mlfoundations-cua-dev/qwen2_5vl_3b_sft_idm_syntheticr_synthetic_text_overlay_yt_labeled_data

qwen2_5vl_3b_sft_idm_synthetic_websites_synthetic_editor_synthetic_text_overlay_yt_labeled_data

This model is a fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct on the synthetic-websites-idm-data, the synthetic-editor-idm-data, the synthetic-text-overlay-idm-data and the yt-labeled-idm-data 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: 1e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 16
• total_eval_batch_size: 64
• optimizer: Use 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_ratio: 0.1
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.5.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1