metadata
library_name: transformers
base_model: gates04/FP16-KD-NID
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: NF4-KD-SD-NID
results: []
NF4-KD-SD-NID
This model is a fine-tuned version of gates04/FP16-KD-NID on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0161
- Accuracy: 0.9923
- Precision: 0.9672
- Recall: 0.9496
- F1 score: 0.9554
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: 500
- eval_batch_size: 500
- seed: 42
- 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 | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|---|---|---|
| 0.0234 | 1.0 | 2376 | 0.0221 | 0.9909 | 0.9307 | 0.9111 | 0.9138 |
| 0.0243 | 2.0 | 4752 | 0.0201 | 0.9910 | 0.9751 | 0.9196 | 0.9268 |
| 0.0199 | 3.0 | 7128 | 0.0217 | 0.9909 | 0.9315 | 0.9148 | 0.9175 |
| 0.0181 | 4.0 | 9504 | 0.0189 | 0.9915 | 0.9331 | 0.9202 | 0.9233 |
| 0.0183 | 5.0 | 11880 | 0.0184 | 0.9917 | 0.9374 | 0.9220 | 0.9259 |
| 0.0194 | 6.0 | 14256 | 0.0175 | 0.9918 | 0.9545 | 0.9321 | 0.9368 |
| 0.0129 | 7.0 | 16632 | 0.0169 | 0.9921 | 0.9596 | 0.9353 | 0.9418 |
| 0.016 | 8.0 | 19008 | 0.0168 | 0.9921 | 0.9666 | 0.9539 | 0.9581 |
| 0.0142 | 9.0 | 21384 | 0.0162 | 0.9922 | 0.9673 | 0.9561 | 0.9600 |
| 0.013 | 10.0 | 23760 | 0.0161 | 0.9923 | 0.9672 | 0.9496 | 0.9554 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1