vntl-13b-v0.1-qlora / checkpoint-300 /trainer_state.json
lmg-anon's picture
Upload folder using huggingface_hub
52721b3
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.935672514619883,
"eval_steps": 500,
"global_step": 300,
"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
},
{
"epoch": 0.47,
"learning_rate": 0.0005753545130538441,
"loss": 0.7613,
"step": 151
},
{
"epoch": 0.47,
"learning_rate": 0.0005743130054211732,
"loss": 0.736,
"step": 152
},
{
"epoch": 0.48,
"learning_rate": 0.0005732652387346351,
"loss": 0.6814,
"step": 153
},
{
"epoch": 0.48,
"learning_rate": 0.0005722112392986265,
"loss": 0.7002,
"step": 154
},
{
"epoch": 0.48,
"learning_rate": 0.0005711510335740182,
"loss": 0.7023,
"step": 155
},
{
"epoch": 0.49,
"learning_rate": 0.0005700846481774913,
"loss": 0.7617,
"step": 156
},
{
"epoch": 0.49,
"learning_rate": 0.0005690121098808687,
"loss": 0.7079,
"step": 157
},
{
"epoch": 0.49,
"learning_rate": 0.0005679334456104429,
"loss": 0.7614,
"step": 158
},
{
"epoch": 0.5,
"learning_rate": 0.000566848682446301,
"loss": 0.6786,
"step": 159
},
{
"epoch": 0.5,
"learning_rate": 0.0005657578476216432,
"loss": 0.6773,
"step": 160
},
{
"epoch": 0.5,
"learning_rate": 0.0005646609685221003,
"loss": 0.7085,
"step": 161
},
{
"epoch": 0.51,
"learning_rate": 0.0005635580726850462,
"loss": 0.7167,
"step": 162
},
{
"epoch": 0.51,
"learning_rate": 0.0005624491877989055,
"loss": 0.7192,
"step": 163
},
{
"epoch": 0.51,
"learning_rate": 0.0005613343417024599,
"loss": 0.6761,
"step": 164
},
{
"epoch": 0.51,
"learning_rate": 0.0005602135623841478,
"loss": 0.7508,
"step": 165
},
{
"epoch": 0.52,
"learning_rate": 0.0005590868779813627,
"loss": 0.6978,
"step": 166
},
{
"epoch": 0.52,
"learning_rate": 0.0005579543167797467,
"loss": 0.7459,
"step": 167
},
{
"epoch": 0.52,
"learning_rate": 0.0005568159072124794,
"loss": 0.7438,
"step": 168
},
{
"epoch": 0.53,
"learning_rate": 0.0005556716778595654,
"loss": 0.7073,
"step": 169
},
{
"epoch": 0.53,
"learning_rate": 0.0005545216574471164,
"loss": 0.6385,
"step": 170
},
{
"epoch": 0.53,
"learning_rate": 0.0005533658748466291,
"loss": 0.6993,
"step": 171
},
{
"epoch": 0.54,
"learning_rate": 0.0005522043590742615,
"loss": 0.7258,
"step": 172
},
{
"epoch": 0.54,
"learning_rate": 0.0005510371392901041,
"loss": 0.7405,
"step": 173
},
{
"epoch": 0.54,
"learning_rate": 0.0005498642447974479,
"loss": 0.7525,
"step": 174
},
{
"epoch": 0.55,
"learning_rate": 0.0005486857050420481,
"loss": 0.6639,
"step": 175
},
{
"epoch": 0.55,
"learning_rate": 0.0005475015496113861,
"loss": 0.7415,
"step": 176
},
{
"epoch": 0.55,
"learning_rate": 0.0005463118082339253,
"loss": 0.7816,
"step": 177
},
{
"epoch": 0.56,
"learning_rate": 0.0005451165107783659,
"loss": 0.711,
"step": 178
},
{
"epoch": 0.56,
"learning_rate": 0.0005439156872528941,
"loss": 0.7138,
"step": 179
},
{
"epoch": 0.56,
"learning_rate": 0.0005427093678044299,
"loss": 0.7069,
"step": 180
},
{
"epoch": 0.56,
"learning_rate": 0.0005414975827178688,
"loss": 0.7553,
"step": 181
},
{
"epoch": 0.57,
"learning_rate": 0.000540280362415323,
"loss": 0.7045,
"step": 182
},
{
"epoch": 0.57,
"learning_rate": 0.0005390577374553561,
"loss": 0.7011,
"step": 183
},
{
"epoch": 0.57,
"learning_rate": 0.0005378297385322177,
"loss": 0.7441,
"step": 184
},
{
"epoch": 0.58,
"learning_rate": 0.0005365963964750707,
"loss": 0.6797,
"step": 185
},
{
"epoch": 0.58,
"learning_rate": 0.0005353577422472196,
"loss": 0.6901,
"step": 186
},
{
"epoch": 0.58,
"learning_rate": 0.0005341138069453313,
"loss": 0.7136,
"step": 187
},
{
"epoch": 0.59,
"learning_rate": 0.0005328646217986553,
"loss": 0.7459,
"step": 188
},
{
"epoch": 0.59,
"learning_rate": 0.0005316102181682396,
"loss": 0.7064,
"step": 189
},
{
"epoch": 0.59,
"learning_rate": 0.0005303506275461433,
"loss": 0.6705,
"step": 190
},
{
"epoch": 0.6,
"learning_rate": 0.0005290858815546459,
"loss": 0.7008,
"step": 191
},
{
"epoch": 0.6,
"learning_rate": 0.0005278160119454536,
"loss": 0.7538,
"step": 192
},
{
"epoch": 0.6,
"learning_rate": 0.0005265410505989021,
"loss": 0.7726,
"step": 193
},
{
"epoch": 0.61,
"learning_rate": 0.000525261029523156,
"loss": 0.7532,
"step": 194
},
{
"epoch": 0.61,
"learning_rate": 0.0005239759808534055,
"loss": 0.6978,
"step": 195
},
{
"epoch": 0.61,
"learning_rate": 0.0005226859368510599,
"loss": 0.7182,
"step": 196
},
{
"epoch": 0.61,
"learning_rate": 0.0005213909299029368,
"loss": 0.6776,
"step": 197
},
{
"epoch": 0.62,
"learning_rate": 0.0005200909925204501,
"loss": 0.7447,
"step": 198
},
{
"epoch": 0.62,
"learning_rate": 0.0005187861573387928,
"loss": 0.7298,
"step": 199
},
{
"epoch": 0.62,
"learning_rate": 0.0005174764571161185,
"loss": 0.6833,
"step": 200
},
{
"epoch": 0.63,
"learning_rate": 0.0005161619247327185,
"loss": 0.7518,
"step": 201
},
{
"epoch": 0.63,
"learning_rate": 0.0005148425931901961,
"loss": 0.7429,
"step": 202
},
{
"epoch": 0.63,
"learning_rate": 0.0005135184956106394,
"loss": 0.763,
"step": 203
},
{
"epoch": 0.64,
"learning_rate": 0.000512189665235788,
"loss": 0.7682,
"step": 204
},
{
"epoch": 0.64,
"learning_rate": 0.0005108561354261996,
"loss": 0.7063,
"step": 205
},
{
"epoch": 0.64,
"learning_rate": 0.0005095179396604121,
"loss": 0.6956,
"step": 206
},
{
"epoch": 0.65,
"learning_rate": 0.0005081751115341034,
"loss": 0.7434,
"step": 207
},
{
"epoch": 0.65,
"learning_rate": 0.0005068276847592474,
"loss": 0.6673,
"step": 208
},
{
"epoch": 0.65,
"learning_rate": 0.0005054756931632682,
"loss": 0.6448,
"step": 209
},
{
"epoch": 0.65,
"learning_rate": 0.0005041191706881909,
"loss": 0.7095,
"step": 210
},
{
"epoch": 0.66,
"learning_rate": 0.0005027581513897888,
"loss": 0.673,
"step": 211
},
{
"epoch": 0.66,
"learning_rate": 0.000501392669436729,
"loss": 0.6363,
"step": 212
},
{
"epoch": 0.66,
"learning_rate": 0.0005000227591097145,
"loss": 0.6711,
"step": 213
},
{
"epoch": 0.67,
"learning_rate": 0.0004986484548006237,
"loss": 0.6375,
"step": 214
},
{
"epoch": 0.67,
"learning_rate": 0.0004972697910116468,
"loss": 0.7466,
"step": 215
},
{
"epoch": 0.67,
"learning_rate": 0.0004958868023544192,
"loss": 0.7147,
"step": 216
},
{
"epoch": 0.68,
"learning_rate": 0.0004944995235491534,
"loss": 0.714,
"step": 217
},
{
"epoch": 0.68,
"learning_rate": 0.0004931079894237669,
"loss": 0.7377,
"step": 218
},
{
"epoch": 0.68,
"learning_rate": 0.0004917122349130078,
"loss": 0.7087,
"step": 219
},
{
"epoch": 0.69,
"learning_rate": 0.000490312295057578,
"loss": 0.6716,
"step": 220
},
{
"epoch": 0.69,
"learning_rate": 0.0004889082050032529,
"loss": 0.7298,
"step": 221
},
{
"epoch": 0.69,
"learning_rate": 0.0004875,
"loss": 0.6557,
"step": 222
},
{
"epoch": 0.7,
"learning_rate": 0.0004860877154010932,
"loss": 0.7042,
"step": 223
},
{
"epoch": 0.7,
"learning_rate": 0.00048467138666222534,
"loss": 0.6617,
"step": 224
},
{
"epoch": 0.7,
"learning_rate": 0.00048325104934061853,
"loss": 0.7019,
"step": 225
},
{
"epoch": 0.7,
"learning_rate": 0.00048182673909413103,
"loss": 0.6756,
"step": 226
},
{
"epoch": 0.71,
"learning_rate": 0.00048039849168036205,
"loss": 0.709,
"step": 227
},
{
"epoch": 0.71,
"learning_rate": 0.00047896634295575434,
"loss": 0.7434,
"step": 228
},
{
"epoch": 0.71,
"learning_rate": 0.00047753032887469385,
"loss": 0.7533,
"step": 229
},
{
"epoch": 0.72,
"learning_rate": 0.0004760904854886072,
"loss": 0.7019,
"step": 230
},
{
"epoch": 0.72,
"learning_rate": 0.0004746468489450562,
"loss": 0.6852,
"step": 231
},
{
"epoch": 0.72,
"learning_rate": 0.0004731994554868307,
"loss": 0.7228,
"step": 232
},
{
"epoch": 0.73,
"learning_rate": 0.000471748341451039,
"loss": 0.7513,
"step": 233
},
{
"epoch": 0.73,
"learning_rate": 0.0004702935432681949,
"loss": 0.6896,
"step": 234
},
{
"epoch": 0.73,
"learning_rate": 0.0004688350974613038,
"loss": 0.6815,
"step": 235
},
{
"epoch": 0.74,
"learning_rate": 0.0004673730406449449,
"loss": 0.7682,
"step": 236
},
{
"epoch": 0.74,
"learning_rate": 0.00046590740952435323,
"loss": 0.7025,
"step": 237
},
{
"epoch": 0.74,
"learning_rate": 0.0004644382408944968,
"loss": 0.6662,
"step": 238
},
{
"epoch": 0.75,
"learning_rate": 0.00046296557163915395,
"loss": 0.7541,
"step": 239
},
{
"epoch": 0.75,
"learning_rate": 0.0004614894387299867,
"loss": 0.7336,
"step": 240
},
{
"epoch": 0.75,
"learning_rate": 0.0004600098792256131,
"loss": 0.6618,
"step": 241
},
{
"epoch": 0.75,
"learning_rate": 0.0004585269302706762,
"loss": 0.6729,
"step": 242
},
{
"epoch": 0.76,
"learning_rate": 0.0004570406290949121,
"loss": 0.7327,
"step": 243
},
{
"epoch": 0.76,
"learning_rate": 0.0004555510130122151,
"loss": 0.6778,
"step": 244
},
{
"epoch": 0.76,
"learning_rate": 0.0004540581194197008,
"loss": 0.6219,
"step": 245
},
{
"epoch": 0.77,
"learning_rate": 0.00045256198579676755,
"loss": 0.6984,
"step": 246
},
{
"epoch": 0.77,
"learning_rate": 0.000451062649704155,
"loss": 0.637,
"step": 247
},
{
"epoch": 0.77,
"learning_rate": 0.000449560148783002,
"loss": 0.658,
"step": 248
},
{
"epoch": 0.78,
"learning_rate": 0.0004480545207539004,
"loss": 0.7305,
"step": 249
},
{
"epoch": 0.78,
"learning_rate": 0.0004465458034159491,
"loss": 0.6788,
"step": 250
},
{
"epoch": 0.78,
"learning_rate": 0.00044503403464580475,
"loss": 0.7096,
"step": 251
},
{
"epoch": 0.79,
"learning_rate": 0.00044351925239673087,
"loss": 0.7108,
"step": 252
},
{
"epoch": 0.79,
"learning_rate": 0.0004420014946976447,
"loss": 0.6518,
"step": 253
},
{
"epoch": 0.79,
"learning_rate": 0.00044048079965216294,
"loss": 0.7262,
"step": 254
},
{
"epoch": 0.8,
"learning_rate": 0.0004389572054376452,
"loss": 0.6988,
"step": 255
},
{
"epoch": 0.8,
"learning_rate": 0.00043743075030423475,
"loss": 0.6637,
"step": 256
},
{
"epoch": 0.8,
"learning_rate": 0.0004359014725738994,
"loss": 0.7055,
"step": 257
},
{
"epoch": 0.8,
"learning_rate": 0.00043436941063946843,
"loss": 0.7179,
"step": 258
},
{
"epoch": 0.81,
"learning_rate": 0.0004328346029636694,
"loss": 0.6955,
"step": 259
},
{
"epoch": 0.81,
"learning_rate": 0.0004312970880781621,
"loss": 0.6749,
"step": 260
},
{
"epoch": 0.81,
"learning_rate": 0.0004297569045825713,
"loss": 0.6711,
"step": 261
},
{
"epoch": 0.82,
"learning_rate": 0.00042821409114351803,
"loss": 0.6366,
"step": 262
},
{
"epoch": 0.82,
"learning_rate": 0.00042666868649364844,
"loss": 0.7144,
"step": 263
},
{
"epoch": 0.82,
"learning_rate": 0.0004251207294306617,
"loss": 0.656,
"step": 264
},
{
"epoch": 0.83,
"learning_rate": 0.00042357025881633535,
"loss": 0.6803,
"step": 265
},
{
"epoch": 0.83,
"learning_rate": 0.00042201731357555073,
"loss": 0.7044,
"step": 266
},
{
"epoch": 0.83,
"learning_rate": 0.0004204619326953149,
"loss": 0.6488,
"step": 267
},
{
"epoch": 0.84,
"learning_rate": 0.00041890415522378223,
"loss": 0.6928,
"step": 268
},
{
"epoch": 0.84,
"learning_rate": 0.00041734402026927394,
"loss": 0.6764,
"step": 269
},
{
"epoch": 0.84,
"learning_rate": 0.00041578156699929636,
"loss": 0.6278,
"step": 270
},
{
"epoch": 0.85,
"learning_rate": 0.0004142168346395577,
"loss": 0.691,
"step": 271
},
{
"epoch": 0.85,
"learning_rate": 0.0004126498624729829,
"loss": 0.6865,
"step": 272
},
{
"epoch": 0.85,
"learning_rate": 0.000411080689838728,
"loss": 0.6715,
"step": 273
},
{
"epoch": 0.85,
"learning_rate": 0.00040950935613119226,
"loss": 0.6563,
"step": 274
},
{
"epoch": 0.86,
"learning_rate": 0.00040793590079902885,
"loss": 0.7608,
"step": 275
},
{
"epoch": 0.86,
"learning_rate": 0.00040636036334415487,
"loss": 0.6189,
"step": 276
},
{
"epoch": 0.86,
"learning_rate": 0.0004047827833207597,
"loss": 0.6981,
"step": 277
},
{
"epoch": 0.87,
"learning_rate": 0.0004032032003343117,
"loss": 0.644,
"step": 278
},
{
"epoch": 0.87,
"learning_rate": 0.0004016216540405639,
"loss": 0.7286,
"step": 279
},
{
"epoch": 0.87,
"learning_rate": 0.0004000381841445586,
"loss": 0.6694,
"step": 280
},
{
"epoch": 0.88,
"learning_rate": 0.00039845283039963093,
"loss": 0.7204,
"step": 281
},
{
"epoch": 0.88,
"learning_rate": 0.0003968656326064099,
"loss": 0.7042,
"step": 282
},
{
"epoch": 0.88,
"learning_rate": 0.00039527663061181983,
"loss": 0.712,
"step": 283
},
{
"epoch": 0.89,
"learning_rate": 0.00039368586430808014,
"loss": 0.7179,
"step": 284
},
{
"epoch": 0.89,
"learning_rate": 0.00039209337363170347,
"loss": 0.6903,
"step": 285
},
{
"epoch": 0.89,
"learning_rate": 0.00039049919856249315,
"loss": 0.6924,
"step": 286
},
{
"epoch": 0.9,
"learning_rate": 0.0003889033791225395,
"loss": 0.6713,
"step": 287
},
{
"epoch": 0.9,
"learning_rate": 0.000387305955375215,
"loss": 0.7852,
"step": 288
},
{
"epoch": 0.9,
"learning_rate": 0.0003857069674241689,
"loss": 0.6517,
"step": 289
},
{
"epoch": 0.9,
"learning_rate": 0.00038410645541232,
"loss": 0.6764,
"step": 290
},
{
"epoch": 0.91,
"learning_rate": 0.0003825044595208488,
"loss": 0.7183,
"step": 291
},
{
"epoch": 0.91,
"learning_rate": 0.000380901019968189,
"loss": 0.6826,
"step": 292
},
{
"epoch": 0.91,
"learning_rate": 0.0003792961770090178,
"loss": 0.6936,
"step": 293
},
{
"epoch": 0.92,
"learning_rate": 0.0003776899709332449,
"loss": 0.718,
"step": 294
},
{
"epoch": 0.92,
"learning_rate": 0.00037608244206500176,
"loss": 0.6795,
"step": 295
},
{
"epoch": 0.92,
"learning_rate": 0.00037447363076162853,
"loss": 0.6517,
"step": 296
},
{
"epoch": 0.93,
"learning_rate": 0.0003728635774126613,
"loss": 0.6849,
"step": 297
},
{
"epoch": 0.93,
"learning_rate": 0.0003712523224388177,
"loss": 0.6663,
"step": 298
},
{
"epoch": 0.93,
"learning_rate": 0.00036963990629098264,
"loss": 0.6585,
"step": 299
},
{
"epoch": 0.94,
"learning_rate": 0.0003680263694491925,
"loss": 0.7054,
"step": 300
}
],
"logging_steps": 1,
"max_steps": 640,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"total_flos": 7.783562896461005e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}