Buckets:
| { | |
| "train": { | |
| "pairs": 26925, | |
| "labels": { | |
| "not_applicable": 8932, | |
| "followed": 8959, | |
| "violated": 9034 | |
| } | |
| }, | |
| "validation": { | |
| "pairs": 3075, | |
| "labels": { | |
| "not_applicable": 1068, | |
| "violated": 966, | |
| "followed": 1041 | |
| } | |
| }, | |
| "test_ood": { | |
| "pairs": 7023, | |
| "labels": { | |
| "followed": 1805, | |
| "not_applicable": 5104, | |
| "violated": 114 | |
| } | |
| } | |
| } | |
| `torch_dtype` is deprecated! Use `dtype` instead! | |
| Some weights of ModernBertForSequenceClassification were not initialized from the model checkpoint at answerdotai/ModernBERT-large and are newly initialized: ['classifier.bias', 'classifier.weight'] | |
| You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. | |
| trainable params: 15,446,019 || all params: 411,280,390 || trainable%: 3.7556 | |
| Map: 0%| | 0/26925 [00:00<?, ? examples/s] Map: 4%|▎ | 1000/26925 [00:00<00:19, 1357.45 examples/s] Map: 7%|▋ | 2000/26925 [00:00<00:10, 2336.62 examples/s] Map: 11%|█ | 3000/26925 [00:01<00:07, 3299.13 examples/s] Map: 15%|█▍ | 4000/26925 [00:01<00:08, 2736.36 examples/s] Map: 19%|█▊ | 5000/26925 [00:01<00:06, 3538.29 examples/s] Map: 22%|██▏ | 6000/26925 [00:01<00:04, 4318.76 examples/s] Map: 26%|██▌ | 7000/26925 [00:01<00:03, 5091.71 examples/s] Map: 30%|██▉ | 8000/26925 [00:02<00:03, 5745.57 examples/s] Map: 33%|███▎ | 9000/26925 [00:02<00:02, 6308.43 examples/s] Map: 37%|███▋ | 10000/26925 [00:02<00:02, 6752.08 examples/s] Map: 41%|████ | 11000/26925 [00:02<00:03, 5018.35 examples/s] Map: 45%|████▍ | 12000/26925 [00:02<00:02, 5657.66 examples/s] Map: 48%|████▊ | 13000/26925 [00:02<00:02, 6158.48 examples/s] Map: 52%|█████▏ | 14000/26925 [00:03<00:01, 6628.59 examples/s] Map: 56%|█████▌ | 15000/26925 [00:03<00:01, 7043.05 examples/s] Map: 59%|█████▉ | 16000/26925 [00:03<00:01, 7320.21 examples/s] Map: 63%|██████▎ | 17000/26925 [00:03<00:01, 7550.45 examples/s] Map: 67%|██████▋ | 18000/26925 [00:03<00:01, 7774.36 examples/s] Map: 71%|███████ | 19000/26925 [00:03<00:00, 7928.63 examples/s] Map: 74%|███████▍ | 20000/26925 [00:03<00:00, 7996.07 examples/s] Map: 78%|███████▊ | 21000/26925 [00:03<00:00, 8056.43 examples/s] Map: 82%|████████▏ | 22000/26925 [00:03<00:00, 8118.78 examples/s] Map: 85%|████████▌ | 23000/26925 [00:04<00:00, 8073.79 examples/s] Map: 89%|████████▉ | 24000/26925 [00:04<00:00, 8125.68 examples/s] Map: 93%|█████████▎| 25000/26925 [00:04<00:00, 8162.54 examples/s] Map: 97%|█████████▋| 26000/26925 [00:04<00:00, 8178.97 examples/s] Map: 100%|██████████| 26925/26925 [00:04<00:00, 7998.99 examples/s] Map: 100%|██████████| 26925/26925 [00:04<00:00, 5833.23 examples/s] | |
| Map: 0%| | 0/3075 [00:00<?, ? examples/s] Map: 33%|███▎ | 1000/3075 [00:00<00:00, 6050.70 examples/s] Map: 65%|██████▌ | 2000/3075 [00:00<00:00, 7245.09 examples/s] Map: 98%|█████████▊| 3000/3075 [00:00<00:00, 7748.73 examples/s] Map: 100%|██████████| 3075/3075 [00:00<00:00, 7363.10 examples/s] | |
| Map: 0%| | 0/7023 [00:00<?, ? examples/s] Map: 14%|█▍ | 1000/7023 [00:00<00:01, 5198.39 examples/s] Map: 28%|██▊ | 2000/7023 [00:00<00:00, 6561.49 examples/s] Map: 43%|████▎ | 3000/7023 [00:00<00:00, 7400.28 examples/s] Map: 57%|█████▋ | 4000/7023 [00:00<00:00, 7741.35 examples/s] Map: 85%|████████▌ | 6000/7023 [00:00<00:00, 8642.52 examples/s] Map: 100%|█████████▉| 7000/7023 [00:00<00:00, 8564.27 examples/s] Map: 100%|██████████| 7023/7023 [00:00<00:00, 7917.78 examples/s] | |
| wandb: [wandb.login()] Loaded credentials for https://api.forge.coreweave.com from /root/.netrc. | |
| wandb: Currently logged in as: mrishikesh104 (storm-dpo) to https://api.forge.coreweave.com. Use `wandb login --relogin` to force relogin | |
| wandb: Tracking run with wandb version 0.31.0 | |
| wandb: Run data is saved locally in /workspace/wandb/run-20261105_094103-zj70dexz | |
| wandb: Run `wandb offline` to turn off syncing. | |
| wandb: Syncing run modernbert-large-30k | |
| wandb: ⭐️ View project at https://forge.coreweave.com/wandb/storm-dpo/policy-classifier | |
| wandb: 🚀 View run at https://forge.coreweave.com/wandb/storm-dpo/policy-classifier/runs/zj70dexz | |
| The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'eos_token_id': None, 'bos_token_id': None}. | |
| 0%| | 0/632 [00:00<?, ?it/s] 0%| | 1/632 [00:01<20:42, 1.97s/it] 0%| | 2/632 [00:02<13:53, 1.32s/it] 0%| | 3/632 [00:03<11:26, 1.09s/it] 1%| | 4/632 [00:04<09:04, 1.15it/s] 1%| | 5/632 [00:04<07:49, 1.34it/s] 1%| | 6/632 [00:05<08:37, 1.21it/s] 1%| | 7/632 [00:06<07:43, 1.35it/s] 1%|▏ | 8/632 [00:06<07:23, 1.41it/s] 1%|▏ | 9/632 [00:07<07:10, 1.45it/s] 2%|▏ | 10/632 [00:08<06:39, 1.56it/s] {'loss': 4.65, 'grad_norm': 19.24226951599121, 'learning_rate': 5.6250000000000005e-05, 'epoch': 0.02} | |
| 2%|▏ | 10/632 [00:08<06:39, 1.56it/s] 2%|▏ | 11/632 [00:08<06:41, 1.55it/s] 2%|▏ | 12/632 [00:09<06:36, 1.56it/s] 2%|▏ | 13/632 [00:10<07:12, 1.43it/s] 2%|▏ | 14/632 [00:10<06:28, 1.59it/s] 2%|▏ | 15/632 [00:11<06:16, 1.64it/s] 3%|▎ | 16/632 [00:11<06:07, 1.68it/s] 3%|▎ | 17/632 [00:12<06:41, 1.53it/s] 3%|▎ | 18/632 [00:13<06:35, 1.55it/s] 3%|▎ | 19/632 [00:13<06:34, 1.55it/s] 3%|▎ | 20/632 [00:14<06:19, 1.61it/s] {'loss': 4.5045, 'grad_norm': 13.50594711303711, 'learning_rate': 0.00011875, 'epoch': 0.05} | |
| 3%|▎ | 20/632 [00:14<06:19, 1.61it/s] 3%|▎ | 21/632 [00:14<06:06, 1.67it/s] 3%|▎ | 22/632 [00:15<06:07, 1.66it/s] 4%|▎ | 23/632 [00:16<05:56, 1.71it/s] 4%|▍ | 24/632 [00:16<06:15, 1.62it/s] 4%|▍ | 25/632 [00:17<06:15, 1.62it/s] 4%|▍ | 26/632 [00:17<06:02, 1.67it/s] 4%|▍ | 27/632 [00:18<06:01, 1.67it/s] 4%|▍ | 28/632 [00:19<06:00, 1.68it/s] 5%|▍ | 29/632 [00:19<05:48, 1.73it/s] 5%|▍ | 30/632 [00:20<05:51, 1.71it/s] {'loss': 4.2278, 'grad_norm': 14.195234298706055, 'learning_rate': 0.00018125000000000001, 'epoch': 0.07} | |
| 5%|▍ | 30/632 [00:20<05:51, 1.71it/s] 5%|▍ | 31/632 [00:20<05:52, 1.71it/s] 5%|▌ | 32/632 [00:21<06:18, 1.59it/s] 5%|▌ | 33/632 [00:22<06:01, 1.66it/s] 5%|▌ | 34/632 [00:22<06:10, 1.62it/s] 6%|▌ | 35/632 [00:23<06:07, 1.62it/s] 6%|▌ | 36/632 [00:23<05:43, 1.74it/s] 6%|▌ | 37/632 [00:24<06:01, 1.65it/s] 6%|▌ | 38/632 [00:25<05:42, 1.73it/s] 6%|▌ | 39/632 [00:25<05:46, 1.71it/s] 6%|▋ | 40/632 [00:26<05:29, 1.80it/s] {'loss': 3.9067, 'grad_norm': 15.036209106445312, 'learning_rate': 0.00019766666666666666, 'epoch': 0.1} | |
| 6%|▋ | 40/632 [00:26<05:29, 1.80it/s] 6%|▋ | 41/632 [00:26<05:41, 1.73it/s] 7%|▋ | 42/632 [00:27<05:30, 1.78it/s] 7%|▋ | 43/632 [00:27<05:28, 1.79it/s] 7%|▋ | 44/632 [00:28<05:10, 1.89it/s] 7%|▋ | 45/632 [00:28<04:54, 1.99it/s] 7%|▋ | 46/632 [00:29<04:58, 1.97it/s] 7%|▋ | 47/632 [00:29<05:19, 1.83it/s] 8%|▊ | 48/632 [00:30<05:25, 1.80it/s] 8%|▊ | 49/632 [00:31<05:27, 1.78it/s] 8%|▊ | 50/632 [00:31<05:58, 1.62it/s] {'loss': 4.0938, 'grad_norm': 26.781375885009766, 'learning_rate': 0.00019433333333333333, 'epoch': 0.12} | |
| 8%|▊ | 50/632 [00:31<05:58, 1.62it/s] 8%|▊ | 51/632 [00:32<05:50, 1.66it/s] 8%|▊ | 52/632 [00:32<05:28, 1.76it/s] 8%|▊ | 53/632 [00:33<05:32, 1.74it/s] 9%|▊ | 54/632 [00:33<05:15, 1.83it/s] 9%|▊ | 55/632 [00:34<05:51, 1.64it/s] 9%|▉ | 56/632 [00:35<05:26, 1.76it/s] 9%|▉ | 57/632 [00:35<05:48, 1.65it/s] 9%|▉ | 58/632 [00:36<05:58, 1.60it/s] 9%|▉ | 59/632 [00:37<05:32, 1.73it/s] 9%|▉ | 60/632 [00:37<05:18, 1.79it/s] {'loss': 3.4711, 'grad_norm': 17.541261672973633, 'learning_rate': 0.000191, 'epoch': 0.14} | |
| 9%|▉ | 60/632 [00:37<05:18, 1.79it/s] 10%|▉ | 61/632 [00:38<05:40, 1.68it/s] 10%|▉ | 62/632 [00:38<05:16, 1.80it/s] 10%|▉ | 63/632 [00:39<05:11, 1.83it/s] 10%|█ | 64/632 [00:39<04:54, 1.93it/s] 10%|█ | 65/632 [00:40<05:20, 1.77it/s] 10%|█ | 66/632 [00:40<05:19, 1.77it/s] 11%|█ | 67/632 [00:41<05:16, 1.79it/s] 11%|█ | 68/632 [00:41<05:06, 1.84it/s] 11%|█ | 69/632 [00:42<04:51, 1.93it/s] 11%|█ | 70/632 [00:42<04:48, 1.95it/s] {'loss': 3.3067, 'grad_norm': 9.352126121520996, 'learning_rate': 0.00018766666666666668, 'epoch': 0.17} | |
| 11%|█ | 70/632 [00:42<04:48, 1.95it/s] 11%|█ | 71/632 [00:43<04:54, 1.91it/s] 11%|█▏ | 72/632 [00:44<05:31, 1.69it/s] 12%|█▏ | 73/632 [00:45<06:07, 1.52it/s] 12%|█▏ | 74/632 [00:45<05:51, 1.59it/s] 12%|█▏ | 75/632 [00:46<05:43, 1.62it/s] 12%|█▏ | 76/632 [00:46<05:35, 1.66it/s] 12%|█▏ | 77/632 [00:47<05:17, 1.75it/s] 12%|█▏ | 78/632 [00:47<05:24, 1.71it/s] 12%|█▎ | 79/632 [00:48<05:30, 1.67it/s] 13%|█▎ | 80/632 [00:49<05:34, 1.65it/s] {'loss': 3.1509, 'grad_norm': 7.357174873352051, 'learning_rate': 0.00018433333333333333, 'epoch': 0.19} | |
| 13%|█▎ | 80/632 [00:49<05:34, 1.65it/s] 13%|█▎ | 81/632 [00:49<05:25, 1.69it/s] 13%|█▎ | 82/632 [00:50<05:07, 1.79it/s] 13%|█▎ | 83/632 [00:50<04:45, 1.92it/s] 13%|█▎ | 84/632 [00:51<05:10, 1.77it/s] 13%|█▎ | 85/632 [00:51<05:07, 1.78it/s] 14%|█▎ | 86/632 [00:52<05:08, 1.77it/s] 14%|█▍ | 87/632 [00:52<04:57, 1.83it/s] 14%|█▍ | 88/632 [00:53<05:02, 1.80it/s] 14%|█▍ | 89/632 [00:54<05:01, 1.80it/s] 14%|█▍ | 90/632 [00:54<05:14, 1.73it/s] {'loss': 3.2024, 'grad_norm': 11.681929588317871, 'learning_rate': 0.000181, 'epoch': 0.21} | |
| 14%|█▍ | 90/632 [00:54<05:14, 1.73it/s] 14%|█▍ | 91/632 [00:55<05:08, 1.75it/s] 15%|█▍ | 92/632 [00:55<05:31, 1.63it/s] 15%|█▍ | 93/632 [00:56<05:15, 1.71it/s] 15%|█▍ | 94/632 [00:56<05:02, 1.78it/s] 15%|█▌ | 95/632 [00:57<04:54, 1.83it/s] 15%|█▌ | 96/632 [00:58<04:56, 1.81it/s] 15%|█▌ | 97/632 [00:58<04:54, 1.81it/s] 16%|█▌ | 98/632 [00:59<04:58, 1.79it/s] 16%|█▌ | 99/632 [00:59<04:57, 1.79it/s] 16%|█▌ | 100/632 [01:00<05:01, 1.76it/s] {'loss': 2.9151, 'grad_norm': 18.67310333251953, 'learning_rate': 0.00017766666666666666, 'epoch': 0.24} | |
| 16%|█▌ | 100/632 [01:00<05:01, 1.76it/s] 16%|█▌ | 101/632 [01:00<05:02, 1.76it/s] 16%|█▌ | 102/632 [01:01<04:53, 1.81it/s] 16%|█▋ | 103/632 [01:02<05:24, 1.63it/s] 16%|█▋ | 104/632 [01:02<05:00, 1.76it/s] 17%|█▋ | 105/632 [01:03<05:02, 1.74it/s] 17%|█▋ | 106/632 [01:03<05:01, 1.74it/s] 17%|█▋ | 107/632 [01:04<05:06, 1.72it/s] 17%|█▋ | 108/632 [01:04<04:54, 1.78it/s] 17%|█▋ | 109/632 [01:05<04:44, 1.84it/s] 17%|█▋ | 110/632 [01:05<04:32, 1.92it/s] {'loss': 2.9938, 'grad_norm': 10.014092445373535, 'learning_rate': 0.00017433333333333336, 'epoch': 0.26} | |
| 17%|█▋ | 110/632 [01:05<04:32, 1.92it/s] 18%|█▊ | 111/632 [01:06<04:36, 1.88it/s] 18%|█▊ | 112/632 [01:06<04:29, 1.93it/s] 18%|█▊ | 113/632 [01:07<04:23, 1.97it/s] 18%|█▊ | 114/632 [01:07<04:14, 2.04it/s] 18%|█▊ | 115/632 [01:08<04:22, 1.97it/s] 18%|█▊ | 116/632 [01:09<04:52, 1.77it/s] 19%|█▊ | 117/632 [01:09<04:41, 1.83it/s] 19%|█▊ | 118/632 [01:10<04:41, 1.83it/s] 19%|█▉ | 119/632 [01:11<05:30, 1.55it/s] 19%|█▉ | 120/632 [01:11<04:57, 1.72it/s] {'loss': 2.7431, 'grad_norm': 13.882220268249512, 'learning_rate': 0.000171, 'epoch': 0.29} | |
