avinasht's picture
Acc0.8764044943820225, F10.8761472718126238 , Augmented with roberta-base.csv, finetuned on google/electra-base-discriminator
3ffe8c3 verified
metadata
license: apache-2.0
base_model: google/electra-base-discriminator
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: electra-base-discriminator_roberta-base
    results: []

electra-base-discriminator_roberta-base

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

  • Loss: 0.4180
  • Accuracy: 0.8768
  • F1: 0.8767
  • Precision: 0.8766
  • Recall: 0.8768

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: 0.0001
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 25

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.955 1.0 91 0.8849 0.6349 0.5849 0.6173 0.6349
0.4845 2.0 182 0.4777 0.8237 0.8221 0.8271 0.8237
0.3434 3.0 273 0.3821 0.8580 0.8579 0.8598 0.8580
0.2683 4.0 364 0.5158 0.8237 0.8213 0.8362 0.8237
0.1675 5.0 455 0.3875 0.8643 0.8633 0.8651 0.8643
0.1788 6.0 546 0.4180 0.8768 0.8767 0.8766 0.8768
0.1669 7.0 637 0.4189 0.8768 0.8754 0.8775 0.8768
0.1103 8.0 728 0.5338 0.8534 0.8542 0.8569 0.8534
0.1597 9.0 819 0.4306 0.8674 0.8674 0.8676 0.8674
0.1443 10.0 910 0.6446 0.8580 0.8574 0.8580 0.8580
0.1012 11.0 1001 0.5104 0.8534 0.8535 0.8541 0.8534

Framework versions

  • Transformers 4.37.0
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.1