ASAP_FineTuningBERT_AugV8_k7_task1_organization_k7_fold1

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: 0.7989
• Qwk: 0.4914
• Mse: 0.7989
• Rmse: 0.8938

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	6	5.2573	0.0377	5.2552	2.2924
No log	2.0	12	2.5087	-0.0010	2.5070	1.5833
No log	3.0	18	1.3849	0.0	1.3834	1.1762
No log	4.0	24	1.7612	-0.0038	1.7595	1.3265
No log	5.0	30	1.1366	0.0	1.1351	1.0654
No log	6.0	36	1.1223	0.0442	1.1215	1.0590
No log	7.0	42	1.2324	0.1867	1.2315	1.1097
No log	8.0	48	1.1346	0.2782	1.1336	1.0647
No log	9.0	54	1.3104	0.2176	1.3096	1.1444
No log	10.0	60	1.1616	0.2879	1.1610	1.0775
No log	11.0	66	1.1562	0.3156	1.1560	1.0752
No log	12.0	72	0.8712	0.4681	0.8713	0.9334
No log	13.0	78	0.8865	0.4659	0.8865	0.9415
No log	14.0	84	0.8601	0.4374	0.8600	0.9274
No log	15.0	90	0.8758	0.4471	0.8758	0.9358
No log	16.0	96	0.8737	0.4367	0.8738	0.9348
No log	17.0	102	0.8386	0.4546	0.8387	0.9158
No log	18.0	108	1.0156	0.3793	1.0155	1.0077
No log	19.0	114	1.3565	0.3169	1.3562	1.1646
No log	20.0	120	0.8249	0.4701	0.8249	0.9082
No log	21.0	126	0.9193	0.4403	0.9193	0.9588
No log	22.0	132	0.8230	0.4363	0.8229	0.9072
No log	23.0	138	0.7801	0.4878	0.7800	0.8832
No log	24.0	144	0.7798	0.5001	0.7797	0.8830
No log	25.0	150	0.8299	0.4664	0.8297	0.9109
No log	26.0	156	1.0127	0.3930	1.0125	1.0062
No log	27.0	162	0.8689	0.4114	0.8687	0.9321
No log	28.0	168	0.8844	0.4035	0.8845	0.9405
No log	29.0	174	0.8088	0.4435	0.8088	0.8994
No log	30.0	180	0.9039	0.4212	0.9039	0.9508
No log	31.0	186	0.7896	0.4756	0.7897	0.8886
No log	32.0	192	0.7748	0.4766	0.7748	0.8802
No log	33.0	198	0.8010	0.4585	0.8009	0.8949
No log	34.0	204	0.7989	0.4914	0.7989	0.8938

Framework versions

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