metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
model-index:
- name: fine_tuned_bert
results: []
fine_tuned_bert
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1446
- F1: 0.6190
- F5: 0.6548
- Precision: 0.5417
- Recall: 0.7222
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | F5 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 65 | 0.3086 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 130 | 0.2538 | 0.5352 | 0.6034 | 0.4130 | 0.76 |
| No log | 3.0 | 195 | 0.3520 | 0.3333 | 0.3107 | 0.4118 | 0.28 |
| No log | 4.0 | 260 | 0.1806 | 0.6531 | 0.6480 | 0.6667 | 0.64 |
| No log | 5.0 | 325 | 0.3014 | 0.5263 | 0.4697 | 0.7692 | 0.4 |
| No log | 6.0 | 390 | 0.2432 | 0.6667 | 0.6562 | 0.6957 | 0.64 |
| No log | 7.0 | 455 | 0.2808 | 0.7059 | 0.7112 | 0.6923 | 0.72 |
| 0.1489 | 8.0 | 520 | 0.2133 | 0.76 | 0.76 | 0.76 | 0.76 |
| 0.1489 | 9.0 | 585 | 0.2639 | 0.7692 | 0.7807 | 0.7407 | 0.8 |
| 0.1489 | 10.0 | 650 | 0.3313 | 0.6809 | 0.6646 | 0.7273 | 0.64 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2