ncbateman's picture
Training in progress, step 195, checkpoint
51eebd3 verified
raw
history blame
34.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2523455192494338,
"eval_steps": 386,
"global_step": 195,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012940795858945326,
"grad_norm": 1.7405146360397339,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.4269,
"step": 1
},
{
"epoch": 0.0012940795858945326,
"eval_loss": 2.247628688812256,
"eval_runtime": 189.8853,
"eval_samples_per_second": 3.428,
"eval_steps_per_second": 0.858,
"step": 1
},
{
"epoch": 0.002588159171789065,
"grad_norm": 1.6643542051315308,
"learning_rate": 4.000000000000001e-06,
"loss": 2.2583,
"step": 2
},
{
"epoch": 0.0038822387576835974,
"grad_norm": 1.8690767288208008,
"learning_rate": 6e-06,
"loss": 2.2696,
"step": 3
},
{
"epoch": 0.00517631834357813,
"grad_norm": 1.828118085861206,
"learning_rate": 8.000000000000001e-06,
"loss": 2.3646,
"step": 4
},
{
"epoch": 0.006470397929472662,
"grad_norm": 1.9319926500320435,
"learning_rate": 1e-05,
"loss": 2.4196,
"step": 5
},
{
"epoch": 0.007764477515367195,
"grad_norm": 1.7723782062530518,
"learning_rate": 1.2e-05,
"loss": 2.4177,
"step": 6
},
{
"epoch": 0.009058557101261728,
"grad_norm": 1.9500815868377686,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.3497,
"step": 7
},
{
"epoch": 0.01035263668715626,
"grad_norm": 2.3909075260162354,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.405,
"step": 8
},
{
"epoch": 0.011646716273050793,
"grad_norm": 2.0620856285095215,
"learning_rate": 1.8e-05,
"loss": 2.4098,
"step": 9
},
{
"epoch": 0.012940795858945324,
"grad_norm": 1.8054910898208618,
"learning_rate": 2e-05,
"loss": 2.1233,
"step": 10
},
{
"epoch": 0.014234875444839857,
"grad_norm": 2.190964937210083,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.3985,
"step": 11
},
{
"epoch": 0.01552895503073439,
"grad_norm": 1.9412921667099,
"learning_rate": 2.4e-05,
"loss": 2.462,
"step": 12
},
{
"epoch": 0.016823034616628922,
"grad_norm": 1.9161555767059326,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.2118,
"step": 13
},
{
"epoch": 0.018117114202523456,
"grad_norm": 1.7161599397659302,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.2175,
"step": 14
},
{
"epoch": 0.019411193788417987,
"grad_norm": 2.173877000808716,
"learning_rate": 3e-05,
"loss": 2.2521,
"step": 15
},
{
"epoch": 0.02070527337431252,
"grad_norm": 2.0000555515289307,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.1615,
"step": 16
},
{
"epoch": 0.021999352960207053,
"grad_norm": 1.5915080308914185,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.9522,
"step": 17
},
{
"epoch": 0.023293432546101587,
"grad_norm": 1.6972448825836182,
"learning_rate": 3.6e-05,
"loss": 1.7224,
"step": 18
},
{
"epoch": 0.024587512131996118,
"grad_norm": 1.7509772777557373,
"learning_rate": 3.8e-05,
"loss": 2.0414,
"step": 19
},
{
"epoch": 0.02588159171789065,
"grad_norm": 1.697340488433838,
"learning_rate": 4e-05,
"loss": 2.0427,
"step": 20
},
{
"epoch": 0.027175671303785183,
"grad_norm": 1.8733758926391602,
"learning_rate": 4.2e-05,
"loss": 1.6772,
"step": 21
},
{
"epoch": 0.028469750889679714,
"grad_norm": 1.6085255146026611,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.6527,
"step": 22
},
{
"epoch": 0.029763830475574248,
"grad_norm": 1.5792337656021118,
"learning_rate": 4.600000000000001e-05,
"loss": 1.6567,
"step": 23
},
{
"epoch": 0.03105791006146878,
"grad_norm": 1.4392567873001099,
"learning_rate": 4.8e-05,
"loss": 1.508,
"step": 24
},
{
"epoch": 0.03235198964736331,
"grad_norm": 1.5222433805465698,
"learning_rate": 5e-05,
"loss": 1.4606,
"step": 25
},
{
"epoch": 0.033646069233257844,
"grad_norm": 1.5480064153671265,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.5027,
"step": 26
},
{
"epoch": 0.034940148819152375,
"grad_norm": 1.6736445426940918,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.2426,
"step": 27
},
{
"epoch": 0.03623422840504691,
"grad_norm": 1.7392551898956299,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.4703,
"step": 28
},
{
"epoch": 0.037528307990941444,
"grad_norm": 1.6173359155654907,
"learning_rate": 5.8e-05,
"loss": 1.4546,
"step": 29
},
{
"epoch": 0.038822387576835975,
"grad_norm": 1.3955802917480469,
"learning_rate": 6e-05,
"loss": 1.3808,
"step": 30
},
{
"epoch": 0.040116467162730506,
"grad_norm": 1.353873372077942,
"learning_rate": 6.2e-05,
"loss": 1.229,
"step": 31
},
{
"epoch": 0.04141054674862504,
"grad_norm": 1.2547746896743774,
"learning_rate": 6.400000000000001e-05,
"loss": 1.1668,
"step": 32
},
{
"epoch": 0.042704626334519574,
"grad_norm": 1.3806778192520142,
"learning_rate": 6.6e-05,
"loss": 1.0691,
"step": 33
},
{
"epoch": 0.043998705920414105,
"grad_norm": 1.2815773487091064,
"learning_rate": 6.800000000000001e-05,
"loss": 1.2409,
"step": 34
},
{
"epoch": 0.045292785506308636,
"grad_norm": 1.3677266836166382,
"learning_rate": 7e-05,
"loss": 0.9668,
"step": 35
},
{
"epoch": 0.046586865092203174,
"grad_norm": 1.5457032918930054,
"learning_rate": 7.2e-05,
"loss": 1.1385,
"step": 36
},
{
"epoch": 0.047880944678097705,
"grad_norm": 1.5587060451507568,
"learning_rate": 7.4e-05,
"loss": 1.1707,
"step": 37
},
{
"epoch": 0.049175024263992236,
"grad_norm": 1.079053282737732,
"learning_rate": 7.6e-05,
"loss": 1.0655,
"step": 38
},
{
"epoch": 0.050469103849886766,
"grad_norm": 1.1773897409439087,
"learning_rate": 7.800000000000001e-05,
"loss": 1.0465,
"step": 39
},
{
"epoch": 0.0517631834357813,
"grad_norm": 1.2437673807144165,
"learning_rate": 8e-05,
"loss": 1.2779,
"step": 40
},
{
"epoch": 0.053057263021675835,
"grad_norm": 1.254847526550293,
"learning_rate": 8.2e-05,
"loss": 1.0898,
"step": 41
},
{
"epoch": 0.054351342607570366,
"grad_norm": 1.1771515607833862,
"learning_rate": 8.4e-05,
"loss": 1.1827,
"step": 42
},
{
"epoch": 0.0556454221934649,
"grad_norm": 1.1400648355484009,
"learning_rate": 8.6e-05,
"loss": 1.1066,
"step": 43
},
{
"epoch": 0.05693950177935943,
"grad_norm": 1.2047138214111328,
"learning_rate": 8.800000000000001e-05,
"loss": 0.8974,
"step": 44
},
{
"epoch": 0.058233581365253966,
"grad_norm": 1.1269346475601196,
"learning_rate": 9e-05,
"loss": 1.0146,
"step": 45
},
{
"epoch": 0.059527660951148496,
"grad_norm": 1.169231653213501,
"learning_rate": 9.200000000000001e-05,
"loss": 1.1266,
"step": 46
},
{
"epoch": 0.06082174053704303,
"grad_norm": 0.9771779179573059,
"learning_rate": 9.4e-05,
"loss": 0.8351,
"step": 47
},
{
"epoch": 0.06211582012293756,
"grad_norm": 1.2849314212799072,
"learning_rate": 9.6e-05,
"loss": 1.1822,
"step": 48
},
{
"epoch": 0.0634098997088321,
"grad_norm": 1.023181676864624,
"learning_rate": 9.8e-05,
"loss": 0.9082,
"step": 49
},
{
"epoch": 0.06470397929472663,
"grad_norm": 1.135751724243164,
"learning_rate": 0.0001,
"loss": 0.9407,
"step": 50
},
{
"epoch": 0.06599805888062116,
"grad_norm": 0.9701154828071594,
"learning_rate": 9.999998300231494e-05,
"loss": 0.9423,
"step": 51
},
{
"epoch": 0.06729213846651569,
"grad_norm": 1.2891143560409546,
"learning_rate": 9.999993200927133e-05,
"loss": 0.9757,
"step": 52
},
{
"epoch": 0.06858621805241022,
"grad_norm": 1.3360975980758667,
"learning_rate": 9.999984702090383e-05,
"loss": 1.0158,
"step": 53
},
{
"epoch": 0.06988029763830475,
"grad_norm": 0.977446436882019,
"learning_rate": 9.999972803727024e-05,
"loss": 0.8175,
"step": 54
},
{
"epoch": 0.0711743772241993,
"grad_norm": 0.9943827390670776,
"learning_rate": 9.999957505845144e-05,
"loss": 0.8627,
"step": 55
},
{
"epoch": 0.07246845681009383,
"grad_norm": 1.1531224250793457,
"learning_rate": 9.999938808455145e-05,
"loss": 1.143,
"step": 56
},
{
"epoch": 0.07376253639598836,
"grad_norm": 1.287972092628479,
"learning_rate": 9.99991671156974e-05,
"loss": 1.2342,
"step": 57
},
{
"epoch": 0.07505661598188289,
"grad_norm": 1.1554590463638306,
"learning_rate": 9.999891215203949e-05,
"loss": 0.9692,
"step": 58
},
{
"epoch": 0.07635069556777742,
"grad_norm": 1.0786008834838867,
"learning_rate": 9.999862319375113e-05,
"loss": 1.1254,
"step": 59
},
{
"epoch": 0.07764477515367195,
"grad_norm": 1.0764508247375488,
"learning_rate": 9.999830024102874e-05,
"loss": 0.9312,
"step": 60
},
{
"epoch": 0.07893885473956648,
"grad_norm": 1.1909526586532593,
"learning_rate": 9.999794329409194e-05,
"loss": 0.9959,
"step": 61
},
{
"epoch": 0.08023293432546101,
"grad_norm": 0.9989166259765625,
"learning_rate": 9.999755235318337e-05,
"loss": 0.934,
"step": 62
},
{
"epoch": 0.08152701391135554,
"grad_norm": 1.0302046537399292,
"learning_rate": 9.999712741856889e-05,
"loss": 1.1017,
"step": 63
},
{
"epoch": 0.08282109349725009,
"grad_norm": 0.9583478569984436,
"learning_rate": 9.999666849053738e-05,
"loss": 1.1384,
"step": 64
},
{
"epoch": 0.08411517308314462,
"grad_norm": 1.001126766204834,
"learning_rate": 9.999617556940085e-05,
"loss": 0.9279,
"step": 65
},
{
"epoch": 0.08540925266903915,
"grad_norm": 1.0130903720855713,
"learning_rate": 9.999564865549449e-05,
"loss": 0.9381,
"step": 66
},
{
"epoch": 0.08670333225493368,
"grad_norm": 1.1210829019546509,
"learning_rate": 9.999508774917652e-05,
"loss": 0.9607,
"step": 67
},
{
"epoch": 0.08799741184082821,
"grad_norm": 1.045749545097351,
"learning_rate": 9.999449285082831e-05,
"loss": 1.0037,
"step": 68
},
{
"epoch": 0.08929149142672274,
"grad_norm": 1.1308139562606812,
"learning_rate": 9.999386396085434e-05,
"loss": 0.9086,
"step": 69
},
{
"epoch": 0.09058557101261727,
"grad_norm": 1.1013413667678833,
"learning_rate": 9.999320107968219e-05,
"loss": 1.0712,
"step": 70
},
{
"epoch": 0.0918796505985118,
"grad_norm": 1.0830566883087158,
"learning_rate": 9.999250420776258e-05,
"loss": 1.0326,
"step": 71
},
{
"epoch": 0.09317373018440635,
"grad_norm": 1.0673171281814575,
"learning_rate": 9.999177334556929e-05,
"loss": 1.0034,
"step": 72
},
{
"epoch": 0.09446780977030088,
"grad_norm": 1.1546461582183838,
"learning_rate": 9.999100849359926e-05,
"loss": 1.059,
"step": 73
},
{
"epoch": 0.09576188935619541,
"grad_norm": 0.9139528870582581,
"learning_rate": 9.999020965237249e-05,
"loss": 0.8596,
"step": 74
},
{
"epoch": 0.09705596894208994,
"grad_norm": 1.1570812463760376,
"learning_rate": 9.998937682243215e-05,
"loss": 1.0456,
"step": 75
},
{
"epoch": 0.09835004852798447,
"grad_norm": 1.3232612609863281,
"learning_rate": 9.998851000434448e-05,
"loss": 0.9994,
"step": 76
},
{
"epoch": 0.099644128113879,
"grad_norm": 1.2017115354537964,
"learning_rate": 9.998760919869883e-05,
"loss": 1.2664,
"step": 77
},
{
"epoch": 0.10093820769977353,
"grad_norm": 1.0694175958633423,
"learning_rate": 9.998667440610765e-05,
"loss": 0.9483,
"step": 78
},
{
"epoch": 0.10223228728566806,
"grad_norm": 0.9963059425354004,
"learning_rate": 9.998570562720654e-05,
"loss": 0.9577,
"step": 79
},
{
"epoch": 0.1035263668715626,
"grad_norm": 0.8873535394668579,
"learning_rate": 9.998470286265416e-05,
"loss": 0.8498,
"step": 80
},
{
"epoch": 0.10482044645745714,
"grad_norm": 1.1350760459899902,
"learning_rate": 9.99836661131323e-05,
"loss": 1.0024,
"step": 81
},
{
"epoch": 0.10611452604335167,
"grad_norm": 0.8355389833450317,
"learning_rate": 9.998259537934586e-05,
"loss": 0.7399,
"step": 82
},
{
"epoch": 0.1074086056292462,
"grad_norm": 0.9935446381568909,
"learning_rate": 9.998149066202284e-05,
"loss": 0.9809,
"step": 83
},
{
"epoch": 0.10870268521514073,
"grad_norm": 1.0571558475494385,
"learning_rate": 9.998035196191435e-05,
"loss": 1.0144,
"step": 84
},
{
"epoch": 0.10999676480103526,
"grad_norm": 0.9860286116600037,
"learning_rate": 9.99791792797946e-05,
"loss": 1.0467,
"step": 85
},
{
"epoch": 0.1112908443869298,
"grad_norm": 1.1422507762908936,
"learning_rate": 9.997797261646089e-05,
"loss": 0.9535,
"step": 86
},
{
"epoch": 0.11258492397282432,
"grad_norm": 0.8561545014381409,
"learning_rate": 9.997673197273365e-05,
"loss": 1.007,
"step": 87
},
{
"epoch": 0.11387900355871886,
"grad_norm": 1.0027543306350708,
"learning_rate": 9.997545734945639e-05,
"loss": 0.9861,
"step": 88
},
{
"epoch": 0.1151730831446134,
"grad_norm": 0.8489773273468018,
"learning_rate": 9.997414874749575e-05,
"loss": 0.9672,
"step": 89
},
{
"epoch": 0.11646716273050793,
"grad_norm": 1.0517115592956543,
"learning_rate": 9.997280616774147e-05,
"loss": 1.1672,
"step": 90
},
{
"epoch": 0.11776124231640246,
"grad_norm": 1.0035395622253418,
"learning_rate": 9.997142961110634e-05,
"loss": 0.9294,
"step": 91
},
{
"epoch": 0.11905532190229699,
"grad_norm": 1.1194915771484375,
"learning_rate": 9.997001907852635e-05,
"loss": 1.0857,
"step": 92
},
{
"epoch": 0.12034940148819152,
"grad_norm": 1.5234825611114502,
"learning_rate": 9.996857457096047e-05,
"loss": 1.027,
"step": 93
},
{
"epoch": 0.12164348107408605,
"grad_norm": 0.949878454208374,
"learning_rate": 9.996709608939088e-05,
"loss": 0.8173,
"step": 94
},
{
"epoch": 0.12293756065998059,
"grad_norm": 0.8736472129821777,
"learning_rate": 9.996558363482277e-05,
"loss": 0.855,
"step": 95
},
{
"epoch": 0.12423164024587512,
"grad_norm": 0.8604567050933838,
"learning_rate": 9.996403720828449e-05,
"loss": 0.9485,
"step": 96
},
{
"epoch": 0.12552571983176966,
"grad_norm": 1.020851492881775,
"learning_rate": 9.996245681082748e-05,
"loss": 1.0024,
"step": 97
},
{
"epoch": 0.1268197994176642,
"grad_norm": 1.0704892873764038,
"learning_rate": 9.996084244352623e-05,
"loss": 0.9246,
"step": 98
},
{
"epoch": 0.12811387900355872,
"grad_norm": 0.8441987037658691,
"learning_rate": 9.99591941074784e-05,
"loss": 1.0343,
"step": 99
},
{
"epoch": 0.12940795858945325,
"grad_norm": 1.0280612707138062,
"learning_rate": 9.995751180380466e-05,
"loss": 0.9644,
"step": 100
},
{
"epoch": 0.13070203817534778,
"grad_norm": 0.9827906489372253,
"learning_rate": 9.995579553364887e-05,
"loss": 0.9583,
"step": 101
},
{
"epoch": 0.13199611776124232,
"grad_norm": 1.035618543624878,
"learning_rate": 9.995404529817791e-05,
"loss": 1.0366,
"step": 102
},
{
"epoch": 0.13329019734713685,
"grad_norm": 1.2775524854660034,
"learning_rate": 9.995226109858178e-05,
"loss": 0.9353,
"step": 103
},
{
"epoch": 0.13458427693303138,
"grad_norm": 1.0101919174194336,
"learning_rate": 9.995044293607355e-05,
"loss": 0.9045,
"step": 104
},
{
"epoch": 0.1358783565189259,
"grad_norm": 0.8396942019462585,
"learning_rate": 9.994859081188943e-05,
"loss": 0.867,
"step": 105
},
{
"epoch": 0.13717243610482044,
"grad_norm": 1.04515540599823,
"learning_rate": 9.99467047272887e-05,
"loss": 0.9693,
"step": 106
},
{
"epoch": 0.13846651569071497,
"grad_norm": 1.099042534828186,
"learning_rate": 9.994478468355369e-05,
"loss": 0.8879,
"step": 107
},
{
"epoch": 0.1397605952766095,
"grad_norm": 0.8710360527038574,
"learning_rate": 9.994283068198988e-05,
"loss": 0.9018,
"step": 108
},
{
"epoch": 0.14105467486250403,
"grad_norm": 0.961025059223175,
"learning_rate": 9.99408427239258e-05,
"loss": 0.8806,
"step": 109
},
{
"epoch": 0.1423487544483986,
"grad_norm": 0.915665328502655,
"learning_rate": 9.993882081071306e-05,
"loss": 0.8628,
"step": 110
},
{
"epoch": 0.14364283403429312,
"grad_norm": 1.2776648998260498,
"learning_rate": 9.993676494372642e-05,
"loss": 0.9742,
"step": 111
},
{
"epoch": 0.14493691362018765,
"grad_norm": 1.1270071268081665,
"learning_rate": 9.993467512436364e-05,
"loss": 0.9729,
"step": 112
},
{
"epoch": 0.14623099320608218,
"grad_norm": 0.8188664317131042,
"learning_rate": 9.99325513540456e-05,
"loss": 0.9428,
"step": 113
},
{
"epoch": 0.1475250727919767,
"grad_norm": 1.0760393142700195,
"learning_rate": 9.993039363421627e-05,
"loss": 0.9482,
"step": 114
},
{
"epoch": 0.14881915237787124,
"grad_norm": 1.019920825958252,
"learning_rate": 9.992820196634273e-05,
"loss": 0.9785,
"step": 115
},
{
"epoch": 0.15011323196376578,
"grad_norm": 0.8342046737670898,
"learning_rate": 9.992597635191509e-05,
"loss": 0.9291,
"step": 116
},
{
"epoch": 0.1514073115496603,
"grad_norm": 0.8460632562637329,
"learning_rate": 9.992371679244658e-05,
"loss": 0.8797,
"step": 117
},
{
"epoch": 0.15270139113555484,
"grad_norm": 0.933060348033905,
"learning_rate": 9.992142328947345e-05,
"loss": 0.9657,
"step": 118
},
{
"epoch": 0.15399547072144937,
"grad_norm": 0.8822593688964844,
"learning_rate": 9.991909584455511e-05,
"loss": 0.8872,
"step": 119
},
{
"epoch": 0.1552895503073439,
"grad_norm": 0.9599350094795227,
"learning_rate": 9.991673445927398e-05,
"loss": 0.9064,
"step": 120
},
{
"epoch": 0.15658362989323843,
"grad_norm": 0.8505874872207642,
"learning_rate": 9.99143391352356e-05,
"loss": 0.9966,
"step": 121
},
{
"epoch": 0.15787770947913296,
"grad_norm": 1.3977786302566528,
"learning_rate": 9.991190987406857e-05,
"loss": 0.9145,
"step": 122
},
{
"epoch": 0.1591717890650275,
"grad_norm": 0.8947294354438782,
"learning_rate": 9.990944667742455e-05,
"loss": 0.9569,
"step": 123
},
{
"epoch": 0.16046586865092202,
"grad_norm": 0.7973839044570923,
"learning_rate": 9.990694954697828e-05,
"loss": 0.8853,
"step": 124
},
{
"epoch": 0.16175994823681655,
"grad_norm": 0.9481159448623657,
"learning_rate": 9.99044184844276e-05,
"loss": 1.04,
"step": 125
},
{
"epoch": 0.16305402782271108,
"grad_norm": 1.3568611145019531,
"learning_rate": 9.990185349149339e-05,
"loss": 1.1104,
"step": 126
},
{
"epoch": 0.16434810740860564,
"grad_norm": 0.900867223739624,
"learning_rate": 9.98992545699196e-05,
"loss": 0.8427,
"step": 127
},
{
"epoch": 0.16564218699450017,
"grad_norm": 0.9025059938430786,
"learning_rate": 9.989662172147326e-05,
"loss": 0.9671,
"step": 128
},
{
"epoch": 0.1669362665803947,
"grad_norm": 0.944692850112915,
"learning_rate": 9.989395494794446e-05,
"loss": 1.0966,
"step": 129
},
{
"epoch": 0.16823034616628924,
"grad_norm": 1.196311116218567,
"learning_rate": 9.989125425114638e-05,
"loss": 1.0888,
"step": 130
},
{
"epoch": 0.16952442575218377,
"grad_norm": 0.9069584608078003,
"learning_rate": 9.988851963291522e-05,
"loss": 0.8579,
"step": 131
},
{
"epoch": 0.1708185053380783,
"grad_norm": 0.8150789141654968,
"learning_rate": 9.988575109511026e-05,
"loss": 0.7622,
"step": 132
},
{
"epoch": 0.17211258492397283,
"grad_norm": 1.0844395160675049,
"learning_rate": 9.988294863961387e-05,
"loss": 0.9284,
"step": 133
},
{
"epoch": 0.17340666450986736,
"grad_norm": 1.0463049411773682,
"learning_rate": 9.988011226833146e-05,
"loss": 0.9185,
"step": 134
},
{
"epoch": 0.1747007440957619,
"grad_norm": 0.9481234550476074,
"learning_rate": 9.987724198319148e-05,
"loss": 0.8631,
"step": 135
},
{
"epoch": 0.17599482368165642,
"grad_norm": 0.882074773311615,
"learning_rate": 9.987433778614549e-05,
"loss": 0.8997,
"step": 136
},
{
"epoch": 0.17728890326755095,
"grad_norm": 0.9853332042694092,
"learning_rate": 9.987139967916805e-05,
"loss": 0.9226,
"step": 137
},
{
"epoch": 0.17858298285344548,
"grad_norm": 1.151941180229187,
"learning_rate": 9.98684276642568e-05,
"loss": 1.0486,
"step": 138
},
{
"epoch": 0.17987706243934,
"grad_norm": 1.0128459930419922,
"learning_rate": 9.986542174343245e-05,
"loss": 1.0797,
"step": 139
},
{
"epoch": 0.18117114202523454,
"grad_norm": 0.9798718094825745,
"learning_rate": 9.986238191873874e-05,
"loss": 0.875,
"step": 140
},
{
"epoch": 0.18246522161112907,
"grad_norm": 0.8143295645713806,
"learning_rate": 9.985930819224247e-05,
"loss": 0.8454,
"step": 141
},
{
"epoch": 0.1837593011970236,
"grad_norm": 0.8755755424499512,
"learning_rate": 9.985620056603348e-05,
"loss": 0.8029,
"step": 142
},
{
"epoch": 0.18505338078291814,
"grad_norm": 0.899174690246582,
"learning_rate": 9.985305904222469e-05,
"loss": 0.9608,
"step": 143
},
{
"epoch": 0.1863474603688127,
"grad_norm": 0.920137882232666,
"learning_rate": 9.984988362295203e-05,
"loss": 0.9022,
"step": 144
},
{
"epoch": 0.18764153995470723,
"grad_norm": 1.1012908220291138,
"learning_rate": 9.984667431037447e-05,
"loss": 0.9621,
"step": 145
},
{
"epoch": 0.18893561954060176,
"grad_norm": 0.8609358668327332,
"learning_rate": 9.98434311066741e-05,
"loss": 0.917,
"step": 146
},
{
"epoch": 0.1902296991264963,
"grad_norm": 0.8248727321624756,
"learning_rate": 9.984015401405594e-05,
"loss": 0.7864,
"step": 147
},
{
"epoch": 0.19152377871239082,
"grad_norm": 0.8680225610733032,
"learning_rate": 9.983684303474815e-05,
"loss": 0.9288,
"step": 148
},
{
"epoch": 0.19281785829828535,
"grad_norm": 1.0807067155838013,
"learning_rate": 9.983349817100188e-05,
"loss": 0.9842,
"step": 149
},
{
"epoch": 0.19411193788417988,
"grad_norm": 0.9310898780822754,
"learning_rate": 9.983011942509131e-05,
"loss": 1.0568,
"step": 150
},
{
"epoch": 0.1954060174700744,
"grad_norm": 0.8052242398262024,
"learning_rate": 9.98267067993137e-05,
"loss": 0.8235,
"step": 151
},
{
"epoch": 0.19670009705596894,
"grad_norm": 0.9700384140014648,
"learning_rate": 9.982326029598931e-05,
"loss": 0.8611,
"step": 152
},
{
"epoch": 0.19799417664186347,
"grad_norm": 0.8437764048576355,
"learning_rate": 9.981977991746142e-05,
"loss": 0.83,
"step": 153
},
{
"epoch": 0.199288256227758,
"grad_norm": 0.930636465549469,
"learning_rate": 9.98162656660964e-05,
"loss": 1.0892,
"step": 154
},
{
"epoch": 0.20058233581365253,
"grad_norm": 0.9111954569816589,
"learning_rate": 9.98127175442836e-05,
"loss": 0.9962,
"step": 155
},
{
"epoch": 0.20187641539954707,
"grad_norm": 0.9521974921226501,
"learning_rate": 9.980913555443541e-05,
"loss": 0.911,
"step": 156
},
{
"epoch": 0.2031704949854416,
"grad_norm": 0.8516745567321777,
"learning_rate": 9.980551969898727e-05,
"loss": 0.9009,
"step": 157
},
{
"epoch": 0.20446457457133613,
"grad_norm": 0.8302998542785645,
"learning_rate": 9.98018699803976e-05,
"loss": 0.8854,
"step": 158
},
{
"epoch": 0.20575865415723066,
"grad_norm": 0.814391016960144,
"learning_rate": 9.979818640114789e-05,
"loss": 0.9601,
"step": 159
},
{
"epoch": 0.2070527337431252,
"grad_norm": 0.8938564658164978,
"learning_rate": 9.979446896374262e-05,
"loss": 0.8834,
"step": 160
},
{
"epoch": 0.20834681332901975,
"grad_norm": 0.9066985249519348,
"learning_rate": 9.979071767070932e-05,
"loss": 0.7427,
"step": 161
},
{
"epoch": 0.20964089291491428,
"grad_norm": 0.7866595983505249,
"learning_rate": 9.978693252459851e-05,
"loss": 0.8556,
"step": 162
},
{
"epoch": 0.2109349725008088,
"grad_norm": 0.9159708023071289,
"learning_rate": 9.978311352798374e-05,
"loss": 0.8101,
"step": 163
},
{
"epoch": 0.21222905208670334,
"grad_norm": 1.1350793838500977,
"learning_rate": 9.977926068346157e-05,
"loss": 0.9374,
"step": 164
},
{
"epoch": 0.21352313167259787,
"grad_norm": 1.0535932779312134,
"learning_rate": 9.977537399365159e-05,
"loss": 1.0238,
"step": 165
},
{
"epoch": 0.2148172112584924,
"grad_norm": 0.8717033267021179,
"learning_rate": 9.977145346119637e-05,
"loss": 1.0265,
"step": 166
},
{
"epoch": 0.21611129084438693,
"grad_norm": 0.8357003927230835,
"learning_rate": 9.976749908876152e-05,
"loss": 0.9016,
"step": 167
},
{
"epoch": 0.21740537043028146,
"grad_norm": 0.8369495868682861,
"learning_rate": 9.976351087903568e-05,
"loss": 0.8764,
"step": 168
},
{
"epoch": 0.218699450016176,
"grad_norm": 0.912352979183197,
"learning_rate": 9.97594888347304e-05,
"loss": 0.9078,
"step": 169
},
{
"epoch": 0.21999352960207053,
"grad_norm": 0.8475804328918457,
"learning_rate": 9.975543295858035e-05,
"loss": 0.8836,
"step": 170
},
{
"epoch": 0.22128760918796506,
"grad_norm": 0.8391397595405579,
"learning_rate": 9.97513432533431e-05,
"loss": 0.9003,
"step": 171
},
{
"epoch": 0.2225816887738596,
"grad_norm": 0.9666821360588074,
"learning_rate": 9.974721972179931e-05,
"loss": 0.9528,
"step": 172
},
{
"epoch": 0.22387576835975412,
"grad_norm": 0.9321691393852234,
"learning_rate": 9.974306236675259e-05,
"loss": 0.9575,
"step": 173
},
{
"epoch": 0.22516984794564865,
"grad_norm": 0.8022271990776062,
"learning_rate": 9.973887119102957e-05,
"loss": 0.8731,
"step": 174
},
{
"epoch": 0.22646392753154318,
"grad_norm": 1.1056872606277466,
"learning_rate": 9.973464619747983e-05,
"loss": 0.9925,
"step": 175
},
{
"epoch": 0.2277580071174377,
"grad_norm": 0.810420036315918,
"learning_rate": 9.9730387388976e-05,
"loss": 1.0073,
"step": 176
},
{
"epoch": 0.22905208670333224,
"grad_norm": 0.9536454677581787,
"learning_rate": 9.972609476841367e-05,
"loss": 0.9595,
"step": 177
},
{
"epoch": 0.2303461662892268,
"grad_norm": 0.8205066919326782,
"learning_rate": 9.972176833871142e-05,
"loss": 0.8146,
"step": 178
},
{
"epoch": 0.23164024587512133,
"grad_norm": 0.9716495275497437,
"learning_rate": 9.971740810281083e-05,
"loss": 1.0377,
"step": 179
},
{
"epoch": 0.23293432546101586,
"grad_norm": 0.828642725944519,
"learning_rate": 9.971301406367644e-05,
"loss": 0.8619,
"step": 180
},
{
"epoch": 0.2342284050469104,
"grad_norm": 0.6980477571487427,
"learning_rate": 9.970858622429579e-05,
"loss": 0.8271,
"step": 181
},
{
"epoch": 0.23552248463280492,
"grad_norm": 0.954387903213501,
"learning_rate": 9.970412458767943e-05,
"loss": 0.8465,
"step": 182
},
{
"epoch": 0.23681656421869945,
"grad_norm": 0.8425692915916443,
"learning_rate": 9.969962915686083e-05,
"loss": 0.8893,
"step": 183
},
{
"epoch": 0.23811064380459399,
"grad_norm": 0.8565071225166321,
"learning_rate": 9.969509993489647e-05,
"loss": 0.939,
"step": 184
},
{
"epoch": 0.23940472339048852,
"grad_norm": 0.8831691145896912,
"learning_rate": 9.969053692486583e-05,
"loss": 0.8907,
"step": 185
},
{
"epoch": 0.24069880297638305,
"grad_norm": 0.9661678075790405,
"learning_rate": 9.96859401298713e-05,
"loss": 0.9191,
"step": 186
},
{
"epoch": 0.24199288256227758,
"grad_norm": 0.8784729838371277,
"learning_rate": 9.968130955303828e-05,
"loss": 1.0393,
"step": 187
},
{
"epoch": 0.2432869621481721,
"grad_norm": 0.8830071091651917,
"learning_rate": 9.967664519751515e-05,
"loss": 0.9837,
"step": 188
},
{
"epoch": 0.24458104173406664,
"grad_norm": 0.862108588218689,
"learning_rate": 9.967194706647322e-05,
"loss": 0.7871,
"step": 189
},
{
"epoch": 0.24587512131996117,
"grad_norm": 1.0068063735961914,
"learning_rate": 9.966721516310682e-05,
"loss": 0.9526,
"step": 190
},
{
"epoch": 0.2471692009058557,
"grad_norm": 0.9828710556030273,
"learning_rate": 9.966244949063316e-05,
"loss": 0.8923,
"step": 191
},
{
"epoch": 0.24846328049175023,
"grad_norm": 1.0729883909225464,
"learning_rate": 9.965765005229248e-05,
"loss": 1.0115,
"step": 192
},
{
"epoch": 0.24975736007764476,
"grad_norm": 0.9844326972961426,
"learning_rate": 9.965281685134796e-05,
"loss": 0.9855,
"step": 193
},
{
"epoch": 0.2510514396635393,
"grad_norm": 1.1593172550201416,
"learning_rate": 9.96479498910857e-05,
"loss": 1.0912,
"step": 194
},
{
"epoch": 0.2523455192494338,
"grad_norm": 0.8835370540618896,
"learning_rate": 9.964304917481482e-05,
"loss": 0.9951,
"step": 195
}
],
"logging_steps": 1,
"max_steps": 3860,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.1799774848024576e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}