prxy5606's picture
Training in progress, step 200, checkpoint
baccdca verified
{
"best_metric": 1.6998058557510376,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.013250517598343685,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.625258799171843e-05,
"grad_norm": 0.16042087972164154,
"learning_rate": 1e-05,
"loss": 1.8028,
"step": 1
},
{
"epoch": 6.625258799171843e-05,
"eval_loss": 1.9379690885543823,
"eval_runtime": 439.528,
"eval_samples_per_second": 57.837,
"eval_steps_per_second": 14.461,
"step": 1
},
{
"epoch": 0.00013250517598343685,
"grad_norm": 0.314959853887558,
"learning_rate": 2e-05,
"loss": 1.7479,
"step": 2
},
{
"epoch": 0.00019875776397515528,
"grad_norm": 0.35511142015457153,
"learning_rate": 3e-05,
"loss": 1.8897,
"step": 3
},
{
"epoch": 0.0002650103519668737,
"grad_norm": 0.38213640451431274,
"learning_rate": 4e-05,
"loss": 1.9621,
"step": 4
},
{
"epoch": 0.0003312629399585921,
"grad_norm": 0.2832004427909851,
"learning_rate": 5e-05,
"loss": 1.9791,
"step": 5
},
{
"epoch": 0.00039751552795031056,
"grad_norm": 0.20917236804962158,
"learning_rate": 6e-05,
"loss": 1.8685,
"step": 6
},
{
"epoch": 0.00046376811594202896,
"grad_norm": 0.17213356494903564,
"learning_rate": 7e-05,
"loss": 2.1435,
"step": 7
},
{
"epoch": 0.0005300207039337474,
"grad_norm": 0.20019783079624176,
"learning_rate": 8e-05,
"loss": 2.0554,
"step": 8
},
{
"epoch": 0.0005962732919254658,
"grad_norm": 0.2595132291316986,
"learning_rate": 9e-05,
"loss": 1.9319,
"step": 9
},
{
"epoch": 0.0006625258799171842,
"grad_norm": 0.24182064831256866,
"learning_rate": 0.0001,
"loss": 1.9353,
"step": 10
},
{
"epoch": 0.0007287784679089027,
"grad_norm": 0.25046980381011963,
"learning_rate": 9.999316524962345e-05,
"loss": 1.9686,
"step": 11
},
{
"epoch": 0.0007950310559006211,
"grad_norm": 0.28490978479385376,
"learning_rate": 9.997266286704631e-05,
"loss": 2.0723,
"step": 12
},
{
"epoch": 0.0008612836438923395,
"grad_norm": 0.2342705875635147,
"learning_rate": 9.993849845741524e-05,
"loss": 1.8186,
"step": 13
},
{
"epoch": 0.0009275362318840579,
"grad_norm": 0.24082574248313904,
"learning_rate": 9.989068136093873e-05,
"loss": 1.9644,
"step": 14
},
{
"epoch": 0.0009937888198757764,
"grad_norm": 0.18043313920497894,
"learning_rate": 9.98292246503335e-05,
"loss": 1.8168,
"step": 15
},
{
"epoch": 0.0010600414078674948,
"grad_norm": 0.14189937710762024,
"learning_rate": 9.975414512725057e-05,
"loss": 1.9482,
"step": 16
},
{
"epoch": 0.0011262939958592132,
"grad_norm": 0.1419694870710373,
"learning_rate": 9.966546331768191e-05,
"loss": 1.8871,
"step": 17
},
{
"epoch": 0.0011925465838509316,
"grad_norm": 0.14735981822013855,
"learning_rate": 9.956320346634876e-05,
"loss": 1.8349,
"step": 18
},
{
"epoch": 0.00125879917184265,
"grad_norm": 0.16133496165275574,
"learning_rate": 9.944739353007344e-05,
"loss": 2.0455,
"step": 19
},
{
"epoch": 0.0013250517598343684,
"grad_norm": 0.15721052885055542,
"learning_rate": 9.931806517013612e-05,
"loss": 1.9066,
"step": 20
},
{
"epoch": 0.001391304347826087,
"grad_norm": 0.1335712969303131,
"learning_rate": 9.917525374361912e-05,
"loss": 1.8125,
"step": 21
},
{
"epoch": 0.0014575569358178055,
"grad_norm": 0.13826707005500793,
"learning_rate": 9.901899829374047e-05,
"loss": 1.8878,
"step": 22
},
{
"epoch": 0.0015238095238095239,
"grad_norm": 0.1362507939338684,
"learning_rate": 9.884934153917997e-05,
"loss": 1.8247,
"step": 23
},
{
"epoch": 0.0015900621118012423,
"grad_norm": 0.1366121768951416,
"learning_rate": 9.86663298624003e-05,
"loss": 1.8805,
"step": 24
},
{
"epoch": 0.0016563146997929607,
