metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: distillbert-bert-clinc-bert-optuna
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.9403225806451613
distillbert-bert-clinc-bert-optuna
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: 0.0999
- Accuracy: 0.9403
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 |
---|---|---|---|---|
No log | 1.0 | 318 | 0.5777 | 0.7348 |
0.7588 | 2.0 | 636 | 0.2863 | 0.8848 |
0.7588 | 3.0 | 954 | 0.1794 | 0.9216 |
0.2787 | 4.0 | 1272 | 0.1386 | 0.93 |
0.1598 | 5.0 | 1590 | 0.1208 | 0.9355 |
0.1598 | 6.0 | 1908 | 0.1111 | 0.9403 |
0.1245 | 7.0 | 2226 | 0.1057 | 0.9397 |
0.1096 | 8.0 | 2544 | 0.1023 | 0.9410 |
0.1096 | 9.0 | 2862 | 0.1005 | 0.9410 |
0.1034 | 10.0 | 3180 | 0.0999 | 0.9403 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2