| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.2164892657405737, | |
| "eval_steps": 100, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036081544290095615, | |
| "eval_loss": NaN, | |
| "eval_runtime": 196.169, | |
| "eval_samples_per_second": 23.796, | |
| "eval_steps_per_second": 5.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036081544290095615, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007216308858019123, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010824463287028685, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014432617716038246, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018040772145047807, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02164892657405737, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025257081003066933, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.028865235432076492, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.032473389861086055, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.036081544290095614, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.036081544290095614, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.2789, | |
| "eval_samples_per_second": 23.662, | |
| "eval_steps_per_second": 5.915, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03968969871910518, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04329785314811474, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0469060075771243, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.050514162006133866, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.054122316435143425, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.057730470864152984, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06133862529316255, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06494677972217211, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06855493415118168, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07216308858019123, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07216308858019123, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.0795, | |
| "eval_samples_per_second": 23.686, | |
| "eval_steps_per_second": 5.921, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0757712430092008, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07937939743821036, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08298755186721991, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08659570629622948, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09020386072523905, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0938120151542486, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09742016958325816, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10102832401226773, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.10463647844127728, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.10824463287028685, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10824463287028685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.2517, | |
| "eval_samples_per_second": 23.665, | |
| "eval_steps_per_second": 5.916, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11185278729929642, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11546094172830597, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.11906909615731553, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.1226772505863251, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12628540501533467, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.12989355944434422, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13350171387335377, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13710986830236335, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1407180227313729, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14432617716038246, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14432617716038246, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.4311, | |
| "eval_samples_per_second": 23.644, | |
| "eval_steps_per_second": 5.911, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14793433158939204, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.1515424860184016, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.15515064044741114, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.15875879487642072, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.16236694930543027, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.1695832581634494, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.17319141259245896, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1767995670214685, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1804077214504781, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1804077214504781, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.1433, | |
| "eval_samples_per_second": 23.678, | |
| "eval_steps_per_second": 5.92, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18401587587948764, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.1876240303084972, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.19123218473750678, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.19484033916651633, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.19844849359552588, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.20205664802453546, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.20566480245354501, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.20927295688255457, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.21288111131156415, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.2164892657405737, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2164892657405737, | |
| "eval_loss": NaN, | |
| "eval_runtime": 197.2007, | |
| "eval_samples_per_second": 23.671, | |
| "eval_steps_per_second": 5.918, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.98122404544512e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |