| { | |
| "best_metric": 0.5070711374282837, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.19061234214915415, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003812246842983083, | |
| "grad_norm": 0.2486516684293747, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003812246842983083, | |
| "eval_loss": 0.6581751704216003, | |
| "eval_runtime": 97.7016, | |
| "eval_samples_per_second": 18.096, | |
| "eval_steps_per_second": 2.262, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007624493685966166, | |
| "grad_norm": 0.297057181596756, | |
| "learning_rate": 0.0001, | |
| "loss": 0.615, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01143674052894925, | |
| "grad_norm": 0.2097022533416748, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.6107, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015248987371932332, | |
| "grad_norm": 0.4043019711971283, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.6057, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019061234214915415, | |
| "grad_norm": 0.28308504819869995, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.6285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0228734810578985, | |
| "grad_norm": 0.20527686178684235, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02668572790088158, | |
| "grad_norm": 0.1658390760421753, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5477, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.030497974743864665, | |
| "grad_norm": 0.17288026213645935, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5283, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.034310221586847746, | |
| "grad_norm": 0.37299853563308716, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5563, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03812246842983083, | |
| "grad_norm": 0.15514422953128815, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041934715272813915, | |
| "grad_norm": 0.16363877058029175, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5594, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.045746962115797, | |
| "grad_norm": 0.17318545281887054, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5484, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.049559208958780084, | |
| "grad_norm": 0.1284005492925644, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5368, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05337145580176316, | |
| "grad_norm": 0.11773151159286499, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5136, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.057183702644746245, | |
| "grad_norm": 0.12845490872859955, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06099594948772933, | |
| "grad_norm": 0.12426241487264633, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4966, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06480819633071241, | |
| "grad_norm": 0.12707611918449402, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06862044317369549, | |
| "grad_norm": 0.1259024292230606, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5172, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07243269001667858, | |
| "grad_norm": 0.12900516390800476, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5277, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07624493685966166, | |
| "grad_norm": 0.1307690441608429, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4994, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08005718370264475, | |
| "grad_norm": 0.1397053748369217, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5204, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08386943054562783, | |
| "grad_norm": 0.13340778648853302, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4789, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0876816773886109, | |
| "grad_norm": 0.13642898201942444, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4858, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.091493924231594, | |
| "grad_norm": 0.14385145902633667, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4907, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09530617107457708, | |
| "grad_norm": 0.1719496101140976, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09530617107457708, | |
| "eval_loss": 0.5152958035469055, | |
| "eval_runtime": 97.4737, | |
| "eval_samples_per_second": 18.138, | |
| "eval_steps_per_second": 2.267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09911841791756017, | |
| "grad_norm": 0.10792405158281326, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5462, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10293066476054324, | |
| "grad_norm": 0.11865006387233734, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5619, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10674291160352632, | |
| "grad_norm": 0.11148977279663086, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5233, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11055515844650941, | |
| "grad_norm": 0.12350525707006454, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5382, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11436740528949249, | |
| "grad_norm": 0.11989864706993103, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11817965213247558, | |
| "grad_norm": 0.12140996754169464, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.544, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12199189897545866, | |
| "grad_norm": 0.12538982927799225, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5021, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12580414581844174, | |
| "grad_norm": 0.13155509531497955, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5056, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12961639266142483, | |
| "grad_norm": 0.13385814428329468, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.533, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13342863950440792, | |
| "grad_norm": 0.13156044483184814, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13724088634739098, | |
| "grad_norm": 0.14174248278141022, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4998, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14105313319037407, | |
| "grad_norm": 0.15541359782218933, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4809, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14486538003335717, | |
| "grad_norm": 0.11500518769025803, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5598, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14867762687634023, | |
| "grad_norm": 0.09926284849643707, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.497, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15248987371932332, | |
| "grad_norm": 0.11181768029928207, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1563021205623064, | |
| "grad_norm": 0.10740184783935547, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5102, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1601143674052895, | |
| "grad_norm": 0.115020751953125, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5418, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16392661424827257, | |
| "grad_norm": 0.11854977160692215, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4986, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16773886109125566, | |
| "grad_norm": 0.11391133815050125, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4962, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17155110793423875, | |
| "grad_norm": 0.12022404372692108, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5195, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1753633547772218, | |
| "grad_norm": 0.1278664618730545, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5102, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1791756016202049, | |
| "grad_norm": 0.1261085867881775, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5061, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.182987848463188, | |
| "grad_norm": 0.13194888830184937, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4893, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1868000953061711, | |
| "grad_norm": 0.1402422934770584, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5238, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "grad_norm": 0.1567613035440445, | |
| "learning_rate": 0.0, | |
| "loss": 0.4982, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19061234214915415, | |
| "eval_loss": 0.5070711374282837, | |
| "eval_runtime": 97.9047, | |
| "eval_samples_per_second": 18.058, | |
| "eval_steps_per_second": 2.257, | |
| "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": 5.979273768059535e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |