roy1109/math_solving_model

1---2license: mit3library_name: peft4tags:5- generated_from_trainer6base_model: microsoft/phi-27model-index:8- name: math_solving_model9  results: []10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# math_solving_model16 17This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.18 19## Model description20 21More information needed22 23## Intended uses & limitations24 25More information needed26 27## Training and evaluation data28 29More information needed30 31## Training procedure32 33### Training hyperparameters34 35The following hyperparameters were used during training:36- learning_rate: 5e-0537- train_batch_size: 138- eval_batch_size: 839- seed: 4240- gradient_accumulation_steps: 841- total_train_batch_size: 842- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0843- lr_scheduler_type: cosine44- lr_scheduler_warmup_steps: 5045- num_epochs: 246- mixed_precision_training: Native AMP47 48### Framework versions49 50- PEFT 0.10.051- Transformers 4.38.252- Pytorch 2.2.1+cu12153- Datasets 2.18.054- Tokenizers 0.15.2