| 19%|█▉ | 120/632 [01:11<04:57, 1.72it/s] 19%|█▉ | 121/632 [01:12<05:06, 1.67it/s] 19%|█▉ | 122/632 [01:12<05:19, 1.60it/s] 19%|█▉ | 123/632 [01:13<04:56, 1.72it/s] 20%|█▉ | 124/632 [01:14<05:24, 1.57it/s] 20%|█▉ | 125/632 [01:14<04:55, 1.71it/s] 20%|█▉ | 126/632 [01:15<04:47, 1.76it/s] 20%|██ | 127/632 [01:15<05:12, 1.62it/s] 20%|██ | 128/632 [01:16<05:05, 1.65it/s] 20%|██ | 129/632 [01:16<04:55, 1.70it/s] 21%|██ | 130/632 [01:17<04:44, 1.76it/s] {'loss': 2.7446, 'grad_norm': 9.795037269592285, 'learning_rate': 0.00016766666666666669, 'epoch': 0.31} | |
| 21%|██ | 130/632 [01:17<04:44, 1.76it/s] 21%|██ | 131/632 [01:18<04:53, 1.71it/s] 21%|██ | 132/632 [01:18<04:51, 1.71it/s] 21%|██ | 133/632 [01:19<04:34, 1.82it/s] 21%|██ | 134/632 [01:19<04:32, 1.83it/s] 21%|██▏ | 135/632 [01:20<04:36, 1.79it/s] 22%|██▏ | 136/632 [01:20<04:40, 1.77it/s] 22%|██▏ | 137/632 [01:21<04:42, 1.75it/s] 22%|██▏ | 138/632 [01:22<04:56, 1.67it/s] 22%|██▏ | 139/632 [01:22<04:32, 1.81it/s] 22%|██▏ | 140/632 [01:22<04:24, 1.86it/s] {'loss': 2.3106, 'grad_norm': 6.634688854217529, 'learning_rate': 0.00016433333333333333, 'epoch': 0.33} | |
| 22%|██▏ | 140/632 [01:22<04:24, 1.86it/s] 22%|██▏ | 141/632 [01:23<04:12, 1.94it/s] 22%|██▏ | 142/632 [01:23<04:09, 1.96it/s] 23%|██▎ | 143/632 [01:24<04:08, 1.97it/s] 23%|██▎ | 144/632 [01:25<04:19, 1.88it/s] 23%|██▎ | 145/632 [01:25<04:36, 1.76it/s] 23%|██▎ | 146/632 [01:26<04:44, 1.71it/s] 23%|██▎ | 147/632 [01:26<04:45, 1.70it/s] 23%|██▎ | 148/632 [01:27<04:37, 1.75it/s] 24%|██▎ | 149/632 [01:27<04:26, 1.81it/s] 24%|██▎ | 150/632 [01:28<04:27, 1.80it/s] {'loss': 2.4578, 'grad_norm': 8.5284423828125, 'learning_rate': 0.000161, 'epoch': 0.36} | |
| 24%|██▎ | 150/632 [01:28<04:27, 1.80it/s] 24%|██▍ | 151/632 [01:29<04:48, 1.67it/s] 24%|██▍ | 152/632 [01:29<04:34, 1.75it/s] 24%|██▍ | 153/632 [01:30<04:30, 1.77it/s] 24%|██▍ | 154/632 [01:30<04:17, 1.86it/s] 25%|██▍ | 155/632 [01:31<04:15, 1.87it/s] 25%|██▍ | 156/632 [01:31<04:06, 1.93it/s] 25%|██▍ | 157/632 [01:32<04:39, 1.70it/s]Saved adapter checkpoint checkpoints/modernbert-large-30k/checkpoint-1of4-step158 | |
| 25%|██▌ | 158/632 [01:33<05:54, 1.34it/s] | |
| 0%| | 0/193 [00:00<?, ?it/s][A | |
| 1%| | 2/193 [00:00<00:25, 7.53it/s][A | |
| 2%|▏ | 3/193 [00:00<00:26, 7.26it/s][A | |
| 3%|▎ | 5/193 [00:00<00:18, 10.36it/s][A | |
| 4%|▎ | 7/193 [00:00<00:15, 11.97it/s][A | |
| 5%|▍ | 9/193 [00:00<00:16, 11.24it/s][A | |
| 6%|▌ | 11/193 [00:00<00:13, 13.24it/s][A | |
| 7%|▋ | 13/193 [00:01<00:15, 11.35it/s][A | |
| 8%|▊ | 15/193 [00:01<00:15, 11.73it/s][A | |
| 9%|▉ | 17/193 [00:01<00:14, 12.27it/s][A | |
| 10%|▉ | 19/193 [00:01<00:15, 10.98it/s][A | |
| 11%|█ | 21/193 [00:01<00:14, 11.74it/s][A | |
| 12%|█▏ | 23/193 [00:01<00:13, 12.59it/s][A | |
| 13%|█▎ | 25/193 [00:02<00:13, 12.09it/s][A | |
| 14%|█▍ | 27/193 [00:02<00:14, 11.64it/s][A | |
| 15%|█▌ | 29/193 [00:02<00:13, 12.20it/s][A | |
| 16%|█▌ | 31/193 [00:02<00:13, 12.29it/s][A | |
| 17%|█▋ | 33/193 [00:02<00:13, 11.54it/s][A | |
| 18%|█▊ | 35/193 [00:02<00:12, 12.59it/s][A | |
| 19%|█▉ | 37/193 [00:03<00:12, 12.11it/s][A | |
| 20%|██ | 39/193 [00:03<00:13, 11.70it/s][A | |
| 21%|██ | 41/193 [00:03<00:12, 11.70it/s][A | |
| 22%|██▏ | 43/193 [00:03<00:12, 12.38it/s][A | |
| 23%|██▎ | 45/193 [00:03<00:12, 11.71it/s][A | |
| 24%|██▍ | 47/193 [00:04<00:12, 11.92it/s][A | |
| 25%|██▌ | 49/193 [00:04<00:11, 12.20it/s][A | |
| 26%|██▋ | 51/193 [00:04<00:12, 11.15it/s][A | |
| 27%|██▋ | 53/193 [00:04<00:12, 11.33it/s][A | |
| 28%|██▊ | 55/193 [00:04<00:11, 12.00it/s][A | |
| 30%|██▉ | 57/193 [00:04<00:11, 12.12it/s][A | |
| 31%|███ | 59/193 [00:05<00:11, 11.53it/s][A | |
| 32%|███▏ | 61/193 [00:05<00:10, 12.67it/s][A | |
| 33%|███▎ | 63/193 [00:05<00:10, 12.23it/s][A | |
| 34%|███▎ | 65/193 [00:05<00:11, 11.27it/s][A | |
| 35%|███▍ | 67/193 [00:05<00:10, 12.09it/s][A | |
| 36%|███▌ | 69/193 [00:05<00:10, 11.70it/s][A | |
| 37%|███▋ | 71/193 [00:06<00:10, 11.24it/s][A | |
| 38%|███▊ | 73/193 [00:06<00:10, 11.52it/s][A | |
| 39%|███▉ | 75/193 [00:06<00:09, 12.71it/s][A | |
| 40%|███▉ | 77/193 [00:06<00:09, 11.67it/s][A | |
| 41%|████ | 79/193 [00:06<00:09, 11.66it/s][A | |
| 42%|████▏ | 81/193 [00:06<00:08, 12.54it/s][A | |
| 43%|████▎ | 83/193 [00:07<00:09, 11.86it/s][A | |
| 44%|████▍ | 85/193 [00:07<00:09, 11.28it/s][A | |
| 45%|████▌ | 87/193 [00:07<00:08, 12.44it/s][A | |
| 46%|████▌ | 89/193 [00:07<00:08, 11.97it/s][A | |
| 47%|████▋ | 91/193 [00:07<00:08, 11.43it/s][A | |
| 48%|████▊ | 93/193 [00:07<00:08, 12.15it/s][A | |
| 49%|████▉ | 95/193 [00:08<00:08, 12.23it/s][A | |
| 50%|█████ | 97/193 [00:08<00:08, 11.38it/s][A | |
| 51%|█████▏ | 99/193 [00:08<00:07, 12.61it/s][A | |
| 52%|█████▏ | 101/193 [00:08<00:07, 12.14it/s][A | |
| 53%|█████▎ | 103/193 [00:08<00:07, 12.25it/s][A | |
| 54%|█████▍ | 105/193 [00:08<00:07, 12.51it/s][A | |
| 55%|█████▌ | 107/193 [00:09<00:07, 11.44it/s][A | |
| 56%|█████▋ | 109/193 [00:09<00:07, 11.67it/s][A | |
| 58%|█████▊ | 111/193 [00:09<00:06, 12.41it/s][A | |
| 59%|█████▊ | 113/193 [00:09<00:06, 11.76it/s][A | |
| 60%|█████▉ | 115/193 [00:09<00:06, 12.55it/s][A | |
| 61%|██████ | 117/193 [00:09<00:05, 12.83it/s][A | |
| 62%|██████▏ | 119/193 [00:10<00:06, 11.43it/s][A | |
| 63%|██████▎ | 121/193 [00:10<00:06, 11.85it/s][A | |
| 64%|██████▎ | 123/193 [00:10<00:05, 12.17it/s][A | |
| 65%|██████▍ | 125/193 [00:10<00:05, 12.11it/s][A | |
| 66%|██████▌ | 127/193 [00:10<00:05, 11.43it/s][A | |
| 67%|██████▋ | 129/193 [00:10<00:05, 12.47it/s][A | |
| 68%|██████▊ | 131/193 [00:11<00:05, 11.94it/s][A | |
| 69%|██████▉ | 133/193 [00:11<00:04, 12.97it/s][A | |
| 70%|██████▉ | 135/193 [00:11<00:04, 12.15it/s][A | |
| 71%|███████ | 137/193 [00:11<00:04, 12.99it/s][A | |
| 72%|███████▏ | 139/193 [00:11<00:04, 12.64it/s][A | |
| 73%|███████▎ | 141/193 [00:11<00:04, 11.66it/s][A | |
| 75%|███████▍ | 144/193 [00:12<00:03, 12.54it/s][A | |
| 76%|███████▌ | 146/193 [00:12<00:03, 11.88it/s][A | |
| 77%|███████▋ | 148/193 [00:12<00:03, 11.65it/s][A | |
| 78%|███████▊ | 150/193 [00:12<00:03, 12.52it/s][A | |
| 79%|███████▉ | 152/193 [00:12<00:03, 12.24it/s][A | |
| 80%|███████▉ | 154/193 [00:12<00:03, 12.18it/s][A | |
| 81%|████████ | 156/193 [00:13<00:03, 12.03it/s][A | |
| 82%|████████▏ | 158/193 [00:13<00:02, 12.13it/s][A | |
| 83%|████████▎ | 160/193 [00:13<00:02, 12.24it/s][A | |
| 84%|████████▍ | 162/193 [00:13<00:02, 12.21it/s][A | |
| 85%|████████▍ | 164/193 [00:13<00:02, 11.99it/s][A | |
| 86%|████████▌ | 166/193 [00:13<00:02, 12.85it/s][A | |
| 87%|████████▋ | 168/193 [00:14<00:02, 11.83it/s][A | |
| 88%|████████▊ | 170/193 [00:14<00:01, 11.54it/s][A | |
| 89%|████████▉ | 172/193 [00:14<00:01, 11.88it/s][A | |
| 90%|█████████ | 174/193 [00:14<00:01, 12.35it/s][A | |
| 91%|█████████ | 176/193 [00:14<00:01, 11.83it/s][A | |
| 92%|█████████▏| 178/193 [00:14<00:01, 13.33it/s][A | |
| 93%|█████████▎| 180/193 [00:15<00:01, 12.36it/s][A | |
| 94%|█████████▍| 182/193 [00:15<00:00, 12.67it/s][A | |
| 95%|█████████▌| 184/193 [00:15<00:00, 12.65it/s][A | |
| 96%|█████████▋| 186/193 [00:15<00:00, 14.04it/s][A | |
| 97%|█████████▋| 188/193 [00:15<00:00, 12.43it/s][A | |
| 98%|█████████▊| 190/193 [00:15<00:00, 11.46it/s][A | |
| 99%|█████████▉| 192/193 [00:15<00:00, 12.58it/s][A | |
| [A{'eval_loss': 0.6205857992172241, 'eval_followed_precision': 0.7216396568160153, 'eval_followed_recall': 0.7271853986551393, 'eval_followed_f1': 0.724401913875598, 'eval_followed_support': 1041, 'eval_violated_precision': 0.6448412698412699, 'eval_violated_recall': 0.6728778467908902, 'eval_violated_f1': 0.6585612968591692, 'eval_violated_support': 966, 'eval_not_applicable_precision': 0.8585461689587426, 'eval_not_applicable_recall': 0.8183520599250936, 'eval_not_applicable_f1': 0.837967401725791, 'eval_not_applicable_support': 1068, 'eval_accuracy': 0.7417886178861789, 'eval_macro_f1': 0.7403102041535193, 'eval_runtime': 16.4592, 'eval_samples_per_second': 186.825, 'eval_steps_per_second': 11.726, 'epoch': 0.38} | |
| 25%|██▌ | 158/632 [01:50<05:54, 1.34it/s] | |
| 100%|██████████| 193/193 [00:16<00:00, 12.58it/s][A | |
| [A 25%|██▌ | 159/632 [01:50<44:16, 5.62s/it] 25%|██▌ | 160/632 [01:51<32:22, 4.12s/it] {'loss': 2.4391, 'grad_norm': 10.398664474487305, 'learning_rate': 0.00015766666666666669, 'epoch': 0.38} | |
| 25%|██▌ | 160/632 [01:51<32:22, 4.12s/it] 25%|██▌ | 161/632 [01:51<23:50, 3.04s/it] 26%|██▌ | 162/632 [01:52<18:15, 2.33s/it] 26%|██▌ | 163/632 [01:53<14:09, 1.81s/it] 26%|██▌ | 164/632 [01:53<11:18, 1.45s/it] 26%|██▌ | 165/632 [01:54<09:18, 1.20s/it] 26%|██▋ | 166/632 [01:54<07:55, 1.02s/it] 26%|██▋ | 167/632 [01:55<07:07, 1.09it/s] 27%|██▋ | 168/632 [01:55<06:05, 1.27it/s] 27%|██▋ | 169/632 [01:56<05:39, 1.36it/s] 27%|██▋ | 170/632 [01:57<05:29, 1.40it/s] {'loss': 2.4836, 'grad_norm': 7.297732353210449, 'learning_rate': 0.00015433333333333334, 'epoch': 0.4} | |
| 27%|██▋ | 170/632 [01:57<05:29, 1.40it/s] 27%|██▋ | 171/632 [01:57<05:22, 1.43it/s] 27%|██▋ | 172/632 [01:58<05:03, 1.51it/s] 27%|██▋ | 173/632 [01:59<04:48, 1.59it/s] 28%|██▊ | 174/632 [01:59<04:50, 1.58it/s] 28%|██▊ | 175/632 [02:00<05:01, 1.52it/s] 28%|██▊ | 176/632 [02:00<04:37, 1.64it/s] 28%|██▊ | 177/632 [02:01<04:19, 1.75it/s] 28%|██▊ | 178/632 [02:02<04:43, 1.60it/s] 28%|██▊ | 179/632 [02:02<04:36, 1.64it/s] 28%|██▊ | 180/632 [02:03<04:18, 1.75it/s] {'loss': 2.2652, 'grad_norm': 7.241300582885742, 'learning_rate': 0.000151, 'epoch': 0.43} | |
| 28%|██▊ | 180/632 [02:03<04:18, 1.75it/s] 29%|██▊ | 181/632 [02:03<04:37, 1.63it/s] 29%|██▉ | 182/632 [02:04<04:51, 1.54it/s] 29%|██▉ | 183/632 [02:05<04:59, 1.50it/s] 29%|██▉ | 184/632 [02:05<04:52, 1.53it/s] 29%|██▉ | 185/632 [02:06<04:33, 1.64it/s] 29%|██▉ | 186/632 [02:07<04:44, 1.57it/s] 30%|██▉ | 187/632 [02:07<04:42, 1.58it/s] 30%|██▉ | 188/632 [02:08<04:40, 1.58it/s] 30%|██▉ | 189/632 [02:09<04:33, 1.62it/s] 30%|███ | 190/632 [02:09<04:24, 1.67it/s] {'loss': 2.4275, 'grad_norm': 5.763534069061279, 'learning_rate': 0.00014766666666666666, 'epoch': 0.45} | |
| 30%|███ | 190/632 [02:09<04:24, 1.67it/s] 30%|███ | 191/632 [02:10<04:52, 1.51it/s] 30%|███ | 192/632 [02:11<04:56, 1.48it/s] 31%|███ | 193/632 [02:11<04:32, 1.61it/s] 31%|███ | 194/632 [02:12<04:32, 1.61it/s] 31%|███ | 195/632 [02:12<04:21, 1.67it/s] 31%|███ | 196/632 [02:13<04:16, 1.70it/s] 31%|███ | 197/632 [02:13<04:19, 1.68it/s] 31%|███▏ | 198/632 [02:14<04:16, 1.69it/s] 31%|███▏ | 199/632 [02:15<04:07, 1.75it/s] 32%|███▏ | 200/632 [02:15<04:09, 1.73it/s] {'loss': 2.0953, 'grad_norm': 7.520849704742432, 'learning_rate': 0.00014433333333333334, 'epoch': 0.48} | |
| 32%|███▏ | 200/632 [02:15<04:09, 1.73it/s] 32%|███▏ | 201/632 [02:16<04:05, 1.75it/s] 32%|███▏ | 202/632 [02:16<04:12, 1.70it/s] 32%|███▏ | 203/632 [02:17<04:11, 1.71it/s] 32%|███▏ | 204/632 [02:17<03:54, 1.82it/s] 32%|███▏ | 205/632 [02:18<03:57, 1.80it/s] 33%|███▎ | 206/632 [02:19<04:06, 1.73it/s] 33%|███▎ | 207/632 [02:19<03:58, 1.78it/s] 33%|███▎ | 208/632 [02:20<03:48, 1.85it/s] 33%|███▎ | 209/632 [02:20<04:02, 1.74it/s] 33%|███▎ | 210/632 [02:21<04:02, 1.74it/s] {'loss': 2.0169, 'grad_norm': 7.263973712921143, 'learning_rate': 0.000141, 'epoch': 0.5} | |
| 33%|███▎ | 210/632 [02:21<04:02, 1.74it/s] 33%|███▎ | 211/632 [02:21<03:50, 1.82it/s] 34%|███▎ | 212/632 [02:22<04:28, 1.56it/s] 34%|███▎ | 213/632 [02:23<04:25, 1.58it/s] 34%|███▍ | 214/632 [02:23<04:23, 1.59it/s] 34%|███▍ | 215/632 [02:24<04:21, 1.59it/s] 34%|███▍ | 216/632 [02:25<04:10, 1.66it/s] 34%|███▍ | 217/632 [02:25<04:09, 1.67it/s] 34%|███▍ | 218/632 [02:26<04:24, 1.56it/s] 35%|███▍ | 219/632 [02:26<04:19, 1.59it/s] 35%|███▍ | 220/632 [02:27<04:05, 1.68it/s] {'loss': 2.0415, 'grad_norm': 4.425047397613525, 'learning_rate': 0.0001376666666666667, 'epoch': 0.52} | |
| 35%|███▍ | 220/632 [02:27<04:05, 1.68it/s] 35%|███▍ | 221/632 [02:28<04:06, 1.67it/s] 35%|███▌ | 222/632 [02:28<04:18, 1.58it/s] 35%|███▌ | 223/632 [02:29<04:32, 1.50it/s] 35%|███▌ | 224/632 [02:30<04:13, 1.61it/s] 36%|███▌ | 225/632 [02:30<03:56, 1.72it/s] 36%|███▌ | 226/632 [02:31<03:57, 1.71it/s] 36%|███▌ | 227/632 [02:31<03:57, 1.70it/s] 36%|███▌ | 228/632 [02:32<03:55, 1.72it/s] 36%|███▌ | 229/632 [02:33<04:17, 1.57it/s] 36%|███▋ | 230/632 [02:33<04:32, 1.48it/s] {'loss': 2.116, 'grad_norm': 13.907865524291992, 'learning_rate': 0.00013433333333333334, 'epoch': 0.55} | |
| 36%|███▋ | 230/632 [02:33<04:32, 1.48it/s] 37%|███▋ | 231/632 [02:34<04:59, 1.34it/s] 37%|███▋ | 232/632 [02:35<04:42, 1.42it/s] 37%|███▋ | 233/632 [02:35<04:21, 1.53it/s] 37%|███▋ | 234/632 [02:36<04:03, 1.64it/s] 37%|███▋ | 235/632 [02:37<03:58, 1.66it/s] 37%|███▋ | 236/632 [02:37<03:42, 1.78it/s] 38%|███▊ | 237/632 [02:38<03:53, 1.69it/s] 38%|███▊ | 238/632 [02:38<03:49, 1.72it/s] 38%|███▊ | 239/632 [02:39<03:55, 1.67it/s] 38%|███▊ | 240/632 [02:39<03:41, 1.77it/s] {'loss': 2.2286, 'grad_norm': 12.071761131286621, 'learning_rate': 0.000131, 'epoch': 0.57} | |
| 38%|███▊ | 240/632 [02:39<03:41, 1.77it/s] 38%|███▊ | 241/632 [02:40<03:42, 1.76it/s] 38%|███▊ | 242/632 [02:40<03:33, 1.83it/s] 38%|███▊ | 243/632 [02:41<03:27, 1.87it/s] 39%|███▊ | 244/632 [02:42<03:37, 1.78it/s] 39%|███▉ | 245/632 [02:42<04:15, 1.51it/s] 39%|███▉ | 246/632 [02:43<04:13, 1.52it/s] 39%|███▉ | 247/632 [02:44<03:59, 1.61it/s] 39%|███▉ | 248/632 [02:44<04:07, 1.55it/s] 39%|███▉ | 249/632 [02:45<03:55, 1.63it/s] 40%|███▉ | 250/632 [02:45<03:48, 1.67it/s] {'loss': 2.0534, 'grad_norm': 10.676264762878418, 'learning_rate': 0.00012766666666666666, 'epoch': 0.59} | |
| 40%|███▉ | 250/632 [02:45<03:48, 1.67it/s] 40%|███▉ | 251/632 [02:46<03:51, 1.64it/s] 40%|███▉ | 252/632 [02:47<03:41, 1.71it/s] 40%|████ | 253/632 [02:47<03:28, 1.82it/s] 40%|████ | 254/632 [02:48<03:45, 1.67it/s] 40%|████ | 255/632 [02:48<03:43, 1.69it/s] 41%|████ | 256/632 [02:49<03:47, 1.65it/s] 41%|████ | 257/632 [02:50<03:45, 1.67it/s] 41%|████ | 258/632 [02:50<03:27, 1.80it/s] 41%|████ | 259/632 [02:51<03:27, 1.80it/s] 41%|████ | 260/632 [02:51<03:34, 1.74it/s] {'loss': 2.0097, 'grad_norm': 6.14788818359375, 'learning_rate': 0.00012433333333333334, 'epoch': 0.62} | |
| 41%|████ | 260/632 [02:51<03:34, 1.74it/s] 41%|████▏ | 261/632 [02:52<03:26, 1.79it/s] 41%|████▏ | 262/632 [02:52<03:33, 1.73it/s] 42%|████▏ | 263/632 [02:53<03:44, 1.64it/s] 42%|████▏ | 264/632 [02:54<03:38, 1.68it/s] 42%|████▏ | 265/632 [02:54<03:37, 1.69it/s] 42%|████▏ | 266/632 [02:55<03:28, 1.75it/s] 42%|████▏ | 267/632 [02:55<03:18, 1.84it/s] 42%|████▏ | 268/632 [02:56<03:56, 1.54it/s] 43%|████▎ | 269/632 [02:57<03:53, 1.55it/s] 43%|████▎ | 270/632 [02:57<04:08, 1.46it/s] {'loss': 2.0773, 'grad_norm': 6.418664932250977, 'learning_rate': 0.000121, 'epoch': 0.64} | |
| 43%|████▎ | 270/632 [02:57<04:08, 1.46it/s] 43%|████▎ | 271/632 [02:58<04:12, 1.43it/s] 43%|████▎ | 272/632 [02:59<04:10, 1.44it/s] 43%|████▎ | 273/632 [03:00<04:03, 1.47it/s] 43%|████▎ | 274/632 [03:00<03:47, 1.58it/s] 44%|████▎ | 275/632 [03:01<03:35, 1.65it/s] 44%|████▎ | 276/632 [03:01<03:19, 1.79it/s] 44%|████▍ | 277/632 [03:02<03:29, 1.70it/s] 44%|████▍ | 278/632 [03:02<03:32, 1.67it/s] 44%|████▍ | 279/632 [03:03<03:35, 1.64it/s] 44%|████▍ | 280/632 [03:03<03:20, 1.76it/s] {'loss': 1.9297, 'grad_norm': 9.235907554626465, 'learning_rate': 0.00011766666666666668, 'epoch': 0.67} | |
| 44%|████▍ | 280/632 [03:03<03:20, 1.76it/s] 44%|████▍ | 281/632 [03:04<03:39, 1.60it/s] 45%|████▍ | 282/632 [03:05<03:33, 1.64it/s] 45%|████▍ | 283/632 [03:05<03:25, 1.70it/s] 45%|████▍ | 284/632 [03:06<03:19, 1.74it/s] 45%|████▌ | 285/632 [03:06<03:03, 1.89it/s] 45%|████▌ | 286/632 [03:07<03:03, 1.89it/s] 45%|████▌ | 287/632 [03:08<03:21, 1.71it/s] 46%|████▌ | 288/632 [03:08<03:29, 1.64it/s] 46%|████▌ | 289/632 [03:09<04:00, 1.42it/s] 46%|████▌ | 290/632 [03:10<03:51, 1.48it/s] {'loss': 1.9716, 'grad_norm': 10.90473747253418, 'learning_rate': 0.00011433333333333334, 'epoch': 0.69} | |
| 46%|████▌ | 290/632 [03:10<03:51, 1.48it/s] 46%|████▌ | 291/632 [03:10<03:34, 1.59it/s] 46%|████▌ | 292/632 [03:11<03:29, 1.62it/s] 46%|████▋ | 293/632 [03:11<03:28, 1.62it/s] 47%|████▋ | 294/632 [03:12<03:27, 1.63it/s] 47%|████▋ | 295/632 [03:13<03:25, 1.64it/s] 47%|████▋ | 296/632 [03:13<03:35, 1.56it/s] 47%|████▋ | 297/632 [03:14<03:34, 1.56it/s] 47%|████▋ | 298/632 [03:15<03:35, 1.55it/s] 47%|████▋ | 299/632 [03:15<03:36, 1.54it/s] 47%|████▋ | 300/632 [03:16<03:32, 1.57it/s] {'loss': 1.9723, 'grad_norm': 8.630451202392578, 'learning_rate': 0.00011100000000000001, 'epoch': 0.71} | |
| 47%|████▋ | 300/632 [03:16<03:32, 1.57it/s] 48%|████▊ | 301/632 [03:17<03:27, 1.60it/s] 48%|████▊ | 302/632 [03:17<03:23, 1.62it/s] 48%|████▊ | 303/632 [03:18<03:15, 1.68it/s] 48%|████▊ | 304/632 [03:18<03:09, 1.73it/s] 48%|████▊ | 305/632 [03:19<03:03, 1.78it/s] 48%|████▊ | 306/632 [03:19<02:59, 1.82it/s] 49%|████▊ | 307/632 [03:20<03:11, 1.69it/s] 49%|████▊ | 308/632 [03:20<03:01, 1.79it/s] 49%|████▉ | 309/632 [03:21<02:56, 1.83it/s] 49%|████▉ | 310/632 [03:21<02:55, 1.83it/s] {'loss': 1.8505, 'grad_norm': 6.160138130187988, 'learning_rate': 0.00010766666666666668, 'epoch': 0.74} | |
| 49%|████▉ | 310/632 [03:21<02:55, 1.83it/s] 49%|████▉ | 311/632 [03:22<03:02, 1.76it/s] 49%|████▉ | 312/632 [03:23<02:57, 1.80it/s] 50%|████▉ | 313/632 [03:23<03:03, 1.74it/s] 50%|████▉ | 314/632 [03:24<02:57, 1.80it/s] 50%|████▉ | 315/632 [03:24<02:53, 1.83it/s]Saved adapter checkpoint checkpoints/modernbert-large-30k/checkpoint-2of4-step316 | |
| 50%|█████ | 316/632 [03:26<04:06, 1.28it/s] | |
| 0%| | 0/193 [00:00<?, ?it/s][A | |
| 1%| | 2/193 [00:00<00:18, 10.16it/s][A | |
| 2%|▏ | 4/193 [00:00<00:23, 8.14it/s][A | |
| 3%|▎ | 5/193 [00:00<00:22, 8.44it/s][A | |
| 4%|▍ | 8/193 [00:00<00:15, 11.68it/s][A | |
| 5%|▌ | 10/193 [00:00<00:16, 10.98it/s][A | |
| 6%|▌ | 12/193 [00:01<00:16, 10.87it/s][A | |
| 7%|▋ | 14/193 [00:01<00:17, 10.33it/s][A | |
| 9%|▉ | 17/193 [00:01<00:15, 11.63it/s][A | |
| 10%|▉ | 19/193 [00:01<00:15, 10.90it/s][A | |
| 11%|█ | 21/193 [00:01<00:14, 11.67it/s][A | |
| 12%|█▏ | 23/193 [00:02<00:13, 12.55it/s][A | |
| 13%|█▎ | 25/193 [00:02<00:14, 11.57it/s][A | |
| 14%|█▍ | 27/193 [00:02<00:13, 12.24it/s][A | |
| 15%|█▌ | 29/193 [00:02<00:14, 11.69it/s][A | |
| 16%|█▌ | 31/193 [00:02<00:13, 11.87it/s][A | |
| 17%|█▋ | 33/193 [00:02<00:14, 11.21it/s][A | |
| 18%|█▊ | 35/193 [00:03<00:12, 12.63it/s][A | |
| 19%|█▉ | 37/193 [00:03<00:13, 11.88it/s][A | |
| 20%|██ | 39/193 [00:03<00:13, 11.41it/s][A | |
| 21%|██ | 41/193 [00:03<00:12, 11.76it/s][A | |
| 22%|██▏ | 43/193 [00:03<00:12, 12.11it/s][A | |
| 23%|██▎ | 45/193 [00:03<00:12, 11.67it/s][A | |
| 24%|██▍ | 47/193 [00:04<00:12, 11.24it/s][A | |
| 25%|██▌ | 49/193 [00:04<00:11, 12.13it/s][A | |
| 26%|██▋ | 51/193 [00:04<00:12, 11.65it/s][A | |
| 27%|██▋ | 53/193 [00:04<00:12, 11.54it/s][A | |
| 28%|██▊ | 55/193 [00:04<00:11, 12.06it/s][A | |
| 30%|██▉ | 57/193 [00:04<00:11, 12.26it/s][A | |
| 31%|███ | 59/193 [00:05<00:10, 12.61it/s][A | |
| 32%|███▏ | 61/193 [00:05<00:10, 12.59it/s][A | |
| 33%|███▎ | 63/193 [00:05<00:10, 12.02it/s][A | |
| 34%|███▎ | 65/193 [00:05<00:09, 12.81it/s][A | |
| 35%|███▍ | 67/193 [00:05<00:10, 11.94it/s][A | |
| 36%|███▌ | 69/193 [00:05<00:10, 12.12it/s][A | |
| 37%|███▋ | 71/193 [00:06<00:10, 11.84it/s][A | |
| 38%|███▊ | 73/193 [00:06<00:09, 12.10it/s][A | |
| 39%|███▉ | 75/193 [00:06<00:10, 11.78it/s][A | |
| 40%|███▉ | 77/193 [00:06<00:09, 12.39it/s][A | |
| 41%|████ | 79/193 [00:06<00:09, 12.18it/s][A | |
| 42%|████▏ | 81/193 [00:06<00:08, 13.42it/s][A | |
| 43%|████▎ | 83/193 [00:07<00:08, 12.65it/s][A | |
| 44%|████▍ | 85/193 [00:07<00:08, 12.53it/s][A | |
| 45%|████▌ | 87/193 [00:07<00:08, 12.71it/s][A | |
| 46%|████▌ | 89/193 [00:07<00:08, 11.99it/s][A | |
| 47%|████▋ | 91/193 [00:07<00:08, 12.48it/s][A | |
| 48%|████▊ | 93/193 [00:07<00:08, 12.28it/s][A | |
| 49%|████▉ | 95/193 [00:08<00:08, 12.02it/s][A | |
| 50%|█████ | 97/193 [00:08<00:07, 12.65it/s][A | |
| 51%|█████▏ | 99/193 [00:08<00:07, 12.27it/s][A | |
| 52%|█████▏ | 101/193 [00:08<00:07, 12.74it/s][A | |
| 53%|█████▎ | 103/193 [00:08<00:07, 12.29it/s][A | |
| 54%|█████▍ | 105/193 [00:08<00:07, 11.91it/s][A | |
| 55%|█████▌ | 107/193 [00:09<00:07, 11.90it/s][A | |
| 56%|█████▋ | 109/193 [00:09<00:06, 12.15it/s][A | |
| 58%|█████▊ | 111/193 [00:09<00:06, 11.89it/s][A | |
| 59%|█████▊ | 113/193 [00:09<00:06, 12.96it/s][A | |
| 60%|█████▉ | 115/193 [00:09<00:06, 12.35it/s][A | |
| 61%|██████ | 117/193 [00:09<00:06, 11.85it/s][A | |
| 62%|██████▏ | 119/193 [00:09<00:05, 12.39it/s][A | |
| 63%|██████▎ | 121/193 [00:10<00:06, 11.96it/s][A | |
| 64%|██████▎ | 123/193 [00:10<00:05, 13.01it/s][A | |
| 65%|██████▍ | 125/193 [00:10<00:05, 12.64it/s][A | |
| 66%|██████▌ | 127/193 [00:10<00:05, 11.72it/s][A | |
| 67%|██████▋ | 129/193 [00:10<00:04, 12.92it/s][A | |
| 68%|██████▊ | 131/193 [00:10<00:05, 12.38it/s][A | |
| 69%|██████▉ | 133/193 [00:11<00:04, 13.34it/s][A | |
| 70%|██████▉ | 135/193 [00:11<00:04, 12.38it/s][A | |
| 71%|███████ | 137/193 [00:11<00:04, 13.50it/s][A | |
| 72%|███████▏ | 139/193 [00:11<00:04, 12.67it/s][A | |
| 73%|███████▎ | 141/193 [00:11<00:04, 11.72it/s][A | |
| 75%|███████▍ | 144/193 [00:11<00:03, 12.74it/s][A | |
| 76%|███████▌ | 146/193 [00:12<00:03, 11.82it/s][A | |
| 77%|███████▋ | 148/193 [00:12<00:03, 12.85it/s][A | |
| 78%|███████▊ | 150/193 [00:12<00:03, 12.09it/s][A | |
