| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.4, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.3297976851463318, | |
| "learning_rate": 0.0002990322580645161, | |
| "loss": 1.0389, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.4069916307926178, | |
| "learning_rate": 0.0002980645161290322, | |
| "loss": 1.3377, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.42084500193595886, | |
| "learning_rate": 0.00029709677419354836, | |
| "loss": 0.9366, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.4641948938369751, | |
| "learning_rate": 0.0002961290322580645, | |
| "loss": 1.0086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3840750455856323, | |
| "learning_rate": 0.00029516129032258065, | |
| "loss": 0.8333, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.4263865053653717, | |
| "learning_rate": 0.00029419354838709674, | |
| "loss": 0.854, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.48615148663520813, | |
| "learning_rate": 0.0002932258064516129, | |
| "loss": 0.9548, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.44419369101524353, | |
| "learning_rate": 0.00029225806451612903, | |
| "loss": 0.8482, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.5317733883857727, | |
| "learning_rate": 0.0002912903225806451, | |
| "loss": 0.9426, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.47260937094688416, | |
| "learning_rate": 0.00029032258064516127, | |
| "loss": 0.9816, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.39063283801078796, | |
| "learning_rate": 0.00028935483870967736, | |
| "loss": 0.84, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.39234670996665955, | |
| "learning_rate": 0.0002883870967741935, | |
| "loss": 0.7476, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.40661805868148804, | |
| "learning_rate": 0.00028741935483870965, | |
| "loss": 0.9282, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.42970865964889526, | |
| "learning_rate": 0.0002864516129032258, | |
| "loss": 0.7858, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.3780193626880646, | |
| "learning_rate": 0.00028548387096774194, | |
| "loss": 0.7968, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.37006014585494995, | |
| "learning_rate": 0.00028451612903225803, | |
| "loss": 0.6801, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.3660840392112732, | |
| "learning_rate": 0.0002835483870967742, | |
| "loss": 0.5914, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.3270975351333618, | |
| "learning_rate": 0.00028258064516129027, | |
| "loss": 0.6449, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.3859024941921234, | |
| "learning_rate": 0.0002816129032258064, | |
| "loss": 0.8144, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.37092071771621704, | |
| "learning_rate": 0.00028064516129032256, | |
| "loss": 0.7667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.37667015194892883, | |
| "learning_rate": 0.0002796774193548387, | |
| "loss": 0.7751, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.3832458555698395, | |
| "learning_rate": 0.0002787096774193548, | |
| "loss": 0.755, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.327288419008255, | |
| "learning_rate": 0.00027774193548387095, | |
| "loss": 0.7178, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.34552687406539917, | |
| "learning_rate": 0.0002767741935483871, | |
| "loss": 0.7057, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.3611259460449219, | |
| "learning_rate": 0.0002758064516129032, | |
| "loss": 0.8159, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.3345054090023041, | |
| "learning_rate": 0.00027483870967741933, | |
| "loss": 0.7208, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.3697254955768585, | |
| "learning_rate": 0.0002738709677419355, | |
| "loss": 0.8964, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.3905017375946045, | |
| "learning_rate": 0.00027290322580645157, | |
| "loss": 0.7794, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.3715725243091583, | |
| "learning_rate": 0.0002719354838709677, | |
| "loss": 0.6966, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3650343120098114, | |
| "learning_rate": 0.00027096774193548386, | |
| "loss": 0.5761, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.33932459354400635, | |
| "learning_rate": 0.00027, | |
| "loss": 0.556, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "grad_norm": 0.6371742486953735, | |
| "learning_rate": 0.0002690322580645161, | |
| "loss": 0.847, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 0.37499895691871643, | |
| "learning_rate": 0.00026806451612903224, | |
| "loss": 0.8419, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "grad_norm": 0.33221954107284546, | |
| "learning_rate": 0.0002670967741935484, | |
| "loss": 0.6011, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.344096839427948, | |
| "learning_rate": 0.0002661290322580645, | |
| "loss": 0.6501, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 0.38429391384124756, | |
| "learning_rate": 0.0002651612903225806, | |
| "loss": 0.8091, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.184, | |
| "grad_norm": 0.38014867901802063, | |
| "learning_rate": 0.00026419354838709677, | |
| "loss": 0.7668, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "grad_norm": 0.3352573812007904, | |
| "learning_rate": 0.00026322580645161286, | |
| "loss": 0.5444, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 0.33811062574386597, | |
| "learning_rate": 0.000262258064516129, | |
| "loss": 0.512, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.3998416066169739, | |
| "learning_rate": 0.00026129032258064515, | |
| "loss": 0.6315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.312, | |
| "grad_norm": 0.3983341157436371, | |
| "learning_rate": 0.0002603225806451613, | |
| "loss": 0.5882, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 0.4585898816585541, | |
| "learning_rate": 0.0002593548387096774, | |
| "loss": 0.761, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.376, | |
| "grad_norm": 0.4080730080604553, | |
| "learning_rate": 0.00025838709677419354, | |
| "loss": 0.6716, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "grad_norm": 0.4068273901939392, | |
| "learning_rate": 0.0002574193548387096, | |
| "loss": 0.6376, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.4406949579715729, | |
| "learning_rate": 0.00025645161290322577, | |
| "loss": 0.4594, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "grad_norm": 0.34500986337661743, | |
| "learning_rate": 0.0002554838709677419, | |
| "loss": 0.3672, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.504, | |
| "grad_norm": 0.4760681390762329, | |
| "learning_rate": 0.00025451612903225806, | |
| "loss": 0.6331, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 0.39281558990478516, | |
| "learning_rate": 0.0002535483870967742, | |
| "loss": 0.5845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.568, | |
| "grad_norm": 0.4265002906322479, | |
| "learning_rate": 0.0002525806451612903, | |
| "loss": 0.4461, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.40967294573783875, | |
| "learning_rate": 0.00025161290322580645, | |
| "loss": 0.7011, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 0.4288088381290436, | |
| "learning_rate": 0.00025064516129032254, | |
| "loss": 0.6928, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.6640000000000001, | |
| "grad_norm": 0.4356289803981781, | |
| "learning_rate": 0.0002496774193548387, | |
| "loss": 0.7972, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.696, | |
| "grad_norm": 0.3827487826347351, | |
| "learning_rate": 0.0002487096774193548, | |
| "loss": 0.2991, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 0.40093398094177246, | |
| "learning_rate": 0.0002477419354838709, | |
| "loss": 0.416, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.41548973321914673, | |
| "learning_rate": 0.00024677419354838707, | |
| "loss": 0.5501, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.792, | |
| "grad_norm": 0.4093388617038727, | |
| "learning_rate": 0.0002458064516129032, | |
| "loss": 0.5557, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 0.3934040665626526, | |
| "learning_rate": 0.00024483870967741936, | |
| "loss": 0.602, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.8559999999999999, | |
| "grad_norm": 0.42221033573150635, | |
| "learning_rate": 0.00024387096774193545, | |
| "loss": 0.6421, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.888, | |
| "grad_norm": 0.4351339340209961, | |
| "learning_rate": 0.0002429032258064516, | |
| "loss": 0.5615, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.4319838881492615, | |
| "learning_rate": 0.00024193548387096771, | |
| "loss": 0.6804, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.952, | |
| "grad_norm": 0.40016525983810425, | |
| "learning_rate": 0.00024096774193548386, | |
| "loss": 0.5432, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "grad_norm": 0.3905942440032959, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.4187, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.016, | |
| "grad_norm": 0.8056382536888123, | |
| "learning_rate": 0.0002390322580645161, | |
| "loss": 1.0174, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.048, | |
| "grad_norm": 0.3835236430168152, | |
| "learning_rate": 0.00023806451612903224, | |
| "loss": 0.5992, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.41092216968536377, | |
| "learning_rate": 0.00023709677419354836, | |
| "loss": 0.4746, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.112, | |
| "grad_norm": 0.39536622166633606, | |
| "learning_rate": 0.0002361290322580645, | |
| "loss": 0.3946, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.144, | |
| "grad_norm": 0.3927665948867798, | |
| "learning_rate": 0.0002351612903225806, | |
| "loss": 0.5187, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.176, | |
| "grad_norm": 0.39792704582214355, | |
| "learning_rate": 0.00023419354838709674, | |
| "loss": 0.4568, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.208, | |
| "grad_norm": 0.5023652911186218, | |
| "learning_rate": 0.0002332258064516129, | |
| "loss": 0.6166, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.425017774105072, | |
| "learning_rate": 0.000232258064516129, | |
| "loss": 0.42, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.2720000000000002, | |
| "grad_norm": 0.46458110213279724, | |
| "learning_rate": 0.00023129032258064516, | |
| "loss": 0.4613, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.304, | |
| "grad_norm": 0.49037960171699524, | |
| "learning_rate": 0.00023032258064516125, | |
| "loss": 0.5509, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.336, | |
| "grad_norm": 0.5233697891235352, | |
| "learning_rate": 0.0002293548387096774, | |
| "loss": 0.6396, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.368, | |
| "grad_norm": 0.4720582962036133, | |
| "learning_rate": 0.0002283870967741935, | |
| "loss": 0.5076, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.4900650382041931, | |
| "learning_rate": 0.00022741935483870966, | |
| "loss": 0.4794, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.432, | |
| "grad_norm": 0.6321704983711243, | |
| "learning_rate": 0.0002264516129032258, | |
| "loss": 0.6677, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.464, | |
| "grad_norm": 0.5305324792861938, | |
| "learning_rate": 0.00022548387096774192, | |
| "loss": 0.5102, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.496, | |
| "grad_norm": 0.5799248218536377, | |
| "learning_rate": 0.00022451612903225804, | |
| "loss": 0.5274, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.528, | |
| "grad_norm": 0.4990101456642151, | |
| "learning_rate": 0.00022354838709677416, | |
| "loss": 0.5407, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.4779827296733856, | |
| "learning_rate": 0.0002225806451612903, | |
| "loss": 0.5166, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.592, | |
| "grad_norm": 0.5140111446380615, | |
| "learning_rate": 0.00022161290322580645, | |
| "loss": 0.3288, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.624, | |
| "grad_norm": 0.5674853920936584, | |
| "learning_rate": 0.00022064516129032257, | |
| "loss": 0.666, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.656, | |
| "grad_norm": 0.5277597308158875, | |
| "learning_rate": 0.00021967741935483871, | |
| "loss": 0.5335, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.6879999999999997, | |
| "grad_norm": 0.6029439568519592, | |
| "learning_rate": 0.0002187096774193548, | |
| "loss": 0.693, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.5039327144622803, | |
| "learning_rate": 0.00021774193548387095, | |
| "loss": 0.5728, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.752, | |
| "grad_norm": 0.5564692616462708, | |
| "learning_rate": 0.00021677419354838707, | |
| "loss": 0.4734, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.784, | |
| "grad_norm": 0.5278319120407104, | |
| "learning_rate": 0.00021580645161290322, | |
| "loss": 0.5834, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.816, | |
| "grad_norm": 0.5445135831832886, | |
| "learning_rate": 0.00021483870967741936, | |
| "loss": 0.4642, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.848, | |
| "grad_norm": 0.5394749045372009, | |
| "learning_rate": 0.00021387096774193545, | |
| "loss": 0.4779, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.5756134390830994, | |
| "learning_rate": 0.0002129032258064516, | |
| "loss": 0.5607, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.912, | |
| "grad_norm": 0.48361241817474365, | |
| "learning_rate": 0.00021193548387096772, | |
| "loss": 0.4278, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.944, | |
| "grad_norm": 0.5017121434211731, | |
| "learning_rate": 0.00021096774193548386, | |
| "loss": 0.4834, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.976, | |
| "grad_norm": 0.4741989076137543, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.468, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.008, | |
| "grad_norm": 1.003368854522705, | |
| "learning_rate": 0.0002090322580645161, | |
| "loss": 0.8614, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 0.4782228469848633, | |
| "learning_rate": 0.00020806451612903225, | |
| "loss": 0.4111, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.072, | |
| "grad_norm": 0.4558674395084381, | |
| "learning_rate": 0.00020709677419354836, | |
| "loss": 0.3463, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.104, | |
| "grad_norm": 0.4409371316432953, | |
| "learning_rate": 0.0002061290322580645, | |
| "loss": 0.2571, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.136, | |
| "grad_norm": 0.5415034890174866, | |
| "learning_rate": 0.00020516129032258063, | |
| "loss": 0.5707, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.168, | |
| "grad_norm": 0.6157724857330322, | |
| "learning_rate": 0.00020419354838709677, | |
| "loss": 0.5692, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.4855688810348511, | |
| "learning_rate": 0.00020322580645161287, | |
| "loss": 0.3311, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.232, | |
| "grad_norm": 0.569878101348877, | |
| "learning_rate": 0.000202258064516129, | |
| "loss": 0.4707, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.2640000000000002, | |
| "grad_norm": 0.645232081413269, | |
| "learning_rate": 0.00020129032258064516, | |
| "loss": 0.5504, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.296, | |
| "grad_norm": 0.5775763392448425, | |
| "learning_rate": 0.00020032258064516128, | |
| "loss": 0.3651, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.328, | |
| "grad_norm": 0.5808250904083252, | |
| "learning_rate": 0.00019935483870967742, | |
| "loss": 0.5068, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 0.689313530921936, | |
| "learning_rate": 0.0001983870967741935, | |
| "loss": 0.4936, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.392, | |
| "grad_norm": 0.6571519374847412, | |
| "learning_rate": 0.00019741935483870966, | |
| "loss": 0.3671, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.424, | |
| "grad_norm": 0.6340517401695251, | |
| "learning_rate": 0.00019645161290322578, | |
| "loss": 0.4783, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.456, | |
| "grad_norm": 0.7031407952308655, | |
| "learning_rate": 0.00019548387096774192, | |
| "loss": 0.427, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.488, | |
| "grad_norm": 0.728496789932251, | |
| "learning_rate": 0.00019451612903225807, | |
| "loss": 0.5497, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 0.6106727719306946, | |
| "learning_rate": 0.00019354838709677416, | |
| "loss": 0.392, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.552, | |
| "grad_norm": 0.5296047329902649, | |
| "learning_rate": 0.0001925806451612903, | |
| "loss": 0.3412, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 3.584, | |
| "grad_norm": 0.6282025575637817, | |
| "learning_rate": 0.00019161290322580643, | |
| "loss": 0.4081, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.616, | |
| "grad_norm": 0.6166461110115051, | |
| "learning_rate": 0.00019064516129032257, | |
| "loss": 0.4771, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 3.648, | |
| "grad_norm": 0.5448863506317139, | |
| "learning_rate": 0.0001896774193548387, | |
| "loss": 0.404, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 0.6598389148712158, | |
| "learning_rate": 0.0001887096774193548, | |
| "loss": 0.3915, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.7119999999999997, | |
| "grad_norm": 0.5567564368247986, | |
| "learning_rate": 0.00018774193548387095, | |
| "loss": 0.3862, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 3.7439999999999998, | |
| "grad_norm": 0.6524521708488464, | |
| "learning_rate": 0.00018677419354838707, | |
| "loss": 0.5315, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 3.776, | |
| "grad_norm": 0.7040128707885742, | |
| "learning_rate": 0.00018580645161290322, | |
| "loss": 0.5387, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.808, | |
| "grad_norm": 0.690262496471405, | |
| "learning_rate": 0.00018483870967741934, | |
| "loss": 0.4877, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 0.6928034424781799, | |
| "learning_rate": 0.00018387096774193548, | |
| "loss": 0.4895, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.872, | |
| "grad_norm": 0.7148469686508179, | |
| "learning_rate": 0.00018290322580645157, | |
| "loss": 0.4814, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 3.904, | |
| "grad_norm": 0.6096572875976562, | |
| "learning_rate": 0.00018193548387096772, | |
| "loss": 0.3403, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.936, | |
| "grad_norm": 0.7132399678230286, | |
| "learning_rate": 0.00018096774193548387, | |
| "loss": 0.4258, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 3.968, | |
| "grad_norm": 0.7302684187889099, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.7215, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.5244004726409912, | |
| "learning_rate": 0.00017903225806451613, | |
| "loss": 0.8544, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.032, | |
| "grad_norm": 0.6032777428627014, | |
| "learning_rate": 0.00017806451612903222, | |
| "loss": 0.4183, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.064, | |
| "grad_norm": 0.6349691152572632, | |
| "learning_rate": 0.00017709677419354837, | |
| "loss": 0.5871, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.096, | |
| "grad_norm": 0.5730060935020447, | |
| "learning_rate": 0.00017612903225806449, | |
| "loss": 0.3786, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.128, | |
| "grad_norm": 0.6988044381141663, | |
| "learning_rate": 0.00017516129032258063, | |
| "loss": 0.3216, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 0.7379153370857239, | |
| "learning_rate": 0.00017419354838709678, | |
| "loss": 0.4026, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.192, | |
| "grad_norm": 0.7058238983154297, | |
| "learning_rate": 0.00017322580645161287, | |
| "loss": 0.4328, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.224, | |
| "grad_norm": 0.80663001537323, | |
| "learning_rate": 0.00017225806451612901, | |
| "loss": 0.3849, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.256, | |
| "grad_norm": 0.899818480014801, | |
| "learning_rate": 0.00017129032258064513, | |
| "loss": 0.4191, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.288, | |
| "grad_norm": 0.8538224697113037, | |
| "learning_rate": 0.00017032258064516128, | |
| "loss": 0.3587, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 0.8948169350624084, | |
| "learning_rate": 0.00016935483870967742, | |
| "loss": 0.3957, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.352, | |
| "grad_norm": 0.7195591926574707, | |
| "learning_rate": 0.00016838709677419354, | |
| "loss": 0.3361, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.384, | |
| "grad_norm": 0.7769681215286255, | |
| "learning_rate": 0.00016741935483870966, | |
| "loss": 0.3519, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.416, | |
| "grad_norm": 0.9509867429733276, | |
| "learning_rate": 0.00016645161290322578, | |
| "loss": 0.4216, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.448, | |
| "grad_norm": 0.7923309206962585, | |
| "learning_rate": 0.00016548387096774193, | |
| "loss": 0.3999, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 0.8961685299873352, | |
| "learning_rate": 0.00016451612903225804, | |
| "loss": 0.5385, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.5120000000000005, | |
| "grad_norm": 0.7496562004089355, | |
| "learning_rate": 0.0001635483870967742, | |
| "loss": 0.341, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 4.5440000000000005, | |
| "grad_norm": 0.8512839674949646, | |
| "learning_rate": 0.00016258064516129034, | |
| "loss": 0.3847, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.576, | |
| "grad_norm": 0.7487362027168274, | |
| "learning_rate": 0.00016161290322580643, | |
| "loss": 0.3694, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 4.608, | |
| "grad_norm": 0.7957774996757507, | |
| "learning_rate": 0.00016064516129032257, | |
| "loss": 0.3379, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 0.7299221754074097, | |
| "learning_rate": 0.0001596774193548387, | |
| "loss": 0.2989, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.672, | |
| "grad_norm": 0.7909884452819824, | |
| "learning_rate": 0.00015870967741935484, | |
| "loss": 0.3675, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 4.704, | |
| "grad_norm": 0.7321597933769226, | |
| "learning_rate": 0.00015774193548387093, | |
| "loss": 0.3243, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 4.736, | |
| "grad_norm": 0.7196181416511536, | |
| "learning_rate": 0.00015677419354838708, | |
| "loss": 0.2709, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 4.768, | |
| "grad_norm": 0.7918142676353455, | |
| "learning_rate": 0.00015580645161290322, | |
| "loss": 0.3934, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.8657622337341309, | |
| "learning_rate": 0.00015483870967741934, | |
| "loss": 0.3583, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.832, | |
| "grad_norm": 0.8207722306251526, | |
| "learning_rate": 0.00015387096774193549, | |
| "loss": 0.412, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 4.864, | |
| "grad_norm": 0.7206109166145325, | |
| "learning_rate": 0.00015290322580645158, | |
| "loss": 0.3594, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.896, | |
| "grad_norm": 0.8529183864593506, | |
| "learning_rate": 0.00015193548387096772, | |
| "loss": 0.512, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.928, | |
| "grad_norm": 0.6895930171012878, | |
| "learning_rate": 0.00015096774193548384, | |
| "loss": 0.333, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.7422910332679749, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2872, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 4.992, | |
| "grad_norm": 0.7366386651992798, | |
| "learning_rate": 0.0001490322580645161, | |
| "loss": 0.3415, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.024, | |
| "grad_norm": 2.1416280269622803, | |
| "learning_rate": 0.00014806451612903225, | |
| "loss": 0.9961, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 5.056, | |
| "grad_norm": 0.7944900393486023, | |
| "learning_rate": 0.00014709677419354837, | |
| "loss": 0.3372, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 5.088, | |
| "grad_norm": 0.7071006298065186, | |
| "learning_rate": 0.00014612903225806452, | |
| "loss": 0.2732, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "grad_norm": 0.7874396443367004, | |
| "learning_rate": 0.00014516129032258063, | |
| "loss": 0.2861, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.152, | |
| "grad_norm": 0.8244249224662781, | |
| "learning_rate": 0.00014419354838709675, | |
| "loss": 0.3428, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 5.184, | |
| "grad_norm": 0.81637042760849, | |
| "learning_rate": 0.0001432258064516129, | |
| "loss": 0.3037, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 5.216, | |
| "grad_norm": 0.9916559457778931, | |
| "learning_rate": 0.00014225806451612902, | |
| "loss": 0.3337, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 5.248, | |
| "grad_norm": 0.9077599048614502, | |
| "learning_rate": 0.00014129032258064514, | |
| "loss": 0.287, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "grad_norm": 0.9824132919311523, | |
| "learning_rate": 0.00014032258064516128, | |
| "loss": 0.3852, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 5.312, | |
| "grad_norm": 1.0016467571258545, | |
| "learning_rate": 0.0001393548387096774, | |
| "loss": 0.3234, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 5.344, | |
| "grad_norm": 0.8697543144226074, | |
| "learning_rate": 0.00013838709677419355, | |
| "loss": 0.2848, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 5.376, | |
| "grad_norm": 0.8214029669761658, | |
| "learning_rate": 0.00013741935483870966, | |
| "loss": 0.3377, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 5.408, | |
| "grad_norm": 0.9105691313743591, | |
| "learning_rate": 0.00013645161290322578, | |
| "loss": 0.2944, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "grad_norm": 0.9642040133476257, | |
| "learning_rate": 0.00013548387096774193, | |
| "loss": 0.3624, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.4719999999999995, | |
| "grad_norm": 0.9218887686729431, | |
| "learning_rate": 0.00013451612903225805, | |
| "loss": 0.3938, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 5.504, | |
| "grad_norm": 0.8704710006713867, | |
| "learning_rate": 0.0001335483870967742, | |
| "loss": 0.3629, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 5.536, | |
| "grad_norm": 0.8207693099975586, | |
| "learning_rate": 0.0001325806451612903, | |
| "loss": 0.3169, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 5.568, | |
| "grad_norm": 0.9315701127052307, | |
| "learning_rate": 0.00013161290322580643, | |
| "loss": 0.429, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 0.860234260559082, | |
| "learning_rate": 0.00013064516129032258, | |
| "loss": 0.3842, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 5.632, | |
| "grad_norm": 0.8927604556083679, | |
| "learning_rate": 0.0001296774193548387, | |
| "loss": 0.3405, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 5.664, | |
| "grad_norm": 0.8084587454795837, | |
| "learning_rate": 0.0001287096774193548, | |
| "loss": 0.306, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 5.696, | |
| "grad_norm": 0.9102941155433655, | |
| "learning_rate": 0.00012774193548387096, | |
| "loss": 0.3285, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 5.728, | |
| "grad_norm": 0.763113796710968, | |
| "learning_rate": 0.0001267741935483871, | |
| "loss": 0.2729, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "grad_norm": 0.8704251646995544, | |
| "learning_rate": 0.00012580645161290322, | |
| "loss": 0.3164, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.792, | |
| "grad_norm": 0.9634932279586792, | |
| "learning_rate": 0.00012483870967741934, | |
| "loss": 0.2939, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 5.824, | |
| "grad_norm": 1.1567790508270264, | |
| "learning_rate": 0.00012387096774193546, | |
| "loss": 0.3076, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 5.856, | |
| "grad_norm": 0.9096764922142029, | |
| "learning_rate": 0.0001229032258064516, | |
| "loss": 0.3289, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 5.888, | |
| "grad_norm": 0.9840425848960876, | |
| "learning_rate": 0.00012193548387096773, | |
| "loss": 0.2772, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "grad_norm": 0.725844144821167, | |
| "learning_rate": 0.00012096774193548386, | |
| "loss": 0.2151, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 5.952, | |
| "grad_norm": 0.8343638181686401, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.3825, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 5.984, | |
| "grad_norm": 0.8040199279785156, | |
| "learning_rate": 0.00011903225806451612, | |
| "loss": 0.2571, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.016, | |
| "grad_norm": 1.6932090520858765, | |
| "learning_rate": 0.00011806451612903225, | |
| "loss": 0.5538, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 6.048, | |
| "grad_norm": 0.744048535823822, | |
| "learning_rate": 0.00011709677419354837, | |
| "loss": 0.2335, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "grad_norm": 0.6974924206733704, | |
| "learning_rate": 0.0001161290322580645, | |
| "loss": 0.2891, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.112, | |
| "grad_norm": 0.7202953696250916, | |
| "learning_rate": 0.00011516129032258062, | |
| "loss": 0.2017, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 6.144, | |
| "grad_norm": 0.8437547087669373, | |
| "learning_rate": 0.00011419354838709676, | |
| "loss": 0.2175, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 6.176, | |
| "grad_norm": 1.0741796493530273, | |
| "learning_rate": 0.0001132258064516129, | |
| "loss": 0.3913, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 6.208, | |
| "grad_norm": 1.031754493713379, | |
| "learning_rate": 0.00011225806451612902, | |
| "loss": 0.298, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "grad_norm": 0.9575178027153015, | |
| "learning_rate": 0.00011129032258064515, | |
| "loss": 0.3201, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 6.272, | |
| "grad_norm": 0.9503082633018494, | |
| "learning_rate": 0.00011032258064516128, | |
| "loss": 0.2005, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 6.304, | |
| "grad_norm": 1.2572892904281616, | |
| "learning_rate": 0.0001093548387096774, | |
| "loss": 0.3045, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 6.336, | |
| "grad_norm": 1.5667368173599243, | |
| "learning_rate": 0.00010838709677419353, | |
| "loss": 0.4053, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 6.368, | |
| "grad_norm": 0.9439151883125305, | |
| "learning_rate": 0.00010741935483870968, | |
| "loss": 0.2721, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 1.0985567569732666, | |
| "learning_rate": 0.0001064516129032258, | |
| "loss": 0.2543, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.7401861644288e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |