metadata
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: NLP_90_1
results: []
NLP_90_1
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3325
- Accuracy: 0.9174
- Precision: 0.9126
- Recall: 0.9140
- F1: 0.9128
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: 1e-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: cosine
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3664 | 1.0 | 48 | 0.3609 | 0.8991 | 0.8935 | 0.8988 | 0.8938 |
| 0.2282 | 2.0 | 96 | 0.3376 | 0.8991 | 0.8920 | 0.8978 | 0.8927 |
| 0.1638 | 3.0 | 144 | 0.3184 | 0.9128 | 0.9070 | 0.9079 | 0.9070 |
| 0.1595 | 4.0 | 192 | 0.3291 | 0.9174 | 0.9147 | 0.9131 | 0.9135 |
| 0.1388 | 5.0 | 240 | 0.3495 | 0.8945 | 0.8844 | 0.8918 | 0.8865 |
| 0.1075 | 6.0 | 288 | 0.3357 | 0.9174 | 0.9151 | 0.9141 | 0.9139 |
| 0.1073 | 7.0 | 336 | 0.3311 | 0.9174 | 0.9126 | 0.9140 | 0.9128 |
| 0.1507 | 8.0 | 384 | 0.3325 | 0.9174 | 0.9126 | 0.9140 | 0.9128 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1