{ "best_metric": 5.2339911460876465, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 1.015228426395939, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01015228426395939, "grad_norm": 0.46062880754470825, "learning_rate": 5e-06, "loss": 5.3841, "step": 1 }, { "epoch": 0.01015228426395939, "eval_loss": 5.5305962562561035, "eval_runtime": 8.7087, "eval_samples_per_second": 19.061, "eval_steps_per_second": 9.531, "step": 1 }, { "epoch": 0.02030456852791878, "grad_norm": 0.5978866815567017, "learning_rate": 1e-05, "loss": 5.4053, "step": 2 }, { "epoch": 0.030456852791878174, "grad_norm": 0.4448310434818268, "learning_rate": 1.5e-05, "loss": 5.3689, "step": 3 }, { "epoch": 0.04060913705583756, "grad_norm": 0.507191002368927, "learning_rate": 2e-05, "loss": 5.4424, "step": 4 }, { "epoch": 0.050761421319796954, "grad_norm": 0.4688023626804352, "learning_rate": 2.5e-05, "loss": 5.4252, "step": 5 }, { "epoch": 0.06091370558375635, "grad_norm": 0.4471573531627655, "learning_rate": 3e-05, "loss": 5.3927, "step": 6 }, { "epoch": 0.07106598984771574, "grad_norm": 0.45171481370925903, "learning_rate": 3.5e-05, "loss": 5.3751, "step": 7 }, { "epoch": 0.08121827411167512, "grad_norm": 0.6176170706748962, "learning_rate": 4e-05, "loss": 5.4215, "step": 8 }, { "epoch": 0.09137055837563451, "grad_norm": 0.5099933743476868, "learning_rate": 4.5e-05, "loss": 5.3422, "step": 9 }, { "epoch": 0.10152284263959391, "grad_norm": 0.48276761174201965, "learning_rate": 5e-05, "loss": 5.4263, "step": 10 }, { "epoch": 0.1116751269035533, "grad_norm": 0.5048362612724304, "learning_rate": 5.500000000000001e-05, "loss": 5.3427, "step": 11 }, { "epoch": 0.1218274111675127, "grad_norm": 0.5130631923675537, "learning_rate": 6e-05, "loss": 5.3817, "step": 12 }, { "epoch": 0.1319796954314721, "grad_norm": 0.5273154377937317, "learning_rate": 6.500000000000001e-05, "loss": 5.3019, "step": 13 }, { "epoch": 0.14213197969543148, "grad_norm": 0.523825466632843, "learning_rate": 7e-05, "loss": 5.2535, "step": 14 }, { "epoch": 0.15228426395939088, "grad_norm": 0.6113125681877136, "learning_rate": 7.500000000000001e-05, "loss": 5.3172, "step": 15 }, { "epoch": 0.16243654822335024, "grad_norm": 0.5640417337417603, "learning_rate": 8e-05, "loss": 5.2758, "step": 16 }, { "epoch": 0.17258883248730963, "grad_norm": 0.4186924397945404, "learning_rate": 8.5e-05, "loss": 5.2586, "step": 17 }, { "epoch": 0.18274111675126903, "grad_norm": 0.5193726420402527, "learning_rate": 9e-05, "loss": 5.2615, "step": 18 }, { "epoch": 0.19289340101522842, "grad_norm": 0.5647014379501343, "learning_rate": 9.5e-05, "loss": 5.2652, "step": 19 }, { "epoch": 0.20304568527918782, "grad_norm": 0.5719868540763855, "learning_rate": 0.0001, "loss": 5.1955, "step": 20 }, { "epoch": 0.2131979695431472, "grad_norm": 0.6991127133369446, "learning_rate": 9.999238475781957e-05, "loss": 5.1646, "step": 21 }, { "epoch": 0.2233502538071066, "grad_norm": 0.7082369327545166, "learning_rate": 9.99695413509548e-05, "loss": 5.1052, "step": 22 }, { "epoch": 0.233502538071066, "grad_norm": 0.7457136511802673, "learning_rate": 9.99314767377287e-05, "loss": 5.1863, "step": 23 }, { "epoch": 0.2436548223350254, "grad_norm": 1.6564850807189941, "learning_rate": 9.987820251299122e-05, "loss": 5.0987, "step": 24 }, { "epoch": 0.25380710659898476, "grad_norm": 5.510101318359375, "learning_rate": 9.980973490458728e-05, "loss": 5.5984, "step": 25 }, { "epoch": 0.2639593908629442, "grad_norm": 4.215838432312012, "learning_rate": 9.972609476841367e-05, "loss": 