metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-expense-ner
results: []
distilbert-expense-ner
This model is a fine-tuned version of Geotrend/distilbert-base-en-fr-de-no-da-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1641
- Precision: 0.9489
- Recall: 0.9430
- F1: 0.9459
- Accuracy: 0.9721
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 112 | 0.1750 | 0.8720 | 0.8891 | 0.8805 | 0.9446 |
| No log | 2.0 | 224 | 0.1339 | 0.8804 | 0.9078 | 0.8939 | 0.9515 |
| No log | 3.0 | 336 | 0.1157 | 0.9315 | 0.9295 | 0.9305 | 0.9666 |
| No log | 4.0 | 448 | 0.1291 | 0.9269 | 0.9326 | 0.9298 | 0.9666 |
| 0.2164 | 5.0 | 560 | 0.1400 | 0.9247 | 0.9285 | 0.9266 | 0.9666 |
| 0.2164 | 6.0 | 672 | 0.1463 | 0.9376 | 0.9347 | 0.9362 | 0.9689 |
| 0.2164 | 7.0 | 784 | 0.1463 | 0.9327 | 0.9337 | 0.9332 | 0.9694 |
| 0.2164 | 8.0 | 896 | 0.1711 | 0.9376 | 0.9337 | 0.9356 | 0.9661 |
| 0.0274 | 9.0 | 1008 | 0.1621 | 0.9421 | 0.9440 | 0.9431 | 0.9735 |
| 0.0274 | 10.0 | 1120 | 0.1641 | 0.9489 | 0.9430 | 0.9459 | 0.9721 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1