LORA_gemma_trained_on_MMLU_5shot_test

This model is a fine-tuned version of justshao/gemma-7b-with-confidence on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2779

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.3002	1.0	877	0.2812
0.2731	2.0	1755	0.2820
0.2539	3.0	2632	0.2787
0.2419	4.0	3510	0.2775
0.2351	5.0	4385	0.2779

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2