Version_Test_ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_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: 0.6278
• Qwk: 0.6047
• Mse: 0.6275
• Rmse: 0.7921

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	4	6.9608	0.0	6.9610	2.6384
No log	2.0	8	4.1239	0.0	4.1242	2.0308
No log	3.0	12	2.4639	0.0451	2.4643	1.5698
No log	4.0	16	1.4713	0.0107	1.4719	1.2132
No log	5.0	20	0.9159	0.0	0.9164	0.9573
No log	6.0	24	0.8217	0.0592	0.8222	0.9067
No log	7.0	28	0.7869	0.1305	0.7870	0.8871
No log	8.0	32	0.5769	0.4875	0.5765	0.7593
No log	9.0	36	1.2039	0.3855	1.2034	1.0970
No log	10.0	40	0.7219	0.5504	0.7213	0.8493
No log	11.0	44	0.5855	0.5053	0.5851	0.7649
No log	12.0	48	0.5793	0.6124	0.5789	0.7608
No log	13.0	52	0.6014	0.5063	0.6011	0.7753
No log	14.0	56	0.5462	0.6095	0.5457	0.7387
No log	15.0	60	0.5715	0.6156	0.5710	0.7556
No log	16.0	64	0.6117	0.6076	0.6113	0.7818
No log	17.0	68	0.6316	0.5872	0.6312	0.7945
No log	18.0	72	0.6118	0.5986	0.6114	0.7819
No log	19.0	76	0.5845	0.6070	0.5842	0.7643
No log	20.0	80	0.6532	0.6212	0.6526	0.8078
No log	21.0	84	0.5561	0.6170	0.5557	0.7455
No log	22.0	88	0.7184	0.6027	0.7178	0.8472
No log	23.0	92	0.5178	0.6124	0.5175	0.7194
No log	24.0	96	0.7115	0.5447	0.7110	0.8432
No log	25.0	100	0.5995	0.6070	0.5991	0.7740
No log	26.0	104	0.5932	0.6179	0.5929	0.7700
No log	27.0	108	0.7895	0.5480	0.7891	0.8883
No log	28.0	112	0.8963	0.5325	0.8958	0.9465
No log	29.0	116	0.6200	0.6002	0.6196	0.7872
No log	30.0	120	0.9308	0.5617	0.9301	0.9644
No log	31.0	124	0.5955	0.6092	0.5951	0.7714
No log	32.0	128	0.6985	0.5962	0.6980	0.8355
No log	33.0	132	0.7799	0.5605	0.7794	0.8828
No log	34.0	136	0.7241	0.5720	0.7237	0.8507
No log	35.0	140	0.9519	0.5046	0.9514	0.9754
No log	36.0	144	0.6803	0.5748	0.6800	0.8246
No log	37.0	148	0.7750	0.5386	0.7747	0.8802
No log	38.0	152	0.8747	0.5154	0.8743	0.9350
No log	39.0	156	0.6594	0.5456	0.6592	0.8119
No log	40.0	160	0.6278	0.6047	0.6275	0.7921

Framework versions

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