|
--- |
|
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 |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9180645161290323 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# distilbert-base-uncased-finetuned-clinc |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7719 |
|
- Accuracy: 0.9181 |
|
|
|
## Model description |
|
|
|
This is an initial example of knowledge-distillation where the student loss is all cross-entropy loss \\(L_{CE}\\) of the ground-truth labels and none of the distillation loss \\(L_{KD}\\). |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
The training and evaluation data come straight from the `train` and `validation` splits in the clinc_oos dataset, respectively; and tokenized using the `distilbert-base-uncased` tokenization. |
|
|
|
## Training procedure |
|
|
|
Please see page 224 in Chapter 8: Making Transformers Efficient in Production, Natural Language Processing with Transformers, May 2022. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- alpha: 1.0 |
|
- temperature: 2.0 |
|
- 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 318 | 3.2882 | 0.7426 | |
|
| 3.7861 | 2.0 | 636 | 1.8744 | 0.8381 | |
|
| 3.7861 | 3.0 | 954 | 1.1567 | 0.8958 | |
|
| 1.6922 | 4.0 | 1272 | 0.8569 | 0.9132 | |
|
| 0.9055 | 5.0 | 1590 | 0.7719 | 0.9181 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 1.16.1 |
|
- Tokenizers 0.15.1 |
|
|
