The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.

0it [00:00, ?it/s]
0it [00:00, ?it/s]
/opt/conda/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/opt/conda/lib/python3.10/site-packages/torchvision/image.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
2024-10-25 01:18:03.423955: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-10-25 01:18:03.424084: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-10-25 01:18:03.562275: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:24: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
  warnings.warn(
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 1 examples [00:00,  9.64 examples/s]
Generating train split: 1629 examples [00:00, 9433.13 examples/s]
Generating train split: 3247 examples [00:00, 12482.57 examples/s]
Generating train split: 5000 examples [00:00, 14388.71 examples/s]
Generating train split: 6882 examples [00:00, 15971.88 examples/s]
Generating train split: 8690 examples [00:00, 16683.55 examples/s]
Generating train split: 10562 examples [00:00, 17344.81 examples/s]
Generating train split: 12423 examples [00:00, 17744.79 examples/s]
Generating train split: 14292 examples [00:00, 18036.96 examples/s]
Generating train split: 16160 examples [00:01, 18234.20 examples/s]
Generating train split: 18000 examples [00:01, 18062.25 examples/s]
Generating train split: 20513 examples [00:01, 17541.22 examples/s]
Generating train split: 22355 examples [00:01, 17775.77 examples/s]
Generating train split: 24183 examples [00:01, 17914.16 examples/s]
Generating train split: 26032 examples [00:01, 18077.37 examples/s]
Generating train split: 28000 examples [00:01, 18229.14 examples/s]
Generating train split: 29906 examples [00:01, 18467.16 examples/s]
Generating train split: 32664 examples [00:01, 18433.43 examples/s]
Generating train split: 35285 examples [00:02, 18091.59 examples/s]
Generating train split: 38013 examples [00:02, 18120.13 examples/s]
Generating train split: 39890 examples [00:02, 18275.79 examples/s]
Generating train split: 42593 examples [00:02, 18185.28 examples/s]
Generating train split: 44444 examples [00:02, 18262.23 examples/s]
Generating train split: 46284 examples [00:02, 18293.94 examples/s]
Generating train split: 48127 examples [00:02, 18326.88 examples/s]
Generating train split: 50000 examples [00:02, 18332.91 examples/s]
Generating train split: 51893 examples [00:02, 18500.54 examples/s]
Generating train split: 54625 examples [00:03, 18388.69 examples/s]
Generating train split: 57265 examples [00:03, 18108.54 examples/s]
Generating train split: 60000 examples [00:03, 18095.93 examples/s]
Generating train split: 62000 examples [00:03, 18222.44 examples/s]
Generating train split: 63941 examples [00:03, 18520.69 examples/s]
Generating train split: 65812 examples [00:03, 18568.69 examples/s]
Generating train split: 68595 examples [00:03, 18561.16 examples/s]
Generating train split: 71360 examples [00:04, 18511.88 examples/s]
Generating train split: 74075 examples [00:04, 18374.99 examples/s]
Generating train split: 75995 examples [00:04, 18568.35 examples/s]
Generating train split: 78707 examples [00:04, 18399.49 examples/s]
Generating train split: 81461 examples [00:04, 18384.03 examples/s]
Generating train split: 84174 examples [00:04, 18285.59 examples/s]
Generating train split: 86021 examples [00:04, 18326.39 examples/s]
Generating train split: 88000 examples [00:04, 18361.99 examples/s]
Generating train split: 89911 examples [00:05, 18552.70 examples/s]
Generating train split: 92600 examples [00:05, 18327.45 examples/s]
Generating train split: 92867 examples [00:05, 17814.29 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 1722 examples [00:00, 17667.23 examples/s]

Running tokenizer on train dataset:   0%|          | 0/92867 [00:00<?, ? examples/s]/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:4126: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
  warnings.warn(

Running tokenizer on train dataset:   1%|          | 1000/92867 [00:01<02:26, 625.39 examples/s]
Running tokenizer on train dataset:   2%|▏         | 2000/92867 [00:02<01:49, 832.46 examples/s]
Running tokenizer on train dataset:   3%|▎         | 3000/92867 [00:04<02:01, 739.13 examples/s]
Running tokenizer on train dataset:   4%|▍         | 4000/92867 [00:05<02:19, 636.15 examples/s]
Running tokenizer on train dataset:   5%|▌         | 5000/92867 [00:07<02:22, 614.54 examples/s]
Running tokenizer on train dataset:   6%|▋         | 6000/92867 [00:09<02:25, 597.43 examples/s]
Running tokenizer on train dataset:   8%|▊         | 7000/92867 [00:11<02:26, 585.93 examples/s]
Running tokenizer on train dataset:   9%|▊         | 8000/92867 [00:12<02:26, 579.26 examples/s]
Running tokenizer on train dataset:  10%|▉         | 9000/92867 [00:14<02:21, 591.36 examples/s]
Running tokenizer on train dataset:  11%|█         | 10000/92867 [00:15<02:06, 655.55 examples/s]
Running tokenizer on train dataset:  12%|█▏        | 11000/92867 [00:16<01:55, 708.72 examples/s]
Running tokenizer on train dataset:  13%|█▎        | 12000/92867 [00:18<01:51, 728.51 examples/s]
Running tokenizer on train dataset:  14%|█▍        | 13000/92867 [00:19<01:47, 745.31 examples/s]
Running tokenizer on train dataset:  15%|█▌        | 14000/92867 [00:20<01:39, 793.11 examples/s]
Running tokenizer on train dataset:  16%|█▌        | 15000/92867 [00:21<01:34, 820.50 examples/s]
Running tokenizer on train dataset:  17%|█▋        | 16000/92867 [00:22<01:30, 850.87 examples/s]
Running tokenizer on train dataset:  18%|█▊        | 17000/92867 [00:23<01:27, 862.91 examples/s]
Running tokenizer on train dataset:  19%|█▉        | 18000/92867 [00:25<01:26, 862.24 examples/s]
Running tokenizer on train dataset:  20%|██        | 19000/92867 [00:26<01:29, 822.66 examples/s]
Running tokenizer on train dataset:  22%|██▏       | 20000/92867 [00:27<01:27, 836.65 examples/s]
Running tokenizer on train dataset:  23%|██▎       | 21000/92867 [00:28<01:23, 856.65 examples/s]
Running tokenizer on train dataset:  24%|██▎       | 22000/92867 [00:29<01:22, 859.16 examples/s]
Running tokenizer on train dataset:  25%|██▍       | 23000/92867 [00:31<01:24, 831.09 examples/s]
Running tokenizer on train dataset:  26%|██▌       | 24000/92867 [00:32<01:25, 808.15 examples/s]
Running tokenizer on train dataset:  27%|██▋       | 25000/92867 [00:33<01:23, 812.17 examples/s]
Running tokenizer on train dataset:  28%|██▊       | 26000/92867 [00:34<01:23, 801.36 examples/s]
Running tokenizer on train dataset:  29%|██▉       | 27000/92867 [00:36<01:22, 798.57 examples/s]
Running tokenizer on train dataset:  30%|███       | 28000/92867 [00:37<01:24, 764.19 examples/s]
Running tokenizer on train dataset:  31%|███       | 29000/92867 [00:39<01:25, 745.10 examples/s]
Running tokenizer on train dataset:  32%|███▏      | 30000/92867 [00:40<01:25, 734.45 examples/s]
Running tokenizer on train dataset:  33%|███▎      | 31000/92867 [00:41<01:26, 717.49 examples/s]
Running tokenizer on train dataset:  34%|███▍      | 32000/92867 [00:43<01:28, 685.96 examples/s]
Running tokenizer on train dataset:  36%|███▌      | 33000/92867 [00:45<01:28, 676.37 examples/s]
Running tokenizer on train dataset:  37%|███▋      | 34000/92867 [00:46<01:28, 666.43 examples/s]
Running tokenizer on train dataset:  38%|███▊      | 35000/92867 [00:48<01:27, 663.37 examples/s]
Running tokenizer on train dataset:  39%|███▉      | 36000/92867 [00:49<01:26, 654.84 examples/s]
Running tokenizer on train dataset:  40%|███▉      | 37000/92867 [00:51<01:23, 667.87 examples/s]
Running tokenizer on train dataset:  41%|████      | 38000/92867 [00:52<01:20, 681.47 examples/s]
Running tokenizer on train dataset:  42%|████▏     | 39000/92867 [00:53<01:19, 681.37 examples/s]
Running tokenizer on train dataset:  43%|████▎     | 40000/92867 [00:55<01:20, 653.39 examples/s]
Running tokenizer on train dataset:  44%|████▍     | 41000/92867 [00:57<01:31, 564.78 examples/s]
Running tokenizer on train dataset:  45%|████▌     | 42000/92867 [00:59<01:28, 573.40 examples/s]
Running tokenizer on train dataset:  46%|████▋     | 43000/92867 [01:01<01:23, 595.67 examples/s]
Running tokenizer on train dataset:  47%|████▋     | 44000/92867 [01:02<01:19, 611.78 examples/s]
Running tokenizer on train dataset:  48%|████▊     | 45000/92867 [01:04<01:18, 613.12 examples/s]
Running tokenizer on train dataset:  50%|████▉     | 46000/92867 [01:06<01:17, 608.62 examples/s]
Running tokenizer on train dataset:  51%|█████     | 47000/92867 [01:07<01:13, 626.29 examples/s]
Running tokenizer on train dataset:  52%|█████▏    | 48000/92867 [01:09<01:13, 606.70 examples/s]
Running tokenizer on train dataset:  53%|█████▎    | 49000/92867 [01:10<01:09, 632.06 examples/s]
Running tokenizer on train dataset:  54%|█████▍    | 50000/92867 [01:12<01:11, 595.62 examples/s]
Running tokenizer on train dataset:  55%|█████▍    | 51000/92867 [01:14<01:14, 560.88 examples/s]
Running tokenizer on train dataset:  56%|█████▌    | 52000/92867 [01:16<01:12, 560.31 examples/s]
Running tokenizer on train dataset:  57%|█████▋    | 53000/92867 [01:18<01:12, 546.70 examples/s]
Running tokenizer on train dataset:  58%|█████▊    | 54000/92867 [01:20<01:09, 562.23 examples/s]
Running tokenizer on train dataset:  59%|█████▉    | 55000/92867 [01:21<01:05, 575.86 examples/s]
Running tokenizer on train dataset:  60%|██████    | 56000/92867 [01:23<01:07, 544.46 examples/s]
Running tokenizer on train dataset:  61%|██████▏   | 57000/92867 [01:25<01:08, 526.17 examples/s]
Running tokenizer on train dataset:  62%|██████▏   | 58000/92867 [01:27<01:07, 519.48 examples/s]
Running tokenizer on train dataset:  64%|██████▎   | 59000/92867 [01:29<01:05, 517.67 examples/s]
Running tokenizer on train dataset:  65%|██████▍   | 60000/92867 [01:30<00:56, 579.37 examples/s]
Running tokenizer on train dataset:  66%|██████▌   | 61000/92867 [01:32<00:51, 620.23 examples/s]
Running tokenizer on train dataset:  67%|██████▋   | 62000/92867 [01:33<00:48, 634.68 examples/s]
Running tokenizer on train dataset:  68%|██████▊   | 63000/92867 [01:35<00:44, 667.18 examples/s]
Running tokenizer on train dataset:  69%|██████▉   | 64000/92867 [01:36<00:40, 709.31 examples/s]
Running tokenizer on train dataset:  70%|██████▉   | 65000/92867 [01:37<00:38, 727.04 examples/s]
Running tokenizer on train dataset:  71%|███████   | 66000/92867 [01:38<00:36, 737.65 examples/s]
Running tokenizer on train dataset:  72%|███████▏  | 67000/92867 [01:40<00:35, 726.30 examples/s]
Running tokenizer on train dataset:  73%|███████▎  | 68000/92867 [01:41<00:33, 738.09 examples/s]
Running tokenizer on train dataset:  74%|███████▍  | 69000/92867 [01:42<00:31, 745.99 examples/s]
Running tokenizer on train dataset:  75%|███████▌  | 70000/92867 [01:44<00:31, 722.74 examples/s]
Running tokenizer on train dataset:  76%|███████▋  | 71000/92867 [01:45<00:30, 708.73 examples/s]
Running tokenizer on train dataset:  78%|███████▊  | 72000/92867 [01:47<00:29, 699.99 examples/s]
Running tokenizer on train dataset:  79%|███████▊  | 73000/92867 [01:48<00:29, 678.72 examples/s]
Running tokenizer on train dataset:  80%|███████▉  | 74000/92867 [01:50<00:28, 656.86 examples/s]
Running tokenizer on train dataset:  81%|████████  | 75000/92867 [01:52<00:27, 650.16 examples/s]
Running tokenizer on train dataset:  82%|████████▏ | 76000/92867 [01:53<00:27, 622.32 examples/s]
Running tokenizer on train dataset:  83%|████████▎ | 77000/92867 [01:55<00:25, 611.97 examples/s]
Running tokenizer on train dataset:  84%|████████▍ | 78000/92867 [01:57<00:24, 600.41 examples/s]
Running tokenizer on train dataset:  85%|████████▌ | 79000/92867 [01:59<00:23, 597.19 examples/s]
Running tokenizer on train dataset:  86%|████████▌ | 80000/92867 [02:00<00:21, 597.76 examples/s]
Running tokenizer on train dataset:  87%|████████▋ | 81000/92867 [02:02<00:19, 607.27 examples/s]
Running tokenizer on train dataset:  88%|████████▊ | 82000/92867 [02:03<00:17, 621.51 examples/s]
Running tokenizer on train dataset:  89%|████████▉ | 83000/92867 [02:06<00:18, 528.75 examples/s]
Running tokenizer on train dataset:  90%|█████████ | 84000/92867 [02:08<00:16, 524.62 examples/s]
Running tokenizer on train dataset:  92%|█████████▏| 85000/92867 [02:09<00:14, 547.10 examples/s]
Running tokenizer on train dataset:  93%|█████████▎| 86000/92867 [02:11<00:12, 567.64 examples/s]
Running tokenizer on train dataset:  94%|█████████▎| 87000/92867 [02:13<00:10, 559.10 examples/s]
Running tokenizer on train dataset:  95%|█████████▍| 88000/92867 [02:15<00:08, 566.64 examples/s]
Running tokenizer on train dataset:  96%|█████████▌| 89000/92867 [02:16<00:06, 559.72 examples/s]
Running tokenizer on train dataset:  97%|█████████▋| 90000/92867 [02:18<00:05, 567.62 examples/s]
Running tokenizer on train dataset:  98%|█████████▊| 91000/92867 [02:20<00:03, 525.32 examples/s]
Running tokenizer on train dataset:  99%|█████████▉| 92000/92867 [02:22<00:01, 521.70 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:24<00:00, 514.17 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:24<00:00, 642.11 examples/s]
Saving cached train data ...

Saving the dataset (0/1 shards):   0%|          | 0/92867 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 942235.04 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 940156.38 examples/s]

Running tokenizer on validation dataset:   0%|          | 0/1722 [00:00<?, ? examples/s]
Running tokenizer on validation dataset:  58%|█████▊    | 1000/1722 [00:01<00:01, 567.28 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 553.93 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 555.50 examples/s]
Saving cached validation data ...

Saving the dataset (0/1 shards):   0%|          | 0/1722 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 1722/1722 [00:00<00:00, 324421.30 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 1722/1722 [00:00<00:00, 313998.41 examples/s]
training_args.use_lang_prefix=True

Downloading builder script:   0%|          | 0.00/8.15k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 8.15k/8.15k [00:00<00:00, 21.4MB/s]
/opt/conda/lib/python3.10/site-packages/transformers/optimization.py:591: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
  warnings.warn(
All 61904 steps, warm_up steps: 200
wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
wandb: Currently logged in as: abdiharyadi. Use `wandb login --relogin` to force relogin
wandb: wandb version 0.18.5 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /kaggle/tmp/amr-tst-indo/AMRBART-id/fine-tune/wandb/run-20241025_012052-278wbs6z
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run /kaggle/tmp/amr-tst-indo/AMRBART-id/fine-tune/../outputs/mbart-en-id-smaller-fted
wandb: ⭐️ View project at https://wandb.ai/abdiharyadi/amr-tst
wandb: 🚀 View run at https://wandb.ai/abdiharyadi/amr-tst/runs/278wbs6z

  0%|          | 0/61904 [00:00<?, ?it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

  0%|          | 1/61904 [00:01<32:12:42,  1.87s/it]
                                                    
{'loss': 3.6995, 'learning_rate': 1e-09, 'epoch': 0.0}

  0%|          | 1/61904 [00:01<32:12:42,  1.87s/it]
  0%|          | 2/61904 [00:03<26:18:45,  1.53s/it]
  0%|          | 3/61904 [00:04<25:53:08,  1.51s/it]
  0%|          | 4/61904 [00:05<24:24:54,  1.42s/it]
  0%|          | 5/61904 [00:07<24:27:12,  1.42s/it]
  0%|          | 6/61904 [00:08<24:16:58,  1.41s/it]
  0%|          | 7/61904 [00:10<23:47:44,  1.38s/it]
  0%|          | 8/61904 [00:11<24:52:38,  1.45s/it]
  0%|          | 9/61904 [00:13<25:27:28,  1.48s/it]
  0%|          | 10/61904 [00:14<25:17:09,  1.47s/it]
  0%|          | 11/61904 [00:15<24:09:02,  1.40s/it]
  0%|          | 12/61904 [00:17<23:56:52,  1.39s/it]
  0%|          | 13/61904 [00:18<23:45:44,  1.38s/it]
  0%|          | 14/61904 [00:20<24:20:04,  1.42s/it]
  0%|          | 15/61904 [00:21<24:25:56,  1.42s/it]
  0%|          | 16/61904 [00:22<23:39:25,  1.38s/it]
  0%|          | 17/61904 [00:24<23:39:12,  1.38s/it]
  0%|          | 18/61904 [00:25<23:02:09,  1.34s/it]
  0%|          | 19/61904 [00:26<23:13:19,  1.35s/it]
  0%|          | 20/61904 [00:28<22:49:33,  1.33s/it]
                                                     
{'loss': 3.6397, 'learning_rate': 2e-08, 'epoch': 0.01}

  0%|          | 20/61904 [00:28<22:49:33,  1.33s/it]
  0%|          | 21/61904 [00:29<22:47:54,  1.33s/it]
  0%|          | 22/61904 [00:30<22:43:44,  1.32s/it]
  0%|          | 23/61904 [00:32<22:26:15,  1.31s/it]
  0%|          | 24/61904 [00:33<22:58:32,  1.34s/it]
  0%|          | 25/61904 [00:34<23:43:43,  1.38s/it]
  0%|          | 26/61904 [00:36<23:17:44,  1.36s/it]
  0%|          | 27/61904 [00:37<23:07:00,  1.34s/it]
  0%|          | 28/61904 [00:38<22:48:45,  1.33s/it]
  0%|          | 29/61904 [00:40<22:31:40,  1.31s/it]
  0%|          | 30/61904 [00:41<23:26:43,  1.36s/it]
  0%|          | 31/61904 [00:42<23:22:25,  1.36s/it]
  0%|          | 32/61904 [00:44<24:55:21,  1.45s/it]
  0%|          | 33/61904 [00:45<24:16:17,  1.41s/it]
  0%|          | 34/61904 [00:47<24:10:49,  1.41s/it]
  0%|          | 35/61904 [00:48<23:26:15,  1.36s/it]
  0%|          | 36/61904 [00:49<23:29:05,  1.37s/it]
  0%|          | 37/61904 [00:51<23:07:11,  1.35s/it]
  0%|          | 38/61904 [00:52<24:00:45,  1.40s/it]
  0%|          | 39/61904 [00:54<23:40:24,  1.38s/it]
  0%|          | 40/61904 [00:55<23:15:58,  1.35s/it]
                                                     
{'loss': 3.6775, 'learning_rate': 4e-08, 'epoch': 0.01}

  0%|          | 40/61904 [00:55<23:15:58,  1.35s/it]
  0%|          | 41/61904 [00:56<23:35:52,  1.37s/it]
  0%|          | 42/61904 [00:58<22:46:48,  1.33s/it]
  0%|          | 43/61904 [00:59<22:50:18,  1.33s/it]
  0%|          | 44/61904 [01:00<22:19:11,  1.30s/it]
  0%|          | 45/61904 [01:02<24:10:13,  1.41s/it]
  0%|          | 46/61904 [01:03<24:29:14,  1.43s/it]
  0%|          | 47/61904 [01:04<23:44:31,  1.38s/it]
  0%|          | 48/61904 [01:06<23:47:13,  1.38s/it]
  0%|          | 49/61904 [01:07<23:20:31,  1.36s/it]
  0%|          | 50/61904 [01:09<23:42:20,  1.38s/it]
  0%|          | 51/61904 [01:10<23:41:00,  1.38s/it]
  0%|          | 52/61904 [01:11<23:13:20,  1.35s/it]
  0%|          | 53/61904 [01:13<23:31:28,  1.37s/it]
  0%|          | 54/61904 [01:14<22:50:04,  1.33s/it]
  0%|          | 55/61904 [01:15<22:49:11,  1.33s/it]
  0%|          | 56/61904 [01:17<23:30:01,  1.37s/it]
  0%|          | 57/61904 [01:18<23:18:36,  1.36s/it]
  0%|          | 58/61904 [01:19<23:31:08,  1.37s/it]
  0%|          | 59/61904 [01:21<23:37:49,  1.38s/it]
  0%|          | 60/61904 [01:22<23:28:56,  1.37s/it]
                                                     
{'loss': 3.8059, 'learning_rate': 6e-08, 'epoch': 0.02}

  0%|          | 60/61904 [01:22<23:28:56,  1.37s/it]
  0%|          | 61/61904 [01:24<24:13:35,  1.41s/it]
  0%|          | 62/61904 [01:25<24:14:15,  1.41s/it]
  0%|          | 63/61904 [01:27<24:12:59,  1.41s/it]
  0%|          | 64/61904 [01:28<24:08:37,  1.41s/it]
  0%|          | 65/61904 [01:29<23:32:01,  1.37s/it]
  0%|          | 66/61904 [01:30<22:59:20,  1.34s/it]
  0%|          | 67/61904 [01:32<22:38:43,  1.32s/it]
  0%|          | 68/61904 [01:33<23:35:36,  1.37s/it]
  0%|          | 69/61904 [01:35<24:33:50,  1.43s/it]
  0%|          | 70/61904 [01:36<24:50:58,  1.45s/it]
  0%|          | 71/61904 [01:38<24:51:09,  1.45s/it]
  0%|          | 72/61904 [01:39<24:31:13,  1.43s/it]
  0%|          | 73/61904 [01:41<25:18:26,  1.47s/it]
  0%|          | 74/61904 [01:42<24:04:32,  1.40s/it]
  0%|          | 75/61904 [01:43<24:36:10,  1.43s/it]
  0%|          | 76/61904 [01:45<24:41:14,  1.44s/it]
  0%|          | 77/61904 [01:46<24:06:01,  1.40s/it]
  0%|          | 78/61904 [01:47<23:03:55,  1.34s/it]
  0%|          | 79/61904 [01:49<22:57:24,  1.34s/it]
  0%|          | 80/61904 [01:50<23:35:03,  1.37s/it]
                                                     
{'loss': 3.6028, 'learning_rate': 8e-08, 'epoch': 0.02}

  0%|          | 80/61904 [01:50<23:35:03,  1.37s/it]
  0%|          | 81/61904 [01:52<23:29:31,  1.37s/it]
  0%|          | 82/61904 [01:53<23:04:34,  1.34s/it]
  0%|          | 83/61904 [01:54<23:13:31,  1.35s/it]
  0%|          | 84/61904 [01:56<23:20:53,  1.36s/it]
  0%|          | 85/61904 [01:57<23:37:45,  1.38s/it]
  0%|          | 86/61904 [01:58<23:09:57,  1.35s/it]
  0%|          | 87/61904 [02:00<23:12:01,  1.35s/it]
  0%|          | 88/61904 [02:01<22:37:26,  1.32s/it]
  0%|          | 89/61904 [02:02<22:39:10,  1.32s/it]
  0%|          | 90/61904 [02:04<23:29:03,  1.37s/it]
  0%|          | 91/61904 [02:05<22:34:25,  1.31s/it]
  0%|          | 92/61904 [02:06<22:47:32,  1.33s/it]
  0%|          | 93/61904 [02:08<23:06:17,  1.35s/it]
  0%|          | 94/61904 [02:09<22:25:57,  1.31s/it]
  0%|          | 95/61904 [02:10<22:31:36,  1.31s/it]
  0%|          | 96/61904 [02:12<22:50:00,  1.33s/it]
  0%|          | 97/61904 [02:13<23:30:41,  1.37s/it]
  0%|          | 98/61904 [02:14<23:19:36,  1.36s/it]
  0%|          | 99/61904 [02:16<23:16:44,  1.36s/it]
  0%|          | 100/61904 [02:17<24:18:57,  1.42s/it]
                                                      
{'loss': 3.5831, 'learning_rate': 1e-07, 'epoch': 0.03}

  0%|          | 100/61904 [02:17<24:18:57,  1.42s/it]
  0%|          | 101/61904 [02:19<24:22:47,  1.42s/it]
  0%|          | 102/61904 [02:20<23:41:57,  1.38s/it]
  0%|          | 103/61904 [02:21<23:38:36,  1.38s/it]
  0%|          | 104/61904 [02:23<23:06:11,  1.35s/it]
  0%|          | 105/61904 [02:24<22:49:32,  1.33s/it]
  0%|          | 106/61904 [02:25<23:21:05,  1.36s/it]
  0%|          | 107/61904 [02:27<23:05:58,  1.35s/it]
  0%|          | 108/61904 [02:28<22:53:00,  1.33s/it]
  0%|          | 109/61904 [02:29<23:33:07,  1.37s/it]
  0%|          | 110/61904 [02:31<23:50:12,  1.39s/it]
  0%|          | 111/61904 [02:32<24:30:50,  1.43s/it]
  0%|          | 112/61904 [02:34<23:45:29,  1.38s/it]
  0%|          | 113/61904 [02:35<23:27:26,  1.37s/it]
  0%|          | 114/61904 [02:36<22:57:17,  1.34s/it]
  0%|          | 115/61904 [02:38<22:58:57,  1.34s/it]
  0%|          | 116/61904 [02:39<22:35:41,  1.32s/it]
  0%|          | 117/61904 [02:40<23:30:50,  1.37s/it]
  0%|          | 118/61904 [02:42<23:16:06,  1.36s/it]
  0%|          | 119/61904 [02:43<22:54:50,  1.34s/it]
  0%|          | 120/61904 [02:44<22:36:24,  1.32s/it]
                                                      
{'loss': 3.4939, 'learning_rate': 1.2e-07, 'epoch': 0.03}

  0%|          | 120/61904 [02:44<22:36:24,  1.32s/it]
  0%|          | 121/61904 [02:45<22:28:34,  1.31s/it]
  0%|          | 122/61904 [02:47<22:45:28,  1.33s/it]
  0%|          | 123/61904 [02:48<22:58:32,  1.34s/it]
  0%|          | 124/61904 [02:50<23:42:49,  1.38s/it]
  0%|          | 125/61904 [02:51<23:30:49,  1.37s/it]
  0%|          | 126/61904 [02:52<22:59:18,  1.34s/it]
  0%|          | 127/61904 [02:54<23:16:49,  1.36s/it]
  0%|          | 128/61904 [02:55<22:53:07,  1.33s/it]
  0%|          | 129/61904 [02:56<23:32:04,  1.37s/it]
  0%|          | 130/61904 [02:58<23:32:28,  1.37s/it]
  0%|          | 131/61904 [02:59<24:12:14,  1.41s/it]
  0%|          | 132/61904 [03:01<23:47:18,  1.39s/it]
  0%|          | 133/61904 [03:02<24:07:15,  1.41s/it]
  0%|          | 134/61904 [03:03<23:34:38,  1.37s/it]
  0%|          | 135/61904 [03:05<23:29:30,  1.37s/it]
  0%|          | 136/61904 [03:06<23:29:37,  1.37s/it]
  0%|          | 137/61904 [03:07<23:05:31,  1.35s/it]
  0%|          | 138/61904 [03:09<23:13:40,  1.35s/it]
  0%|          | 139/61904 [03:10<23:16:14,  1.36s/it]
  0%|          | 140/61904 [03:12<23:32:58,  1.37s/it]
                                                      
{'loss': 3.4946, 'learning_rate': 1.3999999999999998e-07, 'epoch': 0.04}

  0%|          | 140/61904 [03:12<23:32:58,  1.37s/it]
  0%|          | 141/61904 [03:13<24:10:35,  1.41s/it]
  0%|          | 142/61904 [03:14<23:00:51,  1.34s/it]
  0%|          | 143/61904 [03:16<23:33:22,  1.37s/it]
  0%|          | 144/61904 [03:17<22:39:27,  1.32s/it]
  0%|          | 145/61904 [03:18<22:42:41,  1.32s/it]
  0%|          | 146/61904 [03:20<24:18:07,  1.42s/it]
  0%|          | 147/61904 [03:21<23:36:20,  1.38s/it]
  0%|          | 148/61904 [03:23<24:03:53,  1.40s/it]
  0%|          | 149/61904 [03:24<24:11:19,  1.41s/it]
  0%|          | 150/61904 [03:26<24:55:14,  1.45s/it]
  0%|          | 151/61904 [03:27<24:37:44,  1.44s/it]
  0%|          | 152/61904 [03:28<24:01:05,  1.40s/it]
  0%|          | 153/61904 [03:30<23:04:54,  1.35s/it]
  0%|          | 154/61904 [03:31<23:40:56,  1.38s/it]
  0%|          | 155/61904 [03:32<24:08:23,  1.41s/it]
  0%|          | 156/61904 [03:34<23:38:14,  1.38s/it]
  0%|          | 157/61904 [03:35<24:05:33,  1.40s/it]
  0%|          | 158/61904 [03:36<23:21:07,  1.36s/it]
  0%|          | 159/61904 [03:38<23:31:34,  1.37s/it]
  0%|          | 160/61904 [03:39<22:45:53,  1.33s/it]
                                                      
{'loss': 3.4607, 'learning_rate': 1.6e-07, 'epoch': 0.04}

  0%|          | 160/61904 [03:39<22:45:53,  1.33s/it]
  0%|          | 161/61904 [03:40<23:01:25,  1.34s/it]
  0%|          | 162/61904 [03:42<24:16:48,  1.42s/it]
  0%|          | 163/61904 [03:43<23:34:30,  1.37s/it]
  0%|          | 164/61904 [03:45<23:57:44,  1.40s/it]
  0%|          | 165/61904 [03:46<23:32:17,  1.37s/it]
  0%|          | 166/61904 [03:47<23:26:30,  1.37s/it]
  0%|          | 167/61904 [03:49<23:39:12,  1.38s/it]
  0%|          | 168/61904 [03:50<23:48:53,  1.39s/it]
  0%|          | 169/61904 [03:52<23:38:48,  1.38s/it]
  0%|          | 170/61904 [03:53<22:53:24,  1.33s/it]
  0%|          | 171/61904 [03:54<22:42:09,  1.32s/it]
  0%|          | 172/61904 [03:55<22:39:48,  1.32s/it]
  0%|          | 173/61904 [03:57<22:22:01,  1.30s/it]
  0%|          | 174/61904 [03:58<23:37:31,  1.38s/it]
  0%|          | 175/61904 [04:00<23:03:09,  1.34s/it]
  0%|          | 176/61904 [04:01<22:16:43,  1.30s/it]
  0%|          | 177/61904 [04:02<22:57:35,  1.34s/it]
  0%|          | 178/61904 [04:04<22:55:52,  1.34s/it]
  0%|          | 179/61904 [04:05<23:05:31,  1.35s/it]
  0%|          | 180/61904 [04:06<23:12:53,  1.35s/it]
                                                      
{'loss': 3.4372, 'learning_rate': 1.8e-07, 'epoch': 0.05}

  0%|          | 180/61904 [04:06<23:12:53,  1.35s/it]
  0%|          | 181/61904 [04:08<24:10:57,  1.41s/it]
  0%|          | 182/61904 [04:09<23:36:24,  1.38s/it]
  0%|          | 183/61904 [04:10<23:35:55,  1.38s/it]
  0%|          | 184/61904 [04:12<23:25:37,  1.37s/it]
  0%|          | 185/61904 [04:13<23:05:04,  1.35s/it]
  0%|          | 186/61904 [04:14<23:11:19,  1.35s/it]
  0%|          | 187/61904 [04:16<22:40:13,  1.32s/it]
  0%|          | 188/61904 [04:17<22:36:33,  1.32s/it]
  0%|          | 189/61904 [04:18<22:39:13,  1.32s/it]
  0%|          | 190/61904 [04:20<22:36:49,  1.32s/it]
  0%|          | 191/61904 [04:21<23:36:23,  1.38s/it]
  0%|          | 192/61904 [04:23<23:19:19,  1.36s/it]
  0%|          | 193/61904 [04:24<23:42:22,  1.38s/it]
  0%|          | 194/61904 [04:25<23:27:00,  1.37s/it]
  0%|          | 195/61904 [04:27<23:20:03,  1.36s/it]
  0%|          | 196/61904 [04:28<23:03:04,  1.34s/it]
  0%|          | 197/61904 [04:29<23:31:07,  1.37s/it]
  0%|          | 198/61904 [04:31<24:14:21,  1.41s/it]
  0%|          | 199/61904 [04:32<23:31:33,  1.37s/it]
  0%|          | 200/61904 [04:34<23:45:01,  1.39s/it]
                                                      
{'loss': 3.3843, 'learning_rate': 2e-07, 'epoch': 0.05}

  0%|          | 200/61904 [04:34<23:45:01,  1.39s/it]
  0%|          | 201/61904 [04:35<23:50:29,  1.39s/it]
  0%|          | 202/61904 [04:36<24:11:00,  1.41s/it]
  0%|          | 203/61904 [04:38<23:24:45,  1.37s/it]
  0%|          | 204/61904 [04:39<23:09:27,  1.35s/it]
  0%|          | 205/61904 [04:40<23:09:40,  1.35s/it]
  0%|          | 206/61904 [04:42<23:44:09,  1.38s/it]
  0%|          | 207/61904 [04:43<24:05:33,  1.41s/it]
  0%|          | 208/61904 [04:45<23:38:28,  1.38s/it]
  0%|          | 209/61904 [04:46<23:23:47,  1.37s/it]
  0%|          | 210/61904 [04:47<23:45:06,  1.39s/it]
  0%|          | 211/61904 [04:49<23:26:40,  1.37s/it]
  0%|          | 212/61904 [04:50<23:57:31,  1.40s/it]
  0%|          | 213/61904 [04:51<23:17:54,  1.36s/it]
  0%|          | 214/61904 [04:53<22:58:29,  1.34s/it]
  0%|          | 215/61904 [04:54<23:01:42,  1.34s/it]
  0%|          | 216/61904 [04:56<23:29:25,  1.37s/it]
  0%|          | 217/61904 [04:57<23:31:03,  1.37s/it]
  0%|          | 218/61904 [04:58<23:03:00,  1.35s/it]
  0%|          | 219/61904 [05:00<24:10:06,  1.41s/it]
  0%|          | 220/61904 [05:01<24:02:25,  1.40s/it]
                                                      
{'loss': 3.4237, 'learning_rate': 1.9996758719045768e-07, 'epoch': 0.06}

  0%|          | 220/61904 [05:01<24:02:25,  1.40s/it]
  0%|          | 221/61904 [05:03<24:02:26,  1.40s/it]
  0%|          | 222/61904 [05:04<24:35:17,  1.44s/it]
  0%|          | 223/61904 [05:05<24:22:28,  1.42s/it]
  0%|          | 224/61904 [05:07<24:09:12,  1.41s/it]
  0%|          | 225/61904 [05:08<23:51:47,  1.39s/it]
  0%|          | 226/61904 [05:09<23:14:49,  1.36s/it]
  0%|          | 227/61904 [05:11<23:59:56,  1.40s/it]
  0%|          | 228/61904 [05:12<24:23:55,  1.42s/it]
  0%|          | 229/61904 [05:14<24:03:33,  1.40s/it]
  0%|          | 230/61904 [05:15<24:03:13,  1.40s/it]
  0%|          | 231/61904 [05:17<24:05:25,  1.41s/it]
  0%|          | 232/61904 [05:18<23:54:51,  1.40s/it]
  0%|          | 233/61904 [05:19<23:31:00,  1.37s/it]
  0%|          | 234/61904 [05:21<23:49:54,  1.39s/it]
  0%|          | 235/61904 [05:22<24:16:14,  1.42s/it]
  0%|          | 236/61904 [05:24<25:31:01,  1.49s/it]
  0%|          | 237/61904 [05:25<24:48:20,  1.45s/it]
  0%|          | 238/61904 [05:27<24:25:33,  1.43s/it]
  0%|          | 239/61904 [05:28<23:49:51,  1.39s/it]
  0%|          | 240/61904 [05:29<24:25:12,  1.43s/it]
                                                      
{'loss': 3.4052, 'learning_rate': 1.9993517438091531e-07, 'epoch': 0.06}

  0%|          | 240/61904 [05:29<24:25:12,  1.43s/it]
  0%|          | 241/61904 [05:31<24:28:20,  1.43s/it]
  0%|          | 242/61904 [05:32<24:43:33,  1.44s/it]
  0%|          | 243/61904 [05:34<24:50:14,  1.45s/it]
  0%|          | 244/61904 [05:35<23:49:33,  1.39s/it]
  0%|          | 245/61904 [05:36<23:43:01,  1.38s/it]
  0%|          | 246/61904 [05:38<23:16:10,  1.36s/it]
  0%|          | 247/61904 [05:39<23:45:59,  1.39s/it]
  0%|          | 248/61904 [05:41<23:36:18,  1.38s/it]
  0%|          | 249/61904 [05:42<22:57:33,  1.34s/it]
  0%|          | 250/61904 [05:43<22:39:00,  1.32s/it]
  0%|          | 251/61904 [05:44<23:02:40,  1.35s/it]
  0%|          | 252/61904 [05:46<23:36:15,  1.38s/it]
  0%|          | 253/61904 [05:47<23:44:22,  1.39s/it]
  0%|          | 254/61904 [05:49<23:04:04,  1.35s/it]
  0%|          | 255/61904 [05:50<23:40:11,  1.38s/it]
  0%|          | 256/61904 [05:52<24:38:11,  1.44s/it]
  0%|          | 257/61904 [05:53<25:21:23,  1.48s/it]
  0%|          | 258/61904 [05:55<24:52:52,  1.45s/it]
  0%|          | 259/61904 [05:56<24:24:09,  1.43s/it]
  0%|          | 260/61904 [05:57<23:44:54,  1.39s/it]
                                                      
{'loss': 3.4037, 'learning_rate': 1.99902761571373e-07, 'epoch': 0.07}

  0%|          | 260/61904 [05:57<23:44:54,  1.39s/it]
  0%|          | 261/61904 [05:59<24:30:22,  1.43s/it]
  0%|          | 262/61904 [06:00<24:04:45,  1.41s/it]
  0%|          | 263/61904 [06:02<24:05:58,  1.41s/it]
  0%|          | 264/61904 [06:03<23:38:28,  1.38s/it]
  0%|          | 265/61904 [06:04<23:57:18,  1.40s/it]
  0%|          | 266/61904 [06:06<23:27:13,  1.37s/it]
  0%|          | 267/61904 [06:07<23:26:10,  1.37s/it]
  0%|          | 268/61904 [06:08<23:12:19,  1.36s/it]
  0%|          | 269/61904 [06:10<23:02:25,  1.35s/it]
  0%|          | 270/61904 [06:11<22:53:15,  1.34s/it]
  0%|          | 271/61904 [06:12<22:58:26,  1.34s/it]
  0%|          | 272/61904 [06:14<22:49:07,  1.33s/it]
  0%|          | 273/61904 [06:15<22:36:46,  1.32s/it]
  0%|          | 274/61904 [06:16<22:40:13,  1.32s/it]
  0%|          | 275/61904 [06:17<22:06:51,  1.29s/it]
  0%|          | 276/61904 [06:19<22:09:19,  1.29s/it]
  0%|          | 277/61904 [06:20<22:30:27,  1.31s/it]
  0%|          | 278/61904 [06:21<23:03:24,  1.35s/it]
  0%|          | 279/61904 [06:23<22:51:50,  1.34s/it]
  0%|          | 280/61904 [06:24<23:07:32,  1.35s/it]
                                                      
{'loss': 3.4114, 'learning_rate': 1.9987034876183066e-07, 'epoch': 0.07}

  0%|          | 280/61904 [06:24<23:07:32,  1.35s/it]
  0%|          | 281/61904 [06:25<22:23:21,  1.31s/it]
  0%|          | 282/61904 [06:27<23:26:24,  1.37s/it]
  0%|          | 283/61904 [06:28<22:52:01,  1.34s/it]
  0%|          | 284/61904 [06:30<23:09:26,  1.35s/it]
  0%|          | 285/61904 [06:31<22:24:24,  1.31s/it]
  0%|          | 286/61904 [06:32<22:18:08,  1.30s/it]
  0%|          | 287/61904 [06:33<22:02:45,  1.29s/it]
  0%|          | 288/61904 [06:35<23:05:58,  1.35s/it]
  0%|          | 289/61904 [06:36<23:57:50,  1.40s/it]
  0%|          | 290/61904 [06:38<24:02:34,  1.40s/it]
  0%|          | 291/61904 [06:39<24:03:24,  1.41s/it]
  0%|          | 292/61904 [06:41<24:03:14,  1.41s/it]
  0%|          | 293/61904 [06:42<24:43:18,  1.44s/it]
  0%|          | 294/61904 [06:44<25:26:24,  1.49s/it]
  0%|          | 295/61904 [06:45<24:23:07,  1.42s/it]
  0%|          | 296/61904 [06:46<24:13:12,  1.42s/it]
  0%|          | 297/61904 [06:48<24:01:06,  1.40s/it]
  0%|          | 298/61904 [06:49<23:14:51,  1.36s/it]
  0%|          | 299/61904 [06:50<22:56:00,  1.34s/it]
  0%|          | 300/61904 [06:52<23:41:15,  1.38s/it]
                                                      
{'loss': 3.4259, 'learning_rate': 1.9983793595228833e-07, 'epoch': 0.08}

  0%|          | 300/61904 [06:52<23:41:15,  1.38s/it]
  0%|          | 301/61904 [06:53<23:19:37,  1.36s/it]
  0%|          | 302/61904 [06:54<23:22:51,  1.37s/it]
  0%|          | 303/61904 [06:56<23:41:18,  1.38s/it]
  0%|          | 304/61904 [06:57<24:03:16,  1.41s/it]
  0%|          | 305/61904 [06:59<23:29:54,  1.37s/it]
  0%|          | 306/61904 [07:00<23:14:50,  1.36s/it]
  0%|          | 307/61904 [07:01<23:00:12,  1.34s/it]
  0%|          | 308/61904 [07:03<23:13:31,  1.36s/it]
  0%|          | 309/61904 [07:04<24:11:40,  1.41s/it]
  1%|          | 310/61904 [07:06<24:39:52,  1.44s/it]
  1%|          | 311/61904 [07:07<24:53:39,  1.46s/it]
  1%|          | 312/61904 [07:09<24:46:12,  1.45s/it]
  1%|          | 313/61904 [07:10<23:35:01,  1.38s/it]
  1%|          | 314/61904 [07:11<23:10:56,  1.36s/it]
  1%|          | 315/61904 [07:12<22:40:45,  1.33s/it]
  1%|          | 316/61904 [07:14<22:54:01,  1.34s/it]
  1%|          | 317/61904 [07:15<22:54:02,  1.34s/it]
  1%|          | 318/61904 [07:17<23:42:00,  1.39s/it]
  1%|          | 319/61904 [07:18<23:03:42,  1.35s/it]
  1%|          | 320/61904 [07:19<22:19:21,  1.30s/it]
                                                      
{'loss': 3.3792, 'learning_rate': 1.9980552314274602e-07, 'epoch': 0.08}

  1%|          | 320/61904 [07:19<22:19:21,  1.30s/it]
  1%|          | 321/61904 [07:21<23:30:27,  1.37s/it]
  1%|          | 322/61904 [07:22<23:30:04,  1.37s/it]
  1%|          | 323/61904 [07:23<23:35:15,  1.38s/it]
  1%|          | 324/61904 [07:25<23:25:42,  1.37s/it]
  1%|          | 325/61904 [07:26<23:04:58,  1.35s/it]
  1%|          | 326/61904 [07:27<23:05:28,  1.35s/it]
  1%|          | 327/61904 [07:29<22:30:26,  1.32s/it]
  1%|          | 328/61904 [07:30<23:14:56,  1.36s/it]
  1%|          | 329/61904 [07:31<22:54:57,  1.34s/it]
  1%|          | 330/61904 [07:33<23:18:18,  1.36s/it]
  1%|          | 331/61904 [07:34<23:12:51,  1.36s/it]
  1%|          | 332/61904 [07:35<23:07:43,  1.35s/it]
  1%|          | 333/61904 [07:37<23:32:05,  1.38s/it]
  1%|          | 334/61904 [07:38<23:16:37,  1.36s/it]
  1%|          | 335/61904 [07:39<22:50:11,  1.34s/it]
  1%|          | 336/61904 [07:41<23:44:44,  1.39s/it]
  1%|          | 337/61904 [07:42<23:17:29,  1.36s/it]
  1%|          | 338/61904 [07:44<22:47:33,  1.33s/it]
  1%|          | 339/61904 [07:45<22:50:44,  1.34s/it]
  1%|          | 340/61904 [07:46<22:28:05,  1.31s/it]
                                                      
{'loss': 3.2866, 'learning_rate': 1.9977311033320368e-07, 'epoch': 0.09}

  1%|          | 340/61904 [07:46<22:28:05,  1.31s/it]
  1%|          | 341/61904 [07:48<23:33:52,  1.38s/it]
  1%|          | 342/61904 [07:49<22:54:41,  1.34s/it]
  1%|          | 343/61904 [07:50<23:26:36,  1.37s/it]
  1%|          | 344/61904 [07:52<23:21:13,  1.37s/it]
  1%|          | 345/61904 [07:53<23:26:57,  1.37s/it]
  1%|          | 346/61904 [07:54<22:46:27,  1.33s/it]
  1%|          | 347/61904 [07:56<22:46:19,  1.33s/it]
  1%|          | 348/61904 [07:57<22:27:49,  1.31s/it]
  1%|          | 349/61904 [07:58<22:37:30,  1.32s/it]
  1%|          | 350/61904 [08:00<23:14:25,  1.36s/it]
  1%|          | 351/61904 [08:01<24:36:12,  1.44s/it]
  1%|          | 352/61904 [08:03<24:03:02,  1.41s/it]
  1%|          | 353/61904 [08:04<24:37:35,  1.44s/it]
  1%|          | 354/61904 [08:06<23:45:41,  1.39s/it]
  1%|          | 355/61904 [08:07<24:39:05,  1.44s/it]
  1%|          | 356/61904 [08:08<23:31:10,  1.38s/it]
  1%|          | 357/61904 [08:10<22:49:21,  1.33s/it]
  1%|          | 358/61904 [08:11<22:54:08,  1.34s/it]
  1%|          | 359/61904 [08:12<22:48:46,  1.33s/it]
  1%|          | 360/61904 [08:13<22:35:19,  1.32s/it]
                                                      
{'loss': 3.3454, 'learning_rate': 1.9974069752366134e-07, 'epoch': 0.09}

  1%|          | 360/61904 [08:13<22:35:19,  1.32s/it]
  1%|          | 361/61904 [08:15<23:31:31,  1.38s/it]
  1%|          | 362/61904 [08:16<23:28:11,  1.37s/it]
  1%|          | 363/61904 [08:18<23:41:37,  1.39s/it]
  1%|          | 364/61904 [08:19<23:11:42,  1.36s/it]
  1%|          | 365/61904 [08:20<23:19:15,  1.36s/it]
  1%|          | 366/61904 [08:22<22:55:10,  1.34s/it]
  1%|          | 367/61904 [08:23<22:47:50,  1.33s/it]
  1%|          | 368/61904 [08:24<22:24:22,  1.31s/it]
  1%|          | 369/61904 [08:26<22:08:54,  1.30s/it]
  1%|          | 370/61904 [08:27<22:02:33,  1.29s/it]
  1%|          | 371/61904 [08:28<21:38:27,  1.27s/it]
  1%|          | 372/61904 [08:29<22:09:48,  1.30s/it]
  1%|          | 373/61904 [08:31<23:29:57,  1.37s/it]
  1%|          | 374/61904 [08:32<23:24:42,  1.37s/it]
  1%|          | 375/61904 [08:34<23:14:34,  1.36s/it]
  1%|          | 376/61904 [08:35<22:48:56,  1.33s/it]
  1%|          | 377/61904 [08:36<22:19:26,  1.31s/it]
  1%|          | 378/61904 [08:38<23:04:07,  1.35s/it]
  1%|          | 379/61904 [08:39<23:32:30,  1.38s/it]
  1%|          | 380/61904 [08:40<23:31:20,  1.38s/it]
                                                      
{'loss': 3.3625, 'learning_rate': 1.9970828471411903e-07, 'epoch': 0.1}

  1%|          | 380/61904 [08:40<23:31:20,  1.38s/it]
  1%|          | 381/61904 [08:42<23:57:56,  1.40s/it]
  1%|          | 382/61904 [08:43<24:14:46,  1.42s/it]
  1%|          | 383/61904 [08:45<23:39:33,  1.38s/it]
  1%|          | 384/61904 [08:46<23:42:12,  1.39s/it]
  1%|          | 385/61904 [08:47<23:31:47,  1.38s/it]
  1%|          | 386/61904 [08:49<23:33:11,  1.38s/it]
  1%|          | 387/61904 [08:50<23:07:56,  1.35s/it]
  1%|          | 388/61904 [08:51<22:57:56,  1.34s/it]
  1%|          | 389/61904 [08:53<23:31:19,  1.38s/it]
  1%|          | 390/61904 [08:54<23:28:15,  1.37s/it]
  1%|          | 391/61904 [08:56<23:53:23,  1.40s/it]
  1%|          | 392/61904 [08:57<24:42:04,  1.45s/it]
  1%|          | 393/61904 [08:59<24:22:35,  1.43s/it]
  1%|          | 394/61904 [09:00<23:33:25,  1.38s/it]
  1%|          | 395/61904 [09:01<24:15:22,  1.42s/it]
  1%|          | 396/61904 [09:03<24:03:26,  1.41s/it]
  1%|          | 397/61904 [09:04<23:42:35,  1.39s/it]
  1%|          | 398/61904 [09:05<23:20:57,  1.37s/it]
  1%|          | 399/61904 [09:07<23:56:26,  1.40s/it]
  1%|          | 400/61904 [09:08<23:46:34,  1.39s/it]
                                                      
{'loss': 3.3624, 'learning_rate': 1.9967587190457666e-07, 'epoch': 0.1}

  1%|          | 400/61904 [09:08<23:46:34,  1.39s/it]
  1%|          | 401/61904 [09:10<23:42:41,  1.39s/it]
  1%|          | 402/61904 [09:11<25:15:38,  1.48s/it]
  1%|          | 403/61904 [09:13<24:59:42,  1.46s/it]
  1%|          | 404/61904 [09:14<25:11:45,  1.47s/it]
  1%|          | 405/61904 [09:16<24:26:51,  1.43s/it]
  1%|          | 406/61904 [09:17<23:56:44,  1.40s/it]
  1%|          | 407/61904 [09:18<23:57:25,  1.40s/it]
  1%|          | 408/61904 [09:20<23:28:14,  1.37s/it]
  1%|          | 409/61904 [09:21<24:27:29,  1.43s/it]
  1%|          | 410/61904 [09:23<24:18:43,  1.42s/it]
  1%|          | 411/61904 [09:24<25:51:22,  1.51s/it]
  1%|          | 412/61904 [09:26<25:34:02,  1.50s/it]
  1%|          | 413/61904 [09:27<24:07:44,  1.41s/it]
  1%|          | 414/61904 [09:29<24:54:20,  1.46s/it]
  1%|          | 415/61904 [09:30<24:42:33,  1.45s/it]
  1%|          | 416/61904 [09:32<24:58:16,  1.46s/it]
  1%|          | 417/61904 [09:33<23:45:09,  1.39s/it]
  1%|          | 418/61904 [09:34<24:39:30,  1.44s/it]
  1%|          | 419/61904 [09:36<24:38:12,  1.44s/it]
  1%|          | 420/61904 [09:37<24:39:36,  1.44s/it]
                                                      
{'loss': 3.3077, 'learning_rate': 1.9964345909503435e-07, 'epoch': 0.11}

  1%|          | 420/61904 [09:37<24:39:36,  1.44s/it]
  1%|          | 421/61904 [09:39<24:04:27,  1.41s/it]
  1%|          | 422/61904 [09:40<23:28:41,  1.37s/it]
  1%|          | 423/61904 [09:41<24:09:49,  1.41s/it]
  1%|          | 424/61904 [09:43<24:18:08,  1.42s/it]
  1%|          | 425/61904 [09:44<23:57:32,  1.40s/it]
  1%|          | 426/61904 [09:46<24:01:22,  1.41s/it]
  1%|          | 427/61904 [09:47<23:58:05,  1.40s/it]
  1%|          | 428/61904 [09:48<23:56:13,  1.40s/it]
  1%|          | 429/61904 [09:50<23:59:48,  1.41s/it]
  1%|          | 430/61904 [09:51<23:36:34,  1.38s/it]
  1%|          | 431/61904 [09:52<23:19:08,  1.37s/it]
  1%|          | 432/61904 [09:54<22:54:57,  1.34s/it]
  1%|          | 433/61904 [09:55<23:42:15,  1.39s/it]
  1%|          | 434/61904 [09:57<23:15:47,  1.36s/it]
  1%|          | 435/61904 [09:58<22:25:28,  1.31s/it]
  1%|          | 436/61904 [09:59<22:51:14,  1.34s/it]
  1%|          | 437/61904 [10:00<23:02:35,  1.35s/it]
  1%|          | 438/61904 [10:02<22:32:54,  1.32s/it]
  1%|          | 439/61904 [10:03<21:55:59,  1.28s/it]
  1%|          | 440/61904 [10:04<21:56:06,  1.28s/it]
                                                      
{'loss': 3.274, 'learning_rate': 1.99611046285492e-07, 'epoch': 0.11}

  1%|          | 440/61904 [10:04<21:56:06,  1.28s/it]
  1%|          | 441/61904 [10:05<21:49:17,  1.28s/it]
  1%|          | 442/61904 [10:07<22:36:53,  1.32s/it]
  1%|          | 443/61904 [10:08<22:48:55,  1.34s/it]
  1%|          | 444/61904 [10:10<23:17:06,  1.36s/it]
  1%|          | 445/61904 [10:11<23:34:05,  1.38s/it]
  1%|          | 446/61904 [10:13<23:42:50,  1.39s/it]
  1%|          | 447/61904 [10:14<23:36:45,  1.38s/it]
  1%|          | 448/61904 [10:15<23:54:29,  1.40s/it]
  1%|          | 449/61904 [10:17<23:46:20,  1.39s/it]
  1%|          | 450/61904 [10:18<23:03:42,  1.35s/it]
  1%|          | 451/61904 [10:19<23:10:18,  1.36s/it]
  1%|          | 452/61904 [10:21<23:14:31,  1.36s/it]
  1%|          | 453/61904 [10:22<23:21:23,  1.37s/it]
  1%|          | 454/61904 [10:23<23:13:00,  1.36s/it]
  1%|          | 455/61904 [10:25<23:04:55,  1.35s/it]
  1%|          | 456/61904 [10:26<22:57:56,  1.35s/it]
  1%|          | 457/61904 [10:27<22:57:20,  1.34s/it]
  1%|          | 458/61904 [10:29<22:53:03,  1.34s/it]
  1%|          | 459/61904 [10:30<22:30:56,  1.32s/it]
  1%|          | 460/61904 [10:31<22:45:57,  1.33s/it]
                                                      
{'loss': 3.3271, 'learning_rate': 1.9957863347594967e-07, 'epoch': 0.12}

  1%|          | 460/61904 [10:31<22:45:57,  1.33s/it]
  1%|          | 461/61904 [10:33<23:36:07,  1.38s/it]
  1%|          | 462/61904 [10:34<22:50:13,  1.34s/it]
  1%|          | 463/61904 [10:36<23:08:48,  1.36s/it]
  1%|          | 464/61904 [10:37<22:43:32,  1.33s/it]
  1%|          | 465/61904 [10:38<23:42:03,  1.39s/it]
  1%|          | 466/61904 [10:40<23:24:33,  1.37s/it]
  1%|          | 467/61904 [10:41<23:59:35,  1.41s/it]
  1%|          | 468/61904 [10:43<24:06:44,  1.41s/it]
  1%|          | 469/61904 [10:44<23:56:30,  1.40s/it]
  1%|          | 470/61904 [10:45<23:13:52,  1.36s/it]
  1%|          | 471/61904 [10:46<22:33:38,  1.32s/it]
  1%|          | 472/61904 [10:48<23:33:35,  1.38s/it]
  1%|          | 473/61904 [10:49<23:12:23,  1.36s/it]
  1%|          | 474/61904 [10:51<23:43:36,  1.39s/it]
  1%|          | 475/61904 [10:52<23:29:24,  1.38s/it]
  1%|          | 476/61904 [10:53<23:25:58,  1.37s/it]
  1%|          | 477/61904 [10:55<23:14:46,  1.36s/it]
  1%|          | 478/61904 [10:56<22:58:36,  1.35s/it]
  1%|          | 479/61904 [10:58<23:20:46,  1.37s/it]
  1%|          | 480/61904 [10:59<24:03:25,  1.41s/it]
                                                      
{'loss': 3.2978, 'learning_rate': 1.9954622066640736e-07, 'epoch': 0.12}

  1%|          | 480/61904 [10:59<24:03:25,  1.41s/it]
  1%|          | 481/61904 [11:00<23:54:08,  1.40s/it]
  1%|          | 482/61904 [11:02<24:17:08,  1.42s/it]
  1%|          | 483/61904 [11:03<23:38:59,  1.39s/it]
  1%|          | 484/61904 [11:05<23:54:04,  1.40s/it]
  1%|          | 485/61904 [11:06<23:32:13,  1.38s/it]
  1%|          | 486/61904 [11:07<23:28:54,  1.38s/it]
  1%|          | 487/61904 [11:09<23:09:15,  1.36s/it]
  1%|          | 488/61904 [11:10<24:29:09,  1.44s/it]
  1%|          | 489/61904 [11:12<24:38:43,  1.44s/it]
  1%|          | 490/61904 [11:13<23:41:30,  1.39s/it]
  1%|          | 491/61904 [11:14<23:13:58,  1.36s/it]
  1%|          | 492/61904 [11:16<23:05:11,  1.35s/it]
  1%|          | 493/61904 [11:17<23:36:10,  1.38s/it]
  1%|          | 494/61904 [11:18<23:40:54,  1.39s/it]
  1%|          | 495/61904 [11:20<24:40:00,  1.45s/it]
  1%|          | 496/61904 [11:21<24:00:19,  1.41s/it]
  1%|          | 497/61904 [11:23<23:51:15,  1.40s/it]
  1%|          | 498/61904 [11:24<23:13:03,  1.36s/it]
  1%|          | 499/61904 [11:25<23:07:39,  1.36s/it]
  1%|          | 500/61904 [11:27<23:13:42,  1.36s/it]
                                                      
{'loss': 3.3003, 'learning_rate': 1.9951380785686502e-07, 'epoch': 0.13}

  1%|          | 500/61904 [11:27<23:13:42,  1.36s/it]
  1%|          | 501/61904 [11:28<23:15:10,  1.36s/it]
  1%|          | 502/61904 [11:30<23:33:36,  1.38s/it]
  1%|          | 503/61904 [11:31<23:11:38,  1.36s/it]
  1%|          | 504/61904 [11:32<23:13:29,  1.36s/it]
  1%|          | 505/61904 [11:34<23:48:49,  1.40s/it]
  1%|          | 506/61904 [11:35<24:12:24,  1.42s/it]
  1%|          | 507/61904 [11:36<23:26:33,  1.37s/it]
  1%|          | 508/61904 [11:38<23:23:20,  1.37s/it]
  1%|          | 509/61904 [11:39<23:22:36,  1.37s/it]
  1%|          | 510/61904 [11:41<23:40:33,  1.39s/it]
  1%|          | 511/61904 [11:42<23:59:19,  1.41s/it]
  1%|          | 512/61904 [11:43<23:27:47,  1.38s/it]
  1%|          | 513/61904 [11:45<24:33:22,  1.44s/it]
  1%|          | 514/61904 [11:46<24:27:23,  1.43s/it]
  1%|          | 515/61904 [11:48<24:21:17,  1.43s/it]
  1%|          | 516/61904 [11:49<24:07:14,  1.41s/it]
  1%|          | 517/61904 [11:51<24:32:09,  1.44s/it]
  1%|          | 518/61904 [11:52<24:15:23,  1.42s/it]
  1%|          | 519/61904 [11:53<23:28:43,  1.38s/it]
  1%|          | 520/61904 [11:55<23:24:00,  1.37s/it]
                                                      
{'loss': 3.2743, 'learning_rate': 1.9948139504732269e-07, 'epoch': 0.13}

  1%|          | 520/61904 [11:55<23:24:00,  1.37s/it]
  1%|          | 521/61904 [11:56<23:14:41,  1.36s/it]
  1%|          | 522/61904 [11:57<23:04:14,  1.35s/it]
  1%|          | 523/61904 [11:59<24:01:02,  1.41s/it]
  1%|          | 524/61904 [12:00<24:06:02,  1.41s/it]
  1%|          | 525/61904 [12:02<23:46:39,  1.39s/it]
  1%|          | 526/61904 [12:03<23:40:41,  1.39s/it]
  1%|          | 527/61904 [12:04<23:56:13,  1.40s/it]
  1%|          | 528/61904 [12:06<23:57:33,  1.41s/it]
  1%|          | 529/61904 [12:07<23:53:17,  1.40s/it]
  1%|          | 530/61904 [12:09<24:26:05,  1.43s/it]
  1%|          | 531/61904 [12:10<23:31:17,  1.38s/it]
  1%|          | 532/61904 [12:11<23:35:44,  1.38s/it]
  1%|          | 533/61904 [12:13<23:20:04,  1.37s/it]
  1%|          | 534/61904 [12:14<23:51:36,  1.40s/it]
  1%|          | 535/61904 [12:16<23:24:11,  1.37s/it]
  1%|          | 536/61904 [12:17<23:25:09,  1.37s/it]
  1%|          | 537/61904 [12:18<23:19:35,  1.37s/it]
  1%|          | 538/61904 [12:20<23:22:52,  1.37s/it]
  1%|          | 539/61904 [12:21<23:06:48,  1.36s/it]
  1%|          | 540/61904 [12:22<23:02:28,  1.35s/it]
                                                      
{'loss': 3.3829, 'learning_rate': 1.9944898223778038e-07, 'epoch': 0.14}

  1%|          | 540/61904 [12:22<23:02:28,  1.35s/it]
  1%|          | 541/61904 [12:24<22:55:01,  1.34s/it]
  1%|          | 542/61904 [12:25<22:05:02,  1.30s/it]
  1%|          | 543/61904 [12:26<23:11:16,  1.36s/it]
  1%|          | 544/61904 [12:28<22:54:36,  1.34s/it]
  1%|          | 545/61904 [12:29<23:33:52,  1.38s/it]
  1%|          | 546/61904 [12:31<23:51:02,  1.40s/it]
  1%|          | 547/61904 [12:32<23:33:17,  1.38s/it]
  1%|          | 548/61904 [12:33<22:57:21,  1.35s/it]
  1%|          | 549/61904 [12:34<22:50:41,  1.34s/it]
  1%|          | 550/61904 [12:36<23:03:23,  1.35s/it]
  1%|          | 551/61904 [12:37<22:51:17,  1.34s/it]
  1%|          | 552/61904 [12:39<23:05:14,  1.35s/it]
  1%|          | 553/61904 [12:40<23:10:36,  1.36s/it]
  1%|          | 554/61904 [12:41<23:30:14,  1.38s/it]
  1%|          | 555/61904 [12:43<23:47:46,  1.40s/it]
  1%|          | 556/61904 [12:44<23:34:27,  1.38s/it]
  1%|          | 557/61904 [12:45<23:13:15,  1.36s/it]
  1%|          | 558/61904 [12:47<23:08:29,  1.36s/it]
  1%|          | 559/61904 [12:48<22:41:02,  1.33s/it]
  1%|          | 560/61904 [12:49<22:54:53,  1.34s/it]
                                                      
{'loss': 3.2859, 'learning_rate': 1.9941656942823804e-07, 'epoch': 0.14}

  1%|          | 560/61904 [12:49<22:54:53,  1.34s/it]
  1%|          | 561/61904 [12:51<22:34:16,  1.32s/it]
  1%|          | 562/61904 [12:52<22:41:05,  1.33s/it]
  1%|          | 563/61904 [12:53<22:29:02,  1.32s/it]
  1%|          | 564/61904 [12:55<23:03:58,  1.35s/it]
  1%|          | 565/61904 [12:56<23:50:51,  1.40s/it]
  1%|          | 566/61904 [12:58<23:33:34,  1.38s/it]
  1%|          | 567/61904 [12:59<23:17:41,  1.37s/it]
  1%|          | 568/61904 [13:00<23:23:15,  1.37s/it]
  1%|          | 569/61904 [13:02<23:14:27,  1.36s/it]
  1%|          | 570/61904 [13:03<23:24:45,  1.37s/it]
  1%|          | 571/61904 [13:04<22:31:48,  1.32s/it]
  1%|          | 572/61904 [13:06<22:28:55,  1.32s/it]
  1%|          | 573/61904 [13:07<22:05:33,  1.30s/it]
  1%|          | 574/61904 [13:08<22:02:36,  1.29s/it]
  1%|          | 575/61904 [13:10<22:25:26,  1.32s/it]
  1%|          | 576/61904 [13:11<22:23:04,  1.31s/it]
  1%|          | 577/61904 [13:12<22:22:14,  1.31s/it]
  1%|          | 578/61904 [13:13<22:05:12,  1.30s/it]
  1%|          | 579/61904 [13:15<22:33:49,  1.32s/it]
  1%|          | 580/61904 [13:16<22:42:42,  1.33s/it]
                                                      
{'loss': 3.2563, 'learning_rate': 1.993841566186957e-07, 'epoch': 0.15}

  1%|          | 580/61904 [13:16<22:42:42,  1.33s/it]
  1%|          | 581/61904 [13:17<22:15:16,  1.31s/it]
  1%|          | 582/61904 [13:19<22:04:26,  1.30s/it]
  1%|          | 583/61904 [13:20<22:21:50,  1.31s/it]
  1%|          | 584/61904 [13:21<22:13:44,  1.31s/it]
  1%|          | 585/61904 [13:23<22:49:00,  1.34s/it]
  1%|          | 586/61904 [13:24<22:45:25,  1.34s/it]
  1%|          | 587/61904 [13:25<23:03:44,  1.35s/it]
  1%|          | 588/61904 [13:27<23:20:01,  1.37s/it]
  1%|          | 589/61904 [13:28<23:11:08,  1.36s/it]
  1%|          | 590/61904 [13:30<24:19:09,  1.43s/it]
  1%|          | 591/61904 [13:31<23:42:26,  1.39s/it]
  1%|          | 592/61904 [13:32<23:36:06,  1.39s/it]
  1%|          | 593/61904 [13:34<23:14:13,  1.36s/it]
  1%|          | 594/61904 [13:35<23:26:27,  1.38s/it]
  1%|          | 595/61904 [13:37<23:54:38,  1.40s/it]
  1%|          | 596/61904 [13:38<23:06:56,  1.36s/it]
  1%|          | 597/61904 [13:39<23:08:31,  1.36s/it]
  1%|          | 598/61904 [13:41<23:38:20,  1.39s/it]
  1%|          | 599/61904 [13:42<24:16:27,  1.43s/it]
  1%|          | 600/61904 [13:44<25:06:31,  1.47s/it]
                                                      
{'loss': 3.2624, 'learning_rate': 1.993517438091534e-07, 'epoch': 0.16}

  1%|          | 600/61904 [13:44<25:06:31,  1.47s/it]
  1%|          | 601/61904 [13:45<24:46:49,  1.46s/it]
  1%|          | 602/61904 [13:47<24:02:15,  1.41s/it]
  1%|          | 603/61904 [13:48<23:54:04,  1.40s/it]
  1%|          | 604/61904 [13:49<23:32:27,  1.38s/it]
  1%|          | 605/61904 [13:51<23:17:05,  1.37s/it]
  1%|          | 606/61904 [13:52<23:13:51,  1.36s/it]
  1%|          | 607/61904 [13:53<23:07:58,  1.36s/it]
  1%|          | 608/61904 [13:55<23:15:13,  1.37s/it]
  1%|          | 609/61904 [13:56<23:31:24,  1.38s/it]
  1%|          | 610/61904 [13:58<24:06:25,  1.42s/it]
  1%|          | 611/61904 [13:59<23:45:56,  1.40s/it]
  1%|          | 612/61904 [14:00<23:51:59,  1.40s/it]
  1%|          | 613/61904 [14:02<22:52:51,  1.34s/it]
  1%|          | 614/61904 [14:03<23:33:54,  1.38s/it]
  1%|          | 615/61904 [14:04<23:30:14,  1.38s/it]
  1%|          | 616/61904 [14:06<24:26:10,  1.44s/it]
  1%|          | 617/61904 [14:07<23:40:37,  1.39s/it]
  1%|          | 618/61904 [14:09<23:09:47,  1.36s/it]
  1%|          | 619/61904 [14:10<23:20:49,  1.37s/it]
  1%|          | 620/61904 [14:11<22:40:34,  1.33s/it]
                                                      
{'loss': 3.3833, 'learning_rate': 1.9931933099961102e-07, 'epoch': 0.16}

  1%|          | 620/61904 [14:11<22:40:34,  1.33s/it]
  1%|          | 621/61904 [14:13<23:11:47,  1.36s/it]
  1%|          | 622/61904 [14:14<23:05:22,  1.36s/it]
  1%|          | 623/61904 [14:15<22:56:14,  1.35s/it]
  1%|          | 624/61904 [14:17<23:03:33,  1.35s/it]
  1%|          | 625/61904 [14:18<23:32:24,  1.38s/it]
  1%|          | 626/61904 [14:20<23:49:53,  1.40s/it]
  1%|          | 627/61904 [14:21<24:16:10,  1.43s/it]
  1%|          | 628/61904 [14:22<23:47:14,  1.40s/it]
  1%|          | 629/61904 [14:24<24:04:02,  1.41s/it]
  1%|          | 630/61904 [14:25<23:54:07,  1.40s/it]
  1%|          | 631/61904 [14:27<23:32:24,  1.38s/it]
  1%|          | 632/61904 [14:28<23:43:59,  1.39s/it]
  1%|          | 633/61904 [14:29<23:12:07,  1.36s/it]
  1%|          | 634/61904 [14:31<23:31:25,  1.38s/it]
  1%|          | 635/61904 [14:32<23:21:47,  1.37s/it]
  1%|          | 636/61904 [14:34<24:02:51,  1.41s/it]
  1%|          | 637/61904 [14:35<24:24:34,  1.43s/it]
  1%|          | 638/61904 [14:36<24:06:36,  1.42s/it]
  1%|          | 639/61904 [14:38<23:30:12,  1.38s/it]
  1%|          | 640/61904 [14:39<23:39:53,  1.39s/it]
                                                      
{'loss': 3.2947, 'learning_rate': 1.992869181900687e-07, 'epoch': 0.17}

  1%|          | 640/61904 [14:39<23:39:53,  1.39s/it]
  1%|          | 641/61904 [14:40<23:35:34,  1.39s/it]
  1%|          | 642/61904 [14:42<24:26:47,  1.44s/it]
  1%|          | 643/61904 [14:43<24:37:51,  1.45s/it]
  1%|          | 644/61904 [14:45<24:07:10,  1.42s/it]
  1%|          | 645/61904 [14:46<24:27:43,  1.44s/it]
  1%|          | 646/61904 [14:48<25:09:44,  1.48s/it]
  1%|          | 647/61904 [14:49<24:32:25,  1.44s/it]
  1%|          | 648/61904 [14:51<24:28:46,  1.44s/it]
  1%|          | 649/61904 [14:52<24:45:10,  1.45s/it]
  1%|          | 650/61904 [14:53<23:52:43,  1.40s/it]
  1%|          | 651/61904 [14:55<24:05:41,  1.42s/it]
  1%|          | 652/61904 [14:56<24:06:11,  1.42s/it]
  1%|          | 653/61904 [14:58<23:47:38,  1.40s/it]
  1%|          | 654/61904 [14:59<23:57:32,  1.41s/it]
  1%|          | 655/61904 [15:01<24:18:23,  1.43s/it]
  1%|          | 656/61904 [15:02<23:25:35,  1.38s/it]
  1%|          | 657/61904 [15:03<23:19:00,  1.37s/it]
  1%|          | 658/61904 [15:05<23:48:26,  1.40s/it]
  1%|          | 659/61904 [15:06<23:28:07,  1.38s/it]
  1%|          | 660/61904 [15:07<23:06:34,  1.36s/it]
                                                      
{'loss': 3.2239, 'learning_rate': 1.9925450538052637e-07, 'epoch': 0.17}

  1%|          | 660/61904 [15:07<23:06:34,  1.36s/it]
  1%|          | 661/61904 [15:09<23:08:28,  1.36s/it]
  1%|          | 662/61904 [15:10<22:53:01,  1.35s/it]
  1%|          | 663/61904 [15:11<23:26:13,  1.38s/it]
  1%|          | 664/61904 [15:13<23:03:47,  1.36s/it]
  1%|          | 665/61904 [15:14<23:24:48,  1.38s/it]
  1%|          | 666/61904 [15:16<23:41:36,  1.39s/it]
  1%|          | 667/61904 [15:17<23:45:01,  1.40s/it]
  1%|          | 668/61904 [15:18<23:32:52,  1.38s/it]
  1%|          | 669/61904 [15:20<23:38:21,  1.39s/it]
  1%|          | 670/61904 [15:21<23:30:52,  1.38s/it]
  1%|          | 671/61904 [15:23<23:33:24,  1.38s/it]
  1%|          | 672/61904 [15:24<24:22:42,  1.43s/it]
  1%|          | 673/61904 [15:25<24:19:35,  1.43s/it]
  1%|          | 674/61904 [15:27<24:32:21,  1.44s/it]
  1%|          | 675/61904 [15:28<24:38:22,  1.45s/it]
  1%|          | 676/61904 [15:30<24:03:13,  1.41s/it]
  1%|          | 677/61904 [15:31<23:46:13,  1.40s/it]
  1%|          | 678/61904 [15:32<23:32:51,  1.38s/it]
  1%|          | 679/61904 [15:34<23:22:21,  1.37s/it]
  1%|          | 680/61904 [15:35<22:56:44,  1.35s/it]
                                                      
{'loss': 3.2292, 'learning_rate': 1.9922209257098403e-07, 'epoch': 0.18}

  1%|          | 680/61904 [15:35<22:56:44,  1.35s/it]
  1%|          | 681/61904 [15:36<23:00:22,  1.35s/it]
  1%|          | 682/61904 [15:38<23:08:58,  1.36s/it]
  1%|          | 683/61904 [15:39<23:28:18,  1.38s/it]
  1%|          | 684/61904 [15:41<23:16:00,  1.37s/it]
  1%|          | 685/61904 [15:42<23:40:05,  1.39s/it]
  1%|          | 686/61904 [15:43<23:22:35,  1.37s/it]
  1%|          | 687/61904 [15:45<23:40:48,  1.39s/it]
  1%|          | 688/61904 [15:46<23:34:55,  1.39s/it]
  1%|          | 689/61904 [15:48<23:16:29,  1.37s/it]
  1%|          | 690/61904 [15:49<23:19:05,  1.37s/it]
  1%|          | 691/61904 [15:50<23:32:06,  1.38s/it]
  1%|          | 692/61904 [15:52<23:52:08,  1.40s/it]
  1%|          | 693/61904 [15:53<23:25:37,  1.38s/it]
  1%|          | 694/61904 [15:54<23:05:20,  1.36s/it]
  1%|          | 695/61904 [15:56<22:53:30,  1.35s/it]
  1%|          | 696/61904 [15:57<23:01:29,  1.35s/it]
  1%|          | 697/61904 [15:58<22:32:50,  1.33s/it]
  1%|          | 698/61904 [16:00<22:35:31,  1.33s/it]
  1%|          | 699/61904 [16:01<22:27:18,  1.32s/it]
  1%|          | 700/61904 [16:02<22:34:59,  1.33s/it]
                                                      
{'loss': 3.2841, 'learning_rate': 1.9918967976144172e-07, 'epoch': 0.18}

  1%|          | 700/61904 [16:02<22:34:59,  1.33s/it]
  1%|          | 701/61904 [16:04<22:56:26,  1.35s/it]
  1%|          | 702/61904 [16:05<23:26:06,  1.38s/it]
  1%|          | 703/61904 [16:07<24:20:55,  1.43s/it]
  1%|          | 704/61904 [16:08<24:03:13,  1.41s/it]
  1%|          | 705/61904 [16:10<24:02:03,  1.41s/it]
  1%|          | 706/61904 [16:11<24:17:03,  1.43s/it]
  1%|          | 707/61904 [16:12<23:47:40,  1.40s/it]
  1%|          | 708/61904 [16:14<23:17:06,  1.37s/it]
  1%|          | 709/61904 [16:15<23:12:53,  1.37s/it]
  1%|          | 710/61904 [16:16<23:00:26,  1.35s/it]
  1%|          | 711/61904 [16:18<22:42:09,  1.34s/it]
  1%|          | 712/61904 [16:19<23:03:51,  1.36s/it]
  1%|          | 713/61904 [16:20<22:50:47,  1.34s/it]
  1%|          | 714/61904 [16:22<22:58:51,  1.35s/it]
  1%|          | 715/61904 [16:23<23:44:46,  1.40s/it]
  1%|          | 716/61904 [16:25<23:53:38,  1.41s/it]
  1%|          | 717/61904 [16:26<23:25:49,  1.38s/it]
  1%|          | 718/61904 [16:27<23:38:17,  1.39s/it]
  1%|          | 719/61904 [16:29<24:16:45,  1.43s/it]
  1%|          | 720/61904 [16:30<23:46:15,  1.40s/it]
                                                      
{'loss': 3.2612, 'learning_rate': 1.9915726695189938e-07, 'epoch': 0.19}

  1%|          | 720/61904 [16:30<23:46:15,  1.40s/it]
  1%|          | 721/61904 [16:32<23:35:17,  1.39s/it]
  1%|          | 722/61904 [16:33<23:30:38,  1.38s/it]
  1%|          | 723/61904 [16:34<23:44:46,  1.40s/it]
  1%|          | 724/61904 [16:36<22:55:38,  1.35s/it]
  1%|          | 725/61904 [16:37<23:25:55,  1.38s/it]
  1%|          | 726/61904 [16:38<22:50:32,  1.34s/it]
  1%|          | 727/61904 [16:40<23:35:03,  1.39s/it]
  1%|          | 728/61904 [16:41<23:52:52,  1.41s/it]
  1%|          | 729/61904 [16:43<23:40:47,  1.39s/it]
  1%|          | 730/61904 [16:44<24:30:15,  1.44s/it]
  1%|          | 731/61904 [16:46<24:14:39,  1.43s/it]
  1%|          | 732/61904 [16:47<24:08:25,  1.42s/it]
  1%|          | 733/61904 [16:48<23:32:28,  1.39s/it]
  1%|          | 734/61904 [16:50<23:00:57,  1.35s/it]
  1%|          | 735/61904 [16:51<22:39:22,  1.33s/it]
  1%|          | 736/61904 [16:52<22:16:37,  1.31s/it]
  1%|          | 737/61904 [16:54<23:12:56,  1.37s/it]
  1%|          | 738/61904 [16:55<23:27:41,  1.38s/it]
  1%|          | 739/61904 [16:56<22:55:39,  1.35s/it]
  1%|          | 740/61904 [16:58<22:40:53,  1.33s/it]
                                                      
{'loss': 3.2516, 'learning_rate': 1.9912485414235705e-07, 'epoch': 0.19}

  1%|          | 740/61904 [16:58<22:40:53,  1.33s/it]
  1%|          | 741/61904 [16:59<23:03:09,  1.36s/it]
  1%|          | 742/61904 [17:00<23:07:38,  1.36s/it]
  1%|          | 743/61904 [17:02<22:56:22,  1.35s/it]
  1%|          | 744/61904 [17:03<23:11:26,  1.37s/it]
  1%|          | 745/61904 [17:05<24:47:36,  1.46s/it]
  1%|          | 746/61904 [17:06<24:26:02,  1.44s/it]
  1%|          | 747/61904 [17:08<25:05:42,  1.48s/it]
  1%|          | 748/61904 [17:09<24:38:48,  1.45s/it]
  1%|          | 749/61904 [17:11<24:47:20,  1.46s/it]
  1%|          | 750/61904 [17:12<24:21:30,  1.43s/it]
  1%|          | 751/61904 [17:13<23:33:46,  1.39s/it]
  1%|          | 752/61904 [17:15<22:54:27,  1.35s/it]
  1%|          | 753/61904 [17:16<22:49:08,  1.34s/it]
  1%|          | 754/61904 [17:17<23:11:01,  1.36s/it]
  1%|          | 755/61904 [17:19<23:41:33,  1.39s/it]
  1%|          | 756/61904 [17:20<23:36:02,  1.39s/it]
  1%|          | 757/61904 [17:22<25:41:10,  1.51s/it]
  1%|          | 758/61904 [17:23<24:37:12,  1.45s/it]
  1%|          | 759/61904 [17:25<24:19:21,  1.43s/it]
  1%|          | 760/61904 [17:26<23:44:41,  1.40s/it]
                                                      
{'loss': 3.2687, 'learning_rate': 1.9909244133281474e-07, 'epoch': 0.2}

  1%|          | 760/61904 [17:26<23:44:41,  1.40s/it]
  1%|          | 761/61904 [17:27<23:52:49,  1.41s/it]
  1%|          | 762/61904 [17:29<23:30:44,  1.38s/it]
  1%|          | 763/61904 [17:30<23:48:57,  1.40s/it]
  1%|          | 764/61904 [17:31<23:32:39,  1.39s/it]
  1%|          | 765/61904 [17:33<23:48:00,  1.40s/it]
  1%|          | 766/61904 [17:34<23:38:09,  1.39s/it]
  1%|          | 767/61904 [17:36<23:25:34,  1.38s/it]
  1%|          | 768/61904 [17:37<23:28:03,  1.38s/it]
  1%|          | 769/61904 [17:38<23:16:11,  1.37s/it]
  1%|          | 770/61904 [17:40<23:50:00,  1.40s/it]
  1%|          | 771/61904 [17:41<24:01:40,  1.41s/it]
  1%|          | 772/61904 [17:42<23:01:04,  1.36s/it]
  1%|          | 773/61904 [17:44<22:32:16,  1.33s/it]
  1%|▏         | 774/61904 [17:45<22:02:41,  1.30s/it]
  1%|▏         | 775/61904 [17:46<22:31:02,  1.33s/it]
  1%|▏         | 776/61904 [17:48<22:08:11,  1.30s/it]
  1%|▏         | 777/61904 [17:49<22:09:49,  1.31s/it]
  1%|▏         | 778/61904 [17:50<23:10:10,  1.36s/it]
  1%|▏         | 779/61904 [17:52<22:28:14,  1.32s/it]
  1%|▏         | 780/61904 [17:53<22:57:53,  1.35s/it]
                                                      
{'loss': 3.196, 'learning_rate': 1.9906002852327237e-07, 'epoch': 0.2}

  1%|▏         | 780/61904 [17:53<22:57:53,  1.35s/it]
  1%|▏         | 781/61904 [17:54<22:55:01,  1.35s/it]
  1%|▏         | 782/61904 [17:56<24:01:38,  1.42s/it]
  1%|▏         | 783/61904 [17:57<23:50:34,  1.40s/it]
  1%|▏         | 784/61904 [17:59<23:32:33,  1.39s/it]
  1%|▏         | 785/61904 [18:00<23:38:53,  1.39s/it]
  1%|▏         | 786/61904 [18:02<24:08:18,  1.42s/it]
  1%|▏         | 787/61904 [18:03<23:19:26,  1.37s/it]
  1%|▏         | 788/61904 [18:04<23:21:32,  1.38s/it]
  1%|▏         | 789/61904 [18:06<22:55:03,  1.35s/it]
  1%|▏         | 790/61904 [18:07<23:14:42,  1.37s/it]
  1%|▏         | 791/61904 [18:08<23:15:47,  1.37s/it]
  1%|▏         | 792/61904 [18:10<22:55:22,  1.35s/it]
  1%|▏         | 793/61904 [18:11<22:36:23,  1.33s/it]
  1%|▏         | 794/61904 [18:12<22:29:12,  1.32s/it]
  1%|▏         | 795/61904 [18:14<22:48:22,  1.34s/it]
  1%|▏         | 796/61904 [18:15<22:13:40,  1.31s/it]
  1%|▏         | 797/61904 [18:16<22:23:04,  1.32s/it]
  1%|▏         | 798/61904 [18:17<22:18:21,  1.31s/it]
  1%|▏         | 799/61904 [18:19<22:09:56,  1.31s/it]
  1%|▏         | 800/61904 [18:20<21:53:43,  1.29s/it]
                                                      
{'loss': 3.2396, 'learning_rate': 1.9902761571373006e-07, 'epoch': 0.21}

  1%|▏         | 800/61904 [18:20<21:53:43,  1.29s/it]
  1%|▏         | 801/61904 [18:21<22:19:45,  1.32s/it]
  1%|▏         | 802/61904 [18:23<23:28:20,  1.38s/it]
  1%|▏         | 803/61904 [18:24<23:02:36,  1.36s/it]
  1%|▏         | 804/61904 [18:26<23:17:56,  1.37s/it]
  1%|▏         | 805/61904 [18:27<23:41:13,  1.40s/it]
  1%|▏         | 806/61904 [18:28<22:44:47,  1.34s/it]
  1%|▏         | 807/61904 [18:30<23:36:38,  1.39s/it]
  1%|▏         | 808/61904 [18:31<24:09:15,  1.42s/it]
  1%|▏         | 809/61904 [18:33<24:04:43,  1.42s/it]
  1%|▏         | 810/61904 [18:34<23:32:02,  1.39s/it]
  1%|▏         | 811/61904 [18:35<23:31:05,  1.39s/it]
  1%|▏         | 812/61904 [18:37<23:27:58,  1.38s/it]
  1%|▏         | 813/61904 [18:38<23:19:28,  1.37s/it]
  1%|▏         | 814/61904 [18:40<23:15:09,  1.37s/it]
  1%|▏         | 815/61904 [18:41<23:33:45,  1.39s/it]
  1%|▏         | 816/61904 [18:42<23:26:45,  1.38s/it]
  1%|▏         | 817/61904 [18:44<23:05:55,  1.36s/it]
  1%|▏         | 818/61904 [18:45<22:49:40,  1.35s/it]
  1%|▏         | 819/61904 [18:46<22:44:56,  1.34s/it]
  1%|▏         | 820/61904 [18:48<23:12:58,  1.37s/it]
                                                      
{'loss': 3.2147, 'learning_rate': 1.9899520290418775e-07, 'epoch': 0.21}

  1%|▏         | 820/61904 [18:48<23:12:58,  1.37s/it]
  1%|▏         | 821/61904 [18:49<23:02:55,  1.36s/it]
  1%|▏         | 822/61904 [18:50<22:54:11,  1.35s/it]
  1%|▏         | 823/61904 [18:52<23:03:39,  1.36s/it]
  1%|▏         | 824/61904 [18:53<22:45:17,  1.34s/it]
  1%|▏         | 825/61904 [18:54<23:11:44,  1.37s/it]
  1%|▏         | 826/61904 [18:56<23:17:32,  1.37s/it]
  1%|▏         | 827/61904 [18:57<23:49:04,  1.40s/it]
  1%|▏         | 828/61904 [18:59<23:22:25,  1.38s/it]
  1%|▏         | 829/61904 [19:00<23:26:56,  1.38s/it]
  1%|▏         | 830/61904 [19:01<22:50:52,  1.35s/it]
  1%|▏         | 831/61904 [19:03<22:56:03,  1.35s/it]
  1%|▏         | 832/61904 [19:04<23:28:07,  1.38s/it]
  1%|▏         | 833/61904 [19:06<24:46:02,  1.46s/it]
  1%|▏         | 834/61904 [19:07<24:21:13,  1.44s/it]
  1%|▏         | 835/61904 [19:09<25:01:53,  1.48s/it]
  1%|▏         | 836/61904 [19:10<24:42:20,  1.46s/it]
  1%|▏         | 837/61904 [19:12<24:56:06,  1.47s/it]
  1%|▏         | 838/61904 [19:13<23:44:43,  1.40s/it]
  1%|▏         | 839/61904 [19:14<23:26:13,  1.38s/it]
  1%|▏         | 840/61904 [19:16<24:33:44,  1.45s/it]
                                                      
{'loss': 3.1813, 'learning_rate': 1.9896279009464538e-07, 'epoch': 0.22}

  1%|▏         | 840/61904 [19:16<24:33:44,  1.45s/it]
  1%|▏         | 841/61904 [19:17<24:02:39,  1.42s/it]
  1%|▏         | 842/61904 [19:19<23:59:48,  1.41s/it]
  1%|▏         | 843/61904 [19:20<23:21:46,  1.38s/it]
  1%|▏         | 844/61904 [19:21<23:35:39,  1.39s/it]
  1%|▏         | 845/61904 [19:23<23:36:29,  1.39s/it]
  1%|▏         | 846/61904 [19:24<23:05:21,  1.36s/it]
  1%|▏         | 847/61904 [19:25<22:28:15,  1.32s/it]
  1%|▏         | 848/61904 [19:27<22:57:27,  1.35s/it]
  1%|▏         | 849/61904 [19:28<22:29:25,  1.33s/it]
  1%|▏         | 850/61904 [19:29<22:03:42,  1.30s/it]
  1%|▏         | 851/61904 [19:31<23:06:21,  1.36s/it]
  1%|▏         | 852/61904 [19:32<22:55:47,  1.35s/it]
  1%|▏         | 853/61904 [19:33<22:12:37,  1.31s/it]
  1%|▏         | 854/61904 [19:35<22:37:54,  1.33s/it]
  1%|▏         | 855/61904 [19:36<22:33:15,  1.33s/it]
  1%|▏         | 856/61904 [19:37<23:01:25,  1.36s/it]
  1%|▏         | 857/61904 [19:39<22:56:14,  1.35s/it]
  1%|▏         | 858/61904 [19:40<22:45:39,  1.34s/it]
  1%|▏         | 859/61904 [19:41<22:47:39,  1.34s/it]
  1%|▏         | 860/61904 [19:43<22:59:56,  1.36s/it]
                                                      
{'loss': 3.2279, 'learning_rate': 1.9893037728510307e-07, 'epoch': 0.22}

  1%|▏         | 860/61904 [19:43<22:59:56,  1.36s/it]
  1%|▏         | 861/61904 [19:44<23:20:09,  1.38s/it]
  1%|▏         | 862/61904 [19:45<23:12:15,  1.37s/it]
  1%|▏         | 863/61904 [19:47<23:12:12,  1.37s/it]
  1%|▏         | 864/61904 [19:48<22:24:00,  1.32s/it]
  1%|▏         | 865/61904 [19:49<22:59:24,  1.36s/it]
  1%|▏         | 866/61904 [19:51<23:29:38,  1.39s/it]
  1%|▏         | 867/61904 [19:52<23:27:09,  1.38s/it]
  1%|▏         | 868/61904 [19:54<22:54:31,  1.35s/it]
  1%|▏         | 869/61904 [19:55<23:19:50,  1.38s/it]
  1%|▏         | 870/61904 [19:56<23:02:11,  1.36s/it]
  1%|▏         | 871/61904 [19:58<23:05:56,  1.36s/it]
  1%|▏         | 872/61904 [19:59<23:37:31,  1.39s/it]
  1%|▏         | 873/61904 [20:00<23:09:21,  1.37s/it]
  1%|▏         | 874/61904 [20:02<22:52:06,  1.35s/it]
  1%|▏         | 875/61904 [20:03<24:18:33,  1.43s/it]
  1%|▏         | 876/61904 [20:05<24:08:18,  1.42s/it]
  1%|▏         | 877/61904 [20:06<23:54:57,  1.41s/it]
  1%|▏         | 878/61904 [20:07<23:09:16,  1.37s/it]
  1%|▏         | 879/61904 [20:09<23:07:59,  1.36s/it]
  1%|▏         | 880/61904 [20:10<23:38:59,  1.40s/it]
                                                      
{'loss': 3.2183, 'learning_rate': 1.9889796447556073e-07, 'epoch': 0.23}

  1%|▏         | 880/61904 [20:10<23:38:59,  1.40s/it]
  1%|▏         | 881/61904 [20:12<23:22:22,  1.38s/it]
  1%|▏         | 882/61904 [20:13<24:02:30,  1.42s/it]
  1%|▏         | 883/61904 [20:15<24:19:06,  1.43s/it]
  1%|▏         | 884/61904 [20:16<23:32:26,  1.39s/it]
  1%|▏         | 885/61904 [20:17<23:27:56,  1.38s/it]
  1%|▏         | 886/61904 [20:19<23:04:32,  1.36s/it]
  1%|▏         | 887/61904 [20:20<23:15:32,  1.37s/it]
  1%|▏         | 888/61904 [20:21<23:04:54,  1.36s/it]
  1%|▏         | 889/61904 [20:23<22:51:03,  1.35s/it]
  1%|▏         | 890/61904 [20:24<22:44:09,  1.34s/it]
  1%|▏         | 891/61904 [20:25<22:59:12,  1.36s/it]
  1%|▏         | 892/61904 [20:27<23:16:12,  1.37s/it]
  1%|▏         | 893/61904 [20:28<23:29:04,  1.39s/it]
  1%|▏         | 894/61904 [20:30<23:39:10,  1.40s/it]
  1%|▏         | 895/61904 [20:31<24:13:35,  1.43s/it]
  1%|▏         | 896/61904 [20:32<23:08:56,  1.37s/it]
  1%|▏         | 897/61904 [20:34<23:11:06,  1.37s/it]
  1%|▏         | 898/61904 [20:35<22:46:01,  1.34s/it]
  1%|▏         | 899/61904 [20:36<23:02:39,  1.36s/it]
  1%|▏         | 900/61904 [20:38<23:11:30,  1.37s/it]
                                                      
{'loss': 3.2086, 'learning_rate': 1.988655516660184e-07, 'epoch': 0.23}

  1%|▏         | 900/61904 [20:38<23:11:30,  1.37s/it]
  1%|▏         | 901/61904 [20:39<23:18:33,  1.38s/it]
  1%|▏         | 902/61904 [20:41<23:49:20,  1.41s/it]
  1%|▏         | 903/61904 [20:42<23:33:40,  1.39s/it]
  1%|▏         | 904/61904 [20:43<23:16:27,  1.37s/it]
  1%|▏         | 905/61904 [20:45<24:23:49,  1.44s/it]
  1%|▏         | 906/61904 [20:46<24:49:42,  1.47s/it]
  1%|▏         | 907/61904 [20:48<24:48:23,  1.46s/it]
  1%|▏         | 908/61904 [20:49<23:32:04,  1.39s/it]
  1%|▏         | 909/61904 [20:51<24:08:09,  1.42s/it]
  1%|▏         | 910/61904 [20:52<24:00:58,  1.42s/it]
  1%|▏         | 911/61904 [20:53<24:11:13,  1.43s/it]
  1%|▏         | 912/61904 [20:55<23:36:59,  1.39s/it]
  1%|▏         | 913/61904 [20:56<23:25:47,  1.38s/it]
  1%|▏         | 914/61904 [20:58<23:50:24,  1.41s/it]
  1%|▏         | 915/61904 [20:59<24:11:58,  1.43s/it]
  1%|▏         | 916/61904 [21:00<24:00:49,  1.42s/it]
  1%|▏         | 917/61904 [21:02<23:24:15,  1.38s/it]
  1%|▏         | 918/61904 [21:03<23:26:04,  1.38s/it]
  1%|▏         | 919/61904 [21:05<24:17:18,  1.43s/it]
  1%|▏         | 920/61904 [21:06<23:54:33,  1.41s/it]
                                                      
{'loss': 3.1735, 'learning_rate': 1.9883313885647608e-07, 'epoch': 0.24}

  1%|▏         | 920/61904 [21:06<23:54:33,  1.41s/it]
  1%|▏         | 921/61904 [21:07<23:03:26,  1.36s/it]
  1%|▏         | 922/61904 [21:09<23:11:32,  1.37s/it]
  1%|▏         | 923/61904 [21:10<22:33:21,  1.33s/it]
  1%|▏         | 924/61904 [21:11<22:46:26,  1.34s/it]
  1%|▏         | 925/61904 [21:13<22:08:49,  1.31s/it]
  1%|▏         | 926/61904 [21:14<22:50:15,  1.35s/it]
  1%|▏         | 927/61904 [21:15<22:44:35,  1.34s/it]
  1%|▏         | 928/61904 [21:17<22:18:33,  1.32s/it]
  2%|▏         | 929/61904 [21:18<22:20:06,  1.32s/it]
  2%|▏         | 930/61904 [21:19<22:17:15,  1.32s/it]
  2%|▏         | 931/61904 [21:21<22:19:53,  1.32s/it]
  2%|▏         | 932/61904 [21:22<22:13:18,  1.31s/it]
  2%|▏         | 933/61904 [21:23<22:45:51,  1.34s/it]
  2%|▏         | 934/61904 [21:24<21:54:55,  1.29s/it]
  2%|▏         | 935/61904 [21:26<22:10:16,  1.31s/it]
  2%|▏         | 936/61904 [21:27<22:30:02,  1.33s/it]
  2%|▏         | 937/61904 [21:29<22:51:05,  1.35s/it]
  2%|▏         | 938/61904 [21:30<22:58:36,  1.36s/it]
  2%|▏         | 939/61904 [21:31<22:42:13,  1.34s/it]
  2%|▏         | 940/61904 [21:32<22:11:17,  1.31s/it]
                                                      
{'loss': 3.2435, 'learning_rate': 1.9880072604693374e-07, 'epoch': 0.24}

  2%|▏         | 940/61904 [21:32<22:11:17,  1.31s/it]
  2%|▏         | 941/61904 [21:34<21:55:21,  1.29s/it]
  2%|▏         | 942/61904 [21:35<22:06:32,  1.31s/it]
  2%|▏         | 943/61904 [21:36<21:52:33,  1.29s/it]
  2%|▏         | 944/61904 [21:38<21:57:30,  1.30s/it]
  2%|▏         | 945/61904 [21:39<22:25:34,  1.32s/it]
  2%|▏         | 946/61904 [21:40<22:50:58,  1.35s/it]
  2%|▏         | 947/61904 [21:42<22:36:26,  1.34s/it]
  2%|▏         | 948/61904 [21:43<22:37:49,  1.34s/it]
  2%|▏         | 949/61904 [21:44<22:31:18,  1.33s/it]
  2%|▏         | 950/61904 [21:46<24:22:37,  1.44s/it]
  2%|▏         | 951/61904 [21:48<24:40:52,  1.46s/it]
  2%|▏         | 952/61904 [21:49<23:56:10,  1.41s/it]
  2%|▏         | 953/61904 [21:50<24:31:43,  1.45s/it]
  2%|▏         | 954/61904 [21:52<24:45:06,  1.46s/it]
  2%|▏         | 955/61904 [21:53<23:55:36,  1.41s/it]
  2%|▏         | 956/61904 [21:54<23:12:01,  1.37s/it]
  2%|▏         | 957/61904 [21:56<23:32:53,  1.39s/it]
  2%|▏         | 958/61904 [21:57<23:44:18,  1.40s/it]
  2%|▏         | 959/61904 [21:59<24:21:18,  1.44s/it]
  2%|▏         | 960/61904 [22:00<24:15:55,  1.43s/it]
                                                      
{'loss': 3.1959, 'learning_rate': 1.987683132373914e-07, 'epoch': 0.25}

  2%|▏         | 960/61904 [22:00<24:15:55,  1.43s/it]
  2%|▏         | 961/61904 [22:02<23:51:51,  1.41s/it]
  2%|▏         | 962/61904 [22:03<23:57:59,  1.42s/it]
  2%|▏         | 963/61904 [22:04<23:41:42,  1.40s/it]
  2%|▏         | 964/61904 [22:06<23:12:55,  1.37s/it]
  2%|▏         | 965/61904 [22:07<22:32:06,  1.33s/it]
  2%|▏         | 966/61904 [22:08<22:27:21,  1.33s/it]
  2%|▏         | 967/61904 [22:10<22:09:31,  1.31s/it]
  2%|▏         | 968/61904 [22:11<22:06:51,  1.31s/it]
  2%|▏         | 969/61904 [22:12<22:39:48,  1.34s/it]
  2%|▏         | 970/61904 [22:14<22:51:03,  1.35s/it]
  2%|▏         | 971/61904 [22:15<22:47:46,  1.35s/it]
  2%|▏         | 972/61904 [22:16<22:53:59,  1.35s/it]
  2%|▏         | 973/61904 [22:18<22:50:17,  1.35s/it]
  2%|▏         | 974/61904 [22:19<22:57:32,  1.36s/it]
  2%|▏         | 975/61904 [22:20<22:57:43,  1.36s/it]
  2%|▏         | 976/61904 [22:22<22:55:35,  1.35s/it]
  2%|▏         | 977/61904 [22:23<22:47:01,  1.35s/it]
  2%|▏         | 978/61904 [22:25<23:04:09,  1.36s/it]
  2%|▏         | 979/61904 [22:26<22:39:14,  1.34s/it]
  2%|▏         | 980/61904 [22:27<22:53:27,  1.35s/it]
                                                      
{'loss': 3.1981, 'learning_rate': 1.987359004278491e-07, 'epoch': 0.25}

  2%|▏         | 980/61904 [22:27<22:53:27,  1.35s/it]
  2%|▏         | 981/61904 [22:28<22:35:43,  1.34s/it]
  2%|▏         | 982/61904 [22:30<22:10:50,  1.31s/it]
  2%|▏         | 983/61904 [22:31<22:18:19,  1.32s/it]
  2%|▏         | 984/61904 [22:32<22:09:19,  1.31s/it]
  2%|▏         | 985/61904 [22:34<22:15:04,  1.31s/it]
  2%|▏         | 986/61904 [22:35<23:19:43,  1.38s/it]
  2%|▏         | 987/61904 [22:36<22:40:04,  1.34s/it]
  2%|▏         | 988/61904 [22:38<22:30:17,  1.33s/it]
  2%|▏         | 989/61904 [22:39<21:59:30,  1.30s/it]
  2%|▏         | 990/61904 [22:40<22:54:40,  1.35s/it]
  2%|▏         | 991/61904 [22:42<22:04:00,  1.30s/it]
  2%|▏         | 992/61904 [22:43<21:42:02,  1.28s/it]
  2%|▏         | 993/61904 [22:44<21:32:23,  1.27s/it]
  2%|▏         | 994/61904 [22:45<21:51:15,  1.29s/it]
  2%|▏         | 995/61904 [22:47<22:03:30,  1.30s/it]
  2%|▏         | 996/61904 [22:48<22:51:44,  1.35s/it]
  2%|▏         | 997/61904 [22:50<22:54:42,  1.35s/it]
  2%|▏         | 998/61904 [22:51<23:19:11,  1.38s/it]
  2%|▏         | 999/61904 [22:53<23:47:34,  1.41s/it]
  2%|▏         | 1000/61904 [22:54<23:35:25,  1.39s/it]
                                                       
{'loss': 3.166, 'learning_rate': 1.9870348761830673e-07, 'epoch': 0.26}

  2%|▏         | 1000/61904 [22:54<23:35:25,  1.39s/it]
  2%|▏         | 1001/61904 [22:55<23:14:11,  1.37s/it]
  2%|▏         | 1002/61904 [22:57<23:32:29,  1.39s/it]
  2%|▏         | 1003/61904 [22:58<25:26:15,  1.50s/it]
  2%|▏         | 1004/61904 [23:00<24:49:29,  1.47s/it]
  2%|▏         | 1005/61904 [23:01<24:20:32,  1.44s/it]
  2%|▏         | 1006/61904 [23:03<24:02:55,  1.42s/it]
  2%|▏         | 1007/61904 [23:04<23:23:23,  1.38s/it]
  2%|▏         | 1008/61904 [23:05<23:30:57,  1.39s/it]
  2%|▏         | 1009/61904 [23:07<23:50:06,  1.41s/it]
  2%|▏         | 1010/61904 [23:08<23:37:39,  1.40s/it]
  2%|▏         | 1011/61904 [23:09<22:58:32,  1.36s/it]
  2%|▏         | 1012/61904 [23:11<22:29:00,  1.33s/it]
  2%|▏         | 1013/61904 [23:12<22:20:29,  1.32s/it]
  2%|▏         | 1014/61904 [23:13<22:59:09,  1.36s/it]
  2%|▏         | 1015/61904 [23:15<22:41:17,  1.34s/it]
  2%|▏         | 1016/61904 [23:16<22:23:02,  1.32s/it]
  2%|▏         | 1017/61904 [23:17<22:35:18,  1.34s/it]
  2%|▏         | 1018/61904 [23:19<22:18:30,  1.32s/it]
  2%|▏         | 1019/61904 [23:20<21:49:15,  1.29s/it]
  2%|▏         | 1020/61904 [23:21<22:47:42,  1.35s/it]
                                                       
{'loss': 3.2563, 'learning_rate': 1.9867107480876442e-07, 'epoch': 0.26}

  2%|▏         | 1020/61904 [23:21<22:47:42,  1.35s/it]
  2%|▏         | 1021/61904 [23:23<23:06:06,  1.37s/it]
  2%|▏         | 1022/61904 [23:24<23:25:13,  1.38s/it]
  2%|▏         | 1023/61904 [23:25<23:06:15,  1.37s/it]
  2%|▏         | 1024/61904 [23:27<23:16:32,  1.38s/it]
  2%|▏         | 1025/61904 [23:28<23:06:42,  1.37s/it]
  2%|▏         | 1026/61904 [23:30<23:10:26,  1.37s/it]
  2%|▏         | 1027/61904 [23:31<22:37:13,  1.34s/it]
  2%|▏         | 1028/61904 [23:32<23:23:33,  1.38s/it]
  2%|▏         | 1029/61904 [23:34<23:14:05,  1.37s/it]
  2%|▏         | 1030/61904 [23:35<22:34:13,  1.33s/it]
  2%|▏         | 1031/61904 [23:36<22:24:16,  1.32s/it]
  2%|▏         | 1032/61904 [23:38<22:26:35,  1.33s/it]
  2%|▏         | 1033/61904 [23:39<22:34:59,  1.34s/it]
  2%|▏         | 1034/61904 [23:40<22:55:22,  1.36s/it]
  2%|▏         | 1035/61904 [23:42<22:52:49,  1.35s/it]
  2%|▏         | 1036/61904 [23:43<22:42:02,  1.34s/it]
  2%|▏         | 1037/61904 [23:44<22:44:14,  1.34s/it]
  2%|▏         | 1038/61904 [23:46<23:32:23,  1.39s/it]
  2%|▏         | 1039/61904 [23:47<23:39:44,  1.40s/it]
  2%|▏         | 1040/61904 [23:49<23:11:36,  1.37s/it]
                                                       
{'loss': 3.1861, 'learning_rate': 1.9863866199922208e-07, 'epoch': 0.27}

  2%|▏         | 1040/61904 [23:49<23:11:36,  1.37s/it]
  2%|▏         | 1041/61904 [23:50<22:46:43,  1.35s/it]
  2%|▏         | 1042/61904 [23:51<22:43:56,  1.34s/it]
  2%|▏         | 1043/61904 [23:53<22:53:57,  1.35s/it]
  2%|▏         | 1044/61904 [23:54<23:12:25,  1.37s/it]
  2%|▏         | 1045/61904 [23:55<23:30:42,  1.39s/it]
  2%|▏         | 1046/61904 [23:57<23:58:04,  1.42s/it]
  2%|▏         | 1047/61904 [23:58<23:37:52,  1.40s/it]
  2%|▏         | 1048/61904 [24:00<23:16:44,  1.38s/it]
  2%|▏         | 1049/61904 [24:01<22:48:59,  1.35s/it]
  2%|▏         | 1050/61904 [24:02<21:56:31,  1.30s/it]
  2%|▏         | 1051/61904 [24:03<22:18:57,  1.32s/it]
  2%|▏         | 1052/61904 [24:05<22:55:19,  1.36s/it]
  2%|▏         | 1053/61904 [24:06<22:51:38,  1.35s/it]
  2%|▏         | 1054/61904 [24:07<22:35:14,  1.34s/it]
  2%|▏         | 1055/61904 [24:09<22:52:56,  1.35s/it]
  2%|▏         | 1056/61904 [24:10<22:40:14,  1.34s/it]
  2%|▏         | 1057/61904 [24:12<22:41:45,  1.34s/it]
  2%|▏         | 1058/61904 [24:13<23:00:38,  1.36s/it]
  2%|▏         | 1059/61904 [24:14<23:16:15,  1.38s/it]
  2%|▏         | 1060/61904 [24:16<23:41:26,  1.40s/it]
                                                       
{'loss': 3.1872, 'learning_rate': 1.9860624918967974e-07, 'epoch': 0.27}

  2%|▏         | 1060/61904 [24:16<23:41:26,  1.40s/it]
  2%|▏         | 1061/61904 [24:17<23:37:35,  1.40s/it]
  2%|▏         | 1062/61904 [24:19<23:09:09,  1.37s/it]
  2%|▏         | 1063/61904 [24:20<23:37:26,  1.40s/it]
  2%|▏         | 1064/61904 [24:21<22:52:03,  1.35s/it]
  2%|▏         | 1065/61904 [24:23<22:40:09,  1.34s/it]
  2%|▏         | 1066/61904 [24:24<23:03:25,  1.36s/it]
  2%|▏         | 1067/61904 [24:25<22:50:49,  1.35s/it]
  2%|▏         | 1068/61904 [24:27<23:34:40,  1.40s/it]
  2%|▏         | 1069/61904 [24:28<23:35:59,  1.40s/it]
  2%|▏         | 1070/61904 [24:30<23:31:27,  1.39s/it]
  2%|▏         | 1071/61904 [24:31<24:30:43,  1.45s/it]
  2%|▏         | 1072/61904 [24:32<23:22:53,  1.38s/it]
  2%|▏         | 1073/61904 [24:34<23:28:51,  1.39s/it]
  2%|▏         | 1074/61904 [24:35<24:09:57,  1.43s/it]
  2%|▏         | 1075/61904 [24:37<23:28:56,  1.39s/it]
  2%|▏         | 1076/61904 [24:38<23:15:22,  1.38s/it]
  2%|▏         | 1077/61904 [24:39<23:31:56,  1.39s/it]
  2%|▏         | 1078/61904 [24:41<22:49:34,  1.35s/it]
  2%|▏         | 1079/61904 [24:42<22:59:41,  1.36s/it]
  2%|▏         | 1080/61904 [24:43<22:35:15,  1.34s/it]
                                                       
{'loss': 3.1865, 'learning_rate': 1.9857383638013743e-07, 'epoch': 0.28}

  2%|▏         | 1080/61904 [24:43<22:35:15,  1.34s/it]
  2%|▏         | 1081/61904 [24:45<23:02:27,  1.36s/it]
  2%|▏         | 1082/61904 [24:46<23:04:58,  1.37s/it]
  2%|▏         | 1083/61904 [24:47<22:49:23,  1.35s/it]
  2%|▏         | 1084/61904 [24:49<22:15:08,  1.32s/it]
  2%|▏         | 1085/61904 [24:50<22:36:20,  1.34s/it]
  2%|▏         | 1086/61904 [24:51<22:21:26,  1.32s/it]
  2%|▏         | 1087/61904 [24:53<22:06:25,  1.31s/it]
  2%|▏         | 1088/61904 [24:54<22:26:51,  1.33s/it]
  2%|▏         | 1089/61904 [24:55<22:13:54,  1.32s/it]
  2%|▏         | 1090/61904 [24:57<23:15:57,  1.38s/it]
  2%|▏         | 1091/61904 [24:58<23:09:00,  1.37s/it]
  2%|▏         | 1092/61904 [25:00<23:31:17,  1.39s/it]
  2%|▏         | 1093/61904 [25:01<22:49:17,  1.35s/it]
  2%|▏         | 1094/61904 [25:02<23:12:27,  1.37s/it]
  2%|▏         | 1095/61904 [25:04<23:17:34,  1.38s/it]
  2%|▏         | 1096/61904 [25:05<23:25:42,  1.39s/it]
  2%|▏         | 1097/61904 [25:06<22:55:03,  1.36s/it]
  2%|▏         | 1098/61904 [25:08<23:09:12,  1.37s/it]
  2%|▏         | 1099/61904 [25:09<23:52:37,  1.41s/it]
  2%|▏         | 1100/61904 [25:11<23:33:03,  1.39s/it]
                                                       
{'loss': 3.2557, 'learning_rate': 1.985414235705951e-07, 'epoch': 0.28}

  2%|▏         | 1100/61904 [25:11<23:33:03,  1.39s/it]
  2%|▏         | 1101/61904 [25:12<23:41:38,  1.40s/it]
  2%|▏         | 1102/61904 [25:13<23:21:16,  1.38s/it]
  2%|▏         | 1103/61904 [25:15<22:37:54,  1.34s/it]
  2%|▏         | 1104/61904 [25:16<22:27:21,  1.33s/it]
  2%|▏         | 1105/61904 [25:17<22:42:20,  1.34s/it]
  2%|▏         | 1106/61904 [25:19<23:19:03,  1.38s/it]
  2%|▏         | 1107/61904 [25:20<23:48:55,  1.41s/it]
  2%|▏         | 1108/61904 [25:22<23:32:43,  1.39s/it]
  2%|▏         | 1109/61904 [25:23<23:12:24,  1.37s/it]
  2%|▏         | 1110/61904 [25:24<22:50:23,  1.35s/it]
  2%|▏         | 1111/61904 [25:26<23:25:26,  1.39s/it]
  2%|▏         | 1112/61904 [25:27<23:12:02,  1.37s/it]
  2%|▏         | 1113/61904 [25:28<23:09:41,  1.37s/it]
  2%|▏         | 1114/61904 [25:30<23:36:50,  1.40s/it]
  2%|▏         | 1115/61904 [25:31<24:29:34,  1.45s/it]
  2%|▏         | 1116/61904 [25:33<24:08:27,  1.43s/it]
  2%|▏         | 1117/61904 [25:34<23:47:09,  1.41s/it]
  2%|▏         | 1118/61904 [25:36<23:21:39,  1.38s/it]
  2%|▏         | 1119/61904 [25:37<23:32:07,  1.39s/it]
  2%|▏         | 1120/61904 [25:38<23:48:24,  1.41s/it]
                                                       
{'loss': 3.1534, 'learning_rate': 1.9850901076105275e-07, 'epoch': 0.29}

  2%|▏         | 1120/61904 [25:38<23:48:24,  1.41s/it]
  2%|▏         | 1121/61904 [25:40<22:55:57,  1.36s/it]
  2%|▏         | 1122/61904 [25:41<23:54:23,  1.42s/it]
  2%|▏         | 1123/61904 [25:43<23:55:48,  1.42s/it]
  2%|▏         | 1124/61904 [25:44<23:55:32,  1.42s/it]
  2%|▏         | 1125/61904 [25:45<24:19:20,  1.44s/it]
  2%|▏         | 1126/61904 [25:47<24:08:55,  1.43s/it]
  2%|▏         | 1127/61904 [25:48<23:17:05,  1.38s/it]
  2%|▏         | 1128/61904 [25:50<23:16:24,  1.38s/it]
  2%|▏         | 1129/61904 [25:51<23:49:36,  1.41s/it]
  2%|▏         | 1130/61904 [25:52<23:58:02,  1.42s/it]
  2%|▏         | 1131/61904 [25:54<23:54:37,  1.42s/it]
  2%|▏         | 1132/61904 [25:55<23:57:58,  1.42s/it]
  2%|▏         | 1133/61904 [25:57<23:39:28,  1.40s/it]
  2%|▏         | 1134/61904 [25:58<23:21:38,  1.38s/it]
  2%|▏         | 1135/61904 [25:59<23:13:38,  1.38s/it]
  2%|▏         | 1136/61904 [26:01<22:45:16,  1.35s/it]
  2%|▏         | 1137/61904 [26:02<22:30:22,  1.33s/it]
  2%|▏         | 1138/61904 [26:03<22:55:10,  1.36s/it]
  2%|▏         | 1139/61904 [26:05<22:43:32,  1.35s/it]
  2%|▏         | 1140/61904 [26:06<22:52:02,  1.35s/it]
                                                       
{'loss': 3.2257, 'learning_rate': 1.9847659795151044e-07, 'epoch': 0.29}

  2%|▏         | 1140/61904 [26:06<22:52:02,  1.35s/it]
  2%|▏         | 1141/61904 [26:07<22:39:24,  1.34s/it]
  2%|▏         | 1142/61904 [26:09<22:48:25,  1.35s/it]
  2%|▏         | 1143/61904 [26:10<22:31:46,  1.33s/it]
  2%|▏         | 1144/61904 [26:11<22:43:31,  1.35s/it]
  2%|▏         | 1145/61904 [26:13<23:00:26,  1.36s/it]
  2%|▏         | 1146/61904 [26:14<22:49:07,  1.35s/it]
  2%|▏         | 1147/61904 [26:16<23:04:12,  1.37s/it]
  2%|▏         | 1148/61904 [26:17<22:46:19,  1.35s/it]
  2%|▏         | 1149/61904 [26:18<23:02:06,  1.36s/it]
  2%|▏         | 1150/61904 [26:20<23:02:32,  1.37s/it]
  2%|▏         | 1151/61904 [26:21<22:47:21,  1.35s/it]
  2%|▏         | 1152/61904 [26:22<23:01:21,  1.36s/it]
  2%|▏         | 1153/61904 [26:24<22:49:25,  1.35s/it]
  2%|▏         | 1154/61904 [26:25<22:30:24,  1.33s/it]
  2%|▏         | 1155/61904 [26:26<22:42:37,  1.35s/it]
  2%|▏         | 1156/61904 [26:28<22:23:24,  1.33s/it]
  2%|▏         | 1157/61904 [26:29<22:56:23,  1.36s/it]
  2%|▏         | 1158/61904 [26:30<23:26:56,  1.39s/it]
  2%|▏         | 1159/61904 [26:32<23:44:54,  1.41s/it]
  2%|▏         | 1160/61904 [26:33<23:11:06,  1.37s/it]
                                                       
{'loss': 3.2544, 'learning_rate': 1.984441851419681e-07, 'epoch': 0.3}

  2%|▏         | 1160/61904 [26:33<23:11:06,  1.37s/it]
  2%|▏         | 1161/61904 [26:35<25:12:23,  1.49s/it]
  2%|▏         | 1162/61904 [26:36<24:56:08,  1.48s/it]
  2%|▏         | 1163/61904 [26:38<24:00:39,  1.42s/it]
  2%|▏         | 1164/61904 [26:39<23:39:52,  1.40s/it]
  2%|▏         | 1165/61904 [26:40<23:33:28,  1.40s/it]
  2%|▏         | 1166/61904 [26:42<23:56:38,  1.42s/it]
  2%|▏         | 1167/61904 [26:43<23:11:11,  1.37s/it]
  2%|▏         | 1168/61904 [26:45<22:58:27,  1.36s/it]
  2%|▏         | 1169/61904 [26:46<23:18:31,  1.38s/it]
  2%|▏         | 1170/61904 [26:47<23:03:47,  1.37s/it]
  2%|▏         | 1171/61904 [26:49<24:00:25,  1.42s/it]
  2%|▏         | 1172/61904 [26:50<23:51:52,  1.41s/it]
  2%|▏         | 1173/61904 [26:52<23:40:09,  1.40s/it]
  2%|▏         | 1174/61904 [26:53<23:41:44,  1.40s/it]
  2%|▏         | 1175/61904 [26:54<23:28:19,  1.39s/it]
  2%|▏         | 1176/61904 [26:56<24:23:21,  1.45s/it]
  2%|▏         | 1177/61904 [26:57<23:33:33,  1.40s/it]
  2%|▏         | 1178/61904 [26:59<23:35:04,  1.40s/it]
  2%|▏         | 1179/61904 [27:00<23:26:27,  1.39s/it]
  2%|▏         | 1180/61904 [27:02<24:14:25,  1.44s/it]
                                                       
{'loss': 3.1723, 'learning_rate': 1.9841177233242577e-07, 'epoch': 0.3}

  2%|▏         | 1180/61904 [27:02<24:14:25,  1.44s/it]
  2%|▏         | 1181/61904 [27:03<24:04:36,  1.43s/it]
  2%|▏         | 1182/61904 [27:04<23:16:29,  1.38s/it]
  2%|▏         | 1183/61904 [27:06<22:53:19,  1.36s/it]
  2%|▏         | 1184/61904 [27:07<24:11:31,  1.43s/it]
  2%|▏         | 1185/61904 [27:09<24:13:28,  1.44s/it]
  2%|▏         | 1186/61904 [27:10<23:09:24,  1.37s/it]
  2%|▏         | 1187/61904 [27:11<22:53:09,  1.36s/it]
  2%|▏         | 1188/61904 [27:12<22:32:41,  1.34s/it]
  2%|▏         | 1189/61904 [27:14<23:01:51,  1.37s/it]
  2%|▏         | 1190/61904 [27:15<23:06:40,  1.37s/it]
  2%|▏         | 1191/61904 [27:17<23:41:57,  1.41s/it]
  2%|▏         | 1192/61904 [27:18<24:33:53,  1.46s/it]
  2%|▏         | 1193/61904 [27:20<24:01:45,  1.42s/it]
  2%|▏         | 1194/61904 [27:21<23:50:29,  1.41s/it]
  2%|▏         | 1195/61904 [27:22<23:12:38,  1.38s/it]
  2%|▏         | 1196/61904 [27:24<23:05:38,  1.37s/it]
  2%|▏         | 1197/61904 [27:25<23:23:28,  1.39s/it]
  2%|▏         | 1198/61904 [27:27<23:35:42,  1.40s/it]
  2%|▏         | 1199/61904 [27:28<23:19:05,  1.38s/it]
  2%|▏         | 1200/61904 [27:30<24:28:40,  1.45s/it]
                                                       
{'loss': 3.2413, 'learning_rate': 1.9837935952288345e-07, 'epoch': 0.31}

  2%|▏         | 1200/61904 [27:30<24:28:40,  1.45s/it]
  2%|▏         | 1201/61904 [27:31<24:09:52,  1.43s/it]
  2%|▏         | 1202/61904 [27:32<23:34:09,  1.40s/it]
  2%|▏         | 1203/61904 [27:34<24:25:31,  1.45s/it]
  2%|▏         | 1204/61904 [27:35<23:47:06,  1.41s/it]
  2%|▏         | 1205/61904 [27:36<23:01:56,  1.37s/it]
  2%|▏         | 1206/61904 [27:38<23:07:56,  1.37s/it]
  2%|▏         | 1207/61904 [27:39<22:46:46,  1.35s/it]
  2%|▏         | 1208/61904 [27:41<24:05:44,  1.43s/it]
  2%|▏         | 1209/61904 [27:42<23:33:19,  1.40s/it]
  2%|▏         | 1210/61904 [27:43<23:13:03,  1.38s/it]
  2%|▏         | 1211/61904 [27:45<23:11:21,  1.38s/it]
  2%|▏         | 1212/61904 [27:46<22:48:45,  1.35s/it]
  2%|▏         | 1213/61904 [27:47<22:11:54,  1.32s/it]
  2%|▏         | 1214/61904 [27:49<22:58:57,  1.36s/it]
  2%|▏         | 1215/61904 [27:50<22:51:30,  1.36s/it]
  2%|▏         | 1216/61904 [27:51<23:04:12,  1.37s/it]
  2%|▏         | 1217/61904 [27:53<24:20:20,  1.44s/it]
  2%|▏         | 1218/61904 [27:54<24:15:23,  1.44s/it]
  2%|▏         | 1219/61904 [27:56<23:36:49,  1.40s/it]
  2%|▏         | 1220/61904 [27:57<23:02:44,  1.37s/it]
                                                       
{'loss': 3.1966, 'learning_rate': 1.983469467133411e-07, 'epoch': 0.32}

  2%|▏         | 1220/61904 [27:57<23:02:44,  1.37s/it]
  2%|▏         | 1221/61904 [27:58<22:22:32,  1.33s/it]
  2%|▏         | 1222/61904 [28:00<22:36:04,  1.34s/it]
  2%|▏         | 1223/61904 [28:01<22:34:20,  1.34s/it]
  2%|▏         | 1224/61904 [28:02<22:54:33,  1.36s/it]
  2%|▏         | 1225/61904 [28:04<22:45:44,  1.35s/it]
  2%|▏         | 1226/61904 [28:05<22:58:03,  1.36s/it]
  2%|▏         | 1227/61904 [28:07<23:08:06,  1.37s/it]
  2%|▏         | 1228/61904 [28:08<23:09:24,  1.37s/it]
  2%|▏         | 1229/61904 [28:09<22:52:17,  1.36s/it]
  2%|▏         | 1230/61904 [28:10<21:53:21,  1.30s/it]
  2%|▏         | 1231/61904 [28:12<22:20:21,  1.33s/it]
  2%|▏         | 1232/61904 [28:13<22:18:18,  1.32s/it]
  2%|▏         | 1233/61904 [28:14<22:21:42,  1.33s/it]
  2%|▏         | 1234/61904 [28:16<22:33:00,  1.34s/it]
  2%|▏         | 1235/61904 [28:17<22:44:10,  1.35s/it]
  2%|▏         | 1236/61904 [28:19<22:43:50,  1.35s/it]
  2%|▏         | 1237/61904 [28:20<23:14:19,  1.38s/it]
  2%|▏         | 1238/61904 [28:21<22:58:05,  1.36s/it]
  2%|▏         | 1239/61904 [28:23<24:03:40,  1.43s/it]
  2%|▏         | 1240/61904 [28:24<23:31:29,  1.40s/it]
                                                       
{'loss': 3.1888, 'learning_rate': 1.9831453390379878e-07, 'epoch': 0.32}

  2%|▏         | 1240/61904 [28:24<23:31:29,  1.40s/it]
  2%|▏         | 1241/61904 [28:25<22:42:27,  1.35s/it]
  2%|▏         | 1242/61904 [28:27<23:19:26,  1.38s/it]
  2%|▏         | 1243/61904 [28:29<25:05:58,  1.49s/it]
  2%|▏         | 1244/61904 [28:30<23:55:41,  1.42s/it]
  2%|▏         | 1245/61904 [28:31<23:18:22,  1.38s/it]
  2%|▏         | 1246/61904 [28:33<22:59:27,  1.36s/it]
  2%|▏         | 1247/61904 [28:34<24:47:13,  1.47s/it]
  2%|▏         | 1248/61904 [28:36<24:06:48,  1.43s/it]
  2%|▏         | 1249/61904 [28:37<24:11:35,  1.44s/it]
  2%|▏         | 1250/61904 [28:38<23:42:37,  1.41s/it]
  2%|▏         | 1251/61904 [28:40<23:51:00,  1.42s/it]
  2%|▏         | 1252/61904 [28:41<23:12:42,  1.38s/it]
  2%|▏         | 1253/61904 [28:43<23:24:22,  1.39s/it]
  2%|▏         | 1254/61904 [28:44<23:18:11,  1.38s/it]
  2%|▏         | 1255/61904 [28:45<22:55:15,  1.36s/it]
  2%|▏         | 1256/61904 [28:47<23:26:14,  1.39s/it]
  2%|▏         | 1257/61904 [28:48<23:18:19,  1.38s/it]
  2%|▏         | 1258/61904 [28:49<23:13:13,  1.38s/it]
  2%|▏         | 1259/61904 [28:51<22:44:15,  1.35s/it]
  2%|▏         | 1260/61904 [28:52<23:04:24,  1.37s/it]
                                                       
{'loss': 3.1284, 'learning_rate': 1.9828212109425644e-07, 'epoch': 0.33}

  2%|▏         | 1260/61904 [28:52<23:04:24,  1.37s/it]
  2%|▏         | 1261/61904 [28:53<22:56:29,  1.36s/it]
  2%|▏         | 1262/61904 [28:55<23:10:43,  1.38s/it]
  2%|▏         | 1263/61904 [28:56<22:41:19,  1.35s/it]
  2%|▏         | 1264/61904 [28:58<22:52:52,  1.36s/it]
  2%|▏         | 1265/61904 [28:59<22:41:09,  1.35s/it]
  2%|▏         | 1266/61904 [29:00<22:25:47,  1.33s/it]
  2%|▏         | 1267/61904 [29:01<22:28:20,  1.33s/it]
  2%|▏         | 1268/61904 [29:03<22:38:34,  1.34s/it]
  2%|▏         | 1269/61904 [29:04<23:07:29,  1.37s/it]
  2%|▏         | 1270/61904 [29:05<22:15:36,  1.32s/it]
  2%|▏         | 1271/61904 [29:07<22:01:46,  1.31s/it]
  2%|▏         | 1272/61904 [29:08<22:39:33,  1.35s/it]
  2%|▏         | 1273/61904 [29:10<22:58:26,  1.36s/it]
  2%|▏         | 1274/61904 [29:11<23:20:21,  1.39s/it]
  2%|▏         | 1275/61904 [29:12<23:14:26,  1.38s/it]
  2%|▏         | 1276/61904 [29:14<23:59:30,  1.42s/it]
  2%|▏         | 1277/61904 [29:15<23:58:55,  1.42s/it]
  2%|▏         | 1278/61904 [29:17<23:22:26,  1.39s/it]
  2%|▏         | 1279/61904 [29:18<22:53:21,  1.36s/it]
  2%|▏         | 1280/61904 [29:19<23:06:11,  1.37s/it]
                                                       
{'loss': 3.2349, 'learning_rate': 1.982497082847141e-07, 'epoch': 0.33}

  2%|▏         | 1280/61904 [29:19<23:06:11,  1.37s/it]
  2%|▏         | 1281/61904 [29:21<23:22:21,  1.39s/it]
  2%|▏         | 1282/61904 [29:22<22:29:17,  1.34s/it]
  2%|▏         | 1283/61904 [29:23<22:44:20,  1.35s/it]
  2%|▏         | 1284/61904 [29:25<22:19:10,  1.33s/it]
  2%|▏         | 1285/61904 [29:26<22:20:25,  1.33s/it]
  2%|▏         | 1286/61904 [29:27<22:01:35,  1.31s/it]
  2%|▏         | 1287/61904 [29:28<21:43:40,  1.29s/it]
  2%|▏         | 1288/61904 [29:30<21:38:07,  1.28s/it]
  2%|▏         | 1289/61904 [29:31<21:59:11,  1.31s/it]
  2%|▏         | 1290/61904 [29:32<22:26:30,  1.33s/it]
  2%|▏         | 1291/61904 [29:34<22:41:51,  1.35s/it]
  2%|▏         | 1292/61904 [29:35<22:22:16,  1.33s/it]
  2%|▏         | 1293/61904 [29:37<22:50:06,  1.36s/it]
  2%|▏         | 1294/61904 [29:38<22:42:17,  1.35s/it]
  2%|▏         | 1295/61904 [29:39<22:52:47,  1.36s/it]
  2%|▏         | 1296/61904 [29:41<23:49:00,  1.41s/it]
  2%|▏         | 1297/61904 [29:42<24:13:21,  1.44s/it]
  2%|▏         | 1298/61904 [29:44<23:37:55,  1.40s/it]
  2%|▏         | 1299/61904 [29:45<23:00:33,  1.37s/it]
  2%|▏         | 1300/61904 [29:46<23:36:47,  1.40s/it]
                                                       
{'loss': 3.1775, 'learning_rate': 1.982172954751718e-07, 'epoch': 0.34}

  2%|▏         | 1300/61904 [29:46<23:36:47,  1.40s/it]
  2%|▏         | 1301/61904 [29:48<22:42:55,  1.35s/it]
  2%|▏         | 1302/61904 [29:49<22:28:54,  1.34s/it]
  2%|▏         | 1303/61904 [29:50<22:26:42,  1.33s/it]
  2%|▏         | 1304/61904 [29:52<22:58:18,  1.36s/it]
  2%|▏         | 1305/61904 [29:53<23:03:02,  1.37s/it]
  2%|▏         | 1306/61904 [29:54<22:40:15,  1.35s/it]
  2%|▏         | 1307/61904 [29:56<22:52:50,  1.36s/it]
  2%|▏         | 1308/61904 [29:57<23:31:22,  1.40s/it]
  2%|▏         | 1309/61904 [29:59<22:50:08,  1.36s/it]
  2%|▏         | 1310/61904 [30:00<23:32:17,  1.40s/it]
  2%|▏         | 1311/61904 [30:01<23:19:10,  1.39s/it]
  2%|▏         | 1312/61904 [30:03<22:36:01,  1.34s/it]
  2%|▏         | 1313/61904 [30:04<22:45:18,  1.35s/it]
  2%|▏         | 1314/61904 [30:05<23:15:34,  1.38s/it]
  2%|▏         | 1315/61904 [30:07<23:11:15,  1.38s/it]
  2%|▏         | 1316/61904 [30:08<22:31:25,  1.34s/it]
  2%|▏         | 1317/61904 [30:09<22:41:40,  1.35s/it]
  2%|▏         | 1318/61904 [30:11<23:36:54,  1.40s/it]
  2%|▏         | 1319/61904 [30:12<22:59:38,  1.37s/it]
  2%|▏         | 1320/61904 [30:14<23:16:02,  1.38s/it]
                                                       
{'loss': 3.1479, 'learning_rate': 1.9818488266562945e-07, 'epoch': 0.34}

  2%|▏         | 1320/61904 [30:14<23:16:02,  1.38s/it]
  2%|▏         | 1321/61904 [30:15<23:04:42,  1.37s/it]
  2%|▏         | 1322/61904 [30:16<23:05:53,  1.37s/it]
  2%|▏         | 1323/61904 [30:18<22:53:33,  1.36s/it]
  2%|▏         | 1324/61904 [30:19<22:45:44,  1.35s/it]
  2%|▏         | 1325/61904 [30:20<22:49:01,  1.36s/it]
  2%|▏         | 1326/61904 [30:22<22:25:19,  1.33s/it]
  2%|▏         | 1327/61904 [30:23<22:30:50,  1.34s/it]
  2%|▏         | 1328/61904 [30:24<22:38:52,  1.35s/it]
  2%|▏         | 1329/61904 [30:26<22:20:36,  1.33s/it]
  2%|▏         | 1330/61904 [30:27<21:53:13,  1.30s/it]
  2%|▏         | 1331/61904 [30:28<22:00:27,  1.31s/it]
  2%|▏         | 1332/61904 [30:30<22:24:57,  1.33s/it]
  2%|▏         | 1333/61904 [30:31<24:16:41,  1.44s/it]
  2%|▏         | 1334/61904 [30:33<23:42:23,  1.41s/it]
  2%|▏         | 1335/61904 [30:34<23:09:46,  1.38s/it]
  2%|▏         | 1336/61904 [30:35<22:53:47,  1.36s/it]
  2%|▏         | 1337/61904 [30:37<22:59:16,  1.37s/it]
  2%|▏         | 1338/61904 [30:38<22:28:50,  1.34s/it]
  2%|▏         | 1339/61904 [30:39<22:27:12,  1.33s/it]
  2%|▏         | 1340/61904 [30:41<23:04:13,  1.37s/it]
                                                       
{'loss': 3.1342, 'learning_rate': 1.9815246985608711e-07, 'epoch': 0.35}

  2%|▏         | 1340/61904 [30:41<23:04:13,  1.37s/it]
  2%|▏         | 1341/61904 [30:42<23:00:06,  1.37s/it]
  2%|▏         | 1342/61904 [30:44<23:56:18,  1.42s/it]
  2%|▏         | 1343/61904 [30:45<24:05:52,  1.43s/it]
  2%|▏         | 1344/61904 [30:47<24:16:58,  1.44s/it]
  2%|▏         | 1345/61904 [30:48<23:25:12,  1.39s/it]
  2%|▏         | 1346/61904 [30:49<24:13:57,  1.44s/it]
  2%|▏         | 1347/61904 [30:51<23:45:58,  1.41s/it]
  2%|▏         | 1348/61904 [30:52<23:52:40,  1.42s/it]
  2%|▏         | 1349/61904 [30:54<24:27:03,  1.45s/it]
  2%|▏         | 1350/61904 [30:55<24:50:57,  1.48s/it]
  2%|▏         | 1351/61904 [30:57<23:57:05,  1.42s/it]
  2%|▏         | 1352/61904 [30:58<23:16:17,  1.38s/it]
  2%|▏         | 1353/61904 [30:59<22:25:15,  1.33s/it]
  2%|▏         | 1354/61904 [31:00<22:12:26,  1.32s/it]
  2%|▏         | 1355/61904 [31:02<22:36:18,  1.34s/it]
  2%|▏         | 1356/61904 [31:03<23:13:57,  1.38s/it]
  2%|▏         | 1357/61904 [31:05<23:33:16,  1.40s/it]
  2%|▏         | 1358/61904 [31:06<23:40:00,  1.41s/it]
  2%|▏         | 1359/61904 [31:07<22:53:29,  1.36s/it]
  2%|▏         | 1360/61904 [31:09<23:59:32,  1.43s/it]
                                                       
{'loss': 3.1436, 'learning_rate': 1.981200570465448e-07, 'epoch': 0.35}

  2%|▏         | 1360/61904 [31:09<23:59:32,  1.43s/it]
  2%|▏         | 1361/61904 [31:10<24:05:51,  1.43s/it]
  2%|▏         | 1362/61904 [31:12<23:12:38,  1.38s/it]
  2%|▏         | 1363/61904 [31:13<23:26:23,  1.39s/it]
  2%|▏         | 1364/61904 [31:14<23:20:05,  1.39s/it]
  2%|▏         | 1365/61904 [31:16<23:32:58,  1.40s/it]
  2%|▏         | 1366/61904 [31:17<23:24:16,  1.39s/it]
  2%|▏         | 1367/61904 [31:18<22:46:53,  1.35s/it]
  2%|▏         | 1368/61904 [31:20<23:45:01,  1.41s/it]
  2%|▏         | 1369/61904 [31:21<23:30:02,  1.40s/it]
  2%|▏         | 1370/61904 [31:23<23:12:18,  1.38s/it]
  2%|▏         | 1371/61904 [31:24<23:03:54,  1.37s/it]
  2%|▏         | 1372/61904 [31:25<22:56:30,  1.36s/it]
  2%|▏         | 1373/61904 [31:27<23:19:46,  1.39s/it]
  2%|▏         | 1374/61904 [31:28<23:37:45,  1.41s/it]
  2%|▏         | 1375/61904 [31:30<23:19:24,  1.39s/it]
  2%|▏         | 1376/61904 [31:31<22:56:14,  1.36s/it]
  2%|▏         | 1377/61904 [31:32<22:33:45,  1.34s/it]
  2%|▏         | 1378/61904 [31:34<22:38:46,  1.35s/it]
  2%|▏         | 1379/61904 [31:35<23:05:50,  1.37s/it]
  2%|▏         | 1380/61904 [31:36<23:05:48,  1.37s/it]
                                                       
{'loss': 3.1753, 'learning_rate': 1.9808764423700244e-07, 'epoch': 0.36}

  2%|▏         | 1380/61904 [31:36<23:05:48,  1.37s/it]
  2%|▏         | 1381/61904 [31:38<23:38:18,  1.41s/it]
  2%|▏         | 1382/61904 [31:39<23:10:19,  1.38s/it]
  2%|▏         | 1383/61904 [31:41<22:58:08,  1.37s/it]
  2%|▏         | 1384/61904 [31:42<22:35:46,  1.34s/it]
  2%|▏         | 1385/61904 [31:43<22:48:36,  1.36s/it]
  2%|▏         | 1386/61904 [31:45<22:53:22,  1.36s/it]
  2%|▏         | 1387/61904 [31:46<23:33:26,  1.40s/it]
  2%|▏         | 1388/61904 [31:47<23:27:18,  1.40s/it]
  2%|▏         | 1389/61904 [31:49<22:47:03,  1.36s/it]
  2%|▏         | 1390/61904 [31:50<22:50:47,  1.36s/it]
  2%|▏         | 1391/61904 [31:51<22:15:33,  1.32s/it]
  2%|▏         | 1392/61904 [31:53<22:14:31,  1.32s/it]
  2%|▏         | 1393/61904 [31:54<23:03:28,  1.37s/it]
  2%|▏         | 1394/61904 [31:56<23:32:18,  1.40s/it]
  2%|▏         | 1395/61904 [31:57<23:29:17,  1.40s/it]
  2%|▏         | 1396/61904 [31:58<23:37:46,  1.41s/it]
  2%|▏         | 1397/61904 [32:00<23:07:45,  1.38s/it]
  2%|▏         | 1398/61904 [32:01<22:50:53,  1.36s/it]
  2%|▏         | 1399/61904 [32:02<22:10:54,  1.32s/it]
  2%|▏         | 1400/61904 [32:04<22:30:54,  1.34s/it]
                                                       
{'loss': 3.0928, 'learning_rate': 1.9805523142746013e-07, 'epoch': 0.36}

  2%|▏         | 1400/61904 [32:04<22:30:54,  1.34s/it]
  2%|▏         | 1401/61904 [32:05<22:47:13,  1.36s/it]
  2%|▏         | 1402/61904 [32:07<23:14:22,  1.38s/it]
  2%|▏         | 1403/61904 [32:08<23:46:43,  1.41s/it]
  2%|▏         | 1404/61904 [32:09<23:00:12,  1.37s/it]
  2%|▏         | 1405/61904 [32:11<23:35:15,  1.40s/it]
  2%|▏         | 1406/61904 [32:12<22:56:46,  1.37s/it]
  2%|▏         | 1407/61904 [32:14<23:30:07,  1.40s/it]
  2%|▏         | 1408/61904 [32:15<23:28:34,  1.40s/it]
  2%|▏         | 1409/61904 [32:16<23:18:14,  1.39s/it]
  2%|▏         | 1410/61904 [32:18<22:57:00,  1.37s/it]
  2%|▏         | 1411/61904 [32:19<24:10:43,  1.44s/it]
  2%|▏         | 1412/61904 [32:21<23:55:31,  1.42s/it]
  2%|▏         | 1413/61904 [32:22<22:54:26,  1.36s/it]
  2%|▏         | 1414/61904 [32:23<22:13:23,  1.32s/it]
  2%|▏         | 1415/61904 [32:24<22:01:43,  1.31s/it]
  2%|▏         | 1416/61904 [32:26<22:42:36,  1.35s/it]
  2%|▏         | 1417/61904 [32:27<22:16:27,  1.33s/it]
  2%|▏         | 1418/61904 [32:29<22:59:42,  1.37s/it]
  2%|▏         | 1419/61904 [32:30<23:00:50,  1.37s/it]
  2%|▏         | 1420/61904 [32:31<23:14:47,  1.38s/it]
                                                       
{'loss': 3.0965, 'learning_rate': 1.9802281861791781e-07, 'epoch': 0.37}

  2%|▏         | 1420/61904 [32:31<23:14:47,  1.38s/it]
  2%|▏         | 1421/61904 [32:33<22:32:38,  1.34s/it]
  2%|▏         | 1422/61904 [32:34<22:48:15,  1.36s/it]
  2%|▏         | 1423/61904 [32:35<22:31:00,  1.34s/it]
  2%|▏         | 1424/61904 [32:37<23:18:04,  1.39s/it]
  2%|▏         | 1425/61904 [32:38<22:54:24,  1.36s/it]
  2%|▏         | 1426/61904 [32:39<22:40:55,  1.35s/it]
  2%|▏         | 1427/61904 [32:41<23:29:10,  1.40s/it]
  2%|▏         | 1428/61904 [32:42<22:51:53,  1.36s/it]
  2%|▏         | 1429/61904 [32:43<22:43:38,  1.35s/it]
  2%|▏         | 1430/61904 [32:45<23:27:37,  1.40s/it]
  2%|▏         | 1431/61904 [32:46<23:36:27,  1.41s/it]
  2%|▏         | 1432/61904 [32:48<23:28:21,  1.40s/it]
  2%|▏         | 1433/61904 [32:49<22:51:39,  1.36s/it]
  2%|▏         | 1434/61904 [32:50<22:42:03,  1.35s/it]
  2%|▏         | 1435/61904 [32:52<22:54:00,  1.36s/it]
  2%|▏         | 1436/61904 [32:53<22:20:02,  1.33s/it]
  2%|▏         | 1437/61904 [32:54<22:23:44,  1.33s/it]
  2%|▏         | 1438/61904 [32:56<21:58:33,  1.31s/it]
  2%|▏         | 1439/61904 [32:57<21:25:41,  1.28s/it]
  2%|▏         | 1440/61904 [32:58<21:17:32,  1.27s/it]
                                                       
{'loss': 3.1065, 'learning_rate': 1.9799040580837545e-07, 'epoch': 0.37}

  2%|▏         | 1440/61904 [32:58<21:17:32,  1.27s/it]
  2%|▏         | 1441/61904 [32:59<21:52:30,  1.30s/it]
  2%|▏         | 1442/61904 [33:01<21:44:34,  1.29s/it]
  2%|▏         | 1443/61904 [33:02<21:57:54,  1.31s/it]
  2%|▏         | 1444/61904 [33:03<21:34:08,  1.28s/it]
  2%|▏         | 1445/61904 [33:05<21:23:47,  1.27s/it]
  2%|▏         | 1446/61904 [33:06<22:13:20,  1.32s/it]
  2%|▏         | 1447/61904 [33:07<22:36:36,  1.35s/it]
  2%|▏         | 1448/61904 [33:09<23:42:26,  1.41s/it]
  2%|▏         | 1449/61904 [33:10<23:52:58,  1.42s/it]
  2%|▏         | 1450/61904 [33:12<23:38:37,  1.41s/it]
  2%|▏         | 1451/61904 [33:13<23:10:38,  1.38s/it]
  2%|▏         | 1452/61904 [33:14<23:00:50,  1.37s/it]
  2%|▏         | 1453/61904 [33:16<22:50:15,  1.36s/it]
  2%|▏         | 1454/61904 [33:17<23:57:59,  1.43s/it]
  2%|▏         | 1455/61904 [33:19<23:14:43,  1.38s/it]
  2%|▏         | 1456/61904 [33:20<23:18:05,  1.39s/it]
  2%|▏         | 1457/61904 [33:21<23:22:57,  1.39s/it]
  2%|▏         | 1458/61904 [33:23<23:25:33,  1.40s/it]
  2%|▏         | 1459/61904 [33:24<23:26:22,  1.40s/it]
  2%|▏         | 1460/61904 [33:26<23:07:23,  1.38s/it]
                                                       
{'loss': 3.1232, 'learning_rate': 1.9795799299883314e-07, 'epoch': 0.38}

  2%|▏         | 1460/61904 [33:26<23:07:23,  1.38s/it]
  2%|▏         | 1461/61904 [33:27<22:44:20,  1.35s/it]
  2%|▏         | 1462/61904 [33:28<23:05:12,  1.38s/it]
  2%|▏         | 1463/61904 [33:30<23:18:18,  1.39s/it]
  2%|▏         | 1464/61904 [33:31<22:30:19,  1.34s/it]
  2%|▏         | 1465/61904 [33:32<23:06:12,  1.38s/it]
  2%|▏         | 1466/61904 [33:34<22:48:01,  1.36s/it]
  2%|▏         | 1467/61904 [33:35<23:30:40,  1.40s/it]
  2%|▏         | 1468/61904 [33:37<23:29:40,  1.40s/it]
  2%|▏         | 1469/61904 [33:38<23:43:51,  1.41s/it]
  2%|▏         | 1470/61904 [33:40<23:50:46,  1.42s/it]
  2%|▏         | 1471/61904 [33:41<23:27:20,  1.40s/it]
  2%|▏         | 1472/61904 [33:42<23:07:41,  1.38s/it]
  2%|▏         | 1473/61904 [33:44<23:00:27,  1.37s/it]
  2%|▏         | 1474/61904 [33:45<22:42:25,  1.35s/it]
  2%|▏         | 1475/61904 [33:46<22:33:04,  1.34s/it]
  2%|▏         | 1476/61904 [33:48<24:24:20,  1.45s/it]
  2%|▏         | 1477/61904 [33:49<23:59:49,  1.43s/it]
  2%|▏         | 1478/61904 [33:51<23:53:08,  1.42s/it]
  2%|▏         | 1479/61904 [33:52<23:16:58,  1.39s/it]
  2%|▏         | 1480/61904 [33:53<23:31:28,  1.40s/it]
                                                       
{'loss': 3.2101, 'learning_rate': 1.979255801892908e-07, 'epoch': 0.38}

  2%|▏         | 1480/61904 [33:53<23:31:28,  1.40s/it]
  2%|▏         | 1481/61904 [33:55<24:04:18,  1.43s/it]
  2%|▏         | 1482/61904 [33:56<24:41:19,  1.47s/it]
  2%|▏         | 1483/61904 [33:58<24:10:44,  1.44s/it]
  2%|▏         | 1484/61904 [33:59<24:00:21,  1.43s/it]
  2%|▏         | 1485/61904 [34:01<23:57:42,  1.43s/it]
  2%|▏         | 1486/61904 [34:02<23:11:35,  1.38s/it]
  2%|▏         | 1487/61904 [34:03<23:17:09,  1.39s/it]
  2%|▏         | 1488/61904 [34:05<22:41:28,  1.35s/it]
  2%|▏         | 1489/61904 [34:06<23:07:06,  1.38s/it]
  2%|▏         | 1490/61904 [34:07<22:52:10,  1.36s/it]
  2%|▏         | 1491/61904 [34:09<22:58:34,  1.37s/it]
  2%|▏         | 1492/61904 [34:10<22:47:59,  1.36s/it]
  2%|▏         | 1493/61904 [34:11<22:41:37,  1.35s/it]
  2%|▏         | 1494/61904 [34:13<22:33:39,  1.34s/it]
  2%|▏         | 1495/61904 [34:14<22:14:23,  1.33s/it]
  2%|▏         | 1496/61904 [34:16<23:09:07,  1.38s/it]
  2%|▏         | 1497/61904 [34:17<22:49:35,  1.36s/it]
  2%|▏         | 1498/61904 [34:18<22:47:29,  1.36s/it]
  2%|▏         | 1499/61904 [34:20<22:39:14,  1.35s/it]
  2%|▏         | 1500/61904 [34:21<22:31:10,  1.34s/it]
                                                       
{'loss': 3.1625, 'learning_rate': 1.9789316737974846e-07, 'epoch': 0.39}

  2%|▏         | 1500/61904 [34:21<22:31:10,  1.34s/it]
  2%|▏         | 1501/61904 [34:22<22:29:25,  1.34s/it]
  2%|▏         | 1502/61904 [34:24<22:25:49,  1.34s/it]
  2%|▏         | 1503/61904 [34:25<22:44:02,  1.35s/it]
  2%|▏         | 1504/61904 [34:26<22:52:21,  1.36s/it]
  2%|▏         | 1505/61904 [34:28<22:39:23,  1.35s/it]
  2%|▏         | 1506/61904 [34:29<22:39:01,  1.35s/it]
  2%|▏         | 1507/61904 [34:30<23:12:00,  1.38s/it]
  2%|▏         | 1508/61904 [34:32<23:29:38,  1.40s/it]
  2%|▏         | 1509/61904 [34:33<23:24:48,  1.40s/it]
  2%|▏         | 1510/61904 [34:35<23:23:24,  1.39s/it]
  2%|▏         | 1511/61904 [34:36<22:27:16,  1.34s/it]
  2%|▏         | 1512/61904 [34:37<22:37:56,  1.35s/it]
  2%|▏         | 1513/61904 [34:39<22:15:41,  1.33s/it]
  2%|▏         | 1514/61904 [34:40<22:03:46,  1.32s/it]
  2%|▏         | 1515/61904 [34:41<21:41:22,  1.29s/it]
  2%|▏         | 1516/61904 [34:42<22:12:34,  1.32s/it]
  2%|▏         | 1517/61904 [34:44<22:00:53,  1.31s/it]
  2%|▏         | 1518/61904 [34:45<22:23:40,  1.34s/it]
  2%|▏         | 1519/61904 [34:46<22:07:19,  1.32s/it]
  2%|▏         | 1520/61904 [34:48<22:09:54,  1.32s/it]
                                                       
{'loss': 3.0927, 'learning_rate': 1.9786075457020615e-07, 'epoch': 0.39}

  2%|▏         | 1520/61904 [34:48<22:09:54,  1.32s/it]
  2%|▏         | 1521/61904 [34:49<22:59:08,  1.37s/it]
  2%|▏         | 1522/61904 [34:51<23:02:03,  1.37s/it]
  2%|▏         | 1523/61904 [34:52<23:02:56,  1.37s/it]
  2%|▏         | 1524/61904 [34:53<23:37:09,  1.41s/it]
  2%|▏         | 1525/61904 [34:55<24:18:02,  1.45s/it]
  2%|▏         | 1526/61904 [34:56<24:11:15,  1.44s/it]
  2%|▏         | 1527/61904 [34:58<23:36:35,  1.41s/it]
  2%|▏         | 1528/61904 [34:59<23:44:22,  1.42s/it]
  2%|▏         | 1529/61904 [35:00<23:02:00,  1.37s/it]
  2%|▏         | 1530/61904 [35:02<23:00:59,  1.37s/it]
  2%|▏         | 1531/61904 [35:03<22:56:44,  1.37s/it]
  2%|▏         | 1532/61904 [35:04<22:11:34,  1.32s/it]
  2%|▏         | 1533/61904 [35:06<22:34:36,  1.35s/it]
  2%|▏         | 1534/61904 [35:07<22:47:19,  1.36s/it]
  2%|▏         | 1535/61904 [35:09<23:26:34,  1.40s/it]
  2%|▏         | 1536/61904 [35:10<22:27:13,  1.34s/it]
  2%|▏         | 1537/61904 [35:11<23:47:05,  1.42s/it]
  2%|▏         | 1538/61904 [35:13<23:42:02,  1.41s/it]
  2%|▏         | 1539/61904 [35:15<24:46:07,  1.48s/it]
  2%|▏         | 1540/61904 [35:16<23:52:04,  1.42s/it]
                                                       
{'loss': 3.1796, 'learning_rate': 1.978283417606638e-07, 'epoch': 0.4}

  2%|▏         | 1540/61904 [35:16<23:52:04,  1.42s/it]
  2%|▏         | 1541/61904 [35:17<23:47:34,  1.42s/it]
  2%|▏         | 1542/61904 [35:19<23:10:57,  1.38s/it]
  2%|▏         | 1543/61904 [35:20<23:25:24,  1.40s/it]
  2%|▏         | 1544/61904 [35:21<23:33:24,  1.40s/it]
  2%|▏         | 1545/61904 [35:23<23:54:36,  1.43s/it]
  2%|▏         | 1546/61904 [35:24<23:03:44,  1.38s/it]
  2%|▏         | 1547/61904 [35:26<23:18:44,  1.39s/it]
  3%|▎         | 1548/61904 [35:27<23:12:30,  1.38s/it]
  3%|▎         | 1549/61904 [35:28<23:35:39,  1.41s/it]
  3%|▎         | 1550/61904 [35:30<22:48:21,  1.36s/it]
  3%|▎         | 1551/61904 [35:31<23:14:59,  1.39s/it]
  3%|▎         | 1552/61904 [35:32<22:57:44,  1.37s/it]
  3%|▎         | 1553/61904 [35:34<23:18:31,  1.39s/it]
  3%|▎         | 1554/61904 [35:35<24:06:23,  1.44s/it]
  3%|▎         | 1555/61904 [35:37<24:17:21,  1.45s/it]
  3%|▎         | 1556/61904 [35:38<23:45:41,  1.42s/it]
  3%|▎         | 1557/61904 [35:39<22:41:57,  1.35s/it]
  3%|▎         | 1558/61904 [35:41<22:56:56,  1.37s/it]
  3%|▎         | 1559/61904 [35:42<21:49:01,  1.30s/it]
  3%|▎         | 1560/61904 [35:43<21:55:32,  1.31s/it]
                                                       
{'loss': 3.1212, 'learning_rate': 1.9779592895112147e-07, 'epoch': 0.4}

  3%|▎         | 1560/61904 [35:43<21:55:32,  1.31s/it]
  3%|▎         | 1561/61904 [35:45<22:25:57,  1.34s/it]
  3%|▎         | 1562/61904 [35:46<22:45:26,  1.36s/it]
  3%|▎         | 1563/61904 [35:47<22:37:03,  1.35s/it]
  3%|▎         | 1564/61904 [35:49<22:52:14,  1.36s/it]
  3%|▎         | 1565/61904 [35:50<22:32:38,  1.35s/it]
  3%|▎         | 1566/61904 [35:51<21:57:56,  1.31s/it]
  3%|▎         | 1567/61904 [35:53<21:38:52,  1.29s/it]
  3%|▎         | 1568/61904 [35:54<22:12:19,  1.32s/it]
  3%|▎         | 1569/61904 [35:55<22:30:49,  1.34s/it]
  3%|▎         | 1570/61904 [35:57<22:46:47,  1.36s/it]
  3%|▎         | 1571/61904 [35:58<21:51:31,  1.30s/it]
  3%|▎         | 1572/61904 [35:59<21:58:25,  1.31s/it]
  3%|▎         | 1573/61904 [36:01<22:16:19,  1.33s/it]
  3%|▎         | 1574/61904 [36:02<22:24:57,  1.34s/it]
  3%|▎         | 1575/61904 [36:03<22:30:29,  1.34s/it]
  3%|▎         | 1576/61904 [36:05<23:29:12,  1.40s/it]
  3%|▎         | 1577/61904 [36:06<23:11:24,  1.38s/it]
  3%|▎         | 1578/61904 [36:08<23:21:52,  1.39s/it]
  3%|▎         | 1579/61904 [36:09<23:19:44,  1.39s/it]
  3%|▎         | 1580/61904 [36:10<22:44:28,  1.36s/it]
                                                       
{'loss': 3.2041, 'learning_rate': 1.9776351614157916e-07, 'epoch': 0.41}

  3%|▎         | 1580/61904 [36:10<22:44:28,  1.36s/it]
  3%|▎         | 1581/61904 [36:12<22:50:20,  1.36s/it]
  3%|▎         | 1582/61904 [36:13<22:15:03,  1.33s/it]
  3%|▎         | 1583/61904 [36:14<22:45:24,  1.36s/it]
  3%|▎         | 1584/61904 [36:16<23:08:58,  1.38s/it]
  3%|▎         | 1585/61904 [36:17<23:25:26,  1.40s/it]
  3%|▎         | 1586/61904 [36:19<23:00:37,  1.37s/it]
  3%|▎         | 1587/61904 [36:20<22:52:33,  1.37s/it]
  3%|▎         | 1588/61904 [36:21<22:59:39,  1.37s/it]
  3%|▎         | 1589/61904 [36:23<22:33:03,  1.35s/it]
  3%|▎         | 1590/61904 [36:24<22:43:53,  1.36s/it]
  3%|▎         | 1591/61904 [36:25<22:07:17,  1.32s/it]
  3%|▎         | 1592/61904 [36:27<22:45:27,  1.36s/it]
  3%|▎         | 1593/61904 [36:28<22:44:16,  1.36s/it]
  3%|▎         | 1594/61904 [36:30<23:28:17,  1.40s/it]
  3%|▎         | 1595/61904 [36:31<22:58:50,  1.37s/it]
  3%|▎         | 1596/61904 [36:32<22:21:33,  1.33s/it]
  3%|▎         | 1597/61904 [36:33<22:16:39,  1.33s/it]
  3%|▎         | 1598/61904 [36:35<22:23:06,  1.34s/it]
  3%|▎         | 1599/61904 [36:36<22:40:00,  1.35s/it]
  3%|▎         | 1600/61904 [36:37<22:09:30,  1.32s/it]
                                                       
{'loss': 3.1158, 'learning_rate': 1.977311033320368e-07, 'epoch': 0.41}

  3%|▎         | 1600/61904 [36:37<22:09:30,  1.32s/it]
  3%|▎         | 1601/61904 [36:39<22:22:31,  1.34s/it]
  3%|▎         | 1602/61904 [36:40<22:52:23,  1.37s/it]
  3%|▎         | 1603/61904 [36:41<22:06:20,  1.32s/it]
  3%|▎         | 1604/61904 [36:43<21:31:04,  1.28s/it]
  3%|▎         | 1605/61904 [36:44<22:32:06,  1.35s/it]
  3%|▎         | 1606/61904 [36:45<22:35:54,  1.35s/it]
  3%|▎         | 1607/61904 [36:47<22:33:10,  1.35s/it]
  3%|▎         | 1608/61904 [36:48<22:57:29,  1.37s/it]
  3%|▎         | 1609/61904 [36:49<22:31:35,  1.34s/it]
  3%|▎         | 1610/61904 [36:51<21:47:38,  1.30s/it]
  3%|▎         | 1611/61904 [36:52<22:26:23,  1.34s/it]
  3%|▎         | 1612/61904 [36:54<22:44:19,  1.36s/it]
  3%|▎         | 1613/61904 [36:55<22:36:00,  1.35s/it]
  3%|▎         | 1614/61904 [36:56<22:10:03,  1.32s/it]
  3%|▎         | 1615/61904 [36:57<21:49:45,  1.30s/it]
  3%|▎         | 1616/61904 [36:59<21:47:39,  1.30s/it]
  3%|▎         | 1617/61904 [37:00<22:26:33,  1.34s/it]
  3%|▎         | 1618/61904 [37:01<22:24:58,  1.34s/it]
  3%|▎         | 1619/61904 [37:03<22:26:55,  1.34s/it]
  3%|▎         | 1620/61904 [37:04<22:06:20,  1.32s/it]
                                                       
{'loss': 3.1244, 'learning_rate': 1.9769869052249449e-07, 'epoch': 0.42}

  3%|▎         | 1620/61904 [37:04<22:06:20,  1.32s/it]
  3%|▎         | 1621/61904 [37:06<23:00:27,  1.37s/it]
  3%|▎         | 1622/61904 [37:07<23:27:32,  1.40s/it]
  3%|▎         | 1623/61904 [37:08<23:27:23,  1.40s/it]
  3%|▎         | 1624/61904 [37:10<22:55:20,  1.37s/it]
  3%|▎         | 1625/61904 [37:11<22:49:30,  1.36s/it]
  3%|▎         | 1626/61904 [37:12<22:14:04,  1.33s/it]
  3%|▎         | 1627/61904 [37:14<22:56:41,  1.37s/it]
  3%|▎         | 1628/61904 [37:15<22:26:07,  1.34s/it]
  3%|▎         | 1629/61904 [37:16<22:48:19,  1.36s/it]
  3%|▎         | 1630/61904 [37:18<22:39:44,  1.35s/it]
  3%|▎         | 1631/61904 [37:19<22:59:52,  1.37s/it]
  3%|▎         | 1632/61904 [37:21<22:58:35,  1.37s/it]
  3%|▎         | 1633/61904 [37:22<22:46:16,  1.36s/it]
  3%|▎         | 1634/61904 [37:23<22:52:37,  1.37s/it]
  3%|▎         | 1635/61904 [37:25<22:33:12,  1.35s/it]
  3%|▎         | 1636/61904 [37:26<22:44:36,  1.36s/it]
  3%|▎         | 1637/61904 [37:27<22:38:01,  1.35s/it]
  3%|▎         | 1638/61904 [37:29<23:06:51,  1.38s/it]
  3%|▎         | 1639/61904 [37:30<22:43:23,  1.36s/it]
  3%|▎         | 1640/61904 [37:31<22:21:01,  1.34s/it]
                                                       
{'loss': 3.1836, 'learning_rate': 1.9766627771295215e-07, 'epoch': 0.42}

  3%|▎         | 1640/61904 [37:31<22:21:01,  1.34s/it]
  3%|▎         | 1641/61904 [37:33<22:48:40,  1.36s/it]
  3%|▎         | 1642/61904 [37:34<22:42:01,  1.36s/it]
  3%|▎         | 1643/61904 [37:35<22:07:03,  1.32s/it]
  3%|▎         | 1644/61904 [37:37<22:00:49,  1.32s/it]
  3%|▎         | 1645/61904 [37:38<21:52:48,  1.31s/it]
  3%|▎         | 1646/61904 [37:39<21:40:57,  1.30s/it]
  3%|▎         | 1647/61904 [37:41<22:19:19,  1.33s/it]
  3%|▎         | 1648/61904 [37:42<22:38:24,  1.35s/it]
  3%|▎         | 1649/61904 [37:43<22:36:16,  1.35s/it]
  3%|▎         | 1650/61904 [37:45<22:13:55,  1.33s/it]
  3%|▎         | 1651/61904 [37:46<22:24:26,  1.34s/it]
  3%|▎         | 1652/61904 [37:48<23:37:20,  1.41s/it]
  3%|▎         | 1653/61904 [37:49<23:59:46,  1.43s/it]
  3%|▎         | 1654/61904 [37:50<23:19:05,  1.39s/it]
  3%|▎         | 1655/61904 [37:52<22:59:50,  1.37s/it]
  3%|▎         | 1656/61904 [37:53<23:41:13,  1.42s/it]
  3%|▎         | 1657/61904 [37:55<23:42:20,  1.42s/it]
  3%|▎         | 1658/61904 [37:56<23:44:07,  1.42s/it]
  3%|▎         | 1659/61904 [37:57<23:30:51,  1.41s/it]
  3%|▎         | 1660/61904 [37:59<22:37:36,  1.35s/it]
                                                       
{'loss': 3.1079, 'learning_rate': 1.976338649034098e-07, 'epoch': 0.43}

  3%|▎         | 1660/61904 [37:59<22:37:36,  1.35s/it]
  3%|▎         | 1661/61904 [38:00<22:17:12,  1.33s/it]
  3%|▎         | 1662/61904 [38:01<22:25:33,  1.34s/it]
  3%|▎         | 1663/61904 [38:03<22:44:46,  1.36s/it]
  3%|▎         | 1664/61904 [38:04<23:12:01,  1.39s/it]
  3%|▎         | 1665/61904 [38:06<23:42:37,  1.42s/it]
  3%|▎         | 1666/61904 [38:07<24:04:58,  1.44s/it]
  3%|▎         | 1667/61904 [38:09<23:49:43,  1.42s/it]
  3%|▎         | 1668/61904 [38:10<23:20:11,  1.39s/it]
  3%|▎         | 1669/61904 [38:11<22:39:16,  1.35s/it]
  3%|▎         | 1670/61904 [38:12<22:21:23,  1.34s/it]
  3%|▎         | 1671/61904 [38:14<22:50:58,  1.37s/it]
  3%|▎         | 1672/61904 [38:15<22:37:26,  1.35s/it]
  3%|▎         | 1673/61904 [38:17<23:18:23,  1.39s/it]
  3%|▎         | 1674/61904 [38:18<23:21:07,  1.40s/it]
  3%|▎         | 1675/61904 [38:19<23:11:01,  1.39s/it]
  3%|▎         | 1676/61904 [38:21<22:39:25,  1.35s/it]
  3%|▎         | 1677/61904 [38:22<22:30:15,  1.35s/it]
  3%|▎         | 1678/61904 [38:23<22:04:14,  1.32s/it]
  3%|▎         | 1679/61904 [38:25<23:36:35,  1.41s/it]
  3%|▎         | 1680/61904 [38:26<24:14:49,  1.45s/it]
                                                       
{'loss': 3.1643, 'learning_rate': 1.976014520938675e-07, 'epoch': 0.43}

  3%|▎         | 1680/61904 [38:26<24:14:49,  1.45s/it]
  3%|▎         | 1681/61904 [38:28<23:48:48,  1.42s/it]
  3%|▎         | 1682/61904 [38:29<22:40:03,  1.36s/it]
  3%|▎         | 1683/61904 [38:30<22:24:30,  1.34s/it]
  3%|▎         | 1684/61904 [38:32<23:44:27,  1.42s/it]
  3%|▎         | 1685/61904 [38:33<23:24:00,  1.40s/it]
  3%|▎         | 1686/61904 [38:35<23:49:35,  1.42s/it]
  3%|▎         | 1687/61904 [38:36<23:09:46,  1.38s/it]
  3%|▎         | 1688/61904 [38:38<23:40:38,  1.42s/it]
  3%|▎         | 1689/61904 [38:39<23:29:05,  1.40s/it]
  3%|▎         | 1690/61904 [38:41<24:27:13,  1.46s/it]
  3%|▎         | 1691/61904 [38:42<23:40:33,  1.42s/it]
  3%|▎         | 1692/61904 [38:43<22:52:57,  1.37s/it]
  3%|▎         | 1693/61904 [38:44<23:01:10,  1.38s/it]
  3%|▎         | 1694/61904 [38:46<22:39:21,  1.35s/it]
  3%|▎         | 1695/61904 [38:47<22:39:01,  1.35s/it]
  3%|▎         | 1696/61904 [38:48<22:11:24,  1.33s/it]
  3%|▎         | 1697/61904 [38:50<22:04:20,  1.32s/it]
  3%|▎         | 1698/61904 [38:51<22:06:44,  1.32s/it]
  3%|▎         | 1699/61904 [38:52<22:19:45,  1.34s/it]
  3%|▎         | 1700/61904 [38:54<22:02:39,  1.32s/it]
                                                       
{'loss': 3.1435, 'learning_rate': 1.9756903928432516e-07, 'epoch': 0.44}

  3%|▎         | 1700/61904 [38:54<22:02:39,  1.32s/it]
  3%|▎         | 1701/61904 [38:55<21:53:46,  1.31s/it]
  3%|▎         | 1702/61904 [38:56<21:56:49,  1.31s/it]
  3%|▎         | 1703/61904 [38:58<22:36:18,  1.35s/it]
  3%|▎         | 1704/61904 [38:59<22:35:15,  1.35s/it]
  3%|▎         | 1705/61904 [39:00<22:11:52,  1.33s/it]
  3%|▎         | 1706/61904 [39:02<23:11:29,  1.39s/it]
  3%|▎         | 1707/61904 [39:03<23:18:41,  1.39s/it]
  3%|▎         | 1708/61904 [39:05<23:26:27,  1.40s/it]
  3%|▎         | 1709/61904 [39:06<23:31:50,  1.41s/it]
  3%|▎         | 1710/61904 [39:07<22:48:53,  1.36s/it]
  3%|▎         | 1711/61904 [39:09<23:02:09,  1.38s/it]
  3%|▎         | 1712/61904 [39:10<22:34:27,  1.35s/it]
  3%|▎         | 1713/61904 [39:12<22:58:58,  1.37s/it]
  3%|▎         | 1714/61904 [39:13<22:47:51,  1.36s/it]
  3%|▎         | 1715/61904 [39:14<23:32:47,  1.41s/it]
  3%|▎         | 1716/61904 [39:16<23:03:46,  1.38s/it]
  3%|▎         | 1717/61904 [39:17<22:39:37,  1.36s/it]
  3%|▎         | 1718/61904 [39:18<22:40:12,  1.36s/it]
  3%|▎         | 1719/61904 [39:20<23:35:16,  1.41s/it]
  3%|▎         | 1720/61904 [39:21<23:18:48,  1.39s/it]
                                                       
{'loss': 3.2259, 'learning_rate': 1.9753662647478282e-07, 'epoch': 0.44}

  3%|▎         | 1720/61904 [39:21<23:18:48,  1.39s/it]
  3%|▎         | 1721/61904 [39:23<23:21:21,  1.40s/it]
  3%|▎         | 1722/61904 [39:24<24:38:21,  1.47s/it]
  3%|▎         | 1723/61904 [39:26<23:36:37,  1.41s/it]
  3%|▎         | 1724/61904 [39:27<23:17:20,  1.39s/it]
  3%|▎         | 1725/61904 [39:28<23:41:08,  1.42s/it]
  3%|▎         | 1726/61904 [39:30<22:59:19,  1.38s/it]
  3%|▎         | 1727/61904 [39:31<22:37:46,  1.35s/it]
  3%|▎         | 1728/61904 [39:32<22:33:31,  1.35s/it]
  3%|▎         | 1729/61904 [39:34<22:30:43,  1.35s/it]
  3%|▎         | 1730/61904 [39:35<22:38:22,  1.35s/it]
  3%|▎         | 1731/61904 [39:36<23:14:20,  1.39s/it]
  3%|▎         | 1732/61904 [39:38<23:35:08,  1.41s/it]
  3%|▎         | 1733/61904 [39:39<22:59:10,  1.38s/it]
  3%|▎         | 1734/61904 [39:41<23:11:41,  1.39s/it]
  3%|▎         | 1735/61904 [39:42<22:14:59,  1.33s/it]
  3%|▎         | 1736/61904 [39:43<22:29:37,  1.35s/it]
  3%|▎         | 1737/61904 [39:45<22:22:08,  1.34s/it]
  3%|▎         | 1738/61904 [39:46<22:34:56,  1.35s/it]
  3%|▎         | 1739/61904 [39:47<22:25:57,  1.34s/it]
  3%|▎         | 1740/61904 [39:49<22:33:54,  1.35s/it]
                                                       
{'loss': 3.2045, 'learning_rate': 1.975042136652405e-07, 'epoch': 0.45}

  3%|▎         | 1740/61904 [39:49<22:33:54,  1.35s/it]
  3%|▎         | 1741/61904 [39:50<22:31:27,  1.35s/it]
  3%|▎         | 1742/61904 [39:51<22:09:30,  1.33s/it]
  3%|▎         | 1743/61904 [39:53<22:08:58,  1.33s/it]
  3%|▎         | 1744/61904 [39:54<21:56:24,  1.31s/it]
  3%|▎         | 1745/61904 [39:55<22:26:10,  1.34s/it]
  3%|▎         | 1746/61904 [39:57<22:17:02,  1.33s/it]
  3%|▎         | 1747/61904 [39:58<22:36:06,  1.35s/it]
  3%|▎         | 1748/61904 [39:59<22:25:59,  1.34s/it]
  3%|▎         | 1749/61904 [40:01<22:42:21,  1.36s/it]
  3%|▎         | 1750/61904 [40:02<22:53:35,  1.37s/it]
  3%|▎         | 1751/61904 [40:03<22:31:22,  1.35s/it]
  3%|▎         | 1752/61904 [40:05<22:55:52,  1.37s/it]
  3%|▎         | 1753/61904 [40:06<23:00:03,  1.38s/it]
  3%|▎         | 1754/61904 [40:08<23:16:30,  1.39s/it]
  3%|▎         | 1755/61904 [40:09<22:55:29,  1.37s/it]
  3%|▎         | 1756/61904 [40:11<24:17:09,  1.45s/it]
  3%|▎         | 1757/61904 [40:12<23:52:22,  1.43s/it]
  3%|▎         | 1758/61904 [40:13<22:57:50,  1.37s/it]
  3%|▎         | 1759/61904 [40:15<22:41:42,  1.36s/it]
  3%|▎         | 1760/61904 [40:16<22:33:29,  1.35s/it]
                                                       
{'loss': 3.1356, 'learning_rate': 1.9747180085569817e-07, 'epoch': 0.45}

  3%|▎         | 1760/61904 [40:16<22:33:29,  1.35s/it]
  3%|▎         | 1761/61904 [40:17<22:09:25,  1.33s/it]
  3%|▎         | 1762/61904 [40:19<22:27:41,  1.34s/it]
  3%|▎         | 1763/61904 [40:20<22:03:30,  1.32s/it]
  3%|▎         | 1764/61904 [40:21<21:35:20,  1.29s/it]
  3%|▎         | 1765/61904 [40:22<22:15:07,  1.33s/it]
  3%|▎         | 1766/61904 [40:24<22:53:49,  1.37s/it]
  3%|▎         | 1767/61904 [40:25<22:59:52,  1.38s/it]
  3%|▎         | 1768/61904 [40:27<23:05:02,  1.38s/it]
  3%|▎         | 1769/61904 [40:28<23:56:31,  1.43s/it]
  3%|▎         | 1770/61904 [40:30<23:51:01,  1.43s/it]
  3%|▎         | 1771/61904 [40:31<23:34:37,  1.41s/it]
  3%|▎         | 1772/61904 [40:32<22:59:40,  1.38s/it]
  3%|▎         | 1773/61904 [40:34<24:05:30,  1.44s/it]
  3%|▎         | 1774/61904 [40:35<23:40:31,  1.42s/it]
  3%|▎         | 1775/61904 [40:37<23:30:44,  1.41s/it]
  3%|▎         | 1776/61904 [40:38<23:22:34,  1.40s/it]
  3%|▎         | 1777/61904 [40:39<23:24:15,  1.40s/it]
  3%|▎         | 1778/61904 [40:41<22:48:54,  1.37s/it]
  3%|▎         | 1779/61904 [40:42<23:35:14,  1.41s/it]
  3%|▎         | 1780/61904 [40:43<22:49:53,  1.37s/it]
                                                       
{'loss': 3.1475, 'learning_rate': 1.9743938804615583e-07, 'epoch': 0.46}

  3%|▎         | 1780/61904 [40:43<22:49:53,  1.37s/it]
  3%|▎         | 1781/61904 [40:45<22:38:49,  1.36s/it]
  3%|▎         | 1782/61904 [40:46<22:44:16,  1.36s/it]
  3%|▎         | 1783/61904 [40:48<23:16:30,  1.39s/it]
  3%|▎         | 1784/61904 [40:49<22:20:11,  1.34s/it]
  3%|▎         | 1785/61904 [40:50<21:58:59,  1.32s/it]
  3%|▎         | 1786/61904 [40:52<22:16:16,  1.33s/it]
  3%|▎         | 1787/61904 [40:53<21:51:44,  1.31s/it]
  3%|▎         | 1788/61904 [40:54<22:17:21,  1.33s/it]
  3%|▎         | 1789/61904 [40:56<23:17:40,  1.40s/it]
  3%|▎         | 1790/61904 [40:57<22:23:18,  1.34s/it]
  3%|▎         | 1791/61904 [40:58<22:54:03,  1.37s/it]
  3%|▎         | 1792/61904 [41:00<22:54:33,  1.37s/it]
  3%|▎         | 1793/61904 [41:01<23:17:00,  1.39s/it]
  3%|▎         | 1794/61904 [41:03<23:27:27,  1.40s/it]
  3%|▎         | 1795/61904 [41:04<23:23:56,  1.40s/it]
  3%|▎         | 1796/61904 [41:05<23:18:17,  1.40s/it]
  3%|▎         | 1797/61904 [41:07<22:30:35,  1.35s/it]
  3%|▎         | 1798/61904 [41:08<22:13:12,  1.33s/it]
  3%|▎         | 1799/61904 [41:09<22:03:16,  1.32s/it]
  3%|▎         | 1800/61904 [41:11<22:35:16,  1.35s/it]
                                                       
{'loss': 3.1801, 'learning_rate': 1.9740697523661352e-07, 'epoch': 0.47}

  3%|▎         | 1800/61904 [41:11<22:35:16,  1.35s/it]
  3%|▎         | 1801/61904 [41:12<22:49:10,  1.37s/it]
  3%|▎         | 1802/61904 [41:13<22:18:06,  1.34s/it]
  3%|▎         | 1803/61904 [41:15<22:44:29,  1.36s/it]
  3%|▎         | 1804/61904 [41:16<21:57:23,  1.32s/it]
  3%|▎         | 1805/61904 [41:17<21:44:43,  1.30s/it]
  3%|▎         | 1806/61904 [41:19<22:33:13,  1.35s/it]
  3%|▎         | 1807/61904 [41:20<22:02:44,  1.32s/it]
  3%|▎         | 1808/61904 [41:21<22:15:25,  1.33s/it]
  3%|▎         | 1809/61904 [41:23<22:06:40,  1.32s/it]
  3%|▎         | 1810/61904 [41:24<22:19:39,  1.34s/it]
  3%|▎         | 1811/61904 [41:25<22:11:11,  1.33s/it]
  3%|▎         | 1812/61904 [41:27<22:42:44,  1.36s/it]
  3%|▎         | 1813/61904 [41:28<22:54:29,  1.37s/it]
  3%|▎         | 1814/61904 [41:29<22:48:32,  1.37s/it]
  3%|▎         | 1815/61904 [41:31<22:33:05,  1.35s/it]
  3%|▎         | 1816/61904 [41:32<22:08:09,  1.33s/it]
  3%|▎         | 1817/61904 [41:33<21:36:00,  1.29s/it]
  3%|▎         | 1818/61904 [41:35<22:17:58,  1.34s/it]
  3%|▎         | 1819/61904 [41:36<22:55:22,  1.37s/it]
  3%|▎         | 1820/61904 [41:38<23:09:57,  1.39s/it]
                                                       
{'loss': 3.1391, 'learning_rate': 1.9737456242707116e-07, 'epoch': 0.47}

  3%|▎         | 1820/61904 [41:38<23:09:57,  1.39s/it]
  3%|▎         | 1821/61904 [41:39<23:13:49,  1.39s/it]
  3%|▎         | 1822/61904 [41:40<22:23:45,  1.34s/it]
  3%|▎         | 1823/61904 [41:42<22:36:24,  1.35s/it]
  3%|▎         | 1824/61904 [41:43<22:49:37,  1.37s/it]
  3%|▎         | 1825/61904 [41:44<22:42:45,  1.36s/it]
  3%|▎         | 1826/61904 [41:46<22:58:23,  1.38s/it]
  3%|▎         | 1827/61904 [41:47<22:52:16,  1.37s/it]
  3%|▎         | 1828/61904 [41:48<22:24:30,  1.34s/it]
  3%|▎         | 1829/61904 [41:50<22:13:47,  1.33s/it]
  3%|▎         | 1830/61904 [41:51<22:15:31,  1.33s/it]
  3%|▎         | 1831/61904 [41:52<22:20:52,  1.34s/it]
  3%|▎         | 1832/61904 [41:54<22:22:07,  1.34s/it]
  3%|▎         | 1833/61904 [41:55<22:19:23,  1.34s/it]
  3%|▎         | 1834/61904 [41:56<22:21:06,  1.34s/it]
  3%|▎         | 1835/61904 [41:58<22:15:25,  1.33s/it]
  3%|▎         | 1836/61904 [41:59<22:48:30,  1.37s/it]
  3%|▎         | 1837/61904 [42:01<23:21:40,  1.40s/it]
  3%|▎         | 1838/61904 [42:02<23:52:39,  1.43s/it]
  3%|▎         | 1839/61904 [42:04<24:18:13,  1.46s/it]
  3%|▎         | 1840/61904 [42:05<23:45:41,  1.42s/it]
                                                       
{'loss': 3.151, 'learning_rate': 1.9734214961752885e-07, 'epoch': 0.48}

  3%|▎         | 1840/61904 [42:05<23:45:41,  1.42s/it]
  3%|▎         | 1841/61904 [42:06<24:02:36,  1.44s/it]
  3%|▎         | 1842/61904 [42:08<23:50:20,  1.43s/it]
  3%|▎         | 1843/61904 [42:09<23:36:57,  1.42s/it]
  3%|▎         | 1844/61904 [42:11<23:48:04,  1.43s/it]
  3%|▎         | 1845/61904 [42:12<23:40:10,  1.42s/it]
  3%|▎         | 1846/61904 [42:14<24:57:29,  1.50s/it]
  3%|▎         | 1847/61904 [42:15<24:22:33,  1.46s/it]
  3%|▎         | 1848/61904 [42:16<23:32:09,  1.41s/it]
  3%|▎         | 1849/61904 [42:18<23:46:25,  1.43s/it]
  3%|▎         | 1850/61904 [42:19<22:46:33,  1.37s/it]
  3%|▎         | 1851/61904 [42:20<22:09:32,  1.33s/it]
  3%|▎         | 1852/61904 [42:22<22:01:20,  1.32s/it]
  3%|▎         | 1853/61904 [42:23<22:06:40,  1.33s/it]
  3%|▎         | 1854/61904 [42:24<22:11:56,  1.33s/it]
  3%|▎         | 1855/61904 [42:26<22:21:25,  1.34s/it]
  3%|▎         | 1856/61904 [42:27<21:40:38,  1.30s/it]
  3%|▎         | 1857/61904 [42:28<22:06:59,  1.33s/it]
  3%|▎         | 1858/61904 [42:30<22:00:35,  1.32s/it]
  3%|▎         | 1859/61904 [42:31<22:01:12,  1.32s/it]
  3%|▎         | 1860/61904 [42:32<21:32:35,  1.29s/it]
                                                       
{'loss': 3.1714, 'learning_rate': 1.973097368079865e-07, 'epoch': 0.48}

  3%|▎         | 1860/61904 [42:32<21:32:35,  1.29s/it]
  3%|▎         | 1861/61904 [42:33<21:23:12,  1.28s/it]
  3%|▎         | 1862/61904 [42:35<22:01:04,  1.32s/it]
  3%|▎         | 1863/61904 [42:36<22:36:19,  1.36s/it]
  3%|▎         | 1864/61904 [42:38<22:17:06,  1.34s/it]
  3%|▎         | 1865/61904 [42:39<23:07:59,  1.39s/it]
  3%|▎         | 1866/61904 [42:41<23:50:46,  1.43s/it]
  3%|▎         | 1867/61904 [42:42<23:27:06,  1.41s/it]
  3%|▎         | 1868/61904 [42:43<22:55:45,  1.37s/it]
  3%|▎         | 1869/61904 [42:45<23:12:25,  1.39s/it]
  3%|▎         | 1870/61904 [42:46<23:01:23,  1.38s/it]
  3%|▎         | 1871/61904 [42:47<22:35:18,  1.35s/it]
  3%|▎         | 1872/61904 [42:49<22:38:37,  1.36s/it]
  3%|▎         | 1873/61904 [42:50<22:59:07,  1.38s/it]
  3%|▎         | 1874/61904 [42:51<22:13:33,  1.33s/it]
  3%|▎         | 1875/61904 [42:53<21:46:54,  1.31s/it]
  3%|▎         | 1876/61904 [42:54<21:40:24,  1.30s/it]
  3%|▎         | 1877/61904 [42:55<22:14:52,  1.33s/it]
  3%|▎         | 1878/61904 [42:57<22:09:42,  1.33s/it]
  3%|▎         | 1879/61904 [42:58<22:01:31,  1.32s/it]
  3%|▎         | 1880/61904 [42:59<21:48:57,  1.31s/it]
                                                       
{'loss': 3.0818, 'learning_rate': 1.9727732399844417e-07, 'epoch': 0.49}

  3%|▎         | 1880/61904 [42:59<21:48:57,  1.31s/it]
  3%|▎         | 1881/61904 [43:00<21:36:46,  1.30s/it]
  3%|▎         | 1882/61904 [43:02<23:10:11,  1.39s/it]
  3%|▎         | 1883/61904 [43:03<22:47:02,  1.37s/it]
  3%|▎         | 1884/61904 [43:05<22:35:51,  1.36s/it]
  3%|▎         | 1885/61904 [43:06<23:08:38,  1.39s/it]
  3%|▎         | 1886/61904 [43:07<22:43:52,  1.36s/it]
  3%|▎         | 1887/61904 [43:09<22:54:50,  1.37s/it]
  3%|▎         | 1888/61904 [43:10<22:17:57,  1.34s/it]
  3%|▎         | 1889/61904 [43:11<22:05:07,  1.32s/it]
  3%|▎         | 1890/61904 [43:13<22:28:19,  1.35s/it]
  3%|▎         | 1891/61904 [43:14<22:35:53,  1.36s/it]
  3%|▎         | 1892/61904 [43:15<21:50:01,  1.31s/it]
  3%|▎         | 1893/61904 [43:17<22:06:59,  1.33s/it]
  3%|▎         | 1894/61904 [43:18<22:17:32,  1.34s/it]
  3%|▎         | 1895/61904 [43:19<22:10:27,  1.33s/it]
  3%|▎         | 1896/61904 [43:21<21:59:21,  1.32s/it]
  3%|▎         | 1897/61904 [43:22<22:14:51,  1.33s/it]
  3%|▎         | 1898/61904 [43:24<22:29:19,  1.35s/it]
  3%|▎         | 1899/61904 [43:25<22:12:45,  1.33s/it]
  3%|▎         | 1900/61904 [43:26<22:47:37,  1.37s/it]
                                                       
{'loss': 3.0955, 'learning_rate': 1.9724491118890186e-07, 'epoch': 0.49}

  3%|▎         | 1900/61904 [43:26<22:47:37,  1.37s/it]
  3%|▎         | 1901/61904 [43:28<22:32:28,  1.35s/it]
  3%|▎         | 1902/61904 [43:29<23:03:09,  1.38s/it]
  3%|▎         | 1903/61904 [43:30<22:39:10,  1.36s/it]
  3%|▎         | 1904/61904 [43:32<22:15:43,  1.34s/it]
  3%|▎         | 1905/61904 [43:33<22:07:59,  1.33s/it]
  3%|▎         | 1906/61904 [43:34<21:38:08,  1.30s/it]
  3%|▎         | 1907/61904 [43:35<21:24:34,  1.28s/it]
  3%|▎         | 1908/61904 [43:37<22:00:51,  1.32s/it]
  3%|▎         | 1909/61904 [43:38<22:05:28,  1.33s/it]
  3%|▎         | 1910/61904 [43:39<22:16:13,  1.34s/it]
  3%|▎         | 1911/61904 [43:41<22:45:11,  1.37s/it]
  3%|▎         | 1912/61904 [43:42<23:11:28,  1.39s/it]
  3%|▎         | 1913/61904 [43:44<22:29:12,  1.35s/it]
  3%|▎         | 1914/61904 [43:45<22:49:44,  1.37s/it]
  3%|▎         | 1915/61904 [43:46<23:07:38,  1.39s/it]
  3%|▎         | 1916/61904 [43:48<23:24:56,  1.41s/it]
  3%|▎         | 1917/61904 [43:49<23:14:29,  1.39s/it]
  3%|▎         | 1918/61904 [43:51<22:54:32,  1.37s/it]
  3%|▎         | 1919/61904 [43:52<23:32:59,  1.41s/it]
  3%|▎         | 1920/61904 [43:54<23:21:07,  1.40s/it]
                                                       
{'loss': 3.1134, 'learning_rate': 1.9721249837935952e-07, 'epoch': 0.5}

  3%|▎         | 1920/61904 [43:54<23:21:07,  1.40s/it]
  3%|▎         | 1921/61904 [43:55<23:30:01,  1.41s/it]
  3%|▎         | 1922/61904 [43:56<23:16:15,  1.40s/it]
  3%|▎         | 1923/61904 [43:58<24:27:42,  1.47s/it]
  3%|▎         | 1924/61904 [43:59<23:39:00,  1.42s/it]
  3%|▎         | 1925/61904 [44:01<23:06:17,  1.39s/it]
  3%|▎         | 1926/61904 [44:02<23:12:52,  1.39s/it]
  3%|▎         | 1927/61904 [44:04<24:21:10,  1.46s/it]
  3%|▎         | 1928/61904 [44:05<23:30:55,  1.41s/it]
  3%|▎         | 1929/61904 [44:06<23:09:07,  1.39s/it]
  3%|▎         | 1930/61904 [44:08<23:23:24,  1.40s/it]
  3%|▎         | 1931/61904 [44:09<23:05:41,  1.39s/it]
  3%|▎         | 1932/61904 [44:10<23:05:50,  1.39s/it]
  3%|▎         | 1933/61904 [44:12<23:20:13,  1.40s/it]
  3%|▎         | 1934/61904 [44:13<23:16:59,  1.40s/it]
  3%|▎         | 1935/61904 [44:15<22:52:44,  1.37s/it]
  3%|▎         | 1936/61904 [44:16<22:41:57,  1.36s/it]
  3%|▎         | 1937/61904 [44:17<22:20:21,  1.34s/it]
  3%|▎         | 1938/61904 [44:19<22:31:31,  1.35s/it]
  3%|▎         | 1939/61904 [44:20<22:24:33,  1.35s/it]
  3%|▎         | 1940/61904 [44:21<21:51:46,  1.31s/it]
                                                       
{'loss': 3.1444, 'learning_rate': 1.9718008556981718e-07, 'epoch': 0.5}

  3%|▎         | 1940/61904 [44:21<21:51:46,  1.31s/it]
  3%|▎         | 1941/61904 [44:22<22:11:01,  1.33s/it]
  3%|▎         | 1942/61904 [44:24<21:34:50,  1.30s/it]
  3%|▎         | 1943/61904 [44:25<22:49:55,  1.37s/it]
  3%|▎         | 1944/61904 [44:27<22:47:40,  1.37s/it]
  3%|▎         | 1945/61904 [44:28<22:57:42,  1.38s/it]
  3%|▎         | 1946/61904 [44:30<23:46:35,  1.43s/it]
  3%|▎         | 1947/61904 [44:31<22:59:36,  1.38s/it]
  3%|▎         | 1948/61904 [44:32<22:38:43,  1.36s/it]
  3%|▎         | 1949/61904 [44:33<22:12:52,  1.33s/it]
  3%|▎         | 1950/61904 [44:35<22:23:41,  1.34s/it]
  3%|▎         | 1951/61904 [44:36<23:01:43,  1.38s/it]
  3%|▎         | 1952/61904 [44:38<23:04:40,  1.39s/it]
  3%|▎         | 1953/61904 [44:39<22:26:16,  1.35s/it]
  3%|▎         | 1954/61904 [44:40<23:01:57,  1.38s/it]
  3%|▎         | 1955/61904 [44:42<23:00:17,  1.38s/it]
  3%|▎         | 1956/61904 [44:43<22:39:21,  1.36s/it]
  3%|▎         | 1957/61904 [44:44<22:02:49,  1.32s/it]
  3%|▎         | 1958/61904 [44:46<22:29:13,  1.35s/it]
  3%|▎         | 1959/61904 [44:47<23:22:43,  1.40s/it]
  3%|▎         | 1960/61904 [44:49<22:50:02,  1.37s/it]
                                                       
{'loss': 3.1412, 'learning_rate': 1.9714767276027487e-07, 'epoch': 0.51}

  3%|▎         | 1960/61904 [44:49<22:50:02,  1.37s/it]
  3%|▎         | 1961/61904 [44:50<22:29:00,  1.35s/it]
  3%|▎         | 1962/61904 [44:51<22:44:01,  1.37s/it]
  3%|▎         | 1963/61904 [44:53<22:53:46,  1.38s/it]
  3%|▎         | 1964/61904 [44:54<22:36:34,  1.36s/it]
  3%|▎         | 1965/61904 [44:55<22:11:54,  1.33s/it]
  3%|▎         | 1966/61904 [44:57<22:24:33,  1.35s/it]
  3%|▎         | 1967/61904 [44:58<21:55:28,  1.32s/it]
  3%|▎         | 1968/61904 [44:59<21:53:00,  1.31s/it]
  3%|▎         | 1969/61904 [45:00<21:02:15,  1.26s/it]
  3%|▎         | 1970/61904 [45:02<21:34:50,  1.30s/it]
  3%|▎         | 1971/61904 [45:03<21:46:31,  1.31s/it]
  3%|▎         | 1972/61904 [45:04<22:25:28,  1.35s/it]
  3%|▎         | 1973/61904 [45:06<21:56:55,  1.32s/it]
  3%|▎         | 1974/61904 [45:07<22:39:23,  1.36s/it]
  3%|▎         | 1975/61904 [45:08<22:14:48,  1.34s/it]
  3%|▎         | 1976/61904 [45:10<21:50:09,  1.31s/it]
  3%|▎         | 1977/61904 [45:11<22:11:10,  1.33s/it]
  3%|▎         | 1978/61904 [45:12<21:17:15,  1.28s/it]
  3%|▎         | 1979/61904 [45:14<21:21:50,  1.28s/it]
  3%|▎         | 1980/61904 [45:15<22:24:41,  1.35s/it]
                                                       
{'loss': 3.1569, 'learning_rate': 1.971152599507325e-07, 'epoch': 0.51}

  3%|▎         | 1980/61904 [45:15<22:24:41,  1.35s/it]
  3%|▎         | 1981/61904 [45:16<21:53:20,  1.32s/it]
  3%|▎         | 1982/61904 [45:18<21:55:16,  1.32s/it]
  3%|▎         | 1983/61904 [45:19<21:59:18,  1.32s/it]
  3%|▎         | 1984/61904 [45:20<22:07:20,  1.33s/it]
  3%|▎         | 1985/61904 [45:22<22:55:22,  1.38s/it]
  3%|▎         | 1986/61904 [45:23<22:56:42,  1.38s/it]
  3%|▎         | 1987/61904 [45:25<23:48:09,  1.43s/it]
  3%|▎         | 1988/61904 [45:26<24:49:02,  1.49s/it]
  3%|▎         | 1989/61904 [45:28<24:04:30,  1.45s/it]
  3%|▎         | 1990/61904 [45:29<23:26:33,  1.41s/it]
  3%|▎         | 1991/61904 [45:30<23:11:16,  1.39s/it]
  3%|▎         | 1992/61904 [45:32<22:24:29,  1.35s/it]
  3%|▎         | 1993/61904 [45:33<22:45:54,  1.37s/it]
  3%|▎         | 1994/61904 [45:35<23:51:39,  1.43s/it]
  3%|▎         | 1995/61904 [45:36<23:02:45,  1.38s/it]
  3%|▎         | 1996/61904 [45:37<23:03:17,  1.39s/it]
  3%|▎         | 1997/61904 [45:38<22:20:07,  1.34s/it]
  3%|▎         | 1998/61904 [45:40<23:15:24,  1.40s/it]
  3%|▎         | 1999/61904 [45:41<22:50:17,  1.37s/it]
  3%|▎         | 2000/61904 [45:43<23:05:47,  1.39s/it]
                                                       
{'loss': 3.1235, 'learning_rate': 1.970828471411902e-07, 'epoch': 0.52}

  3%|▎         | 2000/61904 [45:43<23:05:47,  1.39s/it]
  3%|▎         | 2001/61904 [45:44<23:05:22,  1.39s/it]
  3%|▎         | 2002/61904 [45:46<23:06:10,  1.39s/it]
  3%|▎         | 2003/61904 [45:47<23:05:42,  1.39s/it]
  3%|▎         | 2004/61904 [45:48<22:33:06,  1.36s/it]
  3%|▎         | 2005/61904 [45:50<23:04:58,  1.39s/it]
  3%|▎         | 2006/61904 [45:51<22:18:44,  1.34s/it]
  3%|▎         | 2007/61904 [45:52<22:48:16,  1.37s/it]
  3%|▎         | 2008/61904 [45:54<23:01:25,  1.38s/it]
  3%|▎         | 2009/61904 [45:55<22:24:38,  1.35s/it]
  3%|▎         | 2010/61904 [45:56<22:24:42,  1.35s/it]
  3%|▎         | 2011/61904 [45:58<22:44:12,  1.37s/it]
  3%|▎         | 2012/61904 [45:59<21:58:52,  1.32s/it]
  3%|▎         | 2013/61904 [46:00<22:30:54,  1.35s/it]
  3%|▎         | 2014/61904 [46:02<22:41:11,  1.36s/it]
  3%|▎         | 2015/61904 [46:03<22:19:05,  1.34s/it]
  3%|▎         | 2016/61904 [46:04<22:29:27,  1.35s/it]
  3%|▎         | 2017/61904 [46:06<23:16:30,  1.40s/it]
  3%|▎         | 2018/61904 [46:07<23:00:11,  1.38s/it]
  3%|▎         | 2019/61904 [46:09<22:49:17,  1.37s/it]
  3%|▎         | 2020/61904 [46:10<22:48:48,  1.37s/it]
                                                       
{'loss': 3.0883, 'learning_rate': 1.9705043433164788e-07, 'epoch': 0.52}

  3%|▎         | 2020/61904 [46:10<22:48:48,  1.37s/it]
  3%|▎         | 2021/61904 [46:12<23:34:18,  1.42s/it]
  3%|▎         | 2022/61904 [46:13<22:39:36,  1.36s/it]
  3%|▎         | 2023/61904 [46:14<22:41:18,  1.36s/it]
  3%|▎         | 2024/61904 [46:16<22:51:36,  1.37s/it]
  3%|▎         | 2025/61904 [46:17<23:20:54,  1.40s/it]
  3%|▎         | 2026/61904 [46:18<22:40:01,  1.36s/it]
  3%|▎         | 2027/61904 [46:20<22:29:52,  1.35s/it]
  3%|▎         | 2028/61904 [46:21<22:04:34,  1.33s/it]
  3%|▎         | 2029/61904 [46:22<21:54:27,  1.32s/it]
  3%|▎         | 2030/61904 [46:23<21:48:43,  1.31s/it]
  3%|▎         | 2031/61904 [46:25<22:16:56,  1.34s/it]
  3%|▎         | 2032/61904 [46:26<22:47:25,  1.37s/it]
  3%|▎         | 2033/61904 [46:28<23:06:28,  1.39s/it]
  3%|▎         | 2034/61904 [46:29<23:40:05,  1.42s/it]
  3%|▎         | 2035/61904 [46:31<24:15:46,  1.46s/it]
  3%|▎         | 2036/61904 [46:32<24:11:09,  1.45s/it]
  3%|▎         | 2037/61904 [46:34<23:58:04,  1.44s/it]
  3%|▎         | 2038/61904 [46:35<23:07:05,  1.39s/it]
  3%|▎         | 2039/61904 [46:37<24:18:35,  1.46s/it]
  3%|▎         | 2040/61904 [46:38<23:28:58,  1.41s/it]
                                                       
{'loss': 3.0439, 'learning_rate': 1.9701802152210552e-07, 'epoch': 0.53}

  3%|▎         | 2040/61904 [46:38<23:28:58,  1.41s/it]
  3%|▎         | 2041/61904 [46:39<24:00:24,  1.44s/it]
  3%|▎         | 2042/61904 [46:41<23:32:09,  1.42s/it]
  3%|▎         | 2043/61904 [46:42<23:01:33,  1.38s/it]
  3%|▎         | 2044/61904 [46:43<23:11:27,  1.39s/it]
  3%|▎         | 2045/61904 [46:45<23:26:15,  1.41s/it]
  3%|▎         | 2046/61904 [46:46<23:24:22,  1.41s/it]
  3%|▎         | 2047/61904 [46:48<23:07:43,  1.39s/it]
  3%|▎         | 2048/61904 [46:49<22:46:23,  1.37s/it]
  3%|▎         | 2049/61904 [46:50<22:46:36,  1.37s/it]
  3%|▎         | 2050/61904 [46:52<23:07:29,  1.39s/it]
  3%|▎         | 2051/61904 [46:53<23:19:50,  1.40s/it]
  3%|▎         | 2052/61904 [46:55<24:02:50,  1.45s/it]
  3%|▎         | 2053/61904 [46:56<23:52:14,  1.44s/it]
  3%|▎         | 2054/61904 [46:58<23:59:45,  1.44s/it]
  3%|▎         | 2055/61904 [46:59<23:44:15,  1.43s/it]
  3%|▎         | 2056/61904 [47:00<23:18:29,  1.40s/it]
  3%|▎         | 2057/61904 [47:02<22:55:24,  1.38s/it]
  3%|▎         | 2058/61904 [47:03<23:26:54,  1.41s/it]
  3%|▎         | 2059/61904 [47:04<22:50:34,  1.37s/it]
  3%|▎         | 2060/61904 [47:06<22:50:20,  1.37s/it]
                                                       
{'loss': 3.0707, 'learning_rate': 1.969856087125632e-07, 'epoch': 0.53}

  3%|▎         | 2060/61904 [47:06<22:50:20,  1.37s/it]
  3%|▎         | 2061/61904 [47:07<22:56:13,  1.38s/it]
  3%|▎         | 2062/61904 [47:09<22:49:25,  1.37s/it]
  3%|▎         | 2063/61904 [47:10<23:21:11,  1.40s/it]
  3%|▎         | 2064/61904 [47:12<23:44:58,  1.43s/it]
  3%|▎         | 2065/61904 [47:13<23:50:58,  1.43s/it]
  3%|▎         | 2066/61904 [47:14<23:57:34,  1.44s/it]
  3%|▎         | 2067/61904 [47:16<23:25:51,  1.41s/it]
  3%|▎         | 2068/61904 [47:17<22:51:38,  1.38s/it]
  3%|▎         | 2069/61904 [47:18<22:25:59,  1.35s/it]
  3%|▎         | 2070/61904 [47:20<22:59:31,  1.38s/it]
  3%|▎         | 2071/61904 [47:21<22:01:47,  1.33s/it]
  3%|▎         | 2072/61904 [47:22<22:08:51,  1.33s/it]
  3%|▎         | 2073/61904 [47:24<21:42:15,  1.31s/it]
  3%|▎         | 2074/61904 [47:25<22:30:19,  1.35s/it]
  3%|▎         | 2075/61904 [47:27<23:11:12,  1.40s/it]
  3%|▎         | 2076/61904 [47:28<23:12:42,  1.40s/it]
  3%|▎         | 2077/61904 [47:29<22:37:44,  1.36s/it]
  3%|▎         | 2078/61904 [47:31<22:16:49,  1.34s/it]
  3%|▎         | 2079/61904 [47:32<22:31:29,  1.36s/it]
  3%|▎         | 2080/61904 [47:33<22:08:25,  1.33s/it]
                                                       
{'loss': 3.1062, 'learning_rate': 1.9695319590302087e-07, 'epoch': 0.54}

  3%|▎         | 2080/61904 [47:33<22:08:25,  1.33s/it]
  3%|▎         | 2081/61904 [47:35<22:06:48,  1.33s/it]
  3%|▎         | 2082/61904 [47:36<21:49:46,  1.31s/it]
  3%|▎         | 2083/61904 [47:37<22:22:12,  1.35s/it]
  3%|▎         | 2084/61904 [47:39<22:26:30,  1.35s/it]
  3%|▎         | 2085/61904 [47:40<22:14:07,  1.34s/it]
  3%|▎         | 2086/61904 [47:41<22:12:29,  1.34s/it]
  3%|▎         | 2087/61904 [47:43<21:53:15,  1.32s/it]
  3%|▎         | 2088/61904 [47:44<22:06:03,  1.33s/it]
  3%|▎         | 2089/61904 [47:45<22:06:31,  1.33s/it]
  3%|▎         | 2090/61904 [47:47<22:21:40,  1.35s/it]
  3%|▎         | 2091/61904 [47:48<22:19:39,  1.34s/it]
  3%|▎         | 2092/61904 [47:49<21:54:48,  1.32s/it]
  3%|▎         | 2093/61904 [47:51<22:00:08,  1.32s/it]
  3%|▎         | 2094/61904 [47:52<22:53:24,  1.38s/it]
  3%|▎         | 2095/61904 [47:53<22:09:16,  1.33s/it]
  3%|▎         | 2096/61904 [47:55<23:50:45,  1.44s/it]
  3%|▎         | 2097/61904 [47:56<23:55:17,  1.44s/it]
  3%|▎         | 2098/61904 [47:58<23:45:04,  1.43s/it]
  3%|▎         | 2099/61904 [47:59<23:17:26,  1.40s/it]
  3%|▎         | 2100/61904 [48:01<23:22:50,  1.41s/it]
                                                       
{'loss': 3.0252, 'learning_rate': 1.9692078309347853e-07, 'epoch': 0.54}

  3%|▎         | 2100/61904 [48:01<23:22:50,  1.41s/it]
  3%|▎         | 2101/61904 [48:02<23:22:58,  1.41s/it]
  3%|▎         | 2102/61904 [48:04<24:15:55,  1.46s/it]
  3%|▎         | 2103/61904 [48:05<23:23:30,  1.41s/it]
  3%|▎         | 2104/61904 [48:06<23:46:24,  1.43s/it]
  3%|▎         | 2105/61904 [48:08<23:16:54,  1.40s/it]
  3%|▎         | 2106/61904 [48:09<24:05:06,  1.45s/it]
  3%|▎         | 2107/61904 [48:11<24:13:39,  1.46s/it]
  3%|▎         | 2108/61904 [48:12<23:22:21,  1.41s/it]
  3%|▎         | 2109/61904 [48:13<23:10:07,  1.39s/it]
  3%|▎         | 2110/61904 [48:15<23:49:06,  1.43s/it]
  3%|▎         | 2111/61904 [48:16<23:01:04,  1.39s/it]
  3%|▎         | 2112/61904 [48:17<22:37:55,  1.36s/it]
  3%|▎         | 2113/61904 [48:19<23:19:42,  1.40s/it]
  3%|▎         | 2114/61904 [48:20<22:54:48,  1.38s/it]
  3%|▎         | 2115/61904 [48:22<22:45:32,  1.37s/it]
  3%|▎         | 2116/61904 [48:23<22:58:22,  1.38s/it]
  3%|▎         | 2117/61904 [48:24<22:09:31,  1.33s/it]
  3%|▎         | 2118/61904 [48:26<22:09:26,  1.33s/it]
  3%|▎         | 2119/61904 [48:27<22:39:32,  1.36s/it]
  3%|▎         | 2120/61904 [48:28<22:25:40,  1.35s/it]
                                                       
{'loss': 3.0621, 'learning_rate': 1.9688837028393622e-07, 'epoch': 0.55}

  3%|▎         | 2120/61904 [48:28<22:25:40,  1.35s/it]
  3%|▎         | 2121/61904 [48:30<22:34:44,  1.36s/it]
  3%|▎         | 2122/61904 [48:31<23:15:44,  1.40s/it]
  3%|▎         | 2123/61904 [48:33<23:30:24,  1.42s/it]
  3%|▎         | 2124/61904 [48:34<23:04:00,  1.39s/it]
  3%|▎         | 2125/61904 [48:35<22:46:31,  1.37s/it]
  3%|▎         | 2126/61904 [48:37<22:35:17,  1.36s/it]
  3%|▎         | 2127/61904 [48:38<22:30:44,  1.36s/it]
  3%|▎         | 2128/61904 [48:39<22:28:49,  1.35s/it]
  3%|▎         | 2129/61904 [48:41<22:37:28,  1.36s/it]
  3%|▎         | 2130/61904 [48:42<22:20:12,  1.35s/it]
  3%|▎         | 2131/61904 [48:43<22:02:11,  1.33s/it]
  3%|▎         | 2132/61904 [48:45<21:55:58,  1.32s/it]
  3%|▎         | 2133/61904 [48:46<22:21:53,  1.35s/it]
  3%|▎         | 2134/61904 [48:47<22:25:43,  1.35s/it]
  3%|▎         | 2135/61904 [48:49<22:54:42,  1.38s/it]
  3%|▎         | 2136/61904 [48:50<22:26:27,  1.35s/it]
  3%|▎         | 2137/61904 [48:51<22:27:17,  1.35s/it]
  3%|▎         | 2138/61904 [48:53<22:59:51,  1.39s/it]
  3%|▎         | 2139/61904 [48:54<23:00:43,  1.39s/it]
  3%|▎         | 2140/61904 [48:56<22:40:03,  1.37s/it]
                                                       
{'loss': 3.1098, 'learning_rate': 1.9685595747439388e-07, 'epoch': 0.55}

  3%|▎         | 2140/61904 [48:56<22:40:03,  1.37s/it]
  3%|▎         | 2141/61904 [48:57<22:30:01,  1.36s/it]
  3%|▎         | 2142/61904 [48:58<22:25:58,  1.35s/it]
  3%|▎         | 2143/61904 [49:00<22:39:30,  1.36s/it]
  3%|▎         | 2144/61904 [49:01<23:27:57,  1.41s/it]
  3%|▎         | 2145/61904 [49:03<23:33:11,  1.42s/it]
  3%|▎         | 2146/61904 [49:04<23:49:37,  1.44s/it]
  3%|▎         | 2147/61904 [49:05<23:05:50,  1.39s/it]
  3%|▎         | 2148/61904 [49:07<22:36:03,  1.36s/it]
  3%|▎         | 2149/61904 [49:08<22:21:57,  1.35s/it]
  3%|▎         | 2150/61904 [49:09<22:50:36,  1.38s/it]
  3%|▎         | 2151/61904 [49:11<21:45:50,  1.31s/it]
  3%|▎         | 2152/61904 [49:12<22:19:28,  1.35s/it]
  3%|▎         | 2153/61904 [49:14<22:53:46,  1.38s/it]
  3%|▎         | 2154/61904 [49:15<23:24:16,  1.41s/it]
  3%|▎         | 2155/61904 [49:16<23:27:51,  1.41s/it]
  3%|▎         | 2156/61904 [49:18<23:14:29,  1.40s/it]
  3%|▎         | 2157/61904 [49:19<23:26:31,  1.41s/it]
  3%|▎         | 2158/61904 [49:21<23:16:20,  1.40s/it]
  3%|▎         | 2159/61904 [49:22<23:56:48,  1.44s/it]
  3%|▎         | 2160/61904 [49:23<23:06:33,  1.39s/it]
                                                       
{'loss': 3.0647, 'learning_rate': 1.9682354466485154e-07, 'epoch': 0.56}

  3%|▎         | 2160/61904 [49:23<23:06:33,  1.39s/it]
  3%|▎         | 2161/61904 [49:25<23:18:15,  1.40s/it]
  3%|▎         | 2162/61904 [49:26<22:47:40,  1.37s/it]
  3%|▎         | 2163/61904 [49:28<22:47:04,  1.37s/it]
  3%|▎         | 2164/61904 [49:29<22:37:39,  1.36s/it]
  3%|▎         | 2165/61904 [49:30<22:00:11,  1.33s/it]
  3%|▎         | 2166/61904 [49:31<21:44:20,  1.31s/it]
  4%|▎         | 2167/61904 [49:33<22:38:17,  1.36s/it]
  4%|▎         | 2168/61904 [49:34<22:49:07,  1.38s/it]
  4%|▎         | 2169/61904 [49:36<23:00:44,  1.39s/it]
  4%|▎         | 2170/61904 [49:37<23:06:21,  1.39s/it]
  4%|▎         | 2171/61904 [49:39<23:23:42,  1.41s/it]
  4%|▎         | 2172/61904 [49:40<23:03:04,  1.39s/it]
  4%|▎         | 2173/61904 [49:41<22:33:35,  1.36s/it]
  4%|▎         | 2174/61904 [49:43<23:25:39,  1.41s/it]
  4%|▎         | 2175/61904 [49:44<22:09:07,  1.34s/it]
  4%|▎         | 2176/61904 [49:45<23:01:46,  1.39s/it]
  4%|▎         | 2177/61904 [49:47<22:56:31,  1.38s/it]
  4%|▎         | 2178/61904 [49:48<22:50:24,  1.38s/it]
  4%|▎         | 2179/61904 [49:49<22:28:54,  1.36s/it]
  4%|▎         | 2180/61904 [49:51<23:50:36,  1.44s/it]
                                                       
{'loss': 3.0435, 'learning_rate': 1.9679113185530923e-07, 'epoch': 0.56}

  4%|▎         | 2180/61904 [49:51<23:50:36,  1.44s/it]
  4%|▎         | 2181/61904 [49:52<23:09:42,  1.40s/it]
  4%|▎         | 2182/61904 [49:54<22:29:54,  1.36s/it]
  4%|▎         | 2183/61904 [49:55<22:00:20,  1.33s/it]
  4%|▎         | 2184/61904 [49:56<21:44:38,  1.31s/it]
  4%|▎         | 2185/61904 [49:58<22:21:31,  1.35s/it]
  4%|▎         | 2186/61904 [49:59<22:30:23,  1.36s/it]
  4%|▎         | 2187/61904 [50:00<23:05:37,  1.39s/it]
  4%|▎         | 2188/61904 [50:02<22:53:05,  1.38s/it]
  4%|▎         | 2189/61904 [50:03<22:51:31,  1.38s/it]
  4%|▎         | 2190/61904 [50:05<23:02:29,  1.39s/it]
  4%|▎         | 2191/61904 [50:06<23:15:13,  1.40s/it]
  4%|▎         | 2192/61904 [50:07<23:24:15,  1.41s/it]
  4%|▎         | 2193/61904 [50:09<23:27:28,  1.41s/it]
  4%|▎         | 2194/61904 [50:10<23:42:10,  1.43s/it]
  4%|▎         | 2195/61904 [50:12<23:47:59,  1.43s/it]
  4%|▎         | 2196/61904 [50:13<23:31:20,  1.42s/it]
  4%|▎         | 2197/61904 [50:14<23:03:15,  1.39s/it]
  4%|▎         | 2198/61904 [50:16<22:19:25,  1.35s/it]
  4%|▎         | 2199/61904 [50:17<21:49:25,  1.32s/it]
  4%|▎         | 2200/61904 [50:18<22:00:18,  1.33s/it]
                                                       
{'loss': 3.0728, 'learning_rate': 1.9675871904576687e-07, 'epoch': 0.57}

  4%|▎         | 2200/61904 [50:18<22:00:18,  1.33s/it]
  4%|▎         | 2201/61904 [50:20<22:24:00,  1.35s/it]
  4%|▎         | 2202/61904 [50:21<22:05:28,  1.33s/it]
  4%|▎         | 2203/61904 [50:22<21:49:06,  1.32s/it]
  4%|▎         | 2204/61904 [50:24<21:27:03,  1.29s/it]
  4%|▎         | 2205/61904 [50:25<21:54:13,  1.32s/it]
  4%|▎         | 2206/61904 [50:26<21:52:27,  1.32s/it]
  4%|▎         | 2207/61904 [50:28<21:44:04,  1.31s/it]
  4%|▎         | 2208/61904 [50:29<22:13:20,  1.34s/it]
  4%|▎         | 2209/61904 [50:30<21:40:25,  1.31s/it]
  4%|▎         | 2210/61904 [50:31<21:32:21,  1.30s/it]
  4%|▎         | 2211/61904 [50:33<22:06:15,  1.33s/it]
  4%|▎         | 2212/61904 [50:34<21:55:59,  1.32s/it]
  4%|▎         | 2213/61904 [50:35<22:00:18,  1.33s/it]
  4%|▎         | 2214/61904 [50:37<22:03:38,  1.33s/it]
  4%|▎         | 2215/61904 [50:38<22:28:12,  1.36s/it]
  4%|▎         | 2216/61904 [50:40<23:28:25,  1.42s/it]
  4%|▎         | 2217/61904 [50:41<23:37:51,  1.43s/it]
  4%|▎         | 2218/61904 [50:43<23:05:03,  1.39s/it]
  4%|▎         | 2219/61904 [50:44<22:46:30,  1.37s/it]
  4%|▎         | 2220/61904 [50:45<23:35:00,  1.42s/it]
                                                       
{'loss': 3.1617, 'learning_rate': 1.9672630623622455e-07, 'epoch': 0.57}

  4%|▎         | 2220/61904 [50:45<23:35:00,  1.42s/it]
  4%|▎         | 2221/61904 [50:47<23:18:20,  1.41s/it]
  4%|▎         | 2222/61904 [50:48<23:02:35,  1.39s/it]
  4%|▎         | 2223/61904 [50:49<22:38:32,  1.37s/it]
  4%|▎         | 2224/61904 [50:51<22:20:50,  1.35s/it]
  4%|▎         | 2225/61904 [50:52<22:05:37,  1.33s/it]
  4%|▎         | 2226/61904 [50:54<22:40:50,  1.37s/it]
  4%|▎         | 2227/61904 [50:55<24:00:02,  1.45s/it]
  4%|▎         | 2228/61904 [50:56<23:32:18,  1.42s/it]
  4%|▎         | 2229/61904 [50:58<23:22:02,  1.41s/it]
  4%|▎         | 2230/61904 [50:59<22:49:19,  1.38s/it]
  4%|▎         | 2231/61904 [51:00<21:53:17,  1.32s/it]
  4%|▎         | 2232/61904 [51:02<22:01:48,  1.33s/it]
  4%|▎         | 2233/61904 [51:03<22:32:25,  1.36s/it]
  4%|▎         | 2234/61904 [51:05<22:45:29,  1.37s/it]
  4%|▎         | 2235/61904 [51:06<22:33:50,  1.36s/it]
  4%|▎         | 2236/61904 [51:07<22:43:50,  1.37s/it]
  4%|▎         | 2237/61904 [51:09<22:45:55,  1.37s/it]
  4%|▎         | 2238/61904 [51:10<22:23:13,  1.35s/it]
  4%|▎         | 2239/61904 [51:11<22:34:52,  1.36s/it]
  4%|▎         | 2240/61904 [51:13<22:49:41,  1.38s/it]
                                                       
{'loss': 3.1428, 'learning_rate': 1.9669389342668222e-07, 'epoch': 0.58}

  4%|▎         | 2240/61904 [51:13<22:49:41,  1.38s/it]
  4%|▎         | 2241/61904 [51:14<23:37:34,  1.43s/it]
  4%|▎         | 2242/61904 [51:16<24:26:45,  1.48s/it]
  4%|▎         | 2243/61904 [51:17<23:34:08,  1.42s/it]
  4%|▎         | 2244/61904 [51:19<23:14:10,  1.40s/it]
  4%|▎         | 2245/61904 [51:20<23:19:11,  1.41s/it]
  4%|▎         | 2246/61904 [51:21<22:55:41,  1.38s/it]
  4%|▎         | 2247/61904 [51:23<22:48:16,  1.38s/it]
  4%|▎         | 2248/61904 [51:24<22:40:22,  1.37s/it]
  4%|▎         | 2249/61904 [51:25<22:21:42,  1.35s/it]
  4%|▎         | 2250/61904 [51:27<22:04:45,  1.33s/it]
  4%|▎         | 2251/61904 [51:28<22:42:09,  1.37s/it]
  4%|▎         | 2252/61904 [51:30<23:07:09,  1.40s/it]
  4%|▎         | 2253/61904 [51:31<23:24:48,  1.41s/it]
  4%|▎         | 2254/61904 [51:32<22:51:38,  1.38s/it]
  4%|▎         | 2255/61904 [51:34<23:55:37,  1.44s/it]
  4%|▎         | 2256/61904 [51:35<23:49:04,  1.44s/it]
  4%|▎         | 2257/61904 [51:37<22:56:23,  1.38s/it]
  4%|▎         | 2258/61904 [51:38<23:06:03,  1.39s/it]
  4%|▎         | 2259/61904 [51:39<23:03:38,  1.39s/it]
  4%|▎         | 2260/61904 [51:41<22:43:09,  1.37s/it]
                                                       
{'loss': 3.0638, 'learning_rate': 1.9666148061713988e-07, 'epoch': 0.58}

  4%|▎         | 2260/61904 [51:41<22:43:09,  1.37s/it]
  4%|▎         | 2261/61904 [51:42<22:00:21,  1.33s/it]
  4%|▎         | 2262/61904 [51:43<21:59:47,  1.33s/it]
  4%|▎         | 2263/61904 [51:45<21:56:03,  1.32s/it]
  4%|▎         | 2264/61904 [51:46<22:22:23,  1.35s/it]
  4%|▎         | 2265/61904 [51:47<22:18:02,  1.35s/it]
  4%|▎         | 2266/61904 [51:49<22:16:48,  1.34s/it]
  4%|▎         | 2267/61904 [51:50<22:42:43,  1.37s/it]
  4%|▎         | 2268/61904 [51:51<22:35:13,  1.36s/it]
  4%|▎         | 2269/61904 [51:53<22:09:43,  1.34s/it]
  4%|▎         | 2270/61904 [51:54<22:31:32,  1.36s/it]
  4%|▎         | 2271/61904 [51:55<22:32:41,  1.36s/it]
  4%|▎         | 2272/61904 [51:57<22:32:11,  1.36s/it]
  4%|▎         | 2273/61904 [51:58<21:42:29,  1.31s/it]
  4%|▎         | 2274/61904 [51:59<21:54:21,  1.32s/it]
  4%|▎         | 2275/61904 [52:01<22:15:59,  1.34s/it]
  4%|▎         | 2276/61904 [52:02<22:36:34,  1.37s/it]
  4%|▎         | 2277/61904 [52:03<21:57:28,  1.33s/it]
  4%|▎         | 2278/61904 [52:05<22:12:03,  1.34s/it]
  4%|▎         | 2279/61904 [52:06<22:14:58,  1.34s/it]
  4%|▎         | 2280/61904 [52:07<21:59:04,  1.33s/it]
                                                       
{'loss': 3.0397, 'learning_rate': 1.9662906780759757e-07, 'epoch': 0.59}

  4%|▎         | 2280/61904 [52:07<21:59:04,  1.33s/it]
  4%|▎         | 2281/61904 [52:09<21:58:51,  1.33s/it]
  4%|▎         | 2282/61904 [52:10<22:53:46,  1.38s/it]
  4%|▎         | 2283/61904 [52:12<22:26:49,  1.36s/it]
  4%|▎         | 2284/61904 [52:13<22:25:32,  1.35s/it]
  4%|▎         | 2285/61904 [52:14<22:33:27,  1.36s/it]
  4%|▎         | 2286/61904 [52:16<22:17:11,  1.35s/it]
  4%|▎         | 2287/61904 [52:17<22:11:38,  1.34s/it]
  4%|▎         | 2288/61904 [52:18<22:23:34,  1.35s/it]
  4%|▎         | 2289/61904 [52:20<22:12:15,  1.34s/it]
  4%|▎         | 2290/61904 [52:21<22:42:24,  1.37s/it]
  4%|▎         | 2291/61904 [52:22<22:19:07,  1.35s/it]
  4%|▎         | 2292/61904 [52:24<22:52:39,  1.38s/it]
  4%|▎         | 2293/61904 [52:25<23:04:44,  1.39s/it]
  4%|▎         | 2294/61904 [52:27<22:51:19,  1.38s/it]
  4%|▎         | 2295/61904 [52:28<22:26:56,  1.36s/it]
  4%|▎         | 2296/61904 [52:29<21:49:14,  1.32s/it]
  4%|▎         | 2297/61904 [52:30<21:37:50,  1.31s/it]
  4%|▎         | 2298/61904 [52:32<22:42:35,  1.37s/it]
  4%|▎         | 2299/61904 [52:33<23:03:15,  1.39s/it]
  4%|▎         | 2300/61904 [52:35<22:39:08,  1.37s/it]
                                                       
{'loss': 3.107, 'learning_rate': 1.9659665499805523e-07, 'epoch': 0.59}

  4%|▎         | 2300/61904 [52:35<22:39:08,  1.37s/it]
  4%|▎         | 2301/61904 [52:36<22:17:32,  1.35s/it]
  4%|▎         | 2302/61904 [52:37<22:57:32,  1.39s/it]
  4%|▎         | 2303/61904 [52:39<23:03:18,  1.39s/it]
  4%|▎         | 2304/61904 [52:40<23:26:53,  1.42s/it]
  4%|▎         | 2305/61904 [52:42<23:11:58,  1.40s/it]
  4%|▎         | 2306/61904 [52:43<23:15:59,  1.41s/it]
  4%|▎         | 2307/61904 [52:44<22:20:36,  1.35s/it]
  4%|▎         | 2308/61904 [52:46<22:25:22,  1.35s/it]
  4%|▎         | 2309/61904 [52:47<22:29:37,  1.36s/it]
  4%|▎         | 2310/61904 [52:48<22:42:59,  1.37s/it]
  4%|▎         | 2311/61904 [52:50<22:11:31,  1.34s/it]
  4%|▎         | 2312/61904 [52:51<22:22:01,  1.35s/it]
  4%|▎         | 2313/61904 [52:52<22:00:00,  1.33s/it]
  4%|▎         | 2314/61904 [52:54<21:40:23,  1.31s/it]
  4%|▎         | 2315/61904 [52:55<21:32:37,  1.30s/it]
  4%|▎         | 2316/61904 [52:56<21:53:24,  1.32s/it]
  4%|▎         | 2317/61904 [52:58<22:09:37,  1.34s/it]
  4%|▎         | 2318/61904 [52:59<21:55:16,  1.32s/it]
  4%|▎         | 2319/61904 [53:00<21:48:32,  1.32s/it]
  4%|▎         | 2320/61904 [53:02<22:41:40,  1.37s/it]
                                                       
{'loss': 3.0346, 'learning_rate': 1.965642421885129e-07, 'epoch': 0.6}

  4%|▎         | 2320/61904 [53:02<22:41:40,  1.37s/it]
  4%|▎         | 2321/61904 [53:03<23:23:27,  1.41s/it]
  4%|▍         | 2322/61904 [53:05<23:17:33,  1.41s/it]
  4%|▍         | 2323/61904 [53:06<23:10:47,  1.40s/it]
  4%|▍         | 2324/61904 [53:07<23:23:24,  1.41s/it]
  4%|▍         | 2325/61904 [53:09<23:01:57,  1.39s/it]
  4%|▍         | 2326/61904 [53:10<23:32:36,  1.42s/it]
  4%|▍         | 2327/61904 [53:12<24:01:31,  1.45s/it]
  4%|▍         | 2328/61904 [53:13<23:56:33,  1.45s/it]
  4%|▍         | 2329/61904 [53:15<24:00:18,  1.45s/it]
  4%|▍         | 2330/61904 [53:16<23:26:37,  1.42s/it]
  4%|▍         | 2331/61904 [53:17<23:20:09,  1.41s/it]
  4%|▍         | 2332/61904 [53:19<23:27:21,  1.42s/it]
  4%|▍         | 2333/61904 [53:20<23:28:04,  1.42s/it]
  4%|▍         | 2334/61904 [53:22<23:08:52,  1.40s/it]
  4%|▍         | 2335/61904 [53:23<22:34:24,  1.36s/it]
  4%|▍         | 2336/61904 [53:24<22:19:37,  1.35s/it]
  4%|▍         | 2337/61904 [53:26<22:09:28,  1.34s/it]
  4%|▍         | 2338/61904 [53:27<22:41:55,  1.37s/it]
  4%|▍         | 2339/61904 [53:28<22:38:30,  1.37s/it]
  4%|▍         | 2340/61904 [53:30<22:14:18,  1.34s/it]
                                                       
{'loss': 3.129, 'learning_rate': 1.9653182937897058e-07, 'epoch': 0.6}

  4%|▍         | 2340/61904 [53:30<22:14:18,  1.34s/it]
  4%|▍         | 2341/61904 [53:31<21:50:18,  1.32s/it]
  4%|▍         | 2342/61904 [53:32<21:36:22,  1.31s/it]
  4%|▍         | 2343/61904 [53:33<20:51:10,  1.26s/it]
  4%|▍         | 2344/61904 [53:35<20:52:52,  1.26s/it]
  4%|▍         | 2345/61904 [53:36<21:13:06,  1.28s/it]
  4%|▍         | 2346/61904 [53:37<22:09:51,  1.34s/it]
  4%|▍         | 2347/61904 [53:39<22:14:55,  1.34s/it]
  4%|▍         | 2348/61904 [53:40<21:52:17,  1.32s/it]
  4%|▍         | 2349/61904 [53:41<22:07:53,  1.34s/it]
  4%|▍         | 2350/61904 [53:43<22:25:03,  1.36s/it]
  4%|▍         | 2351/61904 [53:44<22:20:22,  1.35s/it]
  4%|▍         | 2352/61904 [53:46<22:18:46,  1.35s/it]
  4%|▍         | 2353/61904 [53:47<22:01:00,  1.33s/it]
  4%|▍         | 2354/61904 [53:48<23:13:01,  1.40s/it]
  4%|▍         | 2355/61904 [53:50<22:39:57,  1.37s/it]
  4%|▍         | 2356/61904 [53:51<22:25:26,  1.36s/it]
  4%|▍         | 2357/61904 [53:52<22:12:30,  1.34s/it]
  4%|▍         | 2358/61904 [53:54<22:24:08,  1.35s/it]
  4%|▍         | 2359/61904 [53:55<22:19:16,  1.35s/it]
  4%|▍         | 2360/61904 [53:57<22:55:49,  1.39s/it]
                                                       
{'loss': 3.1397, 'learning_rate': 1.9649941656942821e-07, 'epoch': 0.61}

  4%|▍         | 2360/61904 [53:57<22:55:49,  1.39s/it]
  4%|▍         | 2361/61904 [53:58<22:52:57,  1.38s/it]
  4%|▍         | 2362/61904 [53:59<22:21:54,  1.35s/it]
  4%|▍         | 2363/61904 [54:01<22:40:54,  1.37s/it]
  4%|▍         | 2364/61904 [54:02<22:49:33,  1.38s/it]
  4%|▍         | 2365/61904 [54:03<22:34:14,  1.36s/it]
  4%|▍         | 2366/61904 [54:05<22:17:20,  1.35s/it]
  4%|▍         | 2367/61904 [54:06<22:30:14,  1.36s/it]
  4%|▍         | 2368/61904 [54:07<22:07:15,  1.34s/it]
  4%|▍         | 2369/61904 [54:09<21:44:11,  1.31s/it]
  4%|▍         | 2370/61904 [54:10<22:08:37,  1.34s/it]
  4%|▍         | 2371/61904 [54:11<22:13:45,  1.34s/it]
  4%|▍         | 2372/61904 [54:13<21:58:46,  1.33s/it]
  4%|▍         | 2373/61904 [54:14<22:29:41,  1.36s/it]
  4%|▍         | 2374/61904 [54:16<23:00:25,  1.39s/it]
  4%|▍         | 2375/61904 [54:17<23:12:55,  1.40s/it]
  4%|▍         | 2376/61904 [54:18<23:40:33,  1.43s/it]
  4%|▍         | 2377/61904 [54:20<23:41:26,  1.43s/it]
  4%|▍         | 2378/61904 [54:21<22:48:58,  1.38s/it]
  4%|▍         | 2379/61904 [54:23<22:53:32,  1.38s/it]
  4%|▍         | 2380/61904 [54:24<23:29:29,  1.42s/it]
                                                       
{'loss': 3.1279, 'learning_rate': 1.964670037598859e-07, 'epoch': 0.62}

  4%|▍         | 2380/61904 [54:24<23:29:29,  1.42s/it]
  4%|▍         | 2381/61904 [54:25<23:22:56,  1.41s/it]
  4%|▍         | 2382/61904 [54:27<22:48:48,  1.38s/it]
  4%|▍         | 2383/61904 [54:28<22:31:28,  1.36s/it]
  4%|▍         | 2384/61904 [54:29<22:03:43,  1.33s/it]
  4%|▍         | 2385/61904 [54:31<22:17:09,  1.35s/it]
  4%|▍         | 2386/61904 [54:32<22:00:17,  1.33s/it]
  4%|▍         | 2387/61904 [54:33<22:17:19,  1.35s/it]
  4%|▍         | 2388/61904 [54:35<22:21:36,  1.35s/it]
  4%|▍         | 2389/61904 [54:36<22:29:30,  1.36s/it]
  4%|▍         | 2390/61904 [54:38<22:36:56,  1.37s/it]
  4%|▍         | 2391/61904 [54:39<22:21:13,  1.35s/it]
  4%|▍         | 2392/61904 [54:40<21:47:08,  1.32s/it]
  4%|▍         | 2393/61904 [54:41<21:12:48,  1.28s/it]
  4%|▍         | 2394/61904 [54:43<22:05:06,  1.34s/it]
  4%|▍         | 2395/61904 [54:44<22:05:06,  1.34s/it]
  4%|▍         | 2396/61904 [54:45<22:14:45,  1.35s/it]
  4%|▍         | 2397/61904 [54:47<22:37:22,  1.37s/it]
  4%|▍         | 2398/61904 [54:48<23:11:53,  1.40s/it]
  4%|▍         | 2399/61904 [54:50<23:41:49,  1.43s/it]
  4%|▍         | 2400/61904 [54:51<22:45:23,  1.38s/it]
                                                       
{'loss': 3.0967, 'learning_rate': 1.9643459095034356e-07, 'epoch': 0.62}

  4%|▍         | 2400/61904 [54:51<22:45:23,  1.38s/it]
  4%|▍         | 2401/61904 [54:52<21:47:10,  1.32s/it]
  4%|▍         | 2402/61904 [54:54<21:53:31,  1.32s/it]
  4%|▍         | 2403/61904 [54:55<21:49:16,  1.32s/it]
  4%|▍         | 2404/61904 [54:56<21:44:27,  1.32s/it]
  4%|▍         | 2405/61904 [54:57<21:35:28,  1.31s/it]
  4%|▍         | 2406/61904 [54:59<21:32:17,  1.30s/it]
  4%|▍         | 2407/61904 [55:00<22:00:18,  1.33s/it]
  4%|▍         | 2408/61904 [55:01<21:46:22,  1.32s/it]
  4%|▍         | 2409/61904 [55:03<21:59:43,  1.33s/it]
  4%|▍         | 2410/61904 [55:04<21:59:14,  1.33s/it]
  4%|▍         | 2411/61904 [55:05<21:27:45,  1.30s/it]
  4%|▍         | 2412/61904 [55:07<21:25:30,  1.30s/it]
  4%|▍         | 2413/61904 [55:08<21:18:46,  1.29s/it]
  4%|▍         | 2414/61904 [55:09<21:38:43,  1.31s/it]
  4%|▍         | 2415/61904 [55:11<22:16:58,  1.35s/it]
  4%|▍         | 2416/61904 [55:12<22:03:36,  1.34s/it]
  4%|▍         | 2417/61904 [55:13<21:59:51,  1.33s/it]
  4%|▍         | 2418/61904 [55:15<22:25:52,  1.36s/it]
  4%|▍         | 2419/61904 [55:16<22:56:36,  1.39s/it]
  4%|▍         | 2420/61904 [55:18<22:15:42,  1.35s/it]
                                                       
{'loss': 3.1463, 'learning_rate': 1.9640217814080123e-07, 'epoch': 0.63}

  4%|▍         | 2420/61904 [55:18<22:15:42,  1.35s/it]
  4%|▍         | 2421/61904 [55:19<22:22:30,  1.35s/it]
  4%|▍         | 2422/61904 [55:20<22:32:04,  1.36s/it]
  4%|▍         | 2423/61904 [55:22<23:07:01,  1.40s/it]
  4%|▍         | 2424/61904 [55:23<22:24:57,  1.36s/it]
  4%|▍         | 2425/61904 [55:25<23:24:47,  1.42s/it]
  4%|▍         | 2426/61904 [55:26<23:05:50,  1.40s/it]
  4%|▍         | 2427/61904 [55:27<22:47:43,  1.38s/it]
  4%|▍         | 2428/61904 [55:29<23:48:46,  1.44s/it]
  4%|▍         | 2429/61904 [55:30<23:28:01,  1.42s/it]
  4%|▍         | 2430/61904 [55:32<23:03:33,  1.40s/it]
  4%|▍         | 2431/61904 [55:33<22:59:55,  1.39s/it]
  4%|▍         | 2432/61904 [55:34<22:48:00,  1.38s/it]
  4%|▍         | 2433/61904 [55:36<22:14:00,  1.35s/it]
  4%|▍         | 2434/61904 [55:37<22:53:55,  1.39s/it]
  4%|▍         | 2435/61904 [55:38<23:06:43,  1.40s/it]
  4%|▍         | 2436/61904 [55:40<22:43:08,  1.38s/it]
  4%|▍         | 2437/61904 [55:41<22:22:37,  1.35s/it]
  4%|▍         | 2438/61904 [55:42<22:34:22,  1.37s/it]
  4%|▍         | 2439/61904 [55:44<22:28:19,  1.36s/it]
  4%|▍         | 2440/61904 [55:45<23:34:48,  1.43s/it]
                                                       
{'loss': 3.1406, 'learning_rate': 1.9636976533125891e-07, 'epoch': 0.63}

  4%|▍         | 2440/61904 [55:45<23:34:48,  1.43s/it]
  4%|▍         | 2441/61904 [55:47<22:53:50,  1.39s/it]
  4%|▍         | 2442/61904 [55:48<23:11:00,  1.40s/it]
  4%|▍         | 2443/61904 [55:49<22:42:36,  1.37s/it]
  4%|▍         | 2444/61904 [55:51<22:36:16,  1.37s/it]
  4%|▍         | 2445/61904 [55:52<21:51:18,  1.32s/it]
  4%|▍         | 2446/61904 [55:53<22:28:57,  1.36s/it]
  4%|▍         | 2447/61904 [55:55<21:59:22,  1.33s/it]
  4%|▍         | 2448/61904 [55:56<22:39:38,  1.37s/it]
  4%|▍         | 2449/61904 [55:58<22:41:05,  1.37s/it]
  4%|▍         | 2450/61904 [55:59<22:35:06,  1.37s/it]
  4%|▍         | 2451/61904 [56:00<22:32:48,  1.37s/it]
  4%|▍         | 2452/61904 [56:02<22:15:16,  1.35s/it]
  4%|▍         | 2453/61904 [56:03<22:30:43,  1.36s/it]
  4%|▍         | 2454/61904 [56:04<22:18:53,  1.35s/it]
  4%|▍         | 2455/61904 [56:06<22:33:42,  1.37s/it]
  4%|▍         | 2456/61904 [56:07<22:20:37,  1.35s/it]
  4%|▍         | 2457/61904 [56:09<23:02:16,  1.40s/it]
  4%|▍         | 2458/61904 [56:10<23:04:00,  1.40s/it]
  4%|▍         | 2459/61904 [56:11<23:03:02,  1.40s/it]
  4%|▍         | 2460/61904 [56:13<23:11:05,  1.40s/it]
                                                       
{'loss': 3.082, 'learning_rate': 1.9633735252171658e-07, 'epoch': 0.64}

  4%|▍         | 2460/61904 [56:13<23:11:05,  1.40s/it]
  4%|▍         | 2461/61904 [56:14<23:19:15,  1.41s/it]
  4%|▍         | 2462/61904 [56:16<23:15:00,  1.41s/it]
  4%|▍         | 2463/61904 [56:17<23:16:38,  1.41s/it]
  4%|▍         | 2464/61904 [56:18<23:26:11,  1.42s/it]
  4%|▍         | 2465/61904 [56:20<22:54:01,  1.39s/it]
  4%|▍         | 2466/61904 [56:21<22:31:55,  1.36s/it]
  4%|▍         | 2467/61904 [56:23<23:11:33,  1.40s/it]
  4%|▍         | 2468/61904 [56:24<24:35:31,  1.49s/it]
  4%|▍         | 2469/61904 [56:26<23:39:36,  1.43s/it]
  4%|▍         | 2470/61904 [56:27<22:54:05,  1.39s/it]
  4%|▍         | 2471/61904 [56:28<22:48:26,  1.38s/it]
  4%|▍         | 2472/61904 [56:30<22:26:16,  1.36s/it]
  4%|▍         | 2473/61904 [56:31<23:09:12,  1.40s/it]
  4%|▍         | 2474/61904 [56:32<22:31:53,  1.36s/it]
  4%|▍         | 2475/61904 [56:34<22:39:05,  1.37s/it]
  4%|▍         | 2476/61904 [56:35<21:55:10,  1.33s/it]
  4%|▍         | 2477/61904 [56:36<21:43:28,  1.32s/it]
  4%|▍         | 2478/61904 [56:38<21:58:39,  1.33s/it]
  4%|▍         | 2479/61904 [56:39<21:27:28,  1.30s/it]
  4%|▍         | 2480/61904 [56:40<21:41:04,  1.31s/it]
                                                       
{'loss': 3.1255, 'learning_rate': 1.9630493971217424e-07, 'epoch': 0.64}

  4%|▍         | 2480/61904 [56:40<21:41:04,  1.31s/it]
  4%|▍         | 2481/61904 [56:41<21:33:20,  1.31s/it]
  4%|▍         | 2482/61904 [56:43<21:56:39,  1.33s/it]
  4%|▍         | 2483/61904 [56:44<22:46:24,  1.38s/it]
  4%|▍         | 2484/61904 [56:46<22:11:46,  1.34s/it]
  4%|▍         | 2485/61904 [56:47<21:51:30,  1.32s/it]
  4%|▍         | 2486/61904 [56:48<22:21:31,  1.35s/it]
  4%|▍         | 2487/61904 [56:49<21:43:11,  1.32s/it]
  4%|▍         | 2488/61904 [56:51<21:37:38,  1.31s/it]
  4%|▍         | 2489/61904 [56:52<21:54:41,  1.33s/it]
  4%|▍         | 2490/61904 [56:54<21:59:28,  1.33s/it]
  4%|▍         | 2491/61904 [56:55<21:52:04,  1.33s/it]
  4%|▍         | 2492/61904 [56:56<22:07:47,  1.34s/it]
  4%|▍         | 2493/61904 [56:58<22:39:57,  1.37s/it]
  4%|▍         | 2494/61904 [56:59<23:38:24,  1.43s/it]
  4%|▍         | 2495/61904 [57:01<23:34:22,  1.43s/it]
  4%|▍         | 2496/61904 [57:02<23:00:57,  1.39s/it]
  4%|▍         | 2497/61904 [57:03<23:05:11,  1.40s/it]
  4%|▍         | 2498/61904 [57:05<23:01:33,  1.40s/it]
  4%|▍         | 2499/61904 [57:06<24:22:19,  1.48s/it]
  4%|▍         | 2500/61904 [57:08<24:13:22,  1.47s/it]
                                                       
{'loss': 3.1521, 'learning_rate': 1.9627252690263193e-07, 'epoch': 0.65}

  4%|▍         | 2500/61904 [57:08<24:13:22,  1.47s/it]
  4%|▍         | 2501/61904 [57:09<24:03:56,  1.46s/it]
  4%|▍         | 2502/61904 [57:11<23:17:16,  1.41s/it]
  4%|▍         | 2503/61904 [57:12<23:11:56,  1.41s/it]
  4%|▍         | 2504/61904 [57:13<23:13:53,  1.41s/it]
  4%|▍         | 2505/61904 [57:15<23:08:35,  1.40s/it]
  4%|▍         | 2506/61904 [57:16<23:50:50,  1.45s/it]
  4%|▍         | 2507/61904 [57:18<23:18:43,  1.41s/it]
  4%|▍         | 2508/61904 [57:19<22:14:12,  1.35s/it]
  4%|▍         | 2509/61904 [57:20<22:52:11,  1.39s/it]
  4%|▍         | 2510/61904 [57:22<22:33:38,  1.37s/it]
  4%|▍         | 2511/61904 [57:23<22:58:59,  1.39s/it]
  4%|▍         | 2512/61904 [57:24<22:39:02,  1.37s/it]
  4%|▍         | 2513/61904 [57:26<22:09:33,  1.34s/it]
  4%|▍         | 2514/61904 [57:27<22:13:50,  1.35s/it]
  4%|▍         | 2515/61904 [57:28<21:55:07,  1.33s/it]
  4%|▍         | 2516/61904 [57:30<22:05:06,  1.34s/it]
  4%|▍         | 2517/61904 [57:31<22:02:02,  1.34s/it]
  4%|▍         | 2518/61904 [57:32<21:49:42,  1.32s/it]
  4%|▍         | 2519/61904 [57:34<22:00:18,  1.33s/it]
  4%|▍         | 2520/61904 [57:35<21:58:38,  1.33s/it]
                                                       
{'loss': 3.0601, 'learning_rate': 1.9624011409308956e-07, 'epoch': 0.65}

  4%|▍         | 2520/61904 [57:35<21:58:38,  1.33s/it]
  4%|▍         | 2521/61904 [57:37<23:01:18,  1.40s/it]
  4%|▍         | 2522/61904 [57:38<22:21:08,  1.36s/it]
  4%|▍         | 2523/61904 [57:39<22:18:57,  1.35s/it]
  4%|▍         | 2524/61904 [57:41<23:10:25,  1.40s/it]
  4%|▍         | 2525/61904 [57:42<23:06:35,  1.40s/it]
  4%|▍         | 2526/61904 [57:43<22:46:06,  1.38s/it]
  4%|▍         | 2527/61904 [57:45<22:48:28,  1.38s/it]
  4%|▍         | 2528/61904 [57:46<22:48:42,  1.38s/it]
  4%|▍         | 2529/61904 [57:47<22:21:41,  1.36s/it]
  4%|▍         | 2530/61904 [57:49<21:54:55,  1.33s/it]
  4%|▍         | 2531/61904 [57:50<22:21:26,  1.36s/it]
  4%|▍         | 2532/61904 [57:51<21:57:07,  1.33s/it]
  4%|▍         | 2533/61904 [57:53<22:06:06,  1.34s/it]
  4%|▍         | 2534/61904 [57:54<22:20:14,  1.35s/it]
  4%|▍         | 2535/61904 [57:56<23:02:26,  1.40s/it]
  4%|▍         | 2536/61904 [57:57<23:11:46,  1.41s/it]
  4%|▍         | 2537/61904 [57:58<22:53:12,  1.39s/it]
  4%|▍         | 2538/61904 [58:00<22:30:37,  1.37s/it]
  4%|▍         | 2539/61904 [58:01<22:03:48,  1.34s/it]
  4%|▍         | 2540/61904 [58:02<21:53:22,  1.33s/it]
                                                       
{'loss': 3.0209, 'learning_rate': 1.9620770128354725e-07, 'epoch': 0.66}

  4%|▍         | 2540/61904 [58:02<21:53:22,  1.33s/it]
  4%|▍         | 2541/61904 [58:04<21:46:03,  1.32s/it]
  4%|▍         | 2542/61904 [58:05<22:02:50,  1.34s/it]
  4%|▍         | 2543/61904 [58:06<22:07:30,  1.34s/it]
  4%|▍         | 2544/61904 [58:08<23:15:44,  1.41s/it]
  4%|▍         | 2545/61904 [58:09<22:34:06,  1.37s/it]
  4%|▍         | 2546/61904 [58:11<22:16:00,  1.35s/it]
  4%|▍         | 2547/61904 [58:12<22:19:18,  1.35s/it]
  4%|▍         | 2548/61904 [58:13<22:47:05,  1.38s/it]
  4%|▍         | 2549/61904 [58:15<22:15:04,  1.35s/it]
  4%|▍         | 2550/61904 [58:16<21:52:24,  1.33s/it]
  4%|▍         | 2551/61904 [58:17<21:47:36,  1.32s/it]
  4%|▍         | 2552/61904 [58:19<21:42:03,  1.32s/it]
  4%|▍         | 2553/61904 [58:20<22:31:50,  1.37s/it]
  4%|▍         | 2554/61904 [58:21<22:11:54,  1.35s/it]
  4%|▍         | 2555/61904 [58:23<21:46:11,  1.32s/it]
  4%|▍         | 2556/61904 [58:24<22:06:06,  1.34s/it]
  4%|▍         | 2557/61904 [58:25<22:09:57,  1.34s/it]
  4%|▍         | 2558/61904 [58:27<22:09:35,  1.34s/it]
  4%|▍         | 2559/61904 [58:28<22:57:34,  1.39s/it]
  4%|▍         | 2560/61904 [58:30<23:12:31,  1.41s/it]
                                                       
{'loss': 3.1306, 'learning_rate': 1.9617528847400494e-07, 'epoch': 0.66}

  4%|▍         | 2560/61904 [58:30<23:12:31,  1.41s/it]
  4%|▍         | 2561/61904 [58:31<22:43:00,  1.38s/it]
  4%|▍         | 2562/61904 [58:32<22:16:19,  1.35s/it]
  4%|▍         | 2563/61904 [58:34<22:43:19,  1.38s/it]
  4%|▍         | 2564/61904 [58:35<23:18:50,  1.41s/it]
  4%|▍         | 2565/61904 [58:36<22:55:17,  1.39s/it]
  4%|▍         | 2566/61904 [58:38<22:29:01,  1.36s/it]
  4%|▍         | 2567/61904 [58:39<22:00:03,  1.33s/it]
  4%|▍         | 2568/61904 [58:40<22:37:29,  1.37s/it]
  4%|▍         | 2569/61904 [58:42<22:12:18,  1.35s/it]
  4%|▍         | 2570/61904 [58:43<22:04:23,  1.34s/it]
  4%|▍         | 2571/61904 [58:44<22:03:47,  1.34s/it]
  4%|▍         | 2572/61904 [58:46<22:39:16,  1.37s/it]
  4%|▍         | 2573/61904 [58:47<21:52:05,  1.33s/it]
  4%|▍         | 2574/61904 [58:48<21:54:23,  1.33s/it]
  4%|▍         | 2575/61904 [58:50<22:13:32,  1.35s/it]
  4%|▍         | 2576/61904 [58:51<21:44:41,  1.32s/it]
  4%|▍         | 2577/61904 [58:52<21:40:22,  1.32s/it]
  4%|▍         | 2578/61904 [58:54<21:44:26,  1.32s/it]
  4%|▍         | 2579/61904 [58:55<21:53:07,  1.33s/it]
  4%|▍         | 2580/61904 [58:56<22:13:22,  1.35s/it]
                                                       
{'loss': 3.0942, 'learning_rate': 1.9614287566446257e-07, 'epoch': 0.67}

  4%|▍         | 2580/61904 [58:56<22:13:22,  1.35s/it]
  4%|▍         | 2581/61904 [58:58<22:00:13,  1.34s/it]
  4%|▍         | 2582/61904 [58:59<22:35:18,  1.37s/it]
  4%|▍         | 2583/61904 [59:01<22:30:44,  1.37s/it]
  4%|▍         | 2584/61904 [59:02<21:57:27,  1.33s/it]
  4%|▍         | 2585/61904 [59:03<22:47:01,  1.38s/it]
  4%|▍         | 2586/61904 [59:05<22:01:13,  1.34s/it]
  4%|▍         | 2587/61904 [59:06<21:57:52,  1.33s/it]
  4%|▍         | 2588/61904 [59:07<22:14:20,  1.35s/it]
  4%|▍         | 2589/61904 [59:09<23:05:33,  1.40s/it]
  4%|▍         | 2590/61904 [59:10<23:50:38,  1.45s/it]
  4%|▍         | 2591/61904 [59:12<23:07:32,  1.40s/it]
  4%|▍         | 2592/61904 [59:13<22:52:43,  1.39s/it]
  4%|▍         | 2593/61904 [59:15<23:29:19,  1.43s/it]
  4%|▍         | 2594/61904 [59:16<23:02:41,  1.40s/it]
  4%|▍         | 2595/61904 [59:17<22:38:13,  1.37s/it]
  4%|▍         | 2596/61904 [59:19<22:41:29,  1.38s/it]
  4%|▍         | 2597/61904 [59:20<22:50:21,  1.39s/it]
  4%|▍         | 2598/61904 [59:21<22:41:33,  1.38s/it]
  4%|▍         | 2599/61904 [59:23<23:24:39,  1.42s/it]
  4%|▍         | 2600/61904 [59:24<23:11:46,  1.41s/it]
                                                       
{'loss': 3.0927, 'learning_rate': 1.9611046285492026e-07, 'epoch': 0.67}

  4%|▍         | 2600/61904 [59:24<23:11:46,  1.41s/it]
  4%|▍         | 2601/61904 [59:25<22:23:42,  1.36s/it]
  4%|▍         | 2602/61904 [59:27<22:18:32,  1.35s/it]
  4%|▍         | 2603/61904 [59:28<21:52:22,  1.33s/it]
  4%|▍         | 2604/61904 [59:30<22:33:28,  1.37s/it]
  4%|▍         | 2605/61904 [59:31<22:46:02,  1.38s/it]
  4%|▍         | 2606/61904 [59:32<22:16:24,  1.35s/it]
  4%|▍         | 2607/61904 [59:34<22:52:39,  1.39s/it]
  4%|▍         | 2608/61904 [59:35<22:32:41,  1.37s/it]
  4%|▍         | 2609/61904 [59:36<22:45:30,  1.38s/it]
  4%|▍         | 2610/61904 [59:38<22:10:14,  1.35s/it]
  4%|▍         | 2611/61904 [59:39<22:02:14,  1.34s/it]
  4%|▍         | 2612/61904 [59:40<22:31:13,  1.37s/it]
  4%|▍         | 2613/61904 [59:42<22:01:02,  1.34s/it]
  4%|▍         | 2614/61904 [59:43<22:28:37,  1.36s/it]
  4%|▍         | 2615/61904 [59:44<21:55:46,  1.33s/it]
  4%|▍         | 2616/61904 [59:46<21:18:13,  1.29s/it]
  4%|▍         | 2617/61904 [59:47<22:10:58,  1.35s/it]
  4%|▍         | 2618/61904 [59:48<21:48:55,  1.32s/it]
  4%|▍         | 2619/61904 [59:50<21:38:02,  1.31s/it]
  4%|▍         | 2620/61904 [59:51<21:19:50,  1.30s/it]
                                                       
{'loss': 3.0501, 'learning_rate': 1.9607805004537792e-07, 'epoch': 0.68}

  4%|▍         | 2620/61904 [59:51<21:19:50,  1.30s/it]
  4%|▍         | 2621/61904 [59:52<21:21:27,  1.30s/it]
  4%|▍         | 2622/61904 [59:54<22:14:25,  1.35s/it]
  4%|▍         | 2623/61904 [59:55<22:37:21,  1.37s/it]
  4%|▍         | 2624/61904 [59:57<23:27:55,  1.43s/it]
  4%|▍         | 2625/61904 [59:58<23:24:13,  1.42s/it]
  4%|▍         | 2626/61904 [59:59<22:27:42,  1.36s/it]
  4%|▍         | 2627/61904 [1:00:01<22:59:47,  1.40s/it]
  4%|▍         | 2628/61904 [1:00:02<22:34:30,  1.37s/it]
  4%|▍         | 2629/61904 [1:00:03<22:18:41,  1.36s/it]
  4%|▍         | 2630/61904 [1:00:05<22:54:47,  1.39s/it]
  4%|▍         | 2631/61904 [1:00:06<23:03:28,  1.40s/it]
  4%|▍         | 2632/61904 [1:00:08<22:28:47,  1.37s/it]
  4%|▍         | 2633/61904 [1:00:09<22:06:35,  1.34s/it]
  4%|▍         | 2634/61904 [1:00:11<23:59:31,  1.46s/it]
  4%|▍         | 2635/61904 [1:00:12<23:27:24,  1.42s/it]
  4%|▍         | 2636/61904 [1:00:13<23:18:06,  1.42s/it]
  4%|▍         | 2637/61904 [1:00:15<22:27:44,  1.36s/it]
  4%|▍         | 2638/61904 [1:00:16<21:58:55,  1.34s/it]
  4%|▍         | 2639/61904 [1:00:17<22:38:25,  1.38s/it]
  4%|▍         | 2640/61904 [1:00:19<22:10:40,  1.35s/it]
                                                         
{'loss': 3.0339, 'learning_rate': 1.9604563723583559e-07, 'epoch': 0.68}

  4%|▍         | 2640/61904 [1:00:19<22:10:40,  1.35s/it]
  4%|▍         | 2641/61904 [1:00:20<22:11:55,  1.35s/it]
  4%|▍         | 2642/61904 [1:00:21<22:23:43,  1.36s/it]
  4%|▍         | 2643/61904 [1:00:23<22:48:37,  1.39s/it]
  4%|▍         | 2644/61904 [1:00:24<23:07:38,  1.40s/it]
  4%|▍         | 2645/61904 [1:00:26<23:35:58,  1.43s/it]
  4%|▍         | 2646/61904 [1:00:27<23:34:24,  1.43s/it]
  4%|▍         | 2647/61904 [1:00:28<23:01:52,  1.40s/it]
  4%|▍         | 2648/61904 [1:00:30<23:06:09,  1.40s/it]
  4%|▍         | 2649/61904 [1:00:31<23:25:37,  1.42s/it]
  4%|▍         | 2650/61904 [1:00:33<22:42:59,  1.38s/it]
  4%|▍         | 2651/61904 [1:00:34<22:42:51,  1.38s/it]
  4%|▍         | 2652/61904 [1:00:35<22:48:57,  1.39s/it]
  4%|▍         | 2653/61904 [1:00:37<22:33:02,  1.37s/it]
  4%|▍         | 2654/61904 [1:00:38<22:42:26,  1.38s/it]
  4%|▍         | 2655/61904 [1:00:40<23:32:53,  1.43s/it]
  4%|▍         | 2656/61904 [1:00:41<23:11:19,  1.41s/it]
  4%|▍         | 2657/61904 [1:00:42<22:56:34,  1.39s/it]
  4%|▍         | 2658/61904 [1:00:44<22:54:40,  1.39s/it]
  4%|▍         | 2659/61904 [1:00:45<22:18:36,  1.36s/it]
  4%|▍         | 2660/61904 [1:00:46<22:28:53,  1.37s/it]
                                                         
{'loss': 3.03, 'learning_rate': 1.9601322442629327e-07, 'epoch': 0.69}

  4%|▍         | 2660/61904 [1:00:46<22:28:53,  1.37s/it]
  4%|▍         | 2661/61904 [1:00:48<22:07:38,  1.34s/it]
  4%|▍         | 2662/61904 [1:00:49<22:16:39,  1.35s/it]
  4%|▍         | 2663/61904 [1:00:50<21:59:50,  1.34s/it]
  4%|▍         | 2664/61904 [1:00:52<22:24:28,  1.36s/it]
  4%|▍         | 2665/61904 [1:00:53<22:13:43,  1.35s/it]
  4%|▍         | 2666/61904 [1:00:55<22:03:21,  1.34s/it]
  4%|▍         | 2667/61904 [1:00:56<21:56:09,  1.33s/it]
  4%|▍         | 2668/61904 [1:00:57<21:27:18,  1.30s/it]
  4%|▍         | 2669/61904 [1:00:58<21:29:11,  1.31s/it]
  4%|▍         | 2670/61904 [1:01:00<21:44:46,  1.32s/it]
  4%|▍         | 2671/61904 [1:01:01<22:39:16,  1.38s/it]
  4%|▍         | 2672/61904 [1:01:03<22:21:04,  1.36s/it]
  4%|▍         | 2673/61904 [1:01:04<22:04:13,  1.34s/it]
  4%|▍         | 2674/61904 [1:01:05<21:57:49,  1.33s/it]
  4%|▍         | 2675/61904 [1:01:07<22:14:21,  1.35s/it]
  4%|▍         | 2676/61904 [1:01:08<21:36:41,  1.31s/it]
  4%|▍         | 2677/61904 [1:01:09<21:46:10,  1.32s/it]
  4%|▍         | 2678/61904 [1:01:10<21:40:01,  1.32s/it]
  4%|▍         | 2679/61904 [1:01:12<21:56:57,  1.33s/it]
  4%|▍         | 2680/61904 [1:01:13<22:18:36,  1.36s/it]
                                                         
{'loss': 3.0811, 'learning_rate': 1.9598081161675094e-07, 'epoch': 0.69}

  4%|▍         | 2680/61904 [1:01:13<22:18:36,  1.36s/it]
  4%|▍         | 2681/61904 [1:01:15<22:25:46,  1.36s/it]
  4%|▍         | 2682/61904 [1:01:16<21:51:49,  1.33s/it]
  4%|▍         | 2683/61904 [1:01:17<22:05:06,  1.34s/it]
  4%|▍         | 2684/61904 [1:01:19<22:18:23,  1.36s/it]
  4%|▍         | 2685/61904 [1:01:20<22:32:47,  1.37s/it]
  4%|▍         | 2686/61904 [1:01:21<22:36:59,  1.37s/it]
  4%|▍         | 2687/61904 [1:01:23<22:19:39,  1.36s/it]
  4%|▍         | 2688/61904 [1:01:24<22:03:10,  1.34s/it]
  4%|▍         | 2689/61904 [1:01:25<22:10:10,  1.35s/it]
  4%|▍         | 2690/61904 [1:01:27<22:54:42,  1.39s/it]
  4%|▍         | 2691/61904 [1:01:28<23:16:21,  1.41s/it]
  4%|▍         | 2692/61904 [1:01:30<22:41:24,  1.38s/it]
  4%|▍         | 2693/61904 [1:01:31<22:15:57,  1.35s/it]
  4%|▍         | 2694/61904 [1:01:32<22:01:04,  1.34s/it]
  4%|▍         | 2695/61904 [1:01:34<22:14:08,  1.35s/it]
  4%|▍         | 2696/61904 [1:01:35<22:04:17,  1.34s/it]
  4%|▍         | 2697/61904 [1:01:36<22:12:04,  1.35s/it]
  4%|▍         | 2698/61904 [1:01:38<22:14:30,  1.35s/it]
  4%|▍         | 2699/61904 [1:01:39<21:28:52,  1.31s/it]
  4%|▍         | 2700/61904 [1:01:40<21:33:28,  1.31s/it]
                                                         
{'loss': 3.0863, 'learning_rate': 1.959483988072086e-07, 'epoch': 0.7}

  4%|▍         | 2700/61904 [1:01:40<21:33:28,  1.31s/it]
  4%|▍         | 2701/61904 [1:01:41<21:06:58,  1.28s/it]
  4%|▍         | 2702/61904 [1:01:43<20:53:53,  1.27s/it]
  4%|▍         | 2703/61904 [1:01:44<22:15:53,  1.35s/it]
  4%|▍         | 2704/61904 [1:01:45<21:52:24,  1.33s/it]
  4%|▍         | 2705/61904 [1:01:47<22:18:08,  1.36s/it]
  4%|▍         | 2706/61904 [1:01:48<23:29:06,  1.43s/it]
  4%|▍         | 2707/61904 [1:01:50<23:16:15,  1.42s/it]
  4%|▍         | 2708/61904 [1:01:51<22:32:31,  1.37s/it]
  4%|▍         | 2709/61904 [1:01:53<23:05:15,  1.40s/it]
  4%|▍         | 2710/61904 [1:01:54<22:46:24,  1.39s/it]
  4%|▍         | 2711/61904 [1:01:55<22:32:46,  1.37s/it]
  4%|▍         | 2712/61904 [1:01:57<22:47:15,  1.39s/it]
  4%|▍         | 2713/61904 [1:01:58<22:56:56,  1.40s/it]
  4%|▍         | 2714/61904 [1:02:00<23:03:34,  1.40s/it]
  4%|▍         | 2715/61904 [1:02:01<22:50:48,  1.39s/it]
  4%|▍         | 2716/61904 [1:02:02<23:08:02,  1.41s/it]
  4%|▍         | 2717/61904 [1:02:04<23:03:57,  1.40s/it]
  4%|▍         | 2718/61904 [1:02:05<22:27:58,  1.37s/it]
  4%|▍         | 2719/61904 [1:02:06<22:09:03,  1.35s/it]
  4%|▍         | 2720/61904 [1:02:08<22:40:28,  1.38s/it]
                                                         
{'loss': 3.0027, 'learning_rate': 1.9591598599766629e-07, 'epoch': 0.7}

  4%|▍         | 2720/61904 [1:02:08<22:40:28,  1.38s/it]
  4%|▍         | 2721/61904 [1:02:09<21:45:08,  1.32s/it]
  4%|▍         | 2722/61904 [1:02:10<22:12:20,  1.35s/it]
  4%|▍         | 2723/61904 [1:02:12<21:53:52,  1.33s/it]
  4%|▍         | 2724/61904 [1:02:13<21:37:29,  1.32s/it]
  4%|▍         | 2725/61904 [1:02:14<21:42:29,  1.32s/it]
  4%|▍         | 2726/61904 [1:02:16<21:32:02,  1.31s/it]
  4%|▍         | 2727/61904 [1:02:17<21:41:21,  1.32s/it]
  4%|▍         | 2728/61904 [1:02:19<23:04:35,  1.40s/it]
  4%|▍         | 2729/61904 [1:02:20<22:52:04,  1.39s/it]
  4%|▍         | 2730/61904 [1:02:21<23:33:48,  1.43s/it]
  4%|▍         | 2731/61904 [1:02:23<22:33:22,  1.37s/it]
  4%|▍         | 2732/61904 [1:02:24<22:46:05,  1.39s/it]
  4%|▍         | 2733/61904 [1:02:25<22:36:57,  1.38s/it]
  4%|▍         | 2734/61904 [1:02:27<22:50:10,  1.39s/it]
  4%|▍         | 2735/61904 [1:02:28<22:58:10,  1.40s/it]
  4%|▍         | 2736/61904 [1:02:30<22:49:49,  1.39s/it]
  4%|▍         | 2737/61904 [1:02:31<22:40:58,  1.38s/it]
  4%|▍         | 2738/61904 [1:02:32<22:39:35,  1.38s/it]
  4%|▍         | 2739/61904 [1:02:34<22:42:38,  1.38s/it]
  4%|▍         | 2740/61904 [1:02:35<22:31:43,  1.37s/it]
                                                         
{'loss': 3.0467, 'learning_rate': 1.9588357318812392e-07, 'epoch': 0.71}

  4%|▍         | 2740/61904 [1:02:35<22:31:43,  1.37s/it]
  4%|▍         | 2741/61904 [1:02:36<22:30:33,  1.37s/it]
  4%|▍         | 2742/61904 [1:02:38<21:49:48,  1.33s/it]
  4%|▍         | 2743/61904 [1:02:39<21:50:02,  1.33s/it]
  4%|▍         | 2744/61904 [1:02:40<21:23:04,  1.30s/it]
  4%|▍         | 2745/61904 [1:02:42<22:18:08,  1.36s/it]
  4%|▍         | 2746/61904 [1:02:43<22:12:42,  1.35s/it]
  4%|▍         | 2747/61904 [1:02:44<21:52:57,  1.33s/it]
  4%|▍         | 2748/61904 [1:02:46<22:24:41,  1.36s/it]
  4%|▍         | 2749/61904 [1:02:47<22:40:24,  1.38s/it]
  4%|▍         | 2750/61904 [1:02:49<22:45:37,  1.39s/it]
  4%|▍         | 2751/61904 [1:02:50<22:43:39,  1.38s/it]
  4%|▍         | 2752/61904 [1:02:51<22:48:47,  1.39s/it]
  4%|▍         | 2753/61904 [1:02:53<22:46:48,  1.39s/it]
  4%|▍         | 2754/61904 [1:02:54<22:33:30,  1.37s/it]
  4%|▍         | 2755/61904 [1:02:55<21:50:21,  1.33s/it]
  4%|▍         | 2756/61904 [1:02:57<22:41:25,  1.38s/it]
  4%|▍         | 2757/61904 [1:02:58<22:43:51,  1.38s/it]
  4%|▍         | 2758/61904 [1:03:00<22:57:15,  1.40s/it]
  4%|▍         | 2759/61904 [1:03:01<22:41:34,  1.38s/it]
  4%|▍         | 2760/61904 [1:03:02<22:19:00,  1.36s/it]
                                                         
{'loss': 3.1305, 'learning_rate': 1.958511603785816e-07, 'epoch': 0.71}

  4%|▍         | 2760/61904 [1:03:02<22:19:00,  1.36s/it]
  4%|▍         | 2761/61904 [1:03:04<22:06:51,  1.35s/it]
  4%|▍         | 2762/61904 [1:03:05<22:59:05,  1.40s/it]
  4%|▍         | 2763/61904 [1:03:07<22:57:00,  1.40s/it]
  4%|▍         | 2764/61904 [1:03:08<22:25:19,  1.36s/it]
  4%|▍         | 2765/61904 [1:03:09<21:49:34,  1.33s/it]
  4%|▍         | 2766/61904 [1:03:10<21:51:32,  1.33s/it]
  4%|▍         | 2767/61904 [1:03:12<21:32:18,  1.31s/it]
  4%|▍         | 2768/61904 [1:03:13<22:03:13,  1.34s/it]
  4%|▍         | 2769/61904 [1:03:14<21:51:59,  1.33s/it]
  4%|▍         | 2770/61904 [1:03:16<22:11:31,  1.35s/it]
  4%|▍         | 2771/61904 [1:03:17<21:37:37,  1.32s/it]
  4%|▍         | 2772/61904 [1:03:19<22:22:27,  1.36s/it]
  4%|▍         | 2773/61904 [1:03:20<22:40:04,  1.38s/it]
  4%|▍         | 2774/61904 [1:03:21<23:21:55,  1.42s/it]
  4%|▍         | 2775/61904 [1:03:23<25:08:24,  1.53s/it]
  4%|▍         | 2776/61904 [1:03:25<23:55:28,  1.46s/it]
  4%|▍         | 2777/61904 [1:03:26<23:23:34,  1.42s/it]
  4%|▍         | 2778/61904 [1:03:27<23:40:51,  1.44s/it]
  4%|▍         | 2779/61904 [1:03:29<23:56:02,  1.46s/it]
  4%|▍         | 2780/61904 [1:03:30<22:54:36,  1.39s/it]
                                                         
{'loss': 3.0583, 'learning_rate': 1.9581874756903927e-07, 'epoch': 0.72}

  4%|▍         | 2780/61904 [1:03:30<22:54:36,  1.39s/it]
  4%|▍         | 2781/61904 [1:03:31<22:40:05,  1.38s/it]
  4%|▍         | 2782/61904 [1:03:33<22:15:14,  1.36s/it]
  4%|▍         | 2783/61904 [1:03:34<22:14:31,  1.35s/it]
  4%|▍         | 2784/61904 [1:03:36<22:34:02,  1.37s/it]
  4%|▍         | 2785/61904 [1:03:37<22:35:30,  1.38s/it]
  5%|▍         | 2786/61904 [1:03:38<22:03:12,  1.34s/it]
  5%|▍         | 2787/61904 [1:03:40<22:06:14,  1.35s/it]
  5%|▍         | 2788/61904 [1:03:41<22:06:59,  1.35s/it]
  5%|▍         | 2789/61904 [1:03:42<22:21:45,  1.36s/it]
  5%|▍         | 2790/61904 [1:03:44<22:43:44,  1.38s/it]
  5%|▍         | 2791/61904 [1:03:45<22:14:32,  1.35s/it]
  5%|▍         | 2792/61904 [1:03:46<22:27:34,  1.37s/it]
  5%|▍         | 2793/61904 [1:03:48<21:47:11,  1.33s/it]
  5%|▍         | 2794/61904 [1:03:49<21:21:46,  1.30s/it]
  5%|▍         | 2795/61904 [1:03:50<21:57:50,  1.34s/it]
  5%|▍         | 2796/61904 [1:03:52<21:56:07,  1.34s/it]
  5%|▍         | 2797/61904 [1:03:53<22:16:27,  1.36s/it]
  5%|▍         | 2798/61904 [1:03:54<22:24:33,  1.36s/it]
  5%|▍         | 2799/61904 [1:03:56<22:46:47,  1.39s/it]
  5%|▍         | 2800/61904 [1:03:57<22:23:27,  1.36s/it]
                                                         
{'loss': 3.0924, 'learning_rate': 1.9578633475949693e-07, 'epoch': 0.72}

  5%|▍         | 2800/61904 [1:03:57<22:23:27,  1.36s/it]
  5%|▍         | 2801/61904 [1:03:59<22:20:44,  1.36s/it]
  5%|▍         | 2802/61904 [1:04:00<22:35:44,  1.38s/it]
  5%|▍         | 2803/61904 [1:04:01<22:41:02,  1.38s/it]
  5%|▍         | 2804/61904 [1:04:03<23:29:44,  1.43s/it]
  5%|▍         | 2805/61904 [1:04:04<23:28:29,  1.43s/it]
  5%|▍         | 2806/61904 [1:04:06<22:56:36,  1.40s/it]
  5%|▍         | 2807/61904 [1:04:07<23:10:11,  1.41s/it]
  5%|▍         | 2808/61904 [1:04:08<22:54:39,  1.40s/it]
  5%|▍         | 2809/61904 [1:04:10<22:44:06,  1.39s/it]
  5%|▍         | 2810/61904 [1:04:11<23:28:33,  1.43s/it]
  5%|▍         | 2811/61904 [1:04:13<24:03:52,  1.47s/it]
  5%|▍         | 2812/61904 [1:04:14<23:19:40,  1.42s/it]
  5%|▍         | 2813/61904 [1:04:16<23:31:27,  1.43s/it]
  5%|▍         | 2814/61904 [1:04:17<23:26:24,  1.43s/it]
  5%|▍         | 2815/61904 [1:04:18<22:38:16,  1.38s/it]
  5%|▍         | 2816/61904 [1:04:20<23:17:37,  1.42s/it]
  5%|▍         | 2817/61904 [1:04:21<22:17:21,  1.36s/it]
  5%|▍         | 2818/61904 [1:04:22<22:03:04,  1.34s/it]
  5%|▍         | 2819/61904 [1:04:24<22:19:33,  1.36s/it]
  5%|▍         | 2820/61904 [1:04:25<21:58:29,  1.34s/it]
                                                         
{'loss': 3.0459, 'learning_rate': 1.9575392194995462e-07, 'epoch': 0.73}

  5%|▍         | 2820/61904 [1:04:25<21:58:29,  1.34s/it]
  5%|▍         | 2821/61904 [1:04:26<22:23:06,  1.36s/it]
  5%|▍         | 2822/61904 [1:04:28<22:35:44,  1.38s/it]
  5%|▍         | 2823/61904 [1:04:29<22:59:05,  1.40s/it]
  5%|▍         | 2824/61904 [1:04:31<24:01:49,  1.46s/it]
  5%|▍         | 2825/61904 [1:04:32<23:16:24,  1.42s/it]
  5%|▍         | 2826/61904 [1:04:34<22:42:00,  1.38s/it]
  5%|▍         | 2827/61904 [1:04:35<24:20:17,  1.48s/it]
  5%|▍         | 2828/61904 [1:04:37<24:00:35,  1.46s/it]
  5%|▍         | 2829/61904 [1:04:38<23:29:30,  1.43s/it]
  5%|▍         | 2830/61904 [1:04:40<23:50:17,  1.45s/it]
  5%|▍         | 2831/61904 [1:04:41<22:56:45,  1.40s/it]
  5%|▍         | 2832/61904 [1:04:42<22:34:00,  1.38s/it]
  5%|▍         | 2833/61904 [1:04:44<22:31:50,  1.37s/it]
  5%|▍         | 2834/61904 [1:04:45<22:49:36,  1.39s/it]
  5%|▍         | 2835/61904 [1:04:46<22:51:38,  1.39s/it]
  5%|▍         | 2836/61904 [1:04:48<23:21:26,  1.42s/it]
  5%|▍         | 2837/61904 [1:04:49<23:12:51,  1.41s/it]
  5%|▍         | 2838/61904 [1:04:51<22:58:46,  1.40s/it]
  5%|▍         | 2839/61904 [1:04:52<22:40:45,  1.38s/it]
  5%|▍         | 2840/61904 [1:04:53<21:48:57,  1.33s/it]
                                                         
{'loss': 3.0549, 'learning_rate': 1.9572150914041228e-07, 'epoch': 0.73}

  5%|▍         | 2840/61904 [1:04:53<21:48:57,  1.33s/it]
  5%|▍         | 2841/61904 [1:04:55<21:58:47,  1.34s/it]
  5%|▍         | 2842/61904 [1:04:56<22:26:43,  1.37s/it]
  5%|▍         | 2843/61904 [1:04:57<22:27:51,  1.37s/it]
  5%|▍         | 2844/61904 [1:04:59<23:11:09,  1.41s/it]
  5%|▍         | 2845/61904 [1:05:00<23:41:45,  1.44s/it]
  5%|▍         | 2846/61904 [1:05:02<22:56:32,  1.40s/it]
  5%|▍         | 2847/61904 [1:05:03<22:36:18,  1.38s/it]
  5%|▍         | 2848/61904 [1:05:04<22:03:49,  1.34s/it]
  5%|▍         | 2849/61904 [1:05:06<22:25:25,  1.37s/it]
  5%|▍         | 2850/61904 [1:05:07<22:42:00,  1.38s/it]
  5%|▍         | 2851/61904 [1:05:08<22:47:44,  1.39s/it]
  5%|▍         | 2852/61904 [1:05:10<22:28:17,  1.37s/it]
  5%|▍         | 2853/61904 [1:05:11<22:13:37,  1.36s/it]
  5%|▍         | 2854/61904 [1:05:12<22:11:56,  1.35s/it]
  5%|▍         | 2855/61904 [1:05:14<22:54:24,  1.40s/it]
  5%|▍         | 2856/61904 [1:05:15<23:22:48,  1.43s/it]
  5%|▍         | 2857/61904 [1:05:17<23:17:20,  1.42s/it]
  5%|▍         | 2858/61904 [1:05:18<23:29:23,  1.43s/it]
  5%|▍         | 2859/61904 [1:05:20<22:36:09,  1.38s/it]
  5%|▍         | 2860/61904 [1:05:21<22:25:35,  1.37s/it]
                                                         
{'loss': 3.1416, 'learning_rate': 1.9568909633086995e-07, 'epoch': 0.74}

  5%|▍         | 2860/61904 [1:05:21<22:25:35,  1.37s/it]
  5%|▍         | 2861/61904 [1:05:22<22:27:28,  1.37s/it]
  5%|▍         | 2862/61904 [1:05:24<22:50:13,  1.39s/it]
  5%|▍         | 2863/61904 [1:05:25<22:48:22,  1.39s/it]
  5%|▍         | 2864/61904 [1:05:27<22:42:27,  1.38s/it]
  5%|▍         | 2865/61904 [1:05:28<22:40:40,  1.38s/it]
  5%|▍         | 2866/61904 [1:05:29<22:42:49,  1.39s/it]
  5%|▍         | 2867/61904 [1:05:31<22:37:48,  1.38s/it]
  5%|▍         | 2868/61904 [1:05:32<23:34:49,  1.44s/it]
  5%|▍         | 2869/61904 [1:05:34<23:28:30,  1.43s/it]
  5%|▍         | 2870/61904 [1:05:35<22:59:37,  1.40s/it]
  5%|▍         | 2871/61904 [1:05:36<22:49:40,  1.39s/it]
  5%|▍         | 2872/61904 [1:05:38<22:04:29,  1.35s/it]
  5%|▍         | 2873/61904 [1:05:39<22:12:11,  1.35s/it]
  5%|▍         | 2874/61904 [1:05:40<21:57:03,  1.34s/it]
  5%|▍         | 2875/61904 [1:05:42<22:05:14,  1.35s/it]
  5%|▍         | 2876/61904 [1:05:43<22:14:06,  1.36s/it]
  5%|▍         | 2877/61904 [1:05:44<21:56:32,  1.34s/it]
  5%|▍         | 2878/61904 [1:05:45<21:13:42,  1.29s/it]
  5%|▍         | 2879/61904 [1:05:47<21:28:14,  1.31s/it]
  5%|▍         | 2880/61904 [1:05:48<21:52:12,  1.33s/it]
                                                         
{'loss': 3.084, 'learning_rate': 1.9565668352132763e-07, 'epoch': 0.74}

  5%|▍         | 2880/61904 [1:05:48<21:52:12,  1.33s/it]
  5%|▍         | 2881/61904 [1:05:50<22:46:47,  1.39s/it]
  5%|▍         | 2882/61904 [1:05:51<22:24:08,  1.37s/it]
  5%|▍         | 2883/61904 [1:05:52<22:37:10,  1.38s/it]
  5%|▍         | 2884/61904 [1:05:54<22:09:19,  1.35s/it]
  5%|▍         | 2885/61904 [1:05:55<22:10:29,  1.35s/it]
  5%|▍         | 2886/61904 [1:05:56<22:18:09,  1.36s/it]
  5%|▍         | 2887/61904 [1:05:58<22:56:00,  1.40s/it]
  5%|▍         | 2888/61904 [1:05:59<22:17:22,  1.36s/it]
  5%|▍         | 2889/61904 [1:06:00<21:49:22,  1.33s/it]
  5%|▍         | 2890/61904 [1:06:02<21:32:03,  1.31s/it]
  5%|▍         | 2891/61904 [1:06:03<22:14:29,  1.36s/it]
  5%|▍         | 2892/61904 [1:06:05<22:12:35,  1.35s/it]
  5%|▍         | 2893/61904 [1:06:06<22:02:52,  1.35s/it]
  5%|▍         | 2894/61904 [1:06:07<21:53:50,  1.34s/it]
  5%|▍         | 2895/61904 [1:06:08<21:22:01,  1.30s/it]
  5%|▍         | 2896/61904 [1:06:10<21:46:36,  1.33s/it]
  5%|▍         | 2897/61904 [1:06:11<21:50:52,  1.33s/it]
  5%|▍         | 2898/61904 [1:06:12<21:27:54,  1.31s/it]
  5%|▍         | 2899/61904 [1:06:14<22:09:43,  1.35s/it]
  5%|▍         | 2900/61904 [1:06:15<22:16:49,  1.36s/it]
                                                         
{'loss': 3.1049, 'learning_rate': 1.9562427071178527e-07, 'epoch': 0.75}

  5%|▍         | 2900/61904 [1:06:15<22:16:49,  1.36s/it]
  5%|▍         | 2901/61904 [1:06:17<21:56:09,  1.34s/it]
  5%|▍         | 2902/61904 [1:06:18<21:35:29,  1.32s/it]
  5%|▍         | 2903/61904 [1:06:19<21:34:09,  1.32s/it]
  5%|▍         | 2904/61904 [1:06:20<20:47:05,  1.27s/it]
  5%|▍         | 2905/61904 [1:06:22<21:09:27,  1.29s/it]
  5%|▍         | 2906/61904 [1:06:23<20:58:34,  1.28s/it]
  5%|▍         | 2907/61904 [1:06:24<21:05:12,  1.29s/it]
  5%|▍         | 2908/61904 [1:06:25<21:01:40,  1.28s/it]
  5%|▍         | 2909/61904 [1:06:27<21:33:48,  1.32s/it]
  5%|▍         | 2910/61904 [1:06:28<22:24:56,  1.37s/it]
  5%|▍         | 2911/61904 [1:06:30<22:27:46,  1.37s/it]
  5%|▍         | 2912/61904 [1:06:31<22:09:40,  1.35s/it]
  5%|▍         | 2913/61904 [1:06:32<22:11:29,  1.35s/it]
  5%|▍         | 2914/61904 [1:06:34<21:47:30,  1.33s/it]
  5%|▍         | 2915/61904 [1:06:35<22:13:41,  1.36s/it]
  5%|▍         | 2916/61904 [1:06:36<22:10:33,  1.35s/it]
  5%|▍         | 2917/61904 [1:06:38<21:28:32,  1.31s/it]
  5%|▍         | 2918/61904 [1:06:39<21:25:41,  1.31s/it]
  5%|▍         | 2919/61904 [1:06:40<22:35:27,  1.38s/it]
  5%|▍         | 2920/61904 [1:06:42<21:59:18,  1.34s/it]
                                                         
{'loss': 3.1135, 'learning_rate': 1.9559185790224296e-07, 'epoch': 0.75}

  5%|▍         | 2920/61904 [1:06:42<21:59:18,  1.34s/it]
  5%|▍         | 2921/61904 [1:06:43<23:02:38,  1.41s/it]
  5%|▍         | 2922/61904 [1:06:45<22:48:50,  1.39s/it]
  5%|▍         | 2923/61904 [1:06:46<22:46:21,  1.39s/it]
  5%|▍         | 2924/61904 [1:06:47<22:44:04,  1.39s/it]
  5%|▍         | 2925/61904 [1:06:49<22:28:54,  1.37s/it]
  5%|▍         | 2926/61904 [1:06:50<22:17:03,  1.36s/it]
  5%|▍         | 2927/61904 [1:06:51<21:51:02,  1.33s/it]
  5%|▍         | 2928/61904 [1:06:53<22:33:43,  1.38s/it]
  5%|▍         | 2929/61904 [1:06:54<22:40:31,  1.38s/it]
  5%|▍         | 2930/61904 [1:06:56<23:04:29,  1.41s/it]
  5%|▍         | 2931/61904 [1:06:57<23:19:24,  1.42s/it]
  5%|▍         | 2932/61904 [1:06:59<23:29:40,  1.43s/it]
  5%|▍         | 2933/61904 [1:07:00<22:56:41,  1.40s/it]
  5%|▍         | 2934/61904 [1:07:01<23:13:21,  1.42s/it]
  5%|▍         | 2935/61904 [1:07:03<23:24:42,  1.43s/it]
  5%|▍         | 2936/61904 [1:07:04<22:48:57,  1.39s/it]
  5%|▍         | 2937/61904 [1:07:06<22:34:45,  1.38s/it]
  5%|▍         | 2938/61904 [1:07:07<22:44:03,  1.39s/it]
  5%|▍         | 2939/61904 [1:07:08<23:06:01,  1.41s/it]
  5%|▍         | 2940/61904 [1:07:10<23:23:24,  1.43s/it]
                                                         
{'loss': 3.0329, 'learning_rate': 1.9555944509270062e-07, 'epoch': 0.76}

  5%|▍         | 2940/61904 [1:07:10<23:23:24,  1.43s/it]
  5%|▍         | 2941/61904 [1:07:11<23:16:05,  1.42s/it]
  5%|▍         | 2942/61904 [1:07:13<23:01:40,  1.41s/it]
  5%|▍         | 2943/61904 [1:07:14<23:25:47,  1.43s/it]
  5%|▍         | 2944/61904 [1:07:16<23:39:16,  1.44s/it]
  5%|▍         | 2945/61904 [1:07:17<23:23:55,  1.43s/it]
  5%|▍         | 2946/61904 [1:07:18<23:44:41,  1.45s/it]
  5%|▍         | 2947/61904 [1:07:20<23:42:46,  1.45s/it]
  5%|▍         | 2948/61904 [1:07:21<23:41:50,  1.45s/it]
  5%|▍         | 2949/61904 [1:07:23<22:39:42,  1.38s/it]
  5%|▍         | 2950/61904 [1:07:24<22:44:26,  1.39s/it]
  5%|▍         | 2951/61904 [1:07:25<22:25:32,  1.37s/it]
  5%|▍         | 2952/61904 [1:07:27<23:11:59,  1.42s/it]
  5%|▍         | 2953/61904 [1:07:28<23:16:14,  1.42s/it]
  5%|▍         | 2954/61904 [1:07:30<23:11:22,  1.42s/it]
  5%|▍         | 2955/61904 [1:07:31<23:03:45,  1.41s/it]
  5%|▍         | 2956/61904 [1:07:33<23:30:49,  1.44s/it]
  5%|▍         | 2957/61904 [1:07:34<23:05:01,  1.41s/it]
  5%|▍         | 2958/61904 [1:07:35<23:01:12,  1.41s/it]
  5%|▍         | 2959/61904 [1:07:37<22:42:22,  1.39s/it]
  5%|▍         | 2960/61904 [1:07:38<22:55:01,  1.40s/it]
                                                         
{'loss': 3.0465, 'learning_rate': 1.9552703228315828e-07, 'epoch': 0.76}

  5%|▍         | 2960/61904 [1:07:38<22:55:01,  1.40s/it]
  5%|▍         | 2961/61904 [1:07:39<22:22:17,  1.37s/it]
  5%|▍         | 2962/61904 [1:07:41<21:51:53,  1.34s/it]
  5%|▍         | 2963/61904 [1:07:42<21:53:29,  1.34s/it]
  5%|▍         | 2964/61904 [1:07:43<21:42:33,  1.33s/it]
  5%|▍         | 2965/61904 [1:07:45<22:01:56,  1.35s/it]
  5%|▍         | 2966/61904 [1:07:46<21:39:46,  1.32s/it]
  5%|▍         | 2967/61904 [1:07:48<22:58:32,  1.40s/it]
  5%|▍         | 2968/61904 [1:07:49<22:03:19,  1.35s/it]
  5%|▍         | 2969/61904 [1:07:50<22:32:17,  1.38s/it]
  5%|▍         | 2970/61904 [1:07:52<22:23:00,  1.37s/it]
  5%|▍         | 2971/61904 [1:07:53<22:51:23,  1.40s/it]
  5%|▍         | 2972/61904 [1:07:54<23:09:48,  1.41s/it]
  5%|▍         | 2973/61904 [1:07:56<22:48:41,  1.39s/it]
  5%|▍         | 2974/61904 [1:07:57<22:21:01,  1.37s/it]
  5%|▍         | 2975/61904 [1:07:58<22:21:40,  1.37s/it]
  5%|▍         | 2976/61904 [1:08:00<22:25:19,  1.37s/it]
  5%|▍         | 2977/61904 [1:08:01<22:17:59,  1.36s/it]
  5%|▍         | 2978/61904 [1:08:03<22:59:35,  1.40s/it]
  5%|▍         | 2979/61904 [1:08:04<22:34:47,  1.38s/it]
  5%|▍         | 2980/61904 [1:08:05<22:28:30,  1.37s/it]
                                                         
{'loss': 3.0079, 'learning_rate': 1.9549461947361597e-07, 'epoch': 0.77}

  5%|▍         | 2980/61904 [1:08:05<22:28:30,  1.37s/it]
  5%|▍         | 2981/61904 [1:08:07<21:56:13,  1.34s/it]
  5%|▍         | 2982/61904 [1:08:08<22:18:53,  1.36s/it]
  5%|▍         | 2983/61904 [1:08:10<23:28:33,  1.43s/it]
  5%|▍         | 2984/61904 [1:08:11<24:06:24,  1.47s/it]
  5%|▍         | 2985/61904 [1:08:13<23:31:47,  1.44s/it]
  5%|▍         | 2986/61904 [1:08:14<23:00:19,  1.41s/it]
  5%|▍         | 2987/61904 [1:08:15<23:04:29,  1.41s/it]
  5%|▍         | 2988/61904 [1:08:17<22:44:43,  1.39s/it]
  5%|▍         | 2989/61904 [1:08:18<23:02:16,  1.41s/it]
  5%|▍         | 2990/61904 [1:08:20<23:15:16,  1.42s/it]
  5%|▍         | 2991/61904 [1:08:21<23:05:26,  1.41s/it]
  5%|▍         | 2992/61904 [1:08:22<22:42:32,  1.39s/it]
  5%|▍         | 2993/61904 [1:08:24<22:48:09,  1.39s/it]
  5%|▍         | 2994/61904 [1:08:25<22:42:23,  1.39s/it]
  5%|▍         | 2995/61904 [1:08:27<23:46:31,  1.45s/it]
  5%|▍         | 2996/61904 [1:08:28<23:14:41,  1.42s/it]
  5%|▍         | 2997/61904 [1:08:29<23:12:34,  1.42s/it]
  5%|▍         | 2998/61904 [1:08:31<23:00:51,  1.41s/it]
  5%|▍         | 2999/61904 [1:08:32<22:28:01,  1.37s/it]
  5%|▍         | 3000/61904 [1:08:34<23:19:31,  1.43s/it]
                                                         
{'loss': 3.0706, 'learning_rate': 1.9546220666407363e-07, 'epoch': 0.78}

  5%|▍         | 3000/61904 [1:08:34<23:19:31,  1.43s/it]
  5%|▍         | 3001/61904 [1:08:35<23:54:17,  1.46s/it]
  5%|▍         | 3002/61904 [1:08:37<23:25:32,  1.43s/it]
  5%|▍         | 3003/61904 [1:08:38<23:09:58,  1.42s/it]
  5%|▍         | 3004/61904 [1:08:39<23:09:36,  1.42s/it]
  5%|▍         | 3005/61904 [1:08:41<22:41:02,  1.39s/it]
  5%|▍         | 3006/61904 [1:08:42<23:10:25,  1.42s/it]
  5%|▍         | 3007/61904 [1:08:43<22:25:30,  1.37s/it]
  5%|▍         | 3008/61904 [1:08:45<22:04:48,  1.35s/it]
  5%|▍         | 3009/61904 [1:08:46<22:09:15,  1.35s/it]
  5%|▍         | 3010/61904 [1:08:48<22:35:43,  1.38s/it]
  5%|▍         | 3011/61904 [1:08:49<22:37:35,  1.38s/it]
  5%|▍         | 3012/61904 [1:08:50<22:28:46,  1.37s/it]
  5%|▍         | 3013/61904 [1:08:52<22:40:20,  1.39s/it]
  5%|▍         | 3014/61904 [1:08:53<22:01:19,  1.35s/it]
  5%|▍         | 3015/61904 [1:08:54<21:24:35,  1.31s/it]
  5%|▍         | 3016/61904 [1:08:56<22:07:09,  1.35s/it]
  5%|▍         | 3017/61904 [1:08:57<22:41:00,  1.39s/it]
  5%|▍         | 3018/61904 [1:08:59<22:47:36,  1.39s/it]
  5%|▍         | 3019/61904 [1:09:00<22:59:01,  1.41s/it]
  5%|▍         | 3020/61904 [1:09:01<22:58:08,  1.40s/it]
                                                         
{'loss': 2.9727, 'learning_rate': 1.954297938545313e-07, 'epoch': 0.78}

  5%|▍         | 3020/61904 [1:09:01<22:58:08,  1.40s/it]
  5%|▍         | 3021/61904 [1:09:03<22:14:04,  1.36s/it]
  5%|▍         | 3022/61904 [1:09:04<22:37:25,  1.38s/it]
  5%|▍         | 3023/61904 [1:09:05<22:51:16,  1.40s/it]
  5%|▍         | 3024/61904 [1:09:07<22:25:58,  1.37s/it]
  5%|▍         | 3025/61904 [1:09:08<23:17:07,  1.42s/it]
  5%|▍         | 3026/61904 [1:09:10<22:25:11,  1.37s/it]
  5%|▍         | 3027/61904 [1:09:11<22:38:35,  1.38s/it]
  5%|▍         | 3028/61904 [1:09:12<22:45:09,  1.39s/it]
  5%|▍         | 3029/61904 [1:09:14<22:45:43,  1.39s/it]
  5%|▍         | 3030/61904 [1:09:15<22:50:51,  1.40s/it]
  5%|▍         | 3031/61904 [1:09:17<22:36:26,  1.38s/it]
  5%|▍         | 3032/61904 [1:09:18<21:52:34,  1.34s/it]
  5%|▍         | 3033/61904 [1:09:19<21:57:34,  1.34s/it]
  5%|▍         | 3034/61904 [1:09:20<21:46:02,  1.33s/it]
  5%|▍         | 3035/61904 [1:09:22<21:39:13,  1.32s/it]
  5%|▍         | 3036/61904 [1:09:23<21:25:16,  1.31s/it]
  5%|▍         | 3037/61904 [1:09:24<21:46:50,  1.33s/it]
  5%|▍         | 3038/61904 [1:09:26<21:22:27,  1.31s/it]
  5%|▍         | 3039/61904 [1:09:27<22:13:40,  1.36s/it]
  5%|▍         | 3040/61904 [1:09:28<21:26:47,  1.31s/it]
                                                         
{'loss': 3.0593, 'learning_rate': 1.9539738104498898e-07, 'epoch': 0.79}

  5%|▍         | 3040/61904 [1:09:28<21:26:47,  1.31s/it]
  5%|▍         | 3041/61904 [1:09:30<21:34:05,  1.32s/it]
  5%|▍         | 3042/61904 [1:09:31<21:58:55,  1.34s/it]
  5%|▍         | 3043/61904 [1:09:32<21:33:28,  1.32s/it]
  5%|▍         | 3044/61904 [1:09:34<21:34:53,  1.32s/it]
  5%|▍         | 3045/61904 [1:09:35<21:27:33,  1.31s/it]
  5%|▍         | 3046/61904 [1:09:36<21:53:57,  1.34s/it]
  5%|▍         | 3047/61904 [1:09:38<22:08:06,  1.35s/it]
  5%|▍         | 3048/61904 [1:09:39<22:04:52,  1.35s/it]
  5%|▍         | 3049/61904 [1:09:41<23:53:46,  1.46s/it]
  5%|▍         | 3050/61904 [1:09:42<23:13:46,  1.42s/it]
  5%|▍         | 3051/61904 [1:09:43<22:29:36,  1.38s/it]
  5%|▍         | 3052/61904 [1:09:45<21:52:59,  1.34s/it]
  5%|▍         | 3053/61904 [1:09:46<22:13:19,  1.36s/it]
  5%|▍         | 3054/61904 [1:09:47<22:28:41,  1.38s/it]
  5%|▍         | 3055/61904 [1:09:49<21:30:03,  1.32s/it]
  5%|▍         | 3056/61904 [1:09:50<21:16:30,  1.30s/it]
  5%|▍         | 3057/61904 [1:09:51<20:50:55,  1.28s/it]
  5%|▍         | 3058/61904 [1:09:53<21:20:25,  1.31s/it]
  5%|▍         | 3059/61904 [1:09:54<21:23:03,  1.31s/it]
  5%|▍         | 3060/61904 [1:09:55<21:57:35,  1.34s/it]
                                                         
{'loss': 3.0734, 'learning_rate': 1.9536496823544662e-07, 'epoch': 0.79}

  5%|▍         | 3060/61904 [1:09:55<21:57:35,  1.34s/it]
  5%|▍         | 3061/61904 [1:09:57<22:06:40,  1.35s/it]
  5%|▍         | 3062/61904 [1:09:58<21:50:28,  1.34s/it]
  5%|▍         | 3063/61904 [1:09:59<21:44:11,  1.33s/it]
  5%|▍         | 3064/61904 [1:10:01<21:35:36,  1.32s/it]
  5%|▍         | 3065/61904 [1:10:02<22:10:36,  1.36s/it]
  5%|▍         | 3066/61904 [1:10:03<22:20:40,  1.37s/it]
  5%|▍         | 3067/61904 [1:10:05<22:58:15,  1.41s/it]
  5%|▍         | 3068/61904 [1:10:06<22:50:29,  1.40s/it]
  5%|▍         | 3069/61904 [1:10:08<22:31:36,  1.38s/it]
  5%|▍         | 3070/61904 [1:10:09<22:28:36,  1.38s/it]
  5%|▍         | 3071/61904 [1:10:10<23:16:09,  1.42s/it]
  5%|▍         | 3072/61904 [1:10:12<23:02:57,  1.41s/it]
  5%|▍         | 3073/61904 [1:10:13<22:33:42,  1.38s/it]
  5%|▍         | 3074/61904 [1:10:14<22:14:51,  1.36s/it]
  5%|▍         | 3075/61904 [1:10:16<22:08:32,  1.35s/it]
  5%|▍         | 3076/61904 [1:10:17<22:05:14,  1.35s/it]
  5%|▍         | 3077/61904 [1:10:18<21:42:30,  1.33s/it]
  5%|▍         | 3078/61904 [1:10:20<22:00:14,  1.35s/it]
  5%|▍         | 3079/61904 [1:10:21<23:15:11,  1.42s/it]
  5%|▍         | 3080/61904 [1:10:23<21:53:40,  1.34s/it]
                                                         
{'loss': 3.0553, 'learning_rate': 1.953325554259043e-07, 'epoch': 0.8}

  5%|▍         | 3080/61904 [1:10:23<21:53:40,  1.34s/it]
  5%|▍         | 3081/61904 [1:10:24<22:28:17,  1.38s/it]
  5%|▍         | 3082/61904 [1:10:25<22:25:36,  1.37s/it]
  5%|▍         | 3083/61904 [1:10:27<22:20:12,  1.37s/it]
  5%|▍         | 3084/61904 [1:10:28<22:29:20,  1.38s/it]
  5%|▍         | 3085/61904 [1:10:30<23:12:46,  1.42s/it]
  5%|▍         | 3086/61904 [1:10:31<23:32:16,  1.44s/it]
  5%|▍         | 3087/61904 [1:10:33<22:56:50,  1.40s/it]
  5%|▍         | 3088/61904 [1:10:34<22:20:01,  1.37s/it]
  5%|▍         | 3089/61904 [1:10:35<22:06:09,  1.35s/it]
  5%|▍         | 3090/61904 [1:10:37<22:37:13,  1.38s/it]
  5%|▍         | 3091/61904 [1:10:38<22:24:34,  1.37s/it]
  5%|▍         | 3092/61904 [1:10:39<22:30:17,  1.38s/it]
  5%|▍         | 3093/61904 [1:10:41<22:02:02,  1.35s/it]
  5%|▍         | 3094/61904 [1:10:42<22:20:43,  1.37s/it]
  5%|▍         | 3095/61904 [1:10:43<22:29:56,  1.38s/it]
  5%|▌         | 3096/61904 [1:10:45<21:42:48,  1.33s/it]
  5%|▌         | 3097/61904 [1:10:46<21:38:48,  1.33s/it]
  5%|▌         | 3098/61904 [1:10:47<22:09:02,  1.36s/it]
  5%|▌         | 3099/61904 [1:10:49<22:36:38,  1.38s/it]
  5%|▌         | 3100/61904 [1:10:50<22:20:21,  1.37s/it]
                                                         
{'loss': 3.0315, 'learning_rate': 1.9530014261636197e-07, 'epoch': 0.8}

  5%|▌         | 3100/61904 [1:10:50<22:20:21,  1.37s/it]
  5%|▌         | 3101/61904 [1:10:52<22:50:47,  1.40s/it]
  5%|▌         | 3102/61904 [1:10:53<22:30:08,  1.38s/it]
  5%|▌         | 3103/61904 [1:10:54<22:35:07,  1.38s/it]
  5%|▌         | 3104/61904 [1:10:56<22:18:44,  1.37s/it]
  5%|▌         | 3105/61904 [1:10:57<21:56:00,  1.34s/it]
  5%|▌         | 3106/61904 [1:10:58<22:39:41,  1.39s/it]
  5%|▌         | 3107/61904 [1:11:00<22:51:50,  1.40s/it]
  5%|▌         | 3108/61904 [1:11:01<22:35:03,  1.38s/it]
  5%|▌         | 3109/61904 [1:11:03<22:12:19,  1.36s/it]
  5%|▌         | 3110/61904 [1:11:04<21:50:39,  1.34s/it]
  5%|▌         | 3111/61904 [1:11:05<21:50:07,  1.34s/it]
  5%|▌         | 3112/61904 [1:11:07<22:06:18,  1.35s/it]
  5%|▌         | 3113/61904 [1:11:08<22:22:21,  1.37s/it]
  5%|▌         | 3114/61904 [1:11:09<22:06:03,  1.35s/it]
  5%|▌         | 3115/61904 [1:11:11<22:27:22,  1.38s/it]
  5%|▌         | 3116/61904 [1:11:12<21:36:42,  1.32s/it]
  5%|▌         | 3117/61904 [1:11:13<21:20:10,  1.31s/it]
  5%|▌         | 3118/61904 [1:11:14<20:36:52,  1.26s/it]
  5%|▌         | 3119/61904 [1:11:16<21:56:47,  1.34s/it]
  5%|▌         | 3120/61904 [1:11:17<21:49:02,  1.34s/it]
                                                         
{'loss': 3.086, 'learning_rate': 1.9526772980681963e-07, 'epoch': 0.81}

  5%|▌         | 3120/61904 [1:11:17<21:49:02,  1.34s/it]
  5%|▌         | 3121/61904 [1:11:18<21:53:24,  1.34s/it]
  5%|▌         | 3122/61904 [1:11:20<22:02:12,  1.35s/it]
  5%|▌         | 3123/61904 [1:11:21<22:37:53,  1.39s/it]
  5%|▌         | 3124/61904 [1:11:23<22:00:29,  1.35s/it]
  5%|▌         | 3125/61904 [1:11:24<22:04:14,  1.35s/it]
  5%|▌         | 3126/61904 [1:11:25<22:41:13,  1.39s/it]
  5%|▌         | 3127/61904 [1:11:27<21:42:56,  1.33s/it]
  5%|▌         | 3128/61904 [1:11:28<22:48:13,  1.40s/it]
  5%|▌         | 3129/61904 [1:11:30<23:13:15,  1.42s/it]
  5%|▌         | 3130/61904 [1:11:31<24:37:58,  1.51s/it]
  5%|▌         | 3131/61904 [1:11:33<24:21:58,  1.49s/it]
  5%|▌         | 3132/61904 [1:11:34<24:16:53,  1.49s/it]
  5%|▌         | 3133/61904 [1:11:36<23:41:07,  1.45s/it]
  5%|▌         | 3134/61904 [1:11:37<22:51:37,  1.40s/it]
  5%|▌         | 3135/61904 [1:11:38<22:44:13,  1.39s/it]
  5%|▌         | 3136/61904 [1:11:40<22:39:15,  1.39s/it]
  5%|▌         | 3137/61904 [1:11:41<22:49:47,  1.40s/it]
  5%|▌         | 3138/61904 [1:11:42<22:04:25,  1.35s/it]
  5%|▌         | 3139/61904 [1:11:44<21:55:04,  1.34s/it]
  5%|▌         | 3140/61904 [1:11:45<21:44:31,  1.33s/it]
                                                         
{'loss': 3.046, 'learning_rate': 1.9523531699727732e-07, 'epoch': 0.81}

  5%|▌         | 3140/61904 [1:11:45<21:44:31,  1.33s/it]
  5%|▌         | 3141/61904 [1:11:46<21:49:54,  1.34s/it]
  5%|▌         | 3142/61904 [1:11:48<21:48:14,  1.34s/it]
  5%|▌         | 3143/61904 [1:11:49<21:40:41,  1.33s/it]
  5%|▌         | 3144/61904 [1:11:50<21:54:58,  1.34s/it]
  5%|▌         | 3145/61904 [1:11:52<22:19:15,  1.37s/it]
  5%|▌         | 3146/61904 [1:11:53<21:55:46,  1.34s/it]
  5%|▌         | 3147/61904 [1:11:55<22:27:46,  1.38s/it]
  5%|▌         | 3148/61904 [1:11:56<22:14:51,  1.36s/it]
  5%|▌         | 3149/61904 [1:11:57<22:01:05,  1.35s/it]
  5%|▌         | 3150/61904 [1:11:58<21:49:07,  1.34s/it]
  5%|▌         | 3151/61904 [1:12:00<22:05:40,  1.35s/it]
  5%|▌         | 3152/61904 [1:12:01<22:46:03,  1.40s/it]
  5%|▌         | 3153/61904 [1:12:03<22:33:47,  1.38s/it]
  5%|▌         | 3154/61904 [1:12:04<22:48:09,  1.40s/it]
  5%|▌         | 3155/61904 [1:12:05<22:13:04,  1.36s/it]
  5%|▌         | 3156/61904 [1:12:07<21:55:50,  1.34s/it]
  5%|▌         | 3157/61904 [1:12:08<21:14:20,  1.30s/it]
  5%|▌         | 3158/61904 [1:12:09<21:35:50,  1.32s/it]
  5%|▌         | 3159/61904 [1:12:11<22:08:13,  1.36s/it]
  5%|▌         | 3160/61904 [1:12:12<22:01:54,  1.35s/it]
                                                         
{'loss': 2.9981, 'learning_rate': 1.9520290418773498e-07, 'epoch': 0.82}

  5%|▌         | 3160/61904 [1:12:12<22:01:54,  1.35s/it]
  5%|▌         | 3161/61904 [1:12:14<22:50:02,  1.40s/it]
  5%|▌         | 3162/61904 [1:12:15<22:26:27,  1.38s/it]
  5%|▌         | 3163/61904 [1:12:16<21:59:25,  1.35s/it]
  5%|▌         | 3164/61904 [1:12:18<21:50:00,  1.34s/it]
  5%|▌         | 3165/61904 [1:12:19<22:07:08,  1.36s/it]
  5%|▌         | 3166/61904 [1:12:20<22:38:53,  1.39s/it]
  5%|▌         | 3167/61904 [1:12:22<21:35:10,  1.32s/it]
  5%|▌         | 3168/61904 [1:12:23<21:55:03,  1.34s/it]
  5%|▌         | 3169/61904 [1:12:24<22:00:31,  1.35s/it]
  5%|▌         | 3170/61904 [1:12:26<21:40:42,  1.33s/it]
  5%|▌         | 3171/61904 [1:12:27<21:23:49,  1.31s/it]
  5%|▌         | 3172/61904 [1:12:28<21:54:43,  1.34s/it]
  5%|▌         | 3173/61904 [1:12:30<21:52:39,  1.34s/it]
  5%|▌         | 3174/61904 [1:12:31<22:10:22,  1.36s/it]
  5%|▌         | 3175/61904 [1:12:32<22:14:35,  1.36s/it]
  5%|▌         | 3176/61904 [1:12:34<22:37:47,  1.39s/it]
  5%|▌         | 3177/61904 [1:12:35<22:54:24,  1.40s/it]
  5%|▌         | 3178/61904 [1:12:37<22:49:17,  1.40s/it]
  5%|▌         | 3179/61904 [1:12:38<22:09:00,  1.36s/it]
  5%|▌         | 3180/61904 [1:12:39<22:05:43,  1.35s/it]
                                                         
{'loss': 3.0827, 'learning_rate': 1.9517049137819264e-07, 'epoch': 0.82}

  5%|▌         | 3180/61904 [1:12:39<22:05:43,  1.35s/it]
  5%|▌         | 3181/61904 [1:12:41<22:34:47,  1.38s/it]
  5%|▌         | 3182/61904 [1:12:42<22:18:28,  1.37s/it]
  5%|▌         | 3183/61904 [1:12:43<22:16:58,  1.37s/it]
  5%|▌         | 3184/61904 [1:12:45<22:47:27,  1.40s/it]
  5%|▌         | 3185/61904 [1:12:46<22:42:53,  1.39s/it]
  5%|▌         | 3186/61904 [1:12:48<22:38:31,  1.39s/it]
  5%|▌         | 3187/61904 [1:12:49<21:59:04,  1.35s/it]
  5%|▌         | 3188/61904 [1:12:50<22:34:01,  1.38s/it]
  5%|▌         | 3189/61904 [1:12:52<22:46:22,  1.40s/it]
  5%|▌         | 3190/61904 [1:12:53<22:24:16,  1.37s/it]
  5%|▌         | 3191/61904 [1:12:55<22:43:31,  1.39s/it]
  5%|▌         | 3192/61904 [1:12:56<22:32:16,  1.38s/it]
  5%|▌         | 3193/61904 [1:12:57<22:31:05,  1.38s/it]
  5%|▌         | 3194/61904 [1:12:59<22:16:22,  1.37s/it]
  5%|▌         | 3195/61904 [1:13:00<22:06:32,  1.36s/it]
  5%|▌         | 3196/61904 [1:13:01<22:28:46,  1.38s/it]
  5%|▌         | 3197/61904 [1:13:03<22:56:36,  1.41s/it]
  5%|▌         | 3198/61904 [1:13:04<23:13:59,  1.42s/it]
  5%|▌         | 3199/61904 [1:13:06<22:52:44,  1.40s/it]
  5%|▌         | 3200/61904 [1:13:07<22:32:30,  1.38s/it]
                                                         
{'loss': 3.0582, 'learning_rate': 1.9513807856865033e-07, 'epoch': 0.83}

  5%|▌         | 3200/61904 [1:13:07<22:32:30,  1.38s/it]
  5%|▌         | 3201/61904 [1:13:08<22:12:17,  1.36s/it]
  5%|▌         | 3202/61904 [1:13:10<22:07:55,  1.36s/it]
  5%|▌         | 3203/61904 [1:13:11<22:39:31,  1.39s/it]
  5%|▌         | 3204/61904 [1:13:12<21:55:41,  1.34s/it]
  5%|▌         | 3205/61904 [1:13:14<21:53:14,  1.34s/it]
  5%|▌         | 3206/61904 [1:13:15<22:50:03,  1.40s/it]
  5%|▌         | 3207/61904 [1:13:17<22:32:00,  1.38s/it]
  5%|▌         | 3208/61904 [1:13:18<22:32:41,  1.38s/it]
  5%|▌         | 3209/61904 [1:13:20<23:18:42,  1.43s/it]
  5%|▌         | 3210/61904 [1:13:21<23:05:13,  1.42s/it]
  5%|▌         | 3211/61904 [1:13:22<22:22:48,  1.37s/it]
  5%|▌         | 3212/61904 [1:13:24<22:23:45,  1.37s/it]
  5%|▌         | 3213/61904 [1:13:25<21:57:23,  1.35s/it]
  5%|▌         | 3214/61904 [1:13:26<21:53:59,  1.34s/it]
  5%|▌         | 3215/61904 [1:13:28<22:13:08,  1.36s/it]
  5%|▌         | 3216/61904 [1:13:29<22:13:25,  1.36s/it]
  5%|▌         | 3217/61904 [1:13:30<22:09:50,  1.36s/it]
  5%|▌         | 3218/61904 [1:13:32<22:12:09,  1.36s/it]
  5%|▌         | 3219/61904 [1:13:33<21:29:18,  1.32s/it]
  5%|▌         | 3220/61904 [1:13:34<22:14:27,  1.36s/it]
                                                         
{'loss': 3.0574, 'learning_rate': 1.95105665759108e-07, 'epoch': 0.83}

  5%|▌         | 3220/61904 [1:13:34<22:14:27,  1.36s/it]
  5%|▌         | 3221/61904 [1:13:36<21:31:19,  1.32s/it]
  5%|▌         | 3222/61904 [1:13:37<21:42:56,  1.33s/it]
  5%|▌         | 3223/61904 [1:13:38<22:22:46,  1.37s/it]
  5%|▌         | 3224/61904 [1:13:40<22:25:49,  1.38s/it]
  5%|▌         | 3225/61904 [1:13:41<22:11:29,  1.36s/it]
  5%|▌         | 3226/61904 [1:13:42<22:10:45,  1.36s/it]
  5%|▌         | 3227/61904 [1:13:44<22:24:46,  1.38s/it]
  5%|▌         | 3228/61904 [1:13:45<22:26:40,  1.38s/it]
  5%|▌         | 3229/61904 [1:13:47<22:36:41,  1.39s/it]
  5%|▌         | 3230/61904 [1:13:48<23:29:08,  1.44s/it]
  5%|▌         | 3231/61904 [1:13:50<22:54:04,  1.41s/it]
  5%|▌         | 3232/61904 [1:13:51<22:21:09,  1.37s/it]
  5%|▌         | 3233/61904 [1:13:52<21:43:36,  1.33s/it]
  5%|▌         | 3234/61904 [1:13:53<21:45:50,  1.34s/it]
  5%|▌         | 3235/61904 [1:13:55<21:54:13,  1.34s/it]
  5%|▌         | 3236/61904 [1:13:56<21:38:14,  1.33s/it]
  5%|▌         | 3237/61904 [1:13:57<21:26:16,  1.32s/it]
  5%|▌         | 3238/61904 [1:13:59<21:22:04,  1.31s/it]
  5%|▌         | 3239/61904 [1:14:00<21:06:13,  1.30s/it]
  5%|▌         | 3240/61904 [1:14:01<21:32:24,  1.32s/it]
                                                         
{'loss': 3.0666, 'learning_rate': 1.9507325294956565e-07, 'epoch': 0.84}

  5%|▌         | 3240/61904 [1:14:01<21:32:24,  1.32s/it]
  5%|▌         | 3241/61904 [1:14:03<21:14:49,  1.30s/it]
  5%|▌         | 3242/61904 [1:14:04<21:00:37,  1.29s/it]
  5%|▌         | 3243/61904 [1:14:05<21:00:53,  1.29s/it]
  5%|▌         | 3244/61904 [1:14:07<21:39:33,  1.33s/it]
  5%|▌         | 3245/61904 [1:14:08<21:59:46,  1.35s/it]
  5%|▌         | 3246/61904 [1:14:09<22:02:21,  1.35s/it]
  5%|▌         | 3247/61904 [1:14:11<21:50:41,  1.34s/it]
  5%|▌         | 3248/61904 [1:14:12<21:30:09,  1.32s/it]
  5%|▌         | 3249/61904 [1:14:13<21:41:32,  1.33s/it]
  5%|▌         | 3250/61904 [1:14:15<23:14:06,  1.43s/it]
  5%|▌         | 3251/61904 [1:14:16<23:02:36,  1.41s/it]
  5%|▌         | 3252/61904 [1:14:18<23:25:03,  1.44s/it]
  5%|▌         | 3253/61904 [1:14:19<22:14:43,  1.37s/it]
  5%|▌         | 3254/61904 [1:14:20<22:22:36,  1.37s/it]
  5%|▌         | 3255/61904 [1:14:22<21:58:10,  1.35s/it]
  5%|▌         | 3256/61904 [1:14:23<21:27:38,  1.32s/it]
  5%|▌         | 3257/61904 [1:14:24<21:25:28,  1.32s/it]
  5%|▌         | 3258/61904 [1:14:25<21:06:50,  1.30s/it]
  5%|▌         | 3259/61904 [1:14:27<21:19:39,  1.31s/it]
  5%|▌         | 3260/61904 [1:14:28<21:21:44,  1.31s/it]
                                                         
{'loss': 3.1107, 'learning_rate': 1.9504084014002334e-07, 'epoch': 0.84}

  5%|▌         | 3260/61904 [1:14:28<21:21:44,  1.31s/it]
  5%|▌         | 3261/61904 [1:14:29<21:47:44,  1.34s/it]
  5%|▌         | 3262/61904 [1:14:31<21:15:08,  1.30s/it]
  5%|▌         | 3263/61904 [1:14:32<22:07:58,  1.36s/it]
  5%|▌         | 3264/61904 [1:14:34<22:38:55,  1.39s/it]
  5%|▌         | 3265/61904 [1:14:35<22:00:09,  1.35s/it]
  5%|▌         | 3266/61904 [1:14:36<22:11:31,  1.36s/it]
  5%|▌         | 3267/61904 [1:14:38<22:01:15,  1.35s/it]
  5%|▌         | 3268/61904 [1:14:39<21:30:30,  1.32s/it]
  5%|▌         | 3269/61904 [1:14:40<21:26:37,  1.32s/it]
  5%|▌         | 3270/61904 [1:14:41<21:12:53,  1.30s/it]
  5%|▌         | 3271/61904 [1:14:43<21:05:15,  1.29s/it]
  5%|▌         | 3272/61904 [1:14:44<21:47:22,  1.34s/it]
  5%|▌         | 3273/61904 [1:14:46<21:40:07,  1.33s/it]
  5%|▌         | 3274/61904 [1:14:47<22:18:08,  1.37s/it]
  5%|▌         | 3275/61904 [1:14:48<22:06:05,  1.36s/it]
  5%|▌         | 3276/61904 [1:14:50<22:11:57,  1.36s/it]
  5%|▌         | 3277/61904 [1:14:51<23:34:21,  1.45s/it]
  5%|▌         | 3278/61904 [1:14:53<22:54:19,  1.41s/it]
  5%|▌         | 3279/61904 [1:14:54<22:21:22,  1.37s/it]
  5%|▌         | 3280/61904 [1:14:55<22:18:06,  1.37s/it]
                                                         
{'loss': 2.9972, 'learning_rate': 1.9500842733048098e-07, 'epoch': 0.85}

  5%|▌         | 3280/61904 [1:14:55<22:18:06,  1.37s/it]
  5%|▌         | 3281/61904 [1:14:57<22:06:04,  1.36s/it]
  5%|▌         | 3282/61904 [1:14:58<22:45:13,  1.40s/it]
  5%|▌         | 3283/61904 [1:15:00<23:05:05,  1.42s/it]
  5%|▌         | 3284/61904 [1:15:01<22:37:02,  1.39s/it]
  5%|▌         | 3285/61904 [1:15:02<22:43:35,  1.40s/it]
  5%|▌         | 3286/61904 [1:15:04<21:52:43,  1.34s/it]
  5%|▌         | 3287/61904 [1:15:05<21:59:52,  1.35s/it]
  5%|▌         | 3288/61904 [1:15:06<22:46:16,  1.40s/it]
  5%|▌         | 3289/61904 [1:15:08<22:31:32,  1.38s/it]
  5%|▌         | 3290/61904 [1:15:09<21:56:53,  1.35s/it]
  5%|▌         | 3291/61904 [1:15:10<21:54:33,  1.35s/it]
  5%|▌         | 3292/61904 [1:15:12<22:17:41,  1.37s/it]
  5%|▌         | 3293/61904 [1:15:13<22:25:26,  1.38s/it]
  5%|▌         | 3294/61904 [1:15:15<22:18:23,  1.37s/it]
  5%|▌         | 3295/61904 [1:15:16<22:04:08,  1.36s/it]
  5%|▌         | 3296/61904 [1:15:17<22:53:31,  1.41s/it]
  5%|▌         | 3297/61904 [1:15:19<22:37:38,  1.39s/it]
  5%|▌         | 3298/61904 [1:15:20<23:00:58,  1.41s/it]
  5%|▌         | 3299/61904 [1:15:21<22:26:57,  1.38s/it]
  5%|▌         | 3300/61904 [1:15:23<21:59:57,  1.35s/it]
                                                         
{'loss': 3.0628, 'learning_rate': 1.9497601452093867e-07, 'epoch': 0.85}

  5%|▌         | 3300/61904 [1:15:23<21:59:57,  1.35s/it]
  5%|▌         | 3301/61904 [1:15:24<22:09:39,  1.36s/it]
  5%|▌         | 3302/61904 [1:15:26<22:21:29,  1.37s/it]
  5%|▌         | 3303/61904 [1:15:27<22:10:34,  1.36s/it]
  5%|▌         | 3304/61904 [1:15:28<21:56:10,  1.35s/it]
  5%|▌         | 3305/61904 [1:15:30<22:03:26,  1.36s/it]
  5%|▌         | 3306/61904 [1:15:31<21:30:27,  1.32s/it]
  5%|▌         | 3307/61904 [1:15:32<21:02:43,  1.29s/it]
  5%|▌         | 3308/61904 [1:15:33<21:00:52,  1.29s/it]
  5%|▌         | 3309/61904 [1:15:35<21:51:07,  1.34s/it]
  5%|▌         | 3310/61904 [1:15:36<22:45:41,  1.40s/it]
  5%|▌         | 3311/61904 [1:15:38<21:53:12,  1.34s/it]
  5%|▌         | 3312/61904 [1:15:39<21:01:22,  1.29s/it]
  5%|▌         | 3313/61904 [1:15:40<21:11:55,  1.30s/it]
  5%|▌         | 3314/61904 [1:15:41<21:09:53,  1.30s/it]
  5%|▌         | 3315/61904 [1:15:43<21:18:41,  1.31s/it]
  5%|▌         | 3316/61904 [1:15:44<22:06:28,  1.36s/it]
  5%|▌         | 3317/61904 [1:15:45<21:34:16,  1.33s/it]
  5%|▌         | 3318/61904 [1:15:47<21:53:12,  1.34s/it]
  5%|▌         | 3319/61904 [1:15:48<21:37:08,  1.33s/it]
  5%|▌         | 3320/61904 [1:15:49<21:15:39,  1.31s/it]
                                                         
{'loss': 3.0148, 'learning_rate': 1.9494360171139633e-07, 'epoch': 0.86}

  5%|▌         | 3320/61904 [1:15:49<21:15:39,  1.31s/it]
  5%|▌         | 3321/61904 [1:15:51<21:06:05,  1.30s/it]
  5%|▌         | 3322/61904 [1:15:52<21:43:30,  1.34s/it]
  5%|▌         | 3323/61904 [1:15:53<21:31:45,  1.32s/it]
  5%|▌         | 3324/61904 [1:15:55<21:37:34,  1.33s/it]
  5%|▌         | 3325/61904 [1:15:56<22:00:14,  1.35s/it]
  5%|▌         | 3326/61904 [1:15:58<22:28:24,  1.38s/it]
  5%|▌         | 3327/61904 [1:15:59<22:33:37,  1.39s/it]
  5%|▌         | 3328/61904 [1:16:00<22:38:24,  1.39s/it]
  5%|▌         | 3329/61904 [1:16:02<22:34:10,  1.39s/it]
  5%|▌         | 3330/61904 [1:16:03<22:18:29,  1.37s/it]
  5%|▌         | 3331/61904 [1:16:04<21:53:44,  1.35s/it]
  5%|▌         | 3332/61904 [1:16:06<21:58:17,  1.35s/it]
  5%|▌         | 3333/61904 [1:16:07<22:14:58,  1.37s/it]
  5%|▌         | 3334/61904 [1:16:09<22:49:07,  1.40s/it]
  5%|▌         | 3335/61904 [1:16:10<22:25:22,  1.38s/it]
  5%|▌         | 3336/61904 [1:16:11<22:42:43,  1.40s/it]
  5%|▌         | 3337/61904 [1:16:13<22:13:08,  1.37s/it]
  5%|▌         | 3338/61904 [1:16:14<21:36:28,  1.33s/it]
  5%|▌         | 3339/61904 [1:16:15<22:03:26,  1.36s/it]
  5%|▌         | 3340/61904 [1:16:17<21:47:23,  1.34s/it]
                                                         
{'loss': 3.0553, 'learning_rate': 1.94911188901854e-07, 'epoch': 0.86}

  5%|▌         | 3340/61904 [1:16:17<21:47:23,  1.34s/it]
  5%|▌         | 3341/61904 [1:16:18<22:26:49,  1.38s/it]
  5%|▌         | 3342/61904 [1:16:20<24:23:27,  1.50s/it]
  5%|▌         | 3343/61904 [1:16:21<24:30:08,  1.51s/it]
  5%|▌         | 3344/61904 [1:16:23<23:33:44,  1.45s/it]
  5%|▌         | 3345/61904 [1:16:24<22:46:02,  1.40s/it]
  5%|▌         | 3346/61904 [1:16:25<22:05:06,  1.36s/it]
  5%|▌         | 3347/61904 [1:16:26<21:40:56,  1.33s/it]
  5%|▌         | 3348/61904 [1:16:28<22:37:19,  1.39s/it]
  5%|▌         | 3349/61904 [1:16:29<22:17:17,  1.37s/it]
  5%|▌         | 3350/61904 [1:16:31<21:50:24,  1.34s/it]
  5%|▌         | 3351/61904 [1:16:32<21:38:01,  1.33s/it]
  5%|▌         | 3352/61904 [1:16:33<21:19:36,  1.31s/it]
  5%|▌         | 3353/61904 [1:16:35<22:33:34,  1.39s/it]
  5%|▌         | 3354/61904 [1:16:36<22:19:27,  1.37s/it]
  5%|▌         | 3355/61904 [1:16:38<22:41:47,  1.40s/it]
  5%|▌         | 3356/61904 [1:16:39<22:49:55,  1.40s/it]
  5%|▌         | 3357/61904 [1:16:40<22:35:19,  1.39s/it]
  5%|▌         | 3358/61904 [1:16:42<22:01:12,  1.35s/it]
  5%|▌         | 3359/61904 [1:16:43<22:55:39,  1.41s/it]
  5%|▌         | 3360/61904 [1:16:45<23:27:58,  1.44s/it]
                                                         
{'loss': 2.9124, 'learning_rate': 1.9487877609231168e-07, 'epoch': 0.87}

  5%|▌         | 3360/61904 [1:16:45<23:27:58,  1.44s/it]
  5%|▌         | 3361/61904 [1:16:46<23:11:19,  1.43s/it]
  5%|▌         | 3362/61904 [1:16:47<22:30:15,  1.38s/it]
  5%|▌         | 3363/61904 [1:16:49<22:19:30,  1.37s/it]
  5%|▌         | 3364/61904 [1:16:50<22:12:17,  1.37s/it]
  5%|▌         | 3365/61904 [1:16:51<21:53:10,  1.35s/it]
  5%|▌         | 3366/61904 [1:16:53<21:53:01,  1.35s/it]
  5%|▌         | 3367/61904 [1:16:54<21:56:15,  1.35s/it]
  5%|▌         | 3368/61904 [1:16:56<22:46:50,  1.40s/it]
  5%|▌         | 3369/61904 [1:16:57<23:04:48,  1.42s/it]
  5%|▌         | 3370/61904 [1:16:58<23:09:21,  1.42s/it]
  5%|▌         | 3371/61904 [1:17:00<22:15:37,  1.37s/it]
  5%|▌         | 3372/61904 [1:17:01<22:38:12,  1.39s/it]
  5%|▌         | 3373/61904 [1:17:02<22:16:16,  1.37s/it]
  5%|▌         | 3374/61904 [1:17:04<22:24:39,  1.38s/it]
  5%|▌         | 3375/61904 [1:17:05<21:42:00,  1.33s/it]
  5%|▌         | 3376/61904 [1:17:07<22:08:30,  1.36s/it]
  5%|▌         | 3377/61904 [1:17:08<22:02:00,  1.36s/it]
  5%|▌         | 3378/61904 [1:17:09<21:47:35,  1.34s/it]
  5%|▌         | 3379/61904 [1:17:11<22:10:54,  1.36s/it]
  5%|▌         | 3380/61904 [1:17:12<22:07:40,  1.36s/it]
                                                         
{'loss': 2.9625, 'learning_rate': 1.9484636328276934e-07, 'epoch': 0.87}

  5%|▌         | 3380/61904 [1:17:12<22:07:40,  1.36s/it]
  5%|▌         | 3381/61904 [1:17:13<22:45:38,  1.40s/it]
  5%|▌         | 3382/61904 [1:17:15<22:21:05,  1.37s/it]
  5%|▌         | 3383/61904 [1:17:16<21:47:59,  1.34s/it]
  5%|▌         | 3384/61904 [1:17:17<21:56:07,  1.35s/it]
  5%|▌         | 3385/61904 [1:17:19<22:40:39,  1.40s/it]
  5%|▌         | 3386/61904 [1:17:20<22:12:46,  1.37s/it]
  5%|▌         | 3387/61904 [1:17:21<22:01:13,  1.35s/it]
  5%|▌         | 3388/61904 [1:17:23<21:35:59,  1.33s/it]
  5%|▌         | 3389/61904 [1:17:24<21:27:53,  1.32s/it]
  5%|▌         | 3390/61904 [1:17:25<21:09:28,  1.30s/it]
  5%|▌         | 3391/61904 [1:17:27<21:28:22,  1.32s/it]
  5%|▌         | 3392/61904 [1:17:28<21:40:34,  1.33s/it]
  5%|▌         | 3393/61904 [1:17:30<22:24:45,  1.38s/it]
  5%|▌         | 3394/61904 [1:17:31<21:55:56,  1.35s/it]
  5%|▌         | 3395/61904 [1:17:32<21:23:42,  1.32s/it]
  5%|▌         | 3396/61904 [1:17:33<21:39:55,  1.33s/it]
  5%|▌         | 3397/61904 [1:17:35<21:54:48,  1.35s/it]
  5%|▌         | 3398/61904 [1:17:36<21:42:00,  1.34s/it]
  5%|▌         | 3399/61904 [1:17:37<21:29:15,  1.32s/it]
  5%|▌         | 3400/61904 [1:17:39<21:41:27,  1.33s/it]
                                                         
{'loss': 2.9542, 'learning_rate': 1.94813950473227e-07, 'epoch': 0.88}

  5%|▌         | 3400/61904 [1:17:39<21:41:27,  1.33s/it]
  5%|▌         | 3401/61904 [1:17:40<21:39:03,  1.33s/it]
  5%|▌         | 3402/61904 [1:17:42<22:11:00,  1.37s/it]
  5%|▌         | 3403/61904 [1:17:43<22:04:53,  1.36s/it]
  5%|▌         | 3404/61904 [1:17:44<22:58:56,  1.41s/it]
  6%|▌         | 3405/61904 [1:17:46<22:28:54,  1.38s/it]
  6%|▌         | 3406/61904 [1:17:47<22:41:03,  1.40s/it]
  6%|▌         | 3407/61904 [1:17:48<22:04:32,  1.36s/it]
  6%|▌         | 3408/61904 [1:17:50<21:42:32,  1.34s/it]
  6%|▌         | 3409/61904 [1:17:51<21:26:08,  1.32s/it]
  6%|▌         | 3410/61904 [1:17:52<21:13:43,  1.31s/it]
  6%|▌         | 3411/61904 [1:17:54<21:39:12,  1.33s/it]
  6%|▌         | 3412/61904 [1:17:55<21:34:36,  1.33s/it]
  6%|▌         | 3413/61904 [1:17:56<21:39:57,  1.33s/it]
  6%|▌         | 3414/61904 [1:17:58<21:39:04,  1.33s/it]
  6%|▌         | 3415/61904 [1:17:59<22:31:12,  1.39s/it]
  6%|▌         | 3416/61904 [1:18:00<22:02:53,  1.36s/it]
  6%|▌         | 3417/61904 [1:18:02<21:37:53,  1.33s/it]
  6%|▌         | 3418/61904 [1:18:03<21:53:33,  1.35s/it]
  6%|▌         | 3419/61904 [1:18:04<21:14:20,  1.31s/it]
  6%|▌         | 3420/61904 [1:18:06<21:35:26,  1.33s/it]
                                                         
{'loss': 3.0042, 'learning_rate': 1.947815376636847e-07, 'epoch': 0.88}

  6%|▌         | 3420/61904 [1:18:06<21:35:26,  1.33s/it]
  6%|▌         | 3421/61904 [1:18:07<21:20:37,  1.31s/it]
  6%|▌         | 3422/61904 [1:18:08<20:59:14,  1.29s/it]
  6%|▌         | 3423/61904 [1:18:10<21:38:46,  1.33s/it]
  6%|▌         | 3424/61904 [1:18:11<21:37:40,  1.33s/it]
  6%|▌         | 3425/61904 [1:18:12<22:03:03,  1.36s/it]
  6%|▌         | 3426/61904 [1:18:14<21:55:58,  1.35s/it]
  6%|▌         | 3427/61904 [1:18:15<21:53:33,  1.35s/it]
  6%|▌         | 3428/61904 [1:18:16<21:30:11,  1.32s/it]
  6%|▌         | 3429/61904 [1:18:18<22:19:47,  1.37s/it]
  6%|▌         | 3430/61904 [1:18:19<22:17:09,  1.37s/it]
  6%|▌         | 3431/61904 [1:18:21<22:37:11,  1.39s/it]
  6%|▌         | 3432/61904 [1:18:22<22:16:56,  1.37s/it]
  6%|▌         | 3433/61904 [1:18:23<22:16:32,  1.37s/it]
  6%|▌         | 3434/61904 [1:18:25<22:47:41,  1.40s/it]
  6%|▌         | 3435/61904 [1:18:26<23:14:11,  1.43s/it]
  6%|▌         | 3436/61904 [1:18:28<22:39:59,  1.40s/it]
  6%|▌         | 3437/61904 [1:18:29<23:02:53,  1.42s/it]
  6%|▌         | 3438/61904 [1:18:30<22:42:09,  1.40s/it]
  6%|▌         | 3439/61904 [1:18:32<22:23:22,  1.38s/it]
  6%|▌         | 3440/61904 [1:18:33<23:35:09,  1.45s/it]
                                                         
{'loss': 3.002, 'learning_rate': 1.9474912485414233e-07, 'epoch': 0.89}

  6%|▌         | 3440/61904 [1:18:33<23:35:09,  1.45s/it]
  6%|▌         | 3441/61904 [1:18:35<22:53:54,  1.41s/it]
  6%|▌         | 3442/61904 [1:18:36<22:18:10,  1.37s/it]
  6%|▌         | 3443/61904 [1:18:37<22:49:50,  1.41s/it]
  6%|▌         | 3444/61904 [1:18:39<21:50:19,  1.34s/it]
  6%|▌         | 3445/61904 [1:18:40<22:01:20,  1.36s/it]
  6%|▌         | 3446/61904 [1:18:41<21:19:27,  1.31s/it]
  6%|▌         | 3447/61904 [1:18:43<21:16:23,  1.31s/it]
  6%|▌         | 3448/61904 [1:18:44<21:01:32,  1.29s/it]
  6%|▌         | 3449/61904 [1:18:45<20:44:27,  1.28s/it]
  6%|▌         | 3450/61904 [1:18:46<20:58:22,  1.29s/it]
  6%|▌         | 3451/61904 [1:18:48<22:10:15,  1.37s/it]
  6%|▌         | 3452/61904 [1:18:49<22:20:47,  1.38s/it]
  6%|▌         | 3453/61904 [1:18:51<21:56:23,  1.35s/it]
  6%|▌         | 3454/61904 [1:18:52<22:43:20,  1.40s/it]
  6%|▌         | 3455/61904 [1:18:53<21:58:35,  1.35s/it]
  6%|▌         | 3456/61904 [1:18:55<21:51:34,  1.35s/it]
  6%|▌         | 3457/61904 [1:18:56<22:01:34,  1.36s/it]
  6%|▌         | 3458/61904 [1:18:57<21:54:12,  1.35s/it]
  6%|▌         | 3459/61904 [1:18:59<21:26:30,  1.32s/it]
  6%|▌         | 3460/61904 [1:19:00<21:54:52,  1.35s/it]
                                                         
{'loss': 3.0223, 'learning_rate': 1.9471671204460001e-07, 'epoch': 0.89}

  6%|▌         | 3460/61904 [1:19:00<21:54:52,  1.35s/it]
  6%|▌         | 3461/61904 [1:19:02<22:24:25,  1.38s/it]
  6%|▌         | 3462/61904 [1:19:03<22:10:22,  1.37s/it]
  6%|▌         | 3463/61904 [1:19:04<22:39:37,  1.40s/it]
  6%|▌         | 3464/61904 [1:19:06<22:44:33,  1.40s/it]
  6%|▌         | 3465/61904 [1:19:07<22:38:50,  1.40s/it]
  6%|▌         | 3466/61904 [1:19:09<22:32:16,  1.39s/it]
  6%|▌         | 3467/61904 [1:19:10<22:47:02,  1.40s/it]
  6%|▌         | 3468/61904 [1:19:11<22:50:17,  1.41s/it]
  6%|▌         | 3469/61904 [1:19:13<22:25:28,  1.38s/it]
  6%|▌         | 3470/61904 [1:19:14<23:30:10,  1.45s/it]
  6%|▌         | 3471/61904 [1:19:16<23:54:50,  1.47s/it]
  6%|▌         | 3472/61904 [1:19:17<24:16:06,  1.50s/it]
  6%|▌         | 3473/61904 [1:19:19<23:37:47,  1.46s/it]
  6%|▌         | 3474/61904 [1:19:20<22:40:55,  1.40s/it]
  6%|▌         | 3475/61904 [1:19:21<22:05:47,  1.36s/it]
  6%|▌         | 3476/61904 [1:19:23<21:55:34,  1.35s/it]
  6%|▌         | 3477/61904 [1:19:24<22:54:12,  1.41s/it]
  6%|▌         | 3478/61904 [1:19:26<23:05:11,  1.42s/it]
  6%|▌         | 3479/61904 [1:19:27<22:45:57,  1.40s/it]
  6%|▌         | 3480/61904 [1:19:28<22:32:16,  1.39s/it]
                                                         
{'loss': 3.0038, 'learning_rate': 1.946842992350577e-07, 'epoch': 0.9}

  6%|▌         | 3480/61904 [1:19:28<22:32:16,  1.39s/it]
  6%|▌         | 3481/61904 [1:19:30<22:52:00,  1.41s/it]
  6%|▌         | 3482/61904 [1:19:31<22:51:27,  1.41s/it]
  6%|▌         | 3483/61904 [1:19:32<21:57:56,  1.35s/it]
  6%|▌         | 3484/61904 [1:19:34<21:53:29,  1.35s/it]
  6%|▌         | 3485/61904 [1:19:35<21:58:33,  1.35s/it]
  6%|▌         | 3486/61904 [1:19:37<22:28:05,  1.38s/it]
  6%|▌         | 3487/61904 [1:19:38<21:54:25,  1.35s/it]
  6%|▌         | 3488/61904 [1:19:39<21:56:46,  1.35s/it]
  6%|▌         | 3489/61904 [1:19:41<22:05:20,  1.36s/it]
  6%|▌         | 3490/61904 [1:19:42<21:40:41,  1.34s/it]
  6%|▌         | 3491/61904 [1:19:43<21:35:38,  1.33s/it]
  6%|▌         | 3492/61904 [1:19:45<22:01:38,  1.36s/it]
  6%|▌         | 3493/61904 [1:19:46<22:49:52,  1.41s/it]
  6%|▌         | 3494/61904 [1:19:48<22:41:01,  1.40s/it]
  6%|▌         | 3495/61904 [1:19:49<21:54:44,  1.35s/it]
  6%|▌         | 3496/61904 [1:19:50<21:31:50,  1.33s/it]
  6%|▌         | 3497/61904 [1:19:51<21:40:35,  1.34s/it]
  6%|▌         | 3498/61904 [1:19:53<22:31:10,  1.39s/it]
  6%|▌         | 3499/61904 [1:19:54<22:03:18,  1.36s/it]
  6%|▌         | 3500/61904 [1:19:56<22:17:50,  1.37s/it]
                                                         
{'loss': 3.0014, 'learning_rate': 1.9465188642551534e-07, 'epoch': 0.9}

  6%|▌         | 3500/61904 [1:19:56<22:17:50,  1.37s/it]
  6%|▌         | 3501/61904 [1:19:57<21:57:58,  1.35s/it]
  6%|▌         | 3502/61904 [1:19:58<21:39:24,  1.33s/it]
  6%|▌         | 3503/61904 [1:20:00<22:35:42,  1.39s/it]
  6%|▌         | 3504/61904 [1:20:01<22:35:09,  1.39s/it]
  6%|▌         | 3505/61904 [1:20:03<22:58:59,  1.42s/it]
  6%|▌         | 3506/61904 [1:20:04<22:12:37,  1.37s/it]
  6%|▌         | 3507/61904 [1:20:05<22:16:19,  1.37s/it]
  6%|▌         | 3508/61904 [1:20:06<21:45:43,  1.34s/it]
  6%|▌         | 3509/61904 [1:20:08<22:44:13,  1.40s/it]
  6%|▌         | 3510/61904 [1:20:09<21:54:43,  1.35s/it]
  6%|▌         | 3511/61904 [1:20:11<22:35:27,  1.39s/it]
  6%|▌         | 3512/61904 [1:20:12<22:52:52,  1.41s/it]
  6%|▌         | 3513/61904 [1:20:14<23:09:07,  1.43s/it]
  6%|▌         | 3514/61904 [1:20:15<22:21:11,  1.38s/it]
  6%|▌         | 3515/61904 [1:20:16<22:34:19,  1.39s/it]
  6%|▌         | 3516/61904 [1:20:18<22:43:12,  1.40s/it]
  6%|▌         | 3517/61904 [1:20:19<22:15:08,  1.37s/it]
  6%|▌         | 3518/61904 [1:20:21<22:44:13,  1.40s/it]
  6%|▌         | 3519/61904 [1:20:22<21:43:54,  1.34s/it]
  6%|▌         | 3520/61904 [1:20:23<21:14:03,  1.31s/it]
                                                         
{'loss': 3.0553, 'learning_rate': 1.9461947361597303e-07, 'epoch': 0.91}

  6%|▌         | 3520/61904 [1:20:23<21:14:03,  1.31s/it]
  6%|▌         | 3521/61904 [1:20:24<21:19:43,  1.32s/it]
  6%|▌         | 3522/61904 [1:20:26<21:39:59,  1.34s/it]
  6%|▌         | 3523/61904 [1:20:27<22:07:35,  1.36s/it]
  6%|▌         | 3524/61904 [1:20:28<21:54:40,  1.35s/it]
  6%|▌         | 3525/61904 [1:20:30<22:11:42,  1.37s/it]
  6%|▌         | 3526/61904 [1:20:31<22:14:04,  1.37s/it]
  6%|▌         | 3527/61904 [1:20:33<22:05:12,  1.36s/it]
  6%|▌         | 3528/61904 [1:20:34<22:28:54,  1.39s/it]
  6%|▌         | 3529/61904 [1:20:35<22:11:11,  1.37s/it]
  6%|▌         | 3530/61904 [1:20:37<22:05:57,  1.36s/it]
  6%|▌         | 3531/61904 [1:20:38<21:20:50,  1.32s/it]
  6%|▌         | 3532/61904 [1:20:39<22:28:03,  1.39s/it]
  6%|▌         | 3533/61904 [1:20:41<21:35:10,  1.33s/it]
  6%|▌         | 3534/61904 [1:20:42<21:51:51,  1.35s/it]
  6%|▌         | 3535/61904 [1:20:43<21:35:14,  1.33s/it]
  6%|▌         | 3536/61904 [1:20:45<21:13:00,  1.31s/it]
  6%|▌         | 3537/61904 [1:20:46<22:03:28,  1.36s/it]
  6%|▌         | 3538/61904 [1:20:47<22:07:18,  1.36s/it]
  6%|▌         | 3539/61904 [1:20:49<22:10:59,  1.37s/it]
  6%|▌         | 3540/61904 [1:20:50<22:14:08,  1.37s/it]
                                                         
{'loss': 3.0522, 'learning_rate': 1.945870608064307e-07, 'epoch': 0.91}

  6%|▌         | 3540/61904 [1:20:50<22:14:08,  1.37s/it]
  6%|▌         | 3541/61904 [1:20:52<21:58:05,  1.36s/it]
  6%|▌         | 3542/61904 [1:20:53<22:11:33,  1.37s/it]
  6%|▌         | 3543/61904 [1:20:54<21:54:25,  1.35s/it]
  6%|▌         | 3544/61904 [1:20:56<21:36:48,  1.33s/it]
  6%|▌         | 3545/61904 [1:20:57<22:02:00,  1.36s/it]
  6%|▌         | 3546/61904 [1:20:58<22:44:39,  1.40s/it]
  6%|▌         | 3547/61904 [1:21:00<22:05:22,  1.36s/it]
  6%|▌         | 3548/61904 [1:21:01<22:22:12,  1.38s/it]
  6%|▌         | 3549/61904 [1:21:02<21:46:50,  1.34s/it]
  6%|▌         | 3550/61904 [1:21:04<22:26:25,  1.38s/it]
  6%|▌         | 3551/61904 [1:21:05<22:28:05,  1.39s/it]
  6%|▌         | 3552/61904 [1:21:06<21:38:56,  1.34s/it]
  6%|▌         | 3553/61904 [1:21:08<21:46:36,  1.34s/it]
  6%|▌         | 3554/61904 [1:21:09<21:18:46,  1.31s/it]
  6%|▌         | 3555/61904 [1:21:11<22:20:35,  1.38s/it]
  6%|▌         | 3556/61904 [1:21:12<21:37:40,  1.33s/it]
  6%|▌         | 3557/61904 [1:21:13<22:18:41,  1.38s/it]
  6%|▌         | 3558/61904 [1:21:15<21:55:08,  1.35s/it]
  6%|▌         | 3559/61904 [1:21:16<20:56:54,  1.29s/it]
  6%|▌         | 3560/61904 [1:21:17<21:20:36,  1.32s/it]
                                                         
{'loss': 3.0365, 'learning_rate': 1.9455464799688835e-07, 'epoch': 0.92}

  6%|▌         | 3560/61904 [1:21:17<21:20:36,  1.32s/it]
  6%|▌         | 3561/61904 [1:21:19<21:33:37,  1.33s/it]
  6%|▌         | 3562/61904 [1:21:20<21:55:46,  1.35s/it]
  6%|▌         | 3563/61904 [1:21:21<22:28:39,  1.39s/it]
  6%|▌         | 3564/61904 [1:21:23<21:47:31,  1.34s/it]
  6%|▌         | 3565/61904 [1:21:24<22:31:40,  1.39s/it]
  6%|▌         | 3566/61904 [1:21:26<22:44:08,  1.40s/it]
  6%|▌         | 3567/61904 [1:21:27<22:18:52,  1.38s/it]
  6%|▌         | 3568/61904 [1:21:28<21:46:01,  1.34s/it]
  6%|▌         | 3569/61904 [1:21:29<21:49:07,  1.35s/it]
  6%|▌         | 3570/61904 [1:21:31<22:14:09,  1.37s/it]
  6%|▌         | 3571/61904 [1:21:32<21:56:08,  1.35s/it]
  6%|▌         | 3572/61904 [1:21:34<22:18:01,  1.38s/it]
  6%|▌         | 3573/61904 [1:21:35<21:46:54,  1.34s/it]
  6%|▌         | 3574/61904 [1:21:36<22:29:15,  1.39s/it]
  6%|▌         | 3575/61904 [1:21:38<22:14:58,  1.37s/it]
  6%|▌         | 3576/61904 [1:21:39<21:54:11,  1.35s/it]
  6%|▌         | 3577/61904 [1:21:40<22:10:35,  1.37s/it]
  6%|▌         | 3578/61904 [1:21:42<22:05:19,  1.36s/it]
  6%|▌         | 3579/61904 [1:21:43<22:41:23,  1.40s/it]
  6%|▌         | 3580/61904 [1:21:45<22:17:09,  1.38s/it]
                                                         
{'loss': 3.0001, 'learning_rate': 1.9452223518734604e-07, 'epoch': 0.93}

  6%|▌         | 3580/61904 [1:21:45<22:17:09,  1.38s/it]
  6%|▌         | 3581/61904 [1:21:46<21:58:19,  1.36s/it]
  6%|▌         | 3582/61904 [1:21:47<21:28:02,  1.33s/it]
  6%|▌         | 3583/61904 [1:21:49<21:23:35,  1.32s/it]
  6%|▌         | 3584/61904 [1:21:50<21:58:43,  1.36s/it]
  6%|▌         | 3585/61904 [1:21:51<21:28:13,  1.33s/it]
  6%|▌         | 3586/61904 [1:21:53<22:02:10,  1.36s/it]
  6%|▌         | 3587/61904 [1:21:54<22:25:25,  1.38s/it]
  6%|▌         | 3588/61904 [1:21:55<22:03:43,  1.36s/it]
  6%|▌         | 3589/61904 [1:21:57<21:25:29,  1.32s/it]
  6%|▌         | 3590/61904 [1:21:58<22:01:35,  1.36s/it]
  6%|▌         | 3591/61904 [1:21:59<21:49:30,  1.35s/it]
  6%|▌         | 3592/61904 [1:22:01<21:51:41,  1.35s/it]
  6%|▌         | 3593/61904 [1:22:02<23:33:36,  1.45s/it]
  6%|▌         | 3594/61904 [1:22:04<22:24:29,  1.38s/it]
  6%|▌         | 3595/61904 [1:22:05<22:10:33,  1.37s/it]
  6%|▌         | 3596/61904 [1:22:06<22:47:20,  1.41s/it]
  6%|▌         | 3597/61904 [1:22:08<22:53:00,  1.41s/it]
  6%|▌         | 3598/61904 [1:22:09<22:26:10,  1.39s/it]
  6%|▌         | 3599/61904 [1:22:11<22:29:24,  1.39s/it]
  6%|▌         | 3600/61904 [1:22:12<22:29:31,  1.39s/it]
                                                         
{'loss': 3.0292, 'learning_rate': 1.944898223778037e-07, 'epoch': 0.93}

  6%|▌         | 3600/61904 [1:22:12<22:29:31,  1.39s/it]
  6%|▌         | 3601/61904 [1:22:13<21:57:37,  1.36s/it]
  6%|▌         | 3602/61904 [1:22:15<23:05:37,  1.43s/it]
  6%|▌         | 3603/61904 [1:22:16<22:44:35,  1.40s/it]
  6%|▌         | 3604/61904 [1:22:18<22:11:46,  1.37s/it]
  6%|▌         | 3605/61904 [1:22:19<22:47:44,  1.41s/it]
  6%|▌         | 3606/61904 [1:22:20<22:46:45,  1.41s/it]
  6%|▌         | 3607/61904 [1:22:22<23:29:20,  1.45s/it]
  6%|▌         | 3608/61904 [1:22:24<23:53:19,  1.48s/it]
  6%|▌         | 3609/61904 [1:22:25<22:53:24,  1.41s/it]
  6%|▌         | 3610/61904 [1:22:26<22:27:50,  1.39s/it]
  6%|▌         | 3611/61904 [1:22:27<22:12:28,  1.37s/it]
  6%|▌         | 3612/61904 [1:22:29<22:36:27,  1.40s/it]
  6%|▌         | 3613/61904 [1:22:30<22:55:16,  1.42s/it]
  6%|▌         | 3614/61904 [1:22:32<22:19:30,  1.38s/it]
  6%|▌         | 3615/61904 [1:22:33<22:20:28,  1.38s/it]
  6%|▌         | 3616/61904 [1:22:34<22:04:15,  1.36s/it]
  6%|▌         | 3617/61904 [1:22:36<21:53:49,  1.35s/it]
  6%|▌         | 3618/61904 [1:22:37<21:58:08,  1.36s/it]
  6%|▌         | 3619/61904 [1:22:39<22:34:29,  1.39s/it]
  6%|▌         | 3620/61904 [1:22:40<22:48:25,  1.41s/it]
                                                         
{'loss': 3.1199, 'learning_rate': 1.9445740956826136e-07, 'epoch': 0.94}

  6%|▌         | 3620/61904 [1:22:40<22:48:25,  1.41s/it]
  6%|▌         | 3621/61904 [1:22:41<22:41:39,  1.40s/it]
  6%|▌         | 3622/61904 [1:22:43<22:36:31,  1.40s/it]
  6%|▌         | 3623/61904 [1:22:44<22:41:26,  1.40s/it]
  6%|▌         | 3624/61904 [1:22:46<22:27:03,  1.39s/it]
  6%|▌         | 3625/61904 [1:22:47<22:22:11,  1.38s/it]
  6%|▌         | 3626/61904 [1:22:48<21:58:26,  1.36s/it]
  6%|▌         | 3627/61904 [1:22:49<21:38:58,  1.34s/it]
  6%|▌         | 3628/61904 [1:22:51<22:04:11,  1.36s/it]
  6%|▌         | 3629/61904 [1:22:52<23:01:26,  1.42s/it]
  6%|▌         | 3630/61904 [1:22:54<23:06:56,  1.43s/it]
  6%|▌         | 3631/61904 [1:22:55<23:46:31,  1.47s/it]
  6%|▌         | 3632/61904 [1:22:57<23:22:36,  1.44s/it]
  6%|▌         | 3633/61904 [1:22:58<23:19:34,  1.44s/it]
  6%|▌         | 3634/61904 [1:23:00<23:16:58,  1.44s/it]
  6%|▌         | 3635/61904 [1:23:01<23:10:06,  1.43s/it]
  6%|▌         | 3636/61904 [1:23:03<22:49:42,  1.41s/it]
  6%|▌         | 3637/61904 [1:23:04<23:04:01,  1.43s/it]
  6%|▌         | 3638/61904 [1:23:05<23:03:29,  1.42s/it]
  6%|▌         | 3639/61904 [1:23:07<23:59:39,  1.48s/it]
  6%|▌         | 3640/61904 [1:23:08<23:17:29,  1.44s/it]
                                                         
{'loss': 3.0552, 'learning_rate': 1.9442499675871905e-07, 'epoch': 0.94}

  6%|▌         | 3640/61904 [1:23:08<23:17:29,  1.44s/it]
  6%|▌         | 3641/61904 [1:23:10<23:14:16,  1.44s/it]
  6%|▌         | 3642/61904 [1:23:11<23:02:22,  1.42s/it]
  6%|▌         | 3643/61904 [1:23:13<22:58:48,  1.42s/it]
  6%|▌         | 3644/61904 [1:23:14<22:48:24,  1.41s/it]
  6%|▌         | 3645/61904 [1:23:16<23:38:22,  1.46s/it]
  6%|▌         | 3646/61904 [1:23:17<23:12:23,  1.43s/it]
  6%|▌         | 3647/61904 [1:23:18<22:34:24,  1.39s/it]
  6%|▌         | 3648/61904 [1:23:20<22:03:48,  1.36s/it]
  6%|▌         | 3649/61904 [1:23:21<22:01:58,  1.36s/it]
  6%|▌         | 3650/61904 [1:23:22<21:59:57,  1.36s/it]
  6%|▌         | 3651/61904 [1:23:24<22:02:08,  1.36s/it]
  6%|▌         | 3652/61904 [1:23:25<22:00:41,  1.36s/it]
  6%|▌         | 3653/61904 [1:23:26<22:47:30,  1.41s/it]
  6%|▌         | 3654/61904 [1:23:28<22:06:04,  1.37s/it]
  6%|▌         | 3655/61904 [1:23:29<22:08:35,  1.37s/it]
  6%|▌         | 3656/61904 [1:23:31<22:19:15,  1.38s/it]
  6%|▌         | 3657/61904 [1:23:32<21:58:54,  1.36s/it]
  6%|▌         | 3658/61904 [1:23:33<22:38:48,  1.40s/it]
  6%|▌         | 3659/61904 [1:23:35<22:29:41,  1.39s/it]
  6%|▌         | 3660/61904 [1:23:36<22:27:31,  1.39s/it]
                                                         
{'loss': 3.0105, 'learning_rate': 1.9439258394917669e-07, 'epoch': 0.95}

  6%|▌         | 3660/61904 [1:23:36<22:27:31,  1.39s/it]
  6%|▌         | 3661/61904 [1:23:37<22:25:32,  1.39s/it]
  6%|▌         | 3662/61904 [1:23:39<22:17:30,  1.38s/it]
  6%|▌         | 3663/61904 [1:23:40<22:14:58,  1.38s/it]
  6%|▌         | 3664/61904 [1:23:42<22:06:08,  1.37s/it]
  6%|▌         | 3665/61904 [1:23:43<22:25:38,  1.39s/it]
  6%|▌         | 3666/61904 [1:23:45<23:49:00,  1.47s/it]
  6%|▌         | 3667/61904 [1:23:46<24:00:04,  1.48s/it]
  6%|▌         | 3668/61904 [1:23:48<24:15:38,  1.50s/it]
  6%|▌         | 3669/61904 [1:23:49<23:45:54,  1.47s/it]
  6%|▌         | 3670/61904 [1:23:51<23:37:47,  1.46s/it]
  6%|▌         | 3671/61904 [1:23:52<23:11:39,  1.43s/it]
  6%|▌         | 3672/61904 [1:23:53<23:48:37,  1.47s/it]
  6%|▌         | 3673/61904 [1:23:55<23:41:06,  1.46s/it]
  6%|▌         | 3674/61904 [1:23:56<23:30:00,  1.45s/it]
  6%|▌         | 3675/61904 [1:23:58<22:34:24,  1.40s/it]
  6%|▌         | 3676/61904 [1:23:59<22:27:50,  1.39s/it]
  6%|▌         | 3677/61904 [1:24:00<21:54:57,  1.36s/it]
  6%|▌         | 3678/61904 [1:24:02<21:50:11,  1.35s/it]
  6%|▌         | 3679/61904 [1:24:03<22:12:21,  1.37s/it]
  6%|▌         | 3680/61904 [1:24:04<22:10:44,  1.37s/it]
                                                         
{'loss': 2.989, 'learning_rate': 1.9436017113963437e-07, 'epoch': 0.95}

  6%|▌         | 3680/61904 [1:24:04<22:10:44,  1.37s/it]
  6%|▌         | 3681/61904 [1:24:06<22:30:18,  1.39s/it]
  6%|▌         | 3682/61904 [1:24:07<23:23:18,  1.45s/it]
  6%|▌         | 3683/61904 [1:24:09<24:04:34,  1.49s/it]
  6%|▌         | 3684/61904 [1:24:10<24:00:10,  1.48s/it]
  6%|▌         | 3685/61904 [1:24:12<23:41:22,  1.46s/it]
  6%|▌         | 3686/61904 [1:24:13<23:18:17,  1.44s/it]
  6%|▌         | 3687/61904 [1:24:15<22:39:23,  1.40s/it]
  6%|▌         | 3688/61904 [1:24:16<22:27:52,  1.39s/it]
  6%|▌         | 3689/61904 [1:24:17<22:35:30,  1.40s/it]
  6%|▌         | 3690/61904 [1:24:19<22:57:06,  1.42s/it]
  6%|▌         | 3691/61904 [1:24:20<22:24:59,  1.39s/it]
  6%|▌         | 3692/61904 [1:24:21<22:13:08,  1.37s/it]
  6%|▌         | 3693/61904 [1:24:23<22:05:41,  1.37s/it]
  6%|▌         | 3694/61904 [1:24:24<22:31:52,  1.39s/it]
  6%|▌         | 3695/61904 [1:24:26<22:20:46,  1.38s/it]
  6%|▌         | 3696/61904 [1:24:27<21:55:04,  1.36s/it]
  6%|▌         | 3697/61904 [1:24:28<22:45:44,  1.41s/it]
  6%|▌         | 3698/61904 [1:24:30<22:25:03,  1.39s/it]
  6%|▌         | 3699/61904 [1:24:31<23:06:16,  1.43s/it]
  6%|▌         | 3700/61904 [1:24:33<23:20:33,  1.44s/it]
                                                         
{'loss': 3.0091, 'learning_rate': 1.9432775833009204e-07, 'epoch': 0.96}

  6%|▌         | 3700/61904 [1:24:33<23:20:33,  1.44s/it]
  6%|▌         | 3701/61904 [1:24:34<22:58:18,  1.42s/it]
  6%|▌         | 3702/61904 [1:24:35<22:21:07,  1.38s/it]
  6%|▌         | 3703/61904 [1:24:37<22:42:38,  1.40s/it]
  6%|▌         | 3704/61904 [1:24:38<22:31:15,  1.39s/it]
  6%|▌         | 3705/61904 [1:24:40<22:04:21,  1.37s/it]
  6%|▌         | 3706/61904 [1:24:41<21:27:46,  1.33s/it]
  6%|▌         | 3707/61904 [1:24:42<22:21:35,  1.38s/it]
  6%|▌         | 3708/61904 [1:24:44<23:35:36,  1.46s/it]
  6%|▌         | 3709/61904 [1:24:45<23:25:31,  1.45s/it]
  6%|▌         | 3710/61904 [1:24:47<23:04:06,  1.43s/it]
  6%|▌         | 3711/61904 [1:24:48<22:28:37,  1.39s/it]
  6%|▌         | 3712/61904 [1:24:49<22:02:23,  1.36s/it]
  6%|▌         | 3713/61904 [1:24:51<22:05:00,  1.37s/it]
  6%|▌         | 3714/61904 [1:24:52<22:38:28,  1.40s/it]
  6%|▌         | 3715/61904 [1:24:54<22:22:07,  1.38s/it]
  6%|▌         | 3716/61904 [1:24:55<22:12:22,  1.37s/it]
  6%|▌         | 3717/61904 [1:24:56<22:38:43,  1.40s/it]
  6%|▌         | 3718/61904 [1:24:58<21:59:01,  1.36s/it]
  6%|▌         | 3719/61904 [1:24:59<21:55:27,  1.36s/it]
  6%|▌         | 3720/61904 [1:25:00<22:32:02,  1.39s/it]
                                                         
{'loss': 3.0251, 'learning_rate': 1.942953455205497e-07, 'epoch': 0.96}

  6%|▌         | 3720/61904 [1:25:00<22:32:02,  1.39s/it]
  6%|▌         | 3721/61904 [1:25:02<22:57:07,  1.42s/it]
  6%|▌         | 3722/61904 [1:25:03<22:59:54,  1.42s/it]
  6%|▌         | 3723/61904 [1:25:05<22:50:42,  1.41s/it]
  6%|▌         | 3724/61904 [1:25:06<22:25:54,  1.39s/it]
  6%|▌         | 3725/61904 [1:25:08<22:57:46,  1.42s/it]
  6%|▌         | 3726/61904 [1:25:09<22:45:03,  1.41s/it]
  6%|▌         | 3727/61904 [1:25:10<22:38:59,  1.40s/it]
  6%|▌         | 3728/61904 [1:25:12<22:43:56,  1.41s/it]
  6%|▌         | 3729/61904 [1:25:13<22:05:26,  1.37s/it]
  6%|▌         | 3730/61904 [1:25:14<21:38:55,  1.34s/it]
  6%|▌         | 3731/61904 [1:25:16<21:29:37,  1.33s/it]
  6%|▌         | 3732/61904 [1:25:17<22:19:22,  1.38s/it]
  6%|▌         | 3733/61904 [1:25:19<22:42:48,  1.41s/it]
  6%|▌         | 3734/61904 [1:25:20<22:26:06,  1.39s/it]
  6%|▌         | 3735/61904 [1:25:21<21:51:07,  1.35s/it]
  6%|▌         | 3736/61904 [1:25:23<21:58:22,  1.36s/it]
  6%|▌         | 3737/61904 [1:25:24<22:03:32,  1.37s/it]
  6%|▌         | 3738/61904 [1:25:25<21:53:01,  1.35s/it]
  6%|▌         | 3739/61904 [1:25:27<22:00:45,  1.36s/it]
  6%|▌         | 3740/61904 [1:25:28<21:55:31,  1.36s/it]
                                                         
{'loss': 3.0071, 'learning_rate': 1.9426293271100739e-07, 'epoch': 0.97}

  6%|▌         | 3740/61904 [1:25:28<21:55:31,  1.36s/it]
  6%|▌         | 3741/61904 [1:25:29<22:03:20,  1.37s/it]
  6%|▌         | 3742/61904 [1:25:31<22:09:12,  1.37s/it]
  6%|▌         | 3743/61904 [1:25:32<22:17:53,  1.38s/it]
  6%|▌         | 3744/61904 [1:25:34<22:00:00,  1.36s/it]
  6%|▌         | 3745/61904 [1:25:35<22:10:15,  1.37s/it]
  6%|▌         | 3746/61904 [1:25:36<22:52:44,  1.42s/it]
  6%|▌         | 3747/61904 [1:25:38<22:19:48,  1.38s/it]
  6%|▌         | 3748/61904 [1:25:39<21:27:03,  1.33s/it]
  6%|▌         | 3749/61904 [1:25:40<21:13:36,  1.31s/it]
  6%|▌         | 3750/61904 [1:25:42<22:12:05,  1.37s/it]
  6%|▌         | 3751/61904 [1:25:43<21:59:43,  1.36s/it]
  6%|▌         | 3752/61904 [1:25:45<22:22:30,  1.39s/it]
  6%|▌         | 3753/61904 [1:25:46<21:54:43,  1.36s/it]
  6%|▌         | 3754/61904 [1:25:47<21:25:13,  1.33s/it]
  6%|▌         | 3755/61904 [1:25:49<22:10:13,  1.37s/it]
  6%|▌         | 3756/61904 [1:25:50<23:01:29,  1.43s/it]
  6%|▌         | 3757/61904 [1:25:51<22:37:28,  1.40s/it]
  6%|▌         | 3758/61904 [1:25:53<22:08:40,  1.37s/it]
  6%|▌         | 3759/61904 [1:25:54<21:22:00,  1.32s/it]
  6%|▌         | 3760/61904 [1:25:55<21:48:36,  1.35s/it]
                                                         
{'loss': 2.9836, 'learning_rate': 1.9423051990146505e-07, 'epoch': 0.97}

  6%|▌         | 3760/61904 [1:25:55<21:48:36,  1.35s/it]
  6%|▌         | 3761/61904 [1:25:57<22:26:00,  1.39s/it]
  6%|▌         | 3762/61904 [1:25:58<22:10:19,  1.37s/it]
  6%|▌         | 3763/61904 [1:26:00<22:09:51,  1.37s/it]
  6%|▌         | 3764/61904 [1:26:01<21:51:45,  1.35s/it]
  6%|▌         | 3765/61904 [1:26:02<21:27:59,  1.33s/it]
  6%|▌         | 3766/61904 [1:26:03<21:07:01,  1.31s/it]
  6%|▌         | 3767/61904 [1:26:05<21:10:16,  1.31s/it]
  6%|▌         | 3768/61904 [1:26:06<21:37:21,  1.34s/it]
  6%|▌         | 3769/61904 [1:26:07<21:20:41,  1.32s/it]
  6%|▌         | 3770/61904 [1:26:09<20:50:28,  1.29s/it]
  6%|▌         | 3771/61904 [1:26:10<21:04:35,  1.31s/it]
  6%|▌         | 3772/61904 [1:26:11<20:55:31,  1.30s/it]
  6%|▌         | 3773/61904 [1:26:12<20:43:20,  1.28s/it]
  6%|▌         | 3774/61904 [1:26:14<21:59:01,  1.36s/it]
  6%|▌         | 3775/61904 [1:26:15<21:41:45,  1.34s/it]
  6%|▌         | 3776/61904 [1:26:17<21:26:08,  1.33s/it]
  6%|▌         | 3777/61904 [1:26:18<21:21:10,  1.32s/it]
  6%|▌         | 3778/61904 [1:26:19<21:11:36,  1.31s/it]
  6%|▌         | 3779/61904 [1:26:21<22:01:03,  1.36s/it]
  6%|▌         | 3780/61904 [1:26:22<22:22:08,  1.39s/it]
                                                         
{'loss': 2.9818, 'learning_rate': 1.941981070919227e-07, 'epoch': 0.98}

  6%|▌         | 3780/61904 [1:26:22<22:22:08,  1.39s/it]
  6%|▌         | 3781/61904 [1:26:23<22:08:54,  1.37s/it]
  6%|▌         | 3782/61904 [1:26:25<22:29:19,  1.39s/it]
  6%|▌         | 3783/61904 [1:26:26<22:04:08,  1.37s/it]
  6%|▌         | 3784/61904 [1:26:28<22:12:10,  1.38s/it]
  6%|▌         | 3785/61904 [1:26:29<21:45:52,  1.35s/it]
  6%|▌         | 3786/61904 [1:26:30<21:45:20,  1.35s/it]
  6%|▌         | 3787/61904 [1:26:32<21:35:28,  1.34s/it]
  6%|▌         | 3788/61904 [1:26:33<22:11:08,  1.37s/it]
  6%|▌         | 3789/61904 [1:26:34<21:59:12,  1.36s/it]
  6%|▌         | 3790/61904 [1:26:36<22:28:16,  1.39s/it]
  6%|▌         | 3791/61904 [1:26:37<22:20:59,  1.38s/it]
  6%|▌         | 3792/61904 [1:26:39<22:58:36,  1.42s/it]
  6%|▌         | 3793/61904 [1:26:40<22:08:19,  1.37s/it]
  6%|▌         | 3794/61904 [1:26:41<21:52:32,  1.36s/it]
  6%|▌         | 3795/61904 [1:26:43<22:15:20,  1.38s/it]
  6%|▌         | 3796/61904 [1:26:44<22:39:31,  1.40s/it]
  6%|▌         | 3797/61904 [1:26:45<22:22:29,  1.39s/it]
  6%|▌         | 3798/61904 [1:26:47<22:39:21,  1.40s/it]
  6%|▌         | 3799/61904 [1:26:49<23:53:35,  1.48s/it]
  6%|▌         | 3800/61904 [1:26:50<22:48:36,  1.41s/it]
                                                         
{'loss': 3.1245, 'learning_rate': 1.941656942823804e-07, 'epoch': 0.98}

  6%|▌         | 3800/61904 [1:26:50<22:48:36,  1.41s/it]
  6%|▌         | 3801/61904 [1:26:51<22:12:47,  1.38s/it]
  6%|▌         | 3802/61904 [1:26:53<22:30:36,  1.39s/it]
  6%|▌         | 3803/61904 [1:26:54<22:17:02,  1.38s/it]
  6%|▌         | 3804/61904 [1:26:55<21:57:57,  1.36s/it]
  6%|▌         | 3805/61904 [1:26:57<21:53:39,  1.36s/it]
  6%|▌         | 3806/61904 [1:26:58<22:06:48,  1.37s/it]
  6%|▌         | 3807/61904 [1:26:59<22:29:08,  1.39s/it]
  6%|▌         | 3808/61904 [1:27:01<21:58:51,  1.36s/it]
  6%|▌         | 3809/61904 [1:27:02<21:53:59,  1.36s/it]
  6%|▌         | 3810/61904 [1:27:03<21:29:42,  1.33s/it]
  6%|▌         | 3811/61904 [1:27:05<21:23:34,  1.33s/it]
  6%|▌         | 3812/61904 [1:27:06<21:12:35,  1.31s/it]
  6%|▌         | 3813/61904 [1:27:07<21:40:26,  1.34s/it]
  6%|▌         | 3814/61904 [1:27:09<21:52:08,  1.36s/it]
  6%|▌         | 3815/61904 [1:27:10<21:31:39,  1.33s/it]
  6%|▌         | 3816/61904 [1:27:11<22:01:06,  1.36s/it]
  6%|▌         | 3817/61904 [1:27:13<21:36:11,  1.34s/it]
  6%|▌         | 3818/61904 [1:27:14<21:46:43,  1.35s/it]
  6%|▌         | 3819/61904 [1:27:16<22:04:20,  1.37s/it]
  6%|▌         | 3820/61904 [1:27:17<22:06:12,  1.37s/it]
                                                         
{'loss': 3.0495, 'learning_rate': 1.9413328147283806e-07, 'epoch': 0.99}

  6%|▌         | 3820/61904 [1:27:17<22:06:12,  1.37s/it]
  6%|▌         | 3821/61904 [1:27:18<21:35:10,  1.34s/it]
  6%|▌         | 3822/61904 [1:27:19<21:05:53,  1.31s/it]
  6%|▌         | 3823/61904 [1:27:21<21:12:17,  1.31s/it]
  6%|▌         | 3824/61904 [1:27:22<21:36:50,  1.34s/it]
  6%|▌         | 3825/61904 [1:27:23<21:46:03,  1.35s/it]
  6%|▌         | 3826/61904 [1:27:25<21:35:37,  1.34s/it]
  6%|▌         | 3827/61904 [1:27:26<22:03:57,  1.37s/it]
  6%|▌         | 3828/61904 [1:27:27<21:22:37,  1.33s/it]
  6%|▌         | 3829/61904 [1:27:29<22:11:37,  1.38s/it]
  6%|▌         | 3830/61904 [1:27:30<21:44:42,  1.35s/it]
  6%|▌         | 3831/61904 [1:27:32<22:21:30,  1.39s/it]
  6%|▌         | 3832/61904 [1:27:33<22:20:02,  1.38s/it]
  6%|▌         | 3833/61904 [1:27:34<21:44:55,  1.35s/it]
  6%|▌         | 3834/61904 [1:27:36<21:28:56,  1.33s/it]
  6%|▌         | 3835/61904 [1:27:37<21:25:06,  1.33s/it]
  6%|▌         | 3836/61904 [1:27:39<22:37:13,  1.40s/it]
  6%|▌         | 3837/61904 [1:27:40<21:58:05,  1.36s/it]
  6%|▌         | 3838/61904 [1:27:41<22:25:02,  1.39s/it]
  6%|▌         | 3839/61904 [1:27:43<22:03:21,  1.37s/it]
  6%|▌         | 3840/61904 [1:27:44<22:30:43,  1.40s/it]
                                                         
{'loss': 3.0594, 'learning_rate': 1.9410086866329572e-07, 'epoch': 0.99}

  6%|▌         | 3840/61904 [1:27:44<22:30:43,  1.40s/it]
  6%|▌         | 3841/61904 [1:27:45<22:11:02,  1.38s/it]
  6%|▌         | 3842/61904 [1:27:47<22:27:54,  1.39s/it]
  6%|▌         | 3843/61904 [1:27:48<22:07:09,  1.37s/it]
  6%|▌         | 3844/61904 [1:27:50<22:31:46,  1.40s/it]
  6%|▌         | 3845/61904 [1:27:51<22:40:11,  1.41s/it]
  6%|▌         | 3846/61904 [1:27:52<22:18:09,  1.38s/it]
  6%|▌         | 3847/61904 [1:27:54<21:42:04,  1.35s/it]
  6%|▌         | 3848/61904 [1:27:55<21:47:42,  1.35s/it]
  6%|▌         | 3849/61904 [1:27:56<21:17:03,  1.32s/it]
  6%|▌         | 3850/61904 [1:27:58<21:45:29,  1.35s/it]
  6%|▌         | 3851/61904 [1:27:59<21:48:44,  1.35s/it]
  6%|▌         | 3852/61904 [1:28:00<22:01:24,  1.37s/it]
  6%|▌         | 3853/61904 [1:28:02<22:10:55,  1.38s/it]
  6%|▌         | 3854/61904 [1:28:03<23:24:05,  1.45s/it]
  6%|▌         | 3855/61904 [1:28:05<23:46:51,  1.47s/it]
  6%|▌         | 3856/61904 [1:28:06<22:22:54,  1.39s/it]
  6%|▌         | 3857/61904 [1:28:07<22:03:51,  1.37s/it]
  6%|▌         | 3858/61904 [1:28:09<21:55:57,  1.36s/it]
  6%|▌         | 3859/61904 [1:28:10<22:11:36,  1.38s/it]
  6%|▌         | 3860/61904 [1:28:12<22:09:01,  1.37s/it]
                                                         
{'loss': 3.0219, 'learning_rate': 1.940684558537534e-07, 'epoch': 1.0}

  6%|▌         | 3860/61904 [1:28:12<22:09:01,  1.37s/it]
  6%|▌         | 3861/61904 [1:28:13<21:53:43,  1.36s/it]
  6%|▌         | 3862/61904 [1:28:14<21:57:31,  1.36s/it]
  6%|▌         | 3863/61904 [1:28:16<21:25:27,  1.33s/it]
  6%|▌         | 3864/61904 [1:28:17<20:59:25,  1.30s/it]
  6%|▌         | 3865/61904 [1:28:18<21:25:09,  1.33s/it]
  6%|▌         | 3866/61904 [1:28:20<21:44:27,  1.35s/it]
  6%|▌         | 3867/61904 [1:28:21<21:54:58,  1.36s/it]
  6%|▌         | 3868/61904 [1:28:22<21:38:17,  1.34s/it]
  6%|▋         | 3869/61904 [1:28:24<22:37:29,  1.40s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:03<21:33,  1.51s/it]

  0%|          | 3/861 [00:06<32:23,  2.26s/it]

  0%|          | 4/861 [00:12<50:54,  3.56s/it]

  1%|          | 5/861 [00:14<46:49,  3.28s/it]

  1%|          | 6/861 [00:18<48:27,  3.40s/it]

  1%|          | 7/861 [00:20<42:01,  2.95s/it]

  1%|          | 8/861 [00:23<42:11,  2.97s/it]

  1%|          | 9/861 [00:25<39:17,  2.77s/it]

  1%|          | 10/861 [00:28<38:12,  2.69s/it]

  1%|▏         | 11/861 [00:31<39:52,  2.81s/it]

  1%|▏         | 12/861 [00:35<45:33,  3.22s/it]

  2%|▏         | 13/861 [00:37<41:56,  2.97s/it]

  2%|▏         | 14/861 [00:39<33:42,  2.39s/it]

  2%|▏         | 15/861 [00:41<33:21,  2.37s/it]

  2%|▏         | 16/861 [00:42<28:25,  2.02s/it]

  2%|▏         | 17/861 [00:47<40:38,  2.89s/it]

  2%|▏         | 18/861 [00:48<34:24,  2.45s/it]

  2%|▏         | 19/861 [00:52<41:11,  2.94s/it]

  2%|▏         | 20/861 [00:57<47:30,  3.39s/it]

  2%|▏         | 21/861 [00:59<42:49,  3.06s/it]

  3%|▎         | 22/861 [01:02<41:47,  2.99s/it]

  3%|▎         | 23/861 [01:03<35:15,  2.52s/it]

  3%|▎         | 24/861 [01:07<38:44,  2.78s/it]

  3%|▎         | 25/861 [01:09<35:48,  2.57s/it]

  3%|▎         | 26/861 [01:13<41:50,  3.01s/it]

  3%|▎         | 27/861 [01:16<40:03,  2.88s/it]

  3%|▎         | 28/861 [01:21<49:02,  3.53s/it]

  3%|▎         | 29/861 [01:22<38:27,  2.77s/it]

  3%|▎         | 30/861 [01:26<43:54,  3.17s/it]

  4%|▎         | 31/861 [01:27<35:19,  2.55s/it]

  4%|▎         | 32/861 [01:28<28:24,  2.06s/it]

  4%|▍         | 33/861 [01:31<33:22,  2.42s/it]

  4%|▍         | 34/861 [01:33<31:01,  2.25s/it]

  4%|▍         | 35/861 [01:37<39:37,  2.88s/it]

  4%|▍         | 36/861 [01:39<35:27,  2.58s/it]

  4%|▍         | 37/861 [01:41<32:42,  2.38s/it]

  4%|▍         | 38/861 [01:44<35:37,  2.60s/it]

  5%|▍         | 39/861 [01:46<32:46,  2.39s/it]

  5%|▍         | 40/861 [01:48<32:03,  2.34s/it]

  5%|▍         | 41/861 [01:49<25:57,  1.90s/it]

  5%|▍         | 42/861 [01:53<33:39,  2.47s/it]

  5%|▍         | 43/861 [01:55<33:02,  2.42s/it]

  5%|▌         | 44/861 [01:57<31:38,  2.32s/it]

  5%|▌         | 45/861 [02:00<32:22,  2.38s/it]

  5%|▌         | 46/861 [02:04<40:53,  3.01s/it]

  5%|▌         | 47/861 [02:08<44:01,  3.25s/it]

  6%|▌         | 48/861 [02:11<42:35,  3.14s/it]

  6%|▌         | 49/861 [02:14<41:34,  3.07s/it]

  6%|▌         | 50/861 [02:14<30:29,  2.26s/it]

  6%|▌         | 51/861 [02:17<31:05,  2.30s/it]

  6%|▌         | 52/861 [02:19<30:37,  2.27s/it]

  6%|▌         | 53/861 [02:20<26:24,  1.96s/it]

  6%|▋         | 54/861 [02:21<20:19,  1.51s/it]

  6%|▋         | 55/861 [02:22<19:54,  1.48s/it]

  7%|▋         | 56/861 [02:26<31:44,  2.37s/it]

  7%|▋         | 57/861 [02:27<26:13,  1.96s/it]

  7%|▋         | 58/861 [02:28<22:15,  1.66s/it]

  7%|▋         | 59/861 [02:30<23:03,  1.73s/it]

  7%|▋         | 60/861 [02:32<23:45,  1.78s/it]

  7%|▋         | 61/861 [02:34<22:21,  1.68s/it]

  7%|▋         | 62/861 [02:34<18:57,  1.42s/it]

  7%|▋         | 63/861 [02:36<19:17,  1.45s/it]

  7%|▋         | 64/861 [02:37<19:08,  1.44s/it]

  8%|▊         | 65/861 [02:39<19:53,  1.50s/it]

  8%|▊         | 66/861 [02:40<18:47,  1.42s/it]

  8%|▊         | 67/861 [02:42<21:38,  1.63s/it]

  8%|▊         | 68/861 [02:45<25:32,  1.93s/it]

  8%|▊         | 69/861 [02:49<34:46,  2.63s/it]

  8%|▊         | 70/861 [02:51<32:57,  2.50s/it]

  8%|▊         | 71/861 [02:54<34:18,  2.61s/it]

  8%|▊         | 72/861 [02:57<35:25,  2.69s/it]

  8%|▊         | 73/861 [02:58<27:04,  2.06s/it]

  9%|▊         | 74/861 [03:01<32:29,  2.48s/it]

  9%|▊         | 75/861 [03:04<33:00,  2.52s/it]

  9%|▉         | 76/861 [03:07<35:56,  2.75s/it]

  9%|▉         | 77/861 [03:10<36:38,  2.80s/it]

  9%|▉         | 78/861 [03:11<31:08,  2.39s/it]

  9%|▉         | 79/861 [03:14<33:24,  2.56s/it]

  9%|▉         | 80/861 [03:17<32:04,  2.46s/it]

  9%|▉         | 81/861 [03:22<41:30,  3.19s/it]

 10%|▉         | 82/861 [03:23<33:40,  2.59s/it]

 10%|▉         | 83/861 [03:25<31:39,  2.44s/it]

 10%|▉         | 84/861 [03:28<32:57,  2.54s/it]

 10%|▉         | 85/861 [03:29<30:17,  2.34s/it]

 10%|▉         | 86/861 [03:31<26:11,  2.03s/it]

 10%|█         | 87/861 [03:34<30:13,  2.34s/it]

 10%|█         | 88/861 [03:34<22:51,  1.77s/it]

 10%|█         | 89/861 [03:36<21:51,  1.70s/it]

 10%|█         | 90/861 [03:40<32:34,  2.53s/it]

 11%|█         | 91/861 [03:42<30:08,  2.35s/it]

 11%|█         | 92/861 [03:44<28:04,  2.19s/it]

 11%|█         | 93/861 [03:47<30:58,  2.42s/it]

 11%|█         | 94/861 [03:48<25:06,  1.96s/it]

 11%|█         | 95/861 [03:49<22:58,  1.80s/it]

 11%|█         | 96/861 [03:52<24:57,  1.96s/it]

 11%|█▏        | 97/861 [03:54<28:02,  2.20s/it]

 11%|█▏        | 98/861 [03:56<26:46,  2.11s/it]

 11%|█▏        | 99/861 [04:01<36:52,  2.90s/it]

 12%|█▏        | 100/861 [04:03<32:08,  2.53s/it]

 12%|█▏        | 101/861 [04:04<29:13,  2.31s/it]

 12%|█▏        | 102/861 [04:06<26:21,  2.08s/it]

 12%|█▏        | 103/861 [04:07<22:06,  1.75s/it]

 12%|█▏        | 104/861 [04:12<33:57,  2.69s/it]

 12%|█▏        | 105/861 [04:15<35:08,  2.79s/it]

 12%|█▏        | 106/861 [04:16<30:04,  2.39s/it]

 12%|█▏        | 107/861 [04:18<28:18,  2.25s/it]

 13%|█▎        | 108/861 [04:19<21:29,  1.71s/it]

 13%|█▎        | 109/861 [04:19<17:15,  1.38s/it]

 13%|█▎        | 110/861 [04:22<20:39,  1.65s/it]

 13%|█▎        | 111/861 [04:26<29:12,  2.34s/it]

 13%|█▎        | 112/861 [04:28<29:02,  2.33s/it]

 13%|█▎        | 113/861 [04:30<27:25,  2.20s/it]

 13%|█▎        | 114/861 [04:33<29:32,  2.37s/it]

 13%|█▎        | 115/861 [04:34<25:09,  2.02s/it]

 13%|█▎        | 116/861 [04:35<21:41,  1.75s/it]

 14%|█▎        | 117/861 [04:38<25:23,  2.05s/it]

 14%|█▎        | 118/861 [04:40<25:53,  2.09s/it]

 14%|█▍        | 119/861 [04:42<25:36,  2.07s/it]

 14%|█▍        | 120/861 [04:42<19:29,  1.58s/it]

 14%|█▍        | 121/861 [04:44<21:39,  1.76s/it]

 14%|█▍        | 122/861 [04:47<25:09,  2.04s/it]

 14%|█▍        | 123/861 [04:49<25:33,  2.08s/it]

 14%|█▍        | 124/861 [04:52<29:25,  2.40s/it]

 15%|█▍        | 125/861 [04:56<31:52,  2.60s/it]

 15%|█▍        | 126/861 [04:58<31:59,  2.61s/it]

 15%|█▍        | 127/861 [05:00<30:22,  2.48s/it]

 15%|█▍        | 128/861 [05:02<28:11,  2.31s/it]

 15%|█▍        | 129/861 [05:05<28:14,  2.32s/it]

 15%|█▌        | 130/861 [05:07<27:16,  2.24s/it]

 15%|█▌        | 131/861 [05:09<26:06,  2.15s/it]

 15%|█▌        | 132/861 [05:12<29:31,  2.43s/it]

 15%|█▌        | 133/861 [05:14<30:26,  2.51s/it]

 16%|█▌        | 134/861 [05:15<22:48,  1.88s/it]

 16%|█▌        | 135/861 [05:16<20:15,  1.67s/it]

 16%|█▌        | 136/861 [05:17<19:11,  1.59s/it]

 16%|█▌        | 137/861 [05:19<18:40,  1.55s/it]

 16%|█▌        | 138/861 [05:20<17:27,  1.45s/it]

 16%|█▌        | 139/861 [05:21<15:53,  1.32s/it]

 16%|█▋        | 140/861 [05:22<15:43,  1.31s/it]

 16%|█▋        | 141/861 [05:24<16:07,  1.34s/it]

 16%|█▋        | 142/861 [05:24<13:51,  1.16s/it]

 17%|█▋        | 143/861 [05:28<22:44,  1.90s/it]

 17%|█▋        | 144/861 [05:31<27:27,  2.30s/it]

 17%|█▋        | 145/861 [05:33<24:35,  2.06s/it]

 17%|█▋        | 146/861 [05:35<23:46,  2.00s/it]

 17%|█▋        | 147/861 [05:37<23:20,  1.96s/it]

 17%|█▋        | 148/861 [05:37<18:48,  1.58s/it]

 17%|█▋        | 149/861 [05:38<15:09,  1.28s/it]

 17%|█▋        | 150/861 [05:42<25:46,  2.17s/it]

 18%|█▊        | 151/861 [05:45<29:06,  2.46s/it]

 18%|█▊        | 152/861 [05:48<29:25,  2.49s/it]

 18%|█▊        | 153/861 [05:51<32:11,  2.73s/it]

 18%|█▊        | 154/861 [05:54<32:58,  2.80s/it]

 18%|█▊        | 155/861 [05:57<34:48,  2.96s/it]

 18%|█▊        | 156/861 [06:01<36:02,  3.07s/it]

 18%|█▊        | 157/861 [06:02<30:44,  2.62s/it]

 18%|█▊        | 158/861 [06:06<33:24,  2.85s/it]

 18%|█▊        | 159/861 [06:08<29:50,  2.55s/it]

 19%|█▊        | 160/861 [06:09<27:30,  2.35s/it]

 19%|█▊        | 161/861 [06:13<33:05,  2.84s/it]

 19%|█▉        | 162/861 [06:14<25:58,  2.23s/it]

 19%|█▉        | 163/861 [06:15<19:47,  1.70s/it]

 19%|█▉        | 164/861 [06:19<29:36,  2.55s/it]

 19%|█▉        | 165/861 [06:22<29:57,  2.58s/it]

 19%|█▉        | 166/861 [06:24<30:04,  2.60s/it]

 19%|█▉        | 167/861 [06:25<22:53,  1.98s/it]

 20%|█▉        | 168/861 [06:27<22:37,  1.96s/it]

 20%|█▉        | 169/861 [06:29<23:32,  2.04s/it]

 20%|█▉        | 170/861 [06:31<23:10,  2.01s/it]

 20%|█▉        | 171/861 [06:32<21:00,  1.83s/it]

 20%|█▉        | 172/861 [06:35<21:46,  1.90s/it]

 20%|██        | 173/861 [06:37<23:55,  2.09s/it]

 20%|██        | 174/861 [06:40<26:43,  2.33s/it]

 20%|██        | 175/861 [06:42<26:16,  2.30s/it]

 20%|██        | 176/861 [06:43<20:24,  1.79s/it]

 21%|██        | 177/861 [06:45<20:25,  1.79s/it]

 21%|██        | 178/861 [06:47<21:41,  1.91s/it]

 21%|██        | 179/861 [06:49<22:50,  2.01s/it]

 21%|██        | 180/861 [06:51<22:39,  2.00s/it]

 21%|██        | 181/861 [06:53<21:47,  1.92s/it]

 21%|██        | 182/861 [06:53<17:37,  1.56s/it]

 21%|██▏       | 183/861 [06:56<19:55,  1.76s/it]

 21%|██▏       | 184/861 [06:59<24:56,  2.21s/it]

 21%|██▏       | 185/861 [07:01<25:07,  2.23s/it]

 22%|██▏       | 186/861 [07:02<21:08,  1.88s/it]

 22%|██▏       | 187/861 [07:05<23:32,  2.10s/it]

 22%|██▏       | 188/861 [07:07<24:20,  2.17s/it]

 22%|██▏       | 189/861 [07:10<25:24,  2.27s/it]

 22%|██▏       | 190/861 [07:12<26:46,  2.39s/it]

 22%|██▏       | 191/861 [07:13<22:11,  1.99s/it]

 22%|██▏       | 192/861 [07:16<22:43,  2.04s/it]

 22%|██▏       | 193/861 [07:19<26:06,  2.35s/it]

 23%|██▎       | 194/861 [07:20<23:20,  2.10s/it]

 23%|██▎       | 195/861 [07:21<20:08,  1.81s/it]

 23%|██▎       | 196/861 [07:26<28:20,  2.56s/it]

 23%|██▎       | 197/861 [07:27<25:19,  2.29s/it]

 23%|██▎       | 198/861 [07:29<23:20,  2.11s/it]

 23%|██▎       | 199/861 [07:32<24:53,  2.26s/it]

 23%|██▎       | 200/861 [07:34<25:27,  2.31s/it]

 23%|██▎       | 201/861 [07:37<26:25,  2.40s/it]

 23%|██▎       | 202/861 [07:38<24:14,  2.21s/it]

 24%|██▎       | 203/861 [07:40<23:13,  2.12s/it]

 24%|██▎       | 204/861 [07:41<18:03,  1.65s/it]

 24%|██▍       | 205/861 [07:42<15:42,  1.44s/it]

 24%|██▍       | 206/861 [07:44<17:21,  1.59s/it]

 24%|██▍       | 207/861 [07:46<18:45,  1.72s/it]

 24%|██▍       | 208/861 [07:47<18:30,  1.70s/it]

 24%|██▍       | 209/861 [07:49<17:22,  1.60s/it]

 24%|██▍       | 210/861 [07:51<19:14,  1.77s/it]

 25%|██▍       | 211/861 [07:55<25:20,  2.34s/it]

 25%|██▍       | 212/861 [07:57<24:27,  2.26s/it]

 25%|██▍       | 213/861 [07:58<21:37,  2.00s/it]

 25%|██▍       | 214/861 [08:00<19:39,  1.82s/it]

 25%|██▍       | 215/861 [08:01<19:04,  1.77s/it]

 25%|██▌       | 216/861 [08:02<17:36,  1.64s/it]

 25%|██▌       | 217/861 [08:03<15:18,  1.43s/it]

 25%|██▌       | 218/861 [08:05<14:55,  1.39s/it]

 25%|██▌       | 219/861 [08:08<20:34,  1.92s/it]

 26%|██▌       | 220/861 [08:10<20:46,  1.94s/it]

 26%|██▌       | 221/861 [08:12<19:40,  1.85s/it]

 26%|██▌       | 222/861 [08:15<25:21,  2.38s/it]

 26%|██▌       | 223/861 [08:18<27:16,  2.56s/it]

 26%|██▌       | 224/861 [08:20<23:43,  2.23s/it]

 26%|██▌       | 225/861 [08:22<24:19,  2.29s/it]

 26%|██▌       | 226/861 [08:25<24:59,  2.36s/it]

 26%|██▋       | 227/861 [08:27<25:12,  2.39s/it]

 26%|██▋       | 228/861 [08:29<23:31,  2.23s/it]

 27%|██▋       | 229/861 [08:31<21:57,  2.09s/it]

 27%|██▋       | 230/861 [08:33<22:52,  2.17s/it]

 27%|██▋       | 231/861 [08:37<27:34,  2.63s/it]

 27%|██▋       | 232/861 [08:37<20:36,  1.97s/it]

 27%|██▋       | 233/861 [08:39<21:25,  2.05s/it]

 27%|██▋       | 234/861 [08:41<20:48,  1.99s/it]

 27%|██▋       | 235/861 [08:44<22:14,  2.13s/it]

 27%|██▋       | 236/861 [08:46<21:58,  2.11s/it]

 28%|██▊       | 237/861 [08:48<21:01,  2.02s/it]

 28%|██▊       | 238/861 [08:48<17:35,  1.69s/it]

 28%|██▊       | 239/861 [08:52<21:50,  2.11s/it]

 28%|██▊       | 240/861 [08:54<23:27,  2.27s/it]

 28%|██▊       | 241/861 [08:58<26:46,  2.59s/it]

 28%|██▊       | 242/861 [08:59<24:16,  2.35s/it]

 28%|██▊       | 243/861 [09:03<26:53,  2.61s/it]

 28%|██▊       | 244/861 [09:05<26:23,  2.57s/it]

 28%|██▊       | 245/861 [09:07<25:13,  2.46s/it]

 29%|██▊       | 246/861 [09:10<25:40,  2.50s/it]

 29%|██▊       | 247/861 [09:11<22:17,  2.18s/it]

 29%|██▉       | 248/861 [09:12<16:51,  1.65s/it]

 29%|██▉       | 249/861 [09:14<18:32,  1.82s/it]

 29%|██▉       | 250/861 [09:17<22:46,  2.24s/it]

 29%|██▉       | 251/861 [09:19<22:34,  2.22s/it]

 29%|██▉       | 252/861 [09:20<18:44,  1.85s/it]

 29%|██▉       | 253/861 [09:22<17:25,  1.72s/it]

 30%|██▉       | 254/861 [09:22<14:02,  1.39s/it]

 30%|██▉       | 255/861 [09:24<15:19,  1.52s/it]

 30%|██▉       | 256/861 [09:26<18:03,  1.79s/it]

 30%|██▉       | 257/861 [09:29<20:13,  2.01s/it]

 30%|██▉       | 258/861 [09:31<20:00,  1.99s/it]

 30%|███       | 259/861 [09:34<23:13,  2.31s/it]

 30%|███       | 260/861 [09:37<24:25,  2.44s/it]

 30%|███       | 261/861 [09:40<27:44,  2.77s/it]

 30%|███       | 262/861 [09:42<23:37,  2.37s/it]

 31%|███       | 263/861 [09:42<17:52,  1.79s/it]

 31%|███       | 264/861 [09:44<17:56,  1.80s/it]

 31%|███       | 265/861 [09:45<15:45,  1.59s/it]

 31%|███       | 266/861 [09:47<15:29,  1.56s/it]

 31%|███       | 267/861 [09:48<15:03,  1.52s/it]

 31%|███       | 268/861 [09:50<16:17,  1.65s/it]

 31%|███       | 269/861 [09:52<17:18,  1.75s/it]

 31%|███▏      | 270/861 [09:54<19:12,  1.95s/it]

 31%|███▏      | 271/861 [09:56<19:36,  1.99s/it]

 32%|███▏      | 272/861 [09:59<21:56,  2.23s/it]

 32%|███▏      | 273/861 [10:01<21:49,  2.23s/it]

 32%|███▏      | 274/861 [10:05<25:34,  2.61s/it]

 32%|███▏      | 275/861 [10:05<19:18,  1.98s/it]

 32%|███▏      | 276/861 [10:08<21:46,  2.23s/it]

 32%|███▏      | 277/861 [10:14<31:17,  3.21s/it]

 32%|███▏      | 278/861 [10:17<30:36,  3.15s/it]

 32%|███▏      | 279/861 [10:19<28:33,  2.94s/it]

 33%|███▎      | 280/861 [10:22<27:32,  2.84s/it]

 33%|███▎      | 281/861 [10:25<27:32,  2.85s/it]

 33%|███▎      | 282/861 [10:27<26:20,  2.73s/it]

 33%|███▎      | 283/861 [10:29<24:18,  2.52s/it]

 33%|███▎      | 284/861 [10:30<19:11,  2.00s/it]

 33%|███▎      | 285/861 [10:32<18:29,  1.93s/it]

 33%|███▎      | 286/861 [10:36<24:33,  2.56s/it]

 33%|███▎      | 287/861 [10:40<29:58,  3.13s/it]

 33%|███▎      | 288/861 [10:43<28:25,  2.98s/it]

 34%|███▎      | 289/861 [10:44<22:51,  2.40s/it]

 34%|███▎      | 290/861 [10:46<21:56,  2.31s/it]

 34%|███▍      | 291/861 [10:49<22:56,  2.41s/it]

 34%|███▍      | 292/861 [10:52<25:16,  2.66s/it]

 34%|███▍      | 293/861 [10:54<23:30,  2.48s/it]

 34%|███▍      | 294/861 [10:57<24:52,  2.63s/it]

 34%|███▍      | 295/861 [10:58<19:17,  2.05s/it]

 34%|███▍      | 296/861 [10:59<18:12,  1.93s/it]

 34%|███▍      | 297/861 [11:03<22:52,  2.43s/it]

 35%|███▍      | 298/861 [11:07<28:30,  3.04s/it]

 35%|███▍      | 299/861 [11:10<27:07,  2.90s/it]

 35%|███▍      | 300/861 [11:12<25:55,  2.77s/it]

 35%|███▍      | 301/861 [11:16<29:00,  3.11s/it]

 35%|███▌      | 302/861 [11:17<21:46,  2.34s/it]

 35%|███▌      | 303/861 [11:21<26:03,  2.80s/it]

 35%|███▌      | 304/861 [11:24<27:30,  2.96s/it]

 35%|███▌      | 305/861 [11:27<27:36,  2.98s/it]

 36%|███▌      | 306/861 [11:31<29:05,  3.15s/it]

 36%|███▌      | 307/861 [11:34<29:38,  3.21s/it]

 36%|███▌      | 308/861 [11:35<22:11,  2.41s/it]

 36%|███▌      | 309/861 [11:36<20:37,  2.24s/it]

 36%|███▌      | 310/861 [11:38<19:47,  2.16s/it]

 36%|███▌      | 311/861 [11:43<25:41,  2.80s/it]

 36%|███▌      | 312/861 [11:45<25:26,  2.78s/it]

 36%|███▋      | 313/861 [11:50<29:05,  3.19s/it]

 36%|███▋      | 314/861 [11:52<28:20,  3.11s/it]

 37%|███▋      | 315/861 [11:55<26:54,  2.96s/it]

 37%|███▋      | 316/861 [11:57<25:22,  2.79s/it]

 37%|███▋      | 317/861 [11:58<19:15,  2.12s/it]

 37%|███▋      | 318/861 [12:01<22:09,  2.45s/it]

 37%|███▋      | 319/861 [12:04<23:16,  2.58s/it]

 37%|███▋      | 320/861 [12:06<22:12,  2.46s/it]

 37%|███▋      | 321/861 [12:10<24:13,  2.69s/it]

 37%|███▋      | 322/861 [12:14<28:01,  3.12s/it]

 38%|███▊      | 323/861 [12:17<27:26,  3.06s/it]

 38%|███▊      | 324/861 [12:22<34:31,  3.86s/it]

 38%|███▊      | 325/861 [12:25<31:53,  3.57s/it]

 38%|███▊      | 326/861 [12:26<23:22,  2.62s/it]

 38%|███▊      | 327/861 [12:29<26:02,  2.93s/it]

 38%|███▊      | 328/861 [12:31<24:09,  2.72s/it]

 38%|███▊      | 329/861 [12:36<28:16,  3.19s/it]

 38%|███▊      | 330/861 [12:38<26:05,  2.95s/it]

 38%|███▊      | 331/861 [12:43<30:40,  3.47s/it]

 39%|███▊      | 332/861 [12:45<27:18,  3.10s/it]

 39%|███▊      | 333/861 [12:49<28:39,  3.26s/it]

 39%|███▉      | 334/861 [12:53<30:58,  3.53s/it]

 39%|███▉      | 335/861 [12:56<30:10,  3.44s/it]

 39%|███▉      | 336/861 [13:00<30:01,  3.43s/it]

 39%|███▉      | 337/861 [13:01<25:14,  2.89s/it]

 39%|███▉      | 338/861 [13:05<28:13,  3.24s/it]

 39%|███▉      | 339/861 [13:08<26:20,  3.03s/it]

 39%|███▉      | 340/861 [13:09<22:54,  2.64s/it]

 40%|███▉      | 341/861 [13:10<18:30,  2.14s/it]

 40%|███▉      | 342/861 [13:12<17:33,  2.03s/it]

 40%|███▉      | 343/861 [13:14<17:56,  2.08s/it]

 40%|███▉      | 344/861 [13:16<16:55,  1.96s/it]

 40%|████      | 345/861 [13:18<17:50,  2.08s/it]

 40%|████      | 346/861 [13:21<18:33,  2.16s/it]

 40%|████      | 347/861 [13:22<17:10,  2.01s/it]

 40%|████      | 348/861 [13:24<16:00,  1.87s/it]

 41%|████      | 349/861 [13:27<18:39,  2.19s/it]

 41%|████      | 350/861 [13:30<19:52,  2.33s/it]

 41%|████      | 351/861 [13:32<18:53,  2.22s/it]

 41%|████      | 352/861 [13:33<17:44,  2.09s/it]

 41%|████      | 353/861 [13:35<17:01,  2.01s/it]

 41%|████      | 354/861 [13:37<17:46,  2.10s/it]

 41%|████      | 355/861 [13:38<14:24,  1.71s/it]

 41%|████▏     | 356/861 [13:39<13:01,  1.55s/it]

 41%|████▏     | 357/861 [13:40<11:10,  1.33s/it]

 42%|████▏     | 358/861 [13:42<11:10,  1.33s/it]

 42%|████▏     | 359/861 [13:44<13:17,  1.59s/it]

 42%|████▏     | 360/861 [13:47<17:10,  2.06s/it]

 42%|████▏     | 361/861 [13:49<17:55,  2.15s/it]

 42%|████▏     | 362/861 [13:51<17:11,  2.07s/it]

 42%|████▏     | 363/861 [13:54<20:12,  2.43s/it]

 42%|████▏     | 364/861 [13:57<21:32,  2.60s/it]

 42%|████▏     | 365/861 [14:01<25:03,  3.03s/it]

 43%|████▎     | 366/861 [14:04<22:40,  2.75s/it]

 43%|████▎     | 367/861 [14:07<25:13,  3.06s/it]

 43%|████▎     | 368/861 [14:12<29:40,  3.61s/it]

 43%|████▎     | 369/861 [14:15<26:28,  3.23s/it]

 43%|████▎     | 370/861 [14:17<23:41,  2.89s/it]

 43%|████▎     | 371/861 [14:20<25:03,  3.07s/it]

 43%|████▎     | 372/861 [14:23<25:25,  3.12s/it]

 43%|████▎     | 373/861 [14:26<23:44,  2.92s/it]

 43%|████▎     | 374/861 [14:29<25:18,  3.12s/it]

 44%|████▎     | 375/861 [14:34<28:37,  3.53s/it]

 44%|████▎     | 376/861 [14:36<23:49,  2.95s/it]

 44%|████▍     | 377/861 [14:38<23:12,  2.88s/it]

 44%|████▍     | 378/861 [14:42<26:11,  3.25s/it]

 44%|████▍     | 379/861 [14:43<19:34,  2.44s/it]

 44%|████▍     | 380/861 [14:45<18:15,  2.28s/it]

 44%|████▍     | 381/861 [14:47<17:21,  2.17s/it]

 44%|████▍     | 382/861 [14:49<18:24,  2.31s/it]

 44%|████▍     | 383/861 [14:51<17:35,  2.21s/it]

 45%|████▍     | 384/861 [14:54<17:58,  2.26s/it]

 45%|████▍     | 385/861 [14:55<14:33,  1.84s/it]

 45%|████▍     | 386/861 [14:57<16:50,  2.13s/it]

 45%|████▍     | 387/861 [15:00<18:09,  2.30s/it]

 45%|████▌     | 388/861 [15:01<15:44,  2.00s/it]

 45%|████▌     | 389/861 [15:02<13:17,  1.69s/it]

 45%|████▌     | 390/861 [15:04<13:11,  1.68s/it]

 45%|████▌     | 391/861 [15:06<13:04,  1.67s/it]

 46%|████▌     | 392/861 [15:08<13:29,  1.73s/it]

 46%|████▌     | 393/861 [15:10<15:09,  1.94s/it]

 46%|████▌     | 394/861 [15:14<19:40,  2.53s/it]

 46%|████▌     | 395/861 [15:15<16:25,  2.11s/it]

 46%|████▌     | 396/861 [15:16<14:38,  1.89s/it]

 46%|████▌     | 397/861 [15:17<11:37,  1.50s/it]

 46%|████▌     | 398/861 [15:19<13:09,  1.71s/it]

 46%|████▋     | 399/861 [15:22<14:50,  1.93s/it]

 46%|████▋     | 400/861 [15:24<15:54,  2.07s/it]

 47%|████▋     | 401/861 [15:25<13:13,  1.73s/it]

 47%|████▋     | 402/861 [15:26<12:26,  1.63s/it]

 47%|████▋     | 403/861 [15:29<13:40,  1.79s/it]

 47%|████▋     | 404/861 [15:31<14:44,  1.93s/it]

 47%|████▋     | 405/861 [15:32<13:01,  1.71s/it]

 47%|████▋     | 406/861 [15:35<15:03,  1.98s/it]

 47%|████▋     | 407/861 [15:37<15:35,  2.06s/it]

 47%|████▋     | 408/861 [15:39<15:22,  2.04s/it]

 48%|████▊     | 409/861 [15:41<14:47,  1.96s/it]

 48%|████▊     | 410/861 [15:42<13:32,  1.80s/it]

 48%|████▊     | 411/861 [15:43<12:14,  1.63s/it]

 48%|████▊     | 412/861 [15:47<15:52,  2.12s/it]

 48%|████▊     | 413/861 [15:48<14:26,  1.93s/it]

 48%|████▊     | 414/861 [15:49<12:52,  1.73s/it]

 48%|████▊     | 415/861 [15:51<11:52,  1.60s/it]

 48%|████▊     | 416/861 [15:52<11:03,  1.49s/it]

 48%|████▊     | 417/861 [15:53<11:19,  1.53s/it]

 49%|████▊     | 418/861 [15:55<11:48,  1.60s/it]

 49%|████▊     | 419/861 [15:57<12:24,  1.68s/it]

 49%|████▉     | 420/861 [15:59<12:51,  1.75s/it]

 49%|████▉     | 421/861 [16:00<10:50,  1.48s/it]

 49%|████▉     | 422/861 [16:01<10:00,  1.37s/it]

 49%|████▉     | 423/861 [16:03<12:34,  1.72s/it]

 49%|████▉     | 424/861 [16:05<12:44,  1.75s/it]

 49%|████▉     | 425/861 [16:07<12:25,  1.71s/it]

 49%|████▉     | 426/861 [16:09<14:18,  1.97s/it]

 50%|████▉     | 427/861 [16:11<14:12,  1.96s/it]

 50%|████▉     | 428/861 [16:13<13:19,  1.85s/it]

 50%|████▉     | 429/861 [16:15<13:59,  1.94s/it]

 50%|████▉     | 430/861 [16:18<16:30,  2.30s/it]

 50%|█████     | 431/861 [16:21<17:48,  2.48s/it]

 50%|█████     | 432/861 [16:24<18:40,  2.61s/it]

 50%|█████     | 433/861 [16:27<18:39,  2.62s/it]

 50%|█████     | 434/861 [16:28<16:38,  2.34s/it]

 51%|█████     | 435/861 [16:29<12:31,  1.76s/it]

 51%|█████     | 436/861 [16:30<10:11,  1.44s/it]

 51%|█████     | 437/861 [16:32<11:20,  1.61s/it]

 51%|█████     | 438/861 [16:32<09:54,  1.41s/it]

 51%|█████     | 439/861 [16:34<10:09,  1.44s/it]

 51%|█████     | 440/861 [16:35<08:45,  1.25s/it]

 51%|█████     | 441/861 [16:36<07:39,  1.09s/it]

 51%|█████▏    | 442/861 [16:38<09:30,  1.36s/it]

 51%|█████▏    | 443/861 [16:38<08:39,  1.24s/it]

 52%|█████▏    | 444/861 [16:40<08:31,  1.23s/it]

 52%|█████▏    | 445/861 [16:41<07:58,  1.15s/it]

 52%|█████▏    | 446/861 [16:42<07:59,  1.15s/it]

 52%|█████▏    | 447/861 [16:45<11:48,  1.71s/it]

 52%|█████▏    | 448/861 [16:47<13:00,  1.89s/it]

 52%|█████▏    | 449/861 [16:50<14:27,  2.11s/it]

 52%|█████▏    | 450/861 [16:52<14:27,  2.11s/it]

 52%|█████▏    | 451/861 [16:54<13:32,  1.98s/it]

 52%|█████▏    | 452/861 [16:56<13:29,  1.98s/it]

 53%|█████▎    | 453/861 [16:57<12:02,  1.77s/it]

 53%|█████▎    | 454/861 [16:58<11:22,  1.68s/it]

 53%|█████▎    | 455/861 [17:00<12:01,  1.78s/it]

 53%|█████▎    | 456/861 [17:02<10:55,  1.62s/it]

 53%|█████▎    | 457/861 [17:04<11:39,  1.73s/it]

 53%|█████▎    | 458/861 [17:06<13:26,  2.00s/it]

 53%|█████▎    | 459/861 [17:07<12:02,  1.80s/it]

 53%|█████▎    | 460/861 [17:09<11:30,  1.72s/it]

 54%|█████▎    | 461/861 [17:11<12:21,  1.85s/it]

 54%|█████▎    | 462/861 [17:12<10:59,  1.65s/it]

 54%|█████▍    | 463/861 [17:14<10:09,  1.53s/it]

 54%|█████▍    | 464/861 [17:15<09:36,  1.45s/it]

 54%|█████▍    | 465/861 [17:15<07:33,  1.15s/it]

 54%|█████▍    | 466/861 [17:17<07:49,  1.19s/it]

 54%|█████▍    | 467/861 [17:21<13:19,  2.03s/it]

 54%|█████▍    | 468/861 [17:21<10:40,  1.63s/it]

 54%|█████▍    | 469/861 [17:23<10:39,  1.63s/it]

 55%|█████▍    | 470/861 [17:24<08:58,  1.38s/it]

 55%|█████▍    | 471/861 [17:25<09:24,  1.45s/it]

 55%|█████▍    | 472/861 [17:26<08:03,  1.24s/it]

 55%|█████▍    | 473/861 [17:27<08:08,  1.26s/it]

 55%|█████▌    | 474/861 [17:28<06:32,  1.01s/it]

 55%|█████▌    | 475/861 [17:29<07:31,  1.17s/it]

 55%|█████▌    | 476/861 [17:30<06:27,  1.01s/it]

 55%|█████▌    | 477/861 [17:32<08:25,  1.32s/it]

 56%|█████▌    | 478/861 [17:33<08:38,  1.35s/it]

 56%|█████▌    | 479/861 [17:34<06:57,  1.09s/it]

 56%|█████▌    | 480/861 [17:35<07:29,  1.18s/it]

 56%|█████▌    | 481/861 [17:36<06:53,  1.09s/it]

 56%|█████▌    | 482/861 [17:37<06:29,  1.03s/it]

 56%|█████▌    | 483/861 [17:38<05:55,  1.06it/s]

 56%|█████▌    | 484/861 [17:39<06:03,  1.04it/s]

 56%|█████▋    | 485/861 [17:40<05:31,  1.13it/s]

 56%|█████▋    | 486/861 [17:40<04:45,  1.31it/s]

 57%|█████▋    | 487/861 [17:41<06:05,  1.02it/s]

 57%|█████▋    | 488/861 [17:42<05:03,  1.23it/s]

 57%|█████▋    | 489/861 [17:43<05:56,  1.04it/s]

 57%|█████▋    | 490/861 [17:44<05:30,  1.12it/s]

 57%|█████▋    | 491/861 [17:45<05:38,  1.09it/s]

 57%|█████▋    | 492/861 [17:46<05:10,  1.19it/s]

 57%|█████▋    | 493/861 [17:47<06:11,  1.01s/it]

 57%|█████▋    | 494/861 [17:48<05:16,  1.16it/s]

 57%|█████▋    | 495/861 [17:49<07:04,  1.16s/it]

 58%|█████▊    | 496/861 [17:51<08:21,  1.37s/it]

 58%|█████▊    | 497/861 [17:52<06:35,  1.09s/it]

 58%|█████▊    | 498/861 [17:53<07:10,  1.18s/it]

 58%|█████▊    | 499/861 [17:53<05:37,  1.07it/s]

 58%|█████▊    | 500/861 [17:55<05:57,  1.01it/s]

 58%|█████▊    | 501/861 [17:55<04:57,  1.21it/s]

 58%|█████▊    | 502/861 [17:57<06:36,  1.10s/it]

 58%|█████▊    | 503/861 [17:58<06:44,  1.13s/it]

 59%|█████▊    | 504/861 [17:59<07:09,  1.20s/it]

 59%|█████▊    | 505/861 [18:00<06:09,  1.04s/it]

 59%|█████▉    | 506/861 [18:01<05:30,  1.07it/s]

 59%|█████▉    | 507/861 [18:01<04:31,  1.30it/s]

 59%|█████▉    | 508/861 [18:03<06:39,  1.13s/it]

 59%|█████▉    | 509/861 [18:06<09:10,  1.56s/it]

 59%|█████▉    | 510/861 [18:08<10:03,  1.72s/it]

 59%|█████▉    | 511/861 [18:10<11:03,  1.90s/it]

 59%|█████▉    | 512/861 [18:11<09:54,  1.70s/it]

 60%|█████▉    | 513/861 [18:13<09:33,  1.65s/it]

 60%|█████▉    | 514/861 [18:14<09:29,  1.64s/it]

 60%|█████▉    | 515/861 [18:15<07:27,  1.29s/it]

 60%|█████▉    | 516/861 [18:15<05:52,  1.02s/it]

 60%|██████    | 517/861 [18:16<04:45,  1.21it/s]

 60%|██████    | 518/861 [18:17<06:20,  1.11s/it]

 60%|██████    | 519/861 [18:19<07:23,  1.30s/it]

 60%|██████    | 520/861 [18:21<08:24,  1.48s/it]

 61%|██████    | 521/861 [18:22<08:10,  1.44s/it]

 61%|██████    | 522/861 [18:24<08:53,  1.57s/it]

 61%|██████    | 523/861 [18:26<09:37,  1.71s/it]

 61%|██████    | 524/861 [18:29<11:46,  2.10s/it]

 61%|██████    | 525/861 [18:31<10:54,  1.95s/it]

 61%|██████    | 526/861 [18:32<10:07,  1.81s/it]

 61%|██████    | 527/861 [18:34<09:34,  1.72s/it]

 61%|██████▏   | 528/861 [18:36<10:42,  1.93s/it]

 61%|██████▏   | 529/861 [18:37<08:44,  1.58s/it]

 62%|██████▏   | 530/861 [18:38<07:57,  1.44s/it]

 62%|██████▏   | 531/861 [18:39<07:06,  1.29s/it]

 62%|██████▏   | 532/861 [18:41<07:57,  1.45s/it]

 62%|██████▏   | 533/861 [18:42<07:05,  1.30s/it]

 62%|██████▏   | 534/861 [18:43<07:06,  1.30s/it]

 62%|██████▏   | 535/861 [18:44<07:02,  1.30s/it]

 62%|██████▏   | 536/861 [18:46<07:11,  1.33s/it]

 62%|██████▏   | 537/861 [18:48<08:44,  1.62s/it]

 62%|██████▏   | 538/861 [18:49<07:44,  1.44s/it]

 63%|██████▎   | 539/861 [18:53<10:53,  2.03s/it]

 63%|██████▎   | 540/861 [18:54<10:30,  1.96s/it]

 63%|██████▎   | 541/861 [18:56<09:25,  1.77s/it]

 63%|██████▎   | 542/861 [18:57<08:28,  1.60s/it]

 63%|██████▎   | 543/861 [18:59<09:37,  1.82s/it]

 63%|██████▎   | 544/861 [19:00<08:27,  1.60s/it]

 63%|██████▎   | 545/861 [19:03<10:25,  1.98s/it]

 63%|██████▎   | 546/861 [19:05<10:46,  2.05s/it]

 64%|██████▎   | 547/861 [19:07<10:21,  1.98s/it]

 64%|██████▎   | 548/861 [19:10<12:00,  2.30s/it]

 64%|██████▍   | 549/861 [19:13<12:19,  2.37s/it]

 64%|██████▍   | 550/861 [19:15<12:07,  2.34s/it]

 64%|██████▍   | 551/861 [19:17<11:23,  2.20s/it]

 64%|██████▍   | 552/861 [19:20<12:59,  2.52s/it]

 64%|██████▍   | 553/861 [19:24<14:05,  2.75s/it]

 64%|██████▍   | 554/861 [19:27<14:51,  2.91s/it]

 64%|██████▍   | 555/861 [19:30<15:15,  2.99s/it]

 65%|██████▍   | 556/861 [19:33<14:48,  2.91s/it]

 65%|██████▍   | 557/861 [19:36<15:11,  3.00s/it]

 65%|██████▍   | 558/861 [19:39<15:34,  3.08s/it]

 65%|██████▍   | 559/861 [19:43<16:12,  3.22s/it]

 65%|██████▌   | 560/861 [19:46<16:05,  3.21s/it]

 65%|██████▌   | 561/861 [19:48<14:49,  2.97s/it]

 65%|██████▌   | 562/861 [19:53<16:46,  3.36s/it]

 65%|██████▌   | 563/861 [19:55<15:33,  3.13s/it]

 66%|██████▌   | 564/861 [19:59<16:41,  3.37s/it]

 66%|██████▌   | 565/861 [20:03<17:03,  3.46s/it]

 66%|██████▌   | 566/861 [20:08<18:57,  3.86s/it]

 66%|██████▌   | 567/861 [20:10<17:01,  3.47s/it]

 66%|██████▌   | 568/861 [20:13<16:30,  3.38s/it]

 66%|██████▌   | 569/861 [20:16<15:50,  3.26s/it]

 66%|██████▌   | 570/861 [20:19<14:21,  2.96s/it]

 66%|██████▋   | 571/861 [20:22<14:51,  3.07s/it]

 66%|██████▋   | 572/861 [20:26<15:50,  3.29s/it]

 67%|██████▋   | 573/861 [20:28<13:52,  2.89s/it]

 67%|██████▋   | 574/861 [20:30<13:35,  2.84s/it]

 67%|██████▋   | 575/861 [20:35<16:10,  3.39s/it]

 67%|██████▋   | 576/861 [20:41<19:22,  4.08s/it]

 67%|██████▋   | 577/861 [20:45<19:49,  4.19s/it]

 67%|██████▋   | 578/861 [20:51<21:42,  4.60s/it]

 67%|██████▋   | 579/861 [20:57<23:31,  5.00s/it]

 67%|██████▋   | 580/861 [21:00<20:58,  4.48s/it]

 67%|██████▋   | 581/861 [21:03<18:31,  3.97s/it]

 68%|██████▊   | 582/861 [21:08<19:51,  4.27s/it]

 68%|██████▊   | 583/861 [21:11<18:21,  3.96s/it]

 68%|██████▊   | 584/861 [21:13<16:09,  3.50s/it]

 68%|██████▊   | 585/861 [21:19<18:41,  4.06s/it]

 68%|██████▊   | 586/861 [21:21<15:32,  3.39s/it]

 68%|██████▊   | 587/861 [21:24<15:41,  3.44s/it]

 68%|██████▊   | 588/861 [21:27<14:29,  3.18s/it]

 68%|██████▊   | 589/861 [21:28<12:31,  2.76s/it]

 69%|██████▊   | 590/861 [21:34<16:16,  3.60s/it]

 69%|██████▊   | 591/861 [21:37<14:40,  3.26s/it]

 69%|██████▉   | 592/861 [21:40<14:36,  3.26s/it]

 69%|██████▉   | 593/861 [21:43<14:44,  3.30s/it]

 69%|██████▉   | 594/861 [21:46<14:33,  3.27s/it]

 69%|██████▉   | 595/861 [21:48<12:43,  2.87s/it]

 69%|██████▉   | 596/861 [21:50<10:39,  2.41s/it]

 69%|██████▉   | 597/861 [21:55<14:31,  3.30s/it]

 69%|██████▉   | 598/861 [21:58<14:09,  3.23s/it]

 70%|██████▉   | 599/861 [22:01<13:21,  3.06s/it]

 70%|██████▉   | 600/861 [22:03<12:20,  2.84s/it]

 70%|██████▉   | 601/861 [22:05<11:20,  2.62s/it]

 70%|██████▉   | 602/861 [22:09<12:29,  2.89s/it]

 70%|███████   | 603/861 [22:13<14:05,  3.28s/it]

 70%|███████   | 604/861 [22:16<14:08,  3.30s/it]

 70%|███████   | 605/861 [22:18<12:27,  2.92s/it]

 70%|███████   | 606/861 [22:20<11:07,  2.62s/it]

 70%|███████   | 607/861 [22:22<10:01,  2.37s/it]

 71%|███████   | 608/861 [22:24<09:15,  2.20s/it]

 71%|███████   | 609/861 [22:27<10:57,  2.61s/it]

 71%|███████   | 610/861 [22:31<12:26,  2.97s/it]

 71%|███████   | 611/861 [22:34<11:53,  2.85s/it]

 71%|███████   | 612/861 [22:36<11:24,  2.75s/it]

 71%|███████   | 613/861 [22:38<09:33,  2.31s/it]

 71%|███████▏  | 614/861 [22:40<09:59,  2.43s/it]

 71%|███████▏  | 615/861 [22:43<10:54,  2.66s/it]

 72%|███████▏  | 616/861 [22:49<13:53,  3.40s/it]

 72%|███████▏  | 617/861 [22:52<14:10,  3.49s/it]

 72%|███████▏  | 618/861 [22:55<13:48,  3.41s/it]

 72%|███████▏  | 619/861 [22:58<12:31,  3.11s/it]

 72%|███████▏  | 620/861 [23:02<13:31,  3.37s/it]

 72%|███████▏  | 621/861 [23:05<12:55,  3.23s/it]

 72%|███████▏  | 622/861 [23:06<10:54,  2.74s/it]

 72%|███████▏  | 623/861 [23:11<13:03,  3.29s/it]

 72%|███████▏  | 624/861 [23:14<12:47,  3.24s/it]

 73%|███████▎  | 625/861 [23:15<10:15,  2.61s/it]

 73%|███████▎  | 626/861 [23:17<09:23,  2.40s/it]

 73%|███████▎  | 627/861 [23:21<10:40,  2.74s/it]

 73%|███████▎  | 628/861 [23:24<11:19,  2.92s/it]

 73%|███████▎  | 629/861 [23:28<12:43,  3.29s/it]

 73%|███████▎  | 630/861 [23:32<12:47,  3.32s/it]

 73%|███████▎  | 631/861 [23:33<10:02,  2.62s/it]

 73%|███████▎  | 632/861 [23:36<10:41,  2.80s/it]

 74%|███████▎  | 633/861 [23:38<10:18,  2.71s/it]

 74%|███████▎  | 634/861 [23:42<11:24,  3.02s/it]

 74%|███████▍  | 635/861 [23:44<10:37,  2.82s/it]

 74%|███████▍  | 636/861 [23:46<09:38,  2.57s/it]

 74%|███████▍  | 637/861 [23:48<08:40,  2.32s/it]

 74%|███████▍  | 638/861 [23:50<08:03,  2.17s/it]

 74%|███████▍  | 639/861 [23:53<09:11,  2.48s/it]

 74%|███████▍  | 640/861 [23:55<08:39,  2.35s/it]

 74%|███████▍  | 641/861 [23:57<08:37,  2.35s/it]

 75%|███████▍  | 642/861 [23:59<07:54,  2.16s/it]

 75%|███████▍  | 643/861 [24:01<07:26,  2.05s/it]

 75%|███████▍  | 644/861 [24:03<07:24,  2.05s/it]

 75%|███████▍  | 645/861 [24:04<06:04,  1.69s/it]

 75%|███████▌  | 646/861 [24:05<05:52,  1.64s/it]

 75%|███████▌  | 647/861 [24:06<05:05,  1.43s/it]

 75%|███████▌  | 648/861 [24:08<05:31,  1.56s/it]

 75%|███████▌  | 649/861 [24:10<05:36,  1.59s/it]

 75%|███████▌  | 650/861 [24:11<05:26,  1.55s/it]

 76%|███████▌  | 651/861 [24:12<04:42,  1.35s/it]

 76%|███████▌  | 652/861 [24:14<04:56,  1.42s/it]

 76%|███████▌  | 653/861 [24:15<04:36,  1.33s/it]

 76%|███████▌  | 654/861 [24:16<04:30,  1.31s/it]

 76%|███████▌  | 655/861 [24:17<04:00,  1.17s/it]

 76%|███████▌  | 656/861 [24:18<03:26,  1.01s/it]

 76%|███████▋  | 657/861 [24:19<03:33,  1.05s/it]

 76%|███████▋  | 658/861 [24:20<04:14,  1.25s/it]

 77%|███████▋  | 659/861 [24:22<04:14,  1.26s/it]

 77%|███████▋  | 660/861 [24:24<04:50,  1.45s/it]

 77%|███████▋  | 661/861 [24:25<04:56,  1.48s/it]

 77%|███████▋  | 662/861 [24:28<05:56,  1.79s/it]

 77%|███████▋  | 663/861 [24:31<06:55,  2.10s/it]

 77%|███████▋  | 664/861 [24:32<05:52,  1.79s/it]

 77%|███████▋  | 665/861 [24:33<05:08,  1.58s/it]

 77%|███████▋  | 666/861 [24:34<04:28,  1.38s/it]

 77%|███████▋  | 667/861 [24:35<04:28,  1.38s/it]

 78%|███████▊  | 668/861 [24:36<04:16,  1.33s/it]

 78%|███████▊  | 669/861 [24:37<03:42,  1.16s/it]

 78%|███████▊  | 670/861 [24:38<03:51,  1.21s/it]

 78%|███████▊  | 671/861 [24:39<03:11,  1.01s/it]

 78%|███████▊  | 672/861 [24:41<04:24,  1.40s/it]

 78%|███████▊  | 673/861 [24:44<05:20,  1.71s/it]

 78%|███████▊  | 674/861 [24:45<04:56,  1.59s/it]

 78%|███████▊  | 675/861 [24:50<07:50,  2.53s/it]

 79%|███████▊  | 676/861 [24:51<06:50,  2.22s/it]

 79%|███████▊  | 677/861 [24:53<06:37,  2.16s/it]

 79%|███████▊  | 678/861 [24:54<05:30,  1.81s/it]

 79%|███████▉  | 679/861 [24:55<04:57,  1.64s/it]

 79%|███████▉  | 680/861 [24:56<04:17,  1.42s/it]

 79%|███████▉  | 681/861 [24:59<05:06,  1.70s/it]

 79%|███████▉  | 682/861 [25:02<06:07,  2.05s/it]

 79%|███████▉  | 683/861 [25:03<05:26,  1.83s/it]

 79%|███████▉  | 684/861 [25:05<06:07,  2.08s/it]

 80%|███████▉  | 685/861 [25:07<05:20,  1.82s/it]

 80%|███████▉  | 686/861 [25:08<04:50,  1.66s/it]

 80%|███████▉  | 687/861 [25:12<06:54,  2.38s/it]

 80%|███████▉  | 688/861 [25:13<05:43,  1.99s/it]

 80%|████████  | 689/861 [25:15<05:16,  1.84s/it]

 80%|████████  | 690/861 [25:16<04:55,  1.73s/it]

 80%|████████  | 691/861 [25:18<05:12,  1.84s/it]

 80%|████████  | 692/861 [25:20<05:01,  1.78s/it]

 80%|████████  | 693/861 [25:21<04:37,  1.65s/it]

 81%|████████  | 694/861 [25:22<04:07,  1.48s/it]

 81%|████████  | 695/861 [25:25<04:45,  1.72s/it]

 81%|████████  | 696/861 [25:26<04:08,  1.51s/it]

 81%|████████  | 697/861 [25:27<04:00,  1.47s/it]

 81%|████████  | 698/861 [25:28<03:59,  1.47s/it]

 81%|████████  | 699/861 [25:33<06:19,  2.34s/it]

 81%|████████▏ | 700/861 [25:36<07:07,  2.65s/it]

 81%|████████▏ | 701/861 [25:38<06:19,  2.37s/it]

 82%|████████▏ | 702/861 [25:39<05:39,  2.13s/it]

 82%|████████▏ | 703/861 [25:41<05:01,  1.91s/it]

 82%|████████▏ | 704/861 [25:42<04:42,  1.80s/it]

 82%|████████▏ | 705/861 [25:44<04:38,  1.79s/it]

 82%|████████▏ | 706/861 [25:45<03:59,  1.54s/it]

 82%|████████▏ | 707/861 [25:46<03:22,  1.32s/it]

 82%|████████▏ | 708/861 [25:47<03:16,  1.28s/it]

 82%|████████▏ | 709/861 [25:49<03:23,  1.34s/it]

 82%|████████▏ | 710/861 [25:51<04:10,  1.66s/it]

 83%|████████▎ | 711/861 [25:53<04:17,  1.72s/it]

 83%|████████▎ | 712/861 [25:54<03:53,  1.57s/it]

 83%|████████▎ | 713/861 [25:55<03:20,  1.35s/it]

 83%|████████▎ | 714/861 [25:56<03:26,  1.40s/it]

 83%|████████▎ | 715/861 [25:59<04:17,  1.77s/it]

 83%|████████▎ | 716/861 [26:01<04:28,  1.85s/it]

 83%|████████▎ | 717/861 [26:02<04:00,  1.67s/it]

 83%|████████▎ | 718/861 [26:04<04:16,  1.79s/it]

 84%|████████▎ | 719/861 [26:05<03:43,  1.57s/it]

 84%|████████▎ | 720/861 [26:06<03:18,  1.41s/it]

 84%|████████▎ | 721/861 [26:08<03:00,  1.29s/it]

 84%|████████▍ | 722/861 [26:09<03:17,  1.42s/it]

 84%|████████▍ | 723/861 [26:10<03:04,  1.33s/it]

 84%|████████▍ | 724/861 [26:12<02:57,  1.30s/it]

 84%|████████▍ | 725/861 [26:13<02:52,  1.27s/it]

 84%|████████▍ | 726/861 [26:14<03:06,  1.38s/it]

 84%|████████▍ | 727/861 [26:17<03:52,  1.73s/it]

 85%|████████▍ | 728/861 [26:19<03:54,  1.77s/it]

 85%|████████▍ | 729/861 [26:20<03:28,  1.58s/it]

 85%|████████▍ | 730/861 [26:21<03:00,  1.38s/it]

 85%|████████▍ | 731/861 [26:23<03:36,  1.67s/it]

 85%|████████▌ | 732/861 [26:24<03:11,  1.48s/it]

 85%|████████▌ | 733/861 [26:26<03:08,  1.47s/it]

 85%|████████▌ | 734/861 [26:26<02:37,  1.24s/it]

 85%|████████▌ | 735/861 [26:27<02:27,  1.17s/it]

 85%|████████▌ | 736/861 [26:29<02:38,  1.27s/it]

 86%|████████▌ | 737/861 [26:31<02:59,  1.45s/it]

 86%|████████▌ | 738/861 [26:32<03:03,  1.49s/it]

 86%|████████▌ | 739/861 [26:34<02:49,  1.39s/it]

 86%|████████▌ | 740/861 [26:35<02:33,  1.27s/it]

 86%|████████▌ | 741/861 [26:36<02:49,  1.41s/it]

 86%|████████▌ | 742/861 [26:38<02:56,  1.49s/it]

 86%|████████▋ | 743/861 [26:39<02:36,  1.33s/it]

 86%|████████▋ | 744/861 [26:40<02:23,  1.23s/it]

 87%|████████▋ | 745/861 [26:42<02:51,  1.48s/it]

 87%|████████▋ | 746/861 [26:43<02:36,  1.36s/it]

 87%|████████▋ | 747/861 [26:45<03:13,  1.69s/it]

 87%|████████▋ | 748/861 [26:48<03:29,  1.85s/it]

 87%|████████▋ | 749/861 [26:50<03:28,  1.86s/it]

 87%|████████▋ | 750/861 [26:51<02:55,  1.58s/it]

 87%|████████▋ | 751/861 [26:51<02:14,  1.22s/it]

 87%|████████▋ | 752/861 [26:55<03:34,  1.97s/it]

 87%|████████▋ | 753/861 [26:57<03:50,  2.13s/it]

 88%|████████▊ | 754/861 [26:58<03:10,  1.78s/it]

 88%|████████▊ | 755/861 [26:59<02:48,  1.59s/it]

 88%|████████▊ | 756/861 [27:01<02:38,  1.51s/it]

 88%|████████▊ | 757/861 [27:03<03:09,  1.82s/it]

 88%|████████▊ | 758/861 [27:04<02:53,  1.68s/it]

 88%|████████▊ | 759/861 [27:06<02:34,  1.52s/it]

 88%|████████▊ | 760/861 [27:08<03:09,  1.88s/it]

 88%|████████▊ | 761/861 [27:14<05:04,  3.04s/it]

 89%|████████▊ | 762/861 [27:15<04:11,  2.54s/it]

 89%|████████▊ | 763/861 [27:17<03:36,  2.21s/it]

 89%|████████▊ | 764/861 [27:19<03:20,  2.06s/it]

 89%|████████▉ | 765/861 [27:21<03:39,  2.29s/it]

 89%|████████▉ | 766/861 [27:24<03:34,  2.26s/it]

 89%|████████▉ | 767/861 [27:29<05:12,  3.32s/it]

 89%|████████▉ | 768/861 [27:32<04:38,  3.00s/it]

 89%|████████▉ | 769/861 [27:34<04:15,  2.77s/it]

 89%|████████▉ | 770/861 [27:35<03:27,  2.28s/it]

 90%|████████▉ | 771/861 [27:36<02:56,  1.96s/it]

 90%|████████▉ | 772/861 [27:39<03:10,  2.14s/it]

 90%|████████▉ | 773/861 [27:42<03:44,  2.55s/it]

 90%|████████▉ | 774/861 [27:44<03:23,  2.34s/it]

 90%|█████████ | 775/861 [27:47<03:31,  2.46s/it]

 90%|█████████ | 776/861 [27:50<03:39,  2.58s/it]

 90%|█████████ | 777/861 [27:53<03:59,  2.86s/it]

 90%|█████████ | 778/861 [27:55<03:38,  2.64s/it]

 90%|█████████ | 779/861 [28:00<04:25,  3.23s/it]

 91%|█████████ | 780/861 [28:04<04:39,  3.45s/it]

 91%|█████████ | 781/861 [28:09<05:10,  3.88s/it]

 91%|█████████ | 782/861 [28:12<04:46,  3.63s/it]

 91%|█████████ | 783/861 [28:14<04:06,  3.16s/it]

 91%|█████████ | 784/861 [28:19<04:38,  3.62s/it]

 91%|█████████ | 785/861 [28:20<03:52,  3.06s/it]

 91%|█████████▏| 786/861 [28:22<03:22,  2.70s/it]

 91%|█████████▏| 787/861 [28:24<02:59,  2.43s/it]

 92%|█████████▏| 788/861 [28:29<03:48,  3.13s/it]

 92%|█████████▏| 789/861 [28:31<03:31,  2.93s/it]

 92%|█████████▏| 790/861 [28:34<03:15,  2.76s/it]

 92%|█████████▏| 791/861 [28:36<03:12,  2.75s/it]

 92%|█████████▏| 792/861 [28:38<02:44,  2.38s/it]

 92%|█████████▏| 793/861 [28:41<02:50,  2.51s/it]

 92%|█████████▏| 794/861 [28:42<02:20,  2.10s/it]

 92%|█████████▏| 795/861 [28:48<03:30,  3.18s/it]

 92%|█████████▏| 796/861 [28:49<02:48,  2.60s/it]

 93%|█████████▎| 797/861 [28:51<02:32,  2.38s/it]

 93%|█████████▎| 798/861 [28:54<02:40,  2.55s/it]

 93%|█████████▎| 799/861 [28:56<02:40,  2.58s/it]

 93%|█████████▎| 800/861 [28:59<02:34,  2.53s/it]

 93%|█████████▎| 801/861 [29:01<02:32,  2.54s/it]

 93%|█████████▎| 802/861 [29:03<02:24,  2.45s/it]

 93%|█████████▎| 803/861 [29:06<02:24,  2.49s/it]

 93%|█████████▎| 804/861 [29:12<03:13,  3.40s/it]

 93%|█████████▎| 805/861 [29:16<03:31,  3.77s/it]

 94%|█████████▎| 806/861 [29:17<02:38,  2.87s/it]

 94%|█████████▎| 807/861 [29:19<02:21,  2.62s/it]

 94%|█████████▍| 808/861 [29:21<02:09,  2.45s/it]

 94%|█████████▍| 809/861 [29:22<01:40,  1.93s/it]

 94%|█████████▍| 810/861 [29:24<01:35,  1.87s/it]

 94%|█████████▍| 811/861 [29:26<01:40,  2.01s/it]

 94%|█████████▍| 812/861 [29:27<01:32,  1.89s/it]

 94%|█████████▍| 813/861 [29:31<01:50,  2.29s/it]

 95%|█████████▍| 814/861 [29:34<01:56,  2.47s/it]

 95%|█████████▍| 815/861 [29:36<01:54,  2.49s/it]

 95%|█████████▍| 816/861 [29:38<01:39,  2.22s/it]

 95%|█████████▍| 817/861 [29:40<01:39,  2.27s/it]

 95%|█████████▌| 818/861 [29:43<01:42,  2.38s/it]

 95%|█████████▌| 819/861 [29:44<01:26,  2.05s/it]

 95%|█████████▌| 820/861 [29:46<01:29,  2.17s/it]

 95%|█████████▌| 821/861 [29:50<01:42,  2.57s/it]

 95%|█████████▌| 822/861 [29:53<01:48,  2.77s/it]

 96%|█████████▌| 823/861 [29:57<01:56,  3.07s/it]

 96%|█████████▌| 824/861 [29:58<01:35,  2.57s/it]

 96%|█████████▌| 825/861 [30:00<01:19,  2.22s/it]

 96%|█████████▌| 826/861 [30:03<01:26,  2.46s/it]

 96%|█████████▌| 827/861 [30:05<01:25,  2.50s/it]

 96%|█████████▌| 828/861 [30:07<01:13,  2.23s/it]

 96%|█████████▋| 829/861 [30:10<01:19,  2.50s/it]

 96%|█████████▋| 830/861 [30:13<01:18,  2.54s/it]

 97%|█████████▋| 831/861 [30:15<01:16,  2.56s/it]

 97%|█████████▋| 832/861 [30:18<01:16,  2.63s/it]

 97%|█████████▋| 833/861 [30:19<01:02,  2.22s/it]

 97%|█████████▋| 834/861 [30:22<01:00,  2.25s/it]

 97%|█████████▋| 835/861 [30:24<00:58,  2.23s/it]

 97%|█████████▋| 836/861 [30:26<00:57,  2.32s/it]

 97%|█████████▋| 837/861 [30:29<00:57,  2.38s/it]

 97%|█████████▋| 838/861 [30:32<00:56,  2.48s/it]

 97%|█████████▋| 839/861 [30:33<00:48,  2.21s/it]

 98%|█████████▊| 840/861 [30:35<00:45,  2.17s/it]

 98%|█████████▊| 841/861 [30:37<00:43,  2.15s/it]

 98%|█████████▊| 842/861 [30:39<00:40,  2.12s/it]

 98%|█████████▊| 843/861 [30:42<00:42,  2.38s/it]

 98%|█████████▊| 844/861 [30:44<00:38,  2.27s/it]

 98%|█████████▊| 845/861 [30:47<00:37,  2.32s/it]

 98%|█████████▊| 846/861 [30:49<00:33,  2.21s/it]

 98%|█████████▊| 847/861 [30:51<00:30,  2.21s/it]

 98%|█████████▊| 848/861 [30:54<00:31,  2.44s/it]

 99%|█████████▊| 849/861 [30:57<00:29,  2.48s/it]

 99%|█████████▊| 850/861 [30:58<00:23,  2.18s/it]

 99%|█████████▉| 851/861 [31:00<00:20,  2.09s/it]

 99%|█████████▉| 852/861 [31:01<00:16,  1.88s/it]

 99%|█████████▉| 853/861 [31:05<00:18,  2.27s/it]

 99%|█████████▉| 854/861 [31:06<00:14,  2.12s/it]

 99%|█████████▉| 855/861 [31:08<00:12,  2.13s/it]

 99%|█████████▉| 856/861 [31:12<00:12,  2.46s/it]

100%|█████████▉| 857/861 [31:14<00:09,  2.32s/it]

100%|█████████▉| 858/861 [31:16<00:06,  2.28s/it]

100%|█████████▉| 859/861 [31:18<00:04,  2.37s/it]

100%|█████████▉| 860/861 [31:24<00:03,  3.23s/it]

100%|██████████| 861/861 [31:26<00:00,  2.85s/it]{'score': 0.07411019411915373, 'counts': [9147, 351, 100, 29], 'totals': [421736, 420014, 418292, 416570], 'precisions': [2.1688923876548363, 0.0835686429499969, 0.023906744570778307, 0.006961615094701971], 'bp': 1.0, 'sys_len': 421736, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.979813814163208, 'eval_bleu': 0.0741, 'eval_gen_len': 114.8177, 'eval_runtime': 1993.3083, 'eval_samples_per_second': 0.864, 'eval_steps_per_second': 0.432, 'epoch': 1.0}

  6%|▋         | 3869/61904 [2:01:38<22:37:29,  1.40s/it]

100%|██████████| 861/861 [33:10<00:00,  2.85s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-25 03:22:47,281 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

  6%|▋         | 3870/61904 [2:01:52<9730:10:48, 603.59s/it]
  6%|▋         | 3871/61904 [2:01:54<6817:16:16, 422.90s/it]
  6%|▋         | 3872/61904 [2:01:55<4778:34:57, 296.44s/it]
  6%|▋         | 3873/61904 [2:01:57<3352:37:10, 207.98s/it]
  6%|▋         | 3874/61904 [2:01:58<2354:23:50, 146.06s/it]
  6%|▋         | 3875/61904 [2:02:00<1655:35:21, 102.71s/it]
  6%|▋         | 3876/61904 [2:02:01<1166:37:02, 72.38s/it] 
  6%|▋         | 3877/61904 [2:02:03<822:42:15, 51.04s/it] 
  6%|▋         | 3878/61904 [2:02:04<583:02:18, 36.17s/it]
  6%|▋         | 3879/61904 [2:02:06<414:54:48, 25.74s/it]
  6%|▋         | 3880/61904 [2:02:07<297:12:41, 18.44s/it]
                                                          
{'loss': 3.0219, 'learning_rate': 1.9403604304421105e-07, 'epoch': 1.0}

  6%|▋         | 3880/61904 [2:02:07<297:12:41, 18.44s/it]
  6%|▋         | 3881/61904 [2:02:08<214:38:11, 13.32s/it]
  6%|▋         | 3882/61904 [2:02:10<157:09:50,  9.75s/it]
  6%|▋         | 3883/61904 [2:02:11<116:33:26,  7.23s/it]
  6%|▋         | 3884/61904 [2:02:13<88:43:15,  5.50s/it] 
  6%|▋         | 3885/61904 [2:02:14<69:09:26,  4.29s/it]
  6%|▋         | 3886/61904 [2:02:15<55:16:04,  3.43s/it]
  6%|▋         | 3887/61904 [2:02:17<45:40:38,  2.83s/it]
  6%|▋         | 3888/61904 [2:02:19<39:43:49,  2.47s/it]
  6%|▋         | 3889/61904 [2:02:20<35:31:27,  2.20s/it]
  6%|▋         | 3890/61904 [2:02:22<31:52:09,  1.98s/it]
  6%|▋         | 3891/61904 [2:02:23<29:19:44,  1.82s/it]
  6%|▋         | 3892/61904 [2:02:24<26:55:09,  1.67s/it]
  6%|▋         | 3893/61904 [2:02:26<26:00:11,  1.61s/it]
  6%|▋         | 3894/61904 [2:02:27<25:00:24,  1.55s/it]
  6%|▋         | 3895/61904 [2:02:29<23:50:16,  1.48s/it]
  6%|▋         | 3896/61904 [2:02:30<23:19:09,  1.45s/it]
  6%|▋         | 3897/61904 [2:02:31<23:37:07,  1.47s/it]
  6%|▋         | 3898/61904 [2:02:33<22:55:14,  1.42s/it]
  6%|▋         | 3899/61904 [2:02:34<22:33:14,  1.40s/it]
  6%|▋         | 3900/61904 [2:02:35<21:50:24,  1.36s/it]
                                                         
{'loss': 3.0378, 'learning_rate': 1.9400363023466873e-07, 'epoch': 1.01}

  6%|▋         | 3900/61904 [2:02:35<21:50:24,  1.36s/it]
  6%|▋         | 3901/61904 [2:02:37<21:52:31,  1.36s/it]
  6%|▋         | 3902/61904 [2:02:38<21:48:03,  1.35s/it]
  6%|▋         | 3903/61904 [2:02:39<21:42:57,  1.35s/it]
  6%|▋         | 3904/61904 [2:02:41<22:11:27,  1.38s/it]
  6%|▋         | 3905/61904 [2:02:42<21:41:42,  1.35s/it]
  6%|▋         | 3906/61904 [2:02:43<21:16:43,  1.32s/it]
  6%|▋         | 3907/61904 [2:02:45<20:43:01,  1.29s/it]
  6%|▋         | 3908/61904 [2:02:46<21:13:35,  1.32s/it]
  6%|▋         | 3909/61904 [2:02:47<21:24:06,  1.33s/it]
  6%|▋         | 3910/61904 [2:02:49<21:56:10,  1.36s/it]
  6%|▋         | 3911/61904 [2:02:50<21:15:30,  1.32s/it]
  6%|▋         | 3912/61904 [2:02:51<20:59:11,  1.30s/it]
  6%|▋         | 3913/61904 [2:02:53<21:08:25,  1.31s/it]
  6%|▋         | 3914/61904 [2:02:54<21:16:06,  1.32s/it]
  6%|▋         | 3915/61904 [2:02:55<21:57:50,  1.36s/it]
  6%|▋         | 3916/61904 [2:02:57<21:42:19,  1.35s/it]
  6%|▋         | 3917/61904 [2:02:58<21:24:50,  1.33s/it]
  6%|▋         | 3918/61904 [2:02:59<21:49:14,  1.35s/it]
  6%|▋         | 3919/61904 [2:03:01<21:56:23,  1.36s/it]
  6%|▋         | 3920/61904 [2:03:02<22:05:47,  1.37s/it]
                                                         
{'loss': 3.058, 'learning_rate': 1.939712174251264e-07, 'epoch': 1.01}

  6%|▋         | 3920/61904 [2:03:02<22:05:47,  1.37s/it]
  6%|▋         | 3921/61904 [2:03:04<22:24:28,  1.39s/it]
  6%|▋         | 3922/61904 [2:03:05<23:03:21,  1.43s/it]
  6%|▋         | 3923/61904 [2:03:07<22:55:23,  1.42s/it]
  6%|▋         | 3924/61904 [2:03:08<22:46:08,  1.41s/it]
  6%|▋         | 3925/61904 [2:03:09<23:12:58,  1.44s/it]
  6%|▋         | 3926/61904 [2:03:11<23:29:19,  1.46s/it]
  6%|▋         | 3927/61904 [2:03:12<23:42:16,  1.47s/it]
  6%|▋         | 3928/61904 [2:03:14<23:23:38,  1.45s/it]
  6%|▋         | 3929/61904 [2:03:15<22:52:03,  1.42s/it]
  6%|▋         | 3930/61904 [2:03:17<23:11:51,  1.44s/it]
  6%|▋         | 3931/61904 [2:03:18<23:44:14,  1.47s/it]
  6%|▋         | 3932/61904 [2:03:20<23:02:58,  1.43s/it]
  6%|▋         | 3933/61904 [2:03:21<23:12:23,  1.44s/it]
  6%|▋         | 3934/61904 [2:03:22<22:28:11,  1.40s/it]
  6%|▋         | 3935/61904 [2:03:24<22:43:57,  1.41s/it]
  6%|▋         | 3936/61904 [2:03:25<22:28:19,  1.40s/it]
  6%|▋         | 3937/61904 [2:03:26<22:07:19,  1.37s/it]
  6%|▋         | 3938/61904 [2:03:28<21:53:10,  1.36s/it]
  6%|▋         | 3939/61904 [2:03:29<21:55:22,  1.36s/it]
  6%|▋         | 3940/61904 [2:03:31<22:58:28,  1.43s/it]
                                                         
{'loss': 3.0479, 'learning_rate': 1.9393880461558406e-07, 'epoch': 1.02}

  6%|▋         | 3940/61904 [2:03:31<22:58:28,  1.43s/it]
  6%|▋         | 3941/61904 [2:03:32<22:53:19,  1.42s/it]
  6%|▋         | 3942/61904 [2:03:34<22:54:48,  1.42s/it]
  6%|▋         | 3943/61904 [2:03:35<23:18:06,  1.45s/it]
  6%|▋         | 3944/61904 [2:03:36<22:31:05,  1.40s/it]
  6%|▋         | 3945/61904 [2:03:38<22:43:44,  1.41s/it]
  6%|▋         | 3946/61904 [2:03:39<22:23:20,  1.39s/it]
  6%|▋         | 3947/61904 [2:03:40<22:02:40,  1.37s/it]
  6%|▋         | 3948/61904 [2:03:42<22:08:22,  1.38s/it]
  6%|▋         | 3949/61904 [2:03:43<22:32:03,  1.40s/it]
  6%|▋         | 3950/61904 [2:03:45<22:23:07,  1.39s/it]
  6%|▋         | 3951/61904 [2:03:46<22:21:24,  1.39s/it]
  6%|▋         | 3952/61904 [2:03:48<22:52:13,  1.42s/it]
  6%|▋         | 3953/61904 [2:03:49<22:22:43,  1.39s/it]
  6%|▋         | 3954/61904 [2:03:50<22:49:08,  1.42s/it]
  6%|▋         | 3955/61904 [2:03:52<23:14:56,  1.44s/it]
  6%|▋         | 3956/61904 [2:03:53<22:53:25,  1.42s/it]
  6%|▋         | 3957/61904 [2:03:55<22:30:06,  1.40s/it]
  6%|▋         | 3958/61904 [2:03:56<22:24:57,  1.39s/it]
  6%|▋         | 3959/61904 [2:03:57<21:56:54,  1.36s/it]
  6%|▋         | 3960/61904 [2:03:59<22:28:38,  1.40s/it]
                                                         
{'loss': 3.0733, 'learning_rate': 1.9390639180604175e-07, 'epoch': 1.02}

  6%|▋         | 3960/61904 [2:03:59<22:28:38,  1.40s/it]
  6%|▋         | 3961/61904 [2:04:00<22:36:24,  1.40s/it]
  6%|▋         | 3962/61904 [2:04:02<22:47:41,  1.42s/it]
  6%|▋         | 3963/61904 [2:04:03<22:46:27,  1.42s/it]
  6%|▋         | 3964/61904 [2:04:05<23:52:30,  1.48s/it]
  6%|▋         | 3965/61904 [2:04:06<23:07:17,  1.44s/it]
  6%|▋         | 3966/61904 [2:04:07<22:36:55,  1.41s/it]
  6%|▋         | 3967/61904 [2:04:09<22:17:53,  1.39s/it]
  6%|▋         | 3968/61904 [2:04:10<22:38:11,  1.41s/it]
  6%|▋         | 3969/61904 [2:04:12<22:58:46,  1.43s/it]
  6%|▋         | 3970/61904 [2:04:13<23:42:38,  1.47s/it]
  6%|▋         | 3971/61904 [2:04:14<22:56:23,  1.43s/it]
  6%|▋         | 3972/61904 [2:04:16<23:26:12,  1.46s/it]
  6%|▋         | 3973/61904 [2:04:17<23:23:45,  1.45s/it]
  6%|▋         | 3974/61904 [2:04:19<23:04:30,  1.43s/it]
  6%|▋         | 3975/61904 [2:04:20<23:10:17,  1.44s/it]
  6%|▋         | 3976/61904 [2:04:22<22:52:36,  1.42s/it]
  6%|▋         | 3977/61904 [2:04:23<21:57:00,  1.36s/it]
  6%|▋         | 3978/61904 [2:04:24<22:09:20,  1.38s/it]
  6%|▋         | 3979/61904 [2:04:26<21:30:43,  1.34s/it]
  6%|▋         | 3980/61904 [2:04:27<21:42:28,  1.35s/it]
                                                         
{'loss': 3.0543, 'learning_rate': 1.938739789964994e-07, 'epoch': 1.03}

  6%|▋         | 3980/61904 [2:04:27<21:42:28,  1.35s/it]
  6%|▋         | 3981/61904 [2:04:28<21:29:11,  1.34s/it]
  6%|▋         | 3982/61904 [2:04:30<21:13:45,  1.32s/it]
  6%|▋         | 3983/61904 [2:04:31<21:06:47,  1.31s/it]
  6%|▋         | 3984/61904 [2:04:32<21:40:11,  1.35s/it]
  6%|▋         | 3985/61904 [2:04:34<22:27:45,  1.40s/it]
  6%|▋         | 3986/61904 [2:04:35<22:00:15,  1.37s/it]
  6%|▋         | 3987/61904 [2:04:36<22:18:08,  1.39s/it]
  6%|▋         | 3988/61904 [2:04:38<21:44:03,  1.35s/it]
  6%|▋         | 3989/61904 [2:04:39<22:14:30,  1.38s/it]
  6%|▋         | 3990/61904 [2:04:40<21:36:17,  1.34s/it]
  6%|▋         | 3991/61904 [2:04:42<22:10:06,  1.38s/it]
  6%|▋         | 3992/61904 [2:04:43<22:10:03,  1.38s/it]
  6%|▋         | 3993/61904 [2:04:45<21:51:15,  1.36s/it]
  6%|▋         | 3994/61904 [2:04:46<21:45:57,  1.35s/it]
  6%|▋         | 3995/61904 [2:04:47<22:08:16,  1.38s/it]
  6%|▋         | 3996/61904 [2:04:49<21:43:23,  1.35s/it]
  6%|▋         | 3997/61904 [2:04:50<21:30:02,  1.34s/it]
  6%|▋         | 3998/61904 [2:04:51<20:54:57,  1.30s/it]
  6%|▋         | 3999/61904 [2:04:53<21:06:21,  1.31s/it]
  6%|▋         | 4000/61904 [2:04:54<20:55:21,  1.30s/it]
                                                         
{'loss': 2.9607, 'learning_rate': 1.9384156618695707e-07, 'epoch': 1.03}

  6%|▋         | 4000/61904 [2:04:54<20:55:21,  1.30s/it]
  6%|▋         | 4001/61904 [2:04:55<21:17:26,  1.32s/it]
  6%|▋         | 4002/61904 [2:04:57<21:26:32,  1.33s/it]
  6%|▋         | 4003/61904 [2:04:58<21:34:45,  1.34s/it]
  6%|▋         | 4004/61904 [2:04:59<21:26:44,  1.33s/it]
  6%|▋         | 4005/61904 [2:05:01<21:21:24,  1.33s/it]
  6%|▋         | 4006/61904 [2:05:02<21:36:33,  1.34s/it]
  6%|▋         | 4007/61904 [2:05:03<21:32:07,  1.34s/it]
  6%|▋         | 4008/61904 [2:05:05<22:21:38,  1.39s/it]
  6%|▋         | 4009/61904 [2:05:06<22:52:23,  1.42s/it]
  6%|▋         | 4010/61904 [2:05:08<22:53:08,  1.42s/it]
  6%|▋         | 4011/61904 [2:05:09<21:45:13,  1.35s/it]
  6%|▋         | 4012/61904 [2:05:10<21:08:42,  1.31s/it]
  6%|▋         | 4013/61904 [2:05:11<21:00:42,  1.31s/it]
  6%|▋         | 4014/61904 [2:05:13<20:42:28,  1.29s/it]
  6%|▋         | 4015/61904 [2:05:14<20:40:17,  1.29s/it]
  6%|▋         | 4016/61904 [2:05:15<21:31:11,  1.34s/it]
  6%|▋         | 4017/61904 [2:05:17<21:48:42,  1.36s/it]
  6%|▋         | 4018/61904 [2:05:18<21:36:45,  1.34s/it]
  6%|▋         | 4019/61904 [2:05:19<21:45:36,  1.35s/it]
  6%|▋         | 4020/61904 [2:05:21<21:47:18,  1.36s/it]
                                                         
{'loss': 2.9848, 'learning_rate': 1.9380915337741476e-07, 'epoch': 1.04}

  6%|▋         | 4020/61904 [2:05:21<21:47:18,  1.36s/it]
  6%|▋         | 4021/61904 [2:05:22<21:59:02,  1.37s/it]
  6%|▋         | 4022/61904 [2:05:24<22:07:03,  1.38s/it]
  6%|▋         | 4023/61904 [2:05:25<22:43:30,  1.41s/it]
  7%|▋         | 4024/61904 [2:05:26<22:37:10,  1.41s/it]
  7%|▋         | 4025/61904 [2:05:28<22:10:17,  1.38s/it]
  7%|▋         | 4026/61904 [2:05:29<21:54:58,  1.36s/it]
  7%|▋         | 4027/61904 [2:05:30<21:37:39,  1.35s/it]
  7%|▋         | 4028/61904 [2:05:32<21:15:59,  1.32s/it]
  7%|▋         | 4029/61904 [2:05:33<20:56:53,  1.30s/it]
  7%|▋         | 4030/61904 [2:05:34<21:55:25,  1.36s/it]
  7%|▋         | 4031/61904 [2:05:36<22:15:11,  1.38s/it]
  7%|▋         | 4032/61904 [2:05:37<21:24:57,  1.33s/it]
  7%|▋         | 4033/61904 [2:05:38<21:40:47,  1.35s/it]
  7%|▋         | 4034/61904 [2:05:40<21:36:55,  1.34s/it]
  7%|▋         | 4035/61904 [2:05:41<21:18:27,  1.33s/it]
  7%|▋         | 4036/61904 [2:05:42<21:27:05,  1.33s/it]
  7%|▋         | 4037/61904 [2:05:44<21:27:35,  1.34s/it]
  7%|▋         | 4038/61904 [2:05:45<21:43:47,  1.35s/it]
  7%|▋         | 4039/61904 [2:05:47<22:10:17,  1.38s/it]
  7%|▋         | 4040/61904 [2:05:48<21:41:40,  1.35s/it]
                                                         
{'loss': 3.0765, 'learning_rate': 1.937767405678724e-07, 'epoch': 1.04}

  7%|▋         | 4040/61904 [2:05:48<21:41:40,  1.35s/it]
  7%|▋         | 4041/61904 [2:05:50<23:09:44,  1.44s/it]
  7%|▋         | 4042/61904 [2:05:51<22:40:56,  1.41s/it]
  7%|▋         | 4043/61904 [2:05:52<21:46:40,  1.35s/it]
  7%|▋         | 4044/61904 [2:05:53<21:27:39,  1.34s/it]
  7%|▋         | 4045/61904 [2:05:55<22:40:59,  1.41s/it]
  7%|▋         | 4046/61904 [2:05:56<22:55:18,  1.43s/it]
  7%|▋         | 4047/61904 [2:05:58<23:58:12,  1.49s/it]
  7%|▋         | 4048/61904 [2:06:00<23:55:53,  1.49s/it]
  7%|▋         | 4049/61904 [2:06:01<23:16:07,  1.45s/it]
  7%|▋         | 4050/61904 [2:06:02<22:09:33,  1.38s/it]
  7%|▋         | 4051/61904 [2:06:04<22:05:46,  1.37s/it]
  7%|▋         | 4052/61904 [2:06:05<22:27:30,  1.40s/it]
  7%|▋         | 4053/61904 [2:06:06<22:12:26,  1.38s/it]
  7%|▋         | 4054/61904 [2:06:08<22:20:25,  1.39s/it]
  7%|▋         | 4055/61904 [2:06:09<21:38:51,  1.35s/it]
  7%|▋         | 4056/61904 [2:06:10<21:17:06,  1.32s/it]
  7%|▋         | 4057/61904 [2:06:12<21:17:15,  1.32s/it]
  7%|▋         | 4058/61904 [2:06:13<21:30:52,  1.34s/it]
  7%|▋         | 4059/61904 [2:06:14<22:15:32,  1.39s/it]
  7%|▋         | 4060/61904 [2:06:16<22:41:30,  1.41s/it]
                                                         
{'loss': 2.9827, 'learning_rate': 1.9374432775833008e-07, 'epoch': 1.05}

  7%|▋         | 4060/61904 [2:06:16<22:41:30,  1.41s/it]
  7%|▋         | 4061/61904 [2:06:17<22:20:38,  1.39s/it]
  7%|▋         | 4062/61904 [2:06:19<22:01:34,  1.37s/it]
  7%|▋         | 4063/61904 [2:06:20<21:41:03,  1.35s/it]
  7%|▋         | 4064/61904 [2:06:21<22:11:22,  1.38s/it]
  7%|▋         | 4065/61904 [2:06:23<21:44:59,  1.35s/it]
  7%|▋         | 4066/61904 [2:06:24<21:27:05,  1.34s/it]
  7%|▋         | 4067/61904 [2:06:25<21:03:10,  1.31s/it]
  7%|▋         | 4068/61904 [2:06:27<22:09:03,  1.38s/it]
  7%|▋         | 4069/61904 [2:06:28<22:35:37,  1.41s/it]
  7%|▋         | 4070/61904 [2:06:29<21:54:23,  1.36s/it]
  7%|▋         | 4071/61904 [2:06:31<22:20:21,  1.39s/it]
  7%|▋         | 4072/61904 [2:06:32<22:11:46,  1.38s/it]
  7%|▋         | 4073/61904 [2:06:34<23:03:34,  1.44s/it]
  7%|▋         | 4074/61904 [2:06:35<22:48:32,  1.42s/it]
  7%|▋         | 4075/61904 [2:06:36<22:01:28,  1.37s/it]
  7%|▋         | 4076/61904 [2:06:38<21:22:01,  1.33s/it]
  7%|▋         | 4077/61904 [2:06:39<20:48:31,  1.30s/it]
  7%|▋         | 4078/61904 [2:06:40<21:00:06,  1.31s/it]
  7%|▋         | 4079/61904 [2:06:42<21:55:31,  1.37s/it]
  7%|▋         | 4080/61904 [2:06:43<21:51:36,  1.36s/it]
                                                         
{'loss': 3.0336, 'learning_rate': 1.9371191494878777e-07, 'epoch': 1.05}

  7%|▋         | 4080/61904 [2:06:43<21:51:36,  1.36s/it]
  7%|▋         | 4081/61904 [2:06:44<21:41:30,  1.35s/it]
  7%|▋         | 4082/61904 [2:06:46<21:31:30,  1.34s/it]
  7%|▋         | 4083/61904 [2:06:47<21:09:19,  1.32s/it]
  7%|▋         | 4084/61904 [2:06:48<21:15:43,  1.32s/it]
  7%|▋         | 4085/61904 [2:06:50<21:08:02,  1.32s/it]
  7%|▋         | 4086/61904 [2:06:51<22:17:13,  1.39s/it]
  7%|▋         | 4087/61904 [2:06:52<21:51:32,  1.36s/it]
  7%|▋         | 4088/61904 [2:06:54<21:30:08,  1.34s/it]
  7%|▋         | 4089/61904 [2:06:55<21:44:07,  1.35s/it]
  7%|▋         | 4090/61904 [2:06:57<22:15:49,  1.39s/it]
  7%|▋         | 4091/61904 [2:06:58<22:16:48,  1.39s/it]
  7%|▋         | 4092/61904 [2:06:59<22:30:20,  1.40s/it]
  7%|▋         | 4093/61904 [2:07:01<22:37:42,  1.41s/it]
  7%|▋         | 4094/61904 [2:07:02<22:52:55,  1.42s/it]
  7%|▋         | 4095/61904 [2:07:04<22:43:29,  1.42s/it]
  7%|▋         | 4096/61904 [2:07:05<22:13:14,  1.38s/it]
  7%|▋         | 4097/61904 [2:07:06<21:45:57,  1.36s/it]
  7%|▋         | 4098/61904 [2:07:08<21:42:27,  1.35s/it]
  7%|▋         | 4099/61904 [2:07:09<21:59:22,  1.37s/it]
  7%|▋         | 4100/61904 [2:07:10<21:55:34,  1.37s/it]
                                                         
{'loss': 3.0382, 'learning_rate': 1.936795021392454e-07, 'epoch': 1.06}

  7%|▋         | 4100/61904 [2:07:10<21:55:34,  1.37s/it]
  7%|▋         | 4101/61904 [2:07:12<22:06:10,  1.38s/it]
  7%|▋         | 4102/61904 [2:07:13<22:03:33,  1.37s/it]
  7%|▋         | 4103/61904 [2:07:15<21:59:59,  1.37s/it]
  7%|▋         | 4104/61904 [2:07:16<21:40:10,  1.35s/it]
  7%|▋         | 4105/61904 [2:07:17<22:00:13,  1.37s/it]
  7%|▋         | 4106/61904 [2:07:19<21:20:43,  1.33s/it]
  7%|▋         | 4107/61904 [2:07:20<20:58:03,  1.31s/it]
  7%|▋         | 4108/61904 [2:07:21<21:26:21,  1.34s/it]
  7%|▋         | 4109/61904 [2:07:23<21:22:39,  1.33s/it]
  7%|▋         | 4110/61904 [2:07:24<21:48:04,  1.36s/it]
  7%|▋         | 4111/61904 [2:07:25<22:07:34,  1.38s/it]
  7%|▋         | 4112/61904 [2:07:27<22:30:23,  1.40s/it]
  7%|▋         | 4113/61904 [2:07:28<21:13:54,  1.32s/it]
  7%|▋         | 4114/61904 [2:07:29<21:29:11,  1.34s/it]
  7%|▋         | 4115/61904 [2:07:31<21:40:06,  1.35s/it]
  7%|▋         | 4116/61904 [2:07:32<21:14:45,  1.32s/it]
  7%|▋         | 4117/61904 [2:07:33<21:00:34,  1.31s/it]
  7%|▋         | 4118/61904 [2:07:35<21:48:57,  1.36s/it]
  7%|▋         | 4119/61904 [2:07:36<21:31:49,  1.34s/it]
  7%|▋         | 4120/61904 [2:07:37<21:01:30,  1.31s/it]
                                                         
{'loss': 2.9706, 'learning_rate': 1.936470893297031e-07, 'epoch': 1.06}

  7%|▋         | 4120/61904 [2:07:37<21:01:30,  1.31s/it]
  7%|▋         | 4121/61904 [2:07:39<21:49:28,  1.36s/it]
  7%|▋         | 4122/61904 [2:07:40<22:14:23,  1.39s/it]
  7%|▋         | 4123/61904 [2:07:42<22:07:11,  1.38s/it]
  7%|▋         | 4124/61904 [2:07:43<22:27:40,  1.40s/it]
  7%|▋         | 4125/61904 [2:07:44<22:16:20,  1.39s/it]
  7%|▋         | 4126/61904 [2:07:46<22:01:35,  1.37s/it]
  7%|▋         | 4127/61904 [2:07:47<22:19:50,  1.39s/it]
  7%|▋         | 4128/61904 [2:07:49<22:29:44,  1.40s/it]
  7%|▋         | 4129/61904 [2:07:50<21:39:44,  1.35s/it]
  7%|▋         | 4130/61904 [2:07:51<20:56:42,  1.31s/it]
  7%|▋         | 4131/61904 [2:07:52<21:19:34,  1.33s/it]
  7%|▋         | 4132/61904 [2:07:54<21:45:46,  1.36s/it]
  7%|▋         | 4133/61904 [2:07:55<21:29:18,  1.34s/it]
  7%|▋         | 4134/61904 [2:07:56<21:44:27,  1.35s/it]
  7%|▋         | 4135/61904 [2:07:58<21:41:01,  1.35s/it]
  7%|▋         | 4136/61904 [2:07:59<21:33:48,  1.34s/it]
  7%|▋         | 4137/61904 [2:08:00<21:28:00,  1.34s/it]
  7%|▋         | 4138/61904 [2:08:02<21:58:07,  1.37s/it]
  7%|▋         | 4139/61904 [2:08:03<21:23:07,  1.33s/it]
  7%|▋         | 4140/61904 [2:08:05<21:53:59,  1.36s/it]
                                                         
{'loss': 2.9261, 'learning_rate': 1.9361467652016076e-07, 'epoch': 1.07}

  7%|▋         | 4140/61904 [2:08:05<21:53:59,  1.36s/it]
  7%|▋         | 4141/61904 [2:08:06<21:56:30,  1.37s/it]
  7%|▋         | 4142/61904 [2:08:07<21:49:41,  1.36s/it]
  7%|▋         | 4143/61904 [2:08:09<22:18:08,  1.39s/it]
  7%|▋         | 4144/61904 [2:08:10<22:01:49,  1.37s/it]
  7%|▋         | 4145/61904 [2:08:11<21:39:54,  1.35s/it]
  7%|▋         | 4146/61904 [2:08:13<22:08:55,  1.38s/it]
  7%|▋         | 4147/61904 [2:08:14<21:39:57,  1.35s/it]
  7%|▋         | 4148/61904 [2:08:16<22:00:04,  1.37s/it]
  7%|▋         | 4149/61904 [2:08:17<22:40:35,  1.41s/it]
  7%|▋         | 4150/61904 [2:08:18<22:08:09,  1.38s/it]
  7%|▋         | 4151/61904 [2:08:20<22:34:32,  1.41s/it]
  7%|▋         | 4152/61904 [2:08:21<22:14:39,  1.39s/it]
  7%|▋         | 4153/61904 [2:08:23<23:07:12,  1.44s/it]
  7%|▋         | 4154/61904 [2:08:24<23:00:06,  1.43s/it]
  7%|▋         | 4155/61904 [2:08:25<22:18:00,  1.39s/it]
  7%|▋         | 4156/61904 [2:08:27<22:07:57,  1.38s/it]
  7%|▋         | 4157/61904 [2:08:28<22:09:30,  1.38s/it]
  7%|▋         | 4158/61904 [2:08:30<22:44:00,  1.42s/it]
  7%|▋         | 4159/61904 [2:08:31<22:28:16,  1.40s/it]
  7%|▋         | 4160/61904 [2:08:32<21:46:07,  1.36s/it]
                                                         
{'loss': 3.0358, 'learning_rate': 1.9358226371061842e-07, 'epoch': 1.08}

  7%|▋         | 4160/61904 [2:08:32<21:46:07,  1.36s/it]
  7%|▋         | 4161/61904 [2:08:34<22:02:47,  1.37s/it]
  7%|▋         | 4162/61904 [2:08:35<21:42:05,  1.35s/it]
  7%|▋         | 4163/61904 [2:08:36<22:09:05,  1.38s/it]
  7%|▋         | 4164/61904 [2:08:38<22:34:24,  1.41s/it]
  7%|▋         | 4165/61904 [2:08:39<21:51:12,  1.36s/it]
  7%|▋         | 4166/61904 [2:08:41<22:04:09,  1.38s/it]
  7%|▋         | 4167/61904 [2:08:42<21:44:09,  1.36s/it]
  7%|▋         | 4168/61904 [2:08:43<21:34:25,  1.35s/it]
  7%|▋         | 4169/61904 [2:08:45<21:28:40,  1.34s/it]
  7%|▋         | 4170/61904 [2:08:46<21:42:51,  1.35s/it]
  7%|▋         | 4171/61904 [2:08:47<22:23:57,  1.40s/it]
  7%|▋         | 4172/61904 [2:08:49<22:28:35,  1.40s/it]
  7%|▋         | 4173/61904 [2:08:50<22:28:48,  1.40s/it]
  7%|▋         | 4174/61904 [2:08:52<22:28:48,  1.40s/it]
  7%|▋         | 4175/61904 [2:08:53<22:33:18,  1.41s/it]
  7%|▋         | 4176/61904 [2:08:54<21:59:24,  1.37s/it]
  7%|▋         | 4177/61904 [2:08:56<21:43:55,  1.36s/it]
  7%|▋         | 4178/61904 [2:08:57<21:07:11,  1.32s/it]
  7%|▋         | 4179/61904 [2:08:58<20:54:37,  1.30s/it]
  7%|▋         | 4180/61904 [2:08:59<20:23:55,  1.27s/it]
                                                         
{'loss': 3.0442, 'learning_rate': 1.935498509010761e-07, 'epoch': 1.08}

  7%|▋         | 4180/61904 [2:08:59<20:23:55,  1.27s/it]
  7%|▋         | 4181/61904 [2:09:01<20:27:07,  1.28s/it]
  7%|▋         | 4182/61904 [2:09:02<20:34:21,  1.28s/it]
  7%|▋         | 4183/61904 [2:09:03<21:26:16,  1.34s/it]
  7%|▋         | 4184/61904 [2:09:05<21:46:35,  1.36s/it]
  7%|▋         | 4185/61904 [2:09:06<22:21:38,  1.39s/it]
  7%|▋         | 4186/61904 [2:09:08<22:54:57,  1.43s/it]
  7%|▋         | 4187/61904 [2:09:09<22:47:34,  1.42s/it]
  7%|▋         | 4188/61904 [2:09:10<22:00:11,  1.37s/it]
  7%|▋         | 4189/61904 [2:09:12<21:23:26,  1.33s/it]
  7%|▋         | 4190/61904 [2:09:13<21:10:41,  1.32s/it]
  7%|▋         | 4191/61904 [2:09:14<21:17:50,  1.33s/it]
  7%|▋         | 4192/61904 [2:09:16<21:35:01,  1.35s/it]
  7%|▋         | 4193/61904 [2:09:17<21:39:38,  1.35s/it]
  7%|▋         | 4194/61904 [2:09:18<21:32:45,  1.34s/it]
  7%|▋         | 4195/61904 [2:09:20<21:05:35,  1.32s/it]
  7%|▋         | 4196/61904 [2:09:21<21:26:44,  1.34s/it]
  7%|▋         | 4197/61904 [2:09:23<22:14:16,  1.39s/it]
  7%|▋         | 4198/61904 [2:09:24<22:27:25,  1.40s/it]
  7%|▋         | 4199/61904 [2:09:25<22:08:12,  1.38s/it]
  7%|▋         | 4200/61904 [2:09:27<22:17:34,  1.39s/it]
                                                         
{'loss': 2.9493, 'learning_rate': 1.9351743809153377e-07, 'epoch': 1.09}

  7%|▋         | 4200/61904 [2:09:27<22:17:34,  1.39s/it]
  7%|▋         | 4201/61904 [2:09:28<22:10:11,  1.38s/it]
  7%|▋         | 4202/61904 [2:09:29<21:51:06,  1.36s/it]
  7%|▋         | 4203/61904 [2:09:31<21:32:50,  1.34s/it]
  7%|▋         | 4204/61904 [2:09:32<21:15:41,  1.33s/it]
  7%|▋         | 4205/61904 [2:09:33<21:15:54,  1.33s/it]
  7%|▋         | 4206/61904 [2:09:35<21:25:38,  1.34s/it]
  7%|▋         | 4207/61904 [2:09:36<21:45:13,  1.36s/it]
  7%|▋         | 4208/61904 [2:09:37<21:35:05,  1.35s/it]
  7%|▋         | 4209/61904 [2:09:39<23:00:06,  1.44s/it]
  7%|▋         | 4210/61904 [2:09:40<22:50:10,  1.42s/it]
  7%|▋         | 4211/61904 [2:09:42<22:36:45,  1.41s/it]
  7%|▋         | 4212/61904 [2:09:43<23:18:40,  1.45s/it]
  7%|▋         | 4213/61904 [2:09:45<22:43:37,  1.42s/it]
  7%|▋         | 4214/61904 [2:09:46<22:43:26,  1.42s/it]
  7%|▋         | 4215/61904 [2:09:48<22:50:22,  1.43s/it]
  7%|▋         | 4216/61904 [2:09:49<22:04:26,  1.38s/it]
  7%|▋         | 4217/61904 [2:09:50<21:39:35,  1.35s/it]
  7%|▋         | 4218/61904 [2:09:52<21:51:24,  1.36s/it]
  7%|▋         | 4219/61904 [2:09:53<22:04:32,  1.38s/it]
  7%|▋         | 4220/61904 [2:09:54<22:17:52,  1.39s/it]
                                                         
{'loss': 2.9963, 'learning_rate': 1.9348502528199143e-07, 'epoch': 1.09}

  7%|▋         | 4220/61904 [2:09:54<22:17:52,  1.39s/it]
  7%|▋         | 4221/61904 [2:09:56<23:32:17,  1.47s/it]
  7%|▋         | 4222/61904 [2:09:57<23:04:38,  1.44s/it]
  7%|▋         | 4223/61904 [2:09:59<22:46:57,  1.42s/it]
  7%|▋         | 4224/61904 [2:10:00<22:45:06,  1.42s/it]
  7%|▋         | 4225/61904 [2:10:02<23:06:48,  1.44s/it]
  7%|▋         | 4226/61904 [2:10:03<22:33:04,  1.41s/it]
  7%|▋         | 4227/61904 [2:10:05<23:41:34,  1.48s/it]
  7%|▋         | 4228/61904 [2:10:06<24:04:48,  1.50s/it]
  7%|▋         | 4229/61904 [2:10:08<23:51:13,  1.49s/it]
  7%|▋         | 4230/61904 [2:10:09<23:30:12,  1.47s/it]
  7%|▋         | 4231/61904 [2:10:10<22:32:24,  1.41s/it]
  7%|▋         | 4232/61904 [2:10:12<21:22:40,  1.33s/it]
  7%|▋         | 4233/61904 [2:10:13<21:44:56,  1.36s/it]
  7%|▋         | 4234/61904 [2:10:14<21:45:09,  1.36s/it]
  7%|▋         | 4235/61904 [2:10:16<21:48:25,  1.36s/it]
  7%|▋         | 4236/61904 [2:10:17<22:07:42,  1.38s/it]
  7%|▋         | 4237/61904 [2:10:18<22:00:59,  1.37s/it]
  7%|▋         | 4238/61904 [2:10:20<21:59:38,  1.37s/it]
  7%|▋         | 4239/61904 [2:10:21<21:29:53,  1.34s/it]
  7%|▋         | 4240/61904 [2:10:23<21:54:32,  1.37s/it]
                                                         
{'loss': 3.0102, 'learning_rate': 1.9345261247244912e-07, 'epoch': 1.1}

  7%|▋         | 4240/61904 [2:10:23<21:54:32,  1.37s/it]
  7%|▋         | 4241/61904 [2:10:24<21:46:10,  1.36s/it]
  7%|▋         | 4242/61904 [2:10:25<21:56:07,  1.37s/it]
  7%|▋         | 4243/61904 [2:10:27<21:28:02,  1.34s/it]
  7%|▋         | 4244/61904 [2:10:28<21:02:51,  1.31s/it]
  7%|▋         | 4245/61904 [2:10:29<21:06:14,  1.32s/it]
  7%|▋         | 4246/61904 [2:10:30<21:14:03,  1.33s/it]
  7%|▋         | 4247/61904 [2:10:32<21:48:24,  1.36s/it]
  7%|▋         | 4248/61904 [2:10:33<21:36:39,  1.35s/it]
  7%|▋         | 4249/61904 [2:10:35<22:40:34,  1.42s/it]
  7%|▋         | 4250/61904 [2:10:36<23:21:29,  1.46s/it]
  7%|▋         | 4251/61904 [2:10:38<22:36:02,  1.41s/it]
  7%|▋         | 4252/61904 [2:10:39<22:35:02,  1.41s/it]
  7%|▋         | 4253/61904 [2:10:40<21:52:54,  1.37s/it]
  7%|▋         | 4254/61904 [2:10:42<21:21:40,  1.33s/it]
  7%|▋         | 4255/61904 [2:10:43<21:28:02,  1.34s/it]
  7%|▋         | 4256/61904 [2:10:44<21:33:44,  1.35s/it]
  7%|▋         | 4257/61904 [2:10:46<20:58:43,  1.31s/it]
  7%|▋         | 4258/61904 [2:10:47<20:54:26,  1.31s/it]
  7%|▋         | 4259/61904 [2:10:48<20:51:39,  1.30s/it]
  7%|▋         | 4260/61904 [2:10:50<21:14:50,  1.33s/it]
                                                         
{'loss': 2.9861, 'learning_rate': 1.9342019966290675e-07, 'epoch': 1.1}

  7%|▋         | 4260/61904 [2:10:50<21:14:50,  1.33s/it]
  7%|▋         | 4261/61904 [2:10:51<21:24:25,  1.34s/it]
  7%|▋         | 4262/61904 [2:10:52<21:45:08,  1.36s/it]
  7%|▋         | 4263/61904 [2:10:54<21:39:24,  1.35s/it]
  7%|▋         | 4264/61904 [2:10:55<21:33:26,  1.35s/it]
  7%|▋         | 4265/61904 [2:10:56<21:51:20,  1.37s/it]
  7%|▋         | 4266/61904 [2:10:58<21:31:19,  1.34s/it]
  7%|▋         | 4267/61904 [2:10:59<21:16:09,  1.33s/it]
  7%|▋         | 4268/61904 [2:11:00<21:13:16,  1.33s/it]
  7%|▋         | 4269/61904 [2:11:02<21:15:14,  1.33s/it]
  7%|▋         | 4270/61904 [2:11:03<20:59:51,  1.31s/it]
  7%|▋         | 4271/61904 [2:11:04<20:53:33,  1.31s/it]
  7%|▋         | 4272/61904 [2:11:06<22:25:31,  1.40s/it]
  7%|▋         | 4273/61904 [2:11:07<21:55:58,  1.37s/it]
  7%|▋         | 4274/61904 [2:11:09<22:29:24,  1.40s/it]
  7%|▋         | 4275/61904 [2:11:10<22:13:02,  1.39s/it]
  7%|▋         | 4276/61904 [2:11:11<22:36:34,  1.41s/it]
  7%|▋         | 4277/61904 [2:11:13<21:58:58,  1.37s/it]
  7%|▋         | 4278/61904 [2:11:14<23:16:53,  1.45s/it]
  7%|▋         | 4279/61904 [2:11:16<22:30:53,  1.41s/it]
  7%|▋         | 4280/61904 [2:11:17<22:32:06,  1.41s/it]
                                                         
{'loss': 3.0209, 'learning_rate': 1.9338778685336444e-07, 'epoch': 1.11}

  7%|▋         | 4280/61904 [2:11:17<22:32:06,  1.41s/it]
  7%|▋         | 4281/61904 [2:11:18<22:07:16,  1.38s/it]
  7%|▋         | 4282/61904 [2:11:20<21:19:24,  1.33s/it]
  7%|▋         | 4283/61904 [2:11:21<22:04:09,  1.38s/it]
  7%|▋         | 4284/61904 [2:11:22<22:16:57,  1.39s/it]
  7%|▋         | 4285/61904 [2:11:24<22:25:41,  1.40s/it]
  7%|▋         | 4286/61904 [2:11:25<22:54:56,  1.43s/it]
  7%|▋         | 4287/61904 [2:11:27<22:48:45,  1.43s/it]
  7%|▋         | 4288/61904 [2:11:28<22:13:29,  1.39s/it]
  7%|▋         | 4289/61904 [2:11:30<22:35:36,  1.41s/it]
  7%|▋         | 4290/61904 [2:11:31<22:22:52,  1.40s/it]
  7%|▋         | 4291/61904 [2:11:32<22:34:00,  1.41s/it]
  7%|▋         | 4292/61904 [2:11:34<22:02:46,  1.38s/it]
  7%|▋         | 4293/61904 [2:11:35<21:57:59,  1.37s/it]
  7%|▋         | 4294/61904 [2:11:36<22:07:55,  1.38s/it]
  7%|▋         | 4295/61904 [2:11:38<21:44:04,  1.36s/it]
  7%|▋         | 4296/61904 [2:11:39<22:02:47,  1.38s/it]
  7%|▋         | 4297/61904 [2:11:40<21:42:20,  1.36s/it]
  7%|▋         | 4298/61904 [2:11:42<21:13:16,  1.33s/it]
  7%|▋         | 4299/61904 [2:11:43<21:34:06,  1.35s/it]
  7%|▋         | 4300/61904 [2:11:45<21:42:07,  1.36s/it]
                                                         
{'loss': 2.9864, 'learning_rate': 1.933553740438221e-07, 'epoch': 1.11}

  7%|▋         | 4300/61904 [2:11:45<21:42:07,  1.36s/it]
  7%|▋         | 4301/61904 [2:11:46<23:03:25,  1.44s/it]
  7%|▋         | 4302/61904 [2:11:47<22:13:14,  1.39s/it]
  7%|▋         | 4303/61904 [2:11:49<21:33:06,  1.35s/it]
  7%|▋         | 4304/61904 [2:11:50<21:24:29,  1.34s/it]
  7%|▋         | 4305/61904 [2:11:51<21:11:49,  1.32s/it]
  7%|▋         | 4306/61904 [2:11:53<21:34:39,  1.35s/it]
  7%|▋         | 4307/61904 [2:11:54<21:45:06,  1.36s/it]
  7%|▋         | 4308/61904 [2:11:55<21:26:38,  1.34s/it]
  7%|▋         | 4309/61904 [2:11:57<21:55:39,  1.37s/it]
  7%|▋         | 4310/61904 [2:11:58<21:24:26,  1.34s/it]
  7%|▋         | 4311/61904 [2:11:59<21:25:22,  1.34s/it]
  7%|▋         | 4312/61904 [2:12:01<21:14:41,  1.33s/it]
  7%|▋         | 4313/61904 [2:12:02<22:28:00,  1.40s/it]
  7%|▋         | 4314/61904 [2:12:04<21:52:49,  1.37s/it]
  7%|▋         | 4315/61904 [2:12:05<22:09:22,  1.39s/it]
  7%|▋         | 4316/61904 [2:12:06<21:24:52,  1.34s/it]
  7%|▋         | 4317/61904 [2:12:08<21:05:21,  1.32s/it]
  7%|▋         | 4318/61904 [2:12:09<20:49:37,  1.30s/it]
  7%|▋         | 4319/61904 [2:12:10<20:54:54,  1.31s/it]
  7%|▋         | 4320/61904 [2:12:12<21:35:32,  1.35s/it]
                                                         
{'loss': 2.9766, 'learning_rate': 1.9332296123427977e-07, 'epoch': 1.12}

  7%|▋         | 4320/61904 [2:12:12<21:35:32,  1.35s/it]
  7%|▋         | 4321/61904 [2:12:13<21:37:06,  1.35s/it]
  7%|▋         | 4322/61904 [2:12:14<22:00:41,  1.38s/it]
  7%|▋         | 4323/61904 [2:12:16<22:19:53,  1.40s/it]
  7%|▋         | 4324/61904 [2:12:17<22:19:41,  1.40s/it]
  7%|▋         | 4325/61904 [2:12:18<21:42:02,  1.36s/it]
  7%|▋         | 4326/61904 [2:12:20<22:03:50,  1.38s/it]
  7%|▋         | 4327/61904 [2:12:21<21:52:51,  1.37s/it]
  7%|▋         | 4328/61904 [2:12:23<22:38:16,  1.42s/it]
  7%|▋         | 4329/61904 [2:12:24<22:28:58,  1.41s/it]
  7%|▋         | 4330/61904 [2:12:26<22:37:18,  1.41s/it]
  7%|▋         | 4331/61904 [2:12:27<22:22:28,  1.40s/it]
  7%|▋         | 4332/61904 [2:12:28<22:03:34,  1.38s/it]
  7%|▋         | 4333/61904 [2:12:30<22:06:58,  1.38s/it]
  7%|▋         | 4334/61904 [2:12:31<22:12:35,  1.39s/it]
  7%|▋         | 4335/61904 [2:12:32<21:58:49,  1.37s/it]
  7%|▋         | 4336/61904 [2:12:34<22:14:24,  1.39s/it]
  7%|▋         | 4337/61904 [2:12:35<22:01:58,  1.38s/it]
  7%|▋         | 4338/61904 [2:12:36<21:26:43,  1.34s/it]
  7%|▋         | 4339/61904 [2:12:38<21:06:48,  1.32s/it]
  7%|▋         | 4340/61904 [2:12:39<21:56:27,  1.37s/it]
                                                         
{'loss': 3.0403, 'learning_rate': 1.9329054842473745e-07, 'epoch': 1.12}

  7%|▋         | 4340/61904 [2:12:39<21:56:27,  1.37s/it]
  7%|▋         | 4341/61904 [2:12:41<22:23:00,  1.40s/it]
  7%|▋         | 4342/61904 [2:12:42<22:20:15,  1.40s/it]
  7%|▋         | 4343/61904 [2:12:43<22:03:43,  1.38s/it]
  7%|▋         | 4344/61904 [2:12:45<21:46:07,  1.36s/it]
  7%|▋         | 4345/61904 [2:12:46<21:56:03,  1.37s/it]
  7%|▋         | 4346/61904 [2:12:47<21:42:57,  1.36s/it]
  7%|▋         | 4347/61904 [2:12:49<21:51:25,  1.37s/it]
  7%|▋         | 4348/61904 [2:12:50<22:04:13,  1.38s/it]
  7%|▋         | 4349/61904 [2:12:52<21:54:32,  1.37s/it]
  7%|▋         | 4350/61904 [2:12:53<23:06:46,  1.45s/it]
  7%|▋         | 4351/61904 [2:12:55<22:33:51,  1.41s/it]
  7%|▋         | 4352/61904 [2:12:56<22:23:25,  1.40s/it]
  7%|▋         | 4353/61904 [2:12:57<21:26:10,  1.34s/it]
  7%|▋         | 4354/61904 [2:12:58<21:17:51,  1.33s/it]
  7%|▋         | 4355/61904 [2:13:00<20:41:47,  1.29s/it]
  7%|▋         | 4356/61904 [2:13:01<21:47:42,  1.36s/it]
  7%|▋         | 4357/61904 [2:13:03<22:11:15,  1.39s/it]
  7%|▋         | 4358/61904 [2:13:04<21:34:22,  1.35s/it]
  7%|▋         | 4359/61904 [2:13:05<21:24:18,  1.34s/it]
  7%|▋         | 4360/61904 [2:13:06<21:19:11,  1.33s/it]
                                                         
{'loss': 2.9861, 'learning_rate': 1.9325813561519512e-07, 'epoch': 1.13}

  7%|▋         | 4360/61904 [2:13:06<21:19:11,  1.33s/it]
  7%|▋         | 4361/61904 [2:13:08<21:17:27,  1.33s/it]
  7%|▋         | 4362/61904 [2:13:09<21:08:59,  1.32s/it]
  7%|▋         | 4363/61904 [2:13:10<21:28:44,  1.34s/it]
  7%|▋         | 4364/61904 [2:13:12<22:16:29,  1.39s/it]
  7%|▋         | 4365/61904 [2:13:13<22:10:12,  1.39s/it]
  7%|▋         | 4366/61904 [2:13:15<22:17:03,  1.39s/it]
  7%|▋         | 4367/61904 [2:13:16<22:30:48,  1.41s/it]
  7%|▋         | 4368/61904 [2:13:18<22:13:36,  1.39s/it]
  7%|▋         | 4369/61904 [2:13:19<21:44:00,  1.36s/it]
  7%|▋         | 4370/61904 [2:13:20<21:27:29,  1.34s/it]
  7%|▋         | 4371/61904 [2:13:21<21:13:04,  1.33s/it]
  7%|▋         | 4372/61904 [2:13:23<21:40:55,  1.36s/it]
  7%|▋         | 4373/61904 [2:13:24<21:08:55,  1.32s/it]
  7%|▋         | 4374/61904 [2:13:25<20:36:51,  1.29s/it]
  7%|▋         | 4375/61904 [2:13:27<20:53:08,  1.31s/it]
  7%|▋         | 4376/61904 [2:13:28<20:35:46,  1.29s/it]
  7%|▋         | 4377/61904 [2:13:29<20:59:22,  1.31s/it]
  7%|▋         | 4378/61904 [2:13:31<21:01:22,  1.32s/it]
  7%|▋         | 4379/61904 [2:13:32<21:55:11,  1.37s/it]
  7%|▋         | 4380/61904 [2:13:33<21:25:00,  1.34s/it]
                                                         
{'loss': 3.0244, 'learning_rate': 1.9322572280565278e-07, 'epoch': 1.13}

  7%|▋         | 4380/61904 [2:13:33<21:25:00,  1.34s/it]
  7%|▋         | 4381/61904 [2:13:35<21:24:08,  1.34s/it]
  7%|▋         | 4382/61904 [2:13:36<21:45:59,  1.36s/it]
  7%|▋         | 4383/61904 [2:13:38<21:46:27,  1.36s/it]
  7%|▋         | 4384/61904 [2:13:39<21:34:10,  1.35s/it]
  7%|▋         | 4385/61904 [2:13:40<21:31:16,  1.35s/it]
  7%|▋         | 4386/61904 [2:13:41<21:16:20,  1.33s/it]
  7%|▋         | 4387/61904 [2:13:43<21:21:03,  1.34s/it]
  7%|▋         | 4388/61904 [2:13:44<21:36:43,  1.35s/it]
  7%|▋         | 4389/61904 [2:13:45<21:08:33,  1.32s/it]
  7%|▋         | 4390/61904 [2:13:47<21:53:35,  1.37s/it]
  7%|▋         | 4391/61904 [2:13:48<21:40:14,  1.36s/it]
  7%|▋         | 4392/61904 [2:13:50<21:25:54,  1.34s/it]
  7%|▋         | 4393/61904 [2:13:51<21:05:17,  1.32s/it]
  7%|▋         | 4394/61904 [2:13:52<21:38:24,  1.35s/it]
  7%|▋         | 4395/61904 [2:13:54<21:55:10,  1.37s/it]
  7%|▋         | 4396/61904 [2:13:55<21:43:11,  1.36s/it]
  7%|▋         | 4397/61904 [2:13:56<22:02:49,  1.38s/it]
  7%|▋         | 4398/61904 [2:13:58<22:08:40,  1.39s/it]
  7%|▋         | 4399/61904 [2:13:59<23:03:52,  1.44s/it]
  7%|▋         | 4400/61904 [2:14:01<22:22:07,  1.40s/it]
                                                         
{'loss': 2.9827, 'learning_rate': 1.9319330999611047e-07, 'epoch': 1.14}

  7%|▋         | 4400/61904 [2:14:01<22:22:07,  1.40s/it]
  7%|▋         | 4401/61904 [2:14:02<21:43:03,  1.36s/it]
  7%|▋         | 4402/61904 [2:14:03<21:05:27,  1.32s/it]
  7%|▋         | 4403/61904 [2:14:05<21:09:37,  1.32s/it]
  7%|▋         | 4404/61904 [2:14:06<21:05:00,  1.32s/it]
  7%|▋         | 4405/61904 [2:14:07<21:06:13,  1.32s/it]
  7%|▋         | 4406/61904 [2:14:09<21:19:15,  1.33s/it]
  7%|▋         | 4407/61904 [2:14:10<21:28:22,  1.34s/it]
  7%|▋         | 4408/61904 [2:14:11<21:42:57,  1.36s/it]
  7%|▋         | 4409/61904 [2:14:13<21:34:22,  1.35s/it]
  7%|▋         | 4410/61904 [2:14:14<21:56:08,  1.37s/it]
  7%|▋         | 4411/61904 [2:14:15<22:04:11,  1.38s/it]
  7%|▋         | 4412/61904 [2:14:17<21:46:11,  1.36s/it]
  7%|▋         | 4413/61904 [2:14:18<21:55:05,  1.37s/it]
  7%|▋         | 4414/61904 [2:14:20<22:47:12,  1.43s/it]
  7%|▋         | 4415/61904 [2:14:21<22:56:53,  1.44s/it]
  7%|▋         | 4416/61904 [2:14:23<22:33:57,  1.41s/it]
  7%|▋         | 4417/61904 [2:14:24<22:20:15,  1.40s/it]
  7%|▋         | 4418/61904 [2:14:25<21:48:57,  1.37s/it]
  7%|▋         | 4419/61904 [2:14:27<22:07:48,  1.39s/it]
  7%|▋         | 4420/61904 [2:14:28<21:45:12,  1.36s/it]
                                                         
{'loss': 3.0343, 'learning_rate': 1.931608971865681e-07, 'epoch': 1.14}

  7%|▋         | 4420/61904 [2:14:28<21:45:12,  1.36s/it]
  7%|▋         | 4421/61904 [2:14:29<21:36:25,  1.35s/it]
  7%|▋         | 4422/61904 [2:14:31<21:58:25,  1.38s/it]
  7%|▋         | 4423/61904 [2:14:32<22:08:30,  1.39s/it]
  7%|▋         | 4424/61904 [2:14:33<21:40:59,  1.36s/it]
  7%|▋         | 4425/61904 [2:14:35<22:40:35,  1.42s/it]
  7%|▋         | 4426/61904 [2:14:36<22:17:47,  1.40s/it]
  7%|▋         | 4427/61904 [2:14:38<22:35:02,  1.41s/it]
  7%|▋         | 4428/61904 [2:14:39<22:25:16,  1.40s/it]
  7%|▋         | 4429/61904 [2:14:40<21:52:11,  1.37s/it]
  7%|▋         | 4430/61904 [2:14:42<22:05:42,  1.38s/it]
  7%|▋         | 4431/61904 [2:14:43<22:25:42,  1.40s/it]
  7%|▋         | 4432/61904 [2:14:45<21:43:43,  1.36s/it]
  7%|▋         | 4433/61904 [2:14:46<21:57:12,  1.38s/it]
  7%|▋         | 4434/61904 [2:14:47<22:13:45,  1.39s/it]
  7%|▋         | 4435/61904 [2:14:49<22:13:31,  1.39s/it]
  7%|▋         | 4436/61904 [2:14:50<22:01:58,  1.38s/it]
  7%|▋         | 4437/61904 [2:14:51<21:30:21,  1.35s/it]
  7%|▋         | 4438/61904 [2:14:53<21:36:22,  1.35s/it]
  7%|▋         | 4439/61904 [2:14:54<22:02:43,  1.38s/it]
  7%|▋         | 4440/61904 [2:14:56<21:38:46,  1.36s/it]
                                                         
{'loss': 2.9305, 'learning_rate': 1.931284843770258e-07, 'epoch': 1.15}

  7%|▋         | 4440/61904 [2:14:56<21:38:46,  1.36s/it]
  7%|▋         | 4441/61904 [2:14:57<21:56:39,  1.37s/it]
  7%|▋         | 4442/61904 [2:14:58<22:12:12,  1.39s/it]
  7%|▋         | 4443/61904 [2:15:00<21:40:47,  1.36s/it]
  7%|▋         | 4444/61904 [2:15:01<20:56:45,  1.31s/it]
  7%|▋         | 4445/61904 [2:15:02<20:45:58,  1.30s/it]
  7%|▋         | 4446/61904 [2:15:03<20:22:37,  1.28s/it]
  7%|▋         | 4447/61904 [2:15:05<21:32:53,  1.35s/it]
  7%|▋         | 4448/61904 [2:15:06<22:19:03,  1.40s/it]
  7%|▋         | 4449/61904 [2:15:08<22:01:30,  1.38s/it]
  7%|▋         | 4450/61904 [2:15:09<22:13:29,  1.39s/it]
  7%|▋         | 4451/61904 [2:15:11<23:22:41,  1.46s/it]
  7%|▋         | 4452/61904 [2:15:12<22:25:04,  1.40s/it]
  7%|▋         | 4453/61904 [2:15:13<22:13:44,  1.39s/it]
  7%|▋         | 4454/61904 [2:15:15<21:52:45,  1.37s/it]
  7%|▋         | 4455/61904 [2:15:16<22:22:30,  1.40s/it]
  7%|▋         | 4456/61904 [2:15:17<21:37:57,  1.36s/it]
  7%|▋         | 4457/61904 [2:15:19<22:02:06,  1.38s/it]
  7%|▋         | 4458/61904 [2:15:20<22:04:25,  1.38s/it]
  7%|▋         | 4459/61904 [2:15:22<22:23:54,  1.40s/it]
  7%|▋         | 4460/61904 [2:15:23<21:58:13,  1.38s/it]
                                                         
{'loss': 2.9797, 'learning_rate': 1.9309607156748348e-07, 'epoch': 1.15}

  7%|▋         | 4460/61904 [2:15:23<21:58:13,  1.38s/it]
  7%|▋         | 4461/61904 [2:15:24<21:28:13,  1.35s/it]
  7%|▋         | 4462/61904 [2:15:26<21:01:15,  1.32s/it]
  7%|▋         | 4463/61904 [2:15:27<21:09:26,  1.33s/it]
  7%|▋         | 4464/61904 [2:15:28<21:16:45,  1.33s/it]
  7%|▋         | 4465/61904 [2:15:30<21:42:16,  1.36s/it]
  7%|▋         | 4466/61904 [2:15:31<21:30:41,  1.35s/it]
  7%|▋         | 4467/61904 [2:15:33<22:13:21,  1.39s/it]
  7%|▋         | 4468/61904 [2:15:34<22:05:18,  1.38s/it]
  7%|▋         | 4469/61904 [2:15:35<21:48:59,  1.37s/it]
  7%|▋         | 4470/61904 [2:15:37<21:56:48,  1.38s/it]
  7%|▋         | 4471/61904 [2:15:38<22:04:14,  1.38s/it]
  7%|▋         | 4472/61904 [2:15:40<22:33:57,  1.41s/it]
  7%|▋         | 4473/61904 [2:15:41<22:56:28,  1.44s/it]
  7%|▋         | 4474/61904 [2:15:42<22:55:59,  1.44s/it]
  7%|▋         | 4475/61904 [2:15:44<22:48:25,  1.43s/it]
  7%|▋         | 4476/61904 [2:15:45<22:19:31,  1.40s/it]
  7%|▋         | 4477/61904 [2:15:47<22:01:17,  1.38s/it]
  7%|▋         | 4478/61904 [2:15:48<21:57:46,  1.38s/it]
  7%|▋         | 4479/61904 [2:15:49<21:24:26,  1.34s/it]
  7%|▋         | 4480/61904 [2:15:51<21:41:19,  1.36s/it]
                                                         
{'loss': 2.9846, 'learning_rate': 1.930636587579411e-07, 'epoch': 1.16}

  7%|▋         | 4480/61904 [2:15:51<21:41:19,  1.36s/it]
  7%|▋         | 4481/61904 [2:15:52<22:26:07,  1.41s/it]
  7%|▋         | 4482/61904 [2:15:54<23:08:01,  1.45s/it]
  7%|▋         | 4483/61904 [2:15:55<22:39:12,  1.42s/it]
  7%|▋         | 4484/61904 [2:15:56<22:25:16,  1.41s/it]
  7%|▋         | 4485/61904 [2:15:58<22:15:46,  1.40s/it]
  7%|▋         | 4486/61904 [2:15:59<22:23:21,  1.40s/it]
  7%|▋         | 4487/61904 [2:16:00<22:11:37,  1.39s/it]
  7%|▋         | 4488/61904 [2:16:02<22:11:46,  1.39s/it]
  7%|▋         | 4489/61904 [2:16:03<21:47:55,  1.37s/it]
  7%|▋         | 4490/61904 [2:16:04<20:59:23,  1.32s/it]
  7%|▋         | 4491/61904 [2:16:06<21:03:04,  1.32s/it]
  7%|▋         | 4492/61904 [2:16:07<21:09:09,  1.33s/it]
  7%|▋         | 4493/61904 [2:16:08<21:17:57,  1.34s/it]
  7%|▋         | 4494/61904 [2:16:10<20:58:37,  1.32s/it]
  7%|▋         | 4495/61904 [2:16:11<20:42:59,  1.30s/it]
  7%|▋         | 4496/61904 [2:16:12<21:02:42,  1.32s/it]
  7%|▋         | 4497/61904 [2:16:14<21:13:38,  1.33s/it]
  7%|▋         | 4498/61904 [2:16:15<22:18:21,  1.40s/it]
  7%|▋         | 4499/61904 [2:16:17<21:53:25,  1.37s/it]
  7%|▋         | 4500/61904 [2:16:18<22:28:44,  1.41s/it]
                                                         
{'loss': 3.0176, 'learning_rate': 1.930312459483988e-07, 'epoch': 1.16}

  7%|▋         | 4500/61904 [2:16:18<22:28:44,  1.41s/it]
  7%|▋         | 4501/61904 [2:16:19<22:34:53,  1.42s/it]
  7%|▋         | 4502/61904 [2:16:21<22:20:21,  1.40s/it]
  7%|▋         | 4503/61904 [2:16:22<22:37:50,  1.42s/it]
  7%|▋         | 4504/61904 [2:16:24<22:25:50,  1.41s/it]
  7%|▋         | 4505/61904 [2:16:25<22:01:01,  1.38s/it]
  7%|▋         | 4506/61904 [2:16:27<22:47:46,  1.43s/it]
  7%|▋         | 4507/61904 [2:16:28<22:30:14,  1.41s/it]
  7%|▋         | 4508/61904 [2:16:29<21:58:34,  1.38s/it]
  7%|▋         | 4509/61904 [2:16:31<21:47:02,  1.37s/it]
  7%|▋         | 4510/61904 [2:16:32<21:47:14,  1.37s/it]
  7%|▋         | 4511/61904 [2:16:33<21:49:55,  1.37s/it]
  7%|▋         | 4512/61904 [2:16:35<22:07:38,  1.39s/it]
  7%|▋         | 4513/61904 [2:16:36<21:41:32,  1.36s/it]
  7%|▋         | 4514/61904 [2:16:37<21:15:17,  1.33s/it]
  7%|▋         | 4515/61904 [2:16:39<21:29:30,  1.35s/it]
  7%|▋         | 4516/61904 [2:16:40<21:35:31,  1.35s/it]
  7%|▋         | 4517/61904 [2:16:41<21:31:14,  1.35s/it]
  7%|▋         | 4518/61904 [2:16:43<21:43:46,  1.36s/it]
  7%|▋         | 4519/61904 [2:16:44<21:39:19,  1.36s/it]
  7%|▋         | 4520/61904 [2:16:45<21:33:02,  1.35s/it]
                                                         
{'loss': 2.9897, 'learning_rate': 1.9299883313885646e-07, 'epoch': 1.17}

  7%|▋         | 4520/61904 [2:16:45<21:33:02,  1.35s/it]
  7%|▋         | 4521/61904 [2:16:47<21:25:23,  1.34s/it]
  7%|▋         | 4522/61904 [2:16:48<21:18:08,  1.34s/it]
  7%|▋         | 4523/61904 [2:16:50<22:12:54,  1.39s/it]
  7%|▋         | 4524/61904 [2:16:51<21:44:37,  1.36s/it]
  7%|▋         | 4525/61904 [2:16:52<21:44:16,  1.36s/it]
  7%|▋         | 4526/61904 [2:16:54<21:20:38,  1.34s/it]
  7%|▋         | 4527/61904 [2:16:55<21:53:23,  1.37s/it]
  7%|▋         | 4528/61904 [2:16:56<22:17:59,  1.40s/it]
  7%|▋         | 4529/61904 [2:16:58<22:15:33,  1.40s/it]
  7%|▋         | 4530/61904 [2:16:59<21:51:47,  1.37s/it]
  7%|▋         | 4531/61904 [2:17:01<22:03:52,  1.38s/it]
  7%|▋         | 4532/61904 [2:17:02<21:27:44,  1.35s/it]
  7%|▋         | 4533/61904 [2:17:03<22:03:23,  1.38s/it]
  7%|▋         | 4534/61904 [2:17:05<21:57:36,  1.38s/it]
  7%|▋         | 4535/61904 [2:17:06<21:37:36,  1.36s/it]
  7%|▋         | 4536/61904 [2:17:07<21:35:45,  1.36s/it]
  7%|▋         | 4537/61904 [2:17:09<21:35:54,  1.36s/it]
  7%|▋         | 4538/61904 [2:17:10<21:25:01,  1.34s/it]
  7%|▋         | 4539/61904 [2:17:12<23:06:47,  1.45s/it]
  7%|▋         | 4540/61904 [2:17:13<23:17:04,  1.46s/it]
                                                         
{'loss': 3.0404, 'learning_rate': 1.9296642032931413e-07, 'epoch': 1.17}

  7%|▋         | 4540/61904 [2:17:13<23:17:04,  1.46s/it]
  7%|▋         | 4541/61904 [2:17:15<23:02:02,  1.45s/it]
  7%|▋         | 4542/61904 [2:17:16<22:07:39,  1.39s/it]
  7%|▋         | 4543/61904 [2:17:17<23:00:07,  1.44s/it]
  7%|▋         | 4544/61904 [2:17:19<22:06:45,  1.39s/it]
  7%|▋         | 4545/61904 [2:17:20<22:53:21,  1.44s/it]
  7%|▋         | 4546/61904 [2:17:22<22:59:12,  1.44s/it]
  7%|▋         | 4547/61904 [2:17:23<22:42:44,  1.43s/it]
  7%|▋         | 4548/61904 [2:17:24<21:55:47,  1.38s/it]
  7%|▋         | 4549/61904 [2:17:26<22:00:26,  1.38s/it]
  7%|▋         | 4550/61904 [2:17:27<22:23:50,  1.41s/it]
  7%|▋         | 4551/61904 [2:17:29<22:06:58,  1.39s/it]
  7%|▋         | 4552/61904 [2:17:30<22:00:03,  1.38s/it]
  7%|▋         | 4553/61904 [2:17:31<21:24:46,  1.34s/it]
  7%|▋         | 4554/61904 [2:17:33<21:38:10,  1.36s/it]
  7%|▋         | 4555/61904 [2:17:34<21:17:13,  1.34s/it]
  7%|▋         | 4556/61904 [2:17:35<21:13:20,  1.33s/it]
  7%|▋         | 4557/61904 [2:17:37<21:26:11,  1.35s/it]
  7%|▋         | 4558/61904 [2:17:38<20:49:07,  1.31s/it]
  7%|▋         | 4559/61904 [2:17:39<21:36:35,  1.36s/it]
  7%|▋         | 4560/61904 [2:17:41<22:27:16,  1.41s/it]
                                                         
{'loss': 2.9724, 'learning_rate': 1.9293400751977181e-07, 'epoch': 1.18}

  7%|▋         | 4560/61904 [2:17:41<22:27:16,  1.41s/it]
  7%|▋         | 4561/61904 [2:17:42<21:51:20,  1.37s/it]
  7%|▋         | 4562/61904 [2:17:44<22:16:32,  1.40s/it]
  7%|▋         | 4563/61904 [2:17:45<22:49:36,  1.43s/it]
  7%|▋         | 4564/61904 [2:17:46<22:33:27,  1.42s/it]
  7%|▋         | 4565/61904 [2:17:48<21:45:44,  1.37s/it]
  7%|▋         | 4566/61904 [2:17:49<22:11:50,  1.39s/it]
  7%|▋         | 4567/61904 [2:17:51<22:09:44,  1.39s/it]
  7%|▋         | 4568/61904 [2:17:52<21:44:47,  1.37s/it]
  7%|▋         | 4569/61904 [2:17:53<21:40:02,  1.36s/it]
  7%|▋         | 4570/61904 [2:17:54<21:28:46,  1.35s/it]
  7%|▋         | 4571/61904 [2:17:56<21:46:35,  1.37s/it]
  7%|▋         | 4572/61904 [2:17:57<22:01:35,  1.38s/it]
  7%|▋         | 4573/61904 [2:17:59<22:05:00,  1.39s/it]
  7%|▋         | 4574/61904 [2:18:00<21:24:23,  1.34s/it]
  7%|▋         | 4575/61904 [2:18:01<21:10:12,  1.33s/it]
  7%|▋         | 4576/61904 [2:18:03<22:15:51,  1.40s/it]
  7%|▋         | 4577/61904 [2:18:04<22:36:08,  1.42s/it]
  7%|▋         | 4578/61904 [2:18:06<21:59:05,  1.38s/it]
  7%|▋         | 4579/61904 [2:18:07<22:03:43,  1.39s/it]
  7%|▋         | 4580/61904 [2:18:08<21:55:41,  1.38s/it]
                                                         
{'loss': 3.019, 'learning_rate': 1.9290159471022948e-07, 'epoch': 1.18}

  7%|▋         | 4580/61904 [2:18:08<21:55:41,  1.38s/it]
  7%|▋         | 4581/61904 [2:18:10<21:24:16,  1.34s/it]
  7%|▋         | 4582/61904 [2:18:11<21:36:31,  1.36s/it]
  7%|▋         | 4583/61904 [2:18:12<21:48:19,  1.37s/it]
  7%|▋         | 4584/61904 [2:18:14<21:43:50,  1.36s/it]
  7%|▋         | 4585/61904 [2:18:15<21:35:41,  1.36s/it]
  7%|▋         | 4586/61904 [2:18:16<21:37:25,  1.36s/it]
  7%|▋         | 4587/61904 [2:18:18<21:18:30,  1.34s/it]
  7%|▋         | 4588/61904 [2:18:19<20:56:15,  1.32s/it]
  7%|▋         | 4589/61904 [2:18:20<21:01:17,  1.32s/it]
  7%|▋         | 4590/61904 [2:18:22<20:38:33,  1.30s/it]
  7%|▋         | 4591/61904 [2:18:23<21:12:26,  1.33s/it]
  7%|▋         | 4592/61904 [2:18:24<21:50:06,  1.37s/it]
  7%|▋         | 4593/61904 [2:18:26<21:58:07,  1.38s/it]
  7%|▋         | 4594/61904 [2:18:27<21:27:49,  1.35s/it]
  7%|▋         | 4595/61904 [2:18:28<21:30:36,  1.35s/it]
  7%|▋         | 4596/61904 [2:18:30<21:49:14,  1.37s/it]
  7%|▋         | 4597/61904 [2:18:31<22:25:39,  1.41s/it]
  7%|▋         | 4598/61904 [2:18:33<21:46:08,  1.37s/it]
  7%|▋         | 4599/61904 [2:18:34<22:03:22,  1.39s/it]
  7%|▋         | 4600/61904 [2:18:35<21:56:58,  1.38s/it]
                                                         
{'loss': 2.9637, 'learning_rate': 1.9286918190068714e-07, 'epoch': 1.19}

  7%|▋         | 4600/61904 [2:18:35<21:56:58,  1.38s/it]
  7%|▋         | 4601/61904 [2:18:37<22:21:37,  1.40s/it]
  7%|▋         | 4602/61904 [2:18:38<22:15:30,  1.40s/it]
  7%|▋         | 4603/61904 [2:18:40<21:52:38,  1.37s/it]
  7%|▋         | 4604/61904 [2:18:41<21:44:57,  1.37s/it]
  7%|▋         | 4605/61904 [2:18:42<21:12:49,  1.33s/it]
  7%|▋         | 4606/61904 [2:18:43<20:39:02,  1.30s/it]
  7%|▋         | 4607/61904 [2:18:45<20:59:22,  1.32s/it]
  7%|▋         | 4608/61904 [2:18:46<21:50:36,  1.37s/it]
  7%|▋         | 4609/61904 [2:18:48<21:58:31,  1.38s/it]
  7%|▋         | 4610/61904 [2:18:49<22:05:17,  1.39s/it]
  7%|▋         | 4611/61904 [2:18:50<21:51:56,  1.37s/it]
  7%|▋         | 4612/61904 [2:18:52<22:19:43,  1.40s/it]
  7%|▋         | 4613/61904 [2:18:53<21:35:44,  1.36s/it]
  7%|▋         | 4614/61904 [2:18:54<21:21:37,  1.34s/it]
  7%|▋         | 4615/61904 [2:18:56<21:09:42,  1.33s/it]
  7%|▋         | 4616/61904 [2:18:57<21:03:11,  1.32s/it]
  7%|▋         | 4617/61904 [2:18:59<21:52:39,  1.37s/it]
  7%|▋         | 4618/61904 [2:19:00<22:52:14,  1.44s/it]
  7%|▋         | 4619/61904 [2:19:01<22:09:36,  1.39s/it]
  7%|▋         | 4620/61904 [2:19:03<21:46:16,  1.37s/it]
                                                         
{'loss': 3.0281, 'learning_rate': 1.9283676909114483e-07, 'epoch': 1.19}

  7%|▋         | 4620/61904 [2:19:03<21:46:16,  1.37s/it]
  7%|▋         | 4621/61904 [2:19:04<21:54:22,  1.38s/it]
  7%|▋         | 4622/61904 [2:19:05<21:21:44,  1.34s/it]
  7%|▋         | 4623/61904 [2:19:07<21:29:59,  1.35s/it]
  7%|▋         | 4624/61904 [2:19:08<20:45:18,  1.30s/it]
  7%|▋         | 4625/61904 [2:19:09<20:46:42,  1.31s/it]
  7%|▋         | 4626/61904 [2:19:11<21:12:32,  1.33s/it]
  7%|▋         | 4627/61904 [2:19:12<22:15:30,  1.40s/it]
  7%|▋         | 4628/61904 [2:19:14<22:13:58,  1.40s/it]
  7%|▋         | 4629/61904 [2:19:15<21:32:19,  1.35s/it]
  7%|▋         | 4630/61904 [2:19:16<21:33:47,  1.36s/it]
  7%|▋         | 4631/61904 [2:19:18<21:10:21,  1.33s/it]
  7%|▋         | 4632/61904 [2:19:19<21:26:26,  1.35s/it]
  7%|▋         | 4633/61904 [2:19:20<21:51:33,  1.37s/it]
  7%|▋         | 4634/61904 [2:19:22<22:21:41,  1.41s/it]
  7%|▋         | 4635/61904 [2:19:23<22:23:01,  1.41s/it]
  7%|▋         | 4636/61904 [2:19:25<22:01:17,  1.38s/it]
  7%|▋         | 4637/61904 [2:19:26<22:21:48,  1.41s/it]
  7%|▋         | 4638/61904 [2:19:27<22:14:47,  1.40s/it]
  7%|▋         | 4639/61904 [2:19:29<21:37:20,  1.36s/it]
  7%|▋         | 4640/61904 [2:19:30<21:17:27,  1.34s/it]
                                                         
{'loss': 2.9964, 'learning_rate': 1.9280435628160246e-07, 'epoch': 1.2}

  7%|▋         | 4640/61904 [2:19:30<21:17:27,  1.34s/it]
  7%|▋         | 4641/61904 [2:19:31<22:11:01,  1.39s/it]
  7%|▋         | 4642/61904 [2:19:33<22:28:01,  1.41s/it]
  8%|▊         | 4643/61904 [2:19:34<22:14:21,  1.40s/it]
  8%|▊         | 4644/61904 [2:19:36<21:35:39,  1.36s/it]
  8%|▊         | 4645/61904 [2:19:37<21:09:47,  1.33s/it]
  8%|▊         | 4646/61904 [2:19:38<21:11:20,  1.33s/it]
  8%|▊         | 4647/61904 [2:19:39<20:55:46,  1.32s/it]
  8%|▊         | 4648/61904 [2:19:41<21:39:46,  1.36s/it]
  8%|▊         | 4649/61904 [2:19:42<21:39:01,  1.36s/it]
  8%|▊         | 4650/61904 [2:19:44<21:27:03,  1.35s/it]
  8%|▊         | 4651/61904 [2:19:45<21:43:27,  1.37s/it]
  8%|▊         | 4652/61904 [2:19:46<21:29:08,  1.35s/it]
  8%|▊         | 4653/61904 [2:19:48<21:29:29,  1.35s/it]
  8%|▊         | 4654/61904 [2:19:49<22:12:54,  1.40s/it]
  8%|▊         | 4655/61904 [2:19:51<22:06:05,  1.39s/it]
  8%|▊         | 4656/61904 [2:19:52<21:16:25,  1.34s/it]
  8%|▊         | 4657/61904 [2:19:53<21:41:26,  1.36s/it]
  8%|▊         | 4658/61904 [2:19:54<20:53:01,  1.31s/it]
  8%|▊         | 4659/61904 [2:19:56<20:26:35,  1.29s/it]
  8%|▊         | 4660/61904 [2:19:57<21:16:15,  1.34s/it]
                                                         
{'loss': 3.0762, 'learning_rate': 1.9277194347206015e-07, 'epoch': 1.2}

  8%|▊         | 4660/61904 [2:19:57<21:16:15,  1.34s/it]
  8%|▊         | 4661/61904 [2:19:58<21:42:33,  1.37s/it]
  8%|▊         | 4662/61904 [2:20:00<22:04:44,  1.39s/it]
  8%|▊         | 4663/61904 [2:20:01<21:27:42,  1.35s/it]
  8%|▊         | 4664/61904 [2:20:03<21:15:59,  1.34s/it]
  8%|▊         | 4665/61904 [2:20:04<21:05:09,  1.33s/it]
  8%|▊         | 4666/61904 [2:20:05<21:40:34,  1.36s/it]
  8%|▊         | 4667/61904 [2:20:07<21:47:04,  1.37s/it]
  8%|▊         | 4668/61904 [2:20:08<21:45:05,  1.37s/it]
  8%|▊         | 4669/61904 [2:20:09<21:15:51,  1.34s/it]
  8%|▊         | 4670/61904 [2:20:11<21:12:07,  1.33s/it]
  8%|▊         | 4671/61904 [2:20:12<21:27:17,  1.35s/it]
  8%|▊         | 4672/61904 [2:20:13<21:28:36,  1.35s/it]
  8%|▊         | 4673/61904 [2:20:15<21:44:44,  1.37s/it]
  8%|▊         | 4674/61904 [2:20:16<21:54:31,  1.38s/it]
  8%|▊         | 4675/61904 [2:20:18<22:29:30,  1.41s/it]
  8%|▊         | 4676/61904 [2:20:19<21:56:26,  1.38s/it]
  8%|▊         | 4677/61904 [2:20:20<21:53:22,  1.38s/it]
  8%|▊         | 4678/61904 [2:20:22<21:27:00,  1.35s/it]
  8%|▊         | 4679/61904 [2:20:23<21:42:12,  1.37s/it]
  8%|▊         | 4680/61904 [2:20:24<21:42:22,  1.37s/it]
                                                         
{'loss': 3.035, 'learning_rate': 1.9273953066251784e-07, 'epoch': 1.21}

  8%|▊         | 4680/61904 [2:20:24<21:42:22,  1.37s/it]
  8%|▊         | 4681/61904 [2:20:26<21:23:17,  1.35s/it]
  8%|▊         | 4682/61904 [2:20:27<21:15:06,  1.34s/it]
  8%|▊         | 4683/61904 [2:20:28<21:47:51,  1.37s/it]
  8%|▊         | 4684/61904 [2:20:30<21:35:41,  1.36s/it]
  8%|▊         | 4685/61904 [2:20:31<21:05:02,  1.33s/it]
  8%|▊         | 4686/61904 [2:20:32<20:54:27,  1.32s/it]
  8%|▊         | 4687/61904 [2:20:34<21:35:58,  1.36s/it]
  8%|▊         | 4688/61904 [2:20:35<21:44:32,  1.37s/it]
  8%|▊         | 4689/61904 [2:20:36<21:29:11,  1.35s/it]
  8%|▊         | 4690/61904 [2:20:38<21:25:36,  1.35s/it]
  8%|▊         | 4691/61904 [2:20:39<21:11:22,  1.33s/it]
  8%|▊         | 4692/61904 [2:20:41<22:11:02,  1.40s/it]
  8%|▊         | 4693/61904 [2:20:42<21:39:49,  1.36s/it]
  8%|▊         | 4694/61904 [2:20:43<21:29:14,  1.35s/it]
  8%|▊         | 4695/61904 [2:20:45<21:19:35,  1.34s/it]
  8%|▊         | 4696/61904 [2:20:46<21:24:04,  1.35s/it]
  8%|▊         | 4697/61904 [2:20:47<21:14:19,  1.34s/it]
  8%|▊         | 4698/61904 [2:20:49<21:46:15,  1.37s/it]
  8%|▊         | 4699/61904 [2:20:50<20:50:12,  1.31s/it]
  8%|▊         | 4700/61904 [2:20:51<21:44:16,  1.37s/it]
                                                         
{'loss': 2.9578, 'learning_rate': 1.9270711785297547e-07, 'epoch': 1.21}

  8%|▊         | 4700/61904 [2:20:51<21:44:16,  1.37s/it]
  8%|▊         | 4701/61904 [2:20:53<22:23:48,  1.41s/it]
  8%|▊         | 4702/61904 [2:20:54<22:18:15,  1.40s/it]
  8%|▊         | 4703/61904 [2:20:56<22:05:46,  1.39s/it]
  8%|▊         | 4704/61904 [2:20:57<21:25:45,  1.35s/it]
  8%|▊         | 4705/61904 [2:20:58<21:30:53,  1.35s/it]
  8%|▊         | 4706/61904 [2:21:00<21:42:50,  1.37s/it]
  8%|▊         | 4707/61904 [2:21:01<22:37:51,  1.42s/it]
  8%|▊         | 4708/61904 [2:21:03<22:40:35,  1.43s/it]
  8%|▊         | 4709/61904 [2:21:04<21:54:08,  1.38s/it]
  8%|▊         | 4710/61904 [2:21:05<21:37:11,  1.36s/it]
  8%|▊         | 4711/61904 [2:21:07<21:24:57,  1.35s/it]
  8%|▊         | 4712/61904 [2:21:08<21:25:45,  1.35s/it]
  8%|▊         | 4713/61904 [2:21:09<21:49:33,  1.37s/it]
  8%|▊         | 4714/61904 [2:21:11<21:04:39,  1.33s/it]
  8%|▊         | 4715/61904 [2:21:12<20:51:39,  1.31s/it]
  8%|▊         | 4716/61904 [2:21:13<20:43:54,  1.31s/it]
  8%|▊         | 4717/61904 [2:21:14<20:22:51,  1.28s/it]
  8%|▊         | 4718/61904 [2:21:16<21:37:13,  1.36s/it]
  8%|▊         | 4719/61904 [2:21:17<22:01:22,  1.39s/it]
  8%|▊         | 4720/61904 [2:21:19<21:37:49,  1.36s/it]
                                                         
{'loss': 2.9568, 'learning_rate': 1.9267470504343316e-07, 'epoch': 1.22}

  8%|▊         | 4720/61904 [2:21:19<21:37:49,  1.36s/it]
  8%|▊         | 4721/61904 [2:21:20<22:01:31,  1.39s/it]
  8%|▊         | 4722/61904 [2:21:21<22:05:30,  1.39s/it]
  8%|▊         | 4723/61904 [2:21:23<21:53:40,  1.38s/it]
  8%|▊         | 4724/61904 [2:21:24<21:50:26,  1.38s/it]
  8%|▊         | 4725/61904 [2:21:26<22:07:15,  1.39s/it]
  8%|▊         | 4726/61904 [2:21:27<21:28:45,  1.35s/it]
  8%|▊         | 4727/61904 [2:21:28<21:14:30,  1.34s/it]
  8%|▊         | 4728/61904 [2:21:30<21:33:21,  1.36s/it]
  8%|▊         | 4729/61904 [2:21:31<21:28:31,  1.35s/it]
  8%|▊         | 4730/61904 [2:21:32<21:36:15,  1.36s/it]
  8%|▊         | 4731/61904 [2:21:34<21:12:02,  1.33s/it]
  8%|▊         | 4732/61904 [2:21:35<21:01:41,  1.32s/it]
  8%|▊         | 4733/61904 [2:21:36<22:11:27,  1.40s/it]
  8%|▊         | 4734/61904 [2:21:38<22:00:21,  1.39s/it]
  8%|▊         | 4735/61904 [2:21:39<21:58:17,  1.38s/it]
  8%|▊         | 4736/61904 [2:21:41<22:27:02,  1.41s/it]
  8%|▊         | 4737/61904 [2:21:42<22:07:53,  1.39s/it]
  8%|▊         | 4738/61904 [2:21:43<21:54:42,  1.38s/it]
  8%|▊         | 4739/61904 [2:21:45<22:06:37,  1.39s/it]
  8%|▊         | 4740/61904 [2:21:46<22:01:29,  1.39s/it]
                                                         
{'loss': 3.0495, 'learning_rate': 1.9264229223389082e-07, 'epoch': 1.22}

  8%|▊         | 4740/61904 [2:21:46<22:01:29,  1.39s/it]
  8%|▊         | 4741/61904 [2:21:47<21:17:59,  1.34s/it]
  8%|▊         | 4742/61904 [2:21:49<21:37:46,  1.36s/it]
  8%|▊         | 4743/61904 [2:21:50<21:18:51,  1.34s/it]
  8%|▊         | 4744/61904 [2:21:52<21:37:13,  1.36s/it]
  8%|▊         | 4745/61904 [2:21:53<21:51:15,  1.38s/it]
  8%|▊         | 4746/61904 [2:21:54<22:11:41,  1.40s/it]
  8%|▊         | 4747/61904 [2:21:56<22:29:16,  1.42s/it]
  8%|▊         | 4748/61904 [2:21:57<22:32:02,  1.42s/it]
  8%|▊         | 4749/61904 [2:21:59<21:47:03,  1.37s/it]
  8%|▊         | 4750/61904 [2:22:00<21:00:05,  1.32s/it]
  8%|▊         | 4751/61904 [2:22:01<20:59:59,  1.32s/it]
  8%|▊         | 4752/61904 [2:22:02<21:14:49,  1.34s/it]
  8%|▊         | 4753/61904 [2:22:04<21:30:12,  1.35s/it]
  8%|▊         | 4754/61904 [2:22:05<22:06:06,  1.39s/it]
  8%|▊         | 4755/61904 [2:22:07<21:18:02,  1.34s/it]
  8%|▊         | 4756/61904 [2:22:08<21:09:40,  1.33s/it]
  8%|▊         | 4757/61904 [2:22:09<21:31:56,  1.36s/it]
  8%|▊         | 4758/61904 [2:22:11<22:02:04,  1.39s/it]
  8%|▊         | 4759/61904 [2:22:12<22:07:00,  1.39s/it]
  8%|▊         | 4760/61904 [2:22:13<21:35:31,  1.36s/it]
                                                         
{'loss': 3.0054, 'learning_rate': 1.9260987942434848e-07, 'epoch': 1.23}

  8%|▊         | 4760/61904 [2:22:13<21:35:31,  1.36s/it]
  8%|▊         | 4761/61904 [2:22:15<21:31:53,  1.36s/it]
  8%|▊         | 4762/61904 [2:22:16<21:29:31,  1.35s/it]
  8%|▊         | 4763/61904 [2:22:17<21:43:27,  1.37s/it]
  8%|▊         | 4764/61904 [2:22:19<22:45:37,  1.43s/it]
  8%|▊         | 4765/61904 [2:22:20<22:20:41,  1.41s/it]
  8%|▊         | 4766/61904 [2:22:22<21:57:45,  1.38s/it]
  8%|▊         | 4767/61904 [2:22:23<21:56:58,  1.38s/it]
  8%|▊         | 4768/61904 [2:22:25<21:59:53,  1.39s/it]
  8%|▊         | 4769/61904 [2:22:26<22:14:39,  1.40s/it]
  8%|▊         | 4770/61904 [2:22:27<22:29:35,  1.42s/it]
  8%|▊         | 4771/61904 [2:22:29<21:49:51,  1.38s/it]
  8%|▊         | 4772/61904 [2:22:30<21:12:53,  1.34s/it]
  8%|▊         | 4773/61904 [2:22:31<21:25:23,  1.35s/it]
  8%|▊         | 4774/61904 [2:22:33<21:07:49,  1.33s/it]
  8%|▊         | 4775/61904 [2:22:34<21:46:59,  1.37s/it]
  8%|▊         | 4776/61904 [2:22:35<21:20:53,  1.35s/it]
  8%|▊         | 4777/61904 [2:22:37<21:31:39,  1.36s/it]
  8%|▊         | 4778/61904 [2:22:38<21:15:08,  1.34s/it]
  8%|▊         | 4779/61904 [2:22:39<21:20:34,  1.35s/it]
  8%|▊         | 4780/61904 [2:22:41<21:36:58,  1.36s/it]
                                                         
{'loss': 3.0101, 'learning_rate': 1.9257746661480617e-07, 'epoch': 1.24}

  8%|▊         | 4780/61904 [2:22:41<21:36:58,  1.36s/it]
  8%|▊         | 4781/61904 [2:22:42<21:40:10,  1.37s/it]
  8%|▊         | 4782/61904 [2:22:44<21:32:28,  1.36s/it]
  8%|▊         | 4783/61904 [2:22:45<21:28:58,  1.35s/it]
  8%|▊         | 4784/61904 [2:22:46<21:48:14,  1.37s/it]
  8%|▊         | 4785/61904 [2:22:48<22:02:46,  1.39s/it]
  8%|▊         | 4786/61904 [2:22:49<21:34:52,  1.36s/it]
  8%|▊         | 4787/61904 [2:22:50<21:37:26,  1.36s/it]
  8%|▊         | 4788/61904 [2:22:52<21:26:03,  1.35s/it]
  8%|▊         | 4789/61904 [2:22:53<21:30:58,  1.36s/it]
  8%|▊         | 4790/61904 [2:22:54<21:17:07,  1.34s/it]
  8%|▊         | 4791/61904 [2:22:56<20:59:54,  1.32s/it]
  8%|▊         | 4792/61904 [2:22:57<22:05:53,  1.39s/it]
  8%|▊         | 4793/61904 [2:22:59<22:02:24,  1.39s/it]
  8%|▊         | 4794/61904 [2:23:00<22:00:23,  1.39s/it]
  8%|▊         | 4795/61904 [2:23:01<22:06:26,  1.39s/it]
  8%|▊         | 4796/61904 [2:23:03<22:05:01,  1.39s/it]
  8%|▊         | 4797/61904 [2:23:04<21:40:23,  1.37s/it]
  8%|▊         | 4798/61904 [2:23:05<21:24:10,  1.35s/it]
  8%|▊         | 4799/61904 [2:23:07<22:17:01,  1.40s/it]
  8%|▊         | 4800/61904 [2:23:08<22:54:21,  1.44s/it]
                                                         
{'loss': 2.9621, 'learning_rate': 1.9254505380526384e-07, 'epoch': 1.24}

  8%|▊         | 4800/61904 [2:23:08<22:54:21,  1.44s/it]
  8%|▊         | 4801/61904 [2:23:10<22:02:01,  1.39s/it]
  8%|▊         | 4802/61904 [2:23:11<21:11:24,  1.34s/it]
  8%|▊         | 4803/61904 [2:23:12<20:51:17,  1.31s/it]
  8%|▊         | 4804/61904 [2:23:13<20:11:26,  1.27s/it]
  8%|▊         | 4805/61904 [2:23:15<21:00:56,  1.32s/it]
  8%|▊         | 4806/61904 [2:23:16<21:10:07,  1.33s/it]
  8%|▊         | 4807/61904 [2:23:17<21:03:23,  1.33s/it]
  8%|▊         | 4808/61904 [2:23:19<20:40:15,  1.30s/it]
  8%|▊         | 4809/61904 [2:23:20<21:04:34,  1.33s/it]
  8%|▊         | 4810/61904 [2:23:21<20:47:07,  1.31s/it]
  8%|▊         | 4811/61904 [2:23:23<20:32:08,  1.29s/it]
  8%|▊         | 4812/61904 [2:23:24<22:01:01,  1.39s/it]
  8%|▊         | 4813/61904 [2:23:26<22:45:26,  1.44s/it]
  8%|▊         | 4814/61904 [2:23:27<22:01:21,  1.39s/it]
  8%|▊         | 4815/61904 [2:23:28<21:13:55,  1.34s/it]
  8%|▊         | 4816/61904 [2:23:30<21:25:13,  1.35s/it]
  8%|▊         | 4817/61904 [2:23:31<21:04:12,  1.33s/it]
  8%|▊         | 4818/61904 [2:23:32<21:20:18,  1.35s/it]
  8%|▊         | 4819/61904 [2:23:34<22:11:33,  1.40s/it]
  8%|▊         | 4820/61904 [2:23:35<22:18:50,  1.41s/it]
                                                         
{'loss': 3.0161, 'learning_rate': 1.925126409957215e-07, 'epoch': 1.25}

  8%|▊         | 4820/61904 [2:23:35<22:18:50,  1.41s/it]
  8%|▊         | 4821/61904 [2:23:37<22:06:47,  1.39s/it]
  8%|▊         | 4822/61904 [2:23:38<22:06:39,  1.39s/it]
  8%|▊         | 4823/61904 [2:23:40<23:18:43,  1.47s/it]
  8%|▊         | 4824/61904 [2:23:41<23:42:21,  1.50s/it]
  8%|▊         | 4825/61904 [2:23:43<22:58:50,  1.45s/it]
  8%|▊         | 4826/61904 [2:23:44<22:38:02,  1.43s/it]
  8%|▊         | 4827/61904 [2:23:45<22:14:50,  1.40s/it]
  8%|▊         | 4828/61904 [2:23:47<21:53:18,  1.38s/it]
  8%|▊         | 4829/61904 [2:23:48<22:23:43,  1.41s/it]
  8%|▊         | 4830/61904 [2:23:50<22:39:28,  1.43s/it]
  8%|▊         | 4831/61904 [2:23:51<21:34:54,  1.36s/it]
  8%|▊         | 4832/61904 [2:23:52<21:29:25,  1.36s/it]
  8%|▊         | 4833/61904 [2:23:53<21:26:58,  1.35s/it]
  8%|▊         | 4834/61904 [2:23:55<21:36:42,  1.36s/it]
  8%|▊         | 4835/61904 [2:23:56<22:05:27,  1.39s/it]
  8%|▊         | 4836/61904 [2:23:58<21:26:56,  1.35s/it]
  8%|▊         | 4837/61904 [2:23:59<21:16:14,  1.34s/it]
  8%|▊         | 4838/61904 [2:24:01<22:29:34,  1.42s/it]
  8%|▊         | 4839/61904 [2:24:02<22:28:40,  1.42s/it]
  8%|▊         | 4840/61904 [2:24:03<22:26:06,  1.42s/it]
                                                         
{'loss': 2.9672, 'learning_rate': 1.9248022818617919e-07, 'epoch': 1.25}

  8%|▊         | 4840/61904 [2:24:03<22:26:06,  1.42s/it]
  8%|▊         | 4841/61904 [2:24:05<21:35:47,  1.36s/it]
  8%|▊         | 4842/61904 [2:24:06<21:34:30,  1.36s/it]
  8%|▊         | 4843/61904 [2:24:07<21:14:24,  1.34s/it]
  8%|▊         | 4844/61904 [2:24:09<21:52:01,  1.38s/it]
  8%|▊         | 4845/61904 [2:24:10<22:16:10,  1.41s/it]
  8%|▊         | 4846/61904 [2:24:11<21:30:57,  1.36s/it]
  8%|▊         | 4847/61904 [2:24:13<21:52:15,  1.38s/it]
  8%|▊         | 4848/61904 [2:24:14<21:18:06,  1.34s/it]
  8%|▊         | 4849/61904 [2:24:15<21:14:32,  1.34s/it]
  8%|▊         | 4850/61904 [2:24:17<21:44:58,  1.37s/it]
  8%|▊         | 4851/61904 [2:24:18<22:21:10,  1.41s/it]
  8%|▊         | 4852/61904 [2:24:20<21:12:36,  1.34s/it]
  8%|▊         | 4853/61904 [2:24:21<21:03:06,  1.33s/it]
  8%|▊         | 4854/61904 [2:24:22<22:15:39,  1.40s/it]
  8%|▊         | 4855/61904 [2:24:24<22:43:41,  1.43s/it]
  8%|▊         | 4856/61904 [2:24:25<21:57:33,  1.39s/it]
  8%|▊         | 4857/61904 [2:24:26<21:20:59,  1.35s/it]
  8%|▊         | 4858/61904 [2:24:28<20:56:14,  1.32s/it]
  8%|▊         | 4859/61904 [2:24:29<21:18:10,  1.34s/it]
  8%|▊         | 4860/61904 [2:24:31<21:25:45,  1.35s/it]
                                                         
{'loss': 2.9749, 'learning_rate': 1.9244781537663682e-07, 'epoch': 1.26}

  8%|▊         | 4860/61904 [2:24:31<21:25:45,  1.35s/it]
  8%|▊         | 4861/61904 [2:24:32<21:03:30,  1.33s/it]
  8%|▊         | 4862/61904 [2:24:33<20:47:43,  1.31s/it]
  8%|▊         | 4863/61904 [2:24:34<20:34:48,  1.30s/it]
  8%|▊         | 4864/61904 [2:24:36<20:37:18,  1.30s/it]
  8%|▊         | 4865/61904 [2:24:37<21:10:36,  1.34s/it]
  8%|▊         | 4866/61904 [2:24:39<22:00:43,  1.39s/it]
  8%|▊         | 4867/61904 [2:24:40<23:15:19,  1.47s/it]
  8%|▊         | 4868/61904 [2:24:41<22:09:32,  1.40s/it]
  8%|▊         | 4869/61904 [2:24:43<22:07:03,  1.40s/it]
  8%|▊         | 4870/61904 [2:24:44<22:03:47,  1.39s/it]
  8%|▊         | 4871/61904 [2:24:46<22:03:07,  1.39s/it]
  8%|▊         | 4872/61904 [2:24:47<21:55:08,  1.38s/it]
  8%|▊         | 4873/61904 [2:24:48<21:54:33,  1.38s/it]
  8%|▊         | 4874/61904 [2:24:50<21:47:11,  1.38s/it]
  8%|▊         | 4875/61904 [2:24:51<21:03:28,  1.33s/it]
  8%|▊         | 4876/61904 [2:24:52<21:15:13,  1.34s/it]
  8%|▊         | 4877/61904 [2:24:54<21:17:17,  1.34s/it]
  8%|▊         | 4878/61904 [2:24:55<21:18:52,  1.35s/it]
  8%|▊         | 4879/61904 [2:24:57<22:03:15,  1.39s/it]
  8%|▊         | 4880/61904 [2:24:58<21:38:20,  1.37s/it]
                                                         
{'loss': 2.9898, 'learning_rate': 1.924154025670945e-07, 'epoch': 1.26}

  8%|▊         | 4880/61904 [2:24:58<21:38:20,  1.37s/it]
  8%|▊         | 4881/61904 [2:24:59<21:21:07,  1.35s/it]
  8%|▊         | 4882/61904 [2:25:01<21:38:28,  1.37s/it]
  8%|▊         | 4883/61904 [2:25:02<21:43:09,  1.37s/it]
  8%|▊         | 4884/61904 [2:25:03<22:04:15,  1.39s/it]
  8%|▊         | 4885/61904 [2:25:05<21:21:46,  1.35s/it]
  8%|▊         | 4886/61904 [2:25:06<22:22:03,  1.41s/it]
  8%|▊         | 4887/61904 [2:25:07<21:33:15,  1.36s/it]
  8%|▊         | 4888/61904 [2:25:09<21:04:57,  1.33s/it]
  8%|▊         | 4889/61904 [2:25:10<21:01:45,  1.33s/it]
  8%|▊         | 4890/61904 [2:25:11<21:01:02,  1.33s/it]
  8%|▊         | 4891/61904 [2:25:13<21:14:20,  1.34s/it]
  8%|▊         | 4892/61904 [2:25:14<21:16:55,  1.34s/it]
  8%|▊         | 4893/61904 [2:25:15<20:59:44,  1.33s/it]
  8%|▊         | 4894/61904 [2:25:17<21:01:56,  1.33s/it]
  8%|▊         | 4895/61904 [2:25:18<21:44:01,  1.37s/it]
  8%|▊         | 4896/61904 [2:25:19<21:30:25,  1.36s/it]
  8%|▊         | 4897/61904 [2:25:21<21:33:00,  1.36s/it]
  8%|▊         | 4898/61904 [2:25:22<21:17:28,  1.34s/it]
  8%|▊         | 4899/61904 [2:25:24<21:46:41,  1.38s/it]
  8%|▊         | 4900/61904 [2:25:25<21:13:02,  1.34s/it]
                                                         
{'loss': 2.9917, 'learning_rate': 1.9238298975755217e-07, 'epoch': 1.27}

  8%|▊         | 4900/61904 [2:25:25<21:13:02,  1.34s/it]
  8%|▊         | 4901/61904 [2:25:26<21:21:17,  1.35s/it]
  8%|▊         | 4902/61904 [2:25:28<21:16:05,  1.34s/it]
  8%|▊         | 4903/61904 [2:25:29<20:46:16,  1.31s/it]
  8%|▊         | 4904/61904 [2:25:30<21:14:25,  1.34s/it]
  8%|▊         | 4905/61904 [2:25:31<20:22:45,  1.29s/it]
  8%|▊         | 4906/61904 [2:25:33<20:39:19,  1.30s/it]
  8%|▊         | 4907/61904 [2:25:34<20:04:38,  1.27s/it]
  8%|▊         | 4908/61904 [2:25:35<21:14:35,  1.34s/it]
  8%|▊         | 4909/61904 [2:25:37<21:37:31,  1.37s/it]
  8%|▊         | 4910/61904 [2:25:38<21:41:50,  1.37s/it]
  8%|▊         | 4911/61904 [2:25:39<20:37:35,  1.30s/it]
  8%|▊         | 4912/61904 [2:25:41<21:09:38,  1.34s/it]
  8%|▊         | 4913/61904 [2:25:42<21:52:04,  1.38s/it]
  8%|▊         | 4914/61904 [2:25:44<21:58:25,  1.39s/it]
  8%|▊         | 4915/61904 [2:25:45<21:34:04,  1.36s/it]
  8%|▊         | 4916/61904 [2:25:46<21:33:40,  1.36s/it]
  8%|▊         | 4917/61904 [2:25:48<21:02:58,  1.33s/it]
  8%|▊         | 4918/61904 [2:25:49<21:22:22,  1.35s/it]
  8%|▊         | 4919/61904 [2:25:50<21:40:43,  1.37s/it]
  8%|▊         | 4920/61904 [2:25:52<21:47:58,  1.38s/it]
                                                         
{'loss': 2.9675, 'learning_rate': 1.9235057694800983e-07, 'epoch': 1.27}

  8%|▊         | 4920/61904 [2:25:52<21:47:58,  1.38s/it]
  8%|▊         | 4921/61904 [2:25:53<22:29:38,  1.42s/it]
  8%|▊         | 4922/61904 [2:25:55<22:23:03,  1.41s/it]
  8%|▊         | 4923/61904 [2:25:56<21:46:19,  1.38s/it]
  8%|▊         | 4924/61904 [2:25:57<21:55:00,  1.38s/it]
  8%|▊         | 4925/61904 [2:25:59<21:47:43,  1.38s/it]
  8%|▊         | 4926/61904 [2:26:00<21:55:51,  1.39s/it]
  8%|▊         | 4927/61904 [2:26:01<21:19:49,  1.35s/it]
  8%|▊         | 4928/61904 [2:26:03<21:50:35,  1.38s/it]
  8%|▊         | 4929/61904 [2:26:04<21:46:58,  1.38s/it]
  8%|▊         | 4930/61904 [2:26:06<22:49:23,  1.44s/it]
  8%|▊         | 4931/61904 [2:26:07<22:27:24,  1.42s/it]
  8%|▊         | 4932/61904 [2:26:08<21:50:34,  1.38s/it]
  8%|▊         | 4933/61904 [2:26:10<21:04:26,  1.33s/it]
  8%|▊         | 4934/61904 [2:26:11<20:50:19,  1.32s/it]
  8%|▊         | 4935/61904 [2:26:12<20:48:59,  1.32s/it]
  8%|▊         | 4936/61904 [2:26:14<20:39:47,  1.31s/it]
  8%|▊         | 4937/61904 [2:26:15<22:35:21,  1.43s/it]
  8%|▊         | 4938/61904 [2:26:17<22:11:22,  1.40s/it]
  8%|▊         | 4939/61904 [2:26:18<21:58:54,  1.39s/it]
  8%|▊         | 4940/61904 [2:26:19<21:57:31,  1.39s/it]
                                                         
{'loss': 2.9495, 'learning_rate': 1.9231816413846752e-07, 'epoch': 1.28}

  8%|▊         | 4940/61904 [2:26:19<21:57:31,  1.39s/it]
  8%|▊         | 4941/61904 [2:26:21<21:41:13,  1.37s/it]
  8%|▊         | 4942/61904 [2:26:22<21:29:11,  1.36s/it]
  8%|▊         | 4943/61904 [2:26:23<21:37:42,  1.37s/it]
  8%|▊         | 4944/61904 [2:26:25<21:03:59,  1.33s/it]
  8%|▊         | 4945/61904 [2:26:26<21:02:57,  1.33s/it]
  8%|▊         | 4946/61904 [2:26:27<21:19:01,  1.35s/it]
  8%|▊         | 4947/61904 [2:26:29<21:57:41,  1.39s/it]
  8%|▊         | 4948/61904 [2:26:30<22:15:37,  1.41s/it]
  8%|▊         | 4949/61904 [2:26:32<21:47:31,  1.38s/it]
  8%|▊         | 4950/61904 [2:26:33<21:46:58,  1.38s/it]
  8%|▊         | 4951/61904 [2:26:34<21:28:11,  1.36s/it]
  8%|▊         | 4952/61904 [2:26:36<21:05:50,  1.33s/it]
  8%|▊         | 4953/61904 [2:26:37<21:27:58,  1.36s/it]
  8%|▊         | 4954/61904 [2:26:38<21:20:10,  1.35s/it]
  8%|▊         | 4955/61904 [2:26:40<20:58:30,  1.33s/it]
  8%|▊         | 4956/61904 [2:26:41<20:53:45,  1.32s/it]
  8%|▊         | 4957/61904 [2:26:42<20:50:07,  1.32s/it]
  8%|▊         | 4958/61904 [2:26:44<21:30:23,  1.36s/it]
  8%|▊         | 4959/61904 [2:26:45<21:26:18,  1.36s/it]
  8%|▊         | 4960/61904 [2:26:47<22:02:03,  1.39s/it]
                                                         
{'loss': 3.0443, 'learning_rate': 1.9228575132892518e-07, 'epoch': 1.28}

  8%|▊         | 4960/61904 [2:26:47<22:02:03,  1.39s/it]
  8%|▊         | 4961/61904 [2:26:48<21:39:48,  1.37s/it]
  8%|▊         | 4962/61904 [2:26:49<21:53:28,  1.38s/it]
  8%|▊         | 4963/61904 [2:26:50<20:48:55,  1.32s/it]
  8%|▊         | 4964/61904 [2:26:52<20:16:19,  1.28s/it]
  8%|▊         | 4965/61904 [2:26:53<21:03:48,  1.33s/it]
  8%|▊         | 4966/61904 [2:26:54<20:58:57,  1.33s/it]
  8%|▊         | 4967/61904 [2:26:56<20:53:09,  1.32s/it]
  8%|▊         | 4968/61904 [2:26:57<21:09:48,  1.34s/it]
  8%|▊         | 4969/61904 [2:26:58<20:59:32,  1.33s/it]
  8%|▊         | 4970/61904 [2:27:00<20:48:26,  1.32s/it]
  8%|▊         | 4971/61904 [2:27:01<21:36:35,  1.37s/it]
  8%|▊         | 4972/61904 [2:27:02<21:40:05,  1.37s/it]
  8%|▊         | 4973/61904 [2:27:04<21:40:29,  1.37s/it]
  8%|▊         | 4974/61904 [2:27:05<21:16:11,  1.35s/it]
  8%|▊         | 4975/61904 [2:27:06<20:51:34,  1.32s/it]
  8%|▊         | 4976/61904 [2:27:08<20:14:22,  1.28s/it]
  8%|▊         | 4977/61904 [2:27:09<21:05:25,  1.33s/it]
  8%|▊         | 4978/61904 [2:27:11<21:50:51,  1.38s/it]
  8%|▊         | 4979/61904 [2:27:12<21:19:37,  1.35s/it]
  8%|▊         | 4980/61904 [2:27:13<21:00:20,  1.33s/it]
                                                         
{'loss': 2.9756, 'learning_rate': 1.9225333851938284e-07, 'epoch': 1.29}

  8%|▊         | 4980/61904 [2:27:13<21:00:20,  1.33s/it]
  8%|▊         | 4981/61904 [2:27:15<21:26:11,  1.36s/it]
  8%|▊         | 4982/61904 [2:27:16<21:25:26,  1.35s/it]
  8%|▊         | 4983/61904 [2:27:17<21:06:51,  1.34s/it]
  8%|▊         | 4984/61904 [2:27:19<21:22:05,  1.35s/it]
  8%|▊         | 4985/61904 [2:27:20<21:02:54,  1.33s/it]
  8%|▊         | 4986/61904 [2:27:21<21:10:57,  1.34s/it]
  8%|▊         | 4987/61904 [2:27:23<21:34:27,  1.36s/it]
  8%|▊         | 4988/61904 [2:27:24<22:18:04,  1.41s/it]
  8%|▊         | 4989/61904 [2:27:25<21:44:48,  1.38s/it]
  8%|▊         | 4990/61904 [2:27:27<22:19:37,  1.41s/it]
  8%|▊         | 4991/61904 [2:27:28<22:09:40,  1.40s/it]
  8%|▊         | 4992/61904 [2:27:30<21:37:36,  1.37s/it]
  8%|▊         | 4993/61904 [2:27:31<22:25:12,  1.42s/it]
  8%|▊         | 4994/61904 [2:27:33<22:29:45,  1.42s/it]
  8%|▊         | 4995/61904 [2:27:34<21:35:18,  1.37s/it]
  8%|▊         | 4996/61904 [2:27:35<21:24:36,  1.35s/it]
  8%|▊         | 4997/61904 [2:27:37<21:45:39,  1.38s/it]
  8%|▊         | 4998/61904 [2:27:38<21:32:01,  1.36s/it]
  8%|▊         | 4999/61904 [2:27:39<21:11:15,  1.34s/it]
  8%|▊         | 5000/61904 [2:27:41<21:26:18,  1.36s/it]
                                                         
{'loss': 2.9824, 'learning_rate': 1.9222092570984053e-07, 'epoch': 1.29}

  8%|▊         | 5000/61904 [2:27:41<21:26:18,  1.36s/it]
  8%|▊         | 5001/61904 [2:27:42<21:36:10,  1.37s/it]
  8%|▊         | 5002/61904 [2:27:43<21:20:19,  1.35s/it]
  8%|▊         | 5003/61904 [2:27:45<21:16:36,  1.35s/it]
  8%|▊         | 5004/61904 [2:27:46<21:00:32,  1.33s/it]
  8%|▊         | 5005/61904 [2:27:47<20:58:06,  1.33s/it]
  8%|▊         | 5006/61904 [2:27:49<21:08:47,  1.34s/it]
  8%|▊         | 5007/61904 [2:27:50<21:22:52,  1.35s/it]
  8%|▊         | 5008/61904 [2:27:51<21:33:13,  1.36s/it]
  8%|▊         | 5009/61904 [2:27:53<21:04:34,  1.33s/it]
  8%|▊         | 5010/61904 [2:27:54<20:31:37,  1.30s/it]
  8%|▊         | 5011/61904 [2:27:55<21:05:14,  1.33s/it]
  8%|▊         | 5012/61904 [2:27:57<21:33:34,  1.36s/it]
  8%|▊         | 5013/61904 [2:27:58<20:58:01,  1.33s/it]
  8%|▊         | 5014/61904 [2:27:59<21:34:56,  1.37s/it]
  8%|▊         | 5015/61904 [2:28:01<21:51:29,  1.38s/it]
  8%|▊         | 5016/61904 [2:28:02<21:27:19,  1.36s/it]
  8%|▊         | 5017/61904 [2:28:03<20:44:08,  1.31s/it]
  8%|▊         | 5018/61904 [2:28:05<21:04:06,  1.33s/it]
  8%|▊         | 5019/61904 [2:28:06<21:10:04,  1.34s/it]
  8%|▊         | 5020/61904 [2:28:07<21:04:35,  1.33s/it]
                                                         
{'loss': 3.0607, 'learning_rate': 1.9218851290029817e-07, 'epoch': 1.3}

  8%|▊         | 5020/61904 [2:28:07<21:04:35,  1.33s/it]
  8%|▊         | 5021/61904 [2:28:09<20:44:46,  1.31s/it]
  8%|▊         | 5022/61904 [2:28:10<21:06:32,  1.34s/it]
  8%|▊         | 5023/61904 [2:28:11<21:07:57,  1.34s/it]
  8%|▊         | 5024/61904 [2:28:13<21:56:48,  1.39s/it]
  8%|▊         | 5025/61904 [2:28:14<22:21:56,  1.42s/it]
  8%|▊         | 5026/61904 [2:28:16<22:11:59,  1.41s/it]
  8%|▊         | 5027/61904 [2:28:17<22:07:14,  1.40s/it]
  8%|▊         | 5028/61904 [2:28:18<21:45:00,  1.38s/it]
  8%|▊         | 5029/61904 [2:28:20<21:35:56,  1.37s/it]
  8%|▊         | 5030/61904 [2:28:21<20:37:19,  1.31s/it]
  8%|▊         | 5031/61904 [2:28:22<21:07:45,  1.34s/it]
  8%|▊         | 5032/61904 [2:28:24<21:43:49,  1.38s/it]
  8%|▊         | 5033/61904 [2:28:25<21:41:46,  1.37s/it]
  8%|▊         | 5034/61904 [2:28:27<22:12:23,  1.41s/it]
  8%|▊         | 5035/61904 [2:28:28<21:51:31,  1.38s/it]
  8%|▊         | 5036/61904 [2:28:29<22:16:34,  1.41s/it]
  8%|▊         | 5037/61904 [2:28:31<22:33:57,  1.43s/it]
  8%|▊         | 5038/61904 [2:28:32<21:54:38,  1.39s/it]
  8%|▊         | 5039/61904 [2:28:34<21:20:31,  1.35s/it]
  8%|▊         | 5040/61904 [2:28:35<21:38:06,  1.37s/it]
                                                         
{'loss': 3.0266, 'learning_rate': 1.9215610009075586e-07, 'epoch': 1.3}

  8%|▊         | 5040/61904 [2:28:35<21:38:06,  1.37s/it]
  8%|▊         | 5041/61904 [2:28:36<21:56:01,  1.39s/it]
  8%|▊         | 5042/61904 [2:28:38<22:30:02,  1.42s/it]
  8%|▊         | 5043/61904 [2:28:39<22:09:01,  1.40s/it]
  8%|▊         | 5044/61904 [2:28:41<22:47:25,  1.44s/it]
  8%|▊         | 5045/61904 [2:28:42<22:46:43,  1.44s/it]
  8%|▊         | 5046/61904 [2:28:44<23:08:01,  1.46s/it]
  8%|▊         | 5047/61904 [2:28:45<22:16:08,  1.41s/it]
  8%|▊         | 5048/61904 [2:28:46<21:42:39,  1.37s/it]
  8%|▊         | 5049/61904 [2:28:48<21:39:08,  1.37s/it]
  8%|▊         | 5050/61904 [2:28:49<21:09:43,  1.34s/it]
  8%|▊         | 5051/61904 [2:28:51<23:13:56,  1.47s/it]
  8%|▊         | 5052/61904 [2:28:52<22:22:50,  1.42s/it]
  8%|▊         | 5053/61904 [2:28:53<21:56:49,  1.39s/it]
  8%|▊         | 5054/61904 [2:28:55<21:42:42,  1.37s/it]
  8%|▊         | 5055/61904 [2:28:56<21:37:03,  1.37s/it]
  8%|▊         | 5056/61904 [2:28:57<21:28:02,  1.36s/it]
  8%|▊         | 5057/61904 [2:28:59<21:42:09,  1.37s/it]
  8%|▊         | 5058/61904 [2:29:00<21:35:52,  1.37s/it]
  8%|▊         | 5059/61904 [2:29:02<22:10:27,  1.40s/it]
  8%|▊         | 5060/61904 [2:29:03<22:25:28,  1.42s/it]
                                                         
{'loss': 2.9212, 'learning_rate': 1.9212368728121355e-07, 'epoch': 1.31}

  8%|▊         | 5060/61904 [2:29:03<22:25:28,  1.42s/it]
  8%|▊         | 5061/61904 [2:29:04<21:54:47,  1.39s/it]
  8%|▊         | 5062/61904 [2:29:06<21:06:00,  1.34s/it]
  8%|▊         | 5063/61904 [2:29:07<20:43:57,  1.31s/it]
  8%|▊         | 5064/61904 [2:29:08<21:36:59,  1.37s/it]
  8%|▊         | 5065/61904 [2:29:10<22:51:36,  1.45s/it]
  8%|▊         | 5066/61904 [2:29:11<22:24:20,  1.42s/it]
  8%|▊         | 5067/61904 [2:29:13<21:55:31,  1.39s/it]
  8%|▊         | 5068/61904 [2:29:14<21:39:49,  1.37s/it]
  8%|▊         | 5069/61904 [2:29:15<21:08:58,  1.34s/it]
  8%|▊         | 5070/61904 [2:29:17<21:03:42,  1.33s/it]
  8%|▊         | 5071/61904 [2:29:18<22:27:50,  1.42s/it]
  8%|▊         | 5072/61904 [2:29:20<22:26:13,  1.42s/it]
  8%|▊         | 5073/61904 [2:29:21<21:40:06,  1.37s/it]
  8%|▊         | 5074/61904 [2:29:22<21:22:22,  1.35s/it]
  8%|▊         | 5075/61904 [2:29:24<21:41:36,  1.37s/it]
  8%|▊         | 5076/61904 [2:29:25<21:37:07,  1.37s/it]
  8%|▊         | 5077/61904 [2:29:26<21:29:45,  1.36s/it]
  8%|▊         | 5078/61904 [2:29:28<21:20:39,  1.35s/it]
  8%|▊         | 5079/61904 [2:29:29<21:27:45,  1.36s/it]
  8%|▊         | 5080/61904 [2:29:30<21:02:03,  1.33s/it]
                                                         
{'loss': 3.0226, 'learning_rate': 1.9209127447167118e-07, 'epoch': 1.31}

  8%|▊         | 5080/61904 [2:29:30<21:02:03,  1.33s/it]
  8%|▊         | 5081/61904 [2:29:32<20:44:02,  1.31s/it]
  8%|▊         | 5082/61904 [2:29:33<20:58:37,  1.33s/it]
  8%|▊         | 5083/61904 [2:29:34<21:27:19,  1.36s/it]
  8%|▊         | 5084/61904 [2:29:36<21:00:40,  1.33s/it]
  8%|▊         | 5085/61904 [2:29:37<21:00:43,  1.33s/it]
  8%|▊         | 5086/61904 [2:29:38<21:11:30,  1.34s/it]
  8%|▊         | 5087/61904 [2:29:40<21:19:32,  1.35s/it]
  8%|▊         | 5088/61904 [2:29:41<21:24:18,  1.36s/it]
  8%|▊         | 5089/61904 [2:29:42<20:58:17,  1.33s/it]
  8%|▊         | 5090/61904 [2:29:44<22:01:46,  1.40s/it]
  8%|▊         | 5091/61904 [2:29:45<22:06:58,  1.40s/it]
  8%|▊         | 5092/61904 [2:29:47<21:19:19,  1.35s/it]
  8%|▊         | 5093/61904 [2:29:48<22:05:00,  1.40s/it]
  8%|▊         | 5094/61904 [2:29:49<21:31:20,  1.36s/it]
  8%|▊         | 5095/61904 [2:29:51<21:10:15,  1.34s/it]
  8%|▊         | 5096/61904 [2:29:52<20:57:46,  1.33s/it]
  8%|▊         | 5097/61904 [2:29:53<20:32:25,  1.30s/it]
  8%|▊         | 5098/61904 [2:29:54<20:01:09,  1.27s/it]
  8%|▊         | 5099/61904 [2:29:56<21:07:34,  1.34s/it]
  8%|▊         | 5100/61904 [2:29:57<21:44:58,  1.38s/it]
                                                         
{'loss': 2.9282, 'learning_rate': 1.9205886166212887e-07, 'epoch': 1.32}

  8%|▊         | 5100/61904 [2:29:57<21:44:58,  1.38s/it]
  8%|▊         | 5101/61904 [2:29:59<21:48:33,  1.38s/it]
  8%|▊         | 5102/61904 [2:30:00<22:23:23,  1.42s/it]
  8%|▊         | 5103/61904 [2:30:02<22:55:53,  1.45s/it]
  8%|▊         | 5104/61904 [2:30:03<22:48:39,  1.45s/it]
  8%|▊         | 5105/61904 [2:30:05<23:12:57,  1.47s/it]
  8%|▊         | 5106/61904 [2:30:06<23:05:31,  1.46s/it]
  8%|▊         | 5107/61904 [2:30:07<22:22:06,  1.42s/it]
  8%|▊         | 5108/61904 [2:30:09<21:55:56,  1.39s/it]
  8%|▊         | 5109/61904 [2:30:10<21:02:47,  1.33s/it]
  8%|▊         | 5110/61904 [2:30:11<20:45:37,  1.32s/it]
  8%|▊         | 5111/61904 [2:30:12<20:12:52,  1.28s/it]
  8%|▊         | 5112/61904 [2:30:14<21:25:31,  1.36s/it]
  8%|▊         | 5113/61904 [2:30:15<21:12:39,  1.34s/it]
  8%|▊         | 5114/61904 [2:30:17<20:53:10,  1.32s/it]
  8%|▊         | 5115/61904 [2:30:18<20:59:45,  1.33s/it]
  8%|▊         | 5116/61904 [2:30:19<20:33:06,  1.30s/it]
  8%|▊         | 5117/61904 [2:30:20<20:20:30,  1.29s/it]
  8%|▊         | 5118/61904 [2:30:22<20:47:59,  1.32s/it]
  8%|▊         | 5119/61904 [2:30:23<20:24:00,  1.29s/it]
  8%|▊         | 5120/61904 [2:30:24<20:52:25,  1.32s/it]
                                                         
{'loss': 2.9725, 'learning_rate': 1.9202644885258653e-07, 'epoch': 1.32}

  8%|▊         | 5120/61904 [2:30:24<20:52:25,  1.32s/it]
  8%|▊         | 5121/61904 [2:30:26<20:39:22,  1.31s/it]
  8%|▊         | 5122/61904 [2:30:27<20:54:15,  1.33s/it]
  8%|▊         | 5123/61904 [2:30:28<20:32:24,  1.30s/it]
  8%|▊         | 5124/61904 [2:30:30<20:49:31,  1.32s/it]
  8%|▊         | 5125/61904 [2:30:31<21:31:20,  1.36s/it]
  8%|▊         | 5126/61904 [2:30:33<22:07:42,  1.40s/it]
  8%|▊         | 5127/61904 [2:30:34<21:50:42,  1.39s/it]
  8%|▊         | 5128/61904 [2:30:35<21:47:29,  1.38s/it]
  8%|▊         | 5129/61904 [2:30:37<21:12:00,  1.34s/it]
  8%|▊         | 5130/61904 [2:30:38<20:23:06,  1.29s/it]
  8%|▊         | 5131/61904 [2:30:39<20:32:47,  1.30s/it]
  8%|▊         | 5132/61904 [2:30:40<20:31:41,  1.30s/it]
  8%|▊         | 5133/61904 [2:30:42<20:46:08,  1.32s/it]
  8%|▊         | 5134/61904 [2:30:43<21:19:26,  1.35s/it]
  8%|▊         | 5135/61904 [2:30:45<22:01:05,  1.40s/it]
  8%|▊         | 5136/61904 [2:30:46<21:56:24,  1.39s/it]
  8%|▊         | 5137/61904 [2:30:48<22:11:10,  1.41s/it]
  8%|▊         | 5138/61904 [2:30:49<21:19:19,  1.35s/it]
  8%|▊         | 5139/61904 [2:30:50<21:21:20,  1.35s/it]
  8%|▊         | 5140/61904 [2:30:51<21:09:16,  1.34s/it]
                                                         
{'loss': 2.9777, 'learning_rate': 1.919940360430442e-07, 'epoch': 1.33}

  8%|▊         | 5140/61904 [2:30:51<21:09:16,  1.34s/it]
  8%|▊         | 5141/61904 [2:30:53<20:55:11,  1.33s/it]
  8%|▊         | 5142/61904 [2:30:54<21:36:05,  1.37s/it]
  8%|▊         | 5143/61904 [2:30:56<21:37:23,  1.37s/it]
  8%|▊         | 5144/61904 [2:30:57<21:49:29,  1.38s/it]
  8%|▊         | 5145/61904 [2:30:58<21:19:18,  1.35s/it]
  8%|▊         | 5146/61904 [2:31:00<21:15:48,  1.35s/it]
  8%|▊         | 5147/61904 [2:31:01<21:12:13,  1.34s/it]
  8%|▊         | 5148/61904 [2:31:02<21:09:10,  1.34s/it]
  8%|▊         | 5149/61904 [2:31:04<21:31:53,  1.37s/it]
  8%|▊         | 5150/61904 [2:31:05<22:01:45,  1.40s/it]
  8%|▊         | 5151/61904 [2:31:07<22:03:19,  1.40s/it]
  8%|▊         | 5152/61904 [2:31:08<21:30:05,  1.36s/it]
  8%|▊         | 5153/61904 [2:31:09<21:52:49,  1.39s/it]
  8%|▊         | 5154/61904 [2:31:11<21:57:27,  1.39s/it]
  8%|▊         | 5155/61904 [2:31:12<21:06:32,  1.34s/it]
  8%|▊         | 5156/61904 [2:31:13<20:59:00,  1.33s/it]
  8%|▊         | 5157/61904 [2:31:15<20:59:06,  1.33s/it]
  8%|▊         | 5158/61904 [2:31:16<21:52:57,  1.39s/it]
  8%|▊         | 5159/61904 [2:31:17<21:50:59,  1.39s/it]
  8%|▊         | 5160/61904 [2:31:19<21:31:24,  1.37s/it]
                                                         
{'loss': 2.9426, 'learning_rate': 1.9196162323350188e-07, 'epoch': 1.33}

  8%|▊         | 5160/61904 [2:31:19<21:31:24,  1.37s/it]
  8%|▊         | 5161/61904 [2:31:20<21:20:04,  1.35s/it]
  8%|▊         | 5162/61904 [2:31:21<20:50:23,  1.32s/it]
  8%|▊         | 5163/61904 [2:31:23<21:38:43,  1.37s/it]
  8%|▊         | 5164/61904 [2:31:24<21:49:37,  1.38s/it]
  8%|▊         | 5165/61904 [2:31:26<21:29:05,  1.36s/it]
  8%|▊         | 5166/61904 [2:31:27<22:06:14,  1.40s/it]
  8%|▊         | 5167/61904 [2:31:28<21:38:12,  1.37s/it]
  8%|▊         | 5168/61904 [2:31:30<21:18:57,  1.35s/it]
  8%|▊         | 5169/61904 [2:31:31<20:46:26,  1.32s/it]
  8%|▊         | 5170/61904 [2:31:32<20:30:15,  1.30s/it]
  8%|▊         | 5171/61904 [2:31:33<20:39:36,  1.31s/it]
  8%|▊         | 5172/61904 [2:31:35<20:32:05,  1.30s/it]
  8%|▊         | 5173/61904 [2:31:36<20:38:59,  1.31s/it]
  8%|▊         | 5174/61904 [2:31:38<21:11:05,  1.34s/it]
  8%|▊         | 5175/61904 [2:31:39<20:58:28,  1.33s/it]
  8%|▊         | 5176/61904 [2:31:40<21:35:49,  1.37s/it]
  8%|▊         | 5177/61904 [2:31:42<21:33:55,  1.37s/it]
  8%|▊         | 5178/61904 [2:31:43<21:47:24,  1.38s/it]
  8%|▊         | 5179/61904 [2:31:44<21:53:52,  1.39s/it]
  8%|▊         | 5180/61904 [2:31:46<22:53:38,  1.45s/it]
                                                         
{'loss': 2.9584, 'learning_rate': 1.9192921042395954e-07, 'epoch': 1.34}

  8%|▊         | 5180/61904 [2:31:46<22:53:38,  1.45s/it]
  8%|▊         | 5181/61904 [2:31:47<22:11:58,  1.41s/it]
  8%|▊         | 5182/61904 [2:31:49<21:29:39,  1.36s/it]
  8%|▊         | 5183/61904 [2:31:50<21:39:14,  1.37s/it]
  8%|▊         | 5184/61904 [2:31:51<21:51:19,  1.39s/it]
  8%|▊         | 5185/61904 [2:31:53<21:14:16,  1.35s/it]
  8%|▊         | 5186/61904 [2:31:54<22:09:46,  1.41s/it]
  8%|▊         | 5187/61904 [2:31:56<21:47:25,  1.38s/it]
  8%|▊         | 5188/61904 [2:31:57<22:22:38,  1.42s/it]
  8%|▊         | 5189/61904 [2:31:58<21:43:12,  1.38s/it]
  8%|▊         | 5190/61904 [2:32:00<21:22:23,  1.36s/it]
  8%|▊         | 5191/61904 [2:32:01<21:23:27,  1.36s/it]
  8%|▊         | 5192/61904 [2:32:02<21:10:30,  1.34s/it]
  8%|▊         | 5193/61904 [2:32:04<21:16:53,  1.35s/it]
  8%|▊         | 5194/61904 [2:32:05<21:54:07,  1.39s/it]
  8%|▊         | 5195/61904 [2:32:07<21:53:19,  1.39s/it]
  8%|▊         | 5196/61904 [2:32:08<21:39:40,  1.38s/it]
  8%|▊         | 5197/61904 [2:32:09<21:28:01,  1.36s/it]
  8%|▊         | 5198/61904 [2:32:11<21:38:24,  1.37s/it]
  8%|▊         | 5199/61904 [2:32:12<21:54:22,  1.39s/it]
  8%|▊         | 5200/61904 [2:32:14<22:17:52,  1.42s/it]
                                                         
{'loss': 2.9244, 'learning_rate': 1.918967976144172e-07, 'epoch': 1.34}

  8%|▊         | 5200/61904 [2:32:14<22:17:52,  1.42s/it]
  8%|▊         | 5201/61904 [2:32:15<21:36:50,  1.37s/it]
  8%|▊         | 5202/61904 [2:32:16<21:08:41,  1.34s/it]
  8%|▊         | 5203/61904 [2:32:18<22:16:41,  1.41s/it]
  8%|▊         | 5204/61904 [2:32:19<21:48:31,  1.38s/it]
  8%|▊         | 5205/61904 [2:32:20<21:12:46,  1.35s/it]
  8%|▊         | 5206/61904 [2:32:22<20:51:30,  1.32s/it]
  8%|▊         | 5207/61904 [2:32:23<20:42:15,  1.31s/it]
  8%|▊         | 5208/61904 [2:32:24<21:03:59,  1.34s/it]
  8%|▊         | 5209/61904 [2:32:26<21:12:57,  1.35s/it]
  8%|▊         | 5210/61904 [2:32:27<21:33:38,  1.37s/it]
  8%|▊         | 5211/61904 [2:32:28<21:22:56,  1.36s/it]
  8%|▊         | 5212/61904 [2:32:30<21:26:37,  1.36s/it]
  8%|▊         | 5213/61904 [2:32:31<21:13:52,  1.35s/it]
  8%|▊         | 5214/61904 [2:32:32<20:41:25,  1.31s/it]
  8%|▊         | 5215/61904 [2:32:34<20:43:17,  1.32s/it]
  8%|▊         | 5216/61904 [2:32:35<20:57:29,  1.33s/it]
  8%|▊         | 5217/61904 [2:32:36<21:31:28,  1.37s/it]
  8%|▊         | 5218/61904 [2:32:38<21:26:18,  1.36s/it]
  8%|▊         | 5219/61904 [2:32:39<21:56:27,  1.39s/it]
  8%|▊         | 5220/61904 [2:32:41<21:33:57,  1.37s/it]
                                                         
{'loss': 3.0344, 'learning_rate': 1.918643848048749e-07, 'epoch': 1.35}

  8%|▊         | 5220/61904 [2:32:41<21:33:57,  1.37s/it]
  8%|▊         | 5221/61904 [2:32:42<20:56:44,  1.33s/it]
  8%|▊         | 5222/61904 [2:32:43<21:32:33,  1.37s/it]
  8%|▊         | 5223/61904 [2:32:45<21:50:40,  1.39s/it]
  8%|▊         | 5224/61904 [2:32:46<22:36:54,  1.44s/it]
  8%|▊         | 5225/61904 [2:32:48<22:38:42,  1.44s/it]
  8%|▊         | 5226/61904 [2:32:49<22:04:33,  1.40s/it]
  8%|▊         | 5227/61904 [2:32:50<21:21:26,  1.36s/it]
  8%|▊         | 5228/61904 [2:32:52<21:17:09,  1.35s/it]
  8%|▊         | 5229/61904 [2:32:53<21:04:14,  1.34s/it]
  8%|▊         | 5230/61904 [2:32:54<21:07:13,  1.34s/it]
  8%|▊         | 5231/61904 [2:32:56<21:28:45,  1.36s/it]
  8%|▊         | 5232/61904 [2:32:57<22:13:41,  1.41s/it]
  8%|▊         | 5233/61904 [2:32:59<22:29:31,  1.43s/it]
  8%|▊         | 5234/61904 [2:33:00<22:48:40,  1.45s/it]
  8%|▊         | 5235/61904 [2:33:02<22:32:18,  1.43s/it]
  8%|▊         | 5236/61904 [2:33:03<21:47:42,  1.38s/it]
  8%|▊         | 5237/61904 [2:33:04<21:51:10,  1.39s/it]
  8%|▊         | 5238/61904 [2:33:06<22:03:47,  1.40s/it]
  8%|▊         | 5239/61904 [2:33:07<22:52:37,  1.45s/it]
  8%|▊         | 5240/61904 [2:33:08<21:41:49,  1.38s/it]
                                                         
{'loss': 2.9877, 'learning_rate': 1.9183197199533253e-07, 'epoch': 1.35}

  8%|▊         | 5240/61904 [2:33:08<21:41:49,  1.38s/it]
  8%|▊         | 5241/61904 [2:33:10<22:36:10,  1.44s/it]
  8%|▊         | 5242/61904 [2:33:11<22:08:03,  1.41s/it]
  8%|▊         | 5243/61904 [2:33:13<22:06:04,  1.40s/it]
  8%|▊         | 5244/61904 [2:33:14<22:10:41,  1.41s/it]
  8%|▊         | 5245/61904 [2:33:15<21:38:51,  1.38s/it]
  8%|▊         | 5246/61904 [2:33:17<22:26:07,  1.43s/it]
  8%|▊         | 5247/61904 [2:33:18<21:48:09,  1.39s/it]
  8%|▊         | 5248/61904 [2:33:20<21:10:39,  1.35s/it]
  8%|▊         | 5249/61904 [2:33:21<21:27:58,  1.36s/it]
  8%|▊         | 5250/61904 [2:33:22<21:36:28,  1.37s/it]
  8%|▊         | 5251/61904 [2:33:24<21:05:20,  1.34s/it]
  8%|▊         | 5252/61904 [2:33:25<20:43:45,  1.32s/it]
  8%|▊         | 5253/61904 [2:33:26<21:22:01,  1.36s/it]
  8%|▊         | 5254/61904 [2:33:28<20:54:43,  1.33s/it]
  8%|▊         | 5255/61904 [2:33:29<20:46:49,  1.32s/it]
  8%|▊         | 5256/61904 [2:33:30<21:07:40,  1.34s/it]
  8%|▊         | 5257/61904 [2:33:31<20:39:32,  1.31s/it]
  8%|▊         | 5258/61904 [2:33:33<21:16:21,  1.35s/it]
  8%|▊         | 5259/61904 [2:33:34<21:08:42,  1.34s/it]
  8%|▊         | 5260/61904 [2:33:36<20:43:16,  1.32s/it]
                                                         
{'loss': 2.9763, 'learning_rate': 1.9179955918579022e-07, 'epoch': 1.36}

  8%|▊         | 5260/61904 [2:33:36<20:43:16,  1.32s/it]
  8%|▊         | 5261/61904 [2:33:37<20:24:27,  1.30s/it]
  9%|▊         | 5262/61904 [2:33:38<20:46:21,  1.32s/it]
  9%|▊         | 5263/61904 [2:33:39<20:30:55,  1.30s/it]
  9%|▊         | 5264/61904 [2:33:41<21:44:41,  1.38s/it]
  9%|▊         | 5265/61904 [2:33:42<21:11:47,  1.35s/it]
  9%|▊         | 5266/61904 [2:33:44<22:09:38,  1.41s/it]
  9%|▊         | 5267/61904 [2:33:45<21:24:59,  1.36s/it]
  9%|▊         | 5268/61904 [2:33:46<21:14:56,  1.35s/it]
  9%|▊         | 5269/61904 [2:33:48<20:37:12,  1.31s/it]
  9%|▊         | 5270/61904 [2:33:49<20:49:21,  1.32s/it]
  9%|▊         | 5271/61904 [2:33:50<21:00:55,  1.34s/it]
  9%|▊         | 5272/61904 [2:33:52<20:51:03,  1.33s/it]
  9%|▊         | 5273/61904 [2:33:53<23:20:13,  1.48s/it]
  9%|▊         | 5274/61904 [2:33:55<23:44:27,  1.51s/it]
  9%|▊         | 5275/61904 [2:33:56<22:51:18,  1.45s/it]
  9%|▊         | 5276/61904 [2:33:58<22:09:13,  1.41s/it]
  9%|▊         | 5277/61904 [2:33:59<21:16:14,  1.35s/it]
  9%|▊         | 5278/61904 [2:34:00<20:47:06,  1.32s/it]
  9%|▊         | 5279/61904 [2:34:01<20:45:50,  1.32s/it]
  9%|▊         | 5280/61904 [2:34:03<21:12:44,  1.35s/it]
                                                         
{'loss': 2.9684, 'learning_rate': 1.917671463762479e-07, 'epoch': 1.36}

  9%|▊         | 5280/61904 [2:34:03<21:12:44,  1.35s/it]
  9%|▊         | 5281/61904 [2:34:04<21:30:45,  1.37s/it]
  9%|▊         | 5282/61904 [2:34:06<21:29:07,  1.37s/it]
  9%|▊         | 5283/61904 [2:34:07<21:20:55,  1.36s/it]
  9%|▊         | 5284/61904 [2:34:08<21:08:04,  1.34s/it]
  9%|▊         | 5285/61904 [2:34:10<21:00:45,  1.34s/it]
  9%|▊         | 5286/61904 [2:34:11<20:50:59,  1.33s/it]
  9%|▊         | 5287/61904 [2:34:12<21:31:40,  1.37s/it]
  9%|▊         | 5288/61904 [2:34:14<21:22:40,  1.36s/it]
  9%|▊         | 5289/61904 [2:34:15<22:41:00,  1.44s/it]
  9%|▊         | 5290/61904 [2:34:17<22:00:31,  1.40s/it]
  9%|▊         | 5291/61904 [2:34:18<21:19:57,  1.36s/it]
  9%|▊         | 5292/61904 [2:34:19<21:33:30,  1.37s/it]
  9%|▊         | 5293/61904 [2:34:21<20:53:57,  1.33s/it]
  9%|▊         | 5294/61904 [2:34:22<20:33:32,  1.31s/it]
  9%|▊         | 5295/61904 [2:34:23<20:51:15,  1.33s/it]
  9%|▊         | 5296/61904 [2:34:24<20:44:00,  1.32s/it]
  9%|▊         | 5297/61904 [2:34:26<20:59:12,  1.33s/it]
  9%|▊         | 5298/61904 [2:34:27<21:25:42,  1.36s/it]
  9%|▊         | 5299/61904 [2:34:29<21:39:17,  1.38s/it]
  9%|▊         | 5300/61904 [2:34:30<21:54:20,  1.39s/it]
                                                         
{'loss': 3.0331, 'learning_rate': 1.9173473356670554e-07, 'epoch': 1.37}

  9%|▊         | 5300/61904 [2:34:30<21:54:20,  1.39s/it]
  9%|▊         | 5301/61904 [2:34:31<21:49:14,  1.39s/it]
  9%|▊         | 5302/61904 [2:34:33<21:43:36,  1.38s/it]
  9%|▊         | 5303/61904 [2:34:34<21:32:50,  1.37s/it]
  9%|▊         | 5304/61904 [2:34:35<20:53:59,  1.33s/it]
  9%|▊         | 5305/61904 [2:34:37<20:54:52,  1.33s/it]
  9%|▊         | 5306/61904 [2:34:38<21:06:16,  1.34s/it]
  9%|▊         | 5307/61904 [2:34:40<21:33:52,  1.37s/it]
  9%|▊         | 5308/61904 [2:34:41<21:32:50,  1.37s/it]
  9%|▊         | 5309/61904 [2:34:42<21:36:49,  1.37s/it]
  9%|▊         | 5310/61904 [2:34:44<21:26:52,  1.36s/it]
  9%|▊         | 5311/61904 [2:34:45<21:20:02,  1.36s/it]
  9%|▊         | 5312/61904 [2:34:46<21:47:48,  1.39s/it]
  9%|▊         | 5313/61904 [2:34:48<21:06:37,  1.34s/it]
  9%|▊         | 5314/61904 [2:34:49<20:52:38,  1.33s/it]
  9%|▊         | 5315/61904 [2:34:50<20:44:29,  1.32s/it]
  9%|▊         | 5316/61904 [2:34:52<20:20:27,  1.29s/it]
  9%|▊         | 5317/61904 [2:34:53<20:24:47,  1.30s/it]
  9%|▊         | 5318/61904 [2:34:54<20:18:04,  1.29s/it]
  9%|▊         | 5319/61904 [2:34:56<20:58:25,  1.33s/it]
  9%|▊         | 5320/61904 [2:34:57<20:27:25,  1.30s/it]
                                                         
{'loss': 3.0052, 'learning_rate': 1.9170232075716323e-07, 'epoch': 1.37}

  9%|▊         | 5320/61904 [2:34:57<20:27:25,  1.30s/it]
  9%|▊         | 5321/61904 [2:34:58<20:10:17,  1.28s/it]
  9%|▊         | 5322/61904 [2:34:59<20:15:13,  1.29s/it]
  9%|▊         | 5323/61904 [2:35:01<20:08:47,  1.28s/it]
  9%|▊         | 5324/61904 [2:35:02<20:05:44,  1.28s/it]
  9%|▊         | 5325/61904 [2:35:03<20:20:07,  1.29s/it]
  9%|▊         | 5326/61904 [2:35:04<20:27:40,  1.30s/it]
  9%|▊         | 5327/61904 [2:35:06<20:44:51,  1.32s/it]
  9%|▊         | 5328/61904 [2:35:07<20:46:35,  1.32s/it]
  9%|▊         | 5329/61904 [2:35:09<21:17:40,  1.36s/it]
  9%|▊         | 5330/61904 [2:35:10<21:16:01,  1.35s/it]
  9%|▊         | 5331/61904 [2:35:11<21:36:56,  1.38s/it]
  9%|▊         | 5332/61904 [2:35:13<21:02:44,  1.34s/it]
  9%|▊         | 5333/61904 [2:35:14<21:37:16,  1.38s/it]
  9%|▊         | 5334/61904 [2:35:15<21:21:26,  1.36s/it]
  9%|▊         | 5335/61904 [2:35:17<21:04:45,  1.34s/it]
  9%|▊         | 5336/61904 [2:35:18<21:49:11,  1.39s/it]
  9%|▊         | 5337/61904 [2:35:20<21:51:21,  1.39s/it]
  9%|▊         | 5338/61904 [2:35:21<21:37:57,  1.38s/it]
  9%|▊         | 5339/61904 [2:35:22<21:49:52,  1.39s/it]
  9%|▊         | 5340/61904 [2:35:24<22:29:59,  1.43s/it]
                                                         
{'loss': 2.9511, 'learning_rate': 1.916699079476209e-07, 'epoch': 1.38}

  9%|▊         | 5340/61904 [2:35:24<22:29:59,  1.43s/it]
  9%|▊         | 5341/61904 [2:35:25<22:34:58,  1.44s/it]
  9%|▊         | 5342/61904 [2:35:27<22:43:17,  1.45s/it]
  9%|▊         | 5343/61904 [2:35:28<22:24:40,  1.43s/it]
  9%|▊         | 5344/61904 [2:35:29<21:26:50,  1.37s/it]
  9%|▊         | 5345/61904 [2:35:31<21:36:40,  1.38s/it]
  9%|▊         | 5346/61904 [2:35:32<20:53:47,  1.33s/it]
  9%|▊         | 5347/61904 [2:35:33<20:55:23,  1.33s/it]
  9%|▊         | 5348/61904 [2:35:35<21:36:47,  1.38s/it]
  9%|▊         | 5349/61904 [2:35:36<21:44:27,  1.38s/it]
  9%|▊         | 5350/61904 [2:35:38<21:38:19,  1.38s/it]
  9%|▊         | 5351/61904 [2:35:39<21:38:03,  1.38s/it]
  9%|▊         | 5352/61904 [2:35:40<21:59:28,  1.40s/it]
  9%|▊         | 5353/61904 [2:35:42<21:08:21,  1.35s/it]
  9%|▊         | 5354/61904 [2:35:43<21:09:27,  1.35s/it]
  9%|▊         | 5355/61904 [2:35:44<21:33:45,  1.37s/it]
  9%|▊         | 5356/61904 [2:35:46<22:15:06,  1.42s/it]
  9%|▊         | 5357/61904 [2:35:47<21:46:18,  1.39s/it]
  9%|▊         | 5358/61904 [2:35:49<21:25:59,  1.36s/it]
  9%|▊         | 5359/61904 [2:35:50<21:19:48,  1.36s/it]
  9%|▊         | 5360/61904 [2:35:51<20:56:21,  1.33s/it]
                                                         
{'loss': 2.9444, 'learning_rate': 1.9163749513807855e-07, 'epoch': 1.39}

  9%|▊         | 5360/61904 [2:35:51<20:56:21,  1.33s/it]
  9%|▊         | 5361/61904 [2:35:53<21:02:56,  1.34s/it]
  9%|▊         | 5362/61904 [2:35:54<21:09:26,  1.35s/it]
  9%|▊         | 5363/61904 [2:35:56<22:29:11,  1.43s/it]
  9%|▊         | 5364/61904 [2:35:57<22:27:36,  1.43s/it]
  9%|▊         | 5365/61904 [2:35:58<21:41:11,  1.38s/it]
  9%|▊         | 5366/61904 [2:36:00<21:31:51,  1.37s/it]
  9%|▊         | 5367/61904 [2:36:01<21:08:48,  1.35s/it]
  9%|▊         | 5368/61904 [2:36:02<20:52:57,  1.33s/it]
  9%|▊         | 5369/61904 [2:36:04<21:06:29,  1.34s/it]
  9%|▊         | 5370/61904 [2:36:05<21:06:16,  1.34s/it]
  9%|▊         | 5371/61904 [2:36:06<21:02:53,  1.34s/it]
  9%|▊         | 5372/61904 [2:36:08<20:42:44,  1.32s/it]
  9%|▊         | 5373/61904 [2:36:09<20:46:24,  1.32s/it]
  9%|▊         | 5374/61904 [2:36:10<21:22:03,  1.36s/it]
  9%|▊         | 5375/61904 [2:36:12<21:00:27,  1.34s/it]
  9%|▊         | 5376/61904 [2:36:13<21:33:54,  1.37s/it]
  9%|▊         | 5377/61904 [2:36:14<21:39:29,  1.38s/it]
  9%|▊         | 5378/61904 [2:36:16<21:36:45,  1.38s/it]
  9%|▊         | 5379/61904 [2:36:17<20:57:48,  1.34s/it]
  9%|▊         | 5380/61904 [2:36:18<21:16:52,  1.36s/it]
                                                         
{'loss': 2.9757, 'learning_rate': 1.9160508232853624e-07, 'epoch': 1.39}

  9%|▊         | 5380/61904 [2:36:18<21:16:52,  1.36s/it]
  9%|▊         | 5381/61904 [2:36:20<21:25:32,  1.36s/it]
  9%|▊         | 5382/61904 [2:36:21<21:38:45,  1.38s/it]
  9%|▊         | 5383/61904 [2:36:22<20:47:35,  1.32s/it]
  9%|▊         | 5384/61904 [2:36:24<20:34:35,  1.31s/it]
  9%|▊         | 5385/61904 [2:36:25<21:09:58,  1.35s/it]
  9%|▊         | 5386/61904 [2:36:26<20:38:07,  1.31s/it]
  9%|▊         | 5387/61904 [2:36:28<20:13:13,  1.29s/it]
  9%|▊         | 5388/61904 [2:36:29<20:29:08,  1.30s/it]
  9%|▊         | 5389/61904 [2:36:30<21:04:01,  1.34s/it]
  9%|▊         | 5390/61904 [2:36:32<21:58:36,  1.40s/it]
  9%|▊         | 5391/61904 [2:36:33<21:24:50,  1.36s/it]
  9%|▊         | 5392/61904 [2:36:35<21:53:18,  1.39s/it]
  9%|▊         | 5393/61904 [2:36:36<22:27:05,  1.43s/it]
  9%|▊         | 5394/61904 [2:36:37<21:17:19,  1.36s/it]
  9%|▊         | 5395/61904 [2:36:39<20:47:06,  1.32s/it]
  9%|▊         | 5396/61904 [2:36:40<21:01:02,  1.34s/it]
  9%|▊         | 5397/61904 [2:36:41<20:21:18,  1.30s/it]
  9%|▊         | 5398/61904 [2:36:42<20:22:41,  1.30s/it]
  9%|▊         | 5399/61904 [2:36:44<20:54:24,  1.33s/it]
  9%|▊         | 5400/61904 [2:36:45<20:57:44,  1.34s/it]
                                                         
{'loss': 3.0247, 'learning_rate': 1.915726695189939e-07, 'epoch': 1.4}

  9%|▊         | 5400/61904 [2:36:45<20:57:44,  1.34s/it]
  9%|▊         | 5401/61904 [2:36:47<21:07:10,  1.35s/it]
  9%|▊         | 5402/61904 [2:36:48<20:57:27,  1.34s/it]
  9%|▊         | 5403/61904 [2:36:49<21:41:05,  1.38s/it]
  9%|▊         | 5404/61904 [2:36:51<21:04:22,  1.34s/it]
  9%|▊         | 5405/61904 [2:36:52<20:30:50,  1.31s/it]
  9%|▊         | 5406/61904 [2:36:53<20:40:32,  1.32s/it]
  9%|▊         | 5407/61904 [2:36:55<21:09:22,  1.35s/it]
  9%|▊         | 5408/61904 [2:36:56<21:43:29,  1.38s/it]
  9%|▊         | 5409/61904 [2:36:57<21:36:20,  1.38s/it]
  9%|▊         | 5410/61904 [2:36:59<21:36:56,  1.38s/it]
  9%|▊         | 5411/61904 [2:37:00<21:13:25,  1.35s/it]
  9%|▊         | 5412/61904 [2:37:01<21:06:56,  1.35s/it]
  9%|▊         | 5413/61904 [2:37:03<20:49:16,  1.33s/it]
  9%|▊         | 5414/61904 [2:37:04<21:26:44,  1.37s/it]
  9%|▊         | 5415/61904 [2:37:05<20:50:13,  1.33s/it]
  9%|▊         | 5416/61904 [2:37:07<22:46:48,  1.45s/it]
  9%|▉         | 5417/61904 [2:37:09<22:19:06,  1.42s/it]
  9%|▉         | 5418/61904 [2:37:10<21:45:29,  1.39s/it]
  9%|▉         | 5419/61904 [2:37:11<21:34:15,  1.37s/it]
  9%|▉         | 5420/61904 [2:37:13<21:49:52,  1.39s/it]
                                                         
{'loss': 3.0173, 'learning_rate': 1.9154025670945156e-07, 'epoch': 1.4}

  9%|▉         | 5420/61904 [2:37:13<21:49:52,  1.39s/it]
  9%|▉         | 5421/61904 [2:37:14<22:10:06,  1.41s/it]
  9%|▉         | 5422/61904 [2:37:15<21:46:15,  1.39s/it]
  9%|▉         | 5423/61904 [2:37:17<21:44:27,  1.39s/it]
  9%|▉         | 5424/61904 [2:37:18<21:33:06,  1.37s/it]
  9%|▉         | 5425/61904 [2:37:20<22:14:55,  1.42s/it]
  9%|▉         | 5426/61904 [2:37:21<22:19:41,  1.42s/it]
  9%|▉         | 5427/61904 [2:37:23<22:46:34,  1.45s/it]
  9%|▉         | 5428/61904 [2:37:24<23:16:30,  1.48s/it]
  9%|▉         | 5429/61904 [2:37:26<23:05:23,  1.47s/it]
  9%|▉         | 5430/61904 [2:37:27<22:37:02,  1.44s/it]
  9%|▉         | 5431/61904 [2:37:28<22:26:08,  1.43s/it]
  9%|▉         | 5432/61904 [2:37:30<22:45:25,  1.45s/it]
  9%|▉         | 5433/61904 [2:37:31<22:01:38,  1.40s/it]
  9%|▉         | 5434/61904 [2:37:33<21:47:19,  1.39s/it]
  9%|▉         | 5435/61904 [2:37:34<21:29:25,  1.37s/it]
  9%|▉         | 5436/61904 [2:37:35<21:00:36,  1.34s/it]
  9%|▉         | 5437/61904 [2:37:36<20:54:47,  1.33s/it]
  9%|▉         | 5438/61904 [2:37:38<21:21:12,  1.36s/it]
  9%|▉         | 5439/61904 [2:37:39<21:16:13,  1.36s/it]
  9%|▉         | 5440/61904 [2:37:41<21:31:29,  1.37s/it]
                                                         
{'loss': 2.9848, 'learning_rate': 1.9150784389990925e-07, 'epoch': 1.41}

  9%|▉         | 5440/61904 [2:37:41<21:31:29,  1.37s/it]
  9%|▉         | 5441/61904 [2:37:42<21:00:14,  1.34s/it]
  9%|▉         | 5442/61904 [2:37:43<21:12:06,  1.35s/it]
  9%|▉         | 5443/61904 [2:37:45<20:44:45,  1.32s/it]
  9%|▉         | 5444/61904 [2:37:46<20:53:07,  1.33s/it]
  9%|▉         | 5445/61904 [2:37:47<20:54:21,  1.33s/it]
  9%|▉         | 5446/61904 [2:37:49<21:00:50,  1.34s/it]
  9%|▉         | 5447/61904 [2:37:50<21:12:11,  1.35s/it]
  9%|▉         | 5448/61904 [2:37:51<21:31:45,  1.37s/it]
  9%|▉         | 5449/61904 [2:37:53<21:39:37,  1.38s/it]
  9%|▉         | 5450/61904 [2:37:54<21:25:40,  1.37s/it]
  9%|▉         | 5451/61904 [2:37:56<21:52:11,  1.39s/it]
  9%|▉         | 5452/61904 [2:37:57<21:42:33,  1.38s/it]
  9%|▉         | 5453/61904 [2:37:59<23:23:23,  1.49s/it]
  9%|▉         | 5454/61904 [2:38:00<22:25:02,  1.43s/it]
  9%|▉         | 5455/61904 [2:38:01<22:11:28,  1.42s/it]
  9%|▉         | 5456/61904 [2:38:03<22:50:04,  1.46s/it]
  9%|▉         | 5457/61904 [2:38:04<21:44:28,  1.39s/it]
  9%|▉         | 5458/61904 [2:38:06<21:59:32,  1.40s/it]
  9%|▉         | 5459/61904 [2:38:07<22:16:20,  1.42s/it]
  9%|▉         | 5460/61904 [2:38:08<21:29:17,  1.37s/it]
                                                         
{'loss': 2.9544, 'learning_rate': 1.914754310903669e-07, 'epoch': 1.41}

  9%|▉         | 5460/61904 [2:38:08<21:29:17,  1.37s/it]
  9%|▉         | 5461/61904 [2:38:10<21:24:49,  1.37s/it]
  9%|▉         | 5462/61904 [2:38:11<21:52:50,  1.40s/it]
  9%|▉         | 5463/61904 [2:38:12<21:37:34,  1.38s/it]
  9%|▉         | 5464/61904 [2:38:14<21:06:45,  1.35s/it]
  9%|▉         | 5465/61904 [2:38:15<20:38:43,  1.32s/it]
  9%|▉         | 5466/61904 [2:38:16<21:17:34,  1.36s/it]
  9%|▉         | 5467/61904 [2:38:18<20:53:28,  1.33s/it]
  9%|▉         | 5468/61904 [2:38:19<20:37:37,  1.32s/it]
  9%|▉         | 5469/61904 [2:38:20<20:32:32,  1.31s/it]
  9%|▉         | 5470/61904 [2:38:22<21:50:07,  1.39s/it]
  9%|▉         | 5471/61904 [2:38:23<21:18:29,  1.36s/it]
  9%|▉         | 5472/61904 [2:38:24<20:54:36,  1.33s/it]
  9%|▉         | 5473/61904 [2:38:26<21:02:25,  1.34s/it]
  9%|▉         | 5474/61904 [2:38:27<20:19:28,  1.30s/it]
  9%|▉         | 5475/61904 [2:38:28<20:45:59,  1.32s/it]
  9%|▉         | 5476/61904 [2:38:30<20:23:44,  1.30s/it]
  9%|▉         | 5477/61904 [2:38:31<20:55:08,  1.33s/it]
  9%|▉         | 5478/61904 [2:38:32<21:25:22,  1.37s/it]
  9%|▉         | 5479/61904 [2:38:34<21:04:20,  1.34s/it]
  9%|▉         | 5480/61904 [2:38:35<21:03:05,  1.34s/it]
                                                         
{'loss': 2.9586, 'learning_rate': 1.9144301828082458e-07, 'epoch': 1.42}

  9%|▉         | 5480/61904 [2:38:35<21:03:05,  1.34s/it]
  9%|▉         | 5481/61904 [2:38:37<21:23:41,  1.37s/it]
  9%|▉         | 5482/61904 [2:38:38<20:58:08,  1.34s/it]
  9%|▉         | 5483/61904 [2:38:39<21:18:59,  1.36s/it]
  9%|▉         | 5484/61904 [2:38:41<21:46:55,  1.39s/it]
  9%|▉         | 5485/61904 [2:38:42<21:31:30,  1.37s/it]
  9%|▉         | 5486/61904 [2:38:43<21:32:43,  1.37s/it]
  9%|▉         | 5487/61904 [2:38:45<21:09:54,  1.35s/it]
  9%|▉         | 5488/61904 [2:38:46<20:47:30,  1.33s/it]
  9%|▉         | 5489/61904 [2:38:47<21:04:59,  1.35s/it]
  9%|▉         | 5490/61904 [2:38:49<20:58:18,  1.34s/it]
  9%|▉         | 5491/61904 [2:38:50<20:50:39,  1.33s/it]
  9%|▉         | 5492/61904 [2:38:51<20:43:43,  1.32s/it]
  9%|▉         | 5493/61904 [2:38:53<21:19:33,  1.36s/it]
  9%|▉         | 5494/61904 [2:38:54<20:52:23,  1.33s/it]
  9%|▉         | 5495/61904 [2:38:55<20:27:56,  1.31s/it]
  9%|▉         | 5496/61904 [2:38:57<20:28:25,  1.31s/it]
  9%|▉         | 5497/61904 [2:38:58<21:21:44,  1.36s/it]
  9%|▉         | 5498/61904 [2:38:59<21:43:37,  1.39s/it]
  9%|▉         | 5499/61904 [2:39:01<21:39:20,  1.38s/it]
  9%|▉         | 5500/61904 [2:39:02<21:26:42,  1.37s/it]
                                                         
{'loss': 2.9663, 'learning_rate': 1.9141060547128224e-07, 'epoch': 1.42}

  9%|▉         | 5500/61904 [2:39:02<21:26:42,  1.37s/it]
  9%|▉         | 5501/61904 [2:39:04<21:25:17,  1.37s/it]
  9%|▉         | 5502/61904 [2:39:05<21:20:08,  1.36s/it]
  9%|▉         | 5503/61904 [2:39:06<21:28:06,  1.37s/it]
  9%|▉         | 5504/61904 [2:39:08<21:05:10,  1.35s/it]
  9%|▉         | 5505/61904 [2:39:09<20:57:46,  1.34s/it]
  9%|▉         | 5506/61904 [2:39:10<22:06:12,  1.41s/it]
  9%|▉         | 5507/61904 [2:39:12<22:03:06,  1.41s/it]
  9%|▉         | 5508/61904 [2:39:13<22:12:51,  1.42s/it]
  9%|▉         | 5509/61904 [2:39:15<22:23:49,  1.43s/it]
  9%|▉         | 5510/61904 [2:39:16<22:19:43,  1.43s/it]
  9%|▉         | 5511/61904 [2:39:18<21:50:48,  1.39s/it]
  9%|▉         | 5512/61904 [2:39:19<22:59:25,  1.47s/it]
  9%|▉         | 5513/61904 [2:39:21<22:51:37,  1.46s/it]
  9%|▉         | 5514/61904 [2:39:22<23:13:49,  1.48s/it]
  9%|▉         | 5515/61904 [2:39:23<22:41:33,  1.45s/it]
  9%|▉         | 5516/61904 [2:39:25<22:12:11,  1.42s/it]
  9%|▉         | 5517/61904 [2:39:26<22:11:16,  1.42s/it]
  9%|▉         | 5518/61904 [2:39:28<21:55:02,  1.40s/it]
  9%|▉         | 5519/61904 [2:39:29<22:00:44,  1.41s/it]
  9%|▉         | 5520/61904 [2:39:30<21:53:36,  1.40s/it]
                                                         
{'loss': 2.9736, 'learning_rate': 1.913781926617399e-07, 'epoch': 1.43}

  9%|▉         | 5520/61904 [2:39:30<21:53:36,  1.40s/it]
  9%|▉         | 5521/61904 [2:39:32<21:32:35,  1.38s/it]
  9%|▉         | 5522/61904 [2:39:33<22:06:56,  1.41s/it]
  9%|▉         | 5523/61904 [2:39:35<22:21:33,  1.43s/it]
  9%|▉         | 5524/61904 [2:39:36<23:07:41,  1.48s/it]
  9%|▉         | 5525/61904 [2:39:38<22:25:35,  1.43s/it]
  9%|▉         | 5526/61904 [2:39:39<23:18:05,  1.49s/it]
  9%|▉         | 5527/61904 [2:39:41<22:54:25,  1.46s/it]
  9%|▉         | 5528/61904 [2:39:42<23:39:59,  1.51s/it]
  9%|▉         | 5529/61904 [2:39:44<23:18:45,  1.49s/it]
  9%|▉         | 5530/61904 [2:39:45<22:42:55,  1.45s/it]
  9%|▉         | 5531/61904 [2:39:47<23:24:10,  1.49s/it]
  9%|▉         | 5532/61904 [2:39:48<22:26:04,  1.43s/it]
  9%|▉         | 5533/61904 [2:39:49<21:50:23,  1.39s/it]
  9%|▉         | 5534/61904 [2:39:51<23:21:25,  1.49s/it]
  9%|▉         | 5535/61904 [2:39:52<22:28:16,  1.44s/it]
  9%|▉         | 5536/61904 [2:39:54<22:48:09,  1.46s/it]
  9%|▉         | 5537/61904 [2:39:55<22:28:39,  1.44s/it]
  9%|▉         | 5538/61904 [2:39:57<22:32:21,  1.44s/it]
  9%|▉         | 5539/61904 [2:39:58<22:15:10,  1.42s/it]
  9%|▉         | 5540/61904 [2:39:59<21:16:20,  1.36s/it]
                                                         
{'loss': 2.9392, 'learning_rate': 1.913457798521976e-07, 'epoch': 1.43}

  9%|▉         | 5540/61904 [2:39:59<21:16:20,  1.36s/it]
  9%|▉         | 5541/61904 [2:40:00<20:52:07,  1.33s/it]
  9%|▉         | 5542/61904 [2:40:02<21:19:31,  1.36s/it]
  9%|▉         | 5543/61904 [2:40:03<20:56:46,  1.34s/it]
  9%|▉         | 5544/61904 [2:40:05<20:56:07,  1.34s/it]
  9%|▉         | 5545/61904 [2:40:06<20:56:28,  1.34s/it]
  9%|▉         | 5546/61904 [2:40:07<21:13:39,  1.36s/it]
  9%|▉         | 5547/61904 [2:40:09<21:04:53,  1.35s/it]
  9%|▉         | 5548/61904 [2:40:10<21:31:35,  1.38s/it]
  9%|▉         | 5549/61904 [2:40:11<21:14:32,  1.36s/it]
  9%|▉         | 5550/61904 [2:40:13<21:14:25,  1.36s/it]
  9%|▉         | 5551/61904 [2:40:14<20:52:01,  1.33s/it]
  9%|▉         | 5552/61904 [2:40:15<21:19:24,  1.36s/it]
  9%|▉         | 5553/61904 [2:40:17<20:47:15,  1.33s/it]
  9%|▉         | 5554/61904 [2:40:18<20:53:25,  1.33s/it]
  9%|▉         | 5555/61904 [2:40:20<22:15:43,  1.42s/it]
  9%|▉         | 5556/61904 [2:40:21<21:52:54,  1.40s/it]
  9%|▉         | 5557/61904 [2:40:22<21:30:07,  1.37s/it]
  9%|▉         | 5558/61904 [2:40:24<21:51:07,  1.40s/it]
  9%|▉         | 5559/61904 [2:40:25<21:27:10,  1.37s/it]
  9%|▉         | 5560/61904 [2:40:26<21:28:02,  1.37s/it]
                                                         
{'loss': 2.9724, 'learning_rate': 1.9131336704265525e-07, 'epoch': 1.44}

  9%|▉         | 5560/61904 [2:40:26<21:28:02,  1.37s/it]
  9%|▉         | 5561/61904 [2:40:28<21:14:31,  1.36s/it]
  9%|▉         | 5562/61904 [2:40:29<20:51:53,  1.33s/it]
  9%|▉         | 5563/61904 [2:40:30<20:19:57,  1.30s/it]
  9%|▉         | 5564/61904 [2:40:32<21:35:31,  1.38s/it]
  9%|▉         | 5565/61904 [2:40:33<21:54:31,  1.40s/it]
  9%|▉         | 5566/61904 [2:40:35<21:47:19,  1.39s/it]
  9%|▉         | 5567/61904 [2:40:36<22:14:07,  1.42s/it]
  9%|▉         | 5568/61904 [2:40:38<22:04:46,  1.41s/it]
  9%|▉         | 5569/61904 [2:40:39<21:37:10,  1.38s/it]
  9%|▉         | 5570/61904 [2:40:40<21:21:00,  1.36s/it]
  9%|▉         | 5571/61904 [2:40:42<21:27:10,  1.37s/it]
  9%|▉         | 5572/61904 [2:40:43<21:08:21,  1.35s/it]
  9%|▉         | 5573/61904 [2:40:44<21:35:34,  1.38s/it]
  9%|▉         | 5574/61904 [2:40:46<21:12:30,  1.36s/it]
  9%|▉         | 5575/61904 [2:40:47<20:54:43,  1.34s/it]
  9%|▉         | 5576/61904 [2:40:48<21:14:36,  1.36s/it]
  9%|▉         | 5577/61904 [2:40:50<21:08:00,  1.35s/it]
  9%|▉         | 5578/61904 [2:40:51<22:10:55,  1.42s/it]
  9%|▉         | 5579/61904 [2:40:52<21:28:12,  1.37s/it]
  9%|▉         | 5580/61904 [2:40:54<21:12:04,  1.36s/it]
                                                         
{'loss': 2.9819, 'learning_rate': 1.912809542331129e-07, 'epoch': 1.44}

  9%|▉         | 5580/61904 [2:40:54<21:12:04,  1.36s/it]
  9%|▉         | 5581/61904 [2:40:55<21:28:55,  1.37s/it]
  9%|▉         | 5582/61904 [2:40:57<21:23:36,  1.37s/it]
  9%|▉         | 5583/61904 [2:40:58<21:00:08,  1.34s/it]
  9%|▉         | 5584/61904 [2:40:59<21:06:17,  1.35s/it]
  9%|▉         | 5585/61904 [2:41:01<21:00:29,  1.34s/it]
  9%|▉         | 5586/61904 [2:41:02<21:28:38,  1.37s/it]
  9%|▉         | 5587/61904 [2:41:03<21:16:54,  1.36s/it]
  9%|▉         | 5588/61904 [2:41:05<21:27:46,  1.37s/it]
  9%|▉         | 5589/61904 [2:41:06<21:31:45,  1.38s/it]
  9%|▉         | 5590/61904 [2:41:07<21:30:56,  1.38s/it]
  9%|▉         | 5591/61904 [2:41:09<21:35:14,  1.38s/it]
  9%|▉         | 5592/61904 [2:41:10<21:52:49,  1.40s/it]
  9%|▉         | 5593/61904 [2:41:12<21:43:38,  1.39s/it]
  9%|▉         | 5594/61904 [2:41:13<21:30:54,  1.38s/it]
  9%|▉         | 5595/61904 [2:41:14<21:20:23,  1.36s/it]
  9%|▉         | 5596/61904 [2:41:16<21:12:34,  1.36s/it]
  9%|▉         | 5597/61904 [2:41:17<21:08:11,  1.35s/it]
  9%|▉         | 5598/61904 [2:41:18<21:20:15,  1.36s/it]
  9%|▉         | 5599/61904 [2:41:20<22:35:50,  1.44s/it]
  9%|▉         | 5600/61904 [2:41:21<21:58:58,  1.41s/it]
                                                         
{'loss': 2.8861, 'learning_rate': 1.912485414235706e-07, 'epoch': 1.45}

  9%|▉         | 5600/61904 [2:41:21<21:58:58,  1.41s/it]
  9%|▉         | 5601/61904 [2:41:23<21:59:43,  1.41s/it]
  9%|▉         | 5602/61904 [2:41:24<21:36:19,  1.38s/it]
  9%|▉         | 5603/61904 [2:41:26<21:51:48,  1.40s/it]
  9%|▉         | 5604/61904 [2:41:27<21:16:01,  1.36s/it]
  9%|▉         | 5605/61904 [2:41:28<21:07:42,  1.35s/it]
  9%|▉         | 5606/61904 [2:41:30<21:53:01,  1.40s/it]
  9%|▉         | 5607/61904 [2:41:31<21:17:32,  1.36s/it]
  9%|▉         | 5608/61904 [2:41:33<22:33:52,  1.44s/it]
  9%|▉         | 5609/61904 [2:41:34<21:39:21,  1.38s/it]
  9%|▉         | 5610/61904 [2:41:35<21:34:26,  1.38s/it]
  9%|▉         | 5611/61904 [2:41:37<22:00:46,  1.41s/it]
  9%|▉         | 5612/61904 [2:41:38<22:12:31,  1.42s/it]
  9%|▉         | 5613/61904 [2:41:39<21:10:04,  1.35s/it]
  9%|▉         | 5614/61904 [2:41:41<21:47:16,  1.39s/it]
  9%|▉         | 5615/61904 [2:41:42<22:08:04,  1.42s/it]
  9%|▉         | 5616/61904 [2:41:44<22:33:25,  1.44s/it]
  9%|▉         | 5617/61904 [2:41:45<22:50:15,  1.46s/it]
  9%|▉         | 5618/61904 [2:41:47<22:35:54,  1.45s/it]
  9%|▉         | 5619/61904 [2:41:48<21:16:49,  1.36s/it]
  9%|▉         | 5620/61904 [2:41:49<22:00:24,  1.41s/it]
                                                         
{'loss': 2.9408, 'learning_rate': 1.9121612861402824e-07, 'epoch': 1.45}

  9%|▉         | 5620/61904 [2:41:49<22:00:24,  1.41s/it]
  9%|▉         | 5621/61904 [2:41:51<21:44:34,  1.39s/it]
  9%|▉         | 5622/61904 [2:41:52<21:51:10,  1.40s/it]
  9%|▉         | 5623/61904 [2:41:54<22:12:05,  1.42s/it]
  9%|▉         | 5624/61904 [2:41:55<21:45:00,  1.39s/it]
  9%|▉         | 5625/61904 [2:41:56<21:15:53,  1.36s/it]
  9%|▉         | 5626/61904 [2:41:58<21:12:22,  1.36s/it]
  9%|▉         | 5627/61904 [2:41:59<20:27:03,  1.31s/it]
  9%|▉         | 5628/61904 [2:42:00<20:41:20,  1.32s/it]
  9%|▉         | 5629/61904 [2:42:01<20:58:09,  1.34s/it]
  9%|▉         | 5630/61904 [2:42:03<21:43:40,  1.39s/it]
  9%|▉         | 5631/61904 [2:42:04<20:53:00,  1.34s/it]
  9%|▉         | 5632/61904 [2:42:06<20:59:06,  1.34s/it]
  9%|▉         | 5633/61904 [2:42:07<21:05:39,  1.35s/it]
  9%|▉         | 5634/61904 [2:42:08<20:46:33,  1.33s/it]
  9%|▉         | 5635/61904 [2:42:09<20:34:11,  1.32s/it]
  9%|▉         | 5636/61904 [2:42:11<19:48:23,  1.27s/it]
  9%|▉         | 5637/61904 [2:42:12<20:30:09,  1.31s/it]
  9%|▉         | 5638/61904 [2:42:13<20:33:13,  1.32s/it]
  9%|▉         | 5639/61904 [2:42:15<21:22:46,  1.37s/it]
  9%|▉         | 5640/61904 [2:42:16<21:42:57,  1.39s/it]
                                                         
{'loss': 3.0236, 'learning_rate': 1.9118371580448592e-07, 'epoch': 1.46}

  9%|▉         | 5640/61904 [2:42:16<21:42:57,  1.39s/it]
  9%|▉         | 5641/61904 [2:42:18<21:52:24,  1.40s/it]
  9%|▉         | 5642/61904 [2:42:19<21:25:24,  1.37s/it]
  9%|▉         | 5643/61904 [2:42:20<20:57:02,  1.34s/it]
  9%|▉         | 5644/61904 [2:42:22<21:48:48,  1.40s/it]
  9%|▉         | 5645/61904 [2:42:23<21:41:58,  1.39s/it]
  9%|▉         | 5646/61904 [2:42:25<21:42:40,  1.39s/it]
  9%|▉         | 5647/61904 [2:42:26<21:03:21,  1.35s/it]
  9%|▉         | 5648/61904 [2:42:27<21:14:22,  1.36s/it]
  9%|▉         | 5649/61904 [2:42:28<20:39:09,  1.32s/it]
  9%|▉         | 5650/61904 [2:42:30<20:26:15,  1.31s/it]
  9%|▉         | 5651/61904 [2:42:31<20:11:04,  1.29s/it]
  9%|▉         | 5652/61904 [2:42:32<20:18:03,  1.30s/it]
  9%|▉         | 5653/61904 [2:42:34<19:53:35,  1.27s/it]
  9%|▉         | 5654/61904 [2:42:35<20:55:43,  1.34s/it]
  9%|▉         | 5655/61904 [2:42:36<20:27:38,  1.31s/it]
  9%|▉         | 5656/61904 [2:42:37<20:14:25,  1.30s/it]
  9%|▉         | 5657/61904 [2:42:39<20:05:05,  1.29s/it]
  9%|▉         | 5658/61904 [2:42:40<20:26:23,  1.31s/it]
  9%|▉         | 5659/61904 [2:42:42<21:19:38,  1.37s/it]
  9%|▉         | 5660/61904 [2:42:43<20:36:32,  1.32s/it]
                                                         
{'loss': 2.9481, 'learning_rate': 1.911513029949436e-07, 'epoch': 1.46}

  9%|▉         | 5660/61904 [2:42:43<20:36:32,  1.32s/it]
  9%|▉         | 5661/61904 [2:42:44<21:43:28,  1.39s/it]
  9%|▉         | 5662/61904 [2:42:46<21:45:03,  1.39s/it]
  9%|▉         | 5663/61904 [2:42:47<21:30:28,  1.38s/it]
  9%|▉         | 5664/61904 [2:42:48<20:56:13,  1.34s/it]
  9%|▉         | 5665/61904 [2:42:50<20:36:30,  1.32s/it]
  9%|▉         | 5666/61904 [2:42:51<21:03:15,  1.35s/it]
  9%|▉         | 5667/61904 [2:42:53<21:35:36,  1.38s/it]
  9%|▉         | 5668/61904 [2:42:54<21:37:41,  1.38s/it]
  9%|▉         | 5669/61904 [2:42:55<21:41:04,  1.39s/it]
  9%|▉         | 5670/61904 [2:42:57<21:07:31,  1.35s/it]
  9%|▉         | 5671/61904 [2:42:58<20:58:19,  1.34s/it]
  9%|▉         | 5672/61904 [2:42:59<20:14:14,  1.30s/it]
  9%|▉         | 5673/61904 [2:43:00<20:31:52,  1.31s/it]
  9%|▉         | 5674/61904 [2:43:02<21:16:24,  1.36s/it]
  9%|▉         | 5675/61904 [2:43:03<21:26:31,  1.37s/it]
  9%|▉         | 5676/61904 [2:43:05<20:47:25,  1.33s/it]
  9%|▉         | 5677/61904 [2:43:06<20:54:40,  1.34s/it]
  9%|▉         | 5678/61904 [2:43:07<20:41:12,  1.32s/it]
  9%|▉         | 5679/61904 [2:43:09<20:52:39,  1.34s/it]
  9%|▉         | 5680/61904 [2:43:10<20:58:39,  1.34s/it]
                                                         
{'loss': 2.9892, 'learning_rate': 1.9111889018540125e-07, 'epoch': 1.47}

  9%|▉         | 5680/61904 [2:43:10<20:58:39,  1.34s/it]
  9%|▉         | 5681/61904 [2:43:11<20:33:07,  1.32s/it]
  9%|▉         | 5682/61904 [2:43:13<21:03:34,  1.35s/it]
  9%|▉         | 5683/61904 [2:43:14<20:42:24,  1.33s/it]
  9%|▉         | 5684/61904 [2:43:15<21:29:04,  1.38s/it]
  9%|▉         | 5685/61904 [2:43:17<21:24:05,  1.37s/it]
  9%|▉         | 5686/61904 [2:43:18<21:08:56,  1.35s/it]
  9%|▉         | 5687/61904 [2:43:19<21:04:59,  1.35s/it]
  9%|▉         | 5688/61904 [2:43:21<21:36:42,  1.38s/it]
  9%|▉         | 5689/61904 [2:43:22<21:35:50,  1.38s/it]
  9%|▉         | 5690/61904 [2:43:24<21:17:54,  1.36s/it]
  9%|▉         | 5691/61904 [2:43:25<20:56:17,  1.34s/it]
  9%|▉         | 5692/61904 [2:43:26<21:30:57,  1.38s/it]
  9%|▉         | 5693/61904 [2:43:28<21:57:09,  1.41s/it]
  9%|▉         | 5694/61904 [2:43:29<21:34:21,  1.38s/it]
  9%|▉         | 5695/61904 [2:43:30<21:16:09,  1.36s/it]
  9%|▉         | 5696/61904 [2:43:32<20:50:04,  1.33s/it]
  9%|▉         | 5697/61904 [2:43:33<21:01:09,  1.35s/it]
  9%|▉         | 5698/61904 [2:43:34<20:38:10,  1.32s/it]
  9%|▉         | 5699/61904 [2:43:36<21:00:41,  1.35s/it]
  9%|▉         | 5700/61904 [2:43:37<21:11:25,  1.36s/it]
                                                         
{'loss': 2.9723, 'learning_rate': 1.9108647737585894e-07, 'epoch': 1.47}

  9%|▉         | 5700/61904 [2:43:37<21:11:25,  1.36s/it]
  9%|▉         | 5701/61904 [2:43:39<21:23:51,  1.37s/it]
  9%|▉         | 5702/61904 [2:43:40<21:40:56,  1.39s/it]
  9%|▉         | 5703/61904 [2:43:41<21:24:20,  1.37s/it]
  9%|▉         | 5704/61904 [2:43:43<21:20:58,  1.37s/it]
  9%|▉         | 5705/61904 [2:43:44<21:40:49,  1.39s/it]
  9%|▉         | 5706/61904 [2:43:45<21:23:58,  1.37s/it]
  9%|▉         | 5707/61904 [2:43:47<21:09:09,  1.36s/it]
  9%|▉         | 5708/61904 [2:43:48<22:07:09,  1.42s/it]
  9%|▉         | 5709/61904 [2:43:50<22:04:54,  1.41s/it]
  9%|▉         | 5710/61904 [2:43:51<21:45:05,  1.39s/it]
  9%|▉         | 5711/61904 [2:43:52<21:36:11,  1.38s/it]
  9%|▉         | 5712/61904 [2:43:54<21:44:57,  1.39s/it]
  9%|▉         | 5713/61904 [2:43:55<21:32:05,  1.38s/it]
  9%|▉         | 5714/61904 [2:43:57<21:39:13,  1.39s/it]
  9%|▉         | 5715/61904 [2:43:58<22:04:13,  1.41s/it]
  9%|▉         | 5716/61904 [2:43:59<21:35:02,  1.38s/it]
  9%|▉         | 5717/61904 [2:44:01<22:01:35,  1.41s/it]
  9%|▉         | 5718/61904 [2:44:02<21:39:55,  1.39s/it]
  9%|▉         | 5719/61904 [2:44:04<21:30:24,  1.38s/it]
  9%|▉         | 5720/61904 [2:44:05<21:59:44,  1.41s/it]
                                                         
{'loss': 2.8791, 'learning_rate': 1.910540645663166e-07, 'epoch': 1.48}

  9%|▉         | 5720/61904 [2:44:05<21:59:44,  1.41s/it]
  9%|▉         | 5721/61904 [2:44:06<21:36:42,  1.38s/it]
  9%|▉         | 5722/61904 [2:44:08<21:18:19,  1.37s/it]
  9%|▉         | 5723/61904 [2:44:09<22:08:22,  1.42s/it]
  9%|▉         | 5724/61904 [2:44:11<22:05:20,  1.42s/it]
  9%|▉         | 5725/61904 [2:44:12<21:27:23,  1.37s/it]
  9%|▉         | 5726/61904 [2:44:13<21:24:33,  1.37s/it]
  9%|▉         | 5727/61904 [2:44:14<20:53:37,  1.34s/it]
  9%|▉         | 5728/61904 [2:44:16<21:28:15,  1.38s/it]
  9%|▉         | 5729/61904 [2:44:18<22:37:35,  1.45s/it]
  9%|▉         | 5730/61904 [2:44:19<22:31:05,  1.44s/it]
  9%|▉         | 5731/61904 [2:44:20<21:56:28,  1.41s/it]
  9%|▉         | 5732/61904 [2:44:22<21:33:10,  1.38s/it]
  9%|▉         | 5733/61904 [2:44:23<21:42:32,  1.39s/it]
  9%|▉         | 5734/61904 [2:44:24<20:50:48,  1.34s/it]
  9%|▉         | 5735/61904 [2:44:26<21:12:50,  1.36s/it]
  9%|▉         | 5736/61904 [2:44:27<21:26:20,  1.37s/it]
  9%|▉         | 5737/61904 [2:44:28<21:15:20,  1.36s/it]
  9%|▉         | 5738/61904 [2:44:30<20:38:10,  1.32s/it]
  9%|▉         | 5739/61904 [2:44:31<20:36:47,  1.32s/it]
  9%|▉         | 5740/61904 [2:44:32<20:31:42,  1.32s/it]
                                                         
{'loss': 2.9381, 'learning_rate': 1.9102165175677426e-07, 'epoch': 1.48}

  9%|▉         | 5740/61904 [2:44:32<20:31:42,  1.32s/it]
  9%|▉         | 5741/61904 [2:44:34<20:29:41,  1.31s/it]
  9%|▉         | 5742/61904 [2:44:35<20:46:00,  1.33s/it]
  9%|▉         | 5743/61904 [2:44:36<20:52:56,  1.34s/it]
  9%|▉         | 5744/61904 [2:44:38<21:16:07,  1.36s/it]
  9%|▉         | 5745/61904 [2:44:39<20:45:11,  1.33s/it]
  9%|▉         | 5746/61904 [2:44:40<20:51:56,  1.34s/it]
  9%|▉         | 5747/61904 [2:44:42<20:51:54,  1.34s/it]
  9%|▉         | 5748/61904 [2:44:43<21:41:10,  1.39s/it]
  9%|▉         | 5749/61904 [2:44:45<21:16:56,  1.36s/it]
  9%|▉         | 5750/61904 [2:44:46<21:10:46,  1.36s/it]
  9%|▉         | 5751/61904 [2:44:47<20:49:41,  1.34s/it]
  9%|▉         | 5752/61904 [2:44:48<20:56:15,  1.34s/it]
  9%|▉         | 5753/61904 [2:44:50<21:37:30,  1.39s/it]
  9%|▉         | 5754/61904 [2:44:51<21:44:27,  1.39s/it]
  9%|▉         | 5755/61904 [2:44:53<21:09:40,  1.36s/it]
  9%|▉         | 5756/61904 [2:44:54<21:05:52,  1.35s/it]
  9%|▉         | 5757/61904 [2:44:56<21:59:04,  1.41s/it]
  9%|▉         | 5758/61904 [2:44:57<21:43:33,  1.39s/it]
  9%|▉         | 5759/61904 [2:44:58<21:57:05,  1.41s/it]
  9%|▉         | 5760/61904 [2:45:00<21:19:46,  1.37s/it]
                                                         
{'loss': 2.8873, 'learning_rate': 1.9098923894723195e-07, 'epoch': 1.49}

  9%|▉         | 5760/61904 [2:45:00<21:19:46,  1.37s/it]
  9%|▉         | 5761/61904 [2:45:01<21:09:38,  1.36s/it]
  9%|▉         | 5762/61904 [2:45:02<20:57:10,  1.34s/it]
  9%|▉         | 5763/61904 [2:45:04<20:47:20,  1.33s/it]
  9%|▉         | 5764/61904 [2:45:05<20:33:39,  1.32s/it]
  9%|▉         | 5765/61904 [2:45:06<20:55:07,  1.34s/it]
  9%|▉         | 5766/61904 [2:45:08<20:57:26,  1.34s/it]
  9%|▉         | 5767/61904 [2:45:09<21:33:33,  1.38s/it]
  9%|▉         | 5768/61904 [2:45:10<21:15:37,  1.36s/it]
  9%|▉         | 5769/61904 [2:45:12<21:39:31,  1.39s/it]
  9%|▉         | 5770/61904 [2:45:13<21:17:53,  1.37s/it]
  9%|▉         | 5771/61904 [2:45:15<21:48:45,  1.40s/it]
  9%|▉         | 5772/61904 [2:45:16<22:13:47,  1.43s/it]
  9%|▉         | 5773/61904 [2:45:18<22:57:00,  1.47s/it]
  9%|▉         | 5774/61904 [2:45:19<21:51:27,  1.40s/it]
  9%|▉         | 5775/61904 [2:45:20<21:39:22,  1.39s/it]
  9%|▉         | 5776/61904 [2:45:22<21:08:41,  1.36s/it]
  9%|▉         | 5777/61904 [2:45:23<20:53:18,  1.34s/it]
  9%|▉         | 5778/61904 [2:45:24<20:38:33,  1.32s/it]
  9%|▉         | 5779/61904 [2:45:26<21:26:16,  1.38s/it]
  9%|▉         | 5780/61904 [2:45:27<21:10:52,  1.36s/it]
                                                         
{'loss': 2.8586, 'learning_rate': 1.909568261376896e-07, 'epoch': 1.49}

  9%|▉         | 5780/61904 [2:45:27<21:10:52,  1.36s/it]
  9%|▉         | 5781/61904 [2:45:29<22:02:45,  1.41s/it]
  9%|▉         | 5782/61904 [2:45:30<22:42:30,  1.46s/it]
  9%|▉         | 5783/61904 [2:45:32<22:59:15,  1.47s/it]
  9%|▉         | 5784/61904 [2:45:33<22:34:00,  1.45s/it]
  9%|▉         | 5785/61904 [2:45:34<21:54:50,  1.41s/it]
  9%|▉         | 5786/61904 [2:45:36<22:18:39,  1.43s/it]
  9%|▉         | 5787/61904 [2:45:37<21:52:08,  1.40s/it]
  9%|▉         | 5788/61904 [2:45:38<21:48:27,  1.40s/it]
  9%|▉         | 5789/61904 [2:45:40<21:01:18,  1.35s/it]
  9%|▉         | 5790/61904 [2:45:41<20:26:19,  1.31s/it]
  9%|▉         | 5791/61904 [2:45:42<20:53:31,  1.34s/it]
  9%|▉         | 5792/61904 [2:45:44<20:06:12,  1.29s/it]
  9%|▉         | 5793/61904 [2:45:45<20:48:59,  1.34s/it]
  9%|▉         | 5794/61904 [2:45:46<21:16:14,  1.36s/it]
  9%|▉         | 5795/61904 [2:45:48<21:22:59,  1.37s/it]
  9%|▉         | 5796/61904 [2:45:49<21:08:22,  1.36s/it]
  9%|▉         | 5797/61904 [2:45:50<20:29:16,  1.31s/it]
  9%|▉         | 5798/61904 [2:45:52<20:15:45,  1.30s/it]
  9%|▉         | 5799/61904 [2:45:53<20:41:04,  1.33s/it]
  9%|▉         | 5800/61904 [2:45:54<20:20:32,  1.31s/it]
                                                         
{'loss': 2.9308, 'learning_rate': 1.9092441332814727e-07, 'epoch': 1.5}

  9%|▉         | 5800/61904 [2:45:54<20:20:32,  1.31s/it]
  9%|▉         | 5801/61904 [2:45:56<21:14:59,  1.36s/it]
  9%|▉         | 5802/61904 [2:45:57<20:53:49,  1.34s/it]
  9%|▉         | 5803/61904 [2:45:58<20:56:20,  1.34s/it]
  9%|▉         | 5804/61904 [2:46:00<21:27:34,  1.38s/it]
  9%|▉         | 5805/61904 [2:46:01<21:08:21,  1.36s/it]
  9%|▉         | 5806/61904 [2:46:03<21:16:33,  1.37s/it]
  9%|▉         | 5807/61904 [2:46:04<21:22:26,  1.37s/it]
  9%|▉         | 5808/61904 [2:46:05<21:23:45,  1.37s/it]
  9%|▉         | 5809/61904 [2:46:07<21:19:48,  1.37s/it]
  9%|▉         | 5810/61904 [2:46:08<22:01:06,  1.41s/it]
  9%|▉         | 5811/61904 [2:46:10<22:15:49,  1.43s/it]
  9%|▉         | 5812/61904 [2:46:11<21:39:13,  1.39s/it]
  9%|▉         | 5813/61904 [2:46:12<21:33:30,  1.38s/it]
  9%|▉         | 5814/61904 [2:46:14<21:59:52,  1.41s/it]
  9%|▉         | 5815/61904 [2:46:15<21:55:55,  1.41s/it]
  9%|▉         | 5816/61904 [2:46:17<21:46:23,  1.40s/it]
  9%|▉         | 5817/61904 [2:46:18<21:13:11,  1.36s/it]
  9%|▉         | 5818/61904 [2:46:19<21:21:45,  1.37s/it]
  9%|▉         | 5819/61904 [2:46:20<20:30:31,  1.32s/it]
  9%|▉         | 5820/61904 [2:46:22<21:31:22,  1.38s/it]
                                                         
{'loss': 2.9222, 'learning_rate': 1.9089200051860496e-07, 'epoch': 1.5}

  9%|▉         | 5820/61904 [2:46:22<21:31:22,  1.38s/it]
  9%|▉         | 5821/61904 [2:46:23<20:43:50,  1.33s/it]
  9%|▉         | 5822/61904 [2:46:24<20:39:04,  1.33s/it]
  9%|▉         | 5823/61904 [2:46:26<20:14:47,  1.30s/it]
  9%|▉         | 5824/61904 [2:46:27<20:31:41,  1.32s/it]
  9%|▉         | 5825/61904 [2:46:28<20:50:17,  1.34s/it]
  9%|▉         | 5826/61904 [2:46:30<20:51:30,  1.34s/it]
  9%|▉         | 5827/61904 [2:46:31<20:48:29,  1.34s/it]
  9%|▉         | 5828/61904 [2:46:32<20:35:57,  1.32s/it]
  9%|▉         | 5829/61904 [2:46:34<20:35:53,  1.32s/it]
  9%|▉         | 5830/61904 [2:46:35<20:43:40,  1.33s/it]
  9%|▉         | 5831/61904 [2:46:36<20:34:35,  1.32s/it]
  9%|▉         | 5832/61904 [2:46:38<21:25:41,  1.38s/it]
  9%|▉         | 5833/61904 [2:46:39<20:24:59,  1.31s/it]
  9%|▉         | 5834/61904 [2:46:40<20:32:43,  1.32s/it]
  9%|▉         | 5835/61904 [2:46:42<20:17:23,  1.30s/it]
  9%|▉         | 5836/61904 [2:46:43<20:21:22,  1.31s/it]
  9%|▉         | 5837/61904 [2:46:45<21:48:48,  1.40s/it]
  9%|▉         | 5838/61904 [2:46:46<21:57:12,  1.41s/it]
  9%|▉         | 5839/61904 [2:46:47<21:38:03,  1.39s/it]
  9%|▉         | 5840/61904 [2:46:49<21:19:56,  1.37s/it]
                                                         
{'loss': 2.9787, 'learning_rate': 1.908595877090626e-07, 'epoch': 1.51}

  9%|▉         | 5840/61904 [2:46:49<21:19:56,  1.37s/it]
  9%|▉         | 5841/61904 [2:46:50<21:08:10,  1.36s/it]
  9%|▉         | 5842/61904 [2:46:51<21:22:22,  1.37s/it]
  9%|▉         | 5843/61904 [2:46:53<21:03:15,  1.35s/it]
  9%|▉         | 5844/61904 [2:46:54<21:15:53,  1.37s/it]
  9%|▉         | 5845/61904 [2:46:56<21:25:58,  1.38s/it]
  9%|▉         | 5846/61904 [2:46:57<21:41:12,  1.39s/it]
  9%|▉         | 5847/61904 [2:46:58<21:06:41,  1.36s/it]
  9%|▉         | 5848/61904 [2:47:00<21:18:03,  1.37s/it]
  9%|▉         | 5849/61904 [2:47:01<21:07:15,  1.36s/it]
  9%|▉         | 5850/61904 [2:47:02<20:34:41,  1.32s/it]
  9%|▉         | 5851/61904 [2:47:04<20:57:35,  1.35s/it]
  9%|▉         | 5852/61904 [2:47:05<20:39:38,  1.33s/it]
  9%|▉         | 5853/61904 [2:47:06<20:57:46,  1.35s/it]
  9%|▉         | 5854/61904 [2:47:08<20:38:57,  1.33s/it]
  9%|▉         | 5855/61904 [2:47:09<20:38:27,  1.33s/it]
  9%|▉         | 5856/61904 [2:47:10<20:51:14,  1.34s/it]
  9%|▉         | 5857/61904 [2:47:12<20:44:33,  1.33s/it]
  9%|▉         | 5858/61904 [2:47:13<20:52:49,  1.34s/it]
  9%|▉         | 5859/61904 [2:47:14<20:41:18,  1.33s/it]
  9%|▉         | 5860/61904 [2:47:16<20:35:21,  1.32s/it]
                                                         
{'loss': 2.9207, 'learning_rate': 1.9082717489952028e-07, 'epoch': 1.51}

  9%|▉         | 5860/61904 [2:47:16<20:35:21,  1.32s/it]
  9%|▉         | 5861/61904 [2:47:17<20:41:13,  1.33s/it]
  9%|▉         | 5862/61904 [2:47:18<20:19:39,  1.31s/it]
  9%|▉         | 5863/61904 [2:47:20<20:47:00,  1.34s/it]
  9%|▉         | 5864/61904 [2:47:21<20:41:38,  1.33s/it]
  9%|▉         | 5865/61904 [2:47:22<21:35:15,  1.39s/it]
  9%|▉         | 5866/61904 [2:47:24<21:11:43,  1.36s/it]
  9%|▉         | 5867/61904 [2:47:25<21:14:11,  1.36s/it]
  9%|▉         | 5868/61904 [2:47:26<21:08:10,  1.36s/it]
  9%|▉         | 5869/61904 [2:47:28<21:40:06,  1.39s/it]
  9%|▉         | 5870/61904 [2:47:29<21:28:23,  1.38s/it]
  9%|▉         | 5871/61904 [2:47:31<21:53:24,  1.41s/it]
  9%|▉         | 5872/61904 [2:47:32<22:03:44,  1.42s/it]
  9%|▉         | 5873/61904 [2:47:34<22:08:05,  1.42s/it]
  9%|▉         | 5874/61904 [2:47:35<22:25:58,  1.44s/it]
  9%|▉         | 5875/61904 [2:47:36<22:12:48,  1.43s/it]
  9%|▉         | 5876/61904 [2:47:38<21:45:45,  1.40s/it]
  9%|▉         | 5877/61904 [2:47:39<21:59:04,  1.41s/it]
  9%|▉         | 5878/61904 [2:47:41<22:10:04,  1.42s/it]
  9%|▉         | 5879/61904 [2:47:42<21:28:52,  1.38s/it]
  9%|▉         | 5880/61904 [2:47:43<21:50:28,  1.40s/it]
                                                         
{'loss': 2.9304, 'learning_rate': 1.9079476208997797e-07, 'epoch': 1.52}

  9%|▉         | 5880/61904 [2:47:43<21:50:28,  1.40s/it]
 10%|▉         | 5881/61904 [2:47:45<21:06:19,  1.36s/it]
 10%|▉         | 5882/61904 [2:47:46<20:34:06,  1.32s/it]
 10%|▉         | 5883/61904 [2:47:47<20:46:05,  1.33s/it]
 10%|▉         | 5884/61904 [2:47:49<20:46:33,  1.34s/it]
 10%|▉         | 5885/61904 [2:47:50<20:40:52,  1.33s/it]
 10%|▉         | 5886/61904 [2:47:51<20:48:04,  1.34s/it]
 10%|▉         | 5887/61904 [2:47:53<20:47:57,  1.34s/it]
 10%|▉         | 5888/61904 [2:47:54<20:44:34,  1.33s/it]
 10%|▉         | 5889/61904 [2:47:55<20:30:32,  1.32s/it]
 10%|▉         | 5890/61904 [2:47:57<21:07:20,  1.36s/it]
 10%|▉         | 5891/61904 [2:47:58<21:25:35,  1.38s/it]
 10%|▉         | 5892/61904 [2:48:00<22:08:05,  1.42s/it]
 10%|▉         | 5893/61904 [2:48:01<22:24:14,  1.44s/it]
 10%|▉         | 5894/61904 [2:48:02<21:50:55,  1.40s/it]
 10%|▉         | 5895/61904 [2:48:04<21:27:54,  1.38s/it]
 10%|▉         | 5896/61904 [2:48:05<22:09:31,  1.42s/it]
 10%|▉         | 5897/61904 [2:48:07<22:44:07,  1.46s/it]
 10%|▉         | 5898/61904 [2:48:08<22:23:40,  1.44s/it]
 10%|▉         | 5899/61904 [2:48:09<21:46:45,  1.40s/it]
 10%|▉         | 5900/61904 [2:48:11<21:26:43,  1.38s/it]
                                                         
{'loss': 2.942, 'learning_rate': 1.907623492804356e-07, 'epoch': 1.52}

 10%|▉         | 5900/61904 [2:48:11<21:26:43,  1.38s/it]
 10%|▉         | 5901/61904 [2:48:12<21:07:34,  1.36s/it]
 10%|▉         | 5902/61904 [2:48:14<21:33:41,  1.39s/it]
 10%|▉         | 5903/61904 [2:48:15<22:01:35,  1.42s/it]
 10%|▉         | 5904/61904 [2:48:17<22:34:13,  1.45s/it]
 10%|▉         | 5905/61904 [2:48:18<21:35:51,  1.39s/it]
 10%|▉         | 5906/61904 [2:48:19<21:50:56,  1.40s/it]
 10%|▉         | 5907/61904 [2:48:21<21:43:55,  1.40s/it]
 10%|▉         | 5908/61904 [2:48:22<21:23:40,  1.38s/it]
 10%|▉         | 5909/61904 [2:48:23<20:45:17,  1.33s/it]
 10%|▉         | 5910/61904 [2:48:24<20:23:58,  1.31s/it]
 10%|▉         | 5911/61904 [2:48:26<20:51:34,  1.34s/it]
 10%|▉         | 5912/61904 [2:48:27<20:32:00,  1.32s/it]
 10%|▉         | 5913/61904 [2:48:28<20:33:09,  1.32s/it]
 10%|▉         | 5914/61904 [2:48:30<20:42:23,  1.33s/it]
 10%|▉         | 5915/61904 [2:48:31<20:09:08,  1.30s/it]
 10%|▉         | 5916/61904 [2:48:32<20:05:22,  1.29s/it]
 10%|▉         | 5917/61904 [2:48:34<20:29:36,  1.32s/it]
 10%|▉         | 5918/61904 [2:48:35<20:32:33,  1.32s/it]
 10%|▉         | 5919/61904 [2:48:36<20:49:33,  1.34s/it]
 10%|▉         | 5920/61904 [2:48:38<20:38:07,  1.33s/it]
                                                         
{'loss': 2.9672, 'learning_rate': 1.907299364708933e-07, 'epoch': 1.53}

 10%|▉         | 5920/61904 [2:48:38<20:38:07,  1.33s/it]
 10%|▉         | 5921/61904 [2:48:39<20:48:35,  1.34s/it]
 10%|▉         | 5922/61904 [2:48:40<20:22:03,  1.31s/it]
 10%|▉         | 5923/61904 [2:48:42<19:52:41,  1.28s/it]
 10%|▉         | 5924/61904 [2:48:43<20:14:53,  1.30s/it]
 10%|▉         | 5925/61904 [2:48:44<20:30:17,  1.32s/it]
 10%|▉         | 5926/61904 [2:48:46<21:36:29,  1.39s/it]
 10%|▉         | 5927/61904 [2:48:47<21:31:23,  1.38s/it]
 10%|▉         | 5928/61904 [2:48:49<21:59:06,  1.41s/it]
 10%|▉         | 5929/61904 [2:48:50<22:12:40,  1.43s/it]
 10%|▉         | 5930/61904 [2:48:51<21:39:31,  1.39s/it]
 10%|▉         | 5931/61904 [2:48:53<21:33:24,  1.39s/it]
 10%|▉         | 5932/61904 [2:48:54<21:33:07,  1.39s/it]
 10%|▉         | 5933/61904 [2:48:55<21:02:04,  1.35s/it]
 10%|▉         | 5934/61904 [2:48:57<21:33:46,  1.39s/it]
 10%|▉         | 5935/61904 [2:48:58<21:43:13,  1.40s/it]
 10%|▉         | 5936/61904 [2:49:00<20:53:40,  1.34s/it]
 10%|▉         | 5937/61904 [2:49:01<21:15:22,  1.37s/it]
 10%|▉         | 5938/61904 [2:49:02<21:26:23,  1.38s/it]
 10%|▉         | 5939/61904 [2:49:04<20:47:15,  1.34s/it]
 10%|▉         | 5940/61904 [2:49:05<21:03:44,  1.35s/it]
                                                         
{'loss': 2.9461, 'learning_rate': 1.9069752366135096e-07, 'epoch': 1.54}

 10%|▉         | 5940/61904 [2:49:05<21:03:44,  1.35s/it]
 10%|▉         | 5941/61904 [2:49:06<20:57:24,  1.35s/it]
 10%|▉         | 5942/61904 [2:49:08<20:57:58,  1.35s/it]
 10%|▉         | 5943/61904 [2:49:09<20:43:02,  1.33s/it]
 10%|▉         | 5944/61904 [2:49:10<20:14:58,  1.30s/it]
 10%|▉         | 5945/61904 [2:49:12<20:25:04,  1.31s/it]
 10%|▉         | 5946/61904 [2:49:13<20:46:31,  1.34s/it]
 10%|▉         | 5947/61904 [2:49:14<20:16:53,  1.30s/it]
 10%|▉         | 5948/61904 [2:49:16<20:16:53,  1.30s/it]
 10%|▉         | 5949/61904 [2:49:17<20:37:52,  1.33s/it]
 10%|▉         | 5950/61904 [2:49:18<21:28:24,  1.38s/it]
 10%|▉         | 5951/61904 [2:49:20<20:53:45,  1.34s/it]
 10%|▉         | 5952/61904 [2:49:21<22:03:29,  1.42s/it]
 10%|▉         | 5953/61904 [2:49:23<22:24:11,  1.44s/it]
 10%|▉         | 5954/61904 [2:49:24<21:32:22,  1.39s/it]
 10%|▉         | 5955/61904 [2:49:25<21:12:29,  1.36s/it]
 10%|▉         | 5956/61904 [2:49:27<21:19:35,  1.37s/it]
 10%|▉         | 5957/61904 [2:49:28<21:34:27,  1.39s/it]
 10%|▉         | 5958/61904 [2:49:29<21:24:11,  1.38s/it]
 10%|▉         | 5959/61904 [2:49:31<21:26:11,  1.38s/it]
 10%|▉         | 5960/61904 [2:49:32<21:37:58,  1.39s/it]
                                                         
{'loss': 2.9206, 'learning_rate': 1.9066511085180862e-07, 'epoch': 1.54}

 10%|▉         | 5960/61904 [2:49:32<21:37:58,  1.39s/it]
 10%|▉         | 5961/61904 [2:49:34<21:44:36,  1.40s/it]
 10%|▉         | 5962/61904 [2:49:35<21:37:47,  1.39s/it]
 10%|▉         | 5963/61904 [2:49:36<21:23:15,  1.38s/it]
 10%|▉         | 5964/61904 [2:49:38<21:17:45,  1.37s/it]
 10%|▉         | 5965/61904 [2:49:39<21:25:10,  1.38s/it]
 10%|▉         | 5966/61904 [2:49:41<21:46:28,  1.40s/it]
 10%|▉         | 5967/61904 [2:49:42<21:27:44,  1.38s/it]
 10%|▉         | 5968/61904 [2:49:43<21:57:38,  1.41s/it]
 10%|▉         | 5969/61904 [2:49:45<21:17:08,  1.37s/it]
 10%|▉         | 5970/61904 [2:49:46<21:11:20,  1.36s/it]
 10%|▉         | 5971/61904 [2:49:47<20:47:13,  1.34s/it]
 10%|▉         | 5972/61904 [2:49:49<20:58:23,  1.35s/it]
 10%|▉         | 5973/61904 [2:49:50<21:30:25,  1.38s/it]
 10%|▉         | 5974/61904 [2:49:51<21:05:45,  1.36s/it]
 10%|▉         | 5975/61904 [2:49:53<21:18:26,  1.37s/it]
 10%|▉         | 5976/61904 [2:49:54<21:06:20,  1.36s/it]
 10%|▉         | 5977/61904 [2:49:55<20:39:59,  1.33s/it]
 10%|▉         | 5978/61904 [2:49:57<20:54:07,  1.35s/it]
 10%|▉         | 5979/61904 [2:49:58<21:35:05,  1.39s/it]
 10%|▉         | 5980/61904 [2:50:00<21:09:25,  1.36s/it]
                                                         
{'loss': 3.0094, 'learning_rate': 1.906326980422663e-07, 'epoch': 1.55}

 10%|▉         | 5980/61904 [2:50:00<21:09:25,  1.36s/it]
 10%|▉         | 5981/61904 [2:50:01<20:47:09,  1.34s/it]
 10%|▉         | 5982/61904 [2:50:02<21:17:50,  1.37s/it]
 10%|▉         | 5983/61904 [2:50:04<21:14:17,  1.37s/it]
 10%|▉         | 5984/61904 [2:50:05<20:25:28,  1.31s/it]
 10%|▉         | 5985/61904 [2:50:06<21:10:08,  1.36s/it]
 10%|▉         | 5986/61904 [2:50:08<20:57:06,  1.35s/it]
 10%|▉         | 5987/61904 [2:50:09<20:59:23,  1.35s/it]
 10%|▉         | 5988/61904 [2:50:10<21:04:27,  1.36s/it]
 10%|▉         | 5989/61904 [2:50:12<21:29:08,  1.38s/it]
 10%|▉         | 5990/61904 [2:50:13<21:08:14,  1.36s/it]
 10%|▉         | 5991/61904 [2:50:15<21:02:23,  1.35s/it]
 10%|▉         | 5992/61904 [2:50:16<21:11:52,  1.36s/it]
 10%|▉         | 5993/61904 [2:50:17<20:55:40,  1.35s/it]
 10%|▉         | 5994/61904 [2:50:18<20:27:12,  1.32s/it]
 10%|▉         | 5995/61904 [2:50:20<21:07:51,  1.36s/it]
 10%|▉         | 5996/61904 [2:50:21<21:28:10,  1.38s/it]
 10%|▉         | 5997/61904 [2:50:23<20:49:07,  1.34s/it]
 10%|▉         | 5998/61904 [2:50:24<21:15:24,  1.37s/it]
 10%|▉         | 5999/61904 [2:50:25<21:05:27,  1.36s/it]
 10%|▉         | 6000/61904 [2:50:27<22:06:56,  1.42s/it]
                                                         
{'loss': 2.9333, 'learning_rate': 1.9060028523272397e-07, 'epoch': 1.55}

 10%|▉         | 6000/61904 [2:50:27<22:06:56,  1.42s/it]
 10%|▉         | 6001/61904 [2:50:28<21:35:17,  1.39s/it]
 10%|▉         | 6002/61904 [2:50:30<21:16:48,  1.37s/it]
 10%|▉         | 6003/61904 [2:50:31<21:03:39,  1.36s/it]
 10%|▉         | 6004/61904 [2:50:32<20:53:57,  1.35s/it]
 10%|▉         | 6005/61904 [2:50:34<21:35:09,  1.39s/it]
 10%|▉         | 6006/61904 [2:50:35<21:08:01,  1.36s/it]
 10%|▉         | 6007/61904 [2:50:36<21:21:38,  1.38s/it]
 10%|▉         | 6008/61904 [2:50:38<22:07:06,  1.42s/it]
 10%|▉         | 6009/61904 [2:50:39<21:42:53,  1.40s/it]
 10%|▉         | 6010/61904 [2:50:41<21:34:14,  1.39s/it]
 10%|▉         | 6011/61904 [2:50:42<21:27:38,  1.38s/it]
 10%|▉         | 6012/61904 [2:50:43<21:27:30,  1.38s/it]
 10%|▉         | 6013/61904 [2:50:45<20:37:56,  1.33s/it]
 10%|▉         | 6014/61904 [2:50:46<20:54:37,  1.35s/it]
 10%|▉         | 6015/61904 [2:50:47<20:42:20,  1.33s/it]
 10%|▉         | 6016/61904 [2:50:49<20:16:36,  1.31s/it]
 10%|▉         | 6017/61904 [2:50:50<20:30:35,  1.32s/it]
 10%|▉         | 6018/61904 [2:50:52<21:47:42,  1.40s/it]
 10%|▉         | 6019/61904 [2:50:53<22:05:26,  1.42s/it]
 10%|▉         | 6020/61904 [2:50:54<21:22:30,  1.38s/it]
                                                         
{'loss': 2.8769, 'learning_rate': 1.9056787242318163e-07, 'epoch': 1.56}

 10%|▉         | 6020/61904 [2:50:54<21:22:30,  1.38s/it]
 10%|▉         | 6021/61904 [2:50:56<21:03:54,  1.36s/it]
 10%|▉         | 6022/61904 [2:50:57<21:21:22,  1.38s/it]
 10%|▉         | 6023/61904 [2:50:58<21:05:26,  1.36s/it]
 10%|▉         | 6024/61904 [2:51:00<20:53:31,  1.35s/it]
 10%|▉         | 6025/61904 [2:51:01<20:35:27,  1.33s/it]
 10%|▉         | 6026/61904 [2:51:02<21:32:45,  1.39s/it]
 10%|▉         | 6027/61904 [2:51:04<21:55:30,  1.41s/it]
 10%|▉         | 6028/61904 [2:51:05<21:46:25,  1.40s/it]
 10%|▉         | 6029/61904 [2:51:07<21:24:04,  1.38s/it]
 10%|▉         | 6030/61904 [2:51:08<21:39:02,  1.39s/it]
 10%|▉         | 6031/61904 [2:51:09<21:45:01,  1.40s/it]
 10%|▉         | 6032/61904 [2:51:11<22:31:21,  1.45s/it]
 10%|▉         | 6033/61904 [2:51:12<21:55:38,  1.41s/it]
 10%|▉         | 6034/61904 [2:51:14<21:51:17,  1.41s/it]
 10%|▉         | 6035/61904 [2:51:15<20:57:13,  1.35s/it]
 10%|▉         | 6036/61904 [2:51:16<20:57:55,  1.35s/it]
 10%|▉         | 6037/61904 [2:51:18<20:50:35,  1.34s/it]
 10%|▉         | 6038/61904 [2:51:19<20:37:23,  1.33s/it]
 10%|▉         | 6039/61904 [2:51:20<20:20:06,  1.31s/it]
 10%|▉         | 6040/61904 [2:51:22<21:34:37,  1.39s/it]
                                                         
{'loss': 2.8884, 'learning_rate': 1.9053545961363932e-07, 'epoch': 1.56}

 10%|▉         | 6040/61904 [2:51:22<21:34:37,  1.39s/it]
 10%|▉         | 6041/61904 [2:51:23<21:25:03,  1.38s/it]
 10%|▉         | 6042/61904 [2:51:24<21:10:20,  1.36s/it]
 10%|▉         | 6043/61904 [2:51:26<22:06:28,  1.42s/it]
 10%|▉         | 6044/61904 [2:51:27<22:07:10,  1.43s/it]
 10%|▉         | 6045/61904 [2:51:29<22:36:53,  1.46s/it]
 10%|▉         | 6046/61904 [2:51:30<22:11:15,  1.43s/it]
 10%|▉         | 6047/61904 [2:51:32<21:56:26,  1.41s/it]
 10%|▉         | 6048/61904 [2:51:33<21:53:44,  1.41s/it]
 10%|▉         | 6049/61904 [2:51:34<21:12:19,  1.37s/it]
 10%|▉         | 6050/61904 [2:51:36<21:36:31,  1.39s/it]
 10%|▉         | 6051/61904 [2:51:37<22:37:37,  1.46s/it]
 10%|▉         | 6052/61904 [2:51:39<22:08:18,  1.43s/it]
 10%|▉         | 6053/61904 [2:51:40<22:09:35,  1.43s/it]
 10%|▉         | 6054/61904 [2:51:42<22:18:00,  1.44s/it]
 10%|▉         | 6055/61904 [2:51:43<21:53:56,  1.41s/it]
 10%|▉         | 6056/61904 [2:51:45<22:12:00,  1.43s/it]
 10%|▉         | 6057/61904 [2:51:46<22:12:18,  1.43s/it]
 10%|▉         | 6058/61904 [2:51:48<22:45:48,  1.47s/it]
 10%|▉         | 6059/61904 [2:51:49<21:51:16,  1.41s/it]
 10%|▉         | 6060/61904 [2:51:50<21:19:20,  1.37s/it]
                                                         
{'loss': 2.9742, 'learning_rate': 1.9050304680409696e-07, 'epoch': 1.57}

 10%|▉         | 6060/61904 [2:51:50<21:19:20,  1.37s/it]
 10%|▉         | 6061/61904 [2:51:51<21:08:26,  1.36s/it]
 10%|▉         | 6062/61904 [2:51:53<21:24:51,  1.38s/it]
 10%|▉         | 6063/61904 [2:51:54<21:26:30,  1.38s/it]
 10%|▉         | 6064/61904 [2:51:56<22:01:12,  1.42s/it]
 10%|▉         | 6065/61904 [2:51:57<21:45:51,  1.40s/it]
 10%|▉         | 6066/61904 [2:51:58<21:16:37,  1.37s/it]
 10%|▉         | 6067/61904 [2:52:00<21:51:59,  1.41s/it]
 10%|▉         | 6068/61904 [2:52:01<21:49:20,  1.41s/it]
 10%|▉         | 6069/61904 [2:52:03<21:18:51,  1.37s/it]
 10%|▉         | 6070/61904 [2:52:04<21:28:48,  1.38s/it]
 10%|▉         | 6071/61904 [2:52:05<21:05:03,  1.36s/it]
 10%|▉         | 6072/61904 [2:52:07<21:27:32,  1.38s/it]
 10%|▉         | 6073/61904 [2:52:08<20:44:03,  1.34s/it]
 10%|▉         | 6074/61904 [2:52:09<21:04:14,  1.36s/it]
 10%|▉         | 6075/61904 [2:52:11<20:56:41,  1.35s/it]
 10%|▉         | 6076/61904 [2:52:12<20:48:35,  1.34s/it]
 10%|▉         | 6077/61904 [2:52:13<21:05:10,  1.36s/it]
 10%|▉         | 6078/61904 [2:52:15<20:24:56,  1.32s/it]
 10%|▉         | 6079/61904 [2:52:16<20:42:28,  1.34s/it]
 10%|▉         | 6080/61904 [2:52:17<20:39:58,  1.33s/it]
                                                         
{'loss': 3.0092, 'learning_rate': 1.9047063399455464e-07, 'epoch': 1.57}

 10%|▉         | 6080/61904 [2:52:17<20:39:58,  1.33s/it]
 10%|▉         | 6081/61904 [2:52:19<21:42:55,  1.40s/it]
 10%|▉         | 6082/61904 [2:52:20<22:03:07,  1.42s/it]
 10%|▉         | 6083/61904 [2:52:22<21:21:37,  1.38s/it]
 10%|▉         | 6084/61904 [2:52:23<21:31:49,  1.39s/it]
 10%|▉         | 6085/61904 [2:52:24<20:47:04,  1.34s/it]
 10%|▉         | 6086/61904 [2:52:26<20:19:41,  1.31s/it]
 10%|▉         | 6087/61904 [2:52:27<20:41:24,  1.33s/it]
 10%|▉         | 6088/61904 [2:52:28<20:11:46,  1.30s/it]
 10%|▉         | 6089/61904 [2:52:30<20:16:49,  1.31s/it]
 10%|▉         | 6090/61904 [2:52:31<20:32:00,  1.32s/it]
 10%|▉         | 6091/61904 [2:52:32<20:14:53,  1.31s/it]
 10%|▉         | 6092/61904 [2:52:33<20:28:45,  1.32s/it]
 10%|▉         | 6093/61904 [2:52:35<20:12:42,  1.30s/it]
 10%|▉         | 6094/61904 [2:52:36<20:14:32,  1.31s/it]
 10%|▉         | 6095/61904 [2:52:38<20:58:03,  1.35s/it]
 10%|▉         | 6096/61904 [2:52:39<20:46:15,  1.34s/it]
 10%|▉         | 6097/61904 [2:52:40<20:23:50,  1.32s/it]
 10%|▉         | 6098/61904 [2:52:41<20:42:31,  1.34s/it]
 10%|▉         | 6099/61904 [2:52:43<20:17:53,  1.31s/it]
 10%|▉         | 6100/61904 [2:52:44<19:35:37,  1.26s/it]
                                                         
{'loss': 2.9553, 'learning_rate': 1.904382211850123e-07, 'epoch': 1.58}

 10%|▉         | 6100/61904 [2:52:44<19:35:37,  1.26s/it]
 10%|▉         | 6101/61904 [2:52:45<21:11:08,  1.37s/it]
 10%|▉         | 6102/61904 [2:52:47<21:37:26,  1.40s/it]
 10%|▉         | 6103/61904 [2:52:48<21:39:05,  1.40s/it]
 10%|▉         | 6104/61904 [2:52:50<21:03:45,  1.36s/it]
 10%|▉         | 6105/61904 [2:52:51<21:02:24,  1.36s/it]
 10%|▉         | 6106/61904 [2:52:52<21:17:03,  1.37s/it]
 10%|▉         | 6107/61904 [2:52:54<21:33:20,  1.39s/it]
 10%|▉         | 6108/61904 [2:52:55<21:11:13,  1.37s/it]
 10%|▉         | 6109/61904 [2:52:56<20:53:05,  1.35s/it]
 10%|▉         | 6110/61904 [2:52:58<21:11:19,  1.37s/it]
 10%|▉         | 6111/61904 [2:52:59<21:26:15,  1.38s/it]
 10%|▉         | 6112/61904 [2:53:01<21:25:35,  1.38s/it]
 10%|▉         | 6113/61904 [2:53:02<21:11:42,  1.37s/it]
 10%|▉         | 6114/61904 [2:53:03<21:06:02,  1.36s/it]
 10%|▉         | 6115/61904 [2:53:05<21:09:02,  1.36s/it]
 10%|▉         | 6116/61904 [2:53:06<21:15:22,  1.37s/it]
 10%|▉         | 6117/61904 [2:53:07<20:55:11,  1.35s/it]
 10%|▉         | 6118/61904 [2:53:09<20:56:26,  1.35s/it]
 10%|▉         | 6119/61904 [2:53:10<20:43:39,  1.34s/it]
 10%|▉         | 6120/61904 [2:53:12<21:31:15,  1.39s/it]
                                                         
{'loss': 2.8705, 'learning_rate': 1.9040580837546997e-07, 'epoch': 1.58}

 10%|▉         | 6120/61904 [2:53:12<21:31:15,  1.39s/it]
 10%|▉         | 6121/61904 [2:53:13<21:04:01,  1.36s/it]
 10%|▉         | 6122/61904 [2:53:14<20:41:53,  1.34s/it]
 10%|▉         | 6123/61904 [2:53:15<20:48:52,  1.34s/it]
 10%|▉         | 6124/61904 [2:53:17<21:02:41,  1.36s/it]
 10%|▉         | 6125/61904 [2:53:18<20:30:38,  1.32s/it]
 10%|▉         | 6126/61904 [2:53:20<21:45:34,  1.40s/it]
 10%|▉         | 6127/61904 [2:53:21<21:48:32,  1.41s/it]
 10%|▉         | 6128/61904 [2:53:23<21:56:21,  1.42s/it]
 10%|▉         | 6129/61904 [2:53:24<22:11:03,  1.43s/it]
 10%|▉         | 6130/61904 [2:53:25<21:23:32,  1.38s/it]
 10%|▉         | 6131/61904 [2:53:27<21:25:28,  1.38s/it]
 10%|▉         | 6132/61904 [2:53:28<21:14:28,  1.37s/it]
 10%|▉         | 6133/61904 [2:53:29<21:06:11,  1.36s/it]
 10%|▉         | 6134/61904 [2:53:31<20:48:09,  1.34s/it]
 10%|▉         | 6135/61904 [2:53:32<21:58:59,  1.42s/it]
 10%|▉         | 6136/61904 [2:53:33<21:06:21,  1.36s/it]
 10%|▉         | 6137/61904 [2:53:35<20:41:05,  1.34s/it]
 10%|▉         | 6138/61904 [2:53:36<20:53:42,  1.35s/it]
 10%|▉         | 6139/61904 [2:53:38<21:36:40,  1.40s/it]
 10%|▉         | 6140/61904 [2:53:39<21:38:34,  1.40s/it]
                                                         
{'loss': 2.9877, 'learning_rate': 1.9037339556592766e-07, 'epoch': 1.59}

 10%|▉         | 6140/61904 [2:53:39<21:38:34,  1.40s/it]
 10%|▉         | 6141/61904 [2:53:40<21:38:25,  1.40s/it]
 10%|▉         | 6142/61904 [2:53:42<21:14:37,  1.37s/it]
 10%|▉         | 6143/61904 [2:53:43<21:42:18,  1.40s/it]
 10%|▉         | 6144/61904 [2:53:45<21:20:53,  1.38s/it]
 10%|▉         | 6145/61904 [2:53:46<20:44:18,  1.34s/it]
 10%|▉         | 6146/61904 [2:53:47<21:16:06,  1.37s/it]
 10%|▉         | 6147/61904 [2:53:49<21:18:15,  1.38s/it]
 10%|▉         | 6148/61904 [2:53:50<21:13:20,  1.37s/it]
 10%|▉         | 6149/61904 [2:53:52<21:52:03,  1.41s/it]
 10%|▉         | 6150/61904 [2:53:53<22:00:18,  1.42s/it]
 10%|▉         | 6151/61904 [2:53:54<21:06:42,  1.36s/it]
 10%|▉         | 6152/61904 [2:53:55<20:53:14,  1.35s/it]
 10%|▉         | 6153/61904 [2:53:57<21:13:21,  1.37s/it]
 10%|▉         | 6154/61904 [2:53:58<21:00:46,  1.36s/it]
 10%|▉         | 6155/61904 [2:54:00<21:02:33,  1.36s/it]
 10%|▉         | 6156/61904 [2:54:01<20:54:15,  1.35s/it]
 10%|▉         | 6157/61904 [2:54:02<20:47:44,  1.34s/it]
 10%|▉         | 6158/61904 [2:54:04<20:48:48,  1.34s/it]
 10%|▉         | 6159/61904 [2:54:05<21:08:04,  1.36s/it]
 10%|▉         | 6160/61904 [2:54:06<20:23:13,  1.32s/it]
                                                         
{'loss': 2.966, 'learning_rate': 1.9034098275638532e-07, 'epoch': 1.59}

 10%|▉         | 6160/61904 [2:54:06<20:23:13,  1.32s/it]
 10%|▉         | 6161/61904 [2:54:08<20:25:06,  1.32s/it]
 10%|▉         | 6162/61904 [2:54:09<21:10:47,  1.37s/it]
 10%|▉         | 6163/61904 [2:54:10<21:16:24,  1.37s/it]
 10%|▉         | 6164/61904 [2:54:12<20:58:04,  1.35s/it]
 10%|▉         | 6165/61904 [2:54:13<21:30:24,  1.39s/it]
 10%|▉         | 6166/61904 [2:54:15<21:18:46,  1.38s/it]
 10%|▉         | 6167/61904 [2:54:16<21:30:17,  1.39s/it]
 10%|▉         | 6168/61904 [2:54:17<21:09:25,  1.37s/it]
 10%|▉         | 6169/61904 [2:54:19<20:41:30,  1.34s/it]
 10%|▉         | 6170/61904 [2:54:20<21:06:34,  1.36s/it]
 10%|▉         | 6171/61904 [2:54:21<20:52:44,  1.35s/it]
 10%|▉         | 6172/61904 [2:54:23<20:51:34,  1.35s/it]
 10%|▉         | 6173/61904 [2:54:24<20:32:54,  1.33s/it]
 10%|▉         | 6174/61904 [2:54:25<20:28:23,  1.32s/it]
 10%|▉         | 6175/61904 [2:54:27<20:31:32,  1.33s/it]
 10%|▉         | 6176/61904 [2:54:28<20:47:57,  1.34s/it]
 10%|▉         | 6177/61904 [2:54:29<20:42:06,  1.34s/it]
 10%|▉         | 6178/61904 [2:54:31<20:22:46,  1.32s/it]
 10%|▉         | 6179/61904 [2:54:32<19:58:17,  1.29s/it]
 10%|▉         | 6180/61904 [2:54:33<19:48:35,  1.28s/it]
                                                         
{'loss': 2.9414, 'learning_rate': 1.9030856994684298e-07, 'epoch': 1.6}

 10%|▉         | 6180/61904 [2:54:33<19:48:35,  1.28s/it]
 10%|▉         | 6181/61904 [2:54:34<20:30:48,  1.33s/it]
 10%|▉         | 6182/61904 [2:54:36<20:54:09,  1.35s/it]
 10%|▉         | 6183/61904 [2:54:37<20:58:42,  1.36s/it]
 10%|▉         | 6184/61904 [2:54:39<20:56:56,  1.35s/it]
 10%|▉         | 6185/61904 [2:54:40<20:49:03,  1.35s/it]
 10%|▉         | 6186/61904 [2:54:41<20:22:00,  1.32s/it]
 10%|▉         | 6187/61904 [2:54:43<20:36:07,  1.33s/it]
 10%|▉         | 6188/61904 [2:54:44<20:30:17,  1.32s/it]
 10%|▉         | 6189/61904 [2:54:45<20:19:51,  1.31s/it]
 10%|▉         | 6190/61904 [2:54:46<20:16:26,  1.31s/it]
 10%|█         | 6191/61904 [2:54:48<20:01:42,  1.29s/it]
 10%|█         | 6192/61904 [2:54:49<20:05:57,  1.30s/it]
 10%|█         | 6193/61904 [2:54:50<20:33:08,  1.33s/it]
 10%|█         | 6194/61904 [2:54:52<20:07:16,  1.30s/it]
 10%|█         | 6195/61904 [2:54:53<20:19:04,  1.31s/it]
 10%|█         | 6196/61904 [2:54:54<21:03:23,  1.36s/it]
 10%|█         | 6197/61904 [2:54:56<20:51:15,  1.35s/it]
 10%|█         | 6198/61904 [2:54:57<21:08:22,  1.37s/it]
 10%|█         | 6199/61904 [2:54:58<20:38:29,  1.33s/it]
 10%|█         | 6200/61904 [2:55:00<20:33:11,  1.33s/it]
                                                         
{'loss': 2.9618, 'learning_rate': 1.9027615713730067e-07, 'epoch': 1.6}

 10%|█         | 6200/61904 [2:55:00<20:33:11,  1.33s/it]
 10%|█         | 6201/61904 [2:55:01<20:40:45,  1.34s/it]
 10%|█         | 6202/61904 [2:55:02<20:49:39,  1.35s/it]
 10%|█         | 6203/61904 [2:55:04<21:37:26,  1.40s/it]
 10%|█         | 6204/61904 [2:55:05<21:59:57,  1.42s/it]
 10%|█         | 6205/61904 [2:55:07<21:54:32,  1.42s/it]
 10%|█         | 6206/61904 [2:55:08<22:01:37,  1.42s/it]
 10%|█         | 6207/61904 [2:55:10<21:25:23,  1.38s/it]
 10%|█         | 6208/61904 [2:55:11<21:37:58,  1.40s/it]
 10%|█         | 6209/61904 [2:55:12<21:13:53,  1.37s/it]
 10%|█         | 6210/61904 [2:55:14<21:14:01,  1.37s/it]
 10%|█         | 6211/61904 [2:55:15<20:26:59,  1.32s/it]
 10%|█         | 6212/61904 [2:55:16<21:10:14,  1.37s/it]
 10%|█         | 6213/61904 [2:55:18<21:06:55,  1.36s/it]
 10%|█         | 6214/61904 [2:55:19<21:27:30,  1.39s/it]
 10%|█         | 6215/61904 [2:55:20<21:04:45,  1.36s/it]
 10%|█         | 6216/61904 [2:55:22<21:11:47,  1.37s/it]
 10%|█         | 6217/61904 [2:55:23<20:42:47,  1.34s/it]
 10%|█         | 6218/61904 [2:55:25<21:17:59,  1.38s/it]
 10%|█         | 6219/61904 [2:55:26<21:14:09,  1.37s/it]
 10%|█         | 6220/61904 [2:55:27<20:54:05,  1.35s/it]
                                                         
{'loss': 2.9328, 'learning_rate': 1.902437443277583e-07, 'epoch': 1.61}

 10%|█         | 6220/61904 [2:55:27<20:54:05,  1.35s/it]
 10%|█         | 6221/61904 [2:55:29<21:12:10,  1.37s/it]
 10%|█         | 6222/61904 [2:55:30<20:43:35,  1.34s/it]
 10%|█         | 6223/61904 [2:55:31<20:33:07,  1.33s/it]
 10%|█         | 6224/61904 [2:55:33<20:42:15,  1.34s/it]
 10%|█         | 6225/61904 [2:55:34<21:36:44,  1.40s/it]
 10%|█         | 6226/61904 [2:55:35<21:12:55,  1.37s/it]
 10%|█         | 6227/61904 [2:55:37<20:51:00,  1.35s/it]
 10%|█         | 6228/61904 [2:55:38<20:56:31,  1.35s/it]
 10%|█         | 6229/61904 [2:55:39<20:23:55,  1.32s/it]
 10%|█         | 6230/61904 [2:55:41<20:59:40,  1.36s/it]
 10%|█         | 6231/61904 [2:55:42<20:19:06,  1.31s/it]
 10%|█         | 6232/61904 [2:55:43<20:39:34,  1.34s/it]
 10%|█         | 6233/61904 [2:55:45<20:13:43,  1.31s/it]
 10%|█         | 6234/61904 [2:55:46<21:58:55,  1.42s/it]
 10%|█         | 6235/61904 [2:55:48<22:12:13,  1.44s/it]
 10%|█         | 6236/61904 [2:55:49<21:39:31,  1.40s/it]
 10%|█         | 6237/61904 [2:55:50<21:06:01,  1.36s/it]
 10%|█         | 6238/61904 [2:55:52<21:23:24,  1.38s/it]
 10%|█         | 6239/61904 [2:55:53<21:40:31,  1.40s/it]
 10%|█         | 6240/61904 [2:55:55<22:06:13,  1.43s/it]
                                                         
{'loss': 2.8855, 'learning_rate': 1.90211331518216e-07, 'epoch': 1.61}

 10%|█         | 6240/61904 [2:55:55<22:06:13,  1.43s/it]
 10%|█         | 6241/61904 [2:55:56<21:35:14,  1.40s/it]
 10%|█         | 6242/61904 [2:55:58<21:45:36,  1.41s/it]
 10%|█         | 6243/61904 [2:55:59<21:42:47,  1.40s/it]
 10%|█         | 6244/61904 [2:56:00<21:36:33,  1.40s/it]
 10%|█         | 6245/61904 [2:56:02<22:05:34,  1.43s/it]
 10%|█         | 6246/61904 [2:56:03<22:22:42,  1.45s/it]
 10%|█         | 6247/61904 [2:56:05<21:54:30,  1.42s/it]
 10%|█         | 6248/61904 [2:56:06<21:26:41,  1.39s/it]
 10%|█         | 6249/61904 [2:56:07<21:01:58,  1.36s/it]
 10%|█         | 6250/61904 [2:56:09<20:36:20,  1.33s/it]
 10%|█         | 6251/61904 [2:56:10<20:57:29,  1.36s/it]
 10%|█         | 6252/61904 [2:56:11<21:46:04,  1.41s/it]
 10%|█         | 6253/61904 [2:56:13<21:16:13,  1.38s/it]
 10%|█         | 6254/61904 [2:56:14<21:25:12,  1.39s/it]
 10%|█         | 6255/61904 [2:56:16<21:21:05,  1.38s/it]
 10%|█         | 6256/61904 [2:56:17<21:16:44,  1.38s/it]
 10%|█         | 6257/61904 [2:56:18<21:25:25,  1.39s/it]
 10%|█         | 6258/61904 [2:56:20<21:13:44,  1.37s/it]
 10%|█         | 6259/61904 [2:56:21<21:25:53,  1.39s/it]
 10%|█         | 6260/61904 [2:56:22<21:25:28,  1.39s/it]
                                                         
{'loss': 2.9168, 'learning_rate': 1.9017891870867368e-07, 'epoch': 1.62}

 10%|█         | 6260/61904 [2:56:22<21:25:28,  1.39s/it]
 10%|█         | 6261/61904 [2:56:24<21:22:08,  1.38s/it]
 10%|█         | 6262/61904 [2:56:25<20:38:49,  1.34s/it]
 10%|█         | 6263/61904 [2:56:26<20:36:44,  1.33s/it]
 10%|█         | 6264/61904 [2:56:28<21:59:09,  1.42s/it]
 10%|█         | 6265/61904 [2:56:29<21:38:46,  1.40s/it]
 10%|█         | 6266/61904 [2:56:31<21:22:16,  1.38s/it]
 10%|█         | 6267/61904 [2:56:32<21:04:27,  1.36s/it]
 10%|█         | 6268/61904 [2:56:33<20:29:54,  1.33s/it]
 10%|█         | 6269/61904 [2:56:35<21:04:56,  1.36s/it]
 10%|█         | 6270/61904 [2:56:36<21:27:14,  1.39s/it]
 10%|█         | 6271/61904 [2:56:38<22:29:54,  1.46s/it]
 10%|█         | 6272/61904 [2:56:39<23:09:42,  1.50s/it]
 10%|█         | 6273/61904 [2:56:41<22:55:49,  1.48s/it]
 10%|█         | 6274/61904 [2:56:42<22:33:32,  1.46s/it]
 10%|█         | 6275/61904 [2:56:44<22:04:45,  1.43s/it]
 10%|█         | 6276/61904 [2:56:45<22:28:14,  1.45s/it]
 10%|█         | 6277/61904 [2:56:46<22:01:34,  1.43s/it]
 10%|█         | 6278/61904 [2:56:48<21:26:26,  1.39s/it]
 10%|█         | 6279/61904 [2:56:49<21:03:49,  1.36s/it]
 10%|█         | 6280/61904 [2:56:50<20:52:42,  1.35s/it]
                                                         
{'loss': 2.9443, 'learning_rate': 1.9014650589913132e-07, 'epoch': 1.62}

 10%|█         | 6280/61904 [2:56:50<20:52:42,  1.35s/it]
 10%|█         | 6281/61904 [2:56:52<20:57:45,  1.36s/it]
 10%|█         | 6282/61904 [2:56:53<20:51:39,  1.35s/it]
 10%|█         | 6283/61904 [2:56:54<20:48:16,  1.35s/it]
 10%|█         | 6284/61904 [2:56:56<21:41:51,  1.40s/it]
 10%|█         | 6285/61904 [2:56:57<21:30:21,  1.39s/it]
 10%|█         | 6286/61904 [2:56:59<21:35:54,  1.40s/it]
 10%|█         | 6287/61904 [2:57:00<21:01:43,  1.36s/it]
 10%|█         | 6288/61904 [2:57:01<20:58:24,  1.36s/it]
 10%|█         | 6289/61904 [2:57:03<20:34:13,  1.33s/it]
 10%|█         | 6290/61904 [2:57:04<20:42:21,  1.34s/it]
 10%|█         | 6291/61904 [2:57:05<21:12:41,  1.37s/it]
 10%|█         | 6292/61904 [2:57:07<20:59:52,  1.36s/it]
 10%|█         | 6293/61904 [2:57:08<20:26:57,  1.32s/it]
 10%|█         | 6294/61904 [2:57:09<20:31:40,  1.33s/it]
 10%|█         | 6295/61904 [2:57:11<20:47:38,  1.35s/it]
 10%|█         | 6296/61904 [2:57:12<20:24:44,  1.32s/it]
 10%|█         | 6297/61904 [2:57:13<20:36:11,  1.33s/it]
 10%|█         | 6298/61904 [2:57:15<21:04:13,  1.36s/it]
 10%|█         | 6299/61904 [2:57:16<21:06:23,  1.37s/it]
 10%|█         | 6300/61904 [2:57:18<20:56:29,  1.36s/it]
                                                         
{'loss': 2.9139, 'learning_rate': 1.90114093089589e-07, 'epoch': 1.63}

 10%|█         | 6300/61904 [2:57:18<20:56:29,  1.36s/it]
 10%|█         | 6301/61904 [2:57:19<20:54:59,  1.35s/it]
 10%|█         | 6302/61904 [2:57:20<20:47:43,  1.35s/it]
 10%|█         | 6303/61904 [2:57:21<20:32:46,  1.33s/it]
 10%|█         | 6304/61904 [2:57:23<20:39:14,  1.34s/it]
 10%|█         | 6305/61904 [2:57:24<20:38:02,  1.34s/it]
 10%|█         | 6306/61904 [2:57:26<21:12:05,  1.37s/it]
 10%|█         | 6307/61904 [2:57:27<21:26:41,  1.39s/it]
 10%|█         | 6308/61904 [2:57:28<20:55:40,  1.36s/it]
 10%|█         | 6309/61904 [2:57:30<21:16:18,  1.38s/it]
 10%|█         | 6310/61904 [2:57:31<21:10:34,  1.37s/it]
 10%|█         | 6311/61904 [2:57:32<20:46:49,  1.35s/it]
 10%|█         | 6312/61904 [2:57:34<20:36:51,  1.33s/it]
 10%|█         | 6313/61904 [2:57:35<20:27:37,  1.32s/it]
 10%|█         | 6314/61904 [2:57:36<20:28:43,  1.33s/it]
 10%|█         | 6315/61904 [2:57:38<20:56:52,  1.36s/it]
 10%|█         | 6316/61904 [2:57:39<21:23:24,  1.39s/it]
 10%|█         | 6317/61904 [2:57:41<21:28:20,  1.39s/it]
 10%|█         | 6318/61904 [2:57:42<21:38:22,  1.40s/it]
 10%|█         | 6319/61904 [2:57:43<21:32:04,  1.39s/it]
 10%|█         | 6320/61904 [2:57:45<21:25:49,  1.39s/it]
                                                         
{'loss': 2.9343, 'learning_rate': 1.9008168028004667e-07, 'epoch': 1.63}

 10%|█         | 6320/61904 [2:57:45<21:25:49,  1.39s/it]
 10%|█         | 6321/61904 [2:57:46<21:06:33,  1.37s/it]
 10%|█         | 6322/61904 [2:57:48<21:23:09,  1.39s/it]
 10%|█         | 6323/61904 [2:57:49<21:00:10,  1.36s/it]
 10%|█         | 6324/61904 [2:57:50<20:46:26,  1.35s/it]
 10%|█         | 6325/61904 [2:57:51<20:44:02,  1.34s/it]
 10%|█         | 6326/61904 [2:57:53<20:32:38,  1.33s/it]
 10%|█         | 6327/61904 [2:57:54<20:54:56,  1.35s/it]
 10%|█         | 6328/61904 [2:57:56<20:44:23,  1.34s/it]
 10%|█         | 6329/61904 [2:57:57<20:29:04,  1.33s/it]
 10%|█         | 6330/61904 [2:57:58<20:12:45,  1.31s/it]
 10%|█         | 6331/61904 [2:58:00<20:46:09,  1.35s/it]
 10%|█         | 6332/61904 [2:58:01<21:01:34,  1.36s/it]
 10%|█         | 6333/61904 [2:58:02<21:02:03,  1.36s/it]
 10%|█         | 6334/61904 [2:58:04<20:30:16,  1.33s/it]
 10%|█         | 6335/61904 [2:58:05<20:37:00,  1.34s/it]
 10%|█         | 6336/61904 [2:58:06<20:28:34,  1.33s/it]
 10%|█         | 6337/61904 [2:58:08<20:37:16,  1.34s/it]
 10%|█         | 6338/61904 [2:58:09<20:39:36,  1.34s/it]
 10%|█         | 6339/61904 [2:58:10<21:27:38,  1.39s/it]
 10%|█         | 6340/61904 [2:58:12<21:05:05,  1.37s/it]
                                                         
{'loss': 2.9279, 'learning_rate': 1.9004926747050433e-07, 'epoch': 1.64}

 10%|█         | 6340/61904 [2:58:12<21:05:05,  1.37s/it]
 10%|█         | 6341/61904 [2:58:13<21:18:03,  1.38s/it]
 10%|█         | 6342/61904 [2:58:15<21:40:15,  1.40s/it]
 10%|█         | 6343/61904 [2:58:16<21:30:43,  1.39s/it]
 10%|█         | 6344/61904 [2:58:17<21:26:41,  1.39s/it]
 10%|█         | 6345/61904 [2:58:19<21:21:01,  1.38s/it]
 10%|█         | 6346/61904 [2:58:20<21:08:33,  1.37s/it]
 10%|█         | 6347/61904 [2:58:21<20:44:34,  1.34s/it]
 10%|█         | 6348/61904 [2:58:23<20:31:43,  1.33s/it]
 10%|█         | 6349/61904 [2:58:24<20:59:32,  1.36s/it]
 10%|█         | 6350/61904 [2:58:25<20:58:16,  1.36s/it]
 10%|█         | 6351/61904 [2:58:27<20:57:12,  1.36s/it]
 10%|█         | 6352/61904 [2:58:28<21:06:45,  1.37s/it]
 10%|█         | 6353/61904 [2:58:30<21:34:38,  1.40s/it]
 10%|█         | 6354/61904 [2:58:31<21:39:53,  1.40s/it]
 10%|█         | 6355/61904 [2:58:32<21:14:09,  1.38s/it]
 10%|█         | 6356/61904 [2:58:34<21:19:37,  1.38s/it]
 10%|█         | 6357/61904 [2:58:35<20:52:50,  1.35s/it]
 10%|█         | 6358/61904 [2:58:36<21:01:38,  1.36s/it]
 10%|█         | 6359/61904 [2:58:38<20:46:41,  1.35s/it]
 10%|█         | 6360/61904 [2:58:39<21:48:31,  1.41s/it]
                                                         
{'loss': 2.8902, 'learning_rate': 1.9001685466096202e-07, 'epoch': 1.64}

 10%|█         | 6360/61904 [2:58:39<21:48:31,  1.41s/it]
 10%|█         | 6361/61904 [2:58:41<21:45:57,  1.41s/it]
 10%|█         | 6362/61904 [2:58:42<21:19:06,  1.38s/it]
 10%|█         | 6363/61904 [2:58:43<21:08:53,  1.37s/it]
 10%|█         | 6364/61904 [2:58:45<20:40:23,  1.34s/it]
 10%|█         | 6365/61904 [2:58:46<20:30:21,  1.33s/it]
 10%|█         | 6366/61904 [2:58:47<20:35:32,  1.33s/it]
 10%|█         | 6367/61904 [2:58:49<20:55:04,  1.36s/it]
 10%|█         | 6368/61904 [2:58:50<21:37:51,  1.40s/it]
 10%|█         | 6369/61904 [2:58:52<21:49:28,  1.41s/it]
 10%|█         | 6370/61904 [2:58:53<21:31:39,  1.40s/it]
 10%|█         | 6371/61904 [2:58:54<21:04:06,  1.37s/it]
 10%|█         | 6372/61904 [2:58:56<21:14:46,  1.38s/it]
 10%|█         | 6373/61904 [2:58:57<21:38:13,  1.40s/it]
 10%|█         | 6374/61904 [2:58:58<21:18:26,  1.38s/it]
 10%|█         | 6375/61904 [2:59:00<21:40:44,  1.41s/it]
 10%|█         | 6376/61904 [2:59:02<22:22:30,  1.45s/it]
 10%|█         | 6377/61904 [2:59:03<21:50:17,  1.42s/it]
 10%|█         | 6378/61904 [2:59:04<22:22:00,  1.45s/it]
 10%|█         | 6379/61904 [2:59:06<21:55:53,  1.42s/it]
 10%|█         | 6380/61904 [2:59:07<21:53:37,  1.42s/it]
                                                         
{'loss': 2.9188, 'learning_rate': 1.8998444185141968e-07, 'epoch': 1.65}

 10%|█         | 6380/61904 [2:59:07<21:53:37,  1.42s/it]
 10%|█         | 6381/61904 [2:59:09<21:38:50,  1.40s/it]
 10%|█         | 6382/61904 [2:59:10<22:17:42,  1.45s/it]
 10%|█         | 6383/61904 [2:59:11<22:09:22,  1.44s/it]
 10%|█         | 6384/61904 [2:59:13<21:33:52,  1.40s/it]
 10%|█         | 6385/61904 [2:59:14<21:23:45,  1.39s/it]
 10%|█         | 6386/61904 [2:59:15<21:14:09,  1.38s/it]
 10%|█         | 6387/61904 [2:59:17<20:47:23,  1.35s/it]
 10%|█         | 6388/61904 [2:59:18<21:35:24,  1.40s/it]
 10%|█         | 6389/61904 [2:59:20<21:49:52,  1.42s/it]
 10%|█         | 6390/61904 [2:59:21<21:09:06,  1.37s/it]
 10%|█         | 6391/61904 [2:59:22<21:32:09,  1.40s/it]
 10%|█         | 6392/61904 [2:59:24<21:25:56,  1.39s/it]
 10%|█         | 6393/61904 [2:59:25<20:46:48,  1.35s/it]
 10%|█         | 6394/61904 [2:59:27<21:05:22,  1.37s/it]
 10%|█         | 6395/61904 [2:59:28<20:47:13,  1.35s/it]
 10%|█         | 6396/61904 [2:59:29<21:14:32,  1.38s/it]
 10%|█         | 6397/61904 [2:59:31<21:47:56,  1.41s/it]
 10%|█         | 6398/61904 [2:59:32<22:33:09,  1.46s/it]
 10%|█         | 6399/61904 [2:59:34<23:14:31,  1.51s/it]
 10%|█         | 6400/61904 [2:59:35<21:59:50,  1.43s/it]
                                                         
{'loss': 2.9314, 'learning_rate': 1.8995202904187734e-07, 'epoch': 1.65}

 10%|█         | 6400/61904 [2:59:35<21:59:50,  1.43s/it]
 10%|█         | 6401/61904 [2:59:37<23:25:50,  1.52s/it]
 10%|█         | 6402/61904 [2:59:38<22:31:47,  1.46s/it]
 10%|█         | 6403/61904 [2:59:40<22:37:04,  1.47s/it]
 10%|█         | 6404/61904 [2:59:41<22:25:25,  1.45s/it]
 10%|█         | 6405/61904 [2:59:43<22:03:06,  1.43s/it]
 10%|█         | 6406/61904 [2:59:44<21:55:02,  1.42s/it]
 10%|█         | 6407/61904 [2:59:45<21:44:45,  1.41s/it]
 10%|█         | 6408/61904 [2:59:47<21:35:56,  1.40s/it]
 10%|█         | 6409/61904 [2:59:48<21:31:58,  1.40s/it]
 10%|█         | 6410/61904 [2:59:49<21:25:55,  1.39s/it]
 10%|█         | 6411/61904 [2:59:51<22:16:21,  1.44s/it]
 10%|█         | 6412/61904 [2:59:52<21:23:05,  1.39s/it]
 10%|█         | 6413/61904 [2:59:54<21:13:43,  1.38s/it]
 10%|█         | 6414/61904 [2:59:55<21:52:36,  1.42s/it]
 10%|█         | 6415/61904 [2:59:56<21:06:46,  1.37s/it]
 10%|█         | 6416/61904 [2:59:58<21:09:24,  1.37s/it]
 10%|█         | 6417/61904 [2:59:59<21:08:43,  1.37s/it]
 10%|█         | 6418/61904 [3:00:01<21:18:52,  1.38s/it]
 10%|█         | 6419/61904 [3:00:02<21:21:27,  1.39s/it]
 10%|█         | 6420/61904 [3:00:03<20:41:14,  1.34s/it]
                                                         
{'loss': 2.9729, 'learning_rate': 1.8991961623233503e-07, 'epoch': 1.66}

 10%|█         | 6420/61904 [3:00:03<20:41:14,  1.34s/it]
 10%|█         | 6421/61904 [3:00:05<20:38:18,  1.34s/it]
 10%|█         | 6422/61904 [3:00:06<22:02:41,  1.43s/it]
 10%|█         | 6423/61904 [3:00:08<21:57:42,  1.43s/it]
 10%|█         | 6424/61904 [3:00:09<21:38:33,  1.40s/it]
 10%|█         | 6425/61904 [3:00:10<20:48:41,  1.35s/it]
 10%|█         | 6426/61904 [3:00:12<20:54:15,  1.36s/it]
 10%|█         | 6427/61904 [3:00:13<21:25:03,  1.39s/it]
 10%|█         | 6428/61904 [3:00:14<21:21:43,  1.39s/it]
 10%|█         | 6429/61904 [3:00:16<22:21:09,  1.45s/it]
 10%|█         | 6430/61904 [3:00:17<21:42:02,  1.41s/it]
 10%|█         | 6431/61904 [3:00:19<21:50:06,  1.42s/it]
 10%|█         | 6432/61904 [3:00:20<22:10:18,  1.44s/it]
 10%|█         | 6433/61904 [3:00:22<22:22:34,  1.45s/it]
 10%|█         | 6434/61904 [3:00:23<22:04:31,  1.43s/it]
 10%|█         | 6435/61904 [3:00:25<22:11:22,  1.44s/it]
 10%|█         | 6436/61904 [3:00:26<21:30:52,  1.40s/it]
 10%|█         | 6437/61904 [3:00:27<21:35:43,  1.40s/it]
 10%|█         | 6438/61904 [3:00:29<21:50:07,  1.42s/it]
 10%|█         | 6439/61904 [3:00:30<21:25:01,  1.39s/it]
 10%|█         | 6440/61904 [3:00:31<21:35:14,  1.40s/it]
                                                         
{'loss': 2.9336, 'learning_rate': 1.8988720342279266e-07, 'epoch': 1.66}

 10%|█         | 6440/61904 [3:00:31<21:35:14,  1.40s/it]
 10%|█         | 6441/61904 [3:00:33<21:43:44,  1.41s/it]
 10%|█         | 6442/61904 [3:00:34<21:20:29,  1.39s/it]
 10%|█         | 6443/61904 [3:00:36<21:45:50,  1.41s/it]
 10%|█         | 6444/61904 [3:00:37<21:45:29,  1.41s/it]
 10%|█         | 6445/61904 [3:00:38<21:23:55,  1.39s/it]
 10%|█         | 6446/61904 [3:00:40<21:53:33,  1.42s/it]
 10%|█         | 6447/61904 [3:00:41<21:31:55,  1.40s/it]
 10%|█         | 6448/61904 [3:00:43<21:00:01,  1.36s/it]
 10%|█         | 6449/61904 [3:00:44<21:03:11,  1.37s/it]
 10%|█         | 6450/61904 [3:00:45<21:26:23,  1.39s/it]
 10%|█         | 6451/61904 [3:00:47<21:29:53,  1.40s/it]
 10%|█         | 6452/61904 [3:00:48<21:30:38,  1.40s/it]
 10%|█         | 6453/61904 [3:00:50<22:28:26,  1.46s/it]
 10%|█         | 6454/61904 [3:00:51<21:57:14,  1.43s/it]
 10%|█         | 6455/61904 [3:00:52<21:25:30,  1.39s/it]
 10%|█         | 6456/61904 [3:00:54<21:32:14,  1.40s/it]
 10%|█         | 6457/61904 [3:00:55<22:02:46,  1.43s/it]
 10%|█         | 6458/61904 [3:00:57<21:50:10,  1.42s/it]
 10%|█         | 6459/61904 [3:00:58<21:54:09,  1.42s/it]
 10%|█         | 6460/61904 [3:01:00<21:39:27,  1.41s/it]
                                                         
{'loss': 2.9242, 'learning_rate': 1.8985479061325035e-07, 'epoch': 1.67}

 10%|█         | 6460/61904 [3:01:00<21:39:27,  1.41s/it]
 10%|█         | 6461/61904 [3:01:01<22:44:08,  1.48s/it]
 10%|█         | 6462/61904 [3:01:03<21:59:07,  1.43s/it]
 10%|█         | 6463/61904 [3:01:04<22:08:47,  1.44s/it]
 10%|█         | 6464/61904 [3:01:05<21:35:41,  1.40s/it]
 10%|█         | 6465/61904 [3:01:07<21:26:32,  1.39s/it]
 10%|█         | 6466/61904 [3:01:08<21:13:07,  1.38s/it]
 10%|█         | 6467/61904 [3:01:09<20:54:00,  1.36s/it]
 10%|█         | 6468/61904 [3:01:11<21:07:13,  1.37s/it]
 10%|█         | 6469/61904 [3:01:12<21:36:09,  1.40s/it]
 10%|█         | 6470/61904 [3:01:14<22:01:50,  1.43s/it]
 10%|█         | 6471/61904 [3:01:15<22:06:36,  1.44s/it]
 10%|█         | 6472/61904 [3:01:16<21:33:42,  1.40s/it]
 10%|█         | 6473/61904 [3:01:18<21:35:05,  1.40s/it]
 10%|█         | 6474/61904 [3:01:19<21:29:23,  1.40s/it]
 10%|█         | 6475/61904 [3:01:21<21:19:37,  1.39s/it]
 10%|█         | 6476/61904 [3:01:22<21:10:33,  1.38s/it]
 10%|█         | 6477/61904 [3:01:23<21:03:04,  1.37s/it]
 10%|█         | 6478/61904 [3:01:25<21:24:52,  1.39s/it]
 10%|█         | 6479/61904 [3:01:26<21:33:02,  1.40s/it]
 10%|█         | 6480/61904 [3:01:28<21:14:08,  1.38s/it]
                                                         
{'loss': 3.0066, 'learning_rate': 1.8982237780370804e-07, 'epoch': 1.67}

 10%|█         | 6480/61904 [3:01:28<21:14:08,  1.38s/it]
 10%|█         | 6481/61904 [3:01:29<21:24:18,  1.39s/it]
 10%|█         | 6482/61904 [3:01:30<21:11:12,  1.38s/it]
 10%|█         | 6483/61904 [3:01:31<20:29:29,  1.33s/it]
 10%|█         | 6484/61904 [3:01:33<20:11:10,  1.31s/it]
 10%|█         | 6485/61904 [3:01:34<20:39:19,  1.34s/it]
 10%|█         | 6486/61904 [3:01:36<20:55:46,  1.36s/it]
 10%|█         | 6487/61904 [3:01:37<21:21:37,  1.39s/it]
 10%|█         | 6488/61904 [3:01:38<21:44:11,  1.41s/it]
 10%|█         | 6489/61904 [3:01:40<21:36:14,  1.40s/it]
 10%|█         | 6490/61904 [3:01:41<21:12:16,  1.38s/it]
 10%|█         | 6491/61904 [3:01:43<21:18:05,  1.38s/it]
 10%|█         | 6492/61904 [3:01:44<21:26:34,  1.39s/it]
 10%|█         | 6493/61904 [3:01:45<21:19:38,  1.39s/it]
 10%|█         | 6494/61904 [3:01:47<21:42:10,  1.41s/it]
 10%|█         | 6495/61904 [3:01:48<21:19:13,  1.39s/it]
 10%|█         | 6496/61904 [3:01:50<21:13:34,  1.38s/it]
 10%|█         | 6497/61904 [3:01:51<21:23:34,  1.39s/it]
 10%|█         | 6498/61904 [3:01:52<20:59:12,  1.36s/it]
 10%|█         | 6499/61904 [3:01:54<20:39:46,  1.34s/it]
 11%|█         | 6500/61904 [3:01:55<20:22:53,  1.32s/it]
                                                         
{'loss': 2.9272, 'learning_rate': 1.8978996499416568e-07, 'epoch': 1.68}

 11%|█         | 6500/61904 [3:01:55<20:22:53,  1.32s/it]
 11%|█         | 6501/61904 [3:01:56<21:35:38,  1.40s/it]
 11%|█         | 6502/61904 [3:01:58<22:04:59,  1.43s/it]
 11%|█         | 6503/61904 [3:01:59<21:59:08,  1.43s/it]
 11%|█         | 6504/61904 [3:02:01<21:24:07,  1.39s/it]
 11%|█         | 6505/61904 [3:02:02<21:31:15,  1.40s/it]
 11%|█         | 6506/61904 [3:02:03<21:10:50,  1.38s/it]
 11%|█         | 6507/61904 [3:02:05<21:33:53,  1.40s/it]
 11%|█         | 6508/61904 [3:02:06<20:54:40,  1.36s/it]
 11%|█         | 6509/61904 [3:02:07<20:48:22,  1.35s/it]
 11%|█         | 6510/61904 [3:02:09<21:02:43,  1.37s/it]
 11%|█         | 6511/61904 [3:02:10<21:15:49,  1.38s/it]
 11%|█         | 6512/61904 [3:02:12<21:10:31,  1.38s/it]
 11%|█         | 6513/61904 [3:02:13<21:11:12,  1.38s/it]
 11%|█         | 6514/61904 [3:02:15<21:53:03,  1.42s/it]
 11%|█         | 6515/61904 [3:02:16<21:39:27,  1.41s/it]
 11%|█         | 6516/61904 [3:02:17<21:15:50,  1.38s/it]
 11%|█         | 6517/61904 [3:02:19<21:28:50,  1.40s/it]
 11%|█         | 6518/61904 [3:02:20<20:42:49,  1.35s/it]
 11%|█         | 6519/61904 [3:02:21<21:19:27,  1.39s/it]
 11%|█         | 6520/61904 [3:02:23<21:24:39,  1.39s/it]
                                                         
{'loss': 2.8841, 'learning_rate': 1.8975755218462336e-07, 'epoch': 1.68}

 11%|█         | 6520/61904 [3:02:23<21:24:39,  1.39s/it]
 11%|█         | 6521/61904 [3:02:24<21:33:09,  1.40s/it]
 11%|█         | 6522/61904 [3:02:26<21:38:36,  1.41s/it]
 11%|█         | 6523/61904 [3:02:27<21:46:11,  1.42s/it]
 11%|█         | 6524/61904 [3:02:28<21:43:55,  1.41s/it]
 11%|█         | 6525/61904 [3:02:30<20:56:10,  1.36s/it]
 11%|█         | 6526/61904 [3:02:31<21:39:37,  1.41s/it]
 11%|█         | 6527/61904 [3:02:33<22:02:13,  1.43s/it]
 11%|█         | 6528/61904 [3:02:34<21:41:57,  1.41s/it]
 11%|█         | 6529/61904 [3:02:35<21:23:04,  1.39s/it]
 11%|█         | 6530/61904 [3:02:37<21:34:00,  1.40s/it]
 11%|█         | 6531/61904 [3:02:38<21:30:12,  1.40s/it]
 11%|█         | 6532/61904 [3:02:40<22:02:39,  1.43s/it]
 11%|█         | 6533/61904 [3:02:41<21:35:00,  1.40s/it]
 11%|█         | 6534/61904 [3:02:43<21:49:34,  1.42s/it]
 11%|█         | 6535/61904 [3:02:44<21:36:14,  1.40s/it]
 11%|█         | 6536/61904 [3:02:45<21:08:11,  1.37s/it]
 11%|█         | 6537/61904 [3:02:46<20:43:17,  1.35s/it]
 11%|█         | 6538/61904 [3:02:48<21:05:55,  1.37s/it]
 11%|█         | 6539/61904 [3:02:49<20:39:12,  1.34s/it]
 11%|█         | 6540/61904 [3:02:51<20:41:07,  1.35s/it]
                                                         
{'loss': 2.9365, 'learning_rate': 1.8972513937508103e-07, 'epoch': 1.69}

 11%|█         | 6540/61904 [3:02:51<20:41:07,  1.35s/it]
 11%|█         | 6541/61904 [3:02:52<21:24:55,  1.39s/it]
 11%|█         | 6542/61904 [3:02:54<22:00:30,  1.43s/it]
 11%|█         | 6543/61904 [3:02:55<22:09:29,  1.44s/it]
 11%|█         | 6544/61904 [3:02:56<21:58:23,  1.43s/it]
 11%|█         | 6545/61904 [3:02:58<21:55:42,  1.43s/it]
 11%|█         | 6546/61904 [3:02:59<21:29:12,  1.40s/it]
 11%|█         | 6547/61904 [3:03:01<21:27:09,  1.40s/it]
 11%|█         | 6548/61904 [3:03:02<21:12:01,  1.38s/it]
 11%|█         | 6549/61904 [3:03:03<20:30:46,  1.33s/it]
 11%|█         | 6550/61904 [3:03:05<20:40:39,  1.34s/it]
 11%|█         | 6551/61904 [3:03:06<21:24:47,  1.39s/it]
 11%|█         | 6552/61904 [3:03:07<21:11:47,  1.38s/it]
 11%|█         | 6553/61904 [3:03:09<21:41:25,  1.41s/it]
 11%|█         | 6554/61904 [3:03:10<20:59:14,  1.37s/it]
 11%|█         | 6555/61904 [3:03:11<20:33:06,  1.34s/it]
 11%|█         | 6556/61904 [3:03:13<20:33:51,  1.34s/it]
 11%|█         | 6557/61904 [3:03:14<20:33:22,  1.34s/it]
 11%|█         | 6558/61904 [3:03:15<20:37:10,  1.34s/it]
 11%|█         | 6559/61904 [3:03:17<21:12:22,  1.38s/it]
 11%|█         | 6560/61904 [3:03:18<21:14:41,  1.38s/it]
                                                         
{'loss': 2.9948, 'learning_rate': 1.896927265655387e-07, 'epoch': 1.7}

 11%|█         | 6560/61904 [3:03:18<21:14:41,  1.38s/it]
 11%|█         | 6561/61904 [3:03:20<21:11:43,  1.38s/it]
 11%|█         | 6562/61904 [3:03:21<21:11:03,  1.38s/it]
 11%|█         | 6563/61904 [3:03:22<20:51:17,  1.36s/it]
 11%|█         | 6564/61904 [3:03:24<20:57:20,  1.36s/it]
 11%|█         | 6565/61904 [3:03:25<22:14:30,  1.45s/it]
 11%|█         | 6566/61904 [3:03:27<21:38:58,  1.41s/it]
 11%|█         | 6567/61904 [3:03:28<21:52:21,  1.42s/it]
 11%|█         | 6568/61904 [3:03:29<21:30:28,  1.40s/it]
 11%|█         | 6569/61904 [3:03:31<21:23:59,  1.39s/it]
 11%|█         | 6570/61904 [3:03:32<21:06:54,  1.37s/it]
 11%|█         | 6571/61904 [3:03:33<20:52:33,  1.36s/it]
 11%|█         | 6572/61904 [3:03:35<21:46:13,  1.42s/it]
 11%|█         | 6573/61904 [3:03:36<21:40:32,  1.41s/it]
 11%|█         | 6574/61904 [3:03:38<21:12:41,  1.38s/it]
 11%|█         | 6575/61904 [3:03:39<21:05:42,  1.37s/it]
 11%|█         | 6576/61904 [3:03:40<20:41:38,  1.35s/it]
 11%|█         | 6577/61904 [3:03:42<21:26:55,  1.40s/it]
 11%|█         | 6578/61904 [3:03:43<20:54:44,  1.36s/it]
 11%|█         | 6579/61904 [3:03:45<20:52:33,  1.36s/it]
 11%|█         | 6580/61904 [3:03:46<20:54:53,  1.36s/it]
                                                         
{'loss': 2.9, 'learning_rate': 1.8966031375599638e-07, 'epoch': 1.7}

 11%|█         | 6580/61904 [3:03:46<20:54:53,  1.36s/it]
 11%|█         | 6581/61904 [3:03:47<20:43:31,  1.35s/it]
 11%|█         | 6582/61904 [3:03:49<21:31:29,  1.40s/it]
 11%|█         | 6583/61904 [3:03:50<21:38:46,  1.41s/it]
 11%|█         | 6584/61904 [3:03:52<21:57:32,  1.43s/it]
 11%|█         | 6585/61904 [3:03:53<21:23:00,  1.39s/it]
 11%|█         | 6586/61904 [3:03:54<21:18:20,  1.39s/it]
 11%|█         | 6587/61904 [3:03:56<21:24:07,  1.39s/it]
 11%|█         | 6588/61904 [3:03:57<20:59:33,  1.37s/it]
 11%|█         | 6589/61904 [3:03:58<21:29:06,  1.40s/it]
 11%|█         | 6590/61904 [3:04:00<21:14:24,  1.38s/it]
 11%|█         | 6591/61904 [3:04:01<21:24:00,  1.39s/it]
 11%|█         | 6592/61904 [3:04:03<21:15:36,  1.38s/it]
 11%|█         | 6593/61904 [3:04:04<21:23:04,  1.39s/it]
 11%|█         | 6594/61904 [3:04:05<21:31:49,  1.40s/it]
 11%|█         | 6595/61904 [3:04:07<21:34:58,  1.40s/it]
 11%|█         | 6596/61904 [3:04:08<20:49:24,  1.36s/it]
 11%|█         | 6597/61904 [3:04:09<20:57:43,  1.36s/it]
 11%|█         | 6598/61904 [3:04:11<20:47:39,  1.35s/it]
 11%|█         | 6599/61904 [3:04:12<20:46:15,  1.35s/it]
 11%|█         | 6600/61904 [3:04:14<20:55:20,  1.36s/it]
                                                         
{'loss': 2.9318, 'learning_rate': 1.8962790094645404e-07, 'epoch': 1.71}

 11%|█         | 6600/61904 [3:04:14<20:55:20,  1.36s/it]
 11%|█         | 6601/61904 [3:04:15<20:22:30,  1.33s/it]
 11%|█         | 6602/61904 [3:04:16<20:57:05,  1.36s/it]
 11%|█         | 6603/61904 [3:04:18<21:00:08,  1.37s/it]
 11%|█         | 6604/61904 [3:04:19<20:41:56,  1.35s/it]
 11%|█         | 6605/61904 [3:04:20<20:21:38,  1.33s/it]
 11%|█         | 6606/61904 [3:04:21<20:07:50,  1.31s/it]
 11%|█         | 6607/61904 [3:04:23<20:15:50,  1.32s/it]
 11%|█         | 6608/61904 [3:04:24<20:06:54,  1.31s/it]
 11%|█         | 6609/61904 [3:04:25<19:55:07,  1.30s/it]
 11%|█         | 6610/61904 [3:04:27<20:06:28,  1.31s/it]
 11%|█         | 6611/61904 [3:04:28<19:42:32,  1.28s/it]
 11%|█         | 6612/61904 [3:04:29<19:42:37,  1.28s/it]
 11%|█         | 6613/61904 [3:04:31<20:00:52,  1.30s/it]
 11%|█         | 6614/61904 [3:04:32<20:11:29,  1.31s/it]
 11%|█         | 6615/61904 [3:04:33<20:42:53,  1.35s/it]
 11%|█         | 6616/61904 [3:04:35<20:23:10,  1.33s/it]
 11%|█         | 6617/61904 [3:04:36<21:00:51,  1.37s/it]
 11%|█         | 6618/61904 [3:04:38<21:37:24,  1.41s/it]
 11%|█         | 6619/61904 [3:04:39<21:47:19,  1.42s/it]
 11%|█         | 6620/61904 [3:04:40<21:07:10,  1.38s/it]
                                                         
{'loss': 2.8761, 'learning_rate': 1.895954881369117e-07, 'epoch': 1.71}

 11%|█         | 6620/61904 [3:04:40<21:07:10,  1.38s/it]
 11%|█         | 6621/61904 [3:04:42<20:55:46,  1.36s/it]
 11%|█         | 6622/61904 [3:04:43<20:55:41,  1.36s/it]
 11%|█         | 6623/61904 [3:04:44<20:29:58,  1.33s/it]
 11%|█         | 6624/61904 [3:04:46<20:24:14,  1.33s/it]
 11%|█         | 6625/61904 [3:04:47<20:21:35,  1.33s/it]
 11%|█         | 6626/61904 [3:04:48<20:44:36,  1.35s/it]
 11%|█         | 6627/61904 [3:04:50<20:15:25,  1.32s/it]
 11%|█         | 6628/61904 [3:04:51<21:04:18,  1.37s/it]
 11%|█         | 6629/61904 [3:04:53<21:56:14,  1.43s/it]
 11%|█         | 6630/61904 [3:04:54<22:18:30,  1.45s/it]
 11%|█         | 6631/61904 [3:04:56<22:15:49,  1.45s/it]
 11%|█         | 6632/61904 [3:04:57<21:51:51,  1.42s/it]
 11%|█         | 6633/61904 [3:04:58<21:19:17,  1.39s/it]
 11%|█         | 6634/61904 [3:05:00<20:51:40,  1.36s/it]
 11%|█         | 6635/61904 [3:05:01<20:55:26,  1.36s/it]
 11%|█         | 6636/61904 [3:05:02<21:14:06,  1.38s/it]
 11%|█         | 6637/61904 [3:05:04<20:54:42,  1.36s/it]
 11%|█         | 6638/61904 [3:05:05<20:46:34,  1.35s/it]
 11%|█         | 6639/61904 [3:05:06<21:11:05,  1.38s/it]
 11%|█         | 6640/61904 [3:05:08<20:27:57,  1.33s/it]
                                                         
{'loss': 2.9628, 'learning_rate': 1.895630753273694e-07, 'epoch': 1.72}

 11%|█         | 6640/61904 [3:05:08<20:27:57,  1.33s/it]
 11%|█         | 6641/61904 [3:05:09<20:50:22,  1.36s/it]
 11%|█         | 6642/61904 [3:05:10<20:23:12,  1.33s/it]
 11%|█         | 6643/61904 [3:05:12<21:21:45,  1.39s/it]
 11%|█         | 6644/61904 [3:05:13<20:37:44,  1.34s/it]
 11%|█         | 6645/61904 [3:05:14<20:47:51,  1.35s/it]
 11%|█         | 6646/61904 [3:05:16<20:40:44,  1.35s/it]
 11%|█         | 6647/61904 [3:05:17<21:39:40,  1.41s/it]
 11%|█         | 6648/61904 [3:05:19<21:36:44,  1.41s/it]
 11%|█         | 6649/61904 [3:05:20<21:15:22,  1.38s/it]
 11%|█         | 6650/61904 [3:05:21<21:10:02,  1.38s/it]
 11%|█         | 6651/61904 [3:05:23<21:13:04,  1.38s/it]
 11%|█         | 6652/61904 [3:05:24<21:31:38,  1.40s/it]
 11%|█         | 6653/61904 [3:05:26<22:08:28,  1.44s/it]
 11%|█         | 6654/61904 [3:05:27<20:59:52,  1.37s/it]
 11%|█         | 6655/61904 [3:05:28<20:31:40,  1.34s/it]
 11%|█         | 6656/61904 [3:05:30<20:39:15,  1.35s/it]
 11%|█         | 6657/61904 [3:05:31<20:34:24,  1.34s/it]
 11%|█         | 6658/61904 [3:05:32<20:43:17,  1.35s/it]
 11%|█         | 6659/61904 [3:05:34<21:16:26,  1.39s/it]
 11%|█         | 6660/61904 [3:05:35<20:50:49,  1.36s/it]
                                                         
{'loss': 2.9114, 'learning_rate': 1.8953066251782702e-07, 'epoch': 1.72}

 11%|█         | 6660/61904 [3:05:35<20:50:49,  1.36s/it]
 11%|█         | 6661/61904 [3:05:37<21:14:49,  1.38s/it]
 11%|█         | 6662/61904 [3:05:38<21:03:58,  1.37s/it]
 11%|█         | 6663/61904 [3:05:39<21:13:24,  1.38s/it]
 11%|█         | 6664/61904 [3:05:41<21:29:22,  1.40s/it]
 11%|█         | 6665/61904 [3:05:42<20:51:26,  1.36s/it]
 11%|█         | 6666/61904 [3:05:43<21:13:34,  1.38s/it]
 11%|█         | 6667/61904 [3:05:45<20:52:04,  1.36s/it]
 11%|█         | 6668/61904 [3:05:46<20:42:47,  1.35s/it]
 11%|█         | 6669/61904 [3:05:47<20:42:37,  1.35s/it]
 11%|█         | 6670/61904 [3:05:49<20:34:36,  1.34s/it]
 11%|█         | 6671/61904 [3:05:50<21:12:32,  1.38s/it]
 11%|█         | 6672/61904 [3:05:52<20:50:52,  1.36s/it]
 11%|█         | 6673/61904 [3:05:53<20:24:51,  1.33s/it]
 11%|█         | 6674/61904 [3:05:54<21:07:46,  1.38s/it]
 11%|█         | 6675/61904 [3:05:56<21:02:19,  1.37s/it]
 11%|█         | 6676/61904 [3:05:57<21:07:31,  1.38s/it]
 11%|█         | 6677/61904 [3:05:58<21:05:45,  1.38s/it]
 11%|█         | 6678/61904 [3:06:00<21:31:44,  1.40s/it]
 11%|█         | 6679/61904 [3:06:01<21:42:44,  1.42s/it]
 11%|█         | 6680/61904 [3:06:03<21:25:01,  1.40s/it]
                                                         
{'loss': 2.9338, 'learning_rate': 1.894982497082847e-07, 'epoch': 1.73}

 11%|█         | 6680/61904 [3:06:03<21:25:01,  1.40s/it]
 11%|█         | 6681/61904 [3:06:04<21:01:51,  1.37s/it]
 11%|█         | 6682/61904 [3:06:05<20:58:25,  1.37s/it]
 11%|█         | 6683/61904 [3:06:07<20:25:57,  1.33s/it]
 11%|█         | 6684/61904 [3:06:08<20:50:16,  1.36s/it]
 11%|█         | 6685/61904 [3:06:09<20:40:33,  1.35s/it]
 11%|█         | 6686/61904 [3:06:11<20:34:59,  1.34s/it]
 11%|█         | 6687/61904 [3:06:12<20:47:44,  1.36s/it]
 11%|█         | 6688/61904 [3:06:13<20:45:54,  1.35s/it]
 11%|█         | 6689/61904 [3:06:15<20:30:01,  1.34s/it]
 11%|█         | 6690/61904 [3:06:16<20:49:50,  1.36s/it]
 11%|█         | 6691/61904 [3:06:18<21:15:43,  1.39s/it]
 11%|█         | 6692/61904 [3:06:19<22:03:14,  1.44s/it]
 11%|█         | 6693/61904 [3:06:20<21:42:18,  1.42s/it]
 11%|█         | 6694/61904 [3:06:22<21:16:19,  1.39s/it]
 11%|█         | 6695/61904 [3:06:23<21:25:50,  1.40s/it]
 11%|█         | 6696/61904 [3:06:25<20:58:15,  1.37s/it]
 11%|█         | 6697/61904 [3:06:26<21:43:29,  1.42s/it]
 11%|█         | 6698/61904 [3:06:27<21:04:34,  1.37s/it]
 11%|█         | 6699/61904 [3:06:29<20:25:41,  1.33s/it]
 11%|█         | 6700/61904 [3:06:30<20:12:30,  1.32s/it]
                                                         
{'loss': 2.9956, 'learning_rate': 1.8946583689874237e-07, 'epoch': 1.73}

 11%|█         | 6700/61904 [3:06:30<20:12:30,  1.32s/it]
 11%|█         | 6701/61904 [3:06:31<20:46:50,  1.36s/it]
 11%|█         | 6702/61904 [3:06:33<20:46:55,  1.36s/it]
 11%|█         | 6703/61904 [3:06:34<21:16:57,  1.39s/it]
 11%|█         | 6704/61904 [3:06:35<21:05:53,  1.38s/it]
 11%|█         | 6705/61904 [3:06:37<21:05:23,  1.38s/it]
 11%|█         | 6706/61904 [3:06:38<21:12:56,  1.38s/it]
 11%|█         | 6707/61904 [3:06:40<21:07:34,  1.38s/it]
 11%|█         | 6708/61904 [3:06:41<21:10:35,  1.38s/it]
 11%|█         | 6709/61904 [3:06:42<21:01:08,  1.37s/it]
 11%|█         | 6710/61904 [3:06:44<21:06:41,  1.38s/it]
 11%|█         | 6711/61904 [3:06:45<21:25:55,  1.40s/it]
 11%|█         | 6712/61904 [3:06:47<21:14:52,  1.39s/it]
 11%|█         | 6713/61904 [3:06:48<20:26:43,  1.33s/it]
 11%|█         | 6714/61904 [3:06:49<20:30:57,  1.34s/it]
 11%|█         | 6715/61904 [3:06:50<19:59:48,  1.30s/it]
 11%|█         | 6716/61904 [3:06:52<20:58:16,  1.37s/it]
 11%|█         | 6717/61904 [3:06:53<20:15:38,  1.32s/it]
 11%|█         | 6718/61904 [3:06:54<19:50:23,  1.29s/it]
 11%|█         | 6719/61904 [3:06:56<20:11:35,  1.32s/it]
 11%|█         | 6720/61904 [3:06:57<20:30:27,  1.34s/it]
                                                         
{'loss': 2.9089, 'learning_rate': 1.8943342408920004e-07, 'epoch': 1.74}

 11%|█         | 6720/61904 [3:06:57<20:30:27,  1.34s/it]
 11%|█         | 6721/61904 [3:06:58<20:07:09,  1.31s/it]
 11%|█         | 6722/61904 [3:07:00<20:17:36,  1.32s/it]
 11%|█         | 6723/61904 [3:07:01<19:41:45,  1.28s/it]
 11%|█         | 6724/61904 [3:07:02<19:39:30,  1.28s/it]
 11%|█         | 6725/61904 [3:07:03<19:43:16,  1.29s/it]
 11%|█         | 6726/61904 [3:07:05<20:16:38,  1.32s/it]
 11%|█         | 6727/61904 [3:07:06<20:06:30,  1.31s/it]
 11%|█         | 6728/61904 [3:07:07<20:22:12,  1.33s/it]
 11%|█         | 6729/61904 [3:07:09<20:41:20,  1.35s/it]
 11%|█         | 6730/61904 [3:07:10<20:06:08,  1.31s/it]
 11%|█         | 6731/61904 [3:07:11<20:29:34,  1.34s/it]
 11%|█         | 6732/61904 [3:07:13<19:59:41,  1.30s/it]
 11%|█         | 6733/61904 [3:07:14<20:13:28,  1.32s/it]
 11%|█         | 6734/61904 [3:07:15<20:24:11,  1.33s/it]
 11%|█         | 6735/61904 [3:07:17<20:28:53,  1.34s/it]
 11%|█         | 6736/61904 [3:07:18<20:18:20,  1.33s/it]
 11%|█         | 6737/61904 [3:07:19<20:34:58,  1.34s/it]
 11%|█         | 6738/61904 [3:07:21<21:10:05,  1.38s/it]
 11%|█         | 6739/61904 [3:07:22<20:51:55,  1.36s/it]
 11%|█         | 6740/61904 [3:07:24<21:23:07,  1.40s/it]
                                                         
{'loss': 2.9213, 'learning_rate': 1.8940101127965772e-07, 'epoch': 1.74}

 11%|█         | 6740/61904 [3:07:24<21:23:07,  1.40s/it]
 11%|█         | 6741/61904 [3:07:25<21:02:01,  1.37s/it]
 11%|█         | 6742/61904 [3:07:26<21:22:16,  1.39s/it]
 11%|█         | 6743/61904 [3:07:28<21:23:41,  1.40s/it]
 11%|█         | 6744/61904 [3:07:29<20:38:27,  1.35s/it]
 11%|█         | 6745/61904 [3:07:31<21:02:30,  1.37s/it]
 11%|█         | 6746/61904 [3:07:32<21:01:31,  1.37s/it]
 11%|█         | 6747/61904 [3:07:33<21:28:06,  1.40s/it]
 11%|█         | 6748/61904 [3:07:35<21:24:48,  1.40s/it]
 11%|█         | 6749/61904 [3:07:36<21:21:15,  1.39s/it]
 11%|█         | 6750/61904 [3:07:38<21:09:27,  1.38s/it]
 11%|█         | 6751/61904 [3:07:39<20:32:08,  1.34s/it]
 11%|█         | 6752/61904 [3:07:40<20:43:01,  1.35s/it]
 11%|█         | 6753/61904 [3:07:41<20:39:33,  1.35s/it]
 11%|█         | 6754/61904 [3:07:43<21:01:26,  1.37s/it]
 11%|█         | 6755/61904 [3:07:44<20:56:31,  1.37s/it]
 11%|█         | 6756/61904 [3:07:46<20:32:25,  1.34s/it]
 11%|█         | 6757/61904 [3:07:47<20:03:32,  1.31s/it]
 11%|█         | 6758/61904 [3:07:48<20:17:28,  1.32s/it]
 11%|█         | 6759/61904 [3:07:49<20:13:37,  1.32s/it]
 11%|█         | 6760/61904 [3:07:51<20:03:58,  1.31s/it]
                                                         
{'loss': 2.9461, 'learning_rate': 1.8936859847011539e-07, 'epoch': 1.75}

 11%|█         | 6760/61904 [3:07:51<20:03:58,  1.31s/it]
 11%|█         | 6761/61904 [3:07:52<20:20:32,  1.33s/it]
 11%|█         | 6762/61904 [3:07:53<19:47:34,  1.29s/it]
 11%|█         | 6763/61904 [3:07:55<19:48:38,  1.29s/it]
 11%|█         | 6764/61904 [3:07:56<19:48:48,  1.29s/it]
 11%|█         | 6765/61904 [3:07:57<19:59:10,  1.30s/it]
 11%|█         | 6766/61904 [3:07:59<20:33:29,  1.34s/it]
 11%|█         | 6767/61904 [3:08:00<19:59:03,  1.30s/it]
 11%|█         | 6768/61904 [3:08:01<20:03:34,  1.31s/it]
 11%|█         | 6769/61904 [3:08:03<20:18:53,  1.33s/it]
 11%|█         | 6770/61904 [3:08:04<20:52:54,  1.36s/it]
 11%|█         | 6771/61904 [3:08:05<20:41:53,  1.35s/it]
 11%|█         | 6772/61904 [3:08:07<21:34:20,  1.41s/it]
 11%|█         | 6773/61904 [3:08:08<21:06:07,  1.38s/it]
 11%|█         | 6774/61904 [3:08:10<21:32:21,  1.41s/it]
 11%|█         | 6775/61904 [3:08:11<21:21:08,  1.39s/it]
 11%|█         | 6776/61904 [3:08:12<20:55:34,  1.37s/it]
 11%|█         | 6777/61904 [3:08:14<21:00:36,  1.37s/it]
 11%|█         | 6778/61904 [3:08:15<20:52:36,  1.36s/it]
 11%|█         | 6779/61904 [3:08:16<20:29:01,  1.34s/it]
 11%|█         | 6780/61904 [3:08:18<20:35:44,  1.35s/it]
                                                         
{'loss': 2.9103, 'learning_rate': 1.8933618566057305e-07, 'epoch': 1.75}

 11%|█         | 6780/61904 [3:08:18<20:35:44,  1.35s/it]
 11%|█         | 6781/61904 [3:08:19<20:27:48,  1.34s/it]
 11%|█         | 6782/61904 [3:08:20<20:20:46,  1.33s/it]
 11%|█         | 6783/61904 [3:08:22<20:32:59,  1.34s/it]
 11%|█         | 6784/61904 [3:08:23<20:10:44,  1.32s/it]
 11%|█         | 6785/61904 [3:08:24<20:01:50,  1.31s/it]
 11%|█         | 6786/61904 [3:08:26<19:59:55,  1.31s/it]
 11%|█         | 6787/61904 [3:08:27<20:28:50,  1.34s/it]
 11%|█         | 6788/61904 [3:08:28<20:35:21,  1.34s/it]
 11%|█         | 6789/61904 [3:08:30<20:37:33,  1.35s/it]
 11%|█         | 6790/61904 [3:08:31<20:47:50,  1.36s/it]
 11%|█         | 6791/61904 [3:08:32<20:35:55,  1.35s/it]
 11%|█         | 6792/61904 [3:08:34<20:30:26,  1.34s/it]
 11%|█         | 6793/61904 [3:08:35<20:18:15,  1.33s/it]
 11%|█         | 6794/61904 [3:08:36<20:42:59,  1.35s/it]
 11%|█         | 6795/61904 [3:08:38<20:21:49,  1.33s/it]
 11%|█         | 6796/61904 [3:08:39<20:58:06,  1.37s/it]
 11%|█         | 6797/61904 [3:08:40<20:29:49,  1.34s/it]
 11%|█         | 6798/61904 [3:08:42<20:40:47,  1.35s/it]
 11%|█         | 6799/61904 [3:08:43<20:20:36,  1.33s/it]
 11%|█         | 6800/61904 [3:08:44<20:42:08,  1.35s/it]
                                                         
{'loss': 2.9025, 'learning_rate': 1.8930377285103074e-07, 'epoch': 1.76}

 11%|█         | 6800/61904 [3:08:44<20:42:08,  1.35s/it]
 11%|█         | 6801/61904 [3:08:46<21:00:00,  1.37s/it]
 11%|█         | 6802/61904 [3:08:47<21:06:59,  1.38s/it]
 11%|█         | 6803/61904 [3:08:49<22:04:38,  1.44s/it]
 11%|█         | 6804/61904 [3:08:50<21:30:00,  1.40s/it]
 11%|█         | 6805/61904 [3:08:51<20:51:54,  1.36s/it]
 11%|█         | 6806/61904 [3:08:53<20:57:41,  1.37s/it]
 11%|█         | 6807/61904 [3:08:54<20:08:44,  1.32s/it]
 11%|█         | 6808/61904 [3:08:55<20:04:02,  1.31s/it]
 11%|█         | 6809/61904 [3:08:57<20:02:32,  1.31s/it]
 11%|█         | 6810/61904 [3:08:58<20:03:27,  1.31s/it]
 11%|█         | 6811/61904 [3:08:59<19:48:01,  1.29s/it]
 11%|█         | 6812/61904 [3:09:01<20:35:21,  1.35s/it]
 11%|█         | 6813/61904 [3:09:02<21:44:01,  1.42s/it]
 11%|█         | 6814/61904 [3:09:04<21:44:17,  1.42s/it]
 11%|█         | 6815/61904 [3:09:05<21:41:10,  1.42s/it]
 11%|█         | 6816/61904 [3:09:06<21:04:34,  1.38s/it]
 11%|█         | 6817/61904 [3:09:08<20:21:30,  1.33s/it]
 11%|█         | 6818/61904 [3:09:09<20:11:56,  1.32s/it]
 11%|█         | 6819/61904 [3:09:10<20:07:19,  1.32s/it]
 11%|█         | 6820/61904 [3:09:12<20:05:10,  1.31s/it]
                                                         
{'loss': 2.9723, 'learning_rate': 1.8927136004148837e-07, 'epoch': 1.76}

 11%|█         | 6820/61904 [3:09:12<20:05:10,  1.31s/it]
 11%|█         | 6821/61904 [3:09:13<20:28:19,  1.34s/it]
 11%|█         | 6822/61904 [3:09:14<20:56:27,  1.37s/it]
 11%|█         | 6823/61904 [3:09:16<21:13:11,  1.39s/it]
 11%|█         | 6824/61904 [3:09:17<21:52:12,  1.43s/it]
 11%|█         | 6825/61904 [3:09:19<21:07:51,  1.38s/it]
 11%|█         | 6826/61904 [3:09:20<20:40:13,  1.35s/it]
 11%|█         | 6827/61904 [3:09:21<20:33:41,  1.34s/it]
 11%|█         | 6828/61904 [3:09:23<20:30:05,  1.34s/it]
 11%|█         | 6829/61904 [3:09:24<20:22:13,  1.33s/it]
 11%|█         | 6830/61904 [3:09:25<20:40:59,  1.35s/it]
 11%|█         | 6831/61904 [3:09:27<20:33:52,  1.34s/it]
 11%|█         | 6832/61904 [3:09:28<20:56:49,  1.37s/it]
 11%|█         | 6833/61904 [3:09:29<21:20:32,  1.40s/it]
 11%|█         | 6834/61904 [3:09:31<22:09:46,  1.45s/it]
 11%|█         | 6835/61904 [3:09:32<21:53:17,  1.43s/it]
 11%|█         | 6836/61904 [3:09:34<21:25:52,  1.40s/it]
 11%|█         | 6837/61904 [3:09:35<21:27:54,  1.40s/it]
 11%|█         | 6838/61904 [3:09:36<20:52:00,  1.36s/it]
 11%|█         | 6839/61904 [3:09:38<20:34:27,  1.35s/it]
 11%|█         | 6840/61904 [3:09:39<20:19:16,  1.33s/it]
                                                         
{'loss': 2.9768, 'learning_rate': 1.8923894723194606e-07, 'epoch': 1.77}

 11%|█         | 6840/61904 [3:09:39<20:19:16,  1.33s/it]
 11%|█         | 6841/61904 [3:09:40<20:00:24,  1.31s/it]
 11%|█         | 6842/61904 [3:09:42<19:45:51,  1.29s/it]
 11%|█         | 6843/61904 [3:09:43<19:57:28,  1.30s/it]
 11%|█         | 6844/61904 [3:09:44<20:00:17,  1.31s/it]
 11%|█         | 6845/61904 [3:09:45<19:58:17,  1.31s/it]
 11%|█         | 6846/61904 [3:09:47<20:05:32,  1.31s/it]
 11%|█         | 6847/61904 [3:09:48<20:24:38,  1.33s/it]
 11%|█         | 6848/61904 [3:09:49<19:30:15,  1.28s/it]
 11%|█         | 6849/61904 [3:09:51<19:17:13,  1.26s/it]
 11%|█         | 6850/61904 [3:09:52<19:59:30,  1.31s/it]
 11%|█         | 6851/61904 [3:09:53<20:15:09,  1.32s/it]
 11%|█         | 6852/61904 [3:09:55<20:22:26,  1.33s/it]
 11%|█         | 6853/61904 [3:09:56<20:20:26,  1.33s/it]
 11%|█         | 6854/61904 [3:09:57<20:08:47,  1.32s/it]
 11%|█         | 6855/61904 [3:09:59<20:54:33,  1.37s/it]
 11%|█         | 6856/61904 [3:10:00<20:58:53,  1.37s/it]
 11%|█         | 6857/61904 [3:10:02<21:04:37,  1.38s/it]
 11%|█         | 6858/61904 [3:10:03<20:59:37,  1.37s/it]
 11%|█         | 6859/61904 [3:10:04<20:35:43,  1.35s/it]
 11%|█         | 6860/61904 [3:10:06<22:00:00,  1.44s/it]
                                                         
{'loss': 2.8984, 'learning_rate': 1.8920653442240375e-07, 'epoch': 1.77}

 11%|█         | 6860/61904 [3:10:06<22:00:00,  1.44s/it]
 11%|█         | 6861/61904 [3:10:07<21:37:22,  1.41s/it]
 11%|█         | 6862/61904 [3:10:09<21:43:40,  1.42s/it]
 11%|█         | 6863/61904 [3:10:10<21:04:00,  1.38s/it]
 11%|█         | 6864/61904 [3:10:11<20:48:37,  1.36s/it]
 11%|█         | 6865/61904 [3:10:13<20:24:12,  1.33s/it]
 11%|█         | 6866/61904 [3:10:14<20:50:30,  1.36s/it]
 11%|█         | 6867/61904 [3:10:15<20:43:59,  1.36s/it]
 11%|█         | 6868/61904 [3:10:17<20:37:21,  1.35s/it]
 11%|█         | 6869/61904 [3:10:18<20:28:50,  1.34s/it]
 11%|█         | 6870/61904 [3:10:19<21:27:23,  1.40s/it]
 11%|█         | 6871/61904 [3:10:21<21:13:20,  1.39s/it]
 11%|█         | 6872/61904 [3:10:22<20:44:11,  1.36s/it]
 11%|█         | 6873/61904 [3:10:23<20:47:49,  1.36s/it]
 11%|█         | 6874/61904 [3:10:25<20:53:23,  1.37s/it]
 11%|█         | 6875/61904 [3:10:26<20:43:15,  1.36s/it]
 11%|█         | 6876/61904 [3:10:27<20:16:25,  1.33s/it]
 11%|█         | 6877/61904 [3:10:29<21:02:54,  1.38s/it]
 11%|█         | 6878/61904 [3:10:30<21:08:13,  1.38s/it]
 11%|█         | 6879/61904 [3:10:32<20:57:43,  1.37s/it]
 11%|█         | 6880/61904 [3:10:33<21:10:43,  1.39s/it]
                                                         
{'loss': 2.9167, 'learning_rate': 1.8917412161286138e-07, 'epoch': 1.78}

 11%|█         | 6880/61904 [3:10:33<21:10:43,  1.39s/it]
 11%|█         | 6881/61904 [3:10:35<21:16:38,  1.39s/it]
 11%|█         | 6882/61904 [3:10:36<21:22:17,  1.40s/it]
 11%|█         | 6883/61904 [3:10:38<22:07:33,  1.45s/it]
 11%|█         | 6884/61904 [3:10:39<21:25:52,  1.40s/it]
 11%|█         | 6885/61904 [3:10:40<20:56:39,  1.37s/it]
 11%|█         | 6886/61904 [3:10:42<21:14:18,  1.39s/it]
 11%|█         | 6887/61904 [3:10:43<21:17:42,  1.39s/it]
 11%|█         | 6888/61904 [3:10:44<21:28:43,  1.41s/it]
 11%|█         | 6889/61904 [3:10:46<22:23:49,  1.47s/it]
 11%|█         | 6890/61904 [3:10:47<22:08:49,  1.45s/it]
 11%|█         | 6891/61904 [3:10:49<22:01:44,  1.44s/it]
 11%|█         | 6892/61904 [3:10:50<21:38:08,  1.42s/it]
 11%|█         | 6893/61904 [3:10:52<21:39:42,  1.42s/it]
 11%|█         | 6894/61904 [3:10:53<21:14:40,  1.39s/it]
 11%|█         | 6895/61904 [3:10:54<21:46:46,  1.43s/it]
 11%|█         | 6896/61904 [3:10:56<21:10:33,  1.39s/it]
 11%|█         | 6897/61904 [3:10:57<20:44:53,  1.36s/it]
 11%|█         | 6898/61904 [3:10:58<20:38:26,  1.35s/it]
 11%|█         | 6899/61904 [3:11:00<19:58:04,  1.31s/it]
 11%|█         | 6900/61904 [3:11:01<20:06:21,  1.32s/it]
                                                         
{'loss': 2.9561, 'learning_rate': 1.8914170880331907e-07, 'epoch': 1.78}

 11%|█         | 6900/61904 [3:11:01<20:06:21,  1.32s/it]
 11%|█         | 6901/61904 [3:11:02<20:03:27,  1.31s/it]
 11%|█         | 6902/61904 [3:11:04<20:42:43,  1.36s/it]
 11%|█         | 6903/61904 [3:11:05<20:46:22,  1.36s/it]
 11%|█         | 6904/61904 [3:11:07<21:46:29,  1.43s/it]
 11%|█         | 6905/61904 [3:11:08<20:58:54,  1.37s/it]
 11%|█         | 6906/61904 [3:11:09<20:31:55,  1.34s/it]
 11%|█         | 6907/61904 [3:11:11<21:27:39,  1.40s/it]
 11%|█         | 6908/61904 [3:11:12<20:44:19,  1.36s/it]
 11%|█         | 6909/61904 [3:11:13<20:41:42,  1.35s/it]
 11%|█         | 6910/61904 [3:11:15<20:25:37,  1.34s/it]
 11%|█         | 6911/61904 [3:11:16<20:25:03,  1.34s/it]
 11%|█         | 6912/61904 [3:11:17<20:41:58,  1.36s/it]
 11%|█         | 6913/61904 [3:11:19<20:47:43,  1.36s/it]
 11%|█         | 6914/61904 [3:11:20<20:36:58,  1.35s/it]
 11%|█         | 6915/61904 [3:11:21<21:03:21,  1.38s/it]
 11%|█         | 6916/61904 [3:11:23<21:28:29,  1.41s/it]
 11%|█         | 6917/61904 [3:11:24<21:14:37,  1.39s/it]
 11%|█         | 6918/61904 [3:11:26<21:25:16,  1.40s/it]
 11%|█         | 6919/61904 [3:11:27<22:01:30,  1.44s/it]
 11%|█         | 6920/61904 [3:11:29<22:07:20,  1.45s/it]
                                                         
{'loss': 2.8689, 'learning_rate': 1.8910929599377673e-07, 'epoch': 1.79}

 11%|█         | 6920/61904 [3:11:29<22:07:20,  1.45s/it]
 11%|█         | 6921/61904 [3:11:30<21:30:32,  1.41s/it]
 11%|█         | 6922/61904 [3:11:31<20:59:03,  1.37s/it]
 11%|█         | 6923/61904 [3:11:33<20:53:49,  1.37s/it]
 11%|█         | 6924/61904 [3:11:34<20:26:16,  1.34s/it]
 11%|█         | 6925/61904 [3:11:35<20:19:11,  1.33s/it]
 11%|█         | 6926/61904 [3:11:37<20:32:40,  1.35s/it]
 11%|█         | 6927/61904 [3:11:38<20:19:20,  1.33s/it]
 11%|█         | 6928/61904 [3:11:39<20:22:42,  1.33s/it]
 11%|█         | 6929/61904 [3:11:41<20:33:24,  1.35s/it]
 11%|█         | 6930/61904 [3:11:42<20:20:24,  1.33s/it]
 11%|█         | 6931/61904 [3:11:43<20:13:28,  1.32s/it]
 11%|█         | 6932/61904 [3:11:45<20:56:25,  1.37s/it]
 11%|█         | 6933/61904 [3:11:46<20:42:12,  1.36s/it]
 11%|█         | 6934/61904 [3:11:47<20:35:44,  1.35s/it]
 11%|█         | 6935/61904 [3:11:49<19:59:51,  1.31s/it]
 11%|█         | 6936/61904 [3:11:50<20:43:07,  1.36s/it]
 11%|█         | 6937/61904 [3:11:51<21:07:37,  1.38s/it]
 11%|█         | 6938/61904 [3:11:53<21:24:33,  1.40s/it]
 11%|█         | 6939/61904 [3:11:54<20:42:35,  1.36s/it]
 11%|█         | 6940/61904 [3:11:55<20:28:31,  1.34s/it]
                                                         
{'loss': 2.9081, 'learning_rate': 1.890768831842344e-07, 'epoch': 1.79}

 11%|█         | 6940/61904 [3:11:55<20:28:31,  1.34s/it]
 11%|█         | 6941/61904 [3:11:57<20:11:29,  1.32s/it]
 11%|█         | 6942/61904 [3:11:58<20:12:31,  1.32s/it]
 11%|█         | 6943/61904 [3:11:59<19:42:18,  1.29s/it]
 11%|█         | 6944/61904 [3:12:01<20:11:13,  1.32s/it]
 11%|█         | 6945/61904 [3:12:02<20:15:43,  1.33s/it]
 11%|█         | 6946/61904 [3:12:03<19:55:38,  1.31s/it]
 11%|█         | 6947/61904 [3:12:05<19:49:30,  1.30s/it]
 11%|█         | 6948/61904 [3:12:06<20:19:41,  1.33s/it]
 11%|█         | 6949/61904 [3:12:07<20:00:28,  1.31s/it]
 11%|█         | 6950/61904 [3:12:09<20:41:13,  1.36s/it]
 11%|█         | 6951/61904 [3:12:10<21:28:28,  1.41s/it]
 11%|█         | 6952/61904 [3:12:11<20:44:11,  1.36s/it]
 11%|█         | 6953/61904 [3:12:13<20:34:26,  1.35s/it]
 11%|█         | 6954/61904 [3:12:14<20:27:27,  1.34s/it]
 11%|█         | 6955/61904 [3:12:16<20:35:41,  1.35s/it]
 11%|█         | 6956/61904 [3:12:17<20:56:38,  1.37s/it]
 11%|█         | 6957/61904 [3:12:18<20:45:58,  1.36s/it]
 11%|█         | 6958/61904 [3:12:20<20:58:57,  1.37s/it]
 11%|█         | 6959/61904 [3:12:21<20:43:06,  1.36s/it]
 11%|█         | 6960/61904 [3:12:22<20:00:12,  1.31s/it]
                                                         
{'loss': 2.8818, 'learning_rate': 1.8904447037469208e-07, 'epoch': 1.8}

 11%|█         | 6960/61904 [3:12:22<20:00:12,  1.31s/it]
 11%|█         | 6961/61904 [3:12:24<20:26:00,  1.34s/it]
 11%|█         | 6962/61904 [3:12:25<21:00:27,  1.38s/it]
 11%|█         | 6963/61904 [3:12:26<20:48:50,  1.36s/it]
 11%|█         | 6964/61904 [3:12:28<20:40:32,  1.35s/it]
 11%|█▏        | 6965/61904 [3:12:29<20:49:11,  1.36s/it]
 11%|█▏        | 6966/61904 [3:12:31<21:25:54,  1.40s/it]
 11%|█▏        | 6967/61904 [3:12:32<20:53:22,  1.37s/it]
 11%|█▏        | 6968/61904 [3:12:33<20:09:42,  1.32s/it]
 11%|█▏        | 6969/61904 [3:12:34<20:13:51,  1.33s/it]
 11%|█▏        | 6970/61904 [3:12:36<21:09:56,  1.39s/it]
 11%|█▏        | 6971/61904 [3:12:37<20:53:10,  1.37s/it]
 11%|█▏        | 6972/61904 [3:12:39<20:32:02,  1.35s/it]
 11%|█▏        | 6973/61904 [3:12:40<20:23:30,  1.34s/it]
 11%|█▏        | 6974/61904 [3:12:41<20:43:47,  1.36s/it]
 11%|█▏        | 6975/61904 [3:12:43<20:05:36,  1.32s/it]
 11%|█▏        | 6976/61904 [3:12:44<20:26:24,  1.34s/it]
 11%|█▏        | 6977/61904 [3:12:45<21:14:57,  1.39s/it]
 11%|█▏        | 6978/61904 [3:12:47<20:20:30,  1.33s/it]
 11%|█▏        | 6979/61904 [3:12:48<20:08:01,  1.32s/it]
 11%|█▏        | 6980/61904 [3:12:49<20:02:50,  1.31s/it]
                                                         
{'loss': 2.9503, 'learning_rate': 1.8901205756514975e-07, 'epoch': 1.8}

 11%|█▏        | 6980/61904 [3:12:49<20:02:50,  1.31s/it]
 11%|█▏        | 6981/61904 [3:12:51<19:57:26,  1.31s/it]
 11%|█▏        | 6982/61904 [3:12:52<20:16:16,  1.33s/it]
 11%|█▏        | 6983/61904 [3:12:53<20:10:55,  1.32s/it]
 11%|█▏        | 6984/61904 [3:12:54<19:48:01,  1.30s/it]
 11%|█▏        | 6985/61904 [3:12:56<20:08:51,  1.32s/it]
 11%|█▏        | 6986/61904 [3:12:57<20:14:50,  1.33s/it]
 11%|█▏        | 6987/61904 [3:12:58<20:15:19,  1.33s/it]
 11%|█▏        | 6988/61904 [3:13:00<20:03:32,  1.31s/it]
 11%|█▏        | 6989/61904 [3:13:01<20:21:45,  1.33s/it]
 11%|█▏        | 6990/61904 [3:13:03<20:31:56,  1.35s/it]
 11%|█▏        | 6991/61904 [3:13:04<20:40:32,  1.36s/it]
 11%|█▏        | 6992/61904 [3:13:05<21:18:17,  1.40s/it]
 11%|█▏        | 6993/61904 [3:13:07<20:46:43,  1.36s/it]
 11%|█▏        | 6994/61904 [3:13:08<20:48:03,  1.36s/it]
 11%|█▏        | 6995/61904 [3:13:09<20:14:01,  1.33s/it]
 11%|█▏        | 6996/61904 [3:13:11<20:16:01,  1.33s/it]
 11%|█▏        | 6997/61904 [3:13:12<19:50:32,  1.30s/it]
 11%|█▏        | 6998/61904 [3:13:13<20:05:44,  1.32s/it]
 11%|█▏        | 6999/61904 [3:13:15<20:48:13,  1.36s/it]
 11%|█▏        | 7000/61904 [3:13:16<20:55:11,  1.37s/it]
                                                         
{'loss': 2.985, 'learning_rate': 1.889796447556074e-07, 'epoch': 1.81}

 11%|█▏        | 7000/61904 [3:13:16<20:55:11,  1.37s/it]
 11%|█▏        | 7001/61904 [3:13:17<20:46:56,  1.36s/it]
 11%|█▏        | 7002/61904 [3:13:19<20:28:35,  1.34s/it]
 11%|█▏        | 7003/61904 [3:13:20<19:51:35,  1.30s/it]
 11%|█▏        | 7004/61904 [3:13:21<20:44:04,  1.36s/it]
 11%|█▏        | 7005/61904 [3:13:23<20:17:46,  1.33s/it]
 11%|█▏        | 7006/61904 [3:13:24<20:45:39,  1.36s/it]
 11%|█▏        | 7007/61904 [3:13:26<21:17:10,  1.40s/it]
 11%|█▏        | 7008/61904 [3:13:27<20:26:06,  1.34s/it]
 11%|█▏        | 7009/61904 [3:13:28<20:27:48,  1.34s/it]
 11%|█▏        | 7010/61904 [3:13:29<20:16:48,  1.33s/it]
 11%|█▏        | 7011/61904 [3:13:31<20:28:24,  1.34s/it]
 11%|█▏        | 7012/61904 [3:13:32<20:15:35,  1.33s/it]
 11%|█▏        | 7013/61904 [3:13:33<20:04:07,  1.32s/it]
 11%|█▏        | 7014/61904 [3:13:35<19:48:23,  1.30s/it]
 11%|█▏        | 7015/61904 [3:13:36<19:41:52,  1.29s/it]
 11%|█▏        | 7016/61904 [3:13:37<20:01:08,  1.31s/it]
 11%|█▏        | 7017/61904 [3:13:39<20:03:25,  1.32s/it]
 11%|█▏        | 7018/61904 [3:13:40<20:11:46,  1.32s/it]
 11%|█▏        | 7019/61904 [3:13:41<19:59:07,  1.31s/it]
 11%|█▏        | 7020/61904 [3:13:43<20:04:26,  1.32s/it]
                                                         
{'loss': 2.9812, 'learning_rate': 1.889472319460651e-07, 'epoch': 1.81}

 11%|█▏        | 7020/61904 [3:13:43<20:04:26,  1.32s/it]
 11%|█▏        | 7021/61904 [3:13:44<20:16:59,  1.33s/it]
 11%|█▏        | 7022/61904 [3:13:45<20:34:47,  1.35s/it]
 11%|█▏        | 7023/61904 [3:13:47<20:36:03,  1.35s/it]
 11%|█▏        | 7024/61904 [3:13:48<21:07:17,  1.39s/it]
 11%|█▏        | 7025/61904 [3:13:49<20:46:51,  1.36s/it]
 11%|█▏        | 7026/61904 [3:13:51<20:46:28,  1.36s/it]
 11%|█▏        | 7027/61904 [3:13:52<20:20:39,  1.33s/it]
 11%|█▏        | 7028/61904 [3:13:54<20:46:12,  1.36s/it]
 11%|█▏        | 7029/61904 [3:13:55<21:05:38,  1.38s/it]
 11%|█▏        | 7030/61904 [3:13:56<21:21:50,  1.40s/it]
 11%|█▏        | 7031/61904 [3:13:58<21:01:25,  1.38s/it]
 11%|█▏        | 7032/61904 [3:13:59<20:50:26,  1.37s/it]
 11%|█▏        | 7033/61904 [3:14:00<20:22:56,  1.34s/it]
 11%|█▏        | 7034/61904 [3:14:02<20:42:41,  1.36s/it]
 11%|█▏        | 7035/61904 [3:14:03<20:29:33,  1.34s/it]
 11%|█▏        | 7036/61904 [3:14:04<20:43:58,  1.36s/it]
 11%|█▏        | 7037/61904 [3:14:06<21:24:41,  1.40s/it]
 11%|█▏        | 7038/61904 [3:14:08<22:12:36,  1.46s/it]
 11%|█▏        | 7039/61904 [3:14:09<21:47:42,  1.43s/it]
 11%|█▏        | 7040/61904 [3:14:10<22:01:31,  1.45s/it]
                                                         
{'loss': 2.9244, 'learning_rate': 1.8891481913652273e-07, 'epoch': 1.82}

 11%|█▏        | 7040/61904 [3:14:10<22:01:31,  1.45s/it]
 11%|█▏        | 7041/61904 [3:14:12<21:27:28,  1.41s/it]
 11%|█▏        | 7042/61904 [3:14:13<21:06:57,  1.39s/it]
 11%|█▏        | 7043/61904 [3:14:14<21:14:53,  1.39s/it]
 11%|█▏        | 7044/61904 [3:14:16<20:50:33,  1.37s/it]
 11%|█▏        | 7045/61904 [3:14:17<20:32:45,  1.35s/it]
 11%|█▏        | 7046/61904 [3:14:18<20:10:13,  1.32s/it]
 11%|█▏        | 7047/61904 [3:14:20<20:28:56,  1.34s/it]
 11%|█▏        | 7048/61904 [3:14:21<20:21:58,  1.34s/it]
 11%|█▏        | 7049/61904 [3:14:22<20:25:46,  1.34s/it]
 11%|█▏        | 7050/61904 [3:14:24<20:08:30,  1.32s/it]
 11%|█▏        | 7051/61904 [3:14:25<20:11:07,  1.32s/it]
 11%|█▏        | 7052/61904 [3:14:26<19:47:12,  1.30s/it]
 11%|█▏        | 7053/61904 [3:14:27<19:29:04,  1.28s/it]
 11%|█▏        | 7054/61904 [3:14:29<20:00:12,  1.31s/it]
 11%|█▏        | 7055/61904 [3:14:30<20:17:05,  1.33s/it]
 11%|█▏        | 7056/61904 [3:14:32<20:07:28,  1.32s/it]
 11%|█▏        | 7057/61904 [3:14:33<20:05:35,  1.32s/it]
 11%|█▏        | 7058/61904 [3:14:34<20:24:18,  1.34s/it]
 11%|█▏        | 7059/61904 [3:14:36<20:21:19,  1.34s/it]
 11%|█▏        | 7060/61904 [3:14:37<20:39:54,  1.36s/it]
                                                         
{'loss': 2.9199, 'learning_rate': 1.8888240632698042e-07, 'epoch': 1.82}

 11%|█▏        | 7060/61904 [3:14:37<20:39:54,  1.36s/it]
 11%|█▏        | 7061/61904 [3:14:38<20:38:21,  1.35s/it]
 11%|█▏        | 7062/61904 [3:14:40<20:48:57,  1.37s/it]
 11%|█▏        | 7063/61904 [3:14:41<20:27:45,  1.34s/it]
 11%|█▏        | 7064/61904 [3:14:42<20:49:44,  1.37s/it]
 11%|█▏        | 7065/61904 [3:14:44<20:22:44,  1.34s/it]
 11%|█▏        | 7066/61904 [3:14:45<21:00:33,  1.38s/it]
 11%|█▏        | 7067/61904 [3:14:47<20:50:18,  1.37s/it]
 11%|█▏        | 7068/61904 [3:14:48<20:32:48,  1.35s/it]
 11%|█▏        | 7069/61904 [3:14:49<20:06:37,  1.32s/it]
 11%|█▏        | 7070/61904 [3:14:50<20:30:52,  1.35s/it]
 11%|█▏        | 7071/61904 [3:14:52<20:20:23,  1.34s/it]
 11%|█▏        | 7072/61904 [3:14:53<20:01:54,  1.32s/it]
 11%|█▏        | 7073/61904 [3:14:55<20:37:30,  1.35s/it]
 11%|█▏        | 7074/61904 [3:14:56<20:25:09,  1.34s/it]
 11%|█▏        | 7075/61904 [3:14:57<20:10:47,  1.32s/it]
 11%|█▏        | 7076/61904 [3:14:58<20:06:58,  1.32s/it]
 11%|█▏        | 7077/61904 [3:15:00<21:12:36,  1.39s/it]
 11%|█▏        | 7078/61904 [3:15:01<21:40:31,  1.42s/it]
 11%|█▏        | 7079/61904 [3:15:03<21:31:31,  1.41s/it]
 11%|█▏        | 7080/61904 [3:15:04<21:40:46,  1.42s/it]
                                                         
{'loss': 2.9121, 'learning_rate': 1.8884999351743808e-07, 'epoch': 1.83}

 11%|█▏        | 7080/61904 [3:15:04<21:40:46,  1.42s/it]
 11%|█▏        | 7081/61904 [3:15:06<21:26:01,  1.41s/it]
 11%|█▏        | 7082/61904 [3:15:07<22:26:41,  1.47s/it]
 11%|█▏        | 7083/61904 [3:15:09<22:17:39,  1.46s/it]
 11%|█▏        | 7084/61904 [3:15:10<22:43:06,  1.49s/it]
 11%|█▏        | 7085/61904 [3:15:12<22:03:57,  1.45s/it]
 11%|█▏        | 7086/61904 [3:15:13<21:52:58,  1.44s/it]
 11%|█▏        | 7087/61904 [3:15:14<21:05:03,  1.38s/it]
 11%|█▏        | 7088/61904 [3:15:16<20:54:14,  1.37s/it]
 11%|█▏        | 7089/61904 [3:15:17<21:06:22,  1.39s/it]
 11%|█▏        | 7090/61904 [3:15:18<21:09:07,  1.39s/it]
 11%|█▏        | 7091/61904 [3:15:20<21:12:40,  1.39s/it]
 11%|█▏        | 7092/61904 [3:15:21<20:33:25,  1.35s/it]
 11%|█▏        | 7093/61904 [3:15:23<21:01:10,  1.38s/it]
 11%|█▏        | 7094/61904 [3:15:24<20:46:39,  1.36s/it]
 11%|█▏        | 7095/61904 [3:15:25<20:43:18,  1.36s/it]
 11%|█▏        | 7096/61904 [3:15:26<20:04:53,  1.32s/it]
 11%|█▏        | 7097/61904 [3:15:28<21:18:25,  1.40s/it]
 11%|█▏        | 7098/61904 [3:15:29<21:14:39,  1.40s/it]
 11%|█▏        | 7099/61904 [3:15:31<20:53:07,  1.37s/it]
 11%|█▏        | 7100/61904 [3:15:32<20:37:46,  1.36s/it]
                                                         
{'loss': 2.9476, 'learning_rate': 1.8881758070789574e-07, 'epoch': 1.83}

 11%|█▏        | 7100/61904 [3:15:32<20:37:46,  1.36s/it]
 11%|█▏        | 7101/61904 [3:15:34<21:05:25,  1.39s/it]
 11%|█▏        | 7102/61904 [3:15:35<20:50:10,  1.37s/it]
 11%|█▏        | 7103/61904 [3:15:36<20:46:08,  1.36s/it]
 11%|█▏        | 7104/61904 [3:15:38<20:59:54,  1.38s/it]
 11%|█▏        | 7105/61904 [3:15:39<20:48:26,  1.37s/it]
 11%|█▏        | 7106/61904 [3:15:41<21:48:51,  1.43s/it]
 11%|█▏        | 7107/61904 [3:15:42<21:07:28,  1.39s/it]
 11%|█▏        | 7108/61904 [3:15:43<20:45:52,  1.36s/it]
 11%|█▏        | 7109/61904 [3:15:44<20:28:18,  1.34s/it]
 11%|█▏        | 7110/61904 [3:15:46<20:49:41,  1.37s/it]
 11%|█▏        | 7111/61904 [3:15:47<21:12:19,  1.39s/it]
 11%|█▏        | 7112/61904 [3:15:49<20:40:33,  1.36s/it]
 11%|█▏        | 7113/61904 [3:15:50<20:38:00,  1.36s/it]
 11%|█▏        | 7114/61904 [3:15:52<21:40:33,  1.42s/it]
 11%|█▏        | 7115/61904 [3:15:53<22:11:47,  1.46s/it]
 11%|█▏        | 7116/61904 [3:15:54<21:44:14,  1.43s/it]
 11%|█▏        | 7117/61904 [3:15:56<22:04:32,  1.45s/it]
 11%|█▏        | 7118/61904 [3:15:57<21:42:19,  1.43s/it]
 12%|█▏        | 7119/61904 [3:15:59<21:49:42,  1.43s/it]
 12%|█▏        | 7120/61904 [3:16:00<21:15:05,  1.40s/it]
                                                         
{'loss': 2.9117, 'learning_rate': 1.8878516789835343e-07, 'epoch': 1.84}

 12%|█▏        | 7120/61904 [3:16:00<21:15:05,  1.40s/it]
 12%|█▏        | 7121/61904 [3:16:01<21:19:10,  1.40s/it]
 12%|█▏        | 7122/61904 [3:16:03<21:15:52,  1.40s/it]
 12%|█▏        | 7123/61904 [3:16:04<21:22:44,  1.40s/it]
 12%|█▏        | 7124/61904 [3:16:06<22:03:56,  1.45s/it]
 12%|█▏        | 7125/61904 [3:16:07<21:08:43,  1.39s/it]
 12%|█▏        | 7126/61904 [3:16:08<20:45:57,  1.36s/it]
 12%|█▏        | 7127/61904 [3:16:10<20:24:25,  1.34s/it]
 12%|█▏        | 7128/61904 [3:16:11<20:30:51,  1.35s/it]
 12%|█▏        | 7129/61904 [3:16:12<20:24:47,  1.34s/it]
 12%|█▏        | 7130/61904 [3:16:14<20:58:35,  1.38s/it]
 12%|█▏        | 7131/61904 [3:16:15<20:33:44,  1.35s/it]
 12%|█▏        | 7132/61904 [3:16:17<20:42:55,  1.36s/it]
 12%|█▏        | 7133/61904 [3:16:18<21:03:28,  1.38s/it]
 12%|█▏        | 7134/61904 [3:16:19<21:30:01,  1.41s/it]
 12%|█▏        | 7135/61904 [3:16:21<20:28:28,  1.35s/it]
 12%|█▏        | 7136/61904 [3:16:22<20:57:42,  1.38s/it]
 12%|█▏        | 7137/61904 [3:16:24<21:46:41,  1.43s/it]
 12%|█▏        | 7138/61904 [3:16:25<21:41:05,  1.43s/it]
 12%|█▏        | 7139/61904 [3:16:26<20:55:15,  1.38s/it]
 12%|█▏        | 7140/61904 [3:16:28<20:32:18,  1.35s/it]
                                                         
{'loss': 2.8593, 'learning_rate': 1.887527550888111e-07, 'epoch': 1.85}

 12%|█▏        | 7140/61904 [3:16:28<20:32:18,  1.35s/it]
 12%|█▏        | 7141/61904 [3:16:29<20:35:30,  1.35s/it]
 12%|█▏        | 7142/61904 [3:16:30<20:15:34,  1.33s/it]
 12%|█▏        | 7143/61904 [3:16:32<20:31:00,  1.35s/it]
 12%|█▏        | 7144/61904 [3:16:33<20:36:34,  1.35s/it]
 12%|█▏        | 7145/61904 [3:16:34<20:30:21,  1.35s/it]
 12%|█▏        | 7146/61904 [3:16:36<21:35:37,  1.42s/it]
 12%|█▏        | 7147/61904 [3:16:37<20:56:03,  1.38s/it]
 12%|█▏        | 7148/61904 [3:16:39<20:58:22,  1.38s/it]
 12%|█▏        | 7149/61904 [3:16:40<21:18:54,  1.40s/it]
 12%|█▏        | 7150/61904 [3:16:41<21:01:40,  1.38s/it]
 12%|█▏        | 7151/61904 [3:16:43<21:11:06,  1.39s/it]
 12%|█▏        | 7152/61904 [3:16:44<21:17:03,  1.40s/it]
 12%|█▏        | 7153/61904 [3:16:46<20:52:11,  1.37s/it]
 12%|█▏        | 7154/61904 [3:16:47<20:52:59,  1.37s/it]
 12%|█▏        | 7155/61904 [3:16:48<20:11:02,  1.33s/it]
 12%|█▏        | 7156/61904 [3:16:49<20:14:56,  1.33s/it]
 12%|█▏        | 7157/61904 [3:16:51<21:24:50,  1.41s/it]
 12%|█▏        | 7158/61904 [3:16:52<21:21:10,  1.40s/it]
 12%|█▏        | 7159/61904 [3:16:54<21:02:26,  1.38s/it]
 12%|█▏        | 7160/61904 [3:16:55<20:29:16,  1.35s/it]
                                                         
{'loss': 2.9515, 'learning_rate': 1.8872034227926876e-07, 'epoch': 1.85}

 12%|█▏        | 7160/61904 [3:16:55<20:29:16,  1.35s/it]
 12%|█▏        | 7161/61904 [3:16:56<20:15:53,  1.33s/it]
 12%|█▏        | 7162/61904 [3:16:58<20:05:52,  1.32s/it]
 12%|█▏        | 7163/61904 [3:16:59<20:12:58,  1.33s/it]
 12%|█▏        | 7164/61904 [3:17:00<20:01:02,  1.32s/it]
 12%|█▏        | 7165/61904 [3:17:02<20:01:14,  1.32s/it]
 12%|█▏        | 7166/61904 [3:17:03<20:02:07,  1.32s/it]
 12%|█▏        | 7167/61904 [3:17:04<19:51:56,  1.31s/it]
 12%|█▏        | 7168/61904 [3:17:06<20:05:04,  1.32s/it]
 12%|█▏        | 7169/61904 [3:17:07<19:48:43,  1.30s/it]
 12%|█▏        | 7170/61904 [3:17:08<19:38:30,  1.29s/it]
 12%|█▏        | 7171/61904 [3:17:10<20:18:51,  1.34s/it]
 12%|█▏        | 7172/61904 [3:17:11<19:52:35,  1.31s/it]
 12%|█▏        | 7173/61904 [3:17:12<19:42:09,  1.30s/it]
 12%|█▏        | 7174/61904 [3:17:14<20:52:37,  1.37s/it]
 12%|█▏        | 7175/61904 [3:17:15<20:27:10,  1.35s/it]
 12%|█▏        | 7176/61904 [3:17:16<20:46:40,  1.37s/it]
 12%|█▏        | 7177/61904 [3:17:18<20:29:31,  1.35s/it]
 12%|█▏        | 7178/61904 [3:17:19<20:24:39,  1.34s/it]
 12%|█▏        | 7179/61904 [3:17:20<21:12:31,  1.40s/it]
 12%|█▏        | 7180/61904 [3:17:22<21:33:57,  1.42s/it]
                                                         
{'loss': 2.8816, 'learning_rate': 1.8868792946972644e-07, 'epoch': 1.86}

 12%|█▏        | 7180/61904 [3:17:22<21:33:57,  1.42s/it]
 12%|█▏        | 7181/61904 [3:17:23<21:36:06,  1.42s/it]
 12%|█▏        | 7182/61904 [3:17:25<21:19:59,  1.40s/it]
 12%|█▏        | 7183/61904 [3:17:26<21:10:29,  1.39s/it]
 12%|█▏        | 7184/61904 [3:17:27<21:10:35,  1.39s/it]
 12%|█▏        | 7185/61904 [3:17:29<20:48:54,  1.37s/it]
 12%|█▏        | 7186/61904 [3:17:30<20:50:12,  1.37s/it]
 12%|█▏        | 7187/61904 [3:17:31<20:33:33,  1.35s/it]
 12%|█▏        | 7188/61904 [3:17:33<20:00:18,  1.32s/it]
 12%|█▏        | 7189/61904 [3:17:34<20:48:33,  1.37s/it]
 12%|█▏        | 7190/61904 [3:17:36<21:10:11,  1.39s/it]
 12%|█▏        | 7191/61904 [3:17:37<21:18:47,  1.40s/it]
 12%|█▏        | 7192/61904 [3:17:38<21:24:55,  1.41s/it]
 12%|█▏        | 7193/61904 [3:17:40<21:05:44,  1.39s/it]
 12%|█▏        | 7194/61904 [3:17:41<20:26:35,  1.35s/it]
 12%|█▏        | 7195/61904 [3:17:43<21:38:03,  1.42s/it]
 12%|█▏        | 7196/61904 [3:17:44<22:08:46,  1.46s/it]
 12%|█▏        | 7197/61904 [3:17:45<21:21:59,  1.41s/it]
 12%|█▏        | 7198/61904 [3:17:47<21:33:25,  1.42s/it]
 12%|█▏        | 7199/61904 [3:17:48<21:31:50,  1.42s/it]
 12%|█▏        | 7200/61904 [3:17:50<21:12:06,  1.40s/it]
                                                         
{'loss': 2.8811, 'learning_rate': 1.8865551666018408e-07, 'epoch': 1.86}

 12%|█▏        | 7200/61904 [3:17:50<21:12:06,  1.40s/it]
 12%|█▏        | 7201/61904 [3:17:51<21:27:00,  1.41s/it]
 12%|█▏        | 7202/61904 [3:17:52<20:57:12,  1.38s/it]
 12%|█▏        | 7203/61904 [3:17:54<20:30:20,  1.35s/it]
 12%|█▏        | 7204/61904 [3:17:55<20:49:43,  1.37s/it]
 12%|█▏        | 7205/61904 [3:17:57<21:08:41,  1.39s/it]
 12%|█▏        | 7206/61904 [3:17:58<20:45:19,  1.37s/it]
 12%|█▏        | 7207/61904 [3:17:59<20:36:14,  1.36s/it]
 12%|█▏        | 7208/61904 [3:18:01<20:37:50,  1.36s/it]
 12%|█▏        | 7209/61904 [3:18:02<20:25:08,  1.34s/it]
 12%|█▏        | 7210/61904 [3:18:03<20:16:55,  1.33s/it]
 12%|█▏        | 7211/61904 [3:18:05<20:52:16,  1.37s/it]
 12%|█▏        | 7212/61904 [3:18:06<20:18:56,  1.34s/it]
 12%|█▏        | 7213/61904 [3:18:07<20:34:11,  1.35s/it]
 12%|█▏        | 7214/61904 [3:18:09<20:37:38,  1.36s/it]
 12%|█▏        | 7215/61904 [3:18:10<20:50:31,  1.37s/it]
 12%|█▏        | 7216/61904 [3:18:11<20:28:14,  1.35s/it]
 12%|█▏        | 7217/61904 [3:18:13<20:27:58,  1.35s/it]
 12%|█▏        | 7218/61904 [3:18:14<20:09:49,  1.33s/it]
 12%|█▏        | 7219/61904 [3:18:15<20:33:33,  1.35s/it]
 12%|█▏        | 7220/61904 [3:18:17<20:24:56,  1.34s/it]
                                                         
{'loss': 2.8955, 'learning_rate': 1.8862310385064177e-07, 'epoch': 1.87}

 12%|█▏        | 7220/61904 [3:18:17<20:24:56,  1.34s/it]
 12%|█▏        | 7221/61904 [3:18:18<20:26:33,  1.35s/it]
 12%|█▏        | 7222/61904 [3:18:19<20:23:33,  1.34s/it]
 12%|█▏        | 7223/61904 [3:18:21<19:44:56,  1.30s/it]
 12%|█▏        | 7224/61904 [3:18:22<20:01:17,  1.32s/it]
 12%|█▏        | 7225/61904 [3:18:23<20:11:24,  1.33s/it]
 12%|█▏        | 7226/61904 [3:18:25<19:50:56,  1.31s/it]
 12%|█▏        | 7227/61904 [3:18:26<20:01:13,  1.32s/it]
 12%|█▏        | 7228/61904 [3:18:27<20:30:04,  1.35s/it]
 12%|█▏        | 7229/61904 [3:18:29<20:26:35,  1.35s/it]
 12%|█▏        | 7230/61904 [3:18:30<20:23:03,  1.34s/it]
 12%|█▏        | 7231/61904 [3:18:31<20:21:41,  1.34s/it]
 12%|█▏        | 7232/61904 [3:18:33<19:59:32,  1.32s/it]
 12%|█▏        | 7233/61904 [3:18:34<20:23:32,  1.34s/it]
 12%|█▏        | 7234/61904 [3:18:35<20:33:22,  1.35s/it]
 12%|█▏        | 7235/61904 [3:18:37<20:55:48,  1.38s/it]
 12%|█▏        | 7236/61904 [3:18:38<20:35:25,  1.36s/it]
 12%|█▏        | 7237/61904 [3:18:40<20:34:41,  1.36s/it]
 12%|█▏        | 7238/61904 [3:18:41<22:33:23,  1.49s/it]
 12%|█▏        | 7239/61904 [3:18:43<21:40:02,  1.43s/it]
 12%|█▏        | 7240/61904 [3:18:44<21:18:27,  1.40s/it]
                                                         
{'loss': 2.8895, 'learning_rate': 1.8859069104109943e-07, 'epoch': 1.87}

 12%|█▏        | 7240/61904 [3:18:44<21:18:27,  1.40s/it]
 12%|█▏        | 7241/61904 [3:18:45<20:55:53,  1.38s/it]
 12%|█▏        | 7242/61904 [3:18:47<22:42:37,  1.50s/it]
 12%|█▏        | 7243/61904 [3:18:48<21:43:30,  1.43s/it]
 12%|█▏        | 7244/61904 [3:18:50<21:44:51,  1.43s/it]
 12%|█▏        | 7245/61904 [3:18:51<21:39:52,  1.43s/it]
 12%|█▏        | 7246/61904 [3:18:52<21:02:37,  1.39s/it]
 12%|█▏        | 7247/61904 [3:18:54<20:41:27,  1.36s/it]
 12%|█▏        | 7248/61904 [3:18:55<21:10:24,  1.39s/it]
 12%|█▏        | 7249/61904 [3:18:57<21:03:59,  1.39s/it]
 12%|█▏        | 7250/61904 [3:18:58<20:48:11,  1.37s/it]
 12%|█▏        | 7251/61904 [3:18:59<20:25:24,  1.35s/it]
 12%|█▏        | 7252/61904 [3:19:01<21:05:42,  1.39s/it]
 12%|█▏        | 7253/61904 [3:19:02<20:32:01,  1.35s/it]
 12%|█▏        | 7254/61904 [3:19:03<21:20:28,  1.41s/it]
 12%|█▏        | 7255/61904 [3:19:05<20:57:30,  1.38s/it]
 12%|█▏        | 7256/61904 [3:19:06<20:28:47,  1.35s/it]
 12%|█▏        | 7257/61904 [3:19:07<19:41:39,  1.30s/it]
 12%|█▏        | 7258/61904 [3:19:09<20:25:53,  1.35s/it]
 12%|█▏        | 7259/61904 [3:19:10<20:20:43,  1.34s/it]
 12%|█▏        | 7260/61904 [3:19:12<21:23:21,  1.41s/it]
                                                         
{'loss': 2.8621, 'learning_rate': 1.885582782315571e-07, 'epoch': 1.88}

 12%|█▏        | 7260/61904 [3:19:12<21:23:21,  1.41s/it]
 12%|█▏        | 7261/61904 [3:19:13<20:49:31,  1.37s/it]
 12%|█▏        | 7262/61904 [3:19:14<20:41:43,  1.36s/it]
 12%|█▏        | 7263/61904 [3:19:16<20:57:45,  1.38s/it]
 12%|█▏        | 7264/61904 [3:19:17<20:57:04,  1.38s/it]
 12%|█▏        | 7265/61904 [3:19:18<20:54:43,  1.38s/it]
 12%|█▏        | 7266/61904 [3:19:20<20:35:33,  1.36s/it]
 12%|█▏        | 7267/61904 [3:19:21<20:59:14,  1.38s/it]
 12%|█▏        | 7268/61904 [3:19:23<21:32:27,  1.42s/it]
 12%|█▏        | 7269/61904 [3:19:24<20:31:17,  1.35s/it]
 12%|█▏        | 7270/61904 [3:19:25<20:24:11,  1.34s/it]
 12%|█▏        | 7271/61904 [3:19:27<20:21:06,  1.34s/it]
 12%|█▏        | 7272/61904 [3:19:28<20:20:04,  1.34s/it]
 12%|█▏        | 7273/61904 [3:19:29<20:46:19,  1.37s/it]
 12%|█▏        | 7274/61904 [3:19:31<21:24:16,  1.41s/it]
 12%|█▏        | 7275/61904 [3:19:32<21:33:21,  1.42s/it]
 12%|█▏        | 7276/61904 [3:19:33<20:30:47,  1.35s/it]
 12%|█▏        | 7277/61904 [3:19:35<21:01:56,  1.39s/it]
 12%|█▏        | 7278/61904 [3:19:36<20:19:50,  1.34s/it]
 12%|█▏        | 7279/61904 [3:19:38<20:32:10,  1.35s/it]
 12%|█▏        | 7280/61904 [3:19:39<20:58:40,  1.38s/it]
                                                         
{'loss': 2.8738, 'learning_rate': 1.8852586542201478e-07, 'epoch': 1.88}

 12%|█▏        | 7280/61904 [3:19:39<20:58:40,  1.38s/it]
 12%|█▏        | 7281/61904 [3:19:40<20:58:00,  1.38s/it]
 12%|█▏        | 7282/61904 [3:19:42<20:45:23,  1.37s/it]
 12%|█▏        | 7283/61904 [3:19:43<20:52:43,  1.38s/it]
 12%|█▏        | 7284/61904 [3:19:44<20:34:04,  1.36s/it]
 12%|█▏        | 7285/61904 [3:19:46<21:13:18,  1.40s/it]
 12%|█▏        | 7286/61904 [3:19:47<20:47:58,  1.37s/it]
 12%|█▏        | 7287/61904 [3:19:48<20:20:50,  1.34s/it]
 12%|█▏        | 7288/61904 [3:19:50<20:43:05,  1.37s/it]
 12%|█▏        | 7289/61904 [3:19:51<20:51:17,  1.37s/it]
 12%|█▏        | 7290/61904 [3:19:53<20:44:59,  1.37s/it]
 12%|█▏        | 7291/61904 [3:19:54<20:23:50,  1.34s/it]
 12%|█▏        | 7292/61904 [3:19:55<20:38:18,  1.36s/it]
 12%|█▏        | 7293/61904 [3:19:57<20:52:15,  1.38s/it]
 12%|█▏        | 7294/61904 [3:19:58<20:50:09,  1.37s/it]
 12%|█▏        | 7295/61904 [3:19:59<20:27:33,  1.35s/it]
 12%|█▏        | 7296/61904 [3:20:01<20:12:11,  1.33s/it]
 12%|█▏        | 7297/61904 [3:20:02<20:02:01,  1.32s/it]
 12%|█▏        | 7298/61904 [3:20:03<20:35:47,  1.36s/it]
 12%|█▏        | 7299/61904 [3:20:05<20:38:06,  1.36s/it]
 12%|█▏        | 7300/61904 [3:20:06<20:33:40,  1.36s/it]
                                                         
{'loss': 2.9246, 'learning_rate': 1.8849345261247244e-07, 'epoch': 1.89}

 12%|█▏        | 7300/61904 [3:20:06<20:33:40,  1.36s/it]
 12%|█▏        | 7301/61904 [3:20:08<21:02:50,  1.39s/it]
 12%|█▏        | 7302/61904 [3:20:09<20:32:37,  1.35s/it]
 12%|█▏        | 7303/61904 [3:20:10<20:27:12,  1.35s/it]
 12%|█▏        | 7304/61904 [3:20:11<19:49:23,  1.31s/it]
 12%|█▏        | 7305/61904 [3:20:13<20:03:50,  1.32s/it]
 12%|█▏        | 7306/61904 [3:20:14<20:21:50,  1.34s/it]
 12%|█▏        | 7307/61904 [3:20:16<21:04:20,  1.39s/it]
 12%|█▏        | 7308/61904 [3:20:17<20:40:35,  1.36s/it]
 12%|█▏        | 7309/61904 [3:20:18<20:36:44,  1.36s/it]
 12%|█▏        | 7310/61904 [3:20:20<20:39:02,  1.36s/it]
 12%|█▏        | 7311/61904 [3:20:21<20:09:32,  1.33s/it]
 12%|█▏        | 7312/61904 [3:20:22<20:21:30,  1.34s/it]
 12%|█▏        | 7313/61904 [3:20:24<21:38:50,  1.43s/it]
 12%|█▏        | 7314/61904 [3:20:25<21:12:24,  1.40s/it]
 12%|█▏        | 7315/61904 [3:20:27<21:23:25,  1.41s/it]
 12%|█▏        | 7316/61904 [3:20:28<21:47:20,  1.44s/it]
 12%|█▏        | 7317/61904 [3:20:30<21:14:13,  1.40s/it]
 12%|█▏        | 7318/61904 [3:20:31<21:17:06,  1.40s/it]
 12%|█▏        | 7319/61904 [3:20:32<21:35:53,  1.42s/it]
 12%|█▏        | 7320/61904 [3:20:34<21:23:30,  1.41s/it]
                                                         
{'loss': 2.898, 'learning_rate': 1.884610398029301e-07, 'epoch': 1.89}

 12%|█▏        | 7320/61904 [3:20:34<21:23:30,  1.41s/it]
 12%|█▏        | 7321/61904 [3:20:35<20:34:43,  1.36s/it]
 12%|█▏        | 7322/61904 [3:20:36<20:31:06,  1.35s/it]
 12%|█▏        | 7323/61904 [3:20:38<20:48:45,  1.37s/it]
 12%|█▏        | 7324/61904 [3:20:39<20:42:29,  1.37s/it]
 12%|█▏        | 7325/61904 [3:20:40<20:24:08,  1.35s/it]
 12%|█▏        | 7326/61904 [3:20:42<19:58:45,  1.32s/it]
 12%|█▏        | 7327/61904 [3:20:43<20:52:53,  1.38s/it]
 12%|█▏        | 7328/61904 [3:20:45<20:51:08,  1.38s/it]
 12%|█▏        | 7329/61904 [3:20:46<20:49:11,  1.37s/it]
 12%|█▏        | 7330/61904 [3:20:47<20:43:31,  1.37s/it]
 12%|█▏        | 7331/61904 [3:20:49<20:23:24,  1.35s/it]
 12%|█▏        | 7332/61904 [3:20:50<20:19:43,  1.34s/it]
 12%|█▏        | 7333/61904 [3:20:51<20:35:01,  1.36s/it]
 12%|█▏        | 7334/61904 [3:20:53<20:18:28,  1.34s/it]
 12%|█▏        | 7335/61904 [3:20:54<19:56:38,  1.32s/it]
 12%|█▏        | 7336/61904 [3:20:55<19:49:15,  1.31s/it]
 12%|█▏        | 7337/61904 [3:20:56<19:30:20,  1.29s/it]
 12%|█▏        | 7338/61904 [3:20:58<19:17:24,  1.27s/it]
 12%|█▏        | 7339/61904 [3:20:59<19:39:54,  1.30s/it]
 12%|█▏        | 7340/61904 [3:21:00<20:07:00,  1.33s/it]
                                                         
{'loss': 2.9362, 'learning_rate': 1.884286269933878e-07, 'epoch': 1.9}

 12%|█▏        | 7340/61904 [3:21:00<20:07:00,  1.33s/it]
 12%|█▏        | 7341/61904 [3:21:02<20:18:51,  1.34s/it]
 12%|█▏        | 7342/61904 [3:21:03<20:36:12,  1.36s/it]
 12%|█▏        | 7343/61904 [3:21:05<20:47:53,  1.37s/it]
 12%|█▏        | 7344/61904 [3:21:06<20:04:07,  1.32s/it]
 12%|█▏        | 7345/61904 [3:21:07<20:44:57,  1.37s/it]
 12%|█▏        | 7346/61904 [3:21:09<21:16:07,  1.40s/it]
 12%|█▏        | 7347/61904 [3:21:10<21:02:17,  1.39s/it]
 12%|█▏        | 7348/61904 [3:21:11<20:58:48,  1.38s/it]
 12%|█▏        | 7349/61904 [3:21:13<21:01:41,  1.39s/it]
 12%|█▏        | 7350/61904 [3:21:14<21:08:18,  1.39s/it]
 12%|█▏        | 7351/61904 [3:21:16<21:09:24,  1.40s/it]
 12%|█▏        | 7352/61904 [3:21:17<21:16:42,  1.40s/it]
 12%|█▏        | 7353/61904 [3:21:18<20:53:55,  1.38s/it]
 12%|█▏        | 7354/61904 [3:21:20<21:11:52,  1.40s/it]
 12%|█▏        | 7355/61904 [3:21:21<21:12:13,  1.40s/it]
 12%|█▏        | 7356/61904 [3:21:23<20:51:36,  1.38s/it]
 12%|█▏        | 7357/61904 [3:21:24<21:02:49,  1.39s/it]
 12%|█▏        | 7358/61904 [3:21:25<20:40:45,  1.36s/it]
 12%|█▏        | 7359/61904 [3:21:27<20:11:33,  1.33s/it]
 12%|█▏        | 7360/61904 [3:21:28<20:07:48,  1.33s/it]
                                                         
{'loss': 2.9173, 'learning_rate': 1.8839621418384545e-07, 'epoch': 1.9}

 12%|█▏        | 7360/61904 [3:21:28<20:07:48,  1.33s/it]
 12%|█▏        | 7361/61904 [3:21:29<20:11:50,  1.33s/it]
 12%|█▏        | 7362/61904 [3:21:31<20:13:19,  1.33s/it]
 12%|█▏        | 7363/61904 [3:21:32<20:45:28,  1.37s/it]
 12%|█▏        | 7364/61904 [3:21:34<21:23:05,  1.41s/it]
 12%|█▏        | 7365/61904 [3:21:35<21:15:02,  1.40s/it]
 12%|█▏        | 7366/61904 [3:21:36<21:14:51,  1.40s/it]
 12%|█▏        | 7367/61904 [3:21:38<20:50:36,  1.38s/it]
 12%|█▏        | 7368/61904 [3:21:39<20:32:53,  1.36s/it]
 12%|█▏        | 7369/61904 [3:21:40<20:49:13,  1.37s/it]
 12%|█▏        | 7370/61904 [3:21:42<20:50:25,  1.38s/it]
 12%|█▏        | 7371/61904 [3:21:43<20:48:53,  1.37s/it]
 12%|█▏        | 7372/61904 [3:21:44<20:48:05,  1.37s/it]
 12%|█▏        | 7373/61904 [3:21:46<20:37:37,  1.36s/it]
 12%|█▏        | 7374/61904 [3:21:47<20:54:39,  1.38s/it]
 12%|█▏        | 7375/61904 [3:21:49<20:37:56,  1.36s/it]
 12%|█▏        | 7376/61904 [3:21:50<20:21:34,  1.34s/it]
 12%|█▏        | 7377/61904 [3:21:51<20:06:18,  1.33s/it]
 12%|█▏        | 7378/61904 [3:21:52<19:56:57,  1.32s/it]
 12%|█▏        | 7379/61904 [3:21:54<20:23:17,  1.35s/it]
 12%|█▏        | 7380/61904 [3:21:55<20:07:55,  1.33s/it]
                                                         
{'loss': 2.9209, 'learning_rate': 1.8836380137430312e-07, 'epoch': 1.91}

 12%|█▏        | 7380/61904 [3:21:55<20:07:55,  1.33s/it]
 12%|█▏        | 7381/61904 [3:21:57<20:41:55,  1.37s/it]
 12%|█▏        | 7382/61904 [3:21:58<20:51:51,  1.38s/it]
 12%|█▏        | 7383/61904 [3:21:59<20:56:13,  1.38s/it]
 12%|█▏        | 7384/61904 [3:22:01<20:14:47,  1.34s/it]
 12%|█▏        | 7385/61904 [3:22:02<20:32:24,  1.36s/it]
 12%|█▏        | 7386/61904 [3:22:03<20:18:35,  1.34s/it]
 12%|█▏        | 7387/61904 [3:22:05<20:23:34,  1.35s/it]
 12%|█▏        | 7388/61904 [3:22:06<20:09:16,  1.33s/it]
 12%|█▏        | 7389/61904 [3:22:07<20:22:51,  1.35s/it]
 12%|█▏        | 7390/61904 [3:22:09<20:10:20,  1.33s/it]
 12%|█▏        | 7391/61904 [3:22:10<19:47:24,  1.31s/it]
 12%|█▏        | 7392/61904 [3:22:11<19:43:34,  1.30s/it]
 12%|█▏        | 7393/61904 [3:22:13<19:58:38,  1.32s/it]
 12%|█▏        | 7394/61904 [3:22:14<20:06:19,  1.33s/it]
 12%|█▏        | 7395/61904 [3:22:15<19:23:59,  1.28s/it]
 12%|█▏        | 7396/61904 [3:22:16<19:39:45,  1.30s/it]
 12%|█▏        | 7397/61904 [3:22:18<19:27:40,  1.29s/it]
 12%|█▏        | 7398/61904 [3:22:19<19:39:58,  1.30s/it]
 12%|█▏        | 7399/61904 [3:22:20<20:10:48,  1.33s/it]
 12%|█▏        | 7400/61904 [3:22:22<19:52:34,  1.31s/it]
                                                         
{'loss': 2.9294, 'learning_rate': 1.883313885647608e-07, 'epoch': 1.91}

 12%|█▏        | 7400/61904 [3:22:22<19:52:34,  1.31s/it]
 12%|█▏        | 7401/61904 [3:22:23<20:46:08,  1.37s/it]
 12%|█▏        | 7402/61904 [3:22:25<20:49:57,  1.38s/it]
 12%|█▏        | 7403/61904 [3:22:26<20:17:54,  1.34s/it]
 12%|█▏        | 7404/61904 [3:22:27<20:08:36,  1.33s/it]
 12%|█▏        | 7405/61904 [3:22:29<20:35:51,  1.36s/it]
 12%|█▏        | 7406/61904 [3:22:30<21:07:16,  1.40s/it]
 12%|█▏        | 7407/61904 [3:22:31<20:51:36,  1.38s/it]
 12%|█▏        | 7408/61904 [3:22:33<20:20:01,  1.34s/it]
 12%|█▏        | 7409/61904 [3:22:34<20:15:51,  1.34s/it]
 12%|█▏        | 7410/61904 [3:22:35<20:04:59,  1.33s/it]
 12%|█▏        | 7411/61904 [3:22:37<20:32:54,  1.36s/it]
 12%|█▏        | 7412/61904 [3:22:38<20:43:40,  1.37s/it]
 12%|█▏        | 7413/61904 [3:22:39<20:43:47,  1.37s/it]
 12%|█▏        | 7414/61904 [3:22:41<21:07:48,  1.40s/it]
 12%|█▏        | 7415/61904 [3:22:42<21:20:00,  1.41s/it]
 12%|█▏        | 7416/61904 [3:22:44<20:51:08,  1.38s/it]
 12%|█▏        | 7417/61904 [3:22:45<20:10:04,  1.33s/it]
 12%|█▏        | 7418/61904 [3:22:46<20:41:15,  1.37s/it]
 12%|█▏        | 7419/61904 [3:22:48<20:14:07,  1.34s/it]
 12%|█▏        | 7420/61904 [3:22:49<20:51:25,  1.38s/it]
                                                         
{'loss': 2.9321, 'learning_rate': 1.8829897575521844e-07, 'epoch': 1.92}

 12%|█▏        | 7420/61904 [3:22:49<20:51:25,  1.38s/it]
 12%|█▏        | 7421/61904 [3:22:50<20:37:31,  1.36s/it]
 12%|█▏        | 7422/61904 [3:22:52<20:21:46,  1.35s/it]
 12%|█▏        | 7423/61904 [3:22:53<20:40:32,  1.37s/it]
 12%|█▏        | 7424/61904 [3:22:55<21:03:00,  1.39s/it]
 12%|█▏        | 7425/61904 [3:22:56<20:48:37,  1.38s/it]
 12%|█▏        | 7426/61904 [3:22:57<20:49:16,  1.38s/it]
 12%|█▏        | 7427/61904 [3:22:59<21:07:12,  1.40s/it]
 12%|█▏        | 7428/61904 [3:23:00<21:19:47,  1.41s/it]
 12%|█▏        | 7429/61904 [3:23:02<21:06:58,  1.40s/it]
 12%|█▏        | 7430/61904 [3:23:03<20:43:45,  1.37s/it]
 12%|█▏        | 7431/61904 [3:23:04<20:07:29,  1.33s/it]
 12%|█▏        | 7432/61904 [3:23:06<20:48:28,  1.38s/it]
 12%|█▏        | 7433/61904 [3:23:07<20:39:26,  1.37s/it]
 12%|█▏        | 7434/61904 [3:23:08<21:12:40,  1.40s/it]
 12%|█▏        | 7435/61904 [3:23:10<23:09:35,  1.53s/it]
 12%|█▏        | 7436/61904 [3:23:12<22:20:43,  1.48s/it]
 12%|█▏        | 7437/61904 [3:23:13<21:37:05,  1.43s/it]
 12%|█▏        | 7438/61904 [3:23:14<21:24:12,  1.41s/it]
 12%|█▏        | 7439/61904 [3:23:16<22:02:58,  1.46s/it]
 12%|█▏        | 7440/61904 [3:23:17<21:18:53,  1.41s/it]
                                                         
{'loss': 2.8453, 'learning_rate': 1.8826656294567613e-07, 'epoch': 1.92}

 12%|█▏        | 7440/61904 [3:23:17<21:18:53,  1.41s/it]
 12%|█▏        | 7441/61904 [3:23:18<20:50:05,  1.38s/it]
 12%|█▏        | 7442/61904 [3:23:20<20:46:00,  1.37s/it]
 12%|█▏        | 7443/61904 [3:23:21<20:43:45,  1.37s/it]
 12%|█▏        | 7444/61904 [3:23:23<20:44:05,  1.37s/it]
 12%|█▏        | 7445/61904 [3:23:24<21:02:08,  1.39s/it]
 12%|█▏        | 7446/61904 [3:23:25<21:16:08,  1.41s/it]
 12%|█▏        | 7447/61904 [3:23:27<21:03:38,  1.39s/it]
 12%|█▏        | 7448/61904 [3:23:28<20:46:36,  1.37s/it]
 12%|█▏        | 7449/61904 [3:23:29<20:26:11,  1.35s/it]
 12%|█▏        | 7450/61904 [3:23:31<20:26:28,  1.35s/it]
 12%|█▏        | 7451/61904 [3:23:32<20:23:07,  1.35s/it]
 12%|█▏        | 7452/61904 [3:23:33<20:12:41,  1.34s/it]
 12%|█▏        | 7453/61904 [3:23:35<20:43:37,  1.37s/it]
 12%|█▏        | 7454/61904 [3:23:36<20:14:02,  1.34s/it]
 12%|█▏        | 7455/61904 [3:23:37<20:07:46,  1.33s/it]
 12%|█▏        | 7456/61904 [3:23:39<20:15:24,  1.34s/it]
 12%|█▏        | 7457/61904 [3:23:40<20:14:04,  1.34s/it]
 12%|█▏        | 7458/61904 [3:23:42<21:09:49,  1.40s/it]
 12%|█▏        | 7459/61904 [3:23:43<21:33:54,  1.43s/it]
 12%|█▏        | 7460/61904 [3:23:44<20:50:03,  1.38s/it]
                                                         
{'loss': 2.8941, 'learning_rate': 1.882341501361338e-07, 'epoch': 1.93}

 12%|█▏        | 7460/61904 [3:23:44<20:50:03,  1.38s/it]
 12%|█▏        | 7461/61904 [3:23:46<21:06:12,  1.40s/it]
 12%|█▏        | 7462/61904 [3:23:47<21:01:21,  1.39s/it]
 12%|█▏        | 7463/61904 [3:23:49<20:43:13,  1.37s/it]
 12%|█▏        | 7464/61904 [3:23:50<21:05:32,  1.39s/it]
 12%|█▏        | 7465/61904 [3:23:51<21:10:46,  1.40s/it]
 12%|█▏        | 7466/61904 [3:23:53<21:34:41,  1.43s/it]
 12%|█▏        | 7467/61904 [3:23:54<21:33:59,  1.43s/it]
 12%|█▏        | 7468/61904 [3:23:56<21:13:12,  1.40s/it]
 12%|█▏        | 7469/61904 [3:23:57<20:46:40,  1.37s/it]
 12%|█▏        | 7470/61904 [3:23:58<20:26:51,  1.35s/it]
 12%|█▏        | 7471/61904 [3:24:00<20:17:02,  1.34s/it]
 12%|█▏        | 7472/61904 [3:24:01<20:33:55,  1.36s/it]
 12%|█▏        | 7473/61904 [3:24:03<21:08:31,  1.40s/it]
 12%|█▏        | 7474/61904 [3:24:04<21:46:27,  1.44s/it]
 12%|█▏        | 7475/61904 [3:24:05<20:54:42,  1.38s/it]
 12%|█▏        | 7476/61904 [3:24:07<20:49:00,  1.38s/it]
 12%|█▏        | 7477/61904 [3:24:08<20:14:19,  1.34s/it]
 12%|█▏        | 7478/61904 [3:24:09<20:07:42,  1.33s/it]
 12%|█▏        | 7479/61904 [3:24:10<19:46:11,  1.31s/it]
 12%|█▏        | 7480/61904 [3:24:12<19:46:29,  1.31s/it]
                                                         
{'loss': 2.932, 'learning_rate': 1.8820173732659145e-07, 'epoch': 1.93}

 12%|█▏        | 7480/61904 [3:24:12<19:46:29,  1.31s/it]
 12%|█▏        | 7481/61904 [3:24:13<19:37:46,  1.30s/it]
 12%|█▏        | 7482/61904 [3:24:14<19:10:37,  1.27s/it]
 12%|█▏        | 7483/61904 [3:24:16<20:11:36,  1.34s/it]
 12%|█▏        | 7484/61904 [3:24:17<20:08:20,  1.33s/it]
 12%|█▏        | 7485/61904 [3:24:19<20:35:35,  1.36s/it]
 12%|█▏        | 7486/61904 [3:24:20<20:45:22,  1.37s/it]
 12%|█▏        | 7487/61904 [3:24:21<20:37:01,  1.36s/it]
 12%|█▏        | 7488/61904 [3:24:23<20:51:11,  1.38s/it]
 12%|█▏        | 7489/61904 [3:24:24<20:52:32,  1.38s/it]
 12%|█▏        | 7490/61904 [3:24:25<20:55:07,  1.38s/it]
 12%|█▏        | 7491/61904 [3:24:27<21:14:00,  1.40s/it]
 12%|█▏        | 7492/61904 [3:24:28<21:15:38,  1.41s/it]
 12%|█▏        | 7493/61904 [3:24:30<21:01:38,  1.39s/it]
 12%|█▏        | 7494/61904 [3:24:31<20:18:08,  1.34s/it]
 12%|█▏        | 7495/61904 [3:24:32<20:14:36,  1.34s/it]
 12%|█▏        | 7496/61904 [3:24:34<21:03:20,  1.39s/it]
 12%|█▏        | 7497/61904 [3:24:35<20:53:42,  1.38s/it]
 12%|█▏        | 7498/61904 [3:24:37<21:34:03,  1.43s/it]
 12%|█▏        | 7499/61904 [3:24:38<20:50:13,  1.38s/it]
 12%|█▏        | 7500/61904 [3:24:39<20:10:40,  1.34s/it]
                                                         
{'loss': 2.9291, 'learning_rate': 1.8816932451704914e-07, 'epoch': 1.94}

 12%|█▏        | 7500/61904 [3:24:39<20:10:40,  1.34s/it]
 12%|█▏        | 7501/61904 [3:24:40<19:42:38,  1.30s/it]
 12%|█▏        | 7502/61904 [3:24:42<20:27:11,  1.35s/it]
 12%|█▏        | 7503/61904 [3:24:43<20:46:45,  1.38s/it]
 12%|█▏        | 7504/61904 [3:24:45<20:59:32,  1.39s/it]
 12%|█▏        | 7505/61904 [3:24:46<21:05:59,  1.40s/it]
 12%|█▏        | 7506/61904 [3:24:47<20:44:10,  1.37s/it]
 12%|█▏        | 7507/61904 [3:24:49<20:54:46,  1.38s/it]
 12%|█▏        | 7508/61904 [3:24:50<20:10:43,  1.34s/it]
 12%|█▏        | 7509/61904 [3:24:51<20:23:26,  1.35s/it]
 12%|█▏        | 7510/61904 [3:24:53<19:56:25,  1.32s/it]
 12%|█▏        | 7511/61904 [3:24:54<20:36:33,  1.36s/it]
 12%|█▏        | 7512/61904 [3:24:55<20:14:50,  1.34s/it]
 12%|█▏        | 7513/61904 [3:24:57<20:43:08,  1.37s/it]
 12%|█▏        | 7514/61904 [3:24:58<20:15:55,  1.34s/it]
 12%|█▏        | 7515/61904 [3:25:00<20:44:05,  1.37s/it]
 12%|█▏        | 7516/61904 [3:25:01<21:11:55,  1.40s/it]
 12%|█▏        | 7517/61904 [3:25:02<20:23:03,  1.35s/it]
 12%|█▏        | 7518/61904 [3:25:04<20:30:09,  1.36s/it]
 12%|█▏        | 7519/61904 [3:25:05<20:39:22,  1.37s/it]
 12%|█▏        | 7520/61904 [3:25:07<20:59:35,  1.39s/it]
                                                         
{'loss': 2.9375, 'learning_rate': 1.881369117075068e-07, 'epoch': 1.94}

 12%|█▏        | 7520/61904 [3:25:07<20:59:35,  1.39s/it]
 12%|█▏        | 7521/61904 [3:25:08<20:33:07,  1.36s/it]
 12%|█▏        | 7522/61904 [3:25:09<20:44:04,  1.37s/it]
 12%|█▏        | 7523/61904 [3:25:11<20:41:44,  1.37s/it]
 12%|█▏        | 7524/61904 [3:25:12<20:46:24,  1.38s/it]
 12%|█▏        | 7525/61904 [3:25:13<20:37:32,  1.37s/it]
 12%|█▏        | 7526/61904 [3:25:15<20:25:52,  1.35s/it]
 12%|█▏        | 7527/61904 [3:25:16<20:33:54,  1.36s/it]
 12%|█▏        | 7528/61904 [3:25:17<20:27:33,  1.35s/it]
 12%|█▏        | 7529/61904 [3:25:19<20:48:03,  1.38s/it]
 12%|█▏        | 7530/61904 [3:25:20<20:16:55,  1.34s/it]
 12%|█▏        | 7531/61904 [3:25:21<20:03:11,  1.33s/it]
 12%|█▏        | 7532/61904 [3:25:23<19:43:49,  1.31s/it]
 12%|█▏        | 7533/61904 [3:25:24<19:39:33,  1.30s/it]
 12%|█▏        | 7534/61904 [3:25:25<19:21:40,  1.28s/it]
 12%|█▏        | 7535/61904 [3:25:27<19:56:02,  1.32s/it]
 12%|█▏        | 7536/61904 [3:25:28<20:46:17,  1.38s/it]
 12%|█▏        | 7537/61904 [3:25:29<20:33:33,  1.36s/it]
 12%|█▏        | 7538/61904 [3:25:31<20:53:55,  1.38s/it]
 12%|█▏        | 7539/61904 [3:25:32<20:43:36,  1.37s/it]
 12%|█▏        | 7540/61904 [3:25:33<19:59:23,  1.32s/it]
                                                         
{'loss': 2.9291, 'learning_rate': 1.8810449889796446e-07, 'epoch': 1.95}

 12%|█▏        | 7540/61904 [3:25:33<19:59:23,  1.32s/it]
 12%|█▏        | 7541/61904 [3:25:35<20:08:17,  1.33s/it]
 12%|█▏        | 7542/61904 [3:25:36<19:40:59,  1.30s/it]
 12%|█▏        | 7543/61904 [3:25:37<20:29:20,  1.36s/it]
 12%|█▏        | 7544/61904 [3:25:39<20:35:43,  1.36s/it]
 12%|█▏        | 7545/61904 [3:25:40<19:54:07,  1.32s/it]
 12%|█▏        | 7546/61904 [3:25:41<19:49:39,  1.31s/it]
 12%|█▏        | 7547/61904 [3:25:43<20:13:08,  1.34s/it]
 12%|█▏        | 7548/61904 [3:25:44<19:44:03,  1.31s/it]
 12%|█▏        | 7549/61904 [3:25:45<20:35:43,  1.36s/it]
 12%|█▏        | 7550/61904 [3:25:47<20:25:54,  1.35s/it]
 12%|█▏        | 7551/61904 [3:25:48<19:57:25,  1.32s/it]
 12%|█▏        | 7552/61904 [3:25:49<20:11:17,  1.34s/it]
 12%|█▏        | 7553/61904 [3:25:51<20:28:25,  1.36s/it]
 12%|█▏        | 7554/61904 [3:25:52<20:49:21,  1.38s/it]
 12%|█▏        | 7555/61904 [3:25:54<20:24:00,  1.35s/it]
 12%|█▏        | 7556/61904 [3:25:55<20:06:34,  1.33s/it]
 12%|█▏        | 7557/61904 [3:25:56<20:44:05,  1.37s/it]
 12%|█▏        | 7558/61904 [3:25:58<20:13:18,  1.34s/it]
 12%|█▏        | 7559/61904 [3:25:59<20:02:56,  1.33s/it]
 12%|█▏        | 7560/61904 [3:26:00<20:22:32,  1.35s/it]
                                                         
{'loss': 2.8834, 'learning_rate': 1.8807208608842215e-07, 'epoch': 1.95}

 12%|█▏        | 7560/61904 [3:26:00<20:22:32,  1.35s/it]
 12%|█▏        | 7561/61904 [3:26:01<19:52:34,  1.32s/it]
 12%|█▏        | 7562/61904 [3:26:03<19:35:55,  1.30s/it]
 12%|█▏        | 7563/61904 [3:26:04<19:49:40,  1.31s/it]
 12%|█▏        | 7564/61904 [3:26:05<20:14:30,  1.34s/it]
 12%|█▏        | 7565/61904 [3:26:07<20:12:31,  1.34s/it]
 12%|█▏        | 7566/61904 [3:26:08<20:22:56,  1.35s/it]
 12%|█▏        | 7567/61904 [3:26:09<20:11:50,  1.34s/it]
 12%|█▏        | 7568/61904 [3:26:11<20:21:59,  1.35s/it]
 12%|█▏        | 7569/61904 [3:26:12<20:16:41,  1.34s/it]
 12%|█▏        | 7570/61904 [3:26:13<20:03:30,  1.33s/it]
 12%|█▏        | 7571/61904 [3:26:15<20:29:19,  1.36s/it]
 12%|█▏        | 7572/61904 [3:26:16<20:23:21,  1.35s/it]
 12%|█▏        | 7573/61904 [3:26:18<20:24:07,  1.35s/it]
 12%|█▏        | 7574/61904 [3:26:19<20:07:15,  1.33s/it]
 12%|█▏        | 7575/61904 [3:26:20<20:09:35,  1.34s/it]
 12%|█▏        | 7576/61904 [3:26:22<19:55:16,  1.32s/it]
 12%|█▏        | 7577/61904 [3:26:23<19:54:07,  1.32s/it]
 12%|█▏        | 7578/61904 [3:26:24<20:06:56,  1.33s/it]
 12%|█▏        | 7579/61904 [3:26:26<20:09:42,  1.34s/it]
 12%|█▏        | 7580/61904 [3:26:27<20:37:02,  1.37s/it]
                                                         
{'loss': 2.9606, 'learning_rate': 1.880396732788798e-07, 'epoch': 1.96}

 12%|█▏        | 7580/61904 [3:26:27<20:37:02,  1.37s/it]
 12%|█▏        | 7581/61904 [3:26:28<21:02:00,  1.39s/it]
 12%|█▏        | 7582/61904 [3:26:30<20:43:33,  1.37s/it]
 12%|█▏        | 7583/61904 [3:26:31<21:40:31,  1.44s/it]
 12%|█▏        | 7584/61904 [3:26:33<21:28:19,  1.42s/it]
 12%|█▏        | 7585/61904 [3:26:34<21:22:03,  1.42s/it]
 12%|█▏        | 7586/61904 [3:26:36<21:14:41,  1.41s/it]
 12%|█▏        | 7587/61904 [3:26:37<20:41:20,  1.37s/it]
 12%|█▏        | 7588/61904 [3:26:38<21:05:55,  1.40s/it]
 12%|█▏        | 7589/61904 [3:26:40<20:19:24,  1.35s/it]
 12%|█▏        | 7590/61904 [3:26:41<20:06:05,  1.33s/it]
 12%|█▏        | 7591/61904 [3:26:42<20:25:08,  1.35s/it]
 12%|█▏        | 7592/61904 [3:26:44<20:15:48,  1.34s/it]
 12%|█▏        | 7593/61904 [3:26:45<20:23:33,  1.35s/it]
 12%|█▏        | 7594/61904 [3:26:46<21:08:37,  1.40s/it]
 12%|█▏        | 7595/61904 [3:26:48<22:03:54,  1.46s/it]
 12%|█▏        | 7596/61904 [3:26:49<21:26:13,  1.42s/it]
 12%|█▏        | 7597/61904 [3:26:51<21:43:56,  1.44s/it]
 12%|█▏        | 7598/61904 [3:26:52<21:19:23,  1.41s/it]
 12%|█▏        | 7599/61904 [3:26:53<20:39:58,  1.37s/it]
 12%|█▏        | 7600/61904 [3:26:55<20:35:55,  1.37s/it]
                                                         
{'loss': 2.8769, 'learning_rate': 1.8800726046933748e-07, 'epoch': 1.96}

 12%|█▏        | 7600/61904 [3:26:55<20:35:55,  1.37s/it]
 12%|█▏        | 7601/61904 [3:26:56<20:34:03,  1.36s/it]
 12%|█▏        | 7602/61904 [3:26:58<21:17:01,  1.41s/it]
 12%|█▏        | 7603/61904 [3:26:59<20:44:28,  1.38s/it]
 12%|█▏        | 7604/61904 [3:27:00<20:39:33,  1.37s/it]
 12%|█▏        | 7605/61904 [3:27:02<20:53:00,  1.38s/it]
 12%|█▏        | 7606/61904 [3:27:03<20:34:23,  1.36s/it]
 12%|█▏        | 7607/61904 [3:27:05<21:15:16,  1.41s/it]
 12%|█▏        | 7608/61904 [3:27:06<20:58:31,  1.39s/it]
 12%|█▏        | 7609/61904 [3:27:08<21:47:31,  1.44s/it]
 12%|█▏        | 7610/61904 [3:27:09<20:47:58,  1.38s/it]
 12%|█▏        | 7611/61904 [3:27:10<22:02:09,  1.46s/it]
 12%|█▏        | 7612/61904 [3:27:12<21:56:38,  1.46s/it]
 12%|█▏        | 7613/61904 [3:27:13<20:42:29,  1.37s/it]
 12%|█▏        | 7614/61904 [3:27:14<20:59:59,  1.39s/it]
 12%|█▏        | 7615/61904 [3:27:16<20:47:28,  1.38s/it]
 12%|█▏        | 7616/61904 [3:27:17<20:26:25,  1.36s/it]
 12%|█▏        | 7617/61904 [3:27:18<20:10:07,  1.34s/it]
 12%|█▏        | 7618/61904 [3:27:20<20:10:20,  1.34s/it]
 12%|█▏        | 7619/61904 [3:27:21<19:48:50,  1.31s/it]
 12%|█▏        | 7620/61904 [3:27:22<19:49:44,  1.32s/it]
                                                         
{'loss': 2.9195, 'learning_rate': 1.8797484765979514e-07, 'epoch': 1.97}

 12%|█▏        | 7620/61904 [3:27:22<19:49:44,  1.32s/it]
 12%|█▏        | 7621/61904 [3:27:24<20:17:28,  1.35s/it]
 12%|█▏        | 7622/61904 [3:27:25<20:09:06,  1.34s/it]
 12%|█▏        | 7623/61904 [3:27:26<20:06:17,  1.33s/it]
 12%|█▏        | 7624/61904 [3:27:28<20:36:54,  1.37s/it]
 12%|█▏        | 7625/61904 [3:27:29<19:58:49,  1.33s/it]
 12%|█▏        | 7626/61904 [3:27:30<20:07:54,  1.34s/it]
 12%|█▏        | 7627/61904 [3:27:32<20:26:50,  1.36s/it]
 12%|█▏        | 7628/61904 [3:27:33<20:52:51,  1.38s/it]
 12%|█▏        | 7629/61904 [3:27:34<20:15:07,  1.34s/it]
 12%|█▏        | 7630/61904 [3:27:36<20:36:09,  1.37s/it]
 12%|█▏        | 7631/61904 [3:27:37<20:40:39,  1.37s/it]
 12%|█▏        | 7632/61904 [3:27:39<20:42:30,  1.37s/it]
 12%|█▏        | 7633/61904 [3:27:40<20:13:34,  1.34s/it]
 12%|█▏        | 7634/61904 [3:27:41<20:12:44,  1.34s/it]
 12%|█▏        | 7635/61904 [3:27:43<20:08:30,  1.34s/it]
 12%|█▏        | 7636/61904 [3:27:44<20:18:56,  1.35s/it]
 12%|█▏        | 7637/61904 [3:27:45<19:51:57,  1.32s/it]
 12%|█▏        | 7638/61904 [3:27:47<20:07:10,  1.33s/it]
 12%|█▏        | 7639/61904 [3:27:48<20:27:44,  1.36s/it]
 12%|█▏        | 7640/61904 [3:27:49<20:27:29,  1.36s/it]
                                                         
{'loss': 2.9, 'learning_rate': 1.879424348502528e-07, 'epoch': 1.97}

 12%|█▏        | 7640/61904 [3:27:49<20:27:29,  1.36s/it]
 12%|█▏        | 7641/61904 [3:27:51<20:53:48,  1.39s/it]
 12%|█▏        | 7642/61904 [3:27:52<19:59:35,  1.33s/it]
 12%|█▏        | 7643/61904 [3:27:53<19:37:17,  1.30s/it]
 12%|█▏        | 7644/61904 [3:27:55<19:45:11,  1.31s/it]
 12%|█▏        | 7645/61904 [3:27:56<19:37:48,  1.30s/it]
 12%|█▏        | 7646/61904 [3:27:57<20:02:37,  1.33s/it]
 12%|█▏        | 7647/61904 [3:27:59<21:31:42,  1.43s/it]
 12%|█▏        | 7648/61904 [3:28:00<21:47:33,  1.45s/it]
 12%|█▏        | 7649/61904 [3:28:02<21:29:47,  1.43s/it]
 12%|█▏        | 7650/61904 [3:28:03<21:00:52,  1.39s/it]
 12%|█▏        | 7651/61904 [3:28:05<21:17:56,  1.41s/it]
 12%|█▏        | 7652/61904 [3:28:06<21:05:58,  1.40s/it]
 12%|█▏        | 7653/61904 [3:28:07<21:27:58,  1.42s/it]
 12%|█▏        | 7654/61904 [3:28:09<21:39:39,  1.44s/it]
 12%|█▏        | 7655/61904 [3:28:10<21:10:25,  1.41s/it]
 12%|█▏        | 7656/61904 [3:28:12<20:54:49,  1.39s/it]
 12%|█▏        | 7657/61904 [3:28:13<21:24:58,  1.42s/it]
 12%|█▏        | 7658/61904 [3:28:15<21:28:46,  1.43s/it]
 12%|█▏        | 7659/61904 [3:28:16<21:26:15,  1.42s/it]
 12%|█▏        | 7660/61904 [3:28:17<20:47:49,  1.38s/it]
                                                         
{'loss': 2.9407, 'learning_rate': 1.879100220407105e-07, 'epoch': 1.98}

 12%|█▏        | 7660/61904 [3:28:17<20:47:49,  1.38s/it]
 12%|█▏        | 7661/61904 [3:28:19<20:39:50,  1.37s/it]
 12%|█▏        | 7662/61904 [3:28:20<20:16:14,  1.35s/it]
 12%|█▏        | 7663/61904 [3:28:21<20:51:02,  1.38s/it]
 12%|█▏        | 7664/61904 [3:28:23<21:07:21,  1.40s/it]
 12%|█▏        | 7665/61904 [3:28:24<22:01:21,  1.46s/it]
 12%|█▏        | 7666/61904 [3:28:26<21:52:43,  1.45s/it]
 12%|█▏        | 7667/61904 [3:28:27<21:05:29,  1.40s/it]
 12%|█▏        | 7668/61904 [3:28:29<21:15:09,  1.41s/it]
 12%|█▏        | 7669/61904 [3:28:30<20:59:34,  1.39s/it]
 12%|█▏        | 7670/61904 [3:28:31<21:14:25,  1.41s/it]
 12%|█▏        | 7671/61904 [3:28:33<21:12:22,  1.41s/it]
 12%|█▏        | 7672/61904 [3:28:34<20:57:07,  1.39s/it]
 12%|█▏        | 7673/61904 [3:28:36<21:14:46,  1.41s/it]
 12%|█▏        | 7674/61904 [3:28:37<22:01:25,  1.46s/it]
 12%|█▏        | 7675/61904 [3:28:38<21:18:09,  1.41s/it]
 12%|█▏        | 7676/61904 [3:28:40<20:47:24,  1.38s/it]
 12%|█▏        | 7677/61904 [3:28:41<20:51:24,  1.38s/it]
 12%|█▏        | 7678/61904 [3:28:42<20:50:21,  1.38s/it]
 12%|█▏        | 7679/61904 [3:28:44<21:10:18,  1.41s/it]
 12%|█▏        | 7680/61904 [3:28:45<21:02:21,  1.40s/it]
                                                         
{'loss': 2.9094, 'learning_rate': 1.8787760923116815e-07, 'epoch': 1.98}

 12%|█▏        | 7680/61904 [3:28:45<21:02:21,  1.40s/it]
 12%|█▏        | 7681/61904 [3:28:47<21:44:07,  1.44s/it]
 12%|█▏        | 7682/61904 [3:28:48<21:10:33,  1.41s/it]
 12%|█▏        | 7683/61904 [3:28:49<20:21:45,  1.35s/it]
 12%|█▏        | 7684/61904 [3:28:51<20:59:24,  1.39s/it]
 12%|█▏        | 7685/61904 [3:28:52<20:41:15,  1.37s/it]
 12%|█▏        | 7686/61904 [3:28:54<20:41:25,  1.37s/it]
 12%|█▏        | 7687/61904 [3:28:55<20:16:23,  1.35s/it]
 12%|█▏        | 7688/61904 [3:28:56<20:34:37,  1.37s/it]
 12%|█▏        | 7689/61904 [3:28:58<20:31:12,  1.36s/it]
 12%|█▏        | 7690/61904 [3:28:59<20:09:15,  1.34s/it]
 12%|█▏        | 7691/61904 [3:29:00<20:22:23,  1.35s/it]
 12%|█▏        | 7692/61904 [3:29:02<20:19:23,  1.35s/it]
 12%|█▏        | 7693/61904 [3:29:03<20:03:09,  1.33s/it]
 12%|█▏        | 7694/61904 [3:29:04<20:10:41,  1.34s/it]
 12%|█▏        | 7695/61904 [3:29:05<19:27:05,  1.29s/it]
 12%|█▏        | 7696/61904 [3:29:07<19:32:12,  1.30s/it]
 12%|█▏        | 7697/61904 [3:29:08<20:23:11,  1.35s/it]
 12%|█▏        | 7698/61904 [3:29:10<20:19:45,  1.35s/it]
 12%|█▏        | 7699/61904 [3:29:11<20:00:00,  1.33s/it]
 12%|█▏        | 7700/61904 [3:29:12<19:35:24,  1.30s/it]
                                                         
{'loss': 2.9574, 'learning_rate': 1.878451964216258e-07, 'epoch': 1.99}

 12%|█▏        | 7700/61904 [3:29:12<19:35:24,  1.30s/it]
 12%|█▏        | 7701/61904 [3:29:14<20:45:36,  1.38s/it]
 12%|█▏        | 7702/61904 [3:29:15<20:35:44,  1.37s/it]
 12%|█▏        | 7703/61904 [3:29:16<20:22:40,  1.35s/it]
 12%|█▏        | 7704/61904 [3:29:18<20:30:48,  1.36s/it]
 12%|█▏        | 7705/61904 [3:29:19<20:19:40,  1.35s/it]
 12%|█▏        | 7706/61904 [3:29:20<20:37:10,  1.37s/it]
 12%|█▏        | 7707/61904 [3:29:22<20:20:22,  1.35s/it]
 12%|█▏        | 7708/61904 [3:29:23<20:05:48,  1.33s/it]
 12%|█▏        | 7709/61904 [3:29:24<20:16:09,  1.35s/it]
 12%|█▏        | 7710/61904 [3:29:26<20:04:16,  1.33s/it]
 12%|█▏        | 7711/61904 [3:29:27<19:54:13,  1.32s/it]
 12%|█▏        | 7712/61904 [3:29:28<19:31:22,  1.30s/it]
 12%|█▏        | 7713/61904 [3:29:30<19:54:32,  1.32s/it]
 12%|█▏        | 7714/61904 [3:29:31<20:18:07,  1.35s/it]
 12%|█▏        | 7715/61904 [3:29:32<19:53:36,  1.32s/it]
 12%|█▏        | 7716/61904 [3:29:34<19:48:06,  1.32s/it]
 12%|█▏        | 7717/61904 [3:29:35<19:39:34,  1.31s/it]
 12%|█▏        | 7718/61904 [3:29:36<19:59:20,  1.33s/it]
 12%|█▏        | 7719/61904 [3:29:38<20:07:53,  1.34s/it]
 12%|█▏        | 7720/61904 [3:29:39<20:50:27,  1.38s/it]
                                                         
{'loss': 2.8978, 'learning_rate': 1.878127836120835e-07, 'epoch': 2.0}

 12%|█▏        | 7720/61904 [3:29:39<20:50:27,  1.38s/it]
 12%|█▏        | 7721/61904 [3:29:41<21:25:25,  1.42s/it]
 12%|█▏        | 7722/61904 [3:29:42<20:49:10,  1.38s/it]
 12%|█▏        | 7723/61904 [3:29:43<21:22:57,  1.42s/it]
 12%|█▏        | 7724/61904 [3:29:45<21:26:54,  1.43s/it]
 12%|█▏        | 7725/61904 [3:29:46<21:32:59,  1.43s/it]
 12%|█▏        | 7726/61904 [3:29:48<20:48:12,  1.38s/it]
 12%|█▏        | 7727/61904 [3:29:49<20:32:38,  1.37s/it]
 12%|█▏        | 7728/61904 [3:29:50<20:03:03,  1.33s/it]
 12%|█▏        | 7729/61904 [3:29:52<20:27:46,  1.36s/it]
 12%|█▏        | 7730/61904 [3:29:53<21:33:43,  1.43s/it]
 12%|█▏        | 7731/61904 [3:29:55<22:02:19,  1.46s/it]
 12%|█▏        | 7732/61904 [3:29:56<21:35:08,  1.43s/it]
 12%|█▏        | 7733/61904 [3:29:57<20:54:28,  1.39s/it]
 12%|█▏        | 7734/61904 [3:29:59<21:43:16,  1.44s/it]
 12%|█▏        | 7735/61904 [3:30:00<21:09:00,  1.41s/it]
 12%|█▏        | 7736/61904 [3:30:02<21:09:44,  1.41s/it]
 12%|█▏        | 7737/61904 [3:30:03<21:03:14,  1.40s/it]
 12%|█▎        | 7738/61904 [3:30:05<21:06:24,  1.40s/it]
 13%|█▎        | 7739/61904 [3:30:06<21:12:27,  1.41s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:03<21:49,  1.52s/it]

  0%|          | 3/861 [00:06<32:29,  2.27s/it]

  0%|          | 4/861 [00:12<50:58,  3.57s/it]

  1%|          | 5/861 [00:14<46:47,  3.28s/it]

  1%|          | 6/861 [00:18<47:37,  3.34s/it]

  1%|          | 7/861 [00:20<41:13,  2.90s/it]

  1%|          | 8/861 [00:23<41:00,  2.88s/it]

  1%|          | 9/861 [00:25<38:29,  2.71s/it]

  1%|          | 10/861 [00:27<37:15,  2.63s/it]

  1%|▏         | 11/861 [00:30<38:49,  2.74s/it]

  1%|▏         | 12/861 [00:35<45:00,  3.18s/it]

  2%|▏         | 13/861 [00:37<41:25,  2.93s/it]

  2%|▏         | 14/861 [00:38<33:04,  2.34s/it]

  2%|▏         | 15/861 [00:40<32:53,  2.33s/it]

  2%|▏         | 16/861 [00:41<28:01,  1.99s/it]

  2%|▏         | 17/861 [00:46<39:59,  2.84s/it]

  2%|▏         | 18/861 [00:48<34:03,  2.42s/it]

  2%|▏         | 19/861 [00:52<40:24,  2.88s/it]

  2%|▏         | 20/861 [00:56<46:29,  3.32s/it]

  2%|▏         | 21/861 [00:58<41:48,  2.99s/it]

  3%|▎         | 22/861 [01:01<40:27,  2.89s/it]

  3%|▎         | 23/861 [01:02<34:17,  2.46s/it]

  3%|▎         | 24/861 [01:06<38:18,  2.75s/it]

  3%|▎         | 25/861 [01:08<35:32,  2.55s/it]

  3%|▎         | 26/861 [01:12<41:24,  2.98s/it]

  3%|▎         | 27/861 [01:14<39:25,  2.84s/it]

  3%|▎         | 28/861 [01:19<48:16,  3.48s/it]

  3%|▎         | 29/861 [01:20<37:56,  2.74s/it]

  3%|▎         | 30/861 [01:24<43:19,  3.13s/it]

  4%|▎         | 31/861 [01:25<34:40,  2.51s/it]

  4%|▎         | 32/861 [01:26<27:56,  2.02s/it]

  4%|▍         | 33/861 [01:29<32:35,  2.36s/it]

  4%|▍         | 34/861 [01:31<30:32,  2.22s/it]

  4%|▍         | 35/861 [01:36<39:00,  2.83s/it]

  4%|▍         | 36/861 [01:37<34:57,  2.54s/it]

  4%|▍         | 37/861 [01:39<32:23,  2.36s/it]

  4%|▍         | 38/861 [01:42<35:04,  2.56s/it]

  5%|▍         | 39/861 [01:44<32:22,  2.36s/it]

  5%|▍         | 40/861 [01:47<31:45,  2.32s/it]

  5%|▍         | 41/861 [01:47<25:50,  1.89s/it]

  5%|▍         | 42/861 [01:51<32:31,  2.38s/it]

  5%|▍         | 43/861 [01:53<32:06,  2.36s/it]

  5%|▌         | 44/861 [01:55<30:36,  2.25s/it]

  5%|▌         | 45/861 [01:58<31:12,  2.29s/it]

  5%|▌         | 46/861 [02:02<39:49,  2.93s/it]

  5%|▌         | 47/861 [02:06<43:00,  3.17s/it]

  6%|▌         | 48/861 [02:09<42:19,  3.12s/it]

  6%|▌         | 49/861 [02:11<40:18,  2.98s/it]

  6%|▌         | 50/861 [02:12<29:31,  2.18s/it]

  6%|▌         | 51/861 [02:14<30:24,  2.25s/it]

  6%|▌         | 52/861 [02:16<29:58,  2.22s/it]

  6%|▌         | 53/861 [02:18<25:57,  1.93s/it]

  6%|▋         | 54/861 [02:18<20:02,  1.49s/it]

  6%|▋         | 55/861 [02:19<19:36,  1.46s/it]

  7%|▋         | 56/861 [02:24<31:45,  2.37s/it]

  7%|▋         | 57/861 [02:25<26:03,  1.94s/it]

  7%|▋         | 58/861 [02:26<22:15,  1.66s/it]

  7%|▋         | 59/861 [02:27<21:52,  1.64s/it]

  7%|▋         | 60/861 [02:29<22:58,  1.72s/it]

  7%|▋         | 61/861 [02:31<21:33,  1.62s/it]

  7%|▋         | 62/861 [02:32<18:20,  1.38s/it]

  7%|▋         | 63/861 [02:33<18:53,  1.42s/it]

  7%|▋         | 64/861 [02:35<18:55,  1.43s/it]

  8%|▊         | 65/861 [02:36<19:41,  1.48s/it]

  8%|▊         | 66/861 [02:37<18:49,  1.42s/it]

  8%|▊         | 67/861 [02:40<21:48,  1.65s/it]

  8%|▊         | 68/861 [02:42<25:54,  1.96s/it]

  8%|▊         | 69/861 [02:46<34:27,  2.61s/it]

  8%|▊         | 70/861 [02:48<31:57,  2.42s/it]

  8%|▊         | 71/861 [02:51<33:21,  2.53s/it]

  8%|▊         | 72/861 [02:54<34:30,  2.62s/it]

  8%|▊         | 73/861 [02:55<26:59,  2.06s/it]

  9%|▊         | 74/861 [02:58<32:02,  2.44s/it]

  9%|▊         | 75/861 [03:01<32:37,  2.49s/it]

  9%|▉         | 76/861 [03:04<35:33,  2.72s/it]

  9%|▉         | 77/861 [03:07<36:16,  2.78s/it]

  9%|▉         | 78/861 [03:08<30:39,  2.35s/it]

  9%|▉         | 79/861 [03:11<33:09,  2.54s/it]

  9%|▉         | 80/861 [03:13<31:48,  2.44s/it]

  9%|▉         | 81/861 [03:19<42:19,  3.26s/it]

 10%|▉         | 82/861 [03:20<34:15,  2.64s/it]

 10%|▉         | 83/861 [03:22<32:05,  2.48s/it]

 10%|▉         | 84/861 [03:25<33:16,  2.57s/it]

 10%|▉         | 85/861 [03:26<30:08,  2.33s/it]

 10%|▉         | 86/861 [03:28<25:35,  1.98s/it]

 10%|█         | 87/861 [03:31<29:55,  2.32s/it]

 10%|█         | 88/861 [03:31<22:22,  1.74s/it]

 10%|█         | 89/861 [03:33<21:30,  1.67s/it]

 10%|█         | 90/861 [03:37<32:21,  2.52s/it]

 11%|█         | 91/861 [03:39<29:43,  2.32s/it]

 11%|█         | 92/861 [03:41<27:46,  2.17s/it]

 11%|█         | 93/861 [03:44<31:01,  2.42s/it]

 11%|█         | 94/861 [03:45<25:05,  1.96s/it]

 11%|█         | 95/861 [03:46<22:54,  1.79s/it]

 11%|█         | 96/861 [03:48<25:15,  1.98s/it]

 11%|█▏        | 97/861 [03:51<28:21,  2.23s/it]

 11%|█▏        | 98/861 [03:53<26:55,  2.12s/it]

 11%|█▏        | 99/861 [03:58<37:01,  2.92s/it]

 12%|█▏        | 100/861 [04:00<32:00,  2.52s/it]

 12%|█▏        | 101/861 [04:01<29:01,  2.29s/it]

 12%|█▏        | 102/861 [04:03<26:08,  2.07s/it]

 12%|█▏        | 103/861 [04:04<21:54,  1.73s/it]

 12%|█▏        | 104/861 [04:09<36:46,  2.92s/it]

 12%|█▏        | 105/861 [04:12<36:56,  2.93s/it]

 12%|█▏        | 106/861 [04:14<31:35,  2.51s/it]

 12%|█▏        | 107/861 [04:16<29:13,  2.33s/it]

 13%|█▎        | 108/861 [04:16<21:54,  1.75s/it]

 13%|█▎        | 109/861 [04:17<18:08,  1.45s/it]

 13%|█▎        | 110/861 [04:19<21:35,  1.72s/it]

 13%|█▎        | 111/861 [04:23<28:55,  2.31s/it]

 13%|█▎        | 112/861 [04:25<28:39,  2.30s/it]

 13%|█▎        | 113/861 [04:27<26:58,  2.16s/it]

 13%|█▎        | 114/861 [04:30<28:57,  2.33s/it]

 13%|█▎        | 115/861 [04:31<24:40,  1.98s/it]

 13%|█▎        | 116/861 [04:32<21:20,  1.72s/it]

 14%|█▎        | 117/861 [04:35<24:48,  2.00s/it]

 14%|█▎        | 118/861 [04:37<25:07,  2.03s/it]

 14%|█▍        | 119/861 [04:39<24:28,  1.98s/it]

 14%|█▍        | 120/861 [04:39<18:39,  1.51s/it]

 14%|█▍        | 121/861 [04:41<20:51,  1.69s/it]

 14%|█▍        | 122/861 [04:44<24:39,  2.00s/it]

 14%|█▍        | 123/861 [04:46<25:11,  2.05s/it]

 14%|█▍        | 124/861 [04:49<29:21,  2.39s/it]

 15%|█▍        | 125/861 [04:52<31:34,  2.57s/it]

 15%|█▍        | 126/861 [04:55<31:17,  2.55s/it]

 15%|█▍        | 127/861 [04:57<29:59,  2.45s/it]

 15%|█▍        | 128/861 [04:59<27:46,  2.27s/it]

 15%|█▍        | 129/861 [05:01<27:27,  2.25s/it]

 15%|█▌        | 130/861 [05:03<26:34,  2.18s/it]

 15%|█▌        | 131/861 [05:05<25:33,  2.10s/it]

 15%|█▌        | 132/861 [05:08<29:18,  2.41s/it]

 15%|█▌        | 133/861 [05:11<29:37,  2.44s/it]

 16%|█▌        | 134/861 [05:11<22:13,  1.83s/it]

 16%|█▌        | 135/861 [05:12<19:41,  1.63s/it]

 16%|█▌        | 136/861 [05:14<18:45,  1.55s/it]

 16%|█▌        | 137/861 [05:15<18:20,  1.52s/it]

 16%|█▌        | 138/861 [05:16<17:23,  1.44s/it]

 16%|█▌        | 139/861 [05:17<15:58,  1.33s/it]

 16%|█▋        | 140/861 [05:19<15:45,  1.31s/it]

 16%|█▋        | 141/861 [05:20<16:06,  1.34s/it]

 16%|█▋        | 142/861 [05:21<13:52,  1.16s/it]

 17%|█▋        | 143/861 [05:24<21:29,  1.80s/it]

 17%|█▋        | 144/861 [05:27<26:33,  2.22s/it]

 17%|█▋        | 145/861 [05:29<23:49,  2.00s/it]

 17%|█▋        | 146/861 [05:31<23:10,  1.94s/it]

 17%|█▋        | 147/861 [05:32<22:46,  1.91s/it]

 17%|█▋        | 148/861 [05:33<18:12,  1.53s/it]

 17%|█▋        | 149/861 [05:34<14:44,  1.24s/it]

 17%|█▋        | 150/861 [05:38<24:02,  2.03s/it]

 18%|█▊        | 151/861 [05:41<27:43,  2.34s/it]

 18%|█▊        | 152/861 [05:43<28:32,  2.42s/it]

 18%|█▊        | 153/861 [05:47<31:35,  2.68s/it]

 18%|█▊        | 154/861 [05:50<32:48,  2.78s/it]

 18%|█▊        | 155/861 [05:53<34:49,  2.96s/it]

 18%|█▊        | 156/861 [05:56<35:41,  3.04s/it]

 18%|█▊        | 157/861 [05:58<30:11,  2.57s/it]

 18%|█▊        | 158/861 [06:01<32:55,  2.81s/it]

 18%|█▊        | 159/861 [06:03<29:09,  2.49s/it]

 19%|█▊        | 160/861 [06:05<26:45,  2.29s/it]

 19%|█▊        | 161/861 [06:08<32:19,  2.77s/it]

 19%|█▉        | 162/861 [06:09<25:27,  2.19s/it]

 19%|█▉        | 163/861 [06:10<19:13,  1.65s/it]

 19%|█▉        | 164/861 [06:14<27:13,  2.34s/it]

 19%|█▉        | 165/861 [06:16<28:15,  2.44s/it]

 19%|█▉        | 166/861 [06:19<29:15,  2.53s/it]

 19%|█▉        | 167/861 [06:19<21:45,  1.88s/it]

 20%|█▉        | 168/861 [06:21<21:47,  1.89s/it]

 20%|█▉        | 169/861 [06:24<22:52,  1.98s/it]

 20%|█▉        | 170/861 [06:25<22:40,  1.97s/it]

 20%|█▉        | 171/861 [06:27<20:31,  1.78s/it]

 20%|█▉        | 172/861 [06:29<21:24,  1.86s/it]

 20%|██        | 173/861 [06:31<23:42,  2.07s/it]

 20%|██        | 174/861 [06:34<26:01,  2.27s/it]

 20%|██        | 175/861 [06:36<24:57,  2.18s/it]

 20%|██        | 176/861 [06:37<20:01,  1.75s/it]

 21%|██        | 177/861 [06:39<19:57,  1.75s/it]

 21%|██        | 178/861 [06:41<20:45,  1.82s/it]

 21%|██        | 179/861 [06:43<21:56,  1.93s/it]

 21%|██        | 180/861 [06:45<21:55,  1.93s/it]

 21%|██        | 181/861 [06:46<21:12,  1.87s/it]

 21%|██        | 182/861 [06:47<17:28,  1.54s/it]

 21%|██▏       | 183/861 [06:49<19:48,  1.75s/it]

 21%|██▏       | 184/861 [06:53<24:15,  2.15s/it]

 21%|██▏       | 185/861 [06:54<22:38,  2.01s/it]

 22%|██▏       | 186/861 [06:55<19:21,  1.72s/it]

 22%|██▏       | 187/861 [06:58<22:25,  2.00s/it]

 22%|██▏       | 188/861 [07:00<23:37,  2.11s/it]

 22%|██▏       | 189/861 [07:03<24:25,  2.18s/it]

 22%|██▏       | 190/861 [07:05<26:06,  2.33s/it]

 22%|██▏       | 191/861 [07:06<21:31,  1.93s/it]

 22%|██▏       | 192/861 [07:08<22:09,  1.99s/it]

 22%|██▏       | 193/861 [07:11<25:30,  2.29s/it]

 23%|██▎       | 194/861 [07:13<22:36,  2.03s/it]

 23%|██▎       | 195/861 [07:14<19:31,  1.76s/it]

 23%|██▎       | 196/861 [07:18<27:45,  2.50s/it]

 23%|██▎       | 197/861 [07:20<24:20,  2.20s/it]

 23%|██▎       | 198/861 [07:21<22:39,  2.05s/it]

 23%|██▎       | 199/861 [07:24<24:30,  2.22s/it]

 23%|██▎       | 200/861 [07:27<25:23,  2.31s/it]

 23%|██▎       | 201/861 [07:29<26:26,  2.40s/it]

 23%|██▎       | 202/861 [07:31<24:15,  2.21s/it]

 24%|██▎       | 203/861 [07:33<23:14,  2.12s/it]

 24%|██▎       | 204/861 [07:33<17:28,  1.60s/it]

 24%|██▍       | 205/861 [07:34<15:15,  1.40s/it]

 24%|██▍       | 206/861 [07:36<17:01,  1.56s/it]

 24%|██▍       | 207/861 [07:38<18:15,  1.67s/it]

 24%|██▍       | 208/861 [07:40<18:06,  1.66s/it]

 24%|██▍       | 209/861 [07:41<16:48,  1.55s/it]

 24%|██▍       | 210/861 [07:43<18:41,  1.72s/it]

 25%|██▍       | 211/861 [07:47<24:56,  2.30s/it]

 25%|██▍       | 212/861 [07:49<23:51,  2.21s/it]

 25%|██▍       | 213/861 [07:50<21:04,  1.95s/it]

 25%|██▍       | 214/861 [07:51<19:20,  1.79s/it]

 25%|██▍       | 215/861 [07:53<19:00,  1.77s/it]

 25%|██▌       | 216/861 [07:54<17:00,  1.58s/it]

 25%|██▌       | 217/861 [07:55<14:42,  1.37s/it]

 25%|██▌       | 218/861 [07:56<14:22,  1.34s/it]

 25%|██▌       | 219/861 [08:00<20:00,  1.87s/it]

 26%|██▌       | 220/861 [08:02<20:16,  1.90s/it]

 26%|██▌       | 221/861 [08:03<19:07,  1.79s/it]

 26%|██▌       | 222/861 [08:07<24:48,  2.33s/it]

 26%|██▌       | 223/861 [08:09<26:14,  2.47s/it]

 26%|██▌       | 224/861 [08:11<22:56,  2.16s/it]

 26%|██▌       | 225/861 [08:13<23:39,  2.23s/it]

 26%|██▌       | 226/861 [08:16<24:35,  2.32s/it]

 26%|██▋       | 227/861 [08:18<24:56,  2.36s/it]

 26%|██▋       | 228/861 [08:20<23:15,  2.20s/it]

 27%|██▋       | 229/861 [08:22<21:41,  2.06s/it]

 27%|██▋       | 230/861 [08:24<22:56,  2.18s/it]

 27%|██▋       | 231/861 [08:28<27:38,  2.63s/it]

 27%|██▋       | 232/861 [08:28<20:30,  1.96s/it]

 27%|██▋       | 233/861 [08:31<21:16,  2.03s/it]

 27%|██▋       | 234/861 [08:32<19:49,  1.90s/it]

 27%|██▋       | 235/861 [08:35<21:17,  2.04s/it]

 27%|██▋       | 236/861 [08:36<20:46,  1.99s/it]

 28%|██▊       | 237/861 [08:38<20:11,  1.94s/it]

 28%|██▊       | 238/861 [08:39<16:58,  1.63s/it]

 28%|██▊       | 239/861 [08:42<21:24,  2.07s/it]

 28%|██▊       | 240/861 [08:45<22:51,  2.21s/it]

 28%|██▊       | 241/861 [08:48<26:23,  2.55s/it]

 28%|██▊       | 242/861 [08:50<23:52,  2.31s/it]

 28%|██▊       | 243/861 [08:53<26:54,  2.61s/it]

 28%|██▊       | 244/861 [08:56<26:37,  2.59s/it]

 28%|██▊       | 245/861 [08:58<25:30,  2.48s/it]

 29%|██▊       | 246/861 [09:01<25:38,  2.50s/it]

 29%|██▊       | 247/861 [09:02<22:16,  2.18s/it]

 29%|██▉       | 248/861 [09:02<17:12,  1.68s/it]

 29%|██▉       | 249/861 [09:05<18:30,  1.81s/it]

 29%|██▉       | 250/861 [09:08<22:22,  2.20s/it]

 29%|██▉       | 251/861 [09:10<22:01,  2.17s/it]

 29%|██▉       | 252/861 [09:12<20:48,  2.05s/it]

 29%|██▉       | 253/861 [09:13<18:53,  1.86s/it]

 30%|██▉       | 254/861 [09:14<14:44,  1.46s/it]

 30%|██▉       | 255/861 [09:15<15:52,  1.57s/it]

 30%|██▉       | 256/861 [09:18<18:33,  1.84s/it]

 30%|██▉       | 257/861 [09:20<20:24,  2.03s/it]

 30%|██▉       | 258/861 [09:22<19:59,  1.99s/it]

 30%|███       | 259/861 [09:25<23:12,  2.31s/it]

 30%|███       | 260/861 [09:28<24:35,  2.45s/it]

 30%|███       | 261/861 [09:34<34:06,  3.41s/it]

 30%|███       | 262/861 [09:35<28:08,  2.82s/it]

 31%|███       | 263/861 [09:35<20:46,  2.08s/it]

 31%|███       | 264/861 [09:37<20:02,  2.01s/it]

 31%|███       | 265/861 [09:38<17:15,  1.74s/it]

 31%|███       | 266/861 [09:40<16:14,  1.64s/it]

 31%|███       | 267/861 [09:41<15:30,  1.57s/it]

 31%|███       | 268/861 [09:43<16:35,  1.68s/it]

 31%|███       | 269/861 [09:45<17:33,  1.78s/it]

 31%|███▏      | 270/861 [09:48<19:30,  1.98s/it]

 31%|███▏      | 271/861 [09:50<19:42,  2.00s/it]

 32%|███▏      | 272/861 [09:52<21:49,  2.22s/it]

 32%|███▏      | 273/861 [09:55<21:32,  2.20s/it]

 32%|███▏      | 274/861 [09:58<25:36,  2.62s/it]

 32%|███▏      | 275/861 [09:59<19:30,  2.00s/it]

 32%|███▏      | 276/861 [10:01<21:32,  2.21s/it]

 32%|███▏      | 277/861 [10:07<31:13,  3.21s/it]

 32%|███▏      | 278/861 [10:10<30:21,  3.12s/it]

 32%|███▏      | 279/861 [10:12<28:00,  2.89s/it]

 33%|███▎      | 280/861 [10:15<27:27,  2.84s/it]

 33%|███▎      | 281/861 [10:18<27:26,  2.84s/it]

 33%|███▎      | 282/861 [10:20<26:21,  2.73s/it]

 33%|███▎      | 283/861 [10:22<24:02,  2.49s/it]

 33%|███▎      | 284/861 [10:23<18:52,  1.96s/it]

 33%|███▎      | 285/861 [10:25<18:20,  1.91s/it]

 33%|███▎      | 286/861 [10:28<23:20,  2.44s/it]

 33%|███▎      | 287/861 [10:33<28:25,  2.97s/it]

 33%|███▎      | 288/861 [10:35<27:27,  2.87s/it]

 34%|███▎      | 289/861 [10:36<22:07,  2.32s/it]

 34%|███▎      | 290/861 [10:38<21:26,  2.25s/it]

 34%|███▍      | 291/861 [10:41<22:20,  2.35s/it]

 34%|███▍      | 292/861 [10:44<24:22,  2.57s/it]

 34%|███▍      | 293/861 [10:46<22:04,  2.33s/it]

 34%|███▍      | 294/861 [10:49<23:51,  2.53s/it]

 34%|███▍      | 295/861 [10:49<18:34,  1.97s/it]

 34%|███▍      | 296/861 [10:51<17:32,  1.86s/it]

 34%|███▍      | 297/861 [10:54<21:43,  2.31s/it]

 35%|███▍      | 298/861 [10:59<27:45,  2.96s/it]

 35%|███▍      | 299/861 [11:01<26:34,  2.84s/it]

 35%|███▍      | 300/861 [11:04<25:23,  2.72s/it]

 35%|███▍      | 301/861 [11:08<28:46,  3.08s/it]

 35%|███▌      | 302/861 [11:08<21:36,  2.32s/it]

 35%|███▌      | 303/861 [11:12<25:21,  2.73s/it]

 35%|███▌      | 304/861 [11:15<26:57,  2.90s/it]

 35%|███▌      | 305/861 [11:18<27:09,  2.93s/it]

 36%|███▌      | 306/861 [11:22<28:40,  3.10s/it]

 36%|███▌      | 307/861 [11:25<29:23,  3.18s/it]

 36%|███▌      | 308/861 [11:26<22:01,  2.39s/it]

 36%|███▌      | 309/861 [11:28<20:39,  2.25s/it]

 36%|███▌      | 310/861 [11:30<19:43,  2.15s/it]

 36%|███▌      | 311/861 [11:34<25:30,  2.78s/it]

 36%|███▌      | 312/861 [11:37<25:13,  2.76s/it]

 36%|███▋      | 313/861 [11:41<28:42,  3.14s/it]

 36%|███▋      | 314/861 [11:43<27:58,  3.07s/it]

 37%|███▋      | 315/861 [11:46<25:26,  2.80s/it]

 37%|███▋      | 316/861 [11:48<24:20,  2.68s/it]

 37%|███▋      | 317/861 [11:49<18:27,  2.04s/it]

 37%|███▋      | 318/861 [11:52<21:05,  2.33s/it]

 37%|███▋      | 319/861 [11:54<22:21,  2.48s/it]

 37%|███▋      | 320/861 [11:57<21:39,  2.40s/it]

 37%|███▋      | 321/861 [12:00<23:39,  2.63s/it]

 37%|███▋      | 322/861 [12:04<27:27,  3.06s/it]

 38%|███▊      | 323/861 [12:07<27:11,  3.03s/it]

 38%|███▊      | 324/861 [12:13<34:13,  3.82s/it]

 38%|███▊      | 325/861 [12:15<31:40,  3.54s/it]

 38%|███▊      | 326/861 [12:16<23:08,  2.59s/it]

 38%|███▊      | 327/861 [12:19<25:55,  2.91s/it]

 38%|███▊      | 328/861 [12:22<24:07,  2.72s/it]

 38%|███▊      | 329/861 [12:26<28:59,  3.27s/it]

 38%|███▊      | 330/861 [12:29<26:34,  3.00s/it]

 38%|███▊      | 331/861 [12:33<31:05,  3.52s/it]

 39%|███▊      | 332/861 [12:36<27:41,  3.14s/it]

 39%|███▊      | 333/861 [12:39<28:49,  3.28s/it]

 39%|███▉      | 334/861 [12:43<30:20,  3.45s/it]

 39%|███▉      | 335/861 [12:46<29:32,  3.37s/it]

 39%|███▉      | 336/861 [12:50<30:32,  3.49s/it]

 39%|███▉      | 337/861 [12:52<25:35,  2.93s/it]

 39%|███▉      | 338/861 [12:55<27:19,  3.13s/it]

 39%|███▉      | 339/861 [12:58<25:46,  2.96s/it]

 39%|███▉      | 340/861 [12:59<22:20,  2.57s/it]

 40%|███▉      | 341/861 [13:00<18:05,  2.09s/it]

 40%|███▉      | 342/861 [13:02<17:16,  2.00s/it]

 40%|███▉      | 343/861 [13:04<17:40,  2.05s/it]

 40%|███▉      | 344/861 [13:06<16:46,  1.95s/it]

 40%|████      | 345/861 [13:08<17:46,  2.07s/it]

 40%|████      | 346/861 [13:11<18:21,  2.14s/it]

 40%|████      | 347/861 [13:12<17:03,  1.99s/it]

 40%|████      | 348/861 [13:14<15:56,  1.86s/it]

 41%|████      | 349/861 [13:17<18:38,  2.19s/it]

 41%|████      | 350/861 [13:20<19:50,  2.33s/it]

 41%|████      | 351/861 [13:22<18:48,  2.21s/it]

 41%|████      | 352/861 [13:23<17:38,  2.08s/it]

 41%|████      | 353/861 [13:25<16:58,  2.01s/it]

 41%|████      | 354/861 [13:27<17:48,  2.11s/it]

 41%|████      | 355/861 [13:28<14:13,  1.69s/it]

 41%|████▏     | 356/861 [13:29<12:44,  1.51s/it]

 41%|████▏     | 357/861 [13:30<10:24,  1.24s/it]

 42%|████▏     | 358/861 [13:31<10:28,  1.25s/it]

 42%|████▏     | 359/861 [13:33<12:44,  1.52s/it]

 42%|████▏     | 360/861 [13:36<16:36,  1.99s/it]

 42%|████▏     | 361/861 [13:39<17:41,  2.12s/it]

 42%|████▏     | 362/861 [13:41<16:57,  2.04s/it]

 42%|████▏     | 363/861 [13:44<20:02,  2.41s/it]

 42%|████▏     | 364/861 [13:47<21:09,  2.55s/it]

 42%|████▏     | 365/861 [13:51<24:32,  2.97s/it]

 43%|████▎     | 366/861 [13:53<22:18,  2.70s/it]

 43%|████▎     | 367/861 [13:57<24:57,  3.03s/it]

 43%|████▎     | 368/861 [14:02<30:50,  3.75s/it]

 43%|████▎     | 369/861 [14:04<27:16,  3.33s/it]

 43%|████▎     | 370/861 [14:07<24:11,  2.96s/it]

 43%|████▎     | 371/861 [14:10<25:20,  3.10s/it]

 43%|████▎     | 372/861 [14:13<25:43,  3.16s/it]

 43%|████▎     | 373/861 [14:16<24:06,  2.96s/it]

 43%|████▎     | 374/861 [14:19<24:27,  3.01s/it]

 44%|████▎     | 375/861 [14:23<27:04,  3.34s/it]

 44%|████▎     | 376/861 [14:25<22:39,  2.80s/it]

 44%|████▍     | 377/861 [14:27<22:21,  2.77s/it]

 44%|████▍     | 378/861 [14:31<25:36,  3.18s/it]

 44%|████▍     | 379/861 [14:32<19:11,  2.39s/it]

 44%|████▍     | 380/861 [14:34<17:57,  2.24s/it]

 44%|████▍     | 381/861 [14:36<17:05,  2.14s/it]

 44%|████▍     | 382/861 [14:38<18:02,  2.26s/it]

 44%|████▍     | 383/861 [14:40<17:22,  2.18s/it]

 45%|████▍     | 384/861 [14:43<17:47,  2.24s/it]

 45%|████▍     | 385/861 [14:43<14:26,  1.82s/it]

 45%|████▍     | 386/861 [14:46<16:36,  2.10s/it]

 45%|████▍     | 387/861 [14:49<17:51,  2.26s/it]

 45%|████▌     | 388/861 [14:50<15:22,  1.95s/it]

 45%|████▌     | 389/861 [14:51<13:00,  1.65s/it]

 45%|████▌     | 390/861 [14:53<12:54,  1.64s/it]

 45%|████▌     | 391/861 [14:54<12:48,  1.64s/it]

 46%|████▌     | 392/861 [14:56<13:22,  1.71s/it]

 46%|████▌     | 393/861 [14:59<15:05,  1.94s/it]

 46%|████▌     | 394/861 [15:02<19:22,  2.49s/it]

 46%|████▌     | 395/861 [15:04<16:13,  2.09s/it]

 46%|████▌     | 396/861 [15:05<13:49,  1.78s/it]

 46%|████▌     | 397/861 [15:05<11:01,  1.42s/it]

 46%|████▌     | 398/861 [15:07<12:41,  1.65s/it]

 46%|████▋     | 399/861 [15:10<14:34,  1.89s/it]

 46%|████▋     | 400/861 [15:12<15:56,  2.07s/it]

 47%|████▋     | 401/861 [15:13<13:15,  1.73s/it]

 47%|████▋     | 402/861 [15:15<12:23,  1.62s/it]

 47%|████▋     | 403/861 [15:17<13:31,  1.77s/it]

 47%|████▋     | 404/861 [15:19<14:28,  1.90s/it]

 47%|████▋     | 405/861 [15:20<12:35,  1.66s/it]

 47%|████▋     | 406/861 [15:23<14:44,  1.94s/it]

 47%|████▋     | 407/861 [15:25<15:19,  2.03s/it]

 47%|████▋     | 408/861 [15:28<17:22,  2.30s/it]

 48%|████▊     | 409/861 [15:30<16:19,  2.17s/it]

 48%|████▊     | 410/861 [15:31<14:40,  1.95s/it]

 48%|████▊     | 411/861 [15:32<12:56,  1.73s/it]

 48%|████▊     | 412/861 [15:36<16:11,  2.16s/it]

 48%|████▊     | 413/861 [15:37<14:42,  1.97s/it]

 48%|████▊     | 414/861 [15:38<13:08,  1.76s/it]

 48%|████▊     | 415/861 [15:40<12:13,  1.65s/it]

 48%|████▊     | 416/861 [15:41<11:20,  1.53s/it]

 48%|████▊     | 417/861 [15:43<11:34,  1.56s/it]

 49%|████▊     | 418/861 [15:44<12:03,  1.63s/it]

 49%|████▊     | 419/861 [15:46<12:31,  1.70s/it]

 49%|████▉     | 420/861 [15:48<12:57,  1.76s/it]

 49%|████▉     | 421/861 [15:49<10:44,  1.46s/it]

 49%|████▉     | 422/861 [15:50<09:51,  1.35s/it]

 49%|████▉     | 423/861 [15:52<12:19,  1.69s/it]

 49%|████▉     | 424/861 [15:54<12:23,  1.70s/it]

 49%|████▉     | 425/861 [15:56<12:12,  1.68s/it]

 49%|████▉     | 426/861 [15:58<14:00,  1.93s/it]

 50%|████▉     | 427/861 [16:00<13:55,  1.93s/it]

 50%|████▉     | 428/861 [16:02<13:08,  1.82s/it]

 50%|████▉     | 429/861 [16:04<13:50,  1.92s/it]

 50%|████▉     | 430/861 [16:07<16:04,  2.24s/it]

 50%|█████     | 431/861 [16:10<17:25,  2.43s/it]

 50%|█████     | 432/861 [16:13<18:26,  2.58s/it]

 50%|█████     | 433/861 [16:15<18:40,  2.62s/it]

 50%|█████     | 434/861 [16:17<16:38,  2.34s/it]

 51%|█████     | 435/861 [16:18<12:46,  1.80s/it]

 51%|█████     | 436/861 [16:18<10:13,  1.44s/it]

 51%|█████     | 437/861 [16:20<11:24,  1.61s/it]

 51%|█████     | 438/861 [16:21<09:58,  1.41s/it]

 51%|█████     | 439/861 [16:23<10:03,  1.43s/it]

 51%|█████     | 440/861 [16:24<08:40,  1.24s/it]

 51%|█████     | 441/861 [16:24<07:35,  1.08s/it]

 51%|█████▏    | 442/861 [16:26<09:29,  1.36s/it]

 51%|█████▏    | 443/861 [16:27<08:40,  1.25s/it]

 52%|█████▏    | 444/861 [16:28<08:31,  1.23s/it]

 52%|█████▏    | 445/861 [16:29<07:52,  1.14s/it]

 52%|█████▏    | 446/861 [16:30<07:44,  1.12s/it]

 52%|█████▏    | 447/861 [16:33<11:36,  1.68s/it]

 52%|█████▏    | 448/861 [16:36<12:56,  1.88s/it]

 52%|█████▏    | 449/861 [16:38<14:21,  2.09s/it]

 52%|█████▏    | 450/861 [16:40<14:21,  2.10s/it]

 52%|█████▏    | 451/861 [16:42<13:24,  1.96s/it]

 52%|█████▏    | 452/861 [16:44<13:15,  1.95s/it]

 53%|█████▎    | 453/861 [16:45<11:51,  1.74s/it]

 53%|█████▎    | 454/861 [16:47<11:20,  1.67s/it]

 53%|█████▎    | 455/861 [16:49<11:59,  1.77s/it]

 53%|█████▎    | 456/861 [16:50<10:56,  1.62s/it]

 53%|█████▎    | 457/861 [16:52<11:33,  1.72s/it]

 53%|█████▎    | 458/861 [16:55<13:10,  1.96s/it]

 53%|█████▎    | 459/861 [16:56<11:50,  1.77s/it]

 53%|█████▎    | 460/861 [16:57<11:19,  1.69s/it]

 54%|█████▎    | 461/861 [17:00<12:14,  1.84s/it]

 54%|█████▎    | 462/861 [17:01<11:01,  1.66s/it]

 54%|█████▍    | 463/861 [17:02<10:12,  1.54s/it]

 54%|█████▍    | 464/861 [17:03<09:37,  1.46s/it]

 54%|█████▍    | 465/861 [17:04<07:32,  1.14s/it]

 54%|█████▍    | 466/861 [17:05<07:49,  1.19s/it]

 54%|█████▍    | 467/861 [17:09<13:04,  1.99s/it]

 54%|█████▍    | 468/861 [17:10<10:29,  1.60s/it]

 54%|█████▍    | 469/861 [17:11<10:26,  1.60s/it]

 55%|█████▍    | 470/861 [17:12<08:48,  1.35s/it]

 55%|█████▍    | 471/861 [17:14<09:13,  1.42s/it]

 55%|█████▍    | 472/861 [17:14<07:55,  1.22s/it]

 55%|█████▍    | 473/861 [17:16<07:55,  1.23s/it]

 55%|█████▌    | 474/861 [17:16<06:26,  1.00it/s]

 55%|█████▌    | 475/861 [17:18<07:32,  1.17s/it]

 55%|█████▌    | 476/861 [17:18<06:12,  1.03it/s]

 55%|█████▌    | 477/861 [17:20<08:18,  1.30s/it]

 56%|█████▌    | 478/861 [17:22<08:31,  1.33s/it]

 56%|█████▌    | 479/861 [17:22<06:44,  1.06s/it]

 56%|█████▌    | 480/861 [17:23<07:17,  1.15s/it]

 56%|█████▌    | 481/861 [17:24<06:34,  1.04s/it]

 56%|█████▌    | 482/861 [17:25<06:10,  1.02it/s]

 56%|█████▌    | 483/861 [17:26<05:41,  1.11it/s]

 56%|█████▌    | 484/861 [17:27<05:55,  1.06it/s]

 56%|█████▋    | 485/861 [17:27<05:26,  1.15it/s]

 56%|█████▋    | 486/861 [17:28<04:36,  1.35it/s]

 57%|█████▋    | 487/861 [17:29<06:01,  1.04it/s]

 57%|█████▋    | 488/861 [17:30<04:56,  1.26it/s]

 57%|█████▋    | 489/861 [17:31<05:47,  1.07it/s]

 57%|█████▋    | 490/861 [17:32<05:25,  1.14it/s]

 57%|█████▋    | 491/861 [17:33<05:32,  1.11it/s]

 57%|█████▋    | 492/861 [17:33<05:05,  1.21it/s]

 57%|█████▋    | 493/861 [17:35<06:04,  1.01it/s]

 57%|█████▋    | 494/861 [17:35<05:12,  1.18it/s]

 57%|█████▋    | 495/861 [17:37<07:03,  1.16s/it]

 58%|█████▊    | 496/861 [17:39<08:24,  1.38s/it]

 58%|█████▊    | 497/861 [17:39<06:31,  1.07s/it]

 58%|█████▊    | 498/861 [17:41<07:05,  1.17s/it]

 58%|█████▊    | 499/861 [17:41<05:45,  1.05it/s]

 58%|█████▊    | 500/861 [17:42<06:02,  1.01s/it]

 58%|█████▊    | 501/861 [17:43<05:02,  1.19it/s]

 58%|█████▊    | 502/861 [17:45<06:35,  1.10s/it]

 58%|█████▊    | 503/861 [17:46<06:43,  1.13s/it]

 59%|█████▊    | 504/861 [17:47<07:19,  1.23s/it]

 59%|█████▊    | 505/861 [17:48<06:17,  1.06s/it]

 59%|█████▉    | 506/861 [17:49<05:41,  1.04it/s]

 59%|█████▉    | 507/861 [17:49<04:44,  1.24it/s]

 59%|█████▉    | 508/861 [17:51<06:41,  1.14s/it]

 59%|█████▉    | 509/861 [17:53<09:10,  1.56s/it]

 59%|█████▉    | 510/861 [17:55<09:54,  1.69s/it]

 59%|█████▉    | 511/861 [17:58<10:53,  1.87s/it]

 59%|█████▉    | 512/861 [17:59<09:49,  1.69s/it]

 60%|█████▉    | 513/861 [18:00<09:24,  1.62s/it]

 60%|█████▉    | 514/861 [18:02<09:11,  1.59s/it]

 60%|█████▉    | 515/861 [18:03<07:22,  1.28s/it]

 60%|█████▉    | 516/861 [18:03<05:49,  1.01s/it]

 60%|██████    | 517/861 [18:03<04:45,  1.21it/s]

 60%|██████    | 518/861 [18:05<06:14,  1.09s/it]

 60%|██████    | 519/861 [18:07<07:17,  1.28s/it]

 60%|██████    | 520/861 [18:09<08:18,  1.46s/it]

 61%|██████    | 521/861 [18:10<08:05,  1.43s/it]

 61%|██████    | 522/861 [18:12<08:49,  1.56s/it]

 61%|██████    | 523/861 [18:14<09:37,  1.71s/it]

 61%|██████    | 524/861 [18:17<11:46,  2.10s/it]

 61%|██████    | 525/861 [18:19<10:55,  1.95s/it]

 61%|██████    | 526/861 [18:20<10:12,  1.83s/it]

 61%|██████    | 527/861 [18:22<09:40,  1.74s/it]

 61%|██████▏   | 528/861 [18:24<10:43,  1.93s/it]

 61%|██████▏   | 529/861 [18:25<08:44,  1.58s/it]

 62%|██████▏   | 530/861 [18:26<07:56,  1.44s/it]

 62%|██████▏   | 531/861 [18:27<06:57,  1.26s/it]

 62%|██████▏   | 532/861 [18:29<07:47,  1.42s/it]

 62%|██████▏   | 533/861 [18:29<07:00,  1.28s/it]

 62%|██████▏   | 534/861 [18:31<07:01,  1.29s/it]

 62%|██████▏   | 535/861 [18:32<06:58,  1.28s/it]

 62%|██████▏   | 536/861 [18:33<07:08,  1.32s/it]

 62%|██████▏   | 537/861 [18:36<08:34,  1.59s/it]

 62%|██████▏   | 538/861 [18:37<07:36,  1.41s/it]

 63%|██████▎   | 539/861 [18:40<10:49,  2.02s/it]

 63%|██████▎   | 540/861 [18:42<10:25,  1.95s/it]

 63%|██████▎   | 541/861 [18:43<09:18,  1.74s/it]

 63%|██████▎   | 542/861 [18:44<08:20,  1.57s/it]

 63%|██████▎   | 543/861 [18:47<09:36,  1.81s/it]

 63%|██████▎   | 544/861 [18:48<08:24,  1.59s/it]

 63%|██████▎   | 545/861 [18:51<10:29,  1.99s/it]

 63%|██████▎   | 546/861 [18:53<10:49,  2.06s/it]

 64%|██████▎   | 547/861 [18:55<10:25,  1.99s/it]

 64%|██████▎   | 548/861 [18:58<12:01,  2.30s/it]

 64%|██████▍   | 549/861 [19:00<12:20,  2.37s/it]

 64%|██████▍   | 550/861 [19:03<12:09,  2.35s/it]

 64%|██████▍   | 551/861 [19:04<11:22,  2.20s/it]

 64%|██████▍   | 552/861 [19:08<12:59,  2.52s/it]

 64%|██████▍   | 553/861 [19:11<14:01,  2.73s/it]

 64%|██████▍   | 554/861 [19:14<14:51,  2.90s/it]

 64%|██████▍   | 555/861 [19:17<14:59,  2.94s/it]

 65%|██████▍   | 556/861 [19:20<14:33,  2.86s/it]

 65%|██████▍   | 557/861 [19:23<15:03,  2.97s/it]

 65%|██████▍   | 558/861 [19:26<15:26,  3.06s/it]

 65%|██████▍   | 559/861 [19:30<16:08,  3.21s/it]

 65%|██████▌   | 560/861 [19:33<16:03,  3.20s/it]

 65%|██████▌   | 561/861 [19:36<14:48,  2.96s/it]

 65%|██████▌   | 562/861 [19:40<16:25,  3.30s/it]

 65%|██████▌   | 563/861 [19:42<15:23,  3.10s/it]

 66%|██████▌   | 564/861 [19:46<16:31,  3.34s/it]

 66%|██████▌   | 565/861 [19:50<16:53,  3.42s/it]

 66%|██████▌   | 566/861 [19:54<18:30,  3.76s/it]

 66%|██████▌   | 567/861 [19:57<16:42,  3.41s/it]

 66%|██████▌   | 568/861 [20:00<16:10,  3.31s/it]

 66%|██████▌   | 569/861 [20:03<15:37,  3.21s/it]

 66%|██████▌   | 570/861 [20:05<14:10,  2.92s/it]

 66%|██████▋   | 571/861 [20:09<14:37,  3.02s/it]

 66%|██████▋   | 572/861 [20:12<15:33,  3.23s/it]

 67%|██████▋   | 573/861 [20:14<13:40,  2.85s/it]

 67%|██████▋   | 574/861 [20:17<13:29,  2.82s/it]

 67%|██████▋   | 575/861 [20:21<14:34,  3.06s/it]

 67%|██████▋   | 576/861 [20:25<17:10,  3.61s/it]

 67%|██████▋   | 577/861 [20:30<18:01,  3.81s/it]

 67%|██████▋   | 578/861 [20:35<20:13,  4.29s/it]

 67%|██████▋   | 579/861 [20:41<22:22,  4.76s/it]

 67%|██████▋   | 580/861 [20:44<19:49,  4.23s/it]

 67%|██████▋   | 581/861 [20:47<17:44,  3.80s/it]

 68%|██████▊   | 582/861 [20:52<19:14,  4.14s/it]

 68%|██████▊   | 583/861 [20:55<17:54,  3.86s/it]

 68%|██████▊   | 584/861 [20:57<15:57,  3.46s/it]

 68%|██████▊   | 585/861 [21:03<18:16,  3.97s/it]

 68%|██████▊   | 586/861 [21:05<15:17,  3.34s/it]

 68%|██████▊   | 587/861 [21:08<15:27,  3.39s/it]

 68%|██████▊   | 588/861 [21:11<14:21,  3.16s/it]

 68%|██████▊   | 589/861 [21:12<12:17,  2.71s/it]

 69%|██████▊   | 590/861 [21:17<14:48,  3.28s/it]

 69%|██████▊   | 591/861 [21:19<13:38,  3.03s/it]

 69%|██████▉   | 592/861 [21:23<13:52,  3.09s/it]

 69%|██████▉   | 593/861 [21:26<14:10,  3.17s/it]

 69%|██████▉   | 594/861 [21:29<14:20,  3.22s/it]

 69%|██████▉   | 595/861 [21:31<12:26,  2.81s/it]

 69%|██████▉   | 596/861 [21:32<10:17,  2.33s/it]

 69%|██████▉   | 597/861 [21:37<12:47,  2.91s/it]

 69%|██████▉   | 598/861 [21:40<12:51,  2.94s/it]

 70%|██████▉   | 599/861 [21:42<12:26,  2.85s/it]

 70%|██████▉   | 600/861 [21:45<11:42,  2.69s/it]

 70%|██████▉   | 601/861 [21:47<10:57,  2.53s/it]

 70%|██████▉   | 602/861 [21:50<11:53,  2.75s/it]

 70%|███████   | 603/861 [21:54<12:51,  2.99s/it]

 70%|███████   | 604/861 [21:57<13:03,  3.05s/it]

 70%|███████   | 605/861 [21:59<11:30,  2.70s/it]

 70%|███████   | 606/861 [22:01<10:30,  2.47s/it]

 70%|███████   | 607/861 [22:02<09:35,  2.27s/it]

 71%|███████   | 608/861 [22:04<08:58,  2.13s/it]

 71%|███████   | 609/861 [22:08<10:47,  2.57s/it]

 71%|███████   | 610/861 [22:12<12:19,  2.94s/it]

 71%|███████   | 611/861 [22:14<11:40,  2.80s/it]

 71%|███████   | 612/861 [22:16<11:11,  2.70s/it]

 71%|███████   | 613/861 [22:18<09:22,  2.27s/it]

 71%|███████▏  | 614/861 [22:20<09:47,  2.38s/it]

 71%|███████▏  | 615/861 [22:24<10:39,  2.60s/it]

 72%|███████▏  | 616/861 [22:29<13:45,  3.37s/it]

 72%|███████▏  | 617/861 [22:32<14:07,  3.47s/it]

 72%|███████▏  | 618/861 [22:36<13:46,  3.40s/it]

 72%|███████▏  | 619/861 [22:38<12:31,  3.11s/it]

 72%|███████▏  | 620/861 [22:42<13:34,  3.38s/it]

 72%|███████▏  | 621/861 [22:45<12:58,  3.24s/it]

 72%|███████▏  | 622/861 [22:47<10:55,  2.74s/it]

 72%|███████▏  | 623/861 [22:51<13:24,  3.38s/it]

 72%|███████▏  | 624/861 [22:55<13:01,  3.30s/it]

 73%|███████▎  | 625/861 [22:56<10:24,  2.65s/it]

 73%|███████▎  | 626/861 [22:58<09:28,  2.42s/it]

 73%|███████▎  | 627/861 [23:01<10:33,  2.71s/it]

 73%|███████▎  | 628/861 [23:04<11:28,  2.96s/it]

 73%|███████▎  | 629/861 [23:09<12:45,  3.30s/it]

 73%|███████▎  | 630/861 [23:12<12:51,  3.34s/it]

 73%|███████▎  | 631/861 [23:13<10:02,  2.62s/it]

 73%|███████▎  | 632/861 [23:16<10:43,  2.81s/it]

 74%|███████▎  | 633/861 [23:19<10:18,  2.71s/it]

 74%|███████▎  | 634/861 [23:22<11:19,  2.99s/it]

 74%|███████▍  | 635/861 [23:25<10:33,  2.80s/it]

 74%|███████▍  | 636/861 [23:27<09:37,  2.57s/it]

 74%|███████▍  | 637/861 [23:28<08:38,  2.31s/it]

 74%|███████▍  | 638/861 [23:30<08:00,  2.15s/it]

 74%|███████▍  | 639/861 [23:33<09:08,  2.47s/it]

 74%|███████▍  | 640/861 [23:35<08:39,  2.35s/it]

 74%|███████▍  | 641/861 [23:38<08:25,  2.30s/it]

 75%|███████▍  | 642/861 [23:39<07:45,  2.13s/it]

 75%|███████▍  | 643/861 [23:41<07:20,  2.02s/it]

 75%|███████▍  | 644/861 [23:43<07:21,  2.04s/it]

 75%|███████▍  | 645/861 [23:44<06:02,  1.68s/it]

 75%|███████▌  | 646/861 [23:46<05:49,  1.63s/it]

 75%|███████▌  | 647/861 [23:47<05:09,  1.45s/it]

 75%|███████▌  | 648/861 [23:48<05:36,  1.58s/it]

 75%|███████▌  | 649/861 [23:50<05:40,  1.61s/it]

 75%|███████▌  | 650/861 [23:52<05:27,  1.55s/it]

 76%|███████▌  | 651/861 [23:53<04:45,  1.36s/it]

 76%|███████▌  | 652/861 [23:54<04:52,  1.40s/it]

 76%|███████▌  | 653/861 [23:55<04:33,  1.31s/it]

 76%|███████▌  | 654/861 [23:56<04:26,  1.29s/it]

 76%|███████▌  | 655/861 [23:57<03:56,  1.15s/it]

 76%|███████▌  | 656/861 [23:58<03:21,  1.02it/s]

 76%|███████▋  | 657/861 [23:59<03:28,  1.02s/it]

 76%|███████▋  | 658/861 [24:01<04:09,  1.23s/it]

 77%|███████▋  | 659/861 [24:02<04:06,  1.22s/it]

 77%|███████▋  | 660/861 [24:04<04:40,  1.40s/it]

 77%|███████▋  | 661/861 [24:05<04:51,  1.46s/it]

 77%|███████▋  | 662/861 [24:08<05:54,  1.78s/it]

 77%|███████▋  | 663/861 [24:10<06:51,  2.08s/it]

 77%|███████▋  | 664/861 [24:12<05:50,  1.78s/it]

 77%|███████▋  | 665/861 [24:13<05:06,  1.56s/it]

 77%|███████▋  | 666/861 [24:14<04:27,  1.37s/it]

 77%|███████▋  | 667/861 [24:15<04:27,  1.38s/it]

 78%|███████▊  | 668/861 [24:16<04:16,  1.33s/it]

 78%|███████▊  | 669/861 [24:17<03:42,  1.16s/it]

 78%|███████▊  | 670/861 [24:18<03:45,  1.18s/it]

 78%|███████▊  | 671/861 [24:19<03:04,  1.03it/s]

 78%|███████▊  | 672/861 [24:21<04:22,  1.39s/it]

 78%|███████▊  | 673/861 [24:23<05:16,  1.68s/it]

 78%|███████▊  | 674/861 [24:25<04:54,  1.57s/it]

 78%|███████▊  | 675/861 [24:29<07:11,  2.32s/it]

 79%|███████▊  | 676/861 [24:30<06:22,  2.07s/it]

 79%|███████▊  | 677/861 [24:32<06:16,  2.05s/it]

 79%|███████▊  | 678/861 [24:33<05:15,  1.73s/it]

 79%|███████▉  | 679/861 [24:34<04:37,  1.52s/it]

 79%|███████▉  | 680/861 [24:35<04:01,  1.34s/it]

 79%|███████▉  | 681/861 [24:38<04:56,  1.65s/it]

 79%|███████▉  | 682/861 [24:39<05:04,  1.70s/it]

 79%|███████▉  | 683/861 [24:41<04:43,  1.59s/it]

 79%|███████▉  | 684/861 [24:43<05:38,  1.91s/it]

 80%|███████▉  | 685/861 [24:45<04:59,  1.70s/it]

 80%|███████▉  | 686/861 [24:46<04:35,  1.58s/it]

 80%|███████▉  | 687/861 [24:50<06:45,  2.33s/it]

 80%|███████▉  | 688/861 [24:51<05:37,  1.95s/it]

 80%|████████  | 689/861 [24:53<05:13,  1.82s/it]

 80%|████████  | 690/861 [24:54<04:52,  1.71s/it]

 80%|████████  | 691/861 [24:56<05:09,  1.82s/it]

 80%|████████  | 692/861 [24:58<05:00,  1.78s/it]

 80%|████████  | 693/861 [24:59<04:36,  1.64s/it]

 81%|████████  | 694/861 [25:00<04:06,  1.48s/it]

 81%|████████  | 695/861 [25:02<04:45,  1.72s/it]

 81%|████████  | 696/861 [25:03<04:01,  1.46s/it]

 81%|████████  | 697/861 [25:05<03:52,  1.42s/it]

 81%|████████  | 698/861 [25:06<03:51,  1.42s/it]

 81%|████████  | 699/861 [25:11<06:17,  2.33s/it]

 81%|████████▏ | 700/861 [25:14<07:02,  2.62s/it]

 81%|████████▏ | 701/861 [25:15<06:14,  2.34s/it]

 82%|████████▏ | 702/861 [25:17<05:34,  2.10s/it]

 82%|████████▏ | 703/861 [25:18<04:57,  1.88s/it]

 82%|████████▏ | 704/861 [25:20<04:40,  1.79s/it]

 82%|████████▏ | 705/861 [25:22<04:37,  1.78s/it]

 82%|████████▏ | 706/861 [25:23<03:57,  1.53s/it]

 82%|████████▏ | 707/861 [25:23<03:20,  1.30s/it]

 82%|████████▏ | 708/861 [25:25<03:11,  1.25s/it]

 82%|████████▏ | 709/861 [25:26<03:17,  1.30s/it]

 82%|████████▏ | 710/861 [25:28<04:07,  1.64s/it]

 83%|████████▎ | 711/861 [25:30<04:16,  1.71s/it]

 83%|████████▎ | 712/861 [25:32<03:53,  1.57s/it]

 83%|████████▎ | 713/861 [25:32<03:07,  1.27s/it]

 83%|████████▎ | 714/861 [25:34<03:16,  1.33s/it]

 83%|████████▎ | 715/861 [25:36<04:07,  1.69s/it]

 83%|████████▎ | 716/861 [25:38<04:23,  1.82s/it]

 83%|████████▎ | 717/861 [25:40<03:59,  1.66s/it]

 83%|████████▎ | 718/861 [25:42<04:14,  1.78s/it]

 84%|████████▎ | 719/861 [25:43<03:43,  1.57s/it]

 84%|████████▎ | 720/861 [25:44<03:18,  1.41s/it]

 84%|████████▎ | 721/861 [25:45<03:00,  1.29s/it]

 84%|████████▍ | 722/861 [25:46<03:16,  1.42s/it]

 84%|████████▍ | 723/861 [25:48<03:03,  1.33s/it]

 84%|████████▍ | 724/861 [25:49<02:56,  1.29s/it]

 84%|████████▍ | 725/861 [25:50<02:50,  1.25s/it]

 84%|████████▍ | 726/861 [25:52<03:05,  1.38s/it]

 84%|████████▍ | 727/861 [25:54<03:51,  1.73s/it]

 85%|████████▍ | 728/861 [25:56<03:53,  1.75s/it]

 85%|████████▍ | 729/861 [25:57<03:29,  1.58s/it]

 85%|████████▍ | 730/861 [25:58<02:50,  1.30s/it]

 85%|████████▍ | 731/861 [26:00<03:30,  1.62s/it]

 85%|████████▌ | 732/861 [26:01<03:06,  1.45s/it]

 85%|████████▌ | 733/861 [26:03<03:03,  1.43s/it]

 85%|████████▌ | 734/861 [26:03<02:31,  1.19s/it]

 85%|████████▌ | 735/861 [26:04<02:20,  1.12s/it]

 85%|████████▌ | 736/861 [26:06<02:31,  1.21s/it]

 86%|████████▌ | 737/861 [26:07<02:55,  1.41s/it]

 86%|████████▌ | 738/861 [26:09<03:00,  1.47s/it]

 86%|████████▌ | 739/861 [26:10<02:47,  1.37s/it]

 86%|████████▌ | 740/861 [26:11<02:34,  1.27s/it]

 86%|████████▌ | 741/861 [26:13<02:49,  1.41s/it]

 86%|████████▌ | 742/861 [26:15<02:56,  1.48s/it]

 86%|████████▋ | 743/861 [26:16<02:35,  1.31s/it]

 86%|████████▋ | 744/861 [26:17<02:22,  1.22s/it]

 87%|████████▋ | 745/861 [26:19<02:48,  1.45s/it]

 87%|████████▋ | 746/861 [26:20<02:33,  1.33s/it]

 87%|████████▋ | 747/861 [26:22<03:09,  1.66s/it]

 87%|████████▋ | 748/861 [26:24<03:25,  1.82s/it]

 87%|████████▋ | 749/861 [26:26<03:18,  1.77s/it]

 87%|████████▋ | 750/861 [26:27<02:46,  1.50s/it]

 87%|████████▋ | 751/861 [26:27<02:07,  1.16s/it]

 87%|████████▋ | 752/861 [26:31<03:26,  1.90s/it]

 87%|████████▋ | 753/861 [26:33<03:42,  2.06s/it]

 88%|████████▊ | 754/861 [26:34<03:04,  1.72s/it]

 88%|████████▊ | 755/861 [26:35<02:45,  1.56s/it]

 88%|████████▊ | 756/861 [26:37<02:33,  1.46s/it]

 88%|████████▊ | 757/861 [26:39<03:06,  1.79s/it]

 88%|████████▊ | 758/861 [26:40<02:51,  1.66s/it]

 88%|████████▊ | 759/861 [26:42<02:33,  1.50s/it]

 88%|████████▊ | 760/861 [26:44<03:08,  1.87s/it]

 88%|████████▊ | 761/861 [26:50<05:05,  3.05s/it]

 89%|████████▊ | 762/861 [26:51<04:12,  2.55s/it]

 89%|████████▊ | 763/861 [26:53<03:36,  2.21s/it]

 89%|████████▊ | 764/861 [26:55<03:19,  2.05s/it]

 89%|████████▉ | 765/861 [26:57<03:38,  2.27s/it]

 89%|████████▉ | 766/861 [27:00<03:33,  2.25s/it]

 89%|████████▉ | 767/861 [27:05<05:09,  3.30s/it]

 89%|████████▉ | 768/861 [27:08<04:38,  3.00s/it]

 89%|████████▉ | 769/861 [27:10<04:13,  2.76s/it]

 89%|████████▉ | 770/861 [27:11<03:26,  2.27s/it]

 90%|████████▉ | 771/861 [27:12<02:54,  1.94s/it]

 90%|████████▉ | 772/861 [27:15<03:06,  2.09s/it]

 90%|████████▉ | 773/861 [27:18<03:39,  2.49s/it]

 90%|████████▉ | 774/861 [27:20<03:19,  2.29s/it]

 90%|█████████ | 775/861 [27:23<03:29,  2.43s/it]

 90%|█████████ | 776/861 [27:25<03:37,  2.55s/it]

 90%|█████████ | 777/861 [27:29<03:55,  2.81s/it]

 90%|█████████ | 778/861 [27:31<03:35,  2.59s/it]

 90%|█████████ | 779/861 [27:35<04:21,  3.19s/it]

 91%|█████████ | 780/861 [27:39<04:33,  3.38s/it]

 91%|█████████ | 781/861 [27:44<05:04,  3.81s/it]

 91%|█████████ | 782/861 [27:47<04:46,  3.62s/it]

 91%|█████████ | 783/861 [27:49<04:04,  3.14s/it]

 91%|█████████ | 784/861 [27:54<04:38,  3.62s/it]

 91%|█████████ | 785/861 [27:56<03:53,  3.07s/it]

 91%|█████████▏| 786/861 [27:57<03:18,  2.65s/it]

 91%|█████████▏| 787/861 [27:59<02:53,  2.35s/it]

 92%|█████████▏| 788/861 [28:03<03:34,  2.93s/it]

 92%|█████████▏| 789/861 [28:06<03:21,  2.79s/it]

 92%|█████████▏| 790/861 [28:08<03:08,  2.66s/it]

 92%|█████████▏| 791/861 [28:10<02:52,  2.46s/it]

 92%|█████████▏| 792/861 [28:12<02:29,  2.17s/it]

 92%|█████████▏| 793/861 [28:15<02:40,  2.36s/it]

 92%|█████████▏| 794/861 [28:16<02:14,  2.00s/it]

 92%|█████████▏| 795/861 [28:22<03:27,  3.14s/it]

 92%|█████████▏| 796/861 [28:23<02:46,  2.56s/it]

 93%|█████████▎| 797/861 [28:24<02:27,  2.30s/it]

 93%|█████████▎| 798/861 [28:27<02:37,  2.51s/it]

 93%|█████████▎| 799/861 [28:30<02:38,  2.55s/it]

 93%|█████████▎| 800/861 [28:32<02:32,  2.49s/it]

 93%|█████████▎| 801/861 [28:35<02:30,  2.52s/it]

 93%|█████████▎| 802/861 [28:37<02:22,  2.42s/it]

 93%|█████████▎| 803/861 [28:40<02:21,  2.44s/it]

 93%|█████████▎| 804/861 [28:45<03:11,  3.35s/it]

 93%|█████████▎| 805/861 [28:50<03:31,  3.77s/it]

 94%|█████████▎| 806/861 [28:51<02:38,  2.88s/it]

 94%|█████████▎| 807/861 [28:53<02:20,  2.61s/it]

 94%|█████████▍| 808/861 [28:55<02:09,  2.44s/it]

 94%|█████████▍| 809/861 [28:55<01:40,  1.93s/it]

 94%|█████████▍| 810/861 [28:57<01:34,  1.85s/it]

 94%|█████████▍| 811/861 [28:59<01:39,  2.00s/it]

 94%|█████████▍| 812/861 [29:01<01:31,  1.86s/it]

 94%|█████████▍| 813/861 [29:04<01:48,  2.25s/it]

 95%|█████████▍| 814/861 [29:07<01:53,  2.42s/it]

 95%|█████████▍| 815/861 [29:10<01:52,  2.45s/it]

 95%|█████████▍| 816/861 [29:11<01:37,  2.16s/it]

 95%|█████████▍| 817/861 [29:13<01:39,  2.25s/it]

 95%|█████████▌| 818/861 [29:16<01:41,  2.37s/it]

 95%|█████████▌| 819/861 [29:17<01:26,  2.06s/it]

 95%|█████████▌| 820/861 [29:20<01:30,  2.20s/it]

 95%|█████████▌| 821/861 [29:23<01:43,  2.58s/it]

 95%|█████████▌| 822/861 [29:27<01:48,  2.79s/it]

 96%|█████████▌| 823/861 [29:31<01:57,  3.09s/it]

 96%|█████████▌| 824/861 [29:32<01:35,  2.58s/it]

 96%|█████████▌| 825/861 [29:33<01:20,  2.22s/it]

 96%|█████████▌| 826/861 [29:36<01:21,  2.32s/it]

 96%|█████████▌| 827/861 [29:38<01:21,  2.40s/it]

 96%|█████████▌| 828/861 [29:40<01:11,  2.16s/it]

 96%|█████████▋| 829/861 [29:43<01:17,  2.43s/it]

 96%|█████████▋| 830/861 [29:46<01:16,  2.48s/it]

 97%|█████████▋| 831/861 [29:48<01:15,  2.53s/it]

 97%|█████████▋| 832/861 [29:51<01:16,  2.63s/it]

 97%|█████████▋| 833/861 [29:52<01:01,  2.19s/it]

 97%|█████████▋| 834/861 [29:55<01:00,  2.23s/it]

 97%|█████████▋| 835/861 [29:57<00:57,  2.22s/it]

 97%|█████████▋| 836/861 [29:59<00:57,  2.29s/it]

 97%|█████████▋| 837/861 [30:02<00:56,  2.34s/it]

 97%|█████████▋| 838/861 [30:04<00:56,  2.44s/it]

 97%|█████████▋| 839/861 [30:06<00:47,  2.16s/it]

 98%|█████████▊| 840/861 [30:08<00:44,  2.14s/it]

 98%|█████████▊| 841/861 [30:10<00:42,  2.12s/it]

 98%|█████████▊| 842/861 [30:12<00:39,  2.07s/it]

 98%|█████████▊| 843/861 [30:15<00:41,  2.33s/it]

 98%|█████████▊| 844/861 [30:17<00:37,  2.23s/it]

 98%|█████████▊| 845/861 [30:19<00:36,  2.29s/it]

 98%|█████████▊| 846/861 [30:21<00:32,  2.19s/it]

 98%|█████████▊| 847/861 [30:24<00:30,  2.19s/it]

 98%|█████████▊| 848/861 [30:27<00:31,  2.43s/it]

 99%|█████████▊| 849/861 [30:29<00:29,  2.49s/it]

 99%|█████████▊| 850/861 [30:31<00:23,  2.17s/it]

 99%|█████████▉| 851/861 [30:33<00:21,  2.10s/it]

 99%|█████████▉| 852/861 [30:34<00:16,  1.89s/it]

 99%|█████████▉| 853/861 [30:37<00:18,  2.29s/it]

 99%|█████████▉| 854/861 [30:39<00:14,  2.13s/it]

 99%|█████████▉| 855/861 [30:41<00:12,  2.13s/it]

 99%|█████████▉| 856/861 [30:44<00:12,  2.45s/it]

100%|█████████▉| 857/861 [30:46<00:09,  2.30s/it]

100%|█████████▉| 858/861 [30:48<00:06,  2.27s/it]

100%|█████████▉| 859/861 [30:51<00:04,  2.36s/it]

100%|█████████▉| 860/861 [30:56<00:03,  3.23s/it]

100%|██████████| 861/861 [30:58<00:00,  2.86s/it]{'score': 0.0746729450060007, 'counts': [9027, 347, 98, 29], 'totals': [413937, 412215, 410493, 408771], 'precisions': [2.180766638401496, 0.08417937241488059, 0.023873732316994443, 0.007094436738418332], 'bp': 1.0, 'sys_len': 413937, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.8610005378723145, 'eval_bleu': 0.0747, 'eval_gen_len': 113.0081, 'eval_runtime': 1965.2378, 'eval_samples_per_second': 0.876, 'eval_steps_per_second': 0.438, 'epoch': 2.0}

 13%|█▎        | 7739/61904 [4:02:51<21:12:27,  1.41s/it]

100%|██████████| 861/861 [32:42<00:00,  2.86s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-25 05:24:00,754 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 13%|█▎        | 7740/61904 [4:03:13<8981:53:45, 596.98s/it]
                                                            
{'loss': 2.8846, 'learning_rate': 1.8778037080254114e-07, 'epoch': 2.0}

 13%|█▎        | 7740/61904 [4:03:13<8981:53:45, 596.98s/it]
 13%|█▎        | 7741/61904 [4:03:14<6294:35:44, 418.38s/it]
 13%|█▎        | 7742/61904 [4:03:16<4412:32:50, 293.29s/it]
 13%|█▎        | 7743/61904 [4:03:17<3095:55:39, 205.78s/it]
 13%|█▎        | 7744/61904 [4:03:19<2173:25:21, 144.47s/it]
 13%|█▎        | 7745/61904 [4:03:20<1527:26:31, 101.53s/it]
 13%|█▎        | 7746/61904 [4:03:21<1075:47:08, 71.51s/it] 
 13%|█▎        | 7747/61904 [4:03:23<759:00:34, 50.45s/it] 
 13%|█▎        | 7748/61904 [4:03:24<537:19:22, 35.72s/it]
 13%|█▎        | 7749/61904 [4:03:26<383:04:52, 25.47s/it]
 13%|█▎        | 7750/61904 [4:03:27<274:40:16, 18.26s/it]
 13%|█▎        | 7751/61904 [4:03:28<198:03:11, 13.17s/it]
 13%|█▎        | 7752/61904 [4:03:30<144:57:18,  9.64s/it]
 13%|█▎        | 7753/61904 [4:03:31<107:21:09,  7.14s/it]
 13%|█▎        | 7754/61904 [4:03:33<81:43:30,  5.43s/it] 
 13%|█▎        | 7755/61904 [4:03:34<63:53:19,  4.25s/it]
 13%|█▎        | 7756/61904 [4:03:35<50:55:00,  3.39s/it]
 13%|█▎        | 7757/61904 [4:03:37<41:40:24,  2.77s/it]
 13%|█▎        | 7758/61904 [4:03:38<35:20:56,  2.35s/it]
 13%|█▎        | 7759/61904 [4:03:40<31:42:49,  2.11s/it]
 13%|█▎        | 7760/61904 [4:03:41<28:36:23,  1.90s/it]
                                                         
{'loss': 2.954, 'learning_rate': 1.8774795799299882e-07, 'epoch': 2.01}

 13%|█▎        | 7760/61904 [4:03:41<28:36:23,  1.90s/it]
 13%|█▎        | 7761/61904 [4:03:42<25:49:01,  1.72s/it]
 13%|█▎        | 7762/61904 [4:03:44<24:44:08,  1.64s/it]
 13%|█▎        | 7763/61904 [4:03:45<23:22:02,  1.55s/it]
 13%|█▎        | 7764/61904 [4:03:47<22:52:41,  1.52s/it]
 13%|█▎        | 7765/61904 [4:03:48<21:59:31,  1.46s/it]
 13%|█▎        | 7766/61904 [4:03:49<21:38:15,  1.44s/it]
 13%|█▎        | 7767/61904 [4:03:51<21:01:04,  1.40s/it]
 13%|█▎        | 7768/61904 [4:03:52<21:06:03,  1.40s/it]
 13%|█▎        | 7769/61904 [4:03:53<20:51:05,  1.39s/it]
 13%|█▎        | 7770/61904 [4:03:55<20:26:06,  1.36s/it]
 13%|█▎        | 7771/61904 [4:03:56<21:34:45,  1.44s/it]
 13%|█▎        | 7772/61904 [4:03:58<21:46:10,  1.45s/it]
 13%|█▎        | 7773/61904 [4:03:59<21:50:34,  1.45s/it]
 13%|█▎        | 7774/61904 [4:04:01<21:52:49,  1.46s/it]
 13%|█▎        | 7775/61904 [4:04:02<21:18:00,  1.42s/it]
 13%|█▎        | 7776/61904 [4:04:03<21:13:53,  1.41s/it]
 13%|█▎        | 7777/61904 [4:04:05<20:48:41,  1.38s/it]
 13%|█▎        | 7778/61904 [4:04:06<20:11:15,  1.34s/it]
 13%|█▎        | 7779/61904 [4:04:08<22:02:09,  1.47s/it]
 13%|█▎        | 7780/61904 [4:04:09<22:08:46,  1.47s/it]
                                                         
{'loss': 2.9074, 'learning_rate': 1.8771554518345649e-07, 'epoch': 2.01}

 13%|█▎        | 7780/61904 [4:04:09<22:08:46,  1.47s/it]
 13%|█▎        | 7781/61904 [4:04:11<22:02:07,  1.47s/it]
 13%|█▎        | 7782/61904 [4:04:12<21:16:38,  1.42s/it]
 13%|█▎        | 7783/61904 [4:04:13<20:51:55,  1.39s/it]
 13%|█▎        | 7784/61904 [4:04:15<21:14:21,  1.41s/it]
 13%|█▎        | 7785/61904 [4:04:16<20:54:57,  1.39s/it]
 13%|█▎        | 7786/61904 [4:04:18<21:06:56,  1.40s/it]
 13%|█▎        | 7787/61904 [4:04:19<21:30:57,  1.43s/it]
 13%|█▎        | 7788/61904 [4:04:20<21:36:34,  1.44s/it]
 13%|█▎        | 7789/61904 [4:04:22<21:09:52,  1.41s/it]
 13%|█▎        | 7790/61904 [4:04:23<20:48:51,  1.38s/it]
 13%|█▎        | 7791/61904 [4:04:25<20:38:53,  1.37s/it]
 13%|█▎        | 7792/61904 [4:04:26<21:03:17,  1.40s/it]
 13%|█▎        | 7793/61904 [4:04:27<20:41:08,  1.38s/it]
 13%|█▎        | 7794/61904 [4:04:29<20:28:24,  1.36s/it]
 13%|█▎        | 7795/61904 [4:04:30<20:29:12,  1.36s/it]
 13%|█▎        | 7796/61904 [4:04:31<21:04:25,  1.40s/it]
 13%|█▎        | 7797/61904 [4:04:33<21:29:19,  1.43s/it]
 13%|█▎        | 7798/61904 [4:04:34<21:07:13,  1.41s/it]
 13%|█▎        | 7799/61904 [4:04:36<20:50:26,  1.39s/it]
 13%|█▎        | 7800/61904 [4:04:37<20:31:32,  1.37s/it]
                                                         
{'loss': 2.8973, 'learning_rate': 1.8768313237391415e-07, 'epoch': 2.02}

 13%|█▎        | 7800/61904 [4:04:37<20:31:32,  1.37s/it]
 13%|█▎        | 7801/61904 [4:04:38<21:02:55,  1.40s/it]
 13%|█▎        | 7802/61904 [4:04:40<21:09:16,  1.41s/it]
 13%|█▎        | 7803/61904 [4:04:41<21:11:41,  1.41s/it]
 13%|█▎        | 7804/61904 [4:04:43<21:54:44,  1.46s/it]
 13%|█▎        | 7805/61904 [4:04:45<22:55:43,  1.53s/it]
 13%|█▎        | 7806/61904 [4:04:46<22:01:23,  1.47s/it]
 13%|█▎        | 7807/61904 [4:04:47<21:55:16,  1.46s/it]
 13%|█▎        | 7808/61904 [4:04:49<21:02:42,  1.40s/it]
 13%|█▎        | 7809/61904 [4:04:50<20:10:06,  1.34s/it]
 13%|█▎        | 7810/61904 [4:04:51<20:58:23,  1.40s/it]
 13%|█▎        | 7811/61904 [4:04:53<21:30:50,  1.43s/it]
 13%|█▎        | 7812/61904 [4:04:54<21:09:00,  1.41s/it]
 13%|█▎        | 7813/61904 [4:04:56<21:26:12,  1.43s/it]
 13%|█▎        | 7814/61904 [4:04:57<21:19:53,  1.42s/it]
 13%|█▎        | 7815/61904 [4:04:59<21:35:14,  1.44s/it]
 13%|█▎        | 7816/61904 [4:05:00<21:12:04,  1.41s/it]
 13%|█▎        | 7817/61904 [4:05:01<20:58:11,  1.40s/it]
 13%|█▎        | 7818/61904 [4:05:03<20:52:47,  1.39s/it]
 13%|█▎        | 7819/61904 [4:05:04<20:24:17,  1.36s/it]
 13%|█▎        | 7820/61904 [4:05:05<20:50:50,  1.39s/it]
                                                         
{'loss': 2.9155, 'learning_rate': 1.8765071956437184e-07, 'epoch': 2.02}

 13%|█▎        | 7820/61904 [4:05:05<20:50:50,  1.39s/it]
 13%|█▎        | 7821/61904 [4:05:07<20:23:42,  1.36s/it]
 13%|█▎        | 7822/61904 [4:05:08<20:21:56,  1.36s/it]
 13%|█▎        | 7823/61904 [4:05:09<20:27:54,  1.36s/it]
 13%|█▎        | 7824/61904 [4:05:11<20:45:23,  1.38s/it]
 13%|█▎        | 7825/61904 [4:05:12<21:18:26,  1.42s/it]
 13%|█▎        | 7826/61904 [4:05:14<21:53:08,  1.46s/it]
 13%|█▎        | 7827/61904 [4:05:15<21:16:27,  1.42s/it]
 13%|█▎        | 7828/61904 [4:05:17<20:55:04,  1.39s/it]
 13%|█▎        | 7829/61904 [4:05:18<21:46:11,  1.45s/it]
 13%|█▎        | 7830/61904 [4:05:19<21:03:11,  1.40s/it]
 13%|█▎        | 7831/61904 [4:05:21<20:34:28,  1.37s/it]
 13%|█▎        | 7832/61904 [4:05:22<21:12:22,  1.41s/it]
 13%|█▎        | 7833/61904 [4:05:24<21:12:29,  1.41s/it]
 13%|█▎        | 7834/61904 [4:05:25<21:32:42,  1.43s/it]
 13%|█▎        | 7835/61904 [4:05:27<21:32:46,  1.43s/it]
 13%|█▎        | 7836/61904 [4:05:28<20:53:43,  1.39s/it]
 13%|█▎        | 7837/61904 [4:05:29<20:44:55,  1.38s/it]
 13%|█▎        | 7838/61904 [4:05:31<21:45:47,  1.45s/it]
 13%|█▎        | 7839/61904 [4:05:32<21:38:20,  1.44s/it]
 13%|█▎        | 7840/61904 [4:05:34<21:27:08,  1.43s/it]
                                                         
{'loss': 2.9162, 'learning_rate': 1.876183067548295e-07, 'epoch': 2.03}

 13%|█▎        | 7840/61904 [4:05:34<21:27:08,  1.43s/it]
 13%|█▎        | 7841/61904 [4:05:35<21:27:13,  1.43s/it]
 13%|█▎        | 7842/61904 [4:05:37<22:10:25,  1.48s/it]
 13%|█▎        | 7843/61904 [4:05:38<21:17:32,  1.42s/it]
 13%|█▎        | 7844/61904 [4:05:39<21:24:21,  1.43s/it]
 13%|█▎        | 7845/61904 [4:05:41<21:10:59,  1.41s/it]
 13%|█▎        | 7846/61904 [4:05:42<20:53:02,  1.39s/it]
 13%|█▎        | 7847/61904 [4:05:43<20:22:38,  1.36s/it]
 13%|█▎        | 7848/61904 [4:05:45<20:12:45,  1.35s/it]
 13%|█▎        | 7849/61904 [4:05:46<20:48:03,  1.39s/it]
 13%|█▎        | 7850/61904 [4:05:48<21:06:05,  1.41s/it]
 13%|█▎        | 7851/61904 [4:05:49<20:36:00,  1.37s/it]
 13%|█▎        | 7852/61904 [4:05:50<20:16:33,  1.35s/it]
 13%|█▎        | 7853/61904 [4:05:52<20:52:55,  1.39s/it]
 13%|█▎        | 7854/61904 [4:05:53<20:40:52,  1.38s/it]
 13%|█▎        | 7855/61904 [4:05:54<20:03:05,  1.34s/it]
 13%|█▎        | 7856/61904 [4:05:56<20:12:48,  1.35s/it]
 13%|█▎        | 7857/61904 [4:05:57<20:06:10,  1.34s/it]
 13%|█▎        | 7858/61904 [4:05:58<20:43:42,  1.38s/it]
 13%|█▎        | 7859/61904 [4:06:00<21:16:57,  1.42s/it]
 13%|█▎        | 7860/61904 [4:06:01<21:18:18,  1.42s/it]
                                                         
{'loss': 2.8391, 'learning_rate': 1.8758589394528716e-07, 'epoch': 2.03}

 13%|█▎        | 7860/61904 [4:06:01<21:18:18,  1.42s/it]
 13%|█▎        | 7861/61904 [4:06:03<20:45:59,  1.38s/it]
 13%|█▎        | 7862/61904 [4:06:04<20:14:43,  1.35s/it]
 13%|█▎        | 7863/61904 [4:06:05<20:28:34,  1.36s/it]
 13%|█▎        | 7864/61904 [4:06:07<21:10:46,  1.41s/it]
 13%|█▎        | 7865/61904 [4:06:08<21:15:49,  1.42s/it]
 13%|█▎        | 7866/61904 [4:06:10<21:27:55,  1.43s/it]
 13%|█▎        | 7867/61904 [4:06:11<21:17:55,  1.42s/it]
 13%|█▎        | 7868/61904 [4:06:12<20:37:48,  1.37s/it]
 13%|█▎        | 7869/61904 [4:06:14<20:39:05,  1.38s/it]
 13%|█▎        | 7870/61904 [4:06:15<20:43:28,  1.38s/it]
 13%|█▎        | 7871/61904 [4:06:17<20:37:22,  1.37s/it]
 13%|█▎        | 7872/61904 [4:06:18<20:08:39,  1.34s/it]
 13%|█▎        | 7873/61904 [4:06:19<20:17:15,  1.35s/it]
 13%|█▎        | 7874/61904 [4:06:20<19:53:25,  1.33s/it]
 13%|█▎        | 7875/61904 [4:06:22<20:21:07,  1.36s/it]
 13%|█▎        | 7876/61904 [4:06:23<21:37:25,  1.44s/it]
 13%|█▎        | 7877/61904 [4:06:25<20:54:56,  1.39s/it]
 13%|█▎        | 7878/61904 [4:06:26<20:50:02,  1.39s/it]
 13%|█▎        | 7879/61904 [4:06:27<20:24:16,  1.36s/it]
 13%|█▎        | 7880/61904 [4:06:29<19:44:04,  1.32s/it]
                                                         
{'loss': 2.8963, 'learning_rate': 1.8755348113574485e-07, 'epoch': 2.04}

 13%|█▎        | 7880/61904 [4:06:29<19:44:04,  1.32s/it]
 13%|█▎        | 7881/61904 [4:06:30<19:28:35,  1.30s/it]
 13%|█▎        | 7882/61904 [4:06:31<20:07:01,  1.34s/it]
 13%|█▎        | 7883/61904 [4:06:33<20:32:59,  1.37s/it]
 13%|█▎        | 7884/61904 [4:06:34<20:11:44,  1.35s/it]
 13%|█▎        | 7885/61904 [4:06:35<20:15:18,  1.35s/it]
 13%|█▎        | 7886/61904 [4:06:37<20:38:29,  1.38s/it]
 13%|█▎        | 7887/61904 [4:06:38<20:33:41,  1.37s/it]
 13%|█▎        | 7888/61904 [4:06:40<20:24:55,  1.36s/it]
 13%|█▎        | 7889/61904 [4:06:41<20:33:59,  1.37s/it]
 13%|█▎        | 7890/61904 [4:06:42<20:21:07,  1.36s/it]
 13%|█▎        | 7891/61904 [4:06:44<20:56:04,  1.40s/it]
 13%|█▎        | 7892/61904 [4:06:45<20:59:05,  1.40s/it]
 13%|█▎        | 7893/61904 [4:06:47<20:56:36,  1.40s/it]
 13%|█▎        | 7894/61904 [4:06:48<20:48:09,  1.39s/it]
 13%|█▎        | 7895/61904 [4:06:49<20:50:03,  1.39s/it]
 13%|█▎        | 7896/61904 [4:06:51<21:00:35,  1.40s/it]
 13%|█▎        | 7897/61904 [4:06:52<20:33:56,  1.37s/it]
 13%|█▎        | 7898/61904 [4:06:53<20:16:11,  1.35s/it]
 13%|█▎        | 7899/61904 [4:06:55<19:51:49,  1.32s/it]
 13%|█▎        | 7900/61904 [4:06:56<20:19:35,  1.35s/it]
                                                         
{'loss': 2.9148, 'learning_rate': 1.8752106832620248e-07, 'epoch': 2.04}

 13%|█▎        | 7900/61904 [4:06:56<20:19:35,  1.35s/it]
 13%|█▎        | 7901/61904 [4:06:57<20:05:23,  1.34s/it]
 13%|█▎        | 7902/61904 [4:06:59<20:10:33,  1.35s/it]
 13%|█▎        | 7903/61904 [4:07:00<21:00:01,  1.40s/it]
 13%|█▎        | 7904/61904 [4:07:02<21:15:42,  1.42s/it]
 13%|█▎        | 7905/61904 [4:07:03<20:57:20,  1.40s/it]
 13%|█▎        | 7906/61904 [4:07:04<20:12:59,  1.35s/it]
 13%|█▎        | 7907/61904 [4:07:06<19:57:22,  1.33s/it]
 13%|█▎        | 7908/61904 [4:07:07<20:11:38,  1.35s/it]
 13%|█▎        | 7909/61904 [4:07:08<20:05:54,  1.34s/it]
 13%|█▎        | 7910/61904 [4:07:10<20:08:54,  1.34s/it]
 13%|█▎        | 7911/61904 [4:07:11<20:12:11,  1.35s/it]
 13%|█▎        | 7912/61904 [4:07:12<20:12:21,  1.35s/it]
 13%|█▎        | 7913/61904 [4:07:14<21:18:02,  1.42s/it]
 13%|█▎        | 7914/61904 [4:07:15<20:36:30,  1.37s/it]
 13%|█▎        | 7915/61904 [4:07:17<20:40:32,  1.38s/it]
 13%|█▎        | 7916/61904 [4:07:18<20:11:44,  1.35s/it]
 13%|█▎        | 7917/61904 [4:07:19<20:12:51,  1.35s/it]
 13%|█▎        | 7918/61904 [4:07:21<20:50:39,  1.39s/it]
 13%|█▎        | 7919/61904 [4:07:22<20:52:51,  1.39s/it]
 13%|█▎        | 7920/61904 [4:07:23<20:04:20,  1.34s/it]
                                                         
{'loss': 2.9378, 'learning_rate': 1.8748865551666017e-07, 'epoch': 2.05}

 13%|█▎        | 7920/61904 [4:07:23<20:04:20,  1.34s/it]
 13%|█▎        | 7921/61904 [4:07:25<19:30:43,  1.30s/it]
 13%|█▎        | 7922/61904 [4:07:26<19:45:36,  1.32s/it]
 13%|█▎        | 7923/61904 [4:07:27<19:35:56,  1.31s/it]
 13%|█▎        | 7924/61904 [4:07:29<20:02:11,  1.34s/it]
 13%|█▎        | 7925/61904 [4:07:30<19:47:17,  1.32s/it]
 13%|█▎        | 7926/61904 [4:07:31<19:55:00,  1.33s/it]
 13%|█▎        | 7927/61904 [4:07:32<19:39:03,  1.31s/it]
 13%|█▎        | 7928/61904 [4:07:34<19:33:13,  1.30s/it]
 13%|█▎        | 7929/61904 [4:07:35<19:17:52,  1.29s/it]
 13%|█▎        | 7930/61904 [4:07:36<19:33:46,  1.30s/it]
 13%|█▎        | 7931/61904 [4:07:38<19:44:18,  1.32s/it]
 13%|█▎        | 7932/61904 [4:07:39<20:03:45,  1.34s/it]
 13%|█▎        | 7933/61904 [4:07:41<20:35:32,  1.37s/it]
 13%|█▎        | 7934/61904 [4:07:42<20:19:33,  1.36s/it]
 13%|█▎        | 7935/61904 [4:07:43<20:17:47,  1.35s/it]
 13%|█▎        | 7936/61904 [4:07:45<20:38:33,  1.38s/it]
 13%|█▎        | 7937/61904 [4:07:46<20:06:26,  1.34s/it]
 13%|█▎        | 7938/61904 [4:07:47<20:30:48,  1.37s/it]
 13%|█▎        | 7939/61904 [4:07:49<20:22:07,  1.36s/it]
 13%|█▎        | 7940/61904 [4:07:50<20:32:37,  1.37s/it]
                                                         
{'loss': 2.8385, 'learning_rate': 1.8745624270711783e-07, 'epoch': 2.05}

 13%|█▎        | 7940/61904 [4:07:50<20:32:37,  1.37s/it]
 13%|█▎        | 7941/61904 [4:07:51<20:26:46,  1.36s/it]
 13%|█▎        | 7942/61904 [4:07:53<20:34:08,  1.37s/it]
 13%|█▎        | 7943/61904 [4:07:54<20:58:42,  1.40s/it]
 13%|█▎        | 7944/61904 [4:07:56<20:30:19,  1.37s/it]
 13%|█▎        | 7945/61904 [4:07:57<20:01:38,  1.34s/it]
 13%|█▎        | 7946/61904 [4:07:58<19:53:06,  1.33s/it]
 13%|█▎        | 7947/61904 [4:08:00<20:39:52,  1.38s/it]
 13%|█▎        | 7948/61904 [4:08:01<20:32:44,  1.37s/it]
 13%|█▎        | 7949/61904 [4:08:02<20:09:56,  1.35s/it]
 13%|█▎        | 7950/61904 [4:08:04<20:18:05,  1.35s/it]
 13%|█▎        | 7951/61904 [4:08:05<20:21:59,  1.36s/it]
 13%|█▎        | 7952/61904 [4:08:06<20:21:25,  1.36s/it]
 13%|█▎        | 7953/61904 [4:08:08<20:17:26,  1.35s/it]
 13%|█▎        | 7954/61904 [4:08:09<20:13:01,  1.35s/it]
 13%|█▎        | 7955/61904 [4:08:10<20:17:14,  1.35s/it]
 13%|█▎        | 7956/61904 [4:08:12<20:03:58,  1.34s/it]
 13%|█▎        | 7957/61904 [4:08:13<20:22:25,  1.36s/it]
 13%|█▎        | 7958/61904 [4:08:14<20:11:33,  1.35s/it]
 13%|█▎        | 7959/61904 [4:08:16<20:27:08,  1.36s/it]
 13%|█▎        | 7960/61904 [4:08:17<20:22:01,  1.36s/it]
                                                         
{'loss': 2.9649, 'learning_rate': 1.874238298975755e-07, 'epoch': 2.06}

 13%|█▎        | 7960/61904 [4:08:17<20:22:01,  1.36s/it]
 13%|█▎        | 7961/61904 [4:08:19<20:15:19,  1.35s/it]
 13%|█▎        | 7962/61904 [4:08:20<20:42:26,  1.38s/it]
 13%|█▎        | 7963/61904 [4:08:21<20:15:38,  1.35s/it]
 13%|█▎        | 7964/61904 [4:08:23<20:04:09,  1.34s/it]
 13%|█▎        | 7965/61904 [4:08:24<19:59:20,  1.33s/it]
 13%|█▎        | 7966/61904 [4:08:25<21:10:04,  1.41s/it]
 13%|█▎        | 7967/61904 [4:08:27<21:17:34,  1.42s/it]
 13%|█▎        | 7968/61904 [4:08:28<20:41:52,  1.38s/it]
 13%|█▎        | 7969/61904 [4:08:30<20:30:33,  1.37s/it]
 13%|█▎        | 7970/61904 [4:08:31<20:21:11,  1.36s/it]
 13%|█▎        | 7971/61904 [4:08:32<20:30:30,  1.37s/it]
 13%|█▎        | 7972/61904 [4:08:34<20:43:49,  1.38s/it]
 13%|█▎        | 7973/61904 [4:08:35<20:26:05,  1.36s/it]
 13%|█▎        | 7974/61904 [4:08:36<19:52:14,  1.33s/it]
 13%|█▎        | 7975/61904 [4:08:38<21:26:45,  1.43s/it]
 13%|█▎        | 7976/61904 [4:08:39<21:03:13,  1.41s/it]
 13%|█▎        | 7977/61904 [4:08:41<20:31:19,  1.37s/it]
 13%|█▎        | 7978/61904 [4:08:42<20:33:34,  1.37s/it]
 13%|█▎        | 7979/61904 [4:08:43<20:05:01,  1.34s/it]
 13%|█▎        | 7980/61904 [4:08:44<19:36:53,  1.31s/it]
                                                         
{'loss': 2.8578, 'learning_rate': 1.8739141708803318e-07, 'epoch': 2.06}

 13%|█▎        | 7980/61904 [4:08:44<19:36:53,  1.31s/it]
 13%|█▎        | 7981/61904 [4:08:46<19:52:02,  1.33s/it]
 13%|█▎        | 7982/61904 [4:08:47<20:07:19,  1.34s/it]
 13%|█▎        | 7983/61904 [4:08:49<21:30:44,  1.44s/it]
 13%|█▎        | 7984/61904 [4:08:50<21:28:38,  1.43s/it]
 13%|█▎        | 7985/61904 [4:08:52<20:51:38,  1.39s/it]
 13%|█▎        | 7986/61904 [4:08:53<21:06:39,  1.41s/it]
 13%|█▎        | 7987/61904 [4:08:54<21:17:04,  1.42s/it]
 13%|█▎        | 7988/61904 [4:08:56<20:34:08,  1.37s/it]
 13%|█▎        | 7989/61904 [4:08:57<19:59:32,  1.33s/it]
 13%|█▎        | 7990/61904 [4:08:58<20:09:43,  1.35s/it]
 13%|█▎        | 7991/61904 [4:09:00<20:00:21,  1.34s/it]
 13%|█▎        | 7992/61904 [4:09:01<20:31:22,  1.37s/it]
 13%|█▎        | 7993/61904 [4:09:02<19:56:28,  1.33s/it]
 13%|█▎        | 7994/61904 [4:09:04<21:03:07,  1.41s/it]
 13%|█▎        | 7995/61904 [4:09:05<20:29:43,  1.37s/it]
 13%|█▎        | 7996/61904 [4:09:07<20:32:15,  1.37s/it]
 13%|█▎        | 7997/61904 [4:09:08<20:05:58,  1.34s/it]
 13%|█▎        | 7998/61904 [4:09:09<20:00:38,  1.34s/it]
 13%|█▎        | 7999/61904 [4:09:11<20:35:23,  1.38s/it]
 13%|█▎        | 8000/61904 [4:09:12<20:48:28,  1.39s/it]
                                                         
{'loss': 2.8477, 'learning_rate': 1.8735900427849085e-07, 'epoch': 2.07}

 13%|█▎        | 8000/61904 [4:09:12<20:48:28,  1.39s/it]
 13%|█▎        | 8001/61904 [4:09:14<21:16:00,  1.42s/it]
 13%|█▎        | 8002/61904 [4:09:15<20:46:05,  1.39s/it]
 13%|█▎        | 8003/61904 [4:09:16<20:34:22,  1.37s/it]
 13%|█▎        | 8004/61904 [4:09:17<19:44:50,  1.32s/it]
 13%|█▎        | 8005/61904 [4:09:19<20:39:29,  1.38s/it]
 13%|█▎        | 8006/61904 [4:09:20<20:28:38,  1.37s/it]
 13%|█▎        | 8007/61904 [4:09:22<20:11:15,  1.35s/it]
 13%|█▎        | 8008/61904 [4:09:23<20:30:35,  1.37s/it]
 13%|█▎        | 8009/61904 [4:09:24<20:26:09,  1.37s/it]
 13%|█▎        | 8010/61904 [4:09:26<20:21:37,  1.36s/it]
 13%|█▎        | 8011/61904 [4:09:27<20:38:00,  1.38s/it]
 13%|█▎        | 8012/61904 [4:09:28<19:54:07,  1.33s/it]
 13%|█▎        | 8013/61904 [4:09:30<20:20:11,  1.36s/it]
 13%|█▎        | 8014/61904 [4:09:31<21:01:53,  1.40s/it]
 13%|█▎        | 8015/61904 [4:09:33<20:55:21,  1.40s/it]
 13%|█▎        | 8016/61904 [4:09:34<21:24:43,  1.43s/it]
 13%|█▎        | 8017/61904 [4:09:35<20:31:32,  1.37s/it]
 13%|█▎        | 8018/61904 [4:09:37<20:04:38,  1.34s/it]
 13%|█▎        | 8019/61904 [4:09:38<19:55:51,  1.33s/it]
 13%|█▎        | 8020/61904 [4:09:39<19:36:00,  1.31s/it]
                                                         
{'loss': 2.8336, 'learning_rate': 1.873265914689485e-07, 'epoch': 2.07}

 13%|█▎        | 8020/61904 [4:09:39<19:36:00,  1.31s/it]
 13%|█▎        | 8021/61904 [4:09:41<20:44:32,  1.39s/it]
 13%|█▎        | 8022/61904 [4:09:42<19:59:11,  1.34s/it]
 13%|█▎        | 8023/61904 [4:09:43<20:33:59,  1.37s/it]
 13%|█▎        | 8024/61904 [4:09:45<20:45:40,  1.39s/it]
 13%|█▎        | 8025/61904 [4:09:46<20:27:31,  1.37s/it]
 13%|█▎        | 8026/61904 [4:09:48<20:10:19,  1.35s/it]
 13%|█▎        | 8027/61904 [4:09:49<21:15:43,  1.42s/it]
 13%|█▎        | 8028/61904 [4:09:50<20:57:55,  1.40s/it]
 13%|█▎        | 8029/61904 [4:09:52<20:24:52,  1.36s/it]
 13%|█▎        | 8030/61904 [4:09:53<20:33:53,  1.37s/it]
 13%|█▎        | 8031/61904 [4:09:54<19:53:12,  1.33s/it]
 13%|█▎        | 8032/61904 [4:09:56<20:22:04,  1.36s/it]
 13%|█▎        | 8033/61904 [4:09:57<19:54:21,  1.33s/it]
 13%|█▎        | 8034/61904 [4:09:59<20:35:16,  1.38s/it]
 13%|█▎        | 8035/61904 [4:10:00<20:41:00,  1.38s/it]
 13%|█▎        | 8036/61904 [4:10:01<20:07:58,  1.35s/it]
 13%|█▎        | 8037/61904 [4:10:02<19:32:44,  1.31s/it]
 13%|█▎        | 8038/61904 [4:10:04<20:12:57,  1.35s/it]
 13%|█▎        | 8039/61904 [4:10:05<19:48:30,  1.32s/it]
 13%|█▎        | 8040/61904 [4:10:07<20:33:55,  1.37s/it]
                                                         
{'loss': 2.9005, 'learning_rate': 1.872941786594062e-07, 'epoch': 2.08}

 13%|█▎        | 8040/61904 [4:10:07<20:33:55,  1.37s/it]
 13%|█▎        | 8041/61904 [4:10:08<20:12:43,  1.35s/it]
 13%|█▎        | 8042/61904 [4:10:09<20:18:35,  1.36s/it]
 13%|█▎        | 8043/61904 [4:10:11<19:54:21,  1.33s/it]
 13%|█▎        | 8044/61904 [4:10:12<20:07:42,  1.35s/it]
 13%|█▎        | 8045/61904 [4:10:13<20:15:46,  1.35s/it]
 13%|█▎        | 8046/61904 [4:10:15<20:53:10,  1.40s/it]
 13%|█▎        | 8047/61904 [4:10:16<20:50:33,  1.39s/it]
 13%|█▎        | 8048/61904 [4:10:18<20:34:52,  1.38s/it]
 13%|█▎        | 8049/61904 [4:10:19<21:00:46,  1.40s/it]
 13%|█▎        | 8050/61904 [4:10:20<21:04:40,  1.41s/it]
 13%|█▎        | 8051/61904 [4:10:22<21:46:49,  1.46s/it]
 13%|█▎        | 8052/61904 [4:10:23<21:53:35,  1.46s/it]
 13%|█▎        | 8053/61904 [4:10:25<21:30:42,  1.44s/it]
 13%|█▎        | 8054/61904 [4:10:26<22:26:25,  1.50s/it]
 13%|█▎        | 8055/61904 [4:10:28<22:23:14,  1.50s/it]
 13%|█▎        | 8056/61904 [4:10:29<21:33:36,  1.44s/it]
 13%|█▎        | 8057/61904 [4:10:31<21:43:16,  1.45s/it]
 13%|█▎        | 8058/61904 [4:10:32<20:40:15,  1.38s/it]
 13%|█▎        | 8059/61904 [4:10:33<20:08:43,  1.35s/it]
 13%|█▎        | 8060/61904 [4:10:35<20:27:47,  1.37s/it]
                                                         
{'loss': 2.9426, 'learning_rate': 1.8726176584986386e-07, 'epoch': 2.08}

 13%|█▎        | 8060/61904 [4:10:35<20:27:47,  1.37s/it]
 13%|█▎        | 8061/61904 [4:10:36<20:19:36,  1.36s/it]
 13%|█▎        | 8062/61904 [4:10:37<20:13:28,  1.35s/it]
 13%|█▎        | 8063/61904 [4:10:39<20:15:23,  1.35s/it]
 13%|█▎        | 8064/61904 [4:10:40<20:06:22,  1.34s/it]
 13%|█▎        | 8065/61904 [4:10:41<19:51:14,  1.33s/it]
 13%|█▎        | 8066/61904 [4:10:43<19:56:58,  1.33s/it]
 13%|█▎        | 8067/61904 [4:10:44<20:06:41,  1.34s/it]
 13%|█▎        | 8068/61904 [4:10:45<19:47:27,  1.32s/it]
 13%|█▎        | 8069/61904 [4:10:47<20:20:08,  1.36s/it]
 13%|█▎        | 8070/61904 [4:10:48<21:19:54,  1.43s/it]
 13%|█▎        | 8071/61904 [4:10:50<21:18:39,  1.43s/it]
 13%|█▎        | 8072/61904 [4:10:51<21:15:48,  1.42s/it]
 13%|█▎        | 8073/61904 [4:10:53<21:30:43,  1.44s/it]
 13%|█▎        | 8074/61904 [4:10:54<20:59:23,  1.40s/it]
 13%|█▎        | 8075/61904 [4:10:56<21:46:53,  1.46s/it]
 13%|█▎        | 8076/61904 [4:10:57<21:01:25,  1.41s/it]
 13%|█▎        | 8077/61904 [4:10:58<21:23:49,  1.43s/it]
 13%|█▎        | 8078/61904 [4:11:00<20:49:56,  1.39s/it]
 13%|█▎        | 8079/61904 [4:11:01<20:08:54,  1.35s/it]
 13%|█▎        | 8080/61904 [4:11:02<19:45:58,  1.32s/it]
                                                         
{'loss': 2.8823, 'learning_rate': 1.8722935304032152e-07, 'epoch': 2.09}

 13%|█▎        | 8080/61904 [4:11:02<19:45:58,  1.32s/it]
 13%|█▎        | 8081/61904 [4:11:04<19:57:16,  1.33s/it]
 13%|█▎        | 8082/61904 [4:11:05<20:39:25,  1.38s/it]
 13%|█▎        | 8083/61904 [4:11:06<20:47:22,  1.39s/it]
 13%|█▎        | 8084/61904 [4:11:08<21:13:04,  1.42s/it]
 13%|█▎        | 8085/61904 [4:11:09<20:21:29,  1.36s/it]
 13%|█▎        | 8086/61904 [4:11:10<20:26:13,  1.37s/it]
 13%|█▎        | 8087/61904 [4:11:12<20:51:21,  1.40s/it]
 13%|█▎        | 8088/61904 [4:11:13<20:05:25,  1.34s/it]
 13%|█▎        | 8089/61904 [4:11:15<20:37:04,  1.38s/it]
 13%|█▎        | 8090/61904 [4:11:16<20:25:29,  1.37s/it]
 13%|█▎        | 8091/61904 [4:11:17<20:10:49,  1.35s/it]
 13%|█▎        | 8092/61904 [4:11:19<19:58:30,  1.34s/it]
 13%|█▎        | 8093/61904 [4:11:20<20:23:28,  1.36s/it]
 13%|█▎        | 8094/61904 [4:11:21<20:24:13,  1.37s/it]
 13%|█▎        | 8095/61904 [4:11:23<20:06:59,  1.35s/it]
 13%|█▎        | 8096/61904 [4:11:24<20:29:06,  1.37s/it]
 13%|█▎        | 8097/61904 [4:11:26<20:32:42,  1.37s/it]
 13%|█▎        | 8098/61904 [4:11:27<20:33:28,  1.38s/it]
 13%|█▎        | 8099/61904 [4:11:28<19:54:47,  1.33s/it]
 13%|█▎        | 8100/61904 [4:11:29<19:36:46,  1.31s/it]
                                                         
{'loss': 2.8766, 'learning_rate': 1.871969402307792e-07, 'epoch': 2.09}

 13%|█▎        | 8100/61904 [4:11:29<19:36:46,  1.31s/it]
 13%|█▎        | 8101/61904 [4:11:31<19:32:59,  1.31s/it]
 13%|█▎        | 8102/61904 [4:11:32<19:41:34,  1.32s/it]
 13%|█▎        | 8103/61904 [4:11:33<19:45:47,  1.32s/it]
 13%|█▎        | 8104/61904 [4:11:35<19:47:11,  1.32s/it]
 13%|█▎        | 8105/61904 [4:11:36<20:14:22,  1.35s/it]
 13%|█▎        | 8106/61904 [4:11:37<20:12:25,  1.35s/it]
 13%|█▎        | 8107/61904 [4:11:39<20:03:53,  1.34s/it]
 13%|█▎        | 8108/61904 [4:11:40<19:52:03,  1.33s/it]
 13%|█▎        | 8109/61904 [4:11:41<19:52:35,  1.33s/it]
 13%|█▎        | 8110/61904 [4:11:43<19:23:12,  1.30s/it]
 13%|█▎        | 8111/61904 [4:11:44<19:57:02,  1.34s/it]
 13%|█▎        | 8112/61904 [4:11:45<19:53:28,  1.33s/it]
 13%|█▎        | 8113/61904 [4:11:47<20:27:34,  1.37s/it]
 13%|█▎        | 8114/61904 [4:11:48<20:27:30,  1.37s/it]
 13%|█▎        | 8115/61904 [4:11:50<20:56:59,  1.40s/it]
 13%|█▎        | 8116/61904 [4:11:51<20:20:31,  1.36s/it]
 13%|█▎        | 8117/61904 [4:11:52<20:04:33,  1.34s/it]
 13%|█▎        | 8118/61904 [4:11:54<19:47:24,  1.32s/it]
 13%|█▎        | 8119/61904 [4:11:55<19:59:07,  1.34s/it]
 13%|█▎        | 8120/61904 [4:11:56<20:23:02,  1.36s/it]
                                                         
{'loss': 2.8903, 'learning_rate': 1.8716452742123684e-07, 'epoch': 2.1}

 13%|█▎        | 8120/61904 [4:11:56<20:23:02,  1.36s/it]
 13%|█▎        | 8121/61904 [4:11:58<20:11:10,  1.35s/it]
 13%|█▎        | 8122/61904 [4:11:59<19:54:03,  1.33s/it]
 13%|█▎        | 8123/61904 [4:12:00<19:57:58,  1.34s/it]
 13%|█▎        | 8124/61904 [4:12:02<19:58:36,  1.34s/it]
 13%|█▎        | 8125/61904 [4:12:03<20:01:23,  1.34s/it]
 13%|█▎        | 8126/61904 [4:12:04<20:19:55,  1.36s/it]
 13%|█▎        | 8127/61904 [4:12:06<19:50:26,  1.33s/it]
 13%|█▎        | 8128/61904 [4:12:07<19:46:14,  1.32s/it]
 13%|█▎        | 8129/61904 [4:12:08<19:38:42,  1.32s/it]
 13%|█▎        | 8130/61904 [4:12:10<19:31:51,  1.31s/it]
 13%|█▎        | 8131/61904 [4:12:11<19:47:12,  1.32s/it]
 13%|█▎        | 8132/61904 [4:12:12<19:25:37,  1.30s/it]
 13%|█▎        | 8133/61904 [4:12:13<19:41:08,  1.32s/it]
 13%|█▎        | 8134/61904 [4:12:15<20:03:22,  1.34s/it]
 13%|█▎        | 8135/61904 [4:12:16<19:41:20,  1.32s/it]
 13%|█▎        | 8136/61904 [4:12:18<19:56:50,  1.34s/it]
 13%|█▎        | 8137/61904 [4:12:19<20:08:53,  1.35s/it]
 13%|█▎        | 8138/61904 [4:12:20<20:16:19,  1.36s/it]
 13%|█▎        | 8139/61904 [4:12:22<21:12:21,  1.42s/it]
 13%|█▎        | 8140/61904 [4:12:23<21:31:27,  1.44s/it]
                                                         
{'loss': 2.9383, 'learning_rate': 1.8713211461169453e-07, 'epoch': 2.1}

 13%|█▎        | 8140/61904 [4:12:23<21:31:27,  1.44s/it]
 13%|█▎        | 8141/61904 [4:12:25<21:21:13,  1.43s/it]
 13%|█▎        | 8142/61904 [4:12:26<20:52:12,  1.40s/it]
 13%|█▎        | 8143/61904 [4:12:27<20:28:43,  1.37s/it]
 13%|█▎        | 8144/61904 [4:12:29<21:11:22,  1.42s/it]
 13%|█▎        | 8145/61904 [4:12:30<21:05:23,  1.41s/it]
 13%|█▎        | 8146/61904 [4:12:32<20:50:35,  1.40s/it]
 13%|█▎        | 8147/61904 [4:12:33<20:29:28,  1.37s/it]
 13%|█▎        | 8148/61904 [4:12:34<20:09:09,  1.35s/it]
 13%|█▎        | 8149/61904 [4:12:36<20:43:03,  1.39s/it]
 13%|█▎        | 8150/61904 [4:12:37<20:58:31,  1.40s/it]
 13%|█▎        | 8151/61904 [4:12:38<20:15:55,  1.36s/it]
 13%|█▎        | 8152/61904 [4:12:40<20:37:08,  1.38s/it]
 13%|█▎        | 8153/61904 [4:12:41<20:42:37,  1.39s/it]
 13%|█▎        | 8154/61904 [4:12:43<21:25:55,  1.44s/it]
 13%|█▎        | 8155/61904 [4:12:44<21:41:59,  1.45s/it]
 13%|█▎        | 8156/61904 [4:12:46<22:02:21,  1.48s/it]
 13%|█▎        | 8157/61904 [4:12:47<21:16:47,  1.43s/it]
 13%|█▎        | 8158/61904 [4:12:49<21:00:36,  1.41s/it]
 13%|█▎        | 8159/61904 [4:12:50<20:35:53,  1.38s/it]
 13%|█▎        | 8160/61904 [4:12:51<19:56:01,  1.34s/it]
                                                         
{'loss': 2.8702, 'learning_rate': 1.870997018021522e-07, 'epoch': 2.11}

 13%|█▎        | 8160/61904 [4:12:51<19:56:01,  1.34s/it]
 13%|█▎        | 8161/61904 [4:12:52<19:37:50,  1.31s/it]
 13%|█▎        | 8162/61904 [4:12:54<19:42:25,  1.32s/it]
 13%|█▎        | 8163/61904 [4:12:55<20:25:54,  1.37s/it]
 13%|█▎        | 8164/61904 [4:12:57<20:52:36,  1.40s/it]
 13%|█▎        | 8165/61904 [4:12:58<20:47:20,  1.39s/it]
 13%|█▎        | 8166/61904 [4:12:59<20:29:38,  1.37s/it]
 13%|█▎        | 8167/61904 [4:13:01<19:39:35,  1.32s/it]
 13%|█▎        | 8168/61904 [4:13:02<19:16:57,  1.29s/it]
 13%|█▎        | 8169/61904 [4:13:03<19:23:50,  1.30s/it]
 13%|█▎        | 8170/61904 [4:13:04<19:14:55,  1.29s/it]
 13%|█▎        | 8171/61904 [4:13:06<19:19:52,  1.30s/it]
 13%|█▎        | 8172/61904 [4:13:07<19:30:15,  1.31s/it]
 13%|█▎        | 8173/61904 [4:13:08<20:01:00,  1.34s/it]
 13%|█▎        | 8174/61904 [4:13:10<20:02:18,  1.34s/it]
 13%|█▎        | 8175/61904 [4:13:11<19:55:58,  1.34s/it]
 13%|█▎        | 8176/61904 [4:13:12<19:36:19,  1.31s/it]
 13%|█▎        | 8177/61904 [4:13:14<19:42:44,  1.32s/it]
 13%|█▎        | 8178/61904 [4:13:15<20:06:40,  1.35s/it]
 13%|█▎        | 8179/61904 [4:13:17<21:00:53,  1.41s/it]
 13%|█▎        | 8180/61904 [4:13:18<20:04:43,  1.35s/it]
                                                         
{'loss': 2.8984, 'learning_rate': 1.8706728899260986e-07, 'epoch': 2.11}

 13%|█▎        | 8180/61904 [4:13:18<20:04:43,  1.35s/it]
 13%|█▎        | 8181/61904 [4:13:19<19:54:14,  1.33s/it]
 13%|█▎        | 8182/61904 [4:13:21<20:24:21,  1.37s/it]
 13%|█▎        | 8183/61904 [4:13:22<20:17:02,  1.36s/it]
 13%|█▎        | 8184/61904 [4:13:23<19:48:28,  1.33s/it]
 13%|█▎        | 8185/61904 [4:13:25<20:32:07,  1.38s/it]
 13%|█▎        | 8186/61904 [4:13:26<20:37:46,  1.38s/it]
 13%|█▎        | 8187/61904 [4:13:27<20:05:20,  1.35s/it]
 13%|█▎        | 8188/61904 [4:13:29<19:52:59,  1.33s/it]
 13%|█▎        | 8189/61904 [4:13:30<20:02:24,  1.34s/it]
 13%|█▎        | 8190/61904 [4:13:32<20:59:06,  1.41s/it]
 13%|█▎        | 8191/61904 [4:13:33<21:21:00,  1.43s/it]
 13%|█▎        | 8192/61904 [4:13:34<20:50:17,  1.40s/it]
 13%|█▎        | 8193/61904 [4:13:36<20:30:49,  1.37s/it]
 13%|█▎        | 8194/61904 [4:13:37<20:04:25,  1.35s/it]
 13%|█▎        | 8195/61904 [4:13:38<19:44:01,  1.32s/it]
 13%|█▎        | 8196/61904 [4:13:40<20:04:31,  1.35s/it]
 13%|█▎        | 8197/61904 [4:13:41<20:07:46,  1.35s/it]
 13%|█▎        | 8198/61904 [4:13:42<20:11:35,  1.35s/it]
 13%|█▎        | 8199/61904 [4:13:44<20:06:27,  1.35s/it]
 13%|█▎        | 8200/61904 [4:13:45<20:31:45,  1.38s/it]
                                                         
{'loss': 2.934, 'learning_rate': 1.8703487618306754e-07, 'epoch': 2.12}

 13%|█▎        | 8200/61904 [4:13:45<20:31:45,  1.38s/it]
 13%|█▎        | 8201/61904 [4:13:47<20:44:12,  1.39s/it]
 13%|█▎        | 8202/61904 [4:13:48<21:15:29,  1.43s/it]
 13%|█▎        | 8203/61904 [4:13:49<20:24:41,  1.37s/it]
 13%|█▎        | 8204/61904 [4:13:51<20:41:41,  1.39s/it]
 13%|█▎        | 8205/61904 [4:13:52<20:38:09,  1.38s/it]
 13%|█▎        | 8206/61904 [4:13:53<20:16:02,  1.36s/it]
 13%|█▎        | 8207/61904 [4:13:55<20:04:46,  1.35s/it]
 13%|█▎        | 8208/61904 [4:13:56<19:46:50,  1.33s/it]
 13%|█▎        | 8209/61904 [4:13:57<19:52:11,  1.33s/it]
 13%|█▎        | 8210/61904 [4:13:59<20:49:26,  1.40s/it]
 13%|█▎        | 8211/61904 [4:14:00<20:34:06,  1.38s/it]
 13%|█▎        | 8212/61904 [4:14:02<20:10:58,  1.35s/it]
 13%|█▎        | 8213/61904 [4:14:03<20:17:46,  1.36s/it]
 13%|█▎        | 8214/61904 [4:14:04<20:33:53,  1.38s/it]
 13%|█▎        | 8215/61904 [4:14:06<21:22:17,  1.43s/it]
 13%|█▎        | 8216/61904 [4:14:07<21:05:48,  1.41s/it]
 13%|█▎        | 8217/61904 [4:14:09<20:51:43,  1.40s/it]
 13%|█▎        | 8218/61904 [4:14:10<20:57:45,  1.41s/it]
 13%|█▎        | 8219/61904 [4:14:11<20:27:43,  1.37s/it]
 13%|█▎        | 8220/61904 [4:14:13<19:55:11,  1.34s/it]
                                                         
{'loss': 2.8964, 'learning_rate': 1.870024633735252e-07, 'epoch': 2.12}

 13%|█▎        | 8220/61904 [4:14:13<19:55:11,  1.34s/it]
 13%|█▎        | 8221/61904 [4:14:14<20:01:06,  1.34s/it]
 13%|█▎        | 8222/61904 [4:14:15<20:17:20,  1.36s/it]
 13%|█▎        | 8223/61904 [4:14:17<20:12:03,  1.35s/it]
 13%|█▎        | 8224/61904 [4:14:18<20:13:29,  1.36s/it]
 13%|█▎        | 8225/61904 [4:14:19<20:44:23,  1.39s/it]
 13%|█▎        | 8226/61904 [4:14:21<20:41:51,  1.39s/it]
 13%|█▎        | 8227/61904 [4:14:22<20:29:37,  1.37s/it]
 13%|█▎        | 8228/61904 [4:14:24<20:11:28,  1.35s/it]
 13%|█▎        | 8229/61904 [4:14:25<20:49:40,  1.40s/it]
 13%|█▎        | 8230/61904 [4:14:26<20:57:24,  1.41s/it]
 13%|█▎        | 8231/61904 [4:14:28<20:47:22,  1.39s/it]
 13%|█▎        | 8232/61904 [4:14:29<20:56:42,  1.40s/it]
 13%|█▎        | 8233/61904 [4:14:31<20:43:11,  1.39s/it]
 13%|█▎        | 8234/61904 [4:14:32<20:21:58,  1.37s/it]
 13%|█▎        | 8235/61904 [4:14:33<20:20:29,  1.36s/it]
 13%|█▎        | 8236/61904 [4:14:35<20:04:27,  1.35s/it]
 13%|█▎        | 8237/61904 [4:14:36<20:20:36,  1.36s/it]
 13%|█▎        | 8238/61904 [4:14:37<20:40:55,  1.39s/it]
 13%|█▎        | 8239/61904 [4:14:39<20:28:50,  1.37s/it]
 13%|█▎        | 8240/61904 [4:14:40<20:42:56,  1.39s/it]
                                                         
{'loss': 2.887, 'learning_rate': 1.8697005056398287e-07, 'epoch': 2.13}

 13%|█▎        | 8240/61904 [4:14:40<20:42:56,  1.39s/it]
 13%|█▎        | 8241/61904 [4:14:42<21:13:20,  1.42s/it]
 13%|█▎        | 8242/61904 [4:14:43<20:57:59,  1.41s/it]
 13%|█▎        | 8243/61904 [4:14:44<20:11:31,  1.35s/it]
 13%|█▎        | 8244/61904 [4:14:46<19:53:41,  1.33s/it]
 13%|█▎        | 8245/61904 [4:14:47<19:59:46,  1.34s/it]
 13%|█▎        | 8246/61904 [4:14:48<20:44:02,  1.39s/it]
 13%|█▎        | 8247/61904 [4:14:50<20:40:36,  1.39s/it]
 13%|█▎        | 8248/61904 [4:14:51<21:02:44,  1.41s/it]
 13%|█▎        | 8249/61904 [4:14:53<21:19:49,  1.43s/it]
 13%|█▎        | 8250/61904 [4:14:54<20:34:28,  1.38s/it]
 13%|█▎        | 8251/61904 [4:14:56<21:17:21,  1.43s/it]
 13%|█▎        | 8252/61904 [4:14:57<20:39:04,  1.39s/it]
 13%|█▎        | 8253/61904 [4:14:58<20:44:52,  1.39s/it]
 13%|█▎        | 8254/61904 [4:15:00<20:22:45,  1.37s/it]
 13%|█▎        | 8255/61904 [4:15:01<21:01:11,  1.41s/it]
 13%|█▎        | 8256/61904 [4:15:02<20:55:12,  1.40s/it]
 13%|█▎        | 8257/61904 [4:15:04<20:15:31,  1.36s/it]
 13%|█▎        | 8258/61904 [4:15:05<20:26:41,  1.37s/it]
 13%|█▎        | 8259/61904 [4:15:07<20:31:17,  1.38s/it]
 13%|█▎        | 8260/61904 [4:15:08<21:06:13,  1.42s/it]
                                                         
{'loss': 2.8915, 'learning_rate': 1.8693763775444056e-07, 'epoch': 2.13}

 13%|█▎        | 8260/61904 [4:15:08<21:06:13,  1.42s/it]
 13%|█▎        | 8261/61904 [4:15:09<20:43:09,  1.39s/it]
 13%|█▎        | 8262/61904 [4:15:11<21:28:23,  1.44s/it]
 13%|█▎        | 8263/61904 [4:15:12<20:50:49,  1.40s/it]
 13%|█▎        | 8264/61904 [4:15:14<20:37:46,  1.38s/it]
 13%|█▎        | 8265/61904 [4:15:15<20:33:51,  1.38s/it]
 13%|█▎        | 8266/61904 [4:15:16<21:08:03,  1.42s/it]
 13%|█▎        | 8267/61904 [4:15:18<20:59:42,  1.41s/it]
 13%|█▎        | 8268/61904 [4:15:19<21:57:25,  1.47s/it]
 13%|█▎        | 8269/61904 [4:15:21<21:49:28,  1.46s/it]
 13%|█▎        | 8270/61904 [4:15:22<21:28:35,  1.44s/it]
 13%|█▎        | 8271/61904 [4:15:24<21:29:13,  1.44s/it]
 13%|█▎        | 8272/61904 [4:15:25<21:13:24,  1.42s/it]
 13%|█▎        | 8273/61904 [4:15:26<20:52:05,  1.40s/it]
 13%|█▎        | 8274/61904 [4:15:28<21:44:27,  1.46s/it]
 13%|█▎        | 8275/61904 [4:15:29<21:20:32,  1.43s/it]
 13%|█▎        | 8276/61904 [4:15:31<21:13:19,  1.42s/it]
 13%|█▎        | 8277/61904 [4:15:32<21:07:08,  1.42s/it]
 13%|█▎        | 8278/61904 [4:15:34<21:03:37,  1.41s/it]
 13%|█▎        | 8279/61904 [4:15:35<20:34:22,  1.38s/it]
 13%|█▎        | 8280/61904 [4:15:36<20:34:23,  1.38s/it]
                                                         
{'loss': 2.9201, 'learning_rate': 1.8690522494489822e-07, 'epoch': 2.14}

 13%|█▎        | 8280/61904 [4:15:36<20:34:23,  1.38s/it]
 13%|█▎        | 8281/61904 [4:15:38<20:30:57,  1.38s/it]
 13%|█▎        | 8282/61904 [4:15:39<20:37:06,  1.38s/it]
 13%|█▎        | 8283/61904 [4:15:41<21:00:54,  1.41s/it]
 13%|█▎        | 8284/61904 [4:15:42<20:42:57,  1.39s/it]
 13%|█▎        | 8285/61904 [4:15:43<20:40:58,  1.39s/it]
 13%|█▎        | 8286/61904 [4:15:45<20:03:55,  1.35s/it]
 13%|█▎        | 8287/61904 [4:15:46<19:52:36,  1.33s/it]
 13%|█▎        | 8288/61904 [4:15:47<19:50:36,  1.33s/it]
 13%|█▎        | 8289/61904 [4:15:49<20:04:00,  1.35s/it]
 13%|█▎        | 8290/61904 [4:15:50<19:49:22,  1.33s/it]
 13%|█▎        | 8291/61904 [4:15:51<19:26:51,  1.31s/it]
 13%|█▎        | 8292/61904 [4:15:53<19:54:16,  1.34s/it]
 13%|█▎        | 8293/61904 [4:15:54<20:08:08,  1.35s/it]
 13%|█▎        | 8294/61904 [4:15:55<20:32:36,  1.38s/it]
 13%|█▎        | 8295/61904 [4:15:57<20:05:28,  1.35s/it]
 13%|█▎        | 8296/61904 [4:15:58<20:21:00,  1.37s/it]
 13%|█▎        | 8297/61904 [4:15:59<20:11:34,  1.36s/it]
 13%|█▎        | 8298/61904 [4:16:01<21:02:13,  1.41s/it]
 13%|█▎        | 8299/61904 [4:16:02<21:18:06,  1.43s/it]
 13%|█▎        | 8300/61904 [4:16:04<20:42:02,  1.39s/it]
                                                         
{'loss': 2.8616, 'learning_rate': 1.8687281213535588e-07, 'epoch': 2.14}

 13%|█▎        | 8300/61904 [4:16:04<20:42:02,  1.39s/it]
 13%|█▎        | 8301/61904 [4:16:05<21:02:02,  1.41s/it]
 13%|█▎        | 8302/61904 [4:16:07<20:48:53,  1.40s/it]
 13%|█▎        | 8303/61904 [4:16:08<20:19:41,  1.37s/it]
 13%|█▎        | 8304/61904 [4:16:09<21:05:59,  1.42s/it]
 13%|█▎        | 8305/61904 [4:16:11<21:04:03,  1.42s/it]
 13%|█▎        | 8306/61904 [4:16:12<20:46:10,  1.40s/it]
 13%|█▎        | 8307/61904 [4:16:14<21:13:55,  1.43s/it]
 13%|█▎        | 8308/61904 [4:16:15<20:10:25,  1.36s/it]
 13%|█▎        | 8309/61904 [4:16:16<20:59:41,  1.41s/it]
 13%|█▎        | 8310/61904 [4:16:18<21:11:56,  1.42s/it]
 13%|█▎        | 8311/61904 [4:16:19<21:04:48,  1.42s/it]
 13%|█▎        | 8312/61904 [4:16:20<20:35:08,  1.38s/it]
 13%|█▎        | 8313/61904 [4:16:22<20:35:30,  1.38s/it]
 13%|█▎        | 8314/61904 [4:16:23<20:21:11,  1.37s/it]
 13%|█▎        | 8315/61904 [4:16:24<19:59:03,  1.34s/it]
 13%|█▎        | 8316/61904 [4:16:26<20:17:31,  1.36s/it]
 13%|█▎        | 8317/61904 [4:16:27<20:12:16,  1.36s/it]
 13%|█▎        | 8318/61904 [4:16:29<20:12:40,  1.36s/it]
 13%|█▎        | 8319/61904 [4:16:30<19:35:59,  1.32s/it]
 13%|█▎        | 8320/61904 [4:16:31<19:46:21,  1.33s/it]
                                                         
{'loss': 2.8828, 'learning_rate': 1.8684039932581354e-07, 'epoch': 2.15}

 13%|█▎        | 8320/61904 [4:16:31<19:46:21,  1.33s/it]
 13%|█▎        | 8321/61904 [4:16:32<19:41:38,  1.32s/it]
 13%|█▎        | 8322/61904 [4:16:34<19:53:53,  1.34s/it]
 13%|█▎        | 8323/61904 [4:16:35<20:28:05,  1.38s/it]
 13%|█▎        | 8324/61904 [4:16:37<20:54:46,  1.41s/it]
 13%|█▎        | 8325/61904 [4:16:38<21:06:31,  1.42s/it]
 13%|█▎        | 8326/61904 [4:16:40<20:56:38,  1.41s/it]
 13%|█▎        | 8327/61904 [4:16:41<21:08:35,  1.42s/it]
 13%|█▎        | 8328/61904 [4:16:42<21:08:01,  1.42s/it]
 13%|█▎        | 8329/61904 [4:16:44<21:01:58,  1.41s/it]
 13%|█▎        | 8330/61904 [4:16:45<20:22:16,  1.37s/it]
 13%|█▎        | 8331/61904 [4:16:46<20:10:01,  1.36s/it]
 13%|█▎        | 8332/61904 [4:16:48<20:16:51,  1.36s/it]
 13%|█▎        | 8333/61904 [4:16:49<20:27:38,  1.37s/it]
 13%|█▎        | 8334/61904 [4:16:50<19:46:43,  1.33s/it]
 13%|█▎        | 8335/61904 [4:16:52<19:18:14,  1.30s/it]
 13%|█▎        | 8336/61904 [4:16:53<19:48:07,  1.33s/it]
 13%|█▎        | 8337/61904 [4:16:54<19:33:43,  1.31s/it]
 13%|█▎        | 8338/61904 [4:16:56<19:29:30,  1.31s/it]
 13%|█▎        | 8339/61904 [4:16:57<19:57:22,  1.34s/it]
 13%|█▎        | 8340/61904 [4:16:58<19:51:35,  1.33s/it]
                                                         
{'loss': 2.8614, 'learning_rate': 1.868079865162712e-07, 'epoch': 2.16}

 13%|█▎        | 8340/61904 [4:16:58<19:51:35,  1.33s/it]
 13%|█▎        | 8341/61904 [4:17:00<19:37:51,  1.32s/it]
 13%|█▎        | 8342/61904 [4:17:02<21:47:13,  1.46s/it]
 13%|█▎        | 8343/61904 [4:17:03<22:14:03,  1.49s/it]
 13%|█▎        | 8344/61904 [4:17:04<21:22:32,  1.44s/it]
 13%|█▎        | 8345/61904 [4:17:06<21:26:00,  1.44s/it]
 13%|█▎        | 8346/61904 [4:17:07<21:19:31,  1.43s/it]
 13%|█▎        | 8347/61904 [4:17:09<20:58:07,  1.41s/it]
 13%|█▎        | 8348/61904 [4:17:10<20:00:35,  1.35s/it]
 13%|█▎        | 8349/61904 [4:17:11<20:50:44,  1.40s/it]
 13%|█▎        | 8350/61904 [4:17:13<20:56:38,  1.41s/it]
 13%|█▎        | 8351/61904 [4:17:14<21:31:11,  1.45s/it]
 13%|█▎        | 8352/61904 [4:17:16<21:15:26,  1.43s/it]
 13%|█▎        | 8353/61904 [4:17:17<21:33:29,  1.45s/it]
 13%|█▎        | 8354/61904 [4:17:19<21:06:49,  1.42s/it]
 13%|█▎        | 8355/61904 [4:17:20<20:52:41,  1.40s/it]
 13%|█▎        | 8356/61904 [4:17:21<20:14:21,  1.36s/it]
 13%|█▎        | 8357/61904 [4:17:22<19:59:09,  1.34s/it]
 14%|█▎        | 8358/61904 [4:17:24<19:47:06,  1.33s/it]
 14%|█▎        | 8359/61904 [4:17:25<19:45:20,  1.33s/it]
 14%|█▎        | 8360/61904 [4:17:26<19:16:51,  1.30s/it]
                                                         
{'loss': 2.8295, 'learning_rate': 1.867755737067289e-07, 'epoch': 2.16}

 14%|█▎        | 8360/61904 [4:17:26<19:16:51,  1.30s/it]
 14%|█▎        | 8361/61904 [4:17:28<19:55:24,  1.34s/it]
 14%|█▎        | 8362/61904 [4:17:29<20:17:28,  1.36s/it]
 14%|█▎        | 8363/61904 [4:17:30<19:47:02,  1.33s/it]
 14%|█▎        | 8364/61904 [4:17:32<20:15:57,  1.36s/it]
 14%|█▎        | 8365/61904 [4:17:33<20:28:01,  1.38s/it]
 14%|█▎        | 8366/61904 [4:17:35<21:07:20,  1.42s/it]
 14%|█▎        | 8367/61904 [4:17:36<21:04:24,  1.42s/it]
 14%|█▎        | 8368/61904 [4:17:38<20:50:37,  1.40s/it]
 14%|█▎        | 8369/61904 [4:17:39<20:47:55,  1.40s/it]
 14%|█▎        | 8370/61904 [4:17:40<20:25:28,  1.37s/it]
 14%|█▎        | 8371/61904 [4:17:41<19:48:18,  1.33s/it]
 14%|█▎        | 8372/61904 [4:17:43<21:01:25,  1.41s/it]
 14%|█▎        | 8373/61904 [4:17:44<20:07:21,  1.35s/it]
 14%|█▎        | 8374/61904 [4:17:46<19:36:50,  1.32s/it]
 14%|█▎        | 8375/61904 [4:17:47<20:31:10,  1.38s/it]
 14%|█▎        | 8376/61904 [4:17:48<20:19:16,  1.37s/it]
 14%|█▎        | 8377/61904 [4:17:50<20:39:46,  1.39s/it]
 14%|█▎        | 8378/61904 [4:17:51<20:51:45,  1.40s/it]
 14%|█▎        | 8379/61904 [4:17:53<21:49:46,  1.47s/it]
 14%|█▎        | 8380/61904 [4:17:54<21:55:43,  1.47s/it]
                                                         
{'loss': 2.8375, 'learning_rate': 1.8674316089718655e-07, 'epoch': 2.17}

 14%|█▎        | 8380/61904 [4:17:54<21:55:43,  1.47s/it]
 14%|█▎        | 8381/61904 [4:17:56<21:41:50,  1.46s/it]
 14%|█▎        | 8382/61904 [4:17:57<21:02:19,  1.42s/it]
 14%|█▎        | 8383/61904 [4:17:58<20:42:18,  1.39s/it]
 14%|█▎        | 8384/61904 [4:18:00<20:11:55,  1.36s/it]
 14%|█▎        | 8385/61904 [4:18:01<20:15:59,  1.36s/it]
 14%|█▎        | 8386/61904 [4:18:02<20:05:34,  1.35s/it]
 14%|█▎        | 8387/61904 [4:18:04<20:13:39,  1.36s/it]
 14%|█▎        | 8388/61904 [4:18:05<20:46:05,  1.40s/it]
 14%|█▎        | 8389/61904 [4:18:07<20:27:36,  1.38s/it]
 14%|█▎        | 8390/61904 [4:18:08<19:58:55,  1.34s/it]
 14%|█▎        | 8391/61904 [4:18:09<19:53:01,  1.34s/it]
 14%|█▎        | 8392/61904 [4:18:11<19:47:47,  1.33s/it]
 14%|█▎        | 8393/61904 [4:18:12<19:30:10,  1.31s/it]
 14%|█▎        | 8394/61904 [4:18:13<20:10:18,  1.36s/it]
 14%|█▎        | 8395/61904 [4:18:15<20:09:13,  1.36s/it]
 14%|█▎        | 8396/61904 [4:18:16<19:58:41,  1.34s/it]
 14%|█▎        | 8397/61904 [4:18:17<19:47:33,  1.33s/it]
 14%|█▎        | 8398/61904 [4:18:19<21:02:58,  1.42s/it]
 14%|█▎        | 8399/61904 [4:18:20<21:41:14,  1.46s/it]
 14%|█▎        | 8400/61904 [4:18:22<20:28:52,  1.38s/it]
                                                         
{'loss': 2.844, 'learning_rate': 1.8671074808764422e-07, 'epoch': 2.17}

 14%|█▎        | 8400/61904 [4:18:22<20:28:52,  1.38s/it]
 14%|█▎        | 8401/61904 [4:18:23<19:56:54,  1.34s/it]
 14%|█▎        | 8402/61904 [4:18:24<19:44:42,  1.33s/it]
 14%|█▎        | 8403/61904 [4:18:25<19:29:14,  1.31s/it]
 14%|█▎        | 8404/61904 [4:18:27<19:24:14,  1.31s/it]
 14%|█▎        | 8405/61904 [4:18:28<19:37:46,  1.32s/it]
 14%|█▎        | 8406/61904 [4:18:29<19:17:29,  1.30s/it]
 14%|█▎        | 8407/61904 [4:18:31<20:21:17,  1.37s/it]
 14%|█▎        | 8408/61904 [4:18:32<20:15:46,  1.36s/it]
 14%|█▎        | 8409/61904 [4:18:34<19:56:46,  1.34s/it]
 14%|█▎        | 8410/61904 [4:18:35<19:44:37,  1.33s/it]
 14%|█▎        | 8411/61904 [4:18:36<20:07:31,  1.35s/it]
 14%|█▎        | 8412/61904 [4:18:38<20:21:38,  1.37s/it]
 14%|█▎        | 8413/61904 [4:18:39<20:16:13,  1.36s/it]
 14%|█▎        | 8414/61904 [4:18:40<20:01:37,  1.35s/it]
 14%|█▎        | 8415/61904 [4:18:42<20:32:38,  1.38s/it]
 14%|█▎        | 8416/61904 [4:18:43<20:47:22,  1.40s/it]
 14%|█▎        | 8417/61904 [4:18:44<20:02:53,  1.35s/it]
 14%|█▎        | 8418/61904 [4:18:46<19:39:22,  1.32s/it]
 14%|█▎        | 8419/61904 [4:18:47<20:36:42,  1.39s/it]
 14%|█▎        | 8420/61904 [4:18:49<20:40:19,  1.39s/it]
                                                         
{'loss': 2.8151, 'learning_rate': 1.866783352781019e-07, 'epoch': 2.18}

 14%|█▎        | 8420/61904 [4:18:49<20:40:19,  1.39s/it]
 14%|█▎        | 8421/61904 [4:18:50<21:07:53,  1.42s/it]
 14%|█▎        | 8422/61904 [4:18:51<20:19:39,  1.37s/it]
 14%|█▎        | 8423/61904 [4:18:53<20:25:18,  1.37s/it]
 14%|█▎        | 8424/61904 [4:18:54<19:56:22,  1.34s/it]
 14%|█▎        | 8425/61904 [4:18:56<20:41:13,  1.39s/it]
 14%|█▎        | 8426/61904 [4:18:57<20:11:02,  1.36s/it]
 14%|█▎        | 8427/61904 [4:18:58<20:49:40,  1.40s/it]
 14%|█▎        | 8428/61904 [4:19:00<20:04:17,  1.35s/it]
 14%|█▎        | 8429/61904 [4:19:01<19:43:12,  1.33s/it]
 14%|█▎        | 8430/61904 [4:19:02<20:50:42,  1.40s/it]
 14%|█▎        | 8431/61904 [4:19:04<20:31:42,  1.38s/it]
 14%|█▎        | 8432/61904 [4:19:05<19:59:17,  1.35s/it]
 14%|█▎        | 8433/61904 [4:19:06<20:24:13,  1.37s/it]
 14%|█▎        | 8434/61904 [4:19:08<20:38:59,  1.39s/it]
 14%|█▎        | 8435/61904 [4:19:09<21:19:38,  1.44s/it]
 14%|█▎        | 8436/61904 [4:19:11<21:01:30,  1.42s/it]
 14%|█▎        | 8437/61904 [4:19:12<20:08:05,  1.36s/it]
 14%|█▎        | 8438/61904 [4:19:13<20:27:56,  1.38s/it]
 14%|█▎        | 8439/61904 [4:19:15<20:22:39,  1.37s/it]
 14%|█▎        | 8440/61904 [4:19:16<19:59:10,  1.35s/it]
                                                         
{'loss': 2.8761, 'learning_rate': 1.8664592246855957e-07, 'epoch': 2.18}

 14%|█▎        | 8440/61904 [4:19:16<19:59:10,  1.35s/it]
 14%|█▎        | 8441/61904 [4:19:18<20:29:26,  1.38s/it]
 14%|█▎        | 8442/61904 [4:19:19<20:25:36,  1.38s/it]
 14%|█▎        | 8443/61904 [4:19:20<20:27:33,  1.38s/it]
 14%|█▎        | 8444/61904 [4:19:22<20:26:33,  1.38s/it]
 14%|█▎        | 8445/61904 [4:19:23<20:18:54,  1.37s/it]
 14%|█▎        | 8446/61904 [4:19:24<20:01:44,  1.35s/it]
 14%|█▎        | 8447/61904 [4:19:25<19:24:25,  1.31s/it]
 14%|█▎        | 8448/61904 [4:19:27<19:21:38,  1.30s/it]
 14%|█▎        | 8449/61904 [4:19:28<19:07:55,  1.29s/it]
 14%|█▎        | 8450/61904 [4:19:29<19:21:56,  1.30s/it]
 14%|█▎        | 8451/61904 [4:19:31<19:35:34,  1.32s/it]
 14%|█▎        | 8452/61904 [4:19:32<19:38:20,  1.32s/it]
 14%|█▎        | 8453/61904 [4:19:34<20:25:25,  1.38s/it]
 14%|█▎        | 8454/61904 [4:19:35<21:04:03,  1.42s/it]
 14%|█▎        | 8455/61904 [4:19:36<20:33:33,  1.38s/it]
 14%|█▎        | 8456/61904 [4:19:38<20:29:41,  1.38s/it]
 14%|█▎        | 8457/61904 [4:19:39<19:41:53,  1.33s/it]
 14%|█▎        | 8458/61904 [4:19:40<20:02:37,  1.35s/it]
 14%|█▎        | 8459/61904 [4:19:42<20:18:04,  1.37s/it]
 14%|█▎        | 8460/61904 [4:19:43<20:26:33,  1.38s/it]
                                                         
{'loss': 2.9129, 'learning_rate': 1.8661350965901723e-07, 'epoch': 2.19}

 14%|█▎        | 8460/61904 [4:19:43<20:26:33,  1.38s/it]
 14%|█▎        | 8461/61904 [4:19:44<19:51:21,  1.34s/it]
 14%|█▎        | 8462/61904 [4:19:46<19:46:02,  1.33s/it]
 14%|█▎        | 8463/61904 [4:19:47<20:21:21,  1.37s/it]
 14%|█▎        | 8464/61904 [4:19:48<19:42:26,  1.33s/it]
 14%|█▎        | 8465/61904 [4:19:50<20:01:30,  1.35s/it]
 14%|█▎        | 8466/61904 [4:19:51<20:21:41,  1.37s/it]
 14%|█▎        | 8467/61904 [4:19:53<20:33:51,  1.39s/it]
 14%|█▎        | 8468/61904 [4:19:54<20:09:31,  1.36s/it]
 14%|█▎        | 8469/61904 [4:19:55<20:13:51,  1.36s/it]
 14%|█▎        | 8470/61904 [4:19:57<19:56:09,  1.34s/it]
 14%|█▎        | 8471/61904 [4:19:58<20:54:11,  1.41s/it]
 14%|█▎        | 8472/61904 [4:20:00<21:02:54,  1.42s/it]
 14%|█▎        | 8473/61904 [4:20:01<20:08:54,  1.36s/it]
 14%|█▎        | 8474/61904 [4:20:02<20:02:22,  1.35s/it]
 14%|█▎        | 8475/61904 [4:20:04<20:13:33,  1.36s/it]
 14%|█▎        | 8476/61904 [4:20:05<20:09:38,  1.36s/it]
 14%|█▎        | 8477/61904 [4:20:06<19:57:11,  1.34s/it]
 14%|█▎        | 8478/61904 [4:20:08<19:53:15,  1.34s/it]
 14%|█▎        | 8479/61904 [4:20:09<19:53:55,  1.34s/it]
 14%|█▎        | 8480/61904 [4:20:10<19:48:00,  1.33s/it]
                                                         
{'loss': 2.8907, 'learning_rate': 1.8658109684947492e-07, 'epoch': 2.19}

 14%|█▎        | 8480/61904 [4:20:10<19:48:00,  1.33s/it]
 14%|█▎        | 8481/61904 [4:20:12<20:42:28,  1.40s/it]
 14%|█▎        | 8482/61904 [4:20:13<20:41:54,  1.39s/it]
 14%|█▎        | 8483/61904 [4:20:15<20:31:08,  1.38s/it]
 14%|█▎        | 8484/61904 [4:20:16<19:50:38,  1.34s/it]
 14%|█▎        | 8485/61904 [4:20:17<19:37:27,  1.32s/it]
 14%|█▎        | 8486/61904 [4:20:18<19:16:39,  1.30s/it]
 14%|█▎        | 8487/61904 [4:20:20<19:55:06,  1.34s/it]
 14%|█▎        | 8488/61904 [4:20:21<19:21:42,  1.30s/it]
 14%|█▎        | 8489/61904 [4:20:22<19:41:20,  1.33s/it]
 14%|█▎        | 8490/61904 [4:20:24<19:49:52,  1.34s/it]
 14%|█▎        | 8491/61904 [4:20:25<19:59:54,  1.35s/it]
 14%|█▎        | 8492/61904 [4:20:26<19:45:18,  1.33s/it]
 14%|█▎        | 8493/61904 [4:20:28<20:15:45,  1.37s/it]
 14%|█▎        | 8494/61904 [4:20:29<20:29:27,  1.38s/it]
 14%|█▎        | 8495/61904 [4:20:31<20:22:09,  1.37s/it]
 14%|█▎        | 8496/61904 [4:20:32<21:08:34,  1.43s/it]
 14%|█▎        | 8497/61904 [4:20:33<20:39:51,  1.39s/it]
 14%|█▎        | 8498/61904 [4:20:35<20:56:05,  1.41s/it]
 14%|█▎        | 8499/61904 [4:20:36<21:22:05,  1.44s/it]
 14%|█▎        | 8500/61904 [4:20:38<20:33:06,  1.39s/it]
                                                         
{'loss': 2.9062, 'learning_rate': 1.8654868403993255e-07, 'epoch': 2.2}

 14%|█▎        | 8500/61904 [4:20:38<20:33:06,  1.39s/it]
 14%|█▎        | 8501/61904 [4:20:39<19:41:54,  1.33s/it]
 14%|█▎        | 8502/61904 [4:20:40<19:44:45,  1.33s/it]
 14%|█▎        | 8503/61904 [4:20:42<20:19:15,  1.37s/it]
 14%|█▎        | 8504/61904 [4:20:43<20:05:30,  1.35s/it]
 14%|█▎        | 8505/61904 [4:20:44<20:03:11,  1.35s/it]
 14%|█▎        | 8506/61904 [4:20:46<20:14:36,  1.36s/it]
 14%|█▎        | 8507/61904 [4:20:47<19:49:44,  1.34s/it]
 14%|█▎        | 8508/61904 [4:20:48<19:47:51,  1.33s/it]
 14%|█▎        | 8509/61904 [4:20:50<19:36:16,  1.32s/it]
 14%|█▎        | 8510/61904 [4:20:51<20:00:48,  1.35s/it]
 14%|█▎        | 8511/61904 [4:20:52<19:47:10,  1.33s/it]
 14%|█▍        | 8512/61904 [4:20:54<19:20:03,  1.30s/it]
 14%|█▍        | 8513/61904 [4:20:55<19:27:05,  1.31s/it]
 14%|█▍        | 8514/61904 [4:20:56<19:43:58,  1.33s/it]
 14%|█▍        | 8515/61904 [4:20:58<19:45:30,  1.33s/it]
 14%|█▍        | 8516/61904 [4:20:59<19:44:44,  1.33s/it]
 14%|█▍        | 8517/61904 [4:21:00<20:16:37,  1.37s/it]
 14%|█▍        | 8518/61904 [4:21:02<20:29:15,  1.38s/it]
 14%|█▍        | 8519/61904 [4:21:03<20:00:00,  1.35s/it]
 14%|█▍        | 8520/61904 [4:21:04<19:48:13,  1.34s/it]
                                                         
{'loss': 2.9185, 'learning_rate': 1.8651627123039024e-07, 'epoch': 2.2}

 14%|█▍        | 8520/61904 [4:21:04<19:48:13,  1.34s/it]
 14%|█▍        | 8521/61904 [4:21:06<20:29:26,  1.38s/it]
 14%|█▍        | 8522/61904 [4:21:07<19:59:14,  1.35s/it]
 14%|█▍        | 8523/61904 [4:21:08<19:58:58,  1.35s/it]
 14%|█▍        | 8524/61904 [4:21:10<19:57:29,  1.35s/it]
 14%|█▍        | 8525/61904 [4:21:11<19:11:02,  1.29s/it]
 14%|█▍        | 8526/61904 [4:21:12<19:09:53,  1.29s/it]
 14%|█▍        | 8527/61904 [4:21:14<19:44:46,  1.33s/it]
 14%|█▍        | 8528/61904 [4:21:15<19:28:18,  1.31s/it]
 14%|█▍        | 8529/61904 [4:21:16<19:40:37,  1.33s/it]
 14%|█▍        | 8530/61904 [4:21:18<19:24:53,  1.31s/it]
 14%|█▍        | 8531/61904 [4:21:19<20:27:53,  1.38s/it]
 14%|█▍        | 8532/61904 [4:21:20<20:22:01,  1.37s/it]
 14%|█▍        | 8533/61904 [4:21:22<20:11:28,  1.36s/it]
 14%|█▍        | 8534/61904 [4:21:23<20:07:06,  1.36s/it]
 14%|█▍        | 8535/61904 [4:21:24<20:00:05,  1.35s/it]
 14%|█▍        | 8536/61904 [4:21:26<20:02:55,  1.35s/it]
 14%|█▍        | 8537/61904 [4:21:27<19:56:14,  1.34s/it]
 14%|█▍        | 8538/61904 [4:21:28<19:41:03,  1.33s/it]
 14%|█▍        | 8539/61904 [4:21:30<19:16:53,  1.30s/it]
 14%|█▍        | 8540/61904 [4:21:31<19:06:12,  1.29s/it]
                                                         
{'loss': 2.9334, 'learning_rate': 1.864838584208479e-07, 'epoch': 2.21}

 14%|█▍        | 8540/61904 [4:21:31<19:06:12,  1.29s/it]
 14%|█▍        | 8541/61904 [4:21:32<19:37:58,  1.32s/it]
 14%|█▍        | 8542/61904 [4:21:34<20:27:47,  1.38s/it]
 14%|█▍        | 8543/61904 [4:21:35<21:13:28,  1.43s/it]
 14%|█▍        | 8544/61904 [4:21:37<20:54:42,  1.41s/it]
 14%|█▍        | 8545/61904 [4:21:38<20:56:26,  1.41s/it]
 14%|█▍        | 8546/61904 [4:21:40<21:02:26,  1.42s/it]
 14%|█▍        | 8547/61904 [4:21:41<21:11:43,  1.43s/it]
 14%|█▍        | 8548/61904 [4:21:43<21:04:22,  1.42s/it]
 14%|█▍        | 8549/61904 [4:21:44<22:23:51,  1.51s/it]
 14%|█▍        | 8550/61904 [4:21:46<21:24:50,  1.44s/it]
 14%|█▍        | 8551/61904 [4:21:47<20:38:09,  1.39s/it]
 14%|█▍        | 8552/61904 [4:21:48<19:55:00,  1.34s/it]
 14%|█▍        | 8553/61904 [4:21:49<20:20:57,  1.37s/it]
 14%|█▍        | 8554/61904 [4:21:51<20:14:21,  1.37s/it]
 14%|█▍        | 8555/61904 [4:21:52<20:31:38,  1.39s/it]
 14%|█▍        | 8556/61904 [4:21:54<21:05:17,  1.42s/it]
 14%|█▍        | 8557/61904 [4:21:55<20:18:52,  1.37s/it]
 14%|█▍        | 8558/61904 [4:21:56<20:23:20,  1.38s/it]
 14%|█▍        | 8559/61904 [4:21:58<20:12:32,  1.36s/it]
 14%|█▍        | 8560/61904 [4:21:59<19:42:54,  1.33s/it]
                                                         
{'loss': 2.8598, 'learning_rate': 1.8645144561130556e-07, 'epoch': 2.21}

 14%|█▍        | 8560/61904 [4:21:59<19:42:54,  1.33s/it]
 14%|█▍        | 8561/61904 [4:22:00<19:59:49,  1.35s/it]
 14%|█▍        | 8562/61904 [4:22:02<19:44:06,  1.33s/it]
 14%|█▍        | 8563/61904 [4:22:03<19:58:23,  1.35s/it]
 14%|█▍        | 8564/61904 [4:22:04<19:54:00,  1.34s/it]
 14%|█▍        | 8565/61904 [4:22:06<19:45:04,  1.33s/it]
 14%|█▍        | 8566/61904 [4:22:07<19:47:01,  1.34s/it]
 14%|█▍        | 8567/61904 [4:22:08<19:55:16,  1.34s/it]
 14%|█▍        | 8568/61904 [4:22:10<19:57:30,  1.35s/it]
 14%|█▍        | 8569/61904 [4:22:11<19:46:47,  1.34s/it]
 14%|█▍        | 8570/61904 [4:22:12<19:54:10,  1.34s/it]
 14%|█▍        | 8571/61904 [4:22:14<20:06:20,  1.36s/it]
 14%|█▍        | 8572/61904 [4:22:15<20:37:07,  1.39s/it]
 14%|█▍        | 8573/61904 [4:22:17<20:14:25,  1.37s/it]
 14%|█▍        | 8574/61904 [4:22:18<20:18:06,  1.37s/it]
 14%|█▍        | 8575/61904 [4:22:19<19:51:50,  1.34s/it]
 14%|█▍        | 8576/61904 [4:22:21<19:52:33,  1.34s/it]
 14%|█▍        | 8577/61904 [4:22:22<20:22:17,  1.38s/it]
 14%|█▍        | 8578/61904 [4:22:23<20:27:24,  1.38s/it]
 14%|█▍        | 8579/61904 [4:22:25<21:11:05,  1.43s/it]
 14%|█▍        | 8580/61904 [4:22:26<21:08:34,  1.43s/it]
                                                         
{'loss': 2.8341, 'learning_rate': 1.8641903280176325e-07, 'epoch': 2.22}

 14%|█▍        | 8580/61904 [4:22:26<21:08:34,  1.43s/it]
 14%|█▍        | 8581/61904 [4:22:28<22:01:18,  1.49s/it]
 14%|█▍        | 8582/61904 [4:22:29<21:46:18,  1.47s/it]
 14%|█▍        | 8583/61904 [4:22:31<21:25:22,  1.45s/it]
 14%|█▍        | 8584/61904 [4:22:32<21:02:30,  1.42s/it]
 14%|█▍        | 8585/61904 [4:22:34<20:41:15,  1.40s/it]
 14%|█▍        | 8586/61904 [4:22:35<20:33:36,  1.39s/it]
 14%|█▍        | 8587/61904 [4:22:36<20:28:29,  1.38s/it]
 14%|█▍        | 8588/61904 [4:22:38<20:32:12,  1.39s/it]
 14%|█▍        | 8589/61904 [4:22:39<20:07:47,  1.36s/it]
 14%|█▍        | 8590/61904 [4:22:40<20:16:22,  1.37s/it]
 14%|█▍        | 8591/61904 [4:22:42<20:40:18,  1.40s/it]
 14%|█▍        | 8592/61904 [4:22:43<20:24:36,  1.38s/it]
 14%|█▍        | 8593/61904 [4:22:44<20:12:46,  1.36s/it]
 14%|█▍        | 8594/61904 [4:22:46<20:03:23,  1.35s/it]
 14%|█▍        | 8595/61904 [4:22:47<19:41:58,  1.33s/it]
 14%|█▍        | 8596/61904 [4:22:49<20:26:09,  1.38s/it]
 14%|█▍        | 8597/61904 [4:22:50<19:59:04,  1.35s/it]
 14%|█▍        | 8598/61904 [4:22:51<20:08:08,  1.36s/it]
 14%|█▍        | 8599/61904 [4:22:53<21:14:26,  1.43s/it]
 14%|█▍        | 8600/61904 [4:22:54<20:21:04,  1.37s/it]
                                                         
{'loss': 2.9006, 'learning_rate': 1.8638661999222091e-07, 'epoch': 2.22}

 14%|█▍        | 8600/61904 [4:22:54<20:21:04,  1.37s/it]
 14%|█▍        | 8601/61904 [4:22:55<20:13:12,  1.37s/it]
 14%|█▍        | 8602/61904 [4:22:57<20:30:07,  1.38s/it]
 14%|█▍        | 8603/61904 [4:22:58<20:24:11,  1.38s/it]
 14%|█▍        | 8604/61904 [4:22:59<19:36:01,  1.32s/it]
 14%|█▍        | 8605/61904 [4:23:01<19:50:25,  1.34s/it]
 14%|█▍        | 8606/61904 [4:23:02<19:38:21,  1.33s/it]
 14%|█▍        | 8607/61904 [4:23:04<20:20:56,  1.37s/it]
 14%|█▍        | 8608/61904 [4:23:05<20:04:05,  1.36s/it]
 14%|█▍        | 8609/61904 [4:23:06<19:55:10,  1.35s/it]
 14%|█▍        | 8610/61904 [4:23:08<20:07:54,  1.36s/it]
 14%|█▍        | 8611/61904 [4:23:09<19:40:52,  1.33s/it]
 14%|█▍        | 8612/61904 [4:23:10<19:29:22,  1.32s/it]
 14%|█▍        | 8613/61904 [4:23:12<19:35:13,  1.32s/it]
 14%|█▍        | 8614/61904 [4:23:13<20:10:04,  1.36s/it]
 14%|█▍        | 8615/61904 [4:23:14<19:51:46,  1.34s/it]
 14%|█▍        | 8616/61904 [4:23:16<19:30:17,  1.32s/it]
 14%|█▍        | 8617/61904 [4:23:17<19:12:42,  1.30s/it]
 14%|█▍        | 8618/61904 [4:23:18<20:03:13,  1.35s/it]
 14%|█▍        | 8619/61904 [4:23:20<19:42:14,  1.33s/it]
 14%|█▍        | 8620/61904 [4:23:21<19:27:15,  1.31s/it]
                                                         
{'loss': 2.8851, 'learning_rate': 1.8635420718267858e-07, 'epoch': 2.23}

 14%|█▍        | 8620/61904 [4:23:21<19:27:15,  1.31s/it]
 14%|█▍        | 8621/61904 [4:23:22<19:10:55,  1.30s/it]
 14%|█▍        | 8622/61904 [4:23:23<19:32:48,  1.32s/it]
 14%|█▍        | 8623/61904 [4:23:25<19:34:14,  1.32s/it]
 14%|█▍        | 8624/61904 [4:23:26<20:00:05,  1.35s/it]
 14%|█▍        | 8625/61904 [4:23:28<19:52:34,  1.34s/it]
 14%|█▍        | 8626/61904 [4:23:29<19:48:14,  1.34s/it]
 14%|█▍        | 8627/61904 [4:23:30<19:44:40,  1.33s/it]
 14%|█▍        | 8628/61904 [4:23:32<19:58:55,  1.35s/it]
 14%|█▍        | 8629/61904 [4:23:33<20:24:50,  1.38s/it]
 14%|█▍        | 8630/61904 [4:23:34<19:53:56,  1.34s/it]
 14%|█▍        | 8631/61904 [4:23:36<19:38:00,  1.33s/it]
 14%|█▍        | 8632/61904 [4:23:37<19:16:29,  1.30s/it]
 14%|█▍        | 8633/61904 [4:23:38<19:56:40,  1.35s/it]
 14%|█▍        | 8634/61904 [4:23:40<20:42:27,  1.40s/it]
 14%|█▍        | 8635/61904 [4:23:41<20:30:31,  1.39s/it]
 14%|█▍        | 8636/61904 [4:23:42<20:11:48,  1.36s/it]
 14%|█▍        | 8637/61904 [4:23:44<20:31:40,  1.39s/it]
 14%|█▍        | 8638/61904 [4:23:45<21:04:23,  1.42s/it]
 14%|█▍        | 8639/61904 [4:23:47<21:03:35,  1.42s/it]
 14%|█▍        | 8640/61904 [4:23:48<21:13:19,  1.43s/it]
                                                         
{'loss': 2.8807, 'learning_rate': 1.8632179437313626e-07, 'epoch': 2.23}

 14%|█▍        | 8640/61904 [4:23:48<21:13:19,  1.43s/it]
 14%|█▍        | 8641/61904 [4:23:50<20:59:51,  1.42s/it]
 14%|█▍        | 8642/61904 [4:23:51<20:36:49,  1.39s/it]
 14%|█▍        | 8643/61904 [4:23:52<20:24:02,  1.38s/it]
 14%|█▍        | 8644/61904 [4:23:54<19:59:24,  1.35s/it]
 14%|█▍        | 8645/61904 [4:23:55<20:11:01,  1.36s/it]
 14%|█▍        | 8646/61904 [4:23:56<20:25:15,  1.38s/it]
 14%|█▍        | 8647/61904 [4:23:58<21:09:59,  1.43s/it]
 14%|█▍        | 8648/61904 [4:23:59<20:40:46,  1.40s/it]
 14%|█▍        | 8649/61904 [4:24:01<20:00:22,  1.35s/it]
 14%|█▍        | 8650/61904 [4:24:02<19:47:23,  1.34s/it]
 14%|█▍        | 8651/61904 [4:24:03<20:22:23,  1.38s/it]
 14%|█▍        | 8652/61904 [4:24:05<20:21:49,  1.38s/it]
 14%|█▍        | 8653/61904 [4:24:06<19:58:50,  1.35s/it]
 14%|█▍        | 8654/61904 [4:24:07<19:51:04,  1.34s/it]
 14%|█▍        | 8655/61904 [4:24:09<19:38:23,  1.33s/it]
 14%|█▍        | 8656/61904 [4:24:10<19:01:01,  1.29s/it]
 14%|█▍        | 8657/61904 [4:24:11<19:04:37,  1.29s/it]
 14%|█▍        | 8658/61904 [4:24:12<19:09:51,  1.30s/it]
 14%|█▍        | 8659/61904 [4:24:14<19:25:34,  1.31s/it]
 14%|█▍        | 8660/61904 [4:24:15<19:32:07,  1.32s/it]
                                                         
{'loss': 2.8064, 'learning_rate': 1.8628938156359393e-07, 'epoch': 2.24}

 14%|█▍        | 8660/61904 [4:24:15<19:32:07,  1.32s/it]
 14%|█▍        | 8661/61904 [4:24:16<19:35:49,  1.33s/it]
 14%|█▍        | 8662/61904 [4:24:18<18:57:21,  1.28s/it]
 14%|█▍        | 8663/61904 [4:24:19<19:45:23,  1.34s/it]
 14%|█▍        | 8664/61904 [4:24:20<19:24:43,  1.31s/it]
 14%|█▍        | 8665/61904 [4:24:22<20:11:05,  1.36s/it]
 14%|█▍        | 8666/61904 [4:24:23<19:43:52,  1.33s/it]
 14%|█▍        | 8667/61904 [4:24:24<19:46:25,  1.34s/it]
 14%|█▍        | 8668/61904 [4:24:26<20:07:16,  1.36s/it]
 14%|█▍        | 8669/61904 [4:24:27<20:08:33,  1.36s/it]
 14%|█▍        | 8670/61904 [4:24:29<20:07:48,  1.36s/it]
 14%|█▍        | 8671/61904 [4:24:30<19:55:38,  1.35s/it]
 14%|█▍        | 8672/61904 [4:24:31<19:48:48,  1.34s/it]
 14%|█▍        | 8673/61904 [4:24:33<20:10:48,  1.36s/it]
 14%|█▍        | 8674/61904 [4:24:34<19:58:47,  1.35s/it]
 14%|█▍        | 8675/61904 [4:24:35<20:21:39,  1.38s/it]
 14%|█▍        | 8676/61904 [4:24:37<20:28:43,  1.39s/it]
 14%|█▍        | 8677/61904 [4:24:38<20:17:18,  1.37s/it]
 14%|█▍        | 8678/61904 [4:24:39<20:00:40,  1.35s/it]
 14%|█▍        | 8679/61904 [4:24:41<20:37:34,  1.40s/it]
 14%|█▍        | 8680/61904 [4:24:42<20:34:50,  1.39s/it]
                                                         
{'loss': 2.89, 'learning_rate': 1.862569687540516e-07, 'epoch': 2.24}

 14%|█▍        | 8680/61904 [4:24:42<20:34:50,  1.39s/it]
 14%|█▍        | 8681/61904 [4:24:44<20:11:19,  1.37s/it]
 14%|█▍        | 8682/61904 [4:24:45<19:46:21,  1.34s/it]
 14%|█▍        | 8683/61904 [4:24:46<20:06:39,  1.36s/it]
 14%|█▍        | 8684/61904 [4:24:48<19:50:04,  1.34s/it]
 14%|█▍        | 8685/61904 [4:24:49<19:31:59,  1.32s/it]
 14%|█▍        | 8686/61904 [4:24:50<19:37:20,  1.33s/it]
 14%|█▍        | 8687/61904 [4:24:51<19:24:31,  1.31s/it]
 14%|█▍        | 8688/61904 [4:24:53<20:26:34,  1.38s/it]
 14%|█▍        | 8689/61904 [4:24:54<20:08:45,  1.36s/it]
 14%|█▍        | 8690/61904 [4:24:56<20:11:31,  1.37s/it]
 14%|█▍        | 8691/61904 [4:24:57<19:45:50,  1.34s/it]
 14%|█▍        | 8692/61904 [4:24:58<19:28:28,  1.32s/it]
 14%|█▍        | 8693/61904 [4:25:00<19:38:07,  1.33s/it]
 14%|█▍        | 8694/61904 [4:25:01<20:10:51,  1.37s/it]
 14%|█▍        | 8695/61904 [4:25:03<20:35:10,  1.39s/it]
 14%|█▍        | 8696/61904 [4:25:04<20:10:56,  1.37s/it]
 14%|█▍        | 8697/61904 [4:25:05<19:45:17,  1.34s/it]
 14%|█▍        | 8698/61904 [4:25:06<19:59:11,  1.35s/it]
 14%|█▍        | 8699/61904 [4:25:08<20:25:20,  1.38s/it]
 14%|█▍        | 8700/61904 [4:25:09<20:53:01,  1.41s/it]
                                                         
{'loss': 2.8585, 'learning_rate': 1.8622455594450928e-07, 'epoch': 2.25}

 14%|█▍        | 8700/61904 [4:25:09<20:53:01,  1.41s/it]
 14%|█▍        | 8701/61904 [4:25:11<20:30:35,  1.39s/it]
 14%|█▍        | 8702/61904 [4:25:12<19:50:57,  1.34s/it]
 14%|█▍        | 8703/61904 [4:25:13<19:37:08,  1.33s/it]
 14%|█▍        | 8704/61904 [4:25:15<20:21:30,  1.38s/it]
 14%|█▍        | 8705/61904 [4:25:16<20:16:55,  1.37s/it]
 14%|█▍        | 8706/61904 [4:25:18<20:20:44,  1.38s/it]
 14%|█▍        | 8707/61904 [4:25:19<19:55:18,  1.35s/it]
 14%|█▍        | 8708/61904 [4:25:20<19:59:40,  1.35s/it]
 14%|█▍        | 8709/61904 [4:25:21<19:37:47,  1.33s/it]
 14%|█▍        | 8710/61904 [4:25:23<20:02:25,  1.36s/it]
 14%|█▍        | 8711/61904 [4:25:24<20:29:54,  1.39s/it]
 14%|█▍        | 8712/61904 [4:25:26<20:24:51,  1.38s/it]
 14%|█▍        | 8713/61904 [4:25:27<19:48:34,  1.34s/it]
 14%|█▍        | 8714/61904 [4:25:28<20:31:22,  1.39s/it]
 14%|█▍        | 8715/61904 [4:25:30<19:44:21,  1.34s/it]
 14%|█▍        | 8716/61904 [4:25:31<19:27:57,  1.32s/it]
 14%|█▍        | 8717/61904 [4:25:32<19:22:29,  1.31s/it]
 14%|█▍        | 8718/61904 [4:25:34<20:09:31,  1.36s/it]
 14%|█▍        | 8719/61904 [4:25:35<20:24:55,  1.38s/it]
 14%|█▍        | 8720/61904 [4:25:37<20:34:59,  1.39s/it]
                                                         
{'loss': 2.8825, 'learning_rate': 1.861921431349669e-07, 'epoch': 2.25}

 14%|█▍        | 8720/61904 [4:25:37<20:34:59,  1.39s/it]
 14%|█▍        | 8721/61904 [4:25:38<20:24:26,  1.38s/it]
 14%|█▍        | 8722/61904 [4:25:39<19:59:58,  1.35s/it]
 14%|█▍        | 8723/61904 [4:25:40<19:38:48,  1.33s/it]
 14%|█▍        | 8724/61904 [4:25:42<19:50:33,  1.34s/it]
 14%|█▍        | 8725/61904 [4:25:43<20:03:31,  1.36s/it]
 14%|█▍        | 8726/61904 [4:25:45<20:05:01,  1.36s/it]
 14%|█▍        | 8727/61904 [4:25:46<20:23:49,  1.38s/it]
 14%|█▍        | 8728/61904 [4:25:47<20:05:15,  1.36s/it]
 14%|█▍        | 8729/61904 [4:25:49<19:28:48,  1.32s/it]
 14%|█▍        | 8730/61904 [4:25:50<19:05:32,  1.29s/it]
 14%|█▍        | 8731/61904 [4:25:51<19:03:17,  1.29s/it]
 14%|█▍        | 8732/61904 [4:25:52<19:17:43,  1.31s/it]
 14%|█▍        | 8733/61904 [4:25:54<19:25:24,  1.32s/it]
 14%|█▍        | 8734/61904 [4:25:55<19:17:52,  1.31s/it]
 14%|█▍        | 8735/61904 [4:25:57<20:11:49,  1.37s/it]
 14%|█▍        | 8736/61904 [4:25:58<20:08:31,  1.36s/it]
 14%|█▍        | 8737/61904 [4:25:59<19:57:34,  1.35s/it]
 14%|█▍        | 8738/61904 [4:26:01<20:00:42,  1.36s/it]
 14%|█▍        | 8739/61904 [4:26:02<19:28:38,  1.32s/it]
 14%|█▍        | 8740/61904 [4:26:03<19:58:46,  1.35s/it]
                                                         
{'loss': 2.8311, 'learning_rate': 1.861597303254246e-07, 'epoch': 2.26}

 14%|█▍        | 8740/61904 [4:26:03<19:58:46,  1.35s/it]
 14%|█▍        | 8741/61904 [4:26:05<19:50:05,  1.34s/it]
 14%|█▍        | 8742/61904 [4:26:06<20:14:26,  1.37s/it]
 14%|█▍        | 8743/61904 [4:26:07<19:58:04,  1.35s/it]
 14%|█▍        | 8744/61904 [4:26:09<20:07:32,  1.36s/it]
 14%|█▍        | 8745/61904 [4:26:10<19:40:48,  1.33s/it]
 14%|█▍        | 8746/61904 [4:26:11<19:40:04,  1.33s/it]
 14%|█▍        | 8747/61904 [4:26:13<19:46:32,  1.34s/it]
 14%|█▍        | 8748/61904 [4:26:14<19:30:02,  1.32s/it]
 14%|█▍        | 8749/61904 [4:26:16<20:39:43,  1.40s/it]
 14%|█▍        | 8750/61904 [4:26:17<20:35:55,  1.40s/it]
 14%|█▍        | 8751/61904 [4:26:18<20:20:23,  1.38s/it]
 14%|█▍        | 8752/61904 [4:26:20<20:23:38,  1.38s/it]
 14%|█▍        | 8753/61904 [4:26:21<21:12:01,  1.44s/it]
 14%|█▍        | 8754/61904 [4:26:23<21:50:40,  1.48s/it]
 14%|█▍        | 8755/61904 [4:26:24<20:58:56,  1.42s/it]
 14%|█▍        | 8756/61904 [4:26:25<20:13:44,  1.37s/it]
 14%|█▍        | 8757/61904 [4:26:27<20:58:39,  1.42s/it]
 14%|█▍        | 8758/61904 [4:26:28<20:08:31,  1.36s/it]
 14%|█▍        | 8759/61904 [4:26:30<20:22:43,  1.38s/it]
 14%|█▍        | 8760/61904 [4:26:31<20:27:50,  1.39s/it]
                                                         
{'loss': 2.8857, 'learning_rate': 1.8612731751588226e-07, 'epoch': 2.26}

 14%|█▍        | 8760/61904 [4:26:31<20:27:50,  1.39s/it]
 14%|█▍        | 8761/61904 [4:26:32<20:12:01,  1.37s/it]
 14%|█▍        | 8762/61904 [4:26:34<19:59:02,  1.35s/it]
 14%|█▍        | 8763/61904 [4:26:35<20:08:47,  1.36s/it]
 14%|█▍        | 8764/61904 [4:26:36<19:43:39,  1.34s/it]
 14%|█▍        | 8765/61904 [4:26:38<19:35:52,  1.33s/it]
 14%|█▍        | 8766/61904 [4:26:39<19:41:15,  1.33s/it]
 14%|█▍        | 8767/61904 [4:26:40<19:44:53,  1.34s/it]
 14%|█▍        | 8768/61904 [4:26:42<19:51:59,  1.35s/it]
 14%|█▍        | 8769/61904 [4:26:43<20:37:51,  1.40s/it]
 14%|█▍        | 8770/61904 [4:26:44<20:19:04,  1.38s/it]
 14%|█▍        | 8771/61904 [4:26:46<20:04:04,  1.36s/it]
 14%|█▍        | 8772/61904 [4:26:47<19:46:26,  1.34s/it]
 14%|█▍        | 8773/61904 [4:26:48<19:53:49,  1.35s/it]
 14%|█▍        | 8774/61904 [4:26:50<21:07:30,  1.43s/it]
 14%|█▍        | 8775/61904 [4:26:51<21:00:39,  1.42s/it]
 14%|█▍        | 8776/61904 [4:26:53<21:14:02,  1.44s/it]
 14%|█▍        | 8777/61904 [4:26:54<20:47:29,  1.41s/it]
 14%|█▍        | 8778/61904 [4:26:56<20:15:05,  1.37s/it]
 14%|█▍        | 8779/61904 [4:26:57<19:43:37,  1.34s/it]
 14%|█▍        | 8780/61904 [4:26:58<20:08:32,  1.36s/it]
                                                         
{'loss': 2.8278, 'learning_rate': 1.8609490470633992e-07, 'epoch': 2.27}

 14%|█▍        | 8780/61904 [4:26:58<20:08:32,  1.36s/it]
 14%|█▍        | 8781/61904 [4:27:00<19:59:52,  1.36s/it]
 14%|█▍        | 8782/61904 [4:27:01<20:02:11,  1.36s/it]
 14%|█▍        | 8783/61904 [4:27:02<19:54:28,  1.35s/it]
 14%|█▍        | 8784/61904 [4:27:04<19:58:35,  1.35s/it]
 14%|█▍        | 8785/61904 [4:27:05<19:46:01,  1.34s/it]
 14%|█▍        | 8786/61904 [4:27:06<20:28:34,  1.39s/it]
 14%|█▍        | 8787/61904 [4:27:08<20:14:30,  1.37s/it]
 14%|█▍        | 8788/61904 [4:27:09<20:13:52,  1.37s/it]
 14%|█▍        | 8789/61904 [4:27:11<20:27:29,  1.39s/it]
 14%|█▍        | 8790/61904 [4:27:12<19:50:34,  1.34s/it]
 14%|█▍        | 8791/61904 [4:27:13<19:54:26,  1.35s/it]
 14%|█▍        | 8792/61904 [4:27:15<20:11:51,  1.37s/it]
 14%|█▍        | 8793/61904 [4:27:16<19:43:44,  1.34s/it]
 14%|█▍        | 8794/61904 [4:27:17<20:33:35,  1.39s/it]
 14%|█▍        | 8795/61904 [4:27:19<20:30:30,  1.39s/it]
 14%|█▍        | 8796/61904 [4:27:20<20:20:38,  1.38s/it]
 14%|█▍        | 8797/61904 [4:27:22<20:29:16,  1.39s/it]
 14%|█▍        | 8798/61904 [4:27:23<20:30:22,  1.39s/it]
 14%|█▍        | 8799/61904 [4:27:24<20:54:53,  1.42s/it]
 14%|█▍        | 8800/61904 [4:27:26<21:11:56,  1.44s/it]
                                                         
{'loss': 2.8549, 'learning_rate': 1.860624918967976e-07, 'epoch': 2.27}

 14%|█▍        | 8800/61904 [4:27:26<21:11:56,  1.44s/it]
 14%|█▍        | 8801/61904 [4:27:27<20:36:18,  1.40s/it]
 14%|█▍        | 8802/61904 [4:27:29<21:08:52,  1.43s/it]
 14%|█▍        | 8803/61904 [4:27:30<20:10:30,  1.37s/it]
 14%|█▍        | 8804/61904 [4:27:31<19:50:13,  1.34s/it]
 14%|█▍        | 8805/61904 [4:27:33<20:18:03,  1.38s/it]
 14%|█▍        | 8806/61904 [4:27:34<19:56:55,  1.35s/it]
 14%|█▍        | 8807/61904 [4:27:35<20:28:15,  1.39s/it]
 14%|█▍        | 8808/61904 [4:27:37<20:11:56,  1.37s/it]
 14%|█▍        | 8809/61904 [4:27:38<20:31:34,  1.39s/it]
 14%|█▍        | 8810/61904 [4:27:39<20:08:21,  1.37s/it]
 14%|█▍        | 8811/61904 [4:27:41<20:48:27,  1.41s/it]
 14%|█▍        | 8812/61904 [4:27:42<20:11:58,  1.37s/it]
 14%|█▍        | 8813/61904 [4:27:44<19:53:52,  1.35s/it]
 14%|█▍        | 8814/61904 [4:27:45<20:18:46,  1.38s/it]
 14%|█▍        | 8815/61904 [4:27:46<20:10:45,  1.37s/it]
 14%|█▍        | 8816/61904 [4:27:48<20:12:21,  1.37s/it]
 14%|█▍        | 8817/61904 [4:27:49<19:36:16,  1.33s/it]
 14%|█▍        | 8818/61904 [4:27:50<20:14:54,  1.37s/it]
 14%|█▍        | 8819/61904 [4:27:52<20:26:28,  1.39s/it]
 14%|█▍        | 8820/61904 [4:27:53<19:59:38,  1.36s/it]
                                                         
{'loss': 2.8433, 'learning_rate': 1.8603007908725527e-07, 'epoch': 2.28}

 14%|█▍        | 8820/61904 [4:27:53<19:59:38,  1.36s/it]
 14%|█▍        | 8821/61904 [4:27:55<21:22:28,  1.45s/it]
 14%|█▍        | 8822/61904 [4:27:56<20:38:39,  1.40s/it]
 14%|█▍        | 8823/61904 [4:27:57<20:18:29,  1.38s/it]
 14%|█▍        | 8824/61904 [4:27:59<20:12:33,  1.37s/it]
 14%|█▍        | 8825/61904 [4:28:00<20:31:52,  1.39s/it]
 14%|█▍        | 8826/61904 [4:28:02<20:08:29,  1.37s/it]
 14%|█▍        | 8827/61904 [4:28:03<20:36:00,  1.40s/it]
 14%|█▍        | 8828/61904 [4:28:04<19:48:12,  1.34s/it]
 14%|█▍        | 8829/61904 [4:28:06<20:07:57,  1.37s/it]
 14%|█▍        | 8830/61904 [4:28:07<20:29:17,  1.39s/it]
 14%|█▍        | 8831/61904 [4:28:09<20:39:45,  1.40s/it]
 14%|█▍        | 8832/61904 [4:28:10<20:27:36,  1.39s/it]
 14%|█▍        | 8833/61904 [4:28:11<20:17:21,  1.38s/it]
 14%|█▍        | 8834/61904 [4:28:13<20:12:24,  1.37s/it]
 14%|█▍        | 8835/61904 [4:28:14<20:04:34,  1.36s/it]
 14%|█▍        | 8836/61904 [4:28:15<19:56:24,  1.35s/it]
 14%|█▍        | 8837/61904 [4:28:17<20:14:54,  1.37s/it]
 14%|█▍        | 8838/61904 [4:28:18<19:31:03,  1.32s/it]
 14%|█▍        | 8839/61904 [4:28:19<20:14:36,  1.37s/it]
 14%|█▍        | 8840/61904 [4:28:21<20:11:30,  1.37s/it]
                                                         
{'loss': 2.8928, 'learning_rate': 1.8599766627771294e-07, 'epoch': 2.28}

 14%|█▍        | 8840/61904 [4:28:21<20:11:30,  1.37s/it]
 14%|█▍        | 8841/61904 [4:28:22<20:03:43,  1.36s/it]
 14%|█▍        | 8842/61904 [4:28:23<19:46:39,  1.34s/it]
 14%|█▍        | 8843/61904 [4:28:25<20:33:16,  1.39s/it]
 14%|█▍        | 8844/61904 [4:28:26<20:31:51,  1.39s/it]
 14%|█▍        | 8845/61904 [4:28:28<20:49:34,  1.41s/it]
 14%|█▍        | 8846/61904 [4:28:29<20:37:29,  1.40s/it]
 14%|█▍        | 8847/61904 [4:28:30<20:07:52,  1.37s/it]
 14%|█▍        | 8848/61904 [4:28:32<19:43:46,  1.34s/it]
 14%|█▍        | 8849/61904 [4:28:33<19:52:20,  1.35s/it]
 14%|█▍        | 8850/61904 [4:28:34<20:04:20,  1.36s/it]
 14%|█▍        | 8851/61904 [4:28:36<20:08:12,  1.37s/it]
 14%|█▍        | 8852/61904 [4:28:37<19:41:13,  1.34s/it]
 14%|█▍        | 8853/61904 [4:28:38<20:00:25,  1.36s/it]
 14%|█▍        | 8854/61904 [4:28:40<19:37:49,  1.33s/it]
 14%|█▍        | 8855/61904 [4:28:41<19:56:09,  1.35s/it]
 14%|█▍        | 8856/61904 [4:28:42<19:36:49,  1.33s/it]
 14%|█▍        | 8857/61904 [4:28:44<19:54:07,  1.35s/it]
 14%|█▍        | 8858/61904 [4:28:45<19:44:57,  1.34s/it]
 14%|█▍        | 8859/61904 [4:28:47<19:48:27,  1.34s/it]
 14%|█▍        | 8860/61904 [4:28:48<19:39:39,  1.33s/it]
                                                         
{'loss': 2.909, 'learning_rate': 1.8596525346817062e-07, 'epoch': 2.29}

 14%|█▍        | 8860/61904 [4:28:48<19:39:39,  1.33s/it]
 14%|█▍        | 8861/61904 [4:28:49<19:28:56,  1.32s/it]
 14%|█▍        | 8862/61904 [4:28:51<19:50:22,  1.35s/it]
 14%|█▍        | 8863/61904 [4:28:52<19:36:11,  1.33s/it]
 14%|█▍        | 8864/61904 [4:28:53<20:48:18,  1.41s/it]
 14%|█▍        | 8865/61904 [4:28:55<20:42:14,  1.41s/it]
 14%|█▍        | 8866/61904 [4:28:56<20:06:12,  1.36s/it]
 14%|█▍        | 8867/61904 [4:28:57<19:47:05,  1.34s/it]
 14%|█▍        | 8868/61904 [4:28:59<20:22:55,  1.38s/it]
 14%|█▍        | 8869/61904 [4:29:00<20:02:43,  1.36s/it]
 14%|█▍        | 8870/61904 [4:29:01<19:27:47,  1.32s/it]
 14%|█▍        | 8871/61904 [4:29:03<19:39:27,  1.33s/it]
 14%|█▍        | 8872/61904 [4:29:04<20:07:56,  1.37s/it]
 14%|█▍        | 8873/61904 [4:29:06<20:11:49,  1.37s/it]
 14%|█▍        | 8874/61904 [4:29:07<20:35:13,  1.40s/it]
 14%|█▍        | 8875/61904 [4:29:08<20:00:43,  1.36s/it]
 14%|█▍        | 8876/61904 [4:29:10<21:19:40,  1.45s/it]
 14%|█▍        | 8877/61904 [4:29:11<20:38:21,  1.40s/it]
 14%|█▍        | 8878/61904 [4:29:13<20:32:46,  1.39s/it]
 14%|█▍        | 8879/61904 [4:29:14<19:32:08,  1.33s/it]
 14%|█▍        | 8880/61904 [4:29:15<19:49:54,  1.35s/it]
                                                         
{'loss': 2.8203, 'learning_rate': 1.8593284065862829e-07, 'epoch': 2.29}

 14%|█▍        | 8880/61904 [4:29:15<19:49:54,  1.35s/it]
 14%|█▍        | 8881/61904 [4:29:17<20:10:52,  1.37s/it]
 14%|█▍        | 8882/61904 [4:29:18<20:24:15,  1.39s/it]
 14%|█▍        | 8883/61904 [4:29:19<20:34:42,  1.40s/it]
 14%|█▍        | 8884/61904 [4:29:21<21:11:59,  1.44s/it]
 14%|█▍        | 8885/61904 [4:29:22<20:56:38,  1.42s/it]
 14%|█▍        | 8886/61904 [4:29:24<21:20:45,  1.45s/it]
 14%|█▍        | 8887/61904 [4:29:25<21:16:53,  1.45s/it]
 14%|█▍        | 8888/61904 [4:29:27<21:38:57,  1.47s/it]
 14%|█▍        | 8889/61904 [4:29:28<20:50:39,  1.42s/it]
 14%|█▍        | 8890/61904 [4:29:29<19:51:12,  1.35s/it]
 14%|█▍        | 8891/61904 [4:29:31<19:51:13,  1.35s/it]
 14%|█▍        | 8892/61904 [4:29:32<19:45:42,  1.34s/it]
 14%|█▍        | 8893/61904 [4:29:33<19:48:14,  1.34s/it]
 14%|█▍        | 8894/61904 [4:29:35<20:31:46,  1.39s/it]
 14%|█▍        | 8895/61904 [4:29:36<20:22:14,  1.38s/it]
 14%|█▍        | 8896/61904 [4:29:38<20:20:52,  1.38s/it]
 14%|█▍        | 8897/61904 [4:29:39<20:07:59,  1.37s/it]
 14%|█▍        | 8898/61904 [4:29:40<19:50:01,  1.35s/it]
 14%|█▍        | 8899/61904 [4:29:42<19:36:54,  1.33s/it]
 14%|█▍        | 8900/61904 [4:29:43<19:37:05,  1.33s/it]
                                                         
{'loss': 2.8176, 'learning_rate': 1.8590042784908595e-07, 'epoch': 2.3}

 14%|█▍        | 8900/61904 [4:29:43<19:37:05,  1.33s/it]
 14%|█▍        | 8901/61904 [4:29:44<19:02:40,  1.29s/it]
 14%|█▍        | 8902/61904 [4:29:45<19:22:20,  1.32s/it]
 14%|█▍        | 8903/61904 [4:29:47<19:39:25,  1.34s/it]
 14%|█▍        | 8904/61904 [4:29:48<19:56:55,  1.36s/it]
 14%|█▍        | 8905/61904 [4:29:50<20:01:25,  1.36s/it]
 14%|█▍        | 8906/61904 [4:29:51<19:42:49,  1.34s/it]
 14%|█▍        | 8907/61904 [4:29:52<19:20:00,  1.31s/it]
 14%|█▍        | 8908/61904 [4:29:53<18:49:24,  1.28s/it]
 14%|█▍        | 8909/61904 [4:29:55<19:18:41,  1.31s/it]
 14%|█▍        | 8910/61904 [4:29:56<19:04:28,  1.30s/it]
 14%|█▍        | 8911/61904 [4:29:57<19:12:37,  1.31s/it]
 14%|█▍        | 8912/61904 [4:29:59<19:24:18,  1.32s/it]
 14%|█▍        | 8913/61904 [4:30:00<20:02:00,  1.36s/it]
 14%|█▍        | 8914/61904 [4:30:01<19:45:22,  1.34s/it]
 14%|█▍        | 8915/61904 [4:30:03<19:37:51,  1.33s/it]
 14%|█▍        | 8916/61904 [4:30:04<19:35:43,  1.33s/it]
 14%|█▍        | 8917/61904 [4:30:06<20:15:56,  1.38s/it]
 14%|█▍        | 8918/61904 [4:30:07<20:11:06,  1.37s/it]
 14%|█▍        | 8919/61904 [4:30:08<19:45:28,  1.34s/it]
 14%|█▍        | 8920/61904 [4:30:09<19:20:16,  1.31s/it]
                                                         
{'loss': 2.8396, 'learning_rate': 1.858680150395436e-07, 'epoch': 2.31}

 14%|█▍        | 8920/61904 [4:30:09<19:20:16,  1.31s/it]
 14%|█▍        | 8921/61904 [4:30:11<19:18:09,  1.31s/it]
 14%|█▍        | 8922/61904 [4:30:12<19:02:03,  1.29s/it]
 14%|█▍        | 8923/61904 [4:30:14<21:11:01,  1.44s/it]
 14%|█▍        | 8924/61904 [4:30:15<21:03:46,  1.43s/it]
 14%|█▍        | 8925/61904 [4:30:17<21:08:58,  1.44s/it]
 14%|█▍        | 8926/61904 [4:30:18<21:11:40,  1.44s/it]
 14%|█▍        | 8927/61904 [4:30:19<20:37:57,  1.40s/it]
 14%|█▍        | 8928/61904 [4:30:21<20:40:51,  1.41s/it]
 14%|█▍        | 8929/61904 [4:30:22<20:42:42,  1.41s/it]
 14%|█▍        | 8930/61904 [4:30:24<20:16:39,  1.38s/it]
 14%|█▍        | 8931/61904 [4:30:25<20:10:23,  1.37s/it]
 14%|█▍        | 8932/61904 [4:30:26<19:45:38,  1.34s/it]
 14%|█▍        | 8933/61904 [4:30:27<19:45:30,  1.34s/it]
 14%|█▍        | 8934/61904 [4:30:29<19:13:42,  1.31s/it]
 14%|█▍        | 8935/61904 [4:30:30<20:04:14,  1.36s/it]
 14%|█▍        | 8936/61904 [4:30:32<20:44:50,  1.41s/it]
 14%|█▍        | 8937/61904 [4:30:33<20:23:44,  1.39s/it]
 14%|█▍        | 8938/61904 [4:30:34<20:10:20,  1.37s/it]
 14%|█▍        | 8939/61904 [4:30:36<20:29:07,  1.39s/it]
 14%|█▍        | 8940/61904 [4:30:37<20:14:51,  1.38s/it]
                                                         
{'loss': 2.8307, 'learning_rate': 1.8583560223000127e-07, 'epoch': 2.31}

 14%|█▍        | 8940/61904 [4:30:37<20:14:51,  1.38s/it]
 14%|█▍        | 8941/61904 [4:30:39<20:12:31,  1.37s/it]
 14%|█▍        | 8942/61904 [4:30:40<20:16:15,  1.38s/it]
 14%|█▍        | 8943/61904 [4:30:41<20:11:48,  1.37s/it]
 14%|█▍        | 8944/61904 [4:30:43<19:52:15,  1.35s/it]
 14%|█▍        | 8945/61904 [4:30:44<20:05:50,  1.37s/it]
 14%|█▍        | 8946/61904 [4:30:45<19:47:47,  1.35s/it]
 14%|█▍        | 8947/61904 [4:30:47<19:49:13,  1.35s/it]
 14%|█▍        | 8948/61904 [4:30:48<19:58:10,  1.36s/it]
 14%|█▍        | 8949/61904 [4:30:50<20:41:35,  1.41s/it]
 14%|█▍        | 8950/61904 [4:30:51<20:10:39,  1.37s/it]
 14%|█▍        | 8951/61904 [4:30:52<20:01:07,  1.36s/it]
 14%|█▍        | 8952/61904 [4:30:54<19:59:39,  1.36s/it]
 14%|█▍        | 8953/61904 [4:30:55<20:01:22,  1.36s/it]
 14%|█▍        | 8954/61904 [4:30:56<19:44:44,  1.34s/it]
 14%|█▍        | 8955/61904 [4:30:58<19:49:36,  1.35s/it]
 14%|█▍        | 8956/61904 [4:30:59<19:40:59,  1.34s/it]
 14%|█▍        | 8957/61904 [4:31:00<19:09:38,  1.30s/it]
 14%|█▍        | 8958/61904 [4:31:01<18:47:52,  1.28s/it]
 14%|█▍        | 8959/61904 [4:31:03<19:18:30,  1.31s/it]
 14%|█▍        | 8960/61904 [4:31:04<19:40:16,  1.34s/it]
                                                         
{'loss': 2.895, 'learning_rate': 1.8580318942045896e-07, 'epoch': 2.32}

 14%|█▍        | 8960/61904 [4:31:04<19:40:16,  1.34s/it]
 14%|█▍        | 8961/61904 [4:31:06<20:00:51,  1.36s/it]
 14%|█▍        | 8962/61904 [4:31:07<19:46:45,  1.34s/it]
 14%|█▍        | 8963/61904 [4:31:08<19:24:08,  1.32s/it]
 14%|█▍        | 8964/61904 [4:31:09<19:28:50,  1.32s/it]
 14%|█▍        | 8965/61904 [4:31:11<19:06:35,  1.30s/it]
 14%|█▍        | 8966/61904 [4:31:12<19:38:29,  1.34s/it]
 14%|█▍        | 8967/61904 [4:31:13<19:32:50,  1.33s/it]
 14%|█▍        | 8968/61904 [4:31:15<20:17:00,  1.38s/it]
 14%|█▍        | 8969/61904 [4:31:16<19:27:20,  1.32s/it]
 14%|█▍        | 8970/61904 [4:31:17<19:26:24,  1.32s/it]
 14%|█▍        | 8971/61904 [4:31:19<19:10:14,  1.30s/it]
 14%|█▍        | 8972/61904 [4:31:20<19:03:53,  1.30s/it]
 14%|█▍        | 8973/61904 [4:31:21<18:49:56,  1.28s/it]
 14%|█▍        | 8974/61904 [4:31:23<19:30:32,  1.33s/it]
 14%|█▍        | 8975/61904 [4:31:24<19:29:56,  1.33s/it]
 14%|█▍        | 8976/61904 [4:31:25<20:06:44,  1.37s/it]
 15%|█▍        | 8977/61904 [4:31:27<21:27:51,  1.46s/it]
 15%|█▍        | 8978/61904 [4:31:29<21:24:19,  1.46s/it]
 15%|█▍        | 8979/61904 [4:31:30<21:11:22,  1.44s/it]
 15%|█▍        | 8980/61904 [4:31:31<20:53:06,  1.42s/it]
                                                         
{'loss': 2.8683, 'learning_rate': 1.8577077661091662e-07, 'epoch': 2.32}

 15%|█▍        | 8980/61904 [4:31:31<20:53:06,  1.42s/it]
 15%|█▍        | 8981/61904 [4:31:33<20:41:51,  1.41s/it]
 15%|█▍        | 8982/61904 [4:31:34<20:17:30,  1.38s/it]
 15%|█▍        | 8983/61904 [4:31:35<20:33:21,  1.40s/it]
 15%|█▍        | 8984/61904 [4:31:37<20:13:25,  1.38s/it]
 15%|█▍        | 8985/61904 [4:31:38<19:49:21,  1.35s/it]
 15%|█▍        | 8986/61904 [4:31:39<19:42:01,  1.34s/it]
 15%|█▍        | 8987/61904 [4:31:41<19:30:38,  1.33s/it]
 15%|█▍        | 8988/61904 [4:31:42<19:35:28,  1.33s/it]
 15%|█▍        | 8989/61904 [4:31:43<19:22:55,  1.32s/it]
 15%|█▍        | 8990/61904 [4:31:45<19:37:14,  1.33s/it]
 15%|█▍        | 8991/61904 [4:31:46<19:32:56,  1.33s/it]
 15%|█▍        | 8992/61904 [4:31:47<19:55:37,  1.36s/it]
 15%|█▍        | 8993/61904 [4:31:49<19:45:24,  1.34s/it]
 15%|█▍        | 8994/61904 [4:31:50<20:07:33,  1.37s/it]
 15%|█▍        | 8995/61904 [4:31:52<20:08:53,  1.37s/it]
 15%|█▍        | 8996/61904 [4:31:53<20:15:18,  1.38s/it]
 15%|█▍        | 8997/61904 [4:31:54<20:13:59,  1.38s/it]
 15%|█▍        | 8998/61904 [4:31:56<20:46:33,  1.41s/it]
 15%|█▍        | 8999/61904 [4:31:57<20:27:49,  1.39s/it]
 15%|█▍        | 9000/61904 [4:31:59<20:47:36,  1.41s/it]
                                                         
{'loss': 2.8272, 'learning_rate': 1.8573836380137428e-07, 'epoch': 2.33}

 15%|█▍        | 9000/61904 [4:31:59<20:47:36,  1.41s/it]
 15%|█▍        | 9001/61904 [4:32:00<20:41:03,  1.41s/it]
 15%|█▍        | 9002/61904 [4:32:01<20:13:47,  1.38s/it]
 15%|█▍        | 9003/61904 [4:32:03<20:28:07,  1.39s/it]
 15%|█▍        | 9004/61904 [4:32:04<20:07:21,  1.37s/it]
 15%|█▍        | 9005/61904 [4:32:05<20:06:39,  1.37s/it]
 15%|█▍        | 9006/61904 [4:32:07<19:38:32,  1.34s/it]
 15%|█▍        | 9007/61904 [4:32:08<19:28:42,  1.33s/it]
 15%|█▍        | 9008/61904 [4:32:09<19:59:59,  1.36s/it]
 15%|█▍        | 9009/61904 [4:32:11<19:59:40,  1.36s/it]
 15%|█▍        | 9010/61904 [4:32:12<20:13:02,  1.38s/it]
 15%|█▍        | 9011/61904 [4:32:14<20:30:36,  1.40s/it]
 15%|█▍        | 9012/61904 [4:32:15<20:04:03,  1.37s/it]
 15%|█▍        | 9013/61904 [4:32:16<20:02:49,  1.36s/it]
 15%|█▍        | 9014/61904 [4:32:18<19:34:00,  1.33s/it]
 15%|█▍        | 9015/61904 [4:32:19<20:10:24,  1.37s/it]
 15%|█▍        | 9016/61904 [4:32:20<19:47:21,  1.35s/it]
 15%|█▍        | 9017/61904 [4:32:22<19:40:14,  1.34s/it]
 15%|█▍        | 9018/61904 [4:32:23<19:57:33,  1.36s/it]
 15%|█▍        | 9019/61904 [4:32:24<20:29:06,  1.39s/it]
 15%|█▍        | 9020/61904 [4:32:26<20:35:22,  1.40s/it]
                                                         
{'loss': 2.8701, 'learning_rate': 1.8570595099183197e-07, 'epoch': 2.33}

 15%|█▍        | 9020/61904 [4:32:26<20:35:22,  1.40s/it]
 15%|█▍        | 9021/61904 [4:32:27<20:08:38,  1.37s/it]
 15%|█▍        | 9022/61904 [4:32:28<19:45:20,  1.34s/it]
 15%|█▍        | 9023/61904 [4:32:30<19:58:17,  1.36s/it]
 15%|█▍        | 9024/61904 [4:32:31<19:16:34,  1.31s/it]
 15%|█▍        | 9025/61904 [4:32:33<20:17:19,  1.38s/it]
 15%|█▍        | 9026/61904 [4:32:34<20:30:19,  1.40s/it]
 15%|█▍        | 9027/61904 [4:32:36<21:00:36,  1.43s/it]
 15%|█▍        | 9028/61904 [4:32:37<21:20:55,  1.45s/it]
 15%|█▍        | 9029/61904 [4:32:38<20:19:53,  1.38s/it]
 15%|█▍        | 9030/61904 [4:32:40<20:13:44,  1.38s/it]
 15%|█▍        | 9031/61904 [4:32:41<20:00:54,  1.36s/it]
 15%|█▍        | 9032/61904 [4:32:42<19:57:33,  1.36s/it]
 15%|█▍        | 9033/61904 [4:32:44<20:13:04,  1.38s/it]
 15%|█▍        | 9034/61904 [4:32:45<20:30:53,  1.40s/it]
 15%|█▍        | 9035/61904 [4:32:47<20:32:08,  1.40s/it]
 15%|█▍        | 9036/61904 [4:32:48<20:41:09,  1.41s/it]
 15%|█▍        | 9037/61904 [4:32:49<20:37:17,  1.40s/it]
 15%|█▍        | 9038/61904 [4:32:51<20:27:50,  1.39s/it]
 15%|█▍        | 9039/61904 [4:32:52<19:57:07,  1.36s/it]
 15%|█▍        | 9040/61904 [4:32:53<20:05:15,  1.37s/it]
                                                         
{'loss': 2.9526, 'learning_rate': 1.8567353818228963e-07, 'epoch': 2.34}

 15%|█▍        | 9040/61904 [4:32:53<20:05:15,  1.37s/it]
 15%|█▍        | 9041/61904 [4:32:55<20:06:44,  1.37s/it]
 15%|█▍        | 9042/61904 [4:32:56<19:59:35,  1.36s/it]
 15%|█▍        | 9043/61904 [4:32:58<19:51:40,  1.35s/it]
 15%|█▍        | 9044/61904 [4:32:59<20:03:29,  1.37s/it]
 15%|█▍        | 9045/61904 [4:33:00<19:53:09,  1.35s/it]
 15%|█▍        | 9046/61904 [4:33:02<19:41:24,  1.34s/it]
 15%|█▍        | 9047/61904 [4:33:03<19:34:33,  1.33s/it]
 15%|█▍        | 9048/61904 [4:33:04<20:13:13,  1.38s/it]
 15%|█▍        | 9049/61904 [4:33:06<21:20:50,  1.45s/it]
 15%|█▍        | 9050/61904 [4:33:07<20:54:30,  1.42s/it]
 15%|█▍        | 9051/61904 [4:33:09<20:19:13,  1.38s/it]
 15%|█▍        | 9052/61904 [4:33:10<19:55:18,  1.36s/it]
 15%|█▍        | 9053/61904 [4:33:11<20:18:54,  1.38s/it]
 15%|█▍        | 9054/61904 [4:33:13<20:02:04,  1.36s/it]
 15%|█▍        | 9055/61904 [4:33:14<19:56:47,  1.36s/it]
 15%|█▍        | 9056/61904 [4:33:15<20:11:00,  1.37s/it]
 15%|█▍        | 9057/61904 [4:33:17<20:34:54,  1.40s/it]
 15%|█▍        | 9058/61904 [4:33:18<20:29:54,  1.40s/it]
 15%|█▍        | 9059/61904 [4:33:20<20:34:51,  1.40s/it]
 15%|█▍        | 9060/61904 [4:33:21<20:16:11,  1.38s/it]
                                                         
{'loss': 2.8748, 'learning_rate': 1.856411253727473e-07, 'epoch': 2.34}

 15%|█▍        | 9060/61904 [4:33:21<20:16:11,  1.38s/it]
 15%|█▍        | 9061/61904 [4:33:22<19:39:32,  1.34s/it]
 15%|█▍        | 9062/61904 [4:33:24<19:29:55,  1.33s/it]
 15%|█▍        | 9063/61904 [4:33:25<19:26:09,  1.32s/it]
 15%|█▍        | 9064/61904 [4:33:26<19:42:17,  1.34s/it]
 15%|█▍        | 9065/61904 [4:33:28<19:59:01,  1.36s/it]
 15%|█▍        | 9066/61904 [4:33:29<19:59:21,  1.36s/it]
 15%|█▍        | 9067/61904 [4:33:30<19:59:51,  1.36s/it]
 15%|█▍        | 9068/61904 [4:33:32<19:29:47,  1.33s/it]
 15%|█▍        | 9069/61904 [4:33:33<19:44:51,  1.35s/it]
 15%|█▍        | 9070/61904 [4:33:34<20:06:34,  1.37s/it]
 15%|█▍        | 9071/61904 [4:33:36<20:38:46,  1.41s/it]
 15%|█▍        | 9072/61904 [4:33:37<19:52:09,  1.35s/it]
 15%|█▍        | 9073/61904 [4:33:39<19:39:54,  1.34s/it]
 15%|█▍        | 9074/61904 [4:33:40<19:42:33,  1.34s/it]
 15%|█▍        | 9075/61904 [4:33:41<19:46:46,  1.35s/it]
 15%|█▍        | 9076/61904 [4:33:43<19:33:29,  1.33s/it]
 15%|█▍        | 9077/61904 [4:33:44<19:29:40,  1.33s/it]
 15%|█▍        | 9078/61904 [4:33:45<20:00:38,  1.36s/it]
 15%|█▍        | 9079/61904 [4:33:47<19:55:14,  1.36s/it]
 15%|█▍        | 9080/61904 [4:33:48<20:07:01,  1.37s/it]
                                                         
{'loss': 2.8858, 'learning_rate': 1.8560871256320498e-07, 'epoch': 2.35}

 15%|█▍        | 9080/61904 [4:33:48<20:07:01,  1.37s/it]
 15%|█▍        | 9081/61904 [4:33:50<20:38:05,  1.41s/it]
 15%|█▍        | 9082/61904 [4:33:51<21:07:48,  1.44s/it]
 15%|█▍        | 9083/61904 [4:33:52<20:37:42,  1.41s/it]
 15%|█▍        | 9084/61904 [4:33:54<20:42:36,  1.41s/it]
 15%|█▍        | 9085/61904 [4:33:55<20:55:36,  1.43s/it]
 15%|█▍        | 9086/61904 [4:33:57<20:27:35,  1.39s/it]
 15%|█▍        | 9087/61904 [4:33:58<19:35:39,  1.34s/it]
 15%|█▍        | 9088/61904 [4:33:59<20:00:16,  1.36s/it]
 15%|█▍        | 9089/61904 [4:34:01<19:51:33,  1.35s/it]
 15%|█▍        | 9090/61904 [4:34:02<19:34:30,  1.33s/it]
 15%|█▍        | 9091/61904 [4:34:03<19:23:38,  1.32s/it]
 15%|█▍        | 9092/61904 [4:34:04<19:22:58,  1.32s/it]
 15%|█▍        | 9093/61904 [4:34:06<19:23:06,  1.32s/it]
 15%|█▍        | 9094/61904 [4:34:07<20:05:59,  1.37s/it]
 15%|█▍        | 9095/61904 [4:34:09<19:57:41,  1.36s/it]
 15%|█▍        | 9096/61904 [4:34:10<19:31:30,  1.33s/it]
 15%|█▍        | 9097/61904 [4:34:11<20:23:05,  1.39s/it]
 15%|█▍        | 9098/61904 [4:34:13<20:15:21,  1.38s/it]
 15%|█▍        | 9099/61904 [4:34:14<19:50:36,  1.35s/it]
 15%|█▍        | 9100/61904 [4:34:15<19:38:52,  1.34s/it]
                                                         
{'loss': 2.9003, 'learning_rate': 1.8557629975366262e-07, 'epoch': 2.35}

 15%|█▍        | 9100/61904 [4:34:15<19:38:52,  1.34s/it]
 15%|█▍        | 9101/61904 [4:34:17<19:49:06,  1.35s/it]
 15%|█▍        | 9102/61904 [4:34:18<19:10:57,  1.31s/it]
 15%|█▍        | 9103/61904 [4:34:19<19:50:53,  1.35s/it]
 15%|█▍        | 9104/61904 [4:34:21<20:08:11,  1.37s/it]
 15%|█▍        | 9105/61904 [4:34:22<19:52:30,  1.36s/it]
 15%|█▍        | 9106/61904 [4:34:23<20:01:33,  1.37s/it]
 15%|█▍        | 9107/61904 [4:34:25<19:45:21,  1.35s/it]
 15%|█▍        | 9108/61904 [4:34:26<19:31:45,  1.33s/it]
 15%|█▍        | 9109/61904 [4:34:27<19:14:36,  1.31s/it]
 15%|█▍        | 9110/61904 [4:34:29<20:16:45,  1.38s/it]
 15%|█▍        | 9111/61904 [4:34:30<20:27:39,  1.40s/it]
 15%|█▍        | 9112/61904 [4:34:32<21:00:04,  1.43s/it]
 15%|█▍        | 9113/61904 [4:34:33<20:49:52,  1.42s/it]
 15%|█▍        | 9114/61904 [4:34:35<20:26:13,  1.39s/it]
 15%|█▍        | 9115/61904 [4:34:36<20:39:58,  1.41s/it]
 15%|█▍        | 9116/61904 [4:34:38<21:14:31,  1.45s/it]
 15%|█▍        | 9117/61904 [4:34:39<21:01:26,  1.43s/it]
 15%|█▍        | 9118/61904 [4:34:40<21:15:01,  1.45s/it]
 15%|█▍        | 9119/61904 [4:34:42<20:20:57,  1.39s/it]
 15%|█▍        | 9120/61904 [4:34:43<20:06:32,  1.37s/it]
                                                         
{'loss': 2.8281, 'learning_rate': 1.855438869441203e-07, 'epoch': 2.36}

 15%|█▍        | 9120/61904 [4:34:43<20:06:32,  1.37s/it]
 15%|█▍        | 9121/61904 [4:34:45<20:41:01,  1.41s/it]
 15%|█▍        | 9122/61904 [4:34:46<20:27:30,  1.40s/it]
 15%|█▍        | 9123/61904 [4:34:47<20:14:43,  1.38s/it]
 15%|█▍        | 9124/61904 [4:34:49<20:59:07,  1.43s/it]
 15%|█▍        | 9125/61904 [4:34:50<20:26:11,  1.39s/it]
 15%|█▍        | 9126/61904 [4:34:51<19:55:30,  1.36s/it]
 15%|█▍        | 9127/61904 [4:34:53<19:48:41,  1.35s/it]
 15%|█▍        | 9128/61904 [4:34:54<20:06:31,  1.37s/it]
 15%|█▍        | 9129/61904 [4:34:55<19:37:52,  1.34s/it]
 15%|█▍        | 9130/61904 [4:34:57<19:42:33,  1.34s/it]
 15%|█▍        | 9131/61904 [4:34:58<19:42:27,  1.34s/it]
 15%|█▍        | 9132/61904 [4:34:59<19:27:54,  1.33s/it]
 15%|█▍        | 9133/61904 [4:35:01<20:07:03,  1.37s/it]
 15%|█▍        | 9134/61904 [4:35:02<20:34:04,  1.40s/it]
 15%|█▍        | 9135/61904 [4:35:04<20:27:12,  1.40s/it]
 15%|█▍        | 9136/61904 [4:35:05<20:33:03,  1.40s/it]
 15%|█▍        | 9137/61904 [4:35:06<20:08:18,  1.37s/it]
 15%|█▍        | 9138/61904 [4:35:08<19:47:02,  1.35s/it]
 15%|█▍        | 9139/61904 [4:35:09<19:49:32,  1.35s/it]
 15%|█▍        | 9140/61904 [4:35:11<20:29:52,  1.40s/it]
                                                         
{'loss': 2.81, 'learning_rate': 1.8551147413457797e-07, 'epoch': 2.36}

 15%|█▍        | 9140/61904 [4:35:11<20:29:52,  1.40s/it]
 15%|█▍        | 9141/61904 [4:35:12<20:38:02,  1.41s/it]
 15%|█▍        | 9142/61904 [4:35:13<20:54:04,  1.43s/it]
 15%|█▍        | 9143/61904 [4:35:15<20:33:41,  1.40s/it]
 15%|█▍        | 9144/61904 [4:35:16<20:06:26,  1.37s/it]
 15%|█▍        | 9145/61904 [4:35:17<19:56:33,  1.36s/it]
 15%|█▍        | 9146/61904 [4:35:19<19:50:50,  1.35s/it]
 15%|█▍        | 9147/61904 [4:35:20<20:41:43,  1.41s/it]
 15%|█▍        | 9148/61904 [4:35:22<20:13:23,  1.38s/it]
 15%|█▍        | 9149/61904 [4:35:23<19:53:10,  1.36s/it]
 15%|█▍        | 9150/61904 [4:35:24<19:48:45,  1.35s/it]
 15%|█▍        | 9151/61904 [4:35:26<20:27:37,  1.40s/it]
 15%|█▍        | 9152/61904 [4:35:27<20:17:00,  1.38s/it]
 15%|█▍        | 9153/61904 [4:35:29<20:11:07,  1.38s/it]
 15%|█▍        | 9154/61904 [4:35:30<19:40:36,  1.34s/it]
 15%|█▍        | 9155/61904 [4:35:31<19:34:16,  1.34s/it]
 15%|█▍        | 9156/61904 [4:35:32<19:39:01,  1.34s/it]
 15%|█▍        | 9157/61904 [4:35:34<19:29:20,  1.33s/it]
 15%|█▍        | 9158/61904 [4:35:35<19:30:00,  1.33s/it]
 15%|█▍        | 9159/61904 [4:35:36<19:47:58,  1.35s/it]
 15%|█▍        | 9160/61904 [4:35:38<21:13:12,  1.45s/it]
                                                         
{'loss': 2.8814, 'learning_rate': 1.8547906132503563e-07, 'epoch': 2.37}

 15%|█▍        | 9160/61904 [4:35:38<21:13:12,  1.45s/it]
 15%|█▍        | 9161/61904 [4:35:39<20:39:14,  1.41s/it]
 15%|█▍        | 9162/61904 [4:35:41<20:37:54,  1.41s/it]
 15%|█▍        | 9163/61904 [4:35:42<20:22:06,  1.39s/it]
 15%|█▍        | 9164/61904 [4:35:44<19:56:57,  1.36s/it]
 15%|█▍        | 9165/61904 [4:35:45<19:53:51,  1.36s/it]
 15%|█▍        | 9166/61904 [4:35:46<19:54:28,  1.36s/it]
 15%|█▍        | 9167/61904 [4:35:48<19:34:03,  1.34s/it]
 15%|█▍        | 9168/61904 [4:35:49<19:47:48,  1.35s/it]
 15%|█▍        | 9169/61904 [4:35:50<19:40:51,  1.34s/it]
 15%|█▍        | 9170/61904 [4:35:52<20:03:46,  1.37s/it]
 15%|█▍        | 9171/61904 [4:35:53<19:36:49,  1.34s/it]
 15%|█▍        | 9172/61904 [4:35:54<19:51:35,  1.36s/it]
 15%|█▍        | 9173/61904 [4:35:56<20:22:12,  1.39s/it]
 15%|█▍        | 9174/61904 [4:35:57<19:37:43,  1.34s/it]
 15%|█▍        | 9175/61904 [4:35:58<19:43:00,  1.35s/it]
 15%|█▍        | 9176/61904 [4:36:00<19:49:13,  1.35s/it]
 15%|█▍        | 9177/61904 [4:36:01<20:08:07,  1.37s/it]
 15%|█▍        | 9178/61904 [4:36:03<21:05:06,  1.44s/it]
 15%|█▍        | 9179/61904 [4:36:04<21:15:20,  1.45s/it]
 15%|█▍        | 9180/61904 [4:36:06<21:03:02,  1.44s/it]
                                                         
{'loss': 2.9104, 'learning_rate': 1.8544664851549332e-07, 'epoch': 2.37}

 15%|█▍        | 9180/61904 [4:36:06<21:03:02,  1.44s/it]
 15%|█▍        | 9181/61904 [4:36:07<21:23:36,  1.46s/it]
 15%|█▍        | 9182/61904 [4:36:09<20:58:53,  1.43s/it]
 15%|█▍        | 9183/61904 [4:36:10<20:29:36,  1.40s/it]
 15%|█▍        | 9184/61904 [4:36:11<20:07:08,  1.37s/it]
 15%|█▍        | 9185/61904 [4:36:13<20:11:14,  1.38s/it]
 15%|█▍        | 9186/61904 [4:36:14<20:09:35,  1.38s/it]
 15%|█▍        | 9187/61904 [4:36:15<19:53:26,  1.36s/it]
 15%|█▍        | 9188/61904 [4:36:17<19:48:37,  1.35s/it]
 15%|█▍        | 9189/61904 [4:36:18<19:41:45,  1.35s/it]
 15%|█▍        | 9190/61904 [4:36:19<19:41:51,  1.35s/it]
 15%|█▍        | 9191/61904 [4:36:21<19:51:02,  1.36s/it]
 15%|█▍        | 9192/61904 [4:36:22<20:23:25,  1.39s/it]
 15%|█▍        | 9193/61904 [4:36:23<19:48:45,  1.35s/it]
 15%|█▍        | 9194/61904 [4:36:25<19:57:45,  1.36s/it]
 15%|█▍        | 9195/61904 [4:36:26<19:31:34,  1.33s/it]
 15%|█▍        | 9196/61904 [4:36:27<19:01:22,  1.30s/it]
 15%|█▍        | 9197/61904 [4:36:29<19:06:34,  1.31s/it]
 15%|█▍        | 9198/61904 [4:36:30<19:12:42,  1.31s/it]
 15%|█▍        | 9199/61904 [4:36:31<19:17:00,  1.32s/it]
 15%|█▍        | 9200/61904 [4:36:33<19:32:39,  1.34s/it]
                                                         
{'loss': 2.8546, 'learning_rate': 1.8541423570595098e-07, 'epoch': 2.38}

 15%|█▍        | 9200/61904 [4:36:33<19:32:39,  1.34s/it]
 15%|█▍        | 9201/61904 [4:36:34<19:43:16,  1.35s/it]
 15%|█▍        | 9202/61904 [4:36:35<20:07:39,  1.37s/it]
 15%|█▍        | 9203/61904 [4:36:37<19:53:53,  1.36s/it]
 15%|█▍        | 9204/61904 [4:36:38<19:45:54,  1.35s/it]
 15%|█▍        | 9205/61904 [4:36:39<20:04:47,  1.37s/it]
 15%|█▍        | 9206/61904 [4:36:41<20:02:50,  1.37s/it]
 15%|█▍        | 9207/61904 [4:36:42<20:07:18,  1.37s/it]
 15%|█▍        | 9208/61904 [4:36:44<19:53:19,  1.36s/it]
 15%|█▍        | 9209/61904 [4:36:45<20:26:33,  1.40s/it]
 15%|█▍        | 9210/61904 [4:36:46<19:55:04,  1.36s/it]
 15%|█▍        | 9211/61904 [4:36:48<20:26:16,  1.40s/it]
 15%|█▍        | 9212/61904 [4:36:49<19:58:35,  1.36s/it]
 15%|█▍        | 9213/61904 [4:36:51<20:21:29,  1.39s/it]
 15%|█▍        | 9214/61904 [4:36:52<19:58:07,  1.36s/it]
 15%|█▍        | 9215/61904 [4:36:53<20:21:53,  1.39s/it]
 15%|█▍        | 9216/61904 [4:36:55<19:46:46,  1.35s/it]
 15%|█▍        | 9217/61904 [4:36:56<19:53:53,  1.36s/it]
 15%|█▍        | 9218/61904 [4:36:57<19:24:22,  1.33s/it]
 15%|█▍        | 9219/61904 [4:36:58<19:15:58,  1.32s/it]
 15%|█▍        | 9220/61904 [4:37:00<19:46:48,  1.35s/it]
                                                         
{'loss': 2.8443, 'learning_rate': 1.8538182289640864e-07, 'epoch': 2.38}

 15%|█▍        | 9220/61904 [4:37:00<19:46:48,  1.35s/it]
 15%|█▍        | 9221/61904 [4:37:01<19:28:59,  1.33s/it]
 15%|█▍        | 9222/61904 [4:37:03<19:29:06,  1.33s/it]
 15%|█▍        | 9223/61904 [4:37:04<19:43:08,  1.35s/it]
 15%|█▍        | 9224/61904 [4:37:05<19:44:51,  1.35s/it]
 15%|█▍        | 9225/61904 [4:37:07<19:58:35,  1.37s/it]
 15%|█▍        | 9226/61904 [4:37:08<19:37:45,  1.34s/it]
 15%|█▍        | 9227/61904 [4:37:09<19:28:07,  1.33s/it]
 15%|█▍        | 9228/61904 [4:37:11<19:35:48,  1.34s/it]
 15%|█▍        | 9229/61904 [4:37:12<19:35:33,  1.34s/it]
 15%|█▍        | 9230/61904 [4:37:13<19:24:11,  1.33s/it]
 15%|█▍        | 9231/61904 [4:37:14<19:02:30,  1.30s/it]
 15%|█▍        | 9232/61904 [4:37:16<19:16:11,  1.32s/it]
 15%|█▍        | 9233/61904 [4:37:17<20:15:15,  1.38s/it]
 15%|█▍        | 9234/61904 [4:37:19<20:31:32,  1.40s/it]
 15%|█▍        | 9235/61904 [4:37:20<20:27:45,  1.40s/it]
 15%|█▍        | 9236/61904 [4:37:22<20:15:24,  1.38s/it]
 15%|█▍        | 9237/61904 [4:37:23<19:52:14,  1.36s/it]
 15%|█▍        | 9238/61904 [4:37:24<20:45:50,  1.42s/it]
 15%|█▍        | 9239/61904 [4:37:26<20:03:54,  1.37s/it]
 15%|█▍        | 9240/61904 [4:37:27<20:26:39,  1.40s/it]
                                                         
{'loss': 2.8323, 'learning_rate': 1.8534941008686633e-07, 'epoch': 2.39}

 15%|█▍        | 9240/61904 [4:37:27<20:26:39,  1.40s/it]
 15%|█▍        | 9241/61904 [4:37:29<20:35:30,  1.41s/it]
 15%|█▍        | 9242/61904 [4:37:30<20:11:19,  1.38s/it]
 15%|█▍        | 9243/61904 [4:37:31<19:58:12,  1.37s/it]
 15%|█▍        | 9244/61904 [4:37:33<19:34:08,  1.34s/it]
 15%|█▍        | 9245/61904 [4:37:34<19:48:17,  1.35s/it]
 15%|█▍        | 9246/61904 [4:37:35<20:12:55,  1.38s/it]
 15%|█▍        | 9247/61904 [4:37:37<19:43:41,  1.35s/it]
 15%|█▍        | 9248/61904 [4:37:38<19:33:37,  1.34s/it]
 15%|█▍        | 9249/61904 [4:37:39<20:06:33,  1.37s/it]
 15%|█▍        | 9250/61904 [4:37:41<19:51:48,  1.36s/it]
 15%|█▍        | 9251/61904 [4:37:42<19:41:36,  1.35s/it]
 15%|█▍        | 9252/61904 [4:37:43<20:00:22,  1.37s/it]
 15%|█▍        | 9253/61904 [4:37:45<19:58:42,  1.37s/it]
 15%|█▍        | 9254/61904 [4:37:46<19:37:55,  1.34s/it]
 15%|█▍        | 9255/61904 [4:37:47<19:44:49,  1.35s/it]
 15%|█▍        | 9256/61904 [4:37:49<19:54:04,  1.36s/it]
 15%|█▍        | 9257/61904 [4:37:50<20:16:10,  1.39s/it]
 15%|█▍        | 9258/61904 [4:37:52<20:00:32,  1.37s/it]
 15%|█▍        | 9259/61904 [4:37:53<19:32:25,  1.34s/it]
 15%|█▍        | 9260/61904 [4:37:54<19:22:16,  1.32s/it]
                                                         
{'loss': 2.8195, 'learning_rate': 1.85316997277324e-07, 'epoch': 2.39}

 15%|█▍        | 9260/61904 [4:37:54<19:22:16,  1.32s/it]
 15%|█▍        | 9261/61904 [4:37:56<20:06:51,  1.38s/it]
 15%|█▍        | 9262/61904 [4:37:57<19:33:09,  1.34s/it]
 15%|█▍        | 9263/61904 [4:37:58<19:09:51,  1.31s/it]
 15%|█▍        | 9264/61904 [4:38:00<19:42:29,  1.35s/it]
 15%|█▍        | 9265/61904 [4:38:01<19:19:50,  1.32s/it]
 15%|█▍        | 9266/61904 [4:38:02<19:43:57,  1.35s/it]
 15%|█▍        | 9267/61904 [4:38:04<20:20:03,  1.39s/it]
 15%|█▍        | 9268/61904 [4:38:05<20:02:26,  1.37s/it]
 15%|█▍        | 9269/61904 [4:38:06<20:06:41,  1.38s/it]
 15%|█▍        | 9270/61904 [4:38:08<20:11:05,  1.38s/it]
 15%|█▍        | 9271/61904 [4:38:09<19:47:25,  1.35s/it]
 15%|█▍        | 9272/61904 [4:38:11<20:11:31,  1.38s/it]
 15%|█▍        | 9273/61904 [4:38:12<20:19:25,  1.39s/it]
 15%|█▍        | 9274/61904 [4:38:13<20:19:10,  1.39s/it]
 15%|█▍        | 9275/61904 [4:38:15<20:11:52,  1.38s/it]
 15%|█▍        | 9276/61904 [4:38:16<20:08:03,  1.38s/it]
 15%|█▍        | 9277/61904 [4:38:18<20:22:03,  1.39s/it]
 15%|█▍        | 9278/61904 [4:38:19<21:03:11,  1.44s/it]
 15%|█▍        | 9279/61904 [4:38:20<20:31:46,  1.40s/it]
 15%|█▍        | 9280/61904 [4:38:22<20:43:52,  1.42s/it]
                                                         
{'loss': 2.7998, 'learning_rate': 1.8528458446778166e-07, 'epoch': 2.4}

 15%|█▍        | 9280/61904 [4:38:22<20:43:52,  1.42s/it]
 15%|█▍        | 9281/61904 [4:38:23<20:24:04,  1.40s/it]
 15%|█▍        | 9282/61904 [4:38:25<20:29:51,  1.40s/it]
 15%|█▍        | 9283/61904 [4:38:26<20:20:27,  1.39s/it]
 15%|█▍        | 9284/61904 [4:38:27<19:59:26,  1.37s/it]
 15%|█▍        | 9285/61904 [4:38:29<20:06:34,  1.38s/it]
 15%|█▌        | 9286/61904 [4:38:30<20:01:13,  1.37s/it]
 15%|█▌        | 9287/61904 [4:38:32<20:39:36,  1.41s/it]
 15%|█▌        | 9288/61904 [4:38:33<20:36:31,  1.41s/it]
 15%|█▌        | 9289/61904 [4:38:34<20:35:45,  1.41s/it]
 15%|█▌        | 9290/61904 [4:38:36<20:20:10,  1.39s/it]
 15%|█▌        | 9291/61904 [4:38:37<20:30:53,  1.40s/it]
 15%|█▌        | 9292/61904 [4:38:39<20:11:24,  1.38s/it]
 15%|█▌        | 9293/61904 [4:38:40<19:46:15,  1.35s/it]
 15%|█▌        | 9294/61904 [4:38:41<19:15:22,  1.32s/it]
 15%|█▌        | 9295/61904 [4:38:42<19:18:59,  1.32s/it]
 15%|█▌        | 9296/61904 [4:38:44<19:09:51,  1.31s/it]
 15%|█▌        | 9297/61904 [4:38:45<19:28:18,  1.33s/it]
 15%|█▌        | 9298/61904 [4:38:47<20:03:02,  1.37s/it]
 15%|█▌        | 9299/61904 [4:38:48<19:57:33,  1.37s/it]
 15%|█▌        | 9300/61904 [4:38:49<19:43:41,  1.35s/it]
                                                         
{'loss': 2.85, 'learning_rate': 1.8525217165823934e-07, 'epoch': 2.4}

 15%|█▌        | 9300/61904 [4:38:49<19:43:41,  1.35s/it]
 15%|█▌        | 9301/61904 [4:38:50<19:26:06,  1.33s/it]
 15%|█▌        | 9302/61904 [4:38:52<19:20:34,  1.32s/it]
 15%|█▌        | 9303/61904 [4:38:53<18:52:43,  1.29s/it]
 15%|█▌        | 9304/61904 [4:38:54<18:57:41,  1.30s/it]
 15%|█▌        | 9305/61904 [4:38:56<20:11:06,  1.38s/it]
 15%|█▌        | 9306/61904 [4:38:57<20:05:54,  1.38s/it]
 15%|█▌        | 9307/61904 [4:38:59<20:04:29,  1.37s/it]
 15%|█▌        | 9308/61904 [4:39:00<19:45:11,  1.35s/it]
 15%|█▌        | 9309/61904 [4:39:01<19:25:42,  1.33s/it]
 15%|█▌        | 9310/61904 [4:39:02<19:21:03,  1.32s/it]
 15%|█▌        | 9311/61904 [4:39:04<19:45:24,  1.35s/it]
 15%|█▌        | 9312/61904 [4:39:05<19:55:07,  1.36s/it]
 15%|█▌        | 9313/61904 [4:39:07<19:45:50,  1.35s/it]
 15%|█▌        | 9314/61904 [4:39:08<20:34:09,  1.41s/it]
 15%|█▌        | 9315/61904 [4:39:10<21:00:28,  1.44s/it]
 15%|█▌        | 9316/61904 [4:39:11<20:30:43,  1.40s/it]
 15%|█▌        | 9317/61904 [4:39:12<20:23:14,  1.40s/it]
 15%|█▌        | 9318/61904 [4:39:14<20:30:47,  1.40s/it]
 15%|█▌        | 9319/61904 [4:39:15<20:07:27,  1.38s/it]
 15%|█▌        | 9320/61904 [4:39:16<19:26:37,  1.33s/it]
                                                         
{'loss': 2.8015, 'learning_rate': 1.8521975884869698e-07, 'epoch': 2.41}

 15%|█▌        | 9320/61904 [4:39:16<19:26:37,  1.33s/it]
 15%|█▌        | 9321/61904 [4:39:18<19:17:45,  1.32s/it]
 15%|█▌        | 9322/61904 [4:39:19<19:28:48,  1.33s/it]
 15%|█▌        | 9323/61904 [4:39:20<19:12:25,  1.32s/it]
 15%|█▌        | 9324/61904 [4:39:22<20:18:21,  1.39s/it]
 15%|█▌        | 9325/61904 [4:39:23<20:22:53,  1.40s/it]
 15%|█▌        | 9326/61904 [4:39:24<19:41:33,  1.35s/it]
 15%|█▌        | 9327/61904 [4:39:26<19:43:46,  1.35s/it]
 15%|█▌        | 9328/61904 [4:39:27<19:34:59,  1.34s/it]
 15%|█▌        | 9329/61904 [4:39:28<19:21:51,  1.33s/it]
 15%|█▌        | 9330/61904 [4:39:30<20:26:21,  1.40s/it]
 15%|█▌        | 9331/61904 [4:39:32<20:58:33,  1.44s/it]
 15%|█▌        | 9332/61904 [4:39:33<20:25:12,  1.40s/it]
 15%|█▌        | 9333/61904 [4:39:34<21:27:08,  1.47s/it]
 15%|█▌        | 9334/61904 [4:39:36<20:16:20,  1.39s/it]
 15%|█▌        | 9335/61904 [4:39:37<20:37:45,  1.41s/it]
 15%|█▌        | 9336/61904 [4:39:39<20:29:33,  1.40s/it]
 15%|█▌        | 9337/61904 [4:39:40<19:54:30,  1.36s/it]
 15%|█▌        | 9338/61904 [4:39:41<19:45:44,  1.35s/it]
 15%|█▌        | 9339/61904 [4:39:42<19:21:51,  1.33s/it]
 15%|█▌        | 9340/61904 [4:39:44<19:08:31,  1.31s/it]
                                                         
{'loss': 2.8752, 'learning_rate': 1.8518734603915467e-07, 'epoch': 2.41}

 15%|█▌        | 9340/61904 [4:39:44<19:08:31,  1.31s/it]
 15%|█▌        | 9341/61904 [4:39:45<19:25:15,  1.33s/it]
 15%|█▌        | 9342/61904 [4:39:46<19:57:18,  1.37s/it]
 15%|█▌        | 9343/61904 [4:39:48<19:49:21,  1.36s/it]
 15%|█▌        | 9344/61904 [4:39:49<20:09:06,  1.38s/it]
 15%|█▌        | 9345/61904 [4:39:51<19:36:39,  1.34s/it]
 15%|█▌        | 9346/61904 [4:39:52<19:33:01,  1.34s/it]
 15%|█▌        | 9347/61904 [4:39:53<19:49:46,  1.36s/it]
 15%|█▌        | 9348/61904 [4:39:55<19:52:00,  1.36s/it]
 15%|█▌        | 9349/61904 [4:39:56<19:36:35,  1.34s/it]
 15%|█▌        | 9350/61904 [4:39:57<20:23:16,  1.40s/it]
 15%|█▌        | 9351/61904 [4:39:59<20:38:23,  1.41s/it]
 15%|█▌        | 9352/61904 [4:40:00<20:15:09,  1.39s/it]
 15%|█▌        | 9353/61904 [4:40:02<20:30:53,  1.41s/it]
 15%|█▌        | 9354/61904 [4:40:03<20:20:03,  1.39s/it]
 15%|█▌        | 9355/61904 [4:40:04<19:56:54,  1.37s/it]
 15%|█▌        | 9356/61904 [4:40:06<20:52:11,  1.43s/it]
 15%|█▌        | 9357/61904 [4:40:07<20:56:34,  1.43s/it]
 15%|█▌        | 9358/61904 [4:40:09<20:30:00,  1.40s/it]
 15%|█▌        | 9359/61904 [4:40:10<19:55:32,  1.37s/it]
 15%|█▌        | 9360/61904 [4:40:11<19:50:05,  1.36s/it]
                                                         
{'loss': 2.7702, 'learning_rate': 1.8515493322961233e-07, 'epoch': 2.42}

 15%|█▌        | 9360/61904 [4:40:11<19:50:05,  1.36s/it]
 15%|█▌        | 9361/61904 [4:40:13<19:39:03,  1.35s/it]
 15%|█▌        | 9362/61904 [4:40:14<20:08:03,  1.38s/it]
 15%|█▌        | 9363/61904 [4:40:15<19:39:00,  1.35s/it]
 15%|█▌        | 9364/61904 [4:40:17<20:08:14,  1.38s/it]
 15%|█▌        | 9365/61904 [4:40:18<19:49:39,  1.36s/it]
 15%|█▌        | 9366/61904 [4:40:19<19:52:31,  1.36s/it]
 15%|█▌        | 9367/61904 [4:40:21<20:00:47,  1.37s/it]
 15%|█▌        | 9368/61904 [4:40:22<19:54:48,  1.36s/it]
 15%|█▌        | 9369/61904 [4:40:24<19:37:34,  1.34s/it]
 15%|█▌        | 9370/61904 [4:40:25<20:13:23,  1.39s/it]
 15%|█▌        | 9371/61904 [4:40:26<19:27:07,  1.33s/it]
 15%|█▌        | 9372/61904 [4:40:27<19:05:03,  1.31s/it]
 15%|█▌        | 9373/61904 [4:40:29<19:27:55,  1.33s/it]
 15%|█▌        | 9374/61904 [4:40:30<19:49:02,  1.36s/it]
 15%|█▌        | 9375/61904 [4:40:32<20:40:08,  1.42s/it]
 15%|█▌        | 9376/61904 [4:40:33<20:17:57,  1.39s/it]
 15%|█▌        | 9377/61904 [4:40:35<21:05:42,  1.45s/it]
 15%|█▌        | 9378/61904 [4:40:36<20:58:44,  1.44s/it]
 15%|█▌        | 9379/61904 [4:40:38<20:34:19,  1.41s/it]
 15%|█▌        | 9380/61904 [4:40:39<20:18:03,  1.39s/it]
                                                         
{'loss': 2.9099, 'learning_rate': 1.8512252042007e-07, 'epoch': 2.42}

 15%|█▌        | 9380/61904 [4:40:39<20:18:03,  1.39s/it]
 15%|█▌        | 9381/61904 [4:40:40<20:45:04,  1.42s/it]
 15%|█▌        | 9382/61904 [4:40:42<20:12:45,  1.39s/it]
 15%|█▌        | 9383/61904 [4:40:43<19:17:49,  1.32s/it]
 15%|█▌        | 9384/61904 [4:40:44<19:57:09,  1.37s/it]
 15%|█▌        | 9385/61904 [4:40:46<19:55:31,  1.37s/it]
 15%|█▌        | 9386/61904 [4:40:47<20:43:54,  1.42s/it]
 15%|█▌        | 9387/61904 [4:40:49<21:09:02,  1.45s/it]
 15%|█▌        | 9388/61904 [4:40:50<20:34:31,  1.41s/it]
 15%|█▌        | 9389/61904 [4:40:51<20:10:45,  1.38s/it]
 15%|█▌        | 9390/61904 [4:40:53<19:42:35,  1.35s/it]
 15%|█▌        | 9391/61904 [4:40:54<19:19:43,  1.33s/it]
 15%|█▌        | 9392/61904 [4:40:55<19:22:52,  1.33s/it]
 15%|█▌        | 9393/61904 [4:40:57<19:29:27,  1.34s/it]
 15%|█▌        | 9394/61904 [4:40:58<20:19:14,  1.39s/it]
 15%|█▌        | 9395/61904 [4:40:59<19:56:06,  1.37s/it]
 15%|█▌        | 9396/61904 [4:41:01<20:17:09,  1.39s/it]
 15%|█▌        | 9397/61904 [4:41:02<20:08:57,  1.38s/it]
 15%|█▌        | 9398/61904 [4:41:04<20:39:55,  1.42s/it]
 15%|█▌        | 9399/61904 [4:41:05<20:10:51,  1.38s/it]
 15%|█▌        | 9400/61904 [4:41:06<20:17:05,  1.39s/it]
                                                         
{'loss': 2.8563, 'learning_rate': 1.8509010761052768e-07, 'epoch': 2.43}

 15%|█▌        | 9400/61904 [4:41:06<20:17:05,  1.39s/it]
 15%|█▌        | 9401/61904 [4:41:08<19:56:52,  1.37s/it]
 15%|█▌        | 9402/61904 [4:41:09<19:37:51,  1.35s/it]
 15%|█▌        | 9403/61904 [4:41:10<19:23:56,  1.33s/it]
 15%|█▌        | 9404/61904 [4:41:12<19:03:41,  1.31s/it]
 15%|█▌        | 9405/61904 [4:41:13<18:59:23,  1.30s/it]
 15%|█▌        | 9406/61904 [4:41:14<19:08:28,  1.31s/it]
 15%|█▌        | 9407/61904 [4:41:16<19:03:10,  1.31s/it]
 15%|█▌        | 9408/61904 [4:41:17<18:46:33,  1.29s/it]
 15%|█▌        | 9409/61904 [4:41:18<19:26:43,  1.33s/it]
 15%|█▌        | 9410/61904 [4:41:20<19:59:43,  1.37s/it]
 15%|█▌        | 9411/61904 [4:41:21<20:20:24,  1.39s/it]
 15%|█▌        | 9412/61904 [4:41:23<20:26:54,  1.40s/it]
 15%|█▌        | 9413/61904 [4:41:24<19:58:56,  1.37s/it]
 15%|█▌        | 9414/61904 [4:41:25<19:31:02,  1.34s/it]
 15%|█▌        | 9415/61904 [4:41:26<19:25:24,  1.33s/it]
 15%|█▌        | 9416/61904 [4:41:28<19:02:25,  1.31s/it]
 15%|█▌        | 9417/61904 [4:41:29<19:32:24,  1.34s/it]
 15%|█▌        | 9418/61904 [4:41:30<19:35:22,  1.34s/it]
 15%|█▌        | 9419/61904 [4:41:32<20:36:02,  1.41s/it]
 15%|█▌        | 9420/61904 [4:41:33<20:34:12,  1.41s/it]
                                                         
{'loss': 2.7581, 'learning_rate': 1.8505769480098534e-07, 'epoch': 2.43}

 15%|█▌        | 9420/61904 [4:41:33<20:34:12,  1.41s/it]
 15%|█▌        | 9421/61904 [4:41:35<20:44:43,  1.42s/it]
 15%|█▌        | 9422/61904 [4:41:36<20:53:11,  1.43s/it]
 15%|█▌        | 9423/61904 [4:41:38<20:10:28,  1.38s/it]
 15%|█▌        | 9424/61904 [4:41:39<20:00:07,  1.37s/it]
 15%|█▌        | 9425/61904 [4:41:40<20:37:10,  1.41s/it]
 15%|█▌        | 9426/61904 [4:41:42<20:24:43,  1.40s/it]
 15%|█▌        | 9427/61904 [4:41:43<21:03:09,  1.44s/it]
 15%|█▌        | 9428/61904 [4:41:45<21:01:30,  1.44s/it]
 15%|█▌        | 9429/61904 [4:41:46<21:01:48,  1.44s/it]
 15%|█▌        | 9430/61904 [4:41:47<20:05:23,  1.38s/it]
 15%|█▌        | 9431/61904 [4:41:49<19:54:42,  1.37s/it]
 15%|█▌        | 9432/61904 [4:41:50<19:45:49,  1.36s/it]
 15%|█▌        | 9433/61904 [4:41:52<20:41:41,  1.42s/it]
 15%|█▌        | 9434/61904 [4:41:53<20:25:31,  1.40s/it]
 15%|█▌        | 9435/61904 [4:41:54<19:59:32,  1.37s/it]
 15%|█▌        | 9436/61904 [4:41:56<20:20:47,  1.40s/it]
 15%|█▌        | 9437/61904 [4:41:57<19:55:51,  1.37s/it]
 15%|█▌        | 9438/61904 [4:41:59<20:12:41,  1.39s/it]
 15%|█▌        | 9439/61904 [4:42:00<19:51:41,  1.36s/it]
 15%|█▌        | 9440/61904 [4:42:01<20:09:53,  1.38s/it]
                                                         
{'loss': 2.9199, 'learning_rate': 1.85025281991443e-07, 'epoch': 2.44}

 15%|█▌        | 9440/61904 [4:42:01<20:09:53,  1.38s/it]
 15%|█▌        | 9441/61904 [4:42:03<20:33:27,  1.41s/it]
 15%|█▌        | 9442/61904 [4:42:04<20:14:39,  1.39s/it]
 15%|█▌        | 9443/61904 [4:42:06<20:18:45,  1.39s/it]
 15%|█▌        | 9444/61904 [4:42:07<19:45:47,  1.36s/it]
 15%|█▌        | 9445/61904 [4:42:08<19:42:13,  1.35s/it]
 15%|█▌        | 9446/61904 [4:42:10<20:00:41,  1.37s/it]
 15%|█▌        | 9447/61904 [4:42:11<20:11:21,  1.39s/it]
 15%|█▌        | 9448/61904 [4:42:12<19:21:32,  1.33s/it]
 15%|█▌        | 9449/61904 [4:42:14<20:34:12,  1.41s/it]
 15%|█▌        | 9450/61904 [4:42:15<20:25:33,  1.40s/it]
 15%|█▌        | 9451/61904 [4:42:17<20:43:35,  1.42s/it]
 15%|█▌        | 9452/61904 [4:42:18<20:35:15,  1.41s/it]
 15%|█▌        | 9453/61904 [4:42:19<20:40:05,  1.42s/it]
 15%|█▌        | 9454/61904 [4:42:21<19:42:57,  1.35s/it]
 15%|█▌        | 9455/61904 [4:42:22<19:04:52,  1.31s/it]
 15%|█▌        | 9456/61904 [4:42:23<18:33:41,  1.27s/it]
 15%|█▌        | 9457/61904 [4:42:24<19:19:54,  1.33s/it]
 15%|█▌        | 9458/61904 [4:42:26<19:41:31,  1.35s/it]
 15%|█▌        | 9459/61904 [4:42:27<19:34:57,  1.34s/it]
 15%|█▌        | 9460/61904 [4:42:29<19:46:10,  1.36s/it]
                                                         
{'loss': 2.8404, 'learning_rate': 1.849928691819007e-07, 'epoch': 2.44}

 15%|█▌        | 9460/61904 [4:42:29<19:46:10,  1.36s/it]
 15%|█▌        | 9461/61904 [4:42:30<20:04:16,  1.38s/it]
 15%|█▌        | 9462/61904 [4:42:31<19:42:01,  1.35s/it]
 15%|█▌        | 9463/61904 [4:42:33<19:48:38,  1.36s/it]
 15%|█▌        | 9464/61904 [4:42:34<19:19:55,  1.33s/it]
 15%|█▌        | 9465/61904 [4:42:35<19:25:26,  1.33s/it]
 15%|█▌        | 9466/61904 [4:42:37<19:06:20,  1.31s/it]
 15%|█▌        | 9467/61904 [4:42:38<18:54:49,  1.30s/it]
 15%|█▌        | 9468/61904 [4:42:39<19:21:42,  1.33s/it]
 15%|█▌        | 9469/61904 [4:42:41<19:35:21,  1.34s/it]
 15%|█▌        | 9470/61904 [4:42:42<19:09:30,  1.32s/it]
 15%|█▌        | 9471/61904 [4:42:43<19:38:24,  1.35s/it]
 15%|█▌        | 9472/61904 [4:42:45<19:21:11,  1.33s/it]
 15%|█▌        | 9473/61904 [4:42:46<19:46:54,  1.36s/it]
 15%|█▌        | 9474/61904 [4:42:47<19:51:16,  1.36s/it]
 15%|█▌        | 9475/61904 [4:42:49<19:52:11,  1.36s/it]
 15%|█▌        | 9476/61904 [4:42:50<20:51:53,  1.43s/it]
 15%|█▌        | 9477/61904 [4:42:52<20:06:46,  1.38s/it]
 15%|█▌        | 9478/61904 [4:42:53<20:09:13,  1.38s/it]
 15%|█▌        | 9479/61904 [4:42:54<20:27:22,  1.40s/it]
 15%|█▌        | 9480/61904 [4:42:56<20:04:50,  1.38s/it]
                                                         
{'loss': 2.8321, 'learning_rate': 1.8496045637235835e-07, 'epoch': 2.45}

 15%|█▌        | 9480/61904 [4:42:56<20:04:50,  1.38s/it]
 15%|█▌        | 9481/61904 [4:42:57<20:18:21,  1.39s/it]
 15%|█▌        | 9482/61904 [4:42:59<20:26:57,  1.40s/it]
 15%|█▌        | 9483/61904 [4:43:00<19:45:40,  1.36s/it]
 15%|█▌        | 9484/61904 [4:43:01<19:57:48,  1.37s/it]
 15%|█▌        | 9485/61904 [4:43:03<19:28:47,  1.34s/it]
 15%|█▌        | 9486/61904 [4:43:04<19:00:48,  1.31s/it]
 15%|█▌        | 9487/61904 [4:43:05<19:20:34,  1.33s/it]
 15%|█▌        | 9488/61904 [4:43:07<20:05:16,  1.38s/it]
 15%|█▌        | 9489/61904 [4:43:08<19:43:00,  1.35s/it]
 15%|█▌        | 9490/61904 [4:43:09<19:06:03,  1.31s/it]
 15%|█▌        | 9491/61904 [4:43:10<18:36:38,  1.28s/it]
 15%|█▌        | 9492/61904 [4:43:12<18:37:10,  1.28s/it]
 15%|█▌        | 9493/61904 [4:43:13<18:34:58,  1.28s/it]
 15%|█▌        | 9494/61904 [4:43:14<18:39:05,  1.28s/it]
 15%|█▌        | 9495/61904 [4:43:16<19:06:05,  1.31s/it]
 15%|█▌        | 9496/61904 [4:43:17<19:13:10,  1.32s/it]
 15%|█▌        | 9497/61904 [4:43:18<19:43:21,  1.35s/it]
 15%|█▌        | 9498/61904 [4:43:20<19:44:17,  1.36s/it]
 15%|█▌        | 9499/61904 [4:43:21<19:46:34,  1.36s/it]
 15%|█▌        | 9500/61904 [4:43:22<19:31:30,  1.34s/it]
                                                         
{'loss': 2.781, 'learning_rate': 1.8492804356281602e-07, 'epoch': 2.46}

 15%|█▌        | 9500/61904 [4:43:22<19:31:30,  1.34s/it]
 15%|█▌        | 9501/61904 [4:43:24<19:13:11,  1.32s/it]
 15%|█▌        | 9502/61904 [4:43:25<19:29:04,  1.34s/it]
 15%|█▌        | 9503/61904 [4:43:26<19:36:21,  1.35s/it]
 15%|█▌        | 9504/61904 [4:43:28<19:59:23,  1.37s/it]
 15%|█▌        | 9505/61904 [4:43:29<19:41:37,  1.35s/it]
 15%|█▌        | 9506/61904 [4:43:31<20:14:08,  1.39s/it]
 15%|█▌        | 9507/61904 [4:43:32<19:56:53,  1.37s/it]
 15%|█▌        | 9508/61904 [4:43:33<19:43:58,  1.36s/it]
 15%|█▌        | 9509/61904 [4:43:35<20:18:00,  1.39s/it]
 15%|█▌        | 9510/61904 [4:43:36<19:51:07,  1.36s/it]
 15%|█▌        | 9511/61904 [4:43:37<20:09:37,  1.39s/it]
 15%|█▌        | 9512/61904 [4:43:39<20:04:16,  1.38s/it]
 15%|█▌        | 9513/61904 [4:43:40<19:35:12,  1.35s/it]
 15%|█▌        | 9514/61904 [4:43:41<19:11:41,  1.32s/it]
 15%|█▌        | 9515/61904 [4:43:43<19:37:50,  1.35s/it]
 15%|█▌        | 9516/61904 [4:43:44<19:42:45,  1.35s/it]
 15%|█▌        | 9517/61904 [4:43:45<19:38:08,  1.35s/it]
 15%|█▌        | 9518/61904 [4:43:47<19:57:28,  1.37s/it]
 15%|█▌        | 9519/61904 [4:43:48<20:12:35,  1.39s/it]
 15%|█▌        | 9520/61904 [4:43:50<20:54:18,  1.44s/it]
                                                         
{'loss': 2.9004, 'learning_rate': 1.8489563075327368e-07, 'epoch': 2.46}

 15%|█▌        | 9520/61904 [4:43:50<20:54:18,  1.44s/it]
 15%|█▌        | 9521/61904 [4:43:51<20:35:39,  1.42s/it]
 15%|█▌        | 9522/61904 [4:43:53<20:47:02,  1.43s/it]
 15%|█▌        | 9523/61904 [4:43:54<20:48:36,  1.43s/it]
 15%|█▌        | 9524/61904 [4:43:55<20:01:08,  1.38s/it]
 15%|█▌        | 9525/61904 [4:43:57<20:05:59,  1.38s/it]
 15%|█▌        | 9526/61904 [4:43:58<21:29:20,  1.48s/it]
 15%|█▌        | 9527/61904 [4:44:00<21:47:47,  1.50s/it]
 15%|█▌        | 9528/61904 [4:44:02<21:41:08,  1.49s/it]
 15%|█▌        | 9529/61904 [4:44:03<21:38:56,  1.49s/it]
 15%|█▌        | 9530/61904 [4:44:04<20:44:24,  1.43s/it]
 15%|█▌        | 9531/61904 [4:44:06<20:27:50,  1.41s/it]
 15%|█▌        | 9532/61904 [4:44:07<21:10:16,  1.46s/it]
 15%|█▌        | 9533/61904 [4:44:09<21:00:34,  1.44s/it]
 15%|█▌        | 9534/61904 [4:44:10<20:08:48,  1.38s/it]
 15%|█▌        | 9535/61904 [4:44:11<19:48:47,  1.36s/it]
 15%|█▌        | 9536/61904 [4:44:13<19:57:18,  1.37s/it]
 15%|█▌        | 9537/61904 [4:44:14<19:39:37,  1.35s/it]
 15%|█▌        | 9538/61904 [4:44:15<19:49:03,  1.36s/it]
 15%|█▌        | 9539/61904 [4:44:17<19:32:32,  1.34s/it]
 15%|█▌        | 9540/61904 [4:44:18<20:02:44,  1.38s/it]
                                                         
{'loss': 2.8439, 'learning_rate': 1.8486321794373134e-07, 'epoch': 2.47}

 15%|█▌        | 9540/61904 [4:44:18<20:02:44,  1.38s/it]
 15%|█▌        | 9541/61904 [4:44:19<19:43:21,  1.36s/it]
 15%|█▌        | 9542/61904 [4:44:21<19:24:33,  1.33s/it]
 15%|█▌        | 9543/61904 [4:44:22<19:42:43,  1.36s/it]
 15%|█▌        | 9544/61904 [4:44:23<19:40:33,  1.35s/it]
 15%|█▌        | 9545/61904 [4:44:25<20:14:24,  1.39s/it]
 15%|█▌        | 9546/61904 [4:44:26<19:57:45,  1.37s/it]
 15%|█▌        | 9547/61904 [4:44:28<19:50:46,  1.36s/it]
 15%|█▌        | 9548/61904 [4:44:29<19:46:47,  1.36s/it]
 15%|█▌        | 9549/61904 [4:44:30<20:08:57,  1.39s/it]
 15%|█▌        | 9550/61904 [4:44:32<21:12:02,  1.46s/it]
 15%|█▌        | 9551/61904 [4:44:33<20:56:23,  1.44s/it]
 15%|█▌        | 9552/61904 [4:44:35<20:38:30,  1.42s/it]
 15%|█▌        | 9553/61904 [4:44:36<20:31:50,  1.41s/it]
 15%|█▌        | 9554/61904 [4:44:37<20:28:05,  1.41s/it]
 15%|█▌        | 9555/61904 [4:44:39<20:17:37,  1.40s/it]
 15%|█▌        | 9556/61904 [4:44:40<20:47:25,  1.43s/it]
 15%|█▌        | 9557/61904 [4:44:42<20:27:28,  1.41s/it]
 15%|█▌        | 9558/61904 [4:44:43<19:36:54,  1.35s/it]
 15%|█▌        | 9559/61904 [4:44:44<20:10:12,  1.39s/it]
 15%|█▌        | 9560/61904 [4:44:46<19:49:00,  1.36s/it]
                                                         
{'loss': 2.9077, 'learning_rate': 1.8483080513418903e-07, 'epoch': 2.47}

 15%|█▌        | 9560/61904 [4:44:46<19:49:00,  1.36s/it]
 15%|█▌        | 9561/61904 [4:44:47<20:09:07,  1.39s/it]
 15%|█▌        | 9562/61904 [4:44:48<19:51:46,  1.37s/it]
 15%|█▌        | 9563/61904 [4:44:50<20:13:24,  1.39s/it]
 15%|█▌        | 9564/61904 [4:44:51<19:44:04,  1.36s/it]
 15%|█▌        | 9565/61904 [4:44:52<19:17:56,  1.33s/it]
 15%|█▌        | 9566/61904 [4:44:54<19:35:13,  1.35s/it]
 15%|█▌        | 9567/61904 [4:44:55<19:25:00,  1.34s/it]
 15%|█▌        | 9568/61904 [4:44:57<20:07:29,  1.38s/it]
 15%|█▌        | 9569/61904 [4:44:58<19:45:57,  1.36s/it]
 15%|█▌        | 9570/61904 [4:44:59<19:55:35,  1.37s/it]
 15%|█▌        | 9571/61904 [4:45:01<19:55:59,  1.37s/it]
 15%|█▌        | 9572/61904 [4:45:02<19:38:09,  1.35s/it]
 15%|█▌        | 9573/61904 [4:45:03<19:21:03,  1.33s/it]
 15%|█▌        | 9574/61904 [4:45:05<19:35:48,  1.35s/it]
 15%|█▌        | 9575/61904 [4:45:06<19:55:31,  1.37s/it]
 15%|█▌        | 9576/61904 [4:45:07<19:50:26,  1.36s/it]
 15%|█▌        | 9577/61904 [4:45:09<21:04:43,  1.45s/it]
 15%|█▌        | 9578/61904 [4:45:11<20:57:35,  1.44s/it]
 15%|█▌        | 9579/61904 [4:45:12<21:03:00,  1.45s/it]
 15%|█▌        | 9580/61904 [4:45:13<20:54:27,  1.44s/it]
                                                         
{'loss': 2.8844, 'learning_rate': 1.847983923246467e-07, 'epoch': 2.48}

 15%|█▌        | 9580/61904 [4:45:13<20:54:27,  1.44s/it]
 15%|█▌        | 9581/61904 [4:45:15<20:28:33,  1.41s/it]
 15%|█▌        | 9582/61904 [4:45:16<20:18:39,  1.40s/it]
 15%|█▌        | 9583/61904 [4:45:17<19:37:10,  1.35s/it]
 15%|█▌        | 9584/61904 [4:45:19<19:55:34,  1.37s/it]
 15%|█▌        | 9585/61904 [4:45:20<19:31:50,  1.34s/it]
 15%|█▌        | 9586/61904 [4:45:21<19:41:48,  1.36s/it]
 15%|█▌        | 9587/61904 [4:45:23<19:33:59,  1.35s/it]
 15%|█▌        | 9588/61904 [4:45:24<20:29:12,  1.41s/it]
 15%|█▌        | 9589/61904 [4:45:26<20:16:08,  1.39s/it]
 15%|█▌        | 9590/61904 [4:45:27<19:56:15,  1.37s/it]
 15%|█▌        | 9591/61904 [4:45:28<19:53:32,  1.37s/it]
 15%|█▌        | 9592/61904 [4:45:30<20:45:02,  1.43s/it]
 15%|█▌        | 9593/61904 [4:45:31<20:26:49,  1.41s/it]
 15%|█▌        | 9594/61904 [4:45:33<20:27:00,  1.41s/it]
 15%|█▌        | 9595/61904 [4:45:34<19:55:36,  1.37s/it]
 16%|█▌        | 9596/61904 [4:45:35<19:45:04,  1.36s/it]
 16%|█▌        | 9597/61904 [4:45:37<19:58:15,  1.37s/it]
 16%|█▌        | 9598/61904 [4:45:38<19:36:59,  1.35s/it]
 16%|█▌        | 9599/61904 [4:45:39<19:32:58,  1.35s/it]
 16%|█▌        | 9600/61904 [4:45:41<19:14:35,  1.32s/it]
                                                         
{'loss': 2.8135, 'learning_rate': 1.8476597951510435e-07, 'epoch': 2.48}

 16%|█▌        | 9600/61904 [4:45:41<19:14:35,  1.32s/it]
 16%|█▌        | 9601/61904 [4:45:42<19:25:34,  1.34s/it]
 16%|█▌        | 9602/61904 [4:45:43<19:37:12,  1.35s/it]
 16%|█▌        | 9603/61904 [4:45:45<19:43:52,  1.36s/it]
 16%|█▌        | 9604/61904 [4:45:46<19:13:37,  1.32s/it]
 16%|█▌        | 9605/61904 [4:45:47<19:19:25,  1.33s/it]
 16%|█▌        | 9606/61904 [4:45:49<19:50:01,  1.37s/it]
 16%|█▌        | 9607/61904 [4:45:50<19:47:24,  1.36s/it]
 16%|█▌        | 9608/61904 [4:45:51<19:30:08,  1.34s/it]
 16%|█▌        | 9609/61904 [4:45:53<19:47:23,  1.36s/it]
 16%|█▌        | 9610/61904 [4:45:54<20:31:51,  1.41s/it]
 16%|█▌        | 9611/61904 [4:45:56<19:59:27,  1.38s/it]
 16%|█▌        | 9612/61904 [4:45:57<19:33:25,  1.35s/it]
 16%|█▌        | 9613/61904 [4:45:58<19:18:29,  1.33s/it]
 16%|█▌        | 9614/61904 [4:46:00<20:01:13,  1.38s/it]
 16%|█▌        | 9615/61904 [4:46:01<20:08:27,  1.39s/it]
 16%|█▌        | 9616/61904 [4:46:03<20:47:11,  1.43s/it]
 16%|█▌        | 9617/61904 [4:46:04<20:49:10,  1.43s/it]
 16%|█▌        | 9618/61904 [4:46:05<20:08:44,  1.39s/it]
 16%|█▌        | 9619/61904 [4:46:07<20:21:15,  1.40s/it]
 16%|█▌        | 9620/61904 [4:46:08<20:01:26,  1.38s/it]
                                                         
{'loss': 2.8818, 'learning_rate': 1.8473356670556204e-07, 'epoch': 2.49}

 16%|█▌        | 9620/61904 [4:46:08<20:01:26,  1.38s/it]
 16%|█▌        | 9621/61904 [4:46:10<20:03:21,  1.38s/it]
 16%|█▌        | 9622/61904 [4:46:11<20:57:36,  1.44s/it]
 16%|█▌        | 9623/61904 [4:46:13<20:55:35,  1.44s/it]
 16%|█▌        | 9624/61904 [4:46:14<20:20:00,  1.40s/it]
 16%|█▌        | 9625/61904 [4:46:15<20:17:07,  1.40s/it]
 16%|█▌        | 9626/61904 [4:46:17<20:07:32,  1.39s/it]
 16%|█▌        | 9627/61904 [4:46:18<19:28:09,  1.34s/it]
 16%|█▌        | 9628/61904 [4:46:19<19:48:14,  1.36s/it]
 16%|█▌        | 9629/61904 [4:46:21<19:53:48,  1.37s/it]
 16%|█▌        | 9630/61904 [4:46:22<19:38:33,  1.35s/it]
 16%|█▌        | 9631/61904 [4:46:24<20:26:24,  1.41s/it]
 16%|█▌        | 9632/61904 [4:46:25<20:11:08,  1.39s/it]
 16%|█▌        | 9633/61904 [4:46:26<20:04:05,  1.38s/it]
 16%|█▌        | 9634/61904 [4:46:28<20:21:33,  1.40s/it]
 16%|█▌        | 9635/61904 [4:46:29<20:41:02,  1.42s/it]
 16%|█▌        | 9636/61904 [4:46:30<20:10:17,  1.39s/it]
 16%|█▌        | 9637/61904 [4:46:32<19:31:12,  1.34s/it]
 16%|█▌        | 9638/61904 [4:46:33<19:39:52,  1.35s/it]
 16%|█▌        | 9639/61904 [4:46:35<20:10:14,  1.39s/it]
 16%|█▌        | 9640/61904 [4:46:36<21:21:36,  1.47s/it]
                                                         
{'loss': 2.8716, 'learning_rate': 1.847011538960197e-07, 'epoch': 2.49}

 16%|█▌        | 9640/61904 [4:46:36<21:21:36,  1.47s/it]
 16%|█▌        | 9641/61904 [4:46:37<20:03:27,  1.38s/it]
 16%|█▌        | 9642/61904 [4:46:39<19:45:13,  1.36s/it]
 16%|█▌        | 9643/61904 [4:46:40<19:25:05,  1.34s/it]
 16%|█▌        | 9644/61904 [4:46:41<19:22:42,  1.33s/it]
 16%|█▌        | 9645/61904 [4:46:43<19:28:28,  1.34s/it]
 16%|█▌        | 9646/61904 [4:46:44<19:35:18,  1.35s/it]
 16%|█▌        | 9647/61904 [4:46:45<19:34:27,  1.35s/it]
 16%|█▌        | 9648/61904 [4:46:47<19:26:37,  1.34s/it]
 16%|█▌        | 9649/61904 [4:46:48<19:38:46,  1.35s/it]
 16%|█▌        | 9650/61904 [4:46:49<19:49:04,  1.37s/it]
 16%|█▌        | 9651/61904 [4:46:51<19:56:51,  1.37s/it]
 16%|█▌        | 9652/61904 [4:46:52<19:08:58,  1.32s/it]
 16%|█▌        | 9653/61904 [4:46:54<19:40:49,  1.36s/it]
 16%|█▌        | 9654/61904 [4:46:55<19:46:39,  1.36s/it]
 16%|█▌        | 9655/61904 [4:46:56<19:40:59,  1.36s/it]
 16%|█▌        | 9656/61904 [4:46:58<20:00:47,  1.38s/it]
 16%|█▌        | 9657/61904 [4:46:59<19:56:19,  1.37s/it]
 16%|█▌        | 9658/61904 [4:47:00<19:39:31,  1.35s/it]
 16%|█▌        | 9659/61904 [4:47:02<19:32:47,  1.35s/it]
 16%|█▌        | 9660/61904 [4:47:03<19:49:19,  1.37s/it]
                                                         
{'loss': 2.8514, 'learning_rate': 1.8466874108647736e-07, 'epoch': 2.5}

 16%|█▌        | 9660/61904 [4:47:03<19:49:19,  1.37s/it]
 16%|█▌        | 9661/61904 [4:47:04<19:35:02,  1.35s/it]
 16%|█▌        | 9662/61904 [4:47:06<19:17:32,  1.33s/it]
 16%|█▌        | 9663/61904 [4:47:07<19:46:08,  1.36s/it]
 16%|█▌        | 9664/61904 [4:47:08<19:21:27,  1.33s/it]
 16%|█▌        | 9665/61904 [4:47:10<20:24:56,  1.41s/it]
 16%|█▌        | 9666/61904 [4:47:11<20:48:57,  1.43s/it]
 16%|█▌        | 9667/61904 [4:47:13<20:20:40,  1.40s/it]
 16%|█▌        | 9668/61904 [4:47:14<20:08:16,  1.39s/it]
 16%|█▌        | 9669/61904 [4:47:15<19:33:16,  1.35s/it]
 16%|█▌        | 9670/61904 [4:47:17<20:00:22,  1.38s/it]
 16%|█▌        | 9671/61904 [4:47:18<19:58:54,  1.38s/it]
 16%|█▌        | 9672/61904 [4:47:20<20:01:14,  1.38s/it]
 16%|█▌        | 9673/61904 [4:47:21<20:18:16,  1.40s/it]
 16%|█▌        | 9674/61904 [4:47:22<20:13:22,  1.39s/it]
 16%|█▌        | 9675/61904 [4:47:24<20:36:54,  1.42s/it]
 16%|█▌        | 9676/61904 [4:47:25<20:18:17,  1.40s/it]
 16%|█▌        | 9677/61904 [4:47:27<20:14:07,  1.39s/it]
 16%|█▌        | 9678/61904 [4:47:28<19:56:59,  1.38s/it]
 16%|█▌        | 9679/61904 [4:47:29<19:31:32,  1.35s/it]
 16%|█▌        | 9680/61904 [4:47:31<19:54:00,  1.37s/it]
                                                         
{'loss': 2.8514, 'learning_rate': 1.8463632827693505e-07, 'epoch': 2.5}

 16%|█▌        | 9680/61904 [4:47:31<19:54:00,  1.37s/it]
 16%|█▌        | 9681/61904 [4:47:32<20:04:46,  1.38s/it]
 16%|█▌        | 9682/61904 [4:47:33<19:40:05,  1.36s/it]
 16%|█▌        | 9683/61904 [4:47:35<19:41:34,  1.36s/it]
 16%|█▌        | 9684/61904 [4:47:36<19:18:16,  1.33s/it]
 16%|█▌        | 9685/61904 [4:47:37<19:46:17,  1.36s/it]
 16%|█▌        | 9686/61904 [4:47:39<18:53:37,  1.30s/it]
 16%|█▌        | 9687/61904 [4:47:40<18:50:04,  1.30s/it]
 16%|█▌        | 9688/61904 [4:47:41<19:34:20,  1.35s/it]
 16%|█▌        | 9689/61904 [4:47:43<19:41:48,  1.36s/it]
 16%|█▌        | 9690/61904 [4:47:44<19:31:44,  1.35s/it]
 16%|█▌        | 9691/61904 [4:47:45<19:19:35,  1.33s/it]
 16%|█▌        | 9692/61904 [4:47:47<19:23:29,  1.34s/it]
 16%|█▌        | 9693/61904 [4:47:48<18:51:15,  1.30s/it]
 16%|█▌        | 9694/61904 [4:47:49<18:50:52,  1.30s/it]
 16%|█▌        | 9695/61904 [4:47:51<18:56:52,  1.31s/it]
 16%|█▌        | 9696/61904 [4:47:52<18:37:24,  1.28s/it]
 16%|█▌        | 9697/61904 [4:47:53<18:32:17,  1.28s/it]
 16%|█▌        | 9698/61904 [4:47:54<19:04:48,  1.32s/it]
 16%|█▌        | 9699/61904 [4:47:56<19:24:53,  1.34s/it]
 16%|█▌        | 9700/61904 [4:47:57<19:13:21,  1.33s/it]
                                                         
{'loss': 2.8991, 'learning_rate': 1.846039154673927e-07, 'epoch': 2.51}

 16%|█▌        | 9700/61904 [4:47:57<19:13:21,  1.33s/it]
 16%|█▌        | 9701/61904 [4:47:58<19:16:05,  1.33s/it]
 16%|█▌        | 9702/61904 [4:48:00<19:09:52,  1.32s/it]
 16%|█▌        | 9703/61904 [4:48:01<19:06:52,  1.32s/it]
 16%|█▌        | 9704/61904 [4:48:02<19:09:27,  1.32s/it]
 16%|█▌        | 9705/61904 [4:48:04<19:29:00,  1.34s/it]
 16%|█▌        | 9706/61904 [4:48:05<19:41:27,  1.36s/it]
 16%|█▌        | 9707/61904 [4:48:07<20:20:22,  1.40s/it]
 16%|█▌        | 9708/61904 [4:48:08<19:53:44,  1.37s/it]
 16%|█▌        | 9709/61904 [4:48:09<19:45:23,  1.36s/it]
 16%|█▌        | 9710/61904 [4:48:11<19:37:17,  1.35s/it]
 16%|█▌        | 9711/61904 [4:48:12<19:14:18,  1.33s/it]
 16%|█▌        | 9712/61904 [4:48:13<19:00:26,  1.31s/it]
 16%|█▌        | 9713/61904 [4:48:14<18:42:14,  1.29s/it]
 16%|█▌        | 9714/61904 [4:48:16<19:21:49,  1.34s/it]
 16%|█▌        | 9715/61904 [4:48:17<18:55:42,  1.31s/it]
 16%|█▌        | 9716/61904 [4:48:18<18:55:50,  1.31s/it]
 16%|█▌        | 9717/61904 [4:48:20<19:32:37,  1.35s/it]
 16%|█▌        | 9718/61904 [4:48:21<19:17:53,  1.33s/it]
 16%|█▌        | 9719/61904 [4:48:23<20:38:03,  1.42s/it]
 16%|█▌        | 9720/61904 [4:48:24<21:34:15,  1.49s/it]
                                                         
{'loss': 2.8639, 'learning_rate': 1.8457150265785038e-07, 'epoch': 2.51}

 16%|█▌        | 9720/61904 [4:48:24<21:34:15,  1.49s/it]
 16%|█▌        | 9721/61904 [4:48:26<20:32:09,  1.42s/it]
 16%|█▌        | 9722/61904 [4:48:27<19:58:03,  1.38s/it]
 16%|█▌        | 9723/61904 [4:48:28<19:55:19,  1.37s/it]
 16%|█▌        | 9724/61904 [4:48:30<19:38:42,  1.36s/it]
 16%|█▌        | 9725/61904 [4:48:31<19:53:26,  1.37s/it]
 16%|█▌        | 9726/61904 [4:48:33<20:17:48,  1.40s/it]
 16%|█▌        | 9727/61904 [4:48:34<20:07:56,  1.39s/it]
 16%|█▌        | 9728/61904 [4:48:35<20:02:52,  1.38s/it]
 16%|█▌        | 9729/61904 [4:48:37<20:20:53,  1.40s/it]
 16%|█▌        | 9730/61904 [4:48:38<19:47:01,  1.37s/it]
 16%|█▌        | 9731/61904 [4:48:39<19:36:17,  1.35s/it]
 16%|█▌        | 9732/61904 [4:48:41<19:41:05,  1.36s/it]
 16%|█▌        | 9733/61904 [4:48:42<20:49:19,  1.44s/it]
 16%|█▌        | 9734/61904 [4:48:44<20:41:16,  1.43s/it]
 16%|█▌        | 9735/61904 [4:48:45<20:17:40,  1.40s/it]
 16%|█▌        | 9736/61904 [4:48:46<20:06:03,  1.39s/it]
 16%|█▌        | 9737/61904 [4:48:48<20:44:02,  1.43s/it]
 16%|█▌        | 9738/61904 [4:48:49<19:58:41,  1.38s/it]
 16%|█▌        | 9739/61904 [4:48:50<19:27:10,  1.34s/it]
 16%|█▌        | 9740/61904 [4:48:52<20:06:49,  1.39s/it]
                                                         
{'loss': 2.839, 'learning_rate': 1.8453908984830804e-07, 'epoch': 2.52}

 16%|█▌        | 9740/61904 [4:48:52<20:06:49,  1.39s/it]
 16%|█▌        | 9741/61904 [4:48:53<19:45:40,  1.36s/it]
 16%|█▌        | 9742/61904 [4:48:55<19:33:33,  1.35s/it]
 16%|█▌        | 9743/61904 [4:48:56<19:03:43,  1.32s/it]
 16%|█▌        | 9744/61904 [4:48:57<18:53:02,  1.30s/it]
 16%|█▌        | 9745/61904 [4:48:59<19:14:50,  1.33s/it]
 16%|█▌        | 9746/61904 [4:49:00<19:32:37,  1.35s/it]
 16%|█▌        | 9747/61904 [4:49:01<19:24:43,  1.34s/it]
 16%|█▌        | 9748/61904 [4:49:03<19:39:30,  1.36s/it]
 16%|█▌        | 9749/61904 [4:49:04<20:15:08,  1.40s/it]
 16%|█▌        | 9750/61904 [4:49:05<19:54:39,  1.37s/it]
 16%|█▌        | 9751/61904 [4:49:07<19:55:08,  1.37s/it]
 16%|█▌        | 9752/61904 [4:49:08<20:04:16,  1.39s/it]
 16%|█▌        | 9753/61904 [4:49:10<19:55:22,  1.38s/it]
 16%|█▌        | 9754/61904 [4:49:11<19:42:25,  1.36s/it]
 16%|█▌        | 9755/61904 [4:49:12<19:43:10,  1.36s/it]
 16%|█▌        | 9756/61904 [4:49:14<19:31:23,  1.35s/it]
 16%|█▌        | 9757/61904 [4:49:15<19:07:09,  1.32s/it]
 16%|█▌        | 9758/61904 [4:49:16<19:38:08,  1.36s/it]
 16%|█▌        | 9759/61904 [4:49:18<19:30:39,  1.35s/it]
 16%|█▌        | 9760/61904 [4:49:19<18:59:00,  1.31s/it]
                                                         
{'loss': 2.8364, 'learning_rate': 1.845066770387657e-07, 'epoch': 2.52}

 16%|█▌        | 9760/61904 [4:49:19<18:59:00,  1.31s/it]
 16%|█▌        | 9761/61904 [4:49:20<19:06:29,  1.32s/it]
 16%|█▌        | 9762/61904 [4:49:21<18:51:28,  1.30s/it]
 16%|█▌        | 9763/61904 [4:49:23<19:06:36,  1.32s/it]
 16%|█▌        | 9764/61904 [4:49:24<18:53:26,  1.30s/it]
 16%|█▌        | 9765/61904 [4:49:25<19:31:15,  1.35s/it]
 16%|█▌        | 9766/61904 [4:49:27<19:27:24,  1.34s/it]
 16%|█▌        | 9767/61904 [4:49:28<19:43:11,  1.36s/it]
 16%|█▌        | 9768/61904 [4:49:30<19:55:45,  1.38s/it]
 16%|█▌        | 9769/61904 [4:49:31<19:57:03,  1.38s/it]
 16%|█▌        | 9770/61904 [4:49:32<19:44:55,  1.36s/it]
 16%|█▌        | 9771/61904 [4:49:34<19:49:31,  1.37s/it]
 16%|█▌        | 9772/61904 [4:49:35<19:47:46,  1.37s/it]
 16%|█▌        | 9773/61904 [4:49:37<19:59:35,  1.38s/it]
 16%|█▌        | 9774/61904 [4:49:38<19:47:47,  1.37s/it]
 16%|█▌        | 9775/61904 [4:49:39<19:10:24,  1.32s/it]
 16%|█▌        | 9776/61904 [4:49:40<18:51:16,  1.30s/it]
 16%|█▌        | 9777/61904 [4:49:42<19:18:17,  1.33s/it]
 16%|█▌        | 9778/61904 [4:49:43<19:58:29,  1.38s/it]
 16%|█▌        | 9779/61904 [4:49:45<20:09:39,  1.39s/it]
 16%|█▌        | 9780/61904 [4:49:46<19:58:12,  1.38s/it]
                                                         
{'loss': 2.8632, 'learning_rate': 1.844742642292234e-07, 'epoch': 2.53}

 16%|█▌        | 9780/61904 [4:49:46<19:58:12,  1.38s/it]
 16%|█▌        | 9781/61904 [4:49:47<19:46:52,  1.37s/it]
 16%|█▌        | 9782/61904 [4:49:49<19:40:12,  1.36s/it]
 16%|█▌        | 9783/61904 [4:49:50<19:08:20,  1.32s/it]
 16%|█▌        | 9784/61904 [4:49:51<19:59:01,  1.38s/it]
 16%|█▌        | 9785/61904 [4:49:53<19:38:51,  1.36s/it]
 16%|█▌        | 9786/61904 [4:49:54<19:34:21,  1.35s/it]
 16%|█▌        | 9787/61904 [4:49:55<19:53:09,  1.37s/it]
 16%|█▌        | 9788/61904 [4:49:57<19:40:13,  1.36s/it]
 16%|█▌        | 9789/61904 [4:49:58<19:40:07,  1.36s/it]
 16%|█▌        | 9790/61904 [4:49:59<19:15:59,  1.33s/it]
 16%|█▌        | 9791/61904 [4:50:01<19:25:32,  1.34s/it]
 16%|█▌        | 9792/61904 [4:50:02<19:05:25,  1.32s/it]
 16%|█▌        | 9793/61904 [4:50:03<19:30:23,  1.35s/it]
 16%|█▌        | 9794/61904 [4:50:05<20:11:03,  1.39s/it]
 16%|█▌        | 9795/61904 [4:50:06<19:38:11,  1.36s/it]
 16%|█▌        | 9796/61904 [4:50:08<20:10:56,  1.39s/it]
 16%|█▌        | 9797/61904 [4:50:09<19:49:48,  1.37s/it]
 16%|█▌        | 9798/61904 [4:50:10<20:05:20,  1.39s/it]
 16%|█▌        | 9799/61904 [4:50:12<19:45:48,  1.37s/it]
 16%|█▌        | 9800/61904 [4:50:13<19:56:49,  1.38s/it]
                                                         
{'loss': 2.8573, 'learning_rate': 1.8444185141968105e-07, 'epoch': 2.53}

 16%|█▌        | 9800/61904 [4:50:13<19:56:49,  1.38s/it]
 16%|█▌        | 9801/61904 [4:50:15<20:08:50,  1.39s/it]
 16%|█▌        | 9802/61904 [4:50:16<20:28:58,  1.42s/it]
 16%|█▌        | 9803/61904 [4:50:17<20:05:38,  1.39s/it]
 16%|█▌        | 9804/61904 [4:50:19<20:14:45,  1.40s/it]
 16%|█▌        | 9805/61904 [4:50:20<19:46:22,  1.37s/it]
 16%|█▌        | 9806/61904 [4:50:22<21:12:56,  1.47s/it]
 16%|█▌        | 9807/61904 [4:50:23<21:14:04,  1.47s/it]
 16%|█▌        | 9808/61904 [4:50:25<21:05:03,  1.46s/it]
 16%|█▌        | 9809/61904 [4:50:26<20:29:38,  1.42s/it]
 16%|█▌        | 9810/61904 [4:50:27<19:35:04,  1.35s/it]
 16%|█▌        | 9811/61904 [4:50:29<19:42:57,  1.36s/it]
 16%|█▌        | 9812/61904 [4:50:30<21:17:43,  1.47s/it]
 16%|█▌        | 9813/61904 [4:50:32<20:23:42,  1.41s/it]
 16%|█▌        | 9814/61904 [4:50:33<19:49:49,  1.37s/it]
 16%|█▌        | 9815/61904 [4:50:34<19:40:35,  1.36s/it]
 16%|█▌        | 9816/61904 [4:50:36<20:17:46,  1.40s/it]
 16%|█▌        | 9817/61904 [4:50:37<20:05:06,  1.39s/it]
 16%|█▌        | 9818/61904 [4:50:38<19:45:13,  1.37s/it]
 16%|█▌        | 9819/61904 [4:50:40<20:29:50,  1.42s/it]
 16%|█▌        | 9820/61904 [4:50:41<20:59:55,  1.45s/it]
                                                         
{'loss': 2.869, 'learning_rate': 1.844094386101387e-07, 'epoch': 2.54}

 16%|█▌        | 9820/61904 [4:50:41<20:59:55,  1.45s/it]
 16%|█▌        | 9821/61904 [4:50:43<20:34:10,  1.42s/it]
 16%|█▌        | 9822/61904 [4:50:44<20:37:52,  1.43s/it]
 16%|█▌        | 9823/61904 [4:50:46<20:39:06,  1.43s/it]
 16%|█▌        | 9824/61904 [4:50:47<20:13:14,  1.40s/it]
 16%|█▌        | 9825/61904 [4:50:48<20:11:59,  1.40s/it]
 16%|█▌        | 9826/61904 [4:50:50<19:53:08,  1.37s/it]
 16%|█▌        | 9827/61904 [4:50:51<19:37:47,  1.36s/it]
 16%|█▌        | 9828/61904 [4:50:52<19:56:00,  1.38s/it]
 16%|█▌        | 9829/61904 [4:50:54<19:38:03,  1.36s/it]
 16%|█▌        | 9830/61904 [4:50:55<19:45:47,  1.37s/it]
 16%|█▌        | 9831/61904 [4:50:57<19:45:45,  1.37s/it]
 16%|█▌        | 9832/61904 [4:50:58<19:55:41,  1.38s/it]
 16%|█▌        | 9833/61904 [4:51:00<20:38:05,  1.43s/it]
 16%|█▌        | 9834/61904 [4:51:01<20:10:04,  1.39s/it]
 16%|█▌        | 9835/61904 [4:51:02<19:48:39,  1.37s/it]
 16%|█▌        | 9836/61904 [4:51:04<20:41:21,  1.43s/it]
 16%|█▌        | 9837/61904 [4:51:05<19:49:06,  1.37s/it]
 16%|█▌        | 9838/61904 [4:51:06<19:59:18,  1.38s/it]
 16%|█▌        | 9839/61904 [4:51:08<20:02:27,  1.39s/it]
 16%|█▌        | 9840/61904 [4:51:09<19:21:01,  1.34s/it]
                                                         
{'loss': 2.8879, 'learning_rate': 1.843770258005964e-07, 'epoch': 2.54}

 16%|█▌        | 9840/61904 [4:51:09<19:21:01,  1.34s/it]
 16%|█▌        | 9841/61904 [4:51:10<18:47:35,  1.30s/it]
 16%|█▌        | 9842/61904 [4:51:12<18:56:50,  1.31s/it]
 16%|█▌        | 9843/61904 [4:51:13<19:10:27,  1.33s/it]
 16%|█▌        | 9844/61904 [4:51:14<18:53:16,  1.31s/it]
 16%|█▌        | 9845/61904 [4:51:16<20:44:40,  1.43s/it]
 16%|█▌        | 9846/61904 [4:51:17<20:11:27,  1.40s/it]
 16%|█▌        | 9847/61904 [4:51:18<19:43:35,  1.36s/it]
 16%|█▌        | 9848/61904 [4:51:20<20:00:01,  1.38s/it]
 16%|█▌        | 9849/61904 [4:51:21<19:42:13,  1.36s/it]
 16%|█▌        | 9850/61904 [4:51:23<19:43:22,  1.36s/it]
 16%|█▌        | 9851/61904 [4:51:24<19:58:32,  1.38s/it]
 16%|█▌        | 9852/61904 [4:51:25<19:33:52,  1.35s/it]
 16%|█▌        | 9853/61904 [4:51:27<19:35:15,  1.35s/it]
 16%|█▌        | 9854/61904 [4:51:28<19:30:38,  1.35s/it]
 16%|█▌        | 9855/61904 [4:51:29<19:10:25,  1.33s/it]
 16%|█▌        | 9856/61904 [4:51:31<19:08:04,  1.32s/it]
 16%|█▌        | 9857/61904 [4:51:32<19:29:38,  1.35s/it]
 16%|█▌        | 9858/61904 [4:51:33<19:17:12,  1.33s/it]
 16%|█▌        | 9859/61904 [4:51:35<19:49:14,  1.37s/it]
 16%|█▌        | 9860/61904 [4:51:36<19:37:46,  1.36s/it]
                                                         
{'loss': 2.8887, 'learning_rate': 1.8434461299105406e-07, 'epoch': 2.55}

 16%|█▌        | 9860/61904 [4:51:36<19:37:46,  1.36s/it]
 16%|█▌        | 9861/61904 [4:51:37<19:26:03,  1.34s/it]
 16%|█▌        | 9862/61904 [4:51:39<19:00:47,  1.32s/it]
 16%|█▌        | 9863/61904 [4:51:40<18:36:32,  1.29s/it]
 16%|█▌        | 9864/61904 [4:51:41<19:00:22,  1.31s/it]
 16%|█▌        | 9865/61904 [4:51:43<19:22:32,  1.34s/it]
 16%|█▌        | 9866/61904 [4:51:44<18:34:00,  1.28s/it]
 16%|█▌        | 9867/61904 [4:51:45<19:24:37,  1.34s/it]
 16%|█▌        | 9868/61904 [4:51:47<19:42:54,  1.36s/it]
 16%|█▌        | 9869/61904 [4:51:48<19:48:28,  1.37s/it]
 16%|█▌        | 9870/61904 [4:51:50<20:27:10,  1.42s/it]
 16%|█▌        | 9871/61904 [4:51:51<19:51:39,  1.37s/it]
 16%|█▌        | 9872/61904 [4:51:52<19:28:02,  1.35s/it]
 16%|█▌        | 9873/61904 [4:51:54<20:10:05,  1.40s/it]
 16%|█▌        | 9874/61904 [4:51:55<19:53:24,  1.38s/it]
 16%|█▌        | 9875/61904 [4:51:56<20:07:37,  1.39s/it]
 16%|█▌        | 9876/61904 [4:51:58<19:53:32,  1.38s/it]
 16%|█▌        | 9877/61904 [4:51:59<20:00:00,  1.38s/it]
 16%|█▌        | 9878/61904 [4:52:01<20:15:37,  1.40s/it]
 16%|█▌        | 9879/61904 [4:52:02<19:26:45,  1.35s/it]
 16%|█▌        | 9880/61904 [4:52:03<18:59:49,  1.31s/it]
                                                         
{'loss': 2.817, 'learning_rate': 1.8431220018151172e-07, 'epoch': 2.55}

 16%|█▌        | 9880/61904 [4:52:03<18:59:49,  1.31s/it]
 16%|█▌        | 9881/61904 [4:52:04<18:49:35,  1.30s/it]
 16%|█▌        | 9882/61904 [4:52:06<18:41:28,  1.29s/it]
 16%|█▌        | 9883/61904 [4:52:07<19:01:05,  1.32s/it]
 16%|█▌        | 9884/61904 [4:52:08<19:37:32,  1.36s/it]
 16%|█▌        | 9885/61904 [4:52:10<19:49:43,  1.37s/it]
 16%|█▌        | 9886/61904 [4:52:11<19:03:43,  1.32s/it]
 16%|█▌        | 9887/61904 [4:52:12<19:26:05,  1.35s/it]
 16%|█▌        | 9888/61904 [4:52:14<19:51:12,  1.37s/it]
 16%|█▌        | 9889/61904 [4:52:15<19:23:16,  1.34s/it]
 16%|█▌        | 9890/61904 [4:52:16<19:21:28,  1.34s/it]
 16%|█▌        | 9891/61904 [4:52:18<19:33:33,  1.35s/it]
 16%|█▌        | 9892/61904 [4:52:19<20:10:50,  1.40s/it]
 16%|█▌        | 9893/61904 [4:52:21<20:15:27,  1.40s/it]
 16%|█▌        | 9894/61904 [4:52:22<20:01:30,  1.39s/it]
 16%|█▌        | 9895/61904 [4:52:23<19:30:48,  1.35s/it]
 16%|█▌        | 9896/61904 [4:52:25<19:19:34,  1.34s/it]
 16%|█▌        | 9897/61904 [4:52:26<19:27:06,  1.35s/it]
 16%|█▌        | 9898/61904 [4:52:27<19:48:15,  1.37s/it]
 16%|█▌        | 9899/61904 [4:52:29<19:42:41,  1.36s/it]
 16%|█▌        | 9900/61904 [4:52:30<19:33:03,  1.35s/it]
                                                         
{'loss': 2.8758, 'learning_rate': 1.842797873719694e-07, 'epoch': 2.56}

 16%|█▌        | 9900/61904 [4:52:30<19:33:03,  1.35s/it]
 16%|█▌        | 9901/61904 [4:52:31<18:56:51,  1.31s/it]
 16%|█▌        | 9902/61904 [4:52:33<19:25:04,  1.34s/it]
 16%|█▌        | 9903/61904 [4:52:34<19:09:45,  1.33s/it]
 16%|█▌        | 9904/61904 [4:52:35<19:15:00,  1.33s/it]
 16%|█▌        | 9905/61904 [4:52:37<19:25:33,  1.34s/it]
 16%|█▌        | 9906/61904 [4:52:38<19:08:02,  1.32s/it]
 16%|█▌        | 9907/61904 [4:52:39<18:58:02,  1.31s/it]
 16%|█▌        | 9908/61904 [4:52:41<19:05:59,  1.32s/it]
 16%|█▌        | 9909/61904 [4:52:42<19:20:52,  1.34s/it]
 16%|█▌        | 9910/61904 [4:52:44<19:59:35,  1.38s/it]
 16%|█▌        | 9911/61904 [4:52:45<19:52:00,  1.38s/it]
 16%|█▌        | 9912/61904 [4:52:46<19:41:59,  1.36s/it]
 16%|█▌        | 9913/61904 [4:52:47<19:07:01,  1.32s/it]
 16%|█▌        | 9914/61904 [4:52:49<19:02:47,  1.32s/it]
 16%|█▌        | 9915/61904 [4:52:50<19:04:44,  1.32s/it]
 16%|█▌        | 9916/61904 [4:52:51<19:03:53,  1.32s/it]
 16%|█▌        | 9917/61904 [4:52:53<19:40:59,  1.36s/it]
 16%|█▌        | 9918/61904 [4:52:54<19:59:15,  1.38s/it]
 16%|█▌        | 9919/61904 [4:52:56<19:35:55,  1.36s/it]
 16%|█▌        | 9920/61904 [4:52:57<19:27:56,  1.35s/it]
                                                         
{'loss': 2.8466, 'learning_rate': 1.8424737456242705e-07, 'epoch': 2.56}

 16%|█▌        | 9920/61904 [4:52:57<19:27:56,  1.35s/it]
 16%|█▌        | 9921/61904 [4:52:58<18:33:52,  1.29s/it]
 16%|█▌        | 9922/61904 [4:52:59<18:58:32,  1.31s/it]
 16%|█▌        | 9923/61904 [4:53:01<19:15:57,  1.33s/it]
 16%|█▌        | 9924/61904 [4:53:02<18:57:49,  1.31s/it]
 16%|█▌        | 9925/61904 [4:53:03<19:00:38,  1.32s/it]
 16%|█▌        | 9926/61904 [4:53:05<18:55:45,  1.31s/it]
 16%|█▌        | 9927/61904 [4:53:06<19:01:02,  1.32s/it]
 16%|█▌        | 9928/61904 [4:53:07<18:54:42,  1.31s/it]
 16%|█▌        | 9929/61904 [4:53:09<18:57:58,  1.31s/it]
 16%|█▌        | 9930/61904 [4:53:10<19:14:06,  1.33s/it]
 16%|█▌        | 9931/61904 [4:53:11<19:05:05,  1.32s/it]
 16%|█▌        | 9932/61904 [4:53:13<19:19:46,  1.34s/it]
 16%|█▌        | 9933/61904 [4:53:14<19:23:37,  1.34s/it]
 16%|█▌        | 9934/61904 [4:53:16<20:25:17,  1.41s/it]
 16%|█▌        | 9935/61904 [4:53:17<20:21:55,  1.41s/it]
 16%|█▌        | 9936/61904 [4:53:18<19:52:54,  1.38s/it]
 16%|█▌        | 9937/61904 [4:53:20<20:08:10,  1.39s/it]
 16%|█▌        | 9938/61904 [4:53:21<19:43:55,  1.37s/it]
 16%|█▌        | 9939/61904 [4:53:23<20:23:07,  1.41s/it]
 16%|█▌        | 9940/61904 [4:53:24<20:02:32,  1.39s/it]
                                                         
{'loss': 2.8203, 'learning_rate': 1.8421496175288474e-07, 'epoch': 2.57}

 16%|█▌        | 9940/61904 [4:53:24<20:02:32,  1.39s/it]
 16%|█▌        | 9941/61904 [4:53:25<20:07:07,  1.39s/it]
 16%|█▌        | 9942/61904 [4:53:27<20:08:18,  1.40s/it]
 16%|█▌        | 9943/61904 [4:53:28<19:42:06,  1.36s/it]
 16%|█▌        | 9944/61904 [4:53:29<19:14:38,  1.33s/it]
 16%|█▌        | 9945/61904 [4:53:31<19:42:37,  1.37s/it]
 16%|█▌        | 9946/61904 [4:53:32<19:59:39,  1.39s/it]
 16%|█▌        | 9947/61904 [4:53:34<20:00:31,  1.39s/it]
 16%|█▌        | 9948/61904 [4:53:35<19:49:09,  1.37s/it]
 16%|█▌        | 9949/61904 [4:53:36<19:22:05,  1.34s/it]
 16%|█▌        | 9950/61904 [4:53:38<19:41:51,  1.36s/it]
 16%|█▌        | 9951/61904 [4:53:39<19:17:35,  1.34s/it]
 16%|█▌        | 9952/61904 [4:53:40<19:25:31,  1.35s/it]
 16%|█▌        | 9953/61904 [4:53:42<19:17:55,  1.34s/it]
 16%|█▌        | 9954/61904 [4:53:43<19:14:38,  1.33s/it]
 16%|█▌        | 9955/61904 [4:53:44<19:18:04,  1.34s/it]
 16%|█▌        | 9956/61904 [4:53:46<19:10:43,  1.33s/it]
 16%|█▌        | 9957/61904 [4:53:47<19:40:06,  1.36s/it]
 16%|█▌        | 9958/61904 [4:53:48<19:19:27,  1.34s/it]
 16%|█▌        | 9959/61904 [4:53:50<19:06:31,  1.32s/it]
 16%|█▌        | 9960/61904 [4:53:51<19:37:03,  1.36s/it]
                                                         
{'loss': 2.8138, 'learning_rate': 1.841825489433424e-07, 'epoch': 2.57}

 16%|█▌        | 9960/61904 [4:53:51<19:37:03,  1.36s/it]
 16%|█▌        | 9961/61904 [4:53:52<19:33:36,  1.36s/it]
 16%|█▌        | 9962/61904 [4:53:54<19:37:30,  1.36s/it]
 16%|█▌        | 9963/61904 [4:53:55<19:42:13,  1.37s/it]
 16%|█▌        | 9964/61904 [4:53:56<19:28:44,  1.35s/it]
 16%|█▌        | 9965/61904 [4:53:58<20:21:50,  1.41s/it]
 16%|█▌        | 9966/61904 [4:53:59<20:32:52,  1.42s/it]
 16%|█▌        | 9967/61904 [4:54:01<20:25:04,  1.42s/it]
 16%|█▌        | 9968/61904 [4:54:02<19:50:21,  1.38s/it]
 16%|█▌        | 9969/61904 [4:54:04<19:54:28,  1.38s/it]
 16%|█▌        | 9970/61904 [4:54:05<19:19:04,  1.34s/it]
 16%|█▌        | 9971/61904 [4:54:06<18:59:58,  1.32s/it]
 16%|█▌        | 9972/61904 [4:54:07<19:01:03,  1.32s/it]
 16%|█▌        | 9973/61904 [4:54:09<20:07:40,  1.40s/it]
 16%|█▌        | 9974/61904 [4:54:10<19:46:07,  1.37s/it]
 16%|█▌        | 9975/61904 [4:54:12<19:39:39,  1.36s/it]
 16%|█▌        | 9976/61904 [4:54:13<19:28:59,  1.35s/it]
 16%|█▌        | 9977/61904 [4:54:14<19:21:55,  1.34s/it]
 16%|█▌        | 9978/61904 [4:54:16<19:42:38,  1.37s/it]
 16%|█▌        | 9979/61904 [4:54:17<20:19:09,  1.41s/it]
 16%|█▌        | 9980/61904 [4:54:19<21:13:03,  1.47s/it]
                                                         
{'loss': 2.8538, 'learning_rate': 1.8415013613380006e-07, 'epoch': 2.58}

 16%|█▌        | 9980/61904 [4:54:19<21:13:03,  1.47s/it]
 16%|█▌        | 9981/61904 [4:54:20<20:43:30,  1.44s/it]
 16%|█▌        | 9982/61904 [4:54:22<21:17:53,  1.48s/it]
 16%|█▌        | 9983/61904 [4:54:23<20:03:58,  1.39s/it]
 16%|█▌        | 9984/61904 [4:54:24<20:03:51,  1.39s/it]
 16%|█▌        | 9985/61904 [4:54:26<20:17:23,  1.41s/it]
 16%|█▌        | 9986/61904 [4:54:27<20:19:53,  1.41s/it]
 16%|█▌        | 9987/61904 [4:54:29<20:13:21,  1.40s/it]
 16%|█▌        | 9988/61904 [4:54:30<19:58:20,  1.38s/it]
 16%|█▌        | 9989/61904 [4:54:31<20:14:38,  1.40s/it]
 16%|█▌        | 9990/61904 [4:54:33<19:39:53,  1.36s/it]
 16%|█▌        | 9991/61904 [4:54:34<19:46:06,  1.37s/it]
 16%|█▌        | 9992/61904 [4:54:35<20:05:11,  1.39s/it]
 16%|█▌        | 9993/61904 [4:54:37<20:31:17,  1.42s/it]
 16%|█▌        | 9994/61904 [4:54:38<20:09:48,  1.40s/it]
 16%|█▌        | 9995/61904 [4:54:40<20:33:01,  1.43s/it]
 16%|█▌        | 9996/61904 [4:54:41<20:19:21,  1.41s/it]
 16%|█▌        | 9997/61904 [4:54:43<20:56:30,  1.45s/it]
 16%|█▌        | 9998/61904 [4:54:44<20:18:52,  1.41s/it]
 16%|█▌        | 9999/61904 [4:54:45<20:13:51,  1.40s/it]
 16%|█▌        | 10000/61904 [4:54:47<20:09:23,  1.40s/it]
                                                          
{'loss': 2.779, 'learning_rate': 1.8411772332425775e-07, 'epoch': 2.58}

 16%|█▌        | 10000/61904 [4:54:47<20:09:23,  1.40s/it]
 16%|█▌        | 10001/61904 [4:54:48<19:55:26,  1.38s/it]
 16%|█▌        | 10002/61904 [4:54:49<19:49:16,  1.37s/it]
 16%|█▌        | 10003/61904 [4:54:51<18:56:52,  1.31s/it]
 16%|█▌        | 10004/61904 [4:54:52<18:52:15,  1.31s/it]
 16%|█▌        | 10005/61904 [4:54:53<19:32:44,  1.36s/it]
 16%|█▌        | 10006/61904 [4:54:55<19:33:36,  1.36s/it]
 16%|█▌        | 10007/61904 [4:54:56<20:04:12,  1.39s/it]
 16%|█▌        | 10008/61904 [4:54:58<20:09:21,  1.40s/it]
 16%|█▌        | 10009/61904 [4:54:59<20:46:46,  1.44s/it]
 16%|█▌        | 10010/61904 [4:55:01<20:21:48,  1.41s/it]
 16%|█▌        | 10011/61904 [4:55:02<20:24:27,  1.42s/it]
 16%|█▌        | 10012/61904 [4:55:03<20:42:09,  1.44s/it]
 16%|█▌        | 10013/61904 [4:55:05<20:22:17,  1.41s/it]
 16%|█▌        | 10014/61904 [4:55:06<20:09:15,  1.40s/it]
 16%|█▌        | 10015/61904 [4:55:08<20:42:30,  1.44s/it]
 16%|█▌        | 10016/61904 [4:55:09<20:56:13,  1.45s/it]
 16%|█▌        | 10017/61904 [4:55:10<19:57:51,  1.39s/it]
 16%|█▌        | 10018/61904 [4:55:12<19:47:47,  1.37s/it]
 16%|█▌        | 10019/61904 [4:55:13<20:12:25,  1.40s/it]
 16%|█▌        | 10020/61904 [4:55:15<20:02:26,  1.39s/it]
                                                          
{'loss': 2.8533, 'learning_rate': 1.840853105147154e-07, 'epoch': 2.59}

 16%|█▌        | 10020/61904 [4:55:15<20:02:26,  1.39s/it]
 16%|█▌        | 10021/61904 [4:55:16<20:20:33,  1.41s/it]
 16%|█▌        | 10022/61904 [4:55:17<20:14:20,  1.40s/it]
 16%|█▌        | 10023/61904 [4:55:19<19:58:14,  1.39s/it]
 16%|█▌        | 10024/61904 [4:55:20<20:10:59,  1.40s/it]
 16%|█▌        | 10025/61904 [4:55:22<19:58:18,  1.39s/it]
 16%|█▌        | 10026/61904 [4:55:23<19:34:06,  1.36s/it]
 16%|█▌        | 10027/61904 [4:55:24<19:09:40,  1.33s/it]
 16%|█▌        | 10028/61904 [4:55:26<19:49:09,  1.38s/it]
 16%|█▌        | 10029/61904 [4:55:27<19:42:52,  1.37s/it]
 16%|█▌        | 10030/61904 [4:55:28<19:44:43,  1.37s/it]
 16%|█▌        | 10031/61904 [4:55:30<19:40:10,  1.37s/it]
 16%|█▌        | 10032/61904 [4:55:31<19:29:12,  1.35s/it]
 16%|█▌        | 10033/61904 [4:55:33<20:11:55,  1.40s/it]
 16%|█▌        | 10034/61904 [4:55:34<19:59:57,  1.39s/it]
 16%|█▌        | 10035/61904 [4:55:35<19:28:31,  1.35s/it]
 16%|█▌        | 10036/61904 [4:55:37<19:34:12,  1.36s/it]
 16%|█▌        | 10037/61904 [4:55:38<19:31:52,  1.36s/it]
 16%|█▌        | 10038/61904 [4:55:39<19:15:19,  1.34s/it]
 16%|█▌        | 10039/61904 [4:55:41<19:40:58,  1.37s/it]
 16%|█▌        | 10040/61904 [4:55:42<20:08:15,  1.40s/it]
                                                          
{'loss': 2.8389, 'learning_rate': 1.8405289770517307e-07, 'epoch': 2.59}

 16%|█▌        | 10040/61904 [4:55:42<20:08:15,  1.40s/it]
 16%|█▌        | 10041/61904 [4:55:44<20:46:20,  1.44s/it]
 16%|█▌        | 10042/61904 [4:55:45<20:32:40,  1.43s/it]
 16%|█▌        | 10043/61904 [4:55:46<20:34:37,  1.43s/it]
 16%|█▌        | 10044/61904 [4:55:48<20:01:34,  1.39s/it]
 16%|█▌        | 10045/61904 [4:55:49<20:13:34,  1.40s/it]
 16%|█▌        | 10046/61904 [4:55:50<19:41:48,  1.37s/it]
 16%|█▌        | 10047/61904 [4:55:52<18:56:21,  1.31s/it]
 16%|█▌        | 10048/61904 [4:55:53<19:21:22,  1.34s/it]
 16%|█▌        | 10049/61904 [4:55:54<19:22:48,  1.35s/it]
 16%|█▌        | 10050/61904 [4:55:56<19:19:07,  1.34s/it]
 16%|█▌        | 10051/61904 [4:55:57<19:55:09,  1.38s/it]
 16%|█▌        | 10052/61904 [4:55:59<19:46:01,  1.37s/it]
 16%|█▌        | 10053/61904 [4:56:00<19:54:07,  1.38s/it]
 16%|█▌        | 10054/61904 [4:56:01<19:58:52,  1.39s/it]
 16%|█▌        | 10055/61904 [4:56:03<20:20:43,  1.41s/it]
 16%|█▌        | 10056/61904 [4:56:04<19:52:15,  1.38s/it]
 16%|█▌        | 10057/61904 [4:56:05<19:31:35,  1.36s/it]
 16%|█▌        | 10058/61904 [4:56:07<19:41:31,  1.37s/it]
 16%|█▌        | 10059/61904 [4:56:08<19:48:36,  1.38s/it]
 16%|█▋        | 10060/61904 [4:56:09<19:20:57,  1.34s/it]
                                                          
{'loss': 2.9132, 'learning_rate': 1.8402048489563076e-07, 'epoch': 2.6}

 16%|█▋        | 10060/61904 [4:56:09<19:20:57,  1.34s/it]
 16%|█▋        | 10061/61904 [4:56:11<19:21:58,  1.34s/it]
 16%|█▋        | 10062/61904 [4:56:12<19:23:43,  1.35s/it]
 16%|█▋        | 10063/61904 [4:56:14<19:51:56,  1.38s/it]
 16%|█▋        | 10064/61904 [4:56:15<19:37:41,  1.36s/it]
 16%|█▋        | 10065/61904 [4:56:16<19:23:28,  1.35s/it]
 16%|█▋        | 10066/61904 [4:56:18<20:08:30,  1.40s/it]
 16%|█▋        | 10067/61904 [4:56:19<20:35:07,  1.43s/it]
 16%|█▋        | 10068/61904 [4:56:21<20:25:57,  1.42s/it]
 16%|█▋        | 10069/61904 [4:56:22<20:04:09,  1.39s/it]
 16%|█▋        | 10070/61904 [4:56:23<19:56:02,  1.38s/it]
 16%|█▋        | 10071/61904 [4:56:25<20:17:31,  1.41s/it]
 16%|█▋        | 10072/61904 [4:56:26<19:25:52,  1.35s/it]
 16%|█▋        | 10073/61904 [4:56:27<19:15:36,  1.34s/it]
 16%|█▋        | 10074/61904 [4:56:29<19:15:18,  1.34s/it]
 16%|█▋        | 10075/61904 [4:56:30<18:53:49,  1.31s/it]
 16%|█▋        | 10076/61904 [4:56:31<19:08:22,  1.33s/it]
 16%|█▋        | 10077/61904 [4:56:33<19:17:35,  1.34s/it]
 16%|█▋        | 10078/61904 [4:56:34<19:00:44,  1.32s/it]
 16%|█▋        | 10079/61904 [4:56:35<19:12:14,  1.33s/it]
 16%|█▋        | 10080/61904 [4:56:37<21:18:27,  1.48s/it]
                                                          
{'loss': 2.8213, 'learning_rate': 1.8398807208608842e-07, 'epoch': 2.6}

 16%|█▋        | 10080/61904 [4:56:37<21:18:27,  1.48s/it]
 16%|█▋        | 10081/61904 [4:56:38<20:21:42,  1.41s/it]
 16%|█▋        | 10082/61904 [4:56:40<20:06:05,  1.40s/it]
 16%|█▋        | 10083/61904 [4:56:41<20:10:57,  1.40s/it]
 16%|█▋        | 10084/61904 [4:56:43<20:17:30,  1.41s/it]
 16%|█▋        | 10085/61904 [4:56:44<19:54:43,  1.38s/it]
 16%|█▋        | 10086/61904 [4:56:45<19:41:53,  1.37s/it]
 16%|█▋        | 10087/61904 [4:56:47<19:49:55,  1.38s/it]
 16%|█▋        | 10088/61904 [4:56:48<19:55:17,  1.38s/it]
 16%|█▋        | 10089/61904 [4:56:50<20:18:46,  1.41s/it]
 16%|█▋        | 10090/61904 [4:56:51<20:06:24,  1.40s/it]
 16%|█▋        | 10091/61904 [4:56:52<20:49:30,  1.45s/it]
 16%|█▋        | 10092/61904 [4:56:54<20:37:16,  1.43s/it]
 16%|█▋        | 10093/61904 [4:56:55<20:10:35,  1.40s/it]
 16%|█▋        | 10094/61904 [4:56:57<20:35:30,  1.43s/it]
 16%|█▋        | 10095/61904 [4:56:58<20:13:56,  1.41s/it]
 16%|█▋        | 10096/61904 [4:56:59<20:19:21,  1.41s/it]
 16%|█▋        | 10097/61904 [4:57:01<20:09:33,  1.40s/it]
 16%|█▋        | 10098/61904 [4:57:02<20:25:49,  1.42s/it]
 16%|█▋        | 10099/61904 [4:57:04<20:40:53,  1.44s/it]
 16%|█▋        | 10100/61904 [4:57:05<20:20:32,  1.41s/it]
                                                          
{'loss': 2.7963, 'learning_rate': 1.8395565927654608e-07, 'epoch': 2.61}

 16%|█▋        | 10100/61904 [4:57:05<20:20:32,  1.41s/it]
 16%|█▋        | 10101/61904 [4:57:07<20:56:48,  1.46s/it]
 16%|█▋        | 10102/61904 [4:57:08<21:13:03,  1.47s/it]
 16%|█▋        | 10103/61904 [4:57:10<20:56:19,  1.46s/it]
 16%|█▋        | 10104/61904 [4:57:11<21:30:29,  1.49s/it]
 16%|█▋        | 10105/61904 [4:57:13<21:42:04,  1.51s/it]
 16%|█▋        | 10106/61904 [4:57:14<21:26:21,  1.49s/it]
 16%|█▋        | 10107/61904 [4:57:15<20:34:27,  1.43s/it]
 16%|█▋        | 10108/61904 [4:57:17<20:13:27,  1.41s/it]
 16%|█▋        | 10109/61904 [4:57:18<20:29:43,  1.42s/it]
 16%|█▋        | 10110/61904 [4:57:20<20:04:36,  1.40s/it]
 16%|█▋        | 10111/61904 [4:57:21<19:44:20,  1.37s/it]
 16%|█▋        | 10112/61904 [4:57:22<19:33:42,  1.36s/it]
 16%|█▋        | 10113/61904 [4:57:24<19:10:53,  1.33s/it]
 16%|█▋        | 10114/61904 [4:57:25<19:19:17,  1.34s/it]
 16%|█▋        | 10115/61904 [4:57:26<19:24:44,  1.35s/it]
 16%|█▋        | 10116/61904 [4:57:28<19:21:03,  1.35s/it]
 16%|█▋        | 10117/61904 [4:57:29<18:50:32,  1.31s/it]
 16%|█▋        | 10118/61904 [4:57:30<18:59:03,  1.32s/it]
 16%|█▋        | 10119/61904 [4:57:32<20:00:05,  1.39s/it]
 16%|█▋        | 10120/61904 [4:57:33<19:35:53,  1.36s/it]
                                                          
{'loss': 2.7789, 'learning_rate': 1.8392324646700374e-07, 'epoch': 2.62}

 16%|█▋        | 10120/61904 [4:57:33<19:35:53,  1.36s/it]
 16%|█▋        | 10121/61904 [4:57:34<19:22:00,  1.35s/it]
 16%|█▋        | 10122/61904 [4:57:36<19:38:32,  1.37s/it]
 16%|█▋        | 10123/61904 [4:57:37<18:56:31,  1.32s/it]
 16%|█▋        | 10124/61904 [4:57:38<19:29:41,  1.36s/it]
 16%|█▋        | 10125/61904 [4:57:40<20:41:15,  1.44s/it]
 16%|█▋        | 10126/61904 [4:57:41<20:21:16,  1.42s/it]
 16%|█▋        | 10127/61904 [4:57:43<20:16:23,  1.41s/it]
 16%|█▋        | 10128/61904 [4:57:44<19:27:10,  1.35s/it]
 16%|█▋        | 10129/61904 [4:57:46<20:07:57,  1.40s/it]
 16%|█▋        | 10130/61904 [4:57:47<19:21:19,  1.35s/it]
 16%|█▋        | 10131/61904 [4:57:48<19:37:01,  1.36s/it]
 16%|█▋        | 10132/61904 [4:57:50<19:48:10,  1.38s/it]
 16%|█▋        | 10133/61904 [4:57:51<19:37:17,  1.36s/it]
 16%|█▋        | 10134/61904 [4:57:52<19:30:32,  1.36s/it]
 16%|█▋        | 10135/61904 [4:57:53<19:01:15,  1.32s/it]
 16%|█▋        | 10136/61904 [4:57:55<19:05:27,  1.33s/it]
 16%|█▋        | 10137/61904 [4:57:56<18:48:56,  1.31s/it]
 16%|█▋        | 10138/61904 [4:57:57<18:56:47,  1.32s/it]
 16%|█▋        | 10139/61904 [4:57:59<19:31:04,  1.36s/it]
 16%|█▋        | 10140/61904 [4:58:00<19:22:49,  1.35s/it]
                                                          
{'loss': 2.8891, 'learning_rate': 1.838908336574614e-07, 'epoch': 2.62}

 16%|█▋        | 10140/61904 [4:58:00<19:22:49,  1.35s/it]
 16%|█▋        | 10141/61904 [4:58:01<18:58:55,  1.32s/it]
 16%|█▋        | 10142/61904 [4:58:03<18:49:43,  1.31s/it]
 16%|█▋        | 10143/61904 [4:58:04<18:52:24,  1.31s/it]
 16%|█▋        | 10144/61904 [4:58:06<19:26:29,  1.35s/it]
 16%|█▋        | 10145/61904 [4:58:07<19:26:50,  1.35s/it]
 16%|█▋        | 10146/61904 [4:58:08<19:28:35,  1.35s/it]
 16%|█▋        | 10147/61904 [4:58:09<19:01:06,  1.32s/it]
 16%|█▋        | 10148/61904 [4:58:11<19:03:16,  1.33s/it]
 16%|█▋        | 10149/61904 [4:58:12<18:34:24,  1.29s/it]
 16%|█▋        | 10150/61904 [4:58:13<18:46:37,  1.31s/it]
 16%|█▋        | 10151/61904 [4:58:15<19:16:29,  1.34s/it]
 16%|█▋        | 10152/61904 [4:58:16<19:16:26,  1.34s/it]
 16%|█▋        | 10153/61904 [4:58:18<19:48:58,  1.38s/it]
 16%|█▋        | 10154/61904 [4:58:19<19:21:46,  1.35s/it]
 16%|█▋        | 10155/61904 [4:58:20<19:56:09,  1.39s/it]
 16%|█▋        | 10156/61904 [4:58:22<20:13:15,  1.41s/it]
 16%|█▋        | 10157/61904 [4:58:23<19:42:02,  1.37s/it]
 16%|█▋        | 10158/61904 [4:58:24<19:20:10,  1.35s/it]
 16%|█▋        | 10159/61904 [4:58:26<19:15:44,  1.34s/it]
 16%|█▋        | 10160/61904 [4:58:27<20:14:03,  1.41s/it]
                                                          
{'loss': 2.8305, 'learning_rate': 1.838584208479191e-07, 'epoch': 2.63}

 16%|█▋        | 10160/61904 [4:58:27<20:14:03,  1.41s/it]
 16%|█▋        | 10161/61904 [4:58:29<19:44:20,  1.37s/it]
 16%|█▋        | 10162/61904 [4:58:30<19:10:44,  1.33s/it]
 16%|█▋        | 10163/61904 [4:58:31<19:15:32,  1.34s/it]
 16%|█▋        | 10164/61904 [4:58:32<18:55:31,  1.32s/it]
 16%|█▋        | 10165/61904 [4:58:34<19:10:09,  1.33s/it]
 16%|█▋        | 10166/61904 [4:58:35<19:43:19,  1.37s/it]
 16%|█▋        | 10167/61904 [4:58:37<19:46:46,  1.38s/it]
 16%|█▋        | 10168/61904 [4:58:38<19:38:41,  1.37s/it]
 16%|█▋        | 10169/61904 [4:58:39<19:09:23,  1.33s/it]
 16%|█▋        | 10170/61904 [4:58:40<18:50:31,  1.31s/it]
 16%|█▋        | 10171/61904 [4:58:42<19:16:45,  1.34s/it]
 16%|█▋        | 10172/61904 [4:58:43<19:06:44,  1.33s/it]
 16%|█▋        | 10173/61904 [4:58:44<18:36:48,  1.30s/it]
 16%|█▋        | 10174/61904 [4:58:46<18:53:11,  1.31s/it]
 16%|█▋        | 10175/61904 [4:58:47<19:07:05,  1.33s/it]
 16%|█▋        | 10176/61904 [4:58:48<18:35:52,  1.29s/it]
 16%|█▋        | 10177/61904 [4:58:50<20:24:44,  1.42s/it]
 16%|█▋        | 10178/61904 [4:58:51<19:32:07,  1.36s/it]
 16%|█▋        | 10179/61904 [4:58:53<19:42:50,  1.37s/it]
 16%|█▋        | 10180/61904 [4:58:54<19:27:58,  1.35s/it]
                                                          
{'loss': 2.8333, 'learning_rate': 1.8382600803837676e-07, 'epoch': 2.63}

 16%|█▋        | 10180/61904 [4:58:54<19:27:58,  1.35s/it]
 16%|█▋        | 10181/61904 [4:58:55<19:15:27,  1.34s/it]
 16%|█▋        | 10182/61904 [4:58:57<19:34:00,  1.36s/it]
 16%|█▋        | 10183/61904 [4:58:58<19:40:37,  1.37s/it]
 16%|█▋        | 10184/61904 [4:59:00<20:14:39,  1.41s/it]
 16%|█▋        | 10185/61904 [4:59:01<20:06:34,  1.40s/it]
 16%|█▋        | 10186/61904 [4:59:02<19:41:43,  1.37s/it]
 16%|█▋        | 10187/61904 [4:59:04<19:02:10,  1.33s/it]
 16%|█▋        | 10188/61904 [4:59:05<19:19:47,  1.35s/it]
 16%|█▋        | 10189/61904 [4:59:06<19:26:31,  1.35s/it]
 16%|█▋        | 10190/61904 [4:59:08<19:13:34,  1.34s/it]
 16%|█▋        | 10191/61904 [4:59:09<20:06:57,  1.40s/it]
 16%|█▋        | 10192/61904 [4:59:10<19:40:22,  1.37s/it]
 16%|█▋        | 10193/61904 [4:59:12<18:51:42,  1.31s/it]
 16%|█▋        | 10194/61904 [4:59:13<18:44:29,  1.30s/it]
 16%|█▋        | 10195/61904 [4:59:14<18:49:49,  1.31s/it]
 16%|█▋        | 10196/61904 [4:59:16<20:15:06,  1.41s/it]
 16%|█▋        | 10197/61904 [4:59:17<20:15:54,  1.41s/it]
 16%|█▋        | 10198/61904 [4:59:19<19:58:23,  1.39s/it]
 16%|█▋        | 10199/61904 [4:59:20<19:48:02,  1.38s/it]
 16%|█▋        | 10200/61904 [4:59:21<19:35:46,  1.36s/it]
                                                          
{'loss': 2.8771, 'learning_rate': 1.8379359522883442e-07, 'epoch': 2.64}

 16%|█▋        | 10200/61904 [4:59:21<19:35:46,  1.36s/it]
 16%|█▋        | 10201/61904 [4:59:23<19:42:39,  1.37s/it]
 16%|█▋        | 10202/61904 [4:59:24<20:00:45,  1.39s/it]
 16%|█▋        | 10203/61904 [4:59:25<19:52:55,  1.38s/it]
 16%|█▋        | 10204/61904 [4:59:27<20:17:56,  1.41s/it]
 16%|█▋        | 10205/61904 [4:59:28<19:37:20,  1.37s/it]
 16%|█▋        | 10206/61904 [4:59:30<19:28:04,  1.36s/it]
 16%|█▋        | 10207/61904 [4:59:31<19:44:16,  1.37s/it]
 16%|█▋        | 10208/61904 [4:59:32<19:07:48,  1.33s/it]
 16%|█▋        | 10209/61904 [4:59:33<18:54:57,  1.32s/it]
 16%|█▋        | 10210/61904 [4:59:35<18:41:27,  1.30s/it]
 16%|█▋        | 10211/61904 [4:59:36<18:38:14,  1.30s/it]
 16%|█▋        | 10212/61904 [4:59:37<18:50:39,  1.31s/it]
 16%|█▋        | 10213/61904 [4:59:39<19:25:42,  1.35s/it]
 16%|█▋        | 10214/61904 [4:59:40<19:31:41,  1.36s/it]
 17%|█▋        | 10215/61904 [4:59:42<19:24:22,  1.35s/it]
 17%|█▋        | 10216/61904 [4:59:43<19:30:35,  1.36s/it]
 17%|█▋        | 10217/61904 [4:59:44<19:12:13,  1.34s/it]
 17%|█▋        | 10218/61904 [4:59:46<19:06:05,  1.33s/it]
 17%|█▋        | 10219/61904 [4:59:47<20:06:07,  1.40s/it]
 17%|█▋        | 10220/61904 [4:59:48<19:50:33,  1.38s/it]
                                                          
{'loss': 2.8126, 'learning_rate': 1.837611824192921e-07, 'epoch': 2.64}

 17%|█▋        | 10220/61904 [4:59:48<19:50:33,  1.38s/it]
 17%|█▋        | 10221/61904 [4:59:50<19:05:09,  1.33s/it]
 17%|█▋        | 10222/61904 [4:59:51<19:24:13,  1.35s/it]
 17%|█▋        | 10223/61904 [4:59:52<19:31:56,  1.36s/it]
 17%|█▋        | 10224/61904 [4:59:54<20:33:05,  1.43s/it]
 17%|█▋        | 10225/61904 [4:59:55<20:42:25,  1.44s/it]
 17%|█▋        | 10226/61904 [4:59:57<20:14:53,  1.41s/it]
 17%|█▋        | 10227/61904 [4:59:58<20:12:23,  1.41s/it]
 17%|█▋        | 10228/61904 [5:00:00<19:47:09,  1.38s/it]
 17%|█▋        | 10229/61904 [5:00:01<19:31:16,  1.36s/it]
 17%|█▋        | 10230/61904 [5:00:02<19:14:35,  1.34s/it]
 17%|█▋        | 10231/61904 [5:00:04<19:24:08,  1.35s/it]
 17%|█▋        | 10232/61904 [5:00:05<19:50:12,  1.38s/it]
 17%|█▋        | 10233/61904 [5:00:06<19:44:08,  1.38s/it]
 17%|█▋        | 10234/61904 [5:00:08<19:18:04,  1.34s/it]
 17%|█▋        | 10235/61904 [5:00:09<19:25:38,  1.35s/it]
 17%|█▋        | 10236/61904 [5:00:10<19:21:47,  1.35s/it]
 17%|█▋        | 10237/61904 [5:00:12<19:55:42,  1.39s/it]
 17%|█▋        | 10238/61904 [5:00:13<20:14:43,  1.41s/it]
 17%|█▋        | 10239/61904 [5:00:15<19:52:37,  1.39s/it]
 17%|█▋        | 10240/61904 [5:00:16<20:10:24,  1.41s/it]
                                                          
{'loss': 2.8727, 'learning_rate': 1.8372876960974977e-07, 'epoch': 2.65}

 17%|█▋        | 10240/61904 [5:00:16<20:10:24,  1.41s/it]
 17%|█▋        | 10241/61904 [5:00:17<20:10:36,  1.41s/it]
 17%|█▋        | 10242/61904 [5:00:19<19:51:03,  1.38s/it]
 17%|█▋        | 10243/61904 [5:00:20<19:41:15,  1.37s/it]
 17%|█▋        | 10244/61904 [5:00:21<19:36:28,  1.37s/it]
 17%|█▋        | 10245/61904 [5:00:23<19:52:18,  1.38s/it]
 17%|█▋        | 10246/61904 [5:00:24<19:37:12,  1.37s/it]
 17%|█▋        | 10247/61904 [5:00:26<20:11:16,  1.41s/it]
 17%|█▋        | 10248/61904 [5:00:27<19:46:28,  1.38s/it]
 17%|█▋        | 10249/61904 [5:00:28<19:45:04,  1.38s/it]
 17%|█▋        | 10250/61904 [5:00:30<19:26:05,  1.35s/it]
 17%|█▋        | 10251/61904 [5:00:31<19:17:23,  1.34s/it]
 17%|█▋        | 10252/61904 [5:00:32<19:25:10,  1.35s/it]
 17%|█▋        | 10253/61904 [5:00:34<18:52:29,  1.32s/it]
 17%|█▋        | 10254/61904 [5:00:35<19:15:54,  1.34s/it]
 17%|█▋        | 10255/61904 [5:00:36<19:26:09,  1.35s/it]
 17%|█▋        | 10256/61904 [5:00:38<19:34:04,  1.36s/it]
 17%|█▋        | 10257/61904 [5:00:39<19:18:28,  1.35s/it]
 17%|█▋        | 10258/61904 [5:00:40<19:23:11,  1.35s/it]
 17%|█▋        | 10259/61904 [5:00:42<19:49:54,  1.38s/it]
 17%|█▋        | 10260/61904 [5:00:43<19:39:32,  1.37s/it]
                                                          
{'loss': 2.8323, 'learning_rate': 1.8369635680020743e-07, 'epoch': 2.65}

 17%|█▋        | 10260/61904 [5:00:43<19:39:32,  1.37s/it]
 17%|█▋        | 10261/61904 [5:00:45<19:41:25,  1.37s/it]
 17%|█▋        | 10262/61904 [5:00:46<19:15:00,  1.34s/it]
 17%|█▋        | 10263/61904 [5:00:47<19:57:37,  1.39s/it]
 17%|█▋        | 10264/61904 [5:00:49<19:55:25,  1.39s/it]
 17%|█▋        | 10265/61904 [5:00:50<19:43:27,  1.38s/it]
 17%|█▋        | 10266/61904 [5:00:52<20:22:02,  1.42s/it]
 17%|█▋        | 10267/61904 [5:00:53<19:56:00,  1.39s/it]
 17%|█▋        | 10268/61904 [5:00:54<19:58:14,  1.39s/it]
 17%|█▋        | 10269/61904 [5:00:56<19:22:42,  1.35s/it]
 17%|█▋        | 10270/61904 [5:00:57<19:18:12,  1.35s/it]
 17%|█▋        | 10271/61904 [5:00:58<19:21:09,  1.35s/it]
 17%|█▋        | 10272/61904 [5:01:00<19:36:53,  1.37s/it]
 17%|█▋        | 10273/61904 [5:01:01<19:38:11,  1.37s/it]
 17%|█▋        | 10274/61904 [5:01:03<20:01:32,  1.40s/it]
 17%|█▋        | 10275/61904 [5:01:04<19:54:49,  1.39s/it]
 17%|█▋        | 10276/61904 [5:01:05<19:51:02,  1.38s/it]
 17%|█▋        | 10277/61904 [5:01:07<19:38:14,  1.37s/it]
 17%|█▋        | 10278/61904 [5:01:08<19:23:58,  1.35s/it]
 17%|█▋        | 10279/61904 [5:01:09<19:21:49,  1.35s/it]
 17%|█▋        | 10280/61904 [5:01:11<19:01:40,  1.33s/it]
                                                          
{'loss': 2.7787, 'learning_rate': 1.8366394399066512e-07, 'epoch': 2.66}

 17%|█▋        | 10280/61904 [5:01:11<19:01:40,  1.33s/it]
 17%|█▋        | 10281/61904 [5:01:12<19:40:15,  1.37s/it]
 17%|█▋        | 10282/61904 [5:01:13<19:15:39,  1.34s/it]
 17%|█▋        | 10283/61904 [5:01:15<19:05:04,  1.33s/it]
 17%|█▋        | 10284/61904 [5:01:16<20:07:18,  1.40s/it]
 17%|█▋        | 10285/61904 [5:01:18<19:33:47,  1.36s/it]
 17%|█▋        | 10286/61904 [5:01:19<19:12:04,  1.34s/it]
 17%|█▋        | 10287/61904 [5:01:20<18:44:04,  1.31s/it]
 17%|█▋        | 10288/61904 [5:01:21<18:47:48,  1.31s/it]
 17%|█▋        | 10289/61904 [5:01:23<19:24:44,  1.35s/it]
 17%|█▋        | 10290/61904 [5:01:24<19:01:55,  1.33s/it]
 17%|█▋        | 10291/61904 [5:01:25<19:09:58,  1.34s/it]
 17%|█▋        | 10292/61904 [5:01:27<18:52:12,  1.32s/it]
 17%|█▋        | 10293/61904 [5:01:28<18:54:07,  1.32s/it]
 17%|█▋        | 10294/61904 [5:01:30<20:02:36,  1.40s/it]
 17%|█▋        | 10295/61904 [5:01:31<20:28:00,  1.43s/it]
 17%|█▋        | 10296/61904 [5:01:33<20:24:27,  1.42s/it]
 17%|█▋        | 10297/61904 [5:01:34<20:21:04,  1.42s/it]
 17%|█▋        | 10298/61904 [5:01:35<19:42:20,  1.37s/it]
 17%|█▋        | 10299/61904 [5:01:36<19:19:43,  1.35s/it]
 17%|█▋        | 10300/61904 [5:01:38<19:01:38,  1.33s/it]
                                                          
{'loss': 2.8147, 'learning_rate': 1.8363153118112275e-07, 'epoch': 2.66}

 17%|█▋        | 10300/61904 [5:01:38<19:01:38,  1.33s/it]
 17%|█▋        | 10301/61904 [5:01:39<18:49:10,  1.31s/it]
 17%|█▋        | 10302/61904 [5:01:40<19:07:35,  1.33s/it]
 17%|█▋        | 10303/61904 [5:01:42<20:03:10,  1.40s/it]
 17%|█▋        | 10304/61904 [5:01:43<20:06:05,  1.40s/it]
 17%|█▋        | 10305/61904 [5:01:45<20:31:36,  1.43s/it]
 17%|█▋        | 10306/61904 [5:01:46<20:05:26,  1.40s/it]
 17%|█▋        | 10307/61904 [5:01:48<19:40:40,  1.37s/it]
 17%|█▋        | 10308/61904 [5:01:49<19:51:45,  1.39s/it]
 17%|█▋        | 10309/61904 [5:01:50<20:29:07,  1.43s/it]
 17%|█▋        | 10310/61904 [5:01:52<19:49:00,  1.38s/it]
 17%|█▋        | 10311/61904 [5:01:53<19:59:55,  1.40s/it]
 17%|█▋        | 10312/61904 [5:01:55<20:14:36,  1.41s/it]
 17%|█▋        | 10313/61904 [5:01:56<20:33:42,  1.43s/it]
 17%|█▋        | 10314/61904 [5:01:57<20:21:53,  1.42s/it]
 17%|█▋        | 10315/61904 [5:01:59<19:39:07,  1.37s/it]
 17%|█▋        | 10316/61904 [5:02:00<19:40:47,  1.37s/it]
 17%|█▋        | 10317/61904 [5:02:02<20:11:54,  1.41s/it]
 17%|█▋        | 10318/61904 [5:02:03<19:37:15,  1.37s/it]
 17%|█▋        | 10319/61904 [5:02:04<19:23:38,  1.35s/it]
 17%|█▋        | 10320/61904 [5:02:06<19:13:46,  1.34s/it]
                                                          
{'loss': 2.7373, 'learning_rate': 1.8359911837158044e-07, 'epoch': 2.67}

 17%|█▋        | 10320/61904 [5:02:06<19:13:46,  1.34s/it]
 17%|█▋        | 10321/61904 [5:02:07<19:14:55,  1.34s/it]
 17%|█▋        | 10322/61904 [5:02:08<18:44:42,  1.31s/it]
 17%|█▋        | 10323/61904 [5:02:09<19:03:39,  1.33s/it]
 17%|█▋        | 10324/61904 [5:02:11<19:38:33,  1.37s/it]
 17%|█▋        | 10325/61904 [5:02:12<19:24:30,  1.35s/it]
 17%|█▋        | 10326/61904 [5:02:14<19:40:00,  1.37s/it]
 17%|█▋        | 10327/61904 [5:02:15<19:50:35,  1.39s/it]
 17%|█▋        | 10328/61904 [5:02:17<20:18:44,  1.42s/it]
 17%|█▋        | 10329/61904 [5:02:18<20:09:15,  1.41s/it]
 17%|█▋        | 10330/61904 [5:02:19<19:58:07,  1.39s/it]
 17%|█▋        | 10331/61904 [5:02:21<20:10:36,  1.41s/it]
 17%|█▋        | 10332/61904 [5:02:22<20:32:30,  1.43s/it]
 17%|█▋        | 10333/61904 [5:02:24<20:22:10,  1.42s/it]
 17%|█▋        | 10334/61904 [5:02:25<19:57:28,  1.39s/it]
 17%|█▋        | 10335/61904 [5:02:26<19:23:34,  1.35s/it]
 17%|█▋        | 10336/61904 [5:02:28<19:15:38,  1.34s/it]
 17%|█▋        | 10337/61904 [5:02:29<19:10:37,  1.34s/it]
 17%|█▋        | 10338/61904 [5:02:30<19:57:37,  1.39s/it]
 17%|█▋        | 10339/61904 [5:02:32<20:16:44,  1.42s/it]
 17%|█▋        | 10340/61904 [5:02:33<19:59:21,  1.40s/it]
                                                          
{'loss': 2.8365, 'learning_rate': 1.835667055620381e-07, 'epoch': 2.67}

 17%|█▋        | 10340/61904 [5:02:33<19:59:21,  1.40s/it]
 17%|█▋        | 10341/61904 [5:02:35<20:23:33,  1.42s/it]
 17%|█▋        | 10342/61904 [5:02:36<20:25:25,  1.43s/it]
 17%|█▋        | 10343/61904 [5:02:37<20:02:53,  1.40s/it]
 17%|█▋        | 10344/61904 [5:02:39<19:53:20,  1.39s/it]
 17%|█▋        | 10345/61904 [5:02:40<19:58:50,  1.40s/it]
 17%|█▋        | 10346/61904 [5:02:42<20:17:08,  1.42s/it]
 17%|█▋        | 10347/61904 [5:02:43<20:27:00,  1.43s/it]
 17%|█▋        | 10348/61904 [5:02:45<20:17:30,  1.42s/it]
 17%|█▋        | 10349/61904 [5:02:46<20:09:34,  1.41s/it]
 17%|█▋        | 10350/61904 [5:02:47<19:45:14,  1.38s/it]
 17%|█▋        | 10351/61904 [5:02:49<19:30:49,  1.36s/it]
 17%|█▋        | 10352/61904 [5:02:50<19:20:07,  1.35s/it]
 17%|█▋        | 10353/61904 [5:02:51<19:35:36,  1.37s/it]
 17%|█▋        | 10354/61904 [5:02:53<19:22:17,  1.35s/it]
 17%|█▋        | 10355/61904 [5:02:54<19:43:02,  1.38s/it]
 17%|█▋        | 10356/61904 [5:02:55<19:25:09,  1.36s/it]
 17%|█▋        | 10357/61904 [5:02:57<20:07:29,  1.41s/it]
 17%|█▋        | 10358/61904 [5:02:58<20:40:09,  1.44s/it]
 17%|█▋        | 10359/61904 [5:03:00<20:11:09,  1.41s/it]
 17%|█▋        | 10360/61904 [5:03:01<19:28:36,  1.36s/it]
                                                          
{'loss': 2.7914, 'learning_rate': 1.8353429275249577e-07, 'epoch': 2.68}

 17%|█▋        | 10360/61904 [5:03:01<19:28:36,  1.36s/it]
 17%|█▋        | 10361/61904 [5:03:02<19:27:48,  1.36s/it]
 17%|█▋        | 10362/61904 [5:03:04<19:45:54,  1.38s/it]
 17%|█▋        | 10363/61904 [5:03:05<19:42:30,  1.38s/it]
 17%|█▋        | 10364/61904 [5:03:07<19:37:43,  1.37s/it]
 17%|█▋        | 10365/61904 [5:03:08<19:32:47,  1.37s/it]
 17%|█▋        | 10366/61904 [5:03:09<19:09:32,  1.34s/it]
 17%|█▋        | 10367/61904 [5:03:11<19:27:34,  1.36s/it]
 17%|█▋        | 10368/61904 [5:03:12<19:14:22,  1.34s/it]
 17%|█▋        | 10369/61904 [5:03:13<19:08:44,  1.34s/it]
 17%|█▋        | 10370/61904 [5:03:15<19:09:33,  1.34s/it]
 17%|█▋        | 10371/61904 [5:03:16<19:07:43,  1.34s/it]
 17%|█▋        | 10372/61904 [5:03:17<18:51:57,  1.32s/it]
 17%|█▋        | 10373/61904 [5:03:18<18:59:46,  1.33s/it]
 17%|█▋        | 10374/61904 [5:03:20<19:04:35,  1.33s/it]
 17%|█▋        | 10375/61904 [5:03:21<19:22:40,  1.35s/it]
 17%|█▋        | 10376/61904 [5:03:23<19:15:22,  1.35s/it]
 17%|█▋        | 10377/61904 [5:03:24<20:29:12,  1.43s/it]
 17%|█▋        | 10378/61904 [5:03:26<20:32:09,  1.43s/it]
 17%|█▋        | 10379/61904 [5:03:27<20:30:59,  1.43s/it]
 17%|█▋        | 10380/61904 [5:03:28<19:36:32,  1.37s/it]
                                                          
{'loss': 2.8569, 'learning_rate': 1.8350187994295346e-07, 'epoch': 2.68}

 17%|█▋        | 10380/61904 [5:03:28<19:36:32,  1.37s/it]
 17%|█▋        | 10381/61904 [5:03:30<19:45:54,  1.38s/it]
 17%|█▋        | 10382/61904 [5:03:31<19:32:47,  1.37s/it]
 17%|█▋        | 10383/61904 [5:03:32<19:36:06,  1.37s/it]
 17%|█▋        | 10384/61904 [5:03:34<19:07:46,  1.34s/it]
 17%|█▋        | 10385/61904 [5:03:35<19:25:40,  1.36s/it]
 17%|█▋        | 10386/61904 [5:03:37<20:10:31,  1.41s/it]
 17%|█▋        | 10387/61904 [5:03:38<20:17:26,  1.42s/it]
 17%|█▋        | 10388/61904 [5:03:39<19:48:55,  1.38s/it]
 17%|█▋        | 10389/61904 [5:03:41<20:22:07,  1.42s/it]
 17%|█▋        | 10390/61904 [5:03:42<20:56:42,  1.46s/it]
 17%|█▋        | 10391/61904 [5:03:44<20:48:24,  1.45s/it]
 17%|█▋        | 10392/61904 [5:03:45<20:31:16,  1.43s/it]
 17%|█▋        | 10393/61904 [5:03:47<20:21:50,  1.42s/it]
 17%|█▋        | 10394/61904 [5:03:48<20:06:35,  1.41s/it]
 17%|█▋        | 10395/61904 [5:03:49<20:00:01,  1.40s/it]
 17%|█▋        | 10396/61904 [5:03:51<19:54:35,  1.39s/it]
 17%|█▋        | 10397/61904 [5:03:52<20:04:31,  1.40s/it]
 17%|█▋        | 10398/61904 [5:03:54<19:53:45,  1.39s/it]
 17%|█▋        | 10399/61904 [5:03:55<19:48:30,  1.38s/it]
 17%|█▋        | 10400/61904 [5:03:56<20:18:17,  1.42s/it]
                                                          
{'loss': 2.8851, 'learning_rate': 1.8346946713341112e-07, 'epoch': 2.69}

 17%|█▋        | 10400/61904 [5:03:56<20:18:17,  1.42s/it]
 17%|█▋        | 10401/61904 [5:03:58<19:32:53,  1.37s/it]
 17%|█▋        | 10402/61904 [5:03:59<19:14:17,  1.34s/it]
 17%|█▋        | 10403/61904 [5:04:00<19:03:44,  1.33s/it]
 17%|█▋        | 10404/61904 [5:04:02<19:14:23,  1.34s/it]
 17%|█▋        | 10405/61904 [5:04:03<19:55:55,  1.39s/it]
 17%|█▋        | 10406/61904 [5:04:05<20:17:51,  1.42s/it]
 17%|█▋        | 10407/61904 [5:04:06<20:13:09,  1.41s/it]
 17%|█▋        | 10408/61904 [5:04:07<19:44:03,  1.38s/it]
 17%|█▋        | 10409/61904 [5:04:09<19:47:03,  1.38s/it]
 17%|█▋        | 10410/61904 [5:04:10<19:51:21,  1.39s/it]
 17%|█▋        | 10411/61904 [5:04:11<19:13:22,  1.34s/it]
 17%|█▋        | 10412/61904 [5:04:13<19:09:19,  1.34s/it]
 17%|█▋        | 10413/61904 [5:04:14<19:43:33,  1.38s/it]
 17%|█▋        | 10414/61904 [5:04:15<19:27:11,  1.36s/it]
 17%|█▋        | 10415/61904 [5:04:17<20:19:34,  1.42s/it]
 17%|█▋        | 10416/61904 [5:04:18<19:39:11,  1.37s/it]
 17%|█▋        | 10417/61904 [5:04:20<19:05:24,  1.33s/it]
 17%|█▋        | 10418/61904 [5:04:21<18:57:17,  1.33s/it]
 17%|█▋        | 10419/61904 [5:04:22<19:06:47,  1.34s/it]
 17%|█▋        | 10420/61904 [5:04:24<19:29:15,  1.36s/it]
                                                          
{'loss': 2.8061, 'learning_rate': 1.8343705432386878e-07, 'epoch': 2.69}

 17%|█▋        | 10420/61904 [5:04:24<19:29:15,  1.36s/it]
 17%|█▋        | 10421/61904 [5:04:25<18:55:01,  1.32s/it]
 17%|█▋        | 10422/61904 [5:04:26<19:12:17,  1.34s/it]
 17%|█▋        | 10423/61904 [5:04:28<19:25:13,  1.36s/it]
 17%|█▋        | 10424/61904 [5:04:29<19:38:00,  1.37s/it]
 17%|█▋        | 10425/61904 [5:04:30<19:30:20,  1.36s/it]
 17%|█▋        | 10426/61904 [5:04:32<19:35:44,  1.37s/it]
 17%|█▋        | 10427/61904 [5:04:33<19:28:35,  1.36s/it]
 17%|█▋        | 10428/61904 [5:04:34<19:13:06,  1.34s/it]
 17%|█▋        | 10429/61904 [5:04:36<19:03:58,  1.33s/it]
 17%|█▋        | 10430/61904 [5:04:37<19:28:32,  1.36s/it]
 17%|█▋        | 10431/61904 [5:04:38<19:18:32,  1.35s/it]
 17%|█▋        | 10432/61904 [5:04:40<19:16:42,  1.35s/it]
 17%|█▋        | 10433/61904 [5:04:41<19:05:30,  1.34s/it]
 17%|█▋        | 10434/61904 [5:04:42<18:59:07,  1.33s/it]
 17%|█▋        | 10435/61904 [5:04:44<19:06:23,  1.34s/it]
 17%|█▋        | 10436/61904 [5:04:45<19:09:01,  1.34s/it]
 17%|█▋        | 10437/61904 [5:04:46<18:34:50,  1.30s/it]
 17%|█▋        | 10438/61904 [5:04:48<19:19:15,  1.35s/it]
 17%|█▋        | 10439/61904 [5:04:49<19:26:57,  1.36s/it]
 17%|█▋        | 10440/61904 [5:04:51<19:50:53,  1.39s/it]
                                                          
{'loss': 2.8493, 'learning_rate': 1.8340464151432647e-07, 'epoch': 2.7}

 17%|█▋        | 10440/61904 [5:04:51<19:50:53,  1.39s/it]
 17%|█▋        | 10441/61904 [5:04:52<19:57:55,  1.40s/it]
 17%|█▋        | 10442/61904 [5:04:53<19:45:06,  1.38s/it]
 17%|█▋        | 10443/61904 [5:04:55<19:51:54,  1.39s/it]
 17%|█▋        | 10444/61904 [5:04:56<19:45:24,  1.38s/it]
 17%|█▋        | 10445/61904 [5:04:58<19:32:13,  1.37s/it]
 17%|█▋        | 10446/61904 [5:04:59<19:14:06,  1.35s/it]
 17%|█▋        | 10447/61904 [5:05:00<19:36:01,  1.37s/it]
 17%|█▋        | 10448/61904 [5:05:02<19:46:43,  1.38s/it]
 17%|█▋        | 10449/61904 [5:05:03<19:20:38,  1.35s/it]
 17%|█▋        | 10450/61904 [5:05:04<19:45:13,  1.38s/it]
 17%|█▋        | 10451/61904 [5:05:06<20:35:23,  1.44s/it]
 17%|█▋        | 10452/61904 [5:05:07<20:15:10,  1.42s/it]
 17%|█▋        | 10453/61904 [5:05:09<19:51:42,  1.39s/it]
 17%|█▋        | 10454/61904 [5:05:10<19:06:22,  1.34s/it]
 17%|█▋        | 10455/61904 [5:05:11<18:44:02,  1.31s/it]
 17%|█▋        | 10456/61904 [5:05:13<19:01:23,  1.33s/it]
 17%|█▋        | 10457/61904 [5:05:14<19:08:47,  1.34s/it]
 17%|█▋        | 10458/61904 [5:05:15<18:44:44,  1.31s/it]
 17%|█▋        | 10459/61904 [5:05:16<18:49:05,  1.32s/it]
 17%|█▋        | 10460/61904 [5:05:18<19:35:04,  1.37s/it]
                                                          
{'loss': 2.7935, 'learning_rate': 1.8337222870478413e-07, 'epoch': 2.7}

 17%|█▋        | 10460/61904 [5:05:18<19:35:04,  1.37s/it]
 17%|█▋        | 10461/61904 [5:05:19<19:39:37,  1.38s/it]
 17%|█▋        | 10462/61904 [5:05:21<20:00:24,  1.40s/it]
 17%|█▋        | 10463/61904 [5:05:22<20:04:44,  1.41s/it]
 17%|█▋        | 10464/61904 [5:05:24<20:08:38,  1.41s/it]
 17%|█▋        | 10465/61904 [5:05:25<20:02:59,  1.40s/it]
 17%|█▋        | 10466/61904 [5:05:27<21:01:42,  1.47s/it]
 17%|█▋        | 10467/61904 [5:05:28<20:50:20,  1.46s/it]
 17%|█▋        | 10468/61904 [5:05:29<20:21:10,  1.42s/it]
 17%|█▋        | 10469/61904 [5:05:31<20:49:03,  1.46s/it]
 17%|█▋        | 10470/61904 [5:05:32<20:40:18,  1.45s/it]
 17%|█▋        | 10471/61904 [5:05:34<20:06:58,  1.41s/it]
 17%|█▋        | 10472/61904 [5:05:35<19:51:17,  1.39s/it]
 17%|█▋        | 10473/61904 [5:05:37<20:12:58,  1.42s/it]
 17%|█▋        | 10474/61904 [5:05:38<19:54:05,  1.39s/it]
 17%|█▋        | 10475/61904 [5:05:39<19:23:39,  1.36s/it]
 17%|█▋        | 10476/61904 [5:05:40<18:58:31,  1.33s/it]
 17%|█▋        | 10477/61904 [5:05:42<19:35:38,  1.37s/it]
 17%|█▋        | 10478/61904 [5:05:43<19:35:31,  1.37s/it]
 17%|█▋        | 10479/61904 [5:05:45<19:59:55,  1.40s/it]
 17%|█▋        | 10480/61904 [5:05:46<20:05:38,  1.41s/it]
                                                          
{'loss': 2.8418, 'learning_rate': 1.833398158952418e-07, 'epoch': 2.71}

 17%|█▋        | 10480/61904 [5:05:46<20:05:38,  1.41s/it]
 17%|█▋        | 10481/61904 [5:05:48<20:18:53,  1.42s/it]
 17%|█▋        | 10482/61904 [5:05:49<20:26:30,  1.43s/it]
 17%|█▋        | 10483/61904 [5:05:50<19:38:37,  1.38s/it]
 17%|█▋        | 10484/61904 [5:05:52<19:23:41,  1.36s/it]
 17%|█▋        | 10485/61904 [5:05:53<19:14:46,  1.35s/it]
 17%|█▋        | 10486/61904 [5:05:54<19:50:23,  1.39s/it]
 17%|█▋        | 10487/61904 [5:05:56<19:51:15,  1.39s/it]
 17%|█▋        | 10488/61904 [5:05:57<19:42:01,  1.38s/it]
 17%|█▋        | 10489/61904 [5:05:59<19:35:02,  1.37s/it]
 17%|█▋        | 10490/61904 [5:06:00<19:34:38,  1.37s/it]
 17%|█▋        | 10491/61904 [5:06:01<19:21:34,  1.36s/it]
 17%|█▋        | 10492/61904 [5:06:03<19:15:50,  1.35s/it]
 17%|█▋        | 10493/61904 [5:06:04<20:00:19,  1.40s/it]
 17%|█▋        | 10494/61904 [5:06:05<19:16:32,  1.35s/it]
 17%|█▋        | 10495/61904 [5:06:07<19:51:56,  1.39s/it]
 17%|█▋        | 10496/61904 [5:06:08<20:19:12,  1.42s/it]
 17%|█▋        | 10497/61904 [5:06:10<20:06:34,  1.41s/it]
 17%|█▋        | 10498/61904 [5:06:11<19:56:16,  1.40s/it]
 17%|█▋        | 10499/61904 [5:06:12<19:17:47,  1.35s/it]
 17%|█▋        | 10500/61904 [5:06:14<19:43:23,  1.38s/it]
                                                          
{'loss': 2.7704, 'learning_rate': 1.8330740308569948e-07, 'epoch': 2.71}

 17%|█▋        | 10500/61904 [5:06:14<19:43:23,  1.38s/it]
 17%|█▋        | 10501/61904 [5:06:15<20:20:32,  1.42s/it]
 17%|█▋        | 10502/61904 [5:06:17<20:29:14,  1.43s/it]
 17%|█▋        | 10503/61904 [5:06:18<21:05:21,  1.48s/it]
 17%|█▋        | 10504/61904 [5:06:20<21:07:03,  1.48s/it]
 17%|█▋        | 10505/61904 [5:06:21<20:38:40,  1.45s/it]
 17%|█▋        | 10506/61904 [5:06:22<20:04:09,  1.41s/it]
 17%|█▋        | 10507/61904 [5:06:24<20:04:29,  1.41s/it]
 17%|█▋        | 10508/61904 [5:06:25<19:31:26,  1.37s/it]
 17%|█▋        | 10509/61904 [5:06:27<20:07:19,  1.41s/it]
 17%|█▋        | 10510/61904 [5:06:28<20:05:39,  1.41s/it]
 17%|█▋        | 10511/61904 [5:06:29<19:46:30,  1.39s/it]
 17%|█▋        | 10512/61904 [5:06:31<20:20:27,  1.42s/it]
 17%|█▋        | 10513/61904 [5:06:32<20:05:43,  1.41s/it]
 17%|█▋        | 10514/61904 [5:06:34<19:44:58,  1.38s/it]
 17%|█▋        | 10515/61904 [5:06:35<20:05:29,  1.41s/it]
 17%|█▋        | 10516/61904 [5:06:36<20:12:59,  1.42s/it]
 17%|█▋        | 10517/61904 [5:06:38<20:14:54,  1.42s/it]
 17%|█▋        | 10518/61904 [5:06:39<19:15:06,  1.35s/it]
 17%|█▋        | 10519/61904 [5:06:40<19:01:41,  1.33s/it]
 17%|█▋        | 10520/61904 [5:06:42<19:55:05,  1.40s/it]
                                                          
{'loss': 2.87, 'learning_rate': 1.8327499027615711e-07, 'epoch': 2.72}

 17%|█▋        | 10520/61904 [5:06:42<19:55:05,  1.40s/it]
 17%|█▋        | 10521/61904 [5:06:43<19:55:33,  1.40s/it]
 17%|█▋        | 10522/61904 [5:06:45<20:13:17,  1.42s/it]
 17%|█▋        | 10523/61904 [5:06:46<20:12:48,  1.42s/it]
 17%|█▋        | 10524/61904 [5:06:47<19:44:04,  1.38s/it]
 17%|█▋        | 10525/61904 [5:06:49<19:05:44,  1.34s/it]
 17%|█▋        | 10526/61904 [5:06:50<19:18:00,  1.35s/it]
 17%|█▋        | 10527/61904 [5:06:51<18:51:37,  1.32s/it]
 17%|█▋        | 10528/61904 [5:06:53<19:31:33,  1.37s/it]
 17%|█▋        | 10529/61904 [5:06:54<19:11:07,  1.34s/it]
 17%|█▋        | 10530/61904 [5:06:56<19:24:05,  1.36s/it]
 17%|█▋        | 10531/61904 [5:06:57<20:00:16,  1.40s/it]
 17%|█▋        | 10532/61904 [5:06:58<19:41:24,  1.38s/it]
 17%|█▋        | 10533/61904 [5:07:00<20:08:50,  1.41s/it]
 17%|█▋        | 10534/61904 [5:07:01<19:43:49,  1.38s/it]
 17%|█▋        | 10535/61904 [5:07:03<19:44:53,  1.38s/it]
 17%|█▋        | 10536/61904 [5:07:04<19:49:09,  1.39s/it]
 17%|█▋        | 10537/61904 [5:07:05<19:28:02,  1.36s/it]
 17%|█▋        | 10538/61904 [5:07:07<19:27:54,  1.36s/it]
 17%|█▋        | 10539/61904 [5:07:08<19:30:35,  1.37s/it]
 17%|█▋        | 10540/61904 [5:07:09<19:33:42,  1.37s/it]
                                                          
{'loss': 2.8444, 'learning_rate': 1.832425774666148e-07, 'epoch': 2.72}

 17%|█▋        | 10540/61904 [5:07:09<19:33:42,  1.37s/it]
 17%|█▋        | 10541/61904 [5:07:11<19:53:03,  1.39s/it]
 17%|█▋        | 10542/61904 [5:07:12<19:24:37,  1.36s/it]
 17%|█▋        | 10543/61904 [5:07:13<19:34:11,  1.37s/it]
 17%|█▋        | 10544/61904 [5:07:15<19:16:58,  1.35s/it]
 17%|█▋        | 10545/61904 [5:07:16<18:54:31,  1.33s/it]
 17%|█▋        | 10546/61904 [5:07:17<19:09:42,  1.34s/it]
 17%|█▋        | 10547/61904 [5:07:19<18:57:50,  1.33s/it]
 17%|█▋        | 10548/61904 [5:07:20<19:11:57,  1.35s/it]
 17%|█▋        | 10549/61904 [5:07:21<19:16:42,  1.35s/it]
 17%|█▋        | 10550/61904 [5:07:23<18:59:18,  1.33s/it]
 17%|█▋        | 10551/61904 [5:07:24<18:58:56,  1.33s/it]
 17%|█▋        | 10552/61904 [5:07:25<18:48:39,  1.32s/it]
 17%|█▋        | 10553/61904 [5:07:27<19:09:58,  1.34s/it]
 17%|█▋        | 10554/61904 [5:07:28<20:15:29,  1.42s/it]
 17%|█▋        | 10555/61904 [5:07:30<20:49:34,  1.46s/it]
 17%|█▋        | 10556/61904 [5:07:31<20:18:56,  1.42s/it]
 17%|█▋        | 10557/61904 [5:07:33<20:36:17,  1.44s/it]
 17%|█▋        | 10558/61904 [5:07:34<19:53:39,  1.39s/it]
 17%|█▋        | 10559/61904 [5:07:35<19:31:26,  1.37s/it]
 17%|█▋        | 10560/61904 [5:07:37<19:55:14,  1.40s/it]
                                                          
{'loss': 2.7719, 'learning_rate': 1.8321016465707246e-07, 'epoch': 2.73}

 17%|█▋        | 10560/61904 [5:07:37<19:55:14,  1.40s/it]
 17%|█▋        | 10561/61904 [5:07:38<19:32:57,  1.37s/it]
 17%|█▋        | 10562/61904 [5:07:39<18:58:29,  1.33s/it]
 17%|█▋        | 10563/61904 [5:07:41<18:53:01,  1.32s/it]
 17%|█▋        | 10564/61904 [5:07:42<19:25:02,  1.36s/it]
 17%|█▋        | 10565/61904 [5:07:43<19:09:33,  1.34s/it]
 17%|█▋        | 10566/61904 [5:07:45<19:24:47,  1.36s/it]
 17%|█▋        | 10567/61904 [5:07:46<19:38:51,  1.38s/it]
 17%|█▋        | 10568/61904 [5:07:48<20:01:34,  1.40s/it]
 17%|█▋        | 10569/61904 [5:07:49<19:56:41,  1.40s/it]
 17%|█▋        | 10570/61904 [5:07:50<19:29:47,  1.37s/it]
 17%|█▋        | 10571/61904 [5:07:52<19:21:24,  1.36s/it]
 17%|█▋        | 10572/61904 [5:07:53<19:39:02,  1.38s/it]
 17%|█▋        | 10573/61904 [5:07:54<19:24:45,  1.36s/it]
 17%|█▋        | 10574/61904 [5:07:56<19:17:05,  1.35s/it]
 17%|█▋        | 10575/61904 [5:07:57<19:01:11,  1.33s/it]
 17%|█▋        | 10576/61904 [5:07:58<19:06:38,  1.34s/it]
 17%|█▋        | 10577/61904 [5:08:00<19:02:05,  1.34s/it]
 17%|█▋        | 10578/61904 [5:08:01<19:22:05,  1.36s/it]
 17%|█▋        | 10579/61904 [5:08:02<19:04:39,  1.34s/it]
 17%|█▋        | 10580/61904 [5:08:04<19:23:08,  1.36s/it]
                                                          
{'loss': 2.823, 'learning_rate': 1.8317775184753013e-07, 'epoch': 2.73}

 17%|█▋        | 10580/61904 [5:08:04<19:23:08,  1.36s/it]
 17%|█▋        | 10581/61904 [5:08:05<19:24:36,  1.36s/it]
 17%|█▋        | 10582/61904 [5:08:07<19:18:40,  1.35s/it]
 17%|█▋        | 10583/61904 [5:08:08<18:43:43,  1.31s/it]
 17%|█▋        | 10584/61904 [5:08:09<19:03:31,  1.34s/it]
 17%|█▋        | 10585/61904 [5:08:11<19:26:20,  1.36s/it]
 17%|█▋        | 10586/61904 [5:08:12<19:00:11,  1.33s/it]
 17%|█▋        | 10587/61904 [5:08:13<19:22:13,  1.36s/it]
 17%|█▋        | 10588/61904 [5:08:15<19:50:01,  1.39s/it]
 17%|█▋        | 10589/61904 [5:08:16<19:32:53,  1.37s/it]
 17%|█▋        | 10590/61904 [5:08:17<19:32:18,  1.37s/it]
 17%|█▋        | 10591/61904 [5:08:19<19:10:58,  1.35s/it]
 17%|█▋        | 10592/61904 [5:08:20<19:31:03,  1.37s/it]
 17%|█▋        | 10593/61904 [5:08:22<19:14:18,  1.35s/it]
 17%|█▋        | 10594/61904 [5:08:23<18:59:35,  1.33s/it]
 17%|█▋        | 10595/61904 [5:08:24<19:26:13,  1.36s/it]
 17%|█▋        | 10596/61904 [5:08:26<19:22:54,  1.36s/it]
 17%|█▋        | 10597/61904 [5:08:27<19:27:31,  1.37s/it]
 17%|█▋        | 10598/61904 [5:08:28<19:38:33,  1.38s/it]
 17%|█▋        | 10599/61904 [5:08:30<19:27:34,  1.37s/it]
 17%|█▋        | 10600/61904 [5:08:31<19:20:19,  1.36s/it]
                                                          
{'loss': 2.8562, 'learning_rate': 1.8314533903798782e-07, 'epoch': 2.74}

 17%|█▋        | 10600/61904 [5:08:31<19:20:19,  1.36s/it]
 17%|█▋        | 10601/61904 [5:08:32<18:55:48,  1.33s/it]
 17%|█▋        | 10602/61904 [5:08:34<18:55:27,  1.33s/it]
 17%|█▋        | 10603/61904 [5:08:35<19:06:07,  1.34s/it]
 17%|█▋        | 10604/61904 [5:08:36<19:17:26,  1.35s/it]
 17%|█▋        | 10605/61904 [5:08:38<18:54:20,  1.33s/it]
 17%|█▋        | 10606/61904 [5:08:39<19:36:50,  1.38s/it]
 17%|█▋        | 10607/61904 [5:08:40<19:06:25,  1.34s/it]
 17%|█▋        | 10608/61904 [5:08:42<18:54:39,  1.33s/it]
 17%|█▋        | 10609/61904 [5:08:43<19:12:45,  1.35s/it]
 17%|█▋        | 10610/61904 [5:08:44<18:42:43,  1.31s/it]
 17%|█▋        | 10611/61904 [5:08:46<18:59:24,  1.33s/it]
 17%|█▋        | 10612/61904 [5:08:47<19:10:45,  1.35s/it]
 17%|█▋        | 10613/61904 [5:08:48<19:23:54,  1.36s/it]
 17%|█▋        | 10614/61904 [5:08:50<18:59:30,  1.33s/it]
 17%|█▋        | 10615/61904 [5:08:51<19:24:17,  1.36s/it]
 17%|█▋        | 10616/61904 [5:08:53<19:18:02,  1.35s/it]
 17%|█▋        | 10617/61904 [5:08:54<18:53:02,  1.33s/it]
 17%|█▋        | 10618/61904 [5:08:55<18:44:39,  1.32s/it]
 17%|█▋        | 10619/61904 [5:08:56<18:58:22,  1.33s/it]
 17%|█▋        | 10620/61904 [5:08:58<18:36:06,  1.31s/it]
                                                          
{'loss': 2.8903, 'learning_rate': 1.8311292622844548e-07, 'epoch': 2.74}

 17%|█▋        | 10620/61904 [5:08:58<18:36:06,  1.31s/it]
 17%|█▋        | 10621/61904 [5:08:59<18:51:40,  1.32s/it]
 17%|█▋        | 10622/61904 [5:09:00<19:11:49,  1.35s/it]
 17%|█▋        | 10623/61904 [5:09:02<19:20:57,  1.36s/it]
 17%|█▋        | 10624/61904 [5:09:03<19:40:47,  1.38s/it]
 17%|█▋        | 10625/61904 [5:09:05<20:02:12,  1.41s/it]
 17%|█▋        | 10626/61904 [5:09:06<19:29:03,  1.37s/it]
 17%|█▋        | 10627/61904 [5:09:07<19:24:16,  1.36s/it]
 17%|█▋        | 10628/61904 [5:09:09<19:05:00,  1.34s/it]
 17%|█▋        | 10629/61904 [5:09:10<19:16:21,  1.35s/it]
 17%|█▋        | 10630/61904 [5:09:11<19:20:06,  1.36s/it]
 17%|█▋        | 10631/61904 [5:09:13<18:51:21,  1.32s/it]
 17%|█▋        | 10632/61904 [5:09:14<19:11:53,  1.35s/it]
 17%|█▋        | 10633/61904 [5:09:15<19:04:39,  1.34s/it]
 17%|█▋        | 10634/61904 [5:09:17<18:42:51,  1.31s/it]
 17%|█▋        | 10635/61904 [5:09:18<20:04:30,  1.41s/it]
 17%|█▋        | 10636/61904 [5:09:20<20:13:50,  1.42s/it]
 17%|█▋        | 10637/61904 [5:09:21<19:43:13,  1.38s/it]
 17%|█▋        | 10638/61904 [5:09:23<20:19:01,  1.43s/it]
 17%|█▋        | 10639/61904 [5:09:24<19:57:37,  1.40s/it]
 17%|█▋        | 10640/61904 [5:09:25<19:19:12,  1.36s/it]
                                                          
{'loss': 2.8069, 'learning_rate': 1.8308051341890314e-07, 'epoch': 2.75}

 17%|█▋        | 10640/61904 [5:09:25<19:19:12,  1.36s/it]
 17%|█▋        | 10641/61904 [5:09:26<19:12:56,  1.35s/it]
 17%|█▋        | 10642/61904 [5:09:28<19:29:49,  1.37s/it]
 17%|█▋        | 10643/61904 [5:09:29<20:02:09,  1.41s/it]
 17%|█▋        | 10644/61904 [5:09:31<19:54:50,  1.40s/it]
 17%|█▋        | 10645/61904 [5:09:32<20:45:57,  1.46s/it]
 17%|█▋        | 10646/61904 [5:09:34<20:16:25,  1.42s/it]
 17%|█▋        | 10647/61904 [5:09:35<19:46:28,  1.39s/it]
 17%|█▋        | 10648/61904 [5:09:37<20:19:29,  1.43s/it]
 17%|█▋        | 10649/61904 [5:09:38<20:17:05,  1.42s/it]
 17%|█▋        | 10650/61904 [5:09:39<20:27:27,  1.44s/it]
 17%|█▋        | 10651/61904 [5:09:41<20:06:07,  1.41s/it]
 17%|█▋        | 10652/61904 [5:09:42<19:37:14,  1.38s/it]
 17%|█▋        | 10653/61904 [5:09:43<19:16:27,  1.35s/it]
 17%|█▋        | 10654/61904 [5:09:45<18:46:22,  1.32s/it]
 17%|█▋        | 10655/61904 [5:09:46<18:57:07,  1.33s/it]
 17%|█▋        | 10656/61904 [5:09:47<18:53:42,  1.33s/it]
 17%|█▋        | 10657/61904 [5:09:49<19:13:56,  1.35s/it]
 17%|█▋        | 10658/61904 [5:09:50<19:32:06,  1.37s/it]
 17%|█▋        | 10659/61904 [5:09:51<19:08:46,  1.35s/it]
 17%|█▋        | 10660/61904 [5:09:53<19:05:51,  1.34s/it]
                                                          
{'loss': 2.7696, 'learning_rate': 1.8304810060936083e-07, 'epoch': 2.75}

 17%|█▋        | 10660/61904 [5:09:53<19:05:51,  1.34s/it]
 17%|█▋        | 10661/61904 [5:09:54<18:46:39,  1.32s/it]
 17%|█▋        | 10662/61904 [5:09:55<18:47:15,  1.32s/it]
 17%|█▋        | 10663/61904 [5:09:57<18:49:33,  1.32s/it]
 17%|█▋        | 10664/61904 [5:09:58<19:01:08,  1.34s/it]
 17%|█▋        | 10665/61904 [5:09:59<19:08:22,  1.34s/it]
 17%|█▋        | 10666/61904 [5:10:01<19:03:38,  1.34s/it]
 17%|█▋        | 10667/61904 [5:10:02<18:58:15,  1.33s/it]
 17%|█▋        | 10668/61904 [5:10:03<19:27:01,  1.37s/it]
 17%|█▋        | 10669/61904 [5:10:05<19:14:35,  1.35s/it]
 17%|█▋        | 10670/61904 [5:10:06<19:04:13,  1.34s/it]
 17%|█▋        | 10671/61904 [5:10:07<19:13:38,  1.35s/it]
 17%|█▋        | 10672/61904 [5:10:09<19:24:06,  1.36s/it]
 17%|█▋        | 10673/61904 [5:10:10<20:08:33,  1.42s/it]
 17%|█▋        | 10674/61904 [5:10:12<19:47:34,  1.39s/it]
 17%|█▋        | 10675/61904 [5:10:13<20:24:48,  1.43s/it]
 17%|█▋        | 10676/61904 [5:10:15<20:06:22,  1.41s/it]
 17%|█▋        | 10677/61904 [5:10:16<19:31:17,  1.37s/it]
 17%|█▋        | 10678/61904 [5:10:17<19:47:10,  1.39s/it]
 17%|█▋        | 10679/61904 [5:10:19<19:28:00,  1.37s/it]
 17%|█▋        | 10680/61904 [5:10:20<19:12:00,  1.35s/it]
                                                          
{'loss': 2.7616, 'learning_rate': 1.830156877998185e-07, 'epoch': 2.76}

 17%|█▋        | 10680/61904 [5:10:20<19:12:00,  1.35s/it]
 17%|█▋        | 10681/61904 [5:10:21<19:12:17,  1.35s/it]
 17%|█▋        | 10682/61904 [5:10:23<19:11:55,  1.35s/it]
 17%|█▋        | 10683/61904 [5:10:24<18:39:16,  1.31s/it]
 17%|█▋        | 10684/61904 [5:10:25<19:07:56,  1.34s/it]
 17%|█▋        | 10685/61904 [5:10:27<18:39:01,  1.31s/it]
 17%|█▋        | 10686/61904 [5:10:28<18:19:33,  1.29s/it]
 17%|█▋        | 10687/61904 [5:10:29<18:14:27,  1.28s/it]
 17%|█▋        | 10688/61904 [5:10:30<18:29:38,  1.30s/it]
 17%|█▋        | 10689/61904 [5:10:32<19:32:39,  1.37s/it]
 17%|█▋        | 10690/61904 [5:10:33<19:49:03,  1.39s/it]
 17%|█▋        | 10691/61904 [5:10:35<20:01:25,  1.41s/it]
 17%|█▋        | 10692/61904 [5:10:36<20:06:51,  1.41s/it]
 17%|█▋        | 10693/61904 [5:10:38<20:11:18,  1.42s/it]
 17%|█▋        | 10694/61904 [5:10:39<19:55:00,  1.40s/it]
 17%|█▋        | 10695/61904 [5:10:40<19:33:52,  1.38s/it]
 17%|█▋        | 10696/61904 [5:10:42<19:27:46,  1.37s/it]
 17%|█▋        | 10697/61904 [5:10:43<18:54:13,  1.33s/it]
 17%|█▋        | 10698/61904 [5:10:44<18:23:12,  1.29s/it]
 17%|█▋        | 10699/61904 [5:10:46<20:11:05,  1.42s/it]
 17%|█▋        | 10700/61904 [5:10:47<20:02:42,  1.41s/it]
                                                          
{'loss': 2.7976, 'learning_rate': 1.8298327499027615e-07, 'epoch': 2.77}

 17%|█▋        | 10700/61904 [5:10:47<20:02:42,  1.41s/it]
 17%|█▋        | 10701/61904 [5:10:49<19:35:00,  1.38s/it]
 17%|█▋        | 10702/61904 [5:10:50<19:20:21,  1.36s/it]
 17%|█▋        | 10703/61904 [5:10:51<19:11:33,  1.35s/it]
 17%|█▋        | 10704/61904 [5:10:52<18:52:49,  1.33s/it]
 17%|█▋        | 10705/61904 [5:10:54<18:42:38,  1.32s/it]
 17%|█▋        | 10706/61904 [5:10:55<19:06:42,  1.34s/it]
 17%|█▋        | 10707/61904 [5:10:57<19:30:39,  1.37s/it]
 17%|█▋        | 10708/61904 [5:10:58<19:57:49,  1.40s/it]
 17%|█▋        | 10709/61904 [5:10:59<19:49:36,  1.39s/it]
 17%|█▋        | 10710/61904 [5:11:01<19:34:32,  1.38s/it]
 17%|█▋        | 10711/61904 [5:11:02<20:16:47,  1.43s/it]
 17%|█▋        | 10712/61904 [5:11:04<19:45:51,  1.39s/it]
 17%|█▋        | 10713/61904 [5:11:05<19:41:09,  1.38s/it]
 17%|█▋        | 10714/61904 [5:11:06<19:40:21,  1.38s/it]
 17%|█▋        | 10715/61904 [5:11:08<19:32:24,  1.37s/it]
 17%|█▋        | 10716/61904 [5:11:09<19:24:51,  1.37s/it]
 17%|█▋        | 10717/61904 [5:11:10<19:24:55,  1.37s/it]
 17%|█▋        | 10718/61904 [5:11:12<18:59:46,  1.34s/it]
 17%|█▋        | 10719/61904 [5:11:13<18:52:40,  1.33s/it]
 17%|█▋        | 10720/61904 [5:11:14<19:04:12,  1.34s/it]
                                                          
{'loss': 2.8024, 'learning_rate': 1.829508621807338e-07, 'epoch': 2.77}

 17%|█▋        | 10720/61904 [5:11:14<19:04:12,  1.34s/it]
 17%|█▋        | 10721/61904 [5:11:16<18:53:00,  1.33s/it]
 17%|█▋        | 10722/61904 [5:11:17<19:01:44,  1.34s/it]
 17%|█▋        | 10723/61904 [5:11:18<19:31:29,  1.37s/it]
 17%|█▋        | 10724/61904 [5:11:20<19:00:19,  1.34s/it]
 17%|█▋        | 10725/61904 [5:11:21<18:51:12,  1.33s/it]
 17%|█▋        | 10726/61904 [5:11:22<18:50:41,  1.33s/it]
 17%|█▋        | 10727/61904 [5:11:24<19:06:52,  1.34s/it]
 17%|█▋        | 10728/61904 [5:11:25<18:50:19,  1.33s/it]
 17%|█▋        | 10729/61904 [5:11:27<19:39:35,  1.38s/it]
 17%|█▋        | 10730/61904 [5:11:28<20:00:53,  1.41s/it]
 17%|█▋        | 10731/61904 [5:11:30<20:25:22,  1.44s/it]
 17%|█▋        | 10732/61904 [5:11:31<20:04:08,  1.41s/it]
 17%|█▋        | 10733/61904 [5:11:32<19:50:06,  1.40s/it]
 17%|█▋        | 10734/61904 [5:11:34<19:37:54,  1.38s/it]
 17%|█▋        | 10735/61904 [5:11:35<20:17:28,  1.43s/it]
 17%|█▋        | 10736/61904 [5:11:36<20:02:13,  1.41s/it]
 17%|█▋        | 10737/61904 [5:11:38<19:58:12,  1.41s/it]
 17%|█▋        | 10738/61904 [5:11:39<19:37:48,  1.38s/it]
 17%|█▋        | 10739/61904 [5:11:41<19:56:54,  1.40s/it]
 17%|█▋        | 10740/61904 [5:11:42<19:48:27,  1.39s/it]
                                                          
{'loss': 2.8195, 'learning_rate': 1.8291844937119147e-07, 'epoch': 2.78}

 17%|█▋        | 10740/61904 [5:11:42<19:48:27,  1.39s/it]
 17%|█▋        | 10741/61904 [5:11:43<19:23:42,  1.36s/it]
 17%|█▋        | 10742/61904 [5:11:45<19:35:48,  1.38s/it]
 17%|█▋        | 10743/61904 [5:11:46<20:29:57,  1.44s/it]
 17%|█▋        | 10744/61904 [5:11:48<19:25:10,  1.37s/it]
 17%|█▋        | 10745/61904 [5:11:49<20:12:32,  1.42s/it]
 17%|█▋        | 10746/61904 [5:11:50<19:55:27,  1.40s/it]
 17%|█▋        | 10747/61904 [5:11:52<19:28:52,  1.37s/it]
 17%|█▋        | 10748/61904 [5:11:53<19:41:54,  1.39s/it]
 17%|█▋        | 10749/61904 [5:11:55<19:42:19,  1.39s/it]
 17%|█▋        | 10750/61904 [5:11:56<19:35:12,  1.38s/it]
 17%|█▋        | 10751/61904 [5:11:57<19:23:01,  1.36s/it]
 17%|█▋        | 10752/61904 [5:11:59<19:24:07,  1.37s/it]
 17%|█▋        | 10753/61904 [5:12:00<19:17:52,  1.36s/it]
 17%|█▋        | 10754/61904 [5:12:01<19:14:17,  1.35s/it]
 17%|█▋        | 10755/61904 [5:12:02<18:37:30,  1.31s/it]
 17%|█▋        | 10756/61904 [5:12:04<18:27:46,  1.30s/it]
 17%|█▋        | 10757/61904 [5:12:05<18:32:21,  1.30s/it]
 17%|█▋        | 10758/61904 [5:12:07<19:11:31,  1.35s/it]
 17%|█▋        | 10759/61904 [5:12:08<21:14:15,  1.49s/it]
 17%|█▋        | 10760/61904 [5:12:10<20:36:16,  1.45s/it]
                                                          
{'loss': 2.8792, 'learning_rate': 1.8288603656164916e-07, 'epoch': 2.78}

 17%|█▋        | 10760/61904 [5:12:10<20:36:16,  1.45s/it]
 17%|█▋        | 10761/61904 [5:12:11<20:23:12,  1.44s/it]
 17%|█▋        | 10762/61904 [5:12:13<20:25:19,  1.44s/it]
 17%|█▋        | 10763/61904 [5:12:14<20:47:39,  1.46s/it]
 17%|█▋        | 10764/61904 [5:12:15<19:56:21,  1.40s/it]
 17%|█▋        | 10765/61904 [5:12:17<20:03:46,  1.41s/it]
 17%|█▋        | 10766/61904 [5:12:18<19:55:55,  1.40s/it]
 17%|█▋        | 10767/61904 [5:12:20<19:49:53,  1.40s/it]
 17%|█▋        | 10768/61904 [5:12:21<19:13:37,  1.35s/it]
 17%|█▋        | 10769/61904 [5:12:22<18:50:17,  1.33s/it]
 17%|█▋        | 10770/61904 [5:12:23<18:24:01,  1.30s/it]
 17%|█▋        | 10771/61904 [5:12:25<19:08:09,  1.35s/it]
 17%|█▋        | 10772/61904 [5:12:26<19:01:29,  1.34s/it]
 17%|█▋        | 10773/61904 [5:12:27<18:49:06,  1.32s/it]
 17%|█▋        | 10774/61904 [5:12:29<18:49:58,  1.33s/it]
 17%|█▋        | 10775/61904 [5:12:30<19:09:30,  1.35s/it]
 17%|█▋        | 10776/61904 [5:12:32<19:36:14,  1.38s/it]
 17%|█▋        | 10777/61904 [5:12:33<19:34:54,  1.38s/it]
 17%|█▋        | 10778/61904 [5:12:34<19:09:34,  1.35s/it]
 17%|█▋        | 10779/61904 [5:12:36<19:03:50,  1.34s/it]
 17%|█▋        | 10780/61904 [5:12:37<19:28:10,  1.37s/it]
                                                          
{'loss': 2.8563, 'learning_rate': 1.8285362375210682e-07, 'epoch': 2.79}

 17%|█▋        | 10780/61904 [5:12:37<19:28:10,  1.37s/it]
 17%|█▋        | 10781/61904 [5:12:38<19:23:59,  1.37s/it]
 17%|█▋        | 10782/61904 [5:12:40<18:56:41,  1.33s/it]
 17%|█▋        | 10783/61904 [5:12:41<18:38:45,  1.31s/it]
 17%|█▋        | 10784/61904 [5:12:42<18:43:37,  1.32s/it]
 17%|█▋        | 10785/61904 [5:12:44<19:20:51,  1.36s/it]
 17%|█▋        | 10786/61904 [5:12:45<18:58:05,  1.34s/it]
 17%|█▋        | 10787/61904 [5:12:46<18:51:11,  1.33s/it]
 17%|█▋        | 10788/61904 [5:12:48<19:01:23,  1.34s/it]
 17%|█▋        | 10789/61904 [5:12:49<19:23:16,  1.37s/it]
 17%|█▋        | 10790/61904 [5:12:50<19:28:27,  1.37s/it]
 17%|█▋        | 10791/61904 [5:12:52<19:13:31,  1.35s/it]
 17%|█▋        | 10792/61904 [5:12:53<19:29:49,  1.37s/it]
 17%|█▋        | 10793/61904 [5:12:54<19:16:53,  1.36s/it]
 17%|█▋        | 10794/61904 [5:12:56<18:41:58,  1.32s/it]
 17%|█▋        | 10795/61904 [5:12:57<18:37:55,  1.31s/it]
 17%|█▋        | 10796/61904 [5:12:58<18:34:14,  1.31s/it]
 17%|█▋        | 10797/61904 [5:13:00<18:55:52,  1.33s/it]
 17%|█▋        | 10798/61904 [5:13:01<18:49:55,  1.33s/it]
 17%|█▋        | 10799/61904 [5:13:02<18:25:36,  1.30s/it]
 17%|█▋        | 10800/61904 [5:13:04<19:25:24,  1.37s/it]
                                                          
{'loss': 2.7792, 'learning_rate': 1.8282121094256449e-07, 'epoch': 2.79}

 17%|█▋        | 10800/61904 [5:13:04<19:25:24,  1.37s/it]
 17%|█▋        | 10801/61904 [5:13:05<19:32:40,  1.38s/it]
 17%|█▋        | 10802/61904 [5:13:06<19:17:40,  1.36s/it]
 17%|█▋        | 10803/61904 [5:13:08<19:15:53,  1.36s/it]
 17%|█▋        | 10804/61904 [5:13:09<19:25:36,  1.37s/it]
 17%|█▋        | 10805/61904 [5:13:11<19:18:50,  1.36s/it]
 17%|█▋        | 10806/61904 [5:13:12<19:11:15,  1.35s/it]
 17%|█▋        | 10807/61904 [5:13:13<19:54:31,  1.40s/it]
 17%|█▋        | 10808/61904 [5:13:15<19:21:44,  1.36s/it]
 17%|█▋        | 10809/61904 [5:13:16<19:43:51,  1.39s/it]
 17%|█▋        | 10810/61904 [5:13:18<19:46:02,  1.39s/it]
 17%|█▋        | 10811/61904 [5:13:19<19:42:09,  1.39s/it]
 17%|█▋        | 10812/61904 [5:13:20<19:29:26,  1.37s/it]
 17%|█▋        | 10813/61904 [5:13:21<18:57:26,  1.34s/it]
 17%|█▋        | 10814/61904 [5:13:23<19:00:12,  1.34s/it]
 17%|█▋        | 10815/61904 [5:13:24<18:41:39,  1.32s/it]
 17%|█▋        | 10816/61904 [5:13:25<18:31:37,  1.31s/it]
 17%|█▋        | 10817/61904 [5:13:27<18:48:27,  1.33s/it]
 17%|█▋        | 10818/61904 [5:13:28<19:04:32,  1.34s/it]
 17%|█▋        | 10819/61904 [5:13:29<18:37:09,  1.31s/it]
 17%|█▋        | 10820/61904 [5:13:31<19:25:24,  1.37s/it]
                                                          
{'loss': 2.8382, 'learning_rate': 1.8278879813302218e-07, 'epoch': 2.8}

 17%|█▋        | 10820/61904 [5:13:31<19:25:24,  1.37s/it]
 17%|█▋        | 10821/61904 [5:13:32<19:26:58,  1.37s/it]
 17%|█▋        | 10822/61904 [5:13:34<19:03:10,  1.34s/it]
 17%|█▋        | 10823/61904 [5:13:35<18:48:09,  1.33s/it]
 17%|█▋        | 10824/61904 [5:13:36<19:21:25,  1.36s/it]
 17%|█▋        | 10825/61904 [5:13:38<19:40:49,  1.39s/it]
 17%|█▋        | 10826/61904 [5:13:39<19:15:51,  1.36s/it]
 17%|█▋        | 10827/61904 [5:13:40<19:25:33,  1.37s/it]
 17%|█▋        | 10828/61904 [5:13:42<19:25:07,  1.37s/it]
 17%|█▋        | 10829/61904 [5:13:43<20:01:16,  1.41s/it]
 17%|█▋        | 10830/61904 [5:13:45<19:27:43,  1.37s/it]
 17%|█▋        | 10831/61904 [5:13:46<19:46:43,  1.39s/it]
 17%|█▋        | 10832/61904 [5:13:47<19:39:13,  1.39s/it]
 17%|█▋        | 10833/61904 [5:13:49<20:14:31,  1.43s/it]
 18%|█▊        | 10834/61904 [5:13:50<19:33:49,  1.38s/it]
 18%|█▊        | 10835/61904 [5:13:51<19:03:47,  1.34s/it]
 18%|█▊        | 10836/61904 [5:13:53<18:49:05,  1.33s/it]
 18%|█▊        | 10837/61904 [5:13:54<19:27:44,  1.37s/it]
 18%|█▊        | 10838/61904 [5:13:56<19:16:46,  1.36s/it]
 18%|█▊        | 10839/61904 [5:13:57<18:59:52,  1.34s/it]
 18%|█▊        | 10840/61904 [5:13:58<18:53:10,  1.33s/it]
                                                          
{'loss': 2.7697, 'learning_rate': 1.8275638532347984e-07, 'epoch': 2.8}

 18%|█▊        | 10840/61904 [5:13:58<18:53:10,  1.33s/it]
 18%|█▊        | 10841/61904 [5:13:59<19:04:34,  1.34s/it]
 18%|█▊        | 10842/61904 [5:14:01<19:01:44,  1.34s/it]
 18%|█▊        | 10843/61904 [5:14:02<18:33:39,  1.31s/it]
 18%|█▊        | 10844/61904 [5:14:03<19:01:28,  1.34s/it]
 18%|█▊        | 10845/61904 [5:14:05<18:47:06,  1.32s/it]
 18%|█▊        | 10846/61904 [5:14:06<18:30:02,  1.30s/it]
 18%|█▊        | 10847/61904 [5:14:07<19:00:58,  1.34s/it]
 18%|█▊        | 10848/61904 [5:14:09<18:58:18,  1.34s/it]
 18%|█▊        | 10849/61904 [5:14:10<18:49:34,  1.33s/it]
 18%|█▊        | 10850/61904 [5:14:11<18:53:30,  1.33s/it]
 18%|█▊        | 10851/61904 [5:14:13<19:33:05,  1.38s/it]
 18%|█▊        | 10852/61904 [5:14:14<19:09:31,  1.35s/it]
 18%|█▊        | 10853/61904 [5:14:16<19:47:03,  1.40s/it]
 18%|█▊        | 10854/61904 [5:14:17<19:30:42,  1.38s/it]
 18%|█▊        | 10855/61904 [5:14:18<19:03:07,  1.34s/it]
 18%|█▊        | 10856/61904 [5:14:20<18:51:06,  1.33s/it]
 18%|█▊        | 10857/61904 [5:14:21<18:39:12,  1.32s/it]
 18%|█▊        | 10858/61904 [5:14:22<18:17:45,  1.29s/it]
 18%|█▊        | 10859/61904 [5:14:23<18:24:56,  1.30s/it]
 18%|█▊        | 10860/61904 [5:14:25<18:55:16,  1.33s/it]
                                                          
{'loss': 2.8915, 'learning_rate': 1.827239725139375e-07, 'epoch': 2.81}

 18%|█▊        | 10860/61904 [5:14:25<18:55:16,  1.33s/it]
 18%|█▊        | 10861/61904 [5:14:26<18:55:23,  1.33s/it]
 18%|█▊        | 10862/61904 [5:14:28<19:13:21,  1.36s/it]
 18%|█▊        | 10863/61904 [5:14:29<19:22:36,  1.37s/it]
 18%|█▊        | 10864/61904 [5:14:30<19:56:19,  1.41s/it]
 18%|█▊        | 10865/61904 [5:14:32<19:54:45,  1.40s/it]
 18%|█▊        | 10866/61904 [5:14:33<19:27:46,  1.37s/it]
 18%|█▊        | 10867/61904 [5:14:34<19:10:30,  1.35s/it]
 18%|█▊        | 10868/61904 [5:14:36<19:08:36,  1.35s/it]
 18%|█▊        | 10869/61904 [5:14:37<19:23:04,  1.37s/it]
 18%|█▊        | 10870/61904 [5:14:39<19:16:26,  1.36s/it]
 18%|█▊        | 10871/61904 [5:14:40<19:04:26,  1.35s/it]
 18%|█▊        | 10872/61904 [5:14:41<19:54:54,  1.40s/it]
 18%|█▊        | 10873/61904 [5:14:43<20:28:39,  1.44s/it]
 18%|█▊        | 10874/61904 [5:14:44<20:21:29,  1.44s/it]
 18%|█▊        | 10875/61904 [5:14:46<19:55:51,  1.41s/it]
 18%|█▊        | 10876/61904 [5:14:47<19:50:36,  1.40s/it]
 18%|█▊        | 10877/61904 [5:14:48<19:38:32,  1.39s/it]
 18%|█▊        | 10878/61904 [5:14:50<19:42:42,  1.39s/it]
 18%|█▊        | 10879/61904 [5:14:51<19:24:29,  1.37s/it]
 18%|█▊        | 10880/61904 [5:14:53<19:24:04,  1.37s/it]
                                                          
{'loss': 2.8202, 'learning_rate': 1.826915597043952e-07, 'epoch': 2.81}

 18%|█▊        | 10880/61904 [5:14:53<19:24:04,  1.37s/it]
 18%|█▊        | 10881/61904 [5:14:54<20:05:20,  1.42s/it]
 18%|█▊        | 10882/61904 [5:14:55<20:04:08,  1.42s/it]
 18%|█▊        | 10883/61904 [5:14:57<19:52:27,  1.40s/it]
 18%|█▊        | 10884/61904 [5:14:58<19:24:03,  1.37s/it]
 18%|█▊        | 10885/61904 [5:15:00<19:20:31,  1.36s/it]
 18%|█▊        | 10886/61904 [5:15:01<19:05:56,  1.35s/it]
 18%|█▊        | 10887/61904 [5:15:02<19:18:20,  1.36s/it]
 18%|█▊        | 10888/61904 [5:15:04<19:13:22,  1.36s/it]
 18%|█▊        | 10889/61904 [5:15:05<19:02:56,  1.34s/it]
 18%|█▊        | 10890/61904 [5:15:06<19:06:56,  1.35s/it]
 18%|█▊        | 10891/61904 [5:15:08<20:24:33,  1.44s/it]
 18%|█▊        | 10892/61904 [5:15:09<20:04:48,  1.42s/it]
 18%|█▊        | 10893/61904 [5:15:11<19:28:48,  1.37s/it]
 18%|█▊        | 10894/61904 [5:15:12<19:20:17,  1.36s/it]
 18%|█▊        | 10895/61904 [5:15:13<20:02:26,  1.41s/it]
 18%|█▊        | 10896/61904 [5:15:15<19:19:18,  1.36s/it]
 18%|█▊        | 10897/61904 [5:15:16<19:26:01,  1.37s/it]
 18%|█▊        | 10898/61904 [5:15:17<19:27:40,  1.37s/it]
 18%|█▊        | 10899/61904 [5:15:19<19:24:16,  1.37s/it]
 18%|█▊        | 10900/61904 [5:15:20<19:40:06,  1.39s/it]
                                                          
{'loss': 2.7699, 'learning_rate': 1.8265914689485282e-07, 'epoch': 2.82}

 18%|█▊        | 10900/61904 [5:15:20<19:40:06,  1.39s/it]
 18%|█▊        | 10901/61904 [5:15:22<19:41:09,  1.39s/it]
 18%|█▊        | 10902/61904 [5:15:23<20:08:39,  1.42s/it]
 18%|█▊        | 10903/61904 [5:15:24<20:03:51,  1.42s/it]
 18%|█▊        | 10904/61904 [5:15:26<19:47:07,  1.40s/it]
 18%|█▊        | 10905/61904 [5:15:27<19:44:00,  1.39s/it]
 18%|█▊        | 10906/61904 [5:15:29<19:37:59,  1.39s/it]
 18%|█▊        | 10907/61904 [5:15:30<19:56:59,  1.41s/it]
 18%|█▊        | 10908/61904 [5:15:31<19:42:43,  1.39s/it]
 18%|█▊        | 10909/61904 [5:15:33<20:06:42,  1.42s/it]
 18%|█▊        | 10910/61904 [5:15:35<20:56:08,  1.48s/it]
 18%|█▊        | 10911/61904 [5:15:36<20:06:25,  1.42s/it]
 18%|█▊        | 10912/61904 [5:15:37<19:53:57,  1.40s/it]
 18%|█▊        | 10913/61904 [5:15:39<19:59:34,  1.41s/it]
 18%|█▊        | 10914/61904 [5:15:40<19:27:34,  1.37s/it]
 18%|█▊        | 10915/61904 [5:15:41<18:59:32,  1.34s/it]
 18%|█▊        | 10916/61904 [5:15:43<19:11:52,  1.36s/it]
 18%|█▊        | 10917/61904 [5:15:44<19:44:48,  1.39s/it]
 18%|█▊        | 10918/61904 [5:15:45<19:15:20,  1.36s/it]
 18%|█▊        | 10919/61904 [5:15:47<19:25:37,  1.37s/it]
 18%|█▊        | 10920/61904 [5:15:48<19:07:06,  1.35s/it]
                                                          
{'loss': 2.8795, 'learning_rate': 1.826267340853105e-07, 'epoch': 2.82}

 18%|█▊        | 10920/61904 [5:15:48<19:07:06,  1.35s/it]
 18%|█▊        | 10921/61904 [5:15:49<18:58:03,  1.34s/it]
 18%|█▊        | 10922/61904 [5:15:51<19:26:16,  1.37s/it]
 18%|█▊        | 10923/61904 [5:15:52<19:30:32,  1.38s/it]
 18%|█▊        | 10924/61904 [5:15:54<19:51:07,  1.40s/it]
 18%|█▊        | 10925/61904 [5:15:55<20:17:13,  1.43s/it]
 18%|█▊        | 10926/61904 [5:15:57<20:24:35,  1.44s/it]
 18%|█▊        | 10927/61904 [5:15:58<20:59:56,  1.48s/it]
 18%|█▊        | 10928/61904 [5:15:59<20:20:39,  1.44s/it]
 18%|█▊        | 10929/61904 [5:16:01<20:26:27,  1.44s/it]
 18%|█▊        | 10930/61904 [5:16:02<19:49:01,  1.40s/it]
 18%|█▊        | 10931/61904 [5:16:04<19:52:04,  1.40s/it]
 18%|█▊        | 10932/61904 [5:16:05<20:20:57,  1.44s/it]
 18%|█▊        | 10933/61904 [5:16:07<19:58:49,  1.41s/it]
 18%|█▊        | 10934/61904 [5:16:08<19:42:26,  1.39s/it]
 18%|█▊        | 10935/61904 [5:16:09<19:45:20,  1.40s/it]
 18%|█▊        | 10936/61904 [5:16:11<19:19:08,  1.36s/it]
 18%|█▊        | 10937/61904 [5:16:12<19:12:57,  1.36s/it]
 18%|█▊        | 10938/61904 [5:16:13<18:41:01,  1.32s/it]
 18%|█▊        | 10939/61904 [5:16:15<18:58:36,  1.34s/it]
 18%|█▊        | 10940/61904 [5:16:16<18:59:50,  1.34s/it]
                                                          
{'loss': 2.7777, 'learning_rate': 1.8259432127576817e-07, 'epoch': 2.83}

 18%|█▊        | 10940/61904 [5:16:16<18:59:50,  1.34s/it]
 18%|█▊        | 10941/61904 [5:16:17<18:58:57,  1.34s/it]
 18%|█▊        | 10942/61904 [5:16:18<18:43:01,  1.32s/it]
 18%|█▊        | 10943/61904 [5:16:20<18:45:21,  1.32s/it]
 18%|█▊        | 10944/61904 [5:16:21<18:36:26,  1.31s/it]
 18%|█▊        | 10945/61904 [5:16:22<18:55:17,  1.34s/it]
 18%|█▊        | 10946/61904 [5:16:24<19:55:18,  1.41s/it]
 18%|█▊        | 10947/61904 [5:16:25<19:35:24,  1.38s/it]
 18%|█▊        | 10948/61904 [5:16:27<19:43:09,  1.39s/it]
 18%|█▊        | 10949/61904 [5:16:28<19:25:31,  1.37s/it]
 18%|█▊        | 10950/61904 [5:16:29<19:14:23,  1.36s/it]
 18%|█▊        | 10951/61904 [5:16:31<19:58:38,  1.41s/it]
 18%|█▊        | 10952/61904 [5:16:32<20:10:17,  1.43s/it]
 18%|█▊        | 10953/61904 [5:16:34<19:39:05,  1.39s/it]
 18%|█▊        | 10954/61904 [5:16:35<19:00:51,  1.34s/it]
 18%|█▊        | 10955/61904 [5:16:36<19:11:47,  1.36s/it]
 18%|█▊        | 10956/61904 [5:16:38<19:12:47,  1.36s/it]
 18%|█▊        | 10957/61904 [5:16:39<19:15:31,  1.36s/it]
 18%|█▊        | 10958/61904 [5:16:40<19:09:35,  1.35s/it]
 18%|█▊        | 10959/61904 [5:16:42<18:41:06,  1.32s/it]
 18%|█▊        | 10960/61904 [5:16:43<19:10:35,  1.36s/it]
                                                          
{'loss': 2.8015, 'learning_rate': 1.8256190846622583e-07, 'epoch': 2.83}

 18%|█▊        | 10960/61904 [5:16:43<19:10:35,  1.36s/it]
 18%|█▊        | 10961/61904 [5:16:45<19:59:54,  1.41s/it]
 18%|█▊        | 10962/61904 [5:16:46<20:18:39,  1.44s/it]
 18%|█▊        | 10963/61904 [5:16:47<19:55:21,  1.41s/it]
 18%|█▊        | 10964/61904 [5:16:49<20:01:33,  1.42s/it]
 18%|█▊        | 10965/61904 [5:16:50<19:24:31,  1.37s/it]
 18%|█▊        | 10966/61904 [5:16:52<19:27:38,  1.38s/it]
 18%|█▊        | 10967/61904 [5:16:53<19:43:26,  1.39s/it]
 18%|█▊        | 10968/61904 [5:16:54<19:09:25,  1.35s/it]
 18%|█▊        | 10969/61904 [5:16:56<19:36:05,  1.39s/it]
 18%|█▊        | 10970/61904 [5:16:57<19:13:49,  1.36s/it]
 18%|█▊        | 10971/61904 [5:16:58<19:20:17,  1.37s/it]
 18%|█▊        | 10972/61904 [5:17:00<19:13:08,  1.36s/it]
 18%|█▊        | 10973/61904 [5:17:01<19:35:08,  1.38s/it]
 18%|█▊        | 10974/61904 [5:17:02<19:01:15,  1.34s/it]
 18%|█▊        | 10975/61904 [5:17:04<18:43:13,  1.32s/it]
 18%|█▊        | 10976/61904 [5:17:05<19:18:14,  1.36s/it]
 18%|█▊        | 10977/61904 [5:17:07<19:35:23,  1.38s/it]
 18%|█▊        | 10978/61904 [5:17:08<20:10:17,  1.43s/it]
 18%|█▊        | 10979/61904 [5:17:10<20:16:20,  1.43s/it]
 18%|█▊        | 10980/61904 [5:17:11<19:15:51,  1.36s/it]
                                                          
{'loss': 2.8306, 'learning_rate': 1.8252949565668352e-07, 'epoch': 2.84}

 18%|█▊        | 10980/61904 [5:17:11<19:15:51,  1.36s/it]
 18%|█▊        | 10981/61904 [5:17:12<19:07:51,  1.35s/it]
 18%|█▊        | 10982/61904 [5:17:13<19:02:23,  1.35s/it]
 18%|█▊        | 10983/61904 [5:17:15<19:37:03,  1.39s/it]
 18%|█▊        | 10984/61904 [5:17:16<19:26:33,  1.37s/it]
 18%|█▊        | 10985/61904 [5:17:18<18:56:11,  1.34s/it]
 18%|█▊        | 10986/61904 [5:17:19<19:11:00,  1.36s/it]
 18%|█▊        | 10987/61904 [5:17:20<18:44:10,  1.32s/it]
 18%|█▊        | 10988/61904 [5:17:22<18:51:11,  1.33s/it]
 18%|█▊        | 10989/61904 [5:17:23<19:00:19,  1.34s/it]
 18%|█▊        | 10990/61904 [5:17:24<18:47:41,  1.33s/it]
 18%|█▊        | 10991/61904 [5:17:26<19:28:04,  1.38s/it]
 18%|█▊        | 10992/61904 [5:17:27<19:57:00,  1.41s/it]
 18%|█▊        | 10993/61904 [5:17:28<19:21:53,  1.37s/it]
 18%|█▊        | 10994/61904 [5:17:30<19:05:21,  1.35s/it]
 18%|█▊        | 10995/61904 [5:17:31<19:19:39,  1.37s/it]
 18%|█▊        | 10996/61904 [5:17:32<18:52:49,  1.34s/it]
 18%|█▊        | 10997/61904 [5:17:34<18:30:27,  1.31s/it]
 18%|█▊        | 10998/61904 [5:17:35<18:34:43,  1.31s/it]
 18%|█▊        | 10999/61904 [5:17:36<18:26:25,  1.30s/it]
 18%|█▊        | 11000/61904 [5:17:38<18:55:49,  1.34s/it]
                                                          
{'loss': 2.986, 'learning_rate': 1.8249708284714118e-07, 'epoch': 2.84}

 18%|█▊        | 11000/61904 [5:17:38<18:55:49,  1.34s/it]
 18%|█▊        | 11001/61904 [5:17:39<18:56:41,  1.34s/it]
 18%|█▊        | 11002/61904 [5:17:40<19:01:44,  1.35s/it]
 18%|█▊        | 11003/61904 [5:17:42<18:46:15,  1.33s/it]
 18%|█▊        | 11004/61904 [5:17:43<18:42:54,  1.32s/it]
 18%|█▊        | 11005/61904 [5:17:44<19:04:48,  1.35s/it]
 18%|█▊        | 11006/61904 [5:17:46<19:36:27,  1.39s/it]
 18%|█▊        | 11007/61904 [5:17:47<19:26:10,  1.37s/it]
 18%|█▊        | 11008/61904 [5:17:48<18:50:00,  1.33s/it]
 18%|█▊        | 11009/61904 [5:17:50<19:47:30,  1.40s/it]
 18%|█▊        | 11010/61904 [5:17:51<19:25:56,  1.37s/it]
 18%|█▊        | 11011/61904 [5:17:53<19:35:57,  1.39s/it]
 18%|█▊        | 11012/61904 [5:17:54<19:08:29,  1.35s/it]
 18%|█▊        | 11013/61904 [5:17:56<19:42:45,  1.39s/it]
 18%|█▊        | 11014/61904 [5:17:57<20:08:48,  1.43s/it]
 18%|█▊        | 11015/61904 [5:17:59<20:26:49,  1.45s/it]
 18%|█▊        | 11016/61904 [5:18:00<21:06:34,  1.49s/it]
 18%|█▊        | 11017/61904 [5:18:01<20:32:57,  1.45s/it]
 18%|█▊        | 11018/61904 [5:18:03<19:43:10,  1.40s/it]
 18%|█▊        | 11019/61904 [5:18:04<19:37:12,  1.39s/it]
 18%|█▊        | 11020/61904 [5:18:06<20:01:22,  1.42s/it]
                                                          
{'loss': 2.785, 'learning_rate': 1.8246467003759885e-07, 'epoch': 2.85}

 18%|█▊        | 11020/61904 [5:18:06<20:01:22,  1.42s/it]
 18%|█▊        | 11021/61904 [5:18:07<19:32:16,  1.38s/it]
 18%|█▊        | 11022/61904 [5:18:08<18:53:35,  1.34s/it]
 18%|█▊        | 11023/61904 [5:18:09<19:00:04,  1.34s/it]
 18%|█▊        | 11024/61904 [5:18:11<18:57:23,  1.34s/it]
 18%|█▊        | 11025/61904 [5:18:12<18:41:41,  1.32s/it]
 18%|█▊        | 11026/61904 [5:18:14<19:19:00,  1.37s/it]
 18%|█▊        | 11027/61904 [5:18:15<18:53:45,  1.34s/it]
 18%|█▊        | 11028/61904 [5:18:16<18:40:41,  1.32s/it]
 18%|█▊        | 11029/61904 [5:18:17<18:26:29,  1.30s/it]
 18%|█▊        | 11030/61904 [5:18:19<19:06:12,  1.35s/it]
 18%|█▊        | 11031/61904 [5:18:20<18:37:55,  1.32s/it]
 18%|█▊        | 11032/61904 [5:18:21<18:49:31,  1.33s/it]
 18%|█▊        | 11033/61904 [5:18:23<19:19:29,  1.37s/it]
 18%|█▊        | 11034/61904 [5:18:24<19:13:08,  1.36s/it]
 18%|█▊        | 11035/61904 [5:18:26<18:51:27,  1.33s/it]
 18%|█▊        | 11036/61904 [5:18:27<19:06:02,  1.35s/it]
 18%|█▊        | 11037/61904 [5:18:28<19:17:37,  1.37s/it]
 18%|█▊        | 11038/61904 [5:18:30<19:40:42,  1.39s/it]
 18%|█▊        | 11039/61904 [5:18:31<19:03:23,  1.35s/it]
 18%|█▊        | 11040/61904 [5:18:32<19:01:47,  1.35s/it]
                                                          
{'loss': 2.7796, 'learning_rate': 1.8243225722805653e-07, 'epoch': 2.85}

 18%|█▊        | 11040/61904 [5:18:32<19:01:47,  1.35s/it]
 18%|█▊        | 11041/61904 [5:18:34<19:15:39,  1.36s/it]
 18%|█▊        | 11042/61904 [5:18:35<19:31:57,  1.38s/it]
 18%|█▊        | 11043/61904 [5:18:37<19:29:37,  1.38s/it]
 18%|█▊        | 11044/61904 [5:18:38<19:13:57,  1.36s/it]
 18%|█▊        | 11045/61904 [5:18:39<19:21:36,  1.37s/it]
 18%|█▊        | 11046/61904 [5:18:41<18:58:42,  1.34s/it]
 18%|█▊        | 11047/61904 [5:18:42<18:30:53,  1.31s/it]
 18%|█▊        | 11048/61904 [5:18:43<19:30:15,  1.38s/it]
 18%|█▊        | 11049/61904 [5:18:45<19:57:56,  1.41s/it]
 18%|█▊        | 11050/61904 [5:18:46<19:50:46,  1.40s/it]
 18%|█▊        | 11051/61904 [5:18:48<20:21:42,  1.44s/it]
 18%|█▊        | 11052/61904 [5:18:49<20:13:02,  1.43s/it]
 18%|█▊        | 11053/61904 [5:18:50<19:43:04,  1.40s/it]
 18%|█▊        | 11054/61904 [5:18:52<19:09:59,  1.36s/it]
 18%|█▊        | 11055/61904 [5:18:53<19:20:16,  1.37s/it]
 18%|█▊        | 11056/61904 [5:18:55<19:54:27,  1.41s/it]
 18%|█▊        | 11057/61904 [5:18:56<19:56:48,  1.41s/it]
 18%|█▊        | 11058/61904 [5:18:57<19:36:42,  1.39s/it]
 18%|█▊        | 11059/61904 [5:18:59<19:43:14,  1.40s/it]
 18%|█▊        | 11060/61904 [5:19:00<20:02:14,  1.42s/it]
                                                          
{'loss': 2.7851, 'learning_rate': 1.823998444185142e-07, 'epoch': 2.86}

 18%|█▊        | 11060/61904 [5:19:00<20:02:14,  1.42s/it]
 18%|█▊        | 11061/61904 [5:19:02<19:59:21,  1.42s/it]
 18%|█▊        | 11062/61904 [5:19:03<19:44:09,  1.40s/it]
 18%|█▊        | 11063/61904 [5:19:04<19:22:13,  1.37s/it]
 18%|█▊        | 11064/61904 [5:19:06<19:20:57,  1.37s/it]
 18%|█▊        | 11065/61904 [5:19:07<18:53:15,  1.34s/it]
 18%|█▊        | 11066/61904 [5:19:08<19:39:21,  1.39s/it]
 18%|█▊        | 11067/61904 [5:19:10<20:07:56,  1.43s/it]
 18%|█▊        | 11068/61904 [5:19:11<19:15:15,  1.36s/it]
 18%|█▊        | 11069/61904 [5:19:13<19:10:51,  1.36s/it]
 18%|█▊        | 11070/61904 [5:19:14<19:00:22,  1.35s/it]
 18%|█▊        | 11071/61904 [5:19:15<19:41:17,  1.39s/it]
 18%|█▊        | 11072/61904 [5:19:17<19:26:30,  1.38s/it]
 18%|█▊        | 11073/61904 [5:19:18<19:39:12,  1.39s/it]
 18%|█▊        | 11074/61904 [5:19:19<19:12:46,  1.36s/it]
 18%|█▊        | 11075/61904 [5:19:21<19:19:34,  1.37s/it]
 18%|█▊        | 11076/61904 [5:19:22<18:46:21,  1.33s/it]
 18%|█▊        | 11077/61904 [5:19:23<19:00:18,  1.35s/it]
 18%|█▊        | 11078/61904 [5:19:25<18:41:02,  1.32s/it]
 18%|█▊        | 11079/61904 [5:19:26<18:58:41,  1.34s/it]
 18%|█▊        | 11080/61904 [5:19:27<18:49:05,  1.33s/it]
                                                          
{'loss': 2.8133, 'learning_rate': 1.8236743160897186e-07, 'epoch': 2.86}

 18%|█▊        | 11080/61904 [5:19:27<18:49:05,  1.33s/it]
 18%|█▊        | 11081/61904 [5:19:29<18:58:45,  1.34s/it]
 18%|█▊        | 11082/61904 [5:19:30<18:49:45,  1.33s/it]
 18%|█▊        | 11083/61904 [5:19:31<19:00:39,  1.35s/it]
 18%|█▊        | 11084/61904 [5:19:33<19:24:07,  1.37s/it]
 18%|█▊        | 11085/61904 [5:19:34<19:23:24,  1.37s/it]
 18%|█▊        | 11086/61904 [5:19:36<18:56:50,  1.34s/it]
 18%|█▊        | 11087/61904 [5:19:37<18:39:49,  1.32s/it]
 18%|█▊        | 11088/61904 [5:19:38<18:52:00,  1.34s/it]
 18%|█▊        | 11089/61904 [5:19:40<19:15:44,  1.36s/it]
 18%|█▊        | 11090/61904 [5:19:41<18:56:16,  1.34s/it]
 18%|█▊        | 11091/61904 [5:19:42<18:55:30,  1.34s/it]
 18%|█▊        | 11092/61904 [5:19:44<19:12:30,  1.36s/it]
 18%|█▊        | 11093/61904 [5:19:45<20:41:16,  1.47s/it]
 18%|█▊        | 11094/61904 [5:19:47<20:13:49,  1.43s/it]
 18%|█▊        | 11095/61904 [5:19:48<19:54:42,  1.41s/it]
 18%|█▊        | 11096/61904 [5:19:49<19:51:15,  1.41s/it]
 18%|█▊        | 11097/61904 [5:19:51<19:31:33,  1.38s/it]
 18%|█▊        | 11098/61904 [5:19:52<19:33:52,  1.39s/it]
 18%|█▊        | 11099/61904 [5:19:54<19:46:19,  1.40s/it]
 18%|█▊        | 11100/61904 [5:19:55<20:08:16,  1.43s/it]
                                                          
{'loss': 2.7767, 'learning_rate': 1.8233501879942955e-07, 'epoch': 2.87}

 18%|█▊        | 11100/61904 [5:19:55<20:08:16,  1.43s/it]
 18%|█▊        | 11101/61904 [5:19:56<19:31:04,  1.38s/it]
 18%|█▊        | 11102/61904 [5:19:58<19:48:29,  1.40s/it]
 18%|█▊        | 11103/61904 [5:19:59<19:40:32,  1.39s/it]
 18%|█▊        | 11104/61904 [5:20:01<19:23:46,  1.37s/it]
 18%|█▊        | 11105/61904 [5:20:02<19:10:11,  1.36s/it]
 18%|█▊        | 11106/61904 [5:20:03<19:04:58,  1.35s/it]
 18%|█▊        | 11107/61904 [5:20:05<19:23:00,  1.37s/it]
 18%|█▊        | 11108/61904 [5:20:06<19:05:58,  1.35s/it]
 18%|█▊        | 11109/61904 [5:20:07<18:44:51,  1.33s/it]
 18%|█▊        | 11110/61904 [5:20:09<19:19:34,  1.37s/it]
 18%|█▊        | 11111/61904 [5:20:10<18:48:41,  1.33s/it]
 18%|█▊        | 11112/61904 [5:20:11<18:54:28,  1.34s/it]
 18%|█▊        | 11113/61904 [5:20:13<18:46:44,  1.33s/it]
 18%|█▊        | 11114/61904 [5:20:14<18:24:41,  1.31s/it]
 18%|█▊        | 11115/61904 [5:20:15<18:48:28,  1.33s/it]
 18%|█▊        | 11116/61904 [5:20:17<18:52:35,  1.34s/it]
 18%|█▊        | 11117/61904 [5:20:18<18:39:15,  1.32s/it]
 18%|█▊        | 11118/61904 [5:20:19<18:29:08,  1.31s/it]
 18%|█▊        | 11119/61904 [5:20:20<18:29:12,  1.31s/it]
 18%|█▊        | 11120/61904 [5:20:22<18:29:09,  1.31s/it]
                                                          
{'loss': 2.8456, 'learning_rate': 1.8230260598988718e-07, 'epoch': 2.87}

 18%|█▊        | 11120/61904 [5:20:22<18:29:09,  1.31s/it]
 18%|█▊        | 11121/61904 [5:20:23<19:05:54,  1.35s/it]
 18%|█▊        | 11122/61904 [5:20:24<18:23:27,  1.30s/it]
 18%|█▊        | 11123/61904 [5:20:26<19:01:44,  1.35s/it]
 18%|█▊        | 11124/61904 [5:20:27<19:04:04,  1.35s/it]
 18%|█▊        | 11125/61904 [5:20:29<19:04:22,  1.35s/it]
 18%|█▊        | 11126/61904 [5:20:30<19:03:39,  1.35s/it]
 18%|█▊        | 11127/61904 [5:20:31<18:40:22,  1.32s/it]
 18%|█▊        | 11128/61904 [5:20:32<18:09:04,  1.29s/it]
 18%|█▊        | 11129/61904 [5:20:34<18:24:33,  1.31s/it]
 18%|█▊        | 11130/61904 [5:20:35<19:19:52,  1.37s/it]
 18%|█▊        | 11131/61904 [5:20:37<19:06:47,  1.36s/it]
 18%|█▊        | 11132/61904 [5:20:38<18:53:37,  1.34s/it]
 18%|█▊        | 11133/61904 [5:20:39<19:41:22,  1.40s/it]
 18%|█▊        | 11134/61904 [5:20:41<19:57:45,  1.42s/it]
 18%|█▊        | 11135/61904 [5:20:42<19:16:07,  1.37s/it]
 18%|█▊        | 11136/61904 [5:20:43<18:48:36,  1.33s/it]
 18%|█▊        | 11137/61904 [5:20:45<18:36:47,  1.32s/it]
 18%|█▊        | 11138/61904 [5:20:46<18:36:55,  1.32s/it]
 18%|█▊        | 11139/61904 [5:20:47<18:39:36,  1.32s/it]
 18%|█▊        | 11140/61904 [5:20:49<18:26:15,  1.31s/it]
                                                          
{'loss': 2.7697, 'learning_rate': 1.8227019318034487e-07, 'epoch': 2.88}

 18%|█▊        | 11140/61904 [5:20:49<18:26:15,  1.31s/it]
 18%|█▊        | 11141/61904 [5:20:50<19:25:09,  1.38s/it]
 18%|█▊        | 11142/61904 [5:20:52<19:34:08,  1.39s/it]
 18%|█▊        | 11143/61904 [5:20:53<19:17:57,  1.37s/it]
 18%|█▊        | 11144/61904 [5:20:54<18:46:29,  1.33s/it]
 18%|█▊        | 11145/61904 [5:20:55<18:21:27,  1.30s/it]
 18%|█▊        | 11146/61904 [5:20:57<18:31:19,  1.31s/it]
 18%|█▊        | 11147/61904 [5:20:58<18:49:09,  1.33s/it]
 18%|█▊        | 11148/61904 [5:20:59<19:08:14,  1.36s/it]
 18%|█▊        | 11149/61904 [5:21:01<19:17:40,  1.37s/it]
 18%|█▊        | 11150/61904 [5:21:02<19:28:44,  1.38s/it]
 18%|█▊        | 11151/61904 [5:21:04<19:11:29,  1.36s/it]
 18%|█▊        | 11152/61904 [5:21:05<19:38:37,  1.39s/it]
 18%|█▊        | 11153/61904 [5:21:06<19:41:05,  1.40s/it]
 18%|█▊        | 11154/61904 [5:21:08<20:19:57,  1.44s/it]
 18%|█▊        | 11155/61904 [5:21:09<19:33:50,  1.39s/it]
 18%|█▊        | 11156/61904 [5:21:11<19:20:47,  1.37s/it]
 18%|█▊        | 11157/61904 [5:21:12<19:23:53,  1.38s/it]
 18%|█▊        | 11158/61904 [5:21:13<19:30:08,  1.38s/it]
 18%|█▊        | 11159/61904 [5:21:15<19:16:55,  1.37s/it]
 18%|█▊        | 11160/61904 [5:21:16<19:19:14,  1.37s/it]
                                                          
{'loss': 2.7501, 'learning_rate': 1.8223778037080253e-07, 'epoch': 2.88}

 18%|█▊        | 11160/61904 [5:21:16<19:19:14,  1.37s/it]
 18%|█▊        | 11161/61904 [5:21:17<19:18:25,  1.37s/it]
 18%|█▊        | 11162/61904 [5:21:19<19:37:57,  1.39s/it]
 18%|█▊        | 11163/61904 [5:21:20<19:06:16,  1.36s/it]
 18%|█▊        | 11164/61904 [5:21:22<19:12:44,  1.36s/it]
 18%|█▊        | 11165/61904 [5:21:23<19:05:06,  1.35s/it]
 18%|█▊        | 11166/61904 [5:21:24<19:08:18,  1.36s/it]
 18%|█▊        | 11167/61904 [5:21:26<19:32:12,  1.39s/it]
 18%|█▊        | 11168/61904 [5:21:27<19:19:00,  1.37s/it]
 18%|█▊        | 11169/61904 [5:21:28<19:31:29,  1.39s/it]
 18%|█▊        | 11170/61904 [5:21:30<21:25:30,  1.52s/it]
 18%|█▊        | 11171/61904 [5:21:32<20:28:12,  1.45s/it]
 18%|█▊        | 11172/61904 [5:21:33<20:20:04,  1.44s/it]
 18%|█▊        | 11173/61904 [5:21:34<20:10:23,  1.43s/it]
 18%|█▊        | 11174/61904 [5:21:36<19:50:51,  1.41s/it]
 18%|█▊        | 11175/61904 [5:21:37<19:37:16,  1.39s/it]
 18%|█▊        | 11176/61904 [5:21:39<20:13:25,  1.44s/it]
 18%|█▊        | 11177/61904 [5:21:40<19:59:25,  1.42s/it]
 18%|█▊        | 11178/61904 [5:21:41<19:39:48,  1.40s/it]
 18%|█▊        | 11179/61904 [5:21:43<19:15:18,  1.37s/it]
 18%|█▊        | 11180/61904 [5:21:44<18:46:21,  1.33s/it]
                                                          
{'loss': 2.8102, 'learning_rate': 1.822053675612602e-07, 'epoch': 2.89}

 18%|█▊        | 11180/61904 [5:21:44<18:46:21,  1.33s/it]
 18%|█▊        | 11181/61904 [5:21:46<19:42:14,  1.40s/it]
 18%|█▊        | 11182/61904 [5:21:47<19:32:35,  1.39s/it]
 18%|█▊        | 11183/61904 [5:21:48<18:49:44,  1.34s/it]
 18%|█▊        | 11184/61904 [5:21:50<19:21:37,  1.37s/it]
 18%|█▊        | 11185/61904 [5:21:51<19:49:09,  1.41s/it]
 18%|█▊        | 11186/61904 [5:21:52<19:17:47,  1.37s/it]
 18%|█▊        | 11187/61904 [5:21:54<19:11:10,  1.36s/it]
 18%|█▊        | 11188/61904 [5:21:55<19:30:16,  1.38s/it]
 18%|█▊        | 11189/61904 [5:21:56<19:28:02,  1.38s/it]
 18%|█▊        | 11190/61904 [5:21:58<19:38:43,  1.39s/it]
 18%|█▊        | 11191/61904 [5:21:59<19:16:42,  1.37s/it]
 18%|█▊        | 11192/61904 [5:22:01<19:18:25,  1.37s/it]
 18%|█▊        | 11193/61904 [5:22:02<19:54:45,  1.41s/it]
 18%|█▊        | 11194/61904 [5:22:03<19:49:13,  1.41s/it]
 18%|█▊        | 11195/61904 [5:22:05<19:52:50,  1.41s/it]
 18%|█▊        | 11196/61904 [5:22:06<20:31:53,  1.46s/it]
 18%|█▊        | 11197/61904 [5:22:08<20:00:47,  1.42s/it]
 18%|█▊        | 11198/61904 [5:22:09<20:38:16,  1.47s/it]
 18%|█▊        | 11199/61904 [5:22:11<20:24:09,  1.45s/it]
 18%|█▊        | 11200/61904 [5:22:12<20:23:54,  1.45s/it]
                                                          
{'loss': 2.8303, 'learning_rate': 1.8217295475171788e-07, 'epoch': 2.89}

 18%|█▊        | 11200/61904 [5:22:12<20:23:54,  1.45s/it]
 18%|█▊        | 11201/61904 [5:22:13<19:32:00,  1.39s/it]
 18%|█▊        | 11202/61904 [5:22:15<19:04:07,  1.35s/it]
 18%|█▊        | 11203/61904 [5:22:16<18:32:00,  1.32s/it]
 18%|█▊        | 11204/61904 [5:22:17<18:48:08,  1.34s/it]
 18%|█▊        | 11205/61904 [5:22:19<18:48:58,  1.34s/it]
 18%|█▊        | 11206/61904 [5:22:20<19:45:21,  1.40s/it]
 18%|█▊        | 11207/61904 [5:22:22<20:10:23,  1.43s/it]
 18%|█▊        | 11208/61904 [5:22:23<20:15:07,  1.44s/it]
 18%|█▊        | 11209/61904 [5:22:24<19:31:23,  1.39s/it]
 18%|█▊        | 11210/61904 [5:22:26<19:30:28,  1.39s/it]
 18%|█▊        | 11211/61904 [5:22:27<19:11:05,  1.36s/it]
 18%|█▊        | 11212/61904 [5:22:29<19:25:28,  1.38s/it]
 18%|█▊        | 11213/61904 [5:22:30<19:45:09,  1.40s/it]
 18%|█▊        | 11214/61904 [5:22:31<19:06:06,  1.36s/it]
 18%|█▊        | 11215/61904 [5:22:33<19:42:04,  1.40s/it]
 18%|█▊        | 11216/61904 [5:22:34<19:17:59,  1.37s/it]
 18%|█▊        | 11217/61904 [5:22:36<20:14:53,  1.44s/it]
 18%|█▊        | 11218/61904 [5:22:37<19:39:42,  1.40s/it]
 18%|█▊        | 11219/61904 [5:22:38<19:14:13,  1.37s/it]
 18%|█▊        | 11220/61904 [5:22:40<19:19:09,  1.37s/it]
                                                          
{'loss': 2.8061, 'learning_rate': 1.8214054194217554e-07, 'epoch': 2.9}

 18%|█▊        | 11220/61904 [5:22:40<19:19:09,  1.37s/it]
 18%|█▊        | 11221/61904 [5:22:41<19:44:58,  1.40s/it]
 18%|█▊        | 11222/61904 [5:22:42<19:30:08,  1.39s/it]
 18%|█▊        | 11223/61904 [5:22:44<20:08:53,  1.43s/it]
 18%|█▊        | 11224/61904 [5:22:45<19:43:19,  1.40s/it]
 18%|█▊        | 11225/61904 [5:22:47<19:49:40,  1.41s/it]
 18%|█▊        | 11226/61904 [5:22:48<19:55:31,  1.42s/it]
 18%|█▊        | 11227/61904 [5:22:50<19:39:30,  1.40s/it]
 18%|█▊        | 11228/61904 [5:22:51<19:15:58,  1.37s/it]
 18%|█▊        | 11229/61904 [5:22:52<19:25:21,  1.38s/it]
 18%|█▊        | 11230/61904 [5:22:54<20:11:20,  1.43s/it]
 18%|█▊        | 11231/61904 [5:22:55<19:18:27,  1.37s/it]
 18%|█▊        | 11232/61904 [5:22:56<18:46:06,  1.33s/it]
 18%|█▊        | 11233/61904 [5:22:58<18:31:34,  1.32s/it]
 18%|█▊        | 11234/61904 [5:22:59<18:33:06,  1.32s/it]
 18%|█▊        | 11235/61904 [5:23:00<18:46:26,  1.33s/it]
 18%|█▊        | 11236/61904 [5:23:02<19:19:47,  1.37s/it]
 18%|█▊        | 11237/61904 [5:23:03<19:08:10,  1.36s/it]
 18%|█▊        | 11238/61904 [5:23:05<19:35:09,  1.39s/it]
 18%|█▊        | 11239/61904 [5:23:06<19:23:37,  1.38s/it]
 18%|█▊        | 11240/61904 [5:23:07<18:49:20,  1.34s/it]
                                                          
{'loss': 2.853, 'learning_rate': 1.821081291326332e-07, 'epoch': 2.9}

 18%|█▊        | 11240/61904 [5:23:07<18:49:20,  1.34s/it]
 18%|█▊        | 11241/61904 [5:23:08<18:26:21,  1.31s/it]
 18%|█▊        | 11242/61904 [5:23:10<18:22:07,  1.31s/it]
 18%|█▊        | 11243/61904 [5:23:11<19:26:31,  1.38s/it]
 18%|█▊        | 11244/61904 [5:23:13<19:30:10,  1.39s/it]
 18%|█▊        | 11245/61904 [5:23:14<18:50:01,  1.34s/it]
 18%|█▊        | 11246/61904 [5:23:15<19:25:16,  1.38s/it]
 18%|█▊        | 11247/61904 [5:23:17<19:27:15,  1.38s/it]
 18%|█▊        | 11248/61904 [5:23:18<19:38:31,  1.40s/it]
 18%|█▊        | 11249/61904 [5:23:20<19:50:21,  1.41s/it]
 18%|█▊        | 11250/61904 [5:23:21<19:40:50,  1.40s/it]
 18%|█▊        | 11251/61904 [5:23:23<20:37:09,  1.47s/it]
 18%|█▊        | 11252/61904 [5:23:24<21:04:32,  1.50s/it]
 18%|█▊        | 11253/61904 [5:23:26<21:08:10,  1.50s/it]
 18%|█▊        | 11254/61904 [5:23:27<20:19:45,  1.44s/it]
 18%|█▊        | 11255/61904 [5:23:28<20:18:11,  1.44s/it]
 18%|█▊        | 11256/61904 [5:23:30<19:17:59,  1.37s/it]
 18%|█▊        | 11257/61904 [5:23:31<18:46:09,  1.33s/it]
 18%|█▊        | 11258/61904 [5:23:32<18:42:46,  1.33s/it]
 18%|█▊        | 11259/61904 [5:23:33<18:37:24,  1.32s/it]
 18%|█▊        | 11260/61904 [5:23:35<18:54:13,  1.34s/it]
                                                          
{'loss': 2.8419, 'learning_rate': 1.820757163230909e-07, 'epoch': 2.91}

 18%|█▊        | 11260/61904 [5:23:35<18:54:13,  1.34s/it]
 18%|█▊        | 11261/61904 [5:23:36<19:11:53,  1.36s/it]
 18%|█▊        | 11262/61904 [5:23:38<19:11:39,  1.36s/it]
 18%|█▊        | 11263/61904 [5:23:39<19:12:10,  1.37s/it]
 18%|█▊        | 11264/61904 [5:23:41<19:47:00,  1.41s/it]
 18%|█▊        | 11265/61904 [5:23:42<19:21:26,  1.38s/it]
 18%|█▊        | 11266/61904 [5:23:43<19:35:45,  1.39s/it]
 18%|█▊        | 11267/61904 [5:23:45<19:35:47,  1.39s/it]
 18%|█▊        | 11268/61904 [5:23:46<19:12:17,  1.37s/it]
 18%|█▊        | 11269/61904 [5:23:47<18:39:40,  1.33s/it]
 18%|█▊        | 11270/61904 [5:23:49<18:45:58,  1.33s/it]
 18%|█▊        | 11271/61904 [5:23:50<19:23:57,  1.38s/it]
 18%|█▊        | 11272/61904 [5:23:52<20:06:24,  1.43s/it]
 18%|█▊        | 11273/61904 [5:23:53<20:38:29,  1.47s/it]
 18%|█▊        | 11274/61904 [5:23:55<20:43:45,  1.47s/it]
 18%|█▊        | 11275/61904 [5:23:56<20:14:52,  1.44s/it]
 18%|█▊        | 11276/61904 [5:23:57<20:10:16,  1.43s/it]
 18%|█▊        | 11277/61904 [5:23:59<19:37:28,  1.40s/it]
 18%|█▊        | 11278/61904 [5:24:00<19:20:58,  1.38s/it]
 18%|█▊        | 11279/61904 [5:24:02<19:44:29,  1.40s/it]
 18%|█▊        | 11280/61904 [5:24:03<19:37:04,  1.40s/it]
                                                          
{'loss': 2.8818, 'learning_rate': 1.8204330351354856e-07, 'epoch': 2.92}

 18%|█▊        | 11280/61904 [5:24:03<19:37:04,  1.40s/it]
 18%|█▊        | 11281/61904 [5:24:04<19:40:14,  1.40s/it]
 18%|█▊        | 11282/61904 [5:24:06<19:35:44,  1.39s/it]
 18%|█▊        | 11283/61904 [5:24:07<19:50:53,  1.41s/it]
 18%|█▊        | 11284/61904 [5:24:08<19:08:37,  1.36s/it]
 18%|█▊        | 11285/61904 [5:24:10<19:56:38,  1.42s/it]
 18%|█▊        | 11286/61904 [5:24:11<19:40:47,  1.40s/it]
 18%|█▊        | 11287/61904 [5:24:13<19:17:38,  1.37s/it]
 18%|█▊        | 11288/61904 [5:24:14<19:39:51,  1.40s/it]
 18%|█▊        | 11289/61904 [5:24:16<19:58:07,  1.42s/it]
 18%|█▊        | 11290/61904 [5:24:17<19:35:59,  1.39s/it]
 18%|█▊        | 11291/61904 [5:24:18<20:27:31,  1.46s/it]
 18%|█▊        | 11292/61904 [5:24:20<20:39:44,  1.47s/it]
 18%|█▊        | 11293/61904 [5:24:21<20:34:59,  1.46s/it]
 18%|█▊        | 11294/61904 [5:24:23<20:25:03,  1.45s/it]
 18%|█▊        | 11295/61904 [5:24:24<20:07:28,  1.43s/it]
 18%|█▊        | 11296/61904 [5:24:26<19:58:26,  1.42s/it]
 18%|█▊        | 11297/61904 [5:24:27<20:18:22,  1.44s/it]
 18%|█▊        | 11298/61904 [5:24:29<20:04:41,  1.43s/it]
 18%|█▊        | 11299/61904 [5:24:30<19:35:01,  1.39s/it]
 18%|█▊        | 11300/61904 [5:24:31<19:54:03,  1.42s/it]
                                                          
{'loss': 2.7992, 'learning_rate': 1.8201089070400622e-07, 'epoch': 2.92}

 18%|█▊        | 11300/61904 [5:24:31<19:54:03,  1.42s/it]
 18%|█▊        | 11301/61904 [5:24:33<19:39:54,  1.40s/it]
 18%|█▊        | 11302/61904 [5:24:34<19:32:52,  1.39s/it]
 18%|█▊        | 11303/61904 [5:24:35<19:49:47,  1.41s/it]
 18%|█▊        | 11304/61904 [5:24:37<19:46:16,  1.41s/it]
 18%|█▊        | 11305/61904 [5:24:38<19:38:53,  1.40s/it]
 18%|█▊        | 11306/61904 [5:24:40<20:35:09,  1.46s/it]
 18%|█▊        | 11307/61904 [5:24:41<20:13:12,  1.44s/it]
 18%|█▊        | 11308/61904 [5:24:43<20:03:59,  1.43s/it]
 18%|█▊        | 11309/61904 [5:24:44<19:30:13,  1.39s/it]
 18%|█▊        | 11310/61904 [5:24:45<20:00:58,  1.42s/it]
 18%|█▊        | 11311/61904 [5:24:47<19:55:41,  1.42s/it]
 18%|█▊        | 11312/61904 [5:24:48<19:32:43,  1.39s/it]
 18%|█▊        | 11313/61904 [5:24:50<19:16:49,  1.37s/it]
 18%|█▊        | 11314/61904 [5:24:51<19:10:40,  1.36s/it]
 18%|█▊        | 11315/61904 [5:24:52<19:29:52,  1.39s/it]
 18%|█▊        | 11316/61904 [5:24:54<19:40:09,  1.40s/it]
 18%|█▊        | 11317/61904 [5:24:55<19:21:51,  1.38s/it]
 18%|█▊        | 11318/61904 [5:24:56<19:35:36,  1.39s/it]
 18%|█▊        | 11319/61904 [5:24:58<19:43:53,  1.40s/it]
 18%|█▊        | 11320/61904 [5:24:59<19:30:26,  1.39s/it]
                                                          
{'loss': 2.8553, 'learning_rate': 1.8197847789446388e-07, 'epoch': 2.93}

 18%|█▊        | 11320/61904 [5:24:59<19:30:26,  1.39s/it]
 18%|█▊        | 11321/61904 [5:25:01<19:22:06,  1.38s/it]
 18%|█▊        | 11322/61904 [5:25:02<19:32:07,  1.39s/it]
 18%|█▊        | 11323/61904 [5:25:04<19:57:15,  1.42s/it]
 18%|█▊        | 11324/61904 [5:25:05<19:49:26,  1.41s/it]
 18%|█▊        | 11325/61904 [5:25:06<20:06:24,  1.43s/it]
 18%|█▊        | 11326/61904 [5:25:08<19:12:38,  1.37s/it]
 18%|█▊        | 11327/61904 [5:25:09<19:26:51,  1.38s/it]
 18%|█▊        | 11328/61904 [5:25:10<19:20:05,  1.38s/it]
 18%|█▊        | 11329/61904 [5:25:12<19:25:51,  1.38s/it]
 18%|█▊        | 11330/61904 [5:25:13<19:44:44,  1.41s/it]
 18%|█▊        | 11331/61904 [5:25:15<19:05:06,  1.36s/it]
 18%|█▊        | 11332/61904 [5:25:16<19:31:06,  1.39s/it]
 18%|█▊        | 11333/61904 [5:25:17<19:19:38,  1.38s/it]
 18%|█▊        | 11334/61904 [5:25:19<19:15:43,  1.37s/it]
 18%|█▊        | 11335/61904 [5:25:20<18:55:34,  1.35s/it]
 18%|█▊        | 11336/61904 [5:25:21<19:23:16,  1.38s/it]
 18%|█▊        | 11337/61904 [5:25:23<20:06:48,  1.43s/it]
 18%|█▊        | 11338/61904 [5:25:24<19:51:15,  1.41s/it]
 18%|█▊        | 11339/61904 [5:25:26<20:10:05,  1.44s/it]
 18%|█▊        | 11340/61904 [5:25:27<19:48:47,  1.41s/it]
                                                          
{'loss': 2.7901, 'learning_rate': 1.8194606508492154e-07, 'epoch': 2.93}

 18%|█▊        | 11340/61904 [5:25:27<19:48:47,  1.41s/it]
 18%|█▊        | 11341/61904 [5:25:29<19:32:06,  1.39s/it]
 18%|█▊        | 11342/61904 [5:25:30<19:12:02,  1.37s/it]
 18%|█▊        | 11343/61904 [5:25:31<19:03:05,  1.36s/it]
 18%|█▊        | 11344/61904 [5:25:32<18:44:05,  1.33s/it]
 18%|█▊        | 11345/61904 [5:25:34<18:46:14,  1.34s/it]
 18%|█▊        | 11346/61904 [5:25:35<19:16:53,  1.37s/it]
 18%|█▊        | 11347/61904 [5:25:37<19:03:11,  1.36s/it]
 18%|█▊        | 11348/61904 [5:25:38<19:07:12,  1.36s/it]
 18%|█▊        | 11349/61904 [5:25:39<18:46:47,  1.34s/it]
 18%|█▊        | 11350/61904 [5:25:40<18:20:58,  1.31s/it]
 18%|█▊        | 11351/61904 [5:25:42<18:17:26,  1.30s/it]
 18%|█▊        | 11352/61904 [5:25:43<18:47:35,  1.34s/it]
 18%|█▊        | 11353/61904 [5:25:45<19:06:26,  1.36s/it]
 18%|█▊        | 11354/61904 [5:25:46<18:57:48,  1.35s/it]
 18%|█▊        | 11355/61904 [5:25:47<19:03:18,  1.36s/it]
 18%|█▊        | 11356/61904 [5:25:49<18:53:19,  1.35s/it]
 18%|█▊        | 11357/61904 [5:25:50<19:19:59,  1.38s/it]
 18%|█▊        | 11358/61904 [5:25:52<20:02:15,  1.43s/it]
 18%|█▊        | 11359/61904 [5:25:53<19:46:59,  1.41s/it]
 18%|█▊        | 11360/61904 [5:25:54<20:04:14,  1.43s/it]
                                                          
{'loss': 2.7795, 'learning_rate': 1.8191365227537923e-07, 'epoch': 2.94}

 18%|█▊        | 11360/61904 [5:25:54<20:04:14,  1.43s/it]
 18%|█▊        | 11361/61904 [5:25:56<19:59:28,  1.42s/it]
 18%|█▊        | 11362/61904 [5:25:57<20:00:39,  1.43s/it]
 18%|█▊        | 11363/61904 [5:25:59<20:35:31,  1.47s/it]
 18%|█▊        | 11364/61904 [5:26:00<19:38:06,  1.40s/it]
 18%|█▊        | 11365/61904 [5:26:01<19:26:09,  1.38s/it]
 18%|█▊        | 11366/61904 [5:26:03<19:35:32,  1.40s/it]
 18%|█▊        | 11367/61904 [5:26:04<19:07:27,  1.36s/it]
 18%|█▊        | 11368/61904 [5:26:06<19:25:45,  1.38s/it]
 18%|█▊        | 11369/61904 [5:26:07<19:55:58,  1.42s/it]
 18%|█▊        | 11370/61904 [5:26:09<20:22:29,  1.45s/it]
 18%|█▊        | 11371/61904 [5:26:10<19:57:58,  1.42s/it]
 18%|█▊        | 11372/61904 [5:26:11<19:48:00,  1.41s/it]
 18%|█▊        | 11373/61904 [5:26:13<19:33:44,  1.39s/it]
 18%|█▊        | 11374/61904 [5:26:14<19:35:45,  1.40s/it]
 18%|█▊        | 11375/61904 [5:26:15<19:16:45,  1.37s/it]
 18%|█▊        | 11376/61904 [5:26:17<19:31:38,  1.39s/it]
 18%|█▊        | 11377/61904 [5:26:18<19:19:04,  1.38s/it]
 18%|█▊        | 11378/61904 [5:26:20<19:39:33,  1.40s/it]
 18%|█▊        | 11379/61904 [5:26:21<19:46:31,  1.41s/it]
 18%|█▊        | 11380/61904 [5:26:22<19:44:20,  1.41s/it]
                                                          
{'loss': 2.7977, 'learning_rate': 1.818812394658369e-07, 'epoch': 2.94}

 18%|█▊        | 11380/61904 [5:26:22<19:44:20,  1.41s/it]
 18%|█▊        | 11381/61904 [5:26:24<19:45:56,  1.41s/it]
 18%|█▊        | 11382/61904 [5:26:25<19:35:45,  1.40s/it]
 18%|█▊        | 11383/61904 [5:26:27<20:00:12,  1.43s/it]
 18%|█▊        | 11384/61904 [5:26:28<19:54:24,  1.42s/it]
 18%|█▊        | 11385/61904 [5:26:29<19:28:25,  1.39s/it]
 18%|█▊        | 11386/61904 [5:26:31<19:38:53,  1.40s/it]
 18%|█▊        | 11387/61904 [5:26:32<19:32:21,  1.39s/it]
 18%|█▊        | 11388/61904 [5:26:34<19:37:57,  1.40s/it]
 18%|█▊        | 11389/61904 [5:26:35<19:48:10,  1.41s/it]
 18%|█▊        | 11390/61904 [5:26:37<19:52:41,  1.42s/it]
 18%|█▊        | 11391/61904 [5:26:38<19:54:09,  1.42s/it]
 18%|█▊        | 11392/61904 [5:26:40<20:22:33,  1.45s/it]
 18%|█▊        | 11393/61904 [5:26:41<20:34:22,  1.47s/it]
 18%|█▊        | 11394/61904 [5:26:42<19:54:52,  1.42s/it]
 18%|█▊        | 11395/61904 [5:26:44<19:35:02,  1.40s/it]
 18%|█▊        | 11396/61904 [5:26:45<19:36:58,  1.40s/it]
 18%|█▊        | 11397/61904 [5:26:46<19:26:29,  1.39s/it]
 18%|█▊        | 11398/61904 [5:26:48<19:30:31,  1.39s/it]
 18%|█▊        | 11399/61904 [5:26:49<18:56:29,  1.35s/it]
 18%|█▊        | 11400/61904 [5:26:50<19:05:53,  1.36s/it]
                                                          
{'loss': 2.7824, 'learning_rate': 1.8184882665629455e-07, 'epoch': 2.95}

 18%|█▊        | 11400/61904 [5:26:50<19:05:53,  1.36s/it]
 18%|█▊        | 11401/61904 [5:26:52<19:15:30,  1.37s/it]
 18%|█▊        | 11402/61904 [5:26:53<19:19:38,  1.38s/it]
 18%|█▊        | 11403/61904 [5:26:55<20:00:35,  1.43s/it]
 18%|█▊        | 11404/61904 [5:26:56<20:03:44,  1.43s/it]
 18%|█▊        | 11405/61904 [5:26:58<19:40:24,  1.40s/it]
 18%|█▊        | 11406/61904 [5:26:59<19:27:25,  1.39s/it]
 18%|█▊        | 11407/61904 [5:27:00<19:32:56,  1.39s/it]
 18%|█▊        | 11408/61904 [5:27:02<19:28:20,  1.39s/it]
 18%|█▊        | 11409/61904 [5:27:03<19:41:42,  1.40s/it]
 18%|█▊        | 11410/61904 [5:27:04<18:46:29,  1.34s/it]
 18%|█▊        | 11411/61904 [5:27:06<18:41:09,  1.33s/it]
 18%|█▊        | 11412/61904 [5:27:07<19:04:00,  1.36s/it]
 18%|█▊        | 11413/61904 [5:27:09<19:24:10,  1.38s/it]
 18%|█▊        | 11414/61904 [5:27:10<19:33:26,  1.39s/it]
 18%|█▊        | 11415/61904 [5:27:11<19:34:05,  1.40s/it]
 18%|█▊        | 11416/61904 [5:27:13<19:22:02,  1.38s/it]
 18%|█▊        | 11417/61904 [5:27:14<18:44:50,  1.34s/it]
 18%|█▊        | 11418/61904 [5:27:15<18:50:09,  1.34s/it]
 18%|█▊        | 11419/61904 [5:27:17<20:02:44,  1.43s/it]
 18%|█▊        | 11420/61904 [5:27:18<19:33:21,  1.39s/it]
                                                          
{'loss': 2.7671, 'learning_rate': 1.8181641384675224e-07, 'epoch': 2.95}

 18%|█▊        | 11420/61904 [5:27:18<19:33:21,  1.39s/it]
 18%|█▊        | 11421/61904 [5:27:20<19:10:18,  1.37s/it]
 18%|█▊        | 11422/61904 [5:27:21<18:57:02,  1.35s/it]
 18%|█▊        | 11423/61904 [5:27:22<19:13:15,  1.37s/it]
 18%|█▊        | 11424/61904 [5:27:24<19:46:48,  1.41s/it]
 18%|█▊        | 11425/61904 [5:27:25<19:19:56,  1.38s/it]
 18%|█▊        | 11426/61904 [5:27:26<18:47:20,  1.34s/it]
 18%|█▊        | 11427/61904 [5:27:28<18:55:58,  1.35s/it]
 18%|█▊        | 11428/61904 [5:27:29<19:35:06,  1.40s/it]
 18%|█▊        | 11429/61904 [5:27:31<19:36:00,  1.40s/it]
 18%|█▊        | 11430/61904 [5:27:32<19:46:52,  1.41s/it]
 18%|█▊        | 11431/61904 [5:27:33<19:07:25,  1.36s/it]
 18%|█▊        | 11432/61904 [5:27:35<18:57:07,  1.35s/it]
 18%|█▊        | 11433/61904 [5:27:36<19:25:29,  1.39s/it]
 18%|█▊        | 11434/61904 [5:27:37<19:08:33,  1.37s/it]
 18%|█▊        | 11435/61904 [5:27:39<18:58:46,  1.35s/it]
 18%|█▊        | 11436/61904 [5:27:40<18:57:55,  1.35s/it]
 18%|█▊        | 11437/61904 [5:27:41<18:59:02,  1.35s/it]
 18%|█▊        | 11438/61904 [5:27:43<19:04:56,  1.36s/it]
 18%|█▊        | 11439/61904 [5:27:44<20:09:59,  1.44s/it]
 18%|█▊        | 11440/61904 [5:27:46<20:02:05,  1.43s/it]
                                                          
{'loss': 2.8553, 'learning_rate': 1.817840010372099e-07, 'epoch': 2.96}

 18%|█▊        | 11440/61904 [5:27:46<20:02:05,  1.43s/it]
 18%|█▊        | 11441/61904 [5:27:47<20:22:59,  1.45s/it]
 18%|█▊        | 11442/61904 [5:27:49<19:37:48,  1.40s/it]
 18%|█▊        | 11443/61904 [5:27:50<19:20:34,  1.38s/it]
 18%|█▊        | 11444/61904 [5:27:51<19:46:39,  1.41s/it]
 18%|█▊        | 11445/61904 [5:27:53<19:47:10,  1.41s/it]
 18%|█▊        | 11446/61904 [5:27:54<20:15:43,  1.45s/it]
 18%|█▊        | 11447/61904 [5:27:56<19:56:56,  1.42s/it]
 18%|█▊        | 11448/61904 [5:27:57<19:44:40,  1.41s/it]
 18%|█▊        | 11449/61904 [5:27:58<18:54:42,  1.35s/it]
 18%|█▊        | 11450/61904 [5:28:00<19:41:29,  1.41s/it]
 18%|█▊        | 11451/61904 [5:28:01<19:17:15,  1.38s/it]
 18%|█▊        | 11452/61904 [5:28:03<19:23:17,  1.38s/it]
 19%|█▊        | 11453/61904 [5:28:04<19:35:39,  1.40s/it]
 19%|█▊        | 11454/61904 [5:28:06<19:59:33,  1.43s/it]
 19%|█▊        | 11455/61904 [5:28:07<19:29:01,  1.39s/it]
 19%|█▊        | 11456/61904 [5:28:08<19:03:34,  1.36s/it]
 19%|█▊        | 11457/61904 [5:28:09<18:30:51,  1.32s/it]
 19%|█▊        | 11458/61904 [5:28:11<18:39:12,  1.33s/it]
 19%|█▊        | 11459/61904 [5:28:12<18:48:07,  1.34s/it]
 19%|█▊        | 11460/61904 [5:28:14<19:38:48,  1.40s/it]
                                                          
{'loss': 2.7253, 'learning_rate': 1.8175158822766757e-07, 'epoch': 2.96}

 19%|█▊        | 11460/61904 [5:28:14<19:38:48,  1.40s/it]
 19%|█▊        | 11461/61904 [5:28:15<19:05:58,  1.36s/it]
 19%|█▊        | 11462/61904 [5:28:16<19:01:07,  1.36s/it]
 19%|█▊        | 11463/61904 [5:28:17<18:35:45,  1.33s/it]
 19%|█▊        | 11464/61904 [5:28:19<18:32:28,  1.32s/it]
 19%|█▊        | 11465/61904 [5:28:20<18:23:50,  1.31s/it]
 19%|█▊        | 11466/61904 [5:28:21<18:49:43,  1.34s/it]
 19%|█▊        | 11467/61904 [5:28:23<18:45:20,  1.34s/it]
 19%|█▊        | 11468/61904 [5:28:24<19:00:06,  1.36s/it]
 19%|█▊        | 11469/61904 [5:28:26<19:01:49,  1.36s/it]
 19%|█▊        | 11470/61904 [5:28:27<19:19:12,  1.38s/it]
 19%|█▊        | 11471/61904 [5:28:28<18:53:57,  1.35s/it]
 19%|█▊        | 11472/61904 [5:28:30<19:28:42,  1.39s/it]
 19%|█▊        | 11473/61904 [5:28:31<19:13:51,  1.37s/it]
 19%|█▊        | 11474/61904 [5:28:33<19:30:36,  1.39s/it]
 19%|█▊        | 11475/61904 [5:28:34<19:18:39,  1.38s/it]
 19%|█▊        | 11476/61904 [5:28:35<20:01:46,  1.43s/it]
 19%|█▊        | 11477/61904 [5:28:37<19:37:02,  1.40s/it]
 19%|█▊        | 11478/61904 [5:28:38<18:45:35,  1.34s/it]
 19%|█▊        | 11479/61904 [5:28:39<18:58:21,  1.35s/it]
 19%|█▊        | 11480/61904 [5:28:41<18:58:13,  1.35s/it]
                                                          
{'loss': 2.8338, 'learning_rate': 1.8171917541812525e-07, 'epoch': 2.97}

 19%|█▊        | 11480/61904 [5:28:41<18:58:13,  1.35s/it]
 19%|█▊        | 11481/61904 [5:28:42<19:08:13,  1.37s/it]
 19%|█▊        | 11482/61904 [5:28:43<18:57:01,  1.35s/it]
 19%|█▊        | 11483/61904 [5:28:45<19:05:33,  1.36s/it]
 19%|█▊        | 11484/61904 [5:28:46<18:44:07,  1.34s/it]
 19%|█▊        | 11485/61904 [5:28:47<18:26:35,  1.32s/it]
 19%|█▊        | 11486/61904 [5:28:49<18:36:40,  1.33s/it]
 19%|█▊        | 11487/61904 [5:28:50<18:26:11,  1.32s/it]
 19%|█▊        | 11488/61904 [5:28:51<18:39:38,  1.33s/it]
 19%|█▊        | 11489/61904 [5:28:53<18:57:02,  1.35s/it]
 19%|█▊        | 11490/61904 [5:28:54<18:35:46,  1.33s/it]
 19%|█▊        | 11491/61904 [5:28:55<18:43:33,  1.34s/it]
 19%|█▊        | 11492/61904 [5:28:57<18:55:36,  1.35s/it]
 19%|█▊        | 11493/61904 [5:28:58<18:46:17,  1.34s/it]
 19%|█▊        | 11494/61904 [5:29:00<19:03:32,  1.36s/it]
 19%|█▊        | 11495/61904 [5:29:01<18:38:37,  1.33s/it]
 19%|█▊        | 11496/61904 [5:29:02<18:55:56,  1.35s/it]
 19%|█▊        | 11497/61904 [5:29:03<18:08:49,  1.30s/it]
 19%|█▊        | 11498/61904 [5:29:05<19:21:11,  1.38s/it]
 19%|█▊        | 11499/61904 [5:29:06<19:31:01,  1.39s/it]
 19%|█▊        | 11500/61904 [5:29:08<19:56:06,  1.42s/it]
                                                          
{'loss': 2.7843, 'learning_rate': 1.816867626085829e-07, 'epoch': 2.97}

 19%|█▊        | 11500/61904 [5:29:08<19:56:06,  1.42s/it]
 19%|█▊        | 11501/61904 [5:29:09<19:51:25,  1.42s/it]
 19%|█▊        | 11502/61904 [5:29:11<19:41:03,  1.41s/it]
 19%|█▊        | 11503/61904 [5:29:12<20:18:35,  1.45s/it]
 19%|█▊        | 11504/61904 [5:29:14<19:49:26,  1.42s/it]
 19%|█▊        | 11505/61904 [5:29:15<19:11:33,  1.37s/it]
 19%|█▊        | 11506/61904 [5:29:16<19:16:20,  1.38s/it]
 19%|█▊        | 11507/61904 [5:29:18<19:14:38,  1.37s/it]
 19%|█▊        | 11508/61904 [5:29:19<18:49:02,  1.34s/it]
 19%|█▊        | 11509/61904 [5:29:20<19:24:25,  1.39s/it]
 19%|█▊        | 11510/61904 [5:29:22<18:46:29,  1.34s/it]
 19%|█▊        | 11511/61904 [5:29:23<18:57:36,  1.35s/it]
 19%|█▊        | 11512/61904 [5:29:24<18:42:40,  1.34s/it]
 19%|█▊        | 11513/61904 [5:29:26<19:44:54,  1.41s/it]
 19%|█▊        | 11514/61904 [5:29:27<19:27:42,  1.39s/it]
 19%|█▊        | 11515/61904 [5:29:29<19:23:00,  1.38s/it]
 19%|█▊        | 11516/61904 [5:29:30<19:19:12,  1.38s/it]
 19%|█▊        | 11517/61904 [5:29:31<18:26:03,  1.32s/it]
 19%|█▊        | 11518/61904 [5:29:32<18:23:35,  1.31s/it]
 19%|█▊        | 11519/61904 [5:29:34<18:42:16,  1.34s/it]
 19%|█▊        | 11520/61904 [5:29:35<18:49:49,  1.35s/it]
                                                          
{'loss': 2.8181, 'learning_rate': 1.8165434979904058e-07, 'epoch': 2.98}

 19%|█▊        | 11520/61904 [5:29:35<18:49:49,  1.35s/it]
 19%|█▊        | 11521/61904 [5:29:37<19:07:12,  1.37s/it]
 19%|█▊        | 11522/61904 [5:29:38<19:25:31,  1.39s/it]
 19%|█▊        | 11523/61904 [5:29:39<19:01:35,  1.36s/it]
 19%|█▊        | 11524/61904 [5:29:40<18:29:12,  1.32s/it]
 19%|█▊        | 11525/61904 [5:29:42<19:20:38,  1.38s/it]
 19%|█▊        | 11526/61904 [5:29:43<19:01:36,  1.36s/it]
 19%|█▊        | 11527/61904 [5:29:45<19:39:32,  1.40s/it]
 19%|█▊        | 11528/61904 [5:29:46<19:38:15,  1.40s/it]
 19%|█▊        | 11529/61904 [5:29:48<19:50:35,  1.42s/it]
 19%|█▊        | 11530/61904 [5:29:49<19:15:23,  1.38s/it]
 19%|█▊        | 11531/61904 [5:29:50<18:54:28,  1.35s/it]
 19%|█▊        | 11532/61904 [5:29:52<19:09:57,  1.37s/it]
 19%|█▊        | 11533/61904 [5:29:53<19:09:38,  1.37s/it]
 19%|█▊        | 11534/61904 [5:29:54<19:11:20,  1.37s/it]
 19%|█▊        | 11535/61904 [5:29:56<18:42:55,  1.34s/it]
 19%|█▊        | 11536/61904 [5:29:57<19:21:56,  1.38s/it]
 19%|█▊        | 11537/61904 [5:29:59<19:36:38,  1.40s/it]
 19%|█▊        | 11538/61904 [5:30:00<19:42:05,  1.41s/it]
 19%|█▊        | 11539/61904 [5:30:01<19:31:29,  1.40s/it]
 19%|█▊        | 11540/61904 [5:30:03<19:16:06,  1.38s/it]
                                                          
{'loss': 2.7918, 'learning_rate': 1.8162193698949824e-07, 'epoch': 2.98}

 19%|█▊        | 11540/61904 [5:30:03<19:16:06,  1.38s/it]
 19%|█▊        | 11541/61904 [5:30:04<19:07:45,  1.37s/it]
 19%|█▊        | 11542/61904 [5:30:06<19:59:29,  1.43s/it]
 19%|█▊        | 11543/61904 [5:30:07<19:44:25,  1.41s/it]
 19%|█▊        | 11544/61904 [5:30:08<19:12:44,  1.37s/it]
 19%|█▊        | 11545/61904 [5:30:10<18:49:06,  1.35s/it]
 19%|█▊        | 11546/61904 [5:30:11<18:34:09,  1.33s/it]
 19%|█▊        | 11547/61904 [5:30:12<18:40:43,  1.34s/it]
 19%|█▊        | 11548/61904 [5:30:14<19:06:24,  1.37s/it]
 19%|█▊        | 11549/61904 [5:30:15<18:57:15,  1.36s/it]
 19%|█▊        | 11550/61904 [5:30:16<19:14:27,  1.38s/it]
 19%|█▊        | 11551/61904 [5:30:18<19:19:56,  1.38s/it]
 19%|█▊        | 11552/61904 [5:30:19<19:14:51,  1.38s/it]
 19%|█▊        | 11553/61904 [5:30:21<19:58:11,  1.43s/it]
 19%|█▊        | 11554/61904 [5:30:22<18:51:14,  1.35s/it]
 19%|█▊        | 11555/61904 [5:30:23<18:53:18,  1.35s/it]
 19%|█▊        | 11556/61904 [5:30:24<18:20:27,  1.31s/it]
 19%|█▊        | 11557/61904 [5:30:26<18:18:46,  1.31s/it]
 19%|█▊        | 11558/61904 [5:30:27<18:30:29,  1.32s/it]
 19%|█▊        | 11559/61904 [5:30:29<19:05:18,  1.36s/it]
 19%|█▊        | 11560/61904 [5:30:30<18:49:57,  1.35s/it]
                                                          
{'loss': 2.8051, 'learning_rate': 1.815895241799559e-07, 'epoch': 2.99}

 19%|█▊        | 11560/61904 [5:30:30<18:49:57,  1.35s/it]
 19%|█▊        | 11561/61904 [5:30:31<19:06:56,  1.37s/it]
 19%|█▊        | 11562/61904 [5:30:33<19:17:42,  1.38s/it]
 19%|█▊        | 11563/61904 [5:30:34<19:34:08,  1.40s/it]
 19%|█▊        | 11564/61904 [5:30:36<20:11:21,  1.44s/it]
 19%|█▊        | 11565/61904 [5:30:37<21:04:19,  1.51s/it]
 19%|█▊        | 11566/61904 [5:30:39<20:11:10,  1.44s/it]
 19%|█▊        | 11567/61904 [5:30:40<19:50:05,  1.42s/it]
 19%|█▊        | 11568/61904 [5:30:41<19:13:13,  1.37s/it]
 19%|█▊        | 11569/61904 [5:30:43<19:40:07,  1.41s/it]
 19%|█▊        | 11570/61904 [5:30:44<19:08:28,  1.37s/it]
 19%|█▊        | 11571/61904 [5:30:45<18:51:07,  1.35s/it]
 19%|█▊        | 11572/61904 [5:30:47<18:42:00,  1.34s/it]
 19%|█▊        | 11573/61904 [5:30:48<18:16:24,  1.31s/it]
 19%|█▊        | 11574/61904 [5:30:49<18:29:35,  1.32s/it]
 19%|█▊        | 11575/61904 [5:30:51<18:39:35,  1.33s/it]
 19%|█▊        | 11576/61904 [5:30:52<18:56:09,  1.35s/it]
 19%|█▊        | 11577/61904 [5:30:53<18:25:58,  1.32s/it]
 19%|█▊        | 11578/61904 [5:30:55<18:28:08,  1.32s/it]
 19%|█▊        | 11579/61904 [5:30:56<18:29:51,  1.32s/it]
 19%|█▊        | 11580/61904 [5:30:57<18:31:42,  1.33s/it]
                                                          
{'loss': 2.8276, 'learning_rate': 1.815571113704136e-07, 'epoch': 2.99}

 19%|█▊        | 11580/61904 [5:30:57<18:31:42,  1.33s/it]
 19%|█▊        | 11581/61904 [5:30:59<18:39:59,  1.34s/it]
 19%|█▊        | 11582/61904 [5:31:00<19:21:04,  1.38s/it]
 19%|█▊        | 11583/61904 [5:31:02<21:30:21,  1.54s/it]
 19%|█▊        | 11584/61904 [5:31:03<20:38:07,  1.48s/it]
 19%|█▊        | 11585/61904 [5:31:05<20:54:35,  1.50s/it]
 19%|█▊        | 11586/61904 [5:31:06<19:56:48,  1.43s/it]
 19%|█▊        | 11587/61904 [5:31:07<19:14:43,  1.38s/it]
 19%|█▊        | 11588/61904 [5:31:09<18:52:41,  1.35s/it]
 19%|█▊        | 11589/61904 [5:31:10<18:26:49,  1.32s/it]
 19%|█▊        | 11590/61904 [5:31:11<18:33:11,  1.33s/it]
 19%|█▊        | 11591/61904 [5:31:13<18:34:34,  1.33s/it]
 19%|█▊        | 11592/61904 [5:31:14<20:02:51,  1.43s/it]
 19%|█▊        | 11593/61904 [5:31:16<19:50:18,  1.42s/it]
 19%|█▊        | 11594/61904 [5:31:17<20:07:18,  1.44s/it]
 19%|█▊        | 11595/61904 [5:31:18<19:27:35,  1.39s/it]
 19%|█▊        | 11596/61904 [5:31:20<18:59:37,  1.36s/it]
 19%|█▊        | 11597/61904 [5:31:21<19:40:46,  1.41s/it]
 19%|█▊        | 11598/61904 [5:31:22<19:02:26,  1.36s/it]
 19%|█▊        | 11599/61904 [5:31:24<18:35:39,  1.33s/it]
 19%|█▊        | 11600/61904 [5:31:25<18:42:04,  1.34s/it]
                                                          
{'loss': 2.8109, 'learning_rate': 1.8152469856087125e-07, 'epoch': 3.0}

 19%|█▊        | 11600/61904 [5:31:25<18:42:04,  1.34s/it]
 19%|█▊        | 11601/61904 [5:31:26<18:38:19,  1.33s/it]
 19%|█▊        | 11602/61904 [5:31:28<18:34:03,  1.33s/it]
 19%|█▊        | 11603/61904 [5:31:29<18:44:09,  1.34s/it]
 19%|█▊        | 11604/61904 [5:31:30<18:28:21,  1.32s/it]
 19%|█▊        | 11605/61904 [5:31:32<18:38:11,  1.33s/it]
 19%|█▊        | 11606/61904 [5:31:33<18:25:34,  1.32s/it]
 19%|█▉        | 11607/61904 [5:31:34<18:43:32,  1.34s/it]
 19%|█▉        | 11608/61904 [5:31:36<18:28:34,  1.32s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:02<21:26,  1.50s/it]

  0%|          | 3/861 [00:06<31:58,  2.24s/it]

  0%|          | 4/861 [00:12<50:50,  3.56s/it]

  1%|          | 5/861 [00:14<46:27,  3.26s/it]

  1%|          | 6/861 [00:18<47:34,  3.34s/it]

  1%|          | 7/861 [00:20<41:10,  2.89s/it]

  1%|          | 8/861 [00:23<41:19,  2.91s/it]

  1%|          | 9/861 [00:25<38:29,  2.71s/it]

  1%|          | 10/861 [00:27<37:05,  2.62s/it]

  1%|▏         | 11/861 [00:30<38:34,  2.72s/it]

  1%|▏         | 12/861 [00:34<44:54,  3.17s/it]

  2%|▏         | 13/861 [00:37<41:06,  2.91s/it]

  2%|▏         | 14/861 [00:38<32:38,  2.31s/it]

  2%|▏         | 15/861 [00:40<31:43,  2.25s/it]

  2%|▏         | 16/861 [00:41<27:02,  1.92s/it]

  2%|▏         | 17/861 [00:46<41:16,  2.93s/it]

  2%|▏         | 18/861 [00:48<34:39,  2.47s/it]

  2%|▏         | 19/861 [00:52<40:43,  2.90s/it]

  2%|▏         | 20/861 [00:56<46:21,  3.31s/it]

  2%|▏         | 21/861 [00:58<41:28,  2.96s/it]

  3%|▎         | 22/861 [01:01<40:09,  2.87s/it]

  3%|▎         | 23/861 [01:02<34:10,  2.45s/it]

  3%|▎         | 24/861 [01:05<37:46,  2.71s/it]

  3%|▎         | 25/861 [01:07<35:05,  2.52s/it]

  3%|▎         | 26/861 [01:11<41:04,  2.95s/it]

  3%|▎         | 27/861 [01:14<39:07,  2.81s/it]

  3%|▎         | 28/861 [01:19<46:33,  3.35s/it]

  3%|▎         | 29/861 [01:20<36:48,  2.65s/it]

  3%|▎         | 30/861 [01:24<42:24,  3.06s/it]

  4%|▎         | 31/861 [01:25<34:00,  2.46s/it]

  4%|▎         | 32/861 [01:26<27:27,  1.99s/it]

  4%|▍         | 33/861 [01:29<32:13,  2.34s/it]

  4%|▍         | 34/861 [01:31<30:25,  2.21s/it]

  4%|▍         | 35/861 [01:35<38:33,  2.80s/it]

  4%|▍         | 36/861 [01:37<34:15,  2.49s/it]

  4%|▍         | 37/861 [01:38<31:53,  2.32s/it]

  4%|▍         | 38/861 [01:41<34:37,  2.52s/it]

  5%|▍         | 39/861 [01:43<32:08,  2.35s/it]

  5%|▍         | 40/861 [01:46<31:25,  2.30s/it]

  5%|▍         | 41/861 [01:46<25:32,  1.87s/it]

  5%|▍         | 42/861 [01:50<32:05,  2.35s/it]

  5%|▍         | 43/861 [01:52<31:26,  2.31s/it]

  5%|▌         | 44/861 [01:54<30:09,  2.21s/it]

  5%|▌         | 45/861 [01:57<30:57,  2.28s/it]

  5%|▌         | 46/861 [02:01<39:35,  2.91s/it]

  5%|▌         | 47/861 [02:05<42:26,  3.13s/it]

  6%|▌         | 48/861 [02:07<40:56,  3.02s/it]

  6%|▌         | 49/861 [02:10<39:06,  2.89s/it]

  6%|▌         | 50/861 [02:10<28:27,  2.11s/it]

  6%|▌         | 51/861 [02:11<24:37,  1.82s/it]

  6%|▌         | 52/861 [02:14<26:07,  1.94s/it]

  6%|▌         | 53/861 [02:15<23:11,  1.72s/it]

  6%|▋         | 54/861 [02:15<18:09,  1.35s/it]

  6%|▋         | 55/861 [02:17<19:06,  1.42s/it]

  7%|▋         | 56/861 [02:22<32:35,  2.43s/it]

  7%|▋         | 57/861 [02:23<26:31,  1.98s/it]

  7%|▋         | 58/861 [02:24<22:37,  1.69s/it]

  7%|▋         | 59/861 [02:25<21:53,  1.64s/it]

  7%|▋         | 60/861 [02:27<23:04,  1.73s/it]

  7%|▋         | 61/861 [02:28<21:50,  1.64s/it]

  7%|▋         | 62/861 [02:29<18:30,  1.39s/it]

  7%|▋         | 63/861 [02:31<18:49,  1.42s/it]

  7%|▋         | 64/861 [02:32<18:31,  1.39s/it]

  8%|▊         | 65/861 [02:34<19:40,  1.48s/it]

  8%|▊         | 66/861 [02:35<18:16,  1.38s/it]

  8%|▊         | 67/861 [02:37<21:37,  1.63s/it]

  8%|▊         | 68/861 [02:40<25:36,  1.94s/it]

  8%|▊         | 69/861 [02:44<34:03,  2.58s/it]

  8%|▊         | 70/861 [02:46<32:20,  2.45s/it]

  8%|▊         | 71/861 [02:49<33:47,  2.57s/it]

  8%|▊         | 72/861 [02:52<34:06,  2.59s/it]

  8%|▊         | 73/861 [02:52<25:26,  1.94s/it]

  9%|▊         | 74/861 [02:55<31:10,  2.38s/it]

  9%|▊         | 75/861 [02:58<32:10,  2.46s/it]

  9%|▉         | 76/861 [03:01<35:13,  2.69s/it]

  9%|▉         | 77/861 [03:04<36:11,  2.77s/it]

  9%|▉         | 78/861 [03:06<30:36,  2.35s/it]

  9%|▉         | 79/861 [03:08<32:56,  2.53s/it]

  9%|▉         | 80/861 [03:11<31:42,  2.44s/it]

  9%|▉         | 81/861 [03:15<39:39,  3.05s/it]

 10%|▉         | 82/861 [03:16<32:28,  2.50s/it]

 10%|▉         | 83/861 [03:18<30:39,  2.36s/it]

 10%|▉         | 84/861 [03:21<32:07,  2.48s/it]

 10%|▉         | 85/861 [03:23<29:33,  2.29s/it]

 10%|▉         | 86/861 [03:24<24:43,  1.91s/it]

 10%|█         | 87/861 [03:27<29:10,  2.26s/it]

 10%|█         | 88/861 [03:27<21:44,  1.69s/it]

 10%|█         | 89/861 [03:29<21:04,  1.64s/it]

 10%|█         | 90/861 [03:33<31:48,  2.48s/it]

 11%|█         | 91/861 [03:35<29:34,  2.30s/it]

 11%|█         | 92/861 [03:37<28:00,  2.18s/it]

 11%|█         | 93/861 [03:40<31:05,  2.43s/it]

 11%|█         | 94/861 [03:41<25:07,  1.97s/it]

 11%|█         | 95/861 [03:43<23:00,  1.80s/it]

 11%|█         | 96/861 [03:45<24:42,  1.94s/it]

 11%|█▏        | 97/861 [03:48<27:53,  2.19s/it]

 11%|█▏        | 98/861 [03:50<26:57,  2.12s/it]

 11%|█▏        | 99/861 [03:54<36:55,  2.91s/it]

 12%|█▏        | 100/861 [03:56<32:19,  2.55s/it]

 12%|█▏        | 101/861 [03:58<29:21,  2.32s/it]

 12%|█▏        | 102/861 [03:59<26:25,  2.09s/it]

 12%|█▏        | 103/861 [04:00<22:03,  1.75s/it]

 12%|█▏        | 104/861 [04:05<32:49,  2.60s/it]

 12%|█▏        | 105/861 [04:08<33:37,  2.67s/it]

 12%|█▏        | 106/861 [04:09<29:04,  2.31s/it]

 12%|█▏        | 107/861 [04:11<27:17,  2.17s/it]

 13%|█▎        | 108/861 [04:11<20:32,  1.64s/it]

 13%|█▎        | 109/861 [04:12<15:49,  1.26s/it]

 13%|█▎        | 110/861 [04:14<19:50,  1.59s/it]

 13%|█▎        | 111/861 [04:18<27:36,  2.21s/it]

 13%|█▎        | 112/861 [04:20<27:00,  2.16s/it]

 13%|█▎        | 113/861 [04:22<25:33,  2.05s/it]

 13%|█▎        | 114/861 [04:24<28:01,  2.25s/it]

 13%|█▎        | 115/861 [04:26<24:02,  1.93s/it]

 13%|█▎        | 116/861 [04:27<21:03,  1.70s/it]

 14%|█▎        | 117/861 [04:30<25:10,  2.03s/it]

 14%|█▎        | 118/861 [04:32<25:08,  2.03s/it]

 14%|█▍        | 119/861 [04:33<24:23,  1.97s/it]

 14%|█▍        | 120/861 [04:34<18:19,  1.48s/it]

 14%|█▍        | 121/861 [04:36<20:38,  1.67s/it]

 14%|█▍        | 122/861 [04:39<24:45,  2.01s/it]

 14%|█▍        | 123/861 [04:41<25:01,  2.03s/it]

 14%|█▍        | 124/861 [04:44<28:49,  2.35s/it]

 15%|█▍        | 125/861 [04:47<31:02,  2.53s/it]

 15%|█▍        | 126/861 [04:49<30:32,  2.49s/it]

 15%|█▍        | 127/861 [04:51<29:09,  2.38s/it]

 15%|█▍        | 128/861 [04:53<27:09,  2.22s/it]

 15%|█▍        | 129/861 [04:55<27:03,  2.22s/it]

 15%|█▌        | 130/861 [04:57<26:24,  2.17s/it]

 15%|█▌        | 131/861 [04:59<25:27,  2.09s/it]

 15%|█▌        | 132/861 [05:02<29:10,  2.40s/it]

 15%|█▌        | 133/861 [05:05<29:24,  2.42s/it]

 16%|█▌        | 134/861 [05:05<21:49,  1.80s/it]

 16%|█▌        | 135/861 [05:06<19:37,  1.62s/it]

 16%|█▌        | 136/861 [05:08<18:28,  1.53s/it]

 16%|█▌        | 137/861 [05:09<18:17,  1.52s/it]

 16%|█▌        | 138/861 [05:11<17:33,  1.46s/it]

 16%|█▌        | 139/861 [05:12<16:00,  1.33s/it]

 16%|█▋        | 140/861 [05:13<15:44,  1.31s/it]

 16%|█▋        | 141/861 [05:14<16:05,  1.34s/it]

 16%|█▋        | 142/861 [05:15<13:50,  1.16s/it]

 17%|█▋        | 143/861 [05:18<21:03,  1.76s/it]

 17%|█▋        | 144/861 [05:21<25:58,  2.17s/it]

 17%|█▋        | 145/861 [05:23<23:16,  1.95s/it]

 17%|█▋        | 146/861 [05:25<22:51,  1.92s/it]

 17%|█▋        | 147/861 [05:26<22:40,  1.91s/it]

 17%|█▋        | 148/861 [05:27<18:15,  1.54s/it]

 17%|█▋        | 149/861 [05:28<14:28,  1.22s/it]

 17%|█▋        | 150/861 [05:32<26:35,  2.24s/it]

 18%|█▊        | 151/861 [05:35<29:41,  2.51s/it]

 18%|█▊        | 152/861 [05:38<30:07,  2.55s/it]

 18%|█▊        | 153/861 [05:41<32:50,  2.78s/it]

 18%|█▊        | 154/861 [05:44<33:21,  2.83s/it]

 18%|█▊        | 155/861 [05:48<34:48,  2.96s/it]

 18%|█▊        | 156/861 [05:51<35:39,  3.04s/it]

 18%|█▊        | 157/861 [05:52<30:01,  2.56s/it]

 18%|█▊        | 158/861 [05:56<32:40,  2.79s/it]

 18%|█▊        | 159/861 [05:57<29:06,  2.49s/it]

 19%|█▊        | 160/861 [05:59<26:23,  2.26s/it]

 19%|█▊        | 161/861 [06:03<32:04,  2.75s/it]

 19%|█▉        | 162/861 [06:04<25:20,  2.18s/it]

 19%|█▉        | 163/861 [06:04<19:03,  1.64s/it]

 19%|█▉        | 164/861 [06:08<25:04,  2.16s/it]

 19%|█▉        | 165/861 [06:10<26:26,  2.28s/it]

 19%|█▉        | 166/861 [06:13<27:35,  2.38s/it]

 19%|█▉        | 167/861 [06:13<20:27,  1.77s/it]

 20%|█▉        | 168/861 [06:15<20:39,  1.79s/it]

 20%|█▉        | 169/861 [06:17<22:18,  1.93s/it]

 20%|█▉        | 170/861 [06:19<22:19,  1.94s/it]

 20%|█▉        | 171/861 [06:20<20:07,  1.75s/it]

 20%|█▉        | 172/861 [06:22<21:07,  1.84s/it]

 20%|██        | 173/861 [06:25<23:20,  2.04s/it]

 20%|██        | 174/861 [06:28<25:46,  2.25s/it]

 20%|██        | 175/861 [06:30<24:59,  2.19s/it]

 20%|██        | 176/861 [06:30<18:57,  1.66s/it]

 21%|██        | 177/861 [06:32<19:32,  1.71s/it]

 21%|██        | 178/861 [06:34<20:28,  1.80s/it]

 21%|██        | 179/861 [06:36<21:54,  1.93s/it]

 21%|██        | 180/861 [06:38<22:01,  1.94s/it]

 21%|██        | 181/861 [06:40<21:22,  1.89s/it]

 21%|██        | 182/861 [06:41<17:08,  1.51s/it]

 21%|██▏       | 183/861 [06:43<19:24,  1.72s/it]

 21%|██▏       | 184/861 [06:46<23:51,  2.12s/it]

 21%|██▏       | 185/861 [06:48<22:15,  1.98s/it]

 22%|██▏       | 186/861 [06:49<19:08,  1.70s/it]

 22%|██▏       | 187/861 [06:51<22:09,  1.97s/it]

 22%|██▏       | 188/861 [06:54<23:36,  2.10s/it]

 22%|██▏       | 189/861 [06:56<24:31,  2.19s/it]

 22%|██▏       | 190/861 [06:59<26:06,  2.34s/it]

 22%|██▏       | 191/861 [07:00<21:39,  1.94s/it]

 22%|██▏       | 192/861 [07:02<22:08,  1.99s/it]

 22%|██▏       | 193/861 [07:05<25:11,  2.26s/it]

 23%|██▎       | 194/861 [07:06<22:30,  2.03s/it]

 23%|██▎       | 195/861 [07:07<19:24,  1.75s/it]

 23%|██▎       | 196/861 [07:11<27:10,  2.45s/it]

 23%|██▎       | 197/861 [07:13<23:50,  2.16s/it]

 23%|██▎       | 198/861 [07:14<22:08,  2.00s/it]

 23%|██▎       | 199/861 [07:17<24:22,  2.21s/it]

 23%|██▎       | 200/861 [07:20<24:50,  2.26s/it]

 23%|██▎       | 201/861 [07:22<26:06,  2.37s/it]

 23%|██▎       | 202/861 [07:24<24:00,  2.19s/it]

 24%|██▎       | 203/861 [07:26<22:49,  2.08s/it]

 24%|██▎       | 204/861 [07:26<17:06,  1.56s/it]

 24%|██▍       | 205/861 [07:27<14:55,  1.36s/it]

 24%|██▍       | 206/861 [07:29<16:42,  1.53s/it]

 24%|██▍       | 207/861 [07:31<17:56,  1.65s/it]

 24%|██▍       | 208/861 [07:32<17:53,  1.64s/it]

 24%|██▍       | 209/861 [07:34<16:34,  1.53s/it]

 24%|██▍       | 210/861 [07:36<18:23,  1.70s/it]

 25%|██▍       | 211/861 [07:39<23:51,  2.20s/it]

 25%|██▍       | 212/861 [07:41<23:26,  2.17s/it]

 25%|██▍       | 213/861 [07:43<20:45,  1.92s/it]

 25%|██▍       | 214/861 [07:44<19:06,  1.77s/it]

 25%|██▍       | 215/861 [07:46<18:20,  1.70s/it]

 25%|██▌       | 216/861 [07:47<16:45,  1.56s/it]

 25%|██▌       | 217/861 [07:48<14:33,  1.36s/it]

 25%|██▌       | 218/861 [07:49<14:06,  1.32s/it]

 25%|██▌       | 219/861 [07:52<20:05,  1.88s/it]

 26%|██▌       | 220/861 [07:54<20:25,  1.91s/it]

 26%|██▌       | 221/861 [07:56<19:14,  1.80s/it]

 26%|██▌       | 222/861 [07:59<24:57,  2.34s/it]

 26%|██▌       | 223/861 [08:02<26:25,  2.48s/it]

 26%|██▌       | 224/861 [08:04<23:04,  2.17s/it]

 26%|██▌       | 225/861 [08:06<23:51,  2.25s/it]

 26%|██▌       | 226/861 [08:08<24:37,  2.33s/it]

 26%|██▋       | 227/861 [08:11<24:36,  2.33s/it]

 26%|██▋       | 228/861 [08:13<23:00,  2.18s/it]

 27%|██▋       | 229/861 [08:14<21:32,  2.05s/it]

 27%|██▋       | 230/861 [08:17<22:37,  2.15s/it]

 27%|██▋       | 231/861 [08:20<27:26,  2.61s/it]

 27%|██▋       | 232/861 [08:21<20:16,  1.93s/it]

 27%|██▋       | 233/861 [08:23<20:28,  1.96s/it]

 27%|██▋       | 234/861 [08:24<18:59,  1.82s/it]

 27%|██▋       | 235/861 [08:27<20:41,  1.98s/it]

 27%|██▋       | 236/861 [08:28<19:00,  1.82s/it]

 28%|██▊       | 237/861 [08:30<18:55,  1.82s/it]

 28%|██▊       | 238/861 [08:31<16:07,  1.55s/it]

 28%|██▊       | 239/861 [08:34<20:27,  1.97s/it]

 28%|██▊       | 240/861 [08:36<22:03,  2.13s/it]

 28%|██▊       | 241/861 [08:40<26:00,  2.52s/it]

 28%|██▊       | 242/861 [08:42<23:44,  2.30s/it]

 28%|██▊       | 243/861 [08:45<27:53,  2.71s/it]

 28%|██▊       | 244/861 [08:48<27:33,  2.68s/it]

 28%|██▊       | 245/861 [08:50<26:32,  2.59s/it]

 29%|██▊       | 246/861 [08:53<26:27,  2.58s/it]

 29%|██▊       | 247/861 [08:54<22:43,  2.22s/it]

 29%|██▉       | 248/861 [08:54<16:54,  1.66s/it]

 29%|██▉       | 249/861 [08:57<18:14,  1.79s/it]

 29%|██▉       | 250/861 [09:00<22:06,  2.17s/it]

 29%|██▉       | 251/861 [09:02<21:37,  2.13s/it]

 29%|██▉       | 252/861 [09:03<20:32,  2.02s/it]

 29%|██▉       | 253/861 [09:05<18:41,  1.84s/it]

 30%|██▉       | 254/861 [09:05<14:39,  1.45s/it]

 30%|██▉       | 255/861 [09:07<15:56,  1.58s/it]

 30%|██▉       | 256/861 [09:10<18:31,  1.84s/it]

 30%|██▉       | 257/861 [09:12<20:16,  2.01s/it]

 30%|██▉       | 258/861 [09:14<20:07,  2.00s/it]

 30%|███       | 259/861 [09:17<23:37,  2.35s/it]

 30%|███       | 260/861 [09:20<24:21,  2.43s/it]

 30%|███       | 261/861 [09:24<29:12,  2.92s/it]

 30%|███       | 262/861 [09:25<24:39,  2.47s/it]

 31%|███       | 263/861 [09:26<18:13,  1.83s/it]

 31%|███       | 264/861 [09:28<18:16,  1.84s/it]

 31%|███       | 265/861 [09:29<15:58,  1.61s/it]

 31%|███       | 266/861 [09:30<15:12,  1.53s/it]

 31%|███       | 267/861 [09:31<14:42,  1.49s/it]

 31%|███       | 268/861 [09:33<15:49,  1.60s/it]

 31%|███       | 269/861 [09:35<16:50,  1.71s/it]

 31%|███▏      | 270/861 [09:38<18:45,  1.90s/it]

 31%|███▏      | 271/861 [09:40<19:26,  1.98s/it]

 32%|███▏      | 272/861 [09:42<21:33,  2.20s/it]

 32%|███▏      | 273/861 [09:45<21:25,  2.19s/it]

 32%|███▏      | 274/861 [09:48<25:10,  2.57s/it]

 32%|███▏      | 275/861 [09:48<18:33,  1.90s/it]

 32%|███▏      | 276/861 [09:51<20:37,  2.12s/it]

 32%|███▏      | 277/861 [09:57<30:30,  3.13s/it]

 32%|███▏      | 278/861 [10:00<30:11,  3.11s/it]

 32%|███▏      | 279/861 [10:02<27:42,  2.86s/it]

 33%|███▎      | 280/861 [10:04<27:01,  2.79s/it]

 33%|███▎      | 281/861 [10:07<27:08,  2.81s/it]

 33%|███▎      | 282/861 [10:10<25:58,  2.69s/it]

 33%|███▎      | 283/861 [10:12<23:52,  2.48s/it]

 33%|███▎      | 284/861 [10:12<18:43,  1.95s/it]

 33%|███▎      | 285/861 [10:14<18:08,  1.89s/it]

 33%|███▎      | 286/861 [10:18<22:54,  2.39s/it]

 33%|███▎      | 287/861 [10:22<28:45,  3.01s/it]

 33%|███▎      | 288/861 [10:25<28:42,  3.01s/it]

 34%|███▎      | 289/861 [10:26<23:05,  2.42s/it]

 34%|███▎      | 290/861 [10:28<22:06,  2.32s/it]

 34%|███▍      | 291/861 [10:31<22:53,  2.41s/it]

 34%|███▍      | 292/861 [10:34<24:57,  2.63s/it]

 34%|███▍      | 293/861 [10:36<22:34,  2.38s/it]

 34%|███▍      | 294/861 [10:39<24:07,  2.55s/it]

 34%|███▍      | 295/861 [10:40<18:46,  1.99s/it]

 34%|███▍      | 296/861 [10:41<17:31,  1.86s/it]

 34%|███▍      | 297/861 [10:45<21:53,  2.33s/it]

 35%|███▍      | 298/861 [10:49<27:04,  2.89s/it]

 35%|███▍      | 299/861 [10:51<25:49,  2.76s/it]

 35%|███▍      | 300/861 [10:54<24:45,  2.65s/it]

 35%|███▍      | 301/861 [10:58<28:23,  3.04s/it]

 35%|███▌      | 302/861 [10:58<21:22,  2.30s/it]

 35%|███▌      | 303/861 [11:02<25:09,  2.70s/it]

 35%|███▌      | 304/861 [11:05<27:05,  2.92s/it]

 35%|███▌      | 305/861 [11:08<27:20,  2.95s/it]

 36%|███▌      | 306/861 [11:12<28:58,  3.13s/it]

 36%|███▌      | 307/861 [11:15<29:43,  3.22s/it]

 36%|███▌      | 308/861 [11:15<21:41,  2.35s/it]

 36%|███▌      | 309/861 [11:17<20:11,  2.20s/it]

 36%|███▌      | 310/861 [11:19<19:13,  2.09s/it]

 36%|███▌      | 311/861 [11:23<24:30,  2.67s/it]

 36%|███▌      | 312/861 [11:26<24:25,  2.67s/it]

 36%|███▋      | 313/861 [11:30<28:30,  3.12s/it]

 36%|███▋      | 314/861 [11:33<27:38,  3.03s/it]

 37%|███▋      | 315/861 [11:35<25:07,  2.76s/it]

 37%|███▋      | 316/861 [11:37<24:08,  2.66s/it]

 37%|███▋      | 317/861 [11:38<17:46,  1.96s/it]

 37%|███▋      | 318/861 [11:41<20:07,  2.22s/it]

 37%|███▋      | 319/861 [11:43<21:42,  2.40s/it]

 37%|███▋      | 320/861 [11:46<21:10,  2.35s/it]

 37%|███▋      | 321/861 [11:49<23:13,  2.58s/it]

 37%|███▋      | 322/861 [11:53<26:59,  3.01s/it]

 38%|███▊      | 323/861 [11:56<26:54,  3.00s/it]

 38%|███▊      | 324/861 [12:01<34:13,  3.82s/it]

 38%|███▊      | 325/861 [12:04<31:36,  3.54s/it]

 38%|███▊      | 326/861 [12:05<23:02,  2.58s/it]

 38%|███▊      | 327/861 [12:08<25:50,  2.90s/it]

 38%|███▊      | 328/861 [12:11<24:01,  2.70s/it]

 38%|███▊      | 329/861 [12:15<27:24,  3.09s/it]

 38%|███▊      | 330/861 [12:17<25:13,  2.85s/it]

 38%|███▊      | 331/861 [12:22<30:03,  3.40s/it]

 39%|███▊      | 332/861 [12:24<26:31,  3.01s/it]

 39%|███▊      | 333/861 [12:27<27:52,  3.17s/it]

 39%|███▉      | 334/861 [12:31<30:00,  3.42s/it]

 39%|███▉      | 335/861 [12:34<28:57,  3.30s/it]

 39%|███▉      | 336/861 [12:38<29:56,  3.42s/it]

 39%|███▉      | 337/861 [12:40<25:11,  2.88s/it]

 39%|███▉      | 338/861 [12:43<26:31,  3.04s/it]

 39%|███▉      | 339/861 [12:45<25:02,  2.88s/it]

 39%|███▉      | 340/861 [12:47<22:00,  2.53s/it]

 40%|███▉      | 341/861 [12:48<17:51,  2.06s/it]

 40%|███▉      | 342/861 [12:50<17:10,  1.99s/it]

 40%|███▉      | 343/861 [12:52<17:35,  2.04s/it]

 40%|███▉      | 344/861 [12:54<16:24,  1.90s/it]

 40%|████      | 345/861 [12:56<16:53,  1.96s/it]

 40%|████      | 346/861 [12:58<17:56,  2.09s/it]

 40%|████      | 347/861 [13:00<16:45,  1.96s/it]

 40%|████      | 348/861 [13:01<15:47,  1.85s/it]

 41%|████      | 349/861 [13:04<18:23,  2.16s/it]

 41%|████      | 350/861 [13:07<19:44,  2.32s/it]

 41%|████      | 351/861 [13:09<18:38,  2.19s/it]

 41%|████      | 352/861 [13:11<17:34,  2.07s/it]

 41%|████      | 353/861 [13:13<16:50,  1.99s/it]

 41%|████      | 354/861 [13:15<17:36,  2.08s/it]

 41%|████      | 355/861 [13:16<14:07,  1.68s/it]

 41%|████▏     | 356/861 [13:17<12:54,  1.53s/it]

 41%|████▏     | 357/861 [13:17<10:30,  1.25s/it]

 42%|████▏     | 358/861 [13:19<10:28,  1.25s/it]

 42%|████▏     | 359/861 [13:21<12:42,  1.52s/it]

 42%|████▏     | 360/861 [13:24<16:31,  1.98s/it]

 42%|████▏     | 361/861 [13:26<17:23,  2.09s/it]

 42%|████▏     | 362/861 [13:28<16:37,  2.00s/it]

 42%|████▏     | 363/861 [13:31<19:47,  2.39s/it]

 42%|████▏     | 364/861 [13:34<20:32,  2.48s/it]

 42%|████▏     | 365/861 [13:38<24:14,  2.93s/it]

 43%|████▎     | 366/861 [13:40<21:48,  2.64s/it]

 43%|████▎     | 367/861 [13:44<24:28,  2.97s/it]

 43%|████▎     | 368/861 [13:48<28:58,  3.53s/it]

 43%|████▎     | 369/861 [13:51<26:02,  3.18s/it]

 43%|████▎     | 370/861 [13:53<23:25,  2.86s/it]

 43%|████▎     | 371/861 [13:56<24:30,  3.00s/it]

 43%|████▎     | 372/861 [14:00<25:13,  3.09s/it]

 43%|████▎     | 373/861 [14:02<23:37,  2.90s/it]

 43%|████▎     | 374/861 [14:05<24:18,  3.00s/it]

 44%|████▎     | 375/861 [14:09<26:58,  3.33s/it]

 44%|████▎     | 376/861 [14:11<22:57,  2.84s/it]

 44%|████▍     | 377/861 [14:14<22:30,  2.79s/it]

 44%|████▍     | 378/861 [14:18<26:01,  3.23s/it]

 44%|████▍     | 379/861 [14:18<18:59,  2.36s/it]

 44%|████▍     | 380/861 [14:20<17:43,  2.21s/it]

 44%|████▍     | 381/861 [14:22<16:54,  2.11s/it]

 44%|████▍     | 382/861 [14:25<17:53,  2.24s/it]

 44%|████▍     | 383/861 [14:27<17:13,  2.16s/it]

 45%|████▍     | 384/861 [14:29<17:34,  2.21s/it]

 45%|████▍     | 385/861 [14:30<14:11,  1.79s/it]

 45%|████▍     | 386/861 [14:32<16:28,  2.08s/it]

 45%|████▍     | 387/861 [14:35<17:51,  2.26s/it]

 45%|████▌     | 388/861 [14:36<15:29,  1.97s/it]

 45%|████▌     | 389/861 [14:37<13:12,  1.68s/it]

 45%|████▌     | 390/861 [14:39<13:00,  1.66s/it]

 45%|████▌     | 391/861 [14:41<12:39,  1.62s/it]

 46%|████▌     | 392/861 [14:42<13:14,  1.69s/it]

 46%|████▌     | 393/861 [14:45<14:51,  1.91s/it]

 46%|████▌     | 394/861 [14:49<19:03,  2.45s/it]

 46%|████▌     | 395/861 [14:50<15:57,  2.06s/it]

 46%|████▌     | 396/861 [14:51<13:40,  1.76s/it]

 46%|████▌     | 397/861 [14:51<10:31,  1.36s/it]

 46%|████▌     | 398/861 [14:53<12:19,  1.60s/it]

 46%|████▋     | 399/861 [14:56<14:22,  1.87s/it]

 46%|████▋     | 400/861 [14:58<15:46,  2.05s/it]

 47%|████▋     | 401/861 [14:59<13:09,  1.72s/it]

 47%|████▋     | 402/861 [15:01<12:14,  1.60s/it]

 47%|████▋     | 403/861 [15:03<13:15,  1.74s/it]

 47%|████▋     | 404/861 [15:05<14:14,  1.87s/it]

 47%|████▋     | 405/861 [15:06<12:34,  1.65s/it]

 47%|████▋     | 406/861 [15:09<14:52,  1.96s/it]

 47%|████▋     | 407/861 [15:11<15:32,  2.05s/it]

 47%|████▋     | 408/861 [15:13<15:11,  2.01s/it]

 48%|████▊     | 409/861 [15:15<14:52,  1.97s/it]

 48%|████▊     | 410/861 [15:16<13:31,  1.80s/it]

 48%|████▊     | 411/861 [15:17<12:09,  1.62s/it]

 48%|████▊     | 412/861 [15:20<15:15,  2.04s/it]

 48%|████▊     | 413/861 [15:22<13:57,  1.87s/it]

 48%|████▊     | 414/861 [15:23<12:35,  1.69s/it]

 48%|████▊     | 415/861 [15:24<11:45,  1.58s/it]

 48%|████▊     | 416/861 [15:26<10:59,  1.48s/it]

 48%|████▊     | 417/861 [15:27<11:16,  1.52s/it]

 49%|████▊     | 418/861 [15:29<11:45,  1.59s/it]

 49%|████▊     | 419/861 [15:31<12:21,  1.68s/it]

 49%|████▉     | 420/861 [15:33<12:46,  1.74s/it]

 49%|████▉     | 421/861 [15:34<10:38,  1.45s/it]

 49%|████▉     | 422/861 [15:35<09:46,  1.34s/it]

 49%|████▉     | 423/861 [15:37<12:11,  1.67s/it]

 49%|████▉     | 424/861 [15:39<12:25,  1.71s/it]

 49%|████▉     | 425/861 [15:40<12:16,  1.69s/it]

 49%|████▉     | 426/861 [15:43<13:57,  1.92s/it]

 50%|████▉     | 427/861 [15:45<13:55,  1.92s/it]

 50%|████▉     | 428/861 [15:47<13:13,  1.83s/it]

 50%|████▉     | 429/861 [15:49<13:48,  1.92s/it]

 50%|████▉     | 430/861 [15:52<16:05,  2.24s/it]

 50%|█████     | 431/861 [15:55<17:31,  2.44s/it]

 50%|█████     | 432/861 [15:58<18:38,  2.61s/it]

 50%|█████     | 433/861 [16:00<19:01,  2.67s/it]

 50%|█████     | 434/861 [16:02<16:45,  2.36s/it]

 51%|█████     | 435/861 [16:02<12:24,  1.75s/it]

 51%|█████     | 436/861 [16:03<09:55,  1.40s/it]

 51%|█████     | 437/861 [16:05<11:09,  1.58s/it]

 51%|█████     | 438/861 [16:06<09:49,  1.39s/it]

 51%|█████     | 439/861 [16:07<10:00,  1.42s/it]

 51%|█████     | 440/861 [16:08<08:33,  1.22s/it]

 51%|█████     | 441/861 [16:09<07:36,  1.09s/it]

 51%|█████▏    | 442/861 [16:11<09:28,  1.36s/it]

 51%|█████▏    | 443/861 [16:12<08:33,  1.23s/it]

 52%|█████▏    | 444/861 [16:13<08:25,  1.21s/it]

 52%|█████▏    | 445/861 [16:14<07:47,  1.12s/it]

 52%|█████▏    | 446/861 [16:15<07:38,  1.11s/it]

 52%|█████▏    | 447/861 [16:18<11:40,  1.69s/it]

 52%|█████▏    | 448/861 [16:20<12:55,  1.88s/it]

 52%|█████▏    | 449/861 [16:23<14:15,  2.08s/it]

 52%|█████▏    | 450/861 [16:25<14:18,  2.09s/it]

 52%|█████▏    | 451/861 [16:27<13:26,  1.97s/it]

 52%|█████▏    | 452/861 [16:28<13:10,  1.93s/it]

 53%|█████▎    | 453/861 [16:30<11:43,  1.73s/it]

 53%|█████▎    | 454/861 [16:31<11:09,  1.64s/it]

 53%|█████▎    | 455/861 [16:33<11:50,  1.75s/it]

 53%|█████▎    | 456/861 [16:34<10:43,  1.59s/it]

 53%|█████▎    | 457/861 [16:36<11:28,  1.70s/it]

 53%|█████▎    | 458/861 [16:39<13:08,  1.96s/it]

 53%|█████▎    | 459/861 [16:40<11:53,  1.77s/it]

 53%|█████▎    | 460/861 [16:42<11:24,  1.71s/it]

 54%|█████▎    | 461/861 [16:44<12:12,  1.83s/it]

 54%|█████▎    | 462/861 [16:45<10:48,  1.63s/it]

 54%|█████▍    | 463/861 [16:46<10:04,  1.52s/it]

 54%|█████▍    | 464/861 [16:48<09:30,  1.44s/it]

 54%|█████▍    | 465/861 [16:48<07:27,  1.13s/it]

 54%|█████▍    | 466/861 [16:49<07:52,  1.20s/it]

 54%|█████▍    | 467/861 [16:53<12:33,  1.91s/it]

 54%|█████▍    | 468/861 [16:54<10:07,  1.54s/it]

 54%|█████▍    | 469/861 [16:55<09:58,  1.53s/it]

 55%|█████▍    | 470/861 [16:56<08:29,  1.30s/it]

 55%|█████▍    | 471/861 [16:57<09:02,  1.39s/it]

 55%|█████▍    | 472/861 [16:58<07:42,  1.19s/it]

 55%|█████▍    | 473/861 [16:59<07:44,  1.20s/it]

 55%|█████▌    | 474/861 [17:00<06:15,  1.03it/s]

 55%|█████▌    | 475/861 [17:01<07:07,  1.11s/it]

 55%|█████▌    | 476/861 [17:02<06:12,  1.03it/s]

 55%|█████▌    | 477/861 [17:04<08:18,  1.30s/it]

 56%|█████▌    | 478/861 [17:05<08:27,  1.32s/it]

 56%|█████▌    | 479/861 [17:06<06:47,  1.07s/it]

 56%|█████▌    | 480/861 [17:07<07:17,  1.15s/it]

 56%|█████▌    | 481/861 [17:08<06:35,  1.04s/it]

 56%|█████▌    | 482/861 [17:09<06:16,  1.01it/s]

 56%|█████▌    | 483/861 [17:10<05:44,  1.10it/s]

 56%|█████▌    | 484/861 [17:11<05:54,  1.06it/s]

 56%|█████▋    | 485/861 [17:11<05:35,  1.12it/s]

 56%|█████▋    | 486/861 [17:12<04:46,  1.31it/s]

 57%|█████▋    | 487/861 [17:13<06:02,  1.03it/s]

 57%|█████▋    | 488/861 [17:14<04:56,  1.26it/s]

 57%|█████▋    | 489/861 [17:15<05:46,  1.07it/s]

 57%|█████▋    | 490/861 [17:16<05:24,  1.14it/s]

 57%|█████▋    | 491/861 [17:17<05:33,  1.11it/s]

 57%|█████▋    | 492/861 [17:17<05:06,  1.20it/s]

 57%|█████▋    | 493/861 [17:19<06:02,  1.01it/s]

 57%|█████▋    | 494/861 [17:19<05:12,  1.18it/s]

 57%|█████▋    | 495/861 [17:21<06:56,  1.14s/it]

 58%|█████▊    | 496/861 [17:23<08:09,  1.34s/it]

 58%|█████▊    | 497/861 [17:23<06:18,  1.04s/it]

 58%|█████▊    | 498/861 [17:25<06:57,  1.15s/it]

 58%|█████▊    | 499/861 [17:25<05:29,  1.10it/s]

 58%|█████▊    | 500/861 [17:26<05:51,  1.03it/s]

 58%|█████▊    | 501/861 [17:26<04:50,  1.24it/s]

 58%|█████▊    | 502/861 [17:28<06:20,  1.06s/it]

 58%|█████▊    | 503/861 [17:29<06:30,  1.09s/it]

 59%|█████▊    | 504/861 [17:31<06:54,  1.16s/it]

 59%|█████▊    | 505/861 [17:31<05:55,  1.00it/s]

 59%|█████▉    | 506/861 [17:32<05:18,  1.11it/s]

 59%|█████▉    | 507/861 [17:32<04:24,  1.34it/s]

 59%|█████▉    | 508/861 [17:34<06:32,  1.11s/it]

 59%|█████▉    | 509/861 [17:37<08:59,  1.53s/it]

 59%|█████▉    | 510/861 [17:39<09:40,  1.65s/it]

 59%|█████▉    | 511/861 [17:41<10:41,  1.83s/it]

 59%|█████▉    | 512/861 [17:42<09:40,  1.66s/it]

 60%|█████▉    | 513/861 [17:44<09:28,  1.63s/it]

 60%|█████▉    | 514/861 [17:45<09:09,  1.58s/it]

 60%|█████▉    | 515/861 [17:46<07:14,  1.26s/it]

 60%|█████▉    | 516/861 [17:46<05:55,  1.03s/it]

 60%|██████    | 517/861 [17:47<04:56,  1.16it/s]

 60%|██████    | 518/861 [17:48<06:23,  1.12s/it]

 60%|██████    | 519/861 [17:50<07:16,  1.28s/it]

 60%|██████    | 520/861 [17:52<08:19,  1.46s/it]

 61%|██████    | 521/861 [17:53<08:02,  1.42s/it]

 61%|██████    | 522/861 [17:55<08:47,  1.56s/it]

 61%|██████    | 523/861 [17:57<09:36,  1.71s/it]

 61%|██████    | 524/861 [18:00<11:41,  2.08s/it]

 61%|██████    | 525/861 [18:02<10:52,  1.94s/it]

 61%|██████    | 526/861 [18:03<10:01,  1.80s/it]

 61%|██████    | 527/861 [18:05<09:32,  1.71s/it]

 61%|██████▏   | 528/861 [18:07<10:33,  1.90s/it]

 61%|██████▏   | 529/861 [18:08<08:36,  1.55s/it]

 62%|██████▏   | 530/861 [18:09<07:49,  1.42s/it]

 62%|██████▏   | 531/861 [18:10<06:47,  1.23s/it]

 62%|██████▏   | 532/861 [18:11<07:37,  1.39s/it]

 62%|██████▏   | 533/861 [18:12<06:52,  1.26s/it]

 62%|██████▏   | 534/861 [18:14<06:59,  1.28s/it]

 62%|██████▏   | 535/861 [18:15<06:59,  1.29s/it]

 62%|██████▏   | 536/861 [18:17<07:15,  1.34s/it]

 62%|██████▏   | 537/861 [18:19<08:37,  1.60s/it]

 62%|██████▏   | 538/861 [18:20<07:25,  1.38s/it]

 63%|██████▎   | 539/861 [18:23<10:31,  1.96s/it]

 63%|██████▎   | 540/861 [18:25<10:06,  1.89s/it]

 63%|██████▎   | 541/861 [18:26<09:01,  1.69s/it]

 63%|██████▎   | 542/861 [18:27<08:11,  1.54s/it]

 63%|██████▎   | 543/861 [18:29<09:22,  1.77s/it]

 63%|██████▎   | 544/861 [18:30<08:16,  1.57s/it]

 63%|██████▎   | 545/861 [18:33<10:22,  1.97s/it]

 63%|██████▎   | 546/861 [18:35<10:31,  2.00s/it]

 64%|██████▎   | 547/861 [18:37<10:14,  1.96s/it]

 64%|██████▎   | 548/861 [18:40<11:57,  2.29s/it]

 64%|██████▍   | 549/861 [18:43<12:17,  2.36s/it]

 64%|██████▍   | 550/861 [18:45<12:14,  2.36s/it]

 64%|██████▍   | 551/861 [18:47<11:32,  2.23s/it]

 64%|██████▍   | 552/861 [18:50<13:01,  2.53s/it]

 64%|██████▍   | 553/861 [18:54<14:04,  2.74s/it]

 64%|██████▍   | 554/861 [18:57<14:48,  2.90s/it]

 64%|██████▍   | 555/861 [19:00<14:59,  2.94s/it]

 65%|██████▍   | 556/861 [19:03<14:34,  2.87s/it]

 65%|██████▍   | 557/861 [19:06<15:07,  2.98s/it]

 65%|██████▍   | 558/861 [19:09<15:26,  3.06s/it]

 65%|██████▍   | 559/861 [19:13<16:00,  3.18s/it]

 65%|██████▌   | 560/861 [19:16<15:47,  3.15s/it]

 65%|██████▌   | 561/861 [19:18<14:45,  2.95s/it]

 65%|██████▌   | 562/861 [19:22<16:21,  3.28s/it]

 65%|██████▌   | 563/861 [19:25<15:18,  3.08s/it]

 66%|██████▌   | 564/861 [19:29<16:18,  3.29s/it]

 66%|██████▌   | 565/861 [19:32<16:35,  3.36s/it]

 66%|██████▌   | 566/861 [19:37<17:59,  3.66s/it]

 66%|██████▌   | 567/861 [19:39<16:17,  3.33s/it]

 66%|██████▌   | 568/861 [19:42<16:01,  3.28s/it]

 66%|██████▌   | 569/861 [19:45<15:30,  3.19s/it]

 66%|██████▌   | 570/861 [19:48<14:12,  2.93s/it]

 66%|██████▋   | 571/861 [19:51<14:40,  3.04s/it]

 66%|██████▋   | 572/861 [19:55<15:41,  3.26s/it]

 67%|██████▋   | 573/861 [19:56<13:41,  2.85s/it]

 67%|██████▋   | 574/861 [19:59<13:25,  2.81s/it]

 67%|██████▋   | 575/861 [20:02<13:32,  2.84s/it]

 67%|██████▋   | 576/861 [20:07<16:16,  3.42s/it]

 67%|██████▋   | 577/861 [20:11<17:24,  3.68s/it]

 67%|██████▋   | 578/861 [20:17<19:47,  4.20s/it]

 67%|██████▋   | 579/861 [20:22<21:34,  4.59s/it]

 67%|██████▋   | 580/861 [20:25<19:17,  4.12s/it]

 67%|██████▋   | 581/861 [20:28<17:18,  3.71s/it]

 68%|██████▊   | 582/861 [20:33<18:58,  4.08s/it]

 68%|██████▊   | 583/861 [20:36<17:42,  3.82s/it]

 68%|██████▊   | 584/861 [20:38<15:41,  3.40s/it]

 68%|██████▊   | 585/861 [20:43<17:51,  3.88s/it]

 68%|██████▊   | 586/861 [20:45<14:50,  3.24s/it]

 68%|██████▊   | 587/861 [20:49<15:08,  3.32s/it]

 68%|██████▊   | 588/861 [20:51<14:11,  3.12s/it]

 68%|██████▊   | 589/861 [20:53<12:02,  2.65s/it]

 69%|██████▊   | 590/861 [20:57<14:35,  3.23s/it]

 69%|██████▊   | 591/861 [21:00<13:25,  2.98s/it]

 69%|██████▉   | 592/861 [21:03<13:34,  3.03s/it]

 69%|██████▉   | 593/861 [21:06<14:01,  3.14s/it]

 69%|██████▉   | 594/861 [21:10<14:10,  3.19s/it]

 69%|██████▉   | 595/861 [21:12<12:19,  2.78s/it]

 69%|██████▉   | 596/861 [21:13<10:09,  2.30s/it]

 69%|██████▉   | 597/861 [21:17<12:42,  2.89s/it]

 69%|██████▉   | 598/861 [21:20<12:42,  2.90s/it]

 70%|██████▉   | 599/861 [21:23<12:31,  2.87s/it]

 70%|██████▉   | 600/861 [21:25<11:47,  2.71s/it]

 70%|██████▉   | 601/861 [21:27<10:56,  2.52s/it]

 70%|██████▉   | 602/861 [21:30<11:50,  2.74s/it]

 70%|███████   | 603/861 [21:34<12:53,  3.00s/it]

 70%|███████   | 604/861 [21:37<12:59,  3.03s/it]

 70%|███████   | 605/861 [21:39<11:23,  2.67s/it]

 70%|███████   | 606/861 [21:41<10:23,  2.44s/it]

 70%|███████   | 607/861 [21:43<09:31,  2.25s/it]

 71%|███████   | 608/861 [21:45<08:59,  2.13s/it]

 71%|███████   | 609/861 [21:48<10:48,  2.57s/it]

 71%|███████   | 610/861 [21:52<12:18,  2.94s/it]

 71%|███████   | 611/861 [21:54<11:47,  2.83s/it]

 71%|███████   | 612/861 [21:57<11:15,  2.71s/it]

 71%|███████   | 613/861 [21:58<09:20,  2.26s/it]

 71%|███████▏  | 614/861 [22:01<09:47,  2.38s/it]

 71%|███████▏  | 615/861 [22:04<10:37,  2.59s/it]

 72%|███████▏  | 616/861 [22:08<12:56,  3.17s/it]

 72%|███████▏  | 617/861 [22:12<13:19,  3.28s/it]

 72%|███████▏  | 618/861 [22:15<13:11,  3.26s/it]

 72%|███████▏  | 619/861 [22:17<11:59,  2.98s/it]

 72%|███████▏  | 620/861 [22:21<13:06,  3.26s/it]

 72%|███████▏  | 621/861 [22:24<12:30,  3.13s/it]

 72%|███████▏  | 622/861 [22:26<11:01,  2.77s/it]

 72%|███████▏  | 623/861 [22:31<13:38,  3.44s/it]

 72%|███████▏  | 624/861 [22:34<13:04,  3.31s/it]

 73%|███████▎  | 625/861 [22:35<10:27,  2.66s/it]

 73%|███████▎  | 626/861 [22:37<09:29,  2.42s/it]

 73%|███████▎  | 627/861 [22:41<10:32,  2.70s/it]

 73%|███████▎  | 628/861 [22:44<11:19,  2.91s/it]

 73%|███████▎  | 629/861 [22:48<12:40,  3.28s/it]

 73%|███████▎  | 630/861 [22:51<12:43,  3.31s/it]

 73%|███████▎  | 631/861 [22:52<10:00,  2.61s/it]

 73%|███████▎  | 632/861 [22:56<10:36,  2.78s/it]

 74%|███████▎  | 633/861 [22:58<10:19,  2.72s/it]

 74%|███████▎  | 634/861 [23:02<11:13,  2.97s/it]

 74%|███████▍  | 635/861 [23:04<10:30,  2.79s/it]

 74%|███████▍  | 636/861 [23:06<09:37,  2.57s/it]

 74%|███████▍  | 637/861 [23:08<08:37,  2.31s/it]

 74%|███████▍  | 638/861 [23:10<08:02,  2.16s/it]

 74%|███████▍  | 639/861 [23:13<09:04,  2.45s/it]

 74%|███████▍  | 640/861 [23:15<08:35,  2.33s/it]

 74%|███████▍  | 641/861 [23:17<08:25,  2.30s/it]

 75%|███████▍  | 642/861 [23:19<07:44,  2.12s/it]

 75%|███████▍  | 643/861 [23:21<07:20,  2.02s/it]

 75%|███████▍  | 644/861 [23:23<07:20,  2.03s/it]

 75%|███████▍  | 645/861 [23:23<06:00,  1.67s/it]

 75%|███████▌  | 646/861 [23:25<05:45,  1.61s/it]

 75%|███████▌  | 647/861 [23:26<05:01,  1.41s/it]

 75%|███████▌  | 648/861 [23:28<05:33,  1.57s/it]

 75%|███████▌  | 649/861 [23:29<05:39,  1.60s/it]

 75%|███████▌  | 650/861 [23:31<05:23,  1.53s/it]

 76%|███████▌  | 651/861 [23:32<04:40,  1.34s/it]

 76%|███████▌  | 652/861 [23:33<04:51,  1.39s/it]

 76%|███████▌  | 653/861 [23:34<04:32,  1.31s/it]

 76%|███████▌  | 654/861 [23:36<04:27,  1.29s/it]

 76%|███████▌  | 655/861 [23:36<03:56,  1.15s/it]

 76%|███████▌  | 656/861 [23:37<03:20,  1.02it/s]

 76%|███████▋  | 657/861 [23:38<03:27,  1.02s/it]

 76%|███████▋  | 658/861 [23:40<04:10,  1.24s/it]

 77%|███████▋  | 659/861 [23:41<04:06,  1.22s/it]

 77%|███████▋  | 660/861 [23:43<04:43,  1.41s/it]

 77%|███████▋  | 661/861 [23:44<04:51,  1.46s/it]

 77%|███████▋  | 662/861 [23:47<05:48,  1.75s/it]

 77%|███████▋  | 663/861 [23:50<06:46,  2.05s/it]

 77%|███████▋  | 664/861 [23:51<05:46,  1.76s/it]

 77%|███████▋  | 665/861 [23:52<05:01,  1.54s/it]

 77%|███████▋  | 666/861 [23:53<04:20,  1.34s/it]

 77%|███████▋  | 667/861 [23:54<04:24,  1.36s/it]

 78%|███████▊  | 668/861 [23:55<04:13,  1.31s/it]

 78%|███████▊  | 669/861 [23:56<03:37,  1.13s/it]

 78%|███████▊  | 670/861 [23:57<03:43,  1.17s/it]

 78%|███████▊  | 671/861 [23:58<02:58,  1.06it/s]

 78%|███████▊  | 672/861 [24:00<04:23,  1.39s/it]

 78%|███████▊  | 673/861 [24:02<05:12,  1.66s/it]

 78%|███████▊  | 674/861 [24:04<04:52,  1.56s/it]

 78%|███████▊  | 675/861 [24:08<07:14,  2.34s/it]

 79%|███████▊  | 676/861 [24:09<06:24,  2.08s/it]

 79%|███████▊  | 677/861 [24:11<06:18,  2.06s/it]

 79%|███████▊  | 678/861 [24:12<05:17,  1.73s/it]

 79%|███████▉  | 679/861 [24:13<04:38,  1.53s/it]

 79%|███████▉  | 680/861 [24:14<03:56,  1.31s/it]

 79%|███████▉  | 681/861 [24:16<04:51,  1.62s/it]

 79%|███████▉  | 682/861 [24:18<04:57,  1.66s/it]

 79%|███████▉  | 683/861 [24:20<04:39,  1.57s/it]

 79%|███████▉  | 684/861 [24:22<05:36,  1.90s/it]

 80%|███████▉  | 685/861 [24:23<04:58,  1.69s/it]

 80%|███████▉  | 686/861 [24:25<04:31,  1.55s/it]

 80%|███████▉  | 687/861 [24:29<06:40,  2.30s/it]

 80%|███████▉  | 688/861 [24:30<05:31,  1.92s/it]

 80%|████████  | 689/861 [24:31<05:13,  1.82s/it]

 80%|████████  | 690/861 [24:33<04:53,  1.71s/it]

 80%|████████  | 691/861 [24:35<05:09,  1.82s/it]

 80%|████████  | 692/861 [24:37<05:02,  1.79s/it]

 80%|████████  | 693/861 [24:38<04:37,  1.65s/it]

 81%|████████  | 694/861 [24:39<04:05,  1.47s/it]

 81%|████████  | 695/861 [24:41<04:44,  1.72s/it]

 81%|████████  | 696/861 [24:42<04:00,  1.46s/it]

 81%|████████  | 697/861 [24:43<03:51,  1.41s/it]

 81%|████████  | 698/861 [24:45<03:53,  1.43s/it]

 81%|████████  | 699/861 [24:49<06:12,  2.30s/it]

 81%|████████▏ | 700/861 [24:52<06:52,  2.56s/it]

 81%|████████▏ | 701/861 [24:54<06:05,  2.28s/it]

 82%|████████▏ | 702/861 [24:56<05:27,  2.06s/it]

 82%|████████▏ | 703/861 [24:57<04:53,  1.86s/it]

 82%|████████▏ | 704/861 [24:58<04:35,  1.76s/it]

 82%|████████▏ | 705/861 [25:00<04:35,  1.76s/it]

 82%|████████▏ | 706/861 [25:01<03:55,  1.52s/it]

 82%|████████▏ | 707/861 [25:02<03:22,  1.32s/it]

 82%|████████▏ | 708/861 [25:03<03:12,  1.26s/it]

 82%|████████▏ | 709/861 [25:04<03:13,  1.27s/it]

 82%|████████▏ | 710/861 [25:07<04:03,  1.62s/it]

 83%|████████▎ | 711/861 [25:09<04:13,  1.69s/it]

 83%|████████▎ | 712/861 [25:10<03:51,  1.55s/it]

 83%|████████▎ | 713/861 [25:11<03:04,  1.25s/it]

 83%|████████▎ | 714/861 [25:12<03:12,  1.31s/it]

 83%|████████▎ | 715/861 [25:15<04:04,  1.68s/it]

 83%|████████▎ | 716/861 [25:17<04:22,  1.81s/it]

 83%|████████▎ | 717/861 [25:18<03:54,  1.63s/it]

 83%|████████▎ | 718/861 [25:20<04:14,  1.78s/it]

 84%|████████▎ | 719/861 [25:21<03:42,  1.57s/it]

 84%|████████▎ | 720/861 [25:22<03:17,  1.40s/it]

 84%|████████▎ | 721/861 [25:23<02:59,  1.28s/it]

 84%|████████▍ | 722/861 [25:25<03:16,  1.41s/it]

 84%|████████▍ | 723/861 [25:26<03:03,  1.33s/it]

 84%|████████▍ | 724/861 [25:27<03:00,  1.32s/it]

 84%|████████▍ | 725/861 [25:28<02:31,  1.11s/it]

 84%|████████▍ | 726/861 [25:30<02:53,  1.28s/it]

 84%|████████▍ | 727/861 [25:32<03:43,  1.67s/it]

 85%|████████▍ | 728/861 [25:34<03:50,  1.73s/it]

 85%|████████▍ | 729/861 [25:35<03:25,  1.56s/it]

 85%|████████▍ | 730/861 [25:36<02:46,  1.27s/it]

 85%|████████▍ | 731/861 [25:38<03:30,  1.62s/it]

 85%|████████▌ | 732/861 [25:39<03:06,  1.45s/it]

 85%|████████▌ | 733/861 [25:41<03:02,  1.43s/it]

 85%|████████▌ | 734/861 [25:41<02:27,  1.17s/it]

 85%|████████▌ | 735/861 [25:42<02:15,  1.08s/it]

 85%|████████▌ | 736/861 [25:43<02:27,  1.18s/it]

 86%|████████▌ | 737/861 [25:45<02:52,  1.39s/it]

 86%|████████▌ | 738/861 [25:47<02:59,  1.46s/it]

 86%|████████▌ | 739/861 [25:48<02:44,  1.35s/it]

 86%|████████▌ | 740/861 [25:49<02:29,  1.24s/it]

 86%|████████▌ | 741/861 [25:51<02:45,  1.38s/it]

 86%|████████▌ | 742/861 [25:52<02:52,  1.45s/it]

 86%|████████▋ | 743/861 [25:53<02:32,  1.29s/it]

 86%|████████▋ | 744/861 [25:54<02:20,  1.20s/it]

 87%|████████▋ | 745/861 [25:56<02:47,  1.44s/it]

 87%|████████▋ | 746/861 [25:57<02:31,  1.32s/it]

 87%|████████▋ | 747/861 [26:00<03:10,  1.67s/it]

 87%|████████▋ | 748/861 [26:02<03:24,  1.81s/it]

 87%|████████▋ | 749/861 [26:04<03:17,  1.77s/it]

 87%|████████▋ | 750/861 [26:04<02:46,  1.50s/it]

 87%|████████▋ | 751/861 [26:05<02:09,  1.18s/it]

 87%|████████▋ | 752/861 [26:08<03:22,  1.85s/it]

 87%|████████▋ | 753/861 [26:11<03:38,  2.03s/it]

 88%|████████▊ | 754/861 [26:12<03:01,  1.70s/it]

 88%|████████▊ | 755/861 [26:13<02:42,  1.53s/it]

 88%|████████▊ | 756/861 [26:14<02:31,  1.44s/it]

 88%|████████▊ | 757/861 [26:17<03:04,  1.77s/it]

 88%|████████▊ | 758/861 [26:18<02:49,  1.64s/it]

 88%|████████▊ | 759/861 [26:19<02:31,  1.48s/it]

 88%|████████▊ | 760/861 [26:22<03:06,  1.85s/it]

 88%|████████▊ | 761/861 [26:28<05:03,  3.03s/it]

 89%|████████▊ | 762/861 [26:29<04:10,  2.53s/it]

 89%|████████▊ | 763/861 [26:30<03:34,  2.19s/it]

 89%|████████▊ | 764/861 [26:32<03:17,  2.04s/it]

 89%|████████▉ | 765/861 [26:35<03:36,  2.26s/it]

 89%|████████▉ | 766/861 [26:37<03:33,  2.25s/it]

 89%|████████▉ | 767/861 [26:43<05:11,  3.31s/it]

 89%|████████▉ | 768/861 [26:45<04:39,  3.01s/it]

 89%|████████▉ | 769/861 [26:47<04:16,  2.79s/it]

 89%|████████▉ | 770/861 [26:48<03:29,  2.30s/it]

 90%|████████▉ | 771/861 [26:50<02:54,  1.94s/it]

 90%|████████▉ | 772/861 [26:52<02:52,  1.94s/it]

 90%|████████▉ | 773/861 [26:55<03:27,  2.36s/it]

 90%|████████▉ | 774/861 [26:57<03:12,  2.21s/it]

 90%|█████████ | 775/861 [26:59<03:23,  2.37s/it]

 90%|█████████ | 776/861 [27:02<03:33,  2.52s/it]

 90%|█████████ | 777/861 [27:06<03:54,  2.79s/it]

 90%|█████████ | 778/861 [27:08<03:36,  2.61s/it]

 90%|█████████ | 779/861 [27:13<04:23,  3.22s/it]

 91%|█████████ | 780/861 [27:16<04:36,  3.41s/it]

 91%|█████████ | 781/861 [27:21<05:02,  3.78s/it]

 91%|█████████ | 782/861 [27:24<04:41,  3.56s/it]

 91%|█████████ | 783/861 [27:26<04:01,  3.09s/it]

 91%|█████████ | 784/861 [27:31<04:33,  3.56s/it]

 91%|█████████ | 785/861 [27:33<03:50,  3.03s/it]

 91%|█████████▏| 786/861 [27:34<03:15,  2.60s/it]

 91%|█████████▏| 787/861 [27:36<02:49,  2.29s/it]

 92%|█████████▏| 788/861 [27:40<03:29,  2.87s/it]

 92%|█████████▏| 789/861 [27:42<03:18,  2.75s/it]

 92%|█████████▏| 790/861 [27:45<03:06,  2.63s/it]

 92%|█████████▏| 791/861 [27:47<02:49,  2.42s/it]

 92%|█████████▏| 792/861 [27:48<02:25,  2.11s/it]

 92%|█████████▏| 793/861 [27:51<02:38,  2.33s/it]

 92%|█████████▏| 794/861 [27:52<02:12,  1.97s/it]

 92%|█████████▏| 795/861 [27:58<03:24,  3.10s/it]

 92%|█████████▏| 796/861 [27:59<02:44,  2.53s/it]

 93%|█████████▎| 797/861 [28:01<02:26,  2.28s/it]

 93%|█████████▎| 798/861 [28:04<02:36,  2.49s/it]

 93%|█████████▎| 799/861 [28:06<02:38,  2.55s/it]

 93%|█████████▎| 800/861 [28:09<02:33,  2.51s/it]

 93%|█████████▎| 801/861 [28:11<02:33,  2.56s/it]

 93%|█████████▎| 802/861 [28:14<02:24,  2.44s/it]

 93%|█████████▎| 803/861 [28:16<02:22,  2.46s/it]

 93%|█████████▎| 804/861 [28:22<03:11,  3.37s/it]

 93%|█████████▎| 805/861 [28:26<03:30,  3.76s/it]

 94%|█████████▎| 806/861 [28:27<02:36,  2.84s/it]

 94%|█████████▎| 807/861 [28:29<02:18,  2.57s/it]

 94%|█████████▍| 808/861 [28:31<02:08,  2.42s/it]

 94%|█████████▍| 809/861 [28:32<01:39,  1.91s/it]

 94%|█████████▍| 810/861 [28:33<01:33,  1.83s/it]

 94%|█████████▍| 811/861 [28:36<01:38,  1.97s/it]

 94%|█████████▍| 812/861 [28:37<01:29,  1.83s/it]

 94%|█████████▍| 813/861 [28:40<01:47,  2.24s/it]

 95%|█████████▍| 814/861 [28:43<01:53,  2.42s/it]

 95%|█████████▍| 815/861 [28:46<01:53,  2.47s/it]

 95%|█████████▍| 816/861 [28:47<01:38,  2.19s/it]

 95%|█████████▍| 817/861 [28:50<01:38,  2.23s/it]

 95%|█████████▌| 818/861 [28:52<01:41,  2.36s/it]

 95%|█████████▌| 819/861 [28:54<01:25,  2.04s/it]

 95%|█████████▌| 820/861 [28:56<01:29,  2.18s/it]

 95%|█████████▌| 821/861 [29:00<01:41,  2.54s/it]

 95%|█████████▌| 822/861 [29:03<01:46,  2.74s/it]

 96%|█████████▌| 823/861 [29:06<01:55,  3.03s/it]

 96%|█████████▌| 824/861 [29:08<01:33,  2.52s/it]

 96%|█████████▌| 825/861 [29:09<01:18,  2.17s/it]

 96%|█████████▌| 826/861 [29:12<01:19,  2.28s/it]

 96%|█████████▌| 827/861 [29:14<01:21,  2.39s/it]

 96%|█████████▌| 828/861 [29:16<01:11,  2.16s/it]

 96%|█████████▋| 829/861 [29:19<01:17,  2.43s/it]

 96%|█████████▋| 830/861 [29:22<01:17,  2.50s/it]

 97%|█████████▋| 831/861 [29:24<01:16,  2.53s/it]

 97%|█████████▋| 832/861 [29:27<01:15,  2.61s/it]

 97%|█████████▋| 833/861 [29:28<01:01,  2.18s/it]

 97%|█████████▋| 834/861 [29:31<01:00,  2.26s/it]

 97%|█████████▋| 835/861 [29:33<00:58,  2.23s/it]

 97%|█████████▋| 836/861 [29:36<00:59,  2.38s/it]

 97%|█████████▋| 837/861 [29:38<00:57,  2.40s/it]

 97%|█████████▋| 838/861 [29:41<00:56,  2.47s/it]

 97%|█████████▋| 839/861 [29:42<00:48,  2.19s/it]

 98%|█████████▊| 840/861 [29:44<00:45,  2.16s/it]

 98%|█████████▊| 841/861 [29:46<00:42,  2.15s/it]

 98%|█████████▊| 842/861 [29:48<00:39,  2.08s/it]

 98%|█████████▊| 843/861 [29:51<00:41,  2.32s/it]

 98%|█████████▊| 844/861 [29:53<00:37,  2.20s/it]

 98%|█████████▊| 845/861 [29:56<00:36,  2.27s/it]

 98%|█████████▊| 846/861 [29:57<00:32,  2.16s/it]

 98%|█████████▊| 847/861 [30:00<00:30,  2.17s/it]

 98%|█████████▊| 848/861 [30:03<00:31,  2.40s/it]

 99%|█████████▊| 849/861 [30:05<00:29,  2.48s/it]

 99%|█████████▊| 850/861 [30:07<00:23,  2.17s/it]

 99%|█████████▉| 851/861 [30:09<00:20,  2.07s/it]

 99%|█████████▉| 852/861 [30:10<00:16,  1.84s/it]

 99%|█████████▉| 853/861 [30:13<00:17,  2.25s/it]

 99%|█████████▉| 854/861 [30:15<00:14,  2.10s/it]

 99%|█████████▉| 855/861 [30:17<00:12,  2.15s/it]

 99%|█████████▉| 856/861 [30:20<00:12,  2.45s/it]

100%|█████████▉| 857/861 [30:22<00:09,  2.31s/it]

100%|█████████▉| 858/861 [30:24<00:06,  2.27s/it]

100%|█████████▉| 859/861 [30:27<00:04,  2.38s/it]

100%|█████████▉| 860/861 [30:32<00:03,  3.20s/it]

100%|██████████| 861/861 [30:34<00:00,  2.83s/it]{'score': 0.07946246541694905, 'counts': [8950, 370, 101, 31], 'totals': [404161, 402439, 400717, 398995], 'precisions': [2.214464037846304, 0.09193939951147875, 0.025204820359505588, 0.007769520921314803], 'bp': 1.0, 'sys_len': 404161, 'ref_len': 32555}

                                                          

                                                 
{'eval_loss': 2.76475191116333, 'eval_bleu': 0.0795, 'eval_gen_len': 111.475, 'eval_runtime': 1941.3663, 'eval_samples_per_second': 0.887, 'eval_steps_per_second': 0.444, 'epoch': 3.0}

 19%|█▉        | 11608/61904 [6:03:58<18:28:34,  1.32s/it]

100%|██████████| 861/861 [32:18<00:00,  2.83s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-25 07:25:07,366 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 19%|█▉        | 11609/61904 [6:04:18<8237:10:56, 589.60s/it]
 19%|█▉        | 11610/61904 [6:04:20<5773:02:43, 413.23s/it]
 19%|█▉        | 11611/61904 [6:04:21<4046:58:49, 289.69s/it]
 19%|█▉        | 11612/61904 [6:04:22<2838:21:34, 203.18s/it]
 19%|█▉        | 11613/61904 [6:04:24<1992:53:35, 142.66s/it]
 19%|█▉        | 11614/61904 [6:04:25<1401:03:08, 100.29s/it]
 19%|█▉        | 11615/61904 [6:04:27<986:15:33, 70.60s/it]  
 19%|█▉        | 11616/61904 [6:04:28<696:06:03, 49.83s/it]
 19%|█▉        | 11617/61904 [6:04:29<492:53:12, 35.29s/it]
 19%|█▉        | 11618/61904 [6:04:31<350:58:48, 25.13s/it]
 19%|█▉        | 11619/61904 [6:04:32<251:37:02, 18.01s/it]
 19%|█▉        | 11620/61904 [6:04:33<181:18:10, 12.98s/it]
                                                           
{'loss': 2.8225, 'learning_rate': 1.8149228575132891e-07, 'epoch': 3.0}

 19%|█▉        | 11620/61904 [6:04:33<181:18:10, 12.98s/it]
 19%|█▉        | 11621/61904 [6:04:35<133:00:31,  9.52s/it]
 19%|█▉        | 11622/61904 [6:04:37<100:07:02,  7.17s/it]
 19%|█▉        | 11623/61904 [6:04:38<75:58:30,  5.44s/it] 
 19%|█▉        | 11624/61904 [6:04:39<58:47:41,  4.21s/it]
 19%|█▉        | 11625/61904 [6:04:41<46:56:52,  3.36s/it]
 19%|█▉        | 11626/61904 [6:04:42<38:49:45,  2.78s/it]
 19%|█▉        | 11627/61904 [6:04:44<33:38:10,  2.41s/it]
 19%|█▉        | 11628/61904 [6:04:45<28:46:00,  2.06s/it]
 19%|█▉        | 11629/61904 [6:04:46<25:49:53,  1.85s/it]
 19%|█▉        | 11630/61904 [6:04:48<23:55:02,  1.71s/it]
 19%|█▉        | 11631/61904 [6:04:49<22:23:59,  1.60s/it]
 19%|█▉        | 11632/61904 [6:04:50<21:46:45,  1.56s/it]
 19%|█▉        | 11633/61904 [6:04:52<21:23:28,  1.53s/it]
 19%|█▉        | 11634/61904 [6:04:53<20:32:33,  1.47s/it]
 19%|█▉        | 11635/61904 [6:04:55<19:51:28,  1.42s/it]
 19%|█▉        | 11636/61904 [6:04:56<19:26:14,  1.39s/it]
 19%|█▉        | 11637/61904 [6:04:57<19:18:33,  1.38s/it]
 19%|█▉        | 11638/61904 [6:04:59<19:11:37,  1.37s/it]
 19%|█▉        | 11639/61904 [6:05:00<19:44:00,  1.41s/it]
 19%|█▉        | 11640/61904 [6:05:01<19:19:00,  1.38s/it]
                                                          
{'loss': 2.7593, 'learning_rate': 1.814598729417866e-07, 'epoch': 3.01}

 19%|█▉        | 11640/61904 [6:05:01<19:19:00,  1.38s/it]
 19%|█▉        | 11641/61904 [6:05:03<19:14:00,  1.38s/it]
 19%|█▉        | 11642/61904 [6:05:04<19:33:04,  1.40s/it]
 19%|█▉        | 11643/61904 [6:05:06<19:11:00,  1.37s/it]
 19%|█▉        | 11644/61904 [6:05:07<19:01:33,  1.36s/it]
 19%|█▉        | 11645/61904 [6:05:08<19:07:31,  1.37s/it]
 19%|█▉        | 11646/61904 [6:05:10<19:33:26,  1.40s/it]
 19%|█▉        | 11647/61904 [6:05:11<20:44:42,  1.49s/it]
 19%|█▉        | 11648/61904 [6:05:13<20:11:52,  1.45s/it]
 19%|█▉        | 11649/61904 [6:05:14<19:50:24,  1.42s/it]
 19%|█▉        | 11650/61904 [6:05:15<19:39:59,  1.41s/it]
 19%|█▉        | 11651/61904 [6:05:17<20:31:24,  1.47s/it]
 19%|█▉        | 11652/61904 [6:05:18<19:58:07,  1.43s/it]
 19%|█▉        | 11653/61904 [6:05:20<19:24:34,  1.39s/it]
 19%|█▉        | 11654/61904 [6:05:21<19:04:24,  1.37s/it]
 19%|█▉        | 11655/61904 [6:05:22<19:23:49,  1.39s/it]
 19%|█▉        | 11656/61904 [6:05:24<19:19:55,  1.39s/it]
 19%|█▉        | 11657/61904 [6:05:25<19:08:37,  1.37s/it]
 19%|█▉        | 11658/61904 [6:05:26<18:44:36,  1.34s/it]
 19%|█▉        | 11659/61904 [6:05:28<19:09:11,  1.37s/it]
 19%|█▉        | 11660/61904 [6:05:29<19:15:03,  1.38s/it]
                                                          
{'loss': 2.7975, 'learning_rate': 1.8142746013224426e-07, 'epoch': 3.01}

 19%|█▉        | 11660/61904 [6:05:29<19:15:03,  1.38s/it]
 19%|█▉        | 11661/61904 [6:05:31<19:04:11,  1.37s/it]
 19%|█▉        | 11662/61904 [6:05:32<18:40:39,  1.34s/it]
 19%|█▉        | 11663/61904 [6:05:33<18:20:12,  1.31s/it]
 19%|█▉        | 11664/61904 [6:05:35<18:59:26,  1.36s/it]
 19%|█▉        | 11665/61904 [6:05:36<19:24:12,  1.39s/it]
 19%|█▉        | 11666/61904 [6:05:38<19:30:23,  1.40s/it]
 19%|█▉        | 11667/61904 [6:05:39<19:12:15,  1.38s/it]
 19%|█▉        | 11668/61904 [6:05:40<19:24:50,  1.39s/it]
 19%|█▉        | 11669/61904 [6:05:42<19:32:27,  1.40s/it]
 19%|█▉        | 11670/61904 [6:05:43<19:39:09,  1.41s/it]
 19%|█▉        | 11671/61904 [6:05:44<19:23:27,  1.39s/it]
 19%|█▉        | 11672/61904 [6:05:46<19:56:37,  1.43s/it]
 19%|█▉        | 11673/61904 [6:05:47<19:31:20,  1.40s/it]
 19%|█▉        | 11674/61904 [6:05:49<19:24:36,  1.39s/it]
 19%|█▉        | 11675/61904 [6:05:50<19:10:49,  1.37s/it]
 19%|█▉        | 11676/61904 [6:05:51<19:31:36,  1.40s/it]
 19%|█▉        | 11677/61904 [6:05:53<20:40:49,  1.48s/it]
 19%|█▉        | 11678/61904 [6:05:55<20:11:52,  1.45s/it]
 19%|█▉        | 11679/61904 [6:05:56<20:09:32,  1.44s/it]
 19%|█▉        | 11680/61904 [6:05:57<19:59:43,  1.43s/it]
                                                          
{'loss': 2.8483, 'learning_rate': 1.8139504732270193e-07, 'epoch': 3.02}

 19%|█▉        | 11680/61904 [6:05:57<19:59:43,  1.43s/it]
 19%|█▉        | 11681/61904 [6:05:59<19:47:25,  1.42s/it]
 19%|█▉        | 11682/61904 [6:06:00<19:30:21,  1.40s/it]
 19%|█▉        | 11683/61904 [6:06:01<19:04:27,  1.37s/it]
 19%|█▉        | 11684/61904 [6:06:03<19:11:13,  1.38s/it]
 19%|█▉        | 11685/61904 [6:06:04<19:10:27,  1.37s/it]
 19%|█▉        | 11686/61904 [6:06:05<18:48:27,  1.35s/it]
 19%|█▉        | 11687/61904 [6:06:07<20:10:59,  1.45s/it]
 19%|█▉        | 11688/61904 [6:06:08<19:46:06,  1.42s/it]
 19%|█▉        | 11689/61904 [6:06:10<20:03:15,  1.44s/it]
 19%|█▉        | 11690/61904 [6:06:11<20:11:44,  1.45s/it]
 19%|█▉        | 11691/61904 [6:06:13<19:34:06,  1.40s/it]
 19%|█▉        | 11692/61904 [6:06:14<19:23:14,  1.39s/it]
 19%|█▉        | 11693/61904 [6:06:15<19:22:12,  1.39s/it]
 19%|█▉        | 11694/61904 [6:06:17<19:57:44,  1.43s/it]
 19%|█▉        | 11695/61904 [6:06:18<19:42:06,  1.41s/it]
 19%|█▉        | 11696/61904 [6:06:20<19:21:36,  1.39s/it]
 19%|█▉        | 11697/61904 [6:06:21<18:56:29,  1.36s/it]
 19%|█▉        | 11698/61904 [6:06:22<18:46:29,  1.35s/it]
 19%|█▉        | 11699/61904 [6:06:24<19:02:41,  1.37s/it]
 19%|█▉        | 11700/61904 [6:06:25<19:17:33,  1.38s/it]
                                                          
{'loss': 2.8307, 'learning_rate': 1.8136263451315961e-07, 'epoch': 3.02}

 19%|█▉        | 11700/61904 [6:06:25<19:17:33,  1.38s/it]
 19%|█▉        | 11701/61904 [6:06:27<19:07:27,  1.37s/it]
 19%|█▉        | 11702/61904 [6:06:28<19:40:36,  1.41s/it]
 19%|█▉        | 11703/61904 [6:06:29<19:03:17,  1.37s/it]
 19%|█▉        | 11704/61904 [6:06:31<18:38:41,  1.34s/it]
 19%|█▉        | 11705/61904 [6:06:32<18:28:35,  1.33s/it]
 19%|█▉        | 11706/61904 [6:06:33<19:09:01,  1.37s/it]
 19%|█▉        | 11707/61904 [6:06:35<20:21:54,  1.46s/it]
 19%|█▉        | 11708/61904 [6:06:36<20:27:44,  1.47s/it]
 19%|█▉        | 11709/61904 [6:06:38<20:39:10,  1.48s/it]
 19%|█▉        | 11710/61904 [6:06:40<21:56:10,  1.57s/it]
 19%|█▉        | 11711/61904 [6:06:41<20:42:06,  1.48s/it]
 19%|█▉        | 11712/61904 [6:06:42<20:22:57,  1.46s/it]
 19%|█▉        | 11713/61904 [6:06:44<19:47:47,  1.42s/it]
 19%|█▉        | 11714/61904 [6:06:45<19:20:38,  1.39s/it]
 19%|█▉        | 11715/61904 [6:06:46<19:03:20,  1.37s/it]
 19%|█▉        | 11716/61904 [6:06:48<19:16:22,  1.38s/it]
 19%|█▉        | 11717/61904 [6:06:49<19:02:01,  1.37s/it]
 19%|█▉        | 11718/61904 [6:06:51<19:14:45,  1.38s/it]
 19%|█▉        | 11719/61904 [6:06:52<19:09:28,  1.37s/it]
 19%|█▉        | 11720/61904 [6:06:53<18:55:48,  1.36s/it]
                                                          
{'loss': 2.7256, 'learning_rate': 1.8133022170361725e-07, 'epoch': 3.03}

 19%|█▉        | 11720/61904 [6:06:53<18:55:48,  1.36s/it]
 19%|█▉        | 11721/61904 [6:06:55<19:36:27,  1.41s/it]
 19%|█▉        | 11722/61904 [6:06:56<19:12:44,  1.38s/it]
 19%|█▉        | 11723/61904 [6:06:58<19:40:28,  1.41s/it]
 19%|█▉        | 11724/61904 [6:06:59<19:14:27,  1.38s/it]
 19%|█▉        | 11725/61904 [6:07:00<18:21:52,  1.32s/it]
 19%|█▉        | 11726/61904 [6:07:01<18:37:46,  1.34s/it]
 19%|█▉        | 11727/61904 [6:07:03<18:55:32,  1.36s/it]
 19%|█▉        | 11728/61904 [6:07:04<18:49:38,  1.35s/it]
 19%|█▉        | 11729/61904 [6:07:06<19:07:04,  1.37s/it]
 19%|█▉        | 11730/61904 [6:07:07<18:41:31,  1.34s/it]
 19%|█▉        | 11731/61904 [6:07:08<18:58:42,  1.36s/it]
 19%|█▉        | 11732/61904 [6:07:10<18:51:56,  1.35s/it]
 19%|█▉        | 11733/61904 [6:07:11<19:40:56,  1.41s/it]
 19%|█▉        | 11734/61904 [6:07:12<19:21:34,  1.39s/it]
 19%|█▉        | 11735/61904 [6:07:14<18:52:54,  1.35s/it]
 19%|█▉        | 11736/61904 [6:07:15<18:35:34,  1.33s/it]
 19%|█▉        | 11737/61904 [6:07:17<19:12:19,  1.38s/it]
 19%|█▉        | 11738/61904 [6:07:18<18:49:35,  1.35s/it]
 19%|█▉        | 11739/61904 [6:07:19<18:17:34,  1.31s/it]
 19%|█▉        | 11740/61904 [6:07:20<18:17:19,  1.31s/it]
                                                          
{'loss': 2.8067, 'learning_rate': 1.8129780889407494e-07, 'epoch': 3.03}

 19%|█▉        | 11740/61904 [6:07:20<18:17:19,  1.31s/it]
 19%|█▉        | 11741/61904 [6:07:22<18:11:05,  1.31s/it]
 19%|█▉        | 11742/61904 [6:07:23<18:07:53,  1.30s/it]
 19%|█▉        | 11743/61904 [6:07:24<18:33:14,  1.33s/it]
 19%|█▉        | 11744/61904 [6:07:26<18:31:33,  1.33s/it]
 19%|█▉        | 11745/61904 [6:07:27<18:34:48,  1.33s/it]
 19%|█▉        | 11746/61904 [6:07:28<18:19:11,  1.31s/it]
 19%|█▉        | 11747/61904 [6:07:30<18:47:19,  1.35s/it]
 19%|█▉        | 11748/61904 [6:07:31<18:40:42,  1.34s/it]
 19%|█▉        | 11749/61904 [6:07:32<18:59:36,  1.36s/it]
 19%|█▉        | 11750/61904 [6:07:34<18:46:36,  1.35s/it]
 19%|█▉        | 11751/61904 [6:07:35<18:51:56,  1.35s/it]
 19%|█▉        | 11752/61904 [6:07:36<18:47:23,  1.35s/it]
 19%|█▉        | 11753/61904 [6:07:38<18:38:06,  1.34s/it]
 19%|█▉        | 11754/61904 [6:07:39<18:58:55,  1.36s/it]
 19%|█▉        | 11755/61904 [6:07:40<18:24:47,  1.32s/it]
 19%|█▉        | 11756/61904 [6:07:42<18:35:36,  1.33s/it]
 19%|█▉        | 11757/61904 [6:07:43<18:46:57,  1.35s/it]
 19%|█▉        | 11758/61904 [6:07:45<19:17:22,  1.38s/it]
 19%|█▉        | 11759/61904 [6:07:46<19:24:55,  1.39s/it]
 19%|█▉        | 11760/61904 [6:07:47<18:59:54,  1.36s/it]
                                                          
{'loss': 2.7359, 'learning_rate': 1.812653960845326e-07, 'epoch': 3.04}

 19%|█▉        | 11760/61904 [6:07:47<18:59:54,  1.36s/it]
 19%|█▉        | 11761/61904 [6:07:49<18:45:10,  1.35s/it]
 19%|█▉        | 11762/61904 [6:07:50<19:32:19,  1.40s/it]
 19%|█▉        | 11763/61904 [6:07:52<19:35:53,  1.41s/it]
 19%|█▉        | 11764/61904 [6:07:53<18:56:44,  1.36s/it]
 19%|█▉        | 11765/61904 [6:07:54<19:40:05,  1.41s/it]
 19%|█▉        | 11766/61904 [6:07:56<19:24:49,  1.39s/it]
 19%|█▉        | 11767/61904 [6:07:57<20:18:23,  1.46s/it]
 19%|█▉        | 11768/61904 [6:07:59<20:04:39,  1.44s/it]
 19%|█▉        | 11769/61904 [6:08:00<19:41:47,  1.41s/it]
 19%|█▉        | 11770/61904 [6:08:02<20:18:49,  1.46s/it]
 19%|█▉        | 11771/61904 [6:08:03<19:38:56,  1.41s/it]
 19%|█▉        | 11772/61904 [6:08:04<19:21:54,  1.39s/it]
 19%|█▉        | 11773/61904 [6:08:06<19:04:05,  1.37s/it]
 19%|█▉        | 11774/61904 [6:08:07<19:08:59,  1.38s/it]
 19%|█▉        | 11775/61904 [6:08:08<19:13:58,  1.38s/it]
 19%|█▉        | 11776/61904 [6:08:10<18:52:32,  1.36s/it]
 19%|█▉        | 11777/61904 [6:08:11<18:36:54,  1.34s/it]
 19%|█▉        | 11778/61904 [6:08:12<18:30:29,  1.33s/it]
 19%|█▉        | 11779/61904 [6:08:14<19:00:52,  1.37s/it]
 19%|█▉        | 11780/61904 [6:08:15<19:14:04,  1.38s/it]
                                                          
{'loss': 2.8118, 'learning_rate': 1.8123298327499026e-07, 'epoch': 3.04}

 19%|█▉        | 11780/61904 [6:08:15<19:14:04,  1.38s/it]
 19%|█▉        | 11781/61904 [6:08:17<19:00:38,  1.37s/it]
 19%|█▉        | 11782/61904 [6:08:18<19:15:09,  1.38s/it]
 19%|█▉        | 11783/61904 [6:08:19<19:17:36,  1.39s/it]
 19%|█▉        | 11784/61904 [6:08:21<19:10:19,  1.38s/it]
 19%|█▉        | 11785/61904 [6:08:22<19:45:49,  1.42s/it]
 19%|█▉        | 11786/61904 [6:08:23<19:09:37,  1.38s/it]
 19%|█▉        | 11787/61904 [6:08:25<19:15:17,  1.38s/it]
 19%|█▉        | 11788/61904 [6:08:26<19:17:05,  1.39s/it]
 19%|█▉        | 11789/61904 [6:08:28<18:59:59,  1.36s/it]
 19%|█▉        | 11790/61904 [6:08:29<18:44:13,  1.35s/it]
 19%|█▉        | 11791/61904 [6:08:30<18:32:55,  1.33s/it]
 19%|█▉        | 11792/61904 [6:08:31<18:13:53,  1.31s/it]
 19%|█▉        | 11793/61904 [6:08:33<18:30:57,  1.33s/it]
 19%|█▉        | 11794/61904 [6:08:34<18:29:05,  1.33s/it]
 19%|█▉        | 11795/61904 [6:08:35<18:19:38,  1.32s/it]
 19%|█▉        | 11796/61904 [6:08:37<18:14:05,  1.31s/it]
 19%|█▉        | 11797/61904 [6:08:38<18:49:24,  1.35s/it]
 19%|█▉        | 11798/61904 [6:08:40<19:42:37,  1.42s/it]
 19%|█▉        | 11799/61904 [6:08:41<19:53:36,  1.43s/it]
 19%|█▉        | 11800/61904 [6:08:43<19:40:28,  1.41s/it]
                                                          
{'loss': 2.8233, 'learning_rate': 1.8120057046544795e-07, 'epoch': 3.05}

 19%|█▉        | 11800/61904 [6:08:43<19:40:28,  1.41s/it]
 19%|█▉        | 11801/61904 [6:08:44<19:00:20,  1.37s/it]
 19%|█▉        | 11802/61904 [6:08:45<18:58:47,  1.36s/it]
 19%|█▉        | 11803/61904 [6:08:47<18:53:45,  1.36s/it]
 19%|█▉        | 11804/61904 [6:08:48<18:50:50,  1.35s/it]
 19%|█▉        | 11805/61904 [6:08:49<19:11:25,  1.38s/it]
 19%|█▉        | 11806/61904 [6:08:51<19:04:32,  1.37s/it]
 19%|█▉        | 11807/61904 [6:08:52<19:19:17,  1.39s/it]
 19%|█▉        | 11808/61904 [6:08:54<19:31:48,  1.40s/it]
 19%|█▉        | 11809/61904 [6:08:55<18:47:21,  1.35s/it]
 19%|█▉        | 11810/61904 [6:08:56<18:57:51,  1.36s/it]
 19%|█▉        | 11811/61904 [6:08:58<19:20:25,  1.39s/it]
 19%|█▉        | 11812/61904 [6:08:59<18:55:22,  1.36s/it]
 19%|█▉        | 11813/61904 [6:09:00<18:44:16,  1.35s/it]
 19%|█▉        | 11814/61904 [6:09:01<18:21:15,  1.32s/it]
 19%|█▉        | 11815/61904 [6:09:03<18:03:16,  1.30s/it]
 19%|█▉        | 11816/61904 [6:09:04<18:54:11,  1.36s/it]
 19%|█▉        | 11817/61904 [6:09:06<20:01:16,  1.44s/it]
 19%|█▉        | 11818/61904 [6:09:07<19:59:20,  1.44s/it]
 19%|█▉        | 11819/61904 [6:09:09<20:22:24,  1.46s/it]
 19%|█▉        | 11820/61904 [6:09:10<19:55:34,  1.43s/it]
                                                          
{'loss': 2.8124, 'learning_rate': 1.811681576559056e-07, 'epoch': 3.05}

 19%|█▉        | 11820/61904 [6:09:10<19:55:34,  1.43s/it]
 19%|█▉        | 11821/61904 [6:09:12<20:09:17,  1.45s/it]
 19%|█▉        | 11822/61904 [6:09:13<19:44:20,  1.42s/it]
 19%|█▉        | 11823/61904 [6:09:14<19:35:03,  1.41s/it]
 19%|█▉        | 11824/61904 [6:09:16<19:48:00,  1.42s/it]
 19%|█▉        | 11825/61904 [6:09:17<19:30:41,  1.40s/it]
 19%|█▉        | 11826/61904 [6:09:19<19:21:33,  1.39s/it]
 19%|█▉        | 11827/61904 [6:09:20<19:27:21,  1.40s/it]
 19%|█▉        | 11828/61904 [6:09:21<19:50:00,  1.43s/it]
 19%|█▉        | 11829/61904 [6:09:23<19:18:08,  1.39s/it]
 19%|█▉        | 11830/61904 [6:09:24<18:37:01,  1.34s/it]
 19%|█▉        | 11831/61904 [6:09:25<18:25:56,  1.33s/it]
 19%|█▉        | 11832/61904 [6:09:27<18:33:12,  1.33s/it]
 19%|█▉        | 11833/61904 [6:09:28<18:17:30,  1.32s/it]
 19%|█▉        | 11834/61904 [6:09:29<19:05:59,  1.37s/it]
 19%|█▉        | 11835/61904 [6:09:31<19:52:39,  1.43s/it]
 19%|█▉        | 11836/61904 [6:09:32<19:26:28,  1.40s/it]
 19%|█▉        | 11837/61904 [6:09:34<19:20:36,  1.39s/it]
 19%|█▉        | 11838/61904 [6:09:35<19:28:37,  1.40s/it]
 19%|█▉        | 11839/61904 [6:09:36<19:22:40,  1.39s/it]
 19%|█▉        | 11840/61904 [6:09:38<19:12:39,  1.38s/it]
                                                          
{'loss': 2.7403, 'learning_rate': 1.8113574484636327e-07, 'epoch': 3.06}

 19%|█▉        | 11840/61904 [6:09:38<19:12:39,  1.38s/it]
 19%|█▉        | 11841/61904 [6:09:39<19:06:09,  1.37s/it]
 19%|█▉        | 11842/61904 [6:09:41<18:55:07,  1.36s/it]
 19%|█▉        | 11843/61904 [6:09:42<18:47:15,  1.35s/it]
 19%|█▉        | 11844/61904 [6:09:43<18:51:32,  1.36s/it]
 19%|█▉        | 11845/61904 [6:09:45<18:35:09,  1.34s/it]
 19%|█▉        | 11846/61904 [6:09:46<19:02:10,  1.37s/it]
 19%|█▉        | 11847/61904 [6:09:47<19:18:42,  1.39s/it]
 19%|█▉        | 11848/61904 [6:09:49<19:54:19,  1.43s/it]
 19%|█▉        | 11849/61904 [6:09:50<19:20:10,  1.39s/it]
 19%|█▉        | 11850/61904 [6:09:52<20:17:03,  1.46s/it]
 19%|█▉        | 11851/61904 [6:09:53<19:33:30,  1.41s/it]
 19%|█▉        | 11852/61904 [6:09:55<19:28:42,  1.40s/it]
 19%|█▉        | 11853/61904 [6:09:56<19:30:28,  1.40s/it]
 19%|█▉        | 11854/61904 [6:09:57<19:13:13,  1.38s/it]
 19%|█▉        | 11855/61904 [6:09:58<18:40:20,  1.34s/it]
 19%|█▉        | 11856/61904 [6:10:00<18:43:38,  1.35s/it]
 19%|█▉        | 11857/61904 [6:10:01<18:49:22,  1.35s/it]
 19%|█▉        | 11858/61904 [6:10:03<19:47:39,  1.42s/it]
 19%|█▉        | 11859/61904 [6:10:04<19:21:07,  1.39s/it]
 19%|█▉        | 11860/61904 [6:10:05<19:06:19,  1.37s/it]
                                                          
{'loss': 2.8573, 'learning_rate': 1.8110333203682096e-07, 'epoch': 3.06}

 19%|█▉        | 11860/61904 [6:10:05<19:06:19,  1.37s/it]
 19%|█▉        | 11861/61904 [6:10:07<18:58:08,  1.36s/it]
 19%|█▉        | 11862/61904 [6:10:08<18:56:27,  1.36s/it]
 19%|█▉        | 11863/61904 [6:10:10<18:53:08,  1.36s/it]
 19%|█▉        | 11864/61904 [6:10:11<18:45:36,  1.35s/it]
 19%|█▉        | 11865/61904 [6:10:12<19:04:34,  1.37s/it]
 19%|█▉        | 11866/61904 [6:10:14<19:01:22,  1.37s/it]
 19%|█▉        | 11867/61904 [6:10:15<19:02:58,  1.37s/it]
 19%|█▉        | 11868/61904 [6:10:16<19:17:22,  1.39s/it]
 19%|█▉        | 11869/61904 [6:10:18<18:59:34,  1.37s/it]
 19%|█▉        | 11870/61904 [6:10:19<19:09:26,  1.38s/it]
 19%|█▉        | 11871/61904 [6:10:21<20:06:25,  1.45s/it]
 19%|█▉        | 11872/61904 [6:10:22<19:49:05,  1.43s/it]
 19%|█▉        | 11873/61904 [6:10:23<19:03:21,  1.37s/it]
 19%|█▉        | 11874/61904 [6:10:25<19:22:24,  1.39s/it]
 19%|█▉        | 11875/61904 [6:10:26<20:07:53,  1.45s/it]
 19%|█▉        | 11876/61904 [6:10:28<20:11:47,  1.45s/it]
 19%|█▉        | 11877/61904 [6:10:29<20:20:05,  1.46s/it]
 19%|█▉        | 11878/61904 [6:10:31<20:02:47,  1.44s/it]
 19%|█▉        | 11879/61904 [6:10:32<19:36:35,  1.41s/it]
 19%|█▉        | 11880/61904 [6:10:33<19:13:29,  1.38s/it]
                                                          
{'loss': 2.8055, 'learning_rate': 1.810709192272786e-07, 'epoch': 3.07}

 19%|█▉        | 11880/61904 [6:10:33<19:13:29,  1.38s/it]
 19%|█▉        | 11881/61904 [6:10:35<19:07:38,  1.38s/it]
 19%|█▉        | 11882/61904 [6:10:36<19:29:01,  1.40s/it]
 19%|█▉        | 11883/61904 [6:10:38<19:06:34,  1.38s/it]
 19%|█▉        | 11884/61904 [6:10:39<19:23:52,  1.40s/it]
 19%|█▉        | 11885/61904 [6:10:40<18:55:39,  1.36s/it]
 19%|█▉        | 11886/61904 [6:10:42<18:49:45,  1.36s/it]
 19%|█▉        | 11887/61904 [6:10:43<18:47:03,  1.35s/it]
 19%|█▉        | 11888/61904 [6:10:44<19:22:31,  1.39s/it]
 19%|█▉        | 11889/61904 [6:10:46<19:03:41,  1.37s/it]
 19%|█▉        | 11890/61904 [6:10:47<18:44:17,  1.35s/it]
 19%|█▉        | 11891/61904 [6:10:48<18:27:03,  1.33s/it]
 19%|█▉        | 11892/61904 [6:10:50<18:30:04,  1.33s/it]
 19%|█▉        | 11893/61904 [6:10:51<18:22:34,  1.32s/it]
 19%|█▉        | 11894/61904 [6:10:52<18:36:24,  1.34s/it]
 19%|█▉        | 11895/61904 [6:10:54<18:24:30,  1.33s/it]
 19%|█▉        | 11896/61904 [6:10:55<20:13:43,  1.46s/it]
 19%|█▉        | 11897/61904 [6:10:57<19:18:50,  1.39s/it]
 19%|█▉        | 11898/61904 [6:10:58<19:46:02,  1.42s/it]
 19%|█▉        | 11899/61904 [6:10:59<19:07:34,  1.38s/it]
 19%|█▉        | 11900/61904 [6:11:01<18:59:28,  1.37s/it]
                                                          
{'loss': 2.7713, 'learning_rate': 1.8103850641773629e-07, 'epoch': 3.08}

 19%|█▉        | 11900/61904 [6:11:01<18:59:28,  1.37s/it]
 19%|█▉        | 11901/61904 [6:11:02<18:57:46,  1.37s/it]
 19%|█▉        | 11902/61904 [6:11:03<18:25:00,  1.33s/it]
 19%|█▉        | 11903/61904 [6:11:05<19:13:48,  1.38s/it]
 19%|█▉        | 11904/61904 [6:11:06<19:12:55,  1.38s/it]
 19%|█▉        | 11905/61904 [6:11:08<18:45:54,  1.35s/it]
 19%|█▉        | 11906/61904 [6:11:09<18:37:38,  1.34s/it]
 19%|█▉        | 11907/61904 [6:11:10<18:49:17,  1.36s/it]
 19%|█▉        | 11908/61904 [6:11:12<18:43:03,  1.35s/it]
 19%|█▉        | 11909/61904 [6:11:13<19:47:15,  1.42s/it]
 19%|█▉        | 11910/61904 [6:11:15<19:45:00,  1.42s/it]
 19%|█▉        | 11911/61904 [6:11:16<19:09:11,  1.38s/it]
 19%|█▉        | 11912/61904 [6:11:17<18:34:48,  1.34s/it]
 19%|█▉        | 11913/61904 [6:11:19<19:06:38,  1.38s/it]
 19%|█▉        | 11914/61904 [6:11:20<18:52:27,  1.36s/it]
 19%|█▉        | 11915/61904 [6:11:21<18:18:55,  1.32s/it]
 19%|█▉        | 11916/61904 [6:11:23<18:43:39,  1.35s/it]
 19%|█▉        | 11917/61904 [6:11:24<18:07:03,  1.30s/it]
 19%|█▉        | 11918/61904 [6:11:25<19:01:10,  1.37s/it]
 19%|█▉        | 11919/61904 [6:11:27<18:54:24,  1.36s/it]
 19%|█▉        | 11920/61904 [6:11:28<18:47:47,  1.35s/it]
                                                          
{'loss': 2.7659, 'learning_rate': 1.8100609360819395e-07, 'epoch': 3.08}

 19%|█▉        | 11920/61904 [6:11:28<18:47:47,  1.35s/it]
 19%|█▉        | 11921/61904 [6:11:29<18:59:36,  1.37s/it]
 19%|█▉        | 11922/61904 [6:11:31<19:27:10,  1.40s/it]
 19%|█▉        | 11923/61904 [6:11:32<20:19:41,  1.46s/it]
 19%|█▉        | 11924/61904 [6:11:34<19:50:43,  1.43s/it]
 19%|█▉        | 11925/61904 [6:11:35<19:38:17,  1.41s/it]
 19%|█▉        | 11926/61904 [6:11:37<19:58:22,  1.44s/it]
 19%|█▉        | 11927/61904 [6:11:38<19:23:40,  1.40s/it]
 19%|█▉        | 11928/61904 [6:11:39<19:13:20,  1.38s/it]
 19%|█▉        | 11929/61904 [6:11:41<18:54:37,  1.36s/it]
 19%|█▉        | 11930/61904 [6:11:42<18:47:52,  1.35s/it]
 19%|█▉        | 11931/61904 [6:11:43<18:50:36,  1.36s/it]
 19%|█▉        | 11932/61904 [6:11:45<18:31:04,  1.33s/it]
 19%|█▉        | 11933/61904 [6:11:46<19:05:56,  1.38s/it]
 19%|█▉        | 11934/61904 [6:11:48<19:24:23,  1.40s/it]
 19%|█▉        | 11935/61904 [6:11:49<18:44:47,  1.35s/it]
 19%|█▉        | 11936/61904 [6:11:50<18:32:54,  1.34s/it]
 19%|█▉        | 11937/61904 [6:11:51<18:32:31,  1.34s/it]
 19%|█▉        | 11938/61904 [6:11:53<18:59:53,  1.37s/it]
 19%|█▉        | 11939/61904 [6:11:54<19:33:14,  1.41s/it]
 19%|█▉        | 11940/61904 [6:11:56<19:33:41,  1.41s/it]
                                                          
{'loss': 2.8172, 'learning_rate': 1.809736807986516e-07, 'epoch': 3.09}

 19%|█▉        | 11940/61904 [6:11:56<19:33:41,  1.41s/it]
 19%|█▉        | 11941/61904 [6:11:57<20:06:03,  1.45s/it]
 19%|█▉        | 11942/61904 [6:11:59<19:37:17,  1.41s/it]
 19%|█▉        | 11943/61904 [6:12:00<19:05:57,  1.38s/it]
 19%|█▉        | 11944/61904 [6:12:01<18:40:42,  1.35s/it]
 19%|█▉        | 11945/61904 [6:12:02<18:24:30,  1.33s/it]
 19%|█▉        | 11946/61904 [6:12:04<19:09:35,  1.38s/it]
 19%|█▉        | 11947/61904 [6:12:05<18:57:34,  1.37s/it]
 19%|█▉        | 11948/61904 [6:12:07<19:14:56,  1.39s/it]
 19%|█▉        | 11949/61904 [6:12:08<19:01:34,  1.37s/it]
 19%|█▉        | 11950/61904 [6:12:09<18:54:30,  1.36s/it]
 19%|█▉        | 11951/61904 [6:12:11<18:59:49,  1.37s/it]
 19%|█▉        | 11952/61904 [6:12:12<18:08:47,  1.31s/it]
 19%|█▉        | 11953/61904 [6:12:13<18:19:35,  1.32s/it]
 19%|█▉        | 11954/61904 [6:12:15<18:33:16,  1.34s/it]
 19%|█▉        | 11955/61904 [6:12:16<18:31:05,  1.33s/it]
 19%|█▉        | 11956/61904 [6:12:17<18:37:53,  1.34s/it]
 19%|█▉        | 11957/61904 [6:12:19<18:42:21,  1.35s/it]
 19%|█▉        | 11958/61904 [6:12:20<18:31:34,  1.34s/it]
 19%|█▉        | 11959/61904 [6:12:21<18:47:05,  1.35s/it]
 19%|█▉        | 11960/61904 [6:12:23<19:01:06,  1.37s/it]
                                                          
{'loss': 2.8002, 'learning_rate': 1.809412679891093e-07, 'epoch': 3.09}

 19%|█▉        | 11960/61904 [6:12:23<19:01:06,  1.37s/it]
 19%|█▉        | 11961/61904 [6:12:24<19:18:57,  1.39s/it]
 19%|█▉        | 11962/61904 [6:12:26<19:27:41,  1.40s/it]
 19%|█▉        | 11963/61904 [6:12:27<19:15:48,  1.39s/it]
 19%|█▉        | 11964/61904 [6:12:28<18:59:36,  1.37s/it]
 19%|█▉        | 11965/61904 [6:12:30<18:49:18,  1.36s/it]
 19%|█▉        | 11966/61904 [6:12:31<18:47:46,  1.36s/it]
 19%|█▉        | 11967/61904 [6:12:33<19:20:58,  1.39s/it]
 19%|█▉        | 11968/61904 [6:12:34<20:04:09,  1.45s/it]
 19%|█▉        | 11969/61904 [6:12:36<19:43:51,  1.42s/it]
 19%|█▉        | 11970/61904 [6:12:37<20:13:14,  1.46s/it]
 19%|█▉        | 11971/61904 [6:12:38<19:40:11,  1.42s/it]
 19%|█▉        | 11972/61904 [6:12:40<19:16:52,  1.39s/it]
 19%|█▉        | 11973/61904 [6:12:41<19:10:15,  1.38s/it]
 19%|█▉        | 11974/61904 [6:12:43<19:22:31,  1.40s/it]
 19%|█▉        | 11975/61904 [6:12:44<19:18:11,  1.39s/it]
 19%|█▉        | 11976/61904 [6:12:45<19:18:48,  1.39s/it]
 19%|█▉        | 11977/61904 [6:12:47<19:07:07,  1.38s/it]
 19%|█▉        | 11978/61904 [6:12:48<20:04:53,  1.45s/it]
 19%|█▉        | 11979/61904 [6:12:50<19:27:07,  1.40s/it]
 19%|█▉        | 11980/61904 [6:12:51<19:09:18,  1.38s/it]
                                                          
{'loss': 2.8898, 'learning_rate': 1.8090885517956696e-07, 'epoch': 3.1}

 19%|█▉        | 11980/61904 [6:12:51<19:09:18,  1.38s/it]
 19%|█▉        | 11981/61904 [6:12:52<19:17:24,  1.39s/it]
 19%|█▉        | 11982/61904 [6:12:54<19:52:56,  1.43s/it]
 19%|█▉        | 11983/61904 [6:12:55<19:17:33,  1.39s/it]
 19%|█▉        | 11984/61904 [6:12:57<20:04:53,  1.45s/it]
 19%|█▉        | 11985/61904 [6:12:58<19:45:28,  1.42s/it]
 19%|█▉        | 11986/61904 [6:12:59<19:39:50,  1.42s/it]
 19%|█▉        | 11987/61904 [6:13:01<19:51:40,  1.43s/it]
 19%|█▉        | 11988/61904 [6:13:02<19:16:48,  1.39s/it]
 19%|█▉        | 11989/61904 [6:13:04<19:20:38,  1.40s/it]
 19%|█▉        | 11990/61904 [6:13:05<19:39:31,  1.42s/it]
 19%|█▉        | 11991/61904 [6:13:06<19:19:09,  1.39s/it]
 19%|█▉        | 11992/61904 [6:13:08<19:28:51,  1.41s/it]
 19%|█▉        | 11993/61904 [6:13:09<18:31:34,  1.34s/it]
 19%|█▉        | 11994/61904 [6:13:10<18:47:32,  1.36s/it]
 19%|█▉        | 11995/61904 [6:13:12<19:11:46,  1.38s/it]
 19%|█▉        | 11996/61904 [6:13:13<19:08:52,  1.38s/it]
 19%|█▉        | 11997/61904 [6:13:15<18:44:02,  1.35s/it]
 19%|█▉        | 11998/61904 [6:13:16<19:39:23,  1.42s/it]
 19%|█▉        | 11999/61904 [6:13:17<18:57:51,  1.37s/it]
 19%|█▉        | 12000/61904 [6:13:19<18:37:31,  1.34s/it]
                                                          
{'loss': 2.8703, 'learning_rate': 1.8087644237002462e-07, 'epoch': 3.1}

 19%|█▉        | 12000/61904 [6:13:19<18:37:31,  1.34s/it]
 19%|█▉        | 12001/61904 [6:13:20<19:27:16,  1.40s/it]
 19%|█▉        | 12002/61904 [6:13:22<19:31:29,  1.41s/it]
 19%|█▉        | 12003/61904 [6:13:23<19:37:41,  1.42s/it]
 19%|█▉        | 12004/61904 [6:13:25<19:55:08,  1.44s/it]
 19%|█▉        | 12005/61904 [6:13:26<19:36:22,  1.41s/it]
 19%|█▉        | 12006/61904 [6:13:27<19:14:15,  1.39s/it]
 19%|█▉        | 12007/61904 [6:13:29<19:02:40,  1.37s/it]
 19%|█▉        | 12008/61904 [6:13:30<18:51:03,  1.36s/it]
 19%|█▉        | 12009/61904 [6:13:31<18:29:25,  1.33s/it]
 19%|█▉        | 12010/61904 [6:13:33<18:44:21,  1.35s/it]
 19%|█▉        | 12011/61904 [6:13:34<19:15:02,  1.39s/it]
 19%|█▉        | 12012/61904 [6:13:36<19:33:50,  1.41s/it]
 19%|█▉        | 12013/61904 [6:13:37<19:04:28,  1.38s/it]
 19%|█▉        | 12014/61904 [6:13:38<19:29:35,  1.41s/it]
 19%|█▉        | 12015/61904 [6:13:40<19:34:25,  1.41s/it]
 19%|█▉        | 12016/61904 [6:13:41<18:49:05,  1.36s/it]
 19%|█▉        | 12017/61904 [6:13:42<18:45:09,  1.35s/it]
 19%|█▉        | 12018/61904 [6:13:44<19:35:02,  1.41s/it]
 19%|█▉        | 12019/61904 [6:13:45<19:30:37,  1.41s/it]
 19%|█▉        | 12020/61904 [6:13:47<19:10:30,  1.38s/it]
                                                          
{'loss': 2.7963, 'learning_rate': 1.808440295604823e-07, 'epoch': 3.11}

 19%|█▉        | 12020/61904 [6:13:47<19:10:30,  1.38s/it]
 19%|█▉        | 12021/61904 [6:13:48<19:16:04,  1.39s/it]
 19%|█▉        | 12022/61904 [6:13:49<19:32:14,  1.41s/it]
 19%|█▉        | 12023/61904 [6:13:51<19:43:47,  1.42s/it]
 19%|█▉        | 12024/61904 [6:13:52<19:38:02,  1.42s/it]
 19%|█▉        | 12025/61904 [6:13:54<19:15:00,  1.39s/it]
 19%|█▉        | 12026/61904 [6:13:55<18:44:26,  1.35s/it]
 19%|█▉        | 12027/61904 [6:13:56<18:55:03,  1.37s/it]
 19%|█▉        | 12028/61904 [6:13:58<19:02:49,  1.37s/it]
 19%|█▉        | 12029/61904 [6:13:59<18:57:31,  1.37s/it]
 19%|█▉        | 12030/61904 [6:14:00<18:23:19,  1.33s/it]
 19%|█▉        | 12031/61904 [6:14:02<18:17:07,  1.32s/it]
 19%|█▉        | 12032/61904 [6:14:03<18:18:44,  1.32s/it]
 19%|█▉        | 12033/61904 [6:14:04<18:20:52,  1.32s/it]
 19%|█▉        | 12034/61904 [6:14:06<18:50:40,  1.36s/it]
 19%|█▉        | 12035/61904 [6:14:07<18:28:50,  1.33s/it]
 19%|█▉        | 12036/61904 [6:14:08<18:14:23,  1.32s/it]
 19%|█▉        | 12037/61904 [6:14:09<17:50:18,  1.29s/it]
 19%|█▉        | 12038/61904 [6:14:11<17:49:33,  1.29s/it]
 19%|█▉        | 12039/61904 [6:14:12<17:56:23,  1.30s/it]
 19%|█▉        | 12040/61904 [6:14:13<17:56:08,  1.29s/it]
                                                          
{'loss': 2.7938, 'learning_rate': 1.8081161675093997e-07, 'epoch': 3.11}

 19%|█▉        | 12040/61904 [6:14:13<17:56:08,  1.29s/it]
 19%|█▉        | 12041/61904 [6:14:15<18:25:32,  1.33s/it]
 19%|█▉        | 12042/61904 [6:14:16<18:44:55,  1.35s/it]
 19%|█▉        | 12043/61904 [6:14:18<18:55:11,  1.37s/it]
 19%|█▉        | 12044/61904 [6:14:19<18:34:15,  1.34s/it]
 19%|█▉        | 12045/61904 [6:14:20<18:20:00,  1.32s/it]
 19%|█▉        | 12046/61904 [6:14:21<18:19:02,  1.32s/it]
 19%|█▉        | 12047/61904 [6:14:23<18:12:07,  1.31s/it]
 19%|█▉        | 12048/61904 [6:14:24<18:11:09,  1.31s/it]
 19%|█▉        | 12049/61904 [6:14:25<17:51:36,  1.29s/it]
 19%|█▉        | 12050/61904 [6:14:27<17:45:11,  1.28s/it]
 19%|█▉        | 12051/61904 [6:14:28<18:16:31,  1.32s/it]
 19%|█▉        | 12052/61904 [6:14:29<19:13:06,  1.39s/it]
 19%|█▉        | 12053/61904 [6:14:31<18:58:46,  1.37s/it]
 19%|█▉        | 12054/61904 [6:14:32<18:59:01,  1.37s/it]
 19%|█▉        | 12055/61904 [6:14:33<18:45:45,  1.36s/it]
 19%|█▉        | 12056/61904 [6:14:35<18:20:15,  1.32s/it]
 19%|█▉        | 12057/61904 [6:14:36<18:30:34,  1.34s/it]
 19%|█▉        | 12058/61904 [6:14:38<19:16:56,  1.39s/it]
 19%|█▉        | 12059/61904 [6:14:39<18:53:35,  1.36s/it]
 19%|█▉        | 12060/61904 [6:14:40<18:34:46,  1.34s/it]
                                                          
{'loss': 2.7748, 'learning_rate': 1.8077920394139763e-07, 'epoch': 3.12}

 19%|█▉        | 12060/61904 [6:14:40<18:34:46,  1.34s/it]
 19%|█▉        | 12061/61904 [6:14:42<18:40:14,  1.35s/it]
 19%|█▉        | 12062/61904 [6:14:43<18:36:55,  1.34s/it]
 19%|█▉        | 12063/61904 [6:14:44<19:27:57,  1.41s/it]
 19%|█▉        | 12064/61904 [6:14:46<19:12:25,  1.39s/it]
 19%|█▉        | 12065/61904 [6:14:47<18:48:41,  1.36s/it]
 19%|█▉        | 12066/61904 [6:14:49<19:11:54,  1.39s/it]
 19%|█▉        | 12067/61904 [6:14:50<18:26:10,  1.33s/it]
 19%|█▉        | 12068/61904 [6:14:51<18:59:48,  1.37s/it]
 19%|█▉        | 12069/61904 [6:14:53<18:57:02,  1.37s/it]
 19%|█▉        | 12070/61904 [6:14:54<19:09:35,  1.38s/it]
 19%|█▉        | 12071/61904 [6:14:55<18:41:55,  1.35s/it]
 20%|█▉        | 12072/61904 [6:14:57<18:38:29,  1.35s/it]
 20%|█▉        | 12073/61904 [6:14:58<18:06:27,  1.31s/it]
 20%|█▉        | 12074/61904 [6:14:59<17:52:38,  1.29s/it]
 20%|█▉        | 12075/61904 [6:15:00<18:12:54,  1.32s/it]
 20%|█▉        | 12076/61904 [6:15:02<18:27:55,  1.33s/it]
 20%|█▉        | 12077/61904 [6:15:03<18:49:34,  1.36s/it]
 20%|█▉        | 12078/61904 [6:15:05<18:38:01,  1.35s/it]
 20%|█▉        | 12079/61904 [6:15:06<18:16:58,  1.32s/it]
 20%|█▉        | 12080/61904 [6:15:07<18:03:13,  1.30s/it]
                                                          
{'loss': 2.7813, 'learning_rate': 1.8074679113185532e-07, 'epoch': 3.12}

 20%|█▉        | 12080/61904 [6:15:07<18:03:13,  1.30s/it]
 20%|█▉        | 12081/61904 [6:15:08<18:04:02,  1.31s/it]
 20%|█▉        | 12082/61904 [6:15:10<18:01:26,  1.30s/it]
 20%|█▉        | 12083/61904 [6:15:11<17:59:52,  1.30s/it]
 20%|█▉        | 12084/61904 [6:15:12<18:18:06,  1.32s/it]
 20%|█▉        | 12085/61904 [6:15:14<18:33:46,  1.34s/it]
 20%|█▉        | 12086/61904 [6:15:15<19:17:13,  1.39s/it]
 20%|█▉        | 12087/61904 [6:15:17<19:04:17,  1.38s/it]
 20%|█▉        | 12088/61904 [6:15:18<19:09:27,  1.38s/it]
 20%|█▉        | 12089/61904 [6:15:19<18:57:33,  1.37s/it]
 20%|█▉        | 12090/61904 [6:15:21<19:17:07,  1.39s/it]
 20%|█▉        | 12091/61904 [6:15:22<19:32:16,  1.41s/it]
 20%|█▉        | 12092/61904 [6:15:24<19:21:09,  1.40s/it]
 20%|█▉        | 12093/61904 [6:15:25<19:42:45,  1.42s/it]
 20%|█▉        | 12094/61904 [6:15:26<19:02:09,  1.38s/it]
 20%|█▉        | 12095/61904 [6:15:28<19:34:44,  1.42s/it]
 20%|█▉        | 12096/61904 [6:15:29<19:22:13,  1.40s/it]
 20%|█▉        | 12097/61904 [6:15:31<19:06:00,  1.38s/it]
 20%|█▉        | 12098/61904 [6:15:32<19:07:08,  1.38s/it]
 20%|█▉        | 12099/61904 [6:15:33<19:27:14,  1.41s/it]
 20%|█▉        | 12100/61904 [6:15:35<19:15:40,  1.39s/it]
                                                          
{'loss': 2.8148, 'learning_rate': 1.8071437832231296e-07, 'epoch': 3.13}

 20%|█▉        | 12100/61904 [6:15:35<19:15:40,  1.39s/it]
 20%|█▉        | 12101/61904 [6:15:36<19:16:33,  1.39s/it]
 20%|█▉        | 12102/61904 [6:15:37<18:46:30,  1.36s/it]
 20%|█▉        | 12103/61904 [6:15:39<19:01:23,  1.38s/it]
 20%|█▉        | 12104/61904 [6:15:40<18:46:28,  1.36s/it]
 20%|█▉        | 12105/61904 [6:15:42<19:44:00,  1.43s/it]
 20%|█▉        | 12106/61904 [6:15:43<19:07:40,  1.38s/it]
 20%|█▉        | 12107/61904 [6:15:44<18:55:07,  1.37s/it]
 20%|█▉        | 12108/61904 [6:15:46<19:31:17,  1.41s/it]
 20%|█▉        | 12109/61904 [6:15:47<18:56:00,  1.37s/it]
 20%|█▉        | 12110/61904 [6:15:48<18:25:52,  1.33s/it]
 20%|█▉        | 12111/61904 [6:15:50<18:20:15,  1.33s/it]
 20%|█▉        | 12112/61904 [6:15:51<18:37:42,  1.35s/it]
 20%|█▉        | 12113/61904 [6:15:52<18:23:18,  1.33s/it]
 20%|█▉        | 12114/61904 [6:15:54<18:24:03,  1.33s/it]
 20%|█▉        | 12115/61904 [6:15:55<18:17:32,  1.32s/it]
 20%|█▉        | 12116/61904 [6:15:56<18:39:57,  1.35s/it]
 20%|█▉        | 12117/61904 [6:15:58<19:25:56,  1.41s/it]
 20%|█▉        | 12118/61904 [6:15:59<19:12:52,  1.39s/it]
 20%|█▉        | 12119/61904 [6:16:01<18:50:30,  1.36s/it]
 20%|█▉        | 12120/61904 [6:16:02<18:22:48,  1.33s/it]
                                                          
{'loss': 2.7859, 'learning_rate': 1.8068196551277065e-07, 'epoch': 3.13}

 20%|█▉        | 12120/61904 [6:16:02<18:22:48,  1.33s/it]
 20%|█▉        | 12121/61904 [6:16:03<18:58:29,  1.37s/it]
 20%|█▉        | 12122/61904 [6:16:05<19:26:22,  1.41s/it]
 20%|█▉        | 12123/61904 [6:16:06<18:58:12,  1.37s/it]
 20%|█▉        | 12124/61904 [6:16:08<19:04:17,  1.38s/it]
 20%|█▉        | 12125/61904 [6:16:09<19:06:55,  1.38s/it]
 20%|█▉        | 12126/61904 [6:16:10<19:14:17,  1.39s/it]
 20%|█▉        | 12127/61904 [6:16:12<19:02:19,  1.38s/it]
 20%|█▉        | 12128/61904 [6:16:13<19:37:10,  1.42s/it]
 20%|█▉        | 12129/61904 [6:16:15<19:58:02,  1.44s/it]
 20%|█▉        | 12130/61904 [6:16:16<19:44:39,  1.43s/it]
 20%|█▉        | 12131/61904 [6:16:17<19:10:19,  1.39s/it]
 20%|█▉        | 12132/61904 [6:16:19<19:04:31,  1.38s/it]
 20%|█▉        | 12133/61904 [6:16:20<19:12:05,  1.39s/it]
 20%|█▉        | 12134/61904 [6:16:21<18:45:27,  1.36s/it]
 20%|█▉        | 12135/61904 [6:16:23<19:24:05,  1.40s/it]
 20%|█▉        | 12136/61904 [6:16:24<19:14:42,  1.39s/it]
 20%|█▉        | 12137/61904 [6:16:26<18:57:38,  1.37s/it]
 20%|█▉        | 12138/61904 [6:16:27<19:39:38,  1.42s/it]
 20%|█▉        | 12139/61904 [6:16:29<19:17:51,  1.40s/it]
 20%|█▉        | 12140/61904 [6:16:30<18:50:49,  1.36s/it]
                                                          
{'loss': 2.7769, 'learning_rate': 1.806495527032283e-07, 'epoch': 3.14}

 20%|█▉        | 12140/61904 [6:16:30<18:50:49,  1.36s/it]
 20%|█▉        | 12141/61904 [6:16:31<19:02:29,  1.38s/it]
 20%|█▉        | 12142/61904 [6:16:32<18:22:46,  1.33s/it]
 20%|█▉        | 12143/61904 [6:16:34<18:26:06,  1.33s/it]
 20%|█▉        | 12144/61904 [6:16:35<18:19:41,  1.33s/it]
 20%|█▉        | 12145/61904 [6:16:36<18:32:10,  1.34s/it]
 20%|█▉        | 12146/61904 [6:16:38<18:30:38,  1.34s/it]
 20%|█▉        | 12147/61904 [6:16:39<18:16:31,  1.32s/it]
 20%|█▉        | 12148/61904 [6:16:40<18:15:23,  1.32s/it]
 20%|█▉        | 12149/61904 [6:16:42<18:18:14,  1.32s/it]
 20%|█▉        | 12150/61904 [6:16:43<18:56:48,  1.37s/it]
 20%|█▉        | 12151/61904 [6:16:45<19:18:23,  1.40s/it]
 20%|█▉        | 12152/61904 [6:16:46<19:05:54,  1.38s/it]
 20%|█▉        | 12153/61904 [6:16:47<18:30:54,  1.34s/it]
 20%|█▉        | 12154/61904 [6:16:49<18:59:14,  1.37s/it]
 20%|█▉        | 12155/61904 [6:16:50<19:00:55,  1.38s/it]
 20%|█▉        | 12156/61904 [6:16:51<18:38:37,  1.35s/it]
 20%|█▉        | 12157/61904 [6:16:53<18:23:22,  1.33s/it]
 20%|█▉        | 12158/61904 [6:16:54<18:34:06,  1.34s/it]
 20%|█▉        | 12159/61904 [6:16:56<19:14:12,  1.39s/it]
 20%|█▉        | 12160/61904 [6:16:57<19:14:27,  1.39s/it]
                                                          
{'loss': 2.8138, 'learning_rate': 1.8061713989368597e-07, 'epoch': 3.14}

 20%|█▉        | 12160/61904 [6:16:57<19:14:27,  1.39s/it]
 20%|█▉        | 12161/61904 [6:16:58<19:52:47,  1.44s/it]
 20%|█▉        | 12162/61904 [6:17:00<20:01:43,  1.45s/it]
 20%|█▉        | 12163/61904 [6:17:01<19:27:02,  1.41s/it]
 20%|█▉        | 12164/61904 [6:17:03<19:02:19,  1.38s/it]
 20%|█▉        | 12165/61904 [6:17:04<18:33:55,  1.34s/it]
 20%|█▉        | 12166/61904 [6:17:05<18:27:01,  1.34s/it]
 20%|█▉        | 12167/61904 [6:17:07<18:45:25,  1.36s/it]
 20%|█▉        | 12168/61904 [6:17:08<18:58:28,  1.37s/it]
 20%|█▉        | 12169/61904 [6:17:09<19:14:48,  1.39s/it]
 20%|█▉        | 12170/61904 [6:17:11<18:41:14,  1.35s/it]
 20%|█▉        | 12171/61904 [6:17:12<19:19:14,  1.40s/it]
 20%|█▉        | 12172/61904 [6:17:13<18:59:02,  1.37s/it]
 20%|█▉        | 12173/61904 [6:17:15<18:53:18,  1.37s/it]
 20%|█▉        | 12174/61904 [6:17:16<19:04:33,  1.38s/it]
 20%|█▉        | 12175/61904 [6:17:18<19:28:17,  1.41s/it]
 20%|█▉        | 12176/61904 [6:17:19<19:11:32,  1.39s/it]
 20%|█▉        | 12177/61904 [6:17:21<19:40:09,  1.42s/it]
 20%|█▉        | 12178/61904 [6:17:22<18:56:57,  1.37s/it]
 20%|█▉        | 12179/61904 [6:17:23<19:08:36,  1.39s/it]
 20%|█▉        | 12180/61904 [6:17:25<19:18:25,  1.40s/it]
                                                          
{'loss': 2.8262, 'learning_rate': 1.8058472708414366e-07, 'epoch': 3.15}

 20%|█▉        | 12180/61904 [6:17:25<19:18:25,  1.40s/it]
 20%|█▉        | 12181/61904 [6:17:26<19:22:56,  1.40s/it]
 20%|█▉        | 12182/61904 [6:17:27<18:53:05,  1.37s/it]
 20%|█▉        | 12183/61904 [6:17:29<18:40:48,  1.35s/it]
 20%|█▉        | 12184/61904 [6:17:30<18:24:12,  1.33s/it]
 20%|█▉        | 12185/61904 [6:17:31<18:09:29,  1.31s/it]
 20%|█▉        | 12186/61904 [6:17:33<18:45:52,  1.36s/it]
 20%|█▉        | 12187/61904 [6:17:34<19:20:01,  1.40s/it]
 20%|█▉        | 12188/61904 [6:17:36<19:04:01,  1.38s/it]
 20%|█▉        | 12189/61904 [6:17:37<19:01:10,  1.38s/it]
 20%|█▉        | 12190/61904 [6:17:38<19:03:07,  1.38s/it]
 20%|█▉        | 12191/61904 [6:17:40<18:59:57,  1.38s/it]
 20%|█▉        | 12192/61904 [6:17:41<18:44:10,  1.36s/it]
 20%|█▉        | 12193/61904 [6:17:42<19:16:39,  1.40s/it]
 20%|█▉        | 12194/61904 [6:17:44<19:17:18,  1.40s/it]
 20%|█▉        | 12195/61904 [6:17:45<18:56:46,  1.37s/it]
 20%|█▉        | 12196/61904 [6:17:47<19:03:15,  1.38s/it]
 20%|█▉        | 12197/61904 [6:17:48<19:16:39,  1.40s/it]
 20%|█▉        | 12198/61904 [6:17:49<18:48:37,  1.36s/it]
 20%|█▉        | 12199/61904 [6:17:51<18:41:52,  1.35s/it]
 20%|█▉        | 12200/61904 [6:17:52<19:03:06,  1.38s/it]
                                                          
{'loss': 2.7442, 'learning_rate': 1.8055231427460132e-07, 'epoch': 3.15}

 20%|█▉        | 12200/61904 [6:17:52<19:03:06,  1.38s/it]
 20%|█▉        | 12201/61904 [6:17:54<20:34:44,  1.49s/it]
 20%|█▉        | 12202/61904 [6:17:55<19:27:02,  1.41s/it]
 20%|█▉        | 12203/61904 [6:17:56<19:25:56,  1.41s/it]
 20%|█▉        | 12204/61904 [6:17:58<19:04:42,  1.38s/it]
 20%|█▉        | 12205/61904 [6:17:59<18:38:56,  1.35s/it]
 20%|█▉        | 12206/61904 [6:18:00<18:47:07,  1.36s/it]
 20%|█▉        | 12207/61904 [6:18:02<18:26:42,  1.34s/it]
 20%|█▉        | 12208/61904 [6:18:03<17:55:58,  1.30s/it]
 20%|█▉        | 12209/61904 [6:18:04<17:43:29,  1.28s/it]
 20%|█▉        | 12210/61904 [6:18:06<17:58:18,  1.30s/it]
 20%|█▉        | 12211/61904 [6:18:07<17:57:31,  1.30s/it]
 20%|█▉        | 12212/61904 [6:18:08<17:52:45,  1.30s/it]
 20%|█▉        | 12213/61904 [6:18:09<17:38:19,  1.28s/it]
 20%|█▉        | 12214/61904 [6:18:11<18:01:47,  1.31s/it]
 20%|█▉        | 12215/61904 [6:18:12<18:33:16,  1.34s/it]
 20%|█▉        | 12216/61904 [6:18:13<17:55:08,  1.30s/it]
 20%|█▉        | 12217/61904 [6:18:15<18:08:00,  1.31s/it]
 20%|█▉        | 12218/61904 [6:18:16<18:31:43,  1.34s/it]
 20%|█▉        | 12219/61904 [6:18:18<19:42:29,  1.43s/it]
 20%|█▉        | 12220/61904 [6:18:19<19:33:30,  1.42s/it]
                                                          
{'loss': 2.7795, 'learning_rate': 1.8051990146505898e-07, 'epoch': 3.16}

 20%|█▉        | 12220/61904 [6:18:19<19:33:30,  1.42s/it]
 20%|█▉        | 12221/61904 [6:18:21<19:42:10,  1.43s/it]
 20%|█▉        | 12222/61904 [6:18:22<19:03:39,  1.38s/it]
 20%|█▉        | 12223/61904 [6:18:23<19:29:35,  1.41s/it]
 20%|█▉        | 12224/61904 [6:18:25<19:16:26,  1.40s/it]
 20%|█▉        | 12225/61904 [6:18:26<19:50:28,  1.44s/it]
 20%|█▉        | 12226/61904 [6:18:28<19:16:47,  1.40s/it]
 20%|█▉        | 12227/61904 [6:18:29<18:51:22,  1.37s/it]
 20%|█▉        | 12228/61904 [6:18:30<18:48:33,  1.36s/it]
 20%|█▉        | 12229/61904 [6:18:32<19:24:52,  1.41s/it]
 20%|█▉        | 12230/61904 [6:18:33<19:27:14,  1.41s/it]
 20%|█▉        | 12231/61904 [6:18:35<20:08:23,  1.46s/it]
 20%|█▉        | 12232/61904 [6:18:36<20:17:28,  1.47s/it]
 20%|█▉        | 12233/61904 [6:18:37<19:42:04,  1.43s/it]
 20%|█▉        | 12234/61904 [6:18:39<19:18:20,  1.40s/it]
 20%|█▉        | 12235/61904 [6:18:40<19:22:09,  1.40s/it]
 20%|█▉        | 12236/61904 [6:18:42<19:41:59,  1.43s/it]
 20%|█▉        | 12237/61904 [6:18:43<19:00:59,  1.38s/it]
 20%|█▉        | 12238/61904 [6:18:44<18:44:01,  1.36s/it]
 20%|█▉        | 12239/61904 [6:18:46<19:03:17,  1.38s/it]
 20%|█▉        | 12240/61904 [6:18:47<19:29:36,  1.41s/it]
                                                          
{'loss': 2.8031, 'learning_rate': 1.8048748865551667e-07, 'epoch': 3.16}

 20%|█▉        | 12240/61904 [6:18:47<19:29:36,  1.41s/it]
 20%|█▉        | 12241/61904 [6:18:49<18:59:04,  1.38s/it]
 20%|█▉        | 12242/61904 [6:18:50<18:21:54,  1.33s/it]
 20%|█▉        | 12243/61904 [6:18:51<18:33:03,  1.34s/it]
 20%|█▉        | 12244/61904 [6:18:52<18:13:50,  1.32s/it]
 20%|█▉        | 12245/61904 [6:18:54<18:28:02,  1.34s/it]
 20%|█▉        | 12246/61904 [6:18:55<18:37:20,  1.35s/it]
 20%|█▉        | 12247/61904 [6:18:57<19:57:22,  1.45s/it]
 20%|█▉        | 12248/61904 [6:18:58<19:06:02,  1.38s/it]
 20%|█▉        | 12249/61904 [6:18:59<19:18:51,  1.40s/it]
 20%|█▉        | 12250/61904 [6:19:01<19:30:27,  1.41s/it]
 20%|█▉        | 12251/61904 [6:19:02<19:06:09,  1.39s/it]
 20%|█▉        | 12252/61904 [6:19:04<19:56:27,  1.45s/it]
 20%|█▉        | 12253/61904 [6:19:05<19:32:21,  1.42s/it]
 20%|█▉        | 12254/61904 [6:19:06<18:52:59,  1.37s/it]
 20%|█▉        | 12255/61904 [6:19:08<18:54:06,  1.37s/it]
 20%|█▉        | 12256/61904 [6:19:09<18:48:31,  1.36s/it]
 20%|█▉        | 12257/61904 [6:19:10<18:41:17,  1.36s/it]
 20%|█▉        | 12258/61904 [6:19:12<19:23:52,  1.41s/it]
 20%|█▉        | 12259/61904 [6:19:13<19:22:28,  1.40s/it]
 20%|█▉        | 12260/61904 [6:19:15<19:30:19,  1.41s/it]
                                                          
{'loss': 2.7879, 'learning_rate': 1.804550758459743e-07, 'epoch': 3.17}

 20%|█▉        | 12260/61904 [6:19:15<19:30:19,  1.41s/it]
 20%|█▉        | 12261/61904 [6:19:16<19:12:39,  1.39s/it]
 20%|█▉        | 12262/61904 [6:19:17<18:45:04,  1.36s/it]
 20%|█▉        | 12263/61904 [6:19:19<19:28:16,  1.41s/it]
 20%|█▉        | 12264/61904 [6:19:20<19:05:02,  1.38s/it]
 20%|█▉        | 12265/61904 [6:19:22<19:04:56,  1.38s/it]
 20%|█▉        | 12266/61904 [6:19:23<18:41:45,  1.36s/it]
 20%|█▉        | 12267/61904 [6:19:24<19:01:17,  1.38s/it]
 20%|█▉        | 12268/61904 [6:19:26<18:55:10,  1.37s/it]
 20%|█▉        | 12269/61904 [6:19:27<19:01:17,  1.38s/it]
 20%|█▉        | 12270/61904 [6:19:28<18:36:11,  1.35s/it]
 20%|█▉        | 12271/61904 [6:19:30<19:19:21,  1.40s/it]
 20%|█▉        | 12272/61904 [6:19:31<18:56:52,  1.37s/it]
 20%|█▉        | 12273/61904 [6:19:33<18:59:38,  1.38s/it]
 20%|█▉        | 12274/61904 [6:19:34<18:40:49,  1.36s/it]
 20%|█▉        | 12275/61904 [6:19:35<18:16:57,  1.33s/it]
 20%|█▉        | 12276/61904 [6:19:37<18:28:28,  1.34s/it]
 20%|█▉        | 12277/61904 [6:19:38<18:45:08,  1.36s/it]
 20%|█▉        | 12278/61904 [6:19:39<18:49:08,  1.37s/it]
 20%|█▉        | 12279/61904 [6:19:41<18:45:30,  1.36s/it]
 20%|█▉        | 12280/61904 [6:19:42<18:58:58,  1.38s/it]
                                                          
{'loss': 2.8254, 'learning_rate': 1.80422663036432e-07, 'epoch': 3.17}

 20%|█▉        | 12280/61904 [6:19:42<18:58:58,  1.38s/it]
 20%|█▉        | 12281/61904 [6:19:44<18:44:12,  1.36s/it]
 20%|█▉        | 12282/61904 [6:19:45<18:40:38,  1.36s/it]
 20%|█▉        | 12283/61904 [6:19:46<18:40:26,  1.35s/it]
 20%|█▉        | 12284/61904 [6:19:47<18:19:43,  1.33s/it]
 20%|█▉        | 12285/61904 [6:19:49<18:18:25,  1.33s/it]
 20%|█▉        | 12286/61904 [6:19:50<18:10:10,  1.32s/it]
 20%|█▉        | 12287/61904 [6:19:51<18:12:57,  1.32s/it]
 20%|█▉        | 12288/61904 [6:19:53<19:05:09,  1.38s/it]
 20%|█▉        | 12289/61904 [6:19:54<18:19:03,  1.33s/it]
 20%|█▉        | 12290/61904 [6:19:56<18:55:37,  1.37s/it]
 20%|█▉        | 12291/61904 [6:19:57<19:03:48,  1.38s/it]
 20%|█▉        | 12292/61904 [6:19:58<19:07:38,  1.39s/it]
 20%|█▉        | 12293/61904 [6:20:00<19:37:19,  1.42s/it]
 20%|█▉        | 12294/61904 [6:20:01<19:36:59,  1.42s/it]
 20%|█▉        | 12295/61904 [6:20:03<19:47:39,  1.44s/it]
 20%|█▉        | 12296/61904 [6:20:04<19:39:54,  1.43s/it]
 20%|█▉        | 12297/61904 [6:20:06<19:50:31,  1.44s/it]
 20%|█▉        | 12298/61904 [6:20:07<19:25:44,  1.41s/it]
 20%|█▉        | 12299/61904 [6:20:09<20:05:48,  1.46s/it]
 20%|█▉        | 12300/61904 [6:20:10<20:05:13,  1.46s/it]
                                                          
{'loss': 2.7154, 'learning_rate': 1.8039025022688966e-07, 'epoch': 3.18}

 20%|█▉        | 12300/61904 [6:20:10<20:05:13,  1.46s/it]
 20%|█▉        | 12301/61904 [6:20:12<20:41:32,  1.50s/it]
 20%|█▉        | 12302/61904 [6:20:13<20:04:52,  1.46s/it]
 20%|█▉        | 12303/61904 [6:20:14<19:29:58,  1.42s/it]
 20%|█▉        | 12304/61904 [6:20:16<20:05:25,  1.46s/it]
 20%|█▉        | 12305/61904 [6:20:17<19:39:41,  1.43s/it]
 20%|█▉        | 12306/61904 [6:20:19<19:41:11,  1.43s/it]
 20%|█▉        | 12307/61904 [6:20:20<19:24:30,  1.41s/it]
 20%|█▉        | 12308/61904 [6:20:21<18:40:42,  1.36s/it]
 20%|█▉        | 12309/61904 [6:20:23<18:25:57,  1.34s/it]
 20%|█▉        | 12310/61904 [6:20:24<18:00:17,  1.31s/it]
 20%|█▉        | 12311/61904 [6:20:25<18:01:09,  1.31s/it]
 20%|█▉        | 12312/61904 [6:20:26<18:03:49,  1.31s/it]
 20%|█▉        | 12313/61904 [6:20:28<18:10:39,  1.32s/it]
 20%|█▉        | 12314/61904 [6:20:29<19:24:53,  1.41s/it]
 20%|█▉        | 12315/61904 [6:20:31<19:38:23,  1.43s/it]
 20%|█▉        | 12316/61904 [6:20:32<18:57:48,  1.38s/it]
 20%|█▉        | 12317/61904 [6:20:34<19:40:29,  1.43s/it]
 20%|█▉        | 12318/61904 [6:20:35<19:35:16,  1.42s/it]
 20%|█▉        | 12319/61904 [6:20:36<18:58:10,  1.38s/it]
 20%|█▉        | 12320/61904 [6:20:38<19:03:05,  1.38s/it]
                                                          
{'loss': 2.8229, 'learning_rate': 1.8035783741734732e-07, 'epoch': 3.18}

 20%|█▉        | 12320/61904 [6:20:38<19:03:05,  1.38s/it]
 20%|█▉        | 12321/61904 [6:20:39<18:38:23,  1.35s/it]
 20%|█▉        | 12322/61904 [6:20:40<18:27:47,  1.34s/it]
 20%|█▉        | 12323/61904 [6:20:42<19:07:29,  1.39s/it]
 20%|█▉        | 12324/61904 [6:20:43<19:14:18,  1.40s/it]
 20%|█▉        | 12325/61904 [6:20:45<19:01:07,  1.38s/it]
 20%|█▉        | 12326/61904 [6:20:46<18:39:14,  1.35s/it]
 20%|█▉        | 12327/61904 [6:20:47<18:32:53,  1.35s/it]
 20%|█▉        | 12328/61904 [6:20:49<18:26:26,  1.34s/it]
 20%|█▉        | 12329/61904 [6:20:50<18:28:35,  1.34s/it]
 20%|█▉        | 12330/61904 [6:20:51<18:24:59,  1.34s/it]
 20%|█▉        | 12331/61904 [6:20:53<18:23:51,  1.34s/it]
 20%|█▉        | 12332/61904 [6:20:54<18:50:51,  1.37s/it]
 20%|█▉        | 12333/61904 [6:20:55<19:11:15,  1.39s/it]
 20%|█▉        | 12334/61904 [6:20:57<19:20:14,  1.40s/it]
 20%|█▉        | 12335/61904 [6:20:58<19:46:00,  1.44s/it]
 20%|█▉        | 12336/61904 [6:21:00<19:25:21,  1.41s/it]
 20%|█▉        | 12337/61904 [6:21:01<19:22:40,  1.41s/it]
 20%|█▉        | 12338/61904 [6:21:02<19:06:08,  1.39s/it]
 20%|█▉        | 12339/61904 [6:21:04<18:36:44,  1.35s/it]
 20%|█▉        | 12340/61904 [6:21:05<18:26:44,  1.34s/it]
                                                          
{'loss': 2.7942, 'learning_rate': 1.80325424607805e-07, 'epoch': 3.19}

 20%|█▉        | 12340/61904 [6:21:05<18:26:44,  1.34s/it]
 20%|█▉        | 12341/61904 [6:21:06<18:39:58,  1.36s/it]
 20%|█▉        | 12342/61904 [6:21:08<19:03:13,  1.38s/it]
 20%|█▉        | 12343/61904 [6:21:09<18:53:50,  1.37s/it]
 20%|█▉        | 12344/61904 [6:21:11<18:20:39,  1.33s/it]
 20%|█▉        | 12345/61904 [6:21:12<17:58:49,  1.31s/it]
 20%|█▉        | 12346/61904 [6:21:13<18:29:32,  1.34s/it]
 20%|█▉        | 12347/61904 [6:21:15<18:32:13,  1.35s/it]
 20%|█▉        | 12348/61904 [6:21:16<18:27:24,  1.34s/it]
 20%|█▉        | 12349/61904 [6:21:17<18:34:15,  1.35s/it]
 20%|█▉        | 12350/61904 [6:21:19<19:25:13,  1.41s/it]
 20%|█▉        | 12351/61904 [6:21:20<18:57:43,  1.38s/it]
 20%|█▉        | 12352/61904 [6:21:21<18:39:34,  1.36s/it]
 20%|█▉        | 12353/61904 [6:21:23<18:43:53,  1.36s/it]
 20%|█▉        | 12354/61904 [6:21:24<19:05:09,  1.39s/it]
 20%|█▉        | 12355/61904 [6:21:25<18:41:19,  1.36s/it]
 20%|█▉        | 12356/61904 [6:21:27<18:50:47,  1.37s/it]
 20%|█▉        | 12357/61904 [6:21:28<18:44:28,  1.36s/it]
 20%|█▉        | 12358/61904 [6:21:29<18:10:05,  1.32s/it]
 20%|█▉        | 12359/61904 [6:21:31<18:06:59,  1.32s/it]
 20%|█▉        | 12360/61904 [6:21:32<18:18:00,  1.33s/it]
                                                          
{'loss': 2.7733, 'learning_rate': 1.8029301179826267e-07, 'epoch': 3.19}

 20%|█▉        | 12360/61904 [6:21:32<18:18:00,  1.33s/it]
 20%|█▉        | 12361/61904 [6:21:33<18:24:39,  1.34s/it]
 20%|█▉        | 12362/61904 [6:21:35<19:15:40,  1.40s/it]
 20%|█▉        | 12363/61904 [6:21:37<20:11:04,  1.47s/it]
 20%|█▉        | 12364/61904 [6:21:38<19:23:58,  1.41s/it]
 20%|█▉        | 12365/61904 [6:21:39<18:29:06,  1.34s/it]
 20%|█▉        | 12366/61904 [6:21:41<18:56:58,  1.38s/it]
 20%|█▉        | 12367/61904 [6:21:42<19:38:11,  1.43s/it]
 20%|█▉        | 12368/61904 [6:21:43<19:01:17,  1.38s/it]
 20%|█▉        | 12369/61904 [6:21:45<18:47:32,  1.37s/it]
 20%|█▉        | 12370/61904 [6:21:46<19:07:41,  1.39s/it]
 20%|█▉        | 12371/61904 [6:21:48<18:59:41,  1.38s/it]
 20%|█▉        | 12372/61904 [6:21:49<18:49:50,  1.37s/it]
 20%|█▉        | 12373/61904 [6:21:50<19:29:32,  1.42s/it]
 20%|█▉        | 12374/61904 [6:21:52<18:41:52,  1.36s/it]
 20%|█▉        | 12375/61904 [6:21:53<18:42:39,  1.36s/it]
 20%|█▉        | 12376/61904 [6:21:55<19:26:05,  1.41s/it]
 20%|█▉        | 12377/61904 [6:21:56<19:37:09,  1.43s/it]
 20%|█▉        | 12378/61904 [6:21:57<19:10:36,  1.39s/it]
 20%|█▉        | 12379/61904 [6:21:59<18:53:08,  1.37s/it]
 20%|█▉        | 12380/61904 [6:22:00<18:20:13,  1.33s/it]
                                                          
{'loss': 2.775, 'learning_rate': 1.8026059898872033e-07, 'epoch': 3.2}

 20%|█▉        | 12380/61904 [6:22:00<18:20:13,  1.33s/it]
 20%|██        | 12381/61904 [6:22:01<19:08:40,  1.39s/it]
 20%|██        | 12382/61904 [6:22:03<18:57:56,  1.38s/it]
 20%|██        | 12383/61904 [6:22:04<19:39:35,  1.43s/it]
 20%|██        | 12384/61904 [6:22:06<19:36:36,  1.43s/it]
 20%|██        | 12385/61904 [6:22:07<19:48:44,  1.44s/it]
 20%|██        | 12386/61904 [6:22:09<19:33:37,  1.42s/it]
 20%|██        | 12387/61904 [6:22:10<18:52:15,  1.37s/it]
 20%|██        | 12388/61904 [6:22:11<19:06:02,  1.39s/it]
 20%|██        | 12389/61904 [6:22:13<20:12:05,  1.47s/it]
 20%|██        | 12390/61904 [6:22:14<19:19:14,  1.40s/it]
 20%|██        | 12391/61904 [6:22:15<19:00:50,  1.38s/it]
 20%|██        | 12392/61904 [6:22:17<18:48:00,  1.37s/it]
 20%|██        | 12393/61904 [6:22:18<19:10:06,  1.39s/it]
 20%|██        | 12394/61904 [6:22:20<18:31:10,  1.35s/it]
 20%|██        | 12395/61904 [6:22:21<18:12:04,  1.32s/it]
 20%|██        | 12396/61904 [6:22:22<18:10:21,  1.32s/it]
 20%|██        | 12397/61904 [6:22:23<18:11:26,  1.32s/it]
 20%|██        | 12398/61904 [6:22:25<18:09:20,  1.32s/it]
 20%|██        | 12399/61904 [6:22:26<19:03:46,  1.39s/it]
 20%|██        | 12400/61904 [6:22:28<19:12:05,  1.40s/it]
                                                          
{'loss': 2.7004, 'learning_rate': 1.8022818617917802e-07, 'epoch': 3.2}

 20%|██        | 12400/61904 [6:22:28<19:12:05,  1.40s/it]
 20%|██        | 12401/61904 [6:22:29<19:04:14,  1.39s/it]
 20%|██        | 12402/61904 [6:22:30<18:42:45,  1.36s/it]
 20%|██        | 12403/61904 [6:22:32<18:51:04,  1.37s/it]
 20%|██        | 12404/61904 [6:22:33<18:20:43,  1.33s/it]
 20%|██        | 12405/61904 [6:22:34<18:37:58,  1.36s/it]
 20%|██        | 12406/61904 [6:22:36<18:39:47,  1.36s/it]
 20%|██        | 12407/61904 [6:22:37<18:50:04,  1.37s/it]
 20%|██        | 12408/61904 [6:22:39<19:30:22,  1.42s/it]
 20%|██        | 12409/61904 [6:22:40<18:41:13,  1.36s/it]
 20%|██        | 12410/61904 [6:22:41<18:37:20,  1.35s/it]
 20%|██        | 12411/61904 [6:22:43<18:30:36,  1.35s/it]
 20%|██        | 12412/61904 [6:22:44<18:16:14,  1.33s/it]
 20%|██        | 12413/61904 [6:22:45<18:31:29,  1.35s/it]
 20%|██        | 12414/61904 [6:22:47<18:43:17,  1.36s/it]
 20%|██        | 12415/61904 [6:22:48<18:32:22,  1.35s/it]
 20%|██        | 12416/61904 [6:22:49<18:44:26,  1.36s/it]
 20%|██        | 12417/61904 [6:22:51<18:43:32,  1.36s/it]
 20%|██        | 12418/61904 [6:22:52<18:32:54,  1.35s/it]
 20%|██        | 12419/61904 [6:22:54<19:25:25,  1.41s/it]
 20%|██        | 12420/61904 [6:22:55<19:41:41,  1.43s/it]
                                                          
{'loss': 2.8086, 'learning_rate': 1.8019577336963565e-07, 'epoch': 3.21}

 20%|██        | 12420/61904 [6:22:55<19:41:41,  1.43s/it]
 20%|██        | 12421/61904 [6:22:56<19:11:01,  1.40s/it]
 20%|██        | 12422/61904 [6:22:58<19:03:16,  1.39s/it]
 20%|██        | 12423/61904 [6:22:59<19:25:31,  1.41s/it]
 20%|██        | 12424/61904 [6:23:01<19:11:25,  1.40s/it]
 20%|██        | 12425/61904 [6:23:02<19:02:57,  1.39s/it]
 20%|██        | 12426/61904 [6:23:03<18:41:52,  1.36s/it]
 20%|██        | 12427/61904 [6:23:04<17:59:38,  1.31s/it]
 20%|██        | 12428/61904 [6:23:06<18:48:10,  1.37s/it]
 20%|██        | 12429/61904 [6:23:07<18:10:58,  1.32s/it]
 20%|██        | 12430/61904 [6:23:09<18:38:47,  1.36s/it]
 20%|██        | 12431/61904 [6:23:10<18:17:19,  1.33s/it]
 20%|██        | 12432/61904 [6:23:12<19:35:17,  1.43s/it]
 20%|██        | 12433/61904 [6:23:13<20:03:15,  1.46s/it]
 20%|██        | 12434/61904 [6:23:14<19:53:34,  1.45s/it]
 20%|██        | 12435/61904 [6:23:16<19:36:19,  1.43s/it]
 20%|██        | 12436/61904 [6:23:17<19:20:10,  1.41s/it]
 20%|██        | 12437/61904 [6:23:19<19:00:59,  1.38s/it]
 20%|██        | 12438/61904 [6:23:20<18:38:36,  1.36s/it]
 20%|██        | 12439/61904 [6:23:21<18:17:50,  1.33s/it]
 20%|██        | 12440/61904 [6:23:23<18:47:18,  1.37s/it]
                                                          
{'loss': 2.7877, 'learning_rate': 1.8016336056009334e-07, 'epoch': 3.21}

 20%|██        | 12440/61904 [6:23:23<18:47:18,  1.37s/it]
 20%|██        | 12441/61904 [6:23:24<19:10:44,  1.40s/it]
 20%|██        | 12442/61904 [6:23:25<18:58:41,  1.38s/it]
 20%|██        | 12443/61904 [6:23:27<18:45:39,  1.37s/it]
 20%|██        | 12444/61904 [6:23:28<18:26:48,  1.34s/it]
 20%|██        | 12445/61904 [6:23:29<18:26:45,  1.34s/it]
 20%|██        | 12446/61904 [6:23:31<18:56:17,  1.38s/it]
 20%|██        | 12447/61904 [6:23:32<18:57:14,  1.38s/it]
 20%|██        | 12448/61904 [6:23:34<19:04:18,  1.39s/it]
 20%|██        | 12449/61904 [6:23:35<19:03:15,  1.39s/it]
 20%|██        | 12450/61904 [6:23:36<19:25:14,  1.41s/it]
 20%|██        | 12451/61904 [6:23:38<18:44:20,  1.36s/it]
 20%|██        | 12452/61904 [6:23:39<19:05:33,  1.39s/it]
 20%|██        | 12453/61904 [6:23:40<18:26:57,  1.34s/it]
 20%|██        | 12454/61904 [6:23:42<18:39:43,  1.36s/it]
 20%|██        | 12455/61904 [6:23:43<19:39:37,  1.43s/it]
 20%|██        | 12456/61904 [6:23:45<19:19:31,  1.41s/it]
 20%|██        | 12457/61904 [6:23:46<19:55:57,  1.45s/it]
 20%|██        | 12458/61904 [6:23:48<19:07:11,  1.39s/it]
 20%|██        | 12459/61904 [6:23:49<18:38:47,  1.36s/it]
 20%|██        | 12460/61904 [6:23:50<18:36:52,  1.36s/it]
                                                          
{'loss': 2.8041, 'learning_rate': 1.80130947750551e-07, 'epoch': 3.22}

 20%|██        | 12460/61904 [6:23:50<18:36:52,  1.36s/it]
 20%|██        | 12461/61904 [6:23:51<18:02:02,  1.31s/it]
 20%|██        | 12462/61904 [6:23:53<17:45:59,  1.29s/it]
 20%|██        | 12463/61904 [6:23:54<17:53:42,  1.30s/it]
 20%|██        | 12464/61904 [6:23:55<17:52:42,  1.30s/it]
 20%|██        | 12465/61904 [6:23:57<17:49:39,  1.30s/it]
 20%|██        | 12466/61904 [6:23:58<18:00:59,  1.31s/it]
 20%|██        | 12467/61904 [6:23:59<18:09:40,  1.32s/it]
 20%|██        | 12468/61904 [6:24:01<18:22:27,  1.34s/it]
 20%|██        | 12469/61904 [6:24:02<17:47:36,  1.30s/it]
 20%|██        | 12470/61904 [6:24:03<17:31:02,  1.28s/it]
 20%|██        | 12471/61904 [6:24:04<18:14:32,  1.33s/it]
 20%|██        | 12472/61904 [6:24:06<18:32:42,  1.35s/it]
 20%|██        | 12473/61904 [6:24:07<18:32:39,  1.35s/it]
 20%|██        | 12474/61904 [6:24:09<18:51:08,  1.37s/it]
 20%|██        | 12475/61904 [6:24:10<19:01:21,  1.39s/it]
 20%|██        | 12476/61904 [6:24:11<18:41:46,  1.36s/it]
 20%|██        | 12477/61904 [6:24:13<19:05:28,  1.39s/it]
 20%|██        | 12478/61904 [6:24:14<18:56:06,  1.38s/it]
 20%|██        | 12479/61904 [6:24:16<18:47:46,  1.37s/it]
 20%|██        | 12480/61904 [6:24:17<18:34:08,  1.35s/it]
                                                          
{'loss': 2.8454, 'learning_rate': 1.8009853494100867e-07, 'epoch': 3.23}

 20%|██        | 12480/61904 [6:24:17<18:34:08,  1.35s/it]
 20%|██        | 12481/61904 [6:24:18<18:59:39,  1.38s/it]
 20%|██        | 12482/61904 [6:24:20<18:43:42,  1.36s/it]
 20%|██        | 12483/61904 [6:24:21<18:32:56,  1.35s/it]
 20%|██        | 12484/61904 [6:24:22<19:18:49,  1.41s/it]
 20%|██        | 12485/61904 [6:24:24<19:36:11,  1.43s/it]
 20%|██        | 12486/61904 [6:24:25<19:01:02,  1.39s/it]
 20%|██        | 12487/61904 [6:24:27<18:59:09,  1.38s/it]
 20%|██        | 12488/61904 [6:24:28<19:00:02,  1.38s/it]
 20%|██        | 12489/61904 [6:24:29<18:59:31,  1.38s/it]
 20%|██        | 12490/61904 [6:24:31<18:43:13,  1.36s/it]
 20%|██        | 12491/61904 [6:24:32<18:07:57,  1.32s/it]
 20%|██        | 12492/61904 [6:24:33<18:24:42,  1.34s/it]
 20%|██        | 12493/61904 [6:24:35<18:30:12,  1.35s/it]
 20%|██        | 12494/61904 [6:24:36<18:50:15,  1.37s/it]
 20%|██        | 12495/61904 [6:24:38<19:15:09,  1.40s/it]
 20%|██        | 12496/61904 [6:24:39<19:14:33,  1.40s/it]
 20%|██        | 12497/61904 [6:24:40<18:48:06,  1.37s/it]
 20%|██        | 12498/61904 [6:24:42<18:35:36,  1.35s/it]
 20%|██        | 12499/61904 [6:24:43<18:38:21,  1.36s/it]
 20%|██        | 12500/61904 [6:24:44<18:20:50,  1.34s/it]
                                                          
{'loss': 2.8097, 'learning_rate': 1.8006612213146635e-07, 'epoch': 3.23}

 20%|██        | 12500/61904 [6:24:44<18:20:50,  1.34s/it]
 20%|██        | 12501/61904 [6:24:46<18:58:58,  1.38s/it]
 20%|██        | 12502/61904 [6:24:47<19:04:54,  1.39s/it]
 20%|██        | 12503/61904 [6:24:49<18:55:28,  1.38s/it]
 20%|██        | 12504/61904 [6:24:50<18:55:17,  1.38s/it]
 20%|██        | 12505/61904 [6:24:51<18:26:34,  1.34s/it]
 20%|██        | 12506/61904 [6:24:53<18:33:59,  1.35s/it]
 20%|██        | 12507/61904 [6:24:54<19:13:46,  1.40s/it]
 20%|██        | 12508/61904 [6:24:55<18:56:30,  1.38s/it]
 20%|██        | 12509/61904 [6:24:57<18:45:55,  1.37s/it]
 20%|██        | 12510/61904 [6:24:58<18:31:12,  1.35s/it]
 20%|██        | 12511/61904 [6:24:59<18:21:43,  1.34s/it]
 20%|██        | 12512/61904 [6:25:01<18:40:28,  1.36s/it]
 20%|██        | 12513/61904 [6:25:02<18:50:41,  1.37s/it]
 20%|██        | 12514/61904 [6:25:03<18:18:57,  1.34s/it]
 20%|██        | 12515/61904 [6:25:05<18:14:34,  1.33s/it]
 20%|██        | 12516/61904 [6:25:06<18:08:36,  1.32s/it]
 20%|██        | 12517/61904 [6:25:07<18:30:02,  1.35s/it]
 20%|██        | 12518/61904 [6:25:09<18:27:53,  1.35s/it]
 20%|██        | 12519/61904 [6:25:10<18:28:00,  1.35s/it]
 20%|██        | 12520/61904 [6:25:11<18:22:32,  1.34s/it]
                                                          
{'loss': 2.8309, 'learning_rate': 1.8003370932192402e-07, 'epoch': 3.24}

 20%|██        | 12520/61904 [6:25:11<18:22:32,  1.34s/it]
 20%|██        | 12521/61904 [6:25:13<18:00:08,  1.31s/it]
 20%|██        | 12522/61904 [6:25:14<18:30:22,  1.35s/it]
 20%|██        | 12523/61904 [6:25:15<18:07:29,  1.32s/it]
 20%|██        | 12524/61904 [6:25:17<18:15:41,  1.33s/it]
 20%|██        | 12525/61904 [6:25:18<18:43:51,  1.37s/it]
 20%|██        | 12526/61904 [6:25:20<18:40:16,  1.36s/it]
 20%|██        | 12527/61904 [6:25:21<19:38:41,  1.43s/it]
 20%|██        | 12528/61904 [6:25:23<19:24:26,  1.41s/it]
 20%|██        | 12529/61904 [6:25:24<19:33:03,  1.43s/it]
 20%|██        | 12530/61904 [6:25:25<18:41:44,  1.36s/it]
 20%|██        | 12531/61904 [6:25:27<18:49:54,  1.37s/it]
 20%|██        | 12532/61904 [6:25:28<18:39:35,  1.36s/it]
 20%|██        | 12533/61904 [6:25:29<18:51:22,  1.37s/it]
 20%|██        | 12534/61904 [6:25:31<19:06:41,  1.39s/it]
 20%|██        | 12535/61904 [6:25:32<19:04:33,  1.39s/it]
 20%|██        | 12536/61904 [6:25:34<19:27:12,  1.42s/it]
 20%|██        | 12537/61904 [6:25:35<18:57:50,  1.38s/it]
 20%|██        | 12538/61904 [6:25:36<18:55:18,  1.38s/it]
 20%|██        | 12539/61904 [6:25:38<18:46:04,  1.37s/it]
 20%|██        | 12540/61904 [6:25:39<18:22:57,  1.34s/it]
                                                          
{'loss': 2.7646, 'learning_rate': 1.8000129651238168e-07, 'epoch': 3.24}

 20%|██        | 12540/61904 [6:25:39<18:22:57,  1.34s/it]
 20%|██        | 12541/61904 [6:25:40<18:22:36,  1.34s/it]
 20%|██        | 12542/61904 [6:25:42<18:16:10,  1.33s/it]
 20%|██        | 12543/61904 [6:25:43<18:33:04,  1.35s/it]
 20%|██        | 12544/61904 [6:25:44<18:38:47,  1.36s/it]
 20%|██        | 12545/61904 [6:25:46<19:02:46,  1.39s/it]
 20%|██        | 12546/61904 [6:25:47<19:49:34,  1.45s/it]
 20%|██        | 12547/61904 [6:25:49<19:03:12,  1.39s/it]
 20%|██        | 12548/61904 [6:25:50<19:53:31,  1.45s/it]
 20%|██        | 12549/61904 [6:25:51<19:02:14,  1.39s/it]
 20%|██        | 12550/61904 [6:25:53<18:55:29,  1.38s/it]
 20%|██        | 12551/61904 [6:25:54<18:56:54,  1.38s/it]
 20%|██        | 12552/61904 [6:25:56<18:54:15,  1.38s/it]
 20%|██        | 12553/61904 [6:25:57<18:48:14,  1.37s/it]
 20%|██        | 12554/61904 [6:25:58<19:07:48,  1.40s/it]
 20%|██        | 12555/61904 [6:26:00<19:23:03,  1.41s/it]
 20%|██        | 12556/61904 [6:26:01<18:38:34,  1.36s/it]
 20%|██        | 12557/61904 [6:26:03<19:00:34,  1.39s/it]
 20%|██        | 12558/61904 [6:26:04<18:56:13,  1.38s/it]
 20%|██        | 12559/61904 [6:26:05<19:08:10,  1.40s/it]
 20%|██        | 12560/61904 [6:26:07<19:44:18,  1.44s/it]
                                                          
{'loss': 2.7901, 'learning_rate': 1.7996888370283937e-07, 'epoch': 3.25}

 20%|██        | 12560/61904 [6:26:07<19:44:18,  1.44s/it]
 20%|██        | 12561/61904 [6:26:08<19:10:21,  1.40s/it]
 20%|██        | 12562/61904 [6:26:10<18:57:06,  1.38s/it]
 20%|██        | 12563/61904 [6:26:11<18:49:10,  1.37s/it]
 20%|██        | 12564/61904 [6:26:12<18:36:32,  1.36s/it]
 20%|██        | 12565/61904 [6:26:14<19:28:03,  1.42s/it]
 20%|██        | 12566/61904 [6:26:15<19:30:41,  1.42s/it]
 20%|██        | 12567/61904 [6:26:16<18:51:18,  1.38s/it]
 20%|██        | 12568/61904 [6:26:18<19:41:31,  1.44s/it]
 20%|██        | 12569/61904 [6:26:19<18:47:14,  1.37s/it]
 20%|██        | 12570/61904 [6:26:21<18:30:07,  1.35s/it]
 20%|██        | 12571/61904 [6:26:22<18:36:52,  1.36s/it]
 20%|██        | 12572/61904 [6:26:23<18:58:02,  1.38s/it]
 20%|██        | 12573/61904 [6:26:25<18:40:45,  1.36s/it]
 20%|██        | 12574/61904 [6:26:26<18:42:20,  1.37s/it]
 20%|██        | 12575/61904 [6:26:27<18:37:41,  1.36s/it]
 20%|██        | 12576/61904 [6:26:29<18:41:21,  1.36s/it]
 20%|██        | 12577/61904 [6:26:30<20:03:34,  1.46s/it]
 20%|██        | 12578/61904 [6:26:32<19:51:34,  1.45s/it]
 20%|██        | 12579/61904 [6:26:33<19:09:25,  1.40s/it]
 20%|██        | 12580/61904 [6:26:35<19:13:10,  1.40s/it]
                                                          
{'loss': 2.7912, 'learning_rate': 1.79936470893297e-07, 'epoch': 3.25}

 20%|██        | 12580/61904 [6:26:35<19:13:10,  1.40s/it]
 20%|██        | 12581/61904 [6:26:36<19:04:02,  1.39s/it]
 20%|██        | 12582/61904 [6:26:37<18:28:43,  1.35s/it]
 20%|██        | 12583/61904 [6:26:39<18:56:17,  1.38s/it]
 20%|██        | 12584/61904 [6:26:40<18:34:59,  1.36s/it]
 20%|██        | 12585/61904 [6:26:41<18:16:38,  1.33s/it]
 20%|██        | 12586/61904 [6:26:43<18:45:41,  1.37s/it]
 20%|██        | 12587/61904 [6:26:44<18:32:16,  1.35s/it]
 20%|██        | 12588/61904 [6:26:45<18:45:45,  1.37s/it]
 20%|██        | 12589/61904 [6:26:47<18:32:19,  1.35s/it]
 20%|██        | 12590/61904 [6:26:48<18:36:31,  1.36s/it]
 20%|██        | 12591/61904 [6:26:49<18:43:57,  1.37s/it]
 20%|██        | 12592/61904 [6:26:51<18:57:29,  1.38s/it]
 20%|██        | 12593/61904 [6:26:52<18:47:28,  1.37s/it]
 20%|██        | 12594/61904 [6:26:54<18:38:10,  1.36s/it]
 20%|██        | 12595/61904 [6:26:55<18:58:04,  1.38s/it]
 20%|██        | 12596/61904 [6:26:56<19:06:48,  1.40s/it]
 20%|██        | 12597/61904 [6:26:58<19:37:39,  1.43s/it]
 20%|██        | 12598/61904 [6:26:59<19:10:20,  1.40s/it]
 20%|██        | 12599/61904 [6:27:01<18:39:08,  1.36s/it]
 20%|██        | 12600/61904 [6:27:02<18:28:33,  1.35s/it]
                                                          
{'loss': 2.8004, 'learning_rate': 1.799040580837547e-07, 'epoch': 3.26}

 20%|██        | 12600/61904 [6:27:02<18:28:33,  1.35s/it]
 20%|██        | 12601/61904 [6:27:03<18:39:34,  1.36s/it]
 20%|██        | 12602/61904 [6:27:05<18:33:50,  1.36s/it]
 20%|██        | 12603/61904 [6:27:06<18:50:39,  1.38s/it]
 20%|██        | 12604/61904 [6:27:07<18:29:53,  1.35s/it]
 20%|██        | 12605/61904 [6:27:09<17:58:00,  1.31s/it]
 20%|██        | 12606/61904 [6:27:10<18:25:53,  1.35s/it]
 20%|██        | 12607/61904 [6:27:11<18:19:50,  1.34s/it]
 20%|██        | 12608/61904 [6:27:13<18:23:57,  1.34s/it]
 20%|██        | 12609/61904 [6:27:14<17:55:25,  1.31s/it]
 20%|██        | 12610/61904 [6:27:15<17:55:41,  1.31s/it]
 20%|██        | 12611/61904 [6:27:17<18:02:01,  1.32s/it]
 20%|██        | 12612/61904 [6:27:18<18:10:18,  1.33s/it]
 20%|██        | 12613/61904 [6:27:19<18:56:27,  1.38s/it]
 20%|██        | 12614/61904 [6:27:21<19:00:47,  1.39s/it]
 20%|██        | 12615/61904 [6:27:22<18:47:45,  1.37s/it]
 20%|██        | 12616/61904 [6:27:23<18:33:09,  1.36s/it]
 20%|██        | 12617/61904 [6:27:25<18:46:39,  1.37s/it]
 20%|██        | 12618/61904 [6:27:26<19:10:06,  1.40s/it]
 20%|██        | 12619/61904 [6:27:28<18:53:30,  1.38s/it]
 20%|██        | 12620/61904 [6:27:29<18:44:06,  1.37s/it]
                                                          
{'loss': 2.7432, 'learning_rate': 1.7987164527421235e-07, 'epoch': 3.26}

 20%|██        | 12620/61904 [6:27:29<18:44:06,  1.37s/it]
 20%|██        | 12621/61904 [6:27:30<18:11:53,  1.33s/it]
 20%|██        | 12622/61904 [6:27:32<18:04:03,  1.32s/it]
 20%|██        | 12623/61904 [6:27:33<18:03:19,  1.32s/it]
 20%|██        | 12624/61904 [6:27:34<18:18:41,  1.34s/it]
 20%|██        | 12625/61904 [6:27:36<18:01:21,  1.32s/it]
 20%|██        | 12626/61904 [6:27:37<19:04:56,  1.39s/it]
 20%|██        | 12627/61904 [6:27:39<19:36:10,  1.43s/it]
 20%|██        | 12628/61904 [6:27:40<19:22:20,  1.42s/it]
 20%|██        | 12629/61904 [6:27:41<19:08:40,  1.40s/it]
 20%|██        | 12630/61904 [6:27:43<18:49:15,  1.38s/it]
 20%|██        | 12631/61904 [6:27:44<19:16:00,  1.41s/it]
 20%|██        | 12632/61904 [6:27:45<18:43:17,  1.37s/it]
 20%|██        | 12633/61904 [6:27:47<18:52:27,  1.38s/it]
 20%|██        | 12634/61904 [6:27:48<18:47:19,  1.37s/it]
 20%|██        | 12635/61904 [6:27:50<18:38:54,  1.36s/it]
 20%|██        | 12636/61904 [6:27:51<18:57:53,  1.39s/it]
 20%|██        | 12637/61904 [6:27:52<18:50:19,  1.38s/it]
 20%|██        | 12638/61904 [6:27:54<18:37:38,  1.36s/it]
 20%|██        | 12639/61904 [6:27:55<18:06:03,  1.32s/it]
 20%|██        | 12640/61904 [6:27:56<18:39:34,  1.36s/it]
                                                          
{'loss': 2.7917, 'learning_rate': 1.7983923246467001e-07, 'epoch': 3.27}

 20%|██        | 12640/61904 [6:27:56<18:39:34,  1.36s/it]
 20%|██        | 12641/61904 [6:27:58<18:54:41,  1.38s/it]
 20%|██        | 12642/61904 [6:27:59<18:56:26,  1.38s/it]
 20%|██        | 12643/61904 [6:28:00<18:39:30,  1.36s/it]
 20%|██        | 12644/61904 [6:28:02<18:48:24,  1.37s/it]
 20%|██        | 12645/61904 [6:28:03<18:39:19,  1.36s/it]
 20%|██        | 12646/61904 [6:28:05<19:11:10,  1.40s/it]
 20%|██        | 12647/61904 [6:28:06<19:02:12,  1.39s/it]
 20%|██        | 12648/61904 [6:28:07<18:49:33,  1.38s/it]
 20%|██        | 12649/61904 [6:28:09<18:24:55,  1.35s/it]
 20%|██        | 12650/61904 [6:28:10<18:59:45,  1.39s/it]
 20%|██        | 12651/61904 [6:28:11<18:11:06,  1.33s/it]
 20%|██        | 12652/61904 [6:28:13<18:15:39,  1.33s/it]
 20%|██        | 12653/61904 [6:28:14<17:57:47,  1.31s/it]
 20%|██        | 12654/61904 [6:28:15<18:17:06,  1.34s/it]
 20%|██        | 12655/61904 [6:28:17<19:04:47,  1.39s/it]
 20%|██        | 12656/61904 [6:28:18<19:10:58,  1.40s/it]
 20%|██        | 12657/61904 [6:28:20<19:05:10,  1.40s/it]
 20%|██        | 12658/61904 [6:28:21<18:39:13,  1.36s/it]
 20%|██        | 12659/61904 [6:28:22<18:26:31,  1.35s/it]
 20%|██        | 12660/61904 [6:28:24<18:40:14,  1.36s/it]
                                                          
{'loss': 2.8395, 'learning_rate': 1.798068196551277e-07, 'epoch': 3.27}

 20%|██        | 12660/61904 [6:28:24<18:40:14,  1.36s/it]
 20%|██        | 12661/61904 [6:28:25<18:14:23,  1.33s/it]
 20%|██        | 12662/61904 [6:28:26<18:10:32,  1.33s/it]
 20%|██        | 12663/61904 [6:28:28<18:54:59,  1.38s/it]
 20%|██        | 12664/61904 [6:28:29<18:49:41,  1.38s/it]
 20%|██        | 12665/61904 [6:28:31<19:03:24,  1.39s/it]
 20%|██        | 12666/61904 [6:28:32<19:27:38,  1.42s/it]
 20%|██        | 12667/61904 [6:28:33<19:11:48,  1.40s/it]
 20%|██        | 12668/61904 [6:28:35<18:41:39,  1.37s/it]
 20%|██        | 12669/61904 [6:28:36<19:42:38,  1.44s/it]
 20%|██        | 12670/61904 [6:28:38<20:38:55,  1.51s/it]
 20%|██        | 12671/61904 [6:28:39<20:07:35,  1.47s/it]
 20%|██        | 12672/61904 [6:28:41<19:42:13,  1.44s/it]
 20%|██        | 12673/61904 [6:28:42<19:32:54,  1.43s/it]
 20%|██        | 12674/61904 [6:28:43<19:02:42,  1.39s/it]
 20%|██        | 12675/61904 [6:28:45<18:58:27,  1.39s/it]
 20%|██        | 12676/61904 [6:28:46<19:23:02,  1.42s/it]
 20%|██        | 12677/61904 [6:28:48<19:08:47,  1.40s/it]
 20%|██        | 12678/61904 [6:28:49<19:23:47,  1.42s/it]
 20%|██        | 12679/61904 [6:28:50<19:07:55,  1.40s/it]
 20%|██        | 12680/61904 [6:28:52<18:42:22,  1.37s/it]
                                                          
{'loss': 2.7566, 'learning_rate': 1.7977440684558536e-07, 'epoch': 3.28}

 20%|██        | 12680/61904 [6:28:52<18:42:22,  1.37s/it]
 20%|██        | 12681/61904 [6:28:53<19:21:20,  1.42s/it]
 20%|██        | 12682/61904 [6:28:55<20:04:12,  1.47s/it]
 20%|██        | 12683/61904 [6:28:56<19:57:07,  1.46s/it]
 20%|██        | 12684/61904 [6:28:58<19:31:37,  1.43s/it]
 20%|██        | 12685/61904 [6:28:59<19:36:39,  1.43s/it]
 20%|██        | 12686/61904 [6:29:01<19:42:41,  1.44s/it]
 20%|██        | 12687/61904 [6:29:02<19:22:18,  1.42s/it]
 20%|██        | 12688/61904 [6:29:03<19:00:08,  1.39s/it]
 20%|██        | 12689/61904 [6:29:05<19:31:24,  1.43s/it]
 20%|██        | 12690/61904 [6:29:06<18:53:37,  1.38s/it]
 21%|██        | 12691/61904 [6:29:08<19:58:38,  1.46s/it]
 21%|██        | 12692/61904 [6:29:09<19:56:38,  1.46s/it]
 21%|██        | 12693/61904 [6:29:11<20:09:31,  1.47s/it]
 21%|██        | 12694/61904 [6:29:12<19:40:43,  1.44s/it]
 21%|██        | 12695/61904 [6:29:14<20:59:57,  1.54s/it]
 21%|██        | 12696/61904 [6:29:15<20:35:58,  1.51s/it]
 21%|██        | 12697/61904 [6:29:17<19:45:59,  1.45s/it]
 21%|██        | 12698/61904 [6:29:18<19:12:56,  1.41s/it]
 21%|██        | 12699/61904 [6:29:19<18:58:02,  1.39s/it]
 21%|██        | 12700/61904 [6:29:21<19:04:34,  1.40s/it]
                                                          
{'loss': 2.7603, 'learning_rate': 1.7974199403604303e-07, 'epoch': 3.28}

 21%|██        | 12700/61904 [6:29:21<19:04:34,  1.40s/it]
 21%|██        | 12701/61904 [6:29:22<18:38:04,  1.36s/it]
 21%|██        | 12702/61904 [6:29:23<18:20:08,  1.34s/it]
 21%|██        | 12703/61904 [6:29:24<18:07:15,  1.33s/it]
 21%|██        | 12704/61904 [6:29:26<18:51:14,  1.38s/it]
 21%|██        | 12705/61904 [6:29:28<19:33:53,  1.43s/it]
 21%|██        | 12706/61904 [6:29:29<19:44:29,  1.44s/it]
 21%|██        | 12707/61904 [6:29:31<20:00:53,  1.46s/it]
 21%|██        | 12708/61904 [6:29:32<19:35:14,  1.43s/it]
 21%|██        | 12709/61904 [6:29:33<19:52:02,  1.45s/it]
 21%|██        | 12710/61904 [6:29:35<20:12:00,  1.48s/it]
 21%|██        | 12711/61904 [6:29:36<19:20:04,  1.41s/it]
 21%|██        | 12712/61904 [6:29:37<18:32:36,  1.36s/it]
 21%|██        | 12713/61904 [6:29:39<18:30:08,  1.35s/it]
 21%|██        | 12714/61904 [6:29:40<18:34:23,  1.36s/it]
 21%|██        | 12715/61904 [6:29:42<18:49:09,  1.38s/it]
 21%|██        | 12716/61904 [6:29:43<19:01:43,  1.39s/it]
 21%|██        | 12717/61904 [6:29:44<18:17:29,  1.34s/it]
 21%|██        | 12718/61904 [6:29:46<18:35:32,  1.36s/it]
 21%|██        | 12719/61904 [6:29:47<18:43:19,  1.37s/it]
 21%|██        | 12720/61904 [6:29:48<18:34:09,  1.36s/it]
                                                          
{'loss': 2.7443, 'learning_rate': 1.7970958122650071e-07, 'epoch': 3.29}

 21%|██        | 12720/61904 [6:29:48<18:34:09,  1.36s/it]
 21%|██        | 12721/61904 [6:29:50<19:10:27,  1.40s/it]
 21%|██        | 12722/61904 [6:29:51<19:17:13,  1.41s/it]
 21%|██        | 12723/61904 [6:29:53<18:49:46,  1.38s/it]
 21%|██        | 12724/61904 [6:29:54<18:24:33,  1.35s/it]
 21%|██        | 12725/61904 [6:29:55<18:13:39,  1.33s/it]
 21%|██        | 12726/61904 [6:29:56<18:08:47,  1.33s/it]
 21%|██        | 12727/61904 [6:29:58<18:05:33,  1.32s/it]
 21%|██        | 12728/61904 [6:29:59<18:44:55,  1.37s/it]
 21%|██        | 12729/61904 [6:30:01<18:27:06,  1.35s/it]
 21%|██        | 12730/61904 [6:30:02<18:31:46,  1.36s/it]
 21%|██        | 12731/61904 [6:30:03<18:53:57,  1.38s/it]
 21%|██        | 12732/61904 [6:30:05<18:52:06,  1.38s/it]
 21%|██        | 12733/61904 [6:30:06<18:35:41,  1.36s/it]
 21%|██        | 12734/61904 [6:30:07<18:28:15,  1.35s/it]
 21%|██        | 12735/61904 [6:30:09<18:47:15,  1.38s/it]
 21%|██        | 12736/61904 [6:30:10<18:21:11,  1.34s/it]
 21%|██        | 12737/61904 [6:30:11<18:16:03,  1.34s/it]
 21%|██        | 12738/61904 [6:30:13<18:14:50,  1.34s/it]
 21%|██        | 12739/61904 [6:30:14<18:10:40,  1.33s/it]
 21%|██        | 12740/61904 [6:30:15<18:05:14,  1.32s/it]
                                                          
{'loss': 2.7244, 'learning_rate': 1.7967716841695835e-07, 'epoch': 3.29}

 21%|██        | 12740/61904 [6:30:15<18:05:14,  1.32s/it]
 21%|██        | 12741/61904 [6:30:17<17:47:44,  1.30s/it]
 21%|██        | 12742/61904 [6:30:18<18:29:58,  1.35s/it]
 21%|██        | 12743/61904 [6:30:20<18:47:13,  1.38s/it]
 21%|██        | 12744/61904 [6:30:21<18:41:56,  1.37s/it]
 21%|██        | 12745/61904 [6:30:22<18:48:40,  1.38s/it]
 21%|██        | 12746/61904 [6:30:23<18:00:59,  1.32s/it]
 21%|██        | 12747/61904 [6:30:25<18:33:58,  1.36s/it]
 21%|██        | 12748/61904 [6:30:26<18:31:55,  1.36s/it]
 21%|██        | 12749/61904 [6:30:28<18:03:26,  1.32s/it]
 21%|██        | 12750/61904 [6:30:29<18:07:27,  1.33s/it]
 21%|██        | 12751/61904 [6:30:30<18:15:27,  1.34s/it]
 21%|██        | 12752/61904 [6:30:32<18:58:38,  1.39s/it]
 21%|██        | 12753/61904 [6:30:33<18:31:03,  1.36s/it]
 21%|██        | 12754/61904 [6:30:34<18:27:45,  1.35s/it]
 21%|██        | 12755/61904 [6:30:36<18:48:13,  1.38s/it]
 21%|██        | 12756/61904 [6:30:37<19:06:45,  1.40s/it]
 21%|██        | 12757/61904 [6:30:39<18:46:07,  1.37s/it]
 21%|██        | 12758/61904 [6:30:40<18:35:45,  1.36s/it]
 21%|██        | 12759/61904 [6:30:41<18:44:19,  1.37s/it]
 21%|██        | 12760/61904 [6:30:43<18:20:13,  1.34s/it]
                                                          
{'loss': 2.7736, 'learning_rate': 1.7964475560741604e-07, 'epoch': 3.3}

 21%|██        | 12760/61904 [6:30:43<18:20:13,  1.34s/it]
 21%|██        | 12761/61904 [6:30:44<18:17:27,  1.34s/it]
 21%|██        | 12762/61904 [6:30:45<18:02:00,  1.32s/it]
 21%|██        | 12763/61904 [6:30:46<17:59:22,  1.32s/it]
 21%|██        | 12764/61904 [6:30:48<17:56:29,  1.31s/it]
 21%|██        | 12765/61904 [6:30:49<17:56:50,  1.31s/it]
 21%|██        | 12766/61904 [6:30:50<18:13:43,  1.34s/it]
 21%|██        | 12767/61904 [6:30:52<18:25:31,  1.35s/it]
 21%|██        | 12768/61904 [6:30:53<18:30:32,  1.36s/it]
 21%|██        | 12769/61904 [6:30:55<19:02:08,  1.39s/it]
 21%|██        | 12770/61904 [6:30:56<18:29:35,  1.35s/it]
 21%|██        | 12771/61904 [6:30:57<18:51:24,  1.38s/it]
 21%|██        | 12772/61904 [6:30:59<18:41:58,  1.37s/it]
 21%|██        | 12773/61904 [6:31:00<18:41:45,  1.37s/it]
 21%|██        | 12774/61904 [6:31:01<18:24:04,  1.35s/it]
 21%|██        | 12775/61904 [6:31:03<18:08:38,  1.33s/it]
 21%|██        | 12776/61904 [6:31:04<18:42:23,  1.37s/it]
 21%|██        | 12777/61904 [6:31:06<18:53:21,  1.38s/it]
 21%|██        | 12778/61904 [6:31:07<19:00:34,  1.39s/it]
 21%|██        | 12779/61904 [6:31:08<18:38:51,  1.37s/it]
 21%|██        | 12780/61904 [6:31:10<18:50:52,  1.38s/it]
                                                          
{'loss': 2.7509, 'learning_rate': 1.7961234279787373e-07, 'epoch': 3.3}

 21%|██        | 12780/61904 [6:31:10<18:50:52,  1.38s/it]
 21%|██        | 12781/61904 [6:31:11<18:54:33,  1.39s/it]
 21%|██        | 12782/61904 [6:31:12<18:39:41,  1.37s/it]
 21%|██        | 12783/61904 [6:31:14<18:10:52,  1.33s/it]
 21%|██        | 12784/61904 [6:31:15<18:14:07,  1.34s/it]
 21%|██        | 12785/61904 [6:31:17<18:53:04,  1.38s/it]
 21%|██        | 12786/61904 [6:31:18<18:56:39,  1.39s/it]
 21%|██        | 12787/61904 [6:31:19<18:47:39,  1.38s/it]
 21%|██        | 12788/61904 [6:31:21<18:42:47,  1.37s/it]
 21%|██        | 12789/61904 [6:31:22<18:09:59,  1.33s/it]
 21%|██        | 12790/61904 [6:31:23<17:54:14,  1.31s/it]
 21%|██        | 12791/61904 [6:31:25<18:35:13,  1.36s/it]
 21%|██        | 12792/61904 [6:31:26<18:13:33,  1.34s/it]
 21%|██        | 12793/61904 [6:31:27<18:01:18,  1.32s/it]
 21%|██        | 12794/61904 [6:31:29<18:28:40,  1.35s/it]
 21%|██        | 12795/61904 [6:31:30<18:33:02,  1.36s/it]
 21%|██        | 12796/61904 [6:31:31<18:58:28,  1.39s/it]
 21%|██        | 12797/61904 [6:31:33<18:42:35,  1.37s/it]
 21%|██        | 12798/61904 [6:31:34<18:12:31,  1.33s/it]
 21%|██        | 12799/61904 [6:31:35<18:07:07,  1.33s/it]
 21%|██        | 12800/61904 [6:31:37<18:08:38,  1.33s/it]
                                                          
{'loss': 2.8058, 'learning_rate': 1.7957992998833136e-07, 'epoch': 3.31}

 21%|██        | 12800/61904 [6:31:37<18:08:38,  1.33s/it]
 21%|██        | 12801/61904 [6:31:38<18:33:30,  1.36s/it]
 21%|██        | 12802/61904 [6:31:40<18:35:33,  1.36s/it]
 21%|██        | 12803/61904 [6:31:41<18:12:05,  1.33s/it]
 21%|██        | 12804/61904 [6:31:42<18:55:28,  1.39s/it]
 21%|██        | 12805/61904 [6:31:44<19:20:21,  1.42s/it]
 21%|██        | 12806/61904 [6:31:45<19:36:56,  1.44s/it]
 21%|██        | 12807/61904 [6:31:47<19:43:55,  1.45s/it]
 21%|██        | 12808/61904 [6:31:48<19:01:56,  1.40s/it]
 21%|██        | 12809/61904 [6:31:49<18:23:29,  1.35s/it]
 21%|██        | 12810/61904 [6:31:51<18:09:12,  1.33s/it]
 21%|██        | 12811/61904 [6:31:52<17:56:42,  1.32s/it]
 21%|██        | 12812/61904 [6:31:53<18:18:03,  1.34s/it]
 21%|██        | 12813/61904 [6:31:55<18:57:43,  1.39s/it]
 21%|██        | 12814/61904 [6:31:56<19:00:00,  1.39s/it]
 21%|██        | 12815/61904 [6:31:58<19:07:14,  1.40s/it]
 21%|██        | 12816/61904 [6:31:59<19:58:40,  1.47s/it]
 21%|██        | 12817/61904 [6:32:00<19:01:38,  1.40s/it]
 21%|██        | 12818/61904 [6:32:02<18:52:11,  1.38s/it]
 21%|██        | 12819/61904 [6:32:03<18:51:19,  1.38s/it]
 21%|██        | 12820/61904 [6:32:04<17:59:06,  1.32s/it]
                                                          
{'loss': 2.7647, 'learning_rate': 1.7954751717878905e-07, 'epoch': 3.31}

 21%|██        | 12820/61904 [6:32:04<17:59:06,  1.32s/it]
 21%|██        | 12821/61904 [6:32:06<18:31:30,  1.36s/it]
 21%|██        | 12822/61904 [6:32:07<18:29:07,  1.36s/it]
 21%|██        | 12823/61904 [6:32:08<18:22:42,  1.35s/it]
 21%|██        | 12824/61904 [6:32:10<17:59:48,  1.32s/it]
 21%|██        | 12825/61904 [6:32:11<18:28:20,  1.35s/it]
 21%|██        | 12826/61904 [6:32:13<19:44:05,  1.45s/it]
 21%|██        | 12827/61904 [6:32:14<19:10:48,  1.41s/it]
 21%|██        | 12828/61904 [6:32:15<18:39:39,  1.37s/it]
 21%|██        | 12829/61904 [6:32:17<18:35:51,  1.36s/it]
 21%|██        | 12830/61904 [6:32:18<18:37:25,  1.37s/it]
 21%|██        | 12831/61904 [6:32:19<18:25:00,  1.35s/it]
 21%|██        | 12832/61904 [6:32:21<18:14:40,  1.34s/it]
 21%|██        | 12833/61904 [6:32:22<18:45:47,  1.38s/it]
 21%|██        | 12834/61904 [6:32:24<18:54:59,  1.39s/it]
 21%|██        | 12835/61904 [6:32:25<18:51:20,  1.38s/it]
 21%|██        | 12836/61904 [6:32:26<18:58:07,  1.39s/it]
 21%|██        | 12837/61904 [6:32:28<18:43:30,  1.37s/it]
 21%|██        | 12838/61904 [6:32:29<19:15:32,  1.41s/it]
 21%|██        | 12839/61904 [6:32:31<19:38:38,  1.44s/it]
 21%|██        | 12840/61904 [6:32:32<19:08:39,  1.40s/it]
                                                          
{'loss': 2.7883, 'learning_rate': 1.795151043692467e-07, 'epoch': 3.32}

 21%|██        | 12840/61904 [6:32:32<19:08:39,  1.40s/it]
 21%|██        | 12841/61904 [6:32:33<18:33:00,  1.36s/it]
 21%|██        | 12842/61904 [6:32:35<18:12:05,  1.34s/it]
 21%|██        | 12843/61904 [6:32:36<18:25:07,  1.35s/it]
 21%|██        | 12844/61904 [6:32:37<17:50:40,  1.31s/it]
 21%|██        | 12845/61904 [6:32:39<18:12:59,  1.34s/it]
 21%|██        | 12846/61904 [6:32:40<18:27:40,  1.35s/it]
 21%|██        | 12847/61904 [6:32:41<18:42:14,  1.37s/it]
 21%|██        | 12848/61904 [6:32:43<18:32:51,  1.36s/it]
 21%|██        | 12849/61904 [6:32:44<18:25:44,  1.35s/it]
 21%|██        | 12850/61904 [6:32:45<17:56:56,  1.32s/it]
 21%|██        | 12851/61904 [6:32:47<17:48:34,  1.31s/it]
 21%|██        | 12852/61904 [6:32:48<17:42:00,  1.30s/it]
 21%|██        | 12853/61904 [6:32:49<17:59:43,  1.32s/it]
 21%|██        | 12854/61904 [6:32:51<18:17:24,  1.34s/it]
 21%|██        | 12855/61904 [6:32:52<18:57:12,  1.39s/it]
 21%|██        | 12856/61904 [6:32:54<18:58:00,  1.39s/it]
 21%|██        | 12857/61904 [6:32:55<19:00:07,  1.39s/it]
 21%|██        | 12858/61904 [6:32:56<18:49:45,  1.38s/it]
 21%|██        | 12859/61904 [6:32:58<18:44:02,  1.38s/it]
 21%|██        | 12860/61904 [6:32:59<18:19:10,  1.34s/it]
                                                          
{'loss': 2.8089, 'learning_rate': 1.7948269155970437e-07, 'epoch': 3.32}

 21%|██        | 12860/61904 [6:32:59<18:19:10,  1.34s/it]
 21%|██        | 12861/61904 [6:33:00<18:23:07,  1.35s/it]
 21%|██        | 12862/61904 [6:33:02<18:54:18,  1.39s/it]
 21%|██        | 12863/61904 [6:33:03<19:17:36,  1.42s/it]
 21%|██        | 12864/61904 [6:33:04<18:33:41,  1.36s/it]
 21%|██        | 12865/61904 [6:33:06<19:30:36,  1.43s/it]
 21%|██        | 12866/61904 [6:33:07<18:55:54,  1.39s/it]
 21%|██        | 12867/61904 [6:33:09<18:50:58,  1.38s/it]
 21%|██        | 12868/61904 [6:33:10<19:34:43,  1.44s/it]
 21%|██        | 12869/61904 [6:33:12<18:58:20,  1.39s/it]
 21%|██        | 12870/61904 [6:33:13<18:39:37,  1.37s/it]
 21%|██        | 12871/61904 [6:33:14<19:10:10,  1.41s/it]
 21%|██        | 12872/61904 [6:33:16<20:01:18,  1.47s/it]
 21%|██        | 12873/61904 [6:33:17<19:32:27,  1.43s/it]
 21%|██        | 12874/61904 [6:33:19<19:02:07,  1.40s/it]
 21%|██        | 12875/61904 [6:33:20<18:50:11,  1.38s/it]
 21%|██        | 12876/61904 [6:33:22<19:22:10,  1.42s/it]
 21%|██        | 12877/61904 [6:33:23<19:03:31,  1.40s/it]
 21%|██        | 12878/61904 [6:33:24<18:45:16,  1.38s/it]
 21%|██        | 12879/61904 [6:33:26<18:58:13,  1.39s/it]
 21%|██        | 12880/61904 [6:33:27<19:01:29,  1.40s/it]
                                                          
{'loss': 2.7858, 'learning_rate': 1.7945027875016206e-07, 'epoch': 3.33}

 21%|██        | 12880/61904 [6:33:27<19:01:29,  1.40s/it]
 21%|██        | 12881/61904 [6:33:28<18:44:11,  1.38s/it]
 21%|██        | 12882/61904 [6:33:30<19:12:09,  1.41s/it]
 21%|██        | 12883/61904 [6:33:31<19:14:17,  1.41s/it]
 21%|██        | 12884/61904 [6:33:33<18:48:39,  1.38s/it]
 21%|██        | 12885/61904 [6:33:34<18:59:34,  1.39s/it]
 21%|██        | 12886/61904 [6:33:35<19:07:44,  1.40s/it]
 21%|██        | 12887/61904 [6:33:37<19:23:03,  1.42s/it]
 21%|██        | 12888/61904 [6:33:38<18:45:40,  1.38s/it]
 21%|██        | 12889/61904 [6:33:39<18:11:22,  1.34s/it]
 21%|██        | 12890/61904 [6:33:41<18:19:46,  1.35s/it]
 21%|██        | 12891/61904 [6:33:42<18:34:58,  1.36s/it]
 21%|██        | 12892/61904 [6:33:44<18:47:14,  1.38s/it]
 21%|██        | 12893/61904 [6:33:45<18:30:39,  1.36s/it]
 21%|██        | 12894/61904 [6:33:46<18:23:04,  1.35s/it]
 21%|██        | 12895/61904 [6:33:48<18:10:08,  1.33s/it]
 21%|██        | 12896/61904 [6:33:49<18:02:00,  1.32s/it]
 21%|██        | 12897/61904 [6:33:50<19:04:20,  1.40s/it]
 21%|██        | 12898/61904 [6:33:52<19:03:49,  1.40s/it]
 21%|██        | 12899/61904 [6:33:53<19:13:44,  1.41s/it]
 21%|██        | 12900/61904 [6:33:55<19:31:31,  1.43s/it]
                                                          
{'loss': 2.7449, 'learning_rate': 1.7941786594061972e-07, 'epoch': 3.33}

 21%|██        | 12900/61904 [6:33:55<19:31:31,  1.43s/it]
 21%|██        | 12901/61904 [6:33:56<19:15:51,  1.42s/it]
 21%|██        | 12902/61904 [6:33:57<18:42:44,  1.37s/it]
 21%|██        | 12903/61904 [6:33:59<18:29:32,  1.36s/it]
 21%|██        | 12904/61904 [6:34:00<18:52:50,  1.39s/it]
 21%|██        | 12905/61904 [6:34:02<18:37:47,  1.37s/it]
 21%|██        | 12906/61904 [6:34:03<18:06:24,  1.33s/it]
 21%|██        | 12907/61904 [6:34:04<18:00:05,  1.32s/it]
 21%|██        | 12908/61904 [6:34:05<17:58:41,  1.32s/it]
 21%|██        | 12909/61904 [6:34:07<18:02:56,  1.33s/it]
 21%|██        | 12910/61904 [6:34:08<18:13:09,  1.34s/it]
 21%|██        | 12911/61904 [6:34:09<17:52:10,  1.31s/it]
 21%|██        | 12912/61904 [6:34:11<17:44:31,  1.30s/it]
 21%|██        | 12913/61904 [6:34:12<18:50:51,  1.38s/it]
 21%|██        | 12914/61904 [6:34:14<19:26:12,  1.43s/it]
 21%|██        | 12915/61904 [6:34:15<19:24:19,  1.43s/it]
 21%|██        | 12916/61904 [6:34:17<19:21:47,  1.42s/it]
 21%|██        | 12917/61904 [6:34:18<19:05:36,  1.40s/it]
 21%|██        | 12918/61904 [6:34:19<18:59:39,  1.40s/it]
 21%|██        | 12919/61904 [6:34:21<19:25:07,  1.43s/it]
 21%|██        | 12920/61904 [6:34:22<19:05:43,  1.40s/it]
                                                          
{'loss': 2.7406, 'learning_rate': 1.7938545313107739e-07, 'epoch': 3.34}

 21%|██        | 12920/61904 [6:34:22<19:05:43,  1.40s/it]
 21%|██        | 12921/61904 [6:34:24<19:15:30,  1.42s/it]
 21%|██        | 12922/61904 [6:34:25<19:01:47,  1.40s/it]
 21%|██        | 12923/61904 [6:34:26<18:52:46,  1.39s/it]
 21%|██        | 12924/61904 [6:34:28<18:46:35,  1.38s/it]
 21%|██        | 12925/61904 [6:34:29<18:24:52,  1.35s/it]
 21%|██        | 12926/61904 [6:34:30<18:07:06,  1.33s/it]
 21%|██        | 12927/61904 [6:34:31<17:28:25,  1.28s/it]
 21%|██        | 12928/61904 [6:34:33<17:29:42,  1.29s/it]
 21%|██        | 12929/61904 [6:34:34<18:16:32,  1.34s/it]
 21%|██        | 12930/61904 [6:34:36<18:42:29,  1.38s/it]
 21%|██        | 12931/61904 [6:34:37<18:21:49,  1.35s/it]
 21%|██        | 12932/61904 [6:34:38<18:18:27,  1.35s/it]
 21%|██        | 12933/61904 [6:34:40<19:00:30,  1.40s/it]
 21%|██        | 12934/61904 [6:34:41<18:30:04,  1.36s/it]
 21%|██        | 12935/61904 [6:34:42<18:11:27,  1.34s/it]
 21%|██        | 12936/61904 [6:34:44<18:23:17,  1.35s/it]
 21%|██        | 12937/61904 [6:34:45<18:47:08,  1.38s/it]
 21%|██        | 12938/61904 [6:34:47<18:42:42,  1.38s/it]
 21%|██        | 12939/61904 [6:34:48<18:06:42,  1.33s/it]
 21%|██        | 12940/61904 [6:34:49<18:23:46,  1.35s/it]
                                                          
{'loss': 2.8112, 'learning_rate': 1.7935304032153507e-07, 'epoch': 3.34}

 21%|██        | 12940/61904 [6:34:49<18:23:46,  1.35s/it]
 21%|██        | 12941/61904 [6:34:51<18:44:18,  1.38s/it]
 21%|██        | 12942/61904 [6:34:52<18:17:20,  1.34s/it]
 21%|██        | 12943/61904 [6:34:53<18:48:22,  1.38s/it]
 21%|██        | 12944/61904 [6:34:55<18:21:43,  1.35s/it]
 21%|██        | 12945/61904 [6:34:56<18:28:29,  1.36s/it]
 21%|██        | 12946/61904 [6:34:57<18:40:30,  1.37s/it]
 21%|██        | 12947/61904 [6:34:59<19:08:57,  1.41s/it]
 21%|██        | 12948/61904 [6:35:00<18:43:24,  1.38s/it]
 21%|██        | 12949/61904 [6:35:02<18:40:25,  1.37s/it]
 21%|██        | 12950/61904 [6:35:03<18:38:22,  1.37s/it]
 21%|██        | 12951/61904 [6:35:04<18:28:59,  1.36s/it]
 21%|██        | 12952/61904 [6:35:06<18:08:17,  1.33s/it]
 21%|██        | 12953/61904 [6:35:07<18:00:05,  1.32s/it]
 21%|██        | 12954/61904 [6:35:08<17:55:02,  1.32s/it]
 21%|██        | 12955/61904 [6:35:10<18:11:25,  1.34s/it]
 21%|██        | 12956/61904 [6:35:11<18:43:25,  1.38s/it]
 21%|██        | 12957/61904 [6:35:13<19:28:33,  1.43s/it]
 21%|██        | 12958/61904 [6:35:14<19:41:31,  1.45s/it]
 21%|██        | 12959/61904 [6:35:15<19:25:48,  1.43s/it]
 21%|██        | 12960/61904 [6:35:17<19:37:05,  1.44s/it]
                                                          
{'loss': 2.7738, 'learning_rate': 1.793206275119927e-07, 'epoch': 3.35}

 21%|██        | 12960/61904 [6:35:17<19:37:05,  1.44s/it]
 21%|██        | 12961/61904 [6:35:18<18:56:48,  1.39s/it]
 21%|██        | 12962/61904 [6:35:19<18:37:30,  1.37s/it]
 21%|██        | 12963/61904 [6:35:21<18:28:18,  1.36s/it]
 21%|██        | 12964/61904 [6:35:22<18:05:59,  1.33s/it]
 21%|██        | 12965/61904 [6:35:23<17:41:55,  1.30s/it]
 21%|██        | 12966/61904 [6:35:25<18:15:40,  1.34s/it]
 21%|██        | 12967/61904 [6:35:26<18:16:00,  1.34s/it]
 21%|██        | 12968/61904 [6:35:27<18:18:26,  1.35s/it]
 21%|██        | 12969/61904 [6:35:29<18:06:44,  1.33s/it]
 21%|██        | 12970/61904 [6:35:30<18:12:33,  1.34s/it]
 21%|██        | 12971/61904 [6:35:31<18:19:00,  1.35s/it]
 21%|██        | 12972/61904 [6:35:33<18:28:52,  1.36s/it]
 21%|██        | 12973/61904 [6:35:34<17:55:27,  1.32s/it]
 21%|██        | 12974/61904 [6:35:36<18:21:16,  1.35s/it]
 21%|██        | 12975/61904 [6:35:37<18:00:50,  1.33s/it]
 21%|██        | 12976/61904 [6:35:38<17:55:16,  1.32s/it]
 21%|██        | 12977/61904 [6:35:39<18:02:07,  1.33s/it]
 21%|██        | 12978/61904 [6:35:41<17:36:35,  1.30s/it]
 21%|██        | 12979/61904 [6:35:42<17:48:27,  1.31s/it]
 21%|██        | 12980/61904 [6:35:43<18:02:29,  1.33s/it]
                                                          
{'loss': 2.7914, 'learning_rate': 1.792882147024504e-07, 'epoch': 3.35}

 21%|██        | 12980/61904 [6:35:43<18:02:29,  1.33s/it]
 21%|██        | 12981/61904 [6:35:45<18:16:40,  1.34s/it]
 21%|██        | 12982/61904 [6:35:46<18:37:12,  1.37s/it]
 21%|██        | 12983/61904 [6:35:47<18:15:40,  1.34s/it]
 21%|██        | 12984/61904 [6:35:49<18:34:45,  1.37s/it]
 21%|██        | 12985/61904 [6:35:50<18:18:44,  1.35s/it]
 21%|██        | 12986/61904 [6:35:51<17:54:23,  1.32s/it]
 21%|██        | 12987/61904 [6:35:53<17:29:58,  1.29s/it]
 21%|██        | 12988/61904 [6:35:54<18:52:54,  1.39s/it]
 21%|██        | 12989/61904 [6:35:56<18:55:03,  1.39s/it]
 21%|██        | 12990/61904 [6:35:57<19:00:38,  1.40s/it]
 21%|██        | 12991/61904 [6:35:58<18:58:04,  1.40s/it]
 21%|██        | 12992/61904 [6:36:00<18:43:56,  1.38s/it]
 21%|██        | 12993/61904 [6:36:01<18:46:15,  1.38s/it]
 21%|██        | 12994/61904 [6:36:03<18:32:52,  1.37s/it]
 21%|██        | 12995/61904 [6:36:04<18:17:11,  1.35s/it]
 21%|██        | 12996/61904 [6:36:05<18:15:29,  1.34s/it]
 21%|██        | 12997/61904 [6:36:06<18:11:44,  1.34s/it]
 21%|██        | 12998/61904 [6:36:08<18:05:15,  1.33s/it]
 21%|██        | 12999/61904 [6:36:09<17:33:08,  1.29s/it]
 21%|██        | 13000/61904 [6:36:10<17:36:11,  1.30s/it]
                                                          
{'loss': 2.8128, 'learning_rate': 1.7925580189290806e-07, 'epoch': 3.36}

 21%|██        | 13000/61904 [6:36:10<17:36:11,  1.30s/it]
 21%|██        | 13001/61904 [6:36:12<17:38:24,  1.30s/it]
 21%|██        | 13002/61904 [6:36:13<17:43:05,  1.30s/it]
 21%|██        | 13003/61904 [6:36:14<17:46:25,  1.31s/it]
 21%|██        | 13004/61904 [6:36:15<17:30:26,  1.29s/it]
 21%|██        | 13005/61904 [6:36:17<18:41:57,  1.38s/it]
 21%|██        | 13006/61904 [6:36:19<19:00:11,  1.40s/it]
 21%|██        | 13007/61904 [6:36:20<19:18:28,  1.42s/it]
 21%|██        | 13008/61904 [6:36:21<19:21:20,  1.43s/it]
 21%|██        | 13009/61904 [6:36:23<19:00:01,  1.40s/it]
 21%|██        | 13010/61904 [6:36:24<19:20:33,  1.42s/it]
 21%|██        | 13011/61904 [6:36:26<19:16:41,  1.42s/it]
 21%|██        | 13012/61904 [6:36:27<19:17:22,  1.42s/it]
 21%|██        | 13013/61904 [6:36:28<18:59:31,  1.40s/it]
 21%|██        | 13014/61904 [6:36:30<18:37:08,  1.37s/it]
 21%|██        | 13015/61904 [6:36:31<18:35:07,  1.37s/it]
 21%|██        | 13016/61904 [6:36:32<18:26:48,  1.36s/it]
 21%|██        | 13017/61904 [6:36:34<18:52:42,  1.39s/it]
 21%|██        | 13018/61904 [6:36:35<18:55:19,  1.39s/it]
 21%|██        | 13019/61904 [6:36:37<19:14:22,  1.42s/it]
 21%|██        | 13020/61904 [6:36:38<18:36:59,  1.37s/it]
                                                          
{'loss': 2.8135, 'learning_rate': 1.7922338908336572e-07, 'epoch': 3.36}

 21%|██        | 13020/61904 [6:36:38<18:36:59,  1.37s/it]
 21%|██        | 13021/61904 [6:36:39<18:57:00,  1.40s/it]
 21%|██        | 13022/61904 [6:36:41<18:29:04,  1.36s/it]
 21%|██        | 13023/61904 [6:36:42<18:18:44,  1.35s/it]
 21%|██        | 13024/61904 [6:36:43<18:26:07,  1.36s/it]
 21%|██        | 13025/61904 [6:36:45<18:53:16,  1.39s/it]
 21%|██        | 13026/61904 [6:36:46<19:10:11,  1.41s/it]
 21%|██        | 13027/61904 [6:36:48<19:01:56,  1.40s/it]
 21%|██        | 13028/61904 [6:36:49<18:50:53,  1.39s/it]
 21%|██        | 13029/61904 [6:36:51<18:46:50,  1.38s/it]
 21%|██        | 13030/61904 [6:36:52<18:57:57,  1.40s/it]
 21%|██        | 13031/61904 [6:36:53<18:52:00,  1.39s/it]
 21%|██        | 13032/61904 [6:36:55<19:05:54,  1.41s/it]
 21%|██        | 13033/61904 [6:36:56<18:57:10,  1.40s/it]
 21%|██        | 13034/61904 [6:36:57<18:43:58,  1.38s/it]
 21%|██        | 13035/61904 [6:36:59<19:09:32,  1.41s/it]
 21%|██        | 13036/61904 [6:37:00<19:21:11,  1.43s/it]
 21%|██        | 13037/61904 [6:37:02<19:19:12,  1.42s/it]
 21%|██        | 13038/61904 [6:37:03<19:51:55,  1.46s/it]
 21%|██        | 13039/61904 [6:37:05<19:16:27,  1.42s/it]
 21%|██        | 13040/61904 [6:37:06<19:23:16,  1.43s/it]
                                                          
{'loss': 2.7928, 'learning_rate': 1.791909762738234e-07, 'epoch': 3.37}

 21%|██        | 13040/61904 [6:37:06<19:23:16,  1.43s/it]
 21%|██        | 13041/61904 [6:37:08<20:12:58,  1.49s/it]
 21%|██        | 13042/61904 [6:37:09<19:41:26,  1.45s/it]
 21%|██        | 13043/61904 [6:37:10<18:57:08,  1.40s/it]
 21%|██        | 13044/61904 [6:37:12<18:42:02,  1.38s/it]
 21%|██        | 13045/61904 [6:37:13<18:34:16,  1.37s/it]
 21%|██        | 13046/61904 [6:37:15<19:11:05,  1.41s/it]
 21%|██        | 13047/61904 [6:37:16<18:45:33,  1.38s/it]
 21%|██        | 13048/61904 [6:37:17<19:04:59,  1.41s/it]
 21%|██        | 13049/61904 [6:37:19<18:30:52,  1.36s/it]
 21%|██        | 13050/61904 [6:37:20<18:07:53,  1.34s/it]
 21%|██        | 13051/61904 [6:37:21<18:30:53,  1.36s/it]
 21%|██        | 13052/61904 [6:37:23<18:04:26,  1.33s/it]
 21%|██        | 13053/61904 [6:37:24<18:27:47,  1.36s/it]
 21%|██        | 13054/61904 [6:37:25<18:47:19,  1.38s/it]
 21%|██        | 13055/61904 [6:37:27<18:44:15,  1.38s/it]
 21%|██        | 13056/61904 [6:37:28<18:26:14,  1.36s/it]
 21%|██        | 13057/61904 [6:37:29<18:17:00,  1.35s/it]
 21%|██        | 13058/61904 [6:37:31<18:34:27,  1.37s/it]
 21%|██        | 13059/61904 [6:37:32<18:40:13,  1.38s/it]
 21%|██        | 13060/61904 [6:37:34<19:04:08,  1.41s/it]
                                                          
{'loss': 2.7973, 'learning_rate': 1.7915856346428107e-07, 'epoch': 3.38}

 21%|██        | 13060/61904 [6:37:34<19:04:08,  1.41s/it]
 21%|██        | 13061/61904 [6:37:35<18:47:26,  1.38s/it]
 21%|██        | 13062/61904 [6:37:37<19:11:05,  1.41s/it]
 21%|██        | 13063/61904 [6:37:38<18:57:09,  1.40s/it]
 21%|██        | 13064/61904 [6:37:40<19:40:22,  1.45s/it]
 21%|██        | 13065/61904 [6:37:41<19:12:53,  1.42s/it]
 21%|██        | 13066/61904 [6:37:42<18:37:38,  1.37s/it]
 21%|██        | 13067/61904 [6:37:44<18:41:02,  1.38s/it]
 21%|██        | 13068/61904 [6:37:45<19:05:08,  1.41s/it]
 21%|██        | 13069/61904 [6:37:46<19:25:52,  1.43s/it]
 21%|██        | 13070/61904 [6:37:48<18:23:09,  1.36s/it]
 21%|██        | 13071/61904 [6:37:49<18:44:14,  1.38s/it]
 21%|██        | 13072/61904 [6:37:50<18:14:08,  1.34s/it]
 21%|██        | 13073/61904 [6:37:52<18:34:24,  1.37s/it]
 21%|██        | 13074/61904 [6:37:53<18:14:18,  1.34s/it]
 21%|██        | 13075/61904 [6:37:54<17:53:01,  1.32s/it]
 21%|██        | 13076/61904 [6:37:56<18:05:20,  1.33s/it]
 21%|██        | 13077/61904 [6:37:57<18:21:08,  1.35s/it]
 21%|██        | 13078/61904 [6:37:58<18:07:39,  1.34s/it]
 21%|██        | 13079/61904 [6:38:00<18:32:41,  1.37s/it]
 21%|██        | 13080/61904 [6:38:02<20:00:04,  1.47s/it]
                                                          
{'loss': 2.8088, 'learning_rate': 1.7912615065473873e-07, 'epoch': 3.38}

 21%|██        | 13080/61904 [6:38:02<20:00:04,  1.47s/it]
 21%|██        | 13081/61904 [6:38:03<20:01:35,  1.48s/it]
 21%|██        | 13082/61904 [6:38:04<19:52:17,  1.47s/it]
 21%|██        | 13083/61904 [6:38:06<19:29:59,  1.44s/it]
 21%|██        | 13084/61904 [6:38:07<19:43:08,  1.45s/it]
 21%|██        | 13085/61904 [6:38:09<19:29:57,  1.44s/it]
 21%|██        | 13086/61904 [6:38:10<19:30:37,  1.44s/it]
 21%|██        | 13087/61904 [6:38:11<18:52:27,  1.39s/it]
 21%|██        | 13088/61904 [6:38:13<19:00:27,  1.40s/it]
 21%|██        | 13089/61904 [6:38:14<18:07:23,  1.34s/it]
 21%|██        | 13090/61904 [6:38:15<18:13:49,  1.34s/it]
 21%|██        | 13091/61904 [6:38:17<18:13:03,  1.34s/it]
 21%|██        | 13092/61904 [6:38:18<18:50:28,  1.39s/it]
 21%|██        | 13093/61904 [6:38:20<18:51:12,  1.39s/it]
 21%|██        | 13094/61904 [6:38:21<19:28:46,  1.44s/it]
 21%|██        | 13095/61904 [6:38:23<19:04:58,  1.41s/it]
 21%|██        | 13096/61904 [6:38:24<18:37:55,  1.37s/it]
 21%|██        | 13097/61904 [6:38:25<19:07:57,  1.41s/it]
 21%|██        | 13098/61904 [6:38:27<18:47:29,  1.39s/it]
 21%|██        | 13099/61904 [6:38:28<19:27:16,  1.44s/it]
 21%|██        | 13100/61904 [6:38:30<19:10:08,  1.41s/it]
                                                          
{'loss': 2.7603, 'learning_rate': 1.7909373784519642e-07, 'epoch': 3.39}

 21%|██        | 13100/61904 [6:38:30<19:10:08,  1.41s/it]
 21%|██        | 13101/61904 [6:38:31<19:17:46,  1.42s/it]
 21%|██        | 13102/61904 [6:38:33<19:36:53,  1.45s/it]
 21%|██        | 13103/61904 [6:38:34<19:12:11,  1.42s/it]
 21%|██        | 13104/61904 [6:38:35<19:22:06,  1.43s/it]
 21%|██        | 13105/61904 [6:38:37<19:32:12,  1.44s/it]
 21%|██        | 13106/61904 [6:38:38<19:45:01,  1.46s/it]
 21%|██        | 13107/61904 [6:38:40<19:24:08,  1.43s/it]
 21%|██        | 13108/61904 [6:38:41<19:03:13,  1.41s/it]
 21%|██        | 13109/61904 [6:38:42<18:17:51,  1.35s/it]
 21%|██        | 13110/61904 [6:38:44<18:11:07,  1.34s/it]
 21%|██        | 13111/61904 [6:38:45<19:10:51,  1.42s/it]
 21%|██        | 13112/61904 [6:38:47<18:58:17,  1.40s/it]
 21%|██        | 13113/61904 [6:38:48<18:21:17,  1.35s/it]
 21%|██        | 13114/61904 [6:38:49<18:35:30,  1.37s/it]
 21%|██        | 13115/61904 [6:38:51<19:36:24,  1.45s/it]
 21%|██        | 13116/61904 [6:38:52<19:11:30,  1.42s/it]
 21%|██        | 13117/61904 [6:38:53<18:44:58,  1.38s/it]
 21%|██        | 13118/61904 [6:38:55<18:37:04,  1.37s/it]
 21%|██        | 13119/61904 [6:38:56<19:20:45,  1.43s/it]
 21%|██        | 13120/61904 [6:38:58<19:09:08,  1.41s/it]
                                                          
{'loss': 2.7204, 'learning_rate': 1.7906132503565406e-07, 'epoch': 3.39}

 21%|██        | 13120/61904 [6:38:58<19:09:08,  1.41s/it]
 21%|██        | 13121/61904 [6:38:59<18:33:59,  1.37s/it]
 21%|██        | 13122/61904 [6:39:00<18:20:09,  1.35s/it]
 21%|██        | 13123/61904 [6:39:02<19:45:04,  1.46s/it]
 21%|██        | 13124/61904 [6:39:03<19:05:27,  1.41s/it]
 21%|██        | 13125/61904 [6:39:05<18:56:33,  1.40s/it]
 21%|██        | 13126/61904 [6:39:06<19:35:51,  1.45s/it]
 21%|██        | 13127/61904 [6:39:08<19:18:00,  1.42s/it]
 21%|██        | 13128/61904 [6:39:09<19:12:01,  1.42s/it]
 21%|██        | 13129/61904 [6:39:10<19:13:18,  1.42s/it]
 21%|██        | 13130/61904 [6:39:12<18:55:35,  1.40s/it]
 21%|██        | 13131/61904 [6:39:13<18:39:23,  1.38s/it]
 21%|██        | 13132/61904 [6:39:15<18:45:53,  1.39s/it]
 21%|██        | 13133/61904 [6:39:16<18:41:50,  1.38s/it]
 21%|██        | 13134/61904 [6:39:17<19:36:34,  1.45s/it]
 21%|██        | 13135/61904 [6:39:19<19:08:31,  1.41s/it]
 21%|██        | 13136/61904 [6:39:20<19:03:57,  1.41s/it]
 21%|██        | 13137/61904 [6:39:22<18:44:09,  1.38s/it]
 21%|██        | 13138/61904 [6:39:23<19:07:49,  1.41s/it]
 21%|██        | 13139/61904 [6:39:24<19:12:23,  1.42s/it]
 21%|██        | 13140/61904 [6:39:26<19:26:49,  1.44s/it]
                                                          
{'loss': 2.7494, 'learning_rate': 1.7902891222611175e-07, 'epoch': 3.4}

 21%|██        | 13140/61904 [6:39:26<19:26:49,  1.44s/it]
 21%|██        | 13141/61904 [6:39:27<18:44:25,  1.38s/it]
 21%|██        | 13142/61904 [6:39:29<18:54:32,  1.40s/it]
 21%|██        | 13143/61904 [6:39:30<18:48:05,  1.39s/it]
 21%|██        | 13144/61904 [6:39:31<19:03:36,  1.41s/it]
 21%|██        | 13145/61904 [6:39:33<19:19:09,  1.43s/it]
 21%|██        | 13146/61904 [6:39:34<18:58:27,  1.40s/it]
 21%|██        | 13147/61904 [6:39:36<18:37:48,  1.38s/it]
 21%|██        | 13148/61904 [6:39:37<18:18:45,  1.35s/it]
 21%|██        | 13149/61904 [6:39:38<18:41:57,  1.38s/it]
 21%|██        | 13150/61904 [6:39:40<18:26:54,  1.36s/it]
 21%|██        | 13151/61904 [6:39:41<19:34:52,  1.45s/it]
 21%|██        | 13152/61904 [6:39:43<20:17:09,  1.50s/it]
 21%|██        | 13153/61904 [6:39:44<20:04:28,  1.48s/it]
 21%|██        | 13154/61904 [6:39:46<19:42:44,  1.46s/it]
 21%|██▏       | 13155/61904 [6:39:47<19:35:08,  1.45s/it]
 21%|██▏       | 13156/61904 [6:39:49<19:20:01,  1.43s/it]
 21%|██▏       | 13157/61904 [6:39:50<18:55:03,  1.40s/it]
 21%|██▏       | 13158/61904 [6:39:51<18:59:25,  1.40s/it]
 21%|██▏       | 13159/61904 [6:39:53<18:38:25,  1.38s/it]
 21%|██▏       | 13160/61904 [6:39:54<19:02:50,  1.41s/it]
                                                          
{'loss': 2.7304, 'learning_rate': 1.7899649941656943e-07, 'epoch': 3.4}

 21%|██▏       | 13160/61904 [6:39:54<19:02:50,  1.41s/it]
 21%|██▏       | 13161/61904 [6:39:55<18:41:17,  1.38s/it]
 21%|██▏       | 13162/61904 [6:39:57<18:25:57,  1.36s/it]
 21%|██▏       | 13163/61904 [6:39:58<18:54:05,  1.40s/it]
 21%|██▏       | 13164/61904 [6:40:00<18:32:08,  1.37s/it]
 21%|██▏       | 13165/61904 [6:40:01<18:15:46,  1.35s/it]
 21%|██▏       | 13166/61904 [6:40:02<17:56:08,  1.32s/it]
 21%|██▏       | 13167/61904 [6:40:04<18:40:19,  1.38s/it]
 21%|██▏       | 13168/61904 [6:40:05<18:13:00,  1.35s/it]
 21%|██▏       | 13169/61904 [6:40:06<18:33:16,  1.37s/it]
 21%|██▏       | 13170/61904 [6:40:08<18:27:25,  1.36s/it]
 21%|██▏       | 13171/61904 [6:40:09<18:10:53,  1.34s/it]
 21%|██▏       | 13172/61904 [6:40:10<18:10:57,  1.34s/it]
 21%|██▏       | 13173/61904 [6:40:12<17:57:48,  1.33s/it]
 21%|██▏       | 13174/61904 [6:40:13<18:16:09,  1.35s/it]
 21%|██▏       | 13175/61904 [6:40:14<17:37:12,  1.30s/it]
 21%|██▏       | 13176/61904 [6:40:16<18:13:21,  1.35s/it]
 21%|██▏       | 13177/61904 [6:40:17<18:03:17,  1.33s/it]
 21%|██▏       | 13178/61904 [6:40:18<18:07:09,  1.34s/it]
 21%|██▏       | 13179/61904 [6:40:20<17:54:49,  1.32s/it]
 21%|██▏       | 13180/61904 [6:40:21<17:58:18,  1.33s/it]
                                                          
{'loss': 2.7921, 'learning_rate': 1.7896408660702707e-07, 'epoch': 3.41}

 21%|██▏       | 13180/61904 [6:40:21<17:58:18,  1.33s/it]
 21%|██▏       | 13181/61904 [6:40:22<17:54:58,  1.32s/it]
 21%|██▏       | 13182/61904 [6:40:24<18:05:19,  1.34s/it]
 21%|██▏       | 13183/61904 [6:40:25<18:13:44,  1.35s/it]
 21%|██▏       | 13184/61904 [6:40:26<18:35:54,  1.37s/it]
 21%|██▏       | 13185/61904 [6:40:28<19:01:54,  1.41s/it]
 21%|██▏       | 13186/61904 [6:40:29<18:57:54,  1.40s/it]
 21%|██▏       | 13187/61904 [6:40:31<18:36:07,  1.37s/it]
 21%|██▏       | 13188/61904 [6:40:32<18:10:12,  1.34s/it]
 21%|██▏       | 13189/61904 [6:40:33<18:01:38,  1.33s/it]
 21%|██▏       | 13190/61904 [6:40:34<17:40:01,  1.31s/it]
 21%|██▏       | 13191/61904 [6:40:36<18:15:47,  1.35s/it]
 21%|██▏       | 13192/61904 [6:40:37<18:49:26,  1.39s/it]
 21%|██▏       | 13193/61904 [6:40:39<18:30:25,  1.37s/it]
 21%|██▏       | 13194/61904 [6:40:40<17:57:32,  1.33s/it]
 21%|██▏       | 13195/61904 [6:40:41<18:33:10,  1.37s/it]
 21%|██▏       | 13196/61904 [6:40:43<18:33:11,  1.37s/it]
 21%|██▏       | 13197/61904 [6:40:44<18:30:57,  1.37s/it]
 21%|██▏       | 13198/61904 [6:40:46<19:08:27,  1.41s/it]
 21%|██▏       | 13199/61904 [6:40:47<19:02:52,  1.41s/it]
 21%|██▏       | 13200/61904 [6:40:48<18:56:22,  1.40s/it]
                                                          
{'loss': 2.7574, 'learning_rate': 1.7893167379748476e-07, 'epoch': 3.41}

 21%|██▏       | 13200/61904 [6:40:48<18:56:22,  1.40s/it]
 21%|██▏       | 13201/61904 [6:40:50<18:33:17,  1.37s/it]
 21%|██▏       | 13202/61904 [6:40:51<18:33:59,  1.37s/it]
 21%|██▏       | 13203/61904 [6:40:52<18:52:15,  1.39s/it]
 21%|██▏       | 13204/61904 [6:40:54<18:31:13,  1.37s/it]
 21%|██▏       | 13205/61904 [6:40:55<18:12:09,  1.35s/it]
 21%|██▏       | 13206/61904 [6:40:56<18:02:50,  1.33s/it]
 21%|██▏       | 13207/61904 [6:40:58<19:09:03,  1.42s/it]
 21%|██▏       | 13208/61904 [6:40:59<18:54:59,  1.40s/it]
 21%|██▏       | 13209/61904 [6:41:01<18:29:54,  1.37s/it]
 21%|██▏       | 13210/61904 [6:41:02<18:34:25,  1.37s/it]
 21%|██▏       | 13211/61904 [6:41:03<18:04:29,  1.34s/it]
 21%|██▏       | 13212/61904 [6:41:05<17:42:39,  1.31s/it]
 21%|██▏       | 13213/61904 [6:41:06<17:35:58,  1.30s/it]
 21%|██▏       | 13214/61904 [6:41:07<18:00:31,  1.33s/it]
 21%|██▏       | 13215/61904 [6:41:09<18:14:40,  1.35s/it]
 21%|██▏       | 13216/61904 [6:41:10<18:34:24,  1.37s/it]
 21%|██▏       | 13217/61904 [6:41:11<18:51:05,  1.39s/it]
 21%|██▏       | 13218/61904 [6:41:13<18:36:16,  1.38s/it]
 21%|██▏       | 13219/61904 [6:41:14<18:38:45,  1.38s/it]
 21%|██▏       | 13220/61904 [6:41:15<18:10:12,  1.34s/it]
                                                          
{'loss': 2.7649, 'learning_rate': 1.7889926098794242e-07, 'epoch': 3.42}

 21%|██▏       | 13220/61904 [6:41:15<18:10:12,  1.34s/it]
 21%|██▏       | 13221/61904 [6:41:17<18:21:24,  1.36s/it]
 21%|██▏       | 13222/61904 [6:41:18<18:35:32,  1.37s/it]
 21%|██▏       | 13223/61904 [6:41:20<18:26:04,  1.36s/it]
 21%|██▏       | 13224/61904 [6:41:21<18:21:25,  1.36s/it]
 21%|██▏       | 13225/61904 [6:41:23<20:13:12,  1.50s/it]
 21%|██▏       | 13226/61904 [6:41:24<19:27:41,  1.44s/it]
 21%|██▏       | 13227/61904 [6:41:25<19:02:10,  1.41s/it]
 21%|██▏       | 13228/61904 [6:41:27<18:34:10,  1.37s/it]
 21%|██▏       | 13229/61904 [6:41:28<18:24:44,  1.36s/it]
 21%|██▏       | 13230/61904 [6:41:30<18:50:50,  1.39s/it]
 21%|██▏       | 13231/61904 [6:41:31<19:13:34,  1.42s/it]
 21%|██▏       | 13232/61904 [6:41:32<19:10:25,  1.42s/it]
 21%|██▏       | 13233/61904 [6:41:34<19:26:24,  1.44s/it]
 21%|██▏       | 13234/61904 [6:41:35<18:48:21,  1.39s/it]
 21%|██▏       | 13235/61904 [6:41:37<18:40:15,  1.38s/it]
 21%|██▏       | 13236/61904 [6:41:38<18:36:44,  1.38s/it]
 21%|██▏       | 13237/61904 [6:41:39<18:52:27,  1.40s/it]
 21%|██▏       | 13238/61904 [6:41:41<18:36:36,  1.38s/it]
 21%|██▏       | 13239/61904 [6:41:42<17:54:49,  1.33s/it]
 21%|██▏       | 13240/61904 [6:41:43<17:52:56,  1.32s/it]
                                                          
{'loss': 2.7618, 'learning_rate': 1.7886684817840008e-07, 'epoch': 3.42}

 21%|██▏       | 13240/61904 [6:41:43<17:52:56,  1.32s/it]
 21%|██▏       | 13241/61904 [6:41:45<18:29:40,  1.37s/it]
 21%|██▏       | 13242/61904 [6:41:46<18:28:19,  1.37s/it]
 21%|██▏       | 13243/61904 [6:41:47<18:39:34,  1.38s/it]
 21%|██▏       | 13244/61904 [6:41:49<18:34:58,  1.37s/it]
 21%|██▏       | 13245/61904 [6:41:50<19:12:33,  1.42s/it]
 21%|██▏       | 13246/61904 [6:41:52<18:26:02,  1.36s/it]
 21%|██▏       | 13247/61904 [6:41:53<18:39:25,  1.38s/it]
 21%|██▏       | 13248/61904 [6:41:54<18:16:15,  1.35s/it]
 21%|██▏       | 13249/61904 [6:41:56<19:06:28,  1.41s/it]
 21%|██▏       | 13250/61904 [6:41:57<19:09:05,  1.42s/it]
 21%|██▏       | 13251/61904 [6:41:59<19:22:22,  1.43s/it]
 21%|██▏       | 13252/61904 [6:42:00<18:49:36,  1.39s/it]
 21%|██▏       | 13253/61904 [6:42:02<19:17:02,  1.43s/it]
 21%|██▏       | 13254/61904 [6:42:03<19:49:02,  1.47s/it]
 21%|██▏       | 13255/61904 [6:42:04<19:16:49,  1.43s/it]
 21%|██▏       | 13256/61904 [6:42:06<18:50:53,  1.39s/it]
 21%|██▏       | 13257/61904 [6:42:07<18:25:27,  1.36s/it]
 21%|██▏       | 13258/61904 [6:42:08<17:58:47,  1.33s/it]
 21%|██▏       | 13259/61904 [6:42:10<17:54:02,  1.32s/it]
 21%|██▏       | 13260/61904 [6:42:11<18:10:11,  1.34s/it]
                                                          
{'loss': 2.7628, 'learning_rate': 1.7883443536885777e-07, 'epoch': 3.43}

 21%|██▏       | 13260/61904 [6:42:11<18:10:11,  1.34s/it]
 21%|██▏       | 13261/61904 [6:42:13<19:05:15,  1.41s/it]
 21%|██▏       | 13262/61904 [6:42:14<19:04:13,  1.41s/it]
 21%|██▏       | 13263/61904 [6:42:16<19:49:56,  1.47s/it]
 21%|██▏       | 13264/61904 [6:42:17<18:53:31,  1.40s/it]
 21%|██▏       | 13265/61904 [6:42:18<18:24:39,  1.36s/it]
 21%|██▏       | 13266/61904 [6:42:20<18:54:06,  1.40s/it]
 21%|██▏       | 13267/61904 [6:42:21<18:35:35,  1.38s/it]
 21%|██▏       | 13268/61904 [6:42:22<18:31:11,  1.37s/it]
 21%|██▏       | 13269/61904 [6:42:24<18:25:36,  1.36s/it]
 21%|██▏       | 13270/61904 [6:42:25<18:32:47,  1.37s/it]
 21%|██▏       | 13271/61904 [6:42:26<18:59:43,  1.41s/it]
 21%|██▏       | 13272/61904 [6:42:28<18:47:07,  1.39s/it]
 21%|██▏       | 13273/61904 [6:42:29<19:01:56,  1.41s/it]
 21%|██▏       | 13274/61904 [6:42:31<18:23:08,  1.36s/it]
 21%|██▏       | 13275/61904 [6:42:32<17:56:20,  1.33s/it]
 21%|██▏       | 13276/61904 [6:42:33<18:06:16,  1.34s/it]
 21%|██▏       | 13277/61904 [6:42:34<17:52:50,  1.32s/it]
 21%|██▏       | 13278/61904 [6:42:36<18:46:57,  1.39s/it]
 21%|██▏       | 13279/61904 [6:42:37<18:39:05,  1.38s/it]
 21%|██▏       | 13280/61904 [6:42:39<18:43:40,  1.39s/it]
                                                          
{'loss': 2.7988, 'learning_rate': 1.7880202255931543e-07, 'epoch': 3.43}

 21%|██▏       | 13280/61904 [6:42:39<18:43:40,  1.39s/it]
 21%|██▏       | 13281/61904 [6:42:40<19:07:39,  1.42s/it]
 21%|██▏       | 13282/61904 [6:42:42<19:07:14,  1.42s/it]
 21%|██▏       | 13283/61904 [6:42:43<19:13:10,  1.42s/it]
 21%|██▏       | 13284/61904 [6:42:45<19:17:46,  1.43s/it]
 21%|██▏       | 13285/61904 [6:42:46<19:00:10,  1.41s/it]
 21%|██▏       | 13286/61904 [6:42:47<18:39:17,  1.38s/it]
 21%|██▏       | 13287/61904 [6:42:49<18:23:46,  1.36s/it]
 21%|██▏       | 13288/61904 [6:42:50<18:00:29,  1.33s/it]
 21%|██▏       | 13289/61904 [6:42:51<17:12:48,  1.27s/it]
 21%|██▏       | 13290/61904 [6:42:52<17:07:26,  1.27s/it]
 21%|██▏       | 13291/61904 [6:42:53<17:08:27,  1.27s/it]
 21%|██▏       | 13292/61904 [6:42:55<18:09:50,  1.35s/it]
 21%|██▏       | 13293/61904 [6:42:56<18:06:29,  1.34s/it]
 21%|██▏       | 13294/61904 [6:42:58<18:45:27,  1.39s/it]
 21%|██▏       | 13295/61904 [6:42:59<18:17:26,  1.35s/it]
 21%|██▏       | 13296/61904 [6:43:01<18:47:16,  1.39s/it]
 21%|██▏       | 13297/61904 [6:43:02<19:23:35,  1.44s/it]
 21%|██▏       | 13298/61904 [6:43:03<19:12:12,  1.42s/it]
 21%|██▏       | 13299/61904 [6:43:05<18:50:35,  1.40s/it]
 21%|██▏       | 13300/61904 [6:43:06<18:54:27,  1.40s/it]
                                                          
{'loss': 2.7147, 'learning_rate': 1.787696097497731e-07, 'epoch': 3.44}

 21%|██▏       | 13300/61904 [6:43:06<18:54:27,  1.40s/it]
 21%|██▏       | 13301/61904 [6:43:08<18:48:13,  1.39s/it]
 21%|██▏       | 13302/61904 [6:43:09<18:30:26,  1.37s/it]
 21%|██▏       | 13303/61904 [6:43:10<18:14:45,  1.35s/it]
 21%|██▏       | 13304/61904 [6:43:11<17:53:00,  1.32s/it]
 21%|██▏       | 13305/61904 [6:43:13<18:34:46,  1.38s/it]
 21%|██▏       | 13306/61904 [6:43:14<18:34:48,  1.38s/it]
 21%|██▏       | 13307/61904 [6:43:16<18:25:56,  1.37s/it]
 21%|██▏       | 13308/61904 [6:43:17<18:50:01,  1.40s/it]
 21%|██▏       | 13309/61904 [6:43:19<19:07:52,  1.42s/it]
 22%|██▏       | 13310/61904 [6:43:20<19:04:34,  1.41s/it]
 22%|██▏       | 13311/61904 [6:43:21<18:20:25,  1.36s/it]
 22%|██▏       | 13312/61904 [6:43:22<17:49:11,  1.32s/it]
 22%|██▏       | 13313/61904 [6:43:24<18:01:54,  1.34s/it]
 22%|██▏       | 13314/61904 [6:43:25<18:10:35,  1.35s/it]
 22%|██▏       | 13315/61904 [6:43:27<18:08:09,  1.34s/it]
 22%|██▏       | 13316/61904 [6:43:28<18:22:43,  1.36s/it]
 22%|██▏       | 13317/61904 [6:43:29<18:05:40,  1.34s/it]
 22%|██▏       | 13318/61904 [6:43:31<18:17:08,  1.35s/it]
 22%|██▏       | 13319/61904 [6:43:32<19:05:27,  1.41s/it]
 22%|██▏       | 13320/61904 [6:43:34<18:38:54,  1.38s/it]
                                                          
{'loss': 2.8114, 'learning_rate': 1.7873719694023078e-07, 'epoch': 3.44}

 22%|██▏       | 13320/61904 [6:43:34<18:38:54,  1.38s/it]
 22%|██▏       | 13321/61904 [6:43:35<19:07:03,  1.42s/it]
 22%|██▏       | 13322/61904 [6:43:36<18:33:52,  1.38s/it]
 22%|██▏       | 13323/61904 [6:43:38<18:41:39,  1.39s/it]
 22%|██▏       | 13324/61904 [6:43:39<18:14:30,  1.35s/it]
 22%|██▏       | 13325/61904 [6:43:40<18:24:01,  1.36s/it]
 22%|██▏       | 13326/61904 [6:43:42<18:00:40,  1.33s/it]
 22%|██▏       | 13327/61904 [6:43:43<18:02:13,  1.34s/it]
 22%|██▏       | 13328/61904 [6:43:44<17:45:26,  1.32s/it]
 22%|██▏       | 13329/61904 [6:43:46<17:46:15,  1.32s/it]
 22%|██▏       | 13330/61904 [6:43:47<17:44:24,  1.31s/it]
 22%|██▏       | 13331/61904 [6:43:48<17:33:00,  1.30s/it]
 22%|██▏       | 13332/61904 [6:43:49<17:33:11,  1.30s/it]
 22%|██▏       | 13333/61904 [6:43:51<18:01:26,  1.34s/it]
 22%|██▏       | 13334/61904 [6:43:52<17:49:15,  1.32s/it]
 22%|██▏       | 13335/61904 [6:43:53<17:35:51,  1.30s/it]
 22%|██▏       | 13336/61904 [6:43:55<17:14:14,  1.28s/it]
 22%|██▏       | 13337/61904 [6:43:56<17:34:56,  1.30s/it]
 22%|██▏       | 13338/61904 [6:43:57<17:53:49,  1.33s/it]
 22%|██▏       | 13339/61904 [6:43:59<18:33:53,  1.38s/it]
 22%|██▏       | 13340/61904 [6:44:00<18:08:56,  1.35s/it]
                                                          
{'loss': 2.7474, 'learning_rate': 1.7870478413068842e-07, 'epoch': 3.45}

 22%|██▏       | 13340/61904 [6:44:00<18:08:56,  1.35s/it]
 22%|██▏       | 13341/61904 [6:44:01<17:42:40,  1.31s/it]
 22%|██▏       | 13342/61904 [6:44:03<18:01:48,  1.34s/it]
 22%|██▏       | 13343/61904 [6:44:04<18:45:14,  1.39s/it]
 22%|██▏       | 13344/61904 [6:44:06<18:58:58,  1.41s/it]
 22%|██▏       | 13345/61904 [6:44:07<19:09:49,  1.42s/it]
 22%|██▏       | 13346/61904 [6:44:09<18:55:57,  1.40s/it]
 22%|██▏       | 13347/61904 [6:44:10<18:52:53,  1.40s/it]
 22%|██▏       | 13348/61904 [6:44:11<19:00:23,  1.41s/it]
 22%|██▏       | 13349/61904 [6:44:13<18:24:38,  1.37s/it]
 22%|██▏       | 13350/61904 [6:44:14<18:05:54,  1.34s/it]
 22%|██▏       | 13351/61904 [6:44:15<18:03:39,  1.34s/it]
 22%|██▏       | 13352/61904 [6:44:17<18:34:08,  1.38s/it]
 22%|██▏       | 13353/61904 [6:44:18<19:01:58,  1.41s/it]
 22%|██▏       | 13354/61904 [6:44:20<18:42:17,  1.39s/it]
 22%|██▏       | 13355/61904 [6:44:21<18:32:35,  1.38s/it]
 22%|██▏       | 13356/61904 [6:44:22<18:19:48,  1.36s/it]
 22%|██▏       | 13357/61904 [6:44:24<18:25:13,  1.37s/it]
 22%|██▏       | 13358/61904 [6:44:25<18:47:38,  1.39s/it]
 22%|██▏       | 13359/61904 [6:44:26<18:08:18,  1.35s/it]
 22%|██▏       | 13360/61904 [6:44:28<18:34:03,  1.38s/it]
                                                          
{'loss': 2.7718, 'learning_rate': 1.786723713211461e-07, 'epoch': 3.45}

 22%|██▏       | 13360/61904 [6:44:28<18:34:03,  1.38s/it]
 22%|██▏       | 13361/61904 [6:44:29<18:46:11,  1.39s/it]
 22%|██▏       | 13362/61904 [6:44:31<18:39:33,  1.38s/it]
 22%|██▏       | 13363/61904 [6:44:32<18:05:04,  1.34s/it]
 22%|██▏       | 13364/61904 [6:44:33<18:16:11,  1.36s/it]
 22%|██▏       | 13365/61904 [6:44:35<18:19:15,  1.36s/it]
 22%|██▏       | 13366/61904 [6:44:36<18:31:01,  1.37s/it]
 22%|██▏       | 13367/61904 [6:44:37<18:54:12,  1.40s/it]
 22%|██▏       | 13368/61904 [6:44:39<18:52:17,  1.40s/it]
 22%|██▏       | 13369/61904 [6:44:40<18:23:05,  1.36s/it]
 22%|██▏       | 13370/61904 [6:44:41<18:27:23,  1.37s/it]
 22%|██▏       | 13371/61904 [6:44:43<18:11:14,  1.35s/it]
 22%|██▏       | 13372/61904 [6:44:44<18:15:11,  1.35s/it]
 22%|██▏       | 13373/61904 [6:44:45<18:15:26,  1.35s/it]
 22%|██▏       | 13374/61904 [6:44:47<17:57:00,  1.33s/it]
 22%|██▏       | 13375/61904 [6:44:48<18:02:53,  1.34s/it]
 22%|██▏       | 13376/61904 [6:44:49<17:48:58,  1.32s/it]
 22%|██▏       | 13377/61904 [6:44:51<17:39:51,  1.31s/it]
 22%|██▏       | 13378/61904 [6:44:52<17:35:35,  1.31s/it]
 22%|██▏       | 13379/61904 [6:44:53<17:48:15,  1.32s/it]
 22%|██▏       | 13380/61904 [6:44:55<17:49:12,  1.32s/it]
                                                          
{'loss': 2.821, 'learning_rate': 1.786399585116038e-07, 'epoch': 3.46}

 22%|██▏       | 13380/61904 [6:44:55<17:49:12,  1.32s/it]
 22%|██▏       | 13381/61904 [6:44:56<18:02:37,  1.34s/it]
 22%|██▏       | 13382/61904 [6:44:57<17:55:00,  1.33s/it]
 22%|██▏       | 13383/61904 [6:44:59<17:38:16,  1.31s/it]
 22%|██▏       | 13384/61904 [6:45:00<17:45:15,  1.32s/it]
 22%|██▏       | 13385/61904 [6:45:01<17:39:48,  1.31s/it]
 22%|██▏       | 13386/61904 [6:45:03<17:54:51,  1.33s/it]
 22%|██▏       | 13387/61904 [6:45:04<17:23:28,  1.29s/it]
 22%|██▏       | 13388/61904 [6:45:05<17:27:39,  1.30s/it]
 22%|██▏       | 13389/61904 [6:45:06<17:26:36,  1.29s/it]
 22%|██▏       | 13390/61904 [6:45:08<18:06:26,  1.34s/it]
 22%|██▏       | 13391/61904 [6:45:09<18:17:26,  1.36s/it]
 22%|██▏       | 13392/61904 [6:45:10<17:48:55,  1.32s/it]
 22%|██▏       | 13393/61904 [6:45:12<17:26:51,  1.29s/it]
 22%|██▏       | 13394/61904 [6:45:13<17:48:40,  1.32s/it]
 22%|██▏       | 13395/61904 [6:45:14<17:43:01,  1.31s/it]
 22%|██▏       | 13396/61904 [6:45:16<17:36:47,  1.31s/it]
 22%|██▏       | 13397/61904 [6:45:17<17:45:56,  1.32s/it]
 22%|██▏       | 13398/61904 [6:45:18<18:18:11,  1.36s/it]
 22%|██▏       | 13399/61904 [6:45:20<19:07:21,  1.42s/it]
 22%|██▏       | 13400/61904 [6:45:21<19:00:25,  1.41s/it]
                                                          
{'loss': 2.706, 'learning_rate': 1.7860754570206143e-07, 'epoch': 3.46}

 22%|██▏       | 13400/61904 [6:45:21<19:00:25,  1.41s/it]
 22%|██▏       | 13401/61904 [6:45:23<19:30:10,  1.45s/it]
 22%|██▏       | 13402/61904 [6:45:24<19:28:36,  1.45s/it]
 22%|██▏       | 13403/61904 [6:45:26<18:54:06,  1.40s/it]
 22%|██▏       | 13404/61904 [6:45:27<18:58:25,  1.41s/it]
 22%|██▏       | 13405/61904 [6:45:28<18:42:04,  1.39s/it]
 22%|██▏       | 13406/61904 [6:45:30<19:11:48,  1.42s/it]
 22%|██▏       | 13407/61904 [6:45:31<18:40:30,  1.39s/it]
 22%|██▏       | 13408/61904 [6:45:32<17:59:21,  1.34s/it]
 22%|██▏       | 13409/61904 [6:45:34<18:21:41,  1.36s/it]
 22%|██▏       | 13410/61904 [6:45:35<18:15:59,  1.36s/it]
 22%|██▏       | 13411/61904 [6:45:37<18:26:53,  1.37s/it]
 22%|██▏       | 13412/61904 [6:45:38<17:57:19,  1.33s/it]
 22%|██▏       | 13413/61904 [6:45:39<18:00:23,  1.34s/it]
 22%|██▏       | 13414/61904 [6:45:41<18:01:50,  1.34s/it]
 22%|██▏       | 13415/61904 [6:45:42<18:07:04,  1.35s/it]
 22%|██▏       | 13416/61904 [6:45:43<18:16:44,  1.36s/it]
 22%|██▏       | 13417/61904 [6:45:45<19:27:38,  1.44s/it]
 22%|██▏       | 13418/61904 [6:45:46<19:14:53,  1.43s/it]
 22%|██▏       | 13419/61904 [6:45:48<18:57:09,  1.41s/it]
 22%|██▏       | 13420/61904 [6:45:49<18:16:20,  1.36s/it]
                                                          
{'loss': 2.7982, 'learning_rate': 1.7857513289251912e-07, 'epoch': 3.47}

 22%|██▏       | 13420/61904 [6:45:49<18:16:20,  1.36s/it]
 22%|██▏       | 13421/61904 [6:45:50<18:34:40,  1.38s/it]
 22%|██▏       | 13422/61904 [6:45:52<18:44:06,  1.39s/it]
 22%|██▏       | 13423/61904 [6:45:53<17:59:47,  1.34s/it]
 22%|██▏       | 13424/61904 [6:45:54<17:35:51,  1.31s/it]
 22%|██▏       | 13425/61904 [6:45:56<17:58:53,  1.34s/it]
 22%|██▏       | 13426/61904 [6:45:57<18:38:30,  1.38s/it]
 22%|██▏       | 13427/61904 [6:45:58<18:10:41,  1.35s/it]
 22%|██▏       | 13428/61904 [6:46:00<18:45:17,  1.39s/it]
 22%|██▏       | 13429/61904 [6:46:01<18:46:43,  1.39s/it]
 22%|██▏       | 13430/61904 [6:46:03<18:35:43,  1.38s/it]
 22%|██▏       | 13431/61904 [6:46:04<18:31:03,  1.38s/it]
 22%|██▏       | 13432/61904 [6:46:05<18:17:14,  1.36s/it]
 22%|██▏       | 13433/61904 [6:46:07<18:26:31,  1.37s/it]
 22%|██▏       | 13434/61904 [6:46:08<18:52:08,  1.40s/it]
 22%|██▏       | 13435/61904 [6:46:10<18:24:10,  1.37s/it]
 22%|██▏       | 13436/61904 [6:46:11<18:17:27,  1.36s/it]
 22%|██▏       | 13437/61904 [6:46:12<18:17:16,  1.36s/it]
 22%|██▏       | 13438/61904 [6:46:14<18:19:45,  1.36s/it]
 22%|██▏       | 13439/61904 [6:46:15<18:02:04,  1.34s/it]
 22%|██▏       | 13440/61904 [6:46:16<18:09:38,  1.35s/it]
                                                          
{'loss': 2.7446, 'learning_rate': 1.7854272008297678e-07, 'epoch': 3.47}

 22%|██▏       | 13440/61904 [6:46:16<18:09:38,  1.35s/it]
 22%|██▏       | 13441/61904 [6:46:18<18:37:39,  1.38s/it]
 22%|██▏       | 13442/61904 [6:46:19<19:08:38,  1.42s/it]
 22%|██▏       | 13443/61904 [6:46:21<19:18:01,  1.43s/it]
 22%|██▏       | 13444/61904 [6:46:22<19:14:15,  1.43s/it]
 22%|██▏       | 13445/61904 [6:46:23<18:54:15,  1.40s/it]
 22%|██▏       | 13446/61904 [6:46:25<18:48:52,  1.40s/it]
 22%|██▏       | 13447/61904 [6:46:26<18:49:39,  1.40s/it]
 22%|██▏       | 13448/61904 [6:46:28<18:50:02,  1.40s/it]
 22%|██▏       | 13449/61904 [6:46:29<18:25:33,  1.37s/it]
 22%|██▏       | 13450/61904 [6:46:30<18:16:25,  1.36s/it]
 22%|██▏       | 13451/61904 [6:46:32<17:45:41,  1.32s/it]
 22%|██▏       | 13452/61904 [6:46:33<18:36:20,  1.38s/it]
 22%|██▏       | 13453/61904 [6:46:34<18:34:27,  1.38s/it]
 22%|██▏       | 13454/61904 [6:46:36<18:08:29,  1.35s/it]
 22%|██▏       | 13455/61904 [6:46:37<19:06:34,  1.42s/it]
 22%|██▏       | 13456/61904 [6:46:39<19:06:58,  1.42s/it]
 22%|██▏       | 13457/61904 [6:46:40<19:04:34,  1.42s/it]
 22%|██▏       | 13458/61904 [6:46:42<19:04:31,  1.42s/it]
 22%|██▏       | 13459/61904 [6:46:43<18:54:53,  1.41s/it]
 22%|██▏       | 13460/61904 [6:46:44<18:19:20,  1.36s/it]
                                                          
{'loss': 2.749, 'learning_rate': 1.7851030727343444e-07, 'epoch': 3.48}

 22%|██▏       | 13460/61904 [6:46:44<18:19:20,  1.36s/it]
 22%|██▏       | 13461/61904 [6:46:46<18:33:52,  1.38s/it]
 22%|██▏       | 13462/61904 [6:46:47<18:42:05,  1.39s/it]
 22%|██▏       | 13463/61904 [6:46:48<19:04:53,  1.42s/it]
 22%|██▏       | 13464/61904 [6:46:50<18:47:23,  1.40s/it]
 22%|██▏       | 13465/61904 [6:46:51<18:34:49,  1.38s/it]
 22%|██▏       | 13466/61904 [6:46:53<18:31:48,  1.38s/it]
 22%|██▏       | 13467/61904 [6:46:54<18:39:40,  1.39s/it]
 22%|██▏       | 13468/61904 [6:46:55<18:36:35,  1.38s/it]
 22%|██▏       | 13469/61904 [6:46:57<18:25:55,  1.37s/it]
 22%|██▏       | 13470/61904 [6:46:58<18:48:46,  1.40s/it]
 22%|██▏       | 13471/61904 [6:46:59<18:30:07,  1.38s/it]
 22%|██▏       | 13472/61904 [6:47:01<18:33:51,  1.38s/it]
 22%|██▏       | 13473/61904 [6:47:02<18:18:42,  1.36s/it]
 22%|██▏       | 13474/61904 [6:47:04<18:25:22,  1.37s/it]
 22%|██▏       | 13475/61904 [6:47:05<18:36:54,  1.38s/it]
 22%|██▏       | 13476/61904 [6:47:06<19:11:42,  1.43s/it]
 22%|██▏       | 13477/61904 [6:47:08<18:46:24,  1.40s/it]
 22%|██▏       | 13478/61904 [6:47:09<18:27:28,  1.37s/it]
 22%|██▏       | 13479/61904 [6:47:10<18:23:07,  1.37s/it]
 22%|██▏       | 13480/61904 [6:47:12<18:20:00,  1.36s/it]
                                                          
{'loss': 2.7231, 'learning_rate': 1.7847789446389213e-07, 'epoch': 3.48}

 22%|██▏       | 13480/61904 [6:47:12<18:20:00,  1.36s/it]
 22%|██▏       | 13481/61904 [6:47:13<18:58:53,  1.41s/it]
 22%|██▏       | 13482/61904 [6:47:15<18:31:41,  1.38s/it]
 22%|██▏       | 13483/61904 [6:47:16<19:11:34,  1.43s/it]
 22%|██▏       | 13484/61904 [6:47:18<19:17:56,  1.43s/it]
 22%|██▏       | 13485/61904 [6:47:19<20:24:00,  1.52s/it]
 22%|██▏       | 13486/61904 [6:47:21<19:40:07,  1.46s/it]
 22%|██▏       | 13487/61904 [6:47:22<19:17:17,  1.43s/it]
 22%|██▏       | 13488/61904 [6:47:23<19:04:32,  1.42s/it]
 22%|██▏       | 13489/61904 [6:47:25<19:01:27,  1.41s/it]
 22%|██▏       | 13490/61904 [6:47:26<18:14:39,  1.36s/it]
 22%|██▏       | 13491/61904 [6:47:27<17:54:34,  1.33s/it]
 22%|██▏       | 13492/61904 [6:47:29<17:46:59,  1.32s/it]
 22%|██▏       | 13493/61904 [6:47:30<18:21:59,  1.37s/it]
 22%|██▏       | 13494/61904 [6:47:31<17:50:06,  1.33s/it]
 22%|██▏       | 13495/61904 [6:47:33<17:37:30,  1.31s/it]
 22%|██▏       | 13496/61904 [6:47:34<17:53:35,  1.33s/it]
 22%|██▏       | 13497/61904 [6:47:35<18:01:00,  1.34s/it]
 22%|██▏       | 13498/61904 [6:47:37<17:42:46,  1.32s/it]
 22%|██▏       | 13499/61904 [6:47:38<18:01:46,  1.34s/it]
 22%|██▏       | 13500/61904 [6:47:39<18:14:40,  1.36s/it]
                                                          
{'loss': 2.7026, 'learning_rate': 1.784454816543498e-07, 'epoch': 3.49}

 22%|██▏       | 13500/61904 [6:47:39<18:14:40,  1.36s/it]
 22%|██▏       | 13501/61904 [6:47:41<18:23:49,  1.37s/it]
 22%|██▏       | 13502/61904 [6:47:42<18:01:30,  1.34s/it]
 22%|██▏       | 13503/61904 [6:47:43<17:45:27,  1.32s/it]
 22%|██▏       | 13504/61904 [6:47:45<18:23:35,  1.37s/it]
 22%|██▏       | 13505/61904 [6:47:46<18:46:02,  1.40s/it]
 22%|██▏       | 13506/61904 [6:47:48<18:34:02,  1.38s/it]
 22%|██▏       | 13507/61904 [6:47:49<18:03:35,  1.34s/it]
 22%|██▏       | 13508/61904 [6:47:50<18:12:19,  1.35s/it]
 22%|██▏       | 13509/61904 [6:47:52<18:11:12,  1.35s/it]
 22%|██▏       | 13510/61904 [6:47:53<18:06:12,  1.35s/it]
 22%|██▏       | 13511/61904 [6:47:54<18:14:11,  1.36s/it]
 22%|██▏       | 13512/61904 [6:47:56<18:36:08,  1.38s/it]
 22%|██▏       | 13513/61904 [6:47:57<18:22:08,  1.37s/it]
 22%|██▏       | 13514/61904 [6:47:58<18:24:31,  1.37s/it]
 22%|██▏       | 13515/61904 [6:48:00<18:35:18,  1.38s/it]
 22%|██▏       | 13516/61904 [6:48:02<19:40:36,  1.46s/it]
 22%|██▏       | 13517/61904 [6:48:03<19:04:02,  1.42s/it]
 22%|██▏       | 13518/61904 [6:48:04<19:48:05,  1.47s/it]
 22%|██▏       | 13519/61904 [6:48:06<19:17:23,  1.44s/it]
 22%|██▏       | 13520/61904 [6:48:07<19:00:57,  1.41s/it]
                                                          
{'loss': 2.7534, 'learning_rate': 1.7841306884480745e-07, 'epoch': 3.49}

 22%|██▏       | 13520/61904 [6:48:07<19:00:57,  1.41s/it]
 22%|██▏       | 13521/61904 [6:48:09<18:39:00,  1.39s/it]
 22%|██▏       | 13522/61904 [6:48:10<18:20:25,  1.36s/it]
 22%|██▏       | 13523/61904 [6:48:11<18:13:24,  1.36s/it]
 22%|██▏       | 13524/61904 [6:48:12<17:51:56,  1.33s/it]
 22%|██▏       | 13525/61904 [6:48:14<17:40:11,  1.31s/it]
 22%|██▏       | 13526/61904 [6:48:15<17:46:02,  1.32s/it]
 22%|██▏       | 13527/61904 [6:48:16<17:36:32,  1.31s/it]
 22%|██▏       | 13528/61904 [6:48:18<18:01:11,  1.34s/it]
 22%|██▏       | 13529/61904 [6:48:19<18:00:21,  1.34s/it]
 22%|██▏       | 13530/61904 [6:48:20<17:43:30,  1.32s/it]
 22%|██▏       | 13531/61904 [6:48:22<17:46:40,  1.32s/it]
 22%|██▏       | 13532/61904 [6:48:23<17:43:14,  1.32s/it]
 22%|██▏       | 13533/61904 [6:48:24<17:36:56,  1.31s/it]
 22%|██▏       | 13534/61904 [6:48:26<17:26:28,  1.30s/it]
 22%|██▏       | 13535/61904 [6:48:27<17:10:30,  1.28s/it]
 22%|██▏       | 13536/61904 [6:48:28<17:37:39,  1.31s/it]
 22%|██▏       | 13537/61904 [6:48:29<17:05:22,  1.27s/it]
 22%|██▏       | 13538/61904 [6:48:31<16:59:27,  1.26s/it]
 22%|██▏       | 13539/61904 [6:48:32<17:18:33,  1.29s/it]
 22%|██▏       | 13540/61904 [6:48:33<17:29:19,  1.30s/it]
                                                          
{'loss': 2.8366, 'learning_rate': 1.7838065603526514e-07, 'epoch': 3.5}

 22%|██▏       | 13540/61904 [6:48:33<17:29:19,  1.30s/it]
 22%|██▏       | 13541/61904 [6:48:35<17:50:41,  1.33s/it]
 22%|██▏       | 13542/61904 [6:48:36<18:02:43,  1.34s/it]
 22%|██▏       | 13543/61904 [6:48:37<18:19:55,  1.36s/it]
 22%|██▏       | 13544/61904 [6:48:39<18:09:25,  1.35s/it]
 22%|██▏       | 13545/61904 [6:48:40<18:13:27,  1.36s/it]
 22%|██▏       | 13546/61904 [6:48:42<18:43:08,  1.39s/it]
 22%|██▏       | 13547/61904 [6:48:43<18:57:28,  1.41s/it]
 22%|██▏       | 13548/61904 [6:48:44<18:49:05,  1.40s/it]
 22%|██▏       | 13549/61904 [6:48:46<18:47:18,  1.40s/it]
 22%|██▏       | 13550/61904 [6:48:47<18:22:34,  1.37s/it]
 22%|██▏       | 13551/61904 [6:48:49<18:25:43,  1.37s/it]
 22%|██▏       | 13552/61904 [6:48:50<18:08:15,  1.35s/it]
 22%|██▏       | 13553/61904 [6:48:51<18:11:52,  1.35s/it]
 22%|██▏       | 13554/61904 [6:48:53<18:35:00,  1.38s/it]
 22%|██▏       | 13555/61904 [6:48:54<18:57:21,  1.41s/it]
 22%|██▏       | 13556/61904 [6:48:55<18:14:39,  1.36s/it]
 22%|██▏       | 13557/61904 [6:48:57<18:21:52,  1.37s/it]
 22%|██▏       | 13558/61904 [6:48:58<18:00:23,  1.34s/it]
 22%|██▏       | 13559/61904 [6:48:59<17:35:00,  1.31s/it]
 22%|██▏       | 13560/61904 [6:49:01<18:02:36,  1.34s/it]
                                                          
{'loss': 2.7885, 'learning_rate': 1.7834824322572278e-07, 'epoch': 3.5}

 22%|██▏       | 13560/61904 [6:49:01<18:02:36,  1.34s/it]
 22%|██▏       | 13561/61904 [6:49:02<18:15:13,  1.36s/it]
 22%|██▏       | 13562/61904 [6:49:03<18:23:38,  1.37s/it]
 22%|██▏       | 13563/61904 [6:49:05<17:51:08,  1.33s/it]
 22%|██▏       | 13564/61904 [6:49:06<17:43:51,  1.32s/it]
 22%|██▏       | 13565/61904 [6:49:07<17:49:29,  1.33s/it]
 22%|██▏       | 13566/61904 [6:49:09<18:13:13,  1.36s/it]
 22%|██▏       | 13567/61904 [6:49:10<18:03:15,  1.34s/it]
 22%|██▏       | 13568/61904 [6:49:11<18:11:14,  1.35s/it]
 22%|██▏       | 13569/61904 [6:49:13<17:56:01,  1.34s/it]
 22%|██▏       | 13570/61904 [6:49:14<18:08:52,  1.35s/it]
 22%|██▏       | 13571/61904 [6:49:15<17:45:12,  1.32s/it]
 22%|██▏       | 13572/61904 [6:49:17<18:40:38,  1.39s/it]
 22%|██▏       | 13573/61904 [6:49:18<18:56:59,  1.41s/it]
 22%|██▏       | 13574/61904 [6:49:20<19:40:03,  1.47s/it]
 22%|██▏       | 13575/61904 [6:49:22<19:46:35,  1.47s/it]
 22%|██▏       | 13576/61904 [6:49:23<18:40:53,  1.39s/it]
 22%|██▏       | 13577/61904 [6:49:24<18:48:43,  1.40s/it]
 22%|██▏       | 13578/61904 [6:49:26<19:01:42,  1.42s/it]
 22%|██▏       | 13579/61904 [6:49:27<19:03:11,  1.42s/it]
 22%|██▏       | 13580/61904 [6:49:28<19:20:53,  1.44s/it]
                                                          
{'loss': 2.7273, 'learning_rate': 1.7831583041618047e-07, 'epoch': 3.51}

 22%|██▏       | 13580/61904 [6:49:28<19:20:53,  1.44s/it]
 22%|██▏       | 13581/61904 [6:49:30<18:48:33,  1.40s/it]
 22%|██▏       | 13582/61904 [6:49:31<18:16:31,  1.36s/it]
 22%|██▏       | 13583/61904 [6:49:32<18:18:52,  1.36s/it]
 22%|██▏       | 13584/61904 [6:49:34<18:41:01,  1.39s/it]
 22%|██▏       | 13585/61904 [6:49:35<18:24:40,  1.37s/it]
 22%|██▏       | 13586/61904 [6:49:37<18:31:13,  1.38s/it]
 22%|██▏       | 13587/61904 [6:49:38<18:48:07,  1.40s/it]
 22%|██▏       | 13588/61904 [6:49:39<18:28:12,  1.38s/it]
 22%|██▏       | 13589/61904 [6:49:41<18:33:10,  1.38s/it]
 22%|██▏       | 13590/61904 [6:49:42<18:31:33,  1.38s/it]
 22%|██▏       | 13591/61904 [6:49:43<18:13:59,  1.36s/it]
 22%|██▏       | 13592/61904 [6:49:45<17:59:14,  1.34s/it]
 22%|██▏       | 13593/61904 [6:49:46<17:53:44,  1.33s/it]
 22%|██▏       | 13594/61904 [6:49:47<17:38:22,  1.31s/it]
 22%|██▏       | 13595/61904 [6:49:49<17:31:06,  1.31s/it]
 22%|██▏       | 13596/61904 [6:49:50<17:46:46,  1.32s/it]
 22%|██▏       | 13597/61904 [6:49:51<18:14:52,  1.36s/it]
 22%|██▏       | 13598/61904 [6:49:53<18:14:44,  1.36s/it]
 22%|██▏       | 13599/61904 [6:49:54<18:05:44,  1.35s/it]
 22%|██▏       | 13600/61904 [6:49:56<19:00:12,  1.42s/it]
                                                          
{'loss': 2.7864, 'learning_rate': 1.7828341760663813e-07, 'epoch': 3.51}

 22%|██▏       | 13600/61904 [6:49:56<19:00:12,  1.42s/it]
 22%|██▏       | 13601/61904 [6:49:57<18:43:56,  1.40s/it]
 22%|██▏       | 13602/61904 [6:49:58<18:42:15,  1.39s/it]
 22%|██▏       | 13603/61904 [6:50:00<18:22:14,  1.37s/it]
 22%|██▏       | 13604/61904 [6:50:01<17:51:51,  1.33s/it]
 22%|██▏       | 13605/61904 [6:50:02<17:54:53,  1.34s/it]
 22%|██▏       | 13606/61904 [6:50:04<18:53:09,  1.41s/it]
 22%|██▏       | 13607/61904 [6:50:05<18:12:17,  1.36s/it]
 22%|██▏       | 13608/61904 [6:50:07<18:29:11,  1.38s/it]
 22%|██▏       | 13609/61904 [6:50:08<18:11:37,  1.36s/it]
 22%|██▏       | 13610/61904 [6:50:09<18:17:53,  1.36s/it]
 22%|██▏       | 13611/61904 [6:50:11<18:23:00,  1.37s/it]
 22%|██▏       | 13612/61904 [6:50:12<17:59:20,  1.34s/it]
 22%|██▏       | 13613/61904 [6:50:13<17:38:12,  1.31s/it]
 22%|██▏       | 13614/61904 [6:50:15<17:37:14,  1.31s/it]
 22%|██▏       | 13615/61904 [6:50:16<17:50:29,  1.33s/it]
 22%|██▏       | 13616/61904 [6:50:17<17:53:18,  1.33s/it]
 22%|██▏       | 13617/61904 [6:50:19<17:53:53,  1.33s/it]
 22%|██▏       | 13618/61904 [6:50:20<18:00:51,  1.34s/it]
 22%|██▏       | 13619/61904 [6:50:21<18:15:25,  1.36s/it]
 22%|██▏       | 13620/61904 [6:50:23<18:44:09,  1.40s/it]
                                                          
{'loss': 2.7448, 'learning_rate': 1.782510047970958e-07, 'epoch': 3.52}

 22%|██▏       | 13620/61904 [6:50:23<18:44:09,  1.40s/it]
 22%|██▏       | 13621/61904 [6:50:24<18:43:02,  1.40s/it]
 22%|██▏       | 13622/61904 [6:50:26<18:23:43,  1.37s/it]
 22%|██▏       | 13623/61904 [6:50:27<18:14:41,  1.36s/it]
 22%|██▏       | 13624/61904 [6:50:28<18:30:05,  1.38s/it]
 22%|██▏       | 13625/61904 [6:50:30<18:17:15,  1.36s/it]
 22%|██▏       | 13626/61904 [6:50:31<18:39:19,  1.39s/it]
 22%|██▏       | 13627/61904 [6:50:32<18:19:42,  1.37s/it]
 22%|██▏       | 13628/61904 [6:50:34<18:26:09,  1.37s/it]
 22%|██▏       | 13629/61904 [6:50:35<17:58:04,  1.34s/it]
 22%|██▏       | 13630/61904 [6:50:36<17:55:14,  1.34s/it]
 22%|██▏       | 13631/61904 [6:50:38<17:32:25,  1.31s/it]
 22%|██▏       | 13632/61904 [6:50:39<17:34:31,  1.31s/it]
 22%|██▏       | 13633/61904 [6:50:40<17:54:40,  1.34s/it]
 22%|██▏       | 13634/61904 [6:50:42<18:02:18,  1.35s/it]
 22%|██▏       | 13635/61904 [6:50:43<17:59:12,  1.34s/it]
 22%|██▏       | 13636/61904 [6:50:45<18:57:40,  1.41s/it]
 22%|██▏       | 13637/61904 [6:50:46<18:45:44,  1.40s/it]
 22%|██▏       | 13638/61904 [6:50:47<18:01:19,  1.34s/it]
 22%|██▏       | 13639/61904 [6:50:48<17:51:47,  1.33s/it]
 22%|██▏       | 13640/61904 [6:50:50<17:18:42,  1.29s/it]
                                                          
{'loss': 2.7384, 'learning_rate': 1.7821859198755348e-07, 'epoch': 3.53}

 22%|██▏       | 13640/61904 [6:50:50<17:18:42,  1.29s/it]
 22%|██▏       | 13641/61904 [6:50:51<17:31:50,  1.31s/it]
 22%|██▏       | 13642/61904 [6:50:52<17:44:07,  1.32s/it]
 22%|██▏       | 13643/61904 [6:50:54<18:33:20,  1.38s/it]
 22%|██▏       | 13644/61904 [6:50:55<18:15:58,  1.36s/it]
 22%|██▏       | 13645/61904 [6:50:57<18:28:31,  1.38s/it]
 22%|██▏       | 13646/61904 [6:50:58<19:02:44,  1.42s/it]
 22%|██▏       | 13647/61904 [6:50:59<18:17:32,  1.36s/it]
 22%|██▏       | 13648/61904 [6:51:01<17:49:20,  1.33s/it]
 22%|██▏       | 13649/61904 [6:51:02<17:59:42,  1.34s/it]
 22%|██▏       | 13650/61904 [6:51:03<18:06:29,  1.35s/it]
 22%|██▏       | 13651/61904 [6:51:05<17:51:19,  1.33s/it]
 22%|██▏       | 13652/61904 [6:51:06<17:44:41,  1.32s/it]
 22%|██▏       | 13653/61904 [6:51:07<18:05:30,  1.35s/it]
 22%|██▏       | 13654/61904 [6:51:09<17:51:39,  1.33s/it]
 22%|██▏       | 13655/61904 [6:51:10<18:36:25,  1.39s/it]
 22%|██▏       | 13656/61904 [6:51:11<18:20:39,  1.37s/it]
 22%|██▏       | 13657/61904 [6:51:13<18:45:34,  1.40s/it]
 22%|██▏       | 13658/61904 [6:51:14<18:39:07,  1.39s/it]
 22%|██▏       | 13659/61904 [6:51:16<18:38:23,  1.39s/it]
 22%|██▏       | 13660/61904 [6:51:17<18:42:04,  1.40s/it]
                                                          
{'loss': 2.7694, 'learning_rate': 1.7818617917801114e-07, 'epoch': 3.53}

 22%|██▏       | 13660/61904 [6:51:17<18:42:04,  1.40s/it]
 22%|██▏       | 13661/61904 [6:51:18<18:29:26,  1.38s/it]
 22%|██▏       | 13662/61904 [6:51:20<18:23:39,  1.37s/it]
 22%|██▏       | 13663/61904 [6:51:21<18:24:40,  1.37s/it]
 22%|██▏       | 13664/61904 [6:51:23<18:51:10,  1.41s/it]
 22%|██▏       | 13665/61904 [6:51:24<19:01:35,  1.42s/it]
 22%|██▏       | 13666/61904 [6:51:25<18:21:31,  1.37s/it]
 22%|██▏       | 13667/61904 [6:51:27<18:40:23,  1.39s/it]
 22%|██▏       | 13668/61904 [6:51:28<19:05:58,  1.43s/it]
 22%|██▏       | 13669/61904 [6:51:30<19:05:52,  1.43s/it]
 22%|██▏       | 13670/61904 [6:51:31<18:21:23,  1.37s/it]
 22%|██▏       | 13671/61904 [6:51:32<18:23:56,  1.37s/it]
 22%|██▏       | 13672/61904 [6:51:34<18:01:14,  1.35s/it]
 22%|██▏       | 13673/61904 [6:51:35<18:06:08,  1.35s/it]
 22%|██▏       | 13674/61904 [6:51:36<17:35:52,  1.31s/it]
 22%|██▏       | 13675/61904 [6:51:38<17:29:02,  1.31s/it]
 22%|██▏       | 13676/61904 [6:51:39<17:49:15,  1.33s/it]
 22%|██▏       | 13677/61904 [6:51:40<18:09:34,  1.36s/it]
 22%|██▏       | 13678/61904 [6:51:42<18:11:20,  1.36s/it]
 22%|██▏       | 13679/61904 [6:51:43<18:00:19,  1.34s/it]
 22%|██▏       | 13680/61904 [6:51:44<18:09:40,  1.36s/it]
                                                          
{'loss': 2.7501, 'learning_rate': 1.781537663684688e-07, 'epoch': 3.54}

 22%|██▏       | 13680/61904 [6:51:44<18:09:40,  1.36s/it]
 22%|██▏       | 13681/61904 [6:51:46<18:00:53,  1.34s/it]
 22%|██▏       | 13682/61904 [6:51:47<17:32:09,  1.31s/it]
 22%|██▏       | 13683/61904 [6:51:48<17:53:24,  1.34s/it]
 22%|██▏       | 13684/61904 [6:51:50<17:55:28,  1.34s/it]
 22%|██▏       | 13685/61904 [6:51:51<17:51:12,  1.33s/it]
 22%|██▏       | 13686/61904 [6:51:52<17:41:11,  1.32s/it]
 22%|██▏       | 13687/61904 [6:51:54<17:43:16,  1.32s/it]
 22%|██▏       | 13688/61904 [6:51:55<17:23:43,  1.30s/it]
 22%|██▏       | 13689/61904 [6:51:56<17:28:08,  1.30s/it]
 22%|██▏       | 13690/61904 [6:51:58<17:43:52,  1.32s/it]
 22%|██▏       | 13691/61904 [6:51:59<17:51:25,  1.33s/it]
 22%|██▏       | 13692/61904 [6:52:00<17:47:01,  1.33s/it]
 22%|██▏       | 13693/61904 [6:52:02<17:51:22,  1.33s/it]
 22%|██▏       | 13694/61904 [6:52:03<17:49:09,  1.33s/it]
 22%|██▏       | 13695/61904 [6:52:04<17:27:07,  1.30s/it]
 22%|██▏       | 13696/61904 [6:52:06<17:55:13,  1.34s/it]
 22%|██▏       | 13697/61904 [6:52:07<17:51:20,  1.33s/it]
 22%|██▏       | 13698/61904 [6:52:08<18:20:38,  1.37s/it]
 22%|██▏       | 13699/61904 [6:52:10<17:59:20,  1.34s/it]
 22%|██▏       | 13700/61904 [6:52:11<18:01:31,  1.35s/it]
                                                          
{'loss': 2.8046, 'learning_rate': 1.781213535589265e-07, 'epoch': 3.54}

 22%|██▏       | 13700/61904 [6:52:11<18:01:31,  1.35s/it]
 22%|██▏       | 13701/61904 [6:52:12<18:21:32,  1.37s/it]
 22%|██▏       | 13702/61904 [6:52:14<18:22:36,  1.37s/it]
 22%|██▏       | 13703/61904 [6:52:15<18:48:35,  1.40s/it]
 22%|██▏       | 13704/61904 [6:52:17<19:12:47,  1.44s/it]
 22%|██▏       | 13705/61904 [6:52:18<19:14:53,  1.44s/it]
 22%|██▏       | 13706/61904 [6:52:20<19:40:55,  1.47s/it]
 22%|██▏       | 13707/61904 [6:52:21<19:38:08,  1.47s/it]
 22%|██▏       | 13708/61904 [6:52:23<19:06:48,  1.43s/it]
 22%|██▏       | 13709/61904 [6:52:24<19:13:47,  1.44s/it]
 22%|██▏       | 13710/61904 [6:52:25<18:22:01,  1.37s/it]
 22%|██▏       | 13711/61904 [6:52:27<18:06:55,  1.35s/it]
 22%|██▏       | 13712/61904 [6:52:28<18:07:53,  1.35s/it]
 22%|██▏       | 13713/61904 [6:52:29<17:49:23,  1.33s/it]
 22%|██▏       | 13714/61904 [6:52:31<18:43:04,  1.40s/it]
 22%|██▏       | 13715/61904 [6:52:32<18:55:16,  1.41s/it]
 22%|██▏       | 13716/61904 [6:52:33<18:26:43,  1.38s/it]
 22%|██▏       | 13717/61904 [6:52:35<18:22:20,  1.37s/it]
 22%|██▏       | 13718/61904 [6:52:36<18:27:18,  1.38s/it]
 22%|██▏       | 13719/61904 [6:52:38<18:15:02,  1.36s/it]
 22%|██▏       | 13720/61904 [6:52:39<17:51:26,  1.33s/it]
                                                          
{'loss': 2.752, 'learning_rate': 1.7808894074938413e-07, 'epoch': 3.55}

 22%|██▏       | 13720/61904 [6:52:39<17:51:26,  1.33s/it]
 22%|██▏       | 13721/61904 [6:52:40<18:20:31,  1.37s/it]
 22%|██▏       | 13722/61904 [6:52:42<20:02:05,  1.50s/it]
 22%|██▏       | 13723/61904 [6:52:43<19:37:59,  1.47s/it]
 22%|██▏       | 13724/61904 [6:52:45<18:52:10,  1.41s/it]
 22%|██▏       | 13725/61904 [6:52:46<18:11:00,  1.36s/it]
 22%|██▏       | 13726/61904 [6:52:47<18:33:18,  1.39s/it]
 22%|██▏       | 13727/61904 [6:52:49<18:29:26,  1.38s/it]
 22%|██▏       | 13728/61904 [6:52:50<18:26:59,  1.38s/it]
 22%|██▏       | 13729/61904 [6:52:52<18:37:10,  1.39s/it]
 22%|██▏       | 13730/61904 [6:52:53<18:08:01,  1.36s/it]
 22%|██▏       | 13731/61904 [6:52:54<18:24:09,  1.38s/it]
 22%|██▏       | 13732/61904 [6:52:56<18:08:43,  1.36s/it]
 22%|██▏       | 13733/61904 [6:52:57<17:40:54,  1.32s/it]
 22%|██▏       | 13734/61904 [6:52:59<19:05:32,  1.43s/it]
 22%|██▏       | 13735/61904 [6:53:00<18:23:52,  1.38s/it]
 22%|██▏       | 13736/61904 [6:53:01<18:03:44,  1.35s/it]
 22%|██▏       | 13737/61904 [6:53:02<18:13:26,  1.36s/it]
 22%|██▏       | 13738/61904 [6:53:04<17:56:21,  1.34s/it]
 22%|██▏       | 13739/61904 [6:53:05<17:42:26,  1.32s/it]
 22%|██▏       | 13740/61904 [6:53:06<17:46:52,  1.33s/it]
                                                          
{'loss': 2.771, 'learning_rate': 1.7805652793984181e-07, 'epoch': 3.55}

 22%|██▏       | 13740/61904 [6:53:06<17:46:52,  1.33s/it]
 22%|██▏       | 13741/61904 [6:53:08<17:25:36,  1.30s/it]
 22%|██▏       | 13742/61904 [6:53:09<17:17:42,  1.29s/it]
 22%|██▏       | 13743/61904 [6:53:10<17:07:08,  1.28s/it]
 22%|██▏       | 13744/61904 [6:53:11<17:11:49,  1.29s/it]
 22%|██▏       | 13745/61904 [6:53:13<17:27:47,  1.31s/it]
 22%|██▏       | 13746/61904 [6:53:14<17:41:42,  1.32s/it]
 22%|██▏       | 13747/61904 [6:53:16<18:26:34,  1.38s/it]
 22%|██▏       | 13748/61904 [6:53:17<18:32:35,  1.39s/it]
 22%|██▏       | 13749/61904 [6:53:18<18:07:04,  1.35s/it]
 22%|██▏       | 13750/61904 [6:53:20<18:13:29,  1.36s/it]
 22%|██▏       | 13751/61904 [6:53:21<18:15:00,  1.36s/it]
 22%|██▏       | 13752/61904 [6:53:23<18:38:51,  1.39s/it]
 22%|██▏       | 13753/61904 [6:53:24<18:16:13,  1.37s/it]
 22%|██▏       | 13754/61904 [6:53:25<18:13:11,  1.36s/it]
 22%|██▏       | 13755/61904 [6:53:26<17:54:15,  1.34s/it]
 22%|██▏       | 13756/61904 [6:53:28<18:15:42,  1.37s/it]
 22%|██▏       | 13757/61904 [6:53:29<18:01:25,  1.35s/it]
 22%|██▏       | 13758/61904 [6:53:31<18:11:27,  1.36s/it]
 22%|██▏       | 13759/61904 [6:53:32<18:11:45,  1.36s/it]
 22%|██▏       | 13760/61904 [6:53:33<18:05:28,  1.35s/it]
                                                          
{'loss': 2.7431, 'learning_rate': 1.780241151302995e-07, 'epoch': 3.56}

 22%|██▏       | 13760/61904 [6:53:33<18:05:28,  1.35s/it]
 22%|██▏       | 13761/61904 [6:53:35<18:12:27,  1.36s/it]
 22%|██▏       | 13762/61904 [6:53:36<17:49:18,  1.33s/it]
 22%|██▏       | 13763/61904 [6:53:37<17:54:11,  1.34s/it]
 22%|██▏       | 13764/61904 [6:53:39<17:55:28,  1.34s/it]
 22%|██▏       | 13765/61904 [6:53:40<17:46:42,  1.33s/it]
 22%|██▏       | 13766/61904 [6:53:41<18:10:32,  1.36s/it]
 22%|██▏       | 13767/61904 [6:53:43<17:57:39,  1.34s/it]
 22%|██▏       | 13768/61904 [6:53:44<18:31:47,  1.39s/it]
 22%|██▏       | 13769/61904 [6:53:46<20:17:43,  1.52s/it]
 22%|██▏       | 13770/61904 [6:53:47<19:03:47,  1.43s/it]
 22%|██▏       | 13771/61904 [6:53:49<18:33:30,  1.39s/it]
 22%|██▏       | 13772/61904 [6:53:50<18:47:21,  1.41s/it]
 22%|██▏       | 13773/61904 [6:53:51<18:49:40,  1.41s/it]
 22%|██▏       | 13774/61904 [6:53:53<19:01:08,  1.42s/it]
 22%|██▏       | 13775/61904 [6:53:54<18:25:19,  1.38s/it]
 22%|██▏       | 13776/61904 [6:53:55<18:10:38,  1.36s/it]
 22%|██▏       | 13777/61904 [6:53:57<18:16:29,  1.37s/it]
 22%|██▏       | 13778/61904 [6:53:58<18:21:31,  1.37s/it]
 22%|██▏       | 13779/61904 [6:54:00<18:11:20,  1.36s/it]
 22%|██▏       | 13780/61904 [6:54:01<18:20:26,  1.37s/it]
                                                          
{'loss': 2.7601, 'learning_rate': 1.7799170232075714e-07, 'epoch': 3.56}

 22%|██▏       | 13780/61904 [6:54:01<18:20:26,  1.37s/it]
 22%|██▏       | 13781/61904 [6:54:02<17:58:00,  1.34s/it]
 22%|██▏       | 13782/61904 [6:54:03<17:39:10,  1.32s/it]
 22%|██▏       | 13783/61904 [6:54:05<17:46:03,  1.33s/it]
 22%|██▏       | 13784/61904 [6:54:06<17:56:25,  1.34s/it]
 22%|██▏       | 13785/61904 [6:54:08<18:07:09,  1.36s/it]
 22%|██▏       | 13786/61904 [6:54:09<17:48:17,  1.33s/it]
 22%|██▏       | 13787/61904 [6:54:10<18:16:37,  1.37s/it]
 22%|██▏       | 13788/61904 [6:54:12<18:13:05,  1.36s/it]
 22%|██▏       | 13789/61904 [6:54:13<17:56:32,  1.34s/it]
 22%|██▏       | 13790/61904 [6:54:14<18:17:06,  1.37s/it]
 22%|██▏       | 13791/61904 [6:54:16<18:15:37,  1.37s/it]
 22%|██▏       | 13792/61904 [6:54:17<18:05:15,  1.35s/it]
 22%|██▏       | 13793/61904 [6:54:18<18:04:45,  1.35s/it]
 22%|██▏       | 13794/61904 [6:54:20<18:01:42,  1.35s/it]
 22%|██▏       | 13795/61904 [6:54:21<18:25:28,  1.38s/it]
 22%|██▏       | 13796/61904 [6:54:22<18:04:57,  1.35s/it]
 22%|██▏       | 13797/61904 [6:54:24<18:22:42,  1.38s/it]
 22%|██▏       | 13798/61904 [6:54:25<18:29:51,  1.38s/it]
 22%|██▏       | 13799/61904 [6:54:27<18:28:15,  1.38s/it]
 22%|██▏       | 13800/61904 [6:54:28<18:07:20,  1.36s/it]
                                                          
{'loss': 2.8301, 'learning_rate': 1.7795928951121483e-07, 'epoch': 3.57}

 22%|██▏       | 13800/61904 [6:54:28<18:07:20,  1.36s/it]
 22%|██▏       | 13801/61904 [6:54:29<17:41:20,  1.32s/it]
 22%|██▏       | 13802/61904 [6:54:30<17:16:25,  1.29s/it]
 22%|██▏       | 13803/61904 [6:54:32<17:32:02,  1.31s/it]
 22%|██▏       | 13804/61904 [6:54:33<17:10:43,  1.29s/it]
 22%|██▏       | 13805/61904 [6:54:34<17:33:08,  1.31s/it]
 22%|██▏       | 13806/61904 [6:54:36<17:59:25,  1.35s/it]
 22%|██▏       | 13807/61904 [6:54:37<19:01:43,  1.42s/it]
 22%|██▏       | 13808/61904 [6:54:39<18:51:40,  1.41s/it]
 22%|██▏       | 13809/61904 [6:54:40<18:26:59,  1.38s/it]
 22%|██▏       | 13810/61904 [6:54:42<18:40:30,  1.40s/it]
 22%|██▏       | 13811/61904 [6:54:43<18:51:02,  1.41s/it]
 22%|██▏       | 13812/61904 [6:54:45<19:25:39,  1.45s/it]
 22%|██▏       | 13813/61904 [6:54:46<18:51:17,  1.41s/it]
 22%|██▏       | 13814/61904 [6:54:47<18:22:20,  1.38s/it]
 22%|██▏       | 13815/61904 [6:54:48<18:07:34,  1.36s/it]
 22%|██▏       | 13816/61904 [6:54:50<18:18:31,  1.37s/it]
 22%|██▏       | 13817/61904 [6:54:51<18:34:13,  1.39s/it]
 22%|██▏       | 13818/61904 [6:54:53<18:07:30,  1.36s/it]
 22%|██▏       | 13819/61904 [6:54:54<17:40:35,  1.32s/it]
 22%|██▏       | 13820/61904 [6:54:55<17:50:34,  1.34s/it]
                                                          
{'loss': 2.7157, 'learning_rate': 1.779268767016725e-07, 'epoch': 3.57}

 22%|██▏       | 13820/61904 [6:54:55<17:50:34,  1.34s/it]
 22%|██▏       | 13821/61904 [6:54:57<17:52:36,  1.34s/it]
 22%|██▏       | 13822/61904 [6:54:58<17:59:27,  1.35s/it]
 22%|██▏       | 13823/61904 [6:54:59<17:23:20,  1.30s/it]
 22%|██▏       | 13824/61904 [6:55:01<17:58:29,  1.35s/it]
 22%|██▏       | 13825/61904 [6:55:02<18:11:51,  1.36s/it]
 22%|██▏       | 13826/61904 [6:55:03<18:39:50,  1.40s/it]
 22%|██▏       | 13827/61904 [6:55:05<18:31:02,  1.39s/it]
 22%|██▏       | 13828/61904 [6:55:06<18:13:31,  1.36s/it]
 22%|██▏       | 13829/61904 [6:55:07<18:11:36,  1.36s/it]
 22%|██▏       | 13830/61904 [6:55:09<18:33:29,  1.39s/it]
 22%|██▏       | 13831/61904 [6:55:10<18:20:03,  1.37s/it]
 22%|██▏       | 13832/61904 [6:55:12<17:54:36,  1.34s/it]
 22%|██▏       | 13833/61904 [6:55:13<17:47:48,  1.33s/it]
 22%|██▏       | 13834/61904 [6:55:14<18:11:30,  1.36s/it]
 22%|██▏       | 13835/61904 [6:55:16<18:06:58,  1.36s/it]
 22%|██▏       | 13836/61904 [6:55:17<18:19:04,  1.37s/it]
 22%|██▏       | 13837/61904 [6:55:19<18:42:44,  1.40s/it]
 22%|██▏       | 13838/61904 [6:55:20<18:33:48,  1.39s/it]
 22%|██▏       | 13839/61904 [6:55:21<19:12:27,  1.44s/it]
 22%|██▏       | 13840/61904 [6:55:23<19:36:37,  1.47s/it]
                                                          
{'loss': 2.7602, 'learning_rate': 1.7789446389213015e-07, 'epoch': 3.58}

 22%|██▏       | 13840/61904 [6:55:23<19:36:37,  1.47s/it]
 22%|██▏       | 13841/61904 [6:55:24<19:30:48,  1.46s/it]
 22%|██▏       | 13842/61904 [6:55:26<19:59:30,  1.50s/it]
 22%|██▏       | 13843/61904 [6:55:27<19:22:03,  1.45s/it]
 22%|██▏       | 13844/61904 [6:55:29<19:24:53,  1.45s/it]
 22%|██▏       | 13845/61904 [6:55:30<19:10:56,  1.44s/it]
 22%|██▏       | 13846/61904 [6:55:32<19:19:53,  1.45s/it]
 22%|██▏       | 13847/61904 [6:55:33<18:38:21,  1.40s/it]
 22%|██▏       | 13848/61904 [6:55:34<18:46:58,  1.41s/it]
 22%|██▏       | 13849/61904 [6:55:36<18:01:14,  1.35s/it]
 22%|██▏       | 13850/61904 [6:55:37<18:12:51,  1.36s/it]
 22%|██▏       | 13851/61904 [6:55:39<19:11:51,  1.44s/it]
 22%|██▏       | 13852/61904 [6:55:40<19:21:24,  1.45s/it]
 22%|██▏       | 13853/61904 [6:55:42<19:21:19,  1.45s/it]
 22%|██▏       | 13854/61904 [6:55:43<19:15:43,  1.44s/it]
 22%|██▏       | 13855/61904 [6:55:44<19:12:34,  1.44s/it]
 22%|██▏       | 13856/61904 [6:55:46<20:33:43,  1.54s/it]
 22%|██▏       | 13857/61904 [6:55:48<20:09:49,  1.51s/it]
 22%|██▏       | 13858/61904 [6:55:49<19:54:18,  1.49s/it]
 22%|██▏       | 13859/61904 [6:55:50<19:37:48,  1.47s/it]
 22%|██▏       | 13860/61904 [6:55:52<19:45:05,  1.48s/it]
                                                          
{'loss': 2.7926, 'learning_rate': 1.7786205108258784e-07, 'epoch': 3.58}

 22%|██▏       | 13860/61904 [6:55:52<19:45:05,  1.48s/it]
 22%|██▏       | 13861/61904 [6:55:53<19:22:27,  1.45s/it]
 22%|██▏       | 13862/61904 [6:55:55<18:40:01,  1.40s/it]
 22%|██▏       | 13863/61904 [6:55:56<19:10:26,  1.44s/it]
 22%|██▏       | 13864/61904 [6:55:57<18:28:13,  1.38s/it]
 22%|██▏       | 13865/61904 [6:55:59<17:47:56,  1.33s/it]
 22%|██▏       | 13866/61904 [6:56:00<17:26:26,  1.31s/it]
 22%|██▏       | 13867/61904 [6:56:01<18:15:42,  1.37s/it]
 22%|██▏       | 13868/61904 [6:56:03<18:21:10,  1.38s/it]
 22%|██▏       | 13869/61904 [6:56:04<18:18:47,  1.37s/it]
 22%|██▏       | 13870/61904 [6:56:06<18:19:14,  1.37s/it]
 22%|██▏       | 13871/61904 [6:56:07<18:12:16,  1.36s/it]
 22%|██▏       | 13872/61904 [6:56:08<17:43:14,  1.33s/it]
 22%|██▏       | 13873/61904 [6:56:09<17:51:09,  1.34s/it]
 22%|██▏       | 13874/61904 [6:56:11<18:03:50,  1.35s/it]
 22%|██▏       | 13875/61904 [6:56:12<17:56:40,  1.35s/it]
 22%|██▏       | 13876/61904 [6:56:14<18:09:01,  1.36s/it]
 22%|██▏       | 13877/61904 [6:56:15<17:57:10,  1.35s/it]
 22%|██▏       | 13878/61904 [6:56:16<17:54:17,  1.34s/it]
 22%|██▏       | 13879/61904 [6:56:18<18:26:09,  1.38s/it]
 22%|██▏       | 13880/61904 [6:56:19<18:24:56,  1.38s/it]
                                                          
{'loss': 2.76, 'learning_rate': 1.778296382730455e-07, 'epoch': 3.59}

 22%|██▏       | 13880/61904 [6:56:19<18:24:56,  1.38s/it]
 22%|██▏       | 13881/61904 [6:56:20<18:13:38,  1.37s/it]
 22%|██▏       | 13882/61904 [6:56:22<18:30:35,  1.39s/it]
 22%|██▏       | 13883/61904 [6:56:23<18:49:19,  1.41s/it]
 22%|██▏       | 13884/61904 [6:56:25<19:23:26,  1.45s/it]
 22%|██▏       | 13885/61904 [6:56:26<18:56:37,  1.42s/it]
 22%|██▏       | 13886/61904 [6:56:28<19:02:29,  1.43s/it]
 22%|██▏       | 13887/61904 [6:56:29<18:45:16,  1.41s/it]
 22%|██▏       | 13888/61904 [6:56:30<18:33:43,  1.39s/it]
 22%|██▏       | 13889/61904 [6:56:32<19:01:18,  1.43s/it]
 22%|██▏       | 13890/61904 [6:56:33<19:25:03,  1.46s/it]
 22%|██▏       | 13891/61904 [6:56:35<19:09:04,  1.44s/it]
 22%|██▏       | 13892/61904 [6:56:36<18:43:21,  1.40s/it]
 22%|██▏       | 13893/61904 [6:56:38<18:52:32,  1.42s/it]
 22%|██▏       | 13894/61904 [6:56:39<18:15:18,  1.37s/it]
 22%|██▏       | 13895/61904 [6:56:40<18:13:39,  1.37s/it]
 22%|██▏       | 13896/61904 [6:56:42<17:58:57,  1.35s/it]
 22%|██▏       | 13897/61904 [6:56:43<17:59:07,  1.35s/it]
 22%|██▏       | 13898/61904 [6:56:44<18:48:11,  1.41s/it]
 22%|██▏       | 13899/61904 [6:56:46<19:04:38,  1.43s/it]
 22%|██▏       | 13900/61904 [6:56:47<18:58:31,  1.42s/it]
                                                          
{'loss': 2.735, 'learning_rate': 1.7779722546350316e-07, 'epoch': 3.59}

 22%|██▏       | 13900/61904 [6:56:47<18:58:31,  1.42s/it]
 22%|██▏       | 13901/61904 [6:56:49<18:35:28,  1.39s/it]
 22%|██▏       | 13902/61904 [6:56:50<18:24:12,  1.38s/it]
 22%|██▏       | 13903/61904 [6:56:51<18:07:40,  1.36s/it]
 22%|██▏       | 13904/61904 [6:56:53<18:15:55,  1.37s/it]
 22%|██▏       | 13905/61904 [6:56:54<18:22:35,  1.38s/it]
 22%|██▏       | 13906/61904 [6:56:55<18:23:40,  1.38s/it]
 22%|██▏       | 13907/61904 [6:56:57<19:12:48,  1.44s/it]
 22%|██▏       | 13908/61904 [6:56:58<19:00:00,  1.43s/it]
 22%|██▏       | 13909/61904 [6:57:00<18:46:34,  1.41s/it]
 22%|██▏       | 13910/61904 [6:57:01<18:40:22,  1.40s/it]
 22%|██▏       | 13911/61904 [6:57:02<18:21:05,  1.38s/it]
 22%|██▏       | 13912/61904 [6:57:04<18:19:26,  1.37s/it]
 22%|██▏       | 13913/61904 [6:57:05<18:40:52,  1.40s/it]
 22%|██▏       | 13914/61904 [6:57:07<18:26:20,  1.38s/it]
 22%|██▏       | 13915/61904 [6:57:08<18:46:03,  1.41s/it]
 22%|██▏       | 13916/61904 [6:57:09<18:16:24,  1.37s/it]
 22%|██▏       | 13917/61904 [6:57:11<18:55:45,  1.42s/it]
 22%|██▏       | 13918/61904 [6:57:12<18:14:22,  1.37s/it]
 22%|██▏       | 13919/61904 [6:57:13<17:45:40,  1.33s/it]
 22%|██▏       | 13920/61904 [6:57:15<17:20:58,  1.30s/it]
                                                          
{'loss': 2.7026, 'learning_rate': 1.7776481265396085e-07, 'epoch': 3.6}

 22%|██▏       | 13920/61904 [6:57:15<17:20:58,  1.30s/it]
 22%|██▏       | 13921/61904 [6:57:16<17:15:03,  1.29s/it]
 22%|██▏       | 13922/61904 [6:57:17<18:12:07,  1.37s/it]
 22%|██▏       | 13923/61904 [6:57:19<18:36:05,  1.40s/it]
 22%|██▏       | 13924/61904 [6:57:20<18:56:01,  1.42s/it]
 22%|██▏       | 13925/61904 [6:57:22<18:25:14,  1.38s/it]
 22%|██▏       | 13926/61904 [6:57:23<18:16:08,  1.37s/it]
 22%|██▏       | 13927/61904 [6:57:25<18:31:06,  1.39s/it]
 22%|██▏       | 13928/61904 [6:57:26<18:31:39,  1.39s/it]
 23%|██▎       | 13929/61904 [6:57:27<18:24:41,  1.38s/it]
 23%|██▎       | 13930/61904 [6:57:29<18:16:52,  1.37s/it]
 23%|██▎       | 13931/61904 [6:57:30<17:55:30,  1.35s/it]
 23%|██▎       | 13932/61904 [6:57:31<18:00:52,  1.35s/it]
 23%|██▎       | 13933/61904 [6:57:33<18:02:13,  1.35s/it]
 23%|██▎       | 13934/61904 [6:57:34<18:00:04,  1.35s/it]
 23%|██▎       | 13935/61904 [6:57:35<18:04:36,  1.36s/it]
 23%|██▎       | 13936/61904 [6:57:37<17:46:06,  1.33s/it]
 23%|██▎       | 13937/61904 [6:57:38<18:21:58,  1.38s/it]
 23%|██▎       | 13938/61904 [6:57:39<18:04:45,  1.36s/it]
 23%|██▎       | 13939/61904 [6:57:41<18:00:00,  1.35s/it]
 23%|██▎       | 13940/61904 [6:57:42<18:27:51,  1.39s/it]
                                                          
{'loss': 2.7219, 'learning_rate': 1.7773239984441849e-07, 'epoch': 3.6}

 23%|██▎       | 13940/61904 [6:57:42<18:27:51,  1.39s/it]
 23%|██▎       | 13941/61904 [6:57:44<18:35:38,  1.40s/it]
 23%|██▎       | 13942/61904 [6:57:45<18:29:25,  1.39s/it]
 23%|██▎       | 13943/61904 [6:57:46<18:16:56,  1.37s/it]
 23%|██▎       | 13944/61904 [6:57:48<18:07:53,  1.36s/it]
 23%|██▎       | 13945/61904 [6:57:49<17:52:24,  1.34s/it]
 23%|██▎       | 13946/61904 [6:57:50<17:47:34,  1.34s/it]
 23%|██▎       | 13947/61904 [6:57:52<18:08:27,  1.36s/it]
 23%|██▎       | 13948/61904 [6:57:53<17:43:37,  1.33s/it]
 23%|██▎       | 13949/61904 [6:57:54<17:48:44,  1.34s/it]
 23%|██▎       | 13950/61904 [6:57:56<17:36:10,  1.32s/it]
 23%|██▎       | 13951/61904 [6:57:57<17:30:37,  1.31s/it]
 23%|██▎       | 13952/61904 [6:57:58<17:43:03,  1.33s/it]
 23%|██▎       | 13953/61904 [6:58:00<18:29:04,  1.39s/it]
 23%|██▎       | 13954/61904 [6:58:01<18:38:59,  1.40s/it]
 23%|██▎       | 13955/61904 [6:58:03<18:41:55,  1.40s/it]
 23%|██▎       | 13956/61904 [6:58:04<18:39:51,  1.40s/it]
 23%|██▎       | 13957/61904 [6:58:05<18:46:52,  1.41s/it]
 23%|██▎       | 13958/61904 [6:58:07<18:12:37,  1.37s/it]
 23%|██▎       | 13959/61904 [6:58:08<18:09:26,  1.36s/it]
 23%|██▎       | 13960/61904 [6:58:09<17:56:06,  1.35s/it]
                                                          
{'loss': 2.821, 'learning_rate': 1.7769998703487617e-07, 'epoch': 3.61}

 23%|██▎       | 13960/61904 [6:58:09<17:56:06,  1.35s/it]
 23%|██▎       | 13961/61904 [6:58:11<18:08:42,  1.36s/it]
 23%|██▎       | 13962/61904 [6:58:12<17:49:03,  1.34s/it]
 23%|██▎       | 13963/61904 [6:58:13<17:35:58,  1.32s/it]
 23%|██▎       | 13964/61904 [6:58:15<17:13:45,  1.29s/it]
 23%|██▎       | 13965/61904 [6:58:16<17:43:04,  1.33s/it]
 23%|██▎       | 13966/61904 [6:58:17<17:50:12,  1.34s/it]
 23%|██▎       | 13967/61904 [6:58:19<18:16:53,  1.37s/it]
 23%|██▎       | 13968/61904 [6:58:20<18:48:05,  1.41s/it]
 23%|██▎       | 13969/61904 [6:58:22<18:05:32,  1.36s/it]
 23%|██▎       | 13970/61904 [6:58:23<18:47:23,  1.41s/it]
 23%|██▎       | 13971/61904 [6:58:24<18:44:10,  1.41s/it]
 23%|██▎       | 13972/61904 [6:58:26<18:17:29,  1.37s/it]
 23%|██▎       | 13973/61904 [6:58:27<18:41:14,  1.40s/it]
 23%|██▎       | 13974/61904 [6:58:29<18:32:49,  1.39s/it]
 23%|██▎       | 13975/61904 [6:58:30<18:41:56,  1.40s/it]
 23%|██▎       | 13976/61904 [6:58:31<18:42:32,  1.41s/it]
 23%|██▎       | 13977/61904 [6:58:33<18:39:15,  1.40s/it]
 23%|██▎       | 13978/61904 [6:58:34<18:54:58,  1.42s/it]
 23%|██▎       | 13979/61904 [6:58:36<19:16:35,  1.45s/it]
 23%|██▎       | 13980/61904 [6:58:37<19:09:23,  1.44s/it]
                                                          
{'loss': 2.6779, 'learning_rate': 1.7766757422533386e-07, 'epoch': 3.61}

 23%|██▎       | 13980/61904 [6:58:37<19:09:23,  1.44s/it]
 23%|██▎       | 13981/61904 [6:58:39<19:57:42,  1.50s/it]
 23%|██▎       | 13982/61904 [6:58:40<19:04:57,  1.43s/it]
 23%|██▎       | 13983/61904 [6:58:42<18:46:23,  1.41s/it]
 23%|██▎       | 13984/61904 [6:58:43<18:11:25,  1.37s/it]
 23%|██▎       | 13985/61904 [6:58:44<17:36:21,  1.32s/it]
 23%|██▎       | 13986/61904 [6:58:45<17:30:20,  1.32s/it]
 23%|██▎       | 13987/61904 [6:58:47<17:30:55,  1.32s/it]
 23%|██▎       | 13988/61904 [6:58:48<17:47:12,  1.34s/it]
 23%|██▎       | 13989/61904 [6:58:49<17:39:42,  1.33s/it]
 23%|██▎       | 13990/61904 [6:58:51<17:42:14,  1.33s/it]
 23%|██▎       | 13991/61904 [6:58:52<18:01:00,  1.35s/it]
 23%|██▎       | 13992/61904 [6:58:53<18:20:48,  1.38s/it]
 23%|██▎       | 13993/61904 [6:58:55<17:47:35,  1.34s/it]
 23%|██▎       | 13994/61904 [6:58:56<18:12:48,  1.37s/it]
 23%|██▎       | 13995/61904 [6:58:58<18:14:41,  1.37s/it]
 23%|██▎       | 13996/61904 [6:58:59<18:12:58,  1.37s/it]
 23%|██▎       | 13997/61904 [6:59:00<18:01:15,  1.35s/it]
 23%|██▎       | 13998/61904 [6:59:02<18:41:05,  1.40s/it]
 23%|██▎       | 13999/61904 [6:59:03<18:29:24,  1.39s/it]
 23%|██▎       | 14000/61904 [6:59:04<18:24:47,  1.38s/it]
                                                          
{'loss': 2.7756, 'learning_rate': 1.776351614157915e-07, 'epoch': 3.62}

 23%|██▎       | 14000/61904 [6:59:04<18:24:47,  1.38s/it]
 23%|██▎       | 14001/61904 [6:59:06<18:12:56,  1.37s/it]
 23%|██▎       | 14002/61904 [6:59:07<17:42:12,  1.33s/it]
 23%|██▎       | 14003/61904 [6:59:08<17:56:23,  1.35s/it]
 23%|██▎       | 14004/61904 [6:59:10<18:13:51,  1.37s/it]
 23%|██▎       | 14005/61904 [6:59:11<18:06:12,  1.36s/it]
 23%|██▎       | 14006/61904 [6:59:13<18:15:11,  1.37s/it]
 23%|██▎       | 14007/61904 [6:59:14<18:29:06,  1.39s/it]
 23%|██▎       | 14008/61904 [6:59:15<18:07:46,  1.36s/it]
 23%|██▎       | 14009/61904 [6:59:17<18:01:46,  1.36s/it]
 23%|██▎       | 14010/61904 [6:59:18<18:41:06,  1.40s/it]
 23%|██▎       | 14011/61904 [6:59:20<18:27:31,  1.39s/it]
 23%|██▎       | 14012/61904 [6:59:21<17:54:51,  1.35s/it]
 23%|██▎       | 14013/61904 [6:59:22<17:47:35,  1.34s/it]
 23%|██▎       | 14014/61904 [6:59:23<17:43:28,  1.33s/it]
 23%|██▎       | 14015/61904 [6:59:25<18:00:30,  1.35s/it]
 23%|██▎       | 14016/61904 [6:59:26<18:09:08,  1.36s/it]
 23%|██▎       | 14017/61904 [6:59:28<18:25:03,  1.38s/it]
 23%|██▎       | 14018/61904 [6:59:29<17:59:53,  1.35s/it]
 23%|██▎       | 14019/61904 [6:59:30<18:44:57,  1.41s/it]
 23%|██▎       | 14020/61904 [6:59:32<18:50:35,  1.42s/it]
                                                          
{'loss': 2.7093, 'learning_rate': 1.7760274860624919e-07, 'epoch': 3.62}

 23%|██▎       | 14020/61904 [6:59:32<18:50:35,  1.42s/it]
 23%|██▎       | 14021/61904 [6:59:33<18:37:14,  1.40s/it]
 23%|██▎       | 14022/61904 [6:59:35<18:08:52,  1.36s/it]
 23%|██▎       | 14023/61904 [6:59:36<18:03:40,  1.36s/it]
 23%|██▎       | 14024/61904 [6:59:37<18:11:17,  1.37s/it]
 23%|██▎       | 14025/61904 [6:59:39<18:13:32,  1.37s/it]
 23%|██▎       | 14026/61904 [6:59:40<18:06:10,  1.36s/it]
 23%|██▎       | 14027/61904 [6:59:42<18:42:24,  1.41s/it]
 23%|██▎       | 14028/61904 [6:59:43<19:21:25,  1.46s/it]
 23%|██▎       | 14029/61904 [6:59:44<18:53:54,  1.42s/it]
 23%|██▎       | 14030/61904 [6:59:46<18:54:15,  1.42s/it]
 23%|██▎       | 14031/61904 [6:59:47<18:28:53,  1.39s/it]
 23%|██▎       | 14032/61904 [6:59:48<18:03:24,  1.36s/it]
 23%|██▎       | 14033/61904 [6:59:50<18:06:52,  1.36s/it]
 23%|██▎       | 14034/61904 [6:59:51<17:52:19,  1.34s/it]
 23%|██▎       | 14035/61904 [6:59:52<17:54:28,  1.35s/it]
 23%|██▎       | 14036/61904 [6:59:54<17:39:54,  1.33s/it]
 23%|██▎       | 14037/61904 [6:59:55<18:19:26,  1.38s/it]
 23%|██▎       | 14038/61904 [6:59:57<18:39:52,  1.40s/it]
 23%|██▎       | 14039/61904 [6:59:58<18:08:18,  1.36s/it]
 23%|██▎       | 14040/61904 [6:59:59<17:34:56,  1.32s/it]
                                                          
{'loss': 2.8079, 'learning_rate': 1.7757033579670685e-07, 'epoch': 3.63}

 23%|██▎       | 14040/61904 [6:59:59<17:34:56,  1.32s/it]
 23%|██▎       | 14041/61904 [7:00:01<17:32:25,  1.32s/it]
 23%|██▎       | 14042/61904 [7:00:02<18:01:26,  1.36s/it]
 23%|██▎       | 14043/61904 [7:00:03<18:17:38,  1.38s/it]
 23%|██▎       | 14044/61904 [7:00:05<18:14:50,  1.37s/it]
 23%|██▎       | 14045/61904 [7:00:06<18:18:20,  1.38s/it]
 23%|██▎       | 14046/61904 [7:00:08<19:05:20,  1.44s/it]
 23%|██▎       | 14047/61904 [7:00:09<18:47:25,  1.41s/it]
 23%|██▎       | 14048/61904 [7:00:11<18:54:13,  1.42s/it]
 23%|██▎       | 14049/61904 [7:00:12<17:59:40,  1.35s/it]
 23%|██▎       | 14050/61904 [7:00:13<18:24:07,  1.38s/it]
 23%|██▎       | 14051/61904 [7:00:15<18:50:22,  1.42s/it]
 23%|██▎       | 14052/61904 [7:00:16<19:06:37,  1.44s/it]
 23%|██▎       | 14053/61904 [7:00:18<19:00:39,  1.43s/it]
 23%|██▎       | 14054/61904 [7:00:19<19:03:26,  1.43s/it]
 23%|██▎       | 14055/61904 [7:00:20<18:15:16,  1.37s/it]
 23%|██▎       | 14056/61904 [7:00:22<18:19:46,  1.38s/it]
 23%|██▎       | 14057/61904 [7:00:23<18:43:15,  1.41s/it]
 23%|██▎       | 14058/61904 [7:00:24<18:13:37,  1.37s/it]
 23%|██▎       | 14059/61904 [7:00:26<18:07:42,  1.36s/it]
 23%|██▎       | 14060/61904 [7:00:27<19:28:17,  1.47s/it]
                                                          
{'loss': 2.7358, 'learning_rate': 1.775379229871645e-07, 'epoch': 3.63}

 23%|██▎       | 14060/61904 [7:00:27<19:28:17,  1.47s/it]
 23%|██▎       | 14061/61904 [7:00:29<18:49:51,  1.42s/it]
 23%|██▎       | 14062/61904 [7:00:30<18:38:56,  1.40s/it]
 23%|██▎       | 14063/61904 [7:00:32<19:05:12,  1.44s/it]
 23%|██▎       | 14064/61904 [7:00:33<19:01:31,  1.43s/it]
 23%|██▎       | 14065/61904 [7:00:35<19:24:20,  1.46s/it]
 23%|██▎       | 14066/61904 [7:00:36<18:58:12,  1.43s/it]
 23%|██▎       | 14067/61904 [7:00:37<18:46:15,  1.41s/it]
 23%|██▎       | 14068/61904 [7:00:39<19:08:33,  1.44s/it]
 23%|██▎       | 14069/61904 [7:00:40<18:49:42,  1.42s/it]
 23%|██▎       | 14070/61904 [7:00:42<19:12:23,  1.45s/it]
 23%|██▎       | 14071/61904 [7:00:43<19:13:50,  1.45s/it]
 23%|██▎       | 14072/61904 [7:00:45<19:10:13,  1.44s/it]
 23%|██▎       | 14073/61904 [7:00:46<18:48:09,  1.42s/it]
 23%|██▎       | 14074/61904 [7:00:47<18:50:49,  1.42s/it]
 23%|██▎       | 14075/61904 [7:00:49<18:34:53,  1.40s/it]
 23%|██▎       | 14076/61904 [7:00:50<17:54:21,  1.35s/it]
 23%|██▎       | 14077/61904 [7:00:51<17:40:33,  1.33s/it]
 23%|██▎       | 14078/61904 [7:00:53<17:51:44,  1.34s/it]
 23%|██▎       | 14079/61904 [7:00:54<18:17:47,  1.38s/it]
 23%|██▎       | 14080/61904 [7:00:55<18:23:28,  1.38s/it]
                                                          
{'loss': 2.7401, 'learning_rate': 1.775055101776222e-07, 'epoch': 3.64}

 23%|██▎       | 14080/61904 [7:00:55<18:23:28,  1.38s/it]
 23%|██▎       | 14081/61904 [7:00:57<18:32:34,  1.40s/it]
 23%|██▎       | 14082/61904 [7:00:58<18:06:18,  1.36s/it]
 23%|██▎       | 14083/61904 [7:01:00<18:22:57,  1.38s/it]
 23%|██▎       | 14084/61904 [7:01:01<17:52:15,  1.35s/it]
 23%|██▎       | 14085/61904 [7:01:02<18:12:56,  1.37s/it]
 23%|██▎       | 14086/61904 [7:01:04<17:59:54,  1.36s/it]
 23%|██▎       | 14087/61904 [7:01:05<17:31:26,  1.32s/it]
 23%|██▎       | 14088/61904 [7:01:06<17:40:28,  1.33s/it]
 23%|██▎       | 14089/61904 [7:01:08<17:50:21,  1.34s/it]
 23%|██▎       | 14090/61904 [7:01:09<17:47:25,  1.34s/it]
 23%|██▎       | 14091/61904 [7:01:10<17:34:34,  1.32s/it]
 23%|██▎       | 14092/61904 [7:01:12<18:20:27,  1.38s/it]
 23%|██▎       | 14093/61904 [7:01:13<18:16:46,  1.38s/it]
 23%|██▎       | 14094/61904 [7:01:14<18:30:11,  1.39s/it]
 23%|██▎       | 14095/61904 [7:01:16<17:57:16,  1.35s/it]
 23%|██▎       | 14096/61904 [7:01:17<18:36:01,  1.40s/it]
 23%|██▎       | 14097/61904 [7:01:19<18:30:16,  1.39s/it]
 23%|██▎       | 14098/61904 [7:01:20<18:07:12,  1.36s/it]
 23%|██▎       | 14099/61904 [7:01:21<17:49:44,  1.34s/it]
 23%|██▎       | 14100/61904 [7:01:23<18:32:45,  1.40s/it]
                                                          
{'loss': 2.7088, 'learning_rate': 1.7747309736807986e-07, 'epoch': 3.64}

 23%|██▎       | 14100/61904 [7:01:23<18:32:45,  1.40s/it]
 23%|██▎       | 14101/61904 [7:01:24<18:16:34,  1.38s/it]
 23%|██▎       | 14102/61904 [7:01:26<18:48:08,  1.42s/it]
 23%|██▎       | 14103/61904 [7:01:27<18:28:37,  1.39s/it]
 23%|██▎       | 14104/61904 [7:01:28<17:57:12,  1.35s/it]
 23%|██▎       | 14105/61904 [7:01:29<17:36:32,  1.33s/it]
 23%|██▎       | 14106/61904 [7:01:31<18:27:06,  1.39s/it]
 23%|██▎       | 14107/61904 [7:01:32<18:17:20,  1.38s/it]
 23%|██▎       | 14108/61904 [7:01:34<18:24:23,  1.39s/it]
 23%|██▎       | 14109/61904 [7:01:35<18:15:36,  1.38s/it]
 23%|██▎       | 14110/61904 [7:01:36<18:17:18,  1.38s/it]
 23%|██▎       | 14111/61904 [7:01:38<18:31:27,  1.40s/it]
 23%|██▎       | 14112/61904 [7:01:39<18:28:50,  1.39s/it]
 23%|██▎       | 14113/61904 [7:01:41<17:59:24,  1.36s/it]
 23%|██▎       | 14114/61904 [7:01:42<17:59:32,  1.36s/it]
 23%|██▎       | 14115/61904 [7:01:43<17:52:56,  1.35s/it]
 23%|██▎       | 14116/61904 [7:01:45<18:40:26,  1.41s/it]
 23%|██▎       | 14117/61904 [7:01:46<19:16:17,  1.45s/it]
 23%|██▎       | 14118/61904 [7:01:48<19:14:23,  1.45s/it]
 23%|██▎       | 14119/61904 [7:01:49<18:09:47,  1.37s/it]
 23%|██▎       | 14120/61904 [7:01:50<18:01:44,  1.36s/it]
                                                          
{'loss': 2.6936, 'learning_rate': 1.7744068455853752e-07, 'epoch': 3.65}

 23%|██▎       | 14120/61904 [7:01:50<18:01:44,  1.36s/it]
 23%|██▎       | 14121/61904 [7:01:52<18:25:55,  1.39s/it]
 23%|██▎       | 14122/61904 [7:01:53<18:15:07,  1.38s/it]
 23%|██▎       | 14123/61904 [7:01:54<18:17:45,  1.38s/it]
 23%|██▎       | 14124/61904 [7:01:56<17:46:00,  1.34s/it]
 23%|██▎       | 14125/61904 [7:01:57<17:50:48,  1.34s/it]
 23%|██▎       | 14126/61904 [7:01:58<17:32:37,  1.32s/it]
 23%|██▎       | 14127/61904 [7:02:00<18:08:36,  1.37s/it]
 23%|██▎       | 14128/61904 [7:02:01<17:46:32,  1.34s/it]
 23%|██▎       | 14129/61904 [7:02:03<18:11:24,  1.37s/it]
 23%|██▎       | 14130/61904 [7:02:04<18:06:43,  1.36s/it]
 23%|██▎       | 14131/61904 [7:02:05<17:57:50,  1.35s/it]
 23%|██▎       | 14132/61904 [7:02:07<18:02:21,  1.36s/it]
 23%|██▎       | 14133/61904 [7:02:08<18:03:44,  1.36s/it]
 23%|██▎       | 14134/61904 [7:02:09<18:24:48,  1.39s/it]
 23%|██▎       | 14135/61904 [7:02:11<19:00:54,  1.43s/it]
 23%|██▎       | 14136/61904 [7:02:12<18:45:23,  1.41s/it]
 23%|██▎       | 14137/61904 [7:02:14<18:09:29,  1.37s/it]
 23%|██▎       | 14138/61904 [7:02:15<18:25:43,  1.39s/it]
 23%|██▎       | 14139/61904 [7:02:17<19:04:52,  1.44s/it]
 23%|██▎       | 14140/61904 [7:02:18<18:59:58,  1.43s/it]
                                                          
{'loss': 2.7538, 'learning_rate': 1.774082717489952e-07, 'epoch': 3.65}

 23%|██▎       | 14140/61904 [7:02:18<18:59:58,  1.43s/it]
 23%|██▎       | 14141/61904 [7:02:19<19:07:08,  1.44s/it]
 23%|██▎       | 14142/61904 [7:02:21<19:04:16,  1.44s/it]
 23%|██▎       | 14143/61904 [7:02:22<18:32:46,  1.40s/it]
 23%|██▎       | 14144/61904 [7:02:24<18:16:18,  1.38s/it]
 23%|██▎       | 14145/61904 [7:02:25<18:15:08,  1.38s/it]
 23%|██▎       | 14146/61904 [7:02:26<18:01:50,  1.36s/it]
 23%|██▎       | 14147/61904 [7:02:27<17:41:50,  1.33s/it]
 23%|██▎       | 14148/61904 [7:02:29<17:12:34,  1.30s/it]
 23%|██▎       | 14149/61904 [7:02:30<17:17:35,  1.30s/it]
 23%|██▎       | 14150/61904 [7:02:31<17:12:33,  1.30s/it]
 23%|██▎       | 14151/61904 [7:02:33<17:37:21,  1.33s/it]
 23%|██▎       | 14152/61904 [7:02:34<17:26:17,  1.31s/it]
 23%|██▎       | 14153/61904 [7:02:35<17:16:12,  1.30s/it]
 23%|██▎       | 14154/61904 [7:02:37<17:17:44,  1.30s/it]
 23%|██▎       | 14155/61904 [7:02:38<17:15:04,  1.30s/it]
 23%|██▎       | 14156/61904 [7:02:39<17:35:49,  1.33s/it]
 23%|██▎       | 14157/61904 [7:02:41<17:52:52,  1.35s/it]
 23%|██▎       | 14158/61904 [7:02:42<17:52:05,  1.35s/it]
 23%|██▎       | 14159/61904 [7:02:43<18:13:56,  1.37s/it]
 23%|██▎       | 14160/61904 [7:02:45<18:41:23,  1.41s/it]
                                                          
{'loss': 2.7446, 'learning_rate': 1.7737585893945285e-07, 'epoch': 3.66}

 23%|██▎       | 14160/61904 [7:02:45<18:41:23,  1.41s/it]
 23%|██▎       | 14161/61904 [7:02:46<18:18:39,  1.38s/it]
 23%|██▎       | 14162/61904 [7:02:48<18:12:22,  1.37s/it]
 23%|██▎       | 14163/61904 [7:02:49<18:32:03,  1.40s/it]
 23%|██▎       | 14164/61904 [7:02:50<18:13:18,  1.37s/it]
 23%|██▎       | 14165/61904 [7:02:52<18:14:45,  1.38s/it]
 23%|██▎       | 14166/61904 [7:02:53<18:32:56,  1.40s/it]
 23%|██▎       | 14167/61904 [7:02:55<18:36:45,  1.40s/it]
 23%|██▎       | 14168/61904 [7:02:56<18:19:42,  1.38s/it]
 23%|██▎       | 14169/61904 [7:02:57<18:16:56,  1.38s/it]
 23%|██▎       | 14170/61904 [7:02:59<17:55:09,  1.35s/it]
 23%|██▎       | 14171/61904 [7:03:00<18:03:03,  1.36s/it]
 23%|██▎       | 14172/61904 [7:03:01<18:00:06,  1.36s/it]
 23%|██▎       | 14173/61904 [7:03:03<17:52:54,  1.35s/it]
 23%|██▎       | 14174/61904 [7:03:04<17:50:39,  1.35s/it]
 23%|██▎       | 14175/61904 [7:03:05<17:41:51,  1.33s/it]
 23%|██▎       | 14176/61904 [7:03:07<17:49:09,  1.34s/it]
 23%|██▎       | 14177/61904 [7:03:08<17:49:21,  1.34s/it]
 23%|██▎       | 14178/61904 [7:03:10<18:36:48,  1.40s/it]
 23%|██▎       | 14179/61904 [7:03:11<18:03:12,  1.36s/it]
 23%|██▎       | 14180/61904 [7:03:12<17:42:38,  1.34s/it]
                                                          
{'loss': 2.7566, 'learning_rate': 1.7734344612991053e-07, 'epoch': 3.66}

 23%|██▎       | 14180/61904 [7:03:12<17:42:38,  1.34s/it]
 23%|██▎       | 14181/61904 [7:03:14<18:06:34,  1.37s/it]
 23%|██▎       | 14182/61904 [7:03:15<18:22:10,  1.39s/it]
 23%|██▎       | 14183/61904 [7:03:16<18:20:49,  1.38s/it]
 23%|██▎       | 14184/61904 [7:03:18<18:05:13,  1.36s/it]
 23%|██▎       | 14185/61904 [7:03:19<18:02:09,  1.36s/it]
 23%|██▎       | 14186/61904 [7:03:20<17:46:43,  1.34s/it]
 23%|██▎       | 14187/61904 [7:03:22<17:30:59,  1.32s/it]
 23%|██▎       | 14188/61904 [7:03:23<17:54:03,  1.35s/it]
 23%|██▎       | 14189/61904 [7:03:24<18:14:06,  1.38s/it]
 23%|██▎       | 14190/61904 [7:03:26<18:17:14,  1.38s/it]
 23%|██▎       | 14191/61904 [7:03:27<18:05:06,  1.36s/it]
 23%|██▎       | 14192/61904 [7:03:28<17:43:53,  1.34s/it]
 23%|██▎       | 14193/61904 [7:03:30<17:35:55,  1.33s/it]
 23%|██▎       | 14194/61904 [7:03:31<17:20:13,  1.31s/it]
 23%|██▎       | 14195/61904 [7:03:32<17:46:17,  1.34s/it]
 23%|██▎       | 14196/61904 [7:03:34<17:59:15,  1.36s/it]
 23%|██▎       | 14197/61904 [7:03:35<18:16:15,  1.38s/it]
 23%|██▎       | 14198/61904 [7:03:37<18:54:49,  1.43s/it]
 23%|██▎       | 14199/61904 [7:03:38<18:34:07,  1.40s/it]
 23%|██▎       | 14200/61904 [7:03:40<18:47:42,  1.42s/it]
                                                          
{'loss': 2.7146, 'learning_rate': 1.773110333203682e-07, 'epoch': 3.67}

 23%|██▎       | 14200/61904 [7:03:40<18:47:42,  1.42s/it]
 23%|██▎       | 14201/61904 [7:03:41<18:22:36,  1.39s/it]
 23%|██▎       | 14202/61904 [7:03:42<17:56:57,  1.35s/it]
 23%|██▎       | 14203/61904 [7:03:44<19:10:25,  1.45s/it]
 23%|██▎       | 14204/61904 [7:03:45<18:53:38,  1.43s/it]
 23%|██▎       | 14205/61904 [7:03:47<18:48:39,  1.42s/it]
 23%|██▎       | 14206/61904 [7:03:48<18:39:10,  1.41s/it]
 23%|██▎       | 14207/61904 [7:03:49<18:17:47,  1.38s/it]
 23%|██▎       | 14208/61904 [7:03:51<18:31:47,  1.40s/it]
 23%|██▎       | 14209/61904 [7:03:52<18:43:29,  1.41s/it]
 23%|██▎       | 14210/61904 [7:03:54<18:45:05,  1.42s/it]
 23%|██▎       | 14211/61904 [7:03:55<18:17:16,  1.38s/it]
 23%|██▎       | 14212/61904 [7:03:56<18:22:13,  1.39s/it]
 23%|██▎       | 14213/61904 [7:03:58<18:20:50,  1.38s/it]
 23%|██▎       | 14214/61904 [7:03:59<18:22:28,  1.39s/it]
 23%|██▎       | 14215/61904 [7:04:00<17:55:55,  1.35s/it]
 23%|██▎       | 14216/61904 [7:04:02<18:30:26,  1.40s/it]
 23%|██▎       | 14217/61904 [7:04:03<18:47:05,  1.42s/it]
 23%|██▎       | 14218/61904 [7:04:05<18:03:43,  1.36s/it]
 23%|██▎       | 14219/61904 [7:04:06<17:57:12,  1.36s/it]
 23%|██▎       | 14220/61904 [7:04:07<17:16:07,  1.30s/it]
                                                          
{'loss': 2.7953, 'learning_rate': 1.7727862051082586e-07, 'epoch': 3.67}

 23%|██▎       | 14220/61904 [7:04:07<17:16:07,  1.30s/it]
 23%|██▎       | 14221/61904 [7:04:08<16:55:40,  1.28s/it]
 23%|██▎       | 14222/61904 [7:04:10<17:48:19,  1.34s/it]
 23%|██▎       | 14223/61904 [7:04:11<18:05:13,  1.37s/it]
 23%|██▎       | 14224/61904 [7:04:13<17:46:37,  1.34s/it]
 23%|██▎       | 14225/61904 [7:04:14<18:09:36,  1.37s/it]
 23%|██▎       | 14226/61904 [7:04:15<17:52:46,  1.35s/it]
 23%|██▎       | 14227/61904 [7:04:17<18:00:32,  1.36s/it]
 23%|██▎       | 14228/61904 [7:04:18<17:51:26,  1.35s/it]
 23%|██▎       | 14229/61904 [7:04:19<17:13:29,  1.30s/it]
 23%|██▎       | 14230/61904 [7:04:20<17:14:35,  1.30s/it]
 23%|██▎       | 14231/61904 [7:04:22<17:14:16,  1.30s/it]
 23%|██▎       | 14232/61904 [7:04:23<17:26:29,  1.32s/it]
 23%|██▎       | 14233/61904 [7:04:25<17:58:19,  1.36s/it]
 23%|██▎       | 14234/61904 [7:04:26<17:56:28,  1.35s/it]
 23%|██▎       | 14235/61904 [7:04:27<18:16:09,  1.38s/it]
 23%|██▎       | 14236/61904 [7:04:29<18:12:25,  1.38s/it]
 23%|██▎       | 14237/61904 [7:04:30<18:46:00,  1.42s/it]
 23%|██▎       | 14238/61904 [7:04:32<18:59:12,  1.43s/it]
 23%|██▎       | 14239/61904 [7:04:33<18:42:22,  1.41s/it]
 23%|██▎       | 14240/61904 [7:04:34<18:19:04,  1.38s/it]
                                                          
{'loss': 2.7185, 'learning_rate': 1.7724620770128355e-07, 'epoch': 3.68}

 23%|██▎       | 14240/61904 [7:04:34<18:19:04,  1.38s/it]
 23%|██▎       | 14241/61904 [7:04:36<18:05:32,  1.37s/it]
 23%|██▎       | 14242/61904 [7:04:37<17:49:45,  1.35s/it]
 23%|██▎       | 14243/61904 [7:04:38<17:41:49,  1.34s/it]
 23%|██▎       | 14244/61904 [7:04:40<17:26:04,  1.32s/it]
 23%|██▎       | 14245/61904 [7:04:41<17:40:29,  1.34s/it]
 23%|██▎       | 14246/61904 [7:04:42<18:03:21,  1.36s/it]
 23%|██▎       | 14247/61904 [7:04:44<17:48:37,  1.35s/it]
 23%|██▎       | 14248/61904 [7:04:45<17:46:40,  1.34s/it]
 23%|██▎       | 14249/61904 [7:04:47<18:18:48,  1.38s/it]
 23%|██▎       | 14250/61904 [7:04:48<18:08:08,  1.37s/it]
 23%|██▎       | 14251/61904 [7:04:49<17:46:01,  1.34s/it]
 23%|██▎       | 14252/61904 [7:04:50<17:47:20,  1.34s/it]
 23%|██▎       | 14253/61904 [7:04:52<18:14:42,  1.38s/it]
 23%|██▎       | 14254/61904 [7:04:53<18:42:20,  1.41s/it]
 23%|██▎       | 14255/61904 [7:04:55<18:24:20,  1.39s/it]
 23%|██▎       | 14256/61904 [7:04:56<18:15:07,  1.38s/it]
 23%|██▎       | 14257/61904 [7:04:57<18:00:26,  1.36s/it]
 23%|██▎       | 14258/61904 [7:04:59<18:26:49,  1.39s/it]
 23%|██▎       | 14259/61904 [7:05:00<18:16:19,  1.38s/it]
 23%|██▎       | 14260/61904 [7:05:02<18:29:27,  1.40s/it]
                                                          
{'loss': 2.7957, 'learning_rate': 1.772137948917412e-07, 'epoch': 3.69}

 23%|██▎       | 14260/61904 [7:05:02<18:29:27,  1.40s/it]
 23%|██▎       | 14261/61904 [7:05:03<19:08:37,  1.45s/it]
 23%|██▎       | 14262/61904 [7:05:05<19:24:01,  1.47s/it]
 23%|██▎       | 14263/61904 [7:05:06<18:54:09,  1.43s/it]
 23%|██▎       | 14264/61904 [7:05:08<18:58:45,  1.43s/it]
 23%|██▎       | 14265/61904 [7:05:09<18:37:29,  1.41s/it]
 23%|██▎       | 14266/61904 [7:05:10<18:14:28,  1.38s/it]
 23%|██▎       | 14267/61904 [7:05:12<18:27:13,  1.39s/it]
 23%|██▎       | 14268/61904 [7:05:13<18:25:33,  1.39s/it]
 23%|██▎       | 14269/61904 [7:05:14<18:03:13,  1.36s/it]
 23%|██▎       | 14270/61904 [7:05:16<17:35:49,  1.33s/it]
 23%|██▎       | 14271/61904 [7:05:17<18:08:43,  1.37s/it]
 23%|██▎       | 14272/61904 [7:05:18<18:09:45,  1.37s/it]
 23%|██▎       | 14273/61904 [7:05:20<17:35:22,  1.33s/it]
 23%|██▎       | 14274/61904 [7:05:21<18:17:25,  1.38s/it]
 23%|██▎       | 14275/61904 [7:05:22<17:48:40,  1.35s/it]
 23%|██▎       | 14276/61904 [7:05:24<17:24:05,  1.32s/it]
 23%|██▎       | 14277/61904 [7:05:25<17:32:39,  1.33s/it]
 23%|██▎       | 14278/61904 [7:05:26<17:51:50,  1.35s/it]
 23%|██▎       | 14279/61904 [7:05:28<18:02:44,  1.36s/it]
 23%|██▎       | 14280/61904 [7:05:29<17:54:55,  1.35s/it]
                                                          
{'loss': 2.7017, 'learning_rate': 1.7718138208219887e-07, 'epoch': 3.69}

 23%|██▎       | 14280/61904 [7:05:29<17:54:55,  1.35s/it]
 23%|██▎       | 14281/61904 [7:05:30<17:41:29,  1.34s/it]
 23%|██▎       | 14282/61904 [7:05:32<18:02:21,  1.36s/it]
 23%|██▎       | 14283/61904 [7:05:33<17:55:37,  1.36s/it]
 23%|██▎       | 14284/61904 [7:05:35<18:06:21,  1.37s/it]
 23%|██▎       | 14285/61904 [7:05:36<18:21:16,  1.39s/it]
 23%|██▎       | 14286/61904 [7:05:37<17:50:18,  1.35s/it]
 23%|██▎       | 14287/61904 [7:05:39<17:41:43,  1.34s/it]
 23%|██▎       | 14288/61904 [7:05:40<17:31:22,  1.32s/it]
 23%|██▎       | 14289/61904 [7:05:41<17:36:33,  1.33s/it]
 23%|██▎       | 14290/61904 [7:05:43<17:59:48,  1.36s/it]
 23%|██▎       | 14291/61904 [7:05:44<18:26:41,  1.39s/it]
 23%|██▎       | 14292/61904 [7:05:46<18:42:44,  1.41s/it]
 23%|██▎       | 14293/61904 [7:05:47<18:31:45,  1.40s/it]
 23%|██▎       | 14294/61904 [7:05:48<18:14:45,  1.38s/it]
 23%|██▎       | 14295/61904 [7:05:50<18:25:37,  1.39s/it]
 23%|██▎       | 14296/61904 [7:05:51<17:51:42,  1.35s/it]
 23%|██▎       | 14297/61904 [7:05:52<17:36:29,  1.33s/it]
 23%|██▎       | 14298/61904 [7:05:54<17:38:00,  1.33s/it]
 23%|██▎       | 14299/61904 [7:05:55<19:18:58,  1.46s/it]
 23%|██▎       | 14300/61904 [7:05:57<19:01:11,  1.44s/it]
                                                          
{'loss': 2.7374, 'learning_rate': 1.7714896927265656e-07, 'epoch': 3.7}

 23%|██▎       | 14300/61904 [7:05:57<19:01:11,  1.44s/it]
 23%|██▎       | 14301/61904 [7:05:58<18:12:22,  1.38s/it]
 23%|██▎       | 14302/61904 [7:05:59<17:57:16,  1.36s/it]
 23%|██▎       | 14303/61904 [7:06:01<18:02:44,  1.36s/it]
 23%|██▎       | 14304/61904 [7:06:02<17:37:59,  1.33s/it]
 23%|██▎       | 14305/61904 [7:06:03<17:24:51,  1.32s/it]
 23%|██▎       | 14306/61904 [7:06:05<18:09:43,  1.37s/it]
 23%|██▎       | 14307/61904 [7:06:06<18:29:11,  1.40s/it]
 23%|██▎       | 14308/61904 [7:06:08<18:43:07,  1.42s/it]
 23%|██▎       | 14309/61904 [7:06:09<18:44:31,  1.42s/it]
 23%|██▎       | 14310/61904 [7:06:10<18:27:44,  1.40s/it]
 23%|██▎       | 14311/61904 [7:06:12<18:20:30,  1.39s/it]
 23%|██▎       | 14312/61904 [7:06:13<18:24:26,  1.39s/it]
 23%|██▎       | 14313/61904 [7:06:15<18:34:58,  1.41s/it]
 23%|██▎       | 14314/61904 [7:06:16<18:47:37,  1.42s/it]
 23%|██▎       | 14315/61904 [7:06:17<18:29:32,  1.40s/it]
 23%|██▎       | 14316/61904 [7:06:19<17:57:53,  1.36s/it]
 23%|██▎       | 14317/61904 [7:06:20<17:29:50,  1.32s/it]
 23%|██▎       | 14318/61904 [7:06:21<17:09:06,  1.30s/it]
 23%|██▎       | 14319/61904 [7:06:22<16:53:04,  1.28s/it]
 23%|██▎       | 14320/61904 [7:06:24<17:01:51,  1.29s/it]
                                                          
{'loss': 2.7442, 'learning_rate': 1.771165564631142e-07, 'epoch': 3.7}

 23%|██▎       | 14320/61904 [7:06:24<17:01:51,  1.29s/it]
 23%|██▎       | 14321/61904 [7:06:25<17:29:59,  1.32s/it]
 23%|██▎       | 14322/61904 [7:06:26<17:28:21,  1.32s/it]
 23%|██▎       | 14323/61904 [7:06:28<17:13:22,  1.30s/it]
 23%|██▎       | 14324/61904 [7:06:29<17:35:34,  1.33s/it]
 23%|██▎       | 14325/61904 [7:06:31<17:56:31,  1.36s/it]
 23%|██▎       | 14326/61904 [7:06:32<17:53:53,  1.35s/it]
 23%|██▎       | 14327/61904 [7:06:33<17:41:45,  1.34s/it]
 23%|██▎       | 14328/61904 [7:06:35<17:51:48,  1.35s/it]
 23%|██▎       | 14329/61904 [7:06:36<17:26:55,  1.32s/it]
 23%|██▎       | 14330/61904 [7:06:37<17:41:53,  1.34s/it]
 23%|██▎       | 14331/61904 [7:06:38<17:37:05,  1.33s/it]
 23%|██▎       | 14332/61904 [7:06:40<17:26:21,  1.32s/it]
 23%|██▎       | 14333/61904 [7:06:41<17:16:05,  1.31s/it]
 23%|██▎       | 14334/61904 [7:06:42<16:54:45,  1.28s/it]
 23%|██▎       | 14335/61904 [7:06:44<17:44:47,  1.34s/it]
 23%|██▎       | 14336/61904 [7:06:45<17:58:17,  1.36s/it]
 23%|██▎       | 14337/61904 [7:06:47<17:57:40,  1.36s/it]
 23%|██▎       | 14338/61904 [7:06:48<17:28:12,  1.32s/it]
 23%|██▎       | 14339/61904 [7:06:49<18:02:59,  1.37s/it]
 23%|██▎       | 14340/61904 [7:06:51<18:27:52,  1.40s/it]
                                                          
{'loss': 2.7792, 'learning_rate': 1.7708414365357188e-07, 'epoch': 3.71}

 23%|██▎       | 14340/61904 [7:06:51<18:27:52,  1.40s/it]
 23%|██▎       | 14341/61904 [7:06:52<18:30:32,  1.40s/it]
 23%|██▎       | 14342/61904 [7:06:53<17:55:40,  1.36s/it]
 23%|██▎       | 14343/61904 [7:06:55<18:21:54,  1.39s/it]
 23%|██▎       | 14344/61904 [7:06:56<18:37:56,  1.41s/it]
 23%|██▎       | 14345/61904 [7:06:58<19:02:41,  1.44s/it]
 23%|██▎       | 14346/61904 [7:06:59<18:28:14,  1.40s/it]
 23%|██▎       | 14347/61904 [7:07:00<18:12:31,  1.38s/it]
 23%|██▎       | 14348/61904 [7:07:02<18:03:21,  1.37s/it]
 23%|██▎       | 14349/61904 [7:07:03<17:49:05,  1.35s/it]
 23%|██▎       | 14350/61904 [7:07:04<17:34:56,  1.33s/it]
 23%|██▎       | 14351/61904 [7:07:06<17:21:09,  1.31s/it]
 23%|██▎       | 14352/61904 [7:07:07<18:23:45,  1.39s/it]
 23%|██▎       | 14353/61904 [7:07:09<18:27:21,  1.40s/it]
 23%|██▎       | 14354/61904 [7:07:10<17:55:13,  1.36s/it]
 23%|██▎       | 14355/61904 [7:07:11<17:52:59,  1.35s/it]
 23%|██▎       | 14356/61904 [7:07:13<18:08:14,  1.37s/it]
 23%|██▎       | 14357/61904 [7:07:14<18:18:31,  1.39s/it]
 23%|██▎       | 14358/61904 [7:07:15<18:20:39,  1.39s/it]
 23%|██▎       | 14359/61904 [7:07:17<17:59:18,  1.36s/it]
 23%|██▎       | 14360/61904 [7:07:18<18:02:47,  1.37s/it]
                                                          
{'loss': 2.7355, 'learning_rate': 1.7705173084402957e-07, 'epoch': 3.71}

 23%|██▎       | 14360/61904 [7:07:18<18:02:47,  1.37s/it]
 23%|██▎       | 14361/61904 [7:07:19<17:54:40,  1.36s/it]
 23%|██▎       | 14362/61904 [7:07:21<17:14:27,  1.31s/it]
 23%|██▎       | 14363/61904 [7:07:22<17:14:41,  1.31s/it]
 23%|██▎       | 14364/61904 [7:07:23<18:00:11,  1.36s/it]
 23%|██▎       | 14365/61904 [7:07:25<17:55:27,  1.36s/it]
 23%|██▎       | 14366/61904 [7:07:26<18:00:15,  1.36s/it]
 23%|██▎       | 14367/61904 [7:07:28<18:04:57,  1.37s/it]
 23%|██▎       | 14368/61904 [7:07:29<18:29:51,  1.40s/it]
 23%|██▎       | 14369/61904 [7:07:30<18:38:07,  1.41s/it]
 23%|██▎       | 14370/61904 [7:07:32<18:32:41,  1.40s/it]
 23%|██▎       | 14371/61904 [7:07:33<18:40:11,  1.41s/it]
 23%|██▎       | 14372/61904 [7:07:35<18:56:27,  1.43s/it]
 23%|██▎       | 14373/61904 [7:07:36<18:47:27,  1.42s/it]
 23%|██▎       | 14374/61904 [7:07:38<18:21:53,  1.39s/it]
 23%|██▎       | 14375/61904 [7:07:39<17:53:16,  1.35s/it]
 23%|██▎       | 14376/61904 [7:07:40<17:45:30,  1.35s/it]
 23%|██▎       | 14377/61904 [7:07:42<18:04:54,  1.37s/it]
 23%|██▎       | 14378/61904 [7:07:43<18:02:48,  1.37s/it]
 23%|██▎       | 14379/61904 [7:07:44<18:26:31,  1.40s/it]
 23%|██▎       | 14380/61904 [7:07:46<18:02:29,  1.37s/it]
                                                          
{'loss': 2.7571, 'learning_rate': 1.770193180344872e-07, 'epoch': 3.72}

 23%|██▎       | 14380/61904 [7:07:46<18:02:29,  1.37s/it]
 23%|██▎       | 14381/61904 [7:07:47<18:49:28,  1.43s/it]
 23%|██▎       | 14382/61904 [7:07:49<18:40:32,  1.41s/it]
 23%|██▎       | 14383/61904 [7:07:50<18:42:56,  1.42s/it]
 23%|██▎       | 14384/61904 [7:07:51<18:19:36,  1.39s/it]
 23%|██▎       | 14385/61904 [7:07:53<18:57:42,  1.44s/it]
 23%|██▎       | 14386/61904 [7:07:54<18:52:28,  1.43s/it]
 23%|██▎       | 14387/61904 [7:07:56<19:05:28,  1.45s/it]
 23%|██▎       | 14388/61904 [7:07:57<18:24:47,  1.40s/it]
 23%|██▎       | 14389/61904 [7:07:58<17:48:39,  1.35s/it]
 23%|██▎       | 14390/61904 [7:08:00<18:33:25,  1.41s/it]
 23%|██▎       | 14391/61904 [7:08:02<19:32:19,  1.48s/it]
 23%|██▎       | 14392/61904 [7:08:03<19:16:16,  1.46s/it]
 23%|██▎       | 14393/61904 [7:08:04<18:31:15,  1.40s/it]
 23%|██▎       | 14394/61904 [7:08:06<19:47:44,  1.50s/it]
 23%|██▎       | 14395/61904 [7:08:07<19:28:18,  1.48s/it]
 23%|██▎       | 14396/61904 [7:08:09<18:44:49,  1.42s/it]
 23%|██▎       | 14397/61904 [7:08:10<18:09:01,  1.38s/it]
 23%|██▎       | 14398/61904 [7:08:11<18:17:52,  1.39s/it]
 23%|██▎       | 14399/61904 [7:08:13<17:56:14,  1.36s/it]
 23%|██▎       | 14400/61904 [7:08:14<18:04:42,  1.37s/it]
                                                          
{'loss': 2.6742, 'learning_rate': 1.769869052249449e-07, 'epoch': 3.72}

 23%|██▎       | 14400/61904 [7:08:14<18:04:42,  1.37s/it]
 23%|██▎       | 14401/61904 [7:08:15<17:57:29,  1.36s/it]
 23%|██▎       | 14402/61904 [7:08:17<18:10:51,  1.38s/it]
 23%|██▎       | 14403/61904 [7:08:18<18:10:48,  1.38s/it]
 23%|██▎       | 14404/61904 [7:08:19<18:01:24,  1.37s/it]
 23%|██▎       | 14405/61904 [7:08:21<17:17:29,  1.31s/it]
 23%|██▎       | 14406/61904 [7:08:22<17:15:59,  1.31s/it]
 23%|██▎       | 14407/61904 [7:08:23<17:59:53,  1.36s/it]
 23%|██▎       | 14408/61904 [7:08:25<17:48:02,  1.35s/it]
 23%|██▎       | 14409/61904 [7:08:26<18:31:41,  1.40s/it]
 23%|██▎       | 14410/61904 [7:08:28<18:30:05,  1.40s/it]
 23%|██▎       | 14411/61904 [7:08:29<18:35:03,  1.41s/it]
 23%|██▎       | 14412/61904 [7:08:30<18:02:52,  1.37s/it]
 23%|██▎       | 14413/61904 [7:08:32<17:46:49,  1.35s/it]
 23%|██▎       | 14414/61904 [7:08:33<17:36:39,  1.34s/it]
 23%|██▎       | 14415/61904 [7:08:34<17:04:27,  1.29s/it]
 23%|██▎       | 14416/61904 [7:08:36<17:41:19,  1.34s/it]
 23%|██▎       | 14417/61904 [7:08:37<17:54:19,  1.36s/it]
 23%|██▎       | 14418/61904 [7:08:39<18:24:14,  1.40s/it]
 23%|██▎       | 14419/61904 [7:08:40<18:25:31,  1.40s/it]
 23%|██▎       | 14420/61904 [7:08:41<18:16:24,  1.39s/it]
                                                          
{'loss': 2.7332, 'learning_rate': 1.7695449241540256e-07, 'epoch': 3.73}

 23%|██▎       | 14420/61904 [7:08:41<18:16:24,  1.39s/it]
 23%|██▎       | 14421/61904 [7:08:43<18:01:22,  1.37s/it]
 23%|██▎       | 14422/61904 [7:08:44<17:59:10,  1.36s/it]
 23%|██▎       | 14423/61904 [7:08:45<18:05:50,  1.37s/it]
 23%|██▎       | 14424/61904 [7:08:47<18:19:56,  1.39s/it]
 23%|██▎       | 14425/61904 [7:08:48<18:50:48,  1.43s/it]
 23%|██▎       | 14426/61904 [7:08:50<18:31:38,  1.40s/it]
 23%|██▎       | 14427/61904 [7:08:51<18:24:49,  1.40s/it]
 23%|██▎       | 14428/61904 [7:08:52<18:03:24,  1.37s/it]
 23%|██▎       | 14429/61904 [7:08:54<17:48:53,  1.35s/it]
 23%|██▎       | 14430/61904 [7:08:55<18:10:37,  1.38s/it]
 23%|██▎       | 14431/61904 [7:08:56<17:50:46,  1.35s/it]
 23%|██▎       | 14432/61904 [7:08:58<17:16:21,  1.31s/it]
 23%|██▎       | 14433/61904 [7:08:59<17:19:10,  1.31s/it]
 23%|██▎       | 14434/61904 [7:09:00<17:10:42,  1.30s/it]
 23%|██▎       | 14435/61904 [7:09:01<16:50:06,  1.28s/it]
 23%|██▎       | 14436/61904 [7:09:03<17:00:39,  1.29s/it]
 23%|██▎       | 14437/61904 [7:09:04<17:23:12,  1.32s/it]
 23%|██▎       | 14438/61904 [7:09:05<17:28:56,  1.33s/it]
 23%|██▎       | 14439/61904 [7:09:07<17:57:47,  1.36s/it]
 23%|██▎       | 14440/61904 [7:09:08<17:50:17,  1.35s/it]
                                                          
{'loss': 2.7142, 'learning_rate': 1.7692207960586022e-07, 'epoch': 3.73}

 23%|██▎       | 14440/61904 [7:09:08<17:50:17,  1.35s/it]
 23%|██▎       | 14441/61904 [7:09:10<18:14:34,  1.38s/it]
 23%|██▎       | 14442/61904 [7:09:11<18:26:37,  1.40s/it]
 23%|██▎       | 14443/61904 [7:09:12<18:18:19,  1.39s/it]
 23%|██▎       | 14444/61904 [7:09:14<17:44:48,  1.35s/it]
 23%|██▎       | 14445/61904 [7:09:15<17:24:48,  1.32s/it]
 23%|██▎       | 14446/61904 [7:09:16<17:57:55,  1.36s/it]
 23%|██▎       | 14447/61904 [7:09:18<18:00:59,  1.37s/it]
 23%|██▎       | 14448/61904 [7:09:19<17:39:16,  1.34s/it]
 23%|██▎       | 14449/61904 [7:09:21<18:19:24,  1.39s/it]
 23%|██▎       | 14450/61904 [7:09:22<18:21:54,  1.39s/it]
 23%|██▎       | 14451/61904 [7:09:24<19:03:33,  1.45s/it]
 23%|██▎       | 14452/61904 [7:09:25<18:33:32,  1.41s/it]
 23%|██▎       | 14453/61904 [7:09:26<18:06:40,  1.37s/it]
 23%|██▎       | 14454/61904 [7:09:27<17:41:59,  1.34s/it]
 23%|██▎       | 14455/61904 [7:09:29<17:41:40,  1.34s/it]
 23%|██▎       | 14456/61904 [7:09:30<18:08:16,  1.38s/it]
 23%|██▎       | 14457/61904 [7:09:32<18:02:26,  1.37s/it]
 23%|██▎       | 14458/61904 [7:09:33<18:04:54,  1.37s/it]
 23%|██▎       | 14459/61904 [7:09:34<17:58:33,  1.36s/it]
 23%|██▎       | 14460/61904 [7:09:36<17:33:36,  1.33s/it]
                                                          
{'loss': 2.7682, 'learning_rate': 1.768896667963179e-07, 'epoch': 3.74}

 23%|██▎       | 14460/61904 [7:09:36<17:33:36,  1.33s/it]
 23%|██▎       | 14461/61904 [7:09:37<17:20:59,  1.32s/it]
 23%|██▎       | 14462/61904 [7:09:38<17:21:54,  1.32s/it]
 23%|██▎       | 14463/61904 [7:09:40<18:21:50,  1.39s/it]
 23%|██▎       | 14464/61904 [7:09:41<18:10:45,  1.38s/it]
 23%|██▎       | 14465/61904 [7:09:43<18:16:40,  1.39s/it]
 23%|██▎       | 14466/61904 [7:09:44<18:00:00,  1.37s/it]
 23%|██▎       | 14467/61904 [7:09:45<18:10:07,  1.38s/it]
 23%|██▎       | 14468/61904 [7:09:46<17:37:09,  1.34s/it]
 23%|██▎       | 14469/61904 [7:09:48<17:56:11,  1.36s/it]
 23%|██▎       | 14470/61904 [7:09:49<18:26:45,  1.40s/it]
 23%|██▎       | 14471/61904 [7:09:51<18:10:25,  1.38s/it]
 23%|██▎       | 14472/61904 [7:09:52<18:09:38,  1.38s/it]
 23%|██▎       | 14473/61904 [7:09:54<18:28:53,  1.40s/it]
 23%|██▎       | 14474/61904 [7:09:55<18:22:48,  1.40s/it]
 23%|██▎       | 14475/61904 [7:09:56<17:59:29,  1.37s/it]
 23%|██▎       | 14476/61904 [7:09:58<18:18:48,  1.39s/it]
 23%|██▎       | 14477/61904 [7:09:59<18:28:18,  1.40s/it]
 23%|██▎       | 14478/61904 [7:10:01<19:57:22,  1.51s/it]
 23%|██▎       | 14479/61904 [7:10:02<18:59:52,  1.44s/it]
 23%|██▎       | 14480/61904 [7:10:03<18:19:07,  1.39s/it]
                                                          
{'loss': 2.8006, 'learning_rate': 1.7685725398677557e-07, 'epoch': 3.74}

 23%|██▎       | 14480/61904 [7:10:03<18:19:07,  1.39s/it]
 23%|██▎       | 14481/61904 [7:10:05<18:22:24,  1.39s/it]
 23%|██▎       | 14482/61904 [7:10:06<18:51:14,  1.43s/it]
 23%|██▎       | 14483/61904 [7:10:08<19:05:20,  1.45s/it]
 23%|██▎       | 14484/61904 [7:10:09<18:42:43,  1.42s/it]
 23%|██▎       | 14485/61904 [7:10:11<18:29:54,  1.40s/it]
 23%|██▎       | 14486/61904 [7:10:12<18:12:26,  1.38s/it]
 23%|██▎       | 14487/61904 [7:10:13<18:07:37,  1.38s/it]
 23%|██▎       | 14488/61904 [7:10:15<18:12:53,  1.38s/it]
 23%|██▎       | 14489/61904 [7:10:16<17:54:31,  1.36s/it]
 23%|██▎       | 14490/61904 [7:10:17<17:47:51,  1.35s/it]
 23%|██▎       | 14491/61904 [7:10:19<18:18:27,  1.39s/it]
 23%|██▎       | 14492/61904 [7:10:20<17:55:13,  1.36s/it]
 23%|██▎       | 14493/61904 [7:10:21<17:53:58,  1.36s/it]
 23%|██▎       | 14494/61904 [7:10:23<18:06:14,  1.37s/it]
 23%|██▎       | 14495/61904 [7:10:24<18:18:08,  1.39s/it]
 23%|██▎       | 14496/61904 [7:10:26<19:01:21,  1.44s/it]
 23%|██▎       | 14497/61904 [7:10:27<18:28:27,  1.40s/it]
 23%|██▎       | 14498/61904 [7:10:29<18:18:59,  1.39s/it]
 23%|██▎       | 14499/61904 [7:10:30<18:01:36,  1.37s/it]
 23%|██▎       | 14500/61904 [7:10:31<18:37:02,  1.41s/it]
                                                          
{'loss': 2.7649, 'learning_rate': 1.7682484117723323e-07, 'epoch': 3.75}

 23%|██▎       | 14500/61904 [7:10:31<18:37:02,  1.41s/it]
 23%|██▎       | 14501/61904 [7:10:33<18:16:38,  1.39s/it]
 23%|██▎       | 14502/61904 [7:10:34<18:17:10,  1.39s/it]
 23%|██▎       | 14503/61904 [7:10:36<18:31:30,  1.41s/it]
 23%|██▎       | 14504/61904 [7:10:37<18:42:53,  1.42s/it]
 23%|██▎       | 14505/61904 [7:10:38<18:10:36,  1.38s/it]
 23%|██▎       | 14506/61904 [7:10:40<18:10:41,  1.38s/it]
 23%|██▎       | 14507/61904 [7:10:41<19:02:12,  1.45s/it]
 23%|██▎       | 14508/61904 [7:10:43<19:31:49,  1.48s/it]
 23%|██▎       | 14509/61904 [7:10:44<18:44:08,  1.42s/it]
 23%|██▎       | 14510/61904 [7:10:46<18:57:26,  1.44s/it]
 23%|██▎       | 14511/61904 [7:10:47<18:25:53,  1.40s/it]
 23%|██▎       | 14512/61904 [7:10:48<18:24:31,  1.40s/it]
 23%|██▎       | 14513/61904 [7:10:50<18:37:45,  1.42s/it]
 23%|██▎       | 14514/61904 [7:10:51<18:34:53,  1.41s/it]
 23%|██▎       | 14515/61904 [7:10:52<18:13:24,  1.38s/it]
 23%|██▎       | 14516/61904 [7:10:54<17:56:30,  1.36s/it]
 23%|██▎       | 14517/61904 [7:10:55<18:09:06,  1.38s/it]
 23%|██▎       | 14518/61904 [7:10:57<17:59:57,  1.37s/it]
 23%|██▎       | 14519/61904 [7:10:58<18:31:10,  1.41s/it]
 23%|██▎       | 14520/61904 [7:10:59<18:11:48,  1.38s/it]
                                                          
{'loss': 2.7049, 'learning_rate': 1.7679242836769092e-07, 'epoch': 3.75}

 23%|██▎       | 14520/61904 [7:10:59<18:11:48,  1.38s/it]
 23%|██▎       | 14521/61904 [7:11:01<17:40:21,  1.34s/it]
 23%|██▎       | 14522/61904 [7:11:02<17:52:51,  1.36s/it]
 23%|██▎       | 14523/61904 [7:11:03<17:29:40,  1.33s/it]
 23%|██▎       | 14524/61904 [7:11:05<18:35:10,  1.41s/it]
 23%|██▎       | 14525/61904 [7:11:06<18:38:56,  1.42s/it]
 23%|██▎       | 14526/61904 [7:11:08<18:35:12,  1.41s/it]
 23%|██▎       | 14527/61904 [7:11:09<18:00:59,  1.37s/it]
 23%|██▎       | 14528/61904 [7:11:10<17:52:05,  1.36s/it]
 23%|██▎       | 14529/61904 [7:11:12<18:01:55,  1.37s/it]
 23%|██▎       | 14530/61904 [7:11:13<17:33:39,  1.33s/it]
 23%|██▎       | 14531/61904 [7:11:14<17:52:35,  1.36s/it]
 23%|██▎       | 14532/61904 [7:11:16<18:35:50,  1.41s/it]
 23%|██▎       | 14533/61904 [7:11:17<18:33:51,  1.41s/it]
 23%|██▎       | 14534/61904 [7:11:19<17:54:55,  1.36s/it]
 23%|██▎       | 14535/61904 [7:11:20<17:52:41,  1.36s/it]
 23%|██▎       | 14536/61904 [7:11:21<18:42:56,  1.42s/it]
 23%|██▎       | 14537/61904 [7:11:23<18:20:17,  1.39s/it]
 23%|██▎       | 14538/61904 [7:11:24<17:43:58,  1.35s/it]
 23%|██▎       | 14539/61904 [7:11:25<18:05:26,  1.37s/it]
 23%|██▎       | 14540/61904 [7:11:27<17:50:32,  1.36s/it]
                                                          
{'loss': 2.7923, 'learning_rate': 1.7676001555814855e-07, 'epoch': 3.76}

 23%|██▎       | 14540/61904 [7:11:27<17:50:32,  1.36s/it]
 23%|██▎       | 14541/61904 [7:11:28<18:03:19,  1.37s/it]
 23%|██▎       | 14542/61904 [7:11:30<18:24:10,  1.40s/it]
 23%|██▎       | 14543/61904 [7:11:31<17:44:01,  1.35s/it]
 23%|██▎       | 14544/61904 [7:11:32<18:09:59,  1.38s/it]
 23%|██▎       | 14545/61904 [7:11:34<18:13:51,  1.39s/it]
 23%|██▎       | 14546/61904 [7:11:35<19:22:02,  1.47s/it]
 23%|██▎       | 14547/61904 [7:11:37<19:31:36,  1.48s/it]
 24%|██▎       | 14548/61904 [7:11:38<19:05:34,  1.45s/it]
 24%|██▎       | 14549/61904 [7:11:40<18:52:27,  1.43s/it]
 24%|██▎       | 14550/61904 [7:11:41<18:25:44,  1.40s/it]
 24%|██▎       | 14551/61904 [7:11:42<18:22:37,  1.40s/it]
 24%|██▎       | 14552/61904 [7:11:44<18:26:28,  1.40s/it]
 24%|██▎       | 14553/61904 [7:11:45<18:10:46,  1.38s/it]
 24%|██▎       | 14554/61904 [7:11:47<18:32:50,  1.41s/it]
 24%|██▎       | 14555/61904 [7:11:48<17:44:21,  1.35s/it]
 24%|██▎       | 14556/61904 [7:11:49<17:44:32,  1.35s/it]
 24%|██▎       | 14557/61904 [7:11:51<17:52:43,  1.36s/it]
 24%|██▎       | 14558/61904 [7:11:52<17:17:33,  1.31s/it]
 24%|██▎       | 14559/61904 [7:11:53<16:59:28,  1.29s/it]
 24%|██▎       | 14560/61904 [7:11:54<17:05:28,  1.30s/it]
                                                          
{'loss': 2.6909, 'learning_rate': 1.7672760274860624e-07, 'epoch': 3.76}

 24%|██▎       | 14560/61904 [7:11:54<17:05:28,  1.30s/it]
 24%|██▎       | 14561/61904 [7:11:56<17:46:16,  1.35s/it]
 24%|██▎       | 14562/61904 [7:11:57<17:26:46,  1.33s/it]
 24%|██▎       | 14563/61904 [7:11:58<17:45:45,  1.35s/it]
 24%|██▎       | 14564/61904 [7:12:00<17:38:11,  1.34s/it]
 24%|██▎       | 14565/61904 [7:12:01<17:43:13,  1.35s/it]
 24%|██▎       | 14566/61904 [7:12:03<17:47:07,  1.35s/it]
 24%|██▎       | 14567/61904 [7:12:04<17:48:33,  1.35s/it]
 24%|██▎       | 14568/61904 [7:12:05<18:18:47,  1.39s/it]
 24%|██▎       | 14569/61904 [7:12:07<19:06:54,  1.45s/it]
 24%|██▎       | 14570/61904 [7:12:08<19:00:04,  1.45s/it]
 24%|██▎       | 14571/61904 [7:12:10<18:12:24,  1.38s/it]
 24%|██▎       | 14572/61904 [7:12:11<18:20:01,  1.39s/it]
 24%|██▎       | 14573/61904 [7:12:12<17:59:30,  1.37s/it]
 24%|██▎       | 14574/61904 [7:12:14<17:45:04,  1.35s/it]
 24%|██▎       | 14575/61904 [7:12:15<18:12:28,  1.38s/it]
 24%|██▎       | 14576/61904 [7:12:17<18:27:30,  1.40s/it]
 24%|██▎       | 14577/61904 [7:12:18<18:07:59,  1.38s/it]
 24%|██▎       | 14578/61904 [7:12:19<17:28:40,  1.33s/it]
 24%|██▎       | 14579/61904 [7:12:20<17:23:34,  1.32s/it]
 24%|██▎       | 14580/61904 [7:12:22<18:27:08,  1.40s/it]
                                                          
{'loss': 2.7651, 'learning_rate': 1.7669518993906393e-07, 'epoch': 3.77}

 24%|██▎       | 14580/61904 [7:12:22<18:27:08,  1.40s/it]
 24%|██▎       | 14581/61904 [7:12:23<17:59:28,  1.37s/it]
 24%|██▎       | 14582/61904 [7:12:25<17:44:41,  1.35s/it]
 24%|██▎       | 14583/61904 [7:12:26<17:57:29,  1.37s/it]
 24%|██▎       | 14584/61904 [7:12:27<18:14:12,  1.39s/it]
 24%|██▎       | 14585/61904 [7:12:29<18:23:06,  1.40s/it]
 24%|██▎       | 14586/61904 [7:12:30<18:17:05,  1.39s/it]
 24%|██▎       | 14587/61904 [7:12:32<18:02:17,  1.37s/it]
 24%|██▎       | 14588/61904 [7:12:33<17:51:05,  1.36s/it]
 24%|██▎       | 14589/61904 [7:12:34<17:03:44,  1.30s/it]
 24%|██▎       | 14590/61904 [7:12:36<17:44:09,  1.35s/it]
 24%|██▎       | 14591/61904 [7:12:37<17:31:41,  1.33s/it]
 24%|██▎       | 14592/61904 [7:12:38<17:33:51,  1.34s/it]
 24%|██▎       | 14593/61904 [7:12:39<17:30:58,  1.33s/it]
 24%|██▎       | 14594/61904 [7:12:41<17:40:33,  1.35s/it]
 24%|██▎       | 14595/61904 [7:12:42<17:54:19,  1.36s/it]
 24%|██▎       | 14596/61904 [7:12:44<18:18:32,  1.39s/it]
 24%|██▎       | 14597/61904 [7:12:45<17:59:40,  1.37s/it]
 24%|██▎       | 14598/61904 [7:12:46<18:02:02,  1.37s/it]
 24%|██▎       | 14599/61904 [7:12:48<17:42:21,  1.35s/it]
 24%|██▎       | 14600/61904 [7:12:49<18:05:34,  1.38s/it]
                                                          
{'loss': 2.6994, 'learning_rate': 1.7666277712952157e-07, 'epoch': 3.77}

 24%|██▎       | 14600/61904 [7:12:49<18:05:34,  1.38s/it]
 24%|██▎       | 14601/61904 [7:12:51<18:15:47,  1.39s/it]
 24%|██▎       | 14602/61904 [7:12:52<18:02:07,  1.37s/it]
 24%|██▎       | 14603/61904 [7:12:53<17:59:02,  1.37s/it]
 24%|██▎       | 14604/61904 [7:12:55<17:42:10,  1.35s/it]
 24%|██▎       | 14605/61904 [7:12:56<18:00:24,  1.37s/it]
 24%|██▎       | 14606/61904 [7:12:57<18:17:00,  1.39s/it]
 24%|██▎       | 14607/61904 [7:12:59<18:25:30,  1.40s/it]
 24%|██▎       | 14608/61904 [7:13:00<18:44:59,  1.43s/it]
 24%|██▎       | 14609/61904 [7:13:02<18:58:01,  1.44s/it]
 24%|██▎       | 14610/61904 [7:13:03<18:34:00,  1.41s/it]
 24%|██▎       | 14611/61904 [7:13:04<18:04:28,  1.38s/it]
 24%|██▎       | 14612/61904 [7:13:06<18:19:48,  1.40s/it]
 24%|██▎       | 14613/61904 [7:13:07<17:48:09,  1.36s/it]
 24%|██▎       | 14614/61904 [7:13:09<17:55:19,  1.36s/it]
 24%|██▎       | 14615/61904 [7:13:10<17:45:57,  1.35s/it]
 24%|██▎       | 14616/61904 [7:13:11<17:47:20,  1.35s/it]
 24%|██▎       | 14617/61904 [7:13:13<18:03:40,  1.38s/it]
 24%|██▎       | 14618/61904 [7:13:14<18:03:36,  1.37s/it]
 24%|██▎       | 14619/61904 [7:13:15<18:09:31,  1.38s/it]
 24%|██▎       | 14620/61904 [7:13:17<17:39:24,  1.34s/it]
                                                          
{'loss': 2.7794, 'learning_rate': 1.7663036431997925e-07, 'epoch': 3.78}

 24%|██▎       | 14620/61904 [7:13:17<17:39:24,  1.34s/it]
 24%|██▎       | 14621/61904 [7:13:18<17:59:44,  1.37s/it]
 24%|██▎       | 14622/61904 [7:13:20<18:47:48,  1.43s/it]
 24%|██▎       | 14623/61904 [7:13:21<18:49:50,  1.43s/it]
 24%|██▎       | 14624/61904 [7:13:22<18:23:35,  1.40s/it]
 24%|██▎       | 14625/61904 [7:13:24<18:08:19,  1.38s/it]
 24%|██▎       | 14626/61904 [7:13:25<18:01:29,  1.37s/it]
 24%|██▎       | 14627/61904 [7:13:26<17:42:48,  1.35s/it]
 24%|██▎       | 14628/61904 [7:13:28<17:13:55,  1.31s/it]
 24%|██▎       | 14629/61904 [7:13:29<17:18:17,  1.32s/it]
 24%|██▎       | 14630/61904 [7:13:30<17:34:12,  1.34s/it]
 24%|██▎       | 14631/61904 [7:13:32<17:17:56,  1.32s/it]
 24%|██▎       | 14632/61904 [7:13:33<17:10:24,  1.31s/it]
 24%|██▎       | 14633/61904 [7:13:34<18:08:43,  1.38s/it]
 24%|██▎       | 14634/61904 [7:13:36<18:20:35,  1.40s/it]
 24%|██▎       | 14635/61904 [7:13:37<18:42:29,  1.42s/it]
 24%|██▎       | 14636/61904 [7:13:39<18:25:51,  1.40s/it]
 24%|██▎       | 14637/61904 [7:13:40<18:29:17,  1.41s/it]
 24%|██▎       | 14638/61904 [7:13:42<18:28:29,  1.41s/it]
 24%|██▎       | 14639/61904 [7:13:43<18:46:02,  1.43s/it]
 24%|██▎       | 14640/61904 [7:13:44<18:26:22,  1.40s/it]
                                                          
{'loss': 2.712, 'learning_rate': 1.7659795151043692e-07, 'epoch': 3.78}

 24%|██▎       | 14640/61904 [7:13:44<18:26:22,  1.40s/it]
 24%|██▎       | 14641/61904 [7:13:46<18:37:50,  1.42s/it]
 24%|██▎       | 14642/61904 [7:13:47<18:32:50,  1.41s/it]
 24%|██▎       | 14643/61904 [7:13:49<18:20:30,  1.40s/it]
 24%|██▎       | 14644/61904 [7:13:50<18:07:42,  1.38s/it]
 24%|██▎       | 14645/61904 [7:13:51<18:23:21,  1.40s/it]
 24%|██▎       | 14646/61904 [7:13:53<18:31:54,  1.41s/it]
 24%|██▎       | 14647/61904 [7:13:54<18:25:43,  1.40s/it]
 24%|██▎       | 14648/61904 [7:13:56<18:36:10,  1.42s/it]
 24%|██▎       | 14649/61904 [7:13:57<18:13:02,  1.39s/it]
 24%|██▎       | 14650/61904 [7:13:58<18:16:32,  1.39s/it]
 24%|██▎       | 14651/61904 [7:14:00<18:25:40,  1.40s/it]
 24%|██▎       | 14652/61904 [7:14:01<19:13:18,  1.46s/it]
 24%|██▎       | 14653/61904 [7:14:03<19:00:30,  1.45s/it]
 24%|██▎       | 14654/61904 [7:14:04<18:23:32,  1.40s/it]
 24%|██▎       | 14655/61904 [7:14:06<19:00:16,  1.45s/it]
 24%|██▎       | 14656/61904 [7:14:07<18:08:07,  1.38s/it]
 24%|██▎       | 14657/61904 [7:14:08<18:19:49,  1.40s/it]
 24%|██▎       | 14658/61904 [7:14:10<18:26:17,  1.40s/it]
 24%|██▎       | 14659/61904 [7:14:11<18:21:07,  1.40s/it]
 24%|██▎       | 14660/61904 [7:14:13<18:18:30,  1.40s/it]
                                                          
{'loss': 2.698, 'learning_rate': 1.7656553870089458e-07, 'epoch': 3.79}

 24%|██▎       | 14660/61904 [7:14:13<18:18:30,  1.40s/it]
 24%|██▎       | 14661/61904 [7:14:14<18:01:34,  1.37s/it]
 24%|██▎       | 14662/61904 [7:14:15<17:51:34,  1.36s/it]
 24%|██▎       | 14663/61904 [7:14:17<18:35:51,  1.42s/it]
 24%|██▎       | 14664/61904 [7:14:18<18:34:04,  1.42s/it]
 24%|██▎       | 14665/61904 [7:14:19<18:02:52,  1.38s/it]
 24%|██▎       | 14666/61904 [7:14:21<17:42:54,  1.35s/it]
 24%|██▎       | 14667/61904 [7:14:22<18:20:02,  1.40s/it]
 24%|██▎       | 14668/61904 [7:14:24<18:32:15,  1.41s/it]
 24%|██▎       | 14669/61904 [7:14:25<18:34:48,  1.42s/it]
 24%|██▎       | 14670/61904 [7:14:27<18:37:43,  1.42s/it]
 24%|██▎       | 14671/61904 [7:14:28<18:47:12,  1.43s/it]
 24%|██▎       | 14672/61904 [7:14:29<18:27:20,  1.41s/it]
 24%|██▎       | 14673/61904 [7:14:31<18:19:37,  1.40s/it]
 24%|██▎       | 14674/61904 [7:14:32<18:31:28,  1.41s/it]
 24%|██▎       | 14675/61904 [7:14:34<18:40:26,  1.42s/it]
 24%|██▎       | 14676/61904 [7:14:35<18:09:29,  1.38s/it]
 24%|██▎       | 14677/61904 [7:14:36<17:44:54,  1.35s/it]
 24%|██▎       | 14678/61904 [7:14:38<18:11:57,  1.39s/it]
 24%|██▎       | 14679/61904 [7:14:39<17:57:57,  1.37s/it]
 24%|██▎       | 14680/61904 [7:14:41<18:29:06,  1.41s/it]
                                                          
{'loss': 2.6473, 'learning_rate': 1.7653312589135227e-07, 'epoch': 3.79}

 24%|██▎       | 14680/61904 [7:14:41<18:29:06,  1.41s/it]
 24%|██▎       | 14681/61904 [7:14:42<17:58:33,  1.37s/it]
 24%|██▎       | 14682/61904 [7:14:43<18:14:58,  1.39s/it]
 24%|██▎       | 14683/61904 [7:14:45<18:13:35,  1.39s/it]
 24%|██▎       | 14684/61904 [7:14:46<18:15:46,  1.39s/it]
 24%|██▎       | 14685/61904 [7:14:47<17:59:33,  1.37s/it]
 24%|██▎       | 14686/61904 [7:14:49<18:22:12,  1.40s/it]
 24%|██▎       | 14687/61904 [7:14:50<18:11:22,  1.39s/it]
 24%|██▎       | 14688/61904 [7:14:52<18:27:53,  1.41s/it]
 24%|██▎       | 14689/61904 [7:14:53<18:14:04,  1.39s/it]
 24%|██▎       | 14690/61904 [7:14:54<18:27:33,  1.41s/it]
 24%|██▎       | 14691/61904 [7:14:56<18:31:53,  1.41s/it]
 24%|██▎       | 14692/61904 [7:14:57<18:48:49,  1.43s/it]
 24%|██▎       | 14693/61904 [7:14:59<19:04:39,  1.45s/it]
 24%|██▎       | 14694/61904 [7:15:00<18:22:14,  1.40s/it]
 24%|██▎       | 14695/61904 [7:15:01<18:09:54,  1.39s/it]
 24%|██▎       | 14696/61904 [7:15:03<17:58:48,  1.37s/it]
 24%|██▎       | 14697/61904 [7:15:04<17:48:33,  1.36s/it]
 24%|██▎       | 14698/61904 [7:15:05<17:55:36,  1.37s/it]
 24%|██▎       | 14699/61904 [7:15:07<17:43:20,  1.35s/it]
 24%|██▎       | 14700/61904 [7:15:08<17:32:25,  1.34s/it]
                                                          
{'loss': 2.7231, 'learning_rate': 1.7650071308180993e-07, 'epoch': 3.8}

 24%|██▎       | 14700/61904 [7:15:08<17:32:25,  1.34s/it]
 24%|██▎       | 14701/61904 [7:15:10<17:43:18,  1.35s/it]
 24%|██▎       | 14702/61904 [7:15:11<18:02:10,  1.38s/it]
 24%|██▍       | 14703/61904 [7:15:12<18:46:11,  1.43s/it]
 24%|██▍       | 14704/61904 [7:15:14<18:44:36,  1.43s/it]
 24%|██▍       | 14705/61904 [7:15:16<19:24:19,  1.48s/it]
 24%|██▍       | 14706/61904 [7:15:17<20:27:40,  1.56s/it]
 24%|██▍       | 14707/61904 [7:15:19<19:50:57,  1.51s/it]
 24%|██▍       | 14708/61904 [7:15:20<18:58:45,  1.45s/it]
 24%|██▍       | 14709/61904 [7:15:21<18:27:43,  1.41s/it]
 24%|██▍       | 14710/61904 [7:15:23<18:22:19,  1.40s/it]
 24%|██▍       | 14711/61904 [7:15:24<18:25:44,  1.41s/it]
 24%|██▍       | 14712/61904 [7:15:25<18:01:18,  1.37s/it]
 24%|██▍       | 14713/61904 [7:15:27<18:13:25,  1.39s/it]
 24%|██▍       | 14714/61904 [7:15:28<18:05:08,  1.38s/it]
 24%|██▍       | 14715/61904 [7:15:30<17:54:53,  1.37s/it]
 24%|██▍       | 14716/61904 [7:15:31<17:43:07,  1.35s/it]
 24%|██▍       | 14717/61904 [7:15:32<18:06:17,  1.38s/it]
 24%|██▍       | 14718/61904 [7:15:34<18:05:40,  1.38s/it]
 24%|██▍       | 14719/61904 [7:15:35<18:20:59,  1.40s/it]
 24%|██▍       | 14720/61904 [7:15:36<17:57:47,  1.37s/it]
                                                          
{'loss': 2.7367, 'learning_rate': 1.764683002722676e-07, 'epoch': 3.8}

 24%|██▍       | 14720/61904 [7:15:36<17:57:47,  1.37s/it]
 24%|██▍       | 14721/61904 [7:15:38<17:57:08,  1.37s/it]
 24%|██▍       | 14722/61904 [7:15:39<17:59:46,  1.37s/it]
 24%|██▍       | 14723/61904 [7:15:40<17:40:28,  1.35s/it]
 24%|██▍       | 14724/61904 [7:15:42<17:48:04,  1.36s/it]
 24%|██▍       | 14725/61904 [7:15:43<18:00:33,  1.37s/it]
 24%|██▍       | 14726/61904 [7:15:45<18:13:13,  1.39s/it]
 24%|██▍       | 14727/61904 [7:15:46<18:11:47,  1.39s/it]
 24%|██▍       | 14728/61904 [7:15:48<19:06:20,  1.46s/it]
 24%|██▍       | 14729/61904 [7:15:49<18:36:10,  1.42s/it]
 24%|██▍       | 14730/61904 [7:15:50<18:31:25,  1.41s/it]
 24%|██▍       | 14731/61904 [7:15:52<18:24:28,  1.40s/it]
 24%|██▍       | 14732/61904 [7:15:53<18:12:07,  1.39s/it]
 24%|██▍       | 14733/61904 [7:15:55<19:01:39,  1.45s/it]
 24%|██▍       | 14734/61904 [7:15:56<19:05:54,  1.46s/it]
 24%|██▍       | 14735/61904 [7:15:58<19:28:20,  1.49s/it]
 24%|██▍       | 14736/61904 [7:15:59<18:55:18,  1.44s/it]
 24%|██▍       | 14737/61904 [7:16:00<18:33:03,  1.42s/it]
 24%|██▍       | 14738/61904 [7:16:02<18:37:42,  1.42s/it]
 24%|██▍       | 14739/61904 [7:16:03<18:19:36,  1.40s/it]
 24%|██▍       | 14740/61904 [7:16:05<17:50:13,  1.36s/it]
                                                          
{'loss': 2.7298, 'learning_rate': 1.7643588746272528e-07, 'epoch': 3.81}

 24%|██▍       | 14740/61904 [7:16:05<17:50:13,  1.36s/it]
 24%|██▍       | 14741/61904 [7:16:06<18:23:36,  1.40s/it]
 24%|██▍       | 14742/61904 [7:16:07<18:36:18,  1.42s/it]
 24%|██▍       | 14743/61904 [7:16:09<18:46:32,  1.43s/it]
 24%|██▍       | 14744/61904 [7:16:10<18:05:57,  1.38s/it]
 24%|██▍       | 14745/61904 [7:16:12<18:16:38,  1.40s/it]
 24%|██▍       | 14746/61904 [7:16:13<18:09:27,  1.39s/it]
 24%|██▍       | 14747/61904 [7:16:14<18:13:08,  1.39s/it]
 24%|██▍       | 14748/61904 [7:16:16<18:05:42,  1.38s/it]
 24%|██▍       | 14749/61904 [7:16:17<18:11:24,  1.39s/it]
 24%|██▍       | 14750/61904 [7:16:19<18:38:37,  1.42s/it]
 24%|██▍       | 14751/61904 [7:16:20<19:09:44,  1.46s/it]
 24%|██▍       | 14752/61904 [7:16:22<19:12:11,  1.47s/it]
 24%|██▍       | 14753/61904 [7:16:23<19:17:01,  1.47s/it]
 24%|██▍       | 14754/61904 [7:16:25<19:00:56,  1.45s/it]
 24%|██▍       | 14755/61904 [7:16:26<18:47:32,  1.43s/it]
 24%|██▍       | 14756/61904 [7:16:27<18:48:27,  1.44s/it]
 24%|██▍       | 14757/61904 [7:16:29<18:47:23,  1.43s/it]
 24%|██▍       | 14758/61904 [7:16:30<19:13:31,  1.47s/it]
 24%|██▍       | 14759/61904 [7:16:32<18:29:04,  1.41s/it]
 24%|██▍       | 14760/61904 [7:16:33<18:25:37,  1.41s/it]
                                                          
{'loss': 2.7584, 'learning_rate': 1.764034746531829e-07, 'epoch': 3.81}

 24%|██▍       | 14760/61904 [7:16:33<18:25:37,  1.41s/it]
 24%|██▍       | 14761/61904 [7:16:34<18:20:19,  1.40s/it]
 24%|██▍       | 14762/61904 [7:16:36<18:21:39,  1.40s/it]
 24%|██▍       | 14763/61904 [7:16:37<17:45:51,  1.36s/it]
 24%|██▍       | 14764/61904 [7:16:39<18:04:05,  1.38s/it]
 24%|██▍       | 14765/61904 [7:16:40<18:26:07,  1.41s/it]
 24%|██▍       | 14766/61904 [7:16:41<18:34:29,  1.42s/it]
 24%|██▍       | 14767/61904 [7:16:43<18:16:28,  1.40s/it]
 24%|██▍       | 14768/61904 [7:16:44<17:49:49,  1.36s/it]
 24%|██▍       | 14769/61904 [7:16:45<17:56:40,  1.37s/it]
 24%|██▍       | 14770/61904 [7:16:47<17:47:01,  1.36s/it]
 24%|██▍       | 14771/61904 [7:16:48<17:58:23,  1.37s/it]
 24%|██▍       | 14772/61904 [7:16:50<18:24:27,  1.41s/it]
 24%|██▍       | 14773/61904 [7:16:51<19:12:21,  1.47s/it]
 24%|██▍       | 14774/61904 [7:16:53<18:41:31,  1.43s/it]
 24%|██▍       | 14775/61904 [7:16:54<18:34:54,  1.42s/it]
 24%|██▍       | 14776/61904 [7:16:55<18:00:24,  1.38s/it]
 24%|██▍       | 14777/61904 [7:16:57<17:39:36,  1.35s/it]
 24%|██▍       | 14778/61904 [7:16:58<17:31:39,  1.34s/it]
 24%|██▍       | 14779/61904 [7:16:59<17:20:23,  1.32s/it]
 24%|██▍       | 14780/61904 [7:17:01<17:46:23,  1.36s/it]
                                                          
{'loss': 2.7566, 'learning_rate': 1.763710618436406e-07, 'epoch': 3.82}

 24%|██▍       | 14780/61904 [7:17:01<17:46:23,  1.36s/it]
 24%|██▍       | 14781/61904 [7:17:02<18:26:00,  1.41s/it]
 24%|██▍       | 14782/61904 [7:17:03<17:51:34,  1.36s/it]
 24%|██▍       | 14783/61904 [7:17:05<18:24:58,  1.41s/it]
 24%|██▍       | 14784/61904 [7:17:06<18:00:15,  1.38s/it]
 24%|██▍       | 14785/61904 [7:17:08<17:43:49,  1.35s/it]
 24%|██▍       | 14786/61904 [7:17:09<18:28:24,  1.41s/it]
 24%|██▍       | 14787/61904 [7:17:10<17:44:00,  1.35s/it]
 24%|██▍       | 14788/61904 [7:17:12<17:47:58,  1.36s/it]
 24%|██▍       | 14789/61904 [7:17:13<18:06:45,  1.38s/it]
 24%|██▍       | 14790/61904 [7:17:14<17:49:13,  1.36s/it]
 24%|██▍       | 14791/61904 [7:17:16<17:26:10,  1.33s/it]
 24%|██▍       | 14792/61904 [7:17:17<18:06:57,  1.38s/it]
 24%|██▍       | 14793/61904 [7:17:18<17:41:08,  1.35s/it]
 24%|██▍       | 14794/61904 [7:17:20<17:30:43,  1.34s/it]
 24%|██▍       | 14795/61904 [7:17:21<17:36:01,  1.35s/it]
 24%|██▍       | 14796/61904 [7:17:22<17:11:44,  1.31s/it]
 24%|██▍       | 14797/61904 [7:17:24<17:27:34,  1.33s/it]
 24%|██▍       | 14798/61904 [7:17:25<17:54:33,  1.37s/it]
 24%|██▍       | 14799/61904 [7:17:27<18:18:09,  1.40s/it]
 24%|██▍       | 14800/61904 [7:17:28<19:11:39,  1.47s/it]
                                                          
{'loss': 2.753, 'learning_rate': 1.7633864903409826e-07, 'epoch': 3.82}

 24%|██▍       | 14800/61904 [7:17:28<19:11:39,  1.47s/it]
 24%|██▍       | 14801/61904 [7:17:30<18:41:48,  1.43s/it]
 24%|██▍       | 14802/61904 [7:17:31<18:41:33,  1.43s/it]
 24%|██▍       | 14803/61904 [7:17:33<18:43:19,  1.43s/it]
 24%|██▍       | 14804/61904 [7:17:34<18:01:53,  1.38s/it]
 24%|██▍       | 14805/61904 [7:17:35<17:55:54,  1.37s/it]
 24%|██▍       | 14806/61904 [7:17:36<17:46:57,  1.36s/it]
 24%|██▍       | 14807/61904 [7:17:38<17:54:09,  1.37s/it]
 24%|██▍       | 14808/61904 [7:17:39<18:12:28,  1.39s/it]
 24%|██▍       | 14809/61904 [7:17:41<17:53:28,  1.37s/it]
 24%|██▍       | 14810/61904 [7:17:42<17:41:56,  1.35s/it]
 24%|██▍       | 14811/61904 [7:17:43<17:10:36,  1.31s/it]
 24%|██▍       | 14812/61904 [7:17:44<16:53:36,  1.29s/it]
 24%|██▍       | 14813/61904 [7:17:46<17:29:06,  1.34s/it]
 24%|██▍       | 14814/61904 [7:17:47<17:30:42,  1.34s/it]
 24%|██▍       | 14815/61904 [7:17:49<18:02:44,  1.38s/it]
 24%|██▍       | 14816/61904 [7:17:50<17:26:08,  1.33s/it]
 24%|██▍       | 14817/61904 [7:17:51<17:50:52,  1.36s/it]
 24%|██▍       | 14818/61904 [7:17:53<17:57:08,  1.37s/it]
 24%|██▍       | 14819/61904 [7:17:54<17:43:22,  1.36s/it]
 24%|██▍       | 14820/61904 [7:17:55<17:37:03,  1.35s/it]
                                                          
{'loss': 2.7702, 'learning_rate': 1.7630623622455592e-07, 'epoch': 3.83}

 24%|██▍       | 14820/61904 [7:17:55<17:37:03,  1.35s/it]
 24%|██▍       | 14821/61904 [7:17:57<17:54:55,  1.37s/it]
 24%|██▍       | 14822/61904 [7:17:58<17:47:25,  1.36s/it]
 24%|██▍       | 14823/61904 [7:17:59<17:57:12,  1.37s/it]
 24%|██▍       | 14824/61904 [7:18:01<17:48:19,  1.36s/it]
 24%|██▍       | 14825/61904 [7:18:02<18:04:42,  1.38s/it]
 24%|██▍       | 14826/61904 [7:18:04<17:56:38,  1.37s/it]
 24%|██▍       | 14827/61904 [7:18:05<17:46:27,  1.36s/it]
 24%|██▍       | 14828/61904 [7:18:06<18:19:05,  1.40s/it]
 24%|██▍       | 14829/61904 [7:18:08<18:40:45,  1.43s/it]
 24%|██▍       | 14830/61904 [7:18:09<18:56:54,  1.45s/it]
 24%|██▍       | 14831/61904 [7:18:11<19:15:57,  1.47s/it]
 24%|██▍       | 14832/61904 [7:18:12<19:16:45,  1.47s/it]
 24%|██▍       | 14833/61904 [7:18:14<19:39:42,  1.50s/it]
 24%|██▍       | 14834/61904 [7:18:15<19:16:10,  1.47s/it]
 24%|██▍       | 14835/61904 [7:18:17<19:05:46,  1.46s/it]
 24%|██▍       | 14836/61904 [7:18:18<18:45:32,  1.43s/it]
 24%|██▍       | 14837/61904 [7:18:20<18:31:14,  1.42s/it]
 24%|██▍       | 14838/61904 [7:18:21<18:32:02,  1.42s/it]
 24%|██▍       | 14839/61904 [7:18:22<18:30:25,  1.42s/it]
 24%|██▍       | 14840/61904 [7:18:24<18:27:18,  1.41s/it]
                                                          
{'loss': 2.7236, 'learning_rate': 1.7627382341501361e-07, 'epoch': 3.84}

 24%|██▍       | 14840/61904 [7:18:24<18:27:18,  1.41s/it]
 24%|██▍       | 14841/61904 [7:18:25<18:24:02,  1.41s/it]
 24%|██▍       | 14842/61904 [7:18:27<18:36:06,  1.42s/it]
 24%|██▍       | 14843/61904 [7:18:28<18:01:38,  1.38s/it]
 24%|██▍       | 14844/61904 [7:18:30<18:45:48,  1.44s/it]
 24%|██▍       | 14845/61904 [7:18:31<19:01:21,  1.46s/it]
 24%|██▍       | 14846/61904 [7:18:33<19:12:15,  1.47s/it]
 24%|██▍       | 14847/61904 [7:18:34<18:47:12,  1.44s/it]
 24%|██▍       | 14848/61904 [7:18:35<18:31:40,  1.42s/it]
 24%|██▍       | 14849/61904 [7:18:37<18:51:53,  1.44s/it]
 24%|██▍       | 14850/61904 [7:18:38<18:12:02,  1.39s/it]
 24%|██▍       | 14851/61904 [7:18:39<18:13:33,  1.39s/it]
 24%|██▍       | 14852/61904 [7:18:41<17:59:27,  1.38s/it]
 24%|██▍       | 14853/61904 [7:18:42<17:58:05,  1.37s/it]
 24%|██▍       | 14854/61904 [7:18:44<18:00:52,  1.38s/it]
 24%|██▍       | 14855/61904 [7:18:45<17:51:16,  1.37s/it]
 24%|██▍       | 14856/61904 [7:18:46<18:18:23,  1.40s/it]
 24%|██▍       | 14857/61904 [7:18:48<18:29:23,  1.41s/it]
 24%|██▍       | 14858/61904 [7:18:49<18:14:39,  1.40s/it]
 24%|██▍       | 14859/61904 [7:18:51<18:41:14,  1.43s/it]
 24%|██▍       | 14860/61904 [7:18:52<18:57:32,  1.45s/it]
                                                          
{'loss': 2.8067, 'learning_rate': 1.7624141060547128e-07, 'epoch': 3.84}

 24%|██▍       | 14860/61904 [7:18:52<18:57:32,  1.45s/it]
 24%|██▍       | 14861/61904 [7:18:53<18:23:35,  1.41s/it]
 24%|██▍       | 14862/61904 [7:18:55<18:21:09,  1.40s/it]
 24%|██▍       | 14863/61904 [7:18:56<18:11:48,  1.39s/it]
 24%|██▍       | 14864/61904 [7:18:58<18:16:33,  1.40s/it]
 24%|██▍       | 14865/61904 [7:18:59<18:00:15,  1.38s/it]
 24%|██▍       | 14866/61904 [7:19:00<17:56:46,  1.37s/it]
 24%|██▍       | 14867/61904 [7:19:02<17:59:16,  1.38s/it]
 24%|██▍       | 14868/61904 [7:19:03<18:00:20,  1.38s/it]
 24%|██▍       | 14869/61904 [7:19:05<18:19:14,  1.40s/it]
 24%|██▍       | 14870/61904 [7:19:06<18:08:39,  1.39s/it]
 24%|██▍       | 14871/61904 [7:19:07<18:17:32,  1.40s/it]
 24%|██▍       | 14872/61904 [7:19:09<18:01:19,  1.38s/it]
 24%|██▍       | 14873/61904 [7:19:10<18:05:44,  1.39s/it]
 24%|██▍       | 14874/61904 [7:19:11<17:45:56,  1.36s/it]
 24%|██▍       | 14875/61904 [7:19:13<17:58:32,  1.38s/it]
 24%|██▍       | 14876/61904 [7:19:14<18:20:45,  1.40s/it]
 24%|██▍       | 14877/61904 [7:19:16<17:53:09,  1.37s/it]
 24%|██▍       | 14878/61904 [7:19:17<17:42:43,  1.36s/it]
 24%|██▍       | 14879/61904 [7:19:18<18:03:01,  1.38s/it]
 24%|██▍       | 14880/61904 [7:19:20<17:40:48,  1.35s/it]
                                                          
{'loss': 2.723, 'learning_rate': 1.7620899779592894e-07, 'epoch': 3.85}

 24%|██▍       | 14880/61904 [7:19:20<17:40:48,  1.35s/it]
 24%|██▍       | 14881/61904 [7:19:21<17:31:19,  1.34s/it]
 24%|██▍       | 14882/61904 [7:19:22<17:33:25,  1.34s/it]
 24%|██▍       | 14883/61904 [7:19:24<17:20:55,  1.33s/it]
 24%|██▍       | 14884/61904 [7:19:25<17:51:13,  1.37s/it]
 24%|██▍       | 14885/61904 [7:19:26<17:55:52,  1.37s/it]
 24%|██▍       | 14886/61904 [7:19:28<17:43:14,  1.36s/it]
 24%|██▍       | 14887/61904 [7:19:29<17:30:18,  1.34s/it]
 24%|██▍       | 14888/61904 [7:19:30<17:47:24,  1.36s/it]
 24%|██▍       | 14889/61904 [7:19:32<17:46:59,  1.36s/it]
 24%|██▍       | 14890/61904 [7:19:33<18:06:10,  1.39s/it]
 24%|██▍       | 14891/61904 [7:19:35<17:52:17,  1.37s/it]
 24%|██▍       | 14892/61904 [7:19:36<18:29:51,  1.42s/it]
 24%|██▍       | 14893/61904 [7:19:37<18:25:54,  1.41s/it]
 24%|██▍       | 14894/61904 [7:19:39<18:09:57,  1.39s/it]
 24%|██▍       | 14895/61904 [7:19:40<18:46:12,  1.44s/it]
 24%|██▍       | 14896/61904 [7:19:42<18:27:18,  1.41s/it]
 24%|██▍       | 14897/61904 [7:19:43<18:36:14,  1.42s/it]
 24%|██▍       | 14898/61904 [7:19:45<18:19:36,  1.40s/it]
 24%|██▍       | 14899/61904 [7:19:46<17:54:03,  1.37s/it]
 24%|██▍       | 14900/61904 [7:19:48<19:52:38,  1.52s/it]
                                                          
{'loss': 2.7566, 'learning_rate': 1.7617658498638663e-07, 'epoch': 3.85}

 24%|██▍       | 14900/61904 [7:19:48<19:52:38,  1.52s/it]
 24%|██▍       | 14901/61904 [7:19:49<19:11:59,  1.47s/it]
 24%|██▍       | 14902/61904 [7:19:50<18:52:44,  1.45s/it]
 24%|██▍       | 14903/61904 [7:19:52<18:46:20,  1.44s/it]
 24%|██▍       | 14904/61904 [7:19:53<18:37:16,  1.43s/it]
 24%|██▍       | 14905/61904 [7:19:55<18:02:14,  1.38s/it]
 24%|██▍       | 14906/61904 [7:19:56<18:12:02,  1.39s/it]
 24%|██▍       | 14907/61904 [7:19:57<17:48:33,  1.36s/it]
 24%|██▍       | 14908/61904 [7:19:59<18:04:04,  1.38s/it]
 24%|██▍       | 14909/61904 [7:20:00<17:58:26,  1.38s/it]
 24%|██▍       | 14910/61904 [7:20:01<17:45:34,  1.36s/it]
 24%|██▍       | 14911/61904 [7:20:03<17:54:22,  1.37s/it]
 24%|██▍       | 14912/61904 [7:20:04<17:35:11,  1.35s/it]
 24%|██▍       | 14913/61904 [7:20:05<17:37:53,  1.35s/it]
 24%|██▍       | 14914/61904 [7:20:07<17:32:12,  1.34s/it]
 24%|██▍       | 14915/61904 [7:20:08<17:45:42,  1.36s/it]
 24%|██▍       | 14916/61904 [7:20:09<17:33:42,  1.35s/it]
 24%|██▍       | 14917/61904 [7:20:11<17:56:43,  1.37s/it]
 24%|██▍       | 14918/61904 [7:20:12<17:43:28,  1.36s/it]
 24%|██▍       | 14919/61904 [7:20:14<17:40:45,  1.35s/it]
 24%|██▍       | 14920/61904 [7:20:15<18:01:39,  1.38s/it]
                                                          
{'loss': 2.6923, 'learning_rate': 1.7614417217684426e-07, 'epoch': 3.86}

 24%|██▍       | 14920/61904 [7:20:15<18:01:39,  1.38s/it]
 24%|██▍       | 14921/61904 [7:20:16<17:58:15,  1.38s/it]
 24%|██▍       | 14922/61904 [7:20:18<17:59:29,  1.38s/it]
 24%|██▍       | 14923/61904 [7:20:19<17:58:53,  1.38s/it]
 24%|██▍       | 14924/61904 [7:20:20<17:53:12,  1.37s/it]
 24%|██▍       | 14925/61904 [7:20:22<17:35:04,  1.35s/it]
 24%|██▍       | 14926/61904 [7:20:23<17:41:54,  1.36s/it]
 24%|██▍       | 14927/61904 [7:20:25<18:03:12,  1.38s/it]
 24%|██▍       | 14928/61904 [7:20:26<17:52:03,  1.37s/it]
 24%|██▍       | 14929/61904 [7:20:27<17:28:57,  1.34s/it]
 24%|██▍       | 14930/61904 [7:20:29<17:50:16,  1.37s/it]
 24%|██▍       | 14931/61904 [7:20:30<18:04:51,  1.39s/it]
 24%|██▍       | 14932/61904 [7:20:32<18:19:22,  1.40s/it]
 24%|██▍       | 14933/61904 [7:20:33<18:17:28,  1.40s/it]
 24%|██▍       | 14934/61904 [7:20:34<17:35:36,  1.35s/it]
 24%|██▍       | 14935/61904 [7:20:35<17:16:45,  1.32s/it]
 24%|██▍       | 14936/61904 [7:20:37<17:55:01,  1.37s/it]
 24%|██▍       | 14937/61904 [7:20:38<18:30:23,  1.42s/it]
 24%|██▍       | 14938/61904 [7:20:40<18:42:33,  1.43s/it]
 24%|██▍       | 14939/61904 [7:20:41<18:14:45,  1.40s/it]
 24%|██▍       | 14940/61904 [7:20:43<17:59:05,  1.38s/it]
                                                          
{'loss': 2.7525, 'learning_rate': 1.7611175936730195e-07, 'epoch': 3.86}

 24%|██▍       | 14940/61904 [7:20:43<17:59:05,  1.38s/it]
 24%|██▍       | 14941/61904 [7:20:44<17:42:41,  1.36s/it]
 24%|██▍       | 14942/61904 [7:20:45<17:50:02,  1.37s/it]
 24%|██▍       | 14943/61904 [7:20:47<18:06:56,  1.39s/it]
 24%|██▍       | 14944/61904 [7:20:48<18:00:53,  1.38s/it]
 24%|██▍       | 14945/61904 [7:20:50<18:34:44,  1.42s/it]
 24%|██▍       | 14946/61904 [7:20:51<18:07:06,  1.39s/it]
 24%|██▍       | 14947/61904 [7:20:52<18:04:20,  1.39s/it]
 24%|██▍       | 14948/61904 [7:20:54<17:46:07,  1.36s/it]
 24%|██▍       | 14949/61904 [7:20:55<19:05:45,  1.46s/it]
 24%|██▍       | 14950/61904 [7:20:57<18:44:16,  1.44s/it]
 24%|██▍       | 14951/61904 [7:20:58<17:58:12,  1.38s/it]
 24%|██▍       | 14952/61904 [7:20:59<17:35:47,  1.35s/it]
 24%|██▍       | 14953/61904 [7:21:01<17:39:09,  1.35s/it]
 24%|██▍       | 14954/61904 [7:21:02<18:25:18,  1.41s/it]
 24%|██▍       | 14955/61904 [7:21:03<18:01:45,  1.38s/it]
 24%|██▍       | 14956/61904 [7:21:05<17:41:18,  1.36s/it]
 24%|██▍       | 14957/61904 [7:21:06<17:55:59,  1.38s/it]
 24%|██▍       | 14958/61904 [7:21:07<17:31:39,  1.34s/it]
 24%|██▍       | 14959/61904 [7:21:09<17:32:06,  1.34s/it]
 24%|██▍       | 14960/61904 [7:21:10<17:03:40,  1.31s/it]
                                                          
{'loss': 2.7261, 'learning_rate': 1.7607934655775964e-07, 'epoch': 3.87}

 24%|██▍       | 14960/61904 [7:21:10<17:03:40,  1.31s/it]
 24%|██▍       | 14961/61904 [7:21:11<17:51:03,  1.37s/it]
 24%|██▍       | 14962/61904 [7:21:13<17:41:29,  1.36s/it]
 24%|██▍       | 14963/61904 [7:21:14<17:50:26,  1.37s/it]
 24%|██▍       | 14964/61904 [7:21:15<17:17:09,  1.33s/it]
 24%|██▍       | 14965/61904 [7:21:17<17:20:11,  1.33s/it]
 24%|██▍       | 14966/61904 [7:21:18<17:21:49,  1.33s/it]
 24%|██▍       | 14967/61904 [7:21:19<17:13:21,  1.32s/it]
 24%|██▍       | 14968/61904 [7:21:21<17:14:42,  1.32s/it]
 24%|██▍       | 14969/61904 [7:21:22<17:58:16,  1.38s/it]
 24%|██▍       | 14970/61904 [7:21:24<18:15:22,  1.40s/it]
 24%|██▍       | 14971/61904 [7:21:25<17:57:50,  1.38s/it]
 24%|██▍       | 14972/61904 [7:21:26<17:39:22,  1.35s/it]
 24%|██▍       | 14973/61904 [7:21:28<17:56:19,  1.38s/it]
 24%|██▍       | 14974/61904 [7:21:29<18:45:27,  1.44s/it]
 24%|██▍       | 14975/61904 [7:21:31<18:03:58,  1.39s/it]
 24%|██▍       | 14976/61904 [7:21:32<18:38:42,  1.43s/it]
 24%|██▍       | 14977/61904 [7:21:34<18:48:51,  1.44s/it]
 24%|██▍       | 14978/61904 [7:21:35<18:12:13,  1.40s/it]
 24%|██▍       | 14979/61904 [7:21:36<18:17:03,  1.40s/it]
 24%|██▍       | 14980/61904 [7:21:38<18:07:57,  1.39s/it]
                                                          
{'loss': 2.7879, 'learning_rate': 1.7604693374821727e-07, 'epoch': 3.87}

 24%|██▍       | 14980/61904 [7:21:38<18:07:57,  1.39s/it]
 24%|██▍       | 14981/61904 [7:21:39<18:55:07,  1.45s/it]
 24%|██▍       | 14982/61904 [7:21:41<19:06:55,  1.47s/it]
 24%|██▍       | 14983/61904 [7:21:42<18:19:06,  1.41s/it]
 24%|██▍       | 14984/61904 [7:21:43<18:34:23,  1.43s/it]
 24%|██▍       | 14985/61904 [7:21:45<18:34:26,  1.43s/it]
 24%|██▍       | 14986/61904 [7:21:46<18:43:30,  1.44s/it]
 24%|██▍       | 14987/61904 [7:21:48<18:37:42,  1.43s/it]
 24%|██▍       | 14988/61904 [7:21:49<18:05:06,  1.39s/it]
 24%|██▍       | 14989/61904 [7:21:50<17:59:51,  1.38s/it]
 24%|██▍       | 14990/61904 [7:21:52<17:48:48,  1.37s/it]
 24%|██▍       | 14991/61904 [7:21:53<17:48:44,  1.37s/it]
 24%|██▍       | 14992/61904 [7:21:54<17:49:40,  1.37s/it]
 24%|██▍       | 14993/61904 [7:21:56<17:40:56,  1.36s/it]
 24%|██▍       | 14994/61904 [7:21:57<17:38:06,  1.35s/it]
 24%|██▍       | 14995/61904 [7:21:59<18:07:14,  1.39s/it]
 24%|██▍       | 14996/61904 [7:22:00<17:48:25,  1.37s/it]
 24%|██▍       | 14997/61904 [7:22:01<18:23:01,  1.41s/it]
 24%|██▍       | 14998/61904 [7:22:03<17:48:18,  1.37s/it]
 24%|██▍       | 14999/61904 [7:22:04<17:50:04,  1.37s/it]
 24%|██▍       | 15000/61904 [7:22:06<18:03:07,  1.39s/it]
                                                          
{'loss': 2.7061, 'learning_rate': 1.7601452093867496e-07, 'epoch': 3.88}

 24%|██▍       | 15000/61904 [7:22:06<18:03:07,  1.39s/it]
 24%|██▍       | 15001/61904 [7:22:07<17:46:38,  1.36s/it]
 24%|██▍       | 15002/61904 [7:22:08<18:20:59,  1.41s/it]
 24%|██▍       | 15003/61904 [7:22:10<17:49:20,  1.37s/it]
 24%|██▍       | 15004/61904 [7:22:11<18:45:13,  1.44s/it]
 24%|██▍       | 15005/61904 [7:22:13<19:25:12,  1.49s/it]
 24%|██▍       | 15006/61904 [7:22:14<18:49:35,  1.45s/it]
 24%|██▍       | 15007/61904 [7:22:16<19:05:23,  1.47s/it]
 24%|██▍       | 15008/61904 [7:22:17<18:56:35,  1.45s/it]
 24%|██▍       | 15009/61904 [7:22:18<18:06:47,  1.39s/it]
 24%|██▍       | 15010/61904 [7:22:20<18:28:33,  1.42s/it]
 24%|██▍       | 15011/61904 [7:22:21<18:18:25,  1.41s/it]
 24%|██▍       | 15012/61904 [7:22:23<17:52:12,  1.37s/it]
 24%|██▍       | 15013/61904 [7:22:24<17:58:01,  1.38s/it]
 24%|██▍       | 15014/61904 [7:22:25<17:56:15,  1.38s/it]
 24%|██▍       | 15015/61904 [7:22:27<17:42:32,  1.36s/it]
 24%|██▍       | 15016/61904 [7:22:28<17:57:00,  1.38s/it]
 24%|██▍       | 15017/61904 [7:22:29<18:10:04,  1.39s/it]
 24%|██▍       | 15018/61904 [7:22:31<18:53:12,  1.45s/it]
 24%|██▍       | 15019/61904 [7:22:32<18:38:13,  1.43s/it]
 24%|██▍       | 15020/61904 [7:22:34<18:22:47,  1.41s/it]
                                                          
{'loss': 2.6878, 'learning_rate': 1.7598210812913262e-07, 'epoch': 3.88}

 24%|██▍       | 15020/61904 [7:22:34<18:22:47,  1.41s/it]
 24%|██▍       | 15021/61904 [7:22:35<18:22:36,  1.41s/it]
 24%|██▍       | 15022/61904 [7:22:36<17:55:16,  1.38s/it]
 24%|██▍       | 15023/61904 [7:22:38<18:01:00,  1.38s/it]
 24%|██▍       | 15024/61904 [7:22:39<17:50:43,  1.37s/it]
 24%|██▍       | 15025/61904 [7:22:41<17:51:11,  1.37s/it]
 24%|██▍       | 15026/61904 [7:22:42<17:28:22,  1.34s/it]
 24%|██▍       | 15027/61904 [7:22:43<17:52:27,  1.37s/it]
 24%|██▍       | 15028/61904 [7:22:45<17:59:16,  1.38s/it]
 24%|██▍       | 15029/61904 [7:22:46<17:22:39,  1.33s/it]
 24%|██▍       | 15030/61904 [7:22:47<17:10:54,  1.32s/it]
 24%|██▍       | 15031/61904 [7:22:49<17:06:25,  1.31s/it]
 24%|██▍       | 15032/61904 [7:22:50<17:51:19,  1.37s/it]
 24%|██▍       | 15033/61904 [7:22:51<17:32:55,  1.35s/it]
 24%|██▍       | 15034/61904 [7:22:53<17:40:47,  1.36s/it]
 24%|██▍       | 15035/61904 [7:22:54<18:03:14,  1.39s/it]
 24%|██▍       | 15036/61904 [7:22:55<17:35:07,  1.35s/it]
 24%|██▍       | 15037/61904 [7:22:57<17:27:46,  1.34s/it]
 24%|██▍       | 15038/61904 [7:22:58<17:36:37,  1.35s/it]
 24%|██▍       | 15039/61904 [7:22:59<17:34:33,  1.35s/it]
 24%|██▍       | 15040/61904 [7:23:01<17:22:53,  1.34s/it]
                                                          
{'loss': 2.7831, 'learning_rate': 1.7594969531959028e-07, 'epoch': 3.89}

 24%|██▍       | 15040/61904 [7:23:01<17:22:53,  1.34s/it]
 24%|██▍       | 15041/61904 [7:23:02<17:22:43,  1.34s/it]
 24%|██▍       | 15042/61904 [7:23:04<17:40:58,  1.36s/it]
 24%|██▍       | 15043/61904 [7:23:05<18:25:00,  1.41s/it]
 24%|██▍       | 15044/61904 [7:23:06<18:14:17,  1.40s/it]
 24%|██▍       | 15045/61904 [7:23:08<18:04:54,  1.39s/it]
 24%|██▍       | 15046/61904 [7:23:09<17:54:38,  1.38s/it]
 24%|██▍       | 15047/61904 [7:23:11<17:53:15,  1.37s/it]
 24%|██▍       | 15048/61904 [7:23:12<17:46:09,  1.37s/it]
 24%|██▍       | 15049/61904 [7:23:13<17:40:49,  1.36s/it]
 24%|██▍       | 15050/61904 [7:23:15<18:04:57,  1.39s/it]
 24%|██▍       | 15051/61904 [7:23:16<17:51:25,  1.37s/it]
 24%|██▍       | 15052/61904 [7:23:17<17:53:40,  1.37s/it]
 24%|██▍       | 15053/61904 [7:23:19<17:34:36,  1.35s/it]
 24%|██▍       | 15054/61904 [7:23:20<18:26:27,  1.42s/it]
 24%|██▍       | 15055/61904 [7:23:22<18:36:37,  1.43s/it]
 24%|██▍       | 15056/61904 [7:23:23<17:53:36,  1.38s/it]
 24%|██▍       | 15057/61904 [7:23:24<17:54:18,  1.38s/it]
 24%|██▍       | 15058/61904 [7:23:26<17:21:33,  1.33s/it]
 24%|██▍       | 15059/61904 [7:23:27<17:27:25,  1.34s/it]
 24%|██▍       | 15060/61904 [7:23:28<17:31:17,  1.35s/it]
                                                          
{'loss': 2.751, 'learning_rate': 1.7591728251004797e-07, 'epoch': 3.89}

 24%|██▍       | 15060/61904 [7:23:28<17:31:17,  1.35s/it]
 24%|██▍       | 15061/61904 [7:23:30<17:21:13,  1.33s/it]
 24%|██▍       | 15062/61904 [7:23:31<18:15:33,  1.40s/it]
 24%|██▍       | 15063/61904 [7:23:33<18:38:17,  1.43s/it]
 24%|██▍       | 15064/61904 [7:23:34<18:31:37,  1.42s/it]
 24%|██▍       | 15065/61904 [7:23:35<18:15:28,  1.40s/it]
 24%|██▍       | 15066/61904 [7:23:37<18:34:56,  1.43s/it]
 24%|██▍       | 15067/61904 [7:23:38<19:04:35,  1.47s/it]
 24%|██▍       | 15068/61904 [7:23:40<18:11:31,  1.40s/it]
 24%|██▍       | 15069/61904 [7:23:41<18:29:00,  1.42s/it]
 24%|██▍       | 15070/61904 [7:23:43<18:19:47,  1.41s/it]
 24%|██▍       | 15071/61904 [7:23:44<18:08:02,  1.39s/it]
 24%|██▍       | 15072/61904 [7:23:45<18:05:02,  1.39s/it]
 24%|██▍       | 15073/61904 [7:23:47<18:39:08,  1.43s/it]
 24%|██▍       | 15074/61904 [7:23:48<18:59:18,  1.46s/it]
 24%|██▍       | 15075/61904 [7:23:50<19:02:10,  1.46s/it]
 24%|██▍       | 15076/61904 [7:23:51<18:25:47,  1.42s/it]
 24%|██▍       | 15077/61904 [7:23:53<18:26:37,  1.42s/it]
 24%|██▍       | 15078/61904 [7:23:54<18:10:53,  1.40s/it]
 24%|██▍       | 15079/61904 [7:23:55<18:22:02,  1.41s/it]
 24%|██▍       | 15080/61904 [7:23:57<18:36:28,  1.43s/it]
                                                          
{'loss': 2.7191, 'learning_rate': 1.7588486970050564e-07, 'epoch': 3.9}

 24%|██▍       | 15080/61904 [7:23:57<18:36:28,  1.43s/it]
 24%|██▍       | 15081/61904 [7:23:58<18:18:52,  1.41s/it]
 24%|██▍       | 15082/61904 [7:24:00<18:41:45,  1.44s/it]
 24%|██▍       | 15083/61904 [7:24:01<18:43:52,  1.44s/it]
 24%|██▍       | 15084/61904 [7:24:03<18:54:38,  1.45s/it]
 24%|██▍       | 15085/61904 [7:24:04<18:49:42,  1.45s/it]
 24%|██▍       | 15086/61904 [7:24:06<18:59:04,  1.46s/it]
 24%|██▍       | 15087/61904 [7:24:07<19:08:19,  1.47s/it]
 24%|██▍       | 15088/61904 [7:24:08<18:30:16,  1.42s/it]
 24%|██▍       | 15089/61904 [7:24:10<18:08:27,  1.40s/it]
 24%|██▍       | 15090/61904 [7:24:11<18:26:18,  1.42s/it]
 24%|██▍       | 15091/61904 [7:24:13<18:55:15,  1.46s/it]
 24%|██▍       | 15092/61904 [7:24:14<19:01:49,  1.46s/it]
 24%|██▍       | 15093/61904 [7:24:16<18:55:15,  1.46s/it]
 24%|██▍       | 15094/61904 [7:24:17<18:14:04,  1.40s/it]
 24%|██▍       | 15095/61904 [7:24:18<17:59:57,  1.38s/it]
 24%|██▍       | 15096/61904 [7:24:20<18:07:27,  1.39s/it]
 24%|██▍       | 15097/61904 [7:24:21<18:02:35,  1.39s/it]
 24%|██▍       | 15098/61904 [7:24:23<18:44:06,  1.44s/it]
 24%|██▍       | 15099/61904 [7:24:24<18:31:40,  1.43s/it]
 24%|██▍       | 15100/61904 [7:24:25<18:17:17,  1.41s/it]
                                                          
{'loss': 2.7581, 'learning_rate': 1.758524568909633e-07, 'epoch': 3.9}

 24%|██▍       | 15100/61904 [7:24:25<18:17:17,  1.41s/it]
 24%|██▍       | 15101/61904 [7:24:27<18:09:42,  1.40s/it]
 24%|██▍       | 15102/61904 [7:24:28<18:15:44,  1.40s/it]
 24%|██▍       | 15103/61904 [7:24:30<18:28:14,  1.42s/it]
 24%|██▍       | 15104/61904 [7:24:31<19:00:42,  1.46s/it]
 24%|██▍       | 15105/61904 [7:24:33<18:36:50,  1.43s/it]
 24%|██▍       | 15106/61904 [7:24:34<18:55:35,  1.46s/it]
 24%|██▍       | 15107/61904 [7:24:35<18:49:33,  1.45s/it]
 24%|██▍       | 15108/61904 [7:24:37<18:28:47,  1.42s/it]
 24%|██▍       | 15109/61904 [7:24:38<18:16:54,  1.41s/it]
 24%|██▍       | 15110/61904 [7:24:40<17:55:54,  1.38s/it]
 24%|██▍       | 15111/61904 [7:24:41<17:32:54,  1.35s/it]
 24%|██▍       | 15112/61904 [7:24:42<17:54:01,  1.38s/it]
 24%|██▍       | 15113/61904 [7:24:44<18:38:22,  1.43s/it]
 24%|██▍       | 15114/61904 [7:24:45<18:30:12,  1.42s/it]
 24%|██▍       | 15115/61904 [7:24:47<18:18:29,  1.41s/it]
 24%|██▍       | 15116/61904 [7:24:48<18:05:41,  1.39s/it]
 24%|██▍       | 15117/61904 [7:24:49<17:39:18,  1.36s/it]
 24%|██▍       | 15118/61904 [7:24:50<17:16:19,  1.33s/it]
 24%|██▍       | 15119/61904 [7:24:52<17:05:28,  1.32s/it]
 24%|██▍       | 15120/61904 [7:24:53<17:10:59,  1.32s/it]
                                                          
{'loss': 2.7016, 'learning_rate': 1.7582004408142099e-07, 'epoch': 3.91}

 24%|██▍       | 15120/61904 [7:24:53<17:10:59,  1.32s/it]
 24%|██▍       | 15121/61904 [7:24:54<17:21:38,  1.34s/it]
 24%|██▍       | 15122/61904 [7:24:56<17:35:53,  1.35s/it]
 24%|██▍       | 15123/61904 [7:24:57<17:36:21,  1.35s/it]
 24%|██▍       | 15124/61904 [7:24:59<17:42:53,  1.36s/it]
 24%|██▍       | 15125/61904 [7:25:00<17:28:23,  1.34s/it]
 24%|██▍       | 15126/61904 [7:25:01<17:48:34,  1.37s/it]
 24%|██▍       | 15127/61904 [7:25:03<17:53:55,  1.38s/it]
 24%|██▍       | 15128/61904 [7:25:04<18:21:48,  1.41s/it]
 24%|██▍       | 15129/61904 [7:25:06<18:32:35,  1.43s/it]
 24%|██▍       | 15130/61904 [7:25:07<18:41:07,  1.44s/it]
 24%|██▍       | 15131/61904 [7:25:09<18:38:12,  1.43s/it]
 24%|██▍       | 15132/61904 [7:25:10<18:54:24,  1.46s/it]
 24%|██▍       | 15133/61904 [7:25:11<18:42:13,  1.44s/it]
 24%|██▍       | 15134/61904 [7:25:13<18:10:18,  1.40s/it]
 24%|██▍       | 15135/61904 [7:25:14<18:44:50,  1.44s/it]
 24%|██▍       | 15136/61904 [7:25:16<18:14:28,  1.40s/it]
 24%|██▍       | 15137/61904 [7:25:17<18:05:55,  1.39s/it]
 24%|██▍       | 15138/61904 [7:25:18<18:11:07,  1.40s/it]
 24%|██▍       | 15139/61904 [7:25:20<17:40:25,  1.36s/it]
 24%|██▍       | 15140/61904 [7:25:21<17:51:53,  1.38s/it]
                                                          
{'loss': 2.7306, 'learning_rate': 1.7578763127187862e-07, 'epoch': 3.91}

 24%|██▍       | 15140/61904 [7:25:21<17:51:53,  1.38s/it]
 24%|██▍       | 15141/61904 [7:25:22<17:30:37,  1.35s/it]
 24%|██▍       | 15142/61904 [7:25:24<17:40:33,  1.36s/it]
 24%|██▍       | 15143/61904 [7:25:25<18:09:24,  1.40s/it]
 24%|██▍       | 15144/61904 [7:25:27<17:48:03,  1.37s/it]
 24%|██▍       | 15145/61904 [7:25:28<17:51:43,  1.38s/it]
 24%|██▍       | 15146/61904 [7:25:29<17:29:16,  1.35s/it]
 24%|██▍       | 15147/61904 [7:25:31<17:56:07,  1.38s/it]
 24%|██▍       | 15148/61904 [7:25:32<18:08:59,  1.40s/it]
 24%|██▍       | 15149/61904 [7:25:33<17:51:20,  1.37s/it]
 24%|██▍       | 15150/61904 [7:25:35<17:20:44,  1.34s/it]
 24%|██▍       | 15151/61904 [7:25:36<17:25:44,  1.34s/it]
 24%|██▍       | 15152/61904 [7:25:37<17:20:03,  1.33s/it]
 24%|██▍       | 15153/61904 [7:25:39<17:32:46,  1.35s/it]
 24%|██▍       | 15154/61904 [7:25:40<17:40:23,  1.36s/it]
 24%|██▍       | 15155/61904 [7:25:41<17:26:44,  1.34s/it]
 24%|██▍       | 15156/61904 [7:25:43<17:13:13,  1.33s/it]
 24%|██▍       | 15157/61904 [7:25:44<18:07:27,  1.40s/it]
 24%|██▍       | 15158/61904 [7:25:46<18:08:51,  1.40s/it]
 24%|██▍       | 15159/61904 [7:25:47<18:08:16,  1.40s/it]
 24%|██▍       | 15160/61904 [7:25:48<17:53:59,  1.38s/it]
                                                          
{'loss': 2.7835, 'learning_rate': 1.757552184623363e-07, 'epoch': 3.92}

 24%|██▍       | 15160/61904 [7:25:48<17:53:59,  1.38s/it]
 24%|██▍       | 15161/61904 [7:25:50<18:00:28,  1.39s/it]
 24%|██▍       | 15162/61904 [7:25:51<17:44:26,  1.37s/it]
 24%|██▍       | 15163/61904 [7:25:53<17:54:29,  1.38s/it]
 24%|██▍       | 15164/61904 [7:25:54<17:59:55,  1.39s/it]
 24%|██▍       | 15165/61904 [7:25:55<17:22:26,  1.34s/it]
 24%|██▍       | 15166/61904 [7:25:56<17:12:47,  1.33s/it]
 25%|██▍       | 15167/61904 [7:25:58<17:37:59,  1.36s/it]
 25%|██▍       | 15168/61904 [7:25:59<17:27:55,  1.35s/it]
 25%|██▍       | 15169/61904 [7:26:01<17:35:35,  1.36s/it]
 25%|██▍       | 15170/61904 [7:26:02<18:17:07,  1.41s/it]
 25%|██▍       | 15171/61904 [7:26:03<17:55:06,  1.38s/it]
 25%|██▍       | 15172/61904 [7:26:05<18:03:29,  1.39s/it]
 25%|██▍       | 15173/61904 [7:26:06<18:27:55,  1.42s/it]
 25%|██▍       | 15174/61904 [7:26:08<18:00:23,  1.39s/it]
 25%|██▍       | 15175/61904 [7:26:09<17:47:41,  1.37s/it]
 25%|██▍       | 15176/61904 [7:26:10<17:50:33,  1.37s/it]
 25%|██▍       | 15177/61904 [7:26:12<18:06:38,  1.40s/it]
 25%|██▍       | 15178/61904 [7:26:13<17:58:31,  1.38s/it]
 25%|██▍       | 15179/61904 [7:26:15<17:44:56,  1.37s/it]
 25%|██▍       | 15180/61904 [7:26:16<17:46:04,  1.37s/it]
                                                          
{'loss': 2.7854, 'learning_rate': 1.75722805652794e-07, 'epoch': 3.92}

 25%|██▍       | 15180/61904 [7:26:16<17:46:04,  1.37s/it]
 25%|██▍       | 15181/61904 [7:26:17<18:04:47,  1.39s/it]
 25%|██▍       | 15182/61904 [7:26:19<18:19:55,  1.41s/it]
 25%|██▍       | 15183/61904 [7:26:20<18:23:43,  1.42s/it]
 25%|██▍       | 15184/61904 [7:26:22<18:30:04,  1.43s/it]
 25%|██▍       | 15185/61904 [7:26:23<18:15:34,  1.41s/it]
 25%|██▍       | 15186/61904 [7:26:24<18:22:41,  1.42s/it]
 25%|██▍       | 15187/61904 [7:26:26<18:07:12,  1.40s/it]
 25%|██▍       | 15188/61904 [7:26:27<17:46:23,  1.37s/it]
 25%|██▍       | 15189/61904 [7:26:28<17:34:29,  1.35s/it]
 25%|██▍       | 15190/61904 [7:26:30<18:04:31,  1.39s/it]
 25%|██▍       | 15191/61904 [7:26:31<17:55:28,  1.38s/it]
 25%|██▍       | 15192/61904 [7:26:33<17:27:19,  1.35s/it]
 25%|██▍       | 15193/61904 [7:26:34<17:32:21,  1.35s/it]
 25%|██▍       | 15194/61904 [7:26:35<17:50:42,  1.38s/it]
 25%|██▍       | 15195/61904 [7:26:37<17:51:34,  1.38s/it]
 25%|██▍       | 15196/61904 [7:26:38<17:18:42,  1.33s/it]
 25%|██▍       | 15197/61904 [7:26:39<17:24:32,  1.34s/it]
 25%|██▍       | 15198/61904 [7:26:41<17:33:31,  1.35s/it]
 25%|██▍       | 15199/61904 [7:26:42<17:45:19,  1.37s/it]
 25%|██▍       | 15200/61904 [7:26:43<17:46:11,  1.37s/it]
                                                          
{'loss': 2.7345, 'learning_rate': 1.7569039284325163e-07, 'epoch': 3.93}

 25%|██▍       | 15200/61904 [7:26:43<17:46:11,  1.37s/it]
 25%|██▍       | 15201/61904 [7:26:45<17:42:52,  1.37s/it]
 25%|██▍       | 15202/61904 [7:26:46<17:55:33,  1.38s/it]
 25%|██▍       | 15203/61904 [7:26:48<17:29:28,  1.35s/it]
 25%|██▍       | 15204/61904 [7:26:49<17:15:35,  1.33s/it]
 25%|██▍       | 15205/61904 [7:26:50<17:30:28,  1.35s/it]
 25%|██▍       | 15206/61904 [7:26:51<16:59:36,  1.31s/it]
 25%|██▍       | 15207/61904 [7:26:53<16:50:42,  1.30s/it]
 25%|██▍       | 15208/61904 [7:26:54<17:20:30,  1.34s/it]
 25%|██▍       | 15209/61904 [7:26:55<17:19:58,  1.34s/it]
 25%|██▍       | 15210/61904 [7:26:57<17:25:11,  1.34s/it]
 25%|██▍       | 15211/61904 [7:26:58<17:47:41,  1.37s/it]
 25%|██▍       | 15212/61904 [7:27:00<17:33:46,  1.35s/it]
 25%|██▍       | 15213/61904 [7:27:01<17:32:45,  1.35s/it]
 25%|██▍       | 15214/61904 [7:27:02<17:19:20,  1.34s/it]
 25%|██▍       | 15215/61904 [7:27:04<17:15:06,  1.33s/it]
 25%|██▍       | 15216/61904 [7:27:05<17:27:45,  1.35s/it]
 25%|██▍       | 15217/61904 [7:27:06<17:40:53,  1.36s/it]
 25%|██▍       | 15218/61904 [7:27:08<17:21:55,  1.34s/it]
 25%|██▍       | 15219/61904 [7:27:09<17:38:45,  1.36s/it]
 25%|██▍       | 15220/61904 [7:27:11<18:19:58,  1.41s/it]
                                                          
{'loss': 2.758, 'learning_rate': 1.7565798003370932e-07, 'epoch': 3.93}

 25%|██▍       | 15220/61904 [7:27:11<18:19:58,  1.41s/it]
 25%|██▍       | 15221/61904 [7:27:12<18:15:33,  1.41s/it]
 25%|██▍       | 15222/61904 [7:27:13<17:44:41,  1.37s/it]
 25%|██▍       | 15223/61904 [7:27:14<17:21:57,  1.34s/it]
 25%|██▍       | 15224/61904 [7:27:16<17:23:39,  1.34s/it]
 25%|██▍       | 15225/61904 [7:27:17<17:24:11,  1.34s/it]
 25%|██▍       | 15226/61904 [7:27:19<17:41:26,  1.36s/it]
 25%|██▍       | 15227/61904 [7:27:20<17:48:15,  1.37s/it]
 25%|██▍       | 15228/61904 [7:27:21<17:26:57,  1.35s/it]
 25%|██▍       | 15229/61904 [7:27:23<17:55:55,  1.38s/it]
 25%|██▍       | 15230/61904 [7:27:24<18:18:21,  1.41s/it]
 25%|██▍       | 15231/61904 [7:27:26<18:59:50,  1.47s/it]
 25%|██▍       | 15232/61904 [7:27:27<18:24:19,  1.42s/it]
 25%|██▍       | 15233/61904 [7:27:28<18:12:14,  1.40s/it]
 25%|██▍       | 15234/61904 [7:27:30<18:00:17,  1.39s/it]
 25%|██▍       | 15235/61904 [7:27:31<17:57:56,  1.39s/it]
 25%|██▍       | 15236/61904 [7:27:33<17:39:53,  1.36s/it]
 25%|██▍       | 15237/61904 [7:27:34<17:43:45,  1.37s/it]
 25%|██▍       | 15238/61904 [7:27:35<18:07:20,  1.40s/it]
 25%|██▍       | 15239/61904 [7:27:37<17:51:31,  1.38s/it]
 25%|██▍       | 15240/61904 [7:27:38<18:03:12,  1.39s/it]
                                                          
{'loss': 2.7777, 'learning_rate': 1.7562556722416698e-07, 'epoch': 3.94}

 25%|██▍       | 15240/61904 [7:27:38<18:03:12,  1.39s/it]
 25%|██▍       | 15241/61904 [7:27:39<17:55:55,  1.38s/it]
 25%|██▍       | 15242/61904 [7:27:41<18:07:19,  1.40s/it]
 25%|██▍       | 15243/61904 [7:27:42<17:54:29,  1.38s/it]
 25%|██▍       | 15244/61904 [7:27:44<18:39:35,  1.44s/it]
 25%|██▍       | 15245/61904 [7:27:45<18:34:56,  1.43s/it]
 25%|██▍       | 15246/61904 [7:27:47<18:25:55,  1.42s/it]
 25%|██▍       | 15247/61904 [7:27:48<18:36:21,  1.44s/it]
 25%|██▍       | 15248/61904 [7:27:49<18:15:29,  1.41s/it]
 25%|██▍       | 15249/61904 [7:27:51<18:55:48,  1.46s/it]
 25%|██▍       | 15250/61904 [7:27:52<17:51:19,  1.38s/it]
 25%|██▍       | 15251/61904 [7:27:54<18:22:47,  1.42s/it]
 25%|██▍       | 15252/61904 [7:27:55<18:03:55,  1.39s/it]
 25%|██▍       | 15253/61904 [7:27:56<17:51:26,  1.38s/it]
 25%|██▍       | 15254/61904 [7:27:58<18:04:04,  1.39s/it]
 25%|██▍       | 15255/61904 [7:27:59<17:44:03,  1.37s/it]
 25%|██▍       | 15256/61904 [7:28:01<18:07:16,  1.40s/it]
 25%|██▍       | 15257/61904 [7:28:02<18:22:25,  1.42s/it]
 25%|██▍       | 15258/61904 [7:28:04<19:01:40,  1.47s/it]
 25%|██▍       | 15259/61904 [7:28:05<18:31:29,  1.43s/it]
 25%|██▍       | 15260/61904 [7:28:06<18:09:28,  1.40s/it]
                                                          
{'loss': 2.8035, 'learning_rate': 1.7559315441462464e-07, 'epoch': 3.94}

 25%|██▍       | 15260/61904 [7:28:06<18:09:28,  1.40s/it]
 25%|██▍       | 15261/61904 [7:28:08<17:32:57,  1.35s/it]
 25%|██▍       | 15262/61904 [7:28:09<17:18:53,  1.34s/it]
 25%|██▍       | 15263/61904 [7:28:10<16:59:19,  1.31s/it]
 25%|██▍       | 15264/61904 [7:28:11<16:41:55,  1.29s/it]
 25%|██▍       | 15265/61904 [7:28:13<17:04:06,  1.32s/it]
 25%|██▍       | 15266/61904 [7:28:14<17:02:34,  1.32s/it]
 25%|██▍       | 15267/61904 [7:28:16<17:27:23,  1.35s/it]
 25%|██▍       | 15268/61904 [7:28:17<17:29:02,  1.35s/it]
 25%|██▍       | 15269/61904 [7:28:18<17:03:17,  1.32s/it]
 25%|██▍       | 15270/61904 [7:28:20<17:46:52,  1.37s/it]
 25%|██▍       | 15271/61904 [7:28:21<17:25:00,  1.34s/it]
 25%|██▍       | 15272/61904 [7:28:22<17:17:49,  1.34s/it]
 25%|██▍       | 15273/61904 [7:28:24<17:40:05,  1.36s/it]
 25%|██▍       | 15274/61904 [7:28:25<17:46:52,  1.37s/it]
 25%|██▍       | 15275/61904 [7:28:26<17:31:14,  1.35s/it]
 25%|██▍       | 15276/61904 [7:28:28<17:35:24,  1.36s/it]
 25%|██▍       | 15277/61904 [7:28:29<17:15:22,  1.33s/it]
 25%|██▍       | 15278/61904 [7:28:30<16:56:19,  1.31s/it]
 25%|██▍       | 15279/61904 [7:28:32<17:21:33,  1.34s/it]
 25%|██▍       | 15280/61904 [7:28:33<17:15:39,  1.33s/it]
                                                          
{'loss': 2.7233, 'learning_rate': 1.7556074160508233e-07, 'epoch': 3.95}

 25%|██▍       | 15280/61904 [7:28:33<17:15:39,  1.33s/it]
 25%|██▍       | 15281/61904 [7:28:34<17:27:01,  1.35s/it]
 25%|██▍       | 15282/61904 [7:28:36<18:01:55,  1.39s/it]
 25%|██▍       | 15283/61904 [7:28:37<17:29:44,  1.35s/it]
 25%|██▍       | 15284/61904 [7:28:38<17:27:07,  1.35s/it]
 25%|██▍       | 15285/61904 [7:28:40<17:44:49,  1.37s/it]
 25%|██▍       | 15286/61904 [7:28:41<17:51:51,  1.38s/it]
 25%|██▍       | 15287/61904 [7:28:43<18:46:50,  1.45s/it]
 25%|██▍       | 15288/61904 [7:28:44<18:17:33,  1.41s/it]
 25%|██▍       | 15289/61904 [7:28:46<18:13:44,  1.41s/it]
 25%|██▍       | 15290/61904 [7:28:47<17:43:41,  1.37s/it]
 25%|██▍       | 15291/61904 [7:28:48<17:58:04,  1.39s/it]
 25%|██▍       | 15292/61904 [7:28:50<18:24:39,  1.42s/it]
 25%|██▍       | 15293/61904 [7:28:51<18:19:46,  1.42s/it]
 25%|██▍       | 15294/61904 [7:28:53<18:22:27,  1.42s/it]
 25%|██▍       | 15295/61904 [7:28:54<18:05:27,  1.40s/it]
 25%|██▍       | 15296/61904 [7:28:56<18:54:09,  1.46s/it]
 25%|██▍       | 15297/61904 [7:28:57<18:34:47,  1.44s/it]
 25%|██▍       | 15298/61904 [7:28:58<18:39:07,  1.44s/it]
 25%|██▍       | 15299/61904 [7:29:00<18:04:56,  1.40s/it]
 25%|██▍       | 15300/61904 [7:29:01<18:27:16,  1.43s/it]
                                                          
{'loss': 2.7346, 'learning_rate': 1.7552832879554e-07, 'epoch': 3.95}

 25%|██▍       | 15300/61904 [7:29:01<18:27:16,  1.43s/it]
 25%|██▍       | 15301/61904 [7:29:03<18:12:27,  1.41s/it]
 25%|██▍       | 15302/61904 [7:29:04<18:05:54,  1.40s/it]
 25%|██▍       | 15303/61904 [7:29:05<17:40:46,  1.37s/it]
 25%|██▍       | 15304/61904 [7:29:07<18:44:10,  1.45s/it]
 25%|██▍       | 15305/61904 [7:29:08<18:12:45,  1.41s/it]
 25%|██▍       | 15306/61904 [7:29:10<18:09:18,  1.40s/it]
 25%|██▍       | 15307/61904 [7:29:11<18:07:08,  1.40s/it]
 25%|██▍       | 15308/61904 [7:29:12<18:30:27,  1.43s/it]
 25%|██▍       | 15309/61904 [7:29:14<17:49:42,  1.38s/it]
 25%|██▍       | 15310/61904 [7:29:15<17:37:56,  1.36s/it]
 25%|██▍       | 15311/61904 [7:29:16<17:46:04,  1.37s/it]
 25%|██▍       | 15312/61904 [7:29:18<18:18:18,  1.41s/it]
 25%|██▍       | 15313/61904 [7:29:19<17:55:33,  1.39s/it]
 25%|██▍       | 15314/61904 [7:29:21<17:47:48,  1.38s/it]
 25%|██▍       | 15315/61904 [7:29:22<18:03:34,  1.40s/it]
 25%|██▍       | 15316/61904 [7:29:23<18:11:54,  1.41s/it]
 25%|██▍       | 15317/61904 [7:29:25<17:43:45,  1.37s/it]
 25%|██▍       | 15318/61904 [7:29:26<17:31:08,  1.35s/it]
 25%|██▍       | 15319/61904 [7:29:27<17:03:05,  1.32s/it]
 25%|██▍       | 15320/61904 [7:29:29<17:18:36,  1.34s/it]
                                                          
{'loss': 2.7189, 'learning_rate': 1.7549591598599766e-07, 'epoch': 3.96}

 25%|██▍       | 15320/61904 [7:29:29<17:18:36,  1.34s/it]
 25%|██▍       | 15321/61904 [7:29:30<16:57:45,  1.31s/it]
 25%|██▍       | 15322/61904 [7:29:32<18:14:20,  1.41s/it]
 25%|██▍       | 15323/61904 [7:29:33<18:30:59,  1.43s/it]
 25%|██▍       | 15324/61904 [7:29:34<18:16:00,  1.41s/it]
 25%|██▍       | 15325/61904 [7:29:36<18:22:01,  1.42s/it]
 25%|██▍       | 15326/61904 [7:29:37<17:58:43,  1.39s/it]
 25%|██▍       | 15327/61904 [7:29:39<17:50:32,  1.38s/it]
 25%|██▍       | 15328/61904 [7:29:40<18:05:25,  1.40s/it]
 25%|██▍       | 15329/61904 [7:29:41<17:59:48,  1.39s/it]
 25%|██▍       | 15330/61904 [7:29:43<17:25:47,  1.35s/it]
 25%|██▍       | 15331/61904 [7:29:44<17:32:28,  1.36s/it]
 25%|██▍       | 15332/61904 [7:29:45<17:29:03,  1.35s/it]
 25%|██▍       | 15333/61904 [7:29:47<17:39:23,  1.36s/it]
 25%|██▍       | 15334/61904 [7:29:48<18:00:23,  1.39s/it]
 25%|██▍       | 15335/61904 [7:29:49<17:26:09,  1.35s/it]
 25%|██▍       | 15336/61904 [7:29:51<17:33:13,  1.36s/it]
 25%|██▍       | 15337/61904 [7:29:52<17:30:18,  1.35s/it]
 25%|██▍       | 15338/61904 [7:29:54<18:03:49,  1.40s/it]
 25%|██▍       | 15339/61904 [7:29:55<17:33:15,  1.36s/it]
 25%|██▍       | 15340/61904 [7:29:56<17:27:02,  1.35s/it]
                                                          
{'loss': 2.69, 'learning_rate': 1.7546350317645535e-07, 'epoch': 3.96}

 25%|██▍       | 15340/61904 [7:29:56<17:27:02,  1.35s/it]
 25%|██▍       | 15341/61904 [7:29:58<17:40:39,  1.37s/it]
 25%|██▍       | 15342/61904 [7:29:59<17:53:21,  1.38s/it]
 25%|██▍       | 15343/61904 [7:30:00<17:55:25,  1.39s/it]
 25%|██▍       | 15344/61904 [7:30:02<17:24:52,  1.35s/it]
 25%|██▍       | 15345/61904 [7:30:03<17:42:00,  1.37s/it]
 25%|██▍       | 15346/61904 [7:30:04<17:35:13,  1.36s/it]
 25%|██▍       | 15347/61904 [7:30:06<17:04:39,  1.32s/it]
 25%|██▍       | 15348/61904 [7:30:07<17:06:52,  1.32s/it]
 25%|██▍       | 15349/61904 [7:30:09<17:48:54,  1.38s/it]
 25%|██▍       | 15350/61904 [7:30:10<17:26:23,  1.35s/it]
 25%|██▍       | 15351/61904 [7:30:11<17:18:04,  1.34s/it]
 25%|██▍       | 15352/61904 [7:30:12<17:03:28,  1.32s/it]
 25%|██▍       | 15353/61904 [7:30:14<17:05:03,  1.32s/it]
 25%|██▍       | 15354/61904 [7:30:15<17:29:56,  1.35s/it]
 25%|██▍       | 15355/61904 [7:30:17<18:04:10,  1.40s/it]
 25%|██▍       | 15356/61904 [7:30:18<18:10:00,  1.41s/it]
 25%|██▍       | 15357/61904 [7:30:19<18:05:47,  1.40s/it]
 25%|██▍       | 15358/61904 [7:30:21<18:20:41,  1.42s/it]
 25%|██▍       | 15359/61904 [7:30:22<18:04:45,  1.40s/it]
 25%|██▍       | 15360/61904 [7:30:24<17:44:00,  1.37s/it]
                                                          
{'loss': 2.7707, 'learning_rate': 1.7543109036691298e-07, 'epoch': 3.97}

 25%|██▍       | 15360/61904 [7:30:24<17:44:00,  1.37s/it]
 25%|██▍       | 15361/61904 [7:30:25<17:27:39,  1.35s/it]
 25%|██▍       | 15362/61904 [7:30:26<17:27:55,  1.35s/it]
 25%|██▍       | 15363/61904 [7:30:28<17:41:28,  1.37s/it]
 25%|██▍       | 15364/61904 [7:30:29<17:19:58,  1.34s/it]
 25%|██▍       | 15365/61904 [7:30:30<17:33:32,  1.36s/it]
 25%|██▍       | 15366/61904 [7:30:32<17:16:45,  1.34s/it]
 25%|██▍       | 15367/61904 [7:30:33<18:20:12,  1.42s/it]
 25%|██▍       | 15368/61904 [7:30:35<18:38:10,  1.44s/it]
 25%|██▍       | 15369/61904 [7:30:36<18:17:29,  1.42s/it]
 25%|██▍       | 15370/61904 [7:30:38<18:54:56,  1.46s/it]
 25%|██▍       | 15371/61904 [7:30:39<18:34:27,  1.44s/it]
 25%|██▍       | 15372/61904 [7:30:40<18:11:55,  1.41s/it]
 25%|██▍       | 15373/61904 [7:30:42<18:17:40,  1.42s/it]
 25%|██▍       | 15374/61904 [7:30:43<18:29:40,  1.43s/it]
 25%|██▍       | 15375/61904 [7:30:45<19:31:12,  1.51s/it]
 25%|██▍       | 15376/61904 [7:30:46<19:04:31,  1.48s/it]
 25%|██▍       | 15377/61904 [7:30:48<19:27:06,  1.51s/it]
 25%|██▍       | 15378/61904 [7:30:49<19:29:42,  1.51s/it]
 25%|██▍       | 15379/61904 [7:30:51<19:17:55,  1.49s/it]
 25%|██▍       | 15380/61904 [7:30:52<18:39:12,  1.44s/it]
                                                          
{'loss': 2.7585, 'learning_rate': 1.7539867755737067e-07, 'epoch': 3.97}

 25%|██▍       | 15380/61904 [7:30:52<18:39:12,  1.44s/it]
 25%|██▍       | 15381/61904 [7:30:54<18:06:57,  1.40s/it]
 25%|██▍       | 15382/61904 [7:30:55<17:54:59,  1.39s/it]
 25%|██▍       | 15383/61904 [7:30:56<18:21:28,  1.42s/it]
 25%|██▍       | 15384/61904 [7:30:58<18:54:51,  1.46s/it]
 25%|██▍       | 15385/61904 [7:30:59<18:03:08,  1.40s/it]
 25%|██▍       | 15386/61904 [7:31:01<18:03:55,  1.40s/it]
 25%|██▍       | 15387/61904 [7:31:02<17:57:06,  1.39s/it]
 25%|██▍       | 15388/61904 [7:31:03<18:02:21,  1.40s/it]
 25%|██▍       | 15389/61904 [7:31:05<18:00:43,  1.39s/it]
 25%|██▍       | 15390/61904 [7:31:06<17:54:09,  1.39s/it]
 25%|██▍       | 15391/61904 [7:31:07<17:28:36,  1.35s/it]
 25%|██▍       | 15392/61904 [7:31:09<17:25:58,  1.35s/it]
 25%|██▍       | 15393/61904 [7:31:10<18:03:13,  1.40s/it]
 25%|██▍       | 15394/61904 [7:31:12<18:09:44,  1.41s/it]
 25%|██▍       | 15395/61904 [7:31:13<17:55:51,  1.39s/it]
 25%|██▍       | 15396/61904 [7:31:14<17:45:09,  1.37s/it]
 25%|██▍       | 15397/61904 [7:31:16<18:24:52,  1.43s/it]
 25%|██▍       | 15398/61904 [7:31:17<17:48:55,  1.38s/it]
 25%|██▍       | 15399/61904 [7:31:19<17:51:38,  1.38s/it]
 25%|██▍       | 15400/61904 [7:31:20<18:00:06,  1.39s/it]
                                                          
{'loss': 2.6792, 'learning_rate': 1.7536626474782833e-07, 'epoch': 3.98}

 25%|██▍       | 15400/61904 [7:31:20<18:00:06,  1.39s/it]
 25%|██▍       | 15401/61904 [7:31:21<17:44:10,  1.37s/it]
 25%|██▍       | 15402/61904 [7:31:23<17:27:40,  1.35s/it]
 25%|██▍       | 15403/61904 [7:31:24<17:39:57,  1.37s/it]
 25%|██▍       | 15404/61904 [7:31:25<17:46:36,  1.38s/it]
 25%|██▍       | 15405/61904 [7:31:27<17:51:51,  1.38s/it]
 25%|██▍       | 15406/61904 [7:31:28<17:33:20,  1.36s/it]
 25%|██▍       | 15407/61904 [7:31:30<19:18:23,  1.49s/it]
 25%|██▍       | 15408/61904 [7:31:31<18:58:58,  1.47s/it]
 25%|██▍       | 15409/61904 [7:31:33<18:36:00,  1.44s/it]
 25%|██▍       | 15410/61904 [7:31:34<18:13:56,  1.41s/it]
 25%|██▍       | 15411/61904 [7:31:36<18:33:56,  1.44s/it]
 25%|██▍       | 15412/61904 [7:31:37<18:38:00,  1.44s/it]
 25%|██▍       | 15413/61904 [7:31:38<18:08:27,  1.40s/it]
 25%|██▍       | 15414/61904 [7:31:40<18:55:47,  1.47s/it]
 25%|██▍       | 15415/61904 [7:31:41<18:25:13,  1.43s/it]
 25%|██▍       | 15416/61904 [7:31:43<18:12:32,  1.41s/it]
 25%|██▍       | 15417/61904 [7:31:44<18:40:03,  1.45s/it]
 25%|██▍       | 15418/61904 [7:31:46<18:08:45,  1.41s/it]
 25%|██▍       | 15419/61904 [7:31:47<18:17:18,  1.42s/it]
 25%|██▍       | 15420/61904 [7:31:48<18:41:03,  1.45s/it]
                                                          
{'loss': 2.7379, 'learning_rate': 1.75333851938286e-07, 'epoch': 3.99}

 25%|██▍       | 15420/61904 [7:31:48<18:41:03,  1.45s/it]
 25%|██▍       | 15421/61904 [7:31:50<18:24:53,  1.43s/it]
 25%|██▍       | 15422/61904 [7:31:51<19:05:39,  1.48s/it]
 25%|██▍       | 15423/61904 [7:31:53<18:38:03,  1.44s/it]
 25%|██▍       | 15424/61904 [7:31:54<18:18:21,  1.42s/it]
 25%|██▍       | 15425/61904 [7:31:56<18:22:24,  1.42s/it]
 25%|██▍       | 15426/61904 [7:31:57<18:20:07,  1.42s/it]
 25%|██▍       | 15427/61904 [7:31:58<18:07:39,  1.40s/it]
 25%|██▍       | 15428/61904 [7:32:00<17:38:51,  1.37s/it]
 25%|██▍       | 15429/61904 [7:32:01<17:39:03,  1.37s/it]
 25%|██▍       | 15430/61904 [7:32:03<18:03:52,  1.40s/it]
 25%|██▍       | 15431/61904 [7:32:04<17:32:49,  1.36s/it]
 25%|██▍       | 15432/61904 [7:32:05<17:51:26,  1.38s/it]
 25%|██▍       | 15433/61904 [7:32:07<18:33:02,  1.44s/it]
 25%|██▍       | 15434/61904 [7:32:08<18:01:43,  1.40s/it]
 25%|██▍       | 15435/61904 [7:32:09<18:04:02,  1.40s/it]
 25%|██▍       | 15436/61904 [7:32:11<17:48:45,  1.38s/it]
 25%|██▍       | 15437/61904 [7:32:12<17:50:32,  1.38s/it]
 25%|██▍       | 15438/61904 [7:32:14<17:51:40,  1.38s/it]
 25%|██▍       | 15439/61904 [7:32:15<18:02:30,  1.40s/it]
 25%|██▍       | 15440/61904 [7:32:16<18:01:17,  1.40s/it]
                                                          
{'loss': 2.6914, 'learning_rate': 1.7530143912874368e-07, 'epoch': 3.99}

 25%|██▍       | 15440/61904 [7:32:16<18:01:17,  1.40s/it]
 25%|██▍       | 15441/61904 [7:32:18<18:08:52,  1.41s/it]
 25%|██▍       | 15442/61904 [7:32:19<17:52:39,  1.39s/it]
 25%|██▍       | 15443/61904 [7:32:21<17:43:54,  1.37s/it]
 25%|██▍       | 15444/61904 [7:32:22<17:28:12,  1.35s/it]
 25%|██▍       | 15445/61904 [7:32:23<17:39:00,  1.37s/it]
 25%|██▍       | 15446/61904 [7:32:25<17:34:44,  1.36s/it]
 25%|██▍       | 15447/61904 [7:32:26<17:25:56,  1.35s/it]
 25%|██▍       | 15448/61904 [7:32:27<17:59:32,  1.39s/it]
 25%|██▍       | 15449/61904 [7:32:29<18:04:44,  1.40s/it]
 25%|██▍       | 15450/61904 [7:32:30<18:18:09,  1.42s/it]
 25%|██▍       | 15451/61904 [7:32:32<18:15:53,  1.42s/it]
 25%|██▍       | 15452/61904 [7:32:33<18:22:46,  1.42s/it]
 25%|██▍       | 15453/61904 [7:32:35<19:05:34,  1.48s/it]
 25%|██▍       | 15454/61904 [7:32:36<19:18:47,  1.50s/it]
 25%|██▍       | 15455/61904 [7:32:38<18:45:20,  1.45s/it]
 25%|██▍       | 15456/61904 [7:32:39<18:24:17,  1.43s/it]
 25%|██▍       | 15457/61904 [7:32:40<18:23:03,  1.42s/it]
 25%|██▍       | 15458/61904 [7:32:42<17:54:31,  1.39s/it]
 25%|██▍       | 15459/61904 [7:32:43<18:09:57,  1.41s/it]
 25%|██▍       | 15460/61904 [7:32:44<17:44:39,  1.38s/it]
                                                          
{'loss': 2.7623, 'learning_rate': 1.7526902631920134e-07, 'epoch': 4.0}

 25%|██▍       | 15460/61904 [7:32:44<17:44:39,  1.38s/it]
 25%|██▍       | 15461/61904 [7:32:46<17:53:52,  1.39s/it]
 25%|██▍       | 15462/61904 [7:32:47<18:32:21,  1.44s/it]
 25%|██▍       | 15463/61904 [7:32:49<18:10:34,  1.41s/it]
 25%|██▍       | 15464/61904 [7:32:50<18:32:15,  1.44s/it]
 25%|██▍       | 15465/61904 [7:32:52<18:07:28,  1.41s/it]
 25%|██▍       | 15466/61904 [7:32:53<17:53:13,  1.39s/it]
 25%|██▍       | 15467/61904 [7:32:54<17:32:48,  1.36s/it]
 25%|██▍       | 15468/61904 [7:32:56<17:28:33,  1.35s/it]
 25%|██▍       | 15469/61904 [7:32:57<17:28:03,  1.35s/it]
 25%|██▍       | 15470/61904 [7:32:58<17:14:51,  1.34s/it]
 25%|██▍       | 15471/61904 [7:33:00<17:41:36,  1.37s/it]
 25%|██▍       | 15472/61904 [7:33:01<17:17:38,  1.34s/it]
 25%|██▍       | 15473/61904 [7:33:03<18:03:29,  1.40s/it]
 25%|██▍       | 15474/61904 [7:33:04<17:49:41,  1.38s/it]
 25%|██▍       | 15475/61904 [7:33:05<18:01:39,  1.40s/it]
 25%|██▌       | 15476/61904 [7:33:07<18:22:36,  1.42s/it]
 25%|██▌       | 15477/61904 [7:33:08<17:59:16,  1.39s/it]
 25%|██▌       | 15478/61904 [7:33:09<17:51:46,  1.39s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:02<20:00,  1.40s/it]

  0%|          | 3/861 [00:05<29:47,  2.08s/it]

  0%|          | 4/861 [00:11<49:07,  3.44s/it]

  1%|          | 5/861 [00:14<45:13,  3.17s/it]

  1%|          | 6/861 [00:15<38:18,  2.69s/it]

  1%|          | 7/861 [00:17<34:24,  2.42s/it]

  1%|          | 8/861 [00:20<36:13,  2.55s/it]

  1%|          | 9/861 [00:22<34:55,  2.46s/it]

  1%|          | 10/861 [00:25<36:12,  2.55s/it]

  1%|▏         | 11/861 [00:28<37:53,  2.67s/it]

  1%|▏         | 12/861 [00:32<44:45,  3.16s/it]

  2%|▏         | 13/861 [00:35<41:24,  2.93s/it]

  2%|▏         | 14/861 [00:36<32:47,  2.32s/it]

  2%|▏         | 15/861 [00:38<31:53,  2.26s/it]

  2%|▏         | 16/861 [00:39<27:00,  1.92s/it]

  2%|▏         | 17/861 [00:44<39:02,  2.78s/it]

  2%|▏         | 18/861 [00:45<33:24,  2.38s/it]

  2%|▏         | 19/861 [00:49<39:04,  2.78s/it]

  2%|▏         | 20/861 [00:53<44:39,  3.19s/it]

  2%|▏         | 21/861 [00:55<40:22,  2.88s/it]

  3%|▎         | 22/861 [00:58<39:32,  2.83s/it]

  3%|▎         | 23/861 [00:59<33:35,  2.41s/it]

  3%|▎         | 24/861 [01:03<37:11,  2.67s/it]

  3%|▎         | 25/861 [01:05<34:50,  2.50s/it]

  3%|▎         | 26/861 [01:09<40:54,  2.94s/it]

  3%|▎         | 27/861 [01:11<38:38,  2.78s/it]

  3%|▎         | 28/861 [01:16<45:52,  3.30s/it]

  3%|▎         | 29/861 [01:17<36:16,  2.62s/it]

  3%|▎         | 30/861 [01:21<41:48,  3.02s/it]

  4%|▎         | 31/861 [01:22<33:30,  2.42s/it]

  4%|▎         | 32/861 [01:22<27:10,  1.97s/it]

  4%|▍         | 33/861 [01:26<31:47,  2.30s/it]

  4%|▍         | 34/861 [01:28<30:16,  2.20s/it]

  4%|▍         | 35/861 [01:32<38:37,  2.81s/it]

  4%|▍         | 36/861 [01:34<34:20,  2.50s/it]

  4%|▍         | 37/861 [01:35<32:02,  2.33s/it]

  4%|▍         | 38/861 [01:38<34:42,  2.53s/it]

  5%|▍         | 39/861 [01:40<31:59,  2.34s/it]

  5%|▍         | 40/861 [01:42<30:51,  2.26s/it]

  5%|▍         | 41/861 [01:43<24:20,  1.78s/it]

  5%|▍         | 42/861 [01:47<31:18,  2.29s/it]

  5%|▍         | 43/861 [01:49<31:18,  2.30s/it]

  5%|▌         | 44/861 [01:49<23:48,  1.75s/it]

  5%|▌         | 45/861 [01:52<26:17,  1.93s/it]

  5%|▌         | 46/861 [01:56<36:32,  2.69s/it]

  5%|▌         | 47/861 [02:00<40:08,  2.96s/it]

  6%|▌         | 48/861 [02:02<38:51,  2.87s/it]

  6%|▌         | 49/861 [02:05<37:44,  2.79s/it]

  6%|▌         | 50/861 [02:05<27:34,  2.04s/it]

  6%|▌         | 51/861 [02:06<23:02,  1.71s/it]

  6%|▌         | 52/861 [02:08<24:41,  1.83s/it]

  6%|▌         | 53/861 [02:10<22:12,  1.65s/it]

  6%|▋         | 54/861 [02:10<17:34,  1.31s/it]

  6%|▋         | 55/861 [02:12<18:01,  1.34s/it]

  7%|▋         | 56/861 [02:16<30:11,  2.25s/it]

  7%|▋         | 57/861 [02:17<24:48,  1.85s/it]

  7%|▋         | 58/861 [02:18<20:41,  1.55s/it]

  7%|▋         | 59/861 [02:19<20:37,  1.54s/it]

  7%|▋         | 60/861 [02:21<22:02,  1.65s/it]

  7%|▋         | 61/861 [02:22<20:59,  1.57s/it]

  7%|▋         | 62/861 [02:23<17:57,  1.35s/it]

  7%|▋         | 63/861 [02:25<18:30,  1.39s/it]

  7%|▋         | 64/861 [02:26<18:17,  1.38s/it]

  8%|▊         | 65/861 [02:28<18:44,  1.41s/it]

  8%|▊         | 66/861 [02:28<15:06,  1.14s/it]

  8%|▊         | 67/861 [02:30<19:15,  1.45s/it]

  8%|▊         | 68/861 [02:33<23:48,  1.80s/it]

  8%|▊         | 69/861 [02:37<33:20,  2.53s/it]

  8%|▊         | 70/861 [02:39<30:32,  2.32s/it]

  8%|▊         | 71/861 [02:42<32:10,  2.44s/it]

  8%|▊         | 72/861 [02:45<34:37,  2.63s/it]

  8%|▊         | 73/861 [02:45<25:48,  1.97s/it]

  9%|▊         | 74/861 [02:49<31:26,  2.40s/it]

  9%|▊         | 75/861 [02:51<32:25,  2.48s/it]

  9%|▉         | 76/861 [02:54<34:35,  2.64s/it]

  9%|▉         | 77/861 [02:57<35:22,  2.71s/it]

  9%|▉         | 78/861 [02:58<29:33,  2.26s/it]

  9%|▉         | 79/861 [03:01<32:30,  2.49s/it]

  9%|▉         | 80/861 [03:04<31:03,  2.39s/it]

  9%|▉         | 81/861 [03:08<39:52,  3.07s/it]

 10%|▉         | 82/861 [03:09<32:37,  2.51s/it]

 10%|▉         | 83/861 [03:11<30:50,  2.38s/it]

 10%|▉         | 84/861 [03:14<32:32,  2.51s/it]

 10%|▉         | 85/861 [03:16<29:47,  2.30s/it]

 10%|▉         | 86/861 [03:17<25:01,  1.94s/it]

 10%|█         | 87/861 [03:20<29:28,  2.28s/it]

 10%|█         | 88/861 [03:21<21:53,  1.70s/it]

 10%|█         | 89/861 [03:22<21:17,  1.65s/it]

 10%|█         | 90/861 [03:27<32:19,  2.52s/it]

 11%|█         | 91/861 [03:29<29:49,  2.32s/it]

 11%|█         | 92/861 [03:31<28:40,  2.24s/it]

 11%|█         | 93/861 [03:34<33:01,  2.58s/it]

 11%|█         | 94/861 [03:35<26:30,  2.07s/it]

 11%|█         | 95/861 [03:35<20:20,  1.59s/it]

 11%|█         | 96/861 [03:38<22:40,  1.78s/it]

 11%|█▏        | 97/861 [03:40<26:41,  2.10s/it]

 11%|█▏        | 98/861 [03:42<25:41,  2.02s/it]

 11%|█▏        | 99/861 [03:47<36:51,  2.90s/it]

 12%|█▏        | 100/861 [03:49<32:18,  2.55s/it]

 12%|█▏        | 101/861 [03:51<29:21,  2.32s/it]

 12%|█▏        | 102/861 [03:52<27:07,  2.14s/it]

 12%|█▏        | 103/861 [03:53<22:32,  1.78s/it]

 12%|█▏        | 104/861 [03:58<33:38,  2.67s/it]

 12%|█▏        | 105/861 [04:01<33:39,  2.67s/it]

 12%|█▏        | 106/861 [04:02<29:16,  2.33s/it]

 12%|█▏        | 107/861 [04:04<27:55,  2.22s/it]

 13%|█▎        | 108/861 [04:05<21:15,  1.69s/it]

 13%|█▎        | 109/861 [04:05<16:28,  1.31s/it]

 13%|█▎        | 110/861 [04:07<19:38,  1.57s/it]

 13%|█▎        | 111/861 [04:08<17:49,  1.43s/it]

 13%|█▎        | 112/861 [04:11<20:30,  1.64s/it]

 13%|█▎        | 113/861 [04:12<20:16,  1.63s/it]

 13%|█▎        | 114/861 [04:15<24:41,  1.98s/it]

 13%|█▎        | 115/861 [04:16<21:07,  1.70s/it]

 13%|█▎        | 116/861 [04:17<18:45,  1.51s/it]

 14%|█▎        | 117/861 [04:20<24:00,  1.94s/it]

 14%|█▎        | 118/861 [04:22<24:13,  1.96s/it]

 14%|█▍        | 119/861 [04:24<24:05,  1.95s/it]

 14%|█▍        | 120/861 [04:24<18:07,  1.47s/it]

 14%|█▍        | 121/861 [04:26<20:21,  1.65s/it]

 14%|█▍        | 122/861 [04:29<24:05,  1.96s/it]

 14%|█▍        | 123/861 [04:31<24:23,  1.98s/it]

 14%|█▍        | 124/861 [04:34<27:59,  2.28s/it]

 15%|█▍        | 125/861 [04:37<30:16,  2.47s/it]

 15%|█▍        | 126/861 [04:39<29:54,  2.44s/it]

 15%|█▍        | 127/861 [04:42<28:46,  2.35s/it]

 15%|█▍        | 128/861 [04:43<26:42,  2.19s/it]

 15%|█▍        | 129/861 [04:46<26:53,  2.20s/it]

 15%|█▌        | 130/861 [04:47<25:49,  2.12s/it]

 15%|█▌        | 131/861 [04:49<24:35,  2.02s/it]

 15%|█▌        | 132/861 [04:52<28:13,  2.32s/it]

 15%|█▌        | 133/861 [04:55<28:59,  2.39s/it]

 16%|█▌        | 134/861 [04:55<21:25,  1.77s/it]

 16%|█▌        | 135/861 [04:56<19:09,  1.58s/it]

 16%|█▌        | 136/861 [04:58<18:00,  1.49s/it]

 16%|█▌        | 137/861 [04:59<17:40,  1.47s/it]

 16%|█▌        | 138/861 [05:00<16:41,  1.39s/it]

 16%|█▌        | 139/861 [05:01<15:19,  1.27s/it]

 16%|█▋        | 140/861 [05:02<15:08,  1.26s/it]

 16%|█▋        | 141/861 [05:04<15:39,  1.30s/it]

 16%|█▋        | 142/861 [05:04<12:35,  1.05s/it]

 17%|█▋        | 143/861 [05:07<19:48,  1.66s/it]

 17%|█▋        | 144/861 [05:10<24:39,  2.06s/it]

 17%|█▋        | 145/861 [05:12<22:13,  1.86s/it]

 17%|█▋        | 146/861 [05:14<21:59,  1.85s/it]

 17%|█▋        | 147/861 [05:15<22:05,  1.86s/it]

 17%|█▋        | 148/861 [05:16<17:48,  1.50s/it]

 17%|█▋        | 149/861 [05:17<14:10,  1.19s/it]

 17%|█▋        | 150/861 [05:20<20:05,  1.70s/it]

 18%|█▊        | 151/861 [05:22<21:49,  1.84s/it]

 18%|█▊        | 152/861 [05:24<23:14,  1.97s/it]

 18%|█▊        | 153/861 [05:27<27:52,  2.36s/it]

 18%|█▊        | 154/861 [05:30<29:16,  2.48s/it]

 18%|█▊        | 155/861 [05:33<32:19,  2.75s/it]

 18%|█▊        | 156/861 [05:37<33:52,  2.88s/it]

 18%|█▊        | 157/861 [05:38<28:56,  2.47s/it]

 18%|█▊        | 158/861 [05:41<32:12,  2.75s/it]

 18%|█▊        | 159/861 [05:43<28:49,  2.46s/it]

 19%|█▊        | 160/861 [05:45<26:29,  2.27s/it]

 19%|█▊        | 161/861 [05:49<31:34,  2.71s/it]

 19%|█▉        | 162/861 [05:50<25:13,  2.17s/it]

 19%|█▉        | 163/861 [05:50<18:55,  1.63s/it]

 19%|█▉        | 164/861 [05:54<26:51,  2.31s/it]

 19%|█▉        | 165/861 [05:57<28:27,  2.45s/it]

 19%|█▉        | 166/861 [05:59<28:40,  2.48s/it]

 19%|█▉        | 167/861 [06:00<21:12,  1.83s/it]

 20%|█▉        | 168/861 [06:02<21:18,  1.84s/it]

 20%|█▉        | 169/861 [06:04<22:27,  1.95s/it]

 20%|█▉        | 170/861 [06:06<22:24,  1.95s/it]

 20%|█▉        | 171/861 [06:07<20:10,  1.75s/it]

 20%|█▉        | 172/861 [06:09<20:39,  1.80s/it]

 20%|██        | 173/861 [06:11<23:01,  2.01s/it]

 20%|██        | 174/861 [06:14<26:10,  2.29s/it]

 20%|██        | 175/861 [06:16<25:04,  2.19s/it]

 20%|██        | 176/861 [06:17<18:32,  1.62s/it]

 21%|██        | 177/861 [06:19<19:46,  1.73s/it]

 21%|██        | 178/861 [06:21<20:33,  1.81s/it]

 21%|██        | 179/861 [06:23<21:49,  1.92s/it]

 21%|██        | 180/861 [06:25<21:59,  1.94s/it]

 21%|██        | 181/861 [06:26<21:14,  1.87s/it]

 21%|██        | 182/861 [06:27<15:55,  1.41s/it]

 21%|██▏       | 183/861 [06:29<18:13,  1.61s/it]

 21%|██▏       | 184/861 [06:32<22:34,  2.00s/it]

 21%|██▏       | 185/861 [06:33<21:05,  1.87s/it]

 22%|██▏       | 186/861 [06:34<18:24,  1.64s/it]

 22%|██▏       | 187/861 [06:37<21:08,  1.88s/it]

 22%|██▏       | 188/861 [06:39<22:49,  2.03s/it]

 22%|██▏       | 189/861 [06:42<24:03,  2.15s/it]

 22%|██▏       | 190/861 [06:44<25:45,  2.30s/it]

 22%|██▏       | 191/861 [06:45<19:21,  1.73s/it]

 22%|██▏       | 192/861 [06:47<20:21,  1.83s/it]

 22%|██▏       | 193/861 [06:50<23:28,  2.11s/it]

 23%|██▎       | 194/861 [06:51<21:10,  1.90s/it]

 23%|██▎       | 195/861 [06:52<18:04,  1.63s/it]

 23%|██▎       | 196/861 [06:56<26:26,  2.39s/it]

 23%|██▎       | 197/861 [06:57<23:10,  2.09s/it]

 23%|██▎       | 198/861 [06:59<21:32,  1.95s/it]

 23%|██▎       | 199/861 [07:02<23:25,  2.12s/it]

 23%|██▎       | 200/861 [07:04<23:27,  2.13s/it]

 23%|██▎       | 201/861 [07:06<24:49,  2.26s/it]

 23%|██▎       | 202/861 [07:08<23:03,  2.10s/it]

 24%|██▎       | 203/861 [07:10<22:02,  2.01s/it]

 24%|██▎       | 204/861 [07:10<16:26,  1.50s/it]

 24%|██▍       | 205/861 [07:11<14:38,  1.34s/it]

 24%|██▍       | 206/861 [07:13<16:41,  1.53s/it]

 24%|██▍       | 207/861 [07:15<18:03,  1.66s/it]

 24%|██▍       | 208/861 [07:17<18:01,  1.66s/it]

 24%|██▍       | 209/861 [07:18<16:36,  1.53s/it]

 24%|██▍       | 210/861 [07:20<18:25,  1.70s/it]

 25%|██▍       | 211/861 [07:23<24:00,  2.22s/it]

 25%|██▍       | 212/861 [07:26<23:27,  2.17s/it]

 25%|██▍       | 213/861 [07:27<20:43,  1.92s/it]

 25%|██▍       | 214/861 [07:28<19:00,  1.76s/it]

 25%|██▍       | 215/861 [07:30<18:08,  1.68s/it]

 25%|██▌       | 216/861 [07:31<16:20,  1.52s/it]

 25%|██▌       | 217/861 [07:32<14:27,  1.35s/it]

 25%|██▌       | 218/861 [07:33<13:58,  1.30s/it]

 25%|██▌       | 219/861 [07:36<18:06,  1.69s/it]

 26%|██▌       | 220/861 [07:38<18:57,  1.77s/it]

 26%|██▌       | 221/861 [07:39<17:46,  1.67s/it]

 26%|██▌       | 222/861 [07:43<23:39,  2.22s/it]

 26%|██▌       | 223/861 [07:45<25:39,  2.41s/it]

 26%|██▌       | 224/861 [07:47<22:29,  2.12s/it]

 26%|██▌       | 225/861 [07:49<23:23,  2.21s/it]

 26%|██▌       | 226/861 [07:52<24:16,  2.29s/it]

 26%|██▋       | 227/861 [07:54<24:13,  2.29s/it]

 26%|██▋       | 228/861 [07:56<22:30,  2.13s/it]

 27%|██▋       | 229/861 [07:57<21:03,  2.00s/it]

 27%|██▋       | 230/861 [08:00<22:13,  2.11s/it]

 27%|██▋       | 231/861 [08:03<26:43,  2.55s/it]

 27%|██▋       | 232/861 [08:04<19:41,  1.88s/it]

 27%|██▋       | 233/861 [08:06<20:29,  1.96s/it]

 27%|██▋       | 234/861 [08:07<19:13,  1.84s/it]

 27%|██▋       | 235/861 [08:10<20:43,  1.99s/it]

 27%|██▋       | 236/861 [08:11<18:47,  1.80s/it]

 28%|██▊       | 237/861 [08:13<18:49,  1.81s/it]

 28%|██▊       | 238/861 [08:14<15:45,  1.52s/it]

 28%|██▊       | 239/861 [08:17<20:39,  1.99s/it]

 28%|██▊       | 240/861 [08:19<21:07,  2.04s/it]

 28%|██▊       | 241/861 [08:22<25:04,  2.43s/it]

 28%|██▊       | 242/861 [08:24<23:07,  2.24s/it]

 28%|██▊       | 243/861 [08:28<27:03,  2.63s/it]

 28%|██▊       | 244/861 [08:30<26:29,  2.58s/it]

 28%|██▊       | 245/861 [08:31<21:59,  2.14s/it]

 29%|██▊       | 246/861 [08:34<23:14,  2.27s/it]

 29%|██▊       | 247/861 [08:35<20:25,  2.00s/it]

 29%|██▉       | 248/861 [08:36<15:14,  1.49s/it]

 29%|██▉       | 249/861 [08:37<14:58,  1.47s/it]

 29%|██▉       | 250/861 [08:40<19:17,  1.89s/it]

 29%|██▉       | 251/861 [08:42<19:45,  1.94s/it]

 29%|██▉       | 252/861 [08:44<19:19,  1.90s/it]

 29%|██▉       | 253/861 [08:45<17:59,  1.77s/it]

 30%|██▉       | 254/861 [08:46<13:37,  1.35s/it]

 30%|██▉       | 255/861 [08:47<14:51,  1.47s/it]

 30%|██▉       | 256/861 [08:50<17:47,  1.77s/it]

 30%|██▉       | 257/861 [08:52<19:25,  1.93s/it]

 30%|██▉       | 258/861 [08:54<19:07,  1.90s/it]

 30%|███       | 259/861 [08:57<22:42,  2.26s/it]

 30%|███       | 260/861 [08:59<22:50,  2.28s/it]

 30%|███       | 261/861 [09:03<26:37,  2.66s/it]

 30%|███       | 262/861 [09:04<22:57,  2.30s/it]

 31%|███       | 263/861 [09:05<17:00,  1.71s/it]

 31%|███       | 264/861 [09:06<17:09,  1.73s/it]

 31%|███       | 265/861 [09:08<15:11,  1.53s/it]

 31%|███       | 266/861 [09:09<14:32,  1.47s/it]

 31%|███       | 267/861 [09:10<14:15,  1.44s/it]

 31%|███       | 268/861 [09:12<15:35,  1.58s/it]

 31%|███       | 269/861 [09:14<16:43,  1.70s/it]

 31%|███▏      | 270/861 [09:16<18:32,  1.88s/it]

 31%|███▏      | 271/861 [09:18<18:35,  1.89s/it]

 32%|███▏      | 272/861 [09:21<20:39,  2.10s/it]

 32%|███▏      | 273/861 [09:23<20:51,  2.13s/it]

 32%|███▏      | 274/861 [09:27<24:48,  2.54s/it]

 32%|███▏      | 275/861 [09:27<18:17,  1.87s/it]

 32%|███▏      | 276/861 [09:29<19:56,  2.04s/it]

 32%|███▏      | 277/861 [09:35<29:42,  3.05s/it]

 32%|███▏      | 278/861 [09:37<26:37,  2.74s/it]

 32%|███▏      | 279/861 [09:39<25:06,  2.59s/it]

 33%|███▎      | 280/861 [09:42<24:49,  2.56s/it]

 33%|███▎      | 281/861 [09:44<24:32,  2.54s/it]

 33%|███▎      | 282/861 [09:46<23:46,  2.46s/it]

 33%|███▎      | 283/861 [09:48<22:36,  2.35s/it]

 33%|███▎      | 284/861 [09:49<18:01,  1.87s/it]

 33%|███▎      | 285/861 [09:51<17:33,  1.83s/it]

 33%|███▎      | 286/861 [09:54<22:28,  2.35s/it]

 33%|███▎      | 287/861 [09:59<27:33,  2.88s/it]

 33%|███▎      | 288/861 [10:01<26:16,  2.75s/it]

 34%|███▎      | 289/861 [10:02<21:18,  2.24s/it]

 34%|███▎      | 290/861 [10:04<20:57,  2.20s/it]

 34%|███▍      | 291/861 [10:07<21:49,  2.30s/it]

 34%|███▍      | 292/861 [10:10<24:06,  2.54s/it]

 34%|███▍      | 293/861 [10:11<21:37,  2.28s/it]

 34%|███▍      | 294/861 [10:14<23:24,  2.48s/it]

 34%|███▍      | 295/861 [10:15<18:02,  1.91s/it]

 34%|███▍      | 296/861 [10:17<17:07,  1.82s/it]

 34%|███▍      | 297/861 [10:20<21:48,  2.32s/it]

 35%|███▍      | 298/861 [10:24<26:56,  2.87s/it]

 35%|███▍      | 299/861 [10:27<25:34,  2.73s/it]

 35%|███▍      | 300/861 [10:29<24:23,  2.61s/it]

 35%|███▍      | 301/861 [10:33<27:31,  2.95s/it]

 35%|███▌      | 302/861 [10:33<20:42,  2.22s/it]

 35%|███▌      | 303/861 [10:37<24:14,  2.61s/it]

 35%|███▌      | 304/861 [10:40<25:59,  2.80s/it]

 35%|███▌      | 305/861 [10:43<26:19,  2.84s/it]

 36%|███▌      | 306/861 [10:47<28:23,  3.07s/it]

 36%|███▌      | 307/861 [10:50<29:15,  3.17s/it]

 36%|███▌      | 308/861 [10:50<21:19,  2.31s/it]

 36%|███▌      | 309/861 [10:52<20:01,  2.18s/it]

 36%|███▌      | 310/861 [10:54<19:03,  2.08s/it]

 36%|███▌      | 311/861 [10:58<24:10,  2.64s/it]

 36%|███▌      | 312/861 [11:01<24:16,  2.65s/it]

 36%|███▋      | 313/861 [11:05<27:57,  3.06s/it]

 36%|███▋      | 314/861 [11:07<27:14,  2.99s/it]

 37%|███▋      | 315/861 [11:10<25:02,  2.75s/it]

 37%|███▋      | 316/861 [11:12<23:57,  2.64s/it]

 37%|███▋      | 317/861 [11:12<17:35,  1.94s/it]

 37%|███▋      | 318/861 [11:15<19:44,  2.18s/it]

 37%|███▋      | 319/861 [11:17<20:30,  2.27s/it]

 37%|███▋      | 320/861 [11:20<20:11,  2.24s/it]

 37%|███▋      | 321/861 [11:23<22:28,  2.50s/it]

 37%|███▋      | 322/861 [11:27<26:19,  2.93s/it]

 38%|███▊      | 323/861 [11:29<25:28,  2.84s/it]

 38%|███▊      | 324/861 [11:35<33:11,  3.71s/it]

 38%|███▊      | 325/861 [11:38<30:42,  3.44s/it]

 38%|███▊      | 326/861 [11:38<22:18,  2.50s/it]

 38%|███▊      | 327/861 [11:42<25:09,  2.83s/it]

 38%|███▊      | 328/861 [11:44<23:30,  2.65s/it]

 38%|███▊      | 329/861 [11:47<25:18,  2.85s/it]

 38%|███▊      | 330/861 [11:49<23:14,  2.63s/it]

 38%|███▊      | 331/861 [11:54<28:52,  3.27s/it]

 39%|███▊      | 332/861 [11:56<25:58,  2.95s/it]

 39%|███▊      | 333/861 [12:00<27:18,  3.10s/it]

 39%|███▉      | 334/861 [12:04<29:13,  3.33s/it]

 39%|███▉      | 335/861 [12:07<28:40,  3.27s/it]

 39%|███▉      | 336/861 [12:10<28:34,  3.27s/it]

 39%|███▉      | 337/861 [12:12<24:10,  2.77s/it]

 39%|███▉      | 338/861 [12:13<19:37,  2.25s/it]

 39%|███▉      | 339/861 [12:16<21:14,  2.44s/it]

 39%|███▉      | 340/861 [12:17<19:04,  2.20s/it]

 40%|███▉      | 341/861 [12:18<15:20,  1.77s/it]

 40%|███▉      | 342/861 [12:20<15:09,  1.75s/it]

 40%|███▉      | 343/861 [12:22<16:07,  1.87s/it]

 40%|███▉      | 344/861 [12:24<15:25,  1.79s/it]

 40%|████      | 345/861 [12:26<16:29,  1.92s/it]

 40%|████      | 346/861 [12:28<17:56,  2.09s/it]

 40%|████      | 347/861 [12:30<16:53,  1.97s/it]

 40%|████      | 348/861 [12:31<15:49,  1.85s/it]

 41%|████      | 349/861 [12:34<18:22,  2.15s/it]

 41%|████      | 350/861 [12:37<19:29,  2.29s/it]

 41%|████      | 351/861 [12:39<18:26,  2.17s/it]

 41%|████      | 352/861 [12:41<17:21,  2.05s/it]

 41%|████      | 353/861 [12:42<16:37,  1.96s/it]

 41%|████      | 354/861 [12:45<17:47,  2.11s/it]

 41%|████      | 355/861 [12:45<14:12,  1.68s/it]

 41%|████▏     | 356/861 [12:47<12:30,  1.49s/it]

 41%|████▏     | 357/861 [12:47<10:11,  1.21s/it]

 42%|████▏     | 358/861 [12:48<09:12,  1.10s/it]

 42%|████▏     | 359/861 [12:50<11:50,  1.42s/it]

 42%|████▏     | 360/861 [12:53<15:53,  1.90s/it]

 42%|████▏     | 361/861 [12:54<13:09,  1.58s/it]

 42%|████▏     | 362/861 [12:56<13:46,  1.66s/it]

 42%|████▏     | 363/861 [12:59<18:10,  2.19s/it]

 42%|████▏     | 364/861 [13:02<18:59,  2.29s/it]

 42%|████▏     | 365/861 [13:05<22:26,  2.72s/it]

 43%|████▎     | 366/861 [13:07<20:43,  2.51s/it]

 43%|████▎     | 367/861 [13:11<23:48,  2.89s/it]

 43%|████▎     | 368/861 [13:15<26:27,  3.22s/it]

 43%|████▎     | 369/861 [13:18<24:10,  2.95s/it]

 43%|████▎     | 370/861 [13:20<21:48,  2.66s/it]

 43%|████▎     | 371/861 [13:21<18:26,  2.26s/it]

 43%|████▎     | 372/861 [13:24<20:47,  2.55s/it]

 43%|████▎     | 373/861 [13:27<20:29,  2.52s/it]

 43%|████▎     | 374/861 [13:30<21:57,  2.71s/it]

 44%|████▎     | 375/861 [13:34<25:03,  3.09s/it]

 44%|████▎     | 376/861 [13:35<21:32,  2.67s/it]

 44%|████▍     | 377/861 [13:38<21:53,  2.71s/it]

 44%|████▍     | 378/861 [13:42<25:08,  3.12s/it]

 44%|████▍     | 379/861 [13:43<18:20,  2.28s/it]

 44%|████▍     | 380/861 [13:44<17:16,  2.15s/it]

 44%|████▍     | 381/861 [13:46<16:28,  2.06s/it]

 44%|████▍     | 382/861 [13:49<17:31,  2.20s/it]

 44%|████▍     | 383/861 [13:51<17:00,  2.14s/it]

 45%|████▍     | 384/861 [13:53<17:28,  2.20s/it]

 45%|████▍     | 385/861 [13:54<14:09,  1.78s/it]

 45%|████▍     | 386/861 [13:57<16:17,  2.06s/it]

 45%|████▍     | 387/861 [13:59<17:27,  2.21s/it]

 45%|████▌     | 388/861 [14:00<15:08,  1.92s/it]

 45%|████▌     | 389/861 [14:01<12:51,  1.63s/it]

 45%|████▌     | 390/861 [14:03<12:53,  1.64s/it]

 45%|████▌     | 391/861 [14:05<12:46,  1.63s/it]

 46%|████▌     | 392/861 [14:07<13:14,  1.69s/it]

 46%|████▌     | 393/861 [14:09<14:46,  1.90s/it]

 46%|████▌     | 394/861 [14:13<19:00,  2.44s/it]

 46%|████▌     | 395/861 [14:14<15:54,  2.05s/it]

 46%|████▌     | 396/861 [14:15<13:42,  1.77s/it]

 46%|████▌     | 397/861 [14:15<10:30,  1.36s/it]

 46%|████▌     | 398/861 [14:17<12:18,  1.59s/it]

 46%|████▋     | 399/861 [14:20<13:59,  1.82s/it]

 46%|████▋     | 400/861 [14:22<15:02,  1.96s/it]

 47%|████▋     | 401/861 [14:23<12:39,  1.65s/it]

 47%|████▋     | 402/861 [14:24<11:52,  1.55s/it]

 47%|████▋     | 403/861 [14:26<12:54,  1.69s/it]

 47%|████▋     | 404/861 [14:28<13:55,  1.83s/it]

 47%|████▋     | 405/861 [14:29<11:48,  1.55s/it]

 47%|████▋     | 406/861 [14:32<14:24,  1.90s/it]

 47%|████▋     | 407/861 [14:33<12:45,  1.69s/it]

 47%|████▋     | 408/861 [14:35<13:10,  1.75s/it]

 48%|████▊     | 409/861 [14:37<13:23,  1.78s/it]

 48%|████▊     | 410/861 [14:38<12:28,  1.66s/it]

 48%|████▊     | 411/861 [14:40<11:25,  1.52s/it]

 48%|████▊     | 412/861 [14:43<14:42,  1.97s/it]

 48%|████▊     | 413/861 [14:44<13:44,  1.84s/it]

 48%|████▊     | 414/861 [14:45<12:33,  1.69s/it]

 48%|████▊     | 415/861 [14:47<11:43,  1.58s/it]

 48%|████▊     | 416/861 [14:48<11:00,  1.49s/it]

 48%|████▊     | 417/861 [14:49<10:52,  1.47s/it]

 49%|████▊     | 418/861 [14:51<11:26,  1.55s/it]

 49%|████▊     | 419/861 [14:53<12:07,  1.65s/it]

 49%|████▉     | 420/861 [14:55<12:36,  1.72s/it]

 49%|████▉     | 421/861 [14:56<10:23,  1.42s/it]

 49%|████▉     | 422/861 [14:57<09:42,  1.33s/it]

 49%|████▉     | 423/861 [14:59<11:44,  1.61s/it]

 49%|████▉     | 424/861 [15:01<12:00,  1.65s/it]

 49%|████▉     | 425/861 [15:03<12:06,  1.67s/it]

 49%|████▉     | 426/861 [15:05<13:39,  1.88s/it]

 50%|████▉     | 427/861 [15:07<13:40,  1.89s/it]

 50%|████▉     | 428/861 [15:08<12:57,  1.79s/it]

 50%|████▉     | 429/861 [15:11<13:39,  1.90s/it]

 50%|████▉     | 430/861 [15:14<16:01,  2.23s/it]

 50%|█████     | 431/861 [15:16<17:30,  2.44s/it]

 50%|█████     | 432/861 [15:19<18:28,  2.58s/it]

 50%|█████     | 433/861 [15:22<18:53,  2.65s/it]

 50%|█████     | 434/861 [15:24<16:36,  2.33s/it]

 51%|█████     | 435/861 [15:24<12:20,  1.74s/it]

 51%|█████     | 436/861 [15:25<09:50,  1.39s/it]

 51%|█████     | 437/861 [15:27<11:06,  1.57s/it]

 51%|█████     | 438/861 [15:28<09:43,  1.38s/it]

 51%|█████     | 439/861 [15:29<09:55,  1.41s/it]

 51%|█████     | 440/861 [15:30<08:33,  1.22s/it]

 51%|█████     | 441/861 [15:31<07:16,  1.04s/it]

 51%|█████▏    | 442/861 [15:32<09:10,  1.31s/it]

 51%|█████▏    | 443/861 [15:33<08:30,  1.22s/it]

 52%|█████▏    | 444/861 [15:35<08:28,  1.22s/it]

 52%|█████▏    | 445/861 [15:36<07:43,  1.11s/it]

 52%|█████▏    | 446/861 [15:37<07:33,  1.09s/it]

 52%|█████▏    | 447/861 [15:39<11:14,  1.63s/it]

 52%|█████▏    | 448/861 [15:42<12:33,  1.82s/it]

 52%|█████▏    | 449/861 [15:44<13:55,  2.03s/it]

 52%|█████▏    | 450/861 [15:46<14:04,  2.06s/it]

 52%|█████▏    | 451/861 [15:48<13:11,  1.93s/it]

 52%|█████▏    | 452/861 [15:50<12:59,  1.91s/it]

 53%|█████▎    | 453/861 [15:51<11:32,  1.70s/it]

 53%|█████▎    | 454/861 [15:53<11:00,  1.62s/it]

 53%|█████▎    | 455/861 [15:54<11:39,  1.72s/it]

 53%|█████▎    | 456/861 [15:56<10:41,  1.58s/it]

 53%|█████▎    | 457/861 [15:58<11:16,  1.68s/it]

 53%|█████▎    | 458/861 [16:00<12:55,  1.93s/it]

 53%|█████▎    | 459/861 [16:01<11:31,  1.72s/it]

 53%|█████▎    | 460/861 [16:03<10:56,  1.64s/it]

 54%|█████▎    | 461/861 [16:05<11:59,  1.80s/it]

 54%|█████▎    | 462/861 [16:06<10:38,  1.60s/it]

 54%|█████▍    | 463/861 [16:07<09:51,  1.49s/it]

 54%|█████▍    | 464/861 [16:09<09:20,  1.41s/it]

 54%|█████▍    | 465/861 [16:09<07:19,  1.11s/it]

 54%|█████▍    | 466/861 [16:09<06:03,  1.09it/s]

 54%|█████▍    | 467/861 [16:13<11:11,  1.70s/it]

 54%|█████▍    | 468/861 [16:14<09:04,  1.38s/it]

 54%|█████▍    | 469/861 [16:15<09:14,  1.41s/it]

 55%|█████▍    | 470/861 [16:16<07:59,  1.23s/it]

 55%|█████▍    | 471/861 [16:17<08:26,  1.30s/it]

 55%|█████▍    | 472/861 [16:18<07:11,  1.11s/it]

 55%|█████▍    | 473/861 [16:18<05:27,  1.18it/s]

 55%|█████▌    | 474/861 [16:19<04:40,  1.38it/s]

 55%|█████▌    | 475/861 [16:20<05:55,  1.09it/s]

 55%|█████▌    | 476/861 [16:21<05:19,  1.20it/s]

 55%|█████▌    | 477/861 [16:23<07:38,  1.19s/it]

 56%|█████▌    | 478/861 [16:24<08:01,  1.26s/it]

 56%|█████▌    | 479/861 [16:25<06:26,  1.01s/it]

 56%|█████▌    | 480/861 [16:26<06:55,  1.09s/it]

 56%|█████▌    | 481/861 [16:27<06:11,  1.02it/s]

 56%|█████▌    | 482/861 [16:27<05:01,  1.26it/s]

 56%|█████▌    | 483/861 [16:28<04:50,  1.30it/s]

 56%|█████▌    | 484/861 [16:29<05:16,  1.19it/s]

 56%|█████▋    | 485/861 [16:29<04:56,  1.27it/s]

 56%|█████▋    | 486/861 [16:30<04:13,  1.48it/s]

 57%|█████▋    | 487/861 [16:31<05:31,  1.13it/s]

 57%|█████▋    | 488/861 [16:32<04:32,  1.37it/s]

 57%|█████▋    | 489/861 [16:33<05:32,  1.12it/s]

 57%|█████▋    | 490/861 [16:34<05:13,  1.18it/s]

 57%|█████▋    | 491/861 [16:34<05:24,  1.14it/s]

 57%|█████▋    | 492/861 [16:35<04:56,  1.25it/s]

 57%|█████▋    | 493/861 [16:36<05:57,  1.03it/s]

 57%|█████▋    | 494/861 [16:37<05:03,  1.21it/s]

 57%|█████▋    | 495/861 [16:39<06:42,  1.10s/it]

 58%|█████▊    | 496/861 [16:40<07:47,  1.28s/it]

 58%|█████▊    | 497/861 [16:41<06:03,  1.00it/s]

 58%|█████▊    | 498/861 [16:42<05:43,  1.06it/s]

 58%|█████▊    | 499/861 [16:42<04:38,  1.30it/s]

 58%|█████▊    | 500/861 [16:43<05:15,  1.15it/s]

 58%|█████▊    | 501/861 [16:43<04:23,  1.37it/s]

 58%|█████▊    | 502/861 [16:45<06:07,  1.02s/it]

 58%|█████▊    | 503/861 [16:46<06:21,  1.06s/it]

 59%|█████▊    | 504/861 [16:47<06:33,  1.10s/it]

 59%|█████▊    | 505/861 [16:48<05:37,  1.05it/s]

 59%|█████▉    | 506/861 [16:49<05:03,  1.17it/s]

 59%|█████▉    | 507/861 [16:49<04:13,  1.40it/s]

 59%|█████▉    | 508/861 [16:51<06:24,  1.09s/it]

 59%|█████▉    | 509/861 [16:54<09:19,  1.59s/it]

 59%|█████▉    | 510/861 [16:56<09:54,  1.69s/it]

 59%|█████▉    | 511/861 [16:58<10:30,  1.80s/it]

 59%|█████▉    | 512/861 [16:59<09:31,  1.64s/it]

 60%|█████▉    | 513/861 [17:00<09:06,  1.57s/it]

 60%|█████▉    | 514/861 [17:02<08:54,  1.54s/it]

 60%|█████▉    | 515/861 [17:02<07:02,  1.22s/it]

 60%|█████▉    | 516/861 [17:03<05:30,  1.04it/s]

 60%|██████    | 517/861 [17:03<04:26,  1.29it/s]

 60%|██████    | 518/861 [17:05<05:54,  1.03s/it]

 60%|██████    | 519/861 [17:06<07:02,  1.24s/it]

 60%|██████    | 520/861 [17:08<08:17,  1.46s/it]

 61%|██████    | 521/861 [17:10<07:58,  1.41s/it]

 61%|██████    | 522/861 [17:12<08:44,  1.55s/it]

 61%|██████    | 523/861 [17:14<09:22,  1.67s/it]

 61%|██████    | 524/861 [17:17<11:35,  2.06s/it]

 61%|██████    | 525/861 [17:18<10:43,  1.92s/it]

 61%|██████    | 526/861 [17:20<10:01,  1.80s/it]

 61%|██████    | 527/861 [17:21<09:28,  1.70s/it]

 61%|██████▏   | 528/861 [17:23<10:21,  1.86s/it]

 61%|██████▏   | 529/861 [17:24<08:29,  1.53s/it]

 62%|██████▏   | 530/861 [17:25<07:46,  1.41s/it]

 62%|██████▏   | 531/861 [17:26<06:41,  1.22s/it]

 62%|██████▏   | 532/861 [17:28<07:33,  1.38s/it]

 62%|██████▏   | 533/861 [17:29<06:52,  1.26s/it]

 62%|██████▏   | 534/861 [17:30<06:47,  1.25s/it]

 62%|██████▏   | 535/861 [17:31<06:37,  1.22s/it]

 62%|██████▏   | 536/861 [17:33<06:55,  1.28s/it]

 62%|██████▏   | 537/861 [17:35<08:47,  1.63s/it]

 62%|██████▏   | 538/861 [17:36<07:34,  1.41s/it]

 63%|██████▎   | 539/861 [17:39<10:42,  2.00s/it]

 63%|██████▎   | 540/861 [17:41<10:21,  1.94s/it]

 63%|██████▎   | 541/861 [17:42<09:13,  1.73s/it]

 63%|██████▎   | 542/861 [17:43<08:11,  1.54s/it]

 63%|██████▎   | 543/861 [17:46<09:27,  1.78s/it]

 63%|██████▎   | 544/861 [17:47<08:15,  1.56s/it]

 63%|██████▎   | 545/861 [17:50<10:21,  1.97s/it]

 63%|██████▎   | 546/861 [17:52<10:28,  2.00s/it]

 64%|██████▎   | 547/861 [17:54<10:11,  1.95s/it]

 64%|██████▎   | 548/861 [17:57<11:58,  2.30s/it]

 64%|██████▍   | 549/861 [17:59<11:53,  2.29s/it]

 64%|██████▍   | 550/861 [18:01<11:52,  2.29s/it]

 64%|██████▍   | 551/861 [18:03<11:10,  2.16s/it]

 64%|██████▍   | 552/861 [18:06<12:54,  2.50s/it]

 64%|██████▍   | 553/861 [18:10<14:02,  2.74s/it]

 64%|██████▍   | 554/861 [18:13<14:48,  2.89s/it]

 64%|██████▍   | 555/861 [18:16<14:58,  2.94s/it]

 65%|██████▍   | 556/861 [18:19<14:23,  2.83s/it]

 65%|██████▍   | 557/861 [18:22<14:47,  2.92s/it]

 65%|██████▍   | 558/861 [18:24<13:33,  2.68s/it]

 65%|██████▍   | 559/861 [18:25<11:00,  2.19s/it]

 65%|██████▌   | 560/861 [18:28<12:15,  2.44s/it]

 65%|██████▌   | 561/861 [18:30<12:08,  2.43s/it]

 65%|██████▌   | 562/861 [18:34<14:15,  2.86s/it]

 65%|██████▌   | 563/861 [18:37<13:49,  2.78s/it]

 66%|██████▌   | 564/861 [18:41<15:11,  3.07s/it]

 66%|██████▌   | 565/861 [18:44<15:48,  3.21s/it]

 66%|██████▌   | 566/861 [18:48<17:11,  3.50s/it]

 66%|██████▌   | 567/861 [18:51<15:44,  3.21s/it]

 66%|██████▌   | 568/861 [18:54<15:32,  3.18s/it]

 66%|██████▌   | 569/861 [18:57<15:07,  3.11s/it]

 66%|██████▌   | 570/861 [18:59<13:50,  2.86s/it]

 66%|██████▋   | 571/861 [19:02<13:50,  2.87s/it]

 66%|██████▋   | 572/861 [19:06<15:02,  3.12s/it]

 67%|██████▋   | 573/861 [19:07<13:05,  2.73s/it]

 67%|██████▋   | 574/861 [19:10<13:06,  2.74s/it]

 67%|██████▋   | 575/861 [19:13<13:22,  2.80s/it]

 67%|██████▋   | 576/861 [19:18<15:35,  3.28s/it]

 67%|██████▋   | 577/861 [19:20<14:59,  3.17s/it]

 67%|██████▋   | 578/861 [19:23<14:08,  3.00s/it]

 67%|██████▋   | 579/861 [19:28<16:20,  3.48s/it]

 67%|██████▋   | 580/861 [19:31<15:33,  3.32s/it]

 67%|██████▋   | 581/861 [19:34<14:50,  3.18s/it]

 68%|██████▊   | 582/861 [19:39<17:19,  3.73s/it]

 68%|██████▊   | 583/861 [19:42<16:29,  3.56s/it]

 68%|██████▊   | 584/861 [19:44<15:01,  3.26s/it]

 68%|██████▊   | 585/861 [19:50<17:51,  3.88s/it]

 68%|██████▊   | 586/861 [19:51<14:51,  3.24s/it]

 68%|██████▊   | 587/861 [19:55<15:06,  3.31s/it]

 68%|██████▊   | 588/861 [19:57<14:01,  3.08s/it]

 68%|██████▊   | 589/861 [19:59<12:06,  2.67s/it]

 69%|██████▊   | 590/861 [20:04<14:31,  3.22s/it]

 69%|██████▊   | 591/861 [20:06<13:22,  2.97s/it]

 69%|██████▉   | 592/861 [20:12<17:00,  3.79s/it]

 69%|██████▉   | 593/861 [20:15<16:17,  3.65s/it]

 69%|██████▉   | 594/861 [20:18<15:45,  3.54s/it]

 69%|██████▉   | 595/861 [20:20<13:25,  3.03s/it]

 69%|██████▉   | 596/861 [20:21<10:55,  2.47s/it]

 69%|██████▉   | 597/861 [20:26<13:14,  3.01s/it]

 69%|██████▉   | 598/861 [20:28<12:58,  2.96s/it]

 70%|██████▉   | 599/861 [20:31<12:17,  2.82s/it]

 70%|██████▉   | 600/861 [20:33<11:26,  2.63s/it]

 70%|██████▉   | 601/861 [20:35<10:42,  2.47s/it]

 70%|██████▉   | 602/861 [20:38<11:39,  2.70s/it]

 70%|███████   | 603/861 [20:42<12:32,  2.92s/it]

 70%|███████   | 604/861 [20:45<12:49,  3.00s/it]

 70%|███████   | 605/861 [20:47<11:35,  2.72s/it]

 70%|███████   | 606/861 [20:49<10:29,  2.47s/it]

 70%|███████   | 607/861 [20:51<09:32,  2.25s/it]

 71%|███████   | 608/861 [20:52<08:51,  2.10s/it]

 71%|███████   | 609/861 [20:56<10:34,  2.52s/it]

 71%|███████   | 610/861 [21:00<12:04,  2.89s/it]

 71%|███████   | 611/861 [21:02<11:22,  2.73s/it]

 71%|███████   | 612/861 [21:04<10:53,  2.63s/it]

 71%|███████   | 613/861 [21:06<09:03,  2.19s/it]

 71%|███████▏  | 614/861 [21:08<09:16,  2.25s/it]

 71%|███████▏  | 615/861 [21:11<10:14,  2.50s/it]

 72%|███████▏  | 616/861 [21:16<13:15,  3.25s/it]

 72%|███████▏  | 617/861 [21:19<13:22,  3.29s/it]

 72%|███████▏  | 618/861 [21:23<13:13,  3.27s/it]

 72%|███████▏  | 619/861 [21:25<11:52,  2.95s/it]

 72%|███████▏  | 620/861 [21:29<13:32,  3.37s/it]

 72%|███████▏  | 621/861 [21:32<12:45,  3.19s/it]

 72%|███████▏  | 622/861 [21:33<10:40,  2.68s/it]

 72%|███████▏  | 623/861 [21:38<12:16,  3.10s/it]

 72%|███████▏  | 624/861 [21:40<12:04,  3.05s/it]

 73%|███████▎  | 625/861 [21:42<09:47,  2.49s/it]

 73%|███████▎  | 626/861 [21:44<09:02,  2.31s/it]

 73%|███████▎  | 627/861 [21:47<10:00,  2.57s/it]

 73%|███████▎  | 628/861 [21:50<10:57,  2.82s/it]

 73%|███████▎  | 629/861 [21:54<12:02,  3.12s/it]

 73%|███████▎  | 630/861 [21:57<12:24,  3.22s/it]

 73%|███████▎  | 631/861 [21:58<09:40,  2.53s/it]

 73%|███████▎  | 632/861 [22:01<10:17,  2.70s/it]

 74%|███████▎  | 633/861 [22:04<09:56,  2.61s/it]

 74%|███████▎  | 634/861 [22:07<10:47,  2.85s/it]

 74%|███████▍  | 635/861 [22:10<10:10,  2.70s/it]

 74%|███████▍  | 636/861 [22:12<09:18,  2.48s/it]

 74%|███████▍  | 637/861 [22:13<08:21,  2.24s/it]

 74%|███████▍  | 638/861 [22:15<07:51,  2.11s/it]

 74%|███████▍  | 639/861 [22:18<08:57,  2.42s/it]

 74%|███████▍  | 640/861 [22:20<08:30,  2.31s/it]

 74%|███████▍  | 641/861 [22:22<08:23,  2.29s/it]

 75%|███████▍  | 642/861 [22:24<07:52,  2.16s/it]

 75%|███████▍  | 643/861 [22:26<07:24,  2.04s/it]

 75%|███████▍  | 644/861 [22:28<07:14,  2.00s/it]

 75%|███████▍  | 645/861 [22:29<05:56,  1.65s/it]

 75%|███████▌  | 646/861 [22:30<05:41,  1.59s/it]

 75%|███████▌  | 647/861 [22:31<04:57,  1.39s/it]

 75%|███████▌  | 648/861 [22:33<05:25,  1.53s/it]

 75%|███████▌  | 649/861 [22:35<05:33,  1.57s/it]

 75%|███████▌  | 650/861 [22:35<04:34,  1.30s/it]

 76%|███████▌  | 651/861 [22:36<04:06,  1.17s/it]

 76%|███████▌  | 652/861 [22:38<04:25,  1.27s/it]

 76%|███████▌  | 653/861 [22:39<04:13,  1.22s/it]

 76%|███████▌  | 654/861 [22:40<04:12,  1.22s/it]

 76%|███████▌  | 655/861 [22:41<03:45,  1.09s/it]

 76%|███████▌  | 656/861 [22:41<03:13,  1.06it/s]

 76%|███████▋  | 657/861 [22:42<03:02,  1.12it/s]

 76%|███████▋  | 658/861 [22:44<03:55,  1.16s/it]

 77%|███████▋  | 659/861 [22:45<03:58,  1.18s/it]

 77%|███████▋  | 660/861 [22:47<04:38,  1.38s/it]

 77%|███████▋  | 661/861 [22:49<04:47,  1.44s/it]

 77%|███████▋  | 662/861 [22:51<05:40,  1.71s/it]

 77%|███████▋  | 663/861 [22:52<04:45,  1.44s/it]

 77%|███████▋  | 664/861 [22:53<04:24,  1.34s/it]

 77%|███████▋  | 665/861 [22:54<04:18,  1.32s/it]

 77%|███████▋  | 666/861 [22:55<03:48,  1.17s/it]

 77%|███████▋  | 667/861 [22:56<03:59,  1.23s/it]

 78%|███████▊  | 668/861 [22:58<03:58,  1.23s/it]

 78%|███████▊  | 669/861 [22:58<03:27,  1.08s/it]

 78%|███████▊  | 670/861 [23:00<03:36,  1.14s/it]

 78%|███████▊  | 671/861 [23:00<02:50,  1.12it/s]

 78%|███████▊  | 672/861 [23:03<04:33,  1.45s/it]

 78%|███████▊  | 673/861 [23:05<05:18,  1.69s/it]

 78%|███████▊  | 674/861 [23:06<04:41,  1.51s/it]

 78%|███████▊  | 675/861 [23:10<06:49,  2.20s/it]

 79%|███████▊  | 676/861 [23:11<06:06,  1.98s/it]

 79%|███████▊  | 677/861 [23:13<06:05,  1.99s/it]

 79%|███████▊  | 678/861 [23:14<05:09,  1.69s/it]

 79%|███████▉  | 679/861 [23:15<04:31,  1.49s/it]

 79%|███████▉  | 680/861 [23:16<03:50,  1.27s/it]

 79%|███████▉  | 681/861 [23:18<04:43,  1.58s/it]

 79%|███████▉  | 682/861 [23:20<04:48,  1.61s/it]

 79%|███████▉  | 683/861 [23:21<04:29,  1.51s/it]

 79%|███████▉  | 684/861 [23:24<05:30,  1.86s/it]

 80%|███████▉  | 685/861 [23:25<04:54,  1.67s/it]

 80%|███████▉  | 686/861 [23:26<04:25,  1.52s/it]

 80%|███████▉  | 687/861 [23:30<06:30,  2.24s/it]

 80%|███████▉  | 688/861 [23:31<05:22,  1.87s/it]

 80%|████████  | 689/861 [23:33<05:03,  1.77s/it]

 80%|████████  | 690/861 [23:34<04:47,  1.68s/it]

 80%|████████  | 691/861 [23:36<05:02,  1.78s/it]

 80%|████████  | 692/861 [23:38<04:54,  1.74s/it]

 80%|████████  | 693/861 [23:39<04:31,  1.62s/it]

 81%|████████  | 694/861 [23:40<03:53,  1.40s/it]

 81%|████████  | 695/861 [23:43<04:36,  1.66s/it]

 81%|████████  | 696/861 [23:43<03:53,  1.42s/it]

 81%|████████  | 697/861 [23:45<03:43,  1.37s/it]

 81%|████████  | 698/861 [23:46<03:47,  1.39s/it]

 81%|████████  | 699/861 [23:50<06:01,  2.23s/it]

 81%|████████▏ | 700/861 [23:53<06:44,  2.51s/it]

 81%|████████▏ | 701/861 [23:55<06:04,  2.28s/it]

 82%|████████▏ | 702/861 [23:57<05:25,  2.05s/it]

 82%|████████▏ | 703/861 [23:58<04:51,  1.84s/it]

 82%|████████▏ | 704/861 [24:00<04:33,  1.74s/it]

 82%|████████▏ | 705/861 [24:01<04:31,  1.74s/it]

 82%|████████▏ | 706/861 [24:02<03:52,  1.50s/it]

 82%|████████▏ | 707/861 [24:03<03:18,  1.29s/it]

 82%|████████▏ | 708/861 [24:04<03:10,  1.24s/it]

 82%|████████▏ | 709/861 [24:05<03:02,  1.20s/it]

 82%|████████▏ | 710/861 [24:08<03:53,  1.55s/it]

 83%|████████▎ | 711/861 [24:09<04:03,  1.62s/it]

 83%|████████▎ | 712/861 [24:11<03:43,  1.50s/it]

 83%|████████▎ | 713/861 [24:11<02:59,  1.21s/it]

 83%|████████▎ | 714/861 [24:13<03:08,  1.28s/it]

 83%|████████▎ | 715/861 [24:15<04:04,  1.67s/it]

 83%|████████▎ | 716/861 [24:17<04:17,  1.78s/it]

 83%|████████▎ | 717/861 [24:18<03:50,  1.60s/it]

 83%|████████▎ | 718/861 [24:19<03:18,  1.39s/it]

 84%|████████▎ | 719/861 [24:20<03:04,  1.30s/it]

 84%|████████▎ | 720/861 [24:21<02:51,  1.21s/it]

 84%|████████▎ | 721/861 [24:22<02:41,  1.16s/it]

 84%|████████▍ | 722/861 [24:24<03:05,  1.33s/it]

 84%|████████▍ | 723/861 [24:25<02:53,  1.25s/it]

 84%|████████▍ | 724/861 [24:27<02:52,  1.26s/it]

 84%|████████▍ | 725/861 [24:27<02:26,  1.08s/it]

 84%|████████▍ | 726/861 [24:29<02:48,  1.25s/it]

 84%|████████▍ | 727/861 [24:31<03:38,  1.63s/it]

 85%|████████▍ | 728/861 [24:33<03:41,  1.66s/it]

 85%|████████▍ | 729/861 [24:34<03:21,  1.52s/it]

 85%|████████▍ | 730/861 [24:35<02:42,  1.24s/it]

 85%|████████▍ | 731/861 [24:37<03:24,  1.57s/it]

 85%|████████▌ | 732/861 [24:38<03:02,  1.42s/it]

 85%|████████▌ | 733/861 [24:40<02:59,  1.40s/it]

 85%|████████▌ | 734/861 [24:40<02:26,  1.15s/it]

 85%|████████▌ | 735/861 [24:41<02:14,  1.07s/it]

 85%|████████▌ | 736/861 [24:42<02:21,  1.13s/it]

 86%|████████▌ | 737/861 [24:44<02:50,  1.38s/it]

 86%|████████▌ | 738/861 [24:45<02:32,  1.24s/it]

 86%|████████▌ | 739/861 [24:46<02:24,  1.19s/it]

 86%|████████▌ | 740/861 [24:47<01:56,  1.04it/s]

 86%|████████▌ | 741/861 [24:48<02:20,  1.17s/it]

 86%|████████▌ | 742/861 [24:50<02:35,  1.31s/it]

 86%|████████▋ | 743/861 [24:51<02:19,  1.19s/it]

 86%|████████▋ | 744/861 [24:52<02:10,  1.11s/it]

 87%|████████▋ | 745/861 [24:54<02:38,  1.37s/it]

 87%|████████▋ | 746/861 [24:55<02:25,  1.26s/it]

 87%|████████▋ | 747/861 [24:57<03:05,  1.63s/it]

 87%|████████▋ | 748/861 [24:59<03:21,  1.78s/it]

 87%|████████▋ | 749/861 [25:01<03:13,  1.73s/it]

 87%|████████▋ | 750/861 [25:02<02:42,  1.46s/it]

 87%|████████▋ | 751/861 [25:02<02:05,  1.14s/it]

 87%|████████▋ | 752/861 [25:06<03:18,  1.82s/it]

 87%|████████▋ | 753/861 [25:08<03:32,  1.97s/it]

 88%|████████▊ | 754/861 [25:09<02:57,  1.66s/it]

 88%|████████▊ | 755/861 [25:10<02:38,  1.50s/it]

 88%|████████▊ | 756/861 [25:11<02:27,  1.40s/it]

 88%|████████▊ | 757/861 [25:14<02:57,  1.70s/it]

 88%|████████▊ | 758/861 [25:15<02:45,  1.61s/it]

 88%|████████▊ | 759/861 [25:16<02:29,  1.47s/it]

 88%|████████▊ | 760/861 [25:18<02:47,  1.66s/it]

 88%|████████▊ | 761/861 [25:24<04:50,  2.90s/it]

 89%|████████▊ | 762/861 [25:25<04:00,  2.43s/it]

 89%|████████▊ | 763/861 [25:27<03:29,  2.14s/it]

 89%|████████▊ | 764/861 [25:29<03:14,  2.00s/it]

 89%|████████▉ | 765/861 [25:31<03:33,  2.23s/it]

 89%|████████▉ | 766/861 [25:33<03:28,  2.20s/it]

 89%|████████▉ | 767/861 [25:39<05:09,  3.29s/it]

 89%|████████▉ | 768/861 [25:42<04:37,  2.99s/it]

 89%|████████▉ | 769/861 [25:44<04:13,  2.75s/it]

 89%|████████▉ | 770/861 [25:45<03:25,  2.26s/it]

 90%|████████▉ | 771/861 [25:46<02:51,  1.91s/it]

 90%|████████▉ | 772/861 [25:48<02:51,  1.92s/it]

 90%|████████▉ | 773/861 [25:50<02:55,  1.99s/it]

 90%|████████▉ | 774/861 [25:52<02:47,  1.92s/it]

 90%|█████████ | 775/861 [25:55<03:05,  2.16s/it]

 90%|█████████ | 776/861 [25:57<03:17,  2.33s/it]

 90%|█████████ | 777/861 [26:01<03:43,  2.66s/it]

 90%|█████████ | 778/861 [26:03<03:23,  2.46s/it]

 90%|█████████ | 779/861 [26:05<03:28,  2.54s/it]

 91%|█████████ | 780/861 [26:09<03:55,  2.91s/it]

 91%|█████████ | 781/861 [26:14<04:39,  3.49s/it]

 91%|█████████ | 782/861 [26:17<04:24,  3.35s/it]

 91%|█████████ | 783/861 [26:19<03:49,  2.95s/it]

 91%|█████████ | 784/861 [26:24<04:29,  3.50s/it]

 91%|█████████ | 785/861 [26:26<03:47,  2.99s/it]

 91%|█████████▏| 786/861 [26:27<03:14,  2.60s/it]

 91%|█████████▏| 787/861 [26:29<02:48,  2.27s/it]

 92%|█████████▏| 788/861 [26:33<03:27,  2.84s/it]

 92%|█████████▏| 789/861 [26:35<03:15,  2.71s/it]

 92%|█████████▏| 790/861 [26:38<03:03,  2.58s/it]

 92%|█████████▏| 791/861 [26:40<02:45,  2.36s/it]

 92%|█████████▏| 792/861 [26:41<02:22,  2.07s/it]

 92%|█████████▏| 793/861 [26:44<02:35,  2.28s/it]

 92%|█████████▏| 794/861 [26:45<02:10,  1.94s/it]

 92%|█████████▏| 795/861 [26:50<03:01,  2.75s/it]

 92%|█████████▏| 796/861 [26:50<02:23,  2.20s/it]

 93%|█████████▎| 797/861 [26:52<02:11,  2.06s/it]

 93%|█████████▎| 798/861 [26:55<02:25,  2.31s/it]

 93%|█████████▎| 799/861 [26:57<02:17,  2.22s/it]

 93%|█████████▎| 800/861 [26:59<02:17,  2.25s/it]

 93%|█████████▎| 801/861 [27:02<02:19,  2.32s/it]

 93%|█████████▎| 802/861 [27:04<02:14,  2.29s/it]

 93%|█████████▎| 803/861 [27:06<02:09,  2.23s/it]

 93%|█████████▎| 804/861 [27:12<03:00,  3.17s/it]

 93%|█████████▎| 805/861 [27:16<03:22,  3.61s/it]

 94%|█████████▎| 806/861 [27:17<02:30,  2.75s/it]

 94%|█████████▎| 807/861 [27:19<02:15,  2.52s/it]

 94%|█████████▍| 808/861 [27:21<02:05,  2.37s/it]

 94%|█████████▍| 809/861 [27:22<01:37,  1.87s/it]

 94%|█████████▍| 810/861 [27:23<01:30,  1.78s/it]

 94%|█████████▍| 811/861 [27:25<01:35,  1.91s/it]

 94%|█████████▍| 812/861 [27:27<01:27,  1.78s/it]

 94%|█████████▍| 813/861 [27:30<01:45,  2.19s/it]

 95%|█████████▍| 814/861 [27:33<01:49,  2.33s/it]

 95%|█████████▍| 815/861 [27:35<01:51,  2.41s/it]

 95%|█████████▍| 816/861 [27:37<01:36,  2.14s/it]

 95%|█████████▍| 817/861 [27:39<01:36,  2.19s/it]

 95%|█████████▌| 818/861 [27:42<01:39,  2.30s/it]

 95%|█████████▌| 819/861 [27:43<01:23,  2.00s/it]

 95%|█████████▌| 820/861 [27:45<01:28,  2.16s/it]

 95%|█████████▌| 821/861 [27:49<01:41,  2.54s/it]

 95%|█████████▌| 822/861 [27:52<01:45,  2.72s/it]

 96%|█████████▌| 823/861 [27:56<01:54,  3.00s/it]

 96%|█████████▌| 824/861 [27:57<01:33,  2.52s/it]

 96%|█████████▌| 825/861 [27:58<01:17,  2.16s/it]

 96%|█████████▌| 826/861 [28:01<01:18,  2.25s/it]

 96%|█████████▌| 827/861 [28:03<01:20,  2.35s/it]

 96%|█████████▌| 828/861 [28:05<01:09,  2.11s/it]

 96%|█████████▋| 829/861 [28:08<01:17,  2.42s/it]

 96%|█████████▋| 830/861 [28:11<01:16,  2.47s/it]

 97%|█████████▋| 831/861 [28:13<01:14,  2.49s/it]

 97%|█████████▋| 832/861 [28:16<01:14,  2.58s/it]

 97%|█████████▋| 833/861 [28:17<01:00,  2.16s/it]

 97%|█████████▋| 834/861 [28:20<00:59,  2.21s/it]

 97%|█████████▋| 835/861 [28:22<00:56,  2.19s/it]

 97%|█████████▋| 836/861 [28:24<00:57,  2.31s/it]

 97%|█████████▋| 837/861 [28:27<00:55,  2.32s/it]

 97%|█████████▋| 838/861 [28:29<00:55,  2.41s/it]

 97%|█████████▋| 839/861 [28:31<00:47,  2.16s/it]

 98%|█████████▊| 840/861 [28:33<00:43,  2.09s/it]

 98%|█████████▊| 841/861 [28:35<00:41,  2.09s/it]

 98%|█████████▊| 842/861 [28:37<00:38,  2.04s/it]

 98%|█████████▊| 843/861 [28:40<00:43,  2.42s/it]

 98%|█████████▊| 844/861 [28:42<00:39,  2.30s/it]

 98%|█████████▊| 845/861 [28:45<00:37,  2.37s/it]

 98%|█████████▊| 846/861 [28:47<00:33,  2.23s/it]

 98%|█████████▊| 847/861 [28:49<00:30,  2.17s/it]

 98%|█████████▊| 848/861 [28:51<00:30,  2.34s/it]

 99%|█████████▊| 849/861 [28:54<00:29,  2.44s/it]

 99%|█████████▊| 850/861 [28:55<00:23,  2.14s/it]

 99%|█████████▉| 851/861 [28:57<00:20,  2.05s/it]

 99%|█████████▉| 852/861 [28:59<00:16,  1.82s/it]

 99%|█████████▉| 853/861 [29:02<00:17,  2.23s/it]

 99%|█████████▉| 854/861 [29:03<00:14,  2.09s/it]

 99%|█████████▉| 855/861 [29:06<00:12,  2.11s/it]

 99%|█████████▉| 856/861 [29:09<00:12,  2.41s/it]

100%|█████████▉| 857/861 [29:11<00:08,  2.22s/it]

100%|█████████▉| 858/861 [29:13<00:06,  2.21s/it]

100%|█████████▉| 859/861 [29:14<00:03,  1.79s/it]

100%|█████████▉| 860/861 [29:16<00:01,  1.87s/it]

100%|██████████| 861/861 [29:17<00:00,  1.87s/it]{'score': 0.16852680722117389, 'counts': [9219, 694, 235, 99], 'totals': [371156, 369434, 367712, 365990], 'precisions': [2.4838612335513908, 0.18785493484627835, 0.06390871116525977, 0.027049919396704827], 'bp': 1.0, 'sys_len': 371156, 'ref_len': 32555}

                                                          

                                                 
{'eval_loss': 2.695643186569214, 'eval_bleu': 0.1685, 'eval_gen_len': 105.7747, 'eval_runtime': 1862.1701, 'eval_samples_per_second': 0.925, 'eval_steps_per_second': 0.462, 'epoch': 4.0}

 25%|██▌       | 15478/61904 [8:04:12<17:51:46,  1.39s/it]

100%|██████████| 861/861 [31:00<00:00,  1.87s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-25 09:25:21,216 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 25%|██▌       | 15479/61904 [8:04:32<7294:49:21, 565.67s/it]
 25%|██▌       | 15480/61904 [8:04:33<5112:10:07, 396.43s/it]
                                                             
{'loss': 2.7449, 'learning_rate': 1.75236613509659e-07, 'epoch': 4.0}

 25%|██▌       | 15480/61904 [8:04:33<5112:10:07, 396.43s/it]
 25%|██▌       | 15481/61904 [8:04:35<3583:41:38, 277.91s/it]
 25%|██▌       | 15482/61904 [8:04:36<2513:58:58, 194.96s/it]
 25%|██▌       | 15483/61904 [8:04:38<1766:08:24, 136.97s/it]
 25%|██▌       | 15484/61904 [8:04:39<1242:39:25, 96.37s/it] 
 25%|██▌       | 15485/61904 [8:04:41<874:35:36, 67.83s/it] 
 25%|██▌       | 15486/61904 [8:04:42<617:24:03, 47.88s/it]
 25%|██▌       | 15487/61904 [8:04:43<437:38:39, 33.94s/it]
 25%|██▌       | 15488/61904 [8:04:45<311:45:10, 24.18s/it]
 25%|██▌       | 15489/61904 [8:04:46<223:45:15, 17.35s/it]
 25%|██▌       | 15490/61904 [8:04:48<161:55:21, 12.56s/it]
 25%|██▌       | 15491/61904 [8:04:49<118:26:20,  9.19s/it]
 25%|██▌       | 15492/61904 [8:04:50<88:31:35,  6.87s/it] 
 25%|██▌       | 15493/61904 [8:04:52<67:05:47,  5.20s/it]
 25%|██▌       | 15494/61904 [8:04:53<52:12:21,  4.05s/it]
 25%|██▌       | 15495/61904 [8:04:55<42:32:50,  3.30s/it]
 25%|██▌       | 15496/61904 [8:04:56<35:14:31,  2.73s/it]
 25%|██▌       | 15497/61904 [8:04:58<30:37:37,  2.38s/it]
 25%|██▌       | 15498/61904 [8:04:59<26:36:55,  2.06s/it]
 25%|██▌       | 15499/61904 [8:05:00<23:28:07,  1.82s/it]
 25%|██▌       | 15500/61904 [8:05:02<22:19:47,  1.73s/it]
                                                          
{'loss': 2.7855, 'learning_rate': 1.752042007001167e-07, 'epoch': 4.01}

 25%|██▌       | 15500/61904 [8:05:02<22:19:47,  1.73s/it]
 25%|██▌       | 15501/61904 [8:05:03<21:21:07,  1.66s/it]
 25%|██▌       | 15502/61904 [8:05:04<20:07:57,  1.56s/it]
 25%|██▌       | 15503/61904 [8:05:06<19:35:31,  1.52s/it]
 25%|██▌       | 15504/61904 [8:05:07<19:10:55,  1.49s/it]
 25%|██▌       | 15505/61904 [8:05:09<19:07:14,  1.48s/it]
 25%|██▌       | 15506/61904 [8:05:10<18:49:05,  1.46s/it]
 25%|██▌       | 15507/61904 [8:05:12<18:18:22,  1.42s/it]
 25%|██▌       | 15508/61904 [8:05:13<17:48:31,  1.38s/it]
 25%|██▌       | 15509/61904 [8:05:14<18:07:42,  1.41s/it]
 25%|██▌       | 15510/61904 [8:05:16<17:52:06,  1.39s/it]
 25%|██▌       | 15511/61904 [8:05:17<18:04:05,  1.40s/it]
 25%|██▌       | 15512/61904 [8:05:18<17:44:27,  1.38s/it]
 25%|██▌       | 15513/61904 [8:05:20<17:35:33,  1.37s/it]
 25%|██▌       | 15514/61904 [8:05:21<17:53:45,  1.39s/it]
 25%|██▌       | 15515/61904 [8:05:22<17:16:34,  1.34s/it]
 25%|██▌       | 15516/61904 [8:05:24<17:45:27,  1.38s/it]
 25%|██▌       | 15517/61904 [8:05:25<17:25:21,  1.35s/it]