---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B-Base
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: 500M
  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. -->

# 500M

This model is a fine-tuned version of [/lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base](https://huggingface.co//lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base) on the rv5_g2_2_oldcode_synthcm_newcode and the instruct_replay datasets.

## 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: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 12
- total_train_batch_size: 12
- total_eval_batch_size: 96
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: warmup_stable_decay
- lr_scheduler_warmup_steps: 178
- training_steps: 5597

### Training results



### Framework versions

- Transformers 4.57.6
- Pytorch 2.10.0a0+git449b176
- Datasets 4.5.0
- Tokenizers 0.22.2