metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: product_classifier_split_url_nodigit_lv2
results: []
product_classifier_split_url_nodigit_lv2
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1478
- Accuracy: 0.9712
- F1: 0.9710
- Precision: 0.9710
- Recall: 0.9712
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2139 | 1.0 | 1085 | 0.1540 | 0.9551 | 0.9550 | 0.9550 | 0.9551 |
| 0.1133 | 2.0 | 2170 | 0.1396 | 0.9634 | 0.9629 | 0.9632 | 0.9634 |
| 0.0692 | 3.0 | 3255 | 0.1381 | 0.9691 | 0.9689 | 0.9690 | 0.9691 |
| 0.0416 | 4.0 | 4340 | 0.1478 | 0.9712 | 0.9710 | 0.9710 | 0.9712 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3