fresh-2-layer-arc2000-distill-of-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: 232.3996
• Accuracy: 0.3238

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	1.59	100	200.6664	0.258
No log	3.17	200	214.1454	0.284
No log	4.76	300	217.4835	0.298
No log	6.35	400	230.0120	0.354
109.2674	7.94	500	246.2496	0.332
109.2674	9.52	600	229.0414	0.34
109.2674	11.11	700	225.5762	0.338
109.2674	12.7	800	235.3921	0.324
109.2674	14.29	900	229.8624	0.346

Framework versions

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