metadata
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: twitter_roberta_sentiment_model
results: []
twitter_roberta_sentiment_model
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: 0.3658
- Accuracy: 0.8045
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6116 | 0.2 | 100 | 0.4453 | 0.6965 |
| 0.4047 | 0.4 | 200 | 0.3999 | 0.735 |
| 0.3979 | 0.6 | 300 | 0.3641 | 0.7655 |
| 0.3828 | 0.8 | 400 | 0.3512 | 0.7635 |
| 0.3805 | 1.0 | 500 | 0.3489 | 0.776 |
| 0.3454 | 1.2 | 600 | 0.3488 | 0.774 |
| 0.3135 | 1.4 | 700 | 0.3529 | 0.785 |
| 0.3216 | 1.6 | 800 | 0.3344 | 0.7845 |
| 0.3005 | 1.8 | 900 | 0.3793 | 0.789 |
| 0.3041 | 2.0 | 1000 | 0.3324 | 0.7925 |
| 0.2126 | 2.2 | 1100 | 0.3839 | 0.7895 |
| 0.2218 | 2.4 | 1200 | 0.3653 | 0.7955 |
| 0.1986 | 2.6 | 1300 | 0.3745 | 0.803 |
| 0.2049 | 2.8 | 1400 | 0.3586 | 0.802 |
| 0.1911 | 3.0 | 1500 | 0.3658 | 0.8045 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1