metadata
license: mit
base_model: microsoft/deberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-finetuned-ner-microsoft-disaster-cleaned
results: []
deberta-finetuned-ner-microsoft-disaster-cleaned
This model is a fine-tuned version of microsoft/deberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0791
- Precision: 0.9251
- Recall: 0.9335
- F1: 0.9292
- Accuracy: 0.9808
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: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0908 | 1.0 | 1799 | 0.0765 | 0.9134 | 0.9236 | 0.9185 | 0.9798 |
| 0.0668 | 2.0 | 3598 | 0.0735 | 0.9284 | 0.9305 | 0.9295 | 0.9813 |
| 0.0515 | 3.0 | 5397 | 0.0756 | 0.9231 | 0.9315 | 0.9273 | 0.9804 |
| 0.0394 | 4.0 | 7196 | 0.0791 | 0.9251 | 0.9335 | 0.9292 | 0.9808 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1