metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ft1500_norm500_aug1
results: []
distilbert-base-uncased-finetuned-ft1500_norm500_aug1
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: 2.9086
- Mse: 3.6357
- Mae: 1.0762
- R2: 0.2894
- Accuracy: 0.5170
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: 4
- eval_batch_size: 4
- 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 | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.5856 | 1.0 | 5847 | 3.3101 | 4.1376 | 1.1447 | 0.1913 | 0.4965 |
| 0.442 | 2.0 | 11694 | 2.7448 | 3.4311 | 1.0934 | 0.3294 | 0.4523 |
| 0.2703 | 3.0 | 17541 | 2.9300 | 3.6625 | 1.0907 | 0.2841 | 0.4933 |
| 0.1699 | 4.0 | 23388 | 2.7979 | 3.4973 | 1.0808 | 0.3164 | 0.4805 |
| 0.1168 | 5.0 | 29235 | 2.9086 | 3.6357 | 1.0762 | 0.2894 | 0.5170 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1