fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-3

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

• Loss: 0.8510
• Accuracy: 0.5303

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	2.8211	0.2879
No log	2.0	126	2.0292	0.3889
No log	3.0	189	1.3492	0.4293
No log	4.0	252	0.8583	0.5152
No log	5.0	315	0.8510	0.5303
No log	6.0	378	1.3129	0.4848
No log	7.0	441	0.7994	0.4444
1.9846	8.0	504	0.6454	0.4697
1.9846	9.0	567	0.8126	0.4899
1.9846	10.0	630	0.8618	0.4495
1.9846	11.0	693	0.5559	0.4848
1.9846	12.0	756	0.5902	0.4949
1.9846	13.0	819	0.5117	0.5051
1.9846	14.0	882	0.4989	0.4848
1.9846	15.0	945	0.4913	0.4697
0.2505	16.0	1008	0.4599	0.4949
0.2505	17.0	1071	0.3934	0.4949
0.2505	18.0	1134	0.4083	0.4848
0.2505	19.0	1197	0.4291	0.4798
0.2505	20.0	1260	0.4429	0.4747

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.0