| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014009649145849203, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.004824572924602e-05, | |
| "grad_norm": 6.222772121429443, | |
| "learning_rate": 9.99930017513135e-05, | |
| "loss": 1.1076, | |
| "num_input_tokens_seen": 16384, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014009649145849205, | |
| "grad_norm": 6.042057037353516, | |
| "learning_rate": 9.998600350262697e-05, | |
| "loss": 1.1086, | |
| "num_input_tokens_seen": 32768, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021014473718773804, | |
| "grad_norm": 7.119229316711426, | |
| "learning_rate": 9.997900525394046e-05, | |
| "loss": 1.4047, | |
| "num_input_tokens_seen": 49152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002801929829169841, | |
| "grad_norm": 7.133191108703613, | |
| "learning_rate": 9.997200700525395e-05, | |
| "loss": 1.3921, | |
| "num_input_tokens_seen": 65536, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003502412286462301, | |
| "grad_norm": 6.1078338623046875, | |
| "learning_rate": 9.996500875656743e-05, | |
| "loss": 1.3171, | |
| "num_input_tokens_seen": 81920, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004202894743754761, | |
| "grad_norm": 6.466420650482178, | |
| "learning_rate": 9.995801050788092e-05, | |
| "loss": 1.0732, | |
| "num_input_tokens_seen": 97344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004903377201047221, | |
| "grad_norm": 5.578189849853516, | |
| "learning_rate": 9.99510122591944e-05, | |
| "loss": 0.9929, | |
| "num_input_tokens_seen": 113728, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005603859658339682, | |
| "grad_norm": 7.197720527648926, | |
| "learning_rate": 9.994401401050789e-05, | |
| "loss": 1.2512, | |
| "num_input_tokens_seen": 129528, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006304342115632141, | |
| "grad_norm": 6.618913650512695, | |
| "learning_rate": 9.993701576182136e-05, | |
| "loss": 1.3495, | |
| "num_input_tokens_seen": 145704, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007004824572924602, | |
| "grad_norm": 6.955508232116699, | |
| "learning_rate": 9.993001751313485e-05, | |
| "loss": 1.1823, | |
| "num_input_tokens_seen": 161664, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007705307030217062, | |
| "grad_norm": 6.6807074546813965, | |
| "learning_rate": 9.992301926444835e-05, | |
| "loss": 1.1693, | |
| "num_input_tokens_seen": 177960, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008405789487509522, | |
| "grad_norm": 6.784447193145752, | |
| "learning_rate": 9.991602101576183e-05, | |
| "loss": 1.3744, | |
| "num_input_tokens_seen": 194344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009106271944801982, | |
| "grad_norm": 6.7418437004089355, | |
| "learning_rate": 9.990902276707532e-05, | |
| "loss": 1.22, | |
| "num_input_tokens_seen": 210728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009806754402094443, | |
| "grad_norm": 6.43395471572876, | |
| "learning_rate": 9.990202451838879e-05, | |
| "loss": 1.1772, | |
| "num_input_tokens_seen": 227112, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010507236859386903, | |
| "grad_norm": 6.09422492980957, | |
| "learning_rate": 9.989502626970228e-05, | |
| "loss": 1.195, | |
| "num_input_tokens_seen": 243496, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011207719316679364, | |
| "grad_norm": 6.238271236419678, | |
| "learning_rate": 9.988802802101577e-05, | |
| "loss": 1.2623, | |
| "num_input_tokens_seen": 259744, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011908201773971822, | |
| "grad_norm": 6.56187629699707, | |
| "learning_rate": 9.988102977232926e-05, | |
| "loss": 1.2721, | |
| "num_input_tokens_seen": 276128, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012608684231264283, | |
| "grad_norm": 6.818358898162842, | |
| "learning_rate": 9.987403152364275e-05, | |
| "loss": 1.2649, | |
| "num_input_tokens_seen": 292512, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013309166688556743, | |
| "grad_norm": 5.950352191925049, | |
| "learning_rate": 9.986703327495622e-05, | |
| "loss": 1.0024, | |
| "num_input_tokens_seen": 308632, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014009649145849204, | |
| "grad_norm": 6.387479305267334, | |
| "learning_rate": 9.986003502626971e-05, | |
| "loss": 1.2783, | |
| "num_input_tokens_seen": 325016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014710131603141664, | |
| "grad_norm": 6.187346458435059, | |
| "learning_rate": 9.985303677758318e-05, | |
| "loss": 1.1701, | |
| "num_input_tokens_seen": 341384, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015410614060434125, | |
| "grad_norm": 5.371951103210449, | |
| "learning_rate": 9.984603852889667e-05, | |
| "loss": 1.0483, | |
| "num_input_tokens_seen": 357768, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016111096517726585, | |
| "grad_norm": 6.2206807136535645, | |
| "learning_rate": 9.983904028021016e-05, | |
| "loss": 1.2516, | |
| "num_input_tokens_seen": 374152, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0016811578975019044, | |
| "grad_norm": 6.121264457702637, | |
| "learning_rate": 9.983204203152365e-05, | |
| "loss": 1.1506, | |
| "num_input_tokens_seen": 390536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017512061432311504, | |
| "grad_norm": 6.353756904602051, | |
| "learning_rate": 9.982504378283714e-05, | |
| "loss": 1.3118, | |
| "num_input_tokens_seen": 406920, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018212543889603965, | |
| "grad_norm": 6.270686149597168, | |
| "learning_rate": 9.981804553415061e-05, | |
| "loss": 1.0883, | |
| "num_input_tokens_seen": 422728, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0018913026346896425, | |
| "grad_norm": 6.117632865905762, | |
| "learning_rate": 9.98110472854641e-05, | |
| "loss": 1.3346, | |
| "num_input_tokens_seen": 439112, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0019613508804188886, | |
| "grad_norm": 6.429015159606934, | |
| "learning_rate": 9.980404903677759e-05, | |
| "loss": 1.2494, | |
| "num_input_tokens_seen": 455144, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0020313991261481346, | |
| "grad_norm": 6.4467620849609375, | |
| "learning_rate": 9.979705078809107e-05, | |
| "loss": 1.3335, | |
| "num_input_tokens_seen": 470360, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0021014473718773807, | |
| "grad_norm": 6.57926082611084, | |
| "learning_rate": 9.979005253940455e-05, | |
| "loss": 1.2126, | |
| "num_input_tokens_seen": 486120, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0021714956176066267, | |
| "grad_norm": 5.650569915771484, | |
| "learning_rate": 9.978305429071804e-05, | |
| "loss": 1.1363, | |
| "num_input_tokens_seen": 501896, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0022415438633358728, | |
| "grad_norm": 6.380292892456055, | |
| "learning_rate": 9.977605604203153e-05, | |
| "loss": 1.2251, | |
| "num_input_tokens_seen": 517752, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002311592109065119, | |
| "grad_norm": 5.704173564910889, | |
| "learning_rate": 9.976905779334502e-05, | |
| "loss": 1.1685, | |
| "num_input_tokens_seen": 534136, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0023816403547943644, | |
| "grad_norm": 5.342978000640869, | |
| "learning_rate": 9.97620595446585e-05, | |
| "loss": 1.2012, | |
| "num_input_tokens_seen": 550216, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0024516886005236105, | |
| "grad_norm": 5.7014241218566895, | |
| "learning_rate": 9.975506129597198e-05, | |
| "loss": 1.2342, | |
| "num_input_tokens_seen": 566600, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0025217368462528565, | |
| "grad_norm": 6.26229190826416, | |
| "learning_rate": 9.974806304728546e-05, | |
| "loss": 1.2041, | |
| "num_input_tokens_seen": 582984, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0025917850919821026, | |
| "grad_norm": 6.583463191986084, | |
| "learning_rate": 9.974106479859896e-05, | |
| "loss": 1.3021, | |
| "num_input_tokens_seen": 598968, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0026618333377113486, | |
| "grad_norm": 5.58498477935791, | |
| "learning_rate": 9.973406654991245e-05, | |
| "loss": 1.1622, | |
| "num_input_tokens_seen": 614840, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0027318815834405947, | |
| "grad_norm": 5.906906604766846, | |
| "learning_rate": 9.972706830122592e-05, | |
| "loss": 1.1971, | |
| "num_input_tokens_seen": 631224, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0028019298291698407, | |
| "grad_norm": 5.962359428405762, | |
| "learning_rate": 9.972007005253941e-05, | |
| "loss": 1.1326, | |
| "num_input_tokens_seen": 647000, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002871978074899087, | |
| "grad_norm": 6.447500705718994, | |
| "learning_rate": 9.971307180385289e-05, | |
| "loss": 1.0905, | |
| "num_input_tokens_seen": 662480, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002942026320628333, | |
| "grad_norm": 5.7290520668029785, | |
| "learning_rate": 9.970607355516638e-05, | |
| "loss": 1.3585, | |
| "num_input_tokens_seen": 678480, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003012074566357579, | |
| "grad_norm": 6.063445568084717, | |
| "learning_rate": 9.969907530647987e-05, | |
| "loss": 1.2841, | |
| "num_input_tokens_seen": 694256, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003082122812086825, | |
| "grad_norm": 5.302809238433838, | |
| "learning_rate": 9.969207705779335e-05, | |
| "loss": 1.1168, | |
| "num_input_tokens_seen": 710152, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.003152171057816071, | |
| "grad_norm": 5.634128093719482, | |
| "learning_rate": 9.968507880910684e-05, | |
| "loss": 1.0609, | |
| "num_input_tokens_seen": 726184, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003222219303545317, | |
| "grad_norm": 5.652642726898193, | |
| "learning_rate": 9.967808056042032e-05, | |
| "loss": 1.2228, | |
| "num_input_tokens_seen": 742520, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0032922675492745627, | |
| "grad_norm": 5.340751647949219, | |
| "learning_rate": 9.96710823117338e-05, | |
| "loss": 1.0595, | |
| "num_input_tokens_seen": 758904, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0033623157950038087, | |
| "grad_norm": 5.422239780426025, | |
| "learning_rate": 9.966408406304728e-05, | |
| "loss": 1.1161, | |
| "num_input_tokens_seen": 775040, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0034323640407330548, | |
| "grad_norm": 5.29241418838501, | |
| "learning_rate": 9.965708581436077e-05, | |
| "loss": 1.0255, | |
| "num_input_tokens_seen": 790856, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003502412286462301, | |
| "grad_norm": 5.146270275115967, | |
| "learning_rate": 9.965008756567426e-05, | |
| "loss": 0.9762, | |
| "num_input_tokens_seen": 807064, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003572460532191547, | |
| "grad_norm": 5.825758457183838, | |
| "learning_rate": 9.964308931698775e-05, | |
| "loss": 1.2108, | |
| "num_input_tokens_seen": 823448, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.003642508777920793, | |
| "grad_norm": 6.179538726806641, | |
| "learning_rate": 9.963609106830124e-05, | |
| "loss": 1.322, | |
| "num_input_tokens_seen": 838888, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.003712557023650039, | |
| "grad_norm": 6.464454174041748, | |
| "learning_rate": 9.962909281961471e-05, | |
| "loss": 1.5077, | |
| "num_input_tokens_seen": 855272, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.003782605269379285, | |
| "grad_norm": 5.4227294921875, | |
| "learning_rate": 9.96220945709282e-05, | |
| "loss": 1.2679, | |
| "num_input_tokens_seen": 871656, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.003852653515108531, | |
| "grad_norm": 5.949041366577148, | |
| "learning_rate": 9.961509632224169e-05, | |
| "loss": 1.3618, | |
| "num_input_tokens_seen": 888040, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.003922701760837777, | |
| "grad_norm": 6.050904750823975, | |
| "learning_rate": 9.960809807355516e-05, | |
| "loss": 1.3155, | |
| "num_input_tokens_seen": 904400, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.003992750006567023, | |
| "grad_norm": 6.048308849334717, | |
| "learning_rate": 9.960109982486866e-05, | |
| "loss": 1.3131, | |
| "num_input_tokens_seen": 919952, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004062798252296269, | |
| "grad_norm": 5.683863162994385, | |
| "learning_rate": 9.959410157618214e-05, | |
| "loss": 1.1692, | |
| "num_input_tokens_seen": 936336, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.004132846498025515, | |
| "grad_norm": 5.449287414550781, | |
| "learning_rate": 9.958710332749563e-05, | |
| "loss": 1.0613, | |
| "num_input_tokens_seen": 952152, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.004202894743754761, | |
| "grad_norm": 5.31496524810791, | |
| "learning_rate": 9.958010507880912e-05, | |
| "loss": 0.9605, | |
| "num_input_tokens_seen": 967824, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004272942989484007, | |
| "grad_norm": 5.57105016708374, | |
| "learning_rate": 9.957310683012259e-05, | |
| "loss": 1.1701, | |
| "num_input_tokens_seen": 983864, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.004342991235213253, | |
| "grad_norm": 5.3456830978393555, | |
| "learning_rate": 9.956610858143608e-05, | |
| "loss": 1.0995, | |
| "num_input_tokens_seen": 1000248, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.004413039480942499, | |
| "grad_norm": 5.453295707702637, | |
| "learning_rate": 9.955911033274957e-05, | |
| "loss": 1.2413, | |
| "num_input_tokens_seen": 1016632, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0044830877266717455, | |
| "grad_norm": 4.975449562072754, | |
| "learning_rate": 9.955211208406306e-05, | |
| "loss": 1.0961, | |
| "num_input_tokens_seen": 1033016, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004553135972400991, | |
| "grad_norm": 5.542137145996094, | |
| "learning_rate": 9.954511383537655e-05, | |
| "loss": 1.1171, | |
| "num_input_tokens_seen": 1049400, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004623184218130238, | |
| "grad_norm": 5.213950157165527, | |
| "learning_rate": 9.953811558669002e-05, | |
| "loss": 1.2228, | |
| "num_input_tokens_seen": 1065784, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.004693232463859483, | |
| "grad_norm": 5.496099948883057, | |
| "learning_rate": 9.953111733800351e-05, | |
| "loss": 1.1529, | |
| "num_input_tokens_seen": 1082168, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004763280709588729, | |
| "grad_norm": 5.64145565032959, | |
| "learning_rate": 9.952411908931698e-05, | |
| "loss": 1.2301, | |
| "num_input_tokens_seen": 1098024, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.004833328955317975, | |
| "grad_norm": 5.566709995269775, | |
| "learning_rate": 9.951712084063047e-05, | |
| "loss": 1.2679, | |
| "num_input_tokens_seen": 1114408, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.004903377201047221, | |
| "grad_norm": 6.443673133850098, | |
| "learning_rate": 9.951012259194396e-05, | |
| "loss": 1.2313, | |
| "num_input_tokens_seen": 1130792, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0049734254467764675, | |
| "grad_norm": 5.882962226867676, | |
| "learning_rate": 9.950312434325745e-05, | |
| "loss": 1.4304, | |
| "num_input_tokens_seen": 1147176, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.005043473692505713, | |
| "grad_norm": 6.0052666664123535, | |
| "learning_rate": 9.949612609457094e-05, | |
| "loss": 1.3027, | |
| "num_input_tokens_seen": 1160968, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0051135219382349596, | |
| "grad_norm": 5.260256767272949, | |
| "learning_rate": 9.948912784588441e-05, | |
| "loss": 1.1526, | |
| "num_input_tokens_seen": 1177352, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.005183570183964205, | |
| "grad_norm": 5.641814708709717, | |
| "learning_rate": 9.94821295971979e-05, | |
| "loss": 1.0666, | |
| "num_input_tokens_seen": 1193032, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.005253618429693452, | |
| "grad_norm": 5.121115207672119, | |
| "learning_rate": 9.947513134851138e-05, | |
| "loss": 1.2404, | |
| "num_input_tokens_seen": 1208952, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005323666675422697, | |
| "grad_norm": 5.63930082321167, | |
| "learning_rate": 9.946813309982487e-05, | |
| "loss": 1.5127, | |
| "num_input_tokens_seen": 1225000, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.005393714921151944, | |
| "grad_norm": 4.880716800689697, | |
| "learning_rate": 9.946113485113837e-05, | |
| "loss": 1.1484, | |
| "num_input_tokens_seen": 1241384, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.005463763166881189, | |
| "grad_norm": 5.59611177444458, | |
| "learning_rate": 9.945413660245184e-05, | |
| "loss": 1.1678, | |
| "num_input_tokens_seen": 1257680, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.005533811412610436, | |
| "grad_norm": 5.052026271820068, | |
| "learning_rate": 9.944713835376533e-05, | |
| "loss": 1.2207, | |
| "num_input_tokens_seen": 1274064, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0056038596583396815, | |
| "grad_norm": 5.285096168518066, | |
| "learning_rate": 9.944014010507881e-05, | |
| "loss": 1.1457, | |
| "num_input_tokens_seen": 1290448, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005673907904068927, | |
| "grad_norm": 5.4286580085754395, | |
| "learning_rate": 9.94331418563923e-05, | |
| "loss": 1.3047, | |
| "num_input_tokens_seen": 1306832, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005743956149798174, | |
| "grad_norm": 5.937953472137451, | |
| "learning_rate": 9.942614360770578e-05, | |
| "loss": 1.4353, | |
| "num_input_tokens_seen": 1323216, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.005814004395527419, | |
| "grad_norm": 5.129006385803223, | |
| "learning_rate": 9.941914535901927e-05, | |
| "loss": 1.1434, | |
| "num_input_tokens_seen": 1339408, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.005884052641256666, | |
| "grad_norm": 5.179675102233887, | |
| "learning_rate": 9.941214711033276e-05, | |
| "loss": 1.2452, | |
| "num_input_tokens_seen": 1355792, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.005954100886985911, | |
| "grad_norm": 4.912832736968994, | |
| "learning_rate": 9.940514886164624e-05, | |
| "loss": 1.1255, | |
| "num_input_tokens_seen": 1372176, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.006024149132715158, | |
| "grad_norm": 5.190899848937988, | |
| "learning_rate": 9.939815061295973e-05, | |
| "loss": 1.2543, | |
| "num_input_tokens_seen": 1388560, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.006094197378444403, | |
| "grad_norm": 5.1751275062561035, | |
| "learning_rate": 9.939115236427321e-05, | |
| "loss": 1.3145, | |
| "num_input_tokens_seen": 1404944, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.00616424562417365, | |
| "grad_norm": 5.450705528259277, | |
| "learning_rate": 9.938415411558669e-05, | |
| "loss": 1.2844, | |
| "num_input_tokens_seen": 1421328, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0062342938699028955, | |
| "grad_norm": 5.593935012817383, | |
| "learning_rate": 9.937715586690018e-05, | |
| "loss": 1.3284, | |
| "num_input_tokens_seen": 1437464, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006304342115632142, | |
| "grad_norm": 5.156428813934326, | |
| "learning_rate": 9.937015761821367e-05, | |
| "loss": 1.1682, | |
| "num_input_tokens_seen": 1452952, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006374390361361388, | |
| "grad_norm": 4.673638820648193, | |
| "learning_rate": 9.936315936952715e-05, | |
| "loss": 1.004, | |
| "num_input_tokens_seen": 1469336, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.006444438607090634, | |
| "grad_norm": 4.996700763702393, | |
| "learning_rate": 9.935616112084064e-05, | |
| "loss": 1.087, | |
| "num_input_tokens_seen": 1485448, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.00651448685281988, | |
| "grad_norm": 4.817474365234375, | |
| "learning_rate": 9.934916287215412e-05, | |
| "loss": 1.151, | |
| "num_input_tokens_seen": 1501472, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.006584535098549125, | |
| "grad_norm": 5.400479316711426, | |
| "learning_rate": 9.934216462346761e-05, | |
| "loss": 1.3144, | |
| "num_input_tokens_seen": 1516424, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.006654583344278372, | |
| "grad_norm": 5.232216835021973, | |
| "learning_rate": 9.933516637478108e-05, | |
| "loss": 1.0019, | |
| "num_input_tokens_seen": 1532792, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.006724631590007617, | |
| "grad_norm": 5.392521381378174, | |
| "learning_rate": 9.932816812609457e-05, | |
| "loss": 1.3195, | |
| "num_input_tokens_seen": 1548600, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.006794679835736864, | |
| "grad_norm": 5.5280866622924805, | |
| "learning_rate": 9.932116987740806e-05, | |
| "loss": 1.283, | |
| "num_input_tokens_seen": 1564088, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0068647280814661095, | |
| "grad_norm": 4.963179588317871, | |
| "learning_rate": 9.931417162872155e-05, | |
| "loss": 1.2716, | |
| "num_input_tokens_seen": 1580040, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.006934776327195356, | |
| "grad_norm": 4.920302391052246, | |
| "learning_rate": 9.930717338003504e-05, | |
| "loss": 1.088, | |
| "num_input_tokens_seen": 1595880, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.007004824572924602, | |
| "grad_norm": 4.935486793518066, | |
| "learning_rate": 9.930017513134851e-05, | |
| "loss": 1.0122, | |
| "num_input_tokens_seen": 1611864, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007074872818653848, | |
| "grad_norm": 5.099087238311768, | |
| "learning_rate": 9.9293176882662e-05, | |
| "loss": 1.1605, | |
| "num_input_tokens_seen": 1627472, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.007144921064383094, | |
