README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
  - name: Mistral-7B-Instruct-v0.2-finetune-SWE_70_30
    results: []

Mistral-7B-Instruct-v0.2-finetune-SWE_70_30

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1810

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0462	1.0	1437	0.9927
0.8371	2.0	2874	0.9814
0.4527	3.0	4311	1.0285
0.4723	4.0	5748	1.1818
0.3111	5.0	7185	1.1810

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1