metadata
base_model: daveni/twitter-xlm-roberta-emotion-es
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: base
results: []
base
This model is a fine-tuned version of daveni/twitter-xlm-roberta-emotion-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9425
- Accuracy: 0.8465
- F1: 0.8
- Precision: 0.8667
- Recall: 0.7429
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 |
|---|---|---|---|---|---|---|---|
| 0.6431 | 1.0 | 64 | 0.5474 | 0.7362 | 0.6171 | 0.7714 | 0.5143 |
| 0.4576 | 2.0 | 128 | 0.5103 | 0.7795 | 0.7358 | 0.7290 | 0.7429 |
| 0.2933 | 3.0 | 192 | 0.5647 | 0.8228 | 0.7619 | 0.8571 | 0.6857 |
| 0.198 | 4.0 | 256 | 0.6377 | 0.8346 | 0.7742 | 0.8889 | 0.6857 |
| 0.113 | 5.0 | 320 | 0.6867 | 0.8504 | 0.7935 | 0.9241 | 0.6952 |
| 0.057 | 6.0 | 384 | 0.8875 | 0.8189 | 0.7788 | 0.7864 | 0.7714 |
| 0.0282 | 7.0 | 448 | 0.9361 | 0.8346 | 0.7879 | 0.8387 | 0.7429 |
| 0.0234 | 8.0 | 512 | 1.0229 | 0.8228 | 0.7826 | 0.7941 | 0.7714 |
| 0.0095 | 9.0 | 576 | 0.9131 | 0.8622 | 0.8168 | 0.9070 | 0.7429 |
| 0.0101 | 10.0 | 640 | 0.9425 | 0.8465 | 0.8 | 0.8667 | 0.7429 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1