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: 0.6779
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 |
|---|---|---|---|
| 3.4465 | 1.0 | 6 | 2.8008 |
| 2.4324 | 2.0 | 12 | 2.0258 |
| 1.8717 | 3.0 | 18 | 1.7217 |
| 1.6802 | 4.0 | 24 | 1.6377 |
| 1.5784 | 5.0 | 30 | 1.5571 |
| 1.5182 | 6.0 | 36 | 1.5249 |
| 1.4891 | 7.0 | 42 | 1.5271 |
| 1.491 | 8.0 | 48 | 1.5028 |
| 1.4957 | 9.0 | 54 | 1.4941 |
| 1.4419 | 10.0 | 60 | 1.4593 |
| 1.4233 | 11.0 | 66 | 1.4681 |
| 1.4452 | 12.0 | 72 | 1.3954 |
| 1.3414 | 13.0 | 78 | 1.3100 |
| 1.2882 | 14.0 | 84 | 1.2658 |
| 1.2233 | 15.0 | 90 | 1.1740 |
| 1.1812 | 16.0 | 96 | 1.1963 |
| 1.1567 | 17.0 | 102 | 1.3220 |
| 1.1566 | 18.0 | 108 | 1.1536 |
| 1.0904 | 19.0 | 114 | 1.1253 |
| 1.0811 | 20.0 | 120 | 1.0386 |
| 1.0245 | 21.0 | 126 | 1.0415 |
| 1.0028 | 22.0 | 132 | 0.9741 |
| 0.9561 | 23.0 | 138 | 0.9236 |
| 0.9204 | 24.0 | 144 | 0.9070 |
| 0.9064 | 25.0 | 150 | 0.8667 |
| 0.8868 | 26.0 | 156 | 0.8357 |
| 0.8513 | 27.0 | 162 | 0.8124 |
| 0.8199 | 28.0 | 168 | 0.8041 |
| 0.7951 | 29.0 | 174 | 0.7810 |
| 0.8079 | 30.0 | 180 | 0.7692 |
| 0.7769 | 31.0 | 186 | 0.7839 |
| 0.782 | 32.0 | 192 | 0.7484 |
| 0.7378 | 33.0 | 198 | 0.7386 |
| 0.7591 | 34.0 | 204 | 0.7165 |
| 0.7269 | 35.0 | 210 | 0.7015 |
| 0.7163 | 36.0 | 216 | 0.7006 |
| 0.7231 | 37.0 | 222 | 0.6897 |
| 0.7088 | 38.0 | 228 | 0.6824 |
| 0.7067 | 39.0 | 234 | 0.6795 |
| 0.7004 | 40.0 | 240 | 0.6779 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2