Doctor-Shotgun's picture
Initial model commit
84e2892
raw
history blame
30.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9968051118210862,
"eval_steps": 20,
"global_step": 234,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.4999999999999999e-05,
"loss": 2.2286,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.9999999999999997e-05,
"loss": 2.2437,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.4999999999999996e-05,
"loss": 2.194,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 5.9999999999999995e-05,
"loss": 2.2882,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 7.5e-05,
"loss": 2.1882,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 8.999999999999999e-05,
"loss": 2.2828,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.00010499999999999999,
"loss": 2.1696,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.00011999999999999999,
"loss": 2.0552,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.000135,
"loss": 2.03,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.00015,
"loss": 2.1028,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.0001499982355946975,
"loss": 2.1635,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.0001499929424618067,
"loss": 2.0228,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.00014998412085037382,
"loss": 2.0951,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.00014997177117546275,
"loss": 2.0612,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.0001499558940181357,
"loss": 2.102,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.00014993649012542577,
"loss": 2.0013,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.00014991356041030174,
"loss": 1.9405,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0001498871059516253,
"loss": 2.0392,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.00014985712799410006,
"loss": 1.9541,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.00014982362794821314,
"loss": 2.1119,
"step": 20
},
{
"epoch": 0.09,
"eval_loss": 2.0726754665374756,
"eval_runtime": 22.387,
"eval_samples_per_second": 0.938,
"eval_steps_per_second": 0.491,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.00014978660739016882,
"loss": 1.9826,
"step": 21
},
{
"epoch": 0.09,
"learning_rate": 0.00014974606806181424,
"loss": 1.94,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.00014970201187055753,
"loss": 1.9218,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.00014965444088927814,
"loss": 1.9999,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.00014960335735622916,
"loss": 1.8888,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.0001495487636749321,
"loss": 1.948,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.00014949066241406377,
"loss": 2.0571,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.00014942905630733544,
"loss": 1.984,
"step": 28
},
{
"epoch": 0.12,
"learning_rate": 0.00014936394825336424,
"loss": 1.9825,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.0001492953413155367,
"loss": 1.9785,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 0.00014922323872186468,
"loss": 2.0284,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.00014914764386483347,
"loss": 1.8923,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.0001490685603012422,
