clinical-bigbird-medqa-usmle-nocontext

This model is a fine-tuned version of yikuan8/Clinical-BigBird on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3863
• Accuracy: 0.2482

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: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	159	1.3860	0.2584
No log	2.0	318	1.3859	0.2820
No log	3.0	477	1.3863	0.2522
1.3891	4.0	636	1.3863	0.2498
1.3891	5.0	795	1.3863	0.2404
1.3891	6.0	954	1.3863	0.2498
1.3882	7.0	1113	1.3863	0.2506
1.3882	8.0	1272	1.3863	0.2467
1.3882	9.0	1431	1.3863	0.2490
1.3876	10.0	1590	1.3863	0.2482

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.0
• Tokenizers 0.13.2