ASAP_FineTuningBERT_AugV8_k4_task1_organization_k4_fold4

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: 0.7477
• Qwk: 0.5381
• Mse: 0.7477
• Rmse: 0.8647

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	9.0264	0.0037	9.0264	3.0044
No log	2.0	8	6.8867	0.0018	6.8867	2.6243
No log	3.0	12	5.2704	0.0252	5.2704	2.2957
No log	4.0	16	3.1976	0.0040	3.1976	1.7882
No log	5.0	20	1.8764	0.1049	1.8764	1.3698
No log	6.0	24	1.2299	0.0342	1.2299	1.1090
No log	7.0	28	1.1797	0.0316	1.1797	1.0861
No log	8.0	32	1.2189	0.0316	1.2189	1.1040
No log	9.0	36	1.1759	0.0710	1.1759	1.0844
No log	10.0	40	1.0850	0.1237	1.0850	1.0416
No log	11.0	44	0.8181	0.3737	0.8181	0.9045
No log	12.0	48	0.8148	0.4344	0.8148	0.9027
No log	13.0	52	0.5946	0.5367	0.5946	0.7711
No log	14.0	56	0.5461	0.5392	0.5461	0.7390
No log	15.0	60	0.5473	0.5626	0.5473	0.7398
No log	16.0	64	0.6083	0.5312	0.6083	0.7800
No log	17.0	68	0.5647	0.5938	0.5647	0.7515
No log	18.0	72	0.6112	0.5972	0.6112	0.7818
No log	19.0	76	0.7826	0.5125	0.7826	0.8846
No log	20.0	80	0.7537	0.5447	0.7537	0.8681
No log	21.0	84	0.6924	0.5836	0.6924	0.8321
No log	22.0	88	0.6441	0.5904	0.6441	0.8025
No log	23.0	92	0.6976	0.5699	0.6976	0.8352
No log	24.0	96	0.8570	0.5358	0.8570	0.9258
No log	25.0	100	0.6531	0.5792	0.6531	0.8082
No log	26.0	104	0.6097	0.5993	0.6097	0.7809
No log	27.0	108	0.6699	0.5982	0.6699	0.8185
No log	28.0	112	0.6630	0.5939	0.6630	0.8142
No log	29.0	116	0.7202	0.5755	0.7202	0.8486
No log	30.0	120	0.7905	0.5373	0.7905	0.8891
No log	31.0	124	0.7192	0.5238	0.7192	0.8481
No log	32.0	128	0.7671	0.5125	0.7671	0.8758
No log	33.0	132	0.6287	0.5754	0.6287	0.7929
No log	34.0	136	0.9252	0.4921	0.9252	0.9619
No log	35.0	140	0.6480	0.5615	0.6480	0.8050
No log	36.0	144	0.7477	0.5381	0.7477	0.8647

Framework versions

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