<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Regression_BERT_aug_MSEloss
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: 0.1118
- Mse: 0.1118
- Mae: 0.2369
- R2: 0.7519
- Accuracy: 0.8733
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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 263 | 0.1491 | 0.1491 | 0.2707 | 0.6520 | 0.8367 |
0.1428 | 2.0 | 526 | 0.0948 | 0.0948 | 0.1805 | 0.7788 | 0.9033 |
0.1428 | 3.0 | 789 | 0.0596 | 0.0596 | 0.1209 | 0.8610 | 0.9533 |
0.0215 | 4.0 | 1052 | 0.0534 | 0.0534 | 0.1034 | 0.8755 | 0.9533 |
0.0215 | 5.0 | 1315 | 0.0464 | 0.0464 | 0.0882 | 0.8917 | 0.9567 |
0.0111 | 6.0 | 1578 | 0.0420 | 0.0420 | 0.0852 | 0.9019 | 0.9633 |
0.0111 | 7.0 | 1841 | 0.0419 | 0.0419 | 0.0744 | 0.9022 | 0.9633 |
0.0051 | 8.0 | 2104 | 0.0424 | 0.0424 | 0.0736 | 0.9010 | 0.96 |
0.0051 | 9.0 | 2367 | 0.0457 | 0.0457 | 0.0737 | 0.8935 | 0.9533 |
0.0034 | 10.0 | 2630 | 0.0396 | 0.0396 | 0.0692 | 0.9076 | 0.96 |
0.0034 | 11.0 | 2893 | 0.0419 | 0.0419 | 0.0740 | 0.9023 | 0.9633 |
0.0027 | 12.0 | 3156 | 0.0370 | 0.0370 | 0.0684 | 0.9136 | 0.9667 |
0.0027 | 13.0 | 3419 | 0.0389 | 0.0389 | 0.0688 | 0.9092 | 0.9633 |
0.0023 | 14.0 | 3682 | 0.0392 | 0.0392 | 0.0654 | 0.9085 | 0.9633 |
0.0023 | 15.0 | 3945 | 0.0382 | 0.0382 | 0.0663 | 0.9108 | 0.9633 |
0.0018 | 16.0 | 4208 | 0.0403 | 0.0403 | 0.0655 | 0.9059 | 0.96 |
0.0018 | 17.0 | 4471 | 0.0391 | 0.0391 | 0.0675 | 0.9087 | 0.96 |
0.0016 | 18.0 | 4734 | 0.0386 | 0.0386 | 0.0618 | 0.9099 | 0.9633 |
0.0016 | 19.0 | 4997 | 0.0389 | 0.0389 | 0.0640 | 0.9093 | 0.9633 |
0.0013 | 20.0 | 5260 | 0.0384 | 0.0384 | 0.0623 | 0.9104 | 0.9633 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3