| { | |
| "best_metric": 0.33775803446769714, | |
| "best_model_checkpoint": "/content/dnrti_cybert/checkpoint-6000", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 6570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8477929984779303e-05, | |
| "loss": 0.8529, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.8507513661202186, | |
| "eval_f1": 0.3983656792645557, | |
| "eval_loss": 0.5936621427536011, | |
| "eval_precision": 0.4469914040114613, | |
| "eval_recall": 0.3592814371257485, | |
| "eval_runtime": 1.9061, | |
| "eval_samples_per_second": 346.79, | |
| "eval_steps_per_second": 43.545, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.69558599695586e-05, | |
| "loss": 0.5566, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.863558743169399, | |
| "eval_f1": 0.44201843765162535, | |
| "eval_loss": 0.5027214884757996, | |
| "eval_precision": 0.46694003075345974, | |
| "eval_recall": 0.41962229387379085, | |
| "eval_runtime": 1.4839, | |
| "eval_samples_per_second": 445.446, | |
| "eval_steps_per_second": 55.933, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.54337899543379e-05, | |
| "loss": 0.4678, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.8693647540983607, | |
| "eval_f1": 0.47681818181818186, | |
| "eval_loss": 0.4671035706996918, | |
| "eval_precision": 0.4706146253925527, | |
| "eval_recall": 0.4831874712114233, | |
| "eval_runtime": 1.5205, | |
| "eval_samples_per_second": 434.721, | |
| "eval_steps_per_second": 54.587, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.39117199391172e-05, | |
| "loss": 0.4038, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.8739184881602914, | |
| "eval_f1": 0.4972281449893391, | |
| "eval_loss": 0.4320070147514343, | |
| "eval_precision": 0.462882096069869, | |
| "eval_recall": 0.5370796867802856, | |
| "eval_runtime": 1.5331, | |
| "eval_samples_per_second": 431.143, | |
| "eval_steps_per_second": 54.137, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.2389649923896501e-05, | |
| "loss": 0.3572, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_accuracy": 0.8857581967213115, | |
| "eval_f1": 0.5260557053009883, | |
| "eval_loss": 0.4002175033092499, | |
| "eval_precision": 0.5133713283647523, | |
| "eval_recall": 0.539382772915707, | |
| "eval_runtime": 1.5925, | |
| "eval_samples_per_second": 415.066, | |
| "eval_steps_per_second": 52.119, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.08675799086758e-05, | |
| "loss": 0.3167, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.88257058287796, | |
| "eval_f1": 0.5301542776998598, | |
| "eval_loss": 0.40466251969337463, | |
| "eval_precision": 0.46914893617021275, | |
| "eval_recall": 0.6093965914325196, | |
| "eval_runtime": 2.0051, | |
| "eval_samples_per_second": 329.657, | |
| "eval_steps_per_second": 41.394, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 9.3455098934551e-06, | |
| "loss": 0.2987, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_accuracy": 0.8947518214936248, | |
| "eval_f1": 0.5484358144552318, | |
| "eval_loss": 0.3760905861854553, | |
| "eval_precision": 0.515827922077922, | |
| "eval_recall": 0.5854444956241364, | |
| "eval_runtime": 2.0282, | |
| "eval_samples_per_second": 325.898, | |
| "eval_steps_per_second": 40.922, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.823439878234399e-06, | |
| "loss": 0.2706, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_accuracy": 0.9001024590163934, | |
| "eval_f1": 0.5692673438513076, | |
| "eval_loss": 0.35579434037208557, | |
| "eval_precision": 0.5362377850162866, | |
| "eval_recall": 0.6066328880700138, | |
| "eval_runtime": 1.7022, | |
| "eval_samples_per_second": 388.312, | |
| "eval_steps_per_second": 48.759, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 6.301369863013699e-06, | |
| "loss": 0.2461, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_accuracy": 0.9028346994535519, | |
| "eval_f1": 0.5620767494356659, | |
| "eval_loss": 0.3493354916572571, | |
| "eval_precision": 0.5511288180610889, | |
| "eval_recall": 0.5734684477199448, | |
| "eval_runtime": 1.5761, | |
| "eval_samples_per_second": 419.392, | |
| "eval_steps_per_second": 52.662, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 4.779299847792998e-06, | |
| "loss": 0.2311, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_accuracy": 0.9023793260473588, | |
| "eval_f1": 0.5866500829187397, | |
| "eval_loss": 0.3526126444339752, | |
| "eval_precision": 0.5333584621183566, | |
| "eval_recall": 0.6517733763242746, | |
| "eval_runtime": 1.5505, | |
| "eval_samples_per_second": 426.316, | |
| "eval_steps_per_second": 53.531, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 3.2572298325722984e-06, | |
| "loss": 0.2171, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "eval_accuracy": 0.907103825136612, | |
| "eval_f1": 0.5968676249731818, | |
| "eval_loss": 0.3417607247829437, | |
| "eval_precision": 0.5586345381526104, | |
| "eval_recall": 0.6407185628742516, | |
| "eval_runtime": 1.8615, | |
| "eval_samples_per_second": 355.092, | |
| "eval_steps_per_second": 44.588, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.7351598173515982e-06, | |
| "loss": 0.2062, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_accuracy": 0.9077299635701275, | |
| "eval_f1": 0.6006444683136413, | |
| "eval_loss": 0.33775803446769714, | |
| "eval_precision": 0.5628019323671497, | |
| "eval_recall": 0.6439428834638415, | |
| "eval_runtime": 2.0229, | |
| "eval_samples_per_second": 326.758, | |
| "eval_steps_per_second": 41.03, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 2.1308980213089802e-07, | |
| "loss": 0.1972, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.9086976320582878, | |
| "eval_f1": 0.6055555555555556, | |
| "eval_loss": 0.338409960269928, | |
| "eval_precision": 0.5647668393782384, | |
| "eval_recall": 0.6526946107784432, | |
| "eval_runtime": 1.5917, | |
| "eval_samples_per_second": 415.277, | |
| "eval_steps_per_second": 52.145, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 6570, | |
| "total_flos": 712828548484272.0, | |
| "train_loss": 0.35387681368823465, | |
| "train_runtime": 542.4349, | |
| "train_samples_per_second": 96.786, | |
| "train_steps_per_second": 12.112 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6570, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 712828548484272.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |