|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: disfluency-large |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# disfluency-large |
|
|
|
This model is a fine-tuned version of [vinai/phobert-large](https://huggingface.co/vinai/phobert-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0438 |
|
- Precision: 0.9698 |
|
- Recall: 0.9663 |
|
- F1: 0.9681 |
|
- Accuracy: 0.9921 |
|
|
|
## 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: 5e-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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 140 | 0.0422 | 0.9651 | 0.9627 | 0.9639 | 0.9902 | |
|
| No log | 2.0 | 280 | 0.0315 | 0.9718 | 0.9730 | 0.9724 | 0.9923 | |
|
| No log | 3.0 | 420 | 0.2221 | 0.8079 | 0.7530 | 0.7795 | 0.9355 | |
|
| 0.024 | 4.0 | 560 | 0.0379 | 0.9693 | 0.9675 | 0.9684 | 0.9926 | |
|
| 0.024 | 5.0 | 700 | 0.0499 | 0.9657 | 0.9639 | 0.9648 | 0.9905 | |
|
| 0.024 | 6.0 | 840 | 0.0388 | 0.9688 | 0.9688 | 0.9688 | 0.9925 | |
|
| 0.024 | 7.0 | 980 | 0.0438 | 0.9698 | 0.9663 | 0.9681 | 0.9921 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|