"grad_norm": 0.13203640282154083,
"learning_rate": 9.847001329696653e-05,
"loss": 1.8078,
"step": 25
},
{
"epoch": 0.001722567287784679,
"grad_norm": 0.13456401228904724,
"learning_rate": 9.826044551386744e-05,
"loss": 1.825,
"step": 26
},
{
"epoch": 0.0017888198757763975,
"grad_norm": 0.12458786368370056,
"learning_rate": 9.803768380684242e-05,
"loss": 1.7352,
"step": 27
},
{
"epoch": 0.0018550724637681159,
"grad_norm": 0.13401219248771667,
"learning_rate": 9.780178907671789e-05,
"loss": 1.7095,
"step": 28
},
{
"epoch": 0.0019213250517598345,
"grad_norm": 0.12760014832019806,
"learning_rate": 9.755282581475769e-05,
"loss": 1.8146,
"step": 29
},
{
"epoch": 0.001987577639751553,
"grad_norm": 0.1324598789215088,
"learning_rate": 9.729086208503174e-05,
"loss": 1.7928,
"step": 30
},
{
"epoch": 0.0020538302277432713,
"grad_norm": 0.12801383435726166,
"learning_rate": 9.701596950580806e-05,
"loss": 1.8163,
"step": 31
},
{
"epoch": 0.0021200828157349897,
"grad_norm": 0.13068991899490356,
"learning_rate": 9.672822322997305e-05,
"loss": 1.73,
"step": 32
},
{
"epoch": 0.002186335403726708,
"grad_norm": 0.127804234623909,
"learning_rate": 9.642770192448536e-05,
"loss": 1.8329,
"step": 33
},
{
"epoch": 0.0022525879917184265,
"grad_norm": 0.12634919583797455,
"learning_rate": 9.611448774886924e-05,
"loss": 1.8243,
"step": 34
},
{
"epoch": 0.002318840579710145,
"grad_norm": 0.1265602856874466,
"learning_rate": 9.578866633275288e-05,
"loss": 1.736,
"step": 35
},
{
"epoch": 0.0023850931677018633,
"grad_norm": 0.12357663363218307,
"learning_rate": 9.545032675245813e-05,
"loss": 1.7224,
"step": 36
},
{
"epoch": 0.0024513457556935817,
"grad_norm": 0.1257162094116211,
"learning_rate": 9.509956150664796e-05,
"loss": 1.7733,
"step": 37
},
{
"epoch": 0.0025175983436853,
"grad_norm": 0.1298265904188156,
"learning_rate": 9.473646649103818e-05,
"loss": 1.7741,
"step": 38
},
{
"epoch": 0.0025838509316770185,
"grad_norm": 0.13071277737617493,
"learning_rate": 9.43611409721806e-05,
"loss": 1.7217,
"step": 39
},
{
"epoch": 0.002650103519668737,
"grad_norm": 0.1240500956773758,
"learning_rate": 9.397368756032445e-05,
"loss": 1.7252,
"step": 40
},
{
"epoch": 0.0027163561076604557,
"grad_norm": 0.12909509241580963,
"learning_rate": 9.357421218136386e-05,
"loss": 1.6969,
"step": 41
},
{
"epoch": 0.002782608695652174,
"grad_norm": 0.13177917897701263,
"learning_rate": 9.316282404787871e-05,
"loss": 1.6391,
"step": 42
},
{
"epoch": 0.0028488612836438925,
"grad_norm": 0.13090737164020538,
"learning_rate": 9.273963562927695e-05,
"loss": 1.7604,
"step": 43
},
{
"epoch": 0.002915113871635611,
"grad_norm": 0.13834311068058014,
"learning_rate": 9.230476262104677e-05,
"loss": 1.6368,
"step": 44
},
{
"epoch": 0.0029813664596273293,
"grad_norm": 0.12888137996196747,
"learning_rate": 9.185832391312644e-05,
"loss": 1.7527,
"step": 45
},
{
"epoch": 0.0030476190476190477,
"grad_norm": 0.13120168447494507,
"learning_rate": 9.140044155740101e-05,
"loss": 1.6432,
"step": 46
},
{
"epoch": 0.003113871635610766,
"grad_norm": 0.131545290350914,
"learning_rate": 9.093124073433463e-05,
"loss": 1.6279,
"step": 47
},
{
"epoch": 0.0031801242236024845,
"grad_norm": 0.15421217679977417,
"learning_rate": 9.045084971874738e-05,
"loss": 1.6294,
"step": 48
},
{
"epoch": 0.003246376811594203,
"grad_norm": 0.16506007313728333,
"learning_rate": 8.995939984474624e-05,
"loss": 1.483,
"step": 49
},
{
"epoch": 0.0033126293995859213,
"grad_norm": 0.28360575437545776,
"learning_rate": 8.945702546981969e-05,
"loss": 1.7182,
"step": 50
},
{
"epoch": 0.0033126293995859213,
"eval_loss": 1.7459650039672852,
"eval_runtime": 438.8594,
"eval_samples_per_second": 57.925,
"eval_steps_per_second": 14.483,
"step": 50
},
{
"epoch": 0.0033788819875776397,
"grad_norm": 0.12269020825624466,
"learning_rate": 8.894386393810563e-05,
"loss": 1.6164,
"step": 51
},
{
"epoch": 0.003445134575569358,
"grad_norm": 0.11564924567937851,
"learning_rate": 8.842005554284296e-05,
"loss": 1.6214,
"step": 52
},
{
"epoch": 0.0035113871635610765,
"grad_norm": 0.13417953252792358,
"learning_rate": 8.788574348801675e-05,
"loss": 1.8617,
"step": 53
},
{
"epoch": 0.003577639751552795,
"grad_norm": 0.12606605887413025,
"learning_rate": 8.73410738492077e-05,
"loss": 1.7873,
"step": 54
},
{
"epoch": 0.0036438923395445133,
"grad_norm": 0.13074903190135956,
"learning_rate": 8.678619553365659e-05,
"loss": 1.9241,
"step": 55
},
{
"epoch": 0.0037101449275362317,
"grad_norm": 0.130609929561615,
"learning_rate": 8.622126023955446e-05,
"loss": 1.7914,
"step": 56
},
{
"epoch": 0.00377639751552795,
"grad_norm": 0.12225651741027832,
"learning_rate": 8.564642241456986e-05,
"loss": 1.6789,
"step": 57
},
{
"epoch": 0.003842650103519669,
"grad_norm": 0.12554943561553955,
"learning_rate": 8.506183921362443e-05,
"loss": 1.9594,
"step": 58
},
{
"epoch": 0.003908902691511387,
"grad_norm": 0.12112361937761307,
"learning_rate": 8.44676704559283e-05,
"loss": 1.7804,
"step": 59
},
{
"epoch": 0.003975155279503106,
"grad_norm": 0.11467479914426804,
"learning_rate": 8.386407858128706e-05,
"loss": 1.7347,
"step": 60
},
{
"epoch": 0.004041407867494824,
"grad_norm": 0.11520858854055405,
"learning_rate": 8.32512286056924e-05,
"loss": 1.8907,
"step": 61
},
{
"epoch": 0.0041076604554865425,
"grad_norm": 0.12270911037921906,
"learning_rate": 8.262928807620843e-05,
"loss": 1.8863,
"step": 62
},
{
"epoch": 0.0041739130434782605,
"grad_norm": 0.12307147681713104,
"learning_rate": 8.199842702516583e-05,
"loss": 1.8144,
"step": 63
},
{
"epoch": 0.004240165631469979,
"grad_norm": 0.11784858256578445,
"learning_rate": 8.135881792367686e-05,
"loss": 1.757,
"step": 64
},
{
"epoch": 0.004306418219461697,
"grad_norm": 0.121355339884758,
"learning_rate": 8.07106356344834e-05,
"loss": 1.7827,
"step": 65
},
{
"epoch": 0.004372670807453416,
"grad_norm": 0.1163133755326271,
"learning_rate": 8.005405736415126e-05,
"loss": 1.7288,
"step": 66
},
{
"epoch": 0.004438923395445135,
"grad_norm": 0.11880005896091461,
"learning_rate": 7.938926261462366e-05,
"loss": 1.6676,
"step": 67
},
{
"epoch": 0.004505175983436853,
"grad_norm": 0.12593981623649597,
"learning_rate": 7.871643313414718e-05,
"loss": 1.7214,
"step": 68
},
{
"epoch": 0.004571428571428572,
"grad_norm": 0.13080726563930511,
"learning_rate": 7.803575286758364e-05,
"loss": 1.8356,
"step": 69
},
{
"epoch": 0.00463768115942029,
"grad_norm": 0.1192452535033226,
"learning_rate": 7.734740790612136e-05,
"loss": 1.7133,
"step": 70
},
{
"epoch": 0.004703933747412009,
"grad_norm": 0.11745153367519379,
"learning_rate": 7.66515864363997e-05,
"loss": 1.7411,
"step": 71
},
{
"epoch": 0.0047701863354037265,
"grad_norm": 0.11957097053527832,
"learning_rate": 7.594847868906076e-05,
"loss": 1.747,
"step": 72
},
{
"epoch": 0.004836438923395445,
"grad_norm": 0.12715786695480347,
"learning_rate": 7.52382768867422e-05,
"loss": 1.6503,
"step": 73
},
{
"epoch": 0.004902691511387163,
"grad_norm": 0.12206721305847168,
"learning_rate": 7.452117519152542e-05,
"loss": 1.6912,
"step": 74
},
{
"epoch": 0.004968944099378882,
"grad_norm": 0.1249401718378067,
"learning_rate": 7.379736965185368e-05,
"loss": 1.7007,
"step": 75
},
{
"epoch": 0.0050351966873706,
"grad_norm": 0.12385288625955582,
"learning_rate": 7.30670581489344e-05,
"loss": 1.7002,
"step": 76
},
{
"epoch": 0.005101449275362319,
"grad_norm": 0.11931055039167404,
"learning_rate": 7.233044034264034e-05,
"loss": 1.7467,
"step": 77
},
{
"epoch": 0.005167701863354037,
"grad_norm": 0.12408039718866348,
"learning_rate": 7.158771761692464e-05,
"loss": 1.6931,
"step": 78
},
{
"epoch": 0.005233954451345756,
"grad_norm": 0.1371099054813385,
"learning_rate": 7.083909302476453e-05,
"loss": 1.8054,
"step": 79
},
{
"epoch": 0.005300207039337474,
"grad_norm": 0.1325351744890213,
"learning_rate": 7.008477123264848e-05,
"loss": 1.8544,
"step": 80
},
{
"epoch": 0.005366459627329193,
"grad_norm": 0.11971048265695572,
"learning_rate": 6.932495846462261e-05,
"loss": 1.7795,
"step": 81
},
{
"epoch": 0.005432712215320911,
"grad_norm": 0.12251824140548706,
"learning_rate": 6.855986244591104e-05,
"loss": 1.6998,
"step": 82
},
{
"epoch": 0.005498964803312629,
"grad_norm": 0.1279759407043457,
"learning_rate": 6.778969234612584e-05,
"loss": 1.7439,
"step": 83
},
{
"epoch": 0.005565217391304348,
"grad_norm": 0.11900929361581802,
"learning_rate": 6.701465872208216e-05,
"loss": 1.738,
"step": 84
},
{
"epoch": 0.005631469979296066,
"grad_norm": 0.130741685628891,
"learning_rate": 6.623497346023418e-05,
"loss": 1.6418,
"step": 85
},
{
"epoch": 0.005697722567287785,
"grad_norm": 0.12592850625514984,
"learning_rate": 6.545084971874738e-05,
"loss": 1.7706,
"step": 86
},
{
"epoch": 0.005763975155279503,
"grad_norm": 0.12253115326166153,
"learning_rate": 6.466250186922325e-05,
"loss": 1.6958,
"step": 87
},
{
"epoch": 0.005830227743271222,
"grad_norm": 0.12557706236839294,
"learning_rate": 6.387014543809223e-05,
"loss": 1.6885,
"step": 88
},
{
"epoch": 0.00589648033126294,
"grad_norm": 0.1211329847574234,
"learning_rate": 6.307399704769099e-05,
"loss": 1.5654,
"step": 89
},
{
"epoch": 0.005962732919254659,
"grad_norm": 0.13277782499790192,
"learning_rate": 6.227427435703997e-05,
"loss": 1.8219,
"step": 90
},
{
"epoch": 0.006028985507246377,
"grad_norm": 0.1298239529132843,
"learning_rate": 6.147119600233758e-05,
"loss": 1.7668,
"step": 91
},
{
"epoch": 0.006095238095238095,
"grad_norm": 0.12896321713924408,
"learning_rate": 6.066498153718735e-05,
"loss": 1.6925,
"step": 92
},
{
"epoch": 0.006161490683229813,
"grad_norm": 0.14715975522994995,
"learning_rate": 5.985585137257401e-05,
"loss": 1.6136,
"step": 93
},
{
"epoch": 0.006227743271221532,
"grad_norm": 0.13328595459461212,
"learning_rate": 5.90440267166055e-05,
"loss": 1.6862,
"step": 94
},
{
"epoch": 0.00629399585921325,
"grad_norm": 0.1254388391971588,
"learning_rate": 5.8229729514036705e-05,
"loss": 1.7011,
"step": 95
},
{
"epoch": 0.006360248447204969,
"grad_norm": 0.137003093957901,
"learning_rate": 5.74131823855921e-05,
"loss": 1.6708,
"step": 96
},
{
"epoch": 0.006426501035196687,
"grad_norm": 0.14087547361850739,
"learning_rate": 5.6594608567103456e-05,
"loss": 1.6169,
"step": 97
},
{
"epoch": 0.006492753623188406,
"grad_norm": 0.14654134213924408,
"learning_rate": 5.577423184847932e-05,
"loss": 1.5996,
"step": 98
},
{
"epoch": 0.006559006211180125,
"grad_norm": 0.17681214213371277,
"learning_rate": 5.495227651252315e-05,
"loss": 1.5211,
"step": 99
},
{
"epoch": 0.006625258799171843,
"grad_norm": 0.30253973603248596,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.4522,
"step": 100
},
{
"epoch": 0.006625258799171843,
"eval_loss": 1.7128827571868896,
"eval_runtime": 439.3947,
"eval_samples_per_second": 57.855,
