| { | |
| "best_metric": 0.8287712335586548, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3812246842983083, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007624493685966166, | |
| "grad_norm": 0.273327499628067, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007624493685966166, | |
| "eval_loss": 0.934563934803009, | |
| "eval_runtime": 12.2603, | |
| "eval_samples_per_second": 144.205, | |
| "eval_steps_per_second": 18.026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015248987371932332, | |
| "grad_norm": 0.31604793667793274, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9409, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0228734810578985, | |
| "grad_norm": 0.26551634073257446, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.8929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.030497974743864665, | |
| "grad_norm": 0.24841269850730896, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9061, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03812246842983083, | |
| "grad_norm": 0.2744283676147461, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9127, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.045746962115797, | |
| "grad_norm": 0.264932781457901, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05337145580176316, | |
| "grad_norm": 0.246871680021286, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8858, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06099594948772933, | |
| "grad_norm": 0.2222467064857483, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8231, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06862044317369549, | |
| "grad_norm": 0.224148690700531, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8685, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07624493685966166, | |
| "grad_norm": 0.2204771637916565, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8598, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08386943054562783, | |
| "grad_norm": 0.2148129940032959, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8643, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.091493924231594, | |
| "grad_norm": 0.2276252657175064, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8292, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09911841791756017, | |
| "grad_norm": 0.16194580495357513, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9297, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10674291160352632, | |
| "grad_norm": 0.1492803692817688, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8669, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11436740528949249, | |
| "grad_norm": 0.1596936732530594, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8862, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12199189897545866, | |
| "grad_norm": 0.15809616446495056, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8595, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12961639266142483, | |
| "grad_norm": 0.1597907990217209, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8863, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13724088634739098, | |
| "grad_norm": 0.15602456033229828, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8556, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14486538003335717, | |
| "grad_norm": 0.1547441929578781, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8208, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15248987371932332, | |
| "grad_norm": 0.16280899941921234, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1601143674052895, | |
| "grad_norm": 0.17006684839725494, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8499, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16773886109125566, | |
| "grad_norm": 0.1722775101661682, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8458, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1753633547772218, | |
| "grad_norm": 0.1805761754512787, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8157, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.182987848463188, | |
| "grad_norm": 0.18934600055217743, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "grad_norm": 0.22315742075443268, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "eval_loss": 0.8377934694290161, | |
| "eval_runtime": 12.1988, | |
| "eval_samples_per_second": 144.932, | |
| "eval_steps_per_second": 18.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19823683583512033, | |
| "grad_norm": 0.15700483322143555, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8346, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2058613295210865, | |
| "grad_norm": 0.1602972149848938, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8255, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21348582320705264, | |
| "grad_norm": 0.15739409625530243, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.842, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22111031689301883, | |
| "grad_norm": 0.15054009854793549, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8599, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22873481057898498, | |
| "grad_norm": 0.1502337008714676, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.817, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23635930426495116, | |
| "grad_norm": 0.14839516580104828, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8335, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.24398379795091732, | |
| "grad_norm": 0.1509093940258026, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8419, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2516082916368835, | |
| "grad_norm": 0.15149198472499847, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8169, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25923278532284966, | |
| "grad_norm": 0.15918795764446259, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.859, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.26685727900881584, | |
| "grad_norm": 0.1778258979320526, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8393, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.27448177269478197, | |
| "grad_norm": 0.19277341663837433, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8147, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.28210626638074815, | |
| "grad_norm": 0.19680185616016388, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.78, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.28973076006671433, | |
| "grad_norm": 0.12966406345367432, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8441, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.29735525375268046, | |
| "grad_norm": 0.12343523651361465, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8377, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.30497974743864664, | |
| "grad_norm": 0.12981387972831726, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8426, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3126042411246128, | |
| "grad_norm": 0.13032592833042145, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.84, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.320228734810579, | |
| "grad_norm": 0.1364886462688446, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8459, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.32785322849654513, | |
| "grad_norm": 0.13743382692337036, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8038, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3354777221825113, | |
| "grad_norm": 0.14321595430374146, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8594, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3431022158684775, | |
| "grad_norm": 0.139565110206604, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8038, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3507267095544436, | |
| "grad_norm": 0.15720701217651367, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8524, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3583512032404098, | |
| "grad_norm": 0.16059865057468414, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8119, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.365975696926376, | |
| "grad_norm": 0.1649278700351715, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7992, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3736001906123422, | |
| "grad_norm": 0.17470909655094147, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8197, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3812246842983083, | |
| "grad_norm": 0.21436592936515808, | |
| "learning_rate": 0.0, | |
| "loss": 0.8206, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3812246842983083, | |
| "eval_loss": 0.8287712335586548, | |
| "eval_runtime": 12.2583, | |
| "eval_samples_per_second": 144.228, | |
| "eval_steps_per_second": 18.029, | |
| "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": 5.913400764792832e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |