32_old_wron / checkpoint-232 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
01dba80 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 232,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017241379310344827,
"grad_norm": 16.797964096069336,
"learning_rate": 5.0000000000000004e-08,
"loss": 3.4811,
"step": 1
},
{
"epoch": 0.034482758620689655,
"grad_norm": 16.552379608154297,
"learning_rate": 1.0000000000000001e-07,
"loss": 3.4256,
"step": 2
},
{
"epoch": 0.05172413793103448,
"grad_norm": 16.94522476196289,
"learning_rate": 1.5000000000000002e-07,
"loss": 3.4624,
"step": 3
},
{
"epoch": 0.06896551724137931,
"grad_norm": 16.51656723022461,
"learning_rate": 2.0000000000000002e-07,
"loss": 3.4428,
"step": 4
},
{
"epoch": 0.08620689655172414,
"grad_norm": 16.90593910217285,
"learning_rate": 2.5000000000000004e-07,
"loss": 3.4053,
"step": 5
},
{
"epoch": 0.10344827586206896,
"grad_norm": 16.83192253112793,
"learning_rate": 3.0000000000000004e-07,
"loss": 3.506,
"step": 6
},
{
"epoch": 0.1206896551724138,
"grad_norm": 16.592622756958008,
"learning_rate": 3.5000000000000004e-07,
"loss": 3.4454,
"step": 7
},
{
"epoch": 0.13793103448275862,
"grad_norm": 16.566585540771484,
"learning_rate": 4.0000000000000003e-07,
"loss": 3.4268,
"step": 8
},
{
"epoch": 0.15517241379310345,
"grad_norm": 16.46024513244629,
"learning_rate": 4.5000000000000003e-07,
"loss": 3.4186,
"step": 9
},
{
"epoch": 0.1724137931034483,
"grad_norm": 16.710294723510742,
"learning_rate": 5.000000000000001e-07,
"loss": 3.4258,
"step": 10
},
{
"epoch": 0.1896551724137931,
"grad_norm": 16.718793869018555,
"learning_rate": 5.5e-07,
"loss": 3.3919,
"step": 11
},
{
"epoch": 0.20689655172413793,
"grad_norm": 15.603546142578125,
"learning_rate": 6.000000000000001e-07,
"loss": 3.3223,
"step": 12
},
{
"epoch": 0.22413793103448276,
"grad_norm": 16.184322357177734,
"learning_rate": 6.5e-07,
"loss": 3.3516,
"step": 13
},
{
"epoch": 0.2413793103448276,
"grad_norm": 15.28188419342041,
"learning_rate": 7.000000000000001e-07,
"loss": 3.2181,
"step": 14
},
{
"epoch": 0.25862068965517243,
"grad_norm": 14.98234748840332,
"learning_rate": 7.5e-07,
"loss": 3.1837,
"step": 15
},
{
"epoch": 0.27586206896551724,
"grad_norm": 15.273055076599121,
"learning_rate": 8.000000000000001e-07,
"loss": 3.2103,
"step": 16
},
{
"epoch": 0.29310344827586204,
"grad_norm": 14.799996376037598,
"learning_rate": 8.500000000000001e-07,
"loss": 3.1195,
"step": 17
},
{
"epoch": 0.3103448275862069,
"grad_norm": 13.851456642150879,
"learning_rate": 9.000000000000001e-07,
"loss": 3.0261,
"step": 18
},
{
"epoch": 0.3275862068965517,
"grad_norm": 12.985479354858398,
"learning_rate": 9.500000000000001e-07,
"loss": 2.8995,
"step": 19
},
{
"epoch": 0.3448275862068966,
"grad_norm": 12.569958686828613,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.8289,
"step": 20
},
{
"epoch": 0.3620689655172414,
"grad_norm": 11.687292098999023,
"learning_rate": 1.0500000000000001e-06,
"loss": 2.7955,
"step": 21
},
{
"epoch": 0.3793103448275862,
"grad_norm": 10.375764846801758,
"learning_rate": 1.1e-06,
"loss": 2.6422,
"step": 22
},
{
"epoch": 0.39655172413793105,
"grad_norm": 9.314571380615234,
"learning_rate": 1.1500000000000002e-06,
"loss": 2.5636,
"step": 23
},
{
"epoch": 0.41379310344827586,
"grad_norm": 8.794600486755371,
"learning_rate": 1.2000000000000002e-06,
"loss": 2.4439,
"step": 24
},
{
"epoch": 0.43103448275862066,
"grad_norm": 8.352209091186523,
"learning_rate": 1.25e-06,
"loss": 2.351,
"step": 25
},
{
"epoch": 0.4482758620689655,
"grad_norm": 8.14919662475586,
"learning_rate": 1.3e-06,
"loss": 2.2486,
"step": 26
},
{
"epoch": 0.46551724137931033,
"grad_norm": 8.511932373046875,
"learning_rate": 1.3500000000000002e-06,
"loss": 2.201,
"step": 27
},
{
"epoch": 0.4827586206896552,
"grad_norm": 8.55715274810791,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.0727,
"step": 28
},
{
"epoch": 0.5,
"grad_norm": 8.575194358825684,
"learning_rate": 1.45e-06,
"loss": 1.9386,
"step": 29
},
{
"epoch": 0.5172413793103449,
"grad_norm": 8.735200881958008,
"learning_rate": 1.5e-06,
"loss": 1.8335,
"step": 30
},
{
"epoch": 0.5344827586206896,
"grad_norm": 8.932766914367676,
"learning_rate": 1.5500000000000002e-06,
"loss": 1.7265,
"step": 31
},
{
"epoch": 0.5517241379310345,
"grad_norm": 9.010940551757812,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.5886,
"step": 32
},
{
"epoch": 0.5689655172413793,
"grad_norm": 9.089744567871094,
"learning_rate": 1.6500000000000003e-06,
"loss": 1.4379,
"step": 33
},
{
"epoch": 0.5862068965517241,
"grad_norm": 9.299127578735352,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.2766,
"step": 34
},
{
"epoch": 0.603448275862069,
"grad_norm": 9.707971572875977,
"learning_rate": 1.75e-06,
"loss": 1.1075,
"step": 35
},
{
"epoch": 0.6206896551724138,
"grad_norm": 9.807348251342773,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.9345,
"step": 36
},
{
"epoch": 0.6379310344827587,
"grad_norm": 9.576728820800781,
"learning_rate": 1.85e-06,
"loss": 0.7481,
"step": 37
},
{
"epoch": 0.6551724137931034,
"grad_norm": 8.874764442443848,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.5921,
"step": 38
},
{
"epoch": 0.6724137931034483,
"grad_norm": 7.2561354637146,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.4217,
"step": 39
},
{
"epoch": 0.6896551724137931,
"grad_norm": 4.964897155761719,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.3012,
"step": 40
},
{
"epoch": 0.7068965517241379,
"grad_norm": 3.965514659881592,
"learning_rate": 2.05e-06,
"loss": 0.2359,
"step": 41
},
{
"epoch": 0.7241379310344828,
"grad_norm": 3.0960378646850586,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.1738,
"step": 42
},
{
"epoch": 0.7413793103448276,
"grad_norm": 2.1212306022644043,
"learning_rate": 2.15e-06,
"loss": 0.1364,
"step": 43
},
{
"epoch": 0.7586206896551724,
"grad_norm": 1.155745506286621,
"learning_rate": 2.2e-06,
"loss": 0.1012,
"step": 44
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.7050064206123352,
"learning_rate": 2.25e-06,
"loss": 0.095,
"step": 45
},
{
"epoch": 0.7931034482758621,
"grad_norm": 0.43830573558807373,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.0801,
"step": 46
},
{
"epoch": 0.8103448275862069,
"grad_norm": 0.3802882432937622,
"learning_rate": 2.35e-06,
"loss": 0.0827,
"step": 47
},
{
"epoch": 0.8275862068965517,
"grad_norm": 0.3097267746925354,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0762,
"step": 48
},
{
"epoch": 0.8448275862068966,
"grad_norm": 0.2734082341194153,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.0749,
"step": 49
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.2831459641456604,
"learning_rate": 2.5e-06,
"loss": 0.0762,
"step": 50
},
{
"epoch": 0.8793103448275862,
"grad_norm": 0.2537994086742401,
"learning_rate": 2.55e-06,
"loss": 0.072,
"step": 51
},
{
"epoch": 0.896551724137931,
"grad_norm": 0.3006448745727539,
"learning_rate": 2.6e-06,
"loss": 0.073,
"step": 52
},
{
"epoch": 0.9137931034482759,
"grad_norm": 0.24919214844703674,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0699,
"step": 53
},
{
"epoch": 0.9310344827586207,
"grad_norm": 0.23921510577201843,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0647,
"step": 54
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.1967734843492508,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0711,
"step": 55
},
{
"epoch": 0.9655172413793104,
"grad_norm": 0.1832527369260788,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0686,
"step": 56
},
{
"epoch": 0.9827586206896551,
"grad_norm": 0.16995869576931,
"learning_rate": 2.85e-06,
"loss": 0.0644,
"step": 57
},
{
"epoch": 1.0,
"grad_norm": 0.1822829246520996,
"learning_rate": 2.9e-06,
"loss": 0.0669,
"step": 58
},
{
"epoch": 1.0172413793103448,
"grad_norm": 0.17660750448703766,
"learning_rate": 2.95e-06,
"loss": 0.0668,
"step": 59
},
{
"epoch": 1.0344827586206897,
"grad_norm": 0.12004642933607101,
"learning_rate": 3e-06,
"loss": 0.0588,
"step": 60
},
{
"epoch": 1.0517241379310345,
"grad_norm": 0.15699979662895203,
"learning_rate": 3.05e-06,
"loss": 0.0631,
"step": 61
},
{
"epoch": 1.0689655172413792,
"grad_norm": 0.15650232136249542,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0596,
"step": 62
},
{
"epoch": 1.0862068965517242,
"grad_norm": 0.1188632994890213,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0614,
"step": 63
},
{
"epoch": 1.103448275862069,
"grad_norm": 0.11891665309667587,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0636,
"step": 64
},
{
"epoch": 1.1206896551724137,
"grad_norm": 0.12215171754360199,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0567,
"step": 65
},
{
"epoch": 1.1379310344827587,
"grad_norm": 0.10582094639539719,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0588,
"step": 66
},
{
"epoch": 1.1551724137931034,
"grad_norm": 0.11556132137775421,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0628,
"step": 67
},
{
"epoch": 1.1724137931034484,
"grad_norm": 0.12296544015407562,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0623,
"step": 68
},
{
"epoch": 1.1896551724137931,
"grad_norm": 0.1281358152627945,
"learning_rate": 3.45e-06,
"loss": 0.0626,
"step": 69
},
{
"epoch": 1.206896551724138,
"grad_norm": 0.1277759075164795,
"learning_rate": 3.5e-06,
"loss": 0.0592,
"step": 70
},
{
"epoch": 1.2241379310344827,
"grad_norm": 0.09552627056837082,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0595,
"step": 71
},
{
"epoch": 1.2413793103448276,
"grad_norm": 0.11053085327148438,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0546,
"step": 72
},
{
"epoch": 1.2586206896551724,
"grad_norm": 0.09386970102787018,
"learning_rate": 3.65e-06,
"loss": 0.0556,
"step": 73
},
{
"epoch": 1.2758620689655173,
"grad_norm": 0.0934402197599411,
"learning_rate": 3.7e-06,
"loss": 0.0563,
"step": 74
},
{
"epoch": 1.293103448275862,
"grad_norm": 0.09964020550251007,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0569,
"step": 75
},
{
"epoch": 1.3103448275862069,
"grad_norm": 0.08830665796995163,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0578,
"step": 76
},
{
"epoch": 1.3275862068965516,
"grad_norm": 0.13536307215690613,
"learning_rate": 3.85e-06,
"loss": 0.0569,
"step": 77
},
{
"epoch": 1.3448275862068966,
"grad_norm": 0.10773950815200806,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0581,
"step": 78
},
{
"epoch": 1.3620689655172413,
"grad_norm": 0.09468439221382141,
"learning_rate": 3.95e-06,
"loss": 0.0549,
"step": 79
},
{
"epoch": 1.3793103448275863,
"grad_norm": 0.08775551617145538,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0594,
"step": 80
},
{
"epoch": 1.396551724137931,
"grad_norm": 0.12008150666952133,
"learning_rate": 4.05e-06,
"loss": 0.057,
"step": 81
},
{
"epoch": 1.4137931034482758,
"grad_norm": 0.12070683389902115,
"learning_rate": 4.1e-06,
"loss": 0.0549,
"step": 82
},
{
"epoch": 1.4310344827586206,
"grad_norm": 0.1037198081612587,
"learning_rate": 4.15e-06,
"loss": 0.0554,
"step": 83
},
{
"epoch": 1.4482758620689655,
"grad_norm": 0.14529870450496674,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0549,
"step": 84
},
{
"epoch": 1.4655172413793103,
"grad_norm": 0.0954233855009079,
"learning_rate": 4.25e-06,
"loss": 0.0556,
"step": 85
},
{
"epoch": 1.4827586206896552,
"grad_norm": 0.08504101634025574,
"learning_rate": 4.3e-06,
"loss": 0.0505,
"step": 86
},
{
"epoch": 1.5,
"grad_norm": 0.15293122828006744,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0577,
"step": 87
},
{
"epoch": 1.5172413793103448,
"grad_norm": 0.10908783227205276,
"learning_rate": 4.4e-06,
"loss": 0.0556,
"step": 88
},
{
"epoch": 1.5344827586206895,
"grad_norm": 0.12018983066082001,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0554,
"step": 89
},
{
"epoch": 1.5517241379310345,
"grad_norm": 0.1018645316362381,
"learning_rate": 4.5e-06,
"loss": 0.0548,
"step": 90
},
{
"epoch": 1.5689655172413794,
"grad_norm": 0.09623338282108307,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.0566,
"step": 91
},
{
"epoch": 1.5862068965517242,
"grad_norm": 0.09007120132446289,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0552,
"step": 92
},
{
"epoch": 1.603448275862069,
"grad_norm": 0.07549538463354111,
"learning_rate": 4.65e-06,
"loss": 0.056,
"step": 93
},
{
"epoch": 1.6206896551724137,
"grad_norm": 0.14191967248916626,
"learning_rate": 4.7e-06,
"loss": 0.0547,
"step": 94
},
{
"epoch": 1.6379310344827587,
"grad_norm": 0.13249421119689941,
"learning_rate": 4.75e-06,
"loss": 0.0529,
"step": 95
},
{
"epoch": 1.6551724137931034,
"grad_norm": 0.09079012274742126,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0537,
"step": 96
},
{
"epoch": 1.6724137931034484,
"grad_norm": 0.08319538831710815,
"learning_rate": 4.85e-06,
"loss": 0.0523,
"step": 97
},
{
"epoch": 1.6896551724137931,
"grad_norm": 0.09330669790506363,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0515,
"step": 98
},
{
"epoch": 1.706896551724138,
"grad_norm": 0.1553690880537033,
"learning_rate": 4.95e-06,
"loss": 0.0539,
"step": 99
},
{
"epoch": 1.7241379310344827,
"grad_norm": 0.10644665360450745,
"learning_rate": 5e-06,
"loss": 0.0537,
"step": 100
},
{
"epoch": 1.7413793103448276,
"grad_norm": 0.10171601176261902,
"learning_rate": 4.999799414013322e-06,
"loss": 0.0526,
"step": 101
},
{
"epoch": 1.7586206896551724,
"grad_norm": 0.08432668447494507,
"learning_rate": 4.999197688241076e-06,
"loss": 0.0525,
"step": 102
},
{
"epoch": 1.7758620689655173,
"grad_norm": 0.08552516251802444,
"learning_rate": 4.998194919241471e-06,
"loss": 0.0528,
"step": 103
},
{
"epoch": 1.793103448275862,
"grad_norm": 0.10473164916038513,
"learning_rate": 4.996791267927632e-06,
"loss": 0.0509,
"step": 104
},
{
"epoch": 1.8103448275862069,
"grad_norm": 0.08742501586675644,
"learning_rate": 4.994986959541788e-06,
"loss": 0.0527,
"step": 105
},
{
"epoch": 1.8275862068965516,
"grad_norm": 0.07423796504735947,
"learning_rate": 4.9927822836191185e-06,
"loss": 0.0532,
"step": 106
},
{
"epoch": 1.8448275862068966,
"grad_norm": 0.0921708270907402,
"learning_rate": 4.990177593941303e-06,
"loss": 0.0545,
"step": 107
},
{
"epoch": 1.8620689655172413,
"grad_norm": 0.08664074540138245,
"learning_rate": 4.987173308479738e-06,
"loss": 0.0505,
"step": 108
},
{
"epoch": 1.8793103448275863,
"grad_norm": 0.09824781864881516,
"learning_rate": 4.9837699093284765e-06,
"loss": 0.053,
"step": 109
},
{
"epoch": 1.896551724137931,
"grad_norm": 0.0782749354839325,
"learning_rate": 4.9799679426268575e-06,
"loss": 0.0525,
"step": 110
},
{
"epoch": 1.9137931034482758,
"grad_norm": 0.09107070416212082,
"learning_rate": 4.975768018471877e-06,
"loss": 0.0536,
"step": 111
},
{
"epoch": 1.9310344827586206,
"grad_norm": 0.07815398275852203,
"learning_rate": 4.971170810820279e-06,
"loss": 0.0486,
"step": 112
},
{
"epoch": 1.9482758620689655,
"grad_norm": 0.08175615966320038,
"learning_rate": 4.966177057380409e-06,
"loss": 0.0545,
"step": 113
},
{
"epoch": 1.9655172413793105,
"grad_norm": 0.08906937390565872,
"learning_rate": 4.960787559493836e-06,
"loss": 0.0478,
"step": 114
},
{
"epoch": 1.9827586206896552,
"grad_norm": 0.08419270813465118,
"learning_rate": 4.955003182006761e-06,
"loss": 0.0528,
"step": 115
},
{
"epoch": 2.0,
"grad_norm": 0.10093575716018677,
"learning_rate": 4.948824853131237e-06,
"loss": 0.049,
"step": 116
},
{
"epoch": 2.0172413793103448,
"grad_norm": 0.10379553586244583,
"learning_rate": 4.942253564296217e-06,
"loss": 0.0489,
"step": 117
},
{
"epoch": 2.0344827586206895,
"grad_norm": 0.08708551526069641,
"learning_rate": 4.935290369988468e-06,
"loss": 0.0496,
"step": 118
},
{
"epoch": 2.0517241379310347,
"grad_norm": 0.0780441164970398,
"learning_rate": 4.927936387583348e-06,
"loss": 0.0488,
"step": 119
},
{
"epoch": 2.0689655172413794,
"grad_norm": 0.08206549286842346,
"learning_rate": 4.920192797165511e-06,
"loss": 0.0493,
"step": 120
},
{
"epoch": 2.086206896551724,
"grad_norm": 0.0740761011838913,
"learning_rate": 4.912060841339536e-06,
"loss": 0.0472,
"step": 121
},
{
"epoch": 2.103448275862069,
"grad_norm": 0.10379961133003235,
"learning_rate": 4.9035418250305314e-06,
"loss": 0.0512,
"step": 122
},
{
"epoch": 2.1206896551724137,
"grad_norm": 0.0821395292878151,
"learning_rate": 4.894637115274728e-06,
"loss": 0.0474,
"step": 123
},
{
"epoch": 2.1379310344827585,
"grad_norm": 0.09478521347045898,
"learning_rate": 4.8853481410001225e-06,
"loss": 0.0475,
"step": 124
},
{
"epoch": 2.1551724137931036,
"grad_norm": 0.0971507877111435,
"learning_rate": 4.875676392797169e-06,
"loss": 0.0509,
"step": 125
},
{
"epoch": 2.1724137931034484,
"grad_norm": 0.11455722898244858,
"learning_rate": 4.865623422679593e-06,
"loss": 0.051,
"step": 126
},
{
"epoch": 2.189655172413793,
"grad_norm": 0.10524770617485046,
"learning_rate": 4.855190843835338e-06,
"loss": 0.0486,
"step": 127
},
{
"epoch": 2.206896551724138,
"grad_norm": 0.11388484388589859,
"learning_rate": 4.844380330367701e-06,
"loss": 0.0431,
"step": 128
},
{
"epoch": 2.2241379310344827,
"grad_norm": 0.0915762260556221,
"learning_rate": 4.833193617026692e-06,
"loss": 0.048,
"step": 129
},
{
"epoch": 2.2413793103448274,
"grad_norm": 0.10419991612434387,
"learning_rate": 4.821632498930656e-06,
"loss": 0.0518,
"step": 130
},
{
"epoch": 2.2586206896551726,
"grad_norm": 0.08066820353269577,
"learning_rate": 4.809698831278217e-06,
"loss": 0.0488,
"step": 131
},
{
"epoch": 2.2758620689655173,
"grad_norm": 0.07880278676748276,
"learning_rate": 4.797394529050577e-06,
"loss": 0.048,
"step": 132
},
{
"epoch": 2.293103448275862,
"grad_norm": 0.09013557434082031,
"learning_rate": 4.784721566704217e-06,
"loss": 0.0483,
"step": 133
},
{
"epoch": 2.310344827586207,
"grad_norm": 0.1121375784277916,
"learning_rate": 4.771681977854062e-06,
"loss": 0.0517,
"step": 134
},
{
"epoch": 2.3275862068965516,
"grad_norm": 0.0830090343952179,
"learning_rate": 4.75827785494715e-06,
"loss": 0.0489,
"step": 135
},
{
"epoch": 2.344827586206897,
"grad_norm": 0.08320346474647522,
"learning_rate": 4.744511348926855e-06,
"loss": 0.049,
"step": 136
},
{
"epoch": 2.3620689655172415,
"grad_norm": 0.08780596405267715,
"learning_rate": 4.730384668887731e-06,
"loss": 0.0518,
"step": 137
},
{
"epoch": 2.3793103448275863,
"grad_norm": 0.09375182539224625,
"learning_rate": 4.715900081721021e-06,
"loss": 0.0497,
"step": 138
},
{
"epoch": 2.396551724137931,
"grad_norm": 0.09378068894147873,
"learning_rate": 4.7010599117508936e-06,
"loss": 0.049,
"step": 139
},
{
"epoch": 2.413793103448276,
"grad_norm": 0.11429137736558914,
"learning_rate": 4.685866540361456e-06,
"loss": 0.0464,
"step": 140
},
{
"epoch": 2.4310344827586206,
"grad_norm": 0.08398573845624924,
"learning_rate": 4.670322405614621e-06,
"loss": 0.0487,
"step": 141
},
{
"epoch": 2.4482758620689653,
"grad_norm": 0.08914072066545486,
"learning_rate": 4.654430001858874e-06,
"loss": 0.0483,
"step": 142
},
{
"epoch": 2.4655172413793105,
"grad_norm": 0.09420543164014816,
"learning_rate": 4.638191879329005e-06,
"loss": 0.0496,
"step": 143
},
{
"epoch": 2.4827586206896552,
"grad_norm": 0.13024932146072388,
"learning_rate": 4.621610643736878e-06,
"loss": 0.0437,
"step": 144
},
{
"epoch": 2.5,
"grad_norm": 0.1074167937040329,
"learning_rate": 4.6046889558532925e-06,
"loss": 0.0488,
"step": 145
},
{
"epoch": 2.5172413793103448,
"grad_norm": 0.11312957108020782,
"learning_rate": 4.587429531081019e-06,
"loss": 0.0494,
"step": 146
},
{
"epoch": 2.5344827586206895,
"grad_norm": 0.09910023957490921,
"learning_rate": 4.569835139019054e-06,
"loss": 0.0488,
"step": 147
},
{
"epoch": 2.5517241379310347,
"grad_norm": 0.09021929651498795,
"learning_rate": 4.551908603018191e-06,
"loss": 0.0449,
"step": 148
},
{
"epoch": 2.5689655172413794,
"grad_norm": 0.08959867060184479,
"learning_rate": 4.53365279972796e-06,
"loss": 0.0519,
"step": 149
},
{
"epoch": 2.586206896551724,
"grad_norm": 0.1165613979101181,
"learning_rate": 4.515070658635013e-06,
"loss": 0.0478,
"step": 150
},
{
"epoch": 2.603448275862069,
"grad_norm": 0.10728327184915543,
"learning_rate": 4.4961651615930344e-06,
"loss": 0.0493,
"step": 151
},
{
"epoch": 2.6206896551724137,
"grad_norm": 0.09753444045782089,
"learning_rate": 4.476939342344246e-06,
"loss": 0.0507,
"step": 152
},
{
"epoch": 2.637931034482759,
"grad_norm": 0.08872995525598526,
"learning_rate": 4.457396286032589e-06,
"loss": 0.046,
"step": 153
},
{
"epoch": 2.655172413793103,
"grad_norm": 0.08858656883239746,
"learning_rate": 4.437539128708647e-06,
"loss": 0.0478,
"step": 154
},
{
"epoch": 2.6724137931034484,
"grad_norm": 0.0953850969672203,
"learning_rate": 4.417371056826417e-06,
"loss": 0.0461,
"step": 155
},
{
"epoch": 2.689655172413793,
"grad_norm": 0.09668698161840439,
"learning_rate": 4.396895306731978e-06,
"loss": 0.0476,
"step": 156
},
{
"epoch": 2.706896551724138,
"grad_norm": 0.11896238476037979,
"learning_rate": 4.376115164144157e-06,
"loss": 0.0488,
"step": 157
},
{
"epoch": 2.7241379310344827,
"grad_norm": 0.08256583660840988,
"learning_rate": 4.355033963627277e-06,
"loss": 0.0448,
"step": 158
},
{
"epoch": 2.7413793103448274,
"grad_norm": 0.10837860405445099,
"learning_rate": 4.333655088056065e-06,
"loss": 0.0499,
"step": 159
},
{
"epoch": 2.7586206896551726,
"grad_norm": 0.09428149461746216,
"learning_rate": 4.3119819680728e-06,
"loss": 0.0483,
"step": 160
},
{
"epoch": 2.7758620689655173,
"grad_norm": 0.08462841808795929,
"learning_rate": 4.290018081536807e-06,
"loss": 0.0474,
"step": 161
},
{
"epoch": 2.793103448275862,
"grad_norm": 0.0951421931385994,
"learning_rate": 4.267766952966369e-06,
"loss": 0.0471,
"step": 162
},
{
"epoch": 2.810344827586207,
"grad_norm": 0.08592601120471954,
"learning_rate": 4.245232152973148e-06,
"loss": 0.0452,
"step": 163
},
{
"epoch": 2.8275862068965516,
"grad_norm": 0.09917694330215454,
"learning_rate": 4.222417297689217e-06,
"loss": 0.0489,
"step": 164
},
{
"epoch": 2.844827586206897,
"grad_norm": 0.08759764581918716,
"learning_rate": 4.199326048186783e-06,
"loss": 0.0457,
"step": 165
},
{
"epoch": 2.862068965517241,
"grad_norm": 0.08396806567907333,
"learning_rate": 4.175962109890697e-06,
"loss": 0.0452,
"step": 166
},
{
"epoch": 2.8793103448275863,
"grad_norm": 0.10327853262424469,
"learning_rate": 4.152329231983852e-06,
"loss": 0.0469,
"step": 167
},
{
"epoch": 2.896551724137931,
"grad_norm": 0.11525449901819229,
"learning_rate": 4.128431206805556e-06,
"loss": 0.0486,
"step": 168
},
{
"epoch": 2.913793103448276,
"grad_norm": 0.09090360999107361,
"learning_rate": 4.104271869242975e-06,
"loss": 0.043,
"step": 169
},
{
"epoch": 2.9310344827586206,
"grad_norm": 0.09151678532361984,
"learning_rate": 4.07985509611576e-06,
"loss": 0.0453,
"step": 170
},
{
"epoch": 2.9482758620689653,
"grad_norm": 0.0855179950594902,
"learning_rate": 4.0551848055539345e-06,
"loss": 0.044,
"step": 171
},
{
"epoch": 2.9655172413793105,
"grad_norm": 0.09055305272340775,
"learning_rate": 4.030264956369158e-06,
"loss": 0.0418,
"step": 172
},
{
"epoch": 2.9827586206896552,
"grad_norm": 0.11615358293056488,
"learning_rate": 4.005099547419458e-06,
"loss": 0.0456,
"step": 173
},
{
"epoch": 3.0,
"grad_norm": 0.19266903400421143,
"learning_rate": 3.979692616967543e-06,
"loss": 0.0505,
"step": 174
},
{
"epoch": 3.0172413793103448,
"grad_norm": 0.08485238254070282,
"learning_rate": 3.9540482420327845e-06,
"loss": 0.0445,
"step": 175
},
{
"epoch": 3.0344827586206895,
"grad_norm": 0.11826582998037338,
"learning_rate": 3.9281705377369814e-06,
"loss": 0.0442,
"step": 176
},
