RajuEEE's picture
RajuEEE/Paper_RewardModel_RobertaBase
c6511d9 verified
metadata
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: RewardModel_RobertaBase
    results: []

RewardModel_RobertaBase

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5050
  • F1: 0.7522
  • Roc Auc: 0.7526
  • Accuracy: 0.7509

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
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy
0.6464 1.0 100 0.6186 0.6772 0.6772 0.6737
0.5776 2.0 200 0.5439 0.7298 0.7298 0.7298
0.4806 3.0 300 0.5050 0.7522 0.7526 0.7509
0.3909 4.0 400 0.8594 0.6690 0.6684 0.6667
0.331 5.0 500 0.7766 0.7206 0.7211 0.7193

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1