lora_v5_0414_50万个样本512~1024

<!-- 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. --> # train_2100-01-01-01-01 This model is a fine-tuned version of [/root/autodl-tmp/models/Qwen/Qwen3-VL-32B-Instruct](https://huggingface.co//root/autodl-tmp/models/Qwen/Qwen3-VL-32B-Instruct) on the v4_messages_512, the v4_messages_1024, the v4_messages_class_choice_512, the v4_messages_class_choice_1024, the v4_messages_coord_choice_512, the v4_messages_coord_choice_1024, the v4_train_class_512, the v4_train_class_1024, the v4_train_coord_512 and the v4_train_coord_1024 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-06 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - total_eval_batch_size: 64 - 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: cosine - training_steps: 3922 ### Training results ### Framework versions - PEFT 0.18.1 - Transformers 5.2.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2