metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: irony_es_Mexico
results: []
irony_es_Mexico
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0036
- Accuracy: 0.6531
- Precision: 0.5292
- Recall: 0.5686
- F1: 0.5482
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-06
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.0044 | 1.0 | 129 | 0.0042 | 0.5922 | 0.448 | 0.4392 | 0.4436 |
0.0041 | 2.0 | 258 | 0.0041 | 0.5239 | 0.4238 | 0.7961 | 0.5531 |
0.0039 | 3.0 | 387 | 0.0038 | 0.5864 | 0.4615 | 0.7059 | 0.5581 |
0.0034 | 4.0 | 516 | 0.0034 | 0.5399 | 0.4362 | 0.8314 | 0.5722 |
0.003 | 5.0 | 645 | 0.0032 | 0.6241 | 0.4944 | 0.6902 | 0.5761 |
0.0023 | 6.0 | 774 | 0.0036 | 0.5733 | 0.4509 | 0.7020 | 0.5491 |
0.0022 | 7.0 | 903 | 0.0036 | 0.6531 | 0.5292 | 0.5686 | 0.5482 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1