|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: NEW_OCR_10_8wangchanberta-base-att-spm-uncased |
|
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. --> |
|
|
|
# NEW_OCR_10_8wangchanberta-base-att-spm-uncased |
|
|
|
This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0147 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:------:|:---------------:| |
|
| 0.108 | 1.0 | 10701 | 0.0167 | |
|
| 0.0161 | 2.0 | 21402 | 0.0140 | |
|
| 0.0126 | 3.0 | 32103 | 0.0130 | |
|
| 0.0105 | 4.0 | 42804 | 0.0125 | |
|
| 0.009 | 5.0 | 53505 | 0.0135 | |
|
| 0.008 | 6.0 | 64206 | 0.0137 | |
|
| 0.0074 | 7.0 | 74907 | 0.0139 | |
|
| 0.0064 | 8.0 | 85608 | 0.0143 | |
|
| 0.0058 | 9.0 | 96309 | 0.0147 | |
|
| 0.0054 | 10.0 | 107010 | 0.0147 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.15.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 1.17.0 |
|
- Tokenizers 0.10.3 |
|
|
