disabilityy_model_final

This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7063
• Accuracy: 0.9993
• F1: 0.9993

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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: 10
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
3.3242	0.1361	100	2.9016	0.5510	0.4600
2.1047	0.2721	200	1.7308	0.9109	0.9011
1.3316	0.4082	300	1.0783	0.9776	0.9773
0.9219	0.5442	400	0.8120	0.9905	0.9905
0.7627	0.6803	500	0.7448	0.9939	0.9939
0.7325	0.8163	600	0.7346	0.9959	0.9959
0.7239	0.9524	700	0.7223	0.9980	0.9980
0.7137	1.0884	800	0.7182	0.9980	0.9980
0.711	1.2245	900	0.7175	0.9966	0.9966
0.7103	1.3605	1000	0.7139	0.9986	0.9986
0.7088	1.4966	1100	0.7134	0.9973	0.9973
0.708	1.6327	1200	0.7131	0.9973	0.9973
0.7071	1.7687	1300	0.7102	0.9980	0.9980
0.7056	1.9048	1400	0.7096	0.9986	0.9986
0.7093	2.0408	1500	0.7081	0.9993	0.9993
0.7046	2.1769	1600	0.7069	0.9993	0.9993
0.705	2.3129	1700	0.7063	0.9993	0.9993
0.7035	2.4490	1800	0.7063	0.9993	0.9993
0.7041	2.5850	1900	0.7071	0.9993	0.9993
0.7033	2.7211	2000	0.7065	0.9993	0.9993

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1