--- library_name: transformers tags: - generated_from_trainer datasets: - crispr_data model-index: - name: SX_spcas9_Lindel_ins results: [] --- # SX_spcas9_Lindel_ins 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: 118.8835 ## 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 | |:-------------:|:-----:|:----:|:---------------:| | 2592.139 | 1.0 | 322 | 2299.6372 | | 1882.8207 | 2.0 | 644 | 1432.0791 | | 1117.6372 | 3.0 | 966 | 830.2626 | | 644.7085 | 4.0 | 1288 | 479.4404 | | 378.6847 | 5.0 | 1610 | 290.6512 | | 240.4353 | 6.0 | 1932 | 196.7566 | | 174.4188 | 7.0 | 2254 | 153.8273 | | 144.7067 | 8.0 | 2576 | 134.7553 | | 131.5677 | 9.0 | 2898 | 126.3467 | | 125.732 | 10.0 | 3220 | 122.4993 | | 123.021 | 11.0 | 3542 | 120.7702 | | 121.7424 | 12.0 | 3864 | 119.8428 | | 121.1115 | 13.0 | 4186 | 119.4692 | | 120.7975 | 14.0 | 4508 | 119.2571 | | 120.6251 | 15.0 | 4830 | 119.1266 | | 120.5323 | 16.0 | 5152 | 119.0528 | | 120.4722 | 17.0 | 5474 | 119.0086 | | 120.4303 | 18.0 | 5796 | 119.0070 | | 120.394 | 19.0 | 6118 | 118.9882 | | 120.3706 | 20.0 | 6440 | 118.9626 | | 120.3484 | 21.0 | 6762 | 118.9377 | | 120.3319 | 22.0 | 7084 | 118.9345 | | 120.313 | 23.0 | 7406 | 118.9186 | | 120.2975 | 24.0 | 7728 | 118.9214 | | 120.2867 | 25.0 | 8050 | 118.9044 | | 120.2739 | 26.0 | 8372 | 118.8918 | | 120.2623 | 27.0 | 8694 | 118.8881 | | 120.252 | 28.0 | 9016 | 118.8894 | | 120.2417 | 29.0 | 9338 | 118.8838 | | 120.2334 | 30.0 | 9660 | 118.8835 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu124 - Datasets 2.21.0 - Tokenizers 0.19.1