"loss": 2.0051,
"step": 33
},
{
"epoch": 0.14,
"learning_rate": 0.00014898599175203645,
"loss": 1.9797,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.00014889994210213317,
"loss": 1.9387,
"step": 35
},
{
"epoch": 0.15,
"learning_rate": 0.00014881041540023792,
"loss": 1.9888,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.00014871741585865435,
"loss": 1.9914,
"step": 37
},
{
"epoch": 0.16,
"learning_rate": 0.00014862094785308606,
"loss": 1.9477,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.00014852101592243067,
"loss": 1.9709,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.00014841762476856625,
"loss": 1.9889,
"step": 40
},
{
"epoch": 0.17,
"eval_loss": 2.010409355163574,
"eval_runtime": 22.3318,
"eval_samples_per_second": 0.94,
"eval_steps_per_second": 0.493,
"step": 40
},
{
"epoch": 0.17,
"learning_rate": 0.00014831077925613016,
"loss": 1.8916,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.00014820048441229006,
"loss": 1.9724,
"step": 42
},
{
"epoch": 0.18,
"learning_rate": 0.0001480867454265075,
"loss": 2.0695,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.0001479695676502937,
"loss": 1.9938,
"step": 44
},
{
"epoch": 0.19,
"learning_rate": 0.0001478489565969577,
"loss": 1.8722,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.00014772491794134697,
"loss": 2.1142,
"step": 46
},
{
"epoch": 0.2,
"learning_rate": 0.00014759745751958056,
"loss": 1.866,
"step": 47
},
{
"epoch": 0.2,
"learning_rate": 0.00014746658132877428,
"loss": 1.9808,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.00014733229552675865,
"loss": 1.9279,
"step": 49
},
{
"epoch": 0.21,
"learning_rate": 0.00014719460643178919,
"loss": 1.9375,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.00014705352052224907,
"loss": 1.9435,
"step": 51
},
{
"epoch": 0.22,
"learning_rate": 0.00014690904443634433,
"loss": 2.0176,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.0001467611849717916,
"loss": 1.9315,
"step": 53
},
{
"epoch": 0.23,
"learning_rate": 0.00014660994908549812,
"loss": 2.0235,
"step": 54
},
{
"epoch": 0.23,
"learning_rate": 0.00014645534389323456,
"loss": 1.9458,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.00014629737666930017,
"loss": 1.8879,
"step": 56
},
{
"epoch": 0.24,
"learning_rate": 0.0001461360548461805,
"loss": 1.9711,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.00014597138601419758,
"loss": 2.0011,
"step": 58
},
{
"epoch": 0.25,
"learning_rate": 0.00014580337792115315,
"loss": 1.9624,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.00014563203847196366,
"loss": 1.878,
"step": 60
},
{
"epoch": 0.26,
"eval_loss": 1.9977601766586304,
"eval_runtime": 22.3277,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.493,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 0.0001454573757282887,
"loss": 1.9651,
"step": 61
},
{
"epoch": 0.26,
"learning_rate": 0.00014527939790815147,
"loss": 1.9585,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.00014509811338555222,
"loss": 1.7946,
"step": 63
},
{
"epoch": 0.27,
"learning_rate": 0.00014491353069007428,
"loss": 1.9296,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.00014472565850648259,
"loss": 1.9582,
"step": 65
},
{
"epoch": 0.28,
"learning_rate": 0.00014453450567431517,
"loss": 1.8811,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.00014434008118746728,
"loss": 1.9974,
"step": 67
},
{
"epoch": 0.29,
"learning_rate": 0.0001441423941937681,
"loss": 1.9186,
"step": 68
},
{
"epoch": 0.29,
"learning_rate": 0.0001439414539945505,
"loss": 1.9891,
"step": 69
},
{
"epoch": 0.3,
"learning_rate": 0.00014373727004421316,
"loss": 1.8635,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 0.00014352985194977596,
"loss": 1.9402,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.0001433192094704278,
"loss": 1.8707,
"step": 72
},
{
"epoch": 0.31,
"learning_rate": 0.00014310535251706765,
"loss": 1.8617,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.0001428882911518379,
"loss": 2.0184,
"step": 74
},
{
"epoch": 0.32,
"learning_rate": 0.00014266803558765122,
"loss": 1.9708,
"step": 75
},
{
"epoch": 0.32,
"learning_rate": 0.0001424445961877098,
"loss": 1.819,
"step": 76
},
{
"epoch": 0.33,
"learning_rate": 0.0001422179834650181,
"loss": 1.876,
"step": 77
},
{
"epoch": 0.33,
"learning_rate": 0.00014198820808188775,
"loss": 1.9368,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.0001417552808494362,
"loss": 1.9264,
"step": 79
},
{
"epoch": 0.34,
"learning_rate": 0.00014151921272707803,
"loss": 1.8531,
"step": 80
},
{
"epoch": 0.34,
"eval_loss": 1.9885673522949219,
"eval_runtime": 22.3375,
"eval_samples_per_second": 0.94,
"eval_steps_per_second": 0.492,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.00014128001482200907,
"loss": 1.9065,
"step": 81
},
{
"epoch": 0.35,
"learning_rate": 0.00014103769838868407,
"loss": 1.8165,
"step": 82
},
{
"epoch": 0.35,
"learning_rate": 0.00014079227482828704,
"loss": 1.9162,
"step": 83
},
{
"epoch": 0.36,
"learning_rate": 0.0001405437556881948,
"loss": 1.9949,
"step": 84
},
{
"epoch": 0.36,
"learning_rate": 0.00014029215266143374,
"loss": 1.9014,
"step": 85
},
{
"epoch": 0.37,
"learning_rate": 0.00014003747758612953,
"loss": 1.9389,
"step": 86
},
{
"epoch": 0.37,
"learning_rate": 0.0001397797424449503,
"loss": 1.9126,
"step": 87
},
{
"epoch": 0.37,
"learning_rate": 0.00013951895936454268,
"loss": 1.9983,
"step": 88
},
{
"epoch": 0.38,
"learning_rate": 0.00013925514061496137,
"loss": 1.9044,
"step": 89
},
{
"epoch": 0.38,
"learning_rate": 0.00013898829860909168,
"loss": 1.9961,
"step": 90
},
{
"epoch": 0.39,
"learning_rate": 0.00013871844590206565,
"loss": 1.8608,
"step": 91
},
{
"epoch": 0.39,
"learning_rate": 0.0001384455951906712,
"loss": 1.984,
"step": 92
},
{
"epoch": 0.4,
"learning_rate": 0.00013816975931275473,
"loss": 1.9282,
"step": 93
},
{
"epoch": 0.4,
"learning_rate": 0.00013789095124661725,
"loss": 1.9654,
"step": 94
},
{
"epoch": 0.4,
"learning_rate": 0.00013760918411040356,
"loss": 1.895,
"step": 95
},
{
"epoch": 0.41,
"learning_rate": 0.00013732447116148507,
"loss": 1.902,
"step": 96
},
{
"epoch": 0.41,
"learning_rate": 0.00013703682579583614,
"loss": 1.9818,
"step": 97
},
{
"epoch": 0.42,
"learning_rate": 0.0001367462615474036,
"loss": 1.8978,
"step": 98
},
{
"epoch": 0.42,
"learning_rate": 0.0001364527920874702,
"loss": 1.887,
"step": 99
},
{
"epoch": 0.43,
"learning_rate": 0.00013615643122401113,
"loss": 1.9504,
"step": 100
},
{
"epoch": 0.43,
"eval_loss": 1.98367178440094,
"eval_runtime": 22.3432,
"eval_samples_per_second": 0.94,
"eval_steps_per_second": 0.492,
"step": 100
},
{
"epoch": 0.43,
"learning_rate": 0.0001358571929010445,
"loss": 1.7944,
"step": 101
},
{
"epoch": 0.43,
"learning_rate": 0.0001355550911979752,
"loss": 1.9889,
"step": 102
},
{
"epoch": 0.44,
"learning_rate": 0.00013525014032893256,
"loss": 1.8523,
"step": 103
},
{
"epoch": 0.44,
"learning_rate": 0.00013494235464210129,
"loss": 2.006,
"step": 104
},
{
"epoch": 0.45,
"learning_rate": 0.00013463174861904668,
"loss": 1.8311,
"step": 105
},
{
"epoch": 0.45,
"learning_rate": 0.00013431833687403314,
"loss": 1.9183,
"step": 106
},
{
"epoch": 0.46,
"learning_rate": 0.0001340021341533365,
"loss": 1.9135,
"step": 107
},
{
"epoch": 0.46,
"learning_rate": 0.00013368315533455032,
"loss": 1.8234,
"step": 108
},
{
"epoch": 0.46,
"learning_rate": 0.00013336141542588575,
"loss": 1.7729,
"step": 109
},
{
"epoch": 0.47,
"learning_rate": 0.0001330369295654655,
"loss": 1.9189,
"step": 110
},
{
"epoch": 0.47,
"learning_rate": 0.0001327097130206115,
"loss": 1.9103,
"step": 111
},
{
"epoch": 0.48,
"learning_rate": 0.00013237978118712658,
"loss": 1.8897,
"step": 112
},
{
"epoch": 0.48,
"learning_rate": 0.00013204714958857012,
"loss": 1.9789,
"step": 113
},
{
"epoch": 0.49,
"learning_rate": 0.00013171183387552764,
"loss": 1.9607,
"step": 114
},
{
"epoch": 0.49,
"learning_rate": 0.00013137384982487438,
"loss": 1.9569,
"step": 115
},
{
"epoch": 0.49,
"learning_rate": 0.00013103321333903303,
"loss": 1.9091,
"step": 116
},
{
"epoch": 0.5,
"learning_rate": 0.00013068994044522554,
"loss": 1.9789,
"step": 117
},
{
"epoch": 0.5,
"learning_rate": 0.00013034404729471893,
"loss": 1.9102,
"step": 118
},
{
"epoch": 0.51,
"learning_rate": 0.0001299955501620654,
"loss": 1.8321,
"step": 119
},
{
"epoch": 0.51,
"learning_rate": 0.00012964446544433669,
"loss": 1.9216,
"step": 120
},
{
"epoch": 0.51,
"eval_loss": 1.9825721979141235,
"eval_runtime": 22.3821,
"eval_samples_per_second": 0.938,
"eval_steps_per_second": 0.491,
"step": 120
},
{
"epoch": 0.52,
"learning_rate": 0.0001292908096603525,
"loss": 1.8591,
"step": 121
},
{
"epoch": 0.52,
"learning_rate": 0.0001289345994499032,
"loss": 1.9368,
"step": 122
},
{
"epoch": 0.52,
"learning_rate": 0.000128575851572967,
"loss": 1.9594,
"step": 123
},
{
"epoch": 0.53,
"learning_rate": 0.00012821458290892144,
"loss": 1.8731,
"step": 124
},
{
"epoch": 0.53,
"learning_rate": 0.00012785081045574913,
"loss": 1.9105,
"step": 125
},
{
"epoch": 0.54,
"learning_rate": 0.0001274845513292379,
"loss": 1.8899,
"step": 126
},
{
"epoch": 0.54,
"learning_rate": 0.00012711582276217563,
"loss": 1.9211,
"step": 127
},
{
"epoch": 0.55,
"learning_rate": 0.00012674464210353932,
"loss": 1.9506,
"step": 128
},
{
"epoch": 0.55,
"learning_rate": 0.00012637102681767895,
"loss": 1.8654,
"step": 129
},
{
"epoch": 0.55,
"learning_rate": 0.0001259949944834956,
"loss": 1.9958,
"step": 130
},
{
"epoch": 0.56,
"learning_rate": 0.00012561656279361442,
"loss": 1.9783,
"step": 131
},
{
"epoch": 0.56,
"learning_rate": 0.0001252357495535523,
"loss": 1.9314,
"step": 132
},
{
"epoch": 0.57,
"learning_rate": 0.00012485257268087983,
"loss": 1.8847,
"step": 133
},
{
"epoch": 0.57,
"learning_rate": 0.00012446705020437854,
"loss": 1.9326,
"step": 134
},
