qwen2_5_omni_image_only_3

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7896
• Token Acc: 0.7681

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: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Token Acc
0.8579	1.3562	50	0.9498	0.7264
0.5798	2.7123	100	0.7935	0.7674
0.5528	3.0	111	0.7896	0.7681

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.1