# multi_teacher_electronic_assembly_without_cot This model is a fine-tuned version of [/data/mentianyi/code/PlanPhys/model_configs/qwen2_100M_paper_2_random_pretraining](https://huggingface.co//data/mentianyi/code/PlanPhys/model_configs/qwen2_100M_paper_2_random_pretraining) on the multi_teacher_electronic_assembly_without_cot 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: 0.0001 - train_batch_size: 128 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 2 - total_train_batch_size: 512 - total_eval_batch_size: 16 - 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: 8.0 ### Training results ### Framework versions - Transformers 4.57.3 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.22.2