fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-7

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

• Loss: 0.7407
• Accuracy: 0.4899

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	2.8066	0.2626
No log	2.0	126	1.7729	0.3535
No log	3.0	189	1.8116	0.4394
No log	4.0	252	0.8183	0.4091
No log	5.0	315	0.9311	0.4242
No log	6.0	378	1.3171	0.4495
No log	7.0	441	0.7661	0.4545
2.0871	8.0	504	0.8889	0.4242
2.0871	9.0	567	0.6170	0.4394
2.0871	10.0	630	0.7407	0.4899
2.0871	11.0	693	0.6189	0.4697
2.0871	12.0	756	0.5956	0.4747
2.0871	13.0	819	0.5274	0.4596
2.0871	14.0	882	0.5014	0.4646
2.0871	15.0	945	0.4660	0.4545
0.2452	16.0	1008	0.4361	0.4495
0.2452	17.0	1071	0.3798	0.4697
0.2452	18.0	1134	0.3735	0.4697
0.2452	19.0	1197	0.3530	0.4646
0.2452	20.0	1260	0.3681	0.4646

Framework versions

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