fresh-2-layer-mmlu_EVAL_mmlu

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

• Loss: 0.0196
• Accuracy: 0.9942

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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	439	1.1960	0.518
1.2946	2.0	878	0.9728	0.61
1.1382	3.0	1317	0.6014	0.796
0.8904	4.0	1756	0.3594	0.88
0.5997	5.0	2195	0.2266	0.932
0.413	6.0	2634	0.1883	0.936
0.2801	7.0	3073	0.1547	0.95
0.2194	8.0	3512	0.1150	0.952
0.2194	9.0	3951	0.0860	0.974
0.1697	10.0	4390	0.0870	0.974
0.134	11.0	4829	0.0561	0.98
0.1098	12.0	5268	0.0450	0.99
0.0908	13.0	5707	0.0301	0.988
0.0771	14.0	6146	0.0229	0.992
0.0618	15.0	6585	0.0174	0.996
0.0482	16.0	7024	0.0107	0.998
0.0482	17.0	7463	0.0060	0.996
0.0418	18.0	7902	0.0037	0.998
0.0289	19.0	8341	0.0031	0.998
0.0242	20.0	8780	0.0029	0.998

Framework versions

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