mistral-7b_test3

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mistral-7b_test3

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset.

Model description

mistral-7b quantized with QLoRA and fine-tuned with 12000 randomly selected samples from FLAN V2 (trained with target only)

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2.5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• training_steps: 3000

MMLU accuracy

Overall: 59.30%

STEM: 49.15%

Humanities: 65.28%

Social Sciences: 70.44%

Other (business, health, misc.): 64.12%

Framework versions

• PEFT 0.9.1.dev0
• Transformers 4.38.2
• Pytorch 2.2.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2