:13<38:28,  1.41it/s]
1|22631|Loss: 0.8051462173461914:  87%|████████▋ | 22631/25880 [4:37:14<39:04,  1.39it/s]
1|22632|Loss: 0.7400815486907959:  87%|████████▋ | 22631/25880 [4:37:14<39:04,  1.39it/s]
1|22632|Loss: 0.7400815486907959:  87%|████████▋ | 22632/25880 [4:37:14<39:17,  1.38it/s]
1|22633|Loss: 0.8816241025924683:  87%|████████▋ | 22632/25880 [4:37:15<39:17,  1.38it/s]
1|22633|Loss: 0.8816241025924683:  87%|████████▋ | 22633/25880 [4:37:15<39:59,  1.35it/s]
1|22634|Loss: 0.8341988325119019:  87%|████████▋ | 22633/25880 [4:37:16<39:59,  1.35it/s]
1|22634|Loss: 0.8341988325119019:  87%|████████▋ | 22634/25880 [4:37:16<40:02,  1.35it/s]
1|22635|Loss: 0.7834060192108154:  87%|████████▋ | 22634/25880 [4:37:16<40:02,  1.35it/s]
1|22635|Loss: 0.7834060192108154:  87%|████████▋ | 22635/25880 [4:37:17<41:22,  1.31it/s]
1|22636|Loss: 0.9909343719482422:  87%|████████▋ | 22635/25880 [4:37:17<41:22,  1.31it/s]
1|22636|Loss: 0.9909343719482422:  87%|████████▋ | 22636/25880 [4:37:17<37:43,  1.43it/s]
1|22637|Loss: 0.9487274885177612:  87%|████████▋ | 22636/25880 [4:37:18<37:43,  1.43it/s]
1|22637|Loss: 0.9487274885177612:  87%|████████▋ | 22637/25880 [4:37:18<35:18,  1.53it/s]
1|22638|Loss: 0.9015789031982422:  87%|████████▋ | 22637/25880 [4:37:18<35:18,  1.53it/s]
1|22638|Loss: 0.9015789031982422:  87%|████████▋ | 22638/25880 [4:37:19<36:59,  1.46it/s]
1|22639|Loss: 0.723406970500946:  87%|████████▋ | 22638/25880 [4:37:19<36:59,  1.46it/s] 
1|22639|Loss: 0.723406970500946:  87%|████████▋ | 22639/25880 [4:37:19<36:41,  1.47it/s]
1|22640|Loss: 0.9318267107009888:  87%|████████▋ | 22639/25880 [4:37:20<36:41,  1.47it/s]
1|22640|Loss: 0.9318267107009888:  87%|████████▋ | 22640/25880 [4:37:20<35:45,  1.51it/s]
1|22641|Loss: 0.7693709135055542:  87%|████████▋ | 22640/25880 [4:37:20<35:45,  1.51it/s]
1|22641|Loss: 0.7693709135055542:  87%|████████▋ | 22641/25880 [4:37:21<36:29,  1.48it/s]
1|22642|Loss: 0.8838560581207275:  87%|████████▋ | 22641/25880 [4:37:21<36:29,  1.48it/s]
1|22642|Loss: 0.8838560581207275:  87%|████████▋ | 22642/25880 [4:37:21<39:13,  1.38it/s]
1|22643|Loss: 0.722959578037262:  87%|████████▋ | 22642/25880 [4:37:22<39:13,  1.38it/s] 
1|22643|Loss: 0.722959578037262:  87%|████████▋ | 22643/25880 [4:37:22<43:17,  1.25it/s]
1|22644|Loss: 0.7835156321525574:  87%|████████▋ | 22643/25880 [4:37:23<43:17,  1.25it/s]
1|22644|Loss: 0.7835156321525574:  87%|████████▋ | 22644/25880 [4:37:23<42:00,  1.28it/s]
1|22645|Loss: 0.8273797631263733:  87%|████████▋ | 22644/25880 [4:37:24<42:00,  1.28it/s]
1|22645|Loss: 0.8273797631263733:  88%|████████▊ | 22645/25880 [4:37:24<41:45,  1.29it/s]
1|22646|Loss: 0.8006581664085388:  88%|████████▊ | 22645/25880 [4:37:24<41:45,  1.29it/s]
1|22646|Loss: 0.8006581664085388:  88%|████████▊ | 22646/25880 [4:37:25<40:05,  1.34it/s]
1|22647|Loss: 0.8588104844093323:  88%|████████▊ | 22646/25880 [4:37:25<40:05,  1.34it/s]
1|22647|Loss: 0.8588104844093323:  88%|████████▊ | 22647/25880 [4:37:25<39:35,  1.36it/s]
1|22648|Loss: 0.7283156514167786:  88%|████████▊ | 22647/25880 [4:37:26<39:35,  1.36it/s]
1|22648|Loss: 0.7283156514167786:  88%|████████▊ | 22648/25880 [4:37:26<37:40,  1.43it/s]
1|22649|Loss: 0.7997267842292786:  88%|████████▊ | 22648/25880 [4:37:26<37:40,  1.43it/s]
1|22649|Loss: 0.7997267842292786:  88%|████████▊ | 22649/25880 [4:37:27<36:32,  1.47it/s]
1|22650|Loss: 0.8458157181739807:  88%|████████▊ | 22649/25880 [4:37:27<36:32,  1.47it/s]
1|22650|Loss: 0.8458157181739807:  88%|████████▊ | 22650/25880 [4:37:27<37:48,  1.42it/s]
1|22651|Loss: 0.8729555606842041:  88%|████████▊ | 22650/25880 [4:37:28<37:48,  1.42it/s]
1|22651|Loss: 0.8729555606842041:  88%|████████▊ | 22651/25880 [4:37:28<38:39,  1.39it/s]
1|22652|Loss: 0.8093107342720032:  88%|████████▊ | 22651/25880 [4:37:28<38:39,  1.39it/s]
1|22652|Loss: 0.8093107342720032:  88%|████████▊ | 22652/25880 [4:37:29<39:06,  1.38it/s]
1|22653|Loss: 0.8232734799385071:  88%|████████▊ | 22652/25880 [4:37:29<39:06,  1.38it/s]
1|22653|Loss: 0.8232734799385071:  88%|████████▊ | 22653/25880 [4:37:30<39:02,  1.38it/s]
1|22654|Loss: 0.7882195115089417:  88%|████████▊ | 22653/25880 [4:37:30<39:02,  1.38it/s]
1|22654|Loss: 0.7882195115089417:  88%|████████▊ | 22654/25880 [4:37:30<38:57,  1.38it/s]
1|22655|Loss: 0.782200276851654:  88%|████████▊ | 22654/25880 [4:37:31<38:57,  1.38it/s] 
1|22655|Loss: 0.782200276851654:  88%|████████▊ | 22655/25880 [4:37:31<38:37,  1.39it/s]
1|22656|Loss: 0.9147604703903198:  88%|████████▊ | 22655/25880 [4:37:31<38:37,  1.39it/s]
1|22656|Loss: 0.9147604703903198:  88%|████████▊ | 22656/25880 [4:37:32<38:44,  1.39it/s]
1|22657|Loss: 0.8509906530380249:  88%|████████▊ | 22656/25880 [4:37:32<38:44,  1.39it/s]
1|22657|Loss: 0.8509906530380249:  88%|████████▊ | 22657/25880 [4:37:32<39:32,  1.36it/s]
1|22658|Loss: 0.7028499245643616:  88%|████████▊ | 22657/25880 [4:37:33<39:32,  1.36it/s]
1|22658|Loss: 0.7028499245643616:  88%|████████▊ | 22658/25880 [4:37:33<36:04,  1.49it/s]
1|22659|Loss: 0.7425702214241028:  88%|████████▊ | 22658/25880 [4:37:33<36:04,  1.49it/s]
1|22659|Loss: 0.7425702214241028:  88%|████████▊ | 22659/25880 [4:37:34<35:43,  1.50it/s]
1|22660|Loss: 0.8277237415313721:  88%|████████▊ | 22659/25880 [4:37:34<35:43,  1.50it/s]
1|22660|Loss: 0.8277237415313721:  88%|████████▊ | 22660/25880 [4:37:34<35:16,  1.52it/s]
1|22661|Loss: 0.8319429755210876:  88%|████████▊ | 22660/25880 [4:37:35<35:16,  1.52it/s]
1|22661|Loss: 0.8319429755210876:  88%|████████▊ | 22661/25880 [4:37:35<36:17,  1.48it/s]
1|22662|Loss: 0.8781201839447021:  88%|████████▊ | 22661/25880 [4:37:35<36:17,  1.48it/s]
1|22662|Loss: 0.8781201839447021:  88%|████████▊ | 22662/25880 [4:37:36<37:17,  1.44it/s]
1|22663|Loss: 0.7805619239807129:  88%|████████▊ | 22662/25880 [4:37:36<37:17,  1.44it/s]
1|22663|Loss: 0.7805619239807129:  88%|████████▊ | 22663/25880 [4:37:36<37:47,  1.42it/s]
1|22664|Loss: 0.8988534808158875:  88%|████████▊ | 22663/25880 [4:37:37<37:47,  1.42it/s]
1|22664|Loss: 0.8988534808158875:  88%|████████▊ | 22664/25880 [4:37:37<39:06,  1.37it/s]
1|22665|Loss: 0.8894122838973999:  88%|████████▊ | 22664/25880 [4:37:38<39:06,  1.37it/s]
1|22665|Loss: 0.8894122838973999:  88%|████████▊ | 22665/25880 [4:37:38<37:18,  1.44it/s]
1|22666|Loss: 0.7909582853317261:  88%|████████▊ | 22665/25880 [4:37:38<37:18,  1.44it/s]
1|22666|Loss: 0.7909582853317261:  88%|████████▊ | 22666/25880 [4:37:38<34:30,  1.55it/s]
1|22667|Loss: 0.8514965176582336:  88%|████████▊ | 22666/25880 [4:37:39<34:30,  1.55it/s]
1|22667|Loss: 0.8514965176582336:  88%|████████▊ | 22667/25880 [4:37:39<37:42,  1.42it/s]
1|22668|Loss: 0.6298400163650513:  88%|████████▊ | 22667/25880 [4:37:40<37:42,  1.42it/s]
1|22668|Loss: 0.6298400163650513:  88%|████████▊ | 22668/25880 [4:37:40<38:54,  1.38it/s]
1|22669|Loss: 0.8364725708961487:  88%|████████▊ | 22668/25880 [4:37:40<38:54,  1.38it/s]
1|22669|Loss: 0.8364725708961487:  88%|████████▊ | 22669/25880 [4:37:41<37:40,  1.42it/s]
1|22670|Loss: 0.783014178276062:  88%|████████▊ | 22669/25880 [4:37:41<37:40,  1.42it/s] 
1|22670|Loss: 0.783014178276062:  88%|████████▊ | 22670/25880 [4:37:41<38:38,  1.38it/s]
1|22671|Loss: 0.8640918731689453:  88%|████████▊ | 22670/25880 [4:37:42<38:38,  1.38it/s]
1|22671|Loss: 0.8640918731689453:  88%|████████▊ | 22671/25880 [4:37:42<38:55,  1.37it/s]
1|22672|Loss: 0.7201790809631348:  88%|████████▊ | 22671/25880 [4:37:43<38:55,  1.37it/s]
1|22672|Loss: 0.7201790809631348:  88%|████████▊ | 22672/25880 [4:37:43<38:38,  1.38it/s]
1|22673|Loss: 0.7907966375350952:  88%|████████▊ | 22672/25880 [4:37:43<38:38,  1.38it/s]
1|22673|Loss: 0.7907966375350952:  88%|████████▊ | 22673/25880 [4:37:44<38:39,  1.38it/s]
1|22674|Loss: 0.9113014340400696:  88%|████████▊ | 22673/25880 [4:37:44<38:39,  1.38it/s]
1|22674|Loss: 0.9113014340400696:  88%|████████▊ | 22674/25880 [4:37:44<39:37,  1.35it/s]
1|22675|Loss: 1.0719681978225708:  88%|████████▊ | 22674/25880 [4:37:45<39:37,  1.35it/s]
1|22675|Loss: 1.0719681978225708:  88%|████████▊ | 22675/25880 [4:37:45<40:39,  1.31it/s]
1|22676|Loss: 0.9696115255355835:  88%|████████▊ | 22675/25880 [4:37:46<40:39,  1.31it/s]
1|22676|Loss: 0.9696115255355835:  88%|████████▊ | 22676/25880 [4:37:46<35:47,  1.49it/s]
1|22677|Loss: 0.7649901509284973:  88%|████████▊ | 22676/25880 [4:37:46<35:47,  1.49it/s]
1|22677|Loss: 0.7649901509284973:  88%|████████▊ | 22677/25880 [4:37:46<35:42,  1.50it/s]
1|22678|Loss: 0.8893927335739136:  88%|████████▊ | 22677/25880 [4:37:47<35:42,  1.50it/s]
1|22678|Loss: 0.8893927335739136:  88%|████████▊ | 22678/25880 [4:37:47<35:00,  1.52it/s]
1|22679|Loss: 0.9224072098731995:  88%|████████▊ | 22678/25880 [4:37:47<35:00,  1.52it/s]
1|22679|Loss: 0.9224072098731995:  88%|████████▊ | 22679/25880 [4:37:48<36:57,  1.44it/s]
1|22680|Loss: 0.8351150155067444:  88%|████████▊ | 22679/25880 [4:37:48<36:57,  1.44it/s]
1|22680|Loss: 0.8351150155067444:  88%|████████▊ | 22680/25880 [4:37:48<37:29,  1.42it/s]
1|22681|Loss: 0.8746922612190247:  88%|████████▊ | 22680/25880 [4:37:49<37:29,  1.42it/s]
1|22681|Loss: 0.8746922612190247:  88%|████████▊ | 22681/25880 [4:37:49<34:15,  1.56it/s]
1|22682|Loss: 0.6743466854095459:  88%|████████▊ | 22681/25880 [4:37:49<34:15,  1.56it/s]
1|22682|Loss: 0.6743466854095459:  88%|████████▊ | 22682/25880 [4:37:50<34:47,  1.53it/s]
1|22683|Loss: 0.8403540849685669:  88%|████████▊ | 22682/25880 [4:37:50<34:47,  1.53it/s]
1|22683|Loss: 0.8403540849685669:  88%|████████▊ | 22683/25880 [4:37:50<34:15,  1.56it/s]
1|22684|Loss: 0.9202895760536194:  88%|████████▊ | 22683/25880 [4:37:51<34:15,  1.56it/s]
1|22684|Loss: 0.9202895760536194:  88%|████████▊ | 22684/25880 [4:37:51<34:47,  1.53it/s]
1|22685|Loss: 0.7272464632987976:  88%|████████▊ | 22684/25880 [4:37:51<34:47,  1.53it/s]
1|22685|Loss: 0.7272464632987976:  88%|████████▊ | 22685/25880 [4:37:52<36:39,  1.45it/s]
1|22686|Loss: 0.8772094249725342:  88%|████████▊ | 22685/25880 [4:37:52<36:39,  1.45it/s]
1|22686|Loss: 0.8772094249725342:  88%|████████▊ | 22686/25880 [4:37:52<37:33,  1.42it/s]
1|22687|Loss: 0.7149688005447388:  88%|████████▊ | 22686/25880 [4:37:53<37:33,  1.42it/s]
1|22687|Loss: 0.7149688005447388:  88%|████████▊ | 22687/25880 [4:37:53<39:16,  1.35it/s]
1|22688|Loss: 0.7074151635169983:  88%|████████▊ | 22687/25880 [4:37:54<39:16,  1.35it/s]
1|22688|Loss: 0.7074151635169983:  88%|████████▊ | 22688/25880 [4:37:54<39:21,  1.35it/s]
1|22689|Loss: 0.9379199743270874:  88%|████████▊ | 22688/25880 [4:37:54<39:21,  1.35it/s]
1|22689|Loss: 0.9379199743270874:  88%|████████▊ | 22689/25880 [4:37:55<39:24,  1.35it/s]
1|22690|Loss: 0.867400050163269:  88%|████████▊ | 22689/25880 [4:37:55<39:24,  1.35it/s] 
1|22690|Loss: 0.867400050163269:  88%|████████▊ | 22690/25880 [4:37:55<36:37,  1.45it/s]
1|22691|Loss: 0.792938768863678:  88%|████████▊ | 22690/25880 [4:37:56<36:37,  1.45it/s]
1|22691|Loss: 0.792938768863678:  88%|████████▊ | 22691/25880 [4:37:56<34:42,  1.53it/s]
1|22692|Loss: 0.9546634554862976:  88%|████████▊ | 22691/25880 [4:37:56<34:42,  1.53it/s]
1|22692|Loss: 0.9546634554862976:  88%|████████▊ | 22692/25880 [4:37:56<33:28,  1.59it/s]
1|22693|Loss: 0.8092323541641235:  88%|████████▊ | 22692/25880 [4:37:57<33:28,  1.59it/s]
1|22693|Loss: 0.8092323541641235:  88%|████████▊ | 22693/25880 [4:37:57<35:30,  1.50it/s]
1|22694|Loss: 0.8153899312019348:  88%|████████▊ | 22693/25880 [4:37:58<35:30,  1.50it/s]
1|22694|Loss: 0.8153899312019348:  88%|████████▊ | 22694/25880 [4:37:58<36:52,  1.44it/s]
1|22695|Loss: 0.695814311504364:  88%|████████▊ | 22694/25880 [4:37:58<36:52,  1.44it/s] 
1|22695|Loss: 0.695814311504364:  88%|████████▊ | 22695/25880 [4:37:59<36:28,  1.46it/s]
1|22696|Loss: 0.904369592666626:  88%|████████▊ | 22695/25880 [4:37:59<36:28,  1.46it/s]
1|22696|Loss: 0.904369592666626:  88%|████████▊ | 22696/25880 [4:37:59<36:56,  1.44it/s]
1|22697|Loss: 0.7408686876296997:  88%|████████▊ | 22696/25880 [4:38:00<36:56,  1.44it/s]
1|22697|Loss: 0.7408686876296997:  88%|████████▊ | 22697/25880 [4:38:00<39:08,  1.36it/s]
1|22698|Loss: 0.9328234195709229:  88%|████████▊ | 22697/25880 [4:38:01<39:08,  1.36it/s]
1|22698|Loss: 0.9328234195709229:  88%|████████▊ | 22698/25880 [4:38:01<39:07,  1.36it/s]
1|22699|Loss: 0.8161859512329102:  88%|████████▊ | 22698/25880 [4:38:01<39:07,  1.36it/s]
1|22699|Loss: 0.8161859512329102:  88%|████████▊ | 22699/25880 [4:38:02<40:11,  1.32it/s]
1|22700|Loss: 0.8542875647544861:  88%|████████▊ | 22699/25880 [4:38:02<40:11,  1.32it/s]
1|22700|Loss: 0.8542875647544861:  88%|████████▊ | 22700/25880 [4:38:02<37:11,  1.43it/s]
1|22701|Loss: 1.0849236249923706:  88%|████████▊ | 22700/25880 [4:38:03<37:11,  1.43it/s]
1|22701|Loss: 1.0849236249923706:  88%|████████▊ | 22701/25880 [4:38:03<36:52,  1.44it/s]
1|22702|Loss: 0.7212731242179871:  88%|████████▊ | 22701/25880 [4:38:03<36:52,  1.44it/s]
1|22702|Loss: 0.7212731242179871:  88%|████████▊ | 22702/25880 [4:38:04<39:03,  1.36it/s]
1|22703|Loss: 0.7507745027542114:  88%|████████▊ | 22702/25880 [4:38:04<39:03,  1.36it/s]
1|22703|Loss: 0.7507745027542114:  88%|████████▊ | 22703/25880 [4:38:05<38:17,  1.38it/s]
1|22704|Loss: 0.7022393345832825:  88%|████████▊ | 22703/25880 [4:38:05<38:17,  1.38it/s]
1|22704|Loss: 0.7022393345832825:  88%|████████▊ | 22704/25880 [4:38:05<35:17,  1.50it/s]
1|22705|Loss: 0.8024474382400513:  88%|████████▊ | 22704/25880 [4:38:05<35:17,  1.50it/s]
1|22705|Loss: 0.8024474382400513:  88%|████████▊ | 22705/25880 [4:38:06<34:12,  1.55it/s]
1|22706|Loss: 0.755150318145752:  88%|████████▊ | 22705/25880 [4:38:06<34:12,  1.55it/s] 
1|22706|Loss: 0.755150318145752:  88%|████████▊ | 22706/25880 [4:38:06<35:15,  1.50it/s]
1|22707|Loss: 0.8076541423797607:  88%|████████▊ | 22706/25880 [4:38:07<35:15,  1.50it/s]
1|22707|Loss: 0.8076541423797607:  88%|████████▊ | 22707/25880 [4:38:07<38:05,  1.39it/s]
1|22708|Loss: 0.8009790778160095:  88%|████████▊ | 22707/25880 [4:38:08<38:05,  1.39it/s]
1|22708|Loss: 0.8009790778160095:  88%|████████▊ | 22708/25880 [4:38:08<34:29,  1.53it/s]
1|22709|Loss: 0.9383726716041565:  88%|████████▊ | 22708/25880 [4:38:08<34:29,  1.53it/s]
1|22709|Loss: 0.9383726716041565:  88%|████████▊ | 22709/25880 [4:38:08<33:23,  1.58it/s]
1|22710|Loss: 0.7349063158035278:  88%|████████▊ | 22709/25880 [4:38:09<33:23,  1.58it/s]
1|22710|Loss: 0.7349063158035278:  88%|████████▊ | 22710/25880 [4:38:09<32:04,  1.65it/s]
1|22711|Loss: 0.8606752753257751:  88%|████████▊ | 22710/25880 [4:38:09<32:04,  1.65it/s]
1|22711|Loss: 0.8606752753257751:  88%|████████▊ | 22711/25880 [4:38:10<33:28,  1.58it/s]
1|22712|Loss: 0.7705845832824707:  88%|████████▊ | 22711/25880 [4:38:10<33:28,  1.58it/s]
1|22712|Loss: 0.7705845832824707:  88%|████████▊ | 22712/25880 [4:38:10<34:40,  1.52it/s]
1|22713|Loss: 0.8350929617881775:  88%|████████▊ | 22712/25880 [4:38:11<34:40,  1.52it/s]
1|22713|Loss: 0.8350929617881775:  88%|████████▊ | 22713/25880 [4:38:11<36:26,  1.45it/s]
1|22714|Loss: 0.8498695492744446:  88%|████████▊ | 22713/25880 [4:38:11<36:26,  1.45it/s]
1|22714|Loss: 0.8498695492744446:  88%|████████▊ | 22714/25880 [4:38:12<38:11,  1.38it/s]
1|22715|Loss: 0.7250550389289856:  88%|████████▊ | 22714/25880 [4:38:12<38:11,  1.38it/s]
1|22715|Loss: 0.7250550389289856:  88%|████████▊ | 22715/25880 [4:38:13<41:25,  1.27it/s]
1|22716|Loss: 0.7138874530792236:  88%|████████▊ | 22715/25880 [4:38:13<41:25,  1.27it/s]
1|22716|Loss: 0.7138874530792236:  88%|████████▊ | 22716/25880 [4:38:14<41:12,  1.28it/s]
1|22717|Loss: 0.7991625666618347:  88%|████████▊ | 22716/25880 [4:38:14<41:12,  1.28it/s]
1|22717|Loss: 0.7991625666618347:  88%|████████▊ | 22717/25880 [4:38:14<40:40,  1.30it/s]
1|22718|Loss: 0.7591516375541687:  88%|████████▊ | 22717/25880 [4:38:15<40:40,  1.30it/s]
1|22718|Loss: 0.7591516375541687:  88%|████████▊ | 22718/25880 [4:38:15<41:04,  1.28it/s]
1|22719|Loss: 0.9744252562522888:  88%|████████▊ | 22718/25880 [4:38:15<41:04,  1.28it/s]
1|22719|Loss: 0.9744252562522888:  88%|████████▊ | 22719/25880 [4:38:16<39:05,  1.35it/s]
1|22720|Loss: 0.8176939487457275:  88%|████████▊ | 22719/25880 [4:38:16<39:05,  1.35it/s]
1|22720|Loss: 0.8176939487457275:  88%|████████▊ | 22720/25880 [4:38:16<37:20,  1.41it/s]
1|22721|Loss: 0.9668351411819458:  88%|████████▊ | 22720/25880 [4:38:17<37:20,  1.41it/s]
1|22721|Loss: 0.9668351411819458:  88%|████████▊ | 22721/25880 [4:38:17<36:59,  1.42it/s]
1|22722|Loss: 0.8621824383735657:  88%|████████▊ | 22721/25880 [4:38:17<36:59,  1.42it/s]
1|22722|Loss: 0.8621824383735657:  88%|████████▊ | 22722/25880 [4:38:18<38:31,  1.37it/s]
1|22723|Loss: 0.7320384979248047:  88%|████████▊ | 22722/25880 [4:38:18<38:31,  1.37it/s]
1|22723|Loss: 0.7320384979248047:  88%|████████▊ | 22723/25880 [4:38:18<37:24,  1.41it/s]
1|22724|Loss: 0.8892062306404114:  88%|████████▊ | 22723/25880 [4:38:19<37:24,  1.41it/s]
1|22724|Loss: 0.8892062306404114:  88%|████████▊ | 22724/25880 [4:38:19<32:51,  1.60it/s]
1|22725|Loss: 0.7009802460670471:  88%|████████▊ | 22724/25880 [4:38:19<32:51,  1.60it/s]
1|22725|Loss: 0.7009802460670471:  88%|████████▊ | 22725/25880 [4:38:20<33:23,  1.57it/s]
1|22726|Loss: 0.9041344523429871:  88%|████████▊ | 22725/25880 [4:38:20<33:23,  1.57it/s]
1|22726|Loss: 0.9041344523429871:  88%|████████▊ | 22726/25880 [4:38:20<33:44,  1.56it/s]
1|22727|Loss: 0.6887652277946472:  88%|████████▊ | 22726/25880 [4:38:21<33:44,  1.56it/s]
1|22727|Loss: 0.6887652277946472:  88%|████████▊ | 22727/25880 [4:38:21<32:58,  1.59it/s]
1|22728|Loss: 0.8027492165565491:  88%|████████▊ | 22727/25880 [4:38:21<32:58,  1.59it/s]
1|22728|Loss: 0.8027492165565491:  88%|████████▊ | 22728/25880 [4:38:21<32:39,  1.61it/s]
1|22729|Loss: 1.005273699760437:  88%|████████▊ | 22728/25880 [4:38:22<32:39,  1.61it/s] 
1|22729|Loss: 1.005273699760437:  88%|████████▊ | 22729/25880 [4:38:22<34:02,  1.54it/s]
1|22730|Loss: 0.7377908229827881:  88%|████████▊ | 22729/25880 [4:38:22<34:02,  1.54it/s]
1|22730|Loss: 0.7377908229827881:  88%|████████▊ | 22730/25880 [4:38:23<31:43,  1.65it/s]
1|22731|Loss: 0.8226351141929626:  88%|████████▊ | 22730/25880 [4:38:23<31:43,  1.65it/s]
1|22731|Loss: 0.8226351141929626:  88%|████████▊ | 22731/25880 [4:38:23<29:58,  1.75it/s]
1|22732|Loss: 0.8900094032287598:  88%|████████▊ | 22731/25880 [4:38:24<29:58,  1.75it/s]
1|22732|Loss: 0.8900094032287598:  88%|████████▊ | 22732/25880 [4:38:24<32:56,  1.59it/s]
1|22733|Loss: 0.8555960059165955:  88%|████████▊ | 22732/25880 [4:38:24<32:56,  1.59it/s]
1|22733|Loss: 0.8555960059165955:  88%|████████▊ | 22733/25880 [4:38:25<33:43,  1.55it/s]
1|22734|Loss: 0.9134399890899658:  88%|████████▊ | 22733/25880 [4:38:25<33:43,  1.55it/s]
1|22734|Loss: 0.9134399890899658:  88%|████████▊ | 22734/25880 [4:38:25<34:49,  1.51it/s]
1|22735|Loss: 0.814673662185669:  88%|████████▊ | 22734/25880 [4:38:26<34:49,  1.51it/s] 
1|22735|Loss: 0.814673662185669:  88%|████████▊ | 22735/25880 [4:38:26<37:25,  1.40it/s]
1|22736|Loss: 0.9834950566291809:  88%|████████▊ | 22735/25880 [4:38:27<37:25,  1.40it/s]
1|22736|Loss: 0.9834950566291809:  88%|████████▊ | 22736/25880 [4:38:27<37:04,  1.41it/s]
1|22737|Loss: 0.8629280924797058:  88%|████████▊ | 22736/25880 [4:38:27<37:04,  1.41it/s]
1|22737|Loss: 0.8629280924797058:  88%|████████▊ | 22737/25880 [4:38:28<37:22,  1.40it/s]
1|22738|Loss: 0.6799736022949219:  88%|████████▊ | 22737/25880 [4:38:28<37:22,  1.40it/s]
1|22738|Loss: 0.6799736022949219:  88%|████████▊ | 22738/25880 [4:38:28<37:18,  1.40it/s]
1|22739|Loss: 0.8931583762168884:  88%|████████▊ | 22738/25880 [4:38:29<37:18,  1.40it/s]
1|22739|Loss: 0.8931583762168884:  88%|████████▊ | 22739/25880 [4:38:29<38:11,  1.37it/s]
1|22740|Loss: 0.898543655872345:  88%|████████▊ | 22739/25880 [4:38:29<38:11,  1.37it/s] 
1|22740|Loss: 0.898543655872345:  88%|████████▊ | 22740/25880 [4:38:30<38:30,  1.36it/s]
1|22741|Loss: 0.8342398405075073:  88%|████████▊ | 22740/25880 [4:38:30<38:30,  1.36it/s]
1|22741|Loss: 0.8342398405075073:  88%|████████▊ | 22741/25880 [4:38:30<37:07,  1.41it/s]
1|22742|Loss: 0.9937700033187866:  88%|████████▊ | 22741/25880 [4:38:31<37:07,  1.41it/s]
1|22742|Loss: 0.9937700033187866:  88%|████████▊ | 22742/25880 [4:38:31<37:56,  1.38it/s]
1|22743|Loss: 0.8491514325141907:  88%|████████▊ | 22742/25880 [4:38:32<37:56,  1.38it/s]
1|22743|Loss: 0.8491514325141907:  88%|████████▊ | 22743/25880 [4:38:32<38:14,  1.37it/s]
1|22744|Loss: 0.8599726557731628:  88%|████████▊ | 22743/25880 [4:38:32<38:14,  1.37it/s]
1|22744|Loss: 0.8599726557731628:  88%|████████▊ | 22744/25880 [4:38:33<37:51,  1.38it/s]
1|22745|Loss: 0.7792835235595703:  88%|████████▊ | 22744/25880 [4:38:33<37:51,  1.38it/s]
1|22745|Loss: 0.7792835235595703:  88%|████████▊ | 22745/25880 [4:38:33<38:02,  1.37it/s]
1|22746|Loss: 0.7588068246841431:  88%|████████▊ | 22745/25880 [4:38:34<38:02,  1.37it/s]
1|22746|Loss: 0.7588068246841431:  88%|████████▊ | 22746/25880 [4:38:34<38:25,  1.36it/s]
1|22747|Loss: 0.8863852620124817:  88%|████████▊ | 22746/25880 [4:38:35<38:25,  1.36it/s]
1|22747|Loss: 0.8863852620124817:  88%|████████▊ | 22747/25880 [4:38:35<38:32,  1.35it/s]
1|22748|Loss: 0.8837676048278809:  88%|████████▊ | 22747/25880 [4:38:35<38:32,  1.35it/s]
1|22748|Loss: 0.8837676048278809:  88%|████████▊ | 22748/25880 [4:38:36<38:00,  1.37it/s]
1|22749|Loss: 0.9037300944328308:  88%|████████▊ | 22748/25880 [4:38:36<38:00,  1.37it/s]
1|22749|Loss: 0.9037300944328308:  88%|████████▊ | 22749/25880 [4:38:36<35:07,  1.49it/s]
1|22750|Loss: 0.8755318522453308:  88%|████████▊ | 22749/25880 [4:38:36<35:07,  1.49it/s]
1|22750|Loss: 0.8755318522453308:  88%|████████▊ | 22750/25880 [4:38:37<34:57,  1.49it/s]
1|22751|Loss: 0.7826274633407593:  88%|████████▊ | 22750/25880 [4:38:37<34:57,  1.49it/s]
1|22751|Loss: 0.7826274633407593:  88%|████████▊ | 22751/25880 [4:38:38<36:31,  1.43it/s]
1|22752|Loss: 0.8199136853218079:  88%|████████▊ | 22751/25880 [4:38:38<36:31,  1.43it/s]
1|22752|Loss: 0.8199136853218079:  88%|████████▊ | 22752/25880 [4:38:38<37:14,  1.40it/s]
1|22753|Loss: 0.8144955039024353:  88%|████████▊ | 22752/25880 [4:38:39<37:14,  1.40it/s]
1|22753|Loss: 0.8144955039024353:  88%|████████▊ | 22753/25880 [4:38:39<37:07,  1.40it/s]
1|22754|Loss: 0.8691534996032715:  88%|████████▊ | 22753/25880 [4:38:39<37:07,  1.40it/s]
1|22754|Loss: 0.8691534996032715:  88%|█████���██▊ | 22754/25880 [4:38:40<35:26,  1.47it/s]
1|22755|Loss: 0.8162107467651367:  88%|████████▊ | 22754/25880 [4:38:40<35:26,  1.47it/s]
1|22755|Loss: 0.8162107467651367:  88%|████████▊ | 22755/25880 [4:38:40<35:49,  1.45it/s]
1|22756|Loss: 0.9057316184043884:  88%|████████▊ | 22755/25880 [4:38:41<35:49,  1.45it/s]
1|22756|Loss: 0.9057316184043884:  88%|████████▊ | 22756/25880 [4:38:41<36:38,  1.42it/s]
1|22757|Loss: 0.8554835319519043:  88%|████████▊ | 22756/25880 [4:38:41<36:38,  1.42it/s]
1|22757|Loss: 0.8554835319519043:  88%|████████▊ | 22757/25880 [4:38:42<37:04,  1.40it/s]
1|22758|Loss: 0.8067473769187927:  88%|████████▊ | 22757/25880 [4:38:42<37:04,  1.40it/s]
1|22758|Loss: 0.8067473769187927:  88%|████████▊ | 22758/25880 [4:38:42<34:34,  1.51it/s]
1|22759|Loss: 0.7982097864151001:  88%|████████▊ | 22758/25880 [4:38:43<34:34,  1.51it/s]
1|22759|Loss: 0.7982097864151001:  88%|████████▊ | 22759/25880 [4:38:43<34:39,  1.50it/s]
1|22760|Loss: 0.7506498098373413:  88%|████████▊ | 22759/25880 [4:38:43<34:39,  1.50it/s]
1|22760|Loss: 0.7506498098373413:  88%|████████▊ | 22760/25880 [4:38:44<36:24,  1.43it/s]
1|22761|Loss: 0.7986324429512024:  88%|████████▊ | 22760/25880 [4:38:44<36:24,  1.43it/s]
1|22761|Loss: 0.7986324429512024:  88%|████████▊ | 22761/25880 [4:38:44<34:29,  1.51it/s]
1|22762|Loss: 0.8488718867301941:  88%|████████▊ | 22761/25880 [4:38:45<34:29,  1.51it/s]
1|22762|Loss: 0.8488718867301941:  88%|████████▊ | 22762/25880 [4:38:45<34:27,  1.51it/s]
1|22763|Loss: 0.877530574798584:  88%|████████▊ | 22762/25880 [4:38:45<34:27,  1.51it/s] 
1|22763|Loss: 0.877530574798584:  88%|████████▊ | 22763/25880 [4:38:46<33:36,  1.55it/s]
1|22764|Loss: 0.788975715637207:  88%|████████▊ | 22763/25880 [4:38:46<33:36,  1.55it/s]
1|22764|Loss: 0.788975715637207:  88%|████████▊ | 22764/25880 [4:38:46<33:01,  1.57it/s]
1|22765|Loss: 1.0860559940338135:  88%|████████▊ | 22764/25880 [4:38:47<33:01,  1.57it/s]
1|22765|Loss: 1.0860559940338135:  88%|████████▊ | 22765/25880 [4:38:47<32:18,  1.61it/s]
1|22766|Loss: 0.810143232345581:  88%|████████▊ | 22765/25880 [4:38:47<32:18,  1.61it/s] 
1|22766|Loss: 0.810143232345581:  88%|████████▊ | 22766/25880 [4:38:48<34:39,  1.50it/s]
1|22767|Loss: 0.8013209104537964:  88%|████████▊ | 22766/25880 [4:38:48<34:39,  1.50it/s]
1|22767|Loss: 0.8013209104537964:  88%|████████▊ | 22767/25880 [4:38:48<35:29,  1.46it/s]
1|22768|Loss: 0.9164397716522217:  88%|████████▊ | 22767/25880 [4:38:49<35:29,  1.46it/s]
1|22768|Loss: 0.9164397716522217:  88%|████████▊ | 22768/25880 [4:38:49<36:48,  1.41it/s]
1|22769|Loss: 0.8722606301307678:  88%|████████▊ | 22768/25880 [4:38:49<36:48,  1.41it/s]
1|22769|Loss: 0.8722606301307678:  88%|████████▊ | 22769/25880 [4:38:50<36:15,  1.43it/s]
1|22770|Loss: 0.8016287684440613:  88%|████████▊ | 22769/25880 [4:38:50<36:15,  1.43it/s]
1|22770|Loss: 0.8016287684440613:  88%|████████▊ | 22770/25880 [4:38:50<35:17,  1.47it/s]
1|22771|Loss: 0.8851531744003296:  88%|████████▊ | 22770/25880 [4:38:51<35:17,  1.47it/s]
1|22771|Loss: 0.8851531744003296:  88%|████████▊ | 22771/25880 [4:38:51<35:50,  1.45it/s]
1|22772|Loss: 0.751487135887146:  88%|████████▊ | 22771/25880 [4:38:52<35:50,  1.45it/s] 
1|22772|Loss: 0.751487135887146:  88%|████████▊ | 22772/25880 [4:38:52<35:04,  1.48it/s]
1|22773|Loss: 0.7327362298965454:  88%|████████▊ | 22772/25880 [4:38:52<35:04,  1.48it/s]
1|22773|Loss: 0.7327362298965454:  88%|████████▊ | 22773/25880 [4:38:53<38:41,  1.34it/s]
1|22774|Loss: 0.82233726978302:  88%|████████▊ | 22773/25880 [4:38:53<38:41,  1.34it/s]  
1|22774|Loss: 0.82233726978302:  88%|████████▊ | 22774/25880 [4:38:53<39:00,  1.33it/s]
1|22775|Loss: 0.7872240543365479:  88%|████████▊ | 22774/25880 [4:38:54<39:00,  1.33it/s]
1|22775|Loss: 0.7872240543365479:  88%|████████▊ | 22775/25880 [4:38:54<38:38,  1.34it/s]
1|22776|Loss: 0.6274856328964233:  88%|████████▊ | 22775/25880 [4:38:55<38:38,  1.34it/s]
1|22776|Loss: 0.6274856328964233:  88%|████████▊ | 22776/25880 [4:38:55<39:54,  1.30it/s]
1|22777|Loss: 0.7843847870826721:  88%|████████▊ | 22776/25880 [4:38:55<39:54,  1.30it/s]
1|22777|Loss: 0.7843847870826721:  88%|████████▊ | 22777/25880 [4:38:56<41:20,  1.25it/s]
1|22778|Loss: 0.8221994638442993:  88%|████████▊ | 22777/25880 [4:38:56<41:20,  1.25it/s]
1|22778|Loss: 0.8221994638442993:  88%|████████▊ | 22778/25880 [4:38:57<41:26,  1.25it/s]
1|22779|Loss: 0.6117965579032898:  88%|████████▊ | 22778/25880 [4:38:57<41:26,  1.25it/s]
1|22779|Loss: 0.6117965579032898:  88%|████████▊ | 22779/25880 [4:38:57<39:10,  1.32it/s]
1|22780|Loss: 0.9705933332443237:  88%|████████▊ | 22779/25880 [4:38:58<39:10,  1.32it/s]
1|22780|Loss: 0.9705933332443237:  88%|████████▊ | 22780/25880 [4:38:58<34:58,  1.48it/s]
1|22781|Loss: 0.8631413578987122:  88%|████████▊ | 22780/25880 [4:38:58<34:58,  1.48it/s]
1|22781|Loss: 0.8631413578987122:  88%|████████▊ | 22781/25880 [4:38:59<35:07,  1.47it/s]
1|22782|Loss: 0.7534066438674927:  88%|████████▊ | 22781/25880 [4:38:59<35:07,  1.47it/s]
1|22782|Loss: 0.7534066438674927:  88%|████████▊ | 22782/25880 [4:38:59<34:57,  1.48it/s]
1|22783|Loss: 0.8443841934204102:  88%|████████▊ | 22782/25880 [4:39:00<34:57,  1.48it/s]
1|22783|Loss: 0.8443841934204102:  88%|████████▊ | 22783/25880 [4:39:00<35:31,  1.45it/s]
1|22784|Loss: 0.8598159551620483:  88%|████████▊ | 22783/25880 [4:39:00<35:31,  1.45it/s]
1|22784|Loss: 0.8598159551620483:  88%|████████▊ | 22784/25880 [4:39:01<35:45,  1.44it/s]
1|22785|Loss: 0.9703891277313232:  88%|████████▊ | 22784/25880 [4:39:01<35:45,  1.44it/s]
1|22785|Loss: 0.9703891277313232:  88%|████████▊ | 22785/25880 [4:39:01<35:47,  1.44it/s]
1|22786|Loss: 0.8137951493263245:  88%|████████▊ | 22785/25880 [4:39:02<35:47,  1.44it/s]
1|22786|Loss: 0.8137951493263245:  88%|████████▊ | 22786/25880 [4:39:02<37:07,  1.39it/s]
1|22787|Loss: 0.7334202527999878:  88%|████████▊ | 22786/25880 [4:39:02<37:07,  1.39it/s]
1|22787|Loss: 0.7334202527999878:  88%|████████▊ | 22787/25880 [4:39:03<37:11,  1.39it/s]
1|22788|Loss: 0.5797126889228821:  88%|████████▊ | 22787/25880 [4:39:03<37:11,  1.39it/s]
1|22788|Loss: 0.5797126889228821:  88%|████████▊ | 22788/25880 [4:39:04<40:26,  1.27it/s]
1|22789|Loss: 0.7600497007369995:  88%|████████▊ | 22788/25880 [4:39:04<40:26,  1.27it/s]
1|22789|Loss: 0.7600497007369995:  88%|████████▊ | 22789/25880 [4:39:05<40:50,  1.26it/s]
1|22790|Loss: 0.9516117572784424:  88%|████████▊ | 22789/25880 [4:39:05<40:50,  1.26it/s]
1|22790|Loss: 0.9516117572784424:  88%|████████▊ | 22790/25880 [4:39:05<38:36,  1.33it/s]
1|22791|Loss: 0.8195853233337402:  88%|████████▊ | 22790/25880 [4:39:06<38:36,  1.33it/s]
1|22791|Loss: 0.8195853233337402:  88%|████████▊ | 22791/25880 [4:39:06<39:19,  1.31it/s]
1|22792|Loss: 0.8354194760322571:  88%|████████▊ | 22791/25880 [4:39:06<39:19,  1.31it/s]
1|22792|Loss: 0.8354194760322571:  88%|████████▊ | 22792/25880 [4:39:07<39:14,  1.31it/s]
1|22793|Loss: 0.713261067867279:  88%|████████▊ | 22792/25880 [4:39:07<39:14,  1.31it/s] 
1|22793|Loss: 0.713261067867279:  88%|████████▊ | 22793/25880 [4:39:08<41:01,  1.25it/s]
1|22794|Loss: 0.8876485228538513:  88%|████████▊ | 22793/25880 [4:39:08<41:01,  1.25it/s]
1|22794|Loss: 0.8876485228538513:  88%|████████▊ | 22794/25880 [4:39:08<41:50,  1.23it/s]
1|22795|Loss: 0.8624151349067688:  88%|████████▊ | 22794/25880 [4:39:09<41:50,  1.23it/s]
1|22795|Loss: 0.8624151349067688:  88%|████████▊ | 22795/25880 [4:39:09<41:47,  1.23it/s]
1|22796|Loss: 0.8354153633117676:  88%|████████▊ | 22795/25880 [4:39:10<41:47,  1.23it/s]
1|22796|Loss: 0.8354153633117676:  88%|████████▊ | 22796/25880 [4:39:10<40:21,  1.27it/s]
1|22797|Loss: 0.9567767381668091:  88%|████████▊ | 22796/25880 [4:39:10<40:21,  1.27it/s]
1|22797|Loss: 0.9567767381668091:  88%|████████▊ | 22797/25880 [4:39:11<38:01,  1.35it/s]
1|22798|Loss: 0.8787696957588196:  88%|████████▊ | 22797/25880 [4:39:11<38:01,  1.35it/s]
1|22798|Loss: 0.8787696957588196:  88%|████████▊ | 22798/25880 [4:39:11<37:15,  1.38it/s]
1|22799|Loss: 1.0164307355880737:  88%|████████▊ | 22798/25880 [4:39:12<37:15,  1.38it/s]
1|22799|Loss: 1.0164307355880737:  88%|████████▊ | 22799/25880 [4:39:12<34:44,  1.48it/s]
1|22800|Loss: 0.7667036056518555:  88%|████████▊ | 22799/25880 [4:39:12<34:44,  1.48it/s]
1|22800|Loss: 0.7667036056518555:  88%|████████▊ | 22800/25880 [4:39:13<33:48,  1.52it/s]
1|22801|Loss: 0.6746737957000732:  88%|████████▊ | 22800/25880 [4:39:13<33:48,  1.52it/s]
1|22801|Loss: 0.6746737957000732:  88%|████████▊ | 22801/25880 [4:39:13<32:00,  1.60it/s]
1|22802|Loss: 0.8825402855873108:  88%|█���██████▊ | 22801/25880 [4:39:13<32:00,  1.60it/s]
1|22802|Loss: 0.8825402855873108:  88%|████████▊ | 22802/25880 [4:39:14<32:55,  1.56it/s]
1|22803|Loss: 0.8807823061943054:  88%|████████▊ | 22802/25880 [4:39:14<32:55,  1.56it/s]
1|22803|Loss: 0.8807823061943054:  88%|████████▊ | 22803/25880 [4:39:14<33:09,  1.55it/s]
1|22804|Loss: 0.9894338846206665:  88%|████████▊ | 22803/25880 [4:39:15<33:09,  1.55it/s]
1|22804|Loss: 0.9894338846206665:  88%|████████▊ | 22804/25880 [4:39:15<31:07,  1.65it/s]
1|22805|Loss: 0.8763992786407471:  88%|████████▊ | 22804/25880 [4:39:15<31:07,  1.65it/s]
1|22805|Loss: 0.8763992786407471:  88%|████████▊ | 22805/25880 [4:39:16<31:54,  1.61it/s]
1|22806|Loss: 0.8463876843452454:  88%|████████▊ | 22805/25880 [4:39:16<31:54,  1.61it/s]
1|22806|Loss: 0.8463876843452454:  88%|████████▊ | 22806/25880 [4:39:16<33:26,  1.53it/s]
1|22807|Loss: 0.8732605576515198:  88%|████████▊ | 22806/25880 [4:39:17<33:26,  1.53it/s]
1|22807|Loss: 0.8732605576515198:  88%|████████▊ | 22807/25880 [4:39:17<34:35,  1.48it/s]
1|22808|Loss: 0.837736964225769:  88%|████████▊ | 22807/25880 [4:39:17<34:35,  1.48it/s] 
1|22808|Loss: 0.837736964225769:  88%|████████▊ | 22808/25880 [4:39:18<35:20,  1.45it/s]
1|22809|Loss: 0.9250198006629944:  88%|████████▊ | 22808/25880 [4:39:18<35:20,  1.45it/s]
1|22809|Loss: 0.9250198006629944:  88%|████████▊ | 22809/25880 [4:39:18<35:52,  1.43it/s]
1|22810|Loss: 0.765799343585968:  88%|████████▊ | 22809/25880 [4:39:19<35:52,  1.43it/s] 
1|22810|Loss: 0.765799343585968:  88%|████████▊ | 22810/25880 [4:39:19<33:15,  1.54it/s]
1|22811|Loss: 0.8124316930770874:  88%|████████▊ | 22810/25880 [4:39:19<33:15,  1.54it/s]
1|22811|Loss: 0.8124316930770874:  88%|████████▊ | 22811/25880 [4:39:20<31:52,  1.60it/s]
1|22812|Loss: 0.9000899791717529:  88%|████████▊ | 22811/25880 [4:39:20<31:52,  1.60it/s]
1|22812|Loss: 0.9000899791717529:  88%|████████▊ | 22812/25880 [4:39:20<31:40,  1.61it/s]
1|22813|Loss: 0.7251425385475159:  88%|████████▊ | 22812/25880 [4:39:21<31:40,  1.61it/s]
1|22813|Loss: 0.7251425385475159:  88%|████████▊ | 22813/25880 [4:39:21<31:13,  1.64it/s]
1|22814|Loss: 0.8440746665000916:  88%|████████▊ | 22813/25880 [4:39:21<31:13,  1.64it/s]
1|22814|Loss: 0.8440746665000916:  88%|████████▊ | 22814/25880 [4:39:22<33:26,  1.53it/s]
1|22815|Loss: 0.8269695043563843:  88%|████████▊ | 22814/25880 [4:39:22<33:26,  1.53it/s]
1|22815|Loss: 0.8269695043563843:  88%|████████▊ | 22815/25880 [4:39:22<36:20,  1.41it/s]
1|22816|Loss: 0.9137203693389893:  88%|████████▊ | 22815/25880 [4:39:23<36:20,  1.41it/s]
1|22816|Loss: 0.9137203693389893:  88%|████████▊ | 22816/25880 [4:39:23<36:40,  1.39it/s]
1|22817|Loss: 0.8723032474517822:  88%|████████▊ | 22816/25880 [4:39:23<36:40,  1.39it/s]
1|22817|Loss: 0.8723032474517822:  88%|████████▊ | 22817/25880 [4:39:24<34:35,  1.48it/s]
1|22818|Loss: 0.8825968503952026:  88%|████████▊ | 22817/25880 [4:39:24<34:35,  1.48it/s]
1|22818|Loss: 0.8825968503952026:  88%|████████▊ | 22818/25880 [4:39:24<33:29,  1.52it/s]
1|22819|Loss: 0.8447015881538391:  88%|████████▊ | 22818/25880 [4:39:25<33:29,  1.52it/s]
1|22819|Loss: 0.8447015881538391:  88%|████████▊ | 22819/25880 [4:39:25<32:33,  1.57it/s]
1|22820|Loss: 1.0442789793014526:  88%|████████▊ | 22819/25880 [4:39:25<32:33,  1.57it/s]
1|22820|Loss: 1.0442789793014526:  88%|████████▊ | 22820/25880 [4:39:25<30:36,  1.67it/s]
1|22821|Loss: 0.7103566527366638:  88%|████████▊ | 22820/25880 [4:39:26<30:36,  1.67it/s]
1|22821|Loss: 0.7103566527366638:  88%|████████▊ | 22821/25880 [4:39:26<31:50,  1.60it/s]
1|22822|Loss: 0.8919274806976318:  88%|████████▊ | 22821/25880 [4:39:26<31:50,  1.60it/s]
1|22822|Loss: 0.8919274806976318:  88%|████████▊ | 22822/25880 [4:39:27<33:38,  1.51it/s]
1|22823|Loss: 0.9178450703620911:  88%|████████▊ | 22822/25880 [4:39:27<33:38,  1.51it/s]
1|22823|Loss: 0.9178450703620911:  88%|████████▊ | 22823/25880 [4:39:28<34:20,  1.48it/s]
1|22824|Loss: 0.7694991230964661:  88%|████████▊ | 22823/25880 [4:39:28<34:20,  1.48it/s]
1|22824|Loss: 0.7694991230964661:  88%|████████▊ | 22824/25880 [4:39:28<33:52,  1.50it/s]
1|22825|Loss: 0.8187568783760071:  88%|████████▊ | 22824/25880 [4:39:29<33:52,  1.50it/s]
1|22825|Loss: 0.8187568783760071:  88%|████████▊ | 22825/25880 [4:39:29<34:38,  1.47it/s]
1|22826|Loss: 0.8046950697898865:  88%|████████▊ | 22825/25880 [4:39:29<34:38,  1.47it/s]
1|22826|Loss: 0.8046950697898865:  88%|████████▊ | 22826/25880 [4:39:30<35:18,  1.44it/s]
1|22827|Loss: 0.9273029565811157:  88%|████████▊ | 22826/25880 [4:39:30<35:18,  1.44it/s]
1|22827|Loss: 0.9273029565811157:  88%|████████▊ | 22827/25880 [4:39:30<34:39,  1.47it/s]
1|22828|Loss: 0.8347285389900208:  88%|████████▊ | 22827/25880 [4:39:31<34:39,  1.47it/s]
1|22828|Loss: 0.8347285389900208:  88%|████████▊ | 22828/25880 [4:39:31<36:44,  1.38it/s]
1|22829|Loss: 0.7926664352416992:  88%|████████▊ | 22828/25880 [4:39:32<36:44,  1.38it/s]
1|22829|Loss: 0.7926664352416992:  88%|████████▊ | 22829/25880 [4:39:32<38:36,  1.32it/s]
1|22830|Loss: 0.7488099336624146:  88%|████████▊ | 22829/25880 [4:39:32<38:36,  1.32it/s]
1|22830|Loss: 0.7488099336624146:  88%|████████▊ | 22830/25880 [4:39:33<37:22,  1.36it/s]
1|22831|Loss: 0.8109574317932129:  88%|████████▊ | 22830/25880 [4:39:33<37:22,  1.36it/s]
1|22831|Loss: 0.8109574317932129:  88%|████████▊ | 22831/25880 [4:39:33<34:24,  1.48it/s]
1|22832|Loss: 0.8488498330116272:  88%|████████▊ | 22831/25880 [4:39:34<34:24,  1.48it/s]
1|22832|Loss: 0.8488498330116272:  88%|████████▊ | 22832/25880 [4:39:34<36:03,  1.41it/s]
1|22833|Loss: 0.6985416412353516:  88%|████████▊ | 22832/25880 [4:39:34<36:03,  1.41it/s]
1|22833|Loss: 0.6985416412353516:  88%|████████▊ | 22833/25880 [4:39:34<32:42,  1.55it/s]
1|22834|Loss: 0.7092363834381104:  88%|████████▊ | 22833/25880 [4:39:35<32:42,  1.55it/s]
1|22834|Loss: 0.7092363834381104:  88%|████████▊ | 22834/25880 [4:39:35<32:48,  1.55it/s]
1|22835|Loss: 0.8561888933181763:  88%|████████▊ | 22834/25880 [4:39:35<32:48,  1.55it/s]
1|22835|Loss: 0.8561888933181763:  88%|████████▊ | 22835/25880 [4:39:36<32:08,  1.58it/s]
1|22836|Loss: 0.9861791729927063:  88%|████████▊ | 22835/25880 [4:39:36<32:08,  1.58it/s]
1|22836|Loss: 0.9861791729927063:  88%|████████▊ | 22836/25880 [4:39:37<35:20,  1.44it/s]
1|22837|Loss: 0.8866490125656128:  88%|████████▊ | 22836/25880 [4:39:37<35:20,  1.44it/s]
1|22837|Loss: 0.8866490125656128:  88%|████████▊ | 22837/25880 [4:39:37<34:58,  1.45it/s]
1|22838|Loss: 0.743312418460846:  88%|████████▊ | 22837/25880 [4:39:38<34:58,  1.45it/s] 
1|22838|Loss: 0.743312418460846:  88%|████████▊ | 22838/25880 [4:39:38<36:25,  1.39it/s]
1|22839|Loss: 0.8366166353225708:  88%|████████▊ | 22838/25880 [4:39:38<36:25,  1.39it/s]
1|22839|Loss: 0.8366166353225708:  88%|████████▊ | 22839/25880 [4:39:39<37:39,  1.35it/s]
1|22840|Loss: 0.7128216028213501:  88%|████████▊ | 22839/25880 [4:39:39<37:39,  1.35it/s]
1|22840|Loss: 0.7128216028213501:  88%|████████▊ | 22840/25880 [4:39:40<38:21,  1.32it/s]
1|22841|Loss: 0.88421231508255:  88%|████████▊ | 22840/25880 [4:39:40<38:21,  1.32it/s]  
1|22841|Loss: 0.88421231508255:  88%|████████▊ | 22841/25880 [4:39:40<38:13,  1.32it/s]
1|22842|Loss: 0.8881780505180359:  88%|████████▊ | 22841/25880 [4:39:41<38:13,  1.32it/s]
1|22842|Loss: 0.8881780505180359:  88%|████████▊ | 22842/25880 [4:39:41<37:28,  1.35it/s]
1|22843|Loss: 0.8035040497779846:  88%|████████▊ | 22842/25880 [4:39:41<37:28,  1.35it/s]
1|22843|Loss: 0.8035040497779846:  88%|████████▊ | 22843/25880 [4:39:42<39:26,  1.28it/s]
1|22844|Loss: 0.823478639125824:  88%|████████▊ | 22843/25880 [4:39:42<39:26,  1.28it/s] 
1|22844|Loss: 0.823478639125824:  88%|████████▊ | 22844/25880 [4:39:43<37:47,  1.34it/s]
1|22845|Loss: 1.060251235961914:  88%|████████▊ | 22844/25880 [4:39:43<37:47,  1.34it/s]
1|22845|Loss: 1.060251235961914:  88%|████████▊ | 22845/25880 [4:39:43<38:09,  1.33it/s]
1|22846|Loss: 0.8863553404808044:  88%|████████▊ | 22845/25880 [4:39:44<38:09,  1.33it/s]
1|22846|Loss: 0.8863553404808044:  88%|████████▊ | 22846/25880 [4:39:44<36:58,  1.37it/s]
1|22847|Loss: 0.910918653011322:  88%|████████▊ | 22846/25880 [4:39:44<36:58,  1.37it/s] 
1|22847|Loss: 0.910918653011322:  88%|████████▊ | 22847/25880 [4:39:45<36:23,  1.39it/s]
1|22848|Loss: 0.7496740221977234:  88%|████████▊ | 22847/25880 [4:39:45<36:23,  1.39it/s]
1|22848|Loss: 0.7496740221977234:  88%|████████▊ | 22848/25880 [4:39:45<36:04,  1.40it/s]
1|22849|Loss: 0.7268886566162109:  88%|████████▊ | 22848/25880 [4:39:46<36:04,  1.40it/s]
1|22849|Loss: 0.7268886566162109:  88%|████████▊ | 22849/25880 [4:39:46<36:06,  1.40it/s]
1|22850|Loss: 0.8035404086112976:  88%|████████▊ | 22849/25880 [4:39:47<36:06,  1.40it/s]
1|22850|Loss: 0.8035404086112976:  88%|████████▊ | 22850/25880 [4:39:47<36:15,  1.39it/s]
1|22851|Loss: 0.9545890092849731:  88%|████████▊ | 22850/25880 [4:39:47<36:15,  1.39it/s]
1|22851|Loss: 0.9545890092849731:  88%|████████▊ | 22851/25880 [4:39:48<38:40,  1.31it/s]
1|22852|Loss: 0.7065902948379517:  88%|████████▊ | 22851/25880 [4:39:48<38:40,  1.31it/s]
1|22852|Loss: 0.7065902948379517:  88%|████████▊ | 22852/25880 [4:39:48<38:17,  1.32it/s]
1|22853|Loss: 0.8843156695365906:  88%|████████▊ | 22852/25880 [4:39:49<38:17,  1.32it/s]
1|22853|Loss: 0.8843156695365906:  88%|████████▊ | 22853/25880 [4:39:49<38:27,  1.31it/s]
1|22854|Loss: 0.8688277006149292:  88%|████████▊ | 22853/25880 [4:39:50<38:27,  1.31it/s]
1|22854|Loss: 0.8688277006149292:  88%|████████▊ | 22854/25880 [4:39:50<37:03,  1.36it/s]
1|22855|Loss: 0.8114246726036072:  88%|████████▊ | 22854/25880 [4:39:50<37:03,  1.36it/s]
1|22855|Loss: 0.8114246726036072:  88%|████████▊ | 22855/25880 [4:39:51<36:24,  1.38it/s]
1|22856|Loss: 0.7951316237449646:  88%|████████▊ | 22855/25880 [4:39:51<36:24,  1.38it/s]
1|22856|Loss: 0.7951316237449646:  88%|████████▊ | 22856/25880 [4:39:51<36:25,  1.38it/s]
1|22857|Loss: 0.7520089745521545:  88%|████████▊ | 22856/25880 [4:39:52<36:25,  1.38it/s]
1|22857|Loss: 0.7520089745521545:  88%|████████▊ | 22857/25880 [4:39:52<37:45,  1.33it/s]
1|22858|Loss: 0.835557758808136:  88%|████████▊ | 22857/25880 [4:39:53<37:45,  1.33it/s] 
1|22858|Loss: 0.835557758808136:  88%|████████▊ | 22858/25880 [4:39:53<38:29,  1.31it/s]
1|22859|Loss: 0.8652271032333374:  88%|████████▊ | 22858/25880 [4:39:53<38:29,  1.31it/s]
1|22859|Loss: 0.8652271032333374:  88%|████████▊ | 22859/25880 [4:39:54<40:24,  1.25it/s]
1|22860|Loss: 0.8821251392364502:  88%|████████▊ | 22859/25880 [4:39:54<40:24,  1.25it/s]
1|22860|Loss: 0.8821251392364502:  88%|████████▊ | 22860/25880 [4:39:55<39:50,  1.26it/s]
1|22861|Loss: 0.8793330192565918:  88%|████████▊ | 22860/25880 [4:39:55<39:50,  1.26it/s]
1|22861|Loss: 0.8793330192565918:  88%|████████▊ | 22861/25880 [4:39:55<38:35,  1.30it/s]
1|22862|Loss: 0.8987205028533936:  88%|████████▊ | 22861/25880 [4:39:56<38:35,  1.30it/s]
1|22862|Loss: 0.8987205028533936:  88%|████████▊ | 22862/25880 [4:39:56<36:28,  1.38it/s]
1|22863|Loss: 0.8553385734558105:  88%|████████▊ | 22862/25880 [4:39:56<36:28,  1.38it/s]
1|22863|Loss: 0.8553385734558105:  88%|████████▊ | 22863/25880 [4:39:57<37:05,  1.36it/s]
1|22864|Loss: 0.7756089568138123:  88%|████████▊ | 22863/25880 [4:39:57<37:05,  1.36it/s]
1|22864|Loss: 0.7756089568138123:  88%|████████▊ | 22864/25880 [4:39:57<35:22,  1.42it/s]
1|22865|Loss: 0.8371511697769165:  88%|████████▊ | 22864/25880 [4:39:58<35:22,  1.42it/s]
1|22865|Loss: 0.8371511697769165:  88%|████████▊ | 22865/25880 [4:39:58<35:00,  1.44it/s]
1|22866|Loss: 0.8361842632293701:  88%|████████▊ | 22865/25880 [4:39:58<35:00,  1.44it/s]
1|22866|Loss: 0.8361842632293701:  88%|████████▊ | 22866/25880 [4:39:59<34:18,  1.46it/s]
1|22867|Loss: 0.8907176852226257:  88%|████████▊ | 22866/25880 [4:39:59<34:18,  1.46it/s]
1|22867|Loss: 0.8907176852226257:  88%|████████▊ | 22867/25880 [4:39:59<33:39,  1.49it/s]
1|22868|Loss: 0.8462724685668945:  88%|████████▊ | 22867/25880 [4:40:00<33:39,  1.49it/s]
1|22868|Loss: 0.8462724685668945:  88%|████████▊ | 22868/25880 [4:40:00<35:49,  1.40it/s]
1|22869|Loss: 0.8509060740470886:  88%|████████▊ | 22868/25880 [4:40:01<35:49,  1.40it/s]
1|22869|Loss: 0.8509060740470886:  88%|████████▊ | 22869/25880 [4:40:01<38:19,  1.31it/s]
1|22870|Loss: 0.7835476398468018:  88%|████████▊ | 22869/25880 [4:40:01<38:19,  1.31it/s]
1|22870|Loss: 0.7835476398468018:  88%|████████▊ | 22870/25880 [4:40:02<36:36,  1.37it/s]
1|22871|Loss: 0.9134694337844849:  88%|████████▊ | 22870/25880 [4:40:02<36:36,  1.37it/s]
1|22871|Loss: 0.9134694337844849:  88%|████████▊ | 22871/25880 [4:40:02<37:50,  1.32it/s]
1|22872|Loss: 0.8768954873085022:  88%|████████▊ | 22871/25880 [4:40:03<37:50,  1.32it/s]
1|22872|Loss: 0.8768954873085022:  88%|████████▊ | 22872/25880 [4:40:03<36:30,  1.37it/s]
1|22873|Loss: 0.844119131565094:  88%|████████▊ | 22872/25880 [4:40:04<36:30,  1.37it/s] 
1|22873|Loss: 0.844119131565094:  88%|████████▊ | 22873/25880 [4:40:04<36:06,  1.39it/s]
1|22874|Loss: 0.7460547685623169:  88%|████████▊ | 22873/25880 [4:40:04<36:06,  1.39it/s]
1|22874|Loss: 0.7460547685623169:  88%|████████▊ | 22874/25880 [4:40:05<38:00,  1.32it/s]
1|22875|Loss: 0.9938821792602539:  88%|████████▊ | 22874/25880 [4:40:05<38:00,  1.32it/s]
1|22875|Loss: 0.9938821792602539:  88%|████████▊ | 22875/25880 [4:40:06<39:19,  1.27it/s]
1|22876|Loss: 0.9118123054504395:  88%|████████▊ | 22875/25880 [4:40:06<39:19,  1.27it/s]
1|22876|Loss: 0.9118123054504395:  88%|████████▊ | 22876/25880 [4:40:06<38:49,  1.29it/s]
1|22877|Loss: 0.8029611110687256:  88%|████████▊ | 22876/25880 [4:40:07<38:49,  1.29it/s]
1|22877|Loss: 0.8029611110687256:  88%|████████▊ | 22877/25880 [4:40:07<37:49,  1.32it/s]
1|22878|Loss: 0.8091521263122559:  88%|████████▊ | 22877/25880 [4:40:07<37:49,  1.32it/s]
1|22878|Loss: 0.8091521263122559:  88%|████████▊ | 22878/25880 [4:40:08<39:10,  1.28it/s]
1|22879|Loss: 0.9058129787445068:  88%|████████▊ | 22878/25880 [4:40:08<39:10,  1.28it/s]
1|22879|Loss: 0.9058129787445068:  88%|████████▊ | 22879/25880 [4:40:09<38:37,  1.30it/s]
1|22880|Loss: 0.7946157455444336:  88%|████████▊ | 22879/25880 [4:40:09<38:37,  1.30it/s]
1|22880|Loss: 0.7946157455444336:  88%|████████▊ | 22880/25880 [4:40:09<38:06,  1.31it/s]
1|22881|Loss: 0.8421287536621094:  88%|████████▊ | 22880/25880 [4:40:10<38:06,  1.31it/s]
1|22881|Loss: 0.8421287536621094:  88%|████████▊ | 22881/25880 [4:40:10<38:57,  1.28it/s]
1|22882|Loss: 0.7636351585388184:  88%|████████▊ | 22881/25880 [4:40:11<38:57,  1.28it/s]
1|22882|Loss: 0.7636351585388184:  88%|████████▊ | 22882/25880 [4:40:11<39:24,  1.27it/s]
1|22883|Loss: 0.8110156059265137:  88%|████████▊ | 22882/25880 [4:40:11<39:24,  1.27it/s]
1|22883|Loss: 0.8110156059265137:  88%|████████▊ | 22883/25880 [4:40:12<37:36,  1.33it/s]
1|22884|Loss: 0.9521949887275696:  88%|████████▊ | 22883/25880 [4:40:12<37:36,  1.33it/s]
1|22884|Loss: 0.9521949887275696:  88%|████████▊ | 22884/25880 [4:40:12<36:58,  1.35it/s]
1|22885|Loss: 0.8165033459663391:  88%|████████▊ | 22884/25880 [4:40:13<36:58,  1.35it/s]
1|22885|Loss: 0.8165033459663391:  88%|████████▊ | 22885/25880 [4:40:13<35:25,  1.41it/s]
1|22886|Loss: 0.897032618522644:  88%|████████▊ | 22885/25880 [4:40:13<35:25,  1.41it/s] 
1|22886|Loss: 0.897032618522644:  88%|████████▊ | 22886/25880 [4:40:14<36:05,  1.38it/s]
1|22887|Loss: 0.8464721441268921:  88%|████████▊ | 22886/25880 [4:40:14<36:05,  1.38it/s]
1|22887|Loss: 0.8464721441268921:  88%|████████▊ | 22887/25880 [4:40:14<36:07,  1.38it/s]
1|22888|Loss: 0.770400881767273:  88%|████████▊ | 22887/25880 [4:40:15<36:07,  1.38it/s] 
1|22888|Loss: 0.770400881767273:  88%|████████▊ | 22888/25880 [4:40:15<36:12,  1.38it/s]
1|22889|Loss: 0.7251138091087341:  88%|████████▊ | 22888/25880 [4:40:16<36:12,  1.38it/s]
1|22889|Loss: 0.7251138091087341:  88%|████████▊ | 22889/25880 [4:40:16<33:44,  1.48it/s]
1|22890|Loss: 0.732925295829773:  88%|████████▊ | 22889/25880 [4:40:16<33:44,  1.48it/s] 
1|22890|Loss: 0.732925295829773:  88%|████████▊ | 22890/25880 [4:40:17<35:42,  1.40it/s]
1|22891|Loss: 0.686882734298706:  88%|████████▊ | 22890/25880 [4:40:17<35:42,  1.40it/s]
1|22891|Loss: 0.686882734298706:  88%|████████▊ | 22891/25880 [4:40:17<33:52,  1.47it/s]
1|22892|Loss: 0.7546667456626892:  88%|████████▊ | 22891/25880 [4:40:18<33:52,  1.47it/s]
1|22892|Loss: 0.7546667456626892:  88%|████████▊ | 22892/25880 [4:40:18<33:36,  1.48it/s]
1|22893|Loss: 0.813447892665863:  88%|████████▊ | 22892/25880 [4:40:18<33:36,  1.48it/s] 
1|22893|Loss: 0.813447892665863:  88%|████████▊ | 22893/25880 [4:40:19<34:19,  1.45it/s]
1|22894|Loss: 0.8475850224494934:  88%|████████▊ | 22893/25880 [4:40:19<34:19,  1.45it/s]
1|22894|Loss: 0.8475850224494934:  88%|████████▊ | 22894/25880 [4:40:19<36:19,  1.37it/s]
1|22895|Loss: 0.9575532078742981:  88%|████████▊ | 22894/25880 [4:40:20<36:19,  1.37it/s]
1|22895|Loss: 0.9575532078742981:  88%|████████▊ | 22895/25880 [4:40:20<36:55,  1.35it/s]
1|22896|Loss: 0.7918710708618164:  88%|████████▊ | 22895/25880 [4:40:21<36:55,  1.35it/s]
1|22896|Loss: 0.7918710708618164:  88%|████████▊ | 22896/25880 [4:40:21<37:34,  1.32it/s]
1|22897|Loss: 0.8323662281036377:  88%|████████▊ | 22896/25880 [4:40:21<37:34,  1.32it/s]
1|22897|Loss: 0.8323662281036377:  88%|████████▊ | 22897/25880 [4:40:22<36:11,  1.37it/s]
1|22898|Loss: 0.9528585076332092:  88%|████████▊ | 22897/25880 [4:40:22<36:11,  1.37it/s]
1|22898|Loss: 0.9528585076332092:  88%|████████▊ | 22898/25880 [4:40:22<36:35,  1.36it/s]
1|22899|Loss: 0.7328212857246399:  88%|████████▊ | 22898/25880 [4:40:23<36:35,  1.36it/s]
1|22899|Loss: 0.7328212857246399:  88%|████████▊ | 22899/25880 [4:40:23<36:22,  1.37it/s]
1|22900|Loss: 0.8118320107460022:  88%|████████▊ | 22899/25880 [4:40:23<36:22,  1.37it/s]
1|22900|Loss: 0.8118320107460022:  88%|████████▊ | 22900/25880 [4:40:24<34:22,  1.44it/s]
1|22901|Loss: 0.8399778604507446:  88%|████████▊ | 22900/25880 [4:40:24<34:22,  1.44it/s]
1|22901|Loss: 0.8399778604507446:  88%|████████▊ | 22901/25880 [4:40:24<35:44,  1.39it/s]
1|22902|Loss: 0.7494258880615234:  88%|████████▊ | 22901/25880 [4:40:25<35:44,  1.39it/s]
1|22902|Loss: 0.7494258880615234:  88%|████████▊ | 22902/25880 [4:40:25<37:45,  1.31it/s]
1|22903|Loss: 0.764727771282196:  88%|████████▊ | 22902/25880 [4:40:26<37:45,  1.31it/s] 
1|22903|Loss: 0.764727771282196:  88%|████████▊ | 22903/25880 [4:40:26<34:34,  1.44it/s]
1|22904|Loss: 0.8432812094688416:  88%|████████▊ | 22903/25880 [4:40:26<34:34,  1.44it/s]
1|22904|Loss: 0.8432812094688416:  89%|████████▊ | 22904/25880 [4:40:27<34:12,  1.45it/s]
1|22905|Loss: 0.7445843815803528:  89%|████████▊ | 22904/25880 [4:40:27<34:12,  1.45it/s]
1|22905|Loss: 0.7445843815803528:  89%|████████▊ | 22905/25880 [4:40:27<35:42,  1.39it/s]
1|22906|Loss: 0.7928810715675354:  89%|████████▊ | 22905/25880 [4:40:28<35:42,  1.39it/s]
1|22906|Loss: 0.7928810715675354:  89%|████████▊ | 22906/25880 [4:40:28<35:56,  1.38it/s]
1|22907|Loss: 1.0291025638580322:  89%|████████▊ | 22906/25880 [4:40:28<35:56,  1.38it/s]
1|22907|Loss: 1.0291025638580322:  89%|████████▊ | 22907/25880 [4:40:29<37:24,  1.32it/s]
1|22908|Loss: 0.675314724445343:  89%|████████▊ | 22907/25880 [4:40:29<37:24,  1.32it/s] 
1|22908|Loss: 0.675314724445343:  89%|████████▊ | 22908/25880 [4:40:30<39:45,  1.25it/s]
1|22909|Loss: 0.7626011371612549:  89%|████████▊ | 22908/25880 [4:40:30<39:45,  1.25it/s]
1|22909|Loss: 0.7626011371612549:  89%|████████▊ | 22909/25880 [4:40:30<37:03,  1.34it/s]
1|22910|Loss: 0.865453839302063:  89%|████████▊ | 22909/25880 [4:40:31<37:03,  1.34it/s] 
1|22910|Loss: 0.865453839302063:  89%|████████▊ | 22910/25880 [4:40:31<37:02,  1.34it/s]
1|22911|Loss: 0.7590799331665039:  89%|████████▊ | 22910/25880 [4:40:32<37:02,  1.34it/s]
1|22911|Loss: 0.7590799331665039:  89%|████████▊ | 22911/25880 [4:40:32<36:56,  1.34it/s]
1|22912|Loss: 0.8911490440368652:  89%|████████▊ | 22911/25880 [4:40:32<36:56,  1.34it/s]
1|22912|Loss: 0.8911490440368652:  89%|████████▊ | 22912/25880 [4:40:33<35:37,  1.39it/s]
1|22913|Loss: 0.7986940741539001:  89%|████████▊ | 22912/25880 [4:40:33<35:37,  1.39it/s]
1|22913|Loss: 0.7986940741539001:  89%|████████▊ | 22913/25880 [4:40:33<35:10,  1.41it/s]
1|22914|Loss: 0.772459864616394:  89%|████████▊ | 22913/25880 [4:40:34<35:10,  1.41it/s] 
1|22914|Loss: 0.772459864616394:  89%|████████▊ | 22914/25880 [4:40:34<35:31,  1.39it/s]
1|22915|Loss: 0.7920028567314148:  89%|████████▊ | 22914/25880 [4:40:34<35:31,  1.39it/s]
1|22915|Loss: 0.7920028567314148:  89%|████████▊ | 22915/25880 [4:40:35<35:54,  1.38it/s]
1|22916|Loss: 0.8704255223274231:  89%|████████▊ | 22915/25880 [4:40:35<35:54,  1.38it/s]
1|22916|Loss: 0.8704255223274231:  89%|████████▊ | 22916/25880 [4:40:35<36:17,  1.36it/s]
1|22917|Loss: 0.8151845335960388:  89%|████████▊ | 22916/25880 [4:40:36<36:17,  1.36it/s]
1|22917|Loss: 0.8151845335960388:  89%|████████▊ | 22917/25880 [4:40:36<36:37,  1.35it/s]
1|22918|Loss: 0.6707378029823303:  89%|████████▊ | 22917/25880 [4:40:37<36:37,  1.35it/s]
1|22918|Loss: 0.6707378029823303:  89%|████████▊ | 22918/25880 [4:40:37<38:12,  1.29it/s]
1|22919|Loss: 0.7839159369468689:  89%|████████▊ | 22918/25880 [4:40:37<38:12,  1.29it/s]
1|22919|Loss: 0.7839159369468689:  89%|████████▊ | 22919/25880 [4:40:38<36:23,  1.36it/s]
1|22920|Loss: 0.9133508801460266:  89%|████████▊ | 22919/25880 [4:40:38<36:23,  1.36it/s]
1|22920|Loss: 0.9133508801460266:  89%|████████▊ | 22920/25880 [4:40:38<35:45,  1.38it/s]
1|22921|Loss: 0.8756414651870728:  89%|████████▊ | 22920/25880 [4:40:39<35:45,  1.38it/s]
1|22921|Loss: 0.8756414651870728:  89%|████████▊ | 22921/25880 [4:40:39<36:00,  1.37it/s]
1|22922|Loss: 0.9117760062217712:  89%|████████▊ | 22921/25880 [4:40:40<36:00,  1.37it/s]
1|22922|Loss: 0.9117760062217712:  89%|████████▊ | 22922/25880 [4:40:40<36:00,  1.37it/s]
1|22923|Loss: 0.8322983980178833:  89%|████████▊ | 22922/25880 [4:40:40<36:00,  1.37it/s]
1|22923|Loss: 0.8322983980178833:  89%|████████▊ | 22923/25880 [4:40:41<36:12,  1.36it/s]
1|22924|Loss: 0.8766179084777832:  89%|████████▊ | 22923/25880 [4:40:41<36:12,  1.36it/s]
1|22924|Loss: 0.8766179084777832:  89%|████████▊ | 22924/25880 [4:40:41<34:49,  1.41it/s]
1|22925|Loss: 0.7688056230545044:  89%|████████▊ | 22924/25880 [4:40:42<34:49,  1.41it/s]
1|22925|Loss: 0.7688056230545044:  89%|████████▊ | 22925/25880 [4:40:42<34:50,  1.41it/s]
1|22926|Loss: 0.804571807384491:  89%|████████▊ | 22925/25880 [4:40:42<34:50,  1.41it/s] 
1|22926|Loss: 0.804571807384491:  89%|████████▊ | 22926/25880 [4:40:43<32:50,  1.50it/s]
1|22927|Loss: 0.8817693591117859:  89%|████████▊ | 22926/25880 [4:40:43<32:50,  1.50it/s]
1|22927|Loss: 0.8817693591117859:  89%|████████▊ | 22927/25880 [4:40:43<33:14,  1.48it/s]
1|22928|Loss: 0.9453078508377075:  89%|████████▊ | 22927/25880 [4:40:44<33:14,  1.48it/s]
1|22928|Loss: 0.9453078508377075:  89%|████████▊ | 22928/25880 [4:40:44<32:59,  1.49it/s]
1|22929|Loss: 0.8284871578216553:  89%|████████▊ | 22928/25880 [4:40:44<32:59,  1.49it/s]
1|22929|Loss: 0.8284871578216553:  89%|████████▊ | 22929/25880 [4:40:45<33:39,  1.46it/s]
1|22930|Loss: 0.8053364157676697:  89%|████████▊ | 22929/25880 [4:40:45<33:39,  1.46it/s]
1|22930|Loss: 0.8053364157676697:  89%|████████▊ | 22930/25880 [4:40:45<35:33,  1.38it/s]
1|22931|Loss: 0.7822259068489075:  89%|████████▊ | 22930/25880 [4:40:46<35:33,  1.38it/s]
1|22931|Loss: 0.7822259068489075:  89%|████████▊ | 22931/25880 [4:40:46<36:00,  1.37it/s]
1|22932|Loss: 0.6758803725242615:  89%|████████▊ | 22931/25880 [4:40:47<36:00,  1.37it/s]
1|22932|Loss: 0.6758803725242615:  89%|████████▊ | 22932/25880 [4:40:47<36:12,  1.36it/s]
1|22933|Loss: 0.9251803755760193:  89%|████████▊ | 22932/25880 [4:40:47<36:12,  1.36it/s]
1|22933|Loss: 0.9251803755760193:  89%|████████▊ | 22933/25880 [4:40:48<35:52,  1.37it/s]
1|22934|Loss: 0.827770471572876:  89%|████████▊ | 22933/25880 [4:40:48<35:52,  1.37it/s] 
1|22934|Loss: 0.827770471572876:  89%|████████▊ | 22934/25880 [4:40:48<35:27,  1.38it/s]
1|22935|Loss: 1.0618959665298462:  89%|████████▊ | 22934/25880 [4:40:49<35:27,  1.38it/s]
1|22935|Loss: 1.0618959665298462:  89%|████████▊ | 22935/25880 [4:40:49<35:08,  1.40it/s]
1|22936|Loss: 0.7969545125961304:  89%|████████▊ | 22935/25880 [4:40:50<35:08,  1.40it/s]
1|22936|Loss: 0.7969545125961304:  89%|████████▊ | 22936/25880 [4:40:50<36:08,  1.36it/s]
1|22937|Loss: 0.919651448726654:  89%|████████▊ | 22936/25880 [4:40:50<36:08,  1.36it/s] 
1|22937|Loss: 0.919651448726654:  89%|████████▊ | 22937/25880 [4:40:51<36:51,  1.33it/s]
1|22938|Loss: 0.7297700643539429:  89%|████████▊ | 22937/25880 [4:40:51<36:51,  1.33it/s]
1|22938|Loss: 0.7297700643539429:  89%|████████▊ | 22938/25880 [4:40:51<37:54,  1.29it/s]
1|22939|Loss: 0.9869406223297119:  89%|████████▊ | 22938/25880 [4:40:52<37:54,  1.29it/s]
1|22939|Loss: 0.9869406223297119:  89%|████████▊ | 22939/25880 [4:40:52<37:09,  1.32it/s]
1|22940|Loss: 0.6645705699920654:  89%|████████▊ | 22939/25880 [4:40:53<37:09,  1.32it/s]
1|22940|Loss: 0.6645705699920654:  89%|████████▊ | 22940/25880 [4:40:53<36:37,  1.34it/s]
1|22941|Loss: 0.7311438918113708:  89%|████████▊ | 22940/25880 [4:40:53<36:37,  1.34it/s]
1|22941|Loss: 0.7311438918113708:  89%|████████▊ | 22941/25880 [4:40:54<35:13,  1.39it/s]
1|22942|Loss: 0.8344448208808899:  89%|████████▊ | 22941/25880 [4:40:54<35:13,  1.39it/s]
1|22942|Loss: 0.8344448208808899:  89%|████████▊ | 22942/25880 [4:40:54<36:30,  1.34it/s]
1|22943|Loss: 0.5735668540000916:  89%|████████▊ | 22942/25880 [4:40:55<36:30,  1.34it/s]
1|22943|Loss: 0.5735668540000916:  89%|████████▊ | 22943/25880 [4:40:55<38:20,  1.28it/s]
1|22944|Loss: 0.8801340460777283:  89%|████████▊ | 22943/25880 [4:40:56<38:20,  1.28it/s]
1|22944|Loss: 0.8801340460777283:  89%|████████▊ | 22944/25880 [4:40:56<35:26,  1.38it/s]
1|22945|Loss: 0.8710477352142334:  89%|████████▊ | 22944/25880 [4:40:56<35:26,  1.38it/s]
1|22945|Loss: 0.8710477352142334:  89%|████████▊ | 22945/25880 [4:40:57<34:31,  1.42it/s]
1|22946|Loss: 0.7594611048698425:  89%|████████▊ | 22945/25880 [4:40:57<34:31,  1.42it/s]
1|22946|Loss: 0.7594611048698425:  89%|████████▊ | 22946/25880 [4:40:57<37:00,  1.32it/s]
1|22947|Loss: 0.8355502486228943:  89%|████████▊ | 22946/25880 [4:40:58<37:00,  1.32it/s]
1|22947|Loss: 0.8355502486228943:  89%|████████▊ | 22947/25880 [4:40:58<34:18,  1.42it/s]
1|22948|Loss: 0.765716016292572:  89%|████████▊ | 22947/25880 [4:40:58<34:18,  1.42it/s] 
1|22948|Loss: 0.765716016292572:  89%|████████▊ | 22948/25880 [4:40:59<35:06,  1.39it/s]
1|22949|Loss: 0.89320307970047:  89%|████████▊ | 22948/25880 [4:40:59<35:06,  1.39it/s] 
1|22949|Loss: 0.89320307970047:  89%|████████▊ | 22949/25880 [4:40:59<34:11,  1.43it/s]
1|22950|Loss: 0.9026021957397461:  89%|████████▊ | 22949/25880 [4:41:00<34:11,  1.43it/s]
1|22950|Loss: 0.9026021957397461:  89%|████████▊ | 22950/25880 [4:41:00<33:14,  1.47it/s]
1|22951|Loss: 0.764032781124115:  89%|████████▊ | 22950/25880 [4:41:00<33:14,  1.47it/s] 
1|22951|Loss: 0.764032781124115:  89%|████████▊ | 22951/25880 [4:41:01<35:03,  1.39it/s]
1|22952|Loss: 0.7905982136726379:  89%|████████▊ | 22951/25880 [4:41:01<35:03,  1.39it/s]
1|22952|Loss: 0.7905982136726379:  89%|████████▊ | 22952/25880 [4:41:02<34:39,  1.41it/s]
1|22953|Loss: 0.8354966640472412:  89%|████████▊ | 22952/25880 [4:41:02<34:39,  1.41it/s]
1|22953|Loss: 0.8354966640472412:  89%|████████▊ | 22953/25880 [4:41:02<34:38,  1.41it/s]
1|22954|Loss: 0.885651171207428:  89%|████████▊ | 22953/25880 [4:41:03<34:38,  1.41it/s] 
1|22954|Loss: 0.885651171207428:  89%|████████▊ | 22954/25880 [4:41:03<34:34,  1.41it/s]
1|22955|Loss: 0.7475352883338928:  89%|████████▊ | 22954/25880 [4:41:03<34:34,  1.41it/s]
1|22955|Loss: 0.7475352883338928:  89%|████████▊ | 22955/25880 [4:41:04<33:42,  1.45it/s]
1|22956|Loss: 0.7092487215995789:  89%|████████▊ | 22955/25880 [4:41:04<33:42,  1.45it/s]
1|22956|Loss: 0.7092487215995789:  89%|████████▊ | 22956/25880 [4:41:04<35:23,  1.38it/s]
1|22957|Loss: 0.8887739777565002:  89%|████████▊ | 22956/25880 [4:41:05<35:23,  1.38it/s]
1|22957|Loss: 0.8887739777565002:  89%|████████▊ | 22957/25880 [4:41:05<34:48,  1.40it/s]
1|22958|Loss: 0.8086780905723572:  89%|████████▊ | 22957/25880 [4:41:05<34:48,  1.40it/s]
1|22958|Loss: 0.8086780905723572:  89%|████████▊ | 22958/25880 [4:41:06<34:52,  1.40it/s]
1|22959|Loss: 0.8380427956581116:  89%|████████▊ | 22958/25880 [4:41:06<34:52,  1.40it/s]
1|22959|Loss: 0.8380427956581116:  89%|████████▊ | 22959/25880 [4:41:06<33:49,  1.44it/s]
1|22960|Loss: 0.7362928986549377:  89%|████████▊ | 22959/25880 [4:41:07<33:49,  1.44it/s]
1|22960|Loss: 0.7362928986549377:  89%|████████▊ | 22960/25880 [4:41:07<34:01,  1.43it/s]
1|22961|Loss: 0.7598697543144226:  89%|████████▊ | 22960/25880 [4:41:08<34:01,  1.43it/s]
1|22961|Loss: 0.7598697543144226:  89%|████████▊ | 22961/25880 [4:41:08<34:12,  1.42it/s]
1|22962|Loss: 0.817240834236145:  89%|████████▊ | 22961/25880 [4:41:08<34:12,  1.42it/s] 
1|22962|Loss: 0.817240834236145:  89%|████████▊ | 22962/25880 [4:41:09<35:15,  1.38it/s]
1|22963|Loss: 0.8421822786331177:  89%|████████▊ | 22962/25880 [4:41:09<35:15,  1.38it/s]
1|22963|Loss: 0.8421822786331177:  89%|████████▊ | 22963/25880 [4:41:09<35:16,  1.38it/s]
1|22964|Loss: 0.7805792093276978:  89%|████████▊ | 22963/25880 [4:41:10<35:16,  1.38it/s]
1|22964|Loss: 0.7805792093276978:  89%|████████▊ | 22964/25880 [4:41:10<35:53,  1.35it/s]
1|22965|Loss: 0.6954224705696106:  89%|████████▊ | 22964/25880 [4:41:11<35:53,  1.35it/s]
1|22965|Loss: 0.6954224705696106:  89%|████████▊ | 22965/25880 [4:41:11<36:49,  1.32it/s]
1|22966|Loss: 0.8017755746841431:  89%|████████▊ | 22965/25880 [4:41:11<36:49,  1.32it/s]
1|22966|Loss: 0.8017755746841431:  89%|████████▊ | 22966/25880 [4:41:12<35:35,  1.36it/s]
1|22967|Loss: 0.881627082824707:  89%|████████▊ | 22966/25880 [4:41:12<35:35,  1.36it/s] 
1|22967|Loss: 0.881627082824707:  89%|████████▊ | 22967/25880 [4:41:12<34:16,  1.42it/s]
1|22968|Loss: 0.8914309740066528:  89%|██████��█▊ | 22967/25880 [4:41:13<34:16,  1.42it/s]
1|22968|Loss: 0.8914309740066528:  89%|████████▊ | 22968/25880 [4:41:13<34:00,  1.43it/s]
1|22969|Loss: 0.8048304915428162:  89%|████████▊ | 22968/25880 [4:41:13<34:00,  1.43it/s]
1|22969|Loss: 0.8048304915428162:  89%|████████▉ | 22969/25880 [4:41:13<31:55,  1.52it/s]
1|22970|Loss: 0.6778550148010254:  89%|████████▉ | 22969/25880 [4:41:14<31:55,  1.52it/s]
1|22970|Loss: 0.6778550148010254:  89%|████████▉ | 22970/25880 [4:41:14<34:08,  1.42it/s]
1|22971|Loss: 0.888481855392456:  89%|████████▉ | 22970/25880 [4:41:15<34:08,  1.42it/s] 
1|22971|Loss: 0.888481855392456:  89%|████████▉ | 22971/25880 [4:41:15<35:06,  1.38it/s]
1|22972|Loss: 0.6954554319381714:  89%|████████▉ | 22971/25880 [4:41:15<35:06,  1.38it/s]
1|22972|Loss: 0.6954554319381714:  89%|████████▉ | 22972/25880 [4:41:16<33:54,  1.43it/s]
1|22973|Loss: 0.8563997149467468:  89%|████████▉ | 22972/25880 [4:41:16<33:54,  1.43it/s]
1|22973|Loss: 0.8563997149467468:  89%|████████▉ | 22973/25880 [4:41:16<31:35,  1.53it/s]
1|22974|Loss: 0.8330976963043213:  89%|████████▉ | 22973/25880 [4:41:17<31:35,  1.53it/s]
1|22974|Loss: 0.8330976963043213:  89%|████████▉ | 22974/25880 [4:41:17<31:44,  1.53it/s]
1|22975|Loss: 0.9587692618370056:  89%|████████▉ | 22974/25880 [4:41:17<31:44,  1.53it/s]
1|22975|Loss: 0.9587692618370056:  89%|████████▉ | 22975/25880 [4:41:18<33:32,  1.44it/s]
1|22976|Loss: 0.8665972352027893:  89%|████████▉ | 22975/25880 [4:41:18<33:32,  1.44it/s]
1|22976|Loss: 0.8665972352027893:  89%|████████▉ | 22976/25880 [4:41:18<33:58,  1.42it/s]
1|22977|Loss: 0.827303409576416:  89%|████████▉ | 22976/25880 [4:41:19<33:58,  1.42it/s] 
1|22977|Loss: 0.827303409576416:  89%|████████▉ | 22977/25880 [4:41:19<34:24,  1.41it/s]
1|22978|Loss: 1.0075691938400269:  89%|████████▉ | 22977/25880 [4:41:20<34:24,  1.41it/s]
1|22978|Loss: 1.0075691938400269:  89%|████████▉ | 22978/25880 [4:41:20<33:04,  1.46it/s]
1|22979|Loss: 0.8452122807502747:  89%|████████▉ | 22978/25880 [4:41:20<33:04,  1.46it/s]
1|22979|Loss: 0.8452122807502747:  89%|████████▉ | 22979/25880 [4:41:20<32:18,  1.50it/s]
1|22980|Loss: 0.8699279427528381:  89%|████████▉ | 22979/25880 [4:41:21<32:18,  1.50it/s]
1|22980|Loss: 0.8699279427528381:  89%|████████▉ | 22980/25880 [4:41:21<34:46,  1.39it/s]
1|22981|Loss: 0.6435080766677856:  89%|████████▉ | 22980/25880 [4:41:22<34:46,  1.39it/s]
1|22981|Loss: 0.6435080766677856:  89%|████████▉ | 22981/25880 [4:41:22<35:02,  1.38it/s]
1|22982|Loss: 0.7824080586433411:  89%|████████▉ | 22981/25880 [4:41:22<35:02,  1.38it/s]
1|22982|Loss: 0.7824080586433411:  89%|████████▉ | 22982/25880 [4:41:23<35:02,  1.38it/s]
1|22983|Loss: 0.8064740300178528:  89%|████████▉ | 22982/25880 [4:41:23<35:02,  1.38it/s]
1|22983|Loss: 0.8064740300178528:  89%|████████▉ | 22983/25880 [4:41:23<33:44,  1.43it/s]
1|22984|Loss: 0.836958110332489:  89%|████████▉ | 22983/25880 [4:41:24<33:44,  1.43it/s] 
1|22984|Loss: 0.836958110332489:  89%|████████▉ | 22984/25880 [4:41:24<36:49,  1.31it/s]
1|22985|Loss: 0.8999672532081604:  89%|████████▉ | 22984/25880 [4:41:25<36:49,  1.31it/s]
1|22985|Loss: 0.8999672532081604:  89%|████████▉ | 22985/25880 [4:41:25<37:55,  1.27it/s]
1|22986|Loss: 0.8218223452568054:  89%|████████▉ | 22985/25880 [4:41:25<37:55,  1.27it/s]
1|22986|Loss: 0.8218223452568054:  89%|████████▉ | 22986/25880 [4:41:26<36:04,  1.34it/s]
1|22987|Loss: 0.8624690771102905:  89%|████████▉ | 22986/25880 [4:41:26<36:04,  1.34it/s]
1|22987|Loss: 0.8624690771102905:  89%|████████▉ | 22987/25880 [4:41:26<35:38,  1.35it/s]
1|22988|Loss: 0.803764283657074:  89%|████████▉ | 22987/25880 [4:41:27<35:38,  1.35it/s] 
1|22988|Loss: 0.803764283657074:  89%|████████▉ | 22988/25880 [4:41:27<32:58,  1.46it/s]
1|22989|Loss: 0.9080857634544373:  89%|████████▉ | 22988/25880 [4:41:27<32:58,  1.46it/s]
1|22989|Loss: 0.9080857634544373:  89%|████████▉ | 22989/25880 [4:41:28<31:57,  1.51it/s]
1|22990|Loss: 0.8607935905456543:  89%|████████▉ | 22989/25880 [4:41:28<31:57,  1.51it/s]
1|22990|Loss: 0.8607935905456543:  89%|████████▉ | 22990/25880 [4:41:28<30:25,  1.58it/s]
1|22991|Loss: 0.8896235227584839:  89%|████████▉ | 22990/25880 [4:41:29<30:25,  1.58it/s]
1|22991|Loss: 0.8896235227584839:  89%|████████▉ | 22991/25880 [4:41:29<32:01,  1.50it/s]
1|22992|Loss: 0.6605995297431946:  89%|████████▉ | 22991/25880 [4:41:29<32:01,  1.50it/s]
1|22992|Loss: 0.6605995297431946:  89%|████████▉ | 22992/25880 [4:41:30<34:33,  1.39it/s]
1|22993|Loss: 0.8444673418998718:  89%|████████▉ | 22992/25880 [4:41:30<34:33,  1.39it/s]
1|22993|Loss: 0.8444673418998718:  89%|████████▉ | 22993/25880 [4:41:30<33:53,  1.42it/s]
1|22994|Loss: 0.7980067729949951:  89%|████████▉ | 22993/25880 [4:41:31<33:53,  1.42it/s]
1|22994|Loss: 0.7980067729949951:  89%|████████▉ | 22994/25880 [4:41:31<35:29,  1.36it/s]
1|22995|Loss: 0.6899932622909546:  89%|████████▉ | 22994/25880 [4:41:32<35:29,  1.36it/s]
1|22995|Loss: 0.6899932622909546:  89%|████████▉ | 22995/25880 [4:41:32<33:31,  1.43it/s]
1|22996|Loss: 0.7814416289329529:  89%|████████▉ | 22995/25880 [4:41:32<33:31,  1.43it/s]
1|22996|Loss: 0.7814416289329529:  89%|████████▉ | 22996/25880 [4:41:33<34:19,  1.40it/s]
1|22997|Loss: 0.9075012803077698:  89%|████████▉ | 22996/25880 [4:41:33<34:19,  1.40it/s]
1|22997|Loss: 0.9075012803077698:  89%|████████▉ | 22997/25880 [4:41:33<33:46,  1.42it/s]
1|22998|Loss: 0.9002231359481812:  89%|████████▉ | 22997/25880 [4:41:34<33:46,  1.42it/s]
1|22998|Loss: 0.9002231359481812:  89%|████████▉ | 22998/25880 [4:41:34<35:39,  1.35it/s]
1|22999|Loss: 0.9528917074203491:  89%|████████▉ | 22998/25880 [4:41:35<35:39,  1.35it/s]
1|22999|Loss: 0.9528917074203491:  89%|████████▉ | 22999/25880 [4:41:35<35:57,  1.34it/s]
1|23000|Loss: 0.7018399238586426:  89%|████████▉ | 22999/25880 [4:41:35<35:57,  1.34it/s]
1|23000|Loss: 0.7018399238586426:  89%|████████▉ | 23000/25880 [4:41:36<35:39,  1.35it/s]
1|23001|Loss: 0.9986546635627747:  89%|████████▉ | 23000/25880 [4:41:36<35:39,  1.35it/s]
1|23001|Loss: 0.9986546635627747:  89%|████████▉ | 23001/25880 [4:41:36<35:33,  1.35it/s]
1|23002|Loss: 0.7888147830963135:  89%|████████▉ | 23001/25880 [4:41:37<35:33,  1.35it/s]
1|23002|Loss: 0.7888147830963135:  89%|████████▉ | 23002/25880 [4:41:37<35:27,  1.35it/s]
1|23003|Loss: 0.7433116436004639:  89%|████████▉ | 23002/25880 [4:41:38<35:27,  1.35it/s]
1|23003|Loss: 0.7433116436004639:  89%|████████▉ | 23003/25880 [4:41:38<36:41,  1.31it/s]
1|23004|Loss: 0.9342610239982605:  89%|████████▉ | 23003/25880 [4:41:38<36:41,  1.31it/s]
1|23004|Loss: 0.9342610239982605:  89%|████████▉ | 23004/25880 [4:41:39<35:28,  1.35it/s]
1|23005|Loss: 0.8055397272109985:  89%|████████▉ | 23004/25880 [4:41:39<35:28,  1.35it/s]
1|23005|Loss: 0.8055397272109985:  89%|████████▉ | 23005/25880 [4:41:39<34:04,  1.41it/s]
1|23006|Loss: 0.8845688104629517:  89%|████████▉ | 23005/25880 [4:41:40<34:04,  1.41it/s]
1|23006|Loss: 0.8845688104629517:  89%|████████▉ | 23006/25880 [4:41:40<34:12,  1.40it/s]
1|23007|Loss: 0.8861703872680664:  89%|████████▉ | 23006/25880 [4:41:40<34:12,  1.40it/s]
1|23007|Loss: 0.8861703872680664:  89%|████████▉ | 23007/25880 [4:41:41<34:25,  1.39it/s]
1|23008|Loss: 0.8477346301078796:  89%|████████▉ | 23007/25880 [4:41:41<34:25,  1.39it/s]
1|23008|Loss: 0.8477346301078796:  89%|████████▉ | 23008/25880 [4:41:42<35:33,  1.35it/s]
1|23009|Loss: 0.8552048206329346:  89%|████████▉ | 23008/25880 [4:41:42<35:33,  1.35it/s]
1|23009|Loss: 0.8552048206329346:  89%|████████▉ | 23009/25880 [4:41:42<35:43,  1.34it/s]
1|23010|Loss: 0.784124493598938:  89%|████████▉ | 23009/25880 [4:41:43<35:43,  1.34it/s] 
1|23010|Loss: 0.784124493598938:  89%|████████▉ | 23010/25880 [4:41:43<34:14,  1.40it/s]
1|23011|Loss: 0.8306374549865723:  89%|████████▉ | 23010/25880 [4:41:43<34:14,  1.40it/s]
1|23011|Loss: 0.8306374549865723:  89%|████████▉ | 23011/25880 [4:41:44<34:08,  1.40it/s]
1|23012|Loss: 0.8767098188400269:  89%|████████▉ | 23011/25880 [4:41:44<34:08,  1.40it/s]
1|23012|Loss: 0.8767098188400269:  89%|████████▉ | 23012/25880 [4:41:44<32:04,  1.49it/s]
1|23013|Loss: 0.8788461089134216:  89%|████████▉ | 23012/25880 [4:41:45<32:04,  1.49it/s]
1|23013|Loss: 0.8788461089134216:  89%|████████▉ | 23013/25880 [4:41:45<31:57,  1.49it/s]
1|23014|Loss: 0.811769962310791:  89%|████████▉ | 23013/25880 [4:41:45<31:57,  1.49it/s] 
1|23014|Loss: 0.811769962310791:  89%|████████▉ | 23014/25880 [4:41:46<32:43,  1.46it/s]
1|23015|Loss: 0.8274538516998291:  89%|████████▉ | 23014/25880 [4:41:46<32:43,  1.46it/s]
1|23015|Loss: 0.8274538516998291:  89%|████████▉ | 23015/25880 [4:41:46<33:08,  1.44it/s]
1|23016|Loss: 0.7262768149375916:  89%|████████▉ | 23015/25880 [4:41:47<33:08,  1.44it/s]
1|23016|Loss: 0.7262768149375916:  89%|████████▉ | 23016/25880 [4:41:47<37:53,  1.26it/s]
1|23017|Loss: 0.8523344397544861:  89%|████████▉ | 23016/25880 [4:41:48<37:53,  1.26it/s]
1|23017|Loss: 0.8523344397544861:  89%|████████▉ | 23017/25880 [4:41:48<38:50,  1.23it/s]
1|23018|Loss: 0.791658878326416:  89%|████████▉ | 23017/25880 [4:41:49<38:50,  1.23it/s] 
1|23018|Loss: 0.791658878326416:  89%|████████▉ | 23018/25880 [4:41:49<38:27,  1.24it/s]
1|23019|Loss: 0.8782396912574768:  89%|████████▉ | 23018/25880 [4:41:49<38:27,  1.24it/s]
1|23019|Loss: 0.8782396912574768:  89%|████████▉ | 23019/25880 [4:41:50<35:48,  1.33it/s]
1|23020|Loss: 0.7510981559753418:  89%|████████▉ | 23019/25880 [4:41:50<35:48,  1.33it/s]
1|23020|Loss: 0.7510981559753418:  89%|████████▉ | 23020/25880 [4:41:50<36:11,  1.32it/s]
1|23021|Loss: 0.8472739458084106:  89%|████████▉ | 23020/25880 [4:41:51<36:11,  1.32it/s]
1|23021|Loss: 0.8472739458084106:  89%|████████▉ | 23021/25880 [4:41:51<37:06,  1.28it/s]
1|23022|Loss: 0.7855687141418457:  89%|████████▉ | 23021/25880 [4:41:52<37:06,  1.28it/s]
1|23022|Loss: 0.7855687141418457:  89%|████████▉ | 23022/25880 [4:41:52<36:36,  1.30it/s]
1|23023|Loss: 0.8383265137672424:  89%|████████▉ | 23022/25880 [4:41:52<36:36,  1.30it/s]
1|23023|Loss: 0.8383265137672424:  89%|████████▉ | 23023/25880 [4:41:53<36:09,  1.32it/s]
1|23024|Loss: 0.8899787664413452:  89%|████████▉ | 23023/25880 [4:41:53<36:09,  1.32it/s]
1|23024|Loss: 0.8899787664413452:  89%|████████▉ | 23024/25880 [4:41:53<33:16,  1.43it/s]
1|23025|Loss: 0.9270821213722229:  89%|████████▉ | 23024/25880 [4:41:54<33:16,  1.43it/s]
1|23025|Loss: 0.9270821213722229:  89%|████████▉ | 23025/25880 [4:41:54<34:21,  1.38it/s]
1|23026|Loss: 0.7516864538192749:  89%|████████▉ | 23025/25880 [4:41:54<34:21,  1.38it/s]
1|23026|Loss: 0.7516864538192749:  89%|████████▉ | 23026/25880 [4:41:55<34:56,  1.36it/s]
1|23027|Loss: 0.728147566318512:  89%|████████▉ | 23026/25880 [4:41:55<34:56,  1.36it/s] 
1|23027|Loss: 0.728147566318512:  89%|████████▉ | 23027/25880 [4:41:56<35:58,  1.32it/s]
1|23028|Loss: 0.8317137360572815:  89%|████████▉ | 23027/25880 [4:41:56<35:58,  1.32it/s]
1|23028|Loss: 0.8317137360572815:  89%|████████▉ | 23028/25880 [4:41:56<37:17,  1.27it/s]
1|23029|Loss: 0.7824665307998657:  89%|████████▉ | 23028/25880 [4:41:57<37:17,  1.27it/s]
1|23029|Loss: 0.7824665307998657:  89%|████████▉ | 23029/25880 [4:41:57<36:33,  1.30it/s]
1|23030|Loss: 0.825654923915863:  89%|████████▉ | 23029/25880 [4:41:58<36:33,  1.30it/s] 
1|23030|Loss: 0.825654923915863:  89%|████████▉ | 23030/25880 [4:41:58<35:54,  1.32it/s]
1|23031|Loss: 0.8790731430053711:  89%|████████▉ | 23030/25880 [4:41:58<35:54,  1.32it/s]
1|23031|Loss: 0.8790731430053711:  89%|████████▉ | 23031/25880 [4:41:59<36:10,  1.31it/s]
1|23032|Loss: 0.8545311689376831:  89%|████████▉ | 23031/25880 [4:41:59<36:10,  1.31it/s]
1|23032|Loss: 0.8545311689376831:  89%|████████▉ | 23032/25880 [4:41:59<35:54,  1.32it/s]
1|23033|Loss: 0.7543452978134155:  89%|████████▉ | 23032/25880 [4:42:00<35:54,  1.32it/s]
1|23033|Loss: 0.7543452978134155:  89%|████████▉ | 23033/25880 [4:42:00<36:40,  1.29it/s]
1|23034|Loss: 0.72574782371521:  89%|████████▉ | 23033/25880 [4:42:01<36:40,  1.29it/s]  
1|23034|Loss: 0.72574782371521:  89%|████████▉ | 23034/25880 [4:42:01<38:31,  1.23it/s]
1|23035|Loss: 0.9056954979896545:  89%|████████▉ | 23034/25880 [4:42:02<38:31,  1.23it/s]
1|23035|Loss: 0.9056954979896545:  89%|████████▉ | 23035/25880 [4:42:02<40:52,  1.16it/s]
1|23036|Loss: 0.7397830486297607:  89%|████████▉ | 23035/25880 [4:42:03<40:52,  1.16it/s]
1|23036|Loss: 0.7397830486297607:  89%|████████▉ | 23036/25880 [4:42:03<38:48,  1.22it/s]
1|23037|Loss: 0.7410125136375427:  89%|████████▉ | 23036/25880 [4:42:03<38:48,  1.22it/s]
1|23037|Loss: 0.7410125136375427:  89%|████████▉ | 23037/25880 [4:42:03<36:02,  1.31it/s]
1|23038|Loss: 0.7528368830680847:  89%|████████▉ | 23037/25880 [4:42:04<36:02,  1.31it/s]
1|23038|Loss: 0.7528368830680847:  89%|████████▉ | 23038/25880 [4:42:04<37:01,  1.28it/s]
1|23039|Loss: 0.7717416882514954:  89%|████████▉ | 23038/25880 [4:42:05<37:01,  1.28it/s]
1|23039|Loss: 0.7717416882514954:  89%|████████▉ | 23039/25880 [4:42:05<36:56,  1.28it/s]
1|23040|Loss: 1.2068911790847778:  89%|████████▉ | 23039/25880 [4:42:06<36:56,  1.28it/s]
1|23040|Loss: 1.2068911790847778:  89%|████████▉ | 23040/25880 [4:42:06<37:40,  1.26it/s]
1|23041|Loss: 0.7693607211112976:  89%|████████▉ | 23040/25880 [4:42:06<37:40,  1.26it/s]
1|23041|Loss: 0.7693607211112976:  89%|████████▉ | 23041/25880 [4:42:07<37:16,  1.27it/s]
1|23042|Loss: 0.7091825604438782:  89%|████████▉ | 23041/25880 [4:42:07<37:16,  1.27it/s]
1|23042|Loss: 0.7091825604438782:  89%|████████▉ | 23042/25880 [4:42:07<35:18,  1.34it/s]
1|23043|Loss: 0.9089707732200623:  89%|████████▉ | 23042/25880 [4:42:08<35:18,  1.34it/s]
1|23043|Loss: 0.9089707732200623:  89%|████████▉ | 23043/25880 [4:42:08<34:47,  1.36it/s]
1|23044|Loss: 0.7138970494270325:  89%|████████▉ | 23043/25880 [4:42:08<34:47,  1.36it/s]
1|23044|Loss: 0.7138970494270325:  89%|████████▉ | 23044/25880 [4:42:09<34:46,  1.36it/s]
1|23045|Loss: 0.8355238437652588:  89%|████████▉ | 23044/25880 [4:42:09<34:46,  1.36it/s]
1|23045|Loss: 0.8355238437652588:  89%|████████▉ | 23045/25880 [4:42:10<34:54,  1.35it/s]
1|23046|Loss: 0.8036066293716431:  89%|████████▉ | 23045/25880 [4:42:10<34:54,  1.35it/s]
1|23046|Loss: 0.8036066293716431:  89%|████████▉ | 23046/25880 [4:42:10<33:14,  1.42it/s]
1|23047|Loss: 0.8553820252418518:  89%|████████▉ | 23046/25880 [4:42:11<33:14,  1.42it/s]
1|23047|Loss: 0.8553820252418518:  89%|████████▉ | 23047/25880 [4:42:11<34:23,  1.37it/s]
1|23048|Loss: 0.7200396656990051:  89%|████████▉ | 23047/25880 [4:42:11<34:23,  1.37it/s]
1|23048|Loss: 0.7200396656990051:  89%|████████▉ | 23048/25880 [4:42:11<30:35,  1.54it/s]
1|23049|Loss: 0.873229444026947:  89%|████████▉ | 23048/25880 [4:42:12<30:35,  1.54it/s] 
1|23049|Loss: 0.873229444026947:  89%|████████▉ | 23049/25880 [4:42:12<29:54,  1.58it/s]
1|23050|Loss: 0.8935494422912598:  89%|████████▉ | 23049/25880 [4:42:12<29:54,  1.58it/s]
1|23050|Loss: 0.8935494422912598:  89%|████████▉ | 23050/25880 [4:42:13<32:11,  1.46it/s]
1|23051|Loss: 0.8307061791419983:  89%|████████▉ | 23050/25880 [4:42:13<32:11,  1.46it/s]
1|23051|Loss: 0.8307061791419983:  89%|████████▉ | 23051/25880 [4:42:14<34:11,  1.38it/s]
1|23052|Loss: 0.7259562015533447:  89%|████████▉ | 23051/25880 [4:42:14<34:11,  1.38it/s]
1|23052|Loss: 0.7259562015533447:  89%|████████▉ | 23052/25880 [4:42:14<35:39,  1.32it/s]
1|23053|Loss: 0.870612621307373:  89%|████████▉ | 23052/25880 [4:42:15<35:39,  1.32it/s] 
1|23053|Loss: 0.870612621307373:  89%|████████▉ | 23053/25880 [4:42:15<35:13,  1.34it/s]
1|23054|Loss: 0.7300880551338196:  89%|████████▉ | 23053/25880 [4:42:16<35:13,  1.34it/s]
1|23054|Loss: 0.7300880551338196:  89%|████████▉ | 23054/25880 [4:42:16<38:32,  1.22it/s]
1|23055|Loss: 0.7589860558509827:  89%|████████▉ | 23054/25880 [4:42:17<38:32,  1.22it/s]
1|23055|Loss: 0.7589860558509827:  89%|████████▉ | 23055/25880 [4:42:17<37:50,  1.24it/s]
1|23056|Loss: 0.7290639281272888:  89%|████████▉ | 23055/25880 [4:42:17<37:50,  1.24it/s]
1|23056|Loss: 0.7290639281272888:  89%|████████▉ | 23056/25880 [4:42:17<34:25,  1.37it/s]
1|23057|Loss: 0.7773827314376831:  89%|████████▉ | 23056/25880 [4:42:18<34:25,  1.37it/s]
1|23057|Loss: 0.7773827314376831:  89%|████████▉ | 23057/25880 [4:42:18<33:48,  1.39it/s]
1|23058|Loss: 0.7337216734886169:  89%|████████▉ | 23057/25880 [4:42:19<33:48,  1.39it/s]
1|23058|Loss: 0.7337216734886169:  89%|████████▉ | 23058/25880 [4:42:19<32:56,  1.43it/s]
1|23059|Loss: 0.9435098767280579:  89%|████████▉ | 23058/25880 [4:42:19<32:56,  1.43it/s]
1|23059|Loss: 0.9435098767280579:  89%|████████▉ | 23059/25880 [4:42:20<35:43,  1.32it/s]
1|23060|Loss: 0.9707984328269958:  89%|████████▉ | 23059/25880 [4:42:20<35:43,  1.32it/s]
1|23060|Loss: 0.9707984328269958:  89%|████████▉ | 23060/25880 [4:42:21<38:05,  1.23it/s]
1|23061|Loss: 0.7921444773674011:  89%|████████▉ | 23060/25880 [4:42:21<38:05,  1.23it/s]
1|23061|Loss: 0.7921444773674011:  89%|████████▉ | 23061/25880 [4:42:21<36:25,  1.29it/s]
1|23062|Loss: 0.8187793493270874:  89%|████████▉ | 23061/25880 [4:42:22<36:25,  1.29it/s]
1|23062|Loss: 0.8187793493270874:  89%|████████▉ | 23062/25880 [4:42:22<34:16,  1.37it/s]
1|23063|Loss: 0.8363181352615356:  89%|████████▉ | 23062/25880 [4:42:22<34:16,  1.37it/s]
1|23063|Loss: 0.8363181352615356:  89%|████████▉ | 23063/25880 [4:42:23<32:18,  1.45it/s]
1|23064|Loss: 0.9112749695777893:  89%|████████▉ | 23063/25880 [4:42:23<32:18,  1.45it/s]
1|23064|Loss: 0.9112749695777893:  89%|████████▉ | 23064/25880 [4:42:23<33:48,  1.39it/s]
1|23065|Loss: 0.9381030797958374:  89%|████████▉ | 23064/25880 [4:42:24<33:48,  1.39it/s]
1|23065|Loss: 0.9381030797958374:  89%|████████▉ | 23065/25880 [4:42:24<34:16,  1.37it/s]
1|23066|Loss: 0.8650334477424622:  89%|████████▉ | 23065/25880 [4:42:25<34:16,  1.37it/s]
1|23066|Loss: 0.8650334477424622:  89%|████████▉ | 23066/25880 [4:42:25<34:28,  1.36it/s]
1|23067|Loss: 0.8787215352058411:  89%|████████▉ | 23066/25880 [4:42:25<34:28,  1.36it/s]
1|23067|Loss: 0.8787215352058411:  89%|████████▉ | 23067/25880 [4:42:25<32:51,  1.43it/s]
1|23068|Loss: 0.940207302570343:  89%|████████▉ | 23067/25880 [4:42:26<32:51,  1.43it/s] 
1|23068|Loss: 0.940207302570343:  89%|████████▉ | 23068/25880 [4:42:26<33:00,  1.42it/s]
1|23069|Loss: 0.8039308786392212:  89%|████████▉ | 23068/25880 [4:42:27<33:00,  1.42it/s]
1|23069|Loss: 0.8039308786392212:  89%|████████▉ | 23069/25880 [4:42:27<33:11,  1.41it/s]
1|23070|Loss: 0.8446255326271057:  89%|████████▉ | 23069/25880 [4:42:27<33:11,  1.41it/s]
1|23070|Loss: 0.8446255326271057:  89%|████████▉ | 23070/25880 [4:42:28<33:27,  1.40it/s]
1|23071|Loss: 0.8018866777420044:  89%|████████▉ | 23070/25880 [4:42:28<33:27,  1.40it/s]
1|23071|Loss: 0.8018866777420044:  89%|████████▉ | 23071/25880 [4:42:28<33:49,  1.38it/s]
1|23072|Loss: 0.7753955721855164:  89%|████████▉ | 23071/25880 [4:42:29<33:49,  1.38it/s]
1|23072|Loss: 0.7753955721855164:  89%|████████▉ | 23072/25880 [4:42:29<31:43,  1.48it/s]
1|23073|Loss: 0.9775938987731934:  89%|████████▉ | 23072/25880 [4:42:29<31:43,  1.48it/s]
1|23073|Loss: 0.9775938987731934:  89%|████████▉ | 23073/25880 [4:42:30<33:10,  1.41it/s]
1|23074|Loss: 0.6963737607002258:  89%|████████▉ | 23073/25880 [4:42:30<33:10,  1.41it/s]
1|23074|Loss: 0.6963737607002258:  89%|████████▉ | 23074/25880 [4:42:30<33:48,  1.38it/s]
1|23075|Loss: 0.9683262705802917:  89%|████████▉ | 23074/25880 [4:42:31<33:48,  1.38it/s]
1|23075|Loss: 0.9683262705802917:  89%|████████▉ | 23075/25880 [4:42:31<34:01,  1.37it/s]
1|23076|Loss: 0.7966105937957764:  89%|████████▉ | 23075/25880 [4:42:32<34:01,  1.37it/s]
1|23076|Loss: 0.7966105937957764:  89%|████████▉ | 23076/25880 [4:42:32<34:23,  1.36it/s]
1|23077|Loss: 0.8531392216682434:  89%|████████▉ | 23076/25880 [4:42:32<34:23,  1.36it/s]
1|23077|Loss: 0.8531392216682434:  89%|████████▉ | 23077/25880 [4:42:33<34:21,  1.36it/s]
1|23078|Loss: 0.8492531180381775:  89%|████████▉ | 23077/25880 [4:42:33<34:21,  1.36it/s]
1|23078|Loss: 0.8492531180381775:  89%|████████▉ | 23078/25880 [4:42:34<36:54,  1.27it/s]
1|23079|Loss: 0.8609380722045898:  89%|████████▉ | 23078/25880 [4:42:34<36:54,  1.27it/s]
1|23079|Loss: 0.8609380722045898:  89%|████████▉ | 23079/25880 [4:42:35<38:13,  1.22it/s]
1|23080|Loss: 0.7951639890670776:  89%|████████▉ | 23079/25880 [4:42:35<38:13,  1.22it/s]
1|23080|Loss: 0.7951639890670776:  89%|████████▉ | 23080/25880 [4:42:35<37:07,  1.26it/s]
1|23081|Loss: 0.7237992286682129:  89%|████████▉ | 23080/25880 [4:42:36<37:07,  1.26it/s]
1|23081|Loss: 0.7237992286682129:  89%|████████▉ | 23081/25880 [4:42:36<35:03,  1.33it/s]
1|23082|Loss: 0.8801786303520203:  89%|████████▉ | 23081/25880 [4:42:36<35:03,  1.33it/s]
1|23082|Loss: 0.8801786303520203:  89%|████████▉ | 23082/25880 [4:42:37<34:20,  1.36it/s]
1|23083|Loss: 0.7031883597373962:  89%|████████▉ | 23082/25880 [4:42:37<34:20,  1.36it/s]
1|23083|Loss: 0.7031883597373962:  89%|████████▉ | 23083/25880 [4:42:37<34:25,  1.35it/s]
1|23084|Loss: 0.872981607913971:  89%|████████▉ | 23083/25880 [4:42:38<34:25,  1.35it/s] 
1|23084|Loss: 0.872981607913971:  89%|████████▉ | 23084/25880 [4:42:38<35:36,  1.31it/s]
1|23085|Loss: 0.8332400918006897:  89%|████████▉ | 23084/25880 [4:42:39<35:36,  1.31it/s]
1|23085|Loss: 0.8332400918006897:  89%|████████▉ | 23085/25880 [4:42:39<34:25,  1.35it/s]
1|23086|Loss: 0.8174794316291809:  89%|████████▉ | 23085/25880 [4:42:39<34:25,  1.35it/s]
1|23086|Loss: 0.8174794316291809:  89%|████████▉ | 23086/25880 [4:42:39<31:01,  1.50it/s]
1|23087|Loss: 0.8631973266601562:  89%|████████▉ | 23086/25880 [4:42:40<31:01,  1.50it/s]
1|23087|Loss: 0.8631973266601562:  89%|████████▉ | 23087/25880 [4:42:40<31:07,  1.50it/s]
1|23088|Loss: 0.7994379997253418:  89%|████████▉ | 23087/25880 [4:42:40<31:07,  1.50it/s]
1|23088|Loss: 0.7994379997253418:  89%|████████▉ | 23088/25880 [4:42:41<34:18,  1.36it/s]
1|23089|Loss: 0.8150408864021301:  89%|████████▉ | 23088/25880 [4:42:41<34:18,  1.36it/s]
1|23089|Loss: 0.8150408864021301:  89%|████████▉ | 23089/25880 [4:42:42<34:44,  1.34it/s]
1|23090|Loss: 0.9195341467857361:  89%|████████▉ | 23089/25880 [4:42:42<34:44,  1.34it/s]
1|23090|Loss: 0.9195341467857361:  89%|████████▉ | 23090/25880 [4:42:42<35:12,  1.32it/s]
1|23091|Loss: 0.8945755958557129:  89%|████████▉ | 23090/25880 [4:42:43<35:12,  1.32it/s]
1|23091|Loss: 0.8945755958557129:  89%|████████▉ | 23091/25880 [4:42:43<35:02,  1.33it/s]
1|23092|Loss: 0.7686612606048584:  89%|████████▉ | 23091/25880 [4:42:44<35:02,  1.33it/s]
1|23092|Loss: 0.7686612606048584:  89%|████████▉ | 23092/25880 [4:42:44<34:21,  1.35it/s]
1|23093|Loss: 0.8462256193161011:  89%|████████▉ | 23092/25880 [4:42:44<34:21,  1.35it/s]
1|23093|Loss: 0.8462256193161011:  89%|████████▉ | 23093/25880 [4:42:45<35:48,  1.30it/s]
1|23094|Loss: 0.9098061919212341:  89%|████████▉ | 23093/25880 [4:42:45<35:48,  1.30it/s]
1|23094|Loss: 0.9098061919212341:  89%|████████▉ | 23094/25880 [4:42:45<34:30,  1.35it/s]
1|23095|Loss: 0.7635114789009094:  89%|████████▉ | 23094/25880 [4:42:46<34:30,  1.35it/s]
1|23095|Loss: 0.7635114789009094:  89%|████████▉ | 23095/25880 [4:42:46<32:46,  1.42it/s]
1|23096|Loss: 0.7654309272766113:  89%|████████▉ | 23095/25880 [4:42:46<32:46,  1.42it/s]
1|23096|Loss: 0.7654309272766113:  89%|████████▉ | 23096/25880 [4:42:47<33:58,  1.37it/s]
1|23097|Loss: 0.8478965163230896:  89%|████████▉ | 23096/25880 [4:42:47<33:58,  1.37it/s]
1|23097|Loss: 0.8478965163230896:  89%|████████▉ | 23097/25880 [4:42:48<35:29,  1.31it/s]
1|23098|Loss: 0.8646071553230286:  89%|████████▉ | 23097/25880 [4:42:48<35:29,  1.31it/s]
1|23098|Loss: 0.8646071553230286:  89%|████████▉ | 23098/25880 [4:42:48<35:01,  1.32it/s]
1|23099|Loss: 0.8208302855491638:  89%|████████▉ | 23098/25880 [4:42:49<35:01,  1.32it/s]
1|23099|Loss: 0.8208302855491638:  89%|████████▉ | 23099/25880 [4:42:49<34:26,  1.35it/s]
1|23100|Loss: 0.8100452423095703:  89%|████████▉ | 23099/25880 [4:42:50<34:26,  1.35it/s]
1|23100|Loss: 0.8100452423095703:  89%|████████▉ | 23100/25880 [4:42:50<34:26,  1.35it/s]
1|23101|Loss: 0.8857244849205017:  89%|████████▉ | 23100/25880 [4:42:50<34:26,  1.35it/s]
1|23101|Loss: 0.8857244849205017:  89%|████████▉ | 23101/25880 [4:42:51<32:38,  1.42it/s]
1|23102|Loss: 0.7664673328399658:  89%|████████▉ | 23101/25880 [4:42:51<32:38,  1.42it/s]
1|23102|Loss: 0.7664673328399658:  89%|████████▉ | 23102/25880 [4:42:51<30:30,  1.52it/s]
1|23103|Loss: 0.8757898211479187:  89%|████████▉ | 23102/25880 [4:42:51<30:30,  1.52it/s]
1|23103|Loss: 0.8757898211479187:  89%|████████▉ | 23103/25880 [4:42:52<29:40,  1.56it/s]
1|23104|Loss: 0.7233115434646606:  89%|████████▉ | 23103/25880 [4:42:52<29:40,  1.56it/s]
1|23104|Loss: 0.7233115434646606:  89%|████████▉ | 23104/25880 [4:42:52<30:36,  1.51it/s]
1|23105|Loss: 0.8707707524299622:  89%|████████▉ | 23104/25880 [4:42:53<30:36,  1.51it/s]
1|23105|Loss: 0.8707707524299622:  89%|████████▉ | 23105/25880 [4:42:53<31:10,  1.48it/s]
1|23106|Loss: 0.8590558767318726:  89%|████████▉ | 23105/25880 [4:42:53<31:10,  1.48it/s]
1|23106|Loss: 0.8590558767318726:  89%|████████▉ | 23106/25880 [4:42:54<30:50,  1.50it/s]
1|23107|Loss: 0.7647398114204407:  89%|████████▉ | 23106/25880 [4:42:54<30:50,  1.50it/s]
1|23107|Loss: 0.7647398114204407:  89%|████████▉ | 23107/25880 [4:42:55<33:28,  1.38it/s]
1|23108|Loss: 0.6410073041915894:  89%|████████▉ | 23107/25880 [4:42:55<33:28,  1.38it/s]
1|23108|Loss: 0.6410073041915894:  89%|████████▉ | 23108/25880 [4:42:55<34:46,  1.33it/s]
1|23109|Loss: 0.7439399361610413:  89%|████████▉ | 23108/25880 [4:42:56<34:46,  1.33it/s]
1|23109|Loss: 0.7439399361610413:  89%|████████▉ | 23109/25880 [4:42:56<34:11,  1.35it/s]
1|23110|Loss: 0.8110209107398987:  89%|████████▉ | 23109/25880 [4:42:57<34:11,  1.35it/s]
1|23110|Loss: 0.8110209107398987:  89%|████████▉ | 23110/25880 [4:42:57<34:33,  1.34it/s]
1|23111|Loss: 0.8238325119018555:  89%|████████▉ | 23110/25880 [4:42:57<34:33,  1.34it/s]
1|23111|Loss: 0.8238325119018555:  89%|████████▉ | 23111/25880 [4:42:58<35:09,  1.31it/s]
1|23112|Loss: 0.8295602202415466:  89%|████████▉ | 23111/25880 [4:42:58<35:09,  1.31it/s]
1|23112|Loss: 0.8295602202415466:  89%|████████▉ | 23112/25880 [4:42:58<36:02,  1.28it/s]
1|23113|Loss: 0.895000696182251:  89%|████████▉ | 23112/25880 [4:42:59<36:02,  1.28it/s] 
1|23113|Loss: 0.895000696182251:  89%|████████▉ | 23113/25880 [4:42:59<36:16,  1.27it/s]
1|23114|Loss: 1.0533826351165771:  89%|████████▉ | 23113/25880 [4:43:00<36:16,  1.27it/s]
1|23114|Loss: 1.0533826351165771:  89%|████████▉ | 23114/25880 [4:43:00<34:04,  1.35it/s]
1|23115|Loss: 0.8681454658508301:  89%|████████▉ | 23114/25880 [4:43:00<34:04,  1.35it/s]
1|23115|Loss: 0.8681454658508301:  89%|████████▉ | 23115/25880 [4:43:01<34:35,  1.33it/s]
1|23116|Loss: 0.8828836679458618:  89%|████████▉ | 23115/25880 [4:43:01<34:35,  1.33it/s]
1|23116|Loss: 0.8828836679458618:  89%|████████▉ | 23116/25880 [4:43:01<33:19,  1.38it/s]
1|23117|Loss: 0.8851189613342285:  89%|████████▉ | 23116/25880 [4:43:02<33:19,  1.38it/s]
1|23117|Loss: 0.8851189613342285:  89%|████████▉ | 23117/25880 [4:43:02<33:16,  1.38it/s]
1|23118|Loss: 0.6528230309486389:  89%|████████▉ | 23117/25880 [4:43:03<33:16,  1.38it/s]
1|23118|Loss: 0.6528230309486389:  89%|████████▉ | 23118/25880 [4:43:03<39:03,  1.18it/s]
1|23119|Loss: 0.7467542290687561:  89%|████████▉ | 23118/25880 [4:43:04<39:03,  1.18it/s]
1|23119|Loss: 0.7467542290687561:  89%|████████▉ | 23119/25880 [4:43:04<39:41,  1.16it/s]
1|23120|Loss: 0.889838695526123:  89%|████████▉ | 23119/25880 [4:43:05<39:41,  1.16it/s] 
1|23120|Loss: 0.889838695526123:  89%|████████▉ | 23120/25880 [4:43:05<38:45,  1.19it/s]
1|23121|Loss: 0.8040237426757812:  89%|████████▉ | 23120/25880 [4:43:05<38:45,  1.19it/s]
1|23121|Loss: 0.8040237426757812:  89%|████████▉ | 23121/25880 [4:43:06<38:15,  1.20it/s]
1|23122|Loss: 0.900046169757843:  89%|████████▉ | 23121/25880 [4:43:06<38:15,  1.20it/s] 
1|23122|Loss: 0.900046169757843:  89%|████████▉ | 23122/25880 [4:43:06<36:51,  1.25it/s]
1|23123|Loss: 0.8217927813529968:  89%|████████▉ | 23122/25880 [4:43:07<36:51,  1.25it/s]
1|23123|Loss: 0.8217927813529968:  89%|████████▉ | 23123/25880 [4:43:07<36:51,  1.25it/s]
1|23124|Loss: 0.8862432837486267:  89%|████████▉ | 23123/25880 [4:43:08<36:51,  1.25it/s]
1|23124|Loss: 0.8862432837486267:  89%|████████▉ | 23124/25880 [4:43:08<36:10,  1.27it/s]
1|23125|Loss: 0.8076052069664001:  89%|████████▉ | 23124/25880 [4:43:08<36:10,  1.27it/s]
1|23125|Loss: 0.8076052069664001:  89%|████████▉ | 23125/25880 [4:43:09<35:25,  1.30it/s]
1|23126|Loss: 0.925918698310852:  89%|████████▉ | 23125/25880 [4:43:09<35:25,  1.30it/s] 
1|23126|Loss: 0.925918698310852:  89%|████████▉ | 23126/25880 [4:43:09<35:07,  1.31it/s]
1|23127|Loss: 0.9968760013580322:  89%|████████▉ | 23126/25880 [4:43:10<35:07,  1.31it/s]
1|23127|Loss: 0.9968760013580322:  89%|████████▉ | 23127/25880 [4:43:10<35:31,  1.29it/s]
1|23128|Loss: 0.7697440981864929:  89%|████████▉ | 23127/25880 [4:43:11<35:31,  1.29it/s]
1|23128|Loss: 0.7697440981864929:  89%|████████▉ | 23128/25880 [4:43:11<36:20,  1.26it/s]
1|23129|Loss: 0.7061473727226257:  89%|████████▉ | 23128/25880 [4:43:11<36:20,  1.26it/s]
1|23129|Loss: 0.7061473727226257:  89%|████████▉ | 23129/25880 [4:43:12<33:23,  1.37it/s]
1|23130|Loss: 0.8091883659362793:  89%|████████▉ | 23129/25880 [4:43:12<33:23,  1.37it/s]
1|23130|Loss: 0.8091883659362793:  89%|████████▉ | 23130/25880 [4:43:12<34:09,  1.34it/s]
1|23131|Loss: 0.9044504761695862:  89%|████████▉ | 23130/25880 [4:43:13<34:09,  1.34it/s]
1|23131|Loss: 0.9044504761695862:  89%|████████▉ | 23131/25880 [4:43:13<35:43,  1.28it/s]
1|23132|Loss: 0.7800673246383667:  89%|████████▉ | 23131/25880 [4:43:14<35:43,  1.28it/s]
1|23132|Loss: 0.7800673246383667:  89%|████████▉ | 23132/25880 [4:43:14<37:32,  1.22it/s]
1|23133|Loss: 0.713668942451477:  89%|████████▉ | 23132/25880 [4:43:15<37:32,  1.22it/s] 
1|23133|Loss: 0.713668942451477:  89%|████████▉ | 23133/25880 [4:43:15<37:25,  1.22it/s]
1|23134|Loss: 0.8934808373451233:  89%|████████▉ | 23133/25880 [4:43:16<37:25,  1.22it/s]
1|23134|Loss: 0.8934808373451233:  89%|████████▉ | 23134/25880 [4:43:16<37:12,  1.23it/s]
1|23135|Loss: 0.8576632738113403:  89%|████████▉ | 23134/25880 [4:43:16<37:12,  1.23it/s]
1|23135|Loss: 0.8576632738113403:  89%|████████▉ | 23135/25880 [4:43:17<37:15,  1.23it/s]
1|23136|Loss: 0.942230761051178:  89%|████████▉ | 23135/25880 [4:43:17<37:15,  1.23it/s] 
1|23136|Loss: 0.942230761051178:  89%|████████▉ | 23136/25880 [4:43:17<35:55,  1.27it/s]
1|23137|Loss: 0.7711302042007446:  89%|████████▉ | 23136/25880 [4:43:18<35:55,  1.27it/s]
1|23137|Loss: 0.7711302042007446:  89%|████████▉ | 23137/25880 [4:43:18<32:52,  1.39it/s]
1|23138|Loss: 0.8093647360801697:  89%|████████▉ | 23137/25880 [4:43:18<32:52,  1.39it/s]
1|23138|Loss: 0.8093647360801697:  89%|████████▉ | 23138/25880 [4:43:19<32:33,  1.40it/s]
1|23139|Loss: 0.942872166633606:  89%|████████▉ | 23138/25880 [4:43:19<32:33,  1.40it/s] 
1|23139|Loss: 0.942872166633606:  89%|████████▉ | 23139/25880 [4:43:19<32:50,  1.39it/s]
1|23140|Loss: 0.6294354200363159:  89%|████████▉ | 23139/25880 [4:43:20<32:50,  1.39it/s]
1|23140|Loss: 0.6294354200363159:  89%|████████▉ | 23140/25880 [4:43:20<34:27,  1.33it/s]
1|23141|Loss: 0.9161340594291687:  89%|████████▉ | 23140/25880 [4:43:21<34:27,  1.33it/s]
1|23141|Loss: 0.9161340594291687:  89%|████████▉ | 23141/25880 [4:43:21<34:38,  1.32it/s]
1|23142|Loss: 0.9132390022277832:  89%|████████▉ | 23141/25880 [4:43:21<34:38,  1.32it/s]
1|23142|Loss: 0.9132390022277832:  89%|████████▉ | 23142/25880 [4:43:22<33:56,  1.34it/s]
1|23143|Loss: 0.9325470924377441:  89%|████████▉ | 23142/25880 [4:43:22<33:56,  1.34it/s]
1|23143|Loss: 0.9325470924377441:  89%|████████▉ | 23143/25880 [4:43:22<33:37,  1.36it/s]
1|23144|Loss: 0.818732738494873:  89%|████████▉ | 23143/25880 [4:43:23<33:37,  1.36it/s] 
1|23144|Loss: 0.818732738494873:  89%|████████▉ | 23144/25880 [4:43:23<35:34,  1.28it/s]
1|23145|Loss: 0.8526753783226013:  89%|████████▉ | 23144/25880 [4:43:24<35:34,  1.28it/s]
1|23145|Loss: 0.8526753783226013:  89%|████████▉ | 23145/25880 [4:43:24<36:00,  1.27it/s]
1|23146|Loss: 0.8126363754272461:  89%|████████▉ | 23145/25880 [4:43:25<36:00,  1.27it/s]
1|23146|Loss: 0.8126363754272461:  89%|████████▉ | 23146/25880 [4:43:25<34:25,  1.32it/s]
1|23147|Loss: 0.8317268490791321:  89%|████████▉ | 23146/25880 [4:43:25<34:25,  1.32it/s]
1|23147|Loss: 0.8317268490791321:  89%|████████▉ | 23147/25880 [4:43:26<33:54,  1.34it/s]
1|23148|Loss: 0.7961112856864929:  89%|████████▉ | 23147/25880 [4:43:26<33:54,  1.34it/s]
1|23148|Loss: 0.7961112856864929:  89%|████████▉ | 23148/25880 [4:43:26<35:13,  1.29it/s]
1|23149|Loss: 0.7527028918266296:  89%|████████▉ | 23148/25880 [4:43:27<35:13,  1.29it/s]
1|23149|Loss: 0.7527028918266296:  89%|████████▉ | 23149/25880 [4:43:27<35:51,  1.27it/s]
1|23150|Loss: 0.8544247150421143:  89%|████████▉ | 23149/25880 [4:43:28<35:51,  1.27it/s]
1|23150|Loss: 0.8544247150421143:  89%|████████▉ | 23150/25880 [4:43:28<32:09,  1.41it/s]
1|23151|Loss: 0.8988994359970093:  89%|████████▉ | 23150/25880 [4:43:28<32:09,  1.41it/s]
1|23151|Loss: 0.8988994359970093:  89%|████████▉ | 23151/25880 [4:43:28<32:53,  1.38it/s]
1|23152|Loss: 0.8361767530441284:  89%|████████▉ | 23151/25880 [4:43:29<32:53,  1.38it/s]
1|23152|Loss: 0.8361767530441284:  89%|████████▉ | 23152/25880 [4:43:29<34:40,  1.31it/s]
1|23153|Loss: 0.9162018299102783:  89%|████████▉ | 23152/25880 [4:43:30<34:40,  1.31it/s]
1|23153|Loss: 0.9162018299102783:  89%|████████▉ | 23153/25880 [4:43:30<33:25,  1.36it/s]
1|23154|Loss: 0.8731171488761902:  89%|████████▉ | 23153/25880 [4:43:30<33:25,  1.36it/s]
1|23154|Loss: 0.8731171488761902:  89%|████████▉ | 23154/25880 [4:43:31<31:28,  1.44it/s]
1|23155|Loss: 0.8886027336120605:  89%|████████▉ | 23154/25880 [4:43:31<31:28,  1.44it/s]
1|23155|Loss: 0.8886027336120605:  89%|████████▉ | 23155/25880 [4:43:31<32:42,  1.39it/s]
1|23156|Loss: 0.8098552823066711:  89%|████████▉ | 23155/25880 [4:43:32<32:42,  1.39it/s]
1|23156|Loss: 0.8098552823066711:  89%|████████▉ | 23156/25880 [4:43:32<33:45,  1.35it/s]
1|23157|Loss: 0.8608266711235046:  89%|████████▉ | 23156/25880 [4:43:33<33:45,  1.35it/s]
1|23157|Loss: 0.8608266711235046:  89%|████████▉ | 23157/25880 [4:43:33<32:47,  1.38it/s]
1|23158|Loss: 0.8243708610534668:  89%|████████▉ | 23157/25880 [4:43:33<32:47,  1.38it/s]
1|23158|Loss: 0.8243708610534668:  89%|████████▉ | 23158/25880 [4:43:34<32:35,  1.39it/s]
1|23159|Loss: 1.1097691059112549:  89%|████████▉ | 23158/25880 [4:43:34<32:35,  1.39it/s]
1|23159|Loss: 1.1097691059112549:  89%|████████▉ | 23159/25880 [4:43:34<32:44,  1.39it/s]
1|23160|Loss: 0.8779538869857788:  89%|████████▉ | 23159/25880 [4:43:35<32:44,  1.39it/s]
1|23160|Loss: 0.8779538869857788:  89%|████████▉ | 23160/25880 [4:43:35<31:47,  1.43it/s]
1|23161|Loss: 0.7242844104766846:  89%|████████▉ | 23160/25880 [4:43:35<31:47,  1.43it/s]
1|23161|Loss: 0.7242844104766846:  89%|████████▉ | 23161/25880 [4:43:36<30:56,  1.46it/s]
1|23162|Loss: 0.7974832653999329:  89%|████████▉ | 23161/25880 [4:43:36<30:56,  1.46it/s]
1|23162|Loss: 0.7974832653999329:  89%|████████▉ | 23162/25880 [4:43:36<31:06,  1.46it/s]
1|23163|Loss: 0.7624661326408386:  89%|████████▉ | 23162/25880 [4:43:37<31:06,  1.46it/s]
1|23163|Loss: 0.7624661326408386:  90%|████████▉ | 23163/25880 [4:43:37<30:20,  1.49it/s]
1|23164|Loss: 0.821523904800415:  90%|████████▉ | 23163/25880 [4:43:37<30:20,  1.49it/s] 
1|23164|Loss: 0.821523904800415:  90%|████████▉ | 23164/25880 [4:43:38<32:53,  1.38it/s]
1|23165|Loss: 0.7234351634979248:  90%|████████▉ | 23164/25880 [4:43:38<32:53,  1.38it/s]
1|23165|Loss: 0.7234351634979248:  90%|████████▉ | 23165/25880 [4:43:39<34:02,  1.33it/s]
1|23166|Loss: 0.8140551447868347:  90%|████████▉ | 23165/25880 [4:43:39<34:02,  1.33it/s]
1|23166|Loss: 0.8140551447868347:  90%|████████▉ | 23166/25880 [4:43:39<34:42,  1.30it/s]
1|23167|Loss: 0.8145602941513062:  90%|████████▉ | 23166/25880 [4:43:40<34:42,  1.30it/s]
1|23167|Loss: 0.8145602941513062:  90%|████████▉ | 23167/25880 [4:43:40<36:32,  1.24it/s]
1|23168|Loss: 0.7562454342842102:  90%|████████▉ | 23167/25880 [4:43:41<36:32,  1.24it/s]
1|23168|Loss: 0.7562454342842102:  90%|████████▉ | 23168/25880 [4:43:41<35:39,  1.27it/s]
1|23169|Loss: 0.9318441152572632:  90%|████████▉ | 23168/25880 [4:43:41<35:39,  1.27it/s]
1|23169|Loss: 0.9318441152572632:  90%|████████▉ | 23169/25880 [4:43:42<33:11,  1.36it/s]
1|23170|Loss: 0.8876708745956421:  90%|████████▉ | 23169/25880 [4:43:42<33:11,  1.36it/s]
1|23170|Loss: 0.8876708745956421:  90%|████████▉ | 23170/25880 [4:43:42<30:20,  1.49it/s]
1|23171|Loss: 0.7233566045761108:  90%|████████▉ | 23170/25880 [4:43:43<30:20,  1.49it/s]
1|23171|Loss: 0.7233566045761108:  90%|████████▉ | 23171/25880 [4:43:43<30:11,  1.50it/s]
1|23172|Loss: 0.7325316667556763:  90%|████████▉ | 23171/25880 [4:43:43<30:11,  1.50it/s]
1|23172|Loss: 0.7325316667556763:  90%|████████▉ | 23172/25880 [4:43:43<29:46,  1.52it/s]
1|23173|Loss: 0.766208291053772:  90%|████████▉ | 23172/25880 [4:43:44<29:46,  1.52it/s] 
1|23173|Loss: 0.766208291053772:  90%|████████▉ | 23173/25880 [4:43:44<30:38,  1.47it/s]
1|23174|Loss: 0.9688639044761658:  90%|████████▉ | 23173/25880 [4:43:45<30:38,  1.47it/s]
1|23174|Loss: 0.9688639044761658:  90%|████████▉ | 23174/25880 [4:43:45<33:04,  1.36it/s]
1|23175|Loss: 0.8522654175758362:  90%|████████▉ | 23174/25880 [4:43:45<33:04,  1.36it/s]
1|23175|Loss: 0.8522654175758362:  90%|████████▉ | 23175/25880 [4:43:46<30:31,  1.48it/s]
1|23176|Loss: 0.7769482731819153:  90%|████████▉ | 23175/25880 [4:43:46<30:31,  1.48it/s]
1|23176|Loss: 0.7769482731819153:  90%|████████▉ | 23176/25880 [4:43:46<31:18,  1.44it/s]
1|23177|Loss: 0.8064994215965271:  90%|████████▉ | 23176/25880 [4:43:47<31:18,  1.44it/s]
1|23177|Loss: 0.8064994215965271:  90%|████████▉ | 23177/25880 [4:43:47<34:07,  1.32it/s]
1|23178|Loss: 0.9669992923736572:  90%|████████▉ | 23177/25880 [4:43:48<34:07,  1.32it/s]
1|23178|Loss: 0.9669992923736572:  90%|████████▉ | 23178/25880 [4:43:48<34:21,  1.31it/s]
1|23179|Loss: 0.8153780102729797:  90%|████████▉ | 23178/25880 [4:43:48<34:21,  1.31it/s]
1|23179|Loss: 0.8153780102729797:  90%|████████▉ | 23179/25880 [4:43:49<30:53,  1.46it/s]
1|23180|Loss: 0.9160330295562744:  90%|████████▉ | 23179/25880 [4:43:49<30:53,  1.46it/s]
1|23180|Loss: 0.9160330295562744:  90%|████████▉ | 23180/25880 [4:43:49<30:44,  1.46it/s]
1|23181|Loss: 0.8178771138191223:  90%|████████▉ | 23180/25880 [4:43:50<30:44,  1.46it/s]
1|23181|Loss: 0.8178771138191223:  90%|████████▉ | 23181/25880 [4:43:50<31:12,  1.44it/s]
1|23182|Loss: 0.7705423831939697:  90%|████████▉ | 23181/25880 [4:43:50<31:12,  1.44it/s]
1|23182|Loss: 0.7705423831939697:  90%|████████▉ | 23182/25880 [4:43:51<31:33,  1.43it/s]
1|23183|Loss: 0.7508759498596191:  90%|████████▉ | 23182/25880 [4:43:51<31:33,  1.43it/s]
1|23183|Loss: 0.7508759498596191:  90%|████████▉ | 23183/25880 [4:43:51<33:10,  1.36it/s]
1|23184|Loss: 0.7164971232414246:  90%|████████▉ | 23183/25880 [4:43:52<33:10,  1.36it/s]
1|23184|Loss: 0.7164971232414246:  90%|████████▉ | 23184/25880 [4:43:52<33:11,  1.35it/s]
1|23185|Loss: 0.8065370321273804:  90%|████████▉ | 23184/25880 [4:43:53<33:11,  1.35it/s]
1|23185|Loss: 0.8065370321273804:  90%|████████▉ | 23185/25880 [4:43:53<31:33,  1.42it/s]
1|23186|Loss: 0.7264955043792725:  90%|████████▉ | 23185/25880 [4:43:53<31:33,  1.42it/s]
1|23186|Loss: 0.7264955043792725:  90%|████████▉ | 23186/25880 [4:43:53<30:28,  1.47it/s]
1|23187|Loss: 0.8558084964752197:  90%|████████▉ | 23186/25880 [4:43:54<30:28,  1.47it/s]
1|23187|Loss: 0.8558084964752197:  90%|████████▉ | 23187/25880 [4:43:54<30:52,  1.45it/s]
1|23188|Loss: 0.80033278465271:  90%|████████▉ | 23187/25880 [4:43:55<30:52,  1.45it/s]  
1|23188|Loss: 0.80033278465271:  90%|████████▉ | 23188/25880 [4:43:55<33:26,  1.34it/s]
1|23189|Loss: 0.760567307472229:  90%|████████▉ | 23188/25880 [4:43:55<33:26,  1.34it/s]
1|23189|Loss: 0.760567307472229:  90%|████████▉ | 23189/25880 [4:43:56<33:55,  1.32it/s]
1|23190|Loss: 0.7792376279830933:  90%|████████▉ | 23189/25880 [4:43:56<33:55,  1.32it/s]
1|23190|Loss: 0.7792376279830933:  90%|████████▉ | 23190/25880 [4:43:57<34:30,  1.30it/s]
1|23191|Loss: 0.916590690612793:  90%|████████▉ | 23190/25880 [4:43:57<34:30,  1.30it/s] 
1|23191|Loss: 0.916590690612793:  90%|████████▉ | 23191/25880 [4:43:57<33:52,  1.32it/s]
1|23192|Loss: 0.923607349395752:  90%|████████▉ | 23191/25880 [4:43:58<33:52,  1.32it/s]
1|23192|Loss: 0.923607349395752:  90%|████████▉ | 23192/25880 [4:43:58<33:01,  1.36it/s]
1|23193|Loss: 0.7410116195678711:  90%|████████▉ | 23192/25880 [4:43:58<33:01,  1.36it/s]
1|23193|Loss: 0.7410116195678711:  90%|████████▉ | 23193/25880 [4:43:59<31:55,  1.40it/s]
1|23194|Loss: 0.8199403285980225:  90%|████████▉ | 23193/25880 [4:43:59<31:55,  1.40it/s]
1|23194|Loss: 0.8199403285980225:  90%|████████▉ | 23194/25880 [4:43:59<31:57,  1.40it/s]
1|23195|Loss: 0.8779887557029724:  90%|████████▉ | 23194/25880 [4:44:00<31:57,  1.40it/s]
1|23195|Loss: 0.8779887557029724:  90%|████████▉ | 23195/25880 [4:44:00<32:10,  1.39it/s]
1|23196|Loss: 0.9328318238258362:  90%|████████▉ | 23195/25880 [4:44:01<32:10,  1.39it/s]
1|23196|Loss: 0.9328318238258362:  90%|████████▉ | 23196/25880 [4:44:01<33:03,  1.35it/s]
1|23197|Loss: 0.846733570098877:  90%|████████▉ | 23196/25880 [4:44:01<33:03,  1.35it/s] 
1|23197|Loss: 0.846733570098877:  90%|████████▉ | 23197/25880 [4:44:02<33:56,  1.32it/s]
1|23198|Loss: 0.9210770726203918:  90%|████████▉ | 23197/25880 [4:44:02<33:56,  1.32it/s]
1|23198|Loss: 0.9210770726203918:  90%|████████▉ | 23198/25880 [4:44:02<33:25,  1.34it/s]
1|23199|Loss: 0.9910096526145935:  90%|████████▉ | 23198/25880 [4:44:03<33:25,  1.34it/s]
1|23199|Loss: 0.9910096526145935:  90%|████████▉ | 23199/25880 [4:44:03<31:36,  1.41it/s]
1|23200|Loss: 0.7569360733032227:  90%|████████▉ | 23199/25880 [4:44:03<31:36,  1.41it/s]
1|23200|Loss: 0.7569360733032227:  90%|████████▉ | 23200/25880 [4:44:04<31:08,  1.43it/s]
1|23201|Loss: 0.894788384437561:  90%|████████▉ | 23200/25880 [4:44:04<31:08,  1.43it/s] 
1|23201|Loss: 0.894788384437561:  90%|████████▉ | 23201/25880 [4:44:04<31:11,  1.43it/s]
1|23202|Loss: 0.6861909627914429:  90%|████████▉ | 23201/25880 [4:44:05<31:11,  1.43it/s]
1|23202|Loss: 0.6861909627914429:  90%|████████▉ | 23202/25880 [4:44:05<30:14,  1.48it/s]
1|23203|Loss: 0.7614763379096985:  90%|████████▉ | 23202/25880 [4:44:05<30:14,  1.48it/s]
1|23203|Loss: 0.7614763379096985:  90%|████████▉ | 23203/25880 [4:44:06<31:54,  1.40it/s]
1|23204|Loss: 0.9174395203590393:  90%|████████▉ | 23203/25880 [4:44:06<31:54,  1.40it/s]
1|23204|Loss: 0.9174395203590393:  90%|████████▉ | 23204/25880 [4:44:07<32:39,  1.37it/s]
1|23205|Loss: 0.8228722810745239:  90%|████████▉ | 23204/25880 [4:44:07<32:39,  1.37it/s]
1|23205|Loss: 0.8228722810745239:  90%|████████▉ | 23205/25880 [4:44:07<34:02,  1.31it/s]
1|23206|Loss: 0.8625820875167847:  90%|████████▉ | 23205/25880 [4:44:08<34:02,  1.31it/s]
1|23206|Loss: 0.8625820875167847:  90%|████████▉ | 23206/25880 [4:44:08<33:43,  1.32it/s]
1|23207|Loss: 0.9271406531333923:  90%|████████▉ | 23206/25880 [4:44:09<33:43,  1.32it/s]
1|23207|Loss: 0.9271406531333923:  90%|████████▉ | 23207/25880 [4:44:09<34:00,  1.31it/s]
1|23208|Loss: 0.7887210249900818:  90%|████████▉ | 23207/25880 [4:44:09<34:00,  1.31it/s]
1|23208|Loss: 0.7887210249900818:  90%|████████▉ | 23208/25880 [4:44:10<32:47,  1.36it/s]
1|23209|Loss: 0.9656093716621399:  90%|████████▉ | 23208/25880 [4:44:10<32:47,  1.36it/s]
1|23209|Loss: 0.9656093716621399:  90%|████████▉ | 23209/25880 [4:44:10<30:22,  1.47it/s]
1|23210|Loss: 0.9117060899734497:  90%|████████▉ | 23209/25880 [4:44:11<30:22,  1.47it/s]
1|23210|Loss: 0.9117060899734497:  90%|████████▉ | 23210/25880 [4:44:11<30:28,  1.46it/s]
1|23211|Loss: 0.8685380816459656:  90%|████████▉ | 23210/25880 [4:44:11<30:28,  1.46it/s]
1|23211|Loss: 0.8685380816459656:  90%|████████▉ | 23211/25880 [4:44:12<32:23,  1.37it/s]
1|23212|Loss: 0.8201243877410889:  90%|████████▉ | 23211/25880 [4:44:12<32:23,  1.37it/s]
1|23212|Loss: 0.8201243877410889:  90%|████████▉ | 23212/25880 [4:44:13<33:56,  1.31it/s]
1|23213|Loss: 0.8102125525474548:  90%|████████▉ | 23212/25880 [4:44:13<33:56,  1.31it/s]
1|23213|Loss: 0.8102125525474548:  90%|████████▉ | 23213/25880 [4:44:13<34:31,  1.29it/s]
1|23214|Loss: 0.8489343523979187:  90%|████████▉ | 23213/25880 [4:44:14<34:31,  1.29it/s]
1|23214|Loss: 0.8489343523979187:  90%|████████▉ | 23214/25880 [4:44:14<31:40,  1.40it/s]
1|23215|Loss: 0.7111778259277344:  90%|████████▉ | 23214/25880 [4:44:14<31:40,  1.40it/s]
1|23215|Loss: 0.7111778259277344:  90%|████████▉ | 23215/25880 [4:44:15<30:52,  1.44it/s]
1|23216|Loss: 0.8702152967453003:  90%|████████▉ | 23215/25880 [4:44:15<30:52,  1.44it/s]
1|23216|Loss: 0.8702152967453003:  90%|████████▉ | 23216/25880 [4:44:15<32:00,  1.39it/s]
1|23217|Loss: 0.6505681276321411:  90%|████████▉ | 23216/25880 [4:44:16<32:00,  1.39it/s]
1|23217|Loss: 0.6505681276321411:  90%|████████▉ | 23217/25880 [4:44:16<33:34,  1.32it/s]
1|23218|Loss: 0.8390348553657532:  90%|████████▉ | 23217/25880 [4:44:17<33:34,  1.32it/s]
1|23218|Loss: 0.8390348553657532:  90%|████████▉ | 23218/25880 [4:44:17<35:05,  1.26it/s]
1|23219|Loss: 0.8066725134849548:  90%|████████▉ | 23218/25880 [4:44:18<35:05,  1.26it/s]
1|23219|Loss: 0.8066725134849548:  90%|████████▉ | 23219/25880 [4:44:18<34:42,  1.28it/s]
1|23220|Loss: 0.7140682935714722:  90%|████████▉ | 23219/25880 [4:44:18<34:42,  1.28it/s]
1|23220|Loss: 0.7140682935714722:  90%|████████▉ | 23220/25880 [4:44:18<32:30,  1.36it/s]
1|23221|Loss: 0.885103166103363:  90%|████████▉ | 23220/25880 [4:44:19<32:30,  1.36it/s] 
1|23221|Loss: 0.885103166103363:  90%|████████▉ | 23221/25880 [4:44:19<31:58,  1.39it/s]
1|23222|Loss: 0.952538788318634:  90%|████████▉ | 23221/25880 [4:44:20<31:58,  1.39it/s]
1|23222|Loss: 0.952538788318634:  90%|████████▉ | 23222/25880 [4:44:20<32:14,  1.37it/s]
1|23223|Loss: 0.8742045760154724:  90%|████████▉ | 23222/25880 [4:44:20<32:14,  1.37it/s]
1|23223|Loss: 0.8742045760154724:  90%|████████▉ | 23223/25880 [4:44:21<34:16,  1.29it/s]
1|23224|Loss: 0.9747928380966187:  90%|████████▉ | 23223/25880 [4:44:21<34:16,  1.29it/s]
1|23224|Loss: 0.9747928380966187:  90%|████████▉ | 23224/25880 [4:44:22<35:45,  1.24it/s]
1|23225|Loss: 0.7166310548782349:  90%|████████▉ | 23224/25880 [4:44:22<35:45,  1.24it/s]
1|23225|Loss: 0.7166310548782349:  90%|████████▉ | 23225/25880 [4:44:22<35:45,  1.24it/s]
1|23226|Loss: 0.7577134966850281:  90%|████████▉ | 23225/25880 [4:44:23<35:45,  1.24it/s]
1|23226|Loss: 0.7577134966850281:  90%|████████▉ | 23226/25880 [4:44:23<34:52,  1.27it/s]
1|23227|Loss: 0.7432880401611328:  90%|████████▉ | 23226/25880 [4:44:24<34:52,  1.27it/s]
1|23227|Loss: 0.7432880401611328:  90%|████████▉ | 23227/25880 [4:44:24<36:03,  1.23it/s]
1|23228|Loss: 0.9484872817993164:  90%|████████▉ | 23227/25880 [4:44:25<36:03,  1.23it/s]
1|23228|Loss: 0.9484872817993164:  90%|████████▉ | 23228/25880 [4:44:25<36:27,  1.21it/s]
1|23229|Loss: 0.7943898439407349:  90%|���███████▉ | 23228/25880 [4:44:25<36:27,  1.21it/s]
1|23229|Loss: 0.7943898439407349:  90%|████████▉ | 23229/25880 [4:44:26<36:00,  1.23it/s]
1|23230|Loss: 0.9151591658592224:  90%|████████▉ | 23229/25880 [4:44:26<36:00,  1.23it/s]
1|23230|Loss: 0.9151591658592224:  90%|████████▉ | 23230/25880 [4:44:26<34:45,  1.27it/s]
1|23231|Loss: 0.7978309988975525:  90%|████████▉ | 23230/25880 [4:44:27<34:45,  1.27it/s]
1|23231|Loss: 0.7978309988975525:  90%|████████▉ | 23231/25880 [4:44:27<32:55,  1.34it/s]
1|23232|Loss: 0.7475878000259399:  90%|████████▉ | 23231/25880 [4:44:28<32:55,  1.34it/s]
1|23232|Loss: 0.7475878000259399:  90%|████████▉ | 23232/25880 [4:44:28<33:02,  1.34it/s]
1|23233|Loss: 0.722819983959198:  90%|████████▉ | 23232/25880 [4:44:28<33:02,  1.34it/s] 
1|23233|Loss: 0.722819983959198:  90%|████████▉ | 23233/25880 [4:44:29<34:55,  1.26it/s]
1|23234|Loss: 0.8564256429672241:  90%|████████▉ | 23233/25880 [4:44:29<34:55,  1.26it/s]
1|23234|Loss: 0.8564256429672241:  90%|████████▉ | 23234/25880 [4:44:30<35:14,  1.25it/s]
1|23235|Loss: 0.7980785369873047:  90%|████████▉ | 23234/25880 [4:44:30<35:14,  1.25it/s]
1|23235|Loss: 0.7980785369873047:  90%|████████▉ | 23235/25880 [4:44:30<35:32,  1.24it/s]
1|23236|Loss: 0.8067699670791626:  90%|████████▉ | 23235/25880 [4:44:31<35:32,  1.24it/s]
1|23236|Loss: 0.8067699670791626:  90%|████████▉ | 23236/25880 [4:44:31<33:47,  1.30it/s]
1|23237|Loss: 0.9563804268836975:  90%|████████▉ | 23236/25880 [4:44:31<33:47,  1.30it/s]
1|23237|Loss: 0.9563804268836975:  90%|████████▉ | 23237/25880 [4:44:32<31:51,  1.38it/s]
1|23238|Loss: 0.7110246419906616:  90%|████████▉ | 23237/25880 [4:44:32<31:51,  1.38it/s]
1|23238|Loss: 0.7110246419906616:  90%|████████▉ | 23238/25880 [4:44:33<33:03,  1.33it/s]
1|23239|Loss: 0.8653671741485596:  90%|████████▉ | 23238/25880 [4:44:33<33:03,  1.33it/s]
1|23239|Loss: 0.8653671741485596:  90%|████████▉ | 23239/25880 [4:44:33<34:10,  1.29it/s]
1|23240|Loss: 0.9134376049041748:  90%|████████▉ | 23239/25880 [4:44:34<34:10,  1.29it/s]
1|23240|Loss: 0.9134376049041748:  90%|████████▉ | 23240/25880 [4:44:34<32:10,  1.37it/s]
1|23241|Loss: 0.8275508880615234:  90%|████████▉ | 23240/25880 [4:44:34<32:10,  1.37it/s]
1|23241|Loss: 0.8275508880615234:  90%|████████▉ | 23241/25880 [4:44:35<30:48,  1.43it/s]
1|23242|Loss: 0.9999477863311768:  90%|████████▉ | 23241/25880 [4:44:35<30:48,  1.43it/s]
1|23242|Loss: 0.9999477863311768:  90%|████████▉ | 23242/25880 [4:44:35<30:03,  1.46it/s]
1|23243|Loss: 0.8022384643554688:  90%|████████▉ | 23242/25880 [4:44:36<30:03,  1.46it/s]
1|23243|Loss: 0.8022384643554688:  90%|████████▉ | 23243/25880 [4:44:36<31:27,  1.40it/s]
1|23244|Loss: 0.8457976579666138:  90%|████████▉ | 23243/25880 [4:44:36<31:27,  1.40it/s]
1|23244|Loss: 0.8457976579666138:  90%|████████▉ | 23244/25880 [4:44:37<32:39,  1.35it/s]
1|23245|Loss: 0.8311066627502441:  90%|████████▉ | 23244/25880 [4:44:37<32:39,  1.35it/s]
1|23245|Loss: 0.8311066627502441:  90%|████████▉ | 23245/25880 [4:44:38<31:45,  1.38it/s]
1|23246|Loss: 0.8050730228424072:  90%|████████▉ | 23245/25880 [4:44:38<31:45,  1.38it/s]
1|23246|Loss: 0.8050730228424072:  90%|████████▉ | 23246/25880 [4:44:38<33:06,  1.33it/s]
1|23247|Loss: 0.7650940418243408:  90%|████████▉ | 23246/25880 [4:44:39<33:06,  1.33it/s]
1|23247|Loss: 0.7650940418243408:  90%|████████▉ | 23247/25880 [4:44:39<30:21,  1.45it/s]
1|23248|Loss: 0.8699927926063538:  90%|████████▉ | 23247/25880 [4:44:39<30:21,  1.45it/s]
1|23248|Loss: 0.8699927926063538:  90%|████████▉ | 23248/25880 [4:44:40<30:01,  1.46it/s]
1|23249|Loss: 0.8308210968971252:  90%|████████▉ | 23248/25880 [4:44:40<30:01,  1.46it/s]
1|23249|Loss: 0.8308210968971252:  90%|████████▉ | 23249/25880 [4:44:40<28:21,  1.55it/s]
1|23250|Loss: 0.8331562280654907:  90%|████████▉ | 23249/25880 [4:44:40<28:21,  1.55it/s]
1|23250|Loss: 0.8331562280654907:  90%|████████▉ | 23250/25880 [4:44:41<27:01,  1.62it/s]
1|23251|Loss: 0.8396531939506531:  90%|████████▉ | 23250/25880 [4:44:41<27:01,  1.62it/s]
1|23251|Loss: 0.8396531939506531:  90%|████████▉ | 23251/25880 [4:44:41<27:02,  1.62it/s]
1|23252|Loss: 0.842705488204956:  90%|████████▉ | 23251/25880 [4:44:42<27:02,  1.62it/s] 
1|23252|Loss: 0.842705488204956:  90%|████████▉ | 23252/25880 [4:44:42<26:55,  1.63it/s]
1|23253|Loss: 0.8092091083526611:  90%|████████▉ | 23252/25880 [4:44:42<26:55,  1.63it/s]
1|23253|Loss: 0.8092091083526611:  90%|████████▉ | 23253/25880 [4:44:42<25:09,  1.74it/s]
1|23254|Loss: 0.8373856544494629:  90%|████████▉ | 23253/25880 [4:44:43<25:09,  1.74it/s]
1|23254|Loss: 0.8373856544494629:  90%|████████▉ | 23254/25880 [4:44:43<27:27,  1.59it/s]
1|23255|Loss: 0.8526856303215027:  90%|████████▉ | 23254/25880 [4:44:43<27:27,  1.59it/s]
1|23255|Loss: 0.8526856303215027:  90%|████████▉ | 23255/25880 [4:44:44<26:44,  1.64it/s]
1|23256|Loss: 0.8122906684875488:  90%|████████▉ | 23255/25880 [4:44:44<26:44,  1.64it/s]
1|23256|Loss: 0.8122906684875488:  90%|████████▉ | 23256/25880 [4:44:44<28:53,  1.51it/s]
1|23257|Loss: 0.8231050372123718:  90%|████████▉ | 23256/25880 [4:44:45<28:53,  1.51it/s]
1|23257|Loss: 0.8231050372123718:  90%|████████▉ | 23257/25880 [4:44:45<29:50,  1.46it/s]
1|23258|Loss: 1.0627843141555786:  90%|████████▉ | 23257/25880 [4:44:46<29:50,  1.46it/s]
1|23258|Loss: 1.0627843141555786:  90%|████████▉ | 23258/25880 [4:44:46<31:18,  1.40it/s]
1|23259|Loss: 0.9017210602760315:  90%|████████▉ | 23258/25880 [4:44:46<31:18,  1.40it/s]
1|23259|Loss: 0.9017210602760315:  90%|████████▉ | 23259/25880 [4:44:47<34:13,  1.28it/s]
1|23260|Loss: 0.8549355268478394:  90%|████████▉ | 23259/25880 [4:44:47<34:13,  1.28it/s]
1|23260|Loss: 0.8549355268478394:  90%|████████▉ | 23260/25880 [4:44:48<34:57,  1.25it/s]
1|23261|Loss: 0.9022059440612793:  90%|████████▉ | 23260/25880 [4:44:48<34:57,  1.25it/s]
1|23261|Loss: 0.9022059440612793:  90%|████████▉ | 23261/25880 [4:44:48<33:10,  1.32it/s]
1|23262|Loss: 0.9962214827537537:  90%|████████▉ | 23261/25880 [4:44:49<33:10,  1.32it/s]
1|23262|Loss: 0.9962214827537537:  90%|████████▉ | 23262/25880 [4:44:49<35:06,  1.24it/s]
1|23263|Loss: 0.8082231879234314:  90%|████████▉ | 23262/25880 [4:44:50<35:06,  1.24it/s]
1|23263|Loss: 0.8082231879234314:  90%|████████▉ | 23263/25880 [4:44:50<36:20,  1.20it/s]
1|23264|Loss: 0.8008975386619568:  90%|████████▉ | 23263/25880 [4:44:51<36:20,  1.20it/s]
1|23264|Loss: 0.8008975386619568:  90%|████████▉ | 23264/25880 [4:44:51<35:36,  1.22it/s]
1|23265|Loss: 0.8331331610679626:  90%|████████▉ | 23264/25880 [4:44:51<35:36,  1.22it/s]
1|23265|Loss: 0.8331331610679626:  90%|████████▉ | 23265/25880 [4:44:52<32:15,  1.35it/s]
1|23266|Loss: 0.7087903618812561:  90%|████████▉ | 23265/25880 [4:44:52<32:15,  1.35it/s]
1|23266|Loss: 0.7087903618812561:  90%|████████▉ | 23266/25880 [4:44:52<34:01,  1.28it/s]
1|23267|Loss: 0.7960246205329895:  90%|████████▉ | 23266/25880 [4:44:53<34:01,  1.28it/s]
1|23267|Loss: 0.7960246205329895:  90%|████████▉ | 23267/25880 [4:44:53<33:39,  1.29it/s]
1|23268|Loss: 0.7826422452926636:  90%|████████▉ | 23267/25880 [4:44:54<33:39,  1.29it/s]
1|23268|Loss: 0.7826422452926636:  90%|████████▉ | 23268/25880 [4:44:54<33:05,  1.32it/s]
1|23269|Loss: 0.9615497589111328:  90%|████████▉ | 23268/25880 [4:44:54<33:05,  1.32it/s]
1|23269|Loss: 0.9615497589111328:  90%|████████▉ | 23269/25880 [4:44:55<32:28,  1.34it/s]
1|23270|Loss: 0.8077874779701233:  90%|████████▉ | 23269/25880 [4:44:55<32:28,  1.34it/s]
1|23270|Loss: 0.8077874779701233:  90%|████████▉ | 23270/25880 [4:44:55<31:11,  1.39it/s]
1|23271|Loss: 0.8366752862930298:  90%|████████▉ | 23270/25880 [4:44:56<31:11,  1.39it/s]
1|23271|Loss: 0.8366752862930298:  90%|████████▉ | 23271/25880 [4:44:56<31:11,  1.39it/s]
1|23272|Loss: 0.8051992654800415:  90%|████████▉ | 23271/25880 [4:44:56<31:11,  1.39it/s]
1|23272|Loss: 0.8051992654800415:  90%|████████▉ | 23272/25880 [4:44:57<33:00,  1.32it/s]
1|23273|Loss: 0.8329098224639893:  90%|████████▉ | 23272/25880 [4:44:57<33:00,  1.32it/s]
1|23273|Loss: 0.8329098224639893:  90%|████████▉ | 23273/25880 [4:44:58<34:12,  1.27it/s]
1|23274|Loss: 0.7659805417060852:  90%|████████▉ | 23273/25880 [4:44:58<34:12,  1.27it/s]
1|23274|Loss: 0.7659805417060852:  90%|████████▉ | 23274/25880 [4:44:58<32:45,  1.33it/s]
1|23275|Loss: 0.7155545353889465:  90%|████████▉ | 23274/25880 [4:44:59<32:45,  1.33it/s]
1|23275|Loss: 0.7155545353889465:  90%|████████▉ | 23275/25880 [4:44:59<31:18,  1.39it/s]
1|23276|Loss: 0.8013634085655212:  90%|████████▉ | 23275/25880 [4:44:59<31:18,  1.39it/s]
1|23276|Loss: 0.8013634085655212:  90%|████████▉ | 23276/25880 [4:45:00<31:20,  1.39it/s]
1|23277|Loss: 0.9729503989219666:  90%|████████▉ | 23276/25880 [4:45:00<31:20,  1.39it/s]
1|23277|Loss: 0.9729503989219666:  90%|████████▉ | 23277/25880 [4:45:01<31:25,  1.38it/s]
1|23278|Loss: 0.8988915085792542:  90%|████████▉ | 23277/25880 [4:45:01<31:25,  1.38it/s]
1|23278|Loss: 0.8988915085792542:  90%|████████▉ | 23278/25880 [4:45:01<30:32,  1.42it/s]
1|23279|Loss: 0.977575957775116:  90%|████████▉ | 23278/25880 [4:45:02<30:32,  1.42it/s] 
1|23279|Loss: 0.977575957775116:  90%|████████▉ | 23279/25880 [4:45:02<32:01,  1.35it/s]
1|23280|Loss: 0.9352846741676331:  90%|████████▉ | 23279/25880 [4:45:02<32:01,  1.35it/s]
1|23280|Loss: 0.9352846741676331:  90%|████████▉ | 23280/25880 [4:45:03<32:05,  1.35it/s]
1|23281|Loss: 0.8539485335350037:  90%|████████▉ | 23280/25880 [4:45:03<32:05,  1.35it/s]
1|23281|Loss: 0.8539485335350037:  90%|████████▉ | 23281/25880 [4:45:03<31:32,  1.37it/s]
1|23282|Loss: 0.873906672000885:  90%|████████▉ | 23281/25880 [4:45:04<31:32,  1.37it/s] 
1|23282|Loss: 0.873906672000885:  90%|████████▉ | 23282/25880 [4:45:04<30:20,  1.43it/s]
1|23283|Loss: 0.7163981199264526:  90%|████████▉ | 23282/25880 [4:45:04<30:20,  1.43it/s]
1|23283|Loss: 0.7163981199264526:  90%|████████▉ | 23283/25880 [4:45:05<27:56,  1.55it/s]
1|23284|Loss: 0.8488218188285828:  90%|████████▉ | 23283/25880 [4:45:05<27:56,  1.55it/s]
1|23284|Loss: 0.8488218188285828:  90%|████████▉ | 23284/25880 [4:45:06<33:46,  1.28it/s]
1|23285|Loss: 0.8182560205459595:  90%|████████▉ | 23284/25880 [4:45:06<33:46,  1.28it/s]
1|23285|Loss: 0.8182560205459595:  90%|████████▉ | 23285/25880 [4:45:06<32:04,  1.35it/s]
1|23286|Loss: 0.7578223347663879:  90%|████████▉ | 23285/25880 [4:45:07<32:04,  1.35it/s]
1|23286|Loss: 0.7578223347663879:  90%|████████▉ | 23286/25880 [4:45:07<32:46,  1.32it/s]
1|23287|Loss: 0.9089609980583191:  90%|████████▉ | 23286/25880 [4:45:08<32:46,  1.32it/s]
1|23287|Loss: 0.9089609980583191:  90%|████████▉ | 23287/25880 [4:45:08<31:26,  1.37it/s]
1|23288|Loss: 0.8901650905609131:  90%|████████▉ | 23287/25880 [4:45:08<31:26,  1.37it/s]
1|23288|Loss: 0.8901650905609131:  90%|████████▉ | 23288/25880 [4:45:08<30:17,  1.43it/s]
1|23289|Loss: 0.834771990776062:  90%|████████▉ | 23288/25880 [4:45:09<30:17,  1.43it/s] 
1|23289|Loss: 0.834771990776062:  90%|████████▉ | 23289/25880 [4:45:09<31:28,  1.37it/s]
1|23290|Loss: 0.868828296661377:  90%|████████▉ | 23289/25880 [4:45:10<31:28,  1.37it/s]
1|23290|Loss: 0.868828296661377:  90%|████████▉ | 23290/25880 [4:45:10<31:41,  1.36it/s]
1|23291|Loss: 0.8124901652336121:  90%|████████▉ | 23290/25880 [4:45:10<31:41,  1.36it/s]
1|23291|Loss: 0.8124901652336121:  90%|████████▉ | 23291/25880 [4:45:11<31:16,  1.38it/s]
1|23292|Loss: 0.8903748393058777:  90%|████████▉ | 23291/25880 [4:45:11<31:16,  1.38it/s]
1|23292|Loss: 0.8903748393058777:  90%|█████████ | 23292/25880 [4:45:11<30:03,  1.44it/s]
1|23293|Loss: 0.8879857063293457:  90%|█████████ | 23292/25880 [4:45:12<30:03,  1.44it/s]
1|23293|Loss: 0.8879857063293457:  90%|█████████ | 23293/25880 [4:45:12<29:04,  1.48it/s]
1|23294|Loss: 0.8444179892539978:  90%|█████████ | 23293/25880 [4:45:12<29:04,  1.48it/s]
1|23294|Loss: 0.8444179892539978:  90%|█████████ | 23294/25880 [4:45:13<30:36,  1.41it/s]
1|23295|Loss: 0.8886848092079163:  90%|█████████ | 23294/25880 [4:45:13<30:36,  1.41it/s]
1|23295|Loss: 0.8886848092079163:  90%|█████████ | 23295/25880 [4:45:14<32:10,  1.34it/s]
1|23296|Loss: 0.7611818313598633:  90%|█████████ | 23295/25880 [4:45:14<32:10,  1.34it/s]
1|23296|Loss: 0.7611818313598633:  90%|█████████ | 23296/25880 [4:45:14<32:22,  1.33it/s]
1|23297|Loss: 0.823674738407135:  90%|█████████ | 23296/25880 [4:45:15<32:22,  1.33it/s] 
1|23297|Loss: 0.823674738407135:  90%|█████████ | 23297/25880 [4:45:15<32:59,  1.30it/s]
1|23298|Loss: 0.7593427896499634:  90%|█████████ | 23297/25880 [4:45:16<32:59,  1.30it/s]
1|23298|Loss: 0.7593427896499634:  90%|█████████ | 23298/25880 [4:45:16<32:50,  1.31it/s]
1|23299|Loss: 0.7775058150291443:  90%|█████████ | 23298/25880 [4:45:16<32:50,  1.31it/s]
1|23299|Loss: 0.7775058150291443:  90%|█████████ | 23299/25880 [4:45:17<32:32,  1.32it/s]
1|23300|Loss: 0.7917534112930298:  90%|█████████ | 23299/25880 [4:45:17<32:32,  1.32it/s]
1|23300|Loss: 0.7917534112930298:  90%|█████████ | 23300/25880 [4:45:17<32:20,  1.33it/s]
1|23301|Loss: 0.8745211958885193:  90%|█████████ | 23300/25880 [4:45:18<32:20,  1.33it/s]
1|23301|Loss: 0.8745211958885193:  90%|█████████ | 23301/25880 [4:45:18<30:32,  1.41it/s]
1|23302|Loss: 0.8841431736946106:  90%|█████████ | 23301/25880 [4:45:18<30:32,  1.41it/s]
1|23302|Loss: 0.8841431736946106:  90%|█████████ | 23302/25880 [4:45:19<31:12,  1.38it/s]
1|23303|Loss: 0.8347031474113464:  90%|█████████ | 23302/25880 [4:45:19<31:12,  1.38it/s]
1|23303|Loss: 0.8347031474113464:  90%|█████████ | 23303/25880 [4:45:20<31:33,  1.36it/s]
1|23304|Loss: 0.7767484784126282:  90%|█████████ | 23303/25880 [4:45:20<31:33,  1.36it/s]
1|23304|Loss: 0.7767484784126282:  90%|█████████ | 23304/25880 [4:45:20<30:38,  1.40it/s]
1|23305|Loss: 0.9402391910552979:  90%|█████████ | 23304/25880 [4:45:21<30:38,  1.40it/s]
1|23305|Loss: 0.9402391910552979:  90%|█████████ | 23305/25880 [4:45:21<30:49,  1.39it/s]
1|23306|Loss: 0.7995201945304871:  90%|█████████ | 23305/25880 [4:45:21<30:49,  1.39it/s]
1|23306|Loss: 0.7995201945304871:  90%|█████████ | 23306/25880 [4:45:22<30:06,  1.42it/s]
1|23307|Loss: 0.8659542798995972:  90%|█████████ | 23306/25880 [4:45:22<30:06,  1.42it/s]
1|23307|Loss: 0.8659542798995972:  90%|█████████ | 23307/25880 [4:45:22<32:42,  1.31it/s]
1|23308|Loss: 0.7957344055175781:  90%|█████████ | 23307/25880 [4:45:23<32:42,  1.31it/s]
1|23308|Loss: 0.7957344055175781:  90%|█████████ | 23308/25880 [4:45:23<32:41,  1.31it/s]
1|23309|Loss: 0.7866336107254028:  90%|█████████ | 23308/25880 [4:45:24<32:41,  1.31it/s]
1|23309|Loss: 0.7866336107254028:  90%|█████████ | 23309/25880 [4:45:24<30:47,  1.39it/s]
1|23310|Loss: 0.9697606563568115:  90%|█████████ | 23309/25880 [4:45:24<30:47,  1.39it/s]
1|23310|Loss: 0.9697606563568115:  90%|█████████ | 23310/25880 [4:45:25<30:16,  1.41it/s]
1|23311|Loss: 0.8862105011940002:  90%|█████████ | 23310/25880 [4:45:25<30:16,  1.41it/s]
1|23311|Loss: 0.8862105011940002:  90%|█████████ | 23311/25880 [4:45:25<28:56,  1.48it/s]
1|23312|Loss: 0.864969789981842:  90%|█████████ | 23311/25880 [4:45:25<28:56,  1.48it/s] 
1|23312|Loss: 0.864969789981842:  90%|█████████ | 23312/25880 [4:45:26<28:01,  1.53it/s]
1|23313|Loss: 0.8375104069709778:  90%|█████████ | 23312/25880 [4:45:26<28:01,  1.53it/s]
1|23313|Loss: 0.8375104069709778:  90%|█████████ | 23313/25880 [4:45:27<29:55,  1.43it/s]
1|23314|Loss: 0.8050513863563538:  90%|█████████ | 23313/25880 [4:45:27<29:55,  1.43it/s]
1|23314|Loss: 0.8050513863563538:  90%|█████████ | 23314/25880 [4:45:27<30:50,  1.39it/s]
1|23315|Loss: 0.8382991552352905:  90%|█████████ | 23314/25880 [4:45:28<30:50,  1.39it/s]
1|23315|Loss: 0.8382991552352905:  90%|█████████ | 23315/25880 [4:45:28<28:50,  1.48it/s]
1|23316|Loss: 0.8141119480133057:  90%|█████████ | 23315/25880 [4:45:28<28:50,  1.48it/s]
1|23316|Loss: 0.8141119480133057:  90%|█████████ | 23316/25880 [4:45:28<27:24,  1.56it/s]
1|23317|Loss: 0.7049055099487305:  90%|█████████ | 23316/25880 [4:45:29<27:24,  1.56it/s]
1|23317|Loss: 0.7049055099487305:  90%|█████████ | 23317/25880 [4:45:29<27:10,  1.57it/s]
1|23318|Loss: 0.8593850135803223:  90%|█████████ | 23317/25880 [4:45:29<27:10,  1.57it/s]
1|23318|Loss: 0.8593850135803223:  90%|█████████ | 23318/25880 [4:45:30<27:00,  1.58it/s]
1|23319|Loss: 0.8089033961296082:  90%|█████████ | 23318/25880 [4:45:30<27:00,  1.58it/s]
1|23319|Loss: 0.8089033961296082:  90%|█████████ | 23319/25880 [4:45:30<27:03,  1.58it/s]
1|23320|Loss: 0.7734658718109131:  90%|█████████ | 23319/25880 [4:45:31<27:03,  1.58it/s]
1|23320|Loss: 0.7734658718109131:  90%|█████████ | 23320/25880 [4:45:31<26:37,  1.60it/s]
1|23321|Loss: 0.780194878578186:  90%|█████████ | 23320/25880 [4:45:31<26:37,  1.60it/s] 
1|23321|Loss: 0.780194878578186:  90%|█████████ | 23321/25880 [4:45:32<26:23,  1.62it/s]
1|23322|Loss: 0.8907053470611572:  90%|█████████ | 23321/25880 [4:45:32<26:23,  1.62it/s]
1|23322|Loss: 0.8907053470611572:  90%|█████████ | 23322/25880 [4:45:32<28:33,  1.49it/s]
1|23323|Loss: 0.8271843791007996:  90%|█████████ | 23322/25880 [4:45:33<28:33,  1.49it/s]
1|23323|Loss: 0.8271843791007996:  90%|█████████ | 23323/25880 [4:45:33<31:31,  1.35it/s]
1|23324|Loss: 0.8517157435417175:  90%|█████████ | 23323/25880 [4:45:34<31:31,  1.35it/s]
1|23324|Loss: 0.8517157435417175:  90%|█████████ | 23324/25880 [4:45:34<30:26,  1.40it/s]
1|23325|Loss: 0.856696605682373:  90%|█████████ | 23324/25880 [4:45:34<30:26,  1.40it/s] 
1|23325|Loss: 0.856696605682373:  90%|█████████ | 23325/25880 [4:45:34<28:42,  1.48it/s]
1|23326|Loss: 0.8502281904220581:  90%|█████████ | 23325/25880 [4:45:35<28:42,  1.48it/s]
1|23326|Loss: 0.8502281904220581:  90%|█████████ | 23326/25880 [4:45:35<29:08,  1.46it/s]
1|23327|Loss: 0.918538510799408:  90%|█████████ | 23326/25880 [4:45:36<29:08,  1.46it/s] 
1|23327|Loss: 0.918538510799408:  90%|█████████ | 23327/25880 [4:45:36<29:24,  1.45it/s]
1|23328|Loss: 1.0435494184494019:  90%|█████████ | 23327/25880 [4:45:36<29:24,  1.45it/s]
1|23328|Loss: 1.0435494184494019:  90%|█████████ | 23328/25880 [4:45:36<27:42,  1.53it/s]
1|23329|Loss: 0.9568716287612915:  90%|█████████ | 23328/25880 [4:45:37<27:42,  1.53it/s]
1|23329|Loss: 0.9568716287612915:  90%|█████████ | 23329/25880 [4:45:37<26:26,  1.61it/s]
1|23330|Loss: 0.902220606803894:  90%|█████████ | 23329/25880 [4:45:37<26:26,  1.61it/s] 
1|23330|Loss: 0.902220606803894:  90%|█████████ | 23330/25880 [4:45:38<28:39,  1.48it/s]
1|23331|Loss: 0.8215997815132141:  90%|█████████ | 23330/25880 [4:45:38<28:39,  1.48it/s]
1|23331|Loss: 0.8215997815132141:  90%|█████████ | 23331/25880 [4:45:39<30:29,  1.39it/s]
1|23332|Loss: 0.8992094993591309:  90%|█████████ | 23331/25880 [4:45:39<30:29,  1.39it/s]
1|23332|Loss: 0.8992094993591309:  90%|█████████ | 23332/25880 [4:45:39<28:00,  1.52it/s]
1|23333|Loss: 0.8854215145111084:  90%|█████████ | 23332/25880 [4:45:39<28:00,  1.52it/s]
1|23333|Loss: 0.8854215145111084:  90%|█████████ | 23333/25880 [4:45:40<26:56,  1.58it/s]
1|23334|Loss: 0.8718984723091125:  90%|█████████ | 23333/25880 [4:45:40<26:56,  1.58it/s]
1|23334|Loss: 0.8718984723091125:  90%|█████████ | 23334/25880 [4:45:40<26:58,  1.57it/s]
1|23335|Loss: 0.8127797842025757:  90%|█████████ | 23334/25880 [4:45:41<26:58,  1.57it/s]
1|23335|Loss: 0.8127797842025757:  90%|█████████ | 23335/25880 [4:45:41<27:04,  1.57it/s]
1|23336|Loss: 0.7721313834190369:  90%|█████████ | 23335/25880 [4:45:41<27:04,  1.57it/s]
1|23336|Loss: 0.7721313834190369:  90%|█████████ | 23336/25880 [4:45:42<28:04,  1.51it/s]
1|23337|Loss: 0.7671998143196106:  90%|█████████ | 23336/25880 [4:45:42<28:04,  1.51it/s]
1|23337|Loss: 0.7671998143196106:  90%|█████████ | 23337/25880 [4:45:42<28:53,  1.47it/s]
1|23338|Loss: 0.7675199508666992:  90%|█████████ | 23337/25880 [4:45:43<28:53,  1.47it/s]
1|23338|Loss: 0.7675199508666992:  90%|█████████ | 23338/25880 [4:45:43<27:55,  1.52it/s]
1|23339|Loss: 0.8844078183174133:  90%|█████████ | 23338/25880 [4:45:43<27:55,  1.52it/s]
1|23339|Loss: 0.8844078183174133:  90%|█████████ | 23339/25880 [4:45:44<29:12,  1.45it/s]
1|23340|Loss: 0.8382896780967712:  90%|█████████ | 23339/25880 [4:45:44<29:12,  1.45it/s]
1|23340|Loss: 0.8382896780967712:  90%|█████████ | 23340/25880 [4:45:44<28:24,  1.49it/s]
1|23341|Loss: 0.8935220837593079:  90%|█████████ | 23340/25880 [4:45:45<28:24,  1.49it/s]
1|23341|Loss: 0.8935220837593079:  90%|█████████ | 23341/25880 [4:45:45<28:27,  1.49it/s]
1|23342|Loss: 0.9300695061683655:  90%|█████████ | 23341/25880 [4:45:46<28:27,  1.49it/s]
1|23342|Loss: 0.9300695061683655:  90%|█████████ | 23342/25880 [4:45:46<30:04,  1.41it/s]
1|23343|Loss: 0.9047684073448181:  90%|█████████ | 23342/25880 [4:45:46<30:04,  1.41it/s]
1|23343|Loss: 0.9047684073448181:  90%|█████████ | 23343/25880 [4:45:47<29:43,  1.42it/s]
1|23344|Loss: 0.8572931289672852:  90%|█████████ | 23343/25880 [4:45:47<29:43,  1.42it/s]
1|23344|Loss: 0.8572931289672852:  90%|█████████ | 23344/25880 [4:45:47<28:37,  1.48it/s]
1|23345|Loss: 0.7987828254699707:  90%|█████████ | 23344/25880 [4:45:48<28:37,  1.48it/s]
1|23345|Loss: 0.7987828254699707:  90%|█████████ | 23345/25880 [4:45:48<26:34,  1.59it/s]
1|23346|Loss: 0.8790073990821838:  90%|█████████ | 23345/25880 [4:45:48<26:34,  1.59it/s]
1|23346|Loss: 0.8790073990821838:  90%|█████████ | 23346/25880 [4:45:48<28:15,  1.49it/s]
1|23347|Loss: 0.8336635828018188:  90%|█████████ | 23346/25880 [4:45:49<28:15,  1.49it/s]
1|23347|Loss: 0.8336635828018188:  90%|█████████ | 23347/25880 [4:45:49<29:47,  1.42it/s]
1|23348|Loss: 0.8469392657279968:  90%|█████████ | 23347/25880 [4:45:50<29:47,  1.42it/s]
1|23348|Loss: 0.8469392657279968:  90%|█████████ | 23348/25880 [4:45:50<30:24,  1.39it/s]
1|23349|Loss: 0.8581371903419495:  90%|█████████ | 23348/25880 [4:45:50<30:24,  1.39it/s]
1|23349|Loss: 0.8581371903419495:  90%|█████████ | 23349/25880 [4:45:51<31:13,  1.35it/s]
1|23350|Loss: 0.8427007794380188:  90%|█████████ | 23349/25880 [4:45:51<31:13,  1.35it/s]
1|23350|Loss: 0.8427007794380188:  90%|█████████ | 23350/25880 [4:45:52<30:57,  1.36it/s]
1|23351|Loss: 0.8373745679855347:  90%|█████████ | 23350/25880 [4:45:52<30:57,  1.36it/s]
1|23351|Loss: 0.8373745679855347:  90%|█████████ | 23351/25880 [4:45:52<30:57,  1.36it/s]
1|23352|Loss: 0.7380734086036682:  90%|█████████ | 23351/25880 [4:45:53<30:57,  1.36it/s]
1|23352|Loss: 0.7380734086036682:  90%|█████████ | 23352/25880 [4:45:53<31:47,  1.33it/s]
1|23353|Loss: 0.8162977695465088:  90%|█████████ | 23352/25880 [4:45:53<31:47,  1.33it/s]
1|23353|Loss: 0.8162977695465088:  90%|█████████ | 23353/25880 [4:45:54<30:32,  1.38it/s]
1|23354|Loss: 0.8598969578742981:  90%|█████████ | 23353/25880 [4:45:54<30:32,  1.38it/s]
1|23354|Loss: 0.8598969578742981:  90%|█████████ | 23354/25880 [4:45:54<30:19,  1.39it/s]
1|23355|Loss: 0.9912484884262085:  90%|█████████ | 23354/25880 [4:45:55<30:19,  1.39it/s]
1|23355|Loss: 0.9912484884262085:  90%|█████████ | 23355/25880 [4:45:55<31:13,  1.35it/s]
1|23356|Loss: 0.7645874619483948:  90%|█████████ | 23355/25880 [4:45:56<31:13,  1.35it/s]
1|23356|Loss: 0.7645874619483948:  90%|█████████ | 23356/25880 [4:45:56<33:11,  1.27it/s]
1|23357|Loss: 0.8006165623664856:  90%|█████████ | 23356/25880 [4:45:57<33:11,  1.27it/s]
1|23357|Loss: 0.8006165623664856:  90%|█████████ | 23357/25880 [4:45:57<31:25,  1.34it/s]
1|23358|Loss: 0.8035944700241089:  90%|█████████ | 23357/25880 [4:45:57<31:25,  1.34it/s]
1|23358|Loss: 0.8035944700241089:  90%|█████████ | 23358/25880 [4:45:57<29:55,  1.40it/s]
1|23359|Loss: 0.8744742274284363:  90%|█████████ | 23358/25880 [4:45:58<29:55,  1.40it/s]
1|23359|Loss: 0.8744742274284363:  90%|█████████ | 23359/25880 [4:45:58<29:42,  1.41it/s]
1|23360|Loss: 0.8586602807044983:  90%|█████████ | 23359/25880 [4:45:58<29:42,  1.41it/s]
1|23360|Loss: 0.8586602807044983:  90%|█████████ | 23360/25880 [4:45:59<29:58,  1.40it/s]
1|23361|Loss: 0.8134120106697083:  90%|█████████ | 23360/25880 [4:45:59<29:58,  1.40it/s]
1|23361|Loss: 0.8134120106697083:  90%|█████████ | 23361/25880 [4:46:00<30:00,  1.40it/s]
1|23362|Loss: 0.7454769015312195:  90%|█████████ | 23361/25880 [4:46:00<30:00,  1.40it/s]
1|23362|Loss: 0.7454769015312195:  90%|█████████ | 23362/25880 [4:46:00<31:58,  1.31it/s]
1|23363|Loss: 0.6884620189666748:  90%|█████████ | 23362/25880 [4:46:01<31:58,  1.31it/s]
1|23363|Loss: 0.6884620189666748:  90%|█████████ | 23363/25880 [4:46:01<31:07,  1.35it/s]
1|23364|Loss: 0.756712794303894:  90%|█████████ | 23363/25880 [4:46:01<31:07,  1.35it/s] 
1|23364|Loss: 0.756712794303894:  90%|█████████ | 23364/25880 [4:46:02<29:37,  1.42it/s]
1|23365|Loss: 0.828799307346344:  90%|█████████ | 23364/25880 [4:46:02<29:37,  1.42it/s]
1|23365|Loss: 0.828799307346344:  90%|█████████ | 23365/25880 [4:46:03<31:03,  1.35it/s]
1|23366|Loss: 0.8582054376602173:  90%|█████████ | 23365/25880 [4:46:03<31:03,  1.35it/s]
1|23366|Loss: 0.8582054376602173:  90%|█████████ | 23366/25880 [4:46:03<31:06,  1.35it/s]
1|23367|Loss: 0.849604070186615:  90%|█████████ | 23366/25880 [4:46:04<31:06,  1.35it/s] 
1|23367|Loss: 0.849604070186615:  90%|█████████ | 23367/25880 [4:46:04<29:45,  1.41it/s]
1|23368|Loss: 0.8669699430465698:  90%|█████████ | 23367/25880 [4:46:04<29:45,  1.41it/s]
1|23368|Loss: 0.8669699430465698:  90%|█████████ | 23368/25880 [4:46:04<27:35,  1.52it/s]
1|23369|Loss: 0.8157694339752197:  90%|█████████ | 23368/25880 [4:46:05<27:35,  1.52it/s]
1|23369|Loss: 0.8157694339752197:  90%|█████████ | 23369/25880 [4:46:05<26:47,  1.56it/s]
1|23370|Loss: 0.8435586094856262:  90%|█████████ | 23369/25880 [4:46:05<26:47,  1.56it/s]
1|23370|Loss: 0.8435586094856262:  90%|█████████ | 23370/25880 [4:46:06<26:09,  1.60it/s]
1|23371|Loss: 0.8863140344619751:  90%|█████████ | 23370/25880 [4:46:06<26:09,  1.60it/s]
1|23371|Loss: 0.8863140344619751:  90%|█████████ | 23371/25880 [4:46:06<26:49,  1.56it/s]
1|23372|Loss: 0.7177177667617798:  90%|█████████ | 23371/25880 [4:46:07<26:49,  1.56it/s]
1|23372|Loss: 0.7177177667617798:  90%|█████████ | 23372/25880 [4:46:07<25:38,  1.63it/s]
1|23373|Loss: 0.8905693888664246:  90%|█████████ | 23372/25880 [4:46:07<25:38,  1.63it/s]
1|23373|Loss: 0.8905693888664246:  90%|█████████ | 23373/25880 [4:46:08<25:40,  1.63it/s]
1|23374|Loss: 0.7553750276565552:  90%|█████████ | 23373/25880 [4:46:08<25:40,  1.63it/s]
1|23374|Loss: 0.7553750276565552:  90%|█████████ | 23374/25880 [4:46:08<26:56,  1.55it/s]
1|23375|Loss: 0.8399433493614197:  90%|█████████ | 23374/25880 [4:46:09<26:56,  1.55it/s]
1|23375|Loss: 0.8399433493614197:  90%|█████████ | 23375/25880 [4:46:09<25:48,  1.62it/s]
1|23376|Loss: 0.8399219512939453:  90%|█████████ | 23375/25880 [4:46:09<25:48,  1.62it/s]
1|23376|Loss: 0.8399219512939453:  90%|█████████ | 23376/25880 [4:46:09<25:43,  1.62it/s]
1|23377|Loss: 0.905079185962677:  90%|█████████ | 23376/25880 [4:46:10<25:43,  1.62it/s] 
1|23377|Loss: 0.905079185962677:  90%|█████████ | 23377/25880 [4:46:10<26:42,  1.56it/s]
1|23378|Loss: 0.9350664615631104:  90%|█████████ | 23377/25880 [4:46:10<26:42,  1.56it/s]
1|23378|Loss: 0.9350664615631104:  90%|█████████ | 23378/25880 [4:46:11<27:29,  1.52it/s]
1|23379|Loss: 0.7317000031471252:  90%|█████████ | 23378/25880 [4:46:11<27:29,  1.52it/s]
1|23379|Loss: 0.7317000031471252:  90%|█████████ | 23379/25880 [4:46:11<27:21,  1.52it/s]
1|23380|Loss: 0.7673708200454712:  90%|█████████ | 23379/25880 [4:46:12<27:21,  1.52it/s]
1|23380|Loss: 0.7673708200454712:  90%|█████████ | 23380/25880 [4:46:12<28:14,  1.48it/s]
1|23381|Loss: 0.8074333071708679:  90%|█████████ | 23380/25880 [4:46:13<28:14,  1.48it/s]
1|23381|Loss: 0.8074333071708679:  90%|█████████ | 23381/25880 [4:46:13<29:05,  1.43it/s]
1|23382|Loss: 0.9660642743110657:  90%|█████████ | 23381/25880 [4:46:13<29:05,  1.43it/s]
1|23382|Loss: 0.9660642743110657:  90%|█████████ | 23382/25880 [4:46:14<30:46,  1.35it/s]
1|23383|Loss: 0.7951638698577881:  90%|█████████ | 23382/25880 [4:46:14<30:46,  1.35it/s]
1|23383|Loss: 0.7951638698577881:  90%|█████████ | 23383/25880 [4:46:14<29:57,  1.39it/s]
1|23384|Loss: 0.7745358943939209:  90%|█████████ | 23383/25880 [4:46:15<29:57,  1.39it/s]
1|23384|Loss: 0.7745358943939209:  90%|█████████ | 23384/25880 [4:46:15<30:25,  1.37it/s]
1|23385|Loss: 0.7501720190048218:  90%|█████████ | 23384/25880 [4:46:16<30:25,  1.37it/s]
1|23385|Loss: 0.7501720190048218:  90%|█████████ | 23385/25880 [4:46:16<31:38,  1.31it/s]
1|23386|Loss: 0.8590031266212463:  90%|█████████ | 23385/25880 [4:46:16<31:38,  1.31it/s]
1|23386|Loss: 0.8590031266212463:  90%|█████████ | 23386/25880 [4:46:17<31:41,  1.31it/s]
1|23387|Loss: 0.8023297190666199:  90%|█████████ | 23386/25880 [4:46:17<31:41,  1.31it/s]
1|23387|Loss: 0.8023297190666199:  90%|█████████ | 23387/25880 [4:46:17<30:18,  1.37it/s]
1|23388|Loss: 0.7647936344146729:  90%|█████████ | 23387/25880 [4:46:18<30:18,  1.37it/s]
1|23388|Loss: 0.7647936344146729:  90%|█████████ | 23388/25880 [4:46:18<30:47,  1.35it/s]
1|23389|Loss: 0.830783486366272:  90%|█████████ | 23388/25880 [4:46:19<30:47,  1.35it/s] 
1|23389|Loss: 0.830783486366272:  90%|█████████ | 23389/25880 [4:46:19<32:39,  1.27it/s]
1|23390|Loss: 0.8342471718788147:  90%|█████████ | 23389/25880 [4:46:20<32:39,  1.27it/s]
1|23390|Loss: 0.8342471718788147:  90%|█████████ | 23390/25880 [4:46:20<33:24,  1.24it/s]
1|23391|Loss: 0.7327795028686523:  90%|█████████ | 23390/25880 [4:46:20<33:24,  1.24it/s]
1|23391|Loss: 0.7327795028686523:  90%|█████████ | 23391/25880 [4:46:21<35:02,  1.18it/s]
1|23392|Loss: 0.908599317073822:  90%|█████████ | 23391/25880 [4:46:21<35:02,  1.18it/s] 
1|23392|Loss: 0.908599317073822:  90%|█████████ | 23392/25880 [4:46:22<33:13,  1.25it/s]
1|23393|Loss: 0.7916780710220337:  90%|█████████ | 23392/25880 [4:46:22<33:13,  1.25it/s]
1|23393|Loss: 0.7916780710220337:  90%|█████████ | 23393/25880 [4:46:22<30:58,  1.34it/s]
1|23394|Loss: 0.7664473056793213:  90%|█████████ | 23393/25880 [4:46:23<30:58,  1.34it/s]
1|23394|Loss: 0.7664473056793213:  90%|█████████ | 23394/25880 [4:46:23<30:26,  1.36it/s]
1|23395|Loss: 0.7381687760353088:  90%|█��███████ | 23394/25880 [4:46:23<30:26,  1.36it/s]
1|23395|Loss: 0.7381687760353088:  90%|█████████ | 23395/25880 [4:46:24<30:05,  1.38it/s]
1|23396|Loss: 0.7966842651367188:  90%|█████████ | 23395/25880 [4:46:24<30:05,  1.38it/s]
1|23396|Loss: 0.7966842651367188:  90%|█████████ | 23396/25880 [4:46:24<30:16,  1.37it/s]
1|23397|Loss: 0.9156341552734375:  90%|█████████ | 23396/25880 [4:46:25<30:16,  1.37it/s]
1|23397|Loss: 0.9156341552734375:  90%|█████████ | 23397/25880 [4:46:25<30:22,  1.36it/s]
1|23398|Loss: 0.8570126891136169:  90%|█████████ | 23397/25880 [4:46:25<30:22,  1.36it/s]
1|23398|Loss: 0.8570126891136169:  90%|█████████ | 23398/25880 [4:46:26<28:39,  1.44it/s]
1|23399|Loss: 0.8977063894271851:  90%|█████████ | 23398/25880 [4:46:26<28:39,  1.44it/s]
1|23399|Loss: 0.8977063894271851:  90%|█████████ | 23399/25880 [4:46:26<28:54,  1.43it/s]
1|23400|Loss: 0.7677615284919739:  90%|█████████ | 23399/25880 [4:46:27<28:54,  1.43it/s]
1|23400|Loss: 0.7677615284919739:  90%|█████████ | 23400/25880 [4:46:27<29:08,  1.42it/s]
1|23401|Loss: 0.784856915473938:  90%|█████████ | 23400/25880 [4:46:28<29:08,  1.42it/s] 
1|23401|Loss: 0.784856915473938:  90%|█████████ | 23401/25880 [4:46:28<31:13,  1.32it/s]
1|23402|Loss: 0.8735629320144653:  90%|█████████ | 23401/25880 [4:46:28<31:13,  1.32it/s]
1|23402|Loss: 0.8735629320144653:  90%|█████████ | 23402/25880 [4:46:29<30:26,  1.36it/s]
1|23403|Loss: 0.886890172958374:  90%|█████████ | 23402/25880 [4:46:29<30:26,  1.36it/s] 
1|23403|Loss: 0.886890172958374:  90%|█████████ | 23403/25880 [4:46:29<31:11,  1.32it/s]
1|23404|Loss: 0.7727221250534058:  90%|█████████ | 23403/25880 [4:46:30<31:11,  1.32it/s]
1|23404|Loss: 0.7727221250534058:  90%|█████████ | 23404/25880 [4:46:30<32:17,  1.28it/s]
1|23405|Loss: 0.9354981184005737:  90%|█████████ | 23404/25880 [4:46:31<32:17,  1.28it/s]
1|23405|Loss: 0.9354981184005737:  90%|█████████ | 23405/25880 [4:46:31<31:04,  1.33it/s]
1|23406|Loss: 0.7014909982681274:  90%|█████████ | 23405/25880 [4:46:31<31:04,  1.33it/s]
1|23406|Loss: 0.7014909982681274:  90%|█████████ | 23406/25880 [4:46:32<30:34,  1.35it/s]
1|23407|Loss: 0.750018835067749:  90%|█████████ | 23406/25880 [4:46:32<30:34,  1.35it/s] 
1|23407|Loss: 0.750018835067749:  90%|█████████ | 23407/25880 [4:46:33<31:21,  1.31it/s]
1|23408|Loss: 0.8591129183769226:  90%|█████████ | 23407/25880 [4:46:33<31:21,  1.31it/s]
1|23408|Loss: 0.8591129183769226:  90%|█████████ | 23408/25880 [4:46:33<31:15,  1.32it/s]
1|23409|Loss: 0.7914314866065979:  90%|█████████ | 23408/25880 [4:46:34<31:15,  1.32it/s]
1|23409|Loss: 0.7914314866065979:  90%|█████████ | 23409/25880 [4:46:34<29:51,  1.38it/s]
1|23410|Loss: 0.979373574256897:  90%|█████████ | 23409/25880 [4:46:34<29:51,  1.38it/s] 
1|23410|Loss: 0.979373574256897:  90%|█████████ | 23410/25880 [4:46:35<30:41,  1.34it/s]
1|23411|Loss: 0.7889951467514038:  90%|█████████ | 23410/25880 [4:46:35<30:41,  1.34it/s]
1|23411|Loss: 0.7889951467514038:  90%|█████████ | 23411/25880 [4:46:35<30:31,  1.35it/s]
1|23412|Loss: 0.8562563061714172:  90%|█████████ | 23411/25880 [4:46:36<30:31,  1.35it/s]
1|23412|Loss: 0.8562563061714172:  90%|█████████ | 23412/25880 [4:46:36<30:48,  1.34it/s]
1|23413|Loss: 0.8710356950759888:  90%|█████████ | 23412/25880 [4:46:37<30:48,  1.34it/s]
1|23413|Loss: 0.8710356950759888:  90%|█████████ | 23413/25880 [4:46:37<29:40,  1.39it/s]
1|23414|Loss: 0.8319889903068542:  90%|█████████ | 23413/25880 [4:46:37<29:40,  1.39it/s]
1|23414|Loss: 0.8319889903068542:  90%|█████████ | 23414/25880 [4:46:38<29:15,  1.40it/s]
1|23415|Loss: 0.7577082514762878:  90%|█████████ | 23414/25880 [4:46:38<29:15,  1.40it/s]
1|23415|Loss: 0.7577082514762878:  90%|█████████ | 23415/25880 [4:46:38<30:35,  1.34it/s]
1|23416|Loss: 0.8125832676887512:  90%|█████████ | 23415/25880 [4:46:39<30:35,  1.34it/s]
1|23416|Loss: 0.8125832676887512:  90%|█████████ | 23416/25880 [4:46:39<30:47,  1.33it/s]
1|23417|Loss: 0.8982346653938293:  90%|█████████ | 23416/25880 [4:46:40<30:47,  1.33it/s]
1|23417|Loss: 0.8982346653938293:  90%|█████████ | 23417/25880 [4:46:40<31:54,  1.29it/s]
1|23418|Loss: 0.9299046397209167:  90%|█████████ | 23417/25880 [4:46:40<31:54,  1.29it/s]
1|23418|Loss: 0.9299046397209167:  90%|█████████ | 23418/25880 [4:46:41<30:38,  1.34it/s]
1|23419|Loss: 0.7863371968269348:  90%|█████████ | 23418/25880 [4:46:41<30:38,  1.34it/s]
1|23419|Loss: 0.7863371968269348:  90%|█████████ | 23419/25880 [4:46:41<30:11,  1.36it/s]
1|23420|Loss: 0.8445394039154053:  90%|█████████ | 23419/25880 [4:46:42<30:11,  1.36it/s]
1|23420|Loss: 0.8445394039154053:  90%|█████████ | 23420/25880 [4:46:42<30:46,  1.33it/s]
1|23421|Loss: 0.7348285913467407:  90%|█████████ | 23420/25880 [4:46:43<30:46,  1.33it/s]
1|23421|Loss: 0.7348285913467407:  90%|█████████ | 23421/25880 [4:46:43<28:48,  1.42it/s]
1|23422|Loss: 0.8727941513061523:  90%|█████████ | 23421/25880 [4:46:43<28:48,  1.42it/s]
1|23422|Loss: 0.8727941513061523:  91%|█████████ | 23422/25880 [4:46:43<28:38,  1.43it/s]
1|23423|Loss: 0.8181848526000977:  91%|█████████ | 23422/25880 [4:46:44<28:38,  1.43it/s]
1|23423|Loss: 0.8181848526000977:  91%|█████████ | 23423/25880 [4:46:44<30:23,  1.35it/s]
1|23424|Loss: 0.8571698069572449:  91%|█████████ | 23423/25880 [4:46:45<30:23,  1.35it/s]
1|23424|Loss: 0.8571698069572449:  91%|█████████ | 23424/25880 [4:46:45<30:43,  1.33it/s]
1|23425|Loss: 0.9550756216049194:  91%|█████████ | 23424/25880 [4:46:45<30:43,  1.33it/s]
1|23425|Loss: 0.9550756216049194:  91%|█████████ | 23425/25880 [4:46:46<30:33,  1.34it/s]
1|23426|Loss: 0.8120039701461792:  91%|█████████ | 23425/25880 [4:46:46<30:33,  1.34it/s]
1|23426|Loss: 0.8120039701461792:  91%|█████████ | 23426/25880 [4:46:46<28:24,  1.44it/s]
1|23427|Loss: 0.9667836427688599:  91%|█████████ | 23426/25880 [4:46:47<28:24,  1.44it/s]
1|23427|Loss: 0.9667836427688599:  91%|█████████ | 23427/25880 [4:46:47<27:25,  1.49it/s]
1|23428|Loss: 0.8084903955459595:  91%|█████████ | 23427/25880 [4:46:47<27:25,  1.49it/s]
1|23428|Loss: 0.8084903955459595:  91%|█████████ | 23428/25880 [4:46:48<28:41,  1.42it/s]
1|23429|Loss: 0.9079862236976624:  91%|█████████ | 23428/25880 [4:46:48<28:41,  1.42it/s]
1|23429|Loss: 0.9079862236976624:  91%|█████████ | 23429/25880 [4:46:49<29:16,  1.40it/s]
1|23430|Loss: 0.8984562158584595:  91%|█████████ | 23429/25880 [4:46:49<29:16,  1.40it/s]
1|23430|Loss: 0.8984562158584595:  91%|█████████ | 23430/25880 [4:46:49<29:37,  1.38it/s]
1|23431|Loss: 0.9621933698654175:  91%|█████████ | 23430/25880 [4:46:50<29:37,  1.38it/s]
1|23431|Loss: 0.9621933698654175:  91%|█████████ | 23431/25880 [4:46:50<30:28,  1.34it/s]
1|23432|Loss: 0.8249667882919312:  91%|█████████ | 23431/25880 [4:46:50<30:28,  1.34it/s]
1|23432|Loss: 0.8249667882919312:  91%|█████████ | 23432/25880 [4:46:51<30:13,  1.35it/s]
1|23433|Loss: 0.8105661273002625:  91%|█████████ | 23432/25880 [4:46:51<30:13,  1.35it/s]
1|23433|Loss: 0.8105661273002625:  91%|█████████ | 23433/25880 [4:46:52<30:38,  1.33it/s]
1|23434|Loss: 0.7481197118759155:  91%|█████████ | 23433/25880 [4:46:52<30:38,  1.33it/s]
1|23434|Loss: 0.7481197118759155:  91%|█████████ | 23434/25880 [4:46:52<29:43,  1.37it/s]
1|23435|Loss: 0.9266965985298157:  91%|█████████ | 23434/25880 [4:46:53<29:43,  1.37it/s]
1|23435|Loss: 0.9266965985298157:  91%|█████████ | 23435/25880 [4:46:53<29:33,  1.38it/s]
1|23436|Loss: 0.7684730887413025:  91%|█████████ | 23435/25880 [4:46:53<29:33,  1.38it/s]
1|23436|Loss: 0.7684730887413025:  91%|█████████ | 23436/25880 [4:46:54<29:36,  1.38it/s]
1|23437|Loss: 0.8857526183128357:  91%|█████████ | 23436/25880 [4:46:54<29:36,  1.38it/s]
1|23437|Loss: 0.8857526183128357:  91%|█████████ | 23437/25880 [4:46:55<30:42,  1.33it/s]
1|23438|Loss: 0.8512316942214966:  91%|█████████ | 23437/25880 [4:46:55<30:42,  1.33it/s]
1|23438|Loss: 0.8512316942214966:  91%|█████████ | 23438/25880 [4:46:55<28:15,  1.44it/s]
1|23439|Loss: 0.8216687440872192:  91%|█████████ | 23438/25880 [4:46:55<28:15,  1.44it/s]
1|23439|Loss: 0.8216687440872192:  91%|█████████ | 23439/25880 [4:46:56<27:48,  1.46it/s]
1|23440|Loss: 0.8793233633041382:  91%|█████████ | 23439/25880 [4:46:56<27:48,  1.46it/s]
1|23440|Loss: 0.8793233633041382:  91%|█████████ | 23440/25880 [4:46:57<30:08,  1.35it/s]
1|23441|Loss: 0.8807791471481323:  91%|█████████ | 23440/25880 [4:46:57<30:08,  1.35it/s]
1|23441|Loss: 0.8807791471481323:  91%|█████████ | 23441/25880 [4:46:57<31:26,  1.29it/s]
1|23442|Loss: 0.8500121235847473:  91%|█████████ | 23441/25880 [4:46:58<31:26,  1.29it/s]
1|23442|Loss: 0.8500121235847473:  91%|█████████ | 23442/25880 [4:46:58<30:50,  1.32it/s]
1|23443|Loss: 0.6832304000854492:  91%|█████████ | 23442/25880 [4:46:59<30:50,  1.32it/s]
1|23443|Loss: 0.6832304000854492:  91%|█████████ | 23443/25880 [4:46:59<29:13,  1.39it/s]
1|23444|Loss: 0.9134973287582397:  91%|█████████ | 23443/25880 [4:46:59<29:13,  1.39it/s]
1|23444|Loss: 0.9134973287582397:  91%|█████████ | 23444/25880 [4:46:59<28:11,  1.44it/s]
1|23445|Loss: 0.8566112518310547:  91%|█████████ | 23444/25880 [4:47:00<28:11,  1.44it/s]
1|23445|Loss: 0.8566112518310547:  91%|█████████ | 23445/25880 [4:47:00<27:18,  1.49it/s]
1|23446|Loss: 0.8656755685806274:  91%|█████████ | 23445/25880 [4:47:00<27:18,  1.49it/s]
1|23446|Loss: 0.8656755685806274:  91%|█████████ | 23446/25880 [4:47:01<29:08,  1.39it/s]
1|23447|Loss: 1.0564343929290771:  91%|█████████ | 23446/25880 [4:47:01<29:08,  1.39it/s]
1|23447|Loss: 1.0564343929290771:  91%|█████████ | 23447/25880 [4:47:02<30:54,  1.31it/s]
1|23448|Loss: 0.7690859436988831:  91%|█████████ | 23447/25880 [4:47:02<30:54,  1.31it/s]
1|23448|Loss: 0.7690859436988831:  91%|█████████ | 23448/25880 [4:47:03<31:25,  1.29it/s]
1|23449|Loss: 0.7111847996711731:  91%|█████████ | 23448/25880 [4:47:03<31:25,  1.29it/s]
1|23449|Loss: 0.7111847996711731:  91%|█████████ | 23449/25880 [4:47:03<29:09,  1.39it/s]
1|23450|Loss: 0.8051378130912781:  91%|█████████ | 23449/25880 [4:47:03<29:09,  1.39it/s]
1|23450|Loss: 0.8051378130912781:  91%|█████████ | 23450/25880 [4:47:04<26:08,  1.55it/s]
1|23451|Loss: 0.8241609930992126:  91%|█████████ | 23450/25880 [4:47:04<26:08,  1.55it/s]
1|23451|Loss: 0.8241609930992126:  91%|█████████ | 23451/25880 [4:47:04<25:29,  1.59it/s]
1|23452|Loss: 0.9514373540878296:  91%|█████████ | 23451/25880 [4:47:05<25:29,  1.59it/s]
1|23452|Loss: 0.9514373540878296:  91%|█████████ | 23452/25880 [4:47:05<27:51,  1.45it/s]
1|23453|Loss: 0.7794346213340759:  91%|█████████ | 23452/25880 [4:47:05<27:51,  1.45it/s]
1|23453|Loss: 0.7794346213340759:  91%|█████████ | 23453/25880 [4:47:06<28:52,  1.40it/s]
1|23454|Loss: 0.8419559597969055:  91%|█████████ | 23453/25880 [4:47:06<28:52,  1.40it/s]
1|23454|Loss: 0.8419559597969055:  91%|█████████ | 23454/25880 [4:47:07<29:10,  1.39it/s]
1|23455|Loss: 0.8565512299537659:  91%|█████████ | 23454/25880 [4:47:07<29:10,  1.39it/s]
1|23455|Loss: 0.8565512299537659:  91%|█████████ | 23455/25880 [4:47:07<31:03,  1.30it/s]
1|23456|Loss: 0.8848236203193665:  91%|█████████ | 23455/25880 [4:47:08<31:03,  1.30it/s]
1|23456|Loss: 0.8848236203193665:  91%|█████████ | 23456/25880 [4:47:08<31:44,  1.27it/s]
1|23457|Loss: 0.9559124708175659:  91%|█████████ | 23456/25880 [4:47:09<31:44,  1.27it/s]
1|23457|Loss: 0.9559124708175659:  91%|█████████ | 23457/25880 [4:47:09<29:19,  1.38it/s]
1|23458|Loss: 0.8765802979469299:  91%|█████████ | 23457/25880 [4:47:09<29:19,  1.38it/s]
1|23458|Loss: 0.8765802979469299:  91%|█████████ | 23458/25880 [4:47:09<26:30,  1.52it/s]
1|23459|Loss: 1.0997788906097412:  91%|█████████ | 23458/25880 [4:47:10<26:30,  1.52it/s]
1|23459|Loss: 1.0997788906097412:  91%|█████████ | 23459/25880 [4:47:10<26:43,  1.51it/s]
1|23460|Loss: 0.9300594925880432:  91%|█████████ | 23459/25880 [4:47:10<26:43,  1.51it/s]
1|23460|Loss: 0.9300594925880432:  91%|█████████ | 23460/25880 [4:47:11<26:25,  1.53it/s]
1|23461|Loss: 0.8768301606178284:  91%|█████████ | 23460/25880 [4:47:11<26:25,  1.53it/s]
1|23461|Loss: 0.8768301606178284:  91%|█████████ | 23461/25880 [4:47:11<27:12,  1.48it/s]
1|23462|Loss: 0.840882420539856:  91%|█████████ | 23461/25880 [4:47:12<27:12,  1.48it/s] 
1|23462|Loss: 0.840882420539856:  91%|█████████ | 23462/25880 [4:47:12<27:07,  1.49it/s]
1|23463|Loss: 0.7747945189476013:  91%|█████████ | 23462/25880 [4:47:12<27:07,  1.49it/s]
1|23463|Loss: 0.7747945189476013:  91%|█████████ | 23463/25880 [4:47:13<27:17,  1.48it/s]
1|23464|Loss: 0.873572587966919:  91%|█████████ | 23463/25880 [4:47:13<27:17,  1.48it/s] 
1|23464|Loss: 0.873572587966919:  91%|█████████ | 23464/25880 [4:47:13<27:30,  1.46it/s]
1|23465|Loss: 0.7950341701507568:  91%|█████████ | 23464/25880 [4:47:14<27:30,  1.46it/s]
1|23465|Loss: 0.7950341701507568:  91%|█████████ | 23465/25880 [4:47:14<26:50,  1.50it/s]
1|23466|Loss: 0.8371339440345764:  91%|█████████ | 23465/25880 [4:47:14<26:50,  1.50it/s]
1|23466|Loss: 0.8371339440345764:  91%|█████████ | 23466/25880 [4:47:15<26:26,  1.52it/s]
1|23467|Loss: 0.8863569498062134:  91%|█████████ | 23466/25880 [4:47:15<26:26,  1.52it/s]
1|23467|Loss: 0.8863569498062134:  91%|█████████ | 23467/25880 [4:47:15<27:48,  1.45it/s]
1|23468|Loss: 0.7882474064826965:  91%|█████████ | 23467/25880 [4:47:16<27:48,  1.45it/s]
1|23468|Loss: 0.7882474064826965:  91%|█████████ | 23468/25880 [4:47:16<25:44,  1.56it/s]
1|23469|Loss: 0.877185046672821:  91%|█████████ | 23468/25880 [4:47:16<25:44,  1.56it/s] 
1|23469|Loss: 0.877185046672821:  91%|█████████ | 23469/25880 [4:47:17<26:02,  1.54it/s]
1|23470|Loss: 0.6962328553199768:  91%|█████████ | 23469/25880 [4:47:17<26:02,  1.54it/s]
1|23470|Loss: 0.6962328553199768:  91%|█████████ | 23470/25880 [4:47:17<25:42,  1.56it/s]
1|23471|Loss: 0.780634343624115:  91%|█████████ | 23470/25880 [4:47:18<25:42,  1.56it/s] 
1|23471|Loss: 0.780634343624115:  91%|█████████ | 23471/25880 [4:47:18<26:23,  1.52it/s]
1|23472|Loss: 0.939021646976471:  91%|█████████ | 23471/25880 [4:47:18<26:23,  1.52it/s]
1|23472|Loss: 0.939021646976471:  91%|█████████ | 23472/25880 [4:47:19<29:02,  1.38it/s]
1|23473|Loss: 0.9087777137756348:  91%|█████████ | 23472/25880 [4:47:19<29:02,  1.38it/s]
1|23473|Loss: 0.9087777137756348:  91%|█████████ | 23473/25880 [4:47:20<31:56,  1.26it/s]
1|23474|Loss: 0.953899085521698:  91%|█████████ | 23473/25880 [4:47:20<31:56,  1.26it/s] 
1|23474|Loss: 0.953899085521698:  91%|█████████ | 23474/25880 [4:47:21<32:47,  1.22it/s]
1|23475|Loss: 0.9059836864471436:  91%|█████████ | 23474/25880 [4:47:21<32:47,  1.22it/s]
1|23475|Loss: 0.9059836864471436:  91%|█████████ | 23475/25880 [4:47:22<33:13,  1.21it/s]
1|23476|Loss: 0.6531484127044678:  91%|█████████ | 23475/25880 [4:47:22<33:13,  1.21it/s]
1|23476|Loss: 0.6531484127044678:  91%|█████████ | 23476/25880 [4:47:22<34:37,  1.16it/s]
1|23477|Loss: 0.8697470426559448:  91%|█████████ | 23476/25880 [4:47:23<34:37,  1.16it/s]
1|23477|Loss: 0.8697470426559448:  91%|█████████ | 23477/25880 [4:47:23<33:32,  1.19it/s]
1|23478|Loss: 0.9095633029937744:  91%|█████████ | 23477/25880 [4:47:24<33:32,  1.19it/s]
1|23478|Loss: 0.9095633029937744:  91%|█████████ | 23478/25880 [4:47:24<32:17,  1.24it/s]
1|23479|Loss: 0.8540074825286865:  91%|█████████ | 23478/25880 [4:47:24<32:17,  1.24it/s]
1|23479|Loss: 0.8540074825286865:  91%|█████████ | 23479/25880 [4:47:25<32:18,  1.24it/s]
1|23480|Loss: 0.7567828893661499:  91%|█████████ | 23479/25880 [4:47:25<32:18,  1.24it/s]
1|23480|Loss: 0.7567828893661499:  91%|█████████ | 23480/25880 [4:47:26<33:27,  1.20it/s]
1|23481|Loss: 0.8446879982948303:  91%|█████████ | 23480/25880 [4:47:26<33:27,  1.20it/s]
1|23481|Loss: 0.8446879982948303:  91%|█████████ | 23481/25880 [4:47:27<34:08,  1.17it/s]
1|23482|Loss: 0.7750716805458069:  91%|█████████ | 23481/25880 [4:47:27<34:08,  1.17it/s]
1|23482|Loss: 0.7750716805458069:  91%|█████████ | 23482/25880 [4:47:27<34:19,  1.16it/s]
1|23483|Loss: 0.91921466588974:  91%|█████████ | 23482/25880 [4:47:28<34:19,  1.16it/s]  
1|23483|Loss: 0.91921466588974:  91%|█████████ | 23483/25880 [4:47:28<34:05,  1.17it/s]
1|23484|Loss: 0.7267802953720093:  91%|█████████ | 23483/25880 [4:47:29<34:05,  1.17it/s]
1|23484|Loss: 0.7267802953720093:  91%|█████████ | 23484/25880 [4:47:29<32:51,  1.22it/s]
1|23485|Loss: 0.8753766417503357:  91%|█████████ | 23484/25880 [4:47:29<32:51,  1.22it/s]
1|23485|Loss: 0.8753766417503357:  91%|█████████ | 23485/25880 [4:47:30<31:31,  1.27it/s]
1|23486|Loss: 0.9821615815162659:  91%|█████████ | 23485/25880 [4:47:30<31:31,  1.27it/s]
1|23486|Loss: 0.9821615815162659:  91%|█████████ | 23486/25880 [4:47:30<29:50,  1.34it/s]
1|23487|Loss: 0.8211129903793335:  91%|█████████ | 23486/25880 [4:47:31<29:50,  1.34it/s]
1|23487|Loss: 0.8211129903793335:  91%|█████████ | 23487/25880 [4:47:31<29:29,  1.35it/s]
1|23488|Loss: 0.7984504699707031:  91%|█████████ | 23487/25880 [4:47:32<29:29,  1.35it/s]
1|23488|Loss: 0.7984504699707031:  91%|█████████ | 23488/25880 [4:47:32<29:10,  1.37it/s]
1|23489|Loss: 0.7801046371459961:  91%|█████████ | 23488/25880 [4:47:32<29:10,  1.37it/s]
1|23489|Loss: 0.7801046371459961:  91%|█████████ | 23489/25880 [4:47:33<30:03,  1.33it/s]
1|23490|Loss: 0.8232713937759399:  91%|█████████ | 23489/25880 [4:47:33<30:03,  1.33it/s]
1|23490|Loss: 0.8232713937759399:  91%|█████████ | 23490/25880 [4:47:33<27:52,  1.43it/s]
1|23491|Loss: 0.9670372009277344:  91%|█████████ | 23490/25880 [4:47:34<27:52,  1.43it/s]
1|23491|Loss: 0.9670372009277344:  91%|█████████ | 23491/25880 [4:47:34<27:52,  1.43it/s]
1|23492|Loss: 0.8557780981063843:  91%|█████████ | 23491/25880 [4:47:34<27:52,  1.43it/s]
1|23492|Loss: 0.8557780981063843:  91%|█████████ | 23492/25880 [4:47:35<29:30,  1.35it/s]
1|23493|Loss: 0.740982711315155:  91%|█████████ | 23492/25880 [4:47:35<29:30,  1.35it/s] 
1|23493|Loss: 0.740982711315155:  91%|█████████ | 23493/25880 [4:47:36<29:47,  1.34it/s]
1|23494|Loss: 0.8168426752090454:  91%|█████████ | 23493/25880 [4:47:36<29:47,  1.34it/s]
1|23494|Loss: 0.8168426752090454:  91%|█████████ | 23494/25880 [4:47:36<29:47,  1.34it/s]
1|23495|Loss: 0.9488089084625244:  91%|█████████ | 23494/25880 [4:47:37<29:47,  1.34it/s]
1|23495|Loss: 0.9488089084625244:  91%|█████████ | 23495/25880 [4:47:37<30:37,  1.30it/s]
1|23496|Loss: 0.8592045307159424:  91%|█████████ | 23495/25880 [4:47:37<30:37,  1.30it/s]
1|23496|Loss: 0.8592045307159424:  91%|█████████ | 23496/25880 [4:47:38<29:24,  1.35it/s]
1|23497|Loss: 0.8239598870277405:  91%|█████████ | 23496/25880 [4:47:38<29:24,  1.35it/s]
1|23497|Loss: 0.8239598870277405:  91%|█████████ | 23497/25880 [4:47:39<29:15,  1.36it/s]
1|23498|Loss: 0.8721509575843811:  91%|█████████ | 23497/25880 [4:47:39<29:15,  1.36it/s]
1|23498|Loss: 0.8721509575843811:  91%|█████████ | 23498/25880 [4:47:39<28:10,  1.41it/s]
1|23499|Loss: 0.766935408115387:  91%|█████████ | 23498/25880 [4:47:40<28:10,  1.41it/s] 
1|23499|Loss: 0.766935408115387:  91%|█████████ | 23499/25880 [4:47:40<28:10,  1.41it/s]
1|23500|Loss: 0.7312291264533997:  91%|█████████ | 23499/25880 [4:47:40<28:10,  1.41it/s]
1|23500|Loss: 0.7312291264533997:  91%|█████████ | 23500/25880 [4:47:41<28:33,  1.39it/s]
1|23501|Loss: 0.836002767086029:  91%|█████████ | 23500/25880 [4:47:41<28:33,  1.39it/s] 
1|23501|Loss: 0.836002767086029:  91%|█████████ | 23501/25880 [4:47:41<29:31,  1.34it/s]
1|23502|Loss: 0.7020436525344849:  91%|█████████ | 23501/25880 [4:47:42<29:31,  1.34it/s]
1|23502|Loss: 0.7020436525344849:  91%|█████████ | 23502/25880 [4:47:42<30:04,  1.32it/s]
1|23503|Loss: 0.8536974191665649:  91%|█████████ | 23502/25880 [4:47:43<30:04,  1.32it/s]
1|23503|Loss: 0.8536974191665649:  91%|█████████ | 23503/25880 [4:47:43<30:02,  1.32it/s]
1|23504|Loss: 0.6909244060516357:  91%|█████████ | 23503/25880 [4:47:43<30:02,  1.32it/s]
1|23504|Loss: 0.6909244060516357:  91%|█████████ | 23504/25880 [4:47:44<30:38,  1.29it/s]
1|23505|Loss: 0.7909911870956421:  91%|█████████ | 23504/25880 [4:47:44<30:38,  1.29it/s]
1|23505|Loss: 0.7909911870956421:  91%|█████████ | 23505/25880 [4:47:44<30:04,  1.32it/s]
1|23506|Loss: 0.8449628949165344:  91%|█████████ | 23505/25880 [4:47:45<30:04,  1.32it/s]
1|23506|Loss: 0.8449628949165344:  91%|█████████ | 23506/25880 [4:47:45<26:21,  1.50it/s]
1|23507|Loss: 0.7009665369987488:  91%|█████████ | 23506/25880 [4:47:45<26:21,  1.50it/s]
1|23507|Loss: 0.7009665369987488:  91%|█████████ | 23507/25880 [4:47:46<28:14,  1.40it/s]
1|23508|Loss: 0.7125119566917419:  91%|█████████ | 23507/25880 [4:47:46<28:14,  1.40it/s]
1|23508|Loss: 0.7125119566917419:  91%|█████████ | 23508/25880 [4:47:46<28:00,  1.41it/s]
1|23509|Loss: 0.8632530570030212:  91%|█████████ | 23508/25880 [4:47:47<28:00,  1.41it/s]
1|23509|Loss: 0.8632530570030212:  91%|█████████ | 23509/25880 [4:47:47<28:09,  1.40it/s]
1|23510|Loss: 0.8254535794258118:  91%|█████████ | 23509/25880 [4:47:48<28:09,  1.40it/s]
1|23510|Loss: 0.8254535794258118:  91%|█████████ | 23510/25880 [4:47:48<29:23,  1.34it/s]
1|23511|Loss: 0.8914006352424622:  91%|█████████ | 23510/25880 [4:47:48<29:23,  1.34it/s]
1|23511|Loss: 0.8914006352424622:  91%|█████████ | 23511/25880 [4:47:49<30:58,  1.27it/s]
1|23512|Loss: 0.7435914874076843:  91%|█████████ | 23511/25880 [4:47:49<30:58,  1.27it/s]
1|23512|Loss: 0.7435914874076843:  91%|█████████ | 23512/25880 [4:47:50<33:16,  1.19it/s]
1|23513|Loss: 0.755435049533844:  91%|█████████ | 23512/25880 [4:47:50<33:16,  1.19it/s] 
1|23513|Loss: 0.755435049533844:  91%|████████�� | 23513/25880 [4:47:51<32:41,  1.21it/s]
1|23514|Loss: 0.8335105180740356:  91%|█████████ | 23513/25880 [4:47:51<32:41,  1.21it/s]
1|23514|Loss: 0.8335105180740356:  91%|█████████ | 23514/25880 [4:47:52<32:57,  1.20it/s]
1|23515|Loss: 0.8589010834693909:  91%|█████████ | 23514/25880 [4:47:52<32:57,  1.20it/s]
1|23515|Loss: 0.8589010834693909:  91%|█████████ | 23515/25880 [4:47:52<33:05,  1.19it/s]
1|23516|Loss: 0.6117043495178223:  91%|█████████ | 23515/25880 [4:47:53<33:05,  1.19it/s]
1|23516|Loss: 0.6117043495178223:  91%|█████████ | 23516/25880 [4:47:53<32:38,  1.21it/s]
1|23517|Loss: 0.7501764893531799:  91%|█████████ | 23516/25880 [4:47:54<32:38,  1.21it/s]
1|23517|Loss: 0.7501764893531799:  91%|█████████ | 23517/25880 [4:47:54<30:47,  1.28it/s]
1|23518|Loss: 0.8235030174255371:  91%|█████████ | 23517/25880 [4:47:54<30:47,  1.28it/s]
1|23518|Loss: 0.8235030174255371:  91%|█████████ | 23518/25880 [4:47:55<30:38,  1.29it/s]
1|23519|Loss: 0.7497214674949646:  91%|█████████ | 23518/25880 [4:47:55<30:38,  1.29it/s]
1|23519|Loss: 0.7497214674949646:  91%|█████████ | 23519/25880 [4:47:55<30:20,  1.30it/s]
1|23520|Loss: 0.7398867011070251:  91%|█████████ | 23519/25880 [4:47:56<30:20,  1.30it/s]
1|23520|Loss: 0.7398867011070251:  91%|█████████ | 23520/25880 [4:47:56<29:05,  1.35it/s]
1|23521|Loss: 0.888605535030365:  91%|█████████ | 23520/25880 [4:47:56<29:05,  1.35it/s] 
1|23521|Loss: 0.888605535030365:  91%|█████████ | 23521/25880 [4:47:57<28:45,  1.37it/s]
1|23522|Loss: 0.7922556400299072:  91%|█████████ | 23521/25880 [4:47:57<28:45,  1.37it/s]
1|23522|Loss: 0.7922556400299072:  91%|█████████ | 23522/25880 [4:47:57<28:30,  1.38it/s]
1|23523|Loss: 0.8096359372138977:  91%|█████████ | 23522/25880 [4:47:58<28:30,  1.38it/s]
1|23523|Loss: 0.8096359372138977:  91%|█████████ | 23523/25880 [4:47:58<28:29,  1.38it/s]
1|23524|Loss: 0.9678845405578613:  91%|█████████ | 23523/25880 [4:47:59<28:29,  1.38it/s]
1|23524|Loss: 0.9678845405578613:  91%|█████████ | 23524/25880 [4:47:59<27:27,  1.43it/s]
1|23525|Loss: 0.8672357201576233:  91%|█████████ | 23524/25880 [4:47:59<27:27,  1.43it/s]
1|23525|Loss: 0.8672357201576233:  91%|█████████ | 23525/25880 [4:48:00<28:58,  1.35it/s]
1|23526|Loss: 0.9007653594017029:  91%|█████████ | 23525/25880 [4:48:00<28:58,  1.35it/s]
1|23526|Loss: 0.9007653594017029:  91%|█████████ | 23526/25880 [4:48:00<29:23,  1.34it/s]
1|23527|Loss: 0.6855212450027466:  91%|█████████ | 23526/25880 [4:48:01<29:23,  1.34it/s]
1|23527|Loss: 0.6855212450027466:  91%|█████████ | 23527/25880 [4:48:01<27:47,  1.41it/s]
1|23528|Loss: 0.7431280016899109:  91%|█████████ | 23527/25880 [4:48:01<27:47,  1.41it/s]
1|23528|Loss: 0.7431280016899109:  91%|█████████ | 23528/25880 [4:48:02<29:27,  1.33it/s]
1|23529|Loss: 0.7209343314170837:  91%|█████████ | 23528/25880 [4:48:02<29:27,  1.33it/s]
1|23529|Loss: 0.7209343314170837:  91%|█████████ | 23529/25880 [4:48:03<28:49,  1.36it/s]
1|23530|Loss: 0.789665699005127:  91%|█████████ | 23529/25880 [4:48:03<28:49,  1.36it/s] 
1|23530|Loss: 0.789665699005127:  91%|█████████ | 23530/25880 [4:48:03<28:19,  1.38it/s]
1|23531|Loss: 0.8287804126739502:  91%|█████████ | 23530/25880 [4:48:04<28:19,  1.38it/s]
1|23531|Loss: 0.8287804126739502:  91%|█████████ | 23531/25880 [4:48:04<29:36,  1.32it/s]
1|23532|Loss: 0.817051351070404:  91%|█████████ | 23531/25880 [4:48:05<29:36,  1.32it/s] 
1|23532|Loss: 0.817051351070404:  91%|█████████ | 23532/25880 [4:48:05<29:26,  1.33it/s]
1|23533|Loss: 0.7776067852973938:  91%|█████████ | 23532/25880 [4:48:05<29:26,  1.33it/s]
1|23533|Loss: 0.7776067852973938:  91%|█████████ | 23533/25880 [4:48:06<29:11,  1.34it/s]
1|23534|Loss: 0.8675646781921387:  91%|█████████ | 23533/25880 [4:48:06<29:11,  1.34it/s]
1|23534|Loss: 0.8675646781921387:  91%|█████████ | 23534/25880 [4:48:06<27:10,  1.44it/s]
1|23535|Loss: 0.8858931660652161:  91%|█████████ | 23534/25880 [4:48:06<27:10,  1.44it/s]
1|23535|Loss: 0.8858931660652161:  91%|█████████ | 23535/25880 [4:48:07<26:15,  1.49it/s]
1|23536|Loss: 0.7440265417098999:  91%|█████████ | 23535/25880 [4:48:07<26:15,  1.49it/s]
1|23536|Loss: 0.7440265417098999:  91%|█████████ | 23536/25880 [4:48:07<26:30,  1.47it/s]
1|23537|Loss: 0.817322313785553:  91%|█████████ | 23536/25880 [4:48:08<26:30,  1.47it/s] 
1|23537|Loss: 0.817322313785553:  91%|█████████ | 23537/25880 [4:48:08<29:38,  1.32it/s]
1|23538|Loss: 0.9473308324813843:  91%|█████████ | 23537/25880 [4:48:09<29:38,  1.32it/s]
1|23538|Loss: 0.9473308324813843:  91%|█████████ | 23538/25880 [4:48:09<29:07,  1.34it/s]
1|23539|Loss: 0.835938572883606:  91%|█████████ | 23538/25880 [4:48:09<29:07,  1.34it/s] 
1|23539|Loss: 0.835938572883606:  91%|█████████ | 23539/25880 [4:48:10<27:05,  1.44it/s]
1|23540|Loss: 0.7507407069206238:  91%|█████████ | 23539/25880 [4:48:10<27:05,  1.44it/s]
1|23540|Loss: 0.7507407069206238:  91%|█████████ | 23540/25880 [4:48:11<29:15,  1.33it/s]
1|23541|Loss: 0.8969679474830627:  91%|█████████ | 23540/25880 [4:48:11<29:15,  1.33it/s]
1|23541|Loss: 0.8969679474830627:  91%|█████████ | 23541/25880 [4:48:11<30:34,  1.27it/s]
1|23542|Loss: 0.8571845293045044:  91%|█████████ | 23541/25880 [4:48:12<30:34,  1.27it/s]
1|23542|Loss: 0.8571845293045044:  91%|█████████ | 23542/25880 [4:48:12<31:08,  1.25it/s]
1|23543|Loss: 0.7851313352584839:  91%|█████████ | 23542/25880 [4:48:13<31:08,  1.25it/s]
1|23543|Loss: 0.7851313352584839:  91%|█████████ | 23543/25880 [4:48:13<29:42,  1.31it/s]
1|23544|Loss: 0.8698192238807678:  91%|█████████ | 23543/25880 [4:48:13<29:42,  1.31it/s]
1|23544|Loss: 0.8698192238807678:  91%|█████████ | 23544/25880 [4:48:14<28:58,  1.34it/s]
1|23545|Loss: 0.915980339050293:  91%|█████████ | 23544/25880 [4:48:14<28:58,  1.34it/s] 
1|23545|Loss: 0.915980339050293:  91%|█████████ | 23545/25880 [4:48:14<29:25,  1.32it/s]
1|23546|Loss: 0.9751651883125305:  91%|█████████ | 23545/25880 [4:48:15<29:25,  1.32it/s]
1|23546|Loss: 0.9751651883125305:  91%|█████████ | 23546/25880 [4:48:15<28:11,  1.38it/s]
1|23547|Loss: 0.8697017431259155:  91%|█████████ | 23546/25880 [4:48:15<28:11,  1.38it/s]
1|23547|Loss: 0.8697017431259155:  91%|█████████ | 23547/25880 [4:48:16<27:06,  1.43it/s]
1|23548|Loss: 0.843989908695221:  91%|█████████ | 23547/25880 [4:48:16<27:06,  1.43it/s] 
1|23548|Loss: 0.843989908695221:  91%|█████████ | 23548/25880 [4:48:16<25:15,  1.54it/s]
1|23549|Loss: 0.926496684551239:  91%|█████████ | 23548/25880 [4:48:17<25:15,  1.54it/s]
1|23549|Loss: 0.926496684551239:  91%|█████████ | 23549/25880 [4:48:17<25:44,  1.51it/s]
1|23550|Loss: 0.9378464221954346:  91%|█████████ | 23549/25880 [4:48:17<25:44,  1.51it/s]
1|23550|Loss: 0.9378464221954346:  91%|█████████ | 23550/25880 [4:48:18<25:50,  1.50it/s]
1|23551|Loss: 0.8236888647079468:  91%|█████████ | 23550/25880 [4:48:18<25:50,  1.50it/s]
1|23551|Loss: 0.8236888647079468:  91%|█████████ | 23551/25880 [4:48:18<26:29,  1.47it/s]
1|23552|Loss: 0.9414309859275818:  91%|█████████ | 23551/25880 [4:48:19<26:29,  1.47it/s]
1|23552|Loss: 0.9414309859275818:  91%|█████████ | 23552/25880 [4:48:19<25:43,  1.51it/s]
1|23553|Loss: 0.8314208984375:  91%|█████████ | 23552/25880 [4:48:19<25:43,  1.51it/s]   
1|23553|Loss: 0.8314208984375:  91%|█████████ | 23553/25880 [4:48:20<24:48,  1.56it/s]
1|23554|Loss: 0.70504230260849:  91%|█████████ | 23553/25880 [4:48:20<24:48,  1.56it/s]
1|23554|Loss: 0.70504230260849:  91%|█████████ | 23554/25880 [4:48:20<27:40,  1.40it/s]
1|23555|Loss: 0.7917848229408264:  91%|█████████ | 23554/25880 [4:48:21<27:40,  1.40it/s]
1|23555|Loss: 0.7917848229408264:  91%|█████████ | 23555/25880 [4:48:21<30:42,  1.26it/s]
1|23556|Loss: 0.787123441696167:  91%|█████████ | 23555/25880 [4:48:22<30:42,  1.26it/s] 
1|23556|Loss: 0.787123441696167:  91%|█████████ | 23556/25880 [4:48:22<31:15,  1.24it/s]
1|23557|Loss: 0.7266884446144104:  91%|█████████ | 23556/25880 [4:48:23<31:15,  1.24it/s]
1|23557|Loss: 0.7266884446144104:  91%|█████████ | 23557/25880 [4:48:23<30:36,  1.27it/s]
1|23558|Loss: 0.7738367915153503:  91%|█████████ | 23557/25880 [4:48:23<30:36,  1.27it/s]
1|23558|Loss: 0.7738367915153503:  91%|█████████ | 23558/25880 [4:48:24<29:46,  1.30it/s]
1|23559|Loss: 0.6888420581817627:  91%|█████████ | 23558/25880 [4:48:24<29:46,  1.30it/s]
1|23559|Loss: 0.6888420581817627:  91%|█████████ | 23559/25880 [4:48:25<30:08,  1.28it/s]
1|23560|Loss: 0.8992882370948792:  91%|█████████ | 23559/25880 [4:48:25<30:08,  1.28it/s]
1|23560|Loss: 0.8992882370948792:  91%|█████████ | 23560/25880 [4:48:25<28:49,  1.34it/s]
1|23561|Loss: 0.8128530979156494:  91%|███████��█ | 23560/25880 [4:48:26<28:49,  1.34it/s]
1|23561|Loss: 0.8128530979156494:  91%|█████████ | 23561/25880 [4:48:26<29:05,  1.33it/s]
1|23562|Loss: 0.7869758009910583:  91%|█████████ | 23561/25880 [4:48:26<29:05,  1.33it/s]
1|23562|Loss: 0.7869758009910583:  91%|█████████ | 23562/25880 [4:48:27<28:59,  1.33it/s]
1|23563|Loss: 0.7890262007713318:  91%|█████████ | 23562/25880 [4:48:27<28:59,  1.33it/s]
1|23563|Loss: 0.7890262007713318:  91%|█████████ | 23563/25880 [4:48:27<28:48,  1.34it/s]
1|23564|Loss: 0.8894934058189392:  91%|█████████ | 23563/25880 [4:48:28<28:48,  1.34it/s]
1|23564|Loss: 0.8894934058189392:  91%|█████████ | 23564/25880 [4:48:28<30:30,  1.27it/s]
1|23565|Loss: 0.8094897270202637:  91%|█████████ | 23564/25880 [4:48:29<30:30,  1.27it/s]
1|23565|Loss: 0.8094897270202637:  91%|█████████ | 23565/25880 [4:48:29<28:25,  1.36it/s]
1|23566|Loss: 0.6644089818000793:  91%|█████████ | 23565/25880 [4:48:29<28:25,  1.36it/s]
1|23566|Loss: 0.6644089818000793:  91%|█████████ | 23566/25880 [4:48:30<28:22,  1.36it/s]
1|23567|Loss: 0.8096717000007629:  91%|█████████ | 23566/25880 [4:48:30<28:22,  1.36it/s]
1|23567|Loss: 0.8096717000007629:  91%|█████████ | 23567/25880 [4:48:30<28:10,  1.37it/s]
1|23568|Loss: 0.9089230895042419:  91%|█████████ | 23567/25880 [4:48:31<28:10,  1.37it/s]
1|23568|Loss: 0.9089230895042419:  91%|█████████ | 23568/25880 [4:48:31<28:50,  1.34it/s]
1|23569|Loss: 0.7290236949920654:  91%|█████████ | 23568/25880 [4:48:32<28:50,  1.34it/s]
1|23569|Loss: 0.7290236949920654:  91%|█████████ | 23569/25880 [4:48:32<28:54,  1.33it/s]
1|23570|Loss: 0.8721427321434021:  91%|█████████ | 23569/25880 [4:48:32<28:54,  1.33it/s]
1|23570|Loss: 0.8721427321434021:  91%|█████████ | 23570/25880 [4:48:33<29:37,  1.30it/s]
1|23571|Loss: 0.8416493535041809:  91%|█████████ | 23570/25880 [4:48:33<29:37,  1.30it/s]
1|23571|Loss: 0.8416493535041809:  91%|█████████ | 23571/25880 [4:48:34<31:03,  1.24it/s]
1|23572|Loss: 0.8209209442138672:  91%|█████████ | 23571/25880 [4:48:34<31:03,  1.24it/s]
1|23572|Loss: 0.8209209442138672:  91%|█████████ | 23572/25880 [4:48:34<29:43,  1.29it/s]
1|23573|Loss: 0.6893100142478943:  91%|█████████ | 23572/25880 [4:48:35<29:43,  1.29it/s]
1|23573|Loss: 0.6893100142478943:  91%|█████████ | 23573/25880 [4:48:35<28:12,  1.36it/s]
1|23574|Loss: 0.8794307708740234:  91%|█████████ | 23573/25880 [4:48:35<28:12,  1.36it/s]
1|23574|Loss: 0.8794307708740234:  91%|█████████ | 23574/25880 [4:48:36<27:42,  1.39it/s]
1|23575|Loss: 0.8786843419075012:  91%|█████████ | 23574/25880 [4:48:36<27:42,  1.39it/s]
1|23575|Loss: 0.8786843419075012:  91%|█████████ | 23575/25880 [4:48:36<26:54,  1.43it/s]
1|23576|Loss: 0.9290539026260376:  91%|█████████ | 23575/25880 [4:48:37<26:54,  1.43it/s]
1|23576|Loss: 0.9290539026260376:  91%|█████████ | 23576/25880 [4:48:37<27:03,  1.42it/s]
1|23577|Loss: 0.84716796875:  91%|█████████ | 23576/25880 [4:48:37<27:03,  1.42it/s]     
1|23577|Loss: 0.84716796875:  91%|█████████ | 23577/25880 [4:48:38<28:13,  1.36it/s]
1|23578|Loss: 0.773576021194458:  91%|█████████ | 23577/25880 [4:48:38<28:13,  1.36it/s]
1|23578|Loss: 0.773576021194458:  91%|█████████ | 23578/25880 [4:48:39<28:55,  1.33it/s]
1|23579|Loss: 0.7245992422103882:  91%|█████████ | 23578/25880 [4:48:39<28:55,  1.33it/s]
1|23579|Loss: 0.7245992422103882:  91%|█████████ | 23579/25880 [4:48:39<29:31,  1.30it/s]
1|23580|Loss: 0.823006272315979:  91%|█████████ | 23579/25880 [4:48:40<29:31,  1.30it/s] 
1|23580|Loss: 0.823006272315979:  91%|█████████ | 23580/25880 [4:48:40<28:10,  1.36it/s]
1|23581|Loss: 0.8275614380836487:  91%|█████████ | 23580/25880 [4:48:40<28:10,  1.36it/s]
1|23581|Loss: 0.8275614380836487:  91%|█████████ | 23581/25880 [4:48:41<27:44,  1.38it/s]
1|23582|Loss: 0.855102002620697:  91%|█████████ | 23581/25880 [4:48:41<27:44,  1.38it/s] 
1|23582|Loss: 0.855102002620697:  91%|█████████ | 23582/25880 [4:48:42<27:31,  1.39it/s]
1|23583|Loss: 0.8892398476600647:  91%|█████████ | 23582/25880 [4:48:42<27:31,  1.39it/s]
1|23583|Loss: 0.8892398476600647:  91%|█████████ | 23583/25880 [4:48:42<27:44,  1.38it/s]
1|23584|Loss: 0.7050954699516296:  91%|█████████ | 23583/25880 [4:48:43<27:44,  1.38it/s]
1|23584|Loss: 0.7050954699516296:  91%|█████████ | 23584/25880 [4:48:43<28:51,  1.33it/s]
1|23585|Loss: 0.7710320949554443:  91%|█████████ | 23584/25880 [4:48:44<28:51,  1.33it/s]
1|23585|Loss: 0.7710320949554443:  91%|█████████ | 23585/25880 [4:48:44<29:50,  1.28it/s]
1|23586|Loss: 0.8586784601211548:  91%|█████████ | 23585/25880 [4:48:44<29:50,  1.28it/s]
1|23586|Loss: 0.8586784601211548:  91%|█████████ | 23586/25880 [4:48:44<26:15,  1.46it/s]
1|23587|Loss: 0.8530451655387878:  91%|█████████ | 23586/25880 [4:48:45<26:15,  1.46it/s]
1|23587|Loss: 0.8530451655387878:  91%|█████████ | 23587/25880 [4:48:45<26:02,  1.47it/s]
1|23588|Loss: 0.7808734178543091:  91%|█████████ | 23587/25880 [4:48:45<26:02,  1.47it/s]
1|23588|Loss: 0.7808734178543091:  91%|█████████ | 23588/25880 [4:48:46<26:24,  1.45it/s]
1|23589|Loss: 0.7888789772987366:  91%|█████████ | 23588/25880 [4:48:46<26:24,  1.45it/s]
1|23589|Loss: 0.7888789772987366:  91%|█████████ | 23589/25880 [4:48:47<26:51,  1.42it/s]
1|23590|Loss: 0.8940605521202087:  91%|█████████ | 23589/25880 [4:48:47<26:51,  1.42it/s]
1|23590|Loss: 0.8940605521202087:  91%|█████████ | 23590/25880 [4:48:47<26:21,  1.45it/s]
1|23591|Loss: 0.8574108481407166:  91%|█████████ | 23590/25880 [4:48:48<26:21,  1.45it/s]
1|23591|Loss: 0.8574108481407166:  91%|█████████ | 23591/25880 [4:48:48<26:23,  1.45it/s]
1|23592|Loss: 0.8501692414283752:  91%|█████████ | 23591/25880 [4:48:48<26:23,  1.45it/s]
1|23592|Loss: 0.8501692414283752:  91%|█████████ | 23592/25880 [4:48:49<27:52,  1.37it/s]
1|23593|Loss: 0.9545819759368896:  91%|█████████ | 23592/25880 [4:48:49<27:52,  1.37it/s]
1|23593|Loss: 0.9545819759368896:  91%|█████████ | 23593/25880 [4:48:49<26:24,  1.44it/s]
1|23594|Loss: 0.9135013222694397:  91%|█████████ | 23593/25880 [4:48:50<26:24,  1.44it/s]
1|23594|Loss: 0.9135013222694397:  91%|█████████ | 23594/25880 [4:48:50<26:30,  1.44it/s]
1|23595|Loss: 0.9186756610870361:  91%|█████████ | 23594/25880 [4:48:50<26:30,  1.44it/s]
1|23595|Loss: 0.9186756610870361:  91%|█████████ | 23595/25880 [4:48:51<27:05,  1.41it/s]
1|23596|Loss: 0.878089964389801:  91%|█████████ | 23595/25880 [4:48:51<27:05,  1.41it/s] 
1|23596|Loss: 0.878089964389801:  91%|█████████ | 23596/25880 [4:48:52<28:15,  1.35it/s]
1|23597|Loss: 0.9395930171012878:  91%|█████████ | 23596/25880 [4:48:52<28:15,  1.35it/s]
1|23597|Loss: 0.9395930171012878:  91%|█████████ | 23597/25880 [4:48:52<29:39,  1.28it/s]
1|23598|Loss: 0.8174288868904114:  91%|█████████ | 23597/25880 [4:48:53<29:39,  1.28it/s]
1|23598|Loss: 0.8174288868904114:  91%|█████████ | 23598/25880 [4:48:53<27:17,  1.39it/s]
1|23599|Loss: 0.8466899394989014:  91%|█████████ | 23598/25880 [4:48:53<27:17,  1.39it/s]
1|23599|Loss: 0.8466899394989014:  91%|█████████ | 23599/25880 [4:48:54<26:54,  1.41it/s]
1|23600|Loss: 0.8218637704849243:  91%|█████████ | 23599/25880 [4:48:54<26:54,  1.41it/s]
1|23600|Loss: 0.8218637704849243:  91%|█████████ | 23600/25880 [4:48:54<28:07,  1.35it/s]
1|23601|Loss: 0.6626893877983093:  91%|█████████ | 23600/25880 [4:48:55<28:07,  1.35it/s]
1|23601|Loss: 0.6626893877983093:  91%|█████████ | 23601/25880 [4:48:55<25:42,  1.48it/s]
1|23602|Loss: 0.8660538792610168:  91%|█████████ | 23601/25880 [4:48:55<25:42,  1.48it/s]
1|23602|Loss: 0.8660538792610168:  91%|█████████ | 23602/25880 [4:48:56<26:26,  1.44it/s]
1|23603|Loss: 0.8183212280273438:  91%|█████████ | 23602/25880 [4:48:56<26:26,  1.44it/s]
1|23603|Loss: 0.8183212280273438:  91%|█████████ | 23603/25880 [4:48:57<28:42,  1.32it/s]
1|23604|Loss: 1.0093965530395508:  91%|█████████ | 23603/25880 [4:48:57<28:42,  1.32it/s]
1|23604|Loss: 1.0093965530395508:  91%|█████████ | 23604/25880 [4:48:57<28:30,  1.33it/s]
1|23605|Loss: 0.7675461769104004:  91%|█████████ | 23604/25880 [4:48:58<28:30,  1.33it/s]
1|23605|Loss: 0.7675461769104004:  91%|█████████ | 23605/25880 [4:48:58<29:49,  1.27it/s]
1|23606|Loss: 0.7709699869155884:  91%|█████████ | 23605/25880 [4:48:59<29:49,  1.27it/s]
1|23606|Loss: 0.7709699869155884:  91%|█████████ | 23606/25880 [4:48:59<29:18,  1.29it/s]
1|23607|Loss: 0.8570908308029175:  91%|█████████ | 23606/25880 [4:48:59<29:18,  1.29it/s]
1|23607|Loss: 0.8570908308029175:  91%|█████████ | 23607/25880 [4:49:00<28:26,  1.33it/s]
1|23608|Loss: 0.8201552033424377:  91%|█████████ | 23607/25880 [4:49:00<28:26,  1.33it/s]
1|23608|Loss: 0.8201552033424377:  91%|████���████ | 23608/25880 [4:49:00<28:12,  1.34it/s]
1|23609|Loss: 0.696588397026062:  91%|█████████ | 23608/25880 [4:49:01<28:12,  1.34it/s] 
1|23609|Loss: 0.696588397026062:  91%|█████████ | 23609/25880 [4:49:01<28:15,  1.34it/s]
1|23610|Loss: 0.7993212938308716:  91%|█████████ | 23609/25880 [4:49:02<28:15,  1.34it/s]
1|23610|Loss: 0.7993212938308716:  91%|█████████ | 23610/25880 [4:49:02<29:24,  1.29it/s]
1|23611|Loss: 0.722118079662323:  91%|█████████ | 23610/25880 [4:49:02<29:24,  1.29it/s] 
1|23611|Loss: 0.722118079662323:  91%|█████████ | 23611/25880 [4:49:03<27:52,  1.36it/s]
1|23612|Loss: 0.6431681513786316:  91%|█████████ | 23611/25880 [4:49:03<27:52,  1.36it/s]
1|23612|Loss: 0.6431681513786316:  91%|█████████ | 23612/25880 [4:49:03<28:16,  1.34it/s]
1|23613|Loss: 0.7999093532562256:  91%|█████████ | 23612/25880 [4:49:04<28:16,  1.34it/s]
1|23613|Loss: 0.7999093532562256:  91%|█████████ | 23613/25880 [4:49:04<28:20,  1.33it/s]
1|23614|Loss: 0.7662672400474548:  91%|█████████ | 23613/25880 [4:49:05<28:20,  1.33it/s]
1|23614|Loss: 0.7662672400474548:  91%|█████████ | 23614/25880 [4:49:05<28:14,  1.34it/s]
1|23615|Loss: 0.7064070701599121:  91%|█████████ | 23614/25880 [4:49:05<28:14,  1.34it/s]
1|23615|Loss: 0.7064070701599121:  91%|█████████ | 23615/25880 [4:49:06<28:05,  1.34it/s]
1|23616|Loss: 0.8529049158096313:  91%|█████████ | 23615/25880 [4:49:06<28:05,  1.34it/s]
1|23616|Loss: 0.8529049158096313:  91%|█████████▏| 23616/25880 [4:49:07<28:53,  1.31it/s]
1|23617|Loss: 0.8117519021034241:  91%|█████████▏| 23616/25880 [4:49:07<28:53,  1.31it/s]
1|23617|Loss: 0.8117519021034241:  91%|█████████▏| 23617/25880 [4:49:07<27:53,  1.35it/s]
1|23618|Loss: 1.0395755767822266:  91%|█████████▏| 23617/25880 [4:49:08<27:53,  1.35it/s]
1|23618|Loss: 1.0395755767822266:  91%|█████████▏| 23618/25880 [4:49:08<25:44,  1.46it/s]
1|23619|Loss: 0.9059486389160156:  91%|█████████▏| 23618/25880 [4:49:08<25:44,  1.46it/s]
1|23619|Loss: 0.9059486389160156:  91%|█████████▏| 23619/25880 [4:49:09<27:00,  1.40it/s]
1|23620|Loss: 0.8031902313232422:  91%|█████████▏| 23619/25880 [4:49:09<27:00,  1.40it/s]
1|23620|Loss: 0.8031902313232422:  91%|█████████▏| 23620/25880 [4:49:09<27:35,  1.36it/s]
1|23621|Loss: 0.8117392063140869:  91%|█████████▏| 23620/25880 [4:49:10<27:35,  1.36it/s]
1|23621|Loss: 0.8117392063140869:  91%|█████████▏| 23621/25880 [4:49:10<26:18,  1.43it/s]
1|23622|Loss: 0.8658377528190613:  91%|█████████▏| 23621/25880 [4:49:10<26:18,  1.43it/s]
1|23622|Loss: 0.8658377528190613:  91%|█████████▏| 23622/25880 [4:49:11<25:30,  1.48it/s]
1|23623|Loss: 0.8468398451805115:  91%|█████████▏| 23622/25880 [4:49:11<25:30,  1.48it/s]
1|23623|Loss: 0.8468398451805115:  91%|█████████▏| 23623/25880 [4:49:11<26:05,  1.44it/s]
1|23624|Loss: 0.6849613189697266:  91%|█████████▏| 23623/25880 [4:49:12<26:05,  1.44it/s]
1|23624|Loss: 0.6849613189697266:  91%|█████████▏| 23624/25880 [4:49:12<25:01,  1.50it/s]
1|23625|Loss: 0.8454383611679077:  91%|█████████▏| 23624/25880 [4:49:12<25:01,  1.50it/s]
1|23625|Loss: 0.8454383611679077:  91%|█████████▏| 23625/25880 [4:49:12<24:20,  1.54it/s]
1|23626|Loss: 0.943622350692749:  91%|█████████▏| 23625/25880 [4:49:13<24:20,  1.54it/s] 
1|23626|Loss: 0.943622350692749:  91%|█████████▏| 23626/25880 [4:49:13<25:55,  1.45it/s]
1|23627|Loss: 0.756453275680542:  91%|█████████▏| 23626/25880 [4:49:14<25:55,  1.45it/s]
1|23627|Loss: 0.756453275680542:  91%|█████████▏| 23627/25880 [4:49:14<27:37,  1.36it/s]
1|23628|Loss: 0.9327210187911987:  91%|█████████▏| 23627/25880 [4:49:15<27:37,  1.36it/s]
1|23628|Loss: 0.9327210187911987:  91%|█████████▏| 23628/25880 [4:49:15<27:56,  1.34it/s]
1|23629|Loss: 0.7546584010124207:  91%|█████████▏| 23628/25880 [4:49:15<27:56,  1.34it/s]
1|23629|Loss: 0.7546584010124207:  91%|█████████▏| 23629/25880 [4:49:16<29:06,  1.29it/s]
1|23630|Loss: 0.9435205459594727:  91%|█████████▏| 23629/25880 [4:49:16<29:06,  1.29it/s]
1|23630|Loss: 0.9435205459594727:  91%|█████████▏| 23630/25880 [4:49:17<29:30,  1.27it/s]
1|23631|Loss: 0.7556544542312622:  91%|█████████▏| 23630/25880 [4:49:17<29:30,  1.27it/s]
1|23631|Loss: 0.7556544542312622:  91%|█████████▏| 23631/25880 [4:49:17<28:01,  1.34it/s]
1|23632|Loss: 0.897434651851654:  91%|���████████▏| 23631/25880 [4:49:18<28:01,  1.34it/s] 
1|23632|Loss: 0.897434651851654:  91%|█████████▏| 23632/25880 [4:49:18<27:22,  1.37it/s]
1|23633|Loss: 0.9551922082901001:  91%|█████████▏| 23632/25880 [4:49:18<27:22,  1.37it/s]
1|23633|Loss: 0.9551922082901001:  91%|█████████▏| 23633/25880 [4:49:19<28:00,  1.34it/s]
1|23634|Loss: 0.8986973166465759:  91%|█████████▏| 23633/25880 [4:49:19<28:00,  1.34it/s]
1|23634|Loss: 0.8986973166465759:  91%|█████████▏| 23634/25880 [4:49:19<26:56,  1.39it/s]
1|23635|Loss: 0.8971816897392273:  91%|█████████▏| 23634/25880 [4:49:20<26:56,  1.39it/s]
1|23635|Loss: 0.8971816897392273:  91%|█████████▏| 23635/25880 [4:49:20<24:17,  1.54it/s]
1|23636|Loss: 0.908043622970581:  91%|█████████▏| 23635/25880 [4:49:20<24:17,  1.54it/s] 
1|23636|Loss: 0.908043622970581:  91%|█████████▏| 23636/25880 [4:49:20<24:18,  1.54it/s]
1|23637|Loss: 0.7306979894638062:  91%|█████████▏| 23636/25880 [4:49:21<24:18,  1.54it/s]
1|23637|Loss: 0.7306979894638062:  91%|█████████▏| 23637/25880 [4:49:21<25:08,  1.49it/s]
1|23638|Loss: 0.7729645371437073:  91%|█████████▏| 23637/25880 [4:49:22<25:08,  1.49it/s]
1|23638|Loss: 0.7729645371437073:  91%|█████████▏| 23638/25880 [4:49:22<24:52,  1.50it/s]
1|23639|Loss: 0.9125936031341553:  91%|█████████▏| 23638/25880 [4:49:22<24:52,  1.50it/s]
1|23639|Loss: 0.9125936031341553:  91%|█████████▏| 23639/25880 [4:49:23<26:44,  1.40it/s]
1|23640|Loss: 0.8906159400939941:  91%|█████████▏| 23639/25880 [4:49:23<26:44,  1.40it/s]
1|23640|Loss: 0.8906159400939941:  91%|█████████▏| 23640/25880 [4:49:23<27:18,  1.37it/s]
1|23641|Loss: 0.6723594665527344:  91%|█████████▏| 23640/25880 [4:49:24<27:18,  1.37it/s]
1|23641|Loss: 0.6723594665527344:  91%|█████████▏| 23641/25880 [4:49:24<26:18,  1.42it/s]
1|23642|Loss: 0.9478519558906555:  91%|█████████▏| 23641/25880 [4:49:25<26:18,  1.42it/s]
1|23642|Loss: 0.9478519558906555:  91%|█████████▏| 23642/25880 [4:49:25<27:30,  1.36it/s]
1|23643|Loss: 0.7742156982421875:  91%|█████████▏| 23642/25880 [4:49:25<27:30,  1.36it/s]
1|23643|Loss: 0.7742156982421875:  91%|█████████▏| 23643/25880 [4:49:26<28:25,  1.31it/s]
1|23644|Loss: 0.818403422832489:  91%|█████████▏| 23643/25880 [4:49:26<28:25,  1.31it/s] 
1|23644|Loss: 0.818403422832489:  91%|█████████▏| 23644/25880 [4:49:26<28:22,  1.31it/s]
1|23645|Loss: 0.8424074649810791:  91%|█████████▏| 23644/25880 [4:49:27<28:22,  1.31it/s]
1|23645|Loss: 0.8424074649810791:  91%|█████████▏| 23645/25880 [4:49:27<29:01,  1.28it/s]
1|23646|Loss: 0.9687972664833069:  91%|█████████▏| 23645/25880 [4:49:28<29:01,  1.28it/s]
1|23646|Loss: 0.9687972664833069:  91%|█████████▏| 23646/25880 [4:49:28<29:35,  1.26it/s]
1|23647|Loss: 0.8427097201347351:  91%|█████████▏| 23646/25880 [4:49:29<29:35,  1.26it/s]
1|23647|Loss: 0.8427097201347351:  91%|█████████▏| 23647/25880 [4:49:29<27:31,  1.35it/s]
1|23648|Loss: 0.7916311621665955:  91%|█████████▏| 23647/25880 [4:49:29<27:31,  1.35it/s]
1|23648|Loss: 0.7916311621665955:  91%|█████████▏| 23648/25880 [4:49:29<25:57,  1.43it/s]
1|23649|Loss: 0.8931517004966736:  91%|█████████▏| 23648/25880 [4:49:30<25:57,  1.43it/s]
1|23649|Loss: 0.8931517004966736:  91%|█████████▏| 23649/25880 [4:49:30<25:49,  1.44it/s]
1|23650|Loss: 0.862226665019989:  91%|█████████▏| 23649/25880 [4:49:30<25:49,  1.44it/s] 
1|23650|Loss: 0.862226665019989:  91%|█████████▏| 23650/25880 [4:49:31<25:56,  1.43it/s]
1|23651|Loss: 0.8609289526939392:  91%|█████████▏| 23650/25880 [4:49:31<25:56,  1.43it/s]
1|23651|Loss: 0.8609289526939392:  91%|█████████▏| 23651/25880 [4:49:31<24:23,  1.52it/s]
1|23652|Loss: 0.9366279244422913:  91%|█████████▏| 23651/25880 [4:49:32<24:23,  1.52it/s]
1|23652|Loss: 0.9366279244422913:  91%|█████████▏| 23652/25880 [4:49:32<23:29,  1.58it/s]
1|23653|Loss: 0.7454434037208557:  91%|█████████▏| 23652/25880 [4:49:32<23:29,  1.58it/s]
1|23653|Loss: 0.7454434037208557:  91%|█████████▏| 23653/25880 [4:49:33<24:13,  1.53it/s]
1|23654|Loss: 0.7730206847190857:  91%|█████████▏| 23653/25880 [4:49:33<24:13,  1.53it/s]
1|23654|Loss: 0.7730206847190857:  91%|█████████▏| 23654/25880 [4:49:34<27:29,  1.35it/s]
1|23655|Loss: 0.7146859169006348:  91%|█████████▏| 23654/25880 [4:49:34<27:29,  1.35it/s]
1|23655|Loss: 0.7146859169006348:  91%|█████████▏| 23655/25880 [4:49:34<26:48,  1.38it/s]
1|23656|Loss: 0.7143332362174988:  91%|█████████▏| 23655/25880 [4:49:35<26:48,  1.38it/s]
1|23656|Loss: 0.7143332362174988:  91%|█████████▏| 23656/25880 [4:49:35<26:33,  1.40it/s]
1|23657|Loss: 0.8633385300636292:  91%|█████████▏| 23656/25880 [4:49:35<26:33,  1.40it/s]
1|23657|Loss: 0.8633385300636292:  91%|█████████▏| 23657/25880 [4:49:36<27:57,  1.33it/s]
1|23658|Loss: 0.7685898542404175:  91%|█████████▏| 23657/25880 [4:49:36<27:57,  1.33it/s]
1|23658|Loss: 0.7685898542404175:  91%|█████████▏| 23658/25880 [4:49:37<28:16,  1.31it/s]
1|23659|Loss: 0.8785569667816162:  91%|█████████▏| 23658/25880 [4:49:37<28:16,  1.31it/s]
1|23659|Loss: 0.8785569667816162:  91%|█████████▏| 23659/25880 [4:49:37<28:05,  1.32it/s]
1|23660|Loss: 0.6508446335792542:  91%|█████████▏| 23659/25880 [4:49:38<28:05,  1.32it/s]
1|23660|Loss: 0.6508446335792542:  91%|█████████▏| 23660/25880 [4:49:38<27:36,  1.34it/s]
1|23661|Loss: 0.8207055926322937:  91%|█████████▏| 23660/25880 [4:49:38<27:36,  1.34it/s]
1|23661|Loss: 0.8207055926322937:  91%|█████████▏| 23661/25880 [4:49:39<27:23,  1.35it/s]
1|23662|Loss: 0.775523841381073:  91%|█████████▏| 23661/25880 [4:49:39<27:23,  1.35it/s] 
1|23662|Loss: 0.775523841381073:  91%|█████████▏| 23662/25880 [4:49:39<25:56,  1.43it/s]
1|23663|Loss: 0.7946805357933044:  91%|█████████▏| 23662/25880 [4:49:40<25:56,  1.43it/s]
1|23663|Loss: 0.7946805357933044:  91%|█████████▏| 23663/25880 [4:49:40<27:08,  1.36it/s]
1|23664|Loss: 0.8939703106880188:  91%|█████████▏| 23663/25880 [4:49:41<27:08,  1.36it/s]
1|23664|Loss: 0.8939703106880188:  91%|█████████▏| 23664/25880 [4:49:41<26:39,  1.39it/s]
1|23665|Loss: 0.8947920799255371:  91%|█████████▏| 23664/25880 [4:49:41<26:39,  1.39it/s]
1|23665|Loss: 0.8947920799255371:  91%|█████████▏| 23665/25880 [4:49:41<25:44,  1.43it/s]
1|23666|Loss: 0.9301960468292236:  91%|█████████▏| 23665/25880 [4:49:42<25:44,  1.43it/s]
1|23666|Loss: 0.9301960468292236:  91%|█████████▏| 23666/25880 [4:49:42<26:26,  1.40it/s]
1|23667|Loss: 0.8351901173591614:  91%|█████████▏| 23666/25880 [4:49:43<26:26,  1.40it/s]
1|23667|Loss: 0.8351901173591614:  91%|█████████▏| 23667/25880 [4:49:43<27:51,  1.32it/s]
1|23668|Loss: 0.664989709854126:  91%|█████████▏| 23667/25880 [4:49:43<27:51,  1.32it/s] 
1|23668|Loss: 0.664989709854126:  91%|█████████▏| 23668/25880 [4:49:44<26:32,  1.39it/s]
1|23669|Loss: 0.8066903948783875:  91%|█████████▏| 23668/25880 [4:49:44<26:32,  1.39it/s]
1|23669|Loss: 0.8066903948783875:  91%|█████████▏| 23669/25880 [4:49:44<24:28,  1.51it/s]
1|23670|Loss: 0.8951352834701538:  91%|█████████▏| 23669/25880 [4:49:45<24:28,  1.51it/s]
1|23670|Loss: 0.8951352834701538:  91%|█████████▏| 23670/25880 [4:49:45<23:23,  1.57it/s]
1|23671|Loss: 0.8583454489707947:  91%|█████████▏| 23670/25880 [4:49:45<23:23,  1.57it/s]
1|23671|Loss: 0.8583454489707947:  91%|█████████▏| 23671/25880 [4:49:46<24:36,  1.50it/s]
1|23672|Loss: 0.9282570481300354:  91%|█████████▏| 23671/25880 [4:49:46<24:36,  1.50it/s]
1|23672|Loss: 0.9282570481300354:  91%|█████████▏| 23672/25880 [4:49:46<25:34,  1.44it/s]
1|23673|Loss: 0.8894862532615662:  91%|█████████▏| 23672/25880 [4:49:47<25:34,  1.44it/s]
1|23673|Loss: 0.8894862532615662:  91%|█████████▏| 23673/25880 [4:49:47<26:34,  1.38it/s]
1|23674|Loss: 0.945113480091095:  91%|█████████▏| 23673/25880 [4:49:48<26:34,  1.38it/s] 
1|23674|Loss: 0.945113480091095:  91%|█████████▏| 23674/25880 [4:49:48<27:45,  1.32it/s]
1|23675|Loss: 0.7364906668663025:  91%|█████████▏| 23674/25880 [4:49:48<27:45,  1.32it/s]
1|23675|Loss: 0.7364906668663025:  91%|█████████▏| 23675/25880 [4:49:49<28:09,  1.31it/s]
1|23676|Loss: 0.7677105665206909:  91%|█████████▏| 23675/25880 [4:49:49<28:09,  1.31it/s]
1|23676|Loss: 0.7677105665206909:  91%|█████████▏| 23676/25880 [4:49:50<28:59,  1.27it/s]
1|23677|Loss: 0.7035481929779053:  91%|█████████▏| 23676/25880 [4:49:50<28:59,  1.27it/s]
1|23677|Loss: 0.7035481929779053:  91%|█████████▏| 23677/25880 [4:49:50<26:46,  1.37it/s]
1|23678|Loss: 0.9562552571296692:  91%|█████████▏| 23677/25880 [4:49:50<26:46,  1.37it/s]
1|23678|Loss: 0.9562552571296692:  91%|█████��███▏| 23678/25880 [4:49:51<24:58,  1.47it/s]
1|23679|Loss: 0.7956950068473816:  91%|█████████▏| 23678/25880 [4:49:51<24:58,  1.47it/s]
1|23679|Loss: 0.7956950068473816:  91%|█████████▏| 23679/25880 [4:49:51<25:42,  1.43it/s]
1|23680|Loss: 0.7366958260536194:  91%|█████████▏| 23679/25880 [4:49:52<25:42,  1.43it/s]
1|23680|Loss: 0.7366958260536194:  91%|█████████▏| 23680/25880 [4:49:52<27:10,  1.35it/s]
1|23681|Loss: 0.7419254779815674:  91%|█████████▏| 23680/25880 [4:49:53<27:10,  1.35it/s]
1|23681|Loss: 0.7419254779815674:  92%|█████████▏| 23681/25880 [4:49:53<28:14,  1.30it/s]
1|23682|Loss: 0.7732099890708923:  92%|█████████▏| 23681/25880 [4:49:54<28:14,  1.30it/s]
1|23682|Loss: 0.7732099890708923:  92%|█████████▏| 23682/25880 [4:49:54<28:04,  1.30it/s]
1|23683|Loss: 0.8721693754196167:  92%|█████████▏| 23682/25880 [4:49:54<28:04,  1.30it/s]
1|23683|Loss: 0.8721693754196167:  92%|█████████▏| 23683/25880 [4:49:55<27:30,  1.33it/s]
1|23684|Loss: 0.8860926628112793:  92%|█████████▏| 23683/25880 [4:49:55<27:30,  1.33it/s]
1|23684|Loss: 0.8860926628112793:  92%|█████████▏| 23684/25880 [4:49:55<27:08,  1.35it/s]
1|23685|Loss: 0.8710339665412903:  92%|█████████▏| 23684/25880 [4:49:56<27:08,  1.35it/s]
1|23685|Loss: 0.8710339665412903:  92%|█████████▏| 23685/25880 [4:49:56<26:49,  1.36it/s]
1|23686|Loss: 0.7510389089584351:  92%|█████████▏| 23685/25880 [4:49:56<26:49,  1.36it/s]
1|23686|Loss: 0.7510389089584351:  92%|█████████▏| 23686/25880 [4:49:57<26:28,  1.38it/s]
1|23687|Loss: 0.7379206418991089:  92%|█████████▏| 23686/25880 [4:49:57<26:28,  1.38it/s]
1|23687|Loss: 0.7379206418991089:  92%|█████████▏| 23687/25880 [4:49:57<26:29,  1.38it/s]
1|23688|Loss: 0.8809519410133362:  92%|█████████▏| 23687/25880 [4:49:58<26:29,  1.38it/s]
1|23688|Loss: 0.8809519410133362:  92%|█████████▏| 23688/25880 [4:49:58<27:38,  1.32it/s]
1|23689|Loss: 0.7767090201377869:  92%|█████████▏| 23688/25880 [4:49:59<27:38,  1.32it/s]
1|23689|Loss: 0.7767090201377869:  92%|█████████▏| 23689/25880 [4:49:59<30:02,  1.22it/s]
1|23690|Loss: 0.9881419539451599:  92%|█████████▏| 23689/25880 [4:50:00<30:02,  1.22it/s]
1|23690|Loss: 0.9881419539451599:  92%|█████████▏| 23690/25880 [4:50:00<28:41,  1.27it/s]
1|23691|Loss: 0.7132924795150757:  92%|█████████▏| 23690/25880 [4:50:00<28:41,  1.27it/s]
1|23691|Loss: 0.7132924795150757:  92%|█████████▏| 23691/25880 [4:50:00<25:23,  1.44it/s]
1|23692|Loss: 0.8762310743331909:  92%|█████████▏| 23691/25880 [4:50:01<25:23,  1.44it/s]
1|23692|Loss: 0.8762310743331909:  92%|█████████▏| 23692/25880 [4:50:01<25:35,  1.43it/s]
1|23693|Loss: 0.8647832274436951:  92%|█████████▏| 23692/25880 [4:50:02<25:35,  1.43it/s]
1|23693|Loss: 0.8647832274436951:  92%|█████████▏| 23693/25880 [4:50:02<25:18,  1.44it/s]
1|23694|Loss: 0.6893680691719055:  92%|█████████▏| 23693/25880 [4:50:02<25:18,  1.44it/s]
1|23694|Loss: 0.6893680691719055:  92%|█████████▏| 23694/25880 [4:50:03<26:10,  1.39it/s]
1|23695|Loss: 0.8020889759063721:  92%|█████████▏| 23694/25880 [4:50:03<26:10,  1.39it/s]
1|23695|Loss: 0.8020889759063721:  92%|█████████▏| 23695/25880 [4:50:03<26:24,  1.38it/s]
1|23696|Loss: 0.8517252802848816:  92%|█████████▏| 23695/25880 [4:50:04<26:24,  1.38it/s]
1|23696|Loss: 0.8517252802848816:  92%|█████████▏| 23696/25880 [4:50:04<27:04,  1.34it/s]
1|23697|Loss: 0.7877439856529236:  92%|█████████▏| 23696/25880 [4:50:05<27:04,  1.34it/s]
1|23697|Loss: 0.7877439856529236:  92%|█████████▏| 23697/25880 [4:50:05<27:42,  1.31it/s]
1|23698|Loss: 0.6814969778060913:  92%|█████████▏| 23697/25880 [4:50:05<27:42,  1.31it/s]
1|23698|Loss: 0.6814969778060913:  92%|█████████▏| 23698/25880 [4:50:06<26:07,  1.39it/s]
1|23699|Loss: 0.7723568677902222:  92%|█████████▏| 23698/25880 [4:50:06<26:07,  1.39it/s]
1|23699|Loss: 0.7723568677902222:  92%|█████████▏| 23699/25880 [4:50:06<24:41,  1.47it/s]
1|23700|Loss: 0.8620677590370178:  92%|█████████▏| 23699/25880 [4:50:07<24:41,  1.47it/s]
1|23700|Loss: 0.8620677590370178:  92%|█████████▏| 23700/25880 [4:50:07<25:48,  1.41it/s]
1|23701|Loss: 0.861640214920044:  92%|█████████▏| 23700/25880 [4:50:07<25:48,  1.41it/s] 
1|23701|Loss: 0.861640214920044:  92%|█████████▏| 23701/25880 [4:50:08<26:16,  1.38it/s]
1|23702|Loss: 0.6278523802757263:  92%|█████████▏| 23701/25880 [4:50:08<26:16,  1.38it/s]
1|23702|Loss: 0.6278523802757263:  92%|█████████▏| 23702/25880 [4:50:09<27:33,  1.32it/s]
1|23703|Loss: 0.8875985741615295:  92%|█████████▏| 23702/25880 [4:50:09<27:33,  1.32it/s]
1|23703|Loss: 0.8875985741615295:  92%|█████████▏| 23703/25880 [4:50:09<28:11,  1.29it/s]
1|23704|Loss: 0.8331528902053833:  92%|█████████▏| 23703/25880 [4:50:10<28:11,  1.29it/s]
1|23704|Loss: 0.8331528902053833:  92%|█████████▏| 23704/25880 [4:50:10<27:53,  1.30it/s]
1|23705|Loss: 0.7759711146354675:  92%|█████████▏| 23704/25880 [4:50:11<27:53,  1.30it/s]
1|23705|Loss: 0.7759711146354675:  92%|█████████▏| 23705/25880 [4:50:11<26:16,  1.38it/s]
1|23706|Loss: 0.7747432589530945:  92%|█████████▏| 23705/25880 [4:50:11<26:16,  1.38it/s]
1|23706|Loss: 0.7747432589530945:  92%|█████████▏| 23706/25880 [4:50:12<27:42,  1.31it/s]
1|23707|Loss: 0.9376103281974792:  92%|█████████▏| 23706/25880 [4:50:12<27:42,  1.31it/s]
1|23707|Loss: 0.9376103281974792:  92%|█████████▏| 23707/25880 [4:50:12<26:13,  1.38it/s]
1|23708|Loss: 0.8650458455085754:  92%|█████████▏| 23707/25880 [4:50:13<26:13,  1.38it/s]
1|23708|Loss: 0.8650458455085754:  92%|█████████▏| 23708/25880 [4:50:13<25:38,  1.41it/s]
1|23709|Loss: 0.7894290685653687:  92%|█████████▏| 23708/25880 [4:50:13<25:38,  1.41it/s]
1|23709|Loss: 0.7894290685653687:  92%|█████████▏| 23709/25880 [4:50:14<25:53,  1.40it/s]
1|23710|Loss: 0.7232139706611633:  92%|█████████▏| 23709/25880 [4:50:14<25:53,  1.40it/s]
1|23710|Loss: 0.7232139706611633:  92%|█████████▏| 23710/25880 [4:50:14<26:12,  1.38it/s]
1|23711|Loss: 0.9099884033203125:  92%|█████████▏| 23710/25880 [4:50:15<26:12,  1.38it/s]
1|23711|Loss: 0.9099884033203125:  92%|█████████▏| 23711/25880 [4:50:15<28:05,  1.29it/s]
1|23712|Loss: 0.8960392475128174:  92%|█████████▏| 23711/25880 [4:50:16<28:05,  1.29it/s]
1|23712|Loss: 0.8960392475128174:  92%|█████████▏| 23712/25880 [4:50:16<29:20,  1.23it/s]
1|23713|Loss: 0.8737787008285522:  92%|█████████▏| 23712/25880 [4:50:17<29:20,  1.23it/s]
1|23713|Loss: 0.8737787008285522:  92%|█████████▏| 23713/25880 [4:50:17<28:59,  1.25it/s]
1|23714|Loss: 0.7153875827789307:  92%|█████████▏| 23713/25880 [4:50:17<28:59,  1.25it/s]
1|23714|Loss: 0.7153875827789307:  92%|█████████▏| 23714/25880 [4:50:18<30:18,  1.19it/s]
1|23715|Loss: 0.8102014064788818:  92%|█████████▏| 23714/25880 [4:50:18<30:18,  1.19it/s]
1|23715|Loss: 0.8102014064788818:  92%|█████████▏| 23715/25880 [4:50:19<29:45,  1.21it/s]
1|23716|Loss: 0.7998676300048828:  92%|█████████▏| 23715/25880 [4:50:19<29:45,  1.21it/s]
1|23716|Loss: 0.7998676300048828:  92%|█████████▏| 23716/25880 [4:50:20<29:49,  1.21it/s]
1|23717|Loss: 0.806644856929779:  92%|█████████▏| 23716/25880 [4:50:20<29:49,  1.21it/s] 
1|23717|Loss: 0.806644856929779:  92%|█████████▏| 23717/25880 [4:50:20<29:44,  1.21it/s]
1|23718|Loss: 0.7676241397857666:  92%|█████████▏| 23717/25880 [4:50:21<29:44,  1.21it/s]
1|23718|Loss: 0.7676241397857666:  92%|█████████▏| 23718/25880 [4:50:21<28:57,  1.24it/s]
1|23719|Loss: 0.8744205236434937:  92%|█████████▏| 23718/25880 [4:50:21<28:57,  1.24it/s]
1|23719|Loss: 0.8744205236434937:  92%|█████████▏| 23719/25880 [4:50:22<26:16,  1.37it/s]
1|23720|Loss: 0.8156328201293945:  92%|█████████▏| 23719/25880 [4:50:22<26:16,  1.37it/s]
1|23720|Loss: 0.8156328201293945:  92%|█████████▏| 23720/25880 [4:50:22<24:54,  1.45it/s]
1|23721|Loss: 0.8354436159133911:  92%|█████████▏| 23720/25880 [4:50:23<24:54,  1.45it/s]
1|23721|Loss: 0.8354436159133911:  92%|█████████▏| 23721/25880 [4:50:23<26:05,  1.38it/s]
1|23722|Loss: 0.8872923254966736:  92%|█████████▏| 23721/25880 [4:50:24<26:05,  1.38it/s]
1|23722|Loss: 0.8872923254966736:  92%|█████████▏| 23722/25880 [4:50:24<26:54,  1.34it/s]
1|23723|Loss: 0.6719624400138855:  92%|█████████▏| 23722/25880 [4:50:24<26:54,  1.34it/s]
1|23723|Loss: 0.6719624400138855:  92%|█████████▏| 23723/25880 [4:50:25<28:32,  1.26it/s]
1|23724|Loss: 0.9016140103340149:  92%|█████████▏| 23723/25880 [4:50:25<28:32,  1.26it/s]
1|23724|Loss: 0.9016140103340149:  92%|█████████▏| 23724/25880 [4:50:26<28:19,  1.27it/s]
1|23725|Loss: 0.7520614862442017:  92%|█████████��| 23724/25880 [4:50:26<28:19,  1.27it/s]
1|23725|Loss: 0.7520614862442017:  92%|█████████▏| 23725/25880 [4:50:26<27:44,  1.29it/s]
1|23726|Loss: 0.8848757147789001:  92%|█████████▏| 23725/25880 [4:50:27<27:44,  1.29it/s]
1|23726|Loss: 0.8848757147789001:  92%|█████████▏| 23726/25880 [4:50:27<29:18,  1.23it/s]
1|23727|Loss: 0.7271465063095093:  92%|█████████▏| 23726/25880 [4:50:28<29:18,  1.23it/s]
1|23727|Loss: 0.7271465063095093:  92%|█████████▏| 23727/25880 [4:50:28<28:54,  1.24it/s]
1|23728|Loss: 0.8599981069564819:  92%|█████████▏| 23727/25880 [4:50:28<28:54,  1.24it/s]
1|23728|Loss: 0.8599981069564819:  92%|█████████▏| 23728/25880 [4:50:29<28:09,  1.27it/s]
1|23729|Loss: 1.112937331199646:  92%|█████████▏| 23728/25880 [4:50:29<28:09,  1.27it/s] 
1|23729|Loss: 1.112937331199646:  92%|█████████▏| 23729/25880 [4:50:30<32:49,  1.09it/s]
1|23730|Loss: 0.8180737495422363:  92%|█████████▏| 23729/25880 [4:50:31<32:49,  1.09it/s]
1|23730|Loss: 0.8180737495422363:  92%|█████████▏| 23730/25880 [4:50:31<33:16,  1.08it/s]
1|23731|Loss: 0.7931292057037354:  92%|█████████▏| 23730/25880 [4:50:31<33:16,  1.08it/s]
1|23731|Loss: 0.7931292057037354:  92%|█████████▏| 23731/25880 [4:50:32<32:23,  1.11it/s]
1|23732|Loss: 0.6609846949577332:  92%|█████████▏| 23731/25880 [4:50:32<32:23,  1.11it/s]
1|23732|Loss: 0.6609846949577332:  92%|█████████▏| 23732/25880 [4:50:32<30:43,  1.17it/s]
1|23733|Loss: 0.902304470539093:  92%|█████████▏| 23732/25880 [4:50:33<30:43,  1.17it/s] 
1|23733|Loss: 0.902304470539093:  92%|█████████▏| 23733/25880 [4:50:33<29:47,  1.20it/s]
1|23734|Loss: 0.750478208065033:  92%|█████████▏| 23733/25880 [4:50:34<29:47,  1.20it/s]
1|23734|Loss: 0.750478208065033:  92%|█████████▏| 23734/25880 [4:50:34<29:05,  1.23it/s]
1|23735|Loss: 0.8295842409133911:  92%|█████████▏| 23734/25880 [4:50:34<29:05,  1.23it/s]
1|23735|Loss: 0.8295842409133911:  92%|█████████▏| 23735/25880 [4:50:35<29:33,  1.21it/s]
1|23736|Loss: 0.8585047125816345:  92%|█████████▏| 23735/25880 [4:50:35<29:33,  1.21it/s]
1|23736|Loss: 0.8585047125816345:  92%|█████████▏| 23736/25880 [4:50:36<27:39,  1.29it/s]
1|23737|Loss: 0.9817366600036621:  92%|█████████▏| 23736/25880 [4:50:36<27:39,  1.29it/s]
1|23737|Loss: 0.9817366600036621:  92%|█████████▏| 23737/25880 [4:50:36<25:39,  1.39it/s]
1|23738|Loss: 0.8478189706802368:  92%|█████████▏| 23737/25880 [4:50:36<25:39,  1.39it/s]
1|23738|Loss: 0.8478189706802368:  92%|█████████▏| 23738/25880 [4:50:37<23:36,  1.51it/s]
1|23739|Loss: 1.116989254951477:  92%|█████████▏| 23738/25880 [4:50:37<23:36,  1.51it/s] 
1|23739|Loss: 1.116989254951477:  92%|█████████▏| 23739/25880 [4:50:37<23:35,  1.51it/s]
1|23740|Loss: 0.8236730098724365:  92%|█████████▏| 23739/25880 [4:50:38<23:35,  1.51it/s]
1|23740|Loss: 0.8236730098724365:  92%|█████████▏| 23740/25880 [4:50:38<23:59,  1.49it/s]
1|23741|Loss: 0.8979208469390869:  92%|█████████▏| 23740/25880 [4:50:38<23:59,  1.49it/s]
1|23741|Loss: 0.8979208469390869:  92%|█████████▏| 23741/25880 [4:50:39<23:32,  1.51it/s]
1|23742|Loss: 0.8133010268211365:  92%|█████████▏| 23741/25880 [4:50:39<23:32,  1.51it/s]
1|23742|Loss: 0.8133010268211365:  92%|█████████▏| 23742/25880 [4:50:39<24:50,  1.43it/s]
1|23743|Loss: 0.806378185749054:  92%|█████████▏| 23742/25880 [4:50:40<24:50,  1.43it/s] 
1|23743|Loss: 0.806378185749054:  92%|█████████▏| 23743/25880 [4:50:40<25:09,  1.42it/s]
1|23744|Loss: 0.7619510889053345:  92%|█████████▏| 23743/25880 [4:50:40<25:09,  1.42it/s]
1|23744|Loss: 0.7619510889053345:  92%|█████████▏| 23744/25880 [4:50:41<23:46,  1.50it/s]
1|23745|Loss: 0.7996302843093872:  92%|█████████▏| 23744/25880 [4:50:41<23:46,  1.50it/s]
1|23745|Loss: 0.7996302843093872:  92%|█████████▏| 23745/25880 [4:50:41<24:03,  1.48it/s]
1|23746|Loss: 0.8711280226707458:  92%|█████████▏| 23745/25880 [4:50:42<24:03,  1.48it/s]
1|23746|Loss: 0.8711280226707458:  92%|█████████▏| 23746/25880 [4:50:42<24:23,  1.46it/s]
1|23747|Loss: 0.8110368251800537:  92%|█████████▏| 23746/25880 [4:50:43<24:23,  1.46it/s]
1|23747|Loss: 0.8110368251800537:  92%|█████████▏| 23747/25880 [4:50:43<25:17,  1.41it/s]
1|23748|Loss: 0.9161549210548401:  92%|█████████▏| 23747/25880 [4:50:43<25:17,  1.41it/s]
1|23748|Loss: 0.9161549210548401:  92%|█████████▏| 23748/25880 [4:50:44<25:25,  1.40it/s]
1|23749|Loss: 0.7675378322601318:  92%|█████████▏| 23748/25880 [4:50:44<25:25,  1.40it/s]
1|23749|Loss: 0.7675378322601318:  92%|█████████▏| 23749/25880 [4:50:44<25:28,  1.39it/s]
1|23750|Loss: 0.7694006562232971:  92%|█████████▏| 23749/25880 [4:50:45<25:28,  1.39it/s]
1|23750|Loss: 0.7694006562232971:  92%|█████████▏| 23750/25880 [4:50:45<26:14,  1.35it/s]
1|23751|Loss: 0.9301822185516357:  92%|█████████▏| 23750/25880 [4:50:46<26:14,  1.35it/s]
1|23751|Loss: 0.9301822185516357:  92%|█████████▏| 23751/25880 [4:50:46<26:03,  1.36it/s]
1|23752|Loss: 0.9258106350898743:  92%|█████████▏| 23751/25880 [4:50:46<26:03,  1.36it/s]
1|23752|Loss: 0.9258106350898743:  92%|█████████▏| 23752/25880 [4:50:47<25:37,  1.38it/s]
1|23753|Loss: 0.7457436323165894:  92%|█████████▏| 23752/25880 [4:50:47<25:37,  1.38it/s]
1|23753|Loss: 0.7457436323165894:  92%|█████████▏| 23753/25880 [4:50:47<25:23,  1.40it/s]
1|23754|Loss: 0.8848727345466614:  92%|█████████▏| 23753/25880 [4:50:48<25:23,  1.40it/s]
1|23754|Loss: 0.8848727345466614:  92%|█████████▏| 23754/25880 [4:50:48<24:30,  1.45it/s]
1|23755|Loss: 0.7395156025886536:  92%|█████████▏| 23754/25880 [4:50:48<24:30,  1.45it/s]
1|23755|Loss: 0.7395156025886536:  92%|█████████▏| 23755/25880 [4:50:48<23:22,  1.52it/s]
1|23756|Loss: 0.8510366678237915:  92%|█████████▏| 23755/25880 [4:50:49<23:22,  1.52it/s]
1|23756|Loss: 0.8510366678237915:  92%|█████████▏| 23756/25880 [4:50:49<23:46,  1.49it/s]
1|23757|Loss: 0.7857068777084351:  92%|█████████▏| 23756/25880 [4:50:50<23:46,  1.49it/s]
1|23757|Loss: 0.7857068777084351:  92%|█████████▏| 23757/25880 [4:50:50<24:29,  1.44it/s]
1|23758|Loss: 0.8655292987823486:  92%|█████████▏| 23757/25880 [4:50:50<24:29,  1.44it/s]
1|23758|Loss: 0.8655292987823486:  92%|█████████▏| 23758/25880 [4:50:51<24:43,  1.43it/s]
1|23759|Loss: 0.9157921671867371:  92%|█████████▏| 23758/25880 [4:50:51<24:43,  1.43it/s]
1|23759|Loss: 0.9157921671867371:  92%|█████████▏| 23759/25880 [4:50:52<27:02,  1.31it/s]
1|23760|Loss: 0.8954020142555237:  92%|█████████▏| 23759/25880 [4:50:52<27:02,  1.31it/s]
1|23760|Loss: 0.8954020142555237:  92%|█████████▏| 23760/25880 [4:50:52<27:14,  1.30it/s]
1|23761|Loss: 0.7678061723709106:  92%|█████████▏| 23760/25880 [4:50:53<27:14,  1.30it/s]
1|23761|Loss: 0.7678061723709106:  92%|█████████▏| 23761/25880 [4:50:53<26:35,  1.33it/s]
1|23762|Loss: 0.8501963019371033:  92%|█████████▏| 23761/25880 [4:50:53<26:35,  1.33it/s]
1|23762|Loss: 0.8501963019371033:  92%|█████████▏| 23762/25880 [4:50:54<25:20,  1.39it/s]
1|23763|Loss: 0.8883006572723389:  92%|█████████▏| 23762/25880 [4:50:54<25:20,  1.39it/s]
1|23763|Loss: 0.8883006572723389:  92%|█████████▏| 23763/25880 [4:50:54<25:02,  1.41it/s]
1|23764|Loss: 0.7824508547782898:  92%|█████████▏| 23763/25880 [4:50:55<25:02,  1.41it/s]
1|23764|Loss: 0.7824508547782898:  92%|█████████▏| 23764/25880 [4:50:55<24:55,  1.42it/s]
1|23765|Loss: 0.813673734664917:  92%|█████████▏| 23764/25880 [4:50:55<24:55,  1.42it/s] 
1|23765|Loss: 0.813673734664917:  92%|█████████▏| 23765/25880 [4:50:56<25:09,  1.40it/s]
1|23766|Loss: 0.8698922991752625:  92%|█████████▏| 23765/25880 [4:50:56<25:09,  1.40it/s]
1|23766|Loss: 0.8698922991752625:  92%|█████████▏| 23766/25880 [4:50:56<24:41,  1.43it/s]
1|23767|Loss: 0.8754829168319702:  92%|█████████▏| 23766/25880 [4:50:57<24:41,  1.43it/s]
1|23767|Loss: 0.8754829168319702:  92%|█████████▏| 23767/25880 [4:50:57<26:02,  1.35it/s]
1|23768|Loss: 0.7771229147911072:  92%|█████████▏| 23767/25880 [4:50:58<26:02,  1.35it/s]
1|23768|Loss: 0.7771229147911072:  92%|█████████▏| 23768/25880 [4:50:58<25:23,  1.39it/s]
1|23769|Loss: 0.8375347852706909:  92%|█████████▏| 23768/25880 [4:50:58<25:23,  1.39it/s]
1|23769|Loss: 0.8375347852706909:  92%|█████████▏| 23769/25880 [4:50:59<25:46,  1.36it/s]
1|23770|Loss: 0.9981325268745422:  92%|█████████▏| 23769/25880 [4:50:59<25:46,  1.36it/s]
1|23770|Loss: 0.9981325268745422:  92%|█████████▏| 23770/25880 [4:50:59<25:52,  1.36it/s]
1|23771|Loss: 0.8766255974769592:  92%|█████████▏| 23770/25880 [4:51:00<25:52,  1.36it/s]
1|23771|Loss: 0.8766255974769592:  92%|█████████▏| 23771/25880 [4:51:00<26:16,  1.34it/s]
1|23772|Loss: 0.8170064091682434:  92%|█████████▏| 23771/25880 [4:51:01<26:16,  1.34it/s]
1|23772|Loss: 0.8170064091682434:  92%|█████████▏| 23772/25880 [4:51:01<24:34,  1.43it/s]
1|23773|Loss: 0.7835049629211426:  92%|█████████▏| 23772/25880 [4:51:01<24:34,  1.43it/s]
1|23773|Loss: 0.7835049629211426:  92%|█████████▏| 23773/25880 [4:51:01<23:26,  1.50it/s]
1|23774|Loss: 0.7191586494445801:  92%|█████████▏| 23773/25880 [4:51:02<23:26,  1.50it/s]
1|23774|Loss: 0.7191586494445801:  92%|█████████▏| 23774/25880 [4:51:02<21:32,  1.63it/s]
1|23775|Loss: 0.847567617893219:  92%|█████████▏| 23774/25880 [4:51:02<21:32,  1.63it/s] 
1|23775|Loss: 0.847567617893219:  92%|█████████▏| 23775/25880 [4:51:03<21:54,  1.60it/s]
1|23776|Loss: 0.7737647891044617:  92%|█████████▏| 23775/25880 [4:51:03<21:54,  1.60it/s]
1|23776|Loss: 0.7737647891044617:  92%|█████████▏| 23776/25880 [4:51:03<22:45,  1.54it/s]
1|23777|Loss: 0.8245043158531189:  92%|█████████▏| 23776/25880 [4:51:04<22:45,  1.54it/s]
1|23777|Loss: 0.8245043158531189:  92%|█████████▏| 23777/25880 [4:51:04<23:43,  1.48it/s]
1|23778|Loss: 0.8137090802192688:  92%|█████████▏| 23777/25880 [4:51:04<23:43,  1.48it/s]
1|23778|Loss: 0.8137090802192688:  92%|█████████▏| 23778/25880 [4:51:05<24:11,  1.45it/s]
1|23779|Loss: 0.8602556586265564:  92%|█████████▏| 23778/25880 [4:51:05<24:11,  1.45it/s]
1|23779|Loss: 0.8602556586265564:  92%|█████████▏| 23779/25880 [4:51:06<25:33,  1.37it/s]
1|23780|Loss: 0.8146641254425049:  92%|█████████▏| 23779/25880 [4:51:06<25:33,  1.37it/s]
1|23780|Loss: 0.8146641254425049:  92%|█████████▏| 23780/25880 [4:51:06<26:44,  1.31it/s]
1|23781|Loss: 0.8495510220527649:  92%|█████████▏| 23780/25880 [4:51:07<26:44,  1.31it/s]
1|23781|Loss: 0.8495510220527649:  92%|█████████▏| 23781/25880 [4:51:07<26:20,  1.33it/s]
1|23782|Loss: 0.7168735861778259:  92%|█████████▏| 23781/25880 [4:51:08<26:20,  1.33it/s]
1|23782|Loss: 0.7168735861778259:  92%|█████████▏| 23782/25880 [4:51:08<26:05,  1.34it/s]
1|23783|Loss: 0.7754623889923096:  92%|█████████▏| 23782/25880 [4:51:08<26:05,  1.34it/s]
1|23783|Loss: 0.7754623889923096:  92%|█████████▏| 23783/25880 [4:51:09<26:10,  1.34it/s]
1|23784|Loss: 0.7360323667526245:  92%|█████████▏| 23783/25880 [4:51:09<26:10,  1.34it/s]
1|23784|Loss: 0.7360323667526245:  92%|█████████▏| 23784/25880 [4:51:09<25:05,  1.39it/s]
1|23785|Loss: 0.8927320837974548:  92%|█████████▏| 23784/25880 [4:51:10<25:05,  1.39it/s]
1|23785|Loss: 0.8927320837974548:  92%|█████████▏| 23785/25880 [4:51:10<24:57,  1.40it/s]
1|23786|Loss: 0.8041991591453552:  92%|█████████▏| 23785/25880 [4:51:10<24:57,  1.40it/s]
1|23786|Loss: 0.8041991591453552:  92%|█████████▏| 23786/25880 [4:51:11<24:19,  1.43it/s]
1|23787|Loss: 0.8259273171424866:  92%|█████████▏| 23786/25880 [4:51:11<24:19,  1.43it/s]
1|23787|Loss: 0.8259273171424866:  92%|█████████▏| 23787/25880 [4:51:11<22:11,  1.57it/s]
1|23788|Loss: 0.8352687954902649:  92%|█████████▏| 23787/25880 [4:51:11<22:11,  1.57it/s]
1|23788|Loss: 0.8352687954902649:  92%|█████████▏| 23788/25880 [4:51:12<20:14,  1.72it/s]
1|23789|Loss: 0.8715158104896545:  92%|█████████▏| 23788/25880 [4:51:12<20:14,  1.72it/s]
1|23789|Loss: 0.8715158104896545:  92%|█████████▏| 23789/25880 [4:51:12<19:54,  1.75it/s]
1|23790|Loss: 0.8769121170043945:  92%|█████████▏| 23789/25880 [4:51:12<19:54,  1.75it/s]
1|23790|Loss: 0.8769121170043945:  92%|█████████▏| 23790/25880 [4:51:13<20:19,  1.71it/s]
1|23791|Loss: 0.8743229508399963:  92%|█████████▏| 23790/25880 [4:51:13<20:19,  1.71it/s]
1|23791|Loss: 0.8743229508399963:  92%|█████████▏| 23791/25880 [4:51:13<21:37,  1.61it/s]
1|23792|Loss: 0.9801486134529114:  92%|█████████▏| 23791/25880 [4:51:14<21:37,  1.61it/s]
1|23792|Loss: 0.9801486134529114:  92%|█████████▏| 23792/25880 [4:51:14<22:43,  1.53it/s]
1|23793|Loss: 0.8124784231185913:  92%|█████████▏| 23792/25880 [4:51:15<22:43,  1.53it/s]
1|23793|Loss: 0.8124784231185913:  92%|█████████▏| 23793/25880 [4:51:15<22:32,  1.54it/s]
1|23794|Loss: 0.9166617393493652:  92%|█████████▏| 23793/25880 [4:51:15<22:32,  1.54it/s]
1|23794|Loss: 0.9166617393493652:  92%|█████████▏| 23794/25880 [4:51:15<22:01,  1.58it/s]
1|23795|Loss: 0.8246919512748718:  92%|█████████▏| 23794/25880 [4:51:16<22:01,  1.58it/s]
1|23795|Loss: 0.8246919512748718:  92%|█████████▏| 23795/25880 [4:51:16<21:55,  1.58it/s]
1|23796|Loss: 0.9350903034210205:  92%|█████████▏| 23795/25880 [4:51:16<21:55,  1.58it/s]
1|23796|Loss: 0.9350903034210205:  92%|█████████▏| 23796/25880 [4:51:17<23:00,  1.51it/s]
1|23797|Loss: 0.8523021340370178:  92%|█████████▏| 23796/25880 [4:51:17<23:00,  1.51it/s]
1|23797|Loss: 0.8523021340370178:  92%|█████████▏| 23797/25880 [4:51:17<23:01,  1.51it/s]
1|23798|Loss: 0.7524314522743225:  92%|█████████▏| 23797/25880 [4:51:18<23:01,  1.51it/s]
1|23798|Loss: 0.7524314522743225:  92%|█████████▏| 23798/25880 [4:51:18<22:44,  1.53it/s]
1|23799|Loss: 0.8205272555351257:  92%|█████████▏| 23798/25880 [4:51:18<22:44,  1.53it/s]
1|23799|Loss: 0.8205272555351257:  92%|█████████▏| 23799/25880 [4:51:19<23:19,  1.49it/s]
1|23800|Loss: 0.8311562538146973:  92%|█████████▏| 23799/25880 [4:51:19<23:19,  1.49it/s]
1|23800|Loss: 0.8311562538146973:  92%|█████████▏| 23800/25880 [4:51:20<23:58,  1.45it/s]
1|23801|Loss: 1.0037689208984375:  92%|█████████▏| 23800/25880 [4:51:20<23:58,  1.45it/s]
1|23801|Loss: 1.0037689208984375:  92%|█████████▏| 23801/25880 [4:51:20<22:57,  1.51it/s]
1|23802|Loss: 0.9047811031341553:  92%|█████████▏| 23801/25880 [4:51:20<22:57,  1.51it/s]
1|23802|Loss: 0.9047811031341553:  92%|█████████▏| 23802/25880 [4:51:21<21:28,  1.61it/s]
1|23803|Loss: 0.9242782592773438:  92%|█████████▏| 23802/25880 [4:51:21<21:28,  1.61it/s]
1|23803|Loss: 0.9242782592773438:  92%|█████████▏| 23803/25880 [4:51:21<22:44,  1.52it/s]
1|23804|Loss: 0.8448028564453125:  92%|█████████▏| 23803/25880 [4:51:22<22:44,  1.52it/s]
1|23804|Loss: 0.8448028564453125:  92%|█████████▏| 23804/25880 [4:51:22<22:40,  1.53it/s]
1|23805|Loss: 0.8977123498916626:  92%|█████████▏| 23804/25880 [4:51:23<22:40,  1.53it/s]
1|23805|Loss: 0.8977123498916626:  92%|█████████▏| 23805/25880 [4:51:23<25:24,  1.36it/s]
1|23806|Loss: 0.8267114162445068:  92%|█████████▏| 23805/25880 [4:51:23<25:24,  1.36it/s]
1|23806|Loss: 0.8267114162445068:  92%|█████████▏| 23806/25880 [4:51:24<25:03,  1.38it/s]
1|23807|Loss: 0.8432595729827881:  92%|█████████▏| 23806/25880 [4:51:24<25:03,  1.38it/s]
1|23807|Loss: 0.8432595729827881:  92%|█████████▏| 23807/25880 [4:51:24<22:51,  1.51it/s]
1|23808|Loss: 0.9130507707595825:  92%|█████████▏| 23807/25880 [4:51:25<22:51,  1.51it/s]
1|23808|Loss: 0.9130507707595825:  92%|█████████▏| 23808/25880 [4:51:25<23:01,  1.50it/s]
1|23809|Loss: 0.8220120668411255:  92%|█████████▏| 23808/25880 [4:51:25<23:01,  1.50it/s]
1|23809|Loss: 0.8220120668411255:  92%|█████████▏| 23809/25880 [4:51:26<22:57,  1.50it/s]
1|23810|Loss: 0.8732874989509583:  92%|█████████▏| 23809/25880 [4:51:26<22:57,  1.50it/s]
1|23810|Loss: 0.8732874989509583:  92%|█████████▏| 23810/25880 [4:51:26<22:30,  1.53it/s]
1|23811|Loss: 0.7456949353218079:  92%|█████████▏| 23810/25880 [4:51:26<22:30,  1.53it/s]
1|23811|Loss: 0.7456949353218079:  92%|█████████▏| 23811/25880 [4:51:27<22:19,  1.54it/s]
1|23812|Loss: 0.8022128343582153:  92%|█████████▏| 23811/25880 [4:51:27<22:19,  1.54it/s]
1|23812|Loss: 0.8022128343582153:  92%|█████████▏| 23812/25880 [4:51:27<21:32,  1.60it/s]
1|23813|Loss: 0.8964013457298279:  92%|█████████▏| 23812/25880 [4:51:28<21:32,  1.60it/s]
1|23813|Loss: 0.8964013457298279:  92%|█████████▏| 23813/25880 [4:51:28<22:27,  1.53it/s]
1|23814|Loss: 0.8984352350234985:  92%|█████████▏| 23813/25880 [4:51:28<22:27,  1.53it/s]
1|23814|Loss: 0.8984352350234985:  92%|█████████▏| 23814/25880 [4:51:29<22:26,  1.53it/s]
1|23815|Loss: 1.0473885536193848:  92%|█████████▏| 23814/25880 [4:51:29<22:26,  1.53it/s]
1|23815|Loss: 1.0473885536193848:  92%|█████████▏| 23815/25880 [4:51:29<22:08,  1.55it/s]
1|23816|Loss: 0.7859523892402649:  92%|█████████▏| 23815/25880 [4:51:30<22:08,  1.55it/s]
1|23816|Loss: 0.7859523892402649:  92%|█████████▏| 23816/25880 [4:51:30<22:06,  1.56it/s]
1|23817|Loss: 0.6667011976242065:  92%|█████████▏| 23816/25880 [4:51:30<22:06,  1.56it/s]
1|23817|Loss: 0.6667011976242065:  92%|█████████▏| 23817/25880 [4:51:31<21:42,  1.58it/s]
1|23818|Loss: 0.8788380026817322:  92%|█████████▏| 23817/25880 [4:51:31<21:42,  1.58it/s]
1|23818|Loss: 0.8788380026817322:  92%|█████████▏| 23818/25880 [4:51:31<23:37,  1.45it/s]
1|23819|Loss: 0.9019120931625366:  92%|█████████▏| 23818/25880 [4:51:32<23:37,  1.45it/s]
1|23819|Loss: 0.9019120931625366:  92%|█████████▏| 23819/25880 [4:51:32<24:50,  1.38it/s]
1|23820|Loss: 0.8384481072425842:  92%|█████████▏| 23819/25880 [4:51:33<24:50,  1.38it/s]
1|23820|Loss: 0.8384481072425842:  92%|█████████▏| 23820/25880 [4:51:33<25:15,  1.36it/s]
1|23821|Loss: 0.9529520869255066:  92%|█████████▏| 23820/25880 [4:51:33<25:15,  1.36it/s]
1|23821|Loss: 0.9529520869255066:  92%|█████████▏| 23821/25880 [4:51:34<24:35,  1.40it/s]
1|23822|Loss: 0.8699362277984619:  92%|█████████▏| 23821/25880 [4:51:34<24:35,  1.40it/s]
1|23822|Loss: 0.8699362277984619:  92%|█████████▏| 23822/25880 [4:51:34<23:48,  1.44it/s]
1|23823|Loss: 0.858028769493103:  92%|█████████▏| 23822/25880 [4:51:35<23:48,  1.44it/s] 
1|23823|Loss: 0.858028769493103:  92%|█████████▏| 23823/25880 [4:51:35<24:12,  1.42it/s]
1|23824|Loss: 0.7981044054031372:  92%|█████████▏| 23823/25880 [4:51:35<24:12,  1.42it/s]
1|23824|Loss: 0.7981044054031372:  92%|█████████▏| 23824/25880 [4:51:36<25:09,  1.36it/s]
1|23825|Loss: 0.8570235967636108:  92%|█████████▏| 23824/25880 [4:51:36<25:09,  1.36it/s]
1|23825|Loss: 0.8570235967636108:  92%|█████████▏| 23825/25880 [4:51:37<26:02,  1.32it/s]
1|23826|Loss: 0.749274730682373:  92%|█████████▏| 23825/25880 [4:51:37<26:02,  1.32it/s] 
1|23826|Loss: 0.749274730682373:  92%|█████████▏| 23826/25880 [4:51:37<25:36,  1.34it/s]
1|23827|Loss: 0.899522066116333:  92%|█████████▏| 23826/25880 [4:51:38<25:36,  1.34it/s]
1|23827|Loss: 0.899522066116333:  92%|█████████▏| 23827/25880 [4:51:38<24:23,  1.40it/s]
1|23828|Loss: 0.761381208896637:  92%|█████████▏| 23827/25880 [4:51:38<24:23,  1.40it/s]
1|23828|Loss: 0.761381208896637:  92%|█████████▏| 23828/25880 [4:51:39<22:57,  1.49it/s]
1|23829|Loss: 0.8609937429428101:  92%|█████████▏| 23828/25880 [4:51:39<22:57,  1.49it/s]
1|23829|Loss: 0.8609937429428101:  92%|█████████▏| 23829/25880 [4:51:39<23:15,  1.47it/s]
1|23830|Loss: 0.7980541586875916:  92%|█████████▏| 23829/25880 [4:51:40<23:15,  1.47it/s]
1|23830|Loss: 0.7980541586875916:  92%|█████████▏| 23830/25880 [4:51:40<21:34,  1.58it/s]
1|23831|Loss: 0.8718901872634888:  92%|█████████▏| 23830/25880 [4:51:40<21:34,  1.58it/s]
1|23831|Loss: 0.8718901872634888:  92%|█████████▏| 23831/25880 [4:51:40<21:12,  1.61it/s]
1|23832|Loss: 0.8691079020500183:  92%|█████████▏| 23831/25880 [4:51:41<21:12,  1.61it/s]
1|23832|Loss: 0.8691079020500183:  92%|█████████▏| 23832/25880 [4:51:41<21:11,  1.61it/s]
1|23833|Loss: 0.8032010197639465:  92%|█████████▏| 23832/25880 [4:51:41<21:11,  1.61it/s]
1|23833|Loss: 0.8032010197639465:  92%|█████████▏| 23833/25880 [4:51:42<21:49,  1.56it/s]
1|23834|Loss: 0.8908783793449402:  92%|█████████▏| 23833/25880 [4:51:42<21:49,  1.56it/s]
1|23834|Loss: 0.8908783793449402:  92%|█████████▏| 23834/25880 [4:51:42<22:28,  1.52it/s]
1|23835|Loss: 0.750611424446106:  92%|█████████▏| 23834/25880 [4:51:43<22:28,  1.52it/s] 
1|23835|Loss: 0.750611424446106:  92%|█████████▏| 23835/25880 [4:51:43<22:14,  1.53it/s]
1|23836|Loss: 0.894599437713623:  92%|█████████▏| 23835/25880 [4:51:43<22:14,  1.53it/s]
1|23836|Loss: 0.894599437713623:  92%|█████████▏| 23836/25880 [4:51:44<22:51,  1.49it/s]
1|23837|Loss: 0.8820692300796509:  92%|█████████▏| 23836/25880 [4:51:44<22:51,  1.49it/s]
1|23837|Loss: 0.8820692300796509:  92%|█████████▏| 23837/25880 [4:51:44<22:16,  1.53it/s]
1|23838|Loss: 0.8887916803359985:  92%|█████████▏| 23837/25880 [4:51:45<22:16,  1.53it/s]
1|23838|Loss: 0.8887916803359985:  92%|█████████▏| 23838/25880 [4:51:45<21:00,  1.62it/s]
1|23839|Loss: 0.8212610483169556:  92%|█████████▏| 23838/25880 [4:51:45<21:00,  1.62it/s]
1|23839|Loss: 0.8212610483169556:  92%|█████████▏| 23839/25880 [4:51:45<20:02,  1.70it/s]
1|23840|Loss: 1.020315170288086:  92%|█████████▏| 23839/25880 [4:51:46<20:02,  1.70it/s] 
1|23840|Loss: 1.020315170288086:  92%|█████████▏| 23840/25880 [4:51:46<20:04,  1.69it/s]
1|23841|Loss: 0.8903043270111084:  92%|█████████▏| 23840/25880 [4:51:46<20:04,  1.69it/s]
1|23841|Loss: 0.8903043270111084:  92%|█████��███▏| 23841/25880 [4:51:47<21:04,  1.61it/s]
1|23842|Loss: 0.9042827486991882:  92%|█████████▏| 23841/25880 [4:51:47<21:04,  1.61it/s]
1|23842|Loss: 0.9042827486991882:  92%|█████████▏| 23842/25880 [4:51:47<21:51,  1.55it/s]
1|23843|Loss: 0.8297343254089355:  92%|█████████▏| 23842/25880 [4:51:48<21:51,  1.55it/s]
1|23843|Loss: 0.8297343254089355:  92%|█████████▏| 23843/25880 [4:51:48<22:40,  1.50it/s]
1|23844|Loss: 0.787480354309082:  92%|█████████▏| 23843/25880 [4:51:48<22:40,  1.50it/s] 
1|23844|Loss: 0.787480354309082:  92%|█████████▏| 23844/25880 [4:51:49<22:32,  1.50it/s]
1|23845|Loss: 0.9985656142234802:  92%|█████████▏| 23844/25880 [4:51:49<22:32,  1.50it/s]
1|23845|Loss: 0.9985656142234802:  92%|█████████▏| 23845/25880 [4:51:49<22:06,  1.53it/s]
1|23846|Loss: 0.8061321377754211:  92%|█████████▏| 23845/25880 [4:51:50<22:06,  1.53it/s]
1|23846|Loss: 0.8061321377754211:  92%|█████████▏| 23846/25880 [4:51:50<22:38,  1.50it/s]
1|23847|Loss: 0.7926802039146423:  92%|█████████▏| 23846/25880 [4:51:51<22:38,  1.50it/s]
1|23847|Loss: 0.7926802039146423:  92%|█████████▏| 23847/25880 [4:51:51<24:19,  1.39it/s]
1|23848|Loss: 0.8439165949821472:  92%|█████████▏| 23847/25880 [4:51:51<24:19,  1.39it/s]
1|23848|Loss: 0.8439165949821472:  92%|█████████▏| 23848/25880 [4:51:52<24:34,  1.38it/s]
1|23849|Loss: 0.7728430032730103:  92%|█████████▏| 23848/25880 [4:51:52<24:34,  1.38it/s]
1|23849|Loss: 0.7728430032730103:  92%|█████████▏| 23849/25880 [4:51:52<24:19,  1.39it/s]
1|23850|Loss: 0.7889906764030457:  92%|█████████▏| 23849/25880 [4:51:53<24:19,  1.39it/s]
1|23850|Loss: 0.7889906764030457:  92%|█████████▏| 23850/25880 [4:51:53<24:11,  1.40it/s]
1|23851|Loss: 0.8522226810455322:  92%|█████████▏| 23850/25880 [4:51:54<24:11,  1.40it/s]
1|23851|Loss: 0.8522226810455322:  92%|█████████▏| 23851/25880 [4:51:54<25:15,  1.34it/s]
1|23852|Loss: 0.7138327360153198:  92%|█████████▏| 23851/25880 [4:51:54<25:15,  1.34it/s]
1|23852|Loss: 0.7138327360153198:  92%|█████████▏| 23852/25880 [4:51:55<24:36,  1.37it/s]
1|23853|Loss: 0.8360413312911987:  92%|█████████▏| 23852/25880 [4:51:55<24:36,  1.37it/s]
1|23853|Loss: 0.8360413312911987:  92%|█████████▏| 23853/25880 [4:51:55<24:29,  1.38it/s]
1|23854|Loss: 0.8031784892082214:  92%|█████████▏| 23853/25880 [4:51:56<24:29,  1.38it/s]
1|23854|Loss: 0.8031784892082214:  92%|█████████▏| 23854/25880 [4:51:56<25:01,  1.35it/s]
1|23855|Loss: 0.9785918593406677:  92%|█████████▏| 23854/25880 [4:51:57<25:01,  1.35it/s]
1|23855|Loss: 0.9785918593406677:  92%|█████████▏| 23855/25880 [4:51:57<24:50,  1.36it/s]
1|23856|Loss: 0.8028488755226135:  92%|█████████▏| 23855/25880 [4:51:57<24:50,  1.36it/s]
1|23856|Loss: 0.8028488755226135:  92%|█████████▏| 23856/25880 [4:51:58<25:13,  1.34it/s]
1|23857|Loss: 0.7778441905975342:  92%|█████████▏| 23856/25880 [4:51:58<25:13,  1.34it/s]
1|23857|Loss: 0.7778441905975342:  92%|█████████▏| 23857/25880 [4:51:58<24:01,  1.40it/s]
1|23858|Loss: 0.7583053112030029:  92%|█████████▏| 23857/25880 [4:51:59<24:01,  1.40it/s]
1|23858|Loss: 0.7583053112030029:  92%|█████████▏| 23858/25880 [4:51:59<23:56,  1.41it/s]
1|23859|Loss: 0.8809284567832947:  92%|█████████▏| 23858/25880 [4:51:59<23:56,  1.41it/s]
1|23859|Loss: 0.8809284567832947:  92%|█████████▏| 23859/25880 [4:52:00<24:44,  1.36it/s]
1|23860|Loss: 0.9436535239219666:  92%|█████████▏| 23859/25880 [4:52:00<24:44,  1.36it/s]
1|23860|Loss: 0.9436535239219666:  92%|█████████▏| 23860/25880 [4:52:00<24:59,  1.35it/s]
1|23861|Loss: 0.870186448097229:  92%|█████████▏| 23860/25880 [4:52:01<24:59,  1.35it/s] 
1|23861|Loss: 0.870186448097229:  92%|█████████▏| 23861/25880 [4:52:01<22:42,  1.48it/s]
1|23862|Loss: 0.7888306975364685:  92%|█████████▏| 23861/25880 [4:52:01<22:42,  1.48it/s]
1|23862|Loss: 0.7888306975364685:  92%|█████████▏| 23862/25880 [4:52:02<22:34,  1.49it/s]
1|23863|Loss: 0.8083256483078003:  92%|█████████▏| 23862/25880 [4:52:02<22:34,  1.49it/s]
1|23863|Loss: 0.8083256483078003:  92%|█████████▏| 23863/25880 [4:52:03<24:41,  1.36it/s]
1|23864|Loss: 0.8530177474021912:  92%|█████████▏| 23863/25880 [4:52:03<24:41,  1.36it/s]
1|23864|Loss: 0.8530177474021912:  92%|█████████▏| 23864/25880 [4:52:03<24:15,  1.39it/s]
1|23865|Loss: 0.738609790802002:  92%|█████████▏| 23864/25880 [4:52:04<24:15,  1.39it/s] 
1|23865|Loss: 0.738609790802002:  92%|█████████▏| 23865/25880 [4:52:04<25:16,  1.33it/s]
1|23866|Loss: 0.9289151430130005:  92%|█████████▏| 23865/25880 [4:52:04<25:16,  1.33it/s]
1|23866|Loss: 0.9289151430130005:  92%|█████████▏| 23866/25880 [4:52:05<25:22,  1.32it/s]
1|23867|Loss: 0.8995936512947083:  92%|█████████▏| 23866/25880 [4:52:05<25:22,  1.32it/s]
1|23867|Loss: 0.8995936512947083:  92%|█████████▏| 23867/25880 [4:52:05<24:10,  1.39it/s]
1|23868|Loss: 0.7768276929855347:  92%|█████████▏| 23867/25880 [4:52:06<24:10,  1.39it/s]
1|23868|Loss: 0.7768276929855347:  92%|█████████▏| 23868/25880 [4:52:06<23:53,  1.40it/s]
1|23869|Loss: 0.8056727647781372:  92%|█████████▏| 23868/25880 [4:52:07<23:53,  1.40it/s]
1|23869|Loss: 0.8056727647781372:  92%|█████████▏| 23869/25880 [4:52:07<24:01,  1.40it/s]
1|23870|Loss: 0.8431190252304077:  92%|█████████▏| 23869/25880 [4:52:07<24:01,  1.40it/s]
1|23870|Loss: 0.8431190252304077:  92%|█████████▏| 23870/25880 [4:52:08<24:01,  1.39it/s]
1|23871|Loss: 0.7664514183998108:  92%|█████████▏| 23870/25880 [4:52:08<24:01,  1.39it/s]
1|23871|Loss: 0.7664514183998108:  92%|█████████▏| 23871/25880 [4:52:08<24:41,  1.36it/s]
1|23872|Loss: 0.7552405595779419:  92%|█████████▏| 23871/25880 [4:52:09<24:41,  1.36it/s]
1|23872|Loss: 0.7552405595779419:  92%|█████████▏| 23872/25880 [4:52:09<26:18,  1.27it/s]
1|23873|Loss: 0.8078691959381104:  92%|█████████▏| 23872/25880 [4:52:10<26:18,  1.27it/s]
1|23873|Loss: 0.8078691959381104:  92%|█████████▏| 23873/25880 [4:52:10<25:13,  1.33it/s]
1|23874|Loss: 0.7676663994789124:  92%|█████████▏| 23873/25880 [4:52:10<25:13,  1.33it/s]
1|23874|Loss: 0.7676663994789124:  92%|█████████▏| 23874/25880 [4:52:11<25:19,  1.32it/s]
1|23875|Loss: 0.7261974215507507:  92%|█████████▏| 23874/25880 [4:52:11<25:19,  1.32it/s]
1|23875|Loss: 0.7261974215507507:  92%|█████████▏| 23875/25880 [4:52:12<25:39,  1.30it/s]
1|23876|Loss: 0.841886579990387:  92%|█████████▏| 23875/25880 [4:52:12<25:39,  1.30it/s] 
1|23876|Loss: 0.841886579990387:  92%|█████████▏| 23876/25880 [4:52:12<26:01,  1.28it/s]
1|23877|Loss: 0.858889639377594:  92%|█████████▏| 23876/25880 [4:52:13<26:01,  1.28it/s]
1|23877|Loss: 0.858889639377594:  92%|█████████▏| 23877/25880 [4:52:13<24:48,  1.35it/s]
1|23878|Loss: 0.9007313847541809:  92%|█████████▏| 23877/25880 [4:52:13<24:48,  1.35it/s]
1|23878|Loss: 0.9007313847541809:  92%|█████████▏| 23878/25880 [4:52:14<24:28,  1.36it/s]
1|23879|Loss: 0.8362051844596863:  92%|█████████▏| 23878/25880 [4:52:14<24:28,  1.36it/s]
1|23879|Loss: 0.8362051844596863:  92%|█████████▏| 23879/25880 [4:52:14<23:13,  1.44it/s]
1|23880|Loss: 0.8613876104354858:  92%|█████████▏| 23879/25880 [4:52:15<23:13,  1.44it/s]
1|23880|Loss: 0.8613876104354858:  92%|█████████▏| 23880/25880 [4:52:15<23:15,  1.43it/s]
1|23881|Loss: 0.9506599307060242:  92%|█████████▏| 23880/25880 [4:52:15<23:15,  1.43it/s]
1|23881|Loss: 0.9506599307060242:  92%|█████████▏| 23881/25880 [4:52:16<24:01,  1.39it/s]
1|23882|Loss: 0.900993287563324:  92%|█████████▏| 23881/25880 [4:52:16<24:01,  1.39it/s] 
1|23882|Loss: 0.900993287563324:  92%|█████████▏| 23882/25880 [4:52:17<24:42,  1.35it/s]
1|23883|Loss: 0.9168053269386292:  92%|█████████▏| 23882/25880 [4:52:17<24:42,  1.35it/s]
1|23883|Loss: 0.9168053269386292:  92%|█████████▏| 23883/25880 [4:52:17<24:50,  1.34it/s]
1|23884|Loss: 0.8097214698791504:  92%|█████████▏| 23883/25880 [4:52:18<24:50,  1.34it/s]
1|23884|Loss: 0.8097214698791504:  92%|█████████▏| 23884/25880 [4:52:18<26:21,  1.26it/s]
1|23885|Loss: 0.8351869583129883:  92%|█████████▏| 23884/25880 [4:52:19<26:21,  1.26it/s]
1|23885|Loss: 0.8351869583129883:  92%|█████████▏| 23885/25880 [4:52:19<26:53,  1.24it/s]
1|23886|Loss: 0.8748052716255188:  92%|█████████▏| 23885/25880 [4:52:20<26:53,  1.24it/s]
1|23886|Loss: 0.8748052716255188:  92%|█████████▏| 23886/25880 [4:52:20<26:46,  1.24it/s]
1|23887|Loss: 0.7552592754364014:  92%|█████████▏| 23886/25880 [4:52:20<26:46,  1.24it/s]
1|23887|Loss: 0.7552592754364014:  92%|█████████▏| 23887/25880 [4:52:21<28:02,  1.18it/s]
1|23888|Loss: 0.9024641513824463:  92%|█████████▏| 23887/25880 [4:52:21<28:02,  1.18it/s]
1|23888|Loss: 0.9024641513824463:  92%|█████████▏| 23888/25880 [4:52:22<28:16,  1.17it/s]
1|23889|Loss: 0.8993135690689087:  92%|█████████▏| 23888/25880 [4:52:22<28:16,  1.17it/s]
1|23889|Loss: 0.8993135690689087:  92%|█████████▏| 23889/25880 [4:52:22<25:41,  1.29it/s]
1|23890|Loss: 0.7667655944824219:  92%|█████████▏| 23889/25880 [4:52:23<25:41,  1.29it/s]
1|23890|Loss: 0.7667655944824219:  92%|█████████▏| 23890/25880 [4:52:23<24:34,  1.35it/s]
1|23891|Loss: 0.7642931342124939:  92%|█████████▏| 23890/25880 [4:52:23<24:34,  1.35it/s]
1|23891|Loss: 0.7642931342124939:  92%|█████████▏| 23891/25880 [4:52:24<24:52,  1.33it/s]
1|23892|Loss: 0.6595268249511719:  92%|█████████▏| 23891/25880 [4:52:24<24:52,  1.33it/s]
1|23892|Loss: 0.6595268249511719:  92%|█████████▏| 23892/25880 [4:52:24<24:06,  1.37it/s]
1|23893|Loss: 0.9515564441680908:  92%|█████████▏| 23892/25880 [4:52:25<24:06,  1.37it/s]
1|23893|Loss: 0.9515564441680908:  92%|█████████▏| 23893/25880 [4:52:25<22:01,  1.50it/s]
1|23894|Loss: 0.7590973377227783:  92%|█████████▏| 23893/25880 [4:52:25<22:01,  1.50it/s]
1|23894|Loss: 0.7590973377227783:  92%|█████████▏| 23894/25880 [4:52:26<22:08,  1.50it/s]
1|23895|Loss: 0.8503804802894592:  92%|█████████▏| 23894/25880 [4:52:26<22:08,  1.50it/s]
1|23895|Loss: 0.8503804802894592:  92%|█████████▏| 23895/25880 [4:52:26<22:55,  1.44it/s]
1|23896|Loss: 0.8607180118560791:  92%|█████████▏| 23895/25880 [4:52:27<22:55,  1.44it/s]
1|23896|Loss: 0.8607180118560791:  92%|█████████▏| 23896/25880 [4:52:27<23:52,  1.38it/s]
1|23897|Loss: 0.9077523350715637:  92%|█████████▏| 23896/25880 [4:52:28<23:52,  1.38it/s]
1|23897|Loss: 0.9077523350715637:  92%|█████████▏| 23897/25880 [4:52:28<23:21,  1.42it/s]
1|23898|Loss: 1.0708965063095093:  92%|█████████▏| 23897/25880 [4:52:28<23:21,  1.42it/s]
1|23898|Loss: 1.0708965063095093:  92%|█████████▏| 23898/25880 [4:52:28<21:26,  1.54it/s]
1|23899|Loss: 0.7096089124679565:  92%|█████████▏| 23898/25880 [4:52:29<21:26,  1.54it/s]
1|23899|Loss: 0.7096089124679565:  92%|█████████▏| 23899/25880 [4:52:29<22:29,  1.47it/s]
1|23900|Loss: 0.7903648614883423:  92%|█████████▏| 23899/25880 [4:52:30<22:29,  1.47it/s]
1|23900|Loss: 0.7903648614883423:  92%|█████████▏| 23900/25880 [4:52:30<23:54,  1.38it/s]
1|23901|Loss: 0.9568769931793213:  92%|█████████▏| 23900/25880 [4:52:30<23:54,  1.38it/s]
1|23901|Loss: 0.9568769931793213:  92%|█████████▏| 23901/25880 [4:52:31<24:53,  1.33it/s]
1|23902|Loss: 0.7528191804885864:  92%|█████████▏| 23901/25880 [4:52:31<24:53,  1.33it/s]
1|23902|Loss: 0.7528191804885864:  92%|█████████▏| 23902/25880 [4:52:32<25:22,  1.30it/s]
1|23903|Loss: 0.8784215450286865:  92%|█████████▏| 23902/25880 [4:52:32<25:22,  1.30it/s]
1|23903|Loss: 0.8784215450286865:  92%|█████████▏| 23903/25880 [4:52:32<26:02,  1.27it/s]
1|23904|Loss: 0.8671169877052307:  92%|█████████▏| 23903/25880 [4:52:33<26:02,  1.27it/s]
1|23904|Loss: 0.8671169877052307:  92%|█████████▏| 23904/25880 [4:52:33<25:42,  1.28it/s]
1|23905|Loss: 0.7811152338981628:  92%|█████████▏| 23904/25880 [4:52:33<25:42,  1.28it/s]
1|23905|Loss: 0.7811152338981628:  92%|█████████▏| 23905/25880 [4:52:34<24:29,  1.34it/s]
1|23906|Loss: 0.8889131546020508:  92%|█████████▏| 23905/25880 [4:52:34<24:29,  1.34it/s]
1|23906|Loss: 0.8889131546020508:  92%|█████████▏| 23906/25880 [4:52:35<25:35,  1.29it/s]
1|23907|Loss: 0.8434255719184875:  92%|█████████▏| 23906/25880 [4:52:35<25:35,  1.29it/s]
1|23907|Loss: 0.8434255719184875:  92%|█████████▏| 23907/25880 [4:52:35<26:20,  1.25it/s]
1|23908|Loss: 0.7733311653137207:  92%|█████████▏| 23907/25880 [4:52:36<26:20,  1.25it/s]
1|23908|Loss: 0.7733311653137207:  92%|█████████▏| 23908/25880 [4:52:36<24:47,  1.33it/s]
1|23909|Loss: 0.8827359676361084:  92%|█████████▏| 23908/25880 [4:52:37<24:47,  1.33it/s]
1|23909|Loss: 0.8827359676361084:  92%|█████████▏| 23909/25880 [4:52:37<25:46,  1.27it/s]
1|23910|Loss: 0.8513482213020325:  92%|█████████▏| 23909/25880 [4:52:37<25:46,  1.27it/s]
1|23910|Loss: 0.8513482213020325:  92%|█████████▏| 23910/25880 [4:52:38<25:42,  1.28it/s]
1|23911|Loss: 0.7695024013519287:  92%|█████████▏| 23910/25880 [4:52:38<25:42,  1.28it/s]
1|23911|Loss: 0.7695024013519287:  92%|█████████▏| 23911/25880 [4:52:39<26:05,  1.26it/s]
1|23912|Loss: 0.9322280287742615:  92%|█████████▏| 23911/25880 [4:52:39<26:05,  1.26it/s]
1|23912|Loss: 0.9322280287742615:  92%|█████████▏| 23912/25880 [4:52:39<24:17,  1.35it/s]
1|23913|Loss: 0.9179626703262329:  92%|█████████▏| 23912/25880 [4:52:40<24:17,  1.35it/s]
1|23913|Loss: 0.9179626703262329:  92%|█████████▏| 23913/25880 [4:52:40<23:33,  1.39it/s]
1|23914|Loss: 0.938746452331543:  92%|█████████▏| 23913/25880 [4:52:40<23:33,  1.39it/s] 
1|23914|Loss: 0.938746452331543:  92%|█████████▏| 23914/25880 [4:52:41<23:29,  1.40it/s]
1|23915|Loss: 0.8826801776885986:  92%|█████████▏| 23914/25880 [4:52:41<23:29,  1.40it/s]
1|23915|Loss: 0.8826801776885986:  92%|█████████▏| 23915/25880 [4:52:41<22:51,  1.43it/s]
1|23916|Loss: 0.8840934634208679:  92%|█████████▏| 23915/25880 [4:52:42<22:51,  1.43it/s]
1|23916|Loss: 0.8840934634208679:  92%|█████████▏| 23916/25880 [4:52:42<24:30,  1.34it/s]
1|23917|Loss: 0.9144474864006042:  92%|█████████▏| 23916/25880 [4:52:43<24:30,  1.34it/s]
1|23917|Loss: 0.9144474864006042:  92%|█████████▏| 23917/25880 [4:52:43<25:07,  1.30it/s]
1|23918|Loss: 0.6978360414505005:  92%|█████████▏| 23917/25880 [4:52:43<25:07,  1.30it/s]
1|23918|Loss: 0.6978360414505005:  92%|█████████▏| 23918/25880 [4:52:44<24:03,  1.36it/s]
1|23919|Loss: 0.9144831299781799:  92%|█████████▏| 23918/25880 [4:52:44<24:03,  1.36it/s]
1|23919|Loss: 0.9144831299781799:  92%|█████████▏| 23919/25880 [4:52:44<24:34,  1.33it/s]
1|23920|Loss: 0.8867933750152588:  92%|█████████▏| 23919/25880 [4:52:45<24:34,  1.33it/s]
1|23920|Loss: 0.8867933750152588:  92%|█████████▏| 23920/25880 [4:52:45<25:00,  1.31it/s]
1|23921|Loss: 0.8434110879898071:  92%|█████████▏| 23920/25880 [4:52:46<25:00,  1.31it/s]
1|23921|Loss: 0.8434110879898071:  92%|█████████▏| 23921/25880 [4:52:46<24:38,  1.33it/s]
1|23922|Loss: 0.8024324178695679:  92%|█████████▏| 23921/25880 [4:52:46<24:38,  1.33it/s]
1|23922|Loss: 0.8024324178695679:  92%|█████████▏| 23922/25880 [4:52:47<25:24,  1.28it/s]
1|23923|Loss: 0.8718674182891846:  92%|█████████▏| 23922/25880 [4:52:47<25:24,  1.28it/s]
1|23923|Loss: 0.8718674182891846:  92%|█████████▏| 23923/25880 [4:52:47<23:38,  1.38it/s]
1|23924|Loss: 0.714040994644165:  92%|█████████▏| 23923/25880 [4:52:48<23:38,  1.38it/s] 
1|23924|Loss: 0.714040994644165:  92%|█████████▏| 23924/25880 [4:52:48<22:22,  1.46it/s]
1|23925|Loss: 0.7375752925872803:  92%|█████████▏| 23924/25880 [4:52:48<22:22,  1.46it/s]
1|23925|Loss: 0.7375752925872803:  92%|█████████▏| 23925/25880 [4:52:49<21:52,  1.49it/s]
1|23926|Loss: 0.7668399810791016:  92%|█████████▏| 23925/25880 [4:52:49<21:52,  1.49it/s]
1|23926|Loss: 0.7668399810791016:  92%|█████████▏| 23926/25880 [4:52:49<20:54,  1.56it/s]
1|23927|Loss: 0.7684115171432495:  92%|█████████▏| 23926/25880 [4:52:49<20:54,  1.56it/s]
1|23927|Loss: 0.7684115171432495:  92%|█████████▏| 23927/25880 [4:52:50<21:28,  1.52it/s]
1|23928|Loss: 0.6869840621948242:  92%|█████████▏| 23927/25880 [4:52:50<21:28,  1.52it/s]
1|23928|Loss: 0.6869840621948242:  92%|█████████▏| 23928/25880 [4:52:51<21:32,  1.51it/s]
1|23929|Loss: 0.7065461277961731:  92%|█████████▏| 23928/25880 [4:52:51<21:32,  1.51it/s]
1|23929|Loss: 0.7065461277961731:  92%|█████████▏| 23929/25880 [4:52:51<21:19,  1.52it/s]
1|23930|Loss: 0.8568101525306702:  92%|█████████▏| 23929/25880 [4:52:51<21:19,  1.52it/s]
1|23930|Loss: 0.8568101525306702:  92%|█████████▏| 23930/25880 [4:52:52<20:59,  1.55it/s]
1|23931|Loss: 0.8270336985588074:  92%|█████████▏| 23930/25880 [4:52:52<20:59,  1.55it/s]
1|23931|Loss: 0.8270336985588074:  92%|█████████▏| 23931/25880 [4:52:52<21:37,  1.50it/s]
1|23932|Loss: 0.9040443301200867:  92%|█████████▏| 23931/25880 [4:52:53<21:37,  1.50it/s]
1|23932|Loss: 0.9040443301200867:  92%|█████████▏| 23932/25880 [4:52:53<23:17,  1.39it/s]
1|23933|Loss: 0.8541334271430969:  92%|█████████▏| 23932/25880 [4:52:54<23:17,  1.39it/s]
1|23933|Loss: 0.8541334271430969:  92%|█████████▏| 23933/25880 [4:52:54<22:10,  1.46it/s]
1|23934|Loss: 0.8954614996910095:  92%|█████████▏| 23933/25880 [4:52:54<22:10,  1.46it/s]
1|23934|Loss: 0.8954614996910095:  92%|█████████▏| 23934/25880 [4:52:55<22:45,  1.43it/s]
1|23935|Loss: 0.7466213703155518:  92%|█████████▏| 23934/25880 [4:52:55<22:45,  1.43it/s]
1|23935|Loss: 0.7466213703155518:  92%|█████████▏| 23935/25880 [4:52:55<22:26,  1.44it/s]
1|23936|Loss: 0.8891881704330444:  92%|█████████▏| 23935/25880 [4:52:56<22:26,  1.44it/s]
1|23936|Loss: 0.8891881704330444:  92%|█████████▏| 23936/25880 [4:52:56<23:23,  1.38it/s]
1|23937|Loss: 0.8176097869873047:  92%|█████████▏| 23936/25880 [4:52:57<23:23,  1.38it/s]
1|23937|Loss: 0.8176097869873047:  92%|█████████▏| 23937/25880 [4:52:57<23:47,  1.36it/s]
1|23938|Loss: 0.84510737657547:  92%|█████████▏| 23937/25880 [4:52:57<23:47,  1.36it/s]  
1|23938|Loss: 0.84510737657547:  92%|█████████▏| 23938/25880 [4:52:58<25:49,  1.25it/s]
1|23939|Loss: 0.8541812896728516:  92%|█████████▏| 23938/25880 [4:52:58<25:49,  1.25it/s]
1|23939|Loss: 0.8541812896728516:  92%|█████████▎| 23939/25880 [4:52:59<25:48,  1.25it/s]
1|23940|Loss: 0.8910777568817139:  92%|█████████▎| 23939/25880 [4:52:59<25:48,  1.25it/s]
1|23940|Loss: 0.8910777568817139:  93%|█████████▎| 23940/25880 [4:52:59<26:17,  1.23it/s]
1|23941|Loss: 0.8511659502983093:  93%|█████████▎| 23940/25880 [4:53:00<26:17,  1.23it/s]
1|23941|Loss: 0.8511659502983093:  93%|█████████▎| 23941/25880 [4:53:00<24:55,  1.30it/s]
1|23942|Loss: 0.9710961580276489:  93%|█████████▎| 23941/25880 [4:53:01<24:55,  1.30it/s]
1|23942|Loss: 0.9710961580276489:  93%|█████████▎| 23942/25880 [4:53:01<24:26,  1.32it/s]
1|23943|Loss: 0.8263624906539917:  93%|█████████▎| 23942/25880 [4:53:01<24:26,  1.32it/s]
1|23943|Loss: 0.8263624906539917:  93%|█████████▎| 23943/25880 [4:53:01<22:54,  1.41it/s]
1|23944|Loss: 0.7742549777030945:  93%|█████████▎| 23943/25880 [4:53:02<22:54,  1.41it/s]
1|23944|Loss: 0.7742549777030945:  93%|█████████▎| 23944/25880 [4:53:02<23:35,  1.37it/s]
1|23945|Loss: 0.8456478118896484:  93%|█████████▎| 23944/25880 [4:53:03<23:35,  1.37it/s]
1|23945|Loss: 0.8456478118896484:  93%|█████████▎| 23945/25880 [4:53:03<24:32,  1.31it/s]
1|23946|Loss: 0.8570480346679688:  93%|█████████▎| 23945/25880 [4:53:04<24:32,  1.31it/s]
1|23946|Loss: 0.8570480346679688:  93%|█████████▎| 23946/25880 [4:53:04<25:13,  1.28it/s]
1|23947|Loss: 0.7316416501998901:  93%|█████████▎| 23946/25880 [4:53:04<25:13,  1.28it/s]
1|23947|Loss: 0.7316416501998901:  93%|█████████▎| 23947/25880 [4:53:05<24:46,  1.30it/s]
1|23948|Loss: 0.7444859147071838:  93%|█████████▎| 23947/25880 [4:53:05<24:46,  1.30it/s]
1|23948|Loss: 0.7444859147071838:  93%|█████████▎| 23948/25880 [4:53:05<23:24,  1.38it/s]
1|23949|Loss: 0.9991190433502197:  93%|█████████▎| 23948/25880 [4:53:06<23:24,  1.38it/s]
1|23949|Loss: 0.9991190433502197:  93%|█████████▎| 23949/25880 [4:53:06<23:12,  1.39it/s]
1|23950|Loss: 0.8079689145088196:  93%|█████████▎| 23949/25880 [4:53:06<23:12,  1.39it/s]
1|23950|Loss: 0.8079689145088196:  93%|█████████▎| 23950/25880 [4:53:07<24:11,  1.33it/s]
1|23951|Loss: 0.7447755932807922:  93%|█████████▎| 23950/25880 [4:53:07<24:11,  1.33it/s]
1|23951|Loss: 0.7447755932807922:  93%|█████████▎| 23951/25880 [4:53:08<25:23,  1.27it/s]
1|23952|Loss: 0.9233207106590271:  93%|█████████▎| 23951/25880 [4:53:08<25:23,  1.27it/s]
1|23952|Loss: 0.9233207106590271:  93%|█████████▎| 23952/25880 [4:53:08<24:54,  1.29it/s]
1|23953|Loss: 0.8904427886009216:  93%|█████████▎| 23952/25880 [4:53:09<24:54,  1.29it/s]
1|23953|Loss: 0.8904427886009216:  93%|█████████▎| 23953/25880 [4:53:09<25:28,  1.26it/s]
1|23954|Loss: 0.888842761516571:  93%|█████████▎| 23953/25880 [4:53:10<25:28,  1.26it/s] 
1|23954|Loss: 0.888842761516571:  93%|█████████▎| 23954/25880 [4:53:10<25:56,  1.24it/s]
1|23955|Loss: 0.8569110035896301:  93%|█████████▎| 23954/25880 [4:53:11<25:56,  1.24it/s]
1|23955|Loss: 0.8569110035896301:  93%|█████████▎| 23955/25880 [4:53:11<25:11,  1.27it/s]
1|23956|Loss: 0.8571372628211975:  93%|█████████▎| 23955/25880 [4:53:11<25:11,  1.27it/s]
1|23956|Loss: 0.8571372628211975:  93%|█████████▎| 23956/25880 [4:53:11<22:56,  1.40it/s]
1|23957|Loss: 0.6791531443595886:  93%|█████████▎| 23956/25880 [4:53:12<22:56,  1.40it/s]
1|23957|Loss: 0.6791531443595886:  93%|█████████▎| 23957/25880 [4:53:12<22:42,  1.41it/s]
1|23958|Loss: 0.8345541954040527:  93%|█████████▎| 23957/25880 [4:53:12<22:42,  1.41it/s]
1|23958|Loss: 0.8345541954040527:  93%|█████████▎| 23958/25880 [4:53:13<21:36,  1.48it/s]
1|23959|Loss: 0.7492132782936096:  93%|█████████▎| 23958/25880 [4:53:13<21:36,  1.48it/s]
1|23959|Loss: 0.7492132782936096:  93%|█████████▎| 23959/25880 [4:53:13<21:51,  1.46it/s]
1|23960|Loss: 0.9615524411201477:  93%|█████████▎| 23959/25880 [4:53:14<21:51,  1.46it/s]
1|23960|Loss: 0.9615524411201477:  93%|█████████▎| 23960/25880 [4:53:14<21:02,  1.52it/s]
1|23961|Loss: 0.8654013276100159:  93%|█████████▎| 23960/25880 [4:53:14<21:02,  1.52it/s]
1|23961|Loss: 0.8654013276100159:  93%|█████████▎| 23961/25880 [4:53:15<20:39,  1.55it/s]
1|23962|Loss: 0.9526491761207581:  93%|█████████▎| 23961/25880 [4:53:15<20:39,  1.55it/s]
1|23962|Loss: 0.9526491761207581:  93%|█████████▎| 23962/25880 [4:53:15<21:21,  1.50it/s]
1|23963|Loss: 0.7417513132095337:  93%|█████████▎| 23962/25880 [4:53:16<21:21,  1.50it/s]
1|23963|Loss: 0.7417513132095337:  93%|█████████▎| 23963/25880 [4:53:16<24:07,  1.32it/s]
1|23964|Loss: 0.7655162215232849:  93%|█████████▎| 23963/25880 [4:53:17<24:07,  1.32it/s]
1|23964|Loss: 0.7655162215232849:  93%|█████████▎| 23964/25880 [4:53:17<24:41,  1.29it/s]
1|23965|Loss: 0.8142895102500916:  93%|█████████▎| 23964/25880 [4:53:17<24:41,  1.29it/s]
1|23965|Loss: 0.8142895102500916:  93%|█████████▎| 23965/25880 [4:53:18<24:05,  1.32it/s]
1|23966|Loss: 0.803992748260498:  93%|█████████▎| 23965/25880 [4:53:18<24:05,  1.32it/s] 
1|23966|Loss: 0.803992748260498:  93%|█████████▎| 23966/25880 [4:53:18<22:13,  1.44it/s]
1|23967|Loss: 0.8358051180839539:  93%|█████████▎| 23966/25880 [4:53:19<22:13,  1.44it/s]
1|23967|Loss: 0.8358051180839539:  93%|█████████▎| 23967/25880 [4:53:19<22:15,  1.43it/s]
1|23968|Loss: 0.7716519236564636:  93%|█████████▎| 23967/25880 [4:53:20<22:15,  1.43it/s]
1|23968|Loss: 0.7716519236564636:  93%|█████████▎| 23968/25880 [4:53:20<23:11,  1.37it/s]
1|23969|Loss: 0.8179230093955994:  93%|█████████▎| 23968/25880 [4:53:20<23:11,  1.37it/s]
1|23969|Loss: 0.8179230093955994:  93%|█████████▎| 23969/25880 [4:53:20<21:59,  1.45it/s]
1|23970|Loss: 0.8646175265312195:  93%|█████████▎| 23969/25880 [4:53:21<21:59,  1.45it/s]
1|23970|Loss: 0.8646175265312195:  93%|█████████▎| 23970/25880 [4:53:21<20:28,  1.55it/s]
1|23971|Loss: 0.7839002013206482:  93%|█████████▎| 23970/25880 [4:53:21<20:28,  1.55it/s]
1|23971|Loss: 0.7839002013206482:  93%|█████████▎| 23971/25880 [4:53:22<20:41,  1.54it/s]
1|23972|Loss: 1.2614558935165405:  93%|█████████▎| 23971/25880 [4:53:22<20:41,  1.54it/s]
1|23972|Loss: 1.2614558935165405:  93%|█████████▎| 23972/25880 [4:53:22<21:59,  1.45it/s]
1|23973|Loss: 0.8604485988616943:  93%|█████████▎| 23972/25880 [4:53:23<21:59,  1.45it/s]
1|23973|Loss: 0.8604485988616943:  93%|█████████▎| 23973/25880 [4:53:23<21:48,  1.46it/s]
1|23974|Loss: 0.7671213746070862:  93%|█████████▎| 23973/25880 [4:53:24<21:48,  1.46it/s]
1|23974|Loss: 0.7671213746070862:  93%|█████████▎| 23974/25880 [4:53:24<22:02,  1.44it/s]
1|23975|Loss: 0.7830460071563721:  93%|█████████▎| 23974/25880 [4:53:24<22:02,  1.44it/s]
1|23975|Loss: 0.7830460071563721:  93%|█████████▎| 23975/25880 [4:53:25<22:26,  1.41it/s]
1|23976|Loss: 0.7605305910110474:  93%|█████████▎| 23975/25880 [4:53:25<22:26,  1.41it/s]
1|23976|Loss: 0.7605305910110474:  93%|█████████▎| 23976/25880 [4:53:25<22:00,  1.44it/s]
1|23977|Loss: 0.8468385338783264:  93%|█████████▎| 23976/25880 [4:53:26<22:00,  1.44it/s]
1|23977|Loss: 0.8468385338783264:  93%|█████████▎| 23977/25880 [4:53:26<20:38,  1.54it/s]
1|23978|Loss: 0.7703484892845154:  93%|█████████▎| 23977/25880 [4:53:26<20:38,  1.54it/s]
1|23978|Loss: 0.7703484892845154:  93%|█████████▎| 23978/25880 [4:53:26<20:06,  1.58it/s]
1|23979|Loss: 0.9905303120613098:  93%|█████████▎| 23978/25880 [4:53:27<20:06,  1.58it/s]
1|23979|Loss: 0.9905303120613098:  93%|█████████▎| 23979/25880 [4:53:27<21:32,  1.47it/s]
1|23980|Loss: 0.9088854789733887:  93%|█████████▎| 23979/25880 [4:53:28<21:32,  1.47it/s]
1|23980|Loss: 0.9088854789733887:  93%|█████████▎| 23980/25880 [4:53:28<22:01,  1.44it/s]
1|23981|Loss: 0.7903271913528442:  93%|█████████▎| 23980/25880 [4:53:28<22:01,  1.44it/s]
1|23981|Loss: 0.7903271913528442:  93%|█████████▎| 23981/25880 [4:53:29<22:04,  1.43it/s]
1|23982|Loss: 0.8145015835762024:  93%|█████████▎| 23981/25880 [4:53:29<22:04,  1.43it/s]
1|23982|Loss: 0.8145015835762024:  93%|█████████▎| 23982/25880 [4:53:29<21:36,  1.46it/s]
1|23983|Loss: 0.8974013924598694:  93%|█████████▎| 23982/25880 [4:53:30<21:36,  1.46it/s]
1|23983|Loss: 0.8974013924598694:  93%|█████████▎| 23983/25880 [4:53:30<21:50,  1.45it/s]
1|23984|Loss: 0.8802499175071716:  93%|█████████▎| 23983/25880 [4:53:30<21:50,  1.45it/s]
1|23984|Loss: 0.8802499175071716:  93%|█████████▎| 23984/25880 [4:53:31<23:55,  1.32it/s]
1|23985|Loss: 0.8631203770637512:  93%|█████████▎| 23984/25880 [4:53:31<23:55,  1.32it/s]
1|23985|Loss: 0.8631203770637512:  93%|█████████▎| 23985/25880 [4:53:31<22:07,  1.43it/s]
1|23986|Loss: 0.8516368269920349:  93%|█████████▎| 23985/25880 [4:53:32<22:07,  1.43it/s]
1|23986|Loss: 0.8516368269920349:  93%|█████████▎| 23986/25880 [4:53:32<20:10,  1.57it/s]
1|23987|Loss: 0.739149808883667:  93%|█████████▎| 23986/25880 [4:53:32<20:10,  1.57it/s] 
1|23987|Loss: 0.739149808883667:  93%|█████████▎| 23987/25880 [4:53:33<22:01,  1.43it/s]
1|23988|Loss: 0.9277334809303284:  93%|█████████▎| 23987/25880 [4:53:33<22:01,  1.43it/s]
1|23988|Loss: 0.9277334809303284:  93%|█████████▎| 23988/25880 [4:53:34<23:21,  1.35it/s]
1|23989|Loss: 0.8375604748725891:  93%|█████████▎| 23988/25880 [4:53:34<23:21,  1.35it/s]
1|23989|Loss: 0.8375604748725891:  93%|█████████▎| 23989/25880 [4:53:34<22:35,  1.40it/s]
1|23990|Loss: 0.8362781405448914:  93%|█████████▎| 23989/25880 [4:53:35<22:35,  1.40it/s]
1|23990|Loss: 0.8362781405448914:  93%|█████████▎| 23990/25880 [4:53:35<23:34,  1.34it/s]
1|23991|Loss: 0.7397574186325073:  93%|█████████▎| 23990/25880 [4:53:36<23:34,  1.34it/s]
1|23991|Loss: 0.7397574186325073:  93%|█████████▎| 23991/25880 [4:53:36<24:27,  1.29it/s]
1|23992|Loss: 0.8144830465316772:  93%|█████████▎| 23991/25880 [4:53:36<24:27,  1.29it/s]
1|23992|Loss: 0.8144830465316772:  93%|█████████▎| 23992/25880 [4:53:37<24:33,  1.28it/s]
1|23993|Loss: 0.9314485192298889:  93%|█████████▎| 23992/25880 [4:53:37<24:33,  1.28it/s]
1|23993|Loss: 0.9314485192298889:  93%|█████████▎| 23993/25880 [4:53:37<23:58,  1.31it/s]
1|23994|Loss: 0.9533870220184326:  93%|█████████▎| 23993/25880 [4:53:38<23:58,  1.31it/s]
1|23994|Loss: 0.9533870220184326:  93%|█████████▎| 23994/25880 [4:53:38<23:33,  1.33it/s]
1|23995|Loss: 0.7936104536056519:  93%|█████████▎| 23994/25880 [4:53:39<23:33,  1.33it/s]
1|23995|Loss: 0.7936104536056519:  93%|█████████▎| 23995/25880 [4:53:39<24:03,  1.31it/s]
1|23996|Loss: 0.7836588621139526:  93%|█████████▎| 23995/25880 [4:53:39<24:03,  1.31it/s]
1|23996|Loss: 0.7836588621139526:  93%|█████████▎| 23996/25880 [4:53:40<23:13,  1.35it/s]
1|23997|Loss: 0.9491485357284546:  93%|█████████▎| 23996/25880 [4:53:40<23:13,  1.35it/s]
1|23997|Loss: 0.9491485357284546:  93%|█████████▎| 23997/25880 [4:53:40<22:47,  1.38it/s]
1|23998|Loss: 0.7340101599693298:  93%|█████████▎| 23997/25880 [4:53:41<22:47,  1.38it/s]
1|23998|Loss: 0.7340101599693298:  93%|█████████▎| 23998/25880 [4:53:41<20:55,  1.50it/s]
1|23999|Loss: 0.7230007648468018:  93%|█████████▎| 23998/25880 [4:53:41<20:55,  1.50it/s]
1|23999|Loss: 0.7230007648468018:  93%|█████████▎| 23999/25880 [4:53:41<19:22,  1.62it/s]
1|24000|Loss: 0.8917182683944702:  93%|█████████▎| 23999/25880 [4:53:42<19:22,  1.62it/s]
1|24000|Loss: 0.8917182683944702:  93%|█████████▎| 24000/25880 [4:53:42<19:47,  1.58it/s]
1|24001|Loss: 0.7599037885665894:  93%|█████████▎| 24000/25880 [4:53:42<19:47,  1.58it/s]
1|24001|Loss: 0.7599037885665894:  93%|█████████▎| 24001/25880 [4:53:43<19:57,  1.57it/s]
1|24002|Loss: 0.8546063303947449:  93%|█████████▎| 24001/25880 [4:53:43<19:57,  1.57it/s]
1|24002|Loss: 0.8546063303947449:  93%|█████████▎| 24002/25880 [4:53:43<19:29,  1.61it/s]
1|24003|Loss: 0.9242120385169983:  93%|█████████▎| 24002/25880 [4:53:44<19:29,  1.61it/s]
1|24003|Loss: 0.9242120385169983:  93%|█████████▎| 24003/25880 [4:53:44<20:20,  1.54it/s]
1|24004|Loss: 0.8927781581878662:  93%|█████████▎| 24003/25880 [4:53:44<20:20,  1.54it/s]
1|24004|Loss: 0.8927781581878662:  93%|███��█████▎| 24004/25880 [4:53:45<19:51,  1.57it/s]
1|24005|Loss: 0.7850502133369446:  93%|█████████▎| 24004/25880 [4:53:45<19:51,  1.57it/s]
1|24005|Loss: 0.7850502133369446:  93%|█████████▎| 24005/25880 [4:53:45<18:45,  1.67it/s]
1|24006|Loss: 0.8785638213157654:  93%|█████████▎| 24005/25880 [4:53:45<18:45,  1.67it/s]
1|24006|Loss: 0.8785638213157654:  93%|█████████▎| 24006/25880 [4:53:46<19:19,  1.62it/s]
1|24007|Loss: 0.7590605616569519:  93%|█████████▎| 24006/25880 [4:53:46<19:19,  1.62it/s]
1|24007|Loss: 0.7590605616569519:  93%|█████████▎| 24007/25880 [4:53:46<19:38,  1.59it/s]
1|24008|Loss: 0.71360182762146:  93%|█████████▎| 24007/25880 [4:53:47<19:38,  1.59it/s]  
1|24008|Loss: 0.71360182762146:  93%|█████████▎| 24008/25880 [4:53:47<19:44,  1.58it/s]
1|24009|Loss: 0.8500606417655945:  93%|█████████▎| 24008/25880 [4:53:47<19:44,  1.58it/s]
1|24009|Loss: 0.8500606417655945:  93%|█████████▎| 24009/25880 [4:53:48<19:12,  1.62it/s]
1|24010|Loss: 0.9269662499427795:  93%|█████████▎| 24009/25880 [4:53:48<19:12,  1.62it/s]
1|24010|Loss: 0.9269662499427795:  93%|█████████▎| 24010/25880 [4:53:48<20:24,  1.53it/s]
1|24011|Loss: 0.7329199314117432:  93%|█████████▎| 24010/25880 [4:53:49<20:24,  1.53it/s]
1|24011|Loss: 0.7329199314117432:  93%|█████████▎| 24011/25880 [4:53:49<21:49,  1.43it/s]
1|24012|Loss: 0.8225803971290588:  93%|█████████▎| 24011/25880 [4:53:50<21:49,  1.43it/s]
1|24012|Loss: 0.8225803971290588:  93%|█████████▎| 24012/25880 [4:53:50<22:58,  1.35it/s]
1|24013|Loss: 0.8963813781738281:  93%|█████████▎| 24012/25880 [4:53:50<22:58,  1.35it/s]
1|24013|Loss: 0.8963813781738281:  93%|█████████▎| 24013/25880 [4:53:51<23:38,  1.32it/s]
1|24014|Loss: 0.7524867057800293:  93%|█████████▎| 24013/25880 [4:53:51<23:38,  1.32it/s]
1|24014|Loss: 0.7524867057800293:  93%|█████████▎| 24014/25880 [4:53:52<25:09,  1.24it/s]
1|24015|Loss: 0.9189493060112:  93%|█████████▎| 24014/25880 [4:53:52<25:09,  1.24it/s]   
1|24015|Loss: 0.9189493060112:  93%|█████████▎| 24015/25880 [4:53:53<24:38,  1.26it/s]
1|24016|Loss: 0.714061439037323:  93%|█████████▎| 24015/25880 [4:53:53<24:38,  1.26it/s]
1|24016|Loss: 0.714061439037323:  93%|█████████▎| 24016/25880 [4:53:53<24:42,  1.26it/s]
1|24017|Loss: 0.7989619970321655:  93%|█████████▎| 24016/25880 [4:53:54<24:42,  1.26it/s]
1|24017|Loss: 0.7989619970321655:  93%|█████████▎| 24017/25880 [4:53:54<23:36,  1.32it/s]
1|24018|Loss: 0.8417839407920837:  93%|█████████▎| 24017/25880 [4:53:54<23:36,  1.32it/s]
1|24018|Loss: 0.8417839407920837:  93%|█████████▎| 24018/25880 [4:53:55<22:18,  1.39it/s]
1|24019|Loss: 0.8435677886009216:  93%|█████████▎| 24018/25880 [4:53:55<22:18,  1.39it/s]
1|24019|Loss: 0.8435677886009216:  93%|█████████▎| 24019/25880 [4:53:55<22:09,  1.40it/s]
1|24020|Loss: 0.8066291809082031:  93%|█████████▎| 24019/25880 [4:53:56<22:09,  1.40it/s]
1|24020|Loss: 0.8066291809082031:  93%|█████████▎| 24020/25880 [4:53:56<21:09,  1.47it/s]
1|24021|Loss: 0.8633652925491333:  93%|█████████▎| 24020/25880 [4:53:56<21:09,  1.47it/s]
1|24021|Loss: 0.8633652925491333:  93%|█████████▎| 24021/25880 [4:53:57<20:26,  1.52it/s]
1|24022|Loss: 0.8024482131004333:  93%|█████████▎| 24021/25880 [4:53:57<20:26,  1.52it/s]
1|24022|Loss: 0.8024482131004333:  93%|█████████▎| 24022/25880 [4:53:57<21:53,  1.41it/s]
1|24023|Loss: 0.7010974884033203:  93%|█████████▎| 24022/25880 [4:53:58<21:53,  1.41it/s]
1|24023|Loss: 0.7010974884033203:  93%|█████████▎| 24023/25880 [4:53:58<22:24,  1.38it/s]
1|24024|Loss: 0.852073073387146:  93%|█████████▎| 24023/25880 [4:53:59<22:24,  1.38it/s] 
1|24024|Loss: 0.852073073387146:  93%|█████████▎| 24024/25880 [4:53:59<21:39,  1.43it/s]
1|24025|Loss: 0.7467601895332336:  93%|█████████▎| 24024/25880 [4:53:59<21:39,  1.43it/s]
1|24025|Loss: 0.7467601895332336:  93%|█████████▎| 24025/25880 [4:53:59<20:06,  1.54it/s]
1|24026|Loss: 0.8235566020011902:  93%|█████████▎| 24025/25880 [4:54:00<20:06,  1.54it/s]
1|24026|Loss: 0.8235566020011902:  93%|█████████▎| 24026/25880 [4:54:00<21:12,  1.46it/s]
1|24027|Loss: 0.7398500442504883:  93%|█████████▎| 24026/25880 [4:54:00<21:12,  1.46it/s]
1|24027|Loss: 0.7398500442504883:  93%|█████████▎| 24027/25880 [4:54:01<21:48,  1.42it/s]
1|24028|Loss: 0.9604226350784302:  93%|█████████▎| 24027/25880 [4:54:01<21:48,  1.42it/s]
1|24028|Loss: 0.9604226350784302:  93%|█████████▎| 24028/25880 [4:54:02<21:47,  1.42it/s]
1|24029|Loss: 0.8162963390350342:  93%|█████████▎| 24028/25880 [4:54:02<21:47,  1.42it/s]
1|24029|Loss: 0.8162963390350342:  93%|█████████▎| 24029/25880 [4:54:02<21:17,  1.45it/s]
1|24030|Loss: 0.7958482503890991:  93%|█████████▎| 24029/25880 [4:54:03<21:17,  1.45it/s]
1|24030|Loss: 0.7958482503890991:  93%|█████████▎| 24030/25880 [4:54:03<22:39,  1.36it/s]
1|24031|Loss: 0.8281456232070923:  93%|█████████▎| 24030/25880 [4:54:03<22:39,  1.36it/s]
1|24031|Loss: 0.8281456232070923:  93%|█████████▎| 24031/25880 [4:54:04<23:45,  1.30it/s]
1|24032|Loss: 0.7759379148483276:  93%|█████████▎| 24031/25880 [4:54:04<23:45,  1.30it/s]
1|24032|Loss: 0.7759379148483276:  93%|█████████▎| 24032/25880 [4:54:05<24:58,  1.23it/s]
1|24033|Loss: 1.0087623596191406:  93%|█████████▎| 24032/25880 [4:54:05<24:58,  1.23it/s]
1|24033|Loss: 1.0087623596191406:  93%|█████████▎| 24033/25880 [4:54:06<25:07,  1.23it/s]
1|24034|Loss: 1.01663076877594:  93%|█████████▎| 24033/25880 [4:54:06<25:07,  1.23it/s]  
1|24034|Loss: 1.01663076877594:  93%|█████████▎| 24034/25880 [4:54:06<24:15,  1.27it/s]
1|24035|Loss: 0.7565576434135437:  93%|█████████▎| 24034/25880 [4:54:07<24:15,  1.27it/s]
1|24035|Loss: 0.7565576434135437:  93%|█████████▎| 24035/25880 [4:54:07<24:33,  1.25it/s]
1|24036|Loss: 0.8226324915885925:  93%|█████████▎| 24035/25880 [4:54:08<24:33,  1.25it/s]
1|24036|Loss: 0.8226324915885925:  93%|█████████▎| 24036/25880 [4:54:08<23:20,  1.32it/s]
1|24037|Loss: 0.8099711537361145:  93%|█████████▎| 24036/25880 [4:54:08<23:20,  1.32it/s]
1|24037|Loss: 0.8099711537361145:  93%|█████████▎| 24037/25880 [4:54:09<22:52,  1.34it/s]
1|24038|Loss: 0.7400849461555481:  93%|█████████▎| 24037/25880 [4:54:09<22:52,  1.34it/s]
1|24038|Loss: 0.7400849461555481:  93%|█████████▎| 24038/25880 [4:54:09<21:45,  1.41it/s]
1|24039|Loss: 0.7722269296646118:  93%|█████████▎| 24038/25880 [4:54:10<21:45,  1.41it/s]
1|24039|Loss: 0.7722269296646118:  93%|█████████▎| 24039/25880 [4:54:10<20:48,  1.47it/s]
1|24040|Loss: 0.853894054889679:  93%|█████████▎| 24039/25880 [4:54:10<20:48,  1.47it/s] 
1|24040|Loss: 0.853894054889679:  93%|█████████▎| 24040/25880 [4:54:10<20:54,  1.47it/s]
1|24041|Loss: 0.9601904153823853:  93%|█████████▎| 24040/25880 [4:54:11<20:54,  1.47it/s]
1|24041|Loss: 0.9601904153823853:  93%|█████████▎| 24041/25880 [4:54:11<21:44,  1.41it/s]
1|24042|Loss: 0.6563807129859924:  93%|█████████▎| 24041/25880 [4:54:12<21:44,  1.41it/s]
1|24042|Loss: 0.6563807129859924:  93%|█████████▎| 24042/25880 [4:54:12<19:33,  1.57it/s]
1|24043|Loss: 0.862719714641571:  93%|█████████▎| 24042/25880 [4:54:12<19:33,  1.57it/s] 
1|24043|Loss: 0.862719714641571:  93%|█████████▎| 24043/25880 [4:54:12<20:14,  1.51it/s]
1|24044|Loss: 0.8950750827789307:  93%|█████████▎| 24043/25880 [4:54:13<20:14,  1.51it/s]
1|24044|Loss: 0.8950750827789307:  93%|█████████▎| 24044/25880 [4:54:13<20:21,  1.50it/s]
1|24045|Loss: 0.8282803893089294:  93%|█████████▎| 24044/25880 [4:54:14<20:21,  1.50it/s]
1|24045|Loss: 0.8282803893089294:  93%|█████████▎| 24045/25880 [4:54:14<21:12,  1.44it/s]
1|24046|Loss: 1.0381889343261719:  93%|█████████▎| 24045/25880 [4:54:14<21:12,  1.44it/s]
1|24046|Loss: 1.0381889343261719:  93%|█████████▎| 24046/25880 [4:54:15<22:25,  1.36it/s]
1|24047|Loss: 0.7779472470283508:  93%|█████████▎| 24046/25880 [4:54:15<22:25,  1.36it/s]
1|24047|Loss: 0.7779472470283508:  93%|█████████▎| 24047/25880 [4:54:16<24:34,  1.24it/s]
1|24048|Loss: 0.7759690284729004:  93%|█████████▎| 24047/25880 [4:54:16<24:34,  1.24it/s]
1|24048|Loss: 0.7759690284729004:  93%|█████████▎| 24048/25880 [4:54:16<22:52,  1.33it/s]
1|24049|Loss: 0.7641841173171997:  93%|█████████▎| 24048/25880 [4:54:17<22:52,  1.33it/s]
1|24049|Loss: 0.7641841173171997:  93%|█████████▎| 24049/25880 [4:54:17<21:24,  1.42it/s]
1|24050|Loss: 0.7821425199508667:  93%|█████████▎| 24049/25880 [4:54:17<21:24,  1.42it/s]
1|24050|Loss: 0.7821425199508667:  93%|█████████▎| 24050/25880 [4:54:18<20:47,  1.47it/s]
1|24051|Loss: 0.7819544076919556:  93%|█████████▎| 24050/25880 [4:54:18<20:47,  1.47it/s]
1|24051|Loss: 0.7819544076919556:  93%|█████████▎| 24051/25880 [4:54:18<21:05,  1.44it/s]
1|24052|Loss: 0.8631970882415771:  93%|█████████▎| 24051/25880 [4:54:19<21:05,  1.44it/s]
1|24052|Loss: 0.8631970882415771:  93%|█████████▎| 24052/25880 [4:54:19<21:50,  1.40it/s]
1|24053|Loss: 0.842313826084137:  93%|█████████▎| 24052/25880 [4:54:19<21:50,  1.40it/s] 
1|24053|Loss: 0.842313826084137:  93%|█████████▎| 24053/25880 [4:54:20<23:00,  1.32it/s]
1|24054|Loss: 0.8442257046699524:  93%|█████████▎| 24053/25880 [4:54:20<23:00,  1.32it/s]
1|24054|Loss: 0.8442257046699524:  93%|█████████▎| 24054/25880 [4:54:21<24:01,  1.27it/s]
1|24055|Loss: 0.8771932125091553:  93%|█████████▎| 24054/25880 [4:54:21<24:01,  1.27it/s]
1|24055|Loss: 0.8771932125091553:  93%|█████████▎| 24055/25880 [4:54:21<22:44,  1.34it/s]
1|24056|Loss: 0.7617478370666504:  93%|█████████▎| 24055/25880 [4:54:22<22:44,  1.34it/s]
1|24056|Loss: 0.7617478370666504:  93%|█████████▎| 24056/25880 [4:54:22<21:38,  1.40it/s]
1|24057|Loss: 0.6803016066551208:  93%|█████████▎| 24056/25880 [4:54:22<21:38,  1.40it/s]
1|24057|Loss: 0.6803016066551208:  93%|█████████▎| 24057/25880 [4:54:23<23:00,  1.32it/s]
1|24058|Loss: 0.7974258661270142:  93%|█████████▎| 24057/25880 [4:54:23<23:00,  1.32it/s]
1|24058|Loss: 0.7974258661270142:  93%|█████████▎| 24058/25880 [4:54:24<22:26,  1.35it/s]
1|24059|Loss: 0.7693064212799072:  93%|█████████▎| 24058/25880 [4:54:24<22:26,  1.35it/s]
1|24059|Loss: 0.7693064212799072:  93%|█████████▎| 24059/25880 [4:54:24<22:08,  1.37it/s]
1|24060|Loss: 0.8352369070053101:  93%|█████████▎| 24059/25880 [4:54:25<22:08,  1.37it/s]
1|24060|Loss: 0.8352369070053101:  93%|█████████▎| 24060/25880 [4:54:25<22:52,  1.33it/s]
1|24061|Loss: 0.7977656722068787:  93%|█████████▎| 24060/25880 [4:54:26<22:52,  1.33it/s]
1|24061|Loss: 0.7977656722068787:  93%|█████████▎| 24061/25880 [4:54:26<23:42,  1.28it/s]
1|24062|Loss: 0.811018168926239:  93%|█████████▎| 24061/25880 [4:54:26<23:42,  1.28it/s] 
1|24062|Loss: 0.811018168926239:  93%|█████████▎| 24062/25880 [4:54:27<23:32,  1.29it/s]
1|24063|Loss: 0.8926252126693726:  93%|█████████▎| 24062/25880 [4:54:27<23:32,  1.29it/s]
1|24063|Loss: 0.8926252126693726:  93%|█████████▎| 24063/25880 [4:54:27<22:27,  1.35it/s]
1|24064|Loss: 0.8659085035324097:  93%|█████████▎| 24063/25880 [4:54:28<22:27,  1.35it/s]
1|24064|Loss: 0.8659085035324097:  93%|█████████▎| 24064/25880 [4:54:28<21:05,  1.44it/s]
1|24065|Loss: 0.7586049437522888:  93%|█████████▎| 24064/25880 [4:54:28<21:05,  1.44it/s]
1|24065|Loss: 0.7586049437522888:  93%|█████████▎| 24065/25880 [4:54:29<21:40,  1.40it/s]
1|24066|Loss: 0.8355493545532227:  93%|█████████▎| 24065/25880 [4:54:29<21:40,  1.40it/s]
1|24066|Loss: 0.8355493545532227:  93%|█████████▎| 24066/25880 [4:54:29<21:06,  1.43it/s]
1|24067|Loss: 0.8561814427375793:  93%|█████████▎| 24066/25880 [4:54:30<21:06,  1.43it/s]
1|24067|Loss: 0.8561814427375793:  93%|█████████▎| 24067/25880 [4:54:30<21:14,  1.42it/s]
1|24068|Loss: 0.6901635527610779:  93%|█████████▎| 24067/25880 [4:54:30<21:14,  1.42it/s]
1|24068|Loss: 0.6901635527610779:  93%|█████████▎| 24068/25880 [4:54:31<21:55,  1.38it/s]
1|24069|Loss: 0.8559542298316956:  93%|█████████▎| 24068/25880 [4:54:31<21:55,  1.38it/s]
1|24069|Loss: 0.8559542298316956:  93%|█████████▎| 24069/25880 [4:54:32<22:04,  1.37it/s]
1|24070|Loss: 0.7883571982383728:  93%|█████████▎| 24069/25880 [4:54:32<22:04,  1.37it/s]
1|24070|Loss: 0.7883571982383728:  93%|█████████▎| 24070/25880 [4:54:32<22:10,  1.36it/s]
1|24071|Loss: 0.8627676367759705:  93%|█████████▎| 24070/25880 [4:54:33<22:10,  1.36it/s]
1|24071|Loss: 0.8627676367759705:  93%|█████████▎| 24071/25880 [4:54:33<21:33,  1.40it/s]
1|24072|Loss: 0.721107006072998:  93%|█████████▎| 24071/25880 [4:54:33<21:33,  1.40it/s] 
1|24072|Loss: 0.721107006072998:  93%|█████████▎| 24072/25880 [4:54:34<21:31,  1.40it/s]
1|24073|Loss: 0.7545561194419861:  93%|█████████▎| 24072/25880 [4:54:34<21:31,  1.40it/s]
1|24073|Loss: 0.7545561194419861:  93%|█████████▎| 24073/25880 [4:54:34<21:37,  1.39it/s]
1|24074|Loss: 0.7806439399719238:  93%|█████████▎| 24073/25880 [4:54:35<21:37,  1.39it/s]
1|24074|Loss: 0.7806439399719238:  93%|█████████▎| 24074/25880 [4:54:35<21:47,  1.38it/s]
1|24075|Loss: 0.7929157018661499:  93%|█████████▎| 24074/25880 [4:54:36<21:47,  1.38it/s]
1|24075|Loss: 0.7929157018661499:  93%|█████████▎| 24075/25880 [4:54:36<21:52,  1.37it/s]
1|24076|Loss: 0.697858452796936:  93%|█████████▎| 24075/25880 [4:54:36<21:52,  1.37it/s] 
1|24076|Loss: 0.697858452796936:  93%|█████████▎| 24076/25880 [4:54:37<21:56,  1.37it/s]
1|24077|Loss: 0.901501476764679:  93%|█████████▎| 24076/25880 [4:54:37<21:56,  1.37it/s]
1|24077|Loss: 0.901501476764679:  93%|█████████▎| 24077/25880 [4:54:37<21:47,  1.38it/s]
1|24078|Loss: 0.9390192031860352:  93%|█████████▎| 24077/25880 [4:54:38<21:47,  1.38it/s]
1|24078|Loss: 0.9390192031860352:  93%|█████████▎| 24078/25880 [4:54:38<21:46,  1.38it/s]
1|24079|Loss: 0.8414120078086853:  93%|█████████▎| 24078/25880 [4:54:38<21:46,  1.38it/s]
1|24079|Loss: 0.8414120078086853:  93%|█████████▎| 24079/25880 [4:54:39<20:43,  1.45it/s]
1|24080|Loss: 0.9486081004142761:  93%|█████████▎| 24079/25880 [4:54:39<20:43,  1.45it/s]
1|24080|Loss: 0.9486081004142761:  93%|█████████▎| 24080/25880 [4:54:39<20:07,  1.49it/s]
1|24081|Loss: 0.7730203866958618:  93%|█████████▎| 24080/25880 [4:54:40<20:07,  1.49it/s]
1|24081|Loss: 0.7730203866958618:  93%|█████████▎| 24081/25880 [4:54:40<19:54,  1.51it/s]
1|24082|Loss: 0.821670413017273:  93%|█████████▎| 24081/25880 [4:54:40<19:54,  1.51it/s] 
1|24082|Loss: 0.821670413017273:  93%|█████████▎| 24082/25880 [4:54:41<19:32,  1.53it/s]
1|24083|Loss: 0.6932548880577087:  93%|█████████▎| 24082/25880 [4:54:41<19:32,  1.53it/s]
1|24083|Loss: 0.6932548880577087:  93%|█████████▎| 24083/25880 [4:54:41<20:06,  1.49it/s]
1|24084|Loss: 0.9255861639976501:  93%|█████████▎| 24083/25880 [4:54:42<20:06,  1.49it/s]
1|24084|Loss: 0.9255861639976501:  93%|█████████▎| 24084/25880 [4:54:42<20:40,  1.45it/s]
1|24085|Loss: 0.8150642514228821:  93%|█████████▎| 24084/25880 [4:54:42<20:40,  1.45it/s]
1|24085|Loss: 0.8150642514228821:  93%|█████████▎| 24085/25880 [4:54:43<21:02,  1.42it/s]
1|24086|Loss: 0.7365387082099915:  93%|█████████▎| 24085/25880 [4:54:43<21:02,  1.42it/s]
1|24086|Loss: 0.7365387082099915:  93%|█████████▎| 24086/25880 [4:54:44<21:18,  1.40it/s]
1|24087|Loss: 0.8808605670928955:  93%|█████████▎| 24086/25880 [4:54:44<21:18,  1.40it/s]
1|24087|Loss: 0.8808605670928955:  93%|█████████▎| 24087/25880 [4:54:44<21:56,  1.36it/s]
1|24088|Loss: 0.731028139591217:  93%|█████████▎| 24087/25880 [4:54:45<21:56,  1.36it/s] 
1|24088|Loss: 0.731028139591217:  93%|█████████▎| 24088/25880 [4:54:45<22:52,  1.31it/s]
1|24089|Loss: 0.9834191799163818:  93%|█████████▎| 24088/25880 [4:54:46<22:52,  1.31it/s]
1|24089|Loss: 0.9834191799163818:  93%|█████████▎| 24089/25880 [4:54:46<23:21,  1.28it/s]
1|24090|Loss: 0.9432150721549988:  93%|█████████▎| 24089/25880 [4:54:46<23:21,  1.28it/s]
1|24090|Loss: 0.9432150721549988:  93%|█████████▎| 24090/25880 [4:54:47<21:55,  1.36it/s]
1|24091|Loss: 0.6950182914733887:  93%|█████████▎| 24090/25880 [4:54:47<21:55,  1.36it/s]
1|24091|Loss: 0.6950182914733887:  93%|█████████▎| 24091/25880 [4:54:47<20:00,  1.49it/s]
1|24092|Loss: 0.7401595711708069:  93%|█████████▎| 24091/25880 [4:54:47<20:00,  1.49it/s]
1|24092|Loss: 0.7401595711708069:  93%|█████████▎| 24092/25880 [4:54:48<20:52,  1.43it/s]
1|24093|Loss: 0.8265303373336792:  93%|█████████▎| 24092/25880 [4:54:48<20:52,  1.43it/s]
1|24093|Loss: 0.8265303373336792:  93%|█████████▎| 24093/25880 [4:54:49<22:06,  1.35it/s]
1|24094|Loss: 0.980841338634491:  93%|█████████▎| 24093/25880 [4:54:49<22:06,  1.35it/s] 
1|24094|Loss: 0.980841338634491:  93%|█████████▎| 24094/25880 [4:54:50<23:20,  1.28it/s]
1|24095|Loss: 0.9858579039573669:  93%|█████████▎| 24094/25880 [4:54:50<23:20,  1.28it/s]
1|24095|Loss: 0.9858579039573669:  93%|█████████▎| 24095/25880 [4:54:50<23:43,  1.25it/s]
1|24096|Loss: 0.7618554830551147:  93%|█████████▎| 24095/25880 [4:54:51<23:43,  1.25it/s]
1|24096|Loss: 0.7618554830551147:  93%|█████████▎| 24096/25880 [4:54:51<23:18,  1.28it/s]
1|24097|Loss: 0.8829010128974915:  93%|█████████▎| 24096/25880 [4:54:52<23:18,  1.28it/s]
1|24097|Loss: 0.8829010128974915:  93%|█████████▎| 24097/25880 [4:54:52<22:10,  1.34it/s]
1|24098|Loss: 0.8205596208572388:  93%|█████████▎| 24097/25880 [4:54:52<22:10,  1.34it/s]
1|24098|Loss: 0.8205596208572388:  93%|█████████▎| 24098/25880 [4:54:53<21:51,  1.36it/s]
1|24099|Loss: 0.9282944202423096:  93%|█████████▎| 24098/25880 [4:54:53<21:51,  1.36it/s]
1|24099|Loss: 0.9282944202423096:  93%|█████████▎| 24099/25880 [4:54:53<21:49,  1.36it/s]
1|24100|Loss: 0.7646356821060181:  93%|█████████▎| 24099/25880 [4:54:54<21:49,  1.36it/s]
1|24100|Loss: 0.7646356821060181:  93%|█████████▎| 24100/25880 [4:54:54<23:24,  1.27it/s]
1|24101|Loss: 0.7906968593597412:  93%|█████████▎| 24100/25880 [4:54:55<23:24,  1.27it/s]
1|24101|Loss: 0.7906968593597412:  93%|█████████▎| 24101/25880 [4:54:55<23:41,  1.25it/s]
1|24102|Loss: 0.8328335285186768:  93%|█████████▎| 24101/25880 [4:54:55<23:41,  1.25it/s]
1|24102|Loss: 0.8328335285186768:  93%|█████████▎| 24102/25880 [4:54:56<24:10,  1.23it/s]
1|24103|Loss: 0.7072603106498718:  93%|█████████▎| 24102/25880 [4:54:56<24:10,  1.23it/s]
1|24103|Loss: 0.7072603106498718:  93%|█████████▎| 24103/25880 [4:54:57<23:38,  1.25it/s]
1|24104|Loss: 0.8934153318405151:  93%|█████████▎| 24103/25880 [4:54:57<23:38,  1.25it/s]
1|24104|Loss: 0.8934153318405151:  93%|█████████▎| 24104/25880 [4:54:57<22:21,  1.32it/s]
1|24105|Loss: 0.8114048838615417:  93%|█████████▎| 24104/25880 [4:54:58<22:21,  1.32it/s]
1|24105|Loss: 0.8114048838615417:  93%|█████████▎| 24105/25880 [4:54:58<21:11,  1.40it/s]
1|24106|Loss: 0.7287794351577759:  93%|█████████▎| 24105/25880 [4:54:58<21:11,  1.40it/s]
1|24106|Loss: 0.7287794351577759:  93%|█████████▎| 24106/25880 [4:54:59<20:19,  1.46it/s]
1|24107|Loss: 0.8630771040916443:  93%|█████████▎| 24106/25880 [4:54:59<20:19,  1.46it/s]
1|24107|Loss: 0.8630771040916443:  93%|█████████▎| 24107/25880 [4:54:59<20:32,  1.44it/s]
1|24108|Loss: 0.7261189818382263:  93%|█████████▎| 24107/25880 [4:55:00<20:32,  1.44it/s]
1|24108|Loss: 0.7261189818382263:  93%|█████████▎| 24108/25880 [4:55:00<20:36,  1.43it/s]
1|24109|Loss: 0.6504474878311157:  93%|█████████▎| 24108/25880 [4:55:00<20:36,  1.43it/s]
1|24109|Loss: 0.6504474878311157:  93%|█████████▎| 24109/25880 [4:55:01<20:36,  1.43it/s]
1|24110|Loss: 0.8125442266464233:  93%|█████████▎| 24109/25880 [4:55:01<20:36,  1.43it/s]
1|24110|Loss: 0.8125442266464233:  93%|█████████▎| 24110/25880 [4:55:01<21:52,  1.35it/s]
1|24111|Loss: 0.8727635145187378:  93%|█████████▎| 24110/25880 [4:55:02<21:52,  1.35it/s]
1|24111|Loss: 0.8727635145187378:  93%|█████████▎| 24111/25880 [4:55:02<21:18,  1.38it/s]
1|24112|Loss: 0.7660797834396362:  93%|█████████▎| 24111/25880 [4:55:03<21:18,  1.38it/s]
1|24112|Loss: 0.7660797834396362:  93%|█████████▎| 24112/25880 [4:55:03<20:56,  1.41it/s]
1|24113|Loss: 0.8423629999160767:  93%|█████████▎| 24112/25880 [4:55:03<20:56,  1.41it/s]
1|24113|Loss: 0.8423629999160767:  93%|█████████▎| 24113/25880 [4:55:03<20:12,  1.46it/s]
1|24114|Loss: 0.8720527291297913:  93%|█████████▎| 24113/25880 [4:55:04<20:12,  1.46it/s]
1|24114|Loss: 0.8720527291297913:  93%|█████████▎| 24114/25880 [4:55:04<19:44,  1.49it/s]
1|24115|Loss: 0.9981714487075806:  93%|█████████▎| 24114/25880 [4:55:04<19:44,  1.49it/s]
1|24115|Loss: 0.9981714487075806:  93%|█████████▎| 24115/25880 [4:55:05<19:26,  1.51it/s]
1|24116|Loss: 0.7891662120819092:  93%|█████████▎| 24115/25880 [4:55:05<19:26,  1.51it/s]
1|24116|Loss: 0.7891662120819092:  93%|█████████▎| 24116/25880 [4:55:05<19:08,  1.54it/s]
1|24117|Loss: 0.8989439606666565:  93%|█████████▎| 24116/25880 [4:55:06<19:08,  1.54it/s]
1|24117|Loss: 0.8989439606666565:  93%|█████████▎| 24117/25880 [4:55:06<19:28,  1.51it/s]
1|24118|Loss: 0.7993026971817017:  93%|█████████▎| 24117/25880 [4:55:06<19:28,  1.51it/s]
1|24118|Loss: 0.7993026971817017:  93%|█████████▎| 24118/25880 [4:55:07<18:55,  1.55it/s]
1|24119|Loss: 0.724808931350708:  93%|█████████▎| 24118/25880 [4:55:07<18:55,  1.55it/s] 
1|24119|Loss: 0.724808931350708:  93%|█████████▎| 24119/25880 [4:55:07<19:31,  1.50it/s]
1|24120|Loss: 0.9957765340805054:  93%|█████████▎| 24119/25880 [4:55:08<19:31,  1.50it/s]
1|24120|Loss: 0.9957765340805054:  93%|█████████▎| 24120/25880 [4:55:08<19:32,  1.50it/s]
1|24121|Loss: 0.9329696297645569:  93%|█████████▎| 24120/25880 [4:55:08<19:32,  1.50it/s]
1|24121|Loss: 0.9329696297645569:  93%|█████████▎| 24121/25880 [4:55:09<18:43,  1.57it/s]
1|24122|Loss: 0.8161733746528625:  93%|█████████▎| 24121/25880 [4:55:09<18:43,  1.57it/s]
1|24122|Loss: 0.8161733746528625:  93%|█████████▎| 24122/25880 [4:55:09<19:00,  1.54it/s]
1|24123|Loss: 0.7975432872772217:  93%|█████████▎| 24122/25880 [4:55:10<19:00,  1.54it/s]
1|24123|Loss: 0.7975432872772217:  93%|█████████▎| 24123/25880 [4:55:10<18:59,  1.54it/s]
1|24124|Loss: 0.7005531191825867:  93%|█████████▎| 24123/25880 [4:55:10<18:59,  1.54it/s]
1|24124|Loss: 0.7005531191825867:  93%|█████████▎| 24124/25880 [4:55:11<20:30,  1.43it/s]
1|24125|Loss: 0.7801080942153931:  93%|█████████▎| 24124/25880 [4:55:11<20:30,  1.43it/s]
1|24125|Loss: 0.7801080942153931:  93%|█████████▎| 24125/25880 [4:55:12<21:09,  1.38it/s]
1|24126|Loss: 0.8125641942024231:  93%|█████████▎| 24125/25880 [4:55:12<21:09,  1.38it/s]
1|24126|Loss: 0.8125641942024231:  93%|█████████▎| 24126/25880 [4:55:12<20:16,  1.44it/s]
1|24127|Loss: 0.8130015730857849:  93%|█████████▎| 24126/25880 [4:55:13<20:16,  1.44it/s]
1|24127|Loss: 0.8130015730857849:  93%|█████████▎| 24127/25880 [4:55:13<20:07,  1.45it/s]
1|24128|Loss: 0.8245306015014648:  93%|█████████▎| 24127/25880 [4:55:13<20:07,  1.45it/s]
1|24128|Loss: 0.8245306015014648:  93%|█████████▎| 24128/25880 [4:55:13<19:37,  1.49it/s]
1|24129|Loss: 0.8286799192428589:  93%|█████████▎| 24128/25880 [4:55:14<19:37,  1.49it/s]
1|24129|Loss: 0.8286799192428589:  93%|█████████▎| 24129/25880 [4:55:14<19:15,  1.52it/s]
1|24130|Loss: 0.9067346453666687:  93%|█████████▎| 24129/25880 [4:55:14<19:15,  1.52it/s]
1|24130|Loss: 0.9067346453666687:  93%|█████████▎| 24130/25880 [4:55:15<19:29,  1.50it/s]
1|24131|Loss: 0.8679344058036804:  93%|█████████▎| 24130/25880 [4:55:15<19:29,  1.50it/s]
1|24131|Loss: 0.8679344058036804:  93%|█████████▎| 24131/25880 [4:55:16<20:27,  1.42it/s]
1|24132|Loss: 0.7352690100669861:  93%|█████████▎| 24131/25880 [4:55:16<20:27,  1.42it/s]
1|24132|Loss: 0.7352690100669861:  93%|█████████▎| 24132/25880 [4:55:16<21:20,  1.36it/s]
1|24133|Loss: 0.9598612189292908:  93%|█████████▎| 24132/25880 [4:55:17<21:20,  1.36it/s]
1|24133|Loss: 0.9598612189292908:  93%|█████████▎| 24133/25880 [4:55:17<22:06,  1.32it/s]
1|24134|Loss: 0.8890867233276367:  93%|█████████▎| 24133/25880 [4:55:18<22:06,  1.32it/s]
1|24134|Loss: 0.8890867233276367:  93%|█████████▎| 24134/25880 [4:55:18<21:15,  1.37it/s]
1|24135|Loss: 0.7205712199211121:  93%|█████████▎| 24134/25880 [4:55:18<21:15,  1.37it/s]
1|24135|Loss: 0.7205712199211121:  93%|█████████▎| 24135/25880 [4:55:19<22:11,  1.31it/s]
1|24136|Loss: 0.8007935881614685:  93%|█████████▎| 24135/25880 [4:55:19<22:11,  1.31it/s]
1|24136|Loss: 0.8007935881614685:  93%|█████████▎| 24136/25880 [4:55:20<22:54,  1.27it/s]
1|24137|Loss: 0.7630813121795654:  93%|█████████▎| 24136/25880 [4:55:20<22:54,  1.27it/s]
1|24137|Loss: 0.7630813121795654:  93%|█████████▎| 24137/25880 [4:55:20<22:32,  1.29it/s]
1|24138|Loss: 0.9342586994171143:  93%|█████████▎| 24137/25880 [4:55:21<22:32,  1.29it/s]
1|24138|Loss: 0.9342586994171143:  93%|█████████▎| 24138/25880 [4:55:21<22:06,  1.31it/s]
1|24139|Loss: 0.8258081078529358:  93%|█████████▎| 24138/25880 [4:55:21<22:06,  1.31it/s]
1|24139|Loss: 0.8258081078529358:  93%|█████████▎| 24139/25880 [4:55:22<21:46,  1.33it/s]
1|24140|Loss: 0.7127653956413269:  93%|█████████▎| 24139/25880 [4:55:22<21:46,  1.33it/s]
1|24140|Loss: 0.7127653956413269:  93%|█████████▎| 24140/25880 [4:55:22<21:00,  1.38it/s]
1|24141|Loss: 0.7846544981002808:  93%|█████████▎| 24140/25880 [4:55:23<21:00,  1.38it/s]
1|24141|Loss: 0.7846544981002808:  93%|█████████▎| 24141/25880 [4:55:23<20:42,  1.40it/s]
1|24142|Loss: 0.8667429685592651:  93%|█████████▎| 24141/25880 [4:55:23<20:42,  1.40it/s]
1|24142|Loss: 0.8667429685592651:  93%|█████████▎| 24142/25880 [4:55:24<20:10,  1.44it/s]
1|24143|Loss: 0.8524001240730286:  93%|█████████▎| 24142/25880 [4:55:24<20:10,  1.44it/s]
1|24143|Loss: 0.8524001240730286:  93%|█████████▎| 24143/25880 [4:55:24<19:41,  1.47it/s]
1|24144|Loss: 0.9311345815658569:  93%|█████████▎| 24143/25880 [4:55:25<19:41,  1.47it/s]
1|24144|Loss: 0.9311345815658569:  93%|█████████▎| 24144/25880 [4:55:25<19:20,  1.50it/s]
1|24145|Loss: 0.8207796812057495:  93%|█████████▎| 24144/25880 [4:55:25<19:20,  1.50it/s]
1|24145|Loss: 0.8207796812057495:  93%|█████████▎| 24145/25880 [4:55:26<19:42,  1.47it/s]
1|24146|Loss: 0.8625704646110535:  93%|█████████▎| 24145/25880 [4:55:26<19:42,  1.47it/s]
1|24146|Loss: 0.8625704646110535:  93%|█████████▎| 24146/25880 [4:55:27<21:23,  1.35it/s]
1|24147|Loss: 0.8477790951728821:  93%|█████████▎| 24146/25880 [4:55:27<21:23,  1.35it/s]
1|24147|Loss: 0.8477790951728821:  93%|█████████▎| 24147/25880 [4:55:27<20:58,  1.38it/s]
1|24148|Loss: 0.8342990279197693:  93%|█████████▎| 24147/25880 [4:55:28<20:58,  1.38it/s]
1|24148|Loss: 0.8342990279197693:  93%|█████████▎| 24148/25880 [4:55:28<22:10,  1.30it/s]
1|24149|Loss: 0.8444327116012573:  93%|█████████▎| 24148/25880 [4:55:29<22:10,  1.30it/s]
1|24149|Loss: 0.8444327116012573:  93%|█████████▎| 24149/25880 [4:55:29<21:31,  1.34it/s]
1|24150|Loss: 0.922353208065033:  93%|█████████▎| 24149/25880 [4:55:29<21:31,  1.34it/s] 
1|24150|Loss: 0.922353208065033:  93%|█████████▎| 24150/25880 [4:55:30<21:14,  1.36it/s]
1|24151|Loss: 0.8410466313362122:  93%|█████████▎| 24150/25880 [4:55:30<21:14,  1.36it/s]
1|24151|Loss: 0.8410466313362122:  93%|█████████▎| 24151/25880 [4:55:30<21:06,  1.37it/s]
1|24152|Loss: 0.9141884446144104:  93%|█████████▎| 24151/25880 [4:55:31<21:06,  1.37it/s]
1|24152|Loss: 0.9141884446144104:  93%|█████████▎| 24152/25880 [4:55:31<19:39,  1.46it/s]
1|24153|Loss: 0.8314178586006165:  93%|█████████▎| 24152/25880 [4:55:31<19:39,  1.46it/s]
1|24153|Loss: 0.8314178586006165:  93%|█████████▎| 24153/25880 [4:55:31<18:30,  1.56it/s]
1|24154|Loss: 0.7663528919219971:  93%|█████████▎| 24153/25880 [4:55:32<18:30,  1.56it/s]
1|24154|Loss: 0.7663528919219971:  93%|█████████▎| 24154/25880 [4:55:32<18:46,  1.53it/s]
1|24155|Loss: 0.9357107877731323:  93%|█████████▎| 24154/25880 [4:55:32<18:46,  1.53it/s]
1|24155|Loss: 0.9357107877731323:  93%|█████████▎| 24155/25880 [4:55:33<18:36,  1.54it/s]
1|24156|Loss: 0.7203026413917542:  93%|█████████▎| 24155/25880 [4:55:33<18:36,  1.54it/s]
1|24156|Loss: 0.7203026413917542:  93%|█████████▎| 24156/25880 [4:55:33<18:52,  1.52it/s]
1|24157|Loss: 0.8994747996330261:  93%|█████████▎| 24156/25880 [4:55:34<18:52,  1.52it/s]
1|24157|Loss: 0.8994747996330261:  93%|█████████▎| 24157/25880 [4:55:34<18:47,  1.53it/s]
1|24158|Loss: 0.6493627429008484:  93%|█████████▎| 24157/25880 [4:55:35<18:47,  1.53it/s]
1|24158|Loss: 0.6493627429008484:  93%|█████████▎| 24158/25880 [4:55:35<20:35,  1.39it/s]
1|24159|Loss: 0.954918384552002:  93%|█████████▎| 24158/25880 [4:55:35<20:35,  1.39it/s] 
1|24159|Loss: 0.954918384552002:  93%|█████████▎| 24159/25880 [4:55:36<21:02,  1.36it/s]
1|24160|Loss: 0.7722192406654358:  93%|█████████▎| 24159/25880 [4:55:36<21:02,  1.36it/s]
1|24160|Loss: 0.7722192406654358:  93%|█████████▎| 24160/25880 [4:55:36<20:17,  1.41it/s]
1|24161|Loss: 0.9353111982345581:  93%|█████████▎| 24160/25880 [4:55:37<20:17,  1.41it/s]
1|24161|Loss: 0.9353111982345581:  93%|█████████▎| 24161/25880 [4:55:37<21:09,  1.35it/s]
1|24162|Loss: 0.9042201042175293:  93%|█████████▎| 24161/25880 [4:55:38<21:09,  1.35it/s]
1|24162|Loss: 0.9042201042175293:  93%|█████████▎| 24162/25880 [4:55:38<22:05,  1.30it/s]
1|24163|Loss: 0.8929743766784668:  93%|█████████▎| 24162/25880 [4:55:38<22:05,  1.30it/s]
1|24163|Loss: 0.8929743766784668:  93%|█████████▎| 24163/25880 [4:55:39<21:43,  1.32it/s]
1|24164|Loss: 0.7568134069442749:  93%|█████████▎| 24163/25880 [4:55:39<21:43,  1.32it/s]
1|24164|Loss: 0.7568134069442749:  93%|█████████▎| 24164/25880 [4:55:39<21:23,  1.34it/s]
1|24165|Loss: 0.8348236083984375:  93%|█████████▎| 24164/25880 [4:55:40<21:23,  1.34it/s]
1|24165|Loss: 0.8348236083984375:  93%|█████████▎| 24165/25880 [4:55:40<20:59,  1.36it/s]
1|24166|Loss: 0.9911078214645386:  93%|█████████▎| 24165/25880 [4:55:41<20:59,  1.36it/s]
1|24166|Loss: 0.9911078214645386:  93%|█████████▎| 24166/25880 [4:55:41<20:55,  1.36it/s]
1|24167|Loss: 0.7254108190536499:  93%|█████████▎| 24166/25880 [4:55:41<20:55,  1.36it/s]
1|24167|Loss: 0.7254108190536499:  93%|█████████▎| 24167/25880 [4:55:42<19:54,  1.43it/s]
1|24168|Loss: 0.8712710738182068:  93%|█████████▎| 24167/25880 [4:55:42<19:54,  1.43it/s]
1|24168|Loss: 0.8712710738182068:  93%|█████████▎| 24168/25880 [4:55:42<20:33,  1.39it/s]
1|24169|Loss: 0.9534181356430054:  93%|█████████▎| 24168/25880 [4:55:43<20:33,  1.39it/s]
1|24169|Loss: 0.9534181356430054:  93%|█████████▎| 24169/25880 [4:55:43<21:15,  1.34it/s]
1|24170|Loss: 0.7861016392707825:  93%|█████████▎| 24169/25880 [4:55:44<21:15,  1.34it/s]
1|24170|Loss: 0.7861016392707825:  93%|█████████▎| 24170/25880 [4:55:44<22:15,  1.28it/s]
1|24171|Loss: 0.8542245626449585:  93%|█████████▎| 24170/25880 [4:55:44<22:15,  1.28it/s]
1|24171|Loss: 0.8542245626449585:  93%|█████████▎| 24171/25880 [4:55:45<22:11,  1.28it/s]
1|24172|Loss: 0.8303579688072205:  93%|█████████▎| 24171/25880 [4:55:45<22:11,  1.28it/s]
1|24172|Loss: 0.8303579688072205:  93%|█████████▎| 24172/25880 [4:55:45<21:36,  1.32it/s]
1|24173|Loss: 0.7886272668838501:  93%|█████████▎| 24172/25880 [4:55:46<21:36,  1.32it/s]
1|24173|Loss: 0.7886272668838501:  93%|█████████▎| 24173/25880 [4:55:46<22:06,  1.29it/s]
1|24174|Loss: 0.8030564785003662:  93%|█████████▎| 24173/25880 [4:55:47<22:06,  1.29it/s]
1|24174|Loss: 0.8030564785003662:  93%|█████████▎| 24174/25880 [4:55:47<20:44,  1.37it/s]
1|24175|Loss: 0.8046502470970154:  93%|█████████▎| 24174/25880 [4:55:47<20:44,  1.37it/s]
1|24175|Loss: 0.8046502470970154:  93%|█████████▎| 24175/25880 [4:55:47<17:59,  1.58it/s]
1|24176|Loss: 0.8639947175979614:  93%|█████████▎| 24175/25880 [4:55:48<17:59,  1.58it/s]
1|24176|Loss: 0.8639947175979614:  93%|█████████▎| 24176/25880 [4:55:48<19:09,  1.48it/s]
1|24177|Loss: 0.8636722564697266:  93%|█████████▎| 24176/25880 [4:55:49<19:09,  1.48it/s]
1|24177|Loss: 0.8636722564697266:  93%|█████████▎| 24177/25880 [4:55:49<20:34,  1.38it/s]
1|24178|Loss: 0.9041893482208252:  93%|█████████▎| 24177/25880 [4:55:49<20:34,  1.38it/s]
1|24178|Loss: 0.9041893482208252:  93%|█████████▎| 24178/25880 [4:55:50<21:16,  1.33it/s]
1|24179|Loss: 0.7602242231369019:  93%|█████████▎| 24178/25880 [4:55:50<21:16,  1.33it/s]
1|24179|Loss: 0.7602242231369019:  93%|█████████▎| 24179/25880 [4:55:50<21:12,  1.34it/s]
1|24180|Loss: 0.8320585489273071:  93%|█████████▎| 24179/25880 [4:55:51<21:12,  1.34it/s]
1|24180|Loss: 0.8320585489273071:  93%|█████████▎| 24180/25880 [4:55:51<20:49,  1.36it/s]
1|24181|Loss: 0.8697656989097595:  93%|█████████▎| 24180/25880 [4:55:52<20:49,  1.36it/s]
1|24181|Loss: 0.8697656989097595:  93%|█████████▎| 24181/25880 [4:55:52<20:50,  1.36it/s]
1|24182|Loss: 0.8812984228134155:  93%|█████████▎| 24181/25880 [4:55:52<20:50,  1.36it/s]
1|24182|Loss: 0.8812984228134155:  93%|█████████▎| 24182/25880 [4:55:53<20:06,  1.41it/s]
1|24183|Loss: 0.9232894778251648:  93%|█████████▎| 24182/25880 [4:55:53<20:06,  1.41it/s]
1|24183|Loss: 0.9232894778251648:  93%|█████████▎| 24183/25880 [4:55:53<19:29,  1.45it/s]
1|24184|Loss: 0.7568182945251465:  93%|█████████▎| 24183/25880 [4:55:54<19:29,  1.45it/s]
1|24184|Loss: 0.7568182945251465:  93%|█████████▎| 24184/25880 [4:55:54<18:58,  1.49it/s]
1|24185|Loss: 0.9079546332359314:  93%|█████████▎| 24184/25880 [4:55:54<18:58,  1.49it/s]
1|24185|Loss: 0.9079546332359314:  93%|█████████▎| 24185/25880 [4:55:55<19:16,  1.47it/s]
1|24186|Loss: 0.8812888860702515:  93%|█████████▎| 24185/25880 [4:55:55<19:16,  1.47it/s]
1|24186|Loss: 0.8812888860702515:  93%|█████████▎| 24186/25880 [4:55:55<20:24,  1.38it/s]
1|24187|Loss: 0.9071193933486938:  93%|█████████▎| 24186/25880 [4:55:56<20:24,  1.38it/s]
1|24187|Loss: 0.9071193933486938:  93%|█████████▎| 24187/25880 [4:55:56<20:39,  1.37it/s]
1|24188|Loss: 0.8089298605918884:  93%|█████████▎| 24187/25880 [4:55:57<20:39,  1.37it/s]
1|24188|Loss: 0.8089298605918884:  93%|█████████▎| 24188/25880 [4:55:57<20:43,  1.36it/s]
1|24189|Loss: 0.8488932847976685:  93%|█████████▎| 24188/25880 [4:55:57<20:43,  1.36it/s]
1|24189|Loss: 0.8488932847976685:  93%|█████████▎| 24189/25880 [4:55:57<19:05,  1.48it/s]
1|24190|Loss: 0.847649097442627:  93%|█████████▎| 24189/25880 [4:55:58<19:05,  1.48it/s] 
1|24190|Loss: 0.847649097442627:  93%|█████████▎| 24190/25880 [4:55:58<20:04,  1.40it/s]
1|24191|Loss: 0.7792526483535767:  93%|█████████▎| 24190/25880 [4:55:59<20:04,  1.40it/s]
1|24191|Loss: 0.7792526483535767:  93%|█████████▎| 24191/25880 [4:55:59<19:00,  1.48it/s]
1|24192|Loss: 0.8901035785675049:  93%|█████████▎| 24191/25880 [4:55:59<19:00,  1.48it/s]
1|24192|Loss: 0.8901035785675049:  93%|█████████▎| 24192/25880 [4:56:00<19:44,  1.43it/s]
1|24193|Loss: 0.9144688248634338:  93%|█████████▎| 24192/25880 [4:56:00<19:44,  1.43it/s]
1|24193|Loss: 0.9144688248634338:  93%|█████████▎| 24193/25880 [4:56:00<20:30,  1.37it/s]
1|24194|Loss: 0.8071312308311462:  93%|█████████▎| 24193/25880 [4:56:01<20:30,  1.37it/s]
1|24194|Loss: 0.8071312308311462:  93%|█████████▎| 24194/25880 [4:56:01<20:28,  1.37it/s]
1|24195|Loss: 0.7761815786361694:  93%|█████████▎| 24194/25880 [4:56:01<20:28,  1.37it/s]
1|24195|Loss: 0.7761815786361694:  93%|█████████▎| 24195/25880 [4:56:02<19:52,  1.41it/s]
1|24196|Loss: 0.8011175394058228:  93%|█████████▎| 24195/25880 [4:56:02<19:52,  1.41it/s]
1|24196|Loss: 0.8011175394058228:  93%|█████████▎| 24196/25880 [4:56:03<20:55,  1.34it/s]
1|24197|Loss: 0.8536016941070557:  93%|█████████▎| 24196/25880 [4:56:03<20:55,  1.34it/s]
1|24197|Loss: 0.8536016941070557:  93%|█████████▎| 24197/25880 [4:56:03<21:06,  1.33it/s]
1|24198|Loss: 0.7503294348716736:  93%|█████████▎| 24197/25880 [4:56:04<21:06,  1.33it/s]
1|24198|Loss: 0.7503294348716736:  94%|█████████▎| 24198/25880 [4:56:04<21:22,  1.31it/s]
1|24199|Loss: 0.8537553548812866:  94%|█████████▎| 24198/25880 [4:56:05<21:22,  1.31it/s]
1|24199|Loss: 0.8537553548812866:  94%|█████████▎| 24199/25880 [4:56:05<21:53,  1.28it/s]
1|24200|Loss: 0.8523228764533997:  94%|█████████▎| 24199/25880 [4:56:05<21:53,  1.28it/s]
1|24200|Loss: 0.8523228764533997:  94%|█████████▎| 24200/25880 [4:56:06<20:38,  1.36it/s]
1|24201|Loss: 0.6193918585777283:  94%|█████████▎| 24200/25880 [4:56:06<20:38,  1.36it/s]
1|24201|Loss: 0.6193918585777283:  94%|█████████▎| 24201/25880 [4:56:06<21:49,  1.28it/s]
1|24202|Loss: 0.7920894026756287:  94%|█████████▎| 24201/25880 [4:56:07<21:49,  1.28it/s]
1|24202|Loss: 0.7920894026756287:  94%|█████████▎| 24202/25880 [4:56:07<20:27,  1.37it/s]
1|24203|Loss: 0.7703251838684082:  94%|█████████▎| 24202/25880 [4:56:07<20:27,  1.37it/s]
1|24203|Loss: 0.7703251838684082:  94%|█████████▎| 24203/25880 [4:56:08<19:07,  1.46it/s]
1|24204|Loss: 0.8019940257072449:  94%|█████████▎| 24203/25880 [4:56:08<19:07,  1.46it/s]
1|24204|Loss: 0.8019940257072449:  94%|█████████▎| 24204/25880 [4:56:08<20:17,  1.38it/s]
1|24205|Loss: 0.8437340259552002:  94%|█████████▎| 24204/25880 [4:56:09<20:17,  1.38it/s]
1|24205|Loss: 0.8437340259552002:  94%|█████████▎| 24205/25880 [4:56:09<19:50,  1.41it/s]
1|24206|Loss: 0.764373242855072:  94%|█████████▎| 24205/25880 [4:56:09<19:50,  1.41it/s] 
1|24206|Loss: 0.764373242855072:  94%|█████████▎| 24206/25880 [4:56:10<19:03,  1.46it/s]
1|24207|Loss: 0.8638730645179749:  94%|█████████▎| 24206/25880 [4:56:10<19:03,  1.46it/s]
1|24207|Loss: 0.8638730645179749:  94%|█████████▎| 24207/25880 [4:56:10<19:16,  1.45it/s]
1|24208|Loss: 0.9167364239692688:  94%|█████████▎| 24207/25880 [4:56:11<19:16,  1.45it/s]
1|24208|Loss: 0.9167364239692688:  94%|█████████▎| 24208/25880 [4:56:11<20:13,  1.38it/s]
1|24209|Loss: 0.8994935154914856:  94%|█████████▎| 24208/25880 [4:56:12<20:13,  1.38it/s]
1|24209|Loss: 0.8994935154914856:  94%|█████████▎| 24209/25880 [4:56:12<19:12,  1.45it/s]
1|24210|Loss: 0.8554214835166931:  94%|█████████▎| 24209/25880 [4:56:12<19:12,  1.45it/s]
1|24210|Loss: 0.8554214835166931:  94%|█████████▎| 24210/25880 [4:56:13<20:26,  1.36it/s]
1|24211|Loss: 0.7681633234024048:  94%|█████████▎| 24210/25880 [4:56:13<20:26,  1.36it/s]
1|24211|Loss: 0.7681633234024048:  94%|█████████▎| 24211/25880 [4:56:13<20:31,  1.36it/s]
1|24212|Loss: 0.8403799533843994:  94%|█████████▎| 24211/25880 [4:56:14<20:31,  1.36it/s]
1|24212|Loss: 0.8403799533843994:  94%|█████████▎| 24212/25880 [4:56:14<19:24,  1.43it/s]
1|24213|Loss: 0.7715214490890503:  94%|█████████▎| 24212/25880 [4:56:14<19:24,  1.43it/s]
1|24213|Loss: 0.7715214490890503:  94%|█████████▎| 24213/25880 [4:56:15<19:32,  1.42it/s]
1|24214|Loss: 0.8921862840652466:  94%|█████████▎| 24213/25880 [4:56:15<19:32,  1.42it/s]
1|24214|Loss: 0.8921862840652466:  94%|█████████▎| 24214/25880 [4:56:15<19:14,  1.44it/s]
1|24215|Loss: 0.7877267003059387:  94%|█████████▎| 24214/25880 [4:56:16<19:14,  1.44it/s]
1|24215|Loss: 0.7877267003059387:  94%|█████████▎| 24215/25880 [4:56:16<18:48,  1.48it/s]
1|24216|Loss: 0.8213427066802979:  94%|█████████▎| 24215/25880 [4:56:16<18:48,  1.48it/s]
1|24216|Loss: 0.8213427066802979:  94%|█████████▎| 24216/25880 [4:56:17<19:08,  1.45it/s]
1|24217|Loss: 0.83116614818573:  94%|█████████▎| 24216/25880 [4:56:17<19:08,  1.45it/s]  
1|24217|Loss: 0.83116614818573:  94%|█████████▎| 24217/25880 [4:56:18<20:00,  1.38it/s]
1|24218|Loss: 0.8773210644721985:  94%|█████████▎| 24217/25880 [4:56:18<20:00,  1.38it/s]
1|24218|Loss: 0.8773210644721985:  94%|█████████▎| 24218/25880 [4:56:18<19:37,  1.41it/s]
1|24219|Loss: 0.7559844851493835:  94%|█████████▎| 24218/25880 [4:56:19<19:37,  1.41it/s]
1|24219|Loss: 0.7559844851493835:  94%|█████████▎| 24219/25880 [4:56:19<21:13,  1.30it/s]
1|24220|Loss: 0.8729640245437622:  94%|█████████▎| 24219/25880 [4:56:20<21:13,  1.30it/s]
1|24220|Loss: 0.8729640245437622:  94%|█████████▎| 24220/25880 [4:56:20<20:32,  1.35it/s]
1|24221|Loss: 0.8549458980560303:  94%|█████████▎| 24220/25880 [4:56:20<20:32,  1.35it/s]
1|24221|Loss: 0.8549458980560303:  94%|█████████▎| 24221/25880 [4:56:21<20:40,  1.34it/s]
1|24222|Loss: 0.8022617697715759:  94%|█████████▎| 24221/25880 [4:56:21<20:40,  1.34it/s]
1|24222|Loss: 0.8022617697715759:  94%|█████████▎| 24222/25880 [4:56:21<21:06,  1.31it/s]
1|24223|Loss: 0.8654184341430664:  94%|█████████▎| 24222/25880 [4:56:22<21:06,  1.31it/s]
1|24223|Loss: 0.8654184341430664:  94%|█████████▎| 24223/25880 [4:56:22<21:44,  1.27it/s]
1|24224|Loss: 0.7378999590873718:  94%|█████████▎| 24223/25880 [4:56:23<21:44,  1.27it/s]
1|24224|Loss: 0.7378999590873718:  94%|█████████▎| 24224/25880 [4:56:23<20:03,  1.38it/s]
1|24225|Loss: 0.7466948628425598:  94%|█████████▎| 24224/25880 [4:56:23<20:03,  1.38it/s]
1|24225|Loss: 0.7466948628425598:  94%|█████████▎| 24225/25880 [4:56:23<18:59,  1.45it/s]
1|24226|Loss: 0.9091134667396545:  94%|█████████▎| 24225/25880 [4:56:24<18:59,  1.45it/s]
1|24226|Loss: 0.9091134667396545:  94%|█████████▎| 24226/25880 [4:56:24<18:54,  1.46it/s]
1|24227|Loss: 0.9106490612030029:  94%|█████████▎| 24226/25880 [4:56:25<18:54,  1.46it/s]
1|24227|Loss: 0.9106490612030029:  94%|█████████▎| 24227/25880 [4:56:25<18:36,  1.48it/s]
1|24228|Loss: 0.7941778898239136:  94%|█████████▎| 24227/25880 [4:56:25<18:36,  1.48it/s]
1|24228|Loss: 0.7941778898239136:  94%|█████████▎| 24228/25880 [4:56:26<19:15,  1.43it/s]
1|24229|Loss: 0.7633127570152283:  94%|█████████▎| 24228/25880 [4:56:26<19:15,  1.43it/s]
1|24229|Loss: 0.7633127570152283:  94%|█████████▎| 24229/25880 [4:56:26<20:25,  1.35it/s]
1|24230|Loss: 0.8059712648391724:  94%|█████████▎| 24229/25880 [4:56:27<20:25,  1.35it/s]
1|24230|Loss: 0.8059712648391724:  94%|█████████▎| 24230/25880 [4:56:27<20:29,  1.34it/s]
1|24231|Loss: 0.7967773675918579:  94%|█████████▎| 24230/25880 [4:56:28<20:29,  1.34it/s]
1|24231|Loss: 0.7967773675918579:  94%|█████████▎| 24231/25880 [4:56:28<19:38,  1.40it/s]
1|24232|Loss: 0.9499478936195374:  94%|█████████▎| 24231/25880 [4:56:28<19:38,  1.40it/s]
1|24232|Loss: 0.9499478936195374:  94%|█████████▎| 24232/25880 [4:56:28<18:48,  1.46it/s]
1|24233|Loss: 0.9180794954299927:  94%|█████████▎| 24232/25880 [4:56:29<18:48,  1.46it/s]
1|24233|Loss: 0.9180794954299927:  94%|█████████▎| 24233/25880 [4:56:29<17:42,  1.55it/s]
1|24234|Loss: 0.8640350699424744:  94%|█████████▎| 24233/25880 [4:56:29<17:42,  1.55it/s]
1|24234|Loss: 0.8640350699424744:  94%|█████████▎| 24234/25880 [4:56:30<17:17,  1.59it/s]
1|24235|Loss: 0.7905977964401245:  94%|█████████▎| 24234/25880 [4:56:30<17:17,  1.59it/s]
1|24235|Loss: 0.7905977964401245:  94%|█████████▎| 24235/25880 [4:56:30<17:43,  1.55it/s]
1|24236|Loss: 0.7798992991447449:  94%|█████████▎| 24235/25880 [4:56:31<17:43,  1.55it/s]
1|24236|Loss: 0.7798992991447449:  94%|█████████▎| 24236/25880 [4:56:31<16:56,  1.62it/s]
1|24237|Loss: 0.8619019389152527:  94%|█████████▎| 24236/25880 [4:56:31<16:56,  1.62it/s]
1|24237|Loss: 0.8619019389152527:  94%|█████████▎| 24237/25880 [4:56:31<17:18,  1.58it/s]
1|24238|Loss: 0.8035587668418884:  94%|█████████▎| 24237/25880 [4:56:32<17:18,  1.58it/s]
1|24238|Loss: 0.8035587668418884:  94%|█████████▎| 24238/25880 [4:56:32<18:02,  1.52it/s]
1|24239|Loss: 0.9084174633026123:  94%|█████████▎| 24238/25880 [4:56:33<18:02,  1.52it/s]
1|24239|Loss: 0.9084174633026123:  94%|█████████▎| 24239/25880 [4:56:33<17:40,  1.55it/s]
1|24240|Loss: 0.8563649654388428:  94%|█████████▎| 24239/25880 [4:56:33<17:40,  1.55it/s]
1|24240|Loss: 0.8563649654388428:  94%|█████████▎| 24240/25880 [4:56:33<16:20,  1.67it/s]
1|24241|Loss: 0.806194543838501:  94%|█████████▎| 24240/25880 [4:56:34<16:20,  1.67it/s] 
1|24241|Loss: 0.806194543838501:  94%|█████████▎| 24241/25880 [4:56:34<17:14,  1.58it/s]
1|24242|Loss: 0.7677482962608337:  94%|█████████▎| 24241/25880 [4:56:34<17:14,  1.58it/s]
1|24242|Loss: 0.7677482962608337:  94%|█████████▎| 24242/25880 [4:56:35<18:00,  1.52it/s]
1|24243|Loss: 0.7543718814849854:  94%|█████████▎| 24242/25880 [4:56:35<18:00,  1.52it/s]
1|24243|Loss: 0.7543718814849854:  94%|█████████▎| 24243/25880 [4:56:35<17:56,  1.52it/s]
1|24244|Loss: 0.9140638709068298:  94%|█████████▎| 24243/25880 [4:56:36<17:56,  1.52it/s]
1|24244|Loss: 0.9140638709068298:  94%|█████████▎| 24244/25880 [4:56:36<17:50,  1.53it/s]
1|24245|Loss: 0.8278065323829651:  94%|█████████▎| 24244/25880 [4:56:36<17:50,  1.53it/s]
1|24245|Loss: 0.8278065323829651:  94%|█████████▎| 24245/25880 [4:56:37<17:46,  1.53it/s]
1|24246|Loss: 0.8552084565162659:  94%|█████████▎| 24245/25880 [4:56:37<17:46,  1.53it/s]
1|24246|Loss: 0.8552084565162659:  94%|█████████▎| 24246/25880 [4:56:37<19:07,  1.42it/s]
1|24247|Loss: 0.9915198683738708:  94%|█████████▎| 24246/25880 [4:56:38<19:07,  1.42it/s]
1|24247|Loss: 0.9915198683738708:  94%|█████████▎| 24247/25880 [4:56:38<21:07,  1.29it/s]
1|24248|Loss: 0.7583395838737488:  94%|█████████▎| 24247/25880 [4:56:39<21:07,  1.29it/s]
1|24248|Loss: 0.7583395838737488:  94%|█████████▎| 24248/25880 [4:56:39<19:43,  1.38it/s]
1|24249|Loss: 0.8353664875030518:  94%|█████████▎| 24248/25880 [4:56:39<19:43,  1.38it/s]
1|24249|Loss: 0.8353664875030518:  94%|█████████▎| 24249/25880 [4:56:40<18:47,  1.45it/s]
1|24250|Loss: 0.8515964150428772:  94%|█████████▎| 24249/25880 [4:56:40<18:47,  1.45it/s]
1|24250|Loss: 0.8515964150428772:  94%|█████████▎| 24250/25880 [4:56:40<19:48,  1.37it/s]
1|24251|Loss: 1.0350462198257446:  94%|█████████▎| 24250/25880 [4:56:41<19:48,  1.37it/s]
1|24251|Loss: 1.0350462198257446:  94%|█████████▎| 24251/25880 [4:56:41<20:42,  1.31it/s]
1|24252|Loss: 0.7654781937599182:  94%|█████████▎| 24251/25880 [4:56:42<20:42,  1.31it/s]
1|24252|Loss: 0.7654781937599182:  94%|█████████▎| 24252/25880 [4:56:42<20:00,  1.36it/s]
1|24253|Loss: 0.8462584018707275:  94%|█████████▎| 24252/25880 [4:56:42<20:00,  1.36it/s]
1|24253|Loss: 0.8462584018707275:  94%|█████████▎| 24253/25880 [4:56:43<20:34,  1.32it/s]
1|24254|Loss: 0.8649685978889465:  94%|█████████▎| 24253/25880 [4:56:43<20:34,  1.32it/s]
1|24254|Loss: 0.8649685978889465:  94%|█████████▎| 24254/25880 [4:56:44<21:03,  1.29it/s]
1|24255|Loss: 0.799839973449707:  94%|█████████▎| 24254/25880 [4:56:44<21:03,  1.29it/s] 
1|24255|Loss: 0.799839973449707:  94%|█████████▎| 24255/25880 [4:56:44<20:47,  1.30it/s]
1|24256|Loss: 0.7316294312477112:  94%|█████████▎| 24255/25880 [4:56:45<20:47,  1.30it/s]
1|24256|Loss: 0.7316294312477112:  94%|█████████▎| 24256/25880 [4:56:45<21:29,  1.26it/s]
1|24257|Loss: 0.7424854040145874:  94%|█████████▎| 24256/25880 [4:56:46<21:29,  1.26it/s]
1|24257|Loss: 0.7424854040145874:  94%|█████████▎| 24257/25880 [4:56:46<22:04,  1.23it/s]
1|24258|Loss: 0.8225340247154236:  94%|█████████▎| 24257/25880 [4:56:46<22:04,  1.23it/s]
1|24258|Loss: 0.8225340247154236:  94%|█████████▎| 24258/25880 [4:56:47<21:01,  1.29it/s]
1|24259|Loss: 0.783287763595581:  94%|█████████▎| 24258/25880 [4:56:47<21:01,  1.29it/s] 
