fresh-2-layer-medmcqa2000-distill-of-fresh-2-layer-mmlu_EVAL_mmlu

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

• Loss: 252.9675
• Accuracy: 0.3613

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: 32
• eval_batch_size: 32
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.59	100	200.6515	0.25
No log	3.17	200	195.4351	0.318
No log	4.76	300	234.0640	0.33
No log	6.35	400	256.2066	0.394
124.4314	7.94	500	218.1939	0.372
124.4314	9.52	600	219.9619	0.37
124.4314	11.11	700	232.0276	0.346
124.4314	12.7	800	233.1038	0.386
124.4314	14.29	900	236.9013	0.358

Framework versions

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