bioclinicalbert-base-medqa-usmle-nocontext

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

• Loss: 1.4564
• Accuracy: 0.3009

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	1.3836	0.2757
No log	1.98	78	1.3801	0.2828
No log	2.98	117	1.3816	0.3024
No log	3.98	156	1.4107	0.3111
No log	4.98	195	1.4412	0.3032
No log	5.98	234	1.4564	0.3009

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2