| <!-- 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. --> | |
| # multi_student_6 | |
| 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_student_6 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: 7.0 | |
| ### Training results | |
| ### Framework versions | |
| - Transformers 4.57.3 | |
| - Pytorch 2.6.0+cu124 | |
| - Datasets 4.0.0 | |
| - Tokenizers 0.22.2 | |