ontochem_biobert_1e-5_10epochs_v4

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: 0.0405

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	0.9461
No log	2.0	96	0.5419
No log	3.0	144	0.1535
No log	4.0	192	0.0714
No log	5.0	240	0.0560
No log	6.0	288	0.0492
No log	7.0	336	0.0460
No log	8.0	384	0.0433
No log	9.0	432	0.0440
No log	10.0	480	0.0405

Framework versions

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