metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-multilingual-uncased-finetuned-keyword
results: []
bert-base-multilingual-uncased-finetuned-keyword
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: 6.3507
- Accuracy: 0.0617
- Precision: 0.0398
- Recall: 0.0617
- F1: 0.0393
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 269 | 6.7306 | 0.0024 | 0.0000 | 0.0024 | 0.0000 |
| 6.7277 | 2.0 | 538 | 6.5913 | 0.0090 | 0.0028 | 0.0090 | 0.0036 |
| 6.7277 | 3.0 | 807 | 6.4561 | 0.0276 | 0.0164 | 0.0276 | 0.0159 |
| 6.4145 | 4.0 | 1076 | 6.3776 | 0.0539 | 0.0374 | 0.0539 | 0.0360 |
| 6.4145 | 5.0 | 1345 | 6.3507 | 0.0617 | 0.0398 | 0.0617 | 0.0393 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1