metadata
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: base
results: []
base
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3065
- Accuracy: 0.8228
- F1: 0.7716
- Precision: 0.8261
- Recall: 0.7238
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6706 | 1.0 | 64 | 0.5822 | 0.6811 | 0.5424 | 0.6667 | 0.4571 |
| 0.5059 | 2.0 | 128 | 0.5081 | 0.7520 | 0.6595 | 0.7625 | 0.5810 |
| 0.2901 | 3.0 | 192 | 0.5731 | 0.8465 | 0.7958 | 0.8837 | 0.7238 |
| 0.2094 | 4.0 | 256 | 0.7700 | 0.8189 | 0.7629 | 0.8315 | 0.7048 |
| 0.1235 | 5.0 | 320 | 1.0102 | 0.8150 | 0.7459 | 0.8625 | 0.6571 |
| 0.0435 | 6.0 | 384 | 1.0899 | 0.8268 | 0.7755 | 0.8352 | 0.7238 |
| 0.0099 | 7.0 | 448 | 1.2422 | 0.8268 | 0.7582 | 0.8961 | 0.6571 |
| 0.0111 | 8.0 | 512 | 1.2646 | 0.8386 | 0.7760 | 0.9103 | 0.6762 |
| 0.0023 | 9.0 | 576 | 1.2875 | 0.8228 | 0.7783 | 0.8061 | 0.7524 |
| 0.003 | 10.0 | 640 | 1.3065 | 0.8228 | 0.7716 | 0.8261 | 0.7238 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1