fats-fme's picture
Training in progress, step 166, checkpoint
0fffa4d verified
raw
history blame
29.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5001883239171375,
"eval_steps": 83,
"global_step": 166,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030131826741996233,
"grad_norm": 7.092586040496826,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.9681,
"step": 1
},
{
"epoch": 0.0030131826741996233,
"eval_loss": NaN,
"eval_runtime": 92.9755,
"eval_samples_per_second": 6.012,
"eval_steps_per_second": 1.506,
"step": 1
},
{
"epoch": 0.006026365348399247,
"grad_norm": 6.170314788818359,
"learning_rate": 4.000000000000001e-06,
"loss": 3.029,
"step": 2
},
{
"epoch": 0.00903954802259887,
"grad_norm": 7.000847339630127,
"learning_rate": 6e-06,
"loss": 3.5581,
"step": 3
},
{
"epoch": 0.012052730696798493,
"grad_norm": 7.161468029022217,
"learning_rate": 8.000000000000001e-06,
"loss": 3.5814,
"step": 4
},
{
"epoch": 0.015065913370998116,
"grad_norm": 7.698644638061523,
"learning_rate": 1e-05,
"loss": 3.8585,
"step": 5
},
{
"epoch": 0.01807909604519774,
"grad_norm": 8.074420928955078,
"learning_rate": 1.2e-05,
"loss": 4.001,
"step": 6
},
{
"epoch": 0.021092278719397364,
"grad_norm": 7.968758583068848,
"learning_rate": 1.4000000000000001e-05,
"loss": 4.1068,
"step": 7
},
{
"epoch": 0.024105461393596987,
"grad_norm": 8.725764274597168,
"learning_rate": 1.6000000000000003e-05,
"loss": 3.6916,
"step": 8
},
{
"epoch": 0.02711864406779661,
"grad_norm": 9.704715728759766,
"learning_rate": 1.8e-05,
"loss": 4.083,
"step": 9
},
{
"epoch": 0.030131826741996232,
"grad_norm": 8.977635383605957,
"learning_rate": 2e-05,
"loss": 3.548,
"step": 10
},
{
"epoch": 0.03314500941619586,
"grad_norm": 7.7479376792907715,
"learning_rate": 2.2000000000000003e-05,
"loss": 3.2281,
"step": 11
},
{
"epoch": 0.03615819209039548,
"grad_norm": 6.718513011932373,
"learning_rate": 2.4e-05,
"loss": 3.0443,
"step": 12
},
{
"epoch": 0.039171374764595104,
"grad_norm": 5.1653056144714355,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.6208,
"step": 13
},
{
"epoch": 0.04218455743879473,
"grad_norm": 4.840386867523193,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.3382,
"step": 14
},
{
"epoch": 0.04519774011299435,
"grad_norm": 4.570226669311523,
"learning_rate": 3e-05,
"loss": 2.0896,
"step": 15
},
{
"epoch": 0.04821092278719397,
"grad_norm": 5.179202079772949,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.0368,
"step": 16
},
{
"epoch": 0.051224105461393596,
"grad_norm": 4.725672245025635,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.8898,
"step": 17
},
{
"epoch": 0.05423728813559322,
"grad_norm": 4.372887134552002,
"learning_rate": 3.6e-05,
"loss": 1.6599,
"step": 18
},
{
"epoch": 0.05725047080979284,
"grad_norm": 4.00122594833374,
"learning_rate": 3.8e-05,
"loss": 1.4213,
"step": 19
},
{
"epoch": 0.060263653483992465,
"grad_norm": 4.925197124481201,
"learning_rate": 4e-05,
"loss": 1.5454,
"step": 20
},
{
"epoch": 0.06327683615819209,
"grad_norm": 9.11976146697998,
"learning_rate": 4.2e-05,
"loss": 2.1408,
"step": 21
},
{
"epoch": 0.06629001883239172,
"grad_norm": 15.82564640045166,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.5483,
"step": 22
},
{
"epoch": 0.06930320150659133,
"grad_norm": 15.502534866333008,
"learning_rate": 4.600000000000001e-05,
"loss": 1.8806,
"step": 23
},
{
"epoch": 0.07231638418079096,
"grad_norm": 18.15461540222168,
"learning_rate": 4.8e-05,
"loss": 1.6405,
"step": 24
},
{
"epoch": 0.07532956685499058,
"grad_norm": 23.61888313293457,
"learning_rate": 5e-05,
"loss": 1.2773,
"step": 25
},
{
"epoch": 0.07834274952919021,
"grad_norm": 11.435036659240723,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.3372,
"step": 26
},
{
"epoch": 0.08135593220338982,
"grad_norm": 13.24569320678711,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.3893,
"step": 27
},
{
"epoch": 0.08436911487758945,
"grad_norm": 9.795696258544922,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.3095,
"step": 28
},
{
"epoch": 0.08738229755178907,
"grad_norm": 8.10338020324707,
"learning_rate": 5.8e-05,
"loss": 1.1856,
"step": 29
},
{
"epoch": 0.0903954802259887,
"grad_norm": 5.573620796203613,
"learning_rate": 6e-05,
"loss": 1.0843,
"step": 30
},
{
"epoch": 0.09340866290018833,
"grad_norm": 2.8769285678863525,
"learning_rate": 6.2e-05,
"loss": 0.9771,
"step": 31
},
{
"epoch": 0.09642184557438795,
"grad_norm": 3.623781681060791,
"learning_rate": 6.400000000000001e-05,
"loss": 0.9225,
"step": 32
},
{
"epoch": 0.09943502824858758,
"grad_norm": 3.1273627281188965,
"learning_rate": 6.6e-05,
"loss": 0.8808,
"step": 33
},
{
"epoch": 0.10244821092278719,
"grad_norm": 2.4352469444274902,
"learning_rate": 6.800000000000001e-05,
"loss": 0.8043,
"step": 34
},
{
"epoch": 0.10546139359698682,
"grad_norm": 2.5423271656036377,
"learning_rate": 7e-05,
"loss": 0.7235,
"step": 35
},
{
"epoch": 0.10847457627118644,
"grad_norm": 2.7016396522521973,
"learning_rate": 7.2e-05,
"loss": 0.7387,
"step": 36
},
{
"epoch": 0.11148775894538607,
"grad_norm": 3.2129478454589844,
"learning_rate": 7.4e-05,
"loss": 0.7625,
"step": 37
},
{
"epoch": 0.11450094161958568,
"grad_norm": 2.897091865539551,
"learning_rate": 7.6e-05,
"loss": 0.7295,
"step": 38
},
{
"epoch": 0.11751412429378531,
"grad_norm": 2.90976619720459,
"learning_rate": 7.800000000000001e-05,
"loss": 0.6797,
"step": 39
},
{
"epoch": 0.12052730696798493,
"grad_norm": 2.8482582569122314,
"learning_rate": 8e-05,
"loss": 0.7018,
"step": 40
},
{
"epoch": 0.12354048964218456,
"grad_norm": 2.0846457481384277,
"learning_rate": 8.2e-05,
"loss": 0.7266,
"step": 41
},
{
"epoch": 0.12655367231638417,
"grad_norm": 2.0968143939971924,
"learning_rate": 8.4e-05,
"loss": 0.5808,
"step": 42
},
{
"epoch": 0.1295668549905838,
"grad_norm": 2.948556423187256,
"learning_rate": 8.6e-05,
"loss": 0.7257,
"step": 43
},
{
"epoch": 0.13258003766478343,
"grad_norm": 2.561649799346924,
"learning_rate": 8.800000000000001e-05,
"loss": 0.6828,
"step": 44
},
{
"epoch": 0.13559322033898305,
"grad_norm": 2.9468488693237305,
"learning_rate": 9e-05,
"loss": 0.7191,
"step": 45
},
{
"epoch": 0.13860640301318267,
"grad_norm": 4.2950825691223145,
"learning_rate": 9.200000000000001e-05,
"loss": 0.7896,
"step": 46
},
{
"epoch": 0.1416195856873823,
"grad_norm": 8.009641647338867,
"learning_rate": 9.4e-05,
"loss": 1.2446,
"step": 47
},
{
"epoch": 0.14463276836158193,
"grad_norm": 6.519936561584473,
"learning_rate": 9.6e-05,
"loss": 0.8017,
"step": 48
},
{
"epoch": 0.14764595103578154,
"grad_norm": 5.3175530433654785,
"learning_rate": 9.8e-05,
"loss": 0.6389,
"step": 49
},
{
"epoch": 0.15065913370998116,
"grad_norm": 7.807773113250732,
"learning_rate": 0.0001,
"loss": 0.5498,
"step": 50
},
{
"epoch": 0.1536723163841808,
"grad_norm": 20.014755249023438,
"learning_rate": 9.999687519737639e-05,
"loss": 1.7708,
"step": 51
},
{
"epoch": 0.15668549905838042,
"grad_norm": 14.703155517578125,
"learning_rate": 9.998750118008115e-05,
"loss": 1.7615,
"step": 52
},
{
"epoch": 0.15969868173258003,
"grad_norm": 11.548951148986816,
"learning_rate": 9.997187911979252e-05,
"loss": 1.4554,
"step": 53
},
{
"epoch": 0.16271186440677965,
"grad_norm": 8.304758071899414,
"learning_rate": 9.995001096914461e-05,
"loss": 1.2888,
"step": 54
},
{
"epoch": 0.1657250470809793,
"grad_norm": 5.550910472869873,
"learning_rate": 9.992189946148366e-05,
"loss": 1.0796,
"step": 55
},
{
"epoch": 0.1687382297551789,
"grad_norm": 3.1853792667388916,
"learning_rate": 9.988754811052616e-05,
"loss": 0.9803,
"step": 56
},
{
"epoch": 0.17175141242937852,
"grad_norm": 2.140463352203369,
"learning_rate": 9.984696120991978e-05,
"loss": 0.8841,
"step": 57
},
{
"epoch": 0.17476459510357814,
"grad_norm": 2.4900693893432617,
"learning_rate": 9.980014383270668e-05,
"loss": 0.8013,
"step": 58
},
{
"epoch": 0.17777777777777778,
"grad_norm": 2.4014413356781006,
"learning_rate": 9.974710183068935e-05,
"loss": 0.7769,
"step": 59
},
{
"epoch": 0.1807909604519774,
"grad_norm": 1.818248987197876,
"learning_rate": 9.968784183369929e-05,
"loss": 0.6339,
"step": 60
},
{
"epoch": 0.18380414312617702,
"grad_norm": 2.038853406906128,
"learning_rate": 9.962237124876828e-05,
"loss": 0.7058,
"step": 61
},
{
"epoch": 0.18681732580037666,
"grad_norm": 1.9188238382339478,
"learning_rate": 9.955069825920249e-05,
"loss": 0.6063,
"step": 62
},
{
"epoch": 0.18983050847457628,
"grad_norm": 1.960972547531128,
"learning_rate": 9.947283182355982e-05,
"loss": 0.6681,
"step": 63
},
{
"epoch": 0.1928436911487759,
"grad_norm": 1.8506237268447876,
"learning_rate": 9.938878167452992e-05,
"loss": 0.4687,
"step": 64
},
{
"epoch": 0.1958568738229755,
"grad_norm": 1.7827894687652588,
"learning_rate": 9.929855831771786e-05,
"loss": 0.5907,
"step": 65
},
{
"epoch": 0.19887005649717515,
"grad_norm": 1.788488745689392,
"learning_rate": 9.92021730303309e-05,
"loss": 0.5778,
"step": 66
},
{
"epoch": 0.20188323917137477,
"grad_norm": 1.9174665212631226,
"learning_rate": 9.909963785976903e-05,
"loss": 0.5587,
"step": 67
},
{
"epoch": 0.20489642184557438,
"grad_norm": 1.898708462715149,
"learning_rate": 9.899096562211902e-05,
"loss": 0.4941,
"step": 68
},
{
"epoch": 0.207909604519774,
"grad_norm": 2.086160659790039,
"learning_rate": 9.887616990055262e-05,
"loss": 0.5702,
"step": 69
},
{
"epoch": 0.21092278719397364,
"grad_norm": 3.054201126098633,
"learning_rate": 9.875526504362869e-05,
"loss": 0.6915,
"step": 70
},
{
"epoch": 0.21393596986817326,
"grad_norm": 4.820160388946533,
"learning_rate": 9.86282661634998e-05,
"loss": 1.0488,
"step": 71
},
{
"epoch": 0.21694915254237288,
"grad_norm": 4.556093692779541,
"learning_rate": 9.849518913402334e-05,
"loss": 0.7673,
"step": 72
},
{
"epoch": 0.2199623352165725,
"grad_norm": 3.98148250579834,
"learning_rate": 9.835605058877729e-05,
"loss": 0.7301,
"step": 73
},
{
"epoch": 0.22297551789077213,
"grad_norm": 4.126860618591309,
"learning_rate": 9.821086791898134e-05,
"loss": 0.8709,
"step": 74
},
{
"epoch": 0.22598870056497175,
"grad_norm": 4.8316216468811035,
"learning_rate": 9.805965927132295e-05,
"loss": 0.7508,
"step": 75
},
{
"epoch": 0.22900188323917137,
"grad_norm": 7.367558479309082,
"learning_rate": 9.79024435456893e-05,
"loss": 1.4311,
"step": 76
},
{
"epoch": 0.232015065913371,
"grad_norm": 6.81304407119751,
"learning_rate": 9.773924039280487e-05,
"loss": 1.3631,
"step": 77
},
{
"epoch": 0.23502824858757063,
"grad_norm": 5.532495021820068,
"learning_rate": 9.75700702117753e-05,
"loss": 1.2462,
"step": 78
},
{
"epoch": 0.23804143126177024,
"grad_norm": 3.750790596008301,
"learning_rate": 9.739495414753753e-05,
"loss": 0.9057,
"step": 79
},
{
"epoch": 0.24105461393596986,
"grad_norm": 2.6967413425445557,
"learning_rate": 9.721391408821711e-05,
"loss": 0.8322,
"step": 80
},
{
"epoch": 0.2440677966101695,
"grad_norm": 1.915755271911621,
"learning_rate": 9.702697266239212e-05,
"loss": 0.6605,
"step": 81
},
{
"epoch": 0.24708097928436912,
"grad_norm": 1.681639552116394,
"learning_rate": 9.683415323626485e-05,
"loss": 0.6949,
"step": 82
},
{
"epoch": 0.25009416195856876,
"grad_norm": 1.6740490198135376,
"learning_rate": 9.663547991074127e-05,
"loss": 0.751,
"step": 83
},
{
"epoch": 0.25009416195856876,
"eval_loss": NaN,
"eval_runtime": 92.9339,
"eval_samples_per_second": 6.015,
"eval_steps_per_second": 1.506,
"step": 83
},
{
"epoch": 0.25310734463276835,
"grad_norm": 1.4990551471710205,
"learning_rate": 9.643097751841854e-05,
"loss": 0.5189,
"step": 84
},
{
"epoch": 0.256120527306968,
"grad_norm": 1.4080356359481812,
"learning_rate": 9.622067162048112e-05,
"loss": 0.5112,
"step": 85
},
{
"epoch": 0.2591337099811676,
"grad_norm": 1.3661057949066162,
"learning_rate": 9.600458850350588e-05,
"loss": 0.4688,
"step": 86
},
{
"epoch": 0.2621468926553672,
"grad_norm": 1.570552945137024,
"learning_rate": 9.578275517617645e-05,
"loss": 0.5058,
"step": 87
},
{
"epoch": 0.26516007532956687,
"grad_norm": 1.6037708520889282,
"learning_rate": 9.555519936590738e-05,
"loss": 0.5201,
"step": 88
},
{
"epoch": 0.26817325800376646,
"grad_norm": 1.5268930196762085,
"learning_rate": 9.532194951537838e-05,
"loss": 0.4661,
"step": 89
},
{
"epoch": 0.2711864406779661,
"grad_norm": 1.7837523221969604,
"learning_rate": 9.508303477897924e-05,
"loss": 0.5005,
"step": 90
},
{
"epoch": 0.27419962335216574,
"grad_norm": 1.3590326309204102,
"learning_rate": 9.483848501916578e-05,
"loss": 0.3866,
"step": 91
},
{
"epoch": 0.27721280602636533,
"grad_norm": 1.5031671524047852,
"learning_rate": 9.458833080272722e-05,
"loss": 0.3559,
"step": 92
},
{
"epoch": 0.280225988700565,
"grad_norm": 1.2212880849838257,
"learning_rate": 9.433260339696563e-05,
"loss": 0.3586,
"step": 93
},
{
"epoch": 0.2832391713747646,
"grad_norm": 1.8385019302368164,
"learning_rate": 9.407133476578778e-05,
"loss": 0.4775,
"step": 94
},
{
"epoch": 0.2862523540489642,
"grad_norm": 2.6899161338806152,
"learning_rate": 9.38045575657098e-05,
"loss": 0.6809,
"step": 95
},
{
"epoch": 0.28926553672316385,
"grad_norm": 3.9981398582458496,
"learning_rate": 9.353230514177552e-05,
"loss": 0.8967,
"step": 96
},
{
"epoch": 0.29227871939736344,
"grad_norm": 3.7616143226623535,
"learning_rate": 9.325461152338846e-05,
"loss": 0.9173,
"step": 97
},
{
"epoch": 0.2952919020715631,
"grad_norm": 3.3938989639282227,
"learning_rate": 9.297151142005851e-05,
"loss": 0.7849,
"step": 98
},
{
"epoch": 0.2983050847457627,
"grad_norm": 3.3373446464538574,
"learning_rate": 9.268304021706349e-05,
"loss": 0.6619,
"step": 99
},
{
"epoch": 0.3013182674199623,
"grad_norm": 4.476459503173828,
"learning_rate": 9.23892339710263e-05,
"loss": 0.7758,
"step": 100
},
{
"epoch": 0.30433145009416196,
"grad_norm": 2.75358510017395,
"learning_rate": 9.209012940540805e-05,
"loss": 0.7565,
"step": 101
},
{
"epoch": 0.3073446327683616,
"grad_norm": 2.192662000656128,
"learning_rate": 9.178576390591802e-05,
"loss": 0.6634,
"step": 102
},
{
"epoch": 0.3103578154425612,
"grad_norm": 2.3334836959838867,
"learning_rate": 9.147617551584066e-05,
"loss": 0.6961,
"step": 103
},
{
"epoch": 0.31337099811676083,
"grad_norm": 1.9057625532150269,
"learning_rate": 9.116140293128051e-05,
"loss": 0.5762,
"step": 104
},
{
"epoch": 0.3163841807909605,
"grad_norm": 1.5543274879455566,
"learning_rate": 9.084148549632547e-05,
"loss": 0.5249,
"step": 105
},
{
"epoch": 0.31939736346516007,
"grad_norm": 1.3116902112960815,
"learning_rate": 9.051646319812918e-05,
"loss": 0.4895,
"step": 106
},
{
"epoch": 0.3224105461393597,
"grad_norm": 1.6137094497680664,
"learning_rate": 9.018637666191283e-05,
"loss": 0.5036,
"step": 107
},
{
"epoch": 0.3254237288135593,
"grad_norm": 1.4955766201019287,
"learning_rate": 8.985126714588738e-05,
"loss": 0.4571,
"step": 108
},
{
"epoch": 0.32843691148775894,
"grad_norm": 1.5371748208999634,
"learning_rate": 8.951117653609666e-05,
"loss": 0.4958,
"step": 109
},
{
"epoch": 0.3314500941619586,
"grad_norm": 1.2266839742660522,
"learning_rate": 8.916614734118184e-05,
"loss": 0.4171,
"step": 110
},
{
"epoch": 0.3344632768361582,
"grad_norm": 1.21657133102417,
"learning_rate": 8.881622268706825e-05,
"loss": 0.421,
"step": 111
},
{
"epoch": 0.3374764595103578,
"grad_norm": 1.2184901237487793,
"learning_rate": 8.8461446311575e-05,
"loss": 0.4307,
"step": 112
},
{
"epoch": 0.34048964218455746,
"grad_norm": 1.5124021768569946,
"learning_rate": 8.810186255894803e-05,
"loss": 0.4865,
"step": 113
},
{
"epoch": 0.34350282485875705,
"grad_norm": 1.078994870185852,
"learning_rate": 8.773751637431748e-05,
"loss": 0.3592,
"step": 114
},
{
"epoch": 0.3465160075329567,
"grad_norm": 1.2173560857772827,
"learning_rate": 8.736845329807993e-05,
"loss": 0.3757,
"step": 115
},
{
"epoch": 0.3495291902071563,
"grad_norm": 1.4223103523254395,
"learning_rate": 8.69947194602061e-05,
"loss": 0.4002,
"step": 116
},
{
"epoch": 0.3525423728813559,
"grad_norm": 1.2369580268859863,
"learning_rate": 8.66163615744751e-05,
"loss": 0.3891,
"step": 117
},
{
"epoch": 0.35555555555555557,
"grad_norm": 1.2306034564971924,
"learning_rate": 8.623342693263548e-05,
"loss": 0.3176,
"step": 118
},
{
"epoch": 0.35856873822975516,
"grad_norm": 1.20809805393219,
"learning_rate": 8.584596339849417e-05,
"loss": 0.3715,
"step": 119
},
{
"epoch": 0.3615819209039548,
"grad_norm": 1.59524405002594,
"learning_rate": 8.545401940193392e-05,
"loss": 0.4539,
"step": 120
},
{
"epoch": 0.36459510357815444,
"grad_norm": 2.4288361072540283,
"learning_rate": 8.505764393285984e-05,
"loss": 0.7094,
"step": 121
},
{
"epoch": 0.36760828625235403,
"grad_norm": 2.587125778198242,
"learning_rate": 8.46568865350762e-05,
"loss": 0.7052,
"step": 122
},
{
"epoch": 0.3706214689265537,
"grad_norm": 3.610764980316162,
"learning_rate": 8.425179730009368e-05,
"loss": 0.6835,
"step": 123
},
{
"epoch": 0.3736346516007533,
"grad_norm": 2.254451274871826,
"learning_rate": 8.384242686086848e-05,
"loss": 0.5733,
"step": 124
},
{
"epoch": 0.3766478342749529,
"grad_norm": 3.2182092666625977,
"learning_rate": 8.342882638547351e-05,
"loss": 0.7416,
"step": 125
},
{
"epoch": 0.37966101694915255,
"grad_norm": 2.0895962715148926,
"learning_rate": 8.301104757070274e-05,
"loss": 0.611,
"step": 126
},
{
"epoch": 0.38267419962335214,
"grad_norm": 1.9307582378387451,
"learning_rate": 8.258914263560971e-05,
"loss": 0.6099,
"step": 127
},
{
"epoch": 0.3856873822975518,
"grad_norm": 1.7885206937789917,
"learning_rate": 8.216316431498028e-05,
"loss": 0.4832,
"step": 128
},
{
"epoch": 0.3887005649717514,
"grad_norm": 1.2265185117721558,
"learning_rate": 8.173316585274145e-05,
"loss": 0.4042,
"step": 129
},
{
"epoch": 0.391713747645951,
"grad_norm": 1.369534969329834,
"learning_rate": 8.129920099530607e-05,
"loss": 0.4681,
"step": 130
},
{
"epoch": 0.39472693032015066,
"grad_norm": 1.340951681137085,
"learning_rate": 8.086132398485524e-05,
"loss": 0.4775,
"step": 131
},
{
"epoch": 0.3977401129943503,
"grad_norm": 1.1047234535217285,
"learning_rate": 8.041958955255814e-05,
"loss": 0.4508,
"step": 132
},
{
"epoch": 0.4007532956685499,
"grad_norm": 1.0403156280517578,
"learning_rate": 7.99740529117313e-05,
"loss": 0.4217,
"step": 133
},
{
"epoch": 0.40376647834274954,
"grad_norm": 0.9500618577003479,
"learning_rate": 7.952476975093729e-05,
"loss": 0.34,
"step": 134
},
{
"epoch": 0.4067796610169492,
"grad_norm": 1.1021428108215332,
"learning_rate": 7.907179622702408e-05,
"loss": 0.392,
"step": 135
},
{
"epoch": 0.40979284369114877,
"grad_norm": 1.2623156309127808,
"learning_rate": 7.861518895810596e-05,
"loss": 0.4238,
"step": 136
},
{
"epoch": 0.4128060263653484,
"grad_norm": 1.395652413368225,
"learning_rate": 7.815500501648653e-05,
"loss": 0.4211,
"step": 137
},
{
"epoch": 0.415819209039548,
"grad_norm": 1.3175368309020996,
"learning_rate": 7.769130192152538e-05,
"loss": 0.415,
"step": 138
},
{
"epoch": 0.41883239171374764,
"grad_norm": 1.3882197141647339,
"learning_rate": 7.722413763244838e-05,
"loss": 0.422,
"step": 139
},
{
"epoch": 0.4218455743879473,
"grad_norm": 1.396023154258728,
"learning_rate": 7.675357054110336e-05,
"loss": 0.466,
"step": 140
},
{
"epoch": 0.4248587570621469,
"grad_norm": 1.0779083967208862,
"learning_rate": 7.627965946466166e-05,
"loss": 0.3576,
"step": 141
},
{
"epoch": 0.4278719397363465,
"grad_norm": 1.2511008977890015,
"learning_rate": 7.580246363826621e-05,
"loss": 0.301,
"step": 142
},
{
"epoch": 0.43088512241054616,
"grad_norm": 1.13119375705719,
"learning_rate": 7.532204270762786e-05,
"loss": 0.3332,
"step": 143
},
{
"epoch": 0.43389830508474575,
"grad_norm": 2.0195682048797607,
"learning_rate": 7.483845672156998e-05,
"loss": 0.6475,
"step": 144
},
{
"epoch": 0.4369114877589454,
"grad_norm": 2.429945230484009,
"learning_rate": 7.435176612452286e-05,
"loss": 0.7177,
"step": 145
},
{
"epoch": 0.439924670433145,
"grad_norm": 3.0756828784942627,
"learning_rate": 7.386203174896872e-05,
"loss": 0.741,
"step": 146
},
{
"epoch": 0.4429378531073446,
"grad_norm": 3.7236998081207275,
"learning_rate": 7.336931480783801e-05,
"loss": 0.7999,
"step": 147
},
{
"epoch": 0.44595103578154427,
"grad_norm": 2.7121517658233643,
"learning_rate": 7.287367688685835e-05,
"loss": 0.6044,
"step": 148
},
{
"epoch": 0.44896421845574386,
"grad_norm": 3.661588668823242,
"learning_rate": 7.237517993685678e-05,
"loss": 0.5553,
"step": 149
},
{
"epoch": 0.4519774011299435,
"grad_norm": 4.68520975112915,
"learning_rate": 7.187388626601637e-05,
"loss": 0.411,
"step": 150
},
{
"epoch": 0.45499058380414314,
"grad_norm": 1.866217017173767,
"learning_rate": 7.136985853208824e-05,
"loss": 0.5442,
"step": 151
},
{
"epoch": 0.45800376647834273,
"grad_norm": 1.6526014804840088,
"learning_rate": 7.086315973455981e-05,
"loss": 0.5071,
"step": 152
},
{
"epoch": 0.4610169491525424,
"grad_norm": 1.3213937282562256,
"learning_rate": 7.035385320678036e-05,
"loss": 0.4598,
"step": 153
},
{
"epoch": 0.464030131826742,
"grad_norm": 0.959452211856842,
"learning_rate": 6.984200260804484e-05,
"loss": 0.3485,
"step": 154
},
{
"epoch": 0.4670433145009416,
"grad_norm": 1.0355703830718994,
"learning_rate": 6.932767191563703e-05,
"loss": 0.3648,
"step": 155
},
{
"epoch": 0.47005649717514125,
"grad_norm": 0.9991386532783508,
"learning_rate": 6.881092541683278e-05,
"loss": 0.3535,
"step": 156
},
{
"epoch": 0.47306967984934084,
"grad_norm": 1.0915963649749756,
"learning_rate": 6.829182770086474e-05,
"loss": 0.3682,
"step": 157
},
{
"epoch": 0.4760828625235405,
"grad_norm": 0.9837580323219299,
"learning_rate": 6.777044365084907e-05,
"loss": 0.3703,
"step": 158
},
{
"epoch": 0.47909604519774013,
"grad_norm": 1.258581280708313,
"learning_rate": 6.724683843567568e-05,
"loss": 0.4104,
"step": 159
},
{
"epoch": 0.4821092278719397,
"grad_norm": 0.832224428653717,
"learning_rate": 6.672107750186255e-05,
"loss": 0.2934,
"step": 160
},
{
"epoch": 0.48512241054613936,
"grad_norm": 0.881106436252594,
"learning_rate": 6.619322656537552e-05,
"loss": 0.3127,
"step": 161
},
{
"epoch": 0.488135593220339,
"grad_norm": 1.257350206375122,
"learning_rate": 6.566335160341424e-05,
"loss": 0.3804,
"step": 162
},
{
"epoch": 0.4911487758945386,
"grad_norm": 1.6826411485671997,
"learning_rate": 6.513151884616556e-05,
"loss": 0.4807,
"step": 163
},
{
"epoch": 0.49416195856873824,
"grad_norm": 1.31766676902771,
"learning_rate": 6.459779476852528e-05,
"loss": 0.3872,
"step": 164
},
{
"epoch": 0.4971751412429379,
"grad_norm": 1.438594102859497,
"learning_rate": 6.406224608178932e-05,
"loss": 0.3868,
"step": 165
},
{
"epoch": 0.5001883239171375,
"grad_norm": 1.198364496231079,
"learning_rate": 6.352493972531534e-05,
"loss": 0.3361,
"step": 166
},
{
"epoch": 0.5001883239171375,
"eval_loss": NaN,
"eval_runtime": 93.1419,
"eval_samples_per_second": 6.002,
"eval_steps_per_second": 1.503,
"step": 166
}
],
"logging_steps": 1,
"max_steps": 331,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 83,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.46878716765012e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}