{ "best_metric": 1.2952526807785034, "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": 0.18750134110450745, "learning_rate": 2e-05, "loss": 1.1205, "step": 1 }, { "epoch": 0.0024848578971890046, "eval_loss": 1.5502378940582275, "eval_runtime": 1.16, "eval_samples_per_second": 43.105, "eval_steps_per_second": 11.207, "step": 1 }, { "epoch": 0.004969715794378009, "grad_norm": 0.2050493061542511, "learning_rate": 4e-05, "loss": 1.1432, "step": 2 }, { "epoch": 0.007454573691567014, "grad_norm": 0.23336094617843628, "learning_rate": 6e-05, "loss": 1.1906, "step": 3 }, { "epoch": 0.009939431588756018, "grad_norm": 0.2642175257205963, "learning_rate": 8e-05, "loss": 1.2138, "step": 4 }, { "epoch": 0.012424289485945022, "grad_norm": 0.2873069941997528, "learning_rate": 0.0001, "loss": 1.2386, "step": 5 }, { "epoch": 0.014909147383134027, "grad_norm": 0.3289160430431366, "learning_rate": 9.997539658034168e-05, "loss": 1.3354, "step": 6 }, { "epoch": 0.017394005280323033, "grad_norm": 0.3904762864112854, "learning_rate": 9.990161322484486e-05, "loss": 1.3982, "step": 7 }, { "epoch": 0.019878863177512036, "grad_norm": 0.5013667941093445, "learning_rate": 9.977873061452552e-05, "loss": 1.4638, "step": 8 }, { "epoch": 0.02236372107470104, "grad_norm": 0.7098448872566223, "learning_rate": 9.96068831197139e-05, "loss": 1.6263, "step": 9 }, { "epoch": 0.024848578971890044, "grad_norm": 0.9447751641273499, "learning_rate": 9.938625865312251e-05, "loss": 1.6602, "step": 10 }, { "epoch": 0.02733343686907905, "grad_norm": 1.1918106079101562, "learning_rate": 9.911709846436641e-05, "loss": 1.7242, "step": 11 }, { "epoch": 0.029818294766268055, "grad_norm": 1.6665799617767334, "learning_rate": 9.879969687616027e-05, "loss": 1.9561, "step": 12 }, { "epoch": 0.03230315266345706, "grad_norm": 0.5675529837608337, "learning_rate": 9.84344009624807e-05, "loss": 1.0769, "step": 13 }, { "epoch": 0.034788010560646065, "grad_norm": 0.7401061058044434, "learning_rate": 9.80216101690461e-05, "loss": 1.1726, "step": 14 }, { "epoch": 0.03727286845783507, "grad_norm": 0.6895852088928223, "learning_rate": 9.756177587652856e-05, "loss": 1.1816, "step": 15 }, { "epoch": 0.03975772635502407, "grad_norm": 0.6290579438209534, "learning_rate": 9.705540090697575e-05, "loss": 1.2386, "step": 16 }, { "epoch": 0.042242584252213077, "grad_norm": 0.550385057926178, "learning_rate": 9.650303897398232e-05, "loss": 1.2365, "step": 17 }, { "epoch": 0.04472744214940208, "grad_norm": 0.4426826238632202, "learning_rate": 9.590529407721231e-05, "loss": 1.2245, "step": 18 }, { "epoch": 0.047212300046591084, "grad_norm": 0.3795057535171509, "learning_rate": 9.526281984193436e-05, "loss": 1.2883, "step": 19 }, { "epoch": 0.04969715794378009, "grad_norm": 1.7804195880889893, "learning_rate": 9.4576318804292e-05, "loss": 1.3227, "step": 20 }, { "epoch": 0.05218201584096909, "grad_norm": 0.46404874324798584, "learning_rate": 9.384654164309083e-05, "loss": 1.5023, "step": 21 }, { "epoch": 0.0546668737381581, "grad_norm": 0.63600754737854, "learning_rate": 9.30742863589421e-05, "loss": 1.5474, "step": 22 }, { "epoch": 0.057151731635347106, "grad_norm": 0.8300634622573853, "learning_rate": 9.226039740166091e-05, "loss": 1.5191, "step": 23 }, { "epoch": 0.05963658953253611, "grad_norm": 1.0977858304977417, "learning_rate": 9.140576474687264e-05, "loss": 1.877, "step": 24 }, { "epoch": 0.06212144742972511, "grad_norm": 1.9869602918624878, "learning_rate": 9.051132292283771e-05, "loss": 2.3241, "step": 25 }, { "epoch": 0.06212144742972511, "eval_loss": 1.3513970375061035, "eval_runtime": 1.193, "eval_samples_per_second": 41.912, "eval_steps_per_second": 10.897, "step": 25 }, { "epoch": 0.06460630532691412, "grad_norm": 0.1354065090417862, "learning_rate": 8.957804998855866e-05, "loss": 1.0299, "step": 26 }, { "epoch": 0.06709116322410312, "grad_norm": 0.14030440151691437, "learning_rate": 8.860696646428693e-05, "loss": 1.1064, "step": 27 }, { "epoch": 0.06957602112129213, "grad_norm": 0.16048847138881683, "learning_rate": 8.759913421559902e-05, "loss": 1.1247, "step": 28 }, { "epoch": 0.07206087901848113, "grad_norm": 0.16564105451107025, "learning_rate": 8.655565529226198e-05, "loss": 1.1864, "step": 29 }, { "epoch": 0.07454573691567014, "grad_norm": 0.18728169798851013, "learning_rate": 8.547767072315835e-05, "loss": 1.1942, "step": 30 }, { "epoch": 0.07703059481285914, "grad_norm": 0.21532979607582092, "learning_rate": 8.436635926858759e-05, "loss": 1.2285, "step": 31 }, { "epoch": 0.07951545271004815, "grad_norm": 0.25429460406303406, "learning_rate": 8.322293613130917e-05, "loss": 1.2947, "step": 32 }, { "epoch": 0.08200031060723714, "grad_norm": 0.3389357328414917, "learning_rate": 8.204865162773613e-05, "loss": 1.3498, "step": 33 }, { "epoch": 0.08448516850442615, "grad_norm": 0.44248735904693604, "learning_rate": 8.084478982073247e-05, "loss": 1.4682, "step": 34 }, { "epoch": 0.08697002640161516, "grad_norm": 0.5417070388793945, "learning_rate": 7.961266711550922e-05, "loss": 1.4128, "step": 35 }, { "epoch": 0.08945488429880416, "grad_norm": 0.7389299869537354, "learning_rate": 7.835363082015468e-05, "loss": 1.6869, "step": 36 }, { "epoch": 0.09193974219599317, "grad_norm": 1.0323277711868286, "learning_rate": 7.706905767237288e-05, "loss": 1.7113, "step": 37 }, { "epoch": 0.09442460009318217, "grad_norm": 0.17391887307167053, "learning_rate": 7.576035233404096e-05, "loss": 1.0076, "step": 38 }, { "epoch": 0.09690945799037118, "grad_norm": 0.13513757288455963, "learning_rate": 7.442894585523218e-05, "loss": 1.1018, "step": 39 }, { "epoch": 0.09939431588756018, "grad_norm": 0.1373761147260666, "learning_rate": 7.307629410938363e-05, "loss": 1.0876, "step": 40 }, { "epoch": 0.10187917378474919, "grad_norm": 0.15485402941703796, "learning_rate": 7.170387620131993e-05, "loss": 1.154, "step": 41 }, { "epoch": 0.10436403168193818, "grad_norm": 0.169663667678833, "learning_rate": 7.031319284987394e-05, "loss": 1.2091, "step": 42 }, { "epoch": 0.1068488895791272, "grad_norm": 0.18936441838741302, "learning_rate": 6.890576474687263e-05, "loss": 1.2159, "step": 43 }, { "epoch": 0.1093337474763162, "grad_norm": 0.22018368542194366, "learning_rate": 6.7483130894283e-05, "loss": 1.2628, "step": 44 }, { "epoch": 0.1118186053735052, "grad_norm": 0.2780289053916931, "learning_rate": 6.604684692133597e-05, "loss": 1.3283, "step": 45 }, { "epoch": 0.11430346327069421, "grad_norm": 0.35780683159828186, "learning_rate": 6.459848338346861e-05, "loss": 1.3937, "step": 46 }, { "epoch": 0.11678832116788321, "grad_norm": 0.546146035194397, "learning_rate": 6.313962404494496e-05, "loss": 1.4614, "step": 47 }, { "epoch": 0.11927317906507222, "grad_norm": 0.687628448009491, "learning_rate": 6.167186414703289e-05, "loss": 1.4176, "step": 48 }, { "epoch": 0.12175803696226122, "grad_norm": 1.150036096572876, "learning_rate": 6.019680866363139e-05, "loss": 1.7219, "step": 49 }, { "epoch": 0.12424289485945023, "grad_norm": 2.3322739601135254, "learning_rate": 5.8716070546254966e-05, "loss": 2.1274, "step": 50 }, { "epoch": 0.12424289485945023, "eval_loss": 1.307538628578186, "eval_runtime": 1.1894, "eval_samples_per_second": 42.037, "eval_steps_per_second": 10.93, "step": 50 }, { "epoch": 0.12672775275663922, "grad_norm": 0.1314828097820282, "learning_rate": 5.7231268960295e-05, "loss": 1.0635, "step": 51 }, { "epoch": 0.12921261065382825, "grad_norm": 0.14226771891117096, "learning_rate": 5.574402751448614e-05, "loss": 1.135, "step": 52 }, { "epoch": 0.13169746855101724, "grad_norm": 0.16140902042388916, "learning_rate": 5.425597248551387e-05, "loss": 1.0796, "step": 53 }, { "epoch": 0.13418232644820624, "grad_norm": 0.1799178272485733, "learning_rate": 5.2768731039705e-05, "loss": 1.1422, "step": 54 }, { "epoch": 0.13666718434539524, "grad_norm": 0.2081109583377838, "learning_rate": 5.128392945374505e-05, "loss": 1.2189, "step": 55 }, { "epoch": 0.13915204224258426, "grad_norm": 0.25022587180137634, "learning_rate": 4.980319133636863e-05, "loss": 1.2379, "step": 56 }, { "epoch": 0.14163690013977326, "grad_norm": 0.28561145067214966, "learning_rate": 4.83281358529671e-05, "loss": 1.2227, "step": 57 }, { "epoch": 0.14412175803696226, "grad_norm": 0.39062267541885376, "learning_rate": 4.686037595505507e-05, "loss": 1.4685, "step": 58 }, { "epoch": 0.14660661593415125, "grad_norm": 0.44714751839637756, "learning_rate": 4.54015166165314e-05, "loss": 1.391, "step": 59 }, { "epoch": 0.14909147383134028, "grad_norm": 0.5737501382827759, "learning_rate": 4.395315307866405e-05, "loss": 1.4773, "step": 60 }, { "epoch": 0.15157633172852927, "grad_norm": 0.6805304884910583, "learning_rate": 4.2516869105717004e-05, "loss": 1.5433, "step": 61 }, { "epoch": 0.15406118962571827, "grad_norm": 0.9832828044891357, "learning_rate": 4.109423525312738e-05, "loss": 1.7847, "step": 62 }, { "epoch": 0.1565460475229073, "grad_norm": 0.14597496390342712, "learning_rate": 3.968680715012606e-05, "loss": 1.0738, "step": 63 }, { "epoch": 0.1590309054200963, "grad_norm": 0.12474174797534943, "learning_rate": 3.829612379868006e-05, "loss": 1.0669, "step": 64 }, { "epoch": 0.1615157633172853, "grad_norm": 0.13938696682453156, "learning_rate": 3.692370589061639e-05, "loss": 1.0996, "step": 65 }, { "epoch": 0.16400062121447428, "grad_norm": 0.14947223663330078, "learning_rate": 3.557105414476782e-05, "loss": 1.1537, "step": 66 }, { "epoch": 0.1664854791116633, "grad_norm": 0.15758228302001953, "learning_rate": 3.423964766595906e-05, "loss": 1.1751, "step": 67 }, { "epoch": 0.1689703370088523, "grad_norm": 0.1946917325258255, "learning_rate": 3.293094232762715e-05, "loss": 1.2175, "step": 68 }, { "epoch": 0.1714551949060413, "grad_norm": 0.22615738213062286, "learning_rate": 3.164636917984534e-05, "loss": 1.2667, "step": 69 }, { "epoch": 0.17394005280323033, "grad_norm": 0.2879005968570709, "learning_rate": 3.0387332884490805e-05, "loss": 1.3261, "step": 70 }, { "epoch": 0.17642491070041932, "grad_norm": 0.385571151971817, "learning_rate": 2.9155210179267546e-05, "loss": 1.3998, "step": 71 }, { "epoch": 0.17890976859760832, "grad_norm": 0.4972687363624573, "learning_rate": 2.7951348372263875e-05, "loss": 1.4713, "step": 72 }, { "epoch": 0.18139462649479732, "grad_norm": 0.6449961066246033, "learning_rate": 2.677706386869083e-05, "loss": 1.5434, "step": 73 }, { "epoch": 0.18387948439198634, "grad_norm": 0.8163850903511047, "learning_rate": 2.5633640731412412e-05, "loss": 1.5494, "step": 74 }, { "epoch": 0.18636434228917534, "grad_norm": 1.7719392776489258, "learning_rate": 2.4522329276841663e-05, "loss": 2.154, "step": 75 }, { "epoch": 0.18636434228917534, "eval_loss": 1.3009710311889648, "eval_runtime": 1.193, "eval_samples_per_second": 41.91, "eval_steps_per_second": 10.897, "step": 75 }, { "epoch": 0.18884920018636434, "grad_norm": 0.11202926188707352, "learning_rate": 2.3444344707738015e-05, "loss": 1.0467, "step": 76 }, { "epoch": 0.19133405808355336, "grad_norm": 0.12705056369304657, "learning_rate": 2.2400865784401e-05, "loss": 1.1197, "step": 77 }, { "epoch": 0.19381891598074236, "grad_norm": 0.13754263520240784, "learning_rate": 2.1393033535713093e-05, "loss": 1.1236, "step": 78 }, { "epoch": 0.19630377387793135, "grad_norm": 0.14906519651412964, "learning_rate": 2.0421950011441354e-05, "loss": 1.1776, "step": 79 }, { "epoch": 0.19878863177512035, "grad_norm": 0.18295283615589142, "learning_rate": 1.9488677077162295e-05, "loss": 1.1789, "step": 80 }, { "epoch": 0.20127348967230937, "grad_norm": 0.2125210464000702, "learning_rate": 1.8594235253127375e-05, "loss": 1.2862, "step": 81 }, { "epoch": 0.20375834756949837, "grad_norm": 0.26508280634880066, "learning_rate": 1.77396025983391e-05, "loss": 1.2848, "step": 82 }, { "epoch": 0.20624320546668737, "grad_norm": 0.35227707028388977, "learning_rate": 1.6925713641057904e-05, "loss": 1.4362, "step": 83 }, { "epoch": 0.20872806336387636, "grad_norm": 0.44621512293815613, "learning_rate": 1.6153458356909176e-05, "loss": 1.4328, "step": 84 }, { "epoch": 0.2112129212610654, "grad_norm": 0.5334073305130005, "learning_rate": 1.5423681195707997e-05, "loss": 1.3808, "step": 85 }, { "epoch": 0.2136977791582544, "grad_norm": 0.6840953826904297, "learning_rate": 1.4737180158065644e-05, "loss": 1.5155, "step": 86 }, { "epoch": 0.21618263705544338, "grad_norm": 1.0756030082702637, "learning_rate": 1.4094705922787687e-05, "loss": 1.8925, "step": 87 }, { "epoch": 0.2186674949526324, "grad_norm": 0.15060825645923615, "learning_rate": 1.3496961026017687e-05, "loss": 1.0787, "step": 88 }, { "epoch": 0.2211523528498214, "grad_norm": 0.12421015650033951, "learning_rate": 1.2944599093024267e-05, "loss": 1.075, "step": 89 }, { "epoch": 0.2236372107470104, "grad_norm": 0.12722982466220856, "learning_rate": 1.2438224123471442e-05, "loss": 1.0812, "step": 90 }, { "epoch": 0.2261220686441994, "grad_norm": 0.1435864120721817, "learning_rate": 1.1978389830953907e-05, "loss": 1.1586, "step": 91 }, { "epoch": 0.22860692654138842, "grad_norm": 0.1644206941127777, "learning_rate": 1.1565599037519316e-05, "loss": 1.1476, "step": 92 }, { "epoch": 0.23109178443857742, "grad_norm": 0.19284330308437347, "learning_rate": 1.1200303123839742e-05, "loss": 1.2184, "step": 93 }, { "epoch": 0.23357664233576642, "grad_norm": 0.22463686764240265, "learning_rate": 1.088290153563358e-05, "loss": 1.3173, "step": 94 }, { "epoch": 0.23606150023295544, "grad_norm": 0.2764645218849182, "learning_rate": 1.0613741346877497e-05, "loss": 1.3155, "step": 95 }, { "epoch": 0.23854635813014444, "grad_norm": 0.3586321175098419, "learning_rate": 1.0393116880286118e-05, "loss": 1.4269, "step": 96 }, { "epoch": 0.24103121602733343, "grad_norm": 0.4705638289451599, "learning_rate": 1.0221269385474488e-05, "loss": 1.3914, "step": 97 }, { "epoch": 0.24351607392452243, "grad_norm": 0.6012833714485168, "learning_rate": 1.0098386775155147e-05, "loss": 1.5772, "step": 98 }, { "epoch": 0.24600093182171145, "grad_norm": 0.7574616074562073, "learning_rate": 1.0024603419658329e-05, "loss": 1.5515, "step": 99 }, { "epoch": 0.24848578971890045, "grad_norm": 1.7547069787979126, "learning_rate": 1e-05, "loss": 2.0062, "step": 100 }, { "epoch": 0.24848578971890045, "eval_loss": 1.2952526807785034, "eval_runtime": 1.2125, "eval_samples_per_second": 41.238, "eval_steps_per_second": 10.722, "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 }