{ "best_metric": null, "best_model_checkpoint": null, "epoch": 26.31578947368421, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.63, "eval_accuracy": 0.798690858980248, "eval_f1": 0.8287769784172662, "eval_loss": 0.6110699772834778, "eval_precision": 0.7963133640552995, "eval_recall": 0.864, "eval_runtime": 3.5435, "eval_samples_per_second": 15.239, "eval_steps_per_second": 1.129, "step": 100 }, { "epoch": 5.26, "eval_accuracy": 0.826596233348645, "eval_f1": 0.8665358194308145, "eval_loss": 0.5860626697540283, "eval_precision": 0.850674373795761, "eval_recall": 0.883, "eval_runtime": 3.5697, "eval_samples_per_second": 15.127, "eval_steps_per_second": 1.121, "step": 200 }, { "epoch": 7.89, "eval_accuracy": 0.8425585668350941, "eval_f1": 0.8826268071551091, "eval_loss": 0.5855879783630371, "eval_precision": 0.865449303219606, "eval_recall": 0.9005, "eval_runtime": 3.5797, "eval_samples_per_second": 15.085, "eval_steps_per_second": 1.117, "step": 300 }, { "epoch": 10.53, "eval_accuracy": 0.8426734037666513, "eval_f1": 0.8897131552917903, "eval_loss": 0.6501617431640625, "eval_precision": 0.8801369863013698, "eval_recall": 0.8995, "eval_runtime": 3.5894, "eval_samples_per_second": 15.044, "eval_steps_per_second": 1.114, "step": 400 }, { "epoch": 13.16, "learning_rate": 5e-06, "loss": 0.4088, "step": 500 }, { "epoch": 13.16, "eval_accuracy": 0.8372760679834634, "eval_f1": 0.8959365708622398, "eval_loss": 0.7679007649421692, "eval_precision": 0.888015717092338, "eval_recall": 0.904, "eval_runtime": 3.5844, "eval_samples_per_second": 15.065, "eval_steps_per_second": 1.116, "step": 500 }, { "epoch": 15.79, "eval_accuracy": 0.8332567753789619, "eval_f1": 0.8928395061728396, "eval_loss": 0.8370674848556519, "eval_precision": 0.8819512195121951, "eval_recall": 0.904, "eval_runtime": 3.4921, "eval_samples_per_second": 15.463, "eval_steps_per_second": 1.145, "step": 600 }, { "epoch": 18.42, "eval_accuracy": 0.8336012861736335, "eval_f1": 0.9036561264822135, "eval_loss": 0.8320176601409912, "eval_precision": 0.89306640625, "eval_recall": 0.9145, "eval_runtime": 3.5735, "eval_samples_per_second": 15.111, "eval_steps_per_second": 1.119, "step": 700 }, { "epoch": 21.05, "eval_accuracy": 0.8340606338998622, "eval_f1": 0.9051275699777063, "eval_loss": 0.8494298458099365, "eval_precision": 0.8969072164948454, "eval_recall": 0.9135, "eval_runtime": 3.6561, "eval_samples_per_second": 14.77, "eval_steps_per_second": 1.094, "step": 800 }, { "epoch": 23.68, "eval_accuracy": 0.8385392742305926, "eval_f1": 0.907196029776675, "eval_loss": 0.8700249195098877, "eval_precision": 0.9004926108374385, "eval_recall": 0.914, "eval_runtime": 3.5188, "eval_samples_per_second": 15.346, "eval_steps_per_second": 1.137, "step": 900 }, { "epoch": 26.32, "learning_rate": 0.0, "loss": 0.061, "step": 1000 }, { "epoch": 26.32, "eval_accuracy": 0.8407211759301791, "eval_f1": 0.9107187266849044, "eval_loss": 0.8859658241271973, "eval_precision": 0.9059871350816427, "eval_recall": 0.9155, "eval_runtime": 3.6186, "eval_samples_per_second": 14.923, "eval_steps_per_second": 1.105, "step": 1000 }, { "epoch": 26.32, "step": 1000, "total_flos": 1040713895079936.0, "train_loss": 0.23488603591918944, "train_runtime": 622.7344, "train_samples_per_second": 6.423, "train_steps_per_second": 1.606 } ], "max_steps": 1000, "num_train_epochs": 27, "total_flos": 1040713895079936.0, "trial_name": null, "trial_params": null }