{ "best_metric": 0.22290533781051636, "best_model_checkpoint": "./outputs/google/flan-t5-large_02122024_01_43_15/checkpoint-204", "epoch": 15.0, "global_step": 255, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_f1": 0.35854612429690697, "eval_loss": 0.3239080309867859, "eval_precision": 0.5345785424388172, "eval_recall": 0.329796257224621, "eval_runtime": 38.8356, "eval_samples_per_second": 23.509, "eval_steps_per_second": 0.051, "step": 17 }, { "epoch": 2.0, "eval_f1": 0.4800086503009432, "eval_loss": 0.27419987320899963, "eval_precision": 0.5542260783408233, "eval_recall": 0.45913065421918553, "eval_runtime": 39.8578, "eval_samples_per_second": 22.906, "eval_steps_per_second": 0.05, "step": 34 }, { "epoch": 3.0, "eval_f1": 0.5443215685703763, "eval_loss": 0.25187569856643677, "eval_precision": 0.6206486717460002, "eval_recall": 0.5029506333684081, "eval_runtime": 39.3247, "eval_samples_per_second": 23.217, "eval_steps_per_second": 0.051, "step": 51 }, { "epoch": 4.0, "eval_f1": 0.5459293718280644, "eval_loss": 0.24283328652381897, "eval_precision": 0.616637099118601, "eval_recall": 0.5155663121000017, "eval_runtime": 37.072, "eval_samples_per_second": 24.628, "eval_steps_per_second": 0.054, "step": 68 }, { "epoch": 5.0, "eval_f1": 0.5710196002310937, "eval_loss": 0.23178835213184357, "eval_precision": 0.6282617653909686, "eval_recall": 0.5368555933265855, "eval_runtime": 36.6733, "eval_samples_per_second": 24.895, "eval_steps_per_second": 0.055, "step": 85 }, { "epoch": 6.0, "eval_f1": 0.5886409252490327, "eval_loss": 0.23057235777378082, "eval_precision": 0.6448654434139668, "eval_recall": 0.5537863952595103, "eval_runtime": 37.9819, "eval_samples_per_second": 24.038, "eval_steps_per_second": 0.053, "step": 102 }, { "epoch": 7.0, "eval_f1": 0.600361744212171, "eval_loss": 0.22994089126586914, "eval_precision": 0.6326699786344088, "eval_recall": 0.5875735086169913, "eval_runtime": 36.8118, "eval_samples_per_second": 24.802, "eval_steps_per_second": 0.054, "step": 119 }, { "epoch": 8.0, "eval_f1": 0.5898429185159373, "eval_loss": 0.23065505921840668, "eval_precision": 0.633863994982363, "eval_recall": 0.562442145951263, "eval_runtime": 36.7709, "eval_samples_per_second": 24.829, "eval_steps_per_second": 0.054, "step": 136 }, { "epoch": 9.0, "eval_f1": 0.6065593580472449, "eval_loss": 0.23772038519382477, "eval_precision": 0.6261362704914151, "eval_recall": 0.6057592597310242, "eval_runtime": 38.4187, "eval_samples_per_second": 23.764, "eval_steps_per_second": 0.052, "step": 153 }, { "epoch": 10.0, "eval_f1": 0.6079410417108765, "eval_loss": 0.22976116836071014, "eval_precision": 0.6377255763201906, "eval_recall": 0.5914829425497372, "eval_runtime": 37.0168, "eval_samples_per_second": 24.664, "eval_steps_per_second": 0.054, "step": 170 }, { "epoch": 11.0, "eval_f1": 0.5969861624754838, "eval_loss": 0.22933387756347656, "eval_precision": 0.6259750563139828, "eval_recall": 0.5795562950971751, "eval_runtime": 37.9807, "eval_samples_per_second": 24.039, "eval_steps_per_second": 0.053, "step": 187 }, { "epoch": 12.0, "eval_f1": 0.6081487065194826, "eval_loss": 0.22290533781051636, "eval_precision": 0.6323140438141116, "eval_recall": 0.588223635460403, "eval_runtime": 39.5283, "eval_samples_per_second": 23.097, "eval_steps_per_second": 0.051, "step": 204 }, { "epoch": 13.0, "eval_f1": 0.6024729442886458, "eval_loss": 0.23005685210227966, "eval_precision": 0.6260193130412378, "eval_recall": 0.5896803540305185, "eval_runtime": 39.0168, "eval_samples_per_second": 23.4, "eval_steps_per_second": 0.051, "step": 221 }, { "epoch": 14.0, "eval_f1": 0.6077520041715136, "eval_loss": 0.2309972643852234, "eval_precision": 0.6309778562386218, "eval_recall": 0.5944067259980179, "eval_runtime": 39.6005, "eval_samples_per_second": 23.055, "eval_steps_per_second": 0.051, "step": 238 }, { "epoch": 15.0, "eval_f1": 0.5905725901461648, "eval_loss": 0.23189686238765717, "eval_precision": 0.6228263267388, "eval_recall": 0.5694187522517138, "eval_runtime": 38.3036, "eval_samples_per_second": 23.836, "eval_steps_per_second": 0.052, "step": 255 }, { "epoch": 15.0, "step": 255, "total_flos": 37877602058240.0, "train_loss": 0.27247093051087623, "train_runtime": 6452.7815, "train_samples_per_second": 31.835, "train_steps_per_second": 0.066 } ], "max_steps": 425, "num_train_epochs": 25, "total_flos": 37877602058240.0, "trial_name": null, "trial_params": null }