fresh-12-layer-gpqa

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

• Loss: 0.1852
• Accuracy: 0.9394

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: 16
• eval_batch_size: 16
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	13	1.3865	0.2677
No log	2.0	26	1.3857	0.2374
No log	3.0	39	1.3852	0.2475
No log	4.0	52	1.3852	0.2929
No log	5.0	65	1.3847	0.2929
No log	6.0	78	1.3844	0.3081
No log	7.0	91	1.3839	0.2980
No log	8.0	104	1.3800	0.3081
No log	9.0	117	1.3751	0.3535
No log	10.0	130	1.2007	0.6263
No log	11.0	143	0.9272	0.6515
No log	12.0	156	1.0185	0.6768
No log	13.0	169	0.6580	0.7424
No log	14.0	182	0.4847	0.7828
No log	15.0	195	0.3170	0.8384
No log	16.0	208	0.2830	0.8485
No log	17.0	221	0.3068	0.9192
No log	18.0	234	0.2519	0.9141
No log	19.0	247	0.2426	0.9343
No log	20.0	260	0.1852	0.9394

Framework versions

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