metadata
library_name: transformers
license: mit
base_model: nlptown/bert-base-multilingual-uncased-sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results_bert_full
results: []
results_bert_full
This model is a fine-tuned version of nlptown/bert-base-multilingual-uncased-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5777
- Accuracy: 0.5291
- F1: 0.5313
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 258 | 1.1025 | 0.4399 | 0.3521 |
| 1.0765 | 2.0 | 516 | 1.0620 | 0.4535 | 0.3657 |
| 1.0765 | 3.0 | 774 | 1.0407 | 0.4496 | 0.3876 |
| 0.9785 | 4.0 | 1032 | 1.0211 | 0.5097 | 0.5038 |
| 0.9785 | 5.0 | 1290 | 1.0746 | 0.5116 | 0.5006 |
| 0.8198 | 6.0 | 1548 | 1.0384 | 0.5155 | 0.5122 |
| 0.8198 | 7.0 | 1806 | 1.1387 | 0.5446 | 0.5447 |
| 0.6294 | 8.0 | 2064 | 1.2842 | 0.5310 | 0.5327 |
| 0.6294 | 9.0 | 2322 | 1.4142 | 0.5252 | 0.5288 |
| 0.4711 | 10.0 | 2580 | 1.5777 | 0.5291 | 0.5313 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0