ASAP_FineTuningBERT_AugV8_k4_task1_organization_k4_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: 0.9752
• Qwk: 0.3807
• Mse: 0.9744
• Rmse: 0.9871

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	9.2691	0.0	9.2691	3.0445
No log	2.0	8	5.3661	0.0533	5.3666	2.3166
No log	3.0	12	3.4664	0.0039	3.4668	1.8619
No log	4.0	16	1.9775	0.0957	1.9779	1.4064
No log	5.0	20	1.6049	0.0345	1.6053	1.2670
No log	6.0	24	0.8954	0.0728	0.8958	0.9464
No log	7.0	28	1.4845	0.0539	1.4848	1.2185
No log	8.0	32	0.9713	0.0741	0.9716	0.9857
No log	9.0	36	1.3177	0.0345	1.3180	1.1480
No log	10.0	40	1.4006	0.1129	1.4009	1.1836
No log	11.0	44	1.2372	0.2359	1.2374	1.1124
No log	12.0	48	0.7123	0.4530	0.7124	0.8440
No log	13.0	52	0.8598	0.3303	0.8599	0.9273
No log	14.0	56	0.6567	0.4272	0.6566	0.8103
No log	15.0	60	0.6643	0.4184	0.6639	0.8148
No log	16.0	64	0.7464	0.3432	0.7461	0.8638
No log	17.0	68	0.8292	0.3114	0.8290	0.9105
No log	18.0	72	1.0477	0.3492	1.0468	1.0231
No log	19.0	76	0.8961	0.3822	0.8953	0.9462
No log	20.0	80	0.9472	0.3964	0.9462	0.9727
No log	21.0	84	0.9641	0.4001	0.9633	0.9815
No log	22.0	88	0.9752	0.3807	0.9744	0.9871

Framework versions

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