metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RISE_NER4
results: []
RISE_NER4
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1028
- Precision: 0.8937
- Recall: 0.9059
- F1: 0.8997
- Accuracy: 0.9834
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.012 | 1.0 | 16410 | 0.0639 | 0.8898 | 0.8978 | 0.8938 | 0.9827 |
| 0.0074 | 2.0 | 32820 | 0.0788 | 0.9006 | 0.8950 | 0.8978 | 0.9831 |
| 0.003 | 3.0 | 49230 | 0.0930 | 0.8938 | 0.9012 | 0.8975 | 0.9831 |
| 0.0014 | 4.0 | 65640 | 0.1028 | 0.8937 | 0.9059 | 0.8997 | 0.9834 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0