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-tir
results: []
bert-base-multilingual-cased-tir
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: 0.1424
- Accuracy: 0.6520
- F1 Binary: 0.3654
- Precision: 0.2527
- Recall: 0.6592
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: 55
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Binary | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 276 | 0.1520 | 0.7999 | 0.3719 | 0.3555 | 0.3899 |
| 0.1423 | 2.0 | 552 | 0.1383 | 0.7499 | 0.3835 | 0.3066 | 0.5119 |
| 0.1423 | 3.0 | 828 | 0.1401 | 0.7763 | 0.3807 | 0.3286 | 0.4524 |
| 0.1303 | 4.0 | 1104 | 0.1424 | 0.6520 | 0.3654 | 0.2527 | 0.6592 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0