|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: UNetOscillatoryNeuron |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# UNetOscillatoryNeuron |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0257 |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- num_epochs: 50 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.7184 | 1.0 | 27 | 0.2405 | |
|
|
| 0.1433 | 2.0 | 54 | 0.1415 | |
|
|
| 0.0714 | 3.0 | 81 | 0.0670 | |
|
|
| 0.0523 | 4.0 | 108 | 0.0728 | |
|
|
| 0.0421 | 5.0 | 135 | 0.0372 | |
|
|
| 0.0388 | 6.0 | 162 | 0.0575 | |
|
|
| 0.0336 | 7.0 | 189 | 0.0436 | |
|
|
| 0.0303 | 8.0 | 216 | 0.0395 | |
|
|
| 0.0287 | 9.0 | 243 | 0.0378 | |
|
|
| 0.0264 | 10.0 | 270 | 0.0335 | |
|
|
| 0.0252 | 11.0 | 297 | 0.0367 | |
|
|
| 0.0241 | 12.0 | 324 | 0.0267 | |
|
|
| 0.0247 | 13.0 | 351 | 0.0350 | |
|
|
| 0.0241 | 14.0 | 378 | 0.0296 | |
|
|
| 0.0238 | 15.0 | 405 | 0.0262 | |
|
|
| 0.0217 | 16.0 | 432 | 0.0247 | |
|
|
| 0.0225 | 17.0 | 459 | 0.0287 | |
|
|
| 0.0201 | 18.0 | 486 | 0.0516 | |
|
|
| 0.0193 | 19.0 | 513 | 0.0482 | |
|
|
| 0.0186 | 20.0 | 540 | 0.0254 | |
|
|
| 0.0193 | 21.0 | 567 | 0.0495 | |
|
|
| 0.0179 | 22.0 | 594 | 0.0360 | |
|
|
| 0.0173 | 23.0 | 621 | 0.0282 | |
|
|
| 0.0168 | 24.0 | 648 | 0.0311 | |
|
|
| 0.0162 | 25.0 | 675 | 0.0460 | |
|
|
| 0.0163 | 26.0 | 702 | 0.0351 | |
|
|
| 0.0158 | 27.0 | 729 | 0.0327 | |
|
|
| 0.0153 | 28.0 | 756 | 0.0283 | |
|
|
| 0.015 | 29.0 | 783 | 0.0319 | |
|
|
| 0.0145 | 30.0 | 810 | 0.0343 | |
|
|
| 0.0142 | 31.0 | 837 | 0.0404 | |
|
|
| 0.014 | 32.0 | 864 | 0.0361 | |
|
|
| 0.0139 | 33.0 | 891 | 0.0359 | |
|
|
| 0.0139 | 34.0 | 918 | 0.0307 | |
|
|
| 0.0135 | 35.0 | 945 | 0.0319 | |
|
|
| 0.0131 | 36.0 | 972 | 0.0294 | |
|
|
| 0.0129 | 37.0 | 999 | 0.0282 | |
|
|
| 0.0127 | 38.0 | 1026 | 0.0291 | |
|
|
| 0.0126 | 39.0 | 1053 | 0.0283 | |
|
|
| 0.0124 | 40.0 | 1080 | 0.0296 | |
|
|
| 0.0122 | 41.0 | 1107 | 0.0290 | |
|
|
| 0.0122 | 42.0 | 1134 | 0.0266 | |
|
|
| 0.0121 | 43.0 | 1161 | 0.0288 | |
|
|
| 0.0119 | 44.0 | 1188 | 0.0262 | |
|
|
| 0.0118 | 45.0 | 1215 | 0.0255 | |
|
|
| 0.0118 | 46.0 | 1242 | 0.0253 | |
|
|
| 0.0117 | 47.0 | 1269 | 0.0259 | |
|
|
| 0.0117 | 48.0 | 1296 | 0.0252 | |
|
|
| 0.0117 | 49.0 | 1323 | 0.0259 | |
|
|
| 0.0116 | 50.0 | 1350 | 0.0257 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
