metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: finetuning-sentiment-all_df
    results: []
datasets:
  - glue
  - wisesight_sentiment
  - tweet_eval
  - imdb
language:
  - en
  - th
pipeline_tag: text-classification
widget:
  - text: ไปเลยยยย 555 โคตรคุ้มมมมค่า
    example: pos
  - text: ยาบ้าโทษประหารนะครับ
    example: neu
  - text: จับบุหรี่ไฟฟ้า ยึดรถ????
    example: neg

finetuning-sentiment-all_df

This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5500
Accuracy: 0.7683
F1: 0.7683

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: 2

Training results

Framework versions

Transformers 4.25.1
Pytorch 1.13.1+cu116
Datasets 2.8.0
Tokenizers 0.13.2