---
license: llama2
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/CodeLlama-7b-Instruct-hf
model-index:
- name: CodeLlama-7b-Instruct-hf-FaVe-rank16-10epochs
  results: []
---

<!-- 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. -->

# CodeLlama-7b-Instruct-hf-FaVe-rank16-10epochs

This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5312

## 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: 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: 10

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.2685 | 10   | 2.4114          |
| 2.3826        | 0.5369 | 20   | 2.1148          |
| 2.3826        | 0.8054 | 30   | 1.6293          |
| 1.5952        | 1.0738 | 40   | 1.2775          |
| 1.5952        | 1.3423 | 50   | 1.0305          |
| 0.8958        | 1.6107 | 60   | 0.9094          |
| 0.8958        | 1.8792 | 70   | 0.8423          |
| 0.6775        | 2.1477 | 80   | 0.7922          |
| 0.6775        | 2.4161 | 90   | 0.7561          |
| 0.6156        | 2.6846 | 100  | 0.7230          |
| 0.6156        | 2.9530 | 110  | 0.6956          |
| 0.5043        | 3.2215 | 120  | 0.6791          |
| 0.5043        | 3.4899 | 130  | 0.6685          |
| 0.4784        | 3.7584 | 140  | 0.6406          |
| 0.4784        | 4.0268 | 150  | 0.6200          |
| 0.4181        | 4.2953 | 160  | 0.6194          |
| 0.4181        | 4.5638 | 170  | 0.5997          |
| 0.377         | 4.8322 | 180  | 0.5819          |
| 0.377         | 5.1007 | 190  | 0.5767          |
| 0.3398        | 5.3691 | 200  | 0.5678          |
| 0.3398        | 5.6376 | 210  | 0.5455          |
| 0.313         | 5.9060 | 220  | 0.5499          |
| 0.313         | 6.1745 | 230  | 0.5514          |
| 0.2612        | 6.4430 | 240  | 0.5299          |
| 0.2612        | 6.7114 | 250  | 0.5250          |
| 0.2681        | 6.9799 | 260  | 0.5253          |
| 0.2681        | 7.2483 | 270  | 0.5326          |
| 0.2199        | 7.5168 | 280  | 0.5336          |
| 0.2199        | 7.7852 | 290  | 0.5203          |
| 0.2314        | 8.0537 | 300  | 0.5235          |
| 0.2314        | 8.3221 | 310  | 0.5317          |
| 0.2019        | 8.5906 | 320  | 0.5302          |
| 0.2019        | 8.8591 | 330  | 0.5244          |
| 0.1991        | 9.1275 | 340  | 0.5250          |
| 0.1991        | 9.3960 | 350  | 0.5332          |
| 0.197         | 9.6644 | 360  | 0.5319          |
| 0.197         | 9.9329 | 370  | 0.5312          |


### Framework versions

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