metadata
library_name: peft
tags:
- generated_from_trainer
base_model: VietAI/gpt-neo-1.3B-vietnamese-news
model-index:
- name: gpt-neo-1.3B-vietnamese-news_model_kaggle_test
results: []
gpt-neo-1.3B-vietnamese-news_model_kaggle_test
This model is a fine-tuned version of VietAI/gpt-neo-1.3B-vietnamese-news on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1194
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: 4e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 15 | 4.1718 |
| No log | 2.0 | 30 | 3.6789 |
| No log | 3.0 | 45 | 3.2484 |
| No log | 4.0 | 60 | 2.8954 |
| No log | 5.0 | 75 | 2.6081 |
| No log | 6.0 | 90 | 2.3656 |
| No log | 7.0 | 105 | 2.1602 |
| No log | 8.0 | 120 | 1.9739 |
| No log | 9.0 | 135 | 1.8137 |
| No log | 10.0 | 150 | 1.6778 |
| No log | 11.0 | 165 | 1.5595 |
| No log | 12.0 | 180 | 1.4598 |
| No log | 13.0 | 195 | 1.3742 |
| No log | 14.0 | 210 | 1.3033 |
| No log | 15.0 | 225 | 1.2446 |
| No log | 16.0 | 240 | 1.1988 |
| No log | 17.0 | 255 | 1.1638 |
| No log | 18.0 | 270 | 1.1392 |
| No log | 19.0 | 285 | 1.1243 |
| No log | 20.0 | 300 | 1.1194 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2