{
"epoch": 0.58,
"learning_rate": 0.00012407920026319248,
"loss": 1.9853,
"step": 135
},
{
"epoch": 0.58,
"learning_rate": 0.00012368904110597479,
"loss": 2.0078,
"step": 136
},
{
"epoch": 0.58,
"learning_rate": 0.00012329659109002906,
"loss": 2.0035,
"step": 137
},
{
"epoch": 0.59,
"learning_rate": 0.00012290186868044569,
"loss": 1.8399,
"step": 138
},
{
"epoch": 0.59,
"learning_rate": 0.00012250489244923298,
"loss": 1.8643,
"step": 139
},
{
"epoch": 0.6,
"learning_rate": 0.00012210568107444346,
"loss": 1.8483,
"step": 140
},
{
"epoch": 0.6,
"eval_loss": 1.9794269800186157,
"eval_runtime": 22.3061,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.493,
"step": 140
},
{
"epoch": 0.6,
"learning_rate": 0.00012170425333929485,
"loss": 1.8399,
"step": 141
},
{
"epoch": 0.6,
"learning_rate": 0.00012130062813128651,
"loss": 1.8906,
"step": 142
},
{
"epoch": 0.61,
"learning_rate": 0.00012089482444131057,
"loss": 1.9474,
"step": 143
},
{
"epoch": 0.61,
"learning_rate": 0.00012048686136275862,
"loss": 1.9107,
"step": 144
},
{
"epoch": 0.62,
"learning_rate": 0.00012007675809062313,
"loss": 2.0292,
"step": 145
},
{
"epoch": 0.62,
"learning_rate": 0.00011966453392059446,
"loss": 2.0018,
"step": 146
},
{
"epoch": 0.63,
"learning_rate": 0.00011925020824815293,
"loss": 1.9807,
"step": 147
},
{
"epoch": 0.63,
"learning_rate": 0.00011883380056765621,
"loss": 1.948,
"step": 148
},
{
"epoch": 0.63,
"learning_rate": 0.00011841533047142213,
"loss": 1.9769,
"step": 149
},
{
"epoch": 0.64,
"learning_rate": 0.00011799481764880692,
"loss": 2.0001,
"step": 150
},
{
"epoch": 0.64,
"learning_rate": 0.00011757228188527866,
"loss": 1.9211,
"step": 151
},
{
"epoch": 0.65,
"learning_rate": 0.00011714774306148647,
"loss": 1.9913,
"step": 152
},
{
"epoch": 0.65,
"learning_rate": 0.00011672122115232503,
"loss": 1.9234,
"step": 153
},
{
"epoch": 0.66,
"learning_rate": 0.00011629273622599487,
"loss": 1.9399,
"step": 154
},
{
"epoch": 0.66,
"learning_rate": 0.000115862308443058,
"loss": 1.9234,
"step": 155
},
{
"epoch": 0.66,
"learning_rate": 0.0001154299580554894,
"loss": 2.0013,
"step": 156
},
{
"epoch": 0.67,
"learning_rate": 0.00011499570540572424,
"loss": 2.0099,
"step": 157
},
{
"epoch": 0.67,
"learning_rate": 0.00011455957092570054,
"loss": 1.8489,
"step": 158
},
{
"epoch": 0.68,
"learning_rate": 0.00011412157513589799,
"loss": 1.9815,
"step": 159
},
{
"epoch": 0.68,
"learning_rate": 0.0001136817386443725,
"loss": 1.9668,
"step": 160
},
{
"epoch": 0.68,
"eval_loss": 1.9779595136642456,
"eval_runtime": 22.3755,
"eval_samples_per_second": 0.939,
"eval_steps_per_second": 0.492,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 0.00011324008214578636,
"loss": 1.8557,
"step": 161
},
{
"epoch": 0.69,
"learning_rate": 0.00011279662642043473,
"loss": 1.8822,
"step": 162
},
{
"epoch": 0.69,
"learning_rate": 0.00011235139233326782,
"loss": 1.9452,
"step": 163
},
{
"epoch": 0.7,
"learning_rate": 0.00011190440083290921,
"loss": 1.8977,
"step": 164
},
{
"epoch": 0.7,
"learning_rate": 0.00011145567295067023,
"loss": 1.9694,
"step": 165
},
{
"epoch": 0.71,
"learning_rate": 0.0001110052297995603,
"loss": 1.9932,
"step": 166
},
{
"epoch": 0.71,
"learning_rate": 0.00011055309257329369,
"loss": 1.8577,
"step": 167
},
{
"epoch": 0.72,
"learning_rate": 0.00011009928254529225,
"loss": 1.944,
"step": 168
},
{
"epoch": 0.72,
"learning_rate": 0.0001096438210676845,
"loss": 1.9186,
"step": 169
},
{
"epoch": 0.72,
"learning_rate": 0.000109186729570301,
"loss": 1.9441,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 0.00010872802955966606,
"loss": 1.9223,
"step": 171
},
{
"epoch": 0.73,
"learning_rate": 0.00010826774261798585,
"loss": 1.863,
"step": 172
},
{
"epoch": 0.74,
"learning_rate": 0.0001078058904021329,
"loss": 2.0239,
"step": 173
},
{
"epoch": 0.74,
"learning_rate": 0.00010734249464262721,
"loss": 1.9354,
"step": 174
},
{
"epoch": 0.75,
"learning_rate": 0.00010687757714261369,
"loss": 1.9318,
"step": 175
},
{
"epoch": 0.75,
"learning_rate": 0.00010641115977683641,
"loss": 1.9005,
"step": 176
},
{
"epoch": 0.75,
"learning_rate": 0.00010594326449060932,
"loss": 1.9553,
"step": 177
},
{
"epoch": 0.76,
"learning_rate": 0.00010547391329878373,
"loss": 2.0101,
"step": 178
},
{
"epoch": 0.76,
"learning_rate": 0.00010500312828471247,
"loss": 1.8455,
"step": 179
},
{
"epoch": 0.77,
"learning_rate": 0.00010453093159921094,
"loss": 1.9776,
"step": 180
},
{
"epoch": 0.77,
"eval_loss": 1.9778156280517578,
"eval_runtime": 22.326,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.493,
"step": 180
},
{
"epoch": 0.77,
"learning_rate": 0.00010405734545951468,
"loss": 1.8919,
"step": 181
},
{
"epoch": 0.78,
"learning_rate": 0.00010358239214823427,
"loss": 1.9612,
"step": 182
},
{
"epoch": 0.78,
"learning_rate": 0.00010310609401230684,
"loss": 1.9871,
"step": 183
},
{
"epoch": 0.78,
"learning_rate": 0.00010262847346194452,
"loss": 1.8808,
"step": 184
},
{
"epoch": 0.79,
"learning_rate": 0.00010214955296958019,
"loss": 1.8487,
"step": 185
},
{
"epoch": 0.79,
"learning_rate": 0.00010166935506880997,
"loss": 1.9151,
"step": 186
},
{
"epoch": 0.8,
"learning_rate": 0.00010118790235333316,
"loss": 1.949,
"step": 187
},
{
"epoch": 0.8,
"learning_rate": 0.00010070521747588906,
"loss": 1.9736,
"step": 188
},
{
"epoch": 0.81,
"learning_rate": 0.00010022132314719119,
"loss": 1.891,
"step": 189
},
{
"epoch": 0.81,
"learning_rate": 9.973624213485876e-05,
"loss": 1.9049,
"step": 190
},
{
"epoch": 0.81,
"learning_rate": 9.924999726234535e-05,
"loss": 1.8852,
"step": 191
},
{
"epoch": 0.82,
"learning_rate": 9.876261140786512e-05,
"loss": 1.8468,
"step": 192
},
{
"epoch": 0.82,
"learning_rate": 9.82741075033164e-05,
"loss": 1.9972,
"step": 193
},
{
"epoch": 0.83,
"learning_rate": 9.77845085332026e-05,
"loss": 1.9918,
"step": 194
},
{
"epoch": 0.83,
"learning_rate": 9.729383753355093e-05,
"loss": 1.9932,
"step": 195
},
{
"epoch": 0.83,
"learning_rate": 9.68021175908284e-05,
"loss": 1.9282,
"step": 196
},
{
"epoch": 0.84,
"learning_rate": 9.630937184085566e-05,
"loss": 2.0343,
"step": 197
},
{
"epoch": 0.84,
"learning_rate": 9.581562346771841e-05,
"loss": 1.8442,
"step": 198
},
{
"epoch": 0.85,
"learning_rate": 9.532089570267661e-05,
"loss": 1.8367,
"step": 199
},
{
"epoch": 0.85,
"learning_rate": 9.482521182307136e-05,
"loss": 1.9312,
"step": 200
},
{
"epoch": 0.85,
"eval_loss": 1.977174162864685,
"eval_runtime": 22.3424,
"eval_samples_per_second": 0.94,
"eval_steps_per_second": 0.492,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 9.432859515122974e-05,
"loss": 1.9262,
"step": 201
},
{
"epoch": 0.86,
"learning_rate": 9.383106905336748e-05,
"loss": 1.8701,
"step": 202
},
{
"epoch": 0.86,
"learning_rate": 9.33326569384895e-05,
"loss": 1.974,
"step": 203
},
{
"epoch": 0.87,
"learning_rate": 9.283338225728854e-05,
"loss": 1.8317,
"step": 204
},
{
"epoch": 0.87,
"learning_rate": 9.233326850104182e-05,
"loss": 1.9642,
"step": 205
},
{
"epoch": 0.88,
"learning_rate": 9.18323392005057e-05,
"loss": 1.893,
"step": 206
},
{
"epoch": 0.88,
"learning_rate": 9.133061792480855e-05,
"loss": 1.911,
"step": 207
},
{
"epoch": 0.89,
"learning_rate": 9.08281282803418e-05,
"loss": 1.8981,
"step": 208
},
{
"epoch": 0.89,
"learning_rate": 9.03248939096493e-05,
"loss": 1.928,
"step": 209
},
{
"epoch": 0.89,
"learning_rate": 8.982093849031479e-05,
"loss": 1.8451,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 8.931628573384802e-05,
"loss": 1.8178,
"step": 211
},
{
"epoch": 0.9,
"learning_rate": 8.881095938456899e-05,
"loss": 1.8732,
"step": 212
},
{
"epoch": 0.91,
"learning_rate": 8.830498321849071e-05,
"loss": 1.9206,
"step": 213
},
{
"epoch": 0.91,
"learning_rate": 8.77983810422007e-05,
"loss": 1.9657,
"step": 214
},
{
"epoch": 0.92,
"learning_rate": 8.72911766917407e-05,
"loss": 1.7979,
"step": 215
},
{
"epoch": 0.92,
"learning_rate": 8.678339403148527e-05,
"loss": 1.9761,
"step": 216
},
{
"epoch": 0.92,
"learning_rate": 8.62750569530189e-05,
"loss": 1.9357,
"step": 217
},
{
"epoch": 0.93,
"learning_rate": 8.576618937401188e-05,
"loss": 1.9625,
"step": 218
},
{
"epoch": 0.93,
"learning_rate": 8.525681523709503e-05,
"loss": 1.9171,
"step": 219
},
{
"epoch": 0.94,
"learning_rate": 8.474695850873308e-05,
"loss": 1.9003,
"step": 220
},
{
"epoch": 0.94,
"eval_loss": 1.9738101959228516,
"eval_runtime": 22.3535,
"eval_samples_per_second": 0.939,
"eval_steps_per_second": 0.492,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 8.423664317809711e-05,
"loss": 1.9968,
"step": 221
},
{
"epoch": 0.95,
"learning_rate": 8.372589325593579e-05,
"loss": 1.9338,
"step": 222
},
{
"epoch": 0.95,
"learning_rate": 8.321473277344569e-05,
"loss": 1.943,
"step": 223
},
{
"epoch": 0.95,
"learning_rate": 8.270318578114052e-05,
"loss": 1.9167,
"step": 224
},
{
"epoch": 0.96,
"learning_rate": 8.219127634771965e-05,
"loss": 2.0213,
"step": 225
},
{
"epoch": 0.96,
"learning_rate": 8.167902855893561e-05,
"loss": 1.9531,
"step": 226
},
{
"epoch": 0.97,
"learning_rate": 8.116646651646079e-05,
"loss": 1.9225,
"step": 227
},
{
"epoch": 0.97,
"learning_rate": 8.065361433675343e-05,
"loss": 1.894,
"step": 228
},
{
"epoch": 0.98,
"learning_rate": 8.014049614992304e-05,
"loss": 1.9129,
"step": 229
},
{
"epoch": 0.98,
"learning_rate": 7.962713609859492e-05,
"loss": 1.8996,
"step": 230
},
{
"epoch": 0.98,
"learning_rate": 7.911355833677434e-05,
"loss": 1.8093,
"step": 231
},
{
"epoch": 0.99,
"learning_rate": 7.859978702871e-05,
"loss": 1.9467,
"step": 232
},
{
"epoch": 0.99,
"learning_rate": 7.808584634775706e-05,
"loss": 1.9645,
"step": 233
},
{
"epoch": 1.0,
"learning_rate": 7.757176047523993e-05,
"loss": 1.8858,
"step": 234
}
],
"logging_steps": 1,
"max_steps": 468,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 1.326673328350298e+18,
"trial_name": null,
"trial_params": null
}