metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ft1500_reg3
results: []
distilbert-base-uncased-finetuned-ft1500_reg3
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: 0.7954
- Mse: 0.7954
- Mae: 0.6900
- R2: 0.4769
- Accuracy: 0.4459
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 |
|---|---|---|---|---|---|---|---|
| 1.018 | 1.0 | 3122 | 0.7491 | 0.7491 | 0.6739 | 0.5073 | 0.4555 |
| 0.668 | 2.0 | 6244 | 0.7397 | 0.7397 | 0.6687 | 0.5135 | 0.4689 |
| 0.4871 | 3.0 | 9366 | 0.7542 | 0.7542 | 0.6730 | 0.5040 | 0.4606 |
| 0.3419 | 4.0 | 12488 | 0.7710 | 0.7710 | 0.6802 | 0.4929 | 0.4536 |
| 0.2532 | 5.0 | 15610 | 0.7954 | 0.7954 | 0.6900 | 0.4769 | 0.4459 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1