|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: DS-Chatbox-gpt2-vietnamese-V3 |
|
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. --> |
|
|
|
# DS-Chatbox-gpt2-vietnamese-V3 |
|
|
|
This model is a fine-tuned version of [NlpHUST/gpt2-vietnamese](https://huggingface.co/NlpHUST/gpt2-vietnamese) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7322 |
|
|
|
## 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: 0.0015 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.2 |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 2.9759 | 0.66 | 1400 | 2.6781 | |
|
| 2.5019 | 1.31 | 2800 | 2.4921 | |
|
| 2.3352 | 1.97 | 4200 | 2.3726 | |
|
| 2.0759 | 2.62 | 5600 | 2.3240 | |
|
| 1.9303 | 3.28 | 7000 | 2.3279 | |
|
| 1.7867 | 3.93 | 8400 | 2.2556 | |
|
| 1.5133 | 4.59 | 9800 | 2.3424 | |
|
| 1.3726 | 5.25 | 11200 | 2.5290 | |
|
| 1.1925 | 5.9 | 12600 | 2.5132 | |
|
| 1.0211 | 6.56 | 14000 | 2.7322 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
