| { | |
| "best_metric": 0.8017432615481261, | |
| "best_model_checkpoint": "esm2_t6_8M_general_binding_sites_2023-09-06_06-37-44/checkpoint-5598", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 5598, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0004961698532325722, | |
| "loss": 0.4517, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0004915229079544901, | |
| "loss": 0.3739, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.000483822060129619, | |
| "loss": 0.2989, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.000473164221525201, | |
| "loss": 0.2545, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00045968351633088675, | |
| "loss": 0.2303, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.000443549593265072, | |
| "loss": 0.1825, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00042496549062073606, | |
| "loss": 0.19, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0004041650811182374, | |
| "loss": 0.1797, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00038141012872046516, | |
| "loss": 0.155, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_auc": 0.9497250592971407, | |
| "eval_f1": 0.6353034457695992, | |
| "eval_loss": 0.15242049098014832, | |
| "eval_precision": 0.48784819118169365, | |
| "eval_recall": 0.9105113636363636, | |
| "eval_runtime": 96.7551, | |
| "eval_samples_per_second": 27.223, | |
| "eval_steps_per_second": 3.411, | |
| "step": 1866 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0003569869944490272, | |
| "loss": 0.1261, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.000331203032657322, | |
| "loss": 0.0908, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00030438272311180667, | |
| "loss": 0.0957, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002770023512698231, | |
| "loss": 0.1168, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002491315977879658, | |
| "loss": 0.0938, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00022125732929671252, | |
| "loss": 0.0966, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00019373033114872802, | |
| "loss": 0.0759, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00016689701845284922, | |
| "loss": 0.0714, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00014109507659300455, | |
| "loss": 0.0729, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_auc": 0.976594527628606, | |
| "eval_f1": 0.6780304923769057, | |
| "eval_loss": 0.07192622125148773, | |
| "eval_precision": 0.5231006556112611, | |
| "eval_recall": 0.9633522727272728, | |
| "eval_runtime": 96.8327, | |
| "eval_samples_per_second": 27.202, | |
| "eval_steps_per_second": 3.408, | |
| "step": 3732 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0001166492116068638, | |
| "loss": 0.0787, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.38670639038266e-05, | |
| "loss": 0.0334, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.303533674640114e-05, | |
| "loss": 0.0534, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.4416188216326214e-05, | |
| "loss": 0.0393, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.824393207094711e-05, | |
| "loss": 0.0268, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.472208900811192e-05, | |
| "loss": 0.0359, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.4020825448114917e-05, | |
| "loss": 0.0257, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.306013894033772e-06, | |
| "loss": 0.0418, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.5972878679293278e-06, | |
| "loss": 0.0311, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_auc": 0.9808531184209585, | |
| "eval_f1": 0.8017432615481261, | |
| "eval_loss": 0.07471965998411179, | |
| "eval_precision": 0.6847982829739427, | |
| "eval_recall": 0.9668560606060606, | |
| "eval_runtime": 96.7245, | |
| "eval_samples_per_second": 27.232, | |
| "eval_steps_per_second": 3.412, | |
| "step": 5598 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 5598, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1987518770082000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |