|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: smartmind-cyberone-20250420 |
|
|
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. --> |
|
|
|
|
|
# smartmind-cyberone-20250420 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0035 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 64 |
|
|
- 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: cosine_with_restarts |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.0007 | 0.3504 | 30 | 0.0003 | |
|
|
| 0.0 | 0.7007 | 60 | 0.0037 | |
|
|
| 0.0004 | 1.0584 | 90 | 0.0084 | |
|
|
| 0.0004 | 1.4088 | 120 | 0.0039 | |
|
|
| 0.0 | 1.7591 | 150 | 0.0018 | |
|
|
| 0.0025 | 2.1168 | 180 | 0.0017 | |
|
|
| 0.0 | 2.4672 | 210 | 0.0025 | |
|
|
| 0.0 | 2.8175 | 240 | 0.0024 | |
|
|
| 0.0001 | 3.1752 | 270 | 0.0015 | |
|
|
| 0.0 | 3.5255 | 300 | 0.0023 | |
|
|
| 0.0 | 3.8759 | 330 | 0.0035 | |
|
|
| 0.0 | 4.2336 | 360 | 0.0035 | |
|
|
| 0.0 | 4.5839 | 390 | 0.0035 | |
|
|
| 0.0 | 4.9343 | 420 | 0.0035 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
