---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: SWE-Lego-Qwen3-8B-posttrain
  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. -->

# SWE-Lego-Qwen3-8B-posttrain

This model is a fine-tuned version of [/mmu-vcg-hdd/multimodal/models/Qwen3-8B-fim-v2v3pt](https://huggingface.co//mmu-vcg-hdd/multimodal/models/Qwen3-8B-fim-v2v3pt) on the swe_lego_real_data_resolved_trajectories and the swe_lego_synthetic_data_resolved_trajectories 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 8
- total_train_batch_size: 48
- total_eval_batch_size: 48
- optimizer: Use OptimizerNames.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_steps: 0.1
- num_epochs: 4.0

### Training results



### Framework versions

- Transformers 5.0.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.2