prxy5608's picture
Training in progress, step 200, checkpoint
fef500d verified
{
"best_metric": 1.1573420763015747,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.06404611320150508,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003202305660075254,
"grad_norm": 2.037818431854248,
"learning_rate": 1e-05,
"loss": 2.3457,
"step": 1
},
{
"epoch": 0.0003202305660075254,
"eval_loss": 2.4868569374084473,
"eval_runtime": 368.2649,
"eval_samples_per_second": 14.283,
"eval_steps_per_second": 3.571,
"step": 1
},
{
"epoch": 0.0006404611320150508,
"grad_norm": 2.0211055278778076,
"learning_rate": 2e-05,
"loss": 2.4039,
"step": 2
},
{
"epoch": 0.0009606916980225762,
"grad_norm": 1.9144755601882935,
"learning_rate": 3e-05,
"loss": 2.3608,
"step": 3
},
{
"epoch": 0.0012809222640301017,
"grad_norm": 2.0654098987579346,
"learning_rate": 4e-05,
"loss": 2.4473,
"step": 4
},
{
"epoch": 0.0016011528300376272,
"grad_norm": 2.0989089012145996,
"learning_rate": 5e-05,
"loss": 2.3753,
"step": 5
},
{
"epoch": 0.0019213833960451524,
"grad_norm": 1.925842046737671,
"learning_rate": 6e-05,
"loss": 2.026,
"step": 6
},
{
"epoch": 0.002241613962052678,
"grad_norm": 1.665363073348999,
"learning_rate": 7e-05,
"loss": 1.8335,
"step": 7
},
{
"epoch": 0.0025618445280602034,
"grad_norm": 1.6260919570922852,
"learning_rate": 8e-05,
"loss": 1.8504,
"step": 8
},
{
"epoch": 0.002882075094067729,
"grad_norm": 1.2980161905288696,
"learning_rate": 9e-05,
"loss": 1.4722,
"step": 9
},
{
"epoch": 0.0032023056600752543,
"grad_norm": 1.4088715314865112,
"learning_rate": 0.0001,
"loss": 1.5324,
"step": 10
},
{
"epoch": 0.0035225362260827794,
"grad_norm": 1.7647688388824463,
"learning_rate": 9.999316524962345e-05,
"loss": 1.3009,
"step": 11
},
{
"epoch": 0.003842766792090305,
"grad_norm": 1.3143683671951294,
"learning_rate": 9.997266286704631e-05,
"loss": 1.4116,
"step": 12
},
{
"epoch": 0.004162997358097831,
"grad_norm": 1.2870858907699585,
"learning_rate": 9.993849845741524e-05,
"loss": 1.5258,
"step": 13
},
{
"epoch": 0.004483227924105356,
"grad_norm": 1.3172638416290283,
"learning_rate": 9.989068136093873e-05,
"loss": 1.3318,
"step": 14
},
{
"epoch": 0.004803458490112881,
"grad_norm": 1.0657457113265991,
"learning_rate": 9.98292246503335e-05,
"loss": 1.2955,
"step": 15
},
{
"epoch": 0.005123689056120407,
"grad_norm": 0.987359344959259,
"learning_rate": 9.975414512725057e-05,
"loss": 1.2624,
"step": 16
},
{
"epoch": 0.005443919622127932,
"grad_norm": 0.9995255470275879,
"learning_rate": 9.966546331768191e-05,
"loss": 1.1072,
"step": 17
},
{
"epoch": 0.005764150188135458,
"grad_norm": 1.0182195901870728,
"learning_rate": 9.956320346634876e-05,
"loss": 1.2935,
"step": 18
},
{
"epoch": 0.006084380754142983,
"grad_norm": 1.1560221910476685,
"learning_rate": 9.944739353007344e-05,
"loss": 1.2833,
"step": 19
},
{
"epoch": 0.006404611320150509,
"grad_norm": 1.0936617851257324,
"learning_rate": 9.931806517013612e-05,
"loss": 1.3485,
"step": 20
},
{
"epoch": 0.006724841886158034,
"grad_norm": 0.8886420130729675,
"learning_rate": 9.917525374361912e-05,
"loss": 1.1023,
"step": 21
},
{
"epoch": 0.007045072452165559,
"grad_norm": 1.1434640884399414,
"learning_rate": 9.901899829374047e-05,
"loss": 1.1715,
"step": 22
},
{
"epoch": 0.007365303018173085,
"grad_norm": 1.0264716148376465,
"learning_rate": 9.884934153917997e-05,
"loss": 1.1499,
"step": 23
},
{
"epoch": 0.00768553358418061,
"grad_norm": 0.8777170777320862,
"learning_rate": 9.86663298624003e-05,
"loss": 1.0644,
"step": 24
},
{
"epoch": 0.008005764150188135,
"grad_norm": 1.0160694122314453,
"learning_rate": 9.847001329696653e-05,
"loss": 1.2235,
"step": 25
},
{
"epoch": 0.008325994716195662,
"grad_norm": 1.1108500957489014,
"learning_rate": 9.826044551386744e-05,
"loss": 1.1453,
"step": 26
},
{
"epoch": 0.008646225282203187,
"grad_norm": 1.118847370147705,
"learning_rate": 9.803768380684242e-05,
"loss": 1.2656,
"step": 27
},
{
"epoch": 0.008966455848210712,
"grad_norm": 1.6578736305236816,
"learning_rate": 9.780178907671789e-05,
"loss": 1.084,
"step": 28
},
{
"epoch": 0.009286686414218237,
"grad_norm": 1.0223703384399414,
"learning_rate": 9.755282581475769e-05,
"loss": 1.1693,
"step": 29
},
{
"epoch": 0.009606916980225762,
"grad_norm": 1.0773693323135376,
"learning_rate": 9.729086208503174e-05,
"loss": 1.1995,
"step": 30
},
{
"epoch": 0.009927147546233289,
"grad_norm": 1.1043092012405396,
"learning_rate": 9.701596950580806e-05,
"loss": 0.9622,
"step": 31
},
{
"epoch": 0.010247378112240814,
"grad_norm": 0.9272341132164001,
"learning_rate": 9.672822322997305e-05,
"loss": 1.1182,
"step": 32
},
{
"epoch": 0.010567608678248339,
"grad_norm": 0.9050891399383545,
"learning_rate": 9.642770192448536e-05,
"loss": 1.2091,
"step": 33
},
{
"epoch": 0.010887839244255864,
"grad_norm": 1.0126290321350098,
"learning_rate": 9.611448774886924e-05,
"loss": 1.2509,
"step": 34
},
{
"epoch": 0.01120806981026339,
"grad_norm": 1.064522624015808,
"learning_rate": 9.578866633275288e-05,
"loss": 1.2335,
"step": 35
},
{
"epoch": 0.011528300376270915,
"grad_norm": 0.9452833533287048,
"learning_rate": 9.545032675245813e-05,
"loss": 1.1477,
"step": 36
},
{
"epoch": 0.01184853094227844,
"grad_norm": 0.9947261214256287,
"learning_rate": 9.509956150664796e-05,
"loss": 1.2362,
"step": 37
},
{
"epoch": 0.012168761508285966,
"grad_norm": 1.0642095804214478,
"learning_rate": 9.473646649103818e-05,
"loss": 1.1538,
"step": 38
},
{
"epoch": 0.01248899207429349,
"grad_norm": 0.8688209056854248,
"learning_rate": 9.43611409721806e-05,
"loss": 1.1042,
"step": 39
},
{
"epoch": 0.012809222640301017,
"grad_norm": 0.8616880178451538,
"learning_rate": 9.397368756032445e-05,
"loss": 1.0863,
"step": 40
},
{
"epoch": 0.013129453206308542,
"grad_norm": 0.9572056531906128,
"learning_rate": 9.357421218136386e-05,
"loss": 1.1169,
"step": 41
},
{
"epoch": 0.013449683772316067,
"grad_norm": 1.0412248373031616,
"learning_rate": 9.316282404787871e-05,
"loss": 1.2042,
"step": 42
},
{
"epoch": 0.013769914338323593,
"grad_norm": 0.9184888601303101,
"learning_rate": 9.273963562927695e-05,
"loss": 1.1551,
"step": 43
},
{
"epoch": 0.014090144904331118,
"grad_norm": 1.3677374124526978,
"learning_rate": 9.230476262104677e-05,
"loss": 1.3207,
"step": 44
},
{
"epoch": 0.014410375470338644,
"grad_norm": 0.890541136264801,
"learning_rate": 9.185832391312644e-05,
"loss": 1.1999,
"step": 45
},
{
"epoch": 0.01473060603634617,
"grad_norm": 1.0052913427352905,
"learning_rate": 9.140044155740101e-05,
"loss": 1.2657,
"step": 46
},
{
"epoch": 0.015050836602353694,
"grad_norm": 1.087723970413208,
"learning_rate": 9.093124073433463e-05,
"loss": 1.1891,
"step": 47
},
{
"epoch": 0.01537106716836122,
"grad_norm": 1.0031085014343262,
"learning_rate": 9.045084971874738e-05,
"loss": 1.0996,
"step": 48
},
{
"epoch": 0.015691297734368746,
"grad_norm": 1.3595257997512817,
"learning_rate": 8.995939984474624e-05,
"loss": 1.3953,
"step": 49
},
{
"epoch": 0.01601152830037627,
"grad_norm": 2.4625601768493652,
"learning_rate": 8.945702546981969e-05,
"loss": 1.6946,
"step": 50
},
{
"epoch": 0.01601152830037627,
"eval_loss": 1.2126585245132446,
"eval_runtime": 370.9286,
"eval_samples_per_second": 14.181,
"eval_steps_per_second": 3.545,
"step": 50
},
{
"epoch": 0.016331758866383796,
"grad_norm": 1.5148155689239502,
"learning_rate": 8.894386393810563e-05,
"loss": 1.193,
"step": 51
},
{
"epoch": 0.016651989432391323,
"grad_norm": 1.7631820440292358,
"learning_rate": 8.842005554284296e-05,
"loss": 1.1393,
"step": 52
},
{
"epoch": 0.016972219998398846,
"grad_norm": 0.8869484066963196,
"learning_rate": 8.788574348801675e-05,
"loss": 1.3388,
"step": 53
},
{
"epoch": 0.017292450564406373,
"grad_norm": 0.9143075346946716,
"learning_rate": 8.73410738492077e-05,
"loss": 1.2224,
"step": 54
},
{
"epoch": 0.017612681130413897,
"grad_norm": 1.7052335739135742,
"learning_rate": 8.678619553365659e-05,
"loss": 1.3929,
"step": 55
},
{
"epoch": 0.017932911696421423,
"grad_norm": 1.6410431861877441,
"learning_rate": 8.622126023955446e-05,
"loss": 1.341,
"step": 56
},
{
"epoch": 0.01825314226242895,
"grad_norm": 1.2337192296981812,
"learning_rate": 8.564642241456986e-05,
"loss": 1.2219,
"step": 57
},
{
"epoch": 0.018573372828436473,
"grad_norm": 0.8659921288490295,
"learning_rate": 8.506183921362443e-05,
"loss": 1.0619,
"step": 58
},
{
"epoch": 0.018893603394444,
"grad_norm": 0.9054717421531677,
"learning_rate": 8.44676704559283e-05,
"loss": 1.0988,
"step": 59
},
{
"epoch": 0.019213833960451523,
"grad_norm": 1.1715950965881348,
"learning_rate": 8.386407858128706e-05,
"loss": 1.3152,
"step": 60
},
{
"epoch": 0.01953406452645905,
"grad_norm": 0.9733151197433472,
"learning_rate": 8.32512286056924e-05,
"loss": 1.23,
"step": 61
},
{
"epoch": 0.019854295092466577,
"grad_norm": 0.7634916305541992,
"learning_rate": 8.262928807620843e-05,
"loss": 1.1713,
"step": 62
},
{
"epoch": 0.0201745256584741,
"grad_norm": 0.6630211472511292,
"learning_rate": 8.199842702516583e-05,
"loss": 1.0261,
"step": 63
},
{
"epoch": 0.020494756224481627,
"grad_norm": 0.7927376627922058,
"learning_rate": 8.135881792367686e-05,
"loss": 1.1327,
"step": 64
},
{
"epoch": 0.020814986790489154,
"grad_norm": 0.8792087435722351,
"learning_rate": 8.07106356344834e-05,
"loss": 1.0073,
"step": 65
},
{
"epoch": 0.021135217356496677,
"grad_norm": 0.9809986352920532,
"learning_rate": 8.005405736415126e-05,
"loss": 1.2827,
"step": 66
},
{
"epoch": 0.021455447922504204,
"grad_norm": 0.8197011351585388,
"learning_rate": 7.938926261462366e-05,
"loss": 1.2597,
"step": 67
},
{
"epoch": 0.021775678488511727,
"grad_norm": 0.8156796097755432,
"learning_rate": 7.871643313414718e-05,
"loss": 1.2565,
"step": 68
},
{
"epoch": 0.022095909054519254,
"grad_norm": 0.7012443542480469,
"learning_rate": 7.803575286758364e-05,
"loss": 1.1398,
"step": 69
},
{
"epoch": 0.02241613962052678,
"grad_norm": 0.8510885238647461,
"learning_rate": 7.734740790612136e-05,
"loss": 1.1023,
"step": 70
},
{
"epoch": 0.022736370186534304,
"grad_norm": 1.1383626461029053,
"learning_rate": 7.66515864363997e-05,
"loss": 1.1758,
"step": 71
},
{
"epoch": 0.02305660075254183,
"grad_norm": 1.0016313791275024,
"learning_rate": 7.594847868906076e-05,
"loss": 1.0247,
"step": 72
},
{
"epoch": 0.023376831318549354,
"grad_norm": 0.8533788323402405,
"learning_rate": 7.52382768867422e-05,
"loss": 1.4455,
"step": 73
},
{
"epoch": 0.02369706188455688,
"grad_norm": 0.6485158205032349,
"learning_rate": 7.452117519152542e-05,
"loss": 1.0059,
"step": 74
},
{
"epoch": 0.024017292450564408,
"grad_norm": 1.0234816074371338,
"learning_rate": 7.379736965185368e-05,
"loss": 1.125,
"step": 75
},
{
"epoch": 0.02433752301657193,
"grad_norm": 0.9388783574104309,
"learning_rate": 7.30670581489344e-05,
"loss": 1.2171,
"step": 76
},
{
"epoch": 0.024657753582579458,
"grad_norm": 0.8452920317649841,
"learning_rate": 7.233044034264034e-05,
"loss": 0.9428,
"step": 77
},
{
"epoch": 0.02497798414858698,
"grad_norm": 0.7855011820793152,
"learning_rate": 7.158771761692464e-05,
"loss": 1.1068,
"step": 78
},
{
"epoch": 0.025298214714594508,
"grad_norm": 0.8020321130752563,
"learning_rate": 7.083909302476453e-05,
"loss": 1.134,
"step": 79
},
{
"epoch": 0.025618445280602035,
"grad_norm": 0.7620186805725098,
"learning_rate": 7.008477123264848e-05,
"loss": 1.1103,
"step": 80
},
{
"epoch": 0.025938675846609558,
"grad_norm": 0.8810065984725952,
"learning_rate": 6.932495846462261e-05,
"loss": 1.0261,
"step": 81
},
{
"epoch": 0.026258906412617085,
"grad_norm": 0.7425292730331421,
"learning_rate": 6.855986244591104e-05,
"loss": 1.1013,
"step": 82
},
{
"epoch": 0.026579136978624608,
"grad_norm": 0.8424925208091736,
"learning_rate": 6.778969234612584e-05,
"loss": 1.3318,
"step": 83
},
{
"epoch": 0.026899367544632135,
"grad_norm": 0.8435525894165039,
"learning_rate": 6.701465872208216e-05,
"loss": 1.3248,
"step": 84
},
{
"epoch": 0.02721959811063966,
"grad_norm": 0.819072961807251,
"learning_rate": 6.623497346023418e-05,
"loss": 1.2424,
"step": 85
},
{
"epoch": 0.027539828676647185,
"grad_norm": 0.8948582410812378,
"learning_rate": 6.545084971874738e-05,
"loss": 1.1825,
"step": 86
},
{
"epoch": 0.027860059242654712,
"grad_norm": 0.732230007648468,
"learning_rate": 6.466250186922325e-05,
"loss": 1.2565,
"step": 87
},
{
"epoch": 0.028180289808662235,
"grad_norm": 0.7822135090827942,
"learning_rate": 6.387014543809223e-05,
"loss": 1.1806,
"step": 88
},
{
"epoch": 0.028500520374669762,
"grad_norm": 0.9079301953315735,
"learning_rate": 6.307399704769099e-05,
"loss": 1.2408,
"step": 89
},
{
"epoch": 0.02882075094067729,
"grad_norm": 0.7984238862991333,
"learning_rate": 6.227427435703997e-05,
"loss": 1.2299,
"step": 90
},
{
"epoch": 0.029140981506684812,
"grad_norm": 0.8512197136878967,
"learning_rate": 6.147119600233758e-05,
"loss": 1.2893,
"step": 91
},
{
"epoch": 0.02946121207269234,
"grad_norm": 0.7080538868904114,
"learning_rate": 6.066498153718735e-05,
"loss": 1.0819,
"step": 92
},
{
"epoch": 0.029781442638699866,
"grad_norm": 0.7597021460533142,
"learning_rate": 5.985585137257401e-05,
"loss": 1.1308,
"step": 93
},
{
"epoch": 0.03010167320470739,
"grad_norm": 0.8458277583122253,
"learning_rate": 5.90440267166055e-05,
"loss": 1.2723,
"step": 94
},
{
"epoch": 0.030421903770714916,
"grad_norm": 0.7987385988235474,
"learning_rate": 5.8229729514036705e-05,
"loss": 1.1156,
"step": 95
},
{
"epoch": 0.03074213433672244,
"grad_norm": 0.9873958826065063,
"learning_rate": 5.74131823855921e-05,
"loss": 1.4007,
"step": 96
},
{
"epoch": 0.031062364902729966,
"grad_norm": 0.9611806273460388,
"learning_rate": 5.6594608567103456e-05,
"loss": 1.2421,
"step": 97
},
{
"epoch": 0.03138259546873749,
"grad_norm": 1.002394199371338,
"learning_rate": 5.577423184847932e-05,
"loss": 1.365,
"step": 98
},
{
"epoch": 0.031702826034745016,
"grad_norm": 1.3655023574829102,
"learning_rate": 5.495227651252315e-05,
"loss": 1.3574,
"step": 99
},
{
"epoch": 0.03202305660075254,
"grad_norm": 1.6735059022903442,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.4426,
"step": 100
},
{
"epoch": 0.03202305660075254,
"eval_loss": 1.1776365041732788,
"eval_runtime": 371.043,
"eval_samples_per_second": 14.176,
"eval_steps_per_second": 3.544,
"step": 100
},
{
"epoch": 0.03234328716676007,
"grad_norm": 0.8301069736480713,
"learning_rate": 5.330452921628497e-05,
"loss": 1.2911,
"step": 101
},
{
"epoch": 0.03266351773276759,
"grad_norm": 0.7628312706947327,
"learning_rate": 5.247918773366112e-05,
"loss": 1.1607,
"step": 102
},
{
"epoch": 0.032983748298775116,
"grad_norm": 0.7576774954795837,
"learning_rate": 5.165316846586541e-05,
"loss": 1.1612,
"step": 103
},
{
"epoch": 0.033303978864782646,
"grad_norm": 0.7954198122024536,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.139,
"step": 104
},
{
"epoch": 0.03362420943079017,
"grad_norm": 0.806863009929657,
"learning_rate": 5e-05,
"loss": 1.2543,
"step": 105
},
{
"epoch": 0.03394443999679769,
"grad_norm": 0.8092947006225586,
"learning_rate": 4.917330276168208e-05,
"loss": 1.2492,
"step": 106
},
{
"epoch": 0.03426467056280522,
"grad_norm": 0.741668164730072,
"learning_rate": 4.834683153413459e-05,
"loss": 1.0838,
"step": 107
},
{
"epoch": 0.034584901128812746,
"grad_norm": 0.7461872100830078,
"learning_rate": 4.7520812266338885e-05,
"loss": 1.1515,
"step": 108
},
{
"epoch": 0.03490513169482027,
"grad_norm": 0.7427971363067627,
"learning_rate": 4.669547078371504e-05,
"loss": 1.0883,
"step": 109
},
{
"epoch": 0.03522536226082779,
"grad_norm": 1.1675689220428467,
"learning_rate": 4.5871032726383386e-05,
"loss": 1.3831,
"step": 110
},
{
"epoch": 0.03554559282683532,
"grad_norm": 0.7495681643486023,
"learning_rate": 4.504772348747687e-05,
"loss": 1.1403,
"step": 111
},
{
"epoch": 0.03586582339284285,
"grad_norm": 0.7669549584388733,
"learning_rate": 4.4225768151520694e-05,
"loss": 1.2201,
"step": 112
},
{
"epoch": 0.03618605395885037,
"grad_norm": 0.7834761142730713,
"learning_rate": 4.3405391432896555e-05,
"loss": 1.1919,
"step": 113
},
{
"epoch": 0.0365062845248579,
"grad_norm": 0.7629067301750183,
"learning_rate": 4.2586817614407895e-05,
"loss": 1.2765,
"step": 114
},
{
"epoch": 0.03682651509086542,
"grad_norm": 0.7569834589958191,
"learning_rate": 4.17702704859633e-05,
"loss": 1.2426,
"step": 115
},
{
"epoch": 0.03714674565687295,
"grad_norm": 0.8269571661949158,
"learning_rate": 4.095597328339452e-05,
"loss": 1.2903,
"step": 116
},
{
"epoch": 0.03746697622288048,
"grad_norm": 0.9522500038146973,
"learning_rate": 4.0144148627425993e-05,
"loss": 1.1544,
"step": 117
},
{
"epoch": 0.037787206788888,
"grad_norm": 0.6504029035568237,
"learning_rate": 3.933501846281267e-05,
"loss": 1.1392,
"step": 118
},
{
"epoch": 0.038107437354895524,
"grad_norm": 0.9880499243736267,
"learning_rate": 3.852880399766243e-05,
"loss": 1.1778,
"step": 119
},
{
"epoch": 0.03842766792090305,
"grad_norm": 0.7493283152580261,
"learning_rate": 3.772572564296005e-05,
"loss": 1.1654,
"step": 120
},
{
"epoch": 0.03874789848691058,
"grad_norm": 0.6976988315582275,
"learning_rate": 3.6926002952309016e-05,
"loss": 1.1101,
"step": 121
},
{
"epoch": 0.0390681290529181,
"grad_norm": 0.8585397005081177,
"learning_rate": 3.612985456190778e-05,
"loss": 1.1585,
"step": 122
},
{
"epoch": 0.039388359618925624,
"grad_norm": 0.8890944719314575,
"learning_rate": 3.533749813077677e-05,
"loss": 1.2126,
"step": 123
},
{
"epoch": 0.039708590184933154,
"grad_norm": 0.7071130871772766,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.079,
"step": 124
},
{
"epoch": 0.04002882075094068,
"grad_norm": 0.7253214120864868,
"learning_rate": 3.3765026539765834e-05,
"loss": 1.1399,
"step": 125
},
{
"epoch": 0.0403490513169482,
"grad_norm": 0.7146914601325989,
"learning_rate": 3.298534127791785e-05,
