| { | |
| "best_metric": 0.001949921017512679, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.00253324889170361, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.06649778340722e-05, | |
| "grad_norm": 20.04536247253418, | |
| "learning_rate": 0.0001, | |
| "loss": 15.9577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.06649778340722e-05, | |
| "eval_loss": 16.862504959106445, | |
| "eval_runtime": 2909.45, | |
| "eval_samples_per_second": 2.857, | |
| "eval_steps_per_second": 1.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001013299556681444, | |
| "grad_norm": 20.155981063842773, | |
| "learning_rate": 0.0002, | |
| "loss": 16.5827, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001519949335022166, | |
| "grad_norm": 23.297149658203125, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 15.0496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002026599113362888, | |
| "grad_norm": 27.307846069335938, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 9.8714, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000253324889170361, | |
| "grad_norm": 33.377262115478516, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.5441, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003039898670044332, | |
| "grad_norm": 8.83004379272461, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.5125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003546548448385054, | |
| "grad_norm": 19.265148162841797, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.1222, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004053198226725776, | |
| "grad_norm": 0.0802723839879036, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0025, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004559848005066498, | |
| "grad_norm": 0.02884684130549431, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0008, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000506649778340722, | |
| "grad_norm": 0.09292885661125183, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005573147561747942, | |
| "grad_norm": 0.040504809468984604, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0005, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006079797340088664, | |
| "grad_norm": 0.02018260769546032, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0003, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006586447118429385, | |
| "grad_norm": 0.011460850015282631, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007093096896770108, | |
| "grad_norm": 0.012555892579257488, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0002, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007599746675110829, | |
| "grad_norm": 0.007827025838196278, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008106396453451552, | |
| "grad_norm": 0.010315964929759502, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008613046231792273, | |
| "grad_norm": 0.015333445742726326, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0009119696010132996, | |
| "grad_norm": 0.007192891091108322, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009626345788473718, | |
| "grad_norm": 0.006916944403201342, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001013299556681444, | |
| "grad_norm": 0.0031838975846767426, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010639645345155162, | |
| "grad_norm": 0.005292287562042475, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011146295123495883, | |
| "grad_norm": 0.008216285146772861, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0011652944901836605, | |
| "grad_norm": 0.0019025634974241257, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0012159594680177328, | |
| "grad_norm": 0.0017240965971723199, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001266624445851805, | |
| "grad_norm": 0.004399719648063183, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001266624445851805, | |
| "eval_loss": 0.0031658420339226723, | |
| "eval_runtime": 2911.9261, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 1.427, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001317289423685877, | |
| "grad_norm": 0.0012040651636198163, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0013679544015199492, | |
| "grad_norm": 0.003693037200719118, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0014186193793540216, | |
| "grad_norm": 0.0011092451168224216, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0014692843571880937, | |
| "grad_norm": 0.0016942309448495507, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0015199493350221659, | |
| "grad_norm": 0.0008918177918531001, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015706143128562382, | |
| "grad_norm": 0.0006368808099068701, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0016212792906903104, | |
| "grad_norm": 0.000868378090672195, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0016719442685243825, | |
| "grad_norm": 0.0012875277316197753, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0017226092463584546, | |
| "grad_norm": 0.001103079877793789, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.001773274224192527, | |
| "grad_norm": 0.00059116369811818, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018239392020265991, | |
| "grad_norm": 0.0006111768889240921, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0018746041798606713, | |
| "grad_norm": 0.0005457017105072737, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0019252691576947436, | |
| "grad_norm": 0.0006407860200852156, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0019759341355288155, | |
| "grad_norm": 0.025094201788306236, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002026599113362888, | |
| "grad_norm": 0.0004499408241827041, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020772640911969602, | |
| "grad_norm": 0.0005782039952464402, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0021279290690310324, | |
| "grad_norm": 0.0006991780246607959, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0021785940468651045, | |
| "grad_norm": 0.0004409195389598608, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0022292590246991767, | |
| "grad_norm": 0.0004564693372230977, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002279924002533249, | |
| "grad_norm": 0.0004852621059399098, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002330588980367321, | |
| "grad_norm": 0.0004319900181144476, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.002381253958201393, | |
| "grad_norm": 0.0018095594132319093, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0024319189360354656, | |
| "grad_norm": 0.0007907446706667542, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0024825839138695378, | |
| "grad_norm": 0.002268951153382659, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00253324889170361, | |
| "grad_norm": 0.09747433662414551, | |
| "learning_rate": 0.0, | |
| "loss": 0.0004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00253324889170361, | |
| "eval_loss": 0.001949921017512679, | |
| "eval_runtime": 2915.0095, | |
| "eval_samples_per_second": 2.851, | |
| "eval_steps_per_second": 1.426, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.41887283560448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |