metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilbert-training-2
results: []
distilbert-training-2
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: 0.0164
- Accuracy: 0.9976
- Precision: 0.9982
- Recall: 0.9929
- F1: 0.9956
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.5 | 302 | 0.0849 | 0.9836 | 1.0 | 0.9398 | 0.9690 |
| No log | 1.0 | 604 | 0.0525 | 0.9894 | 0.9755 | 0.9858 | 0.9806 |
| 0.0957 | 1.5 | 906 | 0.0184 | 0.9971 | 0.9982 | 0.9912 | 0.9947 |
| 0.0957 | 2.0 | 1208 | 0.0438 | 0.9923 | 0.9982 | 0.9735 | 0.9857 |
| 0.0265 | 2.5 | 1510 | 0.0246 | 0.9966 | 0.9982 | 0.9894 | 0.9938 |
| 0.0265 | 3.0 | 1812 | 0.0170 | 0.9971 | 0.9982 | 0.9912 | 0.9947 |
| 0.0116 | 3.49 | 2114 | 0.0184 | 0.9971 | 1.0 | 0.9894 | 0.9947 |
| 0.0116 | 3.99 | 2416 | 0.0259 | 0.9961 | 1.0 | 0.9858 | 0.9929 |
| 0.0064 | 4.49 | 2718 | 0.0156 | 0.9976 | 0.9982 | 0.9929 | 0.9956 |
| 0.0064 | 4.99 | 3020 | 0.0164 | 0.9976 | 0.9982 | 0.9929 | 0.9956 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.2.0.dev20230913+cu121
- Tokenizers 0.13.3