Instructions to use Gi8on/calculator_model_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gi8on/calculator_model_test with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Gi8on/calculator_model_test") model = AutoModelForSeq2SeqLM.from_pretrained("Gi8on/calculator_model_test") - Notebooks
- Google Colab
- Kaggle
| library_name: transformers | |
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: calculator_model_test | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # calculator_model_test | |
| This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.6463 | |
| ## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments | |
| - lr_scheduler_type: linear | |
| - num_epochs: 40 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 3.4635 | 1.0 | 5 | 2.8650 | | |
| | 2.5314 | 2.0 | 10 | 2.1158 | | |
| | 1.9819 | 3.0 | 15 | 1.8063 | | |
| | 1.6986 | 4.0 | 20 | 1.6031 | | |
| | 1.5730 | 5.0 | 25 | 1.5538 | | |
| | 1.5102 | 6.0 | 30 | 1.5036 | | |
| | 1.4481 | 7.0 | 35 | 1.4591 | | |
| | 1.3779 | 8.0 | 40 | 1.3530 | | |
| | 1.3051 | 9.0 | 45 | 1.2608 | | |
| | 1.2610 | 10.0 | 50 | 1.1978 | | |
| | 1.2074 | 11.0 | 55 | 1.2343 | | |
| | 1.1567 | 12.0 | 60 | 1.1180 | | |
| | 1.1375 | 13.0 | 65 | 1.1520 | | |
| | 1.1428 | 14.0 | 70 | 1.1030 | | |
| | 1.0972 | 15.0 | 75 | 1.0581 | | |
| | 1.0503 | 16.0 | 80 | 0.9979 | | |
| | 0.9758 | 17.0 | 85 | 0.9513 | | |
| | 0.9473 | 18.0 | 90 | 0.9317 | | |
| | 0.9206 | 19.0 | 95 | 0.9380 | | |
| | 0.9384 | 20.0 | 100 | 0.8643 | | |
| | 0.8769 | 21.0 | 105 | 0.9630 | | |
| | 0.9673 | 22.0 | 110 | 0.9533 | | |
| | 0.9098 | 23.0 | 115 | 0.8435 | | |
| | 0.8675 | 24.0 | 120 | 0.8262 | | |
| | 0.8382 | 25.0 | 125 | 0.8295 | | |
| | 0.8148 | 26.0 | 130 | 0.7936 | | |
| | 0.8002 | 27.0 | 135 | 0.7727 | | |
| | 0.7794 | 28.0 | 140 | 0.7617 | | |
| | 0.7631 | 29.0 | 145 | 0.7373 | | |
| | 0.7419 | 30.0 | 150 | 0.7182 | | |
| | 0.7297 | 31.0 | 155 | 0.7168 | | |
| | 0.7208 | 32.0 | 160 | 0.6962 | | |
| | 0.7054 | 33.0 | 165 | 0.6853 | | |
| | 0.6964 | 34.0 | 170 | 0.6826 | | |
| | 0.6895 | 35.0 | 175 | 0.6700 | | |
| | 0.6787 | 36.0 | 180 | 0.6599 | | |
| | 0.6689 | 37.0 | 185 | 0.6539 | | |
| | 0.6651 | 38.0 | 190 | 0.6495 | | |
| | 0.6646 | 39.0 | 195 | 0.6490 | | |
| | 0.6592 | 40.0 | 200 | 0.6463 | | |
| ### Framework versions | |
| - Transformers 5.0.0 | |
| - Pytorch 2.10.0+cu128 | |
| - Datasets 4.0.0 | |
| - Tokenizers 0.22.2 | |