| "grad_norm": 5.3764328956604, | |
| "learning_rate": 9.928617863397548e-05, | |
| "loss": 1.2225, | |
| "num_input_tokens_seen": 1643856, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.00721496931011234, | |
| "grad_norm": 5.281564712524414, | |
| "learning_rate": 9.927918038528898e-05, | |
| "loss": 1.1483, | |
| "num_input_tokens_seen": 1660240, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.007285017555841586, | |
| "grad_norm": 5.395167827606201, | |
| "learning_rate": 9.927218213660247e-05, | |
| "loss": 1.6014, | |
| "num_input_tokens_seen": 1676624, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.007355065801570832, | |
| "grad_norm": 5.322319507598877, | |
| "learning_rate": 9.926518388791594e-05, | |
| "loss": 1.0933, | |
| "num_input_tokens_seen": 1693008, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.007425114047300078, | |
| "grad_norm": 5.301229953765869, | |
| "learning_rate": 9.925818563922943e-05, | |
| "loss": 1.1998, | |
| "num_input_tokens_seen": 1708424, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.0074951622930293236, | |
| "grad_norm": 4.958597183227539, | |
| "learning_rate": 9.92511873905429e-05, | |
| "loss": 1.3285, | |
| "num_input_tokens_seen": 1724808, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.00756521053875857, | |
| "grad_norm": 4.3913960456848145, | |
| "learning_rate": 9.924418914185639e-05, | |
| "loss": 0.9017, | |
| "num_input_tokens_seen": 1740752, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.007635258784487816, | |
| "grad_norm": 5.401021480560303, | |
| "learning_rate": 9.923719089316988e-05, | |
| "loss": 1.3646, | |
| "num_input_tokens_seen": 1755176, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.007705307030217062, | |
| "grad_norm": 4.894444942474365, | |
| "learning_rate": 9.923019264448337e-05, | |
| "loss": 0.9955, | |
| "num_input_tokens_seen": 1771560, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007775355275946308, | |
| "grad_norm": 4.878688335418701, | |
| "learning_rate": 9.922319439579686e-05, | |
| "loss": 1.1766, | |
| "num_input_tokens_seen": 1787944, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.007845403521675554, | |
| "grad_norm": 4.9379777908325195, | |
| "learning_rate": 9.921619614711033e-05, | |
| "loss": 1.1631, | |
| "num_input_tokens_seen": 1803568, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.0079154517674048, | |
| "grad_norm": 5.101811408996582, | |
| "learning_rate": 9.920919789842382e-05, | |
| "loss": 1.2165, | |
| "num_input_tokens_seen": 1819952, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.007985500013134045, | |
| "grad_norm": 5.32574987411499, | |
| "learning_rate": 9.920219964973731e-05, | |
| "loss": 1.3012, | |
| "num_input_tokens_seen": 1835296, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.008055548258863293, | |
| "grad_norm": 5.2391180992126465, | |
| "learning_rate": 9.919520140105079e-05, | |
| "loss": 1.2451, | |
| "num_input_tokens_seen": 1851224, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.008125596504592538, | |
| "grad_norm": 4.865017890930176, | |
| "learning_rate": 9.918820315236427e-05, | |
| "loss": 1.1683, | |
| "num_input_tokens_seen": 1867608, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.008195644750321784, | |
| "grad_norm": 4.943136215209961, | |
| "learning_rate": 9.918120490367776e-05, | |
| "loss": 1.31, | |
| "num_input_tokens_seen": 1883696, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.00826569299605103, | |
| "grad_norm": 4.769871711730957, | |
| "learning_rate": 9.917420665499125e-05, | |
| "loss": 1.1212, | |
| "num_input_tokens_seen": 1900080, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.008335741241780275, | |
| "grad_norm": 4.785780429840088, | |
| "learning_rate": 9.916720840630474e-05, | |
| "loss": 1.2415, | |
| "num_input_tokens_seen": 1916464, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.008405789487509523, | |
| "grad_norm": 4.802333831787109, | |
| "learning_rate": 9.916021015761822e-05, | |
| "loss": 1.0513, | |
| "num_input_tokens_seen": 1932848, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.008475837733238768, | |
| "grad_norm": 5.22212553024292, | |
| "learning_rate": 9.91532119089317e-05, | |
| "loss": 1.2574, | |
| "num_input_tokens_seen": 1949232, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.008545885978968014, | |
| "grad_norm": 5.104204177856445, | |
| "learning_rate": 9.914621366024518e-05, | |
| "loss": 1.0436, | |
| "num_input_tokens_seen": 1964184, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.00861593422469726, | |
| "grad_norm": 5.11055326461792, | |
| "learning_rate": 9.913921541155868e-05, | |
| "loss": 1.1939, | |
| "num_input_tokens_seen": 1980568, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.008685982470426507, | |
| "grad_norm": 4.784866809844971, | |
| "learning_rate": 9.913221716287216e-05, | |
| "loss": 1.2056, | |
| "num_input_tokens_seen": 1996952, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.008756030716155752, | |
| "grad_norm": 4.763037204742432, | |
| "learning_rate": 9.912521891418564e-05, | |
| "loss": 1.1403, | |
| "num_input_tokens_seen": 2013336, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.008826078961884998, | |
| "grad_norm": 4.813408851623535, | |
| "learning_rate": 9.911822066549913e-05, | |
| "loss": 1.1897, | |
| "num_input_tokens_seen": 2029720, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.008896127207614244, | |
| "grad_norm": 4.79008674621582, | |
| "learning_rate": 9.911122241681261e-05, | |
| "loss": 1.2315, | |
| "num_input_tokens_seen": 2046104, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.008966175453343491, | |
| "grad_norm": 4.843508720397949, | |
| "learning_rate": 9.91042241681261e-05, | |
| "loss": 1.0883, | |
| "num_input_tokens_seen": 2061592, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.009036223699072737, | |
| "grad_norm": 4.917592525482178, | |
| "learning_rate": 9.909722591943959e-05, | |
| "loss": 1.2512, | |
| "num_input_tokens_seen": 2077792, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.009106271944801982, | |
| "grad_norm": 4.9154133796691895, | |
| "learning_rate": 9.909022767075307e-05, | |
| "loss": 1.3284, | |
| "num_input_tokens_seen": 2094176, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009176320190531228, | |
| "grad_norm": 5.2125420570373535, | |
| "learning_rate": 9.908322942206656e-05, | |
| "loss": 1.3469, | |
| "num_input_tokens_seen": 2110480, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.009246368436260475, | |
| "grad_norm": 4.715712547302246, | |
| "learning_rate": 9.907623117338004e-05, | |
| "loss": 1.0844, | |
| "num_input_tokens_seen": 2126864, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.009316416681989721, | |
| "grad_norm": 4.805694580078125, | |
| "learning_rate": 9.906923292469353e-05, | |
| "loss": 1.069, | |
| "num_input_tokens_seen": 2142848, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.009386464927718966, | |
| "grad_norm": 4.961355209350586, | |
| "learning_rate": 9.9062234676007e-05, | |
| "loss": 1.3387, | |
| "num_input_tokens_seen": 2159232, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.009456513173448212, | |
| "grad_norm": 4.582219123840332, | |
| "learning_rate": 9.905523642732049e-05, | |
| "loss": 1.2013, | |
| "num_input_tokens_seen": 2175616, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.009526561419177458, | |
| "grad_norm": 5.195998191833496, | |
| "learning_rate": 9.904823817863398e-05, | |
| "loss": 1.2552, | |
| "num_input_tokens_seen": 2191872, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.009596609664906705, | |
| "grad_norm": 4.934189319610596, | |
| "learning_rate": 9.904123992994747e-05, | |
| "loss": 1.2961, | |
| "num_input_tokens_seen": 2208208, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.00966665791063595, | |
| "grad_norm": 4.981037616729736, | |
| "learning_rate": 9.903424168126096e-05, | |
| "loss": 1.1546, | |
| "num_input_tokens_seen": 2224592, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.009736706156365196, | |
| "grad_norm": 5.469496250152588, | |
| "learning_rate": 9.902724343257443e-05, | |
| "loss": 1.3833, | |
| "num_input_tokens_seen": 2240976, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.009806754402094442, | |
| "grad_norm": 4.889583587646484, | |
| "learning_rate": 9.902024518388792e-05, | |
| "loss": 1.2095, | |
| "num_input_tokens_seen": 2257360, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.00987680264782369, | |
| "grad_norm": 4.532052516937256, | |
| "learning_rate": 9.901324693520141e-05, | |
| "loss": 1.143, | |
| "num_input_tokens_seen": 2272848, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.009946850893552935, | |
| "grad_norm": 5.278079032897949, | |
| "learning_rate": 9.900624868651488e-05, | |
| "loss": 1.2849, | |
| "num_input_tokens_seen": 2289232, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.01001689913928218, | |
| "grad_norm": 4.549891948699951, | |
| "learning_rate": 9.899925043782839e-05, | |
| "loss": 1.0482, | |
| "num_input_tokens_seen": 2305424, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.010086947385011426, | |
| "grad_norm": 4.7777180671691895, | |
| "learning_rate": 9.899225218914186e-05, | |
| "loss": 1.1926, | |
| "num_input_tokens_seen": 2320968, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.010156995630740673, | |
| "grad_norm": 4.320313453674316, | |
| "learning_rate": 9.898525394045535e-05, | |
| "loss": 1.0468, | |
| "num_input_tokens_seen": 2337352, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.010227043876469919, | |
| "grad_norm": 4.915202617645264, | |
| "learning_rate": 9.897825569176882e-05, | |
| "loss": 1.1326, | |
| "num_input_tokens_seen": 2353064, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.010297092122199165, | |
| "grad_norm": 4.569783687591553, | |
| "learning_rate": 9.897125744308231e-05, | |
| "loss": 0.8586, | |
| "num_input_tokens_seen": 2369128, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.01036714036792841, | |
| "grad_norm": 4.591664791107178, | |
| "learning_rate": 9.89642591943958e-05, | |
| "loss": 1.1369, | |
| "num_input_tokens_seen": 2385512, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.010437188613657656, | |
| "grad_norm": 4.913016319274902, | |
| "learning_rate": 9.895726094570929e-05, | |
| "loss": 1.1564, | |
| "num_input_tokens_seen": 2401208, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.010507236859386903, | |
| "grad_norm": 4.908018112182617, | |
| "learning_rate": 9.895026269702278e-05, | |
| "loss": 1.1247, | |
| "num_input_tokens_seen": 2417592, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010577285105116149, | |
| "grad_norm": 4.536910057067871, | |
| "learning_rate": 9.894326444833625e-05, | |
| "loss": 1.014, | |
| "num_input_tokens_seen": 2433976, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.010647333350845395, | |
| "grad_norm": 4.899227142333984, | |
| "learning_rate": 9.893626619964974e-05, | |
