CoolFace
Modelpublic

Abhay11/RewardModel

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes7downloads
Model Card

<!-- 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. -->

RewardModel

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7352
  • —Accuracy: 0.8753

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: 2e-05
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 3

Training results

Training LossEpochStepValidation LossAccuracy
0.48691.016960.62770.88
0.11062.033920.71120.88
0.00083.050880.73520.8753

Framework versions

  • —PEFT 0.10.0
  • —Transformers 4.39.3
  • —Pytorch 2.2.2+cu121
  • —Datasets 2.19.0
  • —Tokenizers 0.15.2