| { | |
| "best_metric": 1.7024426460266113, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.56657223796034, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0113314447592068, | |
| "grad_norm": 0.3384282886981964, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0113314447592068, | |
| "eval_loss": 1.8638567924499512, | |
| "eval_runtime": 1.4119, | |
| "eval_samples_per_second": 105.531, | |
| "eval_steps_per_second": 13.457, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0226628895184136, | |
| "grad_norm": 0.35116004943847656, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0339943342776204, | |
| "grad_norm": 0.32675451040267944, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6902, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": 0.39519521594047546, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.32231006026268005, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7109, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0679886685552408, | |
| "grad_norm": 0.3306005299091339, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07932011331444759, | |
| "grad_norm": 0.24623461067676544, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6435, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "grad_norm": 0.25914400815963745, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7818, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10198300283286119, | |
| "grad_norm": 0.2576405107975006, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7594, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11331444759206799, | |
| "grad_norm": 0.22233405709266663, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.7605, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12464589235127478, | |
| "grad_norm": 0.25532472133636475, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.7194, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1359773371104816, | |
| "grad_norm": 0.252788782119751, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.7752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14730878186968838, | |
| "grad_norm": 0.2589229941368103, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.7019, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15864022662889518, | |
| "grad_norm": 0.28450360894203186, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.7985, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16997167138810199, | |
| "grad_norm": 0.2775594890117645, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7915, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1813031161473088, | |
| "grad_norm": 0.2907847464084625, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.6802, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19263456090651557, | |
| "grad_norm": 0.2851549983024597, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9592, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20396600566572237, | |
| "grad_norm": 0.32117509841918945, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.8445, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21529745042492918, | |
| "grad_norm": 0.3233829438686371, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.9, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22662889518413598, | |
| "grad_norm": 0.3336826264858246, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23796033994334279, | |
| "grad_norm": 0.3345506191253662, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9463, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24929178470254956, | |
| "grad_norm": 0.37882643938064575, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.8697, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26062322946175637, | |
| "grad_norm": 0.20541392266750336, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6108, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2719546742209632, | |
| "grad_norm": 0.19089502096176147, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6219, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "grad_norm": 0.19573427736759186, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5632, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "eval_loss": 1.7306195497512817, | |
| "eval_runtime": 1.3699, | |
| "eval_samples_per_second": 108.767, | |
| "eval_steps_per_second": 13.87, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29461756373937675, | |
| "grad_norm": 0.21815790235996246, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.7345, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3059490084985836, | |
| "grad_norm": 0.2108701467514038, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.5752, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31728045325779036, | |
| "grad_norm": 0.2015771120786667, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5707, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3286118980169972, | |
| "grad_norm": 0.20463882386684418, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.587, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33994334277620397, | |
| "grad_norm": 0.22213023900985718, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.6546, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35127478753541075, | |
| "grad_norm": 0.24201658368110657, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7489, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3626062322946176, | |
| "grad_norm": 0.18713782727718353, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.6503, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37393767705382436, | |
| "grad_norm": 0.20224328339099884, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.6441, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38526912181303113, | |
| "grad_norm": 0.20836849510669708, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6769, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39660056657223797, | |
| "grad_norm": 0.20321877300739288, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.40793201133144474, | |
| "grad_norm": 0.23479226231575012, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6496, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4192634560906516, | |
| "grad_norm": 0.2573692500591278, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6024, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43059490084985835, | |
| "grad_norm": 0.24458742141723633, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.7716, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.44192634560906513, | |
| "grad_norm": 0.2757667899131775, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.867, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45325779036827196, | |
| "grad_norm": 0.22761981189250946, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.8444, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46458923512747874, | |
| "grad_norm": 0.2908417284488678, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7983, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47592067988668557, | |
| "grad_norm": 0.29157117009162903, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7737, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48725212464589235, | |
| "grad_norm": 0.3470527231693268, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7958, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4985835694050991, | |
| "grad_norm": 0.37411051988601685, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.762, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.509915014164306, | |
| "grad_norm": 0.1717747300863266, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5212464589235127, | |
| "grad_norm": 0.16150543093681335, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.4846, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5325779036827195, | |
| "grad_norm": 0.1521836221218109, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.661, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5439093484419264, | |
| "grad_norm": 0.19446030259132385, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.6943, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5552407932011332, | |
| "grad_norm": 0.19089248776435852, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.5123, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "grad_norm": 0.2053840011358261, | |
| "learning_rate": 0.0, | |
| "loss": 1.5716, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "eval_loss": 1.7024426460266113, | |
| "eval_runtime": 1.3758, | |
| "eval_samples_per_second": 108.303, | |
| "eval_steps_per_second": 13.81, | |
| "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": 5, | |
| "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": 1236088022630400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |