metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: patchtst-tsmixup
results: []
patchtst-tsmixup
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1559
- Mse: 274.9792
- Mae: 0.6475
- Rmse: 16.5825
- Smape: 90.3816
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 512
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | Rmse | Smape |
|---|---|---|---|---|---|---|---|
| 0.1858 | 0.0952 | 1000 | 0.1782 | 518.9319 | 0.7698 | 22.7801 | 100.2200 |
| 0.1749 | 0.1904 | 2000 | 0.1696 | 427.1324 | 0.7240 | 20.6672 | 428.4419 |
| 0.1741 | 0.2857 | 3000 | 0.1660 | 502.4791 | 0.7060 | 22.4160 | 93.6057 |
| 0.1705 | 0.3809 | 4000 | 0.1647 | 423.8481 | 0.6876 | 20.5876 | 92.3590 |
| 0.1657 | 0.4761 | 5000 | 0.1636 | 366.2942 | 0.6758 | 19.1388 | 86.3451 |
| 0.1672 | 0.5713 | 6000 | 0.1611 | 365.8203 | 0.6785 | 19.1264 | 126.2944 |
| 0.1621 | 0.6666 | 7000 | 0.1610 | 336.1272 | 0.6763 | 18.3338 | 118.4768 |
| 0.1641 | 0.7618 | 8000 | 0.1598 | 392.5134 | 0.6727 | 19.8120 | 102.6643 |
| 0.1607 | 0.8570 | 9000 | 0.1594 | 292.0475 | 0.6590 | 17.0894 | 114.6111 |
| 0.1615 | 0.9522 | 10000 | 0.1584 | 298.7156 | 0.6652 | 17.2834 | 79.4739 |
| 0.1585 | 1.0474 | 11000 | 0.1583 | 273.0431 | 0.6594 | 16.5240 | 92.2265 |
| 0.16 | 1.1426 | 12000 | 0.1574 | 288.4399 | 0.6531 | 16.9835 | 94.1800 |
| 0.1582 | 1.2379 | 13000 | 0.1581 | 252.3872 | 0.6558 | 15.8867 | 177.7797 |
| 0.1563 | 1.3331 | 14000 | 0.1572 | 283.0400 | 0.6637 | 16.8238 | 76.9167 |
| 0.1583 | 1.4283 | 15000 | 0.1567 | 315.5172 | 0.6533 | 17.7628 | 137.8005 |
| 0.1591 | 1.5235 | 16000 | 0.1573 | 324.9469 | 0.6659 | 18.0263 | 73.2071 |
| 0.1574 | 1.6188 | 17000 | 0.1562 | 369.6110 | 0.6552 | 19.2253 | 77.7899 |
| 0.1592 | 1.7140 | 18000 | 0.1554 | 318.4736 | 0.6430 | 17.8458 | 81.0331 |
| 0.1554 | 1.8092 | 19000 | 0.1560 | 277.4202 | 0.6529 | 16.6559 | 83.8692 |
| 0.1588 | 1.9044 | 20000 | 0.1562 | 287.6734 | 0.6511 | 16.9609 | 73.7841 |
| 0.1543 | 1.9997 | 21000 | 0.1559 | 274.9792 | 0.6475 | 16.5825 | 90.3816 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.1+cu126
- Datasets 2.17.1
- Tokenizers 0.21.1