fresh-2-layer-qasc8134-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: 14.4843
• Accuracy: 0.4495

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	0.39	100	13.9088	0.2677
No log	0.78	200	13.0380	0.4141
No log	1.18	300	14.3170	0.4040
No log	1.57	400	14.8639	0.3939
1.8256	1.96	500	14.4843	0.4495
1.8256	2.35	600	13.3427	0.4394
1.8256	2.75	700	13.3794	0.4141
1.8256	3.14	800	15.4578	0.3838
1.8256	3.53	900	13.4042	0.4192
0.3172	3.92	1000	13.3731	0.3990

Framework versions

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