---
base_model: unsloth/Qwen2-7B
library_name: peft
license: apache-2.0
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Qwen2-7B_pct_reverse
  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_pct_reverse

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: 2.0219

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 2.1146        | 0.0206 | 8    | 2.0126          |
| 2.1241        | 0.0412 | 16   | 2.0399          |
| 2.1297        | 0.0618 | 24   | 2.0522          |
| 2.0751        | 0.0824 | 32   | 2.0553          |
| 2.1182        | 0.1031 | 40   | 2.0606          |
| 2.1169        | 0.1237 | 48   | 2.0666          |
| 2.1253        | 0.1443 | 56   | 2.0730          |
| 2.1136        | 0.1649 | 64   | 2.0714          |
| 2.127         | 0.1855 | 72   | 2.0839          |
| 2.1835        | 0.2061 | 80   | 2.0803          |
| 2.1556        | 0.2267 | 88   | 2.0903          |
| 2.1396        | 0.2473 | 96   | 2.0887          |
| 2.1656        | 0.2680 | 104  | 2.0928          |
| 2.0821        | 0.2886 | 112  | 2.0880          |
| 2.1287        | 0.3092 | 120  | 2.0923          |
| 2.1298        | 0.3298 | 128  | 2.0969          |
| 2.1317        | 0.3504 | 136  | 2.0961          |
| 2.1325        | 0.3710 | 144  | 2.0906          |
| 2.1398        | 0.3916 | 152  | 2.0906          |
| 2.1569        | 0.4122 | 160  | 2.0886          |
| 2.195         | 0.4329 | 168  | 2.0862          |
| 2.1038        | 0.4535 | 176  | 2.0899          |
| 2.1159        | 0.4741 | 184  | 2.0845          |
| 2.1605        | 0.4947 | 192  | 2.0805          |
| 2.0894        | 0.5153 | 200  | 2.0765          |
| 2.1368        | 0.5359 | 208  | 2.0748          |
| 2.1626        | 0.5565 | 216  | 2.0715          |
| 2.0765        | 0.5771 | 224  | 2.0630          |
| 2.0879        | 0.5977 | 232  | 2.0677          |
| 2.0851        | 0.6184 | 240  | 2.0554          |
| 2.0731        | 0.6390 | 248  | 2.0549          |
| 2.113         | 0.6596 | 256  | 2.0517          |
| 2.0796        | 0.6802 | 264  | 2.0484          |
| 2.1406        | 0.7008 | 272  | 2.0457          |
| 2.0454        | 0.7214 | 280  | 2.0421          |
| 2.1278        | 0.7420 | 288  | 2.0378          |
| 2.0616        | 0.7626 | 296  | 2.0353          |
| 2.0697        | 0.7833 | 304  | 2.0340          |
| 2.0557        | 0.8039 | 312  | 2.0300          |
| 2.0954        | 0.8245 | 320  | 2.0304          |
| 2.094         | 0.8451 | 328  | 2.0297          |
| 2.0539        | 0.8657 | 336  | 2.0266          |
| 2.0866        | 0.8863 | 344  | 2.0250          |
| 2.061         | 0.9069 | 352  | 2.0227          |
| 2.126         | 0.9275 | 360  | 2.0220          |
| 2.0616        | 0.9481 | 368  | 2.0222          |
| 2.106         | 0.9688 | 376  | 2.0219          |
| 2.0596        | 0.9894 | 384  | 2.0219          |


### Framework versions

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