| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9977924944812362, | |
| "eval_steps": 500, | |
| "global_step": 113, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008830022075055188, | |
| "grad_norm": 0.8537317514419556, | |
| "learning_rate": 4.999033893736386e-05, | |
| "loss": 0.9875, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017660044150110375, | |
| "grad_norm": 0.7285566926002502, | |
| "learning_rate": 4.99613632163459e-05, | |
| "loss": 0.944, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026490066225165563, | |
| "grad_norm": 0.5551783442497253, | |
| "learning_rate": 4.991309523184661e-05, | |
| "loss": 0.904, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03532008830022075, | |
| "grad_norm": 0.4819079041481018, | |
| "learning_rate": 4.98455722894677e-05, | |
| "loss": 0.8913, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04415011037527594, | |
| "grad_norm": 0.373820960521698, | |
| "learning_rate": 4.975884657667922e-05, | |
| "loss": 0.8511, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 0.2974053621292114, | |
| "learning_rate": 4.965298512248466e-05, | |
| "loss": 0.8311, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06181015452538632, | |
| "grad_norm": 0.25162145495414734, | |
| "learning_rate": 4.952806974561518e-05, | |
| "loss": 0.838, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0706401766004415, | |
| "grad_norm": 0.20863372087478638, | |
| "learning_rate": 4.9384196991293205e-05, | |
| "loss": 0.8468, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07947019867549669, | |
| "grad_norm": 0.18535731732845306, | |
| "learning_rate": 4.922147805661402e-05, | |
| "loss": 0.7884, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08830022075055188, | |
| "grad_norm": 0.16335929930210114, | |
| "learning_rate": 4.904003870460323e-05, | |
| "loss": 0.8009, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09713024282560706, | |
| "grad_norm": 0.1265847086906433, | |
| "learning_rate": 4.884001916701639e-05, | |
| "loss": 0.7764, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "grad_norm": 0.11690282076597214, | |
| "learning_rate": 4.862157403595598e-05, | |
| "loss": 0.7774, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11479028697571744, | |
| "grad_norm": 0.10680913180112839, | |
| "learning_rate": 4.838487214438951e-05, | |
| "loss": 0.7808, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12362030905077263, | |
| "grad_norm": 0.09127331525087357, | |
| "learning_rate": 4.813009643566101e-05, | |
| "loss": 0.8111, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13245033112582782, | |
| "grad_norm": 0.08718351274728775, | |
| "learning_rate": 4.7857443822096905e-05, | |
| "loss": 0.7997, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.141280353200883, | |
| "grad_norm": 0.06960419565439224, | |
| "learning_rate": 4.7567125032815394e-05, | |
| "loss": 0.7537, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15011037527593818, | |
| "grad_norm": 0.0721953734755516, | |
| "learning_rate": 4.7259364450857096e-05, | |
| "loss": 0.7645, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15894039735099338, | |
| "grad_norm": 0.0680830106139183, | |
| "learning_rate": 4.6934399939762746e-05, | |
| "loss": 0.7712, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16777041942604856, | |
| "grad_norm": 0.06572319567203522, | |
| "learning_rate": 4.659248265973205e-05, | |
| "loss": 0.74, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17660044150110377, | |
| "grad_norm": 0.06348133087158203, | |
| "learning_rate": 4.6233876873505694e-05, | |
| "loss": 0.777, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18543046357615894, | |
| "grad_norm": 0.06005046144127846, | |
| "learning_rate": 4.585885974212068e-05, | |
| "loss": 0.7537, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19426048565121412, | |
| "grad_norm": 0.057457394897937775, | |
| "learning_rate": 4.5467721110696685e-05, | |
| "loss": 0.7453, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20309050772626933, | |
| "grad_norm": 0.054359156638383865, | |
| "learning_rate": 4.5060763284419114e-05, | |
| "loss": 0.7573, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2119205298013245, | |
| "grad_norm": 0.054271843284368515, | |
| "learning_rate": 4.463830079489196e-05, | |
| "loss": 0.7626, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22075055187637968, | |
| "grad_norm": 0.048914600163698196, | |
| "learning_rate": 4.420066015704105e-05, | |
| "loss": 0.7558, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22958057395143489, | |
| "grad_norm": 0.04995320364832878, | |
| "learning_rate": 4.374817961675553e-05, | |
| "loss": 0.7654, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23841059602649006, | |
| "grad_norm": 0.04679872468113899, | |
| "learning_rate": 4.3281208889462715e-05, | |
| "loss": 0.7363, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24724061810154527, | |
| "grad_norm": 0.04957474768161774, | |
| "learning_rate": 4.2800108889838244e-05, | |
| "loss": 0.7503, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2560706401766004, | |
| "grad_norm": 0.04368240758776665, | |
| "learning_rate": 4.230525145286057e-05, | |
| "loss": 0.7474, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26490066225165565, | |
| "grad_norm": 0.04365404695272446, | |
| "learning_rate": 4.1797019046425264e-05, | |
| "loss": 0.7442, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2737306843267108, | |
| "grad_norm": 0.04533332213759422, | |
| "learning_rate": 4.127580447574131e-05, | |
| "loss": 0.7492, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.282560706401766, | |
| "grad_norm": 0.045380424708127975, | |
| "learning_rate": 4.0742010579737855e-05, | |
| "loss": 0.7601, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2913907284768212, | |
| "grad_norm": 0.04397201910614967, | |
| "learning_rate": 4.0196049919716004e-05, | |
| "loss": 0.7381, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30022075055187636, | |
| "grad_norm": 0.042593635618686676, | |
| "learning_rate": 3.963834446048644e-05, | |
| "loss": 0.7406, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3090507726269316, | |
| "grad_norm": 0.04130704328417778, | |
| "learning_rate": 3.9069325244239095e-05, | |
| "loss": 0.7573, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31788079470198677, | |
| "grad_norm": 0.04113290086388588, | |
| "learning_rate": 3.848943205739711e-05, | |
| "loss": 0.7419, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32671081677704195, | |
| "grad_norm": 0.0397503562271595, | |
| "learning_rate": 3.7899113090712526e-05, | |
| "loss": 0.7357, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3355408388520971, | |
| "grad_norm": 0.03884141892194748, | |
| "learning_rate": 3.729882459286632e-05, | |
| "loss": 0.7346, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3443708609271523, | |
| "grad_norm": 0.03996223211288452, | |
| "learning_rate": 3.66890305178407e-05, | |
| "loss": 0.7437, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35320088300220753, | |
| "grad_norm": 0.0395955815911293, | |
| "learning_rate": 3.607020216633599e-05, | |
| "loss": 0.742, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3620309050772627, | |
| "grad_norm": 0.03895486891269684, | |
| "learning_rate": 3.544281782150936e-05, | |
| "loss": 0.7136, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3708609271523179, | |
| "grad_norm": 0.03683311864733696, | |
| "learning_rate": 3.4807362379317025e-05, | |
| "loss": 0.7417, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37969094922737306, | |
| "grad_norm": 0.037801578640937805, | |
| "learning_rate": 3.416432697374533e-05, | |
| "loss": 0.7102, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38852097130242824, | |
| "grad_norm": 0.03917045146226883, | |
| "learning_rate": 3.3514208597220705e-05, | |
| "loss": 0.7685, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3973509933774834, | |
| "grad_norm": 0.037231214344501495, | |
| "learning_rate": 3.285750971649167e-05, | |
| "loss": 0.7332, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40618101545253865, | |
| "grad_norm": 0.03943084925413132, | |
| "learning_rate": 3.219473788427984e-05, | |
| "loss": 0.7387, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41501103752759383, | |
| "grad_norm": 0.03614073246717453, | |
| "learning_rate": 3.1526405346999946e-05, | |
| "loss": 0.7096, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.423841059602649, | |
| "grad_norm": 0.03576625511050224, | |
| "learning_rate": 3.085302864885235e-05, | |
| "loss": 0.7242, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4326710816777042, | |
| "grad_norm": 0.0361945666372776, | |
| "learning_rate": 3.017512823259373e-05, | |
| "loss": 0.7338, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.44150110375275936, | |
| "grad_norm": 0.03698369115591049, | |
| "learning_rate": 2.9493228037294702e-05, | |
| "loss": 0.7494, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4503311258278146, | |
| "grad_norm": 0.03586776927113533, | |
| "learning_rate": 2.8807855093395126e-05, | |
| "loss": 0.7272, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.45916114790286977, | |
| "grad_norm": 0.03969455882906914, | |
| "learning_rate": 2.8119539115370218e-05, | |
| "loss": 0.7447, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.46799116997792495, | |
| "grad_norm": 0.037024304270744324, | |
| "learning_rate": 2.742881209232215e-05, | |
| "loss": 0.7219, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4768211920529801, | |
| "grad_norm": 0.035661764442920685, | |
| "learning_rate": 2.6736207876813646e-05, | |
| "loss": 0.7484, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4856512141280353, | |
| "grad_norm": 0.03690381348133087, | |
| "learning_rate": 2.604226177226137e-05, | |
| "loss": 0.7352, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.49448123620309054, | |
| "grad_norm": 0.03607625514268875, | |
| "learning_rate": 2.5347510119207878e-05, | |
| "loss": 0.7254, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5033112582781457, | |
| "grad_norm": 0.036771535873413086, | |
| "learning_rate": 2.4652489880792128e-05, | |
| "loss": 0.724, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5121412803532008, | |
| "grad_norm": 0.035380277782678604, | |
| "learning_rate": 2.395773822773863e-05, | |
| "loss": 0.747, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5209713024282561, | |
| "grad_norm": 0.03334279730916023, | |
| "learning_rate": 2.3263792123186353e-05, | |
| "loss": 0.7246, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5298013245033113, | |
| "grad_norm": 0.03534376993775368, | |
| "learning_rate": 2.2571187907677853e-05, | |
| "loss": 0.7424, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5386313465783664, | |
| "grad_norm": 0.035675469785928726, | |
| "learning_rate": 2.188046088462979e-05, | |
| "loss": 0.7422, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5474613686534217, | |
| "grad_norm": 0.03412646800279617, | |
| "learning_rate": 2.1192144906604876e-05, | |
| "loss": 0.7166, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5562913907284768, | |
| "grad_norm": 0.03617184981703758, | |
| "learning_rate": 2.0506771962705304e-05, | |
| "loss": 0.7564, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.565121412803532, | |
| "grad_norm": 0.03402591496706009, | |
| "learning_rate": 1.982487176740627e-05, | |
| "loss": 0.744, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5739514348785872, | |
| "grad_norm": 0.035137876868247986, | |
| "learning_rate": 1.9146971351147655e-05, | |
| "loss": 0.7523, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5827814569536424, | |
| "grad_norm": 0.03335074707865715, | |
| "learning_rate": 1.847359465300006e-05, | |
| "loss": 0.7274, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5916114790286976, | |
| "grad_norm": 0.032923776656389236, | |
| "learning_rate": 1.780526211572016e-05, | |
| "loss": 0.746, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6004415011037527, | |
| "grad_norm": 0.038766708225011826, | |
| "learning_rate": 1.7142490283508324e-05, | |
| "loss": 0.7423, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.609271523178808, | |
| "grad_norm": 0.032216496765613556, | |
| "learning_rate": 1.648579140277931e-05, | |
| "loss": 0.7234, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6181015452538632, | |
| "grad_norm": 0.03458288684487343, | |
| "learning_rate": 1.583567302625469e-05, | |
| "loss": 0.7495, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6269315673289183, | |
| "grad_norm": 0.033755529671907425, | |
| "learning_rate": 1.5192637620682981e-05, | |
| "loss": 0.7227, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6357615894039735, | |
| "grad_norm": 0.03497767448425293, | |
| "learning_rate": 1.4557182178490636e-05, | |
| "loss": 0.7607, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6445916114790287, | |
| "grad_norm": 0.03499361500144005, | |
| "learning_rate": 1.3929797833664013e-05, | |
| "loss": 0.7296, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6534216335540839, | |
| "grad_norm": 0.033749066293239594, | |
| "learning_rate": 1.3310969482159297e-05, | |
| "loss": 0.7361, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6622516556291391, | |
| "grad_norm": 0.03505317121744156, | |
| "learning_rate": 1.270117540713368e-05, | |
| "loss": 0.7379, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6710816777041942, | |
| "grad_norm": 0.035697367042303085, | |
| "learning_rate": 1.2100886909287478e-05, | |
| "loss": 0.7351, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6799116997792495, | |
| "grad_norm": 0.035562630742788315, | |
| "learning_rate": 1.151056794260289e-05, | |
| "loss": 0.7295, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6887417218543046, | |
| "grad_norm": 0.0363004133105278, | |
| "learning_rate": 1.0930674755760908e-05, | |
| "loss": 0.7333, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6975717439293598, | |
| "grad_norm": 0.034324079751968384, | |
| "learning_rate": 1.0361655539513565e-05, | |
| "loss": 0.7334, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7064017660044151, | |
| "grad_norm": 0.03306734561920166, | |
| "learning_rate": 9.803950080284005e-06, | |
| "loss": 0.7437, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7152317880794702, | |
| "grad_norm": 0.03080984577536583, | |
| "learning_rate": 9.257989420262151e-06, | |
| "loss": 0.7133, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7240618101545254, | |
| "grad_norm": 0.03477946296334267, | |
| "learning_rate": 8.724195524258688e-06, | |
| "loss": 0.7415, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7328918322295805, | |
| "grad_norm": 0.03363949805498123, | |
| "learning_rate": 8.202980953574735e-06, | |
| "loss": 0.7423, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7417218543046358, | |
| "grad_norm": 0.032141055911779404, | |
| "learning_rate": 7.69474854713943e-06, | |
| "loss": 0.7125, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7505518763796909, | |
| "grad_norm": 0.03413500636816025, | |
| "learning_rate": 7.1998911101617575e-06, | |
| "loss": 0.7346, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7593818984547461, | |
| "grad_norm": 0.032283272594213486, | |
| "learning_rate": 6.718791110537287e-06, | |
| "loss": 0.7235, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7682119205298014, | |
| "grad_norm": 0.03352838382124901, | |
| "learning_rate": 6.25182038324447e-06, | |
| "loss": 0.7268, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7770419426048565, | |
| "grad_norm": 0.033114444464445114, | |
| "learning_rate": 5.7993398429589506e-06, | |
| "loss": 0.7251, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7858719646799117, | |
| "grad_norm": 0.03312879428267479, | |
| "learning_rate": 5.361699205108042e-06, | |
| "loss": 0.7216, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7947019867549668, | |
| "grad_norm": 0.034220073372125626, | |
| "learning_rate": 4.939236715580884e-06, | |
| "loss": 0.7386, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8035320088300221, | |
| "grad_norm": 0.03237886354327202, | |
| "learning_rate": 4.5322788893033155e-06, | |
| "loss": 0.734, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8123620309050773, | |
| "grad_norm": 0.032567963004112244, | |
| "learning_rate": 4.14114025787932e-06, | |
| "loss": 0.7519, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8211920529801324, | |
| "grad_norm": 0.032218772917985916, | |
| "learning_rate": 3.7661231264943086e-06, | |
| "loss": 0.7194, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8300220750551877, | |
| "grad_norm": 0.0331319235265255, | |
| "learning_rate": 3.4075173402679574e-06, | |
| "loss": 0.7263, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8388520971302428, | |
| "grad_norm": 0.03236314281821251, | |
| "learning_rate": 3.0656000602372558e-06, | |
| "loss": 0.7093, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.847682119205298, | |
| "grad_norm": 0.03465864434838295, | |
| "learning_rate": 2.7406355491429086e-06, | |
| "loss": 0.7654, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8565121412803532, | |
| "grad_norm": 0.033873483538627625, | |
| "learning_rate": 2.4328749671846116e-06, | |
| "loss": 0.7365, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8653421633554084, | |
| "grad_norm": 0.03332989290356636, | |
| "learning_rate": 2.142556177903096e-06, | |
| "loss": 0.7468, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8741721854304636, | |
| "grad_norm": 0.033005475997924805, | |
| "learning_rate": 1.8699035643389928e-06, | |
| "loss": 0.7264, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8830022075055187, | |
| "grad_norm": 0.034544438123703, | |
| "learning_rate": 1.615127855610496e-06, | |
| "loss": 0.7392, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.891832229580574, | |
| "grad_norm": 0.03568817302584648, | |
| "learning_rate": 1.3784259640440279e-06, | |
| "loss": 0.7378, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9006622516556292, | |
| "grad_norm": 0.03453758731484413, | |
| "learning_rate": 1.1599808329836177e-06, | |
| "loss": 0.7384, | |
| "num_input_tokens_seen": 213909504, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9094922737306843, | |
| "grad_norm": 0.03320000693202019, | |
| "learning_rate": 9.599612953967746e-07, | |
| "loss": 0.7326, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9183222958057395, | |
| "grad_norm": 0.033046990633010864, | |
| "learning_rate": 7.785219433859847e-07, | |
| "loss": 0.7319, | |
| "num_input_tokens_seen": 218103808, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9271523178807947, | |
| "grad_norm": 0.032943662256002426, | |
| "learning_rate": 6.158030087068001e-07, | |
| "loss": 0.7365, | |
| "num_input_tokens_seen": 220200960, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9359823399558499, | |
| "grad_norm": 0.03540504723787308, | |
| "learning_rate": 4.719302543848225e-07, | |
| "loss": 0.75, | |
| "num_input_tokens_seen": 222298112, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9448123620309051, | |
| "grad_norm": 0.03443380072712898, | |
| "learning_rate": 3.470148775153448e-07, | |
| "loss": 0.7468, | |
| "num_input_tokens_seen": 224395264, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9536423841059603, | |
| "grad_norm": 0.03330874443054199, | |
| "learning_rate": 2.4115342332078074e-07, | |
| "loss": 0.7425, | |
| "num_input_tokens_seen": 226492416, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9624724061810155, | |
| "grad_norm": 0.03456017002463341, | |
| "learning_rate": 1.5442771053230665e-07, | |
| "loss": 0.7314, | |
| "num_input_tokens_seen": 228589568, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9713024282560706, | |
| "grad_norm": 0.03423641249537468, | |
| "learning_rate": 8.690476815339244e-08, | |
| "loss": 0.7407, | |
| "num_input_tokens_seen": 230686720, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9801324503311258, | |
| "grad_norm": 0.03197889402508736, | |
| "learning_rate": 3.8636783654100174e-08, | |
| "loss": 0.729, | |
| "num_input_tokens_seen": 232783872, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9889624724061811, | |
| "grad_norm": 0.034751225262880325, | |
| "learning_rate": 9.661062636148744e-09, | |
| "loss": 0.7333, | |
| "num_input_tokens_seen": 234881024, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9977924944812362, | |
| "grad_norm": 0.03236055746674538, | |
| "learning_rate": 0.0, | |
| "loss": 0.7217, | |
| "num_input_tokens_seen": 236978176, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9977924944812362, | |
| "num_input_tokens_seen": 236978176, | |
| "step": 113, | |
| "total_flos": 1.0486889344470614e+19, | |
| "train_loss": 0.7524756815581195, | |
| "train_runtime": 19134.3763, | |
| "train_samples_per_second": 3.027, | |
| "train_steps_per_second": 0.006 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 113, | |
| "num_input_tokens_seen": 236978176, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0486889344470614e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |