fresh-2-layer-medmcqa

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

• Loss: 2.0870
• Accuracy: 0.2677

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	1.3865	0.2273
No log	2.0	126	1.3873	0.2273
No log	3.0	189	1.4299	0.1667
No log	4.0	252	1.4500	0.2071
No log	5.0	315	1.9720	0.2172
No log	6.0	378	2.0870	0.2677
No log	7.0	441	3.0344	0.2374
0.7594	8.0	504	2.8203	0.2222
0.7594	9.0	567	3.0874	0.2121
0.7594	10.0	630	3.1733	0.2525
0.7594	11.0	693	4.0368	0.1970
0.7594	12.0	756	4.1563	0.2273
0.7594	13.0	819	3.8739	0.2424
0.7594	14.0	882	3.6493	0.2576
0.7594	15.0	945	4.2385	0.2273
0.0675	16.0	1008	4.4551	0.2121
0.0675	17.0	1071	4.8175	0.2172
0.0675	18.0	1134	5.1875	0.2121
0.0675	19.0	1197	4.5584	0.2071
0.0675	20.0	1260	4.5618	0.2020

Framework versions

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