Training in progress, epoch 8

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c88a67b8b689abe93a6519e36d6d722690f27e10407c9e555dedd19c5e611d
+oid sha256:6026be240f87a4fc70253ff6e37cf795b93399098bcc5e7dbc2d3ff76e7dcea3
 size 496244100

tb/events.out.tfevents.1725049548.6b97e535edda.20735.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8113d5f7d2de38464c921858844833c0071b925f07d567f6742a2238c6c6e3
-size 9474
+oid sha256:d4c7ed4232c009f016632b1c68ab76f59be9a4cf19fbe8de8ef8cd28ceb594c5
+size 10157

train.log

@@ -1126,4 +1126,123 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:39:49,213 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-2978/special_tokens_map.json
 [INFO|tokenization_utils_base.py:2574] 2024-08-30 20:39:51,528 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
 [INFO|tokenization_utils_base.py:2583] 2024-08-30 20:39:51,528 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
-
 70%|███████   | 2979/4250 [14:02<2:02:04,  5.76s/it]
 70%|███████   | 2980/4250 [14:03<1:26:55,  4.11s/it]
 70%|███████   | 2981/4250 [14:03<1:02:05,  2.94s/it]
 70%|███████   | 2982/4250 [14:03<45:09,  2.14s/it]  
 70%|███████   | 2983/4250 [14:03<32:55,  1.56s/it]
 70%|███████   | 2984/4250 [14:04<24:24,  1.16s/it]
 70%|███████   | 2985/4250 [14:04<19:33,  1.08it/s]
 70%|███████   | 2986/4250 [14:04<14:41,  1.43it/s]
 70%|███████   | 2987/4250 [14:04<11:37,  1.81it/s]
 70%|███████   | 2988/4250 [14:04<09:17,  2.26it/s]
 70%|███████   | 2989/4250 [14:05<07:46,  2.70it/s]
 70%|███████   | 2990/4250 [14:05<06:32,  3.21it/s]
 70%|███████   | 2991/4250 [14:05<06:01,  3.49it/s]
 70%|███████   | 2992/4250 [14:05<05:58,  3.51it/s]
 70%|███████   | 2993/4250 [14:06<05:13,  4.01it/s]
 70%|███████   | 2994/4250 [14:06<05:00,  4.18it/s]
 70%|███████   | 2995/4250 [14:06<04:50,  4.32it/s]
 70%|███████   | 2996/4250 [14:06<04:45,  4.39it/s]
 71%|███████   | 2997/4250 [14:06<04:27,  4.68it/s]
 71%|███████   | 2998/4250 [14:07<04:04,  5.13it/s]
 71%|███████   | 2999/4250 [14:07<04:37,  4.51it/s]
 71%|███████   | 3000/4250 [14:07<05:38,  3.69it/s]
                                                   
 71%|███████   | 3000/4250 [14:07<05:38,  3.69it/s]
 71%|███████   | 3001/4250 [14:07<05:13,  3.99it/s]
 71%|███████   | 3002/4250 [14:08<04:55,  4.23it/s]
 71%|███████   | 3003/4250 [14:08<04:49,  4.31it/s]
 71%|███████   | 3004/4250 [14:08<05:08,  4.04it/s]
 71%|███████   | 3005/4250 [14:08<04:39,  4.45it/s]
 71%|███████   | 3006/4250 [14:09<05:25,  3.82it/s]
 71%|███████   | 3007/4250 [14:09<05:52,  3.53it/s]
 71%|███████   | 3008/4250 [14:09<05:58,  3.46it/s]
 71%|███████   | 3009/4250 [14:09<05:33,  3.72it/s]
 71%|███████   | 3010/4250 [14:10<05:53,  3.51it/s]
 71%|███████   | 3011/4250 [14:10<05:47,  3.56it/s]
 71%|███████   | 3012/4250 [14:10<05:49,  3.54it/s]
 71%|███████   | 3013/4250 [14:11<05:40,  3.64it/s]
 71%|███████   | 3014/4250 [14:11<05:40,  3.63it/s]
 71%|███████   | 3015/4250 [14:11<06:18,  3.26it/s]
 71%|███████   | 3016/4250 [14:11<05:35,  3.67it/s]
 71%|███████   | 3017/4250 [14:12<05:00,  4.10it/s]
 71%|███████   | 3018/4250 [14:12<05:07,  4.01it/s]
 71%|███████   | 3019/4250 [14:12<05:05,  4.03it/s]
 71%|███████   | 3020/4250 [14:12<04:56,  4.16it/s]
 71%|███████   | 3021/4250 [14:13<04:35,  4.47it/s]
 71%|███████   | 3022/4250 [14:13<04:23,  4.66it/s]
 71%|███████   | 3023/4250 [14:13<04:38,  4.40it/s]
 71%|███████   | 3024/4250 [14:13<04:31,  4.52it/s]
 71%|███████   | 3025/4250 [14:13<04:02,  5.06it/s]
 71%|███████   | 3026/4250 [14:14<04:30,  4.52it/s]
 71%|███████   | 3027/4250 [14:14<04:31,  4.50it/s]
 71%|███████   | 3028/4250 [14:14<04:46,  4.27it/s]
 71%|███████▏  | 3029/4250 [14:14<04:41,  4.33it/s]
 71%|███████▏  | 3030/4250 [14:15<04:56,  4.12it/s]
 71%|███████▏  | 3031/4250 [14:15<04:45,  4.26it/s]
 71%|███████▏  | 3032/4250 [14:15<04:47,  4.23it/s]
 71%|███████▏  | 3033/4250 [14:15<05:11,  3.91it/s]
 71%|███████▏  | 3034/4250 [14:16<04:55,  4.11it/s]
 71%|███████▏  | 3035/4250 [14:16<04:31,  4.48it/s]
 71%|███████▏  | 3036/4250 [14:16<04:19,  4.68it/s]
 71%|███████▏  | 3037/4250 [14:16<04:07,  4.90it/s]
+
 70%|███████   | 2979/4250 [14:02<2:02:04,  5.76s/it]
 70%|███████   | 2980/4250 [14:03<1:26:55,  4.11s/it]
 70%|███████   | 2981/4250 [14:03<1:02:05,  2.94s/it]
 70%|███████   | 2982/4250 [14:03<45:09,  2.14s/it]  
 70%|███████   | 2983/4250 [14:03<32:55,  1.56s/it]
 70%|███████   | 2984/4250 [14:04<24:24,  1.16s/it]
 70%|███████   | 2985/4250 [14:04<19:33,  1.08it/s]
 70%|███████   | 2986/4250 [14:04<14:41,  1.43it/s]
 70%|███████   | 2987/4250 [14:04<11:37,  1.81it/s]
 70%|███████   | 2988/4250 [14:04<09:17,  2.26it/s]
 70%|███████   | 2989/4250 [14:05<07:46,  2.70it/s]
 70%|███████   | 2990/4250 [14:05<06:32,  3.21it/s]
 70%|███████   | 2991/4250 [14:05<06:01,  3.49it/s]
 70%|███████   | 2992/4250 [14:05<05:58,  3.51it/s]
 70%|███████   | 2993/4250 [14:06<05:13,  4.01it/s]
 70%|███████   | 2994/4250 [14:06<05:00,  4.18it/s]
 70%|███████   | 2995/4250 [14:06<04:50,  4.32it/s]
 70%|███████   | 2996/4250 [14:06<04:45,  4.39it/s]
 71%|███████   | 2997/4250 [14:06<04:27,  4.68it/s]
 71%|███████   | 2998/4250 [14:07<04:04,  5.13it/s]
 71%|███████   | 2999/4250 [14:07<04:37,  4.51it/s]
 71%|███████   | 3000/4250 [14:07<05:38,  3.69it/s]
                                                   
 71%|███████   | 3000/4250 [14:07<05:38,  3.69it/s]
 71%|███████   | 3001/4250 [14:07<05:13,  3.99it/s]
 71%|███████   | 3002/4250 [14:08<04:55,  4.23it/s]
 71%|███████   | 3003/4250 [14:08<04:49,  4.31it/s]
 71%|███████   | 3004/4250 [14:08<05:08,  4.04it/s]
 71%|███████   | 3005/4250 [14:08<04:39,  4.45it/s]
 71%|███████   | 3006/4250 [14:09<05:25,  3.82it/s]
 71%|███████   | 3007/4250 [14:09<05:52,  3.53it/s]
 71%|███████   | 3008/4250 [14:09<05:58,  3.46it/s]
 71%|███████   | 3009/4250 [14:09<05:33,  3.72it/s]
 71%|███████   | 3010/4250 [14:10<05:53,  3.51it/s]
 71%|███████   | 3011/4250 [14:10<05:47,  3.56it/s]
 71%|███████   | 3012/4250 [14:10<05:49,  3.54it/s]
 71%|███████   | 3013/4250 [14:11<05:40,  3.64it/s]
 71%|███████   | 3014/4250 [14:11<05:40,  3.63it/s]
 71%|███████   | 3015/4250 [14:11<06:18,  3.26it/s]
 71%|███████   | 3016/4250 [14:11<05:35,  3.67it/s]
 71%|███████   | 3017/4250 [14:12<05:00,  4.10it/s]
 71%|███████   | 3018/4250 [14:12<05:07,  4.01it/s]
 71%|███████   | 3019/4250 [14:12<05:05,  4.03it/s]
 71%|███████   | 3020/4250 [14:12<04:56,  4.16it/s]
 71%|███████   | 3021/4250 [14:13<04:35,  4.47it/s]
 71%|███████   | 3022/4250 [14:13<04:23,  4.66it/s]
 71%|███████   | 3023/4250 [14:13<04:38,  4.40it/s]
 71%|███████   | 3024/4250 [14:13<04:31,  4.52it/s]
 71%|███████   | 3025/4250 [14:13<04:02,  5.06it/s]
 71%|███████   | 3026/4250 [14:14<04:30,  4.52it/s]
 71%|███████   | 3027/4250 [14:14<04:31,  4.50it/s]
 71%|███████   | 3028/4250 [14:14<04:46,  4.27it/s]
 71%|███████▏  | 3029/4250 [14:14<04:41,  4.33it/s]
 71%|███████▏  | 3030/4250 [14:15<04:56,  4.12it/s]
 71%|███████▏  | 3031/4250 [14:15<04:45,  4.26it/s]
 71%|███████▏  | 3032/4250 [14:15<04:47,  4.23it/s]
 71%|███████▏  | 3033/4250 [14:15<05:11,  3.91it/s]
 71%|███████▏  | 3034/4250 [14:16<04:55,  4.11it/s]
 71%|███████▏  | 3035/4250 [14:16<04:31,  4.48it/s]
 71%|███████▏  | 3036/4250 [14:16<04:19,  4.68it/s]
 71%|███████▏  | 3037/4250 [14:16<04:07,  4.90it/s]
 71%|███████▏  | 3038/4250 [14:16<04:10,  4.85it/s]
 72%|███████▏  | 3039/4250 [14:17<04:04,  4.96it/s]
 72%|███████▏  | 3040/4250 [14:17<04:05,  4.93it/s]
 72%|███████▏  | 3041/4250 [14:17<04:15,  4.73it/s]
 72%|███████▏  | 3042/4250 [14:17<04:02,  4.99it/s]
 72%|███████▏  | 3043/4250 [14:17<04:10,  4.82it/s]
 72%|███████▏  | 3044/4250 [14:18<03:57,  5.07it/s]
 72%|███████▏  | 3045/4250 [14:18<03:56,  5.10it/s]
 72%|███████▏  | 3046/4250 [14:18<07:02,  2.85it/s]
 72%|███████▏  | 3047/4250 [14:19<06:28,  3.10it/s]
 72%|███████▏  | 3048/4250 [14:19<05:53,  3.40it/s]
 72%|███████▏  | 3049/4250 [14:19<05:36,  3.57it/s]
 72%|███████▏  | 3050/4250 [14:19<05:39,  3.53it/s]
 72%|███████▏  | 3051/4250 [14:20<05:00,  3.99it/s]
 72%|███████▏  | 3052/4250 [14:20<04:50,  4.12it/s]
 72%|███████▏  | 3053/4250 [14:20<04:41,  4.26it/s]
 72%|███████▏  | 3054/4250 [14:20<04:38,  4.30it/s]
 72%|███████▏  | 3055/4250 [14:21<06:12,  3.21it/s]
 72%|███████▏  | 3056/4250 [14:21<06:44,  2.95it/s]
 72%|███████▏  | 3057/4250 [14:21<05:50,  3.40it/s]
 72%|███████▏  | 3058/4250 [14:22<05:15,  3.78it/s]
 72%|███████▏  | 3059/4250 [14:22<04:44,  4.19it/s]
 72%|███████▏  | 3060/4250 [14:22<04:21,  4.54it/s]
 72%|███████▏  | 3061/4250 [14:22<04:18,  4.60it/s]
 72%|███████▏  | 3062/4250 [14:22<04:34,  4.33it/s]
 72%|███████▏  | 3063/4250 [14:23<04:20,  4.55it/s]
 72%|███████▏  | 3064/4250 [14:23<05:18,  3.73it/s]
 72%|███████▏  | 3065/4250 [14:23<05:06,  3.87it/s]
 72%|███████▏  | 3066/4250 [14:23<04:39,  4.24it/s]
 72%|███████▏  | 3067/4250 [14:24<04:26,  4.44it/s]
 72%|███████▏  | 3068/4250 [14:24<04:18,  4.57it/s]
 72%|███████▏  | 3069/4250 [14:24<04:28,  4.40it/s]
 72%|███████▏  | 3070/4250 [14:24<04:33,  4.32it/s]
 72%|███████▏  | 3071/4250 [14:24<04:19,  4.54it/s]
 72%|███████▏  | 3072/4250 [14:25<04:07,  4.76it/s]
 72%|███████▏  | 3073/4250 [14:25<04:54,  3.99it/s]
 72%|███████▏  | 3074/4250 [14:25<05:11,  3.78it/s]
 72%|███████▏  | 3075/4250 [14:26<04:57,  3.96it/s]
 72%|███████▏  | 3076/4250 [14:26<04:29,  4.35it/s]
 72%|███████▏  | 3077/4250 [14:26<04:37,  4.23it/s]
 72%|███████▏  | 3078/4250 [14:26<04:31,  4.32it/s]
 72%|███████▏  | 3079/4250 [14:26<04:15,  4.58it/s]
 72%|███████▏  | 3080/4250 [14:27<04:06,  4.75it/s]
 72%|███████▏  | 3081/4250 [14:27<03:58,  4.91it/s]
 73%|███████▎  | 3082/4250 [14:27<03:58,  4.90it/s]
 73%|███████▎  | 3083/4250 [14:27<05:29,  3.54it/s]
 73%|███████▎  | 3084/4250 [14:28<05:12,  3.73it/s]
 73%|███████▎  | 3085/4250 [14:28<04:37,  4.20it/s]
 73%|███████▎  | 3086/4250 [14:28<04:51,  3.99it/s]
 73%|███████▎  | 3087/4250 [14:28<04:33,  4.25it/s]
 73%|███████▎  | 3088/4250 [14:29<04:32,  4.27it/s]
 73%|███████▎  | 3089/4250 [14:29<04:31,  4.28it/s]
 73%|███████▎  | 3090/4250 [14:29<04:11,  4.61it/s]
 73%|███████▎  | 3091/4250 [14:29<04:10,  4.63it/s]
 73%|███████▎  | 3092/4250 [14:30<04:56,  3.91it/s]
 73%|███████▎  | 3093/4250 [14:30<04:34,  4.22it/s]
 73%|███████▎  | 3094/4250 [14:31<08:09,  2.36it/s]
 73%|███████▎  | 3095/4250 [14:31<06:42,  2.87it/s]
 73%|███████▎  | 3096/4250 [14:31<05:51,  3.29it/s]
 73%|███████▎  | 3097/4250 [14:31<06:14,  3.08it/s]
 73%|███████▎  | 3098/4250 [14:32<05:24,  3.55it/s]
 73%|███████▎  | 3099/4250 [14:32<04:53,  3.92it/s]
 73%|███████▎  | 3100/4250 [14:32<04:45,  4.02it/s]
 73%|███████▎  | 3101/4250 [14:32<04:33,  4.20it/s]
 73%|███████▎  | 3102/4250 [14:32<04:21,  4.38it/s]
 73%|███████▎  | 3103/4250 [14:33<04:10,  4.58it/s]
 73%|███████▎  | 3104/4250 [14:33<05:07,  3.73it/s]
 73%|███████▎  | 3105/4250 [14:33<05:28,  3.48it/s]
 73%|███████▎  | 3106/4250 [14:34<05:40,  3.36it/s]
 73%|███████▎  | 3107/4250 [14:34<05:19,  3.58it/s]
 73%|███████▎  | 3108/4250 [14:34<04:55,  3.86it/s]
 73%|███████▎  | 3109/4250 [14:34<04:49,  3.94it/s]
 73%|███████▎  | 3110/4250 [14:34<04:22,  4.34it/s]
 73%|███████▎  | 3111/4250 [14:35<04:19,  4.38it/s]
 73%|███████▎  | 3112/4250 [14:35<04:02,  4.68it/s]
 73%|███████▎  | 3113/4250 [14:35<04:08,  4.57it/s]
 73%|███████▎  | 3114/4250 [14:35<04:24,  4.29it/s]
 73%|███████▎  | 3115/4250 [14:36<04:06,  4.60it/s]
 73%|███████▎  | 3116/4250 [14:36<03:51,  4.89it/s]
 73%|███████▎  | 3117/4250 [14:36<03:35,  5.26it/s]
 73%|███████▎  | 3118/4250 [14:36<03:54,  4.82it/s]
 73%|███████▎  | 3119/4250 [14:36<03:31,  5.36it/s]
 73%|███████▎  | 3120/4250 [14:36<03:33,  5.28it/s]
 73%|███████▎  | 3121/4250 [14:37<03:40,  5.12it/s]
 73%|███████▎  | 3122/4250 [14:37<03:41,  5.09it/s]
 73%|███████▎  | 3123/4250 [14:37<03:45,  4.99it/s]
 74%|███████▎  | 3124/4250 [14:37<03:37,  5.17it/s]
 74%|███████▎  | 3125/4250 [14:38<04:41,  4.00it/s]
 74%|███████▎  | 3126/4250 [14:38<04:18,  4.35it/s]
 74%|███████▎  | 3127/4250 [14:38<04:13,  4.42it/s]
 74%|███████▎  | 3128/4250 [14:38<03:50,  4.88it/s]
 74%|███████▎  | 3129/4250 [14:38<04:01,  4.64it/s]
 74%|███████▎  | 3130/4250 [14:39<04:05,  4.56it/s]
 74%|███████▎  | 3131/4250 [14:39<04:34,  4.08it/s]
 74%|███████▎  | 3132/4250 [14:39<04:33,  4.09it/s]
 74%|███████▎  | 3133/4250 [14:39<04:22,  4.26it/s]
 74%|███████▎  | 3134/4250 [14:40<04:15,  4.37it/s]
 74%|███████▍  | 3135/4250 [14:40<03:59,  4.65it/s]
 74%|███████▍  | 3136/4250 [14:40<03:48,  4.88it/s]
 74%|███████▍  | 3137/4250 [14:40<03:45,  4.94it/s]
 74%|███████▍  | 3138/4250 [14:40<04:01,  4.61it/s]
 74%|███████▍  | 3139/4250 [14:41<03:48,  4.86it/s]
 74%|███████▍  | 3140/4250 [14:41<03:48,  4.86it/s]
 74%|███████▍  | 3141/4250 [14:41<03:33,  5.20it/s]
 74%|███████▍  | 3142/4250 [14:41<03:26,  5.35it/s]
 74%|███████▍  | 3143/4250 [14:41<03:48,  4.85it/s]
 74%|███████▍  | 3144/4250 [14:42<03:42,  4.97it/s]
 74%|███████▍  | 3145/4250 [14:42<03:42,  4.97it/s]
 74%|███████▍  | 3146/4250 [14:42<04:05,  4.49it/s]
 74%|███████▍  | 3147/4250 [14:42<03:52,  4.74it/s]
 74%|███████▍  | 3148/4250 [14:42<03:42,  4.95it/s]
 74%|███████▍  | 3149/4250 [14:43<04:11,  4.38it/s]
 74%|███████▍  | 3150/4250 [14:43<04:08,  4.43it/s]
 74%|███████▍  | 3151/4250 [14:43<03:51,  4.75it/s]
 74%|███████▍  | 3152/4250 [14:43<03:53,  4.71it/s]
 74%|███████▍  | 3153/4250 [14:44<03:52,  4.71it/s]
 74%|███████▍  | 3154/4250 [14:44<03:59,  4.57it/s]
 74%|███████▍  | 3155/4250 [14:44<05:09,  3.54it/s]
 74%|███████▍  | 3156/4250 [14:44<05:03,  3.61it/s]
 74%|███████▍  | 3157/4250 [14:45<04:21,  4.18it/s]
 74%|███████▍  | 3158/4250 [14:45<04:47,  3.80it/s]
 74%|███████▍  | 3159/4250 [14:45<05:13,  3.48it/s]
 74%|███████▍  | 3160/4250 [14:46<04:55,  3.69it/s]
 74%|███████▍  | 3161/4250 [14:46<04:35,  3.95it/s]
 74%|███████▍  | 3162/4250 [14:46<04:31,  4.00it/s]
