| { | |
| "best_metric": 0.652353048324585, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06483770312436682, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012967540624873365, | |
| "grad_norm": 16.785573959350586, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 43.7265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012967540624873365, | |
| "eval_loss": 1.705428123474121, | |
| "eval_runtime": 2.9276, | |
| "eval_samples_per_second": 17.079, | |
| "eval_steps_per_second": 4.441, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002593508124974673, | |
| "grad_norm": 28.982810974121094, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 42.8946, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038902621874620093, | |
| "grad_norm": 32.87180709838867, | |
| "learning_rate": 0.0001, | |
| "loss": 40.5252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005187016249949346, | |
| "grad_norm": 44.707279205322266, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 37.9476, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006483770312436682, | |
| "grad_norm": 36.72836685180664, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 32.5188, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0077805243749240185, | |
| "grad_norm": 38.171810150146484, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 25.5456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009077278437411355, | |
| "grad_norm": 57.68375015258789, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 23.8212, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010374032499898692, | |
| "grad_norm": 31.480140686035156, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 17.8454, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011670786562386027, | |
| "grad_norm": 31.195682525634766, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 21.7711, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012967540624873364, | |
| "grad_norm": 27.705665588378906, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 27.2241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0142642946873607, | |
| "grad_norm": 27.043445587158203, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 33.6918, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015561048749848037, | |
| "grad_norm": 33.10136413574219, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 42.3679, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016857802812335374, | |
| "grad_norm": 22.521921157836914, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 41.087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01815455687482271, | |
| "grad_norm": 19.09137535095215, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 34.6201, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019451310937310045, | |
| "grad_norm": 15.93561840057373, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 28.9021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020748064999797384, | |
| "grad_norm": 13.309250831604004, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 19.9195, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02204481906228472, | |
| "grad_norm": 10.42359447479248, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 11.9618, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023341573124772055, | |
| "grad_norm": 15.537765502929688, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 14.3353, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02463832718725939, | |
| "grad_norm": 11.342974662780762, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 9.9775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02593508124974673, | |
| "grad_norm": 14.146580696105957, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 14.0379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027231835312234064, | |
| "grad_norm": 15.346806526184082, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 13.1845, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0285285893747214, | |
| "grad_norm": 14.695765495300293, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 18.4925, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029825343437208735, | |
| "grad_norm": 15.247776985168457, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 23.5953, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031122097499696074, | |
| "grad_norm": 19.08445930480957, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 37.6228, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03241885156218341, | |
| "grad_norm": 23.201744079589844, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 35.105, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03241885156218341, | |
| "eval_loss": 0.7101312875747681, | |
| "eval_runtime": 2.9691, | |
| "eval_samples_per_second": 16.84, | |
| "eval_steps_per_second": 4.378, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03371560562467075, | |
| "grad_norm": 9.792278289794922, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 36.8223, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03501235968715808, | |
| "grad_norm": 15.209010124206543, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 28.8723, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03630911374964542, | |
| "grad_norm": 15.312687873840332, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 20.8671, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03760586781213276, | |
| "grad_norm": 11.13228988647461, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 15.874, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03890262187462009, | |
| "grad_norm": 12.170778274536133, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 9.841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04019937593710743, | |
| "grad_norm": 8.809076309204102, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 12.2626, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04149612999959477, | |
| "grad_norm": 8.72727108001709, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 9.9618, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0427928840620821, | |
| "grad_norm": 8.521458625793457, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 11.9306, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04408963812456944, | |
| "grad_norm": 10.72695255279541, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 17.8682, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04538639218705677, | |
| "grad_norm": 12.048954963684082, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 24.6443, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04668314624954411, | |
| "grad_norm": 14.231986045837402, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 30.6334, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04797990031203145, | |
| "grad_norm": 16.270370483398438, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 36.3834, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04927665437451878, | |
| "grad_norm": 14.480351448059082, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 41.1031, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05057340843700612, | |
| "grad_norm": 9.69229507446289, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 30.1462, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05187016249949346, | |
| "grad_norm": 10.705002784729004, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 23.4604, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05316691656198079, | |
| "grad_norm": 11.107697486877441, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 13.1305, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05446367062446813, | |
| "grad_norm": 7.914254665374756, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 10.4824, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05576042468695547, | |
| "grad_norm": 7.241426467895508, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 12.7372, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0570571787494428, | |
| "grad_norm": 7.243592262268066, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 8.7167, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05835393281193014, | |
| "grad_norm": 8.968466758728027, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 11.5413, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05965068687441747, | |
| "grad_norm": 10.867255210876465, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 14.4485, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06094744093690481, | |
| "grad_norm": 10.397505760192871, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 14.4408, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06224419499939215, | |
| "grad_norm": 11.32922077178955, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 21.16, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06354094906187949, | |
| "grad_norm": 15.780669212341309, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 29.0683, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06483770312436682, | |
| "grad_norm": 21.16714096069336, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 35.8908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06483770312436682, | |
| "eval_loss": 0.652353048324585, | |
| "eval_runtime": 2.9375, | |
| "eval_samples_per_second": 17.021, | |
| "eval_steps_per_second": 4.426, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.259926510449459e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |