vlmvector_qwen25vl_train_multi_layer_distill_AOP_pooling_layer8_ablation_1230

This model is a fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct on the None 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: 5e-05
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• total_train_batch_size: 1024
• total_eval_batch_size: 128
• 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: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 5000

Training results

Framework versions

• Transformers 4.52.3
• Pytorch 2.7.1
• Datasets 3.3.0
• Tokenizers 0.21.4