neerajprad's picture
End of training
2bcdc9f
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - financial_phrasebank
metrics:
  - f1
  - accuracy
model-index:
  - name: phrasebank-sentiment-analysis
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: financial_phrasebank
          type: financial_phrasebank
          config: sentences_50agree
          split: train
          args: sentences_50agree
        metrics:
          - name: F1
            type: f1
            value: 0.8479759296912354
          - name: Accuracy
            type: accuracy
            value: 0.8576341127922971

phrasebank-sentiment-analysis

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

  • Loss: 0.5374
  • F1: 0.8480
  • Accuracy: 0.8576

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 8
  • 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 F1 Accuracy
0.5974 0.94 100 0.3898 0.8212 0.8370
0.2647 1.89 200 0.3821 0.8397 0.8583
0.1433 2.83 300 0.4250 0.8487 0.8645
0.0669 3.77 400 0.5374 0.8480 0.8576

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1