---
base_model: unsloth/mistral-7b-v0.3-bnb-4bit
library_name: peft
license: apache-2.0
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Mistral-7B-v0.3_magiccoder_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. -->

# Mistral-7B-v0.3_magiccoder_ortho

This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 7.8323

## 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_ratio: 0.02
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 4.9343        | 0.0262 | 4    | 4.5673          |
| 8.4663        | 0.0523 | 8    | 8.9578          |
| 9.123         | 0.0785 | 12   | 8.6942          |
| 8.1876        | 0.1047 | 16   | 7.9600          |
| 7.9611        | 0.1308 | 20   | 7.9425          |
| 7.8963        | 0.1570 | 24   | 7.8806          |
| 7.9541        | 0.1832 | 28   | 7.8846          |
| 7.8696        | 0.2093 | 32   | 7.9268          |
| 7.8399        | 0.2355 | 36   | 7.8339          |
| 7.9017        | 0.2617 | 40   | 7.8005          |
| 7.9876        | 0.2878 | 44   | 7.8595          |
| 7.7902        | 0.3140 | 48   | 7.8621          |
| 7.9025        | 0.3401 | 52   | 7.8706          |
| 7.8517        | 0.3663 | 56   | 7.8475          |
| 7.8358        | 0.3925 | 60   | 7.8903          |
| 7.8265        | 0.4186 | 64   | 7.8085          |
| 7.9259        | 0.4448 | 68   | 7.8720          |
| 7.8189        | 0.4710 | 72   | 7.8266          |
| 7.866         | 0.4971 | 76   | 7.9089          |
| 7.9191        | 0.5233 | 80   | 7.8740          |
| 7.9035        | 0.5495 | 84   | 7.8838          |
| 7.8126        | 0.5756 | 88   | 7.8359          |
| 7.9197        | 0.6018 | 92   | 7.8574          |
| 7.8146        | 0.6280 | 96   | 7.7690          |
| 7.8805        | 0.6541 | 100  | 7.8380          |
| 7.867         | 0.6803 | 104  | 7.8682          |
| 7.904         | 0.7065 | 108  | 7.8719          |
| 7.8756        | 0.7326 | 112  | 7.8702          |
| 7.8244        | 0.7588 | 116  | 7.7825          |
| 7.8114        | 0.7850 | 120  | 7.8015          |
| 7.9641        | 0.8111 | 124  | 7.8350          |
| 7.8656        | 0.8373 | 128  | 7.7883          |
| 7.8575        | 0.8635 | 132  | 7.8154          |
| 7.8503        | 0.8896 | 136  | 7.8298          |
| 7.7447        | 0.9158 | 140  | 7.8152          |
| 7.8305        | 0.9419 | 144  | 7.8202          |
| 7.7952        | 0.9681 | 148  | 7.8314          |
| 7.8406        | 0.9943 | 152  | 7.8323          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1