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: 0.0162
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 |
|---|---|---|---|
| 2.7671 | 1.0 | 6 | 2.1243 |
| 1.8409 | 2.0 | 12 | 1.5234 |
| 1.3096 | 3.0 | 18 | 1.0612 |
| 0.9557 | 4.0 | 24 | 0.8622 |
| 0.8499 | 5.0 | 30 | 0.7836 |
| 0.7285 | 6.0 | 36 | 0.6873 |
| 0.6464 | 7.0 | 42 | 0.5698 |
| 0.5513 | 8.0 | 48 | 0.5230 |
| 0.4906 | 9.0 | 54 | 0.4933 |
| 0.4817 | 10.0 | 60 | 0.4228 |
| 0.388 | 11.0 | 66 | 0.3776 |
| 0.3697 | 12.0 | 72 | 0.3796 |
| 0.3994 | 13.0 | 78 | 0.3245 |
| 0.3127 | 14.0 | 84 | 0.3145 |
| 0.3215 | 15.0 | 90 | 0.2752 |
| 0.2758 | 16.0 | 96 | 0.2400 |
| 0.2507 | 17.0 | 102 | 0.2158 |
| 0.217 | 18.0 | 108 | 0.2150 |
| 0.2223 | 19.0 | 114 | 0.1940 |
| 0.1746 | 20.0 | 120 | 0.1826 |
| 0.1625 | 21.0 | 126 | 0.1445 |
| 0.1386 | 22.0 | 132 | 0.1421 |
| 0.1432 | 23.0 | 138 | 0.1241 |
| 0.1329 | 24.0 | 144 | 0.1104 |
| 0.1413 | 25.0 | 150 | 0.0889 |
| 0.1093 | 26.0 | 156 | 0.0765 |
| 0.0869 | 27.0 | 162 | 0.0596 |
| 0.0677 | 28.0 | 168 | 0.0495 |
| 0.0646 | 29.0 | 174 | 0.0397 |
| 0.0539 | 30.0 | 180 | 0.0359 |
| 0.0502 | 31.0 | 186 | 0.0339 |
| 0.0399 | 32.0 | 192 | 0.0285 |
| 0.0453 | 33.0 | 198 | 0.0239 |
| 0.0351 | 34.0 | 204 | 0.0223 |
| 0.039 | 35.0 | 210 | 0.0199 |
| 0.0255 | 36.0 | 216 | 0.0195 |
| 0.0259 | 37.0 | 222 | 0.0177 |
| 0.0241 | 38.0 | 228 | 0.0168 |
| 0.0251 | 39.0 | 234 | 0.0163 |
| 0.0239 | 40.0 | 240 | 0.0162 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2