metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ft1500_reg2
results: []
distilbert-base-uncased-finetuned-ft1500_reg2
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: 0.7256
- Mse: 0.7256
- Mae: 0.6674
- R2: 0.4579
- Accuracy: 0.4573
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.0689 | 1.0 | 3000 | 0.7823 | 0.7823 | 0.6948 | 0.4156 | 0.4327 |
| 0.6733 | 2.0 | 6000 | 0.7286 | 0.7286 | 0.6705 | 0.4556 | 0.4447 |
| 0.4735 | 3.0 | 9000 | 0.7125 | 0.7125 | 0.6658 | 0.4677 | 0.46 |
| 0.3358 | 4.0 | 12000 | 0.7256 | 0.7256 | 0.6674 | 0.4579 | 0.4573 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1