Training in progress, epoch 8

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6026be240f87a4fc70253ff6e37cf795b93399098bcc5e7dbc2d3ff76e7dcea3
+oid sha256:703ee1bcf47ee92ab75902a3cdc06782b658c9357d986780daea02cf938bd478
 size 496244100

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c7ed4232c009f016632b1c68ab76f59be9a4cf19fbe8de8ef8cd28ceb594c5
-size 10157
+oid sha256:3264005bdf9414cb231703bbebb90528b9b29ec9b2421bd7a1f0698eed83efbb
+size 10840

train.log

@@ -1245,4 +1245,121 @@ 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 20:41:49,518 >> 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]
+
 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]
 82%|████████▏ | 3469/4250 [16:17<03:05,  4.21it/s]
 82%|████████▏ | 3470/4250 [16:17<02:54,  4.47it/s]
 82%|████████▏ | 3471/4250 [16:17<03:01,  4.29it/s]
 82%|████████▏ | 3472/4250 [16:18<03:30,  3.69it/s]
 82%|████████▏ | 3473/4250 [16:18<03:17,  3.93it/s]
 82%|████████▏ | 3474/4250 [16:18<03:10,  4.07it/s]
 82%|████████▏ | 3475/4250 [16:18<02:57,  4.38it/s]
 82%|████████▏ | 3476/4250 [16:19<02:58,  4.33it/s]
 82%|████████▏ | 3477/4250 [16:19<02:51,  4.52it/s]
 82%|████████▏ | 3478/4250 [16:19<03:05,  4.17it/s]
 82%|████████▏ | 3479/4250 [16:19<02:50,  4.53it/s]
 82%|████████▏ | 3480/4250 [16:19<02:37,  4.90it/s]
 82%|████████▏ | 3481/4250 [16:19<02:29,  5.13it/s]
 82%|████████▏ | 3482/4250 [16:20<03:15,  3.94it/s]
 82%|████████▏ | 3483/4250 [16:20<03:38,  3.51it/s]
 82%|████████▏ | 3484/4250 [16:21<03:38,  3.50it/s]
 82%|████████▏ | 3485/4250 [16:21<03:33,  3.58it/s]
 82%|████████▏ | 3486/4250 [16:21<03:17,  3.88it/s]
 82%|████████▏ | 3487/4250 [16:21<03:14,  3.93it/s]
 82%|████████▏ | 3488/4250 [16:21<03:00,  4.23it/s]
 82%|████████▏ | 3489/4250 [16:22<03:00,  4.21it/s]
 82%|████████▏ | 3490/4250 [16:22<02:43,  4.64it/s]
 82%|████████▏ | 3491/4250 [16:22<02:36,  4.84it/s]
 82%|████████▏ | 3492/4250 [16:22<02:45,  4.59it/s]
 82%|████████▏ | 3493/4250 [16:22<02:44,  4.59it/s]
 82%|████████▏ | 3494/4250 [16:23<02:44,  4.60it/s]
 82%|████████▏ | 3495/4250 [16:23<02:33,  4.91it/s]
 82%|████████▏ | 3496/4250 [16:23<02:39,  4.72it/s]
 82%|████████▏ | 3497/4250 [16:23<02:36,  4.82it/s]
 82%|████████▏ | 3498/4250 [16:24<02:59,  4.20it/s]
 82%|████████▏ | 3499/4250 [16:24<03:03,  4.10it/s]
 82%|████████▏ | 3500/4250 [16:24<02:46,  4.49it/s]
                                                   
 82%|████████▏ | 3500/4250 [16:24<02:46,  4.49it/s]
 82%|████████▏ | 3501/4250 [16:24<02:41,  4.62it/s]
 82%|████████▏ | 3502/4250 [16:24<02:35,  4.81it/s]
 82%|████████▏ | 3503/4250 [16:25<02:41,  4.61it/s]
 82%|████████▏ | 3504/4250 [16:25<02:39,  4.67it/s]
 82%|████████▏ | 3505/4250 [16:25<02:27,  5.05it/s]
 82%|████████▏ | 3506/4250 [16:25<02:30,  4.94it/s]
 83%|████████▎ | 3507/4250 [16:26<02:38,  4.70it/s]
 83%|████████▎ | 3508/4250 [16:26<02:32,  4.86it/s]
 83%|████████▎ | 3509/4250 [16:26<02:22,  5.21it/s]
 83%|████████▎ | 3510/4250 [16:26<02:23,  5.16it/s]
 83%|████████▎ | 3511/4250 [16:26<02:41,  4.58it/s]
 83%|████████▎ | 3512/4250 [16:27<02:47,  4.40it/s]
 83%|████████▎ | 3513/4250 [16:27<02:44,  4.48it/s]
 83%|████████▎ | 3514/4250 [16:27<02:39,  4.61it/s]
 83%|████████▎ | 3515/4250 [16:27<02:37,  4.67it/s]
 83%|████████▎ | 3516/4250 [16:27<02:30,  4.87it/s]
 83%|████████▎ | 3517/4250 [16:28<02:29,  4.90it/s]
 83%|████████▎ | 3518/4250 [16:28<02:29,  4.89it/s]
 83%|████████▎ | 3519/4250 [16:28<02:27,  4.97it/s]
 83%|████████▎ | 3520/4250 [16:28<02:27,  4.95it/s]
 83%|████████▎ | 3521/4250 [16:28<02:21,  5.15it/s]
 83%|████████▎ | 3522/4250 [16:29<02:20,  5.19it/s]
 83%|████████▎ | 3523/4250 [16:29<02:31,  4.81it/s]
 83%|████████▎ | 3524/4250 [16:29<02:49,  4.28it/s]
