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: 0.3223
- Accuracy: 0.9461
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 |
|---|---|---|---|---|
| 2.8424 | 1.0 | 318 | 2.0795 | 0.7271 |
| 1.6103 | 2.0 | 636 | 1.0650 | 0.8577 |
| 0.8466 | 3.0 | 954 | 0.6074 | 0.9135 |
| 0.4999 | 4.0 | 1272 | 0.4376 | 0.9310 |
| 0.3539 | 5.0 | 1590 | 0.3770 | 0.9397 |
| 0.2899 | 6.0 | 1908 | 0.3515 | 0.9419 |
| 0.2589 | 7.0 | 2226 | 0.3353 | 0.9448 |
| 0.2418 | 8.0 | 2544 | 0.3276 | 0.9458 |
| 0.2319 | 9.0 | 2862 | 0.3234 | 0.9458 |
| 0.2284 | 10.0 | 3180 | 0.3223 | 0.9461 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0