metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: distilbert-finetuned-imdb
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: imdb
          type: imdb
          config: plain_text
          split: test
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.93208

distilbert-finetuned-imdb

This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.2742
Accuracy: 0.9321

Model description

More information needed

Intended uses & limitations

The model is fine-tuned for sentiment analysis use cases. It can take a review and classify the review as 'positive' or 'negative'.

Training and evaluation data

The model is fine-tuned with the IMDB dataset which consists of 25000 training records and 25000 testing records. The model is trained and validated on all of them.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2686	1.0	3125	0.2484	0.9223
0.1714	2.0	6250	0.2742	0.9321

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0