metadata
library_name: transformers
base_model: yangwooko/smartmind-cyberone-20250405
tags:
- generated_from_trainer
model-index:
- name: smartmind-cyberone-20250507-0420-revisit
results: []
smartmind-cyberone-20250507-0420-revisit
This model is a fine-tuned version of yangwooko/smartmind-cyberone-20250405 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0135
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 64
- total_train_batch_size: 4096
- optimizer: Use 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 |
|---|---|---|---|
| 0.0153 | 0.3527 | 30 | 0.0180 |
| 0.0161 | 0.7054 | 60 | 0.0312 |
| 0.0207 | 1.0470 | 90 | 0.0364 |
| 0.0285 | 1.3997 | 120 | 0.0227 |
| 0.0211 | 1.7524 | 150 | 0.0218 |
| 0.0161 | 2.0940 | 180 | 0.0202 |
| 0.0174 | 2.4467 | 210 | 0.0197 |
| 0.017 | 2.7994 | 240 | 0.0202 |
| 0.0151 | 3.1411 | 270 | 0.0160 |
| 0.016 | 3.4938 | 300 | 0.0129 |
| 0.0162 | 3.8464 | 330 | 0.0134 |
| 0.0157 | 4.1881 | 360 | 0.0132 |
| 0.0156 | 4.5408 | 390 | 0.0144 |
| 0.015 | 4.8935 | 420 | 0.0135 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Tokenizers 0.21.1