avinasht's picture
Acc0.9188514357053683, F10.9185477500192393 , Augmented with Synonym-wordnet.csv, finetuned on google/electra-base-discriminator
506dd49 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_Synonym-wordnet
    results: []

electra-base-discriminator_Synonym-wordnet

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: 0.2211
  • Accuracy: 0.9267
  • F1: 0.9267
  • Precision: 0.9267
  • Recall: 0.9267

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
0.932 1.0 91 0.8735 0.6412 0.5915 0.6417 0.6412
0.426 2.0 182 0.3389 0.9002 0.9004 0.9008 0.9002
0.259 3.0 273 0.2577 0.9048 0.9039 0.9070 0.9048
0.1619 4.0 364 0.2211 0.9267 0.9267 0.9267 0.9267
0.1574 5.0 455 0.3301 0.8955 0.8959 0.9045 0.8955
0.0929 6.0 546 0.3284 0.9064 0.9054 0.9066 0.9064
0.1079 7.0 637 0.3467 0.9002 0.9003 0.9040 0.9002
0.0927 8.0 728 0.3817 0.9002 0.8993 0.9056 0.9002
0.0876 9.0 819 0.3524 0.9048 0.9044 0.9047 0.9048

Framework versions

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