metadata
tags:
- generated_from_trainer
model-index:
- name: calculator_model_test
results: []
calculator_model_test
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8846
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: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7375 | 1.0 | 14 | 2.8446 |
| 2.5309 | 2.0 | 28 | 2.3889 |
| 2.3406 | 3.0 | 42 | 2.3073 |
| 2.2691 | 4.0 | 56 | 2.2098 |
| 2.1412 | 5.0 | 70 | 2.0464 |
| 1.9372 | 6.0 | 84 | 1.7744 |
| 1.6761 | 7.0 | 98 | 1.5399 |
| 1.4725 | 8.0 | 112 | 1.3886 |
| 1.368 | 9.0 | 126 | 1.3246 |
| 1.33 | 10.0 | 140 | 1.3355 |
| 1.3119 | 11.0 | 154 | 1.2886 |
| 1.2836 | 12.0 | 168 | 1.2712 |
| 1.2668 | 13.0 | 182 | 1.2703 |
| 1.2526 | 14.0 | 196 | 1.2477 |
| 1.2292 | 15.0 | 210 | 1.2339 |
| 1.203 | 16.0 | 224 | 1.1997 |
| 1.1686 | 17.0 | 238 | 1.1764 |
| 1.1308 | 18.0 | 252 | 1.1424 |
| 1.0866 | 19.0 | 266 | 1.1034 |
| 1.0355 | 20.0 | 280 | 1.0546 |
| 1.0031 | 21.0 | 294 | 1.0241 |
| 0.9608 | 22.0 | 308 | 0.9925 |
| 0.924 | 23.0 | 322 | 0.9673 |
| 0.9022 | 24.0 | 336 | 0.9555 |
| 0.8733 | 25.0 | 350 | 0.9381 |
| 0.8549 | 26.0 | 364 | 0.9394 |
| 0.8363 | 27.0 | 378 | 0.9274 |
| 0.8129 | 28.0 | 392 | 0.9211 |
| 0.7894 | 29.0 | 406 | 0.9149 |
| 0.7705 | 30.0 | 420 | 0.9042 |
| 0.7509 | 31.0 | 434 | 0.8962 |
| 0.7363 | 32.0 | 448 | 0.9003 |
| 0.7261 | 33.0 | 462 | 0.8935 |
| 0.7135 | 34.0 | 476 | 0.8923 |
| 0.6988 | 35.0 | 490 | 0.8961 |
| 0.6883 | 36.0 | 504 | 0.8883 |
| 0.6768 | 37.0 | 518 | 0.8905 |
| 0.6686 | 38.0 | 532 | 0.8885 |
| 0.6625 | 39.0 | 546 | 0.8865 |
| 0.6566 | 40.0 | 560 | 0.8846 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2