fresh-2-layer-swag5000-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: 15.3688
• Accuracy: 0.4141

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	0.64	100	16.2017	0.2677
No log	1.27	200	17.0596	0.3384
No log	1.91	300	20.5674	0.3283
No log	2.55	400	15.3688	0.4141
2.2006	3.18	500	16.3588	0.4141
2.2006	3.82	600	16.3945	0.3889
2.2006	4.46	700	16.1531	0.3990
2.2006	5.1	800	15.7578	0.3535
2.2006	5.73	900	17.6009	0.3838

Framework versions

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