| 79%|███████▉ | 152/193 [00:12<00:03, 11.99it/s][A | |
| 80%|███████▉ | 154/193 [00:12<00:03, 12.17it/s][A | |
| 81%|████████ | 156/193 [00:12<00:03, 12.10it/s][A | |
| 82%|████████▏ | 158/193 [00:13<00:02, 12.34it/s][A | |
| 83%|████████▎ | 160/193 [00:13<00:02, 12.44it/s][A | |
| 84%|████████▍ | 162/193 [00:13<00:02, 12.86it/s][A | |
| 85%|████████▍ | 164/193 [00:13<00:02, 13.33it/s][A | |
| 86%|████████▌ | 166/193 [00:13<00:02, 12.58it/s][A | |
| 87%|████████▋ | 168/193 [00:13<00:01, 12.98it/s][A | |
| 88%|████████▊ | 170/193 [00:14<00:01, 12.41it/s][A | |
| 89%|████████▉ | 172/193 [00:14<00:01, 11.76it/s][A | |
| 90%|█████████ | 174/193 [00:14<00:01, 12.81it/s][A | |
| 91%|█████████ | 176/193 [00:14<00:01, 12.24it/s][A | |
| 92%|█████████▏| 178/193 [00:14<00:01, 12.16it/s][A | |
| 93%|█████████▎| 180/193 [00:14<00:01, 12.87it/s][A | |
| 94%|█████████▍| 182/193 [00:15<00:00, 11.61it/s][A | |
| 96%|█████████▌| 185/193 [00:15<00:00, 12.83it/s][A | |
| 97%|█████████▋| 187/193 [00:15<00:00, 12.42it/s][A | |
| 98%|█████████▊| 189/193 [00:15<00:00, 13.11it/s][A | |
| 99%|█████████▉| 191/193 [00:15<00:00, 13.04it/s][A | |
| 100%|██████████| 193/193 [00:15<00:00, 12.72it/s][A | |
| [A{'eval_loss': 0.5575851202011108, 'eval_followed_precision': 0.7107569721115538, 'eval_followed_recall': 0.8568683957732949, 'eval_followed_f1': 0.7770034843205574, 'eval_followed_support': 1041, 'eval_violated_precision': 0.8658718330849479, 'eval_violated_recall': 0.6014492753623188, 'eval_violated_f1': 0.7098350641417227, 'eval_violated_support': 966, 'eval_not_applicable_precision': 0.8424717145343777, 'eval_not_applicable_recall': 0.9063670411985019, 'eval_not_applicable_f1': 0.8732521425349572, 'eval_not_applicable_support': 1068, 'eval_accuracy': 0.7938211382113821, 'eval_macro_f1': 0.7866968969990791, 'eval_runtime': 16.2323, 'eval_samples_per_second': 189.438, 'eval_steps_per_second': 11.89, 'epoch': 0.75} | |
| 50%|█████ | 316/632 [03:42<04:06, 1.28it/s] | |
| 100%|██████████| 193/193 [00:15<00:00, 12.72it/s][A | |
| [A 50%|█████ | 317/632 [03:43<29:30, 5.62s/it] 50%|█████ | 318/632 [03:43<21:25, 4.09s/it] 50%|█████ | 319/632 [03:44<15:49, 3.03s/it] 51%|█████ | 320/632 [03:44<12:01, 2.31s/it] {'loss': 1.75, 'grad_norm': 6.828271865844727, 'learning_rate': 0.00010433333333333333, 'epoch': 0.76} | |
| 51%|█████ | 320/632 [03:44<12:01, 2.31s/it] 51%|█████ | 321/632 [03:45<09:21, 1.81s/it] 51%|█████ | 322/632 [03:45<07:28, 1.45s/it] 51%|█████ | 323/632 [03:46<06:01, 1.17s/it] 51%|█████▏ | 324/632 [03:47<05:03, 1.01it/s] 51%|█████▏ | 325/632 [03:47<04:27, 1.15it/s] 52%|█████▏ | 326/632 [03:48<03:50, 1.33it/s] 52%|█████▏ | 327/632 [03:48<03:34, 1.42it/s] 52%|█████▏ | 328/632 [03:49<03:29, 1.45it/s] 52%|█████▏ | 329/632 [03:49<03:17, 1.53it/s] 52%|█████▏ | 330/632 [03:50<03:00, 1.67it/s] {'loss': 1.6435, 'grad_norm': 5.3480730056762695, 'learning_rate': 0.000101, 'epoch': 0.78} | |
| 52%|█████▏ | 330/632 [03:50<03:00, 1.67it/s] 52%|█████▏ | 331/632 [03:51<03:13, 1.56it/s] 53%|█████▎ | 332/632 [03:51<03:04, 1.62it/s] 53%|█████▎ | 333/632 [03:52<03:01, 1.64it/s] 53%|█████▎ | 334/632 [03:52<02:49, 1.76it/s] 53%|█████▎ | 335/632 [03:53<02:45, 1.79it/s] 53%|█████▎ | 336/632 [03:53<02:52, 1.72it/s] 53%|█████▎ | 337/632 [03:54<02:50, 1.73it/s] 53%|█████▎ | 338/632 [03:54<02:37, 1.86it/s] 54%|█████▎ | 339/632 [03:55<02:38, 1.85it/s] 54%|█████▍ | 340/632 [03:55<02:32, 1.91it/s] {'loss': 1.7539, 'grad_norm': 5.274939060211182, 'learning_rate': 9.766666666666668e-05, 'epoch': 0.81} | |
| 54%|█████▍ | 340/632 [03:55<02:32, 1.91it/s] 54%|█████▍ | 341/632 [03:56<02:30, 1.94it/s] 54%|█████▍ | 342/632 [03:57<02:48, 1.73it/s] 54%|█████▍ | 343/632 [03:57<02:43, 1.77it/s] 54%|█████▍ | 344/632 [03:58<02:50, 1.69it/s] 55%|█████▍ | 345/632 [03:58<02:46, 1.72it/s] 55%|█████▍ | 346/632 [03:59<02:49, 1.68it/s] 55%|█████▍ | 347/632 [04:00<02:47, 1.70it/s] 55%|█████▌ | 348/632 [04:00<02:40, 1.77it/s] 55%|█████▌ | 349/632 [04:01<02:42, 1.75it/s] 55%|█████▌ | 350/632 [04:01<02:38, 1.77it/s] {'loss': 1.8111, 'grad_norm': 10.137001991271973, 'learning_rate': 9.433333333333334e-05, 'epoch': 0.83} | |
| 55%|█████▌ | 350/632 [04:01<02:38, 1.77it/s] 56%|█████▌ | 351/632 [04:02<02:32, 1.84it/s] 56%|█████▌ | 352/632 [04:03<02:48, 1.66it/s] 56%|█████▌ | 353/632 [04:03<02:58, 1.56it/s] 56%|█████▌ | 354/632 [04:04<02:48, 1.65it/s] 56%|█████▌ | 355/632 [04:04<02:55, 1.58it/s] 56%|█████▋ | 356/632 [04:05<02:47, 1.65it/s] 56%|█████▋ | 357/632 [04:06<02:57, 1.55it/s] 57%|█████▋ | 358/632 [04:06<02:53, 1.58it/s] 57%|█████▋ | 359/632 [04:07<02:43, 1.67it/s] 57%|█████▋ | 360/632 [04:07<02:43, 1.67it/s] {'loss': 1.8319, 'grad_norm': 7.701445579528809, 'learning_rate': 9.1e-05, 'epoch': 0.86} | |
| 57%|█████▋ | 360/632 [04:08<02:43, 1.67it/s] 57%|█████▋ | 361/632 [04:08<02:48, 1.61it/s] 57%|█████▋ | 362/632 [04:09<02:43, 1.65it/s] 57%|█████▋ | 363/632 [04:09<02:44, 1.64it/s] 58%|█████▊ | 364/632 [04:10<02:42, 1.65it/s] 58%|█████▊ | 365/632 [04:11<03:32, 1.26it/s] 58%|█████▊ | 366/632 [04:12<03:11, 1.39it/s] 58%|█████▊ | 367/632 [04:12<03:01, 1.46it/s] 58%|█████▊ | 368/632 [04:13<02:46, 1.58it/s] 58%|█████▊ | 369/632 [04:13<02:44, 1.60it/s] 59%|█████▊ | 370/632 [04:14<02:44, 1.60it/s] {'loss': 1.9638, 'grad_norm': 7.314540863037109, 'learning_rate': 8.766666666666668e-05, 'epoch': 0.88} | |
| 59%|█████▊ | 370/632 [04:14<02:44, 1.60it/s] 59%|█████▊ | 371/632 [04:15<02:45, 1.58it/s] 59%|█████▉ | 372/632 [04:15<02:38, 1.64it/s] 59%|█████▉ | 373/632 [04:16<02:30, 1.72it/s] 59%|█████▉ | 374/632 [04:16<02:27, 1.75it/s] 59%|█████▉ | 375/632 [04:17<02:23, 1.79it/s] 59%|█████▉ | 376/632 [04:18<02:39, 1.60it/s] 60%|█████▉ | 377/632 [04:18<02:31, 1.68it/s] 60%|█████▉ | 378/632 [04:19<02:29, 1.70it/s] 60%|█████▉ | 379/632 [04:19<02:18, 1.83it/s] 60%|██████ | 380/632 [04:20<02:27, 1.71it/s] {'loss': 1.6317, 'grad_norm': 8.760168075561523, 'learning_rate': 8.433333333333334e-05, 'epoch': 0.9} | |
| 60%|██████ | 380/632 [04:20<02:27, 1.71it/s] 60%|██████ | 381/632 [04:20<02:23, 1.75it/s] 60%|██████ | 382/632 [04:21<02:14, 1.86it/s] 61%|██████ | 383/632 [04:21<02:14, 1.85it/s] 61%|██████ | 384/632 [04:22<02:23, 1.73it/s] 61%|██████ | 385/632 [04:23<02:14, 1.84it/s] 61%|██████ | 386/632 [04:23<02:21, 1.74it/s] 61%|██████ | 387/632 [04:24<02:24, 1.70it/s] 61%|██████▏ | 388/632 [04:25<02:36, 1.56it/s] 62%|██████▏ | 389/632 [04:25<02:27, 1.65it/s] 62%|██████▏ | 390/632 [04:26<02:21, 1.71it/s] {'loss': 2.2365, 'grad_norm': 10.153656005859375, 'learning_rate': 8.1e-05, 'epoch': 0.93} | |
| 62%|██████▏ | 390/632 [04:26<02:21, 1.71it/s] 62%|██████▏ | 391/632 [04:26<02:21, 1.70it/s] 62%|██████▏ | 392/632 [04:27<02:25, 1.65it/s] 62%|██████▏ | 393/632 [04:28<02:29, 1.60it/s] 62%|██████▏ | 394/632 [04:28<02:21, 1.68it/s] 62%|██████▎ | 395/632 [04:29<02:14, 1.76it/s] 63%|██████▎ | 396/632 [04:29<02:14, 1.76it/s] 63%|██████▎ | 397/632 [04:30<02:31, 1.55it/s] 63%|██████▎ | 398/632 [04:30<02:21, 1.65it/s] 63%|██████▎ | 399/632 [04:31<02:20, 1.66it/s] 63%|██████▎ | 400/632 [04:32<02:18, 1.67it/s] {'loss': 1.72, 'grad_norm': 7.578658103942871, 'learning_rate': 7.766666666666667e-05, 'epoch': 0.95} | |
| 63%|██████▎ | 400/632 [04:32<02:18, 1.67it/s] 63%|██████▎ | 401/632 [04:32<02:21, 1.63it/s] 64%|██████▎ | 402/632 [04:33<02:22, 1.61it/s] 64%|██████▍ | 403/632 [04:33<02:14, 1.71it/s] 64%|██████▍ | 404/632 [04:34<02:28, 1.53it/s] 64%|██████▍ | 405/632 [04:35<02:17, 1.65it/s] 64%|██████▍ | 406/632 [04:35<02:12, 1.70it/s] 64%|██████▍ | 407/632 [04:36<02:21, 1.59it/s] 65%|██████▍ | 408/632 [04:37<02:15, 1.66it/s] 65%|██████▍ | 409/632 [04:37<02:10, 1.71it/s] 65%|██████▍ | 410/632 [04:38<02:13, 1.67it/s] {'loss': 2.0505, 'grad_norm': 5.553631782531738, 'learning_rate': 7.433333333333333e-05, 'epoch': 0.97} | |
| 65%|██████▍ | 410/632 [04:38<02:13, 1.67it/s] 65%|██████▌ | 411/632 [04:38<02:07, 1.74it/s] 65%|██████▌ | 412/632 [04:39<02:01, 1.82it/s] 65%|██████▌ | 413/632 [04:39<02:03, 1.77it/s] 66%|██████▌ | 414/632 [04:40<02:06, 1.73it/s] 66%|██████▌ | 415/632 [04:41<02:07, 1.71it/s] 66%|██████▌ | 416/632 [04:41<02:08, 1.68it/s] 66%|██████▌ | 417/632 [04:42<02:03, 1.74it/s] 66%|██████▌ | 418/632 [04:42<02:06, 1.69it/s] 66%|██████▋ | 419/632 [04:43<02:05, 1.70it/s] 66%|██████▋ | 420/632 [04:43<02:01, 1.75it/s] {'loss': 1.8263, 'grad_norm': 7.197715759277344, 'learning_rate': 7.1e-05, 'epoch': 1.0} | |
| 66%|██████▋ | 420/632 [04:43<02:01, 1.75it/s] 67%|██████▋ | 421/632 [04:44<01:55, 1.83it/s] 67%|██████▋ | 422/632 [04:45<02:19, 1.51it/s] 67%|██████▋ | 423/632 [04:45<02:10, 1.60it/s] 67%|██████▋ | 424/632 [04:46<02:06, 1.65it/s] 67%|██████▋ | 425/632 [04:47<02:08, 1.61it/s] 67%|██████▋ | 426/632 [04:47<02:05, 1.65it/s] 68%|██████▊ | 427/632 [04:48<02:04, 1.65it/s] 68%|██████▊ | 428/632 [04:48<01:58, 1.72it/s] 68%|██████▊ | 429/632 [04:49<01:54, 1.77it/s] 68%|██████▊ | 430/632 [04:49<01:53, 1.78it/s] {'loss': 1.4573, 'grad_norm': 6.076384544372559, 'learning_rate': 6.766666666666667e-05, 'epoch': 1.02} | |
| 68%|██████▊ | 430/632 [04:49<01:53, 1.78it/s] 68%|██████▊ | 431/632 [04:50<01:54, 1.75it/s] 68%|██████▊ | 432/632 [04:51<02:09, 1.54it/s] 69%|██████▊ | 433/632 [04:51<02:06, 1.57it/s] 69%|██████▊ | 434/632 [04:52<02:13, 1.49it/s] 69%|██████▉ | 435/632 [04:53<02:06, 1.56it/s] 69%|██████▉ | 436/632 [04:53<02:00, 1.62it/s] 69%|██████▉ | 437/632 [04:54<02:00, 1.62it/s] 69%|██████▉ | 438/632 [04:55<02:07, 1.53it/s] 69%|██████▉ | 439/632 [04:55<02:01, 1.59it/s] 70%|██████▉ | 440/632 [04:56<01:56, 1.65it/s] {'loss': 1.4335, 'grad_norm': 6.855465412139893, 'learning_rate': 6.433333333333333e-05, 'epoch': 1.05} | |
| 70%|██████▉ | 440/632 [04:56<01:56, 1.65it/s] 70%|██████▉ | 441/632 [04:56<01:52, 1.70it/s] 70%|██████▉ | 442/632 [04:57<01:54, 1.66it/s] 70%|███████ | 443/632 [04:58<01:53, 1.66it/s] 70%|███████ | 444/632 [04:58<01:50, 1.70it/s] 70%|███████ | 445/632 [04:59<02:00, 1.55it/s] 71%|███████ | 446/632 [05:00<02:01, 1.53it/s] 71%|███████ | 447/632 [05:00<01:53, 1.64it/s] 71%|███████ | 448/632 [05:01<01:54, 1.61it/s] 71%|███████ | 449/632 [05:01<01:56, 1.57it/s] 71%|███████ | 450/632 [05:02<01:56, 1.57it/s] {'loss': 1.6172, 'grad_norm': 11.732808113098145, 'learning_rate': 6.1e-05, 'epoch': 1.07} | |
| 71%|███████ | 450/632 [05:02<01:56, 1.57it/s] 71%|███████▏ | 451/632 [05:03<01:50, 1.63it/s] 72%|███████▏ | 452/632 [05:03<01:56, 1.55it/s] 72%|███████▏ | 453/632 [05:04<01:49, 1.63it/s] 72%|███████▏ | 454/632 [05:04<01:47, 1.65it/s] 72%|███████▏ | 455/632 [05:05<01:53, 1.57it/s] 72%|███████▏ | 456/632 [05:06<01:50, 1.59it/s] 72%|███████▏ | 457/632 [05:06<01:45, 1.66it/s] 72%|███████▏ | 458/632 [05:07<01:44, 1.67it/s] 73%|███████▎ | 459/632 [05:07<01:38, 1.75it/s] 73%|███████▎ | 460/632 [05:08<01:37, 1.76it/s] {'loss': 1.3702, 'grad_norm': 6.227572441101074, 'learning_rate': 5.766666666666667e-05, 'epoch': 1.09} | |
