metadata
base_model: Kielak2/calculator_model_test
tags:
- generated_from_trainer
model-index:
- name: calculator_model_test
results: []
calculator_model_test
This model is a fine-tuned version of Kielak2/calculator_model_test on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1439
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.3404 | 1.0 | 41 | 0.9112 |
1.0195 | 2.0 | 82 | 1.0749 |
0.9524 | 3.0 | 123 | 0.9697 |
0.8765 | 4.0 | 164 | 0.7983 |
0.8274 | 5.0 | 205 | 0.9082 |
0.7727 | 6.0 | 246 | 0.7641 |
1.3801 | 7.0 | 287 | 0.7807 |
0.7733 | 8.0 | 328 | 0.8173 |
0.7062 | 9.0 | 369 | 0.6003 |
0.6671 | 10.0 | 410 | 0.7683 |
0.6935 | 11.0 | 451 | 0.6048 |
0.6598 | 12.0 | 492 | 0.6386 |
0.6553 | 13.0 | 533 | 0.5399 |
0.6033 | 14.0 | 574 | 0.5085 |
0.5972 | 15.0 | 615 | 0.5428 |
0.5928 | 16.0 | 656 | 0.5449 |
0.6432 | 17.0 | 697 | 0.5153 |
0.5887 | 18.0 | 738 | 0.4591 |
0.5011 | 19.0 | 779 | 0.4463 |
0.5117 | 20.0 | 820 | 0.4133 |
0.4846 | 21.0 | 861 | 0.5346 |
0.4815 | 22.0 | 902 | 0.3905 |
0.4375 | 23.0 | 943 | 0.3758 |
0.4313 | 24.0 | 984 | 0.3518 |
0.4049 | 25.0 | 1025 | 0.3904 |
0.4028 | 26.0 | 1066 | 0.2871 |
0.3749 | 27.0 | 1107 | 0.3456 |
0.3682 | 28.0 | 1148 | 0.3105 |
0.3442 | 29.0 | 1189 | 0.2684 |
0.3515 | 30.0 | 1230 | 0.2455 |
0.3199 | 31.0 | 1271 | 0.2793 |
0.3196 | 32.0 | 1312 | 0.2236 |
0.3139 | 33.0 | 1353 | 0.2613 |
0.2875 | 34.0 | 1394 | 0.2020 |
0.2639 | 35.0 | 1435 | 0.1783 |
0.261 | 36.0 | 1476 | 0.1987 |
0.2455 | 37.0 | 1517 | 0.1795 |
0.2355 | 38.0 | 1558 | 0.1632 |
0.228 | 39.0 | 1599 | 0.1480 |
0.2177 | 40.0 | 1640 | 0.1439 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2