{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.3009781790820166, "eval_steps": 20, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 5e-07, "loss": 1.1046, "step": 10 }, { "epoch": 0.06, "learning_rate": 1e-06, "loss": 1.0664, "step": 20 }, { "epoch": 0.06, "eval_accuracy": 0.44479243019924036, "eval_combined_score": 0.3403229798934559, "eval_f1": 0.2738667532127967, "eval_loss": 1.065091609954834, "eval_precision": 0.19784030596254612, "eval_recall": 0.44479243019924036, "eval_runtime": 49.6621, "eval_samples_per_second": 604.364, "eval_steps_per_second": 1.188, "step": 20 }, { "epoch": 0.09, "learning_rate": 1.5e-06, "loss": 1.0672, "step": 30 }, { "epoch": 0.12, "learning_rate": 2e-06, "loss": 1.0423, "step": 40 }, { "epoch": 0.12, "eval_accuracy": 0.5033650962883988, "eval_combined_score": 0.4633375988688383, "eval_f1": 0.4137746858205889, "eval_loss": 1.0188277959823608, "eval_precision": 0.43284551707796665, "eval_recall": 0.5033650962883988, "eval_runtime": 49.1985, "eval_samples_per_second": 610.06, "eval_steps_per_second": 1.199, "step": 40 }, { "epoch": 0.15, "learning_rate": 2.5e-06, "loss": 1.027, "step": 50 }, { "epoch": 0.18, "learning_rate": 3e-06, "loss": 1.0137, "step": 60 }, { "epoch": 0.18, "eval_accuracy": 0.5279203038581995, "eval_combined_score": 0.48433586826626607, "eval_f1": 0.4596383010419703, "eval_loss": 0.9871189594268799, "eval_precision": 0.421864564306695, "eval_recall": 0.5279203038581995, "eval_runtime": 49.0237, "eval_samples_per_second": 612.235, "eval_steps_per_second": 1.204, "step": 60 }, { "epoch": 0.21, "learning_rate": 3.5e-06, "loss": 1.0005, "step": 70 }, { "epoch": 0.24, "learning_rate": 4e-06, "loss": 1.0027, "step": 80 }, { "epoch": 0.24, "eval_accuracy": 0.5308189511561271, "eval_combined_score": 0.4866197693698143, "eval_f1": 0.46528335920671143, "eval_loss": 0.9888613224029541, "eval_precision": 0.4195578159602916, "eval_recall": 0.5308189511561271, "eval_runtime": 49.518, "eval_samples_per_second": 606.124, "eval_steps_per_second": 1.191, "step": 80 }, { "epoch": 0.27, "learning_rate": 4.5e-06, "loss": 0.9937, "step": 90 }, { "epoch": 0.3, "learning_rate": 5e-06, "loss": 0.9914, "step": 100 }, { "epoch": 0.3, "eval_accuracy": 0.5307856333710935, "eval_combined_score": 0.48644275806230897, "eval_f1": 0.4666072639999521, "eval_loss": 0.9762536883354187, "eval_precision": 0.4175925015070968, "eval_recall": 0.5307856333710935, "eval_runtime": 49.4629, "eval_samples_per_second": 606.798, "eval_steps_per_second": 1.193, "step": 100 } ], "logging_steps": 10, "max_steps": 1660, "num_train_epochs": 5, "save_steps": 100, "total_flos": 1.34714069876736e+16, "trial_name": null, "trial_params": null }