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_mBERT
results: []
fine_tuned_mBERT
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: 0.0431
- F1: 0.8182
- F5: 0.8792
- Precision: 0.6923
- Recall: 1.0
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: 2.5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | F5 | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 16 | 0.2406 | 0.0 | 0.0 | 0.0 | 0.0 |
No log | 2.0 | 32 | 0.2933 | 0.6471 | 0.6062 | 0.7857 | 0.55 |
No log | 3.0 | 48 | 0.1965 | 0.5000 | 0.4297 | 0.875 | 0.35 |
No log | 4.0 | 64 | 0.1349 | 0.6842 | 0.6707 | 0.7222 | 0.65 |
No log | 5.0 | 80 | 0.1065 | 0.7027 | 0.6816 | 0.7647 | 0.65 |
No log | 6.0 | 96 | 0.1104 | 0.7727 | 0.8005 | 0.7083 | 0.85 |
No log | 7.0 | 112 | 0.1160 | 0.7273 | 0.7534 | 0.6667 | 0.8 |
No log | 8.0 | 128 | 0.1049 | 0.7647 | 0.7164 | 0.9286 | 0.65 |
No log | 9.0 | 144 | 0.0975 | 0.7778 | 0.7461 | 0.875 | 0.7 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.17.1
- Tokenizers 0.15.2