 74%|███████▍  | 3163/4250 [14:46<04:13,  4.28it/s]
 74%|███████▍  | 3164/4250 [14:46<04:12,  4.30it/s]
 74%|███████▍  | 3165/4250 [14:47<05:21,  3.38it/s]
 74%|███████▍  | 3166/4250 [14:47<04:59,  3.62it/s]
 75%|███████▍  | 3167/4250 [14:47<04:47,  3.76it/s]
 75%|███████▍  | 3168/4250 [14:48<04:26,  4.06it/s]
 75%|███████▍  | 3169/4250 [14:48<04:03,  4.44it/s]
 75%|███████▍  | 3170/4250 [14:48<04:14,  4.24it/s]
 75%|███████▍  | 3171/4250 [14:48<04:10,  4.30it/s]
 75%|███████▍  | 3172/4250 [14:48<04:21,  4.13it/s]
 75%|███████▍  | 3173/4250 [14:49<03:56,  4.56it/s]
 75%|███████▍  | 3174/4250 [14:49<04:08,  4.33it/s]
 75%|███████▍  | 3175/4250 [14:49<03:57,  4.52it/s]
 75%|███████▍  | 3176/4250 [14:49<03:34,  5.01it/s]
 75%|███████▍  | 3177/4250 [14:49<04:02,  4.43it/s]
 75%|███████▍  | 3178/4250 [14:50<04:16,  4.17it/s]
 75%|███████▍  | 3179/4250 [14:50<04:10,  4.27it/s]
 75%|███████▍  | 3180/4250 [14:50<03:56,  4.53it/s]
 75%|███████▍  | 3181/4250 [14:50<03:49,  4.66it/s]
 75%|███████▍  | 3182/4250 [14:51<03:49,  4.65it/s]
 75%|███████▍  | 3183/4250 [14:51<03:52,  4.59it/s]
 75%|███████▍  | 3184/4250 [14:51<03:57,  4.49it/s]
 75%|███████▍  | 3185/4250 [14:51<03:38,  4.88it/s]
 75%|███████▍  | 3186/4250 [14:52<05:52,  3.01it/s]
 75%|███████▍  | 3187/4250 [14:52<05:48,  3.05it/s]
 75%|███████▌  | 3188/4250 [14:52<04:51,  3.65it/s]
 75%|███████▌  | 3189/4250 [14:53<05:21,  3.30it/s]
 75%|███████▌  | 3190/4250 [14:53<05:33,  3.18it/s]
 75%|███████▌  | 3191/4250 [14:53<05:32,  3.19it/s]
 75%|███████▌  | 3192/4250 [14:54<06:06,  2.89it/s]
 75%|███████▌  | 3193/4250 [14:54<05:06,  3.44it/s]
 75%|███████▌  | 3194/4250 [14:54<04:38,  3.79it/s]
 75%|███████▌  | 3195/4250 [14:54<04:13,  4.16it/s]
 75%|███████▌  | 3196/4250 [14:55<05:09,  3.40it/s]
 75%|███████▌  | 3197/4250 [14:55<04:49,  3.64it/s]
 75%|███████▌  | 3198/4250 [14:55<04:17,  4.09it/s]
 75%|███████▌  | 3199/4250 [14:55<04:03,  4.32it/s]
 75%|███████▌  | 3200/4250 [14:56<03:50,  4.56it/s]
 75%|███████▌  | 3201/4250 [14:56<04:18,  4.06it/s]
 75%|███████▌  | 3202/4250 [14:56<04:02,  4.32it/s]
 75%|███████▌  | 3203/4250 [14:56<03:41,  4.73it/s]
 75%|███████▌  | 3204/4250 [14:57<04:23,  3.97it/s]
 75%|███████▌  | 3205/4250 [14:57<04:24,  3.95it/s]
 75%|███████▌  | 3206/4250 [14:57<04:06,  4.23it/s]
 75%|███████▌  | 3207/4250 [14:57<03:36,  4.81it/s]
 75%|███████▌  | 3208/4250 [14:57<03:41,  4.71it/s]
 76%|███████▌  | 3209/4250 [14:58<03:58,  4.37it/s]
 76%|███████▌  | 3210/4250 [14:58<03:42,  4.67it/s]
 76%|███████▌  | 3211/4250 [14:58<03:57,  4.38it/s]
 76%|███████▌  | 3212/4250 [14:58<03:52,  4.47it/s]
 76%|███████▌  | 3213/4250 [14:59<03:54,  4.43it/s]
 76%|███████▌  | 3214/4250 [14:59<03:37,  4.77it/s]
 76%|███████▌  | 3215/4250 [14:59<03:35,  4.80it/s]
 76%|███████▌  | 3216/4250 [14:59<04:00,  4.30it/s]
 76%|███████▌  | 3217/4250 [14:59<04:00,  4.29it/s]
 76%|███████▌  | 3218/4250 [15:00<03:53,  4.42it/s]
 76%|███████▌  | 3219/4250 [15:00<03:46,  4.55it/s]
 76%|███████▌  | 3220/4250 [15:00<03:41,  4.65it/s]
 76%|███████▌  | 3221/4250 [15:00<03:48,  4.51it/s]
 76%|███████▌  | 3222/4250 [15:00<03:36,  4.75it/s]
 76%|███████▌  | 3223/4250 [15:01<03:54,  4.38it/s]
 76%|███████▌  | 3224/4250 [15:01<03:46,  4.54it/s]
 76%|███████▌  | 3225/4250 [15:01<03:38,  4.68it/s]
 76%|███████▌  | 3226/4250 [15:01<04:24,  3.87it/s]
 76%|███████▌  | 3227/4250 [15:02<04:25,  3.85it/s]
 76%|███████▌  | 3228/4250 [15:02<05:11,  3.28it/s]
 76%|███████▌  | 3229/4250 [15:02<04:46,  3.56it/s]
 76%|███████▌  | 3230/4250 [15:03<05:46,  2.94it/s]
 76%|███████▌  | 3231/4250 [15:03<05:14,  3.24it/s]
 76%|███████▌  | 3232/4250 [15:03<04:50,  3.50it/s]
 76%|███████▌  | 3233/4250 [15:04<04:49,  3.52it/s]
 76%|███████▌  | 3234/4250 [15:04<07:16,  2.33it/s]
 76%|███████▌  | 3235/4250 [15:05<06:03,  2.79it/s]
 76%|███████▌  | 3236/4250 [15:05<05:09,  3.27it/s]
 76%|███████▌  | 3237/4250 [15:05<04:54,  3.44it/s]
 76%|███████▌  | 3238/4250 [15:05<04:24,  3.82it/s]
 76%|███████▌  | 3239/4250 [15:05<04:32,  3.71it/s]
 76%|███████▌  | 3240/4250 [15:06<04:31,  3.72it/s]
 76%|███████▋  | 3241/4250 [15:06<04:18,  3.91it/s]
 76%|███████▋  | 3242/4250 [15:06<04:15,  3.94it/s]
 76%|███████▋  | 3243/4250 [15:07<04:28,  3.76it/s]
 76%|███████▋  | 3244/4250 [15:07<04:14,  3.96it/s]
 76%|███████▋  | 3245/4250 [15:07<04:34,  3.66it/s]
 76%|███████▋  | 3246/4250 [15:07<04:26,  3.77it/s]
 76%|███████▋  | 3247/4250 [15:07<03:58,  4.21it/s]
 76%|███████▋  | 3248/4250 [15:08<03:42,  4.51it/s]
 76%|███████▋  | 3249/4250 [15:08<03:31,  4.74it/s]
 76%|███████▋  | 3250/4250 [15:08<03:37,  4.60it/s]
 76%|███████▋  | 3251/4250 [15:08<03:37,  4.60it/s]
 77%|███████▋  | 3252/4250 [15:09<04:00,  4.15it/s]
 77%|███████▋  | 3253/4250 [15:09<04:58,  3.34it/s]
 77%|███████▋  | 3254/4250 [15:09<05:02,  3.29it/s]
 77%|███████▋  | 3255/4250 [15:10<04:30,  3.68it/s]
 77%|███████▋  | 3256/4250 [15:10<04:20,  3.82it/s]
 77%|███████▋  | 3257/4250 [15:10<04:07,  4.01it/s]
 77%|███████▋  | 3258/4250 [15:10<03:53,  4.25it/s]
 77%|███████▋  | 3259/4250 [15:10<03:28,  4.74it/s]
 77%|███████▋  | 3260/4250 [15:11<03:56,  4.19it/s]
 77%|███████▋  | 3261/4250 [15:11<03:45,  4.39it/s]
 77%|███████▋  | 3262/4250 [15:11<03:38,  4.52it/s]
 77%|███████▋  | 3263/4250 [15:11<03:28,  4.73it/s]
 77%|███████▋  | 3264/4250 [15:11<03:17,  5.00it/s]
 77%|███████▋  | 3265/4250 [15:12<04:40,  3.51it/s]
 77%|███████▋  | 3266/4250 [15:12<04:22,  3.75it/s]
 77%|███████▋  | 3267/4250 [15:12<03:50,  4.27it/s]
 77%|███████▋  | 3268/4250 [15:12<03:36,  4.54it/s]
 77%|███████▋  | 3269/4250 [15:13<03:27,  4.73it/s]
 77%|███████▋  | 3270/4250 [15:13<03:24,  4.80it/s]
 77%|███████▋  | 3271/4250 [15:13<03:31,  4.62it/s]
 77%|███████▋  | 3272/4250 [15:13<03:23,  4.80it/s]
 77%|███████▋  | 3273/4250 [15:14<03:31,  4.61it/s]
 77%|███████▋  | 3274/4250 [15:14<03:24,  4.78it/s]
 77%|███████▋  | 3275/4250 [15:14<03:14,  5.02it/s]
 77%|███████▋  | 3276/4250 [15:14<03:16,  4.97it/s]
 77%|███████▋  | 3277/4250 [15:14<03:09,  5.12it/s]
 77%|███████▋  | 3278/4250 [15:14<03:08,  5.15it/s]
 77%|███████▋  | 3279/4250 [15:15<03:33,  4.55it/s]
 77%|███████▋  | 3280/4250 [15:15<03:44,  4.33it/s]
 77%|███████▋  | 3281/4250 [15:15<03:26,  4.70it/s]
 77%|███████▋  | 3282/4250 [15:15<03:16,  4.92it/s]
 77%|███████▋  | 3283/4250 [15:16<03:08,  5.12it/s]
 77%|███████▋  | 3284/4250 [15:16<03:23,  4.75it/s]
 77%|███████▋  | 3285/4250 [15:16<03:23,  4.74it/s]
 77%|███████▋  | 3286/4250 [15:16<03:17,  4.87it/s]
 77%|███████▋  | 3287/4250 [15:16<03:34,  4.50it/s]
 77%|███████▋  | 3288/4250 [15:17<03:25,  4.68it/s]
 77%|███████▋  | 3289/4250 [15:17<03:11,  5.02it/s]
 77%|███████▋  | 3290/4250 [15:17<03:22,  4.73it/s]
 77%|███████▋  | 3291/4250 [15:17<03:46,  4.23it/s]
 77%|███████▋  | 3292/4250 [15:18<03:53,  4.10it/s]
 77%|███████▋  | 3293/4250 [15:18<03:43,  4.28it/s]
 78%|███████▊  | 3294/4250 [15:18<03:38,  4.37it/s]
 78%|███████▊  | 3295/4250 [15:18<03:35,  4.42it/s]
 78%|███████▊  | 3296/4250 [15:18<03:25,  4.64it/s]
 78%|███████▊  | 3297/4250 [15:19<03:34,  4.45it/s]
 78%|███████▊  | 3298/4250 [15:19<03:21,  4.73it/s]
 78%|███████▊  | 3299/4250 [15:19<03:54,  4.05it/s]
 78%|███████▊  | 3300/4250 [15:19<04:04,  3.89it/s]
 78%|███████▊  | 3301/4250 [15:20<04:02,  3.91it/s]
 78%|███████▊  | 3302/4250 [15:20<04:09,  3.80it/s]
 78%|███████▊  | 3303/4250 [15:20<04:08,  3.81it/s]
 78%|███████▊  | 3304/4250 [15:21<04:02,  3.90it/s]
 78%|███████▊  | 3305/4250 [15:21<03:40,  4.28it/s]
 78%|███████▊  | 3306/4250 [15:21<03:29,  4.51it/s]
 78%|███████▊  | 3307/4250 [15:21<03:28,  4.52it/s]
 78%|███████▊  | 3308/4250 [15:21<03:19,  4.72it/s]
 78%|███████▊  | 3309/4250 [15:22<03:21,  4.67it/s]
 78%|███████▊  | 3310/4250 [15:22<03:16,  4.78it/s]
 78%|███████▊  | 3311/4250 [15:22<03:09,  4.95it/s]
 78%|███████▊  | 3312/4250 [15:22<03:15,  4.80it/s]
 78%|███████▊  | 3313/4250 [15:22<03:16,  4.76it/s]
 78%|███████▊  | 3314/4250 [15:23<03:11,  4.89it/s]
 78%|███████▊  | 3315/4250 [15:23<03:22,  4.62it/s]
 78%|███████▊  | 3316/4250 [15:23<03:14,  4.79it/s]
 78%|███████▊  | 3317/4250 [15:23<03:21,  4.63it/s]
 78%|███████▊  | 3318/4250 [15:23<03:03,  5.07it/s]
 78%|███████▊  | 3319/4250 [15:24<03:02,  5.09it/s]
 78%|███████▊  | 3320/4250 [15:24<03:06,  4.99it/s]
 78%|███████▊  | 3321/4250 [15:24<03:25,  4.51it/s]
 78%|███████▊  | 3322/4250 [15:24<03:36,  4.29it/s]
 78%|███████▊  | 3323/4250 [15:25<03:27,  4.48it/s]
 78%|███████▊  | 3324/4250 [15:25<03:05,  4.98it/s]
 78%|███████▊  | 3325/4250 [15:25<03:14,  4.75it/s]
 78%|███████▊  | 3326/4250 [15:25<03:30,  4.39it/s]
 78%|███████▊  | 3327/4250 [15:25<03:57,  3.89it/s]
 78%|███████▊  | 3328/4250 [15:26<03:43,  4.12it/s]
 78%|███████▊  | 3329/4250 [15:26<03:32,  4.33it/s]
 78%|███████▊  | 3330/4250 [15:26<03:39,  4.19it/s]
 78%|███████▊  | 3331/4250 [15:26<03:45,  4.07it/s]
 78%|███████▊  | 3332/4250 [15:27<04:31,  3.38it/s]
 78%|███████▊  | 3333/4250 [15:27<04:08,  3.69it/s]
 78%|███████▊  | 3334/4250 [15:27<03:44,  4.08it/s]
 78%|███████▊  | 3335/4250 [15:27<03:26,  4.44it/s]
 78%|███████▊  | 3336/4250 [15:28<03:31,  4.32it/s]
 79%|███████▊  | 3337/4250 [15:28<03:23,  4.48it/s]
 79%|███████▊  | 3338/4250 [15:28<03:38,  4.18it/s]
 79%|███████▊  | 3339/4250 [15:28<03:40,  4.14it/s]
 79%|███████▊  | 3340/4250 [15:29<03:24,  4.44it/s]
 79%|███████▊  | 3341/4250 [15:29<03:10,  4.78it/s]
 79%|███████▊  | 3342/4250 [15:29<03:44,  4.05it/s]
 79%|███████▊  | 3343/4250 [15:29<03:34,  4.23it/s]
 79%|███████▊  | 3344/4250 [15:29<03:21,  4.49it/s]
 79%|███████▊  | 3345/4250 [15:30<03:34,  4.21it/s]
 79%|███████▊  | 3346/4250 [15:30<04:13,  3.57it/s]
 79%|███████▉  | 3347/4250 [15:31<04:38,  3.24it/s]
 79%|███████▉  | 3348/4250 [15:31<04:31,  3.33it/s]
 79%|███████▉  | 3349/4250 [15:31<03:59,  3.77it/s]
 79%|███████▉  | 3350/4250 [15:31<03:34,  4.20it/s]
 79%|███████▉  | 3351/4250 [15:31<03:31,  4.25it/s]
 79%|███████▉  | 3352/4250 [15:32<04:10,  3.59it/s]
 79%|███████▉  | 3353/4250 [15:32<04:04,  3.67it/s]
 79%|███████▉  | 3354/4250 [15:32<03:47,  3.95it/s]
 79%|███████▉  | 3355/4250 [15:32<03:27,  4.31it/s]
 79%|███████▉  | 3356/4250 [15:33<03:06,  4.79it/s]
 79%|███████▉  | 3357/4250 [15:33<02:54,  5.13it/s]
 79%|███████▉  | 3358/4250 [15:33<03:09,  4.71it/s]
 79%|███████▉  | 3359/4250 [15:33<02:58,  4.98it/s]
 79%|███████▉  | 3360/4250 [15:33<03:07,  4.74it/s]
 79%|███████▉  | 3361/4250 [15:34<03:05,  4.80it/s]
 79%|███████▉  | 3362/4250 [15:34<03:28,  4.25it/s]
 79%|███████▉  | 3363/4250 [15:34<04:36,  3.21it/s]
 79%|███████▉  | 3364/4250 [15:35<04:03,  3.64it/s]
 79%|███████▉  | 3365/4250 [15:35<03:51,  3.82it/s]
 79%|███████▉  | 3366/4250 [15:35<03:39,  4.02it/s]
 79%|███████▉  | 3367/4250 [15:35<03:29,  4.21it/s]
 79%|███████▉  | 3368/4250 [15:35<03:23,  4.33it/s]
 79%|███████▉  | 3369/4250 [15:36<03:14,  4.54it/s]
 79%|███████▉  | 3370/4250 [15:36<03:09,  4.65it/s]
 79%|███████▉  | 3371/4250 [15:36<03:02,  4.81it/s]
 79%|███████▉  | 3372/4250 [15:36<03:39,  4.00it/s]
 79%|███████▉  | 3373/4250 [15:37<03:24,  4.29it/s]
 79%|███████▉  | 3374/4250 [15:37<03:58,  3.67it/s]
 79%|███████▉  | 3375/4250 [15:37<03:45,  3.88it/s]
 79%|███████▉  | 3376/4250 [15:37<03:38,  4.00it/s]
 79%|███████▉  | 3377/4250 [15:38<03:46,  3.85it/s]
 79%|███████▉  | 3378/4250 [15:38<03:27,  4.21it/s]
 80%|███████▉  | 3379/4250 [15:38<03:25,  4.23it/s]
 80%|███████▉  | 3380/4250 [15:38<03:12,  4.51it/s]
 80%|███████▉  | 3381/4250 [15:38<03:04,  4.72it/s]
 80%|███████▉  | 3382/4250 [15:39<02:52,  5.03it/s]
 80%|███████▉  | 3383/4250 [15:39<02:59,  4.82it/s]
 80%|███████▉  | 3384/4250 [15:39<02:55,  4.93it/s]
 80%|███████▉  | 3385/4250 [15:39<02:55,  4.92it/s]
 80%|███████▉  | 3386/4250 [15:40<03:18,  4.35it/s]
 80%|███████▉  | 3387/4250 [15:40<03:24,  4.23it/s]
 80%|███████▉  | 3388/4250 [15:40<03:16,  4.38it/s]
 80%|███████▉  | 3389/4250 [15:40<03:15,  4.40it/s]
 80%|███████▉  | 3390/4250 [15:41<04:23,  3.27it/s]
 80%|███████▉  | 3391/4250 [15:41<04:09,  3.44it/s]
 80%|███████▉  | 3392/4250 [15:41<03:53,  3.67it/s]
 80%|███████▉  | 3393/4250 [15:42<04:02,  3.53it/s]
 80%|███████▉  | 3394/4250 [15:42<03:53,  3.67it/s]
 80%|███████▉  | 3395/4250 [15:42<03:40,  3.88it/s]
 80%|███████▉  | 3396/4250 [15:42<03:25,  4.16it/s]
 80%|███████▉  | 3397/4250 [15:43<03:48,  3.73it/s]
 80%|███████▉  | 3398/4250 [15:43<03:25,  4.15it/s]
 80%|███████▉  | 3399/4250 [15:43<03:24,  4.17it/s]
 80%|████████  | 3400/4250 [15:43<03:18,  4.28it/s]
 80%|████████  | 3401/4250 [15:43<03:01,  4.68it/s]
 80%|████████  | 3402/4250 [15:43<02:49,  4.99it/s]
 80%|████████  | 3403/4250 [15:44<03:31,  4.00it/s]
 80%|████████  | 3404/4250 [15:44<03:16,  4.31it/s][INFO|trainer.py:805] 2024-08-30 20:41:33,404 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, ner_tags, id. If tokens, ner_tags, id are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3788] 2024-08-30 20:41:33,406 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3790] 2024-08-30 20:41:33,406 >>   Num examples = 6810
+[INFO|trainer.py:3793] 2024-08-30 20:41:33,406 >>   Batch size = 8
+{'eval_loss': 0.11656877398490906, 'eval_precision': 0.7792032410533424, 'eval_recall': 0.810014038371549, 'eval_f1': 0.7943099690260411, 'eval_accuracy': 0.975997912861988, 'eval_runtime': 14.6842, 'eval_samples_per_second': 463.764, 'eval_steps_per_second': 58.022, 'epoch': 7.0}
+{'loss': 0.0079, 'grad_norm': 0.15811629593372345, 'learning_rate': 1.4705882352941177e-05, 'epoch': 7.05}
+
+
  0%|          | 0/852 [00:00<?, ?it/s]
+
  1%|          | 10/852 [00:00<00:08, 94.18it/s]
+
  2%|▏         | 20/852 [00:00<00:10, 82.94it/s]
+
  3%|▎         | 29/852 [00:00<00:10, 80.84it/s]
+
  4%|▍         | 38/852 [00:00<00:10, 79.75it/s]
+
  6%|▌         | 47/852 [00:00<00:10, 80.38it/s]
+
  7%|▋         | 56/852 [00:00<00:09, 81.23it/s]
+
  8%|▊         | 65/852 [00:00<00:09, 79.78it/s]
+
  9%|▊         | 73/852 [00:00<00:09, 78.93it/s]
+
 10%|▉         | 81/852 [00:01<00:09, 78.65it/s]
+
 10%|█         | 89/852 [00:01<00:09, 78.03it/s]
+
 11%|█▏        | 97/852 [00:01<00:09, 77.03it/s]
+
 12%|█▏        | 105/852 [00:01<00:09, 77.56it/s]
+
 13%|█▎        | 113/852 [00:01<00:09, 77.20it/s]
+
 14%|█▍        | 121/852 [00:01<00:09, 77.93it/s]
+
 15%|█▌        | 129/852 [00:01<00:09, 74.39it/s]
+
 16%|█▌        | 137/852 [00:01<00:09, 74.36it/s]
+
 17%|█▋        | 145/852 [00:01<00:09, 75.51it/s]
+
 18%|█▊        | 153/852 [00:01<00:09, 75.68it/s]
+
 19%|█▉        | 161/852 [00:02<00:09, 73.96it/s]
+
 20%|█▉        | 169/852 [00:02<00:09, 73.70it/s]
+
 21%|██        | 177/852 [00:02<00:09, 74.63it/s]
+
 22%|██▏       | 185/852 [00:02<00:08, 75.95it/s]
+
 23%|██▎       | 193/852 [00:02<00:08, 76.63it/s]
+
 24%|██▎       | 202/852 [00:02<00:08, 78.17it/s]
+
 25%|██▍       | 210/852 [00:02<00:08, 76.89it/s]
+
 26%|██▌       | 218/852 [00:02<00:08, 76.64it/s]
+
 27%|██▋       | 227/852 [00:02<00:08, 78.05it/s]
+
 28%|██▊       | 235/852 [00:03<00:07, 78.40it/s]
+
 29%|██▊       | 243/852 [00:03<00:08, 76.02it/s]
+
 29%|██▉       | 251/852 [00:03<00:07, 77.00it/s]
+
 31%|███       | 260/852 [00:03<00:07, 78.22it/s]
+
 31%|███▏      | 268/852 [00:03<00:07, 77.78it/s]
+
 32%|███▏      | 276/852 [00:03<00:07, 78.20it/s]
+
 33%|███▎      | 284/852 [00:03<00:07, 78.52it/s]
+
 34%|███▍      | 292/852 [00:03<00:07, 77.85it/s]
+
 35%|███▌      | 300/852 [00:03<00:07, 77.72it/s]
+
 36%|███▋      | 309/852 [00:03<00:06, 78.59it/s]
+
 37%|███▋      | 317/852 [00:04<00:07, 73.58it/s]
+
 38%|███▊      | 325/852 [00:04<00:07, 74.80it/s]
+
 39%|███▉      | 333/852 [00:04<00:06, 75.45it/s]
+
 40%|████      | 342/852 [00:04<00:06, 77.58it/s]
+
 41%|████      | 350/852 [00:04<00:06, 78.23it/s]
+
 42%|████▏     | 358/852 [00:04<00:06, 76.38it/s]
+
 43%|████▎     | 366/852 [00:04<00:06, 77.30it/s]
+
 44%|████▍     | 375/852 [00:04<00:06, 78.27it/s]
+
 45%|████▍     | 383/852 [00:04<00:06, 77.74it/s]
+
 46%|████▌     | 392/852 [00:05<00:05, 79.42it/s]
+
 47%|████▋     | 400/852 [00:05<00:05, 79.13it/s]
+
 48%|████▊     | 408/852 [00:05<00:05, 75.68it/s]
+
 49%|████▉     | 416/852 [00:05<00:05, 76.68it/s]
+
 50%|████▉     | 424/852 [00:05<00:05, 77.01it/s]
+
 51%|█████     | 432/852 [00:05<00:05, 76.45it/s]
+
 52%|█████▏    | 441/852 [00:05<00:05, 77.79it/s]
+
 53%|█████▎    | 449/852 [00:05<00:05, 77.79it/s]
+
 54%|█████▎    | 457/852 [00:05<00:05, 77.43it/s]
+
 55%|█████▍    | 465/852 [00:06<00:05, 75.00it/s]
+
 56%|█████▌    | 473/852 [00:06<00:05, 70.78it/s]
+
 56%|█████▋    | 481/852 [00:06<00:05, 72.25it/s]
+
 57%|█████▋    | 489/852 [00:06<00:04, 73.23it/s]
+
 58%|█████▊    | 498/852 [00:06<00:04, 76.18it/s]
+
 60%|█████▉    | 507/852 [00:06<00:04, 76.73it/s]
+
 61%|██████    | 516/852 [00:06<00:04, 78.13it/s]
+
 62%|██████▏   | 524/852 [00:06<00:04, 76.48it/s]
+
 62%|██████▏   | 532/852 [00:06<00:04, 76.43it/s]
+
 63%|██████▎   | 540/852 [00:07<00:04, 77.29it/s]
+
 64%|██████▍   | 548/852 [00:07<00:03, 77.91it/s]
+
 65%|██████▌   | 556/852 [00:07<00:03, 74.83it/s]
+
 66%|██████▋   | 565/852 [00:07<00:03, 77.02it/s]
+
 67%|██████▋   | 573/852 [00:07<00:03, 77.51it/s]
+
 68%|██████▊   | 581/852 [00:07<00:03, 76.63it/s]
+
 69%|██████▉   | 589/852 [00:07<00:03, 76.43it/s]
+
 70%|███████   | 597/852 [00:07<00:03, 77.43it/s]
+
 71%|███████   | 605/852 [00:07<00:03, 77.76it/s]
+
 72%|███████▏  | 613/852 [00:07<00:03, 77.42it/s]
+
 73%|███████▎  | 621/852 [00:08<00:02, 77.61it/s]
+
 74%|███████▍  | 629/852 [00:08<00:02, 76.04it/s]
+
 75%|███████▍  | 638/852 [00:08<00:02, 76.79it/s]
+
 76%|███████▌  | 646/852 [00:08<00:02, 73.10it/s]
+
 77%|███████▋  | 655/852 [00:08<00:02, 75.28it/s]
+
 78%|███████▊  | 663/852 [00:08<00:02, 76.03it/s]
+
 79%|███████▉  | 671/852 [00:08<00:02, 76.46it/s]
+
 80%|███████▉  | 679/852 [00:08<00:02, 77.14it/s]
+
 81%|████████  | 688/852 [00:08<00:02, 78.39it/s]
+
 82%|████████▏ | 697/852 [00:09<00:01, 79.07it/s]
+
 83%|████████▎ | 706/852 [00:09<00:01, 80.55it/s]
+
 84%|████████▍ | 715/852 [00:09<00:01, 81.00it/s]
+
 85%|████████▍ | 724/852 [00:09<00:01, 80.28it/s]
+
 86%|████████▌ | 733/852 [00:09<00:01, 80.77it/s]
+
 87%|████████▋ | 742/852 [00:09<00:01, 81.86it/s]
+
 88%|████████▊ | 751/852 [00:09<00:01, 81.42it/s]
+
 89%|████████▉ | 760/852 [00:09<00:01, 82.14it/s]
+
 90%|█████████ | 769/852 [00:09<00:01, 80.67it/s]
+
 91%|█████████▏| 778/852 [00:10<00:00, 80.31it/s]
+
 92%|█████████▏| 787/852 [00:10<00:00, 78.78it/s]
+
 93%|█████████▎| 795/852 [00:10<00:00, 78.34it/s]