| 73%|███████▎ | 460/632 [05:08<01:37, 1.76it/s] 73%|███████▎ | 461/632 [05:09<01:37, 1.76it/s] 73%|███████▎ | 462/632 [05:09<01:39, 1.71it/s] 73%|███████▎ | 463/632 [05:10<01:49, 1.54it/s] 73%|███████▎ | 464/632 [05:11<01:44, 1.61it/s] 74%|███████▎ | 465/632 [05:11<01:38, 1.70it/s] 74%|███████▎ | 466/632 [05:12<01:40, 1.65it/s] 74%|███████▍ | 467/632 [05:12<01:45, 1.57it/s] 74%|███████▍ | 468/632 [05:13<01:41, 1.61it/s] 74%|███████▍ | 469/632 [05:14<01:39, 1.63it/s] 74%|███████▍ | 470/632 [05:14<01:36, 1.68it/s] {'loss': 1.4817, 'grad_norm': 7.468378067016602, 'learning_rate': 5.433333333333334e-05, 'epoch': 1.12} | |
| 74%|███████▍ | 470/632 [05:14<01:36, 1.68it/s] 75%|███████▍ | 471/632 [05:15<01:34, 1.70it/s] 75%|███████▍ | 472/632 [05:15<01:32, 1.72it/s] 75%|███████▍ | 473/632 [05:16<01:35, 1.67it/s]Saved adapter checkpoint checkpoints/modernbert-large-30k/checkpoint-3of4-step474 | |
| 75%|███████▌ | 474/632 [05:17<02:09, 1.22it/s] | |
| 0%| | 0/193 [00:00<?, ?it/s][A | |
| 1%| | 2/193 [00:00<00:23, 8.13it/s][A | |
| 2%|▏ | 3/193 [00:00<00:26, 7.06it/s][A | |
| 3%|▎ | 5/193 [00:00<00:19, 9.46it/s][A | |
| 4%|▎ | 7/193 [00:00<00:15, 12.24it/s][A | |
| 5%|▍ | 9/193 [00:00<00:16, 10.88it/s][A | |
| 6%|▌ | 11/193 [00:01<00:16, 11.14it/s][A | |
| 7%|▋ | 13/193 [00:01<00:17, 10.42it/s][A | |
| 8%|▊ | 15/193 [00:01<00:14, 12.33it/s][A | |
| 9%|▉ | 17/193 [00:01<00:14, 11.80it/s][A | |
| 10%|▉ | 19/193 [00:01<00:14, 11.80it/s][A | |
| 11%|█ | 21/193 [00:01<00:14, 12.28it/s][A | |
| 12%|█▏ | 23/193 [00:02<00:14, 11.70it/s][A | |
| 13%|█▎ | 25/193 [00:02<00:13, 12.40it/s][A | |
| 14%|█▍ | 27/193 [00:02<00:13, 11.95it/s][A | |
| 15%|█▌ | 29/193 [00:02<00:14, 11.41it/s][A | |
| 17%|█▋ | 32/193 [00:02<00:12, 12.41it/s][A | |
| 18%|█▊ | 34/193 [00:02<00:12, 12.32it/s][A | |
| 19%|█▊ | 36/193 [00:03<00:12, 12.73it/s][A | |
| 20%|█▉ | 38/193 [00:03<00:12, 12.50it/s][A | |
| 21%|██ | 40/193 [00:03<00:13, 11.71it/s][A | |
| 22%|██▏ | 42/193 [00:03<00:11, 12.90it/s][A | |
| 23%|██▎ | 44/193 [00:03<00:12, 12.37it/s][A | |
| 24%|██▍ | 46/193 [00:03<00:12, 11.95it/s][A | |
| 25%|██▍ | 48/193 [00:04<00:11, 12.83it/s][A | |
| 26%|██▌ | 50/193 [00:04<00:11, 12.18it/s][A | |
| 27%|██▋ | 52/193 [00:04<00:10, 13.09it/s][A | |
| 28%|██▊ | 54/193 [00:04<00:11, 12.00it/s][A | |
| 29%|██▉ | 56/193 [00:04<00:11, 11.99it/s][A | |
| 30%|███ | 58/193 [00:04<00:10, 12.66it/s][A | |
| 31%|███ | 60/193 [00:05<00:10, 12.20it/s][A | |
| 32%|███▏ | 62/193 [00:05<00:10, 12.96it/s][A | |
| 33%|███▎ | 64/193 [00:05<00:10, 12.49it/s][A | |
| 34%|███▍ | 66/193 [00:05<00:09, 12.73it/s][A | |
| 35%|███▌ | 68/193 [00:05<00:10, 12.26it/s][A | |
| 36%|███▋ | 70/193 [00:05<00:10, 11.89it/s][A | |
| 37%|███▋ | 72/193 [00:05<00:09, 12.75it/s][A | |
| 38%|███▊ | 74/193 [00:06<00:09, 12.53it/s][A | |
| 39%|███▉ | 76/193 [00:06<00:09, 11.82it/s][A | |
| 40%|████ | 78/193 [00:06<00:09, 12.65it/s][A | |
| 41%|████▏ | 80/193 [00:06<00:09, 12.49it/s][A | |
| 42%|████▏ | 82/193 [00:06<00:08, 12.62it/s][A | |
| 44%|████▎ | 84/193 [00:06<00:08, 12.46it/s][A | |
| 45%|████▍ | 86/193 [00:07<00:07, 13.48it/s][A | |
| 46%|████▌ | 88/193 [00:07<00:08, 12.88it/s][A | |
| 47%|████▋ | 90/193 [00:07<00:08, 12.07it/s][A | |
| 48%|████▊ | 92/193 [00:07<00:08, 12.60it/s][A | |
| 49%|████▊ | 94/193 [00:07<00:08, 12.21it/s][A | |
| 50%|████▉ | 96/193 [00:07<00:07, 13.58it/s][A | |
| 51%|█████ | 98/193 [00:08<00:07, 12.75it/s][A | |
| 52%|█████▏ | 100/193 [00:08<00:07, 12.94it/s][A | |
| 53%|█████▎ | 102/193 [00:08<00:07, 12.25it/s][A | |
| 54%|█████▍ | 104/193 [00:08<00:07, 12.42it/s][A | |
| 55%|█████▍ | 106/193 [00:08<00:06, 13.19it/s][A | |
| 56%|█████▌ | 108/193 [00:08<00:06, 12.38it/s][A | |
| 57%|█████▋ | 110/193 [00:09<00:07, 11.69it/s][A | |
| 58%|█████▊ | 112/193 [00:09<00:06, 12.61it/s][A | |
| 59%|█████▉ | 114/193 [00:09<00:06, 12.29it/s][A | |
| 60%|██████ | 116/193 [00:09<00:06, 12.17it/s][A | |
| 61%|██████ | 118/193 [00:09<00:05, 12.74it/s][A | |
| 62%|██████▏ | 120/193 [00:09<00:06, 12.11it/s][A | |
| 63%|██████▎ | 122/193 [00:09<00:05, 12.83it/s][A | |
| 64%|██████▍ | 124/193 [00:10<00:05, 12.53it/s][A | |
| 65%|██████▌ | 126/193 [00:10<00:05, 12.25it/s][A | |
| 66%|██████▋ | 128/193 [00:10<00:05, 12.78it/s][A | |
| 67%|██████▋ | 130/193 [00:10<00:05, 12.38it/s][A | |
| 68%|██████▊ | 132/193 [00:10<00:04, 13.21it/s][A | |
| 69%|██████▉ | 134/193 [00:10<00:04, 13.63it/s][A | |
| 70%|███████ | 136/193 [00:11<00:04, 13.35it/s][A | |
| 72%|███████▏ | 138/193 [00:11<00:04, 13.32it/s][A | |
| 73%|███████▎ | 140/193 [00:11<00:04, 12.62it/s][A | |
| 74%|███████▎ | 142/193 [00:11<00:04, 12.07it/s][A | |
| 75%|███████▍ | 144/193 [00:11<00:04, 12.05it/s][A | |
| 76%|███████▌ | 146/193 [00:11<00:03, 12.37it/s][A | |
| 77%|███████▋ | 148/193 [00:12<00:03, 12.33it/s][A | |
| 78%|███████▊ | 150/193 [00:12<00:03, 12.32it/s][A | |
| 79%|███████▉ | 152/193 [00:12<00:03, 12.69it/s][A | |
| 80%|███████▉ | 154/193 [00:12<00:03, 12.02it/s][A | |
| 81%|████████ | 156/193 [00:12<00:03, 12.17it/s][A | |
| 82%|████████▏ | 158/193 [00:12<00:02, 12.41it/s][A | |
| 83%|████████▎ | 160/193 [00:12<00:02, 13.41it/s][A | |
| 84%|████████▍ | 162/193 [00:13<00:02, 13.03it/s][A | |
| 85%|████████▍ | 164/193 [00:13<00:02, 13.93it/s][A | |
| 86%|████████▌ | 166/193 [00:13<00:02, 12.54it/s][A | |
| 87%|████████▋ | 168/193 [00:13<00:01, 13.20it/s][A | |
| 88%|████████▊ | 170/193 [00:13<00:01, 12.27it/s][A | |
| 89%|████████▉ | 172/193 [00:13<00:01, 12.13it/s][A | |
| 90%|█████████ | 174/193 [00:14<00:01, 13.06it/s][A | |
| 91%|█████████ | 176/193 [00:14<00:01, 12.03it/s][A | |
| 92%|█████████▏| 178/193 [00:14<00:01, 11.88it/s][A | |
| 93%|█████████▎| 180/193 [00:14<00:01, 12.43it/s][A | |
| 94%|█████████▍| 182/193 [00:14<00:00, 11.86it/s][A | |
| 95%|█████████▌| 184/193 [00:14<00:00, 11.74it/s][A | |
| 96%|█████████▋| 186/193 [00:15<00:00, 13.11it/s][A | |
| 97%|█████████▋| 188/193 [00:15<00:00, 12.10it/s][A | |
| 98%|█████████▊| 190/193 [00:15<00:00, 11.87it/s][A | |
| 99%|█████████▉| 192/193 [00:15<00:00, 12.15it/s][A | |
| [A{'eval_loss': 0.5008335113525391, 'eval_followed_precision': 0.7570776255707763, 'eval_followed_recall': 0.7963496637848223, 'eval_followed_f1': 0.7762172284644194, 'eval_followed_support': 1041, 'eval_violated_precision': 0.7764044943820225, 'eval_violated_recall': 0.7153209109730849, 'eval_violated_f1': 0.7446120689655172, 'eval_violated_support': 966, 'eval_not_applicable_precision': 0.8761467889908257, 'eval_not_applicable_recall': 0.8941947565543071, 'eval_not_applicable_f1': 0.8850787766450418, 'eval_not_applicable_support': 1068, 'eval_accuracy': 0.8048780487804879, 'eval_macro_f1': 0.8019693580249928, 'eval_runtime': 16.0687, 'eval_samples_per_second': 191.366, 'eval_steps_per_second': 12.011, 'epoch': 1.13} | |
| 75%|███████▌ | 474/632 [05:33<02:09, 1.22it/s] | |
| 100%|██████████| 193/193 [00:15<00:00, 12.15it/s][A | |
| [A 75%|███████▌ | 475/632 [05:34<14:36, 5.58s/it] 75%|███████▌ | 476/632 [05:35<10:37, 4.09s/it] 75%|███████▌ | 477/632 [05:35<07:50, 3.03s/it] 76%|███████▌ | 478/632 [05:36<06:03, 2.36s/it] 76%|███████▌ | 479/632 [05:37<04:52, 1.91s/it] 76%|███████▌ | 480/632 [05:37<03:47, 1.50s/it] {'loss': 1.4849, 'grad_norm': 11.591279983520508, 'learning_rate': 5.1000000000000006e-05, 'epoch': 1.14} | |
| 76%|███████▌ | 480/632 [05:37<03:47, 1.50s/it] 76%|███████▌ | 481/632 [05:38<03:12, 1.27s/it] 76%|███████▋ | 482/632 [05:39<02:41, 1.07s/it] 76%|███████▋ | 483/632 [05:39<02:19, 1.07it/s] 77%|███████▋ | 484/632 [05:40<02:02, 1.21it/s] 77%|███████▋ | 485/632 [05:40<01:50, 1.33it/s] 77%|███████▋ | 486/632 [05:41<01:39, 1.47it/s] 77%|███████▋ | 487/632 [05:42<01:34, 1.53it/s] 77%|███████▋ | 488/632 [05:42<01:27, 1.64it/s] 77%|███████▋ | 489/632 [05:43<01:27, 1.63it/s] 78%|███████▊ | 490/632 [05:43<01:30, 1.58it/s] {'loss': 1.3781, 'grad_norm': 8.697712898254395, 'learning_rate': 4.766666666666667e-05, 'epoch': 1.16} | |
| 78%|███████▊ | 490/632 [05:43<01:30, 1.58it/s] 78%|███████▊ | 491/632 [05:44<01:24, 1.67it/s] 78%|███████▊ | 492/632 [05:44<01:23, 1.67it/s] 78%|███████▊ | 493/632 [05:45<01:23, 1.66it/s] 78%|███████▊ | 494/632 [05:46<01:17, 1.77it/s] 78%|███████▊ | 495/632 [05:46<01:18, 1.75it/s] 78%|███████▊ | 496/632 [05:47<01:19, 1.71it/s] 79%|███████▊ | 497/632 [05:47<01:19, 1.69it/s] 79%|███████▉ | 498/632 [05:48<01:27, 1.53it/s] 79%|███████▉ | 499/632 [05:49<01:25, 1.55it/s] 79%|███████▉ | 500/632 [05:49<01:20, 1.64it/s] {'loss': 1.6073, 'grad_norm': 4.699001312255859, 'learning_rate': 4.433333333333334e-05, 'epoch': 1.19} | |
| 79%|███████▉ | 500/632 [05:49<01:20, 1.64it/s] 79%|███████▉ | 501/632 [05:50<01:17, 1.69it/s] 79%|███████▉ | 502/632 [05:51<01:23, 1.56it/s] 80%|███████▉ | 503/632 [05:51<01:20, 1.59it/s] 80%|███████▉ | 504/632 [05:52<01:18, 1.62it/s] 80%|███████▉ | 505/632 [05:52<01:16, 1.66it/s] 80%|████████ | 506/632 [05:53<01:13, 1.71it/s] 80%|████████ | 507/632 [05:53<01:10, 1.76it/s] 80%|████████ | 508/632 [05:54<01:12, 1.71it/s] 81%|████████ | 509/632 [05:55<01:08, 1.79it/s] 81%|████████ | 510/632 [05:55<01:13, 1.66it/s] {'loss': 1.3996, 'grad_norm': 10.348775863647461, 'learning_rate': 4.1e-05, 'epoch': 1.21} | |
| 81%|████████ | 510/632 [05:55<01:13, 1.66it/s] 81%|████████ | 511/632 [05:56<01:19, 1.52it/s] 81%|████████ | 512/632 [05:57<01:14, 1.61it/s] 81%|████████ | 513/632 [05:57<01:15, 1.58it/s] 81%|████████▏ | 514/632 [05:58<01:13, 1.61it/s] 81%|████████▏ | 515/632 [05:59<01:14, 1.57it/s] 82%|████████▏ | 516/632 [05:59<01:13, 1.57it/s] 82%|████████▏ | 517/632 [06:00<01:08, 1.69it/s] 82%|████████▏ | 518/632 [06:00<01:05, 1.75it/s] 82%|████████▏ | 519/632 [06:01<01:07, 1.67it/s] 82%|████████▏ | 520/632 [06:01<01:02, 1.78it/s] {'loss': 1.2911, 'grad_norm': 10.988567352294922, 'learning_rate': 3.766666666666667e-05, 'epoch': 1.24} | |
| 82%|████████▏ | 520/632 [06:01<01:02, 1.78it/s] 82%|████████▏ | 521/632 [06:02<01:00, 1.83it/s] 83%|████████▎ | 522/632 [06:02<00:57, 1.90it/s] 83%|████████▎ | 523/632 [06:03<01:00, 1.80it/s] 83%|████████▎ | 524/632 [06:04<01:04, 1.67it/s] 83%|████████▎ | 525/632 [06:04<01:04, 1.65it/s] 83%|████████▎ | 526/632 [06:05<01:04, 1.64it/s] 83%|████████▎ | 527/632 [06:05<01:01, 1.72it/s] 84%|████████▎ | 528/632 [06:06<01:01, 1.70it/s] 84%|████████▎ | 529/632 [06:07<00:57, 1.78it/s] 84%|████████▍ | 530/632 [06:07<00:56, 1.80it/s] {'loss': 1.3584, 'grad_norm': 6.3393731117248535, 'learning_rate': 3.433333333333333e-05, 'epoch': 1.26} | |
