stage1_5_midtrain
This model is a fine-tuned version of Qwen3-VL-4B on the llava_ov_1_5_midtrain3m dataset.
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 18
- total_train_batch_size: 144
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-05 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_ratio: 0.002
- training_steps: 23831
Training results
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.1