5.5124, "step": 26 }, { "epoch": 0.27411167512690354, "grad_norm": 1.8195075988769531, "learning_rate": 9.962730758206611e-05, "loss": 5.4004, "step": 27 }, { "epoch": 0.28426395939086296, "grad_norm": 1.5931973457336426, "learning_rate": 9.951340343707852e-05, "loss": 5.3794, "step": 28 }, { "epoch": 0.29441624365482233, "grad_norm": 0.6483675241470337, "learning_rate": 9.938441702975689e-05, "loss": 5.3566, "step": 29 }, { "epoch": 0.30456852791878175, "grad_norm": 0.3973766267299652, "learning_rate": 9.924038765061042e-05, "loss": 5.2972, "step": 30 }, { "epoch": 0.3147208121827411, "grad_norm": 0.3534790277481079, "learning_rate": 9.908135917238321e-05, "loss": 5.2902, "step": 31 }, { "epoch": 0.3248730964467005, "grad_norm": 0.3970736861228943, "learning_rate": 9.890738003669029e-05, "loss": 5.2949, "step": 32 }, { "epoch": 0.3350253807106599, "grad_norm": 0.37264251708984375, "learning_rate": 9.871850323926177e-05, "loss": 5.2944, "step": 33 }, { "epoch": 0.34517766497461927, "grad_norm": 0.3872509002685547, "learning_rate": 9.851478631379982e-05, "loss": 5.326, "step": 34 }, { "epoch": 0.3553299492385787, "grad_norm": 0.3853321969509125, "learning_rate": 9.829629131445342e-05, "loss": 5.2708, "step": 35 }, { "epoch": 0.36548223350253806, "grad_norm": 0.39588385820388794, "learning_rate": 9.806308479691595e-05, "loss": 5.3228, "step": 36 }, { "epoch": 0.3756345177664975, "grad_norm": 0.4093726575374603, "learning_rate": 9.781523779815179e-05, "loss": 5.2831, "step": 37 }, { "epoch": 0.38578680203045684, "grad_norm": 0.4420938491821289, "learning_rate": 9.755282581475769e-05, "loss": 5.2103, "step": 38 }, { "epoch": 0.39593908629441626, "grad_norm": 0.5512685775756836, "learning_rate": 9.727592877996585e-05, "loss": 5.1775, "step": 39 }, { "epoch": 0.40609137055837563, "grad_norm": 0.3994300067424774, "learning_rate": 9.698463103929542e-05, "loss": 5.2478, "step": 40 }, { "epoch": 0.41624365482233505, "grad_norm": 0.5147640705108643, "learning_rate": 9.667902132486009e-05, "loss": 5.1743, "step": 41 }, { "epoch": 0.4263959390862944, "grad_norm": 0.6237267851829529, "learning_rate": 9.635919272833938e-05, "loss": 5.2249, "step": 42 }, { "epoch": 0.4365482233502538, "grad_norm": 0.5305359363555908, "learning_rate": 9.602524267262203e-05, "loss": 5.2915, "step": 43 }, { "epoch": 0.4467005076142132, "grad_norm": 0.4987878203392029, "learning_rate": 9.567727288213005e-05, "loss": 5.253, "step": 44 }, { "epoch": 0.45685279187817257, "grad_norm": 0.6333546042442322, "learning_rate": 9.53153893518325e-05, "loss": 5.1612, "step": 45 }, { "epoch": 0.467005076142132, "grad_norm": 0.7043673396110535, "learning_rate": 9.493970231495835e-05, "loss": 5.1424, "step": 46 }, { "epoch": 0.47715736040609136, "grad_norm": 0.6457162499427795, "learning_rate": 9.45503262094184e-05, "loss": 5.1876, "step": 47 }, { "epoch": 0.4873096446700508, "grad_norm": 0.9820389151573181, "learning_rate": 9.414737964294636e-05, "loss": 5.0792, "step": 48 }, { "epoch": 0.49746192893401014, "grad_norm": 2.78731369972229, "learning_rate": 9.373098535696979e-05, "loss": 5.5062, "step": 49 }, { "epoch": 0.5076142131979695, "grad_norm": 2.0711777210235596, "learning_rate": 9.330127018922194e-05, "loss": 5.4469, "step": 50 }, { "epoch": 0.5076142131979695, "eval_loss": 5.311061859130859, "eval_runtime": 8.7447, "eval_samples_per_second": 18.983, "eval_steps_per_second": 9.491, "step": 50 }, { "epoch": 0.5177664974619289, "grad_norm": 0.99236661195755, "learning_rate": 