| { | |
| "best_metric": 0.7865168539325843, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-ktqxy3xz/checkpoint-400", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 2.0802054405212402, | |
| "learning_rate": 4.896382897724454e-05, | |
| "loss": 0.6556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.7415668964385986, | |
| "learning_rate": 4.7708346182956214e-05, | |
| "loss": 0.4257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 6.465210437774658, | |
| "learning_rate": 4.64528633886679e-05, | |
| "loss": 0.8034, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.8712220191955566, | |
| "learning_rate": 4.5197380594379574e-05, | |
| "loss": 0.6423, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 2.292738676071167, | |
| "learning_rate": 4.3941897800091254e-05, | |
| "loss": 0.6402, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 3.6097824573516846, | |
| "learning_rate": 4.268641500580293e-05, | |
| "loss": 0.412, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 3.220292806625366, | |
| "learning_rate": 4.143093221151461e-05, | |
| "loss": 0.5088, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5234849452972412, | |
| "learning_rate": 4.0175449417226294e-05, | |
| "loss": 0.3435, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 1.0715090036392212, | |
| "learning_rate": 3.891996662293797e-05, | |
| "loss": 0.7451, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 6.492457389831543, | |
| "learning_rate": 3.766448382864965e-05, | |
| "loss": 0.2199, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 1.9438965320587158, | |
| "learning_rate": 3.640900103436132e-05, | |
| "loss": 0.7001, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.4070729613304138, | |
| "learning_rate": 3.5153518240073e-05, | |
| "loss": 0.4277, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 0.3407312035560608, | |
| "learning_rate": 3.389803544578468e-05, | |
| "loss": 0.2982, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.44988295435905457, | |
| "learning_rate": 3.264255265149636e-05, | |
| "loss": 0.3097, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.9247645735740662, | |
| "learning_rate": 3.138706985720804e-05, | |
| "loss": 1.0367, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.748664140701294, | |
| "learning_rate": 3.0131587062919714e-05, | |
| "loss": 0.3645, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.425, | |
| "grad_norm": 7.6074910163879395, | |
| "learning_rate": 2.8876104268631394e-05, | |
| "loss": 0.5364, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 6.632686138153076, | |
| "learning_rate": 2.7620621474343077e-05, | |
| "loss": 0.4973, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.475, | |
| "grad_norm": 0.3361460268497467, | |
| "learning_rate": 2.6365138680054754e-05, | |
| "loss": 0.4819, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 5.405449390411377, | |
| "learning_rate": 2.510965588576643e-05, | |
| "loss": 0.3588, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.525, | |
| "grad_norm": 0.504410445690155, | |
| "learning_rate": 2.3854173091478107e-05, | |
| "loss": 0.5494, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 3.5160725116729736, | |
| "learning_rate": 2.2598690297189787e-05, | |
| "loss": 0.5517, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.575, | |
| "grad_norm": 10.914329528808594, | |
| "learning_rate": 2.1343207502901464e-05, | |
| "loss": 0.4456, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 13.415484428405762, | |
| "learning_rate": 2.0087724708613147e-05, | |
| "loss": 0.3435, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.3822052478790283, | |
| "learning_rate": 1.8832241914324824e-05, | |
| "loss": 0.4514, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 13.96898365020752, | |
| "learning_rate": 1.75767591200365e-05, | |
| "loss": 0.5878, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.675, | |
| "grad_norm": 14.09548568725586, | |
| "learning_rate": 1.632127632574818e-05, | |
| "loss": 0.4703, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 8.53896713256836, | |
| "learning_rate": 1.5065793531459857e-05, | |
| "loss": 0.3875, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.725, | |
| "grad_norm": 7.014000415802002, | |
| "learning_rate": 1.3810310737171539e-05, | |
| "loss": 0.2587, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 4.1433258056640625, | |
| "learning_rate": 1.2554827942883215e-05, | |
| "loss": 0.4717, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.775, | |
| "grad_norm": 0.7594526410102844, | |
| "learning_rate": 1.1299345148594894e-05, | |
| "loss": 0.6532, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.1434805393218994, | |
| "learning_rate": 1.0043862354306574e-05, | |
| "loss": 0.3508, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.825, | |
| "grad_norm": 18.727951049804688, | |
| "learning_rate": 8.78837956001825e-06, | |
| "loss": 0.3343, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 4.23914909362793, | |
| "learning_rate": 7.5328967657299285e-06, | |
| "loss": 0.2194, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 14.330482482910156, | |
| "learning_rate": 6.277413971441608e-06, | |
| "loss": 0.4582, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.7658752202987671, | |
| "learning_rate": 5.021931177153287e-06, | |
| "loss": 0.4202, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.925, | |
| "grad_norm": 0.7938013672828674, | |
| "learning_rate": 3.7664483828649642e-06, | |
| "loss": 0.2567, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 1.5704269409179688, | |
| "learning_rate": 2.5109655885766434e-06, | |
| "loss": 0.6044, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.975, | |
| "grad_norm": 5.166118621826172, | |
| "learning_rate": 1.2554827942883217e-06, | |
| "loss": 0.3807, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3811684250831604, | |
| "learning_rate": 0.0, | |
| "loss": 0.4158, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8575, | |
| "eval_f1": 0.7865168539325843, | |
| "eval_loss": 0.42347240447998047, | |
| "eval_precision": 0.7291666666666666, | |
| "eval_recall": 0.8536585365853658, | |
| "eval_runtime": 1.5735, | |
| "eval_samples_per_second": 254.213, | |
| "eval_steps_per_second": 15.888, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 211815370450944.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 5.021931177153286e-05, | |
| "metric": "eval/loss", | |
| "num_train_epochs": 1, | |
| "per_device_train_batch_size": 4, | |
| "seed": 26 | |
| } | |
| } | |