"loss": 0.992,
"step": 126
},
{
"epoch": 0.04066928188295573,
"grad_norm": 0.7379949688911438,
"learning_rate": 3.221030765387417e-05,
"loss": 1.2058,
"step": 127
},
{
"epoch": 0.040989512448963254,
"grad_norm": 0.710760772228241,
"learning_rate": 3.144013755408895e-05,
"loss": 1.0109,
"step": 128
},
{
"epoch": 0.04130974301497078,
"grad_norm": 0.7559716701507568,
"learning_rate": 3.0675041535377405e-05,
"loss": 1.1112,
"step": 129
},
{
"epoch": 0.04162997358097831,
"grad_norm": 0.6374360918998718,
"learning_rate": 2.991522876735154e-05,
"loss": 0.9809,
"step": 130
},
{
"epoch": 0.04195020414698583,
"grad_norm": 0.7205137610435486,
"learning_rate": 2.916090697523549e-05,
"loss": 0.9838,
"step": 131
},
{
"epoch": 0.042270434712993354,
"grad_norm": 0.8026019334793091,
"learning_rate": 2.8412282383075363e-05,
"loss": 1.2029,
"step": 132
},
{
"epoch": 0.04259066527900088,
"grad_norm": 0.7249667644500732,
"learning_rate": 2.766955965735968e-05,
"loss": 1.1735,
"step": 133
},
{
"epoch": 0.04291089584500841,
"grad_norm": 0.7686251997947693,
"learning_rate": 2.693294185106562e-05,
"loss": 0.9731,
"step": 134
},
{
"epoch": 0.04323112641101593,
"grad_norm": 0.7962585091590881,
"learning_rate": 2.6202630348146324e-05,
"loss": 1.1843,
"step": 135
},
{
"epoch": 0.043551356977023455,
"grad_norm": 0.7655040621757507,
"learning_rate": 2.547882480847461e-05,
"loss": 1.1567,
"step": 136
},
{
"epoch": 0.043871587543030985,
"grad_norm": 0.7549670338630676,
"learning_rate": 2.476172311325783e-05,
"loss": 1.1085,
"step": 137
},
{
"epoch": 0.04419181810903851,
"grad_norm": 0.7712312936782837,
"learning_rate": 2.405152131093926e-05,
"loss": 0.9373,
"step": 138
},
{
"epoch": 0.04451204867504603,
"grad_norm": 0.7797657251358032,
"learning_rate": 2.3348413563600325e-05,
"loss": 1.015,
"step": 139
},
{
"epoch": 0.04483227924105356,
"grad_norm": 0.706188976764679,
"learning_rate": 2.2652592093878666e-05,
"loss": 1.0713,
"step": 140
},
{
"epoch": 0.045152509807061085,
"grad_norm": 0.7762495279312134,
"learning_rate": 2.196424713241637e-05,
"loss": 1.2755,
"step": 141
},
{
"epoch": 0.04547274037306861,
"grad_norm": 0.8034321069717407,
"learning_rate": 2.128356686585282e-05,
"loss": 1.1598,
"step": 142
},
{
"epoch": 0.04579297093907613,
"grad_norm": 0.8696984648704529,
"learning_rate": 2.061073738537635e-05,
"loss": 1.1472,
"step": 143
},
{
"epoch": 0.04611320150508366,
"grad_norm": 0.8381091952323914,
"learning_rate": 1.9945942635848748e-05,
"loss": 1.149,
"step": 144
},
{
"epoch": 0.046433432071091185,
"grad_norm": 0.8387601971626282,
"learning_rate": 1.928936436551661e-05,
"loss": 1.2136,
"step": 145
},
{
"epoch": 0.04675366263709871,
"grad_norm": 0.8009840250015259,
"learning_rate": 1.8641182076323148e-05,
"loss": 1.0758,
"step": 146
},
{
"epoch": 0.04707389320310624,
"grad_norm": 0.8337766528129578,
"learning_rate": 1.800157297483417e-05,
"loss": 1.1318,
"step": 147
},
{
"epoch": 0.04739412376911376,
"grad_norm": 1.1293323040008545,
"learning_rate": 1.7370711923791567e-05,
"loss": 1.48,
"step": 148
},
{
"epoch": 0.047714354335121285,
"grad_norm": 1.2191877365112305,
"learning_rate": 1.6748771394307585e-05,
"loss": 1.3757,
"step": 149
},
{
"epoch": 0.048034584901128816,
"grad_norm": 1.564333200454712,
"learning_rate": 1.6135921418712956e-05,
"loss": 1.498,
"step": 150
},
{
"epoch": 0.048034584901128816,
"eval_loss": 1.159428596496582,
"eval_runtime": 371.1526,
"eval_samples_per_second": 14.172,
"eval_steps_per_second": 3.543,
"step": 150
},
{
"epoch": 0.04835481546713634,
"grad_norm": 0.779155969619751,
"learning_rate": 1.553232954407171e-05,
"loss": 1.2244,
"step": 151
},
{
"epoch": 0.04867504603314386,
"grad_norm": 0.6948367357254028,
"learning_rate": 1.4938160786375572e-05,
"loss": 1.1343,
"step": 152
},
{
"epoch": 0.048995276599151386,
"grad_norm": 0.7734284400939941,
"learning_rate": 1.435357758543015e-05,
"loss": 1.1726,
"step": 153
},
{
"epoch": 0.049315507165158916,
"grad_norm": 0.6823763251304626,
"learning_rate": 1.3778739760445552e-05,
"loss": 1.133,
"step": 154
},
{
"epoch": 0.04963573773116644,
"grad_norm": 0.8386368155479431,
"learning_rate": 1.3213804466343421e-05,
"loss": 1.2306,
"step": 155
},
{
"epoch": 0.04995596829717396,
"grad_norm": 0.7109575867652893,
"learning_rate": 1.2658926150792322e-05,
"loss": 1.0013,
"step": 156
},
{
"epoch": 0.05027619886318149,
"grad_norm": 0.6848258376121521,
"learning_rate": 1.2114256511983274e-05,
"loss": 1.1462,
"step": 157
},
{
"epoch": 0.050596429429189016,
"grad_norm": 0.7048079967498779,
"learning_rate": 1.157994445715706e-05,
"loss": 1.0259,
"step": 158
},
{
"epoch": 0.05091665999519654,
"grad_norm": 0.6317865252494812,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.9677,
"step": 159
},
{
"epoch": 0.05123689056120407,
"grad_norm": 0.7606520056724548,
"learning_rate": 1.0542974530180327e-05,
"loss": 1.2544,
"step": 160
},
{
"epoch": 0.05155712112721159,
"grad_norm": 0.7171646952629089,
"learning_rate": 1.0040600155253765e-05,
"loss": 1.1695,
"step": 161
},
{
"epoch": 0.051877351693219116,
"grad_norm": 0.7308404445648193,
"learning_rate": 9.549150281252633e-06,
"loss": 1.0628,
"step": 162
},
{
"epoch": 0.052197582259226646,
"grad_norm": 0.7672210931777954,
"learning_rate": 9.068759265665384e-06,
"loss": 1.2617,
"step": 163
},
{
"epoch": 0.05251781282523417,
"grad_norm": 0.7743724584579468,
"learning_rate": 8.599558442598998e-06,
"loss": 1.2205,
"step": 164
},
{
"epoch": 0.05283804339124169,
"grad_norm": 0.6678279638290405,
"learning_rate": 8.141676086873572e-06,
"loss": 1.0766,
"step": 165
},
{
"epoch": 0.053158273957249216,
"grad_norm": 0.73908931016922,
"learning_rate": 7.695237378953223e-06,
"loss": 1.0539,
"step": 166
},
{
"epoch": 0.05347850452325675,
"grad_norm": 0.6308887004852295,
"learning_rate": 7.260364370723044e-06,
"loss": 0.9857,
"step": 167
},
{
"epoch": 0.05379873508926427,
"grad_norm": 0.8252634406089783,
"learning_rate": 6.837175952121306e-06,
"loss": 1.0783,
"step": 168
},
{
"epoch": 0.05411896565527179,
"grad_norm": 0.6939792633056641,
"learning_rate": 6.425787818636131e-06,
"loss": 1.0681,
"step": 169
},
{
"epoch": 0.05443919622127932,
"grad_norm": 0.7173256874084473,
"learning_rate": 6.026312439675552e-06,
"loss": 1.2131,
"step": 170
},
{
"epoch": 0.05475942678728685,
"grad_norm": 0.7093914151191711,
"learning_rate": 5.6388590278194096e-06,
"loss": 1.052,
"step": 171
},
{
"epoch": 0.05507965735329437,
"grad_norm": 0.696561336517334,
"learning_rate": 5.263533508961827e-06,
"loss": 1.1234,
"step": 172
},
{
"epoch": 0.0553998879193019,
"grad_norm": 0.7869912981987,
"learning_rate": 4.900438493352055e-06,
"loss": 1.1428,
"step": 173
},
{
"epoch": 0.055720118485309424,
"grad_norm": 0.7008021473884583,
"learning_rate": 4.549673247541875e-06,
"loss": 1.0378,
"step": 174
},
{
"epoch": 0.05604034905131695,
"grad_norm": 0.7216114401817322,
"learning_rate": 4.2113336672471245e-06,
"loss": 1.1804,
"step": 175
},
{
"epoch": 0.05636057961732447,
"grad_norm": 0.8145813941955566,
"learning_rate": 3.885512251130763e-06,
"loss": 1.2522,
"step": 176
},
{
"epoch": 0.056680810183332,
"grad_norm": 0.695566713809967,
"learning_rate": 3.5722980755146517e-06,
"loss": 1.0586,
"step": 177
},
{
"epoch": 0.057001040749339524,
"grad_norm": 0.6784931421279907,
"learning_rate": 3.271776770026963e-06,
"loss": 1.0516,
"step": 178
},
{
"epoch": 0.05732127131534705,
"grad_norm": 0.7495012283325195,
"learning_rate": 2.9840304941919415e-06,
"loss": 1.2887,
"step": 179
},
{
"epoch": 0.05764150188135458,
"grad_norm": 0.7123779058456421,
"learning_rate": 2.7091379149682685e-06,
"loss": 1.1573,
"step": 180
},
{
"epoch": 0.0579617324473621,
"grad_norm": 0.8312051892280579,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.3178,
"step": 181
},
{
"epoch": 0.058281963013369624,
"grad_norm": 0.7549231052398682,
"learning_rate": 2.1982109232821178e-06,
"loss": 1.1382,
"step": 182
},
{
"epoch": 0.058602193579377154,
"grad_norm": 0.7890342473983765,
"learning_rate": 1.962316193157593e-06,
"loss": 1.2743,
"step": 183
},
{
"epoch": 0.05892242414538468,
"grad_norm": 0.7165307998657227,
"learning_rate": 1.7395544861325718e-06,
"loss": 1.0504,
"step": 184
},
{
"epoch": 0.0592426547113922,
"grad_norm": 0.7973076105117798,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.9773,
"step": 185
},
{
"epoch": 0.05956288527739973,
"grad_norm": 0.6774954795837402,
"learning_rate": 1.333670137599713e-06,
"loss": 1.05,
"step": 186
},
{
"epoch": 0.059883115843407254,
"grad_norm": 0.7895904183387756,
"learning_rate": 1.1506584608200367e-06,
"loss": 1.1177,
"step": 187
},
{
"epoch": 0.06020334640941478,
"grad_norm": 0.7271930575370789,
"learning_rate": 9.810017062595322e-07,
"loss": 1.0969,
"step": 188
},
{
"epoch": 0.0605235769754223,
"grad_norm": 0.7491040229797363,
"learning_rate": 8.247462563808817e-07,
"loss": 1.1477,
"step": 189
},
{
"epoch": 0.06084380754142983,
"grad_norm": 0.7956143021583557,
"learning_rate": 6.819348298638839e-07,
"loss": 1.3276,
"step": 190
},
{
"epoch": 0.061164038107437355,
"grad_norm": 0.7645721435546875,
"learning_rate": 5.526064699265753e-07,
"loss": 1.2347,
"step": 191
},
{
"epoch": 0.06148426867344488,
"grad_norm": 0.8326579928398132,
"learning_rate": 4.367965336512403e-07,
"loss": 1.2441,
"step": 192
},
{
"epoch": 0.06180449923945241,
"grad_norm": 0.8197948336601257,
"learning_rate": 3.3453668231809286e-07,
"loss": 1.2503,
"step": 193
},
{
"epoch": 0.06212472980545993,
"grad_norm": 0.7467843294143677,
"learning_rate": 2.458548727494292e-07,
"loss": 1.0843,
"step": 194
},
{
"epoch": 0.062444960371467455,
"grad_norm": 0.7013464570045471,
"learning_rate": 1.7077534966650766e-07,
"loss": 1.0437,
"step": 195
},
{
"epoch": 0.06276519093747499,
"grad_norm": 0.8511938452720642,
"learning_rate": 1.0931863906127327e-07,
"loss": 1.214,
"step": 196
},
{
"epoch": 0.06308542150348251,
"grad_norm": 0.7980570197105408,
"learning_rate": 6.150154258476315e-08,
"loss": 1.1664,
"step": 197
},
{
"epoch": 0.06340565206949003,
"grad_norm": 0.9157402515411377,
"learning_rate": 2.7337132953697554e-08,
"loss": 1.1482,
"step": 198
},
{
"epoch": 0.06372588263549755,
"grad_norm": 0.8487852215766907,
"learning_rate": 6.834750376549792e-09,
"loss": 0.9334,
"step": 199
},
{
"epoch": 0.06404611320150508,
"grad_norm": 1.3456616401672363,
"learning_rate": 0.0,
"loss": 1.525,
"step": 200
},
{
"epoch": 0.06404611320150508,
"eval_loss": 1.1573420763015747,
"eval_runtime": 371.0556,
"eval_samples_per_second": 14.176,
"eval_steps_per_second": 3.544,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.660991548522496e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}