ASAP_FineTuningBERT_AugV8_k4_task1_organization_k4_fold0

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: 0.6516
• Qwk: 0.5298
• Mse: 0.6516
• Rmse: 0.8072

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	7.7750	0.0	7.7750	2.7884
No log	2.0	8	6.0952	-0.0078	6.0952	2.4689
No log	3.0	12	4.3086	0.0039	4.3086	2.0757
No log	4.0	16	2.8934	0.0	2.8934	1.7010
No log	5.0	20	1.8576	0.0484	1.8576	1.3629
No log	6.0	24	1.2958	0.0316	1.2958	1.1383
No log	7.0	28	1.7412	0.0601	1.7412	1.3195
No log	8.0	32	0.9508	0.0316	0.9508	0.9751
No log	9.0	36	1.4880	0.0553	1.4880	1.2199
No log	10.0	40	1.3014	0.1107	1.3014	1.1408
No log	11.0	44	1.1317	0.1010	1.1317	1.0638
No log	12.0	48	0.7572	0.4011	0.7572	0.8702
No log	13.0	52	0.6153	0.4312	0.6153	0.7844
No log	14.0	56	0.5995	0.4280	0.5995	0.7743
No log	15.0	60	0.5571	0.4248	0.5571	0.7464
No log	16.0	64	0.5555	0.4404	0.5555	0.7454
No log	17.0	68	0.5835	0.5235	0.5835	0.7638
No log	18.0	72	0.5891	0.5287	0.5891	0.7676
No log	19.0	76	0.5782	0.5255	0.5782	0.7604
No log	20.0	80	0.6654	0.5037	0.6654	0.8157
No log	21.0	84	0.6785	0.4953	0.6785	0.8237
No log	22.0	88	0.6349	0.5266	0.6349	0.7968
No log	23.0	92	0.6461	0.5194	0.6461	0.8038
No log	24.0	96	0.6653	0.5501	0.6653	0.8157
No log	25.0	100	0.6932	0.5362	0.6932	0.8326
No log	26.0	104	0.6632	0.5354	0.6632	0.8144
No log	27.0	108	0.6092	0.5435	0.6092	0.7805
No log	28.0	112	0.6149	0.5668	0.6149	0.7842
No log	29.0	116	0.7618	0.5198	0.7618	0.8728
No log	30.0	120	0.6068	0.5627	0.6068	0.7789
No log	31.0	124	0.6041	0.5638	0.6041	0.7772
No log	32.0	128	0.6448	0.5562	0.6448	0.8030
No log	33.0	132	0.6716	0.5480	0.6716	0.8195
No log	34.0	136	0.7095	0.5311	0.7095	0.8423
No log	35.0	140	0.7092	0.5466	0.7092	0.8421
No log	36.0	144	0.6560	0.5351	0.6560	0.8099
No log	37.0	148	0.7108	0.5377	0.7108	0.8431
No log	38.0	152	0.6516	0.5298	0.6516	0.8072

Framework versions

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