metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: my_ner_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5482388973966309
- name: Recall
type: recall
value: 0.33178869323447635
- name: F1
type: f1
value: 0.41339491916859117
- name: Accuracy
type: accuracy
value: 0.943952802359882
my_ner_model
This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2725
- Precision: 0.5482
- Recall: 0.3318
- F1: 0.4134
- Accuracy: 0.9440
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: 16
- eval_batch_size: 16
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2869 | 0.4186 | 0.1835 | 0.2552 | 0.9356 |
No log | 2.0 | 426 | 0.2692 | 0.5294 | 0.3086 | 0.3899 | 0.9428 |
0.1994 | 3.0 | 639 | 0.2725 | 0.5482 | 0.3318 | 0.4134 | 0.9440 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1