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: 0.1417
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9571 | 1.0 | 6 | 2.2956 |
| 2.0465 | 2.0 | 12 | 1.7293 |
| 1.5363 | 3.0 | 18 | 1.2901 |
| 1.2139 | 4.0 | 24 | 1.0866 |
| 1.0369 | 5.0 | 30 | 0.9429 |
| 0.9144 | 6.0 | 36 | 0.8284 |
| 0.8202 | 7.0 | 42 | 0.7701 |
| 0.7591 | 8.0 | 48 | 0.7184 |
| 0.7075 | 9.0 | 54 | 0.6474 |
| 0.6481 | 10.0 | 60 | 0.6074 |
| 0.611 | 11.0 | 66 | 0.5786 |
| 0.5714 | 12.0 | 72 | 0.5192 |
| 0.5412 | 13.0 | 78 | 0.4924 |
| 0.5092 | 14.0 | 84 | 0.5077 |
| 0.5118 | 15.0 | 90 | 0.4989 |
| 0.4982 | 16.0 | 96 | 0.4349 |
| 0.4512 | 17.0 | 102 | 0.4090 |
| 0.4176 | 18.0 | 108 | 0.3868 |
| 0.395 | 19.0 | 114 | 0.3586 |
| 0.3754 | 20.0 | 120 | 0.3666 |
| 0.3561 | 21.0 | 126 | 0.3182 |
| 0.3284 | 22.0 | 132 | 0.2906 |
| 0.3123 | 23.0 | 138 | 0.2981 |
| 0.3026 | 24.0 | 144 | 0.2740 |
| 0.2809 | 25.0 | 150 | 0.2448 |
| 0.2669 | 26.0 | 156 | 0.2321 |
| 0.257 | 27.0 | 162 | 0.2179 |
| 0.2349 | 28.0 | 168 | 0.2110 |
| 0.2205 | 29.0 | 174 | 0.1969 |
| 0.2142 | 30.0 | 180 | 0.1894 |
| 0.2116 | 31.0 | 186 | 0.1819 |
| 0.195 | 32.0 | 192 | 0.1747 |
| 0.1884 | 33.0 | 198 | 0.1668 |
| 0.1819 | 34.0 | 204 | 0.1615 |
| 0.1741 | 35.0 | 210 | 0.1541 |
| 0.172 | 36.0 | 216 | 0.1524 |
| 0.1726 | 37.0 | 222 | 0.1471 |
| 0.1555 | 38.0 | 228 | 0.1458 |
| 0.1606 | 39.0 | 234 | 0.1430 |
| 0.1604 | 40.0 | 240 | 0.1417 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2