README.md

metadata

license: llama2
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/CodeLlama-7B-Instruct-AWQ
model-index:
  - name: CodeLlama-7B-Instruct-AWQ-FaVe-rank8-2epochs
    results: []

CodeLlama-7B-Instruct-AWQ-FaVe-rank8-2epochs

This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5842

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2685	10	2.0879
1.9597	0.5369	20	0.9830
1.9597	0.8054	30	0.7691
0.7621	1.0738	40	0.6956
0.7621	1.3423	50	0.6332
0.5841	1.6107	60	0.6044
0.5841	1.8792	70	0.5842

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1