multisubject_compsci_mc / trainer_state.json
neginr's picture
End of training
ff7e785 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.955414012738854,
"eval_steps": 500,
"global_step": 364,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01910828025477707,
"grad_norm": 16.207577936529294,
"learning_rate": 5.405405405405406e-07,
"loss": 1.5883,
"step": 1
},
{
"epoch": 0.03821656050955414,
"grad_norm": 16.230231151699186,
"learning_rate": 1.0810810810810812e-06,
"loss": 1.5507,
"step": 2
},
{
"epoch": 0.05732484076433121,
"grad_norm": 16.762660353394043,
"learning_rate": 1.6216216216216219e-06,
"loss": 1.5822,
"step": 3
},
{
"epoch": 0.07643312101910828,
"grad_norm": 15.762795594875254,
"learning_rate": 2.1621621621621623e-06,
"loss": 1.5375,
"step": 4
},
{
"epoch": 0.09554140127388536,
"grad_norm": 14.06711681784781,
"learning_rate": 2.702702702702703e-06,
"loss": 1.4839,
"step": 5
},
{
"epoch": 0.11464968152866242,
"grad_norm": 12.490981158011854,
"learning_rate": 3.2432432432432437e-06,
"loss": 1.4123,
"step": 6
},
{
"epoch": 0.1337579617834395,
"grad_norm": 8.777964378285029,
"learning_rate": 3.7837837837837844e-06,
"loss": 1.2828,
"step": 7
},
{
"epoch": 0.15286624203821655,
"grad_norm": 7.7256263016456534,
"learning_rate": 4.324324324324325e-06,
"loss": 1.2497,
"step": 8
},
{
"epoch": 0.17197452229299362,
"grad_norm": 6.685288662005224,
"learning_rate": 4.864864864864866e-06,
"loss": 1.2233,
"step": 9
},
{
"epoch": 0.1910828025477707,
"grad_norm": 7.331907189555277,
"learning_rate": 5.405405405405406e-06,
"loss": 1.1612,
"step": 10
},
{
"epoch": 0.21019108280254778,
"grad_norm": 5.997175055735039,
"learning_rate": 5.945945945945947e-06,
"loss": 1.1161,
"step": 11
},
{
"epoch": 0.22929936305732485,
"grad_norm": 4.571983748158492,
"learning_rate": 6.486486486486487e-06,
"loss": 1.0614,
"step": 12
},
{
"epoch": 0.2484076433121019,
"grad_norm": 4.562958103868048,
"learning_rate": 7.027027027027028e-06,
"loss": 1.0143,
"step": 13
},
{
"epoch": 0.267515923566879,
"grad_norm": 5.499482262122252,
"learning_rate": 7.567567567567569e-06,
"loss": 0.9787,
"step": 14
},
{
"epoch": 0.28662420382165604,
"grad_norm": 5.124069500758053,
"learning_rate": 8.108108108108109e-06,
"loss": 0.9588,
"step": 15
},
{
"epoch": 0.3057324840764331,
"grad_norm": 4.148025737238825,
"learning_rate": 8.64864864864865e-06,
"loss": 0.9381,
"step": 16
},
{
"epoch": 0.3248407643312102,
"grad_norm": 2.7291692689575813,
"learning_rate": 9.189189189189191e-06,
"loss": 0.9492,
"step": 17
},
{
"epoch": 0.34394904458598724,
"grad_norm": 2.776890761322164,
"learning_rate": 9.729729729729732e-06,
"loss": 0.9234,
"step": 18
},
{
"epoch": 0.3630573248407643,
"grad_norm": 3.0168951061622344,
"learning_rate": 1.027027027027027e-05,
"loss": 0.921,
"step": 19
},
{
"epoch": 0.3821656050955414,
"grad_norm": 3.306312456821951,
"learning_rate": 1.0810810810810812e-05,
"loss": 0.8969,
"step": 20
},
{
"epoch": 0.4012738853503185,
"grad_norm": 2.5792665666577834,
"learning_rate": 1.1351351351351352e-05,
"loss": 0.8863,
"step": 21
},
{
"epoch": 0.42038216560509556,
"grad_norm": 1.9005562538642717,
"learning_rate": 1.1891891891891894e-05,
"loss": 0.8669,
"step": 22
},
{
"epoch": 0.4394904458598726,
"grad_norm": 2.251284284438843,
"learning_rate": 1.2432432432432433e-05,
"loss": 0.8793,
"step": 23
},
{
"epoch": 0.4585987261146497,
"grad_norm": 2.2277623219616434,
"learning_rate": 1.2972972972972975e-05,
"loss": 0.8425,
"step": 24
},
{
"epoch": 0.47770700636942676,
"grad_norm": 2.141589871208081,
"learning_rate": 1.3513513513513515e-05,
"loss": 0.8491,
"step": 25
},
{
"epoch": 0.4968152866242038,
"grad_norm": 2.027931686119723,
"learning_rate": 1.4054054054054055e-05,
"loss": 0.8538,
"step": 26
},
{
"epoch": 0.5159235668789809,
"grad_norm": 1.8301112334746343,
"learning_rate": 1.4594594594594596e-05,
"loss": 0.854,
"step": 27
},
{
"epoch": 0.535031847133758,
"grad_norm": 1.7691120873443633,
"learning_rate": 1.5135135135135138e-05,
"loss": 0.8456,
"step": 28
},
{
"epoch": 0.554140127388535,
"grad_norm": 1.6866307946704169,
"learning_rate": 1.5675675675675676e-05,
"loss": 0.8466,
"step": 29
},
{
"epoch": 0.5732484076433121,
"grad_norm": 1.6972756420973574,
"learning_rate": 1.6216216216216218e-05,
"loss": 0.8436,
"step": 30
},
{
"epoch": 0.5923566878980892,
"grad_norm": 1.6432569739538123,
"learning_rate": 1.6756756756756757e-05,
"loss": 0.7894,
"step": 31
},
{
"epoch": 0.6114649681528662,
"grad_norm": 1.854670403733654,
"learning_rate": 1.72972972972973e-05,
"loss": 0.8254,
"step": 32
},
{
"epoch": 0.6305732484076433,
"grad_norm": 1.64124439180178,
"learning_rate": 1.783783783783784e-05,
"loss": 0.8176,
"step": 33
},
{
"epoch": 0.6496815286624203,
"grad_norm": 1.7261180813219317,
"learning_rate": 1.8378378378378383e-05,
"loss": 0.8253,
"step": 34
},
{
"epoch": 0.6687898089171974,
"grad_norm": 1.619845522166602,
"learning_rate": 1.891891891891892e-05,
"loss": 0.815,
"step": 35
},
{
"epoch": 0.6878980891719745,
"grad_norm": 1.599927606949769,
"learning_rate": 1.9459459459459463e-05,
"loss": 0.7872,
"step": 36
},
{
"epoch": 0.7070063694267515,
"grad_norm": 1.7922176299227872,
"learning_rate": 2e-05,
"loss": 0.7935,
"step": 37
},
{
"epoch": 0.7261146496815286,
"grad_norm": 1.536007138312651,
"learning_rate": 1.9999538500851633e-05,
"loss": 0.8142,
"step": 38
},
{
"epoch": 0.7452229299363057,
"grad_norm": 1.6613731410993215,
"learning_rate": 1.9998154046002822e-05,
"loss": 0.822,
"step": 39
},
{
"epoch": 0.7643312101910829,
"grad_norm": 2.2532855017558195,
"learning_rate": 1.9995846763238514e-05,
"loss": 0.8162,
"step": 40
},
{
"epoch": 0.7834394904458599,
"grad_norm": 2.074212855804817,
"learning_rate": 1.9992616865520515e-05,
"loss": 0.7803,
"step": 41
},
{
"epoch": 0.802547770700637,
"grad_norm": 1.5058548913559864,
"learning_rate": 1.9988464650967834e-05,
"loss": 0.7997,
"step": 42
},
{
"epoch": 0.821656050955414,
"grad_norm": 1.8080159889460914,
"learning_rate": 1.9983390502829168e-05,
"loss": 0.8126,
"step": 43
},
{
"epoch": 0.8407643312101911,
"grad_norm": 1.618198273307259,
"learning_rate": 1.9977394889447526e-05,
"loss": 0.7781,
"step": 44
},
{
"epoch": 0.8598726114649682,
"grad_norm": 1.4264557820424202,
"learning_rate": 1.9970478364217e-05,
"loss": 0.8137,
"step": 45
},
{
"epoch": 0.8789808917197452,
"grad_norm": 1.6470566590256357,
"learning_rate": 1.9962641565531694e-05,
"loss": 0.8133,
"step": 46
},
{
"epoch": 0.8980891719745223,
"grad_norm": 1.447847475953182,
"learning_rate": 1.9953885216726788e-05,
"loss": 0.8048,
"step": 47
},
{
"epoch": 0.9171974522292994,
"grad_norm": 1.5787974396014408,
"learning_rate": 1.994421012601179e-05,
"loss": 0.7991,
"step": 48
},
{
"epoch": 0.9363057324840764,
"grad_norm": 1.5103267139592034,
"learning_rate": 1.9933617186395917e-05,
"loss": 0.7991,
"step": 49
},
{
"epoch": 0.9554140127388535,
"grad_norm": 1.3923044521351269,
"learning_rate": 1.99221073756057e-05,
"loss": 0.8025,
"step": 50
},
{
"epoch": 0.9745222929936306,
"grad_norm": 1.467958208632134,
"learning_rate": 1.990968175599471e-05,
"loss": 0.8108,
"step": 51
},
{
"epoch": 0.9936305732484076,
"grad_norm": 1.4703780581780375,
"learning_rate": 1.9896341474445526e-05,
"loss": 0.7862,
"step": 52
},
{
"epoch": 1.0127388535031847,
"grad_norm": 1.3469297799342106,
"learning_rate": 1.9882087762263857e-05,
"loss": 0.703,
"step": 53
},
{
"epoch": 1.0318471337579618,
"grad_norm": 1.5042329509547805,
"learning_rate": 1.9866921935064907e-05,
"loss": 0.6626,
"step": 54
},
{
"epoch": 1.0509554140127388,
"grad_norm": 1.393720796250388,
"learning_rate": 1.985084539265195e-05,
"loss": 0.6451,
"step": 55
},
{
"epoch": 1.070063694267516,
"grad_norm": 1.4037559400641226,
"learning_rate": 1.983385961888711e-05,
"loss": 0.5885,
"step": 56
},
{
"epoch": 1.089171974522293,
"grad_norm": 1.3525097928344776,
"learning_rate": 1.9815966181554412e-05,
"loss": 0.5928,
"step": 57
},
{
"epoch": 1.10828025477707,
"grad_norm": 1.4663292110903436,
"learning_rate": 1.9797166732215078e-05,
"loss": 0.5763,
"step": 58
},
{
"epoch": 1.127388535031847,
"grad_norm": 1.600751836606609,
"learning_rate": 1.977746300605507e-05,
"loss": 0.5754,
"step": 59
},
{
"epoch": 1.1464968152866242,
"grad_norm": 1.5837199956944725,
"learning_rate": 1.975685682172497e-05,
"loss": 0.5921,
"step": 60
},
{
"epoch": 1.1656050955414012,
"grad_norm": 1.5553081218046214,
"learning_rate": 1.973535008117207e-05,
"loss": 0.6176,
"step": 61
},
{
"epoch": 1.1847133757961783,
"grad_norm": 1.370254316271248,
"learning_rate": 1.9712944769464864e-05,
"loss": 0.5795,
"step": 62
},
{
"epoch": 1.2038216560509554,
"grad_norm": 1.5128484926324381,
"learning_rate": 1.9689642954609808e-05,
"loss": 0.6265,
"step": 63
},
{
"epoch": 1.2229299363057324,
"grad_norm": 1.6301580261980453,
"learning_rate": 1.9665446787360444e-05,
"loss": 0.5898,
"step": 64
},
{
"epoch": 1.2420382165605095,
"grad_norm": 1.367871159170793,
"learning_rate": 1.9640358501018885e-05,
"loss": 0.5458,
"step": 65
},
{
"epoch": 1.2611464968152866,
"grad_norm": 1.6545804449139618,
"learning_rate": 1.9614380411229693e-05,
"loss": 0.5681,
"step": 66
},
{
"epoch": 1.2802547770700636,
"grad_norm": 1.4134557013101863,
"learning_rate": 1.9587514915766124e-05,
"loss": 0.5665,
"step": 67
},
{
"epoch": 1.2993630573248407,
"grad_norm": 1.762211740513235,
"learning_rate": 1.9559764494308838e-05,
"loss": 0.5596,
"step": 68
},
{
"epoch": 1.3184713375796178,
"grad_norm": 1.69069319727097,
"learning_rate": 1.9531131708217005e-05,
"loss": 0.5844,
"step": 69
},
{
"epoch": 1.3375796178343948,
"grad_norm": 1.3995395125931538,
"learning_rate": 1.950161920029191e-05,
"loss": 0.5774,
"step": 70
},
{
"epoch": 1.356687898089172,
"grad_norm": 1.7282434635957937,
"learning_rate": 1.9471229694533003e-05,
"loss": 0.5738,
"step": 71
},
{
"epoch": 1.3757961783439492,
"grad_norm": 1.2784959217059895,
"learning_rate": 1.943996599588649e-05,
"loss": 0.59,
"step": 72
},
{
"epoch": 1.394904458598726,
"grad_norm": 1.2847919850285983,
"learning_rate": 1.940783098998643e-05,
"loss": 0.6056,
"step": 73
},
{
"epoch": 1.4140127388535033,
"grad_norm": 1.347161734736366,
"learning_rate": 1.93748276428884e-05,
"loss": 0.5491,
"step": 74
},
{
"epoch": 1.4331210191082802,
"grad_norm": 1.3959400214553517,
"learning_rate": 1.9340959000795707e-05,
"loss": 0.5982,
"step": 75
},
{
"epoch": 1.4522292993630574,
"grad_norm": 1.30264128607857,
"learning_rate": 1.9306228189778255e-05,
"loss": 0.5659,
"step": 76
},
{
"epoch": 1.4713375796178343,
"grad_norm": 1.3854931038782616,
"learning_rate": 1.927063841548398e-05,
"loss": 0.5501,
"step": 77
},
{
"epoch": 1.4904458598726116,
"grad_norm": 1.342352789440788,
"learning_rate": 1.9234192962842996e-05,
"loss": 0.5704,
"step": 78
},
{
"epoch": 1.5095541401273884,
"grad_norm": 1.4898768421021498,
"learning_rate": 1.9196895195764363e-05,
"loss": 0.6231,
"step": 79
},
{
"epoch": 1.5286624203821657,
"grad_norm": 1.3100235123413457,
"learning_rate": 1.9158748556825637e-05,
"loss": 0.5737,
"step": 80
},
{
"epoch": 1.5477707006369426,
"grad_norm": 1.3140747899036214,
"learning_rate": 1.9119756566955092e-05,
"loss": 0.5758,
"step": 81
},
{
"epoch": 1.5668789808917198,
"grad_norm": 1.1457878792947769,
"learning_rate": 1.907992282510675e-05,
"loss": 0.6008,
"step": 82
},
{
"epoch": 1.5859872611464967,
"grad_norm": 1.2806483267217852,
"learning_rate": 1.90392510079282e-05,
"loss": 0.5783,
"step": 83
},
{
"epoch": 1.605095541401274,
"grad_norm": 1.339094154523494,
"learning_rate": 1.8997744869421248e-05,
"loss": 0.5787,
"step": 84
},
{
"epoch": 1.6242038216560508,
"grad_norm": 1.4804989945217308,
"learning_rate": 1.8955408240595396e-05,
"loss": 0.6337,
"step": 85
},
{
"epoch": 1.643312101910828,
"grad_norm": 1.3722576915531601,
"learning_rate": 1.891224502911428e-05,
"loss": 0.5819,
"step": 86
},
{
"epoch": 1.662420382165605,
"grad_norm": 1.303374906577917,
"learning_rate": 1.886825921893497e-05,
"loss": 0.564,
"step": 87
},
{
"epoch": 1.6815286624203822,
"grad_norm": 1.3557245031901457,
"learning_rate": 1.8823454869940243e-05,
"loss": 0.5912,
"step": 88
},
{
"epoch": 1.700636942675159,
"grad_norm": 1.3659905279941662,
"learning_rate": 1.8777836117563894e-05,
"loss": 0.5729,
"step": 89
},
{
"epoch": 1.7197452229299364,
"grad_norm": 1.2228884554693173,
"learning_rate": 1.873140717240899e-05,
"loss": 0.6001,
"step": 90
},
{
"epoch": 1.7388535031847132,
"grad_norm": 1.2696589961480313,
"learning_rate": 1.8684172319859258e-05,
"loss": 0.6095,
"step": 91
},
{
"epoch": 1.7579617834394905,
"grad_norm": 1.288210734538388,
"learning_rate": 1.863613591968355e-05,
"loss": 0.6119,
"step": 92
},
{
"epoch": 1.7770700636942676,
"grad_norm": 1.4101820674772771,
"learning_rate": 1.858730240563342e-05,
"loss": 0.5596,
"step": 93
},
{
"epoch": 1.7961783439490446,
"grad_norm": 1.4868704394795493,
"learning_rate": 1.8537676285033886e-05,
"loss": 0.6112,
"step": 94
},
{
"epoch": 1.8152866242038217,
"grad_norm": 1.2615707287217766,
"learning_rate": 1.848726213836744e-05,
"loss": 0.5481,
"step": 95
},
{
"epoch": 1.8343949044585988,
"grad_norm": 1.4120088218938998,
"learning_rate": 1.8436064618851225e-05,
"loss": 0.574,
"step": 96
},
{
"epoch": 1.8535031847133758,
"grad_norm": 1.3872342324809461,
"learning_rate": 1.838408845200758e-05,
"loss": 0.5501,
"step": 97
},
{
"epoch": 1.872611464968153,
"grad_norm": 1.265935149100833,
"learning_rate": 1.8331338435227838e-05,
"loss": 0.5783,
"step": 98
},
{
"epoch": 1.89171974522293,
"grad_norm": 1.3615136971359445,
"learning_rate": 1.8277819437329577e-05,
"loss": 0.6018,
"step": 99
},
{
"epoch": 1.910828025477707,
"grad_norm": 1.2831355214080522,
"learning_rate": 1.8223536398107177e-05,
"loss": 0.5573,
"step": 100
},
{
"epoch": 1.929936305732484,
"grad_norm": 1.414983019094222,
"learning_rate": 1.8168494327875918e-05,
"loss": 0.5748,
"step": 101
},
{
"epoch": 1.9490445859872612,
"grad_norm": 1.2644989588144375,
"learning_rate": 1.8112698307009506e-05,
"loss": 0.5961,
"step": 102
},
{
"epoch": 1.9681528662420382,
"grad_norm": 1.3973089183381058,
"learning_rate": 1.8056153485471167e-05,
"loss": 0.6006,
"step": 103
},
{
"epoch": 1.9872611464968153,
"grad_norm": 1.245233746740617,
"learning_rate": 1.799886508233829e-05,
"loss": 0.5827,
"step": 104
},
{
"epoch": 2.0063694267515926,
"grad_norm": 1.3953137880450943,
"learning_rate": 1.7940838385320732e-05,
"loss": 0.4899,
"step": 105
},
{
"epoch": 2.0254777070063694,
"grad_norm": 1.2422344782506196,
"learning_rate": 1.788207875027274e-05,
"loss": 0.3823,
"step": 106
},
{
"epoch": 2.0445859872611467,
"grad_norm": 1.5194218407821385,
"learning_rate": 1.7822591600698632e-05,
"loss": 0.3707,
"step": 107
},
{
"epoch": 2.0636942675159236,
"grad_norm": 1.3858369380237823,
"learning_rate": 1.776238242725217e-05,
"loss": 0.3515,
"step": 108
},
{
"epoch": 2.082802547770701,
"grad_norm": 1.2040084839099645,
"learning_rate": 1.7701456787229805e-05,
"loss": 0.3351,
"step": 109
},
{
"epoch": 2.1019108280254777,
"grad_norm": 1.0813271075846485,
"learning_rate": 1.7639820304057745e-05,
"loss": 0.3682,
"step": 110
},
{
"epoch": 2.121019108280255,
"grad_norm": 1.1941413633816864,
"learning_rate": 1.7577478666772886e-05,
"loss": 0.347,
"step": 111
},
{
"epoch": 2.140127388535032,
"grad_norm": 1.2351647393004164,
"learning_rate": 1.751443762949772e-05,
"loss": 0.306,
"step": 112
},
{
"epoch": 2.159235668789809,
"grad_norm": 1.1577600566794273,
"learning_rate": 1.7450703010909263e-05,
"loss": 0.3544,
"step": 113
},
{
"epoch": 2.178343949044586,
"grad_norm": 1.139653261043234,
"learning_rate": 1.738628069370195e-05,
"loss": 0.3186,
"step": 114
},
{
"epoch": 2.1974522292993632,
"grad_norm": 1.1660921196049734,
"learning_rate": 1.732117662404469e-05,
"loss": 0.3264,
"step": 115
},
{
"epoch": 2.21656050955414,
"grad_norm": 1.2411659528086756,
"learning_rate": 1.7255396811032014e-05,
"loss": 0.3757,
"step": 116
},
{
"epoch": 2.2356687898089174,
"grad_norm": 1.0805464668608402,
"learning_rate": 1.718894732612947e-05,
"loss": 0.3388,
"step": 117
},
{
"epoch": 2.254777070063694,
"grad_norm": 1.077882198033458,
"learning_rate": 1.712183430261319e-05,
"loss": 0.3461,
"step": 118
},
{
"epoch": 2.2738853503184715,
"grad_norm": 1.0679311923670507,
"learning_rate": 1.7054063935003813e-05,
"loss": 0.343,
"step": 119
},
{
"epoch": 2.2929936305732483,
"grad_norm": 1.1845581622661834,
"learning_rate": 1.698564247849473e-05,
"loss": 0.3578,
"step": 120
},
{
"epoch": 2.3121019108280256,
"grad_norm": 1.1549978407787982,
"learning_rate": 1.691657624837472e-05,
"loss": 0.3338,
"step": 121
},
{
"epoch": 2.3312101910828025,
"grad_norm": 1.1992184381026434,
"learning_rate": 1.684687161944506e-05,
"loss": 0.3513,
"step": 122
},
{
"epoch": 2.3503184713375798,
"grad_norm": 1.1870994342333885,
"learning_rate": 1.677653502543113e-05,
"loss": 0.3774,
"step": 123
},
{
"epoch": 2.3694267515923566,
"grad_norm": 1.1727869438510825,
"learning_rate": 1.6705572958388576e-05,
"loss": 0.366,
"step": 124
},
{
"epoch": 2.388535031847134,
"grad_norm": 1.137731691236232,
"learning_rate": 1.6633991968104095e-05,
"loss": 0.3268,
"step": 125
},
{
"epoch": 2.4076433121019107,
"grad_norm": 1.061973314666275,
"learning_rate": 1.6561798661490904e-05,
"loss": 0.3329,
"step": 126
},
{
"epoch": 2.426751592356688,
"grad_norm": 1.084312908045151,
"learning_rate": 1.6488999701978905e-05,
"loss": 0.367,
"step": 127
},
{
"epoch": 2.445859872611465,
"grad_norm": 1.14305018626842,
"learning_rate": 1.6415601808899658e-05,
"loss": 0.2974,
"step": 128
},
{
"epoch": 2.464968152866242,
"grad_norm": 1.157749585944929,
"learning_rate": 1.63416117568662e-05,
"loss": 0.3347,
"step": 129
},
{
"epoch": 2.484076433121019,
"grad_norm": 1.0864100134349601,
"learning_rate": 1.6267036375147728e-05,
"loss": 0.336,
"step": 130
},
{
"epoch": 2.5031847133757963,
"grad_norm": 1.140281558684133,
"learning_rate": 1.619188254703927e-05,
"loss": 0.3083,
"step": 131
},
{
"epoch": 2.522292993630573,
"grad_norm": 1.0816276956540412,
"learning_rate": 1.6116157209226356e-05,
"loss": 0.3366,
"step": 132
},
{
"epoch": 2.5414012738853504,
"grad_norm": 1.0325317959119171,
"learning_rate": 1.6039867351144778e-05,
"loss": 0.3719,
"step": 133
},
{
"epoch": 2.5605095541401273,
"grad_norm": 1.210569091837068,
"learning_rate": 1.5963020014335437e-05,
"loss": 0.3283,
"step": 134
},
{
"epoch": 2.5796178343949046,
"grad_norm": 1.1318710036112303,
"learning_rate": 1.588562229179443e-05,
"loss": 0.3597,
"step": 135
},
{
"epoch": 2.5987261146496814,
"grad_norm": 1.209379497308929,
"learning_rate": 1.5807681327318372e-05,
"loss": 0.361,
"step": 136
},
{
"epoch": 2.6178343949044587,
"grad_norm": 1.1460305712676861,
"learning_rate": 1.5729204314845002e-05,
"loss": 0.3604,
"step": 137
},
{
"epoch": 2.6369426751592355,
"grad_norm": 1.1732165904010456,
"learning_rate": 1.56501984977892e-05,
"loss": 0.3523,
"step": 138
},
{
"epoch": 2.656050955414013,
"grad_norm": 1.1621107710443261,
"learning_rate": 1.557067116837444e-05,
"loss": 0.299,
"step": 139
},
{
"epoch": 2.6751592356687897,
"grad_norm": 1.2164346262777883,
"learning_rate": 1.5490629666959668e-05,
"loss": 0.3457,
"step": 140
},
{
"epoch": 2.694267515923567,
"grad_norm": 1.1823153475333987,
"learning_rate": 1.541008138136183e-05,
"loss": 0.3444,
"step": 141
},
{
"epoch": 2.713375796178344,
"grad_norm": 1.1174073949760772,
"learning_rate": 1.5329033746173975e-05,
"loss": 0.3729,
"step": 142
},
{
"epoch": 2.732484076433121,
"grad_norm": 1.1314239511081268,
"learning_rate": 1.5247494242079024e-05,
"loss": 0.326,
"step": 143
},
{
"epoch": 2.7515923566878984,
"grad_norm": 1.1174177994358805,
"learning_rate": 1.5165470395159314e-05,
"loss": 0.3256,
"step": 144
},
{
"epoch": 2.770700636942675,
"grad_norm": 1.219689897297813,
"learning_rate": 1.5082969776201948e-05,
"loss": 0.3161,
"step": 145
},
{
"epoch": 2.789808917197452,
"grad_norm": 1.0765986737838706,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.3379,
"step": 146
},
{
"epoch": 2.8089171974522293,
"grad_norm": 1.1077246642654066,
"learning_rate": 1.4916568724649688e-05,
"loss": 0.3501,
"step": 147
},
{
"epoch": 2.8280254777070066,
"grad_norm": 1.2638295093687193,
"learning_rate": 1.483268365084351e-05,
"loss": 0.3216,
"step": 148
},
{
"epoch": 2.8471337579617835,
"grad_norm": 1.125839857498556,
"learning_rate": 1.4748352521159492e-05,
"loss": 0.3653,
"step": 149
},
{
"epoch": 2.8662420382165603,
"grad_norm": 1.081095422354445,
"learning_rate": 1.466358311934654e-05,
"loss": 0.3613,
"step": 150
},
{
"epoch": 2.8853503184713376,
"grad_norm": 1.2431757494407534,
"learning_rate": 1.4578383269606004e-05,
"loss": 0.3194,
"step": 151
},
{
"epoch": 2.904458598726115,
"grad_norm": 1.0554692013448208,
"learning_rate": 1.4492760835869504e-05,
"loss": 0.3425,
"step": 152
},
{
"epoch": 2.9235668789808917,
"grad_norm": 1.0106608052986603,
"learning_rate": 1.4406723721073088e-05,
"loss": 0.3483,
"step": 153
},
{
"epoch": 2.9426751592356686,
"grad_norm": 1.0489479689551857,
"learning_rate": 1.4320279866427798e-05,
"loss": 0.3504,
"step": 154
},
{
"epoch": 2.961783439490446,
"grad_norm": 1.0761618786744391,
"learning_rate": 1.4233437250686695e-05,
"loss": 0.3707,
"step": 155
},
{
"epoch": 2.980891719745223,
"grad_norm": 1.157018379192101,
"learning_rate": 1.4146203889408418e-05,
"loss": 0.3321,
"step": 156
},
{
"epoch": 3.0,
"grad_norm": 1.0533667581883366,
"learning_rate": 1.4058587834217356e-05,
"loss": 0.3053,
"step": 157
},
{
"epoch": 3.0191082802547773,
"grad_norm": 1.0547313417924546,
"learning_rate": 1.3970597172060482e-05,
"loss": 0.2188,
"step": 158
},
{
"epoch": 3.038216560509554,
"grad_norm": 0.930934263644112,
"learning_rate": 1.3882240024460928e-05,
"loss": 0.1843,
"step": 159
},
{
"epoch": 3.0573248407643314,
"grad_norm": 0.983478027637516,
"learning_rate": 1.3793524546768358e-05,
"loss": 0.201,
"step": 160
},
{
"epoch": 3.0764331210191083,
"grad_norm": 1.2407814520098055,
"learning_rate": 1.3704458927406261e-05,
"loss": 0.2039,
"step": 161
},
{
"epoch": 3.0955414012738856,
"grad_norm": 1.2647200327067536,
"learning_rate": 1.3615051387116131e-05,
"loss": 0.2,
"step": 162
},
{
"epoch": 3.1146496815286624,
"grad_norm": 0.9644590953094815,
"learning_rate": 1.3525310178198707e-05,
"loss": 0.2408,
"step": 163
},
{
"epoch": 3.1337579617834397,
"grad_norm": 0.9190602503630407,
"learning_rate": 1.3435243583752294e-05,
"loss": 0.2229,
"step": 164
},
{
"epoch": 3.1528662420382165,
"grad_norm": 0.9243907234468131,
"learning_rate": 1.3344859916908206e-05,
"loss": 0.2032,
"step": 165
},
{
"epoch": 3.171974522292994,
"grad_norm": 0.9442060532851655,
"learning_rate": 1.325416752006351e-05,
"loss": 0.2025,
"step": 166
},
{
"epoch": 3.1910828025477707,
"grad_norm": 0.963218763581881,
"learning_rate": 1.3163174764110985e-05,
"loss": 0.1829,
"step": 167
},
{
"epoch": 3.210191082802548,
"grad_norm": 0.9071743366026043,
"learning_rate": 1.3071890047666498e-05,
"loss": 0.227,
"step": 168
},
{
"epoch": 3.229299363057325,
"grad_norm": 1.0315900230652744,
"learning_rate": 1.2980321796293838e-05,
"loss": 0.2156,
"step": 169
},
{
"epoch": 3.248407643312102,
"grad_norm": 1.0187692244394628,
"learning_rate": 1.288847846172701e-05,
"loss": 0.2216,
"step": 170
},
{
"epoch": 3.267515923566879,
"grad_norm": 0.9225592237396303,
"learning_rate": 1.2796368521090143e-05,
"loss": 0.2107,
"step": 171
},
{
"epoch": 3.286624203821656,
"grad_norm": 0.8748399197222058,
"learning_rate": 1.2704000476115079e-05,
"loss": 0.2395,
"step": 172
},
{
"epoch": 3.305732484076433,
"grad_norm": 0.8746681159163586,
"learning_rate": 1.2611382852356632e-05,
"loss": 0.2083,
"step": 173
},
{
"epoch": 3.3248407643312103,
"grad_norm": 0.8888551584950397,
"learning_rate": 1.2518524198405699e-05,
"loss": 0.2076,
"step": 174
},
{
"epoch": 3.343949044585987,
"grad_norm": 0.9463638003097762,
"learning_rate": 1.2425433085100224e-05,
"loss": 0.1926,
"step": 175
},
{
"epoch": 3.3630573248407645,
"grad_norm": 0.9111688438287611,
"learning_rate": 1.233211810473411e-05,
"loss": 0.2096,
"step": 176
},
{
"epoch": 3.3821656050955413,
"grad_norm": 0.923419758792075,
"learning_rate": 1.2238587870264152e-05,
"loss": 0.1926,
"step": 177
},
{
"epoch": 3.4012738853503186,
"grad_norm": 0.946486281258778,
"learning_rate": 1.2144851014515055e-05,
"loss": 0.194,
"step": 178
},
{
"epoch": 3.4203821656050954,
"grad_norm": 0.892594471211745,
"learning_rate": 1.2050916189382646e-05,
"loss": 0.2237,
"step": 179
},
{
"epoch": 3.4394904458598727,
"grad_norm": 0.9130234965474789,
"learning_rate": 1.1956792065035281e-05,
"loss": 0.1652,
"step": 180
},
{
"epoch": 3.4585987261146496,
"grad_norm": 0.8769940165131497,
"learning_rate": 1.1862487329113606e-05,
"loss": 0.239,
"step": 181
},
{
"epoch": 3.477707006369427,
"grad_norm": 0.9228491362173967,
"learning_rate": 1.1768010685928686e-05,
"loss": 0.1775,
"step": 182
},
{
"epoch": 3.4968152866242037,
"grad_norm": 0.8281719893074526,
"learning_rate": 1.1673370855658592e-05,
"loss": 0.2222,
"step": 183
},
{
"epoch": 3.515923566878981,
"grad_norm": 0.8788653643194168,
"learning_rate": 1.1578576573543541e-05,
"loss": 0.1812,
"step": 184
},
{
"epoch": 3.535031847133758,
"grad_norm": 0.869849366163653,
"learning_rate": 1.1483636589079627e-05,
"loss": 0.1933,
"step": 185
},
{
"epoch": 3.554140127388535,
"grad_norm": 0.8998889330605255,
"learning_rate": 1.1388559665211241e-05,
"loss": 0.2232,
"step": 186
},
{
"epoch": 3.573248407643312,
"grad_norm": 0.8751652390981322,
"learning_rate": 1.1293354577522264e-05,
"loss": 0.2141,
"step": 187
},
{
"epoch": 3.5923566878980893,
"grad_norm": 0.8626223839515736,
"learning_rate": 1.1198030113426074e-05,
"loss": 0.1982,
"step": 188
},
{
"epoch": 3.611464968152866,
"grad_norm": 0.8499479463433588,
"learning_rate": 1.1102595071354471e-05,
"loss": 0.18,
"step": 189
},
{
"epoch": 3.6305732484076434,
"grad_norm": 0.9117331474207767,
"learning_rate": 1.1007058259945584e-05,
"loss": 0.228,
"step": 190
},
{
"epoch": 3.6496815286624202,
"grad_norm": 0.7897026778368444,
"learning_rate": 1.0911428497230834e-05,
"loss": 0.2184,
"step": 191
},
{
"epoch": 3.6687898089171975,
"grad_norm": 0.8366867452316553,
"learning_rate": 1.0815714609821027e-05,
"loss": 0.2053,
"step": 192
},
{
"epoch": 3.6878980891719744,
"grad_norm": 0.8587082513394615,
"learning_rate": 1.0719925432091671e-05,
"loss": 0.208,
"step": 193
},
{
"epoch": 3.7070063694267517,
"grad_norm": 0.8675289819107732,
"learning_rate": 1.0624069805367558e-05,
"loss": 0.2075,
"step": 194
},
{
"epoch": 3.7261146496815285,
"grad_norm": 0.8618107937937802,
"learning_rate": 1.0528156577106703e-05,
"loss": 0.2136,
"step": 195
},
{
"epoch": 3.745222929936306,
"grad_norm": 0.8379198429484322,
"learning_rate": 1.043219460008374e-05,
"loss": 0.2306,
"step": 196
},
{
"epoch": 3.7643312101910826,
"grad_norm": 0.8491037924292353,
"learning_rate": 1.0336192731572805e-05,
"loss": 0.1892,
"step": 197
},
{
"epoch": 3.78343949044586,
"grad_norm": 0.8631451283341048,
"learning_rate": 1.0240159832530007e-05,
"loss": 0.2007,
"step": 198
},
{
"epoch": 3.802547770700637,
"grad_norm": 0.892801565631552,
"learning_rate": 1.0144104766775574e-05,
"loss": 0.2022,
"step": 199
},
{
"epoch": 3.821656050955414,
"grad_norm": 0.8581598389309619,
"learning_rate": 1.004803640017571e-05,
"loss": 0.1823,
"step": 200
},
{
"epoch": 3.840764331210191,
"grad_norm": 0.8570289033219508,
"learning_rate": 9.951963599824294e-06,
"loss": 0.2201,
"step": 201
},
{
"epoch": 3.859872611464968,
"grad_norm": 0.860535004343562,
"learning_rate": 9.855895233224431e-06,
"loss": 0.2381,
"step": 202
},
{
"epoch": 3.8789808917197455,
"grad_norm": 0.880171224866928,
"learning_rate": 9.759840167469995e-06,
"loss": 0.159,
"step": 203
},
{
"epoch": 3.8980891719745223,
"grad_norm": 0.8998977132258694,
"learning_rate": 9.663807268427197e-06,
"loss": 0.2114,
"step": 204
},
{
"epoch": 3.917197452229299,
"grad_norm": 0.944910434342897,
"learning_rate": 9.56780539991626e-06,
"loss": 0.1834,
"step": 205
},
{
"epoch": 3.9363057324840764,
"grad_norm": 0.888128708062558,
"learning_rate": 9.471843422893299e-06,
"loss": 0.2224,
"step": 206
},
{
"epoch": 3.9554140127388537,
"grad_norm": 0.8574141414851673,
"learning_rate": 9.375930194632447e-06,
"loss": 0.1822,
"step": 207
},
{
"epoch": 3.9745222929936306,
"grad_norm": 0.8258326063326947,
"learning_rate": 9.28007456790833e-06,
"loss": 0.2582,
"step": 208
},
{
"epoch": 3.9936305732484074,
"grad_norm": 0.8702456676005106,
"learning_rate": 9.184285390178978e-06,
"loss": 0.1941,
"step": 209
},
{
"epoch": 4.012738853503185,
"grad_norm": 0.6419823328435715,
"learning_rate": 9.08857150276917e-06,
"loss": 0.1618,
"step": 210
},
{
"epoch": 4.031847133757962,
"grad_norm": 0.7013125447364849,
"learning_rate": 8.992941740054418e-06,
"loss": 0.1326,
"step": 211
},
{
"epoch": 4.050955414012739,
"grad_norm": 0.6282089961157545,
"learning_rate": 8.897404928645529e-06,
"loss": 0.1239,
"step": 212
},
{
"epoch": 4.070063694267516,
"grad_norm": 0.63559224911429,
"learning_rate": 8.80196988657393e-06,
"loss": 0.1174,
"step": 213
},
{
"epoch": 4.089171974522293,
"grad_norm": 0.744688936893004,
"learning_rate": 8.706645422477739e-06,
"loss": 0.1459,
"step": 214
},
{
"epoch": 4.10828025477707,
"grad_norm": 0.7641003977764952,
"learning_rate": 8.611440334788762e-06,
"loss": 0.1365,
"step": 215
},
{
"epoch": 4.127388535031847,
"grad_norm": 0.8312252860589785,
"learning_rate": 8.516363410920376e-06,
"loss": 0.1055,
"step": 216
},
{
"epoch": 4.146496815286624,
"grad_norm": 0.7705703082497701,
"learning_rate": 8.42142342645646e-06,
"loss": 0.1167,
"step": 217
},
{
"epoch": 4.165605095541402,
"grad_norm": 0.6820769471933187,
"learning_rate": 8.326629144341408e-06,
"loss": 0.1091,
"step": 218
},
{
"epoch": 4.1847133757961785,
"grad_norm": 0.6177823284633078,
"learning_rate": 8.231989314071318e-06,
"loss": 0.108,
"step": 219
},
{
"epoch": 4.203821656050955,
"grad_norm": 0.6334985610396245,
"learning_rate": 8.137512670886397e-06,
"loss": 0.1358,
"step": 220
},
{
"epoch": 4.222929936305732,
"grad_norm": 0.6487652927915302,
"learning_rate": 8.043207934964722e-06,
"loss": 0.1323,
"step": 221
},
{
"epoch": 4.24203821656051,
"grad_norm": 0.6861755433216611,
"learning_rate": 7.949083810617358e-06,
"loss": 0.1203,
"step": 222
},
{
"epoch": 4.261146496815287,
"grad_norm": 0.6070051869465705,
"learning_rate": 7.855148985484946e-06,
"loss": 0.1198,
"step": 223
},
{
"epoch": 4.280254777070064,
"grad_norm": 0.672669819013237,
"learning_rate": 7.761412129735853e-06,
"loss": 0.1328,
"step": 224
},
{
"epoch": 4.2993630573248405,
"grad_norm": 0.6363832766423693,
"learning_rate": 7.667881895265895e-06,
"loss": 0.099,
"step": 225
},
{
"epoch": 4.318471337579618,
"grad_norm": 0.6521275103263113,
"learning_rate": 7.574566914899779e-06,
"loss": 0.1268,
"step": 226
},
{
"epoch": 4.337579617834395,
"grad_norm": 0.6488602770991176,
"learning_rate": 7.481475801594302e-06,
"loss": 0.1164,
"step": 227
},
{
"epoch": 4.356687898089172,
"grad_norm": 0.6579781306485809,
"learning_rate": 7.388617147643371e-06,
"loss": 0.1194,
"step": 228
},
{
"epoch": 4.375796178343949,
"grad_norm": 0.6341477387146806,
"learning_rate": 7.295999523884921e-06,
"loss": 0.1316,
"step": 229
},
{
"epoch": 4.3949044585987265,
"grad_norm": 0.6580995643113278,
"learning_rate": 7.203631478909857e-06,
"loss": 0.129,
"step": 230
},
{
"epoch": 4.414012738853503,
"grad_norm": 0.6606683663693255,
"learning_rate": 7.111521538272997e-06,
"loss": 0.1526,
"step": 231
},
{
"epoch": 4.43312101910828,
"grad_norm": 0.6353533372696129,
"learning_rate": 7.019678203706164e-06,
"loss": 0.1217,
"step": 232
},
{
"epoch": 4.452229299363057,
"grad_norm": 0.6492987875417681,
"learning_rate": 6.928109952333506e-06,
"loss": 0.1308,
"step": 233
},
{
"epoch": 4.471337579617835,
"grad_norm": 0.5683739215865904,
"learning_rate": 6.83682523588902e-06,
"loss": 0.141,
"step": 234
},
{
"epoch": 4.490445859872612,
"grad_norm": 0.5969068164655831,
"learning_rate": 6.745832479936492e-06,
"loss": 0.1076,
"step": 235
},
{
"epoch": 4.509554140127388,
"grad_norm": 0.5935296810482609,
"learning_rate": 6.655140083091794e-06,
"loss": 0.1093,
"step": 236
},
{
"epoch": 4.528662420382165,
"grad_norm": 0.6141503156568103,
"learning_rate": 6.564756416247712e-06,
"loss": 0.1121,
"step": 237
},
{
"epoch": 4.547770700636943,
"grad_norm": 0.606512092804129,
"learning_rate": 6.474689821801295e-06,
"loss": 0.1194,
"step": 238
},
{
"epoch": 4.56687898089172,
"grad_norm": 0.5946851091687231,
"learning_rate": 6.384948612883872e-06,
"loss": 0.1048,
"step": 239
},
{
"epoch": 4.585987261146497,
"grad_norm": 0.6401167422534727,
"learning_rate": 6.2955410725937405e-06,
"loss": 0.1336,
"step": 240
},
{
"epoch": 4.6050955414012735,
"grad_norm": 0.6295133570230956,
"learning_rate": 6.206475453231644e-06,
"loss": 0.1158,
"step": 241
},
{
"epoch": 4.624203821656051,
"grad_norm": 0.6158966292962275,
"learning_rate": 6.117759975539075e-06,
"loss": 0.1252,
"step": 242
},
{
"epoch": 4.643312101910828,
"grad_norm": 0.6115229159056143,
"learning_rate": 6.029402827939519e-06,
"loss": 0.1481,
"step": 243
},
{
"epoch": 4.662420382165605,
"grad_norm": 0.5877582785702361,
"learning_rate": 5.941412165782645e-06,
"loss": 0.1233,
"step": 244
},
{
"epoch": 4.681528662420382,
"grad_norm": 0.575927739748183,
"learning_rate": 5.853796110591583e-06,
"loss": 0.1145,
"step": 245
},
{
"epoch": 4.7006369426751595,
"grad_norm": 0.5798796204817728,
"learning_rate": 5.766562749313309e-06,
"loss": 0.1095,
"step": 246
},
{
"epoch": 4.719745222929936,
"grad_norm": 0.5667423982047629,
"learning_rate": 5.6797201335722064e-06,
"loss": 0.1039,
"step": 247
},
{
"epoch": 4.738853503184713,
"grad_norm": 0.5900922967570229,
"learning_rate": 5.593276278926912e-06,
"loss": 0.1166,
"step": 248
},
{
"epoch": 4.757961783439491,
"grad_norm": 0.5987524140989823,
"learning_rate": 5.507239164130501e-06,
"loss": 0.1434,
"step": 249
},
{
"epoch": 4.777070063694268,
"grad_norm": 0.5668228735032542,
"learning_rate": 5.421616730394e-06,
"loss": 0.1203,
"step": 250
},
{
"epoch": 4.796178343949045,
"grad_norm": 0.6042014069032966,
"learning_rate": 5.336416880653461e-06,
"loss": 0.1192,
"step": 251
},
{
"epoch": 4.8152866242038215,
"grad_norm": 0.6119673045706518,
"learning_rate": 5.251647478840511e-06,
"loss": 0.1049,
"step": 252
},
{
"epoch": 4.834394904458598,
"grad_norm": 0.6047175720281526,
"learning_rate": 5.167316349156495e-06,
"loss": 0.1067,
"step": 253
},
{
"epoch": 4.853503184713376,
"grad_norm": 0.5864037008649898,
"learning_rate": 5.083431275350312e-06,
"loss": 0.1324,
"step": 254
},
{
"epoch": 4.872611464968153,
"grad_norm": 0.6234019198830574,
"learning_rate": 5.000000000000003e-06,
"loss": 0.1016,
"step": 255
},
{
"epoch": 4.89171974522293,
"grad_norm": 0.5973842089783172,
"learning_rate": 4.917030223798057e-06,
"loss": 0.1238,
"step": 256
},
{
"epoch": 4.9108280254777075,
"grad_norm": 0.5421130895514578,
"learning_rate": 4.834529604840686e-06,
"loss": 0.1068,
"step": 257
},
{
"epoch": 4.929936305732484,
"grad_norm": 0.5748700997816383,
"learning_rate": 4.7525057579209775e-06,
"loss": 0.1093,
"step": 258
},
{
"epoch": 4.949044585987261,
"grad_norm": 0.6353485915241656,
"learning_rate": 4.670966253826027e-06,
"loss": 0.1179,
"step": 259
},
{
"epoch": 4.968152866242038,
"grad_norm": 0.59089915427817,
"learning_rate": 4.589918618638173e-06,
"loss": 0.1397,
"step": 260
},
{
"epoch": 4.987261146496815,
"grad_norm": 0.5876648737817116,
"learning_rate": 4.5093703330403385e-06,
"loss": 0.121,
"step": 261
},
{
"epoch": 5.006369426751593,
"grad_norm": 0.500425847147982,
"learning_rate": 4.429328831625565e-06,
"loss": 0.1088,
"step": 262
},
{
"epoch": 5.025477707006369,
"grad_norm": 0.4173760948587404,
"learning_rate": 4.349801502210801e-06,
"loss": 0.0692,
"step": 263
},
{
"epoch": 5.044585987261146,
"grad_norm": 0.45131347307487774,
"learning_rate": 4.270795685155001e-06,
"loss": 0.1,
"step": 264
},
{
"epoch": 5.063694267515924,
"grad_norm": 0.40406972837102645,
"learning_rate": 4.192318672681631e-06,
"loss": 0.088,
"step": 265
},
{
"epoch": 5.082802547770701,
"grad_norm": 0.38068965606156097,
"learning_rate": 4.1143777082055715e-06,
"loss": 0.0632,
"step": 266
},
{
"epoch": 5.101910828025478,
"grad_norm": 0.4033571835311679,
"learning_rate": 4.036979985664566e-06,
"loss": 0.0785,
"step": 267
},
{
"epoch": 5.1210191082802545,
"grad_norm": 0.4003438449286176,
"learning_rate": 3.960132648855226e-06,
"loss": 0.0807,
"step": 268
},
{
"epoch": 5.140127388535032,
"grad_norm": 0.4610641419364593,
"learning_rate": 3.883842790773647e-06,
"loss": 0.0743,
"step": 269
},
{
"epoch": 5.159235668789809,
"grad_norm": 0.46772011723957047,
"learning_rate": 3.8081174529607346e-06,
"loss": 0.083,
"step": 270
},
{
"epoch": 5.178343949044586,
"grad_norm": 0.48469156213513115,
"learning_rate": 3.732963624852275e-06,
"loss": 0.0688,
"step": 271
},
{
"epoch": 5.197452229299363,
"grad_norm": 0.4097707650542374,
"learning_rate": 3.6583882431338047e-06,
"loss": 0.0732,
"step": 272
},
{
"epoch": 5.2165605095541405,
"grad_norm": 0.41662851225355924,
"learning_rate": 3.584398191100341e-06,
"loss": 0.0794,
"step": 273
},
{
"epoch": 5.235668789808917,
"grad_norm": 0.5142480756247851,
"learning_rate": 3.511000298021098e-06,
"loss": 0.0987,
"step": 274
},
{
"epoch": 5.254777070063694,
"grad_norm": 0.4435030725498896,
"learning_rate": 3.4382013385090985e-06,
"loss": 0.0519,
"step": 275
},
{
"epoch": 5.273885350318471,
"grad_norm": 0.45114056016762916,
"learning_rate": 3.3660080318959043e-06,
"loss": 0.1122,
"step": 276
},
{
"epoch": 5.292993630573249,
"grad_norm": 0.4602596362040264,
"learning_rate": 3.2944270416114256e-06,
"loss": 0.074,
"step": 277
},
{
"epoch": 5.312101910828026,
"grad_norm": 0.4215918278487679,
"learning_rate": 3.223464974568874e-06,
"loss": 0.0714,
"step": 278
},
{
"epoch": 5.3312101910828025,
"grad_norm": 0.37639160238215197,
"learning_rate": 3.153128380554941e-06,
"loss": 0.0709,
"step": 279
},
{
"epoch": 5.350318471337579,
"grad_norm": 0.42709349372212563,
"learning_rate": 3.0834237516252817e-06,
"loss": 0.0888,
"step": 280
},
{
"epoch": 5.369426751592357,
"grad_norm": 0.38376449225454184,
"learning_rate": 3.0143575215052732e-06,
"loss": 0.0738,
"step": 281
},
{
"epoch": 5.388535031847134,
"grad_norm": 0.37353723261024324,
"learning_rate": 2.94593606499619e-06,
"loss": 0.1008,
"step": 282
},
{
"epoch": 5.407643312101911,
"grad_norm": 0.4023560034782532,
"learning_rate": 2.878165697386812e-06,
"loss": 0.0812,
"step": 283
},
{
"epoch": 5.426751592356688,
"grad_norm": 0.452345994244169,
"learning_rate": 2.8110526738705345e-06,
"loss": 0.0869,
"step": 284
},
{
"epoch": 5.445859872611465,
"grad_norm": 0.41655876492240235,
"learning_rate": 2.7446031889679893e-06,
"loss": 0.0931,
"step": 285
},
{
"epoch": 5.464968152866242,
"grad_norm": 0.40303769880729684,
"learning_rate": 2.678823375955314e-06,
"loss": 0.0656,
"step": 286
},
{
"epoch": 5.484076433121019,
"grad_norm": 0.3736703542936502,
"learning_rate": 2.6137193062980506e-06,
"loss": 0.0954,
"step": 287
},
{
"epoch": 5.503184713375796,
"grad_norm": 0.3610101674372163,
"learning_rate": 2.5492969890907383e-06,
"loss": 0.0701,
"step": 288
},
{
"epoch": 5.522292993630574,
"grad_norm": 0.3974548348249396,
"learning_rate": 2.485562370502279e-06,
"loss": 0.1008,
"step": 289
},
{
"epoch": 5.54140127388535,
"grad_norm": 0.4075609990175683,
"learning_rate": 2.4225213332271203e-06,
"loss": 0.0752,
"step": 290
},
{
"epoch": 5.560509554140127,
"grad_norm": 0.41207353791669765,
"learning_rate": 2.3601796959422585e-06,
"loss": 0.09,
"step": 291
},
{
"epoch": 5.579617834394904,
"grad_norm": 0.4197933372931118,
"learning_rate": 2.2985432127701945e-06,
"loss": 0.1096,
"step": 292
},
{
"epoch": 5.598726114649682,
"grad_norm": 0.3970630962450117,
"learning_rate": 2.2376175727478346e-06,
"loss": 0.0831,
"step": 293
},
{
"epoch": 5.617834394904459,
"grad_norm": 0.4233872661264893,
"learning_rate": 2.1774083993013715e-06,
"loss": 0.0899,
"step": 294
},
{
"epoch": 5.6369426751592355,
"grad_norm": 0.45476349355512374,
"learning_rate": 2.1179212497272582e-06,
"loss": 0.0844,
"step": 295
},
{
"epoch": 5.656050955414012,
"grad_norm": 0.3652938444091257,
"learning_rate": 2.0591616146792705e-06,
"loss": 0.0638,
"step": 296
},
{
"epoch": 5.67515923566879,
"grad_norm": 0.4198343795853902,
"learning_rate": 2.0011349176617133e-06,
"loss": 0.0987,
"step": 297
},
{
"epoch": 5.694267515923567,
"grad_norm": 0.4637461724517846,
"learning_rate": 1.9438465145288377e-06,
"loss": 0.0857,
"step": 298
},
{
"epoch": 5.713375796178344,
"grad_norm": 0.41439129316088197,
"learning_rate": 1.8873016929904942e-06,
"loss": 0.0981,
"step": 299
},
{
"epoch": 5.732484076433121,
"grad_norm": 0.399364720681734,
"learning_rate": 1.8315056721240831e-06,
"loss": 0.0661,
"step": 300
},
{
"epoch": 5.751592356687898,
"grad_norm": 0.3592826811293026,
"learning_rate": 1.7764636018928249e-06,
"loss": 0.0743,
"step": 301
},
{
"epoch": 5.770700636942675,
"grad_norm": 0.3747827275166178,
"learning_rate": 1.722180562670428e-06,
"loss": 0.061,
"step": 302
},
{
"epoch": 5.789808917197452,
"grad_norm": 0.42899694389637955,
"learning_rate": 1.6686615647721638e-06,
"loss": 0.0812,
"step": 303
},
{
"epoch": 5.80891719745223,
"grad_norm": 0.3890663817302002,
"learning_rate": 1.6159115479924259e-06,
"loss": 0.0918,
"step": 304
},
{
"epoch": 5.828025477707007,
"grad_norm": 0.39746898582488294,
"learning_rate": 1.5639353811487744e-06,
"loss": 0.0825,
"step": 305
},
{
"epoch": 5.8471337579617835,
"grad_norm": 0.3899707969607275,
"learning_rate": 1.5127378616325606e-06,
"loss": 0.1,
"step": 306
},
{
"epoch": 5.86624203821656,
"grad_norm": 0.3878767177963925,
"learning_rate": 1.462323714966114e-06,
"loss": 0.0974,
"step": 307
},
{
"epoch": 5.885350318471337,
"grad_norm": 0.36936598310841057,
"learning_rate": 1.4126975943665844e-06,
"loss": 0.0639,
"step": 308
},
{
"epoch": 5.904458598726115,
"grad_norm": 0.42012980899969893,
"learning_rate": 1.3638640803164516e-06,
"loss": 0.1117,
"step": 309
},
{
"epoch": 5.923566878980892,
"grad_norm": 0.3805627255371633,
"learning_rate": 1.3158276801407432e-06,
"loss": 0.0695,
"step": 310
},
{
"epoch": 5.942675159235669,
"grad_norm": 0.39789591608124625,
"learning_rate": 1.2685928275910142e-06,
"loss": 0.0669,
"step": 311
},
{
"epoch": 5.961783439490446,
"grad_norm": 0.46238384001020055,
"learning_rate": 1.222163882436107e-06,
"loss": 0.0626,
"step": 312
},
{
"epoch": 5.980891719745223,
"grad_norm": 0.41303332492968153,
"learning_rate": 1.1765451300597574e-06,
"loss": 0.0892,
"step": 313
},
{
"epoch": 6.0,
"grad_norm": 0.3770562669073382,
"learning_rate": 1.1317407810650372e-06,
"loss": 0.0607,
"step": 314
},
{
"epoch": 6.019108280254777,
"grad_norm": 0.272426829181539,
"learning_rate": 1.0877549708857228e-06,
"loss": 0.0678,
"step": 315
},
{
"epoch": 6.038216560509555,
"grad_norm": 0.269954454426176,
"learning_rate": 1.0445917594046073e-06,
"loss": 0.0627,
"step": 316
},
{
"epoch": 6.057324840764331,
"grad_norm": 0.3003403674449553,
"learning_rate": 1.0022551305787564e-06,
"loss": 0.0494,
"step": 317
},
{
"epoch": 6.076433121019108,
"grad_norm": 0.2966586294718324,
"learning_rate": 9.607489920717983e-07,
"loss": 0.0949,
"step": 318
},
{
"epoch": 6.095541401273885,
"grad_norm": 0.2919665902100848,
"learning_rate": 9.200771748932513e-07,
"loss": 0.1041,
"step": 319
},
{
"epoch": 6.114649681528663,
"grad_norm": 0.28482433883332764,
"learning_rate": 8.802434330449128e-07,
"loss": 0.0698,
"step": 320
},
{
"epoch": 6.13375796178344,
"grad_norm": 0.29065813094699533,
"learning_rate": 8.412514431743657e-07,
"loss": 0.0698,
"step": 321
},
{
"epoch": 6.1528662420382165,
"grad_norm": 0.3231834141577625,
"learning_rate": 8.031048042356393e-07,
"loss": 0.0846,
"step": 322
},
{
"epoch": 6.171974522292993,
"grad_norm": 0.2949302797499998,
"learning_rate": 7.65807037157007e-07,
"loss": 0.0708,
"step": 323
},
{
"epoch": 6.191082802547771,
"grad_norm": 0.2902725445633967,
"learning_rate": 7.293615845160196e-07,
"loss": 0.0672,
"step": 324
},
{
"epoch": 6.210191082802548,
"grad_norm": 0.28620474425555903,
"learning_rate": 6.937718102217461e-07,
"loss": 0.0847,
"step": 325
},
{
"epoch": 6.229299363057325,
"grad_norm": 0.2655524610396661,
"learning_rate": 6.590409992042957e-07,
"loss": 0.0586,
"step": 326
},
{
"epoch": 6.248407643312102,
"grad_norm": 0.2825516847146469,
"learning_rate": 6.251723571116031e-07,
"loss": 0.0737,
"step": 327
},
{
"epoch": 6.267515923566879,
"grad_norm": 0.2728625024671345,
"learning_rate": 5.921690100135713e-07,
"loss": 0.061,
"step": 328
},
{
"epoch": 6.286624203821656,
"grad_norm": 0.26716342873087257,
"learning_rate": 5.600340041135133e-07,
"loss": 0.0654,
"step": 329
},
{
"epoch": 6.305732484076433,
"grad_norm": 0.3370958532154618,
"learning_rate": 5.287703054670012e-07,
"loss": 0.115,
"step": 330
},
{
"epoch": 6.32484076433121,
"grad_norm": 0.28827532695871755,
"learning_rate": 4.983807997080925e-07,
"loss": 0.0672,
"step": 331
},
{
"epoch": 6.343949044585988,
"grad_norm": 0.31630942692758224,
"learning_rate": 4.6886829178299676e-07,
"loss": 0.0755,
"step": 332
},
{
"epoch": 6.3630573248407645,
"grad_norm": 0.29665281820775447,
"learning_rate": 4.402355056911656e-07,
"loss": 0.0634,
"step": 333
},
{
"epoch": 6.382165605095541,
"grad_norm": 0.2853111456175537,
"learning_rate": 4.124850842338779e-07,
"loss": 0.0652,
"step": 334
},
{
"epoch": 6.401273885350318,
"grad_norm": 0.268449628624925,
"learning_rate": 3.8561958877030957e-07,
"loss": 0.0532,
"step": 335
},
{
"epoch": 6.420382165605096,
"grad_norm": 0.27983344118352355,
"learning_rate": 3.5964149898111587e-07,
"loss": 0.0426,
"step": 336
},
{
"epoch": 6.439490445859873,
"grad_norm": 0.3060643682948817,
"learning_rate": 3.345532126395579e-07,
"loss": 0.0932,
"step": 337
},
{
"epoch": 6.45859872611465,
"grad_norm": 0.27201807551747703,
"learning_rate": 3.1035704539019384e-07,
"loss": 0.0595,
"step": 338
},
{
"epoch": 6.477707006369426,
"grad_norm": 0.26756794456829175,
"learning_rate": 2.870552305351382e-07,
"loss": 0.0758,
"step": 339
},
{
"epoch": 6.496815286624204,
"grad_norm": 0.28201972789789587,
"learning_rate": 2.646499188279328e-07,
"loss": 0.0668,
"step": 340
},
{
"epoch": 6.515923566878981,
"grad_norm": 0.2980403873708406,
"learning_rate": 2.4314317827503375e-07,
"loss": 0.0743,
"step": 341
},
{
"epoch": 6.535031847133758,
"grad_norm": 0.2651477141587895,
"learning_rate": 2.2253699394493066e-07,
"loss": 0.0449,
"step": 342
},
{
"epoch": 6.554140127388535,
"grad_norm": 0.30345561025935347,
"learning_rate": 2.028332677849254e-07,
"loss": 0.077,
"step": 343
},
{
"epoch": 6.573248407643312,
"grad_norm": 0.2906970002565656,
"learning_rate": 1.840338184455881e-07,
"loss": 0.0824,
"step": 344
},
{
"epoch": 6.592356687898089,
"grad_norm": 0.24346921023831067,
"learning_rate": 1.6614038111289034e-07,
"loss": 0.0461,
"step": 345
},
{
"epoch": 6.611464968152866,
"grad_norm": 0.2858491763288342,
"learning_rate": 1.49154607348051e-07,
"loss": 0.0749,
"step": 346
},
{
"epoch": 6.630573248407643,
"grad_norm": 0.33936195518059825,
"learning_rate": 1.330780649350938e-07,
"loss": 0.0743,
"step": 347
},
{
"epoch": 6.649681528662421,
"grad_norm": 0.31972369564639225,
"learning_rate": 1.1791223773614635e-07,
"loss": 0.0809,
"step": 348
},
{
"epoch": 6.6687898089171975,
"grad_norm": 0.2538217909225657,
"learning_rate": 1.0365852555447642e-07,
"loss": 0.0413,
"step": 349
},
{
"epoch": 6.687898089171974,
"grad_norm": 0.25490331468770727,
"learning_rate": 9.031824400528854e-08,
"loss": 0.0552,
"step": 350
},
{
"epoch": 6.707006369426751,
"grad_norm": 0.2760373792657459,
"learning_rate": 7.789262439430012e-08,
"loss": 0.0827,
"step": 351
},
{
"epoch": 6.726114649681529,
"grad_norm": 0.22765815548854168,
"learning_rate": 6.638281360408339e-08,
"loss": 0.0367,
"step": 352
},
{
"epoch": 6.745222929936306,
"grad_norm": 0.3282183977270304,
"learning_rate": 5.578987398821345e-08,
"loss": 0.0711,
"step": 353
},
{
"epoch": 6.764331210191083,
"grad_norm": 0.25052516066266456,
"learning_rate": 4.6114783273213395e-08,
"loss": 0.0581,
"step": 354
},
{
"epoch": 6.7834394904458595,
"grad_norm": 0.29962769715666265,
"learning_rate": 3.735843446830867e-08,
"loss": 0.0836,
"step": 355
},
{
"epoch": 6.802547770700637,
"grad_norm": 0.2869938989717563,
"learning_rate": 2.9521635783001932e-08,
"loss": 0.0706,
"step": 356
},
{
"epoch": 6.821656050955414,
"grad_norm": 0.27576347274162744,
"learning_rate": 2.2605110552477162e-08,
"loss": 0.073,
"step": 357
},
{
"epoch": 6.840764331210191,
"grad_norm": 0.26560170917028647,
"learning_rate": 1.6609497170834154e-08,
"loss": 0.0539,
"step": 358
},
{
"epoch": 6.859872611464969,
"grad_norm": 0.3020008036757105,
"learning_rate": 1.1535349032167908e-08,
"loss": 0.0621,
"step": 359
},
{
"epoch": 6.8789808917197455,
"grad_norm": 0.2527492475352435,
"learning_rate": 7.3831344794872415e-09,
"loss": 0.0518,
"step": 360
},
{
"epoch": 6.898089171974522,
"grad_norm": 0.24543537904631924,
"learning_rate": 4.153236761488266e-09,
"loss": 0.0576,
"step": 361
},
{
"epoch": 6.917197452229299,
"grad_norm": 0.3026674348438263,
"learning_rate": 1.8459539971804608e-09,
"loss": 0.0688,
"step": 362
},
{
"epoch": 6.936305732484076,
"grad_norm": 0.2910639101055271,
"learning_rate": 4.614991483686826e-10,
"loss": 0.0633,
"step": 363
},
{
"epoch": 6.955414012738854,
"grad_norm": 0.24760222696562117,
"learning_rate": 0.0,
"loss": 0.0559,
"step": 364
},
{
"epoch": 6.955414012738854,
"step": 364,
"total_flos": 8.423791610395853e+16,
"train_loss": 0.340403069547572,
"train_runtime": 2690.5724,
"train_samples_per_second": 13.008,
"train_steps_per_second": 0.135
}
],
"logging_steps": 1,
"max_steps": 364,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"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": 8.423791610395853e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}