metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-clinc
results: []
distilbert-base-uncased-finetuned-clinc
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7761
- Accuracy: 0.9174
Model description
This is an initial example of knowledge-distillation where the student loss is all cross-entropy loss of the ground-truth labels and none of the knowledge-distillation loss .
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:
- num_epochs: 5
- alpha: 1.0
- temperature: 2.0
- learning_rate: 2e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 8675309
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 318 | 3.2998 | 0.7132 |
| 3.7996 | 2.0 | 636 | 1.8739 | 0.8390 |
| 3.7996 | 3.0 | 954 | 1.1564 | 0.8903 |
| 1.689 | 4.0 | 1272 | 0.8571 | 0.9126 |
| 0.9017 | 5.0 | 1590 | 0.7761 | 0.9174 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1