GregorRus's picture
Update README.md
d8926d3 verified
metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: distilbert-base-uncased-imdb
    results: []
language:
  - en
library_name: transformers
pipeline_tag: text-classification

distilbert-base-uncased-imdb

This model is a fine-tuned version of distilbert/distilbert-base-uncased on Imdb Movie Reviews Sentiment Analysis (Kaggle) dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2898
  • Accuracy: 0.9284
  • Precision: 0.9281
  • Recall: 0.9288
  • F1: 0.9284

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.2727 1.0 625 0.2194 0.9178 0.8853 0.96 0.9211
0.1569 2.0 1250 0.2082 0.9236 0.8957 0.9588 0.9262
0.1211 3.0 1875 0.2739 0.9256 0.9379 0.9116 0.9245
0.0544 4.0 2500 0.2898 0.9284 0.9281 0.9288 0.9284

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1