ASAP_FineTuningBERT_AugV8_k7_task1_organization_k7_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: 1.8076
• Qwk: 0.2287
• Mse: 1.8076
• Rmse: 1.3445

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	6	7.3068	0.0018	7.3068	2.7031
No log	2.0	12	3.6797	0.0180	3.6797	1.9183
No log	3.0	18	2.4207	0.0148	2.4207	1.5559
No log	4.0	24	1.3920	0.0420	1.3920	1.1798
No log	5.0	30	1.6656	0.0585	1.6656	1.2906
No log	6.0	36	1.1043	0.0316	1.1043	1.0509
No log	7.0	42	1.3495	0.0710	1.3495	1.1617
No log	8.0	48	1.1888	0.1130	1.1888	1.0903
No log	9.0	54	1.0737	0.2885	1.0737	1.0362
No log	10.0	60	0.9037	0.3899	0.9037	0.9506
No log	11.0	66	1.8471	0.1888	1.8471	1.3591
No log	12.0	72	2.6621	0.1092	2.6621	1.6316
No log	13.0	78	1.3250	0.2563	1.3250	1.1511
No log	14.0	84	1.3450	0.2845	1.3450	1.1597
No log	15.0	90	1.3562	0.2478	1.3562	1.1646
No log	16.0	96	1.7269	0.2043	1.7269	1.3141
No log	17.0	102	1.4961	0.2686	1.4961	1.2232
No log	18.0	108	1.5002	0.2446	1.5002	1.2248
No log	19.0	114	1.2252	0.2839	1.2252	1.1069
No log	20.0	120	1.8076	0.2287	1.8076	1.3445

Framework versions

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