ASAP_FineTuningBERT_AugV8_k2_task1_organization_k2_fold2

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7416
• Qwk: 0.4922
• Mse: 0.7414
• Rmse: 0.8611

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	10.3400	0.0004	10.3400	3.2156
No log	2.0	4	7.1380	0.0	7.1384	2.6718
No log	3.0	6	4.9739	0.0127	4.9744	2.2303
No log	4.0	8	3.7366	0.0	3.7370	1.9331
No log	5.0	10	2.8549	0.0	2.8553	1.6898
No log	6.0	12	2.4771	-0.0162	2.4775	1.5740
No log	7.0	14	1.5486	0.0107	1.5490	1.2446
No log	8.0	16	2.0528	0.0511	2.0530	1.4328
No log	9.0	18	1.1497	0.0	1.1500	1.0724
No log	10.0	20	1.0578	0.0	1.0583	1.0287
No log	11.0	22	1.1125	0.0	1.1130	1.0550
No log	12.0	24	1.1155	0.0136	1.1159	1.0564
No log	13.0	26	1.3284	0.0897	1.3288	1.1527
No log	14.0	28	1.2362	0.1292	1.2365	1.1120
No log	15.0	30	0.9294	0.2427	0.9296	0.9642
No log	16.0	32	0.8378	0.4047	0.8380	0.9154
No log	17.0	34	1.0062	0.2982	1.0064	1.0032
No log	18.0	36	0.9553	0.3507	0.9556	0.9775
No log	19.0	38	0.6189	0.5138	0.6189	0.7867
No log	20.0	40	0.5981	0.4394	0.5981	0.7734
No log	21.0	42	0.6043	0.4791	0.6045	0.7775
No log	22.0	44	0.5920	0.4736	0.5922	0.7695
No log	23.0	46	0.6177	0.4149	0.6179	0.7861
No log	24.0	48	0.6335	0.3777	0.6337	0.7961
No log	25.0	50	0.6151	0.3935	0.6152	0.7844
No log	26.0	52	0.6505	0.4043	0.6505	0.8065
No log	27.0	54	0.7290	0.3489	0.7290	0.8538
No log	28.0	56	0.6644	0.4271	0.6643	0.8151
No log	29.0	58	0.5694	0.5605	0.5694	0.7546
No log	30.0	60	0.6181	0.5514	0.6180	0.7861
No log	31.0	62	0.7857	0.3964	0.7855	0.8863
No log	32.0	64	0.7133	0.4335	0.7131	0.8445
No log	33.0	66	0.6362	0.5360	0.6362	0.7976
No log	34.0	68	0.7403	0.5154	0.7401	0.8603
No log	35.0	70	0.7334	0.5308	0.7332	0.8563
No log	36.0	72	0.6273	0.5713	0.6273	0.7920
No log	37.0	74	0.7286	0.5182	0.7285	0.8535
No log	38.0	76	0.9513	0.4302	0.9509	0.9752
No log	39.0	78	0.8116	0.4678	0.8114	0.9008
No log	40.0	80	0.6281	0.5375	0.6282	0.7926
No log	41.0	82	0.7424	0.4658	0.7424	0.8616
No log	42.0	84	0.9882	0.4166	0.9878	0.9939
No log	43.0	86	0.7104	0.4837	0.7103	0.8428
No log	44.0	88	0.7206	0.4959	0.7204	0.8488
No log	45.0	90	0.9736	0.4240	0.9732	0.9865
No log	46.0	92	0.7416	0.4922	0.7414	0.8611

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0