Xin-Rui's picture
Add files using upload-large-folder tool
c0f3f18 verified
metadata
library_name: transformers
license: other
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: output_1
    results: []

output_1

This model is a fine-tuned version of /data2/wuxinrui/RoboBrain2.0/HF_Models/BAAI-RoboBrain2.0-7B_budgetthinker_3ratio on the region_ref_max_points_10_absxy_int_2k_cot_processed_shorten_shorten2_budgetthinker_3ratio_mllm, the region_ref_max_points_10_absxy_int_2k_cot_processed_shorten_budgetthinker_3ratio_mllm, the region_ref_max_points_10_absxy_int_2k_cot_processed_budgetthinker_3ratio_mllm, the sharerobot_trajectory_2k_cot_processed_shorten_shorten2_budgetthinker_3ratio_mllm, the sharerobot_trajectory_2k_cot_processed_shorten_budgetthinker_3ratio_mllm, the sharerobot_trajectory_2k_cot_processed_budgetthinker_3ratio_mllm, the AGD_affordance_train_common_1336_shorten_shorten2_budgetthinker_3ratio_mllm, the AGD_affordance_train_common_1336_shorten_budgetthinker_3ratio_mllm, the AGD_affordance_train_common_1336_budgetthinker_3ratio_mllm, the osd_choice_qa_absolute_position_2k_cot_processed_shorten_shorten2_budgetthinker_3ratio_mllm, the osd_choice_qa_absolute_position_2k_cot_processed_shorten_budgetthinker_3ratio_mllm, the osd_choice_qa_absolute_position_2k_cot_processed_budgetthinker_3ratio_mllm, the osd_reasoning_qa_2k_cot_processed_shorten_shorten2_budgetthinker_3ratio_mllm, the osd_reasoning_qa_2k_cot_processed_shorten_budgetthinker_3ratio_mllm and the osd_reasoning_qa_2k_cot_processed_budgetthinker_3ratio_mllm 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: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 6
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 12
  • total_eval_batch_size: 48
  • 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: 0.1
  • num_epochs: 2.0

Training results

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.8.0+cu128
  • Datasets 3.6.0
  • Tokenizers 0.21.1