metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model_index:
- name: distilbert-base-uncased-finetuned-clinc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
args: plus
metric:
name: Accuracy
type: accuracy
value: 0.9419354838709677
distilbert-base-uncased-finetuned-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: 0.2929
- Accuracy: 0.9419
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: 96
- eval_batch_size: 96
- 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 | 159 | 1.7692 | 0.6606 |
| No log | 2.0 | 318 | 1.1246 | 0.7997 |
| No log | 3.0 | 477 | 0.7261 | 0.8681 |
| 1.5283 | 4.0 | 636 | 0.5132 | 0.9106 |
| 1.5283 | 5.0 | 795 | 0.4002 | 0.9232 |
| 1.5283 | 6.0 | 954 | 0.3460 | 0.9342 |
| 0.4714 | 7.0 | 1113 | 0.3171 | 0.9384 |
| 0.4714 | 8.0 | 1272 | 0.3028 | 0.9410 |
| 0.4714 | 9.0 | 1431 | 0.2947 | 0.9416 |
| 0.2878 | 10.0 | 1590 | 0.2929 | 0.9419 |
Framework versions
- Transformers 4.10.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3