| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.62402496099844, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0124804992199688, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0124804992199688, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1778, | |
| "eval_samples_per_second": 15.734, | |
| "eval_steps_per_second": 4.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0249609984399376, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0374414976599064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0499219968798752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.062402496099843996, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0748829953198128, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0873634945397816, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0998439937597504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11232449297971919, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12480499219968799, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1372854914196568, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1497659906396256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1622464898595944, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1747269890795632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.187207488299532, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1996879875195008, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2121684867394696, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22464898595943839, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23712948517940718, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24960998439937598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2620904836193448, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2745709828393136, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2870514820592824, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2995319812792512, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31201248049922, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31201248049922, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.1834, | |
| "eval_samples_per_second": 15.707, | |
| "eval_steps_per_second": 4.084, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3244929797191888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3369734789391576, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3494539781591264, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3619344773790952, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.374414976599064, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3868954758190328, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3993759750390016, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4118564742589704, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4243369734789392, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.43681747269890797, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.44929797191887677, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46177847113884557, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47425897035881437, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48673946957878317, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.49921996879875197, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5117004680187207, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5241809672386896, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5366614664586583, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5491419656786272, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5616224648985959, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5741029641185648, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5865834633385335, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5990639625585024, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6115444617784711, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.62402496099844, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.62402496099844, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2033, | |
| "eval_samples_per_second": 15.609, | |
| "eval_steps_per_second": 4.058, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658024559509504e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |