--- library_name: transformers tags: - generated_from_trainer datasets: - crispr_data model-index: - name: SX_spymac_Lindel_indel results: [] --- # SX_spymac_Lindel_indel This model is a fine-tuned version of [](https://huggingface.co/) on the crispr_data dataset. It achieves the following results on the evaluation set: - Loss: 38.1306 ## 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: 100 - eval_batch_size: 100 - seed: 63036 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 30.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1004.8263 | 1.0 | 327 | 852.2144 | | 666.3497 | 2.0 | 654 | 499.1797 | | 377.0592 | 3.0 | 981 | 278.4397 | | 210.4376 | 4.0 | 1308 | 155.1109 | | 119.4755 | 5.0 | 1635 | 90.4825 | | 73.7367 | 6.0 | 1962 | 60.2916 | | 52.9741 | 7.0 | 2289 | 47.1790 | | 44.25 | 8.0 | 2616 | 41.8598 | | 40.6432 | 9.0 | 2943 | 39.6603 | | 39.1873 | 10.0 | 3270 | 38.7853 | | 38.5702 | 11.0 | 3597 | 38.4049 | | 38.2968 | 12.0 | 3924 | 38.2860 | | 38.1861 | 13.0 | 4251 | 38.2043 | | 38.1379 | 14.0 | 4578 | 38.1345 | | 38.116 | 15.0 | 4905 | 38.1763 | | 38.1017 | 16.0 | 5232 | 38.1730 | | 38.0909 | 17.0 | 5559 | 38.1854 | | 38.0901 | 18.0 | 5886 | 38.1427 | | 38.0781 | 19.0 | 6213 | 38.1391 | | 38.0695 | 20.0 | 6540 | 38.1281 | | 38.0662 | 21.0 | 6867 | 38.1312 | | 38.0583 | 22.0 | 7194 | 38.1344 | | 38.0541 | 23.0 | 7521 | 38.1393 | | 38.0484 | 24.0 | 7848 | 38.1284 | | 38.0426 | 25.0 | 8175 | 38.1339 | | 38.0359 | 26.0 | 8502 | 38.1325 | | 38.0331 | 27.0 | 8829 | 38.1341 | | 38.0249 | 28.0 | 9156 | 38.1314 | | 38.0197 | 29.0 | 9483 | 38.1297 | | 38.0133 | 30.0 | 9810 | 38.1306 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu124 - Datasets 2.21.0 - Tokenizers 0.19.1