fresh-2-layer-medmcqa5000-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: 195.1898
• Accuracy: 0.3859

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	0.64	100	200.6038	0.252
No log	1.27	200	204.0380	0.342
No log	1.91	300	204.2234	0.33
No log	2.55	400	203.4390	0.39
135.6304	3.18	500	200.8276	0.392
135.6304	3.82	600	206.8670	0.386
135.6304	4.46	700	201.8676	0.386
135.6304	5.1	800	229.1385	0.364
135.6304	5.73	900	198.5690	0.396
56.0896	6.37	1000	194.0026	0.402
56.0896	7.01	1100	214.3130	0.372
56.0896	7.64	1200	220.0111	0.36
56.0896	8.28	1300	209.6216	0.376
56.0896	8.92	1400	213.6702	0.394
31.2764	9.55	1500	210.4745	0.394

Framework versions

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