orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode

<!-- 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. -->

kaist-mistral-orpo-OHP-15k-Mathcode

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the orpo-explorers/OHP-15k-mathcode 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: 5e-06
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —num_epochs: 3

Training results

Framework versions

• —Transformers 4.39.3
• —Pytorch 2.1.2.post303
• —Datasets 2.18.0
• —Tokenizers 0.15.2