metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased-finetuned-ft750_reg5
results: []
distilbert-base-uncased-finetuned-ft750_reg5
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: 0.6298
- Mse: 0.6298
- Mae: 0.6087
- R2: 0.4072
- Accuracy: 0.4973
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.8617 | 1.0 | 188 | 0.7482 | 0.7482 | 0.6639 | 0.2957 | 0.4707 |
| 0.5667 | 2.0 | 376 | 0.6017 | 0.6017 | 0.5978 | 0.4336 | 0.5127 |
| 0.5038 | 3.0 | 564 | 0.6298 | 0.6298 | 0.6087 | 0.4072 | 0.4973 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1