metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-distilled-clinc
results: []
distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7144
- Accuracy: 0.9458
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: 48
- eval_batch_size: 48
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.0788 | 1.0 | 318 | 4.2118 | 0.7068 |
| 3.1783 | 2.0 | 636 | 1.9113 | 0.8548 |
| 1.5075 | 3.0 | 954 | 1.0655 | 0.9087 |
| 0.8843 | 4.0 | 1272 | 0.8456 | 0.9332 |
| 0.6849 | 5.0 | 1590 | 0.7832 | 0.9381 |
| 0.606 | 6.0 | 1908 | 0.7561 | 0.9426 |
| 0.5681 | 7.0 | 2226 | 0.7347 | 0.9452 |
| 0.5453 | 8.0 | 2544 | 0.7227 | 0.9439 |
| 0.5339 | 9.0 | 2862 | 0.7156 | 0.9452 |
| 0.527 | 10.0 | 3180 | 0.7144 | 0.9458 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0
- Datasets 3.0.2
- Tokenizers 0.20.1