fresh-2-layer-qasc2000-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: 207.2272
• Accuracy: 0.3112

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	201.7617	0.23
No log	3.17	200	215.9669	0.294
No log	4.76	300	202.8176	0.334
No log	6.35	400	207.7114	0.356
92.1591	7.94	500	219.4992	0.322
92.1591	9.52	600	219.8570	0.346
92.1591	11.11	700	214.9255	0.352
92.1591	12.7	800	216.3126	0.336
92.1591	14.29	900	216.1720	0.328

Framework versions

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