metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: phobert-base-v2-finetuned-ner-thesis-dseb
results: []
phobert-base-v2-finetuned-ner-thesis-dseb
This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3842
- Precision: 0.75
- Recall: 0.8329
- F1: 0.7893
- Accuracy: 0.9491
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 2.0671 | 1.0 | 23 | 1.4715 | 0.0 | 0.0 | 0.0 | 0.6125 |
| 1.3776 | 2.0 | 46 | 0.9706 | 0.9471 | 0.3860 | 0.5485 | 0.7545 |
| 0.9833 | 3.0 | 69 | 0.6568 | 0.8144 | 0.7207 | 0.7647 | 0.9034 |
| 0.7423 | 4.0 | 92 | 0.4905 | 0.9215 | 0.9045 | 0.9130 | 0.9595 |
| 0.5928 | 5.0 | 115 | 0.3919 | 0.9626 | 0.9517 | 0.9572 | 0.9893 |
| 0.4955 | 6.0 | 138 | 0.3377 | 0.9658 | 0.9579 | 0.9619 | 0.9913 |
| 0.4013 | 7.0 | 161 | 0.3058 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
| 0.3747 | 8.0 | 184 | 0.2874 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
| 0.3618 | 9.0 | 207 | 0.2781 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
| 0.3477 | 10.0 | 230 | 0.2748 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0