|
|
--- |
|
|
library_name: transformers |
|
|
base_model: cabrooks/LOGION-50k_wordpiece |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: gs-Logion |
|
|
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. --> |
|
|
|
|
|
# gs-Logion |
|
|
|
|
|
This model is a fine-tuned version of [cabrooks/LOGION-50k_wordpiece](https://huggingface.co/cabrooks/LOGION-50k_wordpiece) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.5408 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 3.7164 | 1.0 | 1945 | 3.2547 | |
|
|
| 3.1887 | 2.0 | 3890 | 3.0060 | |
|
|
| 2.9816 | 3.0 | 5835 | 2.8557 | |
|
|
| 2.8566 | 4.0 | 7780 | 2.7777 | |
|
|
| 2.7497 | 5.0 | 9725 | 2.7062 | |
|
|
| 2.6705 | 6.0 | 11670 | 2.6446 | |
|
|
| 2.6134 | 7.0 | 13615 | 2.6067 | |
|
|
| 2.5566 | 8.0 | 15560 | 2.5568 | |
|
|
| 2.5294 | 9.0 | 17505 | 2.5612 | |
|
|
| 2.5018 | 10.0 | 19450 | 2.5244 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.7.0+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
