lora_test / checkpoint-334 /trainer_state.json
joseagmz's picture
Upload folder using huggingface_hub
6f68cb5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9776119402985075,
"eval_steps": 42,
"global_step": 334,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 1.6541,
"step": 1
},
{
"epoch": 0.01,
"eval_loss": 1.7634071111679077,
"eval_runtime": 14.5059,
"eval_samples_per_second": 56.46,
"eval_steps_per_second": 28.264,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.6887,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 6e-05,
"loss": 1.828,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 8e-05,
"loss": 1.589,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 1.927,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 0.00012,
"loss": 1.6362,
"step": 6
},
{
"epoch": 0.04,
"learning_rate": 0.00014,
"loss": 1.8546,
"step": 7
},
{
"epoch": 0.05,
"learning_rate": 0.00016,
"loss": 1.5843,
"step": 8
},
{
"epoch": 0.05,
"learning_rate": 0.00018,
"loss": 1.5592,
"step": 9
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.5539,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 0.0001999988602302209,
"loss": 1.4449,
"step": 11
},
{
"epoch": 0.07,
"learning_rate": 0.0001999954409468652,
"loss": 1.8818,
"step": 12
},
{
"epoch": 0.08,
"learning_rate": 0.0001999897422278767,
"loss": 1.6656,
"step": 13
},
{
"epoch": 0.08,
"learning_rate": 0.00019998176420316002,
"loss": 1.4607,
"step": 14
},
{
"epoch": 0.09,
"learning_rate": 0.0001999715070545774,
"loss": 1.4013,
"step": 15
},
{
"epoch": 0.1,
"learning_rate": 0.00019995897101594454,
"loss": 1.5258,
"step": 16
},
{
"epoch": 0.1,
"learning_rate": 0.00019994415637302547,
"loss": 1.404,
"step": 17
},
{
"epoch": 0.11,
"learning_rate": 0.00019992706346352577,
"loss": 1.3919,
"step": 18
},
{
"epoch": 0.11,
"learning_rate": 0.00019990769267708516,
"loss": 1.355,
"step": 19
},
{
"epoch": 0.12,
"learning_rate": 0.00019988604445526827,
"loss": 1.3763,
"step": 20
},
{
"epoch": 0.13,
"learning_rate": 0.000199862119291555,
"loss": 1.3314,
"step": 21
},
{
"epoch": 0.13,
"learning_rate": 0.00019983591773132882,
"loss": 1.4246,
"step": 22
},
{
"epoch": 0.14,
"learning_rate": 0.00019980744037186469,
"loss": 1.5723,
"step": 23
},
{
"epoch": 0.14,
"learning_rate": 0.00019977668786231534,
"loss": 1.2536,
"step": 24
},
{
"epoch": 0.15,
"learning_rate": 0.0001997436609036963,
"loss": 1.3087,
"step": 25
},
{
"epoch": 0.16,
"learning_rate": 0.0001997083602488702,
"loss": 1.2783,
"step": 26
},
{
"epoch": 0.16,
"learning_rate": 0.00019967078670252945,
"loss": 1.2792,
"step": 27
},
{
"epoch": 0.17,
"learning_rate": 0.00019963094112117785,
"loss": 1.2476,
"step": 28
},
{
"epoch": 0.17,
"learning_rate": 0.00019958882441311126,
"loss": 1.265,
"step": 29
},
{
"epoch": 0.18,
"learning_rate": 0.00019954443753839667,
"loss": 1.0884,
"step": 30
},
{
"epoch": 0.19,
"learning_rate": 0.00019949778150885042,
"loss": 1.3294,
"step": 31
},
{
"epoch": 0.19,
"learning_rate": 0.00019944885738801518,
"loss": 1.3434,
"step": 32
},
{
"epoch": 0.2,
"learning_rate": 0.00019939766629113566,
"loss": 1.1457,
"step": 33
},
{
"epoch": 0.2,
"learning_rate": 0.00019934420938513313,
"loss": 1.2138,
"step": 34
},
{
"epoch": 0.21,
"learning_rate": 0.00019928848788857887,
"loss": 1.2118,
"step": 35
},
{
"epoch": 0.21,
"learning_rate": 0.00019923050307166655,
"loss": 1.1426,
"step": 36
},
{
"epoch": 0.22,
"learning_rate": 0.00019917025625618292,
"loss": 1.6279,
"step": 37
},
{
"epoch": 0.23,
"learning_rate": 0.000199107748815478,
"loss": 1.5021,
"step": 38
},
{
"epoch": 0.23,
"learning_rate": 0.00019904298217443366,
"loss": 1.3728,
"step": 39
},
{
"epoch": 0.24,
"learning_rate": 0.00019897595780943102,
"loss": 1.2034,
"step": 40
},
{
"epoch": 0.24,
"learning_rate": 0.00019890667724831707,
"loss": 1.3718,
"step": 41
},
{
"epoch": 0.25,
"learning_rate": 0.00019883514207036956,
"loss": 1.2512,
"step": 42
},
{
"epoch": 0.25,
"eval_loss": 0.8978323936462402,
"eval_runtime": 14.6352,
"eval_samples_per_second": 55.961,
"eval_steps_per_second": 28.015,
"step": 42
},
{
"epoch": 0.26,
"learning_rate": 0.00019876135390626122,
"loss": 1.1787,
"step": 43
},
{
"epoch": 0.26,
"learning_rate": 0.0001986853144380224,
"loss": 1.1917,
"step": 44
},
{
"epoch": 0.27,
"learning_rate": 0.00019860702539900287,
"loss": 1.1933,
"step": 45
},
{
"epoch": 0.27,
"learning_rate": 0.00019852648857383222,
"loss": 1.1922,
"step": 46
},
{
"epoch": 0.28,
"learning_rate": 0.00019844370579837927,
"loss": 1.3017,
"step": 47
},
{
"epoch": 0.29,
"learning_rate": 0.00019835867895971014,
"loss": 1.1193,
"step": 48
},
{
"epoch": 0.29,
"learning_rate": 0.0001982714099960452,
"loss": 1.1572,
"step": 49
},
{
"epoch": 0.3,
"learning_rate": 0.00019818190089671508,
"loss": 1.3277,
"step": 50
},
{
"epoch": 0.3,
"learning_rate": 0.00019809015370211502,
"loss": 1.0658,
"step": 51
},
{
"epoch": 0.31,
"learning_rate": 0.0001979961705036587,
"loss": 1.1656,
"step": 52
},
{
"epoch": 0.32,
"learning_rate": 0.00019789995344373024,
"loss": 1.4204,
"step": 53
},
{
"epoch": 0.32,
"learning_rate": 0.00019780150471563558,
"loss": 1.1551,
"step": 54
},
{
"epoch": 0.33,
"learning_rate": 0.0001977008265635525,
"loss": 1.0993,
"step": 55
},
{
"epoch": 0.33,
"learning_rate": 0.00019759792128247922,
"loss": 1.1311,
"step": 56
},
{
"epoch": 0.34,
"learning_rate": 0.00019749279121818235,
"loss": 1.2163,
"step": 57
},
{
"epoch": 0.35,
"learning_rate": 0.00019738543876714334,
"loss": 1.3178,
"step": 58
},
{
"epoch": 0.35,
"learning_rate": 0.00019727586637650373,
"loss": 1.3744,
"step": 59
},
{
"epoch": 0.36,
"learning_rate": 0.00019716407654400952,
"loss": 1.1413,
"step": 60
},
{
"epoch": 0.36,
"learning_rate": 0.00019705007181795416,
"loss": 1.0372,
"step": 61
},
{
"epoch": 0.37,
"learning_rate": 0.00019693385479712048,
"loss": 1.1601,
"step": 62
},
{
"epoch": 0.38,
"learning_rate": 0.00019681542813072145,
"loss": 1.0976,
"step": 63
},
{
"epoch": 0.38,
"learning_rate": 0.00019669479451833976,
"loss": 1.1584,
"step": 64
},
{
"epoch": 0.39,
"learning_rate": 0.00019657195670986637,
"loss": 1.0962,
"step": 65
},
{
"epoch": 0.39,
"learning_rate": 0.00019644691750543767,
"loss": 1.1044,
"step": 66
},
{
"epoch": 0.4,
"learning_rate": 0.0001963196797553718,
"loss": 1.2431,
"step": 67
},
{
"epoch": 0.41,
"learning_rate": 0.00019619024636010363,
"loss": 1.1651,
"step": 68
},
{
"epoch": 0.41,
"learning_rate": 0.00019605862027011856,
"loss": 1.0513,
"step": 69
},
{
"epoch": 0.42,
"learning_rate": 0.00019592480448588542,
"loss": 1.0175,
"step": 70
},
{
"epoch": 0.42,
"learning_rate": 0.00019578880205778793,
"loss": 1.1306,
"step": 71
},
{
"epoch": 0.43,
"learning_rate": 0.00019565061608605526,
"loss": 1.3121,
"step": 72
},
{
"epoch": 0.44,
"learning_rate": 0.00019551024972069126,
"loss": 1.266,
"step": 73
},
{
"epoch": 0.44,
"learning_rate": 0.00019536770616140276,
"loss": 1.1099,
"step": 74
},
{
"epoch": 0.45,
"learning_rate": 0.0001952229886575266,
"loss": 1.1012,
"step": 75
},
{
"epoch": 0.45,
"learning_rate": 0.00019507610050795558,
"loss": 1.1272,
"step": 76
},
{
"epoch": 0.46,
"learning_rate": 0.0001949270450610631,
"loss": 1.2016,
"step": 77
},
{
"epoch": 0.47,
"learning_rate": 0.00019477582571462705,
"loss": 1.1746,
"step": 78
},
{
"epoch": 0.47,
"learning_rate": 0.00019462244591575222,
"loss": 1.1349,
"step": 79
},
{
"epoch": 0.48,
"learning_rate": 0.0001944669091607919,
"loss": 1.4311,
"step": 80
},
{
"epoch": 0.48,
"learning_rate": 0.00019430921899526787,
"loss": 1.1033,
"step": 81
},
{
"epoch": 0.49,
"learning_rate": 0.00019414937901378982,
"loss": 1.2491,
"step": 82
},
{
"epoch": 0.5,
"learning_rate": 0.0001939873928599734,
"loss": 1.1044,
"step": 83
},
{
"epoch": 0.5,
"learning_rate": 0.00019382326422635705,
"loss": 1.1008,
"step": 84
},
{
"epoch": 0.5,
"eval_loss": 0.8307072520256042,
"eval_runtime": 14.6668,
"eval_samples_per_second": 55.841,
"eval_steps_per_second": 27.954,
"step": 84
},
{
"epoch": 0.51,
"learning_rate": 0.0001936569968543179,
"loss": 1.2317,
"step": 85
},
{
"epoch": 0.51,
"learning_rate": 0.00019348859453398646,
"loss": 1.2317,
"step": 86
},
{
"epoch": 0.52,
"learning_rate": 0.00019331806110416027,
"loss": 1.0989,
"step": 87
},
{
"epoch": 0.53,
"learning_rate": 0.00019314540045221626,
"loss": 1.0466,
"step": 88
},
{
"epoch": 0.53,
"learning_rate": 0.00019297061651402236,
"loss": 1.0798,
"step": 89
},
{
"epoch": 0.54,
"learning_rate": 0.0001927937132738476,
"loss": 1.1175,
"step": 90
},
{
"epoch": 0.54,
"learning_rate": 0.0001926146947642712,
"loss": 1.1292,
"step": 91
},
{
"epoch": 0.55,
"learning_rate": 0.000192433565066091,
"loss": 1.0464,
"step": 92
},
{
"epoch": 0.56,
"learning_rate": 0.00019225032830823011,
"loss": 1.1549,
"step": 93
},
{
"epoch": 0.56,
"learning_rate": 0.00019206498866764288,
"loss": 1.1129,
"step": 94
},
{
"epoch": 0.57,
"learning_rate": 0.00019187755036921978,
"loss": 0.9965,
"step": 95
},
{
"epoch": 0.57,
"learning_rate": 0.0001916880176856909,
"loss": 1.0767,
"step": 96
},
{
"epoch": 0.58,
"learning_rate": 0.0001914963949375288,
"loss": 1.1546,
"step": 97
},
{
"epoch": 0.59,
"learning_rate": 0.0001913026864928498,
"loss": 0.9627,
"step": 98
},
{
"epoch": 0.59,
"learning_rate": 0.00019110689676731454,
"loss": 1.0039,
"step": 99
},
{
"epoch": 0.6,
"learning_rate": 0.00019090903022402729,
"loss": 1.066,
"step": 100
},
{
"epoch": 0.6,
"learning_rate": 0.00019070909137343408,
"loss": 1.0654,
"step": 101
},
{
"epoch": 0.61,
"learning_rate": 0.00019050708477322018,
"loss": 1.3323,
"step": 102
},
{
"epoch": 0.61,
"learning_rate": 0.00019030301502820596,
"loss": 1.1247,
"step": 103
},
{
"epoch": 0.62,
"learning_rate": 0.0001900968867902419,
"loss": 1.0261,
"step": 104
},
{
"epoch": 0.63,
"learning_rate": 0.00018988870475810282,
"loss": 1.0935,
"step": 105
},
{
"epoch": 0.63,
"learning_rate": 0.00018967847367738048,
"loss": 1.1043,
"step": 106
},
{
"epoch": 0.64,
"learning_rate": 0.00018946619834037546,
"loss": 1.1982,
"step": 107
},
{
"epoch": 0.64,
"learning_rate": 0.00018925188358598813,
"loss": 1.0445,
"step": 108
},
{
"epoch": 0.65,
"learning_rate": 0.00018903553429960802,
"loss": 1.086,
"step": 109
},
{
"epoch": 0.66,
"learning_rate": 0.00018881715541300276,
"loss": 1.1509,
"step": 110
},
{
"epoch": 0.66,
"learning_rate": 0.00018859675190420537,
"loss": 1.1473,
"step": 111
},
{
"epoch": 0.67,
"learning_rate": 0.00018837432879740114,
"loss": 1.1677,
"step": 112
},
{
"epoch": 0.67,
"learning_rate": 0.0001881498911628127,
"loss": 1.006,
"step": 113
},
{
"epoch": 0.68,
"learning_rate": 0.00018792344411658468,
"loss": 1.0503,
"step": 114
},
{
"epoch": 0.69,
"learning_rate": 0.00018769499282066717,
"loss": 1.163,
"step": 115
},
{
"epoch": 0.69,
"learning_rate": 0.00018746454248269777,
"loss": 1.1443,
"step": 116
},
{
"epoch": 0.7,
"learning_rate": 0.0001872320983558831,
"loss": 0.9785,
"step": 117
},
{
"epoch": 0.7,
"learning_rate": 0.000186997665738879,
"loss": 1.0605,
"step": 118
},
{
"epoch": 0.71,
"learning_rate": 0.0001867612499756697,
"loss": 1.0203,
"step": 119
},
{
"epoch": 0.72,
"learning_rate": 0.00018652285645544603,
"loss": 1.146,
"step": 120
},
{
"epoch": 0.72,
"learning_rate": 0.00018628249061248262,
"loss": 1.12,
"step": 121
},
{
"epoch": 0.73,
"learning_rate": 0.00018604015792601396,
"loss": 1.1499,
"step": 122
},
{
"epoch": 0.73,
"learning_rate": 0.00018579586392010943,
"loss": 1.1273,
"step": 123
},
{
"epoch": 0.74,
"learning_rate": 0.0001855496141635476,
"loss": 1.0404,
"step": 124
},
{
"epoch": 0.75,
"learning_rate": 0.00018530141426968902,
"loss": 1.1066,
"step": 125
},
{
"epoch": 0.75,
"learning_rate": 0.0001850512698963485,
"loss": 1.0685,
"step": 126
},
{
"epoch": 0.75,
"eval_loss": 0.8026405572891235,
"eval_runtime": 14.5968,
"eval_samples_per_second": 56.108,
"eval_steps_per_second": 28.088,
"step": 126
},
{
"epoch": 0.76,
"learning_rate": 0.000184799186745666,
"loss": 1.0494,
"step": 127
},
{
"epoch": 0.76,
"learning_rate": 0.00018454517056397661,
"loss": 1.1905,
"step": 128
},
{
"epoch": 0.77,
"learning_rate": 0.0001842892271416797,
"loss": 1.2034,
"step": 129
},
{
"epoch": 0.78,
"learning_rate": 0.00018403136231310684,
"loss": 1.2088,
"step": 130
},
{
"epoch": 0.78,
"learning_rate": 0.00018377158195638876,
"loss": 0.9303,
"step": 131
},
{
"epoch": 0.79,
"learning_rate": 0.00018350989199332154,
"loss": 1.1574,
"step": 132
},
{
"epoch": 0.79,
"learning_rate": 0.00018324629838923132,
"loss": 1.1673,
"step": 133
},
{
"epoch": 0.8,
"learning_rate": 0.00018298080715283858,
"loss": 1.1204,
"step": 134
},
{
"epoch": 0.81,
"learning_rate": 0.00018271342433612113,
"loss": 1.0752,
"step": 135
},
{
"epoch": 0.81,
"learning_rate": 0.00018244415603417603,
"loss": 1.0121,
"step": 136
},
{
"epoch": 0.82,
"learning_rate": 0.00018217300838508073,
"loss": 1.0975,
"step": 137
},
{
"epoch": 0.82,
"learning_rate": 0.00018189998756975318,
"loss": 0.9982,
"step": 138
},
{
"epoch": 0.83,
"learning_rate": 0.00018162509981181084,
"loss": 1.1922,
"step": 139
},
{
"epoch": 0.84,
"learning_rate": 0.0001813483513774289,
"loss": 0.9532,
"step": 140
},
{
"epoch": 0.84,
"learning_rate": 0.00018106974857519736,
"loss": 1.0813,
"step": 141
},
{
"epoch": 0.85,
"learning_rate": 0.0001807892977559774,
"loss": 0.9656,
"step": 142
},
{
"epoch": 0.85,
"learning_rate": 0.0001805070053127563,
"loss": 1.1161,
"step": 143
},
{
"epoch": 0.86,
"learning_rate": 0.00018022287768050202,
"loss": 1.0143,
"step": 144
},
{
"epoch": 0.87,
"learning_rate": 0.0001799369213360163,
"loss": 1.1242,
"step": 145
},
{
"epoch": 0.87,
"learning_rate": 0.00017964914279778715,
"loss": 1.0747,
"step": 146
},
{
"epoch": 0.88,
"learning_rate": 0.00017935954862584018,
"loss": 1.1551,
"step": 147
},
{
"epoch": 0.88,
"learning_rate": 0.0001790681454215891,
"loss": 0.9538,
"step": 148
},
{
"epoch": 0.89,
"learning_rate": 0.00017877493982768527,
"loss": 1.0621,
"step": 149
},
{
"epoch": 0.9,
"learning_rate": 0.0001784799385278661,
"loss": 1.0229,
"step": 150
},
{
"epoch": 0.9,
"learning_rate": 0.000178183148246803,
"loss": 0.9991,
"step": 151
},
{
"epoch": 0.91,
"learning_rate": 0.00017788457574994778,
"loss": 1.0045,
"step": 152
},
{
"epoch": 0.91,
"learning_rate": 0.00017758422784337863,
"loss": 1.0675,
"step": 153
},
{
"epoch": 0.92,
"learning_rate": 0.00017728211137364489,
"loss": 0.962,
"step": 154
},
{
"epoch": 0.93,
"learning_rate": 0.000176978233227611,
"loss": 1.0145,
"step": 155
},
{
"epoch": 0.93,
"learning_rate": 0.00017667260033229953,
"loss": 0.9576,
"step": 156
},
{
"epoch": 0.94,
"learning_rate": 0.00017636521965473323,
"loss": 1.0692,
"step": 157
},
{
"epoch": 0.94,
"learning_rate": 0.00017605609820177617,
"loss": 1.2074,
"step": 158
},
{
"epoch": 0.95,
"learning_rate": 0.00017574524301997423,
"loss": 1.1489,
"step": 159
},
{
"epoch": 0.96,
"learning_rate": 0.00017543266119539422,
"loss": 0.9962,
"step": 160
},
{
"epoch": 0.96,
"learning_rate": 0.00017511835985346253,
"loss": 0.8922,
"step": 161
},
{
"epoch": 0.97,
"learning_rate": 0.00017480234615880247,
"loss": 0.9248,
"step": 162
},
{
"epoch": 0.97,
"learning_rate": 0.0001744846273150713,
"loss": 1.1621,
"step": 163
},
{
"epoch": 0.98,
"learning_rate": 0.00017416521056479577,
"loss": 1.0516,
"step": 164
},
{
"epoch": 0.99,
"learning_rate": 0.00017384410318920697,
"loss": 1.0086,
"step": 165
},
{
"epoch": 0.99,
"learning_rate": 0.00017352131250807467,
"loss": 1.0909,
"step": 166
},
{
"epoch": 1.0,
"learning_rate": 0.00017319684587954002,
"loss": 1.1085,
"step": 167
},
{
"epoch": 1.0,
"learning_rate": 0.0001728707106999482,
"loss": 1.1573,
"step": 168
},
{
"epoch": 1.0,
"eval_loss": 0.7850226163864136,
"eval_runtime": 14.526,
"eval_samples_per_second": 56.382,
"eval_steps_per_second": 28.225,
"step": 168
},
{
"epoch": 1.01,
"learning_rate": 0.00017254291440367968,
"loss": 1.1107,
"step": 169
},
{
"epoch": 1.01,
"learning_rate": 0.0001722134644629807,
"loss": 1.1537,
"step": 170
},
{
"epoch": 1.0,
"learning_rate": 0.00017188236838779295,
"loss": 1.1293,
"step": 171
},
{
"epoch": 1.01,
"learning_rate": 0.00017154963372558246,
"loss": 1.0653,
"step": 172
},
{
"epoch": 1.02,
"learning_rate": 0.00017121526806116748,
"loss": 1.0901,
"step": 173
},
{
"epoch": 1.02,
"learning_rate": 0.00017087927901654557,
"loss": 1.1569,
"step": 174
},
{
"epoch": 1.03,
"learning_rate": 0.00017054167425071995,
"loss": 1.022,
"step": 175
},
{
"epoch": 1.03,
"learning_rate": 0.00017020246145952477,
"loss": 1.0639,
"step": 176
},
{
"epoch": 1.04,
"learning_rate": 0.00016986164837544987,
"loss": 1.071,
"step": 177
},
{
"epoch": 1.05,
"learning_rate": 0.00016951924276746425,
"loss": 0.924,
"step": 178
},
{
"epoch": 1.05,
"learning_rate": 0.00016917525244083918,
"loss": 1.0146,
"step": 179
},
{
"epoch": 1.06,
"learning_rate": 0.00016882968523697028,
"loss": 1.0599,
"step": 180
},
{
"epoch": 1.06,
"learning_rate": 0.00016848254903319867,
"loss": 1.0237,
"step": 181
},
{
"epoch": 1.07,
"learning_rate": 0.00016813385174263137,
"loss": 0.9614,
"step": 182
},
{
"epoch": 1.08,
"learning_rate": 0.0001677836013139611,
"loss": 0.9791,
"step": 183
},
{
"epoch": 1.08,
"learning_rate": 0.00016743180573128495,
"loss": 1.0945,
"step": 184
},
{
"epoch": 1.09,
"learning_rate": 0.00016707847301392236,
"loss": 1.0091,
"step": 185
},
{
"epoch": 1.09,
"learning_rate": 0.00016672361121623238,
"loss": 1.1076,
"step": 186
},
{
"epoch": 1.1,
"learning_rate": 0.00016636722842743013,
"loss": 0.9472,
"step": 187
},
{
"epoch": 1.11,
"learning_rate": 0.0001660093327714022,
"loss": 1.0485,
"step": 188
},
{
"epoch": 1.11,
"learning_rate": 0.0001656499324065217,
"loss": 1.0056,
"step": 189
},
{
"epoch": 1.12,
"learning_rate": 0.00016528903552546207,
"loss": 1.0819,
"step": 190
},
{
"epoch": 1.12,
"learning_rate": 0.00016492665035501046,
"loss": 1.1128,
"step": 191
},
{
"epoch": 1.13,
"learning_rate": 0.00016456278515588024,
"loss": 1.056,
"step": 192
},
{
"epoch": 1.14,
"learning_rate": 0.00016419744822252253,
"loss": 1.0468,
"step": 193
},
{
"epoch": 1.14,
"learning_rate": 0.0001638306478829373,
"loss": 0.9966,
"step": 194
},
{
"epoch": 1.15,
"learning_rate": 0.0001634623924984833,
"loss": 0.9898,
"step": 195
},
{
"epoch": 1.15,
"learning_rate": 0.00016309269046368776,
"loss": 1.0431,
"step": 196
},
{
"epoch": 1.16,
"learning_rate": 0.0001627215502060548,
"loss": 1.0327,
"step": 197
},
{
"epoch": 1.17,
"learning_rate": 0.00016234898018587337,
"loss": 1.0382,
"step": 198
},
{
"epoch": 1.17,
"learning_rate": 0.00016197498889602448,
"loss": 1.0287,
"step": 199
},
{
"epoch": 1.18,
"learning_rate": 0.0001615995848617876,
"loss": 1.0244,
"step": 200
},
{
"epoch": 1.18,
"learning_rate": 0.0001612227766406461,
"loss": 1.0989,
"step": 201
},
{
"epoch": 1.19,
"learning_rate": 0.00016084457282209243,
"loss": 1.1219,
"step": 202
},
{
"epoch": 1.2,
"learning_rate": 0.00016046498202743233,
"loss": 0.9456,
"step": 203
},
{
"epoch": 1.2,
"learning_rate": 0.00016008401290958807,
"loss": 1.0259,
"step": 204
},
{
"epoch": 1.21,
"learning_rate": 0.0001597016741529014,
"loss": 1.0929,
"step": 205
},
{
"epoch": 1.21,
"learning_rate": 0.00015931797447293552,
"loss": 1.0716,
"step": 206
},
{
"epoch": 1.22,
"learning_rate": 0.00015893292261627643,
"loss": 0.9947,
"step": 207
},
{
"epoch": 1.23,
"learning_rate": 0.00015854652736033354,
"loss": 0.9707,
"step": 208
},
{
"epoch": 1.23,
"learning_rate": 0.00015815879751313955,
"loss": 0.9492,
"step": 209
},
{
"epoch": 1.24,
"learning_rate": 0.0001577697419131497,
"loss": 0.9346,
"step": 210
},
{
"epoch": 1.24,
"eval_loss": 0.7729161381721497,
"eval_runtime": 14.4823,
"eval_samples_per_second": 56.552,
"eval_steps_per_second": 28.31,
"step": 210
},
{
"epoch": 1.24,
"learning_rate": 0.00015737936942904023,
"loss": 0.9925,
"step": 211
},
{
"epoch": 1.25,
"learning_rate": 0.00015698768895950642,
"loss": 1.032,
"step": 212
},
{
"epoch": 1.26,
"learning_rate": 0.00015659470943305955,
"loss": 1.0372,
"step": 213
},
{
"epoch": 1.26,
"learning_rate": 0.00015620043980782327,
"loss": 0.9926,
"step": 214
},
{
"epoch": 1.27,
"learning_rate": 0.00015580488907132974,
"loss": 0.9653,
"step": 215
},
{
"epoch": 1.27,
"learning_rate": 0.00015540806624031442,
"loss": 1.1205,
"step": 216
},
{
"epoch": 1.28,
"learning_rate": 0.00015500998036051074,
"loss": 1.0311,
"step": 217
},
{
"epoch": 1.29,
"learning_rate": 0.0001546106405064438,
"loss": 0.9639,
"step": 218
},
{
"epoch": 1.29,
"learning_rate": 0.00015421005578122356,
"loss": 1.0489,
"step": 219
},
{
"epoch": 1.3,
"learning_rate": 0.00015380823531633729,
"loss": 1.0312,
"step": 220
},
{
"epoch": 1.3,
"learning_rate": 0.00015340518827144145,
"loss": 1.0165,
"step": 221
},
{
"epoch": 1.31,
"learning_rate": 0.00015300092383415282,
"loss": 1.009,
"step": 222
},
{
"epoch": 1.31,
"learning_rate": 0.0001525954512198392,
"loss": 1.0458,
"step": 223
},
{
"epoch": 1.32,
"learning_rate": 0.0001521887796714092,
"loss": 1.0606,
"step": 224
},
{
"epoch": 1.33,
"learning_rate": 0.0001517809184591017,
"loss": 0.9358,
"step": 225
},
{
"epoch": 1.33,
"learning_rate": 0.00015137187688027436,
"loss": 1.0373,
"step": 226
},
{
"epoch": 1.34,
"learning_rate": 0.00015096166425919175,
"loss": 1.1689,
"step": 227
},
{
"epoch": 1.34,
"learning_rate": 0.00015055028994681284,
"loss": 1.1171,
"step": 228
},
{
"epoch": 1.35,
"learning_rate": 0.00015013776332057786,
"loss": 0.9495,
"step": 229
},
{
"epoch": 1.36,
"learning_rate": 0.0001497240937841944,
"loss": 1.0251,
"step": 230
},
{
"epoch": 1.36,
"learning_rate": 0.00014930929076742316,
"loss": 1.132,
"step": 231
},
{
"epoch": 1.37,
"learning_rate": 0.00014889336372586305,
"loss": 1.0223,
"step": 232
},
{
"epoch": 1.37,
"learning_rate": 0.00014847632214073548,
"loss": 0.9179,
"step": 233
},
{
"epoch": 1.38,
"learning_rate": 0.00014805817551866838,
"loss": 0.915,
"step": 234
},
{
"epoch": 1.39,
"learning_rate": 0.0001476389333914794,
"loss": 1.0096,
"step": 235
},
{
"epoch": 1.39,
"learning_rate": 0.0001472186053159587,
"loss": 1.0108,
"step": 236
},
{
"epoch": 1.4,
"learning_rate": 0.00014679720087365096,
"loss": 0.9954,
"step": 237
},
{
"epoch": 1.4,
"learning_rate": 0.0001463747296706372,
"loss": 1.0534,
"step": 238
},
{
"epoch": 1.41,
"learning_rate": 0.00014595120133731565,
"loss": 0.9521,
"step": 239
},
{
"epoch": 1.42,
"learning_rate": 0.0001455266255281821,
"loss": 1.086,
"step": 240
},
{
"epoch": 1.42,
"learning_rate": 0.00014510101192161018,
"loss": 0.986,
"step": 241
},
{
"epoch": 1.43,
"learning_rate": 0.0001446743702196304,
"loss": 1.1084,
"step": 242
},
{
"epoch": 1.43,
"learning_rate": 0.00014424671014770906,
"loss": 0.9904,
"step": 243
},
{
"epoch": 1.44,
"learning_rate": 0.0001438180414545267,
"loss": 1.019,
"step": 244
},
{
"epoch": 1.45,
"learning_rate": 0.00014338837391175582,
"loss": 1.1684,
"step": 245
},
{
"epoch": 1.45,
"learning_rate": 0.00014295771731383797,
"loss": 0.9792,
"step": 246
},
{
"epoch": 1.46,
"learning_rate": 0.00014252608147776065,
"loss": 1.0375,
"step": 247
},
{
"epoch": 1.46,
"learning_rate": 0.0001420934762428335,
"loss": 0.9413,
"step": 248
},
{
"epoch": 1.47,
"learning_rate": 0.00014165991147046403,
"loss": 1.0807,
"step": 249
},
{
"epoch": 1.48,
"learning_rate": 0.00014122539704393265,
"loss": 0.8643,
"step": 250
},
{
"epoch": 1.48,
"learning_rate": 0.00014078994286816768,
"loss": 0.9569,
"step": 251
},
{
"epoch": 1.49,
"learning_rate": 0.00014035355886951923,
"loss": 1.0299,
"step": 252
},
{
"epoch": 1.49,
"eval_loss": 0.761233925819397,
"eval_runtime": 14.3861,
"eval_samples_per_second": 56.93,
"eval_steps_per_second": 28.5,
"step": 252
},
{
"epoch": 1.49,
"learning_rate": 0.00013991625499553325,
"loss": 0.9685,
"step": 253
},
{
"epoch": 1.5,
"learning_rate": 0.0001394780412147245,
"loss": 1.0123,
"step": 254
},
{
"epoch": 1.51,
"learning_rate": 0.00013903892751634947,
"loss": 0.9601,
"step": 255
},
{
"epoch": 1.51,
"learning_rate": 0.00013859892391017865,
"loss": 0.9661,
"step": 256
},
{
"epoch": 1.52,
"learning_rate": 0.00013815804042626828,
"loss": 1.0132,
"step": 257
},
{
"epoch": 1.52,
"learning_rate": 0.00013771628711473172,
"loss": 1.0511,
"step": 258
},
{
"epoch": 1.53,
"learning_rate": 0.00013727367404551055,
"loss": 1.0637,
"step": 259
},
{
"epoch": 1.54,
"learning_rate": 0.0001368302113081447,
"loss": 0.9781,
"step": 260
},
{
"epoch": 1.54,
"learning_rate": 0.00013638590901154276,
"loss": 1.0151,
"step": 261
},
{
"epoch": 1.55,
"learning_rate": 0.00013594077728375128,
"loss": 0.9971,
"step": 262
},
{
"epoch": 1.55,
"learning_rate": 0.0001354948262717241,
"loss": 0.9202,
"step": 263
},
{
"epoch": 1.56,
"learning_rate": 0.00013504806614109098,
"loss": 1.0605,
"step": 264
},
{
"epoch": 1.57,
"learning_rate": 0.0001346005070759258,
"loss": 1.0303,
"step": 265
},
{
"epoch": 1.57,
"learning_rate": 0.0001341521592785145,
"loss": 0.9228,
"step": 266
},
{
"epoch": 1.58,
"learning_rate": 0.00013370303296912249,
"loss": 0.9659,
"step": 267
},
{
"epoch": 1.58,
"learning_rate": 0.0001332531383857616,
"loss": 0.9742,
"step": 268
},
{
"epoch": 1.59,
"learning_rate": 0.0001328024857839569,
"loss": 1.0524,
"step": 269
},
{
"epoch": 1.6,
"learning_rate": 0.00013235108543651272,
"loss": 1.0277,
"step": 270
},
{
"epoch": 1.6,
"learning_rate": 0.0001318989476332785,
"loss": 0.9731,
"step": 271
},
{
"epoch": 1.61,
"learning_rate": 0.00013144608268091435,
"loss": 1.0629,
"step": 272
},
{
"epoch": 1.61,
"learning_rate": 0.000130992500902656,
"loss": 0.8943,
"step": 273
},
{
"epoch": 1.62,
"learning_rate": 0.00013053821263807946,
"loss": 0.9997,
"step": 274
},
{
"epoch": 1.63,
"learning_rate": 0.00013008322824286555,
"loss": 1.0465,
"step": 275
},
{
"epoch": 1.63,
"learning_rate": 0.00012962755808856342,
"loss": 1.0259,
"step": 276
},
{
"epoch": 1.64,
"learning_rate": 0.00012917121256235455,
"loss": 0.9458,
"step": 277
},
{
"epoch": 1.64,
"learning_rate": 0.00012871420206681571,
"loss": 1.0322,
"step": 278
},
{
"epoch": 1.65,
"learning_rate": 0.000128256537019682,
"loss": 0.8538,
"step": 279
},
{
"epoch": 1.66,
"learning_rate": 0.00012779822785360912,
"loss": 0.9602,
"step": 280
},
{
"epoch": 1.66,
"learning_rate": 0.00012733928501593587,
"loss": 0.9953,
"step": 281
},
{
"epoch": 1.67,
"learning_rate": 0.00012687971896844575,
"loss": 0.8757,
"step": 282
},
{
"epoch": 1.67,
"learning_rate": 0.00012641954018712863,
"loss": 0.9382,
"step": 283
},
{
"epoch": 1.68,
"learning_rate": 0.00012595875916194188,
"loss": 0.8791,
"step": 284
},
{
"epoch": 1.69,
"learning_rate": 0.00012549738639657115,
"loss": 0.9245,
"step": 285
},
{
"epoch": 1.69,
"learning_rate": 0.00012503543240819127,
"loss": 0.9611,
"step": 286
},
{
"epoch": 1.7,
"learning_rate": 0.00012457290772722608,
"loss": 1.0328,
"step": 287
},
{
"epoch": 1.7,
"learning_rate": 0.00012410982289710865,
"loss": 0.8988,
"step": 288
},
{
"epoch": 1.71,
"learning_rate": 0.0001236461884740409,
"loss": 1.0435,
"step": 289
},
{
"epoch": 1.71,
"learning_rate": 0.00012318201502675285,
"loss": 0.9486,
"step": 290
},
{
"epoch": 1.72,
"learning_rate": 0.0001227173131362619,
"loss": 0.8819,
"step": 291
},
{
"epoch": 1.73,
"learning_rate": 0.00012225209339563145,
"loss": 1.024,
"step": 292
},
{
"epoch": 1.73,
"learning_rate": 0.00012178636640972953,
"loss": 0.9137,
"step": 293
},
{
"epoch": 1.74,
"learning_rate": 0.00012132014279498703,
"loss": 1.0057,
"step": 294
},
{
"epoch": 1.74,
"eval_loss": 0.754410445690155,
"eval_runtime": 14.5906,
"eval_samples_per_second": 56.132,
"eval_steps_per_second": 28.1,
"step": 294
},
{
"epoch": 1.74,
"learning_rate": 0.00012085343317915565,
"loss": 1.0209,
"step": 295
},
{
"epoch": 1.75,
"learning_rate": 0.00012038624820106572,
"loss": 0.9985,
"step": 296
},
{
"epoch": 1.76,
"learning_rate": 0.0001199185985103836,
"loss": 0.7608,
"step": 297
},
{
"epoch": 1.76,
"learning_rate": 0.00011945049476736905,
"loss": 0.931,
"step": 298
},
{
"epoch": 1.77,
"learning_rate": 0.00011898194764263197,
"loss": 1.0362,
"step": 299
},
{
"epoch": 1.77,
"learning_rate": 0.00011851296781688952,
"loss": 1.097,
"step": 300
},
{
"epoch": 1.78,
"learning_rate": 0.00011804356598072223,
"loss": 0.9304,
"step": 301
},
{
"epoch": 1.79,
"learning_rate": 0.00011757375283433076,
"loss": 0.9989,
"step": 302
},
{
"epoch": 1.79,
"learning_rate": 0.00011710353908729156,
"loss": 0.971,
"step": 303
},
{
"epoch": 1.8,
"learning_rate": 0.00011663293545831302,
"loss": 0.9942,
"step": 304
},
{
"epoch": 1.8,
"learning_rate": 0.00011616195267499102,
"loss": 0.9824,
"step": 305
},
{
"epoch": 1.81,
"learning_rate": 0.00011569060147356441,
"loss": 0.9901,
"step": 306
},
{
"epoch": 1.82,
"learning_rate": 0.00011521889259867032,
"loss": 1.0445,
"step": 307
},
{
"epoch": 1.82,
"learning_rate": 0.00011474683680309912,
"loss": 0.9421,
"step": 308
},
{
"epoch": 1.83,
"learning_rate": 0.0001142744448475494,
"loss": 0.9692,
"step": 309
},
{
"epoch": 1.83,
"learning_rate": 0.00011380172750038269,
"loss": 0.9473,
"step": 310
},
{
"epoch": 1.84,
"learning_rate": 0.0001133286955373779,
"loss": 1.0931,
"step": 311
},
{
"epoch": 1.85,
"learning_rate": 0.00011285535974148576,
"loss": 1.0236,
"step": 312
},
{
"epoch": 1.85,
"learning_rate": 0.00011238173090258293,
"loss": 0.9002,
"step": 313
},
{
"epoch": 1.86,
"learning_rate": 0.00011190781981722623,
"loss": 0.9209,
"step": 314
},
{
"epoch": 1.86,
"learning_rate": 0.00011143363728840625,
"loss": 0.9155,
"step": 315
},
{
"epoch": 1.87,
"learning_rate": 0.00011095919412530136,
"loss": 1.0064,
"step": 316
},
{
"epoch": 1.88,
"learning_rate": 0.0001104845011430311,
"loss": 0.947,
"step": 317
},
{
"epoch": 1.88,
"learning_rate": 0.00011000956916240985,
"loss": 0.9293,
"step": 318
},
{
"epoch": 1.89,
"learning_rate": 0.00010953440900969994,
"loss": 0.9596,
"step": 319
},
{
"epoch": 1.89,
"learning_rate": 0.00010905903151636501,
"loss": 0.9835,
"step": 320
},
{
"epoch": 1.9,
"learning_rate": 0.00010858344751882304,
"loss": 0.9722,
"step": 321
},
{
"epoch": 1.91,
"learning_rate": 0.00010810766785819946,
"loss": 0.8318,
"step": 322
},
{
"epoch": 1.91,
"learning_rate": 0.00010763170338007978,
"loss": 1.0073,
"step": 323
},
{
"epoch": 1.92,
"learning_rate": 0.00010715556493426262,
"loss": 0.9922,
"step": 324
},
{
"epoch": 1.92,
"learning_rate": 0.00010667926337451217,
"loss": 0.9459,
"step": 325
},
{
"epoch": 1.93,
"learning_rate": 0.00010620280955831087,
"loss": 0.9276,
"step": 326
},
{
"epoch": 1.94,
"learning_rate": 0.000105726214346612,
"loss": 1.027,
"step": 327
},
{
"epoch": 1.94,
"learning_rate": 0.00010524948860359193,
"loss": 0.8963,
"step": 328
},
{
"epoch": 1.95,
"learning_rate": 0.00010477264319640252,
"loss": 1.0102,
"step": 329
},
{
"epoch": 1.95,
"learning_rate": 0.00010429568899492348,
"loss": 0.9058,
"step": 330
},
{
"epoch": 1.96,
"learning_rate": 0.0001038186368715145,
"loss": 1.137,
"step": 331
},
{
"epoch": 1.97,
"learning_rate": 0.00010334149770076747,
"loss": 0.9578,
"step": 332
},
{
"epoch": 1.97,
"learning_rate": 0.00010286428235925849,
"loss": 0.9282,
"step": 333
},
{
"epoch": 1.98,
"learning_rate": 0.00010238700172530009,
"loss": 0.9325,
"step": 334
}
],
"logging_steps": 1,
"max_steps": 668,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 167,
"total_flos": 6.956422447654502e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}