---
library_name: transformers
license: other
base_model: Qwen3.5-9B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: qwen35_caption_galore
  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. -->

# qwen35_caption_galore

This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

using more dense captions

### Training hyperparameters

The following hyperparameters were used during training:
- family_to_muon_lr = {
        "language": _fallback(getattr(training_args, "language_muon_lr", 1e-5), language_lr),
        "vision": _fallback(getattr(training_args, "vision_muon_lr", 1e-5), vision_lr),
        "merger": _fallback(getattr(training_args, "merger_muon_lr", 4e-5), merger_lr),
    }

    family_to_adamw_lr = {
        "language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
        "vision": _fallback(getattr(training_args, "vision_adamw_lr", 1e-6), vision_lr),
        "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
    }
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 3

### Training results



### Framework versions

- Transformers 5.5.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2