fresh-2-layer-piqa2000-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: 13.4591
• Accuracy: 0.3939

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	15.7687	0.2929
No log	3.17	200	14.1653	0.3889
No log	4.76	300	13.4591	0.3939
No log	6.35	400	13.9557	0.3737
2.3193	7.94	500	15.3610	0.3939
2.3193	9.52	600	13.9801	0.3889
2.3193	11.11	700	13.9090	0.3737
2.3193	12.7	800	13.6612	0.3535

Framework versions

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