<!-- 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_AlBERT_aug_MSEloss
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2216
- Mse: 0.2216
- Mae: 0.3302
- R2: 0.5082
- Accuracy: 0.7533
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 | 0.2554 | 0.2554 | 0.3841 | 0.4041 | 0.6867 |
0.2379 | 2.0 | 526 | 0.1471 | 0.1471 | 0.2426 | 0.6568 | 0.86 |
0.2379 | 3.0 | 789 | 0.1189 | 0.1189 | 0.2212 | 0.7226 | 0.8633 |
0.0845 | 4.0 | 1052 | 0.1052 | 0.1052 | 0.2121 | 0.7546 | 0.8767 |
0.0845 | 5.0 | 1315 | 0.0913 | 0.0913 | 0.1642 | 0.7869 | 0.9067 |
0.0441 | 6.0 | 1578 | 0.0610 | 0.0610 | 0.1272 | 0.8577 | 0.9467 |
0.0441 | 7.0 | 1841 | 0.0594 | 0.0594 | 0.0965 | 0.8614 | 0.9433 |
0.0269 | 8.0 | 2104 | 0.0750 | 0.0750 | 0.1312 | 0.8249 | 0.93 |
0.0269 | 9.0 | 2367 | 0.0544 | 0.0544 | 0.0998 | 0.8731 | 0.95 |
0.0218 | 10.0 | 2630 | 0.0680 | 0.0680 | 0.1031 | 0.8413 | 0.93 |
0.0218 | 11.0 | 2893 | 0.0486 | 0.0486 | 0.1015 | 0.8867 | 0.9533 |
0.0141 | 12.0 | 3156 | 0.0582 | 0.0582 | 0.1056 | 0.8643 | 0.95 |
0.0141 | 13.0 | 3419 | 0.0494 | 0.0494 | 0.0832 | 0.8847 | 0.9533 |
0.0112 | 14.0 | 3682 | 0.0561 | 0.0561 | 0.0927 | 0.8690 | 0.9467 |
0.0112 | 15.0 | 3945 | 0.0576 | 0.0576 | 0.0833 | 0.8656 | 0.9467 |
0.0064 | 16.0 | 4208 | 0.0639 | 0.0639 | 0.0972 | 0.8509 | 0.9467 |
0.0064 | 17.0 | 4471 | 0.0657 | 0.0657 | 0.0971 | 0.8467 | 0.9367 |
0.0052 | 18.0 | 4734 | 0.0718 | 0.0718 | 0.0912 | 0.8325 | 0.94 |
0.0052 | 19.0 | 4997 | 0.0689 | 0.0689 | 0.0883 | 0.8392 | 0.94 |
0.0031 | 20.0 | 5260 | 0.0601 | 0.0601 | 0.0816 | 0.8598 | 0.9433 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3