metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-distilled
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.9351612903225807
distilbert-base-uncased-distilled
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: 0.0695
- Accuracy: 0.9352
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.68 | 1.0 | 318 | 0.3985 | 0.6926 |
| 0.3163 | 2.0 | 636 | 0.1939 | 0.8732 |
| 0.1847 | 3.0 | 954 | 0.1241 | 0.9158 |
| 0.1338 | 4.0 | 1272 | 0.0976 | 0.9271 |
| 0.1097 | 5.0 | 1590 | 0.0852 | 0.93 |
| 0.0969 | 6.0 | 1908 | 0.0781 | 0.9342 |
| 0.0891 | 7.0 | 2226 | 0.0739 | 0.9339 |
| 0.0845 | 8.0 | 2544 | 0.0714 | 0.9352 |
| 0.0814 | 9.0 | 2862 | 0.0700 | 0.9361 |
| 0.0801 | 10.0 | 3180 | 0.0695 | 0.9352 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1