---
base_model: unsloth/qwen2-7b-bnb-4bit
library_name: peft
license: apache-2.0
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Qwen2-7B_metamath_default
  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. -->

# Qwen2-7B_metamath_default

This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1552

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.2406        | 0.0211 | 13   | 0.1655          |
| 0.1558        | 0.0421 | 26   | 0.1578          |
| 0.1536        | 0.0632 | 39   | 0.1560          |
| 0.1467        | 0.0842 | 52   | 0.1547          |
| 0.1457        | 0.1053 | 65   | 0.1551          |
| 0.15          | 0.1264 | 78   | 0.1552          |
| 0.1547        | 0.1474 | 91   | 0.1548          |
| 0.1494        | 0.1685 | 104  | 0.1559          |
| 0.1543        | 0.1896 | 117  | 0.1563          |
| 0.1511        | 0.2106 | 130  | 0.1563          |
| 0.1545        | 0.2317 | 143  | 0.1567          |
| 0.148         | 0.2527 | 156  | 0.1576          |
| 0.1559        | 0.2738 | 169  | 0.1584          |
| 0.1497        | 0.2949 | 182  | 0.1579          |
| 0.1577        | 0.3159 | 195  | 0.1582          |
| 0.1505        | 0.3370 | 208  | 0.1585          |
| 0.152         | 0.3580 | 221  | 0.1583          |
| 0.1498        | 0.3791 | 234  | 0.1586          |
| 0.1522        | 0.4002 | 247  | 0.1581          |
| 0.1536        | 0.4212 | 260  | 0.1574          |
| 0.1614        | 0.4423 | 273  | 0.1583          |
| 0.1555        | 0.4633 | 286  | 0.1580          |
| 0.1605        | 0.4844 | 299  | 0.1573          |
| 0.1497        | 0.5055 | 312  | 0.1580          |
| 0.1477        | 0.5265 | 325  | 0.1579          |
| 0.1497        | 0.5476 | 338  | 0.1570          |
| 0.1539        | 0.5687 | 351  | 0.1573          |
| 0.1573        | 0.5897 | 364  | 0.1576          |
| 0.1535        | 0.6108 | 377  | 0.1570          |
| 0.146         | 0.6318 | 390  | 0.1562          |
| 0.1546        | 0.6529 | 403  | 0.1564          |
| 0.1554        | 0.6740 | 416  | 0.1564          |
| 0.1521        | 0.6950 | 429  | 0.1565          |
| 0.1557        | 0.7161 | 442  | 0.1557          |
| 0.1469        | 0.7371 | 455  | 0.1554          |
| 0.1513        | 0.7582 | 468  | 0.1558          |
| 0.153         | 0.7793 | 481  | 0.1557          |
| 0.1518        | 0.8003 | 494  | 0.1555          |
| 0.1482        | 0.8214 | 507  | 0.1554          |
| 0.1514        | 0.8424 | 520  | 0.1554          |
| 0.1533        | 0.8635 | 533  | 0.1553          |
| 0.1521        | 0.8846 | 546  | 0.1554          |
| 0.148         | 0.9056 | 559  | 0.1553          |
| 0.1473        | 0.9267 | 572  | 0.1553          |
| 0.1482        | 0.9478 | 585  | 0.1552          |
| 0.1498        | 0.9688 | 598  | 0.1553          |
| 0.155         | 0.9899 | 611  | 0.1552          |


### Framework versions

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