| 84%|████████▍ | 530/632 [06:07<00:56, 1.80it/s] 84%|████████▍ | 531/632 [06:08<00:54, 1.84it/s] 84%|████████▍ | 532/632 [06:08<00:55, 1.79it/s] 84%|████████▍ | 533/632 [06:09<00:54, 1.80it/s] 84%|████████▍ | 534/632 [06:09<00:52, 1.85it/s] 85%|████████▍ | 535/632 [06:10<01:04, 1.50it/s] 85%|████████▍ | 536/632 [06:11<01:03, 1.52it/s] 85%|████████▍ | 537/632 [06:12<01:05, 1.45it/s] 85%|████████▌ | 538/632 [06:12<01:02, 1.49it/s] 85%|████████▌ | 539/632 [06:13<00:59, 1.57it/s] 85%|████████▌ | 540/632 [06:13<00:54, 1.69it/s] {'loss': 1.2478, 'grad_norm': 8.027005195617676, 'learning_rate': 3.1e-05, 'epoch': 1.28} | |
| 85%|████████▌ | 540/632 [06:13<00:54, 1.69it/s] 86%|████████▌ | 541/632 [06:14<00:52, 1.74it/s] 86%|████████▌ | 542/632 [06:14<00:50, 1.78it/s] 86%|████████▌ | 543/632 [06:15<00:52, 1.70it/s] 86%|████████▌ | 544/632 [06:15<00:49, 1.78it/s] 86%|████████▌ | 545/632 [06:16<00:52, 1.65it/s] 86%|████████▋ | 546/632 [06:17<00:50, 1.70it/s] 87%|████████▋ | 547/632 [06:17<00:52, 1.61it/s] 87%|████████▋ | 548/632 [06:18<00:51, 1.64it/s] 87%|████████▋ | 549/632 [06:18<00:46, 1.78it/s] 87%|████████▋ | 550/632 [06:19<00:48, 1.69it/s] {'loss': 1.5079, 'grad_norm': 12.042950630187988, 'learning_rate': 2.7666666666666667e-05, 'epoch': 1.31} | |
| 87%|████████▋ | 550/632 [06:19<00:48, 1.69it/s] 87%|████████▋ | 551/632 [06:20<00:46, 1.74it/s] 87%|████████▋ | 552/632 [06:20<00:44, 1.79it/s] 88%|████████▊ | 553/632 [06:21<00:44, 1.76it/s] 88%|████████▊ | 554/632 [06:21<00:42, 1.86it/s] 88%|████████▊ | 555/632 [06:22<00:45, 1.71it/s] 88%|████████▊ | 556/632 [06:22<00:42, 1.78it/s] 88%|████████▊ | 557/632 [06:23<00:41, 1.79it/s] 88%|████████▊ | 558/632 [06:24<00:42, 1.73it/s] 88%|████████▊ | 559/632 [06:24<00:42, 1.71it/s] 89%|████████▊ | 560/632 [06:25<00:41, 1.74it/s] {'loss': 1.468, 'grad_norm': 4.875816822052002, 'learning_rate': 2.4333333333333336e-05, 'epoch': 1.33} | |
| 89%|████████▊ | 560/632 [06:25<00:41, 1.74it/s] 89%|████████▉ | 561/632 [06:25<00:41, 1.70it/s] 89%|████████▉ | 562/632 [06:26<00:40, 1.71it/s] 89%|████████▉ | 563/632 [06:27<00:40, 1.70it/s] 89%|████████▉ | 564/632 [06:27<00:40, 1.66it/s] 89%|████████▉ | 565/632 [06:28<00:39, 1.69it/s] 90%|████████▉ | 566/632 [06:28<00:38, 1.71it/s] 90%|████████▉ | 567/632 [06:29<00:36, 1.77it/s] 90%|████████▉ | 568/632 [06:29<00:37, 1.69it/s] 90%|█████████ | 569/632 [06:30<00:35, 1.78it/s] 90%|█████████ | 570/632 [06:31<00:37, 1.63it/s] {'loss': 1.3236, 'grad_norm': 5.8759636878967285, 'learning_rate': 2.1e-05, 'epoch': 1.35} | |
| 90%|█████████ | 570/632 [06:31<00:37, 1.63it/s] 90%|█████████ | 571/632 [06:31<00:38, 1.60it/s] 91%|█████████ | 572/632 [06:32<00:38, 1.56it/s] 91%|█████████ | 573/632 [06:33<00:37, 1.59it/s] 91%|█████████ | 574/632 [06:33<00:34, 1.69it/s] 91%|█████████ | 575/632 [06:34<00:32, 1.75it/s] 91%|█████████ | 576/632 [06:34<00:31, 1.78it/s] 91%|█████████▏| 577/632 [06:35<00:32, 1.71it/s] 91%|█████████▏| 578/632 [06:35<00:30, 1.78it/s] 92%|█████████▏| 579/632 [06:36<00:30, 1.75it/s] 92%|█████████▏| 580/632 [06:37<00:29, 1.75it/s] {'loss': 1.3144, 'grad_norm': 6.194520950317383, 'learning_rate': 1.7666666666666668e-05, 'epoch': 1.38} | |
| 92%|█████████▏| 580/632 [06:37<00:29, 1.75it/s] 92%|█████████▏| 581/632 [06:37<00:28, 1.77it/s] 92%|█████████▏| 582/632 [06:38<00:27, 1.84it/s] 92%|█████████▏| 583/632 [06:38<00:27, 1.80it/s] 92%|█████████▏| 584/632 [06:39<00:27, 1.74it/s] 93%|█████████▎| 585/632 [06:39<00:27, 1.73it/s] 93%|█████████▎| 586/632 [06:40<00:24, 1.85it/s] 93%|█████████▎| 587/632 [06:40<00:24, 1.87it/s] 93%|█████████▎| 588/632 [06:41<00:26, 1.64it/s] 93%|█████████▎| 589/632 [06:42<00:25, 1.66it/s] 93%|█████████▎| 590/632 [06:42<00:25, 1.66it/s] {'loss': 1.2282, 'grad_norm': 5.741563320159912, 'learning_rate': 1.4333333333333334e-05, 'epoch': 1.4} | |
| 93%|█████████▎| 590/632 [06:42<00:25, 1.66it/s] 94%|█████████▎| 591/632 [06:43<00:24, 1.70it/s] 94%|█████████▎| 592/632 [06:43<00:23, 1.72it/s] 94%|█████████▍| 593/632 [06:44<00:23, 1.65it/s] 94%|█████████▍| 594/632 [06:45<00:22, 1.67it/s] 94%|█████████▍| 595/632 [06:46<00:24, 1.48it/s] 94%|█████████▍| 596/632 [06:46<00:21, 1.67it/s] 94%|█████████▍| 597/632 [06:46<00:20, 1.73it/s] 95%|█████████▍| 598/632 [06:47<00:18, 1.83it/s] 95%|█████████▍| 599/632 [06:47<00:17, 1.84it/s] 95%|█████████▍| 600/632 [06:48<00:17, 1.87it/s] {'loss': 1.4673, 'grad_norm': 5.4889607429504395, 'learning_rate': 1.1000000000000001e-05, 'epoch': 1.43} | |
| 95%|█████████▍| 600/632 [06:48<00:17, 1.87it/s] 95%|█████████▌| 601/632 [06:49<00:17, 1.78it/s] 95%|█████████▌| 602/632 [06:49<00:16, 1.77it/s] 95%|█████████▌| 603/632 [06:50<00:16, 1.78it/s] 96%|█████████▌| 604/632 [06:50<00:15, 1.84it/s] 96%|█████████▌| 605/632 [06:51<00:15, 1.72it/s] 96%|█████████▌| 606/632 [06:52<00:15, 1.68it/s] 96%|█████████▌| 607/632 [06:52<00:13, 1.81it/s] 96%|█████████▌| 608/632 [06:53<00:13, 1.75it/s] 96%|█████████▋| 609/632 [06:53<00:14, 1.63it/s] 97%|█████████▋| 610/632 [06:54<00:13, 1.59it/s] {'loss': 1.4056, 'grad_norm': 7.171555042266846, 'learning_rate': 7.666666666666667e-06, 'epoch': 1.45} | |
| 97%|█████████▋| 610/632 [06:54<00:13, 1.59it/s] 97%|█████████▋| 611/632 [06:55<00:12, 1.62it/s] 97%|█████████▋| 612/632 [06:55<00:12, 1.65it/s] 97%|█████████▋| 613/632 [06:56<00:10, 1.76it/s] 97%|█████████▋| 614/632 [06:56<00:10, 1.80it/s] 97%|█████████▋| 615/632 [06:57<00:10, 1.68it/s] 97%|█████████▋| 616/632 [06:57<00:09, 1.70it/s] 98%|█████████▊| 617/632 [06:58<00:08, 1.83it/s] 98%|█████████▊| 618/632 [06:58<00:07, 1.77it/s] 98%|█████████▊| 619/632 [06:59<00:07, 1.84it/s] 98%|█████████▊| 620/632 [07:00<00:06, 1.83it/s] {'loss': 1.3506, 'grad_norm': 9.817628860473633, 'learning_rate': 4.333333333333334e-06, 'epoch': 1.47} | |
| 98%|█████████▊| 620/632 [07:00<00:06, 1.83it/s] 98%|█████████▊| 621/632 [07:00<00:05, 1.88it/s] 98%|█████████▊| 622/632 [07:01<00:05, 1.76it/s] 99%|█████████▊| 623/632 [07:01<00:05, 1.68it/s] 99%|█████████▊| 624/632 [07:02<00:04, 1.76it/s] 99%|█████████▉| 625/632 [07:02<00:04, 1.74it/s] 99%|█████████▉| 626/632 [07:03<00:03, 1.77it/s] 99%|█████████▉| 627/632 [07:04<00:02, 1.75it/s] 99%|█████████▉| 628/632 [07:04<00:02, 1.89it/s] 100%|█████████▉| 629/632 [07:05<00:01, 1.77it/s] 100%|█████████▉| 630/632 [07:05<00:01, 1.74it/s] {'loss': 1.3637, 'grad_norm': 7.710325241088867, 'learning_rate': 1.0000000000000002e-06, 'epoch': 1.5} | |
| 100%|█████████▉| 630/632 [07:05<00:01, 1.74it/s] 100%|█████████▉| 631/632 [07:06<00:00, 1.62it/s]Saved adapter checkpoint checkpoints/modernbert-large-30k/checkpoint-4of4-step632 | |
| 100%|██████████| 632/632 [07:07<00:00, 1.25it/s] | |
| 0%| | 0/193 [00:00<?, ?it/s][A | |
| 1%| | 2/193 [00:00<00:19, 9.76it/s][A | |
| 2%|▏ | 3/193 [00:00<00:26, 7.11it/s][A | |
| 3%|▎ | 5/193 [00:00<00:18, 9.99it/s][A | |
| 4%|▎ | 7/193 [00:00<00:16, 11.58it/s][A | |
| 5%|▍ | 9/193 [00:00<00:17, 10.51it/s][A | |
| 6%|▌ | 11/193 [00:01<00:16, 10.89it/s][A | |
| 7%|▋ | 13/193 [00:01<00:17, 10.18it/s][A | |
| 8%|▊ | 16/193 [00:01<00:14, 12.02it/s][A | |
| 9%|▉ | 18/193 [00:01<00:13, 12.56it/s][A | |
| 10%|█ | 20/193 [00:01<00:14, 11.72it/s][A | |
| 11%|█▏ | 22/193 [00:01<00:14, 11.90it/s][A | |
| 12%|█▏ | 24/193 [00:02<00:14, 11.47it/s][A | |
| 13%|█▎ | 26/193 [00:02<00:13, 11.95it/s][A | |
| 15%|█▍ | 28/193 [00:02<00:13, 12.29it/s][A | |
| 16%|█▌ | 30/193 [00:02<00:13, 11.74it/s][A | |
| 17%|█▋ | 32/193 [00:02<00:13, 11.78it/s][A | |
| 18%|█▊ | 34/193 [00:02<00:12, 12.31it/s][A | |
| 19%|█▊ | 36/193 [00:03<00:12, 12.90it/s][A | |
| 20%|█▉ | 38/193 [00:03<00:12, 12.44it/s][A | |
| 21%|██ | 40/193 [00:03<00:12, 11.81it/s][A | |
| 22%|██▏ | 42/193 [00:03<00:11, 12.98it/s][A | |
| 23%|██▎ | 44/193 [00:03<00:11, 12.42it/s][A | |
| 24%|██▍ | 46/193 [00:03<00:11, 12.61it/s][A | |
| 25%|██▍ | 48/193 [00:04<00:11, 12.64it/s][A | |
| 26%|██▌ | 50/193 [00:04<00:11, 11.96it/s][A | |
| 27%|██▋ | 52/193 [00:04<00:10, 12.86it/s][A | |
| 28%|██▊ | 54/193 [00:04<00:11, 11.83it/s][A | |
| 29%|██▉ | 56/193 [00:04<00:11, 11.79it/s][A | |
| 30%|███ | 58/193 [00:04<00:10, 12.65it/s][A | |
| 31%|███ | 60/193 [00:05<00:11, 11.96it/s][A | |
| 32%|███▏ | 62/193 [00:05<00:10, 12.79it/s][A | |
| 33%|███▎ | 64/193 [00:05<00:10, 12.62it/s][A | |
| 34%|███▍ | 66/193 [00:05<00:10, 11.89it/s][A | |
| 35%|███▌ | 68/193 [00:05<00:10, 12.06it/s][A | |
| 36%|███▋ | 70/193 [00:05<00:09, 12.36it/s][A | |
| 37%|███▋ | 72/193 [00:06<00:09, 13.11it/s][A | |
| 38%|███▊ | 74/193 [00:06<00:09, 12.84it/s][A | |
| 39%|███▉ | 76/193 [00:06<00:10, 11.63it/s][A | |
| 40%|████ | 78/193 [00:06<00:09, 12.77it/s][A | |
| 41%|████▏ | 80/193 [00:06<00:08, 12.57it/s][A | |
| 42%|████▏ | 82/193 [00:06<00:09, 11.75it/s][A | |
| 44%|████▎ | 84/193 [00:06<00:08, 12.71it/s][A | |
| 45%|████▍ | 86/193 [00:07<00:08, 12.20it/s][A | |
| 46%|████▌ | 88/193 [00:07<00:07, 13.36it/s][A | |
| 47%|████▋ | 90/193 [00:07<00:08, 12.48it/s][A | |
| 48%|████▊ | 92/193 [00:07<00:08, 11.56it/s][A | |
| 49%|████▊ | 94/193 [00:07<00:07, 12.45it/s][A | |
| 50%|████▉ | 96/193 [00:07<00:07, 12.61it/s][A | |
| 51%|█████ | 98/193 [00:08<00:07, 13.39it/s][A | |
| 52%|█████▏ | 100/193 [00:08<00:07, 12.28it/s][A | |
| 53%|█████▎ | 102/193 [00:08<00:07, 12.86it/s][A | |
| 54%|█████▍ | 104/193 [00:08<00:06, 12.77it/s][A | |
| 55%|█████▍ | 106/193 [00:08<00:07, 12.20it/s][A | |
| 56%|█████▌ | 108/193 [00:08<00:06, 13.08it/s][A | |
| 57%|█████▋ | 110/193 [00:09<00:06, 12.50it/s][A | |
| 58%|█████▊ | 112/193 [00:09<00:06, 11.59it/s][A | |
| 59%|█████▉ | 114/193 [00:09<00:06, 12.65it/s][A | |
| 60%|██████ | 116/193 [00:09<00:06, 11.46it/s][A | |
| 61%|██████ | 118/193 [00:09<00:06, 11.89it/s][A | |
| 62%|██████▏ | 120/193 [00:09<00:05, 12.58it/s][A | |
| 63%|██████▎ | 122/193 [00:10<00:05, 12.21it/s][A | |
| 64%|██████▍ | 124/193 [00:10<00:05, 13.61it/s][A | |
| 65%|██████▌ | 126/193 [00:10<00:05, 11.96it/s][A | |
| 66%|██████▋ | 128/193 [00:10<00:05, 11.93it/s][A | |
| 67%|██████▋ | 130/193 [00:10<00:04, 13.13it/s][A | |
| 68%|██████▊ | 132/193 [00:10<00:04, 13.72it/s][A | |
| 69%|██████▉ | 134/193 [00:10<00:04, 13.00it/s][A | |
| 70%|███████ | 136/193 [00:11<00:04, 12.31it/s][A | |
| 72%|███████▏ | 138/193 [00:11<00:04, 12.98it/s][A | |
| 73%|███████▎ | 140/193 [00:11<00:04, 11.87it/s][A | |
| 74%|███████▎ | 142/193 [00:11<00:04, 12.30it/s][A | |
| 75%|███████▍ | 144/193 [00:11<00:03, 12.76it/s][A | |
| 76%|███████▌ | 146/193 [00:11<00:03, 11.96it/s][A | |
| 77%|███████▋ | 148/193 [00:12<00:03, 11.99it/s][A | |
| 78%|███████▊ | 150/193 [00:12<00:03, 12.47it/s][A | |
| 79%|███████▉ | 152/193 [00:12<00:03, 12.47it/s][A | |
| 80%|███████▉ | 154/193 [00:12<00:02, 13.29it/s][A | |
| 81%|████████ | 156/193 [00:12<00:02, 12.35it/s][A | |
