---
library_name: peft
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
datasets:
- tttx/test-star-9-step1-trajectories
model-index:
- name: masked-star-test-star-9-step1
  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. -->

# masked-star-test-star-9-step1

This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on the tttx/test-star-9-step1-trajectories dataset.
It achieves the following results on the evaluation set:
- Loss: 3.8782

## 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-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.3298        | 1.0   | 1    | 3.9557          |
| 0.4377        | 2.0   | 2    | 3.8782          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.47.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3