---
library_name: peft
license: llama2
base_model: TheBloke/CodeLlama-7B-Instruct-GPTQ
tags:
- generated_from_trainer
model-index:
- name: jakobpi-ft
  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. -->

# jakobpi-ft

This model is a fine-tuned version of [TheBloke/CodeLlama-7B-Instruct-GPTQ](https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GPTQ) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7915

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9543        | 1.0   | 63   | 0.8840          |
| 0.7467        | 2.0   | 126  | 0.8270          |
| 0.6952        | 3.0   | 189  | 0.7923          |
| 0.6638        | 4.0   | 252  | 0.7860          |
| 0.6442        | 5.0   | 315  | 0.7826          |
| 0.6239        | 6.0   | 378  | 0.7827          |
| 0.6118        | 7.0   | 441  | 0.7859          |
| 0.5984        | 8.0   | 504  | 0.7873          |
| 0.5884        | 9.0   | 567  | 0.7903          |
| 0.5875        | 9.848 | 620  | 0.7915          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0