Version3_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_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: 0.7743
• Qwk: 0.5245
• Mse: 0.7743
• Rmse: 0.8800

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	2	9.2496	-0.0001	9.2496	3.0413
No log	2.0	4	6.9806	0.0	6.9806	2.6421
No log	3.0	6	5.0875	0.0201	5.0875	2.2555
No log	4.0	8	4.2141	0.0039	4.2141	2.0528
No log	5.0	10	3.0463	0.0	3.0463	1.7454
No log	6.0	12	2.3445	0.1320	2.3445	1.5312
No log	7.0	14	1.8738	0.0484	1.8738	1.3689
No log	8.0	16	1.3862	0.0316	1.3862	1.1774
No log	9.0	18	1.0828	0.0316	1.0828	1.0406
No log	10.0	20	0.9196	0.0661	0.9196	0.9589
No log	11.0	22	0.7370	0.4070	0.7370	0.8585
No log	12.0	24	0.7468	0.4012	0.7468	0.8642
No log	13.0	26	0.6084	0.4026	0.6084	0.7800
No log	14.0	28	0.6307	0.4334	0.6307	0.7942
No log	15.0	30	0.6221	0.5217	0.6221	0.7888
No log	16.0	32	0.7180	0.5114	0.7180	0.8473
No log	17.0	34	0.5187	0.5016	0.5187	0.7202
No log	18.0	36	0.6071	0.5379	0.6071	0.7792
No log	19.0	38	0.6245	0.5279	0.6245	0.7903
No log	20.0	40	0.5582	0.5267	0.5582	0.7472
No log	21.0	42	0.7587	0.4711	0.7587	0.8710
No log	22.0	44	0.6011	0.5265	0.6011	0.7753
No log	23.0	46	0.5856	0.5897	0.5856	0.7653
No log	24.0	48	0.6329	0.5303	0.6329	0.7955
No log	25.0	50	0.6139	0.5825	0.6139	0.7835
No log	26.0	52	0.6415	0.5727	0.6415	0.8010
No log	27.0	54	0.6984	0.5271	0.6984	0.8357
No log	28.0	56	0.6809	0.5511	0.6809	0.8252
No log	29.0	58	0.6917	0.5530	0.6917	0.8317
No log	30.0	60	0.7515	0.5086	0.7515	0.8669
No log	31.0	62	0.7920	0.5083	0.7920	0.8900
No log	32.0	64	0.7633	0.5447	0.7633	0.8737
No log	33.0	66	0.7891	0.4764	0.7891	0.8883
No log	34.0	68	0.7580	0.5260	0.7580	0.8706
No log	35.0	70	1.0103	0.5116	1.0103	1.0051
No log	36.0	72	0.8362	0.5414	0.8362	0.9144
No log	37.0	74	0.8107	0.5121	0.8107	0.9004
No log	38.0	76	0.7855	0.5603	0.7855	0.8863
No log	39.0	78	0.7393	0.5635	0.7393	0.8598
No log	40.0	80	0.7141	0.5282	0.7141	0.8450
No log	41.0	82	0.8185	0.5529	0.8185	0.9047
No log	42.0	84	0.8006	0.5570	0.8006	0.8947
No log	43.0	86	0.7743	0.5245	0.7743	0.8800

Framework versions

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