metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased-distilled-clinc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: clinc_oos
type: clinc_oos
args: plus
metrics:
- type: accuracy
value: 0.9467741935483871
name: Accuracy
distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of distilbert-base-uncased on the clinc_oos dataset. It achieves the following results on the evaluation set:
- Loss: 0.2525
- Accuracy: 0.9468
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.2246 | 1.0 | 318 | 3.1584 | 0.7545 |
| 2.4033 | 2.0 | 636 | 1.5656 | 0.8652 |
| 1.1684 | 3.0 | 954 | 0.7795 | 0.9161 |
| 0.5693 | 4.0 | 1272 | 0.4653 | 0.9329 |
| 0.3042 | 5.0 | 1590 | 0.3412 | 0.9406 |
| 0.1794 | 6.0 | 1908 | 0.2912 | 0.9403 |
| 0.1184 | 7.0 | 2226 | 0.2654 | 0.9461 |
| 0.0873 | 8.0 | 2544 | 0.2557 | 0.9439 |
| 0.0719 | 9.0 | 2862 | 0.2549 | 0.9465 |
| 0.0646 | 10.0 | 3180 | 0.2525 | 0.9468 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.0.0
- Tokenizers 0.12.1