fresh-2-layer-gpqa

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

• Loss: 0.1303
• Accuracy: 0.9798

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	1.3863	0.2424
No log	2.0	26	1.3861	0.2424
No log	3.0	39	1.3859	0.2475
No log	4.0	52	1.3857	0.2980
No log	5.0	65	1.3854	0.3232
No log	6.0	78	1.3846	0.2929
No log	7.0	91	1.3836	0.3434
No log	8.0	104	1.3776	0.4343
No log	9.0	117	1.3345	0.6010
No log	10.0	130	1.0517	0.6212
No log	11.0	143	0.7070	0.7475
No log	12.0	156	0.5129	0.8232
No log	13.0	169	0.3645	0.8636
No log	14.0	182	0.2729	0.9242
No log	15.0	195	0.2573	0.9495
No log	16.0	208	0.1570	0.9646
No log	17.0	221	0.1303	0.9798
No log	18.0	234	0.1164	0.9747
No log	19.0	247	0.1218	0.9545
No log	20.0	260	0.1037	0.9697

Framework versions

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