---
base_model: unsloth/Qwen2-7B
library_name: peft
license: apache-2.0
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Qwen2-7B_metamath_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. -->

# Qwen2-7B_metamath_ortho

This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co./unsloth/Qwen2-7B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2061

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.1901        | 0.0211 | 13   | 0.1752          |
| 0.1801        | 0.0421 | 26   | 0.2122          |
| 0.2158        | 0.0632 | 39   | 0.2351          |
| 0.2309        | 0.0842 | 52   | 0.2526          |
| 0.242         | 0.1053 | 65   | 0.2650          |
| 0.2587        | 0.1264 | 78   | 0.2717          |
| 0.2671        | 0.1474 | 91   | 0.2770          |
| 0.2594        | 0.1685 | 104  | 0.2786          |
| 0.2707        | 0.1896 | 117  | 0.2831          |
| 0.2661        | 0.2106 | 130  | 0.2895          |
| 0.2795        | 0.2317 | 143  | 0.2919          |
| 0.2747        | 0.2527 | 156  | 0.2873          |
| 0.2824        | 0.2738 | 169  | 0.2873          |
| 0.2717        | 0.2949 | 182  | 0.2873          |
| 0.2801        | 0.3159 | 195  | 0.2838          |
| 0.2713        | 0.3370 | 208  | 0.2821          |
| 0.2678        | 0.3580 | 221  | 0.2797          |
| 0.2692        | 0.3791 | 234  | 0.2787          |
| 0.2671        | 0.4002 | 247  | 0.2769          |
| 0.268         | 0.4212 | 260  | 0.2742          |
| 0.2713        | 0.4423 | 273  | 0.2729          |
| 0.26          | 0.4633 | 286  | 0.2679          |
| 0.2677        | 0.4844 | 299  | 0.2628          |
| 0.248         | 0.5055 | 312  | 0.2594          |
| 0.2481        | 0.5265 | 325  | 0.2574          |
| 0.2381        | 0.5476 | 338  | 0.2521          |
| 0.2427        | 0.5687 | 351  | 0.2501          |
| 0.2463        | 0.5897 | 364  | 0.2442          |
| 0.2339        | 0.6108 | 377  | 0.2396          |
| 0.2304        | 0.6318 | 390  | 0.2343          |
| 0.2291        | 0.6529 | 403  | 0.2309          |
| 0.2308        | 0.6740 | 416  | 0.2291          |
| 0.224         | 0.6950 | 429  | 0.2254          |
| 0.2248        | 0.7161 | 442  | 0.2224          |
| 0.2122        | 0.7371 | 455  | 0.2184          |
| 0.2135        | 0.7582 | 468  | 0.2162          |
| 0.2181        | 0.7793 | 481  | 0.2154          |
| 0.213         | 0.8003 | 494  | 0.2133          |
| 0.2022        | 0.8214 | 507  | 0.2115          |
| 0.2084        | 0.8424 | 520  | 0.2093          |
| 0.206         | 0.8635 | 533  | 0.2080          |
| 0.201         | 0.8846 | 546  | 0.2074          |
| 0.1971        | 0.9056 | 559  | 0.2069          |
| 0.1986        | 0.9267 | 572  | 0.2065          |
| 0.2049        | 0.9478 | 585  | 0.2064          |
| 0.2034        | 0.9688 | 598  | 0.2061          |
| 0.2044        | 0.9899 | 611  | 0.2061          |


### Framework versions

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