metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-distilled-finetuned-clinc
results: []
distilbert-base-uncased-distilled-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: 0.0979
- Accuracy: 0.9416
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 | 0.5673 | 0.7035 |
| 0.7446 | 2.0 | 636 | 0.2809 | 0.8865 |
| 0.7446 | 3.0 | 954 | 0.1765 | 0.9255 |
| 0.2754 | 4.0 | 1272 | 0.1369 | 0.9284 |
| 0.158 | 5.0 | 1590 | 0.1183 | 0.9361 |
| 0.158 | 6.0 | 1908 | 0.1091 | 0.9406 |
| 0.1237 | 7.0 | 2226 | 0.1035 | 0.94 |
| 0.1088 | 8.0 | 2544 | 0.1008 | 0.94 |
| 0.1088 | 9.0 | 2862 | 0.0986 | 0.9416 |
| 0.1019 | 10.0 | 3180 | 0.0979 | 0.9416 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0