{ "best_metric": 1.425083041191101, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 0.24848578971890045, "eval_steps": 25, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0024848578971890046, "grad_norm": 2.2064015865325928, "learning_rate": 2e-05, "loss": 1.3872, "step": 1 }, { "epoch": 0.0024848578971890046, "eval_loss": 2.3529415130615234, "eval_runtime": 0.5026, "eval_samples_per_second": 99.477, "eval_steps_per_second": 25.864, "step": 1 }, { "epoch": 0.004969715794378009, "grad_norm": 2.8333449363708496, "learning_rate": 4e-05, "loss": 1.4444, "step": 2 }, { "epoch": 0.007454573691567014, "grad_norm": 1.8522814512252808, "learning_rate": 6e-05, "loss": 1.5417, "step": 3 }, { "epoch": 0.009939431588756018, "grad_norm": 0.7707993388175964, "learning_rate": 8e-05, "loss": 1.5648, "step": 4 }, { "epoch": 0.012424289485945022, "grad_norm": 0.8538352251052856, "learning_rate": 0.0001, "loss": 1.6446, "step": 5 }, { "epoch": 0.014909147383134027, "grad_norm": 1.292691946029663, "learning_rate": 9.997539658034168e-05, "loss": 1.8205, "step": 6 }, { "epoch": 0.017394005280323033, "grad_norm": 1.3566771745681763, "learning_rate": 9.990161322484486e-05, "loss": 1.888, "step": 7 }, { "epoch": 0.019878863177512036, "grad_norm": 1.3478772640228271, "learning_rate": 9.977873061452552e-05, "loss": 2.0025, "step": 8 }, { "epoch": 0.02236372107470104, "grad_norm": 2.3724148273468018, "learning_rate": 9.96068831197139e-05, "loss": 2.3861, "step": 9 }, { "epoch": 0.024848578971890044, "grad_norm": 2.5542187690734863, "learning_rate": 9.938625865312251e-05, "loss": 2.4441, "step": 10 }, { "epoch": 0.02733343686907905, "grad_norm": 2.9612715244293213, "learning_rate": 9.911709846436641e-05, "loss": 2.4473, "step": 11 }, { "epoch": 0.029818294766268055, "grad_norm": 3.946715831756592, "learning_rate": 9.879969687616027e-05, "loss": 2.796, "step": 12 }, { "epoch": 0.03230315266345706, "grad_norm": 0.6914235949516296, "learning_rate": 9.84344009624807e-05, "loss": 1.2153, "step": 13 }, { "epoch": 0.034788010560646065, "grad_norm": 0.5879468321800232, "learning_rate": 9.80216101690461e-05, "loss": 1.3014, "step": 14 }, { "epoch": 0.03727286845783507, "grad_norm": 0.4194982051849365, "learning_rate": 9.756177587652856e-05, "loss": 1.3002, "step": 15 }, { "epoch": 0.03975772635502407, "grad_norm": 0.43755513429641724, "learning_rate": 9.705540090697575e-05, "loss": 1.3616, "step": 16 }, { "epoch": 0.042242584252213077, "grad_norm": 0.35957348346710205, "learning_rate": 9.650303897398232e-05, "loss": 1.3768, "step": 17 }, { "epoch": 0.04472744214940208, "grad_norm": 0.4144904911518097, "learning_rate": 9.590529407721231e-05, "loss": 1.4022, "step": 18 }, { "epoch": 0.047212300046591084, "grad_norm": 0.46732762455940247, "learning_rate": 9.526281984193436e-05, "loss": 1.4593, "step": 19 }, { "epoch": 0.04969715794378009, "grad_norm": 0.5609594583511353, "learning_rate": 9.4576318804292e-05, "loss": 1.5165, "step": 20 }, { "epoch": 0.05218201584096909, "grad_norm": 0.7970541715621948, "learning_rate": 9.384654164309083e-05, "loss": 1.7275, "step": 21 }, { "epoch": 0.0546668737381581, "grad_norm": 1.0460487604141235, "learning_rate": 9.30742863589421e-05, "loss": 1.8141, "step": 22 }, { "epoch": 0.057151731635347106, "grad_norm": 1.3908549547195435, "learning_rate": 9.226039740166091e-05, "loss": 1.8613, "step": 23 }, { "epoch": 0.05963658953253611, "grad_norm": 1.8160243034362793, "learning_rate": 9.140576474687264e-05, "loss": 2.2734, "step": 24 }, { "epoch": 0.06212144742972511, "grad_norm": 2.9735653400421143, "learning_rate": 9.051132292283771e-05, "loss": 2.7456, "step": 25 }, { "epoch": 0.06212144742972511, "eval_loss": 1.5912128686904907, "eval_runtime": 0.502, "eval_samples_per_second": 99.599, "eval_steps_per_second": 25.896, "step": 25 }, { "epoch": 0.06460630532691412, "grad_norm": 0.4997400939464569, "learning_rate": 8.957804998855866e-05, "loss": 1.1591, "step": 26 }, { "epoch": 0.06709116322410312, "grad_norm": 0.6131523847579956, "learning_rate": 8.860696646428693e-05, "loss": 1.2452, "step": 27 }, { "epoch": 0.06957602112129213, "grad_norm": 0.5031818747520447, "learning_rate": 8.759913421559902e-05, "loss": 1.2703, "step": 28 }, { "epoch": 0.07206087901848113, "grad_norm": 0.5141401886940002, "learning_rate": 8.655565529226198e-05, "loss": 1.3225, "step": 29 }, { "epoch": 0.07454573691567014, "grad_norm": 0.4961668848991394, "learning_rate": 8.547767072315835e-05, "loss": 1.3459, "step": 30 }, { "epoch": 0.07703059481285914, "grad_norm": 0.4645865857601166, "learning_rate": 8.436635926858759e-05, "loss": 1.3681, "step": 31 }, { "epoch": 0.07951545271004815, "grad_norm": 0.4720369577407837, "learning_rate": 8.322293613130917e-05, "loss": 1.4398, "step": 32 }, { "epoch": 0.08200031060723714, "grad_norm": 0.5064677596092224, "learning_rate": 8.204865162773613e-05, "loss": 1.4973, "step": 33 }, { "epoch": 0.08448516850442615, "grad_norm": 0.7844948172569275, "learning_rate": 8.084478982073247e-05, "loss": 1.6429, "step": 34 }, { "epoch": 0.08697002640161516, "grad_norm": 1.0937235355377197, "learning_rate": 7.961266711550922e-05, "loss": 1.655, "step": 35 }, { "epoch": 0.08945488429880416, "grad_norm": 1.5023084878921509, "learning_rate": 7.835363082015468e-05, "loss": 1.9494, "step": 36 }, { "epoch": 0.09193974219599317, "grad_norm": 1.9704169034957886, "learning_rate": 7.706905767237288e-05, "loss": 2.0052, "step": 37 }, { "epoch": 0.09442460009318217, "grad_norm": 0.3317461609840393, "learning_rate": 7.576035233404096e-05, "loss": 1.1168, "step": 38 }, { "epoch": 0.09690945799037118, "grad_norm": 0.3098306357860565, "learning_rate": 7.442894585523218e-05, "loss": 1.2064, "step": 39 }, { "epoch": 0.09939431588756018, "grad_norm": 0.2434069812297821, "learning_rate": 7.307629410938363e-05, "loss": 1.2017, "step": 40 }, { "epoch": 0.10187917378474919, "grad_norm": 0.2517208158969879, "learning_rate": 7.170387620131993e-05, "loss": 1.2654, "step": 41 }, { "epoch": 0.10436403168193818, "grad_norm": 0.2552037537097931, "learning_rate": 7.031319284987394e-05, "loss": 1.3208, "step": 42 }, { "epoch": 0.1068488895791272, "grad_norm": 0.2989708483219147, "learning_rate": 6.890576474687263e-05, "loss": 1.3169, "step": 43 }, { "epoch": 0.1093337474763162, "grad_norm": 0.38415053486824036, "learning_rate": 6.7483130894283e-05, "loss": 1.3684, "step": 44 }, { "epoch": 0.1118186053735052, "grad_norm": 0.40901339054107666, "learning_rate": 6.604684692133597e-05, "loss": 1.464, "step": 45 }, { "epoch": 0.11430346327069421, "grad_norm": 0.5247498750686646, "learning_rate": 6.459848338346861e-05, "loss": 1.5311, "step": 46 }, { "epoch": 0.11678832116788321, "grad_norm": 0.756410539150238, "learning_rate": 6.313962404494496e-05, "loss": 1.6284, "step": 47 }, { "epoch": 0.11927317906507222, "grad_norm": 0.9791819453239441, "learning_rate": 6.167186414703289e-05, "loss": 1.6159, "step": 48 }, { "epoch": 0.12175803696226122, "grad_norm": 1.455810546875, "learning_rate": 6.019680866363139e-05, "loss": 1.939, "step": 49 }, { "epoch": 0.12424289485945023, "grad_norm": 2.2369606494903564, "learning_rate": 5.8716070546254966e-05, "loss": 2.421, "step": 50 }, { "epoch": 0.12424289485945023, "eval_loss": 1.4801632165908813, "eval_runtime": 0.5016, "eval_samples_per_second": 99.69, "eval_steps_per_second": 25.919, "step": 50 }, { "epoch": 0.12672775275663922, "grad_norm": 0.2692347466945648, "learning_rate": 5.7231268960295e-05, "loss": 1.1845, "step": 51 }, { "epoch": 0.12921261065382825, "grad_norm": 0.2334340512752533, "learning_rate": 5.574402751448614e-05, "loss": 1.2396, "step": 52 }, { "epoch": 0.13169746855101724, "grad_norm": 0.23105919361114502, "learning_rate": 5.425597248551387e-05, "loss": 1.1817, "step": 53 }, { "epoch": 0.13418232644820624, "grad_norm": 0.2562418580055237, "learning_rate": 5.2768731039705e-05, "loss": 1.2478, "step": 54 }, { "epoch": 0.13666718434539524, "grad_norm": 0.2922269403934479, "learning_rate": 5.128392945374505e-05, "loss": 1.3124, "step": 55 }, { "epoch": 0.13915204224258426, "grad_norm": 0.3430224061012268, "learning_rate": 4.980319133636863e-05, "loss": 1.3298, "step": 56 }, { "epoch": 0.14163690013977326, "grad_norm": 0.37545251846313477, "learning_rate": 4.83281358529671e-05, "loss": 1.3167, "step": 57 }, { "epoch": 0.14412175803696226, "grad_norm": 0.4372154474258423, "learning_rate": 4.686037595505507e-05, "loss": 1.5611, "step": 58 }, { "epoch": 0.14660661593415125, "grad_norm": 0.675260603427887, "learning_rate": 4.54015166165314e-05, "loss": 1.5241, "step": 59 }, { "epoch": 0.14909147383134028, "grad_norm": 0.8273709416389465, "learning_rate": 4.395315307866405e-05, "loss": 1.5969, "step": 60 }, { "epoch": 0.15157633172852927, "grad_norm": 1.0075353384017944, "learning_rate": 4.2516869105717004e-05, "loss": 1.7115, "step": 61 }, { "epoch": 0.15406118962571827, "grad_norm": 1.6686378717422485, "learning_rate": 4.109423525312738e-05, "loss": 1.9804, "step": 62 }, { "epoch": 0.1565460475229073, "grad_norm": 0.19904345273971558, "learning_rate": 3.968680715012606e-05, "loss": 1.1648, "step": 63 }, { "epoch": 0.1590309054200963, "grad_norm": 0.1799841821193695, "learning_rate": 3.829612379868006e-05, "loss": 1.1689, "step": 64 }, { "epoch": 0.1615157633172853, "grad_norm": 0.19480910897254944, "learning_rate": 3.692370589061639e-05, "loss": 1.1933, "step": 65 }, { "epoch": 0.16400062121447428, "grad_norm": 0.19751323759555817, "learning_rate": 3.557105414476782e-05, "loss": 1.2421, "step": 66 }, { "epoch": 0.1664854791116633, "grad_norm": 0.21054387092590332, "learning_rate": 3.423964766595906e-05, "loss": 1.2749, "step": 67 }, { "epoch": 0.1689703370088523, "grad_norm": 0.25906527042388916, "learning_rate": 3.293094232762715e-05, "loss": 1.3187, "step": 68 }, { "epoch": 0.1714551949060413, "grad_norm": 0.3064195513725281, "learning_rate": 3.164636917984534e-05, "loss": 1.3584, "step": 69 }, { "epoch": 0.17394005280323033, "grad_norm": 0.38761624693870544, "learning_rate": 3.0387332884490805e-05, "loss": 1.4219, "step": 70 }, { "epoch": 0.17642491070041932, "grad_norm": 0.4902038276195526, "learning_rate": 2.9155210179267546e-05, "loss": 1.4855, "step": 71 }, { "epoch": 0.17890976859760832, "grad_norm": 0.674696147441864, "learning_rate": 2.7951348372263875e-05, "loss": 1.611, "step": 72 }, { "epoch": 0.18139462649479732, "grad_norm": 1.0593940019607544, "learning_rate": 2.677706386869083e-05, "loss": 1.71, "step": 73 }, { "epoch": 0.18387948439198634, "grad_norm": 1.1859633922576904, "learning_rate": 2.5633640731412412e-05, "loss": 1.6977, "step": 74 }, { "epoch": 0.18636434228917534, "grad_norm": 2.17313551902771, "learning_rate": 2.4522329276841663e-05, "loss": 2.2829, "step": 75 }, { "epoch": 0.18636434228917534, "eval_loss": 1.4373173713684082, "eval_runtime": 0.5019, "eval_samples_per_second": 99.622, "eval_steps_per_second": 25.902, "step": 75 }, { "epoch": 0.18884920018636434, "grad_norm": 0.15144409239292145, "learning_rate": 2.3444344707738015e-05, "loss": 1.1409, "step": 76 }, { "epoch": 0.19133405808355336, "grad_norm": 0.1701895296573639, "learning_rate": 2.2400865784401e-05, "loss": 1.2128, "step": 77 }, { "epoch": 0.19381891598074236, "grad_norm": 0.1913847178220749, "learning_rate": 2.1393033535713093e-05, "loss": 1.2066, "step": 78 }, { "epoch": 0.19630377387793135, "grad_norm": 0.209688201546669, "learning_rate": 2.0421950011441354e-05, "loss": 1.2567, "step": 79 }, { "epoch": 0.19878863177512035, "grad_norm": 0.2626892328262329, "learning_rate": 1.9488677077162295e-05, "loss": 1.2534, "step": 80 }, { "epoch": 0.20127348967230937, "grad_norm": 0.28468379378318787, "learning_rate": 1.8594235253127375e-05, "loss": 1.3711, "step": 81 }, { "epoch": 0.20375834756949837, "grad_norm": 0.4000290036201477, "learning_rate": 1.77396025983391e-05, "loss": 1.3722, "step": 82 }, { "epoch": 0.20624320546668737, "grad_norm": 0.5061511397361755, "learning_rate": 1.6925713641057904e-05, "loss": 1.5405, "step": 83 }, { "epoch": 0.20872806336387636, "grad_norm": 0.615593671798706, "learning_rate": 1.6153458356909176e-05, "loss": 1.5413, "step": 84 }, { "epoch": 0.2112129212610654, "grad_norm": 0.8124218583106995, "learning_rate": 1.5423681195707997e-05, "loss": 1.5224, "step": 85 }, { "epoch": 0.2136977791582544, "grad_norm": 0.9472981691360474, "learning_rate": 1.4737180158065644e-05, "loss": 1.6382, "step": 86 }, { "epoch": 0.21618263705544338, "grad_norm": 1.6688803434371948, "learning_rate": 1.4094705922787687e-05, "loss": 2.0258, "step": 87 }, { "epoch": 0.2186674949526324, "grad_norm": 0.21361282467842102, "learning_rate": 1.3496961026017687e-05, "loss": 1.1669, "step": 88 }, { "epoch": 0.2211523528498214, "grad_norm": 0.16145868599414825, "learning_rate": 1.2944599093024267e-05, "loss": 1.1676, "step": 89 }, { "epoch": 0.2236372107470104, "grad_norm": 0.16978983581066132, "learning_rate": 1.2438224123471442e-05, "loss": 1.1627, "step": 90 }, { "epoch": 0.2261220686441994, "grad_norm": 0.20442353188991547, "learning_rate": 1.1978389830953907e-05, "loss": 1.24, "step": 91 }, { "epoch": 0.22860692654138842, "grad_norm": 0.20694726705551147, "learning_rate": 1.1565599037519316e-05, "loss": 1.2345, "step": 92 }, { "epoch": 0.23109178443857742, "grad_norm": 0.26132482290267944, "learning_rate": 1.1200303123839742e-05, "loss": 1.2939, "step": 93 }, { "epoch": 0.23357664233576642, "grad_norm": 0.2953537702560425, "learning_rate": 1.088290153563358e-05, "loss": 1.3983, "step": 94 }, { "epoch": 0.23606150023295544, "grad_norm": 0.3531050980091095, "learning_rate": 1.0613741346877497e-05, "loss": 1.3998, "step": 95 }, { "epoch": 0.23854635813014444, "grad_norm": 0.4567805230617523, "learning_rate": 1.0393116880286118e-05, "loss": 1.5085, "step": 96 }, { "epoch": 0.24103121602733343, "grad_norm": 0.6118177771568298, "learning_rate": 1.0221269385474488e-05, "loss": 1.5085, "step": 97 }, { "epoch": 0.24351607392452243, "grad_norm": 0.8797485828399658, "learning_rate": 1.0098386775155147e-05, "loss": 1.7005, "step": 98 }, { "epoch": 0.24600093182171145, "grad_norm": 1.1694400310516357, "learning_rate": 1.0024603419658329e-05, "loss": 1.6887, "step": 99 }, { "epoch": 0.24848578971890045, "grad_norm": 2.3600339889526367, "learning_rate": 1e-05, "loss": 2.1697, "step": 100 }, { "epoch": 0.24848578971890045, "eval_loss": 1.425083041191101, "eval_runtime": 0.5024, "eval_samples_per_second": 99.514, "eval_steps_per_second": 25.874, "step": 100 } ], "logging_steps": 1, "max_steps": 100, "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": 1.666832784162816e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }