README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - ag_news
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert-base-uncased-news-trained
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: ag_news
          type: ag_news
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9194736842105263
          - name: F1
            type: f1
            value: 0.9195099897221968

distilbert-base-uncased-news-trained

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

• Loss: 0.2420
• Accuracy: 0.9195
• F1: 0.9195

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: 64
• eval_batch_size: 64
• 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	F1
0.346	1.0	469	0.2511	0.9142	0.9142
0.1874	2.0	938	0.2420	0.9195	0.9195

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3