| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.045119990976001806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000902399819520036, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000902399819520036, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9473, | |
| "eval_samples_per_second": 16.965, | |
| "eval_steps_per_second": 4.411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001804799639040072, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027071994585601083, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003609599278080144, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004511999097600181, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0054143989171202165, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063167987366402525, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007219198556160288, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008121598375680324, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009023998195200361, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009926398014720396, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010828797834240433, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01173119765376047, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012633597473280505, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013535997292800542, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014438397112320577, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015340796931840614, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01624319675136065, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017145596570880686, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018047996390400722, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01895039620992076, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019852796029440792, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02075519584896083, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021657595668480866, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022559995488000903, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9784, | |
| "eval_samples_per_second": 16.787, | |
| "eval_steps_per_second": 4.365, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02346239530752094, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024364795127040973, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02526719494656101, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026169594766081047, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027071994585601084, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02797439440512112, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.028876794224641154, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02977919404416119, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030681593863681227, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.031583993683201264, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0324863935027213, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03338879332224134, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03429119314176137, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.035193592961281404, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036095992780801445, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03699839260032148, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03790079241984152, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03880319223936155, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039705592058881585, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.040607991878401625, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04151039169792166, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0424127915174417, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04331519133696173, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.044217591156481766, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045119990976001806, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9828, | |
| "eval_samples_per_second": 16.763, | |
| "eval_steps_per_second": 4.358, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |