---
license: llama2
library_name: peft
tags:
- unsloth
- generated_from_trainer
base_model: meta-llama/Llama-2-13b-hf
model-index:
- name: llama_2_13b_Magiccoder_evol_10k
  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. -->

# llama_2_13b_Magiccoder_evol_10k

This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1044

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 1.2459        | 0.0262 | 4    | 1.2861          |
| 1.2388        | 0.0523 | 8    | 1.2259          |
| 1.1411        | 0.0785 | 12   | 1.1833          |
| 1.0897        | 0.1047 | 16   | 1.1669          |
| 1.1171        | 0.1308 | 20   | 1.1500          |
| 1.0835        | 0.1570 | 24   | 1.1420          |
| 1.0782        | 0.1832 | 28   | 1.1362          |
| 1.1353        | 0.2093 | 32   | 1.1333          |
| 1.0558        | 0.2355 | 36   | 1.1298          |
| 1.1398        | 0.2617 | 40   | 1.1281          |
| 1.1114        | 0.2878 | 44   | 1.1244          |
| 1.1543        | 0.3140 | 48   | 1.1219          |
| 1.1327        | 0.3401 | 52   | 1.1189          |
| 1.1016        | 0.3663 | 56   | 1.1179          |
| 1.1543        | 0.3925 | 60   | 1.1173          |
| 1.1484        | 0.4186 | 64   | 1.1153          |
| 1.095         | 0.4448 | 68   | 1.1130          |
| 1.1118        | 0.4710 | 72   | 1.1109          |
| 1.0624        | 0.4971 | 76   | 1.1103          |
| 1.1475        | 0.5233 | 80   | 1.1093          |
| 1.161         | 0.5495 | 84   | 1.1094          |
| 1.1018        | 0.5756 | 88   | 1.1091          |
| 1.0541        | 0.6018 | 92   | 1.1065          |
| 1.054         | 0.6280 | 96   | 1.1055          |
| 1.1113        | 0.6541 | 100  | 1.1055          |
| 1.0971        | 0.6803 | 104  | 1.1053          |
| 1.0903        | 0.7065 | 108  | 1.1054          |
| 1.1206        | 0.7326 | 112  | 1.1052          |
| 1.0687        | 0.7588 | 116  | 1.1048          |
| 1.0892        | 0.7850 | 120  | 1.1043          |
| 1.1158        | 0.8111 | 124  | 1.1041          |
| 1.0789        | 0.8373 | 128  | 1.1042          |
| 1.0154        | 0.8635 | 132  | 1.1044          |
| 1.1258        | 0.8896 | 136  | 1.1044          |
| 1.0419        | 0.9158 | 140  | 1.1044          |
| 1.0886        | 0.9419 | 144  | 1.1044          |
| 1.1031        | 0.9681 | 148  | 1.1044          |
| 1.0979        | 0.9943 | 152  | 1.1044          |


### Framework versions

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