|
--- |
|
base_model: NghiemAbe/gpt-neo-vi-small-v5 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt-neo-vi-small-v6 |
|
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. --> |
|
|
|
# gpt-neo-vi-small-v6 |
|
|
|
This model is a fine-tuned version of [NlpHUST/gpt-neo-vi-small](https://huggingface.co/NlpHUST/gpt-neo-vi-small) on an [ViQuad](https://huggingface.co/datasets/NghiemAbe/viquad) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4156 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 64 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.3849 | 0.1 | 25 | 0.5802 | |
|
| 0.3747 | 0.19 | 50 | 0.5680 | |
|
| 0.3843 | 0.29 | 75 | 0.5695 | |
|
| 0.4016 | 0.39 | 100 | 0.5782 | |
|
| 0.4101 | 0.49 | 125 | 0.5563 | |
|
| 0.4011 | 0.58 | 150 | 0.5162 | |
|
| 0.3729 | 0.68 | 175 | 0.4888 | |
|
| 0.3512 | 0.78 | 200 | 0.4544 | |
|
| 0.316 | 0.88 | 225 | 0.4319 | |
|
| 0.3126 | 0.97 | 250 | 0.4156 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
