ASAP_FineTuningBERT_AugV8_k10_task1_organization_fold1

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: 1.7684
• Qwk: 0.0315
• Mse: 1.7682
• Rmse: 1.3297

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	0.25	2	10.8084	0.0252	10.8060	3.2873
No log	0.5	4	8.5966	0.0	8.5944	2.9316
No log	0.75	6	6.3101	0.0	6.3085	2.5117
No log	1.0	8	5.0487	0.0676	5.0476	2.2467
5.5629	1.25	10	4.0465	0.0079	4.0455	2.0114
5.5629	1.5	12	3.1947	0.0	3.1940	1.7872
5.5629	1.75	14	2.3820	0.0344	2.3815	1.5432
5.5629	2.0	16	2.0304	0.1357	2.0301	1.4248
5.5629	2.25	18	1.8435	0.0491	1.8433	1.3577
2.1103	2.5	20	1.4209	0.0315	1.4209	1.1920
2.1103	2.75	22	1.2281	0.0211	1.2282	1.1082
2.1103	3.0	24	1.4696	0.0211	1.4695	1.2122
2.1103	3.25	26	1.7809	0.0301	1.7807	1.3344
2.1103	3.5	28	1.6030	0.0418	1.6028	1.2660
1.7334	3.75	30	1.0980	0.0315	1.0980	1.0479
1.7334	4.0	32	0.9716	0.0434	0.9718	0.9858
1.7334	4.25	34	1.2620	0.0289	1.2620	1.1234
1.7334	4.5	36	1.7684	0.0315	1.7682	1.3297

Framework versions

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