Token Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("iroli/my_ner_model")
model = AutoModelForTokenClassification.from_pretrained("iroli/my_ner_model", device_map="auto")Quick Links
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: 0.2682
- Precision: 0.6034
- Recall: 0.3244
- F1: 0.4219
- Accuracy: 0.9431
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2769 | 0.6004 | 0.2576 | 0.3606 | 0.9393 |
| No log | 2.0 | 426 | 0.2682 | 0.6034 | 0.3244 | 0.4219 | 0.9431 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for iroli/my_ner_model
Base model
distilbert/distilbert-base-uncasedDataset used to train iroli/my_ner_model
Evaluation results
- Precision on wnut_17test set self-reported0.603
- Recall on wnut_17test set self-reported0.324
- F1 on wnut_17test set self-reported0.422
- Accuracy on wnut_17test set self-reported0.943
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="iroli/my_ner_model")