ASAP_FineTuningBERT_AugV8_k2_task1_organization_fold3

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: 1.2006
• Qwk: 0.2952
• Mse: 1.2003
• Rmse: 1.0956

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	9.7213	0.0018	9.7204	3.1178
No log	2.0	4	6.5594	0.0	6.5590	2.5610
No log	3.0	6	4.7546	0.0076	4.7545	2.1805
No log	4.0	8	3.7279	0.0	3.7279	1.9308
5.5568	5.0	10	3.0304	0.0	3.0306	1.7408
5.5568	6.0	12	2.3843	0.1141	2.3847	1.5443
5.5568	7.0	14	2.0508	0.0283	2.0512	1.4322
5.5568	8.0	16	1.5329	0.0202	1.5336	1.2384
5.5568	9.0	18	1.2167	0.0202	1.2175	1.1034
2.1277	10.0	20	1.2072	0.0983	1.2077	1.0989
2.1277	11.0	22	1.3225	0.1595	1.3228	1.1501
2.1277	12.0	24	1.1398	0.1653	1.1401	1.0678
2.1277	13.0	26	0.9363	0.1656	0.9367	0.9678
2.1277	14.0	28	0.9429	0.1890	0.9432	0.9712
1.7936	15.0	30	1.2804	0.1936	1.2806	1.1316
1.7936	16.0	32	1.3944	0.2227	1.3944	1.1809
1.7936	17.0	34	1.2971	0.3513	1.2970	1.1389
1.7936	18.0	36	1.0590	0.4595	1.0590	1.0291
1.7936	19.0	38	1.1365	0.3514	1.1364	1.0660
1.4754	20.0	40	0.8608	0.4748	0.8607	0.9278
1.4754	21.0	42	0.8912	0.4264	0.8912	0.9440
1.4754	22.0	44	0.8548	0.4488	0.8547	0.9245
1.4754	23.0	46	0.7108	0.5211	0.7107	0.8430
1.4754	24.0	48	0.9096	0.4145	0.9095	0.9537
0.8721	25.0	50	0.8851	0.3928	0.8850	0.9407
0.8721	26.0	52	0.7125	0.5070	0.7124	0.8440
0.8721	27.0	54	1.1005	0.2778	1.1005	1.0490
0.8721	28.0	56	1.0705	0.2818	1.0704	1.0346
0.8721	29.0	58	0.7957	0.4641	0.7955	0.8919
0.5043	30.0	60	1.0409	0.3147	1.0408	1.0202
0.5043	31.0	62	0.9785	0.3532	0.9783	0.9891
0.5043	32.0	64	0.8540	0.4761	0.8535	0.9239
0.5043	33.0	66	1.2006	0.2952	1.2003	1.0956

Framework versions

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