+
 94%|█████████▍| 804/852 [00:10<00:00, 79.82it/s]
+
 95%|█████████���| 812/852 [00:10<00:00, 78.93it/s]
+
 96%|█████████▋| 821/852 [00:10<00:00, 80.37it/s]
+
 97%|█████████▋| 830/852 [00:10<00:00, 81.07it/s]
+
 98%|█████████▊| 839/852 [00:10<00:00, 80.14it/s]
+
                                                   
+
                                                 
 80%|████████  | 3404/4250 [15:59<03:16,  4.31it/s]
+
+
                                                 [INFO|trainer.py:3478] 2024-08-30 20:41:48,181 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-3404
+[INFO|configuration_utils.py:472] 2024-08-30 20:41:48,183 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-3404/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 20:41:49,516 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-3404/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:41:49,518 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-3404/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:41:49,518 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-3404/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:41:51,822 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:41:51,822 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 80%|████████  | 3405/4250 [16:03<1:21:49,  5.81s/it]
 80%|████████  | 3406/4250 [16:03<57:58,  4.12s/it]  
 80%|████████  | 3407/4250 [16:03<41:20,  2.94s/it]
 80%|████████  | 3408/4250 [16:03<29:36,  2.11s/it]
 80%|████████  | 3409/4250 [16:04<21:45,  1.55s/it]
 80%|████████  | 3410/4250 [16:04<16:01,  1.15s/it]
 80%|████████  | 3411/4250 [16:04<11:57,  1.17it/s]
 80%|████████  | 3412/4250 [16:04<09:18,  1.50it/s]
 80%|████████  | 3413/4250 [16:04<07:25,  1.88it/s]
 80%|████████  | 3414/4250 [16:05<06:04,  2.29it/s]
 80%|████████  | 3415/4250 [16:05<05:01,  2.77it/s]
 80%|████████  | 3416/4250 [16:05<04:20,  3.21it/s]
 80%|████████  | 3417/4250 [16:05<03:56,  3.52it/s]
 80%|████████  | 3418/4250 [16:05<03:31,  3.94it/s]
 80%|████████  | 3419/4250 [16:06<03:22,  4.11it/s]
 80%|████████  | 3420/4250 [16:06<03:11,  4.34it/s]
 80%|████████  | 3421/4250 [16:06<02:53,  4.78it/s]
 81%|████████  | 3422/4250 [16:06<02:47,  4.94it/s]
 81%|████████  | 3423/4250 [16:06<02:55,  4.70it/s]
 81%|████████  | 3424/4250 [16:07<02:46,  4.97it/s]
 81%|████████  | 3425/4250 [16:07<02:55,  4.70it/s]
 81%|████████  | 3426/4250 [16:07<02:43,  5.04it/s]
 81%|████████  | 3427/4250 [16:07<02:37,  5.21it/s]
 81%|████████  | 3428/4250 [16:07<02:42,  5.05it/s]
 81%|████████  | 3429/4250 [16:08<02:45,  4.96it/s]
 81%|████████  | 3430/4250 [16:08<02:44,  4.97it/s]
 81%|████████  | 3431/4250 [16:08<02:42,  5.05it/s]
 81%|████████  | 3432/4250 [16:08<02:34,  5.30it/s]
 81%|████████  | 3433/4250 [16:09<03:14,  4.21it/s]
 81%|████████  | 3434/4250 [16:09<03:12,  4.24it/s]
 81%|████████  | 3435/4250 [16:09<03:24,  3.99it/s]
 81%|████████  | 3436/4250 [16:09<03:47,  3.58it/s]
 81%|████████  | 3437/4250 [16:10<03:30,  3.86it/s]
 81%|████████  | 3438/4250 [16:10<03:28,  3.89it/s]
 81%|████████  | 3439/4250 [16:10<03:21,  4.02it/s]
 81%|████████  | 3440/4250 [16:10<03:03,  4.40it/s]
 81%|████████  | 3441/4250 [16:11<03:13,  4.17it/s]
 81%|████████  | 3442/4250 [16:11<02:57,  4.55it/s]
 81%|████████  | 3443/4250 [16:11<03:00,  4.47it/s]
 81%|████████  | 3444/4250 [16:11<02:59,  4.49it/s]
 81%|████████  | 3445/4250 [16:11<03:03,  4.39it/s]
 81%|████████  | 3446/4250 [16:12<03:11,  4.20it/s]
 81%|████████  | 3447/4250 [16:12<03:00,  4.45it/s]
 81%|████████  | 3448/4250 [16:12<02:56,  4.54it/s]
 81%|████████  | 3449/4250 [16:12<02:49,  4.73it/s]
 81%|████████  | 3450/4250 [16:13<02:58,  4.49it/s]
 81%|████████  | 3451/4250 [16:13<03:03,  4.35it/s]
 81%|████████  | 3452/4250 [16:13<02:54,  4.56it/s]
 81%|████████  | 3453/4250 [16:13<03:24,  3.89it/s]
 81%|███��████▏ | 3454/4250 [16:14<03:16,  4.05it/s]
 81%|████████▏ | 3455/4250 [16:14<02:57,  4.48it/s]
 81%|████████▏ | 3456/4250 [16:14<02:59,  4.43it/s]
 81%|████████▏ | 3457/4250 [16:14<02:55,  4.52it/s]
 81%|████████▏ | 3458/4250 [16:14<02:55,  4.51it/s]
 81%|████████▏ | 3459/4250 [16:15<03:00,  4.38it/s]
 81%|████████▏ | 3460/4250 [16:15<02:49,  4.65it/s]
 81%|████████▏ | 3461/4250 [16:15<02:51,  4.59it/s]
 81%|████████▏ | 3462/4250 [16:15<02:41,  4.88it/s]
 81%|████████▏ | 3463/4250 [16:15<02:57,  4.44it/s]
 82%|████████▏ | 3464/4250 [16:16<03:01,  4.32it/s]
 82%|████████▏ | 3465/4250 [16:16<02:52,  4.55it/s]
 82%|████████▏ | 3466/4250 [16:16<02:48,  4.66it/s]
 82%|████████▏ | 3467/4250 [16:16<02:43,  4.78it/s]
 82%|████████▏ | 3468/4250 [16:17<02:40,  4.86it/s]