ontochem_biobert_1e-5_20epochs

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: 0.0482

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: 3e-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	0.7857
No log	2.0	96	0.1110
No log	3.0	144	0.0554
No log	4.0	192	0.0460
No log	5.0	240	0.0436
No log	6.0	288	0.0430
No log	7.0	336	0.0443
No log	8.0	384	0.0425
No log	9.0	432	0.0468
No log	10.0	480	0.0482

Framework versions

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