epoch 1 log

logs/l40-1gpu-fine-tuned.txt

@@ -254,3 +254,4 @@ Batch output: ['Old Geng raised his rifle and, squinting one of his triangular e
 Qwen/Qwen2-7B-Instruct/epochs-03 metrics: {'meteor': 0.4440963225595562, 'bleu_scores': {'bleu': 0.15514758216718177, 'precisions': [0.4806391496410823, 0.20827497036957224, 0.10928082063569317, 0.06262705238467553], 'brevity_penalty': 0.9589687965342737, 'length_ratio': 0.9597880092745943, 'translation_length': 28976, 'reference_length': 30190}, 'rouge_scores': {'rouge1': 0.47435597120065365, 'rouge2': 0.22969970970677933, 'rougeL': 0.4190988648363645, 'rougeLsum': 0.418702944344323}, 'accuracy': 0.01412180052956752, 'correct_ids': [41, 77, 133, 137, 193, 240, 272, 348, 419, 533, 567, 658, 659, 778, 813, 893]}
 Epoch 4
 loading adapter: llama-factory/saves/Qwen2-7B-Instruct/checkpoint-140
+
  0%|          | 0/1133 [00:00<?, ?it/s]
  0%|          | 1/1133 [00:02<40:10,  2.13s/it]
  0%|          | 2/1133 [00:04<45:55,  2.44s/it]
  0%|          | 3/1133 [00:06<43:20,  2.30s/it]
  0%|          | 4/1133 [00:08<39:14,  2.09s/it]
  0%|          | 5/1133 [00:10<36:44,  1.95s/it]
  1%|          | 6/1133 [00:11<32:00,  1.70s/it]
  1%|          | 7/1133 [00:13<33:47,  1.80s/it]
  1%|          | 8/1133 [00:17<44:47,  2.39s/it]
  1%|          | 9/1133 [00:17<34:26,  1.84s/it]
  1%|          | 10/1133 [00:18<27:37,  1.48s/it]
  1%|          | 11/1133 [00:19<24:04,  1.29s/it]
  1%|          | 12/1133 [00:21<26:15,  1.41s/it]
  1%|          | 13/1133 [00:21<21:35,  1.16s/it]
  1%|          | 14/1133 [00:21<16:23,  1.14it/s]
  1%|▏         | 15/1133 [00:24<24:14,  1.30s/it]
  1%|▏         | 16/1133 [00:24<19:59,  1.07s/it]
  2%|▏         | 17/1133 [00:26<26:08,  1.41s/it]
  2%|▏         | 18/1133 [00:29<32:33,  1.75s/it]
  2%|▏         | 19/1133 [00:29<24:56,  1.34s/it]
  2%|▏         | 20/1133 [00:31<26:07,  1.41s/it]
  2%|▏         | 21/1133 [00:32<23:52,  1.29s/it]
  2%|▏         | 22/1133 [00:34<29:17,  1.58s/it]
  2%|▏         | 23/1133 [00:35<23:05,  1.25s/it]
  2%|▏         | 24/1133 [00:35<20:07,  1.09s/it]
  2%|▏         | 25/1133 [00:37<22:59,  1.24s/it]
  2%|▏         | 26/1133 [00:40<29:57,  1.62s/it]
  2%|▏         | 27/1133 [00:40<25:48,  1.40s/it]
  2%|▏         | 28/1133 [00:41<20:13,  1.10s/it]
  3%|▎         | 29/1133 [00:42<18:27,  1.00s/it]
  3%|▎         | 30/1133 [00:42<15:03,  1.22it/s]
  3%|▎         | 31/1133 [00:42<11:48,  1.55it/s]
  3%|▎         | 32/1133 [00:44<19:00,  1.04s/it]
  3%|▎         | 33/1133 [00:47<30:10,  1.65s/it]
  3%|▎         | 34/1133 [00:49<30:50,  1.68s/it]
  3%|▎         | 35/1133 [00:50<27:35,  1.51s/it]
  3%|▎         | 36/1133 [00:51<24:14,  1.33s/it]
  3%|▎         | 37/1133 [00:52<20:36,  1.13s/it]
  3%|▎         | 38/1133 [00:52<17:37,  1.04it/s]
  3%|▎         | 39/1133 [00:52<13:49,  1.32it/s]
  4%|▎         | 40/1133 [00:54<19:29,  1.07s/it]
  4%|▎         | 41/1133 [00:58<31:12,  1.72s/it]
  4%|▎         | 42/1133 [00:58<24:10,  1.33s/it]
  4%|▍         | 43/1133 [00:59<22:54,  1.26s/it]
  4%|▍         | 44/1133 [01:00<20:46,  1.14s/it]
  4%|▍         | 45/1133 [01:00<16:26,  1.10it/s]
  4%|▍         | 46/1133 [01:03<27:11,  1.50s/it]
  4%|▍         | 47/1133 [01:04<25:06,  1.39s/it]
  4%|▍         | 48/1133 [01:05<19:28,  1.08s/it]
  4%|▍         | 49/1133 [01:05<17:00,  1.06it/s]
  4%|▍         | 50/1133 [01:06<15:04,  1.20it/s]
  5%|▍         | 51/1133 [01:07<16:14,  1.11it/s]
  5%|▍         | 52/1133 [01:09<20:14,  1.12s/it]
  5%|▍         | 53/1133 [01:10<19:29,  1.08s/it]
  5%|▍         | 54/1133 [01:10<15:06,  1.19it/s]
  5%|▍         | 55/1133 [01:13<26:56,  1.50s/it]
  5%|▍         | 56/1133 [01:14<24:42,  1.38s/it]
  5%|▌         | 57/1133 [01:16<27:42,  1.55s/it]
  5%|▌         | 58/1133 [01:17<26:56,  1.50s/it]
  5%|▌         | 59/1133 [01:18<20:18,  1.13s/it]
  5%|▌         | 60/1133 [01:19<22:53,  1.28s/it]
  5%|▌         | 61/1133 [01:20<18:45,  1.05s/it]
  5%|▌         | 62/1133 [01:20<16:03,  1.11it/s]
  6%|▌         | 63/1133 [01:22<18:47,  1.05s/it]
  6%|▌         | 64/1133 [01:23<18:21,  1.03s/it]
  6%|▌         | 65/1133 [01:23<17:08,  1.04it/s]
  6%|▌         | 66/1133 [01:24<17:15,  1.03it/s]
  6%|▌         | 67/1133 [01:27<23:12,  1.31s/it]
  6%|▌         | 68/1133 [01:29<29:21,  1.65s/it]
  6%|▌         | 69/1133 [01:31<31:14,  1.76s/it]
  6%|▌         | 70/1133 [01:32<27:46,  1.57s/it]
  6%|▋         | 71/1133 [01:32<20:52,  1.18s/it]
  6%|▋         | 72/1133 [01:33<17:30,  1.01it/s]
  6%|▋         | 73/1133 [01:33<14:43,  1.20it/s]
  7%|▋         | 74/1133 [01:34<12:09,  1.45it/s]
  7%|▋         | 75/1133 [01:34<11:36,  1.52it/s]
  7%|▋         | 76/1133 [01:35<12:41,  1.39it/s]
  7%|▋         | 77/1133 [01:37<15:57,  1.10it/s]
  7%|▋         | 78/1133 [01:37<13:37,  1.29it/s]
  7%|▋         | 79/1133 [01:39<17:50,  1.02s/it]
  7%|▋         | 80/1133 [01:39<15:21,  1.14it/s]
  7%|▋         | 81/1133 [01:40<13:00,  1.35it/s]
  7%|▋         | 82/1133 [01:40<11:21,  1.54it/s]
  7%|▋         | 83/1133 [01:43<24:03,  1.37s/it]
  7%|▋         | 84/1133 [01:43<17:51,  1.02s/it]
  8%|▊         | 85/1133 [01:44<14:32,  1.20it/s]
  8%|▊         | 86/1133 [01:44<14:15,  1.22it/s]
  8%|▊         | 87/1133 [01:45<14:19,  1.22it/s]
  8%|▊         | 88/1133 [01:47<17:49,  1.02s/it]
  8%|▊         | 89/1133 [01:47<15:19,  1.14it/s]
  8%|▊         | 90/1133 [01:49<20:00,  1.15s/it]
  8%|▊         | 91/1133 [01:50<17:04,  1.02it/s]
  8%|▊         | 92/1133 [01:50<15:12,  1.14it/s]
  8%|▊         | 93/1133 [01:52<17:18,  1.00it/s]
  8%|▊         | 94/1133 [01:52<15:46,  1.10it/s]
  8%|▊         | 95/1133 [01:53<17:00,  1.02it/s]
  8%|▊         | 96/1133 [01:55<21:32,  1.25s/it]
  9%|▊         | 97/1133 [01:56<18:06,  1.05s/it]
  9%|▊         | 98/1133 [01:57<16:18,  1.06it/s]
  9%|▊         | 99/1133 [01:58<16:56,  1.02it/s]
  9%|▉         | 100/1133 [01:58<13:15,  1.30it/s]
  9%|▉         | 101/1133 [02:00<21:12,  1.23s/it]
  9%|▉         | 102/1133 [02:02<23:41,  1.38s/it]
  9%|▉         | 103/1133 [02:03<19:48,  1.15s/it]
  9%|▉         | 104/1133 [02:03<15:03,  1.14it/s]
  9%|▉         | 105/1133 [02:04<18:13,  1.06s/it]
  9%|▉         | 106/1133 [02:10<39:22,  2.30s/it]
  9%|▉         | 107/1133 [02:12<38:04,  2.23s/it]
 10%|▉         | 108/1133 [02:13<31:29,  1.84s/it]
 10%|▉         | 109/1133 [02:14<28:18,  1.66s/it]
 10%|▉         | 110/1133 [02:16<32:37,  1.91s/it]
 10%|▉         | 111/1133 [02:18<31:36,  1.86s/it]
 10%|▉         | 112/1133 [02:22<40:29,  2.38s/it]
 10%|▉         | 113/1133 [02:25<45:54,  2.70s/it]
 10%|█         | 114/1133 [02:26<35:54,  2.11s/it]
 10%|█         | 115/1133 [02:26<27:29,  1.62s/it]
 10%|█         | 116/1133 [02:27<22:24,  1.32s/it]
 10%|█         | 117/1133 [02:29<25:29,  1.51s/it]
 10%|█         | 118/1133 [02:29<21:12,  1.25s/it]
 11%|█         | 119/1133 [02:31<22:29,  1.33s/it]
 11%|█         | 120/1133 [02:31<18:06,  1.07s/it]
 11%|█         | 121/1133 [02:32<15:49,  1.07it/s]
 11%|█         | 122/1133 [02:33<15:02,  1.12it/s]
 11%|█         | 123/1133 [02:33<12:29,  1.35it/s]
 11%|█         | 124/1133 [02:34<14:29,  1.16it/s]
 11%|█         | 125/1133 [02:36<19:42,  1.17s/it]
 11%|█         | 126/1133 [02:37<19:05,  1.14s/it]
 11%|█         | 127/1133 [02:40<26:39,  1.59s/it]
 11%|█▏        | 128/1133 [02:41<22:11,  1.32s/it]
 11%|█▏        | 129/1133 [02:41<19:27,  1.16s/it]
 11%|█▏        | 130/1133 [02:42<14:58,  1.12it/s]
 12%|█▏        | 131/1133 [02:44<21:23,  1.28s/it]
 12%|█▏        | 132/1133 [02:45<19:50,  1.19s/it]
 12%|█▏        | 133/1133 [02:46<17:35,  1.06s/it]
 12%|█▏        | 134/1133 [02:46<14:39,  1.14it/s]
 12%|█▏        | 135/1133 [02:50<29:22,  1.77s/it]
 12%|█▏        | 136/1133 [02:51<24:50,  1.49s/it]
 12%|█▏        | 137/1133 [02:52<23:08,  1.39s/it]
 12%|█▏        | 138/1133 [02:52<18:42,  1.13s/it]
 12%|█▏        | 139/1133 [02:53<16:00,  1.04it/s]
 12%|█▏        | 140/1133 [02:55<18:31,  1.12s/it]
 12%|█▏        | 141/1133 [02:55<16:03,  1.03it/s]
 13%|█▎        | 142/1133 [02:56<13:56,  1.19it/s]
 13%|█▎        | 143/1133 [02:57<17:50,  1.08s/it]
 13%|█▎        | 144/1133 [02:58<15:22,  1.07it/s]
 13%|█▎        | 145/1133 [02:58<13:04,  1.26it/s]
 13%|█▎        | 146/1133 [02:59<12:48,  1.28it/s]
 13%|█▎        | 147/1133 [03:00<13:18,  1.24it/s]
 13%|█▎        | 148/1133 [03:00<10:50,  1.51it/s]
 13%|█▎        | 149/1133 [03:01<12:01,  1.36it/s]
 13%|█▎        | 150/1133 [03:02<10:31,  1.56it/s]
 13%|█▎        | 151/1133 [03:03<15:00,  1.09it/s]
 13%|█▎        | 152/1133 [03:04<15:26,  1.06it/s]
 14%|█▎        | 153/1133 [03:05<12:42,  1.29it/s]
 14%|█▎        | 154/1133 [03:06<17:27,  1.07s/it]
 14%|█▎        | 155/1133 [03:08<18:18,  1.12s/it]
 14%|█▍        | 156/1133 [03:09<19:40,  1.21s/it]
 14%|█▍        | 157/1133 [03:11<22:55,  1.41s/it]
 14%|█▍        | 158/1133 [03:12<22:01,  1.36s/it]
 14%|█▍        | 159/1133 [03:12<16:44,  1.03s/it]
 14%|█▍        | 160/1133 [03:13<15:30,  1.05it/s]
 14%|█▍        | 161/1133 [03:13<11:59,  1.35it/s]
 14%|█▍        | 162/1133 [03:14<12:45,  1.27it/s]
 14%|█▍        | 163/1133 [03:16<15:02,  1.07it/s]
 14%|█▍        | 164/1133 [03:16<12:47,  1.26it/s]
 15%|█▍        | 165/1133 [03:17<12:33,  1.28it/s]
 15%|█▍        | 166/1133 [03:18<15:10,  1.06it/s]
 15%|█▍        | 167/1133 [03:19<15:03,  1.07it/s]
 15%|█▍        | 168/1133 [03:20<15:40,  1.03it/s]
 15%|█▍        | 169/1133 [03:21<13:58,  1.15it/s]
 15%|█▌        | 170/1133 [03:21<13:10,  1.22it/s]
 15%|█▌        | 171/1133 [03:22<10:42,  1.50it/s]
 15%|█▌        | 172/1133 [03:22<08:59,  1.78it/s]
 15%|█▌        | 173/1133 [03:23<09:28,  1.69it/s]
 15%|█▌        | 174/1133 [03:23<08:18,  1.92it/s]
 15%|█▌        | 175/1133 [03:24<10:05,  1.58it/s]
 16%|█▌        | 176/1133 [03:24<09:17,  1.72it/s]
 16%|█▌        | 177/1133 [03:25<10:59,  1.45it/s]
 16%|█▌        | 178/1133 [03:28<21:25,  1.35s/it]
 16%|█▌        | 179/1133 [03:29<18:43,  1.18s/it]
 16%|█▌        | 180/1133 [03:31<21:34,  1.36s/it]
 16%|█▌        | 181/1133 [03:32<19:12,  1.21s/it]
 16%|█▌        | 182/1133 [03:34<25:21,  1.60s/it]
 16%|█▌        | 183/1133 [03:35<22:25,  1.42s/it]
 16%|█▌        | 184/1133 [03:36<19:23,  1.23s/it]
 16%|█▋        | 185/1133 [03:36<15:46,  1.00it/s]
 16%|█▋        | 186/1133 [03:37<13:48,  1.14it/s]
 17%|█▋        | 187/1133 [03:40<21:25,  1.36s/it]
 17%|█▋        | 188/1133 [03:43<29:44,  1.89s/it]
 17%|█▋        | 189/1133 [03:43<23:45,  1.51s/it]
 17%|█▋        | 190/1133 [03:45<23:24,  1.49s/it]
 17%|█▋        | 191/1133 [03:46<21:22,  1.36s/it]
 17%|█▋        | 192/1133 [03:47<18:58,  1.21s/it]
 17%|█▋        | 193/1133 [03:48<20:44,  1.32s/it]
 17%|█▋        | 194/1133 [03:49<17:48,  1.14s/it]
 17%|█▋        | 195/1133 [03:49<14:17,  1.09it/s]
 17%|█▋        | 196/1133 [03:50<11:27,  1.36it/s]
 17%|█▋        | 197/1133 [03:51<14:55,  1.05it/s]
 17%|█▋        | 198/1133 [03:52<12:59,  1.20it/s]
 18%|█▊        | 199/1133 [03:54<19:41,  1.27s/it]
 18%|█▊        | 200/1133 [03:54<14:30,  1.07it/s]
 18%|█▊        | 201/1133 [03:55<13:56,  1.11it/s]
 18%|█▊        | 202/1133 [03:55<10:50,  1.43it/s]
 18%|█▊        | 203/1133 [03:56<09:13,  1.68it/s]
 18%|█▊        | 204/1133 [03:58<17:16,  1.12s/it]
 18%|█▊        | 205/1133 [03:58<13:11,  1.17it/s]
 18%|█▊        | 206/1133 [03:59<12:17,  1.26it/s]
 18%|█▊        | 207/1133 [04:00<13:20,  1.16it/s]
 18%|█▊        | 208/1133 [04:02<17:26,  1.13s/it]
 18%|█▊        | 209/1133 [04:06<31:09,  2.02s/it]
 19%|█▊        | 210/1133 [04:07<29:16,  1.90s/it]
 19%|█▊        | 211/1133 [04:09<28:53,  1.88s/it]
 19%|█▊        | 212/1133 [04:11<29:02,  1.89s/it]
 19%|█▉        | 213/1133 [04:12<23:43,  1.55s/it]
 19%|█▉        | 214/1133 [04:12<17:50,  1.16s/it]
 19%|█▉        | 215/1133 [04:13<15:53,  1.04s/it]
 19%|█▉        | 216/1133 [04:16<26:16,  1.72s/it]
 19%|█▉        | 217/1133 [04:16<19:38,  1.29s/it]
 19%|█▉        | 218/1133 [04:17<16:34,  1.09s/it]
 19%|█▉        | 219/1133 [04:18<14:04,  1.08it/s]
 19%|█▉        | 220/1133 [04:19<15:00,  1.01it/s]
 20%|█▉        | 221/1133 [04:22<27:39,  1.82s/it]
 20%|█▉        | 222/1133 [04:23<23:16,  1.53s/it]
 20%|█▉        | 223/1133 [04:25<26:14,  1.73s/it]
 20%|█▉        | 224/1133 [04:26<20:39,  1.36s/it]
 20%|█▉        | 225/1133 [04:27<18:00,  1.19s/it]
 20%|█▉        | 226/1133 [04:31<31:16,  2.07s/it]
 20%|██        | 227/1133 [04:32<26:54,  1.78s/it]
 20%|██        | 228/1133 [04:33<23:07,  1.53s/it]
 20%|██        | 229/1133 [04:35<27:18,  1.81s/it]
 20%|██        | 230/1133 [04:37<26:2