ontochem_biobert_1e-5_10epochs_v3

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0417

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	48	0.9501
No log	2.0	96	0.4654
No log	3.0	144	0.1178
No log	4.0	192	0.0660
No log	5.0	240	0.0530
No log	6.0	288	0.0472
No log	7.0	336	0.0450
No log	8.0	384	0.0422
No log	9.0	432	0.0438
No log	10.0	480	0.0417

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2