prxy5607's picture
Training in progress, step 150, checkpoint
347a714 verified
raw
history blame
27.7 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.0526315789473684,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007017543859649123,
"grad_norm": 0.00019489355327095836,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.007017543859649123,
"eval_loss": 11.5,
"eval_runtime": 1.1124,
"eval_samples_per_second": 215.742,
"eval_steps_per_second": 53.935,
"step": 1
},
{
"epoch": 0.014035087719298246,
"grad_norm": 7.364416524069384e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.021052631578947368,
"grad_norm": 0.00010246247256873176,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.028070175438596492,
"grad_norm": 0.00013443663192447275,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.03508771929824561,
"grad_norm": 4.613230703398585e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.042105263157894736,
"grad_norm": 9.578445315128192e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.04912280701754386,
"grad_norm": 9.936728747561574e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.056140350877192984,
"grad_norm": 0.000179676542757079,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.06315789473684211,
"grad_norm": 7.581837417092174e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.07017543859649122,
"grad_norm": 0.00010813969129230827,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.07719298245614035,
"grad_norm": 0.00010810636740643531,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.08421052631578947,
"grad_norm": 0.00022396819258574396,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.0912280701754386,
"grad_norm": 0.0002430039894534275,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.09824561403508772,
"grad_norm": 0.0002754931338131428,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.10526315789473684,
"grad_norm": 8.851418533595279e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.11228070175438597,
"grad_norm": 7.622732664458454e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.11929824561403508,
"grad_norm": 0.00011232511315029114,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.12631578947368421,
"grad_norm": 0.00015272368909791112,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.00015221686044242233,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.14035087719298245,
"grad_norm": 0.00015781258116476238,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.14736842105263157,
"grad_norm": 0.0001898309274110943,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.1543859649122807,
"grad_norm": 0.00013631457113660872,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.16140350877192983,
"grad_norm": 0.00016971849254332483,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.16842105263157894,
"grad_norm": 0.000272731005679816,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.17543859649122806,
"grad_norm": 9.159513865597546e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.1824561403508772,
"grad_norm": 0.00016250074259005487,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.18947368421052632,
"grad_norm": 0.0002649310335982591,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.19649122807017544,
"grad_norm": 0.00018527806969359517,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.20350877192982456,
"grad_norm": 0.0004022912762593478,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.21052631578947367,
"grad_norm": 0.0003639620263129473,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.21754385964912282,
"grad_norm": 0.0002767823461908847,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.22456140350877193,
"grad_norm": 0.0002745387319009751,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.23157894736842105,
"grad_norm": 0.0003383495204616338,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.23859649122807017,
"grad_norm": 0.0001990653545362875,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.24561403508771928,
"grad_norm": 0.00039295246824622154,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.25263157894736843,
"grad_norm": 0.00020491330360528082,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.2596491228070175,
"grad_norm": 0.0001439648331142962,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.00021251384168863297,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.2736842105263158,
"grad_norm": 0.00025975375319831073,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.2807017543859649,
"grad_norm": 0.00018315839406568557,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.28771929824561404,
"grad_norm": 0.00017919584934134036,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.29473684210526313,
"grad_norm": 0.0004666546592488885,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.3017543859649123,
"grad_norm": 0.00027068654890172184,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.3087719298245614,
"grad_norm": 0.00021003128495067358,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.3157894736842105,
"grad_norm": 0.00041786220390349627,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.32280701754385965,
"grad_norm": 0.0002459548122715205,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.3298245614035088,
"grad_norm": 0.0008614164544269443,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.3368421052631579,
"grad_norm": 0.0005682702758349478,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.34385964912280703,
"grad_norm": 0.0006924397894181311,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.3508771929824561,
"grad_norm": 0.0005462864646688104,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.3508771929824561,
"eval_loss": 11.5,
"eval_runtime": 1.089,
"eval_samples_per_second": 220.382,
"eval_steps_per_second": 55.095,
"step": 50
},
{
"epoch": 0.35789473684210527,
"grad_norm": 0.0001590331521583721,
"learning_rate": 8.894386393810563e-05,
"loss": 46.0,
"step": 51
},
{
"epoch": 0.3649122807017544,
"grad_norm": 0.0002517325629014522,
"learning_rate": 8.842005554284296e-05,
"loss": 46.0,
"step": 52
},
{
"epoch": 0.3719298245614035,
"grad_norm": 0.00038495680200867355,
"learning_rate": 8.788574348801675e-05,
"loss": 46.0,
"step": 53
},
{
"epoch": 0.37894736842105264,
"grad_norm": 0.00035711415694095194,
"learning_rate": 8.73410738492077e-05,
"loss": 46.0,
"step": 54
},
{
"epoch": 0.38596491228070173,
"grad_norm": 0.00025719121913425624,
"learning_rate": 8.678619553365659e-05,
"loss": 46.0,
"step": 55
},
{
"epoch": 0.3929824561403509,
"grad_norm": 0.0005990781355649233,
"learning_rate": 8.622126023955446e-05,
"loss": 46.0,
"step": 56
},
{
"epoch": 0.4,
"grad_norm": 0.00033211291884072125,
"learning_rate": 8.564642241456986e-05,
"loss": 46.0,
"step": 57
},
{
"epoch": 0.4070175438596491,
"grad_norm": 0.00021700060460716486,
"learning_rate": 8.506183921362443e-05,
"loss": 46.0,
"step": 58
},
{
"epoch": 0.41403508771929826,
"grad_norm": 0.0008800876094028354,
"learning_rate": 8.44676704559283e-05,
"loss": 46.0,
"step": 59
},
{
"epoch": 0.42105263157894735,
"grad_norm": 0.00013740916620008647,
"learning_rate": 8.386407858128706e-05,
"loss": 46.0,
"step": 60
},
{
"epoch": 0.4280701754385965,
"grad_norm": 0.0002479272079654038,
"learning_rate": 8.32512286056924e-05,
"loss": 46.0,
"step": 61
},
{
"epoch": 0.43508771929824563,
"grad_norm": 0.00034167649573646486,
"learning_rate": 8.262928807620843e-05,
"loss": 46.0,
"step": 62
},
{
"epoch": 0.4421052631578947,
"grad_norm": 0.00042292135185562074,
"learning_rate": 8.199842702516583e-05,
"loss": 46.0,
"step": 63
},
{
"epoch": 0.44912280701754387,
"grad_norm": 0.0006429964560084045,
"learning_rate": 8.135881792367686e-05,
"loss": 46.0,
"step": 64
},
{
"epoch": 0.45614035087719296,
"grad_norm": 0.0011160393478348851,
"learning_rate": 8.07106356344834e-05,
"loss": 46.0,
"step": 65
},
{
"epoch": 0.4631578947368421,
"grad_norm": 0.0007693542283959687,
"learning_rate": 8.005405736415126e-05,
"loss": 46.0,
"step": 66
},
{
"epoch": 0.47017543859649125,
"grad_norm": 0.0007329719373956323,
"learning_rate": 7.938926261462366e-05,
"loss": 46.0,
"step": 67
},
{
"epoch": 0.47719298245614034,
"grad_norm": 0.0005806947592645884,
"learning_rate": 7.871643313414718e-05,
"loss": 46.0,
"step": 68
},
{
"epoch": 0.4842105263157895,
"grad_norm": 0.0008097690879367292,
"learning_rate": 7.803575286758364e-05,
"loss": 46.0,
"step": 69
},
{
"epoch": 0.49122807017543857,
"grad_norm": 0.0006609997944906354,
"learning_rate": 7.734740790612136e-05,
"loss": 46.0,
"step": 70
},
{
"epoch": 0.4982456140350877,
"grad_norm": 0.0005276701413094997,
"learning_rate": 7.66515864363997e-05,
"loss": 46.0,
"step": 71
},
{
"epoch": 0.5052631578947369,
"grad_norm": 0.0004524849937297404,
"learning_rate": 7.594847868906076e-05,
"loss": 46.0,
"step": 72
},
{
"epoch": 0.512280701754386,
"grad_norm": 0.0005017757648602128,
"learning_rate": 7.52382768867422e-05,
"loss": 46.0,
"step": 73
},
{
"epoch": 0.519298245614035,
"grad_norm": 0.0005103429430164397,
"learning_rate": 7.452117519152542e-05,
"loss": 46.0,
"step": 74
},
{
"epoch": 0.5263157894736842,
"grad_norm": 0.0004560076049529016,
"learning_rate": 7.379736965185368e-05,
"loss": 46.0,
"step": 75
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.0004853313439525664,
"learning_rate": 7.30670581489344e-05,
"loss": 46.0,
"step": 76
},
{
"epoch": 0.5403508771929825,
"grad_norm": 0.0006764770951122046,
"learning_rate": 7.233044034264034e-05,
"loss": 46.0,
"step": 77
},
{
"epoch": 0.5473684210526316,
"grad_norm": 0.0005036768270656466,
"learning_rate": 7.158771761692464e-05,
"loss": 46.0,
"step": 78
},
{
"epoch": 0.5543859649122806,
"grad_norm": 0.000563987938221544,
"learning_rate": 7.083909302476453e-05,
"loss": 46.0,
"step": 79
},
{
"epoch": 0.5614035087719298,
"grad_norm": 0.0005308451363816857,
"learning_rate": 7.008477123264848e-05,
"loss": 46.0,
"step": 80
},
{
"epoch": 0.5684210526315789,
"grad_norm": 0.0014087476301938295,
"learning_rate": 6.932495846462261e-05,
"loss": 46.0,
"step": 81
},
{
"epoch": 0.5754385964912281,
"grad_norm": 0.0009721022797748446,
"learning_rate": 6.855986244591104e-05,
"loss": 46.0,
"step": 82
},
{
"epoch": 0.5824561403508772,
"grad_norm": 0.0012967647053301334,
"learning_rate": 6.778969234612584e-05,
"loss": 46.0,
"step": 83
},
{
"epoch": 0.5894736842105263,
"grad_norm": 0.0007597978110425174,
"learning_rate": 6.701465872208216e-05,
"loss": 46.0,
"step": 84
},
{
"epoch": 0.5964912280701754,
"grad_norm": 0.00031303270952776074,
"learning_rate": 6.623497346023418e-05,
"loss": 46.0,
"step": 85
},
{
"epoch": 0.6035087719298246,
"grad_norm": 0.000490807753521949,
"learning_rate": 6.545084971874738e-05,
"loss": 46.0,
"step": 86
},
{
"epoch": 0.6105263157894737,
"grad_norm": 0.0007696722750551999,
"learning_rate": 6.466250186922325e-05,
"loss": 46.0,
"step": 87
},
{
"epoch": 0.6175438596491228,
"grad_norm": 0.0006790944607928395,
"learning_rate": 6.387014543809223e-05,
"loss": 46.0,
"step": 88
},
{
"epoch": 0.624561403508772,
"grad_norm": 0.0005392750608734787,
"learning_rate": 6.307399704769099e-05,
"loss": 46.0,
"step": 89
},
{
"epoch": 0.631578947368421,
"grad_norm": 0.0007435527513734996,
"learning_rate": 6.227427435703997e-05,
"loss": 46.0,
"step": 90
},
{
"epoch": 0.6385964912280702,
"grad_norm": 0.0008648040820844471,
"learning_rate": 6.147119600233758e-05,
"loss": 46.0,
"step": 91
},
{
"epoch": 0.6456140350877193,
"grad_norm": 0.000883813772816211,
"learning_rate": 6.066498153718735e-05,
"loss": 46.0,
"step": 92
},
{
"epoch": 0.6526315789473685,
"grad_norm": 0.0002953899675048888,
"learning_rate": 5.985585137257401e-05,
"loss": 46.0,
"step": 93
},
{
"epoch": 0.6596491228070176,
"grad_norm": 0.0015498731518164277,
"learning_rate": 5.90440267166055e-05,
"loss": 46.0,
"step": 94
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.0003299638337921351,
"learning_rate": 5.8229729514036705e-05,
"loss": 46.0,
"step": 95
},
{
"epoch": 0.6736842105263158,
"grad_norm": 0.0003828226472251117,
"learning_rate": 5.74131823855921e-05,
"loss": 46.0,
"step": 96
},
{
"epoch": 0.6807017543859649,
"grad_norm": 0.000486409873701632,
"learning_rate": 5.6594608567103456e-05,
"loss": 46.0,
"step": 97
},
{
"epoch": 0.6877192982456141,
"grad_norm": 0.0006001433939673007,
"learning_rate": 5.577423184847932e-05,
"loss": 46.0,
"step": 98
},
{
"epoch": 0.6947368421052632,
"grad_norm": 0.0012996380683034658,
"learning_rate": 5.495227651252315e-05,
"loss": 46.0,
"step": 99
},
{
"epoch": 0.7017543859649122,
"grad_norm": 0.0014257560251280665,
"learning_rate": 5.4128967273616625e-05,
"loss": 46.0,
"step": 100
},
{
"epoch": 0.7017543859649122,
"eval_loss": 11.5,
"eval_runtime": 1.0931,
"eval_samples_per_second": 219.551,
"eval_steps_per_second": 54.888,
"step": 100
},
{
"epoch": 0.7087719298245614,
"grad_norm": 0.0012257606722414494,
"learning_rate": 5.330452921628497e-05,
"loss": 46.0,
"step": 101
},
{
"epoch": 0.7157894736842105,
"grad_norm": 0.0010115664917975664,
"learning_rate": 5.247918773366112e-05,
"loss": 46.0,
"step": 102
},
{
"epoch": 0.7228070175438597,
"grad_norm": 0.0006419376586563885,
"learning_rate": 5.165316846586541e-05,
"loss": 46.0,
"step": 103
},
{
"epoch": 0.7298245614035088,
"grad_norm": 0.0012752835173159838,
"learning_rate": 5.0826697238317935e-05,
"loss": 46.0,
"step": 104
},
{
"epoch": 0.7368421052631579,
"grad_norm": 0.0010647501330822706,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 105
},
{
"epoch": 0.743859649122807,
"grad_norm": 0.0008769280975684524,
"learning_rate": 4.917330276168208e-05,
"loss": 46.0,
"step": 106
},
{
"epoch": 0.7508771929824561,
"grad_norm": 0.0008139450219459832,
"learning_rate": 4.834683153413459e-05,
"loss": 46.0,
"step": 107
},
{
"epoch": 0.7578947368421053,
"grad_norm": 0.0008274679421447217,
"learning_rate": 4.7520812266338885e-05,
"loss": 46.0,
"step": 108
},
{
"epoch": 0.7649122807017544,
"grad_norm": 0.0007187628070823848,
"learning_rate": 4.669547078371504e-05,
"loss": 46.0,
"step": 109
},
{
"epoch": 0.7719298245614035,
"grad_norm": 0.0005940390983596444,
"learning_rate": 4.5871032726383386e-05,
"loss": 46.0,
"step": 110
},
{
"epoch": 0.7789473684210526,
"grad_norm": 0.0005565033643506467,
"learning_rate": 4.504772348747687e-05,
"loss": 46.0,
"step": 111
},
{
"epoch": 0.7859649122807018,
"grad_norm": 0.001425198744982481,
"learning_rate": 4.4225768151520694e-05,
"loss": 46.0,
"step": 112
},
{
"epoch": 0.7929824561403509,
"grad_norm": 0.0010411118855699897,
"learning_rate": 4.3405391432896555e-05,
"loss": 46.0,
"step": 113
},
{
"epoch": 0.8,
"grad_norm": 0.0007794569828547537,
"learning_rate": 4.2586817614407895e-05,
"loss": 46.0,
"step": 114
},
{
"epoch": 0.8070175438596491,
"grad_norm": 0.0007496122270822525,
"learning_rate": 4.17702704859633e-05,
"loss": 46.0,
"step": 115
},
{
"epoch": 0.8140350877192982,
"grad_norm": 0.0025550099089741707,
"learning_rate": 4.095597328339452e-05,
"loss": 46.0,
"step": 116
},
{
"epoch": 0.8210526315789474,
"grad_norm": 0.0014956446830183268,
"learning_rate": 4.0144148627425993e-05,
"loss": 46.0,
"step": 117
},
{
"epoch": 0.8280701754385965,
"grad_norm": 0.001554667018353939,
"learning_rate": 3.933501846281267e-05,
"loss": 46.0,
"step": 118
},
{
"epoch": 0.8350877192982457,
"grad_norm": 0.0009093582048080862,
"learning_rate": 3.852880399766243e-05,
"loss": 46.0,
"step": 119
},
{
"epoch": 0.8421052631578947,
"grad_norm": 0.0004268164047971368,
"learning_rate": 3.772572564296005e-05,
"loss": 46.0,
"step": 120
},
{
"epoch": 0.8491228070175438,
"grad_norm": 0.0009041683515533805,
"learning_rate": 3.6926002952309016e-05,
"loss": 46.0,
"step": 121
},
{
"epoch": 0.856140350877193,
"grad_norm": 0.0011187340132892132,
"learning_rate": 3.612985456190778e-05,
"loss": 46.0,
"step": 122
},
{
"epoch": 0.8631578947368421,
"grad_norm": 0.0009658985654823482,
"learning_rate": 3.533749813077677e-05,
"loss": 46.0,
"step": 123
},
{
"epoch": 0.8701754385964913,
"grad_norm": 0.000933460658416152,
"learning_rate": 3.4549150281252636e-05,
"loss": 46.0,
"step": 124
},
{
"epoch": 0.8771929824561403,
"grad_norm": 0.0015150044346228242,
"learning_rate": 3.3765026539765834e-05,
"loss": 46.0,
"step": 125
},
{
"epoch": 0.8842105263157894,
"grad_norm": 0.0014008400030434132,
"learning_rate": 3.298534127791785e-05,
"loss": 46.0,
"step": 126
},
{
"epoch": 0.8912280701754386,
"grad_norm": 0.0007195834186859429,
"learning_rate": 3.221030765387417e-05,
"loss": 46.0,
"step": 127
},
{
"epoch": 0.8982456140350877,
"grad_norm": 0.0007124911644496024,
"learning_rate": 3.144013755408895e-05,
"loss": 46.0,
"step": 128
},
{
"epoch": 0.9052631578947369,
"grad_norm": 0.0006670788279734552,
"learning_rate": 3.0675041535377405e-05,
"loss": 46.0,
"step": 129
},
{
"epoch": 0.9122807017543859,
"grad_norm": 0.0005826579872518778,
"learning_rate": 2.991522876735154e-05,
"loss": 46.0,
"step": 130
},
{
"epoch": 0.9192982456140351,
"grad_norm": 0.0007034334703348577,
"learning_rate": 2.916090697523549e-05,
"loss": 46.0,
"step": 131
},
{
"epoch": 0.9263157894736842,
"grad_norm": 0.0011828525457531214,
"learning_rate": 2.8412282383075363e-05,
"loss": 46.0,
"step": 132
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.001470727613195777,
"learning_rate": 2.766955965735968e-05,
"loss": 46.0,
"step": 133
},
{
"epoch": 0.9403508771929825,
"grad_norm": 0.0015500085428357124,
"learning_rate": 2.693294185106562e-05,
"loss": 46.0,
"step": 134
},
{
"epoch": 0.9473684210526315,
"grad_norm": 0.0017265240894630551,
"learning_rate": 2.6202630348146324e-05,
"loss": 46.0,
"step": 135
},
{
"epoch": 0.9543859649122807,
"grad_norm": 0.001150521100498736,
"learning_rate": 2.547882480847461e-05,
"loss": 46.0,
"step": 136
},
{
"epoch": 0.9614035087719298,
"grad_norm": 0.0015598469180986285,
"learning_rate": 2.476172311325783e-05,
"loss": 46.0,
"step": 137
},
{
"epoch": 0.968421052631579,
"grad_norm": 0.0019701942801475525,
"learning_rate": 2.405152131093926e-05,
"loss": 46.0,
"step": 138
},
{
"epoch": 0.9754385964912281,
"grad_norm": 0.0017886764835566282,
"learning_rate": 2.3348413563600325e-05,
"loss": 46.0,
"step": 139
},
{
"epoch": 0.9824561403508771,
"grad_norm": 0.0017487804871052504,
"learning_rate": 2.2652592093878666e-05,
"loss": 46.0,
"step": 140
},
{
"epoch": 0.9894736842105263,
"grad_norm": 0.001383704598993063,
"learning_rate": 2.196424713241637e-05,
"loss": 46.0,
"step": 141
},
{
"epoch": 0.9964912280701754,
"grad_norm": 0.0008848085417412221,
"learning_rate": 2.128356686585282e-05,
"loss": 46.0,
"step": 142
},
{
"epoch": 1.0035087719298246,
"grad_norm": 0.0013748030178248882,
"learning_rate": 2.061073738537635e-05,
"loss": 46.0,
"step": 143
},
{
"epoch": 1.0105263157894737,
"grad_norm": 0.001106771407648921,
"learning_rate": 1.9945942635848748e-05,
"loss": 46.0,
"step": 144
},
{
"epoch": 1.0175438596491229,
"grad_norm": 0.0009946925565600395,
"learning_rate": 1.928936436551661e-05,
"loss": 46.0,
"step": 145
},
{
"epoch": 1.024561403508772,
"grad_norm": 0.0011375717585906386,
"learning_rate": 1.8641182076323148e-05,
"loss": 46.0,
"step": 146
},
{
"epoch": 1.0315789473684212,
"grad_norm": 0.0009219716885127127,
"learning_rate": 1.800157297483417e-05,
"loss": 46.0,
"step": 147
},
{
"epoch": 1.03859649122807,
"grad_norm": 0.0007757642306387424,
"learning_rate": 1.7370711923791567e-05,
"loss": 46.0,
"step": 148
},
{
"epoch": 1.0456140350877192,
"grad_norm": 0.0007281502475962043,
"learning_rate": 1.6748771394307585e-05,
"loss": 46.0,
"step": 149
},
{
"epoch": 1.0526315789473684,
"grad_norm": 0.001610603998415172,
"learning_rate": 1.6135921418712956e-05,
"loss": 46.0,
"step": 150
},
{
"epoch": 1.0526315789473684,
"eval_loss": 11.5,
"eval_runtime": 1.0926,
"eval_samples_per_second": 219.662,
"eval_steps_per_second": 54.916,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 24118847078400.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}