| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4678362573099415, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9988, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9783, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9849, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00025, | |
| "loss": 1.0159, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00030000000000000003, | |
| "loss": 0.9847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00034999999999999994, | |
| "loss": 0.9101, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004, | |
| "loss": 0.9445, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00045, | |
| "loss": 0.8578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0005, | |
| "loss": 0.9356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0005499999999999999, | |
| "loss": 0.8395, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006000000000000001, | |
| "loss": 0.9002, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00065, | |
| "loss": 0.8955, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006499959204043461, | |
| "loss": 0.902, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006499836817198032, | |
| "loss": 0.8578, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006499632842536263, | |
| "loss": 0.9005, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006499347285178979, | |
| "loss": 0.8539, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006498980152295153, | |
| "loss": 0.8595, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006498531453101735, | |
| "loss": 0.8845, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006498001198863406, | |
| "loss": 0.8924, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000649738940289231, | |
| "loss": 0.8365, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006496696080547707, | |
| "loss": 0.8462, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006495921249235596, | |
| "loss": 0.8528, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006495064928408277, | |
| "loss": 0.8159, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006494127139563859, | |
| "loss": 0.8245, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000649310790624572, | |
| "loss": 0.8081, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006492007254041924, | |
| "loss": 0.8535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006490825210584566, | |
| "loss": 0.8162, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006489561805549089, | |
| "loss": 0.8456, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006488217070653535, | |
| "loss": 0.7799, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006486791039657748, | |
| "loss": 0.8088, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006485283748362524, | |
| "loss": 0.8683, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006483695234608723, | |
| "loss": 0.8871, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006482025538276304, | |
| "loss": 0.7711, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006480274701283335, | |
| "loss": 0.7621, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006478442767584937, | |
| "loss": 0.8243, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006476529783172177, | |
| "loss": 0.8257, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006474535796070919, | |
| "loss": 0.8141, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006472460856340619, | |
| "loss": 0.8109, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000647030501607306, | |
| "loss": 0.7873, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000646806832939105, | |
| "loss": 0.7386, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006465750852447068, | |
| "loss": 0.8636, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006463352643421846, | |
| "loss": 0.7357, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006460873762522906, | |
| "loss": 0.8142, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006458314271983063, | |
| "loss": 0.7275, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006455674236058847, | |
| "loss": 0.8029, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00064529537210289, | |
| "loss": 0.7901, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006450152795192307, | |
| "loss": 0.7788, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006447271528866881, | |
| "loss": 0.7621, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006444309994387402, | |
| "loss": 0.7537, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006441268266103796, | |
| "loss": 0.7917, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006438146420379274, | |
| "loss": 0.8451, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006434944535588411, | |
| "loss": 0.8369, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006431662692115173, | |
| "loss": 0.7637, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006428300972350914, | |
| "loss": 0.8365, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006424859460692295, | |
| "loss": 0.7633, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006421338243539165, | |
| "loss": 0.7718, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006417737409292403, | |
| "loss": 0.7672, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006414057048351684, | |
| "loss": 0.8107, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006410297253113221, | |
| "loss": 0.7979, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006406458117967443, | |
| "loss": 0.7634, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006402539739296618, | |
| "loss": 0.7504, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0006398542215472443, | |
| "loss": 0.8082, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0006394465646853571, | |
| "loss": 0.8355, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0006390310135783086, | |
| "loss": 0.7458, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0006386075786585944, | |
| "loss": 0.7525, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0006381762705566343, | |
| "loss": 0.7464, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0006377371001005063, | |
| "loss": 0.78, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0006372900783156745, | |
| "loss": 0.7752, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0006368352164247117, | |
| "loss": 0.7299, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0006363725258470184, | |
| "loss": 0.7722, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0006359020181985365, | |
| "loss": 0.8236, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0006354237052914561, | |
| "loss": 0.7589, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0006349375991339202, | |
| "loss": 0.7948, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0006344437119297233, | |
| "loss": 0.7528, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0006339420560780045, | |
| "loss": 0.7842, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0006334326441729361, | |
| "loss": 0.7541, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000632915489003408, | |
| "loss": 0.7425, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0006323906035527062, | |
| "loss": 0.8168, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0006318580009981871, | |
| "loss": 0.8074, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0006313176947109465, | |
| "loss": 0.7679, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0006307696982554838, | |
| "loss": 0.7465, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0006302140253893622, | |
| "loss": 0.7073, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0006296506900628619, | |
| "loss": 0.7687, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0006290797064186315, | |
| "loss": 0.7578, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0006285010887913319, | |
| "loss": 0.7494, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0006279148517072765, | |
| "loss": 0.7326, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000627321009884067, | |
| "loss": 0.7603, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0006267195782302236, | |
| "loss": 0.8141, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0006261105718448105, | |
| "loss": 0.7542, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0006254940060170575, | |
| "loss": 0.7597, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0006248698962259753, | |
| "loss": 0.7332, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0006242382581399676, | |
| "loss": 0.7031, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0006235991076164375, | |
| "loss": 0.7258, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0006229524607013892, | |
| "loss": 0.7634, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0006222983336290254, | |
| "loss": 0.765, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0006216367428213398, | |
| "loss": 0.7246, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0006209677048877046, | |
| "loss": 0.7115, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0006202912366244535, | |
| "loss": 0.6748, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0006196073550144604, | |
| "loss": 0.6995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0006189160772267127, | |
| "loss": 0.7764, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00061821742061588, | |
| "loss": 0.8628, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0006175114027218794, | |
| "loss": 0.7266, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0006167980412694342, | |
| "loss": 0.7557, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0006160773541676288, | |
| "loss": 0.7518, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0006153493595094602, | |
| "loss": 0.7589, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.000614614075571383, | |
| "loss": 0.7506, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0006138715208128501, | |
| "loss": 0.6617, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0006131217138758505, | |
| "loss": 0.7396, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0006123646735844401, | |
| "loss": 0.7666, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00061160041894427, | |
| "loss": 0.7555, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0006108289691421089, | |
| "loss": 0.7301, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0006100503435453614, | |
| "loss": 0.7364, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0006092645617015822, | |
| "loss": 0.7461, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0006084716433379844, | |
| "loss": 0.8086, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0006076716083609456, | |
| "loss": 0.7577, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0006068644768555068, | |
| "loss": 0.7094, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0006060502690848696, | |
| "loss": 0.726, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0006052290054898859, | |
| "loss": 0.7243, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0006044007066885458, | |
| "loss": 0.7119, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0006035653934754598, | |
| "loss": 0.7049, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0006027230868213366, | |
| "loss": 0.7424, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0006018738078724563, | |
| "loss": 0.7271, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0006010175779501405, | |
| "loss": 0.7996, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0006001544185502158, | |
| "loss": 0.7468, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0005992843513424754, | |
| "loss": 0.7513, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0005984073981701338, | |
| "loss": 0.7461, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0005975235810492794, | |
| "loss": 0.6821, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0005966329221683215, | |
| "loss": 0.7314, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005957354438874327, | |
| "loss": 0.714, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005948311687379884, | |
| "loss": 0.7339, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.000593920119422001, | |
| "loss": 0.7021, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0005930023188115492, | |
| "loss": 0.7228, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005920777899482046, | |
| "loss": 0.7107, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005911465560424532, | |
| "loss": 0.659, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005902086404731118, | |
| "loss": 0.7028, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0005892640667867423, | |
| "loss": 0.7275, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00058831285869706, | |
| "loss": 0.6889, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0005873550400843378, | |
| "loss": 0.7891, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0005863906349948074, | |
| "loss": 0.7904, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0005854196676400555, | |
| "loss": 0.6674, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0005844421623964157, | |
| "loss": 0.7352, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0005834581438043563, | |
| "loss": 0.6965, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.000582467636567865, | |
| "loss": 0.7238, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0005814706655538279, | |
| "loss": 0.7064, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005804672557914059, | |
| "loss": 0.6984, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005794574324714057, | |
| "loss": 0.7594, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0005784412209456479, | |
| "loss": 0.6884, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00057741864672633, | |
| "loss": 0.7141, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0005763897354853866, | |
| "loss": 0.705, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 640, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 3.889192088892211e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |