|
--- |
|
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: 2.2578 |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 3.1989 | 0.06 | 1000 | 3.0855 | |
|
| 2.9934 | 0.12 | 2000 | 2.9327 | |
|
| 2.8951 | 0.18 | 3000 | 2.8807 | |
|
| 2.8375 | 0.23 | 4000 | 2.8522 | |
|
| 2.8234 | 0.29 | 5000 | 2.8395 | |
|
| 2.8097 | 0.35 | 6000 | 2.8198 | |
|
| 2.804 | 0.41 | 7000 | 2.8119 | |
|
| 2.8038 | 0.47 | 8000 | 2.8194 | |
|
| 2.8005 | 0.53 | 9000 | 2.8135 | |
|
| 2.7875 | 0.59 | 10000 | 2.8138 | |
|
| 2.7649 | 0.64 | 11000 | 2.8101 | |
|
| 2.7662 | 0.7 | 12000 | 2.7934 | |
|
| 2.7563 | 0.76 | 13000 | 2.7802 | |
|
| 2.7366 | 0.82 | 14000 | 2.7552 | |
|
| 2.707 | 0.88 | 15000 | 2.7383 | |
|
| 2.6932 | 0.94 | 16000 | 2.7115 | |
|
| 2.6671 | 1.0 | 17000 | 2.6839 | |
|
| 2.5019 | 1.05 | 18000 | 2.6664 | |
|
| 2.4742 | 1.11 | 19000 | 2.6425 | |
|
| 2.4658 | 1.17 | 20000 | 2.5986 | |
|
| 2.4333 | 1.23 | 21000 | 2.5585 | |
|
| 2.4084 | 1.29 | 22000 | 2.5246 | |
|
| 2.3733 | 1.35 | 23000 | 2.4904 | |
|
| 2.3384 | 1.41 | 24000 | 2.4525 | |
|
| 2.2983 | 1.46 | 25000 | 2.4152 | |
|
| 2.2626 | 1.52 | 26000 | 2.3866 | |
|
| 2.2241 | 1.58 | 27000 | 2.3538 | |
|
| 2.2054 | 1.64 | 28000 | 2.3278 | |
|
| 2.1699 | 1.7 | 29000 | 2.3026 | |
|
| 2.1467 | 1.76 | 30000 | 2.2826 | |
|
| 2.1362 | 1.82 | 31000 | 2.2706 | |
|
| 2.1312 | 1.87 | 32000 | 2.2625 | |
|
| 2.1158 | 1.93 | 33000 | 2.2587 | |
|
| 2.1291 | 1.99 | 34000 | 2.2578 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|