fresh-2-layer-qasc2000-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: 14.9062
• Accuracy: 0.4192

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	14.0964	0.2980
No log	3.17	200	15.9598	0.3788
No log	4.76	300	14.9387	0.4091
No log	6.35	400	14.1750	0.4091
1.6819	7.94	500	16.7634	0.4091
1.6819	9.52	600	14.9062	0.4192
1.6819	11.11	700	13.9546	0.4091
1.6819	12.7	800	14.2041	0.4091
1.6819	14.29	900	15.2506	0.4040
0.2306	15.87	1000	14.9041	0.4091
0.2306	17.46	1100	14.9118	0.4141

Framework versions

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