---
base_model: unsloth/llama-3-8b-bnb-4bit
library_name: peft
license: llama3
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Meta-Llama-3-8B_pct_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-3-8B_pct_ortho

This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2409

## 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: 0.0003
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 2.3045        | 0.0206 | 8    | 2.2825          |
| 2.2746        | 0.0412 | 16   | 2.2479          |
| 2.2264        | 0.0618 | 24   | 2.2587          |
| 2.3001        | 0.0824 | 32   | 2.2813          |
| 2.3006        | 0.1030 | 40   | 2.2798          |
| 2.2719        | 0.1236 | 48   | 2.2780          |
| 2.2942        | 0.1442 | 56   | 2.2881          |
| 2.314         | 0.1648 | 64   | 2.2993          |
| 2.2747        | 0.1854 | 72   | 2.3101          |
| 2.3086        | 0.2060 | 80   | 2.3069          |
| 2.3318        | 0.2266 | 88   | 2.2899          |
| 2.3957        | 0.2472 | 96   | 2.3000          |
| 2.3704        | 0.2678 | 104  | 2.2998          |
| 2.3319        | 0.2884 | 112  | 2.3124          |
| 2.3908        | 0.3090 | 120  | 2.3099          |
| 2.3865        | 0.3296 | 128  | 2.3063          |
| 2.3306        | 0.3502 | 136  | 2.2947          |
| 2.326         | 0.3708 | 144  | 2.2973          |
| 2.3421        | 0.3914 | 152  | 2.2987          |
| 2.3277        | 0.4120 | 160  | 2.2820          |
| 2.3739        | 0.4326 | 168  | 2.2931          |
| 2.3157        | 0.4532 | 176  | 2.2898          |
| 2.3296        | 0.4738 | 184  | 2.2915          |
| 2.3274        | 0.4944 | 192  | 2.2818          |
| 2.3225        | 0.5150 | 200  | 2.2861          |
| 2.3181        | 0.5356 | 208  | 2.2817          |
| 2.3393        | 0.5562 | 216  | 2.2708          |
| 2.3276        | 0.5768 | 224  | 2.2763          |
| 2.3053        | 0.5974 | 232  | 2.2791          |
| 2.2739        | 0.6180 | 240  | 2.2721          |
| 2.311         | 0.6386 | 248  | 2.2749          |
| 2.3049        | 0.6592 | 256  | 2.2706          |
| 2.2615        | 0.6798 | 264  | 2.2703          |
| 2.312         | 0.7004 | 272  | 2.2633          |
| 2.3017        | 0.7210 | 280  | 2.2594          |
| 2.3066        | 0.7416 | 288  | 2.2572          |
| 2.2966        | 0.7621 | 296  | 2.2579          |
| 2.3375        | 0.7827 | 304  | 2.2461          |
| 2.2704        | 0.8033 | 312  | 2.2474          |
| 2.2512        | 0.8239 | 320  | 2.2496          |
| 2.2834        | 0.8445 | 328  | 2.2431          |
| 2.2962        | 0.8651 | 336  | 2.2452          |
| 2.3071        | 0.8857 | 344  | 2.2405          |
| 2.2739        | 0.9063 | 352  | 2.2401          |
| 2.2437        | 0.9269 | 360  | 2.2435          |
| 2.2634        | 0.9475 | 368  | 2.2417          |
| 2.3116        | 0.9681 | 376  | 2.2406          |
| 2.2995        | 0.9887 | 384  | 2.2409          |


### Framework versions

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