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: 0.1299
- F1: 0.8444
- F5: 0.8373
- Precision: 0.8636
- Recall: 0.8261
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- 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 | 33 | 0.3776 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 66 | 0.2996 | 0.4 | 0.3359 | 0.8 | 0.2667 |
| No log | 3.0 | 99 | 0.2137 | 0.7273 | 0.7534 | 0.6667 | 0.8 |
| No log | 4.0 | 132 | 0.2161 | 0.6429 | 0.6258 | 0.6923 | 0.6 |
| No log | 5.0 | 165 | 0.2367 | 0.6154 | 0.5812 | 0.7273 | 0.5333 |
| No log | 6.0 | 198 | 0.1997 | 0.7451 | 0.6980 | 0.9048 | 0.6333 |
| No log | 7.0 | 231 | 0.2023 | 0.8000 | 0.8 | 0.8 | 0.8 |
| No log | 8.0 | 264 | 0.2011 | 0.8070 | 0.7911 | 0.8519 | 0.7667 |
| No log | 9.0 | 297 | 0.2196 | 0.7857 | 0.7648 | 0.8462 | 0.7333 |
| No log | 10.0 | 330 | 0.2509 | 0.7667 | 0.7667 | 0.7667 | 0.7667 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.17.1
- Tokenizers 0.15.2