Edit model card

biolinkbert-base-medqa-usmle-nocontext

This model is a fine-tuned version of michiyasunaga/BioLinkBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5149
  • Accuracy: 0.3943

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 64
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.98 39 1.3339 0.3590
No log 1.98 78 1.3685 0.3794
No log 2.98 117 1.4162 0.3912
No log 3.98 156 1.4484 0.3888
No log 4.98 195 1.4869 0.3983
No log 5.98 234 1.5149 0.3943

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2
Downloads last month
10
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Dataset used to train GBaker/biolinkbert-base-medqa-usmle-nocontext