ASAP_FineTuningBERT_AugV8_k7_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: 1.9110
• Qwk: 0.0052
• Mse: 1.9108
• Rmse: 1.3823

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	0.3333	2	10.4949	0.0160	10.4927	3.2392
No log	0.6667	4	8.3835	0.0	8.3817	2.8951
No log	1.0	6	6.5158	0.0	6.5142	2.5523
No log	1.3333	8	5.2521	0.0425	5.2507	2.2914
5.7104	1.6667	10	3.9605	0.0	3.9594	1.9898
5.7104	2.0	12	3.0025	0.0	3.0017	1.7326
5.7104	2.3333	14	2.4025	0.0540	2.4021	1.5499
5.7104	2.6667	16	1.8701	0.0301	1.8699	1.3674
5.7104	3.0	18	1.5437	0.0	1.5437	1.2425
2.2791	3.3333	20	1.3350	0.0	1.3351	1.1555
2.2791	3.6667	22	1.2314	0.0	1.2317	1.1098
2.2791	4.0	24	1.3786	0.0	1.3787	1.1742
2.2791	4.3333	26	1.6914	0.0106	1.6913	1.3005
2.2791	4.6667	28	1.5989	0.0106	1.5989	1.2645
1.7069	5.0	30	1.4087	0.0	1.4088	1.1869
1.7069	5.3333	32	1.3596	0.0	1.3596	1.1660
1.7069	5.6667	34	1.9110	0.0052	1.9108	1.3823

Framework versions

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