 83%|████████▎ | 3525/4250 [16:29<02:38,  4.58it/s]
 83%|████████▎ | 3526/4250 [16:30<02:50,  4.25it/s]
 83%|████████▎ | 3527/4250 [16:30<04:51,  2.48it/s]
 83%|████████▎ | 3528/4250 [16:31<04:29,  2.68it/s]
 83%|████████▎ | 3529/4250 [16:31<03:46,  3.18it/s]
 83%|████████▎ | 3530/4250 [16:31<03:28,  3.45it/s]
 83%|████████▎ | 3531/4250 [16:31<03:05,  3.87it/s]
 83%|████████▎ | 3532/4250 [16:31<02:56,  4.06it/s]
 83%|████████▎ | 3533/4250 [16:32<03:17,  3.63it/s]
 83%|████████▎ | 3534/4250 [16:32<02:57,  4.04it/s]
 83%|████████▎ | 3535/4250 [16:32<02:38,  4.51it/s]
 83%|████████▎ | 3536/4250 [16:32<02:50,  4.18it/s]
 83%|████████▎ | 3537/4250 [16:33<02:41,  4.42it/s]
 83%|████████▎ | 3538/4250 [16:33<02:35,  4.59it/s]
 83%|████████▎ | 3539/4250 [16:33<02:30,  4.72it/s]
 83%|████████▎ | 3540/4250 [16:33<02:54,  4.06it/s]
 83%|████████▎ | 3541/4250 [16:34<02:44,  4.32it/s]
 83%|████████▎ | 3542/4250 [16:34<03:11,  3.69it/s]
 83%|████████▎ | 3543/4250 [16:35<04:27,  2.64it/s]
 83%|████████▎ | 3544/4250 [16:35<03:41,  3.18it/s]
 83%|████████▎ | 3545/4250 [16:35<03:09,  3.73it/s]
 83%|████████▎ | 3546/4250 [16:35<03:07,  3.76it/s]
 83%|████████▎ | 3547/4250 [16:35<03:23,  3.46it/s]
 83%|████████▎ | 3548/4250 [16:36<03:19,  3.52it/s]
 84%|████████▎ | 3549/4250 [16:36<03:09,  3.69it/s]
 84%|████████▎ | 3550/4250 [16:36<02:46,  4.22it/s]
 84%|████████▎ | 3551/4250 [16:36<02:53,  4.03it/s]
 84%|████████▎ | 3552/4250 [16:37<02:44,  4.25it/s]
 84%|████████▎ | 3553/4250 [16:37<02:37,  4.42it/s]
 84%|████████▎ | 3554/4250 [16:37<02:46,  4.18it/s]
 84%|████████▎ | 3555/4250 [16:37<02:31,  4.60it/s]
 84%|████████▎ | 3556/4250 [16:37<02:20,  4.95it/s]
 84%|████████▎ | 3557/4250 [16:38<02:18,  5.02it/s]
 84%|████████▎ | 3558/4250 [16:38<02:20,  4.92it/s]
 84%|████████▎ | 3559/4250 [16:38<02:36,  4.41it/s]
 84%|████████▍ | 3560/4250 [16:39<04:31,  2.54it/s]
 84%|████████▍ | 3561/4250 [16:39<03:54,  2.93it/s]
 84%|████████▍ | 3562/4250 [16:39<03:52,  2.96it/s]
 84%|████████▍ | 3563/4250 [16:40<03:14,  3.54it/s]
 84%|████████▍ | 3564/4250 [16:40<03:05,  3.71it/s]
 84%|████████▍ | 3565/4250 [16:40<02:58,  3.84it/s]
 84%|████████▍ | 3566/4250 [16:41<04:09,  2.75it/s]
 84%|████████▍ | 3567/4250 [16:41<03:39,  3.11it/s]
 84%|████████▍ | 3568/4250 [16:41<03:17,  3.45it/s]
 84%|████████▍ | 3569/4250 [16:41<02:57,  3.84it/s]
 84%|████████▍ | 3570/4250 [16:41<02:39,  4.25it/s]
 84%|████████▍ | 3571/4250 [16:42<02:35,  4.37it/s]
 84%|████████▍ | 3572/4250 [16:42<02:47,  4.05it/s]
 84%|████████▍ | 3573/4250 [16:42<03:08,  3.60it/s]
 84%|████████▍ | 3574/4250 [16:43<02:47,  4.03it/s]
 84%|████████▍ | 3575/4250 [16:43<02:58,  3.79it/s]
 84%|████████▍ | 3576/4250 [16:43<02:41,  4.17it/s]
 84%|████████▍ | 3577/4250 [16:43<02:46,  4.04it/s]
 84%|████████▍ | 3578/4250 [16:43<02:41,  4.16it/s]
 84%|████████▍ | 3579/4250 [16:44<02:34,  4.35it/s]
 84%|████████▍ | 3580/4250 [16:44<02:42,  4.13it/s]
 84%|████████▍ | 3581/4250 [16:44<02:32,  4.39it/s]
 84%|████████▍ | 3582/4250 [16:45<03:19,  3.34it/s]
 84%|████████▍ | 3583/4250 [16:45<02:54,  3.83it/s]
 84%|████████▍ | 3584/4250 [16:45<02:44,  4.05it/s]
 84%|████████▍ | 3585/4250 [16:45<02:31,  4.39it/s]
 84%|████████▍ | 3586/4250 [16:45<02:21,  4.71it/s]
 84%|████████▍ | 3587/4250 [16:46<02:21,  4.70it/s]
 84%|████████▍ | 3588/4250 [16:46<02:15,  4.90it/s]
 84%|████████▍ | 3589/4250 [16:46<02:18,  4.77it/s]
 84%|████████▍ | 3590/4250 [16:46<02:19,  4.73it/s]
 84%|████████▍ | 3591/4250 [16:46<02:21,  4.66it/s]
 85%|████████▍ | 3592/4250 [16:47<02:24,  4.56it/s]
 85%|████████▍ | 3593/4250 [16:47<02:29,  4.41it/s]
 85%|████████▍ | 3594/4250 [16:47<02:45,  3.97it/s]
 85%|████████▍ | 3595/4250 [16:47<02:37,  4.15it/s]
