| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7835455435847208, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 874438.25, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4057, | |
| "eval_samples_per_second": 14.681, | |
| "eval_steps_per_second": 3.817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.031341821743388835, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04701273261508325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06268364348677767, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0940254652301665, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10969637610186092, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12536728697355534, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14103819784524976, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17238001958863858, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.188050930460333, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20372184133202742, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21939275220372184, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23506366307541626, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2507345739471107, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2664054848188051, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2820763956904995, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29774730656219395, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.31341821743388837, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32908912830558273, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34476003917727716, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3604309500489716, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.376101860920666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4492, | |
| "eval_samples_per_second": 14.496, | |
| "eval_steps_per_second": 3.769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40744368266405484, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.42311459353574926, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4387855044074437, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4544564152791381, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4701273261508325, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48579823702252695, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5014691478942214, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5171400587659157, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5328109696376102, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5484818805093046, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.564152791380999, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5798237022526934, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5954946131243879, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6111655239960823, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6268364348677767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6425073457394711, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6581782566111655, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.67384916748286, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6895200783545543, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7051909892262488, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7208619000979432, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7365328109696376, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.752203721841332, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7678746327130265, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7835455435847208, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7835455435847208, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4465, | |
| "eval_samples_per_second": 14.507, | |
| "eval_steps_per_second": 3.772, | |
| "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": 5.641633031572685e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |