---
license: llama3
library_name: peft
tags:
- unsloth
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: meta_llama_3_Magiccoder_evol_10k_ortho
  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. -->

# meta_llama_3_Magiccoder_evol_10k_ortho

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2120

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.02
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.2542        | 0.0259 | 4    | 1.3547          |
| 1.2886        | 0.0518 | 8    | 1.2904          |
| 1.2416        | 0.0777 | 12   | 1.2577          |
| 1.2563        | 0.1036 | 16   | 1.2476          |
| 1.2632        | 0.1296 | 20   | 1.2418          |
| 1.1767        | 0.1555 | 24   | 1.2388          |
| 1.2299        | 0.1814 | 28   | 1.2364          |
| 1.203         | 0.2073 | 32   | 1.2333          |
| 1.2295        | 0.2332 | 36   | 1.2313          |
| 1.2796        | 0.2591 | 40   | 1.2307          |
| 1.2378        | 0.2850 | 44   | 1.2274          |
| 1.162         | 0.3109 | 48   | 1.2276          |
| 1.2157        | 0.3368 | 52   | 1.2251          |
| 1.2534        | 0.3628 | 56   | 1.2245          |
| 1.2336        | 0.3887 | 60   | 1.2226          |
| 1.2928        | 0.4146 | 64   | 1.2219          |
| 1.1455        | 0.4405 | 68   | 1.2216          |
| 1.2152        | 0.4664 | 72   | 1.2194          |
| 1.1637        | 0.4923 | 76   | 1.2201          |
| 1.2462        | 0.5182 | 80   | 1.2180          |
| 1.1747        | 0.5441 | 84   | 1.2157          |
| 1.218         | 0.5700 | 88   | 1.2160          |
| 1.3152        | 0.5960 | 92   | 1.2149          |
| 1.1314        | 0.6219 | 96   | 1.2152          |
| 1.2156        | 0.6478 | 100  | 1.2149          |
| 1.134         | 0.6737 | 104  | 1.2151          |
| 1.1619        | 0.6996 | 108  | 1.2150          |
| 1.1718        | 0.7255 | 112  | 1.2150          |
| 1.2274        | 0.7514 | 116  | 1.2142          |
| 1.211         | 0.7773 | 120  | 1.2136          |
| 1.233         | 0.8032 | 124  | 1.2131          |
| 1.2209        | 0.8291 | 128  | 1.2126          |
| 1.2179        | 0.8551 | 132  | 1.2122          |
| 1.179         | 0.8810 | 136  | 1.2119          |
| 1.1764        | 0.9069 | 140  | 1.2120          |
| 1.1622        | 0.9328 | 144  | 1.2120          |
| 1.1853        | 0.9587 | 148  | 1.2120          |
| 1.1599        | 0.9846 | 152  | 1.2120          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1