metadata
base_model: cardiffnlp/twitter-xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: training_with_callbacks
results: []
training_with_callbacks
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4317
- Precision: 0.7304
- Recall: 0.7613
- F1: 0.7456
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 458 | 0.4317 | 0.7304 | 0.7613 | 0.7456 |
| 0.5107 | 2.0 | 916 | 0.4730 | 0.8008 | 0.6193 | 0.6985 |
| 0.3555 | 3.0 | 1374 | 0.4850 | 0.7512 | 0.7205 | 0.7355 |
| 0.2265 | 4.0 | 1832 | 0.6697 | 0.7379 | 0.7356 | 0.7368 |
| 0.1547 | 5.0 | 2290 | 0.7118 | 0.7491 | 0.6450 | 0.6932 |
| 0.1154 | 6.0 | 2748 | 1.0137 | 0.7177 | 0.7221 | 0.7199 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1