Version_Test_ASAP_FineTuningBERT_AugV14_k3_task1_organization_k3_k3_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: 0.5334
• Qwk: 0.5916
• Mse: 0.5326
• Rmse: 0.7298

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	3	9.8047	0.0030	9.8020	3.1308
No log	2.0	6	7.3059	0.0	7.3034	2.7025
No log	3.0	9	4.6929	0.0237	4.6907	2.1658
No log	4.0	12	3.4553	0.0	3.4531	1.8583
No log	5.0	15	2.0855	0.0794	2.0841	1.4436
No log	6.0	18	1.5727	0.0365	1.5708	1.2533
No log	7.0	21	1.1053	0.0	1.1042	1.0508
No log	8.0	24	1.0008	-0.0025	0.9993	0.9997
No log	9.0	27	0.8487	0.1172	0.8479	0.9208
No log	10.0	30	0.9664	0.0642	0.9656	0.9827
No log	11.0	33	0.6648	0.3082	0.6637	0.8147
No log	12.0	36	0.7291	0.3076	0.7284	0.8535
No log	13.0	39	0.5639	0.4041	0.5630	0.7504
No log	14.0	42	0.4807	0.5968	0.4799	0.6928
No log	15.0	45	0.4937	0.6033	0.4930	0.7021
No log	16.0	48	0.5912	0.5731	0.5906	0.7685
No log	17.0	51	0.4923	0.6251	0.4914	0.7010
No log	18.0	54	0.9909	0.4779	0.9907	0.9953
No log	19.0	57	0.5170	0.5882	0.5161	0.7184
No log	20.0	60	0.7444	0.5285	0.7440	0.8625
No log	21.0	63	0.6413	0.5757	0.6408	0.8005
No log	22.0	66	0.4618	0.6174	0.4610	0.6790
No log	23.0	69	0.8142	0.5331	0.8137	0.9020
No log	24.0	72	0.7058	0.5307	0.7052	0.8398
No log	25.0	75	0.8209	0.5200	0.8205	0.9058
No log	26.0	78	0.4949	0.6293	0.4943	0.7031
No log	27.0	81	0.6427	0.5988	0.6423	0.8015
No log	28.0	84	0.4760	0.6185	0.4752	0.6894
No log	29.0	87	0.6597	0.5621	0.6591	0.8118
No log	30.0	90	0.6626	0.5718	0.6621	0.8137
No log	31.0	93	0.5024	0.6123	0.5017	0.7083
No log	32.0	96	0.6490	0.6091	0.6485	0.8053
No log	33.0	99	0.5373	0.5857	0.5366	0.7325
No log	34.0	102	0.9204	0.4969	0.9199	0.9591
No log	35.0	105	0.5568	0.5766	0.5561	0.7457
No log	36.0	108	0.7656	0.5433	0.7651	0.8747
No log	37.0	111	0.5321	0.5716	0.5314	0.7290
No log	38.0	114	0.7321	0.5137	0.7315	0.8553
No log	39.0	117	0.7780	0.5467	0.7775	0.8817
No log	40.0	120	0.5065	0.6012	0.5059	0.7113
No log	41.0	123	0.7976	0.5782	0.7972	0.8928
No log	42.0	126	0.7353	0.5815	0.7348	0.8572
No log	43.0	129	0.5259	0.6020	0.5252	0.7247
No log	44.0	132	0.8974	0.4893	0.8969	0.9470
No log	45.0	135	0.7172	0.4915	0.7164	0.8464
No log	46.0	138	0.5334	0.5916	0.5326	0.7298

Framework versions

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