fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-8

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

• Loss: 0.7254
• Accuracy: 0.4747

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	3.7644	0.2323
No log	2.0	126	3.6149	0.3687
No log	3.0	189	1.4060	0.4141
No log	4.0	252	1.4429	0.4646
No log	5.0	315	1.2004	0.4545
No log	6.0	378	1.0944	0.4596
No log	7.0	441	1.3715	0.4394
2.4812	8.0	504	1.1383	0.4697
2.4812	9.0	567	1.1514	0.4444
2.4812	10.0	630	1.4900	0.4242
2.4812	11.0	693	0.7765	0.4545
2.4812	12.0	756	0.7740	0.4343
2.4812	13.0	819	1.3336	0.4394
2.4812	14.0	882	0.7081	0.4394
2.4812	15.0	945	0.5895	0.4242
0.2763	16.0	1008	0.7254	0.4747
0.2763	17.0	1071	0.6059	0.4141
0.2763	18.0	1134	0.5857	0.4495
0.2763	19.0	1197	0.6002	0.4394
0.2763	20.0	1260	0.6015	0.4495

Framework versions

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