"eval_steps_per_second": 14.465,
"step": 100
},
{
"epoch": 0.0066915113871635614,
"grad_norm": 0.10286074876785278,
"learning_rate": 5.330452921628497e-05,
"loss": 1.6876,
"step": 101
},
{
"epoch": 0.006757763975155279,
"grad_norm": 0.1276087909936905,
"learning_rate": 5.247918773366112e-05,
"loss": 1.7571,
"step": 102
},
{
"epoch": 0.006824016563146998,
"grad_norm": 0.1294441670179367,
"learning_rate": 5.165316846586541e-05,
"loss": 1.6832,
"step": 103
},
{
"epoch": 0.006890269151138716,
"grad_norm": 0.1463458240032196,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.9144,
"step": 104
},
{
"epoch": 0.006956521739130435,
"grad_norm": 0.11742586642503738,
"learning_rate": 5e-05,
"loss": 1.881,
"step": 105
},
{
"epoch": 0.007022774327122153,
"grad_norm": 0.1266813427209854,
"learning_rate": 4.917330276168208e-05,
"loss": 1.7635,
"step": 106
},
{
"epoch": 0.007089026915113872,
"grad_norm": 0.12258177995681763,
"learning_rate": 4.834683153413459e-05,
"loss": 1.8283,
"step": 107
},
{
"epoch": 0.00715527950310559,
"grad_norm": 0.12947456538677216,
"learning_rate": 4.7520812266338885e-05,
"loss": 1.8947,
"step": 108
},
{
"epoch": 0.007221532091097309,
"grad_norm": 0.12223499268293381,
"learning_rate": 4.669547078371504e-05,
"loss": 1.8042,
"step": 109
},
{
"epoch": 0.007287784679089027,
"grad_norm": 0.1189243420958519,
"learning_rate": 4.5871032726383386e-05,
"loss": 1.9209,
"step": 110
},
{
"epoch": 0.0073540372670807454,
"grad_norm": 0.13120344281196594,
"learning_rate": 4.504772348747687e-05,
"loss": 1.8912,
"step": 111
},
{
"epoch": 0.007420289855072463,
"grad_norm": 0.12762673199176788,
"learning_rate": 4.4225768151520694e-05,
"loss": 1.8247,
"step": 112
},
{
"epoch": 0.007486542443064182,
"grad_norm": 0.12652021646499634,
"learning_rate": 4.3405391432896555e-05,
"loss": 1.7644,
"step": 113
},
{
"epoch": 0.0075527950310559,
"grad_norm": 0.12737470865249634,
"learning_rate": 4.2586817614407895e-05,
"loss": 1.8092,
"step": 114
},
{
"epoch": 0.007619047619047619,
"grad_norm": 0.12595722079277039,
"learning_rate": 4.17702704859633e-05,
"loss": 1.8327,
"step": 115
},
{
"epoch": 0.007685300207039338,
"grad_norm": 0.13216738402843475,
"learning_rate": 4.095597328339452e-05,
"loss": 1.7842,
"step": 116
},
{
"epoch": 0.007751552795031056,
"grad_norm": 0.11884083598852158,
"learning_rate": 4.0144148627425993e-05,
"loss": 1.755,
"step": 117
},
{
"epoch": 0.007817805383022774,
"grad_norm": 0.12388221174478531,
"learning_rate": 3.933501846281267e-05,
"loss": 1.8129,
"step": 118
},
{
"epoch": 0.007884057971014493,
"grad_norm": 0.127731591463089,
"learning_rate": 3.852880399766243e-05,
"loss": 1.6589,
"step": 119
},
{
"epoch": 0.007950310559006211,
"grad_norm": 0.12784713506698608,
"learning_rate": 3.772572564296005e-05,
"loss": 1.7914,
"step": 120
},
{
"epoch": 0.00801656314699793,
"grad_norm": 0.13297195732593536,
"learning_rate": 3.6926002952309016e-05,
"loss": 1.8241,
"step": 121
},
{
"epoch": 0.008082815734989647,
"grad_norm": 0.12336255609989166,
"learning_rate": 3.612985456190778e-05,
"loss": 1.6607,
"step": 122
},
{
"epoch": 0.008149068322981366,
"grad_norm": 0.1255303919315338,
"learning_rate": 3.533749813077677e-05,
"loss": 1.6559,
"step": 123
},
{
"epoch": 0.008215320910973085,
"grad_norm": 0.12798646092414856,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.7108,
"step": 124
},
{
"epoch": 0.008281573498964804,
"grad_norm": 0.1266174167394638,
"learning_rate": 3.3765026539765834e-05,
"loss": 1.7344,
"step": 125
},
{
"epoch": 0.008347826086956521,
"grad_norm": 0.12649928033351898,
"learning_rate": 3.298534127791785e-05,
