metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: cetusian/ner-model-furniture-v2
results: []
metrics:
- accuracy
- f1
- precision
- recall
datasets:
- cetusian/ner-furniture-names
cetusian/ner-model-furniture-v2
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3257
- Validation Loss: 0.3764
- Train Precision: 0.7369
- Train Recall: 0.7941
- Train F1: 0.7644
- Train Accuracy: 0.8553
- Epoch: 4
Model description
The model was fine-tuned in order to recognize product names. Ner tags: O, B-product, I-product.
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 348, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 0.6457 | 0.4855 | 0.6915 | 0.7054 | 0.6984 | 0.8105 | 0 |
| 0.4327 | 0.3963 | 0.7202 | 0.7764 | 0.7472 | 0.8445 | 1 |
| 0.3506 | 0.3764 | 0.7369 | 0.7941 | 0.7644 | 0.8553 | 2 |
| 0.3260 | 0.3764 | 0.7369 | 0.7941 | 0.7644 | 0.8553 | 3 |
| 0.3257 | 0.3764 | 0.7369 | 0.7941 | 0.7644 | 0.8553 | 4 |
Framework versions
- Transformers 4.41.1
- TensorFlow 2.15.0
- Datasets 2.19.2
- Tokenizers 0.19.1