metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - yelp_polarity
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert-base-uncased-finetuned-yelp-polarity
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: yelp_polarity
          type: yelp_polarity
          config: plain_text
          split: train
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9617414248021108
          - name: F1
            type: f1
            value: 0.9617407987866946

distilbert-base-uncased-finetuned-yelp-polarity

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

Loss: 0.1395
Accuracy: 0.9617
F1: 0.9617

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: 24
eval_batch_size: 24
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
0.1334	1.0	2332	0.1141	0.9602	0.9602
0.0722	2.0	4664	0.1395	0.9617	0.9617

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.7.1
Tokenizers 0.13.2