metadata
license: apache-2.0
base_model: MrHungry/lyfi-expert-classification
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: lyfi-expert2-classification
results: []
lyfi-expert2-classification
This model is a fine-tuned version of MrHungry/lyfi-expert-classification on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0368
- Accuracy: 0.9942
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2768 | 0.29 | 500 | 0.1136 | 0.9813 |
| 0.1384 | 0.58 | 1000 | 0.0813 | 0.9866 |
| 0.106 | 0.88 | 1500 | 0.1128 | 0.9831 |
| 0.0776 | 1.17 | 2000 | 0.0657 | 0.9889 |
| 0.055 | 1.46 | 2500 | 0.0528 | 0.9912 |
| 0.041 | 1.75 | 3000 | 0.0542 | 0.9912 |
| 0.045 | 2.04 | 3500 | 0.0641 | 0.9889 |
| 0.0056 | 2.34 | 4000 | 0.0374 | 0.9959 |
| 0.024 | 2.63 | 4500 | 0.0420 | 0.9947 |
| 0.0127 | 2.92 | 5000 | 0.0368 | 0.9942 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0