{ "best_metric": 0.08035404235124588, "best_model_checkpoint": "./models/distilbert-base-uncased_1656660721.137864/checkpoint-9400", "epoch": 3.0, "global_step": 14100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "learning_rate": 1.9334751773049647e-05, "loss": 0.3653, "step": 469 }, { "epoch": 0.2, "learning_rate": 1.866950354609929e-05, "loss": 0.144, "step": 938 }, { "epoch": 0.3, "learning_rate": 1.8004255319148936e-05, "loss": 0.1162, "step": 1407 }, { "epoch": 0.4, "learning_rate": 1.7339007092198585e-05, "loss": 0.1076, "step": 1876 }, { "epoch": 0.5, "learning_rate": 1.667375886524823e-05, "loss": 0.0947, "step": 2345 }, { "epoch": 0.6, "learning_rate": 1.6008510638297874e-05, "loss": 0.0864, "step": 2814 }, { "epoch": 0.7, "learning_rate": 1.534326241134752e-05, "loss": 0.0913, "step": 3283 }, { "epoch": 0.8, "learning_rate": 1.4678014184397164e-05, "loss": 0.076, "step": 3752 }, { "epoch": 0.9, "learning_rate": 1.401276595744681e-05, "loss": 0.0785, "step": 4221 }, { "epoch": 1.0, "learning_rate": 1.3347517730496456e-05, "loss": 0.0749, "step": 4690 }, { "epoch": 1.0, "eval_accuracy": 0.976376791937681, "eval_f1": 0.8418500066134651, "eval_loss": 0.08329251408576965, "eval_precision": 0.8356967787114846, "eval_recall": 0.8480945189659768, "eval_runtime": 18.0373, "eval_samples_per_second": 525.521, "eval_steps_per_second": 32.876, "step": 4700 }, { "epoch": 1.1, "learning_rate": 1.26822695035461e-05, "loss": 0.061, "step": 5159 }, { "epoch": 1.2, "learning_rate": 1.2017021276595745e-05, "loss": 0.0579, "step": 5628 }, { "epoch": 1.3, "learning_rate": 1.1351773049645392e-05, "loss": 0.0564, "step": 6097 }, { "epoch": 1.4, "learning_rate": 1.0686524822695037e-05, "loss": 0.0539, "step": 6566 }, { "epoch": 1.5, "learning_rate": 1.0021276595744682e-05, "loss": 0.0566, "step": 7035 }, { "epoch": 1.6, "learning_rate": 9.356028368794327e-06, "loss": 0.0516, "step": 7504 }, { "epoch": 1.7, "learning_rate": 8.690780141843971e-06, "loss": 0.0506, "step": 7973 }, { "epoch": 1.8, "learning_rate": 8.025531914893618e-06, "loss": 0.0518, "step": 8442 }, { "epoch": 1.9, "learning_rate": 7.360283687943263e-06, "loss": 0.0485, "step": 8911 }, { "epoch": 2.0, "learning_rate": 6.695035460992908e-06, "loss": 0.0549, "step": 9380 }, { "epoch": 2.0, "eval_accuracy": 0.9773085110774329, "eval_f1": 0.8474291524824263, "eval_loss": 0.08035404235124588, "eval_precision": 0.8435134659390953, "eval_recall": 0.8513813627076485, "eval_runtime": 16.8781, "eval_samples_per_second": 561.614, "eval_steps_per_second": 35.134, "step": 9400 }, { "epoch": 2.1, "learning_rate": 6.029787234042554e-06, "loss": 0.0359, "step": 9849 }, { "epoch": 2.2, "learning_rate": 5.3645390070921985e-06, "loss": 0.0357, "step": 10318 }, { "epoch": 2.3, "learning_rate": 4.699290780141844e-06, "loss": 0.0365, "step": 10787 }, { "epoch": 2.39, "learning_rate": 4.03404255319149e-06, "loss": 0.0373, "step": 11256 }, { "epoch": 2.49, "learning_rate": 3.368794326241135e-06, "loss": 0.0356, "step": 11725 }, { "epoch": 2.59, "learning_rate": 2.70354609929078e-06, "loss": 0.0344, "step": 12194 }, { "epoch": 2.69, "learning_rate": 2.0382978723404254e-06, "loss": 0.0394, "step": 12663 }, { "epoch": 2.79, "learning_rate": 1.373049645390071e-06, "loss": 0.035, "step": 13132 }, { "epoch": 2.89, "learning_rate": 7.078014184397164e-07, "loss": 0.04, "step": 13601 }, { "epoch": 2.99, "learning_rate": 4.2553191489361707e-08, "loss": 0.0372, "step": 14070 }, { "epoch": 3.0, "eval_accuracy": 0.9779158976052459, "eval_f1": 0.8553354127311866, "eval_loss": 0.08268037438392639, "eval_precision": 0.8460803059273423, "eval_recall": 0.8647952385182553, "eval_runtime": 17.8553, "eval_samples_per_second": 530.88, "eval_steps_per_second": 33.211, "step": 14100 } ], "max_steps": 14100, "num_train_epochs": 3, "total_flos": 3077290776098406.0, "trial_name": null, "trial_params": null }