9.285836503510562e-05, "loss": 5.3363, "step": 51 }, { "epoch": 0.5279187817258884, "grad_norm": 0.48146185278892517, "learning_rate": 9.24024048078213e-05, "loss": 5.3438, "step": 52 }, { "epoch": 0.5380710659898477, "grad_norm": 0.33013349771499634, "learning_rate": 9.193352839727121e-05, "loss": 5.3068, "step": 53 }, { "epoch": 0.5482233502538071, "grad_norm": 0.37118765711784363, "learning_rate": 9.145187862775209e-05, "loss": 5.306, "step": 54 }, { "epoch": 0.5583756345177665, "grad_norm": 0.4362952411174774, "learning_rate": 9.09576022144496e-05, "loss": 5.2849, "step": 55 }, { "epoch": 0.5685279187817259, "grad_norm": 0.3819132149219513, "learning_rate": 9.045084971874738e-05, "loss": 5.3258, "step": 56 }, { "epoch": 0.5786802030456852, "grad_norm": 0.3916621804237366, "learning_rate": 8.993177550236464e-05, "loss": 5.3383, "step": 57 }, { "epoch": 0.5888324873096447, "grad_norm": 0.36510735750198364, "learning_rate": 8.940053768033609e-05, "loss": 5.2607, "step": 58 }, { "epoch": 0.5989847715736041, "grad_norm": 0.40830719470977783, "learning_rate": 8.885729807284856e-05, "loss": 5.3212, "step": 59 }, { "epoch": 0.6091370558375635, "grad_norm": 0.4307074248790741, "learning_rate": 8.83022221559489e-05, "loss": 5.2596, "step": 60 }, { "epoch": 0.6192893401015228, "grad_norm": 0.3730439245700836, "learning_rate": 8.773547901113862e-05, "loss": 5.2363, "step": 61 }, { "epoch": 0.6294416243654822, "grad_norm": 0.4428587555885315, "learning_rate": 8.715724127386972e-05, "loss": 5.267, "step": 62 }, { "epoch": 0.6395939086294417, "grad_norm": 0.41558074951171875, "learning_rate": 8.656768508095853e-05, "loss": 5.1866, "step": 63 }, { "epoch": 0.649746192893401, "grad_norm": 0.4241006672382355, "learning_rate": 8.596699001693255e-05, "loss": 5.1834, "step": 64 }, { "epoch": 0.6598984771573604, "grad_norm": 0.3360666036605835, "learning_rate": 8.535533905932738e-05, "loss": 5.2194, "step": 65 }, { "epoch": 0.6700507614213198, "grad_norm": 0.38096800446510315, "learning_rate": 8.473291852294987e-05, "loss": 5.2324, "step": 66 }, { "epoch": 0.6802030456852792, "grad_norm": 0.437884122133255, "learning_rate": 8.409991800312493e-05, "loss": 5.2587, "step": 67 }, { "epoch": 0.6903553299492385, "grad_norm": 0.48057064414024353, "learning_rate": 8.345653031794292e-05, "loss": 5.2374, "step": 68 }, { "epoch": 0.700507614213198, "grad_norm": 0.5798227787017822, "learning_rate": 8.280295144952536e-05, "loss": 5.1645, "step": 69 }, { "epoch": 0.7106598984771574, "grad_norm": 0.5949220061302185, "learning_rate": 8.213938048432697e-05, "loss": 5.1196, "step": 70 }, { "epoch": 0.7208121827411168, "grad_norm": 0.6557019948959351, "learning_rate": 8.146601955249188e-05, "loss": 5.1316, "step": 71 }, { "epoch": 0.7309644670050761, "grad_norm": 0.7752095460891724, "learning_rate": 8.07830737662829e-05, "loss": 5.0944, "step": 72 }, { "epoch": 0.7411167512690355, "grad_norm": 0.8926941156387329, "learning_rate": 8.009075115760243e-05, "loss": 5.3464, "step": 73 }, { "epoch": 0.751269035532995, "grad_norm": 0.7516569495201111, "learning_rate": 7.938926261462366e-05, "loss": 5.3015, "step": 74 }, { "epoch": 0.7614213197969543, "grad_norm": 0.6225847005844116, "learning_rate": 7.86788218175523e-05, "loss": 5.3173, "step": 75 }, { "epoch": 0.7715736040609137, "grad_norm": 0.47938278317451477, "learning_rate": 7.795964517353735e-05, "loss": 5.3143, "step": 76 }, { "epoch": 0.7817258883248731, "grad_norm": 0.3764425814151764, "learning_rate": 7.723195175075136e-05, "loss": 5.3017, "step": 77 }, { "epoch": 0.7918781725888325, "grad_norm": 0.3587036430835724, "learning_rate": 7.649596321166024e-05, "loss": 5.2366, "step": 78 }, { "epoch": 0.8020304568527918, "grad_norm": 0.3250347673892975, "learning_rate": 7.575190374550272e-05, "loss": 5.2564, "step": 79 }, { "epoch": 0.8121827411167513, "grad_norm": 0.345753937959671, "learning_rate": 7.500000000000001e-05, "loss": 5.2704, "step": 80 }, { "epoch": 0.8223350253807107, "grad_norm": 0.3820163905620575, "learning_rate": 7.424048101231686e-05, "loss": 5.3212, "step": 81 }, { "epoch": 0.8324873096446701, "grad_norm": 0.40871894359588623, "learning_rate": 7.347357813929454e-05, "loss": 5.2279, "step": 82 }, { "epoch": 0.8426395939086294, "grad_norm": 0.36811622977256775, "learning_rate": 7.269952498697734e-05, "loss": 5.263, "step": 83 }, { "epoch": 0.8527918781725888, "grad_norm": 0.3945890963077545, "learning_rate": 7.191855733945387e-05, "loss": 5.309, "step": 84 }, { "epoch": 0.8629441624365483, "grad_norm": 0.37406954169273376, "learning_rate": 7.113091308703498e-05, "loss": 5.2704, "step": 85 }, { "epoch": 0.8730964467005076, "grad_norm": 0.39915502071380615, "learning_rate": 7.033683215379002e-05, "loss": 5.2693, "step": 86 }, { "epoch": 0.883248730964467, "grad_norm": 0.4481967091560364, "learning_rate": 6.953655642446368e-05, "loss": 5.2332, "step": 87 }, { "epoch": 0.8934010152284264, "grad_norm": 0.4243590235710144, "learning_rate": 6.873032967079561e-05, "loss": 5.2426, "step": 88 }, { "epoch": 0.9035532994923858, "grad_norm": 0.46772047877311707, "learning_rate": 6.7918397477265e-05, "loss": 5.1668, "step": 89 }, { "epoch": 0.9137055837563451, "grad_norm": 0.4974723756313324, "learning_rate": 6.710100716628344e-05, "loss": 5.17, "step": 90 }, { "epoch": 0.9238578680203046, "grad_norm": 0.4955981373786926, "learning_rate": 6.627840772285784e-05, "loss": 5.2168, "step": 91 }, { "epoch": 0.934010152284264, "grad_norm": 0.4544804096221924, "learning_rate": 6.545084971874738e-05, "loss": 5.218, "step": 92 }, { "epoch": 0.9441624365482234, "grad_norm": 0.5566396117210388, "learning_rate": 6.461858523613684e-05, "loss": 5.1191, "step": 93 }, { "epoch": 0.9543147208121827, "grad_norm": 0.5591332316398621, "learning_rate": 6.378186779084995e-05, "loss": 5.0513, "step": 94 }, { "epoch": 0.9644670050761421, "grad_norm": 0.6510249972343445, "learning_rate": 6.294095225512603e-05, "loss": 5.0533, "step": 95 }, { "epoch": 0.9746192893401016, "grad_norm": 0.8038920760154724, "learning_rate": 6.209609477998338e-05, "loss": 5.0682, "step": 96 }, { "epoch": 0.9847715736040609, "grad_norm": 0.5465517640113831, "learning_rate": 6.124755271719325e-05, "loss": 5.3038, "step": 97 }, { "epoch": 0.9949238578680203, "grad_norm": 0.4467344582080841, "learning_rate": 6.0395584540887963e-05, "loss": 5.2282, "step": 98 }, { "epoch": 1.0050761421319796, "grad_norm": 0.6803540587425232, "learning_rate": 5.9540449768827246e-05, "loss": 7.978, "step": 99 }, { "epoch": 1.015228426395939, "grad_norm": 0.3697003424167633, "learning_rate": 5.868240888334653e-05, "loss": 5.1768, "step": 100 }, { "epoch": 1.015228426395939, "eval_loss": 5.2339911460876465, "eval_runtime": 8.769, "eval_samples_per_second": 18.93, "eval_steps_per_second": 9.465, "step": 100 } ], "logging_steps": 1, "max_steps": 200, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 50, "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": false }, "attributes": {} } }, "total_flos": 5.681942422880256e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }