---
license: apache-2.0
base_model: Qwen/Qwen2-7B
tags:
- generated_from_trainer
model-index:
- name: Qwen2-7B-spin-2k
  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-spin-2k

This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1115
- Rewards/real: 6.6307
- Rewards/generated: -5.6978
- Rewards/accuracies: 1.0
- Rewards/margins: 12.3284
- Logps/generated: -348.4622
- Logps/real: -123.6893
- Logits/generated: -0.9537
- Logits/real: -1.6166

## 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: 5e-07
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
| 0.1108        | 0.8   | 50   | 0.1115          | 6.6307       | -5.6978           | 1.0                | 12.3284         | -348.4622       | -123.6893  | -0.9537          | -1.6166     |


### Framework versions

- Transformers 4.43.3
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1