1|24259|Loss: 0.783287763595581:  94%|█████████▎| 24259/25880 [4:56:47<19:13,  1.41it/s]
1|24260|Loss: 0.9090500473976135:  94%|█████████▎| 24259/25880 [4:56:48<19:13,  1.41it/s]
1|24260|Loss: 0.9090500473976135:  94%|█████████▎| 24260/25880 [4:56:48<18:51,  1.43it/s]
1|24261|Loss: 1.0182297229766846:  94%|█████████▎| 24260/25880 [4:56:48<18:51,  1.43it/s]
1|24261|Loss: 1.0182297229766846:  94%|█████████▎| 24261/25880 [4:56:49<18:18,  1.47it/s]
1|24262|Loss: 0.8158668875694275:  94%|█████████▎| 24261/25880 [4:56:49<18:18,  1.47it/s]
1|24262|Loss: 0.8158668875694275:  94%|█████████▎| 24262/25880 [4:56:49<17:39,  1.53it/s]
1|24263|Loss: 0.8970615863800049:  94%|█████████▎| 24262/25880 [4:56:50<17:39,  1.53it/s]
1|24263|Loss: 0.8970615863800049:  94%|█████████▍| 24263/25880 [4:56:50<18:49,  1.43it/s]
1|24264|Loss: 0.8763799667358398:  94%|█████████▍| 24263/25880 [4:56:50<18:49,  1.43it/s]
1|24264|Loss: 0.8763799667358398:  94%|█████████▍| 24264/25880 [4:56:51<19:17,  1.40it/s]
1|24265|Loss: 0.7336032390594482:  94%|█████████▍| 24264/25880 [4:56:51<19:17,  1.40it/s]
1|24265|Loss: 0.7336032390594482:  94%|█████████▍| 24265/25880 [4:56:51<19:11,  1.40it/s]
1|24266|Loss: 0.7646437883377075:  94%|█████████▍| 24265/25880 [4:56:52<19:11,  1.40it/s]
1|24266|Loss: 0.7646437883377075:  94%|█████████▍| 24266/25880 [4:56:52<19:06,  1.41it/s]
1|24267|Loss: 0.7745765447616577:  94%|█████████▍| 24266/25880 [4:56:53<19:06,  1.41it/s]
1|24267|Loss: 0.7745765447616577:  94%|█████████▍| 24267/25880 [4:56:53<19:01,  1.41it/s]
1|24268|Loss: 0.7434641122817993:  94%|█████████▍| 24267/25880 [4:56:53<19:01,  1.41it/s]
1|24268|Loss: 0.7434641122817993:  94%|█████████▍| 24268/25880 [4:56:54<18:59,  1.41it/s]
1|24269|Loss: 0.8929041624069214:  94%|█████████▍| 24268/25880 [4:56:54<18:59,  1.41it/s]
1|24269|Loss: 0.8929041624069214:  94%|█████████▍| 24269/25880 [4:56:54<17:20,  1.55it/s]
1|24270|Loss: 0.9322220087051392:  94%|█████████▍| 24269/25880 [4:56:54<17:20,  1.55it/s]
1|24270|Loss: 0.9322220087051392:  94%|█████████▍| 24270/25880 [4:56:55<16:24,  1.64it/s]
1|24271|Loss: 0.876283586025238:  94%|█████████▍| 24270/25880 [4:56:55<16:24,  1.64it/s] 
1|24271|Loss: 0.876283586025238:  94%|█████████▍| 24271/25880 [4:56:55<15:57,  1.68it/s]
1|24272|Loss: 0.7270280718803406:  94%|█████████▍| 24271/25880 [4:56:56<15:57,  1.68it/s]
1|24272|Loss: 0.7270280718803406:  94%|█████████▍| 24272/25880 [4:56:56<17:31,  1.53it/s]
1|24273|Loss: 0.916778564453125:  94%|█████████▍| 24272/25880 [4:56:56<17:31,  1.53it/s] 
1|24273|Loss: 0.916778564453125:  94%|█████████▍| 24273/25880 [4:56:57<18:28,  1.45it/s]
1|24274|Loss: 0.887230396270752:  94%|█████████▍| 24273/25880 [4:56:57<18:28,  1.45it/s]
1|24274|Loss: 0.887230396270752:  94%|█████████▍| 24274/25880 [4:56:57<17:04,  1.57it/s]
1|24275|Loss: 0.7629490494728088:  94%|█████████▍| 24274/25880 [4:56:58<17:04,  1.57it/s]
1|24275|Loss: 0.7629490494728088:  94%|█████████▍| 24275/25880 [4:56:58<17:57,  1.49it/s]
1|24276|Loss: 0.7816304564476013:  94%|█████████▍| 24275/25880 [4:56:58<17:57,  1.49it/s]
1|24276|Loss: 0.7816304564476013:  94%|█████████▍| 24276/25880 [4:56:59<18:42,  1.43it/s]
1|24277|Loss: 0.7683495879173279:  94%|█████████▍| 24276/25880 [4:56:59<18:42,  1.43it/s]
1|24277|Loss: 0.7683495879173279:  94%|█████████▍| 24277/25880 [4:56:59<18:46,  1.42it/s]
1|24278|Loss: 0.9437810182571411:  94%|█████████▍| 24277/25880 [4:57:00<18:46,  1.42it/s]
1|24278|Loss: 0.9437810182571411:  94%|█████████▍| 24278/25880 [4:57:00<19:44,  1.35it/s]
1|24279|Loss: 0.8056725263595581:  94%|█████████▍| 24278/25880 [4:57:01<19:44,  1.35it/s]
1|24279|Loss: 0.8056725263595581:  94%|█████████▍| 24279/25880 [4:57:01<19:18,  1.38it/s]
1|24280|Loss: 0.8249838948249817:  94%|█████████▍| 24279/25880 [4:57:01<19:18,  1.38it/s]
1|24280|Loss: 0.8249838948249817:  94%|█████████▍| 24280/25880 [4:57:02<19:02,  1.40it/s]
1|24281|Loss: 0.8651800155639648:  94%|█████████▍| 24280/25880 [4:57:02<19:02,  1.40it/s]
1|24281|Loss: 0.8651800155639648:  94%|█████████▍| 24281/25880 [4:57:02<18:31,  1.44it/s]
1|24282|Loss: 0.879601240158081:  94%|█████████▍| 24281/25880 [4:57:03<18:31,  1.44it/s] 
1|24282|Loss: 0.879601240158081:  94%|█████████▍| 24282/25880 [4:57:03<17:45,  1.50it/s]
1|24283|Loss: 0.9779919981956482:  94%|█████████▍| 24282/25880 [4:57:03<17:45,  1.50it/s]
1|24283|Loss: 0.9779919981956482:  94%|█████████▍| 24283/25880 [4:57:04<17:10,  1.55it/s]
1|24284|Loss: 0.7662324905395508:  94%|█████████▍| 24283/25880 [4:57:04<17:10,  1.55it/s]
1|24284|Loss: 0.7662324905395508:  94%|█████████▍| 24284/25880 [4:57:04<17:21,  1.53it/s]
1|24285|Loss: 0.7597936391830444:  94%|█████████▍| 24284/25880 [4:57:05<17:21,  1.53it/s]
1|24285|Loss: 0.7597936391830444:  94%|█████████▍| 24285/25880 [4:57:05<16:58,  1.57it/s]
1|24286|Loss: 0.8322677612304688:  94%|█████████▍| 24285/25880 [4:57:05<16:58,  1.57it/s]
1|24286|Loss: 0.8322677612304688:  94%|█████████▍| 24286/25880 [4:57:06<18:07,  1.47it/s]
1|24287|Loss: 0.8051331043243408:  94%|█████████▍| 24286/25880 [4:57:06<18:07,  1.47it/s]
1|24287|Loss: 0.8051331043243408:  94%|█████████▍| 24287/25880 [4:57:06<19:02,  1.39it/s]
1|24288|Loss: 0.784231960773468:  94%|█████████▍| 24287/25880 [4:57:07<19:02,  1.39it/s] 
1|24288|Loss: 0.784231960773468:  94%|█████████▍| 24288/25880 [4:57:07<19:10,  1.38it/s]
1|24289|Loss: 0.8898755311965942:  94%|█████████▍| 24288/25880 [4:57:07<19:10,  1.38it/s]
1|24289|Loss: 0.8898755311965942:  94%|█████████▍| 24289/25880 [4:57:08<17:37,  1.50it/s]
1|24290|Loss: 0.8578372001647949:  94%|█████████▍| 24289/25880 [4:57:08<17:37,  1.50it/s]
1|24290|Loss: 0.8578372001647949:  94%|█████████▍| 24290/25880 [4:57:08<17:43,  1.50it/s]
1|24291|Loss: 1.0058621168136597:  94%|█████████▍| 24290/25880 [4:57:09<17:43,  1.50it/s]
1|24291|Loss: 1.0058621168136597:  94%|█████████▍| 24291/25880 [4:57:09<18:33,  1.43it/s]
1|24292|Loss: 0.650533139705658:  94%|█████████▍| 24291/25880 [4:57:10<18:33,  1.43it/s] 
1|24292|Loss: 0.650533139705658:  94%|█████████▍| 24292/25880 [4:57:10<18:12,  1.45it/s]
1|24293|Loss: 0.9196562170982361:  94%|█████████▍| 24292/25880 [4:57:10<18:12,  1.45it/s]
1|24293|Loss: 0.9196562170982361:  94%|█████████▍| 24293/25880 [4:57:10<17:49,  1.48it/s]
1|24294|Loss: 0.897935688495636:  94%|█████████▍| 24293/25880 [4:57:11<17:49,  1.48it/s] 
1|24294|Loss: 0.897935688495636:  94%|█████████▍| 24294/25880 [4:57:11<18:08,  1.46it/s]
1|24295|Loss: 0.8772962689399719:  94%|█████████▍| 24294/25880 [4:57:12<18:08,  1.46it/s]
1|24295|Loss: 0.8772962689399719:  94%|█████████▍| 24295/25880 [4:57:12<18:58,  1.39it/s]
1|24296|Loss: 1.0181852579116821:  94%|█████████▍| 24295/25880 [4:57:12<18:58,  1.39it/s]
1|24296|Loss: 1.0181852579116821:  94%|█████████▍| 24296/25880 [4:57:13<20:36,  1.28it/s]
1|24297|Loss: 0.8250329494476318:  94%|█████████▍| 24296/25880 [4:57:13<20:36,  1.28it/s]
1|24297|Loss: 0.8250329494476318:  94%|█████████▍| 24297/25880 [4:57:14<21:00,  1.26it/s]
1|24298|Loss: 0.8778762817382812:  94%|█████████▍| 24297/25880 [4:57:14<21:00,  1.26it/s]
1|24298|Loss: 0.8778762817382812:  94%|█████████▍| 24298/25880 [4:57:14<20:56,  1.26it/s]
1|24299|Loss: 0.6938022375106812:  94%|█████████▍| 24298/25880 [4:57:15<20:56,  1.26it/s]
1|24299|Loss: 0.6938022375106812:  94%|█████████▍| 24299/25880 [4:57:15<20:55,  1.26it/s]
1|24300|Loss: 0.8535248041152954:  94%|█████████▍| 24299/25880 [4:57:16<20:55,  1.26it/s]
1|24300|Loss: 0.8535248041152954:  94%|█████████▍| 24300/25880 [4:57:16<19:56,  1.32it/s]
1|24301|Loss: 0.9024290442466736:  94%|█████████▍| 24300/25880 [4:57:16<19:56,  1.32it/s]
1|24301|Loss: 0.9024290442466736:  94%|█████████▍| 24301/25880 [4:57:17<19:01,  1.38it/s]
1|24302|Loss: 0.8724904656410217:  94%|█████████▍| 24301/25880 [4:57:17<19:01,  1.38it/s]
1|24302|Loss: 0.8724904656410217:  94%|█████████▍| 24302/25880 [4:57:17<19:15,  1.37it/s]
1|24303|Loss: 0.7557670474052429:  94%|█████████▍| 24302/25880 [4:57:18<19:15,  1.37it/s]
1|24303|Loss: 0.7557670474052429:  94%|█████████▍| 24303/25880 [4:57:18<17:58,  1.46it/s]
1|24304|Loss: 0.894243597984314:  94%|█████████▍| 24303/25880 [4:57:18<17:58,  1.46it/s] 
1|24304|Loss: 0.894243597984314:  94%|█████████▍| 24304/25880 [4:57:19<17:48,  1.47it/s]
1|24305|Loss: 0.8462107181549072:  94%|█████████▍| 24304/25880 [4:57:19<17:48,  1.47it/s]
1|24305|Loss: 0.8462107181549072:  94%|█████████▍| 24305/25880 [4:57:19<18:08,  1.45it/s]
1|24306|Loss: 0.822331428527832:  94%|█████████▍| 24305/25880 [4:57:20<18:08,  1.45it/s] 
1|24306|Loss: 0.822331428527832:  94%|█████████▍| 24306/25880 [4:57:20<18:31,  1.42it/s]
1|24307|Loss: 0.9015985727310181:  94%|█████████▍| 24306/25880 [4:57:20<18:31,  1.42it/s]
1|24307|Loss: 0.9015985727310181:  94%|█████████▍| 24307/25880 [4:57:21<18:09,  1.44it/s]
1|24308|Loss: 0.7800114154815674:  94%|█████████▍| 24307/25880 [4:57:21<18:09,  1.44it/s]
1|24308|Loss: 0.7800114154815674:  94%|█████████▍| 24308/25880 [4:57:21<16:56,  1.55it/s]
1|24309|Loss: 1.0112762451171875:  94%|█████████▍| 24308/25880 [4:57:22<16:56,  1.55it/s]
1|24309|Loss: 1.0112762451171875:  94%|█████████▍| 24309/25880 [4:57:22<17:18,  1.51it/s]
1|24310|Loss: 0.9231236577033997:  94%|█████████▍| 24309/25880 [4:57:22<17:18,  1.51it/s]
1|24310|Loss: 0.9231236577033997:  94%|█████████▍| 24310/25880 [4:57:23<17:58,  1.46it/s]
1|24311|Loss: 0.7309485673904419:  94%|█████████▍| 24310/25880 [4:57:23<17:58,  1.46it/s]
1|24311|Loss: 0.7309485673904419:  94%|█████████▍| 24311/25880 [4:57:23<17:31,  1.49it/s]
1|24312|Loss: 0.9523327946662903:  94%|█████████▍| 24311/25880 [4:57:24<17:31,  1.49it/s]
1|24312|Loss: 0.9523327946662903:  94%|█████████▍| 24312/25880 [4:57:24<17:44,  1.47it/s]
1|24313|Loss: 0.8682077527046204:  94%|█████████▍| 24312/25880 [4:57:24<17:44,  1.47it/s]
1|24313|Loss: 0.8682077527046204:  94%|█████████▍| 24313/25880 [4:57:25<18:53,  1.38it/s]
1|24314|Loss: 0.8873977065086365:  94%|█████████▍| 24313/25880 [4:57:25<18:53,  1.38it/s]
1|24314|Loss: 0.8873977065086365:  94%|█████████▍| 24314/25880 [4:57:26<20:18,  1.28it/s]
1|24315|Loss: 0.829761803150177:  94%|█████████▍| 24314/25880 [4:57:26<20:18,  1.28it/s] 
1|24315|Loss: 0.829761803150177:  94%|█████████▍| 24315/25880 [4:57:27<21:24,  1.22it/s]
1|24316|Loss: 0.797938346862793:  94%|█████████▍| 24315/25880 [4:57:27<21:24,  1.22it/s]
1|24316|Loss: 0.797938346862793:  94%|█████████▍| 24316/25880 [4:57:27<21:03,  1.24it/s]
1|24317|Loss: 0.8415462374687195:  94%|█████████▍| 24316/25880 [4:57:28<21:03,  1.24it/s]
1|24317|Loss: 0.8415462374687195:  94%|█████████▍| 24317/25880 [4:57:28<20:49,  1.25it/s]
1|24318|Loss: 0.6888151168823242:  94%|█████████▍| 24317/25880 [4:57:29<20:49,  1.25it/s]
1|24318|Loss: 0.6888151168823242:  94%|█████████▍| 24318/25880 [4:57:29<18:50,  1.38it/s]
1|24319|Loss: 0.7033751606941223:  94%|█████████▍| 24318/25880 [4:57:29<18:50,  1.38it/s]
1|24319|Loss: 0.7033751606941223:  94%|█████████▍| 24319/25880 [4:57:29<17:36,  1.48it/s]
1|24320|Loss: 0.6523276567459106:  94%|█████████▍| 24319/25880 [4:57:30<17:36,  1.48it/s]
1|24320|Loss: 0.6523276567459106:  94%|█████████▍| 24320/25880 [4:57:30<17:12,  1.51it/s]
1|24321|Loss: 0.9428036212921143:  94%|█████████▍| 24320/25880 [4:57:30<17:12,  1.51it/s]
1|24321|Loss: 0.9428036212921143:  94%|█████████▍| 24321/25880 [4:57:31<17:37,  1.47it/s]
1|24322|Loss: 0.9066874980926514:  94%|█████████▍| 24321/25880 [4:57:31<17:37,  1.47it/s]
1|24322|Loss: 0.9066874980926514:  94%|█████████▍| 24322/25880 [4:57:31<18:09,  1.43it/s]
1|24323|Loss: 0.6881552934646606:  94%|█████████▍| 24322/25880 [4:57:32<18:09,  1.43it/s]
1|24323|Loss: 0.6881552934646606:  94%|█████████▍| 24323/25880 [4:57:32<18:32,  1.40it/s]
1|24324|Loss: 0.7425847053527832:  94%|█████████▍| 24323/25880 [4:57:33<18:32,  1.40it/s]
1|24324|Loss: 0.7425847053527832:  94%|█████████▍| 24324/25880 [4:57:33<18:48,  1.38it/s]
1|24325|Loss: 0.8489837050437927:  94%|█████████▍| 24324/25880 [4:57:33<18:48,  1.38it/s]
1|24325|Loss: 0.8489837050437927:  94%|█████████▍| 24325/25880 [4:57:34<18:57,  1.37it/s]
1|24326|Loss: 1.0680232048034668:  94%|█████████▍| 24325/25880 [4:57:34<18:57,  1.37it/s]
1|24326|Loss: 1.0680232048034668:  94%|█████████▍| 24326/25880 [4:57:34<19:37,  1.32it/s]
1|24327|Loss: 0.7539161443710327:  94%|█████████▍| 24326/25880 [4:57:35<19:37,  1.32it/s]
1|24327|Loss: 0.7539161443710327:  94%|█████████▍| 24327/25880 [4:57:35<19:36,  1.32it/s]
1|24328|Loss: 0.9277227520942688:  94%|█████████▍| 24327/25880 [4:57:36<19:36,  1.32it/s]
1|24328|Loss: 0.9277227520942688:  94%|█████████▍| 24328/25880 [4:57:36<19:13,  1.35it/s]
1|24329|Loss: 0.7699494361877441:  94%|█████████▍| 24328/25880 [4:57:36<19:13,  1.35it/s]
1|24329|Loss: 0.7699494361877441:  94%|█████████▍| 24329/25880 [4:57:37<18:30,  1.40it/s]
1|24330|Loss: 0.9304772615432739:  94%|█████████▍| 24329/25880 [4:57:37<18:30,  1.40it/s]
1|24330|Loss: 0.9304772615432739:  94%|█████████▍| 24330/25880 [4:57:37<17:47,  1.45it/s]
1|24331|Loss: 0.7655219435691833:  94%|█████████▍| 24330/25880 [4:57:38<17:47,  1.45it/s]
1|24331|Loss: 0.7655219435691833:  94%|█████████▍| 24331/25880 [4:57:38<17:45,  1.45it/s]
1|24332|Loss: 0.8756901621818542:  94%|█████████▍| 24331/25880 [4:57:38<17:45,  1.45it/s]
1|24332|Loss: 0.8756901621818542:  94%|█████████▍| 24332/25880 [4:57:39<17:55,  1.44it/s]
1|24333|Loss: 0.8044847249984741:  94%|█████████▍| 24332/25880 [4:57:39<17:55,  1.44it/s]
1|24333|Loss: 0.8044847249984741:  94%|█████████▍| 24333/25880 [4:57:39<16:48,  1.53it/s]
1|24334|Loss: 0.677492618560791:  94%|█████████▍| 24333/25880 [4:57:40<16:48,  1.53it/s] 
1|24334|Loss: 0.677492618560791:  94%|█████████▍| 24334/25880 [4:57:40<18:29,  1.39it/s]
1|24335|Loss: 0.7691716551780701:  94%|█████████▍| 24334/25880 [4:57:41<18:29,  1.39it/s]
1|24335|Loss: 0.7691716551780701:  94%|█████████▍| 24335/25880 [4:57:41<19:16,  1.34it/s]
1|24336|Loss: 0.9394168853759766:  94%|█████████▍| 24335/25880 [4:57:41<19:16,  1.34it/s]
1|24336|Loss: 0.9394168853759766:  94%|█████████▍| 24336/25880 [4:57:42<20:12,  1.27it/s]
1|24337|Loss: 0.722033679485321:  94%|█████████▍| 24336/25880 [4:57:42<20:12,  1.27it/s] 
1|24337|Loss: 0.722033679485321:  94%|█████████▍| 24337/25880 [4:57:42<19:52,  1.29it/s]
1|24338|Loss: 0.9138554334640503:  94%|█████████▍| 24337/25880 [4:57:43<19:52,  1.29it/s]
1|24338|Loss: 0.9138554334640503:  94%|█████████▍| 24338/25880 [4:57:43<19:19,  1.33it/s]
1|24339|Loss: 0.8389185667037964:  94%|█████████▍| 24338/25880 [4:57:44<19:19,  1.33it/s]
1|24339|Loss: 0.8389185667037964:  94%|█████████▍| 24339/25880 [4:57:44<19:32,  1.31it/s]
1|24340|Loss: 0.9023361206054688:  94%|█████████▍| 24339/25880 [4:57:44<19:32,  1.31it/s]
1|24340|Loss: 0.9023361206054688:  94%|█████████▍| 24340/25880 [4:57:45<18:41,  1.37it/s]
1|24341|Loss: 0.8562020659446716:  94%|█████████▍| 24340/25880 [4:57:45<18:41,  1.37it/s]
1|24341|Loss: 0.8562020659446716:  94%|█████████▍| 24341/25880 [4:57:45<17:41,  1.45it/s]
1|24342|Loss: 0.787369430065155:  94%|█████████▍| 24341/25880 [4:57:46<17:41,  1.45it/s] 
1|24342|Loss: 0.787369430065155:  94%|█████████▍| 24342/25880 [4:57:46<16:54,  1.52it/s]
1|24343|Loss: 0.9693459272384644:  94%|█████████▍| 24342/25880 [4:57:46<16:54,  1.52it/s]
1|24343|Loss: 0.9693459272384644:  94%|█████████▍| 24343/25880 [4:57:47<17:13,  1.49it/s]
1|24344|Loss: 0.7970452904701233:  94%|█████████▍| 24343/25880 [4:57:47<17:13,  1.49it/s]
1|24344|Loss: 0.7970452904701233:  94%|█████████▍| 24344/25880 [4:57:47<17:07,  1.50it/s]
1|24345|Loss: 0.8290547728538513:  94%|█████████▍| 24344/25880 [4:57:48<17:07,  1.50it/s]
1|24345|Loss: 0.8290547728538513:  94%|█████████▍| 24345/25880 [4:57:48<18:05,  1.41it/s]
1|24346|Loss: 0.8710682988166809:  94%|█████████▍| 24345/25880 [4:57:48<18:05,  1.41it/s]
1|24346|Loss: 0.8710682988166809:  94%|█████████▍| 24346/25880 [4:57:49<18:29,  1.38it/s]
1|24347|Loss: 0.9395556449890137:  94%|█████████▍| 24346/25880 [4:57:49<18:29,  1.38it/s]
1|24347|Loss: 0.9395556449890137:  94%|█████████▍| 24347/25880 [4:57:50<19:34,  1.31it/s]
1|24348|Loss: 0.7518350481987:  94%|█████████▍| 24347/25880 [4:57:50<19:34,  1.31it/s]   
1|24348|Loss: 0.7518350481987:  94%|█████████▍| 24348/25880 [4:57:50<20:26,  1.25it/s]
1|24349|Loss: 0.7675997018814087:  94%|█████████▍| 24348/25880 [4:57:51<20:26,  1.25it/s]
1|24349|Loss: 0.7675997018814087:  94%|█████████▍| 24349/25880 [4:57:51<19:27,  1.31it/s]
1|24350|Loss: 0.8015087246894836:  94%|█████████▍| 24349/25880 [4:57:52<19:27,  1.31it/s]
1|24350|Loss: 0.8015087246894836:  94%|█████████▍| 24350/25880 [4:57:52<18:53,  1.35it/s]
1|24351|Loss: 0.8612629175186157:  94%|█████████▍| 24350/25880 [4:57:52<18:53,  1.35it/s]
1|24351|Loss: 0.8612629175186157:  94%|█████████▍| 24351/25880 [4:57:52<18:06,  1.41it/s]
1|24352|Loss: 0.8820295333862305:  94%|█████████▍| 24351/25880 [4:57:53<18:06,  1.41it/s]
1|24352|Loss: 0.8820295333862305:  94%|█████████▍| 24352/25880 [4:57:53<17:58,  1.42it/s]
1|24353|Loss: 0.7922950983047485:  94%|█████████▍| 24352/25880 [4:57:54<17:58,  1.42it/s]
1|24353|Loss: 0.7922950983047485:  94%|█████████▍| 24353/25880 [4:57:54<18:30,  1.37it/s]
1|24354|Loss: 0.886181652545929:  94%|█████████▍| 24353/25880 [4:57:54<18:30,  1.37it/s] 
1|24354|Loss: 0.886181652545929:  94%|█████████▍| 24354/25880 [4:57:55<17:09,  1.48it/s]
1|24355|Loss: 0.759535551071167:  94%|█████████▍| 24354/25880 [4:57:55<17:09,  1.48it/s]
1|24355|Loss: 0.759535551071167:  94%|█████████▍| 24355/25880 [4:57:55<17:56,  1.42it/s]
1|24356|Loss: 0.8688666224479675:  94%|█████████▍| 24355/25880 [4:57:56<17:56,  1.42it/s]
1|24356|Loss: 0.8688666224479675:  94%|█████████▍| 24356/25880 [4:57:56<18:57,  1.34it/s]
1|24357|Loss: 0.7842544913291931:  94%|█████████▍| 24356/25880 [4:57:57<18:57,  1.34it/s]
1|24357|Loss: 0.7842544913291931:  94%|█████████▍| 24357/25880 [4:57:57<18:17,  1.39it/s]
1|24358|Loss: 0.8805343508720398:  94%|█████████▍| 24357/25880 [4:57:57<18:17,  1.39it/s]
1|24358|Loss: 0.8805343508720398:  94%|█████████▍| 24358/25880 [4:57:57<17:31,  1.45it/s]
1|24359|Loss: 0.8356886506080627:  94%|█████████▍| 24358/25880 [4:57:58<17:31,  1.45it/s]
1|24359|Loss: 0.8356886506080627:  94%|█████████▍| 24359/25880 [4:57:58<16:58,  1.49it/s]
1|24360|Loss: 0.9737394452095032:  94%|█████████▍| 24359/25880 [4:57:58<16:58,  1.49it/s]
1|24360|Loss: 0.9737394452095032:  94%|█████████▍| 24360/25880 [4:57:59<18:42,  1.35it/s]
1|24361|Loss: 0.9561721682548523:  94%|█████████▍| 24360/25880 [4:57:59<18:42,  1.35it/s]
1|24361|Loss: 0.9561721682548523:  94%|█████████▍| 24361/25880 [4:58:00<18:25,  1.37it/s]
1|24362|Loss: 0.9345115423202515:  94%|█████████▍| 24361/25880 [4:58:00<18:25,  1.37it/s]
1|24362|Loss: 0.9345115423202515:  94%|█████████▍| 24362/25880 [4:58:00<18:54,  1.34it/s]
1|24363|Loss: 0.8148167729377747:  94%|█████████▍| 24362/25880 [4:58:01<18:54,  1.34it/s]
1|24363|Loss: 0.8148167729377747:  94%|█████████▍| 24363/25880 [4:58:01<19:20,  1.31it/s]
1|24364|Loss: 0.8998367786407471:  94%|█████████▍| 24363/25880 [4:58:02<19:20,  1.31it/s]
1|24364|Loss: 0.8998367786407471:  94%|█████████▍| 24364/25880 [4:58:02<19:14,  1.31it/s]
1|24365|Loss: 0.8033005595207214:  94%|█████████▍| 24364/25880 [4:58:02<19:14,  1.31it/s]
1|24365|Loss: 0.8033005595207214:  94%|█████████▍| 24365/25880 [4:58:03<18:20,  1.38it/s]
1|24366|Loss: 0.8361905217170715:  94%|█████████▍| 24365/25880 [4:58:03<18:20,  1.38it/s]
1|24366|Loss: 0.8361905217170715:  94%|█████████▍| 24366/25880 [4:58:03<19:14,  1.31it/s]
1|24367|Loss: 0.9725070595741272:  94%|█████████▍| 24366/25880 [4:58:04<19:14,  1.31it/s]
1|24367|Loss: 0.9725070595741272:  94%|█████████▍| 24367/25880 [4:58:04<18:41,  1.35it/s]
1|24368|Loss: 0.7207857966423035:  94%|█████████▍| 24367/25880 [4:58:05<18:41,  1.35it/s]
1|24368|Loss: 0.7207857966423035:  94%|█████████▍| 24368/25880 [4:58:05<18:31,  1.36it/s]
1|24369|Loss: 0.8542683720588684:  94%|█████████▍| 24368/25880 [4:58:05<18:31,  1.36it/s]
1|24369|Loss: 0.8542683720588684:  94%|█████████▍| 24369/25880 [4:58:06<18:30,  1.36it/s]
1|24370|Loss: 0.9225292205810547:  94%|█████████▍| 24369/25880 [4:58:06<18:30,  1.36it/s]
1|24370|Loss: 0.9225292205810547:  94%|█████████▍| 24370/25880 [4:58:06<18:46,  1.34it/s]
1|24371|Loss: 0.8651893138885498:  94%|█████████▍| 24370/25880 [4:58:07<18:46,  1.34it/s]
1|24371|Loss: 0.8651893138885498:  94%|█████████▍| 24371/25880 [4:58:07<19:13,  1.31it/s]
1|24372|Loss: 0.719232439994812:  94%|█████████▍| 24371/25880 [4:58:08<19:13,  1.31it/s] 
1|24372|Loss: 0.719232439994812:  94%|█████████▍| 24372/25880 [4:58:08<20:41,  1.21it/s]
1|24373|Loss: 0.6891737580299377:  94%|█████████▍| 24372/25880 [4:58:09<20:41,  1.21it/s]
1|24373|Loss: 0.6891737580299377:  94%|█████████▍| 24373/25880 [4:58:09<20:33,  1.22it/s]
1|24374|Loss: 1.0854003429412842:  94%|█████████▍| 24373/25880 [4:58:09<20:33,  1.22it/s]
1|24374|Loss: 1.0854003429412842:  94%|█████████▍| 24374/25880 [4:58:10<19:11,  1.31it/s]
1|24375|Loss: 0.8350272178649902:  94%|█████████▍| 24374/25880 [4:58:10<19:11,  1.31it/s]
1|24375|Loss: 0.8350272178649902:  94%|█████████▍| 24375/25880 [4:58:10<18:11,  1.38it/s]
1|24376|Loss: 0.7421804666519165:  94%|█████████▍| 24375/25880 [4:58:11<18:11,  1.38it/s]
1|24376|Loss: 0.7421804666519165:  94%|█████████▍| 24376/25880 [4:58:11<18:23,  1.36it/s]
1|24377|Loss: 0.7203752398490906:  94%|█████████▍| 24376/25880 [4:58:11<18:23,  1.36it/s]
1|24377|Loss: 0.7203752398490906:  94%|█████████▍| 24377/25880 [4:58:12<19:32,  1.28it/s]
1|24378|Loss: 0.879840612411499:  94%|█████████▍| 24377/25880 [4:58:12<19:32,  1.28it/s] 
1|24378|Loss: 0.879840612411499:  94%|█████████▍| 24378/25880 [4:58:13<19:23,  1.29it/s]
1|24379|Loss: 0.711006760597229:  94%|█████████▍| 24378/25880 [4:58:13<19:23,  1.29it/s]
1|24379|Loss: 0.711006760597229:  94%|█████████▍| 24379/25880 [4:58:13<19:45,  1.27it/s]
1|24380|Loss: 0.8741872906684875:  94%|█████████▍| 24379/25880 [4:58:14<19:45,  1.27it/s]
1|24380|Loss: 0.8741872906684875:  94%|█████████▍| 24380/25880 [4:58:14<19:56,  1.25it/s]
1|24381|Loss: 0.5556603670120239:  94%|█████████▍| 24380/25880 [4:58:15<19:56,  1.25it/s]
1|24381|Loss: 0.5556603670120239:  94%|█████████▍| 24381/25880 [4:58:15<21:46,  1.15it/s]
1|24382|Loss: 0.9873746037483215:  94%|█████████▍| 24381/25880 [4:58:16<21:46,  1.15it/s]
1|24382|Loss: 0.9873746037483215:  94%|█████████▍| 24382/25880 [4:58:16<20:35,  1.21it/s]
1|24383|Loss: 0.9953840374946594:  94%|█████████▍| 24382/25880 [4:58:16<20:35,  1.21it/s]
1|24383|Loss: 0.9953840374946594:  94%|█████████▍| 24383/25880 [4:58:17<19:32,  1.28it/s]
1|24384|Loss: 0.8329418897628784:  94%|█████████▍| 24383/25880 [4:58:17<19:32,  1.28it/s]
1|24384|Loss: 0.8329418897628784:  94%|█████████▍| 24384/25880 [4:58:17<19:09,  1.30it/s]
1|24385|Loss: 0.7985415458679199:  94%|█████████▍| 24384/25880 [4:58:18<19:09,  1.30it/s]
1|24385|Loss: 0.7985415458679199:  94%|█████████▍| 24385/25880 [4:58:18<17:33,  1.42it/s]
1|24386|Loss: 0.745389461517334:  94%|█████████▍| 24385/25880 [4:58:18<17:33,  1.42it/s] 
1|24386|Loss: 0.745389461517334:  94%|█████████▍| 24386/25880 [4:58:19<16:44,  1.49it/s]
1|24387|Loss: 0.8175619840621948:  94%|█████████▍| 24386/25880 [4:58:19<16:44,  1.49it/s]
1|24387|Loss: 0.8175619840621948:  94%|█████████▍| 24387/25880 [4:58:19<17:00,  1.46it/s]
1|24388|Loss: 0.7866590023040771:  94%|█████████▍| 24387/25880 [4:58:20<17:00,  1.46it/s]
1|24388|Loss: 0.7866590023040771:  94%|█████████▍| 24388/25880 [4:58:20<17:06,  1.45it/s]
1|24389|Loss: 0.8952566981315613:  94%|█████████▍| 24388/25880 [4:58:20<17:06,  1.45it/s]
1|24389|Loss: 0.8952566981315613:  94%|█████████▍| 24389/25880 [4:58:21<17:41,  1.40it/s]
1|24390|Loss: 0.8658682107925415:  94%|█████████▍| 24389/25880 [4:58:21<17:41,  1.40it/s]
1|24390|Loss: 0.8658682107925415:  94%|█████████▍| 24390/25880 [4:58:22<19:17,  1.29it/s]
1|24391|Loss: 0.830288290977478:  94%|█████████▍| 24390/25880 [4:58:22<19:17,  1.29it/s] 
1|24391|Loss: 0.830288290977478:  94%|█████████▍| 24391/25880 [4:58:22<18:43,  1.33it/s]
1|24392|Loss: 0.7991892099380493:  94%|█████████▍| 24391/25880 [4:58:23<18:43,  1.33it/s]
1|24392|Loss: 0.7991892099380493:  94%|█████████▍| 24392/25880 [4:58:23<19:08,  1.30it/s]
1|24393|Loss: 0.7902519106864929:  94%|█████████▍| 24392/25880 [4:58:24<19:08,  1.30it/s]
1|24393|Loss: 0.7902519106864929:  94%|█████████▍| 24393/25880 [4:58:24<19:39,  1.26it/s]
1|24394|Loss: 0.983921229839325:  94%|█████████▍| 24393/25880 [4:58:25<19:39,  1.26it/s] 
1|24394|Loss: 0.983921229839325:  94%|█████████▍| 24394/25880 [4:58:25<19:56,  1.24it/s]
1|24395|Loss: 0.8489962816238403:  94%|█████████▍| 24394/25880 [4:58:25<19:56,  1.24it/s]
1|24395|Loss: 0.8489962816238403:  94%|█████████▍| 24395/25880 [4:58:26<19:22,  1.28it/s]
1|24396|Loss: 0.8179684281349182:  94%|█████████▍| 24395/25880 [4:58:26<19:22,  1.28it/s]
1|24396|Loss: 0.8179684281349182:  94%|█████████▍| 24396/25880 [4:58:26<18:58,  1.30it/s]
1|24397|Loss: 0.8864049911499023:  94%|█████████▍| 24396/25880 [4:58:27<18:58,  1.30it/s]
1|24397|Loss: 0.8864049911499023:  94%|█████████▍| 24397/25880 [4:58:27<18:47,  1.31it/s]
1|24398|Loss: 0.8348835110664368:  94%|█████████▍| 24397/25880 [4:58:28<18:47,  1.31it/s]
1|24398|Loss: 0.8348835110664368:  94%|█████████▍| 24398/25880 [4:58:28<18:05,  1.37it/s]
1|24399|Loss: 0.8157913088798523:  94%|█████████▍| 24398/25880 [4:58:28<18:05,  1.37it/s]
1|24399|Loss: 0.8157913088798523:  94%|█████████▍| 24399/25880 [4:58:28<17:47,  1.39it/s]
1|24400|Loss: 0.9638473391532898:  94%|█████████▍| 24399/25880 [4:58:29<17:47,  1.39it/s]
1|24400|Loss: 0.9638473391532898:  94%|█████████▍| 24400/25880 [4:58:29<17:08,  1.44it/s]
1|24401|Loss: 0.8202247023582458:  94%|█████████▍| 24400/25880 [4:58:30<17:08,  1.44it/s]
1|24401|Loss: 0.8202247023582458:  94%|█████████▍| 24401/25880 [4:58:30<17:21,  1.42it/s]
1|24402|Loss: 0.8355786204338074:  94%|█████████▍| 24401/25880 [4:58:30<17:21,  1.42it/s]
1|24402|Loss: 0.8355786204338074:  94%|█████████▍| 24402/25880 [4:58:31<17:04,  1.44it/s]
1|24403|Loss: 0.9338089227676392:  94%|█████████▍| 24402/25880 [4:58:31<17:04,  1.44it/s]
1|24403|Loss: 0.9338089227676392:  94%|█████████▍| 24403/25880 [4:58:31<16:41,  1.48it/s]
1|24404|Loss: 0.9087481498718262:  94%|█████████▍| 24403/25880 [4:58:32<16:41,  1.48it/s]
1|24404|Loss: 0.9087481498718262:  94%|█████████▍| 24404/25880 [4:58:32<16:56,  1.45it/s]
1|24405|Loss: 0.8401660323143005:  94%|█████████▍| 24404/25880 [4:58:32<16:56,  1.45it/s]
1|24405|Loss: 0.8401660323143005:  94%|█████████▍| 24405/25880 [4:58:32<16:20,  1.51it/s]
1|24406|Loss: 0.9252731204032898:  94%|█████████▍| 24405/25880 [4:58:33<16:20,  1.51it/s]
1|24406|Loss: 0.9252731204032898:  94%|█████████▍| 24406/25880 [4:58:33<16:56,  1.45it/s]
1|24407|Loss: 0.6853709816932678:  94%|█████████▍| 24406/25880 [4:58:34<16:56,  1.45it/s]
1|24407|Loss: 0.6853709816932678:  94%|█████████▍| 24407/25880 [4:58:34<17:55,  1.37it/s]
1|24408|Loss: 0.8242976665496826:  94%|█████████▍| 24407/25880 [4:58:34<17:55,  1.37it/s]
1|24408|Loss: 0.8242976665496826:  94%|█████████▍| 24408/25880 [4:58:35<18:00,  1.36it/s]
1|24409|Loss: 0.83864825963974:  94%|█████████▍| 24408/25880 [4:58:35<18:00,  1.36it/s]  
1|24409|Loss: 0.83864825963974:  94%|█████████▍| 24409/25880 [4:58:35<17:26,  1.41it/s]
1|24410|Loss: 0.7914037108421326:  94%|█████████▍| 24409/25880 [4:58:36<17:26,  1.41it/s]
1|24410|Loss: 0.7914037108421326:  94%|█████████▍| 24410/25880 [4:58:36<18:12,  1.35it/s]
1|24411|Loss: 0.8203219771385193:  94%|█████████▍| 24410/25880 [4:58:37<18:12,  1.35it/s]
1|24411|Loss: 0.8203219771385193:  94%|█████████▍| 24411/25880 [4:58:37<16:42,  1.47it/s]
1|24412|Loss: 0.8380876779556274:  94%|█████████▍| 24411/25880 [4:58:37<16:42,  1.47it/s]
1|24412|Loss: 0.8380876779556274:  94%|█████████▍| 24412/25880 [4:58:37<16:41,  1.47it/s]
1|24413|Loss: 0.7639174461364746:  94%|█████████▍| 24412/25880 [4:58:38<16:41,  1.47it/s]
1|24413|Loss: 0.7639174461364746:  94%|█████████▍| 24413/25880 [4:58:38<17:00,  1.44it/s]
1|24414|Loss: 0.8099530339241028:  94%|█████████▍| 24413/25880 [4:58:39<17:00,  1.44it/s]
1|24414|Loss: 0.8099530339241028:  94%|█████████▍| 24414/25880 [4:58:39<16:29,  1.48it/s]
1|24415|Loss: 0.8566811680793762:  94%|█████████▍| 24414/25880 [4:58:39<16:29,  1.48it/s]
1|24415|Loss: 0.8566811680793762:  94%|█████████▍| 24415/25880 [4:58:40<16:42,  1.46it/s]
1|24416|Loss: 1.0238670110702515:  94%|█████████▍| 24415/25880 [4:58:40<16:42,  1.46it/s]
1|24416|Loss: 1.0238670110702515:  94%|█████████▍| 24416/25880 [4:58:40<16:52,  1.45it/s]
1|24417|Loss: 1.0267313718795776:  94%|█████████▍| 24416/25880 [4:58:41<16:52,  1.45it/s]
1|24417|Loss: 1.0267313718795776:  94%|█████████▍| 24417/25880 [4:58:41<16:25,  1.49it/s]
1|24418|Loss: 0.9584276676177979:  94%|█████████▍| 24417/25880 [4:58:41<16:25,  1.49it/s]
1|24418|Loss: 0.9584276676177979:  94%|█████████▍| 24418/25880 [4:58:42<16:29,  1.48it/s]
1|24419|Loss: 0.8924610614776611:  94%|█████████▍| 24418/25880 [4:58:42<16:29,  1.48it/s]
1|24419|Loss: 0.8924610614776611:  94%|█████████▍| 24419/25880 [4:58:42<17:12,  1.41it/s]
1|24420|Loss: 0.8350969552993774:  94%|█████████▍| 24419/25880 [4:58:43<17:12,  1.41it/s]
1|24420|Loss: 0.8350969552993774:  94%|█████████▍| 24420/25880 [4:58:43<17:33,  1.39it/s]
1|24421|Loss: 0.6542747616767883:  94%|█████████▍| 24420/25880 [4:58:43<17:33,  1.39it/s]
1|24421|Loss: 0.6542747616767883:  94%|█████████▍| 24421/25880 [4:58:44<15:23,  1.58it/s]
1|24422|Loss: 0.8502940535545349:  94%|█████████▍| 24421/25880 [4:58:44<15:23,  1.58it/s]
1|24422|Loss: 0.8502940535545349:  94%|█████████▍| 24422/25880 [4:58:44<14:58,  1.62it/s]
1|24423|Loss: 0.8727741837501526:  94%|█████████▍| 24422/25880 [4:58:45<14:58,  1.62it/s]
1|24423|Loss: 0.8727741837501526:  94%|█████████▍| 24423/25880 [4:58:45<16:10,  1.50it/s]
1|24424|Loss: 0.9112687706947327:  94%|█████████▍| 24423/25880 [4:58:45<16:10,  1.50it/s]
1|24424|Loss: 0.9112687706947327:  94%|█████████▍| 24424/25880 [4:58:46<16:49,  1.44it/s]
1|24425|Loss: 0.791816771030426:  94%|█████████▍| 24424/25880 [4:58:46<16:49,  1.44it/s] 
1|24425|Loss: 0.791816771030426:  94%|█████████▍| 24425/25880 [4:58:46<16:35,  1.46it/s]
1|24426|Loss: 0.9691829085350037:  94%|█████████▍| 24425/25880 [4:58:47<16:35,  1.46it/s]
1|24426|Loss: 0.9691829085350037:  94%|█████████▍| 24426/25880 [4:58:47<16:37,  1.46it/s]
1|24427|Loss: 1.0000864267349243:  94%|█████████▍| 24426/25880 [4:58:47<16:37,  1.46it/s]
1|24427|Loss: 1.0000864267349243:  94%|█████████▍| 24427/25880 [4:58:48<16:14,  1.49it/s]
1|24428|Loss: 0.7607589364051819:  94%|█████████▍| 24427/25880 [4:58:48<16:14,  1.49it/s]
1|24428|Loss: 0.7607589364051819:  94%|█████████▍| 24428/25880 [4:58:48<16:37,  1.46it/s]
1|24429|Loss: 1.0280991792678833:  94%|█████████▍| 24428/25880 [4:58:49<16:37,  1.46it/s]
1|24429|Loss: 1.0280991792678833:  94%|█████████▍| 24429/25880 [4:58:49<18:05,  1.34it/s]
1|24430|Loss: 0.8102918267250061:  94%|█████████▍| 24429/25880 [4:58:50<18:05,  1.34it/s]
1|24430|Loss: 0.8102918267250061:  94%|█████████▍| 24430/25880 [4:58:50<18:02,  1.34it/s]
1|24431|Loss: 0.8385821580886841:  94%|█████████▍| 24430/25880 [4:58:50<18:02,  1.34it/s]
1|24431|Loss: 0.8385821580886841:  94%|█████████▍| 24431/25880 [4:58:51<16:59,  1.42it/s]
1|24432|Loss: 0.8811570405960083:  94%|█████████▍| 24431/25880 [4:58:51<16:59,  1.42it/s]
1|24432|Loss: 0.8811570405960083:  94%|█████████▍| 24432/25880 [4:58:51<16:07,  1.50it/s]
1|24433|Loss: 0.799076497554779:  94%|█████████▍| 24432/25880 [4:58:52<16:07,  1.50it/s] 
1|24433|Loss: 0.799076497554779:  94%|█████████▍| 24433/25880 [4:58:52<15:34,  1.55it/s]
1|24434|Loss: 0.9258908033370972:  94%|█████████▍| 24433/25880 [4:58:52<15:34,  1.55it/s]
1|24434|Loss: 0.9258908033370972:  94%|█████████▍| 24434/25880 [4:58:52<16:03,  1.50it/s]
1|24435|Loss: 0.9474353790283203:  94%|█████████▍| 24434/25880 [4:58:53<16:03,  1.50it/s]
1|24435|Loss: 0.9474353790283203:  94%|█████████▍| 24435/25880 [4:58:53<17:20,  1.39it/s]
1|24436|Loss: 0.8934262990951538:  94%|█████████▍| 24435/25880 [4:58:54<17:20,  1.39it/s]
1|24436|Loss: 0.8934262990951538:  94%|█████████▍| 24436/25880 [4:58:54<17:40,  1.36it/s]
1|24437|Loss: 0.9495067000389099:  94%|█████████▍| 24436/25880 [4:58:54<17:40,  1.36it/s]
1|24437|Loss: 0.9495067000389099:  94%|█████████▍| 24437/25880 [4:58:55<16:43,  1.44it/s]
1|24438|Loss: 0.8040148615837097:  94%|█████████▍| 24437/25880 [4:58:55<16:43,  1.44it/s]
1|24438|Loss: 0.8040148615837097:  94%|█████████▍| 24438/25880 [4:58:55<16:36,  1.45it/s]
1|24439|Loss: 0.8755410313606262:  94%|█████████▍| 24438/25880 [4:58:56<16:36,  1.45it/s]
1|24439|Loss: 0.8755410313606262:  94%|█████████▍| 24439/25880 [4:58:56<16:56,  1.42it/s]
1|24440|Loss: 0.8100976347923279:  94%|█████████▍| 24439/25880 [4:58:56<16:56,  1.42it/s]
1|24440|Loss: 0.8100976347923279:  94%|█████████▍| 24440/25880 [4:58:57<16:18,  1.47it/s]
1|24441|Loss: 0.8286203742027283:  94%|█████████▍| 24440/25880 [4:58:57<16:18,  1.47it/s]
1|24441|Loss: 0.8286203742027283:  94%|█████████▍| 24441/25880 [4:58:58<17:05,  1.40it/s]
1|24442|Loss: 1.0366363525390625:  94%|█████████▍| 24441/25880 [4:58:58<17:05,  1.40it/s]
1|24442|Loss: 1.0366363525390625:  94%|█████████▍| 24442/25880 [4:58:58<17:55,  1.34it/s]
1|24443|Loss: 0.8630212545394897:  94%|█████████▍| 24442/25880 [4:58:59<17:55,  1.34it/s]
1|24443|Loss: 0.8630212545394897:  94%|█████████▍| 24443/25880 [4:58:59<18:36,  1.29it/s]
1|24444|Loss: 0.7267230749130249:  94%|█████████▍| 24443/25880 [4:59:00<18:36,  1.29it/s]
1|24444|Loss: 0.7267230749130249:  94%|█████████▍| 24444/25880 [4:59:00<18:29,  1.29it/s]
1|24445|Loss: 0.9518048763275146:  94%|█████████▍| 24444/25880 [4:59:00<18:29,  1.29it/s]
1|24445|Loss: 0.9518048763275146:  94%|█████████▍| 24445/25880 [4:59:01<18:20,  1.30it/s]
1|24446|Loss: 0.8584629893302917:  94%|█████████▍| 24445/25880 [4:59:01<18:20,  1.30it/s]
1|24446|Loss: 0.8584629893302917:  94%|█████████▍| 24446/25880 [4:59:01<17:01,  1.40it/s]
1|24447|Loss: 0.8205762505531311:  94%|█��███████▍| 24446/25880 [4:59:02<17:01,  1.40it/s]
1|24447|Loss: 0.8205762505531311:  94%|█████████▍| 24447/25880 [4:59:02<15:36,  1.53it/s]
1|24448|Loss: 0.9536694884300232:  94%|█████████▍| 24447/25880 [4:59:02<15:36,  1.53it/s]
1|24448|Loss: 0.9536694884300232:  94%|█████████▍| 24448/25880 [4:59:03<15:48,  1.51it/s]
1|24449|Loss: 0.7371924519538879:  94%|█████████▍| 24448/25880 [4:59:03<15:48,  1.51it/s]
1|24449|Loss: 0.7371924519538879:  94%|█████████▍| 24449/25880 [4:59:03<17:01,  1.40it/s]
1|24450|Loss: 0.735226571559906:  94%|█████████▍| 24449/25880 [4:59:04<17:01,  1.40it/s] 
1|24450|Loss: 0.735226571559906:  94%|█████████▍| 24450/25880 [4:59:04<18:14,  1.31it/s]
1|24451|Loss: 0.8065682053565979:  94%|█████████▍| 24450/25880 [4:59:05<18:14,  1.31it/s]
1|24451|Loss: 0.8065682053565979:  94%|█████████▍| 24451/25880 [4:59:05<18:13,  1.31it/s]
1|24452|Loss: 0.841926097869873:  94%|█████████▍| 24451/25880 [4:59:05<18:13,  1.31it/s] 
1|24452|Loss: 0.841926097869873:  94%|█████████▍| 24452/25880 [4:59:06<18:21,  1.30it/s]
1|24453|Loss: 0.8112689852714539:  94%|█████████▍| 24452/25880 [4:59:06<18:21,  1.30it/s]
1|24453|Loss: 0.8112689852714539:  94%|█████████▍| 24453/25880 [4:59:07<19:42,  1.21it/s]
1|24454|Loss: 0.6890974640846252:  94%|█████████▍| 24453/25880 [4:59:07<19:42,  1.21it/s]
1|24454|Loss: 0.6890974640846252:  94%|█████████▍| 24454/25880 [4:59:08<20:14,  1.17it/s]
1|24455|Loss: 0.8267282247543335:  94%|█████████▍| 24454/25880 [4:59:08<20:14,  1.17it/s]
1|24455|Loss: 0.8267282247543335:  94%|█████████▍| 24455/25880 [4:59:08<19:32,  1.22it/s]
1|24456|Loss: 0.840700089931488:  94%|█████████▍| 24455/25880 [4:59:09<19:32,  1.22it/s] 
1|24456|Loss: 0.840700089931488:  94%|█████████▍| 24456/25880 [4:59:09<19:24,  1.22it/s]
1|24457|Loss: 0.7529137134552002:  94%|█████████▍| 24456/25880 [4:59:10<19:24,  1.22it/s]
1|24457|Loss: 0.7529137134552002:  95%|█████████▍| 24457/25880 [4:59:10<18:03,  1.31it/s]
1|24458|Loss: 0.8890992403030396:  95%|█████████▍| 24457/25880 [4:59:10<18:03,  1.31it/s]
1|24458|Loss: 0.8890992403030396:  95%|█████████▍| 24458/25880 [4:59:11<17:36,  1.35it/s]
1|24459|Loss: 0.8690425157546997:  95%|█████████▍| 24458/25880 [4:59:11<17:36,  1.35it/s]
1|24459|Loss: 0.8690425157546997:  95%|█████████▍| 24459/25880 [4:59:11<17:29,  1.35it/s]
1|24460|Loss: 0.9970189332962036:  95%|█████████▍| 24459/25880 [4:59:12<17:29,  1.35it/s]
1|24460|Loss: 0.9970189332962036:  95%|█████████▍| 24460/25880 [4:59:12<17:26,  1.36it/s]
1|24461|Loss: 0.8180381059646606:  95%|█████████▍| 24460/25880 [4:59:12<17:26,  1.36it/s]
1|24461|Loss: 0.8180381059646606:  95%|█████████▍| 24461/25880 [4:59:13<17:28,  1.35it/s]
1|24462|Loss: 0.9694530367851257:  95%|█████████▍| 24461/25880 [4:59:13<17:28,  1.35it/s]
1|24462|Loss: 0.9694530367851257:  95%|█████████▍| 24462/25880 [4:59:13<17:18,  1.37it/s]
1|24463|Loss: 0.85442054271698:  95%|█████████▍| 24462/25880 [4:59:14<17:18,  1.37it/s]  
1|24463|Loss: 0.85442054271698:  95%|█████████▍| 24463/25880 [4:59:14<17:50,  1.32it/s]
1|24464|Loss: 0.828673243522644:  95%|█████████▍| 24463/25880 [4:59:15<17:50,  1.32it/s]
1|24464|Loss: 0.828673243522644:  95%|█████████▍| 24464/25880 [4:59:15<18:34,  1.27it/s]
1|24465|Loss: 0.9921987056732178:  95%|█████████▍| 24464/25880 [4:59:16<18:34,  1.27it/s]
1|24465|Loss: 0.9921987056732178:  95%|█████████▍| 24465/25880 [4:59:16<17:44,  1.33it/s]
1|24466|Loss: 0.8193697929382324:  95%|█████████▍| 24465/25880 [4:59:16<17:44,  1.33it/s]
1|24466|Loss: 0.8193697929382324:  95%|█████████▍| 24466/25880 [4:59:17<17:50,  1.32it/s]
1|24467|Loss: 0.6088671684265137:  95%|█████████▍| 24466/25880 [4:59:17<17:50,  1.32it/s]
1|24467|Loss: 0.6088671684265137:  95%|█████████▍| 24467/25880 [4:59:17<18:24,  1.28it/s]
1|24468|Loss: 0.8698861002922058:  95%|█████████▍| 24467/25880 [4:59:18<18:24,  1.28it/s]
1|24468|Loss: 0.8698861002922058:  95%|█████████▍| 24468/25880 [4:59:18<17:33,  1.34it/s]
1|24469|Loss: 0.8046819567680359:  95%|█████████▍| 24468/25880 [4:59:18<17:33,  1.34it/s]
1|24469|Loss: 0.8046819567680359:  95%|█████████▍| 24469/25880 [4:59:19<16:46,  1.40it/s]
1|24470|Loss: 0.8021657466888428:  95%|█████████▍| 24469/25880 [4:59:19<16:46,  1.40it/s]
1|24470|Loss: 0.8021657466888428:  95%|█████████▍| 24470/25880 [4:59:19<15:23,  1.53it/s]
1|24471|Loss: 0.874192476272583:  95%|█████████▍| 24470/25880 [4:59:20<15:23,  1.53it/s] 
1|24471|Loss: 0.874192476272583:  95%|█████████▍| 24471/25880 [4:59:20<14:09,  1.66it/s]
1|24472|Loss: 0.824374258518219:  95%|█████████▍| 24471/25880 [4:59:20<14:09,  1.66it/s]
1|24472|Loss: 0.824374258518219:  95%|█████████▍| 24472/25880 [4:59:20<15:00,  1.56it/s]
1|24473|Loss: 0.7465049624443054:  95%|█████████▍| 24472/25880 [4:59:21<15:00,  1.56it/s]
1|24473|Loss: 0.7465049624443054:  95%|█████████▍| 24473/25880 [4:59:21<15:12,  1.54it/s]
1|24474|Loss: 0.8946043848991394:  95%|█████████▍| 24473/25880 [4:59:22<15:12,  1.54it/s]
1|24474|Loss: 0.8946043848991394:  95%|█████████▍| 24474/25880 [4:59:22<15:59,  1.47it/s]
1|24475|Loss: 0.7863634824752808:  95%|█████████▍| 24474/25880 [4:59:22<15:59,  1.47it/s]
1|24475|Loss: 0.7863634824752808:  95%|█████████▍| 24475/25880 [4:59:23<15:56,  1.47it/s]
1|24476|Loss: 0.8618168830871582:  95%|█████████▍| 24475/25880 [4:59:23<15:56,  1.47it/s]
1|24476|Loss: 0.8618168830871582:  95%|█████████▍| 24476/25880 [4:59:23<16:01,  1.46it/s]
1|24477|Loss: 0.799684464931488:  95%|█████████▍| 24476/25880 [4:59:24<16:01,  1.46it/s] 
1|24477|Loss: 0.799684464931488:  95%|█████████▍| 24477/25880 [4:59:24<16:06,  1.45it/s]
1|24478|Loss: 0.8046454191207886:  95%|█████████▍| 24477/25880 [4:59:24<16:06,  1.45it/s]
1|24478|Loss: 0.8046454191207886:  95%|█████████▍| 24478/25880 [4:59:25<15:51,  1.47it/s]
1|24479|Loss: 0.9390037655830383:  95%|█████████▍| 24478/25880 [4:59:25<15:51,  1.47it/s]
1|24479|Loss: 0.9390037655830383:  95%|█████████▍| 24479/25880 [4:59:25<16:56,  1.38it/s]
1|24480|Loss: 0.817549467086792:  95%|█████████▍| 24479/25880 [4:59:26<16:56,  1.38it/s] 
1|24480|Loss: 0.817549467086792:  95%|█████████▍| 24480/25880 [4:59:26<17:47,  1.31it/s]
1|24481|Loss: 0.7692680954933167:  95%|█████████▍| 24480/25880 [4:59:27<17:47,  1.31it/s]
1|24481|Loss: 0.7692680954933167:  95%|█████████▍| 24481/25880 [4:59:27<17:35,  1.33it/s]
1|24482|Loss: 0.8898370862007141:  95%|█████████▍| 24481/25880 [4:59:27<17:35,  1.33it/s]
1|24482|Loss: 0.8898370862007141:  95%|█████████▍| 24482/25880 [4:59:28<17:53,  1.30it/s]
1|24483|Loss: 0.8854362964630127:  95%|█████████▍| 24482/25880 [4:59:28<17:53,  1.30it/s]
1|24483|Loss: 0.8854362964630127:  95%|█████████▍| 24483/25880 [4:59:28<16:39,  1.40it/s]
1|24484|Loss: 0.8449323177337646:  95%|█████████▍| 24483/25880 [4:59:29<16:39,  1.40it/s]
1|24484|Loss: 0.8449323177337646:  95%|█████████▍| 24484/25880 [4:59:29<15:58,  1.46it/s]
1|24485|Loss: 0.7995544672012329:  95%|█████████▍| 24484/25880 [4:59:29<15:58,  1.46it/s]
1|24485|Loss: 0.7995544672012329:  95%|█████████▍| 24485/25880 [4:59:30<16:15,  1.43it/s]
1|24486|Loss: 0.8589031100273132:  95%|█████████▍| 24485/25880 [4:59:30<16:15,  1.43it/s]
1|24486|Loss: 0.8589031100273132:  95%|█████████▍| 24486/25880 [4:59:30<16:19,  1.42it/s]
1|24487|Loss: 0.7198486924171448:  95%|█████████▍| 24486/25880 [4:59:31<16:19,  1.42it/s]
1|24487|Loss: 0.7198486924171448:  95%|█████████▍| 24487/25880 [4:59:31<16:30,  1.41it/s]
1|24488|Loss: 0.8655796051025391:  95%|█████████▍| 24487/25880 [4:59:32<16:30,  1.41it/s]
1|24488|Loss: 0.8655796051025391:  95%|█████████▍| 24488/25880 [4:59:32<15:50,  1.46it/s]
1|24489|Loss: 0.7663524746894836:  95%|█████████▍| 24488/25880 [4:59:32<15:50,  1.46it/s]
1|24489|Loss: 0.7663524746894836:  95%|█████████▍| 24489/25880 [4:59:32<15:47,  1.47it/s]
1|24490|Loss: 0.7896143794059753:  95%|█████████▍| 24489/25880 [4:59:33<15:47,  1.47it/s]
1|24490|Loss: 0.7896143794059753:  95%|█████████▍| 24490/25880 [4:59:33<16:09,  1.43it/s]
1|24491|Loss: 0.8002113103866577:  95%|█████████▍| 24490/25880 [4:59:34<16:09,  1.43it/s]
1|24491|Loss: 0.8002113103866577:  95%|█████████▍| 24491/25880 [4:59:34<16:29,  1.40it/s]
1|24492|Loss: 0.8359624743461609:  95%|█████████▍| 24491/25880 [4:59:34<16:29,  1.40it/s]
1|24492|Loss: 0.8359624743461609:  95%|█████████▍| 24492/25880 [4:59:35<15:48,  1.46it/s]
1|24493|Loss: 0.9182811975479126:  95%|█████████▍| 24492/25880 [4:59:35<15:48,  1.46it/s]
1|24493|Loss: 0.9182811975479126:  95%|█████████▍| 24493/25880 [4:59:35<16:32,  1.40it/s]
1|24494|Loss: 0.8436402678489685:  95%|█████████▍| 24493/25880 [4:59:36<16:32,  1.40it/s]
1|24494|Loss: 0.8436402678489685:  95%|█████████▍| 24494/25880 [4:59:36<16:11,  1.43it/s]
1|24495|Loss: 0.8405890464782715:  95%|█████████▍| 24494/25880 [4:59:36<16:11,  1.43it/s]
1|24495|Loss: 0.8405890464782715:  95%|█████████▍| 24495/25880 [4:59:37<16:34,  1.39it/s]
1|24496|Loss: 0.8106501698493958:  95%|█████████▍| 24495/25880 [4:59:37<16:34,  1.39it/s]
1|24496|Loss: 0.8106501698493958:  95%|█████████▍| 24496/25880 [4:59:37<16:17,  1.42it/s]
1|24497|Loss: 0.9433931112289429:  95%|█████████▍| 24496/25880 [4:59:38<16:17,  1.42it/s]
1|24497|Loss: 0.9433931112289429:  95%|█████████▍| 24497/25880 [4:59:38<17:09,  1.34it/s]
1|24498|Loss: 0.8148233890533447:  95%|█████████▍| 24497/25880 [4:59:39<17:09,  1.34it/s]
1|24498|Loss: 0.8148233890533447:  95%|█████████▍| 24498/25880 [4:59:39<17:05,  1.35it/s]
1|24499|Loss: 0.9426191449165344:  95%|█████████▍| 24498/25880 [4:59:39<17:05,  1.35it/s]
1|24499|Loss: 0.9426191449165344:  95%|█████████▍| 24499/25880 [4:59:40<16:16,  1.41it/s]
1|24500|Loss: 0.6883856654167175:  95%|█████████▍| 24499/25880 [4:59:40<16:16,  1.41it/s]
1|24500|Loss: 0.6883856654167175:  95%|█████████▍| 24500/25880 [4:59:40<16:15,  1.42it/s]
1|24501|Loss: 0.8164198994636536:  95%|█████████▍| 24500/25880 [4:59:41<16:15,  1.42it/s]
1|24501|Loss: 0.8164198994636536:  95%|█████████▍| 24501/25880 [4:59:41<15:44,  1.46it/s]
1|24502|Loss: 0.8029158115386963:  95%|█████████▍| 24501/25880 [4:59:41<15:44,  1.46it/s]
1|24502|Loss: 0.8029158115386963:  95%|█████████▍| 24502/25880 [4:59:42<15:15,  1.50it/s]
1|24503|Loss: 0.9333917498588562:  95%|█████████▍| 24502/25880 [4:59:42<15:15,  1.50it/s]
1|24503|Loss: 0.9333917498588562:  95%|█████████▍| 24503/25880 [4:59:42<14:45,  1.55it/s]
1|24504|Loss: 0.8028045892715454:  95%|█████████▍| 24503/25880 [4:59:43<14:45,  1.55it/s]
1|24504|Loss: 0.8028045892715454:  95%|█████████▍| 24504/25880 [4:59:43<15:32,  1.48it/s]
1|24505|Loss: 0.8206589221954346:  95%|█████████▍| 24504/25880 [4:59:43<15:32,  1.48it/s]
1|24505|Loss: 0.8206589221954346:  95%|█████████▍| 24505/25880 [4:59:44<15:57,  1.44it/s]
1|24506|Loss: 0.7547868490219116:  95%|█████████▍| 24505/25880 [4:59:44<15:57,  1.44it/s]
1|24506|Loss: 0.7547868490219116:  95%|█████████▍| 24506/25880 [4:59:44<15:40,  1.46it/s]
1|24507|Loss: 0.8729864358901978:  95%|█████████▍| 24506/25880 [4:59:45<15:40,  1.46it/s]
1|24507|Loss: 0.8729864358901978:  95%|█████████▍| 24507/25880 [4:59:45<15:05,  1.52it/s]
1|24508|Loss: 0.8383899927139282:  95%|█████████▍| 24507/25880 [4:59:45<15:05,  1.52it/s]
1|24508|Loss: 0.8383899927139282:  95%|█████████▍| 24508/25880 [4:59:46<16:25,  1.39it/s]
1|24509|Loss: 0.8451526165008545:  95%|█████████▍| 24508/25880 [4:59:46<16:25,  1.39it/s]
1|24509|Loss: 0.8451526165008545:  95%|█████████▍| 24509/25880 [4:59:47<16:49,  1.36it/s]
1|24510|Loss: 0.7491498589515686:  95%|█████████▍| 24509/25880 [4:59:47<16:49,  1.36it/s]
1|24510|Loss: 0.7491498589515686:  95%|█████████▍| 24510/25880 [4:59:47<16:54,  1.35it/s]
1|24511|Loss: 0.7591685056686401:  95%|█████████▍| 24510/25880 [4:59:48<16:54,  1.35it/s]
1|24511|Loss: 0.7591685056686401:  95%|█████████▍| 24511/25880 [4:59:48<15:45,  1.45it/s]
1|24512|Loss: 0.8877876996994019:  95%|█████████▍| 24511/25880 [4:59:48<15:45,  1.45it/s]
1|24512|Loss: 0.8877876996994019:  95%|█████████▍| 24512/25880 [4:59:49<15:33,  1.47it/s]
1|24513|Loss: 0.8207690715789795:  95%|█████████▍| 24512/25880 [4:59:49<15:33,  1.47it/s]
1|24513|Loss: 0.8207690715789795:  95%|█████████▍| 24513/25880 [4:59:49<15:00,  1.52it/s]
1|24514|Loss: 0.8708353042602539:  95%|█████████▍| 24513/25880 [4:59:50<15:00,  1.52it/s]
1|24514|Loss: 0.8708353042602539:  95%|█████████▍| 24514/25880 [4:59:50<15:19,  1.49it/s]
1|24515|Loss: 0.7590872049331665:  95%|█████████▍| 24514/25880 [4:59:50<15:19,  1.49it/s]
1|24515|Loss: 0.7590872049331665:  95%|█████████▍| 24515/25880 [4:59:50<14:33,  1.56it/s]
1|24516|Loss: 0.5905530452728271:  95%|█████████▍| 24515/25880 [4:59:51<14:33,  1.56it/s]
1|24516|Loss: 0.5905530452728271:  95%|█████████▍| 24516/25880 [4:59:51<16:15,  1.40it/s]
1|24517|Loss: 0.7732561826705933:  95%|█████████▍| 24516/25880 [4:59:52<16:15,  1.40it/s]
1|24517|Loss: 0.7732561826705933:  95%|█████████▍| 24517/25880 [4:59:52<17:22,  1.31it/s]
1|24518|Loss: 0.7859196066856384:  95%|█████████▍| 24517/25880 [4:59:53<17:22,  1.31it/s]
1|24518|Loss: 0.7859196066856384:  95%|█████████▍| 24518/25880 [4:59:53<17:14,  1.32it/s]
1|24519|Loss: 0.9063444137573242:  95%|█████████▍| 24518/25880 [4:59:53<17:14,  1.32it/s]
1|24519|Loss: 0.9063444137573242:  95%|█████████▍| 24519/25880 [4:59:54<17:03,  1.33it/s]
1|24520|Loss: 0.8793647289276123:  95%|█████████▍| 24519/25880 [4:59:54<17:03,  1.33it/s]
1|24520|Loss: 0.8793647289276123:  95%|█████████▍| 24520/25880 [4:59:54<16:20,  1.39it/s]
1|24521|Loss: 0.766340434551239:  95%|█████████▍| 24520/25880 [4:59:55<16:20,  1.39it/s] 
1|24521|Loss: 0.766340434551239:  95%|█████████▍| 24521/25880 [4:59:55<16:49,  1.35it/s]
1|24522|Loss: 1.044681429862976:  95%|█████████▍| 24521/25880 [4:59:56<16:49,  1.35it/s]
1|24522|Loss: 1.044681429862976:  95%|█████████▍| 24522/25880 [4:59:56<16:44,  1.35it/s]
1|24523|Loss: 0.8718050122261047:  95%|█████████▍| 24522/25880 [4:59:56<16:44,  1.35it/s]
1|24523|Loss: 0.8718050122261047:  95%|█████████▍| 24523/25880 [4:59:56<15:39,  1.44it/s]
1|24524|Loss: 0.8304693698883057:  95%|█████████▍| 24523/25880 [4:59:57<15:39,  1.44it/s]
1|24524|Loss: 0.8304693698883057:  95%|█████████▍| 24524/25880 [4:59:57<16:20,  1.38it/s]
1|24525|Loss: 0.7940319776535034:  95%|█████████▍| 24524/25880 [4:59:58<16:20,  1.38it/s]
1|24525|Loss: 0.7940319776535034:  95%|█████████▍| 24525/25880 [4:59:58<17:02,  1.33it/s]
1|24526|Loss: 0.75379878282547:  95%|█████████▍| 24525/25880 [4:59:58<17:02,  1.33it/s]  
1|24526|Loss: 0.75379878282547:  95%|█████████▍| 24526/25880 [4:59:59<16:00,  1.41it/s]
1|24527|Loss: 0.8582955002784729:  95%|█████████▍| 24526/25880 [4:59:59<16:00,  1.41it/s]
1|24527|Loss: 0.8582955002784729:  95%|█████████▍| 24527/25880 [4:59:59<16:17,  1.38it/s]
1|24528|Loss: 0.7148284316062927:  95%|█████████▍| 24527/25880 [5:00:00<16:17,  1.38it/s]
1|24528|Loss: 0.7148284316062927:  95%|█████████▍| 24528/25880 [5:00:00<17:01,  1.32it/s]
1|24529|Loss: 0.6919490098953247:  95%|█████████▍| 24528/25880 [5:00:01<17:01,  1.32it/s]
1|24529|Loss: 0.6919490098953247:  95%|█████████▍| 24529/25880 [5:00:01<16:24,  1.37it/s]
1|24530|Loss: 0.8609907031059265:  95%|█████████▍| 24529/25880 [5:00:01<16:24,  1.37it/s]
1|24530|Loss: 0.8609907031059265:  95%|█████████▍| 24530/25880 [5:00:02<15:47,  1.43it/s]
1|24531|Loss: 0.813289999961853:  95%|█████████▍| 24530/25880 [5:00:02<15:47,  1.43it/s] 
1|24531|Loss: 0.813289999961853:  95%|█████████▍| 24531/25880 [5:00:02<15:53,  1.42it/s]
1|24532|Loss: 0.7349120378494263:  95%|█████████▍| 24531/25880 [5:00:03<15:53,  1.42it/s]
1|24532|Loss: 0.7349120378494263:  95%|█████████▍| 24532/25880 [5:00:03<16:23,  1.37it/s]
1|24533|Loss: 0.7705331444740295:  95%|█████████▍| 24532/25880 [5:00:04<16:23,  1.37it/s]
1|24533|Loss: 0.7705331444740295:  95%|█████████▍| 24533/25880 [5:00:04<16:27,  1.36it/s]
1|24534|Loss: 0.760728120803833:  95%|█████████▍| 24533/25880 [5:00:04<16:27,  1.36it/s] 
1|24534|Loss: 0.760728120803833:  95%|█████████▍| 24534/25880 [5:00:05<16:49,  1.33it/s]
1|24535|Loss: 0.9974046945571899:  95%|█████████▍| 24534/25880 [5:00:05<16:49,  1.33it/s]
1|24535|Loss: 0.9974046945571899:  95%|█████████▍| 24535/25880 [5:00:05<16:36,  1.35it/s]
1|24536|Loss: 0.6803275942802429:  95%|█████████▍| 24535/25880 [5:00:06<16:36,  1.35it/s]
1|24536|Loss: 0.6803275942802429:  95%|█████████▍| 24536/25880 [5:00:06<17:06,  1.31it/s]
1|24537|Loss: 0.7410205602645874:  95%|█████████▍| 24536/25880 [5:00:07<17:06,  1.31it/s]
1|24537|Loss: 0.7410205602645874:  95%|█████████▍| 24537/25880 [5:00:07<16:33,  1.35it/s]
1|24538|Loss: 0.9103599786758423:  95%|█████████▍| 24537/25880 [5:00:07<16:33,  1.35it/s]
1|24538|Loss: 0.9103599786758423:  95%|█████████▍| 24538/25880 [5:00:08<16:40,  1.34it/s]
1|24539|Loss: 0.9194234609603882:  95%|█████████▍| 24538/25880 [5:00:08<16:40,  1.34it/s]
1|24539|Loss: 0.9194234609603882:  95%|█████████▍| 24539/25880 [5:00:08<15:42,  1.42it/s]
1|24540|Loss: 0.768105149269104:  95%|█████████▍| 24539/25880 [5:00:09<15:42,  1.42it/s] 
1|24540|Loss: 0.768105149269104:  95%|█████████▍| 24540/25880 [5:00:09<15:08,  1.47it/s]
1|24541|Loss: 0.7050411701202393:  95%|█████████▍| 24540/25880 [5:00:09<15:08,  1.47it/s]
1|24541|Loss: 0.7050411701202393:  95%|█████████▍| 24541/25880 [5:00:10<15:51,  1.41it/s]
1|24542|Loss: 0.7482953071594238:  95%|█████████▍| 24541/25880 [5:00:10<15:51,  1.41it/s]
1|24542|Loss: 0.7482953071594238:  95%|█████████▍| 24542/25880 [5:00:10<15:28,  1.44it/s]
1|24543|Loss: 0.6488702297210693:  95%|█████████▍| 24542/25880 [5:00:11<15:28,  1.44it/s]
1|24543|Loss: 0.6488702297210693:  95%|█████████▍| 24543/25880 [5:00:11<16:35,  1.34it/s]
1|24544|Loss: 0.7902638912200928:  95%|█████████▍| 24543/25880 [5:00:12<16:35,  1.34it/s]
1|24544|Loss: 0.7902638912200928:  95%|█████████▍| 24544/25880 [5:00:12<16:15,  1.37it/s]
1|24545|Loss: 0.8892176747322083:  95%|█████████▍| 24544/25880 [5:00:12<16:15,  1.37it/s]
1|24545|Loss: 0.8892176747322083:  95%|█████████▍| 24545/25880 [5:00:12<15:29,  1.44it/s]
1|24546|Loss: 0.8310976624488831:  95%|█████████▍| 24545/25880 [5:00:13<15:29,  1.44it/s]
1|24546|Loss: 0.8310976624488831:  95%|█████████▍| 24546/25880 [5:00:13<14:54,  1.49it/s]
1|24547|Loss: 0.8345223665237427:  95%|█████████▍| 24546/25880 [5:00:13<14:54,  1.49it/s]
1|24547|Loss: 0.8345223665237427:  95%|█████████▍| 24547/25880 [5:00:14<14:32,  1.53it/s]
1|24548|Loss: 0.8070816397666931:  95%|█████████▍| 24547/25880 [5:00:14<14:32,  1.53it/s]
1|24548|Loss: 0.8070816397666931:  95%|█████████▍| 24548/25880 [5:00:14<15:12,  1.46it/s]
1|24549|Loss: 0.7930577993392944:  95%|█████████▍| 24548/25880 [5:00:15<15:12,  1.46it/s]
1|24549|Loss: 0.7930577993392944:  95%|█████████▍| 24549/25880 [5:00:15<15:40,  1.42it/s]
1|24550|Loss: 0.7833805084228516:  95%|█████████▍| 24549/25880 [5:00:16<15:40,  1.42it/s]
1|24550|Loss: 0.7833805084228516:  95%|█████████▍| 24550/25880 [5:00:16<15:59,  1.39it/s]
1|24551|Loss: 0.798853874206543:  95%|█████████▍| 24550/25880 [5:00:16<15:59,  1.39it/s] 
1|24551|Loss: 0.798853874206543:  95%|█████████▍| 24551/25880 [5:00:17<16:29,  1.34it/s]
1|24552|Loss: 0.8090368509292603:  95%|█████████▍| 24551/25880 [5:00:17<16:29,  1.34it/s]
1|24552|Loss: 0.8090368509292603:  95%|█████████▍| 24552/25880 [5:00:17<15:46,  1.40it/s]
1|24553|Loss: 0.826959490776062:  95%|█████████▍| 24552/25880 [5:00:18<15:46,  1.40it/s] 
1|24553|Loss: 0.826959490776062:  95%|█████████▍| 24553/25880 [5:00:18<15:12,  1.46it/s]
1|24554|Loss: 0.8848149180412292:  95%|█████████▍| 24553/25880 [5:00:18<15:12,  1.46it/s]
1|24554|Loss: 0.8848149180412292:  95%|█████████▍| 24554/25880 [5:00:19<15:45,  1.40it/s]
1|24555|Loss: 0.8966239094734192:  95%|█████████▍| 24554/25880 [5:00:19<15:45,  1.40it/s]
1|24555|Loss: 0.8966239094734192:  95%|█████████▍| 24555/25880 [5:00:20<16:00,  1.38it/s]
1|24556|Loss: 0.861464262008667:  95%|█████████▍| 24555/25880 [5:00:20<16:00,  1.38it/s] 
1|24556|Loss: 0.861464262008667:  95%|█████████▍| 24556/25880 [5:00:20<16:07,  1.37it/s]
1|24557|Loss: 0.7603156566619873:  95%|█████████▍| 24556/25880 [5:00:21<16:07,  1.37it/s]
1|24557|Loss: 0.7603156566619873:  95%|█████████▍| 24557/25880 [5:00:21<17:09,  1.29it/s]
1|24558|Loss: 0.8474677801132202:  95%|█████████▍| 24557/25880 [5:00:22<17:09,  1.29it/s]
1|24558|Loss: 0.8474677801132202:  95%|█████████▍| 24558/25880 [5:00:22<17:43,  1.24it/s]
1|24559|Loss: 0.7289618253707886:  95%|█████████▍| 24558/25880 [5:00:22<17:43,  1.24it/s]
1|24559|Loss: 0.7289618253707886:  95%|█████████▍| 24559/25880 [5:00:23<16:57,  1.30it/s]
1|24560|Loss: 0.849742591381073:  95%|█████████▍| 24559/25880 [5:00:23<16:57,  1.30it/s] 
1|24560|Loss: 0.849742591381073:  95%|█████████▍| 24560/25880 [5:00:23<15:46,  1.39it/s]
1|24561|Loss: 0.8145192861557007:  95%|█████████▍| 24560/25880 [5:00:24<15:46,  1.39it/s]
1|24561|Loss: 0.8145192861557007:  95%|█████████▍| 24561/25880 [5:00:24<15:40,  1.40it/s]
1|24562|Loss: 0.8186083436012268:  95%|█████████▍| 24561/25880 [5:00:24<15:40,  1.40it/s]
1|24562|Loss: 0.8186083436012268:  95%|█████████▍| 24562/25880 [5:00:25<15:05,  1.46it/s]
1|24563|Loss: 0.8315678834915161:  95%|█████████▍| 24562/25880 [5:00:25<15:05,  1.46it/s]
1|24563|Loss: 0.8315678834915161:  95%|█████████▍| 24563/25880 [5:00:25<15:10,  1.45it/s]
1|24564|Loss: 0.8520568609237671:  95%|█████████▍| 24563/25880 [5:00:26<15:10,  1.45it/s]
1|24564|Loss: 0.8520568609237671:  95%|█████████▍| 24564/25880 [5:00:26<15:19,  1.43it/s]
1|24565|Loss: 0.888795793056488:  95%|█████████▍| 24564/25880 [5:00:26<15:19,  1.43it/s] 
1|24565|Loss: 0.888795793056488:  95%|█████████▍| 24565/25880 [5:00:27<15:19,  1.43it/s]
1|24566|Loss: 0.9285403490066528:  95%|█████████▍| 24565/25880 [5:00:27<15:19,  1.43it/s]
1|24566|Loss: 0.9285403490066528:  95%|█████████▍| 24566/25880 [5:00:27<15:17,  1.43it/s]
1|24567|Loss: 0.9745650887489319:  95%|█████████▍| 24566/25880 [5:00:28<15:17,  1.43it/s]
1|24567|Loss: 0.9745650887489319:  95%|█████████▍| 24567/25880 [5:00:28<15:17,  1.43it/s]
1|24568|Loss: 0.7762923836708069:  95%|█████████▍| 24567/25880 [5:00:29<15:17,  1.43it/s]
1|24568|Loss: 0.7762923836708069:  95%|█████████▍| 24568/25880 [5:00:29<16:00,  1.37it/s]
1|24569|Loss: 0.7337256669998169:  95%|█████████▍| 24568/25880 [5:00:29<16:00,  1.37it/s]
1|24569|Loss: 0.7337256669998169:  95%|█████████▍| 24569/25880 [5:00:30<15:23,  1.42it/s]
1|24570|Loss: 0.7780051827430725:  95%|█████████▍| 24569/25880 [5:00:30<15:23,  1.42it/s]
1|24570|Loss: 0.7780051827430725:  95%|█████████▍| 24570/25880 [5:00:30<16:01,  1.36it/s]
1|24571|Loss: 0.7483454942703247:  95%|█████████▍| 24570/25880 [5:00:31<16:01,  1.36it/s]
1|24571|Loss: 0.7483454942703247:  95%|█████████▍| 24571/25880 [5:00:31<16:12,  1.35it/s]
1|24572|Loss: 0.8476219773292542:  95%|█████████▍| 24571/25880 [5:00:32<16:12,  1.35it/s]
1|24572|Loss: 0.8476219773292542:  95%|█████████▍| 24572/25880 [5:00:32<16:45,  1.30it/s]
1|24573|Loss: 0.82328200340271:  95%|█████████▍| 24572/25880 [5:00:32<16:45,  1.30it/s]  
1|24573|Loss: 0.82328200340271:  95%|█████████▍| 24573/25880 [5:00:33<16:45,  1.30it/s]
1|24574|Loss: 0.848967432975769:  95%|█████████▍| 24573/25880 [5:00:33<16:45,  1.30it/s]
1|24574|Loss: 0.848967432975769:  95%|█████████▍| 24574/25880 [5:00:33<16:03,  1.36it/s]
1|24575|Loss: 0.7968096733093262:  95%|█████████▍| 24574/25880 [5:00:34<16:03,  1.36it/s]
1|24575|Loss: 0.7968096733093262:  95%|█████████▍| 24575/25880 [5:00:34<15:44,  1.38it/s]
1|24576|Loss: 0.9078626036643982:  95%|█████████▍| 24575/25880 [5:00:35<15:44,  1.38it/s]
1|24576|Loss: 0.9078626036643982:  95%|█████████▍| 24576/25880 [5:00:35<16:01,  1.36it/s]
1|24577|Loss: 0.9161019921302795:  95%|█████████▍| 24576/25880 [5:00:35<16:01,  1.36it/s]
1|24577|Loss: 0.9161019921302795:  95%|█████████▍| 24577/25880 [5:00:36<16:08,  1.35it/s]
1|24578|Loss: 0.8354529142379761:  95%|█████████▍| 24577/25880 [5:00:36<16:08,  1.35it/s]
1|24578|Loss: 0.8354529142379761:  95%|█████████▍| 24578/25880 [5:00:36<15:55,  1.36it/s]
1|24579|Loss: 0.976159930229187:  95%|█████████▍| 24578/25880 [5:00:37<15:55,  1.36it/s] 
1|24579|Loss: 0.976159930229187:  95%|█████████▍| 24579/25880 [5:00:37<15:15,  1.42it/s]
1|24580|Loss: 0.7929089069366455:  95%|█████████▍| 24579/25880 [5:00:37<15:15,  1.42it/s]
1|24580|Loss: 0.7929089069366455:  95%|█████████▍| 24580/25880 [5:00:38<14:09,  1.53it/s]
1|24581|Loss: 0.8130494356155396:  95%|█████████▍| 24580/25880 [5:00:38<14:09,  1.53it/s]
1|24581|Loss: 0.8130494356155396:  95%|█████████▍| 24581/25880 [5:00:38<14:27,  1.50it/s]
1|24582|Loss: 1.0221216678619385:  95%|█████████▍| 24581/25880 [5:00:39<14:27,  1.50it/s]
1|24582|Loss: 1.0221216678619385:  95%|█████████▍| 24582/25880 [5:00:39<14:55,  1.45it/s]
1|24583|Loss: 0.6948513388633728:  95%|█████████▍| 24582/25880 [5:00:39<14:55,  1.45it/s]
1|24583|Loss: 0.6948513388633728:  95%|█████████▍| 24583/25880 [5:00:40<15:57,  1.35it/s]
1|24584|Loss: 0.8331663012504578:  95%|█████████▍| 24583/25880 [5:00:40<15:57,  1.35it/s]
1|24584|Loss: 0.8331663012504578:  95%|█████████▍| 24584/25880 [5:00:41<16:53,  1.28it/s]
1|24585|Loss: 0.9985823631286621:  95%|█████████▍| 24584/25880 [5:00:41<16:53,  1.28it/s]
1|24585|Loss: 0.9985823631286621:  95%|█████████▍| 24585/25880 [5:00:41<15:31,  1.39it/s]
1|24586|Loss: 0.8998944759368896:  95%|█████████▍| 24585/25880 [5:00:42<15:31,  1.39it/s]
1|24586|Loss: 0.8998944759368896:  95%|█████████▌| 24586/25880 [5:00:42<14:12,  1.52it/s]
1|24587|Loss: 0.8111385107040405:  95%|█████████▌| 24586/25880 [5:00:42<14:12,  1.52it/s]
1|24587|Loss: 0.8111385107040405:  95%|█████████▌| 24587/25880 [5:00:43<15:21,  1.40it/s]
1|24588|Loss: 0.7941718101501465:  95%|█████████▌| 24587/25880 [5:00:43<15:21,  1.40it/s]
1|24588|Loss: 0.7941718101501465:  95%|█████████▌| 24588/25880 [5:00:43<14:34,  1.48it/s]
1|24589|Loss: 0.8545908331871033:  95%|█████████▌| 24588/25880 [5:00:44<14:34,  1.48it/s]
1|24589|Loss: 0.8545908331871033:  95%|█████████▌| 24589/25880 [5:00:44<13:29,  1.60it/s]
1|24590|Loss: 0.8972288966178894:  95%|█████████▌| 24589/25880 [5:00:44<13:29,  1.60it/s]
1|24590|Loss: 0.8972288966178894:  95%|█████████▌| 24590/25880 [5:00:44<13:52,  1.55it/s]
1|24591|Loss: 0.6815083622932434:  95%|█████████▌| 24590/25880 [5:00:45<13:52,  1.55it/s]
1|24591|Loss: 0.6815083622932434:  95%|█████████▌| 24591/25880 [5:00:45<14:50,  1.45it/s]
1|24592|Loss: 0.8631287813186646:  95%|█████████▌| 24591/25880 [5:00:46<14:50,  1.45it/s]
1|24592|Loss: 0.8631287813186646:  95%|█████████▌| 24592/25880 [5:00:46<15:47,  1.36it/s]
1|24593|Loss: 0.8397732377052307:  95%|█████████▌| 24592/25880 [5:00:47<15:47,  1.36it/s]
1|24593|Loss: 0.8397732377052307:  95%|█████████▌| 24593/25880 [5:00:47<16:27,  1.30it/s]
1|24594|Loss: 0.8340641260147095:  95%|█████████▌| 24593/25880 [5:00:47<16:27,  1.30it/s]
1|24594|Loss: 0.8340641260147095:  95%|█████████▌| 24594/25880 [5:00:48<16:57,  1.26it/s]
1|24595|Loss: 0.8582614660263062:  95%|█████████▌| 24594/25880 [5:00:48<16:57,  1.26it/s]
1|24595|Loss: 0.8582614660263062:  95%|█████████▌| 24595/25880 [5:00:49<16:34,  1.29it/s]
1|24596|Loss: 0.944688618183136:  95%|█████████▌| 24595/25880 [5:00:49<16:34,  1.29it/s] 
1|24596|Loss: 0.944688618183136:  95%|█████████▌| 24596/25880 [5:00:49<16:03,  1.33it/s]
1|24597|Loss: 0.7888638973236084:  95%|█████████▌| 24596/25880 [5:00:50<16:03,  1.33it/s]
1|24597|Loss: 0.7888638973236084:  95%|█████████▌| 24597/25880 [5:00:50<14:49,  1.44it/s]
1|24598|Loss: 0.9038201570510864:  95%|█████████▌| 24597/25880 [5:00:50<14:49,  1.44it/s]
1|24598|Loss: 0.9038201570510864:  95%|█████████▌| 24598/25880 [5:00:50<14:46,  1.45it/s]
1|24599|Loss: 0.930437445640564:  95%|█████████▌| 24598/25880 [5:00:51<14:46,  1.45it/s] 
1|24599|Loss: 0.930437445640564:  95%|█████████▌| 24599/25880 [5:00:51<14:15,  1.50it/s]
1|24600|Loss: 0.8167116045951843:  95%|█████████▌| 24599/25880 [5:00:51<14:15,  1.50it/s]
1|24600|Loss: 0.8167116045951843:  95%|█████████▌| 24600/25880 [5:00:52<14:44,  1.45it/s]
1|24601|Loss: 0.7704900503158569:  95%|█████████▌| 24600/25880 [5:00:52<14:44,  1.45it/s]
1|24601|Loss: 0.7704900503158569:  95%|█████████▌| 24601/25880 [5:00:53<16:31,  1.29it/s]
1|24602|Loss: 0.7338691353797913:  95%|█████████▌| 24601/25880 [5:00:53<16:31,  1.29it/s]
1|24602|Loss: 0.7338691353797913:  95%|█████████▌| 24602/25880 [5:00:54<16:08,  1.32it/s]
1|24603|Loss: 0.866337776184082:  95%|█████████▌| 24602/25880 [5:00:54<16:08,  1.32it/s] 
1|24603|Loss: 0.866337776184082:  95%|█████████▌| 24603/25880 [5:00:54<15:52,  1.34it/s]
1|24604|Loss: 0.8621872663497925:  95%|█████████▌| 24603/25880 [5:00:55<15:52,  1.34it/s]
1|24604|Loss: 0.8621872663497925:  95%|█████████▌| 24604/25880 [5:00:55<14:53,  1.43it/s]
1|24605|Loss: 0.8944852948188782:  95%|█████████▌| 24604/25880 [5:00:55<14:53,  1.43it/s]
1|24605|Loss: 0.8944852948188782:  95%|█████████▌| 24605/25880 [5:00:55<14:21,  1.48it/s]
1|24606|Loss: 0.6569737195968628:  95%|█████████▌| 24605/25880 [5:00:56<14:21,  1.48it/s]
1|24606|Loss: 0.6569737195968628:  95%|█████████▌| 24606/25880 [5:00:56<14:25,  1.47it/s]
1|24607|Loss: 0.8671776056289673:  95%|█████████▌| 24606/25880 [5:00:56<14:25,  1.47it/s]
1|24607|Loss: 0.8671776056289673:  95%|█████████▌| 24607/25880 [5:00:57<14:13,  1.49it/s]
1|24608|Loss: 0.8591693639755249:  95%|█████████▌| 24607/25880 [5:00:57<14:13,  1.49it/s]
1|24608|Loss: 0.8591693639755249:  95%|█████████▌| 24608/25880 [5:00:57<14:27,  1.47it/s]
1|24609|Loss: 0.8315136432647705:  95%|█████████▌| 24608/25880 [5:00:58<14:27,  1.47it/s]
1|24609|Loss: 0.8315136432647705:  95%|█████████▌| 24609/25880 [5:00:58<14:51,  1.43it/s]
1|24610|Loss: 0.781253457069397:  95%|██████���██▌| 24609/25880 [5:00:59<14:51,  1.43it/s] 
1|24610|Loss: 0.781253457069397:  95%|█████████▌| 24610/25880 [5:00:59<13:56,  1.52it/s]
1|24611|Loss: 0.8335199952125549:  95%|█████████▌| 24610/25880 [5:00:59<13:56,  1.52it/s]
1|24611|Loss: 0.8335199952125549:  95%|█████████▌| 24611/25880 [5:01:00<14:35,  1.45it/s]
1|24612|Loss: 0.8382601737976074:  95%|█████████▌| 24611/25880 [5:01:00<14:35,  1.45it/s]
1|24612|Loss: 0.8382601737976074:  95%|█████████▌| 24612/25880 [5:01:00<15:16,  1.38it/s]
1|24613|Loss: 0.9633118510246277:  95%|█████████▌| 24612/25880 [5:01:01<15:16,  1.38it/s]
1|24613|Loss: 0.9633118510246277:  95%|█████████▌| 24613/25880 [5:01:01<15:30,  1.36it/s]
1|24614|Loss: 1.0433169603347778:  95%|█████████▌| 24613/25880 [5:01:02<15:30,  1.36it/s]
1|24614|Loss: 1.0433169603347778:  95%|█████████▌| 24614/25880 [5:01:02<16:39,  1.27it/s]
1|24615|Loss: 0.8758081197738647:  95%|█████████▌| 24614/25880 [5:01:02<16:39,  1.27it/s]
1|24615|Loss: 0.8758081197738647:  95%|█████████▌| 24615/25880 [5:01:03<16:25,  1.28it/s]
1|24616|Loss: 0.8533802628517151:  95%|█████████▌| 24615/25880 [5:01:03<16:25,  1.28it/s]
1|24616|Loss: 0.8533802628517151:  95%|█████████▌| 24616/25880 [5:01:03<15:36,  1.35it/s]
1|24617|Loss: 0.8045367002487183:  95%|█████████▌| 24616/25880 [5:01:04<15:36,  1.35it/s]
1|24617|Loss: 0.8045367002487183:  95%|█████████▌| 24617/25880 [5:01:04<15:30,  1.36it/s]
1|24618|Loss: 0.8422548174858093:  95%|█████████▌| 24617/25880 [5:01:05<15:30,  1.36it/s]
1|24618|Loss: 0.8422548174858093:  95%|█████████▌| 24618/25880 [5:01:05<15:46,  1.33it/s]
1|24619|Loss: 0.7745383977890015:  95%|█████████▌| 24618/25880 [5:01:05<15:46,  1.33it/s]
1|24619|Loss: 0.7745383977890015:  95%|█████████▌| 24619/25880 [5:01:06<16:54,  1.24it/s]
1|24620|Loss: 0.7643780708312988:  95%|█████████▌| 24619/25880 [5:01:06<16:54,  1.24it/s]
1|24620|Loss: 0.7643780708312988:  95%|█████████▌| 24620/25880 [5:01:07<16:42,  1.26it/s]
1|24621|Loss: 0.8997297883033752:  95%|█████████▌| 24620/25880 [5:01:07<16:42,  1.26it/s]
1|24621|Loss: 0.8997297883033752:  95%|█████████▌| 24621/25880 [5:01:07<16:07,  1.30it/s]
1|24622|Loss: 0.758788526058197:  95%|█████████▌| 24621/25880 [5:01:08<16:07,  1.30it/s] 
1|24622|Loss: 0.758788526058197:  95%|█████████▌| 24622/25880 [5:01:08<15:05,  1.39it/s]
1|24623|Loss: 0.8228618502616882:  95%|█████████▌| 24622/25880 [5:01:08<15:05,  1.39it/s]
1|24623|Loss: 0.8228618502616882:  95%|█████████▌| 24623/25880 [5:01:09<14:58,  1.40it/s]
1|24624|Loss: 0.8362905979156494:  95%|█████████▌| 24623/25880 [5:01:09<14:58,  1.40it/s]
1|24624|Loss: 0.8362905979156494:  95%|█████████▌| 24624/25880 [5:01:09<14:29,  1.45it/s]
1|24625|Loss: 0.8744890093803406:  95%|█████████▌| 24624/25880 [5:01:10<14:29,  1.45it/s]
1|24625|Loss: 0.8744890093803406:  95%|█████████▌| 24625/25880 [5:01:10<14:57,  1.40it/s]
1|24626|Loss: 0.8320677876472473:  95%|█████████▌| 24625/25880 [5:01:11<14:57,  1.40it/s]
1|24626|Loss: 0.8320677876472473:  95%|█████████▌| 24626/25880 [5:01:11<15:47,  1.32it/s]
1|24627|Loss: 0.8059308528900146:  95%|█████████▌| 24626/25880 [5:01:11<15:47,  1.32it/s]
1|24627|Loss: 0.8059308528900146:  95%|█████████▌| 24627/25880 [5:01:12<15:22,  1.36it/s]
1|24628|Loss: 0.7944002151489258:  95%|█████████▌| 24627/25880 [5:01:12<15:22,  1.36it/s]
1|24628|Loss: 0.7944002151489258:  95%|█████████▌| 24628/25880 [5:01:12<15:34,  1.34it/s]
1|24629|Loss: 0.7826722860336304:  95%|█████████▌| 24628/25880 [5:01:13<15:34,  1.34it/s]
1|24629|Loss: 0.7826722860336304:  95%|█████████▌| 24629/25880 [5:01:13<15:00,  1.39it/s]
1|24630|Loss: 0.820162832736969:  95%|█████████▌| 24629/25880 [5:01:13<15:00,  1.39it/s] 
1|24630|Loss: 0.820162832736969:  95%|█████████▌| 24630/25880 [5:01:14<15:55,  1.31it/s]
1|24631|Loss: 0.6774107217788696:  95%|█████████▌| 24630/25880 [5:01:14<15:55,  1.31it/s]
1|24631|Loss: 0.6774107217788696:  95%|█████████▌| 24631/25880 [5:01:15<15:27,  1.35it/s]
1|24632|Loss: 0.8990189433097839:  95%|█████████▌| 24631/25880 [5:01:15<15:27,  1.35it/s]
1|24632|Loss: 0.8990189433097839:  95%|█████████▌| 24632/25880 [5:01:15<16:05,  1.29it/s]
1|24633|Loss: 0.8134542107582092:  95%|█████████▌| 24632/25880 [5:01:16<16:05,  1.29it/s]
1|24633|Loss: 0.8134542107582092:  95%|█████████▌| 24633/25880 [5:01:16<15:30,  1.34it/s]
1|24634|Loss: 0.8335697054862976:  95%|█████████▌| 24633/25880 [5:01:17<15:30,  1.34it/s]
1|24634|Loss: 0.8335697054862976:  95%|█████████▌| 24634/25880 [5:01:17<15:23,  1.35it/s]
1|24635|Loss: 0.8501234650611877:  95%|█████████▌| 24634/25880 [5:01:17<15:23,  1.35it/s]
1|24635|Loss: 0.8501234650611877:  95%|█████████▌| 24635/25880 [5:01:17<13:58,  1.48it/s]
1|24636|Loss: 1.0221168994903564:  95%|█████████▌| 24635/25880 [5:01:18<13:58,  1.48it/s]
1|24636|Loss: 1.0221168994903564:  95%|█████████▌| 24636/25880 [5:01:18<13:05,  1.58it/s]
1|24637|Loss: 0.705613374710083:  95%|█████████▌| 24636/25880 [5:01:18<13:05,  1.58it/s] 
1|24637|Loss: 0.705613374710083:  95%|█████████▌| 24637/25880 [5:01:19<12:59,  1.60it/s]
1|24638|Loss: 0.7871283292770386:  95%|█████████▌| 24637/25880 [5:01:19<12:59,  1.60it/s]
1|24638|Loss: 0.7871283292770386:  95%|█████████▌| 24638/25880 [5:01:19<13:32,  1.53it/s]
1|24639|Loss: 0.7749804258346558:  95%|█████████▌| 24638/25880 [5:01:20<13:32,  1.53it/s]
1|24639|Loss: 0.7749804258346558:  95%|█████████▌| 24639/25880 [5:01:20<13:32,  1.53it/s]
1|24640|Loss: 0.7254987955093384:  95%|█████████▌| 24639/25880 [5:01:20<13:32,  1.53it/s]
1|24640|Loss: 0.7254987955093384:  95%|█████████▌| 24640/25880 [5:01:20<12:39,  1.63it/s]
1|24641|Loss: 0.7730002403259277:  95%|█████████▌| 24640/25880 [5:01:21<12:39,  1.63it/s]
1|24641|Loss: 0.7730002403259277:  95%|█████████▌| 24641/25880 [5:01:21<13:47,  1.50it/s]
1|24642|Loss: 0.8320444822311401:  95%|█████████▌| 24641/25880 [5:01:22<13:47,  1.50it/s]
1|24642|Loss: 0.8320444822311401:  95%|█████████▌| 24642/25880 [5:01:22<15:08,  1.36it/s]
1|24643|Loss: 0.8767532706260681:  95%|█████████▌| 24642/25880 [5:01:22<15:08,  1.36it/s]
1|24643|Loss: 0.8767532706260681:  95%|█████████▌| 24643/25880 [5:01:23<14:36,  1.41it/s]
1|24644|Loss: 0.8815116882324219:  95%|█████████▌| 24643/25880 [5:01:23<14:36,  1.41it/s]
1|24644|Loss: 0.8815116882324219:  95%|█████████▌| 24644/25880 [5:01:23<13:46,  1.49it/s]
1|24645|Loss: 0.8812931180000305:  95%|█████████▌| 24644/25880 [5:01:24<13:46,  1.49it/s]
1|24645|Loss: 0.8812931180000305:  95%|█████████▌| 24645/25880 [5:01:24<12:36,  1.63it/s]
1|24646|Loss: 0.7913224697113037:  95%|█████████▌| 24645/25880 [5:01:24<12:36,  1.63it/s]
1|24646|Loss: 0.7913224697113037:  95%|█████████▌| 24646/25880 [5:01:25<13:21,  1.54it/s]
1|24647|Loss: 0.7774766683578491:  95%|█████████▌| 24646/25880 [5:01:25<13:21,  1.54it/s]
1|24647|Loss: 0.7774766683578491:  95%|█████████▌| 24647/25880 [5:01:25<14:24,  1.43it/s]
1|24648|Loss: 0.8804718255996704:  95%|█████████▌| 24647/25880 [5:01:26<14:24,  1.43it/s]
1|24648|Loss: 0.8804718255996704:  95%|█████████▌| 24648/25880 [5:01:26<14:01,  1.46it/s]
1|24649|Loss: 0.815911591053009:  95%|█████████▌| 24648/25880 [5:01:26<14:01,  1.46it/s] 
1|24649|Loss: 0.815911591053009:  95%|█████████▌| 24649/25880 [5:01:27<13:31,  1.52it/s]
1|24650|Loss: 0.6981926560401917:  95%|█████████▌| 24649/25880 [5:01:27<13:31,  1.52it/s]
1|24650|Loss: 0.6981926560401917:  95%|█████████▌| 24650/25880 [5:01:27<13:40,  1.50it/s]
1|24651|Loss: 0.7665939927101135:  95%|█████████▌| 24650/25880 [5:01:28<13:40,  1.50it/s]
1|24651|Loss: 0.7665939927101135:  95%|█████████▌| 24651/25880 [5:01:28<13:50,  1.48it/s]
1|24652|Loss: 0.9378587007522583:  95%|█████████▌| 24651/25880 [5:01:28<13:50,  1.48it/s]
1|24652|Loss: 0.9378587007522583:  95%|█████████▌| 24652/25880 [5:01:29<14:09,  1.45it/s]
1|24653|Loss: 0.8821109533309937:  95%|█████████▌| 24652/25880 [5:01:29<14:09,  1.45it/s]
1|24653|Loss: 0.8821109533309937:  95%|█████████▌| 24653/25880 [5:01:30<14:48,  1.38it/s]
1|24654|Loss: 0.9313105940818787:  95%|█████████▌| 24653/25880 [5:01:30<14:48,  1.38it/s]
1|24654|Loss: 0.9313105940818787:  95%|█████████▌| 24654/25880 [5:01:30<14:10,  1.44it/s]
1|24655|Loss: 0.7863340377807617:  95%|█████████▌| 24654/25880 [5:01:30<14:10,  1.44it/s]
1|24655|Loss: 0.7863340377807617:  95%|█████████▌| 24655/25880 [5:01:31<12:49,  1.59it/s]
1|24656|Loss: 0.8754257559776306:  95%|█████████▌| 24655/25880 [5:01:31<12:49,  1.59it/s]
1|24656|Loss: 0.8754257559776306:  95%|█████████▌| 24656/25880 [5:01:31<13:50,  1.47it/s]
1|24657|Loss: 0.8800022006034851:  95%|█████████▌| 24656/25880 [5:01:32<13:50,  1.47it/s]
1|24657|Loss: 0.8800022006034851:  95%|█████████▌| 24657/25880 [5:01:32<15:07,  1.35it/s]
1|24658|Loss: 0.7755206823348999:  95%|█████████▌| 24657/25880 [5:01:33<15:07,  1.35it/s]
1|24658|Loss: 0.7755206823348999:  95%|█████████▌| 24658/25880 [5:01:33<15:51,  1.28it/s]
1|24659|Loss: 0.9974634647369385:  95%|█████████▌| 24658/25880 [5:01:34<15:51,  1.28it/s]
1|24659|Loss: 0.9974634647369385:  95%|█████████▌| 24659/25880 [5:01:34<16:00,  1.27it/s]
1|24660|Loss: 0.9587016701698303:  95%|█████████▌| 24659/25880 [5:01:34<16:00,  1.27it/s]
1|24660|Loss: 0.9587016701698303:  95%|█████████▌| 24660/25880 [5:01:35<15:47,  1.29it/s]
1|24661|Loss: 0.8269653916358948:  95%|█████████▌| 24660/25880 [5:01:35<15:47,  1.29it/s]
1|24661|Loss: 0.8269653916358948:  95%|█████████▌| 24661/25880 [5:01:35<14:38,  1.39it/s]
1|24662|Loss: 0.7193235754966736:  95%|█████████▌| 24661/25880 [5:01:36<14:38,  1.39it/s]
1|24662|Loss: 0.7193235754966736:  95%|█████████▌| 24662/25880 [5:01:36<13:50,  1.47it/s]
1|24663|Loss: 0.7925422191619873:  95%|█████████▌| 24662/25880 [5:01:36<13:50,  1.47it/s]
1|24663|Loss: 0.7925422191619873:  95%|█████████▌| 24663/25880 [5:01:37<13:56,  1.46it/s]
1|24664|Loss: 0.7420585751533508:  95%|█████████▌| 24663/25880 [5:01:37<13:56,  1.46it/s]
1|24664|Loss: 0.7420585751533508:  95%|█████████▌| 24664/25880 [5:01:37<14:09,  1.43it/s]
1|24665|Loss: 0.8110352158546448:  95%|█████████▌| 24664/25880 [5:01:38<14:09,  1.43it/s]
1|24665|Loss: 0.8110352158546448:  95%|█████████▌| 24665/25880 [5:01:38<14:22,  1.41it/s]
1|24666|Loss: 0.841966450214386:  95%|█████████▌| 24665/25880 [5:01:38<14:22,  1.41it/s] 
1|24666|Loss: 0.841966450214386:  95%|█████████▌| 24666/25880 [5:01:39<14:23,  1.41it/s]
1|24667|Loss: 0.8240245580673218:  95%|█████████▌| 24666/25880 [5:01:39<14:23,  1.41it/s]
1|24667|Loss: 0.8240245580673218:  95%|█████████▌| 24667/25880 [5:01:39<14:01,  1.44it/s]
1|24668|Loss: 0.9836357831954956:  95%|█████████▌| 24667/25880 [5:01:40<14:01,  1.44it/s]
1|24668|Loss: 0.9836357831954956:  95%|█████████▌| 24668/25880 [5:01:40<14:07,  1.43it/s]
1|24669|Loss: 0.8192895650863647:  95%|█████████▌| 24668/25880 [5:01:41<14:07,  1.43it/s]
1|24669|Loss: 0.8192895650863647:  95%|█████████▌| 24669/25880 [5:01:41<13:54,  1.45it/s]
1|24670|Loss: 0.8228965997695923:  95%|█████████▌| 24669/25880 [5:01:41<13:54,  1.45it/s]
1|24670|Loss: 0.8228965997695923:  95%|█████████▌| 24670/25880 [5:01:42<14:43,  1.37it/s]
1|24671|Loss: 0.9667537212371826:  95%|█████████▌| 24670/25880 [5:01:42<14:43,  1.37it/s]
1|24671|Loss: 0.9667537212371826:  95%|█████████▌| 24671/25880 [5:01:42<14:23,  1.40it/s]
1|24672|Loss: 0.8185255527496338:  95%|█████████▌| 24671/25880 [5:01:43<14:23,  1.40it/s]
1|24672|Loss: 0.8185255527496338:  95%|█████████▌| 24672/25880 [5:01:43<14:11,  1.42it/s]
1|24673|Loss: 0.717388391494751:  95%|█████████▌| 24672/25880 [5:01:43<14:11,  1.42it/s] 
1|24673|Loss: 0.717388391494751:  95%|█████████▌| 24673/25880 [5:01:44<15:02,  1.34it/s]
1|24674|Loss: 0.8524348139762878:  95%|█████████▌| 24673/25880 [5:01:44<15:02,  1.34it/s]
1|24674|Loss: 0.8524348139762878:  95%|█████████▌| 24674/25880 [5:01:45<15:26,  1.30it/s]
1|24675|Loss: 0.8580760955810547:  95%|█████████▌| 24674/25880 [5:01:45<15:26,  1.30it/s]
1|24675|Loss: 0.8580760955810547:  95%|█████████▌| 24675/25880 [5:01:45<15:51,  1.27it/s]
1|24676|Loss: 0.7751339673995972:  95%|█████████▌| 24675/25880 [5:01:46<15:51,  1.27it/s]
1|24676|Loss: 0.7751339673995972:  95%|█████████▌| 24676/25880 [5:01:46<15:34,  1.29it/s]
1|24677|Loss: 0.8646941184997559:  95%|█████████▌| 24676/25880 [5:01:47<15:34,  1.29it/s]
1|24677|Loss: 0.8646941184997559:  95%|█████████▌| 24677/25880 [5:01:47<14:05,  1.42it/s]
1|24678|Loss: 1.0696941614151:  95%|█████████▌| 24677/25880 [5:01:47<14:05,  1.42it/s]   
1|24678|Loss: 1.0696941614151:  95%|█████████▌| 24678/25880 [5:01:47<12:36,  1.59it/s]
1|24679|Loss: 0.8555191159248352:  95%|█████████▌| 24678/25880 [5:01:48<12:36,  1.59it/s]
1|24679|Loss: 0.8555191159248352:  95%|█████████▌| 24679/25880 [5:01:48<13:06,  1.53it/s]
1|24680|Loss: 0.8343659043312073:  95%|█████████▌| 24679/25880 [5:01:48<13:06,  1.53it/s]
1|24680|Loss: 0.8343659043312073:  95%|█████████▌| 24680/25880 [5:01:49<13:42,  1.46it/s]
1|24681|Loss: 0.725780725479126:  95%|█████████▌| 24680/25880 [5:01:49<13:42,  1.46it/s] 
1|24681|Loss: 0.725780725479126:  95%|█████████▌| 24681/25880 [5:01:49<14:23,  1.39it/s]
1|24682|Loss: 0.78770911693573:  95%|█████████▌| 24681/25880 [5:01:50<14:23,  1.39it/s] 
1|24682|Loss: 0.78770911693573:  95%|█████████▌| 24682/25880 [5:01:50<15:03,  1.33it/s]
1|24683|Loss: 0.7650477290153503:  95%|█████████▌| 24682/25880 [5:01:51<15:03,  1.33it/s]
1|24683|Loss: 0.7650477290153503:  95%|█████████▌| 24683/25880 [5:01:51<14:58,  1.33it/s]
1|24684|Loss: 0.8190730214118958:  95%|█████████▌| 24683/25880 [5:01:51<14:58,  1.33it/s]
1|24684|Loss: 0.8190730214118958:  95%|█████████▌| 24684/25880 [5:01:52<15:08,  1.32it/s]
1|24685|Loss: 0.7762234807014465:  95%|█████████▌| 24684/25880 [5:01:52<15:08,  1.32it/s]
1|24685|Loss: 0.7762234807014465:  95%|█████████▌| 24685/25880 [5:01:53<14:55,  1.33it/s]
1|24686|Loss: 0.7823609709739685:  95%|█████████▌| 24685/25880 [5:01:53<14:55,  1.33it/s]
1|24686|Loss: 0.7823609709739685:  95%|█████████▌| 24686/25880 [5:01:53<14:45,  1.35it/s]
1|24687|Loss: 0.8712432980537415:  95%|█████████▌| 24686/25880 [5:01:54<14:45,  1.35it/s]
1|24687|Loss: 0.8712432980537415:  95%|█████████▌| 24687/25880 [5:01:54<14:40,  1.35it/s]
1|24688|Loss: 0.7992550134658813:  95%|█████████▌| 24687/25880 [5:01:54<14:40,  1.35it/s]
1|24688|Loss: 0.7992550134658813:  95%|█████████▌| 24688/25880 [5:01:55<13:33,  1.47it/s]
1|24689|Loss: 0.8191467523574829:  95%|█████████▌| 24688/25880 [5:01:55<13:33,  1.47it/s]
1|24689|Loss: 0.8191467523574829:  95%|█████████▌| 24689/25880 [5:01:55<13:35,  1.46it/s]
1|24690|Loss: 0.9819203615188599:  95%|█████████▌| 24689/25880 [5:01:56<13:35,  1.46it/s]
1|24690|Loss: 0.9819203615188599:  95%|█████████▌| 24690/25880 [5:01:56<13:09,  1.51it/s]
1|24691|Loss: 0.6890389323234558:  95%|█████████▌| 24690/25880 [5:01:56<13:09,  1.51it/s]
1|24691|Loss: 0.6890389323234558:  95%|█████████▌| 24691/25880 [5:01:57<13:49,  1.43it/s]
1|24692|Loss: 0.7017123699188232:  95%|█████████▌| 24691/25880 [5:01:57<13:49,  1.43it/s]
1|24692|Loss: 0.7017123699188232:  95%|█████████▌| 24692/25880 [5:01:57<14:11,  1.40it/s]
1|24693|Loss: 0.9427270293235779:  95%|█████████▌| 24692/25880 [5:01:58<14:11,  1.40it/s]
1|24693|Loss: 0.9427270293235779:  95%|█████████▌| 24693/25880 [5:01:58<14:53,  1.33it/s]
1|24694|Loss: 0.965406060218811:  95%|█████████▌| 24693/25880 [5:01:59<14:53,  1.33it/s] 
1|24694|Loss: 0.965406060218811:  95%|█████████▌| 24694/25880 [5:01:59<15:00,  1.32it/s]
1|24695|Loss: 0.9816744923591614:  95%|█████████▌| 24694/25880 [5:01:59<15:00,  1.32it/s]
1|24695|Loss: 0.9816744923591614:  95%|█████████▌| 24695/25880 [5:02:00<15:31,  1.27it/s]
1|24696|Loss: 0.7934227585792542:  95%|█████████▌| 24695/25880 [5:02:00<15:31,  1.27it/s]
1|24696|Loss: 0.7934227585792542:  95%|█████████▌| 24696/25880 [5:02:01<15:27,  1.28it/s]
1|24697|Loss: 0.8695365786552429:  95%|█████████▌| 24696/25880 [5:02:01<15:27,  1.28it/s]
1|24697|Loss: 0.8695365786552429:  95%|█████████▌| 24697/25880 [5:02:01<15:31,  1.27it/s]
1|24698|Loss: 0.7474083304405212:  95%|█████████▌| 24697/25880 [5:02:02<15:31,  1.27it/s]
1|24698|Loss: 0.7474083304405212:  95%|█████████▌| 24698/25880 [5:02:02<15:06,  1.30it/s]
1|24699|Loss: 0.8193687796592712:  95%|█████████▌| 24698/25880 [5:02:03<15:06,  1.30it/s]
1|24699|Loss: 0.8193687796592712:  95%|█████████▌| 24699/25880 [5:02:03<14:51,  1.33it/s]
1|24700|Loss: 0.886349081993103:  95%|█████████▌| 24699/25880 [5:02:03<14:51,  1.33it/s] 
1|24700|Loss: 0.886349081993103:  95%|█████████▌| 24700/25880 [5:02:04<14:34,  1.35it/s]
1|24701|Loss: 0.861650288105011:  95%|█████████▌| 24700/25880 [5:02:04<14:34,  1.35it/s]
1|24701|Loss: 0.861650288105011:  95%|█████████▌| 24701/25880 [5:02:04<14:27,  1.36it/s]
1|24702|Loss: 0.815992534160614:  95%|█████████▌| 24701/25880 [5:02:05<14:27,  1.36it/s]
1|24702|Loss: 0.815992534160614:  95%|█████████▌| 24702/25880 [5:02:05<14:40,  1.34it/s]
1|24703|Loss: 0.7769359350204468:  95%|█████████▌| 24702/25880 [5:02:05<14:40,  1.34it/s]
1|24703|Loss: 0.7769359350204468:  95%|█████████▌| 24703/25880 [5:02:06<13:39,  1.44it/s]
1|24704|Loss: 0.8304005265235901:  95%|█████████▌| 24703/25880 [5:02:06<13:39,  1.44it/s]
1|24704|Loss: 0.8304005265235901:  95%|█████████▌| 24704/25880 [5:02:06<13:29,  1.45it/s]
1|24705|Loss: 0.955336332321167:  95%|█████████▌| 24704/25880 [5:02:07<13:29,  1.45it/s] 
1|24705|Loss: 0.955336332321167:  95%|█████████▌| 24705/25880 [5:02:07<14:36,  1.34it/s]
1|24706|Loss: 0.7608202695846558:  95%|█████████▌| 24705/25880 [5:02:08<14:36,  1.34it/s]
1|24706|Loss: 0.7608202695846558:  95%|█████████▌| 24706/25880 [5:02:08<15:39,  1.25it/s]
1|24707|Loss: 0.8647489547729492:  95%|█████████▌| 24706/25880 [5:02:09<15:39,  1.25it/s]
1|24707|Loss: 0.8647489547729492:  95%|█████████▌| 24707/25880 [5:02:09<14:58,  1.31it/s]
1|24708|Loss: 0.8402017951011658:  95%|█████████▌| 24707/25880 [5:02:09<14:58,  1.31it/s]
1|24708|Loss: 0.8402017951011658:  95%|█████████▌| 24708/25880 [5:02:10<15:04,  1.30it/s]
1|24709|Loss: 0.8417360186576843:  95%|█████████▌| 24708/25880 [5:02:10<15:04,  1.30it/s]
1|24709|Loss: 0.8417360186576843:  95%|█████████▌| 24709/25880 [5:02:10<14:57,  1.30it/s]
1|24710|Loss: 0.8098464012145996:  95%|█████████▌| 24709/25880 [5:02:11<14:57,  1.30it/s]
1|24710|Loss: 0.8098464012145996:  95%|█████████▌| 24710/25880 [5:02:11<14:52,  1.31it/s]
1|24711|Loss: 0.8567655086517334:  95%|█████████▌| 24710/25880 [5:02:12<14:52,  1.31it/s]
1|24711|Loss: 0.8567655086517334:  95%|█████████▌| 24711/25880 [5:02:12<14:42,  1.33it/s]
1|24712|Loss: 0.833196222782135:  95%|█████████▌| 24711/25880 [5:02:12<14:42,  1.33it/s] 
1|24712|Loss: 0.833196222782135:  95%|█████████▌| 24712/25880 [5:02:13<14:25,  1.35it/s]
1|24713|Loss: 0.7993026971817017:  95%|█████████▌| 24712/25880 [5:02:13<14:25,  1.35it/s]
1|24713|Loss: 0.7993026971817017:  95%|█████████▌| 24713/25880 [5:02:13<14:19,  1.36it/s]
1|24714|Loss: 0.8651090264320374:  95%|█████████▌| 24713/25880 [5:02:14<14:19,  1.36it/s]
1|24714|Loss: 0.8651090264320374:  95%|█████████▌| 24714/25880 [5:02:14<14:16,  1.36it/s]
1|24715|Loss: 0.8676942586898804:  95%|█████████▌| 24714/25880 [5:02:14<14:16,  1.36it/s]
1|24715|Loss: 0.8676942586898804:  95%|█████████▌| 24715/25880 [5:02:15<14:06,  1.38it/s]
1|24716|Loss: 0.9067559838294983:  95%|█████████▌| 24715/25880 [5:02:15<14:06,  1.38it/s]
1|24716|Loss: 0.9067559838294983:  96%|█████████▌| 24716/25880 [5:02:16<14:32,  1.33it/s]
1|24717|Loss: 0.7809430956840515:  96%|█████████▌| 24716/25880 [5:02:16<14:32,  1.33it/s]
1|24717|Loss: 0.7809430956840515:  96%|█████████▌| 24717/25880 [5:02:16<14:51,  1.30it/s]
1|24718|Loss: 0.8452996015548706:  96%|█████████▌| 24717/25880 [5:02:17<14:51,  1.30it/s]
1|24718|Loss: 0.8452996015548706:  96%|█████████▌| 24718/25880 [5:02:17<14:17,  1.35it/s]
1|24719|Loss: 0.8921005725860596:  96%|█████████▌| 24718/25880 [5:02:17<14:17,  1.35it/s]
1|24719|Loss: 0.8921005725860596:  96%|█████████▌| 24719/25880 [5:02:18<13:28,  1.44it/s]
1|24720|Loss: 0.7347173094749451:  96%|█████████▌| 24719/25880 [5:02:18<13:28,  1.44it/s]
1|24720|Loss: 0.7347173094749451:  96%|█████████▌| 24720/25880 [5:02:18<13:22,  1.45it/s]
1|24721|Loss: 0.8524883389472961:  96%|█████████▌| 24720/25880 [5:02:19<13:22,  1.45it/s]
1|24721|Loss: 0.8524883389472961:  96%|█████████▌| 24721/25880 [5:02:19<13:59,  1.38it/s]
1|24722|Loss: 0.8535492420196533:  96%|█████████▌| 24721/25880 [5:02:19<13:59,  1.38it/s]
1|24722|Loss: 0.8535492420196533:  96%|█████████▌| 24722/25880 [5:02:20<13:12,  1.46it/s]
1|24723|Loss: 0.8320223093032837:  96%|█████████▌| 24722/25880 [5:02:20<13:12,  1.46it/s]
1|24723|Loss: 0.8320223093032837:  96%|█████████▌| 24723/25880 [5:02:20<13:46,  1.40it/s]
1|24724|Loss: 0.8547699451446533:  96%|█████████▌| 24723/25880 [5:02:21<13:46,  1.40it/s]
1|24724|Loss: 0.8547699451446533:  96%|█████████▌| 24724/25880 [5:02:21<13:31,  1.42it/s]
1|24725|Loss: 0.8400973081588745:  96%|█████████▌| 24724/25880 [5:02:22<13:31,  1.42it/s]
1|24725|Loss: 0.8400973081588745:  96%|█████████▌| 24725/25880 [5:02:22<13:35,  1.42it/s]
1|24726|Loss: 0.7582271099090576:  96%|█████████▌| 24725/25880 [5:02:22<13:35,  1.42it/s]
1|24726|Loss: 0.7582271099090576:  96%|███���█████▌| 24726/25880 [5:02:23<13:13,  1.46it/s]
1|24727|Loss: 0.9286776781082153:  96%|█████████▌| 24726/25880 [5:02:23<13:13,  1.46it/s]
1|24727|Loss: 0.9286776781082153:  96%|█████████▌| 24727/25880 [5:02:23<13:20,  1.44it/s]
1|24728|Loss: 0.8722658753395081:  96%|█████████▌| 24727/25880 [5:02:24<13:20,  1.44it/s]
1|24728|Loss: 0.8722658753395081:  96%|█████████▌| 24728/25880 [5:02:24<13:33,  1.42it/s]
1|24729|Loss: 0.8286283612251282:  96%|█████████▌| 24728/25880 [5:02:24<13:33,  1.42it/s]
1|24729|Loss: 0.8286283612251282:  96%|█████████▌| 24729/25880 [5:02:25<14:14,  1.35it/s]
1|24730|Loss: 0.8724086284637451:  96%|█████████▌| 24729/25880 [5:02:25<14:14,  1.35it/s]
1|24730|Loss: 0.8724086284637451:  96%|█████████▌| 24730/25880 [5:02:25<13:49,  1.39it/s]
1|24731|Loss: 0.7666430473327637:  96%|█████████▌| 24730/25880 [5:02:26<13:49,  1.39it/s]
1|24731|Loss: 0.7666430473327637:  96%|█████████▌| 24731/25880 [5:02:26<13:49,  1.38it/s]
1|24732|Loss: 0.8597873449325562:  96%|█████████▌| 24731/25880 [5:02:27<13:49,  1.38it/s]
1|24732|Loss: 0.8597873449325562:  96%|█████████▌| 24732/25880 [5:02:27<13:24,  1.43it/s]
1|24733|Loss: 0.7527980804443359:  96%|█████████▌| 24732/25880 [5:02:27<13:24,  1.43it/s]
1|24733|Loss: 0.7527980804443359:  96%|█████████▌| 24733/25880 [5:02:27<12:25,  1.54it/s]
1|24734|Loss: 0.8375594019889832:  96%|█████████▌| 24733/25880 [5:02:28<12:25,  1.54it/s]
1|24734|Loss: 0.8375594019889832:  96%|█████████▌| 24734/25880 [5:02:28<12:42,  1.50it/s]
1|24735|Loss: 0.7327593564987183:  96%|█████████▌| 24734/25880 [5:02:28<12:42,  1.50it/s]
1|24735|Loss: 0.7327593564987183:  96%|█████████▌| 24735/25880 [5:02:29<12:36,  1.51it/s]
1|24736|Loss: 0.7472039461135864:  96%|█████████▌| 24735/25880 [5:02:29<12:36,  1.51it/s]
1|24736|Loss: 0.7472039461135864:  96%|█████████▌| 24736/25880 [5:02:30<13:21,  1.43it/s]
1|24737|Loss: 0.8432426452636719:  96%|█████████▌| 24736/25880 [5:02:30<13:21,  1.43it/s]
1|24737|Loss: 0.8432426452636719:  96%|█████████▌| 24737/25880 [5:02:30<13:56,  1.37it/s]
1|24738|Loss: 0.7083082795143127:  96%|█████████▌| 24737/25880 [5:02:31<13:56,  1.37it/s]
1|24738|Loss: 0.7083082795143127:  96%|█████████▌| 24738/25880 [5:02:31<14:01,  1.36it/s]
1|24739|Loss: 0.9738036394119263:  96%|█████████▌| 24738/25880 [5:02:31<14:01,  1.36it/s]
1|24739|Loss: 0.9738036394119263:  96%|█████████▌| 24739/25880 [5:02:32<13:11,  1.44it/s]
1|24740|Loss: 0.9428054690361023:  96%|█████████▌| 24739/25880 [5:02:32<13:11,  1.44it/s]
1|24740|Loss: 0.9428054690361023:  96%|█████████▌| 24740/25880 [5:02:32<13:15,  1.43it/s]
1|24741|Loss: 0.7996054291725159:  96%|█████████▌| 24740/25880 [5:02:33<13:15,  1.43it/s]
1|24741|Loss: 0.7996054291725159:  96%|█████████▌| 24741/25880 [5:02:33<12:46,  1.49it/s]
1|24742|Loss: 0.871779203414917:  96%|█████████▌| 24741/25880 [5:02:33<12:46,  1.49it/s] 
1|24742|Loss: 0.871779203414917:  96%|█████████▌| 24742/25880 [5:02:34<12:54,  1.47it/s]
1|24743|Loss: 0.8376599550247192:  96%|█████████▌| 24742/25880 [5:02:34<12:54,  1.47it/s]
1|24743|Loss: 0.8376599550247192:  96%|█████████▌| 24743/25880 [5:02:34<13:02,  1.45it/s]
1|24744|Loss: 0.7910119891166687:  96%|█████████▌| 24743/25880 [5:02:35<13:02,  1.45it/s]
1|24744|Loss: 0.7910119891166687:  96%|█████████▌| 24744/25880 [5:02:35<13:10,  1.44it/s]
1|24745|Loss: 0.77201247215271:  96%|█████████▌| 24744/25880 [5:02:36<13:10,  1.44it/s]  
1|24745|Loss: 0.77201247215271:  96%|█████████▌| 24745/25880 [5:02:36<13:20,  1.42it/s]
1|24746|Loss: 0.907283365726471:  96%|█████████▌| 24745/25880 [5:02:36<13:20,  1.42it/s]
1|24746|Loss: 0.907283365726471:  96%|█████████▌| 24746/25880 [5:02:36<12:33,  1.50it/s]
1|24747|Loss: 0.9412764310836792:  96%|█████████▌| 24746/25880 [5:02:37<12:33,  1.50it/s]
1|24747|Loss: 0.9412764310836792:  96%|█████████▌| 24747/25880 [5:02:37<13:19,  1.42it/s]
1|24748|Loss: 0.7518879175186157:  96%|█████████▌| 24747/25880 [5:02:38<13:19,  1.42it/s]
1|24748|Loss: 0.7518879175186157:  96%|█████████▌| 24748/25880 [5:02:38<14:41,  1.28it/s]
1|24749|Loss: 0.739785373210907:  96%|█████████▌| 24748/25880 [5:02:39<14:41,  1.28it/s] 
1|24749|Loss: 0.739785373210907:  96%|█████████▌| 24749/25880 [5:02:39<14:15,  1.32it/s]
1|24750|Loss: 0.7882566452026367:  96%|█████████▌| 24749/25880 [5:02:39<14:15,  1.32it/s]
1|24750|Loss: 0.7882566452026367:  96%|█████████▌| 24750/25880 [5:02:40<14:38,  1.29it/s]
1|24751|Loss: 0.6719162464141846:  96%|█████████▌| 24750/25880 [5:02:40<14:38,  1.29it/s]
1|24751|Loss: 0.6719162464141846:  96%|█████████▌| 24751/25880 [5:02:40<14:33,  1.29it/s]
1|24752|Loss: 0.8870888352394104:  96%|█████████▌| 24751/25880 [5:02:41<14:33,  1.29it/s]
1|24752|Loss: 0.8870888352394104:  96%|█████████▌| 24752/25880 [5:02:41<13:55,  1.35it/s]
1|24753|Loss: 0.9389106035232544:  96%|█████████▌| 24752/25880 [5:02:42<13:55,  1.35it/s]
1|24753|Loss: 0.9389106035232544:  96%|█████████▌| 24753/25880 [5:02:42<14:22,  1.31it/s]
1|24754|Loss: 0.837519109249115:  96%|█████████▌| 24753/25880 [5:02:42<14:22,  1.31it/s] 
1|24754|Loss: 0.837519109249115:  96%|█████████▌| 24754/25880 [5:02:42<13:08,  1.43it/s]
1|24755|Loss: 0.7384145855903625:  96%|█████████▌| 24754/25880 [5:02:43<13:08,  1.43it/s]
1|24755|Loss: 0.7384145855903625:  96%|█████████▌| 24755/25880 [5:02:43<13:26,  1.40it/s]
1|24756|Loss: 0.6750316619873047:  96%|█████████▌| 24755/25880 [5:02:44<13:26,  1.40it/s]
1|24756|Loss: 0.6750316619873047:  96%|█████████▌| 24756/25880 [5:02:44<13:40,  1.37it/s]
1|24757|Loss: 0.7755759358406067:  96%|█████████▌| 24756/25880 [5:02:44<13:40,  1.37it/s]
1|24757|Loss: 0.7755759358406067:  96%|█████████▌| 24757/25880 [5:02:45<12:40,  1.48it/s]
1|24758|Loss: 0.8526984453201294:  96%|█████████▌| 24757/25880 [5:02:45<12:40,  1.48it/s]
1|24758|Loss: 0.8526984453201294:  96%|█████████▌| 24758/25880 [5:02:45<12:10,  1.54it/s]
1|24759|Loss: 0.6995335221290588:  96%|█████████▌| 24758/25880 [5:02:45<12:10,  1.54it/s]
1|24759|Loss: 0.6995335221290588:  96%|█████████▌| 24759/25880 [5:02:46<11:58,  1.56it/s]
1|24760|Loss: 0.8551543951034546:  96%|█████████▌| 24759/25880 [5:02:46<11:58,  1.56it/s]
1|24760|Loss: 0.8551543951034546:  96%|█████████▌| 24760/25880 [5:02:46<12:23,  1.51it/s]
1|24761|Loss: 0.8606293201446533:  96%|█████████▌| 24760/25880 [5:02:47<12:23,  1.51it/s]
1|24761|Loss: 0.8606293201446533:  96%|█████████▌| 24761/25880 [5:02:47<12:40,  1.47it/s]
1|24762|Loss: 0.7961146831512451:  96%|█████████▌| 24761/25880 [5:02:48<12:40,  1.47it/s]
1|24762|Loss: 0.7961146831512451:  96%|█████████▌| 24762/25880 [5:02:48<12:14,  1.52it/s]
1|24763|Loss: 0.796142041683197:  96%|█████████▌| 24762/25880 [5:02:48<12:14,  1.52it/s] 
1|24763|Loss: 0.796142041683197:  96%|█████████▌| 24763/25880 [5:02:48<11:57,  1.56it/s]
1|24764|Loss: 0.7820430994033813:  96%|█████████▌| 24763/25880 [5:02:49<11:57,  1.56it/s]
1|24764|Loss: 0.7820430994033813:  96%|█████████▌| 24764/25880 [5:02:49<12:11,  1.53it/s]
1|24765|Loss: 0.8770526647567749:  96%|█████████▌| 24764/25880 [5:02:50<12:11,  1.53it/s]
1|24765|Loss: 0.8770526647567749:  96%|█████████▌| 24765/25880 [5:02:50<12:38,  1.47it/s]
1|24766|Loss: 0.9311952590942383:  96%|█████████▌| 24765/25880 [5:02:50<12:38,  1.47it/s]
1|24766|Loss: 0.9311952590942383:  96%|█████████▌| 24766/25880 [5:02:51<12:34,  1.48it/s]
1|24767|Loss: 0.8496421575546265:  96%|█████████▌| 24766/25880 [5:02:51<12:34,  1.48it/s]
1|24767|Loss: 0.8496421575546265:  96%|█████████▌| 24767/25880 [5:02:51<12:50,  1.44it/s]
1|24768|Loss: 0.9253186583518982:  96%|█████████▌| 24767/25880 [5:02:52<12:50,  1.44it/s]
1|24768|Loss: 0.9253186583518982:  96%|█████████▌| 24768/25880 [5:02:52<13:04,  1.42it/s]
1|24769|Loss: 0.8332862257957458:  96%|█████████▌| 24768/25880 [5:02:52<13:04,  1.42it/s]
1|24769|Loss: 0.8332862257957458:  96%|█████████▌| 24769/25880 [5:02:53<13:40,  1.35it/s]
1|24770|Loss: 0.8783280253410339:  96%|█████████▌| 24769/25880 [5:02:53<13:40,  1.35it/s]
1|24770|Loss: 0.8783280253410339:  96%|█████████▌| 24770/25880 [5:02:54<14:16,  1.30it/s]
1|24771|Loss: 0.7522045373916626:  96%|█████████▌| 24770/25880 [5:02:54<14:16,  1.30it/s]
1|24771|Loss: 0.7522045373916626:  96%|█████████▌| 24771/25880 [5:02:54<13:19,  1.39it/s]
1|24772|Loss: 1.1066176891326904:  96%|█████████▌| 24771/25880 [5:02:55<13:19,  1.39it/s]
1|24772|Loss: 1.1066176891326904:  96%|█████████▌| 24772/25880 [5:02:55<13:11,  1.40it/s]
1|24773|Loss: 0.9366734623908997:  96%|█████████���| 24772/25880 [5:02:55<13:11,  1.40it/s]
1|24773|Loss: 0.9366734623908997:  96%|█████████▌| 24773/25880 [5:02:56<12:26,  1.48it/s]
1|24774|Loss: 0.7745686769485474:  96%|█████████▌| 24773/25880 [5:02:56<12:26,  1.48it/s]
1|24774|Loss: 0.7745686769485474:  96%|█████████▌| 24774/25880 [5:02:56<12:30,  1.47it/s]
1|24775|Loss: 0.6945918798446655:  96%|█████████▌| 24774/25880 [5:02:57<12:30,  1.47it/s]
1|24775|Loss: 0.6945918798446655:  96%|█████████▌| 24775/25880 [5:02:57<13:13,  1.39it/s]
1|24776|Loss: 0.9850354194641113:  96%|█████████▌| 24775/25880 [5:02:57<13:13,  1.39it/s]
1|24776|Loss: 0.9850354194641113:  96%|█████████▌| 24776/25880 [5:02:58<13:55,  1.32it/s]
1|24777|Loss: 0.955387532711029:  96%|█████████▌| 24776/25880 [5:02:58<13:55,  1.32it/s] 
1|24777|Loss: 0.955387532711029:  96%|█████████▌| 24777/25880 [5:02:59<13:56,  1.32it/s]
1|24778|Loss: 0.7437794804573059:  96%|█████████▌| 24777/25880 [5:02:59<13:56,  1.32it/s]
1|24778|Loss: 0.7437794804573059:  96%|█████████▌| 24778/25880 [5:02:59<13:15,  1.39it/s]
1|24779|Loss: 0.832947850227356:  96%|█████████▌| 24778/25880 [5:03:00<13:15,  1.39it/s] 
1|24779|Loss: 0.832947850227356:  96%|█████████▌| 24779/25880 [5:03:00<13:12,  1.39it/s]
1|24780|Loss: 0.6458024978637695:  96%|█████████▌| 24779/25880 [5:03:00<13:12,  1.39it/s]
1|24780|Loss: 0.6458024978637695:  96%|█████████▌| 24780/25880 [5:03:01<13:57,  1.31it/s]
1|24781|Loss: 0.9316919445991516:  96%|█████████▌| 24780/25880 [5:03:01<13:57,  1.31it/s]
1|24781|Loss: 0.9316919445991516:  96%|█████████▌| 24781/25880 [5:03:02<14:32,  1.26it/s]
1|24782|Loss: 0.8436418771743774:  96%|█████████▌| 24781/25880 [5:03:02<14:32,  1.26it/s]
1|24782|Loss: 0.8436418771743774:  96%|█████████▌| 24782/25880 [5:03:03<14:42,  1.24it/s]
1|24783|Loss: 0.7627999782562256:  96%|█████████▌| 24782/25880 [5:03:03<14:42,  1.24it/s]
1|24783|Loss: 0.7627999782562256:  96%|█████████▌| 24783/25880 [5:03:03<14:26,  1.27it/s]
1|24784|Loss: 0.8695906400680542:  96%|█████████▌| 24783/25880 [5:03:04<14:26,  1.27it/s]
1|24784|Loss: 0.8695906400680542:  96%|█████████▌| 24784/25880 [5:03:04<13:29,  1.35it/s]
1|24785|Loss: 0.8231968879699707:  96%|█████████▌| 24784/25880 [5:03:04<13:29,  1.35it/s]
1|24785|Loss: 0.8231968879699707:  96%|█████████▌| 24785/25880 [5:03:05<13:06,  1.39it/s]
1|24786|Loss: 0.7447651028633118:  96%|█████████▌| 24785/25880 [5:03:05<13:06,  1.39it/s]
1|24786|Loss: 0.7447651028633118:  96%|█████████▌| 24786/25880 [5:03:05<12:43,  1.43it/s]
1|24787|Loss: 0.906549870967865:  96%|█████████▌| 24786/25880 [5:03:06<12:43,  1.43it/s] 
1|24787|Loss: 0.906549870967865:  96%|█████████▌| 24787/25880 [5:03:06<12:41,  1.44it/s]
1|24788|Loss: 0.7856969833374023:  96%|█████████▌| 24787/25880 [5:03:06<12:41,  1.44it/s]
1|24788|Loss: 0.7856969833374023:  96%|█████████▌| 24788/25880 [5:03:07<12:51,  1.42it/s]
1|24789|Loss: 0.7537117004394531:  96%|█████████▌| 24788/25880 [5:03:07<12:51,  1.42it/s]
1|24789|Loss: 0.7537117004394531:  96%|█████████▌| 24789/25880 [5:03:07<12:12,  1.49it/s]
1|24790|Loss: 0.7494179606437683:  96%|█████████▌| 24789/25880 [5:03:08<12:12,  1.49it/s]
1|24790|Loss: 0.7494179606437683:  96%|█████████▌| 24790/25880 [5:03:08<12:25,  1.46it/s]
1|24791|Loss: 0.986366868019104:  96%|█████████▌| 24790/25880 [5:03:08<12:25,  1.46it/s] 
1|24791|Loss: 0.986366868019104:  96%|█████████▌| 24791/25880 [5:03:09<13:09,  1.38it/s]
1|24792|Loss: 0.8048567175865173:  96%|█████████▌| 24791/25880 [5:03:09<13:09,  1.38it/s]
1|24792|Loss: 0.8048567175865173:  96%|█████████▌| 24792/25880 [5:03:09<12:40,  1.43it/s]
1|24793|Loss: 0.8840401768684387:  96%|█████████▌| 24792/25880 [5:03:10<12:40,  1.43it/s]
1|24793|Loss: 0.8840401768684387:  96%|█████████▌| 24793/25880 [5:03:10<11:46,  1.54it/s]
1|24794|Loss: 0.8697881698608398:  96%|█████████▌| 24793/25880 [5:03:10<11:46,  1.54it/s]
1|24794|Loss: 0.8697881698608398:  96%|█████████▌| 24794/25880 [5:03:11<12:04,  1.50it/s]
1|24795|Loss: 0.7588416934013367:  96%|█████████▌| 24794/25880 [5:03:11<12:04,  1.50it/s]
1|24795|Loss: 0.7588416934013367:  96%|█████████▌| 24795/25880 [5:03:12<13:17,  1.36it/s]
1|24796|Loss: 0.7865752577781677:  96%|█████████▌| 24795/25880 [5:03:12<13:17,  1.36it/s]
1|24796|Loss: 0.7865752577781677:  96%|█████████▌| 24796/25880 [5:03:13<14:31,  1.24it/s]
1|24797|Loss: 0.796889066696167:  96%|█████████▌| 24796/25880 [5:03:13<14:31,  1.24it/s] 
1|24797|Loss: 0.796889066696167:  96%|█████████▌| 24797/25880 [5:03:13<13:37,  1.32it/s]
1|24798|Loss: 0.8761119246482849:  96%|█████████▌| 24797/25880 [5:03:13<13:37,  1.32it/s]
1|24798|Loss: 0.8761119246482849:  96%|█████████▌| 24798/25880 [5:03:14<12:55,  1.39it/s]
1|24799|Loss: 0.8409607410430908:  96%|█████████▌| 24798/25880 [5:03:14<12:55,  1.39it/s]
1|24799|Loss: 0.8409607410430908:  96%|█████████▌| 24799/25880 [5:03:14<12:47,  1.41it/s]
1|24800|Loss: 0.8174115419387817:  96%|█████████▌| 24799/25880 [5:03:15<12:47,  1.41it/s]
1|24800|Loss: 0.8174115419387817:  96%|█████████▌| 24800/25880 [5:03:15<12:28,  1.44it/s]
1|24801|Loss: 0.9718296527862549:  96%|█████████▌| 24800/25880 [5:03:16<12:28,  1.44it/s]
1|24801|Loss: 0.9718296527862549:  96%|█████████▌| 24801/25880 [5:03:16<12:36,  1.43it/s]
1|24802|Loss: 0.8716132044792175:  96%|█████████▌| 24801/25880 [5:03:16<12:36,  1.43it/s]
1|24802|Loss: 0.8716132044792175:  96%|█████████▌| 24802/25880 [5:03:17<12:50,  1.40it/s]
1|24803|Loss: 0.8703673481941223:  96%|█████████▌| 24802/25880 [5:03:17<12:50,  1.40it/s]
1|24803|Loss: 0.8703673481941223:  96%|█████████▌| 24803/25880 [5:03:17<13:28,  1.33it/s]
1|24804|Loss: 0.7720915079116821:  96%|█████████▌| 24803/25880 [5:03:18<13:28,  1.33it/s]
1|24804|Loss: 0.7720915079116821:  96%|█████████▌| 24804/25880 [5:03:18<13:24,  1.34it/s]
1|24805|Loss: 0.971042275428772:  96%|█████████▌| 24804/25880 [5:03:19<13:24,  1.34it/s] 
1|24805|Loss: 0.971042275428772:  96%|█████████▌| 24805/25880 [5:03:19<12:19,  1.45it/s]
1|24806|Loss: 0.8010367751121521:  96%|█████████▌| 24805/25880 [5:03:19<12:19,  1.45it/s]
1|24806|Loss: 0.8010367751121521:  96%|█████████▌| 24806/25880 [5:03:19<12:22,  1.45it/s]
1|24807|Loss: 0.8348650932312012:  96%|█████████▌| 24806/25880 [5:03:20<12:22,  1.45it/s]
1|24807|Loss: 0.8348650932312012:  96%|█████████▌| 24807/25880 [5:03:20<12:39,  1.41it/s]
1|24808|Loss: 0.856151282787323:  96%|█████████▌| 24807/25880 [5:03:21<12:39,  1.41it/s] 
1|24808|Loss: 0.856151282787323:  96%|█████████▌| 24808/25880 [5:03:21<12:22,  1.44it/s]
1|24809|Loss: 0.8639500141143799:  96%|█████████▌| 24808/25880 [5:03:21<12:22,  1.44it/s]
1|24809|Loss: 0.8639500141143799:  96%|█████████▌| 24809/25880 [5:03:22<12:51,  1.39it/s]
1|24810|Loss: 0.7600660920143127:  96%|█████████▌| 24809/25880 [5:03:22<12:51,  1.39it/s]
1|24810|Loss: 0.7600660920143127:  96%|█████████▌| 24810/25880 [5:03:22<13:26,  1.33it/s]
1|24811|Loss: 0.7616708278656006:  96%|█████████▌| 24810/25880 [5:03:23<13:26,  1.33it/s]
1|24811|Loss: 0.7616708278656006:  96%|█████████▌| 24811/25880 [5:03:23<13:48,  1.29it/s]
1|24812|Loss: 0.8337711095809937:  96%|█████████▌| 24811/25880 [5:03:24<13:48,  1.29it/s]
1|24812|Loss: 0.8337711095809937:  96%|█████████▌| 24812/25880 [5:03:24<13:39,  1.30it/s]
1|24813|Loss: 0.7652817964553833:  96%|█████████▌| 24812/25880 [5:03:24<13:39,  1.30it/s]
1|24813|Loss: 0.7652817964553833:  96%|█████████▌| 24813/25880 [5:03:25<12:46,  1.39it/s]
1|24814|Loss: 0.8652631640434265:  96%|█████████▌| 24813/25880 [5:03:25<12:46,  1.39it/s]
1|24814|Loss: 0.8652631640434265:  96%|█████████▌| 24814/25880 [5:03:25<12:15,  1.45it/s]
1|24815|Loss: 0.8147458434104919:  96%|█████████▌| 24814/25880 [5:03:26<12:15,  1.45it/s]
1|24815|Loss: 0.8147458434104919:  96%|█████████▌| 24815/25880 [5:03:26<12:47,  1.39it/s]
1|24816|Loss: 0.7882059216499329:  96%|█████████▌| 24815/25880 [5:03:26<12:47,  1.39it/s]
1|24816|Loss: 0.7882059216499329:  96%|█████████▌| 24816/25880 [5:03:27<12:31,  1.42it/s]
1|24817|Loss: 0.6934409141540527:  96%|█████████▌| 24816/25880 [5:03:27<12:31,  1.42it/s]
1|24817|Loss: 0.6934409141540527:  96%|█████████▌| 24817/25880 [5:03:27<12:09,  1.46it/s]
1|24818|Loss: 0.8403365612030029:  96%|█████████▌| 24817/25880 [5:03:28<12:09,  1.46it/s]
1|24818|Loss: 0.8403365612030029:  96%|█████████▌| 24818/25880 [5:03:28<12:16,  1.44it/s]
1|24819|Loss: 0.8647797703742981:  96%|█████████▌| 24818/25880 [5:03:28<12:16,  1.44it/s]
1|24819|Loss: 0.8647797703742981:  96%|█████████▌| 24819/25880 [5:03:29<12:31,  1.41it/s]
1|24820|Loss: 1.0272098779678345:  96%|█████████▌| 24819/25880 [5:03:29<12:31,  1.41it/s]
1|24820|Loss: 1.0272098779678345:  96%|█████████▌| 24820/25880 [5:03:29<12:15,  1.44it/s]
1|24821|Loss: 0.9344663023948669:  96%|█████████▌| 24820/25880 [5:03:30<12:15,  1.44it/s]
1|24821|Loss: 0.9344663023948669:  96%|█████████▌| 24821/25880 [5:03:30<12:13,  1.44it/s]
1|24822|Loss: 0.8342805504798889:  96%|█████████▌| 24821/25880 [5:03:31<12:13,  1.44it/s]
1|24822|Loss: 0.8342805504798889:  96%|█████████▌| 24822/25880 [5:03:31<12:14,  1.44it/s]
1|24823|Loss: 0.8768181800842285:  96%|█████████▌| 24822/25880 [5:03:31<12:14,  1.44it/s]
1|24823|Loss: 0.8768181800842285:  96%|█████████▌| 24823/25880 [5:03:32<12:43,  1.38it/s]
1|24824|Loss: 0.8403461575508118:  96%|█████████▌| 24823/25880 [5:03:32<12:43,  1.38it/s]
1|24824|Loss: 0.8403461575508118:  96%|█████████▌| 24824/25880 [5:03:32<12:50,  1.37it/s]
1|24825|Loss: 1.2631117105484009:  96%|█████████▌| 24824/25880 [5:03:33<12:50,  1.37it/s]
1|24825|Loss: 1.2631117105484009:  96%|█████████▌| 24825/25880 [5:03:33<12:49,  1.37it/s]
1|24826|Loss: 0.7915672063827515:  96%|█████████▌| 24825/25880 [5:03:33<12:49,  1.37it/s]
1|24826|Loss: 0.7915672063827515:  96%|█████████▌| 24826/25880 [5:03:34<12:25,  1.41it/s]
1|24827|Loss: 0.7933849692344666:  96%|█████████▌| 24826/25880 [5:03:34<12:25,  1.41it/s]
1|24827|Loss: 0.7933849692344666:  96%|█████████▌| 24827/25880 [5:03:34<11:48,  1.49it/s]
1|24828|Loss: 0.7569579482078552:  96%|█████████▌| 24827/25880 [5:03:35<11:48,  1.49it/s]
1|24828|Loss: 0.7569579482078552:  96%|█████████▌| 24828/25880 [5:03:35<11:34,  1.52it/s]
1|24829|Loss: 0.8102988600730896:  96%|█████████▌| 24828/25880 [5:03:35<11:34,  1.52it/s]
1|24829|Loss: 0.8102988600730896:  96%|█████████▌| 24829/25880 [5:03:36<11:51,  1.48it/s]
1|24830|Loss: 0.7896396517753601:  96%|█████████▌| 24829/25880 [5:03:36<11:51,  1.48it/s]
1|24830|Loss: 0.7896396517753601:  96%|█████████▌| 24830/25880 [5:03:36<12:09,  1.44it/s]
1|24831|Loss: 1.0032529830932617:  96%|█████████▌| 24830/25880 [5:03:37<12:09,  1.44it/s]
1|24831|Loss: 1.0032529830932617:  96%|█████████▌| 24831/25880 [5:03:37<12:22,  1.41it/s]
1|24832|Loss: 0.8487026691436768:  96%|█████████▌| 24831/25880 [5:03:38<12:22,  1.41it/s]
1|24832|Loss: 0.8487026691436768:  96%|█████████▌| 24832/25880 [5:03:38<12:35,  1.39it/s]
1|24833|Loss: 0.8528813719749451:  96%|█████████▌| 24832/25880 [5:03:38<12:35,  1.39it/s]
1|24833|Loss: 0.8528813719749451:  96%|█████████▌| 24833/25880 [5:03:39<12:04,  1.44it/s]
1|24834|Loss: 0.8873284459114075:  96%|█████████▌| 24833/25880 [5:03:39<12:04,  1.44it/s]
1|24834|Loss: 0.8873284459114075:  96%|█████████▌| 24834/25880 [5:03:39<12:21,  1.41it/s]
1|24835|Loss: 0.8894004821777344:  96%|█████████▌| 24834/25880 [5:03:40<12:21,  1.41it/s]
1|24835|Loss: 0.8894004821777344:  96%|█████████▌| 24835/25880 [5:03:40<11:42,  1.49it/s]
1|24836|Loss: 0.7633995413780212:  96%|█████████▌| 24835/25880 [5:03:40<11:42,  1.49it/s]
1|24836|Loss: 0.7633995413780212:  96%|█████████▌| 24836/25880 [5:03:40<10:14,  1.70it/s]
1|24837|Loss: 0.8704520463943481:  96%|█████████▌| 24836/25880 [5:03:41<10:14,  1.70it/s]
1|24837|Loss: 0.8704520463943481:  96%|█████████▌| 24837/25880 [5:03:41<10:29,  1.66it/s]
1|24838|Loss: 0.7853071093559265:  96%|█████████▌| 24837/25880 [5:03:41<10:29,  1.66it/s]
1|24838|Loss: 0.7853071093559265:  96%|█████████▌| 24838/25880 [5:03:42<11:34,  1.50it/s]
1|24839|Loss: 0.8646728992462158:  96%|█████████▌| 24838/25880 [5:03:42<11:34,  1.50it/s]
1|24839|Loss: 0.8646728992462158:  96%|█████████▌| 24839/25880 [5:03:43<12:06,  1.43it/s]
1|24840|Loss: 0.7592797875404358:  96%|█████████▌| 24839/25880 [5:03:43<12:06,  1.43it/s]
1|24840|Loss: 0.7592797875404358:  96%|█████████▌| 24840/25880 [5:03:43<12:17,  1.41it/s]
1|24841|Loss: 0.8036197423934937:  96%|█████████▌| 24840/25880 [5:03:44<12:17,  1.41it/s]
1|24841|Loss: 0.8036197423934937:  96%|█████████▌| 24841/25880 [5:03:44<11:59,  1.44it/s]
1|24842|Loss: 0.99394690990448:  96%|█████████▌| 24841/25880 [5:03:44<11:59,  1.44it/s]  
1|24842|Loss: 0.99394690990448:  96%|█████████▌| 24842/25880 [5:03:45<11:58,  1.44it/s]
1|24843|Loss: 0.8723418712615967:  96%|█████████▌| 24842/25880 [5:03:45<11:58,  1.44it/s]
1|24843|Loss: 0.8723418712615967:  96%|█████████▌| 24843/25880 [5:03:45<12:38,  1.37it/s]
1|24844|Loss: 0.8770718574523926:  96%|█████████▌| 24843/25880 [5:03:46<12:38,  1.37it/s]
1|24844|Loss: 0.8770718574523926:  96%|█████████▌| 24844/25880 [5:03:46<13:13,  1.31it/s]
1|24845|Loss: 0.7162283062934875:  96%|█████████▌| 24844/25880 [5:03:47<13:13,  1.31it/s]
1|24845|Loss: 0.7162283062934875:  96%|█████████▌| 24845/25880 [5:03:47<13:12,  1.31it/s]
1|24846|Loss: 0.8604431748390198:  96%|█████████▌| 24845/25880 [5:03:47<13:12,  1.31it/s]
1|24846|Loss: 0.8604431748390198:  96%|█████████▌| 24846/25880 [5:03:48<12:57,  1.33it/s]
1|24847|Loss: 0.7979443073272705:  96%|█████████▌| 24846/25880 [5:03:48<12:57,  1.33it/s]
1|24847|Loss: 0.7979443073272705:  96%|█████████▌| 24847/25880 [5:03:48<12:49,  1.34it/s]
1|24848|Loss: 0.7885909080505371:  96%|█████████▌| 24847/25880 [5:03:49<12:49,  1.34it/s]
1|24848|Loss: 0.7885909080505371:  96%|█████████▌| 24848/25880 [5:03:49<12:12,  1.41it/s]
1|24849|Loss: 0.8577579855918884:  96%|█████████▌| 24848/25880 [5:03:49<12:12,  1.41it/s]
1|24849|Loss: 0.8577579855918884:  96%|█████████▌| 24849/25880 [5:03:50<11:17,  1.52it/s]
1|24850|Loss: 0.874931812286377:  96%|█████████▌| 24849/25880 [5:03:50<11:17,  1.52it/s] 
1|24850|Loss: 0.874931812286377:  96%|█████████▌| 24850/25880 [5:03:50<11:39,  1.47it/s]
1|24851|Loss: 0.7465893030166626:  96%|█████████▌| 24850/25880 [5:03:51<11:39,  1.47it/s]
1|24851|Loss: 0.7465893030166626:  96%|█████████▌| 24851/25880 [5:03:51<11:37,  1.48it/s]
1|24852|Loss: 0.8958193063735962:  96%|█████████▌| 24851/25880 [5:03:51<11:37,  1.48it/s]
1|24852|Loss: 0.8958193063735962:  96%|█████████▌| 24852/25880 [5:03:52<11:27,  1.50it/s]
1|24853|Loss: 0.8627849221229553:  96%|█████████▌| 24852/25880 [5:03:52<11:27,  1.50it/s]
1|24853|Loss: 0.8627849221229553:  96%|█████████▌| 24853/25880 [5:03:52<11:17,  1.52it/s]
1|24854|Loss: 0.8685653209686279:  96%|█████████▌| 24853/25880 [5:03:53<11:17,  1.52it/s]
1|24854|Loss: 0.8685653209686279:  96%|█████████▌| 24854/25880 [5:03:53<10:55,  1.57it/s]
1|24855|Loss: 0.8488125801086426:  96%|█████████▌| 24854/25880 [5:03:53<10:55,  1.57it/s]
1|24855|Loss: 0.8488125801086426:  96%|█████████▌| 24855/25880 [5:03:54<11:15,  1.52it/s]
1|24856|Loss: 0.8076105713844299:  96%|█████████▌| 24855/25880 [5:03:54<11:15,  1.52it/s]
1|24856|Loss: 0.8076105713844299:  96%|█████████▌| 24856/25880 [5:03:55<13:20,  1.28it/s]
1|24857|Loss: 0.7553249001502991:  96%|█████████▌| 24856/25880 [5:03:55<13:20,  1.28it/s]
1|24857|Loss: 0.7553249001502991:  96%|█████████▌| 24857/25880 [5:03:56<13:46,  1.24it/s]
1|24858|Loss: 0.8103721141815186:  96%|█████████▌| 24857/25880 [5:03:56<13:46,  1.24it/s]
1|24858|Loss: 0.8103721141815186:  96%|█████████▌| 24858/25880 [5:03:56<12:36,  1.35it/s]
1|24859|Loss: 0.8606624603271484:  96%|█████████▌| 24858/25880 [5:03:56<12:36,  1.35it/s]
1|24859|Loss: 0.8606624603271484:  96%|█████████▌| 24859/25880 [5:03:57<11:52,  1.43it/s]
1|24860|Loss: 0.7656220197677612:  96%|█████████▌| 24859/25880 [5:03:57<11:52,  1.43it/s]
1|24860|Loss: 0.7656220197677612:  96%|█████████▌| 24860/25880 [5:03:57<11:54,  1.43it/s]
1|24861|Loss: 0.8171756267547607:  96%|█████████▌| 24860/25880 [5:03:58<11:54,  1.43it/s]
1|24861|Loss: 0.8171756267547607:  96%|█████████▌| 24861/25880 [5:03:58<11:55,  1.43it/s]
1|24862|Loss: 0.7615290284156799:  96%|█████████▌| 24861/25880 [5:03:59<11:55,  1.43it/s]
1|24862|Loss: 0.7615290284156799:  96%|█████████▌| 24862/25880 [5:03:59<11:54,  1.43it/s]
1|24863|Loss: 0.8284076452255249:  96%|█████████▌| 24862/25880 [5:03:59<11:54,  1.43it/s]
1|24863|Loss: 0.8284076452255249:  96%|█████████▌| 24863/25880 [5:03:59<11:31,  1.47it/s]
1|24864|Loss: 0.8246222138404846:  96%|█████████▌| 24863/25880 [5:04:00<11:31,  1.47it/s]
1|24864|Loss: 0.8246222138404846:  96%|█████████▌| 24864/25880 [5:04:00<11:53,  1.42it/s]
1|24865|Loss: 0.7926199436187744:  96%|█████████▌| 24864/25880 [5:04:01<11:53,  1.42it/s]
1|24865|Loss: 0.7926199436187744:  96%|█████████▌| 24865/25880 [5:04:01<12:01,  1.41it/s]
1|24866|Loss: 0.7456808090209961:  96%|█████████▌| 24865/25880 [5:04:01<12:01,  1.41it/s]
1|24866|Loss: 0.7456808090209961:  96%|█████████▌| 24866/25880 [5:04:02<12:40,  1.33it/s]
1|24867|Loss: 0.7230381369590759:  96%|█████████▌| 24866/25880 [5:04:02<12:40,  1.33it/s]
1|24867|Loss: 0.7230381369590759:  96%|█████████▌| 24867/25880 [5:04:02<12:21,  1.37it/s]
1|24868|Loss: 0.8687256574630737:  96%|█████████▌| 24867/25880 [5:04:03<12:21,  1.37it/s]
1|24868|Loss: 0.8687256574630737:  96%|█████████▌| 24868/25880 [5:04:03<12:09,  1.39it/s]
1|24869|Loss: 0.8966649174690247:  96%|█████████▌| 24868/25880 [5:04:04<12:09,  1.39it/s]
1|24869|Loss: 0.8966649174690247:  96%|█████████▌| 24869/25880 [5:04:04<12:23,  1.36it/s]
1|24870|Loss: 0.7986294031143188:  96%|█████████▌| 24869/25880 [5:04:04<12:23,  1.36it/s]
1|24870|Loss: 0.7986294031143188:  96%|█████████▌| 24870/25880 [5:04:05<11:38,  1.45it/s]
1|24871|Loss: 0.852527916431427:  96%|█████████▌| 24870/25880 [5:04:05<11:38,  1.45it/s] 
1|24871|Loss: 0.852527916431427:  96%|█████████▌| 24871/25880 [5:04:05<11:35,  1.45it/s]
1|24872|Loss: 0.8963856101036072:  96%|█████████▌| 24871/25880 [5:04:06<11:35,  1.45it/s]
1|24872|Loss: 0.8963856101036072:  96%|█████████▌| 24872/25880 [5:04:06<12:29,  1.35it/s]
1|24873|Loss: 0.9094591736793518:  96%|█████████▌| 24872/25880 [5:04:07<12:29,  1.35it/s]
1|24873|Loss: 0.9094591736793518:  96%|█████████▌| 24873/25880 [5:04:07<13:00,  1.29it/s]
1|24874|Loss: 0.8592936992645264:  96%|█████████▌| 24873/25880 [5:04:07<13:00,  1.29it/s]
1|24874|Loss: 0.8592936992645264:  96%|█████████▌| 24874/25880 [5:04:08<12:51,  1.30it/s]
1|24875|Loss: 0.7873252034187317:  96%|█████████▌| 24874/25880 [5:04:08<12:51,  1.30it/s]
1|24875|Loss: 0.7873252034187317:  96%|█████████▌| 24875/25880 [5:04:08<12:32,  1.33it/s]
1|24876|Loss: 0.6876634359359741:  96%|█████████▌| 24875/25880 [5:04:09<12:32,  1.33it/s]
1|24876|Loss: 0.6876634359359741:  96%|█████████▌| 24876/25880 [5:04:09<12:02,  1.39it/s]
1|24877|Loss: 0.9369379878044128:  96%|█████████▌| 24876/25880 [5:04:09<12:02,  1.39it/s]
1|24877|Loss: 0.9369379878044128:  96%|█████████▌| 24877/25880 [5:04:10<12:13,  1.37it/s]
1|24878|Loss: 0.8602734804153442:  96%|█████████▌| 24877/25880 [5:04:10<12:13,  1.37it/s]
1|24878|Loss: 0.8602734804153442:  96%|█████████▌| 24878/25880 [5:04:11<12:15,  1.36it/s]
1|24879|Loss: 0.8585003614425659:  96%|█████████▌| 24878/25880 [5:04:11<12:15,  1.36it/s]
1|24879|Loss: 0.8585003614425659:  96%|█████████▌| 24879/25880 [5:04:11<12:17,  1.36it/s]
1|24880|Loss: 0.8486207723617554:  96%|█████████▌| 24879/25880 [5:04:12<12:17,  1.36it/s]
1|24880|Loss: 0.8486207723617554:  96%|█████████▌| 24880/25880 [5:04:12<12:47,  1.30it/s]
1|24881|Loss: 0.8449734449386597:  96%|█████████▌| 24880/25880 [5:04:13<12:47,  1.30it/s]
1|24881|Loss: 0.8449734449386597:  96%|█████████▌| 24881/25880 [5:04:13<12:21,  1.35it/s]
1|24882|Loss: 0.8417564034461975:  96%|█████████▌| 24881/25880 [5:04:13<12:21,  1.35it/s]
1|24882|Loss: 0.8417564034461975:  96%|█████████▌| 24882/25880 [5:04:14<12:26,  1.34it/s]
1|24883|Loss: 0.8375674486160278:  96%|█████████▌| 24882/25880 [5:04:14<12:26,  1.34it/s]
1|24883|Loss: 0.8375674486160278:  96%|█████████▌| 24883/25880 [5:04:14<11:33,  1.44it/s]
1|24884|Loss: 0.8143526911735535:  96%|█████████▌| 24883/25880 [5:04:14<11:33,  1.44it/s]
1|24884|Loss: 0.8143526911735535:  96%|█████████▌| 24884/25880 [5:04:15<11:22,  1.46it/s]
1|24885|Loss: 0.9163748621940613:  96%|█████████▌| 24884/25880 [5:04:15<11:22,  1.46it/s]
1|24885|Loss: 0.9163748621940613:  96%|█████████▌| 24885/25880 [5:04:16<11:27,  1.45it/s]
1|24886|Loss: 0.9543875455856323:  96%|█████████▌| 24885/25880 [5:04:16<11:27,  1.45it/s]
1|24886|Loss: 0.9543875455856323:  96%|█████████▌| 24886/25880 [5:04:16<11:49,  1.40it/s]
1|24887|Loss: 0.7477196455001831:  96%|█████████▌| 24886/25880 [5:04:17<11:49,  1.40it/s]
1|24887|Loss: 0.7477196455001831:  96%|█████████▌| 24887/25880 [5:04:17<11:54,  1.39it/s]
1|24888|Loss: 0.9328492283821106:  96%|█████████▌| 24887/25880 [5:04:17<11:54,  1.39it/s]
1|24888|Loss: 0.9328492283821106:  96%|█████████▌| 24888/25880 [5:04:18<11:58,  1.38it/s]
1|24889|Loss: 0.8503232002258301:  96%|█████████▌| 24888/25880 [5:04:18<11:58,  1.38it/s]
1|24889|Loss: 0.8503232002258301:  96%|█████████▌| 24889/25880 [5:04:18<12:02,  1.37it/s]
1|24890|Loss: 0.7441549897193909:  96%|█████████▌| 24889/25880 [5:04:19<12:02,  1.37it/s]
1|24890|Loss: 0.7441549897193909:  96%|█████████▌| 24890/25880 [5:04:19<12:00,  1.37it/s]
1|24891|Loss: 0.8616033792495728:  96%|█████████▌| 24890/25880 [5:04:20<12:00,  1.37it/s]
1|24891|Loss: 0.8616033792495728:  96%|█████████▌| 24891/25880 [5:04:20<11:32,  1.43it/s]
1|24892|Loss: 0.7866370677947998:  96%|█████████▌| 24891/25880 [5:04:20<11:32,  1.43it/s]
1|24892|Loss: 0.7866370677947998:  96%|█████████▌| 24892/25880 [5:04:20<11:11,  1.47it/s]
1|24893|Loss: 0.8779538869857788:  96%|█████████▌| 24892/25880 [5:04:21<11:11,  1.47it/s]
1|24893|Loss: 0.8779538869857788:  96%|█████████▌| 24893/25880 [5:04:21<11:36,  1.42it/s]
1|24894|Loss: 0.8373537063598633:  96%|█████████▌| 24893/25880 [5:04:22<11:36,  1.42it/s]
1|24894|Loss: 0.8373537063598633:  96%|█████████▌| 24894/25880 [5:04:22<11:29,  1.43it/s]
1|24895|Loss: 0.7538148760795593:  96%|█████████▌| 24894/25880 [5:04:22<11:29,  1.43it/s]
1|24895|Loss: 0.7538148760795593:  96%|█████████▌| 24895/25880 [5:04:23<11:33,  1.42it/s]
1|24896|Loss: 0.808228611946106:  96%|█████████▌| 24895/25880 [5:04:23<11:33,  1.42it/s] 
1|24896|Loss: 0.808228611946106:  96%|█████████▌| 24896/25880 [5:04:23<11:42,  1.40it/s]
1|24897|Loss: 0.8168718814849854:  96%|█████████▌| 24896/25880 [5:04:24<11:42,  1.40it/s]
1|24897|Loss: 0.8168718814849854:  96%|█████████▌| 24897/25880 [5:04:24<11:27,  1.43it/s]
1|24898|Loss: 0.8356406688690186:  96%|█████████▌| 24897/25880 [5:04:24<11:27,  1.43it/s]
1|24898|Loss: 0.8356406688690186:  96%|█████████▌| 24898/25880 [5:04:25<11:46,  1.39it/s]
1|24899|Loss: 0.7801386117935181:  96%|█████████▌| 24898/25880 [5:04:25<11:46,  1.39it/s]
1|24899|Loss: 0.7801386117935181:  96%|█████████▌| 24899/25880 [5:04:26<12:26,  1.31it/s]
1|24900|Loss: 0.6784151792526245:  96%|█████████▌| 24899/25880 [5:04:26<12:26,  1.31it/s]
1|24900|Loss: 0.6784151792526245:  96%|█████████▌| 24900/25880 [5:04:26<12:21,  1.32it/s]
1|24901|Loss: 0.8878480195999146:  96%|█████████▌| 24900/25880 [5:04:27<12:21,  1.32it/s]
1|24901|Loss: 0.8878480195999146:  96%|█████████▌| 24901/25880 [5:04:27<11:22,  1.43it/s]
1|24902|Loss: 0.7238025665283203:  96%|█████████▌| 24901/25880 [5:04:27<11:22,  1.43it/s]
1|24902|Loss: 0.7238025665283203:  96%|█████████▌| 24902/25880 [5:04:28<10:48,  1.51it/s]
1|24903|Loss: 0.8570204973220825:  96%|█████████▌| 24902/25880 [5:04:28<10:48,  1.51it/s]
1|24903|Loss: 0.8570204973220825:  96%|█████████▌| 24903/25880 [5:04:28<10:31,  1.55it/s]
1|24904|Loss: 0.8540092706680298:  96%|█████████▌| 24903/25880 [5:04:29<10:31,  1.55it/s]
1|24904|Loss: 0.8540092706680298:  96%|█████████▌| 24904/25880 [5:04:29<10:18,  1.58it/s]
1|24905|Loss: 0.7184203267097473:  96%|█████████▌| 24904/25880 [5:04:29<10:18,  1.58it/s]
1|24905|Loss: 0.7184203267097473:  96%|█████████▌| 24905/25880 [5:04:29<10:29,  1.55it/s]
1|24906|Loss: 0.9046429991722107:  96%|█████████▌| 24905/25880 [5:04:30<10:29,  1.55it/s]
1|24906|Loss: 0.9046429991722107:  96%|█████████▌| 24906/25880 [5:04:30<11:24,  1.42it/s]
1|24907|Loss: 0.7288659811019897:  96%|█████████▌| 24906/25880 [5:04:31<11:24,  1.42it/s]
1|24907|Loss: 0.7288659811019897:  96%|█████████▌| 24907/25880 [5:04:31<12:03,  1.34it/s]
1|24908|Loss: 0.7894450426101685:  96%|█████████▌| 24907/25880 [5:04:32<12:03,  1.34it/s]
1|24908|Loss: 0.7894450426101685:  96%|█████████▌| 24908/25880 [5:04:32<12:26,  1.30it/s]
1|24909|Loss: 0.7472923398017883:  96%|█████████▌| 24908/25880 [5:04:32<12:26,  1.30it/s]
1|24909|Loss: 0.7472923398017883:  96%|█████████▌| 24909/25880 [5:04:33<12:19,  1.31it/s]
1|24910|Loss: 0.8752033114433289:  96%|█████████▌| 24909/25880 [5:04:33<12:19,  1.31it/s]
1|24910|Loss: 0.8752033114433289:  96%|█████████▋| 24910/25880 [5:04:33<12:09,  1.33it/s]
1|24911|Loss: 0.6973692774772644:  96%|█████████▋| 24910/25880 [5:04:34<12:09,  1.33it/s]
1|24911|Loss: 0.6973692774772644:  96%|█████████▋| 24911/25880 [5:04:34<12:04,  1.34it/s]
1|24912|Loss: 0.7944176197052002:  96%|█████████▋| 24911/25880 [5:04:35<12:04,  1.34it/s]
1|24912|Loss: 0.7944176197052002:  96%|█████████▋| 24912/25880 [5:04:35<11:40,  1.38it/s]
1|24913|Loss: 0.9670320749282837:  96%|█████████▋| 24912/25880 [5:04:35<11:40,  1.38it/s]
1|24913|Loss: 0.9670320749282837:  96%|█████████▋| 24913/25880 [5:04:36<11:53,  1.36it/s]
1|24914|Loss: 0.72318035364151:  96%|█████████▋| 24913/25880 [5:04:36<11:53,  1.36it/s]  
1|24914|Loss: 0.72318035364151:  96%|█████████▋| 24914/25880 [5:04:36<11:55,  1.35it/s]
1|24915|Loss: 0.7567927837371826:  96%|█████████▋| 24914/25880 [5:04:37<11:55,  1.35it/s]
1|24915|Loss: 0.7567927837371826:  96%|█████████▋| 24915/25880 [5:04:37<11:34,  1.39it/s]
1|24916|Loss: 0.8461712002754211:  96%|█████████▋| 24915/25880 [5:04:37<11:34,  1.39it/s]
1|24916|Loss: 0.8461712002754211:  96%|█████████▋| 24916/25880 [5:04:38<11:34,  1.39it/s]
1|24917|Loss: 0.982170820236206:  96%|█████████▋| 24916/25880 [5:04:38<11:34,  1.39it/s] 
1|24917|Loss: 0.982170820236206:  96%|█████████▋| 24917/25880 [5:04:39<12:01,  1.34it/s]
1|24918|Loss: 0.8571493625640869:  96%|█████████▋| 24917/25880 [5:04:39<12:01,  1.34it/s]
1|24918|Loss: 0.8571493625640869:  96%|█████████▋| 24918/25880 [5:04:39<11:40,  1.37it/s]
1|24919|Loss: 0.7177709937095642:  96%|█████████▋| 24918/25880 [5:04:40<11:40,  1.37it/s]
1|24919|Loss: 0.7177709937095642:  96%|█████████▋| 24919/25880 [5:04:40<11:34,  1.38it/s]
1|24920|Loss: 0.9099206924438477:  96%|█████████▋| 24919/25880 [5:04:40<11:34,  1.38it/s]
1|24920|Loss: 0.9099206924438477:  96%|█████████▋| 24920/25880 [5:04:41<12:18,  1.30it/s]
1|24921|Loss: 0.7857341766357422:  96%|█████████▋| 24920/25880 [5:04:41<12:18,  1.30it/s]
1|24921|Loss: 0.7857341766357422:  96%|█████████▋| 24921/25880 [5:04:41<10:59,  1.45it/s]
1|24922|Loss: 0.564159095287323:  96%|█████████▋| 24921/25880 [5:04:42<10:59,  1.45it/s] 
1|24922|Loss: 0.564159095287323:  96%|█████████▋| 24922/25880 [5:04:42<10:56,  1.46it/s]
1|24923|Loss: 0.9641194939613342:  96%|█████████▋| 24922/25880 [5:04:42<10:56,  1.46it/s]
1|24923|Loss: 0.9641194939613342:  96%|█████████▋| 24923/25880 [5:04:43<11:10,  1.43it/s]
1|24924|Loss: 0.8096933960914612:  96%|█████████▋| 24923/25880 [5:04:43<11:10,  1.43it/s]
1|24924|Loss: 0.8096933960914612:  96%|█████████▋| 24924/25880 [5:04:44<11:41,  1.36it/s]
1|24925|Loss: 0.9103925228118896:  96%|█████████▋| 24924/25880 [5:04:44<11:41,  1.36it/s]
1|24925|Loss: 0.9103925228118896:  96%|█████████▋| 24925/25880 [5:04:44<11:38,  1.37it/s]
1|24926|Loss: 0.8462007641792297:  96%|█████████▋| 24925/25880 [5:04:45<11:38,  1.37it/s]
1|24926|Loss: 0.8462007641792297:  96%|█████████▋| 24926/25880 [5:04:45<10:30,  1.51it/s]
1|24927|Loss: 0.9687268733978271:  96%|█████████▋| 24926/25880 [5:04:45<10:30,  1.51it/s]
1|24927|Loss: 0.9687268733978271:  96%|█████████▋| 24927/25880 [5:04:45<10:12,  1.56it/s]
1|24928|Loss: 0.7660319209098816:  96%|█████████▋| 24927/25880 [5:04:46<10:12,  1.56it/s]
1|24928|Loss: 0.7660319209098816:  96%|█████████▋| 24928/25880 [5:04:46<09:51,  1.61it/s]
1|24929|Loss: 0.822773277759552:  96%|█████████▋| 24928/25880 [5:04:46<09:51,  1.61it/s] 
1|24929|Loss: 0.822773277759552:  96%|█████████▋| 24929/25880 [5:04:47<09:51,  1.61it/s]
1|24930|Loss: 0.9471197128295898:  96%|█████████▋| 24929/25880 [5:04:47<09:51,  1.61it/s]
1|24930|Loss: 0.9471197128295898:  96%|█████████▋| 24930/25880 [5:04:47<10:16,  1.54it/s]
1|24931|Loss: 0.841128408908844:  96%|█████████▋| 24930/25880 [5:04:48<10:16,  1.54it/s] 
1|24931|Loss: 0.841128408908844:  96%|█████████▋| 24931/25880 [5:04:48<10:39,  1.48it/s]
1|24932|Loss: 0.8645566701889038:  96%|█████████▋| 24931/25880 [5:04:48<10:39,  1.48it/s]
1|24932|Loss: 0.8645566701889038:  96%|█████████▋| 24932/25880 [5:04:49<10:59,  1.44it/s]
1|24933|Loss: 0.8967114090919495:  96%|█████████▋| 24932/25880 [5:04:49<10:59,  1.44it/s]
1|24933|Loss: 0.8967114090919495:  96%|█████████▋| 24933/25880 [5:04:49<10:52,  1.45it/s]
1|24934|Loss: 0.8950092792510986:  96%|█████████▋| 24933/25880 [5:04:50<10:52,  1.45it/s]
1|24934|Loss: 0.8950092792510986:  96%|█████████▋| 24934/25880 [5:04:50<10:52,  1.45it/s]
1|24935|Loss: 0.8869203329086304:  96%|█████████▋| 24934/25880 [5:04:51<10:52,  1.45it/s]
1|24935|Loss: 0.8869203329086304:  96%|█████████▋| 24935/25880 [5:04:51<11:03,  1.42it/s]
1|24936|Loss: 0.8194834589958191:  96%|████████��▋| 24935/25880 [5:04:51<11:03,  1.42it/s]
1|24936|Loss: 0.8194834589958191:  96%|█████████▋| 24936/25880 [5:04:52<11:15,  1.40it/s]
1|24937|Loss: 0.9155464172363281:  96%|█████████▋| 24936/25880 [5:04:52<11:15,  1.40it/s]
1|24937|Loss: 0.9155464172363281:  96%|█████████▋| 24937/25880 [5:04:52<11:53,  1.32it/s]
1|24938|Loss: 0.6623811721801758:  96%|█████████▋| 24937/25880 [5:04:53<11:53,  1.32it/s]
1|24938|Loss: 0.6623811721801758:  96%|█████████▋| 24938/25880 [5:04:53<11:16,  1.39it/s]
1|24939|Loss: 0.7737772464752197:  96%|█████████▋| 24938/25880 [5:04:53<11:16,  1.39it/s]
1|24939|Loss: 0.7737772464752197:  96%|█████████▋| 24939/25880 [5:04:54<11:09,  1.40it/s]
1|24940|Loss: 0.8158895373344421:  96%|█████████▋| 24939/25880 [5:04:54<11:09,  1.40it/s]
1|24940|Loss: 0.8158895373344421:  96%|█████████▋| 24940/25880 [5:04:54<10:47,  1.45it/s]
1|24941|Loss: 0.9727900624275208:  96%|█████████▋| 24940/25880 [5:04:55<10:47,  1.45it/s]
1|24941|Loss: 0.9727900624275208:  96%|█████████▋| 24941/25880 [5:04:55<11:05,  1.41it/s]
1|24942|Loss: 0.8372319340705872:  96%|█████████▋| 24941/25880 [5:04:56<11:05,  1.41it/s]
1|24942|Loss: 0.8372319340705872:  96%|█████████▋| 24942/25880 [5:04:56<11:08,  1.40it/s]
1|24943|Loss: 0.8489530086517334:  96%|█████████▋| 24942/25880 [5:04:56<11:08,  1.40it/s]
1|24943|Loss: 0.8489530086517334:  96%|█████████▋| 24943/25880 [5:04:57<11:38,  1.34it/s]
1|24944|Loss: 0.9054577350616455:  96%|█████████▋| 24943/25880 [5:04:57<11:38,  1.34it/s]
1|24944|Loss: 0.9054577350616455:  96%|█████████▋| 24944/25880 [5:04:57<11:45,  1.33it/s]
1|24945|Loss: 0.777444064617157:  96%|█████████▋| 24944/25880 [5:04:58<11:45,  1.33it/s] 
1|24945|Loss: 0.777444064617157:  96%|█████████▋| 24945/25880 [5:04:58<11:41,  1.33it/s]
1|24946|Loss: 0.8076822757720947:  96%|█████████▋| 24945/25880 [5:04:59<11:41,  1.33it/s]
1|24946|Loss: 0.8076822757720947:  96%|█████████▋| 24946/25880 [5:04:59<11:10,  1.39it/s]
1|24947|Loss: 0.7680184841156006:  96%|█████████▋| 24946/25880 [5:04:59<11:10,  1.39it/s]
1|24947|Loss: 0.7680184841156006:  96%|█████████▋| 24947/25880 [5:04:59<10:32,  1.48it/s]
1|24948|Loss: 0.9398164749145508:  96%|█████████▋| 24947/25880 [5:05:00<10:32,  1.48it/s]
1|24948|Loss: 0.9398164749145508:  96%|█████████▋| 24948/25880 [5:05:00<11:18,  1.37it/s]
1|24949|Loss: 0.8372386693954468:  96%|█████████▋| 24948/25880 [5:05:01<11:18,  1.37it/s]
1|24949|Loss: 0.8372386693954468:  96%|█████████▋| 24949/25880 [5:05:01<11:27,  1.35it/s]
1|24950|Loss: 1.0262349843978882:  96%|█████████▋| 24949/25880 [5:05:01<11:27,  1.35it/s]
1|24950|Loss: 1.0262349843978882:  96%|█████████▋| 24950/25880 [5:05:02<11:05,  1.40it/s]
1|24951|Loss: 0.7644950151443481:  96%|█████████▋| 24950/25880 [5:05:02<11:05,  1.40it/s]
1|24951|Loss: 0.7644950151443481:  96%|█████████▋| 24951/25880 [5:05:02<10:31,  1.47it/s]
1|24952|Loss: 0.7405723333358765:  96%|█████████▋| 24951/25880 [5:05:03<10:31,  1.47it/s]
1|24952|Loss: 0.7405723333358765:  96%|█████████▋| 24952/25880 [5:05:03<10:16,  1.51it/s]
1|24953|Loss: 0.791164755821228:  96%|█████████▋| 24952/25880 [5:05:03<10:16,  1.51it/s] 
1|24953|Loss: 0.791164755821228:  96%|█████████▋| 24953/25880 [5:05:04<10:04,  1.53it/s]
1|24954|Loss: 0.6919967532157898:  96%|█████████▋| 24953/25880 [5:05:04<10:04,  1.53it/s]
1|24954|Loss: 0.6919967532157898:  96%|█████████▋| 24954/25880 [5:05:04<09:57,  1.55it/s]
1|24955|Loss: 0.958570659160614:  96%|█████████▋| 24954/25880 [5:05:05<09:57,  1.55it/s] 
1|24955|Loss: 0.958570659160614:  96%|█████████▋| 24955/25880 [5:05:05<10:59,  1.40it/s]
1|24956|Loss: 0.7493006587028503:  96%|█████████▋| 24955/25880 [5:05:06<10:59,  1.40it/s]
1|24956|Loss: 0.7493006587028503:  96%|█████████▋| 24956/25880 [5:05:06<11:27,  1.34it/s]
1|24957|Loss: 0.8734460473060608:  96%|█████████▋| 24956/25880 [5:05:06<11:27,  1.34it/s]
1|24957|Loss: 0.8734460473060608:  96%|█████████▋| 24957/25880 [5:05:07<11:49,  1.30it/s]
1|24958|Loss: 0.794491708278656:  96%|█████████▋| 24957/25880 [5:05:07<11:49,  1.30it/s] 
1|24958|Loss: 0.794491708278656:  96%|█████████▋| 24958/25880 [5:05:07<11:22,  1.35it/s]
1|24959|Loss: 0.7329648733139038:  96%|█████████▋| 24958/25880 [5:05:08<11:22,  1.35it/s]
1|24959|Loss: 0.7329648733139038:  96%|█████████▋| 24959/25880 [5:05:08<11:44,  1.31it/s]
1|24960|Loss: 0.9115479588508606:  96%|█████████▋| 24959/25880 [5:05:09<11:44,  1.31it/s]
1|24960|Loss: 0.9115479588508606:  96%|█████████▋| 24960/25880 [5:05:09<11:58,  1.28it/s]
1|24961|Loss: 0.791498601436615:  96%|█████████▋| 24960/25880 [5:05:09<11:58,  1.28it/s] 
1|24961|Loss: 0.791498601436615:  96%|█████████▋| 24961/25880 [5:05:10<12:10,  1.26it/s]
1|24962|Loss: 0.872236967086792:  96%|█████████▋| 24961/25880 [5:05:10<12:10,  1.26it/s]
1|24962|Loss: 0.872236967086792:  96%|█████████▋| 24962/25880 [5:05:11<11:36,  1.32it/s]
1|24963|Loss: 0.9000782370567322:  96%|█████████▋| 24962/25880 [5:05:11<11:36,  1.32it/s]
1|24963|Loss: 0.9000782370567322:  96%|█████████▋| 24963/25880 [5:05:11<11:02,  1.38it/s]
1|24964|Loss: 0.8826921582221985:  96%|█████████▋| 24963/25880 [5:05:12<11:02,  1.38it/s]
1|24964|Loss: 0.8826921582221985:  96%|█████████▋| 24964/25880 [5:05:12<11:39,  1.31it/s]
1|24965|Loss: 0.8238343000411987:  96%|█████████▋| 24964/25880 [5:05:12<11:39,  1.31it/s]
1|24965|Loss: 0.8238343000411987:  96%|█████████▋| 24965/25880 [5:05:13<11:33,  1.32it/s]
1|24966|Loss: 0.7819705009460449:  96%|█████████▋| 24965/25880 [5:05:13<11:33,  1.32it/s]
1|24966|Loss: 0.7819705009460449:  96%|█████████▋| 24966/25880 [5:05:13<11:01,  1.38it/s]
1|24967|Loss: 0.88875812292099:  96%|█████████▋| 24966/25880 [5:05:14<11:01,  1.38it/s]  
1|24967|Loss: 0.88875812292099:  96%|█████████▋| 24967/25880 [5:05:14<10:27,  1.45it/s]
1|24968|Loss: 0.7902388572692871:  96%|█████████▋| 24967/25880 [5:05:14<10:27,  1.45it/s]
1|24968|Loss: 0.7902388572692871:  96%|█████████▋| 24968/25880 [5:05:15<10:04,  1.51it/s]
1|24969|Loss: 0.6625820398330688:  96%|█████████▋| 24968/25880 [5:05:15<10:04,  1.51it/s]
1|24969|Loss: 0.6625820398330688:  96%|█████████▋| 24969/25880 [5:05:15<10:36,  1.43it/s]
1|24970|Loss: 0.7680505514144897:  96%|█████████▋| 24969/25880 [5:05:16<10:36,  1.43it/s]
1|24970|Loss: 0.7680505514144897:  96%|█████████▋| 24970/25880 [5:05:16<10:04,  1.50it/s]
1|24971|Loss: 0.8627169132232666:  96%|█████████▋| 24970/25880 [5:05:16<10:04,  1.50it/s]
1|24971|Loss: 0.8627169132232666:  96%|█████████▋| 24971/25880 [5:05:17<09:36,  1.58it/s]
1|24972|Loss: 0.8479302525520325:  96%|█████████▋| 24971/25880 [5:05:17<09:36,  1.58it/s]
1|24972|Loss: 0.8479302525520325:  96%|█████████▋| 24972/25880 [5:05:17<09:48,  1.54it/s]
1|24973|Loss: 0.786641538143158:  96%|█████████▋| 24972/25880 [5:05:18<09:48,  1.54it/s] 
1|24973|Loss: 0.786641538143158:  96%|█████████▋| 24973/25880 [5:05:18<09:44,  1.55it/s]
1|24974|Loss: 0.8269539475440979:  96%|█████████▋| 24973/25880 [5:05:18<09:44,  1.55it/s]
1|24974|Loss: 0.8269539475440979:  96%|█████████▋| 24974/25880 [5:05:18<09:34,  1.58it/s]
1|24975|Loss: 0.8702512979507446:  96%|█████████▋| 24974/25880 [5:05:19<09:34,  1.58it/s]
1|24975|Loss: 0.8702512979507446:  97%|█████████▋| 24975/25880 [5:05:19<09:22,  1.61it/s]
1|24976|Loss: 0.8031730055809021:  97%|█████████▋| 24975/25880 [5:05:19<09:22,  1.61it/s]
1|24976|Loss: 0.8031730055809021:  97%|█████████▋| 24976/25880 [5:05:20<09:47,  1.54it/s]
1|24977|Loss: 0.8695210814476013:  97%|█████████▋| 24976/25880 [5:05:20<09:47,  1.54it/s]
1|24977|Loss: 0.8695210814476013:  97%|█████████▋| 24977/25880 [5:05:21<10:12,  1.47it/s]
1|24978|Loss: 0.7433945536613464:  97%|█████████▋| 24977/25880 [5:05:21<10:12,  1.47it/s]
1|24978|Loss: 0.7433945536613464:  97%|█████████▋| 24978/25880 [5:05:21<10:59,  1.37it/s]
1|24979|Loss: 0.6829954385757446:  97%|█████████▋| 24978/25880 [5:05:22<10:59,  1.37it/s]
1|24979|Loss: 0.6829954385757446:  97%|█████████▋| 24979/25880 [5:05:22<10:30,  1.43it/s]
1|24980|Loss: 0.86063551902771:  97%|█████████▋| 24979/25880 [5:05:22<10:30,  1.43it/s]  
1|24980|Loss: 0.86063551902771:  97%|█████████▋| 24980/25880 [5:05:22<09:14,  1.62it/s]
1|24981|Loss: 0.8005945086479187:  97%|█████████▋| 24980/25880 [5:05:23<09:14,  1.62it/s]
1|24981|Loss: 0.8005945086479187:  97%|█████████▋| 24981/25880 [5:05:23<09:27,  1.58it/s]
1|24982|Loss: 0.9407849311828613:  97%|█████████▋| 24981/25880 [5:05:23<09:27,  1.58it/s]
1|24982|Loss: 0.9407849311828613:  97%|█████████▋| 24982/25880 [5:05:24<09:19,  1.60it/s]
1|24983|Loss: 0.7866603136062622:  97%|█████████▋| 24982/25880 [5:05:24<09:19,  1.60it/s]
1|24983|Loss: 0.7866603136062622:  97%|█████████▋| 24983/25880 [5:05:24<09:33,  1.57it/s]
1|24984|Loss: 0.9004760384559631:  97%|█████████▋| 24983/25880 [5:05:25<09:33,  1.57it/s]
1|24984|Loss: 0.9004760384559631:  97%|█████████▋| 24984/25880 [5:05:25<09:56,  1.50it/s]
1|24985|Loss: 0.8554496765136719:  97%|█████████▋| 24984/25880 [5:05:26<09:56,  1.50it/s]
1|24985|Loss: 0.8554496765136719:  97%|█████████▋| 24985/25880 [5:05:26<10:12,  1.46it/s]
1|24986|Loss: 0.8331129550933838:  97%|█████████▋| 24985/25880 [5:05:26<10:12,  1.46it/s]
1|24986|Loss: 0.8331129550933838:  97%|█████████▋| 24986/25880 [5:05:27<10:03,  1.48it/s]
1|24987|Loss: 0.9525364637374878:  97%|█████████▋| 24986/25880 [5:05:27<10:03,  1.48it/s]
1|24987|Loss: 0.9525364637374878:  97%|█████████▋| 24987/25880 [5:05:27<09:52,  1.51it/s]
1|24988|Loss: 0.7916465401649475:  97%|█████████▋| 24987/25880 [5:05:28<09:52,  1.51it/s]
1|24988|Loss: 0.7916465401649475:  97%|█████████▋| 24988/25880 [5:05:28<10:00,  1.49it/s]
1|24989|Loss: 0.8254994750022888:  97%|█████████▋| 24988/25880 [5:05:28<10:00,  1.49it/s]
1|24989|Loss: 0.8254994750022888:  97%|█████████▋| 24989/25880 [5:05:29<10:25,  1.42it/s]
1|24990|Loss: 0.9503389596939087:  97%|█████████▋| 24989/25880 [5:05:29<10:25,  1.42it/s]
1|24990|Loss: 0.9503389596939087:  97%|█████████▋| 24990/25880 [5:05:29<10:50,  1.37it/s]
1|24991|Loss: 0.7452316284179688:  97%|█████████▋| 24990/25880 [5:05:30<10:50,  1.37it/s]
1|24991|Loss: 0.7452316284179688:  97%|█████████▋| 24991/25880 [5:05:30<10:55,  1.36it/s]
1|24992|Loss: 0.8980510830879211:  97%|█████████▋| 24991/25880 [5:05:31<10:55,  1.36it/s]
1|24992|Loss: 0.8980510830879211:  97%|█████████▋| 24992/25880 [5:05:31<10:46,  1.37it/s]
1|24993|Loss: 0.8547118902206421:  97%|█████████▋| 24992/25880 [5:05:31<10:46,  1.37it/s]
1|24993|Loss: 0.8547118902206421:  97%|█████████▋| 24993/25880 [5:05:32<10:57,  1.35it/s]
1|24994|Loss: 0.7770950794219971:  97%|█████████▋| 24993/25880 [5:05:32<10:57,  1.35it/s]
1|24994|Loss: 0.7770950794219971:  97%|█████████▋| 24994/25880 [5:05:32<11:28,  1.29it/s]
1|24995|Loss: 0.937867283821106:  97%|█████████▋| 24994/25880 [5:05:33<11:28,  1.29it/s] 
1|24995|Loss: 0.937867283821106:  97%|█████████▋| 24995/25880 [5:05:33<11:00,  1.34it/s]
1|24996|Loss: 0.8836727142333984:  97%|█████████▋| 24995/25880 [5:05:34<11:00,  1.34it/s]
1|24996|Loss: 0.8836727142333984:  97%|█████████▋| 24996/25880 [5:05:34<10:25,  1.41it/s]
1|24997|Loss: 0.7368955016136169:  97%|█████████▋| 24996/25880 [5:05:34<10:25,  1.41it/s]
1|24997|Loss: 0.7368955016136169:  97%|█████████▋| 24997/25880 [5:05:35<10:26,  1.41it/s]
1|24998|Loss: 0.69585120677948:  97%|█████████▋| 24997/25880 [5:05:35<10:26,  1.41it/s]  
1|24998|Loss: 0.69585120677948:  97%|█████████▋| 24998/25880 [5:05:35<10:46,  1.36it/s]
1|24999|Loss: 0.7215890288352966:  97%|█████████▋| 24998/25880 [5:05:36<10:46,  1.36it/s]
1|24999|Loss: 0.7215890288352966:  97%|█████████▋| 24999/25880 [5:05:36<10:52,  1.35it/s]
1|25000|Loss: 0.7592124342918396:  97%|█████████▋| 24999/25880 [5:05:36<10:52,  1.35it/s]
1|25000|Loss: 0.7592124342918396:  97%|█████████▋| 25000/25880 [5:05:37<10:08,  1.45it/s]
1|25001|Loss: 0.7816978096961975:  97%|█████████▋| 25000/25880 [5:05:37<10:08,  1.45it/s]
1|25001|Loss: 0.7816978096961975:  97%|█████████▋| 25001/25880 [5:05:37<10:30,  1.39it/s]
1|25002|Loss: 0.9889203906059265:  97%|█████████▋| 25001/25880 [5:05:38<10:30,  1.39it/s]
1|25002|Loss: 0.9889203906059265:  97%|█████████▋| 25002/25880 [5:05:38<10:33,  1.39it/s]
1|25003|Loss: 0.9298969507217407:  97%|█████████▋| 25002/25880 [5:05:39<10:33,  1.39it/s]
1|25003|Loss: 0.9298969507217407:  97%|█████████▋| 25003/25880 [5:05:39<11:03,  1.32it/s]
1|25004|Loss: 0.8728060722351074:  97%|█████████▋| 25003/25880 [5:05:39<11:03,  1.32it/s]
1|25004|Loss: 0.8728060722351074:  97%|█████████▋| 25004/25880 [5:05:40<10:58,  1.33it/s]
1|25005|Loss: 0.8370834589004517:  97%|█████████▋| 25004/25880 [5:05:40<10:58,  1.33it/s]
1|25005|Loss: 0.8370834589004517:  97%|█████████▋| 25005/25880 [5:05:41<11:11,  1.30it/s]
1|25006|Loss: 0.772570788860321:  97%|��████████▋| 25005/25880 [5:05:41<11:11,  1.30it/s] 
1|25006|Loss: 0.772570788860321:  97%|█████████▋| 25006/25880 [5:05:41<11:01,  1.32it/s]
1|25007|Loss: 0.7977256774902344:  97%|█████████▋| 25006/25880 [5:05:42<11:01,  1.32it/s]
1|25007|Loss: 0.7977256774902344:  97%|█████████▋| 25007/25880 [5:05:42<11:04,  1.31it/s]
1|25008|Loss: 0.827816903591156:  97%|█████████▋| 25007/25880 [5:05:42<11:04,  1.31it/s] 
1|25008|Loss: 0.827816903591156:  97%|█████████▋| 25008/25880 [5:05:43<11:14,  1.29it/s]
1|25009|Loss: 0.741570770740509:  97%|█████████▋| 25008/25880 [5:05:43<11:14,  1.29it/s]
1|25009|Loss: 0.741570770740509:  97%|█████████▋| 25009/25880 [5:05:44<11:05,  1.31it/s]
1|25010|Loss: 0.9666426777839661:  97%|█████████▋| 25009/25880 [5:05:44<11:05,  1.31it/s]
1|25010|Loss: 0.9666426777839661:  97%|█████████▋| 25010/25880 [5:05:44<10:59,  1.32it/s]
1|25011|Loss: 0.8370162844657898:  97%|█████████▋| 25010/25880 [5:05:45<10:59,  1.32it/s]
1|25011|Loss: 0.8370162844657898:  97%|█████████▋| 25011/25880 [5:05:45<10:34,  1.37it/s]
1|25012|Loss: 0.9462751150131226:  97%|█████████▋| 25011/25880 [5:05:45<10:34,  1.37it/s]
1|25012|Loss: 0.9462751150131226:  97%|█████████▋| 25012/25880 [5:05:46<09:49,  1.47it/s]
1|25013|Loss: 0.8616486191749573:  97%|█████████▋| 25012/25880 [5:05:46<09:49,  1.47it/s]
1|25013|Loss: 0.8616486191749573:  97%|█████████▋| 25013/25880 [5:05:46<09:04,  1.59it/s]
1|25014|Loss: 0.8880670070648193:  97%|█████████▋| 25013/25880 [5:05:46<09:04,  1.59it/s]
1|25014|Loss: 0.8880670070648193:  97%|█████████▋| 25014/25880 [5:05:47<09:18,  1.55it/s]
1|25015|Loss: 0.7822139859199524:  97%|█████████▋| 25014/25880 [5:05:47<09:18,  1.55it/s]
1|25015|Loss: 0.7822139859199524:  97%|█████████▋| 25015/25880 [5:05:47<09:50,  1.46it/s]
1|25016|Loss: 1.020768404006958:  97%|█████████▋| 25015/25880 [5:05:48<09:50,  1.46it/s] 
1|25016|Loss: 1.020768404006958:  97%|█████████▋| 25016/25880 [5:05:48<09:35,  1.50it/s]
1|25017|Loss: 0.8869178891181946:  97%|█████████▋| 25016/25880 [5:05:49<09:35,  1.50it/s]
1|25017|Loss: 0.8869178891181946:  97%|█████████▋| 25017/25880 [5:05:49<10:06,  1.42it/s]
1|25018|Loss: 0.800784707069397:  97%|█████████▋| 25017/25880 [5:05:49<10:06,  1.42it/s] 
1|25018|Loss: 0.800784707069397:  97%|█████████▋| 25018/25880 [5:05:50<11:06,  1.29it/s]
1|25019|Loss: 0.8480329513549805:  97%|█████████▋| 25018/25880 [5:05:50<11:06,  1.29it/s]
1|25019|Loss: 0.8480329513549805:  97%|█████████▋| 25019/25880 [5:05:51<11:30,  1.25it/s]
1|25020|Loss: 0.7695319056510925:  97%|█████████▋| 25019/25880 [5:05:51<11:30,  1.25it/s]
1|25020|Loss: 0.7695319056510925:  97%|█████████▋| 25020/25880 [5:05:51<10:51,  1.32it/s]
1|25021|Loss: 0.768721342086792:  97%|█████████▋| 25020/25880 [5:05:52<10:51,  1.32it/s] 
1|25021|Loss: 0.768721342086792:  97%|█████████▋| 25021/25880 [5:05:52<10:38,  1.35it/s]
1|25022|Loss: 0.8686930537223816:  97%|█████████▋| 25021/25880 [5:05:52<10:38,  1.35it/s]
1|25022|Loss: 0.8686930537223816:  97%|█████████▋| 25022/25880 [5:05:53<10:14,  1.40it/s]
1|25023|Loss: 0.8454698920249939:  97%|█████████▋| 25022/25880 [5:05:53<10:14,  1.40it/s]
1|25023|Loss: 0.8454698920249939:  97%|█████████▋| 25023/25880 [5:05:53<10:23,  1.37it/s]
1|25024|Loss: 0.8389797806739807:  97%|█████████▋| 25023/25880 [5:05:54<10:23,  1.37it/s]
1|25024|Loss: 0.8389797806739807:  97%|█████████▋| 25024/25880 [5:05:54<10:05,  1.41it/s]
1|25025|Loss: 0.7437506914138794:  97%|█████████▋| 25024/25880 [5:05:55<10:05,  1.41it/s]
1|25025|Loss: 0.7437506914138794:  97%|█████████▋| 25025/25880 [5:05:55<09:42,  1.47it/s]
1|25026|Loss: 0.9443873763084412:  97%|█████████▋| 25025/25880 [5:05:55<09:42,  1.47it/s]
1|25026|Loss: 0.9443873763084412:  97%|█████████▋| 25026/25880 [5:05:55<09:44,  1.46it/s]
1|25027|Loss: 0.8071771860122681:  97%|█████████▋| 25026/25880 [5:05:56<09:44,  1.46it/s]
1|25027|Loss: 0.8071771860122681:  97%|█████████▋| 25027/25880 [5:05:56<09:53,  1.44it/s]
1|25028|Loss: 0.8322376012802124:  97%|█████████▋| 25027/25880 [5:05:57<09:53,  1.44it/s]
1|25028|Loss: 0.8322376012802124:  97%|█████████▋| 25028/25880 [5:05:57<10:04,  1.41it/s]
1|25029|Loss: 0.8782469034194946:  97%|█████████▋| 25028/25880 [5:05:57<10:04,  1.41it/s]
1|25029|Loss: 0.8782469034194946:  97%|█████████▋| 25029/25880 [5:05:58<10:36,  1.34it/s]
1|25030|Loss: 0.6630405783653259:  97%|█████████▋| 25029/25880 [5:05:58<10:36,  1.34it/s]
1|25030|Loss: 0.6630405783653259:  97%|█████████▋| 25030/25880 [5:05:58<10:21,  1.37it/s]
1|25031|Loss: 0.8703466653823853:  97%|█████████▋| 25030/25880 [5:05:59<10:21,  1.37it/s]
1|25031|Loss: 0.8703466653823853:  97%|█████████▋| 25031/25880 [5:05:59<10:16,  1.38it/s]
1|25032|Loss: 0.9276386499404907:  97%|█████████▋| 25031/25880 [5:06:00<10:16,  1.38it/s]
1|25032|Loss: 0.9276386499404907:  97%|█████████▋| 25032/25880 [5:06:00<09:55,  1.42it/s]
1|25033|Loss: 0.802861213684082:  97%|█████████▋| 25032/25880 [5:06:00<09:55,  1.42it/s] 
1|25033|Loss: 0.802861213684082:  97%|█████████▋| 25033/25880 [5:06:01<10:17,  1.37it/s]
1|25034|Loss: 0.7213007807731628:  97%|█████████▋| 25033/25880 [5:06:01<10:17,  1.37it/s]
1|25034|Loss: 0.7213007807731628:  97%|█████████▋| 25034/25880 [5:06:01<10:22,  1.36it/s]
1|25035|Loss: 0.7930318117141724:  97%|█████████▋| 25034/25880 [5:06:02<10:22,  1.36it/s]
1|25035|Loss: 0.7930318117141724:  97%|█████████▋| 25035/25880 [5:06:02<10:01,  1.40it/s]
1|25036|Loss: 0.8038565516471863:  97%|█████████▋| 25035/25880 [5:06:02<10:01,  1.40it/s]
1|25036|Loss: 0.8038565516471863:  97%|█████████▋| 25036/25880 [5:06:03<10:26,  1.35it/s]
1|25037|Loss: 0.7787288427352905:  97%|█████████▋| 25036/25880 [5:06:03<10:26,  1.35it/s]
1|25037|Loss: 0.7787288427352905:  97%|█████████▋| 25037/25880 [5:06:04<10:07,  1.39it/s]
1|25038|Loss: 0.8334610462188721:  97%|█████████▋| 25037/25880 [5:06:04<10:07,  1.39it/s]
1|25038|Loss: 0.8334610462188721:  97%|█████████▋| 25038/25880 [5:06:04<09:58,  1.41it/s]
1|25039|Loss: 0.9371293783187866:  97%|█████████▋| 25038/25880 [5:06:05<09:58,  1.41it/s]
1|25039|Loss: 0.9371293783187866:  97%|█████████▋| 25039/25880 [5:06:05<09:56,  1.41it/s]
1|25040|Loss: 1.028245449066162:  97%|█████████▋| 25039/25880 [5:06:05<09:56,  1.41it/s] 
1|25040|Loss: 1.028245449066162:  97%|█████████▋| 25040/25880 [5:06:06<10:01,  1.40it/s]
1|25041|Loss: 0.7200706005096436:  97%|█████████▋| 25040/25880 [5:06:06<10:01,  1.40it/s]
1|25041|Loss: 0.7200706005096436:  97%|█████████▋| 25041/25880 [5:06:06<09:44,  1.43it/s]
1|25042|Loss: 0.6722216010093689:  97%|█████████▋| 25041/25880 [5:06:07<09:44,  1.43it/s]
1|25042|Loss: 0.6722216010093689:  97%|█████████▋| 25042/25880 [5:06:07<09:24,  1.48it/s]
1|25043|Loss: 0.9010677933692932:  97%|█████████▋| 25042/25880 [5:06:07<09:24,  1.48it/s]
1|25043|Loss: 0.9010677933692932:  97%|█████████▋| 25043/25880 [5:06:08<09:09,  1.52it/s]
1|25044|Loss: 0.880496084690094:  97%|█████████▋| 25043/25880 [5:06:08<09:09,  1.52it/s] 
1|25044|Loss: 0.880496084690094:  97%|█████████▋| 25044/25880 [5:06:08<08:26,  1.65it/s]
1|25045|Loss: 0.9326200485229492:  97%|█████████▋| 25044/25880 [5:06:08<08:26,  1.65it/s]
1|25045|Loss: 0.9326200485229492:  97%|█████████▋| 25045/25880 [5:06:09<08:18,  1.67it/s]
1|25046|Loss: 0.8351431488990784:  97%|█████████▋| 25045/25880 [5:06:09<08:18,  1.67it/s]
1|25046|Loss: 0.8351431488990784:  97%|█████████▋| 25046/25880 [5:06:09<09:08,  1.52it/s]
1|25047|Loss: 0.7583984136581421:  97%|█████████▋| 25046/25880 [5:06:10<09:08,  1.52it/s]
1|25047|Loss: 0.7583984136581421:  97%|█████████▋| 25047/25880 [5:06:10<09:09,  1.52it/s]
1|25048|Loss: 0.7880516052246094:  97%|█████████▋| 25047/25880 [5:06:10<09:09,  1.52it/s]
1|25048|Loss: 0.7880516052246094:  97%|█████████▋| 25048/25880 [5:06:11<09:01,  1.54it/s]
1|25049|Loss: 1.007017731666565:  97%|█████████▋| 25048/25880 [5:06:11<09:01,  1.54it/s] 
1|25049|Loss: 1.007017731666565:  97%|█████████▋| 25049/25880 [5:06:11<09:15,  1.50it/s]
1|25050|Loss: 0.6824484467506409:  97%|█████████▋| 25049/25880 [5:06:12<09:15,  1.50it/s]
1|25050|Loss: 0.6824484467506409:  97%|█████████▋| 25050/25880 [5:06:12<09:54,  1.40it/s]
1|25051|Loss: 0.8507735133171082:  97%|█████████▋| 25050/25880 [5:06:13<09:54,  1.40it/s]
1|25051|Loss: 0.8507735133171082:  97%|█████████▋| 25051/25880 [5:06:13<09:59,  1.38it/s]
1|25052|Loss: 0.8806231617927551:  97%|█████████▋| 25051/25880 [5:06:13<09:59,  1.38it/s]
1|25052|Loss: 0.8806231617927551:  97%|███████���█▋| 25052/25880 [5:06:14<09:23,  1.47it/s]
1|25053|Loss: 0.8108641505241394:  97%|█████████▋| 25052/25880 [5:06:14<09:23,  1.47it/s]
1|25053|Loss: 0.8108641505241394:  97%|█████████▋| 25053/25880 [5:06:14<09:41,  1.42it/s]
1|25054|Loss: 0.9362542033195496:  97%|█████████▋| 25053/25880 [5:06:15<09:41,  1.42it/s]
1|25054|Loss: 0.9362542033195496:  97%|█████████▋| 25054/25880 [5:06:15<09:45,  1.41it/s]
1|25055|Loss: 0.9026103615760803:  97%|█████████▋| 25054/25880 [5:06:15<09:45,  1.41it/s]
1|25055|Loss: 0.9026103615760803:  97%|█████████▋| 25055/25880 [5:06:16<09:20,  1.47it/s]
1|25056|Loss: 0.9556374549865723:  97%|█████████▋| 25055/25880 [5:06:16<09:20,  1.47it/s]
1|25056|Loss: 0.9556374549865723:  97%|█████████▋| 25056/25880 [5:06:16<09:27,  1.45it/s]
1|25057|Loss: 0.8482153415679932:  97%|█████████▋| 25056/25880 [5:06:17<09:27,  1.45it/s]
1|25057|Loss: 0.8482153415679932:  97%|█████████▋| 25057/25880 [5:06:17<09:37,  1.43it/s]
1|25058|Loss: 0.814361035823822:  97%|█████████▋| 25057/25880 [5:06:17<09:37,  1.43it/s] 
1|25058|Loss: 0.814361035823822:  97%|█████████▋| 25058/25880 [5:06:18<09:00,  1.52it/s]
1|25059|Loss: 0.741412341594696:  97%|█████████▋| 25058/25880 [5:06:18<09:00,  1.52it/s]
1|25059|Loss: 0.741412341594696:  97%|█████████▋| 25059/25880 [5:06:18<09:09,  1.49it/s]
1|25060|Loss: 0.8137187957763672:  97%|█████████▋| 25059/25880 [5:06:19<09:09,  1.49it/s]
1|25060|Loss: 0.8137187957763672:  97%|█████████▋| 25060/25880 [5:06:19<09:19,  1.47it/s]
1|25061|Loss: 0.9013136029243469:  97%|█████████▋| 25060/25880 [5:06:19<09:19,  1.47it/s]
1|25061|Loss: 0.9013136029243469:  97%|█████████▋| 25061/25880 [5:06:20<09:23,  1.45it/s]
1|25062|Loss: 0.8336235284805298:  97%|█████████▋| 25061/25880 [5:06:20<09:23,  1.45it/s]
1|25062|Loss: 0.8336235284805298:  97%|█████████▋| 25062/25880 [5:06:20<09:41,  1.41it/s]
1|25063|Loss: 0.906848132610321:  97%|█████████▋| 25062/25880 [5:06:21<09:41,  1.41it/s] 
1|25063|Loss: 0.906848132610321:  97%|█████████▋| 25063/25880 [5:06:21<10:03,  1.35it/s]
1|25064|Loss: 0.795199453830719:  97%|█████████▋| 25063/25880 [5:06:22<10:03,  1.35it/s]
1|25064|Loss: 0.795199453830719:  97%|█████████▋| 25064/25880 [5:06:22<09:33,  1.42it/s]
1|25065|Loss: 0.7953171730041504:  97%|█████████▋| 25064/25880 [5:06:22<09:33,  1.42it/s]
1|25065|Loss: 0.7953171730041504:  97%|█████████▋| 25065/25880 [5:06:22<09:02,  1.50it/s]
1|25066|Loss: 0.880891740322113:  97%|█████████▋| 25065/25880 [5:06:23<09:02,  1.50it/s] 
1|25066|Loss: 0.880891740322113:  97%|█████████▋| 25066/25880 [5:06:23<08:41,  1.56it/s]
1|25067|Loss: 0.9144359827041626:  97%|█████████▋| 25066/25880 [5:06:23<08:41,  1.56it/s]
1|25067|Loss: 0.9144359827041626:  97%|█████████▋| 25067/25880 [5:06:24<08:55,  1.52it/s]
1|25068|Loss: 0.8775883913040161:  97%|█████████▋| 25067/25880 [5:06:24<08:55,  1.52it/s]
1|25068|Loss: 0.8775883913040161:  97%|█████████▋| 25068/25880 [5:06:24<08:55,  1.52it/s]
1|25069|Loss: 0.8668289184570312:  97%|█████████▋| 25068/25880 [5:06:25<08:55,  1.52it/s]
1|25069|Loss: 0.8668289184570312:  97%|█████████▋| 25069/25880 [5:06:25<08:47,  1.54it/s]
1|25070|Loss: 0.8794779777526855:  97%|█████████▋| 25069/25880 [5:06:25<08:47,  1.54it/s]
1|25070|Loss: 0.8794779777526855:  97%|█████████▋| 25070/25880 [5:06:26<09:01,  1.50it/s]
1|25071|Loss: 0.881614625453949:  97%|█████████▋| 25070/25880 [5:06:26<09:01,  1.50it/s] 
1|25071|Loss: 0.881614625453949:  97%|█████████▋| 25071/25880 [5:06:26<08:57,  1.50it/s]
1|25072|Loss: 0.9214285016059875:  97%|█████████▋| 25071/25880 [5:06:27<08:57,  1.50it/s]
1|25072|Loss: 0.9214285016059875:  97%|█████████▋| 25072/25880 [5:06:27<09:27,  1.42it/s]
1|25073|Loss: 0.8202992081642151:  97%|█████████▋| 25072/25880 [5:06:28<09:27,  1.42it/s]
1|25073|Loss: 0.8202992081642151:  97%|█████████▋| 25073/25880 [5:06:28<09:04,  1.48it/s]
1|25074|Loss: 0.7637796998023987:  97%|█████████▋| 25073/25880 [5:06:28<09:04,  1.48it/s]
1|25074|Loss: 0.7637796998023987:  97%|█████████▋| 25074/25880 [5:06:29<09:53,  1.36it/s]
1|25075|Loss: 0.8714444637298584:  97%|█████████▋| 25074/25880 [5:06:29<09:53,  1.36it/s]
1|25075|Loss: 0.8714444637298584:  97%|█████████▋| 25075/25880 [5:06:29<09:41,  1.38it/s]
1|25076|Loss: 0.8060244917869568:  97%|█████████▋| 25075/25880 [5:06:30<09:41,  1.38it/s]
1|25076|Loss: 0.8060244917869568:  97%|█████████▋| 25076/25880 [5:06:30<09:39,  1.39it/s]
1|25077|Loss: 0.7227075099945068:  97%|█████████▋| 25076/25880 [5:06:31<09:39,  1.39it/s]
1|25077|Loss: 0.7227075099945068:  97%|█████████▋| 25077/25880 [5:06:31<10:28,  1.28it/s]
1|25078|Loss: 0.8008586168289185:  97%|█████████▋| 25077/25880 [5:06:31<10:28,  1.28it/s]
1|25078|Loss: 0.8008586168289185:  97%|█████████▋| 25078/25880 [5:06:32<10:03,  1.33it/s]
1|25079|Loss: 0.7727113962173462:  97%|█████████▋| 25078/25880 [5:06:32<10:03,  1.33it/s]
1|25079|Loss: 0.7727113962173462:  97%|█████████▋| 25079/25880 [5:06:33<10:14,  1.30it/s]
1|25080|Loss: 0.8137080073356628:  97%|█████████▋| 25079/25880 [5:06:33<10:14,  1.30it/s]
1|25080|Loss: 0.8137080073356628:  97%|█████████▋| 25080/25880 [5:06:33<10:24,  1.28it/s]
1|25081|Loss: 1.011061429977417:  97%|█████████▋| 25080/25880 [5:06:34<10:24,  1.28it/s] 
1|25081|Loss: 1.011061429977417:  97%|█████████▋| 25081/25880 [5:06:34<10:16,  1.30it/s]
1|25082|Loss: 0.8873904347419739:  97%|█████████▋| 25081/25880 [5:06:35<10:16,  1.30it/s]
1|25082|Loss: 0.8873904347419739:  97%|█████████▋| 25082/25880 [5:06:35<10:21,  1.28it/s]
1|25083|Loss: 0.8132045269012451:  97%|█████████▋| 25082/25880 [5:06:35<10:21,  1.28it/s]
1|25083|Loss: 0.8132045269012451:  97%|█████████▋| 25083/25880 [5:06:36<10:38,  1.25it/s]
1|25084|Loss: 0.7505381107330322:  97%|█████████▋| 25083/25880 [5:06:36<10:38,  1.25it/s]
1|25084|Loss: 0.7505381107330322:  97%|█████████▋| 25084/25880 [5:06:37<10:48,  1.23it/s]
1|25085|Loss: 1.0580430030822754:  97%|█████████▋| 25084/25880 [5:06:37<10:48,  1.23it/s]
1|25085|Loss: 1.0580430030822754:  97%|█████████▋| 25085/25880 [5:06:37<10:31,  1.26it/s]
1|25086|Loss: 0.7609255909919739:  97%|█████████▋| 25085/25880 [5:06:38<10:31,  1.26it/s]
1|25086|Loss: 0.7609255909919739:  97%|█████████▋| 25086/25880 [5:06:38<09:58,  1.33it/s]
1|25087|Loss: 0.7870478630065918:  97%|█████████▋| 25086/25880 [5:06:38<09:58,  1.33it/s]
1|25087|Loss: 0.7870478630065918:  97%|█████████▋| 25087/25880 [5:06:39<09:43,  1.36it/s]
1|25088|Loss: 0.7577894330024719:  97%|█████████▋| 25087/25880 [5:06:39<09:43,  1.36it/s]
1|25088|Loss: 0.7577894330024719:  97%|█████████▋| 25088/25880 [5:06:40<10:15,  1.29it/s]
1|25089|Loss: 0.842377781867981:  97%|█████████▋| 25088/25880 [5:06:40<10:15,  1.29it/s] 
1|25089|Loss: 0.842377781867981:  97%|█████████▋| 25089/25880 [5:06:40<10:07,  1.30it/s]
1|25090|Loss: 0.8231174349784851:  97%|█████████▋| 25089/25880 [5:06:41<10:07,  1.30it/s]
1|25090|Loss: 0.8231174349784851:  97%|█████████▋| 25090/25880 [5:06:41<09:09,  1.44it/s]
1|25091|Loss: 0.890816867351532:  97%|█████████▋| 25090/25880 [5:06:41<09:09,  1.44it/s] 
1|25091|Loss: 0.890816867351532:  97%|█████████▋| 25091/25880 [5:06:42<09:07,  1.44it/s]
1|25092|Loss: 0.8411199450492859:  97%|█████████▋| 25091/25880 [5:06:42<09:07,  1.44it/s]
1|25092|Loss: 0.8411199450492859:  97%|█████████▋| 25092/25880 [5:06:42<08:59,  1.46it/s]
1|25093|Loss: 0.8572574853897095:  97%|█████████▋| 25092/25880 [5:06:42<08:59,  1.46it/s]
1|25093|Loss: 0.8572574853897095:  97%|█████████▋| 25093/25880 [5:06:43<08:12,  1.60it/s]
1|25094|Loss: 0.7946997880935669:  97%|█████████▋| 25093/25880 [5:06:43<08:12,  1.60it/s]
1|25094|Loss: 0.7946997880935669:  97%|█████████▋| 25094/25880 [5:06:43<08:21,  1.57it/s]
1|25095|Loss: 0.9043921232223511:  97%|█████████▋| 25094/25880 [5:06:44<08:21,  1.57it/s]
1|25095|Loss: 0.9043921232223511:  97%|█████████▋| 25095/25880 [5:06:44<08:21,  1.56it/s]
1|25096|Loss: 0.8524346947669983:  97%|█████████▋| 25095/25880 [5:06:44<08:21,  1.56it/s]
1|25096|Loss: 0.8524346947669983:  97%|█████████▋| 25096/25880 [5:06:45<09:23,  1.39it/s]
1|25097|Loss: 0.9194741249084473:  97%|█████████▋| 25096/25880 [5:06:45<09:23,  1.39it/s]
1|25097|Loss: 0.9194741249084473:  97%|█████████▋| 25097/25880 [5:06:46<09:08,  1.43it/s]
1|25098|Loss: 0.7792887091636658:  97%|█████████▋| 25097/25880 [5:06:46<09:08,  1.43it/s]
1|25098|Loss: 0.7792887091636658:  97%|█████████▋| 25098/25880 [5:06:46<08:38,  1.51it/s]
1|25099|Loss: 0.86698979139328:  97%|█████████▋| 25098/25880 [5:06:46<08:38,  1.51it/s]  
1|25099|Loss: 0.86698979139328:  97%|█████████▋| 25099/25880 [5:06:47<08:49,  1.48it/s]
1|25100|Loss: 0.9326668381690979:  97%|█████████▋| 25099/25880 [5:06:47<08:49,  1.48it/s]
1|25100|Loss: 0.9326668381690979:  97%|█████████▋| 25100/25880 [5:06:48<09:03,  1.44it/s]
1|25101|Loss: 0.7939949631690979:  97%|█████████▋| 25100/25880 [5:06:48<09:03,  1.44it/s]
1|25101|Loss: 0.7939949631690979:  97%|█████████▋| 25101/25880 [5:06:48<09:06,  1.43it/s]
1|25102|Loss: 0.8373465538024902:  97%|█████████▋| 25101/25880 [5:06:49<09:06,  1.43it/s]
1|25102|Loss: 0.8373465538024902:  97%|█████████▋| 25102/25880 [5:06:49<08:49,  1.47it/s]
1|25103|Loss: 0.8204325437545776:  97%|█████████▋| 25102/25880 [5:06:49<08:49,  1.47it/s]
1|25103|Loss: 0.8204325437545776:  97%|█████████▋| 25103/25880 [5:06:50<08:39,  1.50it/s]
1|25104|Loss: 0.8526178002357483:  97%|█████████▋| 25103/25880 [5:06:50<08:39,  1.50it/s]
1|25104|Loss: 0.8526178002357483:  97%|█████████▋| 25104/25880 [5:06:50<09:11,  1.41it/s]
1|25105|Loss: 0.9305639266967773:  97%|█████████▋| 25104/25880 [5:06:51<09:11,  1.41it/s]
1|25105|Loss: 0.9305639266967773:  97%|█████████▋| 25105/25880 [5:06:51<09:02,  1.43it/s]
1|25106|Loss: 0.7143665552139282:  97%|█████████▋| 25105/25880 [5:06:51<09:02,  1.43it/s]
1|25106|Loss: 0.7143665552139282:  97%|█████████▋| 25106/25880 [5:06:52<08:59,  1.44it/s]
1|25107|Loss: 0.7736802101135254:  97%|█████████▋| 25106/25880 [5:06:52<08:59,  1.44it/s]
1|25107|Loss: 0.7736802101135254:  97%|█████████▋| 25107/25880 [5:06:53<09:50,  1.31it/s]
1|25108|Loss: 0.7527580261230469:  97%|█████████▋| 25107/25880 [5:06:53<09:50,  1.31it/s]
1|25108|Loss: 0.7527580261230469:  97%|█████████▋| 25108/25880 [5:06:54<10:20,  1.24it/s]
1|25109|Loss: 0.8048524260520935:  97%|█████████▋| 25108/25880 [5:06:54<10:20,  1.24it/s]
1|25109|Loss: 0.8048524260520935:  97%|█████████▋| 25109/25880 [5:06:54<10:04,  1.28it/s]
1|25110|Loss: 0.9077579379081726:  97%|█████████▋| 25109/25880 [5:06:55<10:04,  1.28it/s]
1|25110|Loss: 0.9077579379081726:  97%|█████████▋| 25110/25880 [5:06:55<09:43,  1.32it/s]
1|25111|Loss: 0.8421143293380737:  97%|█████████▋| 25110/25880 [5:06:55<09:43,  1.32it/s]
1|25111|Loss: 0.8421143293380737:  97%|█████████▋| 25111/25880 [5:06:56<09:18,  1.38it/s]
1|25112|Loss: 0.9370672702789307:  97%|█████████▋| 25111/25880 [5:06:56<09:18,  1.38it/s]
1|25112|Loss: 0.9370672702789307:  97%|█████████▋| 25112/25880 [5:06:56<08:36,  1.49it/s]
1|25113|Loss: 0.8835451006889343:  97%|█████████▋| 25112/25880 [5:06:57<08:36,  1.49it/s]
1|25113|Loss: 0.8835451006889343:  97%|█████████▋| 25113/25880 [5:06:57<08:39,  1.48it/s]
1|25114|Loss: 0.9049107432365417:  97%|█████████▋| 25113/25880 [5:06:57<08:39,  1.48it/s]
1|25114|Loss: 0.9049107432365417:  97%|█████████▋| 25114/25880 [5:06:58<09:01,  1.41it/s]
1|25115|Loss: 0.798586368560791:  97%|█████████▋| 25114/25880 [5:06:58<09:01,  1.41it/s] 
1|25115|Loss: 0.798586368560791:  97%|█████████▋| 25115/25880 [5:06:58<09:31,  1.34it/s]
1|25116|Loss: 0.8575516939163208:  97%|█████████▋| 25115/25880 [5:06:59<09:31,  1.34it/s]
1|25116|Loss: 0.8575516939163208:  97%|█████████▋| 25116/25880 [5:06:59<09:27,  1.35it/s]
1|25117|Loss: 0.7534651756286621:  97%|█████████▋| 25116/25880 [5:07:00<09:27,  1.35it/s]
1|25117|Loss: 0.7534651756286621:  97%|█████████▋| 25117/25880 [5:07:00<09:57,  1.28it/s]
1|25118|Loss: 0.7799067497253418:  97%|█████████▋| 25117/25880 [5:07:01<09:57,  1.28it/s]
1|25118|Loss: 0.7799067497253418:  97%|█████████▋| 25118/25880 [5:07:01<09:54,  1.28it/s]
1|25119|Loss: 0.9102705717086792:  97%|█████████▋| 25118/25880 [5:07:01<09:54,  1.28it/s]
1|25119|Loss: 0.9102705717086792:  97%|█████████▋| 25119/25880 [5:07:02<10:03,  1.26it/s]
1|25120|Loss: 0.7952783107757568:  97%|█████████▋| 25119/25880 [5:07:02<10:03,  1.26it/s]
1|25120|Loss: 0.7952783107757568:  97%|█████████▋| 25120/25880 [5:07:02<09:13,  1.37it/s]
1|25121|Loss: 0.924440324306488:  97%|█████████▋| 25120/25880 [5:07:03<09:13,  1.37it/s] 
1|25121|Loss: 0.924440324306488:  97%|█████████▋| 25121/25880 [5:07:03<09:06,  1.39it/s]
1|25122|Loss: 0.7237597703933716:  97%|█████████▋| 25121/25880 [5:07:03<09:06,  1.39it/s]
1|25122|Loss: 0.7237597703933716:  97%|█████████▋| 25122/25880 [5:07:04<09:37,  1.31it/s]
1|25123|Loss: 0.8921573758125305:  97%|█████████▋| 25122/25880 [5:07:04<09:37,  1.31it/s]
1|25123|Loss: 0.8921573758125305:  97%|█████████▋| 25123/25880 [5:07:05<09:21,  1.35it/s]
1|25124|Loss: 0.7917751669883728:  97%|█████████▋| 25123/25880 [5:07:05<09:21,  1.35it/s]
1|25124|Loss: 0.7917751669883728:  97%|█████████▋| 25124/25880 [5:07:05<09:14,  1.36it/s]
1|25125|Loss: 0.842133641242981:  97%|█████████▋| 25124/25880 [5:07:06<09:14,  1.36it/s] 
1|25125|Loss: 0.842133641242981:  97%|█████████▋| 25125/25880 [5:07:06<09:13,  1.36it/s]
1|25126|Loss: 0.9400773644447327:  97%|█████████▋| 25125/25880 [5:07:06<09:13,  1.36it/s]
1|25126|Loss: 0.9400773644447327:  97%|█████████▋| 25126/25880 [5:07:07<08:57,  1.40it/s]
1|25127|Loss: 0.831553041934967:  97%|█████████▋| 25126/25880 [5:07:07<08:57,  1.40it/s] 
1|25127|Loss: 0.831553041934967:  97%|█████████▋| 25127/25880 [5:07:07<08:40,  1.45it/s]
1|25128|Loss: 0.9316507577896118:  97%|█████████▋| 25127/25880 [5:07:08<08:40,  1.45it/s]
1|25128|Loss: 0.9316507577896118:  97%|█████████▋| 25128/25880 [5:07:08<08:28,  1.48it/s]
1|25129|Loss: 0.8674566149711609:  97%|█████████▋| 25128/25880 [5:07:08<08:28,  1.48it/s]
1|25129|Loss: 0.8674566149711609:  97%|█████████▋| 25129/25880 [5:07:09<08:32,  1.46it/s]
1|25130|Loss: 0.8539128303527832:  97%|█████████▋| 25129/25880 [5:07:09<08:32,  1.46it/s]
1|25130|Loss: 0.8539128303527832:  97%|█████████▋| 25130/25880 [5:07:09<09:06,  1.37it/s]
1|25131|Loss: 0.8092238903045654:  97%|█████████▋| 25130/25880 [5:07:10<09:06,  1.37it/s]
1|25131|Loss: 0.8092238903045654:  97%|█████████▋| 25131/25880 [5:07:10<09:07,  1.37it/s]
1|25132|Loss: 0.8893104195594788:  97%|█████████▋| 25131/25880 [5:07:11<09:07,  1.37it/s]
1|25132|Loss: 0.8893104195594788:  97%|█████████▋| 25132/25880 [5:07:11<09:04,  1.37it/s]
1|25133|Loss: 0.8488028049468994:  97%|█████████▋| 25132/25880 [5:07:11<09:04,  1.37it/s]
1|25133|Loss: 0.8488028049468994:  97%|█████████▋| 25133/25880 [5:07:12<09:06,  1.37it/s]
1|25134|Loss: 0.7777737379074097:  97%|█████████▋| 25133/25880 [5:07:12<09:06,  1.37it/s]
1|25134|Loss: 0.7777737379074097:  97%|█████████▋| 25134/25880 [5:07:13<09:48,  1.27it/s]
1|25135|Loss: 0.7410740852355957:  97%|█████████▋| 25134/25880 [5:07:13<09:48,  1.27it/s]
1|25135|Loss: 0.7410740852355957:  97%|█████████▋| 25135/25880 [5:07:13<09:18,  1.33it/s]
1|25136|Loss: 0.8524587750434875:  97%|█████████▋| 25135/25880 [5:07:14<09:18,  1.33it/s]
1|25136|Loss: 0.8524587750434875:  97%|█████████▋| 25136/25880 [5:07:14<09:27,  1.31it/s]
1|25137|Loss: 0.9077989459037781:  97%|█████████▋| 25136/25880 [5:07:14<09:27,  1.31it/s]
1|25137|Loss: 0.9077989459037781:  97%|█████████▋| 25137/25880 [5:07:15<09:27,  1.31it/s]
1|25138|Loss: 0.8963068723678589:  97%|█████████▋| 25137/25880 [5:07:15<09:27,  1.31it/s]
1|25138|Loss: 0.8963068723678589:  97%|█████████▋| 25138/25880 [5:07:16<09:33,  1.29it/s]
1|25139|Loss: 0.8277987241744995:  97%|█████████▋| 25138/25880 [5:07:16<09:33,  1.29it/s]
1|25139|Loss: 0.8277987241744995:  97%|█████████▋| 25139/25880 [5:07:16<09:08,  1.35it/s]
1|25140|Loss: 0.8687633872032166:  97%|█████████▋| 25139/25880 [5:07:17<09:08,  1.35it/s]
1|25140|Loss: 0.8687633872032166:  97%|█████████▋| 25140/25880 [5:07:17<09:04,  1.36it/s]
1|25141|Loss: 1.0156546831130981:  97%|█████████▋| 25140/25880 [5:07:17<09:04,  1.36it/s]
1|25141|Loss: 1.0156546831130981:  97%|█████████▋| 25141/25880 [5:07:18<09:00,  1.37it/s]
1|25142|Loss: 0.7733632922172546:  97%|█████████▋| 25141/25880 [5:07:18<09:00,  1.37it/s]
1|25142|Loss: 0.7733632922172546:  97%|█████████▋| 25142/25880 [5:07:19<09:20,  1.32it/s]
1|25143|Loss: 0.9215192198753357:  97%|█████████▋| 25142/25880 [5:07:19<09:20,  1.32it/s]
1|25143|Loss: 0.9215192198753357:  97%|█████████▋| 25143/25880 [5:07:19<10:01,  1.23it/s]
1|25144|Loss: 0.8277669548988342:  97%|█████████▋| 25143/25880 [5:07:20<10:01,  1.23it/s]
1|25144|Loss: 0.8277669548988342:  97%|█████████▋| 25144/25880 [5:07:20<09:52,  1.24it/s]
1|25145|Loss: 0.8483033776283264:  97%|█████████▋| 25144/25880 [5:07:21<09:52,  1.24it/s]
1|25145|Loss: 0.8483033776283264:  97%|█████████▋| 25145/25880 [5:07:21<09:37,  1.27it/s]
1|25146|Loss: 0.8869083523750305:  97%|█████████▋| 25145/25880 [5:07:21<09:37,  1.27it/s]
1|25146|Loss: 0.8869083523750305:  97%|█████████▋| 25146/25880 [5:07:22<09:44,  1.26it/s]
1|25147|Loss: 0.9228123426437378:  97%|█████████▋| 25146/25880 [5:07:22<09:44,  1.26it/s]
1|25147|Loss: 0.9228123426437378:  97%|█████████▋| 25147/25880 [5:07:23<09:45,  1.25it/s]
1|25148|Loss: 0.972445011138916:  97%|█████████▋| 25147/25880 [5:07:23<09:45,  1.25it/s] 
1|25148|Loss: 0.972445011138916:  97%|█████████▋| 25148/25880 [5:07:23<09:16,  1.32it/s]
1|25149|Loss: 0.9048604369163513:  97%|█████████▋| 25148/25880 [5:07:24<09:16,  1.32it/s]
1|25149|Loss: 0.9048604369163513:  97%|█████████▋| 25149/25880 [5:07:24<09:05,  1.34it/s]
1|25150|Loss: 0.8227770924568176:  97%|█████████▋| 25149/25880 [5:07:24<09:05,  1.34it/s]
1|25150|Loss: 0.8227770924568176:  97%|█████████▋| 25150/25880 [5:07:25<08:37,  1.41it/s]
1|25151|Loss: 0.7815845608711243:  97%|█████████▋| 25150/25880 [5:07:25<08:37,  1.41it/s]
1|25151|Loss: 0.7815845608711243:  97%|█████████▋| 25151/25880 [5:07:26<09:15,  1.31it/s]
1|25152|Loss: 0.8536120057106018:  97%|█████████▋| 25151/25880 [5:07:26<09:15,  1.31it/s]
1|25152|Loss: 0.8536120057106018:  97%|█████████▋| 25152/25880 [5:07:26<09:20,  1.30it/s]
1|25153|Loss: 0.7379492521286011:  97%|█████████▋| 25152/25880 [5:07:27<09:20,  1.30it/s]
1|25153|Loss: 0.7379492521286011:  97%|█████████▋| 25153/25880 [5:07:27<09:12,  1.32it/s]
1|25154|Loss: 0.7310391664505005:  97%|█████████▋| 25153/25880 [5:07:27<09:12,  1.32it/s]
1|25154|Loss: 0.7310391664505005:  97%|█████████▋| 25154/25880 [5:07:28<08:29,  1.42it/s]
1|25155|Loss: 0.7579132914543152:  97%|█████████▋| 25154/25880 [5:07:28<08:29,  1.42it/s]
1|25155|Loss: 0.7579132914543152:  97%|█████████▋| 25155/25880 [5:07:28<07:49,  1.54it/s]
1|25156|Loss: 0.7891095876693726:  97%|█████████▋| 25155/25880 [5:07:28<07:49,  1.54it/s]
1|25156|Loss: 0.7891095876693726:  97%|█████████▋| 25156/25880 [5:07:29<07:38,  1.58it/s]
1|25157|Loss: 0.8358110785484314:  97%|█████████▋| 25156/25880 [5:07:29<07:38,  1.58it/s]
1|25157|Loss: 0.8358110785484314:  97%|█████████▋| 25157/25880 [5:07:29<07:38,  1.58it/s]
1|25158|Loss: 0.7462681531906128:  97%|█████████▋| 25157/25880 [5:07:30<07:38,  1.58it/s]
1|25158|Loss: 0.7462681531906128:  97%|█████████▋| 25158/25880 [5:07:30<08:21,  1.44it/s]
1|25159|Loss: 0.7406237721443176:  97%|█████████▋| 25158/25880 [5:07:31<08:21,  1.44it/s]
1|25159|Loss: 0.7406237721443176:  97%|█████████▋| 25159/25880 [5:07:31<08:38,  1.39it/s]
1|25160|Loss: 0.8756064772605896:  97%|█████████▋| 25159/25880 [5:07:31<08:38,  1.39it/s]
1|25160|Loss: 0.8756064772605896:  97%|█████████▋| 25160/25880 [5:07:32<08:52,  1.35it/s]
1|25161|Loss: 0.8397819995880127:  97%|█████████▋| 25160/25880 [5:07:32<08:52,  1.35it/s]
1|25161|Loss: 0.8397819995880127:  97%|█████████▋| 25161/25880 [5:07:33<08:54,  1.34it/s]
1|25162|Loss: 0.7578677535057068:  97%|█████████▋| 25161/25880 [5:07:33<08:54,  1.34it/s]
1|25162|Loss: 0.7578677535057068:  97%|█████████▋| 25162/25880 [5:07:33<09:01,  1.33it/s]
1|25163|Loss: 0.7125723361968994:  97%|█████████▋| 25162/25880 [5:07:34<09:01,  1.33it/s]
1|25163|Loss: 0.7125723361968994:  97%|█████████▋| 25163/25880 [5:07:34<09:23,  1.27it/s]
1|25164|Loss: 0.9088090658187866:  97%|█████████▋| 25163/25880 [5:07:35<09:23,  1.27it/s]
1|25164|Loss: 0.9088090658187866:  97%|█████████▋| 25164/25880 [5:07:35<09:34,  1.25it/s]
1|25165|Loss: 0.6767293214797974:  97%|█████████▋| 25164/25880 [5:07:35<09:34,  1.25it/s]
1|25165|Loss: 0.6767293214797974:  97%|█████████▋| 25165/25880 [5:07:36<09:16,  1.29it/s]
1|25166|Loss: 0.823669970035553:  97%|█████████▋| 25165/25880 [5:07:36<09:16,  1.29it/s] 
1|25166|Loss: 0.823669970035553:  97%|█████████▋| 25166/25880 [5:07:36<09:06,  1.31it/s]
1|25167|Loss: 0.869286298751831:  97%|█████████▋| 25166/25880 [5:07:37<09:06,  1.31it/s]
1|25167|Loss: 0.869286298751831:  97%|█████████▋| 25167/25880 [5:07:37<09:00,  1.32it/s]
1|25168|Loss: 0.7647191286087036:  97%|█████████▋| 25167/25880 [5:07:38<09:00,  1.32it/s]
1|25168|Loss: 0.7647191286087036:  97%|█████████▋| 25168/25880 [5:07:38<08:34,  1.38it/s]
1|25169|Loss: 0.8613471388816833:  97%|████���████▋| 25168/25880 [5:07:38<08:34,  1.38it/s]
1|25169|Loss: 0.8613471388816833:  97%|█████████▋| 25169/25880 [5:07:38<08:04,  1.47it/s]
1|25170|Loss: 0.7714370489120483:  97%|█████████▋| 25169/25880 [5:07:39<08:04,  1.47it/s]
1|25170|Loss: 0.7714370489120483:  97%|█████████▋| 25170/25880 [5:07:39<08:07,  1.46it/s]
1|25171|Loss: 0.7796134948730469:  97%|█████████▋| 25170/25880 [5:07:39<08:07,  1.46it/s]
1|25171|Loss: 0.7796134948730469:  97%|█████████▋| 25171/25880 [5:07:40<07:56,  1.49it/s]
1|25172|Loss: 0.8442863821983337:  97%|█████████▋| 25171/25880 [5:07:40<07:56,  1.49it/s]
1|25172|Loss: 0.8442863821983337:  97%|█████████▋| 25172/25880 [5:07:40<08:12,  1.44it/s]
1|25173|Loss: 0.7940653562545776:  97%|█████████▋| 25172/25880 [5:07:41<08:12,  1.44it/s]
1|25173|Loss: 0.7940653562545776:  97%|█████████▋| 25173/25880 [5:07:41<08:04,  1.46it/s]
1|25174|Loss: 0.8520593047142029:  97%|█████████▋| 25173/25880 [5:07:42<08:04,  1.46it/s]
1|25174|Loss: 0.8520593047142029:  97%|█████████▋| 25174/25880 [5:07:42<08:03,  1.46it/s]
1|25175|Loss: 0.9328955411911011:  97%|█████████▋| 25174/25880 [5:07:42<08:03,  1.46it/s]
1|25175|Loss: 0.9328955411911011:  97%|█████████▋| 25175/25880 [5:07:43<08:05,  1.45it/s]
1|25176|Loss: 0.7961946725845337:  97%|█████████▋| 25175/25880 [5:07:43<08:05,  1.45it/s]
1|25176|Loss: 0.7961946725845337:  97%|█████████▋| 25176/25880 [5:07:43<07:52,  1.49it/s]
1|25177|Loss: 0.8059459328651428:  97%|█████████▋| 25176/25880 [5:07:44<07:52,  1.49it/s]
1|25177|Loss: 0.8059459328651428:  97%|█████████▋| 25177/25880 [5:07:44<08:00,  1.46it/s]
1|25178|Loss: 0.7520814538002014:  97%|█████████▋| 25177/25880 [5:07:44<08:00,  1.46it/s]
1|25178|Loss: 0.7520814538002014:  97%|█████████▋| 25178/25880 [5:07:44<07:44,  1.51it/s]
1|25179|Loss: 0.8276761770248413:  97%|█████████▋| 25178/25880 [5:07:45<07:44,  1.51it/s]
1|25179|Loss: 0.8276761770248413:  97%|█████████▋| 25179/25880 [5:07:45<07:34,  1.54it/s]
1|25180|Loss: 0.9979817271232605:  97%|█████████▋| 25179/25880 [5:07:45<07:34,  1.54it/s]
1|25180|Loss: 0.9979817271232605:  97%|█████████▋| 25180/25880 [5:07:46<07:42,  1.51it/s]
1|25181|Loss: 0.7584899067878723:  97%|█████████▋| 25180/25880 [5:07:46<07:42,  1.51it/s]
1|25181|Loss: 0.7584899067878723:  97%|█████████▋| 25181/25880 [5:07:46<07:32,  1.54it/s]
1|25182|Loss: 0.8195633292198181:  97%|█████████▋| 25181/25880 [5:07:47<07:32,  1.54it/s]
1|25182|Loss: 0.8195633292198181:  97%|█████████▋| 25182/25880 [5:07:47<07:23,  1.57it/s]
1|25183|Loss: 0.8781574964523315:  97%|█████████▋| 25182/25880 [5:07:47<07:23,  1.57it/s]
1|25183|Loss: 0.8781574964523315:  97%|█████████▋| 25183/25880 [5:07:48<08:18,  1.40it/s]
1|25184|Loss: 0.9821677207946777:  97%|█████████▋| 25183/25880 [5:07:48<08:18,  1.40it/s]
1|25184|Loss: 0.9821677207946777:  97%|█████████▋| 25184/25880 [5:07:49<08:16,  1.40it/s]
1|25185|Loss: 0.9213495850563049:  97%|█████████▋| 25184/25880 [5:07:49<08:16,  1.40it/s]
1|25185|Loss: 0.9213495850563049:  97%|█████████▋| 25185/25880 [5:07:49<08:18,  1.39it/s]
1|25186|Loss: 0.7982494235038757:  97%|█████████▋| 25185/25880 [5:07:50<08:18,  1.39it/s]
1|25186|Loss: 0.7982494235038757:  97%|█████████▋| 25186/25880 [5:07:50<08:37,  1.34it/s]
1|25187|Loss: 0.7616707682609558:  97%|█████████▋| 25186/25880 [5:07:51<08:37,  1.34it/s]
1|25187|Loss: 0.7616707682609558:  97%|█████████▋| 25187/25880 [5:07:51<08:52,  1.30it/s]
1|25188|Loss: 0.8328595161437988:  97%|█████████▋| 25187/25880 [5:07:51<08:52,  1.30it/s]
1|25188|Loss: 0.8328595161437988:  97%|█████████▋| 25188/25880 [5:07:52<09:08,  1.26it/s]
1|25189|Loss: 0.6834246516227722:  97%|█████████▋| 25188/25880 [5:07:52<09:08,  1.26it/s]
1|25189|Loss: 0.6834246516227722:  97%|█████████▋| 25189/25880 [5:07:52<07:59,  1.44it/s]
1|25190|Loss: 1.042697548866272:  97%|█████████▋| 25189/25880 [5:07:53<07:59,  1.44it/s] 
1|25190|Loss: 1.042697548866272:  97%|█████████▋| 25190/25880 [5:07:53<08:11,  1.40it/s]
1|25191|Loss: 0.8144382238388062:  97%|█████████▋| 25190/25880 [5:07:53<08:11,  1.40it/s]
1|25191|Loss: 0.8144382238388062:  97%|█████████▋| 25191/25880 [5:07:54<08:22,  1.37it/s]
1|25192|Loss: 0.7735916972160339:  97%|█████████▋| 25191/25880 [5:07:54<08:22,  1.37it/s]
1|25192|Loss: 0.7735916972160339:  97%|█████████▋| 25192/25880 [5:07:55<08:23,  1.37it/s]
1|25193|Loss: 0.9151541590690613:  97%|█████████▋| 25192/25880 [5:07:55<08:23,  1.37it/s]
1|25193|Loss: 0.9151541590690613:  97%|█████████▋| 25193/25880 [5:07:55<08:07,  1.41it/s]
1|25194|Loss: 0.8272468447685242:  97%|█████████▋| 25193/25880 [5:07:56<08:07,  1.41it/s]
1|25194|Loss: 0.8272468447685242:  97%|█████████▋| 25194/25880 [5:07:56<08:08,  1.41it/s]
1|25195|Loss: 0.8633325099945068:  97%|█████████▋| 25194/25880 [5:07:56<08:08,  1.41it/s]
1|25195|Loss: 0.8633325099945068:  97%|█████████▋| 25195/25880 [5:07:57<08:11,  1.39it/s]
1|25196|Loss: 0.8316858410835266:  97%|█████████▋| 25195/25880 [5:07:57<08:11,  1.39it/s]
1|25196|Loss: 0.8316858410835266:  97%|█████████▋| 25196/25880 [5:07:57<07:39,  1.49it/s]
1|25197|Loss: 0.7778388261795044:  97%|█████████▋| 25196/25880 [5:07:58<07:39,  1.49it/s]
1|25197|Loss: 0.7778388261795044:  97%|█████████▋| 25197/25880 [5:07:58<08:02,  1.42it/s]
1|25198|Loss: 0.8675066232681274:  97%|█████████▋| 25197/25880 [5:07:58<08:02,  1.42it/s]
1|25198|Loss: 0.8675066232681274:  97%|█████████▋| 25198/25880 [5:07:59<07:58,  1.43it/s]
1|25199|Loss: 0.8035016655921936:  97%|█████████▋| 25198/25880 [5:07:59<07:58,  1.43it/s]
1|25199|Loss: 0.8035016655921936:  97%|█████████▋| 25199/25880 [5:07:59<07:14,  1.57it/s]
1|25200|Loss: 0.9687092304229736:  97%|█████████▋| 25199/25880 [5:08:00<07:14,  1.57it/s]
1|25200|Loss: 0.9687092304229736:  97%|█████████▋| 25200/25880 [5:08:00<07:29,  1.51it/s]
1|25201|Loss: 0.7148221731185913:  97%|█████████▋| 25200/25880 [5:08:00<07:29,  1.51it/s]
1|25201|Loss: 0.7148221731185913:  97%|█████████▋| 25201/25880 [5:08:01<07:48,  1.45it/s]
1|25202|Loss: 0.8751451373100281:  97%|█████████▋| 25201/25880 [5:08:01<07:48,  1.45it/s]
1|25202|Loss: 0.8751451373100281:  97%|█████████▋| 25202/25880 [5:08:01<07:39,  1.48it/s]
1|25203|Loss: 0.7515761852264404:  97%|█████████▋| 25202/25880 [5:08:02<07:39,  1.48it/s]
1|25203|Loss: 0.7515761852264404:  97%|█████████▋| 25203/25880 [5:08:02<07:44,  1.46it/s]
1|25204|Loss: 0.7940155863761902:  97%|█████████▋| 25203/25880 [5:08:02<07:44,  1.46it/s]
1|25204|Loss: 0.7940155863761902:  97%|█████████▋| 25204/25880 [5:08:03<07:56,  1.42it/s]
1|25205|Loss: 0.8945665955543518:  97%|█████████▋| 25204/25880 [5:08:03<07:56,  1.42it/s]
1|25205|Loss: 0.8945665955543518:  97%|█████████▋| 25205/25880 [5:08:04<08:06,  1.39it/s]
1|25206|Loss: 0.833949863910675:  97%|█████████▋| 25205/25880 [5:08:04<08:06,  1.39it/s] 
1|25206|Loss: 0.833949863910675:  97%|█████████▋| 25206/25880 [5:08:04<07:55,  1.42it/s]
1|25207|Loss: 0.9535830616950989:  97%|█████████▋| 25206/25880 [5:08:05<07:55,  1.42it/s]
1|25207|Loss: 0.9535830616950989:  97%|█████████▋| 25207/25880 [5:08:05<07:20,  1.53it/s]
1|25208|Loss: 0.8144526481628418:  97%|█████████▋| 25207/25880 [5:08:05<07:20,  1.53it/s]
1|25208|Loss: 0.8144526481628418:  97%|█████████▋| 25208/25880 [5:08:05<06:50,  1.64it/s]
1|25209|Loss: 0.7753117084503174:  97%|█████████▋| 25208/25880 [5:08:06<06:50,  1.64it/s]
1|25209|Loss: 0.7753117084503174:  97%|█████████▋| 25209/25880 [5:08:06<06:50,  1.64it/s]
1|25210|Loss: 0.7879676222801208:  97%|█████████▋| 25209/25880 [5:08:06<06:50,  1.64it/s]
1|25210|Loss: 0.7879676222801208:  97%|█████████▋| 25210/25880 [5:08:07<07:19,  1.52it/s]
1|25211|Loss: 0.7612440586090088:  97%|█████████▋| 25210/25880 [5:08:07<07:19,  1.52it/s]
1|25211|Loss: 0.7612440586090088:  97%|█████████▋| 25211/25880 [5:08:07<07:40,  1.45it/s]
1|25212|Loss: 0.8011075854301453:  97%|█████████▋| 25211/25880 [5:08:08<07:40,  1.45it/s]
1|25212|Loss: 0.8011075854301453:  97%|█████████▋| 25212/25880 [5:08:08<08:09,  1.37it/s]
1|25213|Loss: 0.9340965747833252:  97%|█████████▋| 25212/25880 [5:08:09<08:09,  1.37it/s]
1|25213|Loss: 0.9340965747833252:  97%|█████████▋| 25213/25880 [5:08:09<07:55,  1.40it/s]
1|25214|Loss: 0.8526599407196045:  97%|█████████▋| 25213/25880 [5:08:09<07:55,  1.40it/s]
1|25214|Loss: 0.8526599407196045:  97%|█████████▋| 25214/25880 [5:08:10<08:31,  1.30it/s]
1|25215|Loss: 0.8435233235359192:  97%|█████████▋| 25214/25880 [5:08:10<08:31,  1.30it/s]
1|25215|Loss: 0.8435233235359192:  97%|████████���▋| 25215/25880 [5:08:10<08:15,  1.34it/s]
1|25216|Loss: 0.8921050429344177:  97%|█████████▋| 25215/25880 [5:08:11<08:15,  1.34it/s]
1|25216|Loss: 0.8921050429344177:  97%|█████████▋| 25216/25880 [5:08:11<08:22,  1.32it/s]
1|25217|Loss: 0.8802622556686401:  97%|█████████▋| 25216/25880 [5:08:12<08:22,  1.32it/s]
1|25217|Loss: 0.8802622556686401:  97%|█████████▋| 25217/25880 [5:08:12<08:30,  1.30it/s]
1|25218|Loss: 0.872255802154541:  97%|█████████▋| 25217/25880 [5:08:12<08:30,  1.30it/s] 
1|25218|Loss: 0.872255802154541:  97%|█████████▋| 25218/25880 [5:08:13<08:18,  1.33it/s]
1|25219|Loss: 0.7417066693305969:  97%|█████████▋| 25218/25880 [5:08:13<08:18,  1.33it/s]
1|25219|Loss: 0.7417066693305969:  97%|█████████▋| 25219/25880 [5:08:14<08:13,  1.34it/s]
1|25220|Loss: 0.8005840182304382:  97%|█████████▋| 25219/25880 [5:08:14<08:13,  1.34it/s]
1|25220|Loss: 0.8005840182304382:  97%|█████████▋| 25220/25880 [5:08:14<08:14,  1.34it/s]
1|25221|Loss: 0.839586615562439:  97%|█████████▋| 25220/25880 [5:08:15<08:14,  1.34it/s] 
1|25221|Loss: 0.839586615562439:  97%|█████████▋| 25221/25880 [5:08:15<08:13,  1.34it/s]
1|25222|Loss: 0.839884877204895:  97%|█████████▋| 25221/25880 [5:08:15<08:13,  1.34it/s]
1|25222|Loss: 0.839884877204895:  97%|█████████▋| 25222/25880 [5:08:16<08:32,  1.28it/s]
1|25223|Loss: 0.9336130023002625:  97%|█████████▋| 25222/25880 [5:08:16<08:32,  1.28it/s]
1|25223|Loss: 0.9336130023002625:  97%|█████████▋| 25223/25880 [5:08:17<08:05,  1.35it/s]
1|25224|Loss: 0.809971809387207:  97%|█████████▋| 25223/25880 [5:08:17<08:05,  1.35it/s] 
1|25224|Loss: 0.809971809387207:  97%|█████████▋| 25224/25880 [5:08:17<08:05,  1.35it/s]
1|25225|Loss: 0.7907018065452576:  97%|█████████▋| 25224/25880 [5:08:18<08:05,  1.35it/s]
1|25225|Loss: 0.7907018065452576:  97%|█████████▋| 25225/25880 [5:08:18<08:16,  1.32it/s]
1|25226|Loss: 0.8710528016090393:  97%|█████████▋| 25225/25880 [5:08:18<08:16,  1.32it/s]
1|25226|Loss: 0.8710528016090393:  97%|█████████▋| 25226/25880 [5:08:19<07:55,  1.38it/s]
1|25227|Loss: 0.7818053960800171:  97%|█████████▋| 25226/25880 [5:08:19<07:55,  1.38it/s]
1|25227|Loss: 0.7818053960800171:  97%|█████████▋| 25227/25880 [5:08:20<08:13,  1.32it/s]
1|25228|Loss: 0.8398393988609314:  97%|█████████▋| 25227/25880 [5:08:20<08:13,  1.32it/s]
1|25228|Loss: 0.8398393988609314:  97%|█████████▋| 25228/25880 [5:08:20<08:42,  1.25it/s]
1|25229|Loss: 0.8743654489517212:  97%|█████████▋| 25228/25880 [5:08:21<08:42,  1.25it/s]
1|25229|Loss: 0.8743654489517212:  97%|█████████▋| 25229/25880 [5:08:21<08:35,  1.26it/s]
1|25230|Loss: 0.7872905731201172:  97%|█████████▋| 25229/25880 [5:08:22<08:35,  1.26it/s]
1|25230|Loss: 0.7872905731201172:  97%|█████████▋| 25230/25880 [5:08:22<08:24,  1.29it/s]
1|25231|Loss: 0.7664324641227722:  97%|█████████▋| 25230/25880 [5:08:22<08:24,  1.29it/s]
1|25231|Loss: 0.7664324641227722:  97%|█████████▋| 25231/25880 [5:08:23<08:11,  1.32it/s]
1|25232|Loss: 0.838581383228302:  97%|█████████▋| 25231/25880 [5:08:23<08:11,  1.32it/s] 
1|25232|Loss: 0.838581383228302:  97%|█████████▋| 25232/25880 [5:08:23<07:41,  1.40it/s]
1|25233|Loss: 0.8585307002067566:  97%|█████████▋| 25232/25880 [5:08:24<07:41,  1.40it/s]
1|25233|Loss: 0.8585307002067566:  98%|█████████▊| 25233/25880 [5:08:24<08:14,  1.31it/s]
1|25234|Loss: 0.9422564506530762:  98%|█████████▊| 25233/25880 [5:08:25<08:14,  1.31it/s]
1|25234|Loss: 0.9422564506530762:  98%|█████████▊| 25234/25880 [5:08:25<08:35,  1.25it/s]
1|25235|Loss: 0.768241822719574:  98%|█████████▊| 25234/25880 [5:08:25<08:35,  1.25it/s] 
1|25235|Loss: 0.768241822719574:  98%|█████████▊| 25235/25880 [5:08:26<07:52,  1.36it/s]
1|25236|Loss: 0.8239393830299377:  98%|█████████▊| 25235/25880 [5:08:26<07:52,  1.36it/s]
1|25236|Loss: 0.8239393830299377:  98%|█████████▊| 25236/25880 [5:08:26<06:47,  1.58it/s]
1|25237|Loss: 0.8014760613441467:  98%|█████████▊| 25236/25880 [5:08:26<06:47,  1.58it/s]
1|25237|Loss: 0.8014760613441467:  98%|█████████▊| 25237/25880 [5:08:27<07:03,  1.52it/s]
1|25238|Loss: 0.8004677295684814:  98%|█████████▊| 25237/25880 [5:08:27<07:03,  1.52it/s]
1|25238|Loss: 0.8004677295684814:  98%|█████████▊| 25238/25880 [5:08:27<07:02,  1.52it/s]
1|25239|Loss: 0.7635899186134338:  98%|█████████▊| 25238/25880 [5:08:28<07:02,  1.52it/s]
1|25239|Loss: 0.7635899186134338:  98%|█████████▊| 25239/25880 [5:08:28<07:10,  1.49it/s]
1|25240|Loss: 0.8241277933120728:  98%|█████████▊| 25239/25880 [5:08:28<07:10,  1.49it/s]
1|25240|Loss: 0.8241277933120728:  98%|█████████▊| 25240/25880 [5:08:29<07:20,  1.45it/s]
1|25241|Loss: 0.7844913005828857:  98%|█████████▊| 25240/25880 [5:08:29<07:20,  1.45it/s]
1|25241|Loss: 0.7844913005828857:  98%|█████████▊| 25241/25880 [5:08:30<07:45,  1.37it/s]
1|25242|Loss: 0.9081950187683105:  98%|█████████▊| 25241/25880 [5:08:30<07:45,  1.37it/s]
1|25242|Loss: 0.9081950187683105:  98%|█████████▊| 25242/25880 [5:08:30<07:53,  1.35it/s]
1|25243|Loss: 0.679926872253418:  98%|█████████▊| 25242/25880 [5:08:31<07:53,  1.35it/s] 
1|25243|Loss: 0.679926872253418:  98%|█████████▊| 25243/25880 [5:08:31<08:31,  1.25it/s]
1|25244|Loss: 0.7025169134140015:  98%|█████████▊| 25243/25880 [5:08:32<08:31,  1.25it/s]
1|25244|Loss: 0.7025169134140015:  98%|█████████▊| 25244/25880 [5:08:32<08:27,  1.25it/s]
1|25245|Loss: 0.847648561000824:  98%|█████████▊| 25244/25880 [5:08:32<08:27,  1.25it/s] 
1|25245|Loss: 0.847648561000824:  98%|█████████▊| 25245/25880 [5:08:33<07:46,  1.36it/s]
1|25246|Loss: 0.87087082862854:  98%|█████████▊| 25245/25880 [5:08:33<07:46,  1.36it/s] 
1|25246|Loss: 0.87087082862854:  98%|█████████▊| 25246/25880 [5:08:33<07:47,  1.36it/s]
1|25247|Loss: 0.8622961044311523:  98%|█████████▊| 25246/25880 [5:08:34<07:47,  1.36it/s]
1|25247|Loss: 0.8622961044311523:  98%|█████████▊| 25247/25880 [5:08:34<08:07,  1.30it/s]
1|25248|Loss: 0.7150771617889404:  98%|█████████▊| 25247/25880 [5:08:35<08:07,  1.30it/s]
1|25248|Loss: 0.7150771617889404:  98%|█████████▊| 25248/25880 [5:08:35<07:50,  1.34it/s]
1|25249|Loss: 0.8921585083007812:  98%|█████████▊| 25248/25880 [5:08:35<07:50,  1.34it/s]
1|25249|Loss: 0.8921585083007812:  98%|█████████▊| 25249/25880 [5:08:36<07:58,  1.32it/s]
1|25250|Loss: 0.6936582326889038:  98%|█████████▊| 25249/25880 [5:08:36<07:58,  1.32it/s]
1|25250|Loss: 0.6936582326889038:  98%|█████████▊| 25250/25880 [5:08:37<08:23,  1.25it/s]
1|25251|Loss: 0.7821483016014099:  98%|█████████▊| 25250/25880 [5:08:37<08:23,  1.25it/s]
1|25251|Loss: 0.7821483016014099:  98%|█████████▊| 25251/25880 [5:08:38<08:31,  1.23it/s]
1|25252|Loss: 1.129084587097168:  98%|█████████▊| 25251/25880 [5:08:38<08:31,  1.23it/s] 
1|25252|Loss: 1.129084587097168:  98%|█████████▊| 25252/25880 [5:08:38<08:00,  1.31it/s]
1|25253|Loss: 0.9104923605918884:  98%|█████████▊| 25252/25880 [5:08:39<08:00,  1.31it/s]
1|25253|Loss: 0.9104923605918884:  98%|█████████▊| 25253/25880 [5:08:39<08:17,  1.26it/s]
1|25254|Loss: 0.7832669615745544:  98%|█████████▊| 25253/25880 [5:08:39<08:17,  1.26it/s]
1|25254|Loss: 0.7832669615745544:  98%|█████████▊| 25254/25880 [5:08:40<07:55,  1.32it/s]
1|25255|Loss: 0.8547280430793762:  98%|█████████▊| 25254/25880 [5:08:40<07:55,  1.32it/s]
1|25255|Loss: 0.8547280430793762:  98%|█████████▊| 25255/25880 [5:08:40<07:30,  1.39it/s]
1|25256|Loss: 0.9487555623054504:  98%|█████████▊| 25255/25880 [5:08:41<07:30,  1.39it/s]
1|25256|Loss: 0.9487555623054504:  98%|█████████▊| 25256/25880 [5:08:41<07:43,  1.35it/s]
1|25257|Loss: 0.9367237091064453:  98%|█████████▊| 25256/25880 [5:08:42<07:43,  1.35it/s]
1|25257|Loss: 0.9367237091064453:  98%|█████████▊| 25257/25880 [5:08:42<07:43,  1.34it/s]
1|25258|Loss: 0.8552398085594177:  98%|█████████▊| 25257/25880 [5:08:42<07:43,  1.34it/s]
1|25258|Loss: 0.8552398085594177:  98%|█████████▊| 25258/25880 [5:08:43<07:27,  1.39it/s]
1|25259|Loss: 0.8417077660560608:  98%|█████████▊| 25258/25880 [5:08:43<07:27,  1.39it/s]
1|25259|Loss: 0.8417077660560608:  98%|█████████▊| 25259/25880 [5:08:43<07:22,  1.40it/s]
1|25260|Loss: 0.763893187046051:  98%|█████████▊| 25259/25880 [5:08:44<07:22,  1.40it/s] 
1|25260|Loss: 0.763893187046051:  98%|█████████▊| 25260/25880 [5:08:44<07:23,  1.40it/s]
1|25261|Loss: 0.9425529837608337:  98%|█████████▊| 25260/25880 [5:08:44<07:23,  1.40it/s]
1|25261|Loss: 0.9425529837608337:  98%|█████████▊| 25261/25880 [5:08:45<07:12,  1.43it/s]
1|25262|Loss: 0.9062812924385071:  98%|█████████▊| 25261/25880 [5:08:45<07:12,  1.43it/s]
1|25262|Loss: 0.9062812924385071:  98%|█████████▊| 25262/25880 [5:08:45<06:52,  1.50it/s]
1|25263|Loss: 0.8371457457542419:  98%|█████████▊| 25262/25880 [5:08:46<06:52,  1.50it/s]
1|25263|Loss: 0.8371457457542419:  98%|█████████▊| 25263/25880 [5:08:46<06:44,  1.53it/s]
1|25264|Loss: 0.7305921316146851:  98%|█████████▊| 25263/25880 [5:08:46<06:44,  1.53it/s]
1|25264|Loss: 0.7305921316146851:  98%|█████████▊| 25264/25880 [5:08:47<07:09,  1.43it/s]
1|25265|Loss: 0.795370876789093:  98%|█████████▊| 25264/25880 [5:08:47<07:09,  1.43it/s] 
1|25265|Loss: 0.795370876789093:  98%|█████████▊| 25265/25880 [5:08:48<07:36,  1.35it/s]
1|25266|Loss: 0.7442734241485596:  98%|█████████▊| 25265/25880 [5:08:48<07:36,  1.35it/s]
1|25266|Loss: 0.7442734241485596:  98%|█████████▊| 25266/25880 [5:08:48<07:34,  1.35it/s]
1|25267|Loss: 0.8336071968078613:  98%|█████████▊| 25266/25880 [5:08:49<07:34,  1.35it/s]
1|25267|Loss: 0.8336071968078613:  98%|█████████▊| 25267/25880 [5:08:49<07:04,  1.44it/s]
1|25268|Loss: 0.7637211084365845:  98%|█████████▊| 25267/25880 [5:08:49<07:04,  1.44it/s]
1|25268|Loss: 0.7637211084365845:  98%|█████████▊| 25268/25880 [5:08:50<07:22,  1.38it/s]
1|25269|Loss: 0.8597244620323181:  98%|█████████▊| 25268/25880 [5:08:50<07:22,  1.38it/s]
1|25269|Loss: 0.8597244620323181:  98%|█████████▊| 25269/25880 [5:08:50<07:36,  1.34it/s]
1|25270|Loss: 0.9799327850341797:  98%|█████████▊| 25269/25880 [5:08:51<07:36,  1.34it/s]
1|25270|Loss: 0.9799327850341797:  98%|█████████▊| 25270/25880 [5:08:51<07:53,  1.29it/s]
1|25271|Loss: 0.8879033923149109:  98%|█████████▊| 25270/25880 [5:08:52<07:53,  1.29it/s]
1|25271|Loss: 0.8879033923149109:  98%|█████████▊| 25271/25880 [5:08:52<07:58,  1.27it/s]
1|25272|Loss: 0.883988618850708:  98%|█████████▊| 25271/25880 [5:08:52<07:58,  1.27it/s] 
1|25272|Loss: 0.883988618850708:  98%|█████████▊| 25272/25880 [5:08:53<07:20,  1.38it/s]
1|25273|Loss: 0.8074514865875244:  98%|█████████▊| 25272/25880 [5:08:53<07:20,  1.38it/s]
1|25273|Loss: 0.8074514865875244:  98%|█████████▊| 25273/25880 [5:08:53<07:14,  1.40it/s]
1|25274|Loss: 0.864057719707489:  98%|█████████▊| 25273/25880 [5:08:54<07:14,  1.40it/s] 
1|25274|Loss: 0.864057719707489:  98%|█████████▊| 25274/25880 [5:08:54<07:16,  1.39it/s]
1|25275|Loss: 0.8218103051185608:  98%|█████████▊| 25274/25880 [5:08:54<07:16,  1.39it/s]
1|25275|Loss: 0.8218103051185608:  98%|█████████▊| 25275/25880 [5:08:55<07:14,  1.39it/s]
1|25276|Loss: 0.8090586066246033:  98%|█████████▊| 25275/25880 [5:08:55<07:14,  1.39it/s]
1|25276|Loss: 0.8090586066246033:  98%|█████████▊| 25276/25880 [5:08:55<06:44,  1.49it/s]
1|25277|Loss: 0.8774610161781311:  98%|█████████▊| 25276/25880 [5:08:56<06:44,  1.49it/s]
1|25277|Loss: 0.8774610161781311:  98%|█████████▊| 25277/25880 [5:08:56<06:33,  1.53it/s]
1|25278|Loss: 0.8400367498397827:  98%|█████████▊| 25277/25880 [5:08:56<06:33,  1.53it/s]
1|25278|Loss: 0.8400367498397827:  98%|█████████▊| 25278/25880 [5:08:57<06:40,  1.50it/s]
1|25279|Loss: 0.9376841187477112:  98%|█████████▊| 25278/25880 [5:08:57<06:40,  1.50it/s]
1|25279|Loss: 0.9376841187477112:  98%|█████████▊| 25279/25880 [5:08:57<06:47,  1.47it/s]
1|25280|Loss: 0.879921555519104:  98%|█████████▊| 25279/25880 [5:08:58<06:47,  1.47it/s] 
1|25280|Loss: 0.879921555519104:  98%|█████████▊| 25280/25880 [5:08:58<06:42,  1.49it/s]
1|25281|Loss: 0.992365300655365:  98%|█████████▊| 25280/25880 [5:08:58<06:42,  1.49it/s]
1|25281|Loss: 0.992365300655365:  98%|█████████▊| 25281/25880 [5:08:59<06:51,  1.45it/s]
1|25282|Loss: 0.8300645351409912:  98%|█████████▊| 25281/25880 [5:08:59<06:51,  1.45it/s]
1|25282|Loss: 0.8300645351409912:  98%|█████████▊| 25282/25880 [5:08:59<07:01,  1.42it/s]
1|25283|Loss: 0.9347532987594604:  98%|█████████▊| 25282/25880 [5:09:00<07:01,  1.42it/s]
1|25283|Loss: 0.9347532987594604:  98%|█████████▊| 25283/25880 [5:09:00<06:53,  1.45it/s]
1|25284|Loss: 0.8276236057281494:  98%|█████████▊| 25283/25880 [5:09:01<06:53,  1.45it/s]
1|25284|Loss: 0.8276236057281494:  98%|█████████▊| 25284/25880 [5:09:01<06:43,  1.48it/s]
1|25285|Loss: 0.7746788859367371:  98%|█████████▊| 25284/25880 [5:09:01<06:43,  1.48it/s]
1|25285|Loss: 0.7746788859367371:  98%|█��███████▊| 25285/25880 [5:09:01<06:46,  1.47it/s]
1|25286|Loss: 0.8377359509468079:  98%|█████████▊| 25285/25880 [5:09:02<06:46,  1.47it/s]
1|25286|Loss: 0.8377359509468079:  98%|█████████▊| 25286/25880 [5:09:02<07:08,  1.39it/s]
1|25287|Loss: 0.7305120825767517:  98%|█████████▊| 25286/25880 [5:09:03<07:08,  1.39it/s]
1|25287|Loss: 0.7305120825767517:  98%|█████████▊| 25287/25880 [5:09:03<07:46,  1.27it/s]
1|25288|Loss: 0.8801349997520447:  98%|█████████▊| 25287/25880 [5:09:04<07:46,  1.27it/s]
1|25288|Loss: 0.8801349997520447:  98%|█████████▊| 25288/25880 [5:09:04<07:22,  1.34it/s]
1|25289|Loss: 0.7862501740455627:  98%|█████████▊| 25288/25880 [5:09:04<07:22,  1.34it/s]
1|25289|Loss: 0.7862501740455627:  98%|█████████▊| 25289/25880 [5:09:05<07:41,  1.28it/s]
1|25290|Loss: 0.7582607865333557:  98%|█████████▊| 25289/25880 [5:09:05<07:41,  1.28it/s]
1|25290|Loss: 0.7582607865333557:  98%|█████████▊| 25290/25880 [5:09:05<07:10,  1.37it/s]
1|25291|Loss: 0.7334585189819336:  98%|█████████▊| 25290/25880 [5:09:06<07:10,  1.37it/s]
1|25291|Loss: 0.7334585189819336:  98%|█████████▊| 25291/25880 [5:09:06<07:28,  1.31it/s]
1|25292|Loss: 0.7975781559944153:  98%|█████████▊| 25291/25880 [5:09:07<07:28,  1.31it/s]
1|25292|Loss: 0.7975781559944153:  98%|█████████▊| 25292/25880 [5:09:07<07:07,  1.37it/s]
1|25293|Loss: 0.760402262210846:  98%|█████████▊| 25292/25880 [5:09:07<07:07,  1.37it/s] 
1|25293|Loss: 0.760402262210846:  98%|█████████▊| 25293/25880 [5:09:07<06:22,  1.53it/s]
1|25294|Loss: 0.866183876991272:  98%|█████████▊| 25293/25880 [5:09:08<06:22,  1.53it/s]
1|25294|Loss: 0.866183876991272:  98%|█████████▊| 25294/25880 [5:09:08<06:12,  1.57it/s]
1|25295|Loss: 0.8936067223548889:  98%|█████████▊| 25294/25880 [5:09:08<06:12,  1.57it/s]
1|25295|Loss: 0.8936067223548889:  98%|█████████▊| 25295/25880 [5:09:09<06:47,  1.44it/s]
1|25296|Loss: 0.8438699245452881:  98%|█████████▊| 25295/25880 [5:09:09<06:47,  1.44it/s]
1|25296|Loss: 0.8438699245452881:  98%|█████████▊| 25296/25880 [5:09:10<07:46,  1.25it/s]
1|25297|Loss: 0.803876519203186:  98%|█████████▊| 25296/25880 [5:09:10<07:46,  1.25it/s] 
1|25297|Loss: 0.803876519203186:  98%|█████████▊| 25297/25880 [5:09:10<07:25,  1.31it/s]
1|25298|Loss: 0.8476805686950684:  98%|█████████▊| 25297/25880 [5:09:11<07:25,  1.31it/s]
1|25298|Loss: 0.8476805686950684:  98%|█████████▊| 25298/25880 [5:09:11<06:56,  1.40it/s]
1|25299|Loss: 0.9923715591430664:  98%|█████████▊| 25298/25880 [5:09:11<06:56,  1.40it/s]
1|25299|Loss: 0.9923715591430664:  98%|█████████▊| 25299/25880 [5:09:12<06:42,  1.44it/s]
1|25300|Loss: 0.6943938732147217:  98%|█████████▊| 25299/25880 [5:09:12<06:42,  1.44it/s]
1|25300|Loss: 0.6943938732147217:  98%|█████████▊| 25300/25880 [5:09:12<06:42,  1.44it/s]
1|25301|Loss: 0.8063804507255554:  98%|█████████▊| 25300/25880 [5:09:13<06:42,  1.44it/s]
1|25301|Loss: 0.8063804507255554:  98%|█████████▊| 25301/25880 [5:09:13<06:19,  1.52it/s]
1|25302|Loss: 0.8223696947097778:  98%|█████████▊| 25301/25880 [5:09:13<06:19,  1.52it/s]
1|25302|Loss: 0.8223696947097778:  98%|█████████▊| 25302/25880 [5:09:14<06:36,  1.46it/s]
1|25303|Loss: 0.8879454731941223:  98%|█████████▊| 25302/25880 [5:09:14<06:36,  1.46it/s]
1|25303|Loss: 0.8879454731941223:  98%|█████████▊| 25303/25880 [5:09:14<06:12,  1.55it/s]
1|25304|Loss: 0.8679882287979126:  98%|█████████▊| 25303/25880 [5:09:15<06:12,  1.55it/s]
1|25304|Loss: 0.8679882287979126:  98%|█████████▊| 25304/25880 [5:09:15<05:49,  1.65it/s]
1|25305|Loss: 0.905584990978241:  98%|█████████▊| 25304/25880 [5:09:15<05:49,  1.65it/s] 
1|25305|Loss: 0.905584990978241:  98%|█████████▊| 25305/25880 [5:09:16<06:19,  1.52it/s]
1|25306|Loss: 0.7710021734237671:  98%|█████████▊| 25305/25880 [5:09:16<06:19,  1.52it/s]
1|25306|Loss: 0.7710021734237671:  98%|█████████▊| 25306/25880 [5:09:16<06:24,  1.49it/s]
1|25307|Loss: 0.8985479474067688:  98%|█████████▊| 25306/25880 [5:09:17<06:24,  1.49it/s]
1|25307|Loss: 0.8985479474067688:  98%|█████████▊| 25307/25880 [5:09:17<06:56,  1.38it/s]
1|25308|Loss: 0.820461094379425:  98%|█████████▊| 25307/25880 [5:09:18<06:56,  1.38it/s] 
1|25308|Loss: 0.820461094379425:  98%|█████████▊| 25308/25880 [5:09:18<06:46,  1.41it/s]
1|25309|Loss: 0.691361665725708:  98%|█████████▊| 25308/25880 [5:09:18<06:46,  1.41it/s]
1|25309|Loss: 0.691361665725708:  98%|█████████▊| 25309/25880 [5:09:19<06:47,  1.40it/s]
1|25310|Loss: 0.8473711013793945:  98%|█████████▊| 25309/25880 [5:09:19<06:47,  1.40it/s]
1|25310|Loss: 0.8473711013793945:  98%|█████████▊| 25310/25880 [5:09:19<06:50,  1.39it/s]
1|25311|Loss: 1.0257015228271484:  98%|█████████▊| 25310/25880 [5:09:20<06:50,  1.39it/s]
1|25311|Loss: 1.0257015228271484:  98%|█████████▊| 25311/25880 [5:09:20<07:12,  1.31it/s]
1|25312|Loss: 0.8867005109786987:  98%|█████████▊| 25311/25880 [5:09:21<07:12,  1.31it/s]
1|25312|Loss: 0.8867005109786987:  98%|█████████▊| 25312/25880 [5:09:21<07:21,  1.29it/s]
1|25313|Loss: 0.8052513599395752:  98%|█████████▊| 25312/25880 [5:09:21<07:21,  1.29it/s]
1|25313|Loss: 0.8052513599395752:  98%|█████████▊| 25313/25880 [5:09:22<07:35,  1.25it/s]
1|25314|Loss: 0.8109638690948486:  98%|█████████▊| 25313/25880 [5:09:22<07:35,  1.25it/s]
1|25314|Loss: 0.8109638690948486:  98%|█████████▊| 25314/25880 [5:09:23<07:23,  1.28it/s]
1|25315|Loss: 0.7897204160690308:  98%|█████████▊| 25314/25880 [5:09:23<07:23,  1.28it/s]
1|25315|Loss: 0.7897204160690308:  98%|█████████▊| 25315/25880 [5:09:23<07:27,  1.26it/s]
1|25316|Loss: 0.9621129631996155:  98%|█████████▊| 25315/25880 [5:09:24<07:27,  1.26it/s]
1|25316|Loss: 0.9621129631996155:  98%|█████████▊| 25316/25880 [5:09:24<07:07,  1.32it/s]
1|25317|Loss: 0.8614927530288696:  98%|█████████▊| 25316/25880 [5:09:24<07:07,  1.32it/s]
1|25317|Loss: 0.8614927530288696:  98%|█████████▊| 25317/25880 [5:09:25<06:39,  1.41it/s]
1|25318|Loss: 0.647400975227356:  98%|█████████▊| 25317/25880 [5:09:25<06:39,  1.41it/s] 
1|25318|Loss: 0.647400975227356:  98%|█████████▊| 25318/25880 [5:09:25<06:24,  1.46it/s]
1|25319|Loss: 0.7081350684165955:  98%|█████████▊| 25318/25880 [5:09:26<06:24,  1.46it/s]
1|25319|Loss: 0.7081350684165955:  98%|█████████▊| 25319/25880 [5:09:26<06:28,  1.44it/s]
1|25320|Loss: 0.9343985319137573:  98%|█████████▊| 25319/25880 [5:09:26<06:28,  1.44it/s]
1|25320|Loss: 0.9343985319137573:  98%|█████████▊| 25320/25880 [5:09:27<06:14,  1.49it/s]
1|25321|Loss: 0.8022942543029785:  98%|█████████▊| 25320/25880 [5:09:27<06:14,  1.49it/s]
1|25321|Loss: 0.8022942543029785:  98%|█████████▊| 25321/25880 [5:09:27<06:06,  1.52it/s]
1|25322|Loss: 0.8421719074249268:  98%|█████████▊| 25321/25880 [5:09:28<06:06,  1.52it/s]
1|25322|Loss: 0.8421719074249268:  98%|█████████▊| 25322/25880 [5:09:28<06:23,  1.45it/s]
1|25323|Loss: 1.0063016414642334:  98%|█████████▊| 25322/25880 [5:09:28<06:23,  1.45it/s]
1|25323|Loss: 1.0063016414642334:  98%|█████████▊| 25323/25880 [5:09:29<05:56,  1.56it/s]
1|25324|Loss: 0.866155207157135:  98%|█████████▊| 25323/25880 [5:09:29<05:56,  1.56it/s] 
1|25324|Loss: 0.866155207157135:  98%|█████████▊| 25324/25880 [5:09:29<06:13,  1.49it/s]
1|25325|Loss: 0.7998584508895874:  98%|█████████▊| 25324/25880 [5:09:30<06:13,  1.49it/s]
1|25325|Loss: 0.7998584508895874:  98%|█████████▊| 25325/25880 [5:09:30<06:20,  1.46it/s]
1|25326|Loss: 0.9014905691146851:  98%|█████████▊| 25325/25880 [5:09:30<06:20,  1.46it/s]
1|25326|Loss: 0.9014905691146851:  98%|█████████▊| 25326/25880 [5:09:31<06:25,  1.44it/s]
1|25327|Loss: 0.9111492037773132:  98%|█████████▊| 25326/25880 [5:09:31<06:25,  1.44it/s]
1|25327|Loss: 0.9111492037773132:  98%|█████████▊| 25327/25880 [5:09:31<06:31,  1.41it/s]
1|25328|Loss: 0.8965144753456116:  98%|█████████▊| 25327/25880 [5:09:32<06:31,  1.41it/s]
1|25328|Loss: 0.8965144753456116:  98%|█████████▊| 25328/25880 [5:09:32<06:20,  1.45it/s]
1|25329|Loss: 0.7793911099433899:  98%|█████████▊| 25328/25880 [5:09:32<06:20,  1.45it/s]
1|25329|Loss: 0.7793911099433899:  98%|█████████▊| 25329/25880 [5:09:33<05:56,  1.54it/s]
1|25330|Loss: 0.8792081475257874:  98%|█████████▊| 25329/25880 [5:09:33<05:56,  1.54it/s]
1|25330|Loss: 0.8792081475257874:  98%|█████████▊| 25330/25880 [5:09:33<06:00,  1.53it/s]
1|25331|Loss: 0.8088539242744446:  98%|█████████▊| 25330/25880 [5:09:34<06:00,  1.53it/s]
1|25331|Loss: 0.8088539242744446:  98%|█████████▊| 25331/25880 [5:09:34<05:57,  1.54it/s]
1|25332|Loss: 0.8188966512680054:  98%|████████���▊| 25331/25880 [5:09:34<05:57,  1.54it/s]
1|25332|Loss: 0.8188966512680054:  98%|█████████▊| 25332/25880 [5:09:35<06:02,  1.51it/s]
1|25333|Loss: 0.8816581964492798:  98%|█████████▊| 25332/25880 [5:09:35<06:02,  1.51it/s]
1|25333|Loss: 0.8816581964492798:  98%|█████████▊| 25333/25880 [5:09:35<06:25,  1.42it/s]
1|25334|Loss: 0.8561029434204102:  98%|█████████▊| 25333/25880 [5:09:36<06:25,  1.42it/s]
1|25334|Loss: 0.8561029434204102:  98%|█████████▊| 25334/25880 [5:09:36<06:11,  1.47it/s]
1|25335|Loss: 0.825031578540802:  98%|█████████▊| 25334/25880 [5:09:36<06:11,  1.47it/s] 
1|25335|Loss: 0.825031578540802:  98%|█████████▊| 25335/25880 [5:09:37<06:24,  1.42it/s]
1|25336|Loss: 0.8630238175392151:  98%|█████████▊| 25335/25880 [5:09:37<06:24,  1.42it/s]
1|25336|Loss: 0.8630238175392151:  98%|█████████▊| 25336/25880 [5:09:38<06:30,  1.39it/s]
1|25337|Loss: 0.8712220788002014:  98%|█████████▊| 25336/25880 [5:09:38<06:30,  1.39it/s]
1|25337|Loss: 0.8712220788002014:  98%|█████████▊| 25337/25880 [5:09:38<06:31,  1.39it/s]
1|25338|Loss: 1.0025204420089722:  98%|█████████▊| 25337/25880 [5:09:39<06:31,  1.39it/s]
1|25338|Loss: 1.0025204420089722:  98%|█████████▊| 25338/25880 [5:09:39<06:09,  1.47it/s]
1|25339|Loss: 0.8022512197494507:  98%|█████████▊| 25338/25880 [5:09:39<06:09,  1.47it/s]
1|25339|Loss: 0.8022512197494507:  98%|█████████▊| 25339/25880 [5:09:40<06:12,  1.45it/s]
1|25340|Loss: 0.8779427409172058:  98%|█████████▊| 25339/25880 [5:09:40<06:12,  1.45it/s]
1|25340|Loss: 0.8779427409172058:  98%|█████████▊| 25340/25880 [5:09:40<06:21,  1.42it/s]
1|25341|Loss: 0.8141108155250549:  98%|█████████▊| 25340/25880 [5:09:41<06:21,  1.42it/s]
1|25341|Loss: 0.8141108155250549:  98%|█████████▊| 25341/25880 [5:09:41<06:46,  1.33it/s]
1|25342|Loss: 0.8062581419944763:  98%|█████████▊| 25341/25880 [5:09:42<06:46,  1.33it/s]
1|25342|Loss: 0.8062581419944763:  98%|█████████▊| 25342/25880 [5:09:42<06:47,  1.32it/s]
1|25343|Loss: 0.7208167910575867:  98%|█████████▊| 25342/25880 [5:09:42<06:47,  1.32it/s]
1|25343|Loss: 0.7208167910575867:  98%|█████████▊| 25343/25880 [5:09:43<06:26,  1.39it/s]
1|25344|Loss: 0.6793838739395142:  98%|█████████▊| 25343/25880 [5:09:43<06:26,  1.39it/s]
1|25344|Loss: 0.6793838739395142:  98%|█████████▊| 25344/25880 [5:09:44<07:00,  1.28it/s]
1|25345|Loss: 0.7978809475898743:  98%|█████████▊| 25344/25880 [5:09:44<07:00,  1.28it/s]
1|25345|Loss: 0.7978809475898743:  98%|█████████▊| 25345/25880 [5:09:44<07:02,  1.27it/s]
1|25346|Loss: 0.7799099683761597:  98%|█████████▊| 25345/25880 [5:09:45<07:02,  1.27it/s]
1|25346|Loss: 0.7799099683761597:  98%|█████████▊| 25346/25880 [5:09:45<06:39,  1.34it/s]
1|25347|Loss: 0.9548372626304626:  98%|█████████▊| 25346/25880 [5:09:45<06:39,  1.34it/s]
1|25347|Loss: 0.9548372626304626:  98%|█████████▊| 25347/25880 [5:09:46<06:21,  1.40it/s]
1|25348|Loss: 0.7721702456474304:  98%|█████████▊| 25347/25880 [5:09:46<06:21,  1.40it/s]
1|25348|Loss: 0.7721702456474304:  98%|█████████▊| 25348/25880 [5:09:46<06:21,  1.39it/s]
1|25349|Loss: 0.8741875290870667:  98%|█████████▊| 25348/25880 [5:09:47<06:21,  1.39it/s]
1|25349|Loss: 0.8741875290870667:  98%|█████████▊| 25349/25880 [5:09:47<06:03,  1.46it/s]
1|25350|Loss: 0.865628182888031:  98%|█████████▊| 25349/25880 [5:09:47<06:03,  1.46it/s] 
1|25350|Loss: 0.865628182888031:  98%|█████████▊| 25350/25880 [5:09:48<06:05,  1.45it/s]
1|25351|Loss: 0.7849134206771851:  98%|█████████▊| 25350/25880 [5:09:48<06:05,  1.45it/s]
1|25351|Loss: 0.7849134206771851:  98%|█████████▊| 25351/25880 [5:09:48<05:57,  1.48it/s]
1|25352|Loss: 0.7948850989341736:  98%|█████████▊| 25351/25880 [5:09:49<05:57,  1.48it/s]
1|25352|Loss: 0.7948850989341736:  98%|█████████▊| 25352/25880 [5:09:49<05:44,  1.53it/s]
1|25353|Loss: 0.8350086212158203:  98%|█████████▊| 25352/25880 [5:09:49<05:44,  1.53it/s]
1|25353|Loss: 0.8350086212158203:  98%|█████████▊| 25353/25880 [5:09:50<05:48,  1.51it/s]
1|25354|Loss: 0.7769674062728882:  98%|█████████▊| 25353/25880 [5:09:50<05:48,  1.51it/s]
1|25354|Loss: 0.7769674062728882:  98%|█████████▊| 25354/25880 [5:09:50<05:58,  1.47it/s]
1|25355|Loss: 0.8039342761039734:  98%|█████████▊| 25354/25880 [5:09:51<05:58,  1.47it/s]
1|25355|Loss: 0.8039342761039734:  98%|█████████▊| 25355/25880 [5:09:51<06:12,  1.41it/s]
1|25356|Loss: 0.870050311088562:  98%|█████████▊| 25355/25880 [5:09:52<06:12,  1.41it/s] 
1|25356|Loss: 0.870050311088562:  98%|█████████▊| 25356/25880 [5:09:52<06:33,  1.33it/s]
1|25357|Loss: 0.8678500056266785:  98%|█████████▊| 25356/25880 [5:09:52<06:33,  1.33it/s]
1|25357|Loss: 0.8678500056266785:  98%|█████████▊| 25357/25880 [5:09:53<06:58,  1.25it/s]
1|25358|Loss: 0.6205670833587646:  98%|█████████▊| 25357/25880 [5:09:53<06:58,  1.25it/s]
1|25358|Loss: 0.6205670833587646:  98%|█████████▊| 25358/25880 [5:09:53<06:34,  1.32it/s]
1|25359|Loss: 0.9191086888313293:  98%|█████████▊| 25358/25880 [5:09:54<06:34,  1.32it/s]
1|25359|Loss: 0.9191086888313293:  98%|█████████▊| 25359/25880 [5:09:54<06:11,  1.40it/s]
1|25360|Loss: 0.7943927049636841:  98%|█████████▊| 25359/25880 [5:09:55<06:11,  1.40it/s]
1|25360|Loss: 0.7943927049636841:  98%|█████████▊| 25360/25880 [5:09:55<06:23,  1.36it/s]
1|25361|Loss: 0.8396886587142944:  98%|█████████▊| 25360/25880 [5:09:55<06:23,  1.36it/s]
1|25361|Loss: 0.8396886587142944:  98%|█████████▊| 25361/25880 [5:09:55<05:56,  1.45it/s]
1|25362|Loss: 0.9148681163787842:  98%|█████████▊| 25361/25880 [5:09:56<05:56,  1.45it/s]
1|25362|Loss: 0.9148681163787842:  98%|█████████▊| 25362/25880 [5:09:56<06:02,  1.43it/s]
1|25363|Loss: 0.859769880771637:  98%|█████████▊| 25362/25880 [5:09:57<06:02,  1.43it/s] 
1|25363|Loss: 0.859769880771637:  98%|█████████▊| 25363/25880 [5:09:57<05:54,  1.46it/s]
1|25364|Loss: 0.8673185110092163:  98%|█████████▊| 25363/25880 [5:09:57<05:54,  1.46it/s]
1|25364|Loss: 0.8673185110092163:  98%|█████████▊| 25364/25880 [5:09:57<05:46,  1.49it/s]
1|25365|Loss: 0.8871839046478271:  98%|█████████▊| 25364/25880 [5:09:58<05:46,  1.49it/s]
1|25365|Loss: 0.8871839046478271:  98%|█████████▊| 25365/25880 [5:09:58<05:38,  1.52it/s]
1|25366|Loss: 0.846263587474823:  98%|█████████▊| 25365/25880 [5:09:59<05:38,  1.52it/s] 
1|25366|Loss: 0.846263587474823:  98%|█████████▊| 25366/25880 [5:09:59<05:57,  1.44it/s]
1|25367|Loss: 0.9981133937835693:  98%|█████████▊| 25366/25880 [5:09:59<05:57,  1.44it/s]
1|25367|Loss: 0.9981133937835693:  98%|█████████▊| 25367/25880 [5:10:00<06:02,  1.41it/s]
1|25368|Loss: 0.8934885859489441:  98%|█████████▊| 25367/25880 [5:10:00<06:02,  1.41it/s]
1|25368|Loss: 0.8934885859489441:  98%|█████████▊| 25368/25880 [5:10:00<06:00,  1.42it/s]
1|25369|Loss: 0.8009133338928223:  98%|█████████▊| 25368/25880 [5:10:01<06:00,  1.42it/s]
1|25369|Loss: 0.8009133338928223:  98%|█████████▊| 25369/25880 [5:10:01<06:30,  1.31it/s]
1|25370|Loss: 0.843885064125061:  98%|█████████▊| 25369/25880 [5:10:02<06:30,  1.31it/s] 
1|25370|Loss: 0.843885064125061:  98%|█████████▊| 25370/25880 [5:10:02<06:31,  1.30it/s]
1|25371|Loss: 0.9221848845481873:  98%|█████████▊| 25370/25880 [5:10:02<06:31,  1.30it/s]
1|25371|Loss: 0.9221848845481873:  98%|█████████▊| 25371/25880 [5:10:03<06:26,  1.32it/s]
1|25372|Loss: 0.838526725769043:  98%|█████████▊| 25371/25880 [5:10:03<06:26,  1.32it/s] 
1|25372|Loss: 0.838526725769043:  98%|█████████▊| 25372/25880 [5:10:04<06:38,  1.28it/s]
1|25373|Loss: 0.875055193901062:  98%|█████████▊| 25372/25880 [5:10:04<06:38,  1.28it/s]
1|25373|Loss: 0.875055193901062:  98%|█████████▊| 25373/25880 [5:10:04<06:16,  1.34it/s]
1|25374|Loss: 0.7610312104225159:  98%|█████████▊| 25373/25880 [5:10:05<06:16,  1.34it/s]
1|25374|Loss: 0.7610312104225159:  98%|█████████▊| 25374/25880 [5:10:05<06:10,  1.37it/s]
1|25375|Loss: 0.7880768179893494:  98%|█████████▊| 25374/25880 [5:10:05<06:10,  1.37it/s]
1|25375|Loss: 0.7880768179893494:  98%|█████████▊| 25375/25880 [5:10:06<06:20,  1.33it/s]
1|25376|Loss: 0.7662517428398132:  98%|█████████▊| 25375/25880 [5:10:06<06:20,  1.33it/s]
1|25376|Loss: 0.7662517428398132:  98%|█████████▊| 25376/25880 [5:10:06<06:16,  1.34it/s]
1|25377|Loss: 0.725795567035675:  98%|█████████▊| 25376/25880 [5:10:07<06:16,  1.34it/s] 
1|25377|Loss: 0.725795567035675:  98%|█████████▊| 25377/25880 [5:10:07<06:18,  1.33it/s]
1|25378|Loss: 0.8946942687034607:  98%|█████████▊| 25377/25880 [5:10:08<06:18,  1.33it/s]
1|25378|Loss: 0.8946942687034607:  98%|█████████▊| 25378/25880 [5:10:08<06:25,  1.30it/s]
1|25379|Loss: 0.7440961003303528:  98%|█████████▊| 25378/25880 [5:10:09<06:25,  1.30it/s]
1|25379|Loss: 0.7440961003303528:  98%|█████████▊| 25379/25880 [5:10:09<06:37,  1.26it/s]
1|25380|Loss: 0.762204647064209:  98%|█████████▊| 25379/25880 [5:10:09<06:37,  1.26it/s] 
1|25380|Loss: 0.762204647064209:  98%|█████████▊| 25380/25880 [5:10:10<06:33,  1.27it/s]
1|25381|Loss: 0.8687945008277893:  98%|█████████▊| 25380/25880 [5:10:10<06:33,  1.27it/s]
1|25381|Loss: 0.8687945008277893:  98%|█████████▊| 25381/25880 [5:10:10<06:21,  1.31it/s]
1|25382|Loss: 0.7271674871444702:  98%|█████████▊| 25381/25880 [5:10:11<06:21,  1.31it/s]
1|25382|Loss: 0.7271674871444702:  98%|█████████▊| 25382/25880 [5:10:11<06:03,  1.37it/s]
1|25383|Loss: 0.7522889971733093:  98%|█████████▊| 25382/25880 [5:10:11<06:03,  1.37it/s]
1|25383|Loss: 0.7522889971733093:  98%|█████████▊| 25383/25880 [5:10:12<05:57,  1.39it/s]
1|25384|Loss: 0.8807032108306885:  98%|█████████▊| 25383/25880 [5:10:12<05:57,  1.39it/s]
1|25384|Loss: 0.8807032108306885:  98%|█████████▊| 25384/25880 [5:10:12<06:03,  1.36it/s]
1|25385|Loss: 0.7328181862831116:  98%|█████████▊| 25384/25880 [5:10:13<06:03,  1.36it/s]
1|25385|Loss: 0.7328181862831116:  98%|█████████▊| 25385/25880 [5:10:13<06:06,  1.35it/s]
1|25386|Loss: 0.7378994822502136:  98%|█████████▊| 25385/25880 [5:10:14<06:06,  1.35it/s]
1|25386|Loss: 0.7378994822502136:  98%|█████████▊| 25386/25880 [5:10:14<06:05,  1.35it/s]
1|25387|Loss: 0.8347569704055786:  98%|█████████▊| 25386/25880 [5:10:14<06:05,  1.35it/s]
1|25387|Loss: 0.8347569704055786:  98%|█████████▊| 25387/25880 [5:10:15<05:46,  1.42it/s]
1|25388|Loss: 0.9478246569633484:  98%|█████████▊| 25387/25880 [5:10:15<05:46,  1.42it/s]
1|25388|Loss: 0.9478246569633484:  98%|█████████▊| 25388/25880 [5:10:15<05:35,  1.47it/s]
1|25389|Loss: 0.8587143421173096:  98%|█████████▊| 25388/25880 [5:10:16<05:35,  1.47it/s]
1|25389|Loss: 0.8587143421173096:  98%|█████████▊| 25389/25880 [5:10:16<05:55,  1.38it/s]
1|25390|Loss: 0.7392036318778992:  98%|█████████▊| 25389/25880 [5:10:16<05:55,  1.38it/s]
1|25390|Loss: 0.7392036318778992:  98%|█████████▊| 25390/25880 [5:10:17<05:46,  1.41it/s]
1|25391|Loss: 0.7885617613792419:  98%|█████████▊| 25390/25880 [5:10:17<05:46,  1.41it/s]
1|25391|Loss: 0.7885617613792419:  98%|█████████▊| 25391/25880 [5:10:17<05:48,  1.40it/s]
1|25392|Loss: 0.8355084657669067:  98%|█████████▊| 25391/25880 [5:10:18<05:48,  1.40it/s]
1|25392|Loss: 0.8355084657669067:  98%|█████████▊| 25392/25880 [5:10:18<05:40,  1.43it/s]
1|25393|Loss: 0.8574702143669128:  98%|█████████▊| 25392/25880 [5:10:18<05:40,  1.43it/s]
1|25393|Loss: 0.8574702143669128:  98%|█████████▊| 25393/25880 [5:10:19<05:29,  1.48it/s]
1|25394|Loss: 0.841594398021698:  98%|█████████▊| 25393/25880 [5:10:19<05:29,  1.48it/s] 
1|25394|Loss: 0.841594398021698:  98%|█████████▊| 25394/25880 [5:10:19<05:35,  1.45it/s]
1|25395|Loss: 0.798852801322937:  98%|█████████▊| 25394/25880 [5:10:20<05:35,  1.45it/s]
1|25395|Loss: 0.798852801322937:  98%|█████████▊| 25395/25880 [5:10:20<05:43,  1.41it/s]
1|25396|Loss: 0.8477347493171692:  98%|█████████▊| 25395/25880 [5:10:21<05:43,  1.41it/s]
1|25396|Loss: 0.8477347493171692:  98%|█████████▊| 25396/25880 [5:10:21<05:55,  1.36it/s]
1|25397|Loss: 0.7910753488540649:  98%|█████████▊| 25396/25880 [5:10:21<05:55,  1.36it/s]
1|25397|Loss: 0.7910753488540649:  98%|█████████▊| 25397/25880 [5:10:22<05:58,  1.35it/s]
1|25398|Loss: 0.8220061659812927:  98%|█████████▊| 25397/25880 [5:10:22<05:58,  1.35it/s]
1|25398|Loss: 0.8220061659812927:  98%|█████████▊| 25398/25880 [5:10:22<05:54,  1.36it/s]
1|25399|Loss: 0.7859809398651123:  98%|█████████▊| 25398/25880 [5:10:23<05:54,  1.36it/s]
1|25399|Loss: 0.7859809398651123:  98%|█████████▊| 25399/25880 [5:10:23<05:51,  1.37it/s]
1|25400|Loss: 0.8483870625495911:  98%|█████████▊| 25399/25880 [5:10:24<05:51,  1.37it/s]
1|25400|Loss: 0.8483870625495911:  98%|█████████▊| 25400/25880 [5:10:24<06:01,  1.33it/s]
1|25401|Loss: 0.7953968048095703:  98%|█████████▊| 25400/25880 [5:10:24<06:01,  1.33it/s]
1|25401|Loss: 0.7953968048095703:  98%|█████████▊| 25401/25880 [5:10:25<06:08,  1.30it/s]
1|25402|Loss: 0.8252030611038208:  98%|█████████▊| 25401/25880 [5:10:25<06:08,  1.30it/s]
1|25402|Loss: 0.8252030611038208:  98%|█████████▊| 25402/25880 [5:10:26<06:25,  1.24it/s]
1|25403|Loss: 0.7735454440116882:  98%|█████████▊| 25402/25880 [5:10:26<06:25,  1.24it/s]
1|25403|Loss: 0.7735454440116882:  98%|█████████▊| 25403/25880 [5:10:26<05:56,  1.34it/s]
1|25404|Loss: 0.7417985200881958:  98%|█████████▊| 25403/25880 [5:10:27<05:56,  1.34it/s]
1|25404|Loss: 0.7417985200881958:  98%|█████████▊| 25404/25880 [5:10:27<05:55,  1.34it/s]
1|25405|Loss: 0.8286070227622986:  98%|█████████▊| 25404/25880 [5:10:28<05:55,  1.34it/s]
1|25405|Loss: 0.8286070227622986:  98%|█████████▊| 25405/25880 [5:10:28<06:01,  1.31it/s]
1|25406|Loss: 0.8600960373878479:  98%|█████████▊| 25405/25880 [5:10:28<06:01,  1.31it/s]
1|25406|Loss: 0.8600960373878479:  98%|█████████▊| 25406/25880 [5:10:29<06:01,  1.31it/s]
1|25407|Loss: 0.6814641356468201:  98%|█████████▊| 25406/25880 [5:10:29<06:01,  1.31it/s]
1|25407|Loss: 0.6814641356468201:  98%|█████████▊| 25407/25880 [5:10:29<05:56,  1.33it/s]
1|25408|Loss: 0.8788037300109863:  98%|█████████▊| 25407/25880 [5:10:30<05:56,  1.33it/s]
1|25408|Loss: 0.8788037300109863:  98%|█████████▊| 25408/25880 [5:10:30<05:50,  1.35it/s]
1|25409|Loss: 0.9051527380943298:  98%|█████████▊| 25408/25880 [5:10:30<05:50,  1.35it/s]
1|25409|Loss: 0.9051527380943298:  98%|█████████▊| 25409/25880 [5:10:31<05:36,  1.40it/s]
1|25410|Loss: 0.7545113563537598:  98%|█████████▊| 25409/25880 [5:10:31<05:36,  1.40it/s]
1|25410|Loss: 0.7545113563537598:  98%|█████████▊| 25410/25880 [5:10:31<05:38,  1.39it/s]
1|25411|Loss: 0.7926970720291138:  98%|█████████▊| 25410/25880 [5:10:32<05:38,  1.39it/s]
1|25411|Loss: 0.7926970720291138:  98%|█████████▊| 25411/25880 [5:10:32<05:37,  1.39it/s]
1|25412|Loss: 0.6569090485572815:  98%|█████████▊| 25411/25880 [5:10:33<05:37,  1.39it/s]
1|25412|Loss: 0.6569090485572815:  98%|█████████▊| 25412/25880 [5:10:33<06:03,  1.29it/s]
1|25413|Loss: 0.828474760055542:  98%|█████████▊| 25412/25880 [5:10:34<06:03,  1.29it/s] 
1|25413|Loss: 0.828474760055542:  98%|█████████▊| 25413/25880 [5:10:34<06:00,  1.30it/s]
1|25414|Loss: 0.8161092400550842:  98%|█████████▊| 25413/25880 [5:10:34<06:00,  1.30it/s]
1|25414|Loss: 0.8161092400550842:  98%|█████████▊| 25414/25880 [5:10:35<06:09,  1.26it/s]
1|25415|Loss: 0.8422878384590149:  98%|█████████▊| 25414/25880 [5:10:35<06:09,  1.26it/s]
1|25415|Loss: 0.8422878384590149:  98%|█████████▊| 25415/25880 [5:10:36<06:16,  1.24it/s]
1|25416|Loss: 0.882750928401947:  98%|█████████▊| 25415/25880 [5:10:36<06:16,  1.24it/s] 
1|25416|Loss: 0.882750928401947:  98%|█████████▊| 25416/25880 [5:10:36<06:04,  1.27it/s]
1|25417|Loss: 0.8696317076683044:  98%|█████████▊| 25416/25880 [5:10:37<06:04,  1.27it/s]
1|25417|Loss: 0.8696317076683044:  98%|█████████▊| 25417/25880 [5:10:37<05:57,  1.29it/s]
1|25418|Loss: 0.8730226159095764:  98%|█████████▊| 25417/25880 [5:10:37<05:57,  1.29it/s]
1|25418|Loss: 0.8730226159095764:  98%|█████████▊| 25418/25880 [5:10:38<05:33,  1.39it/s]
1|25419|Loss: 0.7201218605041504:  98%|█████████▊| 25418/25880 [5:10:38<05:33,  1.39it/s]
1|25419|Loss: 0.7201218605041504:  98%|█████████▊| 25419/25880 [5:10:38<05:29,  1.40it/s]
1|25420|Loss: 0.9382131695747375:  98%|█████████▊| 25419/25880 [5:10:39<05:29,  1.40it/s]
1|25420|Loss: 0.9382131695747375:  98%|█████████▊| 25420/25880 [5:10:39<05:59,  1.28it/s]
1|25421|Loss: 0.7712546586990356:  98%|█████████▊| 25420/25880 [5:10:40<05:59,  1.28it/s]
1|25421|Loss: 0.7712546586990356:  98%|█████████▊| 25421/25880 [5:10:40<06:16,  1.22it/s]
1|25422|Loss: 0.9132976531982422:  98%|█████████▊| 25421/25880 [5:10:41<06:16,  1.22it/s]
1|25422|Loss: 0.9132976531982422:  98%|█████████▊| 25422/25880 [5:10:41<06:09,  1.24it/s]
1|25423|Loss: 0.7739574313163757:  98%|█████████▊| 25422/25880 [5:10:41<06:09,  1.24it/s]
1|25423|Loss: 0.7739574313163757:  98%|█████████▊| 25423/25880 [5:10:42<06:01,  1.26it/s]
1|25424|Loss: 0.8553869128227234:  98%|█████████▊| 25423/25880 [5:10:42<06:01,  1.26it/s]
1|25424|Loss: 0.8553869128227234:  98%|█████████▊| 25424/25880 [5:10:42<05:53,  1.29it/s]
1|25425|Loss: 0.6971836686134338:  98%|█████████▊| 25424/25880 [5:10:43<05:53,  1.29it/s]
1|25425|Loss: 0.6971836686134338:  98%|█████████▊| 25425/25880 [5:10:43<05:43,  1.32it/s]
1|25426|Loss: 0.9726058840751648:  98%|█████████▊| 25425/25880 [5:10:44<05:43,  1.32it/s]
1|25426|Loss: 0.9726058840751648:  98%|█████████▊| 25426/25880 [5:10:44<05:35,  1.36it/s]
1|25427|Loss: 0.8677088022232056:  98%|█████████▊| 25426/25880 [5:10:44<05:35,  1.36it/s]
1|25427|Loss: 0.8677088022232056:  98%|█████████▊| 25427/25880 [5:10:44<05:22,  1.41it/s]
1|25428|Loss: 0.8304750919342041:  98%|█████████▊| 25427/25880 [5:10:45<05:22,  1.41it/s]
1|25428|Loss: 0.8304750919342041:  98%|█████████▊| 25428/25880 [5:10:45<05:29,  1.37it/s]
1|25429|Loss: 0.8869255781173706:  98%|█████████▊| 25428/25880 [5:10:46<05:29,  1.37it/s]
1|25429|Loss: 0.8869255781173706:  98%|█████████▊| 25429/25880 [5:10:46<05:28,  1.37it/s]
1|25430|Loss: 0.8571880459785461:  98%|█████████▊| 25429/25880 [5:10:46<05:28,  1.37it/s]
1|25430|Loss: 0.8571880459785461:  98%|█████████▊| 25430/25880 [5:10:47<05:23,  1.39it/s]
1|25431|Loss: 0.8221353888511658:  98%|█████████▊| 25430/25880 [5:10:47<05:23,  1.39it/s]
1|25431|Loss: 0.8221353888511658:  98%|█████████▊| 25431/25880 [5:10:47<05:00,  1.50it/s]
1|25432|Loss: 0.7919859290122986:  98%|█████████▊| 25431/25880 [5:10:48<05:00,  1.50it/s]
1|25432|Loss: 0.7919859290122986:  98%|█████████▊| 25432/25880 [5:10:48<04:47,  1.56it/s]
1|25433|Loss: 0.7259481549263:  98%|█████████▊| 25432/25880 [5:10:48<04:47,  1.56it/s]   
1|25433|Loss: 0.7259481549263:  98%|█████████▊| 25433/25880 [5:10:48<04:32,  1.64it/s]
1|25434|Loss: 0.8877161145210266:  98%|█████████▊| 25433/25880 [5:10:49<04:32,  1.64it/s]
1|25434|Loss: 0.8877161145210266:  98%|█████████▊| 25434/25880 [5:10:49<04:50,  1.53it/s]
1|25435|Loss: 0.8426684737205505:  98%|█████████▊| 25434/25880 [5:10:50<04:50,  1.53it/s]
1|25435|Loss: 0.8426684737205505:  98%|█████████▊| 25435/25880 [5:10:50<05:04,  1.46it/s]
1|25436|Loss: 0.7748812437057495:  98%|█████████▊| 25435/25880 [5:10:50<05:04,  1.46it/s]
1|25436|Loss: 0.7748812437057495:  98%|█████████▊| 25436/25880 [5:10:51<05:19,  1.39it/s]
1|25437|Loss: 0.8512922525405884:  98%|█████████▊| 25436/25880 [5:10:51<05:19,  1.39it/s]
1|25437|Loss: 0.8512922525405884:  98%|█████████▊| 25437/25880 [5:10:51<05:18,  1.39it/s]
1|25438|Loss: 0.7925129532814026:  98%|█████████▊| 25437/25880 [5:10:52<05:18,  1.39it/s]
1|25438|Loss: 0.7925129532814026:  98%|█████████▊| 25438/25880 [5:10:52<05:18,  1.39it/s]
1|25439|Loss: 0.9236905574798584:  98%|█████████▊| 25438/25880 [5:10:53<05:18,  1.39it/s]
1|25439|Loss: 0.9236905574798584:  98%|█████████▊| 25439/25880 [5:10:53<05:25,  1.35it/s]
1|25440|Loss: 0.8083456754684448:  98%|█████████▊| 25439/25880 [5:10:53<05:25,  1.35it/s]
1|25440|Loss: 0.8083456754684448:  98%|█████████▊| 25440/25880 [5:10:54<05:11,  1.41it/s]
1|25441|Loss: 0.8525646924972534:  98%|█████████▊| 25440/25880 [5:10:54<05:11,  1.41it/s]
1|25441|Loss: 0.8525646924972534:  98%|█████████▊| 25441/25880 [5:10:54<05:00,  1.46it/s]
1|25442|Loss: 0.8209512829780579:  98%|█████████▊| 25441/25880 [5:10:54<05:00,  1.46it/s]
1|25442|Loss: 0.8209512829780579:  98%|█████████▊| 25442/25880 [5:10:55<04:48,  1.52it/s]
1|25443|Loss: 0.8087982535362244:  98%|█████████▊| 25442/25880 [5:10:55<04:48,  1.52it/s]
1|25443|Loss: 0.8087982535362244:  98%|█████████▊| 25443/25880 [5:10:55<04:53,  1.49it/s]
1|25444|Loss: 0.7270732522010803:  98%|█████████▊| 25443/25880 [5:10:56<04:53,  1.49it/s]
1|25444|Loss: 0.7270732522010803:  98%|█████████▊| 25444/25880 [5:10:56<05:20,  1.36it/s]
1|25445|Loss: 0.9300664067268372:  98%|█████████▊| 25444/25880 [5:10:57<05:20,  1.36it/s]
1|25445|Loss: 0.9300664067268372:  98%|█████████▊| 25445/25880 [5:10:57<05:33,  1.30it/s]
1|25446|Loss: 0.7941756248474121:  98%|█████████▊| 25445/25880 [5:10:58<05:33,  1.30it/s]
1|25446|Loss: 0.7941756248474121:  98%|█████████▊| 25446/25880 [5:10:58<05:32,  1.31it/s]
1|25447|Loss: 0.8900653123855591:  98%|█████████▊| 25446/25880 [5:10:58<05:32,  1.31it/s]
1|25447|Loss: 0.8900653123855591:  98%|█████████▊| 25447/25880 [5:10:59<05:27,  1.32it/s]
1|25448|Loss: 0.9036331176757812:  98%|█████████▊| 25447/25880 [5:10:59<05:27,  1.32it/s]
1|25448|Loss: 0.9036331176757812:  98%|████��████▊| 25448/25880 [5:10:59<05:02,  1.43it/s]
1|25449|Loss: 0.9078962206840515:  98%|█████████▊| 25448/25880 [5:11:00<05:02,  1.43it/s]
1|25449|Loss: 0.9078962206840515:  98%|█████████▊| 25449/25880 [5:11:00<04:58,  1.44it/s]
1|25450|Loss: 0.8698005676269531:  98%|█████████▊| 25449/25880 [5:11:00<04:58,  1.44it/s]
1|25450|Loss: 0.8698005676269531:  98%|█████████▊| 25450/25880 [5:11:01<04:58,  1.44it/s]
1|25451|Loss: 0.691069483757019:  98%|█████████▊| 25450/25880 [5:11:01<04:58,  1.44it/s] 
1|25451|Loss: 0.691069483757019:  98%|█████████▊| 25451/25880 [5:11:01<04:49,  1.48it/s]
1|25452|Loss: 0.6643792986869812:  98%|█████████▊| 25451/25880 [5:11:02<04:49,  1.48it/s]
1|25452|Loss: 0.6643792986869812:  98%|█████████▊| 25452/25880 [5:11:02<04:52,  1.46it/s]
1|25453|Loss: 0.867974579334259:  98%|█████████▊| 25452/25880 [5:11:02<04:52,  1.46it/s] 
1|25453|Loss: 0.867974579334259:  98%|█████████▊| 25453/25880 [5:11:03<05:08,  1.38it/s]
1|25454|Loss: 0.6121691465377808:  98%|█████████▊| 25453/25880 [5:11:03<05:08,  1.38it/s]
1|25454|Loss: 0.6121691465377808:  98%|█████████▊| 25454/25880 [5:11:04<05:10,  1.37it/s]
1|25455|Loss: 0.8743360638618469:  98%|█████████▊| 25454/25880 [5:11:04<05:10,  1.37it/s]
1|25455|Loss: 0.8743360638618469:  98%|█████████▊| 25455/25880 [5:11:04<05:21,  1.32it/s]
1|25456|Loss: 0.8448793292045593:  98%|█████████▊| 25455/25880 [5:11:05<05:21,  1.32it/s]
1|25456|Loss: 0.8448793292045593:  98%|█████████▊| 25456/25880 [5:11:05<05:12,  1.36it/s]
1|25457|Loss: 0.7536168098449707:  98%|█████████▊| 25456/25880 [5:11:05<05:12,  1.36it/s]
1|25457|Loss: 0.7536168098449707:  98%|█████████▊| 25457/25880 [5:11:06<05:09,  1.37it/s]
1|25458|Loss: 0.9083016514778137:  98%|█████████▊| 25457/25880 [5:11:06<05:09,  1.37it/s]
1|25458|Loss: 0.9083016514778137:  98%|█████████▊| 25458/25880 [5:11:06<04:58,  1.41it/s]
1|25459|Loss: 0.7845637202262878:  98%|█████████▊| 25458/25880 [5:11:07<04:58,  1.41it/s]
1|25459|Loss: 0.7845637202262878:  98%|█████████▊| 25459/25880 [5:11:07<04:54,  1.43it/s]
1|25460|Loss: 0.8735571503639221:  98%|█████████▊| 25459/25880 [5:11:07<04:54,  1.43it/s]
1|25460|Loss: 0.8735571503639221:  98%|█████████▊| 25460/25880 [5:11:08<05:06,  1.37it/s]
1|25461|Loss: 0.8213933706283569:  98%|█████████▊| 25460/25880 [5:11:08<05:06,  1.37it/s]
1|25461|Loss: 0.8213933706283569:  98%|█████████▊| 25461/25880 [5:11:08<04:50,  1.44it/s]
1|25462|Loss: 0.7137816548347473:  98%|█████████▊| 25461/25880 [5:11:09<04:50,  1.44it/s]
1|25462|Loss: 0.7137816548347473:  98%|█████████▊| 25462/25880 [5:11:09<04:51,  1.43it/s]
1|25463|Loss: 0.8783648610115051:  98%|█████████▊| 25462/25880 [5:11:10<04:51,  1.43it/s]
1|25463|Loss: 0.8783648610115051:  98%|█████████▊| 25463/25880 [5:11:10<04:31,  1.54it/s]
1|25464|Loss: 0.5952187180519104:  98%|█████████▊| 25463/25880 [5:11:10<04:31,  1.54it/s]
1|25464|Loss: 0.5952187180519104:  98%|█████████▊| 25464/25880 [5:11:11<05:00,  1.39it/s]
1|25465|Loss: 0.7825977206230164:  98%|█████████▊| 25464/25880 [5:11:11<05:00,  1.39it/s]
1|25465|Loss: 0.7825977206230164:  98%|█████████▊| 25465/25880 [5:11:12<05:21,  1.29it/s]
1|25466|Loss: 0.8893296122550964:  98%|█████████▊| 25465/25880 [5:11:12<05:21,  1.29it/s]
1|25466|Loss: 0.8893296122550964:  98%|█████████▊| 25466/25880 [5:11:12<05:15,  1.31it/s]
1|25467|Loss: 0.9711049795150757:  98%|█████████▊| 25466/25880 [5:11:13<05:15,  1.31it/s]
1|25467|Loss: 0.9711049795150757:  98%|█████████▊| 25467/25880 [5:11:13<04:54,  1.40it/s]
1|25468|Loss: 0.7981264591217041:  98%|█████████▊| 25467/25880 [5:11:13<04:54,  1.40it/s]
1|25468|Loss: 0.7981264591217041:  98%|█████████▊| 25468/25880 [5:11:13<04:32,  1.51it/s]
1|25469|Loss: 0.8875352144241333:  98%|█████████▊| 25468/25880 [5:11:14<04:32,  1.51it/s]
1|25469|Loss: 0.8875352144241333:  98%|█████████▊| 25469/25880 [5:11:14<04:24,  1.56it/s]
1|25470|Loss: 0.8858649730682373:  98%|█████████▊| 25469/25880 [5:11:14<04:24,  1.56it/s]
1|25470|Loss: 0.8858649730682373:  98%|█████████▊| 25470/25880 [5:11:15<04:33,  1.50it/s]
1|25471|Loss: 0.9795857667922974:  98%|█████████▊| 25470/25880 [5:11:15<04:33,  1.50it/s]
1|25471|Loss: 0.9795857667922974:  98%|█████████▊| 25471/25880 [5:11:16<04:51,  1.40it/s]
1|25472|Loss: 0.9355636239051819:  98%|█████████▊| 25471/25880 [5:11:16<04:51,  1.40it/s]
1|25472|Loss: 0.9355636239051819:  98%|█████████▊| 25472/25880 [5:11:16<04:37,  1.47it/s]
1|25473|Loss: 0.9476304054260254:  98%|█████████▊| 25472/25880 [5:11:16<04:37,  1.47it/s]
1|25473|Loss: 0.9476304054260254:  98%|█████████▊| 25473/25880 [5:11:17<04:38,  1.46it/s]
1|25474|Loss: 0.8975025415420532:  98%|█████████▊| 25473/25880 [5:11:17<04:38,  1.46it/s]
1|25474|Loss: 0.8975025415420532:  98%|█████████▊| 25474/25880 [5:11:17<04:32,  1.49it/s]
1|25475|Loss: 0.7979142069816589:  98%|█████████▊| 25474/25880 [5:11:18<04:32,  1.49it/s]
1|25475|Loss: 0.7979142069816589:  98%|█████████▊| 25475/25880 [5:11:18<04:49,  1.40it/s]
1|25476|Loss: 0.7910263538360596:  98%|█████████▊| 25475/25880 [5:11:19<04:49,  1.40it/s]
1|25476|Loss: 0.7910263538360596:  98%|█████████▊| 25476/25880 [5:11:19<04:55,  1.37it/s]
1|25477|Loss: 0.7562711238861084:  98%|█████████▊| 25476/25880 [5:11:20<04:55,  1.37it/s]
1|25477|Loss: 0.7562711238861084:  98%|█████████▊| 25477/25880 [5:11:20<05:09,  1.30it/s]
1|25478|Loss: 0.7777325510978699:  98%|█████████▊| 25477/25880 [5:11:20<05:09,  1.30it/s]
1|25478|Loss: 0.7777325510978699:  98%|█████████▊| 25478/25880 [5:11:21<05:05,  1.31it/s]
1|25479|Loss: 0.7218249440193176:  98%|█████████▊| 25478/25880 [5:11:21<05:05,  1.31it/s]
1|25479|Loss: 0.7218249440193176:  98%|█████████▊| 25479/25880 [5:11:21<04:36,  1.45it/s]
1|25480|Loss: 0.9104239344596863:  98%|█████████▊| 25479/25880 [5:11:21<04:36,  1.45it/s]
1|25480|Loss: 0.9104239344596863:  98%|█████████▊| 25480/25880 [5:11:22<04:13,  1.58it/s]
1|25481|Loss: 0.808970034122467:  98%|█████████▊| 25480/25880 [5:11:22<04:13,  1.58it/s] 
1|25481|Loss: 0.808970034122467:  98%|█████████▊| 25481/25880 [5:11:23<04:36,  1.44it/s]
1|25482|Loss: 1.1494790315628052:  98%|█████████▊| 25481/25880 [5:11:23<04:36,  1.44it/s]
1|25482|Loss: 1.1494790315628052:  98%|█████████▊| 25482/25880 [5:11:23<04:49,  1.38it/s]
1|25483|Loss: 0.8502467274665833:  98%|█████████▊| 25482/25880 [5:11:24<04:49,  1.38it/s]
1|25483|Loss: 0.8502467274665833:  98%|█████████▊| 25483/25880 [5:11:24<04:50,  1.37it/s]
1|25484|Loss: 0.8380069136619568:  98%|█████████▊| 25483/25880 [5:11:25<04:50,  1.37it/s]
1|25484|Loss: 0.8380069136619568:  98%|█████████▊| 25484/25880 [5:11:25<05:03,  1.31it/s]
1|25485|Loss: 0.8906394839286804:  98%|█████████▊| 25484/25880 [5:11:25<05:03,  1.31it/s]
1|25485|Loss: 0.8906394839286804:  98%|█████████▊| 25485/25880 [5:11:26<05:09,  1.28it/s]
1|25486|Loss: 0.8196180462837219:  98%|█████████▊| 25485/25880 [5:11:26<05:09,  1.28it/s]
1|25486|Loss: 0.8196180462837219:  98%|█████████▊| 25486/25880 [5:11:26<05:05,  1.29it/s]
1|25487|Loss: 0.7902785539627075:  98%|█████████▊| 25486/25880 [5:11:27<05:05,  1.29it/s]
1|25487|Loss: 0.7902785539627075:  98%|█████████▊| 25487/25880 [5:11:27<04:57,  1.32it/s]
1|25488|Loss: 0.7518965005874634:  98%|█████████▊| 25487/25880 [5:11:28<04:57,  1.32it/s]
1|25488|Loss: 0.7518965005874634:  98%|█████████▊| 25488/25880 [5:11:28<05:03,  1.29it/s]
1|25489|Loss: 0.8410639762878418:  98%|█████████▊| 25488/25880 [5:11:28<05:03,  1.29it/s]
1|25489|Loss: 0.8410639762878418:  98%|█████████▊| 25489/25880 [5:11:29<04:52,  1.34it/s]
1|25490|Loss: 0.8623774647712708:  98%|█████████▊| 25489/25880 [5:11:29<04:52,  1.34it/s]
1|25490|Loss: 0.8623774647712708:  98%|█████████▊| 25490/25880 [5:11:29<04:36,  1.41it/s]
1|25491|Loss: 0.8406167030334473:  98%|█████████▊| 25490/25880 [5:11:30<04:36,  1.41it/s]
1|25491|Loss: 0.8406167030334473:  98%|█████████▊| 25491/25880 [5:11:30<04:36,  1.41it/s]
1|25492|Loss: 0.8290094137191772:  98%|█████████▊| 25491/25880 [5:11:30<04:36,  1.41it/s]
1|25492|Loss: 0.8290094137191772:  99%|█████████▊| 25492/25880 [5:11:31<04:35,  1.41it/s]
1|25493|Loss: 0.8534676432609558:  99%|█████████▊| 25492/25880 [5:11:31<04:35,  1.41it/s]
1|25493|Loss: 0.8534676432609558:  99%|█████████▊| 25493/25880 [5:11:31<04:36,  1.40it/s]
1|25494|Loss: 0.7163885235786438:  99%|█████████▊| 25493/25880 [5:11:32<04:36,  1.40it/s]
1|25494|Loss: 0.7163885235786438:  99%|█████████▊| 25494/25880 [5:11:32<04:26,  1.45it/s]
1|25495|Loss: 0.9607204794883728:  99%|█████████▊| 25494/25880 [5:11:32<04:26,  1.45it/s]
1|25495|Loss: 0.9607204794883728:  99%|█████████▊| 25495/25880 [5:11:33<04:20,  1.48it/s]
1|25496|Loss: 0.6463976502418518:  99%|█████████▊| 25495/25880 [5:11:33<04:20,  1.48it/s]
1|25496|Loss: 0.6463976502418518:  99%|█████████▊| 25496/25880 [5:11:33<04:24,  1.45it/s]
1|25497|Loss: 0.8753196001052856:  99%|█████████▊| 25496/25880 [5:11:34<04:24,  1.45it/s]
1|25497|Loss: 0.8753196001052856:  99%|█████████▊| 25497/25880 [5:11:34<04:26,  1.44it/s]
1|25498|Loss: 0.769692063331604:  99%|█████████▊| 25497/25880 [5:11:35<04:26,  1.44it/s] 
1|25498|Loss: 0.769692063331604:  99%|█████████▊| 25498/25880 [5:11:35<04:33,  1.39it/s]
1|25499|Loss: 0.7793393135070801:  99%|█████████▊| 25498/25880 [5:11:35<04:33,  1.39it/s]
1|25499|Loss: 0.7793393135070801:  99%|█████████▊| 25499/25880 [5:11:36<04:28,  1.42it/s]
1|25500|Loss: 0.717231035232544:  99%|█████████▊| 25499/25880 [5:11:36<04:28,  1.42it/s] 
1|25500|Loss: 0.717231035232544:  99%|█████████▊| 25500/25880 [5:11:36<04:30,  1.41it/s]
1|25501|Loss: 0.7300220727920532:  99%|█████████▊| 25500/25880 [5:11:37<04:30,  1.41it/s]
1|25501|Loss: 0.7300220727920532:  99%|█████████▊| 25501/25880 [5:11:37<04:19,  1.46it/s]
1|25502|Loss: 0.8761922121047974:  99%|█████████▊| 25501/25880 [5:11:37<04:19,  1.46it/s]
1|25502|Loss: 0.8761922121047974:  99%|█████████▊| 25502/25880 [5:11:38<04:33,  1.38it/s]
1|25503|Loss: 0.8479436635971069:  99%|█████████▊| 25502/25880 [5:11:38<04:33,  1.38it/s]
1|25503|Loss: 0.8479436635971069:  99%|█████████▊| 25503/25880 [5:11:38<04:19,  1.45it/s]
1|25504|Loss: 0.6628568768501282:  99%|█████████▊| 25503/25880 [5:11:39<04:19,  1.45it/s]
1|25504|Loss: 0.6628568768501282:  99%|█████████▊| 25504/25880 [5:11:39<04:03,  1.54it/s]
1|25505|Loss: 0.7479779124259949:  99%|█████████▊| 25504/25880 [5:11:39<04:03,  1.54it/s]
1|25505|Loss: 0.7479779124259949:  99%|█████████▊| 25505/25880 [5:11:40<04:05,  1.53it/s]
1|25506|Loss: 0.889954686164856:  99%|█████████▊| 25505/25880 [5:11:40<04:05,  1.53it/s] 
1|25506|Loss: 0.889954686164856:  99%|█████████▊| 25506/25880 [5:11:40<04:17,  1.45it/s]
1|25507|Loss: 0.9705379009246826:  99%|█████████▊| 25506/25880 [5:11:41<04:17,  1.45it/s]
1|25507|Loss: 0.9705379009246826:  99%|█████████▊| 25507/25880 [5:11:41<04:24,  1.41it/s]
1|25508|Loss: 0.7899227738380432:  99%|█████████▊| 25507/25880 [5:11:42<04:24,  1.41it/s]
1|25508|Loss: 0.7899227738380432:  99%|█████████▊| 25508/25880 [5:11:42<04:17,  1.45it/s]
1|25509|Loss: 0.8651806712150574:  99%|█████████▊| 25508/25880 [5:11:42<04:17,  1.45it/s]
1|25509|Loss: 0.8651806712150574:  99%|█████████▊| 25509/25880 [5:11:43<04:23,  1.41it/s]
1|25510|Loss: 0.913984477519989:  99%|█████████▊| 25509/25880 [5:11:43<04:23,  1.41it/s] 
1|25510|Loss: 0.913984477519989:  99%|█████████▊| 25510/25880 [5:11:43<04:26,  1.39it/s]
1|25511|Loss: 0.9973486065864563:  99%|█████████▊| 25510/25880 [5:11:44<04:26,  1.39it/s]
1|25511|Loss: 0.9973486065864563:  99%|█████████▊| 25511/25880 [5:11:44<04:35,  1.34it/s]
1|25512|Loss: 0.8534886240959167:  99%|█████████▊| 25511/25880 [5:11:45<04:35,  1.34it/s]
1|25512|Loss: 0.8534886240959167:  99%|█████████▊| 25512/25880 [5:11:45<04:34,  1.34it/s]
1|25513|Loss: 0.7992441058158875:  99%|█████████▊| 25512/25880 [5:11:45<04:34,  1.34it/s]
1|25513|Loss: 0.7992441058158875:  99%|█████████▊| 25513/25880 [5:11:45<04:22,  1.40it/s]
1|25514|Loss: 0.7735984921455383:  99%|█████████▊| 25513/25880 [5:11:46<04:22,  1.40it/s]
1|25514|Loss: 0.7735984921455383:  99%|█████████▊| 25514/25880 [5:11:46<04:08,  1.47it/s]
1|25515|Loss: 0.7907943725585938:  99%|█████████▊| 25514/25880 [5:11:46<04:08,  1.47it/s]
1|25515|Loss: 0.7907943725585938:  99%|█████████▊| 25515/25880 [5:11:47<04:21,  1.40it/s]
1|25516|Loss: 0.8640944957733154:  99%|█████████▊| 25515/25880 [5:11:47<04:21,  1.40it/s]
1|25516|Loss: 0.8640944957733154:  99%|█████████▊| 25516/25880 [5:11:48<04:13,  1.44it/s]
1|25517|Loss: 0.7695140838623047:  99%|█████████▊| 25516/25880 [5:11:48<04:13,  1.44it/s]
1|25517|Loss: 0.7695140838623047:  99%|█████████▊| 25517/25880 [5:11:48<04:13,  1.43it/s]
1|25518|Loss: 0.784812867641449:  99%|█████████▊| 25517/25880 [5:11:49<04:13,  1.43it/s] 
1|25518|Loss: 0.784812867641449:  99%|█████████▊| 25518/25880 [5:11:49<04:15,  1.42it/s]
1|25519|Loss: 0.883308470249176:  99%|█████████▊| 25518/25880 [5:11:49<04:15,  1.42it/s]
1|25519|Loss: 0.883308470249176:  99%|█████████▊| 25519/25880 [5:11:50<04:07,  1.46it/s]
1|25520|Loss: 0.8445634245872498:  99%|█████████▊| 25519/25880 [5:11:50<04:07,  1.46it/s]
1|25520|Loss: 0.8445634245872498:  99%|█████████▊| 25520/25880 [5:11:50<03:55,  1.53it/s]
1|25521|Loss: 1.0184047222137451:  99%|█████████▊| 25520/25880 [5:11:51<03:55,  1.53it/s]
1|25521|Loss: 1.0184047222137451:  99%|█████████▊| 25521/25880 [5:11:51<03:50,  1.56it/s]
1|25522|Loss: 0.9033103585243225:  99%|█████████▊| 25521/25880 [5:11:51<03:50,  1.56it/s]
1|25522|Loss: 0.9033103585243225:  99%|█████████▊| 25522/25880 [5:11:52<04:02,  1.48it/s]
1|25523|Loss: 0.8431019186973572:  99%|█████████▊| 25522/25880 [5:11:52<04:02,  1.48it/s]
1|25523|Loss: 0.8431019186973572:  99%|█████████▊| 25523/25880 [5:11:52<04:09,  1.43it/s]
1|25524|Loss: 0.8016011118888855:  99%|█████████▊| 25523/25880 [5:11:53<04:09,  1.43it/s]
1|25524|Loss: 0.8016011118888855:  99%|█████████▊| 25524/25880 [5:11:53<04:00,  1.48it/s]
1|25525|Loss: 0.7839120626449585:  99%|█████████▊| 25524/25880 [5:11:53<04:00,  1.48it/s]
1|25525|Loss: 0.7839120626449585:  99%|█████████▊| 25525/25880 [5:11:54<03:51,  1.54it/s]
1|25526|Loss: 0.8520780801773071:  99%|█████████▊| 25525/25880 [5:11:54<03:51,  1.54it/s]
1|25526|Loss: 0.8520780801773071:  99%|█████████▊| 25526/25880 [5:11:54<03:40,  1.61it/s]
1|25527|Loss: 0.9032924175262451:  99%|█████████▊| 25526/25880 [5:11:54<03:40,  1.61it/s]
1|25527|Loss: 0.9032924175262451:  99%|█████████▊| 25527/25880 [5:11:55<03:56,  1.49it/s]
1|25528|Loss: 0.8327302932739258:  99%|█████████▊| 25527/25880 [5:11:55<03:56,  1.49it/s]
1|25528|Loss: 0.8327302932739258:  99%|█████████▊| 25528/25880 [5:11:56<04:05,  1.43it/s]
1|25529|Loss: 0.9203357696533203:  99%|█████████▊| 25528/25880 [5:11:56<04:05,  1.43it/s]
1|25529|Loss: 0.9203357696533203:  99%|█████████▊| 25529/25880 [5:11:56<04:19,  1.35it/s]
1|25530|Loss: 0.7477841377258301:  99%|█████████▊| 25529/25880 [5:11:57<04:19,  1.35it/s]
1|25530|Loss: 0.7477841377258301:  99%|█████████▊| 25530/25880 [5:11:57<04:29,  1.30it/s]
1|25531|Loss: 0.8935230374336243:  99%|█████████▊| 25530/25880 [5:11:58<04:29,  1.30it/s]
1|25531|Loss: 0.8935230374336243:  99%|█████████▊| 25531/25880 [5:11:58<04:32,  1.28it/s]
1|25532|Loss: 0.8726389408111572:  99%|█████████▊| 25531/25880 [5:11:58<04:32,  1.28it/s]
1|25532|Loss: 0.8726389408111572:  99%|█████████▊| 25532/25880 [5:11:59<04:04,  1.42it/s]
1|25533|Loss: 0.9122899174690247:  99%|█████████▊| 25532/25880 [5:11:59<04:04,  1.42it/s]
1|25533|Loss: 0.9122899174690247:  99%|█████████▊| 25533/25880 [5:11:59<04:05,  1.41it/s]
1|25534|Loss: 0.771748960018158:  99%|█████████▊| 25533/25880 [5:12:00<04:05,  1.41it/s] 
1|25534|Loss: 0.771748960018158:  99%|█████████▊| 25534/25880 [5:12:00<04:01,  1.43it/s]
1|25535|Loss: 0.9451525807380676:  99%|█████████▊| 25534/25880 [5:12:00<04:01,  1.43it/s]
1|25535|Loss: 0.9451525807380676:  99%|█████████▊| 25535/25880 [5:12:01<04:11,  1.37it/s]
1|25536|Loss: 0.8596662878990173:  99%|█████████▊| 25535/25880 [5:12:01<04:11,  1.37it/s]
1|25536|Loss: 0.8596662878990173:  99%|█████████▊| 25536/25880 [5:12:02<04:18,  1.33it/s]
1|25537|Loss: 0.8153361082077026:  99%|█████████▊| 25536/25880 [5:12:02<04:18,  1.33it/s]
1|25537|Loss: 0.8153361082077026:  99%|█████████▊| 25537/25880 [5:12:02<04:27,  1.28it/s]
1|25538|Loss: 0.8566211462020874:  99%|█████████▊| 25537/25880 [5:12:03<04:27,  1.28it/s]
1|25538|Loss: 0.8566211462020874:  99%|█████████▊| 25538/25880 [5:12:03<04:22,  1.30it/s]
1|25539|Loss: 0.733664870262146:  99%|█████████▊| 25538/25880 [5:12:04<04:22,  1.30it/s] 
1|25539|Loss: 0.733664870262146:  99%|█████████▊| 25539/25880 [5:12:04<04:09,  1.37it/s]
1|25540|Loss: 0.8176276087760925:  99%|█████████▊| 25539/25880 [5:12:04<04:09,  1.37it/s]
1|25540|Loss: 0.8176276087760925:  99%|█████████▊| 25540/25880 [5:12:04<03:57,  1.43it/s]
1|25541|Loss: 0.9485757350921631:  99%|█████████▊| 25540/25880 [5:12:05<03:57,  1.43it/s]
1|25541|Loss: 0.9485757350921631:  99%|█████████▊| 25541/25880 [5:12:05<04:06,  1.38it/s]
1|25542|Loss: 0.8848916292190552:  99%|█████████▊| 25541/25880 [5:12:06<04:06,  1.38it/s]
1|25542|Loss: 0.8848916292190552:  99%|█████████▊| 25542/25880 [5:12:06<03:55,  1.44it/s]
1|25543|Loss: 0.6834810972213745:  99%|█████████▊| 25542/25880 [5:12:06<03:55,  1.44it/s]
1|25543|Loss: 0.6834810972213745:  99%|█████████▊| 25543/25880 [5:12:07<04:04,  1.38it/s]
1|25544|Loss: 0.8175281286239624:  99%|█████████▊| 25543/25880 [5:12:07<04:04,  1.38it/s]
1|25544|Loss: 0.8175281286239624:  99%|█████████▊| 25544/25880 [5:12:08<04:12,  1.33it/s]
1|25545|Loss: 0.8021231293678284:  99%|█████████▊| 25544/25880 [5:12:08<04:12,  1.33it/s]
1|25545|Loss: 0.8021231293678284:  99%|█████████▊| 25545/25880 [5:12:08<04:19,  1.29it/s]
1|25546|Loss: 0.7934759259223938:  99%|█████████▊| 25545/25880 [5:12:09<04:19,  1.29it/s]
1|25546|Loss: 0.7934759259223938:  99%|█████████▊| 25546/25880 [5:12:09<04:17,  1.30it/s]
1|25547|Loss: 0.9420726895332336:  99%|█████████▊| 25546/25880 [5:12:10<04:17,  1.30it/s]
1|25547|Loss: 0.9420726895332336:  99%|█████████▊| 25547/25880 [5:12:10<04:31,  1.22it/s]
1|25548|Loss: 0.9513968825340271:  99%|█████████▊| 25547/25880 [5:12:10<04:31,  1.22it/s]
1|25548|Loss: 0.9513968825340271:  99%|█████████▊| 25548/25880 [5:12:11<04:05,  1.35it/s]
1|25549|Loss: 0.9156503081321716:  99%|█████████▊| 25548/25880 [5:12:11<04:05,  1.35it/s]
1|25549|Loss: 0.9156503081321716:  99%|█████████▊| 25549/25880 [5:12:11<04:02,  1.36it/s]
1|25550|Loss: 0.758289635181427:  99%|█████████▊| 25549/25880 [5:12:12<04:02,  1.36it/s] 
1|25550|Loss: 0.758289635181427:  99%|█████████▊| 25550/25880 [5:12:12<04:04,  1.35it/s]
1|25551|Loss: 0.833069384098053:  99%|█████████▊| 25550/25880 [5:12:12<04:04,  1.35it/s]
1|25551|Loss: 0.833069384098053:  99%|█████████▊| 25551/25880 [5:12:13<04:11,  1.31it/s]
1|25552|Loss: 0.9126469492912292:  99%|█████████▊| 25551/25880 [5:12:13<04:11,  1.31it/s]
1|25552|Loss: 0.9126469492912292:  99%|█████████▊| 25552/25880 [5:12:14<04:03,  1.35it/s]
1|25553|Loss: 0.8685688376426697:  99%|█████████▊| 25552/25880 [5:12:14<04:03,  1.35it/s]
1|25553|Loss: 0.8685688376426697:  99%|█████████▊| 25553/25880 [5:12:14<04:15,  1.28it/s]
1|25554|Loss: 0.7798653841018677:  99%|█████████▊| 25553/25880 [5:12:15<04:15,  1.28it/s]
1|25554|Loss: 0.7798653841018677:  99%|█████████▊| 25554/25880 [5:12:15<04:24,  1.23it/s]
1|25555|Loss: 0.7643672823905945:  99%|█████████▊| 25554/25880 [5:12:16<04:24,  1.23it/s]
1|25555|Loss: 0.7643672823905945:  99%|█████████▊| 25555/25880 [5:12:16<04:07,  1.31it/s]
1|25556|Loss: 0.9160960912704468:  99%|█████████▊| 25555/25880 [5:12:16<04:07,  1.31it/s]
1|25556|Loss: 0.9160960912704468:  99%|█████████▊| 25556/25880 [5:12:17<04:00,  1.35it/s]
1|25557|Loss: 0.9149126410484314:  99%|█████████▊| 25556/25880 [5:12:17<04:00,  1.35it/s]
1|25557|Loss: 0.9149126410484314:  99%|█████████▉| 25557/25880 [5:12:17<03:49,  1.41it/s]
1|25558|Loss: 0.8378260731697083:  99%|█████████▉| 25557/25880 [5:12:18<03:49,  1.41it/s]
1|25558|Loss: 0.8378260731697083:  99%|█████████▉| 25558/25880 [5:12:18<03:50,  1.40it/s]
1|25559|Loss: 0.8897968530654907:  99%|█████████▉| 25558/25880 [5:12:18<03:50,  1.40it/s]
1|25559|Loss: 0.8897968530654907:  99%|█████████▉| 25559/25880 [5:12:19<03:56,  1.36it/s]
1|25560|Loss: 0.968027651309967:  99%|█████████▉| 25559/25880 [5:12:19<03:56,  1.36it/s] 
1|25560|Loss: 0.968027651309967:  99%|█████████▉| 25560/25880 [5:12:20<03:54,  1.36it/s]
1|25561|Loss: 0.8557068109512329:  99%|█████████▉| 25560/25880 [5:12:20<03:54,  1.36it/s]
1|25561|Loss: 0.8557068109512329:  99%|█████████▉| 25561/25880 [5:12:20<03:37,  1.47it/s]
1|25562|Loss: 0.7910491824150085:  99%|█████████▉| 25561/25880 [5:12:20<03:37,  1.47it/s]
1|25562|Loss: 0.7910491824150085:  99%|█████████▉| 25562/25880 [5:12:21<03:28,  1.53it/s]
1|25563|Loss: 0.8335555791854858:  99%|█████████▉| 25562/25880 [5:12:21<03:28,  1.53it/s]
1|25563|Loss: 0.8335555791854858:  99%|█████████▉| 25563/25880 [5:12:21<03:22,  1.57it/s]
1|25564|Loss: 0.9778475761413574:  99%|█████████▉| 25563/25880 [5:12:22<03:22,  1.57it/s]
1|25564|Loss: 0.9778475761413574:  99%|█████████▉| 25564/25880 [5:12:22<03:18,  1.59it/s]
1|25565|Loss: 0.8079395294189453:  99%|█████████▉| 25564/25880 [5:12:22<03:18,  1.59it/s]
1|25565|Loss: 0.8079395294189453:  99%|█████████▉| 25565/25880 [5:12:23<03:30,  1.50it/s]
1|25566|Loss: 0.809339702129364:  99%|█████████▉| 25565/25880 [5:12:23<03:30,  1.50it/s] 
1|25566|Loss: 0.809339702129364:  99%|█████████▉| 25566/25880 [5:12:23<03:30,  1.49it/s]
1|25567|Loss: 0.8004308342933655:  99%|█████████▉| 25566/25880 [5:12:24<03:30,  1.49it/s]
1|25567|Loss: 0.8004308342933655:  99%|█████████▉| 25567/25880 [5:12:24<03:33,  1.47it/s]
1|25568|Loss: 0.8740196824073792:  99%|█████████▉| 25567/25880 [5:12:24<03:33,  1.47it/s]
1|25568|Loss: 0.8740196824073792:  99%|█████████▉| 25568/25880 [5:12:25<03:46,  1.38it/s]
1|25569|Loss: 0.8264544010162354:  99%|█████████▉| 25568/25880 [5:12:25<03:46,  1.38it/s]
1|25569|Loss: 0.8264544010162354:  99%|█████████▉| 25569/25880 [5:12:26<03:46,  1.37it/s]
1|25570|Loss: 0.8935429453849792:  99%|█████████▉| 25569/25880 [5:12:26<03:46,  1.37it/s]
1|25570|Loss: 0.8935429453849792:  99%|█████████▉| 25570/25880 [5:12:26<03:45,  1.38it/s]
1|25571|Loss: 0.769064724445343:  99%|█████████▉| 25570/25880 [5:12:27<03:45,  1.38it/s] 
1|25571|Loss: 0.769064724445343:  99%|█████████▉| 25571/25880 [5:12:27<03:49,  1.35it/s]
1|25572|Loss: 0.8600642085075378:  99%|█████████▉| 25571/25880 [5:12:28<03:49,  1.35it/s]
1|25572|Loss: 0.8600642085075378:  99%|█████████▉| 25572/25880 [5:12:28<03:50,  1.34it/s]
1|25573|Loss: 0.8952621817588806:  99%|█████████▉| 25572/25880 [5:12:28<03:50,  1.34it/s]
1|25573|Loss: 0.8952621817588806:  99%|█████████▉| 25573/25880 [5:12:29<03:49,  1.34it/s]
1|25574|Loss: 0.8979553580284119:  99%|█████████▉| 25573/25880 [5:12:29<03:49,  1.34it/s]
1|25574|Loss: 0.8979553580284119:  99%|█████████▉| 25574/25880 [5:12:29<03:50,  1.33it/s]
1|25575|Loss: 0.7538220882415771:  99%|█████████▉| 25574/25880 [5:12:30<03:50,  1.33it/s]
1|25575|Loss: 0.7538220882415771:  99%|█████████▉| 25575/25880 [5:12:30<03:49,  1.33it/s]
1|25576|Loss: 0.8619945645332336:  99%|█████████▉| 25575/25880 [5:12:31<03:49,  1.33it/s]
1|25576|Loss: 0.8619945645332336:  99%|█████████▉| 25576/25880 [5:12:31<03:39,  1.38it/s]
1|25577|Loss: 0.9258103370666504:  99%|█████████▉| 25576/25880 [5:12:31<03:39,  1.38it/s]
1|25577|Loss: 0.9258103370666504:  99%|█████████▉| 25577/25880 [5:12:32<03:52,  1.30it/s]
1|25578|Loss: 0.6866739988327026:  99%|█████████▉| 25577/25880 [5:12:32<03:52,  1.30it/s]
1|25578|Loss: 0.6866739988327026:  99%|█████████▉| 25578/25880 [5:12:32<03:53,  1.30it/s]
1|25579|Loss: 0.8754566311836243:  99%|█████████▉| 25578/25880 [5:12:33<03:53,  1.30it/s]
1|25579|Loss: 0.8754566311836243:  99%|█████████▉| 25579/25880 [5:12:33<03:41,  1.36it/s]
1|25580|Loss: 0.7523409128189087:  99%|█████████▉| 25579/25880 [5:12:34<03:41,  1.36it/s]
1|25580|Loss: 0.7523409128189087:  99%|█████████▉| 25580/25880 [5:12:34<03:48,  1.31it/s]
1|25581|Loss: 0.696820080280304:  99%|█████████▉| 25580/25880 [5:12:34<03:48,  1.31it/s] 
1|25581|Loss: 0.696820080280304:  99%|█████████▉| 25581/25880 [5:12:35<03:46,  1.32it/s]
1|25582|Loss: 0.950695812702179:  99%|█████████▉| 25581/25880 [5:12:35<03:46,  1.32it/s]
1|25582|Loss: 0.950695812702179:  99%|█████████▉| 25582/25880 [5:12:35<03:53,  1.28it/s]
1|25583|Loss: 0.8964112997055054:  99%|█████████▉| 25582/25880 [5:12:36<03:53,  1.28it/s]
1|25583|Loss: 0.8964112997055054:  99%|█████████▉| 25583/25880 [5:12:36<04:01,  1.23it/s]
1|25584|Loss: 0.8185774683952332:  99%|█████████▉| 25583/25880 [5:12:37<04:01,  1.23it/s]
1|25584|Loss: 0.8185774683952332:  99%|█████████▉| 25584/25880 [5:12:37<03:48,  1.30it/s]
1|25585|Loss: 0.7137282490730286:  99%|█████████▉| 25584/25880 [5:12:37<03:48,  1.30it/s]
1|25585|Loss: 0.7137282490730286:  99%|█████████▉| 25585/25880 [5:12:38<03:43,  1.32it/s]
1|25586|Loss: 0.8446008563041687:  99%|█████████▉| 25585/25880 [5:12:38<03:43,  1.32it/s]
1|25586|Loss: 0.8446008563041687:  99%|█████████▉| 25586/25880 [5:12:38<03:31,  1.39it/s]
1|25587|Loss: 0.8771867752075195:  99%|█████████▉| 25586/25880 [5:12:39<03:31,  1.39it/s]
1|25587|Loss: 0.8771867752075195:  99%|█████████▉| 25587/25880 [5:12:39<03:09,  1.55it/s]
1|25588|Loss: 0.7357490062713623:  99%|█████████▉| 25587/25880 [5:12:39<03:09,  1.55it/s]
1|25588|Loss: 0.7357490062713623:  99%|█████████▉| 25588/25880 [5:12:40<03:19,  1.47it/s]
1|25589|Loss: 0.9667229056358337:  99%|█████████▉| 25588/25880 [5:12:40<03:19,  1.47it/s]
1|25589|Loss: 0.9667229056358337:  99%|█████████▉| 25589/25880 [5:12:40<03:30,  1.38it/s]
1|25590|Loss: 0.7352617383003235:  99%|█████████▉| 25589/25880 [5:12:41<03:30,  1.38it/s]
1|25590|Loss: 0.7352617383003235:  99%|█████████▉| 25590/25880 [5:12:41<03:31,  1.37it/s]
1|25591|Loss: 0.8023943901062012:  99%|█████████▉| 25590/25880 [5:12:42<03:31,  1.37it/s]
1|25591|Loss: 0.8023943901062012:  99%|█████████▉| 25591/25880 [5:12:42<03:38,  1.32it/s]
1|25592|Loss: 0.8528350591659546:  99%|█████████▉| 25591/25880 [5:12:42<03:38,  1.32it/s]
1|25592|Loss: 0.8528350591659546:  99%|█████████▉| 25592/25880 [5:12:43<03:30,  1.37it/s]
1|25593|Loss: 0.8507426381111145:  99%|█████████▉| 25592/25880 [5:12:43<03:30,  1.37it/s]
1|25593|Loss: 0.8507426381111145:  99%|█████████▉| 25593/25880 [5:12:43<03:22,  1.42it/s]
1|25594|Loss: 0.784358024597168:  99%|█████████▉| 25593/25880 [5:12:44<03:22,  1.42it/s] 
1|25594|Loss: 0.784358024597168:  99%|█████████▉| 25594/25880 [5:12:44<03:16,  1.46it/s]
1|25595|Loss: 0.8322249054908752:  99%|█████████▉| 25594/25880 [5:12:44<03:16,  1.46it/s]
1|25595|Loss: 0.8322249054908752:  99%|█████████▉| 25595/25880 [5:12:45<03:07,  1.52it/s]
1|25596|Loss: 0.8231266140937805:  99%|█████████▉| 25595/25880 [5:12:45<03:07,  1.52it/s]
1|25596|Loss: 0.8231266140937805:  99%|█████████▉| 25596/25880 [5:12:45<03:16,  1.44it/s]
1|25597|Loss: 0.8576637506484985:  99%|█████████▉| 25596/25880 [5:12:46<03:16,  1.44it/s]
1|25597|Loss: 0.8576637506484985:  99%|█████████▉| 25597/25880 [5:12:46<03:13,  1.46it/s]
1|25598|Loss: 0.8135815858840942:  99%|█████████▉| 25597/25880 [5:12:46<03:13,  1.46it/s]
1|25598|Loss: 0.8135815858840942:  99%|█████████▉| 25598/25880 [5:12:47<03:13,  1.46it/s]
1|25599|Loss: 0.7599821090698242:  99%|█████████▉| 25598/25880 [5:12:47<03:13,  1.46it/s]
1|25599|Loss: 0.7599821090698242:  99%|█████████▉| 25599/25880 [5:12:47<03:07,  1.50it/s]
1|25600|Loss: 0.8507480621337891:  99%|█████████▉| 25599/25880 [5:12:48<03:07,  1.50it/s]
1|25600|Loss: 0.8507480621337891:  99%|█████████▉| 25600/25880 [5:12:48<03:11,  1.46it/s]
1|25601|Loss: 0.8366272449493408:  99%|█████████▉| 25600/25880 [5:12:49<03:11,  1.46it/s]
1|25601|Loss: 0.8366272449493408:  99%|█████████▉| 25601/25880 [5:12:49<03:28,  1.34it/s]
1|25602|Loss: 0.7379797697067261:  99%|█████████▉| 25601/25880 [5:12:49<03:28,  1.34it/s]
1|25602|Loss: 0.7379797697067261:  99%|█████████▉| 25602/25880 [5:12:50<03:20,  1.39it/s]
1|25603|Loss: 1.0046788454055786:  99%|█████████▉| 25602/25880 [5:12:50<03:20,  1.39it/s]
1|25603|Loss: 1.0046788454055786:  99%|█████████▉| 25603/25880 [5:12:50<03:21,  1.38it/s]
1|25604|Loss: 0.7114101052284241:  99%|█████████▉| 25603/25880 [5:12:51<03:21,  1.38it/s]
1|25604|Loss: 0.7114101052284241:  99%|█████████▉| 25604/25880 [5:12:51<03:16,  1.40it/s]
1|25605|Loss: 0.8118003606796265:  99%|█████████▉| 25604/25880 [5:12:51<03:16,  1.40it/s]
1|25605|Loss: 0.8118003606796265:  99%|█████████▉| 25605/25880 [5:12:52<03:01,  1.51it/s]
1|25606|Loss: 0.9810512661933899:  99%|█████████▉| 25605/25880 [5:12:52<03:01,  1.51it/s]
1|25606|Loss: 0.9810512661933899:  99%|█████████▉| 25606/25880 [5:12:52<03:03,  1.49it/s]
1|25607|Loss: 0.912586510181427:  99%|█████████▉| 25606/25880 [5:12:53<03:03,  1.49it/s] 
1|25607|Loss: 0.912586510181427:  99%|█████████▉| 25607/25880 [5:12:53<03:02,  1.49it/s]
1|25608|Loss: 0.8029941320419312:  99%|█████████▉| 25607/25880 [5:12:53<03:02,  1.49it/s]
1|25608|Loss: 0.8029941320419312:  99%|█████████▉| 25608/25880 [5:12:54<03:04,  1.48it/s]
1|25609|Loss: 0.8673838376998901:  99%|█████████▉| 25608/25880 [5:12:54<03:04,  1.48it/s]
1|25609|Loss: 0.8673838376998901:  99%|█████████▉| 25609/25880 [5:12:54<03:17,  1.37it/s]
1|25610|Loss: 0.8957024216651917:  99%|█████████▉| 25609/25880 [5:12:55<03:17,  1.37it/s]
1|25610|Loss: 0.8957024216651917:  99%|█████████▉| 25610/25880 [5:12:55<03:20,  1.35it/s]
1|25611|Loss: 0.716054379940033:  99%|█████████▉| 25610/25880 [5:12:56<03:20,  1.35it/s] 
1|25611|Loss: 0.716054379940033:  99%|█████████▉| 25611/25880 [5:12:56<03:11,  1.41it/s]
1|25612|Loss: 0.9035946130752563:  99%|█████████▉| 25611/25880 [5:12:56<03:11,  1.41it/s]
1|25612|Loss: 0.9035946130752563:  99%|█████████▉| 25612/25880 [5:12:57<03:15,  1.37it/s]
1|25613|Loss: 0.7208210825920105:  99%|█████████▉| 25612/25880 [5:12:57<03:15,  1.37it/s]
1|25613|Loss: 0.7208210825920105:  99%|█████████▉| 25613/25880 [5:12:58<03:24,  1.31it/s]
1|25614|Loss: 0.9093669056892395:  99%|█████████▉| 25613/25880 [5:12:58<03:24,  1.31it/s]
1|25614|Loss: 0.9093669056892395:  99%|█████████▉| 25614/25880 [5:12:58<03:32,  1.25it/s]
1|25615|Loss: 0.8345583081245422:  99%|█████████▉| 25614/25880 [5:12:59<03:32,  1.25it/s]
1|25615|Loss: 0.8345583081245422:  99%|█████████▉| 25615/25880 [5:12:59<03:33,  1.24it/s]
1|25616|Loss: 0.9031761288642883:  99%|█████████▉| 25615/25880 [5:13:00<03:33,  1.24it/s]
1|25616|Loss: 0.9031761288642883:  99%|█████████▉| 25616/25880 [5:13:00<03:20,  1.31it/s]
1|25617|Loss: 0.6972258687019348:  99%|█████████▉| 25616/25880 [5:13:00<03:20,  1.31it/s]
1|25617|Loss: 0.6972258687019348:  99%|█████████▉| 25617/25880 [5:13:01<03:14,  1.35it/s]
1|25618|Loss: 0.8877522349357605:  99%|█████████▉| 25617/25880 [5:13:01<03:14,  1.35it/s]
1|25618|Loss: 0.8877522349357605:  99%|█████████▉| 25618/25880 [5:13:01<03:11,  1.37it/s]
1|25619|Loss: 0.9273908734321594:  99%|█████████▉| 25618/25880 [5:13:02<03:11,  1.37it/s]
1|25619|Loss: 0.9273908734321594:  99%|█████████▉| 25619/25880 [5:13:02<02:59,  1.45it/s]
1|25620|Loss: 0.8199537396430969:  99%|█████████▉| 25619/25880 [5:13:02<02:59,  1.45it/s]
1|25620|Loss: 0.8199537396430969:  99%|█████████▉| 25620/25880 [5:13:02<02:53,  1.50it/s]
1|25621|Loss: 0.8651258945465088:  99%|█████████▉| 25620/25880 [5:13:03<02:53,  1.50it/s]
1|25621|Loss: 0.8651258945465088:  99%|█████████▉| 25621/25880 [5:13:03<02:58,  1.45it/s]
1|25622|Loss: 0.858529269695282:  99%|█████████▉| 25621/25880 [5:13:04<02:58,  1.45it/s] 
1|25622|Loss: 0.858529269695282:  99%|█████████▉| 25622/25880 [5:13:04<02:40,  1.61it/s]
1|25623|Loss: 0.7675256729125977:  99%|█████████▉| 25622/25880 [5:13:04<02:40,  1.61it/s]
1|25623|Loss: 0.7675256729125977:  99%|█████████▉| 25623/25880 [5:13:04<02:44,  1.57it/s]
1|25624|Loss: 0.8370255827903748:  99%|█████████▉| 25623/25880 [5:13:05<02:44,  1.57it/s]
1|25624|Loss: 0.8370255827903748:  99%|█████████▉| 25624/25880 [5:13:05<02:37,  1.62it/s]
1|25625|Loss: 0.7575162649154663:  99%|█████████▉| 25624/25880 [5:13:05<02:37,  1.62it/s]
1|25625|Loss: 0.7575162649154663:  99%|█████████▉| 25625/25880 [5:13:05<02:29,  1.71it/s]
1|25626|Loss: 0.6659058928489685:  99%|█████████▉| 25625/25880 [5:13:06<02:29,  1.71it/s]
1|25626|Loss: 0.6659058928489685:  99%|█████████▉| 25626/25880 [5:13:06<02:30,  1.69it/s]
1|25627|Loss: 0.9130568504333496:  99%|█████████▉| 25626/25880 [5:13:06<02:30,  1.69it/s]
1|25627|Loss: 0.9130568504333496:  99%|█████████▉| 25627/25880 [5:13:07<02:38,  1.60it/s]
1|25628|Loss: 0.9124439358711243:  99%|█████████▉| 25627/25880 [5:13:07<02:38,  1.60it/s]
1|25628|Loss: 0.9124439358711243:  99%|█████████▉| 25628/25880 [5:13:07<02:43,  1.54it/s]
1|25629|Loss: 0.883292555809021:  99%|█████████▉| 25628/25880 [5:13:08<02:43,  1.54it/s] 
1|25629|Loss: 0.883292555809021:  99%|█████████▉| 25629/25880 [5:13:08<02:46,  1.51it/s]
1|25630|Loss: 0.8232660889625549:  99%|█████████▉| 25629/25880 [5:13:09<02:46,  1.51it/s]
1|25630|Loss: 0.8232660889625549:  99%|█████████▉| 25630/25880 [5:13:09<02:41,  1.55it/s]
1|25631|Loss: 0.7379640340805054:  99%|█████████▉| 25630/25880 [5:13:09<02:41,  1.55it/s]
1|25631|Loss: 0.7379640340805054:  99%|█████████▉| 25631/25880 [5:13:10<02:52,  1.44it/s]
1|25632|Loss: 0.9505470991134644:  99%|█████████▉| 25631/25880 [5:13:10<02:52,  1.44it/s]
1|25632|Loss: 0.9505470991134644:  99%|█████████▉| 25632/25880 [5:13:10<02:51,  1.44it/s]
1|25633|Loss: 0.8478484153747559:  99%|█████████▉| 25632/25880 [5:13:11<02:51,  1.44it/s]
1|25633|Loss: 0.8478484153747559:  99%|█████████▉| 25633/25880 [5:13:11<02:53,  1.42it/s]
1|25634|Loss: 0.9004560708999634:  99%|█████████▉| 25633/25880 [5:13:11<02:53,  1.42it/s]
1|25634|Loss: 0.9004560708999634:  99%|█████████▉| 25634/25880 [5:13:12<03:01,  1.35it/s]
1|25635|Loss: 0.9483662247657776:  99%|█████████▉| 25634/25880 [5:13:12<03:01,  1.35it/s]
1|25635|Loss: 0.9483662247657776:  99%|█████████▉| 25635/25880 [5:13:13<03:06,  1.32it/s]
1|25636|Loss: 0.8404752016067505:  99%|█████████▉| 25635/25880 [5:13:13<03:06,  1.32it/s]
1|25636|Loss: 0.8404752016067505:  99%|█████████▉| 25636/25880 [5:13:14<03:15,  1.25it/s]
1|25637|Loss: 0.9632951617240906:  99%|█████████▉| 25636/25880 [5:13:14<03:15,  1.25it/s]
1|25637|Loss: 0.9632951617240906:  99%|█████████▉| 25637/25880 [5:13:14<03:17,  1.23it/s]
1|25638|Loss: 0.942730724811554:  99%|█████████▉| 25637/25880 [5:13:15<03:17,  1.23it/s] 
1|25638|Loss: 0.942730724811554:  99%|█████████▉| 25638/25880 [5:13:15<03:22,  1.19it/s]
1|25639|Loss: 0.8559300899505615:  99%|█████████▉| 25638/25880 [5:13:16<03:22,  1.19it/s]
1|25639|Loss: 0.8559300899505615:  99%|█████████▉| 25639/25880 [5:13:16<03:22,  1.19it/s]
1|25640|Loss: 0.8643313050270081:  99%|█████████▉| 25639/25880 [5:13:17<03:22,  1.19it/s]
1|25640|Loss: 0.8643313050270081:  99%|█████████▉| 25640/25880 [5:13:17<03:24,  1.17it/s]
1|25641|Loss: 0.8182324767112732:  99%|█████████▉| 25640/25880 [5:13:17<03:24,  1.17it/s]
1|25641|Loss: 0.8182324767112732:  99%|█████████▉| 25641/25880 [5:13:18<03:08,  1.26it/s]
1|25642|Loss: 0.8657613396644592:  99%|█████████▉| 25641/25880 [5:13:18<03:08,  1.26it/s]
1|25642|Loss: 0.8657613396644592:  99%|█████████▉| 25642/25880 [5:13:18<02:56,  1.35it/s]
1|25643|Loss: 0.8353297114372253:  99%|█████████▉| 25642/25880 [5:13:19<02:56,  1.35it/s]
1|25643|Loss: 0.8353297114372253:  99%|█████████▉| 25643/25880 [5:13:19<02:52,  1.38it/s]
1|25644|Loss: 0.8583464026451111:  99%|█████████▉| 25643/25880 [5:13:19<02:52,  1.38it/s]
1|25644|Loss: 0.8583464026451111:  99%|█████████▉| 25644/25880 [5:13:20<02:58,  1.32it/s]
1|25645|Loss: 0.989972710609436:  99%|█████████▉| 25644/25880 [5:13:20<02:58,  1.32it/s] 
1|25645|Loss: 0.989972710609436:  99%|█████████▉| 25645/25880 [5:13:20<02:49,  1.39it/s]
1|25646|Loss: 0.8294463753700256:  99%|█████████▉| 25645/25880 [5:13:21<02:49,  1.39it/s]
1|25646|Loss: 0.8294463753700256:  99%|█████████▉| 25646/25880 [5:13:21<02:53,  1.34it/s]
1|25647|Loss: 0.9697794914245605:  99%|█████████▉| 25646/25880 [5:13:22<02:53,  1.34it/s]
1|25647|Loss: 0.9697794914245605:  99%|█████████▉| 25647/25880 [5:13:22<02:58,  1.31it/s]
1|25648|Loss: 0.7004832625389099:  99%|█████████▉| 25647/25880 [5:13:22<02:58,  1.31it/s]
1|25648|Loss: 0.7004832625389099:  99%|█████████▉| 25648/25880 [5:13:23<02:46,  1.39it/s]
1|25649|Loss: 0.9433408379554749:  99%|█████████▉| 25648/25880 [5:13:23<02:46,  1.39it/s]
1|25649|Loss: 0.9433408379554749:  99%|█████████▉| 25649/25880 [5:13:23<02:42,  1.42it/s]
1|25650|Loss: 0.7967724800109863:  99%|█████████▉| 25649/25880 [5:13:24<02:42,  1.42it/s]
1|25650|Loss: 0.7967724800109863:  99%|█████████▉| 25650/25880 [5:13:24<02:44,  1.40it/s]
1|25651|Loss: 0.7618435621261597:  99%|█████████▉| 25650/25880 [5:13:24<02:44,  1.40it/s]
1|25651|Loss: 0.7618435621261597:  99%|█████████▉| 25651/25880 [5:13:25<02:45,  1.39it/s]
1|25652|Loss: 0.8049942851066589:  99%|█████████▉| 25651/25880 [5:13:25<02:45,  1.39it/s]
1|25652|Loss: 0.8049942851066589:  99%|█████████▉| 25652/25880 [5:13:26<02:46,  1.37it/s]
1|25653|Loss: 0.7575973272323608:  99%|█████████▉| 25652/25880 [5:13:26<02:46,  1.37it/s]
1|25653|Loss: 0.7575973272323608:  99%|█████████▉| 25653/25880 [5:13:26<02:41,  1.41it/s]
1|25654|Loss: 0.7526721954345703:  99%|█████████▉| 25653/25880 [5:13:27<02:41,  1.41it/s]
1|25654|Loss: 0.7526721954345703:  99%|█████████▉| 25654/25880 [5:13:27<02:41,  1.40it/s]
1|25655|Loss: 0.744655191898346:  99%|█████████▉| 25654/25880 [5:13:27<02:41,  1.40it/s] 
1|25655|Loss: 0.744655191898346:  99%|█████████▉| 25655/25880 [5:13:28<02:47,  1.34it/s]
1|25656|Loss: 0.7500529289245605:  99%|█████████▉| 25655/25880 [5:13:28<02:47,  1.34it/s]
1|25656|Loss: 0.7500529289245605:  99%|█████████▉| 25656/25880 [5:13:28<02:39,  1.41it/s]
1|25657|Loss: 0.9032320380210876:  99%|█████████▉| 25656/25880 [5:13:29<02:39,  1.41it/s]
1|25657|Loss: 0.9032320380210876:  99%|█████████▉| 25657/25880 [5:13:29<02:37,  1.41it/s]
1|25658|Loss: 0.8517785668373108:  99%|█████████▉| 25657/25880 [5:13:29<02:37,  1.41it/s]
1|25658|Loss: 0.8517785668373108:  99%|█████████▉| 25658/25880 [5:13:30<02:42,  1.36it/s]
1|25659|Loss: 0.8533234000205994:  99%|█████████▉| 25658/25880 [5:13:30<02:42,  1.36it/s]
1|25659|Loss: 0.8533234000205994:  99%|█████████▉| 25659/25880 [5:13:31<02:48,  1.31it/s]
1|25660|Loss: 0.8321682214736938:  99%|█████████▉| 25659/25880 [5:13:31<02:48,  1.31it/s]
1|25660|Loss: 0.8321682214736938:  99%|█████████▉| 25660/25880 [5:13:31<02:38,  1.38it/s]
1|25661|Loss: 0.7653578519821167:  99%|█████████▉| 25660/25880 [5:13:32<02:38,  1.38it/s]
1|25661|Loss: 0.7653578519821167:  99%|█████████▉| 25661/25880 [5:13:32<02:37,  1.39it/s]
1|25662|Loss: 0.8433430790901184:  99%|█████████▉| 25661/25880 [5:13:32<02:37,  1.39it/s]
1|25662|Loss: 0.8433430790901184:  99%|█████████▉| 25662/25880 [5:13:33<02:33,  1.42it/s]
1|25663|Loss: 0.8526460528373718:  99%|█████████▉| 25662/25880 [5:13:33<02:33,  1.42it/s]
1|25663|Loss: 0.8526460528373718:  99%|█████████▉| 25663/25880 [5:13:33<02:33,  1.42it/s]
1|25664|Loss: 0.9572540521621704:  99%|█████████▉| 25663/25880 [5:13:34<02:33,  1.42it/s]
1|25664|Loss: 0.9572540521621704:  99%|█████████▉| 25664/25880 [5:13:34<02:41,  1.33it/s]
1|25665|Loss: 0.8275969624519348:  99%|█████████▉| 25664/25880 [5:13:35<02:41,  1.33it/s]
1|25665|Loss: 0.8275969624519348:  99%|█████████▉| 25665/25880 [5:13:35<02:36,  1.37it/s]
1|25666|Loss: 0.7465112805366516:  99%|█████████▉| 25665/25880 [5:13:35<02:36,  1.37it/s]
1|25666|Loss: 0.7465112805366516:  99%|█████████▉| 25666/25880 [5:13:35<02:23,  1.49it/s]
1|25667|Loss: 0.8025162816047668:  99%|█████████▉| 25666/25880 [5:13:36<02:23,  1.49it/s]
1|25667|Loss: 0.8025162816047668:  99%|█████████▉| 25667/25880 [5:13:36<02:18,  1.54it/s]
1|25668|Loss: 0.7481557726860046:  99%|█████████▉| 25667/25880 [5:13:36<02:18,  1.54it/s]
1|25668|Loss: 0.7481557726860046:  99%|█████████▉| 25668/25880 [5:13:37<02:22,  1.49it/s]
1|25669|Loss: 0.8685157895088196:  99%|█████████▉| 25668/25880 [5:13:37<02:22,  1.49it/s]
1|25669|Loss: 0.8685157895088196:  99%|█████████▉| 25669/25880 [5:13:38<02:25,  1.45it/s]
1|25670|Loss: 0.7179721593856812:  99%|█████████▉| 25669/25880 [5:13:38<02:25,  1.45it/s]
1|25670|Loss: 0.7179721593856812:  99%|█████████▉| 25670/25880 [5:13:38<02:31,  1.39it/s]
1|25671|Loss: 0.7715526819229126:  99%|█████████▉| 25670/25880 [5:13:39<02:31,  1.39it/s]
1|25671|Loss: 0.7715526819229126:  99%|█████████▉| 25671/25880 [5:13:39<02:41,  1.29it/s]
1|25672|Loss: 0.8643472790718079:  99%|█████████▉| 25671/25880 [5:13:40<02:41,  1.29it/s]
1|25672|Loss: 0.8643472790718079:  99%|█████████▉| 25672/25880 [5:13:40<02:47,  1.24it/s]
1|25673|Loss: 0.7359493374824524:  99%|█████████▉| 25672/25880 [5:13:40<02:47,  1.24it/s]
1|25673|Loss: 0.7359493374824524:  99%|█████████▉| 25673/25880 [5:13:41<02:37,  1.32it/s]
1|25674|Loss: 0.8158337473869324:  99%|█████████▉| 25673/25880 [5:13:41<02:37,  1.32it/s]
1|25674|Loss: 0.8158337473869324:  99%|█████████▉| 25674/25880 [5:13:42<02:39,  1.29it/s]
1|25675|Loss: 0.8821810483932495:  99%|█████████▉| 25674/25880 [5:13:42<02:39,  1.29it/s]
1|25675|Loss: 0.8821810483932495:  99%|█████████▉| 25675/25880 [5:13:42<02:38,  1.29it/s]
1|25676|Loss: 0.715189516544342:  99%|█████████▉| 25675/25880 [5:13:43<02:38,  1.29it/s] 
1|25676|Loss: 0.715189516544342:  99%|█████████▉| 25676/25880 [5:13:43<02:34,  1.32it/s]
1|25677|Loss: 0.8096454739570618:  99%|█████████▉| 25676/25880 [5:13:43<02:34,  1.32it/s]
1|25677|Loss: 0.8096454739570618:  99%|█████████▉| 25677/25880 [5:13:44<02:27,  1.38it/s]
1|25678|Loss: 0.7246811985969543:  99%|█████████▉| 25677/25880 [5:13:44<02:27,  1.38it/s]
1|25678|Loss: 0.7246811985969543:  99%|█████████▉| 25678/25880 [5:13:44<02:24,  1.40it/s]
1|25679|Loss: 0.8118263483047485:  99%|█████████▉| 25678/25880 [5:13:45<02:24,  1.40it/s]
1|25679|Loss: 0.8118263483047485:  99%|█████████▉| 25679/25880 [5:13:45<02:27,  1.36it/s]
1|25680|Loss: 0.8077604174613953:  99%|█████████▉| 25679/25880 [5:13:46<02:27,  1.36it/s]
1|25680|Loss: 0.8077604174613953:  99%|█████████▉| 25680/25880 [5:13:46<02:14,  1.49it/s]
1|25681|Loss: 0.7114467620849609:  99%|█████████▉| 25680/25880 [5:13:46<02:14,  1.49it/s]
1|25681|Loss: 0.7114467620849609:  99%|█████████▉| 25681/25880 [5:13:46<02:17,  1.45it/s]
1|25682|Loss: 0.84461909532547:  99%|█████████▉| 25681/25880 [5:13:47<02:17,  1.45it/s]  
1|25682|Loss: 0.84461909532547:  99%|█████████▉| 25682/25880 [5:13:47<02:26,  1.35it/s]
1|25683|Loss: 0.8649976253509521:  99%|█████████▉| 25682/25880 [5:13:48<02:26,  1.35it/s]
1|25683|Loss: 0.8649976253509521:  99%|█████████▉| 25683/25880 [5:13:48<02:27,  1.34it/s]
1|25684|Loss: 0.8389940857887268:  99%|█████████▉| 25683/25880 [5:13:48<02:27,  1.34it/s]
1|25684|Loss: 0.8389940857887268:  99%|█████████▉| 25684/25880 [5:13:49<02:28,  1.32it/s]
1|25685|Loss: 0.7516260147094727:  99%|█████████▉| 25684/25880 [5:13:49<02:28,  1.32it/s]
1|25685|Loss: 0.7516260147094727:  99%|█████████▉| 25685/25880 [5:13:49<02:21,  1.38it/s]
1|25686|Loss: 0.802948534488678:  99%|█████████▉| 25685/25880 [5:13:50<02:21,  1.38it/s] 
1|25686|Loss: 0.802948534488678:  99%|█████████▉| 25686/25880 [5:13:50<02:12,  1.46it/s]
1|25687|Loss: 0.8473415970802307:  99%|█████████▉| 25686/25880 [5:13:50<02:12,  1.46it/s]
1|25687|Loss: 0.8473415970802307:  99%|█████████▉| 25687/25880 [5:13:51<02:12,  1.45it/s]
1|25688|Loss: 0.8195288181304932:  99%|█████████▉| 25687/25880 [5:13:51<02:12,  1.45it/s]
1|25688|Loss: 0.8195288181304932:  99%|█████████▉| 25688/25880 [5:13:51<02:05,  1.53it/s]
1|25689|Loss: 0.7581009864807129:  99%|█████████▉| 25688/25880 [5:13:52<02:05,  1.53it/s]
1|25689|Loss: 0.7581009864807129:  99%|█████████▉| 25689/25880 [5:13:52<01:54,  1.67it/s]
1|25690|Loss: 0.9312206506729126:  99%|█████████▉| 25689/25880 [5:13:52<01:54,  1.67it/s]
1|25690|Loss: 0.9312206506729126:  99%|█████████▉| 25690/25880 [5:13:53<02:08,  1.48it/s]
1|25691|Loss: 0.7942975759506226:  99%|█████████▉| 25690/25880 [5:13:53<02:08,  1.48it/s]
1|25691|Loss: 0.7942975759506226:  99%|█████████▉| 25691/25880 [5:13:54<02:19,  1.36it/s]
1|25692|Loss: 0.8217736482620239:  99%|█████████▉| 25691/25880 [5:13:54<02:19,  1.36it/s]
1|25692|Loss: 0.8217736482620239:  99%|█████████▉| 25692/25880 [5:13:54<02:19,  1.34it/s]
1|25693|Loss: 1.0282564163208008:  99%|█████████▉| 25692/25880 [5:13:55<02:19,  1.34it/s]
1|25693|Loss: 1.0282564163208008:  99%|█████████▉| 25693/25880 [5:13:55<02:08,  1.46it/s]
1|25694|Loss: 0.843112587928772:  99%|█████████▉| 25693/25880 [5:13:55<02:08,  1.46it/s] 
1|25694|Loss: 0.843112587928772:  99%|█████████▉| 25694/25880 [5:13:56<02:10,  1.42it/s]
1|25695|Loss: 0.9544165134429932:  99%|█████████▉| 25694/25880 [5:13:56<02:10,  1.42it/s]
1|25695|Loss: 0.9544165134429932:  99%|█████████▉| 25695/25880 [5:13:56<02:07,  1.46it/s]
1|25696|Loss: 0.8223302364349365:  99%|█████████▉| 25695/25880 [5:13:57<02:07,  1.46it/s]
1|25696|Loss: 0.8223302364349365:  99%|█████████▉| 25696/25880 [5:13:57<02:00,  1.52it/s]
1|25697|Loss: 0.7935753464698792:  99%|█████████▉| 25696/25880 [5:13:57<02:00,  1.52it/s]
1|25697|Loss: 0.7935753464698792:  99%|█████████▉| 25697/25880 [5:13:58<02:05,  1.46it/s]
1|25698|Loss: 0.8691021203994751:  99%|█████████▉| 25697/25880 [5:13:58<02:05,  1.46it/s]
1|25698|Loss: 0.8691021203994751:  99%|█████████▉| 25698/25880 [5:13:58<02:01,  1.50it/s]
1|25699|Loss: 0.8166733980178833:  99%|█████████▉| 25698/25880 [5:13:59<02:01,  1.50it/s]
1|25699|Loss: 0.8166733980178833:  99%|█████████▉| 25699/25880 [5:13:59<02:04,  1.45it/s]
1|25700|Loss: 0.793053388595581:  99%|█████████▉| 25699/25880 [5:13:59<02:04,  1.45it/s] 
1|25700|Loss: 0.793053388595581:  99%|█████████▉| 25700/25880 [5:14:00<02:06,  1.42it/s]
1|25701|Loss: 0.760227382183075:  99%|█████████▉| 25700/25880 [5:14:00<02:06,  1.42it/s]
1|25701|Loss: 0.760227382183075:  99%|█████████▉| 25701/25880 [5:14:01<02:15,  1.32it/s]
1|25702|Loss: 0.8235732913017273:  99%|█████████▉| 25701/25880 [5:14:01<02:15,  1.32it/s]
1|25702|Loss: 0.8235732913017273:  99%|█████████▉| 25702/25880 [5:14:01<02:20,  1.27it/s]
1|25703|Loss: 0.901132345199585:  99%|█████████▉| 25702/25880 [5:14:02<02:20,  1.27it/s] 
1|25703|Loss: 0.901132345199585:  99%|█████████▉| 25703/25880 [5:14:02<02:18,  1.28it/s]
1|25704|Loss: 0.9034998416900635:  99%|█████████▉| 25703/25880 [5:14:03<02:18,  1.28it/s]
1|25704|Loss: 0.9034998416900635:  99%|█████████▉| 25704/25880 [5:14:03<02:20,  1.25it/s]
1|25705|Loss: 0.8970974683761597:  99%|█████████▉| 25704/25880 [5:14:03<02:20,  1.25it/s]
1|25705|Loss: 0.8970974683761597:  99%|█████████▉| 25705/25880 [5:14:04<02:13,  1.31it/s]
1|25706|Loss: 0.7996581792831421:  99%|█████████▉| 25705/25880 [5:14:04<02:13,  1.31it/s]
1|25706|Loss: 0.7996581792831421:  99%|█████████▉| 25706/25880 [5:14:04<01:59,  1.46it/s]
1|25707|Loss: 0.8902688026428223:  99%|█████████▉| 25706/25880 [5:14:05<01:59,  1.46it/s]
1|25707|Loss: 0.8902688026428223:  99%|█████████▉| 25707/25880 [5:14:05<01:57,  1.47it/s]
1|25708|Loss: 0.8030610680580139:  99%|█████████▉| 25707/25880 [5:14:05<01:57,  1.47it/s]
1|25708|Loss: 0.8030610680580139:  99%|█████████▉| 25708/25880 [5:14:06<01:59,  1.44it/s]
1|25709|Loss: 0.8792009949684143:  99%|█████████▉| 25708/25880 [5:14:06<01:59,  1.44it/s]
1|25709|Loss: 0.8792009949684143:  99%|█████████▉| 25709/25880 [5:14:06<02:05,  1.37it/s]
1|25710|Loss: 0.8286972045898438:  99%|█████████▉| 25709/25880 [5:14:07<02:05,  1.37it/s]
1|25710|Loss: 0.8286972045898438:  99%|█████████▉| 25710/25880 [5:14:07<02:07,  1.33it/s]
1|25711|Loss: 0.9047536253929138:  99%|█████████▉| 25710/25880 [5:14:08<02:07,  1.33it/s]
1|25711|Loss: 0.9047536253929138:  99%|█████████▉| 25711/25880 [5:14:08<02:10,  1.29it/s]
1|25712|Loss: 0.8627328872680664:  99%|█████████▉| 25711/25880 [5:14:08<02:10,  1.29it/s]
1|25712|Loss: 0.8627328872680664:  99%|█████████▉| 25712/25880 [5:14:09<02:00,  1.39it/s]
1|25713|Loss: 0.8495994806289673:  99%|█████████▉| 25712/25880 [5:14:09<02:00,  1.39it/s]
1|25713|Loss: 0.8495994806289673:  99%|█████████▉| 25713/25880 [5:14:09<01:53,  1.47it/s]
1|25714|Loss: 0.948445200920105:  99%|█████████▉| 25713/25880 [5:14:10<01:53,  1.47it/s] 
1|25714|Loss: 0.948445200920105:  99%|█████████▉| 25714/25880 [5:14:10<01:58,  1.40it/s]
1|25715|Loss: 0.8992379307746887:  99%|█████████▉| 25714/25880 [5:14:10<01:58,  1.40it/s]
1|25715|Loss: 0.8992379307746887:  99%|█████████▉| 25715/25880 [5:14:11<01:58,  1.39it/s]
1|25716|Loss: 0.7473970651626587:  99%|█████████▉| 25715/25880 [5:14:11<01:58,  1.39it/s]
1|25716|Loss: 0.7473970651626587:  99%|█████████▉| 25716/25880 [5:14:12<02:02,  1.34it/s]
1|25717|Loss: 0.8869848847389221:  99%|█████████▉| 25716/25880 [5:14:12<02:02,  1.34it/s]
1|25717|Loss: 0.8869848847389221:  99%|█████████▉| 25717/25880 [5:14:12<02:01,  1.34it/s]
1|25718|Loss: 0.7716978788375854:  99%|█████████▉| 25717/25880 [5:14:13<02:01,  1.34it/s]
1|25718|Loss: 0.7716978788375854:  99%|█████████▉| 25718/25880 [5:14:13<01:59,  1.36it/s]
1|25719|Loss: 0.7283235192298889:  99%|█████████▉| 25718/25880 [5:14:13<01:59,  1.36it/s]
1|25719|Loss: 0.7283235192298889:  99%|█████████▉| 25719/25880 [5:14:14<01:54,  1.41it/s]
1|25720|Loss: 1.0157666206359863:  99%|█████████▉| 25719/25880 [5:14:14<01:54,  1.41it/s]
1|25720|Loss: 1.0157666206359863:  99%|█████████▉| 25720/25880 [5:14:14<01:47,  1.48it/s]
1|25721|Loss: 0.8950801491737366:  99%|█████████▉| 25720/25880 [5:14:15<01:47,  1.48it/s]
1|25721|Loss: 0.8950801491737366:  99%|█████████▉| 25721/25880 [5:14:15<01:49,  1.46it/s]
1|25722|Loss: 0.9204663634300232:  99%|█████████▉| 25721/25880 [5:14:15<01:49,  1.46it/s]
1|25722|Loss: 0.9204663634300232:  99%|█████████▉| 25722/25880 [5:14:16<01:54,  1.38it/s]
1|25723|Loss: 0.7449164390563965:  99%|█████████▉| 25722/25880 [5:14:16<01:54,  1.38it/s]
1|25723|Loss: 0.7449164390563965:  99%|█████████▉| 25723/25880 [5:14:17<01:54,  1.37it/s]
1|25724|Loss: 0.8575570583343506:  99%|█████████▉| 25723/25880 [5:14:17<01:54,  1.37it/s]
1|25724|Loss: 0.8575570583343506:  99%|█████████▉| 25724/25880 [5:14:17<01:59,  1.30it/s]
1|25725|Loss: 0.8546122908592224:  99%|█████████▉| 25724/25880 [5:14:18<01:59,  1.30it/s]
1|25725|Loss: 0.8546122908592224:  99%|█████████▉| 25725/25880 [5:14:18<01:58,  1.31it/s]
1|25726|Loss: 0.9877616167068481:  99%|█████████▉| 25725/25880 [5:14:19<01:58,  1.31it/s]
1|25726|Loss: 0.9877616167068481:  99%|█████████▉| 25726/25880 [5:14:19<01:55,  1.34it/s]
1|25727|Loss: 0.9436737298965454:  99%|█████████▉| 25726/25880 [5:14:19<01:55,  1.34it/s]
1|25727|Loss: 0.9436737298965454:  99%|█████████▉| 25727/25880 [5:14:19<01:47,  1.42it/s]
1|25728|Loss: 0.7433071732521057:  99%|█████████▉| 25727/25880 [5:14:20<01:47,  1.42it/s]
1|25728|Loss: 0.7433071732521057:  99%|█████████▉| 25728/25880 [5:14:20<01:50,  1.37it/s]
1|25729|Loss: 0.90472012758255:  99%|█████████▉| 25728/25880 [5:14:21<01:50,  1.37it/s]  
1|25729|Loss: 0.90472012758255:  99%|█████████▉| 25729/25880 [5:14:21<01:55,  1.31it/s]
1|25730|Loss: 0.7912800908088684:  99%|█████████▉| 25729/25880 [5:14:21<01:55,  1.31it/s]
1|25730|Loss: 0.7912800908088684:  99%|█████████▉| 25730/25880 [5:14:22<01:51,  1.35it/s]
1|25731|Loss: 0.7293464541435242:  99%|█████████▉| 25730/25880 [5:14:22<01:51,  1.35it/s]
1|25731|Loss: 0.7293464541435242:  99%|█████████▉| 25731/25880 [5:14:22<01:45,  1.42it/s]
1|25732|Loss: 0.871443510055542:  99%|█████████▉| 25731/25880 [5:14:23<01:45,  1.42it/s] 
1|25732|Loss: 0.871443510055542:  99%|█████████▉| 25732/25880 [5:14:23<01:44,  1.42it/s]
1|25733|Loss: 0.917768120765686:  99%|█████████▉| 25732/25880 [5:14:24<01:44,  1.42it/s]
1|25733|Loss: 0.917768120765686:  99%|█████████▉| 25733/25880 [5:14:24<01:47,  1.37it/s]
1|25734|Loss: 0.9716135263442993:  99%|█████████▉| 25733/25880 [5:14:24<01:47,  1.37it/s]
1|25734|Loss: 0.9716135263442993:  99%|█████████▉| 25734/25880 [5:14:25<01:50,  1.32it/s]
1|25735|Loss: 0.9195899367332458:  99%|█████████▉| 25734/25880 [5:14:25<01:50,  1.32it/s]
1|25735|Loss: 0.9195899367332458:  99%|█████████▉| 25735/25880 [5:14:25<01:49,  1.32it/s]
1|25736|Loss: 0.735091507434845:  99%|█████████▉| 25735/25880 [5:14:26<01:49,  1.32it/s] 
1|25736|Loss: 0.735091507434845:  99%|█████████▉| 25736/25880 [5:14:26<01:43,  1.38it/s]
1|25737|Loss: 0.7452408671379089:  99%|█████████▉| 25736/25880 [5:14:27<01:43,  1.38it/s]
1|25737|Loss: 0.7452408671379089:  99%|█████████▉| 25737/25880 [5:14:27<01:46,  1.35it/s]
1|25738|Loss: 1.0283305644989014:  99%|█████████▉| 25737/25880 [5:14:27<01:46,  1.35it/s]
1|25738|Loss: 1.0283305644989014:  99%|█████████▉| 25738/25880 [5:14:28<01:50,  1.29it/s]
1|25739|Loss: 0.782219409942627:  99%|█████████▉| 25738/25880 [5:14:28<01:50,  1.29it/s] 
1|25739|Loss: 0.782219409942627:  99%|█████████▉| 25739/25880 [5:14:29<01:48,  1.29it/s]
1|25740|Loss: 0.9881571531295776:  99%|█████████▉| 25739/25880 [5:14:29<01:48,  1.29it/s]
1|25740|Loss: 0.9881571531295776:  99%|█████████▉| 25740/25880 [5:14:29<01:46,  1.31it/s]
1|25741|Loss: 0.761489748954773:  99%|█████████▉| 25740/25880 [5:14:30<01:46,  1.31it/s] 
1|25741|Loss: 0.761489748954773:  99%|█████████▉| 25741/25880 [5:14:30<01:49,  1.27it/s]
1|25742|Loss: 0.9583987593650818:  99%|█████████▉| 25741/25880 [5:14:31<01:49,  1.27it/s]
1|25742|Loss: 0.9583987593650818:  99%|█████████▉| 25742/25880 [5:14:31<01:50,  1.25it/s]
1|25743|Loss: 0.8023639917373657:  99%|█████████▉| 25742/25880 [5:14:31<01:50,  1.25it/s]
1|25743|Loss: 0.8023639917373657:  99%|█████████▉| 25743/25880 [5:14:32<01:43,  1.32it/s]
1|25744|Loss: 0.7591663599014282:  99%|█████████▉| 25743/25880 [5:14:32<01:43,  1.32it/s]
1|25744|Loss: 0.7591663599014282:  99%|█████████▉| 25744/25880 [5:14:32<01:39,  1.36it/s]
1|25745|Loss: 0.749216616153717:  99%|█████████▉| 25744/25880 [5:14:33<01:39,  1.36it/s] 
1|25745|Loss: 0.749216616153717:  99%|█████████▉| 25745/25880 [5:14:33<01:27,  1.55it/s]
1|25746|Loss: 0.7079865336418152:  99%|█████████▉| 25745/25880 [5:14:33<01:27,  1.55it/s]
1|25746|Loss: 0.7079865336418152:  99%|█████████▉| 25746/25880 [5:14:33<01:27,  1.53it/s]
1|25747|Loss: 0.9117541909217834:  99%|█████████▉| 25746/25880 [5:14:34<01:27,  1.53it/s]
1|25747|Loss: 0.9117541909217834:  99%|█████████▉| 25747/25880 [5:14:34<01:30,  1.47it/s]
1|25748|Loss: 0.8934283256530762:  99%|█████████▉| 25747/25880 [5:14:35<01:30,  1.47it/s]
1|25748|Loss: 0.8934283256530762:  99%|█████████▉| 25748/25880 [5:14:35<01:31,  1.44it/s]
1|25749|Loss: 0.7565119862556458:  99%|█████████▉| 25748/25880 [5:14:35<01:31,  1.44it/s]
1|25749|Loss: 0.7565119862556458:  99%|█████████▉| 25749/25880 [5:14:36<01:32,  1.42it/s]
1|25750|Loss: 0.6556943655014038:  99%|█████████▉| 25749/25880 [5:14:36<01:32,  1.42it/s]
1|25750|Loss: 0.6556943655014038:  99%|█████████▉| 25750/25880 [5:14:36<01:37,  1.33it/s]
1|25751|Loss: 0.8302584886550903:  99%|█████████▉| 25750/25880 [5:14:37<01:37,  1.33it/s]
1|25751|Loss: 0.8302584886550903: 100%|█████████▉| 25751/25880 [5:14:37<01:34,  1.37it/s]
1|25752|Loss: 0.7628777027130127: 100%|█████████▉| 25751/25880 [5:14:38<01:34,  1.37it/s]
1|25752|Loss: 0.7628777027130127: 100%|█████████▉| 25752/25880 [5:14:38<01:32,  1.39it/s]
1|25753|Loss: 0.7563580274581909: 100%|█████████▉| 25752/25880 [5:14:38<01:32,  1.39it/s]
1|25753|Loss: 0.7563580274581909: 100%|█████████▉| 25753/25880 [5:14:38<01:23,  1.53it/s]
1|25754|Loss: 0.7769505381584167: 100%|█████████▉| 25753/25880 [5:14:39<01:23,  1.53it/s]
1|25754|Loss: 0.7769505381584167: 100%|█████████▉| 25754/25880 [5:14:39<01:20,  1.57it/s]
1|25755|Loss: 0.7789831757545471: 100%|█████████▉| 25754/25880 [5:14:39<01:20,  1.57it/s]
1|25755|Loss: 0.7789831757545471: 100%|█████████▉| 25755/25880 [5:14:40<01:19,  1.57it/s]
1|25756|Loss: 0.7825175523757935: 100%|█████████▉| 25755/25880 [5:14:40<01:19,  1.57it/s]
1|25756|Loss: 0.7825175523757935: 100%|█████████▉| 25756/25880 [5:14:40<01:18,  1.57it/s]
1|25757|Loss: 0.7923386096954346: 100%|█████████▉| 25756/25880 [5:14:41<01:18,  1.57it/s]
1|25757|Loss: 0.7923386096954346: 100%|█████████▉| 25757/25880 [5:14:41<01:17,  1.60it/s]
1|25758|Loss: 0.7794287204742432: 100%|█████████▉| 25757/25880 [5:14:41<01:17,  1.60it/s]
1|25758|Loss: 0.7794287204742432: 100%|█████████▉| 25758/25880 [5:14:41<01:18,  1.56it/s]
1|25759|Loss: 0.9026055335998535: 100%|█████████▉| 25758/25880 [5:14:42<01:18,  1.56it/s]
1|25759|Loss: 0.9026055335998535: 100%|█████████▉| 25759/25880 [5:14:42<01:10,  1.72it/s]
1|25760|Loss: 0.7952759861946106: 100%|█████████▉| 25759/25880 [5:14:42<01:10,  1.72it/s]
1|25760|Loss: 0.7952759861946106: 100%|█████████▉| 25760/25880 [5:14:42<01:09,  1.72it/s]
1|25761|Loss: 0.9604504704475403: 100%|█████████▉| 25760/25880 [5:14:43<01:09,  1.72it/s]
1|25761|Loss: 0.9604504704475403: 100%|█████████▉| 25761/25880 [5:14:43<01:17,  1.54it/s]
1|25762|Loss: 0.9051685333251953: 100%|█████████▉| 25761/25880 [5:14:44<01:17,  1.54it/s]
1|25762|Loss: 0.9051685333251953: 100%|█████████▉| 25762/25880 [5:14:44<01:22,  1.43it/s]
1|25763|Loss: 0.8745293021202087: 100%|█████████▉| 25762/25880 [5:14:45<01:22,  1.43it/s]
1|25763|Loss: 0.8745293021202087: 100%|█████████▉| 25763/25880 [5:14:45<01:24,  1.39it/s]
1|25764|Loss: 0.8173372745513916: 100%|█████████▉| 25763/25880 [5:14:45<01:24,  1.39it/s]
1|25764|Loss: 0.8173372745513916: 100%|█████████▉| 25764/25880 [5:14:46<01:27,  1.33it/s]
1|25765|Loss: 0.914484441280365: 100%|█████████▉| 25764/25880 [5:14:46<01:27,  1.33it/s] 
1|25765|Loss: 0.914484441280365: 100%|█████████▉| 25765/25880 [5:14:47<01:32,  1.25it/s]
1|25766|Loss: 0.6523492336273193: 100%|█████████▉| 25765/25880 [5:14:47<01:32,  1.25it/s]
1|25766|Loss: 0.6523492336273193: 100%|█████████▉| 25766/25880 [5:14:47<01:30,  1.26it/s]
1|25767|Loss: 0.8917545676231384: 100%|█████████▉| 25766/25880 [5:14:48<01:30,  1.26it/s]
1|25767|Loss: 0.8917545676231384: 100%|█████████▉| 25767/25880 [5:14:48<01:28,  1.28it/s]
1|25768|Loss: 0.9635873436927795: 100%|█████████▉| 25767/25880 [5:14:49<01:28,  1.28it/s]
1|25768|Loss: 0.9635873436927795: 100%|█████████▉| 25768/25880 [5:14:49<01:23,  1.34it/s]
1|25769|Loss: 0.7921053767204285: 100%|█████████▉| 25768/25880 [5:14:49<01:23,  1.34it/s]
1|25769|Loss: 0.7921053767204285: 100%|█████████▉| 25769/25880 [5:14:49<01:17,  1.44it/s]
1|25770|Loss: 0.7009795308113098: 100%|█████████▉| 25769/25880 [5:14:50<01:17,  1.44it/s]
1|25770|Loss: 0.7009795308113098: 100%|█████████▉| 25770/25880 [5:14:50<01:16,  1.43it/s]
1|25771|Loss: 0.7727879285812378: 100%|█████████▉| 25770/25880 [5:14:51<01:16,  1.43it/s]
1|25771|Loss: 0.7727879285812378: 100%|█████████▉| 25771/25880 [5:14:51<01:20,  1.36it/s]
1|25772|Loss: 0.9183642268180847: 100%|█████████▉| 25771/25880 [5:14:51<01:20,  1.36it/s]
1|25772|Loss: 0.9183642268180847: 100%|█████████▉| 25772/25880 [5:14:52<01:19,  1.36it/s]
1|25773|Loss: 0.8471547961235046: 100%|█████████▉| 25772/25880 [5:14:52<01:19,  1.36it/s]
1|25773|Loss: 0.8471547961235046: 100%|█████████▉| 25773/25880 [5:14:52<01:17,  1.38it/s]
1|25774|Loss: 0.7917348742485046: 100%|█████████▉| 25773/25880 [5:14:53<01:17,  1.38it/s]
1|25774|Loss: 0.7917348742485046: 100%|███████��█▉| 25774/25880 [5:14:53<01:15,  1.40it/s]
1|25775|Loss: 0.8016576766967773: 100%|█████████▉| 25774/25880 [5:14:54<01:15,  1.40it/s]
1|25775|Loss: 0.8016576766967773: 100%|█████████▉| 25775/25880 [5:14:54<01:21,  1.29it/s]
1|25776|Loss: 0.8202407360076904: 100%|█████████▉| 25775/25880 [5:14:54<01:21,  1.29it/s]
1|25776|Loss: 0.8202407360076904: 100%|█████████▉| 25776/25880 [5:14:55<01:19,  1.30it/s]
1|25777|Loss: 0.792853832244873: 100%|█████████▉| 25776/25880 [5:14:55<01:19,  1.30it/s] 
1|25777|Loss: 0.792853832244873: 100%|█████████▉| 25777/25880 [5:14:55<01:14,  1.38it/s]
1|25778|Loss: 0.8464592695236206: 100%|█████████▉| 25777/25880 [5:14:56<01:14,  1.38it/s]
1|25778|Loss: 0.8464592695236206: 100%|█████████▉| 25778/25880 [5:14:56<01:13,  1.39it/s]
1|25779|Loss: 0.7735221982002258: 100%|█████████▉| 25778/25880 [5:14:56<01:13,  1.39it/s]
1|25779|Loss: 0.7735221982002258: 100%|█████████▉| 25779/25880 [5:14:57<01:09,  1.45it/s]
1|25780|Loss: 0.8294466733932495: 100%|█████████▉| 25779/25880 [5:14:57<01:09,  1.45it/s]
1|25780|Loss: 0.8294466733932495: 100%|█████████▉| 25780/25880 [5:14:57<01:07,  1.49it/s]
1|25781|Loss: 0.7756637334823608: 100%|█████████▉| 25780/25880 [5:14:58<01:07,  1.49it/s]
1|25781|Loss: 0.7756637334823608: 100%|█████████▉| 25781/25880 [5:14:58<01:10,  1.40it/s]
1|25782|Loss: 0.9968503713607788: 100%|█████████▉| 25781/25880 [5:14:59<01:10,  1.40it/s]
1|25782|Loss: 0.9968503713607788: 100%|█████████▉| 25782/25880 [5:14:59<01:08,  1.43it/s]
1|25783|Loss: 0.8383822441101074: 100%|█████████▉| 25782/25880 [5:14:59<01:08,  1.43it/s]
1|25783|Loss: 0.8383822441101074: 100%|█████████▉| 25783/25880 [5:15:00<01:10,  1.38it/s]
1|25784|Loss: 0.8179805874824524: 100%|█████████▉| 25783/25880 [5:15:00<01:10,  1.38it/s]
1|25784|Loss: 0.8179805874824524: 100%|█████████▉| 25784/25880 [5:15:00<01:11,  1.34it/s]
1|25785|Loss: 0.7997369766235352: 100%|█████████▉| 25784/25880 [5:15:01<01:11,  1.34it/s]
1|25785|Loss: 0.7997369766235352: 100%|█████████▉| 25785/25880 [5:15:01<01:08,  1.38it/s]
1|25786|Loss: 0.9551565051078796: 100%|█████████▉| 25785/25880 [5:15:01<01:08,  1.38it/s]
1|25786|Loss: 0.9551565051078796: 100%|█████████▉| 25786/25880 [5:15:02<01:07,  1.40it/s]
1|25787|Loss: 0.9141187071800232: 100%|█████████▉| 25786/25880 [5:15:02<01:07,  1.40it/s]
1|25787|Loss: 0.9141187071800232: 100%|█████████▉| 25787/25880 [5:15:02<01:06,  1.41it/s]
1|25788|Loss: 0.7884812355041504: 100%|█████████▉| 25787/25880 [5:15:03<01:06,  1.41it/s]
1|25788|Loss: 0.7884812355041504: 100%|█████████▉| 25788/25880 [5:15:03<01:03,  1.45it/s]
1|25789|Loss: 0.8302767276763916: 100%|█████████▉| 25788/25880 [5:15:03<01:03,  1.45it/s]
1|25789|Loss: 0.8302767276763916: 100%|█████████▉| 25789/25880 [5:15:04<01:05,  1.39it/s]
1|25790|Loss: 0.8917229771614075: 100%|█████████▉| 25789/25880 [5:15:04<01:05,  1.39it/s]
1|25790|Loss: 0.8917229771614075: 100%|█████████▉| 25790/25880 [5:15:05<01:03,  1.41it/s]
1|25791|Loss: 0.752137303352356: 100%|█████████▉| 25790/25880 [5:15:05<01:03,  1.41it/s] 
1|25791|Loss: 0.752137303352356: 100%|█████████▉| 25791/25880 [5:15:05<00:59,  1.49it/s]
1|25792|Loss: 0.7352014780044556: 100%|█████████▉| 25791/25880 [5:15:05<00:59,  1.49it/s]
1|25792|Loss: 0.7352014780044556: 100%|█████████▉| 25792/25880 [5:15:06<00:54,  1.61it/s]
1|25793|Loss: 0.8498579859733582: 100%|█████████▉| 25792/25880 [5:15:06<00:54,  1.61it/s]
1|25793|Loss: 0.8498579859733582: 100%|█████████▉| 25793/25880 [5:15:06<00:51,  1.69it/s]
1|25794|Loss: 0.8795859217643738: 100%|█████████▉| 25793/25880 [5:15:07<00:51,  1.69it/s]
1|25794|Loss: 0.8795859217643738: 100%|█████████▉| 25794/25880 [5:15:07<00:53,  1.60it/s]
1|25795|Loss: 0.9447564482688904: 100%|█████████▉| 25794/25880 [5:15:07<00:53,  1.60it/s]
1|25795|Loss: 0.9447564482688904: 100%|█████████▉| 25795/25880 [5:15:08<00:57,  1.49it/s]
1|25796|Loss: 0.7125440835952759: 100%|█████████▉| 25795/25880 [5:15:08<00:57,  1.49it/s]
1|25796|Loss: 0.7125440835952759: 100%|█████████▉| 25796/25880 [5:15:08<00:58,  1.43it/s]
1|25797|Loss: 0.7718312740325928: 100%|█████████▉| 25796/25880 [5:15:09<00:58,  1.43it/s]
1|25797|Loss: 0.7718312740325928: 100%|█████████▉| 25797/25880 [5:15:09<01:02,  1.32it/s]
1|25798|Loss: 0.7118006944656372: 100%|█████████▉| 25797/25880 [5:15:10<01:02,  1.32it/s]
1|25798|Loss: 0.7118006944656372: 100%|█████████▉| 25798/25880 [5:15:10<00:59,  1.38it/s]
1|25799|Loss: 0.712573766708374: 100%|█████████▉| 25798/25880 [5:15:10<00:59,  1.38it/s] 
1|25799|Loss: 0.712573766708374: 100%|█████████▉| 25799/25880 [5:15:11<01:01,  1.32it/s]
1|25800|Loss: 0.8792983889579773: 100%|█████████▉| 25799/25880 [5:15:11<01:01,  1.32it/s]
1|25800|Loss: 0.8792983889579773: 100%|█████████▉| 25800/25880 [5:15:11<00:57,  1.38it/s]
1|25801|Loss: 0.9224436283111572: 100%|█████████▉| 25800/25880 [5:15:12<00:57,  1.38it/s]
1|25801|Loss: 0.9224436283111572: 100%|█████████▉| 25801/25880 [5:15:12<00:58,  1.34it/s]
1|25802|Loss: 0.7297772169113159: 100%|█████████▉| 25801/25880 [5:15:13<00:58,  1.34it/s]
1|25802|Loss: 0.7297772169113159: 100%|█████████▉| 25802/25880 [5:15:13<00:58,  1.33it/s]
1|25803|Loss: 0.8415873646736145: 100%|█████████▉| 25802/25880 [5:15:13<00:58,  1.33it/s]
1|25803|Loss: 0.8415873646736145: 100%|█████████▉| 25803/25880 [5:15:14<00:54,  1.40it/s]
1|25804|Loss: 0.846825897693634: 100%|█████████▉| 25803/25880 [5:15:14<00:54,  1.40it/s] 
1|25804|Loss: 0.846825897693634: 100%|█████████▉| 25804/25880 [5:15:14<00:53,  1.41it/s]
1|25805|Loss: 0.7583780884742737: 100%|█████████▉| 25804/25880 [5:15:15<00:53,  1.41it/s]
1|25805|Loss: 0.7583780884742737: 100%|█████████▉| 25805/25880 [5:15:15<00:54,  1.38it/s]
1|25806|Loss: 0.9009901285171509: 100%|█████████▉| 25805/25880 [5:15:15<00:54,  1.38it/s]
1|25806|Loss: 0.9009901285171509: 100%|█████████▉| 25806/25880 [5:15:16<00:51,  1.44it/s]
1|25807|Loss: 0.8299580812454224: 100%|█████████▉| 25806/25880 [5:15:16<00:51,  1.44it/s]
1|25807|Loss: 0.8299580812454224: 100%|█████████▉| 25807/25880 [5:15:16<00:45,  1.59it/s]
1|25808|Loss: 0.926297664642334: 100%|█████████▉| 25807/25880 [5:15:17<00:45,  1.59it/s] 
1|25808|Loss: 0.926297664642334: 100%|█████████▉| 25808/25880 [5:15:17<00:46,  1.55it/s]
1|25809|Loss: 0.8146361708641052: 100%|█████████▉| 25808/25880 [5:15:17<00:46,  1.55it/s]
1|25809|Loss: 0.8146361708641052: 100%|█████████▉| 25809/25880 [5:15:17<00:45,  1.55it/s]
1|25810|Loss: 0.865844190120697: 100%|█████████▉| 25809/25880 [5:15:18<00:45,  1.55it/s] 
1|25810|Loss: 0.865844190120697: 100%|█████████▉| 25810/25880 [5:15:18<00:46,  1.51it/s]
1|25811|Loss: 0.789201557636261: 100%|█████████▉| 25810/25880 [5:15:19<00:46,  1.51it/s]
1|25811|Loss: 0.789201557636261: 100%|█████████▉| 25811/25880 [5:15:19<00:41,  1.66it/s]
1|25812|Loss: 0.7694593667984009: 100%|█████████▉| 25811/25880 [5:15:19<00:41,  1.66it/s]
1|25812|Loss: 0.7694593667984009: 100%|█████████▉| 25812/25880 [5:15:19<00:43,  1.55it/s]
1|25813|Loss: 0.8695258498191833: 100%|█████████▉| 25812/25880 [5:15:20<00:43,  1.55it/s]
1|25813|Loss: 0.8695258498191833: 100%|█████████▉| 25813/25880 [5:15:20<00:45,  1.47it/s]
1|25814|Loss: 0.715586245059967: 100%|█████████▉| 25813/25880 [5:15:21<00:45,  1.47it/s] 
1|25814|Loss: 0.715586245059967: 100%|█████████▉| 25814/25880 [5:15:21<00:45,  1.44it/s]
1|25815|Loss: 0.8628138899803162: 100%|█████████▉| 25814/25880 [5:15:21<00:45,  1.44it/s]
1|25815|Loss: 0.8628138899803162: 100%|█████████▉| 25815/25880 [5:15:22<00:47,  1.36it/s]
1|25816|Loss: 0.8619488477706909: 100%|█████████▉| 25815/25880 [5:15:22<00:47,  1.36it/s]
1|25816|Loss: 0.8619488477706909: 100%|█████████▉| 25816/25880 [5:15:22<00:46,  1.39it/s]
1|25817|Loss: 1.0005985498428345: 100%|█████████▉| 25816/25880 [5:15:23<00:46,  1.39it/s]
1|25817|Loss: 1.0005985498428345: 100%|█████████▉| 25817/25880 [5:15:23<00:43,  1.45it/s]
1|25818|Loss: 0.7923578023910522: 100%|█████████▉| 25817/25880 [5:15:23<00:43,  1.45it/s]
1|25818|Loss: 0.7923578023910522: 100%|█████████▉| 25818/25880 [5:15:24<00:42,  1.45it/s]
1|25819|Loss: 0.7319286465644836: 100%|█████████▉| 25818/25880 [5:15:24<00:42,  1.45it/s]
1|25819|Loss: 0.7319286465644836: 100%|█████████▉| 25819/25880 [5:15:25<00:46,  1.30it/s]
1|25820|Loss: 0.7831715941429138: 100%|█████████▉| 25819/25880 [5:15:25<00:46,  1.30it/s]
1|25820|Loss: 0.7831715941429138: 100%|█████████▉| 25820/25880 [5:15:25<00:46,  1.29it/s]
1|25821|Loss: 0.7009378671646118: 100%|█████████▉| 25820/25880 [5:15:26<00:46,  1.29it/s]
1|25821|Loss: 0.7009378671646118: 100%|█████████▉| 25821/25880 [5:15:26<00:46,  1.27it/s]
1|25822|Loss: 0.8276311755180359: 100%|█████████▉| 25821/25880 [5:15:27<00:46,  1.27it/s]
1|25822|Loss: 0.8276311755180359: 100%|█████████▉| 25822/25880 [5:15:27<00:44,  1.29it/s]
1|25823|Loss: 0.7493084073066711: 100%|█████████▉| 25822/25880 [5:15:27<00:44,  1.29it/s]
1|25823|Loss: 0.7493084073066711: 100%|█████████▉| 25823/25880 [5:15:28<00:43,  1.31it/s]
1|25824|Loss: 0.9340927600860596: 100%|█████████▉| 25823/25880 [5:15:28<00:43,  1.31it/s]
1|25824|Loss: 0.9340927600860596: 100%|█████████▉| 25824/25880 [5:15:28<00:42,  1.33it/s]
1|25825|Loss: 0.9059203267097473: 100%|█████████▉| 25824/25880 [5:15:29<00:42,  1.33it/s]
1|25825|Loss: 0.9059203267097473: 100%|█████████▉| 25825/25880 [5:15:29<00:39,  1.38it/s]
1|25826|Loss: 0.8726604580879211: 100%|█████████▉| 25825/25880 [5:15:29<00:39,  1.38it/s]
1|25826|Loss: 0.8726604580879211: 100%|█████████▉| 25826/25880 [5:15:30<00:37,  1.44it/s]
1|25827|Loss: 0.950832724571228: 100%|█████████▉| 25826/25880 [5:15:30<00:37,  1.44it/s] 
1|25827|Loss: 0.950832724571228: 100%|█████████▉| 25827/25880 [5:15:30<00:37,  1.43it/s]
1|25828|Loss: 0.9116134643554688: 100%|█████████▉| 25827/25880 [5:15:31<00:37,  1.43it/s]
1|25828|Loss: 0.9116134643554688: 100%|█████████▉| 25828/25880 [5:15:31<00:35,  1.45it/s]
1|25829|Loss: 0.8670234680175781: 100%|█████████▉| 25828/25880 [5:15:32<00:35,  1.45it/s]
1|25829|Loss: 0.8670234680175781: 100%|█████████▉| 25829/25880 [5:15:32<00:35,  1.43it/s]
1|25830|Loss: 0.8551325798034668: 100%|█████████▉| 25829/25880 [5:15:32<00:35,  1.43it/s]
1|25830|Loss: 0.8551325798034668: 100%|█████████▉| 25830/25880 [5:15:33<00:37,  1.35it/s]
1|25831|Loss: 1.3051185607910156: 100%|█████████▉| 25830/25880 [5:15:33<00:37,  1.35it/s]
1|25831|Loss: 1.3051185607910156: 100%|█████████▉| 25831/25880 [5:15:34<00:38,  1.29it/s]
1|25832|Loss: 0.8059491515159607: 100%|█████████▉| 25831/25880 [5:15:34<00:38,  1.29it/s]
1|25832|Loss: 0.8059491515159607: 100%|█████████▉| 25832/25880 [5:15:34<00:39,  1.23it/s]
1|25833|Loss: 0.8350780010223389: 100%|█████████▉| 25832/25880 [5:15:35<00:39,  1.23it/s]
1|25833|Loss: 0.8350780010223389: 100%|█████████▉| 25833/25880 [5:15:35<00:36,  1.29it/s]
1|25834|Loss: 0.8166097402572632: 100%|█████████▉| 25833/25880 [5:15:36<00:36,  1.29it/s]
1|25834|Loss: 0.8166097402572632: 100%|█████████▉| 25834/25880 [5:15:36<00:34,  1.33it/s]
1|25835|Loss: 0.9117178320884705: 100%|█████████▉| 25834/25880 [5:15:36<00:34,  1.33it/s]
1|25835|Loss: 0.9117178320884705: 100%|█████████▉| 25835/25880 [5:15:37<00:32,  1.39it/s]
1|25836|Loss: 0.7630770206451416: 100%|█████████▉| 25835/25880 [5:15:37<00:32,  1.39it/s]
1|25836|Loss: 0.7630770206451416: 100%|█████████▉| 25836/25880 [5:15:37<00:30,  1.43it/s]
1|25837|Loss: 0.8863041400909424: 100%|█████████▉| 25836/25880 [5:15:38<00:30,  1.43it/s]
1|25837|Loss: 0.8863041400909424: 100%|█████████▉| 25837/25880 [5:15:38<00:30,  1.42it/s]
1|25838|Loss: 0.9466103315353394: 100%|█████████▉| 25837/25880 [5:15:38<00:30,  1.42it/s]
1|25838|Loss: 0.9466103315353394: 100%|█████████▉| 25838/25880 [5:15:39<00:28,  1.45it/s]
1|25839|Loss: 0.7799805402755737: 100%|█████████▉| 25838/25880 [5:15:39<00:28,  1.45it/s]
1|25839|Loss: 0.7799805402755737: 100%|█████████▉| 25839/25880 [5:15:39<00:28,  1.45it/s]
1|25840|Loss: 0.7444869875907898: 100%|█████████▉| 25839/25880 [5:15:40<00:28,  1.45it/s]
1|25840|Loss: 0.7444869875907898: 100%|█████████▉| 25840/25880 [5:15:40<00:28,  1.42it/s]
1|25841|Loss: 0.7566753625869751: 100%|█████████▉| 25840/25880 [5:15:40<00:28,  1.42it/s]
1|25841|Loss: 0.7566753625869751: 100%|█████████▉| 25841/25880 [5:15:41<00:28,  1.37it/s]
1|25842|Loss: 0.9039849638938904: 100%|█████████▉| 25841/25880 [5:15:41<00:28,  1.37it/s]
1|25842|Loss: 0.9039849638938904: 100%|█████████▉| 25842/25880 [5:15:41<00:24,  1.55it/s]
1|25843|Loss: 0.7448551654815674: 100%|█████████▉| 25842/25880 [5:15:41<00:24,  1.55it/s]
1|25843|Loss: 0.7448551654815674: 100%|█████████▉| 25843/25880 [5:15:42<00:23,  1.59it/s]
1|25844|Loss: 0.6407977342605591: 100%|█████████▉| 25843/25880 [5:15:42<00:23,  1.59it/s]
1|25844|Loss: 0.6407977342605591: 100%|█████████▉| 25844/25880 [5:15:43<00:25,  1.43it/s]
1|25845|Loss: 0.6786493062973022: 100%|█████████▉| 25844/25880 [5:15:43<00:25,  1.43it/s]
1|25845|Loss: 0.6786493062973022: 100%|█████████▉| 25845/25880 [5:15:43<00:24,  1.45it/s]
1|25846|Loss: 0.7226603627204895: 100%|█████████▉| 25845/25880 [5:15:44<00:24,  1.45it/s]
1|25846|Loss: 0.7226603627204895: 100%|█████████▉| 25846/25880 [5:15:44<00:22,  1.49it/s]
1|25847|Loss: 0.7533113360404968: 100%|█████████▉| 25846/25880 [5:15:44<00:22,  1.49it/s]
1|25847|Loss: 0.7533113360404968: 100%|█████████▉| 25847/25880 [5:15:45<00:22,  1.47it/s]
1|25848|Loss: 0.8301931619644165: 100%|█████████▉| 25847/25880 [5:15:45<00:22,  1.47it/s]
1|25848|Loss: 0.8301931619644165: 100%|█████████▉| 25848/25880 [5:15:45<00:21,  1.46it/s]
1|25849|Loss: 0.8667705059051514: 100%|█████████▉| 25848/25880 [5:15:46<00:21,  1.46it/s]
1|25849|Loss: 0.8667705059051514: 100%|█████████▉| 25849/25880 [5:15:46<00:22,  1.39it/s]
1|25850|Loss: 0.6586621403694153: 100%|█████████▉| 25849/25880 [5:15:47<00:22,  1.39it/s]
1|25850|Loss: 0.6586621403694153: 100%|█████████▉| 25850/25880 [5:15:47<00:21,  1.37it/s]
1|25851|Loss: 0.7534868717193604: 100%|█████████▉| 25850/25880 [5:15:47<00:21,  1.37it/s]
1|25851|Loss: 0.7534868717193604: 100%|█████████▉| 25851/25880 [5:15:48<00:21,  1.37it/s]
1|25852|Loss: 0.8357459306716919: 100%|█████████▉| 25851/25880 [5:15:48<00:21,  1.37it/s]
1|25852|Loss: 0.8357459306716919: 100%|█████████▉| 25852/25880 [5:15:48<00:19,  1.42it/s]
1|25853|Loss: 0.8776223063468933: 100%|█████████▉| 25852/25880 [5:15:49<00:19,  1.42it/s]
1|25853|Loss: 0.8776223063468933: 100%|█████████▉| 25853/25880 [5:15:49<00:19,  1.35it/s]
1|25854|Loss: 0.8109071254730225: 100%|█████████▉| 25853/25880 [5:15:50<00:19,  1.35it/s]
1|25854|Loss: 0.8109071254730225: 100%|█████████▉| 25854/25880 [5:15:50<00:19,  1.33it/s]
1|25855|Loss: 1.040002703666687: 100%|█████████▉| 25854/25880 [5:15:50<00:19,  1.33it/s] 
1|25855|Loss: 1.040002703666687: 100%|█████████▉| 25855/25880 [5:15:51<00:18,  1.35it/s]
1|25856|Loss: 0.9357210397720337: 100%|█████████▉| 25855/25880 [5:15:51<00:18,  1.35it/s]
1|25856|Loss: 0.9357210397720337: 100%|█████████▉| 25856/25880 [5:15:51<00:18,  1.32it/s]
1|25857|Loss: 0.8517163395881653: 100%|█████████▉| 25856/25880 [5:15:52<00:18,  1.32it/s]
1|25857|Loss: 0.8517163395881653: 100%|█████████▉| 25857/25880 [5:15:52<00:17,  1.32it/s]
1|25858|Loss: 0.9717182517051697: 100%|█████████▉| 25857/25880 [5:15:53<00:17,  1.32it/s]
1|25858|Loss: 0.9717182517051697: 100%|█████████▉| 25858/25880 [5:15:53<00:17,  1.24it/s]
1|25859|Loss: 0.7628149390220642: 100%|█████████▉| 25858/25880 [5:15:53<00:17,  1.24it/s]
1|25859|Loss: 0.7628149390220642: 100%|█████████▉| 25859/25880 [5:15:54<00:14,  1.40it/s]
1|25860|Loss: 0.8960565328598022: 100%|█████████▉| 25859/25880 [5:15:54<00:14,  1.40it/s]
1|25860|Loss: 0.8960565328598022: 100%|█████████▉| 25860/25880 [5:15:54<00:13,  1.48it/s]
1|25861|Loss: 0.8244989514350891: 100%|█████████▉| 25860/25880 [5:15:55<00:13,  1.48it/s]
1|25861|Loss: 0.8244989514350891: 100%|█████████▉| 25861/25880 [5:15:55<00:12,  1.47it/s]
1|25862|Loss: 0.8438642024993896: 100%|█████████▉| 25861/25880 [5:15:55<00:12,  1.47it/s]
1|25862|Loss: 0.8438642024993896: 100%|█████████▉| 25862/25880 [5:15:55<00:11,  1.54it/s]
1|25863|Loss: 0.8109126091003418: 100%|█████████▉| 25862/25880 [5:15:56<00:11,  1.54it/s]
1|25863|Loss: 0.8109126091003418: 100%|█████████▉| 25863/25880 [5:15:56<00:10,  1.57it/s]
1|25864|Loss: 0.8837546110153198: 100%|█████████▉| 25863/25880 [5:15:56<00:10,  1.57it/s]
1|25864|Loss: 0.8837546110153198: 100%|█████████▉| 25864/25880 [5:15:57<00:10,  1.49it/s]
1|25865|Loss: 0.8228654861450195: 100%|█████████▉| 25864/25880 [5:15:57<00:10,  1.49it/s]
1|25865|Loss: 0.8228654861450195: 100%|█████████▉| 25865/25880 [5:15:57<00:10,  1.46it/s]
1|25866|Loss: 0.8723759651184082: 100%|█████████▉| 25865/25880 [5:15:58<00:10,  1.46it/s]
1|25866|Loss: 0.8723759651184082: 100%|█████████▉| 25866/25880 [5:15:58<00:10,  1.37it/s]
1|25867|Loss: 0.886535108089447: 100%|█████████▉| 25866/25880 [5:15:59<00:10,  1.37it/s] 
1|25867|Loss: 0.886535108089447: 100%|█████████▉| 25867/25880 [5:15:59<00:09,  1.31it/s]
1|25868|Loss: 0.8860310316085815: 100%|█████████▉| 25867/25880 [5:16:00<00:09,  1.31it/s]
1|25868|Loss: 0.8860310316085815: 100%|█████████▉| 25868/25880 [5:16:00<00:08,  1.36it/s]
1|25869|Loss: 0.9088529944419861: 100%|█████████▉| 25868/25880 [5:16:00<00:08,  1.36it/s]
1|25869|Loss: 0.9088529944419861: 100%|█████████▉| 25869/25880 [5:16:01<00:08,  1.34it/s]
1|25870|Loss: 0.7498743534088135: 100%|█████████▉| 25869/25880 [5:16:01<00:08,  1.34it/s]
1|25870|Loss: 0.7498743534088135: 100%|█████████▉| 25870/25880 [5:16:01<00:07,  1.30it/s]
1|25871|Loss: 0.9307419657707214: 100%|█████████▉| 25870/25880 [5:16:02<00:07,  1.30it/s]
1|25871|Loss: 0.9307419657707214: 100%|█████████▉| 25871/25880 [5:16:02<00:06,  1.35it/s]
1|25872|Loss: 0.9336363077163696: 100%|█████████▉| 25871/25880 [5:16:03<00:06,  1.35it/s]
1|25872|Loss: 0.9336363077163696: 100%|█████████▉| 25872/25880 [5:16:03<00:06,  1.32it/s]
1|25873|Loss: 0.8423687219619751: 100%|█████████▉| 25872/25880 [5:16:03<00:06,  1.32it/s]
1|25873|Loss: 0.8423687219619751: 100%|█████████▉| 25873/25880 [5:16:04<00:05,  1.28it/s]
1|25874|Loss: 0.8290508985519409: 100%|█████████▉| 25873/25880 [5:16:04<00:05,  1.28it/s]
1|25874|Loss: 0.8290508985519409: 100%|█████████▉| 25874/25880 [5:16:05<00:04,  1.25it/s]
1|25875|Loss: 0.7661713361740112: 100%|█████████▉| 25874/25880 [5:16:05<00:04,  1.25it/s]
1|25875|Loss: 0.7661713361740112: 100%|█████████▉| 25875/25880 [5:16:05<00:03,  1.28it/s]
1|25876|Loss: 1.0250906944274902: 100%|█████████▉| 25875/25880 [5:16:06<00:03,  1.28it/s]
1|25876|Loss: 1.0250906944274902: 100%|█████████▉| 25876/25880 [5:16:06<00:02,  1.35it/s]
1|25877|Loss: 0.8027727603912354: 100%|█████████▉| 25876/25880 [5:16:06<00:02,  1.35it/s]
1|25877|Loss: 0.8027727603912354: 100%|█████████▉| 25877/25880 [5:16:07<00:02,  1.44it/s]
1|25878|Loss: 0.8988720178604126: 100%|█████████▉| 25877/25880 [5:16:07<00:02,  1.44it/s]
1|25878|Loss: 0.8988720178604126: 100%|█████████▉| 25878/25880 [5:16:07<00:01,  1.45it/s]
1|25879|Loss: 0.9082497358322144: 100%|█████████▉| 25878/25880 [5:16:08<00:01,  1.45it/s]
1|25879|Loss: 0.9082497358322144: 100%|█████████▉| 25879/25880 [5:16:08<00:00,  1.40it/s]
1|25880|Loss: 0.8834850192070007: 100%|█████████▉| 25879/25880 [5:16:08<00:00,  1.40it/s]
1|25880|Loss: 0.8834850192070007: 100%|██████████| 25880/25880 [5:16:09<00:00,  1.30it/s]
1|25880|Loss: 0.8834850192070007: 100%|██████████| 25880/25880 [5:16:09<00:00,  1.36it/s]
+Model checkpoint of size 25961 MB saved to output/alpaca-colorful-llama2-finetune/model_0_25880.ckpt
+Skipping uploading to HuggingFace Hub (no repo id specified)
+wandb: - 0.010 MB of 0.016 MB uploaded
wandb: \ 0.016 MB of 0.027 MB uploaded
wandb: | 0.016 MB of 0.027 MB uploaded
wandb: / 0.027 MB of 0.027 MB uploaded
wandb:                                                                                
+wandb: 
+wandb: Run history:
+wandb: gpu_resources ▄▄▃▃▆▂▅▅█▁▅▅▆▄▅▂▅▆▃▂▄▇▇▅▅▂▆▄▇▃▂▇▆▆▄▆▄▄▇▆
+wandb:          loss █▂▂▂▁▂▁▂▂▂▂▂▂▂▂▂▂▂▁▁▁▂▃▁▂▂▂▂▂▂▁▂▂▂▂▃▂▁▁▂
+wandb:            lr ▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+wandb: 
+wandb: Run summary:
+wandb: gpu_resources 45408555520
+wandb:          loss 0.88349
+wandb:            lr 2e-05
+wandb: 
+wandb: 🚀 View run lambent-monkey-9 at: https://wandb.ai/laurence_r/colorful-llama/runs/bm22a3e4
+wandb: ️⚡ View job at https://wandb.ai/laurence_r/colorful-llama/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjE0MDkwNjI2OA==/version_details/v0
+wandb: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)
+wandb: Find logs at: ./wandb/run-20240218_171717-bm22a3e4/logs