nikitakapitan's picture
End of training
4ebee7c
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
  - f1
model-index:
  - name: bert-base-uncased-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:
              accuracy: 0.94124
          - name: F1
            type: f1
            value:
              f1: 0.9412364248240864

bert-base-uncased-finetuned-imdb

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

  • Loss: 0.2708
  • Accuracy: {'accuracy': 0.94124}
  • F1: {'f1': 0.9412364248240864}

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.2201 1.0 1563 0.2556 {'accuracy': 0.91716} {'f1': 0.9168776701523282}
0.1445 2.0 3126 0.2199 {'accuracy': 0.94092} {'f1': 0.940911994189728}
0.0719 3.0 4689 0.2708 {'accuracy': 0.94124} {'f1': 0.9412364248240864}

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3