de-beginning / README.md
satpalsr's picture
satpalsr/de-beginning
af410c9
|
raw
history blame
1.39 kB
metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
model-index:
  - name: reward-model-out
    results: []

reward-model-out

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.6273
  • eval_accuracy: 0.6449
  • eval_precision: 0.6600
  • eval_recall: 0.8789
  • eval_f1: 0.7539
  • eval_runtime: 110.7892
  • eval_samples_per_second: 35.536
  • eval_steps_per_second: 8.891
  • epoch: 0.51
  • step: 600

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: 6e-06
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.14.1