---
library_name: transformers
license: other
base_model: qwen/qwen3-32b
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: qwen3-32b-stage2-v2
  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. -->

# qwen3-32b-stage2-v2

This model is a fine-tuned version of [/workspace/llama-factory/saves/Qwen3-32B-Instruct/full/train_2025-05-25-12-02-28](https://huggingface.co//workspace/llama-factory/saves/Qwen3-32B-Instruct/full/train_2025-05-25-12-02-28) on the private_roleplay and the enhance datasets.
It achieves the following results on the evaluation set:
- Loss: 2.4615
- Num Input Tokens Seen: 2064704

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.PAGED_LION_8BIT and the args are:
No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3.0

### Training results



### Framework versions

- Transformers 4.52.1
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1