| "loss": 1.0418, | |
| "num_input_tokens_seen": 2448072, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.01071738159657464, | |
| "grad_norm": 4.600861072540283, | |
| "learning_rate": 9.892926795096323e-05, | |
| "loss": 1.0459, | |
| "num_input_tokens_seen": 2464240, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.010787429842303888, | |
| "grad_norm": 4.707681179046631, | |
| "learning_rate": 9.89222697022767e-05, | |
| "loss": 1.0859, | |
| "num_input_tokens_seen": 2480624, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.010857478088033133, | |
| "grad_norm": 4.748518466949463, | |
| "learning_rate": 9.89152714535902e-05, | |
| "loss": 1.0608, | |
| "num_input_tokens_seen": 2497008, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.010927526333762379, | |
| "grad_norm": 4.794179439544678, | |
| "learning_rate": 9.890827320490368e-05, | |
| "loss": 1.2243, | |
| "num_input_tokens_seen": 2513392, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.010997574579491624, | |
| "grad_norm": 4.593925476074219, | |
| "learning_rate": 9.890127495621717e-05, | |
| "loss": 1.1002, | |
| "num_input_tokens_seen": 2529776, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.011067622825220872, | |
| "grad_norm": 4.318257808685303, | |
| "learning_rate": 9.889427670753066e-05, | |
| "loss": 0.9561, | |
| "num_input_tokens_seen": 2546160, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.011137671070950117, | |
| "grad_norm": 4.631777286529541, | |
| "learning_rate": 9.888727845884414e-05, | |
| "loss": 1.1553, | |
| "num_input_tokens_seen": 2562544, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.011207719316679363, | |
| "grad_norm": 4.896609783172607, | |
| "learning_rate": 9.888028021015762e-05, | |
| "loss": 1.1779, | |
| "num_input_tokens_seen": 2578088, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.011277767562408609, | |
| "grad_norm": 4.3978681564331055, | |
| "learning_rate": 9.88732819614711e-05, | |
| "loss": 1.1778, | |
| "num_input_tokens_seen": 2594416, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.011347815808137854, | |
| "grad_norm": 4.82927942276001, | |
| "learning_rate": 9.886628371278459e-05, | |
| "loss": 1.0339, | |
| "num_input_tokens_seen": 2609776, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.011417864053867102, | |
| "grad_norm": 4.413319110870361, | |
| "learning_rate": 9.885928546409809e-05, | |
| "loss": 1.0992, | |
| "num_input_tokens_seen": 2626160, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.011487912299596347, | |
| "grad_norm": 4.626354694366455, | |
| "learning_rate": 9.885228721541156e-05, | |
| "loss": 1.1948, | |
| "num_input_tokens_seen": 2642464, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.011557960545325593, | |
| "grad_norm": 4.328434467315674, | |
| "learning_rate": 9.884528896672505e-05, | |
| "loss": 1.1493, | |
| "num_input_tokens_seen": 2658528, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.011628008791054838, | |
| "grad_norm": 4.57839822769165, | |
| "learning_rate": 9.883829071803853e-05, | |
| "loss": 1.0775, | |
| "num_input_tokens_seen": 2674912, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.011698057036784086, | |
| "grad_norm": 5.103973865509033, | |
| "learning_rate": 9.883129246935202e-05, | |
| "loss": 1.2458, | |
| "num_input_tokens_seen": 2690792, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.011768105282513331, | |
| "grad_norm": 4.558016300201416, | |
| "learning_rate": 9.88242942206655e-05, | |
| "loss": 1.0122, | |
| "num_input_tokens_seen": 2705616, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.011838153528242577, | |
| "grad_norm": 4.811260223388672, | |
| "learning_rate": 9.8817295971979e-05, | |
| "loss": 1.2989, | |
| "num_input_tokens_seen": 2721704, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.011908201773971823, | |
| "grad_norm": 4.726966857910156, | |
| "learning_rate": 9.881029772329248e-05, | |
| "loss": 1.176, | |
| "num_input_tokens_seen": 2738088, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01197825001970107, | |
| "grad_norm": 4.874902725219727, | |
| "learning_rate": 9.880329947460596e-05, | |
| "loss": 1.2586, | |
| "num_input_tokens_seen": 2754040, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.012048298265430316, | |
| "grad_norm": 4.379549980163574, | |
| "learning_rate": 9.879630122591945e-05, | |
| "loss": 1.1771, | |
| "num_input_tokens_seen": 2770424, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.012118346511159561, | |
| "grad_norm": 4.455331802368164, | |
| "learning_rate": 9.878930297723292e-05, | |
| "loss": 1.0714, | |
| "num_input_tokens_seen": 2786808, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.012188394756888807, | |
| "grad_norm": 4.42273473739624, | |
| "learning_rate": 9.878230472854641e-05, | |
| "loss": 1.1798, | |
| "num_input_tokens_seen": 2803176, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.012258443002618052, | |
| "grad_norm": 4.4078874588012695, | |
| "learning_rate": 9.87753064798599e-05, | |
| "loss": 1.1672, | |
| "num_input_tokens_seen": 2819448, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.0123284912483473, | |
| "grad_norm": 4.79048490524292, | |
| "learning_rate": 9.876830823117339e-05, | |
| "loss": 1.3331, | |
| "num_input_tokens_seen": 2835832, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.012398539494076545, | |
| "grad_norm": 4.212133884429932, | |
| "learning_rate": 9.876130998248688e-05, | |
| "loss": 1.0007, | |
| "num_input_tokens_seen": 2851776, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.012468587739805791, | |
| "grad_norm": 5.7587738037109375, | |
| "learning_rate": 9.875431173380035e-05, | |
| "loss": 1.4729, | |
| "num_input_tokens_seen": 2867896, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.012538635985535037, | |
| "grad_norm": 4.3469462394714355, | |
| "learning_rate": 9.874731348511384e-05, | |
| "loss": 0.957, | |
| "num_input_tokens_seen": 2884280, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.012608684231264284, | |
| "grad_norm": 4.584625244140625, | |
| "learning_rate": 9.874031523642733e-05, | |
| "loss": 1.0753, | |
| "num_input_tokens_seen": 2899208, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01267873247699353, | |
| "grad_norm": 4.544627666473389, | |
| "learning_rate": 9.87333169877408e-05, | |
| "loss": 1.1706, | |
| "num_input_tokens_seen": 2915416, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.012748780722722775, | |
| "grad_norm": 4.8749237060546875, | |
| "learning_rate": 9.872631873905429e-05, | |
| "loss": 1.3382, | |
| "num_input_tokens_seen": 2931360, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.01281882896845202, | |
| "grad_norm": 4.593903541564941, | |
| "learning_rate": 9.871932049036778e-05, | |
| "loss": 1.1588, | |
| "num_input_tokens_seen": 2947744, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.012888877214181268, | |
| "grad_norm": 4.478219509124756, | |
| "learning_rate": 9.871232224168127e-05, | |
| "loss": 1.1013, | |
| "num_input_tokens_seen": 2963664, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.012958925459910514, | |
| "grad_norm": 5.028106212615967, | |
| "learning_rate": 9.870532399299476e-05, | |
| "loss": 1.3223, | |
| "num_input_tokens_seen": 2980048, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.01302897370563976, | |
| "grad_norm": 4.866946697235107, | |
| "learning_rate": 9.869832574430823e-05, | |
| "loss": 1.2376, | |
| "num_input_tokens_seen": 2995992, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.013099021951369005, | |
| "grad_norm": 4.421341419219971, | |
| "learning_rate": 9.869132749562172e-05, | |
| "loss": 1.2252, | |
| "num_input_tokens_seen": 3012000, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.01316907019709825, | |
| "grad_norm": 4.88083028793335, | |
| "learning_rate": 9.86843292469352e-05, | |
| "loss": 1.2951, | |
| "num_input_tokens_seen": 3028384, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.013239118442827498, | |
| "grad_norm": 4.654318809509277, | |
| "learning_rate": 9.86773309982487e-05, | |
| "loss": 1.2839, | |
| "num_input_tokens_seen": 3044768, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.013309166688556744, | |
| "grad_norm": 4.626763820648193, | |
| "learning_rate": 9.867033274956219e-05, | |
| "loss": 1.2389, | |
| "num_input_tokens_seen": 3061152, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01337921493428599, | |
| "grad_norm": 4.178484916687012, | |
| "learning_rate": 9.866333450087566e-05, | |
| "loss": 1.1186, | |
| "num_input_tokens_seen": 3077056, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.013449263180015235, | |
| "grad_norm": 4.755034923553467, | |
| "learning_rate": 9.865633625218915e-05, | |
| "loss": 1.0594, | |
| "num_input_tokens_seen": 3093400, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.013519311425744482, | |
| "grad_norm": 4.437506198883057, | |
| "learning_rate": 9.864933800350263e-05, | |
| "loss": 1.2078, | |
| "num_input_tokens_seen": 3109784, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.013589359671473728, | |
| "grad_norm": 5.140488624572754, | |
| "learning_rate": 9.864233975481611e-05, | |
| "loss": 1.4312, | |
| "num_input_tokens_seen": 3124976, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.013659407917202973, | |
| "grad_norm": 4.72155237197876, | |
| "learning_rate": 9.86353415061296e-05, | |
| "loss": 1.1752, | |
| "num_input_tokens_seen": 3140632, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.013729456162932219, | |
| "grad_norm": 4.914645671844482, | |
| "learning_rate": 9.862834325744309e-05, | |
| "loss": 1.2464, | |
| "num_input_tokens_seen": 3156616, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.013799504408661466, | |
| "grad_norm": 4.23387336730957, | |
| "learning_rate": 9.862134500875658e-05, | |
| "loss": 0.9722, | |
| "num_input_tokens_seen": 3172840, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.013869552654390712, | |
| "grad_norm": 4.659370422363281, | |
| "learning_rate": 9.861434676007005e-05, | |
| "loss": 1.1981, | |
| "num_input_tokens_seen": 3188584, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.013939600900119958, | |
| "grad_norm": 4.580902576446533, | |
| "learning_rate": 9.860734851138354e-05, | |
| "loss": 1.1913, | |
| "num_input_tokens_seen": 3204432, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.014009649145849203, | |
| "grad_norm": 4.208237648010254, | |
| "learning_rate": 9.860035026269702e-05, | |
| "loss": 1.2056, | |
| "num_input_tokens_seen": 3220816, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.014009649145849203, | |
| "eval_loss": 1.2226407527923584, | |
| "eval_runtime": 0.3992, | |
| "eval_samples_per_second": 2.505, | |
| "eval_steps_per_second": 2.505, | |
| "num_input_tokens_seen": 3220816, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 14275, | |
| "num_input_tokens_seen": 3220816, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6916343792996352.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |