deepspeed_no_offload_liger / trainer_state.json
sedrickkeh's picture
End of training
71dd683 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.980891719745223,
"eval_steps": 500,
"global_step": 156,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01910828025477707,
"grad_norm": 9.227933285503074,
"learning_rate": 6.25e-07,
"loss": 1.3425,
"step": 1
},
{
"epoch": 0.03821656050955414,
"grad_norm": 9.472026160514938,
"learning_rate": 1.25e-06,
"loss": 1.3611,
"step": 2
},
{
"epoch": 0.05732484076433121,
"grad_norm": 8.830253076867896,
"learning_rate": 1.8750000000000003e-06,
"loss": 1.2961,
"step": 3
},
{
"epoch": 0.07643312101910828,
"grad_norm": 8.795159256298211,
"learning_rate": 2.5e-06,
"loss": 1.3066,
"step": 4
},
{
"epoch": 0.09554140127388536,
"grad_norm": 8.376308303967003,
"learning_rate": 3.125e-06,
"loss": 1.3082,
"step": 5
},
{
"epoch": 0.11464968152866242,
"grad_norm": 6.297341255951074,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.2617,
"step": 6
},
{
"epoch": 0.1337579617834395,
"grad_norm": 3.914176086886225,
"learning_rate": 4.3750000000000005e-06,
"loss": 1.1772,
"step": 7
},
{
"epoch": 0.15286624203821655,
"grad_norm": 3.4470404125397502,
"learning_rate": 5e-06,
"loss": 1.2102,
"step": 8
},
{
"epoch": 0.17197452229299362,
"grad_norm": 4.0406911254613584,
"learning_rate": 5.625e-06,
"loss": 1.1231,
"step": 9
},
{
"epoch": 0.1910828025477707,
"grad_norm": 4.245079114114731,
"learning_rate": 6.25e-06,
"loss": 1.0776,
"step": 10
},
{
"epoch": 0.21019108280254778,
"grad_norm": 4.077365681327481,
"learning_rate": 6.875e-06,
"loss": 1.0761,
"step": 11
},
{
"epoch": 0.22929936305732485,
"grad_norm": 3.445755837445021,
"learning_rate": 7.500000000000001e-06,
"loss": 1.0193,
"step": 12
},
{
"epoch": 0.2484076433121019,
"grad_norm": 3.8318543379579544,
"learning_rate": 8.125000000000001e-06,
"loss": 1.0478,
"step": 13
},
{
"epoch": 0.267515923566879,
"grad_norm": 3.071258708578322,
"learning_rate": 8.750000000000001e-06,
"loss": 1.0033,
"step": 14
},
{
"epoch": 0.28662420382165604,
"grad_norm": 2.2020115811514214,
"learning_rate": 9.375000000000001e-06,
"loss": 0.9645,
"step": 15
},
{
"epoch": 0.3057324840764331,
"grad_norm": 2.0537353235418565,
"learning_rate": 1e-05,
"loss": 0.958,
"step": 16
},
{
"epoch": 0.3248407643312102,
"grad_norm": 2.524923375900554,
"learning_rate": 9.998741174712534e-06,
"loss": 0.9511,
"step": 17
},
{
"epoch": 0.34394904458598724,
"grad_norm": 2.3962991975778745,
"learning_rate": 9.994965332706574e-06,
"loss": 0.9528,
"step": 18
},
{
"epoch": 0.3630573248407643,
"grad_norm": 1.8297697509151722,
"learning_rate": 9.98867437523228e-06,
"loss": 0.9514,
"step": 19
},
{
"epoch": 0.3821656050955414,
"grad_norm": 1.3987683439205127,
"learning_rate": 9.979871469976197e-06,
"loss": 0.9267,
"step": 20
},
{
"epoch": 0.4012738853503185,
"grad_norm": 1.4250398603915928,
"learning_rate": 9.968561049466214e-06,
"loss": 0.9386,
"step": 21
},
{
"epoch": 0.42038216560509556,
"grad_norm": 1.4588002478638835,
"learning_rate": 9.954748808839675e-06,
"loss": 0.8951,
"step": 22
},
{
"epoch": 0.4394904458598726,
"grad_norm": 1.1563385781170124,
"learning_rate": 9.938441702975689e-06,
"loss": 0.8936,
"step": 23
},
{
"epoch": 0.4585987261146497,
"grad_norm": 0.9988253832636228,
"learning_rate": 9.91964794299315e-06,
"loss": 0.914,
"step": 24
},
{
"epoch": 0.47770700636942676,
"grad_norm": 1.1162721659508148,
"learning_rate": 9.898376992116179e-06,
"loss": 0.8876,
"step": 25
},
{
"epoch": 0.4968152866242038,
"grad_norm": 1.0983952836290436,
"learning_rate": 9.874639560909118e-06,
"loss": 0.8914,
"step": 26
},
{
"epoch": 0.5159235668789809,
"grad_norm": 1.1365401656120768,
"learning_rate": 9.848447601883436e-06,
"loss": 0.9179,
"step": 27
},
{
"epoch": 0.535031847133758,
"grad_norm": 1.0308244141669993,
"learning_rate": 9.819814303479268e-06,
"loss": 0.9224,
"step": 28
},
{
"epoch": 0.554140127388535,
"grad_norm": 1.0310315272236807,
"learning_rate": 9.788754083424654e-06,
"loss": 0.8651,
"step": 29
},
{
"epoch": 0.5732484076433121,
"grad_norm": 0.9389390550731398,
"learning_rate": 9.755282581475769e-06,
"loss": 0.8732,
"step": 30
},
{
"epoch": 0.5923566878980892,
"grad_norm": 0.9326204153377393,
"learning_rate": 9.719416651541839e-06,
"loss": 0.8963,
"step": 31
},
{
"epoch": 0.6114649681528662,
"grad_norm": 1.0133137708359177,
"learning_rate": 9.681174353198687e-06,
"loss": 0.8958,
"step": 32
},
{
"epoch": 0.6305732484076433,
"grad_norm": 0.9984007412220515,
"learning_rate": 9.640574942595195e-06,
"loss": 0.8807,
"step": 33
},
{
"epoch": 0.6496815286624203,
"grad_norm": 0.9685258044300203,
"learning_rate": 9.597638862757255e-06,
"loss": 0.8394,
"step": 34
},
{
"epoch": 0.6687898089171974,
"grad_norm": 0.9743488277031624,
"learning_rate": 9.552387733294081e-06,
"loss": 0.8645,
"step": 35
},
{
"epoch": 0.6878980891719745,
"grad_norm": 1.7264735775688218,
"learning_rate": 9.504844339512096e-06,
"loss": 0.8792,
"step": 36
},
{
"epoch": 0.7070063694267515,
"grad_norm": 1.0278226090106095,
"learning_rate": 9.45503262094184e-06,
"loss": 0.8784,
"step": 37
},
{
"epoch": 0.7261146496815286,
"grad_norm": 1.2544830756610066,
"learning_rate": 9.40297765928369e-06,
"loss": 0.8944,
"step": 38
},
{
"epoch": 0.7452229299363057,
"grad_norm": 1.0796488440630818,
"learning_rate": 9.348705665778479e-06,
"loss": 0.8572,
"step": 39
},
{
"epoch": 0.7643312101910829,
"grad_norm": 0.9510410365427641,
"learning_rate": 9.292243968009332e-06,
"loss": 0.8044,
"step": 40
},
{
"epoch": 0.7834394904458599,
"grad_norm": 1.0524980356996851,
"learning_rate": 9.233620996141421e-06,
"loss": 0.8773,
"step": 41
},
{
"epoch": 0.802547770700637,
"grad_norm": 0.9106456383960799,
"learning_rate": 9.172866268606514e-06,
"loss": 0.853,
"step": 42
},
{
"epoch": 0.821656050955414,
"grad_norm": 0.9932738231293439,
"learning_rate": 9.110010377239552e-06,
"loss": 0.8874,
"step": 43
},
{
"epoch": 0.8407643312101911,
"grad_norm": 46.913671484235365,
"learning_rate": 9.045084971874738e-06,
"loss": 0.847,
"step": 44
},
{
"epoch": 0.8598726114649682,
"grad_norm": 8.233867144282662,
"learning_rate": 8.978122744408905e-06,
"loss": 0.8741,
"step": 45
},
{
"epoch": 0.8789808917197452,
"grad_norm": 4.658535571300973,
"learning_rate": 8.90915741234015e-06,
"loss": 0.8413,
"step": 46
},
{
"epoch": 0.8980891719745223,
"grad_norm": 1.4039031696066469,
"learning_rate": 8.838223701790057e-06,
"loss": 0.8343,
"step": 47
},
{
"epoch": 0.9171974522292994,
"grad_norm": 1.213771543456484,
"learning_rate": 8.765357330018056e-06,
"loss": 0.8285,
"step": 48
},
{
"epoch": 0.9363057324840764,
"grad_norm": 1.003822361975443,
"learning_rate": 8.690594987436705e-06,
"loss": 0.8567,
"step": 49
},
{
"epoch": 0.9554140127388535,
"grad_norm": 0.9671839723514609,
"learning_rate": 8.613974319136959e-06,
"loss": 0.8519,
"step": 50
},
{
"epoch": 0.9745222929936306,
"grad_norm": 1.1205438105215009,
"learning_rate": 8.535533905932739e-06,
"loss": 0.8742,
"step": 51
},
{
"epoch": 0.9936305732484076,
"grad_norm": 1.013109679210764,
"learning_rate": 8.455313244934324e-06,
"loss": 0.8529,
"step": 52
},
{
"epoch": 1.0127388535031847,
"grad_norm": 1.9649084155391565,
"learning_rate": 8.373352729660373e-06,
"loss": 1.2827,
"step": 53
},
{
"epoch": 1.0318471337579618,
"grad_norm": 1.0716652833426663,
"learning_rate": 8.289693629698564e-06,
"loss": 0.7438,
"step": 54
},
{
"epoch": 1.0509554140127388,
"grad_norm": 0.8516544983006089,
"learning_rate": 8.204378069925121e-06,
"loss": 0.7591,
"step": 55
},
{
"epoch": 1.070063694267516,
"grad_norm": 1.0044162501877292,
"learning_rate": 8.117449009293668e-06,
"loss": 0.7465,
"step": 56
},
{
"epoch": 1.089171974522293,
"grad_norm": 1.0968519968804,
"learning_rate": 8.0289502192041e-06,
"loss": 0.706,
"step": 57
},
{
"epoch": 1.10828025477707,
"grad_norm": 0.9435346629435438,
"learning_rate": 7.938926261462366e-06,
"loss": 0.7278,
"step": 58
},
{
"epoch": 1.127388535031847,
"grad_norm": 0.9124827226604812,
"learning_rate": 7.84742246584226e-06,
"loss": 0.7418,
"step": 59
},
{
"epoch": 1.1464968152866242,
"grad_norm": 0.8637501333239377,
"learning_rate": 7.754484907260513e-06,
"loss": 0.6898,
"step": 60
},
{
"epoch": 1.1656050955414012,
"grad_norm": 0.9648201707603152,
"learning_rate": 7.660160382576683e-06,
"loss": 0.7668,
"step": 61
},
{
"epoch": 1.1847133757961783,
"grad_norm": 0.8599220030220159,
"learning_rate": 7.564496387029532e-06,
"loss": 0.697,
"step": 62
},
{
"epoch": 1.2038216560509554,
"grad_norm": 0.9160692690066139,
"learning_rate": 7.467541090321735e-06,
"loss": 0.7462,
"step": 63
},
{
"epoch": 1.2229299363057324,
"grad_norm": 0.8326673988749977,
"learning_rate": 7.369343312364994e-06,
"loss": 0.6747,
"step": 64
},
{
"epoch": 1.2420382165605095,
"grad_norm": 0.9697357293095302,
"learning_rate": 7.269952498697734e-06,
"loss": 0.7475,
"step": 65
},
{
"epoch": 1.2611464968152866,
"grad_norm": 0.9078120230587216,
"learning_rate": 7.169418695587791e-06,
"loss": 0.7289,
"step": 66
},
{
"epoch": 1.2802547770700636,
"grad_norm": 0.9578137480834857,
"learning_rate": 7.067792524832604e-06,
"loss": 0.7498,
"step": 67
},
{
"epoch": 1.2993630573248407,
"grad_norm": 0.8659383416965061,
"learning_rate": 6.965125158269619e-06,
"loss": 0.6954,
"step": 68
},
{
"epoch": 1.3184713375796178,
"grad_norm": 0.889634817408517,
"learning_rate": 6.8614682920097265e-06,
"loss": 0.756,
"step": 69
},
{
"epoch": 1.3375796178343948,
"grad_norm": 0.9043394818021243,
"learning_rate": 6.7568741204067145e-06,
"loss": 0.681,
"step": 70
},
{
"epoch": 1.356687898089172,
"grad_norm": 1.069208998312765,
"learning_rate": 6.651395309775837e-06,
"loss": 0.725,
"step": 71
},
{
"epoch": 1.3757961783439492,
"grad_norm": 0.7778562459017252,
"learning_rate": 6.545084971874738e-06,
"loss": 0.6893,
"step": 72
},
{
"epoch": 1.394904458598726,
"grad_norm": 0.8151710764791644,
"learning_rate": 6.437996637160086e-06,
"loss": 0.709,
"step": 73
},
{
"epoch": 1.4140127388535033,
"grad_norm": 0.8743990369674942,
"learning_rate": 6.330184227833376e-06,
"loss": 0.6778,
"step": 74
},
{
"epoch": 1.4331210191082802,
"grad_norm": 0.8331075043131652,
"learning_rate": 6.2217020306894705e-06,
"loss": 0.6839,
"step": 75
},
{
"epoch": 1.4522292993630574,
"grad_norm": 0.7331493898351021,
"learning_rate": 6.112604669781572e-06,
"loss": 0.7109,
"step": 76
},
{
"epoch": 1.4713375796178343,
"grad_norm": 0.8211933601016228,
"learning_rate": 6.002947078916365e-06,
"loss": 0.7523,
"step": 77
},
{
"epoch": 1.4904458598726116,
"grad_norm": 0.7670684755775976,
"learning_rate": 5.892784473993184e-06,
"loss": 0.6795,
"step": 78
},
{
"epoch": 1.5095541401273884,
"grad_norm": 0.7515884912328964,
"learning_rate": 5.782172325201155e-06,
"loss": 0.666,
"step": 79
},
{
"epoch": 1.5286624203821657,
"grad_norm": 0.7891358665398239,
"learning_rate": 5.671166329088278e-06,
"loss": 0.701,
"step": 80
},
{
"epoch": 1.5477707006369426,
"grad_norm": 0.7989435969138721,
"learning_rate": 5.559822380516539e-06,
"loss": 0.7023,
"step": 81
},
{
"epoch": 1.5668789808917198,
"grad_norm": 0.7827014240647194,
"learning_rate": 5.448196544517168e-06,
"loss": 0.7271,
"step": 82
},
{
"epoch": 1.5859872611464967,
"grad_norm": 0.8274859991710798,
"learning_rate": 5.336345028060199e-06,
"loss": 0.7432,
"step": 83
},
{
"epoch": 1.605095541401274,
"grad_norm": 0.7657377353023954,
"learning_rate": 5.224324151752575e-06,
"loss": 0.7103,
"step": 84
},
{
"epoch": 1.6242038216560508,
"grad_norm": 0.8059764585321254,
"learning_rate": 5.112190321479026e-06,
"loss": 0.7116,
"step": 85
},
{
"epoch": 1.643312101910828,
"grad_norm": 0.7347224257680689,
"learning_rate": 5e-06,
"loss": 0.6722,
"step": 86
},
{
"epoch": 1.662420382165605,
"grad_norm": 0.8028061476445927,
"learning_rate": 4.887809678520976e-06,
"loss": 0.7636,
"step": 87
},
{
"epoch": 1.6815286624203822,
"grad_norm": 0.8349493532591638,
"learning_rate": 4.775675848247427e-06,
"loss": 0.7164,
"step": 88
},
{
"epoch": 1.700636942675159,
"grad_norm": 0.869601870652576,
"learning_rate": 4.663654971939802e-06,
"loss": 0.6914,
"step": 89
},
{
"epoch": 1.7197452229299364,
"grad_norm": 0.76042774797527,
"learning_rate": 4.551803455482833e-06,
"loss": 0.7241,
"step": 90
},
{
"epoch": 1.7388535031847132,
"grad_norm": 0.7703317051128579,
"learning_rate": 4.4401776194834615e-06,
"loss": 0.7143,
"step": 91
},
{
"epoch": 1.7579617834394905,
"grad_norm": 0.8089333300210244,
"learning_rate": 4.3288336709117246e-06,
"loss": 0.7519,
"step": 92
},
{
"epoch": 1.7770700636942676,
"grad_norm": 0.8010756503113291,
"learning_rate": 4.217827674798845e-06,
"loss": 0.689,
"step": 93
},
{
"epoch": 1.7961783439490446,
"grad_norm": 0.7769443002602437,
"learning_rate": 4.107215526006818e-06,
"loss": 0.6654,
"step": 94
},
{
"epoch": 1.8152866242038217,
"grad_norm": 0.7401764704224425,
"learning_rate": 3.997052921083637e-06,
"loss": 0.7507,
"step": 95
},
{
"epoch": 1.8343949044585988,
"grad_norm": 0.7606400054072479,
"learning_rate": 3.887395330218429e-06,
"loss": 0.7146,
"step": 96
},
{
"epoch": 1.8535031847133758,
"grad_norm": 0.77501344642517,
"learning_rate": 3.778297969310529e-06,
"loss": 0.7085,
"step": 97
},
{
"epoch": 1.872611464968153,
"grad_norm": 0.8843714906023279,
"learning_rate": 3.669815772166625e-06,
"loss": 0.7262,
"step": 98
},
{
"epoch": 1.89171974522293,
"grad_norm": 0.8134477369459705,
"learning_rate": 3.562003362839914e-06,
"loss": 0.691,
"step": 99
},
{
"epoch": 1.910828025477707,
"grad_norm": 0.8250498280158337,
"learning_rate": 3.4549150281252635e-06,
"loss": 0.6462,
"step": 100
},
{
"epoch": 1.929936305732484,
"grad_norm": 0.814856379236683,
"learning_rate": 3.3486046902241663e-06,
"loss": 0.7647,
"step": 101
},
{
"epoch": 1.9490445859872612,
"grad_norm": 0.7638202491156124,
"learning_rate": 3.2431258795932863e-06,
"loss": 0.6822,
"step": 102
},
{
"epoch": 1.9681528662420382,
"grad_norm": 0.695613860392128,
"learning_rate": 3.1385317079902743e-06,
"loss": 0.7024,
"step": 103
},
{
"epoch": 1.9872611464968153,
"grad_norm": 0.8099526198543524,
"learning_rate": 3.0348748417303826e-06,
"loss": 0.6904,
"step": 104
},
{
"epoch": 2.0063694267515926,
"grad_norm": 1.6100851699308538,
"learning_rate": 2.932207475167398e-06,
"loss": 1.1124,
"step": 105
},
{
"epoch": 2.0254777070063694,
"grad_norm": 0.8571163553138604,
"learning_rate": 2.83058130441221e-06,
"loss": 0.6577,
"step": 106
},
{
"epoch": 2.0445859872611467,
"grad_norm": 0.8272319704418373,
"learning_rate": 2.7300475013022666e-06,
"loss": 0.5686,
"step": 107
},
{
"epoch": 2.0636942675159236,
"grad_norm": 0.7324205693555381,
"learning_rate": 2.6306566876350072e-06,
"loss": 0.6029,
"step": 108
},
{
"epoch": 2.082802547770701,
"grad_norm": 0.6871754965898416,
"learning_rate": 2.532458909678266e-06,
"loss": 0.5759,
"step": 109
},
{
"epoch": 2.1019108280254777,
"grad_norm": 0.7337471592562097,
"learning_rate": 2.43550361297047e-06,
"loss": 0.6313,
"step": 110
},
{
"epoch": 2.121019108280255,
"grad_norm": 0.7828664153327386,
"learning_rate": 2.339839617423318e-06,
"loss": 0.642,
"step": 111
},
{
"epoch": 2.140127388535032,
"grad_norm": 0.7477311758006457,
"learning_rate": 2.245515092739488e-06,
"loss": 0.6071,
"step": 112
},
{
"epoch": 2.159235668789809,
"grad_norm": 0.8108622801703812,
"learning_rate": 2.1525775341577404e-06,
"loss": 0.6389,
"step": 113
},
{
"epoch": 2.178343949044586,
"grad_norm": 0.7283345401587005,
"learning_rate": 2.061073738537635e-06,
"loss": 0.5686,
"step": 114
},
{
"epoch": 2.1974522292993632,
"grad_norm": 0.6953720571113524,
"learning_rate": 1.971049780795901e-06,
"loss": 0.5922,
"step": 115
},
{
"epoch": 2.21656050955414,
"grad_norm": 0.7034103566372156,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.6002,
"step": 116
},
{
"epoch": 2.2356687898089174,
"grad_norm": 0.7356697319097925,
"learning_rate": 1.7956219300748796e-06,
"loss": 0.6249,
"step": 117
},
{
"epoch": 2.254777070063694,
"grad_norm": 0.6772874883734505,
"learning_rate": 1.7103063703014372e-06,
"loss": 0.5775,
"step": 118
},
{
"epoch": 2.2738853503184715,
"grad_norm": 0.7169981331948195,
"learning_rate": 1.6266472703396286e-06,
"loss": 0.6113,
"step": 119
},
{
"epoch": 2.2929936305732483,
"grad_norm": 0.7431489549123004,
"learning_rate": 1.544686755065677e-06,
"loss": 0.6283,
"step": 120
},
{
"epoch": 2.3121019108280256,
"grad_norm": 0.7446254093400961,
"learning_rate": 1.4644660940672628e-06,
"loss": 0.5991,
"step": 121
},
{
"epoch": 2.3312101910828025,
"grad_norm": 0.7501216116687166,
"learning_rate": 1.3860256808630429e-06,
"loss": 0.5943,
"step": 122
},
{
"epoch": 2.3503184713375798,
"grad_norm": 0.7159395398297718,
"learning_rate": 1.3094050125632973e-06,
"loss": 0.61,
"step": 123
},
{
"epoch": 2.3694267515923566,
"grad_norm": 0.6592000520850055,
"learning_rate": 1.234642669981946e-06,
"loss": 0.5619,
"step": 124
},
{
"epoch": 2.388535031847134,
"grad_norm": 0.7506492489640302,
"learning_rate": 1.1617762982099446e-06,
"loss": 0.6469,
"step": 125
},
{
"epoch": 2.4076433121019107,
"grad_norm": 0.6780909174203167,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.5711,
"step": 126
},
{
"epoch": 2.426751592356688,
"grad_norm": 0.7057741532093048,
"learning_rate": 1.0218772555910955e-06,
"loss": 0.6099,
"step": 127
},
{
"epoch": 2.445859872611465,
"grad_norm": 0.7403339136251366,
"learning_rate": 9.549150281252633e-07,
"loss": 0.6232,
"step": 128
},
{
"epoch": 2.464968152866242,
"grad_norm": 0.737304698767744,
"learning_rate": 8.899896227604509e-07,
"loss": 0.6051,
"step": 129
},
{
"epoch": 2.484076433121019,
"grad_norm": 0.6691852021800104,
"learning_rate": 8.271337313934869e-07,
"loss": 0.5551,
"step": 130
},
{
"epoch": 2.5031847133757963,
"grad_norm": 0.7191977678487883,
"learning_rate": 7.663790038585794e-07,
"loss": 0.6801,
"step": 131
},
{
"epoch": 2.522292993630573,
"grad_norm": 0.6666608438228615,
"learning_rate": 7.077560319906696e-07,
"loss": 0.5733,
"step": 132
},
{
"epoch": 2.5414012738853504,
"grad_norm": 0.7193470384011437,
"learning_rate": 6.512943342215234e-07,
"loss": 0.6124,
"step": 133
},
{
"epoch": 2.5605095541401273,
"grad_norm": 0.6633677932208085,
"learning_rate": 5.9702234071631e-07,
"loss": 0.5694,
"step": 134
},
{
"epoch": 2.5796178343949046,
"grad_norm": 0.6820884190975942,
"learning_rate": 5.449673790581611e-07,
"loss": 0.5906,
"step": 135
},
{
"epoch": 2.5987261146496814,
"grad_norm": 0.686115043867371,
"learning_rate": 4.951556604879049e-07,
"loss": 0.596,
"step": 136
},
{
"epoch": 2.6178343949044587,
"grad_norm": 0.7102770507120266,
"learning_rate": 4.4761226670592074e-07,
"loss": 0.6075,
"step": 137
},
{
"epoch": 2.6369426751592355,
"grad_norm": 0.6943090370227929,
"learning_rate": 4.0236113724274716e-07,
"loss": 0.6073,
"step": 138
},
{
"epoch": 2.656050955414013,
"grad_norm": 0.6638939951973273,
"learning_rate": 3.5942505740480583e-07,
"loss": 0.5987,
"step": 139
},
{
"epoch": 2.6751592356687897,
"grad_norm": 0.6869312039050859,
"learning_rate": 3.18825646801314e-07,
"loss": 0.5869,
"step": 140
},
{
"epoch": 2.694267515923567,
"grad_norm": 0.6861653360508139,
"learning_rate": 2.8058334845816214e-07,
"loss": 0.6231,
"step": 141
},
{
"epoch": 2.713375796178344,
"grad_norm": 0.6862321292929283,
"learning_rate": 2.447174185242324e-07,
"loss": 0.6306,
"step": 142
},
{
"epoch": 2.732484076433121,
"grad_norm": 0.680463673317858,
"learning_rate": 2.1124591657534776e-07,
"loss": 0.6098,
"step": 143
},
{
"epoch": 2.7515923566878984,
"grad_norm": 0.6736559206438442,
"learning_rate": 1.801856965207338e-07,
"loss": 0.5506,
"step": 144
},
{
"epoch": 2.770700636942675,
"grad_norm": 0.6606157362336229,
"learning_rate": 1.5155239811656562e-07,
"loss": 0.5764,
"step": 145
},
{
"epoch": 2.789808917197452,
"grad_norm": 0.6978415306898502,
"learning_rate": 1.253604390908819e-07,
"loss": 0.6209,
"step": 146
},
{
"epoch": 2.8089171974522293,
"grad_norm": 0.7142833069748467,
"learning_rate": 1.0162300788382263e-07,
"loss": 0.6466,
"step": 147
},
{
"epoch": 2.8280254777070066,
"grad_norm": 0.6469786334667661,
"learning_rate": 8.035205700685167e-08,
"loss": 0.5619,
"step": 148
},
{
"epoch": 2.8471337579617835,
"grad_norm": 0.6246382103597099,
"learning_rate": 6.15582970243117e-08,
"loss": 0.6001,
"step": 149
},
{
"epoch": 2.8662420382165603,
"grad_norm": 0.6660698521873251,
"learning_rate": 4.52511911603265e-08,
"loss": 0.5876,
"step": 150
},
{
"epoch": 2.8853503184713376,
"grad_norm": 0.6537694564043967,
"learning_rate": 3.143895053378698e-08,
"loss": 0.6018,
"step": 151
},
{
"epoch": 2.904458598726115,
"grad_norm": 0.7003986004279357,
"learning_rate": 2.012853002380466e-08,
"loss": 0.5735,
"step": 152
},
{
"epoch": 2.9235668789808917,
"grad_norm": 0.713812945220065,
"learning_rate": 1.132562476771959e-08,
"loss": 0.6618,
"step": 153
},
{
"epoch": 2.9426751592356686,
"grad_norm": 0.663021221536703,
"learning_rate": 5.034667293427053e-09,
"loss": 0.582,
"step": 154
},
{
"epoch": 2.961783439490446,
"grad_norm": 0.6774361613282582,
"learning_rate": 1.2588252874673469e-09,
"loss": 0.5935,
"step": 155
},
{
"epoch": 2.980891719745223,
"grad_norm": 0.6518163764831584,
"learning_rate": 0.0,
"loss": 0.6098,
"step": 156
},
{
"epoch": 2.980891719745223,
"step": 156,
"total_flos": 6.084353864735949e+16,
"train_loss": 0.7682466140160193,
"train_runtime": 1871.3915,
"train_samples_per_second": 8.017,
"train_steps_per_second": 0.083
}
],
"logging_steps": 1.0,
"max_steps": 156,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.084353864735949e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}