metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: bert-base-multilingual-cased-esp
results: []
bert-base-multilingual-cased-esp
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1008
- Accuracy: 0.8433
- F1 Binary: 0.7014
- Precision: 0.6370
- Recall: 0.7803
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 29
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Binary | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 150 | 0.1366 | 0.8056 | 0.5258 | 0.6190 | 0.4569 |
| No log | 2.0 | 300 | 0.0880 | 0.8284 | 0.6709 | 0.6125 | 0.7417 |
| No log | 3.0 | 450 | 0.0810 | 0.8333 | 0.6959 | 0.6109 | 0.8084 |
| 0.0885 | 4.0 | 600 | 0.1008 | 0.8433 | 0.7014 | 0.6370 | 0.7803 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0