metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-base-Whatsapp-ner
results: []
deberta-v3-base-Whatsapp-ner
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0904
- Precision: 0.9322
- Recall: 0.9649
- F1: 0.9483
- Accuracy: 0.9813
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 58 | 0.1103 | 0.9316 | 0.9561 | 0.9437 | 0.9762 |
| No log | 2.0 | 116 | 0.1157 | 0.9474 | 0.9474 | 0.9474 | 0.9796 |
| No log | 3.0 | 174 | 0.1069 | 0.9153 | 0.9474 | 0.9310 | 0.9779 |
| No log | 4.0 | 232 | 0.0904 | 0.9322 | 0.9649 | 0.9483 | 0.9813 |
| No log | 5.0 | 290 | 0.0990 | 0.9322 | 0.9649 | 0.9483 | 0.9796 |
| No log | 6.0 | 348 | 0.0964 | 0.9244 | 0.9649 | 0.9442 | 0.9813 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2