obamaTeo's picture
End of training
554ed17 verified
metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: deberta-v3-large-262-ver1
    results: []

deberta-v3-large-262-ver1

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

  • Loss: 0.0768
  • Precision: 0.9904
  • Recall: 0.9904
  • F1: 0.9904
  • Accuracy: 0.9904

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: 12
  • eval_batch_size: 12
  • 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 Precision Recall F1 Accuracy
0.0624 1.0 1287 0.0447 0.9907 0.9907 0.9907 0.9907
0.0272 2.0 2574 0.0899 0.9865 0.9865 0.9865 0.9865
0.0136 3.0 3861 0.0605 0.9894 0.9894 0.9894 0.9894
0.0071 4.0 5148 0.0771 0.9894 0.9894 0.9894 0.9894
0.0015 5.0 6435 0.0768 0.9904 0.9904 0.9904 0.9904

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.2.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1