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: 0.3798
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 |
---|---|---|---|
2.8946 | 1.0 | 41 | 2.3454 |
2.1015 | 2.0 | 82 | 1.9329 |
1.8297 | 3.0 | 123 | 1.6538 |
1.4394 | 4.0 | 164 | 1.2883 |
1.2328 | 5.0 | 205 | 1.1711 |
1.1398 | 6.0 | 246 | 1.0309 |
1.0575 | 7.0 | 287 | 0.9585 |
0.9607 | 8.0 | 328 | 0.9029 |
0.8955 | 9.0 | 369 | 0.8200 |
0.8318 | 10.0 | 410 | 0.7741 |
0.7961 | 11.0 | 451 | 0.7525 |
0.7713 | 12.0 | 492 | 0.7437 |
0.7477 | 13.0 | 533 | 0.6924 |
0.7197 | 14.0 | 574 | 0.6796 |
0.6971 | 15.0 | 615 | 0.6514 |
0.6734 | 16.0 | 656 | 0.6209 |
0.6593 | 17.0 | 697 | 0.6080 |
0.6396 | 18.0 | 738 | 0.5799 |
0.6208 | 19.0 | 779 | 0.5706 |
0.6004 | 20.0 | 820 | 0.5619 |
0.5805 | 21.0 | 861 | 0.5368 |
0.5765 | 22.0 | 902 | 0.5237 |
0.5591 | 23.0 | 943 | 0.5110 |
0.5462 | 24.0 | 984 | 0.5035 |
0.5345 | 25.0 | 1025 | 0.4991 |
0.5208 | 26.0 | 1066 | 0.4734 |
0.5064 | 27.0 | 1107 | 0.4680 |
0.4989 | 28.0 | 1148 | 0.4560 |
0.4892 | 29.0 | 1189 | 0.4560 |
0.4821 | 30.0 | 1230 | 0.4438 |
0.4726 | 31.0 | 1271 | 0.4383 |
0.4659 | 32.0 | 1312 | 0.4314 |
0.453 | 33.0 | 1353 | 0.4122 |
0.4466 | 34.0 | 1394 | 0.4115 |
0.4393 | 35.0 | 1435 | 0.3996 |
0.4315 | 36.0 | 1476 | 0.4007 |
0.4266 | 37.0 | 1517 | 0.3949 |
0.4219 | 38.0 | 1558 | 0.3878 |
0.416 | 39.0 | 1599 | 0.3816 |
0.4133 | 40.0 | 1640 | 0.3798 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.