jialicheng/ddi-biobert

biobert

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

• Loss: 0.4906
• Accuracy: 0.9444

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: 32
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	791	0.2279	0.9384
0.1997	2.0	1582	0.3086	0.9326
0.0772	3.0	2373	0.3142	0.9305
0.0504	4.0	3164	0.3149	0.9417
0.0504	5.0	3955	0.3344	0.9414
0.0367	6.0	4746	0.3333	0.9430
0.0245	7.0	5537	0.3671	0.9409
0.0204	8.0	6328	0.4249	0.9395
0.0134	9.0	7119	0.3557	0.9456
0.0134	10.0	7910	0.4586	0.9384
0.0109	11.0	8701	0.5423	0.9374
0.0087	12.0	9492	0.4680	0.9458
0.0052	13.0	10283	0.4594	0.9458
0.0071	14.0	11074	0.5178	0.9389
0.0071	15.0	11865	0.4706	0.9421
0.0056	16.0	12656	0.4917	0.9435
0.0034	17.0	13447	0.4678	0.9447
0.0026	18.0	14238	0.4793	0.9447
0.0023	19.0	15029	0.4869	0.9458
0.0023	20.0	15820	0.4906	0.9444

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2