metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - ag_news
widget:
  - text: >-
      At current rates, 5 key climate tipping points are already possible, new
      study warns
metrics:
  - accuracy
model-index:
  - name: distilroberta-base-finetuned-topic-news
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: ag_news
          type: ag_news
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9446052631578947

distilroberta-base-finetuned-topic-news

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

Loss: 0.2698
Accuracy: 0.9446

Label_0, Label_1, Label_2, Label_3 correspond to World News, Sports News, Business News, Sci/Tech News respectively

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: 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2639	1.0	15000	0.2809	0.9326
0.2045	2.0	30000	0.2420	0.9403
0.1467	3.0	45000	0.2674	0.9441
0.1061	4.0	60000	0.2698	0.9446

Framework versions

Transformers 4.22.2
Pytorch 1.12.1+cu113
Datasets 2.5.1
Tokenizers 0.12.1