metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
my_awesome_model
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7944
- Accuracy: 0.8683
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 84 | 0.3652 | 0.8593 |
| No log | 2.0 | 168 | 0.3665 | 0.8593 |
| No log | 3.0 | 252 | 0.3688 | 0.8533 |
| No log | 4.0 | 336 | 0.3782 | 0.8473 |
| No log | 5.0 | 420 | 0.3860 | 0.8503 |
| 0.1818 | 6.0 | 504 | 0.4037 | 0.8503 |
| 0.1818 | 7.0 | 588 | 0.4540 | 0.8503 |
| 0.1818 | 8.0 | 672 | 0.4915 | 0.8563 |
| 0.1818 | 9.0 | 756 | 0.5585 | 0.8353 |
| 0.1818 | 10.0 | 840 | 0.6261 | 0.8503 |
| 0.1818 | 11.0 | 924 | 0.6174 | 0.8623 |
| 0.075 | 12.0 | 1008 | 0.6421 | 0.8653 |
| 0.075 | 13.0 | 1092 | 0.7308 | 0.8563 |
| 0.075 | 14.0 | 1176 | 0.7812 | 0.8473 |
| 0.075 | 15.0 | 1260 | 0.7944 | 0.8683 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3