 85%|████████▍ | 3596/4250 [16:48<02:25,  4.50it/s]
 85%|████████▍ | 3597/4250 [16:48<02:14,  4.86it/s]
 85%|████████▍ | 3598/4250 [16:48<02:23,  4.55it/s]
 85%|████████▍ | 3599/4250 [16:48<02:10,  4.98it/s]
 85%|████████▍ | 3600/4250 [16:48<02:14,  4.85it/s]
 85%|████████▍ | 3601/4250 [16:49<02:05,  5.18it/s]
 85%|████████▍ | 3602/4250 [16:49<02:05,  5.17it/s]
 85%|████████▍ | 3603/4250 [16:49<02:16,  4.75it/s]
 85%|████████▍ | 3604/4250 [16:49<02:12,  4.87it/s]
 85%|████████▍ | 3605/4250 [16:49<02:10,  4.95it/s]
 85%|████████▍ | 3606/4250 [16:50<02:03,  5.21it/s]
 85%|████████▍ | 3607/4250 [16:50<02:08,  5.02it/s]
 85%|████████▍ | 3608/4250 [16:50<02:24,  4.45it/s]
 85%|████████▍ | 3609/4250 [16:50<02:26,  4.37it/s]
 85%|████████▍ | 3610/4250 [16:51<02:40,  3.99it/s]
 85%|████████▍ | 3611/4250 [16:51<02:36,  4.08it/s]
 85%|████████▍ | 3612/4250 [16:51<02:22,  4.47it/s]
 85%|████████▌ | 3613/4250 [16:51<02:15,  4.70it/s]
 85%|████████▌ | 3614/4250 [16:51<02:31,  4.20it/s]
 85%|████████▌ | 3615/4250 [16:52<02:30,  4.23it/s]
 85%|████████▌ | 3616/4250 [16:52<02:23,  4.43it/s]
 85%|████████▌ | 3617/4250 [16:52<02:28,  4.28it/s]
 85%|████████▌ | 3618/4250 [16:53<02:58,  3.54it/s]
 85%|████████▌ | 3619/4250 [16:53<02:40,  3.92it/s]
 85%|████████▌ | 3620/4250 [16:53<02:33,  4.11it/s]
 85%|████████▌ | 3621/4250 [16:53<02:24,  4.36it/s]
 85%|████████▌ | 3622/4250 [16:53<02:15,  4.63it/s]
 85%|████████▌ | 3623/4250 [16:54<02:37,  3.99it/s]
 85%|████████▌ | 3624/4250 [16:54<02:22,  4.38it/s]
 85%|████████��� | 3625/4250 [16:54<02:13,  4.68it/s]
 85%|████████▌ | 3626/4250 [16:54<02:11,  4.76it/s]
 85%|████████▌ | 3627/4250 [16:54<02:09,  4.80it/s]
 85%|████████▌ | 3628/4250 [16:55<02:17,  4.52it/s]
 85%|████████▌ | 3629/4250 [16:55<02:24,  4.30it/s]
 85%|████████▌ | 3630/4250 [16:55<02:48,  3.69it/s]
 85%|████████▌ | 3631/4250 [16:56<02:46,  3.71it/s]
 85%|████████▌ | 3632/4250 [16:56<02:33,  4.02it/s]
 85%|████████▌ | 3633/4250 [16:56<02:19,  4.43it/s]
 86%|████████▌ | 3634/4250 [16:56<02:12,  4.67it/s]
 86%|████████▌ | 3635/4250 [16:56<02:11,  4.69it/s]
 86%|████████▌ | 3636/4250 [16:57<02:02,  5.00it/s]
 86%|████████▌ | 3637/4250 [16:57<02:06,  4.85it/s]
 86%|████████▌ | 3638/4250 [16:57<02:07,  4.78it/s]
 86%|████████▌ | 3639/4250 [16:57<02:11,  4.65it/s]
 86%|████████▌ | 3640/4250 [16:57<02:12,  4.60it/s]
 86%|████████▌ | 3641/4250 [16:58<02:35,  3.91it/s]
 86%|████████▌ | 3642/4250 [16:58<02:35,  3.92it/s]
 86%|████████▌ | 3643/4250 [16:58<02:36,  3.88it/s]
 86%|████████▌ | 3644/4250 [16:58<02:24,  4.19it/s]
 86%|████████▌ | 3645/4250 [16:59<02:26,  4.14it/s]
 86%|████████▌ | 3646/4250 [16:59<02:15,  4.45it/s]
 86%|████████▌ | 3647/4250 [16:59<02:13,  4.52it/s]
 86%|████████▌ | 3648/4250 [16:59<02:13,  4.52it/s]
 86%|████████▌ | 3649/4250 [17:00<02:07,  4.70it/s]
 86%|████████▌ | 3650/4250 [17:00<02:05,  4.80it/s]
 86%|████████▌ | 3651/4250 [17:00<02:32,  3.93it/s]
 86%|████████▌ | 3652/4250 [17:00<02:26,  4.08it/s]
 86%|████████▌ | 3653/4250 [17:01<02:18,  4.32it/s]
 86%|████████▌ | 3654/4250 [17:01<02:53,  3.43it/s]
 86%|████████▌ | 3655/4250 [17:01<02:34,  3.86it/s]
 86%|████████▌ | 3656/4250 [17:01<02:27,  4.02it/s]
 86%|████████▌ | 3657/4250 [17:02<02:30,  3.95it/s]
 86%|████████▌ | 3658/4250 [17:02<02:37,  3.76it/s]
 86%|████████▌ | 3659/4250 [17:02<02:34,  3.82it/s]
 86%|████████▌ | 3660/4250 [17:02<02:22,  4.15it/s]
 86%|████████▌ | 3661/4250 [17:03<02:44,  3.59it/s]
 86%|████████▌ | 3662/4250 [17:03<02:31,  3.87it/s]
 86%|████████▌ | 3663/4250 [17:03<02:51,  3.41it/s]
 86%|████████▌ | 3664/4250 [17:04<02:54,  3.36it/s]
 86%|████████▌ | 3665/4250 [17:04<02:49,  3.45it/s]
 86%|████████▋ | 3666/4250 [17:04<02:46,  3.50it/s]
 86%|████████▋ | 3667/4250 [17:04<02:42,  3.59it/s]
 86%|████████▋ | 3668/4250 [17:05<02:32,  3.82it/s]
 86%|████████▋ | 3669/4250 [17:05<02:16,  4.24it/s]
 86%|████████▋ | 3670/4250 [17:05<02:07,  4.56it/s]
 86%|████████▋ | 3671/4250 [17:05<02:36,  3.71it/s]
 86%|████████▋ | 3672/4250 [17:06<02:29,  3.87it/s]
 86%|████████▋ | 3673/4250 [17:06<02:48,  3.42it/s]
 86%|████████▋ | 3674/4250 [17:06<02:26,  3.93it/s]
 86%|████████▋ | 3675/4250 [17:06<02:22,  4.05it/s]
 86%|████████▋ | 3676/4250 [17:07<02:09,  4.44it/s]
 87%|████████▋ | 3677/4250 [17:07<02:09,  4.43it/s]
 87%|████████▋ | 3678/4250 [17:07<02:18,  4.12it/s]
 87%|████████▋ | 3679/4250 [17:07<02:07,  4.47it/s]
 87%|████████▋ | 3680/4250 [17:08<02:28,  3.85it/s]
 87%|████████▋ | 3681/4250 [17:08<02:37,  3.61it/s]
 87%|████████▋ | 3682/4250 [17:08<02:25,  3.91it/s]
 87%|████████▋ | 3683/4250 [17:08<02:20,  4.03it/s]
 87%|████████▋ | 3684/4250 [17:09<02:09,  4.38it/s]
 87%|████████▋ | 3685/4250 [17:09<02:28,  3.79it/s]
 87%|████████▋ | 3686/4250 [17:09<02:20,  4.01it/s]
 87%|████████▋ | 3687/4250 [17:09<02:06,  4.43it/s]
 87%|████████▋ | 3688/4250 [17:10<02:15,  4.13it/s]
 87%|████████▋ | 3689/4250 [17:10<02:17,  4.09it/s]
 87%|████████▋ | 3690/4250 [17:10<02:15,  4.15it/s]
 87%|████████▋ | 3691/4250 [17:10<02:36,  3.58it/s]
 87%|████████▋ | 3692/4250 [17:11<02:30,  3.72it/s]
 87%|████████▋ | 3693/4250 [17:11<02:20,  3.97it/s]
 87%|████████▋ | 3694/4250 [17:11<02:13,  4.17it/s]
 87%|████████▋ | 3695/4250 [17:11<02:10,  4.26it/s]
 87%|████████▋ | 3696/4250 [17:12<02:09,  4.26it/s]
 87%|████████▋ | 3697/4250 [17:12<02:04,  4.45it/s]
 87%|████████▋ | 3698/4250 [17:12<02:06,  4.37it/s]
 87%|████████▋ | 3699/4250 [17:12<02:22,  3.86it/s]
 87%|████████▋ | 3700/4250 [17:13<02:19,  3.95it/s]
 87%|████████▋ | 3701/4250 [17:13<02:31,  3.63it/s]
 87%|████████▋ | 3702/4250 [17:13<02:16,  4.01it/s]
 87%|████████▋ | 3703/4250 [17:13<02:08,  4.26it/s]
 87%|████████▋ | 3704/4250 [17:13<02:07,  4.29it/s]
 87%|████████▋ | 3705/4250 [17:14<02:03,  4.41it/s]
 87%|████████▋ | 3706/4250 [17:14<02:02,  4.44it/s]
 87%|████████▋ | 3707/4250 [17:14<01:54,  4.74it/s]
 87%|████████▋ | 3708/4250 [17:14<01:59,  4.52it/s]
 87%|████████▋ | 3709/4250 [17:15<02:09,  4.17it/s]
 87%|████████▋ | 3710/4250 [17:15<02:00,  4.48it/s]
 87%|████████▋ | 3711/4250 [17:15<01:54,  4.69it/s]
 87%|████████▋ | 3712/4250 [17:15<01:54,  4.72it/s]
 87%|████████▋ | 3713/4250 [17:16<03:11,  2.81it/s]
 87%|████████▋ | 3714/4250 [17:16<02:47,  3.19it/s]
 87%|████████▋ | 3715/4250 [17:16<02:30,  3.55it/s]
 87%|████████▋ | 3716/4250 [17:17<02:29,  3.57it/s]
 87%|████████▋ | 3717/4250 [17:17<02:23,  3.71it/s]
 87%|████████▋ | 3718/4250 [17:17<02:20,  3.78it/s]
 88%|████████▊ | 3719/4250 [17:17<02:16,  3.90it/s]
 88%|████████▊ | 3720/4250 [17:18<02:26,  3.61it/s]
 88%|████████▊ | 3721/4250 [17:18<02:40,  3.31it/s]
 88%|████████▊ | 3722/4250 [17:18<02:19,  3.80it/s]
 88%|████████▊ | 3723/4250 [17:18<02:16,  3.87it/s]
 88%|████████▊ | 3724/4250 [17:19<02:27,  3.56it/s]
 88%|████████▊ | 3725/4250 [17:19<03:05,  2.83it/s]
 88%|████████▊ | 3726/4250 [17:20<02:41,  3.24it/s]
 88%|████████▊ | 3727/4250 [17:20<02:27,  3.54it/s]
 88%|████████▊ | 3728/4250 [17:20<02:10,  4.01it/s]
 88%|████████▊ | 3729/4250 [17:20<01:58,  4.41it/s]
 88%|████████▊ | 3730/4250 [17:20<01:53,  4.60it/s]
 88%|████████▊ | 3731/4250 [17:20<01:50,  4.68it/s]
 88%|████████▊ | 3732/4250 [17:21<01:53,  4.55it/s]
 88%|████████▊ | 3733/4250 [17:21<01:52,  4.60it/s]
 88%|████████▊ | 3734/4250 [17:21<01:51,  4.64it/s]
 88%|████████▊ | 3735/4250 [17:21<01:46,  4.83it/s]
 88%|████████▊ | 3736/4250 [17:22<02:00,  4.28it/s]
 88%|████████▊ | 3737/4250 [17:22<01:55,  4.44it/s]
