fresh-2-layer-swag73545-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

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

• Loss: 13.2860
• Accuracy: 0.5

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	0.04	100	15.3746	0.3030
No log	0.09	200	15.8323	0.3788
No log	0.13	300	18.5973	0.3586
No log	0.17	400	18.2249	0.3788
2.3639	0.22	500	17.3930	0.4141
2.3639	0.26	600	12.7479	0.4242
2.3639	0.3	700	13.6916	0.4646
2.3639	0.35	800	13.2860	0.5
2.3639	0.39	900	13.5986	0.4596
0.6733	0.43	1000	12.9991	0.4646
0.6733	0.48	1100	12.2002	0.4697
0.6733	0.52	1200	11.8489	0.4848
0.6733	0.57	1300	12.4483	0.4949

Framework versions

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