BERT_AugV8_k7_task1_organization_sp010_lw050_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: 1.2723
• Qwk: 0.2610
• Mse: 1.2723
• Rmse: 1.1280

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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	5	9.1827	0.0	9.1829	3.0303
No log	2.0	10	7.3085	0.0	7.3088	2.7035
No log	3.0	15	5.1032	0.0102	5.1035	2.2591
No log	4.0	20	3.2191	0.0	3.2195	1.7943
No log	5.0	25	1.8735	0.0513	1.8740	1.3689
No log	6.0	30	1.0675	0.0280	1.0679	1.0334
No log	7.0	35	1.0709	0.0345	1.0713	1.0350
No log	8.0	40	0.8680	0.1882	0.8683	0.9318
No log	9.0	45	0.7438	0.4067	0.7437	0.8624
No log	10.0	50	0.7641	0.3644	0.7636	0.8739
No log	11.0	55	1.1598	0.2621	1.1594	1.0767
No log	12.0	60	1.2722	0.2936	1.2717	1.1277
No log	13.0	65	1.0088	0.2753	1.0088	1.0044
No log	14.0	70	0.8769	0.3336	0.8769	0.9364
No log	15.0	75	1.2128	0.2603	1.2127	1.1012
No log	16.0	80	0.9802	0.2869	0.9803	0.9901
No log	17.0	85	0.8601	0.3298	0.8604	0.9276
No log	18.0	90	1.1144	0.2394	1.1146	1.0558
No log	19.0	95	1.5041	0.1688	1.5044	1.2265
No log	20.0	100	1.4642	0.1900	1.4643	1.2101
No log	21.0	105	0.8850	0.3258	0.8850	0.9408
No log	22.0	110	1.0353	0.2738	1.0353	1.0175
No log	23.0	115	1.3748	0.2295	1.3749	1.1726
No log	24.0	120	1.2723	0.2610	1.2723	1.1280

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0