"loss": 1.6957,
"step": 126
},
{
"epoch": 0.00841407867494824,
"grad_norm": 0.13522803783416748,
"learning_rate": 3.221030765387417e-05,
"loss": 1.6892,
"step": 127
},
{
"epoch": 0.008480331262939959,
"grad_norm": 0.14272339642047882,
"learning_rate": 3.144013755408895e-05,
"loss": 1.8254,
"step": 128
},
{
"epoch": 0.008546583850931678,
"grad_norm": 0.12243382632732391,
"learning_rate": 3.0675041535377405e-05,
"loss": 1.597,
"step": 129
},
{
"epoch": 0.008612836438923395,
"grad_norm": 0.1254020780324936,
"learning_rate": 2.991522876735154e-05,
"loss": 1.731,
"step": 130
},
{
"epoch": 0.008679089026915113,
"grad_norm": 0.12628696858882904,
"learning_rate": 2.916090697523549e-05,
"loss": 1.7534,
"step": 131
},
{
"epoch": 0.008745341614906832,
"grad_norm": 0.12439960241317749,
"learning_rate": 2.8412282383075363e-05,
"loss": 1.696,
"step": 132
},
{
"epoch": 0.008811594202898551,
"grad_norm": 0.12046002596616745,
"learning_rate": 2.766955965735968e-05,
"loss": 1.7372,
"step": 133
},
{
"epoch": 0.00887784679089027,
"grad_norm": 0.12436595559120178,
"learning_rate": 2.693294185106562e-05,
"loss": 1.6194,
"step": 134
},
{
"epoch": 0.008944099378881987,
"grad_norm": 0.1323857605457306,
"learning_rate": 2.6202630348146324e-05,
"loss": 1.6794,
"step": 135
},
{
"epoch": 0.009010351966873706,
"grad_norm": 0.13171963393688202,
"learning_rate": 2.547882480847461e-05,
"loss": 1.7782,
"step": 136
},
{
"epoch": 0.009076604554865425,
"grad_norm": 0.13648442924022675,
"learning_rate": 2.476172311325783e-05,
"loss": 1.7369,
"step": 137
},
{
"epoch": 0.009142857142857144,
"grad_norm": 0.14303649961948395,
"learning_rate": 2.405152131093926e-05,
"loss": 1.7502,
"step": 138
},
{
"epoch": 0.00920910973084886,
"grad_norm": 0.1271563470363617,
"learning_rate": 2.3348413563600325e-05,
"loss": 1.6775,
"step": 139
},
{
"epoch": 0.00927536231884058,
"grad_norm": 0.13029299676418304,
"learning_rate": 2.2652592093878666e-05,
"loss": 1.7709,
"step": 140
},
{
"epoch": 0.009341614906832298,
"grad_norm": 0.13401445746421814,
"learning_rate": 2.196424713241637e-05,
"loss": 1.6546,
"step": 141
},
{
"epoch": 0.009407867494824017,
"grad_norm": 0.1321835070848465,
"learning_rate": 2.128356686585282e-05,
"loss": 1.7146,
"step": 142
},
{
"epoch": 0.009474120082815734,
"grad_norm": 0.1340716928243637,
"learning_rate": 2.061073738537635e-05,
"loss": 1.7886,
"step": 143
},
{
"epoch": 0.009540372670807453,
"grad_norm": 0.1321353018283844,
"learning_rate": 1.9945942635848748e-05,
"loss": 1.7399,
"step": 144
},
{
"epoch": 0.009606625258799172,
"grad_norm": 0.1309817135334015,
"learning_rate": 1.928936436551661e-05,
"loss": 1.7183,
"step": 145
},
{
"epoch": 0.00967287784679089,
"grad_norm": 0.14503782987594604,
"learning_rate": 1.8641182076323148e-05,
"loss": 1.7645,
"step": 146
},
{
"epoch": 0.009739130434782608,
"grad_norm": 0.14578962326049805,
"learning_rate": 1.800157297483417e-05,
"loss": 1.6109,
"step": 147
},
{
"epoch": 0.009805383022774327,
"grad_norm": 0.15625157952308655,
"learning_rate": 1.7370711923791567e-05,
"loss": 1.524,
"step": 148
},
{
"epoch": 0.009871635610766046,
"grad_norm": 0.18671369552612305,
"learning_rate": 1.6748771394307585e-05,
"loss": 1.4527,
"step": 149
},
{
"epoch": 0.009937888198757764,
"grad_norm": 0.3633573651313782,
"learning_rate": 1.6135921418712956e-05,
"loss": 1.4227,
"step": 150
},
{
"epoch": 0.009937888198757764,
"eval_loss": 1.7021275758743286,
"eval_runtime": 439.8227,
"eval_samples_per_second": 57.798,
"eval_steps_per_second": 14.451,
"step": 150
},
{
"epoch": 0.010004140786749483,
"grad_norm": 0.10729548335075378,
"learning_rate": 1.553232954407171e-05,
"loss": 1.4979,
"step": 151
},
{
"epoch": 0.0100703933747412,
"grad_norm": 0.11312545835971832,
"learning_rate": 1.4938160786375572e-05,
"loss": 1.7936,
"step": 152
},
{
"epoch": 0.010136645962732919,
"grad_norm": 0.1266067922115326,
"learning_rate": 1.435357758543015e-05,
"loss": 1.7841,
"step": 153
},
{
"epoch": 0.010202898550724638,
"grad_norm": 0.11736242473125458,
"learning_rate": 1.3778739760445552e-05,
"loss": 1.7188,
"step": 154
},
{
"epoch": 0.010269151138716357,
"grad_norm": 0.1273820996284485,
"learning_rate": 1.3213804466343421e-05,
"loss": 1.8252,
"step": 155
},
{
"epoch": 0.010335403726708074,
"grad_norm": 0.13111338019371033,
"learning_rate": 1.2658926150792322e-05,
"loss": 1.6367,
"step": 156
},
{
"epoch": 0.010401656314699793,
"grad_norm": 0.12052463740110397,
"learning_rate": 1.2114256511983274e-05,
"loss": 1.7269,
"step": 157
},
{
"epoch": 0.010467908902691512,
"grad_norm": 0.1232714131474495,
"learning_rate": 1.157994445715706e-05,
"loss": 1.804,
"step": 158
},
{
"epoch": 0.01053416149068323,
"grad_norm": 0.11604554206132889,
"learning_rate": 1.1056136061894384e-05,
"loss": 1.6583,
"step": 159
},
{
"epoch": 0.010600414078674947,
"grad_norm": 0.12130093574523926,
"learning_rate": 1.0542974530180327e-05,
"loss": 1.6631,
"step": 160
},
{
"epoch": 0.010666666666666666,
"grad_norm": 0.12418082356452942,
"learning_rate": 1.0040600155253765e-05,
"loss": 1.7618,
"step": 161
},
{
"epoch": 0.010732919254658385,
"grad_norm": 0.12796759605407715,
"learning_rate": 9.549150281252633e-06,
"loss": 1.6703,
"step": 162
},
{
"epoch": 0.010799171842650104,
"grad_norm": 0.13356627523899078,
"learning_rate": 9.068759265665384e-06,
"loss": 1.8309,
"step": 163
},
{
"epoch": 0.010865424430641823,
"grad_norm": 0.12603557109832764,
"learning_rate": 8.599558442598998e-06,
"loss": 1.8709,
"step": 164
},
{
"epoch": 0.01093167701863354,
"grad_norm": 0.12487031519412994,
"learning_rate": 8.141676086873572e-06,
"loss": 1.6649,
"step": 165
},
{
"epoch": 0.010997929606625259,
"grad_norm": 0.12683650851249695,
"learning_rate": 7.695237378953223e-06,
"loss": 1.8663,
"step": 166
},
{
"epoch": 0.011064182194616978,
"grad_norm": 0.12115644663572311,
"learning_rate": 7.260364370723044e-06,
"loss": 1.7037,
"step": 167
},
{
"epoch": 0.011130434782608696,
"grad_norm": 0.12117600440979004,
"learning_rate": 6.837175952121306e-06,
"loss": 1.7597,
"step": 168
},
{
"epoch": 0.011196687370600414,
"grad_norm": 0.12432435154914856,
"learning_rate": 6.425787818636131e-06,
"loss": 1.6298,
"step": 169
},
{
"epoch": 0.011262939958592132,
"grad_norm": 0.12444484233856201,
"learning_rate": 6.026312439675552e-06,
"loss": 1.618,
"step": 170
},
{
"epoch": 0.011329192546583851,
"grad_norm": 0.12366094440221786,
"learning_rate": 5.6388590278194096e-06,
"loss": 1.6378,
"step": 171
},
{
"epoch": 0.01139544513457557,
"grad_norm": 0.12173435091972351,
"learning_rate": 5.263533508961827e-06,
"loss": 1.6687,
"step": 172
},
{
"epoch": 0.011461697722567287,
"grad_norm": 0.13134273886680603,
"learning_rate": 4.900438493352055e-06,
"loss": 1.7764,
"step": 173
},
{
"epoch": 0.011527950310559006,
"grad_norm": 0.12765035033226013,
"learning_rate": 4.549673247541875e-06,
"loss": 1.7224,
"step": 174
},
{
"epoch": 0.011594202898550725,
"grad_norm": 0.14251765608787537,
"learning_rate": 4.2113336672471245e-06,
"loss": 1.6037,
"step": 175
},
{
"epoch": 0.011660455486542444,
"grad_norm": 0.13152077794075012,
"learning_rate": 3.885512251130763e-06,
"loss": 1.7116,
"step": 176
},
{
"epoch": 0.01172670807453416,
"grad_norm": 0.12907034158706665,
"learning_rate": 3.5722980755146517e-06,
"loss": 1.6615,
"step": 177
},
{
"epoch": 0.01179296066252588,
"grad_norm": 0.12604530155658722,
"learning_rate": 3.271776770026963e-06,
"loss": 1.7437,
"step": 178
},
{
"epoch": 0.011859213250517598,
"grad_norm": 0.1284632831811905,
"learning_rate": 2.9840304941919415e-06,
"loss": 1.6218,
"step": 179
},
{
"epoch": 0.011925465838509317,
"grad_norm": 0.12516699731349945,
"learning_rate": 2.7091379149682685e-06,
"loss": 1.6682,
"step": 180
},
{
"epoch": 0.011991718426501036,
"grad_norm": 0.1341974288225174,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.6652,
"step": 181
},
{
"epoch": 0.012057971014492753,
"grad_norm": 0.1347489356994629,
"learning_rate": 2.1982109232821178e-06,
"loss": 1.7097,
"step": 182
},
{
"epoch": 0.012124223602484472,
"grad_norm": 0.12645584344863892,
"learning_rate": 1.962316193157593e-06,
"loss": 1.6848,
"step": 183
},
{
"epoch": 0.01219047619047619,
"grad_norm": 0.14024832844734192,
"learning_rate": 1.7395544861325718e-06,
"loss": 1.7295,
"step": 184
},
{
"epoch": 0.01225672877846791,
"grad_norm": 0.12278766930103302,
"learning_rate": 1.5299867030334814e-06,
"loss": 1.6852,
"step": 185
},
{
"epoch": 0.012322981366459627,
"grad_norm": 0.1317070722579956,
"learning_rate": 1.333670137599713e-06,
"loss": 1.7597,
"step": 186
},
{
"epoch": 0.012389233954451346,
"grad_norm": 0.13534079492092133,
"learning_rate": 1.1506584608200367e-06,
"loss": 1.7254,
"step": 187
},
{
"epoch": 0.012455486542443064,
"grad_norm": 0.1295829564332962,
"learning_rate": 9.810017062595322e-07,
"loss": 1.6592,
"step": 188
},
{
"epoch": 0.012521739130434783,
"grad_norm": 0.1378515362739563,
"learning_rate": 8.247462563808817e-07,
"loss": 1.6303,
"step": 189
},
{
"epoch": 0.0125879917184265,
"grad_norm": 0.13493184745311737,
"learning_rate": 6.819348298638839e-07,
"loss": 1.6417,
"step": 190
},
{
"epoch": 0.01265424430641822,
"grad_norm": 0.12714862823486328,
"learning_rate": 5.526064699265753e-07,
"loss": 1.6406,
"step": 191
},
{
"epoch": 0.012720496894409938,
"grad_norm": 0.1322127729654312,
"learning_rate": 4.367965336512403e-07,
"loss": 1.5815,
"step": 192
},
{
"epoch": 0.012786749482401657,
"grad_norm": 0.1372261494398117,
"learning_rate": 3.3453668231809286e-07,
"loss": 1.6885,
"step": 193
},
{
"epoch": 0.012853002070393374,
"grad_norm": 0.13817864656448364,
"learning_rate": 2.458548727494292e-07,
"loss": 1.7072,
"step": 194
},
{
"epoch": 0.012919254658385093,
"grad_norm": 0.14454637467861176,
"learning_rate": 1.7077534966650766e-07,
"loss": 1.5637,
"step": 195
},
{
"epoch": 0.012985507246376812,
"grad_norm": 0.141245499253273,
"learning_rate": 1.0931863906127327e-07,
"loss": 1.7511,
"step": 196
},
{
"epoch": 0.01305175983436853,
"grad_norm": 0.1369493454694748,
"learning_rate": 6.150154258476315e-08,
"loss": 1.6315,
"step": 197
},
{
"epoch": 0.01311801242236025,
"grad_norm": 0.15233369171619415,
"learning_rate": 2.7337132953697554e-08,
"loss": 1.479,
"step": 198
},
{
"epoch": 0.013184265010351966,
"grad_norm": 0.16971765458583832,
"learning_rate": 6.834750376549792e-09,
"loss": 1.6512,
"step": 199
},
{
"epoch": 0.013250517598343685,
"grad_norm": 0.26924997568130493,
"learning_rate": 0.0,
"loss": 1.3145,
"step": 200
},
{
"epoch": 0.013250517598343685,
"eval_loss": 1.6998058557510376,
"eval_runtime": 439.6685,
"eval_samples_per_second": 57.819,
"eval_steps_per_second": 14.456,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.380644787585024e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}