fresh-4-layer-gpqa

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

• Loss: 0.1650
• Accuracy: 0.9697

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	1.3861	0.2424
No log	2.0	26	1.3858	0.2576
No log	3.0	39	1.3856	0.2828
No log	4.0	52	1.3853	0.3131
No log	5.0	65	1.3851	0.3232
No log	6.0	78	1.3847	0.3131
No log	7.0	91	1.3836	0.3384
No log	8.0	104	1.3803	0.3636
No log	9.0	117	1.3556	0.4545
No log	10.0	130	1.0943	0.6414
No log	11.0	143	0.8911	0.7374
No log	12.0	156	0.6231	0.7475
No log	13.0	169	0.4360	0.8384
No log	14.0	182	0.3315	0.8889
No log	15.0	195	0.2405	0.9444
No log	16.0	208	0.1650	0.9697
No log	17.0	221	0.1396	0.9444
No log	18.0	234	0.1169	0.9646
No log	19.0	247	0.1054	0.9545
No log	20.0	260	0.1236	0.9697

Framework versions

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