 88%|████████▊ | 3738/4250 [17:22<01:49,  4.66it/s]
 88%|████████▊ | 3739/4250 [17:22<01:48,  4.71it/s]
 88%|████████▊ | 3740/4250 [17:22<01:42,  4.98it/s]
 88%|████████▊ | 3741/4250 [17:23<01:48,  4.69it/s]
 88%|████████▊ | 3742/4250 [17:23<02:04,  4.09it/s]
 88%|████████▊ | 3743/4250 [17:23<01:56,  4.36it/s]
 88%|████████▊ | 3744/4250 [17:23<02:03,  4.09it/s]
 88%|████████▊ | 3745/4250 [17:24<01:52,  4.47it/s]
 88%|████████▊ | 3746/4250 [17:24<02:37,  3.19it/s]
 88%|████████▊ | 3747/4250 [17:24<02:14,  3.74it/s]
 88%|████████▊ | 3748/4250 [17:25<02:14,  3.72it/s]
 88%|████████▊ | 3749/4250 [17:25<02:09,  3.88it/s]
 88%|████████▊ | 3750/4250 [17:25<02:01,  4.13it/s]
 88%|████████▊ | 3751/4250 [17:25<01:51,  4.49it/s]
 88%|████████▊ | 3752/4250 [17:25<01:52,  4.43it/s]
 88%|████████▊ | 3753/4250 [17:26<01:49,  4.54it/s]
 88%|████████▊ | 3754/4250 [17:26<01:49,  4.53it/s]
 88%|████████▊ | 3755/4250 [17:26<01:55,  4.27it/s]
 88%|████████▊ | 3756/4250 [17:26<01:46,  4.62it/s]
 88%|████████▊ | 3757/4250 [17:27<01:55,  4.25it/s]
 88%|████████▊ | 3758/4250 [17:27<02:09,  3.80it/s]
 88%|████████▊ | 3759/4250 [17:27<02:27,  3.33it/s]
 88%|████████▊ | 3760/4250 [17:27<02:12,  3.70it/s]
 88%|████████▊ | 3761/4250 [17:28<01:56,  4.19it/s]
 89%|████████▊ | 3762/4250 [17:28<02:06,  3.85it/s]
 89%|████████▊ | 3763/4250 [17:28<02:12,  3.67it/s]
 89%|████████▊ | 3764/4250 [17:28<02:09,  3.75it/s]
 89%|████████▊ | 3765/4250 [17:29<02:03,  3.92it/s]
 89%|████████▊ | 3766/4250 [17:29<01:52,  4.29it/s]
 89%|████████▊ | 3767/4250 [17:29<01:49,  4.41it/s]
 89%|████████▊ | 3768/4250 [17:29<01:40,  4.80it/s]
 89%|████████▊ | 3769/4250 [17:29<01:36,  4.96it/s]
 89%|████████▊ | 3770/4250 [17:30<01:47,  4.48it/s]
 89%|████████▊ | 3771/4250 [17:30<01:48,  4.40it/s]
 89%|████████▉ | 3772/4250 [17:30<01:40,  4.75it/s]
 89%|████████▉ | 3773/4250 [17:30<01:44,  4.56it/s]
 89%|████████▉ | 3774/4250 [17:31<01:43,  4.61it/s]
 89%|████████▉ | 3775/4250 [17:31<01:42,  4.64it/s]
 89%|████████▉ | 3776/4250 [17:31<01:37,  4.84it/s]
 89%|████████▉ | 3777/4250 [17:31<01:38,  4.81it/s]
 89%|████████▉ | 3778/4250 [17:31<01:42,  4.62it/s]
 89%|████████▉ | 3779/4250 [17:32<01:40,  4.71it/s]
 89%|████████▉ | 3780/4250 [17:32<01:47,  4.39it/s]
 89%|████████▉ | 3781/4250 [17:32<01:40,  4.65it/s]
 89%|████████▉ | 3782/4250 [17:32<01:38,  4.73it/s]
 89%|████████▉ | 3783/4250 [17:33<01:42,  4.56it/s]
 89%|████████▉ | 3784/4250 [17:33<01:33,  4.97it/s]
 89%|████████▉ | 3785/4250 [17:33<02:11,  3.53it/s]
 89%|████████▉ | 3786/4250 [17:33<02:04,  3.74it/s]
 89%|████████▉ | 3787/4250 [17:34<02:19,  3.31it/s]
 89%|████████▉ | 3788/4250 [17:34<02:14,  3.43it/s]
 89%|████████▉ | 3789/4250 [17:34<01:57,  3.93it/s]
 89%|████████▉ | 3790/4250 [17:34<01:48,  4.26it/s]
 89%|████████▉ | 3791/4250 [17:35<01:54,  4.01it/s]
 89%|████████▉ | 3792/4250 [17:35<01:53,  4.03it/s]
 89%|████████▉ | 3793/4250 [17:35<01:44,  4.35it/s]
 89%|████████▉ | 3794/4250 [17:35<01:51,  4.09it/s]
 89%|████████▉ | 3795/4250 [17:36<01:56,  3.92it/s]
 89%|████████▉ | 3796/4250 [17:36<01:50,  4.12it/s]
 89%|████████▉ | 3797/4250 [17:36<01:46,  4.24it/s]
 89%|████████▉ | 3798/4250 [17:36<01:45,  4.30it/s]
 89%|████████▉ | 3799/4250 [17:37<01:39,  4.53it/s]
 89%|████████▉ | 3800/4250 [17:37<01:46,  4.24it/s]
 89%|████████▉ | 3801/4250 [17:37<01:37,  4.58it/s]
 89%|████████▉ | 3802/4250 [17:37<01:30,  4.95it/s]
 89%|████████▉ | 3803/4250 [17:37<01:28,  5.04it/s]
 90%|████████▉ | 3804/4250 [17:38<01:33,  4.76it/s]
 90%|████████▉ | 3805/4250 [17:38<01:27,  5.11it/s]
 90%|████████▉ | 3806/4250 [17:38<01:43,  4.29it/s]
 90%|████████▉ | 3807/4250 [17:38<01:36,  4.60it/s]
 90%|████████▉ | 3808/4250 [17:38<01:27,  5.05it/s]
 90%|████████▉ | 3809/4250 [17:39<01:37,  4.50it/s]
 90%|████████▉ | 3810/4250 [17:39<01:43,  4.25it/s]
 90%|████████▉ | 3811/4250 [17:39<01:46,  4.11it/s]
 90%|████████▉ | 3812/4250 [17:39<01:36,  4.55it/s]
 90%|████████▉ | 3813/4250 [17:40<01:48,  4.03it/s]
 90%|████████▉ | 3814/4250 [17:40<01:41,  4.29it/s]
 90%|████████▉ | 3815/4250 [17:40<01:54,  3.81it/s]
 90%|████████▉ | 3816/4250 [17:40<01:41,  4.26it/s]
 90%|████████▉ | 3817/4250 [17:41<01:33,  4.65it/s]
 90%|████████▉ | 3818/4250 [17:41<01:29,  4.84it/s]
 90%|████████▉ | 3819/4250 [17:41<01:37,  4.42it/s]
 90%|████████▉ | 3820/4250 [17:41<01:36,  4.46it/s]
 90%|████████▉ | 3821/4250 [17:41<01:40,  4.28it/s]
 90%|████████▉ | 3822/4250 [17:42<01:31,  4.69it/s]
 90%|████████▉ | 3823/4250 [17:42<01:25,  5.00it/s]
 90%|████████▉ | 3824/4250 [17:42<01:24,  5.03it/s]
 90%|█████████ | 3825/4250 [17:42<01:31,  4.65it/s]
 90%|█████████ | 3826/4250 [17:42<01:31,  4.63it/s]
 90%|█████████ | 3827/4250 [17:43<01:29,  4.72it/s]
 90%|█████████ | 3828/4250 [17:43<01:28,  4.78it/s]
 90%|█████████ | 3829/4250 [17:43<01:42,  4.09it/s][INFO|trainer.py:805] 2024-08-30 20:43:32,652 >> 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 20:43:32,655 >> 
+***** Running Evaluation *****
+[INFO|trainer.py:3790] 2024-08-30 20:43:32,655 >>   Num examples = 6810
+[INFO|trainer.py:3793] 2024-08-30 20:43:32,655 >>   Batch size = 8
+{'eval_loss': 0.1294233798980713, 'eval_precision': 0.7938948817994033, 'eval_recall': 0.8093121197941039, 'eval_f1': 0.8015293708724366, 'eval_accuracy': 0.9767668584453568, 'eval_runtime': 14.774, 'eval_samples_per_second': 460.946, 'eval_steps_per_second': 57.669, 'epoch': 8.0}
+{'loss': 0.0053, 'grad_norm': 0.11404519528150558, 'learning_rate': 8.823529411764707e-06, 'epoch': 8.23}
+
+
  0%|          | 0/852 [00:00<?, ?it/s]
+
  1%|          | 10/852 [00:00<00:08, 94.75it/s]
+
  2%|▏         | 20/852 [00:00<00:09, 84.41it/s]
+
  3%|▎         | 29/852 [00:00<00:09, 82.78it/s]
+
  4%|▍         | 38/852 [00:00<00:09, 81.94it/s]
+
  6%|▌         | 47/852 [00:00<00:09, 82.75it/s]
+
  7%|▋         | 56/852 [00:00<00:09, 83.21it/s]
+
  8%|▊         | 65/852 [00:00<00:09, 81.64it/s]
+
  9%|▊         | 74/852 [00:00<00:09, 80.44it/s]
+
 10%|▉         | 83/852 [00:01<00:09, 80.52it/s]
+
 11%|█         | 92/852 [00:01<00:09, 80.86it/s]
+
 12%|█▏        | 101/852 [00:01<00:09, 80.27it/s]
+
 13%|█▎        | 110/852 [00:01<00:09, 79.98it/s]
+
 14%|█▍        | 119/852 [00:01<00:09, 80.67it/s]
+
 15%|█▌        | 128/852 [00:01<00:09, 77.69it/s]
+
 16%|█▌        | 137/852 [00:01<00:09, 77.69it/s]
+
 17%|█▋        | 146/852 [00:01<00:08, 78.94it/s]
+
 18%|█▊        | 154/852 [00:01<00:08, 79.19it/s]
+
 19%|█▉        | 163/852 [00:02<00:08, 80.85it/s]
+
 20%|██        | 172/852 [00:02<00:08, 81.65it/s]
+
 21%|██        | 181/852 [00:02<00:08, 81.83it/s]
+
 22%|██▏       | 190/852 [00:02<00:07, 83.10it/s]
+
 23%|██▎       | 199/852 [00:02<00:07, 82.56it/s]
+
 24%|██▍       | 208/852 [00:02<00:07, 81.21it/s]
+
 25%|██▌       | 217/852 [00:02<00:07, 81.35it/s]
+
 27%|██▋       | 226/852 [00:02<00:07, 81.04it/s]
+
 28%|██▊       | 235/852 [00:02<00:07, 81.38it/s]
+
 29%|██▊       | 244/852 [00:03<00:07, 78.41it/s]
+
 30%|██▉       | 253/852 [00:03<00:07, 80.66it/s]
+
 31%|███       | 262/852 [00:03<00:07, 81.83it/s]
+
 32%|███▏      | 271/852 [00:03<00:07, 80.77it/s]
+
 33%|███▎      | 280/852 [00:03<00:07, 81.68it/s]
+
 34%|███▍      | 289/852 [00:03<00:06, 80.93it/s]
+
 35%|███▍      | 298/852 [00:03<00:06, 81.54it/s]
+
 36%|███▌      | 307/852 [00:03<00:06, 82.54it/s]
+
 37%|███▋      | 316/852 [00:03<00:06, 80.63it/s]
+
 38%|███▊      | 325/852 [00:04<00:06, 80.73it/s]
+
 39%|███▉      | 334/852 [00:04<00:06, 80.54it/s]
+
 40%|████      | 343/852 [00:04<00:06, 81.78it/s]
+
 41%|████▏     | 352/852 [00:04<00:06, 81.65it/s]
+
 42%|████▏     | 361/852 [00:04<00:06, 79.42it/s]
+
 43%|████▎     | 370/852 [00:04<00:06, 80.20it/s]
+
 44%|████▍     | 379/852 [00:04<00:05, 80.28it/s]
+
 46%|████▌     | 388/852 [00:04<00:05, 79.82it/s]
+
 47%|████▋     | 397/852 [00:04<00:05, 80.72it/s]
+
 48%|████▊     | 406/852 [00:05<00:05, 78.03it/s]
+
 49%|████▊     | 415/852 [00:05<00:05, 79.05it/s]
+
 50%|████▉     | 424/852 [00:05<00:05, 79.88it/s]
+
 51%|█████     | 433/852 [00:05<00:05, 79.61it/s]
+
 52%|█████▏    | 442/852 [00:05<00:05, 80.90it/s]
+
 53%|█████▎    | 451/852 [00:05<00:04, 81.08it/s]
+
 54%|█████▍    | 460/852 [00:05<00:04, 80.48it/s]
+
 55%|█████▌    | 469/852 [00:05<00:04, 78.62it/s]
+
 56%|█████▌    | 477/852 [00:05<00:04, 75.74it/s]
+
 57%|█████▋    | 485/852 [00:06<00:04, 75.79it/s]
+
 58%|█████▊    | 494/852 [00:06<00:04, 78.23it/s]
+
 59%|█████▉    | 503/852 [00:06<00:04, 80.14it/s]
+
 60%|██████    | 512/852 [00:06<00:04, 80.16it/s]
+
 61%|██████    | 521/852 [00:06<00:04, 79.20it/s]
+
 62%|██████▏   | 529/852 [00:06<00:04, 78.30it/s]
+
 63%|██████▎   | 537/852 [00:06<00:04, 78.59it/s]
+
 64%|██████▍   | 545/852 [00:06<00:03, 78.89it/s]
+
 65%|██████▍   | 553/852 [00:06<00:03, 77.01it/s]
+
 66%|██████▌   | 561/852 [00:06<00:03, 77.30it/s]
+
 67%|██████▋   | 570/852 [00:07<00:03, 78.14it/s]
+
 68%|██████▊   | 578/852 [00:07<00:03, 77.85it/s]
+
 69%|██████▉   | 586/852 [00:07<00:03, 78.04it/s]
+
 70%|██████▉   | 595/852 [00:07<00:03, 79.15it/s]
+
 71%|███████   | 604/852 [00:07<00:03, 79.49it/s]
+
 72%|███████▏  | 612/852 [00:07<00:03, 78.20it/s]
+
 73%|███████▎  | 620/852 [00:07<00:02, 78.36it/s]
+
 74%|███████▎  | 628/852 [00:07<00:02, 77.45it/s]
+
 75%|███████▍  | 636/852 [00:07<00:02, 75.82it/s]
+
 76%|███████▌  | 644/852 [00:08<00:02, 72.49it/s]
+
 77%|███████▋  | 652/852 [00:08<00:02, 73.94it/s]
+
 77%|███████▋  | 660/852 [00:08<00:02, 74.46it/s]
+
 78%|███████▊  | 668/852 [00:08<00:02, 73.75it/s]
+
 79%|███████▉  | 676/852 [00:08<00:02, 73.60it/s]
+
 80%|████████  | 684/852 [00:08<00:02, 73.69it/s]
+
 81%|████████  | 692/852 [00:08<00:02, 74.72it/s]
+
 82%|████████▏ | 700/852 [00:08<00:02, 75.02it/s]
+
 83%|████████��� | 708/852 [00:08<00:01, 76.07it/s]
+
 84%|████████▍ | 716/852 [00:09<00:01, 75.73it/s]
+
 85%|████████▍ | 724/852 [00:09<00:01, 75.75it/s]
+
 86%|████████▌ | 732/852 [00:09<00:01, 76.10it/s]
+
 87%|████████▋ | 740/852 [00:09<00:01, 76.51it/s]
+
 88%|████████▊ | 748/852 [00:09<00:01, 75.96it/s]
+
 89%|████████▊ | 756/852 [00:09<00:01, 75.69it/s]
+
 90%|████████▉ | 764/852 [00:09<00:01, 76.06it/s]
+
 91%|█████████ | 772/852 [00:09<00:01, 73.73it/s]
+
 92%|█████████▏| 780/852 [00:09<00:00, 72.56it/s]
+
 92%|█████████▏| 788/852 [00:10<00:00, 72.74it/s]
+
 93%|█████████▎| 796/852 [00:10<00:00, 73.32it/s]
+
 94%|█████████▍| 804/852 [00:10<00:00, 73.56it/s]
+
 95%|█████████▌| 812/852 [00:10<00:00, 72.12it/s]
+
 96%|█████████▌| 820/852 [00:10<00:00, 72.20it/s]
+
 97%|█████████▋| 828/852 [00:10<00:00, 73.55it/s]
+
 98%|█████████▊| 836/852 [00:10<00:00, 73.27it/s]
+
 99%|█████████▉| 844/852 [00:10<00:00, 70.70it/s]
+
                                                   
+
                                                 
 90%|█████████ | 3829/4250 [17:58<01:42,  4.09it/s]
+
+
                                                 [INFO|trainer.py:3478] 2024-08-30 20:43:47,100 >> Saving model checkpoint to /content/dissertation/scripts/ner/output/checkpoint-3829
+[INFO|configuration_utils.py:472] 2024-08-30 20:43:47,101 >> Configuration saved in /content/dissertation/scripts/ner/output/checkpoint-3829/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 20:43:48,426 >> Model weights saved in /content/dissertation/scripts/ner/output/checkpoint-3829/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:43:48,427 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/checkpoint-3829/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:43:48,428 >> Special tokens file saved in /content/dissertation/scripts/ner/output/checkpoint-3829/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:43:50,869 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:43:50,869 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+
 90%|█████████ | 3830/4250 [18:02<40:12,  5.74s/it]
 90%|█████████ | 3831/4250 [18:02<28:31,  4.08s/it]
 90%|█████████ | 3832/4250 [18:02<20:17,  2.91s/it]
 90%|█████████ | 3833/4250 [18:02<14:41,  2.11s/it]
 90%|█████████ | 3834/4250 [18:03<10:39,  1.54s/it]
 90%|█████████ | 3835/4250 [18:03<08:04,  1.17s/it]
 90%|█████████ | 3836/4250 [18:03<06:02,  1.14it/s]
 90%|█████████ | 3837/4250 [18:03<04:54,  1.40it/s]
 90%|█████████ | 3838/4250 [18:04<03:47,  1.81it/s]
 90%|█████████ | 3839/4250 [18:04<03:39,  1.87it/s]
 90%|█████████ | 3840/4250 [18:04<02:53,  2.36it/s]
 90%|█████████ | 3841/4250 [18:05<02:27,  2.77it/s]
 90%|█████████ | 3842/4250 [18:05<02:22,  2.86it/s]
 90%|█████████ | 3843/4250 [18:05<02:01,  3.34it/s]
 90%|█████████ | 3844/4250 [18:05<02:03,  3.28it/s]
 90%|█████████ | 3845/4250 [18:06<01:49,  3.71it/s]
 90%|█████████ | 3846/4250 [18:06<01:41,  3.97it/s]
 91%|█████████ | 3847/4250 [18:06<01:36,  4.17it/s]
 91%|█████████ | 3848/4250 [18:06<01:27,  4.58it/s]
 91%|█████████ | 3849/4250 [18:06<01:22,  4.87it/s]
 91%|█████████ | 3850/4250 [18:07<01:37,  4.11it/s]
 91%|█████████ | 3851/4250 [18:07<01:36,  4.15it/s]
 91%|█████████ | 3852/4250 [18:07<01:28,  4.52it/s]
 91%|█████████ | 3853/4250 [18:07<01:23,  4.75it/s]
 91%|█████████ | 3854/4250 [18:07<01:30,  4.39it/s]
 91%|█████████ | 3855/4250 [18:08<01:26,  4.56it/s]
 91%|█████████ | 3856/4250 [18:08<01:28,  4.43it/s]
 91%|█████████ | 3857/4250 [18:08<01:31,  4.29it/s]
 91%|█████████ | 3858/4250 [18:08<01:31,  4.29it/s]
 91%|█████████ | 3859/4250 [18:09<01:56,  3.36it/s]
 91%|█████████ | 3860/4250 [18:09<01:49,  3.57it/s]
 91%|█████████ | 3861/4250 [18:09<01:50,  3.52it/s]
 91%|█████████ | 3862/4250 [18:10<01:38,  3.94it/s]
 91%|█████████ | 3863/4250 [18:10<01:46,  3.62it/s]
 91%|█████████ | 3864/4250 [18:10<01:46,  3.63it/s]
 91%|█████████ | 3865/4250 [18:10<01:46,  3.60it/s]
 91%|█████████ | 3866/4250 [18:11<01:40,  3.83it/s]
 91%|█████████ | 3867/4250 [18:11<01:34,  4.07it/s]
 91%|█████████ | 3868/4250 [18:11<01:34,  4.06it/s]
 91%|█████████ | 3869/4250 [18:11<01:32,  4.14it/s]
 91%|█████████ | 3870/4250 [18:12<01:30,  4.18it/s]
 91%|█████████ | 3871/4250 [18:12<01:33,  4.06it/s]
 91%|█████████ | 3872/4250 [18:12<01:28,  4.29it/s]
 91%|█████████ | 3873/4250 [18:12<01:20,  4.70it/s]
 91%|█████████ | 3874/4250 [18:13<01:35,  3.95it/s]
 91%|█████████ | 3875/4250 [18:13<01:29,  4.19it/s]
 91%|█████████ | 3876/4250 [18:13<01:22,  4.54it/s]
 91%|█████████ | 3877/4250 [18:13<01:14,  4.98it/s]
 91%|█████████ | 3878/4250 [18:13<01:26,  4.31it/s]
 91%|█████████▏| 3879/4250 [18:14<01:21,  4.58it/s]
 91%|█████████▏| 3880/4250 [18:14<01:22,  4.46it/s]
 91%|█████████▏| 3881/4250 [18:14<01:17,  4.78it/s]
 91%|█████████▏| 3882/4250 [18:14<01:24,  4.36it/s]
 91%|█████████▏| 3883/4250 [18:15<01:51,  3.30it/s]
 91%|█████████▏| 3884/4250 [18:15<01:50,  3.30it/s]
 91%|█████████▏| 3885/4250 [18:15<01:49,  3.33it/s]
 91%|█████████▏| 3886/4250 [18:16<01:36,  3.77it/s]
 91%|█████████▏| 3887/4250 [18:16<01:30,  4.03it/s]
 91%|█████████▏| 3888/4250 [18:16<01:26,  4.16it/s]
 92%|█████████▏| 3889/4250 [18:16<01:24,  4.28it/s]