metadata
library_name: transformers
language:
- en
base_model: cardiffnlp/twitter-roberta-base-sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: twitter-roberta-base-sentiment-tweet-sentiment
results: []
twitter-roberta-base-sentiment-tweet-sentiment
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment on the Twitter Sentiment Datasets dataset. It achieves the following results on the evaluation set:
- Loss: 0.4612
- Accuracy: 0.8139
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: 1.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5631 | 0.9985 | 332 | 0.4943 | 0.8013 |
| 0.4851 | 2.0 | 665 | 0.4745 | 0.8099 |
| 0.4166 | 2.9985 | 997 | 0.4612 | 0.8139 |
| 0.3621 | 4.0 | 1330 | 0.4830 | 0.8141 |
| 0.325 | 4.9925 | 1660 | 0.4989 | 0.8164 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1