{
"epoch": 3.0517241379310347,
"grad_norm": 0.15860383212566376,
"learning_rate": 3.902063656644012e-06,
"loss": 0.0427,
"step": 177
},
{
"epoch": 3.0689655172413794,
"grad_norm": 0.16386628150939941,
"learning_rate": 3.875731788093478e-06,
"loss": 0.041,
"step": 178
},
{
"epoch": 3.086206896551724,
"grad_norm": 0.11814900487661362,
"learning_rate": 3.84917915752845e-06,
"loss": 0.0438,
"step": 179
},
{
"epoch": 3.103448275862069,
"grad_norm": 0.09317006170749664,
"learning_rate": 3.8224100258174066e-06,
"loss": 0.0426,
"step": 180
},
{
"epoch": 3.1206896551724137,
"grad_norm": 0.11639382690191269,
"learning_rate": 3.795428688570505e-06,
"loss": 0.0429,
"step": 181
},
{
"epoch": 3.1379310344827585,
"grad_norm": 0.17201626300811768,
"learning_rate": 3.7682394754502687e-06,
"loss": 0.0454,
"step": 182
},
{
"epoch": 3.1551724137931036,
"grad_norm": 0.12582926452159882,
"learning_rate": 3.7408467494768104e-06,
"loss": 0.0435,
"step": 183
},
{
"epoch": 3.1724137931034484,
"grad_norm": 0.1028057187795639,
"learning_rate": 3.7132549063277033e-06,
"loss": 0.0413,
"step": 184
},
{
"epoch": 3.189655172413793,
"grad_norm": 0.22918114066123962,
"learning_rate": 3.685468373632613e-06,
"loss": 0.043,
"step": 185
},
{
"epoch": 3.206896551724138,
"grad_norm": 0.10135816037654877,
"learning_rate": 3.657491610262802e-06,
"loss": 0.0422,
"step": 186
},
{
"epoch": 3.2241379310344827,
"grad_norm": 0.13638071715831757,
"learning_rate": 3.6293291056156178e-06,
"loss": 0.0428,
"step": 187
},
{
"epoch": 3.2413793103448274,
"grad_norm": 0.10949620604515076,
"learning_rate": 3.600985378894086e-06,
"loss": 0.0401,
"step": 188
},
{
"epoch": 3.2586206896551726,
"grad_norm": 0.09426940977573395,
"learning_rate": 3.572464978381719e-06,
"loss": 0.0434,
"step": 189
},
{
"epoch": 3.2758620689655173,
"grad_norm": 0.09857774525880814,
"learning_rate": 3.5437724807126583e-06,
"loss": 0.0436,
"step": 190
},
{
"epoch": 3.293103448275862,
"grad_norm": 0.1132907122373581,
"learning_rate": 3.514912490137268e-06,
"loss": 0.0426,
"step": 191
},
{
"epoch": 3.310344827586207,
"grad_norm": 0.13569223880767822,
"learning_rate": 3.4858896377832966e-06,
"loss": 0.0432,
"step": 192
},
{
"epoch": 3.3275862068965516,
"grad_norm": 0.10156653821468353,
"learning_rate": 3.4567085809127247e-06,
"loss": 0.0429,
"step": 193
},
{
"epoch": 3.344827586206897,
"grad_norm": 0.08835293352603912,
"learning_rate": 3.42737400217442e-06,
"loss": 0.0423,
"step": 194
},
{
"epoch": 3.3620689655172415,
"grad_norm": 0.10820037126541138,
"learning_rate": 3.397890608852718e-06,
"loss": 0.0411,
"step": 195
},
{
"epoch": 3.3793103448275863,
"grad_norm": 0.10201743245124817,
"learning_rate": 3.3682631321120507e-06,
"loss": 0.0452,
"step": 196
},
{
"epoch": 3.396551724137931,
"grad_norm": 0.11937723308801651,
"learning_rate": 3.3384963262377434e-06,
"loss": 0.0414,
"step": 197
},
{
"epoch": 3.413793103448276,
"grad_norm": 0.0974365696310997,
"learning_rate": 3.3085949678730953e-06,
"loss": 0.0427,
"step": 198
},
{
"epoch": 3.4310344827586206,
"grad_norm": 0.08945067226886749,
"learning_rate": 3.278563855252885e-06,
"loss": 0.0443,
"step": 199
},
{
"epoch": 3.4482758620689653,
"grad_norm": 0.11221472173929214,
"learning_rate": 3.248407807433396e-06,
"loss": 0.0452,
"step": 200
},
{
"epoch": 3.4655172413793105,
"grad_norm": 0.0896143838763237,
"learning_rate": 3.2181316635191125e-06,
"loss": 0.0406,
"step": 201
},
{
"epoch": 3.4827586206896552,
"grad_norm": 0.10082851350307465,
"learning_rate": 3.1877402818861954e-06,
"loss": 0.0419,
"step": 202
},
{
"epoch": 3.5,
"grad_norm": 0.08753880858421326,
"learning_rate": 3.157238539402862e-06,
"loss": 0.0452,
"step": 203
},
{
"epoch": 3.5172413793103448,
"grad_norm": 0.11920648068189621,
"learning_rate": 3.1266313306468018e-06,
"loss": 0.0435,
"step": 204
},
{
"epoch": 3.5344827586206895,
"grad_norm": 0.09174811840057373,
"learning_rate": 3.095923567119748e-06,
"loss": 0.043,
"step": 205
},
{
"epoch": 3.5517241379310347,
"grad_norm": 0.09737736731767654,
"learning_rate": 3.0651201764593375e-06,
"loss": 0.0426,
"step": 206
},
{
"epoch": 3.5689655172413794,
"grad_norm": 0.11272215098142624,
"learning_rate": 3.034226101648377e-06,
"loss": 0.0441,
"step": 207
},
{
"epoch": 3.586206896551724,
"grad_norm": 0.09450715780258179,
"learning_rate": 3.0032463002216504e-06,
"loss": 0.0396,
"step": 208
},
{
"epoch": 3.603448275862069,
"grad_norm": 0.10545044392347336,
"learning_rate": 2.972185743470386e-06,
"loss": 0.0417,
"step": 209
},
{
"epoch": 3.6206896551724137,
"grad_norm": 0.12524767220020294,
"learning_rate": 2.941049415644522e-06,
"loss": 0.0419,
"step": 210
},
{
"epoch": 3.637931034482759,
"grad_norm": 0.11580915749073029,
"learning_rate": 2.909842313152888e-06,
"loss": 0.0425,
"step": 211
},
{
"epoch": 3.655172413793103,
"grad_norm": 0.10487856715917587,
"learning_rate": 2.878569443761442e-06,
"loss": 0.0414,
"step": 212
},
{
"epoch": 3.6724137931034484,
"grad_norm": 0.10465347766876221,
"learning_rate": 2.847235825789673e-06,
"loss": 0.0422,
"step": 213
},
{
"epoch": 3.689655172413793,
"grad_norm": 0.10166613757610321,
"learning_rate": 2.8158464873053236e-06,
"loss": 0.041,
"step": 214
},
{
"epoch": 3.706896551724138,
"grad_norm": 0.13111358880996704,
"learning_rate": 2.784406465317538e-06,
"loss": 0.0444,
"step": 215
},
{
"epoch": 3.7241379310344827,
"grad_norm": 0.10421358048915863,
"learning_rate": 2.752920804968581e-06,
"loss": 0.0401,
"step": 216
},
{
"epoch": 3.7413793103448274,
"grad_norm": 0.10978563874959946,
"learning_rate": 2.7213945587242507e-06,
"loss": 0.0422,
"step": 217
},
{
"epoch": 3.7586206896551726,
"grad_norm": 0.11075913906097412,
"learning_rate": 2.689832785563116e-06,
"loss": 0.0429,
"step": 218
},
{
"epoch": 3.7758620689655173,
"grad_norm": 0.15385261178016663,
"learning_rate": 2.658240550164704e-06,
"loss": 0.0401,
"step": 219
},
{
"epoch": 3.793103448275862,
"grad_norm": 0.10451245307922363,
"learning_rate": 2.626622922096782e-06,
"loss": 0.0426,
"step": 220
},
{
"epoch": 3.810344827586207,
"grad_norm": 0.11295191198587418,
"learning_rate": 2.5949849750018486e-06,
"loss": 0.0422,
"step": 221
},
{
"epoch": 3.8275862068965516,
"grad_norm": 0.11170029640197754,
"learning_rate": 2.56333178578297e-06,
"loss": 0.0451,
"step": 222
},
{
"epoch": 3.844827586206897,
"grad_norm": 0.11065405607223511,
"learning_rate": 2.5316684337891005e-06,
"loss": 0.0412,
"step": 223
},
{
"epoch": 3.862068965517241,
"grad_norm": 0.12961585819721222,
"learning_rate": 2.5e-06,
"loss": 0.042,
"step": 224
},
{
"epoch": 3.8793103448275863,
"grad_norm": 0.10577612370252609,
"learning_rate": 2.4683315662109003e-06,
"loss": 0.0408,
"step": 225
},
{
"epoch": 3.896551724137931,
"grad_norm": 0.10059581696987152,
"learning_rate": 2.436668214217031e-06,
"loss": 0.0398,
"step": 226
},
{
"epoch": 3.913793103448276,
"grad_norm": 0.10648361593484879,
"learning_rate": 2.4050150249981522e-06,
"loss": 0.0389,
"step": 227
},
{
"epoch": 3.9310344827586206,
"grad_norm": 0.10775142163038254,
"learning_rate": 2.3733770779032185e-06,
"loss": 0.0408,
"step": 228
},
{
"epoch": 3.9482758620689653,
"grad_norm": 0.11544917523860931,
"learning_rate": 2.341759449835297e-06,
"loss": 0.0359,
"step": 229
},
{
"epoch": 3.9655172413793105,
"grad_norm": 0.10996822267770767,
"learning_rate": 2.310167214436885e-06,
"loss": 0.0392,
"step": 230
},
{
"epoch": 3.9827586206896552,
"grad_norm": 0.1188119500875473,
"learning_rate": 2.27860544127575e-06,
"loss": 0.0368,
"step": 231
},
{
"epoch": 4.0,
"grad_norm": 0.12459355592727661,
"learning_rate": 2.24707919503142e-06,
"loss": 0.0383,
"step": 232
}
],
"logging_steps": 1,
"max_steps": 348,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 58,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.193794508347671e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}