| 82%|████████▏ | 158/193 [00:12<00:02, 13.67it/s][A | |
| 83%|████████▎ | 160/193 [00:13<00:02, 12.04it/s][A | |
| 84%|████████▍ | 162/193 [00:13<00:02, 12.67it/s][A | |
| 85%|████████▍ | 164/193 [00:13<00:02, 12.75it/s][A | |
| 86%|████████▌ | 166/193 [00:13<00:02, 11.71it/s][A | |
| 87%|████████▋ | 168/193 [00:13<00:01, 12.55it/s][A | |
| 88%|████████▊ | 170/193 [00:13<00:01, 12.51it/s][A | |
| 89%|████████▉ | 172/193 [00:14<00:01, 11.92it/s][A | |
| 90%|█████████ | 174/193 [00:14<00:01, 10.73it/s][A | |
| 91%|█████████ | 176/193 [00:14<00:01, 11.93it/s][A | |
| 92%|█████████▏| 178/193 [00:14<00:01, 13.46it/s][A | |
| 93%|█████████▎| 180/193 [00:14<00:00, 13.64it/s][A | |
| 94%|█████████▍| 182/193 [00:14<00:00, 13.32it/s][A | |
| 95%|█████████▌| 184/193 [00:14<00:00, 13.38it/s][A | |
| 96%|█████████▋| 186/193 [00:15<00:00, 13.27it/s][A | |
| 97%|█████████▋| 188/193 [00:15<00:00, 13.64it/s][A | |
| 98%|█████████▊| 190/193 [00:15<00:00, 12.75it/s][A | |
| 99%|█████████▉| 192/193 [00:15<00:00, 13.41it/s][A | |
| [A{'eval_loss': 0.5091826915740967, 'eval_followed_precision': 0.7833333333333333, 'eval_followed_recall': 0.7675312199807877, 'eval_followed_f1': 0.7753517709849588, 'eval_followed_support': 1041, 'eval_violated_precision': 0.7520242914979757, 'eval_violated_recall': 0.7691511387163561, 'eval_violated_f1': 0.7604912998976459, 'eval_violated_support': 966, 'eval_not_applicable_precision': 0.895032802249297, 'eval_not_applicable_recall': 0.8941947565543071, 'eval_not_applicable_f1': 0.8946135831381733, 'eval_not_applicable_support': 1068, 'eval_accuracy': 0.8120325203252032, 'eval_macro_f1': 0.8101522180069259, 'eval_runtime': 16.0027, 'eval_samples_per_second': 192.155, 'eval_steps_per_second': 12.06, 'epoch': 1.5} | |
| 100%|██████████| 632/632 [07:23<00:00, 1.25it/s] | |
| 100%|██████████| 193/193 [00:15<00:00, 13.41it/s][A | |
| [A {'train_runtime': 443.7181, 'train_samples_per_second': 91.021, 'train_steps_per_second': 1.424, 'train_loss': 2.1310453241384484, 'epoch': 1.5} | |
| 100%|██████████| 632/632 [07:23<00:00, 1.25it/s] 100%|██████████| 632/632 [07:23<00:00, 1.42it/s] | |
| 0%| | 0/193 [00:00<?, ?it/s] 1%| | 2/193 [00:00<00:19, 9.81it/s] 2%|▏ | 3/193 [00:00<00:27, 7.01it/s] 3%|▎ | 5/193 [00:00<00:18, 9.94it/s] 4%|▎ | 7/193 [00:00<00:15, 12.11it/s] 5%|▍ | 9/193 [00:00<00:14, 12.74it/s] 6%|▌ | 11/193 [00:00<00:14, 12.75it/s] 7%|▋ | 13/193 [00:01<00:15, 11.95it/s] 8%|▊ | 15/193 [00:01<00:13, 13.13it/s] 9%|▉ | 17/193 [00:01<00:13, 13.18it/s] 10%|▉ | 19/193 [00:01<00:14, 11.97it/s] 11%|█ | 21/193 [00:01<00:14, 12.21it/s] 12%|█▏ | 23/193 [00:01<00:14, 11.34it/s] 13%|█▎ | 25/193 [00:02<00:12, 12.94it/s] 14%|█▍ | 27/193 [00:02<00:12, 12.96it/s] 15%|█▌ | 29/193 [00:02<00:12, 12.62it/s] 16%|█▌ | 31/193 [00:02<00:12, 12.69it/s] 17%|█▋ | 33/193 [00:02<00:13, 12.28it/s] 18%|█▊ | 35/193 [00:02<00:12, 13.13it/s] 19%|█▉ | 37/193 [00:02<00:11, 13.98it/s] 20%|██ | 39/193 [00:03<00:11, 13.11it/s] 21%|██ | 41/193 [00:03<00:11, 12.68it/s] 22%|██▏ | 43/193 [00:03<00:11, 13.13it/s] 23%|██▎ | 45/193 [00:03<00:12, 12.18it/s] 24%|██▍ | 47/193 [00:03<00:11, 12.27it/s] 25%|██▌ | 49/193 [00:03<00:11, 12.46it/s] 26%|██▋ | 51/193 [00:04<00:11, 12.19it/s] 27%|██▋ | 53/193 [00:04<00:10, 13.21it/s] 28%|██▊ | 55/193 [00:04<00:11, 12.29it/s] 30%|██▉ | 57/193 [00:04<00:10, 12.78it/s] 31%|███ | 59/193 [00:04<00:10, 12.39it/s] 32%|███▏ | 61/193 [00:04<00:10, 12.21it/s] 33%|███▎ | 63/193 [00:05<00:09, 13.27it/s] 34%|███▎ | 65/193 [00:05<00:10, 12.17it/s] 35%|███▍ | 67/193 [00:05<00:10, 12.33it/s] 36%|███▌ | 69/193 [00:05<00:10, 11.65it/s] 37%|███▋ | 71/193 [00:05<00:10, 11.37it/s] 38%|███▊ | 74/193 [00:05<00:09, 13.07it/s] 39%|███▉ | 76/193 [00:06<00:10, 11.36it/s] 40%|████ | 78/193 [00:06<00:09, 12.15it/s] 41%|████▏ | 80/193 [00:06<00:08, 12.76it/s] 42%|████▏ | 82/193 [00:06<00:08, 13.76it/s] 44%|████▎ | 84/193 [00:06<00:08, 12.26it/s] 45%|████▍ | 86/193 [00:06<00:08, 13.08it/s] 46%|████▌ | 88/193 [00:07<00:08, 12.96it/s] 47%|████▋ | 90/193 [00:07<00:07, 13.79it/s] 48%|████▊ | 92/193 [00:07<00:09, 10.85it/s] 49%|████▊ | 94/193 [00:07<00:08, 11.96it/s] 50%|█████ | 97/193 [00:07<00:06, 14.31it/s] 51%|█████▏ | 99/193 [00:07<00:07, 13.23it/s] 52%|█████▏ | 101/193 [00:08<00:07, 12.50it/s] 53%|█████▎ | 103/193 [00:08<00:06, 13.25it/s] 54%|█████▍ | 105/193 [00:08<00:07, 12.27it/s] 55%|█████▌ | 107/193 [00:08<00:07, 12.20it/s] 56%|█████▋ | 109/193 [00:08<00:06, 13.53it/s] 58%|█████▊ | 112/193 [00:08<00:05, 15.55it/s] 60%|█████▉ | 115/193 [00:09<00:05, 14.72it/s] 61%|██████ | 117/193 [00:09<00:05, 15.07it/s] 62%|██████▏ | 119/193 [00:09<00:04, 15.59it/s] 63%|██████▎ | 121/193 [00:09<00:04, 15.68it/s] 64%|██████▎ | 123/193 [00:09<00:04, 15.14it/s] 65%|██████▍ | 125/193 [00:09<00:04, 16.12it/s] 66%|██████▌ | 127/193 [00:09<00:04, 14.43it/s] 67%|██████▋ | 129/193 [00:10<00:04, 13.34it/s] 68%|██████▊ | 132/193 [00:10<00:03, 16.19it/s] 69%|██████▉ | 134/193 [00:10<00:03, 16.78it/s] 70%|███████ | 136/193 [00:10<00:03, 14.51it/s] 72%|███████▏ | 138/193 [00:10<00:03, 14.77it/s] 73%|███████▎ | 140/193 [00:10<00:03, 14.63it/s] 74%|███████▎ | 142/193 [00:10<00:03, 13.15it/s] 75%|███████▌ | 145/193 [00:11<00:03, 15.16it/s] 76%|███████▌ | 147/193 [00:11<00:03, 14.31it/s] 78%|███████▊ | 150/193 [00:11<00:02, 15.64it/s] 79%|███████▉ | 153/193 [00:11<00:02, 17.23it/s] 80%|████████ | 155/193 [00:11<00:02, 17.43it/s] 81%|████████▏ | 157/193 [00:11<00:02, 17.81it/s] 82%|████████▏ | 159/193 [00:11<00:02, 16.61it/s] 83%|████████▎ | 161/193 [00:12<00:02, 15.36it/s] 84%|████████▍ | 163/193 [00:12<00:02, 13.96it/s] 85%|████████▌ | 165/193 [00:12<00:02, 13.84it/s] 87%|████████▋ | 167/193 [00:12<00:02, 12.96it/s] 88%|████████▊ | 169/193 [00:12<00:01, 14.12it/s] 89%|████████▊ | 171/193 [00:12<00:01, 12.70it/s] 90%|████████▉ | 173/193 [00:13<00:01, 11.76it/s] 91%|█████████ | 175/193 [00:13<00:01, 11.79it/s] 92%|█████████▏| 177/193 [00:13<00:01, 12.29it/s] 93%|█████████▎| 179/193 [00:13<00:01, 12.48it/s] 94%|█████████▍| 181/193 [00:13<00:00, 13.35it/s] 95%|█████████▍| 183/193 [00:13<00:00, 12.21it/s] 96%|█████████▌| 185/193 [00:13<00:00, 12.91it/s] 97%|█████████▋| 187/193 [00:14<00:00, 12.63it/s] 98%|█████████▊| 189/193 [00:14<00:00, 12.94it/s] 99%|█████████▉| 191/193 [00:14<00:00, 12.45it/s] 100%|██████████| 193/193 [00:14<00:00, 11.99it/s] 100%|██████████| 193/193 [00:14<00:00, 13.16it/s] | |
| precision recall f1-score support | |
| followed 0.7833 0.7675 0.7754 1041 | |
| violated 0.7520 0.7692 0.7605 966 | |
| not_applicable 0.8950 0.8942 0.8946 1068 | |
| accuracy 0.8120 3075 | |
| macro avg 0.8101 0.8103 0.8102 3075 | |
| weighted avg 0.8123 0.8120 0.8121 3075 | |
| validation natural (582 pairs): macro F1 0.6304, violated precision 0.1828, violated recall 0.4722 | |
| validation edited (2493 pairs): macro F1 0.7933, violated precision 0.8112, violated recall 0.7806 | |
| ***** validation metrics ***** | |
| validation_accuracy = 0.812 | |
| validation_followed_f1 = 0.7754 | |
| validation_followed_precision = 0.7833 | |
| validation_followed_recall = 0.7675 | |
| validation_followed_support = 1041 | |
| validation_loss = 0.5092 | |
| validation_macro_f1 = 0.8102 | |
| validation_not_applicable_f1 = 0.8946 | |
| validation_not_applicable_precision = 0.895 | |
| validation_not_applicable_recall = 0.8942 | |
| validation_not_applicable_support = 1068 | |
| validation_runtime = 0:00:14.91 | |
| validation_samples_per_second = 206.157 | |
| validation_steps_per_second = 12.939 | |
| validation_violated_f1 = 0.7605 | |
| validation_violated_precision = 0.752 | |
| validation_violated_recall = 0.7692 | |
| validation_violated_support = 966 | |
| 0%| | 0/439 [00:00<?, ?it/s] 1%| | 3/439 [00:00<00:18, 24.07it/s] 1%|▏ | 6/439 [00:00<00:34, 12.39it/s] 2%|▏ | 8/439 [00:00<00:34, 12.39it/s] 3%|▎ | 11/439 [00:00<00:27, 15.62it/s] 3%|▎ | 13/439 [00:00<00:30, 14.13it/s] 3%|▎ | 15/439 [00:01<00:27, 15.35it/s] 4%|▍ | 17/439 [00:01<00:32, 13.13it/s] 5%|▍ | 20/439 [00:01<00:25, 16.17it/s] 5%|▌ | 22/439 [00:01<00:33, 12.31it/s] 5%|▌ | 24/439 [00:01<00:30, 13.49it/s] 6%|▌ | 26/439 [00:01<00:32, 12.60it/s] 6%|▋ | 28/439 [00:02<00:30, 13.56it/s] 7%|▋ | 30/439 [00:02<00:32, 12.68it/s] 7%|▋ | 32/439 [00:02<00:29, 13.75it/s] 8%|▊ | 34/439 [00:02<00:31, 12.78it/s] 8%|▊ | 36/439 [00:02<00:29, 13.76it/s] 9%|▊ | 38/439 [00:02<00:31, 12.91it/s] 9%|▉ | 40/439 [00:02<00:29, 13.62it/s] 10%|▉ | 42/439 [00:03<00:27, 14.23it/s] 10%|█ | 44/439 [00:03<00:28, 13.75it/s] 10%|█ | 46/439 [00:03<00:27, 14.12it/s] 11%|█ | 48/439 [00:03<00:29, 13.28it/s] 11%|█▏ | 50/439 [00:03<00:28, 13.48it/s] 12%|█▏ | 52/439 [00:03<00:30, 12.73it/s] 12%|█▏ | 54/439 [00:03<00:28, 13.34it/s] 13%|█▎ | 56/439 [00:04<00:28, 13.40it/s] 13%|█▎ | 58/439 [00:04<00:30, 12.48it/s] 14%|█▎ | 60/439 [00:04<00:28, 13.53it/s] 14%|█▍ | 62/439 [00:04<00:29, 12.90it/s] 15%|█▍ | 64/439 [00:04<00:27, 13.58it/s] 15%|█▌ | 66/439 [00:04<00:28, 12.98it/s] 15%|█▌ | 68/439 [00:05<00:27, 13.43it/s] 16%|█▌ | 70/439 [00:05<00:28, 12.81it/s] 16%|█▋ | 72/439 [00:05<00:26, 13.83it/s] 17%|█▋ | 74/439 [00:05<00:27, 13.09it/s] 17%|█▋ | 76/439 [00:05<00:26, 13.74it/s] 18%|█▊ | 78/439 [00:05<00:25, 14.18it/s] 18%|█▊ | 80/439 [00:05<00:26, 13.72it/s] 19%|█▊ | 82/439 [00:06<00:24, 14.36it/s] 19%|█▉ | 84/439 [00:06<00:23, 15.00it/s] 20%|█▉ | 86/439 [00:06<00:25, 13.85it/s] 20%|██ | 88/439 [00:06<00:27, 12.67it/s] 21%|██ | 90/439 [00:06<00:25, 13.89it/s] 21%|██ | 92/439 [00:06<00:24, 14.11it/s] 22%|██▏ | 95/439 [00:06<00:21, 15.76it/s] 22%|██▏ | 97/439 [00:07<00:24, 13.73it/s] 23%|██▎ | 99/439 [00:07<00:23, 14.71it/s] 23%|██▎ | 101/439 [00:07<00:25, 13.50it/s] 23%|██▎ | 103/439 [00:07<00:23, 14.45it/s] 24%|██▍ | 105/439 [00:07<00:23, 14.49it/s] 24%|██▍ | 107/439 [00:07<00:24, 13.78it/s] 25%|██▍ | 109/439 [00:07<00:22, 14.44it/s] 25%|██▌ | 111/439 [00:08<00:24, 13.13it/s] 26%|██▌ | 114/439 [00:08<00:23, 14.08it/s] 26%|██▋ | 116/439 [00:08<00:21, 14.71it/s] 27%|██▋ | 118/439 [00:08<00:23, 13.46it/s] 27%|██▋ | 120/439 [00:08<00:22, 14.13it/s] 28%|██▊ | 122/439 [00:08<00:24, 13.12it/s] 28%|██▊ | 124/439 [00:09<00:23, 13.43it/s] 29%|██▊ | 126/439 [00:09<00:23, 13.29it/s] 29%|██▉ | 128/439 [00:09<00:22, 13.95it/s] 30%|██▉ | 130/439 [00:09<00:23, 13.16it/s] 30%|███ | 132/439 [00:09<00:21, 14.19it/s] 31%|███ | 134/439 [00:09<00:23, 12.91it/s] 31%|███ | 136/439 [00:09<00:21, 13.97it/s] 31%|███▏ | 138/439 [00:10<00:23, 12.97it/s] 32%|███▏ | 140/439 [00:10<00:21, 13.96it/s] 32%|███▏ | 142/439 [00:10<00:19, 14.88it/s] 33%|███▎ | 145/439 [00:10<00:19, 15.33it/s] 33%|███▎ | 147/439 [00:10<00:21, 13.81it/s] 34%|███▍ | 150/439 [00:10<00:17, 16.81it/s] 35%|███▍ | 152/439 [00:10<00:19, 15.09it/s] 35%|███▌ | 154/439 [00:11<00:18, 15.40it/s] 36%|███▌ | 156/439 [00:11<00:18, 15.53it/s] 36%|███▌ | 158/439 [00:11<00:19, 14.10it/s] 36%|███▋ | 160/439 [00:11<00:18, 14.81it/s] 37%|███▋ | 162/439 [00:11<00:20, 13.58it/s] 37%|███▋ | 164/439 [00:11<00:18, 14.83it/s] 38%|███▊ | 166/439 [00:11<00:18, 15.14it/s] 38%|███▊ | 168/439 [00:12<00:20, 13.50it/s] 39%|███▉ | 171/439 [00:12<00:18, 14.48it/s] 39%|███▉ | 173/439 [00:12<00:18, 14.77it/s] 40%|███▉ | 175/439 [00:12<00:19, 13.77it/s] 40%|████ | 177/439 [00:12<00:17, 14.67it/s] 41%|████ | 179/439 [00:12<00:18, 13.79it/s] 41%|████ | 181/439 [00:13<00:17, 14.41it/s] 42%|████▏ | 183/439 [00:13<00:19, 12.94it/s] 42%|████▏ | 185/439 [00:13<00:19, 13.24it/s] 43%|████▎ | 187/439 [00:13<00:19, 13.20it/s] 43%|████▎ | 189/439 [00:13<00:20, 12.40it/s] 44%|████▎ | 191/439 [00:13<00:18, 13.21it/s] 44%|████▍ | 193/439 [00:13<00:18, 13.15it/s] 44%|████▍ | 195/439 [00:14<00:19, 12.58it/s] 45%|████▍ | 197/439 [00:14<00:19, 12.31it/s] 45%|████▌ | 199/439 [00:14<00:18, 13.25it/s] 46%|████▌ | 201/439 [00:14<00:18, 12.65it/s] 46%|████▌ | 203/439 [00:14<00:17, 13.79it/s] 47%|████▋ | 205/439 [00:14<00:18, 12.65it/s] 47%|████▋ | 207/439 [00:15<00:17, 13.58it/s] 48%|████▊ | 209/439 [00:15<00:18, 12.72it/s] 48%|████▊ | 211/439 [00:15<00:17, 13.31it/s] 49%|████▊ | 213/439 [00:15<00:17, 12.89it/s] 49%|████▉ | 215/439 [00:15<00:16, 13.50it/s] 49%|████▉ | 217/439 [00:15<00:16, 13.09it/s] 50%|████▉ | 219/439 [00:15<00:15, 13.79it/s] 50%|█████ | 221/439 [00:16<00:16, 12.98it/s] 51%|█████ | 223/439 [00:16<00:15, 13.78it/s] 51%|█████▏ | 225/439 [00:16<00:14, 14.88it/s] 52%|█████▏ | 227/439 [00:16<00:13, 15.94it/s] 52%|█████▏ | 229/439 [00:16<00:14, 14.61it/s] 53%|█████▎ | 231/439 [00:16<00:13, 14.92it/s] 53%|█████▎ | 233/439 [00:16<00:15, 13.73it/s] 54%|█████▎ | 235/439 [00:17<00:14, 14.31it/s] 54%|█████▍ | 237/439 [00:17<00:15, 13.42it/s] 54%|█████▍ | 239/439 [00:17<00:14, 14.03it/s] 55%|█████▍ | 241/439 [00:17<00:14, 13.41it/s] 55%|█████▌ | 243/439 [00:17<00:13, 14.29it/s] 56%|█████▌ | 245/439 [00:17<00:12, 14.97it/s] 56%|█████▋ | 248/439 [00:17<00:12, 15.64it/s] 57%|█████▋ | 250/439 [00:18<00:13, 13.87it/s] 57%|█████▋ | 252/439 [00:18<00:13, 14.35it/s] 58%|█████▊ | 254/439 [00:18<00:13, 13.46it/s] 59%|█████▊ | 257/439 [00:18<00:10, 16.70it/s] 59%|█████▉ | 259/439 [00:18<00:12, 14.44it/s] 59%|█████▉ | 261/439 [00:18<00:11, 15.38it/s] 60%|█████▉ | 263/439 [00:18<00:11, 15.08it/s] 60%|██████ | 265/439 [00:19<00:12, 14.26it/s] 61%|██████ | 267/439 [00:19<00:11, 15.20it/s] 61%|██████▏ | 269/439 [00:19<00:12, 13.61it/s] 62%|██████▏ | 271/439 [00:19<00:11, 14.82it/s] 62%|██████▏ | 273/439 [00:19<00:11, 15.05it/s] 63%|██████▎ | 275/439 [00:19<00:11, 13.83it/s] 63%|██████▎ | 277/439 [00:19<00:10, 15.01it/s] 64%|██████▎ | 279/439 [00:20<00:10, 15.38it/s] 64%|██████▍ | 281/439 [00:20<00:11, 13.97it/s] 64%|██████▍ | 283/439 [00:20<00:10, 15.25it/s] 65%|██████▍ | 285/439 [00:20<00:11, 13.57it/s] 66%|██████▌ | 288/439 [00:20<00:08, 16.98it/s] 66%|██████▌ | 290/439 [00:20<00:10, 14.87it/s] 67%|██████▋ | 293/439 [00:20<00:08, 17.40it/s] 67%|██████▋ | 295/439 [00:21<00:09, 15.20it/s] 68%|██████▊ | 297/439 [00:21<00:09, 15.46it/s] 68%|██████▊ | 299/439 [00:21<00:08, 15.69it/s] 69%|██████▉ | 302/439 [00:21<00:08, 15.81it/s] 69%|██████▉ | 304/439 [00:21<00:09, 14.09it/s] 70%|██████▉ | 306/439 [00:21<00:09, 14.40it/s] 70%|███████ | 308/439 [00:22<00:09, 13.66it/s] 71%|███████ | 310/439 [00:22<00:09, 14.32it/s] 71%|███████▏ | 313/439 [00:22<00:08, 15.10it/s] 72%|███████▏ | 315/439 [00:22<00:07, 15.91it/s] 72%|███████▏ | 317/439 [00:22<00:08, 14.05it/s] 73%|███████▎ | 319/439 [00:22<00:08, 14.91it/s] 73%|███████▎ | 321/439 [00:22<00:07, 15.23it/s] 74%|███████▎ | 323/439 [00:23<00:08, 14.16it/s] 74%|███████▍ | 325/439 [00:23<00:07, 14.77it/s] 74%|███████▍ | 327/439 [00:23<00:07, 14.92it/s] 75%|███████▍ | 329/439 [00:23<00:07, 13.83it/s] 75%|███████▌ | 331/439 [00:23<00:08, 12.72it/s] 76%|███████▌ | 334/439 [00:23<00:07, 13.52it/s] 77%|███████▋ | 336/439 [00:24<00:08, 12.38it/s] 77%|███████▋ | 338/439 [00:24<00:07, 13.57it/s] 77%|███████▋ | 340/439 [00:24<00:07, 12.61it/s] 78%|███████▊ | 342/439 [00:24<00:07, 13.81it/s] 78%|███████▊ | 344/439 [00:24<00:07, 12.83it/s] 79%|███████▉ | 346/439 [00:24<00:06, 13.59it/s] 79%|███████▉ | 348/439 [00:24<00:07, 12.41it/s] 80%|███████▉ | 350/439 [00:25<00:06, 13.49it/s] 80%|████████ | 352/439 [00:25<00:06, 12.80it/s] 81%|████████ | 354/439 [00:25<00:07, 11.95it/s] 81%|████████ | 356/439 [00:25<00:06, 13.56it/s] 82%|████████▏ | 358/439 [00:25<00:06, 12.35it/s] 82%|████████▏ | 360/439 [00:25<00:05, 13.76it/s] 82%|████████▏ | 362/439 [00:26<00:06, 12.45it/s] 83%|████████▎ | 364/439 [00:26<00:05, 14.02it/s] 83%|████████▎ | 366/439 [00:26<00:05, 12.92it/s] 84%|████████▍ | 368/439 [00:26<00:05, 13.85it/s] 84%|████████▍ | 370/439 [00:26<00:04, 14.41it/s] 85%|████████▍ | 372/439 [00:26<00:04, 13.59it/s] 85%|████████▌ | 374/439 [00:26<00:04, 14.82it/s] 86%|████████▌ | 376/439 [00:26<00:04, 14.10it/s] 86%|████████▌ | 378/439 [00:27<00:04, 13.78it/s] 87%|████████▋ | 381/439 [00:27<00:03, 14.51it/s] 87%|████████▋ | 383/439 [00:27<00:03, 14.67it/s] 88%|████████▊ | 385/439 [00:27<00:03, 13.81it/s] 88%|████████▊ | 387/439 [00:27<00:03, 14.54it/s] 89%|████████▊ | 389/439 [00:27<00:03, 13.74it/s] 89%|████████▉ | 391/439 [00:28<00:03, 14.54it/s] 90%|████████▉ | 393/439 [00:28<00:03, 13.41it/s] 90%|████████▉ | 395/439 [00:28<00:03, 14.17it/s] 90%|█████████ | 397/439 [00:28<00:02, 14.84it/s] 91%|█████████ | 399/439 [00:28<00:02, 13.55it/s] 91%|█████████▏| 401/439 [00:28<00:02, 14.91it/s] 92%|█████████▏| 403/439 [00:28<00:02, 13.61it/s] 92%|█████████▏| 405/439 [00:29<00:02, 14.21it/s] 93%|█████████▎| 407/439 [00:29<00:02, 15.13it/s] 93%|█████████▎| 409/439 [00:29<00:02, 14.02it/s] 94%|█████████▎| 411/439 [00:29<00:01, 14.90it/s] 94%|█████████▍| 413/439 [00:29<00:01, 15.09it/s] 95%|█████████▍| 415/439 [00:29<00:01, 14.04it/s] 95%|█████████▍| 417/439 [00:29<00:01, 14.53it/s] 95%|█████████▌| 419/439 [00:30<00:01, 13.37it/s] 96%|█████████▌| 421/439 [00:30<00:01, 13.88it/s] 96%|█████████▋| 423/439 [00:30<00:01, 13.13it/s] 97%|█████████▋| 425/439 [00:30<00:01, 12.19it/s] 97%|█████████▋| 427/439 [00:30<00:00, 13.37it/s] 98%|█████████▊| 429/439 [00:30<00:00, 12.68it/s] 98%|█████████▊| 431/439 [00:30<00:00, 13.76it/s] 99%|█████████▊| 433/439 [00:31<00:00, 13.94it/s] 99%|█████████▉| 435/439 [00:31<00:00, 13.45it/s] 100%|█████████▉| 437/439 [00:31<00:00, 14.55it/s] 100%|██████████| 439/439 [00:31<00:00, 12.45it/s] 100%|██████████| 439/439 [00:31<00:00, 13.91it/s] | |
| precision recall f1-score support | |
| followed 0.8475 0.7053 0.7699 1805 | |
| violated 0.0449 0.2719 0.0770 114 | |
| not_applicable 0.9435 0.8928 0.9175 5104 | |
| accuracy 0.8345 7023 | |
| macro avg 0.6120 0.6233 0.5881 7023 | |
| weighted avg 0.9042 0.8345 0.8659 7023 | |
| test_ood natural (7023 pairs): macro F1 0.5881, violated precision 0.0449, violated recall 0.2719 | |
| ***** test_ood metrics ***** | |
| test_ood_accuracy = 0.8345 | |
| test_ood_followed_f1 = 0.7699 | |
| test_ood_followed_precision = 0.8475 | |
| test_ood_followed_recall = 0.7053 | |
| test_ood_followed_support = 1805 | |
| test_ood_loss = 0.4521 | |
| test_ood_macro_f1 = 0.5881 | |
| test_ood_not_applicable_f1 = 0.9175 | |
| test_ood_not_applicable_precision = 0.9435 | |
| test_ood_not_applicable_recall = 0.8928 | |
| test_ood_not_applicable_support = 5104 | |
| test_ood_runtime = 0:00:31.94 | |
| test_ood_samples_per_second = 219.855 | |
| test_ood_steps_per_second = 13.743 | |
| test_ood_violated_f1 = 0.077 | |
| test_ood_violated_precision = 0.0449 | |
| test_ood_violated_recall = 0.2719 | |
| test_ood_violated_support = 114 | |
| wandb: updating run metadata; uploading artifact run-zj70dexz-test_ood_errors; uploading artifact run-zj70dexz-test_ood_confusion_matrix_table | |
| wandb: uploading artifact run-zj70dexz-test_ood_errors; uploading artifact run-zj70dexz-test_ood_confusion_matrix_table | |
| wandb: uploading artifact run-zj70dexz-test_ood_errors; uploading artifact run-zj70dexz-test_ood_confusion_matrix_table; uploading history steps 73-76, summary, console lines 106-136 | |
| wandb: uploading artifact run-zj70dexz-test_ood_errors; uploading artifact run-zj70dexz-test_ood_confusion_matrix_table | |
| wandb: uploading artifact run-zj70dexz-test_ood_errors | |
| wandb: uploading output.log; uploading wandb-summary.json; uploading config.yaml; uploading media/table/test_ood_errors_76_053dede0f3db568906e8.table.json; uploading media/table/test_ood_confusion_matrix_table_76_1b992457d682bab97dbf.table.json | |
| wandb: uploading wandb-summary.json; uploading config.yaml; uploading media/table/test_ood_errors_76_053dede0f3db568906e8.table.json; uploading media/table/test_ood_confusion_matrix_table_76_1b992457d682bab97dbf.table.json | |
| wandb: uploading config.yaml; uploading media/table/test_ood_errors_76_053dede0f3db568906e8.table.json; uploading media/table/test_ood_confusion_matrix_table_76_1b992457d682bab97dbf.table.json | |
| wandb: uploading media/table/test_ood_errors_76_053dede0f3db568906e8.table.json | |
| wandb: uploading data | |
| wandb: | |
| wandb: Run history: | |
| wandb: eval/accuracy ▁▆▇█ | |
| wandb: eval/followed_f1 ▁███ | |
| wandb: eval/followed_precision ▂▁▅█ | |
| wandb: eval/followed_recall ▁█▅▃ | |
| wandb: eval/followed_support ▁▁▁▁ | |
| wandb: eval/loss █▄▁▁ | |
| wandb: eval/macro_f1 ▁▆▇█ | |
| wandb: eval/not_applicable_f1 ▁▅▇█ | |
| wandb: eval/not_applicable_precision ▃▁▅█ | |
| wandb: eval/not_applicable_recall ▁█▇▇ | |
| wandb: +130 ... | |
| wandb: | |
| wandb: Run summary: | |
| wandb: eval/accuracy 0.81203 | |
| wandb: eval/followed_f1 0.77535 | |
| wandb: eval/followed_precision 0.78333 | |
| wandb: eval/followed_recall 0.76753 | |
| wandb: eval/followed_support 1041 | |
| wandb: eval/loss 0.50918 | |
| wandb: eval/macro_f1 0.81015 | |
| wandb: eval/not_applicable_f1 0.89461 | |
| wandb: eval/not_applicable_precision 0.89503 | |
| wandb: eval/not_applicable_recall 0.89419 | |
| wandb: +136 ... | |
| wandb: | |
| wandb: 🚀 View run modernbert-large-30k at: https://forge.coreweave.com/wandb/storm-dpo/policy-classifier/runs/zj70dexz | |
| wandb: ⭐️ View project at: https://forge.coreweave.com/wandb/storm-dpo/policy-classifier | |
| wandb: Synced 5 W&B file(s), 4 media file(s), 8 artifact file(s) and 0 other file(s) | |
| wandb: Find logs at: ./wandb/run-20261105_094103-zj70dexz/logs | |
Xet Storage Details
- Size:
- 111 kB
- Xet hash:
- caaf6eaa1ca1ce83fe3ea40340050f664c56d68ea0cc65d0724b654d494d0e6a
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.