Mbabazi's picture
End of training
46e710a
metadata
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: cardiffnlp_twitter_roberta_base_sentiment_latest_Nov2023
    results: []

cardiffnlp_twitter_roberta_base_sentiment_latest_Nov2023

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3189
  • Accuracy: 0.805

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
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6619 0.2 100 0.5226 0.6285
0.4526 0.4 200 0.4150 0.716
0.4092 0.6 300 0.3898 0.728
0.3886 0.8 400 0.3441 0.773
0.3822 1.0 500 0.3494 0.767
0.3396 1.2 600 0.3470 0.7865
0.3156 1.4 700 0.3418 0.7875
0.3099 1.6 800 0.3231 0.794
0.2994 1.8 900 0.3371 0.7885
0.2907 2.0 1000 0.3189 0.805

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1