fresh-2-layer-medmcqa10000-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: 182.8575
• Accuracy: 0.4225

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	0.32	100	200.8704	0.264
No log	0.64	200	196.7610	0.376
No log	0.96	300	208.2900	0.39
No log	1.28	400	191.1668	0.382
139.6607	1.6	500	200.9705	0.398
139.6607	1.92	600	189.0896	0.406
139.6607	2.24	700	185.7183	0.41
139.6607	2.56	800	174.6011	0.426
139.6607	2.88	900	186.1249	0.422
79.571	3.19	1000	185.1113	0.424
79.571	3.51	1100	181.1421	0.398
79.571	3.83	1200	186.5035	0.412
79.571	4.15	1300	184.2203	0.432
79.571	4.47	1400	189.4636	0.396
56.051	4.79	1500	188.4894	0.412
56.051	5.11	1600	190.0390	0.43
56.051	5.43	1700	191.3842	0.416
56.051	5.75	1800	195.1680	0.406

Framework versions

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