|
--- |
|
library_name: transformers |
|
license: other |
|
base_model: aubmindlab/aragpt2-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: DrAI-chatbot |
|
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. --> |
|
|
|
# DrAI-chatbot |
|
|
|
This model is a fine-tuned version of [aubmindlab/aragpt2-large](https://huggingface.co/aubmindlab/aragpt2-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.2181 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 32 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 107.5815 | 1.0 | 135 | 3.1959 | |
|
| 92.4065 | 2.0 | 270 | 3.1177 | |
|
| 82.5107 | 3.0 | 405 | 3.1419 | |
|
| 69.6446 | 4.0 | 540 | 3.2807 | |
|
| 61.3893 | 5.0 | 675 | 3.4748 | |
|
| 51.678 | 6.0 | 810 | 3.6348 | |
|
| 45.5323 | 7.0 | 945 | 3.8739 | |
|
| 38.5833 | 8.0 | 1080 | 4.0467 | |
|
| 35.6599 | 9.0 | 1215 | 4.1354 | |
|
| 31.9573 | 9.9264 | 1340 | 4.2181 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
