metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
- f1
model-index:
- name: NL_BERT_michelin_finetuned
results: []
NL_BERT_michelin_finetuned
This model is a fine-tuned version of GroNLP/bert-base-dutch-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2675
- Accuracy: 0.968
- Recall: 0.1562
- Precision: 0.5
- F1: 0.2381
- Mse: 0.032
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | Mse |
|---|---|---|---|---|---|---|---|---|
| 0.1078 | 1.0 | 125 | 0.2461 | 0.969 | 0.0312 | 1.0 | 0.0606 | 0.031 |
| 0.0258 | 2.0 | 250 | 0.2353 | 0.969 | 0.2188 | 0.5385 | 0.3111 | 0.031 |
| 0.0011 | 3.0 | 375 | 0.2675 | 0.968 | 0.1562 | 0.5 | 0.2381 | 0.032 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1