PC-Agent-E

<!-- 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. -->

PC-Agent-E

This model is a fine-tuned version of Qwen/Qwen2.5-VL-72B-Instruct on the PC-Agent-E dataset.

It was presented in Efficient Agent Training for Computer Use.

Github repository: https://github.com/GAIR-NLP/PC-Agent-E

Training procedure

Github repository: https://github.com/GAIR-NLP/PC-Agent-E

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 256
• 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
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0